From bb77cd9855adff18de60a74d8a45dce964407099 Mon Sep 17 00:00:00 2001
From: CSH <40987381+csatsurnh@users.noreply.github.com>
Date: Mon, 6 Mar 2023 14:49:37 +0800
Subject: [PATCH 01/32] [Doc] Add zh_cn add_transforms doc (#2673)

as title
---
 docs/zh_cn/advanced_guides/add_transforms.md | 52 +++++++++++++++++++-
 1 file changed, 50 insertions(+), 2 deletions(-)

diff --git a/docs/zh_cn/advanced_guides/add_transforms.md b/docs/zh_cn/advanced_guides/add_transforms.md
index 58a2485e04..d7206680d3 100644
--- a/docs/zh_cn/advanced_guides/add_transforms.md
+++ b/docs/zh_cn/advanced_guides/add_transforms.md
@@ -1,3 +1,51 @@
-# 新增数据增强（待更新）
+# 新增数据增强
 
-中文版文档支持中，请先阅读[英文版本](../../en/advanced_guides/add_transform.md)
+## 自定义数据增强
+
+自定义数据增强必须继承 `BaseTransform` 并实现 `transform` 函数。这里我们使用一个简单的翻转变换作为示例：
+
+```python
+import random
+import mmcv
+from mmcv.transforms import BaseTransform, TRANSFORMS
+
+@TRANSFORMS.register_module()
+class MyFlip(BaseTransform):
+    def __init__(self, direction: str):
+        super().__init__()
+        self.direction = direction
+
+    def transform(self, results: dict) -> dict:
+        img = results['img']
+        results['img'] = mmcv.imflip(img, direction=self.direction)
+        return results
+```
+
+此外，新的类需要被导入。
+
+```python
+from .my_pipeline import MyFlip
+```
+
+这样，我们就可以实例化一个 `MyFlip` 对象并使用它来处理数据字典。
+
+```python
+import numpy as np
+
+transform = MyFlip(direction='horizontal')
+data_dict = {'img': np.random.rand(224, 224, 3)}
+data_dict = transform(data_dict)
+processed_img = data_dict['img']
+```
+
+或者，我们可以在配置文件中的数据流程中使用 `MyFlip` 变换。
+
+```python
+pipeline = [
+    ...
+    dict(type='MyFlip', direction='horizontal'),
+    ...
+]
+```
+
+需要注意，如果要在配置文件中使用 `MyFlip`，必须确保在运行时导入了包含 `MyFlip` 的文件。

From e541d1acd48cac67d9a71a1bcadba7cce3bb9c4e Mon Sep 17 00:00:00 2001
From: CSH <40987381+csatsurnh@users.noreply.github.com>
Date: Mon, 6 Mar 2023 18:03:12 +0800
Subject: [PATCH 02/32] [Doc] Add zh_cn add_models doc & fix link (#2702)

as title
---
 docs/en/advanced_guides/add_models.md    |   2 +-
 docs/zh_cn/advanced_guides/add_models.md | 261 ++++++++++++++++++++++-
 2 files changed, 260 insertions(+), 3 deletions(-)

diff --git a/docs/en/advanced_guides/add_models.md b/docs/en/advanced_guides/add_models.md
index 1f1969db39..e470e48ef2 100644
--- a/docs/en/advanced_guides/add_models.md
+++ b/docs/en/advanced_guides/add_models.md
@@ -202,7 +202,7 @@ In MMSegmentation 1.x versions, we use [SegDataPreProcessor](https://github.com/
 
 ## Develop new segmentors
 
-The segmentor is an algorithmic architecture in which users can customize their algorithms by adding customized components and defining the logic of algorithm execution. Please refer to [the model document](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/en/advanced_guides/models.md) for more details.
+The segmentor is an algorithmic architecture in which users can customize their algorithms by adding customized components and defining the logic of algorithm execution. Please refer to [the model document](./models.md) for more details.
 
 Since the [BaseSegmentor](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/models/segmentors/base.py#L15) in MMSegmentation unifies three modes for a forward process, to develop a new segmentor, users need to overwrite `loss`, `predict` and `_forward` methods corresponding to the `loss`, `predict` and `tensor` modes.
 
diff --git a/docs/zh_cn/advanced_guides/add_models.md b/docs/zh_cn/advanced_guides/add_models.md
index 3f86a0c7c6..2f0a5af0d1 100644
--- a/docs/zh_cn/advanced_guides/add_models.md
+++ b/docs/zh_cn/advanced_guides/add_models.md
@@ -1,3 +1,260 @@
-# 新增模块（待更新）
+# 新增模块
 
-中文版文档支持中，请先阅读[英文版本](../../en/advanced_guides/add_models.md)
+## 开发新组件
+
+我们可以自定义 [模型文档](./models.md) 中介绍的所有组件，例如**主干网络（backbone）**、**头（head）**、**损失函数（loss function）**和**数据预处理器（data preprocessor）**。
+
+### 添加新的主干网络（backbone）
+
+在这里，我们以 MobileNet 为例展示如何开发新的主干网络。
+
+1. 创建一个新文件 `mmseg/models/backbones/mobilenet.py`。
+
+   ```python
+   import torch.nn as nn
+
+   from mmseg.registry import MODELS
+
+
+   @MODELS.register_module()
+   class MobileNet(nn.Module):
+
+       def __init__(self, arg1, arg2):
+           pass
+
+       def forward(self, x):  # should return a tuple
+           pass
+
+       def init_weights(self, pretrained=None):
+           pass
+   ```
+
+2. 在 `mmseg/models/backbones/__init__.py` 中引入模块。
+
+   ```python
+   from .mobilenet import MobileNet
+   ```
+
+3. 在配置文件中使用它。
+
+   ```python
+   model = dict(
+       ...
+       backbone=dict(
+           type='MobileNet',
+           arg1=xxx,
+           arg2=xxx),
+       ...
+   ```
+
+### 添加新的头（head）
+
+在 MMSegmentation 中，我们提供 [BaseDecodeHead](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/models/decode_heads/decode_head.py#L17) 用于开发所有分割头。
+所有新实现的解码头都应该从中派生出来。
+接下来我们以 [PSPNet](https://arxiv.org/abs/1612.01105) 为例说明如何开发新的头。
+
+首先，在 `mmseg/models/decode_heads/psp_head.py` 中添加一个新的解码头。
+PSPNet 实现了用于分割解码的解码头。
+为了实现解码头，在新模块中我们需要执行以下三个函数。
+
+```python
+from mmseg.registry import MODELS
+
+@MODELS.register_module()
+class PSPHead(BaseDecodeHead):
+
+    def __init__(self, pool_scales=(1, 2, 3, 6), **kwargs):
+        super(PSPHead, self).__init__(**kwargs)
+
+    def init_weights(self):
+        pass
+
+    def forward(self, inputs):
+        pass
+```
+
+接下来，用户需要在 `mmseg/models/decode_heads/__init__.py` 中添加模块，这样相应的注册器就可以找到并加载它们。
+
+PSPNet 的配置文件如下
+
+```python
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    pretrained='pretrain_model/resnet50_v1c_trick-2cccc1ad.pth',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='PSPHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        pool_scales=(1, 2, 3, 6),
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)))
+
+```
+
+### 添加新的损失函数（loss）
+
+假设您想为分割解码添加一个叫做 `MyLoss` 的新的损失函数。
+要添加新的损失函数，用户需要在 `mmseg/models/loss/my_loss.py` 中实现它。
+修饰器 `weighted_loss` 可以对损失的每个元素进行加权。
+
+```python
+import torch
+import torch.nn as nn
+
+from mmseg.registry import MODELS
+from .utils import weighted_loss
+
+@weighted_loss
+def my_loss(pred, target):
+    assert pred.size() == target.size() and target.numel() > 0
+    loss = torch.abs(pred - target)
+    return loss
+
+@MODELS.register_module()
+class MyLoss(nn.Module):
+
+    def __init__(self, reduction='mean', loss_weight=1.0):
+        super(MyLoss, self).__init__()
+        self.reduction = reduction
+        self.loss_weight = loss_weight
+
+    def forward(self,
+                pred,
+                target,
+                weight=None,
+                avg_factor=None,
+                reduction_override=None):
+        assert reduction_override in (None, 'none', 'mean', 'sum')
+        reduction = (
+            reduction_override if reduction_override else self.reduction)
+        loss = self.loss_weight * my_loss(
+            pred, target, weight, reduction=reduction, avg_factor=avg_factor)
+        return loss
+```
+
+然后，用户需要将其添加到 `mmseg/models/loss/__init__.py` 中。
+
+```python
+from .my_loss import MyLoss, my_loss
+
+```
+
+要使用它，请修改 `loss_xx` 字段。
+然后需要修改头中的 `loss_decode` 字段。
+`loss_weight` 可用于平衡多重损失。
+
+```python
+loss_decode=dict(type='MyLoss', loss_weight=1.0))
+```
+
+### 添加新的数据预处理器（data preprocessor）
+
+在 MMSegmentation 1.x 版本中，我们使用 [SegDataPreProcessor](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/data_preprocessor.py#L13) 将数据复制到目标设备，并将数据预处理为默认的模型输入格式。这里我们将展示如何开发一个新的数据预处理器。
+
+1. 创建一个新文件 `mmseg/models/my_datapreprocessor.py`。
+
+   ```python
+   from mmengine.model import BaseDataPreprocessor
+
+   from mmseg.registry import MODELS
+
+   @MODELS.register_module()
+   class MyDataPreProcessor(BaseDataPreprocessor):
+       def __init__(self, **kwargs):
+           super().__init__(**kwargs)
+
+       def forward(self, data: dict, training: bool=False) -> Dict[str, Any]:
+           # TODO Define the logic for data pre-processing in the forward method
+           pass
+   ```
+
+2. 在 `mmseg/models/__init__.py` 中导入数据预处理器
+
+   ```python
+   from .my_datapreprocessor import MyDataPreProcessor
+   ```
+
+3. 在配置文件中使用它。
+
+   ```python
+   model = dict(
+       data_preprocessor=dict(type='MyDataPreProcessor)
+       ...
+   )
+   ```
+
+## 开发新的分割器（segmentor）
+
+分割器是一种户可以通过添加自定义组件和定义算法执行逻辑来自定义其算法的算法架构。请参考[模型文档](./models.md)了解更多详情。
+
+由于 MMSegmentation 中的 [BaseSegmenter](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/models/segmentors/base.py#L15) 统一了前向过程的三种模式，为了开发新的分割器，用户需要重写与 `loss`、`predict` 和 `tensor` 相对应的 `loss`、`predict` 和 `_forward` 方法。
+
+这里我们将展示如何开发一个新的分割器。
+
+1. 创建一个新文件 `mmseg/models/segmentors/my_segmentor.py`。
+
+   ```python
+    from typing import Dict, Optional, Union
+
+    import torch
+
+    from mmseg.registry import MODELS
+    from mmseg.models import BaseSegmentor
+
+    @MODELS.register_module()
+    class MySegmentor(BaseSegmentor):
+        def __init__(self, **kwargs):
+            super().__init__(**kwargs)
+            # TODO users should build components of the network here
+
+        def loss(self, inputs: Tensor, data_samples: SampleList) -> dict:
+            """Calculate losses from a batch of inputs and data samples."""
+            pass
+
+        def predict(self, inputs: Tensor, data_samples: OptSampleList=None) -> SampleList:
+            """Predict results from a batch of inputs and data samples with post-
+            processing."""
+            pass
+
+       def _forward(self,
+                 inputs: Tensor,
+                 data_samples: OptSampleList = None) -> Tuple[List[Tensor]]:
+            """Network forward process.
+
+            Usually includes backbone, neck and head forward without any post-
+            processing.
+            """
+            pass
+   ```
+
+2. 在 `mmseg/models/segmentors/__init__.py` 中导入分割器。
+
+   ```python
+   from .my_segmentor import MySegmentor
+   ```
+
+3. 在配置文件中使用它。
+
+   ```python
+   model = dict(
+       type='MySegmentor'
+       ...
+   )
+   ```

From 6c3599bd9dd7106de7b9167e5e5113e72e9ea435 Mon Sep 17 00:00:00 2001
From: CSH <40987381+csatsurnh@users.noreply.github.com>
Date: Tue, 7 Mar 2023 11:47:10 +0800
Subject: [PATCH 03/32] [Doc] Add zh_cn models doc and fix en doc typo (#2703)

as title

---------

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
---
 docs/en/advanced_guides/models.md    |  10 +-
 docs/zh_cn/advanced_guides/models.md | 176 ++++++++++++++++++++++++++-
 2 files changed, 179 insertions(+), 7 deletions(-)

diff --git a/docs/en/advanced_guides/models.md b/docs/en/advanced_guides/models.md
index 8202e95b7c..84e6cb6a9e 100644
--- a/docs/en/advanced_guides/models.md
+++ b/docs/en/advanced_guides/models.md
@@ -1,7 +1,5 @@
 # Models
 
-# Models
-
 We usually define a neural network in a deep learning task as a model, and this model is the core of an algorithm. [MMEngine](https://github.com/open-mmlab/mmengine) abstracts a unified model [BaseModel](https://github.com/open-mmlab/mmengine/blob/main/mmengine/model/base_model/base_model.py#L16) to standardize the interfaces for training, testing and other processes. All models implemented by MMSegmentation inherit from `BaseModel`, and in MMSegmentation we implemented forward and added some functions for the semantic segmentation algorithm.
 
 ## Common components
@@ -22,9 +20,9 @@ In MMSegmentation, we abstract the network architecture as a **Segmentor**, it i
 
 **Neck** is the part that connects the backbone and heads. It performs some refinements or reconfigurations on the raw feature maps produced by the backbone. An example is **Feature Pyramid Network (FPN)**.
 
-### Decode Head
+### Decode head
 
-**Decode Head** is the part that transforms the feature maps into a segmentation mask, such as **PSPNet**.
+**Decode head** is the part that transforms the feature maps into a segmentation mask, such as **PSPNet**.
 
 ### Auxiliary head
 
@@ -110,7 +108,7 @@ Parameters:
 - data (dict or tuple or list) - Data sampled from the dataset. In MMSegmentation, the data dict contains `inputs` and `data_samples` two fields.
 - optim_wrapper (OptimWrapper) - OptimWrapper instance used to update model parameters.
 
-**Note:** [OptimWrapper](https://github.com/open-mmlab/mmengine/blob/main/mmengine/optim/optimizer/optimizer_wrapper.py#L17) provides a common interface for updating parameters, please refer to optimizer wrapper [documentation](https://mmengine.readthedocs.io/zh_CN/latest/tutorials/optim_wrapper.html) in [MMEngine](https://github.com/open-mmlab/mmengine) for more information.
+**Note:** [OptimWrapper](https://github.com/open-mmlab/mmengine/blob/main/mmengine/optim/optimizer/optimizer_wrapper.py#L17) provides a common interface for updating parameters, please refer to optimizer wrapper [documentation](https://mmengine.readthedocs.io/en/latest/tutorials/optim_wrapper.html) in [MMEngine](https://github.com/open-mmlab/mmengine) for more information.
 
 Returns:
 
@@ -157,7 +155,7 @@ The parameters of the `SegDataPreProcessor` constructor:
 - pad_val (float, optional) - Padding value. Default: 0.
 - seg_pad_val (float, optional) - Padding value of segmentation map. Default: 255.
 - bgr_to_rgb (bool) - whether to convert image from BGR to RGB. Defaults to False.
-- rgb_to_bgr (bool) - whether to convert image from RGB to RGB. Defaults to False.
+- rgb_to_bgr (bool) - whether to convert image from RGB to BGR. Defaults to False.
 - batch_augments (list\[dict\], optional) - Batch-level augmentations. Default to None.
 
 The data will be processed as follows:
diff --git a/docs/zh_cn/advanced_guides/models.md b/docs/zh_cn/advanced_guides/models.md
index 62dbea38c4..408a57863c 100644
--- a/docs/zh_cn/advanced_guides/models.md
+++ b/docs/zh_cn/advanced_guides/models.md
@@ -1,3 +1,177 @@
 # 模型
 
-中文版文档支持中，请先阅读[英文版本](../../en/advanced_guides/models.md)
+我们通常将深度学习任务中的神经网络定义为模型，这个模型即是算法的核心。[MMEngine](https://github.com/open-mmlab/mmengine) 抽象出了一个统一模型 [BaseModel](https://github.com/open-mmlab/mmengine/blob/main/mmengine/model/base_model/base_model.py#L16) 以标准化训练、测试和其他过程。MMSegmentation 实现的所有模型都继承自 `BaseModel`，并且在 MMSegmention 中，我们实现了前向传播并为语义分割算法添加了一些功能。
+
+## 常用组件
+
+### 分割器（Segmentor）
+
+在 MMSegmentation 中，我们将网络架构抽象为**分割器**，它是一个包含网络所有组件的模型。我们已经实现了**编码器解码器（EncoderDecoder）**和**级联编码器解码器（CascadeEncoderDecoder）**，它们通常由**数据预处理器**、**骨干网络**、**解码头**和**辅助头**组成。
+
+### 数据预处理器（Data preprocessor）
+
+**数据预处理器**是将数据复制到目标设备并将数据预处理为模型输入格式的部分。
+
+### 主干网络（Backbone）
+
+**主干网络**是将图像转换为特征图的部分，例如没有最后全连接层的 **ResNet-50**。
+
+### 颈部（Neck）
+
+**颈部**是连接主干网络和头的部分。它对主干网络生成的原始特征图进行一些改进或重新配置。例如 **Feature Pyramid Network（FPN）**。
+
+### 解码头（Decode head）
+
+**解码头**是将特征图转换为分割掩膜的部分，例如 **PSPNet**。
+
+### 辅助头（Auxiliary head）
+
+**辅助头**是一个可选组件，它将特征图转换为仅用于计算辅助损失的分割掩膜。
+
+## 基本接口
+
+MMSegmentation 封装 `BaseModel` 并实现了 [BaseSegmenter](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/models/segmentors/base.py#L15) 类，主要提供 `forward`、`train_step`、`val_step` 和 `test_step` 接口。接下来将详细介绍这些接口。
+
+### forward
+
+<center>
+  <img src='../../../resources/encoder_decoder_dataflow.png' />
+  <center>编码器解码器数据流</center>
+</center>
+
+<center>
+  <center><img src='../../../resources/cascade_encoder_decoder_dataflow.png' /></center>
+  <center>级联编码器解码器数据流</center>
+</center>
+
+`forward` 方法返回训练、验证、测试和简单推理过程的损失或预测。
+
+该方法应接受三种模式：“tensor”、“predict” 和 “loss”：
+
+- “tensor”：前向推理整个网络并返回张量或张量数组，无需任何后处理，与常见的 `nn.Module` 相同。
+- “predict”：前向推理并返回预测值，这些预测值将被完全处理到 `SegDataSample` 列表中。
+- “loss”：前向推理并根据给定的输入和数据样本返回损失的`字典`。
+
+**注：**[SegDataSample](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/structures/seg_data_sample.py) 是 MMSegmentation 的数据结构接口，用作不同组件之间的接口。`SegDataSample` 实现了抽象数据元素 `mmengine.structures.BaseDataElement`，请参阅 [MMMEngine](https://github.com/open-mmlab/mmengine) 中的 [SegDataSample 文档](https://mmsegmentation.readthedocs.io/zh_CN/1.x/advanced_guides/structures.html)和[数据元素文档](https://mmengine.readthedocs.io/zh_CN/latest/advanced_tutorials/data_element.html)了解更多信息。
+
+注意，此方法不处理在 `train_step` 方法中完成的反向传播或优化器更新。
+
+参数：
+
+- inputs（torch.Tensor）- 通常为形状是（N, C, ...) 的输入张量。
+- data_sample（list\[[SegDataSample](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/structures/seg_data_sample.py)\]) - 分割数据样本。它通常包括 `metainfo` 和 `gt_sem_seg` 等信息。默认值为 None。
+- mode (str) - 返回什么类型的值。默认为 'tensor'。
+
+返回值：
+
+- `dict` 或 `list`：
+  - 如果 `mode == "loss"`，则返回用于反向过程和日志记录的损失张量`字典`。
+  - 如果 `mode == "predict"`，则返回 `SegDataSample` 的`列表`，推理结果将被递增地添加到传递给 forward 方法的 `data_sample` 参数中，每个 `SegDataSeample` 包含以下关键词：
+    - pred_sm_seg (`PixelData`)：语义分割的预测。
+    - seg_logits (`PixelData`)：标准化前语义分割的预测指标。
+  - 如果 `mode == "tensor"`，则返回`张量`或`张量数组`的`字典`以供自定义使用。
+
+### 预测模式
+
+我们在[配置文档](../user_guides/1_config.md)中简要描述了模型配置的字段，这里我们详细介绍 `model.test_cfg` 字段。`model.test_cfg` 用于控制前向行为，`"predict"` 模式下的 `forward` 方法可以在两种模式下运行：
+
+- `whole_inference`：如果 `cfg.model.test_cfg.mode == 'whole'`，则模型将使用完整图像进行推理。
+
+  `whole_inference` 模式的一个示例配置：
+
+  ```python
+  model = dict(
+    type='EncoderDecoder'
+    ...
+    test_cfg=dict(mode='whole')
+  )
+  ```
+
+- `slide_inference`：如果 `cfg.model.test_cfg.mode == ‘slide’`，则模型将通过滑动窗口进行推理。**注意：** 如果选择 `slide` 模式，还应指定 `cfg.model.test_cfg.stride` 和 `cfg.model.test_cfg.crop_size`。
+
+  `slide_inference` 模式的一个示例配置：
+
+  ```python
+  model = dict(
+    type='EncoderDecoder'
+    ...
+    test_cfg=dict(mode='slide', crop_size=256, stride=170)
+  )
+  ```
+
+### train_step
+
+`train_step` 方法调用 `loss` 模式的前向接口以获得损失`字典`。`BaseModel` 类实现默认的模型训练过程，包括预处理、模型前向传播、损失计算、优化和反向传播。
+
+参数：
+
+- data (dict or tuple or list) - 从数据集采样的数据。在 MMSegmentation 中，数据字典包含 `inputs` 和 `data_samples` 两个字段。
+- optim_wrapper (OptimWrapper) - 用于更新模型参数的 OptimWrapper 实例。
+
+**注：**[OptimWrapper](https://github.com/open-mmlab/mmengine/blob/main/mmengine/optim/optimizer/optimizer_wrapper.py#L17) 提供了一个用于更新参数的通用接口，请参阅 [MMMEngine](https://github.com/open-mmlab/mmengine) 中的优化器封装[文档](https://mmengine.readthedocs.io/zh_CN/latest/tutorials/optim_wrapper.html)了解更多信息。
+
+返回值：
+
+-Dict\[str, `torch.Tensor`\]：用于记录日志的张量的`字典`。
+
+<center>
+  <img src='../../../resources/train_step.png' />
+  <center>train_step 数据流</center>
+</center>
+
+### val_step
+
+`val_step` 方法调用 `predict` 模式的前向接口并返回预测结果，预测结果将进一步被传递给评测器的进程接口和钩子的 `after_val_inter` 接口。
+
+参数：
+
+- data (`dict` or `tuple` or `list`) - 从数据集中采样的数据。在 MMSegmentation 中，数据字典包含 `inputs` 和 `data_samples` 两个字段。
+
+返回值：
+
+- `list` - 给定数据的预测结果。
+
+<center>
+  <img src='../../../resources/test_step.png' />
+  <center>test_step/val_step 数据流</center>
+</center>
+
+### test_step
+
+`BaseModel` 中 `test_step` 与 `val_step` 的实现相同。
+
+## 数据预处理器（Data Preprocessor）
+
+MMSegmentation 实现的 [SegDataPreProcessor](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/models/data_preprocessor.py#L13) 继承自由 [MMEngine](https://github.com/open-mmlab/mmengine) 实现的 [BaseDataPreprocessor](https://github.com/open-mmlab/mmengine/blob/main/mmengine/model/base_model/data_preprocessor.py#L18)，提供数据预处理和将数据复制到目标设备的功能。
+
+Runner 在构建阶段将模型传送到指定的设备，而 [SegDataPreProcessor](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/models/data_preprocessor.py#L13) 在 `train_step`、`val_step` 和 `test_step` 中将数据传送到指定设备，之后处理后的数据将被进一步传递给模型。
+
+`SegDataPreProcessor` 构造函数的参数：
+
+- mean (Sequence\[Number\], 可选) - R、G、B 通道的像素平均值。默认为 None。
+- std (Sequence\[Number\], 可选) - R、G、B 通道的像素标准差。默认为 None。
+- size (tuple, 可选) - 固定的填充大小。
+- size_divisor (int, 可选) - 填充大小的除法因子。
+- pad_val (float, 可选) - 填充值。默认值：0。
+- seg_pad_val (float, 可选) - 分割图的填充值。默认值：255。
+- bgr_to_rgb (bool) - 是否将图像从 BGR 转换为 RGB。默认为 False。
+- rgb_to_bgr (bool) - 是否将图像从 RGB 转换为 BGR。默认为 False。
+- batch_augments (list\[dict\], 可选) - 批量化的数据增强。默认值为 None。
+
+数据将按如下方式处理：
+
+- 收集数据并将其移动到目标设备。
+- 用定义的 `pad_val` 将输入填充到输入大小，并用定义的 `seg_Pad_val` 填充分割图。
+- 将输入堆栈到 batch_input。
+- 如果输入的形状为 (3, H, W)，则将输入从 BGR 转换为 RGB。
+- 使用定义的标准差和平均值标准化图像。
+- 在训练期间进行如 Mixup 和 Cutmix 的批量化数据增强。
+
+`forward` 方法的参数：
+
+- data (dict) - 从数据加载器采样的数据。
+- training (bool) - 是否启用训练时数据增强。
+
+`forward` 方法的返回值：
+
+- Dict：与模型输入格式相同的数据。

From a8aafdd902b9fe73596fb4b8c03ec693416acf42 Mon Sep 17 00:00:00 2001
From: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
Date: Tue, 7 Mar 2023 17:57:37 +0800
Subject: [PATCH 04/32] [Fix] Support format_result and fix prefix param in
 cityscape metric, and rename CitysMetric to CityscapesMetric (#2660)

as title
---
 mmseg/evaluation/__init__.py                  |   4 +-
 mmseg/evaluation/metrics/__init__.py          |   4 +-
 mmseg/evaluation/metrics/citys_metric.py      | 116 ++++++++++--------
 .../test_metrics/test_citys_metric.py         |  44 ++++---
 4 files changed, 94 insertions(+), 74 deletions(-)

diff --git a/mmseg/evaluation/__init__.py b/mmseg/evaluation/__init__.py
index c28bb75cb4..a82008f3ad 100644
--- a/mmseg/evaluation/__init__.py
+++ b/mmseg/evaluation/__init__.py
@@ -1,4 +1,4 @@
 # Copyright (c) OpenMMLab. All rights reserved.
-from .metrics import CitysMetric, IoUMetric
+from .metrics import CityscapesMetric, IoUMetric
 
-__all__ = ['IoUMetric', 'CitysMetric']
+__all__ = ['IoUMetric', 'CityscapesMetric']
diff --git a/mmseg/evaluation/metrics/__init__.py b/mmseg/evaluation/metrics/__init__.py
index aec08bb071..0aa39e480c 100644
--- a/mmseg/evaluation/metrics/__init__.py
+++ b/mmseg/evaluation/metrics/__init__.py
@@ -1,5 +1,5 @@
 # Copyright (c) OpenMMLab. All rights reserved.
-from .citys_metric import CitysMetric
+from .citys_metric import CityscapesMetric
 from .iou_metric import IoUMetric
 
-__all__ = ['IoUMetric', 'CitysMetric']
+__all__ = ['IoUMetric', 'CityscapesMetric']
diff --git a/mmseg/evaluation/metrics/citys_metric.py b/mmseg/evaluation/metrics/citys_metric.py
index 50e9ea68a0..a2c008b99d 100644
--- a/mmseg/evaluation/metrics/citys_metric.py
+++ b/mmseg/evaluation/metrics/citys_metric.py
@@ -1,30 +1,41 @@
 # Copyright (c) OpenMMLab. All rights reserved.
 import os.path as osp
-from typing import Dict, List, Optional, Sequence
+import shutil
+from collections import OrderedDict
+from typing import Dict, Optional, Sequence
+
+try:
+
+    import cityscapesscripts.evaluation.evalPixelLevelSemanticLabeling as CSEval  # noqa
+    import cityscapesscripts.helpers.labels as CSLabels
+except ImportError:
+    CSLabels = None
+    CSEval = None
 
 import numpy as np
+from mmengine.dist import is_main_process, master_only
 from mmengine.evaluator import BaseMetric
 from mmengine.logging import MMLogger, print_log
-from mmengine.utils import mkdir_or_exist, scandir
+from mmengine.utils import mkdir_or_exist
 from PIL import Image
 
 from mmseg.registry import METRICS
 
 
 @METRICS.register_module()
-class CitysMetric(BaseMetric):
+class CityscapesMetric(BaseMetric):
     """Cityscapes evaluation metric.
 
     Args:
+        output_dir (str): The directory for output prediction
         ignore_index (int): Index that will be ignored in evaluation.
             Default: 255.
-        citys_metrics (list[str] | str): Metrics to be evaluated,
-            Default: ['cityscapes'].
-        to_label_id (bool): whether convert output to label_id for
-            submission. Default: True.
-        suffix (str): The filename prefix of the png files.
-            If the prefix is "somepath/xxx", the png files will be
-            named "somepath/xxx.png". Default: '.format_cityscapes'.
+        format_only (bool): Only format result for results commit without
+            perform evaluation. It is useful when you want to format the result
+            to a specific format and submit it to the test server.
+            Defaults to False.
+        keep_results (bool): Whether to keep the results. When ``format_only``
+            is True, ``keep_results`` must be True. Defaults to False.
         collect_device (str): Device name used for collecting results from
             different ranks during distributed training. Must be 'cpu' or
             'gpu'. Defaults to 'cpu'.
@@ -35,19 +46,34 @@ class CitysMetric(BaseMetric):
     """
 
     def __init__(self,
+                 output_dir: str,
                  ignore_index: int = 255,
-                 citys_metrics: List[str] = ['cityscapes'],
-                 to_label_id: bool = True,
-                 suffix: str = '.format_cityscapes',
+                 format_only: bool = False,
+                 keep_results: bool = False,
                  collect_device: str = 'cpu',
                  prefix: Optional[str] = None) -> None:
         super().__init__(collect_device=collect_device, prefix=prefix)
-
+        if CSEval is None:
+            raise ImportError('Please run "pip install cityscapesscripts" to '
+                              'install cityscapesscripts first.')
+        self.output_dir = output_dir
         self.ignore_index = ignore_index
-        self.metrics = citys_metrics
-        assert self.metrics[0] == 'cityscapes'
-        self.to_label_id = to_label_id
-        self.suffix = suffix
+
+        self.format_only = format_only
+        if format_only:
+            assert keep_results, (
+                'When format_only is True, the results must be keep, please '
+                f'set keep_results as True, but got {keep_results}')
+        self.keep_results = keep_results
+        self.prefix = prefix
+        if is_main_process():
+            mkdir_or_exist(self.output_dir)
+
+    @master_only
+    def __del__(self) -> None:
+        """Clean up."""
+        if not self.keep_results:
+            shutil.rmtree(self.output_dir)
 
     def process(self, data_batch: dict, data_samples: Sequence[dict]) -> None:
         """Process one batch of data and data_samples.
@@ -59,26 +85,23 @@ def process(self, data_batch: dict, data_samples: Sequence[dict]) -> None:
             data_batch (dict): A batch of data from the dataloader.
             data_samples (Sequence[dict]): A batch of outputs from the model.
         """
-        mkdir_or_exist(self.suffix)
+        mkdir_or_exist(self.output_dir)
 
         for data_sample in data_samples:
             pred_label = data_sample['pred_sem_seg']['data'][0].cpu().numpy()
-            # results2img
-            if self.to_label_id:
-                pred_label = self._convert_to_label_id(pred_label)
+            # when evaluating with official cityscapesscripts,
+            # labelIds should be used
+            pred_label = self._convert_to_label_id(pred_label)
             basename = osp.splitext(osp.basename(data_sample['img_path']))[0]
-            png_filename = osp.join(self.suffix, f'{basename}.png')
+            png_filename = osp.abspath(
+                osp.join(self.output_dir, f'{basename}.png'))
             output = Image.fromarray(pred_label.astype(np.uint8)).convert('P')
-            import cityscapesscripts.helpers.labels as CSLabels
-            palette = np.zeros((len(CSLabels.id2label), 3), dtype=np.uint8)
-            for label_id, label in CSLabels.id2label.items():
-                palette[label_id] = label.color
-            output.putpalette(palette)
             output.save(png_filename)
-
-        ann_dir = osp.join(data_samples[0]['seg_map_path'].split('val')[0],
-                           'val')
-        self.results.append(ann_dir)
+            # when evaluating with official cityscapesscripts,
+            # **_gtFine_labelIds.png is used
+            gt_filename = data_sample['seg_map_path'].replace(
+                'labelTrainIds.png', 'labelIds.png')
+            self.results.append((png_filename, gt_filename))
 
     def compute_metrics(self, results: list) -> Dict[str, float]:
         """Compute the metrics from processed results.
@@ -90,38 +113,28 @@ def compute_metrics(self, results: list) -> Dict[str, float]:
             dict[str: float]: Cityscapes evaluation results.
         """
         logger: MMLogger = MMLogger.get_current_instance()
-        try:
-            import cityscapesscripts.evaluation.evalPixelLevelSemanticLabeling as CSEval  # noqa
-        except ImportError:
-            raise ImportError('Please run "pip install cityscapesscripts" to '
-                              'install cityscapesscripts first.')
-        msg = 'Evaluating in Cityscapes style'
+        if self.format_only:
+            logger.info(f'results are saved to {osp.dirname(self.output_dir)}')
+            return OrderedDict()
 
+        msg = 'Evaluating in Cityscapes style'
         if logger is None:
             msg = '\n' + msg
         print_log(msg, logger=logger)
 
-        result_dir = self.suffix
-
         eval_results = dict()
-        print_log(f'Evaluating results under {result_dir} ...', logger=logger)
+        print_log(
+            f'Evaluating results under {self.output_dir} ...', logger=logger)
 
         CSEval.args.evalInstLevelScore = True
-        CSEval.args.predictionPath = osp.abspath(result_dir)
+        CSEval.args.predictionPath = osp.abspath(self.output_dir)
         CSEval.args.evalPixelAccuracy = True
         CSEval.args.JSONOutput = False
 
-        seg_map_list = []
-        pred_list = []
-        ann_dir = results[0]
-        # when evaluating with official cityscapesscripts,
-        # **_gtFine_labelIds.png is used
-        for seg_map in scandir(ann_dir, 'gtFine_labelIds.png', recursive=True):
-            seg_map_list.append(osp.join(ann_dir, seg_map))
-            pred_list.append(CSEval.getPrediction(CSEval.args, seg_map))
+        pred_list, gt_list = zip(*results)
         metric = dict()
         eval_results.update(
-            CSEval.evaluateImgLists(pred_list, seg_map_list, CSEval.args))
+            CSEval.evaluateImgLists(pred_list, gt_list, CSEval.args))
         metric['averageScoreCategories'] = eval_results[
             'averageScoreCategories']
         metric['averageScoreInstCategories'] = eval_results[
@@ -133,7 +146,6 @@ def _convert_to_label_id(result):
         """Convert trainId to id for cityscapes."""
         if isinstance(result, str):
             result = np.load(result)
-        import cityscapesscripts.helpers.labels as CSLabels
         result_copy = result.copy()
         for trainId, label in CSLabels.trainId2label.items():
             result_copy[result == trainId] = label.id
diff --git a/tests/test_evaluation/test_metrics/test_citys_metric.py b/tests/test_evaluation/test_metrics/test_citys_metric.py
index a6d6db5caa..0a20b41aee 100644
--- a/tests/test_evaluation/test_metrics/test_citys_metric.py
+++ b/tests/test_evaluation/test_metrics/test_citys_metric.py
@@ -1,15 +1,17 @@
 # Copyright (c) OpenMMLab. All rights reserved.
+import os.path as osp
 from unittest import TestCase
 
 import numpy as np
+import pytest
 import torch
 from mmengine.structures import BaseDataElement, PixelData
 
-from mmseg.evaluation import CitysMetric
+from mmseg.evaluation import CityscapesMetric
 from mmseg.structures import SegDataSample
 
 
-class TestCitysMetric(TestCase):
+class TestCityscapesMetric(TestCase):
 
     def _demo_mm_inputs(self,
                         batch_size=1,
@@ -42,9 +44,8 @@ def _demo_mm_inputs(self,
             gt_sem_seg_data = dict(data=gt_semantic_seg)
             data_sample.gt_sem_seg = PixelData(**gt_sem_seg_data)
             mm_inputs['data_sample'] = data_sample.to_dict()
-            mm_inputs['data_sample']['seg_map_path'] = \
-                'tests/data/pseudo_cityscapes_dataset/gtFine/val/\
-                    frankfurt/frankfurt_000000_000294_gtFine_labelTrainIds.png'
+            mm_inputs['data_sample'][
+                'seg_map_path'] = 'tests/data/pseudo_cityscapes_dataset/gtFine/val/frankfurt/frankfurt_000000_000294_gtFine_labelTrainIds.png'  # noqa
 
             mm_inputs['seg_map_path'] = mm_inputs['data_sample'][
                 'seg_map_path']
@@ -86,9 +87,8 @@ def _demo_mm_model_output(self,
         for pred in batch_datasampes:
             if isinstance(pred, BaseDataElement):
                 test_data = pred.to_dict()
-                test_data['img_path'] = \
-                    'tests/data/pseudo_cityscapes_dataset/leftImg8bit/val/\
-                        frankfurt/frankfurt_000000_000294_leftImg8bit.png'
+                test_data[
+                    'img_path'] = 'tests/data/pseudo_cityscapes_dataset/leftImg8bit/val/frankfurt/frankfurt_000000_000294_leftImg8bit.png'  # noqa
 
                 _predictions.append(test_data)
             else:
@@ -104,15 +104,23 @@ def test_evaluate(self):
             dict(**data, **result)
             for data, result in zip(data_batch, predictions)
         ]
-        iou_metric = CitysMetric(citys_metrics=['cityscapes'])
-        iou_metric.process(data_batch, data_samples)
-        res = iou_metric.evaluate(6)
-        self.assertIsInstance(res, dict)
-        # test to_label_id = True
-        iou_metric = CitysMetric(
-            citys_metrics=['cityscapes'], to_label_id=True)
-        iou_metric.process(data_batch, data_samples)
-        res = iou_metric.evaluate(6)
+        # test keep_results should be True when format_only is True
+        with pytest.raises(AssertionError):
+            CityscapesMetric(
+                output_dir='tmp', format_only=True, keep_results=False)
+
+        # test evaluate with cityscape metric
+        metric = CityscapesMetric(output_dir='tmp')
+        metric.process(data_batch, data_samples)
+        res = metric.evaluate(2)
         self.assertIsInstance(res, dict)
+
+        # test format_only
+        metric = CityscapesMetric(
+            output_dir='tmp', format_only=True, keep_results=True)
+        metric.process(data_batch, data_samples)
+        metric.evaluate(2)
+        assert osp.exists('tmp')
+        assert osp.isfile('tmp/frankfurt_000000_000294_leftImg8bit.png')
         import shutil
-        shutil.rmtree('.format_cityscapes')
+        shutil.rmtree('tmp')

From 91c62abcf44528f007ffa220af8873499790337d Mon Sep 17 00:00:00 2001
From: MengzhangLI <mcmong@pku.edu.cn>
Date: Tue, 7 Mar 2023 21:21:01 +0800
Subject: [PATCH 05/32] [Fix] Fix the correct location of FAQ in dev-1.x
 (#2717)

---
 docs/en/get_started.md    | 2 +-
 docs/zh_cn/get_started.md | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/docs/en/get_started.md b/docs/en/get_started.md
index cf861b1fe8..b082508693 100644
--- a/docs/en/get_started.md
+++ b/docs/en/get_started.md
@@ -197,5 +197,5 @@ docker run --gpus all --shm-size=8g -it -v {DATA_DIR}:/mmsegmentation/data mmseg
 
 ## Trouble shooting
 
-If you have some issues during the installation, please first view the [FAQ](faq.md) page.
+If you have some issues during the installation, please first view the [FAQ](notes/faq.md) page.
 You may [open an issue](https://github.com/open-mmlab/mmsegmentation/issues/new/choose) on GitHub if no solution is found.
diff --git a/docs/zh_cn/get_started.md b/docs/zh_cn/get_started.md
index da6d728a15..38e93e9cb4 100644
--- a/docs/zh_cn/get_started.md
+++ b/docs/zh_cn/get_started.md
@@ -197,4 +197,4 @@ docker run --gpus all --shm-size=8g -it -v {DATA_DIR}:/mmsegmentation/data mmseg
 
 ## 问题解答
 
-如果您在安装过程中遇到了其他问题，请第一时间查阅 [FAQ](faq.md) 文件。如果没有找到答案，您也可以在 GitHub 上提出 [issue](https://github.com/open-mmlab/mmsegmentation/issues/new/choose)
+如果您在安装过程中遇到了其他问题，请第一时间查阅 [FAQ](notes/faq.md) 文件。如果没有找到答案，您也可以在 GitHub 上提出 [issue](https://github.com/open-mmlab/mmsegmentation/issues/new/choose)

From 7e41b5af8d769b6b4e0aa95943068b25ef7e3c75 Mon Sep 17 00:00:00 2001
From: jinxianwei <81373517+jinxianwei@users.noreply.github.com>
Date: Tue, 7 Mar 2023 21:23:04 +0800
Subject: [PATCH 06/32] en doc of uisualization_feature_map.md (#2715)

## Motivation

En doc for visualization_feature_map.md and index.rst

## Modification

Add new file and change index.rst
---
 docs/en/user_guides/index.rst                 |   1 +
 .../user_guides/visualization_feature_map.md  | 201 ++++++++++++++++++
 2 files changed, 202 insertions(+)
 create mode 100644 docs/en/user_guides/visualization_feature_map.md

diff --git a/docs/en/user_guides/index.rst b/docs/en/user_guides/index.rst
index 9e7d365925..1feb1271ae 100644
--- a/docs/en/user_guides/index.rst
+++ b/docs/en/user_guides/index.rst
@@ -18,3 +18,4 @@ Useful Tools
    visualization.md
    useful_tools.md
    deployment.md
+   visualization_feature_map.md
diff --git a/docs/en/user_guides/visualization_feature_map.md b/docs/en/user_guides/visualization_feature_map.md
new file mode 100644
index 0000000000..d61226f055
--- /dev/null
+++ b/docs/en/user_guides/visualization_feature_map.md
@@ -0,0 +1,201 @@
+# Wandb Feature Map Visualization
+
+MMSegmentation 1.x provides backend support for Weights & Biases to facilitate visualization and management of project code results.
+
+## Wandb Configuration
+
+Install Weights & Biases following [official instructions](https://docs.wandb.ai/quickstart) e.g.
+
+```shell
+pip install wandb
+wandb login
+```
+
+Add `WandbVisBackend` in `vis_backend` of `visualizer` in `default_runtime.py` config file:
+
+```python
+vis_backends=[dict(type='LocalVisBackend'),
+              dict(type='TensorboardVisBackend'),
+              dict(type='WandbVisBackend')]
+```
+
+## Examining feature map visualization in Wandb
+
+`SegLocalVisualizer` is child class inherits from `Visualizer` in MMEngine and works for MMSegmentation visualization, for more details about `Visualizer` please refer to [visualization tutorial](https://github.com/open-mmlab/mmengine/blob/main/docs/en/advanced_tutorials/visualization.md) in MMEngine.
+
+Here is an example about `SegLocalVisualizer`, first you may download example data below by following commands:
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/24582831/189833109-eddad58f-f777-4fc0-b98a-6bd429143b06.png" width="70%"/>
+</div>
+
+```shell
+wget https://user-images.githubusercontent.com/24582831/189833109-eddad58f-f777-4fc0-b98a-6bd429143b06.png --output-document aachen_000000_000019_leftImg8bit.png
+wget https://user-images.githubusercontent.com/24582831/189833143-15f60f8a-4d1e-4cbb-a6e7-5e2233869fac.png --output-document aachen_000000_000019_gtFine_labelTrainIds.png
+
+wget https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_40k_cityscapes/ann_r50-d8_512x1024_40k_cityscapes_20200605_095211-049fc292.pth
+
+```
+
+```python
+# Copyright (c) OpenMMLab. All rights reserved.
+from argparse import ArgumentParser
+from typing import Type
+
+import mmcv
+import torch
+import torch.nn as nn
+
+from mmengine.model import revert_sync_batchnorm
+from mmengine.structures import PixelData
+from mmseg.apis import inference_model, init_model
+from mmseg.structures import SegDataSample
+from mmseg.utils import register_all_modules
+from mmseg.visualization import SegLocalVisualizer
+
+
+class Recorder:
+    """record the forward output feature map and save to data_buffer."""
+
+    def __init__(self) -> None:
+        self.data_buffer = list()
+
+    def __enter__(self, ):
+        self._data_buffer = list()
+
+    def record_data_hook(self, model: nn.Module, input: Type, output: Type):
+        self.data_buffer.append(output)
+
+    def __exit__(self, *args, **kwargs):
+        pass
+
+
+def visualize(args, model, recorder, result):
+    seg_visualizer = SegLocalVisualizer(
+        vis_backends=[dict(type='WandbVisBackend')],
+        save_dir='temp_dir',
+        alpha=0.5)
+    seg_visualizer.dataset_meta = dict(
+        classes=model.dataset_meta['classes'],
+        palette=model.dataset_meta['palette'])
+
+    image = mmcv.imread(args.img, 'color')
+
+    seg_visualizer.add_datasample(
+        name='predict',
+        image=image,
+        data_sample=result,
+        draw_gt=False,
+        draw_pred=True,
+        wait_time=0,
+        out_file=None,
+        show=False)
+
+    # add feature map to wandb visualizer
+    for i in range(len(recorder.data_buffer)):
+        feature = recorder.data_buffer[i][0]  # remove the batch
+        drawn_img = seg_visualizer.draw_featmap(
+            feature, image, channel_reduction='select_max')
+        seg_visualizer.add_image(f'feature_map{i}', drawn_img)
+
+    if args.gt_mask:
+        sem_seg = mmcv.imread(args.gt_mask, 'unchanged')
+        sem_seg = torch.from_numpy(sem_seg)
+        gt_mask = dict(data=sem_seg)
+        gt_mask = PixelData(**gt_mask)
+        data_sample = SegDataSample()
+        data_sample.gt_sem_seg = gt_mask
+
+        seg_visualizer.add_datasample(
+            name='gt_mask',
+            image=image,
+            data_sample=data_sample,
+            draw_gt=True,
+            draw_pred=False,
+            wait_time=0,
+            out_file=None,
+            show=False)
+
+    seg_visualizer.add_image('image', image)
+
+
+def main():
+    parser = ArgumentParser(
+        description='Draw the Feature Map During Inference')
+    parser.add_argument('img', help='Image file')
+    parser.add_argument('config', help='Config file')
+    parser.add_argument('checkpoint', help='Checkpoint file')
+    parser.add_argument('--gt_mask', default=None, help='Path of gt mask file')
+    parser.add_argument('--out-file', default=None, help='Path to output file')
+    parser.add_argument(
+        '--device', default='cuda:0', help='Device used for inference')
+    parser.add_argument(
+        '--opacity',
+        type=float,
+        default=0.5,
+        help='Opacity of painted segmentation map. In (0, 1] range.')
+    parser.add_argument(
+        '--title', default='result', help='The image identifier.')
+    args = parser.parse_args()
+
+    register_all_modules()
+
+    # build the model from a config file and a checkpoint file
+    model = init_model(args.config, args.checkpoint, device=args.device)
+    if args.device == 'cpu':
+        model = revert_sync_batchnorm(model)
+
+    # show all named module in the model and use it in source list below
+    for name, module in model.named_modules():
+        print(name)
+
+    source = [
+        'decode_head.fusion.stages.0.query_project.activate',
+        'decode_head.context.stages.0.key_project.activate',
+        'decode_head.context.bottleneck.activate'
+    ]
+    source = dict.fromkeys(source)
+
+    count = 0
+    recorder = Recorder()
+    # registry the forward hook
+    for name, module in model.named_modules():
+        if name in source:
+            count += 1
+            module.register_forward_hook(recorder.record_data_hook)
+            if count == len(source):
+                break
+
+    with recorder:
+        # test a single image, and record feature map to data_buffer
+        result = inference_model(model, args.img)
+
+    visualize(args, model, recorder, result)
+
+
+if __name__ == '__main__':
+    main()
+
+```
+
+Save the above code as feature_map_visual.py and execute the  following code in terminal
+
+```shell
+python feature_map_visual.py ${image} ${config} ${checkpoint} [optional args]
+```
+
+e.g
+
+```shell
+python feature_map_visual.py \
+aachen_000000_000019_leftImg8bit.png \
+configs/ann/ann_r50-d8_4xb2-40k_cityscapes-512x1024.py \
+ann_r50-d8_512x1024_40k_cityscapes_20200605_095211-049fc292.pth \
+--gt_mask aachen_000000_000019_gtFine_labelTrainIds.png
+```
+
+The visualized image result and its corresponding reature map will appear in the wandb account.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/76149310/217520321-647f5bf9-eef2-446d-a9e8-5ca7b621d500.png">
+</div>

From 645dcf8c49e78529176f9f9893faa878f843cc65 Mon Sep 17 00:00:00 2001
From: CSH <40987381+csatsurnh@users.noreply.github.com>
Date: Thu, 9 Mar 2023 22:27:42 +0800
Subject: [PATCH 07/32] [Doc] Add zh_cn evaluation doc and fix en typo (#2701)

as title

---------

Signed-off-by: csatsurnh <cshan1995@126.com>
---
 docs/en/advanced_guides/evaluation.md    |  28 ++--
 docs/zh_cn/advanced_guides/evaluation.md | 157 ++++++++++++++++++++++-
 2 files changed, 170 insertions(+), 15 deletions(-)

diff --git a/docs/en/advanced_guides/evaluation.md b/docs/en/advanced_guides/evaluation.md
index ee5a927ff7..1e42db2a10 100644
--- a/docs/en/advanced_guides/evaluation.md
+++ b/docs/en/advanced_guides/evaluation.md
@@ -1,6 +1,6 @@
 # Evaluation
 
-The evaluation procedure would be executed at [ValLoop](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/loops.py#L300) and [TestLoop](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/loops.py#L373), users can evaluate model performance during training or using the test script with simple settings in the configuration file. The `ValLoop` and `TestLoop` are properties of [Runner](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/runner.py#L59), they will be built the first time they are called. To build the `ValLoop` successfully, the `val_dataloader` and `val_evaluator` must be set when building `Runner` since `dataloder` and `evaluator` are required parameters, and the same goes for `TestLoop`. For more information about the Runner's design, please refer to the [documentoation](https://github.com/open-mmlab/mmengine/blob/main/docs/en/design/runner.md) of [MMEngine](https://github.com/open-mmlab/mmengine).
+The evaluation procedure would be executed at [ValLoop](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/loops.py#L300) and [TestLoop](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/loops.py#L373), users can evaluate model performance during training or using the test script with simple settings in the configuration file. The `ValLoop` and `TestLoop` are properties of [Runner](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/runner.py#L59), they will be built the first time they are called. To build the `ValLoop` successfully, the `val_dataloader` and `val_evaluator` must be set when building `Runner` since `dataloader` and `evaluator` are required parameters, and the same goes for `TestLoop`. For more information about the Runner's design, please refer to the [documentation](https://github.com/open-mmlab/mmengine/blob/main/docs/en/design/runner.md) of [MMEngine](https://github.com/open-mmlab/mmengine).
 
 <center>
   <img src='../../../resources/test_step.png' />
@@ -61,7 +61,7 @@ In MMSegmentation, the settings of `test_dataloader` and `test_evaluator` are th
 
 ## IoUMetric
 
-MMSegmentation implements [IoUMetric](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/evaluation/metrics/iou_metric.py) and [CitysMetric](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/evaluation/metrics/citys_metric.py) for evaluating the performance of models, based on the [BaseMetric](https://github.com/open-mmlab/mmengine/blob/main/mmengine/evaluator/metric.py) provided by [MMEngine](https://github.com/open-mmlab/mmengine). Please refer to [the documentation](https://mmengine.readthedocs.io/en/latest/tutorials/evaluation.html) for more details about the unified evaluation interface.
+MMSegmentation implements [IoUMetric](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/evaluation/metrics/iou_metric.py) and [CityscapesMetric](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/evaluation/metrics/citys_metric.py) for evaluating the performance of models, based on the [BaseMetric](https://github.com/open-mmlab/mmengine/blob/main/mmengine/evaluator/metric.py) provided by [MMEngine](https://github.com/open-mmlab/mmengine). Please refer to [the documentation](https://mmengine.readthedocs.io/en/latest/tutorials/evaluation.html) for more details about the unified evaluation interface.
 
 Here we briefly describe the arguments and the two main methods of `IoUMetric`.
 
@@ -102,9 +102,9 @@ Returns:
 
 - Dict\[str, float\] - The computed metrics. The keys are the names of the metrics, and the values are corresponding results. The key mainly includes **aAcc**, **mIoU**, **mAcc**, **mDice**, **mFscore**, **mPrecision**, **mRecall**.
 
-## CitysMetric
+## CityscapesMetric
 
-`CitysMetric` uses the official [CityscapesScripts](https://github.com/mcordts/cityscapesScripts) provided by Cityscapes to evaluate model performance.
+`CityscapesMetric` uses the official [CityscapesScripts](https://github.com/mcordts/cityscapesScripts) provided by Cityscapes to evaluate model performance.
 
 ### Usage
 
@@ -114,10 +114,10 @@ Before using it, please install the `cityscapesscripts` package first:
 pip install cityscapesscripts
 ```
 
-Since the `IoUMetric` is used as the default evaluator in MMSegmentation, if you would like to use `CitysMetric`, customizing the config file is required. In your customized config file, you should overwrite the default evaluator as follows.
+Since the `IoUMetric` is used as the default evaluator in MMSegmentation, if you would like to use `CityscapesMetric`, customizing the config file is required. In your customized config file, you should overwrite the default evaluator as follows.
 
 ```python
-val_evaluator = dict(type='CitysMetric', citys_metrics=['cityscapes'])
+val_evaluator = dict(type='CityscapesMetric', output_dir='tmp')
 test_evaluator = val_evaluator
 ```
 
@@ -125,27 +125,27 @@ test_evaluator = val_evaluator
 
 The arguments of the constructor:
 
+- output_dir (str) - The directory for output prediction
 - ignore_index (int) - Index that will be ignored in evaluation. Default: 255.
-- citys_metrics (list\[str\] | str) - Metrics to be evaluated, Default: \['cityscapes'\].
-- to_label_id (bool) - whether convert output to label_id for submission. Default: True.
-- suffix (str): The filename prefix of the png files. If the prefix is "somepath/xxx", the png files will be named "somepath/xxx.png". Default: '.format_cityscapes'.
-- collect_device (str): Device name used for collecting results from different ranks during distributed training. Must be 'cpu' or 'gpu'. Defaults to 'cpu'.
-- prefix (str, optional): The prefix that will be added in the metric names to disambiguate homonymous metrics of different evaluators. If the prefix is not provided in the argument, self.default_prefix will be used instead. Defaults to None.
+- format_only (bool) - Only format result for results commit without perform evaluation. It is useful when you want to format the result to a specific format and submit it to the test server. Defaults to False.
+- keep_results (bool) - Whether to keep the results. When `format_only` is True, `keep_results` must be True. Defaults to False.
+- collect_device (str) - Device name used for collecting results from different ranks during distributed training. Must be 'cpu' or 'gpu'. Defaults to 'cpu'.
+- prefix (str, optional) - The prefix that will be added in the metric names to disambiguate homonymous metrics of different evaluators. If prefix is not provided in the argument, self.default_prefix will be used instead. Defaults to None.
 
-#### CitysMetric.process
+#### CityscapesMetric.process
 
 This method would draw the masks on images and save the painted images to `work_dir`.
 
 Parameters:
 
-- data_batch (Any) - A batch of data from the dataloader.
+- data_batch (dict) - A batch of data from the dataloader.
 - data_samples (Sequence\[dict\]) - A batch of outputs from the model.
 
 Returns:
 
 This method doesn't have returns, the annotations' path would be stored in `self.results`, which will be used to compute the metrics when all batches have been processed.
 
-#### CitysMetric.compute_metrics
+#### CityscapesMetric.compute_metrics
 
 This method would call `cityscapesscripts.evaluation.evalPixelLevelSemanticLabeling` tool to calculate metrics.
 
diff --git a/docs/zh_cn/advanced_guides/evaluation.md b/docs/zh_cn/advanced_guides/evaluation.md
index a82311ccc7..dc93a46e13 100644
--- a/docs/zh_cn/advanced_guides/evaluation.md
+++ b/docs/zh_cn/advanced_guides/evaluation.md
@@ -1,3 +1,158 @@
 # 模型评测
 
-中文版文档支持中，请先阅读[英文版本](../../en/advanced_guides/evaluation.md)
+模型评测过程会分别在 [ValLoop](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/loops.py#L300) 和 [TestLoop](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/loops.py#L373) 中被执行，用户可以在训练期间或使用配置文件中简单设置的测试脚本进行模型性能评估。`ValLoop` 和 `TestLoop` 属于 [Runner](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/runner.py#L59)，它们会在第一次被调用时构建。由于 `dataloader` 与 `evaluator` 是必需的参数，所以要成功构建 `ValLoop`，在构建 `Runner` 时必须设置 `val_dataloader` 和 `val_evaluator`，`TestLoop` 亦然。有关 Runner 设计的更多信息，请参阅 [MMEngine](https://github.com/open-mmlab/mmengine) 的[文档](https://github.com/open-mmlab/mmengine/blob/main/docs/zh_cn/design/runner.md)。
+
+<center>
+  <img src='../../../resources/test_step.png' />
+  <center>测试/验证 数据流</center>
+</center>
+
+在 MMSegmentation 中，默认情况下，我们将 dataloader 和 metrics 的设置写在数据集配置文件中，并将 evaluation loop 的配置写在 `schedule_x` 配置文件中。
+
+例如，在 ADE20K 配置文件 `configs/_base_/dataset/ADE20K.py` 中，在第37到48行，我们配置了 `val_dataloader`，在第51行，我们选择 `IoUMetric` 作为 evaluator，并设置 `mIoU` 作为指标：
+
+```python
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/validation',
+            seg_map_path='annotations/validation'),
+        pipeline=test_pipeline))
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+```
+
+为了能够在训练期间进行评估模型，我们将评估配置添加到了 `configs/schedules/schedule_40k.py` 文件的第15至16行：
+
+```python
+train_cfg = dict(type='IterBasedTrainLoop', max_iters=40000, val_interval=4000)
+val_cfg = dict(type='ValLoop')
+```
+
+使用以上两种设置，MMSegmentation 在 40K 迭代训练期间，每 4000 次迭代进行一次模型 **mIoU** 指标的评估。
+
+如果我们希望在训练后测试模型，则需要将 `test_dataloader`、`test_evaluator` 和 `test_cfg` 配置添加到配置文件中。
+
+```python
+test_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/validation',
+            seg_map_path='annotations/validation'),
+        pipeline=test_pipeline))
+
+test_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_cfg = dict(type='TestLoop')
+```
+
+在 MMSegmentation 中，默认情况下，`test_dataloader` 和 `test_evaluator` 的设置与 `ValLoop` 的 dataloader 和 evaluator 相同，我们可以修改这些设置以满足我们的需要。
+
+## IoUMetric
+
+MMSegmentation 基于 [MMEngine](https://github.com/open-mmlab/mmengine) 提供的 [BaseMetric](https://github.com/open-mmlab/mmengine/blob/main/mmengine/evaluator/metric.py) 实现 [IoUMetric](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/evaluation/metrics/iou_metric.py) 和 [CityscapesMetric](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/evaluation/metrics/citys_metric.py)，以评估模型的性能。有关统一评估接口的更多详细信息，请参阅[文档](https://mmengine.readthedocs.io/zh_CN/latest/tutorials/evaluation.html)。
+
+这里我们简要介绍 `IoUMetric` 的参数和两种主要方法。
+
+除了 `collect_device` 和 `prefix` 之外，`IoUMetric` 的构建还包含一些其他参数。
+
+构造函数的参数：
+
+- ignore_index（int）- 将在评估中忽略的类别索引。默认值：255。
+- iou_metrics（list\[str\] | str）- 需要计算的指标，可选项包括 'mIoU'、'mDice' 和 'mFscore'。
+- nan_to_num（int，可选）- 如果指定，NaN 值将被用户定义的数字替换。默认值：None。
+- beta（int）- 决定综合评分中 recall 的权重。默认值：1。
+- collect_device（str）- 用于在分布式训练期间从不同进程收集结果的设备名称。必须是 'cpu' 或 'gpu'。默认为 'cpu'。
+- prefix（str，可选）- 将添加到指标名称中的前缀，以消除不同 evaluator 的同名指标的歧义。如果参数中未提供前缀，则将使用 self.default_prefix 进行替代。默认为 None。
+
+`IoUMetric` 实现 IoU 指标的计算，`IoUMetric` 的两个核心方法是 `process` 和 `compute_metrics`。
+
+- `process` 方法处理一批 data 和 data_samples。
+- `compute_metrics` 方法根据处理的结果计算指标。
+
+### IoUMetric.process
+
+参数：
+
+- data_batch（Any）- 来自 dataloader 的一批数据。
+- data_samples（Sequence\[dict\]）- 模型的一批输出。
+
+返回值：
+
+此方法没有返回值，因为处理的结果将存储在 `self.results` 中，以在处理完所有批次后进行指标的计算。
+
+### IoUMetric.compute_metrics
+
+参数：
+
+- results（list）- 每个批次的处理结果。
+
+返回值：
+
+- Dict\[str，float\] - 计算的指标。指标的名称为 key，值是相应的结果。key 主要包括 **aAcc**、**mIoU**、**mAcc**、**mDice**、**mFscore**、**mPrecision**、**mPrecall**。
+
+## CityscapesMetric
+
+`CityscapesMetric` 使用由 Cityscapes 官方提供的 [CityscapesScripts](https://github.com/mcordts/cityscapesScripts) 进行模型性能的评估。
+
+### 使用方法
+
+在使用之前，请先安装 `cityscapesscripts` 包：
+
+```shell
+pip install cityscapesscripts
+```
+
+由于 `IoUMetric` 在 MMSegmentation 中作为默认的 evaluator 使用，如果您想使用 `CityscapesMetric`，则需要自定义配置文件。在自定义配置文件中，应按如下方式替换默认 evaluator。
+
+```python
+val_evaluator = dict(type='CityscapesMetric', output_dir='tmp')
+test_evaluator = val_evaluator
+```
+
+### 接口
+
+构造函数的参数：
+
+- output_dir (str) - 预测结果输出的路径
+- ignore_index (int) - 将在评估中忽略的类别索引。默认值：255。
+- format_only (bool) - 只为提交进行结果格式化而不进行评估。当您希望将结果格式化为特定格式并将其提交给测试服务器时有用。默认为 False。
+- keep_results (bool) - 是否保留结果。当 `format_only` 为 True 时，`keep_results` 必须为 True。默认为 False。
+- collect_device (str) - 用于在分布式训练期间从不同进程收集结果的设备名称。必须是 'cpu' 或 'gpu'。默认为 'cpu'。
+- prefix (str，可选) - 将添加到指标名称中的前缀，以消除不同 evaluator 的同名指标的歧义。如果参数中未提供前缀，则将使用 self.default_prefix 进行替代。默认为 None。
+
+#### CityscapesMetric.process
+
+该方法将在图像上绘制 mask，并将绘制的图像保存到 `work_dir` 中。
+
+参数：
+
+- data_batch（dict）- 来自 dataloader 的一批数据。
+- data_samples（Sequence\[dict\]）- 模型的一批输出。
+
+返回值：
+
+此方法没有返回值，因为处理的结果将存储在 `self.results` 中，以在处理完所有批次后进行指标的计算。
+
+#### CityscapesMetric.compute_metrics
+
+此方法将调用 `cityscapessscripts.evaluation.evalPixelLevelSemanticLabeling` 工具来计算指标。
+
+参数：
+
+- results（list）- 数据集的测试结果。
+
+返回值：
+
+- dict\[str:float\] - Cityscapes 评测结果。

From 6468d3150a0a02c212bd1515b9b52f9a74a95f94 Mon Sep 17 00:00:00 2001
From: CSH <40987381+csatsurnh@users.noreply.github.com>
Date: Thu, 9 Mar 2023 22:28:58 +0800
Subject: [PATCH 08/32] [Doc] Add zh_cn transforms doc and format en doc
 (#2722)

as title
---
 docs/en/advanced_guides/transforms.md    |  24 ++---
 docs/zh_cn/advanced_guides/transforms.md | 118 ++++++++++++++++++++++-
 2 files changed, 124 insertions(+), 18 deletions(-)

diff --git a/docs/en/advanced_guides/transforms.md b/docs/en/advanced_guides/transforms.md
index e0c4155b57..68b1f44bd3 100644
--- a/docs/en/advanced_guides/transforms.md
+++ b/docs/en/advanced_guides/transforms.md
@@ -12,15 +12,10 @@ The structure of this guide is as follows:
 
 ## Design of Data pipelines
 
-Following typical conventions, we use `Dataset` and `DataLoader` for data loading
-with multiple workers. `Dataset` returns a dict of data items corresponding
-the arguments of models' forward method.
-Since the data in semantic segmentation may not be the same size,
-we introduce a new `DataContainer` type in MMCV to help collect and distribute
-data of different size.
-See [here](https://github.com/open-mmlab/mmcv/blob/master/mmcv/parallel/data_container.py) for more details.
+Following typical conventions, we use `Dataset` and `DataLoader` for data loading with multiple workers. `Dataset` returns a dict of data items corresponding the arguments of models' forward method. Since the data in semantic segmentation may not be the same size, we introduce a new `DataContainer` type in MMCV to help collect and distribute data of different size. See [here](https://github.com/open-mmlab/mmcv/blob/master/mmcv/parallel/data_container.py) for more details.
 
 In 1.x version of MMSegmentation, all data transformations are inherited from [`BaseTransform`](https://github.com/open-mmlab/mmcv/blob/2.x/mmcv/transforms/base.py#L6).
+
 The input and output types of transformations are both dict. A simple example is as follows:
 
 ```python
@@ -38,13 +33,11 @@ The input and output types of transformations are both dict. A simple example is
 dict_keys(['img_path', 'seg_map_path', 'reduce_zero_label', 'seg_fields', 'gt_seg_map'])
 ```
 
-The data preparation pipeline and the dataset are decomposed. Usually a dataset
-defines how to process the annotations and a data pipeline defines all the steps to prepare a data dict.
-A pipeline consists of a sequence of operations. Each operation takes a dict as input and also outputs a dict for the next transform.
+The data preparation pipeline and the dataset are decomposed. Usually a dataset defines how to process the annotations and a data pipeline defines all the steps to prepare a data dict. A pipeline consists of a sequence of operations. Each operation takes a dict as input and also outputs a dict for the next transform.
 
 The operations are categorized into data loading, pre-processing, formatting and test-time augmentation.
 
-Here is a pipeline example for PSPNet.
+Here is a pipeline example for PSPNet:
 
 ```python
 crop_size = (512, 1024)
@@ -71,8 +64,7 @@ test_pipeline = [
 ]
 ```
 
-For each operation, we list the related dict fields that are `added`/`updated`/`removed`.
-Before pipelines, the information we can directly obtain from the datasets are `img_path` and `seg_map_path`.
+For each operation, we list the related dict fields that are `added`/`updated`/`removed`. Before pipelines, the information we can directly obtain from the datasets are `img_path` and `seg_map_path`.
 
 ### Data loading
 
@@ -98,16 +90,14 @@ Before pipelines, the information we can directly obtain from the datasets are `
 
 `RandomCrop`: Random crop image & segmentation map.
 
-- update: `img`, `gt_seg_map`, `img_shape`.
+- update: `img`, `gt_seg_map`, `img_shape`
 
 `RandomFlip`: Flip the image & segmentation map.
 
 - add: `flip`, `flip_direction`
 - update: `img`, `gt_seg_map`
 
-`PhotoMetricDistortion`: Apply photometric distortion to image sequentially,
-every transformation is applied with a probability of 0.5.
-The position of random contrast is in second or second to last(mode 0 or 1 below, respectively).
+`PhotoMetricDistortion`: Apply photometric distortion to image sequentially, every transformation is applied with a probability of 0.5. The position of random contrast is in second or second to last(mode 0 or 1 below, respectively).
 
 ```
 1. random brightness
diff --git a/docs/zh_cn/advanced_guides/transforms.md b/docs/zh_cn/advanced_guides/transforms.md
index 1cbe79ba49..e5f3bebf6d 100644
--- a/docs/zh_cn/advanced_guides/transforms.md
+++ b/docs/zh_cn/advanced_guides/transforms.md
@@ -1,3 +1,119 @@
 # 数据增强变化
 
-中文版文档支持中，请先阅读[英文版本](../../en/advanced_guides/transforms.md)
+在本教程中，我们将介绍 MMSegmentation 中数据增强变化流程的设计。
+
+本指南的结构如下：
+
+- [数据增强变化](#数据增强变化)
+  - [数据增强变化流程设计](#数据增强变化流程设计)
+    - [数据加载](#数据加载)
+    - [预处理](#预处理)
+    - [格式修改](#格式修改)
+
+## 数据增强变化流程设计
+
+按照惯例，我们使用 `Dataset` 和 `DataLoader` 多进程地加载数据。`Dataset` 返回与模型 forward 方法的参数相对应的数据项的字典。由于语义分割中的数据可能大小不同，我们在 MMCV 中引入了一种新的 `DataContainer` 类型，以帮助收集和分发不同大小的数据。参见[此处](https://github.com/open-mmlab/mmcv/blob/master/mmcv/parallel/data_container.py)了解更多详情。
+
+在 MMSegmentation 的 1.x 版本中，所有数据转换都继承自 [`BaseTransform`](https://github.com/open-mmlab/mmcv/blob/2.x/mmcv/transforms/base.py#L6).
+
+转换的输入和输出类型都是字典。一个简单的示例如下：
+
+```python
+>>> from mmseg.datasets.transforms import LoadAnnotations
+>>> transforms = LoadAnnotations()
+>>> img_path = './data/cityscapes/leftImg8bit/train/aachen/aachen_000000_000019_leftImg8bit.png.png'
+>>> gt_path = './data/cityscapes/gtFine/train/aachen/aachen_000015_000019_gtFine_instanceTrainIds.png'
+>>> results = dict(
+>>>     img_path=img_path,
+>>>     seg_map_path=gt_path,
+>>>     reduce_zero_label=False,
+>>>     seg_fields=[])
+>>> data_dict = transforms(results)
+>>> print(data_dict.keys())
+dict_keys(['img_path', 'seg_map_path', 'reduce_zero_label', 'seg_fields', 'gt_seg_map'])
+```
+
+数据准备流程和数据集是解耦的。通常，数据集定义如何处理标注，数据流程定义准备数据字典的所有步骤。流程由一系列操作组成。每个操作都将字典作为输入，并为接下来的转换输出字典。
+
+操作分为数据加载、预处理、格式修改和测试数据增强。
+
+这里是 PSPNet 的流程示例：
+
+```python
+crop_size = (512, 1024)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=(2048, 1024),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+```
+
+对于每个操作，我们列出了 `添加`/`更新`/`删除` 相关的字典字段。在流程前，我们可以从数据集直接获得的信息是 `img_path` 和 `seg_map_path`。
+
+### 数据加载
+
+`LoadImageFromFile`：从文件加载图像。
+
+- 添加：`img`，`img_shape`，`ori_shape`
+
+`LoadAnnotations`：加载数据集提供的语义分割图。
+
+- 添加：`seg_fields`，`gt_seg_map`
+
+### 预处理
+
+`RandomResize`：随机调整图像和分割图大小。
+
+-添加：`scale`，`scale_factor`，`keep_ratio`
+-更新：`img`，`img_shape`，`gt_seg_map`
+
+`Resize`：调整图像和分割图的大小。
+
+-添加：`scale`，`scale_factor`，`keep_ratio`
+-更新：`img`，`gt_seg_map`，`img_shape`
+
+`RandomCrop`：随机裁剪图像和分割图。
+
+-更新：`img`，`gt_seg_map`，`img_shape`
+
+`RandomFlip`：翻转图像和分割图。
+
+-添加：`flip`，`flip_direction`
+-更新：`img`，`gt_seg_map`
+
+`PhotoMetricDistortion`：按顺序对图像应用光度失真，每个变换的应用概率为 0.5。随机对比度的位置是第二或倒数第二（分别为下面的模式 0 或 1）。
+
+```
+1.随机亮度
+2.随机对比度（模式 0）
+3.将颜色从 BGR 转换为 HSV
+4.随机饱和度
+5.随机色调
+6.将颜色从 HSV 转换为 BGR
+7.随机对比度（模式 1）
+```
+
+- 更新：`img`
+
+### 格式修改
+
+`PackSegInputs`：为语义分段打包输入数据。
+
+- 添加：`inputs`，`data_sample`
+- 删除：由 `meta_keys` 指定的 keys（合并到 data_sample 的 metainfo 中），所有其他 keys

From 45fae72de5d3bf933504348daba5c848f752d4a1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E8=B0=A2=E6=98=95=E8=BE=B0?= <xiexinch@outlook.com>
Date: Fri, 10 Mar 2023 19:25:47 +0800
Subject: [PATCH 09/32] [Feature] Support calculating FLOPs of segmentors
 (#2706)

## Motivation

fix compute flops problems

## Modification

Please briefly describe what modification is made in this PR.
---
 tools/analysis_tools/get_flops.py | 108 ++++++++++++++++++++++++------
 1 file changed, 86 insertions(+), 22 deletions(-)

diff --git a/tools/analysis_tools/get_flops.py b/tools/analysis_tools/get_flops.py
index 1e8f188e18..66b2d52fcd 100644
--- a/tools/analysis_tools/get_flops.py
+++ b/tools/analysis_tools/get_flops.py
@@ -1,10 +1,23 @@
 # Copyright (c) OpenMMLab. All rights reserved.
 import argparse
+import tempfile
+from pathlib import Path
 
-from mmcv.cnn import get_model_complexity_info
-from mmengine import Config
+import torch
+from mmengine import Config, DictAction
+from mmengine.logging import MMLogger
+from mmengine.model import revert_sync_batchnorm
+from mmengine.registry import init_default_scope
 
-from mmseg.models import build_segmentor
+from mmseg.models import BaseSegmentor
+from mmseg.registry import MODELS
+from mmseg.structures import SegDataSample
+
+try:
+    from mmengine.analysis import get_model_complexity_info
+    from mmengine.analysis.print_helper import _format_size
+except ImportError:
+    raise ImportError('Please upgrade mmengine >= 0.6.0 to use this script.')
 
 
 def parse_args():
@@ -17,13 +30,33 @@ def parse_args():
         nargs='+',
         default=[2048, 1024],
         help='input image size')
+    parser.add_argument(
+        '--cfg-options',
+        nargs='+',
+        action=DictAction,
+        help='override some settings in the used config, the key-value pair '
+        'in xxx=yyy format will be merged into config file. If the value to '
+        'be overwritten is a list, it should be like key="[a,b]" or key=a,b '
+        'It also allows nested list/tuple values, e.g. key="[(a,b),(c,d)]" '
+        'Note that the quotation marks are necessary and that no white space '
+        'is allowed.')
     args = parser.parse_args()
     return args
 
 
-def main():
+def inference(args: argparse.Namespace, logger: MMLogger) -> dict:
+    config_name = Path(args.config)
 
-    args = parse_args()
+    if not config_name.exists():
+        logger.error(f'Config file {config_name} does not exist')
+
+    cfg: Config = Config.fromfile(config_name)
+    cfg.work_dir = tempfile.TemporaryDirectory().name
+    cfg.log_level = 'WARN'
+    if args.cfg_options is not None:
+        cfg.merge_from_dict(args.cfg_options)
+
+    init_default_scope(cfg.get('scope', 'mmseg'))
 
     if len(args.shape) == 1:
         input_shape = (3, args.shape[0], args.shape[0])
@@ -31,29 +64,60 @@ def main():
         input_shape = (3, ) + tuple(args.shape)
     else:
         raise ValueError('invalid input shape')
+    result = {}
 
-    cfg = Config.fromfile(args.config)
-    cfg.model.pretrained = None
-    model = build_segmentor(
-        cfg.model,
-        train_cfg=cfg.get('train_cfg'),
-        test_cfg=cfg.get('test_cfg')).cuda()
+    model: BaseSegmentor = MODELS.build(cfg.model)
+    if hasattr(model, 'auxiliary_head'):
+        model.auxiliary_head = None
+    if torch.cuda.is_available():
+        model.cuda()
+    model = revert_sync_batchnorm(model)
+    result['ori_shape'] = input_shape[-2:]
+    result['pad_shape'] = input_shape[-2:]
+    data_batch = {
+        'inputs': [torch.rand(input_shape)],
+        'data_samples': [SegDataSample(metainfo=result)]
+    }
+    data = model.data_preprocessor(data_batch)
     model.eval()
+    if cfg.model.decode_head.type in ['MaskFormerHead', 'Mask2FormerHead']:
+        # TODO: Support MaskFormer and Mask2Former
+        raise NotImplementedError('MaskFormer and Mask2Former are not '
+                                  'supported yet.')
+    outputs = get_model_complexity_info(
+        model,
+        input_shape,
+        inputs=data['inputs'],
+        show_table=False,
+        show_arch=False)
+    result['flops'] = _format_size(outputs['flops'])
+    result['params'] = _format_size(outputs['params'])
+    result['compute_type'] = 'direct: randomly generate a picture'
+    return result
 
-    if hasattr(model, 'forward_dummy'):
-        model.forward = model.forward_dummy
-    else:
-        raise NotImplementedError(
-            'FLOPs counter is currently not currently supported with {}'.
-            format(model.__class__.__name__))
 
-    flops, params = get_model_complexity_info(model, input_shape)
+def main():
+
+    args = parse_args()
+    logger = MMLogger.get_instance(name='MMLogger')
+
+    result = inference(args, logger)
     split_line = '=' * 30
-    print('{0}\nInput shape: {1}\nFlops: {2}\nParams: {3}\n{0}'.format(
-        split_line, input_shape, flops, params))
+    ori_shape = result['ori_shape']
+    pad_shape = result['pad_shape']
+    flops = result['flops']
+    params = result['params']
+    compute_type = result['compute_type']
+
+    if pad_shape != ori_shape:
+        print(f'{split_line}\nUse size divisor set input shape '
+              f'from {ori_shape} to {pad_shape}')
+    print(f'{split_line}\nCompute type: {compute_type}\n'
+          f'Input shape: {pad_shape}\nFlops: {flops}\n'
+          f'Params: {params}\n{split_line}')
     print('!!!Please be cautious if you use the results in papers. '
-          'You may need to check if all ops are supported and verify that the '
-          'flops computation is correct.')
+          'You may need to check if all ops are supported and verify '
+          'that the flops computation is correct.')
 
 
 if __name__ == '__main__':

From 684d79fedc2d144c8ac9e4ce16cd3b0dbd524ccb Mon Sep 17 00:00:00 2001
From: CSH <40987381+csatsurnh@users.noreply.github.com>
Date: Mon, 13 Mar 2023 19:23:22 +0800
Subject: [PATCH 10/32] [Doc] add zh_cn migration doc (#2733)

as title

---------

Co-authored-by: MeowZheng <meowzheng@outlook.com>
---
 README_zh-CN.md                   |   2 +-
 docs/en/migration/interface.md    |  39 +--
 docs/en/migration/package.md      |   7 +-
 docs/zh_cn/migration.md           |   3 -
 docs/zh_cn/migration/index.rst    |   8 +
 docs/zh_cn/migration/interface.md | 496 ++++++++++++++++++++++++++++++
 docs/zh_cn/migration/package.md   | 113 +++++++
 7 files changed, 637 insertions(+), 31 deletions(-)
 delete mode 100644 docs/zh_cn/migration.md
 create mode 100644 docs/zh_cn/migration/index.rst
 create mode 100644 docs/zh_cn/migration/interface.md
 create mode 100644 docs/zh_cn/migration/package.md

diff --git a/README_zh-CN.md b/README_zh-CN.md
index 858485fd54..f7c3b0b18e 100644
--- a/README_zh-CN.md
+++ b/README_zh-CN.md
@@ -76,7 +76,7 @@ MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 O
 
 同时，我们提供了 Colab 教程。你可以在[这里](demo/MMSegmentation_Tutorial.ipynb)浏览教程，或者直接在 Colab 上[运行](https://colab.research.google.com/github/open-mmlab/mmsegmentation/blob/1.x/demo/MMSegmentation_Tutorial.ipynb)。
 
-若需要将0.x版本的代码迁移至新版，请参考[迁移文档](docs/zh_cn/migration.md)。
+若需要将0.x版本的代码迁移至新版，请参考[迁移文档](docs/zh_cn/migration)。
 
 ## 基准测试和模型库
 
diff --git a/docs/en/migration/interface.md b/docs/en/migration/interface.md
index d75f8ec3ef..3dab125ebc 100644
--- a/docs/en/migration/interface.md
+++ b/docs/en/migration/interface.md
@@ -6,14 +6,17 @@ This guide describes the fundamental differences between MMSegmentation 0.x and
 
 ## New dependencies
 
-MMSegmentation 1.x depends on some new packages, you can prepare a new clean environment and install again according to the [installation tutorial](get_started.md).
+MMSegmentation 1.x depends on some new packages, you can prepare a new clean environment and install again according to the [installation tutorial](../get_started.md).
+
 Or install the below packages manually.
 
 1. [MMEngine](https://github.com/open-mmlab/mmengine): MMEngine is the core the OpenMMLab 2.0 architecture, and we splited many compentents unrelated to computer vision from MMCV to MMEngine.
 
 2. [MMCV](https://github.com/open-mmlab/mmcv): The computer vision package of OpenMMLab. This is not a new dependency, but you need to upgrade it to above **2.0.0rc1** version.
 
-3. [MMClassification](https://github.com/open-mmlab/mmclassification)(Optional): The  image classification toolbox and benchmark of OpenMMLab. This is not a new dependency, but you need to upgrade it to above **1.0.0rc0** version.
+3. [MMClassification](https://github.com/open-mmlab/mmclassification)(Optional): The image classification toolbox and benchmark of OpenMMLab. This is not a new dependency, but you need to upgrade it to above **1.0.0rc0** version.
+
+4. [MMDetection](https://github.com/open-mmlab/mmdetection)(Optional): The object detection toolbox and benchmark of OpenMMLab. This is not a new dependency, but you need to upgrade it to above **3.0.0rc0** version.
 
 ## Train launch
 
@@ -86,7 +89,7 @@ Add `model.data_preprocessor` field to configure the `DataPreProcessor`, includi
 
 - `bgr_to_rgb` (bool): whether to convert image from BGR to RGB.Defaults to False.
 
-- `rgb_to_bgr` (bool): whether to convert image from RGB to RGB. Defaults to False.
+- `rgb_to_bgr` (bool): whether to convert image from RGB to BGR. Defaults to False.
 
 **Note:**
 Please refer [models documentation](../advanced_guides/models.md) for more details.
@@ -260,8 +263,7 @@ tta_pipeline = [
 Changes in **`evaluation`**:
 
 - The **`evaluation`** field is split to `val_evaluator` and `test_evaluator`. And it won't support `interval` and `save_best` arguments.
-  The `interval` is moved to `train_cfg.val_interval`, and the `save_best`
-  is moved to `default_hooks.checkpoint.save_best`. `pre_eval` has been removed.
+  The `interval` is moved to `train_cfg.val_interval`, and the `save_best` is moved to `default_hooks.checkpoint.save_best`. `pre_eval` has been removed.
 - `'mIoU'` has been changed to `'IoUMetric'`.
 
 <table class="docutils">
@@ -291,8 +293,7 @@ test_evaluator = val_evaluator
 
 Changes in **`optimizer`** and **`optimizer_config`**:
 
-- Now we use `optim_wrapper` field to specify all configuration about the optimization process. And the
-  `optimizer` is a sub field of `optim_wrapper` now.
+- Now we use `optim_wrapper` field to specify all configuration about the optimization process. And the `optimizer` is a sub field of `optim_wrapper` now.
 - `paramwise_cfg` is also a sub field of `optim_wrapper`, instead of `optimizer`.
 - `optimizer_config` is removed now, and all configurations of it are moved to `optim_wrapper`.
 - `grad_clip` is renamed to `clip_grad`.
@@ -326,11 +327,9 @@ optim_wrapper = dict(
 Changes in **`lr_config`**:
 
 - The `lr_config` field is removed and we use new `param_scheduler` to replace it.
-- The `warmup` related arguments are removed, since we use schedulers combination to implement this
-  functionality.
+- The `warmup` related arguments are removed, since we use schedulers combination to implement this functionality.
 
-The new schedulers combination mechanism is very flexible, and you can use it to design many kinds of learning
-rate / momentum curves. See [the tutorial](TODO) for more details.
+The new schedulers combination mechanism is very flexible, and you can use it to design many kinds of learning rate / momentum curves. See [the tutorial](TODO) for more details.
 
 <table class="docutils">
 <tr>
@@ -374,8 +373,7 @@ param_scheduler = [
 
 Changes in **`runner`**:
 
-Most configuration in the original `runner` field is moved to `train_cfg`, `val_cfg` and `test_cfg`, which
-configure the loop in training, validation and test.
+Most configuration in the original `runner` field is moved to `train_cfg`, `val_cfg` and `test_cfg`, which configure the loop in training, validation and test.
 
 <table class="docutils">
 <tr>
@@ -402,8 +400,7 @@ test_cfg = dict(type='TestLoop') # Use the default test loop.
 </tr>
 </table>
 
-In fact, in OpenMMLab 2.0, we introduced `Loop` to control the behaviors in training, validation and test. The functionalities of `Runner` are also changed. You can find more details of [runner tutorial](https://github.com/open-mmlab/mmengine/blob/main/docs/en/design/runner.md)
-in [MMEngine](https://github.com/open-mmlab/mmengine/).
+In fact, in OpenMMLab 2.0, we introduced `Loop` to control the behaviors in training, validation and test. The functionalities of `Runner` are also changed. You can find more details of [runner tutorial](https://github.com/open-mmlab/mmengine/blob/main/docs/en/design/runner.md) in [MMEngine](https://github.com/open-mmlab/mmengine/).
 
 ### Runtime settings
 
@@ -433,8 +430,7 @@ default_hooks = dict(
     visualization=dict(type='SegVisualizationHook'))
 ```
 
-In addition, we split the original logger to logger and visualizer. The logger is used to record
-information and the visualizer is used to show the logger in different backends, like terminal and TensorBoard.
+In addition, we split the original logger to logger and visualizer. The logger is used to record information and the visualizer is used to show the logger in different backends, like terminal and TensorBoard.
 
 <table class="docutils">
 <tr>
@@ -478,8 +474,7 @@ Changes in **`load_from`** and **`resume_from`**:
   - If `resume=False` and `load_from` is **not None**, only load the checkpoint, not resume training.
   - If `resume=False` and `load_from` is **None**, do not load nor resume.
 
-Changes in **`dist_params`**: The `dist_params` field is a sub field of `env_cfg` now. And there are some new
-configurations in the `env_cfg`.
+Changes in **`dist_params`**: The `dist_params` field is a sub field of `env_cfg` now. And there are some new configurations in the `env_cfg`.
 
 ```python
 env_cfg = dict(
@@ -496,8 +491,6 @@ env_cfg = dict(
 
 Changes in **`workflow`**: `workflow` related functionalities are removed.
 
-New field **`visualizer`**: The visualizer is a new design in OpenMMLab 2.0 architecture. We use a
-visualizer instance in the runner to handle results & log visualization and save to different backends.
-See the [visualization tutorial](user_guides/visualization.md) for more details.
+New field **`visualizer`**: The visualizer is a new design in OpenMMLab 2.0 architecture. We use a visualizer instance in the runner to handle results & log visualization and save to different backends. See the [visualization tutorial](../user_guides/visualization.md) for more details.
 
-New field **`default_scope`**: The start point to search module for all registries. The `default_scope` in MMSegmentation is `mmseg`. See [the registry tutorial](https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/registry.md) for more details.
+New field **`default_scope`**: The start point to search module for all registries. The `default_scope` in MMSegmentation is `mmseg`. See [the registry tutorial](https://github.com/open-mmlab/mmengine/blob/main/docs/en/advanced_tutorials/registry.md) for more details.
diff --git a/docs/en/migration/package.md b/docs/en/migration/package.md
index c0aa1d6e31..728e9a9bb6 100644
--- a/docs/en/migration/package.md
+++ b/docs/en/migration/package.md
@@ -74,9 +74,8 @@ We moved registry implementations for all kinds of modules in MMSegmentation in
 
 ### `mmseg.apis`
 
-OpenMMLab 2.0 tries to support unified interface for multitasking of Computer Vision,
-and releases much stronger [`Runner`](https://github.com/open-mmlab/mmengine/blob/main/docs/en/design/runner.md),
-so MMSeg 1.x removed modules in `train.py` and `test.py` renamed `init_segmentor` to `init_model` and `inference_segmentor` to `inference_model`
+OpenMMLab 2.0 tries to support unified interface for multitasking of Computer Vision, and releases much stronger [`Runner`](https://github.com/open-mmlab/mmengine/blob/main/docs/en/design/runner.md), so MMSeg 1.x removed modules in `train.py` and `test.py` renamed `init_segmentor` to `init_model` and `inference_segmentor` to `inference_model`.
+
 Here is the changes of `mmseg.apis`:
 
 |       Function        | Changes                                         |
@@ -92,7 +91,7 @@ Here is the changes of `mmseg.apis`:
 
 ### `mmseg.datasets`
 
-OpenMMLab 2.0 defines the `BaseDataset` to function and interface of dataset, and MMSegmentation 1.x also follow this protocol and defines the `BaseSegDataset` inherited from `BaseDataset`. MMCV 2.x collects general data transforms for multiple tasks e.g. classification, detection, segmentation, so MMSegmentation 1.x uses these data transforms and removes them from mmseg.datasets
+OpenMMLab 2.0 defines the `BaseDataset` to function and interface of dataset, and MMSegmentation 1.x also follow this protocol and defines the `BaseSegDataset` inherited from `BaseDataset`. MMCV 2.x collects general data transforms for multiple tasks e.g. classification, detection, segmentation, so MMSegmentation 1.x uses these data transforms and removes them from mmseg.datasets.
 
 |   Packages/Modules    | Changes                                                                                     |
 | :-------------------: | :------------------------------------------------------------------------------------------ |
diff --git a/docs/zh_cn/migration.md b/docs/zh_cn/migration.md
deleted file mode 100644
index 3f19b26714..0000000000
--- a/docs/zh_cn/migration.md
+++ /dev/null
@@ -1,3 +0,0 @@
-# 迁移文档
-
-中文迁移文档在支持中，请先阅读[英文版迁移文档](../en/migration/)
diff --git a/docs/zh_cn/migration/index.rst b/docs/zh_cn/migration/index.rst
new file mode 100644
index 0000000000..854b9e61d0
--- /dev/null
+++ b/docs/zh_cn/migration/index.rst
@@ -0,0 +1,8 @@
+迁移
+***************
+
+.. toctree::
+    :maxdepth: 1
+
+    interface.md
+    package.md
diff --git a/docs/zh_cn/migration/interface.md b/docs/zh_cn/migration/interface.md
new file mode 100644
index 0000000000..a329ce38a8
--- /dev/null
+++ b/docs/zh_cn/migration/interface.md
@@ -0,0 +1,496 @@
+# 从 MMSegmentation 0.x 迁移
+
+## 引言
+
+本指南介绍了 MMSegmentation 0.x 和 MMSegmentation1.x 在行为和 API 方面的基本区别，以及这些如何都与您的迁移过程相关。
+
+## 新的依赖
+
+MMSegmentation 1.x 依赖于一些新的软件包，您可以准备一个新的干净环境，然后根据[安装教程](../get_started.md)重新安装。
+
+或手动安装以下软件包。
+
+1. [MMEngine](https://github.com/open-mmlab/mmengine)：MMEngine 是 OpenMMLab 2.0 架构的核心，我们将许多与计算机视觉无关的内容从 MMCV 拆分到 MMEngine 中。
+
+2. [MMCV](https://github.com/open-mmlab/mmcv)：OpenMMLab 的计算机视觉包。这不是一个新的依赖，但您需要将其升级到 **2.0.0rc1** 以上的版本。
+
+3. [MMClassification](https://github.com/open-mmlab/mmclassification)（可选）：OpenMMLab 的图像分类工具箱和基准。这不是一个新的依赖，但您需要将其升级到 **1.0.0rc0** 以上的版本。
+
+4. [MMDetection](https://github.com/open-mmlab/mmdetection)(可选): OpenMMLab 的目标检测工具箱和基准。这不是一个新的依赖，但您需要将其升级到 **3.0.0rc0** 以上的版本。
+
+## 启动训练
+
+OpenMMLab 2.0 的主要改进是发布了 MMEngine，它为启动训练任务的统一接口提供了通用且强大的执行器。
+
+与 MMSeg 0.x 相比，MMSeg 1.x 在 `tools/train.py` 中提供的命令行参数更少
+
+<table class="docutils">
+<tr>
+<td>功能</td>
+<td>原版</td>
+<td>新版</td>
+</tr>
+<tr>
+<td>加载预训练模型</td>
+<td>--load_from=$CHECKPOINT</td>
+<td>--cfg-options load_from=$CHECKPOINT</td>
+</tr>
+<tr>
+<td>从特定检查点恢复训练</td>
+<td>--resume-from=$CHECKPOINT</td>
+<td>--resume=$CHECKPOINT</td>
+</tr>
+<tr>
+<td>从最新的检查点恢复训练</td>
+<td>--auto-resume</td>
+<td>--resume='auto'</td>
+</tr>
+<tr>
+<td>培训练期间是否不评估检查点</td>
+<td>--no-validate</td>
+<td>--cfg-options val_cfg=None val_dataloader=None val_evaluator=None</td>
+</tr>
+<tr>
+<td>指定训练设备</td>
+<td>--gpu-id=$DEVICE_ID</td>
+<td>-</td>
+</tr>
+<tr>
+<td>是否为不同进程设置不同的种子</td>
+<td>--diff-seed</td>
+<td>--cfg-options randomness.diff_rank_seed=True</td>
+</tr>
+<td>是否为 CUDNN 后端设置确定性选项</td>
+<td>--deterministic</td>
+<td>--cfg-options randomness.deterministic=True</td>
+</table>
+
+## 配置文件
+
+### 模型设置
+
+`model.backend`、`model.neck`、`model.decode_head` 和 `model.loss` 字段没有更改。
+
+添加 `model.data_preprocessor` 字段以配置 `DataPreProcessor`，包括：
+
+- `mean`（Sequence，可选）：R、G、B 通道的像素平均值。默认为 None。
+
+- `std`（Sequence，可选）：R、G、B通道的像素标准差。默认为 None。
+
+- `size`（Sequence，可选）：固定的填充大小。
+
+- `size_divisor`（int，可选）：填充大小的除法因子。
+
+- `seg_pad_val`（float，可选）：分割图的填充值。默认值：255。
+
+- `padding_mode`（str）：填充类型。默认值：'constant'。
+
+  - constant：常量值填充，值由 pad_val 指定。
+
+- `bgr_to_rgb`（bool）：是否将图像从 BGR 转换为 RGB。默认为 False。
+
+- `rgb_to_bgr`（bool）：是否将图像从 RGB 转换为 BGR。默认为 False。
+
+**注：**
+有关详细信息，请参阅[模型文档](../advanced_guides/models.md)。
+
+### 数据集设置
+
+**data** 的更改：
+
+原版 `data` 字段被拆分为 `train_dataloader`、`val_dataloader` 和 `test_dataloader`。这允许我们以细粒度配置它们。例如，您可以在训练和测试期间指定不同的采样器和批次大小。
+`samples_per_gpu` 重命名为 `batch_size`。
+`workers_per_gpu` 重命名为 `num_workers`。
+
+<table class="docutils">
+<tr>
+<td>原版</td>
+<td>
+
+```python
+data = dict(
+    samples_per_gpu=4,
+    workers_per_gpu=4,
+    train=dict(...),
+    val=dict(...),
+    test=dict(...),
+)
+```
+
+</td>
+<tr>
+<td>新版</td>
+<td>
+
+```python
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    dataset=dict(...),
+    sampler=dict(type='DefaultSampler', shuffle=True)  # necessary
+)
+
+val_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    dataset=dict(...),
+    sampler=dict(type='DefaultSampler', shuffle=False)  # necessary
+)
+
+test_dataloader = val_dataloader
+```
+
+</td>
+</tr>
+</table>
+
+**流程**变更
+
+- 原始格式转换 **`ToTensor`**、**`ImageToTensor`**、**`Collect`** 组合为 [`PackSegInputs`](mmseg.datasets.transforms.PackSegInputs)
+- 我们不建议在数据集流程中执行 **`Normalize`** 和 **Pad**。请将其从流程中删除，并将其设置在 `data_preprocessor` 字段中。
+- MMSeg 1.x 中原始的 **`Resize`** 已更改为 **`RandomResize `**，输入参数 `img_scale` 重命名为 `scale`，`keep_ratio` 的默认值修改为 False。
+- 原始的 `test_pipeline` 将单尺度和多尺度测试结合在一起，在 MMSeg 1.x 中，我们将其分为 `test_pipeline` 和 `tta_pipeline`。
+
+**注：**
+我们将一些数据转换工作转移到数据预处理器中，如归一化，请参阅[文档](package.md)了解更多详细信息。
+
+训练流程
+
+<table class="docutils">
+<tr>
+<td>原版</td>
+<td>
+
+```python
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(type='Resize', img_scale=(2560, 640), ratio_range=(0.5, 2.0)),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
+]
+```
+
+</td>
+<tr>
+<td>新版</td>
+<td>
+
+```python
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(
+        type='RandomResize',
+        scale=(2560, 640),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+```
+
+</td>
+</tr>
+</table>
+
+测试流程
+
+<table class="docutils">
+<tr>
+<td>原版</td>
+<td>
+
+```python
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(2560, 640),
+        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+```
+
+</td>
+<tr>
+<td>新版</td>
+<td>
+
+```python
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2560, 640), keep_ratio=True),
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+```
+
+</td>
+</tr>
+</table>
+
+**`evaluation`** 中的更改：
+
+- **`evaluation`** 字段被拆分为 `val_evaluator` 和 `test_evaluator `。而且不再支持 `interval` 和 `save_best` 参数。
+  `interval` 已移动到 `train_cfg.val_interval`，`save_best` 已移动到 `default_hooks.checkpoint.save_best`。`pre_eval` 已删除。
+- `IoU` 已更改为 `IoUMetric`。
+
+<table class="docutils">
+<tr>
+<td>原版</td>
+<td>
+
+```python
+evaluation = dict(interval=2000, metric='mIoU', pre_eval=True)
+```
+
+</td>
+<tr>
+<td>新版</td>
+<td>
+
+```python
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator
+```
+
+</td>
+</tr>
+</table>
+
+### Optimizer 和 Schedule 设置
+
+**`optimizer`** 和 **`optimizer_config`** 中的更改：
+
+- 现在我们使用 `optim_wrapper` 字段来指定优化过程的所有配置。以及 `optimizer` 是 `optim_wrapper` 的一个子字段。
+- `paramwise_cfg` 也是 `optim_wrapper` 的一个子字段，以替代 `optimizer`。
+- `optimizer_config` 现在被删除，它的所有配置都被移动到 `optim_wrapper` 中。
+- `grad_clip` 重命名为 `clip_grad`。
+
+<table class="docutils">
+<tr>
+<td>原版</td>
+<td>
+
+```python
+optimizer = dict(type='AdamW', lr=0.0001, weight_decay=0.0005)
+optimizer_config = dict(grad_clip=dict(max_norm=1, norm_type=2))
+```
+
+</td>
+<tr>
+<td>新版</td>
+<td>
+
+```python
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='AdamW', lr=0.0001, weight_decay=0.0005),
+    clip_grad=dict(max_norm=1, norm_type=2))
+```
+
+</td>
+</tr>
+</table>
+
+**`lr_config`** 中的更改：
+
+- 我们将 `lr_config` 字段删除，并使用新的 `param_scheduler` 替代。
+- 我们删除了与 `warmup` 相关的参数，因为我们使用 scheduler 组合来实现该功能。
+
+新的 scheduler 组合机制非常灵活，您可以使用它来设计多种学习率/动量曲线。有关详细信息，请参见[教程](TODO)。
+
+<table class="docutils">
+<tr>
+<td>原版</td>
+<td>
+
+```python
+lr_config = dict(
+    policy='poly',
+    warmup='linear',
+    warmup_iters=1500,
+    warmup_ratio=1e-6,
+    power=1.0,
+    min_lr=0.0,
+    by_epoch=False)
+```
+
+</td>
+<tr>
+<td>新版</td>
+<td>
+
+```python
+param_scheduler = [
+    dict(
+        type='LinearLR', start_factor=1e-6, by_epoch=False, begin=0, end=1500),
+    dict(
+        type='PolyLR',
+        power=1.0,
+        begin=1500,
+        end=160000,
+        eta_min=0.0,
+        by_epoch=False,
+    )
+]
+```
+
+</td>
+</tr>
+</table>
+
+**`runner`** 中的更改：
+
+原版 `runner` 字段中的大多数配置被移动到 `train_cfg`、`val_cfg` 和 `test_cfg` 中，以在训练、验证和测试中配置 loop。
+
+<table class="docutils">
+<tr>
+<td>原版</td>
+<td>
+
+```python
+runner = dict(type='IterBasedRunner', max_iters=20000)
+```
+
+</td>
+<tr>
+<td>新版</td>
+<td>
+
+```python
+# The `val_interval` is the original `evaluation.interval`.
+train_cfg = dict(type='IterBasedTrainLoop', max_iters=20000, val_interval=2000)
+val_cfg = dict(type='ValLoop') # Use the default validation loop.
+test_cfg = dict(type='TestLoop') # Use the default test loop.
+```
+
+</td>
+</tr>
+</table>
+
+事实上，在 OpenMMLab 2.0 中，我们引入了 `Loop` 来控制训练、验证和测试中的行为。`Runner` 的功能也发生了变化。您可以在 [MMMEngine](https://github.com/open-mmlab/mmengine/) 的[执行器教程](https://github.com/open-mmlab/mmengine/blob/main/docs/zh_cn/design/runner.md) 中找到更多的详细信息。
+
+### 运行时设置
+
+**`checkpoint_config`** 和 **`log_config`** 中的更改：
+
+`checkpoint_config` 被移动到 `default_hooks.checkpoint` 中，`log_config` 被移动到 `default_hooks.logger` 中。
+并且我们将许多钩子设置从脚本代码移动到运行时配置的 `default_hooks` 字段中。
+
+```python
+default_hooks = dict(
+    # record the time of every iterations.
+    timer=dict(type='IterTimerHook'),
+
+    # print log every 50 iterations.
+    logger=dict(type='LoggerHook', interval=50, log_metric_by_epoch=False),
+
+    # enable the parameter scheduler.
+    param_scheduler=dict(type='ParamSchedulerHook'),
+
+    # save checkpoint every 2000 iterations.
+    checkpoint=dict(type='CheckpointHook', by_epoch=False, interval=2000),
+
+    # set sampler seed in distributed environment.
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+
+    # validation results visualization.
+    visualization=dict(type='SegVisualizationHook'))
+```
+
+此外，我们将原版 logger 拆分为 logger 和 visualizer。logger 用于记录信息，visualizer 用于在不同的后端显示 logger，如 terminal 和 TensorBoard。
+
+<table class="docutils">
+<tr>
+<td>原版</td>
+<td>
+
+```python
+log_config = dict(
+    interval=100,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        dict(type='TensorboardLoggerHook'),
+    ])
+```
+
+</td>
+<tr>
+<td>新版</td>
+<td>
+
+```python
+default_hooks = dict(
+    ...
+    logger=dict(type='LoggerHook', interval=100),
+)
+vis_backends = [dict(type='LocalVisBackend'),
+                dict(type='TensorboardVisBackend')]
+visualizer = dict(
+    type='SegLocalVisualizer', vis_backends=vis_backends, name='visualizer')
+```
+
+</td>
+</tr>
+</table>
+
+**`load_from`** 和 **`resume_from`** 中的更改：
+
+- 删除 `resume_from`。我们使用 `resume` 和 `load_from` 来替换它。
+  - 如果 `resume=True` 且 `load_from` 为 **not None**，则从 `load_from` 中的检查点恢复训练。
+  - 如果 `resume=True` 且 `load_from` 为 **None**，则尝试从工作目录中的最新检查点恢复。
+  - 如果 `resume=False` 且 `load_from` 为 **not None**，则只加载检查点，而不继续训练。
+  - 如果 `resume=False` 且 `load_from` 为 **None**，则不加载或恢复。
+
+**`dist_params`** 中的更改：`dist_params` 字段现在是 `env_cfg` 的子字段。并且 `env_cfg` 中还有一些新的配置。
+
+```python
+env_cfg = dict(
+    # whether to enable cudnn benchmark
+    cudnn_benchmark=False,
+
+    # set multi process parameters
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+
+    # set distributed parameters
+    dist_cfg=dict(backend='nccl'),
+)
+```
+
+**`workflow`** 的改动:`workflow` 相关功能被删除。
+
+新字段 **`visualizer`**：visualizer 是 OpenMMLab 2.0 体系结构中的新设计。我们在 runner 中使用 visualizer 实例来处理结果和日志可视化，并保存到不同的后端。更多详细信息，请参阅[可视化教程](../user_guides/visualization.md)。
+
+新字段 **`default_scope`**：搜索所有注册模块的起点。MMSegmentation 中的 `default_scope` 为 `mmseg`。请参见[注册器教程](https://github.com/open-mmlab/mmengine/blob/main/docs/zh_cn/advanced_tutorials/registry.md)了解更多详情。
diff --git a/docs/zh_cn/migration/package.md b/docs/zh_cn/migration/package.md
new file mode 100644
index 0000000000..d8d2245bed
--- /dev/null
+++ b/docs/zh_cn/migration/package.md
@@ -0,0 +1,113 @@
+#包结构更改
+
+本节包含您对 MMSeg 0.x 和 1.x 之间的变化感到好奇的内容。
+
+<table>
+<tr>
+<td>MMSegmentation 0.x</td>
+<td>MMSegmentation 1.x</td>
+</tr>
+<tr>
+<td>mmseg.api</td>
+<td>mmseg.api</td>
+</tr>
+<tr>
+<td bgcolor=#fcf7f7>- mmseg.core</td>
+<td bgcolor=#ecf4eb>+ mmseg.engine</td>
+</tr>
+<tr>
+<td>mmseg.datasets</td>
+<td>mmseg.datasets</td>
+</tr>
+<tr>
+<td>mmseg.models</td>
+<td>mmseg.models</td>
+</tr>
+<tr>
+<td bgcolor=#fcf7f7>- mmseg.ops</td>
+<td bgcolor=#ecf4eb>+ mmseg.structure</td>
+</tr>
+<tr>
+<td>mmseg.utils</td>
+<td>mmseg.utils</td>
+</tr>
+<tr>
+<td></td>
+<td bgcolor=#ecf4eb>+ mmseg.evaluation</td>
+</tr>
+<tr>
+<td></td>
+<td bgcolor=#ecf4eb>+ mmseg.registry</td>
+<tr>
+</table>
+
+## 已删除的包
+
+### `mmseg.core`
+
+在 OpenMMLab 2.0 中，`core` 包已被删除。`core` 的 `hooks` 和 `optimizers` 被移动到了 `mmseg.engine` 中，而 `core` 中的 `evaluation` 目前是 mmseg.evaluation。
+
+## `mmseg.ops`
+
+`ops` 包包含 `encoding` 和 `wrappers`，它们被移到了 `mmseg.models.utils` 中。
+
+## 增加的包
+
+### `mmseg.engine`
+
+OpenMMLab 2.0 增加了一个新的深度学习训练基础库 MMEngine。它是所有 OpenMMLab 代码库的训练引擎。
+mmseg 的 `engine` 包是一些用于语义分割任务的定制模块，如 `SegVisualizationHook` 用于可视化分割掩膜。
+
+### `mmseg.structure`
+
+在 OpenMMLab 2.0 中，我们为计算机视觉任务设计了数据结构，在 mmseg 中，我们在 `structure` 包中实现了 `SegDataSample`。
+
+### `mmseg.evaluation`
+
+我们将所有评估指标都移动到了 `mmseg.evaluation` 中。
+
+### `mmseg.registry`
+
+我们将 MMSegmentation 中所有类型模块的注册实现移动到 `mmseg.registry` 中。
+
+## 修改的包
+
+### `mmseg.apis`
+
+OpenMMLab 2.0 尝试支持计算机视觉的多任务统一接口，并发布了更强的 [`Runner`](https://github.com/open-mmlab/mmengine/blob/main/docs/zh_cn/design/runner.md)，因此 MMSeg 1.x 删除了 `train.py` 和 `test.py` 中的模块，并将 `init_segmentor` 重命名为 `init_model`，将 `inference_segmentor` 重命名为 `inference_model`。
+
+以下是 `mmseg.apis` 的更改：
+
+|         函数          | 变化                                           |
+| :-------------------: | :--------------------------------------------- |
+|   `init_segmentor`    | 重命名为 `init_model`                          |
+| `inference_segmentor` | 重命名为 `inference_model`                     |
+| `show_result_pyplot`  | 基于 `SegLocalVisualizer` 实现                 |
+|     `train_model`     | 删除，使用 `runner.train` 训练。               |
+|   `multi_gpu_test`    | 删除，使用 `runner.test` 测试。                |
+|   `single_gpu_test`   | 删除，使用 `runner.test` 测试。                |
+|   `set_random_seed`   | 删除，使用 `mmengine.runner.set_random_seed`。 |
+|  `init_random_seed`   | 删除，使用 `mmengine.dist.sync_random_seed`。  |
+
+### `mmseg.datasets`
+
+OpenMMLab 2.0 将 `BaseDataset` 定义为数据集的函数和接口，MMSegmentation 1.x 也遵循此协议，并定义了从 `BaseDataset` 继承的 `BaseSegDataset`。MMCV 2.x 收集多种任务的通用数据转换，例如分类、检测、分割，因此 MMSegmentation 1.x 使用这些数据转换并将其从 mmseg.dataset 中删除。
+
+|        包/模块        | 更改                                                                                 |
+| :-------------------: | :----------------------------------------------------------------------------------- |
+|   `mmseg.pipelines`   | 移动到 `mmcv.transforms` 中                                                          |
+|    `mmseg.sampler`    | 移动到 `mmengine.dataset.sampler` 中                                                 |
+|    `CustomDataset`    | 重命名为 `BaseSegDataset` 并从 MMEngine 中的 `BaseDataset` 继承                      |
+| `DefaultFormatBundle` | 替换为 `PackSegInputs`                                                               |
+|  `LoadImageFromFile`  | 移动到 `mmcv.transforms.LoadImageFromFile` 中                                        |
+|   `LoadAnnotations`   | 移动到 `mmcv.transforms.LoadAnnotations` 中                                          |
+|       `Resize`        | 移动到 `mmcv.transforms` 中并拆分为 `Resize`，`RandomResize` 和 `RandomChoiceResize` |
+|     `RandomFlip`      | 移动到 `mmcv.transforms.RandomFlip` 中                                               |
+|         `Pad`         | 移动到 `mmcv.transforms.Pad` 中                                                      |
+|      `Normalize`      | 移动到 `mmcv.transforms.Normalize` 中                                                |
+|       `Compose`       | 移动到 `mmcv.transforms.Compose` 中                                                  |
+|    `ImageToTensor`    | 移动到 `mmcv.transforms.ImageToTensor` 中                                            |
+
+### `mmseg.models`
+
+`models` 没有太大变化，只是从以前的 `mmseg.ops` 中添加了 `encoding` 和 `wrappers`

From 6ba4696648c7bef22ccfcd19eb7031925e982f82 Mon Sep 17 00:00:00 2001
From: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
Date: Tue, 14 Mar 2023 23:14:41 +0800
Subject: [PATCH 11/32] [Enhancement] Support input gt seg map is not 2D
 (#2739)

Thanks for your contribution and we appreciate it a lot. The following
instructions would make your pull request more healthy and more easily
get feedback. If you do not understand some items, don't worry, just
make the pull request and seek help from maintainers.

## Motivation

fix #2593

## Modification

1. Only when gt seg map is 2D, extend its shape to 3D PixelData
2. If seg map is not 2D, we raised warning for users.

---------

Co-authored-by: xiexinch <xiexinch@outlook.com>
---
 mmseg/datasets/transforms/formatting.py | 15 ++++++++++++---
 tests/test_datasets/test_formatting.py  |  5 +++++
 2 files changed, 17 insertions(+), 3 deletions(-)

diff --git a/mmseg/datasets/transforms/formatting.py b/mmseg/datasets/transforms/formatting.py
index 4391161dfd..57cda9b10e 100644
--- a/mmseg/datasets/transforms/formatting.py
+++ b/mmseg/datasets/transforms/formatting.py
@@ -1,4 +1,6 @@
 # Copyright (c) OpenMMLab. All rights reserved.
+import warnings
+
 import numpy as np
 from mmcv.transforms import to_tensor
 from mmcv.transforms.base import BaseTransform
@@ -72,9 +74,16 @@ def transform(self, results: dict) -> dict:
 
         data_sample = SegDataSample()
         if 'gt_seg_map' in results:
-            gt_sem_seg_data = dict(
-                data=to_tensor(results['gt_seg_map'][None,
-                                                     ...].astype(np.int64)))
+            if results['gt_seg_map'].shape == 2:
+                data = to_tensor(results['gt_seg_map'][None,
+                                                       ...].astype(np.int64))
+            else:
+                warnings.warn('Please pay attention your ground truth '
+                              'segmentation map, usually the segentation '
+                              'map is 2D, but got '
+                              f'{results["gt_seg_map"].shape}')
+                data = to_tensor(results['gt_seg_map'].astype(np.int64))
+            gt_sem_seg_data = dict(data=data)
             data_sample.gt_sem_seg = PixelData(**gt_sem_seg_data)
 
         if 'gt_edge_map' in results:
diff --git a/tests/test_datasets/test_formatting.py b/tests/test_datasets/test_formatting.py
index 4babaad269..51fd90d048 100644
--- a/tests/test_datasets/test_formatting.py
+++ b/tests/test_datasets/test_formatting.py
@@ -45,6 +45,11 @@ def test_transform(self):
                               BaseDataElement)
         self.assertEqual(results['data_samples'].ori_shape,
                          results['data_samples'].gt_sem_seg.shape)
+        results = copy.deepcopy(self.results)
+        results['gt_seg_map'] = np.random.rand(3, 300, 400)
+        results = transform(results)
+        self.assertEqual(results['data_samples'].ori_shape,
+                         results['data_samples'].gt_sem_seg.shape)
 
     def test_repr(self):
         transform = PackSegInputs(meta_keys=self.meta_keys)

From 447a398c24f76be71b8851183a347ff181e5a1c1 Mon Sep 17 00:00:00 2001
From: Junhwa Song <ethan9867@gmail.com>
Date: Wed, 15 Mar 2023 00:56:40 +0900
Subject: [PATCH 12/32] [Typo] Change indexes to indices (#2747)

## Modification

I just replaced the `indexes` variable name with `indices` for naming
consistency.
---
 mmseg/datasets/dataset_wrappers.py                        | 8 ++++----
 mmseg/datasets/transforms/transforms.py                   | 8 ++++----
 .../tools/dataset_converters/mapillary.py                 | 2 +-
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/mmseg/datasets/dataset_wrappers.py b/mmseg/datasets/dataset_wrappers.py
index 933eb50d99..082c116ff4 100644
--- a/mmseg/datasets/dataset_wrappers.py
+++ b/mmseg/datasets/dataset_wrappers.py
@@ -106,11 +106,11 @@ def __getitem__(self, idx):
                 continue
 
             if hasattr(transform, 'get_indices'):
-                indexes = transform.get_indices(self.dataset)
-                if not isinstance(indexes, collections.abc.Sequence):
-                    indexes = [indexes]
+                indices = transform.get_indices(self.dataset)
+                if not isinstance(indices, collections.abc.Sequence):
+                    indices = [indices]
                 mix_results = [
-                    copy.deepcopy(self.dataset[index]) for index in indexes
+                    copy.deepcopy(self.dataset[index]) for index in indices
                 ]
                 results['mix_results'] = mix_results
 
diff --git a/mmseg/datasets/transforms/transforms.py b/mmseg/datasets/transforms/transforms.py
index ef4e78dd8c..4f5316026f 100644
--- a/mmseg/datasets/transforms/transforms.py
+++ b/mmseg/datasets/transforms/transforms.py
@@ -1029,17 +1029,17 @@ def transform(self, results: dict) -> dict:
         return results
 
     def get_indices(self, dataset: MultiImageMixDataset) -> list:
-        """Call function to collect indexes.
+        """Call function to collect indices.
 
         Args:
             dataset (:obj:`MultiImageMixDataset`): The dataset.
 
         Returns:
-            list: indexes.
+            list: indices.
         """
 
-        indexes = [random.randint(0, len(dataset)) for _ in range(3)]
-        return indexes
+        indices = [random.randint(0, len(dataset)) for _ in range(3)]
+        return indices
 
     @cache_randomness
     def generate_mosaic_center(self):
diff --git a/projects/mapillary_dataset/tools/dataset_converters/mapillary.py b/projects/mapillary_dataset/tools/dataset_converters/mapillary.py
index 3ccb2d67b3..a881564cab 100644
--- a/projects/mapillary_dataset/tools/dataset_converters/mapillary.py
+++ b/projects/mapillary_dataset/tools/dataset_converters/mapillary.py
@@ -106,7 +106,7 @@ def mapillary_colormap2label(colormap: np.ndarray) -> list:
 
     Returns:
         list: values are mask labels,
-              indexes are  palette's convert results.、
+              indices are palette's convert results.
     """
     colormap2label = np.zeros(256**3, dtype=np.longlong)
     for i, colormap_ in enumerate(colormap):

From 8c89ff3dd1409445858399cc346ff2518ddbe5df Mon Sep 17 00:00:00 2001
From: Tianlong Ai <50650583+AI-Tianlong@users.noreply.github.com>
Date: Wed, 15 Mar 2023 14:44:38 +0800
Subject: [PATCH 13/32] [Datasets] Add Mapillary Vistas Datasets to MMSeg Core
 Package. (#2576)

## [Datasets] Add Mapillary Vistas Datasets to MMSeg Core Package .
## Motivation
Add Mapillary Vistas Datasets to core package.
Old PR #2484

## Modification
- Add Mapillary Vistas Datasets to core package.
- Delete `tools/datasets_convert/mapillary.py` , dataset does't need
converting.
- Add `schedule_240k.py`  config.
- Add configs files.
  ```none
  deeplabv3plus_r101-d8_4xb2-240k_mapillay_v1-512x1024.py
  deeplabv3plus_r101-d8_4xb2-240k_mapillay_v2-512x1024.py
  maskformer_swin-s_4xb2-240k_mapillary_v1-512x1024.py
  maskformer_swin-s_4xb2-240k_mapillary_v2-512x1024.py
  maskformer_r101-d8_4xb2-240k_mapillary_v1-512x1024.py
  maskformer_r101-d8_4xb2-240k_mapillary_v2-512x1024.py
  pspnet_r101-d8_4xb2-240k_mapillay_v1-512x1024.py
  pspnet_r101-d8_4xb2-240k_mapillay_v2-512x1024.py
  ```
- Synchronized changes to `projects/mapillary_datasets`

---------

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
Co-authored-by: xiexinch <xiexinch@outlook.com>
---
 README.md                                     |   1 +
 README_zh-CN.md                               |   1 +
 .../_base_/datasets/mapillary_v1.py           |   7 +-
 configs/_base_/datasets/mapillary_v1_65.py    |  37 +++
 .../_base_/datasets/mapillary_v2.py           |   7 +-
 configs/_base_/schedules/schedule_240k.py     |  25 ++
 configs/deeplabv3plus/README.md               |   6 +
 configs/deeplabv3plus/deeplabv3plus.yml       |  22 ++
 ...0-d8_4xb2-300k_mapillay_v1_65-1280x1280.py |  58 ++++
 docs/en/user_guides/2_dataset_prepare.md      |  74 +++++
 mmseg/datasets/__init__.py                    |   4 +-
 .../datasets/mapillary.py                     |  66 +++-
 mmseg/utils/class_names.py                    | 124 +++++++-
 projects/mapillary_dataset/README.md          |  23 +-
 .../configs/_base_/datasets/mapillary_v1.py   |  68 ++++
 .../_base_/datasets/mapillary_v1_65.py        |  37 +++
 .../configs/_base_/datasets/mapillary_v2.py   |  68 ++++
 ...lus_r101-d8_4xb2-240k_mapillay-512x1024.py | 103 ------
 ..._r101-d8_4xb2-240k_mapillay_v1-512x1024.py |  17 +
 ..._r101-d8_4xb2-240k_mapillay_v2-512x1024.py |  16 +
 ..._r101-d8_4xb2-240k_mapillay_v1-512x1024.py |  16 +
 ..._r101-d8_4xb2-240k_mapillay_v2-512x1024.py |  16 +
 .../docs/en/user_guides/2_dataset_prepare.md  | 300 +++++++++++++-----
 .../mmseg/datasets/mapillary.py               | 177 +++++++++++
 .../mmseg/datasets/mapillary_v1_2.py          |  65 ----
 .../tools/dataset_converters/mapillary.py     | 245 --------------
 .../images/__CRyFzoDOXn6unQ6a3DnQ.jpg         | Bin 0 -> 1227776 bytes
 .../v1.2/__CRyFzoDOXn6unQ6a3DnQ.png           | Bin 0 -> 75488 bytes
 .../v2.0/__CRyFzoDOXn6unQ6a3DnQ.png           | Bin 0 -> 75316 bytes
 tests/test_datasets/test_dataset.py           |  24 +-
 30 files changed, 1089 insertions(+), 518 deletions(-)
 rename projects/mapillary_dataset/configs/_base_/datasets/mapillary_v1_2.py => configs/_base_/datasets/mapillary_v1.py (91%)
 create mode 100644 configs/_base_/datasets/mapillary_v1_65.py
 rename projects/mapillary_dataset/configs/_base_/datasets/mapillary_v2_0.py => configs/_base_/datasets/mapillary_v2.py (91%)
 create mode 100644 configs/_base_/schedules/schedule_240k.py
 create mode 100644 configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280.py
 rename projects/mapillary_dataset/mmseg/datasets/mapillary_v2_0.py => mmseg/datasets/mapillary.py (66%)
 create mode 100644 projects/mapillary_dataset/configs/_base_/datasets/mapillary_v1.py
 create mode 100644 projects/mapillary_dataset/configs/_base_/datasets/mapillary_v1_65.py
 create mode 100644 projects/mapillary_dataset/configs/_base_/datasets/mapillary_v2.py
 delete mode 100644 projects/mapillary_dataset/configs/deeplabv3plus_r101-d8_4xb2-240k_mapillay-512x1024.py
 create mode 100644 projects/mapillary_dataset/configs/deeplabv3plus_r101-d8_4xb2-240k_mapillay_v1-512x1024.py
 create mode 100644 projects/mapillary_dataset/configs/deeplabv3plus_r101-d8_4xb2-240k_mapillay_v2-512x1024.py
 create mode 100644 projects/mapillary_dataset/configs/pspnet_r101-d8_4xb2-240k_mapillay_v1-512x1024.py
 create mode 100644 projects/mapillary_dataset/configs/pspnet_r101-d8_4xb2-240k_mapillay_v2-512x1024.py
 create mode 100644 projects/mapillary_dataset/mmseg/datasets/mapillary.py
 delete mode 100644 projects/mapillary_dataset/mmseg/datasets/mapillary_v1_2.py
 delete mode 100644 projects/mapillary_dataset/tools/dataset_converters/mapillary.py
 create mode 100644 tests/data/pseudo_mapillary_dataset/images/__CRyFzoDOXn6unQ6a3DnQ.jpg
 create mode 100644 tests/data/pseudo_mapillary_dataset/v1.2/__CRyFzoDOXn6unQ6a3DnQ.png
 create mode 100644 tests/data/pseudo_mapillary_dataset/v2.0/__CRyFzoDOXn6unQ6a3DnQ.png

diff --git a/README.md b/README.md
index 9b4a580f39..52eda092c8 100644
--- a/README.md
+++ b/README.md
@@ -181,6 +181,7 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
 - [x] [Potsdam](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/en/user_guides/2_dataset_prepare.md#isprs-potsdam)
 - [x] [Vaihingen](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/en/user_guides/2_dataset_prepare.md#isprs-vaihingen)
 - [x] [iSAID](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/en/user_guides/2_dataset_prepare.md#isaid)
+- [x] [Mapillary Vistas](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/en/user_guides/2_dataset_prepare.md#mapillary-vistas-datasets)
 
 </details>
 
diff --git a/README_zh-CN.md b/README_zh-CN.md
index f7c3b0b18e..167ecbdc40 100644
--- a/README_zh-CN.md
+++ b/README_zh-CN.md
@@ -162,6 +162,7 @@ MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 O
 - [x] [Potsdam](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/zh_cn/dataset_prepare.md#isprs-potsdam)
 - [x] [Vaihingen](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/zh_cn/dataset_prepare.md#isprs-vaihingen)
 - [x] [iSAID](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/zh_cn/dataset_prepare.md#isaid)
+- [x] [Mapillary Vistas](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/en/user_guides/2_dataset_prepare.md#mapillary-vistas-datasets)
 
 </details>
 
diff --git a/projects/mapillary_dataset/configs/_base_/datasets/mapillary_v1_2.py b/configs/_base_/datasets/mapillary_v1.py
similarity index 91%
rename from projects/mapillary_dataset/configs/_base_/datasets/mapillary_v1_2.py
rename to configs/_base_/datasets/mapillary_v1.py
index a0e7d14b52..611aa4741b 100644
--- a/projects/mapillary_dataset/configs/_base_/datasets/mapillary_v1_2.py
+++ b/configs/_base_/datasets/mapillary_v1.py
@@ -1,5 +1,5 @@
 # dataset settings
-dataset_type = 'MapillaryDataset_v1_2'
+dataset_type = 'MapillaryDataset_v1'
 data_root = 'data/mapillary/'
 crop_size = (512, 1024)
 train_pipeline = [
@@ -48,8 +48,7 @@
         type=dataset_type,
         data_root=data_root,
         data_prefix=dict(
-            img_path='training/images',
-            seg_map_path='training/v1.2/labels_mask'),
+            img_path='training/images', seg_map_path='training/v1.2/labels'),
         pipeline=train_pipeline))
 val_dataloader = dict(
     batch_size=1,
@@ -61,7 +60,7 @@
         data_root=data_root,
         data_prefix=dict(
             img_path='validation/images',
-            seg_map_path='validation/v1.2/labels_mask'),
+            seg_map_path='validation/v1.2/labels'),
         pipeline=test_pipeline))
 test_dataloader = val_dataloader
 
diff --git a/configs/_base_/datasets/mapillary_v1_65.py b/configs/_base_/datasets/mapillary_v1_65.py
new file mode 100644
index 0000000000..f594f37333
--- /dev/null
+++ b/configs/_base_/datasets/mapillary_v1_65.py
@@ -0,0 +1,37 @@
+# dataset settings
+_base_ = './mapillary_v1.py'
+metainfo = dict(
+    classes=('Bird', 'Ground Animal', 'Curb', 'Fence', 'Guard Rail', 'Barrier',
+             'Wall', 'Bike Lane', 'Crosswalk - Plain', 'Curb Cut', 'Parking',
+             'Pedestrian Area', 'Rail Track', 'Road', 'Service Lane',
+             'Sidewalk', 'Bridge', 'Building', 'Tunnel', 'Person', 'Bicyclist',
+             'Motorcyclist', 'Other Rider', 'Lane Marking - Crosswalk',
+             'Lane Marking - General', 'Mountain', 'Sand', 'Sky', 'Snow',
+             'Terrain', 'Vegetation', 'Water', 'Banner', 'Bench', 'Bike Rack',
+             'Billboard', 'Catch Basin', 'CCTV Camera', 'Fire Hydrant',
+             'Junction Box', 'Mailbox', 'Manhole', 'Phone Booth', 'Pothole',
+             'Street Light', 'Pole', 'Traffic Sign Frame', 'Utility Pole',
+             'Traffic Light', 'Traffic Sign (Back)', 'Traffic Sign (Front)',
+             'Trash Can', 'Bicycle', 'Boat', 'Bus', 'Car', 'Caravan',
+             'Motorcycle', 'On Rails', 'Other Vehicle', 'Trailer', 'Truck',
+             'Wheeled Slow', 'Car Mount', 'Ego Vehicle'),
+    palette=[[165, 42, 42], [0, 192, 0], [196, 196, 196], [190, 153, 153],
+             [180, 165, 180], [90, 120, 150], [102, 102, 156], [128, 64, 255],
+             [140, 140, 200], [170, 170, 170], [250, 170, 160], [96, 96, 96],
+             [230, 150, 140], [128, 64, 128], [110, 110, 110], [244, 35, 232],
+             [150, 100, 100], [70, 70, 70], [150, 120, 90], [220, 20, 60],
+             [255, 0, 0], [255, 0, 100], [255, 0, 200], [200, 128, 128],
+             [255, 255, 255], [64, 170, 64], [230, 160, 50], [70, 130, 180],
+             [190, 255, 255], [152, 251, 152], [107, 142, 35], [0, 170, 30],
+             [255, 255, 128], [250, 0, 30], [100, 140, 180], [220, 220, 220],
+             [220, 128, 128], [222, 40, 40], [100, 170, 30], [40, 40, 40],
+             [33, 33, 33], [100, 128, 160], [142, 0, 0], [70, 100, 150],
+             [210, 170, 100], [153, 153, 153], [128, 128, 128], [0, 0, 80],
+             [250, 170, 30], [192, 192, 192], [220, 220, 0], [140, 140, 20],
+             [119, 11, 32], [150, 0, 255], [0, 60, 100], [0, 0, 142],
+             [0, 0, 90], [0, 0, 230], [0, 80, 100], [128, 64, 64], [0, 0, 110],
+             [0, 0, 70], [0, 0, 192], [32, 32, 32], [120, 10, 10]])
+
+train_dataloader = dict(dataset=dict(metainfo=metainfo))
+val_dataloader = dict(dataset=dict(metainfo=metainfo))
+test_dataloader = val_dataloader
diff --git a/projects/mapillary_dataset/configs/_base_/datasets/mapillary_v2_0.py b/configs/_base_/datasets/mapillary_v2.py
similarity index 91%
rename from projects/mapillary_dataset/configs/_base_/datasets/mapillary_v2_0.py
rename to configs/_base_/datasets/mapillary_v2.py
index 7332d43fad..7cb7a958e5 100644
--- a/projects/mapillary_dataset/configs/_base_/datasets/mapillary_v2_0.py
+++ b/configs/_base_/datasets/mapillary_v2.py
@@ -1,5 +1,5 @@
 # dataset settings
-dataset_type = 'MapillaryDataset_v2_0'
+dataset_type = 'MapillaryDataset_v2'
 data_root = 'data/mapillary/'
 crop_size = (512, 1024)
 train_pipeline = [
@@ -48,8 +48,7 @@
         type=dataset_type,
         data_root=data_root,
         data_prefix=dict(
-            img_path='training/images',
-            seg_map_path='training/v2.0/labels_mask'),
+            img_path='training/images', seg_map_path='training/v2.0/labels'),
         pipeline=train_pipeline))
 val_dataloader = dict(
     batch_size=1,
@@ -61,7 +60,7 @@
         data_root=data_root,
         data_prefix=dict(
             img_path='validation/images',
-            seg_map_path='validation/v2.0/labels_mask'),
+            seg_map_path='validation/v2.0/labels'),
         pipeline=test_pipeline))
 test_dataloader = val_dataloader
 
diff --git a/configs/_base_/schedules/schedule_240k.py b/configs/_base_/schedules/schedule_240k.py
new file mode 100644
index 0000000000..feb2ce9637
--- /dev/null
+++ b/configs/_base_/schedules/schedule_240k.py
@@ -0,0 +1,25 @@
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer, clip_grad=None)
+# learning policy
+param_scheduler = [
+    dict(
+        type='PolyLR',
+        eta_min=1e-4,
+        power=0.9,
+        begin=0,
+        end=240000,
+        by_epoch=False)
+]
+# training schedule for 240k
+train_cfg = dict(
+    type='IterBasedTrainLoop', max_iters=240000, val_interval=24000)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+default_hooks = dict(
+    timer=dict(type='IterTimerHook'),
+    logger=dict(type='LoggerHook', interval=50, log_metric_by_epoch=False),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    checkpoint=dict(type='CheckpointHook', by_epoch=False, interval=24000),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    visualization=dict(type='SegVisualizationHook'))
diff --git a/configs/deeplabv3plus/README.md b/configs/deeplabv3plus/README.md
index b3d3ce7678..f60f547391 100644
--- a/configs/deeplabv3plus/README.md
+++ b/configs/deeplabv3plus/README.md
@@ -124,6 +124,12 @@ Spatial pyramid pooling module or encode-decoder structure are used in deep neur
 | DeepLabV3+ | R-18-D8  | 896x896   |   80000 | 6.19     | 24.81          | 61.35 |         62.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid_20220110_180526-7059991d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid_20220110_180526.log.json) |
 | DeepLabV3+ | R-50-D8  | 896x896   |   80000 | 21.45    | 8.42           | 67.06 |         68.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid_20220110_180526-598be439.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid_20220110_180526.log.json) |
 
+### Mapillary Vistas v1.2
+
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                               | download                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3+ | R-50-D8  | 1280x1280 |  300000 | 24.04    | 17.92          | A100   | 47.35 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280_20230301_110504-655f8e43.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280_20230301_110504.json) |
+
 Note:
 
 - `D-8`/`D-16` here corresponding to the output stride 8/16 setting for DeepLab series.
diff --git a/configs/deeplabv3plus/deeplabv3plus.yml b/configs/deeplabv3plus/deeplabv3plus.yml
index 755c1fd4be..949cbcecc0 100644
--- a/configs/deeplabv3plus/deeplabv3plus.yml
+++ b/configs/deeplabv3plus/deeplabv3plus.yml
@@ -11,6 +11,7 @@ Collections:
     - Potsdam
     - Vaihingen
     - iSAID
+    - Mapillary Vistas v1.2
   Paper:
     URL: https://arxiv.org/abs/1802.02611
     Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
@@ -848,3 +849,24 @@ Models:
       mIoU(ms+flip): 68.02
   Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_isaid-896x896.py
   Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid_20220110_180526-598be439.pth
+- Name: deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280
+  In Collection: DeepLabV3+
+  Metadata:
+    backbone: R-50-D8
+    crop size: (1280,1280)
+    lr schd: 300000
+    inference time (ms/im):
+    - value: 55.8
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (1280,1280)
+    Training Memory (GB): 24.04
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: Mapillary Vistas v1.2
+    Metrics:
+      mIoU: 47.35
+  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280_20230301_110504-655f8e43.pth
diff --git a/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280.py b/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280.py
new file mode 100644
index 0000000000..133c45ae1d
--- /dev/null
+++ b/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280.py
@@ -0,0 +1,58 @@
+_base_ = [
+    '../_base_/models/deeplabv3plus_r50-d8.py',
+    '../_base_/datasets/mapillary_v1_65.py',
+    '../_base_/default_runtime.py',
+]
+
+crop_size = (1280, 1280)
+data_preprocessor = dict(size=crop_size)
+model = dict(
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(depth=50),
+    decode_head=dict(num_classes=65),
+    auxiliary_head=dict(num_classes=65))
+
+iters = 300000
+# optimizer
+optimizer = dict(
+    type='AdamW', lr=0.0001, betas=(0.9, 0.999), weight_decay=0.0001)
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=optimizer,
+    clip_grad=dict(max_norm=0.01, norm_type=2),
+    paramwise_cfg=dict(
+        custom_keys={'backbone': dict(lr_mult=0.1, decay_mult=1.0)}))
+param_scheduler = [
+    dict(
+        type='PolyLR',
+        eta_min=0,
+        power=0.9,
+        begin=0,
+        end=iters,
+        by_epoch=False)
+]
+
+# training schedule for 300k
+train_cfg = dict(
+    type='IterBasedTrainLoop', max_iters=iters, val_interval=iters // 10)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+
+default_hooks = dict(
+    timer=dict(type='IterTimerHook'),
+    logger=dict(type='LoggerHook', interval=50, log_metric_by_epoch=False),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    checkpoint=dict(
+        type='CheckpointHook', by_epoch=False, interval=iters // 10),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    visualization=dict(type='SegVisualizationHook'))
+
+train_dataloader = dict(batch_size=2)
+
+# Default setting for scaling LR automatically
+#   - `enable` means enable scaling LR automatically
+#       or not by default.
+#   - `base_batch_size` = (4 GPUs) x (2 samples per GPU).
+auto_scale_lr = dict(enable=False, base_batch_size=8)
diff --git a/docs/en/user_guides/2_dataset_prepare.md b/docs/en/user_guides/2_dataset_prepare.md
index 5d36061d89..6c81d60f41 100644
--- a/docs/en/user_guides/2_dataset_prepare.md
+++ b/docs/en/user_guides/2_dataset_prepare.md
@@ -154,6 +154,29 @@ mmsegmentation
 │   │   │   ├── training
 │   │   │   ├── validation
 │   │   │   ├── test
+│   ├── mapillary
+│   │   ├── training
+│   │   │   ├── images
+│   │   │   ├── v1.2
+|   │   │   │   ├── instances
+|   │   │   │   ├── labels
+|   │   │   │   └── panoptic
+│   │   │   ├── v2.0
+|   │   │   │   ├── instances
+|   │   │   │   ├── labels
+|   │   │   │   ├── panoptic
+|   │   │   │   └── polygons
+│   │   ├── validation
+│   │   │   ├── images
+|   │   │   ├── v1.2
+|   │   │   │   ├── instances
+|   │   │   │   ├── labels
+|   │   │   │   └── panoptic
+│   │   │   ├── v2.0
+|   │   │   │   ├── instances
+|   │   │   │   ├── labels
+|   │   │   │   ├── panoptic
+|   │   │   │   └── polygons
 ```
 
 ### Cityscapes
@@ -551,3 +574,54 @@ The script will make directory structure below:
 ```
 
 It includes 400 images for training, 400 images for validation and 400 images for testing which is the same as REFUGE 2018 dataset.
+
+## Mapillary Vistas Datasets
+
+- The dataset could be download [here](https://www.mapillary.com/dataset/vistas) after registration.
+
+- Mapillary Vistas Dataset use 8-bit with color-palette to store labels. No conversion operation is required.
+
+- Assumption you have put the dataset zip file in `mmsegmentation/data/mapillary`
+
+- Please run the following commands to unzip dataset.
+
+  ```bash
+  cd data/mapillary
+  unzip An-ZjB1Zm61yAZG0ozTymz8I8NqI4x0MrYrh26dq7kPgfu8vf9ImrdaOAVOFYbJ2pNAgUnVGBmbue9lTgdBOb5BbKXIpFs0fpYWqACbrQDChAA2fdX0zS9PcHu7fY8c-FOvyBVxPNYNFQuM.zip
+  ```
+
+- After unzip, you will get Mapillary Vistas Dataset like this structure. Semantic segmentation mask labels in `labels` folder.
+
+  ```none
+  mmsegmentation
+  ├── mmseg
+  ├── tools
+  ├── configs
+  ├── data
+  │   ├── mapillary
+  │   │   ├── training
+  │   │   │   ├── images
+  │   │   │   ├── v1.2
+  |   │   │   │   ├── instances
+  |   │   │   │   ├── labels
+  |   │   │   │   └── panoptic
+  │   │   │   ├── v2.0
+  |   │   │   │   ├── instances
+  |   │   │   │   ├── labels
+  |   │   │   │   ├── panoptic
+  |   │   │   │   └── polygons
+  │   │   ├── validation
+  │   │   │   ├── images
+  |   │   │   ├── v1.2
+  |   │   │   │   ├── instances
+  |   │   │   │   ├── labels
+  |   │   │   │   └── panoptic
+  │   │   │   ├── v2.0
+  |   │   │   │   ├── instances
+  |   │   │   │   ├── labels
+  |   │   │   │   ├── panoptic
+  |   │   │   │   └── polygons
+  ```
+
+- You could set Datasets version with `MapillaryDataset_v1` and `MapillaryDataset_v2` in your configs.
+  View the Mapillary Vistas Datasets config file here [V1.2](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/datasets/mapillary_v1.py) and  [V2.0](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/datasets/mapillary_v2.py)
diff --git a/mmseg/datasets/__init__.py b/mmseg/datasets/__init__.py
index 0dd19ee312..a90d53c88e 100644
--- a/mmseg/datasets/__init__.py
+++ b/mmseg/datasets/__init__.py
@@ -14,6 +14,7 @@
 from .isprs import ISPRSDataset
 from .lip import LIPDataset
 from .loveda import LoveDADataset
+from .mapillary import MapillaryDataset_v1, MapillaryDataset_v2
 from .night_driving import NightDrivingDataset
 from .pascal_context import PascalContextDataset, PascalContextDataset59
 from .potsdam import PotsdamDataset
@@ -49,5 +50,6 @@
     'DecathlonDataset', 'LIPDataset', 'ResizeShortestEdge',
     'BioMedicalGaussianNoise', 'BioMedicalGaussianBlur',
     'BioMedicalRandomGamma', 'BioMedical3DPad', 'RandomRotFlip',
-    'SynapseDataset', 'REFUGEDataset'
+    'SynapseDataset', 'REFUGEDataset', 'MapillaryDataset_v1',
+    'MapillaryDataset_v2'
 ]
diff --git a/projects/mapillary_dataset/mmseg/datasets/mapillary_v2_0.py b/mmseg/datasets/mapillary.py
similarity index 66%
rename from projects/mapillary_dataset/mmseg/datasets/mapillary_v2_0.py
rename to mmseg/datasets/mapillary.py
index 9c67a8b212..6c2947338e 100644
--- a/projects/mapillary_dataset/mmseg/datasets/mapillary_v2_0.py
+++ b/mmseg/datasets/mapillary.py
@@ -1,10 +1,72 @@
 # Copyright (c) OpenMMLab. All rights reserved.
-from mmseg.datasets.basesegdataset import BaseSegDataset
 from mmseg.registry import DATASETS
+from .basesegdataset import BaseSegDataset
 
 
 @DATASETS.register_module()
-class MapillaryDataset_v2_0(BaseSegDataset):
+class MapillaryDataset_v1(BaseSegDataset):
+    """Mapillary Vistas Dataset.
+
+    Dataset paper link:
+    http://ieeexplore.ieee.org/document/8237796/
+
+    v1.2 contain 66 object classes.
+    (37 instance-specific)
+
+    v2.0 contain 124 object classes.
+    (70 instance-specific, 46 stuff, 8 void or crowd).
+
+    The ``img_suffix`` is fixed to '.jpg' and ``seg_map_suffix`` is
+    fixed to '.png' for Mapillary Vistas Dataset.
+    """
+    METAINFO = dict(
+        classes=('Bird', 'Ground Animal', 'Curb', 'Fence', 'Guard Rail',
+                 'Barrier', 'Wall', 'Bike Lane', 'Crosswalk - Plain',
+                 'Curb Cut', 'Parking', 'Pedestrian Area', 'Rail Track',
+                 'Road', 'Service Lane', 'Sidewalk', 'Bridge', 'Building',
+                 'Tunnel', 'Person', 'Bicyclist', 'Motorcyclist',
+                 'Other Rider', 'Lane Marking - Crosswalk',
+                 'Lane Marking - General', 'Mountain', 'Sand', 'Sky', 'Snow',
+                 'Terrain', 'Vegetation', 'Water', 'Banner', 'Bench',
+                 'Bike Rack', 'Billboard', 'Catch Basin', 'CCTV Camera',
+                 'Fire Hydrant', 'Junction Box', 'Mailbox', 'Manhole',
+                 'Phone Booth', 'Pothole', 'Street Light', 'Pole',
+                 'Traffic Sign Frame', 'Utility Pole', 'Traffic Light',
+                 'Traffic Sign (Back)', 'Traffic Sign (Front)', 'Trash Can',
+                 'Bicycle', 'Boat', 'Bus', 'Car', 'Caravan', 'Motorcycle',
+                 'On Rails', 'Other Vehicle', 'Trailer', 'Truck',
+                 'Wheeled Slow', 'Car Mount', 'Ego Vehicle', 'Unlabeled'),
+        palette=[[165, 42, 42], [0, 192, 0], [196, 196, 196], [190, 153, 153],
+                 [180, 165, 180], [90, 120, 150], [102, 102, 156],
+                 [128, 64, 255], [140, 140, 200], [170, 170, 170],
+                 [250, 170, 160], [96, 96, 96],
+                 [230, 150, 140], [128, 64, 128], [110, 110, 110],
+                 [244, 35, 232], [150, 100, 100], [70, 70, 70], [150, 120, 90],
+                 [220, 20, 60], [255, 0, 0], [255, 0, 100], [255, 0, 200],
+                 [200, 128, 128], [255, 255, 255], [64, 170,
+                                                    64], [230, 160, 50],
+                 [70, 130, 180], [190, 255, 255], [152, 251, 152],
+                 [107, 142, 35], [0, 170, 30], [255, 255, 128], [250, 0, 30],
+                 [100, 140, 180], [220, 220, 220], [220, 128, 128],
+                 [222, 40, 40], [100, 170, 30], [40, 40, 40], [33, 33, 33],
+                 [100, 128, 160], [142, 0, 0], [70, 100, 150], [210, 170, 100],
+                 [153, 153, 153], [128, 128, 128], [0, 0, 80], [250, 170, 30],
+                 [192, 192, 192], [220, 220, 0], [140, 140, 20], [119, 11, 32],
+                 [150, 0, 255], [0, 60, 100], [0, 0, 142], [0, 0, 90],
+                 [0, 0, 230], [0, 80, 100], [128, 64, 64], [0, 0, 110],
+                 [0, 0, 70], [0, 0, 192], [32, 32, 32], [120, 10,
+                                                         10], [0, 0, 0]])
+
+    def __init__(self,
+                 img_suffix='.jpg',
+                 seg_map_suffix='.png',
+                 **kwargs) -> None:
+        super().__init__(
+            img_suffix=img_suffix, seg_map_suffix=seg_map_suffix, **kwargs)
+
+
+@DATASETS.register_module()
+class MapillaryDataset_v2(BaseSegDataset):
     """Mapillary Vistas Dataset.
 
     Dataset paper link:
diff --git a/mmseg/utils/class_names.py b/mmseg/utils/class_names.py
index 662199f21e..961a08520d 100644
--- a/mmseg/utils/class_names.py
+++ b/mmseg/utils/class_names.py
@@ -126,6 +126,126 @@ def stare_classes():
     return ['background', 'vessel']
 
 
+def mapillary_v1_classes():
+    """mapillary_v1 class names for external use."""
+    return [
+        'Bird', 'Ground Animal', 'Curb', 'Fence', 'Guard Rail', 'Barrier',
+        'Wall', 'Bike Lane', 'Crosswalk - Plain', 'Curb Cut', 'Parking',
+        'Pedestrian Area', 'Rail Track', 'Road', 'Service Lane', 'Sidewalk',
+        'Bridge', 'Building', 'Tunnel', 'Person', 'Bicyclist', 'Motorcyclist',
+        'Other Rider', 'Lane Marking - Crosswalk', 'Lane Marking - General',
+        'Mountain', 'Sand', 'Sky', 'Snow', 'Terrain', 'Vegetation', 'Water',
+        'Banner', 'Bench', 'Bike Rack', 'Billboard', 'Catch Basin',
+        'CCTV Camera', 'Fire Hydrant', 'Junction Box', 'Mailbox', 'Manhole',
+        'Phone Booth', 'Pothole', 'Street Light', 'Pole', 'Traffic Sign Frame',
+        'Utility Pole', 'Traffic Light', 'Traffic Sign (Back)',
+        'Traffic Sign (Front)', 'Trash Can', 'Bicycle', 'Boat', 'Bus', 'Car',
+        'Caravan', 'Motorcycle', 'On Rails', 'Other Vehicle', 'Trailer',
+        'Truck', 'Wheeled Slow', 'Car Mount', 'Ego Vehicle', 'Unlabeled'
+    ]
+
+
+def mapillary_v1_palette():
+    """mapillary_v1_ palette for external use."""
+    return [[165, 42, 42], [0, 192, 0], [196, 196, 196], [190, 153, 153],
+            [180, 165, 180], [90, 120, 150], [102, 102, 156], [128, 64, 255],
+            [140, 140, 200], [170, 170, 170], [250, 170, 160], [96, 96, 96],
+            [230, 150, 140], [128, 64, 128], [110, 110, 110], [244, 35, 232],
+            [150, 100, 100], [70, 70, 70], [150, 120, 90], [220, 20, 60],
+            [255, 0, 0], [255, 0, 100], [255, 0, 200], [200, 128, 128],
+            [255, 255, 255], [64, 170, 64], [230, 160, 50], [70, 130, 180],
+            [190, 255, 255], [152, 251, 152], [107, 142, 35], [0, 170, 30],
+            [255, 255, 128], [250, 0, 30], [100, 140, 180], [220, 220, 220],
+            [220, 128, 128], [222, 40, 40], [100, 170, 30], [40, 40, 40],
+            [33, 33, 33], [100, 128, 160], [142, 0, 0], [70, 100, 150],
+            [210, 170, 100], [153, 153, 153], [128, 128, 128], [0, 0, 80],
+            [250, 170, 30], [192, 192, 192], [220, 220, 0], [140, 140, 20],
+            [119, 11, 32], [150, 0, 255], [0, 60, 100], [0, 0, 142],
+            [0, 0, 90], [0, 0, 230], [0, 80, 100], [128, 64, 64], [0, 0, 110],
+            [0, 0, 70], [0, 0, 192], [32, 32, 32], [120, 10, 10], [0, 0, 0]]
+
+
+def mapillary_v2_classes():
+    """mapillary_v2 class names for external use."""
+    return [
+        'Bird', 'Ground Animal', 'Ambiguous Barrier', 'Concrete Block', 'Curb',
+        'Fence', 'Guard Rail', 'Barrier', 'Road Median', 'Road Side',
+        'Lane Separator', 'Temporary Barrier', 'Wall', 'Bike Lane',
+        'Crosswalk - Plain', 'Curb Cut', 'Driveway', 'Parking',
+        'Parking Aisle', 'Pedestrian Area', 'Rail Track', 'Road',
+        'Road Shoulder', 'Service Lane', 'Sidewalk', 'Traffic Island',
+        'Bridge', 'Building', 'Garage', 'Tunnel', 'Person', 'Person Group',
+        'Bicyclist', 'Motorcyclist', 'Other Rider',
+        'Lane Marking - Dashed Line', 'Lane Marking - Straight Line',
+        'Lane Marking - Zigzag Line', 'Lane Marking - Ambiguous',
+        'Lane Marking - Arrow (Left)', 'Lane Marking - Arrow (Other)',
+        'Lane Marking - Arrow (Right)',
+        'Lane Marking - Arrow (Split Left or Straight)',
+        'Lane Marking - Arrow (Split Right or Straight)',
+        'Lane Marking - Arrow (Straight)', 'Lane Marking - Crosswalk',
+        'Lane Marking - Give Way (Row)', 'Lane Marking - Give Way (Single)',
+        'Lane Marking - Hatched (Chevron)',
+        'Lane Marking - Hatched (Diagonal)', 'Lane Marking - Other',
+        'Lane Marking - Stop Line', 'Lane Marking - Symbol (Bicycle)',
+        'Lane Marking - Symbol (Other)', 'Lane Marking - Text',
+        'Lane Marking (only) - Dashed Line', 'Lane Marking (only) - Crosswalk',
+        'Lane Marking (only) - Other', 'Lane Marking (only) - Test',
+        'Mountain', 'Sand', 'Sky', 'Snow', 'Terrain', 'Vegetation', 'Water',
+        'Banner', 'Bench', 'Bike Rack', 'Catch Basin', 'CCTV Camera',
+        'Fire Hydrant', 'Junction Box', 'Mailbox', 'Manhole', 'Parking Meter',
+        'Phone Booth', 'Pothole', 'Signage - Advertisement',
+        'Signage - Ambiguous', 'Signage - Back', 'Signage - Information',
+        'Signage - Other', 'Signage - Store', 'Street Light', 'Pole',
+        'Pole Group', 'Traffic Sign Frame', 'Utility Pole', 'Traffic Cone',
+        'Traffic Light - General (Single)', 'Traffic Light - Pedestrians',
+        'Traffic Light - General (Upright)',
+        'Traffic Light - General (Horizontal)', 'Traffic Light - Cyclists',
+        'Traffic Light - Other', 'Traffic Sign - Ambiguous',
+        'Traffic Sign (Back)', 'Traffic Sign - Direction (Back)',
+        'Traffic Sign - Direction (Front)', 'Traffic Sign (Front)',
+        'Traffic Sign - Parking', 'Traffic Sign - Temporary (Back)',
+        'Traffic Sign - Temporary (Front)', 'Trash Can', 'Bicycle', 'Boat',
+        'Bus', 'Car', 'Caravan', 'Motorcycle', 'On Rails', 'Other Vehicle',
+        'Trailer', 'Truck', 'Vehicle Group', 'Wheeled Slow', 'Water Valve',
+        'Car Mount', 'Dynamic', 'Ego Vehicle', 'Ground', 'Static', 'Unlabeled'
+    ]
+
+
+def mapillary_v2_palette():
+    """mapillary_v2_ palette for external use."""
+    return [[165, 42, 42], [0, 192, 0], [250, 170, 31], [250, 170, 32],
+            [196, 196, 196], [190, 153, 153], [180, 165, 180], [90, 120, 150],
+            [250, 170, 33], [250, 170, 34], [128, 128, 128], [250, 170, 35],
+            [102, 102, 156], [128, 64, 255], [140, 140, 200], [170, 170, 170],
+            [250, 170, 36], [250, 170, 160], [250, 170, 37], [96, 96, 96],
+            [230, 150, 140], [128, 64, 128], [110, 110, 110], [110, 110, 110],
+            [244, 35, 232], [128, 196, 128], [150, 100, 100], [70, 70, 70],
+            [150, 150, 150], [150, 120, 90], [220, 20, 60], [220, 20, 60],
+            [255, 0, 0], [255, 0, 100], [255, 0, 200], [255, 255, 255],
+            [255, 255, 255], [250, 170, 29], [250, 170, 28], [250, 170, 26],
+            [250, 170, 25], [250, 170, 24], [250, 170, 22], [250, 170, 21],
+            [250, 170, 20], [255, 255, 255], [250, 170, 19], [250, 170, 18],
+            [250, 170, 12], [250, 170, 11], [255, 255, 255], [255, 255, 255],
+            [250, 170, 16], [250, 170, 15], [250, 170, 15], [255, 255, 255],
+            [255, 255, 255], [255, 255, 255], [255, 255, 255], [64, 170, 64],
+            [230, 160, 50], [70, 130, 180], [190, 255, 255], [152, 251, 152],
+            [107, 142, 35], [0, 170, 30], [255, 255, 128], [250, 0, 30],
+            [100, 140, 180], [220, 128, 128], [222, 40, 40], [100, 170, 30],
+            [40, 40, 40], [33, 33, 33], [100, 128, 160], [20, 20, 255],
+            [142, 0, 0], [70, 100, 150], [250, 171, 30], [250, 172, 30],
+            [250, 173, 30], [250, 174, 30], [250, 175, 30], [250, 176, 30],
+            [210, 170, 100], [153, 153, 153], [153, 153, 153], [128, 128, 128],
+            [0, 0, 80], [210, 60, 60], [250, 170, 30], [250, 170, 30],
+            [250, 170, 30], [250, 170, 30], [250, 170, 30], [250, 170, 30],
+            [192, 192, 192], [192, 192, 192], [192, 192, 192], [220, 220, 0],
+            [220, 220, 0], [0, 0, 196], [192, 192, 192], [220, 220, 0],
+            [140, 140, 20], [119, 11, 32], [150, 0, 255], [0, 60, 100],
+            [0, 0, 142], [0, 0, 90], [0, 0, 230], [0, 80, 100], [128, 64, 64],
+            [0, 0, 110], [0, 0, 70], [0, 0, 142], [0, 0, 192], [170, 170, 170],
+            [32, 32, 32], [111, 74, 0], [120, 10, 10], [81, 0, 81],
+            [111, 111, 0], [0, 0, 0]]
+
+
 def cityscapes_palette():
     """Cityscapes palette for external use."""
     return [[128, 64, 128], [244, 35, 232], [70, 70, 70], [102, 102, 156],
@@ -313,7 +433,9 @@ def lip_palette():
     ],
     'isaid': ['isaid', 'iSAID'],
     'stare': ['stare', 'STARE'],
-    'lip': ['LIP', 'lip']
+    'lip': ['LIP', 'lip'],
+    'mapillary_v1': ['mapillary_v1'],
+    'mapillary_v2': ['mapillary_v2']
 }
 
 
diff --git a/projects/mapillary_dataset/README.md b/projects/mapillary_dataset/README.md
index 2b3099522e..cdc61d53a9 100644
--- a/projects/mapillary_dataset/README.md
+++ b/projects/mapillary_dataset/README.md
@@ -34,6 +34,7 @@ Preparing `Mapillary Vistas Dataset` dataset following [Mapillary Vistas Dataset
   |   │   │   │   └── polygons
   │   │   ├── validation
   │   │   │   ├── images
+  │   │   │   ├── v1.2
   |   │   │   │   ├── instances
   |   │   │   │   ├── labels
   |   │   │   │   ├── labels_mask
@@ -46,12 +47,12 @@ Preparing `Mapillary Vistas Dataset` dataset following [Mapillary Vistas Dataset
   |   │   │   │   └── polygons
 ```
 
-### Training commands with `deeplabv3plus_r101-d8_4xb2-240k_mapillay-512x1024.py`
+### Training commands
 
 ```bash
 # Dataset train commands
 # at `mmsegmentation` folder
-bash tools/dist_train.sh projects/mapillary_dataset/configs/deeplabv3plus_r101-d8_4xb2-240k_mapillay-512x1024.py 4
+bash tools/dist_train.sh projects/mapillary_dataset/configs/deeplabv3plus_r101-d8_4xb2-240k_mapillay_v1-512x1024.py 4
 ```
 
 ## Checklist
@@ -66,20 +67,20 @@ bash tools/dist_train.sh projects/mapillary_dataset/configs/deeplabv3plus_r101-d
 
   - [x] A full README
 
-- [ ] Milestone 2: Indicates a successful model implementation.
+- [x] Milestone 2: Indicates a successful model implementation.
 
-  - [ ] Training-time correctness
+  - [x] Training-time correctness
 
-- [ ] Milestone 3: Good to be a part of our core package!
+- [x] Milestone 3: Good to be a part of our core package!
 
-  - [ ] Type hints and docstrings
+  - [x] Type hints and docstrings
 
-  - [ ] Unit tests
+  - [x] Unit tests
 
-  - [ ] Code polishing
+  - [x] Code polishing
 
-  - [ ] Metafile.yml
+  - [x] Metafile.yml
 
-- [ ] Move your modules into the core package following the codebase's file hierarchy structure.
+- [x] Move your modules into the core package following the codebase's file hierarchy structure.
 
-- [ ] Refactor your modules into the core package following the codebase's file hierarchy structure.
+- [x] Refactor your modules into the core package following the codebase's file hierarchy structure.
diff --git a/projects/mapillary_dataset/configs/_base_/datasets/mapillary_v1.py b/projects/mapillary_dataset/configs/_base_/datasets/mapillary_v1.py
new file mode 100644
index 0000000000..611aa4741b
--- /dev/null
+++ b/projects/mapillary_dataset/configs/_base_/datasets/mapillary_v1.py
@@ -0,0 +1,68 @@
+# dataset settings
+dataset_type = 'MapillaryDataset_v1'
+data_root = 'data/mapillary/'
+crop_size = (512, 1024)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=(2048, 1024),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='training/images', seg_map_path='training/v1.2/labels'),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='validation/images',
+            seg_map_path='validation/v1.2/labels'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator
diff --git a/projects/mapillary_dataset/configs/_base_/datasets/mapillary_v1_65.py b/projects/mapillary_dataset/configs/_base_/datasets/mapillary_v1_65.py
new file mode 100644
index 0000000000..f594f37333
--- /dev/null
+++ b/projects/mapillary_dataset/configs/_base_/datasets/mapillary_v1_65.py
@@ -0,0 +1,37 @@
+# dataset settings
+_base_ = './mapillary_v1.py'
+metainfo = dict(
+    classes=('Bird', 'Ground Animal', 'Curb', 'Fence', 'Guard Rail', 'Barrier',
+             'Wall', 'Bike Lane', 'Crosswalk - Plain', 'Curb Cut', 'Parking',
+             'Pedestrian Area', 'Rail Track', 'Road', 'Service Lane',
+             'Sidewalk', 'Bridge', 'Building', 'Tunnel', 'Person', 'Bicyclist',
+             'Motorcyclist', 'Other Rider', 'Lane Marking - Crosswalk',
+             'Lane Marking - General', 'Mountain', 'Sand', 'Sky', 'Snow',
+             'Terrain', 'Vegetation', 'Water', 'Banner', 'Bench', 'Bike Rack',
+             'Billboard', 'Catch Basin', 'CCTV Camera', 'Fire Hydrant',
+             'Junction Box', 'Mailbox', 'Manhole', 'Phone Booth', 'Pothole',
+             'Street Light', 'Pole', 'Traffic Sign Frame', 'Utility Pole',
+             'Traffic Light', 'Traffic Sign (Back)', 'Traffic Sign (Front)',
+             'Trash Can', 'Bicycle', 'Boat', 'Bus', 'Car', 'Caravan',
+             'Motorcycle', 'On Rails', 'Other Vehicle', 'Trailer', 'Truck',
+             'Wheeled Slow', 'Car Mount', 'Ego Vehicle'),
+    palette=[[165, 42, 42], [0, 192, 0], [196, 196, 196], [190, 153, 153],
+             [180, 165, 180], [90, 120, 150], [102, 102, 156], [128, 64, 255],
+             [140, 140, 200], [170, 170, 170], [250, 170, 160], [96, 96, 96],
+             [230, 150, 140], [128, 64, 128], [110, 110, 110], [244, 35, 232],
+             [150, 100, 100], [70, 70, 70], [150, 120, 90], [220, 20, 60],
+             [255, 0, 0], [255, 0, 100], [255, 0, 200], [200, 128, 128],
+             [255, 255, 255], [64, 170, 64], [230, 160, 50], [70, 130, 180],
+             [190, 255, 255], [152, 251, 152], [107, 142, 35], [0, 170, 30],
+             [255, 255, 128], [250, 0, 30], [100, 140, 180], [220, 220, 220],
+             [220, 128, 128], [222, 40, 40], [100, 170, 30], [40, 40, 40],
+             [33, 33, 33], [100, 128, 160], [142, 0, 0], [70, 100, 150],
+             [210, 170, 100], [153, 153, 153], [128, 128, 128], [0, 0, 80],
+             [250, 170, 30], [192, 192, 192], [220, 220, 0], [140, 140, 20],
+             [119, 11, 32], [150, 0, 255], [0, 60, 100], [0, 0, 142],
+             [0, 0, 90], [0, 0, 230], [0, 80, 100], [128, 64, 64], [0, 0, 110],
+             [0, 0, 70], [0, 0, 192], [32, 32, 32], [120, 10, 10]])
+
+train_dataloader = dict(dataset=dict(metainfo=metainfo))
+val_dataloader = dict(dataset=dict(metainfo=metainfo))
+test_dataloader = val_dataloader
diff --git a/projects/mapillary_dataset/configs/_base_/datasets/mapillary_v2.py b/projects/mapillary_dataset/configs/_base_/datasets/mapillary_v2.py
new file mode 100644
index 0000000000..7cb7a958e5
--- /dev/null
+++ b/projects/mapillary_dataset/configs/_base_/datasets/mapillary_v2.py
@@ -0,0 +1,68 @@
+# dataset settings
+dataset_type = 'MapillaryDataset_v2'
+data_root = 'data/mapillary/'
+crop_size = (512, 1024)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=(2048, 1024),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='training/images', seg_map_path='training/v2.0/labels'),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='validation/images',
+            seg_map_path='validation/v2.0/labels'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator
diff --git a/projects/mapillary_dataset/configs/deeplabv3plus_r101-d8_4xb2-240k_mapillay-512x1024.py b/projects/mapillary_dataset/configs/deeplabv3plus_r101-d8_4xb2-240k_mapillay-512x1024.py
deleted file mode 100644
index 6f7ad65ed8..0000000000
--- a/projects/mapillary_dataset/configs/deeplabv3plus_r101-d8_4xb2-240k_mapillay-512x1024.py
+++ /dev/null
@@ -1,103 +0,0 @@
-_base_ = ['./_base_/datasets/mapillary_v1_2.py']  # v 1.2 labels
-# _base_ = ['./_base_/datasets/mapillary_v2_0.py']  # v2.0 labels
-custom_imports = dict(imports=[
-    'projects.mapillary_dataset.mmseg.datasets.mapillary_v1_2',
-    'projects.mapillary_dataset.mmseg.datasets.mapillary_v2_0',
-])
-
-norm_cfg = dict(type='SyncBN', requires_grad=True)
-data_preprocessor = dict(
-    type='SegDataPreProcessor',
-    mean=[123.675, 116.28, 103.53],
-    std=[58.395, 57.12, 57.375],
-    bgr_to_rgb=True,
-    pad_val=0,
-    seg_pad_val=255,
-    size=(512, 1024))
-
-model = dict(
-    type='EncoderDecoder',
-    data_preprocessor=data_preprocessor,
-    pretrained=None,
-    backbone=dict(
-        type='ResNet',
-        depth=101,
-        num_stages=4,
-        out_indices=(0, 1, 2, 3),
-        dilations=(1, 1, 2, 4),
-        strides=(1, 2, 1, 1),
-        norm_cfg=norm_cfg,
-        norm_eval=False,
-        style='pytorch',
-        contract_dilation=True),
-    decode_head=dict(
-        type='DepthwiseSeparableASPPHead',
-        in_channels=2048,
-        in_index=3,
-        channels=512,
-        dilations=(1, 12, 24, 36),
-        c1_in_channels=256,
-        c1_channels=48,
-        dropout_ratio=0.1,
-        num_classes=66,  # v1.2
-        # num_classes=124, # v2.0
-        norm_cfg=norm_cfg,
-        align_corners=False,
-        loss_decode=dict(
-            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
-    auxiliary_head=dict(
-        type='FCNHead',
-        in_channels=1024,
-        in_index=2,
-        channels=256,
-        num_convs=1,
-        concat_input=False,
-        dropout_ratio=0.1,
-        num_classes=66,  # v1.2
-        # num_classes=124, # v2.0
-        norm_cfg=norm_cfg,
-        align_corners=False,
-        loss_decode=dict(
-            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
-    train_cfg=dict(),
-    test_cfg=dict(mode='whole'))
-default_scope = 'mmseg'
-env_cfg = dict(
-    cudnn_benchmark=True,
-    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
-    dist_cfg=dict(backend='nccl'))
-vis_backends = [dict(type='LocalVisBackend')]
-visualizer = dict(
-    type='SegLocalVisualizer',
-    vis_backends=[dict(type='LocalVisBackend')],
-    name='visualizer')
-log_processor = dict(by_epoch=False)
-log_level = 'INFO'
-load_from = None
-resume = False
-tta_model = dict(type='SegTTAModel')
-optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
-optim_wrapper = dict(
-    type='OptimWrapper',
-    optimizer=dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001),
-    clip_grad=None)
-param_scheduler = [
-    dict(
-        type='PolyLR',
-        eta_min=0.0001,
-        power=0.9,
-        begin=0,
-        end=240000,
-        by_epoch=False)
-]
-train_cfg = dict(
-    type='IterBasedTrainLoop', max_iters=240000, val_interval=24000)
-val_cfg = dict(type='ValLoop')
-test_cfg = dict(type='TestLoop')
-default_hooks = dict(
-    timer=dict(type='IterTimerHook'),
-    logger=dict(type='LoggerHook', interval=50, log_metric_by_epoch=False),
-    param_scheduler=dict(type='ParamSchedulerHook'),
-    checkpoint=dict(type='CheckpointHook', by_epoch=False, interval=24000),
-    sampler_seed=dict(type='DistSamplerSeedHook'),
-    visualization=dict(type='SegVisualizationHook'))
diff --git a/projects/mapillary_dataset/configs/deeplabv3plus_r101-d8_4xb2-240k_mapillay_v1-512x1024.py b/projects/mapillary_dataset/configs/deeplabv3plus_r101-d8_4xb2-240k_mapillay_v1-512x1024.py
new file mode 100644
index 0000000000..b559e0d6aa
--- /dev/null
+++ b/projects/mapillary_dataset/configs/deeplabv3plus_r101-d8_4xb2-240k_mapillay_v1-512x1024.py
@@ -0,0 +1,17 @@
+_base_ = [
+    '../../../configs/_base_/models/deeplabv3plus_r50-d8.py',
+    './_base_/datasets/mapillary_v1.py',
+    '../../../configs/_base_/default_runtime.py',
+    '../../../configs/_base_/schedules/schedule_240k.py'
+]
+custom_imports = dict(
+    imports=['projects.mapillary_dataset.mmseg.datasets.mapillary'])
+
+crop_size = (512, 1024)
+data_preprocessor = dict(size=crop_size)
+model = dict(
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://resnet101_v1c',
+    backbone=dict(depth=101),
+    decode_head=dict(num_classes=66),
+    auxiliary_head=dict(num_classes=66))
diff --git a/projects/mapillary_dataset/configs/deeplabv3plus_r101-d8_4xb2-240k_mapillay_v2-512x1024.py b/projects/mapillary_dataset/configs/deeplabv3plus_r101-d8_4xb2-240k_mapillay_v2-512x1024.py
new file mode 100644
index 0000000000..cfe31a2c12
--- /dev/null
+++ b/projects/mapillary_dataset/configs/deeplabv3plus_r101-d8_4xb2-240k_mapillay_v2-512x1024.py
@@ -0,0 +1,16 @@
+_base_ = [
+    '../../../configs/_base_/models/deeplabv3plus_r50-d8.py',
+    './_base_/datasets/mapillary_v2.py',
+    '../../../configs/_base_/default_runtime.py',
+    '../../../configs/_base_/schedules/schedule_240k.py'
+]
+custom_imports = dict(
+    imports=['projects.mapillary_dataset.mmseg.datasets.mapillary'])
+crop_size = (512, 1024)
+data_preprocessor = dict(size=crop_size)
+model = dict(
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://resnet101_v1c',
+    backbone=dict(depth=101),
+    decode_head=dict(num_classes=124),
+    auxiliary_head=dict(num_classes=124))
diff --git a/projects/mapillary_dataset/configs/pspnet_r101-d8_4xb2-240k_mapillay_v1-512x1024.py b/projects/mapillary_dataset/configs/pspnet_r101-d8_4xb2-240k_mapillay_v1-512x1024.py
new file mode 100644
index 0000000000..1ca2b57f73
--- /dev/null
+++ b/projects/mapillary_dataset/configs/pspnet_r101-d8_4xb2-240k_mapillay_v1-512x1024.py
@@ -0,0 +1,16 @@
+_base_ = [
+    '../../../configs/_base_/models/pspnet_r50-d8.py',
+    './_base_/datasets/mapillary_v1.py',
+    '../../../configs/_base_/default_runtime.py',
+    '../../../configs/_base_/schedules/schedule_240k.py'
+]
+custom_imports = dict(
+    imports=['projects.mapillary_dataset.mmseg.datasets.mapillary'])
+crop_size = (512, 1024)
+data_preprocessor = dict(size=crop_size)
+model = dict(
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://resnet101_v1c',
+    backbone=dict(depth=101),
+    decode_head=dict(num_classes=66),
+    auxiliary_head=dict(num_classes=66))
diff --git a/projects/mapillary_dataset/configs/pspnet_r101-d8_4xb2-240k_mapillay_v2-512x1024.py b/projects/mapillary_dataset/configs/pspnet_r101-d8_4xb2-240k_mapillay_v2-512x1024.py
new file mode 100644
index 0000000000..c04746a3dc
--- /dev/null
+++ b/projects/mapillary_dataset/configs/pspnet_r101-d8_4xb2-240k_mapillay_v2-512x1024.py
@@ -0,0 +1,16 @@
+_base_ = [
+    '../../../configs/_base_/models/pspnet_r50-d8.py',
+    './_base_/datasets/mapillary_v2.py',
+    '../../../configs/_base_/default_runtime.py',
+    '../../../configs/_base_/schedules/schedule_240k.py'
+]
+custom_imports = dict(
+    imports=['projects.mapillary_dataset.mmseg.datasets.mapillary'])
+crop_size = (512, 1024)
+data_preprocessor = dict(size=crop_size)
+model = dict(
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://resnet101_v1c',
+    backbone=dict(depth=101),
+    decode_head=dict(num_classes=124),
+    auxiliary_head=dict(num_classes=124))
diff --git a/projects/mapillary_dataset/docs/en/user_guides/2_dataset_prepare.md b/projects/mapillary_dataset/docs/en/user_guides/2_dataset_prepare.md
index 405e533156..fa07454330 100644
--- a/projects/mapillary_dataset/docs/en/user_guides/2_dataset_prepare.md
+++ b/projects/mapillary_dataset/docs/en/user_guides/2_dataset_prepare.md
@@ -1,87 +1,20 @@
-## Prepare datasets
+## Mapillary Vistas Datasets
 
-It is recommended to symlink the dataset root to `$MMSEGMENTATION/data`.
-If your folder structure is different, you may need to change the corresponding paths in config files.
+- The dataset could be download [here](https://www.mapillary.com/dataset/vistas) after registration.
 
-```none
-mmsegmentation
-├── mmseg
-├── tools
-├── configs
-├── data
-│   ├── mapillary
-│   │   ├── training
-│   │   │   ├── images
-│   │   │   ├── v1.2
-|   │   │   │   ├── instances
-|   │   │   │   ├── labels
-|   │   │   │   ├── labels_mask
-|   │   │   │   └── panoptic
-│   │   │   ├── v2.0
-|   │   │   │   ├── instances
-|   │   │   │   ├── labels
-|   │   │   │   ├── labels_mask
-|   │   │   │   ├── panoptic
-|   │   │   │   └── polygons
-│   │   ├── validation
-│   │   │   ├── images
-|   │   │   │   ├── instances
-|   │   │   │   ├── labels
-|   │   │   │   ├── labels_mask
-|   │   │   │   └── panoptic
-│   │   │   ├── v2.0
-|   │   │   │   ├── instances
-|   │   │   │   ├── labels
-|   │   │   │   ├── labels_mask
-|   │   │   │   ├── panoptic
-|   │   │   │   └── polygons
-```
+- Mapillary Vistas Dataset use 8-bit with color-palette to store labels. No conversion operation is required.
 
-## Mapillary Vistas Datasets
+- Assumption you have put the dataset zip file in `mmsegmentation/data/mapillary`
 
-- The dataset could be download [here](https://www.mapillary.com/dataset/vistas) after registration.
-- Assumption you have put the dataset zip file in `mmsegmentation/data`
 - Please run the following commands to unzip dataset.
+
   ```bash
-  cd data
-  mkdir mapillary
-  unzip -d mapillary An-ZjB1Zm61yAZG0ozTymz8I8NqI4x0MrYrh26dq7kPgfu8vf9ImrdaOAVOFYbJ2pNAgUnVGBmbue9lTgdBOb5BbKXIpFs0fpYWqACbrQDChAA2fdX0zS9PcHu7fY8c-FOvyBVxPNYNFQuM.zip
-  ```
-- After unzip, you will get Mapillary Vistas Dataset like this structure.
-  ```none
-  ├── data
-  │   ├── mapillary
-  │   │   ├── training
-  │   │   │   ├── images
-  │   │   │   ├── v1.2
-  |   │   │   │   ├── instances
-  |   │   │   │   ├── labels
-  |   │   │   │   └── panoptic
-  │   │   │   ├── v2.0
-  |   │   │   │   ├── instances
-  |   │   │   │   ├── labels
-  |   │   │   │   ├── panoptic
-  |   │   │   │   └── polygons
-  │   │   ├── validation
-  │   │   │   ├── images
-  |   │   │   │   ├── instances
-  |   │   │   │   ├── labels
-  |   │   │   │   └── panoptic
-  │   │   │   ├── v2.0
-  |   │   │   │   ├── instances
-  |   │   │   │   ├── labels
-  |   │   │   │   ├── panoptic
-  |   │   │   │   └── polygons
-  ```
-- run following commands to convert RGB labels to mask labels
-  ```bash
-  # --nproc optional, default 1, whether use multi-progress
-  # --version optional, 'v1.2', 'v2.0','all', default 'all', choose convert which version labels
-  # run this command at 'mmsegmentation/projects/Mapillary_dataset' folder
-  cd mmsegmentation/projects/mapillary_dataset
-  python tools/dataset_converters/mapillary.py ../../data/mapillary --nproc 8 --version all
+  cd data/mapillary
+  unzip An-ZjB1Zm61yAZG0ozTymz8I8NqI4x0MrYrh26dq7kPgfu8vf9ImrdaOAVOFYbJ2pNAgUnVGBmbue9lTgdBOb5BbKXIpFs0fpYWqACbrQDChAA2fdX0zS9PcHu7fY8c-FOvyBVxPNYNFQuM.zip
   ```
-  After then, you will get this structure
+
+- After unzip, you will get Mapillary Vistas Dataset like this structure. Semantic segmentation mask labels in `labels` folder.
+
   ```none
   mmsegmentation
   ├── mmseg
@@ -94,24 +27,229 @@ mmsegmentation
   │   │   │   ├── v1.2
   |   │   │   │   ├── instances
   |   │   │   │   ├── labels
-  |   │   │   │   ├── labels_mask
   |   │   │   │   └── panoptic
   │   │   │   ├── v2.0
   |   │   │   │   ├── instances
   |   │   │   │   ├── labels
-  |   │   │   │   ├── labels_mask
   |   │   │   │   ├── panoptic
   |   │   │   │   └── polygons
   │   │   ├── validation
   │   │   │   ├── images
+  |   │   │   ├── v1.2
   |   │   │   │   ├── instances
   |   │   │   │   ├── labels
-  |   │   │   │   ├── labels_mask
   |   │   │   │   └── panoptic
   │   │   │   ├── v2.0
   |   │   │   │   ├── instances
   |   │   │   │   ├── labels
-  |   │   │   │   ├── labels_mask
   |   │   │   │   ├── panoptic
   |   │   │   │   └── polygons
   ```
+
+- You could set Datasets version with `MapillaryDataset_v1` and `MapillaryDataset_v2` in your configs.
+  View the Mapillary Vistas Datasets config file here [V1.2](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/datasets/mapillary_v1.py) and  [V2.0](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/datasets/mapillary_v2.py)
+
+- **View datasets labels index and palette**
+
+- **Mapillary Vistas Datasets labels information**
+  **v1.2 information**
+
+  ```none
+  There are 66 labels classes in v1.2
+  0--Bird--[165, 42, 42],
+  1--Ground Animal--[0, 192, 0],
+  2--Curb--[196, 196, 196],
+  3--Fence--[190, 153, 153],
+  4--Guard Rail--[180, 165, 180],
+  5--Barrier--[90, 120, 150],
+  6--Wall--[102, 102, 156],
+  7--Bike Lane--[128, 64, 255],
+  8--Crosswalk - Plain--[140, 140, 200],
+  9--Curb Cut--[170, 170, 170],
+  10--Parking--[250, 170, 160],
+  11--Pedestrian Area--[96, 96, 96],
+  12--Rail Track--[230, 150, 140],
+  13--Road--[128, 64, 128],
+  14--Service Lane--[110, 110, 110],
+  15--Sidewalk--[244, 35, 232],
+  16--Bridge--[150, 100, 100],
+  17--Building--[70, 70, 70],
+  18--Tunnel--[150, 120, 90],
+  19--Person--[220, 20, 60],
+  20--Bicyclist--[255, 0, 0],
+  21--Motorcyclist--[255, 0, 100],
+  22--Other Rider--[255, 0, 200],
+  23--Lane Marking - Crosswalk--[200, 128, 128],
+  24--Lane Marking - General--[255, 255, 255],
+  25--Mountain--[64, 170, 64],
+  26--Sand--[230, 160, 50],
+  27--Sky--[70, 130, 180],
+  28--Snow--[190, 255, 255],
+  29--Terrain--[152, 251, 152],
+  30--Vegetation--[107, 142, 35],
+  31--Water--[0, 170, 30],
+  32--Banner--[255, 255, 128],
+  33--Bench--[250, 0, 30],
+  34--Bike Rack--[100, 140, 180],
+  35--Billboard--[220, 220, 220],
+  36--Catch Basin--[220, 128, 128],
+  37--CCTV Camera--[222, 40, 40],
+  38--Fire Hydrant--[100, 170, 30],
+  39--Junction Box--[40, 40, 40],
+  40--Mailbox--[33, 33, 33],
+  41--Manhole--[100, 128, 160],
+  42--Phone Booth--[142, 0, 0],
+  43--Pothole--[70, 100, 150],
+  44--Street Light--[210, 170, 100],
+  45--Pole--[153, 153, 153],
+  46--Traffic Sign Frame--[128, 128, 128],
+  47--Utility Pole--[0, 0, 80],
+  48--Traffic Light--[250, 170, 30],
+  49--Traffic Sign (Back)--[192, 192, 192],
+  50--Traffic Sign (Front)--[220, 220, 0],
+  51--Trash Can--[140, 140, 20],
+  52--Bicycle--[119, 11, 32],
+  53--Boat--[150, 0, 255],
+  54--Bus--[0, 60, 100],
+  55--Car--[0, 0, 142],
+  56--Caravan--[0, 0, 90],
+  57--Motorcycle--[0, 0, 230],
+  58--On Rails--[0, 80, 100],
+  59--Other Vehicle--[128, 64, 64],
+  60--Trailer--[0, 0, 110],
+  61--Truck--[0, 0, 70],
+  62--Wheeled Slow--[0, 0, 192],
+  63--Car Mount--[32, 32, 32],
+  64--Ego Vehicle--[120, 10, 10],
+  65--Unlabeled--[0, 0, 0]
+  ```
+
+  **v2.0 information**
+
+  ```none
+  There are 124 labels classes in v2.0
+  0--Bird--[165, 42, 42],
+  1--Ground Animal--[0, 192, 0],
+  2--Ambiguous Barrier--[250, 170, 31],
+  3--Concrete Block--[250, 170, 32],
+  4--Curb--[196, 196, 196],
+  5--Fence--[190, 153, 153],
+  6--Guard Rail--[180, 165, 180],
+  7--Barrier--[90, 120, 150],
+  8--Road Median--[250, 170, 33],
+  9--Road Side--[250, 170, 34],
+  10--Lane Separator--[128, 128, 128],
+  11--Temporary Barrier--[250, 170, 35],
+  12--Wall--[102, 102, 156],
+  13--Bike Lane--[128, 64, 255],
+  14--Crosswalk - Plain--[140, 140, 200],
+  15--Curb Cut--[170, 170, 170],
+  16--Driveway--[250, 170, 36],
+  17--Parking--[250, 170, 160],
+  18--Parking Aisle--[250, 170, 37],
+  19--Pedestrian Area--[96, 96, 96],
+  20--Rail Track--[230, 150, 140],
+  21--Road--[128, 64, 128],
+  22--Road Shoulder--[110, 110, 110],
+  23--Service Lane--[110, 110, 110],
+  24--Sidewalk--[244, 35, 232],
+  25--Traffic Island--[128, 196, 128],
+  26--Bridge--[150, 100, 100],
+  27--Building--[70, 70, 70],
+  28--Garage--[150, 150, 150],
+  29--Tunnel--[150, 120, 90],
+  30--Person--[220, 20, 60],
+  31--Person Group--[220, 20, 60],
+  32--Bicyclist--[255, 0, 0],
+  33--Motorcyclist--[255, 0, 100],
+  34--Other Rider--[255, 0, 200],
+  35--Lane Marking - Dashed Line--[255, 255, 255],
+  36--Lane Marking - Straight Line--[255, 255, 255],
+  37--Lane Marking - Zigzag Line--[250, 170, 29],
+  38--Lane Marking - Ambiguous--[250, 170, 28],
+  39--Lane Marking - Arrow (Left)--[250, 170, 26],
+  40--Lane Marking - Arrow (Other)--[250, 170, 25],
+  41--Lane Marking - Arrow (Right)--[250, 170, 24],
+  42--Lane Marking - Arrow (Split Left or Straight)--[250, 170, 22],
+  43--Lane Marking - Arrow (Split Right or Straight)--[250, 170, 21],
+  44--Lane Marking - Arrow (Straight)--[250, 170, 20],
+  45--Lane Marking - Crosswalk--[255, 255, 255],
+  46--Lane Marking - Give Way (Row)--[250, 170, 19],
+  47--Lane Marking - Give Way (Single)--[250, 170, 18],
+  48--Lane Marking - Hatched (Chevron)--[250, 170, 12],
+  49--Lane Marking - Hatched (Diagonal)--[250, 170, 11],
+  50--Lane Marking - Other--[255, 255, 255],
+  51--Lane Marking - Stop Line--[255, 255, 255],
+  52--Lane Marking - Symbol (Bicycle)--[250, 170, 16],
+  53--Lane Marking - Symbol (Other)--[250, 170, 15],
+  54--Lane Marking - Text--[250, 170, 15],
+  55--Lane Marking (only) - Dashed Line--[255, 255, 255],
+  56--Lane Marking (only) - Crosswalk--[255, 255, 255],
+  57--Lane Marking (only) - Other--[255, 255, 255],
+  58--Lane Marking (only) - Test--[255, 255, 255],
+  59--Mountain--[64, 170, 64],
+  60--Sand--[230, 160, 50],
+  61--Sky--[70, 130, 180],
+  62--Snow--[190, 255, 255],
+  63--Terrain--[152, 251, 152],
+  64--Vegetation--[107, 142, 35],
+  65--Water--[0, 170, 30],
+  66--Banner--[255, 255, 128],
+  67--Bench--[250, 0, 30],
+  68--Bike Rack--[100, 140, 180],
+  69--Catch Basin--[220, 128, 128],
+  70--CCTV Camera--[222, 40, 40],
+  71--Fire Hydrant--[100, 170, 30],
+  72--Junction Box--[40, 40, 40],
+  73--Mailbox--[33, 33, 33],
+  74--Manhole--[100, 128, 160],
+  75--Parking Meter--[20, 20, 255],
+  76--Phone Booth--[142, 0, 0],
+  77--Pothole--[70, 100, 150],
+  78--Signage - Advertisement--[250, 171, 30],
+  79--Signage - Ambiguous--[250, 172, 30],
+  80--Signage - Back--[250, 173, 30],
+  81--Signage - Information--[250, 174, 30],
+  82--Signage - Other--[250, 175, 30],
+  83--Signage - Store--[250, 176, 30],
+  84--Street Light--[210, 170, 100],
+  85--Pole--[153, 153, 153],
+  86--Pole Group--[153, 153, 153],
+  87--Traffic Sign Frame--[128, 128, 128],
+  88--Utility Pole--[0, 0, 80],
+  89--Traffic Cone--[210, 60, 60],
+  90--Traffic Light - General (Single)--[250, 170, 30],
+  91--Traffic Light - Pedestrians--[250, 170, 30],
+  92--Traffic Light - General (Upright)--[250, 170, 30],
+  93--Traffic Light - General (Horizontal)--[250, 170, 30],
+  94--Traffic Light - Cyclists--[250, 170, 30],
+  95--Traffic Light - Other--[250, 170, 30],
+  96--Traffic Sign - Ambiguous--[192, 192, 192],
+  97--Traffic Sign (Back)--[192, 192, 192],
+  98--Traffic Sign - Direction (Back)--[192, 192, 192],
+  99--Traffic Sign - Direction (Front)--[220, 220, 0],
+  100--Traffic Sign (Front)--[220, 220, 0],
+  101--Traffic Sign - Parking--[0, 0, 196],
+  102--Traffic Sign - Temporary (Back)--[192, 192, 192],
+  103--Traffic Sign - Temporary (Front)--[220, 220, 0],
+  104--Trash Can--[140, 140, 20],
+  105--Bicycle--[119, 11, 32],
+  106--Boat--[150, 0, 255],
+  107--Bus--[0, 60, 100],
+  108--Car--[0, 0, 142],
+  109--Caravan--[0, 0, 90],
+  110--Motorcycle--[0, 0, 230],
+  111--On Rails--[0, 80, 100],
+  112--Other Vehicle--[128, 64, 64],
+  113--Trailer--[0, 0, 110],
+  114--Truck--[0, 0, 70],
+  115--Vehicle Group--[0, 0, 142],
+  116--Wheeled Slow--[0, 0, 192],
+  117--Water Valve--[170, 170, 170],
+  118--Car Mount--[32, 32, 32],
+  119--Dynamic--[111, 74, 0],
+  120--Ego Vehicle--[120, 10, 10],
+  121--Ground--[81, 0, 81],
+  122--Static--[111, 111, 0],
+  123--Unlabeled--[0, 0, 0]
+  ```
diff --git a/projects/mapillary_dataset/mmseg/datasets/mapillary.py b/projects/mapillary_dataset/mmseg/datasets/mapillary.py
new file mode 100644
index 0000000000..f49bd54451
--- /dev/null
+++ b/projects/mapillary_dataset/mmseg/datasets/mapillary.py
@@ -0,0 +1,177 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from mmseg.datasets.basesegdataset import BaseSegDataset
+
+# from mmseg.registry import DATASETS
+
+
+# @DATASETS.register_module()
+class MapillaryDataset_v1(BaseSegDataset):
+    """Mapillary Vistas Dataset.
+
+    Dataset paper link:
+    http://ieeexplore.ieee.org/document/8237796/
+
+    v1.2 contain 66 object classes.
+    (37 instance-specific)
+
+    v2.0 contain 124 object classes.
+    (70 instance-specific, 46 stuff, 8 void or crowd).
+
+    The ``img_suffix`` is fixed to '.jpg' and ``seg_map_suffix`` is
+    fixed to '.png' for Mapillary Vistas Dataset.
+    """
+    METAINFO = dict(
+        classes=('Bird', 'Ground Animal', 'Curb', 'Fence', 'Guard Rail',
+                 'Barrier', 'Wall', 'Bike Lane', 'Crosswalk - Plain',
+                 'Curb Cut', 'Parking', 'Pedestrian Area', 'Rail Track',
+                 'Road', 'Service Lane', 'Sidewalk', 'Bridge', 'Building',
+                 'Tunnel', 'Person', 'Bicyclist', 'Motorcyclist',
+                 'Other Rider', 'Lane Marking - Crosswalk',
+                 'Lane Marking - General', 'Mountain', 'Sand', 'Sky', 'Snow',
+                 'Terrain', 'Vegetation', 'Water', 'Banner', 'Bench',
+                 'Bike Rack', 'Billboard', 'Catch Basin', 'CCTV Camera',
+                 'Fire Hydrant', 'Junction Box', 'Mailbox', 'Manhole',
+                 'Phone Booth', 'Pothole', 'Street Light', 'Pole',
+                 'Traffic Sign Frame', 'Utility Pole', 'Traffic Light',
+                 'Traffic Sign (Back)', 'Traffic Sign (Front)', 'Trash Can',
+                 'Bicycle', 'Boat', 'Bus', 'Car', 'Caravan', 'Motorcycle',
+                 'On Rails', 'Other Vehicle', 'Trailer', 'Truck',
+                 'Wheeled Slow', 'Car Mount', 'Ego Vehicle', 'Unlabeled'),
+        palette=[[165, 42, 42], [0, 192, 0], [196, 196, 196], [190, 153, 153],
+                 [180, 165, 180], [90, 120, 150], [102, 102, 156],
+                 [128, 64, 255], [140, 140, 200], [170, 170, 170],
+                 [250, 170, 160], [96, 96, 96],
+                 [230, 150, 140], [128, 64, 128], [110, 110, 110],
+                 [244, 35, 232], [150, 100, 100], [70, 70, 70], [150, 120, 90],
+                 [220, 20, 60], [255, 0, 0], [255, 0, 100], [255, 0, 200],
+                 [200, 128, 128], [255, 255, 255], [64, 170,
+                                                    64], [230, 160, 50],
+                 [70, 130, 180], [190, 255, 255], [152, 251, 152],
+                 [107, 142, 35], [0, 170, 30], [255, 255, 128], [250, 0, 30],
+                 [100, 140, 180], [220, 220, 220], [220, 128, 128],
+                 [222, 40, 40], [100, 170, 30], [40, 40, 40], [33, 33, 33],
+                 [100, 128, 160], [142, 0, 0], [70, 100, 150], [210, 170, 100],
+                 [153, 153, 153], [128, 128, 128], [0, 0, 80], [250, 170, 30],
+                 [192, 192, 192], [220, 220, 0], [140, 140, 20], [119, 11, 32],
+                 [150, 0, 255], [0, 60, 100], [0, 0, 142], [0, 0, 90],
+                 [0, 0, 230], [0, 80, 100], [128, 64, 64], [0, 0, 110],
+                 [0, 0, 70], [0, 0, 192], [32, 32, 32], [120, 10,
+                                                         10], [0, 0, 0]])
+
+    def __init__(self,
+                 img_suffix='.jpg',
+                 seg_map_suffix='.png',
+                 **kwargs) -> None:
+        super().__init__(
+            img_suffix=img_suffix, seg_map_suffix=seg_map_suffix, **kwargs)
+
+
+# @DATASETS.register_module()
+class MapillaryDataset_v2(BaseSegDataset):
+    """Mapillary Vistas Dataset.
+
+    Dataset paper link:
+    http://ieeexplore.ieee.org/document/8237796/
+
+    v1.2 contain 66 object classes.
+    (37 instance-specific)
+
+    v2.0 contain 124 object classes.
+    (70 instance-specific, 46 stuff, 8 void or crowd).
+
+    The ``img_suffix`` is fixed to '.jpg' and ``seg_map_suffix`` is
+    fixed to '.png' for Mapillary Vistas Dataset.
+    """
+    METAINFO = dict(
+        classes=(
+            'Bird', 'Ground Animal', 'Ambiguous Barrier', 'Concrete Block',
+            'Curb', 'Fence', 'Guard Rail', 'Barrier', 'Road Median',
+            'Road Side', 'Lane Separator', 'Temporary Barrier', 'Wall',
+            'Bike Lane', 'Crosswalk - Plain', 'Curb Cut', 'Driveway',
+            'Parking', 'Parking Aisle', 'Pedestrian Area', 'Rail Track',
+            'Road', 'Road Shoulder', 'Service Lane', 'Sidewalk',
+            'Traffic Island', 'Bridge', 'Building', 'Garage', 'Tunnel',
+            'Person', 'Person Group', 'Bicyclist', 'Motorcyclist',
+            'Other Rider', 'Lane Marking - Dashed Line',
+            'Lane Marking - Straight Line', 'Lane Marking - Zigzag Line',
+            'Lane Marking - Ambiguous', 'Lane Marking - Arrow (Left)',
+            'Lane Marking - Arrow (Other)', 'Lane Marking - Arrow (Right)',
+            'Lane Marking - Arrow (Split Left or Straight)',
+            'Lane Marking - Arrow (Split Right or Straight)',
+            'Lane Marking - Arrow (Straight)', 'Lane Marking - Crosswalk',
+            'Lane Marking - Give Way (Row)',
+            'Lane Marking - Give Way (Single)',
+            'Lane Marking - Hatched (Chevron)',
+            'Lane Marking - Hatched (Diagonal)', 'Lane Marking - Other',
+            'Lane Marking - Stop Line', 'Lane Marking - Symbol (Bicycle)',
+            'Lane Marking - Symbol (Other)', 'Lane Marking - Text',
+            'Lane Marking (only) - Dashed Line',
+            'Lane Marking (only) - Crosswalk', 'Lane Marking (only) - Other',
+            'Lane Marking (only) - Test', 'Mountain', 'Sand', 'Sky', 'Snow',
+            'Terrain', 'Vegetation', 'Water', 'Banner', 'Bench', 'Bike Rack',
+            'Catch Basin', 'CCTV Camera', 'Fire Hydrant', 'Junction Box',
+            'Mailbox', 'Manhole', 'Parking Meter', 'Phone Booth', 'Pothole',
+            'Signage - Advertisement', 'Signage - Ambiguous', 'Signage - Back',
+            'Signage - Information', 'Signage - Other', 'Signage - Store',
+            'Street Light', 'Pole', 'Pole Group', 'Traffic Sign Frame',
+            'Utility Pole', 'Traffic Cone', 'Traffic Light - General (Single)',
+            'Traffic Light - Pedestrians', 'Traffic Light - General (Upright)',
+            'Traffic Light - General (Horizontal)', 'Traffic Light - Cyclists',
+            'Traffic Light - Other', 'Traffic Sign - Ambiguous',
+            'Traffic Sign (Back)', 'Traffic Sign - Direction (Back)',
+            'Traffic Sign - Direction (Front)', 'Traffic Sign (Front)',
+            'Traffic Sign - Parking', 'Traffic Sign - Temporary (Back)',
+            'Traffic Sign - Temporary (Front)', 'Trash Can', 'Bicycle', 'Boat',
+            'Bus', 'Car', 'Caravan', 'Motorcycle', 'On Rails', 'Other Vehicle',
+            'Trailer', 'Truck', 'Vehicle Group', 'Wheeled Slow', 'Water Valve',
+            'Car Mount', 'Dynamic', 'Ego Vehicle', 'Ground', 'Static',
+            'Unlabeled'),
+        palette=[[165, 42, 42], [0, 192, 0], [250, 170, 31], [250, 170, 32],
+                 [196, 196, 196], [190, 153, 153], [180, 165, 180],
+                 [90, 120, 150], [250, 170, 33], [250, 170, 34],
+                 [128, 128, 128], [250, 170, 35], [102, 102, 156],
+                 [128, 64, 255], [140, 140, 200], [170, 170, 170],
+                 [250, 170, 36], [250, 170, 160], [250, 170, 37], [96, 96, 96],
+                 [230, 150, 140], [128, 64, 128], [110, 110, 110],
+                 [110, 110, 110], [244, 35, 232], [128, 196,
+                                                   128], [150, 100, 100],
+                 [70, 70, 70], [150, 150, 150], [150, 120, 90], [220, 20, 60],
+                 [220, 20, 60], [255, 0, 0], [255, 0, 100], [255, 0, 200],
+                 [255, 255, 255], [255, 255, 255], [250, 170, 29],
+                 [250, 170, 28], [250, 170, 26], [250, 170,
+                                                  25], [250, 170, 24],
+                 [250, 170, 22], [250, 170, 21], [250, 170,
+                                                  20], [255, 255, 255],
+                 [250, 170, 19], [250, 170, 18], [250, 170,
+                                                  12], [250, 170, 11],
+                 [255, 255, 255], [255, 255, 255], [250, 170, 16],
+                 [250, 170, 15], [250, 170, 15], [255, 255, 255],
+                 [255, 255, 255], [255, 255, 255], [255, 255, 255],
+                 [64, 170, 64], [230, 160, 50],
+                 [70, 130, 180], [190, 255, 255], [152, 251, 152],
+                 [107, 142, 35], [0, 170, 30], [255, 255, 128], [250, 0, 30],
+                 [100, 140, 180], [220, 128, 128], [222, 40,
+                                                    40], [100, 170, 30],
+                 [40, 40, 40], [33, 33, 33], [100, 128, 160], [20, 20, 255],
+                 [142, 0, 0], [70, 100, 150], [250, 171, 30], [250, 172, 30],
+                 [250, 173, 30], [250, 174, 30], [250, 175,
+                                                  30], [250, 176, 30],
+                 [210, 170, 100], [153, 153, 153], [153, 153, 153],
+                 [128, 128, 128], [0, 0, 80], [210, 60, 60], [250, 170, 30],
+                 [250, 170, 30], [250, 170, 30], [250, 170,
+                                                  30], [250, 170, 30],
+                 [250, 170, 30], [192, 192, 192], [192, 192, 192],
+                 [192, 192, 192], [220, 220, 0], [220, 220, 0], [0, 0, 196],
+                 [192, 192, 192], [220, 220, 0], [140, 140, 20], [119, 11, 32],
+                 [150, 0, 255], [0, 60, 100], [0, 0, 142], [0, 0, 90],
+                 [0, 0, 230], [0, 80, 100], [128, 64, 64], [0, 0, 110],
+                 [0, 0, 70], [0, 0, 142], [0, 0, 192], [170, 170, 170],
+                 [32, 32, 32], [111, 74, 0], [120, 10, 10], [81, 0, 81],
+                 [111, 111, 0], [0, 0, 0]])
+
+    def __init__(self,
+                 img_suffix='.jpg',
+                 seg_map_suffix='.png',
+                 **kwargs) -> None:
+        super().__init__(
+            img_suffix=img_suffix, seg_map_suffix=seg_map_suffix, **kwargs)
diff --git a/projects/mapillary_dataset/mmseg/datasets/mapillary_v1_2.py b/projects/mapillary_dataset/mmseg/datasets/mapillary_v1_2.py
deleted file mode 100644
index 975d07b24e..0000000000
--- a/projects/mapillary_dataset/mmseg/datasets/mapillary_v1_2.py
+++ /dev/null
@@ -1,65 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-from mmseg.datasets.basesegdataset import BaseSegDataset
-from mmseg.registry import DATASETS
-
-
-@DATASETS.register_module()
-class MapillaryDataset_v1_2(BaseSegDataset):
-    """Mapillary Vistas Dataset.
-
-    Dataset paper link:
-    http://ieeexplore.ieee.org/document/8237796/
-
-    v1.2 contain 66 object classes.
-    (37 instance-specific)
-
-    v2.0 contain 124 object classes.
-    (70 instance-specific, 46 stuff, 8 void or crowd).
-
-    The ``img_suffix`` is fixed to '.jpg' and ``seg_map_suffix`` is
-    fixed to '.png' for Mapillary Vistas Dataset.
-    """
-    METAINFO = dict(
-        classes=('Bird', 'Ground Animal', 'Curb', 'Fence', 'Guard Rail',
-                 'Barrier', 'Wall', 'Bike Lane', 'Crosswalk - Plain',
-                 'Curb Cut', 'Parking', 'Pedestrian Area', 'Rail Track',
-                 'Road', 'Service Lane', 'Sidewalk', 'Bridge', 'Building',
-                 'Tunnel', 'Person', 'Bicyclist', 'Motorcyclist',
-                 'Other Rider', 'Lane Marking - Crosswalk',
-                 'Lane Marking - General', 'Mountain', 'Sand', 'Sky', 'Snow',
-                 'Terrain', 'Vegetation', 'Water', 'Banner', 'Bench',
-                 'Bike Rack', 'Billboard', 'Catch Basin', 'CCTV Camera',
-                 'Fire Hydrant', 'Junction Box', 'Mailbox', 'Manhole',
-                 'Phone Booth', 'Pothole', 'Street Light', 'Pole',
-                 'Traffic Sign Frame', 'Utility Pole', 'Traffic Light',
-                 'Traffic Sign (Back)', 'Traffic Sign (Front)', 'Trash Can',
-                 'Bicycle', 'Boat', 'Bus', 'Car', 'Caravan', 'Motorcycle',
-                 'On Rails', 'Other Vehicle', 'Trailer', 'Truck',
-                 'Wheeled Slow', 'Car Mount', 'Ego Vehicle', 'Unlabeled'),
-        palette=[[165, 42, 42], [0, 192, 0], [196, 196, 196], [190, 153, 153],
-                 [180, 165, 180], [90, 120, 150], [102, 102, 156],
-                 [128, 64, 255], [140, 140, 200], [170, 170, 170],
-                 [250, 170, 160], [96, 96, 96],
-                 [230, 150, 140], [128, 64, 128], [110, 110, 110],
-                 [244, 35, 232], [150, 100, 100], [70, 70, 70], [150, 120, 90],
-                 [220, 20, 60], [255, 0, 0], [255, 0, 100], [255, 0, 200],
-                 [200, 128, 128], [255, 255, 255], [64, 170,
-                                                    64], [230, 160, 50],
-                 [70, 130, 180], [190, 255, 255], [152, 251, 152],
-                 [107, 142, 35], [0, 170, 30], [255, 255, 128], [250, 0, 30],
-                 [100, 140, 180], [220, 220, 220], [220, 128, 128],
-                 [222, 40, 40], [100, 170, 30], [40, 40, 40], [33, 33, 33],
-                 [100, 128, 160], [142, 0, 0], [70, 100, 150], [210, 170, 100],
-                 [153, 153, 153], [128, 128, 128], [0, 0, 80], [250, 170, 30],
-                 [192, 192, 192], [220, 220, 0], [140, 140, 20], [119, 11, 32],
-                 [150, 0, 255], [0, 60, 100], [0, 0, 142], [0, 0, 90],
-                 [0, 0, 230], [0, 80, 100], [128, 64, 64], [0, 0, 110],
-                 [0, 0, 70], [0, 0, 192], [32, 32, 32], [120, 10,
-                                                         10], [0, 0, 0]])
-
-    def __init__(self,
-                 img_suffix='.jpg',
-                 seg_map_suffix='.png',
-                 **kwargs) -> None:
-        super().__init__(
-            img_suffix=img_suffix, seg_map_suffix=seg_map_suffix, **kwargs)
diff --git a/projects/mapillary_dataset/tools/dataset_converters/mapillary.py b/projects/mapillary_dataset/tools/dataset_converters/mapillary.py
deleted file mode 100644
index a881564cab..0000000000
--- a/projects/mapillary_dataset/tools/dataset_converters/mapillary.py
+++ /dev/null
@@ -1,245 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import argparse
-import os.path as osp
-from functools import partial
-
-import mmcv
-import numpy as np
-from mmengine.utils import (mkdir_or_exist, scandir, track_parallel_progress,
-                            track_progress)
-
-colormap_v1_2 = np.array([[165, 42, 42], [0, 192, 0], [196, 196, 196],
-                          [190, 153, 153], [180, 165, 180], [90, 120, 150],
-                          [102, 102, 156], [128, 64, 255], [140, 140, 200],
-                          [170, 170, 170], [250, 170, 160], [96, 96, 96],
-                          [230, 150, 140], [128, 64, 128], [110, 110, 110],
-                          [244, 35, 232], [150, 100, 100], [70, 70, 70],
-                          [150, 120, 90], [220, 20, 60], [255, 0, 0],
-                          [255, 0, 100], [255, 0, 200], [200, 128, 128],
-                          [255, 255, 255], [64, 170, 64], [230, 160, 50],
-                          [70, 130, 180], [190, 255, 255], [152, 251, 152],
-                          [107, 142, 35], [0, 170, 30], [255, 255, 128],
-                          [250, 0, 30], [100, 140, 180], [220, 220, 220],
-                          [220, 128, 128], [222, 40, 40], [100, 170, 30],
-                          [40, 40, 40], [33, 33, 33], [100, 128, 160],
-                          [142, 0, 0], [70, 100, 150], [210, 170, 100],
-                          [153, 153, 153], [128, 128, 128], [0, 0, 80],
-                          [250, 170, 30], [192, 192, 192], [220, 220, 0],
-                          [140, 140, 20], [119, 11, 32], [150, 0, 255],
-                          [0, 60, 100], [0, 0, 142], [0, 0, 90], [0, 0, 230],
-                          [0, 80, 100], [128, 64, 64], [0, 0, 110], [0, 0, 70],
-                          [0, 0, 192], [32, 32, 32], [120, 10, 10], [0, 0, 0]])
-
-colormap_v2_0 = np.array([[165, 42, 42], [0, 192, 0], [250, 170, 31],
-                          [250, 170, 32], [196, 196, 196], [190, 153, 153],
-                          [180, 165, 180], [90, 120, 150], [250, 170, 33],
-                          [250, 170, 34], [128, 128, 128], [250, 170, 35],
-                          [102, 102, 156], [128, 64, 255], [140, 140, 200],
-                          [170, 170, 170], [250, 170, 36], [250, 170, 160],
-                          [250, 170, 37], [96, 96, 96], [230, 150, 140],
-                          [128, 64, 128], [110, 110, 110], [110, 110, 110],
-                          [244, 35, 232], [128, 196, 128], [150, 100, 100],
-                          [70, 70, 70], [150, 150, 150], [150, 120, 90],
-                          [220, 20, 60], [220, 20, 60], [255, 0, 0],
-                          [255, 0, 100], [255, 0, 200], [255, 255, 255],
-                          [255, 255, 255], [250, 170, 29], [250, 170, 28],
-                          [250, 170, 26], [250, 170, 25], [250, 170, 24],
-                          [250, 170, 22], [250, 170, 21], [250, 170, 20],
-                          [255, 255, 255], [250, 170, 19], [250, 170, 18],
-                          [250, 170, 12], [250, 170, 11], [255, 255, 255],
-                          [255, 255, 255], [250, 170, 16], [250, 170, 15],
-                          [250, 170, 15], [255, 255, 255], [255, 255, 255],
-                          [255, 255, 255], [255, 255, 255], [64, 170, 64],
-                          [230, 160, 50], [70, 130, 180], [190, 255, 255],
-                          [152, 251, 152], [107, 142, 35], [0, 170, 30],
-                          [255, 255, 128], [250, 0, 30], [100, 140, 180],
-                          [220, 128, 128], [222, 40, 40], [100, 170, 30],
-                          [40, 40, 40], [33, 33, 33], [100, 128, 160],
-                          [20, 20, 255], [142, 0, 0], [70, 100, 150],
-                          [250, 171, 30], [250, 172, 30], [250, 173, 30],
-                          [250, 174, 30], [250, 175, 30], [250, 176, 30],
-                          [210, 170, 100], [153, 153, 153], [153, 153, 153],
-                          [128, 128, 128], [0, 0, 80], [210, 60, 60],
-                          [250, 170, 30], [250, 170, 30], [250, 170, 30],
-                          [250, 170, 30], [250, 170, 30], [250, 170, 30],
-                          [192, 192, 192], [192, 192, 192], [192, 192, 192],
-                          [220, 220, 0], [220, 220, 0], [0, 0, 196],
-                          [192, 192, 192], [220, 220, 0], [140, 140, 20],
-                          [119, 11, 32], [150, 0, 255], [0, 60, 100],
-                          [0, 0, 142], [0, 0, 90], [0, 0, 230], [0, 80, 100],
-                          [128, 64, 64], [0, 0, 110], [0, 0, 70], [0, 0, 142],
-                          [0, 0, 192], [170, 170, 170], [32, 32, 32],
-                          [111, 74, 0], [120, 10, 10], [81, 0, 81],
-                          [111, 111, 0], [0, 0, 0]])
-
-
-def parse_args():
-    parser = argparse.ArgumentParser(
-        description='Convert Mapillary dataset to mmsegmentation format')
-    parser.add_argument('dataset_path', help='Mapillary folder path')
-    parser.add_argument(
-        '--version',
-        default='all',
-        help="Mapillary labels version, 'v1.2','v2.0','all'")
-    parser.add_argument('-o', '--out_dir', help='output path')
-    parser.add_argument(
-        '--nproc', default=1, type=int, help='number of process')
-    args = parser.parse_args()
-    return args
-
-
-def mapillary_colormap2label(colormap: np.ndarray) -> list:
-    """Create a `list` shaped (256^3, 1), convert each color palette to a
-    number, which can use to find the correct label value.
-
-    For example labels 0--Bird--[165, 42, 42]
-    (165*256 + 42) * 256 + 42 = 10824234 (This is list's index])
-    `colormap2label[10824234] = 0`
-
-    In converting, if a RGB pixel value is [165, 42, 42],
-    through colormap2label[10824234]-->can quickly find
-    this labels value is 0.
-    Through matrix multiply to compute a img is very fast.
-
-    Args:
-        colormap (np.ndarray):  Mapillary Vistas Dataset palette
-
-    Returns:
-        list: values are mask labels,
-              indices are palette's convert results.
-    """
-    colormap2label = np.zeros(256**3, dtype=np.longlong)
-    for i, colormap_ in enumerate(colormap):
-        colormap2label[(colormap_[0] * 256 + colormap_[1]) * 256 +
-                       colormap_[2]] = i
-    return colormap2label
-
-
-def mapillary_masklabel(rgb_label: np.ndarray,
-                        colormap2label: list) -> np.ndarray:
-    """Computing a img mask label through `colormap2label` get in
-    `mapillary_colormap2label(COLORMAP: np.ndarray)`
-
-    Args:
-        rgb_label (np.array): a RGB labels img.
-        colormap2label (list): get in mapillary_colormap2label(colormap)
-
-    Returns:
-        np.ndarray: mask labels array.
-    """
-    colormap_ = rgb_label.astype('uint32')
-    idx = np.array((colormap_[:, :, 0] * 256 + colormap_[:, :, 1]) * 256 +
-                   colormap_[:, :, 2]).astype('uint32')
-    return colormap2label[idx]
-
-
-def RGB2Mask(rgb_label_path: str, colormap2label: list) -> None:
-    """Mapillary Vistas Dataset provide 8-bit with color-palette class-specific
-    labels for semantic segmentation. However, semantic segmentation needs
-    single channel mask labels.
-
-    This code is about converting mapillary RGB labels
-    {traing,validation/v1.2,v2.0/labels} to mask labels
-    {{traing,validation/v1.2,v2.0/labels_mask}
-
-    Args:
-        rgb_label_path (str): image absolute path.
-        dataset_version (str): v1.2 or v2.0 to choose color_map .
-    """
-    rgb_label = mmcv.imread(rgb_label_path, channel_order='rgb')
-
-    masks_label = mapillary_masklabel(rgb_label, colormap2label)
-
-    mmcv.imwrite(
-        masks_label.astype(np.uint8),
-        rgb_label_path.replace('labels', 'labels_mask'))
-
-
-def main():
-    colormap2label_v1_2 = mapillary_colormap2label(colormap_v1_2)
-    colormap2label_v2_0 = mapillary_colormap2label(colormap_v2_0)
-
-    dataset_path = args.dataset_path
-    if args.out_dir is None:
-        out_dir = dataset_path
-    else:
-        out_dir = args.out_dir
-
-    RGB_labels_path = []
-    RGB_labels_v1_2_path = []
-    RGB_labels_v2_0_path = []
-    print('Scanning labels path....')
-    for label_path in scandir(dataset_path, suffix='.png', recursive=True):
-        if 'labels' in label_path:
-            rgb_label_path = osp.join(dataset_path, label_path)
-            RGB_labels_path.append(rgb_label_path)
-            if 'v1.2' in label_path:
-                RGB_labels_v1_2_path.append(rgb_label_path)
-            elif 'v2.0' in label_path:
-                RGB_labels_v2_0_path.append(rgb_label_path)
-
-    if args.version == 'all':
-        print(f'Totaly found {len(RGB_labels_path)} {args.version} RGB labels')
-    elif args.version == 'v1.2':
-        print(f'Found {len(RGB_labels_v1_2_path)} {args.version} RGB labels')
-    elif args.version == 'v2.0':
-        print(f'Found {len(RGB_labels_v2_0_path)} {args.version} RGB labels')
-    print('Making directories...')
-    mkdir_or_exist(osp.join(out_dir, 'training', 'v1.2', 'labels_mask'))
-    mkdir_or_exist(osp.join(out_dir, 'validation', 'v1.2', 'labels_mask'))
-    mkdir_or_exist(osp.join(out_dir, 'training', 'v2.0', 'labels_mask'))
-    mkdir_or_exist(osp.join(out_dir, 'validation', 'v2.0', 'labels_mask'))
-    print('Directories Have Made...')
-
-    if args.nproc > 1:
-        if args.version == 'all':
-            print('Converting v1.2 ....')
-            track_parallel_progress(
-                partial(RGB2Mask, colormap2label=colormap2label_v1_2),
-                RGB_labels_v1_2_path,
-                nproc=args.nproc)
-            print('Converting v2.0 ....')
-            track_parallel_progress(
-                partial(RGB2Mask, colormap2label=colormap2label_v2_0),
-                RGB_labels_v2_0_path,
-                nproc=args.nproc)
-        elif args.version == 'v1.2':
-            print('Converting v1.2 ....')
-            track_parallel_progress(
-                partial(RGB2Mask, colormap2label=colormap2label_v1_2),
-                RGB_labels_v1_2_path,
-                nproc=args.nproc)
-        elif args.version == 'v2.0':
-            print('Converting v2.0 ....')
-            track_parallel_progress(
-                partial(RGB2Mask, colormap2label=colormap2label_v2_0),
-                RGB_labels_v2_0_path,
-                nproc=args.nproc)
-
-    else:
-        if args.version == 'all':
-            print('Converting v1.2 ....')
-            track_progress(
-                partial(RGB2Mask, colormap2label=colormap2label_v1_2),
-                RGB_labels_v1_2_path)
-            print('Converting v2.0 ....')
-            track_progress(
-                partial(RGB2Mask, colormap2label=colormap2label_v2_0),
-                RGB_labels_v2_0_path)
-        elif args.version == 'v1.2':
-            print('Converting v1.2 ....')
-            track_progress(
-                partial(RGB2Mask, colormap2label=colormap2label_v1_2),
-                RGB_labels_v1_2_path)
-        elif args.version == 'v2.0':
-            print('Converting v2.0 ....')
-            track_progress(
-                partial(RGB2Mask, colormap2label=colormap2label_v2_0),
-                RGB_labels_v2_0_path)
-
-    print('Have convert Mapillary Vistas Datasets RGB labels to Mask labels!')
-
-
-if __name__ == '__main__':
-    args = parse_args()
-    main()
diff --git a/tests/data/pseudo_mapillary_dataset/images/__CRyFzoDOXn6unQ6a3DnQ.jpg b/tests/data/pseudo_mapillary_dataset/images/__CRyFzoDOXn6unQ6a3DnQ.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..deed3177806e443cee9b00e0fb0e80315488742e
GIT binary patch
literal 1227776
zcmcG#Wl&sE7bV)z1Sf>x!QBGE-3hLZdlKA(Yan<?)4?Io5WMlm8;2l)#<g(?uEE`s
z;hULyuV!j~%)ENDZ|(c%p4xTSxu^EId#`o=&HY;iyiik8RRW-)0RU)E7vSF_KmmY_
ziHU{z3>ymz3kL@q7oUUx9}f?o@+C1L3C$}yTAEkX)bz|eZ1jw;nW(ARML1sb@(BtG
z(y@t2iSkSG2nh23CkPr24h}vZJ_P{*1wR8d1ONZA{p$n}VdGU0CIHbG0q8_%Kq9n%
zzW{Vk@A(YvzZ&4b8yY$g;~6FvHV!V{(*VQ^06H2Fh>ih#_6!5#X>{<@a{va>vzH8f
za+t)R4_J&IB>Z8CdDu+yHC?2-6DQ09R-WNFxMbuMl&@G=+1NQa1%-q~M8(7v-YP07
ztEj5!=^Gdt8Jn0|+t}LKJ2*OddHeYK`3D3>L`Fq_iTMgnN=`{l`<|Ww%`Yf~6&071
zmetnPBN`f;np?Vie)aYt`v(Rmr%=-~vvczcYwH`ETiZLkd;6zn=NFe(*EhF!|G|X@
z0RA^vPxt=@?0>>V^n?o?0|SVG^&ebl=zdQQB*J*cz=!!#4uti=gP4&&44XtgF|Vcz
zhe<&9gw)D&0+)<gaE;~kKhXXwvj06`;s2kI{Xf9|Ut9|Sd?4D>#{&`pWB}LCFVLVK
zwDnd9F{Slzf7qUqXf9?VRN+{=vych;UVxHBuV&v-JeXt2khq;@PZ=`~1<2Wfvr~`D
z_OkFkZ!g(~gb3=;7a&M<&_X#lv^8{f(7^(#Ss+<F<t;_JZvZwY&E{geWCVbf-;qPx
zR6`GtALppNBa3sONE1Z@(AE8`pHW1AtRBbCL}C~E5)6Rt%JhZ4j6=O*2R!WNg8}UM
z@jJ4ZQl%a$fuL-5G-WsgEO#6ru7gG5BP8g4bfCKoR@<bJ0NqZH)p^V$!u?mz)qfDq
z*OnZpBHL9y*hqpuxu;1^ZOd=k2wI<(YdU9N5_k3od#xlTQAIG0uyTID+bD7{PH({O
zmA2tgdMhTKLIiGTSoPUXS>&Mh&>IC`xfBr!7DJO%z_fw-7W>J~+{TuuP@e+k>=e87
zsII~S+GTb+7=WTcYA-O`VP_`v#bp7t?!`p`96(QU67_|8vQRM|9j;6S8hHz|+Q3VI
zHGgcMgmXqwknD4@9=R2~&j)jmkbo2c|9?Aa#Ja`H4Rb^sw%c3I;%!5^pi}rhJCI!I
zWG1Izkx}_0@hJIDdhu{y)6cJ(?`f(057$H}duoe^(dhn`T}&O$G{a76$0{3&OIox#
zw*^6=gf5d#`<?FMbUm>{V?0-nWTK5&#_~JvbStC_L+dnbvZ@SZ>y%TJDky^KS$k^l
zN-CtI+oU}0kXPzIfH~jP?RDu5Q!Y&^Y}ly5eW_>Iv&42Rui{WiLfvAD@>y##BqG%5
zOE|&cjT>RTily|Y_MyS54<^~dWD7ltMWzKqC48%S^z8otPKZc&sld01UjM3J9DZ!c
z)Zqs=3f;oz=7(*3i^~E|4d*f1%6;-zJEVuwv?qo?@)x;OamT!sN0{Qb_H>=IpI6W1
z5!oz$n|B5Cqb$U{_@%PHd}BXZE~=qOLTP?v#elSx?X>&cMMo5v>~ROfEQ7PjE%O?G
zea1bikbL7<Y!d5($H{p}YjqCp?|6#uX}-`l!}9ketoqwO0NS2KVkue02T_48o2VJz
zxP^7GiIB|*$V|!tPyS3P=V-ChKR|hi$A!=?@dLl{8a<NW+JiBNRql~+&z!c|zWl~l
z0Y6sKUEmX(i*VN&T0~=lC|N(wi(>W^Tmdl!Y@EU}KEgK`)$MG7$Mj{M>aQU-J@!Rg
z+pRKq{_%=YHKojn>euRIuM1}c9eVe;aeqv<aQfTL8r1nC%Goteyi=L_)^2At%RlLW
z)rm;>?DTpHo*Nx3WR%@Za&xXxX$sew4qZp{`UN|q(=hx020_*N(`pIZGX1SDNf(-}
zkMzWTx7`*xR(z;G_u00kaAT2)G@|nR%(>G4+tL1F1LphfWcJt9%*#S@mCpFf_p{l*
z=PmZWYdiaA>(^wx=&OcnBJu@`j`KW(f?|FLE)7=x^uuBjYAyQocBcN8fzFv<sR9`A
z1G`edB}s)L-m5>5(bL(G4%^uehpL`Y&=+vj&vgve&jU&17bTl!FME`k`xh&Gu(BGe
z#F32X4e%{p8_`oA_=%W*^*F1SXmK5V!R@CuIc_G@){%#bpOtcsJ2e9P%pK8o9}%Om
zMcNYH&1x|cxi^0kM#UKhm#O^&cuzYrCl>g`$%^39aw6v!R=+0@Ev*+o`EaSdEY-zh
z{;aWNW(65s8boZ5dd$t(BK|mgRM(V#tW31JeaCzabB_8lR{F=PEH}rr%x%XbE1|gE
zAY3>DDR!*8bQs6Wk7J3tRZ1jYW^j@4f_nCMG#{H(7B+u0^~`er{6jA;LWmZ-NFF3F
z`tVK1F`Hsuey!t(@YEnSpn8ztop_){BE90RR)Et;P;1z{L!f<>&<}J0?`}Mpc1nM5
zz}?BKX0uooxZ4V8D(g2KbU9Np^6%n|&l<mDt1c5i3{Gd3Ex|Xl{Ss<aC&Imjrc5iG
zxQSBUPxl6_sSGi3(WcYQ<V}3!{<+3nPtHX*pHcm1>3MXW8+HCB{=HqM<7>^&xLVz!
zLug5&W9^y*tQoqN2U4wOC&Ceat{;Q#H|4}hJ(ZP!jR%$=*OAe9{yGZ*dSv(g{>Llz
zK8H-EQx_~yybM@Pr=7l6J-5eqTAPW=tpw5?{3WB{z^obsgacWMlgadv+WXd#ViV$#
zqjgCk?_sn$RRn$c5RB6s;5xU@j+VS<L^||bQ<3=%ezXXkh`BG!{LXqI<wxfa?O}=O
zq*v_M=mC^vWk3BW;bsya5pQ2~1W|*#-8!9j?@H#t^9)V&sJm~ObzfiD3G4<`IMySl
zmMttAveTtFA71q>dXbb7-kThld&V`!3|^bQt>sKuOnDwTZ7``rGvbCrTJGxG$b2Z)
z)wNx307?l5zV|NEOClN?dd=IIRvpPSZqUy8*CF-=enO)GjbZuz`@*HLsRTvch7Pji
zugP?WUKT{j)x^%iF+9>!`0ts2e4(CkS0W7Ss;qQw<y!o})E!sB>n=w6<xN^;pYW0t
zp;Oc7eOQJ-{m1j?Qi{CHp2!X{Y$?>_a+;&)mJ_KG7PD0g@wmc9a~g5IE4@d5(U2FD
z=MA#DmrAT(@R-B6@-&i-+V{HD7cDVDgcFZw&hT3jmKCI;LOj}BkH<Tx{AF?vtJTL1
zV4~?Og9QsTf~nBk?tXHra`E`(aT{`8KF`xQ!V_>M5n#)`yZ$&~Ax-c6IZ`NTisvW@
zC9ky*dd$l})iRZ>pZ@-@4>Nm`2#b5L6JAVSL-Muf<zGUz$v2=m5VnpeDWiPzfM$0d
zculSc#4^u@lVzBcIZtHmiFbNs?aY#sNkvdtiX?rzfW%=S2@TlvGI-y?7reP7HDdfl
zN7V**Z!6rxd<v3)jg3XGf7(pP+owz)gz_x3PmW^tDdMz=UtzJ$9o>+dE@*2Yn_MKU
zXWS{KofbM%C{cRfg7}siSh_=}w&8MARF}c5#N_yJP^js~m7(WZRu_Vpz#S;(S36vd
z#cLH24q8vXQFZY$uc>dEs*)b~WJG^x(Sg{%BEaXh-R^!oavp25_99++D9up#1Q8oC
zQ)J@OuOpI=D>J&O6&vA(4@c97_0aES6R6E5soH_QiuDPY42Ty6Ja9<}R|q={g+Jw&
zdlXL-jgyK6TdXIaV8*$$c6W81wys(wuh_$WeWh<g4&0<!>1#vUi13(3J1S$N7NW8r
zNVcE?-|O4p$M#s1oasm=+e?TurcRaOT%B;^wwVtG%5D?|O}7SltJb!?njU$VlIE;X
z;MfTIA{>(x7**D28qi3k<0)0{yEt?&>U--8F`$t@5;%)EN1OR#+Z5*!!SOeMgoI$g
zG|l<PMk=-6WeLVFgh$gsp2|~3ep;dJCiTg<y@C4LL1<rwpajVKL2*M+i^C=h$s>WI
zrm<c95zY>E;7pLqOZQFce*gl#w6((fUw^$j{o+%y9-TdC5hn+I367kCBXV@k!2^AK
z@qrgq@#OwC(cm*@yOp13<G{pQqp=3^X!gZG9IR{g_kS@n{X&vQ&XCNKgsB}aAwrAz
zx;p3l-bY7n{(}S<&Idk4o!GxyRP>ITt`1GUTPrj*5*8KCG;)SG{7&euThA23V$c?o
zTt~QEn7moMCa+FK7K>GIS(zVuIlI{R0!J6gsbYi<XfaMhe!%u}tU5AQz4wnN;t`(0
z9b_%l3EIr#;&BBZP2X@^8=Vskif-P$>W*fbm-?C|miP|o*;{_lx4&>{uYw%p>mR$Q
zAOX*Bpc{7&Hc|a-H~J{tN~W~)v)vFctPhVCGuUZ=_9||Tbg+WCL5GLZUq~h;$t;xs
zf^R*Ec+)1GI3HWs!s)x&x4|THY>1!S!tt&pnCn%dM<egCm#`1}FcpyY5;LHD61n}*
zQw5Vxn-q8t@t7%lzA6_dTe=Z%wRx^)b#~rEXUUPZdEzYh+#ND!v#eivILWe<74)j3
z?bCd*pp|0RK+%urjF`ClhUd`@hpxXsZc^H!W#I-5z6Oe~rJP3E?^kLJ`SRZYvx^W^
zIO%C?9+ySEly;+HLcV5pprmJ<?D|Vissh{3lf1H}IJcru;Apbop<~tRf!Q3mq~fat
z^wsQ(Xt6>N{WHv9N1ioD#)T@#1V6U*$}~`mE%syD#ODTW)9?O}N~o6`R)}n|IA<jl
zByc+N6VHr~=rJ^UtDDy2VLu=p=hdG+0+TpP;cP|w`pWXK`0h;7!QPzq<S~+BytuyP
zC^!F-UnVl9xgWE3l5fTvE18FCx=Qpnv48ro%};pkEh6mNdn9ZOTJxDBeC&(VJ!UG2
zILP$8J~UBZ!_!}JVER9BrVwF93S(+JHBuNpQ$hoRM+>WR$;a8L(Tof|um0+TE5D$;
zE4_mYh8NIx4vgSOM{pA6Nb#Ccs%&Y*aDl684GhCljkp;kHOj?#cZ*+9D@G?WQ*Ms*
z@Sr?X5tH$rah_i)87|QemV@uXSjvf9j|vQKDTsHS$}NOLj!Cg0J2V7JS}TZ_qJ%%D
zuFCJxd6mS0`bW0>HP)SCB{mXXI`xIn8No?P`$In#-}>RfAX=v&RrP`TvmirvJ8Q_f
znYck7_9TC}YNwzob7-{7>sGb(AG9M)k~1kazYJ>IpkuajPnkl^NZv&rJl{?0q{4tM
z>wAI)dqGbOj4y%j!VT9*ipJ+Qg*28ENGGy|0IRvw5HGEaf+QgummCG%p^w!mGC?zS
zojr%F&Ete0TcaMGBBOm%!lm_gxiq<#ZGa#4vcScDl2>&p3y^mGsBJ{_I&)*#M2Neb
z<TT2vNlF@#;G?SWLZ8mX;6S~fnZ9)+PIia1J<=zTX-u4-()W!OXHj{sN^eo)XFepA
zlv7M|OXEA?!8PsN1C8&!Mm8TNtUu~FHZ5U?bh*Q;dl?(^OarTu*4T#atCPbWPi~TR
zlWBEK9_8Mhz)4!0f1<fn=<-c*o7^)a-s?0)o(vA^<|TsJ`vi=H)LHzm6nG7Hjb`es
z!*VrLJAvgOZs8Y0H(SmYrwK}8i*trbw_xjG&!+ogn0K|H0J4#@LTVp2-Db^lm5d@%
z<EQ*?E0fHiM91YdS-<>?_xN2aWTV|4ds1of+G_;?_om8>@gf}*za#E1T+M8vI8&RF
zHp_vlx=i%_Qjx`KSGjW?_N=W9Yp60?TtFrZ_E*ZZgG+^+0YdeZD`I#0#Mq$=m|li4
z=M)v6#qYqMI6gKy4<Oq4z<tAZo=P~tk85C)4^SZhgX9U9B3!NE#&%RZOwUo9vc=1L
zTWij#(oUDtWbc^LC?$$39Ic#O*g@;O{=JWowNXbL(>;V|0+KyFrX4I<K<kLiEdhU*
z5gM>94Q2O$!0l_Z+d2LL+!X0}SxVz&prSz9>Dl2(c_ro2a^VUFHc5STs;rJla@1tF
z07PGN$(LIKGo;;r%=BC8_a>%=1e#p^$fN>l9mM!s{4GVs6+!!taMi8NhaScxXMLZ?
zIi_8HN7EkK@1E2jNWhKH`co2=2w}QWwD<)_1V^09HH}M#$_rAOf}LspiR4}?ISTp~
z3Eo1ULB=Y-NxDL>M-0d&B9cwb-#VWsL#TuFCph@a=yw*rTPd}tLF?q>@I)TZJoK2;
z$#<6Vl}lXwDmYk|=0#a6E#BdLw<7D4n8v3wP48kTu-1ak*cfjm<Q<6{oTVkwE#-<H
zC!2S;`-|Ppe5=2KY}I;%a;T+`P*(X8z(|fR%fh`~AoxKB96GJGXWDQfe<??H0{kpO
zv6``Jn7_pf>E|3?h%=`PuiKhux>O%s43lgx*gOAPp(Q7esMePrzfFFvRo;lz@Qkm@
ziXb8(*qJp`z-BF;VvLk!`tf3BoAL)GAq5^7Ou6AZxIr_bE!1V)z`03;x+;r=k$#{&
zHS61X=}j9BJ$<e5sRIix+PtLn85gB0`0>v_0H?ZH1ZU~v`p?g!_0d&2&5^U7)@Ze8
z>v{advKmQB?y7yk9G}`=HSp=Am8NjL`5eMQ^qfC8%eORFmf|)P;#*=3D14z(Dxk_n
zjr(ns1o~rujUSz`3Skrk5n1Uk!ADM!{JKrQ6l9+xz%EqkL|U%upQ&RT5M<q1l_;l%
zAee;T0ju`(-m|>USd%NxNaQ;M9)grHS|hN`{YY)|<HcOIV`F|6DZ2*d@>ghQdx}Hr
zKHD)i4sQ501|soe_{m>OId%v9kX<4T=5XONF^7ajnEHZshu!*|W+K)IynZS8WEsa-
zUP;oyBrHy5U~6Aryen|==;`wmP}GoI@{w;JgwsKr*nin0_}2$EA_A30kRhB5{{1;z
z_B7`j7M8)i7Gd(dN?v+e)DbnwoLezIU3(EA`)pA-*FV5-)*EBtz*Vcdk%}!p&X-co
zu6@|xM=j2gACEJs-fXqst^F`;g!E(GMctJ+mAK*pSfQD*;{=-8zeJ$x#fvfamP(k<
z><eMq+Av-cTsc#_jaKaDlAQK(qGFQ!pI@+6ibf5~%}lh`)CRf^4d3c9%nglcaV5fn
z0dea3$(4!@dpWiZI<5YrAqczQvaQV#qmW7|@oCJ4rp9EOel*K<gkG@h9Ms*KfQp~X
z2dmw7xyRMJ@D>~XxHbd5ei>jxi^*9}uIyB~&wN}mI7XNDxi7s|9GyR)oWJ8J*DiOp
zrtn#S#c#2_12tGETV5%RiKp_iRLNW4cTIuzf}P`aM%=XBew#of>C}k5;8iAZ8qImH
zCs||m+t_U7n(fB-DBZOr?0*0srYsIGBQ5S-72})0TiDw(RpUjjG1Fc9lPN@YXXaD;
zfm=VDTV1~H-upVC?GrVtDrE`$!Ii6DjsJxN(Lh<2z6f4M(q1Dd0ghi0v}*WiMz=tC
zYcX!v8P;^l(S$D<Nq~|*N==%~EPhcloRk&f4RUOK`--yAL1bb1kD=j26VE?@AS}dy
z=3u`5A0Q%xCSFUw=^Lzx>s-u=->E9RgLaGt(Z1YQbnpVyAmIgxzb;38h<g9kT4PO#
zUrW<(UeT;%Qu_032jM$M0jcR)*hrc1YHNop;=mI4T|2WUZGDtt;|#?`zh7viKS-nU
z9$Ts$mjIWFz@V~%`3#bCz%VwbT~el}^_<ChrMY!WDS)piBxOsd02e@uDiEbSP_%I%
z(SPHG;Te<dFr%~!tJc(%#aU_F=nKI?J!n=czIOZSl1uRG;<8Gma7;+e5c7k-bB}Nb
z)l}L7x<yNC*4YZ8U5OpWAtq6+!k!OSz-7-5{h$54GvxGjW@RE@mXXymfyb-UH|3->
z3Dn#0m&0`fMcY|DP<c#kIKQm)G@Dd8Wai|$t1jm|VAet+@@uR+-%L|$GjOS9LCXKw
zMBkP%Za6py%@kxdfPw!9Fk%pepUnAuyG3H|%5h>NZ-=o6Pu5<Nfms0G#=ES0-*}6j
zUP#Yy20FM@2ow<Od}ESkTKeA7_O)5WE`haSFbIDoMrveJ+J^5L_iS}#pO|&ZpQY@a
zz_x#Yds)wcZyk}-GKZNFo~1Yjexj>amt{Su-Ck~Otr?!<zuhPEqGDJMeTwd-KJKQ9
zE#JAvpQ^vvy=y+>UF#r9Y7Q~C;?pXL<{9dxkuB4{m`UoFo|=aAD$rp0c^=T0W8Z9F
z@QlgE%*9zv?^fd3R<CC_TSD3={5!)RVZwiE1Mc0u;-*tL&6eL^H-GmlGM`f$;CvDL
z5d4k#WxZ}e9&<!C*Tm~17X*d8#>7PzW-Wr7@wa-4xfybsoszvka7*r8#`E<Br{sDk
zTG<-wB3{nQ8j;L;=Gb~aQmu2d^9dr?Px(ujfqi}{4OjQe=O$Xd*C5rX;W+AYzRptm
z&-L;;o2jcd`dHhm=en|#%-wh1@LiOqv0t;&+j#~W>_Vok1EV)qw=;?WbZHj@hN+nb
z3c`?!KlUpSk1oNS^js`pHmZ;~D}E3v9+t$RO~b*=%ZxUeEM|^BF-u|teb07Q9K0Sp
z>L?Ib-{vl`>z^yvNU|mAT{tGTLsGsM=Lk9YM9j*=yu)I4bmuL!#}1(31E2i^VD(4n
zx_cz$Ui{%g>2FZ>IV*5ENo0+S(q3ddl<fQG=FLBF2;7VZPQJ&*pn1-rZP{G(qw`eB
ze@_-SkO+*xo(J+B8YKFu6kL>(e`aPt+q~0xrkLz~-vXJ5{6wdqpC@0Mb!Sk&nN#Hi
zXvd+pCN;fh-dWO5q{}2(>_W<^pf9=Z6gl<ppqF(AATP@&Sg&YN_@$q*$zYG=sS4+h
zRG6)17j(8vQ|%ruz8&JOlF&Z0l(+(I2{<ZT_-+>GRN~z|S@yW>?>73dI1h_&@CCEI
zKO+;$=xxME=!TQ{qLS!aQHhZHm4di0ysDfs-SsXLktQ3^vB-d=viM2FgfM;A&J;;!
zvYYs1STE~F*54HS^NT_<YN`Ih{=((t0huV)wTNU*er2L~Ck4p4EdBEW7;7+}YIXI-
zb<4Suzoh*FG>~pjP1`aj3P??1mq0y9bOzaxQPUjCf&zSld|_i78cR3_p%S13fS4d)
zeU7q_O%e@hu7?+*lpJ`pFQD;S#f+wejV;@Wm~-dYy9m+!{#?cPHRev0U{r0eQ%#HB
z2=DTnV!=u>ZhM)(EwYbg8Es<#po&}n;jJD~kl%>PJLVkIf~y8(pmu$Y%w&Rb8>Rn6
zfj<`9{&sZv9{^XIZ{Q$IZ9`@JO<Ym(@IQbvcntscSWV%TBDqGHI25B_Y*}Bvn#Qrq
zYbERz(NbwDdA7FGWfgA2p;*8M>4rPKfPFTWoaNA(B3@A?6*EArGUkExqgRlm*VIC4
zfZ&hTSEhh>YpjXx9NM%g5plnxc*$v+)}vN8fRhnZ2tnR{%3PeT_3urOj<MtV5%GZ-
zSiiyX&838x`5}D25kOiobDbyhtI&|zOFe-QOAt_as+xUE61kca=t#Y(gT9LSghAJT
zqoinuTW&-2Ko<C;e4w*e4><b0ij=!2>ko}1k#FVHO2Pohvxiiemw=y9cs0)PkAD$R
zb>wXzDr2m<i1%qS0dJ%){@8dIg&p5cX4eDSC3IwP(F$3^upgkZVs{fcnQRDl`a2z9
zXlJ4I2<x9$O7vj|DmE{3lE-Jr>ME42@d)N5g1O9en&M`b3lk23iOH6V>ry5=EvaX{
z<XaSbmqLWPiJ4{lA0>BASHVbzOw^=c>s$igB|KJ2WH^kng=i6B5LQQuLfHnrnrI3u
zurnMY{mU~AUE({C{eqUG#*4EJC2XhKm36!E2;XOGrl+2*2ykXeu<gH9lB%<m$m=Hu
z#ng1l`0r2~)z0-Z*C?}<>^hgW6GgRe+r-*LeGTCi2b!4nRqXiGn~PoirGp!vl9gWR
zo+5LEH9Rpt_g6CT*f>6asQW0!e5PGm0W0;D9x7M?3qX^33r-3Ib<h?dpd2TOaWt@_
zsbz$qJ!3k7VER=t)bT);U|>wJ=)0SQt~JRKgZPAcypx8<fd+bfpbRJb3thd|NgXt~
zO;DE3Q?B4ekC=jhz@`9)J-LhRw1~+tY%LDy{O<?`>Wd<@8&Gz1e0Q=~F7ULV{f!G)
z4IrTGb`e6Y;~1lbYPy?%YUrRtwc&4^)BxrlN>YwkYU1azxS9;GLqz~9J5tMmF+~S0
z?gFF^fub=;-03wW>-Iih6_~83P?IopvrCK`Ok_2!EL+ui0qhm8^K7pF@I<F^s=p`^
z1U%y=0q7_>Jng7_iX`UfVD{YCLMZXoY04J`R`nc7O3c*LN`{Oc%|E~r`n5_rDEnM^
za`WhPWG_jGw_g!`!GUt14gr9@lrjEubxHRI!ZOM|<FX{>8xs{chQzygLea`CHT)^+
z2gN7$^Z%lw(>5Pkx^7q~tz4Z>l5uY;4@L9^mzSNY9S|1R?j@E3ue)<{PO3zv9@wg!
z{6>?yxLbC10vg}PZ-E3CYJsRW5sKKJ1_1Ro>BnLHt2=MdyRpED;!HL`SU)N24+j_T
z#UT0nVZJiAJ^^r}em$U<^=alhHE?rVY&@3gPlxCUrf~*mqDZD3G|k7-mXKqhL*s?M
zBq3*|a5*Zj&tq>#e590xOw9~J^jGf;tIH-Jd%mLOpV1st-D=E@6&XN~s7kE9e*i*;
zNhXmyy?S@D+YQOE9JQ<BDAbu~NpXWozCTR1zb6qq`$P49A;T0Tt#A8%KzAaG_NMap
znpySqwv2<yeEeO}e(=G&URvz7sY`3AALZ)BgM$`&`B(IYeK{wKDtz$nuWO0b^UCz4
z#cD~A=1R__7Abs8EMFNSW9V#jeX!5$y*x^yN{RXvcu^MhC;D}pobc#?7hT33)OO0h
zjLgtXU1C_+@7E%~bmTPmg<W8lTg}>#HrfhL=?9{;6~mtH9hn%mc7s_-k0K{=%OT^<
zI3p@Gh}*kgMnOES#qVSnLJ*GJvHh)T<~$^iuiAe0(c&a4`=SJUc8mwcj&2uZq#XzK
zHmBT8hxA}K_Uo!U=iawFMrWfh=-T6}0$WcR`^+*0KUdecY8~@Se)>7n7BYCZqt$HI
zDpnY7KrJl#P+paZY)L(WGBx)JKR%`#J~)#aXgW7*5vc8MM@WAT2oKuSceJN@yfCaa
zhc!aoD>s;gFlN6oe$=~e7Oj}CT(Rg6@~*^IUTGB(w{TudX)v_gC(vbk=2c%x`RL5n
zV`>mx$5->S>8!GAA-7rQx7rYNd*3+njgQ1zakg|19S$2VL>B4hivZGvElr8Dq!f6$
zc<{S!@@!fH-o_*q0CPVzwGp3Sx8df-xKY4r`-jV+%ZW?f>lXmw2H(U>r0J2Q!byQj
z+Z0q&SU7qUKfJh#HoDB)8pNSo$_e{X=+6=FaWDxJ7Ga!QD&!v^_bd>t%<G``FBl4L
z@nBFANWgh?OfxO~OAFash|XcG9>c2IGHH{D|MgCM*K;81{nDxF%<M!z@uustdvmWL
zbW>weysOU3#u^^@B^*JA*^qoCQKXU{ZYq(Td)-x$rzFIai8GdJe%@S#ry>h<*mbI?
zYoeUPzOIbudnKG|TY@!NnX)*@4~DnqIBi?dSoernW>h$VbbL7lG)W7a`Q4QnGZ~rt
zl{K;=)QJ3iwzI6~FtG)>aV6q$Z!Wz@sP5l@8j}3=Qwgt|u1SaY$qi>kUOuK`NBCj)
z01Q1Fo^gEk$TC2|Id+Fpx^royMokbR)T|k7F)w!Tb(vY7)Iq}6>fHwjt#ffh@M$TX
zZ?h9yvo%5#!q=ir;^KSfdp9e(3#<lKsqMSLYSP(T(+fl02?O(3;8BAl4NVH1*9W@k
z!zHUw#bIlvDWL*u=Cm`OO;Jf|U!foOLyjt<OT~=}dclp}pZy5-^n^U9`~rK+yR99}
z{9Fu~Yv2C%%PA>4<~a&a#|y+w)nrJ^Z3zkx$zz%`xIi@uU)n*ka}8xhB`1$XWrX=u
z`&KR6e%KjG3=uDZN6vJ$qP+GrtbW~1&;i-#XTBQafg~0ydwmyYNoEtlN!lBlsuAu;
zibF%jZ`2PPp0s?~?CKy&&p~yM$w;0Jr%%YKc1<t4a)x_>qjw7G&$9Lx`xmeRXZGk{
zE>jksZR$b--Kbx+Tpg2-v|^zQN^JBfp7RHJ=t>XxAA`43jXd&t%sx18X}<hPoxqv$
zm52(7>x2VJjFH+O#t<({AP~F@9pE2m4ES(tqWeV_4eP)x-eoVM2D~BZrTYhwv|NzQ
z(B2{~^FyD4x?5#6+K4k)kxQV}&8s=yYb7nni?|w;n9XP8Ju_vZW-(kn@Sx70MR%>T
zXTkSvkn8P17HtuX-6MgQv#nbBD(#-{Rv_-V?A@!`y2iMzxBROwMFj=b1!ApFNRZD%
z+_Wd_-MpLOUzZf<|1xNTDbcsdbsnGU^sfSuF9*NX8l7WF81J0H8rq-}gImUahU*ne
zl;F*>!iaJ-?PM)-_rd{oLnIUBh&^k^_`spt$oM&ta8~frG|H>%VuuM~Z({bCapoRm
zRnISwor=_5TG{=k-x~La(PH>C!JQ`1@W*s&!Q9DL@$5eW=B0sC_0#x<+sl1c$RWJ|
z0tzDrSDQqp(QYK|3Tm10#@K03nzYNJNO)HnZkb{AW6{%A_2Iz2`yhAWcZSd#ju!-F
zU-C$IKWvRKN3rE;{R4pN+tXED9jSSYw&#>(%nbuMUhcU1T5`pAlN<jXbSP+%l5FOc
z;Yl65^;(F2$#!2{>F{eR#ddfgvJwn(^t+oWajgJ2hLh1>tj8`h>5cP%gt$z&VUiWO
zPq9@$3iOn*pgafgzfQh&q3df6${`yoHF=EJBU<WKlI)@wF=tWKyZ({B=qGyW=fPQ(
z>BS5SIZmI4XHqgGk)FR0hy$YOEjmIqPE*6ZKlx%MY6z>k443@^1Uo;YwIA`olP=ig
zP&jAPpiNDd`sIg@?P5PuWwF?8&8kFI(^XL(q!8pkbE1~*U|yDe@t6YRqHpS>WZD4)
zO}>67>=&W^cL>k>^|7V1`p?znb1sxf8Z;HMqTWk8@nF(-+&LX=3A*{>t$Ah4Ec){0
z$`_c;K2iFX^t9uP<J(5A_&~F{hh8HoMIJMLh%HO#m{@7*r@BNv7d^FXIrmx>IX0jl
z$?+UIhj~AFmO*)p8wTz+ztNu2KS1?SZm2d(O84)|lV&=YYJk_3v&;L3CG=%Zm%BU)
zkea|4P1ys#6s%j5i2i7YRGn%rO_8n10De!yb*RIYcfIhio@_)jnl=RrI3yijvHJXC
z&w!_UxKbw$)7_bK=g>3|W3g+4OMm1dvmIM<z1pdhf48>Pbxd--^cJGsZr0?*LD-Kp
zDAULhnGECCt{>X^!(XFuv|z?0Si_gvAOXBA`y(c}M$Fsae_iIbE||7V0*vE0N~o}Q
zepq(r5*)OW&x;2(SIk=~B|J;*9Mf?q#(C$FDb}^AGtNO(&2i@z8&K-ly}fV?gdBl2
zd@d?(-W)MB3t#gc+On8oF*aW5#kVn@DKsTNHGh|dB?PBk$y}>Qk|N!Md-b#5;!@ZX
z?CJBc4xVO<VNEtfRaQz{JfA{lKby**TJM;=#-R+gA^0(0;^Qh!Bhz!+K5_LT&+u&*
zvcs9FTVTKCs@c_U_9OEP-h^YSX3{?`zr!nq4mr3-Hr=~J?5R9e4lOG_kW*drxv9dK
zcGf;qA+P5kmrSG<#}rvi(ET?1Rqt{AA-l<;x@}K*LcvN?l<pj`>Z}qsWr-%E3^ggB
z5kq5sD0M%T*OZ$6;|A$Vv+uC+!42q@9XV@ovLo9tix`kbb+{0Po!N&w>V6Tdc<E~-
zPC(ub)n8yVcfx+<qr2FcAj7%CQz^+zdWgVNrB5~flO}LBo9jQ-3H8k^K#XR*P8*K!
zVo1y|+ZV9pF2`YsEqP6q1M@aav6@mD{jr5wsm<yB-gS6fk-zf%rSbM+;t^LC3eL^#
zHs^R=->?h_DL0u=9AG}*Gh!N2j+S}jGze2<smcG=l1dpPI2pWm9uD8<M0a<7i9AAj
z2JeY@N|k2TXc3I5S#v+un2?I=A_>zEo+`tN$mi3I#l5cLtg@>c^fN*%gOz*}9AW4(
z3QJd|MjA_>dfb~qSzPa@7t8gbQkjFPyF;KpHN{$6qlJ(g>h&fR3L)Q2td!I#Txa7w
z!ibOmQuUo4h)iYd<x7EEgC;oa?4fH=#6yq0J~ZMGgiK{ho}1As{>&U#nnV)l2fwaS
z4;$x-`$DR8ppLDunK*t(!&x#)l$NiE&25{;KZqHOQ+nu9^X5)=0gYfxtlWbW`vsT1
zD_?rru4=gt^A&npv7<wJqJGI=AC-m0`k;c<J7Tk$1Dd;Z8;F~wQZN_$qN&;7hi3jB
z#^h*f_(vtpa=wgw?#kw!?CFWcRWnx#AhmBr%<D?K%xi7xTv{raOS%U-#P8Su^ff`1
zF`Da8e{oAP1mRNT=>e|jSI~c}fQ7|Gd09TbubaE}6$v*m{%h``i7U6MGu`J5+gUKf
zm$jaI>bjC0Q=VgK?0|D;wiP>9r>yHy8y}NapIvY#-s*Gu&8&LA`jqYDskGLGG3{!~
z(C8<M1+5~>3Ff>_G;7U1Cf3I^tNp9l-CyyuhrU$ZtOz*a8a?ZOa?meC^Q)W(w>w4|
zql&V4v$Ttn_96;Mi;0E!NXDvZ4b$X%PLud~e$RrSA^H85U(b&E)N8I+1bTxK;?{X=
zl;sU8Owpt7E@J%v{{XKZIt{<Z?6Nk3SLnEz-hP<F%{7^CNa8!t8CZ9fiighPG3Kmc
zktTj#k1<*NlSoF{Iiz!h8MPI*+|(hrH)0U|hWFMBy{CpW$)|MdHWL@?y_4}Jn_H!#
zx)EB-w*phmc6Do+AR5kAOI6N4NfvWgy_V2BlMf3wwo=-GWB$!c5;H2+;i0W{y(aZ2
z>CxN$WnPKtApginbg>bq#d$?HeE7>c->&WSSF|p~3uM6?k82~=RBvRqje2ZW6FW;6
z)|OAJIrVFJ$IK0dSU0MP%oc}Sq%Coz5lnsXb7_93g*4k9{CgCC-+f)2lr#3UE2PXW
z$c~#5xG$hi(($P`vuZLgWBf%$1tFYYYJX6V{)l?!%6Htl>cs3#g2(U4lB7s#{70@3
z^_l?k?;aTbV}r||#Y<*D<u<Oim!y0-?)+&3MYo}yLcS8rojL{52oGZFI8Lteyq78F
z_M}c)@-@0Qu8S1+?P6tvt?x=owo<e12x0QKwhw{e33@>j-25FH@olJ-NQjVXp`B$j
zdST@2ranc3&`G%_4=wdC4es)BoNaEP@FW>pPP53@>AOKzRo)DZv*<S*oJ3#pO6wzV
z>`mfkcBu_NId9hR$PmvID$Cwt#0L)B9+W#6Ds%XoAj@X-;Y|JWY*lb+6A=;fN5?q-
zfdd1g2-T?T64mW*^E8f8D1(=3<nFg#IdXCsHdg7$t{;x|)@(4oJg_6872-!L`glW6
z!I8g|>Fsj1MdR&;ttX>9v$W8&MFQ;#c#8AT(<r9gj3-rcOOYh`f<{o;@-T252h0SG
z5{S}c9;(J0D8D*+2o;v%7?^WSP-R^bIP1$(JZHWvzb5)h)Z&ID84{(jd%RGyx|`e{
zm)nd<p|;*rPiEZk<x*Q0H3e?wpQ3;!-6D_+#v-20)J@q6xqS}Gl=n6h{6Ev@$D{;Q
zxR-d=C>IY5f#`qrF)n(gY9K^lcMZ>=DHkk7_xE}+{DJmDf}pn5)`Bq2#j}h4<1jr1
zw&YG4PB#fi(EI0dZa)a#j@RfClKSlEif}dr+2tjfNAyXjq=Q-KYo0V;PAVI?Iqr0U
zH5862y1&8}s#KlPWu-i_?m+JR5Nk=jbu=x$8x-tC68R)7db$?gwNq2#g6Yb%O-j{D
zJgVeu=<tEpO<uu|76CatCrZ=;h}j@l{u+o^bL8ylPy03LEX^9NJqj;~F(yupc#S7^
z!ZG^m-@QCoaH<IO`BhHqb?q*lomwXn@1sYlzQ>dilol@vZ`WjuLwdU(x;0mcwl>|r
z9YX~XtyC?H>@p|PT&xF`vM59_EXnTat9AUjD5scP%p@6#4dWO^Q5<mz$C9yf`q{?^
zq7XO?U3g=q6)cHihk896zFnSD?T&&>me=b0SBqvq31?}p2*UnT$Tfxm?5DpqZj<zO
zX<LVPWGk);)-nYoKo%H?3!@HW#t04O{1wjMr2E{d4GfAPN)X$C8^+6JlASds1uPyK
zdfx}Zm39UrOZ3G&pY$#bAeKMxm@YQ5Ig-uHfBlk2j;DO0gV~ibU*gdu@4FT$HK;ZY
zgPwY*#^g{ilVH+TY@lDoy>Gh+?pY68o@jrsjLsK6H!SGDlxuuS75D4{kn=sqL4<~}
znrH6gGX*jr{&WLMvLplKfpjYOmS^(ef}8}Gk{r3_+CaxA>oX9VV+>3b{YOq$dAUey
z+D$u030zG`4`0(75)*32>+NznS%K(R^;OG}aaZKuX68dLQ<gO7#V&Ql|L*5VqJ}3@
z+F7~S)j=M#Y^tt~KmgIgQpltvJh{O2Ey2>qqXvX=!rQH`T)%`xG^rbfCrK<Ro)b!6
zPRT6<CUbxL{8gGT=k3JE#mlcRc;-p@^OQ>{?~D?a1zNalLz&uxh06V3+!QOwLSfwn
zY)jnDW(UyIy$*8ch821X7Er*mNqL-S&Sl=WKgMT}eD(pa-;&=}iyPH_5<3z6ZZ~Do
z^g}$2C~{PZZ>E{+II5*6lA-zMqEIf=sLg8b<#m<wNk?9u;{pK!(U6Cg5(8jC3X$w_
zI%l{MdKG{5RU&?`BMQ)O=SrUa<Og#k>+sb2j#UlWfo@iIa4n1Dy#DhSbe)=#^qEt$
zvf|SKZQV-U+kolVBT=N<`J=@8rWttOFrH$c+QSIm!8ETOyj|!iRL5hG#vgE920kZ-
z+UL{3-`d3p<AbTj5dkt^J6PW_Z%YZYssOqYzf=De>RR$I)@{x>qTSayp2fN~^em-l
z<vZ{AGH%+7h}tT>S7+U#<BIOW%*<QH5!}66fp=F?Ew+C;@LA`&-5`3*2O*kzHe^iU
zj#cmGpETZW{<D&yPN~NAteZjq05K27f)u~L3KBo8nGj+C^)GV1ira2(Q}vOJJh0qg
z7)5KAN**0eN~B5dBsns6%!RmiJ<&d#)$Qq(V`cPB;BC@09MX*s2}62DiT-rGci(DR
zQqqh>42Qb;mHcoog96%a42HESKm4fVRWvWKHf~J@DUz~0BLT_&kDg)|`szu7IEz<)
zUMAtUfXUUI9JA15@%9LHL|E{Q)MG9hB=cpRqaaM%O}ajPXEK=-GGb_vhD=O6Fc0Gi
zxeh^$JD+diqIJ3PI%C9tpK0Dc8lrLOwOwJdBDpHN`v-`%36mb7X+SQX)lqLZ)SCsL
zNsx|x$acz!mE^qUxQfZpnlzCuX8xltxv+ibTuQkk5nm*(M+TY?9V;mwa@{=H?f3L-
zKiA>kx%o_FT=Lsfb>%`SN5D3?yzb;GN?<;A7yf{B1Lag#3QwYLCq@stv;H_8!`qxm
z(|&9QXWC7K^~3XqFjQmVzn5d<88_=4dOoJXd+m@yZ2^Ca%ALfUezrT>`rsnB45+89
z#*ep@nz6eXMexsiwR=m3Uas^kQWVRH%RCF!Lv7cFdOZ*zL3)ebBaBC)l$$`~MIDLX
z1bYo<Di%kd#@<@;a@D<{mo4H|ZW;*~`Ei4YxK>P!&)qJUiTRk{#7%$#qirz{RNiO_
z6U`q~F9v6PjpBbQT?qrvxsoP^J3Yo=F3UIJe{azxipC6tV*Qfjq!B+9DZM!eR3DW%
z7c`1qibUPb*g1>_8LEM`cFSKK);jym&A;Y-qH~#DC9unVbpea~N{(+B7g<k4KdQ~y
zg5tYVsBPj>UKCJ6HN115i82WiL8V$is51wOADTQKO8$lGVYpZ!jsg*X1?|2|=ch+u
zB#FT&>Aef7eRpQE34p?FJjTupesRQM@g9~<v1eTN5-DDma%;0^m;Leb2cg=i&)<SD
zUcZ`Q3>Gb?$5PYbW#3qcIM4u=9>^Vx0HM14q64{@8wkJ)j$huLg-F3ra_rUYY3kz+
zot~^fy*YQMCOSSr{8nPjcpzn|l?>mGknYmv3#TP12lPpI)b~$)BV)^jdi|ZSrXhtJ
z9SjgPZx=k)|7l^tKXi(;#DgqIa2i;0v8(ij>g<}#a>>@t<J!wRngN|X3r!NMialtM
z?V1dS-c!uh$DE=R&Bd#%^){`21uxI3pT9%2xMn^nyCun`ncqQIc`iJS!%5zhl<Kng
zB0i902)V3WEhAxyk13DK@l7N-^NT8@+vP2!u~w_X0S8*dq3xedBL)_DMTN+Evg<3K
z^@u(?e!92>3h50YPwl=BA)kmP4>HBUo$QE(1Pk^(XvE+Wp_4W{Q8qg|asdVGD#{!c
z*JtDv=j|0O3(M)(;oIK(La%3fB+u8l*UL65lZw^6YQK>BOJpoH?$0^I<3M$LI51m^
z<8}`cs7rQ*ago2u2bCAduFv5UeEj7@ab3tCCF8Hd*GgC=7!dpnU6J|Q(zwlDl$|un
z*pKiH0u4Yn89Msw5UgEV?3#T4WhEBdK~@<?L9qkl0PD>=cCT28aoymeZ(!4uY}x~b
z-ptcAGo2LUNuDQbWTuXy4Ls2{fkX@N;IB9Xo4T<Sj~vE+oB<Kk)+Cu-dpUzuc>3>7
zies?YsDs&QhEIM~qKj;(0e6o6D%F3=YsBz|5tY!U81oo5#Obj=&K;njSMLZoUIp&N
ze@6u9du&$nOMmFEGCBDNcnIL=+%%k+8)?^c=Tj4tzF7HuhdN!F1{8(z2W5dq1Ye=A
zCnB97iQphwLO3sgN(Kge&6p&$_si$6Nul1^MOQKYa|hB0F_KADCXzpBnlA4H$ALyL
zj@2psi@)AKzmovG)B>-^0u=_v)HGJTWbvPrA8_U*487ze$KEeu>$x9xRI9xUdB6IJ
zq;E+29&1zDkMc_G-2ic=cPU`2Z<ceh7zVFlV>>GCr(MN9B){0S;e7o}agLj4y+Yrm
zYQO-eI1ZH&`qev7;zB6RMIn=5?&<irk^?%whe{!?*K?fpe87%W3EJlSDI3=>U~FW&
z*9yywZXe<67nEV!u#`BjKGVs8mfsSclBb<?YUdI|Inq`houZ_9WtJI5o=6_$j|axf
z91IQWWVGIv8BWLELoy;-F4ozyNE)ut$aNdHuBgDc(0nsS(Zw(`mZJ>SeXm!r5+io>
zh&^*yC)XRsc08lVfZ@d;T4mGK<0*2jL0+nDI<*lfV~!T8JW=^`pbmc^@kJh2wcv%Z
z<%aH8V*0GZ&qq0?SFTdjj;BeyD!Wo#VJE&{5gqfq@5!-f|EBKNXvGu7@pW19?OD8W
zrVu%%?kFd-NJZ6N4y;~QlI!wy2`{as6N4`_HJ@*HVYqB&BeoYtPkomNUxzA}2*nC1
z&#yfl56oN%n~Wer)h~?`Istqr3J;Y6VDHIE(hI~21dY)X)+1CLL+eAg!CDVG3?3?u
zUP@v`=r7m{s6iUQc2?;WP#im;08a9}K2(=KAQv*BdYOwJcj0@TpN=C7J64?uLtBT6
z(l{=k%8_*UsKCSunP_&U#7||>HgXHvvEb;T_}g(Q^(g>dB6Yd#^vFXcc9MEP3J5Ye
zjvhjiAMx~8&BsQ$p6vVTtt_!2V`O6qDZg3%xgJ`WiJIL+5o3u#CoCU4JolvEc{;85
zzjm<g5<(-wX!Ab0q;UmKKg`LH^1Qw{6=pE7Uf&E=D1fwjEEJRdz1U@1KnU4vjufDy
z5ekV?kbrdO^9`Q_K?&VYJmY^D%>Sz%=dfMp)4VdPk>s5S+UP+a0n0jq%<U341QQG5
zF2nE_--cS#W>oeX^I}j(^fN{t0Za11?@9E%WK!|^F?~y20#Rh*Q5^+XnI9P&ufI!{
zUI?POf!$6h-cT~p>u!gVK&I5f#q~;Z4Fy&lT<!JK-YR;9QcM*!=%s1kUy%-dQkb~p
z)}36u7Z>rYI**jRH{6c0_Hr&X>-GL)r%!b@ze8FU=w&{tGwyHud+UhS{#x5qmx4CZ
zP$u?|O{S)EYyd4)x{~f&W+F>_*Hanux<^zu#})Ob9<1{b*Wx!qqb3exM$;zGAlZS+
z%>G+8=ChQJ`6DIFwGM&Zy?Aucg|{oA*A!A*Sh_dRmbC1NHbVUNR`5>!80oSj6ujKU
zl=_#Mjp55ho*~4$SrWeQ;QWqI^6l*NiFr9D5yPkx!d0iyXn5Y7bY|tErh~_s`fIa<
zdmAIz-m9&SRv2u$HH^bNm0%o2<X_ag6C`o*LJMABm~}*(Uk|QpF^$M{8ovDp_$8cn
zC7w0e6-08<zsx9#cVkz*VE$5nGuU~h?Hys{NJRZiTA|3P5_;BO($$4X-^AsXdHaDS
zj~unWdeWnBjuHjsCm$o@!LBg(`w-Xixco|)Zn%w;?&8te1|a?SvD-xj;j^2foo;Ap
z8jGXr=KX2>p5<b}gT}<=KtVXgCUNR$PZw$72OLF5Pu49;YUN02I_Fm+F;OEI_+?EC
z`*H-9v$O`X%ad6YwZL$G4i6}GYKkuL^b*)CrBQcEROP;A&r<u;OtvMP;j>HmYbnZ9
zX<Ite%Z$9Z^%WHs^FpxxEW|(i*yyAP_F7m3;`)wRk!_T3FG97cq@hd7Te4H$D?t^2
zN^Dj#w8Y*!H1ffl?Pzk$7L*U@{!HGkvpf=@m)1gKmhAeQk#{w3FmY~r-tJ!hHF-%%
z@zE%zQt*MW@~!`RdR+%#MQx{Dh?NJ_68+uFme<xp(zV~?FR6*Obr&0W++?C}`Qf6M
zVLsaf>bn076A~8wnMkMRL;rfcy(J%tPA!akC_9)V3_Bym3pv>+7?gxY&~8vI7xE9F
z_A6~UymoaHd`bAsDVyx)II$**hQ3LE@qX>m*?7{xAgq<Tp*qogQM~n!C>{TkTz5Os
zCS1olBg`_=NDnSY8g<^8q%8TY7DDK><HmTa-u?HcLMn$RLTfuUG1`Sdetzk5fD;v>
z5xmwh_-;@NIIFl8jLvPO^<2n*X4R%mm;3#`p{JSUfLpJOU!TsYp13C%r84#;{&WxS
z%+=@-Jf{&X(HpTFA25{Nv~_m^xz%zoR6A9_r!a_A6+SW@+2xCYeEVBtwx?VB6%&)6
ztK-D7eC@02voGM+4E)779*vZ=o8HAYnQ|v7M@mudr!u;vv2V7W3sODLS(!#HC;Y-6
zgB6V}PE@H}UPo@ktHtUdIL^2P#IxJK>8Q76`f%3rBJE1!V6OsGYrZ&l4;N5_Z5v8#
zEt0|stq)AmwGY2NyMm|`<loKMKy`vZUe6vhbUsbcQWy*-WyyX2^0cdVO<-|H7}MJ9
zYO%V@v}*EePXGAkB`HDFF@)dr3>D}FlEh>Y^~ix+cX`w_bQl}#v5pEiV3olBWGPuj
zfU^1O#QMa+Nn6*=>EMw#O(fh@gs<L8SoC^PTSuUZMf3L?+G&l4X}ci9H;MebQoXMY
z`AL>kkO*&B?hCVl&4KJ(U%1M#p&{+N6`FP~@%81r4-v?A)2WYEhG$2@t`xU}s}tOj
z-hm<cMFIqO2^FFV8>AVZUv_!4%-zQL4^D5rNdE`$V|MxBFQlP#;87<=yL=$Tm0)yc
zlcBXLd#qiD5N`gJ+qbmQZmCQVQwZRtO~oj7Y45+xFZ@UYh<?lN$sspTN@3&EU(#^6
z-DKRElL;5`#WE#S<AZER0#m;p-|Bavz01t|<J9nnP}}Qm+?Gey%*B)y&MTocUcNo8
zIM4pFUnv(C6_1Oy3^6qOf3PKY8#_=-{LV&xxl=sq))@bVwzmjt^9|p$gA`hd6fN%V
z?p7%70fJK?xCbXlkwPK37J?Rcw_wHH-6?Lxt;K%B|M<4^9kZEPyo+R$-IM3Nulqc&
zDUSa7k9Wl@;UsuygENh1P8EMD=TFbUKXMSUa+)xof+Xj!tRsy=RGuN0_`Z-Kig$Vx
z$2#+tD|qr)hx0ilq5B_-_a(4wmu>fQc}J?_#bO%{H)zZs!YWS957456c;)Tyd!=xe
zj~8?7=Y%5jlfnD6h_=TFpk6&s3x#*+Q@@<ewqFO{0Sm7GZ%ZDHg$`B$yhJa8+?A<&
zDl)EbVTp1j5psS0ecn!H4rz1Zx`i5B2<r6Q)}<EAG_>|+)5SB-<-Y3u(=JSk=0M%p
z7OEcKa}({VO3Tl7oy9T&QPyf<pHT9>=^E*H)hIPzNGfPrvi}kWE+{@kN;?0(s}{^_
zDp}~;2DDGzo$y-=k)U6fV~jxK1~PxTuOJBJ(_&1>`bksc%-BC&n|F6hbmrBca}~7f
zDdk_&xhLXi-4yLWex{(a`kt{VSuja-vk~-}8es)Rdl0r2nGnYPSZ(gGQdY_TAX4%(
zVOjZgmjBsWFvi44%fMJZCLVoHf6`+(CLh8?OfYCsmszEBZgSAeg=2W~k;B(73}flD
z1Q~kuznjX#8C@G|)q*^j5GBSu_V?#<2RaqX@qIqZw}hi;!;)pLpQ?*Ivw*$54}1v?
zwABE;$=3O8(=RF>L$yCddTve(w_PuyU65(m($3@Emw*ahpP0X2mo0vbYBQUpV67WL
z4NluqfEbVDxXbElk2}i;*h9?F$Sf$`Lsc9Y>bZs?WcZ7jx_`5|f2u}JKwxe3Z@~6p
z-qcr{^TK5_EBrB22Mdi#JGSwXA`ifUO~D1Rz(xlx^5->gP<%OkERuNeN-4u?LX*u9
z#c);L9mQQ8+75F0UyD)YIBg!E@E%zwzQ8l{c))$7-He-;ta}}T>ASxZWUJvSuOZyF
zHAL9{)I%z=`C(^Ge~mEC?d9BNqzCaI0RJyCYL?B#?&|Nrgn;Ay!7zUX%bt@*NlzX(
z3Uq<BEM=&K>dLoUxpf=OU$c#E5qQVaIODCdZLSq!8Tp>ViE^6HB*|b;J5zgj%5I?C
z4Y#uP-*i`<1zA}^AB_`Z-D7tZx7>;tYIo;ibb*a0#(Bq^b(w9p^i)2&Js}8u%W2j#
z7evK<uJJAcx`USTuB5Fd**7K5^6yW9_7$0N2M_T+Di5Iz%Cu_!*_&z%2U0MJfK7ep
zAoF-Ie1GF%t5^QaL}Iw2l$=PSc95{3T;3=T{El{fFT=oe+?f$SPiT}juAL={j(I?&
zMApnzu@GAYqaPldt%`{|*{Cf(k4SPwN7c0kvS7MEk-GEAr_iBb@^^!V9?sJ>mKMb;
za2^GSQhCJ2tN_Wb7$Z$fS0xG6D6r20QNm;!XeAzM#09l#LM;J8VO!-Y8?8u^o6dvx
z3EYDaJ&$qub*fPVvQevvMGA);ah_9cqZWgYOfbZ(x*!PxBDw6{clJ>PpuMs;=8Ka(
zF9VvG;rpu-KV<2`MG@eDttLqCP|J~|TUCYk=0AY#0b!}9ZGutxRfW%Og%W`js^zY`
z9`W+=+qsMRdVB3!ti<x+8;UX)ycGo-Tmudn1j)4oD+j*HT!pnmOE!1xr+;KMRZ$?&
zT!peSL9J=W@!EEQ*6?45Q{f!OI-$OF58_thYl`D>jjWTX96_fAH@&;oC$N(X5#<L8
z9}w0!J-5Qa8RwvrUL&vt<{ZI`?XD@%maSI|Z7d%rNdN#+&S%PV!Bl9)IVFT6f57l?
zhmyQ_7V~phHaK|Fa59<3F%txvbmgaRZSu!uMn5tnx;E-s9l~CZ6c~R!hRaj;-t~ob
z-4f!39HO26iZq=u4v3*-|LwFD_VFRBv-*Qov+bT~SnC3NbX!e9rZ@kI_tF>?BU>lP
zV{(sEak5dyxtrLu5$ihffE>G#q63lcU2Yl6W5f}Zm2W4)1P{|qPSJDr)9KEXobA_e
z97=pz)mX^t88A+*=hTlWzdccJZoIbAoN>A@Z^q-R9gwC<;eBru6)tH=DV7AA*%sn>
z;%02tKDgV-zD@8gHnyvG^w{V~XOo{*P1iWDHszHH=K~qeqx=UL>`N5-k~!Ce_Sr%S
zpM@+?*Fwz8=OXuD3WlI8rHC2);TqJR-O=v>Fj7HJ$C(I6tgRfPGdKq`kpGS|toL>^
zxC|aNSDT~dQH3PHCpo>{Y&*JUn-Cz(LT(LNP=DP>TPtZ_q{;5Tcj)967301T>omQS
z=PmezN6s>-bq`k5+AOJN?sZ(Hg<Pqru_}Qix<5qEP>E3+*SKD1AS`PaNWq^l#?!D%
zIWKC+E0_6`c+ymkIfQsX=V|@eA1xyG`$B`;pO1WnG}vp;%&|H;|1vI13Y^{4rAR+v
zjJf*UR}8ltRn6_vMI-5Z^VTLs^5qOPeNj}<Nc6_`+b&Vb8%7~=2xCR_C9XUY_C^sO
z*$D;8@&N61W{cA^%-5T1%C6|Tl!wWFQbhE7=!3`dnUJdt`c%$_0e59Q1O4?&x`zg#
zSkZcf?C479E0$KVa%%1F1~a$>V~HXo_vHzr1bWz3Yh*<V%Hyp`V+e2K)B9oqB6f~B
zv#>S$fiqqa!gSKT!A4uQJy&^Vh_n)_g<VKP20^w`xn8UHvN^tQ*wn3LikbrPgv7Xu
zK}zDPu+o6!2|WA{+FMNps<eVct{)O*&tnVMN>`r~5|)L_fI|i5(1p@9IVGgEfHz9c
zJQM0_H01Zi)V&Z{<fpe4EEGL21WSdse}C`iB?7M!pY4&}Gjx%I1>R3A-4%-2Wq*Mq
z4hWTqM3G6F$uXMh%7uPbY|uGc&MsJx(N(JEsqpJN?<U15J20aC9)!WjVs@}`wm{ND
zllCJ|c_dEIVQNfX*7eZ}#p<~BudJhOa(Jm&nVy7&=G=)WWKQ7hH%8O$NHTW4<hzhT
z{s`m2tNn)E5Eg=_>4YO){Bx(}sc90X8raD9a!oX&qa!^-ZaoSto6$}|6m)oHS5rO;
zNxw+YkfcSN{RI11n*Ha9wm0<25_WD#HNoJ=T~hy6KYqVOwuClRZ3dzf<WpyRs?+oZ
zDfU`Ra*w<&Sv=9<%;-nZH}f_BX9@e1h8_cNr>8f@t{Jh@(RbsrB&I&fD(#e5%wFdA
z5t4bS*31a3oJwt>*9jByz%UNk<`Fzvw&5DYL9ZYj(BDxu9roS^jN`5(7^EiIv$BH{
zNRR%rs{T`B$XvOx6x)>ZHX=>37q!P4b9~C|rYfYHe_Xogh>_&?hxsyZd<AV!_c!C6
zy$y8OohdyhL<<Y!9b{v-gCteWFSuz>SyP)6pZ=)1JuJkzzh&~;BYz=ORop2`*%i-8
zO`o^7i_fpi3|<uY@cW)WoZC&LIJn_#edfmqQwnM&l2=X|ki^{LT7LU?fURwc#>O~L
z)Z3RY6S+1?&TbkDi837h?oKYe4XZgWju7DHrjfDiW8sp{D>PJ_Ddr~6G7^?-1MAe`
zbr3_)v|vO_yNAfxjTWvIKj^2V_=QPTTJ>TxYG;3%aPZj_X}anb77rxkOZo05=8#eF
z*eo)LF1{#d1$HTsYqe35{tu7}hV6kJRfZ-s2n#VpM<|8Z+Dg!B?^4$|h4gBgnv>rv
zdT}4~!3&?W+%6jOh*mm=D)n@}W?dMO&yNdAHEgb~l02m;^=AG?G6b4VAF5bFzedv4
z)-O#3J=boOt5nz5+I^^T_B~{q-T5n9a16CrTiqDxf3etVMyqDKr2nx3s`kwP7p@a=
zidpu?{vy(ze}q@PSx+v5YR9mY@^FBgElnjgR<=WNHKyyXDs@B`zQ!-z{Hqb72aIY(
ziYw~sOFdv}^vEW-c==JLdbbGwu@p!40g_-qqhy*Trt4QJri-Ba(===Lv>G3<WoUN1
z5qOs;8Fx{YE*Mr^8QgBvW+l}cpOdaP`)_)C^MmZxBT9)mgKZ54$}s9;texS<KK%;W
zzGmD$bfip=2Wtd}gZ@HcTk5Dz`WTE`Yf>r(ieEC@vM~61-%`Q(c*wgFM3<@<;WPY*
zs3z!8siXxv(d{K?6_SNhobZZ8MHs8R-}-)u0s7^e;o0lrc_4A}ZZuOt7CWVS(&g^k
z>=~+rcMBNaQM9SxLdG$O-679bJp00A*q_Ug3_+w@tPV{|-u5b5B3gYVb?vCcFW#8z
zUJWxxgx>=bw~vP69Bs}*4O<z)YXeL84+}jV&8lTz2;j}(MGdp#%WW_jG_Tm(FFl<c
z?H7NBbPcvhEDBqw!km<qdGCX>&JY)Or~C$7R&7ZWI-4~&LlkUdTa0E=p{c+1a*sEO
zq#8Y%n_uazx_BiDw)Cm}`V=WY=T3_o$@y%il##=dW64n&xn@4&T<gJ+;!G-N&s+)}
zg0)R1M?K|`h{tf9kA8+A`hn8^;V<pR*?jR#C04gZpf43{f;(fWjZ!l@!advGXHVW)
zm<}FTp1*!Xnw+`_Ny~xs;69ZRTTt4tzv>!x$W*iiD_&!}UcV*I8{OqlTK|HusuS_;
zcB!rVNIkhWqPor#0}V{6u<}*&6s8!<m{2zCx79Mx<=E`LWG%T*C0YtlW<Vb7e;!%s
z_wsg#{7PgLnCaY#@l=rI;JwpL72e;o&dj8o%uAD3O6S;!qCBka%gt)iA}{3|!=*%&
zaam3f?YxL-K)H}!>lFu#%`)deo5_;jU9_Ob;ebw9J8qz~)J1F1Fd-pwFY;c%dSXDy
zN{>27q{?Y&e4G-AoTRH)*M)TGj#NC+=(i%8!rp&?lS(THDr@Al--2m9vgwM_LCnc)
zlHqWk2F0~y3z$8f{h$K}wcGn2JAM_!XiA?Q{_U~P&V{50<zd0JVaNv8NO=#x3R}*~
ztk#6{sp2|Rr!b|!+34I`fd9i_CTha2WKnUB{9NL4l_^CnQl=+=KUhPpZJK|Utd9M<
zc{FK=aBlr%+`AxwAT_>9G<@7Q!hLAhqS8=lU$F-4d|b>TU~br(^&cQ`kBkm-uu$CG
z>JzzI(_BhmVxZ#K31%98-NIqWYFPa7j)3*Oko!#Cw=djLclT}|F%?no%R|IW6ns{M
zVhc#u>n_;i@P;LN&|KQlAbJN=jvnQF--k*5Ww&-@)Ks|69=RDNPS=ax(KYILJ4d_6
z87?ImC>kUT4rR?*m)K*WF2gZzCY7TI60+5p4CD6w<Av{w-+VpSCB;M5#!8BZf-;W|
zj6yOm;Uj?GZVn3S!dSTAFtV_ZC{n_cbTHFKi7{G{wk-r9(R8dR9JyD>U8UWogR?uw
zIr%3<8k1yF_5@~pJxlNh1*WP=gAEB*x;DEj#*J+$elv8&64a$n*}<~q)-q0fu5xvq
z$b#MfOd(?*-?TqTCm9O66O&)JkA`MD4Dn|el~!+ggf*4Y=h)x25m?s87?nlq7O8N8
zj}+w<pn$?MdUQjvgq4uMh6X_9%nn=(7^_ATp~rRt`#!q+pqpu(UQa)Ts`Y`M(3$Q!
zZci6|l(}5XlIld7XwLGsUlfwoRki^}D^>kHxR8cDOKp%v&#un<_S9(Prw(>c{mrU5
zfyjL&<vbm2nl&S3UW=1~;D(gp*)ECpxv^yX@ee=u!~iU?W`WyEt2IitoZAl`=Tnow
zTza43)7X@8MbU=^209{rv<-CSQhIcf!G$JEnMU1Ny31n7(umJRyDpLNIcx>aUMi4%
z_j4)L_z{#amyvv5tkx@1z*}}};Rk{l%K!2NI3xO%sWsi3_iy`6!rYn0C?GWd0fI=~
zBFPGz6=s@<aNADQuh9Ia&5Z~2_ocizHSS|sHa_p(Xc@kI(MX1<>_M+=YpN^*QY`{6
zsKSKxM>HNbdkHJ(20Q2!VC-V)U=5Oeg(nud5R|EdjfVF2>3WKPxq5sH10NJd;oi$S
znBNFJ7^Mb&nDf6G30ar9K$A@FG}U+yf?Wlainl*%zfXDkWp5IMQS$+MlkdEd9J1#Y
z^nig3*(}s(z_x3-IgyUIv%Jl>RxnKdNnyK^Ux-4BA)W8yzhAVPqb$=>fGQ?$w{)s8
zAPPJknMLMqzs(2eWVk|SYX|ABa*@})6@xrM6m0Vi^s5#Hx7A!tBg$1s6Oe@t4Y|oB
zf|r!Mr6ffgi8rj-P#}sr<;{R_tUdKx{%togxSSMEE=u!45^*8@-7e0no{_{{@_>Rx
zK{9zxipfxG4kC?V)Wj+%asu~KmpCde%|+YJ3Wdu}C`bg@xhF}70X%=kFd0(RNLA9L
zRMCsMiq39pk)p%~unG_SQ%zxgI+e!ON@(#Y#!WaqQO6)Ko1sMiRmlB;QcW@q{p(ED
z$&vIo@fn^IWi-3D+d;JCjY`oNF^X6krfL8#L!i6bPP4sntmqVqMxjDXrH1n@YW>?q
zcaPgr7FsO%OAa$%iXh?N;7VWgh{hy8*E8c}@*uHAh3&}?0)0iylf$#wY!k)FBTvuM
zT?M=!Eq-5a{G>x!D4-*sCDx=?4WHaGE!~pG0ncJW_uE?;-qiVaRV!R1m%gcxw;-s)
z*pPacIqX@`%P4#hH`0P-%C6RiUbT7sZ?Vw6OIcD~fllDyVOP#-A`m<Wa_;Zzd2bX*
zF}<mU;0Q8DNB5RJW8+;}ew90h5oA3<Op_d3h(ZhYA}~MZmYJUAB^`#%oo~%l%q;LU
zNAIjOwhQr@7#5_9n5R%cUd3sCKKIRu>XY4%p<aREZ8>jMI#J(txfnnG2guxSjA~ac
zYT~kwkQEXcT2ZPNy`)#dKU)t81a?4<OjF7SbUU4YD!rt1{Y_ji0yppt$?G5uIyYvl
z%~Ki0HZ*jU;uvBATv_~Pz}XGfQJ7x71rv766wFBOu{Tuqsx$jR*bV80^uR!Zx9End
zmnzW@Gn8rof_#3jydY#dEKU|tP2?FZ7)y|M;VXOGPXNd-WFVky09c27WmOi{q^6&l
zhA|`IIL`$Er(<urWEbL2l>J^|!OR&yt!Nym7zTiu9L78jAV@3B@8Efh4mD&xwrxRU
z9whj?=#B&et$CNaDK?U&0B%k|9KGlR!lmusPzY`{^P@q)lySQE*spLOR>=P$2t#XG
zYgAjr=_-%z!uZCO&gh3x@aJ>NKw*=s{tKaKU-^{wVZr*q|2yyI|IXt{_-1T>WxYT@
z+ob(ey-|XsAK<&twtZ5R=yQ7Chx_&0{lODk*t~#W`QK>XaW*DT8+y`HN$R6bONj5A
z`aenMt=Q-i{{alIS*oObTz#vQVM@nuq8yfUe?Xi@)Lp-RKQe86jnNG=v>M<G(#q0E
z3KOq$b5l0<zhT#lcDs5VK12&*U*GAs4wPLDP{95J5ZNCdqpON)DT)Gb1*TAeqO5{f
zE!{(m?ZHpdD^d|w?XxDRzO2(qnYbp_h#j=qMmuUjM~nBPiK2_i4y153KmL+n+*Ma9
z!-G=og3rrqrcWBy*%P*>f@wzgxstNT+|t$3GybwR<#zEKMVg9;m32A)wZ*c^?x6|$
z`C=I7&2PEJ(LC}!QJ7XK=TG;Io4Akq$MDLD?02#HX@AzAWLk;D2;+<~w>x#zEPM{|
zD<<kg+r~iRq<3G#IynQN1KSICCu8lAS7n1)+4BuHkc@27ONxQo68jG-*wgR#kalcu
ziXApMUwWL9j%InJJd;Bz_0BnOCb4rGhB3ODxxS}-{M&I7e|c7$zj=7X&{>L`5_nwt
z%6}UdB=A}X7GE+ep++)<hS8C8_xm=k7OvHeMb^99pw1he^cbCsvHXT&j5_2b*MNgJ
z>Qk)eqeVPhPJYnJQxF6;8Y{bJCTNX{4METDk>Pdt^NJOmT8;TWA=jVNI@$~5H=$A&
zrJgx>Dqop$5c9C-skIl+a4ZG3@&ReWb{_m@j-lO1(;dxJ8xn7}!*O^i`!B<Uq$yqR
z-D}-Rx2dv!B&Muq8Gi0X$GD~jox^kz-_chI<?y{_wNF`n2q78jhop!<f>gxS;CjWq
zT9D_CkMQJ{Ayls)zg*dA7ZE$KBSqt}Rv{s}_<i7thZqdx|L!V=py+oXm&-00o-x63
z>-?MHTQI!)<!G35t8YqZ<Uc@|?_lJUqQGjkB%3ewB=Gc^EzO~AdHV{aWTp7xh}k6d
znx||CJH>Qp1oWgBRw++|-fB1PjZdr(GA(4Z*>-Q2zW&C3<+6fcp;r^+8=mkEWV>Zu
zaQsYuJSoT74&a6)Z6G0C4vqa@c3AbxrO7OAddd=X5YjG76zN%a{MNa`(j`q8DQTl2
zhQo<Q(8iXMob)O2b91DN`>$OE;&qTq1AdW-K-LU*IskBs3SG=I-uR2X{j%}$4&3y^
zdji1r?;*fpDpd;e80w}$U5|+1lqDDNQo%tdm>*l4%<%taDjJ)fE03T2CCy8MZG-Cx
zX)DWXe5LzMdrVfHT&B&DsY&HuDZMGqF?VUTTBmZ!wQAGGZzcS&=qh*RyL;b_Y@-{A
z;~rU5yg>+NzbRkJEn%(S#d+U_5yR``)7PmPVyn0tAk|YN(*nltrByC=pfUYaWtfmD
zz&t(IXf;Qp<7b84jz(2!-q9`>g?b>_XugCQ+5%aJXeG5^e-%COq+efVlldd0-N3-8
zUjP&y@$bDP)X6K|q5EY#7wLwJQFrjzKF1}D&X^-!*fM17iY+=18kW*fuBR{SO_FPY
z8DQW~I?mQB?|q=>VxrzT(ff%FLwi;ENPomAz=1jsnDXTmnzI<AXDeX}OOz{1=*v0m
z)lqaqvghHhde!4MMM_=!Kb3w0687T{uyU01OHhHrC=z8WKd2yg@X5K)b-ZnHZHH_{
zud*!8gn&D;wX=Wp{}jvN;~^YfhzLOSBH?!uCMiaD6Tu&z6npsw>;9*)Z-2uM5eg#N
z`TPYTJaco4Q}4x^qv(UD;KlnWQy3Pw-$lx~oAz}Bc{XxUJk^|HHMD06f5LI|SRdws
zYmZ=giH=U0!AG#<PSI?(oYXONaTfNVkWVCs4$2c#3RD|ROV<Wk!{L=t2BAfIm*odF
zX+IWfRh+IVqLD-l_xpHVR`kg!TPjWDsw@#S1|hiJ5<I%#;GM7O&7jN`V@29#9hzQL
z=bgv-VjItNJQiaAzBi2ZcYH0MN$4+F=<y8{vu%d@&d}=Ze@}GosHB@+lMsg3KqymE
zc+hz20kP?oWKwu&HCILccWY?!Y_txCRr)2=<U1z@2%Zlp)FM08g;Ks28ZP!B@-z{X
z$}yIcTL!`=YnJ=l!kg&F_Mhn0-75dVCR>4H?@$Pa@IdB!F2Xklgn5NTbY3KQ0#+%6
za}P5C*(CZ6%+km9Z_Qi%EiJJTmBa*}^J@pC9rAeU=q<fU2uij7!a{s7{W(QWVN=*`
z&^h(v<u_kRt8~x|2g;Pp)!5%j2@{{g6Sv6g!9fnZzX|D^)l+ywz;e$UX8&TJyvGeR
z@JyGu5@GbwcjmK~6;aYX)^uVD#=51a(WR|SsIh&Z_iHI>LyWCL+7hExJ%h!Cp9Ec;
zhN8}^uL|M?l`l2R(=7iPp|7;k>W<i(kWGcgrdW&lTGA0yzj(42S~@+-YZMAtv)n@;
zL9w48b^Y{Mjrq<{+;I)U=(A26fM@r1W>Oos_36@FoyjmWvk`K=+aVh)(Mj0x6#>;z
zR7mb6OpE6sMxAd-w3RtMIyX>ev8TCKo(eKH!;hX7|E)kC+pgQ#nsJsDoz;s`N#C@a
zX)Y0F$%D6*Y*r=rHaAhapX}3P!7C&1mbSn$x;!&!+}2=2BAjx?j@IRl3}vA%#Tzm;
zOQ|P!wM+~#noWxB8#bPAS*R{HR&!@>KX9m}ew@qiy*h^asoh1~iQZ~Y&eU#W??^~C
z+#3t(u?|*|kyQRP+PJ^{$k9YsbCF$Hx}o9XM2to=-+A<)LmD1gVtfD9rZcE~hq{`M
z@UW9=p@I0u9X}&V?4ms(DfQ*P!yOs{zuJphYcE3|F{%=?*=Ri;z>u^6I%O7h<+@6r
zXc(+hc`5a)dE@uexe(t8s5Te6>*vcz$oe8Jr&b2EGXHq?k}@3B&sr^1ktoGQF8%T6
z4HGU|xgTNAKgdLd1}bIa%prVyKf`fKzILNafxGUibAIFytT;PgFxNhxK0sm>9sCz!
zgzHnUF?~jpqt;}gE$k`sThD}9coj%?=&_;@)!;<yecdn^uD1GvJmu-c{$Tqh;%?H#
z9n6CYexo3uZTO=%kpJQze8mS}D^|Q(%s|cO@ww<-_WS5m?WqUQeAx)4r3`NB*y3E(
z&B?lqQp2ALjcZ3HG5h4wSbJhxlgIB^usYDEmMiU<cKf>h9G+GX-ilfs;jskkO>I5X
zNP(_Cs_kmfegj>LOpYJr?X>bKQtZMEN@zB8!D`IZ2>aiO3IAbLTT0L4g4}rM8V?Wm
zn$)-1lz2L7S9@DMU$o+v;f`(&?5PfYIBk>F>s4GOoj`E}^DFaRSw(J68*E15v$3Vk
zk=7^%&)T;T=u{dBXNv?&qq9!eQM9fFw%Z%s0f3*T6sab0XzhD&6*}SE(N~<tEIn1D
zznHXwyKJN_J-}tW-PC>cv;^mW^IyC*dx{V+Lhvq2oRqI$Ai;O_9F3Ml5`~GF=sW&G
zH?~x$au<lLC4l)guoj)$f($}Eq}j80S)JeH#n#%05TstwPEcG2PZHYcm~m<P^n(yh
zwx65|aAxvIYZwse``?1x5Ql0uQNC+ibWBS+cVpt?uaXhSD&f4LT~nv&txMYD)b=dy
zq}}v}-59A31nC&*$WUwT%<)|$)w+Q76&KyPRq{P@iFoP^BS4p_g>X_2q&s-au3-os
zuIKdAF-n)8S*C2nACifeuGpcFE<;~EOB1CCx)ZMCs+C0!CTqj|N~qPGpcPk${{_#r
zGT5lC;{)ELLyHY6<$Q{}nL#LBykDqZep|NmAw9<*KOHqu=T*i%y1(BAJpSe9MsPGN
zdQPUL9eyfITs9LQA<gunmQ*{&KkS8<%{cpKYgF2wp``u3-Oi55yi8EVtXwFF(bCD<
z3}eHrhJ^o~{ZkcIt;;UK`tH4N=1rk-r!YAv3klAv`s1xWAeRd|A^&`_yHlv20F!I9
zf4gWmj?9nBTFhzRGgeA9q(A`ooIFPsb)NLs`y}|oNfaISfjoBoIAy8IT;VGQ%kLkh
z6$SXI3E{*Zl=Hx|E;%lm_}IK6m{~%YF)~XH9irJNa;c3_^45Ct8SNvbxz)41exAc<
zzz7d*_AN-)1Ed`dwXV-$Lw<Kgs@E%dUa8BJps0j3E<wu|ohx!*QE3rbnE}QVW{kSw
z%ZnY=%(|=r0kLeK^2nvWD$irliJ~g%XS*8_CH9q=WN^j4{^RIwDIBOh%5aTt7P6El
z+oEgp`S(`a*OT;q_(FYGQEtVnc6D2<&KUDzw(hsU`$y?@Q*t;HufwNMr~5ZVC-G>?
zEu*6}aihHe85Y_}`cvCcK58N%@jXu0yx%wY{#x?4ltHXTSW)RaD!x<~Lqz^&VP#Lj
zw}`H8`b9ZWdv?sYhP9<}1bI11w9~kL+hXF&nu5Dy`76@C(#oN{(X&k@DctRK0JyDS
zgdt_c2O9;aMe9+M`UAzCLVWHDvgVW_Gx>VJE+CkMb!eu^Xzx_35y4bx<RR7yQ4`iW
zIh6t9F((l-79?m%9<6H;^(&So(hQC&9nuiEI3ZSV%j3uIfJ5H_54wEsAK(r)cI0zs
zw0(Dfh{x8@4nj4}!2Fv$6Zl>V=0F9~gm9*da%o1san@3TYRWZ2GlfD7gK$2j8iLOL
z`y%|dq<+=A8QfnYJK{Q@%`CBPBc^72?#neJ@VHOJd|UP~E_D@eP@kENXIqQ|hLq}Q
zp9;KgOXzkg701Iw2tQszlz0Rc{{wK16~GhO5<jBHRes*Z-N+wgs${G}jrFb-IsZ4e
z;Pwo6dTgC{d=(Vkh~ulTApPRD4iZ-oArICGQGeP&h3e{a?tKHaSG(FD{-X9z2tLtF
z2}-aWDI1OsUC7{8A}Af)(gi26KdvUau`(s<#8-bh(h2EN&QLm619_5r7bhCeluVM0
z8zDuLOz2;)!e#6OUMEU-k}2<HH<<{9ko&VgryI{t8Dw%*yMr1=jUedfifc=UP;KkF
zR1u+k=jfYB!$`JZ^(`-Eu~3^v?ZMjeJ=E%YDejV&p$+GW>|5ry7RkNg(Ob`~-g9Ro
zye%Mf1UU@hkoR16#PPCB?)Z$&rl3DnabrY1YZ7VFy(Im+xzN6JxIAn^_m|IV2GeEL
zk6vB{)EI(qZ=`q+8r?q)p!o<?7YrjeeM$6#>D8nks(Ew7F0P%wr9j#)8?X4}$pUPL
zQl=z$mdou$EU0s%E9cgK{-az&|3I3q3uEkq4`gz#1*DlZ1K+s+X!UR6ePgqp%@=z+
z*X>`6Fi@YrJvBb7EzLLiZSnb}A81#JCW~51EHX$@Cg_n8IUt#0az>kMrR~zlE=!%D
z-pkRK2hyRyA+$d3lEe0SVx!3Tr93@bHD|>{A9|wPrLEKbuQZX{^l9Pm6y-j?KpR$p
zYks4<9(RLwgL9yjF#ptWUOGtCX-MGf*c)CP;);kgx~FxC<7>;}k=Fwn(uT`BhWWkF
zR@P0`PbMMzHk?<TTTMUQ=KFV4%mwYRDbmQreI~%%?|8Rwub6trCui@foo<OT5PMYo
zt1?Hc{}4UTM`N2~BBQV>i(S%A?)}FxDb|x46S`iv=X$MQg8Nr?LMk2gwY8Zz6YcbB
zNmutbrQ6vL`?f!o)_w^0HhsLTTH4N7llu=qZg&UnYmRi({V8UG@s;&<63fuXMdzZ4
zh*+h;T%Q0?JR*E#DqCuMzd+>RDL$oK)vXBHQ<$mv`_=Gev}J5(tO-2kS3AK<sItx*
zhNyRv(n8c*V_Nv5-IngmbLPG+bv@b3>6#OL<u@8KmZyvi>9M62xOd?Lq_<_<8w`+_
zepmS{eT{XL8NKbMLZ@P4)prQ(5Vm2@EEy*iP)lcevv^k5iALMp%fjCv#Sc%LLSG7P
zqM~atMenK(M}U97@v9#TM(?c6p6<Wrwl?0G^PANl@O^7{Sy%VGA;FwfLxC|=m987@
zJ%Rz}X)(J#H6U74qST7R^x1BtNf!$4MsIY}acZk!iuF@`FDLfFh~iP#p<D&RChpXz
zA-<@aH@qdqG`dhpf9<D)i2cgibt!Xr=N%~+$)DIW#zzqJJJ55M*u>o!vqjfbx=1Yo
z+UOz3hSg4IcTKiXIleQ*#h+RmCm$}v60?WKhN2!~^ObQkQKY*NNd8FBAj*%hu^<$*
ziC%2*A!PW1BX1@1T^R777bY238qHS|6+3?th<0h3K?zG0(nBMuOlBkTd)#kjmQAG@
zv-8>MuJQSyZXKh`MYl&q_}eLOqqpQaM8_jz>}r@UcsxL~wKKby_6{W>r;`mIRCm!-
z>`UBsMY*k!B8WhJ(QT%;Jf~?&PuThuz9LtYfp3D|k{mO(3JVELS=P6!Ihu;7Oz)G;
zt9R}f)2R8b(WGz2>uWEJ`B<xmj+~hz4I_dv7wEhHf99)iQ^+?(xB2{@<eJp{$-pTj
zc|H}Tb7|c1m#P+{pf|5B!~0k{Z@yP5PM~-6KLC~XWnAV$l!c=4DR2<J@5$tVNY@E&
z{#EE=(%Rq{wBt=u;p?Plw>&t5IOd5rTB60>r|5bBMce+AMmf8wXtcwvA-g^`3=RtQ
zJ)o_l7!=)t9v~y6h)y=m>h<&D(frGzy~|s}Yj=sl*GcUzqdiEfB^N8s;9n$<JrZ5E
zbSFnoWmAHBuj#Eg=(75o_gmFalmlco$C7>y1E6{mgzZ1@>8agzu`~6`Y)O^vR(!+)
zozf&jqSlheZY|-1z*P2A)x7|S$>cZjPj(VN628`|er3Vg+(2-BOeQTO6i;<r6epD)
zd=oBlyd(H+;$*-Zj{7_g|7=4S9*r&8*n`BHwv7G7RVx-cS5laaGHx)t-T(Y+NckgK
z%c-I4MgsfI=|}0<d)cwk)YTBB?UrTsj8B&s3h}tH65$RDuU2v;RptRH(Q-(h{^rP}
z`&&1^*!kI^Y7g3h%ni>F+~H3RI~@?J4=!-FFZE}r2r8B%lT1T@sK4XXIJG8E!(!s!
zkxS>sugqu9o5mjFEOpzjkgZWBn9N;oTZ4D(Ynu+3{jTgQMu+8UMQx^M1qO@b{nO!U
z?9CN`AG{G9(a4YI3oQ32>FTHQaeITp&jrRaJXbf6kYE$85{m{EM*WK?UM;(vg#P50
zXHn*+qijI>upRALI5=mWB=P{Aq7f;4H55w^9aI`N&AM<de-^wVl<M;#sCuIol%2dQ
z@BJ1wHU<e|D`~h$RnAC{-6&x25Nx$-EVB^4+x6_1O`G7H?QL%6cpQ2v7~GU7FQ~uh
z$Yg7EREA8&vbo9wC~8mC>5*D)Zc7f#1UFD4IQv)7&4epQEigsI&9-Z`<})z-7CLI5
z#~qZ`QVk|VCJ7J(p@m%bOYuzn*3p;pz7Mk>fT5vEaLoV~%y{xRLoA_xz#A8PK-D0=
zMJ1DcsnEl8?7Xv7tLU^V+R^Z-MpM*;Q$EVipHoeOu(rb0z-!+@^<<=K0#l&VxD-J<
zRBJKLFd;?YU4KV%9o5;ra5WF?&zJR4R}H2;twTPOk9}&!`gYinjLXDkdN^AM|5YnD
z_kJr0n1IU<?j}(%ah0hht^A#ERoT&}h(#XJr#})WL_p@`37@ia67<+xkMKd|u)z}k
zaP35%+E9!7k*$CGjafpa#3wqgLKkfMczvHIo40`f0(aqVLDILSJ^wQ&h+d_6mt(KN
zS@G>)Z6<k`pbvz54L1q$d}bY(5CgvbcTkAT=CretWIn(;F$UFEo<VL=mZfr!D>Pv1
z=O1vF{@_RuCTjDFZl|C$3fb?>y)M(ohjs7HoDS{)agzp^S10+qzB_|{IO7<`SC0fB
z<#JU+rR9QS(T^0h8H?D0W77)gC~uI6CJ?zLrONwBwv)=}ZX6w0j2j}QO|xDv1R=Xt
zkXg!`magqAnBcQ5Qb%VpV#2OpeIq&7Y^RW$p`NUYj>2~w>Kv`HgdfdQE!ZUHOxHzy
zc50ec$jLqnZ>)(5J<&klND`)C=_M}WmI~vigu=AfbOOi<QRoMtaP@yD@_`NMx$ksh
zT254E8|6EAo=SV+X2L<}1mBBn*Z*q2*F@f-tA@Igh#wI2OLjI=OZe^wA-e`Pnyl_K
zzgwT%E=U;q0=3`*2~hI{zi%!*wAXh7{GOFb$~gcscb$y$qoz;NhDh%xp)bT$@)%nO
zIyd~myf2DJvCe!=QeM}m0%l>Z{g_g$fa*AS_S<n9Vy2BB!aL240FrZcYA{LB0YO;p
zv>G)gnoHVmJ&x@TT@DUP;lk(Nhv;AJSLR$22R6qn0Cbs)F@NKXh1~1PV{#8%L<kup
zM&?{Lws&h!ZpU>)_#o8MI1A;eqm;K(f4!DepM}5zAV$@3_>AK7U`xN2t5)qw8-?kx
zmOO#`(F($0=}ziMQL!qq-9O(+vT@l*l`Q?^M0`A1^x{YO$rJIT$=sC+Y$3Y@2B&M7
zJ58iNl-adzQFHs4Fhs?z`I<c)t|Zn*)=oH(c(m+$c%xjtu(H2P3nZGs8$s`EA-3N0
z_9E2l6V2^tx1}}TD|_AWKIwOI__(3N;$jOp4W7anp1HAg=KM9o3#RJL^gdT!B=r*6
zk7IkR(T_Kfsf1F6I#&ITM4d|3Mak(ED0FZtvP<};m=8oJDfenE;Np&?6kJ(L5r@r)
z(psJ|mZhr)HAx@LR+?$>6K%m|T1?dg*z)Hz&Z16FCfHz$)bU+Ce9?o=kU~hm@k0`S
zj<T|$yfk!L!Co1a)6O0443T&5N1+&i&S=4v0iKKynCf<Pw3gY&wQ0Eejg}cXP9w@n
z#%<v^fO&T+@RorAz(IghhzgNLx5q+G64#`0@2BC{S_#6Q^Ul>;i2?v;FsB!SkY5uo
zMD7%_)*SG@V1OA3QJ5PCWeKu~fBks+Kfw0pYdK!%YaL%PDr5W%1^Pqxsor<xYD@+r
z#)<`AZ=r9FuOX9Cu9h4D;Q#c@<jw>Ewp0K2VA}s5u=aoJ`*8go_(zzfUQ9TNz9p_H
z#r7(NpoHm{T1En!gs#Uy*xl$qQ?hs2!r2NKUS*g`raBu~uY#k!lsqF(XPwc0Fo@F#
z>EN9B&5!D>*MKX>z@ZXbjn@|`alV$ADKTeP@1x&uE?ff>cKPWdc?&$n7qh_5ltal6
z7am@n<RKiu*^v&Q`i-OT?oNVovK0}!<DZ0|-qg&yNu~kYR1~8Wlgs>fG2TsGk8KM~
zG5hlkQTg^O4KrQ6d#KlOmla<COM{g@wZJ3sA&yyy-mWwM+UgHhWQ`ApflLil4jo}<
zU~sC>i&N)qpQ$24-2M>yN@qzTK_Xh%_n}_mYO2fP-crZ*arquuez{0Xm*150y!rDO
zgNX=DzDy(#!*t{4dZWgAxC+RmM{&`$u(gS~iUK3&?7rIXuNh6-1w(}!YLfFV^>wV;
zhnRlw0pZ$7Ch5XdBhw65>KRL6$mhe$xNG?4->`fmyFkV)Com72(E1;x16c3HMvhbI
z-`I^_&9q+BO=efW2VJ+eL%M>6PP$`wRsqquK>IKWwlPjeY@ZIEJt<d2ek7f&Rp6kl
zvAJQ@-})`E50t7|-{f88>UsHvoGX_zIG)e>&FhdbnSWt7J0{oG&^gIpyYFr_&+B=<
zYhUW;P1Ro?vhLOpqWUYrY()iB(u-k%XP}BzQ{ur`q;K!Fmf;D$;Yhz_yz^PKeMg=N
zs#l=!1!qPsqO}&WQt%(3>=+Beh1Di|1t9h;7g`+m$=KM|o4ja)kNDLmBEJYEH+su3
z*8BN5_pZyI0#2GLkAE%m=K4{rPTqrRSI)79DgPCb%-3|qZyMU^zg?GRs$y-Q4n7Cb
zXZTrWKF+2%6$I7u(PwvjDwEcZ3P*u8;}v*owvSA{{hG;TtbJO!l@3b}`DL!=s+r7*
zz41*qSID!3->Y7wQuKm{oH(Mp!bx%lOBM*5*gkRsswZ;q@Xr}=8i3zYJTQ^J+EZN6
zk3W*;NxVdQN@PaGCAcbdI_NVn)#%^4yzv)op4xeoZjC)<K#H&({8Gs`xPd%%&OgjK
z!{5*vqv9Ox=2Lm1CIp&pxQS8<D~jO4Redzjm|INwyQz68+?pr>WO16hK#m1Gz&7FQ
z9{8%)Mr}$?2R=*TY*)M9{RT7bQl-b!4R^RUqr&V)=#uk%xpWecW9Zz9SI5`fiE(q`
z7^BpfAFOKbM*;G>b6n!mVHMTI@fH5&UE%=_Tw^@V7{XQS0xmc{sd%1Yenv0Z7B(bR
zf@g1?&P;_1uIaSHT(q==s&-TzKh_(q@lSOQIFs<i&s#Vd+8HzvMY-+VJL)PvfPAB`
z<d|b3S7DG+hB=UgOZQj8{aMF1S?f^~G@2+s4=CzQ<QDr^jiS819X4yUo3UuR8-MHx
zP?4RzW%&V0F;6v+lutTKSm_K_31HG~82`1rr?KU8;p$L0Y{y97DEU=V;u0<FwcUq<
zvAI5_nW23+<w=6o0f*SO-o96Jf!_{{0Ak;WQ*~`u`#kC{@cSJ#lwy9w6<#NgAtFY}
z*#r4=YzLqi)tLzO6S=;_KT{tK`bs%>R>fD`F&9Yrw^)sPT%sL#+SBGAofG5B715x0
zQ$F70onT_b{f`1ixT?HglIkK1PBhEJ!tyVK?hLKO$EMrxO9ZvlrGVg~czi~yo`kLY
zW9i!ik1yDhWhMo6^hIOjQmH~zL++-p-G<^9Ewy^D4g+sts;}aK0c>NpPGo(7NOPYW
zIyPO}+>~Pmx7naL(S~77nNFTDA`EM7{#}A+1V^*cgxNc_MuWewKFTP}d6b9wsag(f
z_TC7L9c2@={AzGm_U?9xOVlMfe7y+8^==aSxR}mnsLU-eB)L1qy7wZx8+I~W^d6Er
z{^%q@d>BCDvLA#B&Azrbz4es#aXQUkTJx2+N(QqkKw|}6G$tzT4J#Y>ul>wwHdwax
zTQCDtGCAE4yN`Mqris5=wZIb->Z}bv=rfUYNxiPUuXEJrtq5&MOvzd*B(lD-Dyr-k
zBoB&if6^jO^V1Bvr=Mz`k|}IO>MEuYtgjdamX18mC3Ic!00OO>)m0!xhI0)Cb2~7f
z!nc2SA9X)pgpK@6aHdID5I&T%T_P_xsu2tNr>52F5MgD7*8+G&hgS3*dk{g(YmDa`
zv@PtN`7Ko~N7*FpwMH?5&%aw<m@{qQ{SeF{Lo2cGkd5NzFfH$VXR48;^4xETx~m^_
z4u13RKAd(NgA$a|D8>$!=2e2j=$Jwcio}vHq`S)Fd#<ud=kCk8-TqD*&NSMAMWp#=
z2{Le<_lLI{uhGa~-%7uOmmo&kc;M$t>g;)C-3E+)E0FmdicZkMnWdNTFknvd)w#iW
zmY)lTH;M)I;dY<HDntU&p&Oz!iM^bAlBU1?VCm%b0QZHo(!KbT)kc#@+60~8@MF2p
z71SK9JlEQKfZI~~NDxn`?o+V@@q)Agt|ZDX@1u6*={hG+vB>svlH&Nir|o2w{S&V5
z_t;#IpJGTgi_X(;m|qW4AB^ff4Vn>biL&`Rd@|odnH>@VWsfW?#)*KF=iU<|xjGV7
zqq@xc?DT$#-ALirO;-mZzqX6l!VU$)a;6m<+5JR?4*d$-$#PjT$0ag>49@_9<#)KK
z_hogjueV1k3<W`G#+i>m$8u}~jLeWvw}f6R^5Cq#{rYc?`TN_IM)h~+`Z{w~ubWjO
z!f2%u@HXdheNVHlwoD+mw1k|h<u<QCgG|es`zeqCM)fQ4RSb9$s0~}1S{S)HTwNc!
zNQx=&u;0kq{lk<yDk0dNFSfSlr}v2}bbKP~fH5^LY-EUmRb$IEa;yKs368VAN@78l
zmaSM7s(Z;9zQSH@<L$g-hhj(JfH0p~8(pD0Fp62IYXJ5)eRkwNkr`t!hHBqp-3z%Z
zpC(SID+Jmzn+rQ)ryQuW-XZGd3D1ascAe|Gr%q_>0N2{y;V_new^%=7j;=-FRr)q4
z5vM$p4gt7{(20XA?Pv+Dzr1wlJ2df}0<H%o${4Ve-#ZKunKbk8P(+-{^<Apa@YuLG
z!m1amKHZkAQfJ?Ot{WL|2v$qI5^zZmw+9GetFsx&&Vgr(Qt`nQe}GTpWUqV#t39xu
zCjOI`ft1&O0H%_1JIRIJv-^r?)9o>P%m;s<QTRVNy78N`1$c=(8#9PxE44Y<*Cb?M
zZ>1OFOnhp6f6PXzqQi9mm8-VWNae&}wuC<M-5GOh<LY%-m&CEWWyw{Bi^$*!P&_Tp
z3kn4eUkM4Ij)m|lQF9e?D^^O@`m(E`zBXfCUUO0F>LRQr$OyhW;5TR6O|Q0ReS}R<
zB0z+UZ(3_C+~XZS8LU~Y)l(ic3X;)KiMgMHh{R*ls(dGYt5zj2vyVtN@~#cCo@$R<
zt{JxSxbouIXZLVrQufrlf?7zm`oly@Fe$Z@_W4kj?#eYrc7EQL?4dGZI|zty=Go@E
zGMZlv$;9?9q}xH*_1M}VScB>*Y&_`Xuxyf+f6vf)kr4Uhdh5CH$uZFdnfxH-Sm?qC
zK{kM-_FU)eG;o{}v_lgo!yTByzgH@!zmEMGCPm7i^GYE&d<OM^L^90DVGC;5+wZ9w
zjaQW<er@1MuT^iE=q!p&C7~VD0|IWXk5YE7%Z@O=T+OH9Xo2>BrTTwnz+1IprtsC$
zIe#0AbZvHDo_Z%&_;dCzSSL=lZJR%P;Y+9TF6_`#3a_Jm!z+dUt96R&boB-NYSl^I
z2(&`Z`_*HizhhS$P__h~=v7)QR~IiC@HiX2_olTldAu4ZLym2WPsCCL&|&goDG>1F
zr^M8e)mD*h0;e%2=zsxl<Qz)qy^-P|(WDug5k<ZOY!V@SHXU~F`O(!VR!o12Nt-Vc
zf=<`vXLjSDNwUqpk)Kx-&~i#w#IXq<C_^F?G<ilcck%d)R^*<h<x7^#a5NkjSXhgH
z%~W*<{hW^2flrr59Kj!uNZb^OrC2I-eVjQzDMnz;E7*q^G;?}em#iM&-8GBthRa!v
zoXO_Q)I-cXNV9)XG=^$mMw3VjS6F+(0lhRql@W~@6w3INmq|;}*7e2pv2?8>Le%&B
z^$=OUv@q@HIlB;6UyM6K;+UmGJ(Pt~Bo}4Nk1=G?XXH9UZ8X0;J&C2bNlw)w6Uox{
zECRJxDo^%j?ud&U5)3W3YDD^l*%UE-ao_!W^;T-3eS|z{6E<09cP96;@l<}}9K)T{
z?)?px%Hp#O!k+^YueWK6!OGqr&_C)-(~hhmOB~aa3ELwuzKJEz)zBqM{Cb8)zGx+Z
z80dewD}q-LR{XSz9L^-1+k@}3)y4E2-t=)HHwck^nQ2){<`343UR1D^9LwL;Gxn(b
z@WI~H&S~OT47g#*nFoHnZ)B7K>gvUvL9h*pM}=!8GRKcPK#xPwsbqBv5;7B^*^L;;
z3O7H8O&zjw8T5yb^vqFQex4h+s&9CSLFe~5QU)Ot%zG@j6AZjWu`=xkgxsxcMD)1|
zDV*zmx)L$`-)w>n^FK!vB}DNI8h%H8t=VL4bSKTba)ky87<?z!UQ<OlxS5f4?H471
z9Kw1n$_J2FUCe`F`TPEV6#F&mRWnGBSby2mH(!5*5I=y7y*aa_l-sa#UktEwV(ooN
zKjc_5yCTr1;9nRnP=a%eXEOS{%tLd4_T{Eqal@I=`GP*v*qz}wLU_fSg*xyZJ24Gy
zwSQLs?!Xdd?`9NhNZ$cY+FS_j0EPFYa@y@es@nL)Z2z?HJ4Li%UM%?M3E!nWbev{i
z*EBT#>LeJo_gyCw=sT8u+3z|KuwHf@gmfRl^ujcs5JN?$Bopqi$k%N+Oqqr7bj#){
z@6LYH&f8QZ6tpTsHCjyeRmiC(?f6S9EqJ%+$qTJsa-3I)Rn9JIAySFgg)ukvX)<Wd
zPqSc(pde;Gcw9er`R;tR#ZM<gWk7kmAbdAsMEHQh){XecS_``?m-26!HTPPR+-s}j
z4-5ojRI*R_uuc(_a-i%E*+`$S4fCypJJ9%W##i3<9erGz0S@E9hzR;hgOjJo=fE%N
zla(qOt~`63RF<I*v3c>7tf%MaqhdS0=dfyuiW&KFQfIA=Mk6GmfNPlAIy3OQ2)%nW
zFcX{kJ<g|JOS8rwpx27nqS{Jpw#Zf}RM5;n1Ux$e7|-^)VTG@F?YVlFJn`9yx?Not
zDJ6-;<4M9XE84`)a9)?GRthQ#Oh!=v)!Xl*%iifH#5$9@gsrVyZ6Z3s%z7P59<W>$
z(|z2U_F=g8qn!vrb&2ZqsSVBR?v4Nxid3QEN9udZWNHC^E^G(G=dPEbrbHcdJAX61
zV!L0cw<>=m%b^^<mZPo9pM)=OpkTwJ#n+NIg*{$8o|%sN$FC}n!kL?0bOY|Kt^ep8
z3SHGGZP2?T`P*8~9dC)x7$WvS9>Oo4-Tvycp5?+|(v(cC)qx$n&w-cKwu^yuhbvCy
z&+t9Q96MHY<%@H|zboeh#IQ5!c(&L6K>VzHYrbzhsp91GQ98EjZqhfURi9-kmH*rl
zVz9LgXw2!+c_ZIICf!pbQMmk@mA_+F5A|{x#;*7}6}WIr;B1uA+Y$Q~P*gzS=`s(W
zz4*6V<RjjRRQOeMtVL{LARWF@B5U$J-^d0h1bWB>rep~V^Y9B|NsSo~VLaO<_R+Yo
z;84z!C#tF|IX=#R6%UQRHY$hp^{j~n*qvHMQ%X-7dS)$7;9gFW6m-J$i?A~y1U`Xl
zrid7uaoZn_a=R;j;T<;BHm~RogP%7~^cTD}2!6&&-x8LVZ}xJee@=40@R~|vbnhXM
z4V_?J!~4+k+DgdNu}Yg=JE7RaJ?XF61^;a2UpD(QtO`dw-W}HJxF9S(7$5T5#LJqe
zTAqpt(VzRZi~<z)Dxpj<%RAUVIx=7h{9m-aRa9GD*tQ$2NRd+9DelD`iWGN;;7;)1
zQYca^#hu_1+}$a~-Cc@naksvIzCFesW1sye`#Z>4#!3#7x#nE=b6*$wpsKxRw`Lch
zTHK(R<~2d$h#!2R&e69NFXkYu^e^z<_iVM&ki>R`isc!)I13!MUa?770=el;FIvAQ
z$`B2&?B)VD=WcUbHt1VcEq?lpBs{bG#fDz)_D)OoXwF-9r9Xi9gAHek{&Z^G{I$EG
zO8#hAc2}ijXcguw#0WQ7UmZkkzwu~Cc^K5kWM454Q|{E}*9Vcmj*G#+!Cf*%dUUG^
z@wo-aa=lzt0{_f>w=Ec@I%gzxD!pzV8jUMSX^zY}sc=wkXiqfro0i8pI<8%hxS~X`
zbsaO=so#CG5?S!2IQM!0ZiZtc&$>~AK5h6&i0GUn5pwpSF7dg|WLOPoX?oq2o#}^<
z;Xx){r{&aOreY~Os;S3d28<uz`0p6EZ+gAnl%FoI$G`-g+`i@u7C%won9FMs*8QlN
zX^O4;f1W4*2(NC#3c{bwuAJ6>-`rJkR=Hgdf3_Urm<<s5hG*F5m_0n;Ve&qbyE2-4
zzlE^IW>GE7^G#f)9rAAXLSXcFr`K7f$A;G5Rpn|6)TFGq$)+?mFVwPy_4WoQlk5Oc
z%d<<iZI_(Reo!w#wnG2_jZTvGj*fI$VDJPnlZ1B2nW@J@RojLJxkZyh@a4{&kJbf@
zIlW$&h!;OKAy>A%MjI|C(y_NFeXbQ|#$_<6^+N5}9D0R#qLjYV**ECJ_KwRW4YN$t
zfzBz#S+WLNnd*BWk2{)r^7PVu_ZQ0FU<o^NU7PSeP$D&tE2}EgJ_tL|Oo^T56hq@Z
zxk~TUDD5ksV$be1r|Y4P2ZuN;+zz!Sjxux5;m~4caj?oa(fgzpnHD6bW>`=rC!a_U
z02uKtSJO&idGBVF7UQv*K4|1B3TrF|b2I-3Sb%QT7$@$0!xq3Z{@cgJc~?!QgYG;_
zbs_M@Xh9$^8vTw~bNBDd6jV<{zFa{x&Z9R|NQ`T?^f5&lEVealEr#mn9Ot^Eh`!N>
z>3?Ok%NN#>lm*tl_*@*q7a5HzNKgTG$Es>jVg;0oEYU4#ni`W0xvWQr8TV8vO`{si
zA!{@?e7?XTVTbHjZvZvrXjdywo)fyVWYN*71Ru(k5_w)v6JbjA1}Ie>UBf=!wzC}*
z;*&=!RQw78PRDC}rhTLRSD5A!<h#(5px;4Q#=IA93Hz%pVR!G>ZrC)aSV8;k2W=f=
zLTtr$#j@+dTYBx~-xhRT-me-fTMv!P88<Dd3Ru`8ZR4PG!2RrQe?IMfR%I>jxTL5s
z9-?oIp`1nAX|GV>CPV3$2tKmEJS12lhSi}cIcPZ8#GkY2b@6jGL8}!0K!W8igeq`#
z-x8cm{ZW9IZ{KWzNtOrPJde*y<vtDC4y?8^g9p0=do3?TDb`>5vCK7P>*(r*8g*V-
z-hNV1R|7<1H0A~^zpF3!jeoGxTH=fUAlO%XTO<liG><ZTntR6_l$_^2B`wQ!tcco0
zNaC;bA0V#MlKO31x9O+#lZ`Cpo#Kf8xDL0%5J4GL#Kq_8HSqPe7{Zx^Q7?MWzH);f
z#!}to#QxR>t1t8ILHmS&RCAqa>ZcCTq>(DOJWPy<VeG)6K7M{krR9wk(#03P+5{Gs
zJdL}O;a>clzAj0uSv8J<k%!8)R=n(Tu3v?K;7R+cOA%C)#%4#X*4?aGV&1<tYgslW
zZa{9~Xpi!Syc;pWT>`L><WduL8#1v$J&H4sUmYC6`U%e={0!LabRFxjJ0F$cc%ypc
zz6li$VD?{<q)Af9f{LgM=An?gD|RQZUqRd;0Qkchnw-MLbm5x;c_GT=pfbU?ePBfL
zy9!nArwUFm#`8`PgYMf-=w|cZe0_5izl6=YDszL9!$*0Vc6@aRKE^v?=vh6#*HJ;X
z{wBjbp6V=p!Wt5Y&by3MG-8LN-uZ5-fst#lGuN+Tn>CJ;+m?<?Q^xH%<+!~kXV)9s
zO+dFLgpuC&ME^g4a7GnE_TBK?3c>gWrm{mxhIECW9-mKZ@;{x)F&VtzIX<$_ludAH
zun$B0hg~!`-*Rq_Mas4+iY8U-w?hh6d1nS(Mv=M!)x0d6V+Ep(`wBEpHG=7A{a=k8
zl4Z^6L`cV~zuRz9u3x5U0S{%rc6oo8ZK)GcGlynrDPp>>mYAoWLL}NwB|h+4;?Jg-
zRjYl6@#e9|-iGV3Ce4O~Lb768i_dne0MboDyVu2yR+M)_$W$<f_2*eciZ;f$$s}^^
z4nNHg@&kmpxTb^g)mZX!i)l`u;*%fpI8YQ?;($_xEr$}rmngi!11iz*Q05HI`TVMB
zNnD0@KfoYV#8u=+$?WxfTY~ZiT7C*BMKq)iT)-7?ItH2zMEleTHJIKeALc6F#)y2e
zLO#q%DeyyU#NoYCM&iBX984ehg_tq@3<XnX%?B9P>`UP2Fdj=|sM`&2h0N7uX=%Hw
zO$pxSA;#Arrkya8m8j06*?{M&M6)m=@1`8pFRslfRX)YgjW7sf_`A9?>qt?fmK7cU
z;|+2*7nu#;n{}0|LSHOJ&9OU^WV|jC&1poF9s^H^kcWU;9|q*{EqMWR5<>Sdy1ODq
z2q0Yg#wH7GfN!XZC3J`vQ<FP@IfnWteK=T^aVbmh^G=M*-_&banA})&s6q_+Qp`8W
z!z6UU2jGoiS?95m`{P2F;@x4Z+eKUYKdA;a#$(L{d3D*qro~4&x@xZYe*YyJ!Rm(J
zIRBEuetqg#oWE0^v{kBHLqZ?@huCUt&OZzw7IQbrs2KPc4PI!Q@V##${J<nMAdL^-
z78-y4VM;Xn`K4(*bQ-d8*=MQE8olox4Ak(4luzHSBv>_%k$=njr!(fzUcX{k=|7s?
zHcSpZj@q#4yi+z?!m3^&ixMb(O8eygHH0)H;e>NP<7c93p!MF|e}Lvy&cN|tinvYD
zEByv4`sR^&KkY9LYnui8%ku$J*XQ5wCQSp?Enyx&bbkedbK>&4$zG#xq$Tm_Cf%)7
zF*v#oKhNr|qQOsBdZ=!6aZ;_F0-Pu-v7JkN6*OZG)E06iyHy@Xk&DYF-9>r=WjDxK
z?o;?&eU`_5SR_Tf#HjYD>P)af<{(Y%@Zcf1o-NB0#*jolEdyXalgIHh(vU|czfoku
z*8(si27!bMlO&9QOyue+)EK6dP*j>!cv@!(5uTX<AV$wT&U%P32f+c85m04|ApG6=
z**iF)lG6@BjTcEFhuM9Anh>HWqK+^dJjJWI6I7dy9}x!xVsYXjzi0+S0Pv0+w!hA>
z<?p=(pE-9N#r8tP`b@qOTst^3a{d3WnC*Y-I?O__f*?G0$w{<Hp3T(I;Q@fpMcgZ2
znPll(TQ$}=-bXiC{_hP&I@uG8Dc@T78#*=J(4`^INc}+lMP7q5_lUtgN85Lus5;F)
z&LnhC`krF%97rLn!6zozkHK#+7X6c4wn?u6CUUM@zD1wZomH%N`_;jmDZOhZjN6~z
zpFlTWlx$fIhp5IGX=D0oYZNIl7it>s8W#A563JgjLxo=L7gmwRc&V^zAfk%*wd;+p
zg9z(=^bvmdhEy2G-IUFV4zj7s<>v_nZU{pyiY-NUq~F8YR-7bOh5o1GRS6$OBK2`Q
zS#?mV$e`67ce&0zU`bSxB;V`Co)dK`UElofsKkVtXGE~m7UR9mP*qghK6{QbZ|9Bh
zV65U-65g2oZiO^}W_RMFCo9Ky#g+N3)Pvvp+ivwva1xdZYw*@;T<o2YhXHSuo|+{M
zR!8^o)NCtin}7I9ZH*Wz@c329<r`l{_j=+0vnXv1RhU~+nNlpmuvj@ML;tj-8^`v4
z0681YmDT?MOy3<B7wbxn%N&y=UED!#eaT2}&`A~NeWxFGnc(Hu-vvp!T~HkMKi(w-
z?6SQUggTNTkIy+xVySWdWn6}aLM3PEOEg^~+qvN$pYe|-AMP`&X#%Rf11|jTHh8|y
zH9A;_jIIhM_#@~L(>1-PV%|I=dUl!cwFG})B=H%h%GL>5lL2E!I8d8+;^v5_+@nmu
zn)cYS`kCn*Id#(b4px_bvlBY}%&h;)CBRY!KOV#R&NPdSWav(Te~OKy;HPAs0k`s2
z5yKYyV^O&x$s!Xn2a&zDDE;f6KBLop1wp=?@o*Wo@BG`V=^e=k6AEnUrtQmj1N<u{
zCp*NSdJ`?1xLtYfDsa8kVhzVm{q^xPisGGmduysi1wizvVGj6x4?l^KbDH+4umg#t
z-_zfhU;peE>9>V@h$-*R><R=IP$dT(-xe&titx#4HP^M*C$dWk7KJ76$)o7E^7wwf
z56H2jVha56KdbOnP7QGY_l?>$+M!zu)-8-+o}~Y=TkPYQQ3mhr+q95bOqL#=#}&_c
z)N<LsJA=-YJ&S!}9ygy|z8nbU2`+bSoX?-&SFuyEk=n9PsG)<*@Z!8fLFX)QT0Ie|
z&Y0qEcm!zUNte3i2K$%S7qv~WQko$GzNRHLBtw$U>%ycE_Dc5Cc-p+DzTJn>W1ZGA
z;c4;xH})$dqAxc5Y@=k(ceDwo&{^J%zanJ0?>pa{?>LZr_Qc_d;>`CUrrL!*IPu8V
z&zvp37yN3+%G29Tu7+jDf3Ns%->6xn#qXF)kI}``QG}eazl%s|o>w*p{>~q$qiN)a
zvz@Gpv%nYqmfGkB*>l`1jOS{2?rOoM_ECZ4q`HkDIfrzX{ZrcCX0CxAwoTw2ugt*e
z4p`7hY1=bvmE(mva53TES*WM|p6T{M<>JwUULA0KFSyC~KR|bIjmqU_b{W}AM;l`+
z1Z&?SxRoq0yutIZJ$K-K)g#b0QM+-ghC&$9_1Rqi%E?9k3TMr7?wkW?rl9{I0Gyxy
zygDTNZ(^yD8Mm|cqdGV7n?wF%8jL^J5;@+8P>r*B=meXUW_O75q#frzu*?FeBN>52
z4ITB861_AOb?W{&vv*D`#xm!V+0QApI2Pb)K}&|t#`4!o0M9VP=`4Gj0<H81ZhOsz
z3A5N-er4PKJZAF}y$!1<bI(F@SsC>_drROoV&2`dPr>y+(9Vl!WfF?uQ_{OKIs3ov
zDZ^)qMpc;88SE4-lC)Iz+COdR5SpKZbubO(hQSl|AmERC9;7xP&qHBg$^_Fo+CdiM
z^JGMR`9E9FV_?gKbt$6eXXfWEj|rRf#m@<IxiF?CTwXf+zr87Os7-cG3TciR@B{8w
zqahqjwA%__I%f6pji5t50{VbpG=slI3WZK<IF_q5rV}V<_3JYIzrKyB8v{3iGTjG*
z`=7oHTK=jWvRjm7uNq<96d<mm$<$3`(tRk~vIue?;65P4Wt+~o8Z;z8=^B)s%krAA
z6|B?mGzgl!xt-9{IB2z43-`rev08V<Mkw8i+6kEHp%_57L$xkECJorHp-yEifhl?C
zA1{JC2FZNLYKz;_`TR50F+L5Sh8hRPlr0-G-4ykY3yaz3MG5`H5`Ho0PG$8Ozsm39
zI0rp+6A~JH8~{7-HY_$57WqO;R&P5-*o)4!XrHv9(d`=p>9NnR<Av3hBm<x^N_8P2
z>JJr68q@>UjsAur4&ZGNw?_Sf>0g1^u<jvd_&A-0KlXv6Jr#>j{zAbQc7yAXiKg(S
zp$##RbtFM=srx+Qrlbgq(64`2WmdtK@k{}~9teyrm)Fu-fY}OzelMhHd&p5vDVvF`
zmUX3=*D{<|f<s^x_qKYRJ$rsSQUwGH70qku8%2pD0R9o*`}BXd?`aMbrWZa9X-Ewd
zLF)96oSMiSmb+bP<G;Vxb-Ft-8=@o$(+c~PDBZEY8>&9qZM3`<eWROBV3n|_rnLl}
z3%T3>f#~O1#D8fr6eK0j0$rPO5Yi%H!P&%zfxcRI1h?AWl$s}ztPQAixE`M8EU2oK
z?nOg>)Z}6N?z@MJVlU7+Ru|c#ZkDIo9;@OGe+h+@d|*revl<hNv*8%KwKZ2YMnK?W
zgos#wa|%%cla$fTsPv4dxgIBdUBZ)h@4S0;P?)Eb(QZZX*L|>{Z_JT3qdyco`CAk#
zx#g$()tgeUeG#JCAk+6jjhOF8Vbz$7NJ8tyfX>Do(z~jTi_u(@CZpfOTbD9M9>h-R
zmaP?Bgse@aAF*FC{Mzw)c?Y@DLWH4J%q));t;la`epT)y0Dd0Gh_k}Skw&~B#oJtz
zM?AG9-lL0i=W6zIY;C8Vwi@I|4mJFZH0XB@d`Em#=zaKQcUj(1Y%0;!6ghaCCYw_)
z?gHbEb6#`NSeZqsNDco=H}hRw^^<~#sT>*BXdf!Es7;5l$ToK7j@U=m4h56J?P-40
z@ixB0v{~in=zs2bj2Sl{SDwEM|Lr8W!oK-^#aA`%;%Oty^vn8m?zVs@PPCwZJ+W={
zG3l2H_2rLnhfH_+T9;J2rzv3UQa@qh+LL$rObdcxDc^a^CeQS%T)qlH)5(CyCra%e
zA9DYt$@Z?qpEoX!*FuTX*W9;4XEO3KCoLR2nzA`COV`?fa#oPZO54ZM;Yxiz683ZC
z=`)K?C-6W3<JKP>;MyaQOgAQ03oBvJA3h86A7Fc;Igai*4E88-uHP^B?Y2Axg&<D~
z)WH+p+4)n4l~$JBS~)~7enFSDEZ>!<O^%o^pUjSCzNmIxM(`q0k}sE{=*D(fCn>4d
zk@Nt{%a<RoLJWS=i7Z@qS3hnRNIg+5Ew5Tom@u`%#Z3KmVU$8U$}2k^rRSpNXGVDc
zAAs2!JAftSzPz;Ch>`tIlXjz)z~mvDP?>rf`!ZQMe)L@tThYscPWoUvU>4Q(G(p3R
zEz%-+w+zNVS}{djyjJc!<*u=z($u_%aIDEaj~$Bs>wynDAAO@IaQm-MxuQ3vs$>-!
ze9i{(b(uE@8a=h{=XIe(SOPYu9Cj}L>avBE@T8l4o?bvMll{_8c^6Z91l><WFP^ix
zj+1+zyKlJt1gn&veU1T8N}g_(|GDY~ypYye-$c6!?cqW~wbYYJ$!*&GGCkOas_B};
zXLpsu`oIV8dI_@bCkwr)v3E<0q6GN;bqdJe<{q`OGP$k1o}({6)Z7fMlXl!k+NxW)
z6?skp%bOwV&64mgMU#AHvHPk1D6R!vD@dh|(&qJ$AXz!@mZtF>HMJ8AEjeVV9ksHF
ztU#E1RJ5`Py3`99T5RH5cI$nx+O4ua{<tdrGV#OvS4GQnG|`MxBzLQ5f<gyEs5?>G
z$g^fqkrcl6Tv-;mo1CT2SL_l8%>#sE{OY0~U&6GZ{0go_qFZ}jRcKJV<Z|Wh05Rr7
zeueeF_Cg_jv@wb?31+*qP@4?DG9;LMgVndT4P{Ta<u?{KB#k%?U1`y2$F=Y?XpAMA
zJJe4l;sg|Iu#=@6X=!HIWAD@05xHxIG*8;VHz+|eDMA|N3}cVuje}{%69AVRBgV~G
z?5eic0jp}&_7^LK?aKA<_;f01qgqE_bkpc+>k8aszYAN{5Sx6kDP+@8W5`Pw^m()Q
z4NpK$N*yI2z8m7L>t4ReX{-!x%eS<7i5wRTBkyCEP;XWO$W_USb}Ywi&cFDBq)`)G
zbMC-tstU+qZl}w0%DPm=ASDJmmc4%kO{%&4Xp!Ig8WwyyB{7+BHA4I#9fUn4&1$*f
z{{f0a2?{LglDt7>y{Y;{loJNmhDJs>n=(yr4$iyk{w;5Fvb*!7R<*<NdlXZ#A;r$4
zyF$$^P=;P)+*1`#TNGe(>P$A8&GX)((?Vx_4|(XZK1)^~b@<9m{Z`lmfz>d9uPCH^
z@+vlK!P}cXd$3XQIfiJ}*GlufC52#l$Ui&c(8g!5<|kWao1ACA(G1(wz!ZgQm^*&X
z(G-Ifh3`(pH*##5Pt8p0Svx_YjAASU;QIACm7YFjsme}BqMdeh9v!Yu2xqy3QE&ng
z36gl@Yq$v~OE4X2ij|j<O&Ze=_Zv-w*5_%-!!9LK@Le%x$9pCn)#B=@?}9Cy4F@z`
z7?82JhzX$OLAB6M@x29e#w;IzgCDXkj(vp$awwB?Of+=b^disFwc;PPA=|ydr^;}T
zhMYRR8m$_qt*|5i{_tg?XS^r4LRCyr@Tj@{SpclMe#JkHjRTw$0Eu33w!|pC_T$bb
zQzs>c)FlTu2(C@AoEru5i8Vz@0A(2A6D>#<Zzyz24y0xryK~U7jIpn*32K<K9~HMF
z6!RkY=MkdkXO%A$Na%-%pBJ;Ls9TqslNib0Ks~mu?k!&w7c5EhhK25mhzLie(x?v#
zH<2M4{afF?m*?okfeUN7j4?Is1ud~chuZN$-FM)aCToH-#&~54OYQ*HJSSO_vwH<c
z1f-w^`mU;I=5`W%@FcL|ys&v4$Qln`U}YA!p{eR^`Qhx-ZE9couo#RnL|W*VpuV9(
z_lKrXM<949jS9GlJB=k@eRdBgk#!=w4}c8*fUdt@ap31}J7c-ie)1`ubi*m}tFhsp
zc$Fn<esZmvtq9wJDTTAv{WC-L!w3;1kobyoU1DXs8J|x9((%2^lS)KY)DlOvx6BE!
zA44NWL5g_Dvw#g{6V7tlS44A709%@6*MaIRWRc2FZ(IJe-FZ5+bXRH+S~^G}t=O?t
zqWxbqycRKcm3jkiP}<MNTFjihyV6a<pJ_v4T)^qE1H*4c7045os)iG0LxPoatv@gk
z{w4G7s}kLmeOw-+Bxr8wlIH8IYn~PVp@lHQLnt&=?4T*8YaKeKK=*zwl`k>D$`(c?
ze3!qDCEE!ibI(fT(%@}9gcj4&S#~Mb6Ak+8l&CZQ>ABGAPbj~en%0&EfOA-c(u3nn
z=37YEJCEAKIuPGkllMs8-Pc&nH@RRMJ*w<>7)sL0G!^|obU$J33qsxw*W0XK`x-k&
zxl^%j3t3P~(YGoici<VqBaAWJW1Ow|nPDcQV}t|q6i2_LFNwT>;gmP3kf5l427d3S
zLfi0B+4gKTsIq#}nc93;P-NXsdH9)aM(x9my6wEKW2)ERy<#~y>9;i{*G}+Rdz$C(
z%gXcoN<rIKe;w&Q+he^dMPu2;zk%PE2#^W&{KBT2>%$dnEn~{tYSgC1(d^Uw+>HL1
z{1gcny8bnS*ceSWU^!|t(OC8Vvah6z>x#CT40<MNyd|b3%T2#}z&kh=JS?8lJ6wgF
zW4QIDu6*AvLv~1^_&8Dr$<6SBYp0zgadLENkI8hc3Y;pO)f^RJeAum`(=pGGBPCsr
zBLOn`3T-b-{mZ#W>!&BaX=MvyB%t$48TUna!10UP<IdVCo+|CXA=WN6?#>q0_V<~B
zDMnELoxqfZ6-PeU7qyZcBDT}d<u}wXlc-|*iY}<oT(R$xL~}=fTqrD6Ls?~&nh8Hg
zKWMYxs7Q{7de&sp@(Y8f{1PvLm8!Z@i8(<@$}J06DQ!=Zv<zicw{CUVtwN^;Qk98J
zQ>|U*BIV_;tp_#74GP>8r*Zr0T@|B$uVjh+Ff=H3z<aw#paqRG3Uup^4$lP6^#GRO
zI_dua?1Im_O$D&s0wu;&HH$9$g{6qS=IGW8I>o~uFoIFqoWxlnnw39`4Vx3xBA9v2
z!izC$y+}?d<J}?kRxzu(qR|i4t4_;ov?z>#7w!A20n&@sB>Q{BhP`y@gd91|`BU$f
zB%1F$;J?D83l+h|e5`g+xUA&Qi^aJ<#1*XOU0g=V36bfJlOhOujW@LNB-}#B8p6UR
zG`9JmoymWDa;57d_#$oAw+}T^?K7e{*pTrU1a~T|4t5g}2Um%wp*;s#b}vIa$nQ4P
zQhW8PvGWnM+3DL>297fi2~8<PaPS3CfM{{?dwb#ucL0hj-o~cbcth%S-+utKQj}ke
z9$78!kj9Om6X$dDR2!~wGCuX?ra{9AjIPs9jDYH?&JEVuIg4vY%=+KNIfpR%@n4Wd
z2Pbhh)^}bcyU=iBO}&&1olwfdE^hzQMO|@ybzw8GuE&viH<*-=yY5LUwzxLgUfZh{
zyRo}9R^<gLUJh%v3rF#)IUimz0IvA9U}Yh_@|h|;g6Mx&F146wa{dR<BQl*VTFk4v
zB#ymChoxFxKRE{8d6}2Z7rniO9r(S=AQ)Y%*c3lrwyvAj*){=NUukX{7Z?f&yGar(
z9|cl3Eje|bek&y>a4u+XOs(UMP91FeL_XILEb}hJgW?#3Fu@K$N>G_1E=0x00N^Mx
zoys!N$FIlN*42nDz+PnfgQ5Yw;jHcR^!+lD2d#!%6|Q>;Q&j@B(d<(5#$S&%u-r{u
z(xj|8GUAH;5FKh-pY(kHV!7MQy?E`ROLEd4Qe;8~q9-!dbNh*KWyy!I-E^Bg`9g-2
z>{`lSvsFx0_(zusW9d~&YO289H0`O^N2_bUjTnt$#VSa;gDg=ImZ>riM4=s)<a&BE
z{BC9QyIt%h;hu&qznbl)<GKgiRd{-%Kr{+q*K?`2nQ7AByq*Lx6a2r)lsuU_cW)|Q
zasD;&)4!)=-mP|kvEs8Vrj)T056X4fatKwCX{GRW(dZw`qELVNEOb}K@Y3|*3kPe}
z2fnt0{OG`&Y0nDO{BpO3B1b*Cgh3{MEOMeK=hRb8`A2#;uu*ZoeYXuN<-)u%D6wiU
zO%r!y3wt5cANvk@m!|dLj+gT+A8ijotM8?4Z#OA)LJeOq`I!pXMgeUc_>;pahJqeB
z+zMxYfd~EP$ph^7U(Gp&O*>*)Y6&E$i7Wg9)4-*Q1s~Sj!yUmu;FpMl9?wK;R-8OB
zhmQKWPj$`OQHVi80}Sst61I<=w0R-MQ*0{EG<5b-(Hgv0h8#xQ0p&bQ(2W&r!OG>4
zA5qh|(D9z0MD!HERxFps@rq%%a-zb8<_TxTa7WvKJR#44VInx3Kxz)%J7FnBu%da3
z7_WzXK|Rx1&Dn>5mffg~E6d|urd?}H#EbUB7gp@HqG0fC9-FZCrsOM&HnF6fxx^$h
zV4t?jxKWUJLIX+kAA#HSH7n3C3QB!78y!0zwCCyrqwv#HK$xDE6Do*JMgt50;@zP}
zmR(3tKzsm5@>kIy3e({$2s74tL`zFbGUBpWu~p}Gf<0|gol@4-4#`2KMWq9-VqDDq
zHqW2H<{GU%AI_+I2=kR2!15U)Zi*T4#r}eEdnUEd?nJ3eX9hMEdTh}ZSRJ37#Hjgx
zEZ^uZpvkK8C#OhHWoz0ZAvwCnes5Qe+tmJ4RPbA7H%`gEqT$CWX_r>;9KqxX(!=9F
z&lya#A-~>vy~C+0_vGj$suWI0a`Znw65`<^^>Hgp!SWVbO!+h2x+HZY4r0#|iV@2^
zB>T9*%7V}#zYuJ^wlm!sSBGi_W%Zsa!A~^Vu{^3nd|wl|5q)>zHM(PHnk_GkXG&}U
zku~}BjfpwzpC`vUW%qn0&-!fb2g}-`wat=M0WFLx`GSvMfFRQ<RW06)lFcCMH3-Hb
zBq2F#7lxt+l=`%c3IsiC@A=JnO(WBRRj3bPY7Ow*UWIvTHi(v0p<%U%6$0Q5myY%<
zP8q?P&|gV9)*2|8;xta+y1gyh2v<jknzHR(8FJZKVJ+dI^{kkv7{tD3{pR>{!u(ZJ
z*V(QyTF|lDRuJ;BZwY26mxn0XmQ73X``Z3xL&&&Xs-^%EoDoToSt>$!=G6FNfSN{?
zKJ=IgJz+QGWI95%-#f#(m?u3s3%-`zX(>LBw2o7AS1m@^Oum}@jxmkuEOz`Odafsh
zH=5K;6cckcX{nmI?P7xEZh#YE$Q`0fH%r;L)i%_chk`r}0^b&$2u~w(fB5;v93Qgc
zzWe}7a~BSt<K<$>M|ic@9}0g86GT|b(zfTiC7^z31a$dN2ieZXheGjR7bN7}WYzG~
zM^4q?XWB#2onTBhB#WF9nnIiVl6-ice43=fNEIW}%pzdH%_V^usKS!N932RJUkOgL
z0G!I(Rg~MmHwV!Yu5NjXu?~KdtO%(0CGWnoG{%V*l|EEnEd7fLHo~0sjX9GqsBq7n
zg4+5eL^ScBlH>ub;1o7EeR|Xc_jDMZS{!Phof$&K<}2K2;{f${RiFg1IOTbOzllCT
z{l<v02K&g=1=U%5$r`IO#))jb`<{6T4pUwzVE9PH3&qE#-c6dzRXqDfQZT`G>H&|w
z%?OY^E5)efGBrBmqQBOpGS2IHdY1JSNyRf$w*XKoLhAVVrjPd|*lSzGO{I;(E63k^
zVXVj5A6L?W{^BswIag9>2>AYp)$w_NaRwjg{Z$#u%25zqPzG<-*k>7Mg-#KCy{n9o
zLxL<_-bCK{T*VYw=9(<TVxv_&E9aP$y!RlhP&7;ui?eEYyMy?V_AcnebhZ)GX2mYF
z6@PwJ(nAft&|ih7#JU(!b}q=LQ_11%D{Q9mdKXzxi_d!xa4_W|UqFD0Jf{-xgJt37
zI9q%`vgVd1B@+TjcxDv>;F4vQD5Q`<Fc+Co8ldJy35olih7YG;0<uf<Fue=A0H`n|
zD3?SrLhNn!mD2R=cM1UWT@krW8o9bp9>B8zzQDMjNuW9>Q-T#{)5xb0Af5tG)69Sp
zxT<*sR+NWQNU{@rS5_FEl%&vsAOHAHcmZP1!MyO(TbQO2-qxe}zhNu?SKV&^7i8xD
z_p^~HRD5jXQquI>Olh5s!UWHP-yAkXmXdvXq`SMWv>naNo!Cy^hbBzUys=nSquOo-
zuz^en8>7n%D7;(6OQ1)WpwbY*1XLM-)=AK=Xuvm%#@I#vr?mrX)Y2NRmRZ|{8kDB&
z_Rgw@bT`z+F8lugzco%)3r$Ro8W_oFR0VG*9FCu5!jmY+Sgn4F$)9{DjUelYypG|K
zzCsP{lm_{W3f0@9(|!#!qS7##X#Ie8<RGHc*&M#y#~VqPw*U3q9f-z78oG?pp>O+n
z*A$zfsaP~2h=W!ugoqCQP%bu?uWJoGd{+E^JJ#V;JXi5%3ipwF^tAu}VJWkyuGNKo
z8ob})G8t62FO1qZVc72{VzNSf)mlBY%Qpl1j(kVfYS2WM@A&kj{cYi_Jun+ov;u=A
zv*NSPXzNs~uu|6z`QY>>`iRf&Y#Nwnx}Ph2_yE2zj%7kjO-GX>7=K(c2vwTiR}i;N
z@Crk0_lvc&$ncsVmG6#j%fm_F6M!g1*&x&#3hD?}4hk79ExP##^j(i%{|B%!tPt#T
zk_>&+L$7*eoU>h;^;c)Fs>?vczT*)1R5<!gz}*Fe9B=RE;oUsj>=t<a#*$NJS<JrT
z#78IZ?X2Tm>afuCJ^a}zCfHxa?CaR%2!Dc!R$zTEZ+d?R_IpO^MK@<U{o5({V-#GM
z#D7aN3kKHVYKcPW+i7#+-6>~n$hIxO$LBG1=pXf#HvM!_Zq(!Gr8!E%tFYWi-rD<Z
z=nh}sKtcy!rS-&#&ctc9=IG+8QWOU*T2P{rM-3l;;;Zc9qIZx?vBaP6ohdO_csi*U
z>hJlJ#EJ!Pi~=r>9O^F-6+jjVz26<g@~J#!F-S{CCwtw2H@)pl^%l(^NGwegAlOaY
zoAe8`si4ODS?Z4!DF#|Ks3bK-&d48S>b;F)hS;MQsV^hKAJ{_GS~wzH-Q3*o_!Ku}
zed0no@%{s#W7?e1vJr79gu7_m)_iThG){p<DXj@IsB|cK@U{6@0FU&7o!EEXd;@+U
z#hn_EE<q~cjl?L8oxlum%Ozim!N4c<{I`x?vI4@{^&>ZmVfFpIS25P<s?XHjO-h*{
z<OIRd+R84<Y4M-rAGtj3o;K7U4druX!VhLO(#K(i0W0vuo2JqEWLHi`20w#<{=E!I
z>0Yv2kYCO`$_PtVyHjKP5AVu|sTi-&oCWu$Pb4L-LN!E>x<ma?Ls-9QmxQ8xkB{CY
zG(5!xb^>4@GnR^r2urgJ&OJ1he@q+T4<v88aTa&H3KRXObK?@tx6IdNeZHkeoiz2L
zt>mO&v!3>>?f3mv@eW`h_v){l{u<-(jkhWM0@(HWqfx#_8`>1#fyk=<THBD{GtRb2
zjBUvg?s|HNkz!uQp-^e@`G}B9R1RT%bKIFOA((cH(1ggz_2yA~r0D0V$PtzOxz7}F
zjoa1wv-w=ltO@$Nz|*A|JHO4JB|cEFzdf015|RVfFH(9Hj6>pnRswM2TwlLBYwb{%
zA7jkLH#~QHGL<mG?X>;tG|2U_d5pUGi=XbtlIkrJ1L~-T9@Y~U1$~v9{_UXGQ{;}&
zK5|mpjQk|Gx(TJCm*5@}g)}S3ca|0>R^Yk}uN)4Uv(X~A$?z|Vbnyjevh1;k9;C&#
zeG&%L^06ynvKXv0m)ojwJ?F=NW`Z@Jy5d#5{z8VM-4F-@IL4h~^A<pRazdh{t9&;9
zsA=lk5+`c)(=*GTwW?{a|M<lv)XTEG14mQl-1fOs8)uCA={6s*?DltLQdQ|2L>{Zu
zH$xv>n}UnY))Y&CUS*aQ$I=0d8DM<r#}(Bt!m26vi257r<gs@a3}l0<Xczhk_Vp;l
zU(Evi7FzEJ(yv?3CCap+eo2<iGoCKB=Sp!<@o``3B_+y|VpCaN154`Iw~8_IF09`?
z0a(V(^NR~{qh#Kwylb_wznv%-6`)GAWcL74m|GgDKYPC#T>wFTpp1p#Nrj6SLv%gY
zUg;#O?2C!gGN}-8^fUGs;mjL$b^Im+M^8R%b-EL73c=n=U))*hSwwD;d2a5#WV$#l
z)t9dgGWD`-s8yDuzhZ^b<=aR|Do|2dB}aA&zp8Y<G0)V>ZK(Fuv89>-LuA*V7j#1;
zN@7!d=><^9mc(yY%o9HFz-8ent4Mq)DP>_^IreK?<XiJH+BrPhMaYc%Ca-f0HhV~V
zJ1v{OR56mCXtK1IRUaT4sjAxB<^ArR8JqSCO<{$--6Bz<GY=`{SOeIj#hioMnEyQL
z4B7j8N#Ioo$uXUj5azi9Z#9p<_Kpf{&EU1q<G=hcDwk^4$elJtwzLHZ>(ic`DJ8yi
zgTfcQ_D70&M^g70E%%vCtK<bdFD^6;CE7$(;q28sFy*B;V`-V0s6uR~W}}7Oi`g8-
z!cOlHfqDb8hyr32C%V(Op7yO54LmDL7;m>+DJ(|vKLC<6GlK4!lt_acNI6q=vminI
z9)9+rw*d5g;8BZZ`b}tiI)@)axkXmR<M(b5bz28qAYUZQmLG@Or8?H7=G-LbSJ_ta
zqt&RI$Dpa~qZrY4N?2D`Txq@P9(h`fk{QyGc*==D`@qCzO84kUbsqJFm53qnE#L4f
zQAcx{LgIQd5!#{adBEx1<|q7tpuxaPiqqwvMrHcHmuyGc>jtYlDEVW?a#JG2>`PNp
z8ltlvYOEeBw&c<&+*RTZ-e+jYX`Gtymy?}`5W7mA84(;`j~>i0Pq=e8FFpl5RAC|M
zg^U?Awzq{9U1z2+h7;ualIUv6p$6+jpvX^x=2Dta$#PYJ-;^)+ycB<mkLY|^NTKQM
z*+GR+Uny3qFF$F%J5YaxY@bzs`wtMG&<gL9D7y-lm;JOqrXdg!8&xQ&-Sy%EevsL#
z8GWbb$|50^zp+|oVz1y_nXs2@s<?BQycr%IYE;j02tMM`UwRHze8D@f@ta6JFbv;d
zeL=`!hR^mktADq%a#R~%pl>>r=-YSddaNGWJ}ds|?PIY(N#AOqBzNFVTw`X6<D+`d
z+XUSl6(WAklz*yd7qn(Fiqh8b5+$+vL-`+IHomQTcgO@?oJ_m5{zp^U7m?6-)}Jw7
zqtU8K8?yy$G`*K+W|OVyQUsWUti=ZGeL~c*<?I@U94!-knYzeMwezKDk&v#+1q_Xn
z9r2DFSah_Vp>0MjTxl8x3{RhyOA4TWc~=t7)UooLuUWCzq_LP%XjcQ!w{(K&>UD2K
zD7mzBq`sruO)Yw&hyAV{b#x38c6BiQN9fh)F;&|x_lY%V%Pj79JwvL{&^Wi`sir=e
zgVIs8$)EABC-BjtzQuco6ygb)j(UQ5x(*k9vu+o+cPz~8u!ZXG2^U=MAbs8YCf~vn
zM54MNInMomD#b-Joys|sDOUc(wk8>jm=5`}9DWU|E^f!<$*W%Z#p`U|uK4VeEOuRk
z=zksRuD(Qm6WGz$)CVdl?H_gcOt^7>B+CjU;42(s$4t&#udOaGi5pB`Z{oBHj-Ctt
zH3aO94so08gUWBMh11e`lzpp7|EMB1AB!S^XxwSafnciG1|JdqNJJnXUlE@h1Drko
zp+`^7gf*QDRKZODSgpbq_X8VeLj45q$s4Jl!egjP4zF``4Z-c5D=V{1EpBoAAq)xg
z-R?+{U6Evj6s!xBcgDDyWE_;B%L{IURD*%s1~h9?yBXPHrx*s_;yekud94|=*QqMQ
zavNghRb~tjszyxK+%!?rkgq;g7{4H?vp%~iiL%S+zj#ld46Memp7sdJYw-`#?7@rq
zaQ#OMZz69c&ag!JXzahC=>?|hLSA-0kXh>_cct&UM#c^Zxa}SKfMu`!S$rSrVig;=
zOsphgv6BZu)SfdcarqQYwE{c=np7rB_Bb<ecX=sJwge{)1pv$skm3SUre(YxQ_Tyk
zrj*&;#HBy*3|Cwt)&;Tbqc{N;5?>~i@j{Qaml56U3BgG@C;-}kCFD52pNP`Yl6Bz&
zbhT%uT~KXZ=TMlcQ*pdCt)+@l1%7@)p3@b7pP_DAk{adpe)==UIKLj7s+lWjhJK>Z
z`lCc(mS#>t9gM9bZXC^C0yjyBq<m+`*VS4rbBTa1p;4)m!F`E<E2vT<*;!DOpd7xH
z23i;$B9mJD{_EiMgT3uKn0-=CF;S^#rO~t0DsJp_GoLlb4nYA^fo@hNJTZMO;_~WL
zHLTf_K$<?i;sa5%4x=pAY9&=hH&8P(n7F)^0K>8rrhhF*U?rIp5*VI~iOFz(s?xz4
zY$WsPDB@HL`FC(AboP2`wCkNvu>!VM*x_vbeUQ2ii?G&Co0TKl^_Ogh5mX(aTLNLw
z4IECSx&^%P%ClC-(n{6Kx)cwo66P*73Shn@PEHYA_n&XmN2`jDHK`gA)u>hqzAJa<
zUtF!yv5sR;niL`sjXC+1<IwE<;kC&W%y@9Pna(M8Wcz-=uFxC@l|n_#cKKulb+sZx
z4$iMATvt;~(W8htu3<lH)-0EH5@Y33KSynnL`%q4RsChZ)<aB{f<hy|!!wL0XmXHv
z&Xn(xa`V?;M~E(kjOlO5YCcE*{>W4pdoQ$^ZMNYv8Cb`9plSX`!btf~F6rw;F?)Wt
zv&0qgTQ{`%*nPE)0coy36Pm~+bXnRv>V2V8U97ywZWIxGlz(ptc-BVftQXKV<`<lE
zIUL~jJZBL1s1F~Fl+oMOEzC;eRT}b+lZUc6EAOCi;*0n#8oAXRe=CK(j?sUB4@Ks&
zScC{6QaGsZvTWEl(_Q^EBV)Hu;Xg1X5_LJ`h4pu;;_CLePIUH_!)t1ODYCMXm3zY+
z12oc<@>9Uc9M4o)vrKR87+U8+!MkGO!S67pAlXMzoytAy4!;Gva5`e?y9&+M!la~S
z3=R|n^e>+98Xw^yG9}BF)GLxkR|n@P1onxb7i%e04Ha~uMMi`~A4CPL^eQ2XDwO5k
zGv&T3qn^9qV@-wpM$P$3V%Ak&K3bms)Not<vp456C1Gc)cLN?<-vwo3AsNEd=Bn|E
z(Oc>{9{!fCd6{G7`Jp47Q%kXf=>T-}@uy*&ro3o0!$f##pX*gzN+jh%*1pZVWU5uD
z^bpwjTGsMtCI{q6MQD2J^_y%hlm%(fU#rqHT<6->b!;WFGC)Fh$v5JhQuUos0pI7m
z8JQX7!-L@pjV%JeE;P)^o9olti8bdTDp{AvV)0P(H-eWhs}}{Fj2S_vpU4wTrXBXb
zqdw+pUH&WOa7yFiCkXv)f4_b8SuJ+z+Z913+#pKO2n3<S*~*(4lofXOH-<%Z_3<k;
zITvY4v&HRm&fi43wrw<+m9xC~ZbeKKpJ_J@N>g<sI~|r7$#vi5mV;W_y<b&ejYJ%1
zp5K@$hxokk=AXWSS{@Mg8|SL&gOWl@U0FYc680i<=R{QbAJpySZ=2t<ivrj66<R+@
zjt35Qs;S$wE^s)@1IC|zRqk6!X4DtU|Mb@y&0fc-!_-I4Ny)^euWG#!|K=#_4wQOt
zT=>B%mb(OhO-V2JAP$qLw5m0`$|?OVogdZt?kDgBZT#&p(KS=fz6xW1^1EVV+L<>Q
z5;5_YKK0*~R;;1=+RFuB(;KY;BgYdqMRDv?sXA~A9M3x%+v9Z|G9|;vYD}2w%=#_t
zJySEPjHNeLdvwu{hbM)dT>hH(&5N5Q)fg6e|E42|*DKzbAW9&k)a8wC=er3fFGRWy
zhyg-O)ECA1pia03i-GcK!fJDv#+s{~X1BJCw<66jxaT4AUm?scubRP5EG5J_(IH5l
ze9N=i?L{3Tq^uk2A^kXfVd%FXqCCdU!%UqDxPt#*?k&T6J;^GXIlrbkIZX^i<kTDX
zjAe)URt|)}zoVm~dpHX<o(jJu^JrW<1ejvoV5cY<UWVv5Yz(;)bB??#W;YqO?!i88
zcLzqE<I=@5jo~gfe)e#nuADC5@Y~YkDlsMV(Zf_lmDyW3TrknZqgQxoBd)UM(56Y*
z=vh8kU3ovFaAeQf@h_sw<#+}*p3&K>+S>(!_G=jC>*G7}^=aHFUQxvAo(l=sCZdAX
zS7i=1Wd*65vCmUHV|^w;Gb>NK_FJ|!1YJU#!eKGJwhm-8>DwayWfMB{cT4cmh&|>$
zr&HBg^Vl`qCrVo}{l#(<gVm9=MtuoK=e5no65iXd4Iej^GAx-cl_ih7J~Gd|H7{zg
zz2{ZNL3QRbZWIXoW?mrk{!FuRcqW16^Db~m&Q11FZ(x(HC+_d!Ol29#>NV%F!6v_O
zO5gVq-b6+0gEbP2!X`VrK$cLcE`Qyx@>XNcGE)=AQL`7K%45PN1qSkkZoa<jB1=Yj
zB>=gfD-oc}GTPx?`@a{rH9nX8xeU1lGGzKqZM1AgG5re@RK4x|(PMOkrPdVW(a<Bn
zZY+u|TDe0CDbpQcYV?fqJktbzHWq+_867rKlqV^#iojc3v8k{R?C{uu;%2kuSWV=l
zSF0J;5n=r1x7)X(b*)b2e{x@k4lI?#j?PpwIF+{@Bq2>)+>wpxh5Qcuni-rVn!~C&
z>2ECF7lB3Vfs|wr51OjnR0wc0pwVUE^ov!y9gy)C1-jRrRGb;eV~x2zw0*{73-GO|
zGnA$@Fqh1=-~F`2XSfc_qW8D@jM)Ar%$gE~H9vmQl6A@QfpBQ!*A}U)WUOErV3&8%
zj3}oO(<06ft@k#M{6!re@V;ZByz`pNf)oy@xVXmK`j^LP0kzgsO;giR$+ZZdH}@=<
z3DP}RK`UojOIFJLjM2IQ`@h0?=Hr0fL$%fZ{XCHfMxIDiK>FI5Tp!Wljfg;rYOg&?
z6%VtBdfhjNcYChOQ^2i+0-h8umK>I25gPbi5P)R$#&TPm(sEc@9z?8XNz0hypx3vG
zWC~B?(W3mEDL|`%sn6NhvUvMgi4L<na~5+>v=Zq<z<C)m|F6wqmNMiz?5b~-gNV)}
z2w<%f9{IutRRDqP)3-JKeP=&y&X1SA_X_;Nu{p`@t`luoYhB`We~P#Mg9nam;j^d9
z^O$9bPu>|*-`sVp=a`4KHHLG${sRQ-R0LsKY1dLW5&yt6i^bww`gllr`=}lEWfb;{
zeYlMH&+jxB-YyVaPkA>>JoDOC@>%uPlk(O!I&?D#-?M^$Twu$y{72S8rq<1y$YSyX
zJv1~3o7tzhikWXd5<A&8OC5{D4lu#A-JxlVpLZB4@ewIuNYTh$o=Z*<Kra}L(Nyr8
zLCAB9t9-I@*el?Cp#vtfFQFZ)#z$?35Qa1xo7_{yt$-|V^sLEDuGi0QWdKqm%_1U`
zxU0!^vG&CockSO>`hG>E@Be1DR?(80!FXx{X11|F*hrF;$s}&Ikd?DMHH1p8`2C1w
z<wsdVBk&tkNlVD}%WzZ@W5IzExY&=(FFC~7&()bNf=;#hWLAsrZuvr)iTAL(Sh$7C
z<X?{?#8cSv3rR{Djo{tbv_v&~$6e-D%mq0x7klv9&}<FOjdqp%E<xa@c-AUMi=pyT
zxSlLW=uA;Iu%wF{4dMY`jwh5tALkU~19O@rWc65Qp?XL#mB!G;__)C!YSv&C7KJhh
z)EVw<qv0&10Hs@M?an4SQGcS1_1D7LD1&?iRkr4#L2OsURa*~=Fch}jHR+44FB5Wy
zAepfPsu9)9ig>qt<xn61tN*016_|pR(kia}Y3gAWHZKpuV<1zgCc~ATIQJp&^w6Nh
z8t>&<cGsmmmm3YO^<&oq8D%A^Se(=+E9??_6-8QZE>rQ$nOqz2gs=Q<LfD)AP9%yE
z!7y4|ENeN!5PzfaXEmApey4aB58q<|CERWh7(d1zfp__Z^pw44z6J)@l)uqZE-XsM
zG5PE1(C24GMbIQuDN6X+B;Qs=Aq{ZF@$M=Q+990$x?0WhL8_81Bw%*DD@IaPAfU-Y
zP~I2>D+(Ro=Aq(cX^~vE@@}cfVjoQUlo9_PKppqpN#s;x$fn-(v(kin&k$n`iA$od
zAVf=dut^-nJTp~y6_d6L)xXSz@bEKJ{5BhlL3OiJW3EOK06LycaX*Ggfe`XgQ-^wH
z(^Wxg6kimjT-B<Oh#x8BDes0JD@<P4DCNy>Tmh$stBWwKn4cm!U95wA8|Kv)bjjFi
zQvPt-=~Q>e&4J^`ez;{_N0CN1;rC~@g<6k|=HC0-;Zu1I^KN@lXbYGswI|N6Bx{<h
zH}V4LC$g&^nG{<H9h;Ofs59dzAU@h@gtg%<--}ptALqrU|6-`Eu0n38-xYNE-NGBr
zeZ0*0Wm~7jr%H4vskD4K^0W@Py1FFa;QNu9c>hvl=`)yTW8L@M$L4=Fi^Ad69Mz~I
zIzEW`T4bDPl0!lRe66c>n|4E<rJBp1WNc5An$|>LyI2l_8IAyx`?Nx(cbp}6h*^<8
zMSBdJzc;zaSd>hASI#*x9ko?AXcGsLEyxqZ_sV_47$|h-`CE@^ZNHHHGc&Tw8ypAB
z47*5}&8c@<_I4+GHyLnpd`x3-0%ZCR5M_>Zem9`i6E~hHoyA2=Isb<3xO}FEihliq
zc_nkzyRM2o{^lV2)k8d(aWfUdqi#j<tZ`eA8bo#~r}zbf32>_T9RprFyk<gRLgn>@
zol2m~HGNhC@=O5WLliu+0i}Rr87d$afO>Z}`$-EVxf4W~xtT4m0${w!^MIWyKma1M
z-v1hlL%@$(fI+5X1*p+9!lSy~#RSPA4De|ucu))^I0<r}4Z?Sq+m{#i%)@~O5kg$0
zhw$^iC}zfdA_~=`rD7@{Az`R0I5X09v#E_dVJgU5{@*H({cl{C8G~80lyO~i=6@KO
z|IdqngZEUVMJ{Jkz=OI1clgzQ177ztdWhD1YDC8hDf2Kp%gMv`sSYnprGqj;B-_Z%
zLM2GVi59V2@})f)ko)%HaV{`ctM&SXl~)NX0&I}T6mT*~&Wv>c|F6c4frT|HtgB(P
z?~^Q8OV^|e#@|q+V$;B@$@yfYjvDH7qf@`Y2g+Gpl=sRK{K6!DHv$~nQ*7N9V=cZy
z{n50+ec8)bndodrD5I&<Lu%E7`Aw5OaF(qfBD5Me$%>JXM4z7;=d610)#h1eA;(Z8
zxxL;U`N)k#uriWRi3DE9RUogpu5aH81>&yzj-@>7VYcO+NAdA}p>!a+ce3>*=*%Gg
z)7<tFpsR$}jcDn<$pi76H|TQ}PsuvH!JW-*&T65X@46DNC<UT%e1@%-cr%n1xA;0A
zj<#m|oG}k*I7S~rqB3YnEWDl*fc^^N`4)RX*t$2!)iz;6-|cKobP0qt4vY*@Amb8Y
zj>m4T5l)oQ3pKV0F6$F(3rn+_xfA?Fy9m2+=JoH1;CnCfCZ>`-oXj}d*ZRD8A!%ZK
zxw-0IvAM|-xP95>7q7;5A~;ebqXcD6jqdVRcVbob-$(dilsw7(f2cdFt+?7QN<*;V
z?i$?PU4pwi1c$=iEqLJ$g}WB+7J|E5u;5-eAxQYT{<9u^2Ys-wV2^h!oAa5>;N<u=
z<ulQdfyB>m6Q>T^hPx7hhP=oY{+Tvf^?3QX6O9OI``f{X5%UZ+H8q-2IKLnvOn+k>
zszz{CdVt1>gV_1NiCgnnZwV~FXyf?v&z+j>c)?4K6E^Je-=!um^}Uj@exGxP9E9$K
z&hwuZ0p<jwf)%@;IJ)Zl0rMJtZ8pn|v-KN-Q;3LtYQqQYy)K8&)7(#+hg9q3e+fs7
z#$$`KPHxAKA|f|)W*ybs)1T#M+z3D5?p(n2FGh8((jy=5;&Nh9o&yYj14M<0@*s3A
zA(u(*kK>wQj*)jo;jTd{AJ)QY#pb=Z<Ad*jlZ=#K4^_V^)70q&jr1i33mhF)@61|D
zOInR{A%`?X8Nu@bPn5_(yaP+^-7ek|^ePQlCG(H<^H2y@esFI66@}DyWom*_UXXE`
ze`TF_jUvP5@eka(P?C;NrP08|2cGMfJTTzrzN*K?l@vh{t4GtEHG-^6ji0gMVjkfi
zwc5}`A^iO1o!D6yZol)*It69j=eD85DhZ?Sj=r++-|^n`m}M9<=GEs?zRC;MDHX58
z6Impd1DE#nHSpzUfo-Wbn`b*>jQoKyQ<8sbz<c(2tb=cQJZZ2qElxxxD~JRP7%Y;L
z<J6_LY&V8A;flpnugOZD#tqxBK&bEmn79oazE-1Re-VTZJ`?8aiqKu&nD6y1ER#^$
zy(1ji;6r6{W^*RB5b>lw!fzCmWA^>TbFO~{0rTPCKeuT=je{K^<<Z|}YFI1&M6pex
zE)}4@aNm|Kr|LI&b+n|^HCe4w*S0hWXhPVjCv)(%!!VnwbN@nASp6&0M)q_*|7zx+
zchapulv$x@C;zD{qD>3CRQn4ijmZ*bT-!)oM>dA}2LyN2hN=9DhQRmV{slT8t&NK!
zzOQyC6Qd2|L;zL*3J}$>B6((fx)2lWNFE*iQjz0KpM5epk8gwL%+dy@!O1*M6TX%*
z?X!3dO-8z_yE7TaVxcM7*;wQ1mQ`UwztJ_@kGE@Fs~zG{6{Xh0PMhwH(2~W>>CL`g
z3z+N<8zg=NGfvA8$vg+22l7&jjS9jiSIF=y(0WQ)buH66Pq(>)_+hF0unVe=UB-%N
z%1;^K-}D0OB4&+SO-DEY#bh<%YvD8up;O@Y{PD<yj$i~i-mL}!>A@l+Ru=q(T(JlF
z9G!@SH<FePZRqV+lRhNV%|L|VhKA9;3D3&LeF##=Wh#$m%ST%zEm)nYD}eT(WB7a4
zB1}PW)HZWt8snFX$O@XGXo#+sZ$8%$x27v?G9zX_rO|*XO!N9$g=$3goP%}eMsMZ=
z1Q@9>tx&FT*5{0LSAAEAE;#=HqYq3OyNWtI!kp2v_ho1kdHyOVf4f4cr)@m{@NZ0%
zk5;=ye1Apfe%9R|mHrw@)TfwTiq(Qp@Nli7y>IJYp&KbVpqA|@1-marge1V|2_s-F
zzb2h#>4V(l+{mn!u8%bVa<AO=J}~~&7{pE6aduASMH7vGpH<-YM<v&l8+SNjtsiqJ
z6pL!nn!t1R#Ni(I!8hUU6$mL4w=R7p>c@1&rd=Bog7I=`-}`|b1jnCT!(URh)oZAv
zEIz+)l@^Nf1Ys~)-kqQM{whQj)bjpooKGw!_OSrq7%zBaXe3UXm<_Da?rGJRWhy&S
z-XYX%Z+&oOwM}Bh{ox{OiO%i6l1FsXy|q$`!*bz@ZSRu}rTsWCkCRpFJDd_XSPh2|
z<_&R9E!68XLb{Hd+cecbcdDpWBo`2=I<x<>$RgC9dm44vGG`xsfIaQ^-KDx?@ryAk
z9NT5_L-U85F&_vZdHAQbsVWTF&mvlu;Jn|WZXU6?GRhn``JHWA^8%VoadFC;rI}0%
zSi)RtPS8;jQAZ9E7H3)l?d{6r<%&o`3^zN&+f51lY0?a6bwqKtQw=%-GLIvpm6dC#
ztdcbLbi2I+^BxBNoEXx6K!aVFgL(n-KRh|dqeWt9cH6wRDw7~sFNqIm<o{U2USHpq
zwzmHjdZ*jo_SaGPb3|o377h%sc6Tp*j0gO%mm?BsUg{RA|7IMW#<xLs>T02Bcu9~A
z&B<<7OzxSTRa$0A&eCyxR&$)IGixiTWE^FSOqKAFq!p;HXXq$6-TLtXuj<rFQ8ZV(
z!;%vh=Mh|M#iraHVpljd&sedw*?iPB(ATlM)&iNAj0Aaiw0eBOR){&?I|b_m2Wobt
zW+6{8JiCJ~D-;E8FkZ2beLe3xOAg9Sn)mJ?dS0RUq?mjhPG9<gGHGP6!0*==n+N}n
z+aj*+1QcQ<0jIKbUNh;wtLS6&Ch3p0J$W{%vPRNl-jfrh=h97pO!~w>ayneiLWiF!
zxyKSXe@7|OR_Fu5nAp;GAtc1>))CiTm-_R;hPk|ioRi~Fx~g^{ZvH>!S_iNz)%H0<
z3BEs}<*naijk6bB+OXw4`+*-tJ6ZEpkT*p;-ZMsB*bKr~_6lZhfD={5cdn%xWtO_c
z?(ufxje9P(`4Hx|^qeAl$(2QgrB*J0&lqad79)|KSgoK%o?6#1r{Lo?bGbH-fb-9~
z%F9{R7H>1D`eU!Fuugx5O$*#FJ4vOjEs}fQRdMbqJhS5brW;-~h3K>dOl=~0$3(O0
zU5qG5d;tQI9`*HNvNE)+O9Y>NUV$8LOf%ijyeYjAF`|0Vm?@Rsj|Gialq%X!zy9P3
zJXaPB%E`HC19RnxZH(&aH@7jJP=Z=!NROon(p3|hkTw4?3wR9YM`(bDV}8<?ryb{L
zX?)^-;H1Kls?MKGF2E2280hq(bSN;j_h@?_FR*I@=~KH(?Kde8-fM$DjLE;}viL9D
z3)QJMmwydY$TN?))D`{S>hg2zg4wU~v!q4pjh4Dko;wM|Wdn?3)dUW*FyCnukIv+C
zET7bTT?_eDE`-mk@{@n23(7zxzcN?VJMTuioeyZnXgL0EGPY~(BQt9=MZwi0fDp{g
zSZGK)c>1a{X-_upj8U<__}LDVM&LG6sJ_7L&)8nLWkX&!4H3R%3xooY#-%!AZ9~Hv
zc(le9-HDqyZkYJ8tv-FJXZAHwow~LGQ<gcHM`4j*m~2%^z&gQq7r=UuIe|o6*?dS-
zf&5uM2-7HjW*q#*s&@@^NHptUkv`nsLy|h61|YQ=Ri&C*X`+vep%K;HSmQf-!cPKI
zccPE?8!Aqi1uTkbkRW~wT(-%9XGK&v#ZQ?#EyI4SDo#l<7Oa0^MUt{!^X0rT&yrf_
zBb_V!W(tK5?CA-%XU=IeOFfM$%n&kl;a=)?5kR@%L?|KOgmo2+L(ST8Wupb1PGTqI
zU*8s|iwUKzwJC7?Yb=q7e~z*=!zWNM>n<crDu1CN;=_1<)BPpxLj`nO4%#M55jkjA
zK_QLt)S@PUTUg6&PJ(~&XXvgyC%|w+;7(!OC{j`v=M}P<Wvz$V0)-WOu6Rm)o%MoF
zGF*?<JL2YG&hcY@&vXTw7YCfL+G2<fi({VYN;ZO<FqJ%A2leP|;-~7JnQI?}sS2b@
zNeJ5gj;<X-t)@-hn!9DlUDhDcKJX`wP1BKEXWwCrRW(hD6Po*4C{yW0D{-sIQ*siu
zfwNBs-V@Y(Oddf7N=(h(UdXwYFKjDD)3VAx$TW7SMGf0qIt7JjB>V@1FOKRdE@@*9
zrlLWE`W*fH|9A+MJL>CQe6G+DQwQivniGy0z<>Q_MWzEyh8>~ocA7kM6vQe6wpa16
zO}g&0EVZQ4*vQ9C_3SNYxKCW_d)uK?+zN9L)navT;76;mh^>yOz>uMQhDN!{Bo#2?
zSo9<-@u9+K@gy<pIt4Bg<9wGobC+>8du$jQw*H!f@6X>LqO0F7E2IdQl)sX8O$9jv
zlvq}!gfcI}TG;52Du7iH9u2)mOkG2N0pCkJC*N7<5fhW=zcbHo=t*@WO<#fldf&W5
z*gJ3kRkU&2+ne#ji>tYtNERed2}1Np3<dD)SO*Gfc{{g<;rfN>x-g;-6pk<u-7mG(
zMN9;cp?CwGOQ%u!`#K;2-B2-91pTH^$!l#95hWz4fDn6bcDI)tEl$w8NK<%V5$Mji
zJ<|xhv;Djj@`xiQZ*=oPL|;T1t9i}G5N`3ZB=F)J`c&7E&7#LA%z+mql0E$M=CRx{
zPvRh^PX6&v1KZxi&%Ct6P3Y#&bp7!So#15un%a#<Q1_eXXwbCH!MC)T7WSiELq*=A
zo=19>YhLp>P<9O4Xu2G`bBcw)lcuS7{NXI6PMTw)(GX+B1mmcHb%^evQDGzb<iAbl
zC+ZSaJx`3E-O_g{l@+V@d3isuT)_?RvNXTAV~OCRh-TdzUQA24Zj5kyW*;PWpK6_{
zlRl64OXpw>yVB0z-y&%N9{-Gy1{GrPC<ET|5k9rGvuJe~=Oj=Jfkk2`mc2D?M-7!-
z4*3=~FWuT0jwdMk9f8bWBM*trK}+!gvPF#fN$or`P|OT5JGrH5Spxz_6fIebI-tgW
zqrlwilmEFsyFr$mczfg?!rM0r3LWw?-nZ-#1fQo%;H+^n<Lw@%jFxf;ipBSbbAvGg
zE3SQqLc2r@TV`PlRfQIH{QD9_`rQ&;==`Qi);!MW?W?Ex92J-yCQ7&8A1ME^P^9W$
zW7S@0siyGQu&Szx_7KyO1f2<I(V_yPM1fUw2ZXAzgiVKFD7qL|l$0QX8X#=1;7kPX
zm%T3L7!!rPKZ&%~bab4}nEN9by=~J)<9(>x9@44UT*Wx@MBPYZs_sr+(DL0{5aAUi
zTX(_r@vl{22AZ|tzh4ZmdVhQt;t9QWcr?7t=^|q>P#?=zytZ;uBP$JgR%}}zXFcB3
zKk+{BpTc>pYdX}3*AU*MdI*gNjE-rpCJf&GOjcYk?M_2)Qt%<j?r>agZ$viu+cG5*
zFVZzFn=+t5G{4q8+18{XYEK@p->Yr4#=%>T^^+-yYZ14?e66(1fr`7Gg}5y+y3MUo
z6d**-LT*=hB8Mx*3d9iq%Gd1f@u2n~l5HzA?ExtF-2Ul)GW1tWEr8@8%DQ39wla^l
zQzWsisaRsHYt~dD4L5f1Q{y&(P{6%$(@^p99!=K?&S0*6gwl%uE_GJO1=3g=7#O=1
zYL<aWbkfWxreHKNV6JYog)R{I1=Z6xxKcrn*nEo8cNt&DF(5s^e;9#sr%K+7kJkDD
z`X~8VJsC~1kiY?=Q=92lOCN;iKAZg`o#{igX*BK17%b~50-BiHeSt6sVqO0n=R{%a
zHqX|e4j8Pt@e};B+1kyq;@<GW{B^AwVh&G>QCd|;ciQQ<4HXv=U63VrPqfx&vGW}S
zv{hI<%XBciU%5s<6Ea@zV;S#fM&8^qUX=Z%R=!-Ht*eh`{0h+M>fBpSc87muDqWD1
ztl17r(%*QWFHLc%!Kb<?f|EC|`c@tvS~pj9JzdImdUuGO<ijazO<3}Oml((6-|RG6
z)muhVWXF`fd7JIQtUx~86MV>}si$0RiKcXE0t}1rEhNMG9$*k<pd~moPD1^Lk}biG
ze5tx~4|MS~Y)+mdC<UZ9;*Igqp(7UT<}D>Gbzw+AVY6$WD-U$gkSv)SwV?`#;9foG
zZa*ukkBM@Ugz7&SYs=Cx5^!?wWbJU4g=uv(R~-Jx-yR>u0}Vg&x{eU8S^rbu*363Z
zcTORpnmiI-HVg=te#HHQ!7~l3qp@1h`Cqb6?YU53+d3|5X_Z8QL2tqCGA1aNac9;j
zpJU?=R1GH_8bcuM?VwaJwSCgVfxS&VMzs^|nwPY418?{*LQc+m^T-oa1x|N&`xpnV
zrdfnpciQ}OpwrJ9w?A~KDIsRhfvlDP$}!~*1`ti@X|)>n2?~;*uU%LLh2Yb*KytGw
zs(>DeEnd~cWQ!*zg-Av@l}E&nRSG370h(b5%Adqa)XC4p{3@(w1sK-KzhU?nTZ2^g
zw9-ev#5gT^Fzx)P;4Lgtf<aJsLUw<umS3s}kA)VEE*E7!sY9R%Na0p58-Go*Uly*>
zNcgaw936)7y+(4BYVt<z+WwQ&>(b*X2=I8Ryz&hM({F>Ek`3AHaPBhksulM5fZh_e
z_f`^`mzsk#s~ZZ+r@wsrY?5v)Q{m4rs_K=MG>Q4!iC_3mq1@l42C83N7eIUA783QT
ze=~R%zoNjzGwI@JmxH+itme~cyWc?93!V738wV#6wqz?*Fm3>Yzb^SGD$xP_AZ4S7
zF-~SSMUOtrxpdj!wYv8UXGs^8<bC`ICb9=Kugb!Hrt1ndrUY?7S~T{&q$+L1v)}ow
zL_c55RDiZ5Hv-Jvn5w-Tr+kG*#LW|!C|WI$<T7cDn@%cqw~)|%@E~8X0uHe{ybCW!
zEO4b)4u)Yjg-s)NVh_cI3mUW>zQtP*UTiHJe4Ym|LODpma(=u~?1U4nLxr18ECQ>r
zrLhv52$18HYAMv=5ir;ao}TOBs#`s%9Prg4YL#I#k1-?CB^k!eS~2&>Ymmn)hhQ7Y
zJ-K8k26Aa3;sv0D_jstU<#-wh@tcO1v-+1m&QdDLOpelXl0PUG+S6)aNQ{LediX&x
zbY@*8VdHpcA|x<_qf~p^tzCA!VX+B(3K#*}3gf(cq0BIymOO&vMwis^)WBm_#Peub
zZ}&T#2h)r{JXQ}%m}FW$qZ}+RdXeFmAcuW-<=?!^X@bQi+9fwy;SYf;3jQ^)hj+y?
zIqo-?s@mg5^1M46<^hPbi4&hP$eXY5B49fUJ(#RWi$X0nQ*b`tcU4-YYP%e6<|v#4
zi?KaQ3lz{9;qwC)U>vH>m1n<9irHh+`;niQ=RYXrH!xC%kr-2hgqLes-&bHcD3yS|
z3T1Xy2^f`yp2<o_q85!61<gtH#I7L@cpe|z>(;q5OjMgyjaFvCtd(+eT<7|HsLA45
zgU!VA5=*Tc)(Z&z5|mEKm!rOw%ibWN)8msaHo>SLk%xbK^s6QF+91PW`oKDSneB&v
za+ujP>+Ke)n?197Fx3~O-Eu^pV`8<a(kN+gad?F@=<=_+JKR&smu*Qr30R8b{SN8}
zcpYMP!&NiO@!?|udggI7{yC+J&5~y<B}>j9leSoP6*i7s(N52zwheL`3lDK$_^*A_
z{3pfRn$6l&_?szqSLu7MpomyPzLcD8Zh-d6(z=-P&u80%9VF==hf8fwT#4JBpu-@x
zI(hp#G|g6ikBx=_$Z;moJ=P;dy9XCgP&GsbE4cq<)>GZ%qa1W0s?<#`+<^ReX%a4k
zA1_QWQt2!9QsqA*bts5$4oZbql2Q&0yJ|l<n?U;wsITb5oDFb+Jg2}n|Cir%?W}jj
zis7*#PfLsXdDe@F;?^FDtqYsL^F7EOa6o#1LKL6=M~LIq0&z0J3Ik0-cwtA$4#Kb!
zNQ}&wgh4Q789wE+3;-C7KuyK<exhO+&!r5@@U<jH7zUtvfQgn*G0b9uhEOpOMtCt{
z5y&Npyy9B{kwYLy;KYbd&`iqEfR#6rdDRL}dW6B2yp$C}RCp{Oi^pb{=VQoVvVvi(
zT4T!_qtSI&D+Q)YmI4`J{y+ZU_?-cB<YsJKIWPAKVZta&^+NA_&f<NbW{_^?XAya&
z?c)F2r}HU777teI^?q&%G3{PqmGEtK1nQ;1fn0qke?}jqIkp=04*9aMzwUL?8C*wo
zA|RIN?*2}%2t#O;hfg_75}GKh<``HisA{KAa=g4fQ>arRxhZT{=m=X<h{T?p6pHdk
z@B`O@QHFG@(&Dm{a;iyGc~1nw{;R>6j?m}uh6TO8eN>oFz<Oi<Fhiw;Si#A+)^oVM
zt8&tlt$sYnPw1_(5_ln!LHi!*jo5T-uZl;T%<Lz+F14qQvE`R+(ADxoqD#jlXhWpG
zHqRk_8sOqwnr5G|-+{KbYRvQ=7nxcgN1czD_@{|)Rnc$<IPPEbj+I6|Uw&a|awN|<
zzMrb=rH<+sKP=~)t(tTq(Q`qXk8x0cE`j}&XTQcn{hPy;OZ=Mz%9AOjc8u0C!Bx+-
zd$!8I;d4_U$~xn{Gv!#B{2lHTTVj7bIPO3+bv@sw(XOqx6Kdm#chFPFx8}}YkMz5^
zn0@*aXl<Uef6G<aB~hWdAZl9e=K~>G@~}8t6nas3hQ66eJ;nPbvGj4_uSVH1Cn;OV
zwvjGsZlS_2Cl|Qz2@%OTcV~_pHy?~=*&y0Q1vBEK*nKF6n&ggL?rm=OV#hQGW6ur<
zgebD$Y@{j3FXhxDlda0;_q-29X4nZm&w6^asKv-E+phEZv9kUAHvXI-5#@MJjw#o<
z*mefqOQ6!+><isTTjPHnohUru18MZ)cg+T}*916uox4~uE3r#5M3_b4W#ES;J_QB_
z>xm#2IZh#~Jo43<i}=Nl>Vqm<|A41)jXNjXTTMG72k3%pR}3${%NKYAJ*vD9{H;Ar
zC`eT-tO&#W^c@Zj>+^GMkMoeJA?@8XbW{d|0(K-_NGQ3!7F(C>9TZj&gTSMas7C<C
zFF-RKi^2KzcE9Z8#N&$nNPx4q{V+2IPjbK?bsRu|{Dxig3K9BQh@SRKgt^Eihb#Hj
z5E2`<pvkLkD_A>=|4U}umcn(VO$cdcKigB<m}uvbH@+HbGr}MhL@c(hQ$KYcr)9tZ
z&8vZaL?c;!a_2axtgB|UbV9VLO#CF(n<<SmPdBEf)^ocpu{%i&rtWmXCNRgkEjQv8
zcFbY$2;-@n`)|Or(r+3Q<6Y(_;xCCdL%7M=P#<?dIHJ2|ZrFt6oV-REU-^RFhXGEx
zC)BxE6wB7fA^PD1>eN)&Yj&yAC2@Eno|f{5O<`?rdP1xhFE}{~6nHokZGpbTb(@3W
z&>`V>y1k`Y@QFtQp{w}c2E;GEHr^-l{GU%*-p$79(wGvww5S+pPRwcnemlyp$&5n{
zVzXK0`0OiN+lBBzK?$P@uSCmZTa)Uu!>$^8r0w0d%l4jRqe|h&7l(7A0s)zaVBrPL
z^e^FBVh#o>p}$hIJ)WwUSQVrwH5F{XaSH2XF)l0pBK|qc;7%Y5y`fP%CV$zA+U90H
zo=fP+I)&iWPd|6z8(D9C5xmi7!+&D2iz1H*4^yWKmv&d$^Gr%*>CEC3W6_$r(}P1*
zh#>cMS4mg5Ki*;u#IzJyHJ-NSI%Ev|wo0EfJ=dF?@RcG^cZZ7ZZ=hqQF73X$2TT5U
z{jm4)S1UeS(rD$#T(Y_^ND_(20E8WFnVzQHjN!M|XVU;Zkus*A_`i29sBaWb5rC)E
zUEK#m-@K5(#@O1od@f8bHZici+;@|;XB8$cM|u_A*eT~@enK@K#PX*c4_3)an)j~<
z_39*(LeAx<P1U<Rl;*vfGw`xfeBcUooNCip0}2lo-fF}Q^eSez;F?OB(k$iTUWg8k
z2+3?H*6x=0WQp|j3g@VKbANZPv{=X8e=uTrk2QR#xV&}&E?Odue6_Tef0H)t4Mc6o
z<*6R)FAD<w?iY1xC<>U1o4=+MK&3|2rv}tE2&6?aDp;e^r*1CjD$c0`mK*Ndnxun+
z2otZX$*oNZ1N+Hf1+1QI4a$7qYI1(GtMd)*nGITP;w=}bfS;SbPy0UeCwXmKHgRZ=
zj?PS>9m99%ZKbaW&=zgj76W0*66ABi<H|~=iAY!j^hOPCBUOW)c@PX*2~Ypl+BHpS
zr{X2lbA}eM^^dI&J=b-1IMTR3$JPHmxVN6y5(DU!a`3WlWJ)15;#cioqH<t4raJhl
z)2cG>(<V2c^3Ea(wg*nKv0M9T&}**v&iZ)#g+E)QZ*=fm+}Yv)kzr6m^L@6(FdUVP
ziKk3a1F{D%&z$=pEZT-@JT02Q2je%=9R`iGsSgfzFPBKS-%8KUa0d<Pf$#+D7z<|k
z^h4#}S0{pWdy_8g(K?vBHKu)#&W&`->^tHTmVE@pxE<gVYFI|x#4iKa)hl-|+||_5
zo-w^PkSwqF?7;34_GvpRi)7q3;rNiE&xI>zLk{Ih%BRzug4;s%_MVE@I;9EIj;5h+
zMr_LF9qE$^FrOu60&RPDM3j>L#%UeXwOKPyB~OZHF3@#%(@u0thg@Qy+X2KWJFpbl
z5}P}_QG6y{-afwzlU(bvcDu-gk2*>qdD(LBZ0>9uPp4hT1TUN69|$%;_!OPlD;2YF
zbgi%D`vWM-4sNiF|7LmxD}5ZG`g%n6R0~3u>P_B-7dY5R?p5tPf6R8ZEY%><Id81g
zKZ#l=ohB?FUU4#?v|55(D(HGt=;A^yR~gqFXdG~ejrczJq-EW@T5YP+f(C}ya>ytW
zB;cTzaCwAn?OB&>PNtXrkOY>V{^dScu!D3k|Gg^rKYelK<P1=|YS*@NMfcC<iE;WI
zzZ%*k1%vVeokNdD*MP*BwN}{A+ACT$*d50c;>F9J$|?2^Xlre&N3zJA4|rZ;qfWGE
zYbW;G6f9{t%upRT(!y%ILm~Zkzp%dO?Oi}I+a&vo$=j-;6<zC68vz#!A-NdSxH@+V
z4HCmrQi$n@4Qr^t?8|EG;qbrzZFhO)v3Xwhjo&I;jt!m5b%UbC&`oTsTH)ld#&l1C
z#!!4^inAM1Nj2D-ZWzZyjCpoDcMx^nQxPN)IiJR#fZ&-H%-GQx{Pu#kX3GWvwY9wX
zjbAFMmfKEK3c&G37M|W$#>Z|IdaCUv4)P_Hhkug#E?AuafF)bmvjS@ItmAp|!r{HR
z^K&bb*9qYUjdXdDVdm&n6OFMLORtnJHJT|G@RR<vzQpS%JU5aK+Jv2RCXI#v765(G
zi0T0lzJ8J6o+;FS)Pcd`Zn=S4TwVWIVsX?HM2$%W#~AaCz8NM_$q5Goz|*rXzxL$h
zIEPYZxlcXaf&umSN>{!j+^-ZF(iqPqSSBfhdng0R?j*><<LhASg9c+0?uId^<bdw+
zrfF^!b*jBLlCWObtdmO1#APrm6>BZA4BW<=JvN!*$@_E>Sg9gf>J;BYhf9`JDvaoT
zN*>@iR&LjQ39LjwG{K$adM?ZvZ#VEB$`56(Kg9cL6YoNO4$A5J2A$Et4m>rwOsSXW
zrsx$>eW`I|6afzg(~1ZQv{5HT)A6LqR?1@SqrF#I+(^|&`f4EO1W#mrzi(my$GcO*
z0bCz31d7FyeDuMedwV+WHsy7ln$Ac`(X~{=cc$*Xu>_e4WY7``!*DXIWGzTM&ZlOu
z(Gl>E*@|!_&Gap1ig~ntK<21w&moH)c%;A`Xj|R`!^!9;RwF*B%-b}x{fW7k(=6g#
zp)T_yQ&bPaD56iRwefkF>j(|xhB0yk(u=m4_%$x0@Mjsa4Gt60?7~urQuEATq1!B6
zrqKPkJt)<F_(swe&HP<qj(Kg>2E`wuiJ5v2m{vuVjieH&5P`+T#v&qTChQVA2U=`n
zGVqB8I6Z_-t}iT3QNz+ecO?kI1fHBk6F2&KirsChbHz0fl{lY!?IM7RRpEwzVBBUf
z0zVNd#k<ZFg~G=<nQxU`OXKt$*Mg1<709Ee$qmUw&ntGkP}YT2O40){FhYmJ)J&!g
z7FdDRU08pZkgvTg67LL6K8Lyv1#5h5Jli01!n&O7TM9<lv&t)v)esF)k+3mlY0b~m
zCoOc%m2?b(CzbG2^A$WZ+Pm3Pwq$PYdbB{}WUkmTq<+acJUc=BGG|9(OKZ<_-A1R(
zBuhba8Qtd6R0UO72?>`c&Q_o<CNdPnRMQFfy%>~+l!n<o-dy44lypF7#`9f-q;_f;
zY?jeiZ`iZSBu9&?#)|c~3?ZD)B~XVmf|BE0(b<A`@mj0w0x&2aHN?Xt#?4Hp-88Je
z47naq-1m01QeW}Psb9!3NDv5EZSzTpx!D4y{oOJ%&hXhh91vMETYW$~eBTq-H*=7w
zq0UlP)RXQt2p_vKiXCllP6wSSibWb|Z>A|chv4G`RW$&HPRSOVfQh8hV@&*HUUi1^
zX6{mqi0EX)%%3MNnAbpQ>H*DPQ0EjYY_<MJxX&VZZYZXedds>{wbN^4HD+STeK;dz
zf!g#^lPev`GrmLHopZCgdcS}xqnkEqB5(ACb#!N!MPlmSnCIFp50P~-VQ^h@SI!qV
zS%Z!tPB864!wu2D0-lIT7X;(@pPQ+~4kd|U=LxGyeFTZ6PS)GoAve=RwGKaAd`{Y2
zc+s^)!f~YS4n?wogla!prcE{{at~o_+q9y<?gq1TCKNtJGOFZqss>$KEbc#_Yj34a
z=4d7+pTNBB<Cf;)jCf5G^CqitPz6_P{Zwcy28+`8(5+SQ197~^r$UyR*3MQSCS4hY
z0U63+9k8;^C~3T?ns^V`m&M<yRPpTkhi_vbu6+9%dzi@T-|KAG?LdWtK!G!w*7ypu
z1a)m8J@<x56^FMKe(R^GreMHmn7(SEWeFsGtz^|YXFD?Q*`+Ge0_cTo`-Ow{vd;r5
z0KJZ~fH;$R{>b^I<wspXA>H(=SNtjCd2|~xxBMLJp!G*`V{%K$JtH%Ye+5DY4DOY8
zr=M|RsB~m!Ibn<Tw)y8M&1l<aLol6vh(9jq0hX^R5znYbrh2>rwAVW$R=9G@pZGg*
zm){QcAS4dVQ0LM0kgYjE5c)>oQRJmDjX*>(mg&K&Kk&?cZJ$|hj(sTzaX~WIG;=&g
zR@mTHw=mURJ=~Exrv3)mgSt$ts`%P!4G<3_w)mDV-#QWHZT9EIbfIWyo`0+O%k+gE
z{KL;fDrg5K1l$NXvwpP&8M-W&adhhR#Hsp}0ZobeT1G8OzS5+5>Cv0JT?aMh=a(pT
zw0UzOXLVIF1NNzV1$G`GI<i81=i-Ea1JR74GF~gLXHq7jBt`xSHN3i=tl}k$EC;bQ
z;=f6scd}r;v@GUpu)DAy@y}e;_K_vEKgG7nw%rTh<hd{CPnof|C{vPLXh<7d{vdlW
zQX{LA+VJX8W(^e#f0)~2VZY?RcV?he@@{+Pn(I!@6(g+xOxMXDU%gS^eEivEDKg&B
z=lar@bBc3FUSno!BNFF%V>WJeTRU&IkamU*{~(94#}#3s9y>s3`qxLmf#X~DG)?#l
zuzN^J04~zbd82L(m|lWIhH<)-?{)9-3+}eg&Dfu1y_0Y5f(oId!y?k#_9qb%=n<-(
zf7gwXUMy(_jWlM|hA}^hw~uT%^f09L?iDI`T!q~S3)bGB2h8}r$z=+E4>6sP^9az_
z5lUM?S0@UR%^P_}ra*I}my}w*aO8m!6yi$T=4ex*%(H(0%Bt<P&zo60`2{p+LUBEy
zEk%SYxW3QW@*xVl&e=93j6woTF%JS9^<#d$P5vGvYf(L3t&E0_HPs??l&m=#(B9qA
zuOA2b-WJ5&1NC<I6PvRs9l8jPe!DDWSn^_tHtv3}OU#RwgQYaOG-AQG;u!^Xr0#7A
zR;En}Jd_Vg!o02%*7|i0lZ<9W&#M`55V_MY)MKu7bHs{MXOFf@TXiK{qe)V<&zy%?
zs+cL{If#l2HmIoD7GI%Vu)4O3SXu?9v)XlEFm~m%<(iL`>FXy5KjY(4h}DgI`=`VO
z4gZEGk%V?Gtamrcy}$AEuBa{jo~q;RD(rSIntt|qj9`R$)jRM_(mFXg7q0e;idJ;d
zlz~1N3Ddh?VL_*ju9jKS2A=1}0j^1>P3^`OR%nZd#4ap+cXb!)-n7!30mWyI-5ODh
zJDkKQ(`4dK%%3elzZTzraW922kua7;SxH4vWY(3LoMVkm`cTO444PjW_Rbm|u*!3(
zaCdxutm3b8+n|?&p*R#>Ma`>DTq)GzmU(9$2C+Til0^V0FcG^M1&}Wui6J4VMcR4t
z3BP4KX{gd?y@?xn7e2mxJ}__r|GC=B|7id1@LJJO<wD<)!d<v}Q#0lW`a<Z8+C5qE
zUc)53%=-ztU<R3k>Cw4K(Oywh0+#7Q+3BsqfirDuB%z$57<okZ!_~E#PT4fZ=LWu^
zVz*F|N$V2_rGpPTEi-MF*C8N@=Nx28{r0A`(`Zc!_vxp41-c=IaK^i`@A3JKOXN!n
zdM%Pks^+;-pppH=Y{7L|gu%_}r8uK$;#=$n50>Anz6F$XC;M51L+SerKT$0Yl~o$^
z1C(Mi__J0Ew-8`W4L45A8^L?>e5o>P&9!HlGyGVEIR)BI0H!9+K>>Dp-9OsfOqXYX
z?NR;*D=Oo5xI*M6i?;uZ=EOntYzww;UU9C-Oe2<QDJmkbo3|Sn=t~9pZ#kS1wmbQm
z`0LNf1YcRN%L*Dq2MDJox$E-0ja4afWFsExIJ=C_%%(3q@-4*C_1h}jg-n|{SN|vq
z7VV9LJEmCO`3tm(QFH1L*K(Zi+q=8_y;f>N<0vmu|L09tWX_t;Rp#3Q<ifw&H3K>J
zESM$B7>W)%Y1oi__Dz*8b3^0N{Y)+lMUnNIi|FjMLCD}X^I;34;HlSDWnpSQv!H6L
z8F+Aeg3hkDgR0Ap&kcHNZ9-92^2i>8R3yjHm3rl_UNu{v2mjotGj)ea6v)79Mb>0|
zdm^ea#CTth>KWRK@l+RG;YvNEPK{<#!{kl;Eyk=w^NmM^h9(JJs9BXQX{a3TyYOPZ
z?*Yh9%zmCcR9I3()cd`<{9Jhjgh)IN2x9$OcMh_9nHA@WAv)JbpGXB$C?&XSVQ-ek
zTEJd0{d;L>L9$B*2$QHRepiR?iQSj7g~T(4M;S$v+R*$&UzdA;vSiD#FZOWSO5d#D
zB!<`8zR}D;!7S=iqXDOnVEZIW@(Y7;03nN=4Q<1qySad0oldZ_exaRHX*23?N~J#%
zv6~yqUadGqxqk<V8;csPX*0GJ8Pc`PrTe6g^QtJSz>Xt1304)_O)(N&?=12iVvJb3
z4wosMn7j-AV@xk1p(yZkzlZPZw%B(uwz1ER1j?Qn*74)_J9m(YAja8-oRmsqf!~EX
z=T7F$0ST*dp4~}OLe&9J)Wyv?;`vM1nN{ht#4ir9-)TB5l5)U|9{OaKt%ol*Cv9aK
zT<d3!wWP!fO=ZV5pH2}$@%PDq43vfNu0gyC524F*wK03AQ&H_tV!4%&Q6)r!gF-AA
z)Q2l(8`|j9PviYf%o?%zKg5SJD})AN<%_EoZ$>@m>Y$?|@7xY&-ML2kjTCfRvTSm0
zmFlgDDL%-^=c-I2?MF8Gym92YqAgt5c8WI?VkF7##~aa3JVB;8CwQ*2@L8Qc!$a(x
zC)vpC-`Uxx!}c#kc-I+uo|jsjaOaN|?@U~?M0n9(C=>Z4=i5b-9Ewq3`m6qf86R5L
zBt#LU?heF!x`ddTgkG#S;{Q^&V#3hkTKn#Pqkt*8bP8NakpS~1IjAYVYT41JjH-|w
zlxu31eCbaV%|ewN@qAgKISKIO8b8!LolgE&Sq@+CvE`oF=dKNVAFlbe&-w|FL8eQE
zN12tQMp6jipSza*M25~td$$Y1kZ)()uZI0q>4sc&nv^kSlEm1Bp&dTT?pGOp|BsOz
zBS3>o;RW!?<M+Py^+BzPTGN=d&k#^jZ?$o0Xf`3{H`s5Wv$p?fWo86Fo$8a&sH<P+
zh^w!Mm6k5I6#fW~VQW$W6Ix;tfLf@Ij+2?*%pQM|%_CcrlXy5{Hef8v$eA|{X?g+W
zzRuoAv257N5pFiXEHMyX4@>}=85RT+jEK#M*`gtB3bCa*#&w%^V)mwk9!)iaPHb7)
z@F(yG&DlA~(!;gv_2bZ%J}=lLOPNLO@38UqesSkV&D>Um7z_|B!bARa|J-^Px`r0i
zSUz2btCWF-e3C^LdzqCB-eA?nlXQzc>tHv4s;;E8$b-pqWJ9JwwNuB3R70M=%9!7g
zZ*4BB=S-gzF~)cjm%-O>6z$7@fnv3PHJ|uq(xXoKvbA-a*Zy)Qw{?FL46?iDJM%48
zB)|(?&-tsSmA%B=0c(O0kp3UcMWcEbDOe{7ahFA#y$bn2;n@hM?m7ELA8SKQXfyz$
z3;aiJ-c47%-wo$WLWY<=UqWKaj8(f}pf}!cBe%UbE#t&1pAS?^rKI96D`*=+-&=S6
zjiIPFU%$YQ-va-#j$rcVVbhsJW`OG8Z`WSYN5me(`ISGfjAa$Jl0Id4o=S|c5-8$r
z8ul<{yx+5Hpm!0m8q9VWHlmZ{H6V-<lcy{UarrD8yv8S3Wf0P*Y%mNRQ3XU%5|K$n
zs}O+$0OP_a#uNaQW`rSoT^z46;(}g|E}?k1>SFjYPvxx&BEd4^N=_u+BP6%VB0v_k
zfE7NgeJdp&9d!bV(P#nJ|4cJ7D2%0H|6hL<Hnm0<nB2yS-6hTq%;&^JV(7N#J!}n`
ztoOz@Gvl;ebBu6G{|`A14ouHvUkpDUv_=^33f-GdCY-2e19xjl8gdEhswN#7FT}M(
zNVN1NgPsH7owkZ@xMo%N&mIGVE$CNhz07;tDvvCT^$T%VRi0s_QKc0Qe=Iebt93=a
zcWY0%g;-IIZ9c5-vuW~+Ez2)@IVx+@7vQk+1VP%4C~q6Z?g(RekwxtQsa>dU<FnBc
zCX_k)t`+t@HoJ*fohc>ugB;FG=Er9K2eY3phd}L>rLDYwny1Kw-liYC#M^fmoSkTv
zd0ju-Z_-mNtp?3@?QVliL&orzZM%U>{JD7fjZ-@!ByM*IwP(Lw5|?yzc80BJE=@X0
z?$p2Dqe)nIWhmaaU~whS)oSUj@QTVCbv<zWI^3>R<|l5Egv@FuU0rRC7ik*_U#;o;
z-p|{(+|tJQX8o(f9v6R_fGm8SrzeD~l4PdteFY^1%_k1~nzb`dB~T2k<}JvSbnpnI
z6Yf4&b)*KhL~-V)CnR}(b?3pR?l$opb^g~q+tZvwK<OQ$sXg<B{&udWax1>H81mAI
zc;v3g0OX5l=Pz>Y!m>gzd{FJb<1h2H`eS%xs4Xf;WMPQIGD=O_8yIWB3hSfBW!$+$
zP2obEmo=y636*vZ5z%+uAuLCtBSM2qKRgX6Zxig-dwe%}XZ=Z>`$om_if$WiZwX`e
zZ%@Ke>B%=-e9WRd%2Y>p!mENEL(5dwdvqK{(If%^#;ynLC%c??kpaVBEjqf|dty_&
z-plo^4%8_e?lyS!TAK=T8u*{d9Y@<me)HRTezEmAFU%wYz7JgaGIDsoy~QAV`_f+Y
z3kWDpc^ht#rG*MBvXy)9c0X0?$tNaPUn6*${wqP|tCQO%JE-3rC7<e%m>51rtea$;
zwxTl($>ELny682O5-*ETyllcDWy?$Hp7?W6-4ixqThF(0r7llt2Ec;zkVC#e=h{eA
z+?Q8t2MFov!^5ZtBu{8`?}W=hG<YWe;9V22{@NDGDe<}ADhwoPtW#L%NnLpLt?RMA
zog{5Uxtv26(6I-8KVR{Es;sy{NU+Z6ItMm2c8dW<lX6^Xi5R{er7-VS6suQJD;4#}
z=978j-H>jeMcarv&l-MzXEjru3EUHP5!1_UgDot4+$fK-o|!yh@IoT4ZI70-G-ZAW
zQd7a)5)-Qi-CdhIShS%f0BuX?^SHL`$VXH#XIdyQmr5h#2m0cJo6!1&oJbZcdJ!45
zJPQGVBJJ&&7=l*qag~Ofs^nAk6EfGw=+3)mYsoG%amV5wZi4g`V@HYIU0jxaWl6f1
zO^?)_k2|(Q2kXy1)9|&3lB4bb>o!E{U2B8G%_1_FrJA@~$|ROTuePSye`Y5_MgAI`
z9$Y5v%fv*^<U~hn4Hb^GdT)zAlZ7mPSF(H-Nru{3GK3_X$(*L6#zKv(v+lopLW%dv
zc3X_BnEQI~GYwot=Q>-`UpjgVcll%QW5SRC`rj_2v}a|YA;>5r$Li$FM4JW^Q!U9d
zGV2-)R7`aQKgp9!z|te!r~Rx>o=X)?Y|Wbi3CqNp*^Uot+uz0WSB%5w0W+VCxC?ls
zXPTR~bLRosVBVTB_fZprcuvQ$nFB^Cq*|zca<pR!J)0|M;$7C$)wS!|B$%0AI^skF
z3G7rJcKNYb1?BZ}kDpjox~YBxaML;;^XrC>Q@8FXttpNdamD(0nWUOU6`zBGA=&A^
zHBu}^JuXy-ullmWL1)<|KkIFxbxtbKseNfS!G7O=IyG*5iI}2v+Y;AVQ}O5_bJ-R{
zw-OZW#WOsN*p1r$MMN5SlH2=3O2KxUQxKx~Wy7h3=r_RYxq>~?x(5DL+YQ>9@ning
zMbo68fz({Zal5cfib>X<;|dMdh|jZ9@>p|JmtPHnl)FdDUH1ZYI5>ppGxqYIEAdR8
zW>v$QI5aJhaYdaZXiOsu#Rmo!%|?rzkA0A2ASOmXU8&!1jtfV0|FMz=hRGlkuD?6V
znrY~L6|5vMitOlg+aBZM>qQ(+dfIT5z*6fkZI7DEkEa@=6rwab^|pXdppAw3`?Ee>
zqnTT2=t#e7=o<VSVp5pV@x1(N{$xw#cJker2<YQC4oH&2t~@CI=OA6CE?rn<RTcF0
zjx7h4Ptg$1y%+ucb=|QdNNN4L?SaQQzDt-`lT#k-2i!$`@wwX~doWFo{-EZF;hn$w
z^$5A>erauQedPOvl9v9Qi}6{V$n4jJR{UGAmZHld6jMAUezR|=t>_81cjWcCtuLcX
zaBkbvqb~`{?#Wo!9Bxt=ZBiF~P+#KXxT?GJJj%t-cBB$K<lVm3`npTevGhc4#$sw|
zXwjK|gp<7Q8t^>JG8~{E)hBi&FY1fcYzby0KF!w;yCe+oep=t;{afBi%ERg;xO2hM
z)w<|i;QI3*nEU$GdGWXejm+Ac=u(M$X|&ueU@_`xdL2lYs1ga$PF-);RQB!8rRt2F
zW@#eD^9C#bM*AC~mLPVW?Tu3OVt<!{5a>D-ih8!mUqt?IyW@UW$=AgxXkaC)zK(1@
z2AWPl(vafvgc`?s8e)~)fYj9}c*hZQ-N)B3U%4#-!g_CkO<3Q^-aN^xGHjn6T~Wk&
zW-}KIl3E#0d{?WfFnn32Ohv&^MaLM=N$spIN8jv?`@sFXCPL%omBozc^GN`6m~V92
z*&kuqNZF2io9SmVG@eceI9?XSeQOf~^xBHE?bI(ItFfa>c45iAOOA0B<p8(${h5Sk
z5A|(sLDyL13)UWfP1`nVTX6nT9?NAq)X!pmM;ZQZQRe!CP!CkO_<&XznyH&^gz{(m
zfmAtL&W48S5B`b+C&A`?=AZgR_A%Zb8@-2;Ian7A5q(wCa*PT>6ik}6zCIa~?P_#G
zR<IVK4~i82>1)2*bim@bD48*q=2eab11|M!U*dVCy(7y95m$y~-fFqc*j#FC&P_G3
zi#3mlJmQ>N7}K#@x!=C|{{R=$bbU3VIJ_Pl%ojYS@xiLTaRtF}QjC~nsRU;&UyS15
zCZ@Xa>%f0&|AW!#An0@-d=pk8gx4bq;Z`*{=;7he@);74$f+9TuKVUyJ8}etGBf96
zWWs0D<;(fHz-=sK=lzK1GnFjxNu39Pskrz#^^z2tc+30j6$ZB}bLk#>PCjY8^4Y!2
z45z6v4M`8;6HzBAlqP~vHJa&dR=z9J2#~I)KGqy}1C?X$#rGMUEhcGk7)5-PA-j?6
zcvxy;wH39v9J^9pxItweff$*x8Tc0xC`)at?<Gg`GuC&h`B0}^h0}J^_rMIJ3`jAN
zEvqLmji_u_AO%TfW$7yAz57$%abmyw*K&Tfwc4_qnrFNZSd*uDBcNao8XPb)2}!(w
zg(aMIIcJ{?_py|8B-4iiLy%UN`-+fsz~qsSLg8GGds;!p8Q{p=G(mH&>0&zu`28!Y
zy|Hj&3C-@fboh(>J+V45bmw7cQhpn)o}E-smzt)@wUZyQ)L?&ow=KRjDkpCCtENu1
z-3v*FIOhmET;a8iA0=o~@Uec<=-yBvQM&p{ReJ4O{Z$fe_g@{+&wnK*(SJTj4`yh%
zI{Pitb1?zS-3rUgpt)3Wr$0{(wLWK`LHOKB>Pi_y@@5&+mb#wDtsE-hTIJCvnk3y?
zf!M0OpR<0eK?SyR-+~d00u?Mwn&2NNFBS33t&i_LFLl{n(PC~O@Q0w$2Yv+Gl&qmo
zIwT$<l_<?fE7}oMf($@i#(+l%us7^ZbmVA2zNFf=o6hH+qzbq(v9AeDY&I?sJGAJJ
z5sN}D=8oMSU&}9ZK&mh%FoeTke50ZF*gI%DkzvX9kW&k3yDhFcC^&vtSnZWU$|-f>
zdC_!7EOLf#`FIm?AFp&Y^%;2+gcHTq?oaE1L!6iWRFXAyAiMb~^tbNUB;}#B7hJM3
zuL&qJ>J$H89d5hgN>tKZov{zI(8$77pS2}-%1qw6`8%eXv@Uu(1*?0VMvOob1wC8h
zI8;hN=40;)8*P0efgj6St95UIqQUf7t$Y3<A4sM2u|=f}hkkgA59!yM`j1&VvC-)c
z!`$wRvGVW!WiFn{GOCp{A#0nzG_XI}tpIaDSn8w-kLQM)L1Pa5{Mzm>P)_f!a;$9s
zA232S?UPK?>>&pc$wrMQGD6IY5UM}t+Fx}$@s9#m<znMd;eJ9??Gf5qB|~J!`-L(F
zQ67?wq8R)Zyd;bYh0;8~4^q6;s_0SujyPlfhGTF${=;Yi+lbYF(n`01p|dmDW6XF#
zE5%?Egvl(2RApo#>8@wj_Yn7Q$!cA6HTd1D24?fq!)}?v!sG-|4bcr`sgxDpUE5=s
zUfe`AV{+U=kIl}o0_8S|MZ|sQQo+`*z!Z6VAd_8y`BaW3CAAYK5ZLJZ)}`EXlyuNa
zYTTd3!E&r6$d&}a=AD1uNeVcr`nBQ9K-stNIS-iV$2Fb_8e!?W)33<fBh7e#=(4jP
z_iD6Y6wDi)m)6tDlWqGTRw*93&`SI5*A}8Pfl1(GuC5Qg>^xq937Zp3r7pu<HyWF}
zVy!kIHWEXCt=;lLA=Uc6Lq3c%>DjUi{+j+02i!F-P`b*SQ$U9HX5$Tw(57SeB0Dr!
z_1_FW@#Kv%emV8ctOtJh<4L!po_l-`0!>5P+Hu#?8cUu}l62ogp<@vVdG;1<zTy|V
zIgLW*M{QW5OU)@6%na!L`PS5bXG{8J%!18oE3sBs$C=kTjoZ!tAXjWK&XcD$VjDEo
zb%&nVirpI`r(jgARU_ua0{Xofhx35TE^>&U+~}99HPhZY21$z4)A?Y1u-<0#L=DI%
zndr%4sdAu>|MpE>+OJU=Gor1#62Z_Vaimh7#{IF1UZ%Y6Clb{PqG+Mu<m=juFrYn0
z^!iF&#`Hc7*wg?xCrJ=s|6;j6cqn%1FxV*p_1{i5urCpVZ%Wd{4ag{~0+!ai2|RJw
z{pQpG54HOl71tTL11=VmR0+?cfb;cfiX~+0=aa5p(v2PIY5L)XbW?a1T*iAB*grca
zOO@v$#VXAQU{uvL=aHrf9Nm`)Sd*;yQhEH#ab{%xLL%U$>WG{4+m0Hc;Ji_ztFLR~
zS#xXV9FHk)-AV?lR`aCe8inqLeewOulX%-dnqk$N6zhyJiC<)Eg=N)>zHi-M5(UVM
zpTGr_D!pwnvkvlE{zHEnK<#uSMq&z?4XhOSZJizWkmeuVA%H)rWqJ71^t9JHy5+QF
zxjZ*|TES%{e0%eRy4TYxjecLEltppG#p=>l(uk{A@roZC))a$AnJ>1~iR;OgWgjYV
zj5`hjN}x)_bxeJb(KV(v+;JRdze8P3q-ipNdb_=1$u9GaCElyM;e&CQQrAliIm<#~
z_K58-=@U=h(SftaSzZ-gz?QM>JlR3(NqEFw3W8I<*$~?~Xy-b&dfeBs(<2o1k#A%E
zV5=Zx3D=V$la;~k{_n8<r{=3~$V6aeLuxr98?->sFWuusv?o*!3diZn7uy2?8&Vn0
zlfGdiTvJEf?Me3Y?f0v|m1p7h*>V7Nst={o{F`FhVNg}{r777uYJqyBD6;#(SXXFU
z8#U*r_x|9Es(4Wb?|qTuj;{0|mu^L_^|f9J1iwSs+no%(t2FFZ*1tD81GIlz)$eTD
z>wRR<ab29p^8+-+Wox%Fe*b(0AODDOHaplSiWR^Kcx<Fz^NwD<IqmiNwv?Ya4~M^U
zUdXbzf4gbW6LN<;O||}ixI2r0HomZ5L!rgpy-0D2J3&fucL-8kf)k)fDb@l_L$Kmj
zN^k<jo#O6<;8L`B@uL5mZ+ka)eZR#lW;SOvXWlvQ`+FWNO8wuxW0ZSxsM_SLT8@%e
zhh6Ge(OSemoO3vFO}GBS+dpXoDV_HI_3Km5EXhbEit=7k#r}lQ9Wmq12QauQF9(Ia
z-Y^}^ASTk=(u>mycY4gH`nBj)mrP){)m;_(d-qq>M9RL5hrW~!oX(O#RRP$0HXnQC
zDQXdVf67hJxbkG_;_1m(x=6ee54Oy<nEg2JvvXFz_r3`HQ<*2zn&KtdWT(4YPgY=R
z>7o0JhL5&Q7`B3H5AO5ZfAwPNyO{Wl)MHL8a)j={Mz}g?l9xL=)-E=BEKlG*;BE=G
zE^<6g2-*55ejwvjShU;#9~BtWOGvy{*ftaNj~O&>sU!C~w|ul^Qrb3Suk4p+98%{v
z*_vNNAX}{Z0<}}rv(x|ZHGE>7oxfpighjRA>m{Wf@l4?T;hXVKHTx_Y-Rxh<QC-Nn
z%e%@c8dV7R6Pl4qFtmZGdq$ld)Aw3U>ad?P-=+AmmgLw%Z*c%C(y9WFhL2L^`j67B
z#)fmPIFa1~)#onxhW)jde<!0AegZdpwg=gY|2m|k+|I`~y?!7S@wM#5q4&Cvy9&eU
z|HzoH4C~p_yQr4y_-rDgN7ego|9p9k2{nmrD14q8`*$uM^PL;e^yf_o?DxPz7ai49
z(5P{OaYtkF#FFdr*8RjjtYO+_MDmRq6Qv;I7SH*-64`SjTE@UqQb*&nE%qt16hqIS
z{M`&I+BKY*06aM}osxep`d_|U4to^cbxJbMi^O+7HLSTZ^VZLbH6JfgyO<1Yt+oD4
zWepFGOb^)53AuK7DXf(!@3dhiTj~ac#e=usaixVa7hY8BM{hFvC^|qEMPxqAC6sCf
zY-URG2E#f?efTVTK6MhAPY?YG(Jex(@>(npv%#u*32x_`gB+ARsryv7(-egFIt>0o
z-T@T_syqxaBA$Ef1qA$Pv(qt({~=!5QrLl2q#~C<>6FZwnDCnk1fe!Gm9SOpn$QXM
z>eyNZuHCs?zI*l7OLc2P#UF@#VnuCa^^9~M&BYK-{Ci3rU;OZ@#b+|ST%;{0iAJHU
zybdxo0?cUq$UY|y@Ed>a&4I@sX~iB`ZD%ep({EA}B|Lm+^*NzuoOfbZdg=T?O}W_*
zM;tsrZ*p_Z@yos?Wt$-aXLrN&%jzpX!<ssW-;bQ*SwRQ~as^X|tckN%m-JrQJ_lzN
zN3x1r@^f1Xf0GYgD~s>61=p<RPD#}7cH60+%rYr<2%ylc;kGQrOFg{hqnW<imlm|!
zXX9RE9X`B#jxg>tsTia_4ysZWz6-BoJ_lsd?pwg5b{iXBbptA>ZoNl}mH8wvi<vPw
zHY-3`xmB51awn8`=-EP<e2Ac+Gau+f>DdC<z*gq)IB-ypMXoy=z?a^B2H3ej{uE5+
zf|l6!n)~?Ox|~>MrH|nkW}#t}ucZsu`itHtrld5_Mqm|`&ef8f7vbdbsn~L2n|4NW
ziobfOAdx;byZj>8p~^B+|AqgGC`vsLR;j?-Tle|6frccRp#?ES?76l5xP*8gaj?*h
zFd~cGyrrv**iVAqo3YUL2!<p4p9EU*oQrDBZp|1<*42EzJHDvgHk4r^-8g0hXIZNR
zPOJl+Q_olY2XuhQ9~`kO&+g~t(u&yG3nrCpVmAmx(msZkF{H~qx<@QI+D5p5F??;>
zzV}}1kc;ywVL^Nphl_1*o}<r@@`^JP6k>RT^fG0W4z)@-?e9!K<@9pW(lgA@z<nb^
z&K72AqdItLar>Ctk*~vu<dSuH(JAJ`tQcYQjeufVJMdb@9_8+R-j5<ERM^WcSpu(n
zs6_BAuymV6=n^ixS0qd#R#+lti=W7GM^Blj0CWY2@PHNjk9BQmKN`=tDSO)Lv5On5
zWHJc*eS69=*56>gDf>5x2xJ$|B@$HR=_3sPOiMc`*5$-|b*j5~!2L=;ccO45OHokQ
zZR5;%8(GOF6*`3TKwKdicbW0U$lpBSgjGy9`_7Uovjt({OufAA&~tfH6{><{Yisq)
zvo(6qZ3B@og2qeSbcYoENH{J_o!G~p*xgm{fn;CQVM0C_C+?q3E-YQ2{2$+3YpjnY
zEoOFlY$kV$NH(4M!$sd<FH%oQKSN{jQq@N1X-hC%F`w;~7N|*;I55{&C^8Agl1y~e
zSTk<ja4>?cnqn<I5P8S_0bp{6N|)xOi4{U!)u21$=isb5e_@_Mz(GwnAXxl49!&K)
zEshuqg7@;~yCa7EJ1f&1oi-NDaXF2DD5yd}(Du9u09tIRG$3qv%*ZlR_{n!tGgIVa
zOoJ#5qwi8q*{|iSkil-TGcwSZiDk+ks+vD?qdBfh8TV2yD_#p>Jn+_SC*`FMODvX8
zIXn~9UR^Gd0&6FFQfAF;5zf*ki$X+HWNXSHtz-nDMwol-l!$Kl9eswEFbCk^#UBw+
zFsADTEHzcE5|NV(Ad-Hm^0;_6YxT2O@g51z6E%`tW&Q?;u-_{v!_o9QN*UbJ#oj8}
zH;f2W;pFkn!i5iTVKrdSY+W8|43G0gFntf5PL;dR%2VMonu&P5zi_X?TqtK|7z@Hg
zwS-CSdTmi5Uuz1USB-?y4FyUMf7h2Uj?w|C)4OPX1V6fwD2=nmlSE<c!iVuvw6R^X
zOg#r_4^_HcIcl7bz}f_z+Ie~3_M~NL&PoO%&CtBeZ(!JSDPN5&8^s5=IGk#bgX3)1
z9&`OXW9SqX4xb*5IPFuzOR4WT;hOFg5Sw85u_A7XT*y>!gR0)R9v7CFgwW(jSc`a1
z&}<(Yt~Sp;6gD^YFV-wU>*sqHOvvLp@GQ(-Kl#LOV%tTUu8dCgV1Fl_0XBVzDxS5w
z*BK%d>EM&{2}SM2OaTr`j8Ij)n`tqhkD~@LdOqZegv?8WS<*R0A(uM3NCqz>#%L>v
z3cN41(sYN0-E@o6Xm8E*0~euy$15+bQt4_*M#lMqAU5qK2f5=xad@CJcx4L3#+n_u
z581Y#X3<ApiwsfFIl%bZel=YbjZ$v}P#Idr`TrvxOP6!bntIOzYT|+Ke|*dGfvDY#
zS(NAX@>fZYtff|gV9wi?rxV_$MH4-oYJ~bY389cy@$;XHrpwj?a7pFmBrDY~#G||2
z-Ry|>H021-M89WO;)S9I!KZN!48*$|_RSaP+b-hk2iJejNdN8CRGCz!NKbyeN)fjt
z5Ay5_`SF5Ln6?^-Ar3i9fr;AK6}?S*r*@-Cc`iF&V#$QUNZSykYEqVL89l_+DbpuD
ziH2O1ZG{6S6@sp-^^j(`A=~5{Rpht$E7BZ9>q1n}cnaY@oqf%hzWJKXZe}q=`-Twl
zc1eof5GOC84w*BX@7oPOB(+N)h=TJ{OCQsW$<*kiU)B12Y*<|)Xv_8%abB>D`i{C0
z2K<MCkcl1?%YCkqVE{F}g0m-_!G*4VKxB<bJ6v%fLT=ocO5dUMy7h&qL>!xXl9A+e
z=~KlX$O|4l1O}&keJ+oBAu|%gKm%&HnSuAuAj^gX!Gz}i?Q5yKVm!J5_E%;?^)ZzS
z5w!4U4wM@$W$a(2#<kf9W>S(gIi3sg!0ju4c6FDsWLb5OsD_}An51#WHA{h&954M`
zJxcqM<d0<{RUAE{(5*Q;6*TVdf9ds{VVR}jwf(nl!G}u|90lNo0#lHsex#+oR$ppp
z#p{*%?*~t;4O4&Tr^jl@&WFCX=ry6*fAz1Evd?|BR3f832y$4ft#Ai%`syFPzte`I
z<|z~(9%^c^AZ3+7gO+mz=7NIopt|X^EUglXM!)Bt4>Er@57&4({mCsAGkroB(b{wQ
z)X%b`O0;QN@naGL+*LcqAJuW9k0GC{l%GLy*_*GbZO+nr<K@?NlK;cde1XSC=X!B2
z^pv_SD)Qnsv4U7ghXR^{e4*wY97Mactl`^qiknyi{PV!FK`=?NqIKP$HNl+;&KO#g
zy|CWv@gxtrj6wERhP&EpdowFBRUplH<qr~W+=Gm?Ol6tFB)fkRj5|)<8ganG5f;Qp
zck|Gox}Ndh*7jQFdl#Mq_-WGOC;6n}ZO81|7Xs8OE4Y3*dOq%Zp6?7=kO6p{EomBz
ziGF(=21e=j7Vg?juqT0>$_|_&v$p!yI*|f&@aC*|e@4SIq>l9^R<bavmB{{X<N)&m
zyM@IccGb7_N&wrBQ2lvb^gQCdJpJ712c;jQ@Q(7;cHf*b?=`CHt7CJZPEKoSCWCtD
z&kPa{jjTVHk6gfM=dZ?%Q!Yj%D@js5fWh#Q*0SP6nC9tQq*xhL5=Fku^4rCVWTKTx
zw7>N_!M<_oK%14Ii<cJvSM|Tmy*|?)Bj<g~L$So`j}BI!nh0=tqBe+mUHB9NBK>a6
z+FQKk|7g5)$d^-#0FgBHK(y0_ePR=p{rGG~2X9Q5+<xY3H8p?rn)AvDMd2BQRGMPq
zdTC<L6wK;eyfd`0(K=2h!?0ua!<1(Gaj(P$cqB4^8U^>H+!|NF%OiJfcfTl_@v4Pb
zG~UWK4~y-;@#3eU+oP(BvyTN0e7{He*W4DhI^G#`o5M#&^aZuUcqOvk*y$d4NJiO-
zdpnrz^E8umRCkDB0fF6HOL@#p|AzOLApx!EY&6F;<#NVb(dRo#SA{ONyrZ5Ret2yB
z#*8PbRVBTu02`FL*U(zK?K~e_D^|_WWKqBx6>=jn*i1c1_t(IS)j9ExOwV=^F)5EJ
z?2&B4n8O&vsd7yQpSgcqFw{_HeeNlw#-_TWN|DVpyTjkssX<Tj(K8eaMbtEDo7zUk
zvFgb;pmeBnP#%JXz2Ss$A*O_*o&*%wosPj9C&N`seyvncvxby0uizthuxe*0_Xx$b
znpbhD_U(N+sJX*+IRn@LI_UDR9d!wgUELW$bEmqL8ROfgP^@jHO#M29kR#~_SKXc(
zfgz)|msE!-CWux0OwB#~5d7NlUpoUJGGfMLVU4y(z~!!aRH+Ax(M%naL`qieg?gd$
zlo`S#<y9-amLk<Ve$WazMsT@S_akpmHW$9US4LT4JRT>j>ip!^47^^gHH9VU9`zyZ
zV5K(qsbfEJ*w;m*=~S+6H3V7YTj*{yo4h8TiD^2xa#e{y@1{>w#dYHWt`>Vlf8ZON
z<v@bql5;0ktH-Gj;}a}4pMTg!aQu$)vBc%&(Vejb@<8wu^1V=SFb9cX-E}FM+DCKa
z7Q%LzTX}h~nkh3<MnYz@9$NWwjJ<{A&JfQGknmeu*y~V}^$_CO_qL`Lk8I4f+wv7d
zVW?S|@@B3K3lVLVoV;D1i(3SaRk-H41b=K4*ywdp$WL0+UB$eJc^l>uHVQMIwPDJ6
zBQ4xz3i3Dkzso%8<2C;cpsr^`hCUh&DS8+5n=~65Oa@XNuM?qpo2P^Vd82VfUnFkZ
z<gM=MmvT(hO4s7ft+iC=#NsYW7l!fw!<f{qxJB8&mbY7Ln`Cwec2riwS65ZQ1b&sq
zF9v^Gy>u~oMdM3F<yP9pmbjaw=8<I%zo31+;#{3i>@ET%C_PI3F`&gCF{fp)J=*F~
z#$@`_m55JD;(Wt*sQ{^tH=xc`eq?stk3aYeAa4g`rklPLBwe+#I7mNr@on>eP0Q_6
z3h`1_W8-`y<rRhtS0#7B%KEkWi%{!#yanQOkJWOM@JLDNO=YOxs1W0wX*^-xo1w*H
zEpIS~Kqp1?sTuy!^6pF9wZdrKX2_}o2`)k29A2`{b?J$jtc4@M7^$)~Aqh5~9ymHD
zY0$<^426ss{3MUj4%;%&B!K$D+?v_*zHKPbQ~ZRS_3yO)<dE^hJ#tqwoU3YZSKvHn
zaHA!x9LcsaabTgNa-ME{K^Pg!<nD^JbwX4mrEM`cPzx<ghAbp&g$;((yaS<yMDgcu
zViyO2CHiDv*=U@;D6JgfP+gPs9#a#s^hn?_;xQt~GjSPHAh%u%-gA{t!|0CaH@2L!
z;hXBh*Ox4`i+?QZ5gs~hgGmH^<$6po85DAL`iJC)_YA*236A*|{)GPRm3v>Eb!oY%
z45(|*#$<O@c>lLrnT1;1t@5>4yp|@3U#WwirGrb!%lWKjB@W31*=KDT$t4Xg){CwZ
zuGaDI4BDG!1*%<=ycpRA*>lWVKgj)i@BLd=uYQ#>-!SpRIcCp2{@GW{xf-OvX?ua_
z^3Q-bzFC)i2~hI!qHhg#!q%RHle2$I3rzg($6kjx|0-`xEz<ENw6~zrr4iqvW)}E6
z*H{7$t#T{!E>;j*7AcvfiUe;m=^ln>21_hT`wJ%J+gYJ%IE`AEOR{u-bvW`RoOM<g
zA1tNk7T<oMceESi5+7lsb2i4=<-+1j+jXK{@d5A-q@i{<G(_sSx2cYSo=n&iwLL??
z<;qIc&6ex(bL*3Id>>KufFLN*Gw<$gN7LXW2iC9RKHQRgLvQasFXN7Q(aQPpQ7ayh
zTvmiY`?pLJepQ2tD8vv=$!H}~lm;eSlo_nSP75At5s%^7^(<d5SZP8&)p^wZQ(Qc!
zo^%<C&ohEl<Fb^qhtavvLU@So=KI9k+8@#9PpUtb^MStMLeOV!=3;2&PN;L#3qD#a
znWy^E%!gaa+K8~SD6`aSSm$LjA5Sl#uW^i!i?|p;$L$7*racS{X~I@h0D3|zz_jFc
z;C{<li~vXe_re=2nxW>lCtM*-(q-iH!_rXtSaEmUYJT#fZo>9}7nN|30}f--1otuz
zi<CHMRUi}NeUhcOd}gU1nR@BCdc|aTk^1!?#CeO@{3{#};}hY^1zMaW13Ke9@K%;b
z?J@S8@BQE;a|4K-|HSl<#xp44Uyu-#7Q^@0kaimwh<Q&?H8(8Z(|Sz4q$O*>G-j_p
zbfD{=7P&-yfhm272-OMUdK{aUbD1Mnd7EvCmvoTF)DWB($|dZ$Js@K&qmr=r$|app
z0|D*lMYE<CkEiBzK3jjeDg&piWT(AaqWpPP?$I_pZsq#5JM|^XJQto?h_M4=Tvw#3
zA970ZhtBCf&Bz*($<CE%<pVH@ezMr43jBw$X!A-dCwkULZuV2Q6Q^NKM~s}>%Y{(p
zxym+699L;Z`rX%t9B8#U=hY<kRhg$ap63_q<wUgJaqqmu@M}n)^UnD9X1%1wpW7zx
zZua%5n@In4dHI4=QKRKGj&fYP%d*`RJ}7w!!j5i4FinXGUosHrc#c<zQqcxe&=*Li
z5Js}U!6_+neVe4ZH)?c?^56fG+vf5Mco4tnZ8%=ZY0$#p4A4=NOL>9bTSbYlEClfh
zO+ICe$+j^IJ(s9-HgU_5n1UPKG|uo2HDwNLF|XgmD~SZF(d~W`p|;oMNpY-Z;$ezA
zHK;p7X3cP`ls0_54<KMHH})swbI@sN?s((alW?skKKew}V8<rVIhVNCVM!s8XBiZ<
zHuf=<e3h@0ohWi%T+vwr!;EWIJbXyYT<uJliX$y;KO<P7CuGh|Y>3{}_TRNQB{m)y
zrcqWUAHd%c#!bh#6i`vZ!XFX#+rrRN%uAVP&;h8qAUz0j>hDSh)WajHy;^K_Ro6g$
zwd$3fZu}X?`zFT=Y2Dq&rmues;vRM#>x)>pe0F$T$H(!yQfZ*wawedVZ1aVPeNt`h
zZCQpr?gxBTf$ZaxD!-?6Lv|Xrw1_r_;4=iS2nxJWrD1Mht5sbW?k;bJ)adYwz;s22
zI2)qBu(NZNm5aXK#bFHNHRr-_29&AC#9$5&xZ&CjNS6^#ry#M^a%n63?W$9)@_6%D
z-Yegll<mD~W`7xC+(^PWduz`{ccMmlWMH60(d2dqnTD|Mly-64^jox;G-7e913oJ;
zZ4fGexll!MnPNqW)Mi#!1AM&Kben$Io_X!2Q?2;uvJRp8A4a>!MZaclq-d6RW2$W8
z5mTs%&xn;5?G06R`Gi4W!N%ET<r~0ZE%Be)E)%8;y>sO#Fr*?12k2K9jfB|hZF}x#
z5qd_~`|*%1Y&e2VsU%WAT#6H_1^i|hLaQS`ntbr=2Hc|>t3lU&Lkv3rVJlQ*n8!BX
zt<RXAHaIVJZkT5IrR>Vt3fSt@)Y*?F-LLM9&ll+efxl+j#;Ci`?KACoN;?y!w2Iuf
z=%MW%`wsOl^)H;JjJvXMzUTHxes;;((%=H1YdN*1dZ^&gge)?zWtQ=K^4ou^!2;9)
zXA=0eq<cFhZufs2Z+U+s=hHJ_20ujDUa@yL)$^BNo0g9ec}nbXeG{dEx)d<E7dha4
z@^E5}1^qT@FB~)gwt9Uxx^enKR|UMx?~7Q62o=hH^fs`d@fkbc@B`nP)*I5;WQ-f5
z`DKFCW_lvjavoPVl{}jB&j#{K${OB@t7T6pRo-XQM5zkN^6^X(S#t!|tg7w4!ReGi
z1&mj8vl0i1@$UZw(l22vc$iqiZD`7<oNs#44aYnCNvq%eYOF1&YiW!dXBuRVs<r^t
zB3k0B91Zf@8F0i-nWoF#PV8)!-T^1jVVTs}vp{j=etMUA9Da?gJFmrdOK$t1%ix<8
z<n>ZwV*rF3J2`N;(#c@*t^JK4FV+4ps*o2wA0EO$%U^>kANGYf<WnbBL8$V+QJ?0g
zO=fqxsaVf9JNsUE8J_$3z%=(i$F?Ld(fuYYE2o>dg82V1rVEp@=dvmk;+*rC>acx6
zlV<9RqJ2LMQ~5nrZ1Tl^P+|YXR3Snzka@1Lm!ENAk)k=XGtAtR@AQ&9plW#b#%ov-
zoI?uAz03U+0XF?qUb7Q9>0wM#W^ueNy9c%ZS)3J$zpIZXdo5LV6$ev=9dz{e&3Jvr
zk6y^~aJu>1_fdRl#`V2S>ARz8&$I<~67*u%>c#0o{dGjM;>OmRM((myH{!V2tPyfk
zFQOl&_TKA-R8?a6tcD$Ar#Z1E;56WIN>A$gDw|<>p(bwhW%&_KEgly;1)zP;4-{1d
z4uG{UoB;Jb7R`pgSx-R^8jPkV@)HL@6}$eB*n|gPnwa{e?W5#fuV*PsjU^gyB*`}J
zvWs(DI>$0hmm^U%)q<#f%=5-$It1V2+rxAU-Cl>G<(hqC)vToI*Sf)UyM;>?&`a-F
z1)^%NV>{IGRW+MEE_X$K*M+g%$5tpXVy1z|(8A$4N^yls&Zv|5-})07b>7mJC~)*5
zM({?Lw<)1r$7$2re(eMWXfrB(;#~skxZ>sTEsi<re@$%1d~^?0n!nN`ZXYE{Gc{qT
zZP~5cpwMDfu?O6nw0J^^TawHv4lPDA1+d4Fb4%Bc)tm&o>fgzh%G@iM`gBC1gn}uD
z?7B#xE;-0^MNY%&A$CSnNe?x~q~TY6_Hyhom`bNMzl;9iKdo!sd!$Qy3;M*HMGhhy
z(6v{XTcr))cx|sqt<QCErUNavwIlt^fU%qaI@V8kUDz<0muK8;lndXZ1yrOVqt*PG
zB3yf;YhaT09cBZ046|ag|GW@X29Ds};!_V4prbP*KsLDQxG+dG7TXI8aLBC`s_5kY
zmB3o9SLOGV*NZ<lILZ$#)k5iSf5iY!J%zDKP8NLM8C#DQFa8U9Ok!6@DWn=ZK+V$k
zZDi`w=n9(a@Qsg+=6w(c+(o7AgU13cS^L;d4gu0*u~dHq!Ua&-*V1Et!U;rmi9}!<
zZoE==3aj4Faa+#3Rhi-7674mu9dkcn^HBBXdOmtP!tgfs)D7fx-YPH8$;WBQ95g0e
zS7s_c>l~zJjnT@0VT(NLoWbRod-cex@-gVp>X@)&FA0f)rBsYN2sy1ZORv$_kUB=`
z0KXu8vu3EA^vvU~)}J5NfeiJS#=AW$@x8E;tViZQyOIKSYp{hz>-YF^xL9U7T2aE-
z_z@|Q$oV!^uOe|y(vXyCjr<TkW!2X~<?pYPSC`ribnOCZ(S%Yn9=zi0H?G^q>3uSy
zEcKK~0i2tUcM0!87NZRskOB+b9+!>*FCjDg#)7uyTcUjtBIk;yK$S9p_EOCRh#CLy
zUAOrBBDUuZY)0{+0;l_q(UeGh^Ti^2nh7BCSgSlJZL1Ge>y~9@I52XL9(ImgYV=1+
zG$vUxmqxR%rRorTsd%vH*Ygs=D<6?JF!M~`o(vhQ6E(7)2--vVd}Kev23oO+u@>7!
zV4hlg#|N0#d-7_m#%$zsb0LE8S9QwQwcab7Nsa)XzrB8Tj64U4+|KKzO(+7Mivv02
z!v4c3GD|i!f<+j~O&zyklUa%MX%z^hGaEF$w6ADil`i=?7R+>jN%wNw7(C*b41d@x
zF&ozpSX$Q%8S;(R6yJFvo2~(BDjwchS6n~dFa-{opb?>gi@(AcUTjO!R=<fi5%Rcd
z;~f9N{K(y6Rk~R)%Ob(kh3#wV#L~8HrVo*%7Fq|^Q(ze1o3Vy%V8`f5>Lz}lTmkSk
zez|dUNHUa?4dbB<?*H6b=;A*NsLv2UGV|^hGn*1_x#2*~Y^S4Wo48u4z{b!Is~RtA
zGSy4qK!$kJS2(ij;)jNUNw!I>gQNXEAMtA}0;p4CSLGi0THC{pC<%=;yHr5GBs+QL
zw}kR!jqEq|WsTFdIvELP$;O7{otcQtxRQBS{=?vh0`BIF&RfcCjol+sJUDiLyq5=U
zfU{Dkf^VH3Kplf4xBKhj+1wurDGLQyC~LX0GOh|<Oz<kkJ~zLgT9n#^d-22@3d{KL
zi01ifK}bAiFbc8go{as`I+g?w2JYTG#Q0WMjcX=yo~cZcaw?PKu5IZ*jI!E1@Sj{>
zaa2IC0`kv2&ZAh!Y~x6EgRU9!DPWPD4#suHKlZGsQu=a_GG^2={V}l0Xwm*zqvD{Z
zjqmWdK2&9DH}T_t7)EX3`W#&))iIa9FXa3*Lr)X47RFhn;Lkax{gLmIClvaetCZcb
zd7mlMM@~I2an5TQ7b52}x6XIF4Hn;fN7~>J<}c9AYL=39az%4~4EO1ikTruHLeJd|
zlaCZ>`;~bZcSh@U{-Nf+v9jAp_d8CKiTa36g4Up(+P+=eGs+xGn0p*XjXB$f+`Bp7
znOiQ4u{5OaW<E<@qT7y4-0wOxyWCy-1eW3#s`?W553NkUy;-fU^6d{y%AF2VaWL``
zI;A1sE&sW{R{bu%_H4GnfM1O&Q{C<IJ0UpBsB1#zOp)o|_ZN~Q3#W%>0x>)94ox_i
zh(k@<l+R&7;?r98oUYHi4tQ5cg_jmKF30ITvsW~QXQ%E^%}uy3LQUfnlT>UmoRf8l
zfEm11yMJU%IP)YuOYfIwslJN6<qxN?de}-aY92nEDM&{ekH`>yQ4>qXH$bH+TBy+#
z9Fp?o)$iPQxaG>yn@{NS+7dzxE<%ig2I=mM&!IU1rD`6VMSljcQu|Gt8#IX3(0bSE
z4&n3A&1_qfC>E}lw#Wh49_9OiaQy6u*lM}m2oZGLNcIk2nNgY+4sd&qxt6$<u&;PT
z`@kauQR<%X)l>uD&e*atO;Y|&04gXTBz-1C-;fm+^H4zdsAgc4;F*>VfnQ;R)q24F
z$dP+9PXKhA?)Yv>)eUfVRkRPpRiM|tEIfnD?UgdQVSI{T*!`CKb<$`i@!2~71{{0z
zwJdRQBDpfN?yj8Ch~w;is3CKMqSX7#LOFjp9b1&>i7TekGVF2@mtb73N+^sc*-yS6
zlXlSS@+`-`P`^<A@@(j-9-~8cD(F;o>N&fga6g7x4&zm^)kLCY-4MFFyPJ1JWu6jI
znDzUE(<W(6yW0h!BNSOvn04mWaJ?MUE2Zc=?(6qq!n_6z*xF4T*{)IeQkvng7MYZT
z8jQ`RkGhBD$2(jAvlz(AR8pk?>Ij|_?Q6j6e>C;{7}Dt2?bT53o4~E25Q%BdoOtAM
z6_-uyw*5xVIZlx@oBgFUp)I4C_r{k%AwtWP!3LkL2tCk=9Ep=yzBD$`BIW*3kBeRD
z$}2>hD7S3zc<@?DsfPH%POAEU7@ZZ<0U5~NmUQ{vnPvemN(g6IAy>hqrZ$@?>`d`C
zCmMEn-4<6Wd)p62_-IK;-xR^@+V*xrk;NvkQI%HZ;PbML_f*Rb2Ra}!%+*<`YM~mG
zrXC~dKmqMu-fjntF0)e<x!-z_FN{xT3{m#Ey!s@elw+Rh)e?^M<QA&U+S)Jq>=He~
zVr4U=pcw;-XV5xY`M#Qv!JO+pTi*h`W^{>MUu*XhF;%?XCbMb!UAMbfUai}LFlyJ{
zX?X!Jad#;=ws~J6Z8<MJ`u@6F3&}3;z{4o05Fgywp6#7+j`I>SqS7}mN|BNi#)CaR
zIc^XjRx#V)Y*A1=vhJz-xrvZsKkI5$EcU0VG;7d!&}s<{S)v}H%%l5)7@c+_hXQuq
zstnqYSMfupuO~!w-L?O<kj#{d5}Sb*M0pVPH6r#|H0s;b3s+KnnQ5h~@3yYTs^A$2
z_A{uV17&e!tdR<3y%qKVpiB?QJ@6cZiP-f}ZBG>s{*2xxDus@+5LVx%ZFoPeg7J#d
zfs(kMFv(#>#t22x>}Z_i_oJwCSseP7px$s3!b`-@s=w;i3Cu&@aW|VQ7KET5aufWI
z399G+N~t~j-*JxvkVZ!vwKu;pPW?}l@40|(4?s&VYsSQsoCnKi=tbv;vv;wAmjX&#
zZ4vzZV1|-a(4AcVM9qUnaeujMO7E+3D<MMzmia>??hDNGhpxC`>=W;Ag!5Ahgby-V
zTrq{Yvow;5>f5le&%vf&f42mXPyrWdFG$nJl6-S8f?srgfr!UY#s`_uQi=T@VW$}&
z&uAA8T-d^3DGsjA5+ogGW&Z~!h(2;ZU?H<a|Kr{d72Ow$xbOa{9G{G<JSI&i@qw&c
zugsKIO|iTU3fBvhRBDV_shXzk^PW`z4x-uvml#LA-^0flE0;|&&tumE`F=*qwYkpT
zmp`}v*W%we_4-A5+?l7W@#E(D(LJh?gyxJTzJY|iu3s){X@R_$0}xKXRdwvyq%fi3
zfQF;bX#Hjiyq-Swe|)XlxaZ9x0qAhYzv%tQ8nZHSr?LoT)=TqKz~4>>T)!%0T*+YY
z2#vcMS9>*|8NVJ{?3P>+rCeB8wqxO=q7tEI<7$*{V1DWSnMT7C%(1>y(?j?fxNwFR
z-|c^J+LHG40tzS?e$z_Ge8&22qTNtzCsT+4)o^*cmGnuJ6ZMDD<lec^j=Ea#RYz(`
z?&xTqF7KD6zG$GN=`MFhFT?OrJBn}kOJh>~4WW>Gz6I#TYISU$Z@Xsm-CXt0hO+Zv
z9Hv9wQT>)0>Bzr`Im;x|Z8XXyCcvb7l4<`3osU}gQ!2yv0U|MX>fhnPJ5eeo*@lh0
zA6k^|APszR)nIwlax?@gs^0d^*T6~>+HRs(FJxVob5B1l{6qGOyz`*d?8{Z2!6K71
zH>M#U@TnHX5Uq!77+4bpqz3T|GMt*egf#w{$Au@4TTE5X43#@dU5j@(JnMV$*yn<9
zo;T&otYDsQh}8qS=`%<n7#8L-j<)1bzA)_#$cXL+EN1Di)k3AqDR*}T=?c(txlXS+
zQ3kSmyyPAneJhxtSr_2rXx;Oc?jWObizKN2bxD|8I0J{}T<lFOs7Imoj|iW#(2Aq#
zzZ5B6(C0pWKY&c6WxqLYA3Tbej`HW0IESt3RyfBcm1`BHFihp0bwl|JXH{dCcSRQD
z8148ok@f$&)-nOg#xxR*M&xXXuzxrm^tdpBVwi65pk@PL+enpIs1Iy0ZhNq(Cc=6W
zYRLA`uiniBR*kR-{4x(?Xco7=1K-YGV_>e)-uoJe8KR>VsKl5nagKL<yBS~e8bp5l
zhe7i!h0J}NoFwPM@U1%I<BAEj6Pm8cz81;8728#LtJu;)dIzZx=^IZxQ796l26W$)
zI-0H<C(@H!w{`v0;L0eM;zD@3%8WztJ*$RH6xQjeMj~s#NaG~EoksPc5?dLB;b89#
zdGNHg8e?vIV^<|XMt=oq?QL{T5wqp%e`klMsvDy*{mu)JH8+8!JjOetS1LHmGv90@
z6GpybB7Uz@>yaM{yOq94W61pKK#+CG1l|BI?H_|nKt)9+lPSU*PvW~Wo<}J997&;Z
zvFCasZ$8>8&|ifKO>UWQYJAY~@g#-DLfKsotruKX4eGFlyu}XD^tQ%Us2cAXbRPWu
zK^;xp(!%rq*+%1<Op%mtWme$6hA~b2nGOEaO1ISKLW*Ax)fw6x;~ttRuo@V*5P>=F
zx^<K<_GX^n-R!vH-ROJKSQlv{SX3Q`^sUAVxE(q*VEk!I{8NeF7sN@`Z&P(I=Xi$l
ziZf099BS{03@P-N$S{2ZO$xwGBE|t~kc=k30I^8xKa4$RMe36X+IrmBLCEQq-)pcg
zbHKV7OSz=V3hR~FT0A4@t1RV?2S8mgWjz1q=?nS`<84h%p`?)Eq*=GhzzK=83Epxt
z1~2p(q-hq{yY`WF&2OIolrMI_r5Wmi_2K!F#6;%HsasT{q?Z99*3Fz1e#IpuZCoX~
z4HBe(WdaMqf>^Y0Y{Hxfj6-!sipb&XVk~?KP<wSl%}k|+;J0ooDz7dG>hEr@0|L~m
zi+sbY^HlD+tjVH{N>Wyzn8Nc6nWA-UR`DFCblJ5#e)pDZfQWhkx1hbDJ<3+d(EK{d
z#xC^l?nMth6xdO8K8pPs!N9k3c57z6MHJrq#Q8U;j4)B-L(RiiUb{#%Wu+0CJXM%?
zmj0zapF)FiN||8{{xjFi9Tq~r{V)-HcxZ7g0k*_==Pe)GVCjZ2NLR&M*B)7m^iaB@
zT;yQ;0a0qBL#wh4S9nakqG~YNvjfB8&5#_b(9;QDEn4nRXzRSQjRspXG42&3D$&eV
z*)IGsJB(?lA!Zvh24<H8nQEW&5a%o1i`KS$fkjvohN}FelG>BDoE5s%t}SnCRw`9h
zrllzHG)a$fplj}eAa@G~G22_wqA}DY2<NvGWpfEzW(A$xZ7d}>6_k~Ikd)<bvXay{
z6={L)l(GwUt@u%fSTsh>q53oJ876_u$n9)pax>FJ%tJ#BW)nT&=cz)%fFBk>(n>3`
zwR-i=&%p&2j<<d)B2rm$P70b+QM-7$JGPdy1tnJ28L`99k{);Ai`l#{x1<IU+$}JP
z;eO-h%;LmUov(j*U&3b^Zpf+v7~I&G8{Yd5GtRMkd2>8_wHBtdZ!#mkB5H<!Ykhct
zyEK<;{T%8~e%mWe^atdX`IO3-5}eQ$>~RCXFe?cMr7ciX)f__f(XmD9pvzLfcRNN2
zA-Mv%v0!xOi}c4^CdSCTn0$T(Zim}Bp2DD_rIC$5ajzK@SEykQW^RKfH*Vd4Z`THr
zh%JV#QhQoe^AzU~D69X~<QNo!d7wjP%G=99mU??5G&H2!JSo1cM$_B&__9n=LekcO
zBj+)6o<O|rM@q7fZ<2{plAb+@b+33imYHFF)TBYOtZYf%GRD9$s^Ift9Gyb0F}bKM
z^E0TgDWdSU+k(J%#r|8p;%HKTPFnFTi1y5I$lT%k15dK(4`#eOQ+yprpG_z$w#1AK
z*%AWy?&nBbUD|%0JL|gdHrWwqyr@mRt13*XJXyo~Gc0dH)ybJZtZahDmlZ?4KCL@#
zfrk;|k<1UWh@-u#!U?=2z&&Dz)?npHS8DBJ$Nyr4@rLFqdC8wDS<DPKqkW74yn%CZ
z#oIKy-{{qF#IhsgQ)di0A$r^~IDae7Kw~V9mDCbjKF1dF$nxyg%bU_~>;eP+d<?I;
zGC9oRu9#CT&Ces_Q_7g)MY<!NF>PQj%(-v$Y`Hhh&Qg(?1`?#Q#TO+Re-xhrR+^fY
z?tJv&6Ila9hg?;Vh$ggayeravJjRv})5sIS1_2J`HAeH?IKI_*5zihQ1PAX!ng@DF
zb61{H>F(wtiRI5q;c<d$tK+T_Uz@2Ao*v6Dc4YNJM&6}PUG?H09&t3L&4suB3c~l$
z7F*^pUNa+<y$>-c8<OizXglDY8TmX?tT-7mIw!J?=3tQk-%!($N=PP5AmDK#j60!Z
zR><!u5$YI7RR6NqE89>*0(w!s9pSE5p!mMXUKvM1qwUo9w_do%S!Hs9xd&U`#lb&r
zXcwyCUzrw63K8nl-+~IaO|S@9vR~vsFC1FSI8}!55J&kX$C|#p>344!vFa0^;1e7*
zwy(^&n^n%Rstuc6nDK2M9Wx;r?{}Hl)KGrSt5GFC&HOAC&5lgOW~A3JPyW-I#KxCp
z%s-vJjkWZhU=SGeEzt}@OSB%XvFn1wm++FWM<q;aP@1cZ;`ZGrik4U3TOT$yYPqsn
zHw!{tJbg$>UaL3^kc1pn3VL#?sHBO6VeZzHF4^0IK2)iB&E>Ib(Cl!8LKa$}8gwHM
zF+brJ2>2^Xv<oSF<xRH3uUB7<-y0z+)$))D6*7;b0hhbAg0F2h-&jV3;x~5>ABd^=
z3V%D{k}fZ5+1Jzq*>Q;@Q{(Z-YD0`WwQ6ofK$Pe}(&uCiu~D)Xb2f(y*-J`csz#3k
z-7p@VzGkeM#(-+#&J=H|9#GnRQcL&w9b{mMNDFh6UG!OS_mF&Qn?n`)MHjAd9iE(=
zq>3tJr`^smMP-8=Kb7ZuHGG>Ja#14r^3cZzCK+2vmZ6U}G4~c=cI6;=$>M)zo~-JS
z;{I0!P3kW{y$PXcYH%*JRly_tLgBcz^M{Axm_dsw)tJ$*xoUS=ar#O<QQ{)6n0*2i
z_D%!F;9Uz(;NX<|cyVg7YF;?8oz%tT7U!7T_~XRGzk(*McukdX{q+ei6(@hIJh99i
zEBWi}kOcwEe)C4CTGIy+9;1Jz@vtAWs%6r6NxftdpshDMe|^9(vkn*O{Zgx`S%G8c
z&(^CKe{?Le2xyV97a@C?ZFBBU=j`1WXWdK((nYWR)WiqU4M$Crl|5gQC6|V`FILR^
zD$8NFT`W_@w`)MzqKK?its|LRiuBf}l#k3Ut0ZqD&SEOa7gc;OddYbJij<>aGF(mM
zYQC^`lYpdeDSHt(McM`2LwFy@rt<S$OYMx^a}S#N@^nmEe!XWT#_<c83-TV}lU8mH
zp<l|C#vg!H`yYBK1=3#bTXi?Nk>+K0?56`i%^ON)y;#?*c!e7C6kpZN=N=fPfM;+?
z6;lBYg5Dh~@R22<6LAu47`;?29NO|mky@BMFJ*nlg&L)|XH$`pYbj<}hFXoTBez_S
zXu}Qd!($9+TW6P(@|@=oR4Wm<_qS9-1yh}o@l20U#rhswDMmXqd<`Abgnk&DUHe>0
zDyJujmvmXeVQA?PBJ>VO?xHl0!&I&;DkbgLJ2mU!SaXC%Z<Ppq3GAWTnsZCc=ze}K
zpZc@Y<Wfl>Hf^iZ%}TBCLArg~A3!y8@SC-5_2M?i@jlcn|KH5*RRY=S$ZT+8VQPZg
z7V{kTi)+64l%9Fv|1g5KcB-OgmX&kg>(R!yZa`213oc9^_6?p3(nmO8;B#tMX44hY
zk2rs;)@F2`@vxb=o5owYNKJ^22j;!X?w)6+Xt#7}aD#GuhsH0r8IPns?&AKXdzQA5
z6E0KZ?(I6gYvK5&BqADN{3XerZvEk48<i54FhSOo8ovktc{^iqAq!%Km6Oe&Nfzg8
zbh;KR`8HQTwRP6hNuaAXjL(;$)wHdSbTm0Se#{*n^ZOOU4>d=Ew!mJ<wpc!o7tKWD
zh0o$%!FBbIcJ|UgDgW#_S{oZ0StV+zsXmo~J&xE}e#783AS26BDO{s%-QE)M{hKCI
zL}7kIoURCy`cQRVKrrj<2NnM;tHnr5KhlpUp+@r-?P&rDehUgcBvb?pBM1&L+5Xl;
z9fTgi#0@^;d?<Lge806&{kPR#<2rB*8TrjKUg-AFm_1nF@1iu*{y>SyE`?;kqopZz
zzwr>;fDqa)?L2Bg{Kk(2v_RjhN0Z#=_#Z}ShYPv_)8W_}e(UUz^X!G|x7){QJbpv<
z4K}&F>8hhJkkjn-he~{nc|u{c-!iboa?8>942SzUu-ad=Z2W^sz^gv>PQ!<`?OUZg
z({F`A%cT>6=N2Aag3KGT(fu-`1{bh(K^B{<y3KHsm3_mnmR)jVA1Y<&_l_=G49}eJ
zmGD*sffN24mkzG0SO5jhBzs!ytomuU^Ti5F4e3m^GyeyW6n|BfnUESsp_D9*lz6WU
zMMq+!{_}0*9|NE8+_(056pgNq&^sA=eYKAb>2>a^I2OOHL*_M*SnY3P4@N|7dYyu)
zjtKZI8*5{3)2TM-!)_K_)YRvqe!5@>RtL-k;J&W^vlDN{!$gOFeNzp_y)8}7g@cHn
zQ%x#B>s?RsmNdrvRMkDIsX#1b`;z!{g6!Q_8}n*>e7Q8I-sB^5CH~GP+nc%We(C!B
zLqdoNB9pepuV!_wX}|jfx`mU*WhUm2Na19{u1E&~RQX8vn9Tui!=XogQrsWBt$p3*
zmY9jvl4hTzYL2W6LFy0M=j=iJq#=%pe!NELM#^qU^ksch%)ud@TZ!{_;JAeaflUB=
zGGFH3_X)PhH;Y<y7BCI=Vt2U1Q`#rO*C8|Csz$$574k|WXlcmKP;~{ejgV=hS`j@(
zX)%bL%NBE~V`szc)D6G;mswA;-wT%BSY`dL4@&L#-cV=l<Qf+obfNDUY|KdZhnH!^
zACI91=ypBwww66*3dLOH%_tJwxGh34JM$w)u3SFwMQMhYrblpYBIEhopkemfTMEkq
zvavV*%UNk!Ibm}HvRT9UHN#0sKw;hFt@l{PI$#Yc*}gY)H%&#DF`_C<%gcQhibHf<
zXk87L+d4i0II^)^XwRxwz$NFp?0D#63-IQr*l+iS@SsY>A2$d5`1~Q$OSErV$pPgr
zxn2wnrJqWXB`KL{-_kwv9RK8ws|3BFYGH{VgZ(VZYHRXa3FkeAu@MqS30@UfCY_^f
z^1;6Ta>KvPGx9J175ZVbSqu1E-vEbs$gbxdAs3d@@*1@4)xZ&?zU)!=s03P0KBA_y
zvHXrp?;<C+FJM5_l5ly?8)Pl>s&QtD`-yB^gmwOQ3hiNFL(U{RaF_&2r7TrSk8wsw
z-)G#&O4^3tPr9y;4c)g)@EJPX4_+~W3Ypq(#Q6z_NAb>}2?kmmynCF8A(^f7(gfzz
zY&vS;eopW#OD-R?+ppeyJ<Z5?FSUQhj<z3D+5JnG0X&4RfPJY!g<KpMvcnC7xIK%6
z&`s^~vXE}_;yVURdYl`(se$h5Ak;8Y2eZ)Yqb_gQ+MMoO_pK5RbIzF==I~Y3(2;Ym
zte!3pI4Mhe6MD99{E{on>g-f|T#zk-<|V8r4~~`BKq|K56~_IHZ~MYN=;G#c&|X}D
zyQj(I_ysXh$noQ33RcUlB2Lyh38@vqef*yZiEW2psDf|M4QkcB1kh~UjuLZ5)kkRy
zGzQ7RkG3{{XDt~^NeyY#S^s5H`KoAeOB;)+?shin;!x2l=}_0?W?$V2A-B2VrzSV=
z?(yDoaNkO$X;kFSxy_RO3EGY_A*H)HZ20QX;nFDUdkk!ix{|tcu3b(Jb7za21RC5L
z=J7O70x>+I`TqHu@l%Z1MwfZbS;USIi}1PknpTS~pA8&;r~gw@LoO30G3r65oe=V2
zom;vK;fotXPGX&}ZN{)!QIQ>l`Kh)HVD_`Pn>DMKx;Byh9Fx(E@Aq=7+lW*zrv_m-
z{(4PP$*f-Hu=u26{EH@7UdxSmHr;HVD$SvRraUl|5j|ap7`ZoSeby;e!ZQMKzyPSo
zh^Dd?3w~cD$RT!vd~|rC;)o@I#O0+j2qz1zq~di+U6v`0Am2iL)cYy0>56~Jw}%+!
zU9z;HO1_gZhv#Cw+)a(VDo%sT;^i3bar_ll4>`M=-sRbhV4B}ob;BD3kyuUpLexTZ
zOJ=??Kl0%1Nr_>!JnYLnx^=kuCap!%hgkG=04j=bq)x3+i3%Zbw5vJM=U0$@o7)4Y
zhmXCe#y^7`UnQKZ8qDIxaG5}#Il5EGvrSD6TC11}(o*$*+c%|!3Ay99#=T|e*2>Wy
zOtCl(y~ycA1{h)suoU~%2jKZSTqYVNx)kwjk>xXc6vYxW%S=H4ix1WzI|IXnA1qFW
zm{4NAWcLO-NZN$czjqiAH4&^LpIL<`re02lC_4R%Hih*Js5;ZJCp>iop~}htJH6`W
zxvLcp{q%=xYf>t#>>P||S=*Uk$wO!8Kx-5}_eM>2Mk|Z$j54;Ugcw^3X8;3}B0|Sz
zh_?!dt2nq{qLTfqT?_)iJpcI0>y-}#vu7{G*ef;J*}8cUA;QV_KNcwhth+g7UoD3@
zPj9EJX#;ycT7!!_6mc`m-q)Hr;fq*z%&l*pyR3fwz4AAFKUwGckj%afe*bx-cN!%Z
zX6@cm2e8}IKh&uy!8S1=0~1x|mSs%ORMz~>=`6>`o#y!b9jG8?Cyrcc5?Bh;J`!AX
zY#<sUl%2<{h7N#{m&|i(qZbxLgSmxtRif4y%WceoIfNmmez<kfSG%w|cGWQr{E$0C
zTr2d%V5t~qgKZNY4A0l5<A+cvb@y#33+P-n=#@zEl-kP_o08us&OWTiH9qqr7lDyG
zcsNH+o=R}%k2bGSQooh?63|GX%t<!@a5&ju`NqovP1k|i7prhOl4QU9`#j{=r)>eZ
zS&mEQT)wfiMOEqX5R&M|O7*XEU$*CZf3p?uqKeMzB&`QoG%pg!3ob79A8xC4kZKIA
zSXL}?i1~DZsXeS;)t9BouW^|E8Aa?z8l_t0I7hP}Q7TCVJh61L>K<lQ|J+dShBQ?x
zXUh+}?cY^#*^y@OAo({As+gUg-H**w(<Gk;iuYy~Hd8vV&(wA-l3yf7D{V~YgRo!G
zc3qeFZzj%S%6|(e0`SP{V?rUq{geUUu_!yZv9hGUW6|v<TtK*Y6A7T<pD8;oR4^nd
z4KItjzrUD<8s2=r{BCcciNi9JPKmL;qdO>OpHs-;s}aQ&X9v;*K{0hJ7iXE!F(tUr
zkN>~bT>nq4*tid~5HcVP|FO#RJ)$zgv218^rgin5N#l%%V^-*=FHsL|ZTUsPW^r=C
zVc}Ry!GY&oH*@NPd#E3NwN&HBESqveA397|TB&<RGKTITM`A2wOF^GqLRCBy8)qy#
zKKzGqojiU4Irzw^<I^dqj#!DyCD5cPV7{U}kT~kPA)HnZ5>G&YlH4?FhdC<pgi1BD
z7Mv{F-Qmltqu!!2axU1%n?J?#Y2E1C38>;9`#VlHN-0H7C;w($Oj6m%f>MU8fs$b(
zk5V^Po+nQKVE}1&<egs5i&o82O&0TuA>@bIlh<Y_Q@roGqTlZUnN+}eFOWrZa$GKQ
zr=8Yq79H+CCUE3PfPZwigg+>i9E23*FM4?WXjHpD>E%e!?D|_BS@3tunn}|#G)eUJ
z0D1*_B=W%<?ncA8cDBYN3NvHBpxVt7`j;S4e7<C!=*jX~4qZkAGc^SI!AqtmNbSZ$
zIcMt@Tm~*GblBLq2AxfQr(L(7ETqAP9{jCX@uB;ezoqjp;P<WADwB6L@nKt1o4}me
zPee71TN8ar%!wyL{o*ejrqqP2Nn|xUqWyWA1n<|}nku~wJ{a<e{h!x}YGaFAG+_k^
z-*dg0vY^mSBB)Hr{@u#BXSkPysJfJgzw}i#(^+S`xK3cO;jXladASTBqoLo=j6D8O
zPc@^~*6AhpW{akp^Ul+GSn5b&#DXxPLvpBD;RF9!T519OI;+PH4sJ9oq`l-U|Db_v
z7cB$HfBcs81@dt6C1MWxBM+V<;%PckU<Vt3r_ow#4YCu<1~AX*-PqlDC6Y?@Th%p%
zRzb0tPc4pc;17IZ#609DdnT^cfvG{x0|S=_3J9Bji1$BM&@}y~&pVT%1BHD1<H4<e
z4)H&nH=d#spc4C398!tsbEJ+O)4XZmkQv9lw$?e?Yn->U8u+~naKH-NJF9rJxhD1G
zdShS2YE}F)O=abKj&ThoM(p7U&*X<l%h9fKPvIn(<?fyS6o-XQBqXx?`(P}``_f}%
z`lNzp<6)P$pd#CdG-k~>cirotCli9g*cJFyMcRdscLwpdPs0C)yR%$tqiwq|1zOyp
zSg=B&Skd6_?!lpGad)?3DFnCR?(Xic#S6jRix=zjWdpt~cz?|QOma+)x$bM7=dv%3
z4MXgM+<Rg?#=;}7vNDx;FlmU~*txY=W3uTl)w(OKC;dh|cty+L)j#3#(rJ$=i@N_1
zOb%;hO&vH96S7NxRlJqNI+0(>n8>PqJE+>A<I3)d(`bUztqq-8qu9S*ORvjV^aI2a
z&_6Oirsco+uH@_fou8G%Dn9))O^5Ys9LDp8V_O?gV~sv1Uvg5fjLUC6kV0gOC)ecC
zP=q@n^2<>}&6|JCO=CmIwZHwB*yTVs{<_j%w_U}6`BNR=fXT4*1OMQ_DxBLIS*`ht
zJB&iC)MBjrjvG|NP+=?va$EJ%KTu(;E=?BShGClY_pO}4V+Qj*AzgnCV}o!~+)DJv
z()*?)X^-uWm<9bP9H%BN9c(Pi3WF;39xf^K?J5=mzuJ)jYgcQ{BQE6vRkL1S{UBKG
z!=q_p?KA#Tf0}C}o5#%?lnhd5=3TYOcK2H7_9+9-imqkBrPo+5hOnBA>6<+MXYGF}
z+Y~Z;sxQ(o-j74ElP{rXaT?Ml3%*0L*!3xfyhMcHu50K@XMHNaB?xb#@>PA`<qnum
z>)OpR>pN?3O3PQ|11qg9&oeA|jgkMRFJC=T=}Q?5@(AM}3CgzqVPJuEOQU(Bqy^i?
z%X%mkCxyQvss*hBt@X!AVe9Nc(aQ9nevURr4Ws`6cbuZA%LAMfm1^(;REaW8bfl54
zJWAP(-<Yf-eiyJ}4U7o}`z`xNmW>2d6l9X9D1GBNQ2mfTgx79Rt>Zzvh}~^1v%W&-
zr`=V+0P&QW71^!%SvKH=(MeH}7fu%?PjGh%-zvT%eJ2xO3m`!Jl|moq{Gn1Pgj0MU
z<dGxAV25|g7=8m+M{1qFA8ylr@=Y?%hL74K(2ofwEFNz_3+WxJ-<`Ka``1_tObCj+
z2yArA6Z-f<?OFW{h2<#sl`$K<c@(t}k6bk4$xaCfD5ZUil&SEPc{alnV&E6#*R9`P
z2cgN{iT+2UW#o*a|5-B~b)WXS_@{epYcsi|XMg!8M3FG47^k6(-~P*@OKS$T^19oZ
zYMXXKKT@$2b+Us)IucaOs8#Ro?60G_?o>inZF;-rUmfWRZ>X^2==qAkhit%LT+=|O
zd>N}5__<%hSP>`rS=;d0zm8pPI_0qt+V7eWZMGAqs^46?F;r!`5x*hK<kT2Y07Hq2
zpc=ulQbvvYtBdOkSz;}>7ECn$-K3-^a;3(lH*`B~*Dsollfr;0a>Bh;SM_tzs+KVM
zqL36CnH8c<+s52KyCXICq})0YGzj(g<m8OTYrCU`mVQ^Hb2sBf2vC;sVi)zM5|{Kj
zV^jh_?#<BBM<!Ve3|6R8l!M*L3>ybK(8T!;44Ucmh4;OvNivfj!_l}WLz75WvjXgD
z=4(@#h0_v#mR*N$4gPa)me$R|5+VQj8GHj1oeaxq7PEfPcS}NZsOfdj+HID8tKedy
z`Ta`k>7u(9J5Ot=Iyu9fbEAY2TZU(E2D{9KvAFz2A8E6+AszBFps2uU?)l@ry;wt9
zi1`60zfj%K)OAqk%_e3V(wogim#bPV7$|sjCKfgIgR-PXmMs$(c^_Qa!|5u+ctU3_
zqTwbfrpzQqyifY94H|NdIKWaBUThy|N4N(fxS~v{HruIC%X|WjGl!jGi3Z9F&0l(n
zEV4MvNE;xi=N9Yg%2O_V^CSm={nN1PFZ9q~-a+H>&CE!|p#}zJ3DF7UkQAv61++n{
zKSjJO{~-jSP+S{Gd$E2jY1gwd&ikHGMlF|w61D;~#69QV*LqCo)Q>dbfHYfv!r-vC
z5X?vwUzo2U(&$8Te1?ulsHeaq`aRyM?Cb2Cp#?6dl6ZyVd%`w|7P|$U>~OA~K!c^7
zf(cm<GE7H0NpPWUvd}6zO-~F!(n^($E8I=LZRg*V5ysLm<35@<lR)P+?piYV>Cq}q
zvngA`WS}Q0J!T)L-?9FcRnOo<E^FV2Vq5>f(M=`ZCg)B<J!Faecb!9JTnQ6>^xnX0
zDfc<2&pmNGGV^*l+@@$FHu$pn#^}Evc96K>{O_M_dn&IG<7kO>-8k8e(tFe}%EfyN
zS|*Oo3IKuT@T_k%63ggq-Py2qZ}d=~i8<eiHoiK6WdxS>=Yq|WI}eu}F`;GuS7<%p
z1X09*dKr@DK$}Fr%ul+;Y$+t@xW{6^y6AYKQ+-Z0y_EmE-p{N=Hyvofg_md;IyaW@
z$GHcTfV=xU{s@wtv&H2$A<t60H=E6y7CK{*=5aSsRu-5$MICLU^hLqA^<D1C`em>d
z;raVq#<u8T%RHSK8?A)fG~EF?XP~((d2TwxgIP*r(`y@d`Tb?lijqXcYJknHL3|sN
zSVaNuw`wM>d<wB23ZOF1{rmFi8l0_fGer?Iq`%E4qT`gOgY7&_b;~TMgYGNveXjHy
zZMa7MS}*z%ISgcV&?du@WK;wwnQA`hLw(5G4ogze3LWCe9Vx-KANTmRsX)WTh<;i@
zyumJa<&L|ioPS1<$}2nEaSqCmYF%^=o8HzkLNNId>pXx+pV$%v@l^1Oioy}dQg>0}
z$hE>9|4wT`Ve1IzfREht>FElYBoCA+l-tDN{Ij-pJeTcM`g3)SKA&7ZnNW2o8(p-4
z_2>d@yMmD(<KRS@)^FxdS=&oqF(Em2Qk-~ewQEM1)-67kab<iJVnpT1AJzI?KqhQ8
zWv4^$1p|}Qh-W#^Vg0Ur6wF_3im}2S8O@S=an?%u&8z}d__%wNdW_#noy4T2WU!g0
zn|5&}V`_`vWBNqEsJgE}l5SatMQv&`dNS|s$~exH(TD3@a`-FpcoE_{-<X8}nyqyt
z$a8a(DznZmBxfVGorp1@5iC0!7unD=c5{e~fF@ghbR<9Jo1I92JuTP4eK}3Y#zP)`
zAx8l;l|1gNm>2sak&^U+X_NmR3X#5|M@-U;?dfT}+^{7}DGBmjX_F!Y?R(X3D^FV5
zss0_D<)YX}|2CkbqK6~Gn=NOi3g0v_B7;(^Ka~RJ7iaPQH(St?0iA`02x+6jBjsUD
zlDCPVRj%s;@?CW~EqIsn<WuY13MJt^MSHcJV@5uR76(#VY<0fiML)3lTe1@~&uVTN
z`4<zv+EC6@CGUvyP&>6%{h3zCQ4;h-pYYSV&(KaV<zb#TSOj*I(`@mFsS{9tSdE1k
z<5j*Q$g%jMg>rfL!xanDvTR(v>Bz|*+DOsBEe(qoW-8dfjo?3iuP9u7(Gdw<KBW`h
zVDHVA{_(Z1Xb%Op)M-!>5*8N9$u79;0xN~OPD6g@=W~0!zi38nH)#OJ-kqrHrkDxq
zKo5JC`ybgR0;KJ9|AH^^32QT{3Nfil>~hqgtJ=I>%-#=a(`frWx=4%A%VuCxXZ=Qu
zDUwyU&yS860%fA9FV`~=v<o9pN#R4LyQlqL*?qC+C&6jNnVm4$r!le9fd)vnC1%m6
zJqGq$rS_FhC=i3IA^)l29Z-Wj-BF(BCi0%*ET>uCebt&+r8!Y}fu4NHdl<-y|KW)=
zJ*ZhTDJw+X(1;GtQkVFSXquQIZ(M0C^3X7@nnx!%-#nfvxPzBGBLd-`NZ&z%fOF`x
z;Zf<|<++&kx@nTDb5xF^Ez$h)U#&bi;%bHi(CmsT7yY5_upYWWvkGOiYk8_?#bnCr
zm|sjT8Vx2+Fdt^~sNz$0F<=ZkagMT1TXHxCUUBrn?;d;eRkNmK1V8+(ube&i5)YT3
z5rIr75;m=^FN8&6^}@qC;S_}%ECGHA2AZV~x*v{Xf|!{>vOkd%U4<)NKjJXs6WcyN
zFBi9@;8%X=pY{E$&tdkR0xAI^)1;;hcF}=Ovyq(Bu6r1D%*n-c7Zu07-qOa+G%EMx
zBRTNQkk8?%01H1~*5fG`Pm@xg|A!C^ty$(|M6tv7MPN3g>s)_X&2Z(K*1Lg~k({0A
zDRll^#Pk#N(NOBRP+u-d+%bBfZAgH5Rca3DggtA#LE-jK3u{GD!yMZbMaYQKt|_(i
z{$6_}2c8Qh+938~5_^1VT-F1;+RinJ(R8d@lPJmxEVqB4`;YM0gcCr}D(q&kP7M`~
z(c&$uI*YofmY3MKD&|32o=ZW`1Nf3T&6+ZCkce!Y7EF9pKB2|QFMr)V<~;8U@?MPT
zX5CMV=`k?*2l`wgPy3GHx&Ku*1mu4B0~XO1T_;$nBT48h49kCgh+RpnPO11=hfxX}
zH+2pDH_w03yS5*uT}uZ(E?VZ0wf)(yKscgWE$?Dy=k{UJrw}GUvED0i^mVVZ(IHVz
z#Sc6KV(@#Xts6MY2s`fg*=w6NFw&5TRi}_L!9)}U$*s0qdW_$5k0%rW@)2^rC`VPh
z*il}b@{RJHLG$*I|3he8Zq~35&4LR^KbAE_;*7XW+n{%o;H|<i{K__UCmBkZ^U@4A
zGfe|B;E!&$7Y$T6szTN<1f;P9T9jK4xYlGe#IiGp8h7e&_4TS$Ic|sd&AQjE4)0{8
zFl0T{<VqWOr~8am$?^xLgvA&%l4f#}?6Tc{9I@lk*pBF5lU2C;c-_^auw1XZHU{Pi
zgD|Hr(j{s2*d>vb{Hq`80?qvTt2?#s0k)3X7A*(P9UEixE@Mm*!SLSi$aqoJHd{=V
ztQ!QcCa45nRonjc(^kgTGnD4GA0>r3OB)emyzFz!mj4aXo4XX9H{p^ckC1oEih*nW
zYv=uSyzK1#yS_R*GbgP0t5$zA;{Cl(k8~3Zb5XaMrPDq;;@CL1Ee1($o0>iTbUIkN
z`gp3%@+;;GFvQ-_k)>F?vT-AE9qD?NEL;u7t}Upus3Y3cE;&yhPsLgnVCOdA#S8u3
zjL3FX2o>uDY-_ul(!5h|rPAO0Q^a%g7cyt)$l!UrLi$u$i+sh&P=D&X@`Kf1((ETK
zD!??1x<=t~$8yTsPVq-31O$Qe9|HGM2r_vtqlD)=N+$!VTA(<(1rf?Ko)vYNJW>12
zDjxZGKUInsfgNKpxAw{l>rfV=0j)?zO=6eVZpw833M&oMN9uO+cI1UP)-T6DcCG&w
zO3XFqC9R#Rtt&(xGRcs2-RREG99rYc1XSsG|6`h11j>eLYiEG1Qb1#(;o=`FViZ$Y
z;o^XC?MBx_Fj3sMKRPk2v@Lc9Coz6FnE(Dmh+u9H!aeyCK7B5QBU78D{OT~}Lh_ez
z!P$bu)o1&#C4xEET|!&1H%dfESpxRk=F-2;`I{5UT35raDzF{-HV22O>X!j3HnGSL
zvay@Ktm~9-%h4?xzYBQogr!c>)F$ejFmjWF^zQ<2hS^W&M;h1?$6h0Z?Pi<oNJ3d|
zW<zn%I-eGtNOO+mahWQ&;1#QDtd##Dz?pO}X!=Q_Evxyr1@0G8q%Fx_8$KA<H&H{|
zj<v62U*Si<UJO~jAbKP1OR@QAx}z&WXU3W47K(ufokfrJ$`vY~S;_wKa@{?^t@^m*
z!+7`e3rNxvgA#2Ty?W1u$CwTpGe}DiHU3Q<q<r=TPI^B<TTLrR63zp|gqA_Jn*!*E
z+6CwwH0Tc%GKWT)VziLKYI|G9G|XADkQ}~$9+{*{4-aKOA3g9sL&rH|PgjLAyPfnt
z7Z*51qxbq2+Nwc<I1C<sNlb>T4Y@y-B{^7gi>l&&>tvZgf4BHp?#Rk=ak!Stft2O?
z9+XOpfv*Bj_Q*Qd%L(j1dsX=qtuRV8%75_8<A>iTQTt9?6}~Euh1(Yrm@Hz$rrfen
z@(b*)OyilmPy4k}fzz2ln3c!;V4pIg3iEuo4MP-f7CBF_v(R0m^sZ(_wfn`REMAh%
z(A_1>xSIdAGRj{*!amWqqmRB@d=>?0%h{jle0HVi6yCkDMG6nOaXWFWqYnvaP!G$H
zPsMv)X;9+$N`A7>VEXPaAzLl==67F|(o&4XnRWPmRH14Q-0{c!=mKPUc2{nZlI0rE
zeM+D?_Fin`cCFD8FZUK~N|jJr_Z&#L5cXOj!=7|sLbY7P0O|5uw7~y>(k(Ya)gdq^
zhw!3lnaCG$WJ0`L&*rag`u#lrb>$R6bN(mlCO>ryd>4i_z0uup=(86qtXFSnv;qcV
z%+L%e_y%L!aU|NMvO0Sut=?+qjd-*Mvb2QDHHROW=lE)~j<lB>)q^(hb1#7!a`+sN
zfhm^cShKXiDpNB9K^zR`BE`dY&r!M@HzQun#TC|_$hS2}uD6Z~ww)%&Z>l$6C9nWk
zayfl?wx0V(unpSmxB2*7HEY}t!|yw`=kXca`_IJ2zSh&RM5ffJz$@ZH<s0h+THJD&
ztJ89%)l#XaWH_<tLjYg%cgCy^a7!J#nUgyj(^Rv<a&X+nYrolfAm#723u`P%|A7V9
z!hLPZtBom5OXvuYtY^r5E%LSD*L}wTEY2fIi06C6a)yOstJy+Z9@ZW}!+jr-ojSP~
zb{JuvHu~v;Sie<-q1R_S4OW#k@y9>H@<k)xqF&G5>>BFETS@O~m`DqQ+PwZl=rn>P
zx;YA?UfR;XD`OkKuL?z=II~kTED`44t%pZ)3Are9vq}0#Toi)^7V1+=LZa%^o(Q+$
z_Vz1(-qN3T7ABd_Jm7;nJE~^G%6sYU7wDa$cWl>tt$-!I>g^_)l>2B42#ll+?o5}}
zhzv|UJ)d&9#rLTJA6jME+s79)d?h6JA<l`&#7JM$WQ+fma8sLK6`;cP{^4PaA)NFI
zK7?4de^LE*3$CsiZVy9{A0>HSwzoV!z?X{6`op+=NmAj-i4r14dvI5&peih06dWPh
zTwbwi9;TY^|8#$*euPxQUv|o2Y0T>Zd}pR2tB^g$v51lsW0pj6;FSE@G{W5uPo|^2
zG4gPro++`;=Vm?dmEg&l5#;cfynp0A6?jG$BO#aOvIc+y`DTle7?y+IBOpC%P$mZv
z3m=~bOj9FrjfgT~p_HmI;;7gJx6^H#B|Ez<YT$|Soh)oZ;WcuiJxFwJ&=cZfH+{9K
zc4J?Unt0cOPR3Vy7GuVB75-^zp~EzOKwz^8cgX$2G?$~HOR&vRwXhBfH^QM><t7w|
z`$WL2q}I?JY9d%xQnv^8*>)eM84;L6q!|^TmLILLWtU@!@hY{V1tWNwE88Q_230fE
z3TfO^HoenrAuHA#rO#)+eI0}*V{<HUM=(0)r^j5tyNz0-^ggjm3}>`Wx>MdSc*p7f
zRH^r8$ILs*@zsew<*oJL&&c>WR_JMiS?a<VzkNF+|5z4DpHxkyZ;f5s4^Qg;al7SJ
zRX5_Px6RR8O~3lP@_C1pXR9F*fsguSC7?n&9sT~v4Z18hEv(AE_$yWNEGD;FO*K`T
z;c0oKCDY)LghC_*><hRawN3Yz?vB&_GwIXeZT#Z9G+7MU;^L=sA0tZJ9!G0HcZ)3y
z<v-E<n*f)Z$G4^yc?{dIVis7~uC;ZV;y0FQ?<e(FJjief9Mzu+=!gP4*W}i7U30uX
z&e$qCh!<L_O$C~c_^K0^?Z>HU7!Ns6Ew{%?AoA|T=*Snhrzw-C^R^jk^VDQYRkhP0
z^<8OFM~_TIk@gsBA)Cjr8MjwFrYWUi<{JhmYuSaW&NqHpIE&50gx}##$#9iIVQ`+C
zu^|KB-hpteR}OAhqBTMv%H>71+1orFButysOl;tO*csY8N$WAmOSj@vF8k65$+%i>
zW5X+b9^fZM5uGWKmYT$_TmZP&%=RbItkuh5FAH`z8v7&RBfP%%62WQp(_y0lk+;Gz
z#WG<;>kALmF%2A5O+$t#*@^kPSv5Z$uK)pgr^iRDW|u&ks44~_M+!fU_=1@)lS#SD
zNmC*z#3;1!C?t92^9{gyksFw6-eb*6ztRAaw%K5v5I`rl4B-!R(;xd)co5L*9xkC<
zYNCt);oUoYX7d#l2;&eX6EI6FC(PLE-4Vmsj8P9}93;dv1<Yfo(3Iebp>2XS7#X7!
zJgD>35afpeNn*tmaNQu(@PRwqnt?D_%}r7H<V0oTN^I~?A>sG5yrOpy>q4rOFI4&n
zO5bxyCKvn`f7LMQsY}6^c4Y$pBPbP|qx$myUlq2z5)<QxU!%mfdlg!Ib#h<jn|l1T
za!4tvA9ms~!$miX?!=ro8LxrU8)ua>jTMjLt$&C{Cj-44@#69dE~0G^TU30P-Rgy`
zu4@>1eq+v){cyy-qh2X{r3qdB*1S>JIQgg|yYWy<EQWLqy<__U4WBLruWj;e?6j+H
z1~oz=nhLM6C|@?aT6aITSN=8vR*sT1zWk1H)!FP;>~^IToTpuE^78D|B@+?1M4??c
zF~VQ90>e&29o9$gOc#ifwdA?g3&ZjG40{nYznWQ>dZ(&?(d^f+q>Je*1VFY|SgOX`
z@8Ncaw!0u4eZ3J^ybrowB2E7x;M#K7_zJDyj~>#qPv(qv`{4ZOVVEvF`DtF34@Hew
zOfWbEUF7&w)#7`vT^YGIwe}`ll*ChOj|TZ}tw~e2ht$|^IV_TaJQ0#^xHIcl-8P$h
zD33Y3(}rBg(=^}L!;XV~uAdkuZ=rYb1{I7Rj?(E+>P}tv@;_5DkKQxO{3&Vw^xJsM
zGP+0J%VG9FZ6T&T((P1B8UmCe0g)iKT@ia%><#j|Bu5#FGi4vEpuaH>YwoH>(<X~P
zBso%un8_Y!HRqC^k-f;Q+|<H5cuoV{KujIhKYrsx-@7k1%h#CW%O)D;i_Wy$&<$?y
zA0;J0e`W7^&ycgWI;!4Rpv&yE%P^TTUot1I(R4UOwU3=aQcj+!LSKQ^-XP;$CuX%+
za%b?jtd#!{EUu0HO50lbrLdCbRwSJmB5PPZPgVV_TyCj&KB529lJ5>Z67|ayE-3~U
zX;v2S5XDW|naCFFulk?Sag`k;#gCro7M!pgrLe5R`a2nELw|rH{7xA70!0Cf-NP=A
zym8bHHLJp>@gzcl?z?;?DWm@(7(=7!>W31sEzviBc$7Wj@@xm#d{E_|oloB{1xgZ_
zQ|<JXu-}z`+=&{Ugp;hid}Z&JZwXDikaU)%668>F#r3e|XCH0Cy!WZDODA1cd#-K)
zVBLM)(Wx!AZn3GV&IT{PMOAJM*)YUP>|@)+x}OdKxQ>!kc|`&#Z95r}d<bkn=!_2n
zKu3KWBO7sR$aCJ#(@g<wt&n^{xJO?Y8bAL<&n`jV5Rp<nXV|;?_*J^JEB8zxr<<=<
z`}*j|E9uwphjQ+6`_-C*oJ~YT_~J1H{HJstq0QRiJHcR<%p1<0RC!t6fk4KEy+@gP
zMk{9yopG~_k+8!j>$#(?5<7GGIs<Fe5%QQ2>5GEK3aMHaNTBZAM{`5X?2QPB{J3HM
zjNtc@)>Htu3aZW}lihJ)O9zLMB)4Plz+}@riCT>ok1+ZzXbQ6un4}NmiZ_4&Jd4u^
z4D8Kkyd19#Fr2F$8XQVbnVEDOw&>@%vas(<fh}~3qI9zuDpkAuNDdSR6qP4NNTZwN
zi*Tf@2eR}_qDcpthH7qQrbXp}m}kZF0QtJbd64-p_!Q_wq-&=wAsCCkEZ9?W`s*R<
z1tO}cqtc+$E}zW{xx5=$-cKFA$eluHkLzt8_L-Wyz-mLNp0DixLO|y@YR69cy}DWj
z75^7{egEA*4{ZOLT`NXzI*vY+oSYQU+-PJ!QZ12Xjn<d3r^dPaiW@`VkYhp~N<GlU
zjF~*)s654J8|4t~u@`+w{_dK@`fEv&kbQ#lKs|{i#MxF3z>+~rQrS>9Nlcu-Wp9C(
z(<ICDVMTeuPfJ7K<3#Y6nGb%8-09)g1)&mSRcKV<V!lV+dQV0!Pzf+L)7(U<9a7fO
ze0u%s>OT*`q2g}gVHVH*ti#NAQA$Q9=l{&Iuye9B<YGv!m$OL*5ebjxi{F9L4u!~+
zw6lI5*5dt>DC8LgT;Er;5!q)+SLpTJgnXwGEfuyq!E#fcyPtg@@_C4JBKl?m{SpiO
z^y^|tbrTb%nQudZ_T~qqp0cdQIS8FU-Y`*~l02H)i;mXBVvhY}B#5jETW0A@A8#G+
z<2j|YBt}Yx%gJ5Ep+o6q?m%fq-MX?4M_6`EJ5qiHo+G@`GEbEG1bTKi&85^Cc^JDF
z?*f08IjnY`t_t)%rD#a=4?>s&$;msp(HG>x-m>tX!AeS<^f{>u4(bDU!!i#xJpMyt
z&x>_N4LhHo{zF&;a@XXUuwk7j3=z^bM9FAyBfQyt^#djym^R&s+&3qZ+=9NQaehF8
z+^6VHtVAtvnEyITJ^aFoA<rE{L_iDOXq#i>{=4K<_0_@RC9lK3DroaW?-oS{Ut%gT
z9|kE!rm{Vk1t;mw>8SSPs^c>`&rBQ}yq!C~*=WKOA$a-Y6#T)$qIl2@d-zX_PTo2>
zY!nvw;dcFSR%t1LtmEy{&Z0&<!=X6V_)-ux6*=R!)n^s$j`IFz&9T5$_@$J7c550r
zfUa$Vch6uY^}us1Mm;4Av0DqWTY0w0uyn7?@FH@vZ7AU!<VQ8tE2+XGEuHR}_N%Fr
zl5p#k*?Q{mGYlNo!px?)pn(bdh|Lj00A190)GTgpvYinhxI`E5Th^5C#)6Awk;`BE
zs?O4UsDwLWv^rwE$b3WG?0}6{Oh(Qe_f`AdT(7^6<`YY;TsT2$u8MefrKATEh=S~Q
z!b}<QD*KFMAM)cTkvqBi4>M!OfVznSW|;?EybPtbl~{W*h_1qCiWds;KB2&)<-*@%
z(mISdTYKHQ5x?2;r@MZ(1)*&(V?JsaD$T$U1CJ}o?7Da<&G^6R_gdyny4kE0;nua$
zw%9&ontgBOFdRAi0sxq`nB-2!$_d-bN(`Qy>D_h*?|Wd_Rg$WX>4|m~HcL8)c>70O
z7_shsY^7=c<~z{L6R|DxjXGyTyD6qU{#?3UanE_0Zh(Vymd;aCr>03hIV~hi$_G>R
zQ+e@EG*NFDb|HneHVkuK=JE^kU+wUXih<4t0Jax)Xk}mLK4zq-!jhtRO5`R<b$Ik;
zmBLqE^I)6#by^94IgltX<NMqCHf4LMUuq10K`I)$JUJuEeC-cYM^aUiBXFm`^a#<D
z<6$a>e9q!|Ov;IZhEl3!j&G7S9tW=f8)M>-xjp-uAK0Gw3uj3G#_BIqY@0c@37^tW
zlhm7MKkmyc#7HhmBA8*@3+foesqW&f&3X||^6Us#^9{*~ocJZ7I<kU2Cl3{P6^0Hh
za#Z@$?E#l^!Y|q(>O!nJDuUXE;Olq_RQL=JSi$=^FnZ`3P>yU)!T9@#`{3?EdPE{G
zbsPX1OK2QbS0w6P<6Iwb$+6Xn981pL2S>A0cSKJ(BJmZB98}Z8sw5tXzH10Ij`b6z
z_eBU@OM#ZsDU2Ycgx9YPv6F*{KGhn-=CF6b{&l6fnNlR1?WDCPm2w}eulKIM*r}KS
z;DgFAhfUi0MW<2L{(GRzqvnl{y<AN|tTc8l)}6EpzVWHD_KQHL|4@RSW}($p2*5MZ
zSn)`(XZf{KpU+_zq!r@=yDu}Rr(1ueoiDVD_)hK2R6I>hS}x=&8#d^^H{V{q$`bii
z=eh>6)6zFQ;<iPE5^?ye%3ty!)_1z5=}5T<8LRGj#gS6v_*ZBHqbRc#MSo?7XZrK>
ztEY=$KSmuL_eHSW1$5(jkrLnM;<AgGD?IS?k0Ycl=%K0dhQy2ZtQc=i)s;I&a$T?P
zD*MDZ!6mY0>>c}P0*Tw%X8nHr4=vabo0zIXjfK+{o?a8J<-PTRrJf1HTdhJpfrQS%
z+QyT*F8dhh=_#_?=tZ$a&(u{Amy?OE^Ib`z1HTl~0um9?#;+7lLC5>5*;ctBA{59-
z4Jy>mNtoSbQHy(d+uFL-$jmfh!9%%RDoIMm`guthW0IpQvtjhEGAY%QDa_4JTU8!)
z0`iM6?wf7T;AHDlKk{AWatnGCeVaYiWdi7HHa$kXM6IeXttM20{WF!IS%SHCY#1MA
zfQ_S`hK5%lk%nY@gE!H!l!@8k9zSWN42vwB=Tj#?Jmol3WZeNFiq4doTgArT9nBZS
z97LQ7t;D|$?IwT4p*Uf$x6kt+7g#`jk_k*68<&|?NHy*91^6z)i@If)2=2<Y9L~nd
z)>A7<(sxtDkLF`cG`(>B<`FM`rX<vP6P}I#zMa*NSl*VsiRbj&&2`_Y3o4dwrmG=~
zcxo?t)?5LbNNEb+F!}i$1n*GY?rV}@tKO6lgh7#Q-kN)3iG{~@%O?dt&RqHaoHA>p
z<vze@N_s8Vd&kZD4nhuC9MFy1bZKdf+K0QrIfWTrF_%1FIHS$qCwuTsOY@YFzZuIm
zYlU8H&xlw$R@iFVrzu!O9=I*pCgWoeu%5d~X{!L9mw109waZd25zvkdQ^<+j<#ISC
z4-C{ZkLrKNcD0qrjvD4A5iW<B#lcNkVF?<+2Eir8(%LT@fystCRMumvv$QgU`9xl7
z%WRhpWb<|lF7HOMn>8oIdfnkC;5C|*t0(e;;Ul=y%UNA6V2K^oYP%DtP-_F?pL!+0
zQSW?2-z4~Rs<gzg+ZM2B%`oAMyLN)u_-;m-ZZ?k$l~oEZRhJI9xAZTBWcTLlr-Yx*
zdMHl%X`Zz7CT8(>_rp%sI<>$~=9KrY{6v{vm^z$I@qEl9?=BhF3`joHj9H3wSMoFG
z>mNe$%OnAvbWw5w0FN@(>I*XI)GdyzJFF0`uLt<BR1Hyd10D93y%9TpnO}3Bf&nyl
zyy+#abmw`91;Fh9xw88VZZtZNUl&HW@1l+37_MtP4HCFb4RSTUgtC3&YX1|-8fquV
zfT3$~BY8NY87O?_)u;b4#jb|5`L7vtakSkF^G49kaC;HK2{ux*S;JSUCTN(*_BrU$
z+#Y>C>A@g;R_pp=G@N?w!MgXmVp3=ULKpbPr>3|qT1#wwF~>_|vSjq|67rp*?|Yds
zso9YW^C^~<hFbDdydiW}ZkdgiQ__w(PxNNW>b~k{`GG++O+bGFxXv+e`5?8o;-tRG
z)2k}Vha({&*S1z9+lt%GSoo!RF~d_W%dvWeP38kP$EAiQo!?TW8R-MQw@9<CV0vEj
zS_1t&h1g-Ec^YQ~h5WNd&XlYwvTc2+C{ukn->j-ap&dsma3BG~G~W~+K?uFEfSR$4
zekG@fRr;1&t=$)Q<xz>-WzTEcOE$9>Tmd($C)zQC76T`Q+R{Hd3ZH53?$Ab^)3w+5
zunN5_aNRaH@CGTI7OGyzS+`o1z*IsGps2T-8a}T~8xKESQ>%M)C(J9@Y%RNToq9gT
z693t^>ZY$|J<Mk6Zxa|3(c<5`uQoZDv6-9s=nG6q0uCi8^Qs?AHbEzvyBZVE#*;WI
z0Uy4f+*fM<13;hm{1aI?j)X9q-N}L?s@%6#um+Q6p@px^CDpbrhC_}PMyumiExI*k
zi9-IXj<&toPE0AO_=a9*M)c*yPc8o;96#_3lJ38@)hPHGqyt!@z?&hB;0g~~4c@3K
zN#T4O&a7gE_~cknCe?iPnnCyMn5A@(Oo`#|E>0${$`7IgUzU#Fv#(pchp&U(=4<-B
z+z1ZV5BRphbM^C!B;&Esj@|%Jw}DbP_kRc+#95AjM<Nv#8T+`;3s<s<JpUn>gQ>x%
zyD~rhxUf6nf0?3s26`}Mhi(j08K25W-`J*YMQdYz#M{=gDi|G@yJ>ZKz>`<d?RQ0L
zeVN2<;CWc;Hf2gK>)m;;ARt#iuY@u8@@5olEfW)o$LxT>J|oS3xyGp#XWQwRr~h7q
zik4(lA)hsGQ)SB(46zPz9J#+J8WZbp`&6?b?;yymnBtpnhbALr8JHqGB|T6_nA3?`
zZw27uS9I0;>F}=Yu%oSuXqVQWUXkKh=bv7i=+p|S6+uz%r`zRD3f|Ek>V-nc?@Kf9
zwAf;wve+;3FT=D%RR<BW-~%!S%?ND9<zn-U)*j+|qVft`*R%9QDcwJAqvVy@9YKsO
zB|&7LG1wi4pYG)@4q<&`#5uD1mMdVPNlh|+WQOai?<|wIfLu+`I{(?iTG`Z6W2YB`
zpR2MFXM7RTw5dV8HVV+c-nuTb+HHa-e(baVl=Ft2#K$3Ohw-xnt-{v9&^|YP4#_O{
z=bRLm*auQN%T{czoTc`>&EZn`sHznFsh1V<u|jM)VOt1H0#B?duF_<qg-=?z3p3Yb
zb*FVHE<R&3uiLO{dt~r9%(!XYZQ<MaR!_A&EF9|2kjf4FKYpwZvO$Ue`WcOCg2*Pp
zHtpkWRh``NUa!(pm%TuKNdR+@cMFfJA%`I~U8svO@io#25A?J@$|82xEd-`5{0P1`
z_-T|z?5O5}l3!zNkbbH6n9_f&lcZHy@pFUXQj?d>&2_8O@`zOUbbt{+`BvWYi*^fD
z!$Pyw#Ri+%5zn0BPTtGqAfJ>KW%jR@AJ4dbKCX%L2eJDLZL{dyBxtvvNb-vIiK(DG
zWnhrdd#XvGfmSx_cGNnCv*LdUlb<hCxG&0DzpmTxrY-ka;00$;6Yn-Ced}`HZb(W}
zZCSpTH?ptFQK}mUjjE1h3U@8bK9<+#W+6d4W;f=VqA*LSQ8MCeF>h56M>%s=r?qm}
z_@j<al$u&z0R4;gPBKE;c!@2=WF_*TKxa;z5Aj>vV&!z6Gq#MiWc&8c1b{#3Z*HK5
zDHWfqB;639#|SB*BU%bOPL7x1P1JuW4oOHgOic}+60;nK?Ub2O^?r*#DRX{8J36@J
zFVhzr6>?GQddal)@2+_Admk%K&KXZGjII1#krblw-dbYa6v^3f2|1Yd(lK(mQAZy&
zaa?6rk)4lZ*inyblse@=(53ILitjSP!f?mW*-jpa0SKOLJ1W6BwU#e=Us)}NCgOaQ
z<)RX)*~;KJAa`l2IMlkx68!_2?@TvdM*XJ0?a4+S`w+GO>_em|boux7z4h<Es#@J}
zpp?41kAK)?-HCT@6cA`N#aC-KPs6@ikp7X~cdy%hKA*S@tp6>tx@ppxl<0sq?XlWA
z4R2cuB8YAw8@AkuFXu)3?LPgnte6eZ<@>x;hCAs=U~|+hs^9wYIMbDDxkOSr^TXCH
zm8yQrAS;ObHLAbTp3{{{fs~qbh7klB;ebXMl+mV`eH9wuY64A4ZzMq&LsTxQ6U^(Y
zqO~v|sxQR3;zbJT4$1v)HHNhP&B0ZJ*OfTgLuUEHa&Wc^Beuvz**qi*0J3{iSyz#`
zog@pnde$K*_ntXD(PJsRNj^Gq48qg23t8Pf^=!erY>TI6Af0x7j*QWZRwRk;A9)ZR
zLq8<_-Vr}3$l-aa_`O6<oqtrMph@cmvODYMS0<-)JJxr^oWoeRUg62VO`vHG5mf+f
z%z0F*%Sn`B+?Apn7H))$7qP8y_a%#}IyU{?%5j^m*2d{9t>)uDIeUdWx6{INBaAn=
zu8gb!35K%amh_%yG20<$XGVPtJven0bOQI>Kiszd6we}{tCXbEU~%UzXZKU!H1oo}
z?Z`8X@5ZhaHf*vv#AvGCeLDfAn_O$hDgB4Q^rJ>UekAIq?dSx00F08@yyV|FwyRe^
zGaQXl8}%lq@_Blwve4inj-Uu)YCR}__9A*mGOUk;l5=0gLod@4S)#ioe*jw_y7)JL
zSalkN)#L~3LN!UsA%vH<hVx7wp!D$798<;fuw!XTC|!46MRatB+_IDqApAz+12*rR
z2~HY_rTyaU$a1@{m0`RBPcANoj~hPrRUI~cIbwUqkrZb;9Ef4Q-0C=Pt!g_EZziK@
zIMqZAa8V51@(T5ve|K*CkZrp{Y|AmaP+k$*Ng%L=`J2TPygELszuuE0*Drn9wXgBJ
z|H02S-v@2j5(a}egFp}+gqiaaB){VtkOEUDNQ=Z@jVe|D>D}{JouC;cK?F3+`1_+g
zDCM6ZAB1g<w1t;r_EOb{>5IbI6u&&B{A4?bJJY6n+9A;#JGs!~Oo%IPL;r>S`=3XC
zTf~g-vSt0vmGFmiTxPL50K`^?CBqVkVI{g;O6MS|5YhnGdJlRz+H%F@^y+J-yxLTW
zb4SnuuGN$7OOJB=G&t@M<45+Oc9bah#e5<qP!(xvf=|hm98fV?V;g~Z-#|EeH;fz~
z@CCsND$JLM#Es9DdnAss{-@|z`0cpv-KpO%sM7u%-__qa8d=(6UOrpHdFOy20bFu2
zzNb<9Ya>F_mXJi|%=scImP;{^@T@{7ydCZ@s@$ex<iB${`I=RGi|K^rh*?S9Z|efF
zqaS?@n5cHs_bB((>^*+gIC|ir?lC$F2Ka&AH3EmbFfvNzMmygrw|0ddrGN8%hNNWU
zL{`OLr2{9Qr@Y9PT0{9h-Rwz&C=f_0#1z;+_$JA<eaO-&;ZXXPe4mH1w^B@@!#B+b
z|9~<FLD>lGxCVEn?=O^44$rQph1~A*-j8x;j5d?LmJ7O_EeC%}cA$H#c=WQfw4LXh
zMS)LO__)L@Vw8tnS0iNqR{f)3{@acg<0R#bfU9Va!XO`dj33%GvbEi=j#C#&n#zo+
z62lE#!%|{^=LJN3{$e%3Bd~@~9uJPvn>CWxAidlb@-X>?As{E^m}_&`%~7X(J?lj$
z^Mn_F(hr@BL(CT`#5e<h@jxvRa&rM}Tp|^o!7+xfwL(>e%!^Id^cDR)Q?K#b+xYKl
zI(3^<oz-zK8AyprcQ(jandUY&5Xs9oKUl{&l)+**aFqT{E&QTr@7wke)l^<waKnrb
zY*rZ6x4V!}5J#<UU2F1y>wEV;Wq#(G2EI*xMVlEBbUD$z9;Rzxs<I!tU2gSP>9nBe
zaqZGZ?_~Cm0d<R4Eg#lu`Obtmf2v30011km2rU_@9%-YEJG$D&h2yFsc4e41{_VC?
z)QpuCR8?|O&R``y^ewx&N(WpHtMkt=e>0AI<D)Ef#Im?x$SVWB8$ay)_8t~^HzW=#
z4Goxf0mtTcNP7h03OZVl&|Qwd+Ufg|F0NkP14X`>jyg6U{renc|4xvDHmCWxHJF4v
z#>C^HhWuNYyT#sSa{RVSaH~p6XPzo>`gDDgtAf1`ZN!dHYV~EcI^aFeX;eSt+*!6n
z`U|#IiKIz_!H4mu1)-djX*&ZbF?u@!WjEJ}Q7F~}x|UU|aAn3)TXb6=DScKH<S0|X
z-mIHL2?cTwTuW|Gkdfg#g8l?1@ltjRuBh*z@of31rfSaRPPAJhXE`9R$nS&_sA+Zr
zoO|x8xtJnXMypYvhKEUK8sBM1D4PoT@_xM@BTz7k7v*`LiJ{x{W-}fpQQjd~t%b?j
zq9`4v{}`qCGX2&2u}}nVax5MNsNWaH%poEKSc@zcgw6j94t@r6jWBX3E(a3}pY$#8
z6Xwmod)iw|)_hlrv;~#~pa4w;K<?urOQs(_=0p2D2-P)g3Du<${+BP5V$dRMLD#}z
zsA;l0^-_|dQ`~*)0{20vC_iRc8t6&2#YQ;zIv02Cb4@AdNZ)n}pUC}eT|WR{m4d&T
zd0dif>`4&fMRj1r5c-M|u#0i*^wpewb!5Fk2JKmg&SZbQep+_t!giN~$%fZ~z!^0*
z@~+n7ug^|Mo;9BEbVKo7p?i#vlc|wEE*&17dKr2lVgv9SZjc2U=7Z~41t%s88tt)*
z5qn92dZj>GD}1VFa!HC??(w{iT`s41eR$N-^r4x(?7G?e4`IoOA-d<w)<)l-RhiUZ
zM^2lQE2*2OoEu!E7T?WbInvUybEy-FMv8x*(Z!v0{hywf&`1~m^woANA`t`b@2a45
z&0WOEA-S5`+ld5BPZOR<Sz&rgf9->q)EV~}Zp-W9Byx9wZ!K{TUmU;3^G>#pP8FU(
zf|z!`TBVxYv{@x|8vr$|Xb%Cq8GuW1k`GNfe!*kwqU^Je<y$t)n|Wq<?eP3)OuTF{
zD8i5cMJRV7m-KxIAXj1LeLuOE$6e)I{u&7wzb?abQ@Q%D)*~0`CsGoO*=7y=^yd(;
zp5wcpiK@m-**V*ihc(_p9%Yk=s<x3+C^affAhpSyh{Du<GwY%#fI`OXHM5&a#NPR>
zBVN^bj<)!s7KyWrnSIW?S;B|bb}7LN7|zv$Xe=-<5(YDv*wtm#NBsRYvjN^+lW2%2
zlAI)elM}=N!r9zE%&tK`OBJPeJAu}dDNNpuXje$nL=R%yzSvrf=vdSJQ5I28-WNn8
z*$p0ong)zQUE^ipIOI=+H+Vk*55LoOUMswoayvnSB+q?X85jK&7GVsERD+{W7T2oL
z8>><IJ_`41Tp-h&5X)<vVV*T}z0WYO)FOwsXGhxWs<>7mu(56`gIS=~2ooFX30AG`
zq^XNP)J}ARivcr$YpuIf@~>pcpu^{ycHA5pe()iho>zcuwbd8pV?j!TQrlBfa~JCG
z1GS__3*e2$u4|O=W}e0W5b9S4oH1ZhtLx_*l}?&}Nxjpmo_T5;-VaJKn72`t{fB_Q
z90qU93u9eg8S=GWyjvt!o-zTjQONE6dnS~`Ogc0_;M*d8l?xm4{Iurqaf42CFcmqj
z*d+n>!<i)H9(bm|bTp`ndy?33QQwIckI#jNvhY&U<$H}sI!`JzMCH-4y$s5GYW^JU
z;fe8@%T~udwCMSoC?mR6H2_Gu5%Ei!eor^coU5vDJgqzRTW^qU41SuTVpl*O?kXIs
z9is#(owP)@O3*0dlz&tVU<!arw(W6F4GN|q1KyYpHj9N)Gchw}*j?s-W;5=!-0sO*
zBDmzp))GOhN&(l>!8SjLVM95uixYt=t{V|HieD(Kk*y$2S0>cnDNn{+YgzGFMP3)$
zsGt#XWJuHUXg%ekTRp7U1t(>e;Y^+!MaelZ`*d3<2W3xHw=l3SezU^1J-DbsFGM|+
z@bKi;apTHh8On2@hsr!V-I3SZ2r|w(it#GGz$FFu=hM>i(Pt2?s`eDkU#!QAm7q#h
z-tdY<H0cM|GVyL)ttD6t>}wJ^uj^i)X|iCoVl+pVara4eTSvc(D)yPok^fX4FTYLZ
zMeSLHd?>z_?}f6cf#{OMSj8y-M#x$EMdg<}NaWH?gmMs5N5TB1wpn0P3?f-cbSajf
zS1**r+~Rqo!l6^$G)}@YFQX@{nFWgF*1N)d)|!QDUCZPyio+h|CPX`AIOOH+>8HF8
z>_F?J+m95sQ~GeaQ^)xS<2GC}tPfQdpeUt#-Ugx3G=$Nsvg14+yUHav#U#WDtRG2^
zm*p*Ii0G+p2lZ9lr#EM#j|@6>9&snxcuF3A84EztY^R3Cc8_?rsj3ZrDEi{k9yMBP
zTQK)~V2}N3v=a0ZL~jtpW>FvG-*p(lSrwJYXgTNyhLDt~zqE~Mj#%?(_OqoYJ|!fL
z36Z6grlc_@gv~9w7X0`jckVpIey*%~sOtFJa^mQ0Se+MM@Hm3gYzVog6mo4l_gkX*
z_&t^1p+^i`c9$9b9zAh~t2GAF>_0=8SP?XmsQOjcXwl>mr9Kba*{Fj%`p5cK{XY+a
z${8LswJeu5xS{UKv-`X>=CNR9QuezE{Df~(Q_GJb9Jqx&yF=nW?P=imGioV~mr1pT
z{Y^k8bzQQ=;BOvr)OcxCm4CC~Bj&$??%eHjyGk3)ljoeDn9Cfo%eRwu@jm;GK!&&;
zioZ^>A@^<WFTp<&=+yWJC_95^sgA%)Lp71Pe<PLtq%0K}S+kh7GhpF;H@y2tU^qPu
zb}-{K^n0i#?rKbk`%UJ=_R{Do{=7uq8T=$DgYdGHBsZQx<C$~soHZD`;d@wl`P6uJ
zAr*G;@KE%rehmkOVXd^~y@50Bu`PQAUn%}+FB_fvW6|n#rs6nmnX%6ic(b|9AQ>Tx
z%CY&IN`pbB=w^Ow6iMGOu<4|_2s<xDbG_STx`bP=t!3Q8k`8aH+U1eQ^eZY$X7t!8
z&Ysa<khPBQ5x9Tp9BCp+hTZMfe7+<_Q4ljQ*}}k5C&7@aQyn(=FCjZP3<lZ&R>$^y
zqA?1*5xpxA!<HwZTs(5`i@?yz<RC<5?<dOi**U7mVQm>TE=EzmtJbX%ism#3QR-Qy
zZ+EE2t=xh%?H*950m?h6<8^E8$?6^Ge}menABaj=KY4toWr6MA>OJzz_a`QNP*oGq
z{!^9{{^|S-kvd`T`>-tQzVi?&OPQ}Z^jwJI&+hF=i>6VmxC1^{^M?&M+(WwC371g3
zQqDJxrJtQqY^=%m@W_)pZn<nW$1-1X4cd2!R-N^B)h&E2)n<6iF>nxta40XCcGi7b
z2hGi+sZKPEe_Z$`WhaV%$A-bbaB)F8^o{9B4Ea?gWlx0nTKFoKP3V^cp)<{nOA>fq
z{orHd2LqumNGA%!w7_znOsd~KY9E!{PqdOh#HJ`B_I~A1D|U61LR(+StwyM$g#?@m
zZ}a-Lv~rL<qz~c>fXVSbH}^|8d+ya&<{5mWU!hhIFxiHV=@k+%3mKcS3CfaIvH=@O
z*48!^y^M7~j#XuOw1uZBLPayaF<)tA&_xflTq!Sg!!yC0o#Vn0HjWNT(e3|CdSi9i
zN!gWf_xK(v#Y60KXNnDolHQCLY5&TfDO>Ny?R)<ggC7UM!#pi=4Xa-Tu<vt1i4BRK
zx@~P7enBpV68#`{GV24aT)|hK2{L{c(;7Cc;-v9<-0(h33yiEJ=o$T-N!LP*!7{&R
zC<Ttfj01K6r?iW68mc!nCRtYlku<C`uz6bF@hl}7)bQtJ4YTXd*xS4EqUIZf?;b+8
zV7;%N&qvFZq{Tj77Us*1{x@DG3Oc?!db0IrDy{REhv79e&23PipqDHGfXsUBFTTU5
z|B7j;_t^`V{0k-z-iX9C3+qUL!qNiRFY1ux6<FyFUEa6(glOVW4Tx*Ly#tPHu5F(1
z-spalnuAF>Px!5f2YETOS@ed=v(|k6oRR0+^^Yix#f$eQpyWn7N4f2mv>{0Uyl7q;
z-`hzdZKz|>*CFSlj>h@FuoHdbFMr@|L_aP+McfxTaa&SNu8Cw+kt=p~Gpj>hRD5Wl
zT!Z=5v3A29v(ek&Ev=02x{w1n9I7y{{b4EqzR&)SR+^MMl1oOAg?Ut0HO6$iE(%8l
zji0|<NoTKPCGwL0hmfM)8a}k++@IOPbeBW5Xe{l0k;P^-ah7|euAy#IGLq3-Z7twX
zNt(Dy#qR2BR);@<mz{=Hciozx-}{>^d%8`wd%g9a-UQe4LfRl#D)w!->51XyF9SWo
zjfs{yIwlZ`G1H<VK(Hv`k5~yz(%d0xKL?c10a(N#8;i8>F{!#wKym`ApgOF(K|a`K
zt<)D-j%eK-5!s*A4TTq*=U$Gz1`@@(VFp=?D9KU{?WNQ}oudf9mO$irk!jD=D;-OX
z#KvAjQOo8`{B+E|*s;U>G-cH#F@a1eS6K^)Vtfy!?-6d7gZXBxg?-8qZWSmQB~wc%
zt+nWOe1P(p3E0M|<`KuD=pQ+Md@oLXN4*=&cu5~y3<os*WTnPvl6|!RkUNAO;vG3Y
z_%|!yo2U)-0e+%{Pibm_rt2qi{1l86{KGV;eTPYoj7Owr3aHz7!-zyO@A=M6oNeTl
z%n9ejDLC$mI2-F>Hr=*9`I@)yX1k@tiR6%x=oZ3oC7DeiyHFb>U$gYd&|UJF&r|R~
z$gCI#*mX@vaylwnrv`q&98*!4$fW{4AO2T8CIXv7zVsTuts}iJ$DdaH{I~c;w?nO=
zZ#Ys$8fZpHx^{dTw5GvC8Cp+J<w8%8wWL1jx0IPI2iuF$62o-aEZJo-z!#@LJ(Xs!
zcuEH>dNz(&^*du3SQ9D$QmBR%Gm|lVc`Dy>nORbQCEqhA>8FuhWxa#EkAdu#85yom
zJ4Qjuwk~hAGJ^N20go7Dy=xzi8^)uFFXMv->aS>8@B=SD!;j{?n&o2aju=Yy?H8nJ
z5nPVn<;&OWmT-;mT@CBkGlg#|{|iRfq)HWCiowgViCI@2V}#Nf8CYL_<A~-7nY)%+
zt}F1r!4{+`F}Ud@UHx#@Qp2r=dL67^+!S1sbRkaBMfV><lZs8j`mA7)d3V6cIB^oq
zsz9#(|8aL#U2Qeo8ifJ{iff^`J1y?+?ykk%f=h8}iaWtwgS!-W2^u807A;QE_wfCV
zbCIizk&&^Jy|c5{^UPUq)rSBa(R8&iVqLTUL%DH?DIoAyo32BCpX%*z1wpA}J%OxC
z06@zz$w;l7BOdWRKX~0eAIG~{lBLA0%5TN+dS$TuCA(jU650Ijh$pi~FEmZG7|gM6
zdjc?$3^R(Ids|Sz+F%A8>lS8+0b-%Zl=omEQMhsIaz@58^x0(CbVThLdBKuQOR6H*
zb;4hNo#kv7p}L0hNiV#?13xQXj?NO9F2@p_GtC*j4x(v;&l=wblOw!O_3tYzC*Qxm
z=GrCcPB+F21#JitR_p8JEE2?olziXl8@7Wpy<Qw;NNC=t0X8*#EiRWdP3!b`=fiaS
ziK7TaiJ@_Q0ZRh3)YgwN2w=`5jh57yl&P^dPJZwX{p=ijlK=e^5F-5jU7?<$E38m0
z<4G0VgdH3iXC<1CBN}`kqP65R9&gWn$01S}8NzRhLUyWV13Q%25|29jyB-?-@~IhY
zo$jaoj*B+`DeazT=FNYCp)Hux(CSma23US!^dw#SDZ;#`^gD>VTN%xgmdB0FU07=x
z|Bp`;Wtd~ZoUo<H5dE45IKOKIwT4XpNE4(S2o4ik(kMP#N+h7g)Ndp!A!pvqb@ihC
zV}+CixZ$X}H~Y=N0GIQFpvKA4E@8&|cBd0Mq2i*@z7`jY&5#krGIsQy{%`GZ{~?^4
zZD}s+9<Dpw($Xw7p+}*Wvt&Rmxr)+#2TqavhUjD@#<xshBM{hr|4r=MxuNDjCF=Lv
zVe3Xz_JVhm(yLvvigAgtk!_xEp=IcUZ<PXmqI}gJQV@oBn<+tSh7y*&XT_`hrr%3-
zLjEhJZsZn#U9XP5WBV~JaXS0^b0jlr-w}SPheyDDO*Mv0K|7)-!uy&CEcDZdg2P1L
z@*@8C9Ym8&almrUO_l$}f8k{+mPb=*v43o=5`1CVK9N&bCZmlfDTqN$WEI<-?{f;Q
z3vjh@=~v(PIU@K*y*ZS&(|T7`&uqeb=ya6cf0&wK&W0K`LV$@^hGhr_I5kFEj|7BI
zn?BRJGnuSDfoukIt4i`E^p*0yqy%I($<F11mGvjX#0jdInVjQ^)d~rWWs?Mk!YLHz
zd0fJV@wG@ihfPBbipTnSlr(+=VWF5euiFmbw8d%<aChijRXMrcx~+<{C6&<F7<s{>
zo}p<m_xlf%=&)X?v%SwB=+48-<nnvu-q~Y9&#qQi=co!S$k`f|Q_i&Claih;pyb6b
ztUYoU!dgG}4q)5u^!N!#a%J>9?*eJhnOgqzjZN4-)jctjRtlYXZJHiWl9el{K>vfa
zIqa3}D>*~Abu@<k^kMXcx!BiM^^ETO)|A+M$0==#)yk2fzLiR?tO#TLz=RA-@5IK!
z$4;7p)jmGffS&eYiB|Dmx@u=KtW*wz0dRgN7pt!+txhicfky-{CewrW6f_go<*JtY
z>G#Zu>a~v8FNz)Io<(qE>o8IbWID&WPLazazNle@D{P8?SOGmd`^ds?hD+yy7d59)
zNMR$H={`xgkqI*K(GQG0x8nQb8lr~VMSssP6m!_rLfG+p>99kG1!rW5Ezwa>!H~L;
zPE{;gq)K}U7IO7o6mmCMzRzi8tasMOnExnssxwYiKa>xU8HP<{#t6FXU+|#BOO|H!
zQ*1zZrb%Gxq#J@sx216gGYFOh=n<ib0@JiESM{SOOwIj-d3?VP+!KRjwA&-TJus9S
zI`;jMx;fTaMcMZxz0py9m6dMII_aY@ti7Lz4$lwN3EOWsMG_uuC#`$}t}fQs%Ag_b
zf1L`l%Y!>1wH0kH66qb$TPwQJ(7&5jxwueJl(S|KK-B&L@Mh&O#H=6VV_|a1(f-Jv
zQHJ5r0$&*{7^y*%<2hdKt=To+@e6kotb=Gb8sDqfWo>uXN8N;eEyGlTY`cS!ZlV^j
z?}UK(P^YJg9VED%=Bu9Rh120S9gFQ(rycv_*u#UvBsHxlBp_%(XBWYJ?B%4-R7m?f
ziiLZAsU7D?Hu>q)-o-7?=byCGQz)wMdZ?DT-qqdBt-yqdj&rAr&adGQJzNH3CHD3&
z!{?eCV^^>SX^YVUf{!2{qdfkKJKsB{U%F9!qvZZwd^DHC(i=q|Rl>$xOOmd}M~Dt0
zy$R)|1?rfCWN)N@14%}1a@$|$_ft%>id9`aXBEdu_Wq?N9BC-3fW^H|u2oq+d`}2=
z*EszWRq9xg36(g2zrhtt`@ZRjCtE6f$d*^!qTGOE2w&;W>iq}8<*d#Uw=AsYraf9_
zI88$?eBS*DT)}fUhjG961z`g74qcDy>)3@`&x1`v9+f9r4s6)Z&zJT$u8Ym{6tdzU
zxoGMD$#=`pBHj(TVYLIb@qyar8znOun`D5&4_#V5GIu3dTNPT8lC`_j8QsqXSK+<#
z9d+A$#Z!w;rDt_mhTHZY!KA4q^qNzwZX(FBD%aGFn)Vg}h)NoJ6Tdi*;<DGqJupOw
zm_O0Nn6h%qy}l1fI@d@)u}Aa2I~K=v=_^IN30Du}g62?wImpB!V0_B45`!O5?&>5M
z4v%7QOr3WO#1`@|DUT}p-&&5D71U9lbg&1Zspvpuz=i)@+j|NtBz_CbMJzC4KlJ2g
z2jPZ;5)<{6&>)a8jb0aoisR&1ZfzERzX{MjpO%*6hG%u)c-PAu1<FP<^TtMf?Bs`#
zouUod@m|1%E<!okh~hcIm?z8&_=WGQ&Zisz{RF~N`^YWYy!0~9$g7^wTP}{X&M}VC
z#N!ZmQ-Bl9Mw0W}d#jp^=V3K`i=dEpUk5`$A+lbce~+MG5L#)*#NmIXAp(^9%0DG-
z{$x{cJqq%x4YMXu^B>6kae4dVm<GZ@XiLPJ^{H(dOedusmWNFLTNbi(zRw<#SR~ye
zIPMJUO>y{4z99fM|7pp7U`MH*yLd!)N=QdLG#y{+d#-y?YVTScmq5}Qs)2}d3{k+a
zqt<k5zvanr<DCrMY~J7I<H_}Qd+s<w0K$zfS>9kV*wG-e@zSq{lSS$;(%ew5W1>`j
zYvn9zOp>4KRAWA#`G)2~zT}Jj2TOdQs5`+E))P`1+4LpWvt~pQ^K<xZg?`?<Ku{na
z(_MKTtMH-1@(Unuabe-*FlXh6fZQ$UMjUy{-<JF~TFg)rmf$Zt`rD3ZWYlaTg?pD{
znu{3nzRsJKBRZDF65CPAV~Y77QJUQsV#ujRpF*8zjCFjj=qC41OHIUXBwzuX@d^Fu
zN&@09R!WL6ObOqAS2E6Ro5!TEZ#9cFNy1-C^b`Nv1xcwV;XUsqb<D2zJwa0O-qeVi
zh;MBI5&y7vznxA0#~FO2CwEl@#3SK3pz%XBc8*r!9_fO-Ksl8_8Nx(3G&^VEef($x
ze=d$idLzFfPC6fktZ83jTMmZfrcmBq2puD{kL8%v>gyvlSAS3D2$bbDU%(CPb#?)v
zxEF5i!m}fmzS(-ws*UdLt`q}?-Da9S0pq`fdRg7d>(5whhe0qi6P$WyxiNtm{~P0K
z4iEinHGsTz7r*En4LZlDvQF0q{~*zTWxQJ85(K^WfpLO&A1CP%T3cr$T*FAGWGhf*
zm+Cf;&OvtEtD(zYe7z5gkE*_zR*=~cG-JM}7Ke2qKIws1DpOR9u>qz+E|N3R2!DM<
zs#myC37Q+OLpq2E8doNal1d{OpG*7EW=KGzODze_2~8414sMHo@l4lc>(Ck1Drfj>
z1(`OC4j~M}^X;@=orsQP<Bu?;#+F4h_CKn=!)|MIx4}+2w*118cRZWMKd#pS4;ehl
zCaPFN=@#0g=C<L+mkUX9GY7xR380SU6OrpFEq=QlHa${#VqEI>fTqh#c}g70fxSYo
zvxFN8EFWzCPxg-*{oJ@F{Krle8INe!@*VA|yrcY6b*c=Hb7bMrS*YwVS+(mBW>qxY
zfxOtaW8<Cn+nUuz*0^59mCM_T44A0(*!ZaNrz6CDQgRk0>2|w2{Y)z>Y<({R&n!Gc
z@)mZwCQLo}jO$uC1GQU=;Gd4*&{$Alu&9x%u~)5`p2h($C%*vqx6lCrEgCQ3rD<Lb
zvRg}UK2mlhTa~mtnNiA{aLu)EMv)$FV^Zk;K=t*?vjCpLujcS4el;RG2&2?kr4DxS
z6l$Xky{g46nv3ccA_g&IqXe3qp@&~Uh`nCMmxA$k+To{$hEv~NH;`Q%LSmC{Yic~v
zz8rL389kx<_JpZsx^S%H7-&dFN+$Z>0AUO8VY|YyOip;f`K&al)0(+>CVx$zN-p#x
z5aX$$95>v$MMe)|fV$w5I{eD}Gq<JG@1V_fi}>Ho?JpJFa3L1)_TsxK_;8lJhD`3~
z3b9`h8OaxOE6x@Dhzk%;6}Hw=U+oG$Bseg+&oIKbmt*<^RM9~Gg$(>9s|uJug%)pt
z-<TYET?x#KfK2%RpLcQi7Qmt9X4vVZp0ntiFTKV9)1zSs+sT)f^bGRn%CMsXGRL3G
zqSSWFDCzX8W$}7w44M3B>$~0Wn$5gj0c)d-q<uN&{TwLS<YQmL5QYCynt|zn(_P6W
zVPvscS@(@1^w$lM0Ur`W`8G>?!(ub69e-uL?>L@-$m+*C))Mnyv<*n`Sn$$K=M$=8
zhOU|aVW4cMN!(-mJP&~{tx)t7s+z-+!l$FAf8m-9jq|q20mGqT$+2}&7%-w5yKXV-
zJuFNENQJQqZ5+iUrzi^KrVf3PhuDRNs?5(Ie$(i$zh|A(Ka<iEL$fGvv$$%Oj5su_
ziYnE;jw4a#f6kS5YKKNyU!72ei(V$*F5g;)jE@IUbXF!0{)1bPPq;ZY(>~EOm9aUu
zbtIdN6zlSV<<I~2y>hAi(V03s`TZVl=<QGKMR2Jt|J_G7ADjvc{J^|B6FTfM?Y(&B
z(>>;SxkE|;s~ObVk%`Hjnd&kGp5e`WUu5PZH^_m81?DFOi_|c9#JfrbDGCwyQ3ASK
zZ|?`(($xRp>>^ch#X0f^sv3^N<)y7d_C%NvyVO*FG~<s`T5cxR9i3}O$#MO)2)L^l
ziY*~)DJ}ogX4p7=Z^qgzjS;0%v+iAWbDVK$ER1E#keQQM?n7YzK{`D{qj${mdh2x9
zOy*Ji%#o0PJd*_v4<WpJ8(QK)%Mv%#u>We$QxVagU^jzOHRB@-lM|`(qvJ%lA-@Yy
zowHnG4V(;8WxU9U3e%yvE@bI}Cqi=DK<+W%3@NCwEjXUfaz{^Z`-;A@Sx#&keXK-M
zXxcrie&qp^|0K5zvTx7&u^)^7AKXXZm&(#8Kk7`iXYHR<N%5)x<&gmGVF~;q!4gFG
z3R(0qGCA$H%iC%nmXe9kbLx(k#GrjZnwa8uWlU8Jy^JIXeI|x59?&gbPu6bayhr?0
zo!ozEgKbkNY%kH5IyE<~uOfoa)czUe9$bBjVr`R*UCpqMVbe^fpzu+|UE>Q-ifS_?
z=;BA(ZFIjHx`Cmux&tc>$T59g!K~}t*tP!^P5O#G->=l66_tB7canFVtbDTviR=ey
z`N}e24ap`NVE*mB$JDGS=ju~*>~q}uSFJVG6RDV(LTXW$=P25>W{z(5j(G1n=DV$M
z_MW*|q{4IWQK>}bChT8tf3oqhmKf->KQk|}aWHD#=eDbSVB`?U!I5*Yr9SXc)O8sY
zfO#}WDA>|+7JN!5u>6zCn<S|Vc=Y18i`Mg1R%{j6IJM>1P9@`OQ;*RQP`)g+QNKPQ
zb;I#;n(K;Vs`!C>K17bW@tfI@O_^rvfYTh5hof5IX#IF@kjpBI`cdlLGE4oFE@sLa
zxUoMtQKdE^xVM?lGeC5GQS9S%*mheNqYKiBZJo2%h<0-O_-E^+TTf8W$LcAY^Pi<k
z5UuGk=)82D1}Ux206REeorT+;_r#--CF+E~#*asZPrWOk0*pJGr>v2Xstb-Uw<jW^
ztRT&~QS^u(YGi>)KMPSJ)+5%k;0_r1y8H;5&~}sG<5}1=mX-Gu3I~7=yo|hbZ$5tl
zB-&GvES!3y5)Se%oX8POnLyB#GQB(Vvi-Hum1>FJyo~5P6v~P?XU45!g*lpmqL-$<
zX)1_E9*59(q~0X7Y`%u@%3yFJo`1@wby=xPhFoW@;f$UFnhKI?$Raz_EYyrtb(44}
z8lcxV*6t7eT8?Kvy9c;T54Xo95R*o|IFyWCv46@T&r8e1Kd`7U&~}HB&Ko%-S5olb
z(>Y9;oeDs9wEq_BB;|1=h&#%|Y(A#`pllDR%PjJIqx^^|QnkA1>^htIE1()3$9P~$
z>U$K6A(HklkG;zx?PR?VOq7qAO#5#<Xp&ceE*?)(V5LwVU|BRx{X<FJ%{z;-xyVN1
zIz?w+l9rY<MPi1z9}hL^>;@X0DCUyu(5q&sj^;Bg1W!eJTf~#Br!5a-cdOZAezO4y
z5AR#|M0y({{-$hdu$QSR8je<~wz#4gCDp8-L!>}|vGzms7%XW^e<kJo4=&C>VQ?#)
z(;mVD`B~JOKZRgrp3b7MWA>}H(<E`BrOWDC>p;P&L;d%Os^jOO-@M;F=Y3s=GUj3O
zVtbpit|>RwjY=kp9k#n_k+)wl@w4SR<gJ8zs+GEY7U;VVMLY<Ih4x%^2-GweYh5o8
zmvOt3<1ai^Y#K;O_l}L5N>PQ1NIK?PyJy<bN!H&%Pghi&PW>W}H6o)8VsT2{X-6VV
z*LW6F%XMVqpmkZS0<vmdh=x%CJc;ogQgx2i_;d43AL;fJG=|mtn_)3yQX9wZ43p^v
zn(^Nhd$N#eK&#;yv_OW}>Q`a^Ay`2)&D&7?)5HpGz9C6{jib>P-E^OLL4un&n4+N!
zK{&{d6pB<bCy$bl<9@7b)t*f7F1>?a&F4u@IYX-crLXid*54yhfzge^snh$nD(+5w
z?wdI*+Fkzvlr~Vi1b4A*0dhVQ`f_c&!Z_Gj8w}%40JubiG!ntu-^VNZMd@!x4jp<7
z)#OOd!{x>XBQ-O{uEL%?YBCiQdTUa}Szxm%*^`Ku!50S%X2|)|G&o`gdh9MZN*mkj
zBf{b({n-K2ZF0j1|9HDi2YxAQ@rsgPpfb+LZc_Qlvj2^u^Ah@tAQjXGb6)y5@Ex@|
z06RF>qZi-Hs&_%G>5M_aN_Q%$roe^hkBpy8UF?g5y$kEIRtN8B7<$CjvA*F<IqjJa
z*CEIA<HHeXWAS&t`!#b+{GA4;+sa+dBMIPqO;v>xKY-r{d%jX6Qn_&u3zCpsPry3W
zMAoc;eZ$dJNuHMB*(cxc@wr7*sWtcKpojlg|Hz%J1ROEZq7bT?%~uB*!0WDPY7}b7
zV`}JM6<93kVl!9KT(|foXTPVCtSZ9!u}L!L#IJf6sdqrLKUufe6ErV3$j52hXl6pJ
zT~!94Q@)6K;uy?m?T36@1M6?ycvE*^5m7rwc!)ma231>p;4~7BbvI6LV&Xzk43kRy
z$fC$J*`K=|zS*Q>nIwk}-U3Pn_IAepNLwJ7>N7ZG6ENP^u15)Z4<Y;q_o0Hwub7E6
z7TKg21Tx{BKlx^fg$MtT<p-uC4>53~*-sQXDQS}rIcNg@^c-g+VPUks5UFBW!JC|7
z2E@yOv7?IRY6BUryc3F7)?sETi1Xw5+*Ia+>%e2L|KMT}&b1`0(Y1^kzcc6^c7K(~
z)6XfpX{#T0Rq~(_(#A2GsiT!NB=`#^R62Gc8)sD`KGt9al6%iXJS1Hhu4`CwWfg3(
z3*i+`LA!^!x)K1*?l$R_IqRpmvihlpZ!RdV#yY>Ut#u~khkruoo2<}Di1zPm+ojU<
zEzXfTc56@&f8`(OEb<E%R%3t7W@ZtRyI}5%+g|aQ*v7o$X=dR}LbXYmYZn8%z>X7N
zbFGyYn2_l^b6Je$i{qSY3uDQ%m=f)I+>LKq3}}M-iRFb<9S!Htg_9do+A;Z0O;qbj
z{`ntFg=x7`?F(YEWOZG>4rG94d}}Sv2;Q8u4PvI-^S_4hQ&d(HUgt#mX1xAYtT^VT
z>-D-x$iV0)_|!7<!!p6ao+?+Qr5P7vpQipy#*VHZr%Ld<T<P~?&H`D)G|}iMonzbe
z68ax4{W=O==;<fsRZ~C=i`Sl#q_hJ#ta-2!OAS_{8UchhPI&6W)hmmk_C*Vc%~eON
z+>LW${Pt4No9l*i$r6(MREW>rv;vKv(lXegAkstO{NQ?g{3%@Lyq2!TwWlXI22aIr
z6~Z>3f!Zb@a1Z{{S<kEA)nkyzYMubr^V`)QNVNp%$XL@_g9@Kn8|%&3LLYXM6$m`^
zT`k%IYn&fls*_K6n?_rTnez8;tJExJWk(V79m=d|S~P+F1-#DNZ4}ox_#sa%_D15s
zA1dW{wGMo==2t*+<6t~=|1VjZDJM!oJU=r%qEC<vfqpx0SLAnnzdAmbEL7YBbS;<I
z6C>j<EYu#dc_6|pj&4F3i<TfhOhX2QsB_~JQwYzj0t%ov`a`8mtqB#i4Q`#PZkYn^
zPTO$el!sg?|NKE52tiIqI-T*~<EU1=LrW*C`1_tLk`~hNO@Xe*0Vu_hW)-&{`ocEf
z9M<^JOWm+^O04H}1qYO>uRn^0n)F$0!|Yi5+|>lU3^*J8u2m3!V*W*4oa9};EuHmu
z2d`SFnT=aW`<#tpBIq=0@kK1Sbe$mIQ7)bgncxIRiLR$oyX$pR&}-QJshLkOZjd!Y
zVs|4y1L)xLb*y<tYK+x`>9=NOzW})7_Fs+pxPXh_w51UG)kDCi4WU%#kP^*itQku;
zI0%{o`Z#IVYD0WlL1$NfI$eSt*%K&zZ3Vq1e9WQCYAht>ApxJe|Iyb%ESg&u=j|9}
zw4r1LJt=qN7e@Cj{uZw^1=9->Z5Bq<_QHn?Lvs-q7x;bjfEF2Q<Z+#0%AZYILpcB`
zZ#+xt*gcHC!ovRdo5sL_<N?LNQdviV)x`5@+93q$vR{Wn*;f?=znyZl2Dfi_v&nv;
z|BM%0vj1TWnAVTEfZGLG5I@FD(-N{o_l+v%QIi}?Mo3LLY#BDU5%vYXCwE4EA;r-4
zN$I#5U4;Dz=PAE$4?f7PhxBrfbmr{K;@cKg6a<!V*!$oz+L9aQ@6wkmIWlIVYR||8
zLd&9{4|?kKRZ`L<N0RQN(3U`pJd)-npfd)64J!gcP+x)~a>LB8Y+qH&);Kw{4mA@!
z^8q5{)_wymWoxI<P>m85?y3;4!h$27Exqq4hgGjg(k^SpT=McyhXvV6$(xjC9grR=
zQqDXY$<^Buc7O|;=EAskM^l(NmV1g4>zZV(<wDWM1%J)re0gUAOPZ@n3t~E-?s=oi
z=sZYb%IvduCH?z{sC%c*Y~W>McOL{|^+aT|bfOUfoa=$*J>fe;HH6so0fkW)U%5Qz
zlJeRs$6GSq$2iY?hUqp*NtTSnSS?zhKI*8|*gS#CZhZi~GHtWgTYFnQzQX?47GwW8
z2#6M(ec1n`6aMAs;?1*TH?n|4V8gAJVny9^GL>W%b4%S$E}i~$F%rw6{zl}CTxp%T
zRWPqCpJ#$)6s_TrR`)5--ViPFxoZDaqN1eD5zsQa8vyj^7)8$cq&i?-F$5;U%FHKo
zSO1pI>7&p~hEmQNy_f)2wswvn{Xt#yC&QvLYm6lW(&DftW6f6P>QWp29^TS5UXlQC
zyC<_{tWI05Zz{2tX8D~1=b4{z9mv=TGhT5Fb%b9wRAhLQ(~msI51PosLF1qC3O7g-
zi0^bOvvoSMbl8oiG)B&D<mhA;t(O+&)JUH}AV$l$DE0r~`h1IMVxp(>1Q*AM+MUbo
z?`y1?M2Mn{Ik^HWV}E$=*flY_a@oJHj=7ID{CA@Fl;ei{h#@V?9m%s+SA&%1;RW~Q
z3aAvGcxu3Hqyu-gn<DFRbn)8?trT4gnxB|{L|_zP1$+jNCe*I<{c0orxmLzO*4au(
zx`D-qq&mIWXXVp!zi{k`!0>m`ZPoQ<6@V+c-4I7${3viBn~iVm*JvBhf|NNY?fRL)
zgYB}2LxUgMOY|WbDo<%J>BO(+9RC(|X<|s7|6kquaoXQ`GB}eH@sHDzIBIY|nhQ0u
z!$fl#Q9_P-p_#_%n`TX-7n}kwjt=v7>^jriYk+>3{tqpjzEefIG_6SnwDm9I(?|97
zP9mk_6E_L}!I=m$d~3(_VfWW1MXafkfRA*RbD5V!U7wCus5xLk>2*g_bL=1|T8Pcr
z2SPH&KdGy}myx^Fq9`q|SGJETcx<4X(}kiQ)RVD<WT#?wAC)6%o@<6EG=N6(ZCFB<
ziC9FWK@NNN^(B!n|G_2RN)y<~#SXWUcwjl*;w#pse__P1KOa2Xw1B&W8*#+l^=@z9
z++#?|ODhzq0b=SUIFxe-(DV~%=lH|5+TbU09mTt^b<!=avMI`-3&0*4jH5IAo7P%t
zlI^|m`c9{r6T8~O{OEm<G7eoYVs*NR3`%v~Mls$=&Sk)b0dQM+kGQi+?__hVH+4hm
zyLf8WzQJT5a5ZT}Y$<$N>zSjz-St)hNAM#jA>>GVUN2td<N)P@zglzMSb+lKc8zYE
z|JFh~G(OcZ{-A^_a*TKpa);<MZIv!QoHq7-;jsG8DJw&wzSl6Wq|_ATtGYo?q(&Ou
zjgp|!Y5S)-_W$5`Qu!zh8_ErhO_ep*)|A3}B$=Evh}s%tQWrFzaETRM3T#2;gjsCe
zXWi$wq|3&M5bNhk@RVA}u;O--b{&qCAMjJk%A$@(d^o$ECSBWC@=Li5n!?gWy3cwT
z&uJ)JqX2`sX=<#VP)(MPfk`PRjv$`1$&S+Z#t>tP58xogt;&p|)Qd1lWPNvY^`?DK
zs2=&)_-nFNCN@m|k7H%CMT2<`c~&L(SENAsEFbsX2Jf>>Bi<BEGPT=O#J<0Gjqj#F
zitmw^E2Ls$bFG<E*_(5><8Z;YRoU-Et5&?o7pP<Hi!(9%XXjCY;i`&H&q9D0y-V``
zD{w9hIcvyf&)kJm#Z#2*ax-)JFWoxy!7`TSd)Trp1%_Z_=ZYM>$Yq>Vlx9$azF=hJ
z@Z@U=!{jn?oj<hjQZyU;bE5vpMi}MBlO9&!Z)D%q1@#^aKm)RPP<x%x$u)4D_#oxD
z7W#ZI8ssQ6kw^7@CQ86syHKYx^pc025l@}4CTYt_A~hY&8cpQf=@xMwo%8&Pa#MSD
zGR{QN|7B}6f6jC6rW%pt+I|b`U~`rIeF-grey$Q;gl~+dtW&(b{a5Pl>d-nK@Yd(P
z@JMlF{8r7I9e90$RoSux6_^rvD{HGN+Vf;=YZ4IRN&jK+g?j`*Ic)D#A4S$^qCgYu
z{s9^=&b5;@^VcN}E%8^%GPM26Ppj(<*>F#duz=45W>bFpdCX0LLx8&y&HmqMx}Q0O
z8`GSNucj5yKGXQ;7gU9~Sb~z}?9$|2{RLzI3cDc#kQ?NxnCXr-7O%esMYfi?qoM_i
zRcGaN<D#jIJ|ESDXY}LR|7s*`VZ1j{m}oPC`HwdXe@;w}s`)R;4#lfGTe&7;2bhyC
zI#bft!%-+U@v-DXt1R;k)x=qgEU*Xbptbf*<A*s`*#0=fa#rF9G@--xHNGzSrRFCr
zYf`drkz5#x>#YJ1)umGoz6*7Pq<9R!kMW8p*m<jUCQU*$yO!&ob+Xy2g6OH{S{mpn
zMFCfuUQd`yBC&KwTVWh)m7)H}-PsyZgYQ+Xfu-W<+Jon5!?yW!E9KiNpVQ9auE36I
zTY623vP5X{^GbDzxhI5-B{pB5u(gJ=-JSX>RNE=gxdMU6Gg*6d${Q-W$+UvGOU4d0
zYM?P3m@232#Kf@MoT+D~PRj8<H?;%@O0YOx8H6S0@!9q``l_jRr@Zn$*_Zg?(KgwD
z)w0cLt^yRvzy7`$^_hfr1pM@-KVt9})P*F}icZa8aZD0!BM-YPx%Vcj2635M`}{>s
z5k8yp-GdcYamf?^zTCdAuBNUfTWrO2V{RGhwTE2ja-1(N%AnA6M5Y|2<j)i&ec!ll
zbrjTIWtdD-m4)Ry%rUfo@pdM~CC2~W)4B93&SCwfXqAEtFl|knDZD`Ym;f;0&e5MM
zdumq0lXaeDBBJ~>>QUOhah_g`+^}2BAgpJ|sx^u%7D?~cO`4(t*-^-ob1)aH{0qV-
zgT344D$p*4v?pC@kOuMscFWgj=^g)BXSI-J5h2{2o8~9txF@@h*ReF&v{?JjtRgFa
zTK;l=xvf0-hGg*Sg2?rot@-_SH<$gTj$qjSGasMNrqx2j_&`+cEF6LR0>K>W4NHus
z-)?ehEc#n>uwg@tzq@=ev$sH5k~nIz$XgoDv~Yel0x&LG#2%j8%nd3Q^N|vwxbkbW
zv0Geh79ycRodiiI*R)IkD|~+Hb+E`8z$!Rb4ZrX@mPVqUl0zhqZt?MF?XOwHOIhaW
zFIb;^bp+3rBQU+lwb&`l;b{N;{GiOGhf?+M3Ek?UGJQ~viSzXmm7l-HU;(e~y}q&0
zVXSzx*<`rBZc1y*&o)i~nFL5V4uIUQhiX4wsNS9aTQ(Bv*1+fnEYDZlxBhf=sp$3x
zhP|%7A1NU@b4P6&&ZQE^-I+6(wQ!<ffDWt_#v~&8qvb>G<cx?EsSd1#UeY}_(LN?j
z*&G@)J4P01H$Dpu-1GE30f@&wrg8`P9X49h%FFs48%}wk-tIP*4f!BGzj>tsB~?3O
z<73^&Drkf}Fq9$r{@;&EttP&#$76hJxO-(f%DbZw_p2l#q)?2#8Y4~c_dW5Qriu6e
z0_PHRj48CQ0rWxiI?Tj*IG*Nn6=}LFrNt_x+@3RU$BBOrSJHDO2d4?VH+pm5QZqjx
zt707}YGbB`*!Bqg+xIF%w5895f$Yg|x9#B;`u?iSFda0g2!q6l`GtYX@0rDKB20Zb
zPqU$Cj>mB65O<SLw|7s_kFmYomK$BV|F)MsdATfJk-05zi&Lh*F5gwtVqypg?q;iM
z`gquV(7G$b6}b*rNI1Bw$gfkL<y2V}0m!NeUn!fF3db{k;B~^8W_DY5pXP{S(heyh
zo#mL?mY&i-Cq3-G8QG*753t)pzS#D@t4$etTJ$%~SwDE(<Jrx4$al^y6&l%lG3jxT
z)y|q~Bou(lgBK{nv|~F~6yPrlIToheI-V&{#OHk0(*X|z7Ir^OyT1_xI*2okxRD&2
zT+~$4Rl97%-wr!+@pK#tRyno*2N&vD^LM6=XDloc)<NHZGK!EKplcIxulv`_51;Y9
zwsBo&J9m!pJF{>g8W!dVylhQpa|T`OjEWfb60F$!ocsPAyMF6ov2KXXD^snH8Tu(s
zdCkcJX+dpO9V^dSE^%c3kXK$`$Gb!`eERmG$yz#Fw$pksDfi!T7z_0K+L}L~xd3_E
z{*z3FQ3LB4jm&dFez)U7%>`M_62Z4BjvIjCMZ|*u1Y0gf-#`8>?dYH>=jr`b-5XjG
zabWFr0x2IPITm7VnyiaUFP)-<+SC=+B|h{ZXcDyvP|1P)@}sO#E6n#vZBI>8cx{@G
zE)r38E3=dU(O1+Iv=O5JTy{GULXhuj_l7u9Tvle>q3s@+Dpn6X;+QCht<6HHhh0D~
z<_hqO3besLK>Pms9ZPFnum3@$s`3I?B!2#$sAh<bxhwu#H<Z4{M}qxZSJxeZk3<_#
ziE~Hw-FCQHu$YGD`wlSxcHk!Pb|4y$1wCugP%4%}CQw9}gTx7Xy#7~k-78n#YmpYE
zE^RpdO_Hi$A@ox4gWG||2{;rugwwTI=_@II&k<jm!Eg;0k&q>!p?r&KNy<^<Ti$VP
zOGci|Lpe4${=9sBZ1S<i;#{yXXn1Dlu4XYD_hl#)+Q{9WID*I4C9uCVhSoD5lOQl?
zTTo#tUTlY-wBButmdFJvQ4$>~84=P-;Lfbz!b29ZcUJ&vh@&b2Ib<2(u~btv=Vba+
zZ!OZ}i$ZW?)fo#AL`PD%n=LX?b3Q2pRQn2M5#%8b#_9lZd=$Z1CU=l}#5~czf5J<l
zu{ze882XA)j);Ol#!8+~j71^;uOArr>d07o!6*`yYdx=x1Rbgd+Lv3=U|;Z}Q;Hx?
z!{T<hnOY}Hp`7}}AR_tQ;J@BM)6dbWj=!?C!^ANMDG=WXQjc#O=zW!wos>zJ)V}fZ
zBgRME5fu8NE6~LFIAL5LHkrIMy<grGj~b9QE+3x1sC}+-L^da~<I7KM>j|R6k-~kH
zQM8QfVc9!omySj4V_8Sn3*L66Ft+2Hlks6qF#ivZg~}PG_7LgWU#(vfgl1e9-`qq0
zADlQyMFF3aT~i`tBB<Kud^d>SWQDQ|vn!D%G=HR<Z<hh+6#y%1?rKS%q2uS^^?UkK
zDMZ!k_9cQtiUlR)`iW}V1}7;60<AGt$gr{5f6^hgv39cMfpj23b#crb((e;I(kmGZ
zh_?0Ab}6DigV+*#T6&|dx5&7r-FF_~^M152b+!{8QnXCaFr=-ESJe~r2_RM?lP(OL
zn{3TDdj=8Sm|&4b4tE)k<_wIY53Y5QiR~QZ6_$(zx7?e_y)_d5Fe#q}>#+pDA9)Bd
zVb)GaY*&toR3EEFY!Zfz4stlO(ad!Jmhth!yb${Icy){RuxO?lh1`)&%}M?E>#P6$
zU-TEHg<BOuHo>=<!`1UtN}$YsK=9K^u~&zD&z0I>9&r%m#yV^e=~9elh&TOd4;=XD
z?nILmMs^IDeyN`84&M9oqTv2T!tr3>7gV(z4ETZbj#c<|H`M&o%1GzXUVM){)rGg#
z1C}QEMx9MlmHVb|8LKzXw}mA9)yJXoixT2V`(|AKQ@AP5o*CTq4w=-%jq=>L_0s-V
z4AP<l{(+&|Pl?5Ch8}WV6_xWC(@|rhX)GfRBPhh{z8^{(6=NgZWSO$v9LBx&$%|Wb
z(ly3OEkZHAMvXAr!B`eRtj#@2I$vM&zq@;Uu8c#)2V*Sd#35}oC%%gmMwmkYxXiR_
z9QS!#r)pnQ7Vavh!hNkjCSs38l2&7;{TPQgzAf)oH?7LFLZc+Z@=spd*rp}Tf$A_^
zgqo8BQh)(NDQ^Dphl%U~^Nr_^)!CU?;{U#akDmy^L5{(KgGbvVfBXJ!_I%yNxQO=K
z`KjsHUXu8|=z7fNmF0*_un)iEeLetYeJW9Fn*oH*#_o0&>#RW$XX*y>M1qmkgz4ek
z(G!w&VyGL1jdqpPa8J|#NWi{WK(7ng@0Mu=x`tdsgOvfb8O!~p!m?qvIk~c_<!P4h
zmY;kQD!?vlEFK`3vB}1x_neAwDd1p)&t0S2Lxu|Y{$H*su9m~}<}zXD^*+Ie7hJU#
z^Q!`fCFt)Dmf+ol$OXOmJzhic_AZ;zEPMlNibx*Z4z=vtk`^^=gJ65tXOu)@@3{2<
z;1i$Lzn~oo+<&f+1?ThJ0T%`EnDKkq(+n<<rET7v546#(Wuhpy#J`U3|7CM25U-T%
zZ;5GZoUa}nY_dgdDR`igeaG@h9*mj9-Ri?D=h1+aW4^>hY$$6Uf_`O^5!WqLXYV6>
zs-0+D?0z`ZmoU+ujx7A9GpV)9X+0^BW<%~d52woM_o216W;=Q7p^8Fev=l%SpL*Nd
z)fQ9Yfvh_A%B&8&k)=*rl32rp7a7(S`UpsLuxBUUh@bsESgOmCl7C=GRd~6f=FFH5
z)s-WQmL<Pi(*FlqJH*b2p3JA%;IGw}CjOzdmND`D?VO1gT5K!lRVk@m#KH2=QL|Uk
zNtUgv582dof7CUXLx@dM)fr_dwV_d=X=`V7&MnS(^HUB^s`4q*H=6`8AQNvaQjAoM
zGieN~*w?7RuL}N(A-b*=ppY_@F}A`$kY7dkSSs_ac6RiSqq5PkCzviLO9M(RKp?5V
z+SqRGx~K`Cz?IPH4ho&DKXIU;VW}6XTErW%r24JtFpr~=S~*RxCk$%x2z3k4!R>3<
z1*0eJnRLjG-&QOF6cU3f`(m}~$1ReIlgQ9$3MZ0QmV-+Jjjsr^%7c=2n{we!sl8t~
zOaoCqqz1mA=YJPJGwE5(*Z7@xuoKUlHQ7kHjd!d;<z@Uq{Ap3Kr1s47uH<F|xm39Y
zkIwSFx@v{DnQ<;MfgYe0UQ_-M@H^67!x5K5i(yu~3MN4@Q-Z^9s&`pw-el`GlcSC#
zD||$BU$*CixLa!?9<wSD!i*6SkBpCEoBC0pRMOIXumvNr`!eW+mqBbtd^$Tw`T#&3
zMC@0s)wqrx0)Jma6oukC-)z~=L~h_qfGaOue(*eWBV~Wz=Id>*{U2PTyN-3Y=BjYY
zx$@_EMj_G)(Ir#`j4x3n0VKg2$%^laYoLj|(#Pp+{xe683#+6bwrqE0m6LF8%#W_^
zpFL1-@b-fZ+ddZe1h&CC0LwkL$gqSu|29(Q$u8k1C_ooOiRtFT1Ma9rH<>nB`JKHE
zOr2<`N8kGT9aJYW%Ne06Kk861-LTSy-Y^h~I&s%umIX%dqqQT+v35wkP*(gLd!-@e
zU>x2RDL~+;Y0x@6=feyq_)=87)o$%qfwW*WLU28vKT*bI)EzJ{k*`?7lEm$F6f<^T
zbvO=4kBd}w$%@BwFUz8JA@2Rej-*#F{zL9)v%IBMKmU;S)j>d200NEdjClcWKYto2
zU7Ib|aGvsD{TY(CWO1U!N<&KU;t-b!pppgP?(w^%nh1^T3g4Wt<Y{N=k|)I%-|z@I
zHNj}k($o%_LCP>yfeNdiw&qqFqdoSjgiEnOhdoH$E1~eN;v8y?P@2V(YnZ3Ue{h};
zHIJTSR$08tvU_1zJRFy2iDQk#aIo3ReuCyB#2SojTmxmi;Oq#IhWVyi=QX;`l)q0`
zy72{b;^t}LR?e)Bg2$RW9z^J#)Qxenbo9If=jp+@F%ZT1j_zl{+IwWT<5PX5=PY>3
zSe;+LP7P*dSY>Yh8qR#OUfW~n&D-^ojsvEQ%uO4_6PT)Pia4M-M(T=6IX~qr&HJwV
z&o{;o*i%O&Td0)3a|yK94;}#Ly6ggJ*&Tn?<-N;=p_Loh0=85Q{ZGJ5709~D%DKVG
z5RU;vf+7*8hUdwnr1rCBP?2Nnko!27<>4BOqa<$zwmdoF&1|0hsnI=GjJb7dYnYt!
zUsWWPae-+Lo_&j-c7NdonE2mxs@XIAT5Q^)0_=rGC|ESjve?CfoR)d#u>mA_t&L(W
zJOq8u($zB@GP6HzfJ)0a#)a`#NYZ&_??;KYHL=({VTa~lwdv-bdbT}ic}Cfa>!tir
z>&}FCn?k@k6x$1P%eyICsZv(@Ga9zQ*dD1C^iL(m;RW#p)2ZD8MY^Mplc(&dh6-ZC
z3mBnNq;+4LHgnvy6yWrQo7Q<8HsdIy9J|j&WqkDaQ=$^La#aUHnMf5(@SK=L#;#|{
zoLQurIBQSXwy>gH6R1^r4`%!GvmZ{!R*P!AeI{UuO<G-_-a^zE%P><`ydU|h`e*$9
z5BkKhj(yu>?Y{Wgm@=d{;|Chxiot{2HLdOXr?K_u4*aSeu7;;&;k3T4uMlG5!;X%A
z1yX<VmRYs|zAfR!&zwf&pD;$3L7pYMXIun<M?3iW-*ug9zU;I%;RBwu8WD2PgP6~g
zqcdG8zgB`_AEnm-Yv1Vx@#doa<G}Eb(a5v9;MbT4RGP=c_=3aAj~XK<(L%VkW054t
zVsU~{n=q%H5C*W>w_!fbk4%@xe<o8Oe>c--&e@2uAJPle!+d$9O{dW#`99!35aZX>
zA;y-|(6q?yH}Sf8hmPZyq(yle$}F#8a}87so%fUCoa)gv`cX^)+2Y=&ZD5>!W?lOT
z^J!jXk*z=V&95>1ZoEhykiIWxXo?GW#a*F$iC|c(c_s~z(W9fBly!25#8+Es>e(Y$
zk##2-WRT;}??p^BPPs1t+*pdz>6ttrvfS~yj#)PR7H&c|1>ZYVxj>$SpEavUt6Gr+
z#7EU;ddPk;pVQuQ-#JHU*F+P2DEijH@Sy@Z3-$O>D{zDX4j>LRzOU4Uiw<bzm_btd
zU{&AVk>K{|z6fd~%=q;BXvOvii-1-2;G=$$`eY^kN0I6-VbI7;0E)u7b*!~GlMX!X
zC5HT3YDmLQ=s6I4pYvM{xsE_LL!F%|8K<NFQ;<V*Z0tdMX+Y6cge_eVh8`=|d?lrP
z>NheZq>Qy9hWX+(fbM5Dzd?$C>%x-5YPi+%5chFN51dHJVfa__#dXY=g-<u~>|#Hd
z^~*Twt%<+S7kol}D6be5C=tp|e_-*>8A0rkWsW@Q5-cvzS|+X_lryOz4f~x|N;chE
z62?-p_KFzZQ99`?d1xSsrHIXMF40fMyfGbdAA&oe50OPEsDRfLOsKWzRq%2>_?CG{
zZvO6N@|Ybn#MOTCE@RX)#RRNtj=BsO-<c^!Q>!?VIiW=u#qvEX^^eZCvQM|H=!HJg
z(5V?7eYR32qI_>-{$UMc{a~M_Xn9pm95d9}h|_v^MCQQR3gg6FMK<%F&AXV<b*0y=
z{_|Q*ew@m2J^p<i`16D_Sd0cf<N<%)!+-y2i5p#Q15&1<M!e>S0Gh6bXP`V#Q?$=V
z*W)3bsp3D?(eq3;&r@sBjG4@{@gv?%ikBBYTB}xW?DHcfzim)nd5nTTtb!sKqD>7S
znABbh^0lz0JA9sr925skYsH0QqrRM~_A9$6SkQbQJ3&$gv3LL*0qF?u?>NH^E}hkl
zrMjtg-i7$*^|)Ejh(Kj7_h5&G-E90maAaq~gAYwuJ#b>v$RA46s#bAV3(;ywIXk<8
zkXCJkZhzW8iV+yNN{}$&HVyN~PtbZ-4FUxi$Q?t%bI8kb?>z*MPL-{UV}Yw@GzA}^
z`jQfi3=8d*dx>kI?YPMPmA1|}YP{GQA>#;z6&EhFTm;_7Ywc~`(jd-p%#utUmIN(>
zqD>7(I6kuD`_Ex(d!FDJh^AxFB2qJSlH17OYPr2iu^)h;WO+nTS}sHEWa;h{gk&XD
zZy7bM<XX3}RzFZ_`fq#jI?loW3k>#)vZm@FnkoQF+p6oql}{%{p4SW_Z_bGCe;F3&
zABP<1{XLuO4MO8}L{%xb;leet{E*v$wt}Y|eKs{XJ#kpZL|a1B1z2Bt<x_367Ypnv
zGmU7)pF1ZAWl6KeUR(R?8#wl=xGdnzvblBk(}T~})s&^RyWN-0$R|Pp4HM<)vVv~D
zIZgoS+J<=RpO3qdq{HwkvEfJ(B4G!JlPiqqtCTT#x-N;~0!DLJyAf!@oSb0aBlzJx
zMJzbBv|^@6zm6lqd!zR$*`HgfVWxOIsgI}7)g?J$6HfljZ`$#n+<^MOswcbu;998~
zePO61*G5~!)#TqUbxXG!+c=Gf{p_Yb-tJLo7%Aq=cQA<YQ{4|$_MbH$vzN=jj}sF;
zsxqgpg;+i}qhR?vVbBc*hH$)8X;Z8b+l9AHd3fKQYRdVcTYY~#V<xVxrHL82$jf1~
z8Fx<~FF9V9eaV<h8*_Shw!sJUWsRFhBa@wSox}Sh<oio`?|Wk06{^eI%8(Z%vk&5U
z458bWe%2MrK8joPLUy)YH7+pYDig%gGSQ8z8>Aw9(4CE<@XWb+ga&qlV*0+=ogP$@
zw}S(ML?SSfmfX0E=7-V9{=^jA8#+)hTFa5|@gzWL*pMv1Y5T1c8WX+dSPsbtmU%0a
z_qmOn1ZyG=;LWlB;QT_kmgDad=w|dUoW8c0{y~Me__zb{?=2rlY1gBL{|l{<{j=>P
zaJvicqkyPKW8_>J6xDbp+4+A@2t0v5;rmkO{@q;E$g;W3&0pJxuu08DQK30>R2XUw
z+$9$C*QZeQ_;C@|fHV^4Lwa%ADi2G8L3<o`Bvn3Ux181Nk^Hp1`F3=|Vd{!>%78Kc
z%A%*Tw7YO%|6%aZ3$a$kK5EFrM4R|eFt!VKmW6)S-e=oLYhmDx!P(2OsMceIPLS%g
z(kZmVt>cZHS;%MsKg(y-#WAmYNuk5@1NJ!SZ{skP%@Ba@4WjR4V|<6ZZuhAT)rLX#
z^P~>@Jh2hw`Rz2|?Ys-U3qO78^kBTB2Y%S|2U%l+dbj)?1BcNCiKN2#e{lZo9M+6p
z*9KXD93ZR#?~$U1wX4$~n!2Zy%UjE)X4Eq;{I%SWJN8Oi{CVe*=itGVRw-B3QOQWw
zS7%J2=^^^SgrF|!MR3hw-PlZlyUWM<Yr>0n!}(YI*vwT~c?6=p7RT5~!sV_?_r=3I
zthRp2I6Ti}zOf$1@_Au|s+pvXtrHDH$w79UnKOTXUEX@7&so;y<2URJQ510o3p`|m
z&&seGN4|r_8#IN8Iw=GqMgZ~RT(;pxMkMzsM+5HRUfJ&RPqB%1SeyoROlew;JKlOM
zXkgJrlT3Aob)2{Vx5~@aT}fL~EeY9c5Yu9%j~g+-FTkCvdv(OEr=Eq}ZgbZe7LP1(
zY(o14=nhC4QPXs!V?D%+nfoGV8IlwW%Cr3%;X@Taj^m-_eww0LKM+@r=&$?Q8`5p!
zhYDijl}TuQVS06B4?;7HKQRhEgGKqm9M2`~?s-gi8G~+?U7_#HmWQ#jbtSr*bM);|
z>dT4Ogu;q7-+k3A$b$;IZ01-jjDpPfrOG<!L=hN|qCCU@w6xz8DSJrEqZ2lSBi8|e
zG(UqH=yPoPZK#5x9JtDRbH4B*BD}6Gx1m#$wDZ&uM(Pjct8k!)=u<e<Vp~RzLOVUK
zkev7P{rh{YZrsWJA1agR1Ta02k5uCLlzZGk0aiEtMKsaqzD2ui>#~!Ccd|6c+MyIf
zDCdTAW(ATFmB<yYh7Dh&r-&%;*91ZFwu`dHm;_4_e`j@Hc$cw=zN1H9R*&x-*I5jC
z!{kW?OdSj6Us&$FUT@>&5%$Mx4pc7=XaP@w0JdAEgYn$e<N2OoRm7DMl3q)F?|XNn
z8&Y%24pQiAwGGb7^RhEp4QHRJziwKiQ$)U*V&Rtys(^gOUbi=GI0R_3xn>3%ljSt;
zvG63X*6X@9c)&L0w#Kmz#}GC&r{e1NJ8~h+ftK6K(AUr??JL<DJJtr1;r*Jw!O-lK
z&g-}CPcEU=2F8RMg4MR6T`B)`o5QC8Z5Xg{^@1qB14yI`&sW?*>LJlFO#RU7E0bo>
zYgB?u>v?<oHvBqtA>pfv%LmR_&pHxl-r<o}dwV)l1WtZZ7K)kwNb`Y8Kn1!Q`N@q#
z=emcV2P-pYh))IU7U8aP5PWICq*3~#t)yI?VaP-bCS(d=4A82`=%oLJYnt|k9aIr^
zV2$h_B4_T9El+g$&AtKF4Qb?|eb%YcRMM2(4yF145)i3eCUnNnHj9E>J(OJM%DI+m
zZ>Ebg3Xn05&ulcuaH^sVi}L7_@^Tq4m=n``#}DavxXB+8S91;@#xj*YBZeo-icI@x
zf$A@GUO1U1@p|DbYJX8z=No!@Yl%%a@9~RNDpvm?9RzcatTzfF{RK9-@nRJJv$tp`
zd>@=9u55pDx^9^h)z>!7(WBj8$)?srNPy;8?TMyt(M1Ya_CIgsS{2chUk=A!%$(sf
z_9Ijdd%Z1<`~J8crHbHB49|f#vG5!_;yKg!C+?%Ma8pw5z6RP51Q^D0fUs1X^P`yj
zeM%4vd@J;|N6AwMdXMno{<$H;feP!`oti@Xcz#e!R5>E>+KS~$eG%{#XrZWs=A!I}
zF}1FItN$ZnZz;ydUBs&|74>jm8!bauM&ibYeq($a%xC!9C9X)WLG>c%Q|q|U?oP-s
zr$(k4{v__S1)9ew0qw6&E@%`Ns7sxlf@TZUP-6dPy_GX)hfpS@tvB&5qdOi6fab+M
z_5(r<*d};fa^zgL_{3%!b|)2|e+qmkU9vTSX<RGbRydEnZV62IRAV298Vq_qcP~wb
zCbi#ES8uTMl6wDDP5UVgDg8i96Id?nZgBm3c71<obc8u#UEru<8vPSzZpYY%CYR6N
zfE?Y}|KNO|mzd!CM?W?tPQ;3zKhC0v{2zH|xzJV@Ze66srBK|p6ao|r#kIJ*QyhW^
zcbDRB!CiwC*W$sUxVux_rF~D%-|rI6_ahgulf8G=TF;zgpz1U2p^8RT6gp)j2c*S(
zPK{UTmL5Nk_7Z-2A)^#SxO-9MVh?leyDJS)cAaac9eKeB_*$;&x*3KQN&S`YFil$X
zW%gs<XLasSF}#lbIl-5OND8plZ9*x{Cu*)2NbMdf$zgeT@b(-d0+1J33<x(!4wzGq
z<xtyRk5;w~C&3J71Y9AgOi9wBERslG|C%P(XSeahDQ1vWP}@uSi$yYFrO1D``XTFz
z8^2{4NorMuv=8}fl!$XnOw6O#Mo{AcE##z}E9bK4lN3I)@Qb`Z9eihAPH=Fh#K#2X
z!||~SqR!9AAA<}MokaWMc%91<m^|=ci3K#3*Qrz%xG2K~odk#!xqMYio@TSCY4sTK
z+}fpr1UY+D&4)c)*EqVX{YRoh@wv9r@veg%Yp29D=%Stc3A61j>niheC9d?uuE{o>
zANY@LNR2umh%{7PFB&<f@N@RyPzmI~frm-L*-1f~iwd8=cAa@n0`s}WWp)#H!{+|v
zUm1Aq=IMU$=EZtLAElL6a@bpOu6nX6ganJb|86IRqN(1<UK+hWOnZ2U=Z1;$qViRH
zs!)ZO)^J#67obAvYSpe$%J2dkp>4g-KZF4?{oI1E`uk~msEZOs9QR1CWxO(=;;Q9c
zzHjWmX0_!ga)F=wchA0uU2}%&8MbgU*JOUFPhJ^EP#zozImjWJQ;YZG`*3Mdk$L~b
zCq-+TYvcAJzI>IjTv)A=H<=VbbR;gvN2l^hm%6^{gV-wWY^5Jv`o7Pg1&paoa4Ac<
z)6r6UI|6vx@zY5U;qKhnp+fKHCg+svC@`B1y{HAqz$bKV+(?33J}gV#V60Ilxxe*o
z^6v#;0gC3pCFD*i1)3Q%$m!`QgytY{3B!fI<cw=HNA5mWRWT2suZhA+&fNM%%Ip4n
zIXDZcacW}78j?3-wO$xL^F6Yt(ORm40dA7J<ier@SjI3X4`XiS1;Q9Up-Sa6gMM|Z
z#V^@lz`WL9B}B#q<cq~dE*Xd&bFN%|C$9YTDD_wi@OZ^BD+_#nqWgRynr7C@BaGbV
z$rr+dO0HYE7i&#8w^fVsyH_M__=(p;PhTjmGtx2lthHPHDrG%ktb@U<l|MViBirkk
zd;M1L_9PmYE65jFe@?j}(#jJ4=XP}2{Nr0GA!R1T^&DX~8`6n$wUd<@ICxT)jfQdr
z4nk^K6tP;(@r~6CT#c8(V8(&1cwg91=TaU|%4MpF6(yo@uBQ6_UJSk~Kqf7|DoS-f
z5kmtByv{X<!@HNNDA*(q#myX8YHI{$85HIO2&v}66~i|4NI_V>YSDsjrN}%8pBbWa
zHKOB)yOo=<AriDr>cRgzK&)4jBEb4w6piqI{R5cjp*P+fb!IDQO4g+_Yz$+-xLcLH
z8!1`neGWVENjpwfFcLVlG_HvT>t%Fkm)ho8PGy5Bte;l7M05QOE246%s`JIwHrP51
zMjz57i9{UsVzuR?8H@Mo*dP)fc=wevO}66uI^XxG|196fgqqPacT#_@74a5BNwG6i
zI{z~C(vv_nPAM;o_z%HLG+b@5ORoBi8*s|4z&uSV1}J}$D+1|HRl15)(Wi`?Gz=cy
z5BbXc;4#AYCv*2=BPg*prSU7vj`5fFt8{*5%WGC36<S<u#~%pfQ3xsg0beev3W6AD
zgPncmaKs*f^G{!US2N-qEr}W#J`6frnC3$|g0CVRi0(_T(e>`mGxbbG-5ZDfS(1^b
zyMR0`FDo6b^QH~$F@Fsddj0MXyNPw17rT^9l0_dB)(3y_B<2X}knh%EpXjr_e9HE6
z#B0A9L3P@D*2eE#Yqv4lwWm`1QSK}_9nrB+9?@kpdxmihC{Hzf>oW+QJ}@5Nb0Al|
zR*9ILtVy3$BH6;K7)UySJll8Xq<fezvAVeG5bJbC=`zep<67_$T&P>OKLL6JaIaC)
z9@4pu48M$W@q~MPoe31Ui^CmQwT@)NuFZ0!lW=iyk$YJR^<y%UJ{!avCtfWIJHQ@l
z8$qq5uA^A`-TR^7W6Ju1{t$|H?blr)efv$a#P83+Go*AD2|~eh@Q%Lsg%@&r9otj+
zZUxQU>e%KBzU=efTH9Y&N#wzrE<x`)+Z4SMr`ut@`tx~f!gFK9Cq0m9Sr=p<Y`Ctl
z_8K||+#!PG9_ChLkMmFH2p!DtiH5t$UE>a>8281Ds(bV!e>C}8svMiWd>8oRKLjij
zJ5K*1J<epI#;UgM0O0mg%a@NN``Q}6gHHj+&vQc`z2qi0n~J0pSp6D$U#`CkpNiQ0
z%2fOZS`P>`wyDn+yo?CMgZgosEb6DFw7nK-l5YEIdk%gf*MBN=CxY1S7(BX|ABu*9
zSx5sewmFv<TcVu&Dev<t-&eLpY${C@>?dtS>(uM^B^g=Zb*W3kp7g+KTzHTNT#~1{
zeto#xeJq<dQdRO1E07Pke?f5Mv~hk{AY}rMzz)F?C-f1PKhQ&1_T*551fju8AF*v3
z$?e0Z_g~)o@%|P9TYPaKIvxDB&F7S5u!NF9m%b;<Lml2jv&5*A1I=w@_v@9kJ~2wq
zzG5FkkFgcVY31At7jNknl%Fg5-85o9YvmRt5s`SSbDG9i8&2i9`z5j^Zs)nE>BHCw
z5ux?>D>y0PdK&dfN2c>vcZ^X(hu80x=k!zAgtO=u?!lK-GOHxkR=hEDOBQ3`)E3l>
zDY8q(q425b{NDl#oXO>qg?h?-95&&E@1--K?UOuEWUH=}p=EQp$A8CH2fp$Q?qas4
z?7q*fYTmcS*<)r5#9E5>`_`c(qpy$+V%wKP5Zr}FyTDhSFzs0-oP?UeY8RAccG$ZF
zX<<+`XYslXDGWIMl=t$g^t<F&eS1__Lt9NW3Em&jKm5h-##aZ;cQrk(`ywd(D4CP%
zRt0&Rm_NqW#VLAm;)AQ)Y3^wL0=U($QBsN%?$(xzMK?C455%Y__a>>;TIZSCT7Em8
z|9Qk$#+fj`spCz|lZzKWgAv}p`-LaOYWab;poaQjYF5)<MZUxIs&QG4cM=Hwe%bQT
zPFuZn;zB`Ybl~uPB#p;iNs?|}+Vay1kHr!@xt#7d>|Q*#S_#Q!?oKE1l-2gt#s(t5
zA8*`?-DE}g&s^`_G~W2G?FGDk2`JW~8x5F@B5(LCwY>?<`3V<1+42%={~TqSxM`r~
ztj&8l)9l7}C^aaNm&P9a<%Vl&gpn6sl92QE<*IYgn5FsE0-F-r@D3oi9xvctCBkrJ
zRlOsa7Nf4a^8G@N6h1KbS1CC;D>(tLMQomu<^~NPGBMo)Z@&*xs_$tn)$Zr%a8|br
zZuJNE_P(7cL+W|rzXaeglRlm0+d@7Mj85}Bvn3{P;6g3O&AC}5yQBEa8LT}#_O-I;
z5IfY7@Q|vut*TA%fh>KyNl7qC$Xxs`c|Vb#lxqUqq8eV!uOs}~8JBWMsW(ME?!$YF
z!JHdZl%LC<!*<$&gLr@QPCSQ|xlm-wHbKNmQV%~&x!0&W8LWl;0h(jnk;tf}GIZE0
zl&|Wq8fmVY@5Dt})Z6%wA!}Ec;rHJOzmJ2;=!oMyIbD?(guYfk*{R98+i8cjeqP?5
z=^s{Wf&j68=a99V+GUZ(ya$}kEQ}hJYKbT1>&w<yX|xHMw~tn+x678gJhg#aMK7+H
zX<O#l>1mAC`@ky}N@Ia6vqoe$n#4#`dgk}y5GdmvZ?cft+_?Ln4ckNlnufFy7>TIY
z6+oGsBM6;I3|63)@~p|4;VN@P@<@Bu+AN3M+*wmG#7GfADfKPNK6@fsD16;0u&b>M
zbICPw7+0CaAXoqJuexB1j7{I_85KHQt=|6bGmxPLglU;^$goGrjNQc<#F=tm!B!_5
zOAn6!*VMRKSEj^?x6b<QEhbh=99Ky5=+FpGZV>@KcLWdw#nG9FVW>2VIv(_mkR02-
zv521}l*(Tfv-^-u*<&$9rOd<+7cw0lwklO2-nv4@+L~>a(?-8LE~usr>o7G78(?w0
z|2mqQM{uhy<Mdf5xo1$j1<7k9EfrZGo2!rHS<cYnuWfS|iNj=wzby#(`FteGo2g}e
zkz1*r(y405t^*LqwR*@sVm=rh(5z-o<tl)L7ca*2sf;W~usxbfV7pYl)noR<H$mTP
z<;(ivpUk~Nnm<mcDTPnF7v_bL_Hk`v3ERlMkmnab1Pa&^+nh*WQK?cp^bM454822?
zm&@2Q3y>Z$V;>0O9Fz9&ttrteT@|I9I{bPAi<QVj-%t-swN^KG>9bM`?$5N$AiG@B
zZ*{f&P&?91%jG%n91dUE`xwNsO!1Be?w_96(Z05;LgHa$YH^V+Ar%{l4m8IyF3lL>
z?eBv}DZ@Xhn;EW`{>kr(3km!QR;!m4(?oS@pTw?@tCDl_iNd_-o8Hsg+&ct1%mRa2
zb~;J>YECXNJFO2$&vlxfsHEKCFYEYR=0|<P{@UXu7J+?tg8oAb?lAk>UGdr?J#zuG
zN4R-Om@o!C&?{aTx740ojtn6@6xVPGsGSouIPZ{TKIIHYoHr(sw(t#jh%~dUIR7(f
z0dE%1ZBK3@1F&3hZBL?`5YhdqrB7X>%L%KMovZw>^##Jj(MVy<+714Vc=|(|jKva*
z6dZcQSc1DbN2sJF>5}np(LrO}r*@wt&6!j(Je_>X#=G`JbM+vB8H5_FM+eh8Iz+TZ
z!cC>YLPw?e+~%ke4;AfGs6Z2=#umFMPRf2M+HK2*j*bmf`B&hKw}D@Ib>v7bMIrbW
zYhfG^#ro46@{Q!AlP)djzVe(Qo|=nj>`|Mts^+WhhbU7iKM&*k{-HfK<M(LB{Ka?9
z;?Ow3ArDXJ&qJnYbz#0YX5Dl+vu5gSLHy6>WRgps#}LhNu6siL)4k~)2Im~ayUIGo
zY^7xWAY3A6&6#H8c*yvlN1S4&!ztT0pOoQ3p<((qM=5(dJSlfarr0o(Za~fr*WeLd
z5lDEvy_n$Pw*8i*+I@<zOo1-MgTVAGx{4lih~`qgh#2kSfL+~YW>^^!nUHc_W7v~+
zgNpm+p_&#?OWY6=u!}e><ydTLIQV`m7Sf2n9WTctU(mn@oBa`ltwBpfg1mHFMxg4W
z3d5F%rpy+Yy+sO94=#ACi;s}1o#^P0OpB)B)1M29!|!MraF*>`>|r@K2Q_;jqS}wJ
z_^+Y|+It~Dn4gdK;zv>pMS@gs-uxZ5A;YE!29_JiwjgoTQtnA3xU^3fi1==7mVJMU
zobnfj5}Lzvb58k65t@v8mzKs6jC6oQ#dfyym1jtQL&RDn^_6e)b5z<7rdHcTuJgCK
zwq%ut>dzPB5j2`h+$QH3xIHXY_!EdEgscU(7IAViEdEle$#M)XLzy{?*?r**NVZ`!
z&kn=R{-FNP*idW+7g9!K3UkV{5{I&tw11aS@QV^GiG6Xb81GhlVPHJAbWBKPj__!y
z_zMWGZJTGMlPj@vba5HjTK%a&XwT7i2W<DGoI>iOx>>o5E(8`v2+#g~I3lf+h`pO{
z8jEd2>)QGxN&VP=tyXe8q51V_$lVxefwd`tK>8&%z@a3nz8bri;zdX1+M!DnY-%Tx
zU}vA~#F&RbOs!^=H+gf5u6zN@%8FEk_#saw;;dAyJa=e~$fUNv#aYs>xAR2s$$mF|
z(pC(PaR&-LN=t?g3r7F=O0~eLjYrJ?SVCWTsX?Hj1PIl9r}rORJ)_CQb6$W2A)Kd5
z9i}y3S4Z+^ejX`9gdljCu2al94uc_%oAaHncLkEc(*&K${3RGNrOIu9=yYVdRkTUr
zmilK~UNpW>*}o{U5oA9`r_()5w<Cxe+tw%bjR1>Ut4uM>RsBK13}huqvI@1Tf44VS
z{zS^#gu|9S9|e^GgeB5W9V|m}rv~kE2sc}`@Ro9V&qm2F(UqTd9U?4h>{%?-%;mw;
zZ+HBJ@-HLIc0ar&M=@6`P^S3bP7OaIEAL|dm~R-YJk8%xg`Uq=N?4-jh1)i1D3Fp<
zX8c{PZ(ZVt6WCSeHT7t1#OZrnaQOG=nxr<mCo5vcm-h-Et9~lZZug*5L!}2W6U81%
z+hQ8l+Fq;Ms3nz?XDt{Ufa<H;{e9PMI1BFXn&x97KH84>iddt{h|=oil-PRpVc<{v
z!rbcJ6E0sTNjEOF3oLG;7-b4BwI2|F8hA%zVjVT}==E2RUC$=%f;iN&ymyP@LFOjt
z4}FKls%&gs@?FR|8vmv+9VJ}6`FN5PD4=n%*hZ?T8z*|aGX!Pf>z?Y}LpmSjaJP(L
zWl}a1CqcgE&8F+)bQ2^4w3H*HP}57BvGz{v^Uf6>%dwtKal)XZ#|f`t+rJ&zPZI%Z
zGL+oIw&+lObPqoMdnhfHnrtmh$eiaXZzd!K_Q_vU{n^9?6n~1V>|fdJf(fedPuP#3
z9P_vR$lR9gt;p@8wZ_b<=V^%7*(~Skjqq&xg8~ehPGW1tQ`MJUKcAF)K>y}<sU<AS
zS246+@Pd(Xo)QlDMZZ~C_O9hYN<PD5<!;gjRs@2f$m#WTEs%TXz`_H3Tn##0R37YG
z)5q5+?J(l)DxFCkO4*v1(-&fxu918eH#Qm>8`3DM^NI@R>eTsTU4~IE!WMJ?d}N?a
zIfU0b4_s1wQm3R9vb3#7hXo;ZC^f%Ukw_U#(DsC}zjs9$QBKYL3+;AcAnY=80UNoU
z46ES_lCSJaZIS1|Rbnk^<xZP|qK~et1qte7B@Sfyiu09RM6d9(LQPsT2AH?uQ7L1;
zccQm-qRMyqpExRXg<11=gboH~iqiF+Kii3U)kheoH>KBFQs67@#!B%ABl%N3bJUB@
zl;_0)KdSQC#(T`q*GGuc`m4DhQ4cA4-gWP|Sfuyg<I>-66IQUL(VGpIdZYZgjlGUu
z_GDH**!N4B7FzJ6=Z8@>o9)c%2!6OeWy$v6QzCd5!hBuTiBNE>wvfpb!Ffx|bfzf1
znPh2;B!8?otin`kJ8F$RPA{D;{|F2QRZ8PdV}6{L-)QQJmr>0kr3A!RgHGus7UgIY
z%w^>+<I}v^KRQh;zbr~l-hySRef-9gE{**vT{(ao>Ru~+CO+1suD77+cY}q`=-ZHA
z@8ZaI0xnAhb^|$B_OCegHPqw7Njd1h?FT2tngavqQxZ{uT1z&2&-2yJiNolkX-;F>
z!*N}~Ryb4QRB0}Jmq2eUA|e+>joSH9YW<_3Kgsp+o1eHo!U*q(2aHI0wy=f-v#?qb
zWOvo#N}@OOh_hUIWi((Vv!CkI=;!ga6JyUUs}=3HW9aV)XWlgP_}$L}8IH^n2i@v~
zk`G|xqeHGr4C~?$b*`~NBs6#cjRW_-q&a2cA6agM0m+by{U5ZrPc|LwcJgcEZ3%Xt
z_53GwqSpfXNviFf>O*H6D+y_n89ouMN=tJ?e0xw_q-fNu*C8Ms55~^lgeIf}H`R&Z
z_1;5<x50`ZBVHEVqcX@r@K_3d8L{(TEZJngvZ<@YxLS-#TK=C=k)5fX93AFe>llrB
zZBqvdMdJ77$968*LTeJndKA}FxBm#I3=M^ra2q%Z_EL=FSW?2g<r=i?2b`afI=*0f
zc>|$ptmFV{b&Z!rK6|9WE5MQnWj@yODrTYkN8^sSNqVg4i+-8hR$5_fl7D!|J*xPI
z8{Fn~<NpX-3%sc1ukPX)JJ5~dJ;w^_-|V!<^&5U!5#0jbZ>J1>*U@>cfhI^AwH&Mv
z)xf~99#vmGu4U{142U_QL8ux!x0>#5?J4qY3Nq+|wD6jJIdR1wugUxY<hrwr)$}GL
zhFXuoxRIl7m+v3^P(eE<?}vWKZi~MTvC2KrZ`La8PUCx-tEaD?99qGHgt_E-%~885
zr0Y*1AF+;+K72(02xR{_a#;8f6xJ|gEAEs&5%p;^Qb-eGIh97E^}$TaxM!hJ$hYWJ
z#5gTjwuE&X?*eoFh#o4@`-M`hT6-3kZ9a$u2eE20_df(l{Xq<3d=L6~J9b$yGci7)
zC9&(`5K>o_P?_}SSdS}<gk8swpQ%O{O7S2(*Z6<;<TMQX(F+Sr3b{O$sk~^<KM1oa
zFjQKh3T6P3USuJROF!<NYT_1!^t3fFcF@8EB^_vQ%P~B`9&&OgtoMhGqs!N02b?gK
z;)A#bXu@-7jYEWMK+_iBrpiTaoIlY%1jvM@_ZrU6I3Do`Cn^blTJx`Osjl<5M{53-
zwNQ?@8R_4uQZroAQf_!@Jn0mGbfQ@7Jx~-~6Z8k>ptK=u_5DBK1v7&V|EfZ^;C%f*
zMR5K+C=0RtyIhZIW^cLvTZ3cO<?WapR2SFuwI_|N?0A`rnfe^V*CjOxslPOi<Y7^}
z&Sj@Cfz?}(!}ecx*^oJX7ys&HCsZ2&`nngSvS*O2Ko}R5=b?!?J-L}IN#ETOf~Hm4
zr!5Sa_(x~=na4W%^8<>Y&o*SGb6!ZHnkU6TPn<G3KXG(jC-bRM_3Ki^oT^zJu}!>q
z$ryh%-(&r5b3K8k_O*fZuTGB_Jnfwyt;~(rJiMR8@_E583!UVHO{u&xe5jOFlM8pe
zSMP2H<l-f;7KJkK#?~Uorxo35^^+a4Mozyt(shJ6{&)!iz#B}M;T};CM*gEx<5@)w
z2{Oq}%F~U5jV8N>Y^u#>h|y?!hPOLjESkfD!HMRhg(G|k-Kryd<0vK(zhG3WQ}|As
zD{eECunYsXn#L|Y%ME{}e;9szACG`MKNlV5*rg>{z)Bt^r&^^K;Z^Od5O8(w5zhmY
z@UH3O#kCKXpLL>X;D<qhf&jz-L7hBshByhON??CY3U(WYA?{*Bj6gzaZu^Nu@*p@x
zy?6Q5!opM&-xlb^rP@yV2vpxBHMab_<{%6M9{U(amiy=G6>6s-^Fs?GQ+pEzI>cI0
z4zkeA+x7!lj(d^er2HS1{Rq`3$}pk3I(fVUZG<zqc)s!vpZA1WBDksMyKdi3eAS(8
zNCuK^dH105QXGGo5soALt0)z%MiUAu&G~E-R7o36V;?ILe~;>0kK6AF2N&|WE<p^;
z=gpT0G6%;vr)*VMJl-Qd;^k<KqiJ8fChF1$G%H)(n5u1cJ03qoph@=3PEHfb8KyW2
zORxS$lIv>Wlbvs<*nCy*)K*X+jDRC`*w}H<-&iIy46o!a;PV~?k6mc+*hcA~OM32O
z`yT<^QWaBI3P6hvhU|$#Rou@2U}jL(o>PAV{7gFPLNYc{90}UbG5Qo;jbX;u@OMwA
zm;`|;xN1;fkI{UuoIn;eIqpOezSNrHFZDp#S_}fTkHO93i9T-CdK2!-_PY`9ndR(X
zAk|FDX;#YIFIswtG(OQ&l2V|E<LNR^tq<Y$=7iwhH`}mwx#?Eh!J<(<q!P;sJ$@h&
z7vlc)Vu^(O`8mV}<ISuzrVS=<A9f)!FTG}vcSl3Y^5G~xqL_mBqO8V{_FOCaR-s}v
z$1#TVOe=bOK0+FyoI38CvdV0tuBKTek024kmH$a(jyj@TklP!xPiU~*JXW-@Ff*1a
z7{*iM!rXr0UCIaRM#jmNLcPfOEz4IRafB4)kHd@(69(a+GDX{v&e$C78^+`Mtc*^R
z*7(zcN$#NF-v9M8!a`y4ino`SVnSv?$^u$H_$OKNymu37-=jY^<_T9IImRS{Wp&d^
zr%8pGYo6&ck@CDtoxY1JqS95{5*PI^>~Gv6&dfKIn0uA$C#W=d?U~(R`9*tAKLdA{
zT2T(2IB(nHT~?q@_-FXGIui<S1<3_eT)4m>7Zu~CXttAM%WkPVVboH$uRdNkynkTM
zy4plZ{~^%w-8c&z&329-!}AQtZSTQa4(L7QIh(M9j`-rm>LXws6xNVovj??sT`jR#
zEP>8{Ln5D`PWP@eoz0v!BfvslUy2)EV~owe#JIo2&G<K=J|b>>*pkry?GgV$*KK)K
zroVmLs_oe+`NGP>%zF<NYV%Y?+%-nbr;(#WVety!N=U6N;fcHX7$Wdu)qKZ<={!P=
z><k>nmezR0<@*CDm^t#Y{wTk~DzXDqvzVk@Eb4@|#KReoXLwfz2poG1OGb<XlTP_x
zY|i10OImXZYh=OTVUR4H#eqxvvHw~7)!?t=imw()YtKvRHFd!$M$;h|k789DT0eR(
zmA{BV1lSY``Ob#C|J60HXHx9@E(Q7xE&Sw8f!t2x(aVT<s~SXS;V^uVj{%ck-_+Ns
z&X(S?DvMkQK&}@YVo4tQ>a?yVA`A#AevR=170fJ}>E_KgD8dpEjv%)i5)!Sb2Q=2P
zOC_haBwzhPA-Dck!WomtGKBa%QldQ8-7F*MFd+74(!Emob?YK8E_a(53KYXy8A@z7
zvgC9`l^(nJE5AX`i?3FlapDSvr||gM2(0q(AAO8{I1D+yIU*`2#}{lQ`h#{;5-~rc
zd`~xNAavbh($ZY3;nz+=vdc0P$=>>5=gMP@TI`X7vk$#}2Rb!oPM%#ClYiCi8?cz`
z)Md4k)nnpmqsbbn%`Q8XC(;IaiE!ieI$c^cs1`|6GwA_~-Hz7|51px-?w?n&$Og06
zq@2v!Q}Hi()n+;<F^6mnN-Fbz2xppWAc<S~1D9CLU`4tz$M+KJWbYQj&SY%Gd}j}{
z=zh;@xCT$MgT*kw(w`?Oj}c0S_)Ju#eP)mlpCFvk9$U7Gs>onvwMmllqV2;JW_*^p
z3Ia{?5;)lv`Tulv@&Bo2et4**-c@|W1AR`KQvWI{fV)e$PF2)3up2gY3nP*h%RxK^
z$*rKnAv<xiUrDA*&6G$tmVm!1sIwxxYAR9oa&#y!M#)Q6z~-KZ2FcX??<idL$;#@g
z)~kVot=Oc-;;s=;CloJSwd-K-?OZl^->_zKT1Eb}c`M9kC_HA;+N-q?MV}+nsn-+A
zZ`mDm9qH*he?+lAZ$fboJ<G-4MbBcCJp8g{=n9#FP_y+4`&a#Dvb=%~fws?;O@+87
zoxmY}Ew627u;&wFXq}(t)!++j1N|uXSf^ii&eF8Jo~CR3UHo%wqAXkQ%Yv<7!aTb<
z<oYm<*GZUr(mEx5q;~jh=c3N8jP1|jZN)12Bxbk4S$x{qI8LvMqpw@#vV9FmOjJK$
zR%T-oD83OvQkEINv@`q*`edyYuYd_+YU&VL+fMo<P=8lfynRhr(?SP&*Yfix5xmkM
z{T~AIlg^|u{x$R{5^Da_*QS=nXj4zr>+51i`V-WbH-#<tph*YqSj(4sxH?z2WNMR|
zOl9|6S{R9zv2iqoaS->7{>`?h`O0|pVqtYltBn{rXM_tI{0nV!_iUK%;!~?pVLF^a
z_;iod-8dKk_<1#%ylyN5aO6WPPElT3w;uE9N#jlO=fNLKZgSM1uNAL3X8+XE-P#sg
z!8ry^KkQ7PwDq83=&?HoC??|%W>~?#8zL)TE%ieUhI|zD!*uYzg+ImhQGbCVxQWm&
z_(}UQOgi~m0}FdWrVJGR0y_Cm2K{9Dv0pIsycH{Y$0#3CzRR9`$GtP4#23Vj(LE4E
z8UY8v=9hBLUew>XuiXUl;=vRZlHcInnfTpI-T8%o?@w-*vv|%TBd(Y*CT~)V#jB1X
zbrE0kRxR6F+EB@puE=`Q;X}5V{UtZe`H%ALeGGWy%qRDBU7ow1QRnyFQbj~_22J1D
zKN&&Qgg;Q3I#1m2%!bTTp$nxL@NS}9Gp>WUKvQP!>+voq0Cx3S4)Ny>vOhdqQU7RW
zd4?Oc<GmI*%EZU!%Uy7|)#jXP7+={Aiif!U3aIYynffQcyaIaD)tc<%&$>ggC?L06
zNKfD{?{{Q*wHfr|DLy?q=B{&u7fI5IgGn^~6}^PbHTtM=jB&+DlJr;~?8ff%32a5M
z7x!C2G~4Q}#)jw}S%kX*b3io9d=&_vHHW<Bd7=mK_A%N|WSVhk-RF*2Lt6Riz@Y}$
zC#oeq$l&_>kO9={cTM_l6X}bDPT=9V0Q8P~6fFy{mB+GU&JrPzg#WH;YWd`ONt7oG
zJNE&)TZd~aATL9dS?!^N@H4pex|Yk8+|1?^#^{^KeFi-|9?at6f7bAG?(J(}d5!1$
z^Dn$d6Hcig-{SOVJOS%Z37QVnf3}?3Z{%<B0z^VryFGV)4Jy(3<IKrrdK3SqQ7tjy
zryTMg-2BkgHb-X1W`zpj884<nujTd9U-RX>IY{UroBenpm@f%(^~x2}@W2j>7&|qL
z#NYn>@9{vN_&)?pw_N!{gP6|oMfSBHIDCHraaUCN*GP}j5jWV{j4c6b?8=9*10(6?
zonI7ND-JQ=gZL?ivs8L{0TQ*|t#NO}WlsU;AC(v0h3{+Ll$z%G9(G&HK6w|)?40=;
zWQzk*-|w%BGZFTB1@0(A1EEbl401#p-dK$98g+h7f-Q?cRaQx6t-%~$se)94^SQl_
z<U$904mNVzoIZaYZ@WWj8~wz^d{jr_R%iH>n9;)(`Klm48`ctCf(~OBgUjL`(Z*^x
z`i2ovL$Iy3Qy5;5x9{^KORom0+&pehaa_ikCg7YNqd0tq<!C|~Q$v;h4fv$@$|&Vq
zh4D9>>EN8at|j{#Qcq?qT(CZta7U=I)SgpVLX|Dj<+qy|*#NKH`VTJ&PEI$%GMb$N
z0U54tmF>k6V)wwIWk0>&#_O1Wuat`qdq>RA<>KUFNoUm9LJB*_d560*h6V-Wa>z&o
zJ}*mOi4v;5w~Q-^fV}%wOW?ox!@0p8PUb@#c3N@g=#AC)&PgBXTr9AzWCNi~=tZn1
zpP})Yi0p#Ums*foR2@%eW-(0L7<EsNTw=S~U*?)guXEOoi|%K%m(_dH+@6ycoe6H0
zqmilY&!YXP@=+3lO=0S2!z^io!4|8{mIqqu^r+WWT*X9e64Bpsbq2ETw64D-)p8nu
zhUZg+XyLKN{}6@)h?{00fDO7+{u-;DJrZ*Nr`;|+F0^S!yMO_8kC?IB9G3i!30aY+
zQms{b%t?$X8Lr+X^eH_pPmC#lDk(EMzq)GeQ^TJ<`!3MaX8zR4bVq~5c9F)<)w=A~
zHe9E9R0~9}Ds8%@$P~PuxRUyLEY|_0yHerqz*scz_oxgD{MTd@U|r(azJFG*QU~dp
zqc*zbp7l1o5E-zM=K!DEr1?+?TuVFJx{v!P{#c8#W)ZL1gAI~G!>K#8w>;inT#`%m
zC*AuDr`+1?*Cylh6I4K^5h@=EZ-IL<Y;UuGk>e?4-P`D2m39IXNetXZ>+2GNP2oXr
zEG?16MqU}Z3Cb;4*$J17Yl*+~e|P?2Q}WfLvm?~K2~4V~jLZNyqm}_`7XMM(1>m;G
zl_v{kYx7M64m{~_@@os$%MCjNNNvQ8xo;hXS<sESHvV^U*xEN&_vB?u+<NXLRP1Jx
zOXz<VJ>Rs_^`*)Xq)|d#Urbpe!=sC1PmjZ2mMBiCWZ?0x6@lH0Dx|>t791_6A7P>i
zpm}52$B0ZW@VEOcKRUMX<6>;PBTtycBFr{vn&1xgmwYh$uFaC!KX()C(L-q&$~dcG
zhON_ab^t%U!wNf}@Q^-akMoAZwuxP@v1u_?l~{dwWQ)VtpE(2XS$61Q$7?rlN#vV1
z>fu98mUXf<KjV+R=wl?U%;%MDWGyG@6CbRX`QLp2q-7en!;<6$OKPvsytaxCWMNu-
z99)sKLXgcY(*((virvztxsV>uBRDKWf>8A{AIw%UJCm45`R4((3l0p*%V<Fp;9kyP
z(Li6SZ8Lhx!a$4?OeTD~|Fy6p5nsTpCKL<vbz@m1P3PR>bRUJ$*BWYRJ%ipaK)5XF
zSY~WwWH9)vgG6+&8QApW6K=A2bxPUO6X|z(c}G?_^{1nA>va@O@>%N~pwjcJ8?!9D
zBdzgf7)MGkj#b-mQ@`ozZaMOu?^44XU{Q#=u#c6*S0M_=Z><@j{yzlYQun^fq9!3H
z)%vcvi*&(PJt!PCXRr18dABQJJSn<|1F#stZ2O{J>DaJ_NnTHU;3f*+0=P_5v%DJF
zktG@-F0VCs^Q?@?u{8N}2rMSeC(_=m^Lp*JXFBb5TFMa&|K*-1Yf?#f#(~FY9c%_c
zrTbQj3hASF<;L=bvc}4MNL5np^zY}9WuZN$Q&MJo6TJ~^M5lL0R&(*t*{bnEqm$(4
z+G~?Mk7l=VpDXcp?^R&{q&=(l!Vfm(&plhkl`=!B|HACTVByeqDxf9%kr)%^x7gE5
zFDm#~P!rQJ?1uL>`Z)Ga4Uo1qt^s*3N83&*sSipiLFcdp8ojW?TS)b1DJGAXt!Mc6
zcqHG*a>I8AR5>hW)A!|4a1n*L=7I3J(<qJ>3$$r8D}~k~C!bUoLJqRjXjIgF7u26c
zXQ579pWj)`l51KXyPm1PclNc)B{5|o0HmFKTTJ;BV3=U*rp@)sFrl2_4(}Iyaf*AN
z4|nEb+sQfK_Ky5PA978Utp7VDqfJ<R#42`~3SOQs#M=m^Rz^S9T>U0~%Rz8<uD>dW
zv7adL0f2FMG$r~)o`ReVnC@jXRtyg%bHQ#up6GharKTK;vbo_2D15M_d5yN^MGWEP
zFG0A$*42p3LxpN|ILoc%ETGjnXY0n>lC&q{gd{emjEcsg@*`6mrlt++Cw~GYP0CQC
zqLk#h-RPK8Zk!e-cH)55Ouk(7R#KfE42;5)AU;1!64TaF67(C(K>z&4{t#RH&8d-;
z+3A?jvrcLt2FIFTL8ExGZHV3YUdSdg!zjV=&4mn72#*!3BCdLm#IxQd^hvGJtstQk
z34JlX%QLw$K_XMuFnf1((JpRnhBgm%j9PywYZ;FiT0sS0j4XC_D|&Jzi#5tfyv}GT
zZS8lrN(gySNlx(#7Omc{TD0ecBTc7049PDvbLKr_Yh+yhlLl<>u6J@+UKXVEVy9Z#
zdFQIbvA9QoZLMI#;rJgPd@u&{R_F)lqfnbg`2UTSY~LP(G!56#mTp_V{3^BH8lm(Q
z6@OB5@Jb2J3BA;w_%OoB;2T+3Q`F8_@yYd^CE25a;vSU%%9%wVRO>8qBBXWJ>1#7n
zLX<3+7mNs01$hSOC9buta)&N<(hF9nYqE?5LS<`Juw{3WqT5XGNy_kDwVW9^zHV+}
z1HB##6#JZ+vs=F^s?vdBDq|3Fo*&BG%IvP8>PW#iAH*sMo&9a!OsP=zFNRqPV&Oo!
zGESr%b%%$_kXUoLDTgk%Hx^Oc(4#z^+*wTIZbqdW;Va*{L<=@E)qIf23{w5ZSTsnv
z=?bjSnY5S~@qUPpA{qyAKcFdqpx0Ry6)D1!zLbX-m%pr`uZ&xJ%-!oPDi9eG;`^mh
zuIcaG$fpXFzIWEqzav!@eoPQ|6&~MniP3!`_UM<Htyw#1&F~v=JU}~xQHRS=WOQgA
z>Nc`cMJ5>$md7}RghSSc!Sk-s`?aT1#u&TIOyLRXWO~^F+|5eXpOSb|1PE5h@_YV6
z7&5YW$t|61_p(3;&I3R?y3;Z*?DNt{eA1Y%u?oK?foNls*o9dbe_;%Ks8IKr6;c!N
z>VxBvL1mcfeTlv}_p6_5dZV~5OoKMl0H7@OnI7C~vSy5Nv=!0>r*76b_tBfZwbM8~
z9=Qa!M-Ev1KH|D()s+&S*_0fxRCsY8K2>aZUf`We_G>P45e>s&g_<Vw9Di_N1pWU0
z=d#N>6u#YCJVn5&7ZLXPjTqNs+DBQ*NAsm=!T>Bp*7<I2@0nWA=cw5#GHyO}l9PBe
z#fRvfk2<)`a2|3rF62(Jul1zV(tr>WxG}*$!pF2(FKIdMX|AG2YQUT*1J+Cn%}l<O
z>zF&RWSM1B-J7lGXz_lhy-x<+79)uwrl^ix$mdq*SvwNDmYegUz^D$7*R`M$oIl2-
zy6@Vgj@~uY-}<)hKet$^Qm$kTJ`i}@=q4*t)CRCB5`~i|$hXbNHKqdOC<|H9li(bX
z@k~j&sIX{yCRZJ`@-?fiqf{B)FNmvz{36w>W$np3G=mATb!v-+Llez~g#xLGe^Mss
z+o1m3gI~y4zg7%Vebr$DxpujJl7E?>HR_Bt1)siGC@+ol%`G-Kd2DF03afms#|2K<
z8WY45bL*99#b0*oK|7>2gHS1l+y&Tf4EtKNpED|itJ7U_i6A~`JMW~}N%b(!_fTs4
z(e_Adryj*4ZX|hBNCkax^#?lYU-_AvnAN6m-~uz7`Q<3mbJ`P$;aT$*TV}^FnS<Dr
zQ_%a@yxx!J`f@#C8S1}v@|xDF^~jKf>JlHTCjG_}GOg-FiVp|sbD$u!l3G9}ObWA;
zJHc{D@<9#rI{g9aGT<TD%=O~l)H<CMAv!d#WmsaeK840o*$T{}i(A*q(rx5?mvft<
z#&Yp2@dk@stW4MDxsPop5weD=Jm{&$ouU%5st*40Zn&>%8z*Y1Lb*7K_tn^xmTMhW
zzMezLVmOYe=k;-W(QLU{MZ2+J*&38R(Y@&@YJehlT}Aehp6A)h25U^qPep)HUn<jJ
z#xi`>)qEy6J`aSG0v<j%L;oRgYIFTXIEPFnUkT;P-VG^UVrfqq9{kvLudz;SF-STY
zG6d;1#SvI~yUr)*`}bd{%8bMB*|~Ff!Af;mR!3tYYiA7u2dt!Xy%f9PTjsLu-HUHo
z5{rilpaJ?1r(VFNzH55JkdO9t4YGTc=US``O|hSC=tb4E9c%yS)03?QsgNL(K%bx0
zP%MWVeQVwxSv!Nz^=_Rs8mZ$z12##1Bl&DnJp3XH{aanC9eS1|!b*mTJH6+6NwPER
z%*p}H-~+~BAx&lGWxR$mDT=|%EOX>M-}w|J0`APN?f($Y5#e@~mTSFgILYXBU)%SL
z*G743%j8OmNwV$2aad@|HN0$H<$V#S)zoIQ@qk+TCFe6Zc%CfeWpR5%e1Q3gq^y2y
zx9zwY2vKSXD5^uX>br~w>$O~q+ZN_3P>&`1%frRi2Z@0{?O0Ov(}Q#t>h@X9<LZkV
zCYCjBZWWt1JiU6;HO-vmMu$|qZP}tt1X0c=?MMv70O)x-w7wKzZK!0g!al%*#;qcS
zJ`I@^`U?l-e5N1k(fSn$P1%#fbka?NJ2llzfwKHNQTxi#A8nGPN0TJu4BWwSN`c?3
z=TKvBde!#n``SqPE73^%yMuT%+HC5tnNRQopg^K;Zq#_229mfJjooOEb<!6(>g(Fp
zUB~*jb{-+$*9VVkY+s`ntMqpsd49G(3hBf>S$~VB<ag%>w(q9RdFwJ@Ae==n&I+lR
z`b<(4?~?!O(jp|Mu#UYpuz7ed=m_#txjOGDEbcl%0L@rCQzVr7t&eoR72zBYFH*wb
z&$e%1QJjEE!ztsFknC&qk&=IL%HY=o{BZSwG?I6Zz;GEWqYJyIz=8BU^^L6D(br-j
zf0q08{<VD<Lb=}2S||AhN1nIg_)hM0wzU(Zci_K`ZgaAAdD*_&=Iut(qF(&dCyE;p
zqc55%?^``kFQO}erA=)jhM%7t<;o{bc<ou~yOVS#m^u+pjE2HfJ<{9MVjpYim9B%6
zchq*`87Zv09pk($f}FDCzm6xZmX26#(kLiodtkNu=Sq3U3?|9$NFt!08K;>CT7nOq
zvdEvD?c%P5Fuufyadr7`4L2laWniz@`;U_9yfzEhWPDsl+kKyvAR1>~!CxCXpxvtC
zlOjpNd7Cbz>ByjK^i?aK=0>j*!Iz_a&3F>?!k6?02h9;s-@V9I1MN-fGviY;?0kw?
z1nJ8e(uF>H{2m48N~dvmc{^()bZk^t)H`M5ETw#jrrOhrCb#}ONA+ga{Y7!U;8jQg
z03SxU|DF>QP~jertYxlF=GM&Hu~us=ywphzII(j^p7zmgNM`2nc;s1Xi(lkTm%OPn
zKa-0i_0;iL{F>)JzN2#p-%W6O?+PAxHm3`Vh-fwp@7>ible)ucg+jjzBUsNL`Rl|<
zZqhWuU`UA*aUS1({$8g+Bg8?d%XY_9k~q`M`?ETxwidCr+MU14TXQ|g_N`B7pq27$
z`e2^n^-FS}9ym61Qo)09491c4hg?Ms#<N=^^Dd#(Ey*izsu7f?eA%r#yS!d9Ec!_@
zK9)F|J<D)3tB!DZFEr-`V!iSy<Dv{+dWaTVyIP@GEYg+4sQI}bf-v%Kp09|(Y7La(
z%q(J`^p~pfAlfoJJX!K$=$F8jzdR8mW)+i}lHQzoLx&?Jt}q-y(DZ{}59?}}w9q_X
z@me{7oB0lAyl_ly`cwBmgn+8vK=g`QA*OPpa!3U|@?k%P=CY>@>ANzf0fgRI^>x|U
zzL2yBAk@EPb>+*2M(~#K*(d)_XFfPP3Hh7+m<+)#D#>mE<u4)iD9+$cU_K4ePUa_R
zZrM{z3kofhv)FxVC~an|J+5uDyrRb!ad+WP_E7_yQ-N#a(4B58%xwQ42WMv&?>ZjI
zv?;ritAA<0ja4~{GYl*z%GK7Qb)(D#1>?~9*`(E?)|innnYI?b(IX(&{h3h#lf2~g
zjspDX3qyi?H8}D+6wappej@kSUVv~{kwD1&X3M*qh)zQO6JZ)kd>Syk|C<^m-|eeG
z>uWO?8Q+;b`quJ%pLiSg-?<!3=eid;68=g3HYC2rgv<xREJ<j=S5H$<%IYQ5Zg=Mj
z-33%~X#n6`6X%+D!kdiH;#lxf>|#Z_itTcuc2V2_{7VsG&|hmcghA}FC|%f!J@=j#
z>6}mf&kC2Et5D0&46hKtm%8_)HKC8XFzGYx-r>ty+a_~PQQIt8hR59+i7~FS?EDS0
z64%!r?@6t#wzLA2hG!N1s(sG;YV15IEvwa|QY?&*pLO<v7pq&)UKX+on_uqFwe&iC
z7ws)v%&)76&C}@W+Ip)zkvSn_QdmDORNH|9RMNJo*zk@1qW84Ctoebe_oNQnt!6Us
zu0P8s(xP38TOw6X)mENeW%RqUWFPlRbMky!T>gSt3mhAgxM^`EdZZj>!CChb#MSuJ
z?#gziGcgPfRG#+T>?d`2y%qj=savJ`s&Y(IXf!|+_h$rfq?rr33xC5d63q337PS*5
zOcr}onmu6VOl@sv3iGqp5YaSM_)FGD!!_?HT2<HvNn#^T+TY(+JfvJ`Uhil&w-@9d
zdtrW~1M!+0WMdo9|F+d>Ttas8rcnb8uhay${oTCZd(8Oa>OAG|&6J|9rU&;)`pyYZ
z!4*fk9|UE(urQ+bR=taQb?1~fBq)**ow0p<3zGY}1Z(Xk+}6AgyJCkvn#wZ5-NeQj
z@3xmqBpG{$>>d=i2Ek-+$QhKbo9zn}ICk~d@94*^&BX8i*kv>~`F56sa3;f;PBu%W
z|CIazdAZ8?tEfxB@MK1X?H0~w$$h0l*gfLQ+Dq&LaY4GO+1E4Ikn91SI*;%YhDOJe
zIbfX<*8a$Sv)8IMg-M7=+Tr7r{;A@X>&RoB`l2*J2p>JDj$?j?aqj~MuFsg%U==#d
zP&+=3`%^IqtMdTKW6iXFtI4ZVq41+ddD}t5S<>6X=e58v9p<`XV5bF^+l!7?d3%bA
z2HX)2K>aTDDwONGMAhs<hnkDrSKHVZ=KZHD4hjQ~aXe?b@YlxlC#Q9r;0US*Yw-%>
z|Kl(tsS~+Y6uPAF+W`Eo(^9Haq|ia#^_osylW}Y+`ApH>gg4D0$ADJ;6z3xy>S<~1
zL{_sifL)Br0J+6-_OEWevXLkbz@;$D@gSIrf9@J$D)m14K}Yup-gY=KP75TfF-<kW
zIqZ5J1RpBxfK%Y(&`&7LnmZlpZhU{4bxOsp)pmFXU&Z@|_wx1c6l%yVMXKWg6GD7L
zPU5I_By}o)e?Ln0EoE+?FZ4|9W2eqCT>I{8>pFrAriPzMFO3}b?HGb(d#3;*2D%?m
zZ59%grR6HwxY_%i*iVHs1+yKcd>A{<8^6!I>fjOlmSTD4Kp1l=i8bp0=rJU7-At^3
zJ3+@y7n1sE_m1YPp@P})%l9;QeJESOBw0)J2Q+mqI-q^7A^E!#pB5~<A9y?Ok65z;
z=8VX8-#~b?wVW*@8AV;zYUvX1^IOQ}qm;NdiF7@P*cFX{=&&3u(`bey$v{O36B!6{
zD++F9&2{G$xop+>3b5vAi;&s~GKUm(gfvLBK3UC7%zQ4&44>jF<|`?l4Wf*7l~>tO
zLP>R<L}0%Ff!=@KO&lsz`UD!6OT$;2O;1#x&kiS06MO&v(FfIM$4_ZHS8~uZPVkgd
zqWD6ZAP>+{LeJxf8g)vI=3e-*i#YwJo`0A_$@!<3xvGQ4D{$|_`Vna3QRlj@GC~R*
zKz~J`Ke^u#rsIU&N8v!Bt(?4pp7Mk&o-oiu84u%Z+VYW6j#X0H%_q#ql@4YtP1~Xt
z*-8um9z?wA{&p9tEoO!=u^>35CX@;e8uQHG#}G89N*Cbf2A!!u26<iKEwqw_duDbj
zl3lh(4;^Ob>?2m6#XT056xufc-HT1;zw@6yZWW3lVZHD~M~Xt6<>DWFdlI30cJear
z%|a8s_DLVq{y?+@ywjiG*BuS)Jl|pY?~4A_0;PRCwv&Y(%ofE-2(f)2p$OspF6i|i
z!T>(VXMXlii>w8cQ!3oN3OGi0186t#UXePWtfREJWWEXLM0rj3We_dl8|s~!t7|cE
z5sz2g6_pJ&PLff^on0!Llu(JX<n1yi+NY86YDB1WYQ_+%s+{Q3iPcLcvPh-Lo=unP
zSW%v|V{|5%>X^u=ZCmxk40~{&%se-K(k<|BCxMCP`X0rYEi~uj%9%lEAbP}?#75N@
z!e`_ENW4(>+Ikw77H#%gcOqZSXO?Ep`h(96pfR$~ItFvUe$v}G{c&Wi^+?2^PJ(o7
zMgGE%2rZ4{R%=eyrDtHM;0`{vYkn%<k*v`xePa*a(Z-4e=Yube-^Br|@k@&1vA>m$
zee&JRzm62k+a98uCZmcU&!Lvz5pvoc|Ng-%c_PSq4qj_s>!XJQX|^fltP~yh6PbG(
zDUd_FCnYPFr!!w#<;Wbfiv}pm(+I1W5P;tItzm`NPSN*(wKbDPnrBdFY`&WDH=vO`
zIoNSE>^}qx21l`t>f<^zyH&=m$n*56dlKm&4v&EZs0}1ZUMBacb9;R7m+g$^SoI@x
zrJY*-#<!crKn}8c%1@i-W#NccS9!NZbmIAVy9^ye-?c}AA^uAndsDwU%=Rvi6Hmk6
z2e&!vmpPwC!w1p5|3rJPa(^uc5fg3oCR3r#Jk&0~S)_k^W_4KTJk&526%Or(OHHht
z4%B{J$k7tyms(CU&QFfqvq|o5Rtk5*D0qKIP%bYa^UN7KCgr3j#qj!Q(<_f{b-$~-
z2FGgu4RLHGS5}Kuk<VZjDV&(HI^A?jOUot|*3Rs(xFovFid^jEX>9cvAIh(@9bbrB
zNP}HyDSF-Q#*Dt7GW*@t9^EFyizaO6HHt4yoGfFmDgbkh%5+G?hyZcm-qsul*0<9e
zJ&XMeZo3ESHX4Qeg3+#W`Oc%VZg`cSlgplK5u1oaJvr_Ee6g&Jsa(sp3o~kv71_^m
zn}+%*`GuNSZ|c?131$(G!2{h>Bs#WR#K0_`0T7tNMPwaaoJGo=r4p*3F5JJT+uELY
zrqtMpw>6wafxOf<t$&3}Z5zPYJU^M&=uR)Ke6aF}Z7#lR_iCi_DzSN}2A-Ze67tau
zV7YcUiV{j_hEYQbDlINPyX%M@k`{Xn7|iT4n|j80OqpgJ8V9B+Z6BLlGYtY{?{!<D
zeXJv)$TU{%gMyr0_@Sh0OO)5f-B+D`WDbjkIKRqmzp(Trnz{AiCVU?*<L<=F8^;Ib
zQT$$@$6M1gC`T4TG?sL|CUXD`E^&igpC8y?A*8sdOH^r<*XFtg1_u888!?H7!NY;m
zz@1I6#7hc)CCwv;NY~B#?=kv3FO-7{6fths=QnFf`A{$S^Bdv0CP`!=pJ2_wULVyD
z=^LtLoBJ&ajyvo-X(^wRtMSez{k3-fLm;$SoeX0Gd6PI4knB6uh$4SyK0<;r?l+Wu
zOGru>Yw8X;n(g8IAM(!XA&S3k;|nMqlG3$wN_R^v-3`*+NP_~BD=b|LEZr>Kp&;G8
zG}1^*3n;&L-@oHInA17>&dfdc6`$X|_26?uV2x0t+;y~--WBP#CI269@0~m~^a^)B
zva>vDx^Z~UN6sm(DOb3bXJC9Lc-xNHJgWII@p(+z)1k^^&xiee)wCG~B9}`+4CA`;
zK*IP*J3&znNP+KS<}0WR$rVtiPa6qt_w05yq}E|AoQ|O)v8uHv_q<r396ymL;90}E
zz!!*H_8!uPI6xHp_ZC|Hf|cXS=RBkr+-z7q_~=LLlwa)wbDZ-=tutBTV+~Tg76*1F
z;0_e_P0BfYGW_fS#8LcTQ=!MbR9A_>O>~iwpI3F>Law=-1>)1Y#-P*Yiak?#>ZDCd
ze#G=H!U(kMWPwk?M7>nR07R2q?26u8x-D>q$^mIx<#?psE8y--TO~FZur2jcc+0&M
zr>`91QZRSG&+1p|e}Fff0|rR8X<$GMb+7>uE~}@!luOWsnxk{=pAqwAMjXi#!r(!S
zao3#9hL{8FCj+_4CZ2hehf;yZaaE*c!9~lPO6Sj|Wqa(|tP7Dc(bY9kDS~<EZfOH9
zG<b>3YaJn~9)o=Q(aV8YrhE{vNEXGuBQ(<(@va1er7+SVx_^c?!^K2b<q_F|gIPy~
zH>L7U$%Scc3f!QFjlr0Pa(|WS9#?v_&}y0L*|;8l;R}oH)oI6vU&lOwf4RFez-H{n
zJ)iE%3c+1;u}FJ^oZypvb`C>Wg2?t^8^OS5iuJWI38!mP>KzKui(k=>hL0x(h;PBx
z5N!B*H~BvR(4v%%f(O@!=?Mg=!q$1PdPbyxaY_ctZV)>=nLz3|uhG4XD(hHZNE8Cr
zD7NJ1T#tPg^dS$SKMP8T2mZx-zks@)Q!Hz%bJ<ne3gs+m(x~j)zOQ~Ku%6W0<2Rr$
zKy%(pQY5AL-fC-4oO<1?ZjaFusi9O0oi~c&rMkX`?`Jd-h*qJJpyd&23=giXNPwm<
z@Dw-)t5vK_t8%LV0KyRkS<iR&UGq2u8?2&U-p6{173;(6Q9&~2z6N~*b&6&p%=&Kh
zVXk5~+%fT%^nGq9{<nQqgsVyd2B}xgH_1O$(=A3iE|CqP5JNsP-mQbaHJ1t18rq=)
zDLkES7%?HCw1xpVNTA(cDP)Pm$3}=D+vB;kN^-ZkRdimhgo!!a1G9XL`h1$4z$L0X
zsV4|-Q_B~RVu(>EVWem8SHaxKkTr!?B)Kd}niF6Pc9LbH*3AowaUJ{UkcRS2=V@N@
z9P3eh>D@7EL^9~MJg7TYtQKy~fAVwmI93#+p;C>_y^m5wHmhTbY5Ss&;ylHGL?vkQ
zd~t6+HAu1)?+KeR$%<ls-XdY>)Mydd5&1!Q<Bp<Q17Mwm$j60z*{2w-5+*Z;yJaLg
zC_zK~h>DPbS&>HHV`w9JMiU0wR`NFl{ddM#&Nl{RL`R3)_$~LXm;;{Dt*)Q`1ME#P
z1TK1n4Tczccx)R6ZW?*vJ?a&u|3m2A!P!{aG6fDmcX<8PS#9lV@$}lK8v!NIi%ATe
z$Zxwj_XDZb;!lgrrN%EGac+e^ByK>(Jop#0^lY7&eK#nlvn71ajGv$_Q-?P?{Jg63
z96va%zAVd_`p<2Za?YS;8+0RUJ>LOSeIw3I$#&KJUt>DW*y=Ojn)o1l$11FG?I4@Y
zx)PKE)8%{-;He-0`PdUQd<&Q$ti)cHsu_Dznh`m$pME6PS5B4iQ0nE~M=~S_bBP?x
z&Hp3B$x$1cN39FQeO}BZ)B3K<2sz>&c2ym|zF2(-t;?T_R$|cpq@zpJM_|fBCiH!W
zsfE4COe`aASedc$vOd$%lb4>(6k->+%P(n%UBZt0>BBhub&P<o8C$UgU{heN(I5J=
zeVw`ZN>AItP5?Oi*80_xVWcel%ipR~a+>fbZF41onH`f}e-v!D(J46w>UpUjX?ZVx
zmY@g<n(B1fAf4_@>>Nfbbj-glso%_`{<+vCXPo|-T?%gnl8|#kIHiLq3M$%3fi-EJ
z*-cNdCA87nZQQ)8WcDHYhG(Dm-JN^jjW404Y|mS*iL^Et2aIqt^9kHYm6b>iR$8mZ
zPUch7^_@1zM9P%iMD;YpU+oS($2aVLSx2(e{p@Y85;r^-kInzXy=V=%sbPVudd=nJ
zRpP;P$rs}X;p;Vx1JD=^`A2Iby9Hp{Ls#f?+kb!wkyG7?x9f0#J>PV`(UV~&MM@qt
z1?A;j=`9`v=^|)4+YM)?r}Hcm+!N%g{%Puxmp9)Kk4AckgsNkdNwY|VpM%10lRg$v
zfNQ87=iypKAKsHLKcqA~kK!4@MBZHX<1A8M2-d8JsmWh2_;gs52JANGmC@*^?DKHD
zoxvadQ+36O7ZEz5r>4ZISvC^UGt8PUgHU2gI;TjBtCZwIUn7cjZ}RnK*&0G;XnNG6
zzn+M6dg>5!vwKJUo~M%Of-E^>a^1hgwj90qa7%u<+sbS@^}`5UE&<K)h!;`{UAzwq
zeJNm3@+a-h@N%tS>-{SukJ>f#K3$_W4l~YI>6a<y_}RtV4pFxAu(qbrz`iHMx-k&c
zMk<Nls%z}nmUa|%en-RRX0x_2;Y>U7Z}%2iisjg5Wi|!`7FG5jeCLbPd=^jo(l?8#
zId-HtTG9^2bTt@~L|G;04tA>)8O#$JSrKsK*q}b6HD5#_pZ@)cO;#X<6yN(6VsTp!
zIN{HCiM_5o4p5f0w1c4SfSQ4SjP%%!kd|L(y22C4n!WM;oVNQJul0SKx66q7b<wsg
z%<l|T&S%*k1f&%4Up**>)U3U_;t@K6j%>=4C5WavJ41Rw+=@;d)064%yfPVr-^h=O
z&YU#pJEPl}DRft>w2_gh^_sw+zDW71I=>~ve&nXQgZTB2Ctpp=j!P{!Ueh;K(k;1!
zlJ;^m(dw5T;*(<M1}jw-odDR9xtWI;h0J`#r!pW27(f2#*}8aPs29mu9O>#VPZD`a
z>*?Y38O>Z?$tKr}MjX+(L?5~NdG4V>X3$$l_;Orl_QRh~yQ1U+#9jVC=s^Y8$&Q^z
zZ<g{jRA%p0SG({76RwxQv7uuK*7|;;NfLbuRKw>2G~t{WE%vxU`&yw=!|Oa=yBPM)
zwIWTa-H(U7hT!7LI7@hb(1cQUKxPP$Zr6o-M3KPV58NtM+g73(douXi%MmmXWPHcE
z)jW?d-iS<a_4F(3tSQ^_>~?zOga}yR3cwp=cqhX+bJ{-u4~MbtYR)CPa2vOcNLARi
zWIJmg6ia{78uZH5G>UHw2Za6g6N-10)KT(L>(%;K)F#)+cLy)h;EuNofQHl#g+IEA
ztB~<n%+zsQ)O%gO_m|+6O7tBzFnY|%eumDmfJEC<cR!?wPFbj#Me7PTjFf4Ew_{%G
zT_eSGmX9Yg#HLJ)rHwskz8+{a8oE%&yw@8;!P~8_qqu*C$@Te7lqv1Apz%(+e1A(I
z=^ZMIM6b2Hxj-2SL}4x^oFZGt$7bALi9%B5^q}>rX9PkLO5{=TI5LH#TwWkgjvOGJ
zf>Fb;d>miT`3ziR|8eTMm08(~pR?jO_?Jelf^@4VdmFYFu3bH%TkEaqA07=R=_DWS
z!!`f7KNzQ~+NtKtI51ns7HPzz*;XqgS1^u7d0ffYSVJr#y@Bc~?a~N-SJM!Ifi1;}
zL3YPY_BTB~30fGjAf&&wPC+Td{D(SizO*CLIlWteSRd6#tWtG<ET8#%9FLouA(d;4
zfuuW4B}A#i5$e{Gh}4<qRP)lN%pp%|eiTYx;tp-!V(cFhYEpX)x(yxfft?i9!JjIe
zMIG|h-T#VSaO(bW7dIiF@#SKAxAK;H(dPz_A|N>Nprznsqdd^66g%u&aTe$ETx&0<
ztp&oat37r7UADk=GWsrOila8N`K~fU^eom_V^*2vx18SlWta10z7+#BVAFp9G7e)M
zQ6A%fW8;o>ZK2!eZ0^0!5?bw@TpI#+s8#09iQWO+gTRT+2Ys*CqL!<QWSeIri`=>$
zi)}I2W?tt|@ARWW8lDu~Ob*<hv=L2ClS>~=b>EF;fnpaUJ{8H4jl}c5x>?KP>yaDG
zE<bX3W^UZ!9l6?%5sKYTM<krPS;R7@?rDd+4rr$yVuko{uUL!gkkW3OM>+0Ck0Ip*
zGxJo)Tev8@!LDi4HfHy{SnA$XA-ygNXAFKaK%)|Gr+!}21$%B`G@jDZ{86j0SRV)p
z_$*ktV)Zowx^ne4{8oxr3$lyYP;N8ez3~~41o!>+gj~Qa7`pjz3^Y0@rd?(rl6qu~
zp09g*4)leO0DkpKz7-%}!nYp-?mtn^OOMcHpvW6tG9_UCa~*j>YG8PjFI$0!9VvD;
zI4aLc^DQkiZ(V}TRq^)5XwN6f_oHt~Jx2lzgO6fq?K?mYiJ>dQ7rx*ESISuru98Xa
z16Nlc(iL~Txh}M|2K#K}ZI6Wf5xcv;$q`a#pSw-EqKM44-t5E#qlz2835E>kmp2O)
zr$ZE4VCg@`Lh>T9_S5vawxKrI!>W#zHOExtBvs^+ySV}WR{E(MC80k95N$0JOJGTf
z(2D$)g;z#z8UwI{0j`oiPO$g!OTK`bQl#sviFq%6L`%(hme~fK18-TW9l8>EmX-OC
zqqWCgw+LhPN!va4B;s00T3eP>a@n6E%bmY!-}h8A^(unl!<R*Uj%>HvDLJWb2|L1(
z8k_oL#b3-oR}6cpK&jLBAfUnx8L+<B-eg!uIa}X1B4*mPun|hd)e}eVSS5sql6b_g
ziaw0?udFUt4lzH!u|AG@8p+YqW^0zLh9$$}MdDXm^EK$><6r=${yqI+YFuJ&Ys~fj
zWN9-kZ0T#|s`=p0ZbPS;Enuq}-hY7f4!Mj|(-iX(CG7Ck6Fk=jYD57bq=l$ck$Zp^
zvtDEV(=ejyb<2ccL<hwf>CjI>U*Tbm3L4qEv_9eQj{o+nNk!5+dpT9T%{B<+7PbSe
z5@aL;YL?d$DBY{oyta9L0@uyk<9bY-OMh&=|FvLyVA)YG(0gSFuMx=-e4d-Z0e4O`
zDp$)4(r_C`P52Ls)rMS>(l|U(NjTWWLyT?HEJL+c7cgSrS{O+(gPCV^&gN-ph$g-6
zh9tw5W(z5J-;wuW*8;to4lrzqG~!ctXr?(e;e5d^jgkZ}!RST*Cw0VF#Qqll6<+T$
z7*|BLwMWt}c<Dp)iX~%jd?@WuM;(h<R_|gRk6maE^&V+&d3*BsxEFzriM~I{-2BFg
zud(qXn_fUga3Qp$^s~f1tjC}TKkuq`**nuyZ?p!>xqOOT7*2@MAXZxkn$%*;SXp8x
zPe6V<Xf9H9D2gcR{CE6?C6)&CR8F*0<oDA+c88pU_Q{F0*e|3^@jV}_hZ!y25m-7o
z>Bj%cd<PN_N@TgC8FDt;tTl<wrM60P8J+*DR&o5~1@fV)z=8HH`~4L6y4MUd1Hv^D
z&OVwhS|wh!ZHI9}@+VX#11CaTR_-{L%|YxV6)v_a)2pJQH9CS|>H@w~!(_9d&w^jP
zX{zHy50mM1l$#f8aMq>R0CUSy$IA09NEi($B~09=7dWsc3+7{EYWIcl9b0;Il5;-9
z*29CBV^!Rxu=8RcBdQY&_d!%_Mfz+^5t_$P<ZP`Hj3|vbo}$ZVBZ-Bhy@7?yqoipb
zLI8#6l(q?Iy2MjTBVJFsD8TK-W>jmB9GtD<q)VIf3^n<GFQ)M%5OLtwBN~8M6{Atl
zqM@X8U(mXa1w*8xTN-Ssd*|7v;c*hv|GqM&?m)nXEt5%~rlZO?LSsbmWF^x0lk;2J
z-qT=)rZ-ps{PHHZ;w|4_F8}tynS;bP!MbR<OJ$B->)(BFw-KIVQZAc|EM%`cC#Vgy
zKe>!u2-t`akcFhcIE*1iCmgL+EJCmD&kaj<lu2zcL=}E<)Y^H7-PQ2>MCr3rV28}U
za`VzMcc`*>LrweA>ausBr+=|d$VmyP_YsJZ!qa2r93k~E#G|8&))C4Zj*@c0GU6C$
ztSYGEV3CBCH>D`rg>#~cRgwD%?gGji9~*V~qWo^l-yQeOw2EG7u)^5QZ9b*XOy@7x
zAFIgD1OuE$Jkl42*wGMa5h}LGS^!=Oj8<;e&?jwFN7|QLv@bIx9VCR%R~QtB$#*5|
zcZEsNY;37$dJH(=MgJoSpwJ3(TX-{{Or57Y8<CHm)G@LUfoL6>Z~j=)M%Z2-JUcB~
zw{m7D6RzCL>S>Bn$~s?(1?Vq?X$S~z`vfnb?C+t$TxE0?fsO54E7Js)Oa34-CP&{0
z$hVAxPeRM42hde2%<sbz_oafqPcPLEH_fT?ME;f1cX6>F<0^_6W5Y%&v{c`_r*hhM
z6nO~1+nV*PTi?*7-_=sJ5Ei5rp>)<ws3m^TASY+=PpZ&5Hb1N)Ow7mjA*)u2OV=~%
zN#H2b*F@<<n$?vbTlSCqLzc72Bn-MCuJeC+erN~*sFaxq>SY#}26k9Na-LdikiVRX
zBMT(|FcgzOZ6bOJ67<OTrju<V40P3s;&OCnp>4_69v@kpGFm9)KwA^~l)pTgz^Hd!
z_2SS)hb5{HNU(x&;`UXP1i&`|=Xq5ltTL))4LSAI3G6fiTRj67D4t*KVt^S!CjsN?
zj<8KUueH`D$+8@U&w;R3B1I&m667)D0kmEeg)6wfk@2#HOW7#Wp99dK`nR@jw_zlY
znRrREL8Mvma_)U#;r*$Rq?C8pBz{De=xya4BPF|(ESw^bK%g@^dg9zX0Z|c?sdC4V
z_j->W)-uuGcA+q&Ri;YxBmm7O6)8HNf4TlC<<mOq+BU(R^K)_e12GntJ{!HQ(4=eU
zHADc+#72#=`e*;{+`=)6)J7tJ?6D>*z`%wxVBoE2R|?-)KYAP_gy!HWwOb2tH{|sV
zm~@#EsefhhZ$63H4DM|SOoWQ8h>lW}G05&Uu7lqm3Klw)K_rpttz1!2N!!HeRsK-;
z_Hwmsz)CsDy~MemZy{|0CXkftk5aGNWaFm)g5Lhi?t!1z%vEIZu1-sTk=4Zi^3i+c
z26`%_=-oYgTQB`RWxp$IGk(aC#a#Jco7<PePQVeV_ucW@&+&fT0o?wsFi!G>g&1E%
z@m|BB)nGCoRC9IaNErdEob+eB@DU|p_F`&-fa=KD`W;0dWygksk0L{PpmvrYD<y|d
zv`kC3J#hw5xu>QP{u0e+L3J1RP9L8QlmB*5qb!%XHcG%6T225%q?0bmwop$*z6MJ;
zF`OjKi6zpQGGQU2@J2l|PNlS>p*#iLowK42mQMfF(orbOMm+~%Lrc&`i`a$4M1WvU
zD89PNI*yF6JYD<u*}C&+L)>z+$S5P=f8$aX1n7Xq>ePlm0lVkOgj!a!=!BJ2s?uxg
z(5GwaOpkTtNOFS8z2d$iS_KxizIiYDt*_VI_Bj8XPPkNu?e-4*_(mT)NGT{#`}ICr
zyQxr$s#j6G+M~~NDdZbhg%}WX1013ncS@yFw0=<~2}PQ6+vbPyaoAB?32$CnejYb{
z(+uzvN*xw{o{2DByVV^C5hT8%_aD7KH*k}bghm&2MBcsnLO(b{y)0OuAZ)eyK4D$$
z;)9O<R1em}8@`8Q!+N0bb&H3OGBsu4bzI{Oig`e8F!m5t@)R3{FY*E~QWhq&U4Vz=
z4M=#B7QGrR+WgQtQt$FOyrz+rxeWfw5UCjYIfSO><TL(>w<{%S{+Wu7U83f~I{2)J
z^Ow1%<6yy?y;;UovD@|R3v}6O;eVfCcRRt~<LWN&;x83iJkC4FUo4T$AY4@4@kqxN
zcjnF}*4o$3{{a6CcHg!cW%@iC`KSHZ2^P;dtgD5xr=2Xnb9wi#<eUg=`I0Hz5G@Z-
z(dwdR&7k!?VSBeq%jJspliLGoW5R`;wq3!g?r^zT+_u4g0ONiimoWbRJ1LJDEs75<
zDpehR)VsZvp$uO%x>{h$sUgD2T#b+_Sb_}Yns{cC`fo@UOX5xl6-B8Dt!N)t2>?;H
zQOs#V-pt<LZ`sl|%MGv9Rx&PiAyuQ!)8mChFQ!#=?p2h>w_@5TcD`|3MQ@cJu3m_&
z7xi!CY6SgTyehHAlpgNVqWI%!Jm)cCVcIRPMN~OXcz0LFFKZHS8K&s7c=)Z{hwE!6
zn0!f2VFhfXOh1hDN!HF0cQN{&&$nQECPkzet7=eWU;vMfk2N9Nib=da{I_i0nt@jf
z*VPHNOqEAgu5$k4hO*NXnn>!#r6l(*Cp>r>X=!Q2G>Lg-<2MF8wR9NY=X5Ni&vo?7
z{wSTHe<C>E*;y~glU6z9$*#2KQzlMmtaCzZ-hC}w>e^XnKhUkB6(A;f>^AVG$s5+%
zI>t>kL6r$8+=Qulo4%VOQEQV)4>2UTXS%L(4SMr0cp=3T-jwxDdghXC3RUD~_MC;H
z<IK6;M_H&*iB6=dHt;f1t=UV6dH=-@C5?NCz=~~*_`R?P6M<@xk5@<G_|Ug2l5Jq}
z&QIruGV%aQ_R=P%PU?tLT{WK%$=%LrteJnN<=`~LaxbeJ*Qz?=00N;Bm6kYqYsT#~
zC`hOONYZfXC4w}{&di+5kIw6%`bw6`T&#aa&xCJf+=z2nQ%XySMU;YRvAr<}U*4+T
zd@1lki=&VFSx@I%r9uRgZGB^1(vK~nrBI;nx2XZMX8S@Z%FY0P!|jiy#CbK2xMIip
zby5D`_^!qS2Y<|)3ch8}+i5Db={QIjMonATs#mKO8tSUeoW+tu9=do4M@q7aZ#bZQ
z1*csqh&IDsWp$)X&k;yd^=myzs=7El(`Xg8J^O&&cqF80Vg|4SFaQ1=^I=%L2O4l6
z-pbY;VLyFR9+ME;VdPeDpxtKDF;=hL^G5(Zg*vh3w3vS6LAUTxX4_!E<%#uP@l*lt
zOeA@aQU6$V$jMgNcZP)5JfO^B?4i60hf#pDi4$+UBDMDzvxza|lb^hDWeuOqIM&~q
z4h^*auHmoui9jP)&hzg=y#uza3#7vv##1gU!y#55|8g*gg`*oMg0<$qeobw3qkmzn
zVM;5_&7xmS>z<-DD^q3zuihAh(^H1Wiji*{RBq2q<>|4eRg#m#Qz=yPW6=cvr0lyf
zUX&T4U0N;u5+b)jVM>UW^w2uh@6Y0L416=fcx7-2gaqO9Q%MRLvj|(vb#<IWTHh+Y
zsuG%B%3)EzKgY5Eb_o|>&yjdG%+(^3K04CQ{b~d1!<DM;TsLgMO>?Po*j{4I;?{zC
z@;#tL9Bb(7Eti?wmKS0N+@7ju@wHLJ33(vBoTL;&g%K=?2Jk&A=?i5+RYNqMHPjWR
z7X!bngU9OGXy6Vp?UJd9uJHPkp~el0P~P0&p4TY6CQP0*l)AdWGGn^55mrIU<&nsi
zly<JrMJ%qCik+3{Lp9&5Cdn}pf}21LO&2#En8=jQ$nf(!6u|!?)FP3}9};<)mq+W;
z!Q6PP?x?*or9nj06Up9~Mo%S2zZCZ8a;rk&dQV7K6KfBOuENxhEOnjkqzk#JEP4IQ
z?HL-+8Q$%+`I#eCx>rM~+B9yR$o5gU;cY6Z)7Xsk9cmH3EzsQ(OqMDwvBXZemy%hE
z!!+<_%zTM6H#+%m3C@as5*5;D*;&n$w~(L>_!O*P)Hn`~f&?!tiddQb;*{kn>*qU?
zoTDBChOTU08d#@@xKC@9nSs|sOCr&O7hBNt4AuNRdogi)Y)K1z-L8a1X-kAU-8oFw
z-LXyLesR9l7TDkmgzt}?gQuLv1vYJULCKD%I)Y^pe4cKf1EAfmE(#vd!I+s(cm8T2
zk;=)%gvV{U>3R(mYjz7*KYIAjJa;+Gh!~YbBFUGcoQd9bj*XPbPgCy<BkoAn)noLT
z8fhxMDETX(p%YAw<@)%=HMOylSK9r!&1>x}Qa$f}g)H5m)?wEP7`*pjGE%2(dcdx^
zc~gs_x}<v0{?VXQ$wP$n9Jy@UAGPt_ioXaQK26as|GgnHaaSG%qP0c(N*gkpHi$^@
zT7J=+MURcL_Btt($D=~RPO;OPXR-N?YpIW%Wim{R_Y+l)!Fgg1Xc&Tz0}6yh$UXLr
ziEn$ynZpcoXJT65mV}`;XUA^pFHZBf3jO5M&M8T`z5e}9WK5e8L&k|I%SD^>MI%h!
zI<;GRzJGQr6)O@yV_PTX@gC_+g!H(}L54G#efU8|iH!Q%;TIUBx+Vx^`Xf@VX(bZ6
zOr!?oEl-XJ^{-G`6{4VCNc*DMr%AO?5F9_@M^d`bj@DOZMaHhBbgr-g_{rm~E<K#B
ze;ECy(FLc6n)*dZV&iNd7ZF^ip+eDku9bqq)!wYy;rJ--Uj1joi8>EE&69?Gt?wN@
zY4EhNUbCc4_4b!3(Qf+PvYNR0Ab&{klJf<SFquGli6DE5E)@LLnRP2Q?oA#n%w?%P
z73C)A_OPY_2)X@1VD8Y;Ft*PZ`)|wtiBgeOj1(IZv<n}gu<^gq;|`x)xMXan`yK_N
z^WN$u04*Rx*@S{*S41l>w65bH4w83!sdoM?60Xsw+T#u+Yl+pVwwzbSg=*{w8fy$S
z1^M9q78ml?$;38@)kON|KW379azh!%`@UG3?dHF}eg4AbG*13^g~r8M>#Q+{3}zx`
zhtV!1nEAUCRr1TM-Ia;=2M`vJE`pSPaeS1@5eZg?Gw`$DPMiw!pM^Re*hxl!Tr0<@
zBlcNjMf*?9ICnoj^C?Gv&8Yk2NUS~&cpLB=vSiy?CY(=JnCNRuj~~R>9y|)Au*oRN
zz!p7oz5+23#WN<?puspzw~YOm_%`Y<yS}JdXM?kaIKZ$F$4EmZ44Oofuc{p|(p2)v
z@H-qtTB`g?Y2}6Vd!`V*VqFiQvXS-(1!Mb}wb>iB#8U6pQ~#N<&SZ4smA#0FA;)vG
zl~~3Ee@w3BNqK|VPZ^|zX=)C}z}HlDt`(_kd~}<A$Kb;IqA>tMcL_BE;t=A^+?Q#2
zlw$hE<*PlpTA&;n#57Gm(Y?_2pb@zznQZ@<A3nV$Fj|tKrsVAFGh+l(izZ6q*7BZ3
zObtHy9b`_xqcVOOK@Uo^*LIR2Vq=Fj6LmA<K@OO6nsUHih2q8DIrGu(NODiRH=u7s
zKBWcorIFJi(UYzjcP!A~sGSN0E(wyq`Bs4=u)by8Zj>4KgK^vB?Pr5r3E2b_GsYT$
z9J7zH+^4$h7D0G7w-054XXqsW49-;c+2IEaYj1K=I#@zf)vIR%qaN>!6+B0r2rfkZ
ztEe#e{XK_Ee!u&7p+QK<g`k>vwAh&FFFc)p6CxX7t0$&yrs2Q)wS=gfn~9t!QJ!0g
zt4vz}EMDT?p!*o^(IJsmw#Q1;eYd(E>czMnCJbcUiqdz4lubgbvN9P08%jyu%fmLg
zAd<}TDhv>sQVtNr4Xqe<zLD6VcgA;>)-mput|bL4jfeen>4Djebxb~Y1D3R0Q0B|G
zBzy4LwAHLv=ofk2H&FQOk(S+h7Px@$5twDhhR?(pa3sW~Ofw`V_pY(X*O#O!T_f>0
z4?JUH!Ah{=Uvb$lM)712^ppGgFx}Rw(Z>X4NKQ`5q)bk8DlC?-6`W_0EJgw%wlx)9
zdNGo9IrA<BC3uAx8nhm&^#A1;Z2v-j*qMh+SR3c)#J{%^IM(L@^2j3xW5eiPB>j^H
z&#Zm+Wx*@k|4~a$ziiyZ_WkUcL#qxuL)YD~tG*JwdtwWZH*~3Oz7V{mqw{6&PqkPJ
z5|77fV!hFtUKTdiN!_TL`5lOgxeYzEPqpRbN_is(|IT%Mb#cA+en$Rw)h|(6#kiFF
zu--;unOlg%{ThyvT~3jkt`KpoQ0vXkns%y{rMvMTpesK7A4mRVjEDCZGvBe^_lBW8
zrS}z;qkTtfxzqv@fDV~xVXOO}pChF>&b>4H_2~l0EBAZa5{Lh0oxOID8oX{>nr6RR
zYqXdweco+L2#M?EnNq3Msi_HbmEKc^ZRC%yN{Q|-eFc4+s$3uabn;zjbA4Sg#H&u$
zy~i-#*hq4Q8wW5hCtY0E#}d|C)4UWaTC6))Ztxwib!Njki)`v4Vy~i1I|tPs!!qAR
zY~Mj)h9rkGe*nG20ax}^@12sts9##pKJ9J+mdRU;N_Y)_dy`OmM#>3C|L?^4NmWTz
z_=1>_<-C*zu1ZPZPai&AaY8*tsi7b7D|<j+0`(iyEK7>T^L37tuKxfH8fw<%8n3v8
zmcCE-8nvp`xW{Bn7jxSVtSMy!Z`5Pau-YY!IICUxKD2Se_f&j4n>sc%pu596suLbM
z8I8;HjTcNtDJ4ntc3xp@M!DU*={#E$%Ln8mdK&FJaWr9UZ>+rntAHwdG9t&OYCEV4
z6LI&Die6c;+;hdL%JQ3Ly8JAR`AmtZ_y?@)`UjQD1TF<7NJa(s-EtP=RBPZkKBt<+
zTw+G06EI-JeBRWxd|v9igEg|;gd?z(;%@BI%zbHs?JHa8Y%X=OSv1gw^l54EE9djT
z4BT_;*MK@lz~eyu45FdcBtJv`Toyl&lvnAUzGo-lXw}X_+i2Yh=(hG$L;38+J&089
z!c{fQlD@hobtDhsLTO_^=W#hNQ_jKu@wwQ)l=tMdM&X~7S`QXy?o{`mAKP6D^sW@g
zzBy-Z8ghA&x>(SQJ+Fs!$WC&VY#6$t<K6IZ7Jnux`$bjc5fZUht>uc>&*W)%eryOe
zMaiPOlvegflWuLbb*Vw8S<RY*1l1O~NiHRB%CWTTfnaQZ_q@vZ#*<XRDYO3Uy*G6_
zXecL?b<QcR>jhiy{7xvQbn-@+fAnJxhyV&sbu3LRR|+$7Aq5PTiA;zeLgh*^`@=h+
z)BdRt-UuE^v4GMMcP`-?u~X_&BCR&pzO%a0RL}fyoDGO;+wb9$vSSUd_WSQnK0etL
zL!PnFs7^cey5J8<3o7%W5<t^6)7qr#N=3B#vcSIrg5cV5xrbA|z?#8$xQi-7>_lsV
z74B{`u~BO@W-4-lcQ`aP?H{kQ)&`y2P|Esd6_Jap2mf&Oik1e_uL)fU8r+kJuf>xY
z5)bR07j2mq{db^$#Tu_vsdpBa9EW^5#g`Q^ujku!1k^OsROh9GY<)n}a<!j{$K0z#
zJDT0jx9dU-1r?97nNr)t51^@D?)%qEO}#!6i<PFK1FQ=c#c7wxz0of5)*Gv~chap1
zSu$)Ga4qsIpGLf<c#DLvKCb@sy|tnrM~4(NCqbq1qB7=-ipjXvkPsBT$w7e$SsxOI
z)T@*??)IYneQ=yW+l+?aDjg>()oYMk$_%GsBx|__83V1;3Hh~;Sr;92!s)0wce|<B
z$d}zsU1iUy^XpzX@<bry6$gf4%IVx5wEqmjNlf(}@anL=cXnDl3`cWz%s<*e??GUi
zQ(2=e#@{)TAwG6Ps=7UXH_#w|S?Zm@d;@nYRuPrl`gEXBnvIAj&)J#CqqH3n?K^SG
ziS|yB<=l&_h*_xf;sxqoa8lA`!V=X8>_khzre5ZUxB&}`v&$UjCN5^jh)b?&>mnrz
zeT0ElRjn&Xo=*h-&z%rc*TIAU7ty!=aFkQ9o{@sm(!qXaxFBMqzE#T;KEeG><T0e{
zb+MGq*8R-5tE0`^*K7GrtK9z8Y#!mu;vNI;nD@UmD7b)*z`CGnPRCcc7TS(~!m8g&
z8+tuH>9Rb&xnn)m6oML}k6r-r*K=aRriAAe+`XDcfI#-`GJ~-7>D>VsEd5U*RO$7b
zhWkn%I~t4juR?@=gsJjZHTZD7KQlwII`c2%)jk6l&UNN%k)3|lkl~sx_3O}HDNHzn
z!HQFvJEhrZ6L~+*3V1=Sh!4d;-=9=x>3dufoI_I&!uP&>MWCW3h7jMw?iJyKf&tY!
zj*tx^i<cz(OvAD4hj@4_DgVVb@_Z0gBSusIwVWkC>Pd9mP1&6YcQgIONhJ^!a%DZ%
z8DB|ay+mR%YufbHGnJAKfE4A9cU9y9jogUjk&)mtl|_%=1fPeY23U83{{eVul#kRJ
z2o<Ak_(l{)%4q(KRbgAvnF=Rtdu!k(`2zsNvSNMf;7=Q0lBS_bA$sIFq7P+s!Rhnc
zX<%87gWTW9POlwBta3*DT=8I|^o$=!G}uU#k$+w`1%sk9F+0^nUm2B>^I5mI22GgD
z7(p2e*69@6j#BV$nj|(lRbVObs-zVyLKf4o*gFML4uq7Kcn{G76$h|k@~_?(Ac_IR
z`a<158Rx=JA)6;my8JjSMKyvd6RnzCoQ;t(Jg?-ENsM@RT*>@hbCkJn!d&54BNeUs
z2FZN+Pr4CVL+sSvh*B`)WxwE{i*cdBrnZH+hSxY>gdrM^tIgC5d2Mb`&nnu3lrtv0
zs&00(kFhE4@zhmcofnw*#dzxB`LH?jfKvE~kGH<nI3W$mnRfD~l_D^0$HyUJk29iC
zZWTkhUb)KCvlH_n@H<w+xs3kYGqzQU{Z=Df>$;j)_?dfCrKVkGC@lfI`0ZqS;N!Fp
z9t$JDCyKJVkA2@DJfZW|B0nzex4VQ@mG~sNr$u#dXi99I3;(CcCVN6y`ap7+^U+_Z
zho&!75zjg$$<!g}NpIx{!XCRU2>20rsiGytZtQ!m&MMskpnWZvd0Rp2dwi)Og`{TC
z<G(BxChR7sfMCuE<}ZSN=b$NGz1zZ9QqI9T%NS6JFsC>8Em5{;=wId&uC|h2i)o?e
z=IMR0I{L;@(vdUoZ2Mr_IpnklOfh+Kd}=)b+`?%iyKNh@a|CyloO>17_Cpo`QdP>#
zLAz;r!TNgNGjPO2A2k5JFWd;c{I87sS)sTgMoF6+lJlWQ$*vVw?q}_9C%3FtN~i<s
z<gznaQWRA7;4CV-vio|Ch<wWO{{Z=M=6)o59XY?YXjfUFQpyy6UEi8&@yHhh5)H8a
zeMV%()RU~nStn+@Pw(lt3`{!Oh=-Pj+{w(h<PiFc#{Bx%;B6VPJ@$32I9X*q50Wv!
zjbw^&x47PnuDn7HW_NfPS{fo+i3D3X2@e%`k!5wdSJYW}I3t7r@txd`I!q83xiY!b
zP_S?{KfkgV6ZTD*rNgrxUbnJo4j$QC9X3Aj`tQ4o=UVs2Bt3J(%i#IB1BXQ&oDRKT
zAq!uKm8*V|B8!09&6f#wDKt8!H9>XbqNHw1>DJ)Gj-NzD#^lLZ>jv~+#hOF^95JSy
zd-TCv3dg7q^LkyG?znCXFu&(Gi7|!qnTqEH;=L?c2QsP`SLmgsL67ga`1h!f5)3ED
zC14h{9vX6u!x{qWCTsUHYyrc2YqhSGw%^3W#DtV^s;p%gfGL0Um3_8G8jNMK%3lS%
zz7OXQs^xZ87(NT)G!#^`%Ull`1LmRfJ1v!<QoOB1Bh_VO&6zB7@Sf2dat;hlsbYC2
zL06{zjf$6U<F4v9tywqfnn19q(|6_0_r|mYmVInq-d6DI9EMC&l0~W6M73Kdhq)FY
zZ1CLnFp7#&h@)0h0}m@AX+|V>ORt+oJk|GvB)!kKZ%LUmxtDEGSGNzm*Lu;Elc($k
znjjf{itfw{kIpHOiiWxc)wHve+7E#cQ8<qRv0ehH<Q}Z`C>ZM2h4zZ}PrcGNdye{)
z8JBH8zjYrJa!=K1rMQV{<z6wPHn#QY*P;Zuh%(LuZDfGO<s?+5l!IeqLrLKR_w5?|
zk6!=6hvD|rf0MtZYHW3*Kd#=>uNAt#g0&XUrhOW|=2Y`Cj)-^&JB41c##!2B9nw?V
z=IyOD@!Z*xxM9fzU=#!&*=O!vSPZ5V>{QvRJiCC|YBf-^6{W#|B&cwz^PjRI)P|{V
zw{8`4vc?WSUF5?T)Ac&?RL`=dj>8?{#(uYz<Gz}Q9!z#0%Sg(cQ1eF{zDK{iE0fd>
z*v$r<>hd^e_g6sJ`HHQ4r?~l?@6dlC$$IGj3+fPQV%^V^wl|M$WSl;QJ^?;5*sJ9#
z{fq%jR;WRR1oWL(hwV3fDa8_TYb6&iexoPBn}=n-N0u9-myn#@mQa&m55M>vQXK{A
z=wGfGDNR~JN1D1}Acq7~`=Q;Sh8}gkR2-`XuDcL8$LCvT%eQ!Adc&?_AZ`EA(J+HX
zRqip1p~r_R6=mz9z-s#|gN(a>6OyX_oi>3pq!+VO$ZQ6eIt{tqyZTIn94hC!p9A0C
zeQS#|;~q=ww!4G>T59k5aTq)3j_2kHJ4AnUq=J|g)eEE=#Xq2Yfdtj94;p2e4o*Ml
zy_F*QNM6Tt!Wy?-LIAfl30Y=N-%kq~6BAr_EphZd!Ys*9SsQ&xPb4Pm)6+mkKKtoR
z^)F|QSh_pfGj*@bFtzU#C5bJ&x2Nca{eziwS1f+CU38j-z-lbDob6J7nwB0t@N&dU
zBbDfuUwdCQ+f_a<MNzp{r}JL&@A{fzH7%57x?3VaEnbp)Uh;dZA-2b+!G}o|fmuq>
zw}fiF_+xsns_uopUg2n(eEfAer$6>~)c4=Q3+W+nP^2r=zP4^ZDX%G}k9EUfx`HPW
zFYmCqB40!siVrgxmf{pf|8oAOZ0oMwVKAXr-=J4n8}@Vvs-qq~pCHz!Xs6SHd$m_#
z*ki<e?8Pu_yduk~90+kHS%=Z>?SE>$fWD36@_W`o4qTmp8=!TJ!sQ398h4LBG;bx1
z+<%`AikLcr3*#g}q{|ok@?IEHp9xMa1Z!L!bRB1ZB-qU@r)(8>rn12|%e|0RpgbcJ
zM~OW=U(JQv_~Op@d0pq%Ps<UOLmn1oU<L|S3C_YR>e=!N--Ahe`H?@(Tb&YBW&mEa
z3ZWU@OIr$l-j*NrG2~KLAm%~mH0s>OMatsI+I0|W+Qcam-D<Z!n{vI8HZzG)Ct6OS
zX18wum%cw78h0~c@bGUq)`GGfWRx191u&r`%zHJA+xXv3iDr0@mf6c<qT&5=>BbV6
zPYsXdu4BTbPFZwpHAx1w*!`AR)Q$yQ?$Jz1TFA>8hSD8rQ~`!^c04H3VcScki*|B1
zDwD2^CK<UXNqcHE!vmL>hIQfJg|5|~?OXAs^sN?W2UCA+S=v$s;`@RpUE|R_w)fUb
zMUb=I22g6q;K#7vXeRrLv<!CLP!b%uoApt9698Ad#^*DdvQF<=wjZ8fVr~%`<Ct=p
zAADKue_Cq6#F&&%GVOI@iO2UK-SY^?&)}&~0i|)h)%($;A^!NK04|!=fU@LVwyGs1
z4z{S<lj^N`%Q8-%$v{6muT^GbMy>#%6_$$MZ6Vqm6Ft}I(6^aN#WQD`<C^JdBjgEA
zaw+vsu%q0P&Enn%V1DA)aQJB=Rno+N*s9w>8eC6PRo39@GSJ^u2e(>=nzt=PJQNe$
zaNCZ#3$@haO>*N_dW|m`5>lmtX3*du>TGJ*=X@n4Gg9Kb;C%yn)^yHyYc5k!?ZN^~
z_ctKiFMpD^5jO9(_ygf8<Jlu(Wg=EWo}mg=rzprie5lIuACo6U*aS_rSUHdKqW)Cl
zwwQGX_C&U#bw$~@0PxdI*OF0N3X{r<0nd)lX7w$9@w-QmRWRZ(ho*OP@a<RT_5$3T
zYZlQ>{Zav?qwN_mW24%-7RNF61+7~6(wNv{Evu{AL8e$*3`l%=R+{`zPT9t49502N
z2TA&h*@5UoJ;R@`)n+FzEY9#{4t^X+B6zOUWD+C*TjH2H9BBqe+a-LiJwDb*Jy#~I
z98zYhHMV=-?mpAnZRpD13=6!gapj+)04Zx`fMz{Jr#Zr#1RpZ#PfiR=T;FQ?I3u!%
zka0o==FeThhG`usJ|T;p#<=r!z#pmKRWqsLZC_IiRGov<>st*!GC(j6)Vz(E8JZ)&
z^;{uYUq-9&f3NhHL(FKf?y6M>8qHBFk`*aV0C1M(RJG9JNJX9NJX^0JCy>pw!RGTo
zf<Zz1kNVc`U;|QZ^uXO{4&^CC(eSoKXE#6Z#b@#Qql*Nt#tYz|?pcV4wUKBgY&*s?
zjm}h+3`G|`=bm1A5b^h&qP6>>`uNQ9R_B0($D^in`Y$lqzhfWYQ>cdsp~vo_$!3!#
z2TfftxIq|(j1r9PfnDX^D3Be0x>TLh2e_k&mdlZe&8RYG?78t^gwFQGMe>Vd*X?l$
z41o@PBZJD=KCI7Y3^U2v3Q91x&leE!^NmNA7enc?4+vPr%Dm{P3B>dBF@j;7!cmEP
ztccq62CM{Isc56`-GQTW%QV#<=;;B5v$F5AaX(Yme2nM4v}H(#EX7<mLwXSTQHk7j
z1WaDe#{Trq=6K&S0<;#ktPi_hE<1;`J3p{k_wXga{O{_T2a<5D)djL3TH9Hb)hdc=
zfh|A076u8_9a_$B|1ssSFPy;jPP$%~?NShlBIL!`hkR0<wLFCfLq#krz=h%=9X+D&
z(v)y$qtWqnLR>jN!|)C;fRpDM4GZetwP^)>|4!ut63_2dzBq1H*@~TR+H8k5vc(bX
zqQUhj|2^?Y_9=IP5xw(PkkK)ZZ(eBSK8g;eQV|l4arm1Y7Vt{*$oa#k7hPH<99RkX
z7to?Hdc%y`zM9atLY^P;1&x~99K=maziTBDy!g{1&aLi5dA=CBxhgqmzPDB%Bv-^s
z<w$)C=a#;Zs8o{A^CPcr?K{}>SMI+&)iHlBf{KoHTUVez8#-`gYFq9P?MuZ1var8(
zt+!Q(BiUo7tU6JjMxQRPoq89273o5L05MtA_~FM=#A9g6j}RmHopxJ8*w3q(^K$2+
z4*mE+s-<o+4A0TLCt;P99sxG*b6NXgtxmjED*)jSyc3E_OYUIqxP%7f(pw|DMTYh3
zhW!vV*0>z!9G;@04#%eTlpuTx(xq5L&*jv<Jw!lH18x~L=p#xaT6Sil^bNk#aiqtb
zG)8~q^lNECQbgF7v?IFYQ{O|?&QksPMd*IU%7fvtk;k1v<@-c_mYsg`y11%-lM{5?
znci66`Mjz_>Xa!hjuNYCz}8|)jOBN@v$rv0`xuuJ->I6HmvGTxF4N>dq--^uPwX%P
zVs8`V;`|{vG4~YoeSxJ?K7*pPj|8b&B!B@{GQw=bR1o&(;Cc7L*L0>{^!G(?iw;Zo
zkiXI7=C<UO8`Qs%t?MF8z8XeePH+0k!~}1cRSdEnDM&_=Xct*fJvOAANp^ZGE%Dgh
zuwSWsVFhRGTn~pl>+2LfFFvq@Ggx5=VTo2{?~!7ex0_nAoaxVQNU|PO-X}ZPO8v5B
z2{KjQlBH86GE$F9S(aK{RGSI*f2}}R;adIE?A)oIMZQ<s*YtAt_zuUgZIPI@C48Cx
z9T^O%D&$tYokdqYJ5#&fYMFkl@X`?6_BI3fmr3dcpuUy>1Jr}{E7#3weZ*}_(0EG9
zHJr)|u%me{Q(O5{&C*rv&7Q+z<Bd8mb$^L?mRoX6pH=(j|J0dsG=J}IE}qun!+v<~
z5krj&IV@JoG1f4@<*W&j(p|w&++5^emPGihs!w5l!vEBoV!Mkacx=d``}=C4)ql<X
zU+b;)o}Hca27+6ZqSdA~vv5J_*P{^{F8i-PpDN%MVZxlTH^4qm#XTX_5dXNNiR1!B
z^Eq$hnrch#)^C4-1sBi*4<V)e0dfPekqJ}iX2$cm)2>8F%x;rXzE__e{n7K1TIL#*
z@l<}wgSx}MT7xoW$Rrlj!?w~v{U3m!Oo6$!ZQvink0f*LGTJ?ktd&7_A>z(Y6<0O<
zrSBaCy0_qF&Wui>!(Lx6&59`EDgsQq?cJDjFY)s+OQB1)VR6qj3YzWLX};8r=f?^-
z85hh>rPna}l0^fMgH;q8I{YMj55~_)Pfgn@Swb`RJOUT7I-e3vNHVo@qijKi<t;kq
z>BAE{Nr`bk3HEsiB+T|uV*YiqWJ9$M?;H}P`B5@5fym@1t)@ir{_@W`fIq<z45A6}
z5-r6q4sW=_pg;;|Hec90_>|^@?g}wqI!~d&+q5mq<^-x%f@iN|y)Z^Kj2xI|wSq+@
z7aCC8g*eJ@rsNVFTg@WUd8ZJ?@<42Z;f0o^AxEwXXSaJ21ek@YD+C<Y!12j&+o3r*
z@tpqz(~J5Y2DRT|y$hN581}~MrnpMpj%kyd-TMjgBgkSFFOm6U<&ge=08F8;vLD3*
zz~?Yh@Vye`qeRf9(Xs_Ukc&0&7<z~pM;r@aF*i<g>S@jI#lAlLD4l35T2YPKdoXqO
z@JjVf<uAjk^uMkyu44P%`#o9|l2EV){_*hp6jT?$gyIIls4^mbaOKIc$tg><<{E>w
z3U7%2a9#x{F<bB9yjny8FH;c-N`m}d;*1u#k)UVroi9xRd2opG>aJvDV2$;!1sk@^
z4#VRU8_<of%zhuwkQT?IZu=;TXn?7j4;jRe(X!Ty5-j2xYAbKE%3q-V6aQU_q!i&w
zG1RW_*gs!U*~^5uTW!fM^IQA;KLb-U*VmmqS@h9NLRql4*z|Rhe7e#!mX%!XKSvet
z?$60+*)+O*d&SP8pP30&N6-)F^}G+3uBysb0?Mu6jO;V-tdvI&od}GD`Dzjxh-)E2
zr$X8*Ztr=ewnmNJ!*2CQSWsVee&ldwqW3GlzjO9ikpply=FN%Jt3vW)XgL>Gtraix
zGzcx6lfbAK%ARhfIgpfoTW3$}Smbp4)38(B6Y%u6qq^Buae>wl^CZkQyS1Y$a0_%{
z5hL(L#WQ{fJxs1fKgYJ7+4;b+?-lGvj=SB^&9c<kv6eOy#W3Gk6+@TGPqafESVm2c
zt(~y5@Yh#!?kVd(?Hxb-@%qty&SaZ#V0;L#t0$tn^P#>+FJSpjG_1Uu3q*A4S697R
z9c?1@SJtf+|02tTF9w%*oPP<MlO2rs%Q;`kPqGt%F}wWHVoro5_1gB$Ch!f0Y9!+7
zyzc#1An>TNkWmDG5F5ljhiM;%MEpubl=0N~1~Fdb=L^gwkuuL2MG?u3^g71bT|b;L
zd{#}GVk0L`Iac$g85ux&;wj;OE6h7_7~9Cm+)GX^coPMaFrC{b{^fWRby9N(pD*nb
zPTF)34W)n9G34<q>m0sWD1tjIB&Oo2HTHO$XHh397<rVL#bJN>V~DHEXWfxzWZNP8
zZiLCdmUICf96Ob`Sn*oJb>&1}k#CaZO$b8&%MsH@WLi}V&Gi#!{#2pLHZ>Mq0-~{O
zrkaox*_<$Kr!*=R&0Wfi^BQU**|<my<6Lc-i8h2PWuAYg?@UpWvwVl-K~=Q1_Ab>G
zwtnDY%dW(ADWkO@&t+IGjbb5!d0Lu5Yl4_k8God-M8U%C7I@v^Esr@4aWuV{a0{G4
zN{>X5bzm#e=v(qMs5aPBN5nQqxSedFJ_knu=FOO5iZy;Dc0T0vr($SiaF`@SbVp_S
ztRB75{h}oP#Y#SHt)ZSY3`a5kyuI!~UU|M+!`jUX9pr%Tn=Fnj<Fq`!Va+t>2}x0W
zN%8<XMm)sqe=#2qP11pR(NXB-eE}Q#P)T^38D)Y~1>DeRs=vGszey_dXJ@I4GWr@K
zYV!_dnqzV5h|R!H57ufhEq!^ULRapqfI4V+LC4eoEyF|1Ke>A3*Z^L(vWX#hwEi6k
z&PA!Afh^%MUd%`?EOMyQ7_(FCR`pH}p=OOoXk*2B^g!d4wm*8i>Ipi?FwitcV+%m5
z0whzc^Mb59`bqIKf@sP{3RsyEdu~ZCiOe=nq%B6pVx-4L$WKAK-}d-<J#R8(v84X7
ze>^um{GsuCd}0NTJWgxxI?;Niw^l9Xn?0z#!M{|;`}~Y3j~C&z5;5|Fwg5vMvJEeO
z0Yr@;4smF1+?|linsNduUbqW6u7FBmQtqivPt*CR=wFwh5*y!cu`0KZUlZl6sqLaq
zyP^a{reM0nud}bf$)@T>#yck6l*egG;(|q+CL7eLr=~_m{sC<vcJT&J$f&SUG5REq
zm}KcHWMg6T#kM`kv|ehEQ+kjUBL!KYz-OSB2OXa@qBWyag<>_xnlDXg@N*|JFLZu*
zax~yo_Zod&DXnb@N0j%C9lj@Q=0E6KgxW92tGd%}_}4Z{(52@U1h>1%!v2rCw~mSH
zjiWvXcP&u7Sg`?G+`V{lch|uNmqKwFU~n5K?l8DZTZ%(ra41&X-6^!coj2KJ-%WNm
zoBiWW_K$CJGnt#rP42y!=Q-zd4)+{Oa2|T0YE`wF;@+$Z7nM<rrYDead*cXaFX9jE
zbY(}awULx2IyV~)rDf9l^}~^G&}bw!$PhioyMwpWRUCYz4a9gDay36frW<MsCNOmi
z&6a6f37#=F2KXx%rBCr|aDB11y%kJ%|7wdeX?bnJ1&&;W34ARQndJP&CT$X!GC@zs
z$&d>+&^L4!E%Az?k7TFUWQOs-)Xc3q?i(D;*0#FSoYQB{;5KCqRq!*VGkaJ#F+@U~
z$*TrwT85o@M;5;*@<T9%>3CsIm8peCiXy{KD4nd?bm|iLxEKuNib|8;k1Q%TE7mJ2
zJ+jI72G}<G*!ubR2MOU*7|yRmzqm#bBJYo=X$?&QZ&<U8mza)iLB`ixA{T(X8gesG
zRnZynGlU~KU-z+U?MeoJjbBfYK>X|{jt$^1=kkdGv!$-GZR?3|YnyV4CzfEq-#M)+
z30rdB-37ov`f|F7pC>_4Q{7{__dmhrK_v%7iqM@PgZ=Tt$HFd)pBM(smKi*}vBR8S
zc3QK&l?U$##^5yeD4kgKPOn~TTduVS?v#69dx1*7Y0Z2yv*~&Y2%0j@NH9p0+ip;J
z_}W(J+M8VN^Z^{kQH-A7J;&%#z*z8Dsj+IzUtmgZ)V^SOZ`r0rGG4x8cToM$*MyQK
zeie+OX>B;m_KxihX9sH@`^icSvyc{mja*Jk_<%fUbI&NmC9%&7SYXfeS^^T4t|NM|
zQOcG+R+qpm5v;3nF<UV50<-?-6C-fVQMnQE8AW9{wDr53GqQ|pBz!S1aTW!qzv3WW
zLwa{kWD=FI)z;|`E?;07?R^FB_k4%&Ny?|7Ikg(75fL1XZUtJ<I`5a+K19=XhX(1R
zNcZM+(A^_)SLY>@eW>IykD0f9G}skW@BN4~(Rl81{Goc9sDcCgV0(_I0&u$gwW2|(
zn1QjtX7DpMt-&`BIOWUnHmleQdbDR4iY{2W$gLcS&a^e5Ua358CnoBIAHl2`T_zUo
zecE@Tne!JLzPSutVcS;b<3}5?_zQ&7%hrfb@VC6`@&9;N_c-(AK0IIldGjBLVk>@%
z(~V+vDocZ}znQ&pwJDqBV?K#Cl0Pv(OyqR{446MPzrU>rJME?FDyBN7Jdnf^fzuhR
zeoFfs2t9pM^k%mC6UD$oD%$MF!okmXwe?-?$&=1@yU?~4{@@&HMQHn+<jeAUWQQc@
z--41Q6X>AXJDVWt;_4HU@iTm-z2{2IY^5w-k&(-MU0Lp=iMw&szeH$HhIydsy|wBQ
z1BRta7f$>T6e@CL>3w70fbwB+vIHbP^Hn1A{*j?i^H|l;b%BPMPwiJ7Lb>_&PL(-8
z(g;jz%}bI3lixWqqVf&gtAH`~6Dc66hjPdl1|~hKg{nv_@-#xUZwd(c4Vgs>yzd>6
zz0xJWnnlUI<Pw<c!L9cf7wR|2?gXidY%ve4fBQOE4^Q<|Pu_(GX426-x@YCmaW|3X
z>j<H}rr9=!5KXZwg6_bru&0(u>pD<s<YKo6DbM2i#S|!)l-P@RL^ZlAgh=DEYu!N%
zlC2}tKmQ-#b<otM&+{qSXA*SS!aOnU8w-&d2axwqU*+DOxs&u17aIQdW9GwkkdlSg
zyJRY<wwzKf-uy&*4kd4;rsHl?k2yrW7%mbBOv9cE*6YT5%958jr>gdNMKrpp&o7dn
zw4V3$3wxsQ9Lia$@P239`<8rhTt{R=3U#NtF0i3Ap|+&@0v2(u1))i)M9I{|!fY29
zTbU&fPE$nI`(*sd5S8w=kmTgA{-KC7dS4D+{^kug)AanY!J@Y(U(l9y|IVkYz>z!u
z9JN&VGPzUazCx&sT%{jTR0>W<W?l`y7Dp_0YvKo}ax41yDcWJh2r3Pj=>LxMNJV#T
zKmO%+8Up-vdU|%ds*t3uFLTQIkJMd(?EO)Ye>O30oOEWOKcr3O{4Ae7-%w$@fyA4O
zS8C{EwTA|9>@GyvYz=MQkj{li=fn2i{stn9NL*btIY0WuDB{zfWRn8maGaHGzD_5i
z8>w-OHkLrx0sr$LU#w~h07fn6uSNoY*vVrkuQ_6PTwFNT%;Fk4+}O#5IQcq7OLo1W
zCLxMt4h3R5+;|FPT3Xr)WPtzYq5B`WjS384!hup=gbHCt4*&o7XafR3{*eFQ3~02e
z*x#x~lx4w~bWXp?siSUMq@VrwmaZ9-WG`fsk6aY9SM|oIcgEKlTIhGha~h>P^x<F}
z13~<VXV~$T_vn8Acs*}V@;j2&|M)1+wG&$F$7FCY5u5%56VQx*NIh1guOmNuv&U1K
zA=P$#i4;MATpIMkR0de^57sy?VO!RZ3R|Q9p1M+kUJoh%#`(l2`$I$WWk7BF;`K&=
zJM!)d)l22u1-@gL4<)^l`nE0pA3zY!oUEyR(`1HrE7kgB9c+ZJZn$|I?JV#`Hu4_&
z`Kq4T;4-VP7=PVJb*4eZc9$p=czB~P$N}G++Yc@&Fqr$Y&LQ^R#&I$W?(0?9(<OaA
zw$j1P?eps_N-XVTI@<Ll)p*C2vDm8Hf?cqkR^n>sCZTiI!<6n@2>s^#FDkywwRr0)
z0eiI{m8f#OuvI+g&lT}oD>4?5Z8F&@KP9?e+AZaPWtYh@t$#r}93DK&%>MyQNjuEu
zw9V0-Uj#0_);Sghf$qYgTbB9BW`^|ua?etL4{A|UbAo0wWETGk%(H+sTWLe0#t*>q
zHg$DPP2ZMek_0Ki7A9hbcb9{gro{4vh5XZHE}I41lJl*$zn0VYd0PZ-{|AV<4uJkW
zhhJpT{nbt{{sWmR6HTFi#cZF9CV2$u`I>ohUx>k7+L817cgv`TcFB|9(ihMl78AnK
zw{?aVLGNh(o<M!}=!^-dXvhjxJId7QD!y5Rr9Q>&VT?-r`46C4{Ee%$hps4i{+04k
z7mHjOt#zj$@5Z)NktNL`v)XG=2$j}1e`(=83*&7>+(S^c(EVxZ>dke7?uCUt-5gi2
zthn+a0T+nn;32^O_QIU6u79-mL3hnTb4NPK(AXiJv4pvxvJcRTufH%rIH;fF3*e>w
z?JwyRRWHx)ZUY<>d|OHy>v?8)ewI=wB(zr9W=Nc=K3+BlmIEHRM%T>#MBUvX$Br5e
z)Zvt;Tw!KN{DaGd0m?;5;e*9aiR>5p+s*Loap~RG%`x*RdP6H(8mVoz?9>ybJj@n-
zp4OEAa`JlVX7)?nF@9k&i?Vm$T!0ggj-fk3Gx2Ka6-0BO%N3ZML364*wAmUEt@@Bj
z6><b(?otqk>ctt~h>Fhnnt>;`lr2?pQxk5WXGQ3(T1o3z?y!wflq9w#%G@R;(2Lj1
z`$&KLm(yu>$1dv2M&|4gZX#XjRcQvksie^H$G=5n9u9DkQ;DXV_KR|-;o44AURc_(
zX|U7qKZ1|NR$bBTK<1h>-j(V`aEkWVimc<1r2?CYD1_>4gwX~A{3hsqwX#1SQ?gyy
z7+$wO8r<zw>H13C?w8DY&o>uvHR>Pl>yIV>=;MuT>C7~jHaO6^Jo(^d!hRfR<|C{F
znSf9ep;f&*4huO817uDS5;m1yq5O9$I#SMezKrmQi7Q2m2LE+R-1v#Fmr{FBRqZ}6
zM9&y~&T&@pvEWP4>~IAWsqY$*wF!zU<%E>bX3!!mdYI#*c6v8&e?|1urAXcGIpba?
z7D5{-0(k3~FZZTiC{BsNKZId7DpJS6F;(7-iyUe2)j(ws7A`g8a)o(?L3Qp%yjYmE
zX*)u07ZU9RZOXR-6T{FG8rtE3>$=f$p3XO!>^wA70#B~*eR%K0TTaxaG9EfIUIz1n
zb#Y<EnBdu1!x0>vlF0eQ#iU-()NVyBNp;p!3?RE@mW2M!T)C+e{1-~h2ai&H4wjXX
z*=F}0f}$(^eW<>btv%Y>Y;O@-I;8A|LfWLN=q;w}%ix=G4oYie$)H)}q#AA92!3d0
zk=d{C++s8j@;v{{bVqU;)$#XrV6E1uyGa4YEhQa}P1ev0K}xH6W{l9*LDj0~4)jrS
z+L@<H$-l>cHdvHPY5&Y?VDxh(7Tw*Jd-4y}<%MrIaOWw#$qiF#Gjy%$7pUc+q(RIH
z6cm}s;oG8S=xM!|2yJ7hJP??9+bO#~7rs$rS#79;sR)L#blc0t&)?NNPZZ|gl`W6b
z>vKw(!#Ci@U-$3_#5IHJj#>+|1-%xPqr~Yn`16xZve2k~Z@_aB3)!;l==3fbsT?+B
z1#LF#xiWG%Qbl^ob`T+OIt+4ToGxx0c5!6j7X)>FT3uaf)@h`4>RENMPkvBvI{JAz
zuHSDl!qgzsG{SSIfLYcJl<1#%AG{5p?;Q1jFKTrTbBa)%#g64WmYZ^9oM>kNC%E;D
zavf&s>&+uZ4<qLnOIfr`DcHbt2-fDaGCL|dPSN^@uKw@0@Dyl*+N!UU;<?@deWuB2
zRNnZMl8HGhX3Wt3Ap(I}60?4gWo+Daa;A*`i>a@XTQD-PNq8e3ssZ9W)`NY1uQ<c|
zjNCoaP)ns7sQ28+tub_cE8Z00{GJo%s}<_*pM}wv?QwYcA!mw~ov!Kq^t-HP(#j5#
zu%^%rMd;7cOcrQcUgetLmwz|u^ydm1tMRvQOe#GMxbpvz8<MOIgt!UF3~%m+tX*>w
z$g6eCGjliMU~evcQQ?YFKjKO))N|FJFb~#hbB*ssX#LALM-w!c0vV6@dbIirW<jW8
zzquS&ToJUr(C~1NrmuN|2zuLdnv=SY&Xn7#wM(wQ82LO@v+8FWdTetB=RB-7S@yQ6
z3fXH`s>-)TKa0OJ+fOsPy1^$hp*Dr`wkE>`T5Mrl=vLbWX`H(SF2Vp(bzZ2Lei>T1
z*V*@NSf#rpyYl)JfVGYb2v}!Bg7|h<wiAdTILl8YFGSAbo%V9OUz9l^$P#ATWeu^?
z87UXX#}X)RhdRe4#mvnmn>dMX>ZOrB0%oxxNS+TcjdP?ifHE5<N1yqgaR?xzBB9eT
zSE!m(Q#hQX<tG5Z8Ug5rA1&*+j>yBDKIS`w(NFP@sPg6`n-WB1NW=J7FRKCEnRGH$
z_uh*IYxFr~qjyDIiUYL!nN*+S9P$VKs>V=4j>Cf2&Ynvlvc3hi`pMji{4x{|rNZl*
zv(i`$HpOvgf<P}0=zzNLD%p9);kJX+JWh$=^F}7??_t<D8hx+sd?Ic<wpaC(bHnvN
zK_Hl3L7&UGnt?T1nB&|zjS>C6OvQx%dWL0amBm)jN+Ep?rhXbyJ;{2CZ+oPS`I#E?
z-P@r2KaiECF14yece&B8Z4feK%Tkk_E>jwj88rlQXb+d!^81XlpRPGOITy=^@zIgK
z%{eLKl7zNQSvtB#UD}0bkl8DLyV=V{=)+hR&uta;>cm?<ECT3VjN664!#i|n*na?0
zdZ5Lz|BAd-utDIw38^f4L#2t&Do7jdFD6X{dhMRumHm^!svd0eA7FK^bXV?6;6XWf
z%pL@eN1D<%M#xOpLefrbMrYYHbM{;Exoh5*mM^@U+!epX6vrJ?xS?5{*L&!~ZccRb
zP=&7Oonu)2dRvt;ELrolJYey@><P$v{@!J*fVfa#CfRk-y&CK$fhmw{^aocj-5cGi
z_4rgZEbN{RXt41TlI$pdWK2M2ds)pKAoG0+G_%}8K`J+E-xq9<uQ@to>%J0D>$eoJ
z6(cz$z~rWXL-_(EJ3oQUeodd$g@Q!Vq%r_8O2cco*0ee)&MMmxu?-xP?;F_qRB+Rr
z>{r$xRv*a1oUtn%_bcl(g1CWUh^-M54|$zl*IYJ8)PqQo6<CL<nii5kdn?G<jwKCe
zMX!m6fhnbv6f4;xb>3;}s$fH9N2;sTKR!v;yfQ#jK4hnJl6022FG8at=cK**sHIFU
z_CYGAD(@B7;OoTO^3}-eyDAH%XvGCYpJE4(X$43i%G5FU^=?QTF8>50U%T={Rl()$
z>f;<!ev5UWhiWBB)=p2_hWhl!!-3zB6CX?B5nsxVul=qeS7wT#t{o=1c3LvJkt<Er
zNI{7!Nbj;lM!j7bjUnsA%=Schdi1L96d;JbaEIRU{^^$vZ<=UL<7!|T1^3-ubtR$x
z1@4IE)^F0EY1r<T%%Wo#=B&ld$FCS&AGSNiLH6w-<K=xPYR^_t*DDnCPn9B-ofPKG
zn(r_E7$`S(e(h$${!)535;Ps*v`TnrMATc+9n7sWrtP=QCl<jes%H@9E!1HcL>A7H
zi0K~cGA;Z-o#ycg|383V-Ep#G2qVw<tH|yz1RL45#7X*vP?!1@a!BJCzBiY9Pah}<
z8A2E7<uN7Z&^6I@MwOV7R0L_W4oH_BdooPiFHI$jzi=G<NK7(hd$fOkpnbiizDw&^
z0hD{tjuGHRAG<rzKD5Egt!GTrdfMY%thCN*Q*PjP>(Zj?p;wSEbM|s+ZuN7~IST^%
zAfCv*brzU-NaYU2=<dS7z5=g7U`LkJPR5Q3mn|KR=VzSKn$FA2p*k<MZS1!YE}j7_
z2KuM^*QV-H+~!#;j%jbTlh%`b(jIG#=G_$P9zGt;v~1MMm;D-{w~N>8q3+JK`bvg<
zkh<gZ1KAbzks~sblC@hFR9<X@gs0~X?8lX8(mL^ujy`Z&7ME$Os>NAFM|R>XsZQ{B
z3t6W`-@}un_J1s%TedrYbK?t{{XKA|FDPP@^-l$EMREC+m-w)vtyx(obNq62FfcKY
z?6ES&aFs_xv!3J9gu>w6m)yImvR38a9BF+Diczog@$A<<Nc1I@Mai?dVzlgRpNEe*
z=hmk#<7SjKz5sdT4s$pE0`-X-|50^SH$w(!+upV%-5#@;s^AhPrCMZeO2>AyL2kEL
zI=ucidG9m0x=Ll%Ig8>Rpu#f7+!>e4Y%i$Gn$D%A0S^rZ3;(d!kEUDOAI3OQl?_I>
zJ9^(<`m6WO>0B6YAlUJVh4J*N1nPkW%mnb3SFz%K$D&qFc?-dYGh&tfNkpf!Diu#D
zYbcoq{)eEkJ87H~DgR$~&6#fve%QaKxvIYZ=s=OWHR){_UOso*Ri+jCw5j*H+xI*>
zz^&m7h7&@KbZstvGTh92$EikaeOR=a`eZ1+O`xWA<=z2$`x8hD^;0afZGgY3eABG{
zE84@>`?F`(V&fPKBA*lT@GkZ@QJXpI5Aj@I@dRVa^Y>7ty%RI67v}EYk@k^>D^TKV
znb9|vE_ca<FKSKm+(PS>zxK4Dnpj8X#Ac~;o?YozM8k&N+@(fk(Alx;SYYB({Oah1
zm%~k5O8d6=MxWy#wGX}6)hD4NFO2Syp5z9>Lu%o$7s(P+b~VZ`-}hB8HBXFHCC;}c
zNCkzRK3&(BJ|=nlf9vW=cf?u7y+y={i7rT}VHAX8hm;<?|GOZ10on0I+6G)qXmQ?N
z#bLUA<2VpZQuWdtbvmH1{f${*eE(9)TEbKo_wpzSB+dQpRDcrktY-S0^kLB0pEzk4
zh#BI2y7bEULyYz-a#G*XyRzm^D5Z{Q0}nOr%XH~2-4N*aFQ*+%VKMuRCNuK&ZbSI7
zZq$yKZ3t9#d#j!*F_)?)nY2L3q+m0hnOEW<UypJJcA&cY+NP(1BQFq5&=!!IZot*r
z>46v6@)Y`gF-}2QxA3Z(B`LGZLed3vf>zmxZ9dlnv-5U0?{lG>CW0y>NbUS;G1plD
zL!(35BrT-UUz}y;jQaOgo0@l)iYh@#_@F>$`P8HV@~*9kPSzXlhI3n^rYJ=b=>xb|
zn#(J*b(Y|J=5Z{vCc)p9hX%v}HfmAvpXP|U2I|44ieJL^dlhWm-24h{7=EnL(xZ^)
zIip(yfYP4zc3m$_=n29v5|20oqcuDS`gE5{(pHU9(H#UNC9#J%6#J{W4^{O4{VXT;
zmskL)(bU$4rLK-@(w;HZ1$g$jSQ}p_^2Rh+wYA4k+A<OgZFmC3QI+yP|DdY2mK*H>
zk6Dk_C(BI}X4Tw$j1D_n=?-pH;r@*;Y+EF_-(8oTvaW*nbDQ_UNQgt65f=JxaTCHC
zgGIz_?I~_Z+dRgML1jHhwlDLROV;5CMzkS<0b<j}ZUU3}T~#|}q`oNDzMaBePUs(Y
z3V<o}+l00@8OMFKEp&I%QFmdw6;9sE6usLis_~xaOwWf<Th%CnSE|%ly(5Q+V@jC|
zEDM2?>iAv0<B`cG^{D9xU4x?5RK%zVB52mHF~P!51^~b+=lqHt>cz<#zr#X5zm&mr
z4I&mQ>Wkk&S*}L=7WDHQz5fL!?-8ub5rGoJLH=;5@&H%l;=^9H+paHtD*e1sF@jIy
zo%q+qhqDy7Smw4W!=v$3?)2D8bgX*EYa)?a(H@}@Qa#4xa|q;^OFyJw)13tNl<fLe
z)MA*Wr)rOh;H5t4lxvuMM=EK&6L(ep|ID3Fe~xf#3si})7*-?^pUyc;%ztOt5!jSH
zLPk;zQJ!dw4HM7>Bkcp4KQi!bvYEnHH_}nYhWx+c*xm=+^lP_w3O*0i6ZlKvGLLEG
zpxwclK0udsqtT$)Wo*+6DU>_qSdmH|C(49D)G|C+qDA;VMXxpzuVk=)l%#-lQqv#(
zE2M$>T72!E>zn}{q!@Cdp>6Jrt+S{;wDSdbZz`ORU7}1{<z_Ka%N7cKq|EGg>j?>@
zrlaDrp4()1N!Q*VoapfL?2@HMf-`mv;Kl2th5F?3`aeda!Xq->$Ku<P|E{1<yk>i!
zYWA{2ihn2gjd3mZ$jDHhl#mc4n)K=yv0jiPxtro5eRxfI*h&$RN&7BP^kH{_fyO6P
zPR#md(!kfP8Dn>sRxkVGN4|fU)kbR)D`hihESx;1S2bvUWcE?%^GFBD!3F&<cnrGy
z=%E<yNVhca9~~P-eS{gB@%3h+LDa6@BB<c&9fD~FFI4{(K0T-50c)|;a@{z!CfN_?
zv(zK)YjtIUQL-pcjv(KPgM6DDEQ=srf4@qS!iNx-r2T3~r*FMqa1d*{V<q2>nW^?O
zpf7(G+3wfoYPrAUCnGjoVBEs`^ORKe)Rc(JcjN}Br`ZNqZ(#ZuJr2ds&Kcq8+>Dag
zwE8ES_$wbU4+o>@)viJAG$Pw(oESy;l&zDBTVCg>s6lLO<h7vU)xp(us^4_xEha9I
zz8Fai5wv_Q-bR@wqD&e3$Z}OaO%sjzuG=Enr4v;}%phvp@l>88I;~*X@V6_AJO}Iz
z7T;sC87pCbk|PLSom#h&KK*|0znc+5zFO`&DGd$se213k#p)Uj;U?>XCnTo3L&CpM
zlFNc+jkV@q9kghW@JikRB8z+x&SPPAr}2}4{|RW%9Vy9g<N*HZf2md2|JA&ChXt8t
zLoLm~)TzvrRA4ONt}_v{)QAEU4nSJAMk&=9SM-7kUJTW@lNeYE0vOy}4qD^((?TMY
zlAWpO+q9Qi#7*OHa##t;sQ1csSUf@%{DRu@<mv_~xKGRyw@46eK$MOxoDYW0>|<Wz
zs(*paODutI$WSf*37aMfx)KZ`Z?R7!ssBE6{$5P~DcgF}6CnvwRMMR~cO&S9^8`AG
zAWYiIHpGrONISHUYju(#g?e71Lj}j9W|A6Y2upG~b~Uhcp&s)@ZX=RYDsw0xLawQ)
ze<yX)&*|88jxM{;i=HJ`=o}oQFN$?jViP|mxKj|qZaRi?5GFclXp4B9{hY5S`zr%s
zbh-P@sS&}vhnTGa0dsc0Z|X`gbC?1u>yc4^cLCF-e(Osst-1L`?>jNvE&a{zs#>5i
zb;rQ=KQiJrwE&bO*x>x?<$Rv+dotclyYPa$qnkuiH<78eC75$ishkd8z)rG1P16);
z+KutIQ?q!NjVSt!DR*MQ!Q1V)8~4eG&<pa>&4S1JgTXkd;Q@5mHfkdh1bOGRIO4py
znpDL24Dl>7)czDZ@$gX3|AQ1oAihloD;e(px@M9h=%E%V-H2bI{(G?%sms|xd8$ts
zBu;r8<_j|T;JFtj0m<wNA-oyj&eMN$x(~N}$GzkZ6d!P%AY9v_{YPG1MTkxJSd&U3
zk`yw=O@GfG?9g@n$o6M(B#wEoJkl`*NQVE$Wei3*#=Mb%U+^vZt;jn#Bjk0P<*Y!L
zpqm`f{!Nc-wp4=tW_#B5N4cmp@QBOZXI!VnKd$U{ANbr()(lb%79bx_dIga+pMLCd
zMZB65ke^o?9rr%h+cuQoR7LnUqce(f4u|!;Z^K(8Sz_0jJ7bh9Ml7!5%9Qvw*eE#H
zTtClA(tELyDw1@hy4*%(LP(t{%nY?(sk(|wc1)o4;RCKjv(cY9)UJQ8l$ADawH0Ko
zk!lCZ|J^7naFYSPb8M$1t6H@FU+5udi($CzCCE9FMamzl*pmPbkuuhFI2qt{PQ%%I
zh^h#XKck{#f=<Wb4O7)}0?@*6?n|r6C(-a{X49EcU;sa-7Y-~{69D^#0-FiIguQGM
zz)hy5@qgBE{%1Ys|2P)?-&L3Yp}hRBA51Ziq>MCSe1}fp@8~T5^j>(i8K!so_Xe4=
zk>YBwrl&;r=g3CBe>(;l@Baf7#HVU62Y3&|Fh-kN=1Yud&iSSEo&idjeTL+z+iD)I
zhv}Jb?c)Md8zo}M>8F5JA`Op*f2P`MXc~xr504jNka)vxP1TgS+-y5Kl5_+pQ53-4
zSjlH>vd*>2)?JBbe5u#p9;r_cI-xYWo~FpYJ<r=(h?*5!-J4g3k*2c+f;P=n<2U{A
zU{KXNYtq&6X2$c1t_$MF-yf$*Kje4i2H;|uc*r=$K0=U<7klk)=)#kKK^dL%Z1|`J
zFH2=0{}qSocPqs<IyT1PbU5{5_Y;~nL;0R!)%AXMKYM~Zc=#843S(i*%~$r#6KvV&
zT{`P1?!Ou&g58=OMEwbi<`=VdhM3}I7<{bN3VulSc4phxr7^QJdf^;d2yR=_xbT~)
zP@4s+(4bZ&6)1qO9={oZUb(=M2IM<H)$ZU^5Z#z-`}WV!D@hkei$9Dv^o7n>5%)lS
zmAaiYEpYx0Q_nZNfR%|sExEiM=-IFd!#ePQCB96zEt$?`KR3j?^w{9xe%8jxi0^7?
zc`n-FE91=@?G01-LVlyDRec$0CA#6y4fYNYw?P2$Q@L4U`ULG=!-u}dZ?t~|s_AM6
z{KJGD8G@I9o4KcV->Cmq>cY72zd%E8(gKIf_NZ3a{RKj40??0_2&ztm65GdXri(@J
zLqO9K)|(-0`ZKJ*JZN=`*3wWSM_gL!PVSM-y&L*I!Afooqy>i4aPJMS$H)>F6ZEWm
zVba!9MKaVf{p(@gMtUk=yTuj(1#nC9aA`-%sz&{{U`dzzqA6w~E<688+xYNLv`gar
zVuSOHUG0N4b<58Ki%s>VNrlLcxCQpg04UjfL9kSC2<UB5{AQYyW|r5C5B&l|H~Ruc
z@AxmnCr#IfDwZ$)shvdDhEvP0)&JCbacI=#MbxpKXqg<H_>2gngf!`>RH(T=t6^G9
z%B4`uUT*|6{te9}YtK5TJVnY)MFDbE%ol{MTt7tOL?;E#naU^2T=;q+RZX^n5*;Zq
zj2(_EMQKjPL|KEu)J>Tcv<1UOwA88nF0xdToYP}g`o7}b_myt_yFL|z(Byna$yyb+
z!KU=qT6Tn>j6-jn$htPI_t;C#;LO=4zQjNCS@+{F^NDa*<!<wupWeg3=C+IxY7a>z
zv_7rYW}_JJ4Sh^qpq<K%kfN9tv&M$asooA<l1)JTL5GjHap~9u;lek3gOVA`NnCIN
z2=&3>x{~B6LMEtIZxmmiHx&o%rnX&o^He+XOh>}tfj8I9&#_jKC}{YG&Q5eZ|5_5r
ze#~zX95KRmr?RI#bE73W@@0gj;1<E`j!jk57@v8$=6zzo*q!z+qXpy7Y`;y5!dJA`
z2VGUJocC+raVZjUhR%8u+I4i_Tu&2Xuq@h68IWQn`g}i9S0QN4Rj*`D*<paN&I>h(
z=wmgOT}%@IL8iJCyfJ?<6#U&&zix#?7j#yR?4=4itIJjBz-fkXfF5Yikfi(N>jK#k
zb+z4J7w=L8+Xcx0#R0j2vN=&E-<c?a>_bUnLq0U3mc{iHfWC0!OeM*;;IhcRJw6`R
zVLRKdql}N>F1;6Yppvnw@1k!tFIF6NjfB;)+PRIRNT2DuW1J)`r$2-cS!7zejO81K
zTz3CJ42rF_w>ULT(6C)t$fs1U^jwg<;5T>v_AN1|Q9(TzW9D@BYFfS&h)@FWMU2c=
z=CVf1z$h#mR9Es8dgeUJ+j~$PqTBQJ+go2_W939ad3D*`z7Nf~Mm;|y6~uf&x)Snx
z!$#L)G2vsNw=K39vWH5lM*@9sG?#AoWo%6|DYt50i$h1Scrk?pvuLJ6^_N^M-ehZL
zZU>^-bU9}z@w18<+}@*9r=RGM3>hPX=l<=~Jd^0Emm@sr@2M;vD+YCGAh(l>zsOz4
z2BWCmevk%%k2%b62lh<(Vc3&2gkoSl^n|pEoL^XbEL!kZYJ>f<4_unMnr5lWw>=QJ
z7KIf|BzAK2wlbuJt%5*{yPzW5PZV*WYxOR$scFwsvs~zd_s`ErGtG(#!e__n$Ae(e
zG`#r?5Fxhcwwx{|o(QOqqV8lehaA7JT&xlOd&ni$E&^Xw-tLNGE|$C&w~6P?eMW5@
zeQ_D;`<>3z!k(&kK+ZkO!kaog3w%dOr_TNTq$~}g8?Ndg8g^uqW;#KZSXX9KJpg2O
zH|D*C=Tz{$yI2cRx7(>22M_Qkr%+U<?W^esE2`1+CN9ESJ*zlnv7TF#L&&>vLVwnu
zf>Y&W44tWL*9A+7gXuXNvlch`hD4Qglj@zbgUW~I2!-A~xa5tXC*p^>-=V^t@H_Xe
zn)LGLnA$MaXGO54=OeX(oeV_ml`QXLMQS2;r~U)<q6r$hD(>QLp)&K#9NxL$Wwb@l
zAh2c|lj@mCZJA0zT~yTXiJB_Ot$WDN_lSHZJ3ORXCkL+z`f6};>eYM&aW(qG(IX9T
zUMI?eS5l`&|2-4FP)FDM6DkQ{_{qt20UXOQmZjFNZoMj3B7^Ln5j`teI9z#qFs5Js
zIJ+C2#Z`z&LnaBoZ)-cOiO&(IECg;h0i*bo{y?g%eMJ>FB%K<&6d1B9co~}&Iqh{j
zSV%sm$%#m1FsKeCILEHL-;u9(CKFISsq3q}-&v^)#CwN@S~Ik==P6p*gdxL}2UQ2+
zhrdKqFbxvDO4gCAzU(is3^&kn(?)2T$lnmTSSkJ_vk?^3{<YrhZ77HC_Nzjbq}wWJ
zdYL>!>-&8*uXZ{@Ae}hJT3wP~hZOs+Vn<LJ`x@o8GO!F6oB-4&=M2(C*_sH_?XW4;
z);vPm0mmOtbTBPd!@M=D=Vnuk3WK0v?Urg<u(}pl`Ds{O3-u|fpo?sP84V_zf2F(z
z<3fEZZ%WtTjy}<T<Knri#jEB3Q)gyFBSS$5e8(<ZRuEyY1j`U4T6b0>m~t@1v|*SW
zw14JyxQgb437@KGgunmf9dR*y#l+p!ttBc*<&jrZje@RYmwedg!ky3~QXRxCz%a=`
zsp}ztNXcKwqOAJJ(k?qBFf2*RrjaXI9rM1jO}R?Tdoe0{&l8n`?n*wzEb7|%s^cdB
zJ$;0{gCfCc1}Lr!KV8#PI;G%_%jbu79SGvq1hKs4%U4ds8$MK$Q&1x-H&Tu|$7+)@
zS5?8;L^*VMn;XB2_NW_b!`j`$S09K~EGU&{eIWhC3zz98awE?nRg?4F?4kcivD#k>
z39P+udLaAY1iOFH_|)TtF8>W~kc3B!Wm1e+qAD@;R($bql%KbCsi^DU-$AhCOq^zW
zB~B^t@a0+6!=~#2|2@O62pUFuhq=2djl@I)O^I<y?0N<Ejnh1;rtd=?zJmCR)_E*p
zSc20EZum+E1h+%V)^i>1?=NhZZ{dA4hgeMaF0#C$Y>hSXT{Qa!h}j;sDz|;JIDO^k
zGB9MkK!UC=jL1x1vF#QwXYV^|PP1@sMs0(Q9nC`QY>fg5bkE-heo?G2?~o=T=B>XU
z^I>-+e0i}jtDG!6an3H`CvEzPu~?O&&=PZnbF`(jZ}OIDJg%ZwU&ztvc$~`jV*OJA
zo02hV`+mS|6OD^$?xMkp7;eM-cH2i=f7^0#ZxopKNGlqICUXdlxQUr;Bl1W|U{C$m
z1CqlCd)qU=jgel>EXV>5^VSJ(p#ng%hP*1XW-eU@Wx~@93~d`YISdei;--}@X5V#F
zcwJ%P=>;+Mqj@y$-r8{wpNYv;<v87j09Ja*ud1i`IEp;I4Z&%g?q~hA)2mOt{x!T`
zr#S!CmHvG4!afI5#iw(}N4;#9Ls!-chz+9ZSUSu{4sHdt4GUFwGjd|S@C+-`%p_0G
z@wi&G$K@~%_=(mw0f<!9a_l>kU8RA3tQCUgleN=?)@gDFelDPZdyxy1gmSZ{zgt?8
zNko-gqMy<sNB1*9jET=8pZGV?R?0!OMyU08g|c!nPF-|Bp)DDA3~}s@*3NK5j@^fk
zx3$8gD?MnG2lKeQ+wwi(cW|Rm2#!z4q^^|~7*$2OJf1sSgZ^E0#7JoIwlNd)Y-2@7
zXBQj8$SKHR=%78`*4JPE&8K(d{7I!nM!Chl==?%Ta9Jkhnda+-PinNM0Eq%ldAGeU
zi0^cuw>ncl{X~v<EJSey+;i>(srr1kJ`EInzpD+Jc<L~FCp}&x@4-)Z92S0JUd<Y|
z(DE(*yNYl`@RE8-p1%)}KQRsYzquECYhO2Y8h2^#?wN*M-^l2jY^qtCvv4Eb+^W%J
zTV<m1#5Alif|2q=2MS=AcgTyo!QK3ML9&n2N$_O7MrT_%;p<+#@zzC;t-zf+&jQ)n
z$m^_;G}(HG>pgq7@LzFfD-A9%#LBc>+_<LhO3l%IRzqKXy=}A@Pq3jmwJLj=!#*~)
z?U!92+J!(KdS~yc8RXW0GS_K`VB4`7;ebT4$xl$UQ*LJ9sk$#agKKL`9X?g6ad5$%
z+=&)}^yoLXa#@yKHnuhct6x-=V_xc};=kW#utXN1)Gnh3J#06+t=gVTmzz8*Q9|V^
znlssgON?g}Bvb%$2}pnAq|Zr+G3&Qjp_eqk=%ikIUyQ<F&YHAImUEf{=W9r(o~J)!
z`eU+gBMjtmsx|YSymvvq)$vI8QFoX+JElCd_3<a<EbE6O?7-sP_ON7a<>e=nx2tVm
z*0M>~doD@tBh7uv_HW6d7iw3Z<6d;qfo21)BoU|JNb{t^c)>|LRi+0u(<*DryJ?Z#
z&pl?)*vkt4c^>zReWua$J&cSC=6Trol|?U%>p*F?fff8_bo`<dccWC5$rQGdJskYY
z@-HS!yxujXL(ezt<E#Rn8T|_jj`LWaBCG0#{I?x}72>$Xwh!?Q;K$%iyd<VYNjW+j
z1!q0dnl4@Axy+raKe_axm+<@aD){beQkBXc{3odC_{*~a_kVy`kBSKKQB<MX_usE2
zhk~IEWjsw~>b71_H_X6J!q~-5I<)?v`(&?sFBg^jx2_d|EJ5D0)e36WA17c$lxBw&
zczM|SZM<h(ly-@}CuZoXSx_tQq)L3T&80bBlWx;MLhW?QO}_@b$K1_lH`1+(y7Rce
z-Lbe1oe&`I$$B@bqVJdOqYmd_H~+S!<_GeXcSCr1dCHreP@A7ZEkK_J){c&zu2jZ^
z37z#_SKQOv&(W}$+NSbvZSi9N4$lP(==JGWag}Nw-7f~RvXr^)ljv>J?4<dr4?<ZV
z!M=Zmr<y%ym2TV!hRj+X4c(j|8s*;1RR?U4*_paJF8ALbVZt}w-}t<{y9>X<tZSq|
z>Qeil*a#8n0C;OX=<~n^#<zt#r!)5}H=Ny+Uu;JfxjXC3>eGJazf7YGw$13iwg$ZZ
z2t6?tZc#PfqQvV7H}ff4a5qM#&Xc~pA@EVhL}OnCo*jvdVl6hE_X>g}_w69BXcD94
zJb`l!HvFVbnXca9lU^oe9TaITfjB^vq{>J|VPz+0CGUwB>#aC0+Z(vn?zP`-J+@b=
z^uO-A-z4S&e}dz=d)qlRkc;FGL*XPP;$6=*rEKJrDk@4F0<fNG2Y~3LQAbC2m)t#=
zik7aI`mog!XT9sSaK!r}&&a~z_Nhz{o7HXHFfUKB#g5l4BEUFbr*yYd_rk}AH_=KU
zG%6YW`hU;*EfH%^mEhGm^0BWCPD^j+ZP^-2VY{l5kOzu1GJMQMNdirK+O&V?cKE!*
z!E+nBU{-Cyjb4N3wuJg6SLhBoVF=FqHff@bz|<$La|7GCj`ARlO#4bxXOe+xGpr0A
z)YoGkt_J$~{G!~6!=>NM7NPMVit+}l(pR{bG8eNw&OOCK=FQVvt;jxgQ{OP&@07bs
zSpivl=WSzDsbL=*qz_iUCZzphZYOEnQdGnWx@w5?`<R_d*0B<Ot$Z=bk&*Zr%gA)Y
zqAp$ZH;uK7;0dEOlsM`o%tvrvig?bvp)A$Bgc(;0iY*D8-T1X3sL1%mkV>+a3V*LH
z-XX#vSYOoP<jCyH+0QhMA6h%khrzIuJDR1Yl)5~XDKeYRNsYVnb2V^d$eJO)p^Y68
z!!TG|(ZX1$UTmJFMF_)X#W-#YJ-_KqrkV4ag6PbaFGfG2T#aRHFAP2@b}lGe;2)$P
z0Lgk<V#<q-krlw<_vVqTq7EYY*K#T7XD$}p_swC5D@gFHJ1h6Qro7hf><nZ-NFJZ4
zGci?{d%OB58LS4zl(JDG&t=|f<SeDP64?C~9mb_`T*-EkcfMZ=ar~Hxm;Rfoa&Sp^
z99MA)OQ(9sBsvVEb%0<mMbbrifjlgfvp+<pN+x!H2gBvmBpCbCL<&``d8-jFv>&h%
zP+i2Nw>~0aU_YCQT!H$LONNiXARe_!1e~5!mCSSrT5dHyQ{(3;(ZZOr_n%<3umL7}
zUrJH4pn0C}c6an`4X##cdla^rlEBg|0tz)>N-Sndaub}Eu$z|YzsE50=xp!e^%HYL
zq&llULNXB%B0A*YVnH9wKJek^*l`F)1+Jn%%5EYdhM=y~kY*yjFIm1#t74p$1;_Gz
zX@>@u?g!NyFsVS&VM)#)GZjKrdqlEUXLaDAxriSl>WziEtI4C+_*=tle(6sIL|Zz$
zQC`!E*X_%xWulwh{skm0ogIn2Gf#n|xXzbDWYWhw%Fmxl+I*V*Q&%OAkY3>U)ULz=
zB!Cmdue4>Fh6Pdee;Q(ZsUo(8n0&laDa<ZsOc;~ofQIU7BFIKYHRi)=Nq$Dz!YvZ5
zA|cfj!ubpH41d|F7)Q}&GXN+fCe93rIuYUrmo+T8=e>D;GQ9;c)uv<dc)Z8nw`HB)
z$frYgY6hBH_C3!K`*MWUJ6e)`cK4k_uB0TVc=@`OX{SiV5kU^_`4k}sN}W_@(x=Y!
z>HT)yFd);5jSYCC#P+p@bif;vg1xVSl4AR{MuoXo(|SwNLNA~FV5k-4>_+8d46ay^
zj-sOq@z}1EPi06~SV?2s*`|S&EjuQ#wmnV(cUWXdEB0fkJQPHFX`LsP*&)0pbr<XV
zfY?)s;A4|GSgaZc*e(hB?J(Tc@X>lNcI}%0n@+UT6X&6xQkfK(L7N7)l=Eu^KxwTd
zt~x!gwDU}_)z{Vaq2|H53#RrNtOC-pC+ZAh2?-M*J4cumq)#bmID4?>8ofDcvLHH!
zU(5K>COG@%!j7#SE9j{8jG9J4J$~9p;FLcvSkhKs%64o|CSV1gXpos4&AnyTc|!>`
zTGFIzW<YcK%V|vs0EZv4capi?9&YL{LjaW9^-8EEVPbm4p8T3<l+3d!*srjlF&PlM
z4&v`!xwE{-CQTPF#+AkdU3^`K6bUHpM2opBS8{l&$3_0Eo#GeNmS&_`RZSe{3icQa
zZ93Gtj5=bsl~&>j$S&^ok1`oO4OYOs-m8Vb!*?wmB-J8ofr1vRKmJ*<DvjP=nEJt3
zh?DP3^Jb#oi;5C9)d=UZ%!){J&|&Qv!X>zYRX2}+=t0epNi6{8N@M%-bE_FX(2}U1
zVtv#se4*9^k8<a8rqZ6_q6Aon<<o*feAd}(S39d`{V)-7GKSNUay4`Ip9J)`BoL0U
z3fS6A{><Eo44KDi+WC4)6`~J(c|>Y-9Gg@nmcG)1fXlNe&r&eBNzG5wYIMB9STVgI
zB=EZLHnlufYnQBn_r=pX^tf59?_0OwFel>HStTep`islox#q*#it72c{{g8OTa-lY
z*^=GCh7KNlQ>@I7poGD6v$FG3OaIUE<`51cv@}mFsmBUt$fBO&L|1dpuyU2#J2=-%
z6GkJ?;HN3^zaS;^uwIQSPb8QF$}@EqCKx$?`Bi;vC_j5jl;_lppQa>_G%9Pk{fax8
z1Rb%o7Zly$>G|e-^V*?{o79Vs-$y*;wJ{8tWsP!0p*lw_h^IdqNU9V5?)S<HM>*+%
zyB{l~@onP6y}uIKDWS0e^6_uXg^GlEG&kV;Hm#0X$5&7O=b|Ik7kZcKZlIJJvtqXW
zy6;#)-<LxRa5of3id^n$0d|et^N!Ndff7ofb4vRCK10P66{}K8skYY8R~+uPpw#nr
z@78?7f;4@o(w0SbU4^x4$PDbpdC6_C^lwe>>sKBFIwXFWfos_0hv}ad2j(F++!%@e
z<7fGX<s5t_#Z!taEz+&tCVk!GVx&PnM@C85Nnej%YU_P}mg&CjAncFRK2~Rfgwp!k
z=+y#<z~-1mo#qEnkQm3A+ZdEeUVTWD-z|Y(Eo|g588hY_hqk`M?g9S?8Jmb?kb%ss
zJ548|+(#_>Z|^4@vPQbsurW6ssZ}VDZ+u7PQ^+NOYPVe1^V1HkuBDDvFC)Tw4R-oT
za_gzS)HHVv?;-52MmaC_5cW}sGWBMk{$P&0O{gp@wZLn6OTlpdmm8HQj_%0x5?%E%
zpMXaUC;teXAi|LQgnDPnk2TO0ywa$H{ZgEoez7E|y_;J0E{))QYwpy}(|nex6Zg&N
zn<O<4x)QbS4|08-H8g7e0)UCNE7eUG3-eX6s2CP~spU!Cn^HQ!OOL*1KFl*&@(}IZ
zguSGN>;DrvQz}3hh!lauW<%IfoW*d(wP65WMQ45)G5{`nsQ@-d&<qmFQ8fdrEFqOC
zo2)!F8NfqHR{9O{9Fg)O^itMHnO!Z^$c+d|4kW_!&Q*IholJ{&UdIteqzW(*)AiOk
zlffXv{eL4${jd6tU38SImi_lp%&_;q9wY>8`Y|}F&8m8~w29A4vYo_4wicq><{F^C
z3Z?T}vSJansfmV`TfeDR`l38tnps{It@b64KVBF=D+KeJojKKHtwd)YyacZ+G2R;N
z=Paeym$m=4`^*vh=k&_No$pR-!53ssKfPuyqEETgRa@Ur)^vyo8j)f+sjfCVg|OjK
zUq1cI$ZMqUbN0u$EAtmRr)Q(m0lpi|@^4uV{Npo8HxFpu-0{4v*+A#}{DaPVKR+%1
zjq8>98w+tQtmKYCxcjsKUmgC*%&+$@G38gLI(h18YXdlrlpDQZtxsxmCJ2Mf)b~jU
z^1UTe+8ya=@2~D4v#iN@-@etv@t;E-6qtSKTMtl{MY{y$PQ5%5J7p2^kfBevc6ap&
z-@hW^n<$SVza@C2`y<rS+K}Ap;{#mj`}I@0W~ocMu?i#0NMZJE1NXuU<F;|zV*59@
zS#qwlrg7mNi~j(~EBcGPqFJt#(VonV{jS0|ifgGD9>$yj7VebI9XGQQh(yDW4#XCn
z@$ChP@$ljt&u`us@Y0)D)?^y_t>p`Ny(?QZ!<UhqDpBo%g{c6@jZR-0$2&IT68#^U
zBU1Za3Ev%uDI@y$jn=ub9pQzMDaQs^7Dpz_yrW$-F<XBO>9#+|{^^LxpO8qMaQij)
z!qHAI93WuX%s=7gi8(#pWxjl02Ui+`ec2yOJ69=@4Qr-7IFa9D-KCfiEc@y{dpMAJ
zUz-d@PXl5A(<2D96SU*Qryf@;#3Bvg6>XilI<8e7+i0}&zASxUQ2QG(RGGT=ynXQ`
zx1V42>_3F3#-QBSCFEHrR+sDQTXCwqm#~|kDVyQcBy-oJTU~k#Iqp{Iy7WGp^f<b~
zQ*%q~nI_E4*D^a6K*Yih;sq#uUxgaT;V75CZ5H=7bFU_tO7MRRpLgKc5!dttmCk-;
z1c|-vikSTX^6XUJJ@A<AydXY#-CbX@l-=_&jeY>Nz13Ab!(9-^VbqJJO=tb)jR`2f
zV=-ssvZnDhQ-%*0b}iLv43;2dGIB_x1KwC#AnEc}voXo{`uugwK!Z!U2=5qzsWgIP
z*MpCo%X^CR<tniDh6lT<1Bi+jJRBc0aEsYqGJk`)6qj{3X)T~e`kG<Wu=4TUR$C>+
zC)iEdOpSPoB{Bbi+$?_;e~Yz?#tQ{e?x^YclW1Hqc&X&^VC#jRy6st^Z4FunZu;kP
z6Zl3_FWFWusg=ai;R60H^Tth}IPR#ws@xA@Qbccyr}E`XHK~o^J_E!qjYmXKp5<A$
z`bn1DkBTK=_;k^SknS=l*<>L$8en@_!6ej?3cYjv576v#mq<d=xhss!eoT1!l)Ttb
zuROK(rksHX!|Y97xPCnkbGUb5-t=O~`fkE?trg)yHVd3_A}zEHS3NE*_$eW+zF(8Z
zdq^uy(RNa^QP~g5`BSLzKL91mf|)&~apnMrbhJ?>8b`|K?^Qh{EA`;;m6DdO{{YG>
zzrmdci|Ok1)>(38+L+f5K_uF3gYq>}lCtoC8U6QwmB9Y8;9%P~f69^dsQ2Udww%W6
zOa$XkmZ1a+JS8P^Qde}*&WG;<+}*5;mJ*vx`I5PJ4l6n&ls4gH!)cG7P1_0t%?Fit
zy#DFWQ2U$p+a|!y+1{`sOAd6I!L$dnZGuGj7S1y`y@#xki5cz+b}7f97GF5Kbnr-H
zcyDbu$1T+g%#-OR9nYCBu5=hjOsGj_Sxc(jsfB3Tp?$SXpx7(}M~Q`y9jW=e?B(D^
z7a`OiQpg}1a9Q*;g@}i>F+`Z0VIgk7ES2_6ulKUnaNNZ&egAiyZ3VIphoI&;A6Bto
z$?=r6{P)P-f!CQ$^Q626l{R&*0lG%L)914wwXCqhZ3O!BQth`Pf*>Gwv+2rY7kHm>
zH96?YPIfw!slMM=fOnG@cx2q&Y)UF@@U6Fd!D9cixfPMc)LuM$dcjSxzj4*{n_M}g
zFE)kda#!22%JRs%__`$P)ig?LxY2lRVb!_D%%qDdj&Q@bppMetlJE)lSSRV>zFIL*
zn;%yx`hAtoR;2H)fvQ{dq$Y{_t5S`$^BwYm3A8n}ZpK2_C2by_EvFpJHD046kGEw#
z;Apf&Lv`G2<SrX`N<b;fG$wspF~!mNU~xy&hy_rTRq=_{s<LU)<rh|bHh%rrl6D7w
zroPLU_RGNVIX~|qYk??XtQ1h~e8a+7Z}wInD2t+#(gD$@B-jDW2{kYpmZ|z_8oD*4
zno@&*F)5KTA`i*tHJgI1$4;S?EMsMSSpVyCzXg>xam>P5dyO@(&jH;FPWap+MSHdU
zXLfZpK7M_+Auv4GwkzI@FqU@yge*Wx$8C~Lr{9~g&ivqd%Y0y7f7OlQ9YV^V5E7)f
z|HG+XVp?Mgi`;Xf@0I6MHiXXNyMf|06ca#>N3aU@-YCzN>!3UCt|Cg;?u?>1we(iH
zUYP%~ll-9i+C$Z<%a-CtsHLhrt1V}r^Erli?XL>+G-B|Ye+`ngsZ?Gq6k%Q|1QEl`
z`@{{Z@k3gPI8GvuOtoVe<rDR^Ov`8!7mE734Ro@tBLu*IH|{LXy<6FL9aBFX*fgP~
z8ecGiZwNUUDSkUAsluWXafx^jX1~zbQ)wQkhg%qqnA97`eqPM-$c&qmEpXWkn}r-j
zF_Qgr$XaK~QqML288BoJh1z*>VaUBaB-TWW>jgo@d#1@Tqbm7vFX>Xsmesai+`7m`
z{qD&HOCySU$73s4Z8&-w`oHn^RzYpP;k#~dC{A&A2~u2&6ligGr#K|IdkdvdnnKVZ
z!CiwprKL!4cXudWyh!=&{Abq8I@mLNucLMF&gA6HQD*Xd-~HUzwIc@;%v090ruJah
zpJJ_hewBsY>{s=#SOxgOKaCwD&i+te`SCsT4MG4rekr<`!;ttbWGq=L=LiH<SwA*%
z@Y8!7wO{{CMR(ge(X5*O?vWP3#{8K70=0TlU3k&q)pcdGm$`W0u7<zo1)_lwy*Lm>
zGYFOqLWI8_wNjYidjoS8RDOi0%(sdvoBlGU-a+ul652RPUak&64e#>BCB^v9CYoO^
z1j-oV$B=VsCVJj?=nMTCl$oZ^O0%BB-o`6+GQGl&LX`*QQnSW+RvMp0qiv&@XG{t9
zb5C%<2>~I#@}_c85M3|S0%NFMHulzUa70j&{80H~mA)WQ7EGTq&W-MdrmC!?4o+Fm
z)y6@g$b<~oZQ>feb;*cB@O}+)#zZ77Iz*FCE}iS$=gv+aG&6JXj$t|&Dk>5;OG|&D
zpA=+`AOd-7qh}DTMGo%AJsQ+&M8W|sY@*J&sl~*Wy4bIEg%t9qozhDPFn@n&n(m{2
z0n=?YHy{eafoH|mC=<SxV2R)?g)fZAv`JO&33|irID(;PLJ;uiV^>9ik{Y${>XZ#9
zf$9MYUtJ8;@E((_m=I$IuHqJtaNb;xnZJg!Tj-;|p)DRPre}n`6p+^6)5H^a#hFpz
zWP>A5OkrsY#lpa}%dSiFAQlT@rm{yn0uEb9bKCx%O|)=lZe^QBAY;@hR5YJ9)W`Kn
z{s9M(4zNWVsB9&Er>)pZ%O!TuK#BW?MV5uUByLc*STdu?Y{GcK(1twEh>cNT?U>##
z-epyD8T63-Cc+~E!uBU%XgsUN$j4@jZZBbN;_ITk;_lI|4$%0vX*i*lW0lMc(xsN`
zLD8h&cY#S!q?-Qs6^Xx1d`9X{8FxzLzyXbprfZ-6S^TqIl~t(fBrUok*)<VuNv92q
z;rW!b7`2@13@2RIjBCFZOK(_Eq?OQCJ2X7!kE?GuUk>#(^?koC^>4Rtr;WPYcx&m|
ziJh@;4ygS)`b&lfo86Z{#(0Cb_?<N>BkQG~_`*)^8Dnx6KIq;nZX<@eV$2oxO7XfG
zo2V2;zT0=%k4Uw#)9=iPStZu4O)y?}CEI|t%GtSaI}_#`54zw1Csn_JKd5iYfID5T
z)Z7tykrld*?FF_Y&SKmNCF0%2TpmEVzx4aXi{8iD(L&6gXR|HB3Z;Wo!H&OZ20~KJ
zN!l5}#(B*AvhVlU#PURFG!;KCKLI`K>*e(tQHf_2YlT!9jqg-jshZkc;qD(`<La>K
z<{$85T~f<M)4X4-(cemW?##Sn10tfJ%A?E*Sit7Xx9Hl%2T6Jz=%A%jEh+L8v_cuu
zjpb_PYDBxjv2F~ee^uHa4ffC-tC7j+tVupIP;3J8Zi4wIezU|#c4lX&RF&?EXxC2+
zZFl_O!MA^Dha_dGzw)0KX78N+1OE<trTGXc_y=Xy)jnMdF2OqerH^bs(l@!2|IR*O
z{pN+^ATbSolp%=@+m>Zrm0i!)AI$PEZKBGsoJsP}9s@4cO~;+05VC&cmhsliD-`vS
zbu+NM#_eNpiwVcTo)vF~lX+NW01Nvy0-s4-^!|tD?U;!$M|KH?u#WHYS7xXed(z4R
zTE$RF+nBRyoO2*xejQf15}vveQGI-D37;U*Dn^ZWs7`^#=d1uD9myKAwKLuviqRwy
z=Mh7X{5k1E8h#CD3`SU|`z>9T5{yI|`uV2%aaD*VJ#v=RtT$X;a)~lD(}ImpsyO*p
z!|*bfC0PjmTm9{niWq&G>VJS>i3CO04lxp_)VdlwpO5cyEeN$8U{)kh*vdX_&s^=2
z|Ibx?9~r79Y|j#|1RA5NW6Uci#yRYe@@%+Ab%y^vINvX@1p5=TPK%OO>q%_^ki3-B
zw|Z2mRv90gLiD~@dGe=Bn8VX@ca&j$NtHO~=a&CgpMC%2-wqu@AZNi0_x4SUFjJ{#
zzU|nzso1>PHCxlwG`i(4z>U#I2)N7Ud?Ej4`OrU5PLSxkQA3YYh4)#^H~Ba~=g2Yb
zdi%;}zZKP`V$6TM=5#s|5h4(WhA&G@w*K0=Fpes>4s^?tF;7rSO+#uJxrdOk^Q3LM
zUy|g6t-7ujZq-NUVjb5XG(}LO1GLV0TuTa}q;_ou?5?*x9|_!=gMZ8g1~gi{da74w
zN;z}o+7?JC`1@g-&Pr}xBRI-uG|1LsruYzf$9czlxbf2e7@w(5=*nK9bySLr@dnwv
z+bSVEex{i$uI)PcOb2e6s2~)+mbdZ#%%L1;^z-WvyvAuOF_Z&iB`?kYz3+Te1r^8W
zV&Ob8y%!~9F>Wp`Ehv|16gPESi;$|dnGwyn{^sA(9QgS9-)sP%Qt+$Z1bR@2avC3J
zfTTTC`lI=^luYOrYHDu!7WO&v&UZ|r^qWmw(q!X(Ut!DZs3_~u3v9`gq8JU=OuO$d
z6w^|ldb@mIGxZfWUWnc02+@XJQtEf-ly<x)`AucbbLnp(WgOJw$i`L^&eJsgT_yCl
z7vauFvR!tc!MN{~uVAGro|S(~4?j%#El6nG*%@tyg9-I{$M`c}RhP6L&}9Za@lJkt
zX|9|mysjCGB6?ScY!@gD$=QU6K)U`A{d8{uA?)LcY1VrFx#s_I{_<VTxkAa;ogJI7
z%zFc7duTntr?>iUYOr7`hA=p{1i|#B;|>-jkmI9)JL~gh86x;uU{cNUdU1q$Aqee{
zFb=}zZ_E-aoKT);lxrU-wW2d6V_;j`ooqIU!DvQ*$?HWjGEQv(>OazNN&sHic#>Ew
zf0I8+8cO4eLs?s~gG|kp?{fVL)#Q}vei&HQloc(51yhq{NXK=zb8t!D)%5|E1trhl
zu{rH>)$Kuec~#P7DwEY}>F1ujc8qc;d?J6&6RAvh64U>!{12emN_mRu$Z3fu0(I>b
z;0$(1T0HRexDPSm1j^igEs-T!(VgF(y+*zi=4LxbjSy*5qV1yz65~MxJ#{el-2FFc
ziUl$9H4V4p7)2>!ZGb?r&$h$Wu0FEP$QCB2%j%)P-$LDEK7y`yU=0n?_>`FdZ^If&
zv7{s%w0hl$T$nj2kL67J&qwo<qqcK1CG?4z0t(jC_uxFz==G%uYV>c(@eD#ewOo<e
z2VEY7?uA<Av5RMGRj?Ri+a@od)ZEjwZau?&O(1^#km=DvAC*#1e%vb`-u6EUvF;ox
zglMsmIj7cIb|QD<GZU<>QziALBQ0o$ki+6V!qEip_MqZ8H-Ba#L09YtBz`Hn%Upsc
zYM0^qC-qzKSGr+IrcfHzYF9?7rq=om_s7GmJ%*|et}s#$zEi(%DPE)XNU1mKgR@Uw
z;wLlP#JLi!6hqcviI5STHfOfS_7W(Twzo!N{c=o!e=z6$`#;s0??W-^^AyZeC`jq&
zq=S0ZEg$a6Z_T5>x}Riuj^c?iOk2JirC2hk#jeE$_A&r-4nf4`TBgP#=G&V8_T2(G
za|NuGx>=NzfU4~r;<Z=hsWn@<IsLMje(O{TMrxV!*lEPy@etwa7tS3Tprk@iMc}I!
zL0`0Inzk9YS|3R7!2cRnj$6lsI=}v~Zz5`|$dPLy{Ssc-SS6W-2fZ0yGn4J4-$jHt
zA@Wz>68&~uebeEZ4j-hj7eNn=GN37`S9xO#UJ$_~a~nb)ou}(iK4_E4kK$NkyGD1y
zc>|VSY$j}vDG}BB;@t~4Ff)GMHI7G{+CC&g&kddRS^sQH4>8L6q_+KyFhCl%#M0|r
zSAJ9ev@1|XLvL5CXth{0&`vMS*wYx69^IHwVp{hdpO*KB1@)L|VkVZZ=<6ZOI0>Tc
z`M3v*@NBtjoVv;fzjvDeADy=rm9|jfMgb+>7YF>wlI+gQ*^LdYf9InQ8<=AgaTtgZ
zPN^ekLk~umJgj$O)wQ`?SVXe%o;hk<t@z$?q;d8LUt@Fk)ri+h(Xxv>koh1?!3YJr
zHpXVS_G@8xd&b*|Q>wQo<)bCBk_^E9+UQpTFT+L?3+NrLOx(lv((k;PvTDJL1it_@
zhvtv(ASNRDf5x+1??%%JpBHq7o9v;I180-W^Z+c$4~7HYOxFLZB&5@ARr%B=M0YN?
zGiqwu(F>9?RHeGb0OpuPbH3`C4p}3BsN7~XqFtQ&Dsw0M_Q9Q2F$8}<TOk8&1VGdt
zJN3%S$xYGa{S_SdP&w#S9&o6xu%ecI$$fmN3h?=k;!}t-&g$*}Lno0&nv~m!d_#Jt
z%CZf%Wdz0;OR_<_EU0Rxgd0apk)>nky|->TmWZ)4UCMkF67TJRx+2-meq)m4u^vbT
z?J;C#Z(qXFzx1%XIwAK<GqV`1t>5WLEh_gJ7EUZPC#!Kr#S~I%K}b=Za1OC=(R%%$
zSWV8<MKh-4@^M;ZGD-hmj({iIdb?ylDf)W6LlUd{fUoc+p?kr0RX^=p>UUOEhsO3&
zGzh%56pX!Wg50_2z@~P@(AUe0Y-7U3)dBcdLK-SQY#sB$r@V_QlPeWWPd+FqiH}aR
z7wy0|_B7+>nG}BL`!=y}N=1SC^X{VEVfP9ikvNtMT!FPmuRFgRe~V4HBi<WRD+~H?
z^t?0ioy(UrXEo*A$|J8}#k^d#h|Z)GOFK#`T)JnBwaQ9_EZ8n|zoS!@5#P;S;e^+S
zMQLF8LuttiVIrw~T)P%SOS>{$z@g5{giI)WY}WtujYfRjOa)s${WNJl)gA^t#I2zh
zFglH?H^jbx|8b}4Yq8Lx{77dJqp%z-fiI+{)@w{OnG{-5hqI*=6R_|sI8*)A&<Qs1
zr@Y4JYJjR${n(W>ArSuvi2oixhW9}3Y`^7Hl+MK{pj1_Ah@4>0%wJ>Yu~%vbC-@kZ
zUJ3V4j<R>t4Au<OVOlE!!jHBU>T-$@0N<7lOj1dE+8^OcuKji-Sj&L_08UNsOl1tK
zC}n@6CtGlHLBal?ff2@K_)*&Z%&epd>Oq=91LP+T2K8syJb<yLJ^DEdg!1s@OTOQ@
zchxZ$(U~yHwLlL^thO;r%0g$uB7i~1oCR-`Kl-qV=QIK(!k%~H*_=kx_y>A@mv0Lt
zlxUW&)frBNV6rh3vCsRpnn!7UZpN1Dqx})gIGfOYIHpe;Rj!@LmC0kYEG730L-D+~
z+Pi|jN*Z)NEI4kHUy*jx$VU6j=Q3F-{$^g!VEEXjRSzp{H={7krjP0mFiys)JNO$T
zPmvzDrGbxo7hKJb^f@=KE`~~ba*b}ZKK_J>4mlZD=dqE-!Tz~si?G!W28Q#tJhF>e
z0#)<NPr`wt>ohYCU-qI6<g)dT^ehx%><t8Ek(UVuYL%}>SUiLU!KWqJlo|~z-FM}l
z-FDps2VDk>u!4hDXuaiY39H4*bsuMhv<aPOG1IA^*gFE>>3Y%E{{iqUkpe_hgC5N*
z;1}<h(<YjO2cq+wN@fAx35XD-;r-QQ1?oYH&N&(sxo(1_fb3H*CaGySmR~N1d|<Xs
z8a?VgH0imih@Rq~kbk^0VIthgi`bF?f3f{oG*1O9)a&xS4Kj>7vmivp6Q}PhaQTZL
z;jZJa>{iOvj&$~{v&zf##=YU2uku;%pWnlv3I$L$(Gom=#xvNV_}Gsj;y+1{s}br<
zkC)JY$CG~le%c{@RKVf5p_#3t2EMP>WlSi_H%71AuPpX93D<ZV=h6kYbjHoUKijrA
zZw68jrjvzA|7=|4TYc)1st_YI4_9cZU!lFm=yLWb<DseG_NH;$g&XN)#U+ClH{nZ@
zey!hU?b(TW@8^^yu-*Q?>hUbs7C10K?Q1};Lt~<Jnz)NuF?%5OCEr{bWaXD51iUT3
z#ER|O^($t3<v$ptur3JsudGtC70}yvdHas+x2X1;|LlTa>Yw2<NFExAi{lKg$pQ)a
zRFV$mnZ$u_F_L<OZp!$Z79T&`C6fB4oU27bZyZ+IXr7zqqek|gb3kZBB6)lI_7Gct
zy@(HG(=Y{(;KD8YGaz?i{{M?m_rDuW|2sT7M>VnlF8wrx5idpc{U7uX;ON_vuMI+O
z$%{(Ryl@~q-1!*I<fVy|%>7K`5g=|f-$-Q;cfNuWd0_-uTFP>|C?HjTYCVE1T~tpV
z2Q00JBGaY%7e-LY==Gy438+v@SMpR|D&KB91;NiEGl{0L0MVR+qi-pZ2jmMd#WP^>
z6hG*qPeDO%Xf3xRzbSEog2n*ky2R7}L$-su01BbAx@gyh5Fu1BruTpMu>1poP)yV9
z@6K}Zp{2uImp_)M(B8+GU)<#GZ=Vc+Fvhp)DvRLPwGc{MTDrc=UyBMjRUdO*2iBim
z@#or`GPjc~8HQ1ErsCidTLuL5+xCjaZ-M+7=lHoO^!LpFT$lLHYxH|~#JFWL129;u
z4QZ{2?)?eLrcbFQlR4a=PX;w&yd0n23p>y$5LA1)ntSP*zt}hVD)ZLWwOC_UGg&&0
z5P^C~Fl>9-+2}yILs5p<SnfJOE-T|w=RG$&9o{niNd)Ve{t_6nJn*LXRvVMBwY-}k
z>}gr2um7ry-cxj4E|x$E3K5n}^Sa{x4`AHos@=1O5Pb}y|1_1auY&NhmYx4DC7!$P
zSGiD6M&)upP+t|onjn7B3MrefrFAlT#{|TBJ`KLE%^Pp>ta&=jVhWUDGB2H^I-p2?
zC!FQ}YXz>VO2)ebI|EL(44A*?&<!iBh&_IKwX<f@E0lpKb^e@pqjSY?eZka+u&`==
z6s=C|eNukC*?wKVD!6-aQN1B}_Imp?(9!Dl;IWK6IBpHc{Al~4<omMDVvVQ^N4nD-
zQphrVte0>6oGBS^l{`1KUEV%@h<zHMb_8_rbD)cqi^+oVLyYUiNj#A2F#fho(^p1Z
z?T4C9rbyqEL-kg*PPE{PK#F)HsLm_8XG>>>!@4~FXAs`|w}$;^hCV*v&JDDbraWD+
zzl~?VCpol1h3iMJ?h$b_avmuQjBno6NLTX;8Y~2TpStq9DV_V&n`>lbeR`@FUY;>5
zNtAnoE6D{<rq)D6CX^xYBGu(F#NWL529iXG#|W!a^uGAIY4l(`g(2D3$D|&a8Y5#|
zmR!7N`b>^&)g%j<E5%&Ke12DR7RXiB<+?iJ%KIh0?%x2y$xKE!0J$^9K3O?vW(fli
z7s<bO*5TU~Ky~eJ!g2bjmQ7;j-G$v>ACV{c4ltdq>C8yhvNkb4Atnl{wqEoM*BG{_
zP~^PMPNyl_CME&XKGpKC7T0_*y}ENvPSaLp!&xp(R6}FSzd1H6oyZ6}HY^EXK`T{{
zTiS+xHcV2dsO(16?c@R_B*j8h%+wAcHIuJofial`4riN&>uwNv&2$-nEC|!$<HPKd
z_M}%Z{l$DdGUTq83GHzC;rnuvZ&NH9_W{PAn&ZCr_)Xl`Lk@Ktp06u_rP|cbV*49}
zVP+hNisn4SwnqOqe6=LWZw9)oFY=)NNaeZ|{ie1S?<D><8n!1_4Q7?>W6Cj5xf<z#
z=SXtM9AP&UBvAT_MLHw5I9KcK{`I+;Pi$kNEDzb9%;?M3)j2&cw8#8s(IqA?8M}05
z24WaipJ|f5ku0&j-hjKO$8Iss0_Lu<du*HXurr9BXs)LA2TR-L9c#N&wp9)0r+2=Q
zmwDQA)<<uf3ghzLtK(Y(pHDyM{82LA5N$|dW-S$ch;z_o7#Ky1HY4pvFTb39q&4AX
z8eIcsFW5PAx6^sKx~ywruWMjl#KbT|ais&p5DDPl9N+(pH<nfo*tj)|cHajPs7$x3
z`Or~!pF+}*Z2ZHdNlgc=t-m=fa{I!AH{oCTEh89s3!uX^wwmH6ft>JVAL7n^fj7&8
z`B~Y!^IFuyJVV#T8oZh0kuRg3C;R>9Z@aTQq`4I3_rRCsdf$Ae?aO&nl=s*Y|2$`j
zKD1kut3m}Tjt{MFR?U^ONq1)Kh5a^|FpXR=$9-6PcWTvZWjsZ*@X!r5WWf$6paL0q
zK>#rgi>#1YV9dBO2tI}HKS)3KWyaZbNnv>{!QPZiO;kAJU^750HA66wjZ9DcpqW(X
zHgJ5h`^G@MqRm^=pQWd6+*O!H?E6_d$Cf-*M~cZF`sPcLhk1|=e_()U(z>Wf4AP`a
zLP=JQ@?Fp_7wAqD5*R-R^8Ah*UyagJohtfN6`>;<D$q-6mI~F`Qj>A#^;lM)|FqZ}
zOnH;h*L#7T-wv@L{R%S|mV3BT7ivVW{N+YP%oy%#>^_g1iaX-YP$fx5x3_7u5<KHH
z(9L`xRt39eul2opBkOBKy%`SN9d1xHa!|Va0F#kpYR`O|X}hwp=Qgip;Z>h9NJIZf
z1UCHQ7n*IuI9J9|X<9=xJ<wL%`e{X1zgAj#ILOwB@)J@J!y9m2u@z4j@ZR;sPv7E_
z>W>$H*x#%pf!We}Ux)LMS+n-L?{LvJAEq6M{sX``rbSp`Yz+71<Xheo+B~L&+_kyX
zx97tT`s$NPXz9tagwE1oZCr;sWcP`<8@WPi?{JH=hc_c3*uG=RNt;*qv!i&--0a&;
zbwu$JuM<K9UJg3~eZ19Z2dhJw)O{^G8EPs)`7F_`S}~eY%e5yl*wVTfheqFERx7^H
zo^l<ptGdULgb;VjDh7IKj&J<X*Dq8JvR{2P-!~Z*pjO|xKxk+*(w+vg>wC*v=dSI>
zo!Au5hpqsbZkFUSs>*Z|hWp&8|AAuzoj4V7$3f;j{K4Qq5!l2CW3CbQ8ZFb%&!pT0
z+TlQQ2LbWD@;dT04KnZSX%$L~BuJNx4Ph_aq5-q}B?WV~ksBZhNH8;6UMc>vb3Mna
z(|)JKS#><f9MRL?{1cA%xx9}_um5d1n9RB%laAf5T-C{{_E));Am|b?OwMGWy{w|0
z+LJ-o>Yz&qc!L9?mYI*v0!>;KpSv}>Gs(PUg8hgoFGe!^lF5aNNpV4yA3J3mlQfkO
z9`3-ysq0gzQ@X#iKQ=$WlD{4Io92*9Q1{EPuK`oIVcIiE)7imN$3{`~cU7cMt4@&+
zDmGc3i`5|vN4#=}^kHht53I>jeR(`_&a=9PR$o#6^7>uW-+(}z>X^mn$XpT4cC9wa
z?%QI+n9Lz<Ecx!FF&5E1BS)Fd8D)F<!R>5eEcw0|$$Sx_{hWx5xJiZm0%4NZ2jszD
zWPOz)0#3YDQ6NTVnMnX^&SxD`q7Sxkc3t9O00mjg44hW;E*~vHbmrMx)e@el{8%>v
z<wob<FgMWl@BPCK&}C&U4j`ZDH(i3EIx^y)Uh8=$+GV%jl{HYv`f74UF#Ht7=@+S0
z*KHRy#d6}z{jM)eL4RF}2S5pT<;k+05iX$l2mfC8cH#3I%uQn#$Cd1ZLkn81CK2?#
ziHx5;A%;VX4uNn#$_6`{z=DI^!f*WI8l{Ahd$SX6&fk$U1K2H_N--q)w(>|UTk|UQ
zDQvxP^r^bQ!7mJOn4h$%vL<u{S`At-Zz2hU1h&>6ng)h^PUq|O#{C#mNLs}|#8mzZ
zME+Tct#M}oGJdX(GoM2)yxOv88;rNJ_x{)lWCj+h8mhq5q>6T8EI=6qx4MjGg;xle
zOpv_l>tjuH!R&4R?u#6%hx!K;btk?ojgxS=$dRwP1g%~>RO4?X?tcLBNmn3WaD)R%
zP~jm0tq>`+oE~KT0{da6W;<<8Z+Ktg+(@(YerSv|(1bnsQX(9QqG^`Tqi8Dj^OckY
zzf|~i00c8|8a<y$)ymLRW+Oo-h$fK_(S~`-=|xXK?613urf&`%t=zqPvUoRDBU{Hx
zn8MORzfs>-rO02(OS53oaAf?$c#_<YwQ9wzp7%C>h~~(o?gmknaniIRSe>=8Qc=Dg
zf5yU3GALWQ$II+k#ZRZB&q%YbsB+<JMOfhSK^}WU)8rK>l%v9BS+;j0&S>`s%=F%)
zI{>>4tmwX0&mi$2FwP$=3&z08wP5PJ*{|O)%qgPb^4grk^KeRaUstKXZiwf+bA&D!
zXmUXBK!*OxH5OyseXn@WEkr;^_35st-?p(s-Mh?R6I~&x$$Aaw*>Uu{-a0Yp2h(Lx
zy70}Wk?Se~JrxS~Sgjt>MP)D^%Jg@xY7r<YS_WfHmVZl8Je{&<lNaJ^v8ueO89}VK
zj#%<gahxD{ZP?g1DkybbrAcrcds&cZzi6ae#ujBx^aYb?xZs5eLcH5_yC>#A@=)iO
zKG4(_?qO#+*FWt+A8~?;OsH6Bme?<JzADypsHo@eXm@@NE2j^MGU6~Z!LQrT-QjTk
z%%Auj9)Ct8XFW$6f00~vs0|fib7PK!1SohTL~=_r_kULOTjb7DZ?B@Q8Hs0az9_Nb
zW6viXI1ebd*p~&V^7LXHYsrSrpj{-Emgv3oO_pnZu~YH}e9%S75Y0}xoftoWT`aU~
z@FI?BxEL#j#M0ONfsI|HN&6??7ij35hT%KRr1?zV=!}fNfIncyd=Jb20EKHzDR(MK
z6Cv#svp$ja0r0*A-L{|rOL@n*-2Av%1V@KT&K0-prvnODH7}i}-Ol*>hBi$9Rx(2b
zi!OZ3k*|(rctU8Ryi6y2f1r*`MF9>~8S^%U&tvC)T-DBdRZ+HPHlE@ctizbl@BGVF
zgp{p7FYdwU_m+OQYH@9;tD|Gx0B4~sqgm3QpzXwu#iS7@K$Ds6oXA+=hq(PFT3iI;
z8T3i;0KK6?Vp3UbEf(YB(!TNgZRX8+-ycDiI~$Nwgp3Nv<A+sWkKXe+Ykk;Tv7D)w
z=C7TlfUlF(iFDKm4on;3ZcCM<ixN#wW#!8TM~PR*Opq42F&$Dy&Fn|lp#zao@BW?{
zUe_wLwA9b?8JpQ)bu45ou9+7S7PCCIiOn5aGefXQy9SxPe0bw~^-2vF3etF+A30jX
zY+j7CQF*=HAH#$c)$q1|dQ@#oKY&wu29zC#IF^=_y;fikM-hQ@ax$j&lh=pYh+mQ#
ztQ<4?1WSBPUd6Tsm+W;eORqFMjjS4(vLxm0-@8^VA^S}y+nY$=WTLmsj2Rg@qd?PE
zSYOi8A~_wosD~=`m%ilfdbgHne*bJcLSqrx{R=U8{Wo_`<6S~77|$=_idS}1w+N<Z
zveVTV!x1%ZXA*aMY#`o)4C@eUDpzDxR<SiraF}Yr*>tTZS&=xGs2@BLGBwZYX?WhG
ze?=|VWKh9*!Y0MqO`dCp6PXB9+v+fVTDu@WzRU$J`=^yvj9x7LVvm%&$ImuVjLWEb
zmn<xJugau8+wy}{;N)PrS=0>S7rNt!SpI(De8vql-1&K+vEBKTAXrbWV0nnVd&gC1
z;D@idq?w1-@I(bmY=?&lLp0?=An~1mIL0_y^^^~XRW0QVG#t2}SvKS^-0LRT=ge6b
zHi7bFJ*iavP7$$K6JKzv!+{Je+>9VR4jnrZ+X*{!=X@Sj=JH|8p(@UaTQnx0!h!2W
ze|GxPLTqO}$N;ff!w2wnf#RZb^!oUswSO^}baQs*JQTOkzqJZ;VOmu|J4$Ii6IviD
zHowR(!z%XHCa!$Seq;_Tww<2l*G$Ag@iNlRtf0pd758z+f%o8YEuXf*FHE6t(=7NE
zS9D$RY*s`~35fs9b#@8w&oc~HTTB|SN_bX)O-xR_uIP8%t%<tBmY!VutG;D}U7Exs
zANf%-RF|JVgIQmM=}qPsY2y?M%m=#Y+`z&`7$sr<0c87x{@sg5ZHUb;1?4GC`z6*}
zu8s&tUS_Ht99koZem0eWTpalsCiE|GzMMQM*!<BU6R`)XjuQr9H)8+X%$ko_ZLkp8
zdLi+?rwill-=<bD-$ARYGhT0}ty-<rMgPs(b2I&d1TRod9ryWYzPWVP&t6NzxB5?Q
zKki9Fdc~?v>tD59W1YTN)Qf*Vg??;E-17Z0L48-F<^H*jK&4Zzix;?!fnO)S_u>w{
zeJ|F>7>hhXYf_Fm96pS1i`7w!dy;JvvQP(NWSKrk*paLw$Cbs?_kS2S1%CAcu(t5s
zNFkWQd^=taV8fB`)e3x?|Kuqj|KM(!v@@$A8NwHz9#k1IGv|sIUDLnRzpMr#F269-
zUP!O`g#NwNkV!6oCJUlSo$wNn8QgR9==Q6G@=G{C_MGdU%xABU<1vxZjv1s)wSN}A
zs<6POU-HC>V?W<4f(`}Bs4Xh2o^y_#UUOz*W{@ar`?e#!O=qiutq7&*_d5EWsh52B
z0l^dIs5V^M(HpK0x*sThe{}^B)*C_4vp#+%;{Dt;>0T>F!zkgu>fJ0!Qxj;?ZaKgv
zx5Un(B2`xMEvYj?8h$7c#y461Z#i04O-fAW!A(3(+H7J>G3Od1(M8_PS#*eMuf#ub
z_%WciwS?Pv<;rG$zW(hNH9Lx^E4hdm!daZQP;Ow#rnnPB{QDvbp?#AVwSmxzX`Y1e
z`q*#0;NcyY1)r`h<hWGuxg`hi0pVKyCH0Gt+ULoMEvvo|@{aMebO}k-INLl=hW36C
z`EJ~*xnvewgTiGDAY{(ngr8MVldB#PZlclJ5H0tMJ(=L?5$eUu!ta4QkfwSgnq4hg
ztw1sSu6k^tuAgO&mABP)NLCFATyc2@KR*ZQI+vcn!;IldDfB7Q_63j4>h7s}%J7Sy
z0a+2}#`7$0I2j{(3VQ2DSZtT>Nw)6|&Bw^nJu@%0ta|o`IO<!YD=)Jp01gjx4w=1x
zvIK;Jx6jeW>~u)<5EoiH!A3-7*~xEt_GcqwHQKjVl5ezuWRJ9EiOQ)?V;*E?8sydi
z+>di}OG_)@$&Y=NJwfaWN#X%lmUv+c_FEq*Ef-bTiR;SfsG;G<s#RoE5*?*q1Y<4@
zL|U2eqkrb;cFb{nx2gf$Qi!*U9JOwMoO_5OUX&4*66rO7Y2(lIG6M>Nk<@bv3n-(S
zKb7Q|{v{r}KSBVr<qFGM+C&8)kya*`!P=g|X4t0tbP&PY&{VHlWR(fH?456L)ho)4
z($W)Oz(A{dXHgs`;3ey-?JBzZo<c8yp5K+ii=#QCmsxVV`OG6f)OJ#en%P)J^-}Pi
z;^_c-hZR?EXQpF2jpSojG?6$3G-O7ly@RK9FZPcHfsOIMny>DztuNTwI-xg{VjYTE
zM#{34)oluCZYWVLIm9i487&UQca34F3}ou$E4!#n9G(#Gk@gqM;$}3AdpclJPpu%W
z$H_1EwA*zq(V!AK_^B>$3^Ad?GQC(X&GtyhZN`XC$N85wFpm%vz+>YgCs*?LV6dL%
zmd#kyMR{C59u9PRpN>GMWP%GFF4rsy2)qH7(VkS@T8?D@!vbk+b7Yy_cR~V!OK-4q
z;3pykdBafyB^X_tf>OuwSOOwy%0lu)^wUYOV#c2A4_gd`%)orqy!Jwp0{vrk75b;I
zhGF^i`W3yQ2Ey_H{iq4@KHh}1$^zsWp}B`jvmuVaDx>r?DP4B5h=$Y8?`z9NVK{Hh
zb7x8V9<PhBZm22r|1$B^-&BFs7((VWrXJJezNuRflJmD`1dRC!c1NI7UDSk3?)xA2
z`%PYukQdZt6h9g!{Q*+41^zWGS73zYM`vNZzNyhMpGBEm0^!aW4Dp^v3rUNMY9c>}
ziwd6ocNWINw@=Mt1}I$yfIs`kG-Kk%-s=6lu)2sLWnJ-I!MG6XEc|OtXDDF6@#9aw
zUx;-yQM$)B5*&>EJFy@nw$7V)hY_A%PD$>Ig5h94#qZnM{cQT9Tk;3+eSc3H^QFNl
z^C+3)?g4yVk&-}&=qujOFQnKP-c<ZWB8PHpu+2=Ops+!$;A&TW+u|gW%@aVxhvtH^
zAX{Pc%`ag$Y+aP-i1XMREwk0PKe)Z)xXd*?30EzFSzjbQblCI8JMrB)sbeOyLm`tI
zy6tSALZ(T_m;Qdh|9IoQ`H+G#dC1CAc-Ij<8E3?z4L*Uk0QrvW%@~IUu|S(l(LWgs
zmC8c)-4x8)Ao&B7FCa;=bJySK9|(X&zKQK?+Pcm&!&g`8e*SN+Cgf_s_j@Pbrjq3*
z6$5CIXm7YOd6Yaf+t_`-t90oTN1J|#E$^qaW3xFXVm9|9a;5{FFTIU}5rd2N<2W(~
zb#&=Jq~kRZh(?C*9^l@#3!=vImN_!!J8FchC!u1VG@FQh7kK5c9(W?;@GyfB_f2)S
zW^YY2|CKRc$TLN4*<VMtOmh@rqCsf6Bjc3hBRT{wiQd*-1>J2_9)2aTWKeeq&yy5g
ztgD9#U6=WZO=dDn4Tu&y%jivp=uPa&;~gs;9%@W|y(!I3(!?nH4`7|q3&@_iFKyq>
zfVx`hDgbuaD3V;O2TGHze358ktq1|b1IU(`>M!n(9jJ}8KHAxi>iFGcTi)#3TSP4Z
zvdWF_lX&EWjQ@WC+I?d|A{@q^js!x9GxaS6sqTl54~GS+lN`oZ9$N!U>I=fis+cq}
z>N8h-1FJ?UYst;1>9)tt3az1iMU{erxU=MasTvx)BukG0?6fo4Z`t<8mJ2bC&e>IR
zUK=of^UuL3ZK<cN?1aSpCVq%|ob&y>XR5D7$Tc`UE7fPII@_3Uinc@a5ObLIE2YVO
zph+OPCr88J>8wc(sHQ5M#x@Cl{isNk$MmL0g`vu^KDAZyKL9z4g|mAm{(Rd7XQ+w$
zwkXOudKr%8E$t;$ZC1(9NwM-*(bC;|rB3S9Ql6>AUydZ*y?b!@?5RpUlx9}ibq`B}
zc(`5TQHm?eN7<BUn76ibAho;JeDI2r^OsGOn4OB?d}Aq2>e7Vfl~r0|1ApteGM?;f
zcz@{NyW|h|s>X-#pJngwr|Q4PV)~!Ui>j3)$NL1(xPF4S_owziW+R_OP<f__0VcH*
zKhj6bC%q#ZBtRONw|ziOk;OxfOn}n5{lilGmriVT5<XP^AE4=%6S_>ejyinYB1ieu
zJzt^iKL7~>xB8yAS<}>JTcQBb=+o-Ldt36?VN6_@fwC3z%ThB43{}BBuW()}z1cpW
zCb0aQ9%<UH==R$1nk0OJyjRo*UEZxG{N6nF*T+VlHGAHz!F;~i^PsgE@9M=dPa%^}
z#+kRDxz1n7-DHrYEF`Gw@O^lr{#NwEBqZ2IE_I?=nd)5V37DyHuCD7`3kGDKU3DMo
zcAhi6RojCEOn}o)L}P%_a?RWsJJi(Ir6hoB^1OJbr2x5uLJ06P`Tt~K|9^)T1rki@
z;^%4xaG7(L<SPaimCzKy0k}o^{g~Uy5tIqYlrC~y+47=hasa9&CaTL4qBkFh3fhRS
z(Z(2lV@I_47bZ?$ivnoP)wuy<{4B@HE`TxWn<7zXa;%=T6jA?tTaD$!DS3Q2@pLlu
z8W6CZmJ9({&pN}kXZ`YVoRU*kAgDA?LrvL*+OMdYp~402wXPO9EdWcvTP+TC4`Qxe
z2)!mS=V{+hFCzyO#_h*VJ1<92T^2$V<o`!q^*=C2bVe)`MG^HW@PF8d*#8UC`2PWV
z{9pI}=kEXUQ3bh5n9e%Q@R@J(Dz`05z38@!0RAo0Xr1#jE6k{@)7M+6ug&$hz@6UP
zrc=f7P&l??g2-4@gHHm7-M7bOnrp~h52IjSZKsf7i_8}P5D7^0IicBoKuTH*;Hh@-
zeF^^rq{d&e7{0YImKfHrW4@2@pO3opRqCQGb!ur-akW!;W@n=yBc)$ZTC2|{N_`~M
zKh~JF?P|$PekZwI@j7Sq6LFW{I@+Jj3&s}4Z9~dQi7}d^xdi^b0@b^4x_(-Zva;Sc
z%SBLSd2=bEd8X(flRh<+h+9dj(LV`4XY`BALdoCSo(?Q%ssnWAq^4+((Fv`VF6hTx
zIAKox`juKEv<&_`b@@)&*&^tp`H$vDtI|ww*`Ieimd`LUh1U}4?4B?0OsH$C!eonk
z3xB80dvl|apohCk_sdaCi)Cru>9T6#;tR)-8W$2W2{nmuuhq9CY~v^Cje6mfgp9ZU
z`KdqUUiy9de00j+#Z06>*r{kAdAdK)%H`6%U#gl#GbUsiY2*mYc$gVn>lYa*Z;Nh8
z?Pa!&yWVeUa+ej`AT=}7%$hbB#Gxr~TH~C)TvT;@FOpqxtjjSCO0Qd6A#CX0LT=a_
zW-#tmhOtaLPOY7|!SS0De4^81+yW`KI!g06v%GE_S40hzRb>`B)GlPKgXA<~5wA}7
zFQ3gYrBm||L2?D*;$@+HGn!*O?gPPR;M^h+wSdRoi<+vQXPm75mJj|dMVMq2%XS~T
z;QJc(<rB?XC^An9U(2{{lJ?tzUt<D>YK_~(xZodj%8#~C)vKo0v<JDG<%9QKt{?sb
z^uyCi%J3~t)3Jid7@L#m6?Qp%=gZ!);&LQl3MVcd@f-&k-8Ov6h1u<Bk=Cx?^&35s
zHC%A+oa>(;HBYEL6a_=|@ytT}Z_7Vx*1}NIKglhjGvkpvoMxqn1mF5`;@R0`Y?s)9
z9epMLy`iQElS6~i-&39dUvnPZ38+-#WqFw@RAm(R!Klj27=?u<+Aay!O-dNNE%O3$
z$G`j$x}W=Opwv!89Z<S<;zaO9-A$eeRiOc+udLqt*g%_$uP`W8z+)LI8!6_rmYh3m
z(up4l?b(Iv69<F6qmFeg%{}g;B7gIGU;i}>pDwMi`n9WU_ThI`8Ma!??ImZ>1VYgV
z%MC#9U=w9j!)Nx@ult5#%7zC+IcPk%#LrJA&T!JAxi@wuT_#c=`8HX4;q4X^i7ANc
zn6ciLVn44l;05|%cok5K^M)D&?O;7wOKy9PV48E5VT=?8kv-CR879)zU}lY5loTPQ
zdOP?NvXJq&*J!G?H0T<UTqW_)%ZSuFKelvYSR=P-BthXvCTk<Y%w*G7n5Rc4cLMBf
zmY$o#7BJv#-#~*lOV{P-$>HG8*s>;A(f8<We>V!-$!RP_N!zGHP28P#Tz6mFLX4wp
zm)PF00H9;bRl&S_XRE-f(zE;WY!8A%!+g3nz%<S2HgYF|7h5`0&x=s3EC7R@cK@OC
z$M$QE`I8+?fm?<@?Uk2ZUA^~pLcb2Ek-UKViTA^$&7Fcmt0k$q%3v6sn~39%FjDmw
z<65QIH@lX_UV^~NPbZYaj^ULfRumC!*9YX;4lNjRJLm?NJM?y?GtebvV$E6o)@4%?
zuY=_bR`_ZR@FUSptAa><Bi)YiDa3v3KR|jaZV^+Cv&FG-%dNEV%I%#s?2GL2n24aP
zjyaze6jeG3b&clkj`0$7t$@;$DYZeB5@soC@HL@yJ^E&5rV=5C?#*;#Z~Q)jV;tyl
zH_A&G0E=+PWPZe}^N>9y-`AfPlG>JNV1@@FUJ4HeH8Q5j!&CP-ALWnZoXQzY4B(oq
zpStAstYYH3xGXKIJR7YlppG{TE}f|kEoe;YWtmU;&Uim-6t|PuH(;`%w7V76kaje#
z;4)!ev?Mjw&7@TW2PdULNzvq4YRxwRSWfLMv0_111@{(*@G4+jvJ}O%+Dr8dfc%)K
z<=~UBjlL@JpDVqHKEM5B8|&saUgrBHlS!0(Gr+_qsU>$VW%!mt)WBhLipPaD*kI&X
z3+fpEi=7~3dbF?RgpzSi(eBa@6T?)QzfP1Lj>lli%~)6*^Ls^=mN;G3+YFDOd~*lA
zw%4C5zBcY*J~`?w|9eeGL;D1T5s`gtL(3Zk`&HFbG3lY<nFBA?VDMc<oP4h97q}o@
ztGAJ{xbv#WfTeNBgmCs3V0h(Nbu!Itqcc~t`^gDrN~Z_SplF>HOj<+Vn&;}rPlSPt
z1UYwU45;bocty0H#B_H~wZRKKYs1JZUX4}CU9~u;b|5cjdC(;jGcKq)0Cw%^RPf*_
zpk(nBm%Rr-2N3cc_?)UpLS?fbzbDAoR<vKwvFjC(PbCM`jq|?V#macfCssE~dW$X9
z&))CgzBCR#5oXT6t|(0KwRwgS>wpbYhy)k=IX_$C)wfZLvAsK{Niwx>6TQvQ!sSqK
z^QTZ$^FRY84VuWnb1kC3*_}CJ>{CA&O$8xbbH3eFd!-Y!3$~TS@Fs|$nSE%Ij0BZ|
zh$yK40cT0b<I*s=vJK~Nx5akz5bC>V3lwoB;UuH@?eE8JXj(#?A#SgruKM9}Y#0-a
zC2rGbDR|Uk(Bw0jNQ-_K%<6$~DTwd^{atxx3=cj9J;7W=r;dk`2qtZsxbfpK*r7f*
z7$>c`_AWtPYw<<Vztw*{gjE!)Q3>kxeAWufyXZXimde_b-BVt?_ntGLig(PM76?=4
z7r^S|G*M<=$-Xa;kWOCjw?2#gvW7b)X77HHX}1-8QaXfx)j<C3{XpKp;@gfIbvl2s
zQGhJQ5^$y~V5q%4IZn1csoN5}&ndWz-K=TBtlZ+v2J6WNDM>~@n$^gVDJgKpppxTd
zXj32a;dDBt?{b7()4AX&lAC00Ro|muGP}GqnlplMsq7V7iBLNEpI!(+7gyHX_{Zcq
zi3$x{mkIrKg~@tJYy?|ME_m)c;FFophbHKbCrz1(6#kuRKKAg6@~Rh*u@p8U&B$Xk
zxRnlhL2bgCGCa6n?1bq+Z-CE;%!s-72hU5wHAkb<3jnv3N6At>KH*qe<i0set%>eO
zs{I5+xeTu~+gl0AU#K353|4vlHZBz&qE}gp_Ab2K#(Ue(qHHkT;)j~7-%t3lCiXWy
z2=K!FcAMJ?g+s^WD2;U*3zLw#c8zxNi2dIx)MI|>05!&wt;!}hwEG{n8~%<oT^Tiw
z!<R~|gGGO%Ex(glfwU)cs(TZG4?}LfXn<QbNUKLu#XW`kgOP;0dV7C=shU`$x^Qs-
z8^X}g=fk1ovDLpmv?8akipf&w?e(++C}4+<n0jN~sLjvsdW`|Ztepr3q0-V7ZyZKg
zf^8XIt+D>^`dW6zo91fGi^Y9{M4WYPA$9!&1z*%sVxI)9FD7?`!wy%o5mjPPG8;jA
zYhC~Vhk16LVRFU-6hAb$HhEJDwx(^L^j9ryY8wq6T$MZj4`2>2p+<;?4~+UzhG>;7
znlGl1w;@g1s{aH0HJN{;7VGtp`9yq;7*W%ARn;2n0|`f_X@8!N-@RR+Jl?Z>zR|H=
zZ?jUb+O+Q)w;So*UY|NWPalo-PBA=xdQ~z&`RHI58o%FRXyOw1!(w5*f-WeoN2>v2
zf@V8*zJkW8o<bBM(6i2wauUl_s^zj_f#^?p_m%O)i&)dp*;hgrr_1ixyzkZq35oj>
z7d1u_SE+p%d%)G2)^qx46^+Z2x9-6>KBiUBn_~Km=J7Aml?-IHD-Z%VU7KKcAO>Go
z8pOehaV%sJ#RsFQ&TslGD45%to8vHD{@|c#yXGY5cP|gM%Mx<W3jYV_Y<<Vj<(j@I
zSFIes6I}6w1MA;7&wRiFCZ&z!;kc`~?t%lA0I_>%7TM~eL?*tf^2gX2zjHdSa=L9!
z`j-$_g$Q*B!Wpr$_68<#=5QlR2xfMaZcJK)?1Oa!TwY4?9=A|&O7IocjtXhLkqJw&
z3cIbdQfYCqPwJ$k7(Wsp^H{`1w`ardET4;mC8=ecP*~J_fW01SW8~@dStS1w;p$Cf
z%$a(j_f;J338#Y?qxbooxRqBB&ZNv>tXE-k1m#nrz|ERxqrSR7ZuVku+RB*HQy?)W
z>%n#^CG@T6dp}BVM?ULrm~+kTwoxxdZD2S48c_GzPj8ghx&2DV^!<ahM+p^K1(SH_
zm2RcS8}-DVU1w(f26Wr7kb4cd_Z$}+J~>zpW@R&k{DWmm*=drJSHjCe^8HeM$^P)V
z*dXn2Or16EsjRl3h`S8%!Uk-n+VHkMg{?wv&OpEA(;GMyLx_E|xYTXbljLt-BLP}7
zI&Uck7yQKVshf%-AC$)}_GKKY;*a_La>rS|v#K^?Ujq%QG(h*kbmagu0p4#ymrWf!
zn-Ab&?FrrX7j>5C!ayG6dms^zl~YapDj}pJsiWNK;867~KS2iFmyr$Dnw3FF-#Jni
z9OMiQ3d<~_>lEB>e8qp}zAODwi197_3w}d#yVDV7ifcdX+4Jx1qE8bdTp21jY`Hh;
zG^?r-JAbMU*>zHKRlpyKKGoM)ZGOhqW3`VHbC~#0-;U|dnz$;=ChD{K;9O$hu4eT!
z)D3D9mwR1=jg>Z+h1tC;p*dqadyuu4aW;59rpO>rv|3mFp<DkK;3}ZqhWLWt08&?N
zPWii+IiNC{T-8K!pu{3~X)9qbv4im$rZ$|{HgHiwC_yT0t0KQ)4lyEFX>l*Uazeh2
zTu<XJ&UjiS4spZg1CBwGU2r9hCGW&O%p)bAo#+~mHT*rJelqb?&z_yc=(R*tu<Eph
zI@L5^Pwu(zI!qK9*-33@vv8MuJ=_p0sckQek1YXN8}Lnw2%YP%w2o>RY+qgma-N04
zLza~-0<%d!cJN4DV-I~r5jlLJ2PHzu`ohx=jNNk<#fCPOdyW03pLi(cu+#{X?i=3;
z(W0Fjm>n4m2t8UVrNq%YmBiw3nEGCqWvDk?!1Wsy+uaAVh@$quF)p^@r49zr%(4Nw
zZV5l~B{DT#SZeh1Aw{Y|8?{NRS5>fhU4>lnJTj_sq?moibj>YT?kQ9l-^h$?NYx@%
zS;g2II4ksyg_F7$siGT9u|x~yRamT&D+>HrJ`w2iSdzl@rCBI8@Ue)i+3M3W9y`vk
z``GyWsb<?(doSx{)sHZ{BWp#Pe|f@X+4J{GCCy#mo4TN(V#^l?sIrH#`Cb!{H48TI
zKExst>~Ll4vvdLiHbk`{e7mM)!i5^4vdYp1lQ=7%c#Tfej+RxPmm~tFeOUP0?5}Fs
z-V1{St>$E1bu^O0f#LfHep0`EFXu1&D+XX^0&fwou@gMj?JV-;x=n;?LCJU$y|k>a
zB*(E_HMX_Hy<4PKMm_qxTp6DqoS42F)VFQk)&x}zP6HoPMZ1)jr+p6uH+L|)Jp2A^
zG-w>~=>_6+`I=Bs{&Zf>AP6^jm=8-S*ZtuEIE>QvOA?pHUs3hwRRIroGitjgbbQj#
zQYZ>M9OsV9>D)=0&D|>Jr_cVO5t1?{sZ{XNd^BlIf#=ua{Q$!Cn5CI}GbrFZzOm`z
zugRN(UeaxbzQCFkC0C8XFF9UGLcj6KB*Yl-n&bZFcYcmZ0^9&lvG~TR-enuR&3^NS
zjuI35C#4BJJ!(q1Y}$dGddmY3H@OK$`627>`M27bC|>R>M1XH!EnUo!3Ple%UnwNu
zYCsGjYhA*ozOLr{eysroQ~gO4Up4-?9RyR@;UCkR^eAZ6b&9s&l9H{eok3Ltcl&_t
z6Ot9#C6s0rwr;oJTqg;p@02x`$oLot^%b=1NXRen2|+CzDQ3KF@gG1ad%Y*=fyfn$
zlaNh)jaGGuLAZ-o{F2Us=kw@M+v8H$i~Z)0WMJ`2rpERUiwV>1T5t6`XTLmXCSzZV
z6@!Kq>wl94rH#hN*!-2jI=HEEwVp3-kIy8D#$n<f5*tD8(N&<Bv6CBo$$VUZe<AaA
zCBtXGc&WEdlJy6qGj`BhPvSm0zvKPsLJub_$!Yqe9|`qc5UVIVorSJgI2dcwWY%H1
zo$^E4-@j_~z$R9JSU9)0WSqiHXTztKJHp@el2|HQhaz9{JY!Qo8!7LocbL(#gwekm
z255uBv(tL^c?o@N#MQ_RHc=|e?PjX}bZ?7b9_M--N#Z2ahZq<I?B}w8%vyJVBooY8
z?PJEDSjlsESOby0x;uE^coEY(@LoBnaze_F(=}OSd;>ffy6`42!3!t~Duo%GQ%d%~
zYeK&;<l>plo|A5N{||7I+ta%B=eDqAWt2TR+dkJthuB*EgWn6B4>xhn&gG`vaUB&z
z?e9ZE%)TP`n5H}M{Hk~*XV-|=Kl+IoaRfZ?k#ptOz<u^fqh4#EZF)~v4r@4zHOh94
z{kk_YbgnYOj~Cl94$LwA=x3aTme~p#eD;6o8~}Eb))vu1;i304NTWW<9?gA^q^Ea2
zHiE!pX11kl;ncMIzoU^KU(~yQ$iHl>zG(E6fq&zwuZHi_)cUiI8&;wrv3csv(6ujB
z>MD)n)&ta@!h!z*(j0A@q0-w3mugnSsoh5hp9rtAvYVP5z5j=`w+w3Q3*UBw6qf>_
zCAd2+?ocSjCAdRzclTn2lHyKqmk>NS6xU+GiWhe%UZCyo&Hv1tIbY5knR!2~FPYgh
zJCn(tz1IC)_oXL#uDLQK87&nsqHe^rn#PS1^8Vc#saABF-{5xOUxO*qy_L>D1}G{)
zY@K7Z4O`EAcUmi0hvxoBk(Y(pR1qYM_YJ!O@q{BHe&`)SSMk%84FQMY5=-wO<(dt-
zMnp7^tHFB8xa9S9ORsPv?rKjFH<kocy`DOoVfPdpK^8hB1ex_mFDxcM=tude=g}3{
z{0uZ8clzP#7C@UpJ@;o9S!QKgceL_lPgi*GAz)O_03=8MK#m?+8+uF-<Io$jFdq5!
z6r%W|OS^ueGEW;Vf_H;clh>hdO;PSr22b6zNz}`!%1s(!H+!IF4R-|Zuqyn(2H<%B
zhu^VRqOv9_u7>ZXvl@YA(;9rL1)@dR9^w#wu~YRChoTqEyAg#W`FT<2>KMRnWb(_m
zlWao#X}@&=#QYW1n*4gy+9>BORQrb@AeH*9hPuAa4T*Nl=Ejszh8(H)dlGXutk9F;
z>Yq;suxS9HzQy*(AMu*}lS-3!$9gu8J7VJ#$g#b&yQ+-1B&lj%u2pZ(s09K8b-I^z
z&biIn|MQeH;{;gKF7lBvc*j%@dEQp7U0Mr~Po94cKUvq06a&8kOE>xnp87EGWAI90
zIo;=$nH(>{Na@EYSnCWO#}b!`zIC%@GNs+YkepTA3a^*S<EMS;GAx{-e+!ZmdSz}%
z+7$?8cZf+RdungT9wwv>!Uj5?!NlsGOzWFtQ%oT%Og;9DDLMXCr?d>oU-}c*3m`vG
z6)QR0Hi}!K<81NQ0%kmQ`2=Vm0x;@Tx>EpvQF07{bD!TowHg7V6r;u+G@W(4e4Di|
z2Jy5KmG_Wn<N%6u4U9CEcBw`=UOfp^Rh=Us`@YnXt@6-_G8W>qA+pCG$9zk@ED*SB
zGC8_tNt`Ke@8(EwVOzj%;FDM-HD&cNpi8Yq|Hq~ywPnyj2bwj^$-Q^S5wF>cs@!2M
zzzlexK9d-*3l*fuGUxx+X{Rb0FC*eR?JQ)u<jdi&a!t<myO4ZYwzQw(kt7rxviQ4J
z3rw$xP2;|;*3_L4PUN@qKipaX@H|0r!Ct7l^#prkSR)0%-VU1mG1C5sjnPoOi_nzN
z+oq`Gj7Vf}CyxeD?-cIi<)#d?pN=1HhBIErILT{-rJs4uYEp1n{M1R@VM{`jm!QUT
zN)8x%r{ceVS6700yamB#%|h{pd^kZj%7sokqfT<e0M@{#`-;M@nL`apsI$$U_k0hp
z9Z>@sHe}CseoM2RucX@Y$Fg-zF}q1A(W0CZLe8@z4%0i_DLcMh^5wqVWPoPDSa%qr
zy7IS^6yHbJK`|GSLgS;xBTnIm^C{-O1B7Ts*$>_P2?aufuY;W~CpMWhQ>V~xHQtP=
zem}jF;Jgz|&HmHU+UjBi!-nuP1eg<ZpqJuY3Rax2td)!_UD19jMsY$lz84?Lg~&Q+
zr8wOGmtlqzoQEA(ipxbC&_}yCP5r!VvJ>#DY>#C9pU`+K?j7?I_Z*o~7t42f@OKJ>
zn&Wup#<lp*yMLU=OZzNGxaMy;{0+~j^X!Fc{TPFDp7tbuN+!!5aYeXXy2N`q&j}em
z4E+s7tC!BUGQhMx7`A8D{*ffwH|+C|^2;cjWfw}gvig?)Jy_NZE497*V>Yo<r&YnI
zzmGSzH?l*@P4{yk{j%<P?+d1i&6xH}(gAa(M85HRn9YX+=KPJMnNf*Qn98WpGfRg&
z0rS6KmxkT(!9nw%?Y-X*J?N}Y%y1`q&nX{qzN`@^Mp@BNtsSH%=r#oanj@867F4nD
z_!9eUGv7}G*l&};m&dKu+|{wvdrKnGK0<9;-u&$Ld-hdzU0Ms;tAsgXbUAS059SAM
zT>&X0R+uS?y?2L{wMT4^flQIkI%Z3G7l!3DflR4f>Hh00c5Lf+wQD?hV5z_gvQrf$
zNxJDY)NDD$_IUX)W8TwzEcjFj>mW*lUMpVP#j=2%=lZ9A#dQG1o?jVT0iThS%KNKA
zCkk|q*n)JzA^&pA_2&WzI~?=>HLChQqpVn{F`o>MqXe=*o=ydmqT=uW2)T$=*g-%X
zW3?N3AdbLo*@%N6tz&pcSxHp<EPY8b6qPW^v(QwbIUFk^qvp#2ZyZYNfgMFw_Kcay
zP(lE0i(e@!sd_&LmGNK)4P(3(D~;E-M_{ie<0B&-JIbd~*DD68yrTpdbFfQlqR$et
zdZJ*mH#{Iz&}H|Pz;tdIm5uopy_iBrg<HnNDk|(~@-#=s@)*SBZ`6e&WK2E9&XpAc
zie_IEr5D|oZV6@=VQZ-$E2?0L`jn0K08k{_PuwZYo#ek94uJ7eu`)q>2*8iMj2czR
z2=JwzQw%~;X#Yc^{qI|H$OcL4u+>ko_C6px3iP%am7D(naS!|n((Lq!MtnEY!($km
zX&9sRb(98=(}o4kZ=7BK6e8=<4th<`nX244^*`gCzwkUa0<~CkYmKf61(6ciW^z+g
zduj;Jaruef*0l|6Qh(L#h(SI1H(zeYdl7bx?ke&OjDGxCh#v4sbFO5;9_w!3l+XJC
z><K|GNK+g`ww&f@)upcjwd?%SOn#aF4jx>hH8ptE`YTZdMx^dd`E58sc<JL?jiht)
z!~KK$RCZW_|BeH~Ik=i}3G}rRqky<a_m|+(%K#(@flDenC&J*}?<5J{`3euax^S~p
zO8fn~$MQHRbg8WhUxK}D!b6#jD)clrbAFb%-1igN@v27NGV6}8YsUv{7T9a$G@~n>
z!BF2;<cJ6{wNv-_-Hg-l?7!DwoJdzy&6~*N5p-Ogr{!{b$SQNZYXZ=MD6(^QR0%gB
zGF(FxySTov+ZL3hpF7=bsC$ReSg*4v8ERc}a&5Q)<0l}`z>=A<HdowrCndBtO4-J<
z!bp8#ZDM$&Ds~#@6Uel})4I}lJ=XJ1<&agq?B^YfzcYtu>2g+^pI-gP;byaPvX<4a
z{0Yz7nkGIU%T#_oV~t71pSzHm92^(oE`yg6mxO=xzRmd*o;~L(y(vl%t{#~;)rVC}
zR|m4pmw9Gct!Y~5IqWzRamw0vUFsL<lfK+s<YdeHP0rgK?@Lo-gZN-}#2aKU#1lcB
zt`&Cg<ZzHdL=rRjhuN;gV!yHNsv5u$h)Fr#NSx~D*^q}9>jn_~iFU4mL#&|@>hy+R
z(C%Y4!84^}j;alTNV$rVmbS^7yhQ$m@-1t%6F=~yxNOAyC9zY7r0_9`O{Zz1-#hGI
zRTsOjYTzJL+*2^$;qr|Umaa}3*etWZo0X)ddDD%wu~p~oB*&y1fW~6O0d6Y};;5Ng
zsx=8)D9Z)&;dKp~X-K(WK{VysFXka9q!Fq+cZ&UmTq9aig_AqUQPz_})s|};z3L73
z7k`dFjzZ;q2OFNt^*zSO3X|aOtX1L=q&lrZx$XCVCMly!72;pc%edZtkFTw47aXT2
z9k6DKxvf(e)l6Nr3K_u*mC#=gLiERrE5%biPpWs3S;2?%mR_@DfJ)d7q|<M_ASa+0
zDF;_O11yn5ez8O7c&6D*28Grt)Wu$*LB?_@^OTeKd7w!l*OTzpmdQ8Hgo{3G^R_i8
zHa%OivfOFdAGlt;TSsg>p~v#NT2a-4aJcG**U+B{s=8)&+6<^Zlh<xq=q~%Q=X$2@
zz%%DoMslwA+LK~;;NBIZDy5A!{Qi$)Cu`SE68;7vp|y&q=pUU_Q*@Y6?RAszEmg$1
zVdstFCtT%l1+8n|GpAjhl+QCVOTI8Ooq>y|3^;s$ChMUTFU(!boP_h-k24pT_xTov
zDokjJbtzYQFiqqndp`fp8|rD|&8np<K^uDwr{MnHdg#u)aBu7jKeOQ{_q`CO>>wZ+
z=2euio|#Gn?{7BcVp(M4wXp#QN=4yQA5~*;hL%?2{rMV?m{uo$>(iTN>;ZzI#RQy+
zPOsepr<B$_6MoJs?ZWwzloqq1W)Nzr=@YauH866QgpFXl*+gIln$^UXincYA0-q9v
zHTF`WP@f+C-_`hdnjQ~Nt+B3UiqW8%Y8E?72GOzma(TQp2o}a~@A&ylvd)4=l5=CU
z#!BH_dNi}*w4x1Tco`p~;$Zb*kcjaC<99_bf|OMR!}8_){<T(C#oP#|3s$Mo>Kfrc
zL#BmABX?_2RofMYUD2K9dSB&3i+X_ihPr7()I;!whDm{=Mo7)Jm5bW%E&5L(Rwb@;
zZAds1#a3}Yj0@8M8<Ur<y-rc0t1&$)FfQ-5=HbnbB)RAvI)X|gz{FD&dtrf8=4f;h
zy7@uM+P)IIiXxhn7kl^p<6L|dbEtrcd%5a9sMNGhU_S;#r&7|?x>KMF!L}!#&7Whz
z%IN_-;l($y^*Y@yS&kev7Rn9lry_MR8+I2o8R<lruv1Rex0EJyy*MSI+*lbsvzS<;
zLPb^a#c2e@o`$0K<Zeq^Zn5zHIk;TVX#96>z}k>cD?CZ$U4ZZlm2b1oL)C@Y+_c22
zyOi4S@2EBX$|F&l>`)TYrr6`@QP>LV#R)+VB<C?C*u`BB<-Ge`mZtIfH3L`>PCJY5
zb62TwU9-cX7H~mGBqt~o%s`yFOM}x_Yeb?vEv}#5b~A|<V?c_r4w><eq2DFvL#xi9
zCVFAmn)c9cnRi=dfSsaK28l}UD2By%lH*d0NFCc7F1_2dI4sw?`R4*7IfvGBiSV@l
z^C<<lBiRCz+c0|g_EtOa#O|sr{RQ6arWmkt2nKt$t?Qk=;&|N7qH+XcoNF~v{D?oK
z8D{*o;S`=Dt1yVyjEQp{wZ4EQ%oj7_t>5zZpB-P~<GYCpV>C+;2F|Y+4ss0fzXTwC
zU3RLO5=lZV`MYal^?Yw%H<VjarK&NjS=iMehAb>l3LZ1_2nyl<0Q_y5gXHp+j?`%_
zp`4~4e1u)nK2!8diB(-pbqfS~b%4$|>rxX0bCo63-*j1Bt;c!c9HEsJ)$wJ0wX-IC
zy>-Xftl~w)sa|&)&X>58SKY|}=Xvpr?<=jMQ`*^SQg+mB87apu=0dKr>CNvsk46Q3
zoHc_;4#uALSOykRskog&AL49WZGm-N4$Ah!cL~Oe1UW2T|LlH#tY;DmJJl)pM?yZ_
z)3_>aL@wM=`?pK+wn&1m{FRL4d!-ZhRoKEovA^fmI~Duv$~wm%_%G&L-{Hx!idNy%
z_tQAyx^;WYTo~TONr@F3!fgKX={?XHYYx3Nod<aqk^UJ|LLFTv7fZJs?bB_dN(`ym
z1Y<q~f`e*C38M_q^A6EVGD)dCFlbwbCjNNJx={LUnQAplsq-sfW9q~Z(wehlpnnbD
z;hQlQK@ZXv!M{|2P@O7aTQio}96}21(8kNIy9#2GNnqzkoU-&x5lVCW4G1zUohd%j
z4vT;(!HLo8D%AaGsWZk3?9`6hdZNA(q~SFFMo&+~u7&&Za|wUbp3l03c3Q)P{6|lH
z3d<3W0mgu7PSpy#?1^ulv6#9HahEc2@P$#2gaglYyw&bZW$wh8izU2P3Q`p0l%724
zq$|p{*<A2IGSy7|XB1j6;?8<4%oK?d;+Z13wRa7iO{(PRMMvJjjhAm#UHNTZJ;saZ
zajT1I@LZEy`|&q1c6!0J%OPqMF?gW@rWx?_*<?28$eZ|*w%u=$_#U}5GjK1J{J1@C
zb!VW~f!6g?q9adPE5?Js+u19l)Gaq_$_Ble4LAi4eS0)aLHH_9PazZ9<Z3N{QIv?$
zzW;5d&L~s)694_@EXjj9b0d~seHJSORxUH2SrG^=kx+D?&so-*cEOf_xC3rt;_#=L
ztT2rl-O>JKKhVn^)fht=QIQa%)fk0@8-dp6=Kp+^_$>b@J9gMnYLqnPYw&(-5JM=*
zlZjj(kg1dG>>(+hm<p#3SHa$MNDs`2Jg{w{v$6I2Krie;=#t}tV8x|aVf3ZpO3BrE
zspfC{MZ#~VQrXVlq>4rNPG?=8A2lwocJyZcEH%*OkWg=2Utx{?I8P_nur+m2dzX-P
zvlL;|_1b;IrXpa<LxYGLmL~L_g)ZzW@sWJ!#0?(GI?6&Udu;Y%Pn9!!J;RP-?1VF&
z_BGT(;~*u89v#cMjc6BV<4d2Oy{|lhDz*Nq1F{S)p9oy8_9WKQY1lfJl=o*;2w4SY
zQ2jFma8^N>=asnZGta)YPWsLp8Eqe>_i7_5q!g7eoxHu{$O%c;YVn`4QW^>w6}xbJ
z?-dN$XOdjnBW`YvTF2{g_U1WzLrVgp28gE^&6}%9?}i}km3kxWt}n`L#U4G4Ro-SE
zI~jADMkm_E|6I)FF?Lq$_qwuY0Xxlg&hfa*sp6lf-*Rj=G9wZA_Cv|k_Lq>by~S)n
zzgG`_{&78QI2()Y<(;i<1skabT1Ss{s?YqVjwyx$L_ca20^71z-&1%P2u1TgZStd^
zZ<MTk*JD-23Ru(pLU8ERJFkUh6;ue9lBK>lT<v=KId$0bU5`J{87DQpB#Y^%ma$S%
zPHb<z6>uffQvRri5k*KTMVbGo;AaiKM2FF;DKsy}p?M0s+8Ty`v<}Z)WY>22eHCbe
zMTN$lOJtmpil>?_VIR#~OfeHS_@eYNi<71~tIIK=>S!=b2OY1Jq@`4C)1Q>3m@%(G
z;~Kk5waWWR(AUyCW%A)EV0`Q(o|T9i`0LCcYf0tKN7sF(gQ9eN6Nfzp3ogB*5|}JI
zY>{BbaDj+F979)8!!INbaucQGd6_)hgwWh`E6F8<<>i`@)qvYHu1L=B+Ud4~zK4*?
zmV?^0&e28LCuq*d5vb_M{+P|}j{6OhS-cl`S5I;ngXyNK)GIY+I`Bx{a%{+99TU(L
z0zZY?h)1VHrsj_;A246DTetY5=LDn6)3b-&i&97Erf6k+CE{TNdBF;HAs^<fa<hGz
zXfI@JXHJd$O%<fQ2z3=b6voZejgxZP`0WszaluZtr{2IK?`tAw_KB<BWeRtVjB4lV
zY+l0{>CZI_S+7K_1xzACo$A-~392p(E&cSyF52E~WJ|Xk$E4xgTnGKM`*LwcC1GuU
zKddTisU@2bHPu2J?pymPa>3co)W`}S_jhNaW9AID%eH3mzj~arG>o7%474-*X52&F
zYZaL{@7mpd_)%QQXNCc0d~L=qBRz>%`*kHqS9CoW2tUYBMGpWTGY3)u!lh2)V(eXi
z7WN?}`*A_siz*~0uQI;o0!i}d%K5hao-3suYggWs5ss3VR+<S7W@Lb=ZPnG%jMG>d
zsXn{70K$9{m`2&AW;~7S@ko-o?wnxUeBs`#JH!;^P=EST$xUaB*{A|8tAPUnhlGWj
zLgNWOF0%e%<0iA(3F)Ki>ISNll!>BqV}-9l)I`BLJT_*vUF|epPT*FPflo{JM_dKC
z6$B+ZF40P#L*-2jq6ZOrZIm%5JDb~RFCu7HYU0;`4Pmd_;pZM5I$CYH0Ui;%w^B~a
zv4S*m29AYl2-mS69?Z6XIVtX9iOBVoB==!0zutX0YYG0E<F^0mY?^|ens?ZDc0cSa
zdfz(hTl=EqyAZ2|T65NEjCbI^Mdt)Js{SZuh%RcNVW;zBoVh^kPy-^N+lh&Y7}_oY
zo57}T{Bx`u?_PA_#!RBJqFK<r7`;ZTV>x4vQtZYAlE`Q%BJ&AvYI7IE-JSaT`SO9U
zuBQY&<XcqE$mNLcR#ks3o0^b$OP4xQOZbZde!b(|m3#+NbN{LAR{Hhu1+&A0_p#Z`
z7fCtT-!C#*b6|`;UJ`5C4QIpmz~h@qFDkqG=yOS61HL0ttS)Zkv5zGQVe$KB!2QMQ
zy2DYENgEc<a>hfQEn7b1b0<l|zmw&P-*m&7OZt<JpE8r_?utH%ZzeM4o3S{@ZL+@p
z{O_e4%<*c&DJvD1!i}Vo%2`qKw{qpNpVvfYllkXEbTjxr@+1Gm<$J43h0X+9u5=48
zxar<MiH<pI;Z24XEQRNKG)xjR^C_SA+R~xj=v&(DG3<ZZ<w79Ac(oITdj@j53eRp`
zti{eYS8F7xQ^Vd9>&rAsE19yA6>qcR=N#?*!?s<Mg~962ffeQo!%Z(JeU^nEICx+r
zlJ*{G$|WS)epYq|g%!VZm8_Xt4Y=G3vt5}D^z5rv&Ht1~eitvLCQ;AY$!v$37^^$J
zy3P|*|5jWtRB&*j+TmvWzG-Z&36=MY{|@Ld=T<ho!#^5WYef@1k`LTpuv2}+czfjw
zd)3R?^KnCC*O6i!JE-|k@Wd9cPU5G&*4NJ$TFQzW2?nSLliAQDC#2hL(uUTl)HXLj
zf%f*ej`=0fdKsA>>)~qUsC%JL)nlG-mzC92)6e8G?Exk)kmVZ4!&{oolgsq->Y#G6
z*~u7pnd@u}R?3QKzhi8w15R`q+O=H1EeIjXzJ&6;p-%v>dT0cg-=$U!<$NEnG{c_w
zFkM+7p*>nju{Zg48a2p%;{Jy5W!N^~8r;rgq-pF!LOgBG374{72E;hsrm?q2CNpzJ
z#69z?MCeD2u>#y}j1F_Iw)wX$r|i5mt}Ebr<Bt1w#Eayz62mF)$yeK@#{R<lv-`I&
zgh-#6+BVJ+v5xjhXT1LF$$Mez>-`9!+<Ft%EP5MmSvP*EM0G2~<hxCsVLzQbXeYnJ
ziPaL15XGM!eGqg1K)44dKAazy(Z2b8%6|a78|dNBZo{(4&>;Q%*7|+aX2RiWd`4wO
zWZ?s!W3vkJuS6^=$lPqpqwC$58$<_)4OuG}NIsDvJEMW6;izTP@co}n0-L!^EvEzw
zm?Up+=$cW%P6iqm9rpJB$Aq+g3w(37cm6#TmeR9W=iYqKopS_iqs!1zY8vVoKkcin
zo--MH^Y!LM>h^&Vi^u3cW524=NpO4?7>ulpoMLtv8^vf^wr`1k`Ms;s7Mz}!B&SQe
zor9OE5$ar;InqCFfP&P;YLE{4!~SdQ%EyQi=XcIncVuFb+19B2PB!ySotf;Ol4dg4
zi?i47j=Y{X+QGjt-9i^a$_{B_BHPS8e8~$y&!(U?+)1-w-@93@H(4nw4D53osA6*S
zK<{Ato2G9SGFB+upJ#(~yv5KU6cah~U+XF+@3GwOvX3*9JT{Tc`^8oLYhcY3rGY2u
z`$wj_!=tjM9$sF<mbY#}tpnXp_%Y8rgf$ze9x>ys5_C0+Y&3q_QI;G`*t~P2sxG%6
zn!6>Bb~Z~qfWVac$^8ZVu*r`*39Fjs$XiQ#rvs<CqGxLhuJ1hOmr?)lxyM)IIHqpu
zl~`TJa9n;+X?M6_KX|eu6oz-Mx*B^y<!-zL?dLhq-?e|6cy5#{vN{%(keBF?OUd~8
zLna1YfbXb^AsIs&f+zgr8=Dc&X%0Q+7;v^_u*DL0i);&bL3$d;E+ixzmly4>%%uTT
zWzA&zXuVWo8B?8vUMhJ{PA?)xx2+)0W|?@~^LGjZ?R<(IB%S`Y97A+Z6C?b|s@C|1
ze+TAUeg2qiU#=_7Xw)9dB)B`z23MpCDHURWZm*l?rD4aQVF%#(q4;@rrgG|kf;sg6
z0TKYBlmUBq7SA0!dBni*I<y;3-$VEZ?*qST&7ZeL#V6f=gBHB<LY>~PDR}GkZ}Bh~
zrV93LsGPRnR;OF&7<wYBajHG9VfM%jX}za#N4M9U6MUIET8Rcp7Z4fIn3RRLZ2l^<
z0eal`8H4tzPBhXRW!W9i#Z6Mf4x77Y-^H~t(1)-(Tzm-4DA+8X^s(}aOnHxIoHnNw
zUN@A5f1ch%6tFz&O%H*zmBea#=@*yP+iVs7KHIx-ej@H?Z+iZabHgmraR@160^?GD
z;=`aZ?g+KI*wwUlx8oxsp6LR?pC9qx46zaR*WMuv8CSxI#35<~TqrhrK11eXhm_My
zCNPZLOH+yy9S77`TV~94eqRk3MNO=wiL$Mhws%BMfev%X75#(&YPtnLyOM$n{101_
zag<LT!(RUXcr)!C1gi*QMYsL~EY)roZ=N7=>kqS}RLGDKP-s%3)%!Wa4@eO(Uo2or
zu+nUq`S0miL#uGah}7@8%t6^!M8DFn$yq+QA?hfL;!icf9*-pR*YDqv-%OvE&g;?$
z@M;?CX<C;C2Ey$ziGu<(i2>T^sYW$<5s*e|dSbUlUJ8(wh76}0A1OWYMmb4%kj}9|
z9p4myo*FqHj_FUXf2rBjloUEVz$$@Kv>E<k2c$su-6ef3iL{ZdInQLsj^}T$P9D}u
z+x{Z&SEeM;j?&CbRukscDTxXNtQzi!DUbDCw2byFM`;m5Gy;YT8g6VU-%cw$jfHzj
z<RZ`fY0Et!e(1xaNp%PR0g{5>$NhL1)^Gl{=>B$BV*QO*-wk9XYViJw<hgkC)VNij
z16U>NQqPu%&|J@SHLOlt#FmnHS}dN2Lg+I2mda*?kV@^RQw-;d#=JqhP@A~rtD=G^
zAjxPChuEbI;h*ZdAr3K=g2*H_w1<=Gi@w7zFzrY<KSDu=f?*`cLQkEcS;9V^sO9ur
ziX>+_u>Z)o2wBQ{AP>S@lR1DD(SXFTAu;-EeW>D)%7}T<OEu55R1SJxgjTZX2(fX0
zci>e0(*UeMAqaAe5TpwH$xcrfw0DQ=Nfj~6QPB^&zi;FJ$i(QGXG0s=mCo79j?dw1
zE+cf1YNo`TK(eCRS#2v?_n_ALp;1AM`H;2Rg@Z@!E$N$Qe>#r!ZyBEPydH`|8>d%x
z>#YLeE2su8k|v6)v0dnd{HTQ{dLC+zI43E%b}kT(qlxv-_+|*RP~|d&@wpiAr<){x
zspTJ;7*xE(%>dQ3=$3JKW74*|N6kC)@z^}2nx5$ZyHd+E{|qO(^S!_CBbgAtynK#l
zvEJIekl*5;uBv4w=7;jOsPD;GL}Zf5?Qp@E)de(H{7g0;rdH1nK4juwY!Y13>fWCZ
zdq16-6sP-+4VyqNB%HzG+rPj}tf(VD9QWihro_EpggTZ$PyAGI>r;(exIU6nL97s4
zY8fHwh$nsfGyci1s?kmpK$o2~(iw{Jfgo&!Ke_bc5bhZ8sedxyz%jiEBLf8hZY{X>
z4iy7kDgLON)ykoay_%}*aY+)5ZGhW4d;MiQKZk(^_e%`uSIw?5Tf!%Oi@`tNJ07ZC
z91V*Fli0Szq%&xjW=LAG5l%TIs9L;{Qpfp)Fy9wIOgGPH_lZ1)^lMT$)#uY>sp<r;
z@`j3VCRIm@TiPB^xndb$V$fYh4>B!2v&uMhD$iT{#~l4TzM{l#h<#3EKpFqlspbUm
z5FuC)q%GJn3JB#uo7uc8w@k!L6@?|s_#J|V<uS#~{#b9unTBgxBssN2hYrfK29^rO
z@ce(TN!$#7c{|J^p1X<Sw#tg$BekFcGSQ{Lmh>SW7NGT2k!+$P&M?gs^(>l#r#ukg
zSALL&c<TgEF;<aI2ZW`QZAP6dZ-xUk3F$>oRSRwbK1E1-L7fKt<^KTnvSlS-0hJMo
z#^4Ev%v%+4ZF`8ow5JUAw(4q{AejvQqjr?~46w%m&C7v?gOL5c2ov)kuy-N<2ne{i
z&9B0W7%#Fc2zB&^%E=bJphh8Z<uu1HhH2POHzT0z6#hGj3tFq;cmjznS_KP$o}){7
z7F0@?3c(Uj)|#D@!3N@iCo;oPhPJVT#1?>;qwGOy{FMxzSh*Aj&J;=zf&ug?EvKgt
zYyoI(LjJEh%>TQJ%>O^1RW#N6VoL>7YROQvZN8op;s{xTOTYePYSn!3J9K+RcFk^%
zkH$LXv#%)7LX(Sv(m%?Fh9_#!l1holfAWTIsWtv(i!CMl1T9_$MRoWv185lFVJ`HG
zJf_@|XAz1Y91UWSKK{cs;LcqRQ816s^F942|9f!gI>2wyhzI$Rmn1X9^$%CyUB2yI
z!h7Yt2&S#S{Yxbk19teeiO(N}KB;~yRPKKLY6!OLzBvlS9N($>Udz0DD>OOf1vWtZ
z9t@>M=Qx`s31=pRt~LEeV74Bf>#H&yQdxiMdAu?QVupwALSQ`o`j1^f&^g`Y>E}^%
zhI!xIip=R%r7{c5@P@uRER!sP3F66Pl?OsLiD^E){N}s6a@cx`v6^u3V#6sn{lf(p
zU!kNo)G=exgHZc@qhuW#)6LX-QF2hS+v8W#P&A=N%k5Ba-FXxo%FRu1|1;SmP+Lk~
zf@s7`WpZ>^hdClvY^K5qR+geRHw8+RXXY2tlJ!}+p{D&&Syk)A$SUHBshhMPXg$g1
z@8QgLUe)OGywLA)DDlyiH5YxYQD+S}lAcjhVU!bduk%}z&e_W;5Rjd<c8$=N<12Jg
zWlj`Zg{A3Z{-C}xE}&etp8fMa%e#*ik&KzaH!US^91eOm)|wD+IH~287n$&}%(R#Y
zUjAkh@OrRU07IM0o0@+_vMCA>{2$=y6mpd`&=Dd@87$H4?GpGR5ic~<$&`{NQAf6A
z?oLjs7anwfVHoIAiC%R=sfWlvYcSaeEfJCwBX?TUh)-xHpuSj#&o20L>`%xE2R@IK
zkI8e~22hf*AjY_{IX9;4wv$5!G4=CKfEU=Cr7Uz={en9e7~EwsVvBj<pL)gXk)1S(
zBO(t__xsS{o%PX_mWF;n@G_gIeA<JJ^{E;acoPI`pt3tBFrv>}a@~WRC%@ol#c4m{
zu;I%PJJp)Bpa*~JgR2@0>{itdr(k@#t1&!W^<r;`bLZJt#xH%@n_(_BS}#;&o47;G
z1^7|pAS_{XP$)y!;?pO%e?#`y<YkaunXbZ-=UpXEpE-rTi+yc~$ebkC&Ib3&)`!y?
z#y?Ztk)fkbr8`MDPSURzkT_pe9T|qSzkw^4ItnoYY6B!pMUq_azu2M~V#Itb4}R4H
zH~xJ&5VQNC@S!1pimW1VbVI1tad^~168dlFpwFcv%4s)FLZ53QOQKb&?r;m*{Zxzc
zeH;wa=s_g4Md(avGtz=zB#gk_rm%nT<c9|`N`yb`l<2zMVkUkY@RufP3ZyfNk?+z<
zK-T>Xi);)relojgfN!sPU9~?BRD<f0w0{R49D8mWI;EWWjdqgsyfb%N%HOUhJ?ga7
zoliaaPEcEgLGs%dPTG3Z9Mhm|?V2icCGuc`Z1JUG<(mA&|B^AA2=~-jV9m7U%#Pb+
zo?>)cOW8Sk^ZR7PTDd)|?4)eDy1R$DV;e?4cDX9dNbcV1s^qmEN;&0sVj9u`s_p6^
zPBo-;(lZD~`x-7`@kE)*OKoujiAD2{>c4{tleDCgO{1L}H$tH<W0{xK4UuDEI*E(s
zGDvBFh0?J>j+zvp|59^o2%{xr1NQ0;Ln;~eGFbbw6qY)7f|y-k5yy<_0hG#5{PPU6
zU!@(xePeeUm7azoa}Zv^(_94UTZ|qb%FyD1aWj?#$n9>A95azu>gagw`o?(2^Z*3)
z$}zi;8!N;2d;ak2SWfaCwZ($V509VrGzlMhCttBTcSXm$`haKz%mn?8fif@fZ)=^U
zbU!G#E@RY<3_FGPf~<K!?xh5jht=O#lu{~USg6uGpBC{GbccS&kp!Nu>%M-?^7~lt
zJ-YXJ@dw<`lVf`mXDj~!9Oh}qnHe%=N1bH&`YNmO$A9W4H(7Pit(fJZF^3Z?2zd-$
z4Pbm9A{tth$bI<C=f*o)T_dNN(gcc=zH5!nqCK}}JE#cl;n$0>aF*KJNcC`H<qWM-
z!fys+7W!Dh&b4La9_M%B;sg2irR3F#S9D|8*J9s;RRGaLeja$xq=z1Ub@Noit<Ncj
z59mdyOp6*XFgX9_+x!PG;U5Vmo8mhQ-?t@A(yjip{N>`&C={n+#^*+4{2EoDtL<X7
z8Xm9J^o}x97f<w{y4IaJVtgDMZZ>Z5f)CdrRoR0KZT4=;#mwkKYjBB7ofy5Y-^&-8
zgY|HpaT~Sjz0ec=c8Zg_=}~MU^MLaAs>A~=%qc*3xyWE$9^alY_v|pA5iPR~j+4ao
zpU~u*W}i`nd0Tr6y*xjEueAOQ(A3Ti$Hl+=`s-Uw>|!{`rLCQ>fU_*T)a571`&4Vr
zXue)BT+K{_DCkLZjE?YFePm7zGo)i$gQJ8O%v$~)Faun+(2yAhn6$3SyjNVRtz&Y-
zB66lznG>}L(vSBZWR|%c^e4~%&<Cp`nCJ;jkkEKTB)l(ssefOVy^cXFr_Z2d4Jg8p
z>e9VAwj>>QNE<}N;9hW%!&gBnqW!czrvajDOwbqy>vU2t^$+%z<SupQ!del>(4%d>
zlUMT0bRuqdlS&oBYly}*a#+d4@cp?(Wyc-d8b*S#Vk*b6f@58fUCC4CZ%8J`D0-wA
zw3W(YRmtRWTdoYC`gm{)$M*i3Pl@#UY^JE82u%6j)gQ8S-^`HXS6cE+n_cH_b$E%P
z>XlL{_{kxP9r$clEnA`L`(`LWs}U&|zc4%9ST~@Om;*Fjk!O5GhAkZnEcM~f-)Olf
z!?9bX`Wv%OC`@m2<oFe9FzHlg12hJ+VoA}-`{!#^icwrmYj!)R4w!APBsoSVblet2
zN~ib9Chn9m?M-t;LA-rVWkwEv=+>-dmg1*C)iMr}FH|$Jqf+$AGnP?Bp*MQzk(>@D
z?vm7=QEDY18NyMyQ!P(uM<~%uPS}A{CUT=0`k^tD*HM_%d#TJYQA%CR%H33lahF^K
z4VtVNajAfWh@GMiL#Qo~G{gNmdG@E^n?6&tsrR<lr|Qh8DX3&M+^2cw^q&bOIT<r@
zDh2^R=Vd-<IG$jK=zQ?CqvC>PuBK$rti-$^EN>rMY`r};_Jbl2EhhTkmDylERfX@{
zb-7ve-FB(NeDjWGduco`bsWCGah$9f_FA)Vh-Ugk>PxN=pvKHAQR?0~P`uGaad@on
zTGEAK5#C~7^9^`znQ^0Ed+|X-tB-Tz7<rtEkqwpp6y2us<;QxxGzwkAqsgYJ{OqeP
z#3KBFQ!Np?w3fe6Al&kP+;g^?F2V8$CTN_|orK|PE?`C%Z>-puu(N8A$n`ZVvo%Wb
zZTZTSAP@f#C~%K*G2Y}$(=}(ZIGO$}{b{j8^rMH;Zn+n!so>ZBj7ic!^j1%=WC6_<
ztld~Fp+jGHqpdXt-AsA0e?O-@m+o%_u<&Fqq4RBs0t1}aI0}Z1!yM8&!U-F8!J>19
zA-l7bV{tB)*39;k$%)?j2{lIY-zGN)n{EuV1VH(D72j{szes$U58fu;u#hPh%1?OU
z=X#koWA32K|F>_r<_ye%9NwX_WeRaCT{QXQtg@xqkmjG_-I)6uXV|Ot$tSgeKx1jw
zfqGfTal5T8!Zs9AT9|ErSHx|<ZX~fO*cUG%ijqNXF4@IbKUY3?FJ$p6=-_Sn!G<MC
z$M?s*X5U%ILq=TFzj_>}?8O<SBq``jy^L_?qEDBWDBxhBReE866Cow9t;gz{OtTRu
zG%0$+DqzpS%kcP6wPF|7jGyrUTnn`J5^k6&t}e@Uc*lX7pNi%8Lr<6l3%KX>T7KYF
z=a%oc(^~VD_2x_Yf^oAGy`ZK=F-q0WOnJ*O?`oF(Ln(DEFrH0R?9}L~7_uY<XWvSU
zY2|je3{(nO$-XLBv^Ho!bVbwgfR+=*m*zfaGev6?e?%s?j!gXBUPt9OX{&8BBzVCK
zpu1D!3kQ=}op$9^83QjLiawzQ<KHC%S1)?b6gZ^7^#6p0Yl9P%_lhtmrtHNvGmk*a
zW+vI6g7H)HyRM8Lh|-2u5^zUNy_{&+jGsAPJ<tiNkA!js?MUb&Hb~jm1=38r>++&K
z%RQ52cGATo0mi92!bT>K^RKWl!uFpG9QgJ9*5Y+7Y{O60Q(Z>^)K5|BNgghD6^tjc
z3@0_x6{P`@jfaI!b`NgS?gLTXhx<%G92xYyodSDK-aM4B$$u0BE+|5C)F^Wk?UL#h
zyufP7v@k4EIrXUL`BF!nA&C>L;h-rn#o4-8AvU%PDPp#u01&;Sv@{}14yaP5pN}3^
zz%3bIOVWh05foATz$xkzOA1VDyS`j_BAfLXGjKLyA8M{Y%!x?SX{n6aC9Da3n@m>z
z<5cS(D4K?%>#W(>n4h4gXscgw7GHrqDFOm_**2?kKs4!zu~@Y~oapTTu0^#xkXv0-
z1)5BM?xVR<=+h#q4-c3EH<E)t1=VjsQk3c6!c{E{+cNM2-H4?K)s{}WV|QvW`=^~`
zRxHHtsh8Y#fC=>()e6Uke#7{fup3F&_$S?QT0_^%r81m4MlH%eMQz2Gs`pC6y$=c4
zG}Uh|2)G;1A7kO~=QXaf`1U;wsM2+kt0o>Qxrr&=jkL0!I}Wmk-iZzdFPMPJ@JgAV
zmp(IkFs0RxZ6fMR1%)s4Z82#R3@<ST^ZO1;Z<Odl3Y{RyhY2x$X@-U~wA-W@3opef
zVYG419pzAadg4xagmM|r@YJ`7Z@lNLU-Lz@UB8b`etld90_XR=I2iGtzk0+_SrB*B
z;1*OqE*#@2XoOi`%CZM|$lj5!Q1M`HKpsTOiW6RAELG!D-_P_I2K)yI&<hHJLO0iG
zYY4@JfXez5@zW)(3;`~h90@sJ#<{ct8DILbik++JOMJ-`LuJH}{$Bq*WtQQA@v(`&
z8cr<Cx4<oqybDdgzZ_$^i5u;sJ$lhf{GvjrEE99s24rf1SGDyPPSU#c!uwc<#fS0y
z*N1kOkWzQ2k@oiN@fK=gEn`w#Hp@m;5p>wNEt4qeze}m$6b)R4q^95~H@!A;+f%3)
zz2+cxp^gC~WSYuu2<bP*hF&$!f5D)%i_EwqA<l>sA()?Ro$H7j1sluAy4*lgc@jMf
z%{f{zKe+E5LQ|J0HeJThG!@O$$MMnqEUe1g>_51k5Xo~mzqG6Wp>bZ_f^n>+T5LR~
zie>A))c~Um8PN3d0KnYVI?>KeX_v}uo#PK_2X+Sb1U1lO#yA6EqxwCDDuG>1UaH<x
z(t8&?x;X*k_3!ikmbub1tNSj!cPp|7-v=8gmTXkiKf~lXb;Cn;A^S-7GBIxKrIaQ1
zz4howEHrFj0cEbgLrhS@->pAPnMIRz7NLD9sa*NpSBM?CJ?1&nAqA21y)fSau(#km
zsoBJBzY8P;HAdtxfP2q}5(&o&O1~~*HtAZdtH2V;DU1IP@M)=7HmFY|?b=@q)lFq%
z#?C|k2sj_FnpMUfNP~FgKd>8p<p*fOg6H7|M)NGMg<Iim9T<L!+u-EX@CnG^iMPon
z?IKDw&6dM#mfj#*D^*)sMSXt$ccj$&z;sMsM);hG9DAkBo=s@$R79M%IGUH&a^yUF
z*gFeqvew7k#;{A1WL&jqCNqYZlU`UKo2$B|aW0?dfuHHJgGT*oo)j8gEUxX<n}|e#
z$Jvtc26=NFA3aG=JQO(ylH!Aw1W+Up3B^p%YRq_Dm`ulgC2MMe=l-OPpFeY+K7U5v
zs8X2PD3wS%xf>3Prt+irZ~eVY?6DOG$#T$0sB?Z-%pLXPisuob%^itE6N;h{oWq}t
ziBkscK}yOO7N1Qj5|Sn;o`^X8FjblZ1LKkf=(M!(<qLx!iz)IfZp$*?yAcdoEbyBu
zx4%mR>D^7alZUD>Ab#CVSBKp<i~$)Q3+tquVPL$?BgbB<sXgM($zeStf&t$xPA~80
z)vz0(@yR142L%(+Zr+0aqS2W|GjyRGdM_Na&4e8pIOX*qe2JOO$6sG9Hsw#580#IN
zx;7Ch`*(Y(d2O)GA1(FSOL2sf^-?2!_k~5rP*YlgD9y1|qLGOetMYjwSFIW4^x_1)
zBe{Y<YFnGfv-72pLoM(Y_O$M9Bawh?nat*y9DsFneFL`frEnx3cwK<Mqis9&EZ!|v
zEJAdSXN1($rG_e$Ck|I(p8}}fP-qi{1Ei|229^ar$6HICV83WhNd=Qv+d8+dOYrKu
zfhFfyirH<4-nxTK6E+u(KoMe2c9ri|(gU>vn`k>~TNcXQyTh&9$)RPF9kX&S%OtN9
z#>Z<z-#fbQ<8~2={#<xl{XP5~;C6&oqpi$5)u~}p?n>#18zs^4_(Mp89{iT4O~?$5
zt%7eeqX`_;NWc{%3P(A9J|xwUqiDGX0AoXn=YoFgS7)K&CvJX0`z|7NQxTHWhgYxg
zEB{<6lAfQMtHOS)$yJH9ViPV49c7W49Y1NXG^KvbqT0y9zN_ai*sthJHIn1-MpfsX
zYt$lU@s0KFmU4Vj<+9A<qnEXO-Uv;y1TsO;5+i!ur`vzjMT$(UKVO->%Jr^XU;7VG
zHthGY@?!j7Mqa(>N`%ST4%v;HC<+PO&0q6U{7hR3cN%K7|Es3Mj$PX^W!BPcbfE<p
zNSm@HkZ{*dtn3%os9{Zi>4_>ZnCZz{O`X7Oo=?&8OBL4^UGKPXMk10^G(3CP>+7+}
zqnwDduV{Bcb&)cDx3x0m?m?c=Y5A8Xtdp_-0i2`s*+3sHk+}(}G1$~Q`CK9Gqe0{G
zRWkijQy+ediBVJ=?h4^LO{IVM>qTsw#N>}GA6;0mj~Eq<5#03$55!ydFfd8+%{b}I
z00HS`1alA+PQ;F;C?tr@kA~tjN&4@ri~a+c{vY`R+qzsqDO`zHQEmS91)7FAwv;mh
zlsF^U)#HeESX5fhOVpxWke*ZY0=rz2x?UrF`p-gCg{KT7Q~2#w@{eKO_;0{kKS)YE
z)LiB-r%AwXY`O%!FYfJ<1VKxX+ns1Yj~E6-amFc(?^3-_jQl;P`uM{Lr)bR1mv?cV
z5!%wYQtC$YJZ&%cEUb|cl=>cDEC>r)vMdA%6P-N!@K;Oo>|Q--TUZ*_tyN%vW{elQ
zJ5)^qnXO74PJ;CHa!}|(R79b1)NslaPi1OTIEDQcFnL-ZX%wQmlf>J~@KtmMtigq3
z`pCF~e)w*pv0I>A&f1zPqE%t<pp{u7`>m{Q3U{3K&&HaYI$oJmV-~*=Y)f4?EGp3M
zYD@&E*&?MNL;pRxKqDStZ((^^%V@wZzqN=i-}52MIHp4+16``8QS=QFZmo?m9V{SQ
zj>*K3E&p9LHF3~*l2X?qn=%5VK*akRg}8TFmk!!s0aGPV2bZhf=c5Rl6?uFq&P}uk
z(rqw$3rcD~CK){6cTk4G2CPHJ?3<Egr=AtRLFT=VM_bAsVod*2<O38Y12KdlQbKoJ
z*}&6}Lv^A*@}T+{Ce?ROTFFJ142s{#2h9RDFZNd@@TDSpPrn&YJNTaKMVgs*7E?#5
z3`)T2Umj<EeV&ZA&a;$u-#7hxnUqeGnT*m<`PBFokbQZ<pJn&Fo@b*!RS@Bf9-i`6
z^0v~FdhO&N!=h2EyRO?wx#uHta2p1zer2>J5u@zZQMbw?^)htsQ7^(ZS#$>R8Z>G0
zTYv6lU`ia3_sxy*?6D`a(<{kPE?Wz&KTN>?0QC0duSuY-7T%5C$B=v;U4rv|SS0s+
z<SqiB_ww`curjrxKWk-QxmMJat_T@z6!7Y{A}V6W$%Cn2aY4p9G2NO=bu&%6Wr#xb
z%rRczT!Z<a&t^J-Mznno-%aEvPVd&uN=V65ek+dskD!o+A-N!2oxc}|tnxAG+2Mde
z*Ks(0wZ82ecyeh~Z5LV7X@S_OE>pQ>!44EW!O<VnzmTT`233J_Y5>;jd=E)j?Hg)`
zK?OwL_lQ>NHt+D)3S}ggX#zohRIyXDkXCFKi7ykcFheGPdz+_~^M<}l73lxVHG@#K
zXjYIJIp&LBE;{0T4W>S%5m4r}^K0sYfAq)3v@s}X*YyhDOA5L@e~;-pw&fGQ%p%zt
z3j203Pk&Dhop#qQZH%H;<5hVnrS7{)8j=bdSssx(&FknE(csOMxr5i^si5islG%TX
zXc^D{$jSG;{}A?<Gbck!%oYPBxDUM^*^4Y)YX9rCBWgYK5Ky8q0O^oy`-Mv-K!1O#
zNn^b5mehXBoqQZu!%O)fkNMbWy^HE0C<8ulmZ}W$?9<yRGSgV$YZy;bM<i1f8vDM+
zrySMOm*k-7fSaLj?izNhr$mu{n`!qnToq1}hKDr{MOhW*^l&Zv^zai>_FHR>QKy`m
zu(&Fx37&1of)T4&qLU=1AHN_po80(=&gG1uy*<=Qis-y$w9b>ha68rNoHkP2M+I?R
z6}fn&x_a8cFikJc##HP706aKPl(owV%kGD2BK$#k)B8W#_2QVJvbbZzI?uY_z~u}D
za?`u=!&bkd3wLIARhZN)zhE`TCk7!Htb(C(Ld;58C_wbxdc8saeeI6&g`?Q8((6^F
zi08*A9kn_3U1<4uDf|`sT#n}!kY}L&*FnvFso=;*@i>k)2im_U3;~KxFxAZnx?p>(
zbXpFaio?|i(=bmBtkO$l9+5mlg)~GBIjgCK%BTLH7ex`^wgOpbjJ+#^3l*P(s9@4K
zpvn?y<<U_t5TNfc&2cKlPHGnDAgu>LQTnU&t|S})R*{&Cr(_2_2<Ef16)f0=6U?#~
z=>ST5Kt;0vb&66Z>bV6?v}p$^cAB6$87%f=#jy0S7Jz2Jv4Vpn9zd)l?Oi?(fGx<F
z{aoe+U>72;h3aGE5WiAX;YPnLx|#yEguf5`AGaC43`Hp%E1Y;FYAJ0s{YnNau)HEo
zg&2VWq?D2erUNR{M9a%Am0ldHpyX@l5CK%#<6#dv>cZi&k}L!Om~((CbCjo^ML}|W
z4i6=1Kmx5{%xCQ|!Hyz~&CE17Mmd0o=6`s-|D7vQAD19e1Auu@R);;h$u6w#WoWX7
zdXaft(SZQ2XQ)m{KRS88>Im#}0Zip1MzcItK(IE_Zlr)xD%Old3@4Tz27Uc3<rFM=
zNHv~!lTg-U(|SLE+*@PbZpk;;Rd~zqF%NyPiWYG!LWl8&^vAe6>@pWbGM4?<+bCGN
z-+KH{+fD@p^PNDI(7JI5)0O1IrrJre$zhHv2gN=4CR;z4C^S;EEI6qJ?M5x(A!&9`
zvwECpbmoC~@PG_3S~V>%yt)daF8}TxHCyUauXklIkn2ut+_T?XB3Urbc@19bzS<>`
zMg!d+8%!+iG^Th~4x_nqDzlicwZomkIBVd_xcZB?+-z)7g7%Y4r^u@B*Ms8X<O~{T
zLOzbW!8x^*L$HeNBrViXMn!G-w_o1x=kJIq%y`BVw=L8d8^+u}-JF{D?6`6V7!Tit
zqOXcV3U9x9NGls0pI(|9{c0OrTCHgF=k|Zl_xE@?H;!*Db`~0zu@-PM1bv8Y8FzUz
z+*(Xs{W;fd<Uc^fTku4+;J{(dNz-rt;itYpvlf#M;y07M!tanRWIw}uW$t@fBh}&~
z$&zN5^EcF%`6b4RB=}s2wp0v-@L?jv&c1@$Zxs{;FT&@q=m!7V4>Z#uC@Nw>q#wKp
zt&AM~J1fcwKc_ph46XdY9dTNmM%0|}cdnbRZxGl<OzLp^swTYEZtF!@lYi&Qus4@Z
zkN&vWO}67sR5M<E{2j%u6_25YzaVoa1ZJTTb%SQV>uUp|<S1QcO*r0#UgZz8XU`?0
z3qWygGh3sBh(i_#F-_}DpJzjMx9C1gv(qG+{vt$|_=NTQ!QfXdmpiZ|*b4p8>!yWZ
z*S*r%|4WE-?di3O+eh0j+mJHzA9r<}fqvoDtJ%!Cs2_%SsY2TUAGz)(#*o$Ot-EP}
zahVqk{TyApB@mWDgd@r=QyT-GM9pyA={vNh$^e2OVR!#nEpLk>$tN1$nR6zS`&$HS
zf-4BQ-e@SQd`JrZnJRTMBBnv%wjaFsHJYTPQ`mc1a0KBa*}$}vHXcIGT^@QwLM6Nl
z^|6T>5m2*XcXVhNkDI}?Kqhw21C<%CqV9mjDjq|2W%56g51F9MoC1C0RSYRv7-GQ3
zD2|O}dG%=1&)jS+_R4Nn?a^KdulCt~)eZKUi-QT|h03R5bAa&fCR)X9Q<_Bhr%JJB
zL5NloU*|z=cY9}kS(e+5_rNZ>s(SePm2e|b8(iJfl{gESbY1+9(Xmr8>aA}zEnTa;
zt?(!R7b6DWX^S3ev(HoAsOmKhARBF|`|uat%cPT}c@b>y;1cU)XC%MDL(s5}S7}sf
z0yGo)ACpn8%X9Eh!7JqG>X}V^I8gn?nxOqZz$oPA{LGI$RsHJk$fnmfuu2!tXxty=
z|Hax{M77nw;o1QTv^W&^;$Gaf6xZPH8r)q{JV0=F*WgZRk>Vb-SaFx)McVh|Kl)~8
zoxwLv_DUwnUcdd^&wX7khzZVC2_enx6fx~f;ho5;aRKUO((YNE?y^mXVX4iQFMhJb
zuop>STZ?h*{#(9vcpv?MQD^*JyiWV_opD^-X0NOZvfT3*r@TLDjyu^U#+$5IUSmJn
ztZD5}KA&{7Q6-6V^+A#THHHR7=+Xd{@al}pQ2x!=w&KlpQS+^3E(=#Ck8)1*t0NQi
zg72$!QkSA)+B7!~V9Sc@l=Pn1CJQM2m(aI+36MBu=sQD9hCB@{966IO&s+N!9}g4}
z+S+Y+uPlX^cS<wX)2yXo+SW9^`#!EKTZl56A=*v%=me_P4Z{FC1&sw;y52b|F2_ZC
zK_2C;+EhyZ`@3nE;~rzFt8z18Qc!!HBW;-mIhwB7r~B7BAv3n%QeI~P$F`G*(FrKV
z5zKq;)c3iF?58{WrZ|d;>r}*I(sEmUhIK6BaDJ3qMR?CxrlFPOZJduv-)D=u_hx&!
zXpMT86Z%q%)~@hSe;KJ|Fdpo>hLGCp>Epj~>89$hmWy@XiAAnZ#87y=VM%4NQ=wcK
z4DX_H{FL$wv41iJ#P7|#t6$|2+|A*K)Fk{PlvrzidQW3yNe#-kpa~?v*Y<EN)@A_U
zrt4N;0L0t%GX%%M!>)8hart}QcQ7Y*(#%hGvMFN>x<M>W>)G1~IC94$imwo&l#qJy
zFnq%zem`u}(oB0#RGgc;J|SC0U9R)g`Sqzp8n;s!FlN>Vnz9g@08KsH^eP!VQSlg_
z+kiV1>tX-k_q9zwGB=J=z-uWk@**{K={zICHN$NTnOehrtU?waRFrII)6uD72=6;Q
z3XZqI`5D4>nT`A7H`lX3Q<RC8wU)6zCVuq=YVww=8V4OCDCpl<dXsz=j}Z>9tpOJi
zbl<H|OW9M88DILHkUy|py7wcxF?*00kh~Dev<7>mIOWTd2q~&q(uwpaL4}GvS~1r2
zFn`BR!nL{_+4MWCPL~jYRtvo2AnNu;H-U;1snbcHA*=2j;ZXDgZ3S|nnN$~#^{t9w
zSFEkBmM<ph@lHvyh9r1T%%qYz_jQh89tX}DR_;;>*p+#_{PTNaU_@n7A3wj$jp#k4
zy;OmU2UZhJ!CURQrO=2zBhsjlW-VhE!;zhv!mi5qf99$VEBP!vDbL5L@05RjlIYPj
z7j;Z_-dGR3Rl{c1tM4l;Z}BO#O|p>URCDt@I<TGwI*NMo-Pc$?=@7U(xa;9pmgA41
zOPo%BeL$c#^fbc~^o&egr1)&o^tGI;0sDdE<MLCOXMS1Og!vD9v<qBE&crrsLAzym
zso<CsU^dgQsYvDumnk%X&0R4(w2<B<#uOEowVxN^YQCAG$e@Jl0<E=msQ6gG>#Z4h
zC;r#lKW-X$rw_TGSDLwk|Abro2gp7%8Wb`j=hE?S6V?5@i01G?2_T*%AdCCwUG34n
zdG^J*jKE1?^!M%WglE^Xf(1A!j=g!=;i!M1=tO>|zpEnd#8CU-SDYVrGnxi>hLG-T
zPxN*euz%c=UJ%$kxn(ksZurkiCCV?qm#>HeVD$POl%Lb%GuRw__H?5u;JXk`vIm|R
zbkH-#z1g>bBdiWFKdq8O;A|wFZzZ*GBtYHa_0!Pwxz#FOt8D$;Vumq^VW!K)!BxV+
zABEZXmAqpt@=C=nQkw!g)c16h7<$N~=~agsKeSW6G}7nBkwy$lrO5zoTIAuh`}-Kx
zy6GtkRJCxPosb}H+fT;A(;vo7=t4%ZpBB6J1PEGcZyZwnAO7yhWJIR)-_=fS6tY-n
z&N!BXS0L7ky4Ho!1+!KBOB;d6AP+Zw2*$@l54jjCDVP$L8sCMq(gR@#^oX*8&3H@x
zDQU{w$650=d_HCfF1#sT!Z)_cXVkIg-LcQMDIT|qhiZS4n>hTP#ABMR5M35BPabI-
zrzW|LlLtk=6_}KA*v!G%pGHG72;pUoClncg@P-T%NZYN`wI&DI<u_*|GNt-tvfSd%
z4vL*Gj9H5qqxw#9$cTrbpl)HJ);bx=39|4F1XXzkBiSp$)ZI_cq*pRN#1&=SVT2m~
zk*+*mt}hdxGvCb9Z_PLNM4S<ZT)Mn#HA+fG1fO*BLOtCyxXAIC3f2iy2;%NOF#q=D
zQ)*uJPmQUs2?&c%r+#K4&O^vo+b+qaQ!Dr{ofvF4N^R?g%ljCnWX^qd?`&JQOqntM
z3ikB!glTqSQRXZU=G3zhGXDnK*&-hN>r}6(VLt>rY>n8(-sdgt-xVNa|KCW5kOq>J
z;3X>4bA)xh^A16ALEhn>2Nio@kX|cTQij9EgAQgD&9*8bnNfpN6@U>SmZ_*XGI}n>
zc9iFm=&V)vDTN2SjYfGW<1^GfJPEYYmzdo;QvC5z=0x}W{ICmQy43J6mRI^boN>Wl
z?Mm~$Ew=2XFavJ%himKby+C1AJFc*0@BOsii$t3>2?<8mKfKl1BV%&2s<LuyHv&Zs
z&y2i0XSss+a_z182v5b`nAzPdu~|7Dsg;<)9sq|AI9@Gh%eC&oWSrRR#CERWBf@c8
zM}ug`kXJ7oV~yjB7l<&Yod5%jNo{cY&Ro}KDCF&fI(^vu*$vkUrg&5K8-!n0M;u?J
z%@*2T9HoD84JvMj5jjd`*+pDkiR^&?vggg+t7PBfw$@BBS4s;@?U>5Jr<)WL@wI0b
zh6U7U*=NgFO_;{^@uv%sYD(tqJ2iJ5#s;4F^8aEhxOg!b^2(73ZyyQQxodp<xc~3?
zk%+f4Z_b{zZZLI&HQHbSv8+RT*ql3Z|4tGZ`ji;u_goo=)@<{m^eKCml5(X;<zbU<
zr_|npsHvhy@3+yrB;<d5!(Xe2N<eO8x^FxQ!oGPx7Uu5bo$m2Ainw;<dCso%?E7+u
z*CdYj!`^!jYcovbDde8ec;^}1Ann_ApPW;_!^lLCMt?G17hTbTPuaOn2bC)AQPuYz
zo8eX2<ufks@2J$UxOw?<7kl7#V61F?6CWx$o8Fpj$_1lLp8QUr9!`a))y+5~DCbPM
zuDf>4RJxm@HL2h`oA%&ql>lXc8G<PJMda#4iw+BWRiNx0INA9i#@cY^-G6{HZP-5d
zcyGS;dx8E)q?-%LcC)=g;z9%EZY>_oPO~z?x79j_33!g@(r!kM9t%$kq&w3*1LAvh
z$(<(TLis^+{GUgWvvC3!^7r=$H>_Y-Z;!x=n)vXdgaj@8StEd};5Iyqql>@XE}glG
zDH-cm#t4rZ;iD?$!(%xn1mIb-o*%R@7Y?$f=8T8>*B-B)vV9ureGs7YS}vXC|5L8(
zEWi#JwPHZ=cs+ShVG*IdALBpK;X{*AQ?R{AxsoR5KE0L0hZ=M?aF_d3eA(k=w}?c^
z&vo`~-jJSY<vMp=2O6PK?4_vh%nAs05nnd)pJhMv?)0FcNJVM;FDks$JffWP=r(BE
zY~V<+rifr65ni}_8B%0Z_Zl`?kQPD@c=Ax=zT=vz(__edyN5~6>UO0|9DgY0X#QAk
zsX!*6=i5ocfu~S-p#$)hEIZSd8?vq`zhgOWQ~QL;5;09t7cnnFIPLXA#S2rxg?>b=
z*(8*55wD^vN_Im?YLK|jbd~NFUr&2A_W+nA#D~s_^`qNcWD5b?j@lKT>Bnu?6C^Q|
z>JfhAUyR!G$~f!@Zq#O)R)p=QG9^z&9J75$4=&9#2RU;i;O;KyFym;1zYf_wC^vc}
zZb!l3QBwMjt{mcEGnRz@1`_Sp*%uLC+WctZ19K5&r)ef_?xzfHk6e>wr7PWkb2eUC
zkKa6z)W7uet}JnWYV{m&p+p3h`+G!`UeLi<Dq=zK318DD!5-c^lO=AE@gY5wsFgf`
zGx^;EqE+E~V`fg29+`9*MYN)^6~{!FP^%%nh|V=3zCd~zxZ)T<1nXj}&dcyR^)gwH
z6+cv(YYZ8LeTbtlSTo)?324v|YhG?D+@BO#4G-RI)!&~p9nW0hWztafP;z^dSvz)3
zXg#8))ihq#ngLr8$LX4u+kfJv6g?_=sQcY)eK6LWyj0`N5sCC5xZT}<bW`7uxouZI
zHgpK!zN=Zv7;(oX(pz3u=}jXq(LMD`u&OsXf%nUDPJE!^O98U5U#i%|@#|gOJf5=~
zaft4FpYoZ6jAez2k2q8Mo$0%LbiKG3d^&<oecf%Xi|OeJ1os7gP>fI&`A5x8tjC9P
zz{Rs5;9_qdn{(hOJVp_y=M6u&sX|#0s35(mBb2ww!JWzT`X$i2^B({e6iU~Pl)t`?
z|6?+G_RK)u(FAFTroqYl^OArH8FqVQJxalV(vDL@ereG+yM^PA5OKCGf*vsSZ&Qx1
zAsa4#outldJcy4sRiGXxdIFOna+M?`0|l!`w3jF+hC58MX<tK7KUX#u&po+ah2O*{
zlO*+kgv&iQaV6UYZ}hqLX#yK=>aE4zQ5Wl&w!{fd_%qYPD?7gi$-i`KDA!O<(xL|H
zoXk?{jGKb!OXJ|zJT%&?UJ%_b7lEIyrM`(h+($%NPCOl<gnQqGVJg|vOGT3f{eBYc
ziCes_tN2DvI>~=aCv@Bc);Dy++NR#ALnRzD%h!5Qpu*EC9EbqZqITwcCcAf@h4(+2
z%r!xRO+k#CGJ%q6^Z0RH&g<rYy*{r@%_r_?4w}VWcnr`WE4Fmo*C>wlj-iRsgRTM2
zrjjU%nJvWiCemkGC#W*R*ljXpPLE+yr0bThXoB<zGc}A{`C~PmSe=N=k&lh=ELsjx
z8zLX|>7w$z)?ePdGPQg$iR%00Dgc*rK}{@{?P^KdC455jtaG?gM4Q4zV2F}rw#vtd
z^vQO*Uu%!1X1i=&I2{cK+^?^=xknoV;}#F*386}vm||sEZ#BGbb{onY%8AYjm+Jg%
zTE1<AZOr;w*cq?RFB-6TC*#m0ujrxzU})1w)uIX$w{v)bi>$kX`nGKKGW!VbWYv)(
z)Us;=OAtM9_;aDiJ3DlVP@@@s=T7`Nvr{GSAKA!4CNLfSU;VS~x*SxYas&GpDB`*S
zt_N|xPc|Vs5l`AWd6*=&aZDCe0aVy}nNtnQKa88MbU*aD?6i(QK~FcM4fZ2@h?9%5
zK(|H}!o6=Bt(^jSZQ{5QC*$^;Erto$J6g|*0Mfb=rWYGG))eiRhy=Zx*h5Wv9gkBv
z?;%a$A7VuWjnl`VsB@0gXn6|7lVhjW@4sJfN-~Ah?VAwc_7$gHR0b1;aTAPqmv8AE
znYi|Yh4!Fj=uNJskRUH&U^zjLc_nj}o08!bKB3WEEZ3U=$7gI=C;l<9@z{_hBN~!%
zI!%%J@7PR9G9${ZLW3<eO<n?tsH_}zndZ-!`SvGz=#u;VhC-vE>RMvgt@EbUI$Zbc
zk52T+a7@;NLGuO@WQS%%6j~-~u#Ot<r-duraHiUM!?6%Vu<z9i^I^)KNb@(B%@eEt
zFn;=J7ba7+_S5*uUAj7=xGuaw;kI(}Ut_{w2S)=O6`cf*yygW+-%g15hIu_SRA$k-
zLZ*(DLtfHX99dXk>5u2ad5>QX9o1ABEd=60!DX(NLxe8Ts(AKNs3Bm`op}_hj;q`!
zgm={E@WWn_`|VwQeAK$2{z~pr4s;KCU*Jv#RYO1vi3ay0G}Ru___Qxk-4UCTs^I=v
zc#~~u9Tv2m?Af~}?>kMwr#&JRdS}+^Jju2Piy#b$Y|)vb)xB`B2ZH!Ks;zAiU@=F>
z?byGMXl6MA9w=&10pb=#Myc;#=I^UpN6iPzV_!FMc-Cqu;_~MI4$qo{LS*r$EFkG#
zV^RgaWjsm<pP$w}^<wrYJR65F(z>J=fU9hR(CQE(fwgdz6W(8GP(r)zrvdW&mlv8Q
zN{`ZHlHD~-?%_o{_X1k)k2I1!%kFE)d}lZmGPlzf1iZa~Na0cyis(d2fNlm|D*4-U
z--dmpl*QccU+7iKUFIaGlMG*$`ELEN*TS2di%mPK+%LL29v&NJNQ2YYPt5$b4I_G4
zj<Ech`aUSgLfghjBr8+pwi3`yw2tyUa%Ja^Dgc(oBbJLQ9&HhS$g{NLr{fHEI<7TU
zxLq_q^+M4+(TM_YB${ykwbk?VgiYGjiUHX69gA`jH5dN*4F2YWw}(@B=)}>x1CH8l
zPlb5aDis;W7<GJLVlntX3{niV`d9SP^sO{Nq?G5G??Kvs8*an09<?ObLrzE2o2x%-
z5_*%u9O*IY39YIpN0pCqO4(gTwV&aBRW!Y-5&>ja1}!l-*uw7@?P|<Gf|>YFY2&wH
z?$jDP27G6^&|=j<pR!Mgl+u{?FkCb~@ze5z#ESMvBs8iCvAu9z9f0~R&tXAncFG^Q
zPIl*KL$*?Y*u-eVt+8+JXX0ag9jrhMYZ1pR(<K|b?k@j5sR0V_*V?73$Q=wAubcI_
z6~Y$n)S%*RR#eC)gX7MpylrE2d~MvYx;H8^?J(*9aVNyphP1a77GucL8T;%lSKudD
zS4bs1FMPQkMkc2xED6}--&xL(9>0Ko)kN_<f-aU-ZH_LN<@#Hg!j)scHEie!T*Z6G
zGa|xb2Ks*i$&Lvd+rWsG;`;`Ivt8651OEY9>%+<V{ivKc?`a4?&SwnkL|K=}I@(Rt
zi9Xe9hKUO%BN3Z*qEdt>@QrNCkV`4Hot@vC(=#Kz-6^vsHp`c3JI63CJ>92*K;k18
z9pX}Z7p$l~?1))VSm@pAr*g%w`8p9P8!NzM9EFl%oWL804fN{g`H`@ZaGcf3{ksb0
z*IZQ^5E^~84SPbw`f{BTG9kUiXrIw+&Fmg<ywkEW(sDx{QeWNcVYuAb@f+pux$aA{
zUrNzPEBb3FtA#qQ?0p^nlDrowvsgE2r4kzpGXhzdcA^6KJ8`>~{hR*Ye6W=)FQ8hM
z)kg84pL9b%!eBw(3<xe7>=BDyvUUdWvKLy%bu=zwG<*@^^bXKZZgzenj3MXyjL(Ev
zalcK8SnJXtz*}L>&lGX?zA#OSVVurJafRc`4zpZpbAVWsiM5|r3eDMI1Df(WD`mfG
zR#*RB$(j(CfyVuRVt0q{QEKIq^UeEln;rI;zIUnb_hC-Zlc=ZT=M~*fGWuR=LMHHL
zhzFgXee7Ags)Sc8zO{#l5do=aKpDnoO>a<iws-Ms7}${}{oUtfVh_<IRgEb1tJ1ar
zkKyF-Z*#Mjhl~DeL#OU@q8nE*Nm$BLadhJ%U=ZUCOwlciJIJt3G%e@>uz&mgF9o}x
zXPV{j4ynjJ%mP-&*jo8}B*m%9D6yO2@2<Q^)!Eut_s%rD$$MsTB*VwR^#QaW^p)?9
zoghp1S!uyCvHu=KUXRlwlc(Jb0&HwZ_vld&B?~`4yGd%$j|M|^CCPgOaPD~SyDhK+
z!YNi>!Ec2qP|Zt|l_UEUzbtgXU5=K+39^vW*=cr|3ieeAi&&c^YF5##5_EQFwv+BZ
zK53JqYmb%oD@YSwqvV=1M977|Og6&v^0k`Ehv_~QmS$s%+ks1h=2)dG%8mY?qA0gO
zA12}AH)Vw6EO_Z{z$9hBCx>GPaZSfm{(t;khgp48&vPHD65tQ_<+O;_7r$Q_CHzjf
z5*d$GRO@9ojjR}@5e~icJ&^-^K!+#T!1r=l007{9S<whI9Z-M^V%30sAl=qPj!@{M
z-A&K`i)ezS{Vs+8%wg1v>9{4uC>0+;JPI%XjS<Vgbf03B69_t?Jp>!@27bgJoy8Bp
z5QW2i5np0t0{1IT22@;~$+Hab1Ax+J3Lt<ehGbjB?}||v3f8rX(pJ)7I2Ih5p7VO*
z02oH(h51?!<;cKXBV_>ML$v0&%LvoE55ZAf0p%CccZiS=@rIGIkqlykL<`zxm4GBY
z{K`^UC|rSp98L@o14^U*zZd=f@7D@6$-f<YtkMkB#HwSA${%{nY?6AJk1%QI{=Ghw
zTkb~NMhv&EXSS#-{BVs^Qt^40lUMeHMQr7!QE(;Lwh;t;8#=$w?)6gA`MlW8pyDg~
zF?tKD6@GQ)gF2b+MQGcD<ue@UA-<9m%zurd;KG#^CLYF49NQXvkv6;BhwsK|lQm(S
zoe=TI4{M$R=b+GGw2xG>UCqasWU)xyIPyiSVUIdsSQ8)gECB7ce^5CN9=q)hphsVU
z{6>s8f<+g-MHqV8FeNfQCEaoq;NQTb0terT?y=Q4hii?~+oVP)uAcw0s#u6K?H|O7
zb8j!Q5XpO~cWW{9qo3&f{OwyP**@EiHj=T+sq*<7iKx$L`o3k41*CabisE#OE+ur$
zda&Ww=Jm9f&6mw)HF~sMJ-o<5jljgYmV7^|T4`=Iu5%2(H$k2K-_J1<=?qf01eVH3
z^SQ?@XK-&DzK{4y;xu(QCE6>8zw^J<qgHx`{C11>GwS&>{$c*`reKBlz>k%B@1|jP
zclZcGu(fJFOp@%$hbL@(Wh}qUaqHsaowZaU%8yI*?LR<<$x#we7kwg}yz=JKeKIL4
ze<?kCBK{_7)MRlZGp@|^sC!nx)m9NE?|<&0+QCY*WtqyCu$ZNqgo{q=M~G(=y|tYX
zD!>rx+>*T$twd3Yd{;T{g^}^YHl3TJDj^9Lg1;R`?$2b3!_wceP@#*gc&I7zAaTO7
z;VVvjq>+ny`!25R9z7XR*_uspcXvk(WFE$LQ~tU%6=>2lPD(aqO)v4(D3J5`x?XF-
zfnv5r7kbTk-(OB`1SsjQ9-j@A7P*iMFPhxVt&3P-ip(!{5r5GZ-^-sv&19RLHA>7u
zfG^*r7<j48AR=<!9}%u7`^5V?*k2^hyySickac<uK3eMfU^5-U^~8i~L~tZnRIvsI
z?yK-{=^?rRsE0aR5anM7Ktg_)QI?mrI9x7+nVza<C&L)v4pOpK*;@`r$VDDM$p>n!
z?we3uAB48OZFj+{1&oAdl#%3?zec`5fZ`6{Sy2}9wbc+&h|)B!G^f0uPs3<GHCy}d
zii@Gm4?ODn43vAnhz1zv^!Becx(bQa<rTDKz3ZRuyA|*M1CR!rwLsqP%}=PM<@kMh
zYku8eto<jW6x73RY<9d}#Tu22%0PZIUfE%Nt3dBn^j$rAnarGf2CwMJ?mxhuDfPmq
zIO>U+eevZ^5_HNZUM49Zu-IVFVqSsvlBV4>{*l)Uyn2f$RH(#00(gbTsy(})ArH-B
znjf30eG4{g7w5ieM9lqWBcP&au9ampC^Wbxw}GOuJE_5$MxJbK_DUgDWvytwSd+IH
z8$p9dR>bCE%KJam{SIPDN@Hc;YN{Y@EDT+^^`;$T+i@h)U<!K8V5@hMjd-P;m^s%>
zJX(>3RIQo5XO)L&kL--qzq>}CFu)UooD7YiUr}I$sOdl^)xRz3VNaxT19<3*ob`3d
zQ<bM2O|vu4Ja@_!8F`@fBoO180{V@56kM~VV=v=T7pHx?5#jBa!){0ZJVh--uK5c6
z*(nX=_Q>vnb6sT+$3F4HiTs;${a?B5j@8OGLk%*QZ0xHp!waw$BJ~Y-kduKai62sr
zzDc@^r?X+EFO5$v)w#Oy_rL;L?Z<uTkdqc;Q7AcIVK!)Fko4>I`c^ugFc}dUL|TI;
zL!h(H;#ws=RqI@Me=%qisx;dtLNzehO@xnQobtR>%sI+VI<w{t%wk|6dlarNNdjE*
zKRAahO!K5pg03r{2&sd-fbXWT)AyFae!O91^k=|v-m$OMZvrtK<RX_2<kpTgDk+G3
z#q!jYsnYNo*Ck}?=@LRu`9fHXSr6P&e~!N*RM_#JtFw;6n_03GU6k5fG_Dxn-W37g
zWh!L`Ovb_5_m4E#!-7|834%L5P0vJozst{oMq8I!L+&S6`UhW=i!nE>suLxjG?lPh
zXK5biD7DSD&bjvEJ0EL|XtlmFe8W+?(p5)it}qi!RUQq{b@S5vO8q(8$7HFJ*Wl-8
ziwI5S_3XzgzUBwQkLm%HC_*e|I>5tX8W!Yo&xEfE(f88|P5Aj%;6y9Z!wkXbe{IX!
z>vxq=h#i!V90%xXTO$!(A5bg?5F4+QzywboElX`u%EdO+KMipI*ZA~RToegxU~jXN
zr(vkg{j^#}A#DT1zXsn1z!p3{S4YirS7U^f@@3I7#@a~3n#`mYRWhPND?5PKg=MH~
z59UywjgM~YeyT{<D3_HW1k+axzI2xt5vZ`YNche<bUgwuBg}hG7rmi4P~?D;ubUZ-
z<+((;eEWG6zZtlx4(duj!cGn$)#;!c%_60(%|D9BE%J2v(TsnYp*=N9HVRLk7{Hd5
zPO-cv-P39sQ}O;#TkqFWo`=}GuAbKQ+xU?(O;>cowg^<B5~$elDo!O+R_qHHAgbV7
zJ57#l?BKIT>R($LVwlD%w8G8nkaJrF*&T}Kv*X}WoiV@DUKT^j3oECR{G?o;Vt?SV
zeg-Tro6~!3u~lxl(%Xg%erpQSVo2B}mH<CF8O)q%c0s+MQfvmAy?ZV)gu|Y=Q*8d1
z7vn=iEQpOWhQmD4m%im{T<baVXtC^aQm^(tR5?FSX2iWJPvI4zyG565Ta?Z~a9^vI
z%dEi~=za39h3yvH`Ec*5aMAb6(I(Wa;qw}AtlRnegb^fofP0NB<)SS0NLEQXzj5c&
zp$=tWZm&<(STi`E`e*$y<LW?<5X{smj*(W(MklvSLf#;TN_1h;n9GCI`Z7?bWdzR+
zC1R`ke}2EuyrXMC<G)5JcNH%l=G_?9TXogb!eAMO-KW{#w9ncM-6=1N-V5NQ16A}m
zo0G1+GYtZ6vaMeQ(i()WW5t-6Ei<kpnU+SW^%K3n+|5mvN%H6#$9@Ds5~f*69c}36
zI*IaYZpC7MMd)SNDW-gr-MEKUKPr)D4hRg!F#lSsU*FnTSEOd1ec>EKOxg9k%0l9r
z;lD=e-le30|Ex$nd=yw8%M>~)CaOS>CHTy<In-1rM7vwu)&afJGqCRVzQqCV9p-C)
z@gwKIOC&x;Gt9HvLqO<Pj6qG<%_<BY6T&n?Mq_D%S^FhHkEuKx?v9PyXYsLd?cWIg
z12nVUH-sGc{+Q{@sfe<bQzG?t=LIGH_!q3o=yh{HaM;x5g!}&F5lM?yliJ#zbo9v7
zbTe(!Xy+n9h(q#NTvw0|lj23&?SLPaL1m&B+RB-DNMuPcBmAjAVNcJyfMCaP>p#Gw
z$}ykzjQ1JK<2n-k`@|pi0#3mEa*ydZMf?<DTa;R}K7^{`zw+Pz2jG~~$%R(aO!cqN
zpox)Bc3^wBd-i70_*M*~3nZ?q5H2d(wQ=J3r-{Qs#4|i@E+TQ#qZ55{ZVt;+oTj=D
zfUhVff6v7A<#0Jf0sgONB(9O&CgY;Q`kd^U_Z#fWBmA*o*BOd=LN8-Mqo{)6UdF*F
zgwNepX_r$Jvz2JLJ`P_j7%?R|1Nz=6;zX!*7GCmBx(>gTRhf?z_()X1dSN3)9DFRo
zdXx4iMr%yn&Y9gEU64}_ThDELldObbSJzx8#twg*(aUu)@MDQ~nk{|8;=O*?H+HOq
z<j=~e=#9&@?enhRXKE>1gQpBT3DiZHvV=(+hB2MRi0M)?Z7mc<259#n7ckTER;^3Q
z=fkego?<?i?Ai(`yS<vwv)-l?pthU`RaASvU-2iJam!z>p6s@;OiY)&PU{5dQcQq&
zhdXS-)e6l}rg}8)qLFhpHC6uaTY8w9RG<)kDCWu+D|{j7>k_9Hri&3laB%}VErkEU
z2{9h&3}O3vGwKvPmweq!8T>?(1zLK$e|dM}+@S9^f%kg^Ca|&a8LOT&X;+}rS9P+`
zoH`@ky?^w^;}<%N{R?f-lM6iunDk**87wXvii=Dc=u+DvPZhvaN90hHtgze$RQ;xH
z76Lj|jNz&C8(cQ--B48F<_N+7L)Dea2^XDt$2x)&f3e)vqzdSgQs!pPTiZ}u3ZoQ)
zSY6AMFb1=!?+ezEd@rc)DWMvG-GZ-O`?vSCNzBs&<F$&ujBg6R&bI~XfDj|D=5REl
za2moGUy-VDUPM)dt=<N3ATKd3uf8|S|K4(V=>2l8x?`kIY4#{GI{yv}%9{{uK1#oG
zdcuBR8RkAN)?zIih=urE7`cO+k=E*cF$(3vjdZo2SFTX=i8MKJGehmfSy!&@aPInc
z!fsI&{iVo=Xl~(MRAjQqZs{{vS!kj#<XU}=Lb6@gxKIKF7iL#Fe&gJ$;H8FD{&$Ye
z?-`=OsciqJ50pkuzg4R+X)K7hZu+xe0_ApYnVqiDNRbg=wabf~_zB7a+MYh6a3I(V
zYK_qzkl%)bc*|5WD50>e+_d%2d8yu^k{O?jiv(3KCyr2v^0l3na5Ah4#RX-|B6UsV
z@Sj4h#FonJ1K1*ndV7T22TNTf4{)zIE0dV7M0Xob=wcJ5nK9}^GkDu96=;Mi%-cJm
zZwCNb^lAFL!M}ea<6aZ(wq%%kGiMJF@X&aN3eY9irSj;z(rya-FJj%3_E)Jm5vGLO
zu!QJn9d((^D!6afx*s*jsdCc3LGkPl>ov;kVc-LZUxk8fS-@#W1=*V`TO~M1%w(|f
zVBv9A&676hTPn7?V}cPWKb|ZqeNutk{Gix6d?c_qf-9vWm&<cg7nD2WZ<E*|+R|Ba
zp?6Mf6Sg@uS)`q!cGiTvKI-5pqbvTqo2bGu3{=D#QqtR!q8FP=`b8OX^f%X~y`JEp
zkn+W+KG)4Netz~%G4Hv!w_fEYhv#TFQA$jiU4|7z;DZI`s3u#)EWZ{(q=?xM9f6Iv
zRf}@9b_PGYN8FvbH%*j2=1{QtT*2GrE7x<Fqds|`t=yFp2bvDK`X>v8dKi5IQN&i$
z^%XfE`tSD-pnPGA8Xiy8)rrlTWq5#L#=5xtj`LvA@+4t?TA+n<?xmZee}o>vTyrz)
z(@NmpIzbG#3~P$JIew+$PPf^IQQ$Gm&$)v#Z&~_dpHcdWlplxT;_|{)(jI?L3AI--
z;wbUQj094UE;=cf%ELGkJUW{GZQUq+P5CbJP>1~BXF4cA=}i>_v(`$_rn1YS^h?<%
z+K_10+*nsajN>q<q(|<}P@PXYG%E`4vN!^0KN>BxcQUjNk;;o_vde1y#Fq0BUYR2f
z=v16Y{CDZ}`FMpyaF-DO{A83;Un77b0Q<Y;-WPO%iOr$f&53b)FG5<6#9=jCQgyAx
z@7`mJ;sQQZiC0YxA|L((R9H_|mEkB%A3NFoIW_Vu?n|khMVj2_wCgCZszsZv68MS9
zAZyDQ{#lW}Lgft?v!S*p!tsb#H)+8{@q?Mcry5R?Nrxv(Bh91YLCpAl%8K<$w@H-J
zX3-(Sk=k+nMCZ!lh4%06p{$P9Nm5g_yR-bAsB4;+uv6ba2sBLj4A>TriG*D`qSH7*
z=3zoyP$LW4S91CK;9<=EF~8K3k4S=W55lpWm@vFlkG@u3h*z9;%Z4#!ah)%O*2DVE
zej|)+=6k|~u=zxr`ZjsUamS(DhQx@6e)%`v4>vljuHE%K6pctpM_TJ7(Ppwz)zhrQ
z{JiTi7V7<>(M1Gw`5k@>Hj6~>#Q2ho;O$;Pr1Yf1hgFum4A~Z3S3~^wJ)H_eBCjl8
zn-zh1<5)rYOL7jz5rh$)Ott%&9|fd%@u|K~o~mi;rhxr2bc3*$+{R*RukUJ8*In79
zNzwaMQprFQPQC84j;!dlm-~7XPD0^!=k(xt!04H7Jwr1D|2=Z!8MK{ogIkF0h`QLj
zo>_}?)n@)rT#427+NT6j+g6~;?zH^DXwJ<?_sUkatZYSs>tFORhCokZih{g#%1~Wi
zApWA^DSNF#i?m@L_@MJmkgnK&0Blp?0M0LOqy{=ELcTxWQ|Ixt+is;0zVv>%VE?n+
zH++9kA9TSS7xSrwJX?8Y%wf-(Sz{A>x{Q*#H)%&3*45>kp&8{G3i9o)H!)47q-$x~
z!rNcMml%*H4bR!*j4<U*oI7_llz`R8OuF_dkrBDNxGv+3jWzsv83@bp`tp}RqQZSN
z0@_|6e&oSAa5t^$=!Lb~L%gCDS1y}!)p=LBwyEIw;YHMC(kpiaa%k&T#D!|!DJ$vw
z>BhPVt?_4Hobz&~;??NP6jWrQ9p53;IN*9~JlW3z=Wg`?Lb&<?|C{f2qk!GonV0ic
zpj{=r@?3G;hf`~8+vJ@#6)Dm`H5+rp&SQ>@m}pDdoI7Zw0WObbK<Ksuoc6k0PXskg
zeAecbAI2XC{vs8w9?fAQk}axmaC~+$S8pE0w|+GZhfOA;9jSHPQg5(GZHArb9Y$No
zR8ABNW!DaM8o@hT*|@g_gP`s5LEU90iPcr$^urwL3Vsd-oO6W(r5Z)~b3Lw9jubvt
z^h!@`P@CuMJ6vjGA_dhYwaMT=>cXRB&&%-7sSSH9WEZ(xtOi($40-B3eCvY<Wvuss
zlk38WQ0YIG@>Kpe7MYZGt@pS*#&3B6`_K#s)2E}*%RV^`u~_O&N6`)AdT@k&4HX+=
zefHV}JxW~0$&o<8_r@mQ&1={%WtQ^yRpKLipie`rj<yj}u8Z1oaWx+}B41yd4hAcZ
z^5mHn$g&{0NL=57ZO$I5>Qd19)j|8mI2Yfc@#xz#Pd;4fT8)8ny<Un&@{l8Am<5bv
zx&TYI-PM#<Ey?rp+U>E`o1rFHc9|E0<M$_O*u6#YX1iEeQugzrI?sQAl^UBJ1pCvb
zt}sS`o+T|BaeGt3om?p1En?o<yDv#6LLB6D5+G99)aYnc*inZix@#JLv|CU4?ke0V
zH6%{ZUB4GF@gXj%@>u99MkSqAB6%LBN|a4m&rSXKt^1X&q${V}S;`$8^FdB69QQ=C
zKg{nJTIE@Sz9%nn^6OWv-+>UB+2wGO#tJTpVcK#2J_o=EF5&eFqJ^aV6@Qd4+76^f
z*HW6yr|10PW{w(_<2sIkY~OoWjap$+nphP2J%jD;L}`X)M&_;<L$u=6S5Qmw4+9S2
zO6ulTNXxTRG)?gR{qu_Uo*J<8t@WD0-)(FUgpWvVLUa~Yy%`ilh}63P?{hJxZ#*+2
zDK_o<)=GdZ?RvJ{*D*bn$<yJvIsn6u-)N$M9@d=d7umP5CEj+OvQ2V-=Gb64GkGn!
z$JSw|lrIuQ_fW+QG;JWNO8)ozLHrQ5RdnZfM3blv!AE`$)Dfb8{J4$+!?HD{XYYP@
z5CC&UH;aH-oj|c>^d+-l6yrZMw-esaX)@{bdU<e5yQ7Mfu7)G2IN~7cr?>qzN2U{j
zFPa0SHwh?)@T8*VVTY-%S*@U;6_FYzy!B?tYFs5VDC)3#KM|jE@!I&uEC-~FY$QMc
z>``k5;yhR#nV0zwAVC&T_pV|(KqU8RO>LBp*Pp12@*O#g&Ip=t{ZDy;#+do?+s3!K
z@=}63#+pX;CZ7ett2k`Z2<y0iKP4oYLGfV`jQqR^Qj~0G@>&e_#xngLUR(i)wm!R1
z>IL22{B<BL%Qa)CLs*&veG6`;-7)_Ic!(~eu0U;5AghM07QYcx%Oyqp4FF(PMyH{@
zPqd$=%}k!>r@ETE=l9rqCEOg(>yJLisA?pUYw}a@URUvaB=vr0bN}a=4;?eaIWGj#
zM2SKWpTDXu?MY*(J*B>|UJcxJ>5@<O-^J66+)u7)`(xQ2F^9Q@lg`!jUN67)aAA64
zrWp}`!|O=+a%}#$bmOm6Gj#C-MVL{x>=is73`UD_#Mx|OaqT`!Gs3h9Pf7`6gX1Uo
z@^42FBFVV`D3P8P=lhG1k}3>-j?!A?7rPMw15?N4{ilWP7mwiJ1fQ}h(8&h~ufqt=
zyH^&pWbgt!8+}Kqkkun|MwmbR{p^8s`1YcwXV(m>6iW5%E{JS^hkFeB6AIb^xZs;}
zVP)&#2V4C$A(YM{FZ~8W&L5GF5^RZZ)EpYhv|r0@_zT8V%P*bwYlWi`xkKi7t83Dq
zi-O%hJ=Vy#-469|3hwk_TIld(aoOnVQA8^^uSj`^n{b`uNItM3qI{KvN!*O2-ptwM
z(mv9ZEJynFK7AQV`M#v~5m}V>CXF!VlVBk)yiU^@A@B7QljS-Jf!*dYDn-j_vpJlP
zI@Z*cks<|&Yftg3_6zOS8dV`>&fw&a*Eadf=X?8;))h8prhlP$|BRZ@d#xdrs;WQv
z=Oc0marzfKev3OJWz#*^?l#-6G+-ql%XErk5y(mVOoq!y$NvXFIxNefSK({Teb}1$
zNtTaBFBalNjev;1CeE=V{k?R`DSS5E_?nt|Bs@wu5I~odu^NIcn~S6E{&St4(rEY(
zqhg(Fv6XOEhwqA@tGNh=*QMi|oKfdM&0I`Acrc%fi-)(6eEqhKbrVb?KyoJhQ=Z3G
zHw~(}M6a^o?Mh)bOzQm^%}^IW0fnf}h8_jj%l<gFzb61$As)SAWnSdubtDfE@=6MA
z>o2PzO0$d9zOa8nLfKek;`JYq%<yuc8Pa%LmRhz}j^XiB@rao=aJTZ`w6lHK3X!uS
z`ZYkZZ9hkdaxCIZnlQBg`xbvRoZBPqX{p;jfznm)k?38a_}^_Fr39<>5vdp{ZDk9!
z@9^lZ!~oo)3TaoF@;6{Yn%=^@<DHFPekYokh#D*}2$|=Hwd7s@+?P%3r&)&347zGN
zT6u+<Q+DoCsKVRQ^fMtD_dJq~kNo`$y}9f*_+_{}-~K$*cchei4l$(ZQU@@Km0Mk$
zI?Da1?Ug|aO@Eu8jA^qCaSbgpsyEH6Df77J$9maAPHyBsWmB-sbM#%PF6JNv$~%z$
z->Y^1U-d2mf=k$@iQ)m#;!)Xx-T`LPsS8*~Qo-+_4#S*O)p*(eE4$S*iOo4WR3amt
zDLMw-$|I6JBzY+e6T5JVg!u^dXDuIoKv5LcNf^f4Dt7`1j~swT8Jo1M0syd>N3{Hq
zAUq03@+^Q?mQjA-RyfunMAWAkG4sEYXE{?)2C$s63=;zS6!`OTVJHZpVmL`BLJ$YH
zi$`E3G1PhFXuG@#`<fNiKAM97EdQ&-VIktcwFFH>AJ0o^psWvo0u|LdOw9zxfOw=!
zlhJ`H5SC&qtry@{!vEq>;BvxI1qw0ZHH2}F1qt!1JdyXWK>WXlst>`^CkjUYzq;c7
z=bh`nR#sfo&MwJSK%wa|-Ox|k8X1u{<UByES9L@={d&<C+KqSMf=#`%cqCDk{1mrv
z3Sy>6o!`ZMKP>F;ish`JxjO7%q)-bIvcgnJ;yuX<%->5nUdq{}dan(4Ef?z0mVHlo
zboKGbs0gPqSj4RseTi#JEW>T1l}Cpr!>07gO1;#L)W37c*HXZgWvtho0sSc@_crf4
zf!PK~0cdCoJt*>Q>EJON-V1RROTtm?aUhTWC*><M9Q+@^eU`F5b;R1^m8n48;U2T_
zU^^^MZ)Lg2difGA)+TId9*&SczTb`RtvZEa_Z3z$u8BY;<wM&Ki0e46ItY0E2ZYgj
ziZIqs9&$&-<ztsqnU;iiG<JX&#&cX=xEAwcTdo__3TV|^>-66aws8X=`;2#1q6JL3
zH%>^Xb-=vP)Jyc+Mv_JExcbUeL5nS8Yxb>-&)ZBEf3xvdXpG`^22-o5j5?VJlZ|S{
z_JnaXno2pF@$sSm0SXj~lnu@QUJYXla?=P)gwz>h-AR2(T^-sBkXtMj*_4i9M(UFb
z!Q6#WuN%#|a$eFIN@{6KBnHPgi`T$y?exui`uB*gq_Bd0yc)}MiR-vibu~7}HVvH=
zm5984_yjSwEHXuDTWEQrH+X2C%p0pz8?SAdU^)fhEQpv6X!Hd!$4O#>^!2?=96NtE
zWyCxCtS61;-hRaQXE*sh_p@friZ@g#{Y!W0vZeI~=Rd+ffsaF(r$kKI(t@V)9*D7d
zz_-NTL;5|}Rws`gt(8R-MS|+mv|;VP#KQ^;i+%?_JX{Sl$Ja&X06Tu5>i|cv{Z@oD
z4f_{Nlv75^7_+w#Y;dT#_V1Wz+TYh-4o7}kL`!AlBXuSjJ;m!AxCn^F7Hig09DG3B
zy+6{tY9+++|K(8NkTVeLl)o7E_udM*7{DLAnHVl|wq_=qR!wDWAv>^p`H}fp8-oH#
zm0?h~&SZwjymE0n=3K0QbHMv>4$|(gtceS~MVbvvL2k{UQqTl3&~e<(DqAzL{RES`
zyKjBT@AxBv*g?DfkS<+QVyh&?jU~aRq+hd&st<sc5&3mdg{HeyV5|q68AZ#I0I>TO
zq3z?x?`t=br`A2u6qL`DtMBQTTY^$2^aIs%0u3XPg<R{qDObci$~V_l=gZaT><`@8
z>)*BIdzXMsl0B67Hzqsb)VCTykM|1PH2%0p211#9hBMba)|6iY$uD3H`+(w^U&?j0
z(w&-8V`O8y8Rug8<@7<Q&R9!njt6O9Py!EYo(KXWdGRL4-{`=VU!?n=Ax$4rS;2@7
zVG_dOIg)PMbyuNzBc$9-`RT*#R!v?L0WTT~Z5mL+8P19{i1Soq`tTt*A5uqkLlHYY
zG0uTBnhS9^3_+C>@CD+o3WZI2zquo;sz^vloH#`c2o^5dX`(uNXn#2|_RXofc>bK-
z_AsHWv%5T;^~>lwM~8O?qE5kX-@RqO`3w4+{|{&rs`>m-{rWX?M&@3Ct^ZVVj|TA!
z>nWZ66PD@o6xvn4^2I+p0<$GzQD4Kwk?IFh<;VBl8*IJ{nhMzsD9@LK8PXyzBHNKJ
z1K4vBxl8yYrq@0r(gLlPRnlFleo8zu%Tx#}<%KUgkW6+}M_I@ZvoK7cef0IlZLndW
z^4BnK{=_$PbdiP={<9Ca*~xW2BD>WfzO@0@vDA_I&WXChj10xeEa~o1<x3j$sQTVc
zT($<W-wLEKu`HQx75fHko6PCK*RRB97jg{1UV9IgPR;cVaOcrJ#E_DY$Ikiv;F4z}
zA&3x-u(_-^I;;5D$%&54=u+75o2{*xsGjZc54LqWuke6rN3$4vO&kSPU8YX0@287F
z3rX3Ryacv80n_T1Hmb#k742Z_*ln*ftw_r>BSVY>?ur=nloO?BW+$4#dVa1JH}xu*
ztcM2yH_qFzBh|Op(IZmi1(rUh>;BaXz*u*n|36wD4HqR+7fr;-A<2S4vGe2f(~^B6
zSoq{jTOqjIvWFanzL3hd@E+rF@onm|QjDb$agVAAnSR)E6?hx?WBwmnrPCN)La%DX
zKUBTAHyseH*ksy=swSkcWq^cIZCx!r*7*eD5w1vLLG_#{oAqwDV2*@TdBJ%*33#H{
zfkHh(MtTM`9EzMdPtzBq^d&^Xj_eFHZffi6f-wCD$OQdjdBr8l^G{U^UZChE%e%Vl
zM?BN%p2baJrVZTH8(ylyNyI}~UA5>7ITO1O1vw=z`Wv>HcjiWd?*6Y1WN+WFqWAHo
zpR>t}Txh5Yv;D+ki}A$SlroYXJA2YDFf>jE5hzuXFz{TGQB_k~I}jch?T?<R`B;S-
z`64^4&=<CGKgI45QL3K?9G2hGZ>aNVkuXSmfPq=rJSX{!!|B)?R>i3vh!rDYQ*l-9
z{@d42ZHz@Tok=`j6pHJa#r}q2Y_{|^2g%^(w0uG%miY^^gVo|SpZl!u*W!HVH0sci
z{seJM;H>dRkxXAVP7jkg7t>)2SL(Fh*EU?5VbJwBmab!rP#9&ZR?H6ezJpmUrZ5JS
zsM?aCtd*eTllP#zeAT9A#Lmt6kduYqrseZwTvEO0Wh{h`*1o0Va$gS~AfrhX?#+xQ
zDkZ~uA5e|9(?2Z|L!<0Ss|)^aSsg#T`o>Z8VU1f&iK~VmspR`Y-lVu&Qi{pBR(3f~
zJAY5&dP>KxbkQcWKzwOqQ_KdecVgPrJ*Hj9q68XH?x=M1ti$0Mc-WEP%&(|;22ou=
znpTXz(BWnl*A~tF^!2fd4RH`!Usy{{puYR}^Pf&cnsoFYp;ZAyR0~is&Hu0My&^i=
zK+XKKuJgWjR&;T7tDG@Cw(emE?WLLiR#X-k+HR}pLpH078JHeikF^_Z)JjJrZcT)V
z1@sb>Rya`9r@BQ{OztZ2XVqC_tv$akh)gRh5KeihqSH=eQwM40Yd>nfA*Ef2(5XsM
z{fX$J5OweC#v9jMaJ^Yhee(S1j#PUPHdY~%<fg2OlPX1c*1689dW`SSsDlDIb|zNg
zIgHCG=oVkWxAc6txq@z1&RVb+cPw*F;!2JjAc#8DVHKWw35~_w>KzicN~;ey?ABK(
z!}>)Ai^RG*X^*B|<F$3Z%|>m<-OeFDNr(!noKj8A+l07l!E?pCO=_1S@@oZo<{A=T
z#tESfJa?~kbRqH=@BQ(bFOjYJ_c-bXMb?4N8@yBT_rhgs?>*}{6aRc<EaiYbcGaJF
z|AAE!^e1JAW#NPw&G!-vc7NWIAcQQ>anLU*6eJ{v9tP?)XY8sF59v5^5ScB0)*zb(
zE?LXs<`oq+HAFwJj<P0NJdsdBe)PEsQu2dp-=VcEDu}p+WIZVX3jdx?zcx?X9Kg!b
z!6TsbhuBmeb-uOib3JtY-ySP-bDiYexx!1Ur7hM?*28+4N>nZ922frN0g(1B)ob^u
z$8wzzL+)jqHC}Rvn)qD_U~{~}*`<z@eUGNX+l;c+u=3VMMD+_=h}eoSH!R<-LdirB
zxQTJcwmNL9B|b4ILHF+?@Aw?Ddtm{4>_P?pRu8YeQ*vl~W2HYV(#bx6ST_q<dQ;8H
zWQ=y1(fdDu-Z`nBj@8~}Gha7cxek5wyFk&d%`Nl$kCU`}^b7EYRZ%4en`r4jX6-rE
zMLY%s8X~Y9CU2p%5pD#~l3n!qzRX#Uph+T8@sZON)_F*sk^Tt1$y{#>ae#CKKf8(e
zj&B!krNamQSWl~n1I5Kwkn-BKkDYW3>Z8;};kYB^=$_kPRYXa`LcBvBsS=7y#Nkdx
zinZ-mhkw#we3jT1W5w^TPbyM-^8s6*A<@!GG`Hc2ABmg`G@FtAk{d;MB-zfc)E;UE
z`Yf+cM1kSqdzJ>gV#>xq+AV<aMNNN5lc>f!_fqsoQ{@P89O%>p;9!4rGg1bwzyK^J
z5o#Wg45h=owRkYjyK~3mNXpz~90brqdE2O?fateBTK!g(lXU`KKz%bfNx8u0*9|fA
zbq#W{#LHr=LMVdrYaGVuS295kc6Yo)-H*#b;d)!Cgh@MY0(A3CNo?$;9_rKJduR1T
z8NvrIG0*MS8KvAU<4!nAScrEXW9A3n&UqN6iwcKJA?o4vbY1<ozMbER@(#Cy`$8Pg
z#F)33mrH{;-~9Y}((y=)f}ielCr}Z@udnIi?=NoE<juNYkbX&l9(dxK%d%s_n|5K+
zpiz@DzA4>t!yTt&@_g86_$!HJRI~}D1gK{uC8*lNC7F>^D;$Zc!zK~MaH+*=q8x1p
z-E8XZ;#75D&^_p+0e-f{MGYhOG(NQOM3g~WR$*{iwt!yqH{|opi_BkCM_JkbE}zIO
z&=%StnRLGVghl`U`VN#t#xoTb&s3@|hBGwN?a4j;hQYc)q>iUt2wW8l{;-{}!pB;;
zrcK$s_Z_C;7&^~$j_oy3@PJ}<r23*|IsX~L^VO$bu)Vh}xh5`+#wW%@zw&E$C~$la
z691wLM&1j;iL{Glm0LvsaBI&$UQsM$!1&uT*HCyBm8eVWjmMEX^gc}}?)%lB)xBif
zU_htJAIXM&96C{OUVz_)L`c-XKA@0R{XDhJvmMyK1NC|!n{hp&QhZw*`PK~OyAhd1
zcdY)(7F2DUcaBV@uCQF3FwJ(z*Y&ZuYMrJ{dY<=naznR|Q&$Q48U64W#1Bot3hT&B
zqy4hmXspBuCo=0gmT;0+G1&9eT0^BS0c9-hFRL;@-t7J9(Ss-(F?`@!c4Ajm&*mKQ
zvuj1etqcK8<qr4#TL^MK_ez}Dz-Y-7)k&rM+oCAzbqfG}qv~(81w9hn4IVYZd;@*+
zFsgC5F&2H<t(|MAdWTpk`NR--rg@X@Nvyrf<qMOA8b2!)_vW_9^PkNM*Sf%6l~}vC
zDJ7JzJ2kBXeoUWUV-*;3XUSFSa~zXe8tFPJ8?e@?8F_=D*0|8Y?hsksMfz{J<SsJ5
zni`VS7Z&m}<xlc;0;9tzb0p!HNK)*mL?#^sJVj>zhqbc`YU_=|bZ{v}S||?1o#GC~
zU4sW{OK=Y^r9}#q6!)gM69^t03M~-aoj@sC+zS+FH~+obncbP4o!N^o7nvlJ%$zwV
z=X-ze^O&`)_!1971_$)O^f#$y=N_t-TW99wEpC=p+k-~4^PENFg&#KqAzEq@pcfjI
ztitqLau;I?j6f-NbVp1`Zd=Ve+7x#5(wjYy{>QV}r1CP?TX)V^UF|c+OL@k^*{Adc
z_f?F2F1ZDpYfXr1;O{4u8QDzfEg(`v*|!-R%lyX8hu0`7EiCA($NkP0tJW;&g!9B=
zaivwO6obg^pLcMw`Lu*@D9x;TnIsuGrke^+g)w%^mJ}V*(cp4t54_p<#$eCg1jL@X
z=e;z&^+TaVUlhCmN4%f6{=-qd7L8)X-Ox&{YqnK`+KwRM@0z$K>h1_->O^toQ0%rN
zb=;W?Twl$x$;c41(+W71UCiQ|L9YEhU6V)F;Z$aPL%8n{JlQI|$TA0V|9o~wiHDH-
zv=sO&#*MSAMboIzu*V;sWw}iJCamAgVD+Vn*@sBYTkQHB7ib@OFpKxnh0HT?+;y+@
zGc&Vk$G1iPCouo<EdOnuc<j|)*M-bYT2Dz%bK2|5>aBqE0rXDejLy7jlzXVg-9|~M
zTQ<Owl;PSKHeO0kJWv9EW1J^?Vp$vJ{o#|}?H`=^9GpHJnUe{xe*jZ$2i0h;6foBf
zrLU=e##J(ONTPVhvo#&gygnh$E1F5t!b8ur1DC6l3s3$TcQt0Es;>KxoBO^S!xR}1
zUM#YASsieQTV$#Z<F!#SijgALA@PxtA|VJVWUp73s9@WRfL8ka`eg-iJb<RhC|=Nh
z;g?8T^eg*lCI6Bxc88#l>B?0$Euzc!kWcSJ-?`=;D)DOmCeXOKnTI6q`s>F(3p@e?
z$K)PIx-I#GS)o<U^hgs;S%m8V-{)sR-um7Fu#qgymktv-Dyd<W{Nk!GkwFDB=^ccg
zKRv4DrW*;wNrLgvHtTR6L;7{x%1csz4kvkmCMAZ)mA5>%*8SiM&t@$37$y=5wiqxe
zI9T$??~9Z`=iCKQvGWbQ>$q4h8tgMpjS=o<F8^wcePfR%I6ZX}`Mu+ieaw%w*W3W<
z-c((nZVoie_B0;$7PjO%{HWZY$q0WfQ2GyGYmv7o&s#Pt$`}zoj*qFx4Obh5teqTw
z^~MfapPhEQChjaE!=Tjp8<H2zq^XGP#wNsz%&8Kt&M5v$T{D0a@l+U>ZS>ALiMAs4
zERAYMCH=<yB>u#?z2X&91^7Q&jwKgdQQL{CZ)2>gIqh!tSgJn31b-1J{lUL-zhkp|
zD~+3MG{NrPx{h`v5u}Z~Ne%V>Vp{+n;bg{r4~4dQ4p>S`(w^9Y%YwQx4R~L(830A|
z=Q{)>``dNTQ8aDDW8aSD=nl(`#Mnv)7B))0C>X&ft^0j5<Dx2$d4nM{Navn1b58j9
zw!zm@X9)t=k=clI+8C3>pz1Op@7mYnlvCeSBwpv2WHb4iD*m$(*Y$dp-s`IQb4ugR
z*NNHH(x3Q8%W<fTj>&VsG$yvf|746-x$llHS1avV%Y~q4Y&*g>zqZNq@#yO1{sW{R
z7970<#l_4&1i>Zf;{1s+S=v($%(b}kd|bF7{qZOS0gg0&7JG|4Pl5mLX}M4T5O%t;
z0cZMF6h;<<lgg|5Gg_2sc1zYW)Yp`;Z)`C*Aq@UHEI|otRA&a38*){%Wsh=Vqm07%
zZ<6M7@TL2OsB@<O0dj!;_b$D%bO5EB85BkV;9Nu-Or>~?qOv&1B$VJ^13QI7LCGU&
z<jjmN#%U)e)P~d|KLw7d-gh4~ncm#8hVwH;iL01&=*UVsdY8m+N>z=n^F4cxHSRY4
z_7z<0T6xvV+c+%>IFRUbzIl}8qkF%Fp{P<B<?!x)E!EZ+H7OI3z6~)+x11?os#M}$
zZF?03yAFHyMlhGgHV7S7)wBNaWAq(RdYo@rjw2}5d4Fs7(PX^Y)Z%~@42GP@B1rFe
z=e|XuKjVSdMBMK)W~jluBKUTIy~Ifz-XD2>4{M5Rorg>prDZRM`T}`(Vea7`3QgHl
zS#~Re%LuK%8IV*1M)@kC!I7{g5~oT;E8F=dL8U7z$y-;zX1oz^YP=2}ic9QlhAItV
zoBYX*I5TAhw_;B(jz$Lg(BJnD0B$sdE3I+{Q<=?Z$4rVInPtR|?xtBu{H6f)|6TFv
zyBJgBwQJjQhN?*j0xE`jcgnn_51`Rq2ly7BX^(&b2S%6MA92>|PwutexSX@cSibLI
z77Jem%Dk6B1XfvC@JLDuSN`4cam!4-vz}Y({Ca6YG_cyaQQCA`?fKV#L~H{6lJ>d)
zTyyUP5v932pynzFq^aI*S@5_1G}OFXu!s6-V<KY$sW_kHW^A8BB2A^4gZ^9>IB~iC
zlp=Uio~?DP=V|3a{;hyrySNnvnz#6UMR^)^UbMl7DB7h#xd&9H;@Jutd!SfzsOOUh
z2z#v8X9oik@$m!|nqn`;0GvFFTZYu~qS^uQ$i5fz;aFNIh>0NbNMeRnr{XVkNjxfe
z^MK~n2vUXbPg=h)qciRJ`wVUrBf;!O=i2T7sC4O(7gPU9IOKM2j95?q{I;ayCC?@;
zyJJ)2tnMXV@1DNYxR6VVJ!{&0?vF&if*4MEB==qC^d`Gw<bOmSmtN_D@W%uxP@<Fh
za5{AjBi-ybTKl}FltW+Va!%!43K@`>e{H6m2pEOuE3Nf*$x<}`%snX8`wxvUztWC`
zG&xoFTYMB~T3WfDymkNHfibkjRo-eJ_~NiIqA=*u=lL&ISWD(Me>`$mvz3;r42>VK
zO3%A3QC0*e6YX7=?@Mu`TDlx96IvF1L`XI25LTmNjD(wA7VSB<#m_t~TQ`vg#cB;_
zL0s`^#<u;0VWTpq1_;p1v0by#z1xxTte0_lwjI?UQY7jo(Z!U|kPt0@W)s<{<<{XT
z4BfiddNdei?*Pq{xGD;)Ge&P&<%P~@^;Us(ySBnGCytXseLB+>QsozS18u?f?nYuW
zd(de*@c|+i*53mz-_^OIyo-M|&C=M=GP?AvZy*!n!(XE%!lI@9TA%KqchB}f9Cn)g
z{sfI0Z=x9ok9l)fZ($m5;)RE}y0qSJ_h~;LkePSGQL(ERwXT<555to@dJ+Qt)J0Pw
zVxXX`a8~x2CaD{JHv{RXDZt}L-BgmzL&-4Zqg)Q|10_r&NElNp(w3dxhz~WyT22OT
zB)PukplotFFTl<S7K==WsP)`oIDnPh|HTH}V#eOSilqN9@+!=0u?R5*swu_Czqkj2
z%MI0?u>i&RnNWZ((68Js-jF35BL_3&BZ>zaSH2|1d&4d7q6aX>lDR6z&Z0DADKVPC
z=)r^)iL`mR#Rz4L)EFzn^P_3@bdIzz-{;=>S8zW~KY-Fm1Cy4NG8oNc@*zWRN(?`d
zyIAa<A0VKZVM+~vGoKEGT$b)(oMf`V>yrNG)CC7>oG!jl><vG$?t%EtwfGA~YhyJI
zN<d&KXIeq2+@#P>Vr2Xz4*;SA<q=ivFM?_V{5d$JE);u=G>{nnE+*I+kSgs5;LsK?
zN6i{K(=-{WVZO%y=j8<BA$pV=gdM>YwwXk=H&nK2*{O6)euz~E$-CNWe;JJ=dt%eR
zSBHn891G-n6KvXWCF)Ys^-pA?j}JxDY+i+TdXzn6h^@>)hktrgwDbJ~M8A0#yqE?<
z-uQ3IGc;u)ytq9p8m{iotbcc5s7NTbwf$$fg<I(kJ+*}|uDIQ++1o_am21?kqHJ}l
z@2xVO9g$WR00+KSiJ!2Ar7EJvvGrz)B!ZL`v07PDvga7S)rsZK3tFt~-AR*?cWM0>
z1!PCoraX7cg!QDQfzB%hZJBZb#(HjFUvfl=w(y6!#z<_1ziX|M@a}8~n@Rj!ji!0#
z_aLj+Hi!6O3RQ7MfrH;toV-%pQ@}Yz=B5VI>2<<Ka%VWt-^-lNAv3u?F@*2y6DYk>
zba}@zT{6v*{zI_>PMPVA@74@8tD9oJfBu*D$!(Ns<Ky`ERW$ciLw^N=+?1y_&1XEo
zEgi`WytzeP%aU4P(s)`6Z?(4%XAZ1%2ifSM{LY%K2#|Qe(sn1=xALaWwz`g(<9SDD
zkpA}TVE8%nKoJ3dahnuv^$QOz`GfDwbVsF)78nNC6O&tz#Vzy4icYUH9i`bzOa3E)
z<vp~w#cQ6cS{`KGXT)`eZf)UC!?A#wbT8Krb~AYCw_TleFM5OZ2T1Aiz<?)vbnqW$
zL<n`<-{&_v7L7LZGq<B9apY9zD?jEtJ*~`ygFo%fS02+ITKI|GE-w<*da8{6RB;Dq
z{20P6M7HM*9|<0n3G3z(?i8gz5p6F(`vM76Fi~9|do<HekNaO;_|r-?VL#88GEQl{
z)m=s)>^6Th6ml!9tVXBSTu!Y~Ja^*(8TYO|6(q^p4Fi-7=Y=t9ue#<ox(G+gRJ^3_
z&WpoNzO`_jJ}V7&zh1VUFI&7HBFu;296+}mpgO@Io|%yheOj%e1?*{S?C*RxbJ45M
z2ldHl#~fm)M0BTWs1mp+pYdDs72ZY*AQsXWgHmSDzNR2E_h&m_c9P0N%qW&!E<ifW
z<R4dR$na|`+4ihWn@jm|u?uHf<=^92HUG)a?nucF7;t+AV}acsy7EZVyK>hot?U>Q
zofx6_y;mT}_^2E()ST**Fb_t)^BXON4u((Zg>n?3C*DAC^#;@4EF~d?Y*bMSb}g+T
z{Lg4BhS|c)>A%EpmiopAiqg$}#qcaBUx#c|hC$V&?FfHY0yPWgr`{+@@06rK<})SE
z_pG<<fjKja#P?}Kn`@QUfYgSFtEvX=k0QHNpXCO$w1)ak<+YWgCiIa$%gWUTuRv9v
ztXaJ4k+M<d;E1PqzE|)s*h93mm@HE7Il3#4@Nwd2`Ko90ZW?bMqcJ<IqqYU}N7WwX
zEO+t)zchb>+U!?*ACtMa=r9g9S#Ku#g6du9{D#_j*yHQ&_Ji)LV6&bd5_NpOw;q|Y
z%$2vGD}A3E-*YxaP14Tl6|O3GAdaVBS>Ko6&I!FhunU^3`xC%+nSrfZotJrLuLIrD
zkXy5ino9Z0cdpV2v-dsmj!m;^n)}-3+$8Qn&tb#4nHxrISSdQb+!=oZaPvyTTr#J4
zV;0wItwT%<UMq!y<$gz6IpEeBnI1J=s*=6uR+On#F=x6PiYPMcWus-RVs$CC)2a7D
z=qb2aOfC=PfK6LEV`<mDXyMdZ*sI+@`d>kCGLEMDBVjyuZ#5%3xHlZnJq52AjxBUX
z9-8dKd(@O-&EQG((Gk-|xhduDNlZuM`{g^CnmueJN^wEM+iMQ%Q1gwYUuAuVxaKRX
zM&v&Kh}cu6s9qqiksJoV8?6Kmyr72WR~5Nb>LR?{Xcf*Yc8Wc<+?sHmPqc`b&5MB$
ziU(JUR4J;ubE2PE`acshU}v|w>cXnLk|oe5V(gdY$r}1R&w|<Hp59J3#&FGE!O_ZK
zHYrq>aQB;oe2|%UC*5mV7-s7xSivKT%E6ek@%OC{{wk`Xit`U8+X<cClPLtl0KZe|
zD@lrA`XQRDF<%WMr=OZD$4DHsG+rQMcjTw1VD*0hBTHsGfcaO1k!2dAu%YMUBLgTa
z3bF;P*Lp_nVqH1LBGu2r5_IUYRW{Kn<5!kU-Vk*&`H?z*SC8}&1lWRx*Y%bx<Etx`
zWvDazg}IQ87K_bocH;rKGMdi%<+!b%uBE*r70sEeu)%e(AVVR9SWV4r72y}EPg4mv
zYwC?wpyl3Ett&ZoCs4qLXE@uOFf1|8o=UK6cT=?pCn$6IrHIl!+y+V@?l{aa)cS&{
zwN%m`KQ(?yB#-RCVyf*^lKw5CO?^=lhqI2I!{Q7&0Bg0FLgsXD5a9*)?ipFTiqyTP
zdS|?6di2+0ae^rWsPTpmCl3k#c<9y}V0D7c!{OwfEOk{qc*6dPncF=;JU~EwX_7yp
z*sDxUwV2giwdK6;FhAG;Y&f`oY-8>$->Bt7sj2JL6>3-bgzBXb;t3tcgzeX8q3L6w
zR0%F!VVt@UPY;Q)6>)bu;2Tb0*%3|`i)YY@KCkBZOJ0C5?EUGV832kkk2K`63`Zib
z2~Mamdv2B%H62bmJKaMEVK5dR#LRt2GZ+U?X#3-xO^4HAD%|f(zO;?=1Ol1>>zMzT
zVypN5B^TVZyxRuajg(#TaCl?JCU%|(fmk)j;ncJjcNbdAuBOHN-KF9?fY(7b)-~Ay
zd|hv(5EyDY^k#K9-qai|CGS#%Yn><0li0)H*)Od>V}2;^SWlAR<l+0&U(2jQ4UeEg
zx_lSP;Sjv0xk15}^KtgHdlsE1Bx0Z_JBfV;Q&wbv*f8a<hq)O?b0ip1wa3Uo_YS-1
zKvra;#u+*P0D%E`dVRqK{^JBM_1%CYnlR%X^h)aoKjyVs?NE=GdY?ux`*+}*ZyOD3
zS{zx@9^H|pgVyuXZl<ZBO_AT2c{#jtzkWm3oQN|@E4E}rF#e9ZKhP>MO#$n5G>(Dt
z#GQW+M`6w_>2_<yzvFkw;{5Tyxjr*A@C-@mckL%lO%7`qCa{jL(~|s~!MAAHsVc_I
z!<gV}4uUk~kI$^B@nP~@ioJr{W0xO6-{$f9ylLt0%DL4XUw#zucO*xzd=&lG`gZP!
zhu-irU8u#HenR@zU;nPaA{PUX1|2C6bUaQY!(2tLKy=~YV+pHZD%fkbm;O<(<4!7{
z=6ZMcj9t#+nI?K?1c|X$#^K1~JMpU0#l@BX?i0U^zds)IcK&4FsJ`=HyCuWZ%jhO*
z*eKZsp=%i#=gq5xcQxf%#ty$*`sJEY^YtAK;TolF+kh*qO+xy?%u>MqVK#K}ABMeB
zB&ZTu`&1((-*xZm(?@X*rT~&~e<kRS*KSaOeY8lQU7?!ocXj)^4t?eJlnE|qqD8#5
zFmnX_+fnZb&qQHaaPJD2+=BKewW1!`kP5L6TTYa#_fAMISi-kmaTQ8n<rYMfK<pQ5
zaH&Z`;L9#fmi`u@qr}SwHqC+~kFKD~W3hv(0DOBKh07U|50K|Z4>Lx7xXbG051-li
z<npWn2GrcFZLHAur^B?GS2b_)8J>vhM_*)I?U_tggIe2^`wgAYrs~ft4-AAoJT)l2
zzy5`jPhna6$%UBk%O_a6P%^g}J?*%09Z<;$s5HIy4iY0o>C(MoPrS6YukRk1aP4fV
zFN$P%nwX)8%D}LS&re+>jKmsfty^3jC7HDW{gN~XYJE~_iIV=6&*Vs$T-(G>gf_ca
za8ou@W~K{IjEP94OFT-p;*GK56+sTtv2sAXG2zGZu4=zzV9!Jhw3EHF`Lx%C8)431
z7>#j?;%yQLU#Ew1edwy<yS*`KD6sBn9a^LbZA7vofmJt@r-5{q$ey6i^<q8TSE}?J
zA5{;;4=3gE9_|zBWmJ<4WPscl(~4+^yfknHKPT80XF8lLNeice1<?G(434<4Z{*cG
z1P}e0`*>)-$j%ZF7F=G0ok<q*=nrv=_~%#czNWvaFh7V;J-EEl)1&yR;v$l_kA-2g
zQod5evbGRC;>9%eq#@52Hm|cST9J-t`$OD(W-9_r2wqxDmN7j@;9TDJNfXIijd4qK
zX?tonn??BimYQpJPP%|vDC7Cl6Ch}D#Pfq*tkP5?>~nF1#bL62fOwW9A5K;tkH?o?
zWr7-)PonDYZ25{?TP#`Gp5K|vL!Op&D4$sk1oCd**{IFU7WtikzFVafV{PKziTes4
zD{A&A>}0o~Mp<r3=6*AdM;>#ZfY%VnSUK33#i=HaINj<o&Jzr(ro}-%r)S`9TK9?#
z`UGn#(;)rq&z#kSfJG|~RZ;Uz7A=2XQC!oYO~knL1edrhmSE1|JlDI;h~5g?Tb8df
z?ZhiR1ZzD<mP@P2Zqj;#L{y2grlEtteTGOJQW;=y1kLVwC3#6yd>Aj)`f)g_rBlL~
zf>TI;b?vH_(6ZzS0Xxoo{gv!{K_ebBseJ;Blxj|?zhgjMcB9?3#`!{(wj9E)38%AZ
zyJB=@t++u;a&?){{tbN_%_svyl-p>s^6+lv>(2?<9`y-~LA9j0E1()u@GMYJe3jRl
zj4#M><HvDl?>nTvBQ$_skURuu4H+x`?VHQUZ!NjSrH?PaFSlFCgPs?R27o6Qq={+9
zEfQNdKJ%kIC*K``xur*pEDqi`xxXmEOghAi;IGRt%*_<C;;<W!Q@3f6s(G6&oLi!a
z0B9MH{s0;L&NNx|8fIJ^dghM5;!SoNI${W8ZkCJf7fI>)AcSxEP2{}c)X<J{@EU+?
zZ_M4=McHfZyTa%N)Gv@aIU{L2Q8SiaUy17VYqX7luV*EM#6D+RdmXmz<-tKhReavd
z6~EK<2>7)zk%2J1^*Fdj#q``ueXgA%W1sR}dWzrNIQZ}w@hzUr*qA7wZZj{(v=#9@
zI?+DW%TCz*HHN#?)1t;y;H$U)ipB05b?j5kDR{&MpJ|thnbn=K2fHVmQH%8YyzZFT
zQF>0!Z+Sdc(8q3<nlB2_rdkKP^e4h6&!3$%vkK<`G+Yy&sWbb3#pCQ?|70NXo<Fn%
z=lNjUPCdrHENF5>PyH}U$%8i2orsYgT;+%%YI)zPafw*0J?V38u?4^OlQU&LqMu4y
z+dM7ndKfL)zTQMS0bzN+%p{KGR6?4&)!?``t-A={CrZIPUO_N*PaP+iueH9_Zop1E
zf>_fjE+gg9d!(iQyKgeAmg80`Y!dV4Y9}b|?m7#rn%{S-wJUYZ8CGYw4a*eUeG<Z`
zk>y4YuRbVSt6{?8%&t$8h@yTi<M*G21M*}bL_ni*5^Gt&rF2yh(S6S;o)^N=4HP|<
zG#I4p)LN9)^}IgQpFYb@Hz`SXu9Zs!JO)!r45u4Q(AvD6{pqbPvtUI5ci)9%mwLVG
zcJ>YUHPsPMx`|L?+(LXX%0xJ{EIE$<c$@gJZ$%MZKX1@AcrZrNA3?Gz?_w{_uLCeJ
z(lg~>)x%~8kC!+n^-URb>#wGaIy`x1lGK&+E+aeTXZ^%<s{O6HNg8k?Z=Jp2IQfrL
z1dP>zpJ?yI5MYX;0d+7|X|DrHLeiiCnpN@4-99PUs3jM(VN-&T^*eJNhq4uTMv`kA
zBe1Ze$r%S*={{us?ee0A96X{U%?!Innz@u?^aa@otx$CcG*Ob{;}OVqQ0<eG(8xL1
z%bWMMZ+gA^2V}W{xPfsbZ6D9lI)l_eoV0+h8we^$;rMZ^XZK_Oh2Nq;2IWEA4gfC9
z_e&3G<-+Cp)LGtQ4rLU_JiJ6TYiVia`V9AWY$sw+V8AUem9Q}BB-6`!mSTh*_s|EU
z2%)0`9~-$J>-zec-DaDuPp7(3wKWo>JuwQ{VO<9w%kLS-nuCZjGPAt3r$l}!)Zqme
zP!AW#hmB>;cN;MSBFNNJcQ9&(>fKo~T2zDnF*=X8J$^G}{kK#(K5H{^d_a{<Nbof)
zndAt+HyH?AW`&a!GTk_HlpH+4^J11X5-~)G3@kEmAP*bxm)FKz*|d;QNdxU)EVG9t
zF{&b(C8QB?RO9*;Gu=yAy4$`BRG(B-8$en<N^yZ?2HMk;BYO+nf&y<Bv+p-wPB#>0
zS~;2}3{us4AxayGtjU%3@m+rwd_DvTjG8|iv_m?ZdntFg9*(opXa5Xy8}l1;{0A^p
z{GBDz08Z$FA6IRB>7al5Xtc~u2tMo!+w&KAqF>?G?l}F`J;BCD2yKRs+~lKS6;gk@
zFc7qd0a1zfHFgYfjZQP<%yr;K9|NV|9R!T|$ef2zit5czx&kLeqR~rtb6?-rt{gEt
zfZ6j_`FvIsXY^{WT9P1F3=5)Fd)~c}HX^0L*RD=}rlVuVuQE4g`&!M8EHVqX(&*#7
zjE!wqhIX8sxiJT9V*}WCXIQ%^F_bv7>8Xqkt>6*c#^RuXY^)L}b74UwM~`%78g4b=
z&{UqS$&{;S1=Z|3+Gft0oYEJF9{HY<rY$WGkNWZMf?na3r|a?{0_AR&SzlzIy*nQ%
zV@L{t5{=<u?PL(5C7F1dwrSqvm}>Y~Hj>n%2t{Q6`pwT(8*WYj!vL%IaGFDbUHa_^
zOBAhm2wzaKH9sWckguM$q1d%F_K$qd#nZ`*<(DAS*4Z*<fgDI^XWIks@2TZHO04M$
zV%8r<X$lU@{rR`MOfM0SO7Z^zUIqKUctG|bNVeW5;NXT_C{k`tyH7@XOeIw%{1~r6
zkr>s?sWD|U@`V1TJex2WNM<GKAzOq@=Q08IZjA-iX@kWIBUP<vmqj&;5<4mp2~nFT
zM~A_+yqRFxEZ?>-Z3k9se6wrkzZCHU^4xMbA_j5JDrqUFadEF-X2=@Eqn{0+O|?GB
z#ZDvrg0k6m>v2P;X)Py9s=L$!HagxvMvpu$F^t)|xCt?rewMcY%Is6_ZIe2(IZi8n
zfLUnW?aSCTN2E{9@140Lt-~eX4wQ0*;xRxWOg8NyFipzSF%WIiGN6Z%CsC?0`@!|u
zKLBf)iaN<Z0LP!qzgM2>KZ`L)RHnjq+17k!!4p`sz_`c7%6z&~suovzbiK*zrXQkc
zsqbkS;(U_%g8gjHjJ%V$f--aUtkJ_fN0!E0!t(9DpleGUscJptV?Irg))!|+43R{|
z#PqF0i#Gx2`>gmus2qyyWM}uo);n>kvDLLIK7Qvn;R;g6yl#3TYYPRyrGv!3$SD3H
zXK|Z1U&CIcJ$jG1>6vMoL{u+XsK#sf&eBZ*oaz*iyl2{*gg;f8c>(l!c)FCNt(bWp
zq+GyGGU*>6^R~9k@6yMMWaHsa8JIynSG#3AC7TR$d<Z9l`iXphnwP7_Y1-e#u+{^|
zG$nB&rKnIgH#>L%I<hY8Z|)r%%jf(b^qL2{P4vcn|LVzNt&P2RbM2_%N)*T7H0mu{
z@<gW*k8oE-D}UkhWg3v$SXYF0G>l92N^c+q-ikWW;|phjf4m&d4X^UuOwix6;TIrz
zouAP@Z~tk7(LllP0#9C1R(ZjJH0ue88aWfvl}{)(n%DsJ8bThVuVq31StnwDYaY=O
zUA?ia>%8U1=mvkbFWlt!yZob)+=~N6nz}tL!sQfhqbUv7>4s+VZsjAU42-h`sY7>h
zVop%W-&8zle3p+8fA?!l&UdYyko1FL*ab}Y^5o_}8k)+9-X0WUoTTk#G{8;%;h1^8
z@p!%M-J3Q@%MIb6_}k0Bk+A#9A+c$SLEDl8DN%CE*7DJ%7BjXod{++#>^5ns14H2#
z&a#(-R0Y&xW~SqtO?BUWe;{pUJq@j-E-33ap*yL+H5E1@Q0(y+max3KZCr<RY36T8
zfycxzMr`Xo0t{BI--CW}-Xe^p*=sR43wF)psS%RKa19Kj5X}>+YHKiJ!qt}jv3hr#
zfZ;+nbBD%Z8Jl`SQL$eoxJw7?d@~6FL{7fWi4D#TemsFt-72o4OBgR3KXxgQHhe18
z1DC0~^_HcG?v-YMRRvvVo{D!x!U3^6TsKwe9hv_CES?<Ri<nD`U;~eFO2MCM4lST2
z&J04?U+OG3KCFtb{IRBD^+RPjOUZJDJS*Ro*mt;sK5IM~&^5x=c|~WLfW>*AG{i1W
z9A_(?mjAtWnIh%d{e=N+Yq`(oNnhH~v7V|1<9^temDVcqMfLSeu0=z9Z`vcMFh~zf
zE=^ki8qiQu#t|*$bTdCZOZqv1lv1M;R0W@xEKa2j9cfeM&6Sx_O94WO6SBA>{!Bp@
zi<{F`cMI;}8>o&0^CN`myMR|;ZjC8YGmYzh234Btw5K&h9Kg`LI;2v+DXmvIU|1KT
zEe<sOhVeX2x6heHE4ii%g>vR9Ib5t$g~*ijesN=eO(qC2!k)d^q$$}`9K6pc9yS;*
zIXY1~>IaC9;MDz@q{PA;MF%jOwj;%)4op0h8u?#?<$qhcQ_0Q%+A#r6NIy$~N<~>@
zn9D55|4ftqOO*aEOIRyPM-3nmZ?u-^O#Z<L3X-1C#^n&8j0wk?kDt=?)lF$F2Rey?
z#Q=fDT{OjFgpWCWFqNHmJRc3Eic-TNijR^&JfcTBFnpRZ#>celQ;I}TYoqBzZY%<j
ztS{!HIc0p6{s1p2F_9R}22}P;4M4j~=>+30!BP(@iZ>KOAt~(=X92AR7wSC01%N3H
zTOMvKXB;S2QSxNhnTFWsF+qsp_lV`p)F>E0=D+Ak*o7N~6aaA0;-~wS6xc=d3t-}?
zA22-3quT%HrK$K@iT1xN?X31A26r7$x~rD5%eX3&j|hI4P3u$mO>mtR$+xEm){Zit
zSz9wPV}Dy3t76Nx!TeYuMYejq;-#NIRkS8YCCRoR5<>{-EboA6YWA9W&PB+5mU|a=
z0KD|zmmwZZ2h2$}_ff8{ybOA99jjimkDz%||J{Tn_kF338^5=%++s`R2^!e?NhFT#
zuJ+a}CWWv4<%#y7eCW(PUuZ>C@r$4OG2%!&-#j$2nQowD!5mF_mJpDDmeEaSUzFaF
z+OBOiJY-HIqs7UEQtXf#ul2H;VL60!w|?)(Q?XV*1A+KB2xSoAgTbaP7@@w#o~g6o
zt(*AD(Hmls=YpFk;(DCT2|HtL`Jg9yTA?or3Jum#<Sva2j$t8}Z`-Nqjw1{wYxv;5
zcYaw@cJVzVp+c*C>R90BAHX8p|4)uzmA6$%^Bt#dl94e_>oHqOovvCVAVZ$_Cn4z!
z@%>scbgs27)}WP|;%q5-R+4l0<W2LAZ}d3|Xh2oM%PC9q)v+P*e3dKd*%)hecmOb1
zd@krqPaa9q_lZhNn_&JZX)Q_YFusP<q;R^mVN0Y<gM1Hj$AB`K_Rn{0H*CgrpT9O7
z?WFc6Wj_&@HD6$DFQ%I1pI~nFZWx5?_k*JhHN8nm$q-hp5u1*dSOl$XRHj)lML(e%
z84nEuNto%qIlG{)4UL&;RxC0>`L7jynEZC@hj(X~InTySO~yRhl8AqRE_%D#y*17`
zzc71O;nl%WZw{0hHVhlNnpjvO4c%GW7&pCQC;Qg0$cSR&Y8&%k<2%#2foVD=noHwZ
z60g6|-d^UHoDY8#)VYKma$Rn{GUUdsML>`OTuQo(#;Mpc8>l26a)ocE42s9^FKc1N
zVzW<|yiGtcn6#J;;liQpw13ZM|M<s$b=A@|rufx!VZ#I9jiaz2GcuC7uT{zkEsVvB
z5uN_BD<b7LTzAY@@wF*tA6;Qs{Z**n_mg|s_8XW<oFv`_jW^FsMR{wSvH54I=aQSy
z=-Q<%+B-zQ^Zpu5*Yr9yr!!ZRXKLS%Q8UhQ4S8vVw4ueX^)vO35=$fkdH2YiK0s3v
zya(I0)#At~apK56=8_shP`6ngD$BW@U!PcRd&~Uw*SdW4L`{B$u}bc1?yH!6Q>nn!
z8#6z_sa8JFsg)NX$JdCPlT){bF_6L>QP7-Ata*=N=9*?sL7MEzz($X#6BW<USc!dR
zp6Ob=uH+h&2paE)UN{plAK_-Jn)dUF$y0DN7XqAnHdH@bl{io%4`rJ2h)yaP3vv8>
zIz0k9{pKoT+aUK3@B$LO!WJMCYM#@xf)e*3a%jFq>^Og!BciOSb!3@Q;;25s-LGP0
zL`1FCF53>CeZ01>1^h94ZDyy_79ekNjmRfk?mN#N?{)%;TFx3_XN-FNXd5#<Pt;;N
ztBEo+N%%}?9F@q&vby1ZM8i0ys!fO>smkc>Ie=M=&U-=zk3U?O{6!}UNm{WG#3ypk
zGN~zm)y^f=soIt4u8pYC{pl%_zr`OJG%NoctRN<O#jV7CDb8@#eqYXP=xaPo^i(S_
z=i+A8?l67vMxhK2CLp+~EJUVy2M8WQOp20^`8=L)rs&#q^;;$BwgG4<pI^fRy@zmi
zc}=b<rzu#!1U#2smUo%{?pZ-B^!ysXB9<-ZY|o6%-k(+%jG<i{hJ&S12+a<qO@#7k
z3<ju2Xj7-OQ5c?jERgbNCh$A&hT7uas%gX!KuUVcI6%FAJ60?WTk4TjCW_ZNZ*%N@
zyN|rfnGo5v64U3R4e{~QR;F};V_dep*%A-h5+K%pvn^ibrOqPcrAgur&((A{)0F!M
z_LIr7Fb!|Z!U>#G#k1GfRqlP_YJ4P4P(i|KiY}L*QrG1b6WG;i?tRCe>DKt5Woq{p
zY=rK{%M5jSJTkv}&PlRelf3oL&qs=}a$n$2gqO?lXs&k3D7g1UO&*i?Q!`vuG72Gi
zzFk%v+rQ$En9ru*xvi5feRIJ;_N_2B4f?s{(d?Ze?vv()BV!`N%keN?0<1)r5K?EF
z2K_^CdT1;=P!vmBWOn)ypu7?XAxRkvRS{5@Obiz9C|e%k4~7!B2O9k`mt^RdF;^+D
zLGu@n<VM=xN6i=2e#1*pUOVP9^J>s1g?ux^Ezu@5C+Sk6+M`(Arxqd<SQF`cKcZsY
zj4WLpIP_#o;P`va5K|N4tF_p{@Q}=^(XZx>l`-^Zem<qhMt35^3@wbY5sc4Xe#w>D
zs=gx@zSVAaE7X^)6E7XT2<PbxQ`0_M_Y)^wa~&klIn%KHks&B!+*5#STK+n)Am_65
z;6RZSCuz@U(5E|n1ESS?qDao0b7n@>ZP;4ULs{Uf_}CLqvew$9#M>oWvuItYwiPo3
z5)Yj6#tynJyV^;={F^>aMA>8g$5`K48UXa<45x%7Ubaopl<l&H_XHLIQu5MYfXK87
zr3&8U>+|@mHEk&mWXx6;;Nm8gYNwiT!lc9~UukSgkC8@9$c4EUy+r8OMx~9hP>4`@
z{s2jd?cTzlq3N=poaMRBeE}&2G9cJL8}}^r8)-=QQu#do#G2}Af60=UTYOVK7=gW=
z9x%XXioAJ|bv;FhYCEuItb16_cb%Dellbr%{8{N$Co-~P?E_3QFi!T?aP#rro+%ff
z7d4F&TbJu6?jwN_Z!4;aR~@(2m;<QK>`7+!?n$Uw2}_Amn#Bvrv{}yyuvs;-WMz9W
zKIiJlvYC%QRfAV0V*u@69cQVNZ=~Nb@96wCJ2LtTuH~CH@g6kb!0x=L@8S6&BG4?a
zI80!Z_3%0A2QwUlrl{$-6Hd+h#ZunyWg1kFt{4xLFYjxwHzwj*p4BB*2NG;ve@6Y`
zkbPL`bPBGpENN>^;`q1Y6K&RG_Jk!(Sv_DoRs4Y$?eZ#1lyOpxRE7_qNsyD~JeBSE
z`id+mF+<diIaOe3Oh!tbcKsMf>MNHPY#pnF0*OP@B~Lat^V9LF5>dtjF}CB@&5IgO
z^AsY|5`~ZjUzd%_(oci4Kh5J>F9=?izCQRP=Uvx@%y9U)%N8h>x}cQfKi5&X+LUnx
zZ>>71kUjm%eF^u7@dEuaZ!Y~9OBh_P+5v;rx7kvQ!4s>c#E$WjiR9*11vlv37T4Up
z(WWFB2V*a!hhcGo4tDyxCK4@~9h?5in?--j`9x8ye-Eipt})AjaY>_!^6D-ff5Axz
zCmIXF&q{3mVn@ck*!hqi`7YPE-J2@=7&j$;FCq<T*K#TQ&#_WRrdbi!UwI$Z%jG<{
zEC#TThwV)z&(Z8wme=Bkb1akcU@E4!(+ni!JkcY5w3Y5e0g!%G1F^z<nvHk{n95VJ
z=`cK5T1q?uN-SFZ<jd<yiQP4rx_o5>EyGmKOk9DlE-sEZD@kC<%7LEaF7&mwH<_z4
zPKzO)Dp^QKvW7fd6(4i2Yt!Lsh;|aEN8-?EFr`mcyiZI{IniqK_HOD)8~)_=qY4(b
z*OcbMZzt!?`vKCFfK=D2Iw)B^`mw!5redsM1yTaLgL-9er;Z%hXsg5YCkERTKyS2m
z&#NQ?pIDKxd5^!_s}!tZ9C_AzS>x>c%}#f`u_e(`V%)}ex@lwPCo-ENGS^4nO}so)
z!&D9%<5;>i`_YDSoi52m`E0uUZgKCn;^R64V?woD;^#{&0(;QG`uXm0I_5?arx*f+
z+cJ7c#=FFKt#JnyVCP=$Tb5k-`~K^2{fR()5O0pT5wH8JuAIAh_qz~Dm1SgnwC`u(
zI<GI~UHm?HknoV-Rar*Gnwm6lTMJrTKSUty>>i!*c%UBN2gVjV#J&;Ai#EYQJ{YSi
zJ=Ul#Q8CYjI1GND`q>UG^XJd3n3m6qY3dY|wsUah#tI1vTw9rW&J<K*wBw_>XGLc-
zXusGOl@HpjeJqGy0@Q6F%h_Bj?1%|od22L)Y7>YuD^^_9(7$5g&YoZf?M6{R`@zOL
zZ!{~O1X*vW4*or@g5`F4!~%WyEV+Bc{na>YfG^}fKS$QkKcvl9iHdoR|Jt@4D76GJ
zh{U%b6lB{tli3Gr$lhzaG#S?IFEH=-Vsr@B_3bdNY`q*ms@$;G&%vycBrkctmcOkR
zyhw{Tnbls#`_w|JLNx^MNe(s6Kk-$rAq@#N7d2ydEAxgJksCEU2BAh^2@}kLVjF}N
z{)$NrHs9;yUDC)cWZ=xoyvXwtyFnRKi_{|vp}22!hb9}zW2jE8qYol|A_N3T<Ch)A
zNOQ4*+$g?rUdiO_!IkOa)D=R5##rF1NA1O#?8+L0ikIR{M}7D{uCy&I6H<HTlp~sr
zPkhgv&cs>2^_>#AX6YyF7(P>wtw&I|kdrzl2%n7U*7|@%^2Ra(>na5{GKKV7WgpaB
zA1l*PW6?PgoK}ooPDgDiK7DyOyBf<g^9xk6|Ac46gYBftbzhm~kxV^M18f`O^`f9P
zVMW^b+9IGP(XHdts=V#e!YtN3Jnx(L^H~K=eFp~8wi^AN4UDW#Vb^-@0HHQ~>ywl%
zbTDfS)6vN$F=_+neK5>L(oLdbHhykx9se=Ka4$aRsrBnO3-{bzr-sRzPRSSZJW;vW
zgucCAd^-xikWckm9xt9W-Re&KyZDrj@0#(#NR2<7N*&L@u>?Xa>?0w)Z(hp7S9GlB
z!4enl`0Z|{rdc~1%E2{js`odLsIC5C3Z}BFE_66tUUtkUA6-w9dENr-4TEbI5_Tw#
zDab~WPU4Vu&d+Bt<@>D&Qa@g(#g8>AvK$@3?H|~hkcXqKjyBBbvzTH_JrC-Zm%k-A
zJSEp;@S_?Z^Nqj%kzgQN*~Yg0)h)Z8Emb(_3&Pw&OLsFshOXeE%4tDtCQyi8CAm8T
zURs(=S8s~}g0g>zUXP!v+-{krWCNsv3wPRXtZ&1GH=5!N1(}1cpU?c}(NUfPSroVU
ze8vqyh#Lo@%brBvxX)EYsb@2Snw|O8DNz?rDQMtGp!A0*_UN#o($<Lk+`GF=D%>Zd
zzXs92Z!0T4Lb>nvgml8N5R~yKCfPZ+px@|3NL21zF?&U{Pfx^hk#39%ebKPwsl2OO
z{tM5*7^XRWGrZQTBSTT){h-RaYW<q{pOE>Q?B4?x5|oJp4QVI#zMy##t5_nIZ}kT!
zDp;qV!b=8@tI&U@8?-N8%QpH;yUul-vwp}eIm2X?hN}hA4v+Fm=#pQ^$EBjHaxSLp
zcA8VybSZAleVtj)>C~~pkL7vka}|b<@wvU1_Vz&RFdV3*Jub;c4O?SHm5)nYTPqc1
z3jO;O6N-lu(0B<|6E>}#zivd{m5~?w@*9fHJU1ZM==<r$TE}xoVnfoUisF|IBGKQ5
z^0QLVW-&>xxsv5a*Q{Mb=xQ|I1^R^Xq&D5Gbnq?d`N^vXo=y~vku624|5PV6hg$d@
z@&2OHasF$&Zr93PnkvRFF&%ON?5(iv`#zEraiaZQ=CO_z>``(vB(ilvAl}rVv4bb^
zjGW@vQk9I}_Ub5!gxI+gm5Px@V@7HBD}nr*K%f>5Ynq<oKL8syL7AR)lzNON%}7{k
zC?A+A{RL~rZw*1wG3TXUpwjbVOLfaI9lJ{Ptqc#prN@UxxBDL_nsR>Ed^bF`Q!DxO
zN$jHLWxKvxT4!C?bPd=lDH9lK?o<?1Qd$vX`eHy7wkB+&=KCp3;#7Z#pUHM6snk}F
zbtvs^R%p-`jt%2wzFP+Dafu|Tf0i7i(XARU{p(rbz&Cyu$;@TWEo2~XXeJyKe^9ad
z0N2v#mWT{Bm0}m!lpj!6Q<J9H^@U8gm2C~gk)r)6=UQWEsTOk_8|_;sR);pF;nnE0
zRNn(t7x~5U{Sk{*vg6VWbGh7|)B~H~r+Cl6iIQgTqU^7q73u9$wDlh7enmcFVHuEF
zH%mPf12qNhs)weg@W}DzWsnr1MF~IuV8p(zPIGPZSUrO+Phl(GrkLP)K4L;XCW+%e
zF&Iy7Cpk--1=4@1Sjk8RSH5;@NOUgM8{A*}_C@H!fbJK-zK+RxcYJ`<W`&J?_&WD*
zgbk~u;C1JxuP(PfGEk3)<B!ml4?u>?q_m^y%G|I`dj6xjE}t;hpF~%WEcQPgNe|4S
zbm!c1_2-x6#$*I#N!>C+bJh2iXRN7kw|LL`SwYY3ti9N`(yVw@+8QO}iUFUT=``53
zIja(kfo=XY<h5t7fB%{DTaMbs3fp(Kdct$x??UH-;}lqmEkG&TxK3)o*+dD@$1|KB
z@CZLhEHS+Y&o_%Q8FX<=%h7qU)ru8E0sh<@+4|CZ`Ui?A{9ULwW?TfEnBFE9L4o#7
z+Ov4~e71Y2oSgmyVnyA+tJJ!S-8o~~oq2wiQJl=1Cqkxh#oy%E=*6+PRnPC^Yg*&5
zSY8uqf?y%a7x>CsbnN&Rj9^K%QgxJl;47Rwg1MDN<EtxxEi=s~Si?WF{{xWneVuIT
zYiTi#*9_yW)(SM3VL^IKsY*(k%e&cOHJFM&i8nlEi*Ggnz$#M5`V_nYCU=ks%Rj1X
zewGusA@dQhrH2r@F~cj0;@G*E<`k{to!&sdG>XAAHQSI!xR}hsxDB%4y(umhsN^w6
z)$kDG0{b!a>@@5^R6XOkd=$F4|JaFf;J1vMW^>ujeh-uD;K1^0DFA6WP*18QcFc3N
z3aE>4GyG(LbV|$Ghsx&74G828AcR`G?{a?n_}V;LmM9G5nCs<ug#FQg!LNLThFD#A
zK!`7|utYZ|j*SMVR5j$Xw+fh8oD%`7{{H;JdRk2Ju_nT37i|nPfr?BEnKF)P4yDh=
zr9vjnU;1yjX)<UyD$EG~BG4}6Zy%`cr;Tp1>;;^=L`<)_&YLlxoyp+D9}&QM+s{Hr
z&Rv>4F;h?sxjX`$lGqsmz@vSXcsW(%fRrIYU4hd}?geo!0kIu1&#7iS9gm;c84+RQ
zp{bz@T8wbMz{+_Jh6t!2zP*gK5LN>o&Al6tQZ?2qgXzTDBmz(#Pw|)1nh*#eTV=}N
z?ZfeIEw4aHl~?uyG`2~0N+`ndcz;ib9b-g4*^eJBrwhJBaBrO%jX_A551bNSuDRlB
zMQVKQ;;kWL6OZ-X7~@6%biAOSG#2~%^f7R&M5v~Bt`Vf<%IP<V$1~x{Qz0=^-|uG;
z;iE^}`+O>G1?Dmac+n+RD^<$AS>qy{<IfDTqths5ix-faVYqK%VHj^J=nfumtv1NU
znlMzeUQox93#V%=xIGG=kXLt8#aFv%=OKK_`<*?Lzh^5aXa4H!(bt_nW-{tC!YCa1
zJ>lpaGJzgdhI(2yWZ)-vjH&6k#PmIx%Or~F9BRdtHjjM4*+OhS21F$k&nGj)RArbS
zETkArHH>sr60{YY*xa(wPEawWzHJ`CrVN=EU+5_G7AwQOq8f5D$`{39%Yhw~_+fQJ
zBIVt3=U7sIHZsv14TxITed-=qklqkQPsIm_`?&<lf2*BOcQK~O^y6AIL&uwQGej+C
zD7jAAJZJ92)X^l;Xc?`^bZ36M>#NJAT3l|x-aoZsUOY|ONa+eLrSl^ipMJk4Ud}@;
z0#+UsUarAHs%f5S(0gFKcTJ-dd9&fx7c&UXpgpKFs)l<!blTkot1J^`J)L%9Bx*lP
znH+DCmp&Q&C7Ls@s)NyWnmgV{)Fhb*mtM3Ldo8;vJaZG*)ILp6Lp#svLrZ*GI0Q2*
zUC*|g>rp%$|MHE+wCos9%EaiZtA-0l#wP-<`hG3OrfH_<DczqGp^N=uiSiJu%r(0C
z6N5j3S)xwe-`so_etLa6UU^j7KxVf2XHpcp_+1X7O&N8qMYS)HkKJkD-7_IZ@#5|u
z;K6mR@gbjsMiSJ+G~D*L3F~KXQ0X$6w*vCgCcnpvthZ^^c0`yd8@u`FFU5__!ikmK
z*#5XP&UPJj4bdNB7@tm@=J}BWWG4FLm8H^p645evWNO_jkp63~i%R)kKo#cdwJaoy
zi@`mrQJTd6pArq1V!7!QEhsLF*yo){c^7Vu7?++u#)Q44_~C5=lu#cYXa4`w+y1xb
zFkyrtwq53bm6|agOmgC-t?VrJxgWRQ7p9-?nE9DC%o#;f+W$gZg+@JeQk`cu7HU^F
zGehZwBtWnnD6vjyP3PeOSoX9G`Z2gP*~embIgh!z09;BMAnVX+W55_AQ87*Nd<1^*
ziB3NUW9TGy9`}S;K7!F1%lT+6GjWzgSS!iZdMZT|_ZN5R5mXzWQBQz_Te<){k$YT?
z(HVf93)6+D;gF`|C{jW+u@lpQXHa}b?js#7#qX`9VmXt+7;zDnwsbKrFyj9f{zO9l
z7sJp~sLbU5Q+%Q)SQwcJ$cxN1tvTH2iXBO3Hg%BV4O0W?u*Z=&Y`uodq}d9bG55^}
zE(qYYXZqa+?n3wO^$LTUofAqk&f1#Z;V|GE9lK$ZMP-?*jLnM6$A8~3p?z>pogN%E
zmn+(Vurc{srVdMjr@J2YeI<LP{Q8-tCt~rwpKY5OJ>%(@gje=yN9_Djw5<;+;9W*m
zojsGczQsm02qfQEz;JZ@t*CvGQ^D-$^R3naR8#lY_n`o@e*nk&5R$dTS(lN!>XehU
z!Yts@1Timr=8kILc^1=UVm%Y_Ru~_VfgwNYUE=@|ig6Di1YU;!RJ=7LRsgRx((wy3
z1YT27wmf#<6MK?frjqV2#ajH@GT>x6l)<=rL|U(bS35R*Z`Q17z6EFgUi2(xT#v>5
zs`H_c+9kP`%%Uy`N{>)~#VNJf%pVZ$dkaPehpi&UDj&8~2Nd=g<|kq?VpIkZvTSgd
z7sz@NXG)whac3w|L!UJ4AhB+4YsR0wgMvNbsl8J-SqMxgHbHZ3-ESq2kJH|PqcO$W
zFzw?+i5N4zbNg7Tm?We+0?T=*m+JGzkB>5rpPcwTX?GlkxoIEUVlkZe<+IhHlu3DB
zcrx8_ZYYnnICIt2{Msm<BR(8j@Rz<y0ET|{7Wu(#iemT&xT<;{&j5z~DmvXNdm$oQ
z;*WEjGI3Guc4vlcvwufs{b#a@N7LCOmG)5qpjnCl`cd@=vaMO2^vlKLl>^%S{e<|8
zj(w_T7DY-P4n*5unubyU(OGJ}UK0u(>x%wxv@ICOfMwMpa%r>5E0(N`8wI|j8#2kb
z{h;PhC}$_V3~oJFqHKqzFinkls8xLTcUP{>G{4~!IhtjNTB|osFAc^U*i%&VY6)LL
z6CnuFMqjmyTG$2?OlQjO8KHQU4$a_(9%w<A@m|b+w)lkHlT{tAEOJO*Of%t~`Hx?r
z#Gj#-J!X{O!7xKuRKug3M*bA)q|l1L?5q8vQdJk<9Fhmo%-SFO;4<cZHYiAP&tXX-
zL1o2+b%@#8XY$lVQBE@HiUnOx_2Jh6{f`$(vU7?f0bby>W^gvmTt+|(#FUQDnR)kT
ztgAtDUu>eQ^_NB6Y0M`1s<hY-u`B5c0dY-`fk5H1fy#1e2ir^Dzv>M>Sw>V_7Hb|i
zx2O<KKEDVXC5K;gPlX12$3y`a6O%?2Q*XeUth=@EWK6UK=cRwSDRXGCjby@&+co$e
z=O+NM`;6>8383|DW{ST6ZziFm(Cv(vagEYf8jq7ix33ShK4O4*hA*C*jBC6Pfvz0~
z5s7kVkQut_d^{Q?$)Xr0E8KcV1+u2R)f1~0nfU?A=!s=oJTaY{Hl9p!t<0<<ua$<A
zUpp`dwqV25*V}f!$OgNMPG{K1Cv}QyMevIh`TQzBts1JRe&sDFx@Q@SkvTo{bm9BB
zkhxvD^)99YUFj~(G&{%`t7JADT$hWcYw8(2kLAqnowO%zAV+bHO8pPM-ZH4Iuz%ML
zQlL0AP~6?!o#Jl6DaC`kLy-a{4eqW1f<p;TOR?bYUbH}QYoYDC^X~KE?AiZ0=R;<a
zNhZmx_2F6T_uTh&0oBWpTYE(#rjX+anbIdn580$46q;hkRXa>EdK@4T4^7Ezs^VhF
zptLiOJ|q$u_T33~%In*q{wkHupAnl3wis-N2t=Axcls6y>ps8XSam|WrnM8M<g4Sa
z*-IXMoUiZU_V)Q@%)8P=R*K}NT^)l<8!Iy$H^|F)dxLRe)G%slHiO7`AVPiyOrJYV
zWL?YA)i@G61ZEKG0b<O!JrT8dAM?eLqFBpy&0`L^T{VL=*NV!?xo~C!=wr1lJzhAf
z4u0hSh9={#ert0fHt^Ji_S1|HCB>=h=k&opuEfY7Q74>(ycQ~Q**L90vUsK}$rHUi
zVLG*KvUg?KTYtLt96b9UYc6nb)oRKg$slO|Tv3&<Dxuv4!Cxl$K93@$_W63+COsZP
zM?Z*oZ0RozJ$OeHJ0EHE6&fK(<!nk*A#8j}!@l=a*~bG%8nIm64iA!KxM0XJpYbcC
z#m<6uV49bF2+AcaY<RUaQi8szK<Dx#faEr=zs%>1`bkJZW%QWZ=rYrkAz<ml;#q`)
zf}cEv+~aX<7N&;W*JKZH&g7E#M!KUdSN3Q$WQJ%(sf8Z-nu0imj`HAI1R2W2lr}<P
zru=Z0$Jatu)59tD=N1pCqLV!vzI2tzS;Bp-BeR+xV!{YrFUK#8B!BU4yP#Yk5w1Cz
zHg9=-H9RUHXFuD{3Tj3XsyAwso?KI3;@n(=7=zyLVOP0k83~i_4Aw9Z2^W@lww0{n
z6Yc?3rSnfIc>BIM3{-`!aMztFfdmv#>Pn!hVRpa0jeGKWx(twZWx0%C7{AnCWYC(N
zHg0Q5!k)(X4Q^Vf5t`pL4*YfXzV-;0igX_wUoNwA^tgdfP>u2%oCJ?mxQc5UTa-k>
zGT#NO_Md;HT}dautG#$TSN}UokvQ=7UGDE1w9aYHHvwGLw35}ipVe`nQBfr|x3pWo
zGc9~ZOLoe0qxb{dX+yLs){QoRT$ZMZqdT4JtyJwnK1?J!1*?z`(|iikZ&)nnD_NOR
z+!2hHi%S0&5KZnql^Z<ZL>C(WtqwrYIjlbUPsO|qqS45V8_b^XHk>DTW<jp}vp-Yc
z>}hdojdV(SEqi-SKjLV=0sKqXO<IyA|FEAY)Rfsz<VGj2`zf&cC8aT)@Omp$(tuo+
z@7Q`_tA#S~ZS}8Zl^<I0$vKh^TJD0D%t>tJWNNH#78S_qpT0WIv7aJP>3(gPnrplW
zXR=FYfjiQ>e~QPQ{^C~i+q=V$42G4fwm8!|@?L%*p55DOYBfCzS8=os{P4oZJ2;E&
z0|m1vAB;No1|YbeG>6E+a9f6mkz_dgKXhn`=r!NjhEiR6@UL4s2A&R<Hpv9t97<<+
zH^!<hlB=ha;TzMIp~8=)Y|C~oo<p@l^f6Mn)8c5R#~(8OjWvF?jFD`!Dn%PWRm*)z
zQmc=@yS^0W=Wn!-d2>$jlf2a--<Lw9ap<0PMl|r>vwOTmv*`+%a<IMSH*;VbF8UOt
zi?%ztQ)G07hig5l2K!7`y9}oAP?Z*YY4|E`#<k|A+1&?{iE;2;h`+$(8)=idW=Rrj
zFwB*Rx;^hfa~MUd(%{={rE`_EBt^j%gq%fwk^{$Y_^9(0s#1$lG6>wYVF4O=zE8?_
zVJ^)=0$VChUG%Uza6wO3dY0bJDV5MZ3j9^zP=}|U!qLY7``w93RFUF^pE9v5f!dMt
ztiiWS&3?WM@Wd^ZLY^#mJXglRE_JW>{tp+M$cag+^Gaup_$wWTW^obz<$}(+5zdc3
z?h6`6Q9kM+vNdQEvAX@(?VPn=+V=8fU7FE&b(ktm=-RHmI1M*YAV38*ppD!4^xP@<
z(&MmQY8G<F;4Xl%-p<g~Y>f8Uv){O$sN3&2Ov&=wr$zGIVtHkLwR#$s;VBksTn%b7
z!R0-WD>QQGX-&QD)9XHJ$?)C6X{Og(T<~{?vq|k^Mv7`i$lYbM7%Y5#rJc+4?z;)Y
zjrx5JN#j-rvwG*9D=GK~lX~0lHxLKx6wR;LskMeDf<OGsy=0dKJXtVAo*m6;F0(qQ
zsKQ#PCmh{Fk~;6nxSEqRN7N}V&9kp3fF;bd)it6Xu$zCLI*#vyRnEd()+RG1JK3Xk
zJLk_EXD*H%n5!<bk{v@5w^u3m5X?CNAIDf*9^))L&@uwPKi8oQ;To^k%XB35=|y!f
z_S!uzn|mmq0%4tKzo!*zkKXwKMoRZxFxFE`w!UNUx}Gm`jvxn3m~h+;e5_#JkXVVM
z@_0Y|38s6SB~OQ)VH3eDi3TGb^UMGXj|0;*z}FBJb1r2M|3BPmG0t%vs>3?|+4-&7
zW$gX#0gcXjX+JP;k<@%j(Bzn|I>b$tR}O}(TOG+uqj2|ngyAXmJNhTh-O#;SA<Ri>
z>BKA?|M6pZ9m&>^rwNGorK~G#=ohBaRFuz@i6y+kc668I6s<urBu)L!T3WaLOZ1o3
zkIICC%eAL+G~_rAZT5%z^3wiKptlKsG`u~@sXxwEZ{f?&kbT`_$-292Qx+z}$fOlC
zdloa9R?s~B{WGKva?qr`{C=I``P=VH0|GtF%xP>pjx4sxsnV}}>chr8T_o{}k1fLr
z`CoQ{S=igTx5~_aZrDx@Vw3lo43+7Y1dA0q&(#&qw811{`5XDWdatJm6=&|s4%Cz9
zpvQf3<0g`*6soHu=uTkW$8;7;yCtb!0juDZ>eQpJ8X4_o?JW9hOsXc2&?~K?+WqYh
zZ6aOO#}fU|pUzFwN41D^r6qr;!R&NuWGYK|)k@L32}r}hymNf4H<gYD{zv6O7KttH
zKXWBL>W%5*+&t%j<`};<-{a24a2V2I9WdoF*GMF@0qk0wJaY4=2C!B?R&OrrAf_f?
zd8%h+-dhiWmMcFAU)*&2WRVr8d3c)2#~GU&ID#t|8jrU8JebCQ>fP0zdsMY;%uasr
zxmixyS$o&<_l~87KG@q0`<$bvUCHOd&A~i4cO@>!E3hgL?P*E<LcCqf4n`<BI;=cv
z$^s6IO@3K}RV_sdV}7r5W`tzIi0A&bC^U#a6_<wn2QTf7^`jDd!rRUc`JNbnEMUZS
zu{)`;60N(#-#y|$G}FJ!FO7kDmMR>yz}Ua8@L08%-S1{;agxO7a!E<?9uK#hdA=b-
zE+~)R3JMt%&_rVu=WmcB-?{l$e4k-TvIbt!X0kmyil^rg9d_fQHqIDVq%r%hFhUf1
zE+XuK`R<bTox$2P=RYQEBBQqd0Mxo;XKX%*hvwSwWQM?F36^sWKKV?!{(ff$#ZRsT
zHRe?f`-=DG(m}Y(g()XQ6oHq_KU_b{5x%02^UoiNWz6jBIed?bL(lvhE~e;3LX)}u
z=S+o7gD^pHy`5H?f|sBbg<gTge#6{pA~N&y%5eV8f0+e@wi%@7Hy6N~pWy0npIwjR
z*&~>gvBB_>jwCY;ptDwSk0lu*QOfW0eM1J4D(D_m#ZBs6&6KIpL31oh{!01Z)lqTw
zB~v<Ximxk)<jmFx=b87*ewghGon%!tGCnjK5(6YjzCMZGA!tW4&(`#$>*Ke|+4wO(
znOL`WV^nihR^iNmw{N|R8t5VWvTAb-5y&4|6-V5Hs5&EMB>y>Ri^OO!E56uU`!Yu~
zl@XJ7Zq-IAq}3b9)KO6|*|B@EE?JXV$fEP9y`v#Sj#8{-z9_PR)N>=18|@(YaQEC%
zhDw9)Vmy`2?n`_d$X>lWr-qPD2&c+Q!_9{h1Uf0sD(E_}@9KUsIl!rreqI*(V0V#V
z2gj{Qjwy3XRGa8bGaY9RUp<QUz=xXezl9mQTKZ(Au@(8oQar#J7Ml221#5pY*NNJE
za<|3Q$40zG^tplYymu@b!=k!be@X$jttVoT6~`DS=G%gcc3(U7IK_!Bjq@93Huy-b
zdo<~`&bT5T4e{H<?BF5@bXhKmFLPg<^`$&SPw7Z{4G-T@ChEPtYLcXqJ0R%gIJ4f4
z771)-Xm<dO2!t(Xo+`FFxCCDe%->8-(UhEUiE||*j@yN@!aW?1`@*>Xrtbkf?LI;S
zP)^^|j!+q~ix=e%{tWh_^>?OtG;xS;$%?TnT@4L%)4Y1drX_@FcVuImHYzli2y45o
zRBWqI)6!qurVGxX<n^`kOriqc8&|M&VuhB;+}-Lqj@i6yg*?|@ZxhIcE$_?B=#L$X
zN4y%|qqls4dc1wQ+>mSjXx=^OHh7*P^~SgZ(<ndt2gy;lelo4vcxO_j#_N=Z0QmPh
zSxr4DOs}5t4#2WY3=Yor{^T9DsIRO?Jup)`e#Z(VvqH)A?SVTJ(X~NijtY~J)nr?Q
z?T_dAB_~b0B`pTby%(^jcBT)L0fla9^gxsS9#hEp4GOydC~+pQ>9<hqLs47?wcK}y
zPIP&Dx!(?ahu2kQ$EM7p&BUiGotLxfF(2N0wtsT0PbWt0gu+Rm4!<t2`o8bh<qlK$
z9Bpr|H$LP{KVMS2(NYqWE#{1tVA1F@Y@K|B8EDWbB;{YnXiNvh{gS2xP*ssTM#xzP
z8;En={@_%5t!sFw+*PQ6mt3AI0a&nZ9tt%MnF_!!crS9`*Xg%u;<0`At3(Kiq>d95
zo^Oj7ne*#s7Of~*{w$(gK*rt_I*(0pZmfP0lS5er4V#Z2t3uyJ)0+0v!9b4*E`1>%
z8ZSY2mw6cqX!41N!Y{3s&hypJZz4_Rr-dq)t!jxR;4UtQUOdD~Q&9T_m|qN_wOIPT
z@!{wNN2F2y!91!|Ex<1s$)zdUD_)&fMe1+8+IUJaqzQOC4nHB6w~toyTLmTlwxkes
z_+&8NlR-JGk^fHeu?+3K(#K%{!9qqfNK~uovvTxOH^-U5st%1nOQiHaQGCIIvxlq^
zX6(ZmHiY(Ac0Hq@a$i5;U^UFl{=_f~&w%_mdKg^@5wL@S?_k$*XGnHE8ydEJR4ME^
zgum<G7^KHdut4uO?C^zYXCM$K`25$BbQdO+X+~Bq^MvmW`SYVg+IsoIt7$eT>|#^V
z7J^qY+(6AzKeNXYZhDxPuJ7xT@#e;FTm6*vuCHJ5xkF&gA3#CgsHxd}hRIUH-PJ~(
z`7^)8w;O)Z9A2O2I?vIUn5b00=$jRb(+XfqQgtfS>mP{;^TH*9d?$o)9qFSW(eTMy
zj)R!#O)0-F*B&|+HhO6g$Jz<`^6w2gjUR40c4($6Wk3eX8BvD)Djf_U02{_8IpgYm
zqGnXA!tmk(JXpLq5cqslETo2d^N+1R47)?or20!+yDIpCMDX9zyRBa<I_>yO{KCoO
zQVY$r0um>hGl$R?gL~2An_q(_y*%yh<$@cBERaf(zhTC|8=W(~&U+w%7=69hSOs<;
zrhH3Oj+!t2gb@p=IlE4)DJ|uIzhlyDW(U3<UEXSp29t{obX}-d+X}$0343ai=Gb#c
zWYO<x{{vX<PC7f<Q&PVO5#3aKM@901UV&@2<6&C11_RoDRVi4rNx3l>=l{f(Ly#jl
z@`{}Sx0iu(TAu1Nt}T>mzF;xilCG`vC@VCelxj1IVZWxTq)(Tb?k@JXKDs^jnW8*L
zh0Lvb$gm(z@KNqyO6YrKMM?`>KdK+oKGB^ZozisBYQ?D@%-t=j6^@Nf6X7PV#oFOB
zqX#oY$19SPSmnfwK6U-NT5gn;f-TAhC-0D%v^8vD_cJ@9H9uH&a8DJ`GPHG<FIIdj
zreX*fDD*K*+-++IvxbYwRg>xN3|JH$NEiP$EiSLh=+7Zcm|9H4Xny;zk8u^%j4&lg
zH82jUu{hm&ixvFqPBaH@u3T*s!gCn&r!EchCVq9W^FUnNkZYvitwqXj_i9l**T7GI
zBCh8@YvW86drKSZLShg5f$^?I7KGzFNlNPj?=dBfF3n>-LwxiAwzt1=UpQEKSZH74
zMuj>YRd^U4cC!Re32|5_OyDQ{!!T{|r?t2r-#F<&*-|?{%t`~N?k9Y*=msi5SuK4n
zXV$7ER};fIo$p{mu_#Xw)@EeD+}a<~Ymr~V6JFTuek#NEQv*?4Y&yLeHcQ|ulF_&A
zuBX`7Tx{<xHrsyDeqS|xd=wrZ>_o9I)PGMa$tO@e&Er@ntKQDMduy~2&UF<5$6WoL
z@VA3qw8`r`KmOW(0PuNU#YgS=7E?L31g+jKuk`5<3Y4zM&!Ro@#Wm{*z4P1=LrL$b
z+nGc1z?uSN9Y_Z$HEb`#x5sdiZP6X&3txM8l`_0w9|0MmejdV)M09yvQCns!csA{R
zw6C#S{lmRkV8nir_RHAmpHaUE?s2wxIH2`YL7(y0#zmxjV#9`BOfeAQeJeZk>*plk
z?~A~Aa0$HX`vzR(V#sklm}r2UndHQ~UH<Fsd#R;Z-MM<?lU#vk?n%3#=Bw?Z_Ehp0
zli(rm@|1UqeV&^UTwf$hc>!7vaGX<cys1b5SfLb?2YI3qo2(;ExtG)im=$nAid?mk
zl@eHRlvkFbfM0<B>w)%i7$YC0Vi8opQ4#i(GS2*<&rL$tX1g#t`ZSBh!8Xt!m5NVg
zfs4yg9vufX_&>(}|NqYknDQ5I=krxvSd-3&`M`o&$%{iAlGS#p{353+jDqSaQmC4S
zY@5e^emWHQ#kerQaIZ)OLtWc0UlokpPKBTksvpG&YC)uo*ajn}=#w}rfVcxe6@d9P
zbq-<@_29jtOLg!^?Pr6M2JHWqU<$~g|A57d`rMy%u|>wM_F@{PG8))IU?TCrAlSoy
zyB^V6I<zOK&63I);Fmi<z_|*LFf*Q)Vb|~oIxEQOlmCJeNi!?JoTmAL5>{%5>Yx0-
zmYe@+!(kM8*#fSd%lACRT<wBk1E-d<0vZ(^;osb(&u?#l3z`SF1(HvOP6Z|Jhd>?=
zaPp!6bnQSSx5s9vQwi^2;bLjnf-*W9Hp3&Z8pe2wSL`w+&Xy4vcJv8bkj-UESi~6^
zo0}nGB&>@S)5wcD?gRg$yYt^Z4+?)~g*vlQsIwDAj8c`oo&zs8_({ka{@tsPs6%A!
zvGA8!1B7p=d^Qu^)v!KSZEsw*b;cMD#<8cnjfeYux3)Cvc{ZjZ%AzWo9z7jS_-^Gm
zwKXJsnYhi#>@n!(lYdu25U$p>c$W~J{wjia1Q`MAJ8jHw$#Bko`^$;jaho-bWo8Ok
zL6ARXDVk7R8M<Pyhqtluj7<McLL<ni=6ZaXf%z!<&D_o5g|oZ=2$ztWg{ctv291y=
zvb=Px_VZZ4OC~qUil+t#xCS&=z4S)mY0+03l4p*k14=hw3CC@GT^t%_^33gtc`1GV
zykt3<>P!1gF3Iq_`bg-)G8xTM10ajviRAm*rhSDkSD22jmg)<SMYTT)R59!Hh;0@3
z<X4j(RmyX2TGm%f(@Aa*CGE;0yuX)x;k*fck<xAr%G#EryF78i-)ddQ=coe}@Pb6A
zPx7bBs>8E8Cet3FP)HYBg-B;wKOwRfB+AL!{8C8I{m{yu=9tEir=WX*Kfv6fZFOAZ
zo-QlxxYgg8-fFSdlyXj)TWQ01Kj1Y9>!On+nHGrDRh9La$1jyzbN#R?#oMs+(p)#Q
zqGs~i@d5mC0}6_<O3jrGTZCcO-TJB+7Rhu@6RMM0O<Sg`@bu)SOc#)5dwqolPQCf{
z2#jUMq*`Nq-HsE*6}l+w<$?T)5Iv&CBGfSzXSIT+8I50{r~Zxp1D+GAzzWZI$xXY5
zIpPa({Z&|fP4e-ZV%mNES|k0GgeOsh8cp)2=>9u0>)eEc#esB-=rFE{{A4ZXOiw5}
zwn2Uz3(DPQ)39dsuHBp4q?8KOk90S_nlP}omLb2;ckB~3(qp*kiEv{xC)|5EI-{&>
zh#^whnw=K^@=RY~3>mt}k{Th)1+8$)uhBdtc_H&&>Z=#uk1M}nkYzi-!I{P%_N*)&
z9);^`ie*VYKe^NOvCmq|i-lm{4Q+O*fWz7&NOiYel1%AnPb1h<wodkgoW>$iYT=?^
zn{d-)v;*z1il<^KR>YU1rWxK3+|OIk2o-L$5)Z5qmOEOm?Vo;6CX)QS?2nc$mxjtx
z>Ue||2<<Yq{&Y2^q%6Raf#<VdjN*M|HpuCBC~i7+{7r9%Oz6^jzaW#{Ux_I>^WKa&
znowiNSq$1yIcHb$r3I$yO<Ub9KL$+cb)Suj(g!}m1(V8wi+z|rNe+W8l}k9yQQqS7
z?E5T?mI^N)y1BHrzg)Aq^jGz{B@{LY!OgIF7nLz9ahTF1k>b=F>G@+YJ3=SQp1vS@
z%G`O<R?Ib*a9Z;LPUqAQx;xXh6UM*RSXqF0>I#8}>_z4&?i}QKMse;hjjB`iYgnQe
zM6)k~jIYx7WjUc)OIq)IbW9{+h6&QGIB=%uk_$1lKK4?aS|SUd_K5x_&98)6(v9cW
z&_LHBqRc?8sEE*IzK9Qw)RJuS{`SkY8n0Im=mmIWxl7acc07SG5h`}pBTbCqX+K?0
z#&u4G3P!D4!KZUsKl}{ry<DYM)L*rzQHL$^phNV%yZ&-kUX<c|I~EOHAKLU~QF&m4
zL!I-#+Ft*L*$C|ZcczSA@)IZF$i4YYZ%eLt&n1Rrg|dOeqYST8$@njL{!L0!zbSK_
z(+lyud!1Imo5Vj7d$pV9R^uBM?7E>VigcspXjrm8LNwg(>;LvPp>}Aup|b-l8lRI(
zArmqyYV|fF?IS|fVcvj7X9|kOang*W1FYiWY;kP&mJdaG6EoY7jn$e%W=2Hg@}F87
znZ$9FF=C`w>|t&XW1cNm?<h?hC59y%57d89eJ3W$d?6Q86@NJi;P(6BCL2IaUG}lP
z3u!Ehx6zW}|B7Pt=RmcRr$5(onQcGKE#&+C23|1xtrF&Dkf7pn_XMYNwruM;U!VG=
zxy6AJC&mS!xHeROMEK1!?^daxMz%p)>~g~?IS+4MM^pqi)jXJ|Y6st-*%98vzr9Bn
zFQg`Kagg~|bX+?}^EdP4K9AgEOC7cnV)2NGu%h{xO(vO}lshlHg#_*6<(a;fg*D?V
zWETrYOaj7sAvDLYAz3SlrJm!2i;z%7?AAcN99;26^)lMZ*Yzp&jPKHpYkUVUYiJVf
zf=JU7Q_N}StRpBxsu#+PuexI~&V{WE;`h)t>fyr`9Q{@c4Kuak^}u4=BNF)<e66wg
zSn6{L!Yl@<Nb1ASbX51!Dn;UT1?QvWJeSNQu^VIrMa9r}3^dZx402dQ|A~_9&Nq`&
z<8leDmCDolg5#PwE71>*Qd6>1H5E^Ei8^h4K<M_e95{Yyikq^W<CXU(XBy3H21aVs
zT@O#j-lL`8yM~1<R|wiThMg{kbmxGlDvI3aRuFr=E*(Kg=QoL}a!l<*c;_f^uU77i
z3N?HY>_o~K?&ljp=L(HbxqKjvL+FAW!fDxY=WybY8k+Ah+!g&xI`!{72fD-txXxv;
z4+KSb4M2(2&DB$znHijl$Tr_2v*Z?MOQFX%wXFnAMsA7aV3?4)w{Kr9d8A-5C*@UJ
ze?1ark|ri1lHk=|v+YxOZ4H}@_K0)>oL{)bf9`yy8Bi!~rafJJ`q0tJk&#7*m@zC7
zX=Kxp4w=tL=1kLI5eokr)W@Y3x24VUL}Ox3YE4?1&anB~XM`Z&$tjC!q*5%1-@qoE
zA@RV}$rkObIO`-7u;Eb4{sOR{4`vX!*HD4YnqwJ1Ug}$g=wSUQp*%P3H7D&2Tda$a
zHWkL4Jc#*&Ypdohb`NiRP9r!786}uq3}VNInV65aV@Z?}{`+$@fwMNF>z2AqJ<;JV
zMp2w)dHz}Td$t<gMrZxT^HFbxA3<f<e3E?VZkl$whU^rBByj(qkB+PyYQz3oZfGVn
zbbN9!A6}e!wE;F$g`yDau4ytRusp{OhI<T1T}DQJZYfFPMlu4hyA&_~H`EEO4qa%C
zMjus;=16iG;h-o8gy;<v3t%(FLNHNZe&-o7thRUu!^WPke3>}5hmy-@HUkIz&Q#(#
zJO#BDjW`DjjR3=#B)TJDHQ)y(PkK#I8hl)E3X|VRVTe?0lO)Y#lWx-(#fpvU>CqP%
zMPo*du`NK*Su~o+wjpsADsPZTPngk?rKgX=Fdigw^U27>GC&iUF&`}?lj`bnn8}HI
zz~9G^;tf3PNc{?oa+{I=bI*LDtx;rln_-0b?9UP@N|N&KC)iA-{K#aiUv6<aLH38S
zbWo@fb<n=P(4vxwe9ybKCrHWUyV+agh6@@wq>VJm8EEB2>mOcw5heyIHO5)c2T%(-
zy~`*piIEGpS@Iy?Kj$HP5I2cA2)#KYV~%vfRj5m1HvmpnLGgR>8N;lDs`r*}v|mMT
zNk`dXv>IP>inwyQUQID@xL>Cey{grE*^vkngnI_4VjboFh7|n_vmW-tTCy+kvAk)+
z3NQPfd8vdW>pImp-@N)KlqzCSjVFnwqIl%<QHQ^MN7g;iOy#6h4Ya-$!7aMyPcbHU
z1oJRB-}}AGqee+X)%aBJTllx=k*<Gkd|-fBl{1}#I}N#<RT=b;>|<Cl7-Mk67kO8!
zQMQ_7ANXAr{4<^;M?#dd+a($YP|XJO;NT3Q+kOAZL)<4zZi|aO2QO2%8mm102>jY@
zbXd*aV&0{Fz9Y}`fb%CxK^5fgQMvl9S=Dd7(D8LMftu6XEI<9R$1XTy#)Oxv$Kc4!
zjWfOG98;QD@oM*~C0asL=ueRd4U7GshMkT9&(+JFjEtrrs{<O;QpWW&H`%l>c}eJ_
z&|_j-P+RZqyQJ`{pNJWUrk2OXT(|cwiR8A!NQKR1;Bolz!3HGXH%x%Z)MzOLX8V%C
z@KcCjk24*DweRzcKoSKv&3)~x!|c?DbzL9B5gM{IBj4D0*uN361?~y&rhnrNZyDdU
z|DCl8sCQ;*Q!p()VgKZA;QkH?Y+3z%;I*4y>gZxs_`Q1>7WX~VgR?U^3%Z%!&9tAP
z-C=d1vrkLls8>C}!Uiy1E#`K5n6w&F(j485{Z{J(&Pgj8c;hMc%0##Ia0!Yeo}fAF
z@<yfZ`xZWxPmvHxiNnM$q(63{%JctN59~f`sjx-bxRr|)!<f5Tme|?=nYX+tK7T~#
zEnLNN1SxF?1CM$KHuSq&b>Qhy_E-(;r_slxBO{b(&qYbv@P}8?8?LXxulYXaQZ`0j
z4v{c8v=0j1_;OMAMV>HXS*oPH927V=Gs3x`8ACIceExzc1V6qYT^gxffrO97bTl|O
zuR*MY1ZO<&1=~W5BEKgi8i$Fiu|>K9BrzKJwh~SZSs<$PK%A(uwAO=#r0(xzB@?Q)
zc*RTJmK$7oRB!uDI9ZZf1vH-*J}sKEM-Wudd1SV3ziaPIk~>!z5lO2^qjfM!z!y*f
zyL@5$G8=x-ZtRd5Kgh3a?A2Jgcu#rhWJ0Q`$mkXdA+TW?o~UWrk)c1$OP2po%yl4D
zsmE~J@X(=iviw;IzgSRnZZ{ke%XMtz<w00l$<jqDhG4yj2IGgVFe3Z>0#{l$#OxxP
z&Mb`1h-#FY$3Dw-4XZIEes9iJe9pWTJOPzuYrWla7wnWJFkWcn7daAA6<1rZCF`Kw
zYOmlbSVh_K&J5^3X1ji}45{y!91lJv<oYmY$r3gQr{B6X++0-#zW*^ie!s5c*xg-{
z7l?|2YBm;-G|<7E+@ZWP?jX#o4VDzXLls%H%6xY2=Th;oW#0a*18&p>duTT*T}8?I
zQ0}OV|Mv9B78mZGh6<v)(4YImBPR=d>xD1%MLdU+2N0bLVitJ5WkxhXWJ-Hm%<SB8
z_adX(@F>eZYa!+;7VY^iQz7S1F4%z)wU{{*w*8AM(SzR=(QD%*rwPoGw&eWH^}F_&
zx`kQGKD;i#OWud<W}lR~Lx}|~mowO4SOfK?wzhN#AtmlpUj;Vwb&t)1v=bBDHfU(t
zshhcfgrHe0cLkldMILXjH+suB{c0fGPgxjXvhPB7?@8T)J)T$?z*H48MN@PEBwS1%
zXw>$>G?>jF`{IPb*U0O+x2_S_@~w8xocjxT#HcJ)Wsc69@374+U#_9R?5j87UsE4_
zLqvPs<3XL#W&IGIk_Hwn&eOPvB+V<!9-3{jOIP*n@z=;A5vZ&LaMOq)#4mdU$RAon
zk^{$lf`oTGq>kVz=!SV6)fHI)zIL_${<`5hHQ)J(D;ar+>UbGaINF$db4wz$5+$tD
zQdH`)w;fs%vh7g$h-YHfFz0Of`xfNCt0^^b^+2QfMeK1JLeRp8AT^D}HdcR(#*Om5
zFx^t1mSQ&ZLSfRi<%9rxsV9f&vq(Yqi+BShbDGh~HtRDDI>#)jR9F33k;(--Ki{&G
z{NSvyw8|FRmkum-<(U9Z_S9F=X0Hvu{JBU)xnD`9)E*M`aHzdXOTD~<u*#O)(?xov
zn@xz8R5-r$AyWI=dW2Vf^5HTn^r<RRoH?FIud-^&2aLw6^Qo-6{{XIKdebK8(0pG6
zr44`YVKp!7j3Uep5qG|AqPSU7cmGUe5AuKTI_EG~C9|S;{SoK<ndHaQd1Fewh2W=g
z<qqncC)12G@|$(5kT-QNF0wX*6U^f7E;;QChxVH^_YO_-Xh*I7x^Zf4Qwfp5zd;_W
zDI(n={(*+t3N+5ka5O*NVnMO_Ja=cddh1QaWHX}h$68X$0#&q>sU2W{OUsyu7;~7;
z67_`H=bl;IKA+mjN|u&FIyBK4r4+gm#eOol=+7JycY(P70Nf<&H$#@9=2W&JyY{lR
zdV<XI()dK7Fvp;FF>^v9*QNl8tPK}{sVI#|;U!b59#dNaEf?*ts#jBt$oW2{gm_V=
zl04zHI8#i!Vl$|Hg9uw_<VQa{ZUc=GRc>Zw`XAh9^N0k>qc(>3-}B`%OGfoM(6;YL
ze$TBZ_r2!=D9-$v4S~tz<CHoGN32h$g@{&j429p-KhV(KMO8~V2_t3e_*LhFT&JXK
zkl3_S{^+8CBkLWQFG<FsuT<i7KSe9ji@Tyww)^wBFO$K9Y9c>r7R+|T=F#FdQxlW6
z+#;7n;@6A=WHQVQINhS5H{9jeBpjE~7DLlY9b0yxxZ{wkO=}UCNE4ZS9h>I~s3IL+
zNuS<=2LYm)f1-nBfhFLWxMRLceN)+A%NK20C!j+sceIh(bhEXaooq&y#TB8t)izVJ
z<!(db9emeV%xbJqx89{kz^LWd8+j{}e`<V;(dV9r?>>0wSz=@*{_*}Rmveio{zB)v
z7z&}<)$ktx@#%~QWqUhXRYsJs8HkE&gR`p;t25`w9d+rh4lB#CFC+I6-KS*x#}G=j
zaFd0F9=A_HR(dM#GvZp<yCU;R#W%C(JuZkg)JRpw!6YFzHb2!NALdtMvG&Gh&oM<-
z*eu9~pVH;$c`=Cg<=%(*fDl|cuS~ilxV0NOxlUrEQP87eqoHzx8(ue9TYa_PX31`4
z;JUs5=A1PHvR5G8{5AX*@16UFp5Z=4Z3<r>ynUr$OnDS<*dO$yEf9_HNpby3TU&Fk
zO(;i%n@1r#nZ*ArDL;)k|04-Tk7`aq7Q2-uv(gV5{&pn*IH^>t=Ar?Z`}9x}O90ok
z0teoPNPlB911(|1sR@*0giAYYAqwL}9V-rL5o{AtV<R75h^@<kR-o!?)=!{g3t(xc
zw{SNaSn$wDOKEA~ywKvs)%RNfhWbI?y8d9nnPT%fnWEUAHHxBqIMc>T4l@k=7aw!o
zbd9E2P$dD8q+ip|#}o+yqL@f^b0<{wXU`2{UcZQktx^Uo7E5E@KN8j5m4CPYu&lJ3
zJ%a6L{-o_P)uovnOj|d55&7Dc3R=+URi32&&4kQL=a-3xZKX!7;Bh$v{fwxoqCHgF
zPz;3JI$Q6m8nkf-S>;$f2wtry?sV^+o_d+^N4Y7je2XOe{5As>BX(e|wMwv`YJeq-
zV}v>c&S<86$Z&iYZ*E4k3(da|b{BEeyQlJKeg19Nh&QCm90v@;HKkIU%1;>l3Oo}Z
zF!MhVJ7#E&`*Umh^9ycp)px}_y9D+MiQn(Jp73`xX8j+ksJm9@J7;JSzg~v!Qul!*
zX1w!6TfDAbsh|pws$jWXvL8p_k7wF!N|C?IcYWJSu>a7z2wjZ{-a9w+yvO{dIeREl
zV5cVOh}8u2Tg;dFBH)6q&eP^5_$fkeOYrX^nPhLgd>1KEX>IXa1b@!CIv)KxPvi+8
zf-|W`JP23zl%9p^xK~GX7*P;Wlu7E7p@VZm_sf~imVLe80seB7?C2lW*RNsM`18Ga
zGd8PDYVksIoLs6AE@%xh$TIYT=SLK4^g{&K`bLe+!T`rEu7Uyi(BEVGdr^jVo8Y=&
zp#6FjgPFp)E=h`JE;n6FF=ODrR|>?Kl(3B{GxC|jE6yDU`=vO537#5l?QWaFm@B?M
z=kLNufBb4KkcFiLQi%Q7gl+k*z&m{6V-8(|0^uJHT;wku$Ial&!H2b-5S(wwZL*Y*
zYrnzeYIHAQR7I5!+lnD8;iVpV>$7RzR=C$fM$p>%K`P;|dab6UN3Y?A#N#r1m8gd_
zr(cKtFtL`DJ_h=v@c#e;uKk9@DT$FZk;we9uIm+umoL?S0235HGR=r;YW_coQXD4=
zFBoNOroqy)3{07J1uOH#QvVySB=CQ2JpA7q5&z?LB@+ssq`-kfGy(qS{2d6$tz;@X
z*NAdK6WmVE0S1(Uh>!9)^+fXa^6;ey!NSEZ(_mrkD0Z2-OB6%Oh&ZqUXrFI^3B=IQ
zQl@BY+ni5sgD8JiI7-jNRl!qpeevHPVJzk2rG=xxu%hGm5v+V*e5tu712xK0yW>K`
zyQ=xvVZi@0iT~dp{y+Z}RunGSJ%Ay?t?-(!q2@>Pr%zs7W@CqMYZ|$3_cCubMBdvQ
zhwrBTi3Gw}X(u;R6jwyW=53!XQiLh6WbSMHOUS{YgCF;DS$1xxQbhNIzOeT!GCH`m
zb8ViVK_<lKnd?}fjYX7%3ue7<j9xj<TSm(&R!#+9#{FZmTDQUxH5FDx;{F=J?h7Tp
zu1Y+78MzpzSJtptzO=w}bkK^k&!ZE9orI|FT*_3=a<k9+c4=LO*e9UV5qryaXg&U?
zl+JC$(@W+oC&NcNw=lzexwed&9WJZqbM-aR<6f4IE!+4t?pLYU*%jLT5}-=te*m@}
zw&M-A60$grgxgpB8p-Cw#p6B(y#*UhqB+YK?TdlVwZZfwOqOq(PYt7atgvMXT!Isj
z`e0|rGL1?kvkcKlZ@O$bpQ>JiaY^{)S+QiplBtJ2LOS|d+@$Ag{5r=TItcFu`VVp1
zj`nXFdY;WC<aWFzHZ)jcse2)34m>{@ar;3aw<qad&ZWkEW}&2OfPP5(g9h@lv_-KR
zLmT;B7ckFDipz<uX`veZKha)sG0<W_DQ-|c4EDkCf)%H3yQKh$T3PL%?JgVN?h$=t
zj(_Lou9sieHNKKD6<GRNK#~_V&xRmmi?aof-0#ng_T<+BaLAX^EhB#Atk5lOf!DLz
z;VwC1^H?Ct-Mgk7n`>P)`SJEUJ>cfajotd5`oYL-#Fs3RAx_U|u?U8JUy@GveUog@
z^@o4-*GiVIL2jZIDZQ^>L?Wh$5~=c$hdm)lNj)toBVDpi50=&Gdx5tssn_}2!YPW9
zViAlUegucDR*DSi?9^EaJ|+PXk_c`}2Cew$Ra*(lzg#)7a~Xr=j0uxW`oRwkn-QFS
zbn%~zgNtET71m*Ji<jpI%8wcnQ+}^e)l3;vr#)r+uYYSS)84AJjke;fMLGR=d1hz`
z7Wbvm%Us`n;-upqJv2A1$w1jv8MIqu2;CO{acg+;m8&Pd0+`3}A6oGz{E-gYD^mVB
zi$S9`F={HB`J;pPWy^Xv$5m&cT!SA4*D(%-KiS!9DU-NG0^qWDcN$a(x2|mUOG>pG
zSf~s~@Q9&bKEd@f+!e3dTy|k(h7{WJ_B$P-8`P#hQz*yivfS<2#}oKqw=KrbLWe;9
z<~&2f0_EhE8bm!@!KFbcMvDM<LXhN{nW@cH8h>h^;;{5sw(1(bq2}MfnkmIsRys0)
z52rTf6kH8qkApJ_D^#Kh8%_>xT~R!(_>g@65QOav&Ae!yza^-3QKWEWDE)?yTS#lP
z2?HAqz*2rOEtmD9gskdo`k@EwLiQ5ck%HnD>Z)4yY=RD*kQ=PF_JgH=<V_*f>b!@_
z{e3SsD~q%`K^tVcBkq$upm<5-suiC;N9G`~F>t|=Eg&={D!`0Y(b3*Vs`WU)_pv)*
zDkJxz+{FP<D7Bw5(oIXWN8VR%r4WB#jW9iAIZkN^ef-o*@4UZ-jyK`<v7(Uge7|Ur
zmfLLZ1L70yOtHtd%)3n5ZG@9##fM$up4#Dmx$7*K&e9cH^y8X^%SO$<*pXRN9M*9Y
zNpjST-{=-c3Ok1l$3SOB*!u{z&&{)%L5xVOQk~Ok2{=n?pk}BP{)G*q{1vxw;j^)>
zP)HrAZAP<?zEFBdtrCeEO*>ccmTAR5GV;xU3R@nD6Wu{pAwf^6*?(={nQH&+V>~bJ
z^Jw=HM`lJv+w%x<8N9MDdxB&Oz<ev|?M=zwxLi%NL2~?GsHCe{7j)o4<0VJySTh<_
z&2>ZP(Xlp}S@_gzeOvruhg~i<W<lXYZIiO6Cl^A1-o>lNBiffW*GO5gp$1c`j5``#
zg=n3!nEMEBLTXbafgTU>_}7qV+B2F{p={7<><UJM=6Y<m2ZyQbuuftN!R*ayjpQSl
zF(BgPB1AgHB76HqRv#zSK|hgD3b%PzwLrgcaf2yNcPIC0$tf-C^PeBKYTf$YXmb4^
zL{agN!Ksl@<G@$U?F$t6SiW4tlRv2&Un7)RW;zl1LP&<jV2LVjIf1PR*Q>nTfYF+D
z5&Lvkz8ALIYMhU?fd(>R9|w)B_maGk#fvI3o;cWaQA>=OYu+On6xCg(8Od$Cc^0-}
zf|o}8?h6Ju62mg2l9g!rR_KJ_Qe3aR_Eb_9X!XTjgKG1nSm*CLnekuyx0T{TO@NdJ
zLSE=nhIX;a-|;fJqnb?%>kV|L4{`U{B4;|9!DEEaNZT-zo%5uMW0_E@l29qM^z8Xf
z=ZO)uCg6RHTOc<R+0$cPf^poz7&IlI4om%#>4g<JZDK{Swf^KiR5*MMiEvq$ZLMM?
z$oP92V>ao6hjCw9t{{&~b@WPnKT{mj#Ii0`&KiPhcAG|HD}g&+af@A#gc;XH3@MM=
zz1K|M{rxF9VLj$|#fx~Kj33-4)My6Z9S_nVP|hh-X1zL>1@OMrwIx?fVSl|{h4CWz
zOlRiIAmfJ%<rF{~TLu*ONdq{3h9@C=Jzs;x)K(t={%%`uYD=qTk+;==<xl+$@MkAW
zg@I)^5<&lve7#5oam&WofO-20zQW3&oY8b&m^%FTlUd@YMU7SjgI-R}iMj9R@r@Em
z(Rz+Ybho%-u($>#h_-tXecfoz&ro5$zEFMtx^D6U$?{KhwkWEyU8ogKAN<f5Gct1R
z5r}B>BGT@xpBnNzu?EHZ`Ovni-AKJaPA(R7@r)_+@ZRuEhvN3pHHP;JOrVmfS%+OY
z1bt**vhtVNR3(wJCuZqph!D!JK{x~(;4_Q4DcVIveiE~i>DGCP^A)_9?Y7y=ql%1C
zS+D@FW`5|TeUiE6?Q-4b`XJ9+mQwh6vYXT1Hg%6kM46+(a#vSnK!F#f#kfAF5Jy@1
z%OGd&6I1)lb7l&;%zl}nX+cf(B)?(Xzkjh*0$kYQVpK7TgZH}D_JUXI;MlV(4mR?v
zW}VFIHCq;zTO&grJF81ZnWg89G=&SpG?tpQ+e-?C%S-2JpHKzsN3yJ&6@T0}ly;#;
z!}1~@ZkO8>*uXC-4h(dda*=?SaHS}&&ND-9KZt@x@jzPVAF%Kghx;8c$`efSypX%Q
zpuWk0R_doIQBhi1g*l+juW7(fM)(r8ak*TH$A#b9WRY0mv3Y-~YY+|H%S=^!3u9np
zMlWcuW@bx$BMaWdQ9uFThSg1N$C%GFNLe<b@<_gJNMPlDoWWkteQ%L%2G!Niat{K|
z0?xJVaWmFon;Yl{yMd+Rv{+m!i3e736l6SnZ-n#H9GJJGfMOK?jQ1&+4@4kuAR54<
zPm{a$a#>VrT+k2f9q5f~-}v(zm;~rP7<ZYuPX@1wZH5mbG)Oyb#g>z+T})p!MGn9>
zCif5Ji)dCXh|SW6txbNT$dWIOC^w##qJ#TiIL`D59uc~U957AQg`lF}2>j;W2wm0C
z`HfNdZNNjdNO714`(cFvF$;unGE&sm^|jA%t2l1wh>F0;7QUJf{IyOhT3=M15~ogp
z?>+&yc%zQk?ALWwOB87GGxDkT)tQNjLr0#C%B~TH>W`<Z2(C}0vZp~s?27SYHJTS?
zfH4?~HdVhjRG5$O`8I4K1NvBrU0gViBA)UQ0Y_N*yg4ZMMdG9Al2zriWGiPpT^Tq>
zQWKm-(0Z1$OfgvYMP98s=%WiFfd%mKxJ`7089yx%qL+hY439<%FMFaPNr~(*+P`1{
z^)m&)H2C0qsF8xq4X08*mH?@a#(Zj%h&~E>x9g`)C^ffuzZb<qaSxjoG&rWH#(*fX
zfR15|+7H7b?VR!2`G8;(cFe_%rPtK&rRoXH36qHNd!J@8nU5r4jvG@9{qCTV4BH$x
zZppV^u6bHnR+aV{v3d&UZNJ?y!a#9Hh3}kP4%Gm6jp+kqQesZ4D9ux%aWl=g&y3>S
ze$XXdEn;8lZA3>6h8G5KjD&SUeES|)VQ|lO6o?}m3>Qza2+tO(**Quo`fQRXcxkcu
za%3RHvuy;o0VzsMQAffw?tKCDS<XOTYQ><Ch0iOQc?;gvk?%?9j-*k9h8Z2_Q&<Kb
zILgI$6=dC!=yJ=n@I;)BZw|Ww6PfBTqADM1=WVdPQqdsErne!?JHSPUM|2^qhnquN
zA$7Ve>#aoAM0tz%*}~Afn$0Mm!u&Y~ntIpCcfGA)RAt4x%SG7^9is;jBM=#MjhV?P
zI@L{0#U6P2vVSYTLW-i2y+!tiMwPC8IK4%6Ep2ku6Kl3uCaM`$n1gC7+og=&v6WHn
znkfM{!%)uix=+<bpNIkHklckY-|a2HOkHENT$zm|0wv?H)^{xIK4@^89e$*;aT}Eo
zw5RLr9!_$rAtGlC)1y5>zpJARWEGA<qa0R!XB(JyKE*=Rc7IgOLZ`<(UzR#`F2-i&
z^G9yU&W)ujZgICnSv7};A7^z<Vnp_I<Bjowf1}eqUZKfS#y9V?*tVdW*SOyO^sZ<8
z4d@k<Fm>c4x6q14`yxfmIdyWRk+t!$zoC=G1XZ%J$(hFYtne!LR|^pTCrXIlEA7KD
zL9(KN>R!^H=HkxV_2moyMT}xE`e;2YPOp8ZRtq=-@no&9ZfvEFtBr4+Hf&XAh+*sI
ziIQuRvZg;Uldq~_FZ!8?1HMJCM}VV+Hn6v4Pro5<GL9Mk5@4{u8l9MMDxq{d)tJ$D
zli5}w?q`>~m+f2E4NUhlpQcrJOl&Cr9yC&!rqA0p7c)filaRp0LX#oae|^i(^3g)2
z{-MMTqNen^^uV~fjMal}cFb#qFGAN%?&jfU`+K<{2gNkkNDlmO+RBtYqI=hw>}v#B
zG0blJZRREPf;ZL-L4L0+`D~h%N!dIe%;hTS{|W54b;}_`i%{S0tKR@7=(`?RRBFHG
zF-d7~+6NJBQIST_i~Z!?;Jt7w$mV2p*NkIn?B<ST7TBx|jkP+0Qx|D;kSfyt2Qbs;
z|E?OPN>lzBkl29C-k(ZA9lW(u?CGcwJ_%+DGLwcf$j(ytwaMPrYr%Fo#Qf5TTVAnn
zv(&+RV!-0jiOr6^(C51ovpJCwN0563jkgpC8fuZ&$1)L#h>e1@B2z=gP~F;Mw7U9}
zSFP%row6qrvRyWB<@yZ`T~z(}7N&GRX7EX18qfH64pOjXbClb@^#%mah$;zhi-R_x
zf4R);QVZ$l>x-akicq68&9oD>Hew{g7Mq2t@p^(n<^Tjq4|A%>UOrO&O&0p-3M{~o
z#wc9Oeo)=huj!Jv==9fWKWs@+1T`>Fg?Wv#JTHk2$uYjKuFm13VqTC1&rUu+{>u`{
zhgk8at6DaTy6Ij0oi6{aK_&7ZKwwsPx^>4=e_YW1EM!h_<21XZN5W_4i)+i3bNbib
zMa>eO^6VA00zEtX#l^<3MlNUIQZ6&q-u%(J>h=fwva?}>LY9`u>(O_sd~Q8qVQ#RO
z+zt=6ZhU822t*deZUx<!EMkbd^9zpm0_PaCUGR6eYWjq3enxF^M@HxeM18}~A0JXO
zU!9xG_+)L*JG~Wr?TuB4;m!{HeZd+ppXV)Gn?A+^jg0&f3$s9XPOP>~NDdL1c$WCC
z&0!mHW;e17{^#?GBs#;uRZO{#t|-M`Yuz6s%O#iIVtI~gQKQ{sd|v`^<znf;Tj-$w
zgLhS^dZKWt%Np%#0JwUPBAblwm_6`xsLMHCry@>fsb=k<-LNrtL{K**d@}x{Geu(<
zf{}7$&&rlyq)FLcGGRLRC;e6xCdrpW1qy$-r<a9UVCT2HDYpktq0Hy6QS>!cmX>2a
z0x7|Cuq5-i&;2OsC!(7s^76<_7a<7uK>ETCoQCHpm&Ps-XsS7XEz%=iScM5A+6Nga
z@AlxFU5EmIPlMFQOUvO+2VZmRDk{qm1HEej7|9E(fV!1X#NnniODaj>F37iQ>(;*(
zeMpcSV;WFRh6z1R3GJd?>di(C_78$E`b+@c>Sx=nnNh7d!XlBD(n7^Ui)rhX)qj0!
zXg`~f{DyxLYIIdd-gh@VS95->iB%u+u+MLPJOW@SHOk_Yy1tYKG&9j#G$`$pht(v^
z^oA|fcx~mR>&l+l?WlVgj+trq$^E!AzbxDO#{7~5B>2as&9|{sKRqyQ?BMvW_NVT}
z*DT8(4JN%UwnJGn|5}4)UqzAnZk!G`ulL@i8w&F^GJjU#e^xpI6TfM^uBpAUnR40b
z&dUmGYLGfQZ``D5)R@sW^3i@{YN#PNvR`7g^qy~*SX^+*1y92f`obpkU{Rc;fORt6
zu{O1TJp}ZdXCuL)?0EA{@Tgo>wbWqTMhnq$g}9#2$;>-ra@u1p-^fU_VjVf@5Egef
zIYh;~cL<Y8tBf&=R@<)37h2x2v~kKLy6ej>dY621x}ETR+iJWi9iQq6T=ch+H4XD?
zrV$ea+n<&*GN|YhCf{bK6=3qpHZpL33cmiKKCH;>*f;E<^TUw%3wEEfOk>)ie#;%4
zP%qRo_^|=YStQ5#@F%v-9o#EG7+_UHJ66|!yC4a#keCie(JqA-{>b698Z5?Pv$em+
z9lm-L<6e+JZy%93Y7@qf9p>2GOC^+=--{xTddZer90Aq?0($M|Gp;K)UvP|;I{4w2
z)xNR4h0JDL<d>TsKa{>KP3hCsmE~llXA4{S2*lTq&=I-4D@~U814m<d)_+a&UegU~
z6n&KMf^MnY?)VP@^YLwem=Z30=Zi?A_DJ>95|o0TQOVg)<B<6<IapZN?d%{9PE8aB
zQ1|BoothAe59-XiB*E|$JYz-BE@@>@Bfp{Y!}3-PL11faJlW`}TkG+CW9UdTuL}|o
z<7a7_V>dok^mUmej%*t2i<!e-Z8RnHbdQkLly;F!3`Q+9`k|zAep;>K>3u)XP62Xx
zdri7u`DD3%68{$4z^3@=3Y(>tA4o(OE=aqt^;*21GA}l3nC+d%)C=7UkSCpaFW9~i
z#PJMkzpHnImy0$b!enK{ix_SNQ)9ZidKGJ3dF)%EY9zFJ+tq772)Gj)9Yg57q>(Jk
zf290fdX&&cB<dUNl3jNci~Wvlq}6|_VP0E4bh8i_emHIsh0!Sb44a#MdmD;=Kw`l~
zD6iRE1Nb4Ad2fYpG_V`3K!B%bki6JSNPzW5FE<T>B@3$Dh^u10U^QR~Jo}*JdLZRl
z;g`a$+vVk3;BsgS8VSu;k{oStxN7>yDxo9oT71a_$qmLH%D8fFZO8ti^}kqqtDv^t
z@NGAETdcIWy99Ul;_mJm+#L!<3c($M7k6k01Z#13f)p$6?$-Xk{P)?m+4IfpgPg3%
z(Mr}k?|Sd&zAild>L#u)2l<;pkVf&pnKkEy`}~wqOIrT{-em=6p}!1hfB)=7zxvl{
zudNqxZMEq3D-0%iHu?{LfyVTPwUHDwle|WsUZlxwBuL4<;FeRL7^ihCuh<yedMO!s
zigA8h>o@#AoFHd8%2ZHv+m8r^7iQq!e3^qu*7AUUgY0<c{?5N&(EKFuFNxyV{c=wY
z-RZOZ$qk_Y0UT))=#?eDKvojImK%Sk-zmAYZ|KLp_jzEf@81;uj`jQ{+1B_laknmb
z9_#zBE9-)u@#LNrC%2o1{m^xJIrT#P%U4-+jP&1Sk~;<f>p$FlsFMH@R(9YYO0@*)
zq^NphBE`tvIHE(SuDs~{mxv1~LhRG8<=hQ+?%Ts#s)HQ!iflA#GC}j|JMj7YxwGOo
z_xGg^P^H#%$`(LRt@;YfBfd{D`dO(P=yj)?nCVdsz{if}t^H<K{QZ1%OPSB`VmR#z
z^9r!1CFPD<=jRB<h9?+M8*!wpYh9O9KNB*?Ol6#S;qxf*dX-%LZBynWQ@KDW&&oAV
z8{rllVVFxMb|kcU$iCm1KOji;yi({-vBhk$IrWwzdk%}N1l3J~9IGb0G>m7s2!)T#
zodd5L<sxaR&qK4C8vY4&{s$N?k1u+F72`S*_LD=zVzVy<_ni-3iV`5FJx>DQ+(V@!
z!v`w75FP&%H$tvZQ7ub}ED+lc6<@4GMXgdDDCO_b4kDxIl#K0?_4yoJtrGcnaZo2q
zWxVLF?MK_fBq7StNfDW&esL}*E%C|CyW!5q+N~4I&vRPMhu#(<p@}(ZDs2nZ+r7A#
zVLqoA(2Wq6xsvI0veBam!?w?474DDs-&2x3&26*jI*=xnTch&PDO*l4Oc1fk01?Uq
zH@$DB=g!5)wV1&fRmA4u2jTSInqP8bP{5ZrqidUj6^?tDiFqbV4LL244A?!t(&Dj~
zu~AuS-o*!}i(IF&eck8%oae+SI&b0Orb^3pMI#52jj%c=xn}LK&1rLmpb*G<)xWD@
zlq4s{C42{4;hpvh)+~KELJvwJR9Rl3Ag1qdzurRy1il>bV;;99RDNKl4EHa_-g5dX
zO#VF6ECYDznXYc|SYPAW9a$G1{A3Oy!a6${q$zTll_N;C`oEut{~rkrN|06|2!W+S
zrQR=4D;3%fr$Bu1e>=AM|B87^>uEM;ApjYnGQRdnzPsWWzPWeWfn^lHgk^+L-LXP(
z!x2Hx(wYkgF&Cp<s2nL`lMK=%m!YS4o~SIQN~hnJHU{xNYht6ox}Imjs{08EGpzAS
zGc!1jgD4bph*r2@Jw>zBxhS8ueR$|0X1t2pG@k=R7Iqnyq2mo^rWl@8yHF{zL1^RC
z`RpU&<@g{na6<#Cq97iiIJ~5aVEChA;O1@FB$LjW8p5D1L08uFezx<;i-UxBFi>rF
z<t!=lwy@I1F4RT)nm$#5&g00OWrxg+bYoj@e#q9Gm}XPox5RhCE>xXhH(+|iL!9MG
zeQMdSLh+3a;_V)=E|2E%JrOZF4b6UNeoCb*_9gJ!zMstVEmW4Ir(8&3f1Tbzw6u)_
z^u~oGm4#cH**~=OnZG{kx^yKg2d&^#y*}%dD5O~-Cv=hn)P?I#SCN?vdVYrwM?lV8
zev%w#`;B^K*VK*S^mR*;{<*9Sx6)0z{}1r+-E|9B+DyHq5wt>D_i?PbY6k-vq{~&q
z{m{nnWAdVlsv4xfJ5B6sv17cy9`&JB-E)4W8)cyAJzdO4R3HPJNK!x}SJzJ>19Vfg
zX;Ei3)lzIa7@dtq#9bb|IpT71RAS+bl57SYah{K&XqvR&MWwK?s`%3c7S7h?Z9cw*
zOK$ua9a2HdlATy~SKFuCWqd4A=`f=m5uudCvRpr=sD68;h|bcZ3!z7ZY|{VN|0psy
zjrwf*k?DE)b|*V`A?smz-0+Jq#zu!oN%hfUP+}*;uG4r@C6rG!8E3JP{m#{CdwW?Z
zws5CjJITFi=&&j+vMBYWY3Y?AK3yQ$BmKR{tgTN2@E>cAouflU>Qa)NjrND`3FT~D
z)MM4fktoDtU0t6qufZL}sqVzO1<cP+5?S!;a%TnX?m#VfQwaBcEw+2fmp*TDz8kIs
zt{-c~L~(I9I$g)v+9&M&eQGT00<eGVYyF1)^bTd(cq67^`*(p^7x(G_U4oUI0X%Fj
zYm%Y1DidAGvp?8C7~wfmN8q}Cz_2zGvSlB_zEwRY4?jB{HnK-=cebIBFR4NN?Skc;
z$&<lipkQBrV%-<MtVURccNW1>A^sJX1nsPKy8^l<H*M0Sh0un@xTnYU#O8>Ju<`Qc
z*95m$&d}KV?v@6WTEB<7Ogk2@@A_Y7wU>=12FqI$m+#oxD~v&YB4Inu&iH`*lz4Dx
z;!O9Cq&>fs<2SvNMnZI`_AQ;pgw&SfDPFkc-jrOB`&EU^I@gKl2rNM?o5k;9TH8-z
ztX0gd@lz4Q(|DUK_xw}NMflcmA0_>nI`2&3#2BaTc4L>xk!v$mHU5c2YLbHp!*k(-
zdYA6rRMjL2KN9zP*GKn0W6rqK++WZY%v<t-HS4DPkZV7RQz+e|$yR@TK!LltRI~9f
z0Ad!ZvCQ39MVv~5XBzlTKKI0eeT?bSzGmDmXk3IFZ5|Oe<Y`@HtSrC~)=3z#9?cZ)
zmho^FaPCmWy`=35Wsq~*`Cd_%y-VTU`lKf|iUSi#qiOP%Uj0y1_K`QO=~Hm5_}fO&
z!X8=PPk}&B$kcatO?e-@oNWh`N}VHhBnNs)8Q{W7AmJmqeesXz4Y5?yJ(8Q1Of(JF
zGZRwA=2|24)*nC9i1&8vy?|X;-#?H@Q%KjitzvTc6}ID>4O_SIakSLtGB~&wteta0
zrt(x^@>|~er%;w18oQJZ+zvI6N)?Or^@rg~3SeLZ9Yi3T?w`>=`uW7V6UuGapbN*-
z@(-$h0=_(mcn+#IsRJJs#f`R=)H;l`In<?uq;D&`L3H7L4)uJ~DhFqlwOGQlo&!rK
zwN5tEWyM*)&0G{s53-1-IyB<E!qBypXW|tQ$#1)w9ezrlYQB2efcs{&td}$04U&L@
zV{s8_A|uula1HVoNIUCn3AkDLG^pTVm4Ht;8+l^hc;##|ALY4f{AM?Yyx?c%jz5t(
zXk`0GH3kV__)TpAjNjsntr9`iG8m@>Ap?Z*!R?mHQZKm`7Yyyh_&u*X_&Xf4lZu1_
zbPaez!7<yltp#55?t1bTnoj7UXJ_i#M>llei);)Ctl~Ke0xb3-B@-3?76p;9yDZ<K
z>i!EICB7+p-p{W%z2=~QChZJQHB|b+{&xLPR7Ze?!SKC;aR&d8_W_sN?RV7%#X`wP
z(!28D@MW;c&-;Fd=4yt{4M~4ujSxLy<clZrjJxU#?9x;OgN^LHywa5Cnc`6v1<Pqq
z5E$9b6wat(Esy2$E(Pd^%|xHvR~rM^;VZN!23OGbHOvT=4=HrNEy$lSZbp8aLDdZ|
zr+ycvldso4!V0O8Hz|yPhW80RJ=GSo)Ev1(GQAQL4j?XX-wZFNUwDYXBU4isi#a|O
z00Hs}(|nU(nda&Pj}o?X=3|7Zv4V6+fj@Oa#&4^<3-9>S+!#v%h$fckT$;Re`7j?B
zLikl~6eEQ(_f3y2ObgP~s$D3Peg;-60ne+BN2i?KmMNO64=h9_mPqp0EQ166-QJ^7
ze);w{YN!sKi>J)K*o};>pFsHLtAUVsP0N+-2Vmv^rC0S1{vk)2u-6Xj+PiOS9>JQV
zHA^VaACL{lp(WWOb13#krd@D*nAE}Je7%>jbpV4x8~$#ZVbX3c{Q11DJKcmQmH$4E
zA+OcLph8abrJ_;kGuv#Sw<JXTc|jZLzJ4dzi93839zO@c*XcpvHj$24<-Oiis`%1>
zoj=mrA=kBQKT*lVN}pgXe;J>v$(mHbx*#6bx{!-9ic>Qrp$^vNUMp=C*h+S4sv0U!
z8{N_MAeiFuglv3OyLKHS=bF}B1NXNj38a5i)C)y(3a!~ddqcm8Q&Aja*4n)MmO~@N
zz9O|LhJRDf@s3O_@-NNX+X^+GL`*S`y3p!aZzb~2f#DS`<7~mD=Hkw@4h-?TS^Sj&
zQxHY!Gn%01MQ^{RQzv6}v`+8TBcqSdu54B5exE^m6LV8O6WMJUbWcUH56vmj4>iG9
zi-iXx;en#`_l!T>INaP8q*kdq?yA`LqB*$EV3eSx>o>8>IJmMWhRj~y8|YO+-5Kvv
zO@nxS>sJjFr0>J=u2$Ol+x_T@`s&?z7#Hndu|KLR$T7s+vE%1b^c&FB_GCTS>2B@_
z(GfTblsf+NAyVD^j6(S<+J|sSAdL3Az=LL>KfufH;hw+Dw50z0%K>&LpMJrguZ?GJ
zSk~f4zlX~;vryhXT@@)GYsW8t<B<n(g9Wy;PjtDt3o~GRr|irqP-?o-5&WxEjo}b&
z?n!DQ(XZW1(sOwUUM#&oz*00M6$I|*@J`TJJ%V3qpgk6(7kg;{$)X3muEDjvh8+i4
z!+9N`TwabV2jre78gi?tfA9hAJLO2t7m5LV8E?{9tW<K01IGKlqfleiJR4M<{G@yQ
z?7h{<IISLc?uUvh2hHB-%I#fO%E!s97cOgM82T$MkB*q^aAmG$)(#jniDV}P7L#9l
z>hv;Y4ZlD?NO8m2qSXu&OWt08kbq(((2IW6IZ?x$;!c>+D!22Y&4|b+UEt;5aTZuv
zW($s;o~y7LCVw&DyR&vl+gtcXqaIpIv*{5)O=a8>rcn?2eb{s?VE@S<M+98Xp;xU$
z90&4<@6ILBD5=U1S+j20z-Y6NQ?mS7TJDgV3rufkGc<^VxRj(<(pG9ksCgCw<EX($
zTW+|N3m&E_)Tr&NM&~&tMkx-G^;~>->n0bTI?5$G^bN=3FHYfJmHc5-o630+D;t>{
zCt4&)b!i`XfcHggJQK9-u4UJ_^@bf04Mf0W@n$2Q(m`qiVylfBjy*ztmCv-Bm6vy@
z{se`ZNts?IqxN5IBQ#1b^!oK<ZA}!vmGjMk!dJK<X8m&oFbCvtV*GpLf`oTLpRS8C
zy_g-xtW)r^=&e&o^|g6V6on72i{HwIz^qciAnJ!=O5Ab=WKtp~{Blou<|zzifF>Hb
zA3urET_tBX3RUk3M5dc%nfSg;9AWOm??hnTli+T}7!m1<`EuOqpxp>XSu(m4)oS8>
zL=FOQJg66IUDN)DzqF|Xz`<}zQ3HA<jTd%05llI`wo|a+Yq)z-r|@!1wAb5ZLdaR)
zSGGE%S=cNbp3^6Zm1u{akf!|Xvm3(rWt@=qmY<yHi}t5@=rL<;QcaX@m1v4StUXPE
zc}h76KF>5JqKm~lDM-1{{%P>3dNw&*4~g2LTeb0e2MQ1y>4_+sO8FopHm_?7pL2c3
zJz9-K7XoRbb1=n$nlp@J`AmwJT`#|PL?U)|3wT}#j9Jr95cH7vV2et*AKxuR9My!~
z<9A!$G*PT5=CG{4pXll}->_<LH?m$RRA==ueaMSdyYG+Y*N0i<P2WB!uw$steyV+I
zH73Fy8mGd!p&10;=dux{P?mf!w1&!e2jd^xr7qyVj^P@gM91WAyGjUCAgA#bM(N|_
zm8BK-DdcseD3$1bob>7V71_w9J8ez6{a#pW6uG@=(3bgdtiOtmVD{~h)0JI%nFmr<
zel>Z7aqHCxEf&FV$!<Nqcy528)FrP*IdRtNn60iNnmTjlrNpa*$R~aNitSr8%>3?C
z6_Imtp4+-X*LGAJf<K&JCkNYe<!6EmS+n3i7r@WisMWnSm3rbxwItxqJaAL$FDdUL
zV|i&(Fxu40k{8L$VbjwG)=og#HET(Z3>`ap%|_1>Ho@+Bsq@uby~)&-P|8?8{M|t{
z&On~`>nzlIkh`e^gpWM18)<y0L2=e@6*26zcWxR#e6m=8Q&m;q(zfW|`inOzBy?rB
z5#w1}b1TEgN-Os*)s`Av)1;5#EDbN?dgtmTzaMKhOzw*uj=^KHaiTUZecJ@pM#+l4
zoNZ{G2&uH!`J?7pmVnNQVh#9ZJA>*--_12~Fy?w+rc?-}+m<!j#p}%}h>y`X#kB7p
zbsCiez(1)*+dZVspQu1gU_Ez(^lgR2(1#y2l{+(zTsKA7@EpTasQyggpI-Dg6qcle
z+d3Kq)e=nuZG3=4bF)Z!^68E51Q`eY!3FtUg&b8TwJn<@sk5wT5wDHS;+Itni2^6M
zydg|&d|#o(bJCuWAyEP}V(K>K)Sm9%try;g|3k*VOxsN?G6`tcnx~n;2h%^qtrt{Z
zvJH>5l?K`Z6c4T%5bLG~IrHcttFW@>ENy~HB0)WkJr4%Jp^-n~)ZgdGOuibYn#~Zr
zOnm9FTASl&A&e-fA&4e^4_`e?auul;VmbEP3T%~<5eZ8@bg6;+OqJnlQ#~7RC6RGh
zGtTHQU#`PYU<*WbrfDE{ba}tYz*Fe%w)RSi&yqet_4C+|3>Vbv6?_*ropT`FOT>+L
zk@8{78ExPGj1pGDbW(KZ0@<X<{sO7eHl>9|HYCDu3hX0>2X1Kqi&B+4Ow?$cU!zI=
z7)ksRP;s=DN7Tq^^q%b#y7&oyB`h=M$s##KH%&RM5fD=qzEf{%V@t@-4i&aW%zINv
z^=doI*+F4n_cZP98a(B3p(a1_r8y^Z@ym*2j76|{&d0{AAGprxN`{<EEr^zDXjclN
zt`ea`qhdU5k{lpX`cESPf8}Ic^hH^qm|uR{aQt0=&<!%RKR=l6kfhCL=ARt&n|zZ*
zs~#|2?wjRt+GMta+1A*NOj2vSJ_uY}uH{K0Mwztg-fhE<i==BrQ*-aF`kQNHZjq9N
zX~0{pYTpU6vK&2TeU~EpDf)px=GWl#90G_qKR52&|D$TsduC)`?wvoc2b#rV%XoD2
zdJ6B6oRGNyiLtB$v~{;yj8J&H^vj!a>Oo>)Ft~T)%2j`wKWJ=gHh>;whP0AI8fy^-
zZ*(OZi>(<FO{ypX`*)-S!dwdF6zE-j+R1e_SJqaQDX31AIcP;#>v?+XWNBRwgehtX
zPOa8fbHUH>2O=-=CYc%>FRlfSLYMtD4%@!l6B9#u)x)N%cSMv6!kNX9K|3B)KJbT8
zXOMs^!ym**VP)151`379{ts8C>Q7p0Vo8%UFKd@TNA^0VOtrxyIf`VG5|`ytm#1W9
zXUA+DL1M*weox4<{Mw3n_Pt#&NI8=#z}xV;V^xvD%))BF3cA_s7d`trl_L%$;90ke
zTltx(4q3wnbxED!W|h1TTEw0>V_VHhU*%g`BO@WHQl!7zT^Ka9zUZmd*B|v~!DW^z
zy(ynN)&BQn=?}!wpl}*$FK0}rmk~(Kd?_+6$tp=&oCS-<Py|$(|B>bkGu0YC>S+j!
zci3l=$n+XpIX+>0gBh_#uJ83#lS%r<QzJ7$D@LfdYS%sjEID=p_n*`W#B4MD3zDa$
zPt&2p+Rh>989C80ruIYXSge~FMr-eDkUH*b!6VG9T?3u8FdB&eWi5@ly4c34EgVLN
zr3<skvs%a}1MO}qwaHQnSViJsok(4-1j*BpXDi>`Z&U0x^0b1kObD}QN6dwh$kcg)
z7EW~AI$(Hv#LuKREb!X5zY{k1lO30vMN{Dsx_KUwT)<H5V6$Ie>p!q>|HgQc?G8Ku
zyI|bMjOd1*ub<3B>pq|qw038aL~!_h{s3P6V6r~&HreAO=ER6e4nDo!!iF2#*HY($
zSv6eX*ZYymAJORb@`TPKos^qsOs{E8D}PZ5pviLqia7Y!TL|WnSgIvp1cC3#w46*C
zhfWo2lsRGX&jdf#c!F*gJM@2W*>!d8qz%EaIn9gIVQf-9>~kFoSH93)WMRCNB3X6!
z^6(<<>j@6Lm{XtI1}PSQ)H_7^p+D<7+i}?RMpsXfkNJDbR^PKWH~o3JTQ{$o7|wG2
zcAcgVUu2~*hB1bgE;nFMHQZ+y1NsSfN4s&x=R!AXTJ`de0Lv{3Ka4BL6FhKvAiz3v
zwbJ@*-NI{$&Lv4|{!3YP{>KnAV$cEId!=B;Q;PfwAr|(Kxc#GyV2z`g+J!pN$J*NJ
zPI#*8_04F`4pU|<@|{|z{B;DF`cHv~ZB{Z!i8WEA%9xNdD4E?dkjUJCo}>Jq725R7
zPD}j|o4^F{a<i%Ia0T$&r*WatLA&FX;_pDPKR1<+-uP-X6dH)DN1`bT>792igEuCg
zo}{#6c9uKJCBotyQH1tl)LC;E(HXH5@>9)}%t}ef4FntU<xmsyZwaRL%t(9oIWMvn
zKa@00cnF^uhmnMDPW`sGXMzlc3OK)%*|ip$RZ^oecDhn2!`~IF32f;m`7?@Wse18$
zWm$ssFW!-ba;)#=4iPn<J6DOI|DYEwY18u(x*;Q9;t#&eGhRHGJvPpGKO}L?XacTy
zO9|rNI{<UOc^ZTXQHSL=WKAo58RPOpYOB6&RGRxqcqC#fZG88qD6f*g88<RS)IIU4
z3-<4((23lQchokZcdPfdx0+5NC+wJo{C*{BzdMbBNeU5>=v7Lmt`*nD`#Qh-cf5`t
z%&zc5R?KfzZlOWryrnZul+g5l_(r|vG&w0Qi`2ngk<SJd1xm^9qI6w9^I`#{Do<y~
zO{s8vi8OBG4@>C1o7`$oF1J?!rcU0$rvL*PHx9C&XuKakPGl;xAjxo|Jca>CHF)gL
zjb*178{|q437H-Qxc(|mvV^CPx6P%W=A0u`@SdFPR;F^OPU2bFFIv-YNnUFu0$!`)
zi?$j#{sRp8`>jMuWB(x5Az|};(y|msx_hfZ4rdSaT4R3JqX1r7nAAmks5v1;^c265
zoHKpB0E<=ryW+QH;_GBaZcHJ*nO-c|4R@NFRcX<rg~h%L0GDrPh125cbakY#;ytK|
z$<q8ok$Qhx{*HUn@P+Mb154P5=Zz4)DVu%|zNdaytigq%q)6O3-(%S8p+vphkb-iJ
zhEuI%Tnj6|ecCkvN`s-k-t@pP>{Z_`nb7t!4B6e0AO;~5Wd$kLFCCB5C2~b<ygM+0
zINz%=j;uxX&`EB}7PjTPpwGYYLk}9?bUu#PPhR)Br0(8HWF~uG@eUH1gu@hjcYq>V
z_87B+>^c`hRQgr6zveAT(gJ!Y>n*s|wu|uAY{#o6V>Zu1^nI2DA3l8KKkFxda1u70
zuCl)}k9L1(v_cTH9QDPQ263^COWdKg!JPazscrU>yzLU59W$+<CCBM*2`$qH(O-!o
ze5SJGX`a0(-PUHWUP6*~P2T4Vd$o2wWcW4}EJM@&uv`2m8H5|^D%&)ND`u7`iN~3C
zXWIeXppH69HP@s+Ls{dkvMXPsvPo4>Ug8z_s<Um<q;Dp#Rv8&ncf<r|be-EURaBq~
zs<-})PsNWRJ+95aP-Z0IlooopC+(H|TQK2=@N;uH;oG84NYgX4F2pO8TT7{)>GfuW
zuWvWbR^t-^&``hwIZ~I(I3%%|6As7FYnK#h(m9eMleDH7sf@QZFPCU<@V&!qf6MS6
z!jfE`rSXd{lvgS#&$q)jP2wl?qlHm5E6nqdHIF+zEqE?=xzJk?dvTGSKz$*lZ~@b~
zI)M#!Cn=z=k(C1DK$&*hGz@>p+|^4)C{Frz@{_Mgg&P^=0w7*8QA{5Bl2<A!c)S`N
zD{;77VPElcZ2mKR5Z`yD`_Lg4H+Si>_}!K%*2h6)-V<&9^^S=A)Z410(sz+i-n(Lq
zCnE|TP#=fVpn*tQc$jIL6Cph3@4_HAy~Xw8uD3c~qX#Ps^leg@TWAfhFRP9Bj8=1$
zsrSm4+3KepTu;M9-ZrnWmO{`pMJO}M1p+YD{Qu%XNw`5Ye#B<f7(JyTyD4vd?@ER6
z0b6ohq<)T=@&7+2NJzqy2wOWMq=M)yrp!=Rq^c;Y@ffaoE6ru|+2`iHQ@{23mP@1b
zm&IF23UkV_Y?2*-QcsnMp8<fCqim#i10ocy?@Rf7zeU6_AIWhB0W=Pz#O5f~D43Cc
zPohRB$$M{v6Y;?+uB4Bo&N(FCaVug|R5f9Okp>w-p+`8|2N1+&pc|W{*q`EmXk9`V
z%GgMrph~cIK*fH90LdU=&X-SzaeF^q9OQT=m1Hx}!O<N0kwOH~mH~Q`ank>F9=cn{
zG@K{?`+ZKT^C#$I!N%RKg>r51d&qjE%=ZMZGT%!2ih3H}y>|TC%>!{y-Ew=ae#@7o
zx`4|56|6~`w!|~Hu>&_8;YN`>Iaq8*=0@#CyOZXwWtqdO69f8hfi@30GnKsR-yc>4
zQj5OfKn)F1cq#z)H1f{yF4oJ9XQ9oXM70Ecul?^xJdZvxvvfu}K+L4;4SychIVAY5
zjT@ZJLYWETiT8Cn>8ct-l8%|vPlG1QJSDgq<aa+0wI{z1_$-^G<L&T4fzx6=A9t)k
zRm{3QonZ3UTZ@jzFdA<UhE$^TnWch&RbA4C5<2-(m(RfT4M_Hpoy0(H2KU|OV(9O<
zoH*RE^+D5GVc7}x>hV!Jti<0EcR1S!{ipwZJbw7Vu`a^#U1s?2WxMN1u2l;ddLE>o
z89i>&(WN>oBC+Rl0vS<&*bflStNh!BoQUymhFT0rfUMY4%!wvsC!N(3<<G;<_;6#F
zE^AiJSK}+`QLq19QJl=RoT)m!e=9M`CwxZT$ky`sdHXZ2>EDVz73c4gQI{GA|M)i!
zvngqFn?HlFTP!`0MjIX(cP_9+DY#CgDp-V`s(+8{K(KZ2AyT07AEv)z#auyKPx`_(
zAd*fTIP+SzD1|x5nM!eqW}#)|qBJp;s@TR@OFf-&R~TQYg<mvX3z1}&8MbIaco7i2
z+=@W3IttdaeT1OZ_cb}9=V8n{{=Gupt5CRsw&99tBnf%y^OE!xy71>8+Io3-r7@O5
zlEzng)epi?4_J3~%><ztK3wVhe)RGBT`gTi0&SdR2MykX=3Q5+OC@0&u@jPe->yt2
z(xXEh2vEjTAHIvT#;>S>hYBmb-Nl5XBW&QLJ?u9g+&Xxj0363_*nY-G8)`aF6oQRM
z=b?1a3RhD*)&Prcs+uQ=Uhxgxp{FXuItqn6LZb%HEaR!9h9R31ih($5F)H$IJ`X$7
z1C5#!Z~9fyi*_HC(j_^QAfQovigv;e{2!Zup=xvvb9rq)fgeeZ3yB`9p6!#eyjQ5!
ziuEi5s14jVFUZy&V@NjkiL<zNY4m%C=ejU8n!A2kvb&b0PzoYlhxs-U{s;JEc@@~2
zUeu-c9or9~yZXCVl4tHv{J1(mxF|?OEi#SZx1O16Fy{GwCh7iaO~*|uDQ!GEk`4Ky
zRy}d?)@uJ{NoPCw0$XA0dJ&f@e;gX}6FT$vQXzfJju`D1&{o?ubTw&fNUs@OU~N=j
zcGEU5UPG31_MRnT`QV3NgULM~{(u8Rmi77PpF#8Anml>9SFc;oHH<6d1JU!-l}jnD
zSd~vn#qA_$otWgDDdNe?1-@cHy#$l!(KUDv#L_~Y-z}c?V8Rx%Q(*hxOfr4js?>ka
z+dKA3D2uI@v2yQqX5fU#ym*#8{ZQk~;go?|ite5x9SUW-_5i8z<P;x7U2BPF;6W5G
zZrF<((#dc@rq%lWbxgxX`_D;o)ha!wgB!h05r0sGTFaYpofx#Bg;kJQ+3)mKa8+rc
z(-|y5sol^v2r@xZyO){ZJsqUMy2qG#ZmEaMnwgk9p_7K@!&Zp-Z}LNbO_x7XnB}_C
zGwBNcT3mbopV~M94opEn@Ir0~_BJuQ#NyS^?2aG)4fwc=Ds)STKaR>Uh1;f8l3S3G
zcd?sO`>HX@ojp&Dw{L67DWt3+4BEn631cZepe|P@ejkdB9nBwX8pCR4zAa=d5Fg0e
z`~zI?4)P6V0WYo?8DhPDYp*0z9_j9ND?<Tn>e_FWW>3i5x$C*;ltW={UfG1#GJn=n
zJ)G(yyWbsxK1_PkAA}@LEe|PG1-f`5lslE~J(aLgnN6L(1K6umyPs9UoV%sOJvJ*^
z+;6}$oCoCsjFQ6Jkv@UZ$QTcZn`He^3D)cvXQ}f(clxr)Vd}eICnw~Bm>owqEsQDC
z8^Td4sf`HC!Bw`R-}NhNOP<2W$2$h4)y)c{1>BX7(UM5$3z6$5L9P_*(g1JI<s1mt
z!kp50MqV<u^WZoUw^a%BjT^Uhpz>>@lm;$md2D&XC{`Gbs9tbRDa<-Zuz{5k@#9q6
zN%jtbVteB@7VOUaP|}Elz%>XXT4oI>A)q5uentre+>Bp0euG7&Tt>|5`wHAn(IxlP
z-bPmHZXPB+(>7Vn*7QsRU5%1i5pTtA=etqDUtz)}NOS|%7CGL93uXf6`(-!AK1}pU
zn|cmN76%Nx8&w!_rHLbaPx=C8S3-0Rz`Enw**1snPjv=#`Pxl{i(LH>8-=!1C3oQ0
zrytW!g=(;!ZthGOHwsW68xBhkxlWAKvnEYVo(8{|Q^HzOCKX@t<{V~HuAks&PX$Yk
z;76|eN%8N?6h~!fD2ypH4QH>e>37uxD!AFSH7O(=Nx)q%YE8t+@ojVt`3EOLb47kD
z3zYg#C)tyz8D(GhN2=cK)I0GRk(_CX$x;AgazC+iXYAA)rF^^Hg^ND#=PJg#<9~%{
zZ>(v85~LT)um?W{J!@A#RG<#8<mjhxVQdr<<4KJqsR`2S)(KbON#R7_uhB4}h^3pT
zFzynQ5T6-dDpF@C&d`tl9c9(kATQ<WqtO)7bh7=F^7r6K`J!Dx_!<5ojirguO$7el
zkPSe^JUv(5miLgSwE0kloTV+2`bkTv^Ze#akxj!3M&Z<_)G_hN#4BQEL3lZ{S1fh0
z<mO!!TJn|-^IDk(L#I3nO~sS9sU;Uuw{+#8&z=DH`d#hJC@IH1V7}=+W5J$pzknnV
zd`ZPta?GmCk|i^loZZHs=i|T5ZJzOE-v}VV4K5Va4B9VZ_<04xacWpkP@o383F4K#
zS1!kNWrEd{ePrm8!vg>1>d_bDB}bbA?v)DWwTV#~_nJ9k$YJlg{pt!4{1sGQ^=K__
zz$;B1*ZincY#W=*7XsxUYQpoAP5cS<Oe~lox4TbU2`SW>X!s9sx_}I;FHpmj%vawR
z_ck2tZHWCokMDb=@pc&f+xn#P+d<8Ndp@+$io$M?!HFUUkXLYh(o9A1%S}F9pib6z
zq!#@4Xz`n>oI@1L<~)}!e2y}ZxB_i$8NYAG%k!=RAiD4$fI-;{YTDOxfa0pbHIieg
zgY?w?dOZJW;%mZobt<%d8)8j<jIGe=Zk!@W3H`VL;9ggCl0Q=0T_{=B4BRh(-&Fw9
zwNW36+32ud7UF}o1m1UkWeTtE<j3)ABwzR|sZE$vcf35!5Cm3L^*Yj_v(}<Lc$rPr
zpI3{e>QbzC4EeP5k=AVJ!Oum)QWyD`a(#XIFYMA$#`)>2@dsyM+^uc(do;t3piSQz
zZ__jhDG%TWHz^4pFLGSvI>yx1Jyet>a88f))6{VO;$lQFd*;-UAaNdeTpM;PR8PU7
zV!>5DzDXH1tFy(fJOn)g8$mwFpm;f>n}kd#SMo13<aYn^<!MnUXFdD|u<%$GzH118
zxAqA;-oCWUTgOZ4fI}d1*EA0Ai&09&-Bi3StD$Z=nc{@aoNmTju~^FYlOPhcW)g37
zgB8TUGuWwNXQZ0ZY|JCfsWMysSh{`&Ck;6<O{m%?WvGi3Z9b<}2wQKQwAK_;<ul)B
z-=!;j@z?avb$IP}wAJ}K(zHcDWP6vZxg3_x??E#-pa=%WfU@bJH`9nJJgMl7G8#LQ
z)e-NfFk`IfB$IU2Ns=dTxo`#gIiLM6Yjc~0jz~!RMJYr_N?>ztMH$=ul!TpnrIa8r
zXoz<b!0ReReIXxMi82TfwlT2i@)CCvBjC4^=C-wj%XtM9+hEY9G}f!8<iBWlRDIk0
zRMTa<UDQGf8e)+~=|;wnM(O5C5&h?LGs#E$FbN=QKT@+F<WIsDB&k4c9;pc=xvx&?
zs(ceu+R~DCY*sx(spiuPanbJ~G@CprWF=iFRpqc7Ea!{lq4?PsUmKi<O02j-w}#_f
z^1iWhOZQHxM8z*Qg*+j`6n--1-Nb0sSIw69^CT!}PCZJ(b5gGB7NeXwrDOBbxy=gi
zY#pv+#HA)W!Mtpx1`_nEK(6@`SRV4u%?~1@f~S-a;(%VL#0V+Hyii|}T9dA_X8S$h
zkUb{lowOjf!dQXH1!V|>@%?37+%%^@?8V3W;0)`4S<uMK2f39`TDt}QZOFPA(e{O4
z9P<>^*r$b3y0h<c;vIE#*tcs4MN*GER70>O_QkV3V)QQ-OLPC2eVy?BA&p*wTi~{3
zFWD!$pkk8i!tq7OvToT<9L?u!t5!w-rXJJPtw>PWbt5Yzoh3oyjijKK+&rheAt9ki
zbgm8ZTZv4<f<Q`0^1C4kbHKDRc<2rm?M1w6`>s;FZj?6;@RV$Rha*m0=i8x>xY=w$
zd%SLBxanfL=pSdks;7_eD-)OqyTWK;!D;sos<PxUJB%$v79FiEtNotIkP6*;`fV-!
zz<=Y!Ngw<lsJEeF;@f12{7H|ma3*Sg??yj222L8O;VR>qxl_pTCMz%SZX24f2mP3t
z)cP_gXq?z7OOEip4j=&f6Q+a*@WrM35S0%*$w8LQQK6fG4gR(Y+~XT2PmY5y^dHJq
zl$G6ng8EGa%WIY0mgYxs??~tlMS~XM$CbtNyrte$$`(Qmm>-|uvitlq0rvA6!Sze2
zlXMO*?Z$I;8MM1Im=&OoqO>J$f+VKXe#l6N^%6TQ<Vg(49Lio_u#h$G@b-|f>Fd{X
zm)w8T6rF_hd(Zo@>K%U9Ofqu2n6IB}kS*Uu{_VQa=$bwE`7N;a6nLup(5N!ELs;E$
zjV61XzbFXapShrZau_HrHpg+=0(%#+RD5M|55;$+h5R;YvQqu^exi7oSf8LUjldUs
z1f#k>TG5SeO3}(pJDUZo-15exc|8sH^1j;r!^-Z5Sk%(FB0l?d1DAHnOnG^>fa6eR
z?RHuPH?0R8Y{lzln{<d_Lf7u=&ltp8K(u1+@;!14O|^tPPgurgWI8x=p;Xka6|ZoZ
z;3N6RX##+nt2ed1yd<3mQcYVp%To}QGL#gj+vG^^A_hQ?{!ptb?<{DVexVU9*tA2N
zYJ&-f|FqKTMLdXmrLmR(+`00WUtDH%X?_T0khd^XA(ZXSoFMCPb%`j_!XKx9u2qVE
zn2uK3<Fr;ZQqCvYvN7?PyS8id+Lfp&es1UV8Q%Xr=hYO{&{9uRu)6V1y2CjwggSmR
zlrkdXuTTcQzE;<T_SdU67zNlo!pDe^kJtaES@66iQScC5th}FGZlV8o_vX+UVpI64
z*Dc{eK1jo$Aq{b&qfNUBNiaatu+nUaXx6b<iM1c|_}bR3(_7P&%cU(2>Q9|31^eqH
zc<QULR_#EfxD;ywx69ed8pl41#70f?(>nr2E|g-mIM)0Jjljph4S0Hpi`1Rk(&|Ei
z6NJb%4@p3ZD6^P-YT0kEkx=Jf@wxSj>oi01f*%dlJ`84#R=Z+hGMb`4gB3{$ASU5h
z^B+ndJ;90oEGvoE2&K{eHj(cqA<6|EoAh3xX=8FX^vu?~Tw85f&aj0;Qp;rR7G0QB
z&&`=B=L$RZkN000u9gjyHcu|EYKSmU|DlMpNE^zn{(5UTc6wNx^lHHE`Ayc{vsHi^
z{m}Wx(#71==(_E@0iVgh7D#FC+SAv4$xH$|A9Q%uIO*m{>5RVb8Qibw!{q2o>0(Xb
z_fgK=uJmINCtG=koR<oLsVhPY;(d$`>P~65cXQTIgC)t{IFQ`dXdTV5A|J{ml`UL(
z(It;c;U{f(>}IwgadIeS)bwcu9#A+DgzoHRyN3b&SFfAf?S+Tt=hB{3@z@$knT1G<
z$33%K#><jI=i0`E`DaK@?Gw;DNW?CK4Uq0<_1POzM{)lVNQ}1m(Y5~TpLg$B8{6tQ
zztA)b5Fv<V&(Fgs5w7l{ad7weY1h}}yGyZV-N9OdrQo6+$9-gG+JQFB)ji`@S1}Nw
z{Gvw$)$|^1c+gE-+2^S_X0Xti^fEx&PHleUdp9Xx9ia{%br%^W9#6`t{|yD)@3~Wt
zFeUL$+8Xhw2-CkAw$eGqVNi?nZNY&T?&1C$Y+k_17HDHoI?frw7L;j$Yu~FF<|@05
z3mxg!749z-(0Dg@Tp8=5I~sP39S`hoxBNgc(7Md9qg3L|r1)vS1KH(p{jhP^kM++h
z0=}erMY7N~HZj~uTJ2hCILLTpN=Vh`*hD-VxOh&ERM@jv4UZlWb<^iQ2dZfsl8UD?
z(ho@w6NJ0Ek)H!KU}CzlE#O2}R}^;}<E-qVK|`0d`q4q#UX(`Jn_zfnnSMVV-boVB
z*jixTpfyc3H2-y&elB;*C}f#<;OWeWoz0b)80fiDBbHQ*7_sCC(iQsSA)YPWsZ)s}
z_IpQ?y8&fj2~VvW#hs^J-sSA>%<w?x7cAU_epS;ZdJ_^6H7jr+o4)Z~_jE|{X5*V1
zkrzPxn7hubMUK+J_n~CPsFX&#Dg*dPN6>{(17NlaT5$~L4}+$~xed-6<__#ys6<A4
z`J)Ul3Y~(TBS0dfUwS@co5aR7@Qr>O?d>_>e^<(k2z@r_z{mUvGCOn)D^u-RZw(Ra
z-1(bQO;k5DRUUjVH9fEm3}vp)s~_xfYK+s;J}Br+u{QI*a32cnOP}N_%DAsQL$#da
z@gK$qOet-`Q%9jOire4bw%nBi6;P@vSW0*oLipQVbh*wF77wRbG5ezm#D(aA5hgH%
zfWE&3AJ<7lCq@mxPJA>{Hd1NB2f$NGR`%FW%_F%lwze+AOaXGUS%#b1-VXCy3%S`1
zjjP1y9FY{;qT0?Y-q+L5K;!Zrf`WGzmf20?dskY1gUsJ3SQWrytf)7^&UmdIBOwSw
zi6cDeLKmP{)y48nc4F#AfXiRd7}W!O%!OI?>d5m&9>Mc1N>yt76sa`hO3WvKM@TU;
zS{v_)YV&^e8?IfYhu8+Tq*goK==?b`<(^;iVuv`d^g>tafmE}@qY8?d@J}xZt>oeg
zvN)4!dd-4}+I;ArFZ|f*7PqyB#ZgqSNc!ZUrPj;x%oZgw(`LPYhl3V>XwDsbnW{^3
zqf<W|28ocjh)#PA^8<f_v_i*;y^r-1i;Oi(`5Jhn`8*R8{wHBcZ78RsKy+jXvt0pv
zqpbdtaTV_ms;gUP+rS*ClosR=tv9zPI+pKD-$_Z)U_hB;ZOYXWNHuw--p4j8(;Yyv
zGFZgpo;6X!%*c2*Dhy5k10Yq#2jW^i&7iq+q*RD5%sQ?wYr1Z0-Hb3JN2LVLX8Z|v
z&TYSZ-~RLFSIe8&R%PNFvvgC#J_+Y2D*YPo$7FdZ)z7ZjP~-UU)*xE}fo);~p?`E6
zb(sFA&<M{f)_(on<hCKjTmG;9SEbUC68cZve-V>A{=e)p?(w%kOn%5+StmOg3bczu
z^5Ss_cviy7+DnwcC{_D@MB&A~CdS03Ha;{V<eK>z^7Qj$TLaATYwyU0>J*HiXA%Ai
zSgnBXNsJBX{6IN6;%5i0E2V8yV|Y3991K&Ee`heif3ILE7c$D$_TxW5LsxG5G`m*3
z+CbXWz%wMIPGKhdGtsNCJB+?=H;CQJEX4D>S>MW>!A>Oj3jPBnmG~K6>-;6mG<c?%
zNc`Q-j(sKb1R*u<LoMaWc2V3p@!4<E!v1tq7?k)(`we=K?ff2QcI8!aoLlUlst%Oj
z!TK&s&jsUQ&;Pb=4)@EiGeWN=KdJ@RTfNLH{09itvRbRK%#t4;XQjGNq_X}G;J~y|
z=_)^p`w>|j^wpphkP7>Ue@d;QN(IB%(#CZ2@PyPnAB;y(QPgxg>)>58Ylb?a7#iOR
zNwi$KM3UT2TK%l{*+J`}TtHbf71^CwzUS*Xy!!BWU;3^hFa8rfk*30d=@wgmHdEp4
zdj0|ILMkZ&Dk>DiHGJ5mi(S`;Ll;%(IcfXm@jt-Hd{-SrhL6m|rl1*ZxL)RYaGu=i
zGq85gHezWbpAK`WoQu*Ivz<%jpL{8(!sdn>k*WZbHnr2h5)N8-#dd!BVYp$SPpaxW
zqt)1x9S0BbkMpGe)}=+`p5Fny`U^oJ>EQ6=RNO6o68PxU0+s0u?M3PzlJaW=$|>hL
zp)wyyi~qFFJ54;AHDMWX-%hcfAyPK~u9NGn`N!Kfyw!Mwd-lTx3b%=$M}9@iyO)rN
z%h_%{NAtbebBou=(kM2acU7hye&fUlkCg;A0E=5Q{sW+i8MR9WU)ShXJY(j55Gdg$
ze~;@FwW0bs0sd_mJ|7)B^jR7DHIHfKQ_Xz)KcM}C_%#2wR#^h-78G**__sWvEvj9j
zxW=g3A0NC;kO7r|cOFqTg_+J6Yv#X6FkM-3`U=_pwAWjP2We++;s_lX*U_tPP){J_
zqoaIRl?^<ffiuY2_G*qzS2Fi!8CgSIp>nFN&5f4gLbU)-l@@Y`a?q(Yr{i=BqNsC;
zE5(ec>-?WT|6_-zDHT3abbOy%oUi>6tUAxo{JV?^tU5>K^cMCjlbLVgzF3op;h`LV
zCZG~Uc_=PkjuGTY{Qtyx``^9>QJwoJ)j;FM(q39!b_hyYZr@LVu&|^pYe}ET@t_uy
z%1+|HG5zO*0znjv@U`Z^=#0$eWyJuW@+ol;Qu!p32e}r6`CG3CzP5k)BuzvqU+zBG
zn&|3VT6Q;0IA41i`3xM(m|Gqsj1TB$E)_0L-3Z4WO1Ud0*OJ2c9K<|Hp$6b^6lWG^
z0Zam@5;>J+dj|2}7_;!oJ0gKFT}f_BTOFwhsBbG6y~3E<<`4996yrQF!g$Tyy|jLs
zbtZYInh7S>r&uJkZU=vy>$=f0s*iVd&@;Ve6`5pIT$i6E&adkCLqIs+K0e>{&y^S4
z7KX<7eHHs|@R70VnsL$PD&e7KF=g%8pxVJPM#*-ka-9;IDe_~#MUzUielM%BJn%9D
z_C;>w!kl*-Gad%brGskIU?FIcRhJE^oYBR;aQjsDd@M!cGb*i>A6;6NM!#FK7oWjm
zs{RD@<OX(%!L2gwgBuo4PT%&aO8wElmoF^paX;l!Al0*mFPWapRQ@s^ZEtIp(UvN8
z_if;b4<g7nK5ru|;<h3=9!Io_{t=vKZ=Jy0+%#6|&AzndpzDaUMqK_KnQsjHZ9hR)
zIl+T%dZmy6WjEho^@Qq(orw>+D{Gp>RL%t1$Cs~|$g{iB=nj+Vx6I;UjMV&+wh%s~
zB7oL2GP^Wz1JU0#{Pl!9<7#x7oDetQC+8qL6?Rl;+jZ@9lO=jlGF=%zy8WAzCp+6^
zutRB6|6HKqzT--{fBa^rOa9~E84c=r51Ru8O>fA}ACkw41G%5kr*TH;A%pH63IvPJ
zq>cBk@uu=4%Ll0Ujc>0$gLfC*{KrX$#spGuq^t9G6Gy$;*QBr9xvaN`U2>-MVEjD+
z$pbtmZPTI&bY5|VnbV;q<<#iIP()q4sVBMKbF5{}g_SaQOCy%h&sYTXz&(;ox+O1h
z7sT`h$_Q_H;}D3NAg@HB(A=0m=hzRF5T+BmZ}h*U7ctK(QQ)uJ>=&TODg2+6&_JHD
ztO9|nnL4CoW{*&lH;@|X&A6q7*vW;q@3;K0?;2pzYyQxp=1r>Dt(WwsmU|+tIAGmK
zLk8Q!;(eDW`>mG6Dgn9#{i$N3*j$%R&0&@6-0qWTk_{7eD2v(<eMiy(^!Ojmd`s*P
zUyqvM;%Ua}wIj_Fzmz}5X5$|-|B%sa9u&$2ls|RAM`4h|Q9AO5{Y~$=Zts5M3GM(V
z0%CT2DFTc_G+p|_fp&>X>>YOVW5yTqQ~x1>AAU?n2rb!|X~q!uN{2hKQ>FHTZKf_G
zm+*yYS?u6<0Do_6$W2o^u}qt>fNY`eJ9(wxN^>ZiUwTf|5aIRo6=kO8ms8P**4V@`
zVFJ`K55Q|p4_UyjuK(L62jOYHxh8`9Go;Qhk_DjzrH+K8jnTzQ_20a%a7ur&9#~I`
zv41CYjk2vmbhhw9T|Kw*bjU|~sHeq+8fw^oFKc-BcWG_DoMGza{Uw+~{zJ#ipu8k7
zZ1Y~{Cztc#H2&jP6&1305ItB4?=8^zAg*C<-#>l)ZI%#Vu3jxfMx*&{^5=3P<NeBI
zLoA$c8Lwa3yCEcvTNe0ckEVP)CiRnfZR_F&{1|bsvX#f*`C7;MJ{+7=W@fp)4?SJ<
zU0=g~C854{)?;D5j{Z8t;kF6-AS1JDU7c&XODJ^9Z#}N{B8K%1)veOQ%~?#bf1fVR
z%P~!#R4$dZcQp2UD*RnFH%`xH^l(tl`gbfrPrVhd0FvG_E$i`1lR<jwA4qx(@#EGg
zZdH*yw|w+<^{{J}W$VV=E;J!PLXp!E=@g0^<Ci<C=ESf3vC1OV(lN)LnnZ`{JS_a4
z0&XVb_ksS%=t0{Z$ryiD)M}yiyQzb2!`?)a!AY41)gEJ>u!R%nD0zLaN~+wd#LaUR
z@wtcIpBOJZy<W3%l`is^e@_eZ-|coOT<)tNF@K-?U8<FHju+#3&dSugK{wBLrl|J$
zZR+S+lDZ#~d7ItN8PPyT=;U|dxb!`;skzWWKe;{?E7PZ`?YUrufXc))y_Yd3W@IRw
zR)&x<1%rMEbEA#_aLw7Ddy+H9|L=c*`B&Btk8GwKbL|KG<Ma($Cut!PGthMwH=i?Q
zW;YV)ZPn@q^@pv{<AHNuOoLqSm+!#_*c1cJ*v(^Oys0fa1a6`)6&cFz3?Ol%S~sWA
zIDh%YxJ_|)vzt8i<&c<_)jSe@1)VwHY3z+}=G8HVtH6nN^lp>Q^IES~^xu5jI>GJ*
zrZ)Wk+iQQW7;hLA1$SMsgdghl_!edw0t)V{1xi04*eqtB6Ae(|`a!Lwl@6y%WZVw{
zFHoZ*e>(F203tS|2c7LD)f`>?9+CPWh|kOSO4+-*QAO+3AcsgzN-{cdDvv@ri|FwX
zS0sdcP*DnnYAhw>TguSD7S;Z)?%5vfNveX+ar6DML<|I@n+6BZcJ2wYNJmkcd_ViA
zKPd-I1MC$@!$FpUt;F)=d7{_42`NL{{gkOhJZS*o<ZK`0N)p<9(dlzDH{8!5CFK)n
zlZrFFpy(hCD|cnXcwm4?^mghS56rgidDV%6XIzaphnsigDceu9m+?#EcExciTei7Z
z8s$VxL&oxOJy=NjnJRaTIv{a8sQ~N+o_3aTOYKqQ?`e7d!SHvJL|ETyl}@#+q=hf;
zYNlOA8I3YnBw8vQJcp6LdA2Kb>)Ke-Q>r@9e|@Od>gTjX(^qi_3kqI{bhwVpr-TcH
z+eA-OwhW_X6Npe>EEdoQP;nk8Zz|YcU{VGk;KdD_fvE0pP+o@0S|iF_k_>&2%i%2p
zZx1&26ehtRF$vJ3+IZh=(=nB}q3O4`LdHG=T^vZr)a8^XrV0P>_Y8^5YY~`!Q1N_K
z;FppmHljk|_h`VuP}Tubf=iS7vV{Fw&pK<|XtdF%)RAA{$&@V9UbcW}1Sq;eHRJ{?
zLrsS|XM;F{-03Y#B@vnmWm!WBAcx~@*z8<SDkZboB^m@uyJv&(WG6dqDdCsgkGjsn
zly}sw{To$p^|edujT19tymcK7R)Xg6{I+#}H~H4Moc?~QKBIOEm^ARG>GW20{31>J
zOI#cTn|_49TnkrZPI)+`eqso~FBlY0jXQy$s^ijKSD*;o^_H!8PpZ<6+?KxuTS_O~
zR|2U_bq9d+B#$G-fJ>2iH7>z!F#_=;EZ(GrpoIl^c$iZKKAzHE!kuIRBkgIK+b*~b
zxz5ual@f}0PLA|xi(JTX;ktZk@hV<eQMSlHBL|PN(hyi(ah<xzegmyga{41F8)K}o
zA0x!H@D<)jJmsmG+HzZgdb!bp5~UqFXc({ST_nJV@)t6FvQj{LUN%Fz`0&37JBz3`
z+pcZnE~Nx_DGo(~OL5oW?(XhI3nj&!6eqa5x3~v)cZ#-nk@9?b$N%6TWR%IhR@S<5
zUwfbDar_8Gd>0;Y+{!p_%l#W$2lyeO&X0T0m->FqRE?;|Op9!5zUY_I7>1&2d6Zh3
z+AZ1<1AjFTF}JIJa;03kh^yM(&QJ9Hp*@1mtzg3#{rq7dk=6=_XVkD$d(7`zdctm|
zO)s4#3URBE<1=ou5|2&z*sPZix^6b_<p~z1Sc(`TVe|MabXQTTIY<kay_(9-Dfa~}
zx$|dqsxA=Vq*RC02_mmIUA5%s<j@X&d{pW$-!WIFEZ+N^=PWcalW-&aA3}s)quh{F
zNe&XK)#zWzN-{<e(LuoYX|H01Kfq&b3hRbKY^kzUw7X)7Ico}gHpK`a|Drz+F&1YH
zzbZXd<S=P6Qz0C+)FVH#7V~oEcN1F2Kq^ZVwqbB0%)jTv8fuy_IZnkSvjse~`@}a_
z_Eo(!&X;=#2wo{C>JA(R>5`tL=Z5a-r?eO9p*6RLCwa1->Ov9jtGW6F$48e7GyE;T
z7$H?!h-e!&@F@XpyhL@B5nTu&b99LueCjCFc~yd-G6)`9cyca8I@EDuY?B&SbVB?q
zeK-R;>2H|(=>vCD;J64J@Je7H>x#bK?!$9K&`f&8F7lm_$pOliM{-k&?kG%JZ4s8H
zIW-*0V{&Z6?2Op@bw<;{*a1pmiuep-x2s_osZQ>6H(BUZ%JEmScbcFUrkJn3TG%)a
zu#q~$HSO(I+L*{ENE{AYb{$(47)^~`u65$w3^uWvK2xiHrRXd^e!f9jJ5j7&$UHY(
zzR8AemZLA~j=Q(ZGeGFr!h*#XZ`RWFRkFNeot&GY(NXEcxbG2vFl`r1Kvk_%hV}Zi
z10`Jh=DRShw}m9q+Xb%6r^?AH_LGYSaVl%y(eriyqjly{M`Un<bY!uL64r+KJ1T{M
z@r7Qv+;H|{xMo0+1LDDLshD=))_nT4B!)4-{#?x#hAez4i3cdOE)~dPd|p8Ggnc9}
z#KCjygd%7#<+75X_`_Idl=a`)MckL8K-s}u$jNA8*LwTy(MT#W4^=9;*BWF}{goDK
zthz$T)JvFd0i~N7o%dygQEE6jj04F|Orl*7&47w;?*q#%aDUwO;B`Q!S^MlFusaCV
zH8GEK+H%oY5I@k)xg+LlQD6SJi>AD*79dCyc8ds3Q&y|^CEz0<;${3rS9r$Th@KYL
zW~OFiqeyo9iUb)MTo@wdWz9ZIqkQ}Ci&A%!dJ0(nvprn)*12W2tKxx<zNx2^Cic5?
zHTM~!-SJU%zl+s!Nze}@L)JO%v`IY48^hrx&X&U2O<Id9zC?lNmt?dZjQm01SIJ77
z1MwNfRlGkD)LMpG+Yx?bM<I)|=Zq)Y%vdRHkw`3=3~Am3-qjYp6m_J5M?14Zro17`
zxQ*Zr8l!G!w@0pSH2q#%w5R50eJSX<fZkuj+BJD$%dv9C=l8H+pTso)rOzn8?UB56
zl{~srtF=Hu*gFSl#UStH0-#49F9TMPRbg6AFDTJaUdn9=MNkl<8z4-bUDq_ds77n`
zEwPnju1e|Vi_m$5B;{p(k-wW1_t?Z%TRyw#74A|RX;HGUd6!P2L*^N&!pF1)hic8h
z+l?&MI&mlY7Ga0FknZrNI9kuy4){p$fvgTNh8co$g{u-=p@EZ4tB9^^3sWgSU&fH0
zt|nk06=(4ZhB|vA)|eS*Y+@kiLRQT&VHID8{CS|(sTjvK=D=<D0*6S4usEIgC78&=
z+M?|?I%Pw;EA&jTB5#uCueHiT3fX?#k=8hUad&51Jd27|_OCvjtcVXuhd;jFrV8q4
z!BfRefhBk65EyLIi-OAC8*t)0T_uhyCsvd8b>+nTH(oj}pL|C9w||Mjtd+~lEFW-D
zUq6Wc7OpwGiZ+d$7S!sMvGE<Yb=szZu=_!#Py4QtOesn9KwL}R3Aw(=M0!^@Yl}nE
zc)=fyj>=g_f`|j1$9`D9pG*!M_M^rVEkr;tX1qPuCy|ZeHe;!sJ}Afu(j{89n5#1g
zEeMH<BrFYbD;H^!^i4Zs5_-7MO8i^F>6@N!5iKBSv8x9ZSt_fLFd6y}VbfE)fENu1
zDdo~6wH)nYw$87pwkKimF|zUFow%U3f(H9UN^=aAx6XS<sM>%d33Z0o_R+LpTPVzH
zny;J_E$1X?J3-(Zw;{5aiwDhowc%!<y7lMmUC5nl*chZQuB}b@e~9jwwM7a)#+6#-
zaxs3kJ;wN?cpEL8YvT3sn0vJ9)W2AR*A>k%2ko`y%oadfjjSW_ZY|tPST`~SLhzvu
zri8v5?#Jv>e;cgy9Hv}I$>!kE7*Td&2Q-?|+6Rn5RV^Wm@YE}!(=d^?>5>7iZ&wZ}
zbQ~=G*E;_GNohs6pI^o>M$~45;x_{_fBi$YwRFWU93bT+h_t_(!GINrT<T~^^mm#M
z(uy0`5tl>iM*SZ`sf=6Ujl5nB=4;Hq)mJuyiQ=u4KL->+D>7xP>pSb2V(|R2a1CqS
zj*tg3XniMJE4>l^Zi!2bO$eiE0X3nB>RgWhR<&(rBXJvCu2S);QxyJW6#nBtz0a^C
zl2L7vJ~_y$dDR<)L$CnYeD4Wv(aaM81NPu)E6p4#Rve3l@m0P_YoRLA)C%lQH3iBt
zLEObeXZ8K*Wp>j!^SISEq{~sF^aE?FY>LKgUu<16cINV4%~aUInB{y?Q}(FH?M<2y
zIk-vogC45rVhdVWdfy3H_bf;!-^2D&t6_ZiT2VR^F~;ea&MG(CSCbnx<Mx~w!a64#
zq-69~htvNMxF4!qc!el~wcPz01cH*3Cq0Spkr;@iutlD+T(@@Cp(q~cE(>xKBPINP
zh)rmlfz0UhU#(MR9ye%=Agp^ijq(4S1{71qNNM}-irVPJn&bVd_2!kV_6@!}+w+Ik
ztQ+(Uo2Liqh0IPgS=5D|i_5M;5*zu~3xwO>2@xf|<76Qtvo;d+c>6_FC?K-zqBVAl
zkiCiP5dO>cf-#YRF&Zz7&CqQbfZ(l9*Xe$-2bfKrg1Ql9abcyrR_84|hI{nfdXUA4
z<0>xmkUpZDPgH#On(Xhd#a5~KJOv7I+cK&!44+gH`hb-x#3eb}YYrKjs>Ng@_~(=#
zi&CO_yOb%ZghJzTS2t`EW6+oXu6DcCX+VhLC+@Z}b2gkhV=d-O^!@0I`}aupSvTKr
z><R);%;H@u;+2jM?YtCU5#`;-78LD(`pp|9UyoAc`38OJ_5YOR*bAgKF-9EOQl1Du
z)_-saDYMvIZi}skl?lP=3z8yr0cGK*Ju-VwyNft5MoWxAo&y@?<FbE)T@2O150$N<
zcBZBSGlEzB(|pU73_~Sp86}y|>HIERha3XY^m$@_vqJiy=_SAEEBbTdt*3*;r8$Af
zG{c%9mcD6$Tf<xE1EFxhkwM83ujhQVg5Qn<b|ZWjZ}ibVE?Yn#@u^mvetVweePD3T
z&#w=qY!IwtLq`V7^mTmI`G)sxd*If3g}C<N1#!e0Egx&Qe}Odzf*zfAyYjWSvNUT|
z0Y<_kc0-y0`<1Xjx78EeUk)ufHeG7bL^D#xoRT3AmxS(;2s2W;wwd}*BFkH6P>*UG
zJ-W2C_9Smz%Xd7ktG2@m^zNs6eYzBRi|wVd(}}AfR2dl>XEYDl2#n*p=GY|XwzI;v
ztIKG{!-rZ?S0NWPX%#;xxKWiA<oW2-@~!jQ*xd>1a#-rYVD`iUrb91ERty`bBv5{k
ztiuq#ua)faf$BbWoa#?7fg!eWguDOHg7s>*!N2kT6{d3Is+0}c=6R3J(5`4k0uV%R
zM9Im}A>*!x?V=sko^|?n|FiZOt(R>@yFJzjNy#LvtqY9?d2(X516_p<YBebNR9963
zv8luHT1%Yw^89X@aOp1+hej0cYB@}&LcG_r9E6b}7p|Yl0_u)B7kV03xOTDDTmN#_
zt0YNWtt0-z`+cgwLTzLH)G$a|jxo?cYcDQ-zFPZ+F74sYAE^-<mvnASyn`Y3(Zydw
z?3U)?JIw?{+MZ^wOm3lx;z%4*OmBUxkjIV`nVE9M-F`0#*RisVg5PrG#A;`{zHt6>
z^s1)F+#|!EX*8dKENp3zAxT%-Y06LVCSlytW3X`}>BRK<ht^viKk}Mmf-l1(!|5<>
z<M_s3cfC%U>x)LbpFQq>svG_aoYR~NHkMG2bq>2~gjmG4q(y6OB}m~_;`R@D$4V>?
z3~2>?(xBWlg|WUORBQhAmTY(3vBMkf&RzUM)jw&K?K<<AK-=g=S7wAG<BSq;r={+y
z$GGQthg8K`D3<@ZmCdLskpzs!?vyI@L{u5Gf2Q&9xm73{Z*h+rUK7e<4}D}RIK(-;
zucl!2i=Rb7qGjDSFI9_JPAe+J7zhGg&=<(h2a_YXZO*loz8edRUKnmJkW$3pku!K<
zp$QzO;4GmLE4c<DnqZmTsZ}`o_2qC`n*_DmZUt-%wkf<f8^A9+Ls-NzE-ZiIrCzNQ
zIN$#r>pK13Vn@orzkuR`K&h?GUo1bMcsD4#EjdxL9NSF74nhB`X^89M2Mf-c2K>iF
zcH)!$STI+U);w*f2$&!FR~k`Q=##>U*0_JU)Z}#3|EfVI0qsLsw(VzLEDR`Eu*_Rf
z!N1V^p{Rwx;wk*{D>37}7rr?6%cWlI_+|c`VGW#h9PCziTeA9G2wHN;vHWu@+iIa3
zBD@)-hu&fK3g@q(U;I&G_d6hp^S>UkN59C#FL<b)T%N5sjeo2pp6R75@~-dt+q*BC
zDyx`+Jm2Wn<Guf_KX#Fv=WUcIyKPN)SZv_iV~*5g`9$QQ_gPTy0ddD7lULY!RRSRO
zKZKf0J$KV3pK(`G3Mj}iDa-*ZO#1L!F4?5^fgb^>v=>f!`}WFGtt!&nWRJ1-?5QQu
zya=@kPE*zA;;atx{jKrBMUmf{`P@4gI#B&rhqGd<^H}u_fC}4bE}Vfqfm|XGHh-Zn
zcOH21;gFG+d|1sJ?kwXga-QUe3xU9B!8-P!HX5Ik?S>&2g&?s^@gNXE!}<iyg_%?L
zIVksw+<wIqL;WWiWxA~mh=uxk>4uL-=W&s9ciY(QM*dwS!QX{w3+fUuiuAk^vp(}G
z{N~}UO%fN>Q1<<+WWURP_&YAvkRGt*k7&v-aN_>gGbx3M+>>6qOg%A5?E%lUq*D7l
zd6`+Z=lv4rCxd%htMJC^qxg6PhkvW)IqAWA>?UJ7BaSh8VpoNBa}c7l!9QjEM;&L*
zw6?t(tt<*+F8n4nM&xQ0^3Z$W$l^E+8=_A1`}RNAAkJK<ACYqUj%1ILdI<|D4*DK^
zAvPtPoKz}iz%ybDI9eDD`roc9pQX-?GT)q^%+GzFQ7^nnYCXSgF6vRLmiWDfm#Izs
zwBIgkDb`6bWZBr4i~%XX5plWJV(j5qu|1;;F)1jZ(L26@sH!q?vE#0m7>}{*0``JA
z!<nm7U0!(4RPV~%%Ej$07n5W~<)>}TNQFQ|+pe`<V~w5*_W{pog6WoQJ+XqcqgAwB
zVJt|s+OjXw+~G7vS~SAt*0{@Al)7GYxA81OC6jl@1xZ>ex!OlWV-s-lq~ElsI_2|R
z(sW)NlH@_FAi^8qAWa!92#bR~o)%fbjrAn$4M22v(92DT0HW^k0oI6E#cNp*#{0lQ
z_vl6l)aeHHYj;|5A^qoH09ul$WPs=eL2t?Lj4(Rj=Dgc+go)po$pYr3Bn;8>2|%cJ
z36>5l<YE;&PA*V(b2!wd-@h+|_&d4sV6gzwKLas9EL5zbb6^BNN2xO3LJ)Zh)0w7|
z*z>JATI6CJA`GxO*G+Xw<hf{<ZIrNxIy$Gi1*52FFbM^0LIgEQsN|R&V93N^UY0^6
z@c-|_idl#(rUkJU1mqNcPl7-1&PX!E>X=fE$q_z*BlKK@LSbZ&Woo0^p$_K?PAGs}
zt!=OsF<2eGvtZ>>QJN12Xbr<Dl$K!8Ifya>E9>Gq3fVAK#hXvZFaqhRQc|rbpriPp
zVeYPUm~@!x8AKHce<oyLZ^fm&LJ%5lF_>>V0*zI&1ZWRL0D&H%Km@BqIVzSB2h!dk
z2p^ayVwi~qQEIFZgfstGh@3muS5k^#pF4}VoPFLaa6&`}unHFz*X~>HDqS!U-yD#?
z9ATg7F)nONEH!+jJCJC-RNr{l8mOOe*BfTsb92d|VqA_*C+^f4xX_7nBie147V<Th
zI$Xc{mG{q4Mqc3}a|U@Jn(=z|UzNS(QtGO9NQ?EPdDr)j*Xmi{PZ+1|ZM<^t1K$%&
zrG%8_vB*<gG404uj8cDCxB%u@8y5T7j%EgKnIVUMesmfAz+jyher^25IZL6`<!t|b
z%H=xqaG5%<M59WHe#8$N8u<HE+vxH}RxySmjv%;w9%}5!MatLtSk=C~B4WGuW!0Xn
znA3D0M9t0fD&6U_z_J}HFhL~3DR7LMOH9h#Nc8nUr|aLHUzUW_DLvf?n_|lgRO8cS
zbjFD@4uQH-ZC|2JprHJ0s{Y?tr}J0NYZ`+;5A+$Ztp-Go(G-*3d?;t>t&n%V)NiAR
zyGv=?z+wp*kC(96?XS~Xelh}L*85{(a*Xe#5Y<X@^D`#Db%G>+P1NB@jVk{PD|bwm
z`YxKr%RQ0UQA4KHNqPNS8G3lsQRCyE&%O8?xZKpy$;2&ml4gJ}m{;)qSllV<-__lV
z9Ve4$kdD%Lt%9{YATXQW*E%A9Y3r|hpZAV&+`Z#9fq4c&H8|b{;efREn|PRJbGw6O
zr>|PKUw+i7a-QPw%b4nA>=!Y9%J0N-cJZ%$`5l$e&Of~|sUriIvqYchJL!HRn;A-!
zi{W-s4N}(^3^c3uxE{p>z<fAlKTjzgxqHw0?0gkTOraQdW$#goB$`oY|M}OxW~N@j
zH_-o64r_Wi<}MD_9|C4dzuMn;&W~@DJu21m6V@j(_hfH6+O_O0BgLVt`@Hh8-d{NU
zs8K_<Jbs@DVNDdCKpx#O|2FLmi&)om6Kmac5nh^k?*B$NH+JUY;DqLr@s5$?{b(&U
zQrB$4KKD*|F-~c}E{)ay*~qcn&Xo}Fx;4yuJaIK5Z#?Np%g|g&Mg$*oPQaU|yIDZ8
zAYPSP1CuG66s7b7&$5jzXhQqdQdl#Y0f$u145Fqze|O1W68$Clzf&HC=f_B-pV8_v
z1etxl6tnKO%M=vVHTSoj2Rr-Pd-4{Iui|@}Ts7`(sSK8?&R|zly2%)NY?{_oh0OD8
zQtGQ3NB178AHnQZJLi2XIoB;21IC8!wv1J1aVX>cV5WYVfjCW~qU{_*^F16^+rmiA
znRUNx@~M|8q<9%K2OMmKnLGIP+=<LL&iGWyMc0QeryMrP8_VQyxB8VD8-wC^7x)YC
zR%tn{Lti$p95!!_hG(+maZP4il~vLh(|A%2k0z;G{WX?-I;?q2P92%Tl4>ohfPqw>
zGsr%L*YrZuu*v<qYH*ZV(SXcfVLGOYm;HUOPAO6xU*q?XDM`eM+v<97c^xN%U8^=s
zxCD7w5hBzDv*%e2>CcVQ1?Y8T=#Jp2$6mL;N&SA$oK+_Mp2unbA#iNP@(%%}XpYBh
zuh@bU)b|b2Rm4(J_J}rwYIpZDE7T-nmHghQ-^M?pnCVW`KR5BDnN$l=UH@GP+xrjU
z%gTC-URO*B?>9ly8)kW=_PSSsKhM)NT*v<*SQqT$r?TZSb4n?*T<^b?17|0UY4zHA
zOV=DBQ8MM*p;enVwZGUI-(l7mwZ&9}d{W37#yfPjO?%=7quph6aVA8t)ZpjF!FKXE
z_~K1MJb}9|I7-ooRzeRZZ4&bo@T^J9$Y6O=UMm{*6Zp-u(@*4z^taLx!@uSJJ0Jv`
z*tJA2-LADH&UNR}MQVf>*Gl%omzDUa?e>0c^5<o~*-UV|+!61@6pY>1?S454@2|DV
z+}cH5Dy|ed)~n4M|D@tr^hv93N))TDSWuLlu(6L?j@i}H#Z_s<Do^}@$1g_&M1OmT
zODc&S$8ax9!{s{^XOq)d&fqMBtj5_0<&vp@$G{vu&wVLt5i<_--H#)7?tEYiC*~JJ
z-tN5rxkfz~amALN)%1R+XY8*0(k`Qp-IsN9L%f=Z*@N=9iZE?dx%<OVT0QKJ2r-I5
z{FF%xgY;4xF<wVb@lyS%aXE&B@)aw3F`jR}<N=tBg-{-e*bfAw@xgc^c2d@}<Bs~1
zgevADgvwH-cOeE@!iDIHokrgr;g%0RxR)lr7KkjppNlJ@q}2ehd09a7l*B>@tW0l{
zFs$dw_z_ucGmABl6213(H>nz_grf7C8$HqS2%elg*RkU!ZwP9{;WBvE(dLr8uQZNQ
z45VT^D4aEtui4<cwJufpP&KmpDMQnaUY%FeQ%?(Av3Z#E+1Zd-wTeVyahx(GLN(C4
zAn2VNLfWt$trpmWE$9x)1Tl6eh4GLJ%#V_ukWoprWQlaHYER1K|HzP1H_DVV7?HN;
zSG4BIo{X;O*L~U4IrmCcXq8{4v{({G&cP?GLcFAp5e?Et9jw<GD~r@jWN{R}d)Bhx
z8ph1f$+D$h3PoWj#p%;y>B-Zf4T(5oeecK^La08_=oK0#@b1d2vn(ghTwALtLx|1M
z8eT*X(lI~-Cdy;%7g^rw_T$~I&=@(ds%}P+QI9}uiDp@;*fe`QSZj*Vc=^<o1n{Nw
zkS=L&c(lfpli9rCfh0&R^OUG2@jFEskf__JlPW0Gfi&lN4))1m1eYHirHWt&m7!Uu
zSAk>9axtkysvavshSAehQ!NIms*-0k7sasmQ2y*ZWERwq*<k02;{C`t*5FcFUqkMd
zri#48>kqn|0ety~s@*R2o|w6pNll&txTlB;V{vz~Je&uSalJYAkBgB<rKp1(4X{=E
zj<aZWT}M~Ins)|z93@{|@|Q%-j|48ND8AkocH9^DTTPn1N1tF7{7rVM>kVndo97k=
zLWp9mA?@$$X4x8${eqU#ElNBu&p}F7WJdG8kPlBQWkI@YVluuQ1!7w1G<lXv6+$j_
z6N_#0*hzL&2~2hD#P$5&+WHcvRPrMmp()2+Hv-4vXG_<J4cuy)49wfPRw<5nGa4tR
zZeMC9Ie%s_<QASeCnJON*N;^UqZ_%meg%Uo*`pNf*>fmz$rWqoW|+^|c}I0sMpmuY
z|Mk_<daQk7y{~b#!U^?P2@Y*`eF~MVVW6ST*f2kD9JYN3EHn-ubn`Zeirz{GRj=BY
zI=|o7V@*@Y`f>~vBc~9m?v$oIh|q6&;gq<ia%&}YWXmT?J7PFD+{;l{01$tCOjOe`
zjmW#t_zxk<V&0}Xe}Ih3nnHHE=jRXSZz}Ume9YrypV&S+mB)Lq>I5z6KnkQ8D11Lk
zlrX$@9xM<M-zD3;)?VtiBhKgYZZ#Vi4U=4I)22nT>38awQ83Ty1$6kBMn<c>LNcS(
znI;L-l7ez<w#yM{g6f+AFBUQYaa<$@KZ>@;sts=M5!QtmLq&daNQ)Lj1sjj%ZLUu3
z#Qkv&*g}wuh|vb@2q<zu(vv<wuB`i}go%S{6!1u}xx#Hwd9G))Ehoj8{60GL8m3w@
z#Z>2KaUxdv?5%rfnU<^1WB<9$MOmgN>?gRHsbhNQES&7pP{busTennmd+`V*e%U0e
zVvbcFUEJwk-UaUfL5}XIRnVeWqXAR=C!=znIK;`QOOW|^^RfI1Rid12Zkq<kS#ikP
z_CEx}mj;9T{ZfLdYy2&tS9TTk)=a|Vi<w2g+QW`M)Y>L-an?57Y323pedaMUd@UnR
zTb`sT*|CS(94<~JhKtkgQ{D13HeIy7P&TvT&M4j^k5|25F49|LZGn}4`|t6C;%Y6^
zZ9VvOTCj7RJXgt`X$ES?9VQ<Gt1ijppQ`G#sILMGaR&-UOBG4jbG_9M*a7$DRoXd@
zh<(Mo=n>~?q8<Ct$HMzU3=gI9Cu=H4c}%D`xR6v{sF2cPKT5fz9nhb+TL}{+gTG3r
zskGNBBGs{Ocq)s6GDc;F)rJI9d6bUQU`mwkbWefRWn0CuSHG<jQQ0F3S~yuy6Ga!+
z3^k@O?qI++Tm)cbc`2RNs$DJ&;-<z;Lb+fhb_=S2v9lso9kB2E(B}%3^8*vbD>|ab
zUmd*@9eJXpgkZ=3A+%E5{`-dtbR)kj)_Bj9ta{+)74)zjcn?=`Bjw&#bF&fVATm%@
z(IS+hQ?c?y_hZ`zP*qk8QG(tnl@EpIJMtRxDqmM1c0AUG3OI1-Pvn6KH_1m*6y~d2
zN-2(Z^Y1AuQ+@P<a8Q78pAQldosJLV<%it168E8kUQI4`W5d!K=emITMJub^!Uy1h
zr@F$SU1h41feFl-C3P#E(&D73E^|jeRGPOPqgd`p@wdq$qIALp58TUA@^SoQW@yj~
zFfZ<i%XsW&`|@KuWi(UW)`tyyo3F^e2usF7Rxy?g9VyM3^j(SvZC!{xP?Y;3(J%4F
zRQxCIA{KZ&5$o-Ru2q^AwaWWK*6SSzp2Jc&VCK;SND-+~Tc+u{oJ{87e#bxgF&T!;
z)8A%Up+1?Hu?SanqC?FalVohyF;sE{K@i!2rru7lZz35ON$9Q)tgA(mLl@%D068vR
zV~FVEpL>69h3E$GudKNkS)<fEeN<J<YsV`ob&zqieD{>ah~L}Q84F76v%z<2Nc}N)
zD|n)7g_m&wd@1b<`#!tOKV86?8(;h>?Pc=xw=SaV+NRW9rIB$C8udl=9Wz*+1VzQ>
zSGywBb;mu-_uU|#%xi37>j+KbZeSY2yHHPKV!a9Lorf5kJH1P75xpgVqmzEtyWwoB
zP0W6V`A+tx`LU}(yqye})~PoK;x(SA7<{D<-!~-;J<k&}*wjTMrYdcO7~}oX+JUv2
zMK_FIYcDm6lm7%S{!VW@3)dEiQHxj09{?FT+YFV^6Uu*_`5s+;N4n_jl2m-Da)vD6
z6ml?GA$vxxLl?!w-S~h_jdq96dQJps%_#AC(gttyBkRZd;SZd{va#$L=dziz>~Q+-
z=##d9ix5@!iZobx7|O0D;293b@#vPOIcTN9rGZcb_$)Z#W~$e7l;7Oo&qz_}1ZoeH
zFM7f^m~=J8O=gLAekyCRn|{<7G=W;L?_|BpXWs3o<-OSk5KDCNA;?E>7#d!a-+9KC
zzOb4j+5bWd53pq1Y=u`LNt3pVI~(iTrpok@o?bW;MMz>&1(7$wmB1Pk{@z+&HiPa<
z>~tDuh!_b+J2<}G(T6u$&1<k^Kh{x{IZeF_TwxE#)8PO9p?TtHA1@`bwHvAsiTx)4
zO8=wQIq9R<0~}rUnms2qs$q1>FZ7M;N+9t*{1;inCYPg$4PG3By&HZj-xxt2>=xgt
zozZVD+%jd7;L)g9_=;!P$eQloDoS8j0#G3;Wvo&#7-zoPwTy&5Rk}A82v+CQE-lZ0
z(vHwKSI8;kbi;w-ccF^LkKF<UJTQqkk{PevWp0DCsVB}p-Z${ld|v!Z=lj$wW6f5l
zvwL6bDx%vFSCo#N&jwu{dOeR)jp)hAloU4NLcVe_+FA?7i>XFzxiwxPz<vRy3JiX9
znjnZ&gdbA+p8q!IH@X@7?l1MG5QA|*^ulfcM5RedfttfO{gXbL>1KBZLY3Zk*0~W1
z)79;eIK!-7yJ(>CLE-bF`@0J^d;8P)f2`Ma+8nXJoMtDgqN&l3^h)&6k577m6M#!y
zz+IN-x(6zfy`?4h3l}!)7(A7zH+J5O=ghY3O(_vm8moP?8GB?5mL=FSVrNph7zH^4
zI>06)N4<S@iBCkAgA9=xQYM2YEg)`Ccau~RAi=>mjvCl*G5wDZoOUryfs<WDOcICv
zluP{E6!%BDJFnet6&9>p#d5XmA-X>*JXEQgm<HchO&JjgUn08%*|(~BBXlHFpx=^t
zC`XwR7wj9fVEe}0XxfZ!5iO{VRu~-m;!?eS!YRWZH?v&*h@eMdzD;d(tS8Rb)%A(s
zZ}hn!sX+=I`pR!Tj0VT#rgZED;Zn|FD^5|3&SicAcPEYPK>IDT6xTnaM#L%%=1c(l
z^pjJQtk`>JeEe;)XkH*JQA2g5bT!1VIsYS<qI4a%y0ePZP};=3E7$(|mEsm+#%J@a
zqMF0jJR8yE3aaz=Ypznu>YZ8`<o4Aj9t#Hc0+i6FtS&46vK8gm{0Vf}(SnKG5arV&
z!MXk3U=7yfLux)1jtB;hgCnF?R?@N5ewKhEtTS)O=C`58x$yYwba*{ydQ-KYb!}J)
zzR_C@4_$h@_g?(6n$yZuOEoUKA5Y_Uuf@+=bI2qHph_@{8CZu4BX^iYAWLlmBzo`)
zL<UK~0aj<F7UOXpzhDoU@4A9h1)!0Vx^=ld(%z3(_Jv;T72ZZuK`a~76y-4^1)G#I
zxGM)^><u;0Sx+m%<b0X3n*vj$89V~%8#v(#wvP)9<sv2%hYIe%9C4%t&5Thi<CU1B
z7^XDjm$FLnF7ACp^fu>``4F0lt*SVntLhIAtfBre^5vvGjc<0jEkSOJV)#6Zo=?kF
zyx7!%j5y_yqi2rbM9f{t1G`2<*X4|0mfkGu#ZP{BgICO^Sf+D*zZos^h&O(99FBm@
zyza26`h{G5HGr{xE`Dt=XTbms)>?z3>O%XAM*N#@uj}rA2-t>o4D<V+pOW3)eArAU
zBtlpy^Wqo|Ds^FO4kEn^$2%%r$<zg1LiME<Z40hp2iqeUZ(rHMS}tEwivOXSSR~Vk
zY`ltHo32d-S;|?z29W-9w%gc!jI$g4{-H(kesdE()_Az}Wxao8jZq@K8L8_FEX(*4
z<V<fCs>efjCT;(`{4IoY0h-<OoO_s-ON*fI8FOFA$&NMp0evtGXFvxAcvLNqVt_10
z4Q!LQjb@b?Q&L8bVb<oQcPp4^BVnX2uSxgYqBw~lWPDt=qw&=F4ER@^<;qRxc$NKU
z6)-}AzjQXeE-;I#(LCYVrLFY9FGkFKUELj6ihV9gM7%^&e4I;%y<Tg9WuC4{%=T|*
z4~7u=`Si7FhdLeg<Z2!neC_+)Ou9n%wdY1UpIvakjHUy8rc`)~qdMqlAqoEr&P2`^
zc(cl92(d1FDBcArQnG9ZmVaH6Gvo;uwxvk`{)2q_$@}Jm_>Qy$xW+HeyBTsjB2m_S
z6=GYs7C#>NJ_)p`<pJ!o5(4Z2VvFGg!XNAbUK<|9P#2tQn8nts`@*{vcgob4syWa6
ze9lAWWK_|Mj<fw9>E8#whw%f;uzzti#s%OXA3COII03WhbEurNAvY0!mjd1ICVi)}
z2qLbQZaLn#uQ^vm@6ix@*?Eog<WK&&-u?a$0l9ceVZq;w@6W%l|Bf~p-cZ=zKkl!@
z*76ejdcV!^-_EQ}hQ7AH3@t3fKAq%A=<%)omJl>#=Uq4Mi4O8K5G)|~Rl>jG6!=)J
zpI=)>a<!{d?Sl1h?+(a<@vH6!^WXgQtErU8uxOtexI7{t@hJO8IoHApE;#Dq7fDsr
zm1E7rT%wJ-$m`;hrb&$Rx0lSRm3BOZYP%w1S6C+3=8e*{)A)}jsmG^^#Cq3)6vOb-
z2(X_dy<xcqhi~PVGIix^UA#7b0s1`!ltuUIO@f;*XyHIur6%8UE~mowKYXL1G_9`W
zuo~JItS_a>@qq~iwFo{qv>H9XK9S3KyCf=Pchvb$a`ePMo+>k-+z8QUC$uebYK9cH
zH&hfDB>lA-Jur;qz`rgv@Ls8JMKE<WQw^yoE)G>bdUUnGl{-B2RKIBhBUqbkazACi
zp=GPqKIRrw!VIvYXm}UQ6bWk@-_VlZU2rafo)~xcb65P%AE7i~q}QX_0#x6CeOVK<
z@C2|Hp11CIZLPe<lQSoh#Zs|dEPZ5|iKi~m*HKGD&I%Lmk$s5_vd;8-@25ErfjC{0
zR5k`NHg%)MsV`lJ3tmI7g>O1eeJjo{zG7|+r&<C<G`8^cDtj2Nu&b?g-!Q0La8_Tg
zZP6e%{C~Tg*P2j?^rgn+dw%-UwKFw`3bk+lTjfB<pQiDREHjd>b?+9k&e(Jt;=SW_
zYdCVaYP3=fuFf3&y72&M#`H@F&)U(*3kAw^mNXzLA8U*crwzyXoJ?-H<m(2pZY@6y
zpRwjF={4GUQKMrkU#nynl0Jtv8+|tKMX|W=t0g98?3ya<3Ng!hh9n!x{~TajGh_9`
zYpp6Gnk{ge*x&wO;zBlK6c{HZ=CfahJ%&zNXx|CbZ<g(f|H`Czs*v@xxZxEvr;$Q9
zE!UhBgcZpK>MTo{X*FlVv+NcjH;t;N)c$$^5jX*JeDTCe=on_=`MWUo6bvF5HA^32
z;#rUCE1{hGYZZ<-%q8>yEk`a;_Inpa3jM8;itc2D0{pk*sVp)p3?m&zKzZ}gboi}`
zkgGLvrQn2dQp;j~B-sa#)v)o+C~NjSYr@+<y{v(76DOOW<S-dhax~eiBL)L$xjkIN
zOVQruDA|9m96C14Bn;#E79M=9j1=z+6}yKX<S!yV_yV-dxq=blFg+xK6g4sJ(;A^d
zRa-7py8U!Y2qs11U1#|L(E3!BgE#qE`vHF0eLpl_0*uyDO$owlNw){){d!k851Lbz
zlB2#$N9crq6(M;XPEyJu(UJ}#w{BK~sOI_>&RO2#!I%PJAE<scn0SbvE>7*IQ?mlH
zdlTp+TFCK@koF2{xz6mh6%HgjV`IvZwT^RzfW%NmJO?N`pc88F|1`Cf;HWcfIbbW3
z1JURq$PS{$6s*Y(=LQ3F9-+*@q1EVFR89n|9K>0WPdUivu6P%@ln&4V`{;yV3m{O~
zlcJM%KnCuzkjr=ula{Bb6{_Ku2o=uz?B_64vXH@lkwQx)6*+_tfR>mDEJs}Uq6)Pf
zQL#9`mz4y-0<cOaH<Hh!0IRi}v0&q{gH>@BAdsM08EK!=!g*~*R)=ShZy_p-Nsa}1
z9gLuCmL4=8AvutS@K6e0EFl0u2UM(ll88Voi5CAt1mAKCZHIHoQBB8AxY;;7pfIEa
z0a2bu34%!?@v3Lm>G`4VJ4a(KZ{=^j-~RtH*7<G`N7#q%^TKok%MzW(k*+NCNlB~J
z<h*$qr|nG_?H2i!>^cV}Jn&0xLyL_~V94o~ldiw-YyD!j?Hv8D?9Sk?u?-z`n6L8e
z-yt_03|PlUSBG{Pan>vR@{0X9y@=KA?^IB}r@!wNDnnJuVxahu!5M!Z^6{EDlu(^K
z^fKO`AflC$l2ZR;?Ky6h6Yo^=w}9*u2eBn<S3Z$Z0Iw=+mj1X@jn|N7JcBWA^f6Xr
zx+OzNXf2|k`(G7=tn}-VX>5bI<E?=j@`VMSDA?fATv#mBnS_z|0(6zc9+BUtYtBd4
z48I=i{k_Y|yYy9H?|8dhiPz=yS8raZ2OG^CS9`HpV^>EcFd%tv7bk#~F|M5a5Wh!g
z8?TiPf#cuIjuC{(u<xrR)!St$g+6_)#-{b~G&YKj^`%f_p5ikyl`JGmQKuk+H#h1K
zNST@|)e4z9zQK|Z!}(?DX80>y?QT>aC?VlS-T$_KEGo!VOq_lZ=4abNwJ1pqLe{69
z8=A~YJ7cq*FKRRA$6yRv@NT%!YwiBg*hxZM&%s+yTQuxPjy|lWpwY#k3!C?I<1;y%
zIcAmIO&P&;`O7{iV%J$Sw*F;G_T%IsHQc0ys|Vd`qgNu&XTNSuimN4}Yo?b;%E^i_
zQDKqRX``qYcU}xp`!lK9((K$zFIn@GC%#RpUOY=P#dV$jYct)z<Q>0mWv7z&`<$Iu
zp+Cx|82puPm}4_p5lN*%p>MIyq0UD!4j+)QITW0+ZfG!GRrA-4gK_1B4pc8+Bu@)G
z&3<|ZyE0`il+K{?GRCiflGseTF<Te^)YJU(fBsw?CsF7|?<cBa%|9vLJE#ybjqbE^
zP4u|YI{y8V*M!Z3>Yo#P2(NXi*Gj6lADbxUPM(+-!Ew_;V>##H7~k=mZ?|vx##UtC
zWmch!o@^J@dQ=PhOO$~(Kwr?fAWUY30gQ6{-h?T1G^|$PL&g+i%$KD3Y7!qI+FH>~
z4xdb=k~0xQrITRiAyV64d<G!4O16X!<Zz8rJ^Wi6-^#Sl3vIl?cjcUt2t+^@B1M#l
zO|%Nx@LVF~_1q?Fa702!6IYl|;3!#jKFuGu_I;Js#OXz-am=ZP<r%As#dqx=F#~JZ
z8tfLqSkM0bpQ*k{&hAFj;*q2!dYb}?bLWx2hEj}*D8$;dtvLsPquE&p4^HFt!DqxP
znp-{oV|o_qy2GJKki#DBU2%q?22rK=gPw^WBoXUkxk9O<Z=fLs!q~Hj`K?+%+%gvb
zwhyKS1Z!umgYwM|TB1zaRhRL&xTfZCh7m(qhnDg_ss3E5Gulyab&f+A$6n8<(?S}K
zfXI{9K^FS9KXi5o#A@)UR(D|H@v<d0?uq+LTmLJv`W0@|aH=~t>`mt(JaejOey-2Z
z;<d#cimS?@8jIT!yx)9`opDJu1aE=Ow-c!B(&zfY^jcfmnouT%-2xH(sz)BSS#l2g
zH&#w%VtF{z>#~l7A8U$@__AN_0jF0-`FlHz2%|_jCoG>ttT(mBCmY5Itn=PHteF=|
z&Ad`%1-kC0<+L`T9{VXjY}e(OVy(Q+6t-b}3=((0iib>&vk=H(UsWxGKsNW~zJQ%c
zK;!|X052PAS}wm)|EGy+B~m;!kfrCD&Ld2SX-~88DMmy$GlxN)TaBC0ZBC6RZN5+t
z?*wJPJRu3$--rX5?6WqE$22{c{O6&C4Wt@qW_;3Eh>@tlT+2tw&p>^*1%1{nif4=h
z$<bOzsq*C70|%g#a~2%a7)i9dx;FOcbeo~LViQLKg39(m-w{7!jw86Cyg-^lvp*9h
zN-@-`020f8+Y@m?h`tSfc5|%h_uys2bX!Xg=MJ)~$`Kx~)I|9Picoqt2B(mI^Rfx+
zakT0i+s$1P2UAa|1cNF@|7zk-$vf`CWeM3)k)h(O7$cwH1I(C;qZGtGv4wYNSiPUv
zaOd*{UaYE#z4Ozj6`ba1KZKTc$Z7pzVF;k&WfM#Lg-X#7SZ)cHVqCznd8o{GJ0!PT
zF)Adr>MPaQ+TC5OWKt)GT7{FVTG-saOZEso<L`7RI2q&$2BD3WJ-LkL>OfKEO}X~9
z0%n5Z&0XD;9-+Rb5r(mQYQ%rq|IQXi4y6&$zW=CURLAS#2*aZNw~=xViHky9q0b)e
zw)J5B-T<#FBSQ+QAiUyosF+6aMRx#12JVZ%isuDP@n3*GPcuiPXRy|MF8+}!*<66}
z0QcYM%+5vPIn05EL5twTrH$<nyg1-;Pt)~>o<X<0T#Gm1dM0!`WnxgkM6O-k>2u2i
zM_*w_LJXGTrrx)dD`wbi<V}C=$K&QL$|MTcEead{|D6Uh9|;l9wN19<JiTla*M-m@
zb>3PDHP~^;46|kzyM4$IRegc;(K@kA@$ZF?q1FmOM2P3^ye9WARFwET=s1jZKRNtx
zL4fd7{iD2NIAZ&s@*zbRZKcX0<SE@NH6|wW_E-;;_~0eu`3dP;@B&0Gl2!)!f}LFd
zmV)sXl){K|n9q9Ms6;d(gRh)a7V7A&Zxv@cRhy=^@f$`f^jHp-M9@}_TF*;lVFpX8
zSRGTe_V<aOS0z36%iPg-98=-{bn3OQR&$c>+@V>3WKn>Jd)+oJn&`GN#O#{<?b_}G
z^{&R5)FT`4O_pRG0w1C9MpfZ{mamp{%BdOy73&}b7m1>q0T7-$e@S*6L9KYkf)wEL
zdflN|ec?1P&`=4#Bes&u>fqSr%cH|lS&UVaIcydkNJZAScIEPT;^LJJB!9iZ)}2Ym
zXl0{CRVyIx2qh;v<{U1(3(H<M1lE%6TzsM;>*irH==rHS=;yGaG@b_FA~6O^hcMPx
zL3R^*iuf@z{%0@|^*)JJx69oOAV<8iw81fa-w~fuTd4%tm&OltQ(p3AeAc<f69z!g
z;4H^fjaJ&-`x2@OB<OeYF4x!Jyc^2;j=wx%uHOS0H(q85mpf6qoC9?S&_=C?eMLT(
zQ<u6C$&X%@FP9b@G3IbukbXPyew970YBTiK>#10LEy=%IAer*u0Wk=#cwL_B!djw_
z*iKDaWjqOoCI&?{N|EU}kFM#kHz4v~Khdyriaq)BBmoH%V~O&3^2a9`B4hI%6s@@~
zj^diW4vSZj7BHhh-xj-P-Xn?g3`^bulX@ZwEWz``#8{C*3ubF;{)Jn2733fXB|}mo
zq2fX6@TjO^_V|1@DX+wzV)hb+i*9oVM>rB?;S8sW+pi1RL0aS|^~x6flFTRz52)ha
zcjbXjBA^2}ki_O$J3VbVixjZ6Dg;F-ycBm74Az#hul?xODnMYhZ2L8>J-?N)tL4pZ
z@uu%?L&yJ}<CmMYB3W!glS#oHi_ek8==9mft;kWjmWib!66uB3sSa*JK#U-tO2LGV
z5hoy0{v>=&hJ_}*Igh1JO63@FEiK7<ke@!_I2>0Nk)p#*sU2R<MhL30d4SQaI@N`;
zDj@_fm<WoIXK-$~osa@B<7eg*?;^N^7o*%ZtsyD62fa#U=U}_3yGm=UpJB8?i(hTN
z&yejG1^h7WJ6SHx(GgzVh^;khrzl!i*k|btpF&EHUplV_M1=G+@di<6$Tl2;p;yR@
zAFpv1_P!XIsiXJGL(@QY0b@W!Ph&ToiqZN~xQeMs)s1vU#;^#?jb5q<Xc)8BJn#_s
zG4F+yQlMqzw|>_k%ZEjH#-8%2%d|h+TaV*oX<(b@jFjPv==<sE4b#Lw*`+cRi8;TV
zdPl1Ht4U<_HQDLfPK5iRkU$bqo+M?5?<8TZ<~q`e#lr7waF*qUoOyh+T_s|Yg#EAf
zj2VQgZ#G85+`Ii&C~b5<Sj~lV4ybc0QB{{j+&VY@I5mrD?8!`YAs&~B(hhS_FQ8>3
zSs)@}n3~N_vz`)F2>R+q#To(|m1w!|hre7Pc3KFHmnpBAz?D$Kn!=+8st$wR;kfJ(
zxV3q`L#1|B-_ClSp4wGxG3`aiN|uX>gDv<NuGaa6Wo^1PZrp`_%U#77gO42yJn$>T
z*$zoAJ{)1awI*|IA#4NMm!WFPyY(2~5)U8~I^U7Yot=Zn8rd=*&>G4X7$cIhIx1fZ
zm-5)&SU<2`$>e()JrYccyd8xLy|Eo9oK9v$j43fNcpWJ}>#T^RnHiFryp!CEsKx$=
z8gZ*S8dgYYRUwe%gG`!(aoz$xk1j@&X3h*4<EOPl$UU4_#8R9%Z<7<EeJEZ=@5*xE
zco(|QZg)p65{5c9cNQZpEw6A*iF{YD(rZY{k)r%9Kl+A!wBDER{Ws^ZUTVaU{q8WF
zfUfPcA!9S%IHEw56{-NGm*d%t#4o9au7^rUpUC!tRtnB|whYfc-dunXpF~%bYW{w|
zm`!gT(b)2w??hc@?&?H4%E<L+Xk{Zv$IJ!aB%I*q-XCfUVvJy*hT=Lpan;&=kfw}y
zl(S{b4?&C-vnN`D6+u`x>oeD+vGR-It%Ol0fd!Dz%iuz*9wy5q!XVYP5hvJT?n`MD
zWhQbYuA{Ni7aYaA8lm6dc*RfT?e08YA-&}cz3LU;DUvGIG4fgC*uvKKbBGdhJN#{K
zjDI-uyT%uY?#Saml6k_EPB=U-#l^eqiW-jI@9(JPeZQDPQlLmrflTLrVx3@C^{<xF
zLgrP}NrTkPqj_)FBEFY36|^V9)Z<LN4-$*VTLj7$bQi!=9j)e!d^}H~)t?9TBS{S<
zKRn~;y&o`bBLrs@zX+{EDHoMY>|%<7(MrgkB&_?N^*DZZ4MZQT=h_f7UdmF~egFO0
zC$(W@^eET1>!B0^(CVS?tr}|kRlmY;I-jZ-GWJ7$M3lUNp*baGqMc>2SsDbA$7-jI
z(Cx{QdfD(aGCz0qXGKU{<Vk8#QCeC)G81^a(G{(*YDtbx$)(OIAEdk_e!xJJI2BtY
z%#GL~!bmCBW&W+nJ9<RMRD`{i1<tV%^`xQHJ|eT^yb`eaLLJqs15rxPVAP&>On!y^
zT{M%;dQWUpFbIam$Tpo+9Os+6Gt?WoWX@1nz$t%LSBjq!bfcX%)TumkLmiK3ZJ%-z
zgLPSK)+NXGYv0`z{z9*)aQIHF15{oO9i-F~pD)ig3=lry4`{Af$3M`qPxFZtD#E2l
zP;T=y>hjSO3{dIJGjCe}PwUa*d1?d<h4aFZxc0Wz&W^U2ncK%o@ElU<LJMYyOf|dk
zaMM8;?6GTwHs*-XDiyuVQ{VOeTQ_inXeg!P?OeB-*4}x)0LjSlIpDj-IvLtA%88gh
zp~G5^RS423q@4upo(?cBOAC9<^3^xEa;uk^1AxX1Bc8OuASBqs_Xkia9kaK0SEUTj
zm&Y$;_jQH8B<PpmY%TKZQC%k9;#Q6~(!V2qs6Iz=iZj1Wbf6c+LW`+z!&q4z<6P6f
zUHp)hLb*TMLnJc)n2wjJwv>gLpY#&y`?zUBw_85PQGcqHkS7)!Lkh)ssDNTjAX^h%
z`Td80_9}{q=KMXULA2p5vbFXz&0qPkkS?#Wpx49p+gcZN*fGHRM$)hwH_usmbny9d
zRmQ$#OSyLT>ljUe^0U)|+MLU$g9X*L`2P?ZNr{3l9m!uSs_y`~gxE9^Mj`yyz7q-S
z1_>IEN0gsi7k_=iy5C^va;(`OA3q!EH95oie0p%I)qCy_WMO2d>@mm3jIQ0TIn4iI
zgs2|7=O1HjmwNP}%gakO>5a4w9%K-HDM!n#xsY&^$k0>t<GXw%+Y@ETZV3j3t;dru
zC9-2%pb%>oQh#NQaP0S94`+U{Fz*2Wlu{D}<=<0pYPDr!*`;)+sZCPf?XtklrS8CP
zxlhRR;Vg*X9X-`wS(vFR5Rqn4h1jXN)r2imVzDK0M(5*o29{-3X!1U;c`j8VqM?2;
z;E^l{(xpj|`Ed0eeJ4-o97aN#^H6%2AJcp#W>{#%b;`9*dhayW`L}eh+U2rKk2VYg
zXrcfj*eHg0L`sW%_C3)zr|>aIq)$}Be_?;){}OmTEv>x1+9&~icx6FeldFlXMpSlP
zQh<F3K%E)k4DuV|X0+aJtdpP%DErlR-rIS1DPI`M_S>FjCr9Bx*LL~tyJc*?*gxl^
zryi+#Q%|naPt0Yv;8J$eO`0837&E1tmjj&p6+A=p_w!gra7U9U3DFn->nN%4kW};s
z%9U_z@hN0tcU4G=OH;`qrPjp2N!`|~XZtp2dtLjNr$PHCa$nZiXa17-g8e#FPIT>M
zC~-;mM}QaVH27rSKh8}^L3XCqW@dlqy{Xr86sve<6=|{5R0aAnWWi`eIKy+hfR><l
zxm0*+C9PB3V~J!<1;1eGlO8|oqAMVzC~2Wr_PGi5i58CQH>p51=8`z}K4bH3LzKi$
zaw=Z$fz1(VR8$y)IzvMKK5I9S53EU^DYS}CNcJ?ms#z*|du-Y86Y?n~OpSz#Aam9P
z?9jj5YPFTvl_S1|>%B{2zFO#M3f4qxTsr8-$`e;pU}~q^Bk~Y;7LtjY0sdxY3TF=0
zJMBPWsYp1Qj3hUKGsOW!n!%reSVLwu9U~7CL-VNOXWER;uQFg~Q|Vqx5F(1~jnesi
z5_`d0D^LAC?ucWo=BO;XM9UTGmv2}Ky`mFT!MenYlu_}YiLgy4G>i~dZvNnt(kEYP
z@=iW2^W@8)!JZbd4`1fVnid8MEpJr?Ju1(F{D@MCR{xOa(&u!sj`o7$3#1$zeiU{-
z5gt*uQaHILrQ?_C8M972&?G1VADJ_UL8XGTCUeqx^44Q6p=`{(dH*3CRqvOZ3R!ck
zl_!Wxo<1$rh^<M?e?aCd*cU3x5<6TjUPA=c7T1fxvpANFDpm0wlz$LkEB7%q{_MA*
zU;u6*<{WyB{dLf;5#@Eoplc9U{*<u$Kr50p*l%LVl2)c>>S!VBe;|-_gW(kixKWga
z(!U&aY}#3IulTF4jjpkdS)P*=#{W@tmSIi4eHb3yr32}f28q!%M7l>xiJ-vfMnGCn
zM>mWbF**gLL=j=5V<RM`JESG_|L*;?ec16F$Fm*V?)$p0-+3}_)ayU`98wvPRa*Wb
zkclRngt5|t-~fVmu#ibP69y6slJZh8X`jT7lU<af-qdXI=Ngn3q(?FXc+d4Tp=WXZ
zXjN<bFcVFwWa!WQconZ!Jd`-q6O!KuxCKQLx~hylx02lJFlf`XsrQLIE~BPP!{m@C
z1(e}pa1@`UzuuSt<4z*E`ZNZx$_|w<+*?V$uu}J3$T`p=0QU4$(H8#QlVhu1-V^uL
zck<0fL>m$SJ+BdjCPl3d*qB>PRO~|Phu%RXTln4$0Rrg4)>-k0@e${#8X@-FU;+dn
z0(Ic078r+IA&5AA$Cv;Y<pk3hx)U(9C|dXFQmDz|LMnCmUevy>JQ~S}aHRgSin#>I
zZY{uZa#QsW>ly49e#F!QoGJAHu06dX1C|g34UQR4Y`}E6r)957ZY(iIpfXkp6W&U3
z_&?fAkQ7-O#b^;FUkMkW%>$TPZEzRsb4N=^8Zedf<xijL$D?s~2{Y6Ju|rdV5Dfd9
z3NC>$QH~^h+Nn$ARcX{iAY=+m){8`3lp}}+aHAl7>De#<5q^~GfwtpzMvs^)kWx)g
z%MEw+F##ov$zna8?|db3)wwPe_w+}#GL;$jLzAuq`cWk~fmv9~N)E_M{-cx*JW-Yj
z!7Res-&xL=S5V*#BglpL>lBCTPhnzg<AyGQ&iOdhwqr;fKU_*j2bbEru#GWo=fedk
zlE;|J%MoIVatOHEZ1PW>(*~|!3a+GvQcCEgxCP0Vv1d~E;Ta-)akCga%+4W5&=Qtg
zO;4u?3QfmPZgostkB(QaLXyC3A$T3-m5zy_#taXEjyXVtu_7svfRYI&5k@Sw?;}4T
z1$qeAu#LozH6Q_cl`AGBVjQEUAD-yzL(5ML<w1pGl8l)Uj47?jgs!eFhPD&I4pk)=
zU_-ksB%T_S)f05ALZNx+P;3144dV2~DL6n7io0=usg^DtVm%693S6c%Z91IxZ1gCK
z2-LvWr{kplSrfovpSAIVF5ph?$@A4T%h8)A8YAnr_5T3$`L&%Q^_8P0X&vw_?``)3
zf3aXW_RgwmIrK7*f5FJ{-ID3!F4xCf!B0wRu!?p4UVvCk`isKw0Y5h>9Xl7EYdJ!T
zhLqL4z#VSJL?MMCOs7rQ{3@fx{Y^vd4-Pu7xAM8iCFk||*qYharI4Q0*CRdnJH6K*
z!zkBH{sSm&GA$qIpFV=M{`LD#+C*#jge!%k-sMdtifmoDEuH@L$1vvY^4w2nWJrtd
z1mE~Rjhw*3Fai^Cp|ADkYA5hiUETAG2FdUL9JH$HZnjf#i{YsNe-_$u2j8wwn|RTW
zyDToiMJq1p8cEz#JcXr=+)Il?|I)m-Vo{;7R{Q<p3))_Y<hJ(8ePLcrHq(G97eBfE
zuS=HCAYmV79%O$$%lnYP5y0F?j;2IZQP=*&Vz$Z5XZeO3)iGsyiY<a?j?N_86K=x}
zwqNo`+PHu(JJ+kA5oQ=kgD06ACCXH8x#<CC<t!|iPYrdYFjI<l)jr?ZmNe})e@V40
zOA)Di=`8<H?!>jui_7wlqmqo9T+^X520E!tf+)Z(B$0l&)7*>q!3o4{M~S%;%G*5X
z{BfRF`FqWz`gVoABz@Pbz<PmF?Npa^<%3col%MpsHSX!hNlxkOV8CJ&nlNnEY>w(A
z@w(RJ#_$VWv9IBslIV53R-4=Ayr5Od!@9)U#8?~LM9@|uF=OLnt8bk}!pbG>AKL|v
zRvI*@TAS~8mT28&1x2|T^y>~O7#398c!OhpdcRE59%A({8~m08=}aSCV0&|9b!ZYO
z-R+VY6DM(RSM4SJfy@6aTlJ9nN3g9!v<c(P`MHH(MNyeFN57iXXLcNhn&Ir^$dv4<
z&?`T@N<9FYwZM!|c7v|C-rZ1QSE5<_fd=m@YSd@Wq7|#FGyj9<TpV}tb&IGWPA?7U
zOA634nII?lhis}b_s>>Bho;?8I=%PqHpag-28#0kBHDev$WfXl7pp&mc6tcsMLe9%
z`LV+D-uTUE+J<}bYUtdwHO+^BzrjYy>*KE+EFb$1Hl}YRYlSy|=jl)lG?i<#`lC+S
z6+T)WiCorvrOJCm;KZJXrk~QVSE_%=?`h;m{oJoZ$&zFJ+as9-uPMEXiO%SS)z^^<
zD?M|dBLzO_j@g1#?DSvZ;V<r|lH>nSVJu;?9-AZ%S{pV`WrEWu4K0736$6(d-S#=$
zWcj@6fW_TMwo|s`Qyqo2TRy-Gw*3V7cERzOqvli-6Pn&%d#3S1_%y82&@t1ArzPC2
zONt|haHq}oy-^6>le6Ucs;h#o%<+8FKgEr1@eGuoG5z1a430~|Y<_)!U$uLDwshua
z+)4SOd{ATu@?s2BnQ>N@vmRx-ANc?HOvP!a)%Xy#D}{W}ei-)k;)9KhqS)E`S}yxe
z`sUScDw#V}_DH0ph${hi^IE=ip=yK$@nPtrAKvfNzNUL!zM&sOu?z=}PyICi_2`}*
z>wUQ0fzfI2L_KqQC%xNuHjEl|w3-Fk{&r8EdmC0UQDOL*IVVeoyxKKoFU@W$_G^Ng
zKhO5v81shyG_tKH<yDRUY+2ev78#e7&(dMlV&3dJ+mgEIboa+YqC*WrpRPwbb=J9h
zYRp#sVG)YhpkoheDzdmCCtj2SMEqDD`H|!9i|KsOtY_5t{5o8VAMWlKhQ+=6J3zp_
z@0j`%rC3<T_=m=o@7FbBVsi94luxzU{EeF?W(&r;k)-tnv#~tnI=gN@jjc|xCl;Kd
zg<qU76*3iSY3SJuSF$4~xb}NE01(JJqc}FiC)Hc6(VxBHz-taYR=OT3fM>ShMR#1{
za5K22$^(fLePL^W;Nu##g3EPyEXhKV)f4#vfTHWm*!vnmV9lxa9GD}M9NMwctviYD
zwO$S;znccEb(y})y(~fS^WvNuh;}!Mz=}=BbagSCHHYoer9Snh6jaGlcxX_$qZ(Uv
zbQz2Opeza*2KP;uSlVvM8TD`|2zR}~rp?VFze{9qWd`jTGf{^ymD|LqoC)5-D62N&
zzL#b9D#+L${4u@ZucQZXm_Uj%gAo?^zDEZC6ihR;4RJ>EEV<2Tq&nrfN#FPQr4+ZO
zN35s%8k&Pj)A~0!nV>CYqoG^AAi`DSt*mu!Is-f{ZVM&I>$yY@cpqeBEh~NtVFv8f
z1FYiCzi$_qg+kOB@Ls}0*2{@Qoc6%RLT}PI;{OU_`_l><w6785KUc9<v<lluRxGn<
zKNcTfN+(Llpv0yalXqF8{t!d}S5KTW6IZU5^wmo{&<w}pEsBYvbS@y)>Jj-UB1Sl=
z#~%3=={iKx#z!fU(xV~Bi(v+XU^3V^!q8v@F`Yh-5<H`xPii5Wa#2?fS*B#lh&S#Q
zpu@E&^<AiBcZ*u6bLb=`bWilHZ`~sF$cg8BpvOq72rdtq#C~#gW*b8n{owE+kFCVS
z2fH}Sjf7H?zZ_B)BzjMGqOB?Ly^MrAir!7_$Ycjtg02T>Q-@cf+xRrNd=xQwHuUU%
zf}`^lE|@5O*zvP>0|h0QN5&4t$R}#rMxb6}<=uY)xgd4{#-kq<&|v2>1p6BVnQt0I
zy**Ni{KLaNy;N8H->=z7x${J#EgPlHWCWa-O@_HxG9XWVLI$2fL&<CLpqps*8*^tS
zl~xyJK|hJ77HsiO!1XV_TGqCvc<&srMwp`Ty^b*eC#b|%=W~IokOkmKTho<4xs_u_
zpGbRoeA>3SUYHAFj>7J`@xaM=&%qA_zHe71W<;A$p9z8Q3^geAKWT<dwMH2+vR}j)
zA9Q;Wsq+qW(DVLudSGN-Y!sx|_9JTuMG{&kIP9aI_$r{Jq&3*$H2Z_By#m(W^}FNv
zBle1_z1zQEtRsdbdbEtJzfZUEg!9mrsO>G3JS#FqsBfzdtFgVQCGzW#9<h2c<oqAt
zP3|3R@8!3)js!oQKkRLyRw6uo-`{|>bSwRx(|gUT?}c@lro|V}Y4oS(DC-&4CA8_j
zH!buB;y#ZKdg*C<^Tp_E{{ao0nzmyA_-!@{H_jw<s_pmnB7liRRo7tt08GOQ&!nWz
zVs&6On`fVn(iJDM7c^2b^N<t|#o+bF2zF~8!W_7CwsU-xsl+*wBYO78dMks7-#Mg=
z)67Pb{t8YNdLU(#*WSs4d`2yp7}@~+?h{f`8#bM{9#0U*;{b6{mPedlmXkV;6Zpwh
zQ}(7lx~y6dM`QB0=s|}PXGLxb!EDgsRutzBrrc}{FJ#jUwiroHtld;_Q4M?hg*v=C
zL4eb-u5naSh}bkaQtah+g;vRtwUh|tDLYqGNZkQ~u&<DEU81!}SwQL)1h@EIPt!Ew
zCC~PYYl$5^F)vJE&wOXlmKmFNS-ozg{P~HhZs{Bez@j2c#Q4W{CsB{$^pGN+z|>5{
z-9w0m8;^skP`2VgVFy2ZM>U1hw>2xBCLw$4k2ypi(3}>gKMi_fqNDG%kY3u0`TR)B
zoVY7Ay-z;asSd(*lNkZL8dP>0N+I#}YO{yPzJ7CEkL^H7DAzc!jL_ThX{0{dB(Ny&
z)G;S?Z!>cscj8G6seMmK8yaiE{YCP<=AJ3RzQD_jNeJ;r`@cVFGJRJXcq`U_i3FXF
zE6zGL*y6XnUN7QZsT5Ge)9tr%8pK-=ylVIMmN99fF<Gd-$y036wrVjZzG!3}*}m|f
z!>^I_^0*iS)JYJho*tQ!MoiJ<d+qOV1ox=pf9@09)gG$Uj9a9+`^=U<Th`(46&Z3J
zu7T_9_PV8u@o8|<^B2r8HgfS(E^1ZpSzydWNF7{VsqW(1X$6w#)!1tDdr~zAoV>!K
zZD?}}wU$wG@^#(y3OZtx-^rBasuOf#oIO4}k`j*Icz=O9^u$G2zROlVx3nG|F5#7@
zx3^(jeR<a#W?s$TsnOx`(Mb~TJP5xvpvPLLc=&BRS{=P*dqDExVn9T)sWUO2>)J;{
zL)XoOVDe?on|W@R1ARDlByoi7KR^_7rTbf0G<dYE8wV-*s<-Hz<n(i=vr*b#Gn8~q
z4ESqbv>VruWB8@p><hAx2oZOXjR>i)tygik(s#WYk>8>IBRy^hZJ(r(eAC_-oOs-5
z_z<#Gnx>dv$zLx4dk^>>uHn8Ls<+?HGjd}Rntfn5YX1;ZSARdhW|48%@0_K38oznY
z?oU6$%H?P|C+&22e3}i&x~eaH@xztvxZc{}TYpqQO*Z)vqfu^w!>KtLO81n>#M?Pq
zCaF%Dw5oi%fi8J)BPl$)erXSj&YAC376NKlMAd%A?uO3HQ!$+c47B?&-a=U3zdV;v
znJ-TlO^ob@h<?6Y>0GaSmA#vkevq~s1{pNg>3Wj!6C#KQ9s`|^>2PjszUb_#h&7hb
zG$~t=+QZ~~@(8bmT-8GCQ8rFs;2m|Vmt<Ybqa7B16Onuy`61TJ+UT+@A0QxHQ@}Er
zr+Jky@=aiwqxMFg-6yia%X*5y=Om-Pd+?fwv6$0D*$8ND!0s;*#m;*n@9?Nj-$$9t
zT5HeGZOLr5JR0?9r?qpM&!QulN5dsbyZ6r6wdjTHP_R-ay`<{y8}sYW?X)Lp<n5)i
zg<nW{*qE!_EG+r2tJDRKbj-S$z(DkKU=SPBv541)Vly=D`6t~&U0SnbbgY3%hK&_n
zqfB3f#hB!Zw-~rQ=6!P&kHe~12r@%xSzJpW(lqku(-$xCrzM9%r9&AL(h&@Lwaz-=
zC54A(<gNN@wobDNq*>Y?1iDTWLPB^#MY$9D)4vr5sRuVB^{HDA3H@T*3rrDdWhB%x
zw-)6J)NP@NMc27>f@Mdi`#AUK_c$5n@6k{elwwHvlXLFsXD*K=&TTj^4~%&=!se>1
z@5xS|9XEomviCz{ZqR#n^u>oa>}u1}qqyI4&D?*^wV7J)x6D{mB`h9nY4`H}#cM1T
zi6Hs&bgW(f`VnD}OYdI^JNn8WxCr=Xbc<Hp;O;BCU*pN(=CgZYuEbCM$1B6`jvUm#
z_8GqI-qMezH=%PmRVU~#fefMM@VGW?{RTl3SZHD)C}kOyaADo>jAS$@l3d9yxZOF|
zk>pRggTx<8t=GSKUS!4whIrFX{4V$ppnL7_FZho~U$S%G-zW=jE2tPymp1akT~a2r
zMu1~Ny3^(Ni#~=gV>?S6SHCz$=ocT%pXk6uh?Og&?%67%w_ImOwSo<Pjekb8V?~_E
z+?~81BuCTY=_F3In&UaF#Bm74-I6CYIxFJ}2V_T@;{y2nUphC<4E%kIF8v*@${a2b
z<iz`4?~L<*ozN=R;Ls@V|3E92DPH+N@nRc(4Ivl4eCYIe+i~pv@JEDDzC~eKk!Z(>
zoilRn&!wCU%lnT#K2(+%B`(j3VQ09vilanfw1#4IdDF>@%+mwi&u{kUYhy&e1wd||
zBxgo7a8VeN3PrZ`2($z4$B6)Ht>i*ZS62V-N6<YM`4*V^_a|OXrpMEO{{Vea<yX>4
z{y5v~!UN`i)N*n!t#Tq6zu<%mTJnC1LU1t>uV(GY_b{K&sb{|SrXi=ONqkYy$Nr1a
zR>6_XfzLmQ)?NJv`0CohzH?<8z5|@Kd2<tz86kaM_^bcd!)2Om*R=^HYIla6{uRz1
z)t>2Xbc<tQE{Bm`4b);o(oU14+ro1qSxNqNvE&tP<Vs^6FMK~}wB27je4+GC=GdxP
z<w$pwrsVjm*c-o}GDE>>^BOpTwl@}wzp|nwicPdk5Ut5bjr|1+wLZTF-wSMcSFxuA
zpLQFk(s{pZEy_=!$4M<r`>!MSSLD>L8eV#)uttFX1GIP^V2U|yyHyjF^nzF-kevK?
zZF!<A)d5DuRkm`<?L}@+J#*yKv?5w(zqF(<`bESPbK|$D@xI@2c1jH2Fw}cSF4=jd
zg#8cD=9#%E%n_Q@7DpgansF@nlMFYg6+UoZz2{ye0YlvO?;Mv-YngO8->rrd0X$ed
z-xs*7#55sBv||^gqp-T#BQ24=)g{!&{{fQlWyWUUw3G=GNYH*z?X_9+t;N%URKd4p
zd-_xivjA0IMwQElZY^?azzBLXb+jr{?kU+Gn8tmvlH)+}g8t!{Z~+rp^}FZ5(Y_u#
zC>|cf&jv&~VH;ST_*?KlfYmqMq(%fAV{u=?2f`3Jl;GP2A%^J;RRO|jgK7y?5eH+*
z)kKG>twu!M_P5jv4>N;6o<JvkD(8hV-UevVD^3@mTMM<kmTP!ow-Y&fPqW1T`SF^4
ze3|Sn%~B0MQ|^C&+LxEW%jOR6wcbly7dd11kw*Nq)de8T%phD$Q=CXXpfka5GqTt1
z6-L{(rM<ETQYK@hWTL+`xNP?|i>bq_e`lf1Qa_Q_K##qcb~9PIW|r9_$6BC&slTWq
znzepV|8DN-=PG%W1cV}h<Yu;(RIefVt+lP(8j<$rhje>KHho<4{wKOXf&xm51mX{G
zVu8?C$uAlWg`Q!}F1OpFfG!mw^$g4cIrf@9*iw$~$(I6c8cKK;e{h9ljwIKrXYb9k
z2D%d8)(G}-DwuWb4Y2jp%z!>#y^F9q!6d~>Kjs*&O(T&Tb%K$u7ior|L6qUpvxHpd
zrBlscy1wN~Ggg+g01{isYADQ50!~8$va)=1Rz@O!q$y|yz?lN|!ys2kl%g?_aePsa
zE2u|tlI8{k=s-t6JMIPN7eWU3Bc=g)+nK(LpiF<bW5>oH2;G<f+wNik22T!Gpw?B*
z66A;jI818CRx(~83fikG@k!=ZGI;hhaAL9|0g5O|Fs_}$rygd?*fDgVi8scl=_-e!
z0a4nLOOh~-L#Y-0FUv(!^l_`+oyH9v)QScZ&^gL+^VKOPW}X$|57Q-7^t~vbXaok8
z-C}7YGc*OIV#frwqnA|21?28s2`*05{<TJ_AFX7lWR~q|Svx*dnXX90unPik!Xe-q
zCdL(ynuuwDag2*`PoIe7KfsKp#3Y2HTMym12JQ{m({fWV=~fnC43t-PReELGvqz%*
zHIsn0NWu8mcqT5sO{wQ1VZ044CrMT?)_g<)dtu}Rci=bC)nKJoWhU8EcL*=k5SNx?
zzH$25(Q2aU%J>il1wEX=1#+ae7?^9BTxnm&zf9Dg=AkLsgtemwjkT`2h7`j<nOyl8
zes04PYyGJL*#EoPGRYD!Kp=kpLUt5&X?BKu83@oCj05}N9v}g@wmHT`gMcBYUUp9p
z_hQa6rAY}W?pgx0tr0-y<O_hw7=NfWK-c>Jwv5tr7+938Sw{~%Fadg~qveLbzMXnI
z>AHurT|>wn$>mC6gg|NmoFoH)1VSbyB$6-uTuW1bC_ymJnZ_Ww03-m<0EEDZN@$nM
zALtrzA&84wF@oqeKq!_IEa-cQM1$T(gRMvhWOC#WGzDl2tLG=&B*w(32p(qWVPbpt
zv_rO|lNkq?(7L+HyLdFV#zsh{`#l;Usnj2AG#WUif!|TSIt4c*;&a8t%X?}djOzr5
zBG+~s=7oE5D4fif`dfKVDoxXs_TiWSXwp{?Og&g$fjc<>w6?CahMj|{#~$<H>Sf@8
z@-eZHBONdiU`h`TkkW(-AP6%eerz2r|CH6;eEZyeU9Z+ck0@aTt!R^B7bh`N^Pr43
zs3xH)@BH;8a;9KBNBoOd|KCd<zU<!Wn-`p+mX&|@!zIs%W5OK8v@`|4xIdHHp#>d}
za;Q?HL^z-!baE^Bv4pfIwI;E9WbxO9K8RVXpP&|7QsC)+&{>5ORrjBG39|;r`19>-
zy6zV0wk()@$!MWm?IVl*sTz7f=<Q6WXbD6nwi`4=ZR*WLKOygCEeTmdt*o^9ipVxH
z4OM(;*8J&1S{>PHhW-#QGZnT^B*^uKci|xU29aLdDbW!Md+x<<L9{O^TY!(J(&{D5
za4h}M-wTK$NZu%^+rn-aNR<%&2MB64)q!h|lu)&&)6lbuIQWq_-6mS3xp6utSZHn+
zwznIFcJrM0Ppp}3-H>hPXZ2c<!AzRx{g*73v+I>>g&6ocH(z#dJJuHWELj@8uHd~|
zOW&6#F=?F|;p2MZy_0hdTa|5WGcDQ~<I3IY8Iv{s<t>}t?>j*v4HpaMaDuG=oC2ks
zvwgwZofWI@XyuajvaXi~ru`w{gC{UmES%)O5{0jT1XL{Sb8DvTBphYD{$*)6q{`@S
z?6-NovdVd~H~aZ<$$D@Q0i$#%Cq%4+e|py44pj&cU8IlHOE5lVTmNa*SD`*`1Qr~S
zcjY`Q^377stD^q1$kKV)sDn|Va_4~RJZUIBGZLXoj?8j*FD5Y;EeaR19ZPof!n?0o
zCZ5Y}c(bAO{?EDj7NubbVL*M7lg9J~^!XE!1*PDlKNdV+H+s?EkS`B63(Fx+fCxVg
zWnc&6dOOH>?GLR?B``yKB+=<xn_l(qw*0KSsLZi21Jly!#yxEJ_G=Ec6KSnu7U`ZP
zC1-SUQI_T&+Y7<7btLKspZsOjs{(#arWym#{N}$l3I^P6jd}ppm2PY%hmwd9uEZ*N
zN4g**otJ(PjdBH5tPRo+)Ox-gv(d5uY{$t`y_=eQ6N#EzU_IoCUvYh&@DfEjG!|%Z
zntW{I{HzHkyIV&U;v?`=%d<Oq8P(JBLzViiRO6c<{sca|j&lMW&txTYdo~fJV|)Hr
z9e14K&(vtQ?c)cqXDDsSYYY3~{hCE8YspVjc%fA_zDwn!i;y0(;Zfn}D!a1q;M*60
z{{cvU!CwDES(WKiR<TB8F7u1N=A2Sw!a<uvM7QkbLyV>a<QtsVhmI<~>kIC>>lvTQ
z)K)Erv_FhS$xvrO6tC@(R-w#Wg{6P7uZEjz$%t2!4_=mYi#N`(2_@!l5_pK^?GDOS
zpGp|5_$P0FDk^(49uSZP81-OusiZ%OplijxeTitiYV{!=VlnSztL@L<hA2ALTk8Zm
z&bM~H`FQY2-?<@9gK7|d82nHEw`N)?c#he*lpyeog|N6ncw{pn;KNY&C@&FU_1tnh
z`#JS1#r)}WGw0=2$>KaKS`FKpfp39U#)b=pz$+EWwzjyFk}h{wlv!~u-t*cJ-dJ~P
z<&H*=wlA|Azg<HNkPCGzANbwF{3qvN%ijuvdAi;?_(p|V8oUUS?LZt~2`y<e#j~WD
z#|kK|m**1kds|1L4*iqe;|;gp9e&WFr?sokz+|%G3rb~}_&m{)lyq`<fi%x=fFkH7
zyxm|fyl*SgtrHVMCUjqYITM79E7a>S=oS1k@A@!EqYN!4u69P9M-NC#6lvH+xuJBb
zqtLeGcz{zQH0wE}m#(j4h$G3+3v5pX2~zBGEEDmC*_QFb4bYucnapN(M~T=1Cs=E|
zYzmTdCrxcL%ygO@;H|FCifvAweidp=sHtQM=C1S6;1NLW2jf$>mJ#%j5S|+F|E?g2
zCOlUI_}^Fe`06Dlw*q!=JY4V_MAC#d9X1*?AOwutMTkJl0d=rVvZ`v<s`E$Dey!}C
z$?5Fti3dlolHNC}>u0MAw_H$ZlOLC1@|q3wXBg#h^5D|Hf*c&nWr`$7iIr615ahmc
z_&)a%_B&y41%4HN9XeU%?KXm7r9e|l*AibZj!Ub$rgOV!wAZ0vI#3%*6TH`3l>+LH
zW5SPWilQX<t7*YI0B`3Y@f@A|I038EPH>kzxcS>D2mTK)(el+U_66tW&uZ$V=2j{t
zMLrf?%Fy8{8ps(U-u9I_lO$J^@beW$WoudN8E3?fiK%2dk+d13GT`DyNKrX|eKAh3
zh7nbLe_cHuUiA3U&+k=xo#gZK9La)9Vu6iyZ}LssJh|#2e-3Y+b5r&P3=X`scMV;R
zIqAV1mvXGU8T^-}8h@`AyjG}pbS2F4pyO3Ue7lm-DUI1Fcb%8Y7%j>|W_*82V8~v7
z_$=X*HLDXojS_?=)P7l~yv_i?;U=lUR)rwmoEj56I8wU?Q9hN@S%`r`qY5<`k*aFi
zQ~*(~ThnSPfRtPrsIpjB{SpX>c#%Yqp*O(AI!W-I(AQw2O*=-0L+X?4r%hAso!KZx
ze>9R0y6Fhl05IOWA}LUkf?)h8N+&jf0Y)U7E5Pj5cwcHjiB$}zq5w!C_B4+bAX)1f
zYyyCBC<P?=L@N~VhCAj>g%kXZX(Akd!_Rd*46;+SUYLT4jyF^=DH75EJmF5^_gRJD
zt6VsNkfdd-SUl1)CJ;?%ur8Rd7fQZfVC1G&;G9b-tkb>+i73rbGA1yGYEQV?u3}t@
zrU5luPQ7DNp!31<0bI6xw33<mp3Rl<9e$X<+A5}c2nAi#IgDr}H9tt6dFfYs#u_d}
zM95)XXoJ)~l(RP??T0A*lSV?<Wv%WLy1gYrADK>UJx@dwy{Q^@Dk;mf5Z(9m6e-n%
zO6~Uyxa`0)oaHNCQR{#J*eF4=a_6B9q!8=x5X93B{2Zooo}zoxES+5{PWJZ{nB>+a
zTIJp4Ibc+lQPV9%2aSP$qSHR<a8WG;XpZc`{Q`H+5NDwnF=e+X2&odQu^QSsl@hDH
ziNSmK8v0&UH{bP8aKGlqHmiw`aJ_b8v9<rxcdupfmBXef$uEJ|OagM1Vp7ICjFlvO
z33$SkrcCE6xmIaoV)EO$y?$;Qdteio=^6DjpyRTVAa)^_j4xBn$XcH)^E_qCvOYuP
zk!q5OCB;wX7I(h{fkEZa=_Cnwrbse#H9_owO=ulwFPkB_j)}}<_MP6dBnciyR<p2=
zRlyl6QD`~7hCW^tkshOGkFP%1h_BL+h@d$L<*dHdbOYXZ+sr5xlqbBku=1V6S|zf#
zWmYeV*rmS|+OlChGIQ>D%@W}enxQX7i<>ikBJg(8G)a-PjULl=<V>!mKP@%Z(?vPs
z2rME}WIC|OilPB^E@Be#W)mHAhtlnq*oDCUD<!(YhEVFw?|JeUwRA7OE@!;VnXMfV
zu@PTAuFM_B3=NhuOJHosY~G5<2HQ>>xJ#yV^_#(hF4rrc6a4lQ^0MT9O~CT${zs+1
zVa)UTa(0_l7rELUCz>=|f9GX;1VZrE#Mkd(L+RrC!UrARYO(O5b-WOE6HVO>!Wqsp
z8QMB0_BKyXd+pzyJ6+R?d@804b_!?Q{@z)artr>6v><DvVQ2MMbTw-0!QS&Q;dW`i
z$JwOkk4uO6?`UQVb^=QZ5@w&c)|I4jMQqB_JD#qd1()F*j&7|_u_Mbe1$RBaK)SQ(
zG0h7&k|+JBn)Z@^a+bwj#!C<UAE|Er*{{A)r8v5J%ESI$1!|}i%n0(54nfOv-wojo
zR7K^>(jMo{aGMr~{%mT&ZX|Z8=5AC=$A$-->pFRN(Eu!JY{v&%B1D~0vf5KjOObT-
z-R?U{c!^vSN^?Zs0!iP!z$Z2qI1wyoBEFWNmTq4?i~9q^Y_reP>VJD^lMyMW4bIya
z(40k)yhI+3ZvT#lyTX1p34!mj3xQdKYzHy}0ejNYVF~5N#9${FOt!^CEbz)iOEd~j
z+x+=gKEZi4Py0ihO0&bE?6bROuT3tU=Y6|=pkaJjSJcyi#1OVOOaqQHL$8H9-uW<z
zW^FCVlgsmUD$aI6S}5cl&F@A>V8>-)IVqkkd<wK$pd_g1rn796LX(j1xEpl(%8$^8
zZr{|7ukVBW{eHnM)ek8h)^~!6ojdfCZYmF_MYo`b4#Nch>Q0}xKe9A&W;*JZOeR}~
z@0-6`UcUfo$tzJ2Ml(u1+=HmGWG)Z$hoe3pUTlPj2WR13NNe>oRJ#W<a45!OcZHEg
zxs=yJDd~O+zJ}TJ>8j%5f=6m*0jtqy-M3IVP1`M-rrM`m?Vc_FUjf%XZVgV2VHBpm
z%()6F%ZUE2#5|2%bWr>~e>9s5T##w^Oo@&i6RPuDv+J$5>6R{%++m4A8R-sd(^(z+
zriP%UW$>7ZGzlWeD%%RDgZ??P4a)bH9bydk9dsT$M3|fLOLtfP2_BHWduj0CWcX#w
z+tP2<z|I%o=2*`VUhg=E6-1G{+U1B2&(GgYZ^PFP?2tKqFMvzhY$9uICdrReBlTyO
zUJyv@EqyMlUieYG1{3`cP(5Jzse@g|yEX)J|3d&>iKyo|3JV_mIAb%_W!W@;kN<n7
z)1telEAPEIC6EKtMd2OykMt8R*n1Zj*4@mJ4ZWjC#Eoo+yw2YyKl%@#pHnY`)tPQI
z6b(4YOSz*f-g{xc_$I8cE6l4M<5Bi<=~-uO-)-MdM}c*d-CFA^E1E116_!84r?KD5
zmb8k_s5)?)uVy=g#_u!?_6X>|F%Kh`oU|K)7hpD**iTY7rqm??J5fMffqK(A^6;;c
z7yG%L`Nna1$X}g?beb3yhL5p!OG``ace#}Ro_2el56v`RAfD~iJ~Yat6jpt2Plj#Y
z+M^r(@ukyy$0leYBE_+z1yk?Hafl+)=f*E!D14_a7F0#X>V9EOHH!Z8O~_eU5R4!c
zI~sC?N`@OKdWtOs;pOu8u)NuWIG98c0mP|Y7sph2kbJ8Gc->GRXs=X&DMaJ}dn^!-
zT5&2_Xt2d;CaN+VE`2wyssJ`e18I;}P?1umkj!ucvyQn|cj?h~<Em>9V?u-rqEf`m
zh|Eg%1>G0<S1f^>uNq%({>zFEJFR?*Gve+kM<HmyHc%r6oXOQ~`A;Kz*Pl%tRp+ME
zSgdq(@M(g5=U@z>{>9+V%_PYrF|VQBG>yML^l;s_bx@W0ru1N)1}4_|2$shhCGlM9
zAar?;Z^tAx_B&n`!9LUFk<j8_&uORAy0GF8MXYTi%vXFoRaEes>g;v(^QF;W7Uc{H
z1q`B>phJ?cc5h!#at<bq`~}WZouK7n>D*m-qJJSnm=_RtRdQF=3_qQYr-n(w0#D1V
zbJM)tXd~OL+Fv|)YvM<G2hsX><o_SQnZHfRhWdT%iBTq5<thJ%CwS+9@=b=?)NZju
zfr`#Hd9PGY%ww7bwy@_F(#v1odXelsh0zbM&jsm-^k4IX)|{ii?(FFXDh4XXY|`i^
zwIvoWSMJ~x84O=uQHD*&EH&zmdRni2C$Cb8DGj^(tTZ&yR6#s3KeV|@<FAwO>h7%c
z`oKz5WCAzWgp=%=0$&wi2?AEEH6^LTYxrjnCTFOz6x~6x>FdkN5UoYHn%~W=_7YEA
zc)OWF&G=X<$(s2yCG0z0)kY9tyQd=}UA(GD=M|&aX1JRgBh%g(QJG2l$jv07mGge+
z71C;46)9}{jD%Y1#H8)QZRMLTSeN@I1k?>UGEXj*I73X-Kbt$5#?z-*SAi}9g9uLR
z%7S?U{Z!iMIvgWT5mbePaw0^sN3@Nn0n#bkQUz4~*e`jD<(^t1QJA{`2dBo43Yqe<
zIDK>J<_`YjjeR$Btc%kGy>7v;ry;2uRZY7R@WfxEzXsa(Op^o(oK1_bp$8S3l4Nc;
zI{2ejm_Xa~*v!wAP?v(0inbiXca%r>I+Y0^jy@{uzQJOTL}RuT(s`8`?nPViHK{+d
z3yV&yjz!!|>#bHQn|Dt10e9IPeP8>hYmuF(9g;m8F5)o9;?^*WS_+_g!)PWZgW{W9
zb&h^J8_)fLmV@%158efRozJNq>D6d8TY>u&;9f`#pJt6-Red)0;Ql~Ehucn5{2Ab1
z=4y$i49s>?0mpK+uK2j~GD;Pd8GU51D~H^duN;gUW$Pj*o4};PsaQ)p%8E}B0p+U!
zWf_Kj9nQ(6i3M<}ROnAaG*7e|N)aZNade_>2p+@l5I;E3(OWEPedkhDfzM&BhF;T4
zRfdN87_DhU(GavTvO+FU)B*&F<RbX~#k$_|Tg`^3ka8vG1WLnj4KCK}N@}_F0xgx+
zzRg#-mI8JNaDn)&EP&U65ah31GZfLjLM|_YNTKR*<0Lf@1E)V2&#-@z7B9Iqs^Eez
zu}GjPZb7k)QB6lXB9nUKBLEW5cr;NjwFq=dRWzkN+H^`4q;SqCIk+(nIT-_xzzxfQ
z6{+NeglWa~Ou#SOsnp82Rd*P~PjNfvTN|em^*q9H6XWt9U{0@KQtqlkoCMetRjzX3
z!s&ovroM+1_hod*<Dx@+I5?yXR}pRq7r@adoO9Ypl>cRts_V+%8q1yhG5O;d{T}Gx
zoEUpiegMY1T2E!gD}el;(E#>`+lN<^e8T(=^9Pe@kW>Q8sr_)xU&8N;m}Ds|D3=L|
zR{3`U!1)f7FTR9f0uV$5jlhmuY$!RzmC@n+z6$-~6cL%BjjjX&yigI=5U`2PG>4I!
z&jC1o2WB#~Pb_eta~}|8GDw`b(Zi>y7>Fdv7~Ft6gr{{CP)WjWVy7XzV?@<?S0Lxq
zoA=JCxP%tt9PLlN{AbbtWU^8i=QH+L%-}KMXVJ&NnB3SoxL_zGT<`-C2~3q->d+NX
z*29TBnT?{nn<}_2LlV>jaJwg*E7;AR=rM8Bqdl!q!;7*xxH?1XlpdH22G~xqmVyDS
zbp>4kIMN7?q|T7hBg%h<z)!rL($dBCUwd{DM92!<A`;iOf-0D3L|F?eOfB{RL?1KZ
z>cwTCOk;v-K`FgrU4Shl!Yrtq9}WoK(BK5M0w6dhJEgUK>w+zYaW&LLTL4jl%BU^_
zU@(k%KuF+$t^^hikTl>r(mT*8Fr{Ud(z2%M!Kb_<HxBnTm;iQOB8ZN3W?@okU~<<Z
zO<cB%DiT0ml_Ro&CVz~fuyqIoW6X)`GYcN9M9=kz(_SLST}z|MQrzrYsS5=LxZ>~=
zofE?aD9AKb{|1zYO)UcZ*#w4gci+Yc0_1MzwCk$0#x{lmaNjtSB3A?vaSXH^g8@tc
zaXB>gbZcH2Qe3=kg5tS*$(J41`FO@E)_;y2BPa2X7<^k7A`lpQ+>xSRbjqY<6*V-S
zwwd(;c?#v_*%37z|I|%8_~8@fdvsMzbv2=fLJ7%vBY5U5S$Ly6Hg}oxvuNsf9o3!F
z+R3+USfY*xOR5Vb_id)X_MT7wXcJ}R3$gjJ-Qh^>hMcMUAWJm7G27h;d}DF`BlSIX
zJ8kTbbOQ2KF=-v%$6Arr8?~AyuPgl(*654j^=Ie;M`U5)*(ixhmcfwx;D8yO`uzFi
z^wrsirAMlwra#fZcb<34`-krWP26U`n|efZC@Z@|v_0Ac%qz%k{#dbReP_}=orYtv
z4U)wNxeiXm8Bf`&=i3VI%-f$d*Ujrp$a9$3cmvZvKW{lP_vSh4i^{XVxh#1`ne;15
zMUYOOBe-J^@`XZR6%Z~&@KD$xx%H6v<jP?Big;&)iiK+N+U2~?_hHM?0%@(xZPHAg
zD4`VH!$AFMiP2M;)p_|HC2Y_xaa>z$*H(&QN3BGS^*6hp#~P4uZI_g^lxg#jK#KIT
z2sB%YE?_xZ+y0kuEXt2WcL4qy952X~tUWX#{a~M}sc|G@q0UARx!gMxLV*@%IuBz;
zNM*ivv@F@~PKm$G+RmvD36g1Ex*6;IE+_nF?vdz+kKckNJ5Xx$PP#K~95nk9_6r6{
ziDaht<~|r`tTo3A>!Cntcnc~`ul;z3yYtC|KixLJPaf>)aMSfSO9<b0)Uq?4_B6Dw
z?KU!%J@0dVMpanJI#=xe9{`v%Gc%U>+1ci8*07)Nft{O7x4SySEzhI=e@}YmjwTAy
z`oHzz4c%H6*$#6pja`0U@6ron!P#?O=rCk>jF#~-$<-({#$Sp`KJ7}%uf8PUp`S3#
z>;BoX8}y4Rg0&F(a;8m_2JeRk!y9yUqi4_LkrycElQEsHCn0s#Mltc_{Nbe_D9?*=
zQG682&nSJ!eBA9_W~JPZw8Bd&tFABIdi_!+#O32#lCs@dPd|RHtk7<1gAjvL^=u;T
zqt9Lc0ay<nS@(Z+voQct$~_hy-zuDmdKu5wBjo=4(2OvXV0y-{SeCf(Td?&@)>}*Y
zs#2v>c=qE!FZrr$4fUj@TPNwMH->$4Hgl#%9V@lmYgR!Zflfv4=b6+I_J)z~EF141
zIT5z-&d$;0sPg8scqvO+cX9Ncmag=yE(SBb$SF_=$6K8(y$567s#a0xB?zv4NPaQI
zS$&db2XgIL&K=f1zD$q^sW75-tTSGFk3$#zNylhQKQGC<9%hXRo9j4G1-3E<d``#s
zOUdGaIk&&CJfA5xn|A5)K@83_R@DX?j?$MOC%$k0zUs1Ps_y=vaDv^aM~|T9mCoQ1
zEb}n+cW;C=Dv2yBi-$<XHi(`AHxD=c(WTX!+V{lx3k!>K^-p|hmai`dlzya>ZzIkV
zy;L-nJAixML4u0~S7Qe8B7>UYLY)Tv6~qQQR0|^%B6akC4ZN(Ec6G`!U9Tq?74<4d
zZD!*r;!!=7Nv~qn72akqYGpO)Fdf;(4W^6-#SK|{E@71Z14xj6qMO@fs!7+Db>T1S
zcbFOWhqpY?p_WLR2VUuOqUoQzaK(c+W|1M{h)ufZt%{T=?1Wp^(|60UW-F@?O<L;@
z^s-l<r>_B5FWKVMMG~$vi^AP_28T!v^rh=wzD#F&uM`0iiN%zn!c6_Gt(<-p<CY8f
ziK|W*6~~K<Fk(S|IeJIA+{RI;L&D|*@%3WfC?9I5l?GJK!?}cq-fdyn^XWepZ6=22
z$@B%Q=12a0aP<2i<$L*${|?j6q%06CB@yvY)8H9GBZ>Yd1V)347u5pln5dtt)31|V
z`FR$yqEb6R%e_;SeCykC&ptBwM~(XktDF5kMwapVEurckCi8wcelcFJ))VKiB%^>m
z?Rg`ARV8(zTi^QI%|k+$7D~PW&j<=*y~Q#z1E71_@}NV1Lye)*RTjo%BB2t~m7;IL
zVWxTGD`4&n2aw=|$4oAI$o%>oQ<-?*Qv-H?KyrapFY34@f4uOBH>IzHS_7cNuYXmg
zyNyI?LM5WXbRN9ZAIi;OfCEFPWT>r}7R+{oJHIFtW*ZBp3=|!#VtK<${<*T!J5>Fc
z$e310;=qtpO?hwgOn^YS89X>dE{Kfvh4X5Orjk|pX?YLl((tneBmaMBYd{4L!cDM<
zv-(bBv%%CXH)b{{!Co%}aSL$<U}smbpSkmInZPHRMnbXNh4N$#h<z)miQ4yy9KeQ8
zi4}V$rL~U|#yQIXAK$gtO_NOk2PMwtV$SFxs8DcDyZ^E-?V!2<%Bx7%>H%=EPF<Ey
zoR^C(<Wdh#=ugeU4WVX}kMJcH;6{8%9v)a?HG=SDj0rix236dFzw{+z+MJX~Zd0xw
zUetbm^s>W(BS`JOIzvHe{PY=*=8m)f=UfzwY&{Y4a3z%tTTh%{6oNbg6VtSb0;a$c
zZ+MV;p6-tqKWXs_j4a@G7qHy#;R1MPny1=RUu6Zqqjg>PH2qwajPW;qm!>8w@A-l$
z;69ANC>+L&cCGakrpYK@jv}$v-%iDIDz=vDUdUj@MhyVOD_noh2<$AxPEYx8FY4r&
zK+?2bJLtT&3+e~Q1j$wVa(!X1AJ*bo)b~riQp~&<aB%^;tR#@55~uoV?>>!(yH&_v
z3~07=Rg<HMGe(thZGi~+N(U##s^9|5`xCebVF%~MdR9CQaHhMEw)ES`uAA~auuk&n
zoATuWDW&T&)lDqkVv8oUb3@5w+LZBpfQhZT;{<NYu85(1cM2v-8JVp#OY!o#>)F>J
zt-X$L`Xwz2+teYTWDTrsCe8BsBW*U(x=QXoPJa3wSxb@Ztl>vYT3O3OT_}|6G^U*t
zYi8mIhZ1ZT(2NWKG?#_s@o@O;&~r6h@zfHqUCg|?3QNTWqphMPG3KLRXxt1f=+w%N
z1xt0ni{D_)K3rOh6cR5iYU&I_C%Mh!c|y~bYc#D`ju}k<P1YRnln^qvY~Q32b4K82
z;B!17;Ka(fl$7NA?qL#r4Je_6%s#B=aD}4j@>N{%7QY((AHY6-r>TO0FOwC6H<V^5
z8Y74Zbu4(Kx(24`R_;IwF!^`5V9NN}e<jIjce^s87$<Zc0GRA0=rDmfrK_!JR><Ya
zfT|Y>s1i4MOV(R8|FN31cSxFrnNUbZ{=gJP(1^4!jWv8ADK0$5#Q>u;dv<s+xLuGz
za*OF;+=CE*C?0RRROvZjQ15PtWbSbt<rV4_3dMj3hc$;?%aooOsr`YcIdUe#ru5zh
za>OZ@Zd3t}83aW_E|BvRh8hM*6<PVAcawyaf^lbp<8P{T5X7BBWsfZ~u{KDM_DW^j
z6I~79p)uY<c@jk^o=NmV`QFlBSG+%L)hd~IFvU~wJ03Pg^AVer)Dl)-^CT7e5vQ+0
zR?MH1+*~vS{ESxIc2x#g&>t;ijPwH=>}}*7+t1Yz?5O&AcdQL6ZHzP%@49<VX?>+C
z7$kO~7j&~`_wI@cz4iRen!@Fnruo2Pd(Pq+yIpr}=qdWZjIw2XJ}vK4*cFofb%*~a
z3vY4HpWi-IwxP32B-;1%IW=j{agqW_Tt%hctc^&<POZW)xBF@1{7m(k>y+TRC^Bzu
zvUA|&@^Xk&#EH9E>i+qru#0z_ijIxCmustD(3}j$gND;|H`ELoB2IAKe<v#)SSZG|
z8BfyV($gaB<41yIt)QHOt-WF#T(+>D-9@Cm?ddt2iOo?jif=pIN#9;>{vl9T$@1XE
zr(}i<Mf`7mmG#Cm0Z6gehAcnLZr`F<>eK1Y*{Qt02#PVXe{GA+uau|=SrpXdil_E9
z{BY#+=3urf$^BVYiPY0hfWPg~Uo257(EGUE`uN@S%#_8Go}FA+c}6r0_U!!8ak3lZ
zvU#-J&Pv_Khv`hdD^>Yy-Z6oEqE|Y0>dB8(vUVQ~r<KNU!cN`8ay}Qym#%OqQ3f^|
zVFKj?DL{hI5T#*xGBWQiTj>(H?ta^fW+^*#Ggl(PQej0)_F1@)#huo0S<x3?n^3R9
zhF{u*p&FPc^?ipFHb$$$%eu5V%{DdHd{1p|EZp90pE#H(jo6<iZ4KW9McDU=zv%Ik
z3b8zE8RI|cshy+gMM6Jj*twSe+k_6@`~MZz#IB~q9hE<@U0$(my3Am@j|*0(#E79k
z{Gg4FDen)HKt(D9G*OIdnk@g@?Olf7s?7DO(0np}qyvK}FlnCu2S~A)>B-J;1mJp@
zrRcy!9K`aMFNe_gwIs)l1kVSzuMeN`6NbB&H2tyJ5S}52JG84$4zD^yD%=_!<!cQw
zH%^*bA6uNHAl<5ey2Q`Fr8uRmQ<<+?1Q#Esqi@J}>r{vq)Wp*dY_ggpKBPW59}9h1
zq<IXDE4ZEU<7^&P`(4{N>0oe`km8bwOFS*g*(rV}A&lXowe-8M!02;nWLpx8)QM3R
zCkHun7FO-~n$Y!I05={itMTgZG{J7$i`QaP$<Qe2i+ADM_d;Y(meq!OuicuOc`WHS
z;yUyKlNIBWY_^7d!EDAwI43e;7%L`sxoeJXm2g@$wBc-o(Tg$Nk{#6p&_a(2MuTm<
z_NlZ#!{i6-NJ-p+u*pC;prHwG0S9ERq#cfoFAyzPiHQ<EMAX|bRCbe7(l(0nA83>3
zZYK*p7X#h-=J6+nTUU>*8&EHvEcZ$Ln?#VE7DZv-c`XCy6a!Bcf5^a$7L7MPom<I9
zvVi2G&v@VvMO@c}8E_%tE%=W$9NLF5or!AX`0{6az~->)ZQj2J%fi$r8#Es(oi=~4
zs<Z9wlYIS~O7l&iLcHZe#983I!P~jOQ<4GMcg5`?Zef&^78<DLx@DJ%>204dFTMnE
zm6BqcDNniVea>(S3*}$^k(AE`RXsn#uIwYT-p>B>sL$ieoA4XczY|yOGn#{oJW}4i
z-Y|TR|8Eskzf1CGmi`y|kwe5tWw*<5`kO`phCjQ+q1bGmqFC5lM6fKbTdF3fV&3Z8
zh@%RKMf{&CP<+wMqztD2Ali~KgbwwIa^l5V=b{2po%PEZS4o=Ari;P!8t<^L%R924
zhHlktgqXzkOw;{rdo~wTeO->9K)y-gCY7FdJDuPK^eGf<tg()JtP|-Y#5enpQQPXT
zYm;qjQ?wzS3)AXsnA;ggN9`Zj$2Q??UXlfsOe-;u5cRJ03_7u3g~YH~Iyf%O$sYIr
zHzWRDZipY)yDS^z_Uj<E>AFIv)&`|*Y_r>z+<g1*P34DO{5!Y57_L9?q_*eHXWX#|
zvo#++3679&M1!f_4=Pk6Q|z-?^n^L`ex~@F5*ml}-eRAxn`ChR^#{{t@y5cHT7JQN
zyFROp?Cc83e2b#V@kNLz4qu|6&s64X#;T&PA!VK#gKJ;}#Ts#_NfQB<!+O+xFSj_q
z*e$NX4vhm2$mnR?jmPdo<KJkVHn_8liWa>3OQghGf9>Rd34GoYg>fHz4>ou<xA7?=
z(9Wa5)+Yh?j|8e-x?i+B9s57*)^>=%?EzhMtC?pA*Wi=rBa1mL-Y5*maHRpaxB@Y{
zx}JgEBL^ZdDD@Sm<f)ep@w&MeMx^LR%e#JO^EDN%5$H|w-6gW_)6RL$x`5{SJI$|r
z3aL-}5eeW(3UH()66<BeF}c(FXitd&*vHB^%spR9T6XGRB2SMC{DOzVSjLNb3kHD{
zuhA^b%NJkD6EFGdkcp&z&74=Yi^Rv7o=lAO^rWSB78W)E<~L>$W~b!05rMBQlU0SD
zmYd)48nwRS7MIH6*wE$KL28pQ4#<g-AZo5$i-I(1Lmf<mD2uXW<SN(|Ot&6MFib7v
z!!oMMdEpJl9g{RKbV>M;a`>U9Iar_-%fmEGMpfkzu2W~&$C7weKJWzCIRUh?WI2J^
z>->d=o@$3)Zy=3{r7jWF5_$_!egd@bRs(RDYPytA{7ru_v8I9vHbXCp^gn=Hx!jR9
zArC?HpQ#(nCf-8g`9dzK+Rn{XObBuU$+hz}BC~HT`aqW+H>^IK>aR@@BL{k)2q`LB
zxp=pUZF)CusCWz6Ijz{)uB7oW#zX5G{FEPfG7Gm+3cfYP^Vd?J*a446qB3!fOxJPc
z>Se{LVmGoK7(g8Z$L)Uf$n{tM16TuS*nGi!F|MqkllZHYx04FSazK~pF-~$LM41wf
zFdj0&RKX>ulGz%23ZgUysKg}FE#$z#OAeF&qwCGXp?duA?_q4&Wn|yQj4jKM-B9*@
zCQC@7FeJ;^vy5bEvWC(mhM6&TDne4qGE@`BR!Fui$-X9hp7VYFd#>mA`{P`fKMdzO
zW1RQ7-}n8xr9tp$@{IRjTo{5&98e#B#1dsP|D8sFczSbp_s9y<SU`x(p%=%6P2`h>
zPhgpByQ>yL#1?DKWvCFC#`F()Q=(Oj{)k(jE=2ixjP6LNie)VcShi^J90vW4!z0yK
z%n=*I&El~nDH<r$5ZWW=O9o02fi)~q_TR^QVVwj}7(F>R0exnPEWC6a0NOBT`yE3X
zAgjhOVtIOj@X@{Oiez?s7-<+gKp@FNK*ia;$)$0q6na7NW*8!E{wD-T!sS?BqJhq<
zV%AK=?hXeCZLFGy0V-|9Lh(*9D$T;3Mf?qYDf{j4UDO-NhBzh#g$@vdH3G2nayN0_
znNIpx5E@q!z$9ssy~_eNJQ`&E4tc&z6K;5F$V+S%UoP*IB1@)<FB44gFikUtP%?>3
zF!jOd4NYUY(SR&D44gENyC=@Ri48;&Ur8E(i-7E#h}kfJxCRID9}aRUByEu)pok-&
zIFbv*^7s+(Gz)K<fHI5}5#hxLaBOrSAhQ<WL0&LTtHYs@LB_@Gk<wIgz{p|kZa)%D
zK%ik^G)Sj4EUu*K`3po>2hcCMd<<p4{6#v^bI2f8<5UPAkXYocNH&o}MgiL8k<*8A
zz%t|*=QQYq2kD8hLL%Y*+Xn=nApk+VW*$pm9td;~350=WZSw5MtCls{;sM7iZDbm=
z=k<@7Ge~~CKJZKiNUnIO{2X#I7tgE@7;d9U8;CiqxY>CXkZOQ@KD@v!T2KaO8a53$
zNTf#!QpS?|2&VZx=fwcaY^T?5G?@b*{lxkgbn2D>G#iUWwt3zUB>h8mCpMpl)VpH`
zlu@?8Zg0qp`YA)r!rgvUSGXe9=Xu}$%?O_gc4ko%h^OIGE_vOmeRgdgYt;*WCOG3d
zTNM1K>cfZM^YYfr45}ai?XJz>H763eOJqz29{(V%@B&Z-=@w_J0WK2KnZ@TL7PjHJ
z|9)On<xH6L1?d^ZdqHuFL#jl@YlC@NeX#;dMskPV2h!`c7k;4;v$vM^s<TS|<;$&=
zbsu*1wz#ise=PF$a`V^K>guij5*_9tc%(92s-C?r=<3Drw-JpuPS@h$^%Sb(t(DcM
zC{bsx+7~bW`D7>OJ0(vKH4(UM(Y9&M94SIgJHL5&2@~3|n9$X(tK~P|wJ#WFJ+1UO
z&lSTprCytGfB2WA`sZg!Dj4dl^N;Pxn4>EPE&9Slsf9Q(_OI8r^=gw0vO{Z1tg04n
zoo$l0Pm$Q|NppK}Q+ET^&-{zfGa})>#PF&|^UEy*W7!vFy_Q@Fs<S_=jhT{1hAJOB
zP3mZ6wvatSS8Y_whqn(|-$6%|FYmm3%{vq4ldSoY&YIO54c@KTkSL(~bX&hvL&?Zq
z1c|(bk2_Dvfg+Fa-375J!UBoCi#K1p9W1~AmXciO3(OPQxcb>CXCKYHug2DZiA%a@
zCa-ve<?=Mkv80K4?d4k_Lu0*A(0nE?s@I?xd7(_eRoI7Z&i7O0L66O^G#~ZC>aFLL
zy;Ya9A<B1js8!{20gu7^+Va9TGh41T;2sH|oi>4Mt`&(b%$GJa``bmf-r_c?MrvAh
zVg3ZpYCFJo)3I=&df$gGkKH)GXqeT+*R3bmMT(542Jh9hqg6oxv$y|9@&5G0{Y^62
zI#)M4u7N%n{zy4AVe;Psn%*~hAHEW?sQxCL4yNVYOJZL`EsZJDYVO3rHdS$NGF=-z
z<d765MOD$=>S_4B399);^C7=&dvo)v2|Xcby>5{nLR*WKBVVy)>q*e_t@j!5_5>pj
zj)f;0Fz`We$}ZgGGyaQ+ivcbP=W6VaA4@P2o{_sB+$w$7@9o@gUrhK8<V@>QfH-r+
z!Kq+-p5NP4lZ;10m4@#M&3VoQxw<3;ru`5X+=%Zo{#sF!uc~d%Ynxs0gF<hqjlWp)
zJJ)t>-+q+=`oTfBcI8h+^YhuK?3R>5DO}G-8xMgmQP<hVZQqRh(f4ei3Oj<(^)}=6
z@#e{6t<7JL8zhJ!x6he;qV^6Z1TFD!U(34CJtp|lQr2=o^qF|gZ|#xb<}9Xu-?&t~
zapC-p+%ON+p>sz5E4UZDnW1pVk^7_uyVa4N*6g86LeFF$NGfAzUNq>8#k<yc*oBb;
zbIx}=y;!`olS8Qs4-aHClWp0&r%2Iqu&6l?Gt3AHCgCjX{*6T3QULl%A1?jtT6MLX
zXJjODIu3tKM9W^IzK@$Jc&2^%#uGo2ABfvK^t}4u9A_z>c+?IUrj%D22Xy&xw1K|a
zThuAHWW4<|o!IQ6AM5brtD&8Vva8}hOV(xd4twwY=!`Rewf~g_zNM2t?~7UptvZXn
zxgf<}UpK(YI`+I?(<Jw-=1APIv-NB6W=xNq*@QuhgZm9rdyOzh%@EVA;DNLY?v`~k
zZ(8zCZffivb4kdLt{IppN4w}bd>h&RQ`MXB;&2Q+agT>q@*}8rv-IJApvE;1z@B@!
z5v&pV1+0<N`$lRwM@hOS5ToAdtFS01(OWnq;1R%q@2H-hocev17R=tm&+}Nzt9UG^
z&qE-yMHsALfD#?NQYZ?}>ou$@d-xZ1@AxOZ(D(eAxhIA>?oH|juf_!+4;!7ap`n4o
zS8aUj9A(5Fg~DddH3HaKbO2}CS4)zUVoMP*fZABq4GxiIDaYM1NfwrWrZS(IRU}@O
zk@>eu?=yeVLe|Sneb?HRQ`MaAQ?7i6QMy$<@mhuD?9bh`vA5|oKcmw<t-8@sQm>6o
zOH0(h9uLq-P@r=xTt0NsBn%i~W$s5ZWM8ZwKEz=&M<0HE_Vm||s^8Ad_336*nEb29
zwIuz34ZBHP)LoPnH7+kJ-~hJ2a;@WW8>#e+sPI|YFfs4o(5|r4=AMv=7|58eu1wSY
zsVE2$LwI62M9Z0wX>Gr%p2ts3K6Ejtto$Z+W$dW1+p)-f4ke-9lIa}#O?OHo&|fKw
zlV+Xq(&BX7y`jBi&p@$riBS8EHNQk?u7uB3qG`@V7RP?mUqFy|IBf-|eKQP6l`Km1
zT>24a&ug9D(xH^>S)sXN%?7T!8ainifm${*AN#u6>V4M_&-emth(<^>)$v_Q`9N}H
zs1|B(?UVsN5v&tL4a}Muwm_T9l9sou`1<s;Ak97;*kLQ5Q}*7YDDITNRCW~TwFOii
z(jcENB(rrbr%or?Cb{K^&M1`#xLo06O{WKpTXt$PPoKJRkMb(KcW;)vF)mZ%%gTx)
zsr5ifOi`5R3Wg@W;XR@dgb+#C3}B!{*9R~iVQg&7I+x=$s{{6<d$j8GU@D}UKK}Db
z?EbjAUCTYDXP2MfY$><{HNMxFfH5CsO_fY_)f#>9YwUngcdjrFsitUt_XwDo@-o~+
z9J@NyaHg8O1lGs)BWJnHSpsBBU~bAf#q4)tDVwfB0uqKW?2M+pqXPxrBbjQz8^AD?
zheO_Ps1prWUqyykZqxeyFoR5Q+}?3&o6ynH_hb<RACCH5l(1uC;+$^!vw%{!=5plz
z3jJyUe_?t)xZ+CAj{(R^-Nd)l=&UZzw5%4eS(-&D8RB=3qPu3vy!HW-RsddgfaMLI
z1Td-}`aB8PB~K>Pq`jdGYE3sqxS?JS5YVhW6~d5Wp+hiPGgD<F9UJR`ppbNmJF}FS
z*?CoCcJ*m22o|?blC2Zx0ttOsu?w|mHiqZ)?Go5D0@kciko28usJ>&sGK@QHtcWcX
z+II}?)gNk_!*X)ci|6aaPM{0Gm~ApXR+@=JsIMYc=!Ko?|KnM)qO6VXl{_dpta6{0
zmY9Y5u2|2Q8dkeisP)x4dB$m(+XLhGI#l2@#<TVd$*l3<15HyZyR|a@gPle)z2c*?
z5QO@kmSg<G??d(doouK|JKny~MZ`4Q!8*DbbY}$@W6K>NRB2U(*{$rP?26Ha`0O@L
z;S?t1JPY=mj(hM2qs=7&e$6VWb)^24%}+N9)cR_6EYNYpo0alw*_6$yJ0E-{!+a6_
zIx8rL;PbC;q|Y&5!ubS*irTMhZn*SJShsu0nd;-pW2q3LQi@d>|EC*Lw^vsu%8c3|
zzi!=<+9N66#n^$Sa85M1>Y_|>KcIqxJpJD<nX4I|R1xw9hf~7Lu%QOS>0aE1D{X{U
za3xKOMQC-PLp@b~+fD~_CAZtDuS&p-ohYCOHH2wvXy`j-UhqZo4bY3GkbJ@lkdKCe
z4t4NNP20<teX={yOZhl6F(B^dZNq-+P<F+>)!dXjNiQSknG!y)0?qGROmF<`j?(bF
zAdEVwafvYVIb8kb;_~SJ)OI(I^+cOPftC&QYb*k2Clb8<Kixqou~|S(TJ8v^YxF)<
zCp)Z1+oU<Mpfk;7B5azVB_BSuV>vZ^{>AeZ%;X+X%qb_1NhTZp4>+R>afJyl5S&6>
z*%W%+Ll|CK>QavVT&>%bsoEp9t|*;4(ller$K<QlL|g6~h4~w@7yf-R(+s6WYEE9l
zoD)?H%T_w;5p#Q8*!m8*P;NMLof%<bu;BcUO*V@AU$*`g4L#i{_LMc$_a7GE#DfB|
zexvr7(9O(xx?_%ecL$E?+0Dy2K7rj6UlLs=6CD75p2!#OZObpAR)&U(vMenE>6Os$
zKMvX313$F((U1%+7@Exc{7{apu0d3QGWxTO)Za<Tw7}Gb+)u5U`jXd3$ZNJQliN%s
z6Zgb4?bCg3j1QyX^P++06f>sHrJZx$(GgW=&m5$>J%5J_Y91uMebe&&Tp>m_;$*}u
zeZ@WWP_jpG`^D?Qb!Ug`TJdjBBmR<p)H;16Jd&HqO@Q?q#oowq-}MN&=cV#ibTLT(
z_I|8J5+W#^x*zA=FHdX`%X!;K%^4Z}r`_ZG$@^tcr<=KBQge?5q|~<~;Cn%XZ3_NK
z_4BMlTCMM77$z+8&$jPhpQhkr;hASFQ+UIg_q8=|Pus|UJf@W6H}0g?Ke8;3jl1Ct
z{O7&aQSqQEkdNop@<Hm0ULU0+{C=gVeN(1||E;so<thng+mH%b_A(24*({{R=f#3{
z63<(dI`!LJGEeMH$&<J@?^*XaGM{~()VUaW6G=UCr97qF0d)O4Vx@0`+-}S=lmxMM
z()d6Z@f}~XO8?$u%vtq_l4Oq;rWDG54SI}vPVb97W?_z!xVnxu9eZ2J?t&LguXQtg
z{lG7~L-Lbn4!!x@vPE~8OwPVbSuZTizU%x&j0Av`<g9m?u2_RJ6HL$fPUmLg6Nk(}
z6=3Zh`jcQ|z(WJN^RpM*TE*D5oK_-LP}&M$3h$p+of=JTDk!l|cK9bH8E1=RBrs;P
zlHHZiyeA7a)Eeijd(S1l@T+{04XGk9_r@_M7W~4Qi%Hkoyw5lle#IJ9#wVKz>#t8d
zm^V)b2j924a69#XisA-+bY}o^@Dg`L3GUQKc~$>=YxRBhtq12GbN}3M;riJt$!AaP
zzo%2MI{;_c6|oRg|AWX#IlKabJ-X&@_W83A_@w&pqYdgQ?2YclUkrbm^TTRa1=IO|
zN2~n4D7i)PHX^oespbTbKF6M&A5Hb~ig(x?Eq@e3^w#-n6!Po3RufY9FDdWU@7~nc
zCZE!OtiE~3upa$Ww8<@8W&RQBHw*KPAIIT^1son{J@@?@RCvQWg$~Humg1@U3===%
zy|(0f?mKn9D`GtkIyX;!2Yd7N-(qG-Cp(ol7xt0Y5c-QjVKnk?-oF#;*$-kV(z?}I
z{C)5B+xBUmioCZPLF<7R+g{t-=AD>OyruqW@XRjk$rrz#msA8u6c+o1FH4^Qda-P+
zl$XqrU(rJ)ZarMmcPu#ND%CZ&bT9Dj7Cv=P^sz!vC4f;4K(KJY2-QlM%rUU1?T>43
z_6@H1Ul>_G8q`dvzhQfCl}f%Gsej9WMQ8B^Q*7Uw17EHol#ev=Y3U%;f3@fGQ4=*a
z%k^C#<w<t988oNV9aPvX+QJmVv0KUU<!7A#K!>Hw{Lx}=fn)fmunh!X@cCzluS~m5
z=HdG#ObRN8xEt?U#5LD?z~aC1CJKEFeCrUA0$d;cC$;zkk>~nw>boRagjvq)K!=2T
z_KzUtY1^MYRI+-#c+QvZ6FWf;kzaY{R!)b*T-}I-%`mrr{f1ns;%_*IUwH?LF0)ou
z{zRD^@Phx23f%KQ<>bL2AHsNC%#H&`bzf+wzavT;0E$x4IK8nmyloYii|$T-OsU87
zpsrNfJs82kn!a{DJ+miVA!rzT%p4?NDkO#t{N!F<(j`$?{;_}E;`M`j)$2xA!VSZa
z5B1Yd8F||3hS;-#ah5rt@#dRF8FVz)v9&QDN;TL1q9tO#F4d7)e}lWcIs2S^2=A9~
zyG5)DcYQYnl;a}UfBr5wF%LW)vImQ~eC81teBy3ftCHtRSehtlloHDstLT(@j%Agp
z`A)KVc9YRaKY`0qP-u^`J8;QDqB%aJ<VJh!0nr;W`*%21pFdoqIDc}iSiNPUn48BM
znUJKYte?e^hq!JJ!|W0^F#sMmZLRY-pm*3oHXBW$#3@V3W;25`7dQtQSnFUwvlJVv
zaXn0L_|1`1@rj*UD|aj?@k){+t5_7Uo@Vt5R1jOZa{nISyd0aEuLD_3;_d)<(|P05
zH`)upf|}J~lj4nsnKOeyMdDCuGgQ~<cv+WlDe8zF)JdiZ9RUSdhe!$i-8GwRJ-YvE
zbcW8+u*rUp&cfY9$Wz85W>%Sec*iR`mNy@W3zNnF9#?4?Rx*GVAK#0e%UoKu1ye5B
z{3MY2kD&xp36_`@6CFu<O7?E?DFk%Z0uU8*izCRsINNxt4gtg%yJ9ohEHn_PdB_gZ
zJw~hNuUfO-F%~gZf5Z%u?pw7s1kr?65Cm54ru0n+JCE02f{*V{3YoRUm@M2`u{2%>
zf>A5bn&x46V`~tK>dB7)lG?UMPP+g!O;^%AB+=|b{0!39_#_bINl%1Oj2GyUr^=2}
z1|=i+OP-_SxbM>aCvhOB;bzu4@hgt8QjUz#^JJJX>8nxGS-_+T77w8Qg)|k>7zN9y
z5DDXlaPKX=8t9Li8t*<y=h#rwUMe$5-RkE=o=M5u#q9F@WFXc|0E@@K+m5%a9@&ZO
z4KrY}8ID&pGrb+r4iGFj%&K^gxJ`s(&j2J->L3y*$h+_h`06i&KNHDqo>ZtNrWXOZ
zKXinYC}8u<vl@va0vD`b_@IK3SKkM#`yYtkl1FUIX1D_+zGdMBL#xxIIFrr8ELl51
zz|vtHk+Lb7CA3dI+O!jIM+spuc@x>Yd^^aQZFNMKE})NA>>3&?h8Yx}Mqqh#dkt6E
zsPMK<nm8MQ$soI6t(9;#jGj**@VuzHJ7gB$zswRqgg7$%9WsM}oXpNMa?*#aMjQcN
ziHN5YAP|ZtRH4<)82M!$=aa=(un`Bq)U#m@1<7uczQO`@Xdoe>@|<}h@Y=~7dUk;$
z!*nLbVimAp>fu<MSu4;13{WzV0`JOh^2>?S8<g6xu;!A?4gdk~AR!K~53H>VL~Ku+
z92qPi{%}VII!+TvxAmwfGy@?)&bvsu6A+DWDggQ9e0=-}%NaI?(?b>mB58q$I^YAP
z<6r>{`h&)WDw6J(&SuU%&P0J|DpD(EQs;2?1%Aot@K%yIU=c0HUFu<Ew`PHY<%^gh
z9eP7Kfr#@LoXnwXW>jw)Xo0?_yJD_B@h~;5q$x3CvyJ>M%zFOUP2b@<#u7)|9d-M;
zUp|g{^gOHVfU}qT`zRw$#aEh@r}dd3PL_@3I4JN7{{KgXhF__fAit|L)S^y)cm*|N
zzpyPMo=(T6(<{m!rpw6k&EZ`IwB(_!;WEn3HtlKm<Zq@~>6|hv{B=HQc0Za`UXv>^
zHI?d@slI?b5ANUduygHk|9rLM;l!lB(apT#`7MEEcl*>^<=<-6F5@6kLY24U?Z|=r
zaQo9M{Ues`Nza2ida6t%-1hUP#=b@m30;+7-Et#MJR;rEHdp_ZeXs4Aow*x)hu1b(
zG)AYMGG~`n9n>=`*18lNCdjo=&wL}J>a)Hy)mP^C%n$os%Wu44`0txq<ol<pErRsw
z>iGV*n|3!XtA$D!3>M2Tvt04by|O1z?Eh&U9n2Ga_=K|J6krwlkb`L<d8A}?_E8P1
z9F`|;_{~UtMe2>mvp)oLDP>1v7;Tmq8X8&sRLy0oA!P$^*TJltZMb|P4+|2=tDM3I
zg$8it+jG3f>H_TJA1SWhF>l{8Lgp!C<aRM88!8KUJ(aE9{sRe3Iu_m@CdLDjU|n6v
zg|nA#=QU=|)M)e6$zf~6>O}p;uFTmj85*<KDTjy(c!Tevh)gh}CY@ye#HnFhqJcz0
z^^1hMgZFwv^oVvtdls~odPpegbgdD3Wu4g~zl!mZ+Ky$Fh`#P}Mw>kGxj|Kl;p~3t
zTU|)5Ck-8%|3S$@&R_9k!=uUMpNF!YHC2J~c8Rc=7N@pzmY>p&gT}O;m7WREyZHUr
z>(`IqlFBz2sE4klKvsM!@W|#{Q1r)(;E<vRP4gr8g~-0zxwo`>LW@lag|Qu#DZ5^z
z1+zib3>nGLW@$(i8q!dqnN*nzG%I>NypZu$cAf?|!zep>3UuxuTu^`PVpIxiqsQ}1
z570~s8~rO@?+Nkho8(b^%RZ5&bYa@+3ZK)Nw!35BFjfKHze`v~;H`ez6C+8tbUzBK
zv7I`1cE#Q$+HOq*YFMQG-8V7;M!wzmLdQC7!+&h?QB}(OpDxB~yt9i{DF&k3gePjX
zceY+kWqoSa!(S!bzgu#$`L3sSS68*+7S6m4qq;R->OS)hrutOA{h20f(NwD!X-s82
ztN!i%Y#LWX5rvkm{Wo^Qv-p7J>eB(0k|z7GUuW;v>)lFH!Gfdo$J>sfTk@%@X^%_W
z?rpJ%y9FyJ1bt-6PAn87&l&~BzhC3#@@2>AiC7C7rq4;HRg4*!rdzk5<Q{xUZEPO6
zwE3iaPUX*j_ue;;{3BPDpx8N~vaIiWOqm$b<DaR)SL4mMR0_Xv9;Af{|B^gRFQWx4
z**i?jPMdRAk*_Zw@Nn%l<yn>J=on}De){r-ZROg=!&4cB2es#>R#v(C{?R3VUYc%I
zo4H^Z#GZ#sTp>kDZBH7X#I@hf6jjJub36l4n<hbbt6Eew`CWn`*MBx~s?VT^N=iQV
zCC!gtw%)Nia_+n1n4O5as^ezrH8~TXdNm<O%bg?AT$H-xa@^hjH&s<OvVYZqz!~+i
z*qd_{Depg@Jg((k`mEXTCI8@vbb-f0yfI7RO^#D|y=%12S2U!Wr@gosq_^0_aB1O@
z&YGRVR=HWstBz}$gL-r28vd<IW7$q_d1@Z`Vww47<g|r7EcIuYewL9FUICm!owbrv
zYKgljUqyNudhwCrZ|8!P{3FyW#N|shl1rAB#_lg<S!|bfs!13-&QQfL`!gkb=fX_F
zc_6(Ws8?l`3R6_sy~-~Xql%)h9>S*)onFt;2-Q#6<koowvbj;y?C^$nHU@F-PHjaq
zsK2pn*`&JDdt~R@=P+KYt5&EFy<8@xWKLFJ`4q_xDY<z_J9aLY)7v5tP3<svcNY~S
zQ^Wz$n6mlR{cORwtN2QVXhzPH^KZ+jn|}-yrOGm-a=Xe{^IXi<=zT8}s;~W46Dk?u
zOj8p&;+vqbGCtM+9H~&MnSR?hREWmc=s%hH5BFHcd117*__EQB6c?2`8TItwDg2{r
z+UIn$eME=8jWk&?6gBQue&6{iAk`G}VJ25UJ5WI&H(8*6_SKq`rMQOLCo_FH-{LFu
z3Y8Wc+5B%3fw^DyF*!v$cCPa!P(Ow@bpDciP0-9oG`m|&5y!s~dU=0`MJam~ShS;V
zg}QjMJlVJCq?$X+mSdm0Eb%r&e~;4Cose9HD^9qaCls=w+%02zKH|Dl?wR@N<l(V$
zfbGHLJ6*w*?+Cu0TDurhJeJzU3;+VJ&fKcbJu64HFc|zJv;;!2QO75ebKJ|Ys}78K
zW`o2gkY8?29E$#|eUktdf=7_{$Y2~3On2@X{>%rW&MM;EY_XhjEz->R;}5ede*G&5
znY;{^B6e={x7`ZA0w6N73|+N6L$j>v#aLmVVF3C)=WVt=3d1n2u&;B&s!@m-zB88R
zgTk?TF<WO6MGpzgmYu8y34y|)aS;M?)KGmZ&<H5{^a?gJI|d@QgnKO~t)0o^rPvNK
z56tCTlPk5hYo%Z<;?!+#-nCk#K|P}=+yT8nC#;?I(_51Cr!6w2!p>di!~n_hekT*o
z*D9xrUgGEJEjA(t=(Cr2UuX#*kfl=0HR(lXO6#nP7>mx82tqtBwI2=Td@K-iba+3H
zxZlg#A+1C4O}3Mz=W>jo?3o##h&eJUdDGi{$!eKmgRwx8euoF(c78Y-RtMJj=*)b$
z`aoPTlqSt)A0V_2H9*BBWvQ26e@rweL7yQ=#<8fv!VZx*JxA&Oyk*Qd{4AIuGk=f)
zA7H5DYq}*ckY0Z}6vS2Az4KsL=LqHg;FYpc2uEY)uAI+vt@d69earpZ;}&x~;?swZ
zzPL|)bGvN3L~_badX717KiyVV6Up?Qn@b+HmfT<FTln1BH@7{4Ar_tnnn5mz#5dAd
z3=YpfG`v{meoLM+bi(8hx{YeBM^Da1vt=cd<^_}rCp#<Oi;&boG&}CmLNCk9l{_?I
zpNokyMZ|4NGByqcMmasZ-1>m~xqn!Y+OHOE*S}*?zi-^I<VJ($sNd*mLLVx`_{Z?!
zFwWOQg@_*+U(xN=_4DgVBF=XLgni*N-Fzv1m7~d3po21k#Lkz`&67aU){RRTdI68S
zxzK;0JvxJkf#j-bJ;vnD$hitBrDVIs=WRK{^YkK<xm+$WG2C7C{EgtgbrzWVS1tv{
zBEHf%r{bi&Wg+>35*YSb#)?&b2~;ZInz(}Kamq(Q`zk7{1hrJKTcTL*VSA*7xTXWU
zHJCc@cy38yw@NOr2*eU7uX_}Sl8nB-WXJOt#n64+)^piPLB61kCS5I5)4yiE9%iQ?
zu{(7F`*xFz!#jRA81Y`3F2?$$Vc+}A-efJ?tD`1qGc%<mySaFWEVxwlJ><CBcT1Pp
zUF<Iap5^g$e(+6klm*CwF<jfk<T>fDL*_aY0+sLFiK&nhb4=>1V$X3$JcV~(wjhhM
z*4Z_?K0+J~ho+02UV?)jAaCo?jD*fVF}k9myUXD|_KtT;WgX~J@M<*tV#~UOLtL~8
z*5+FjWEg$Zy5Q1f1^FbQ?IJc)cWw9`PYiwQeXMsQ%PGv0GtvCb52YEuw^a|<tS7YQ
z*MH^g*81CZIM&7<XJt$_GPX_jciEf&0vlqkn|K^^4|nz~wuDX(-AF140^EHA_v%C=
z`op5W0Y;{m|AEpJSB8VaO4a`2>>>Go-i{2KMCwj*HPtU{3WNu(+FWNk)N}xu%>FaA
zh|W+4I_ddt1eU4PN<DDJ@_~AS`eYZ{9heR)j*~;mrXSsHQYP+b4Wa*6-4hnx6`AQW
zbMP3!x`IFQ{CzfC0Ft1n-S!64wN||V?zw#mUZv-TL@Mb=Qf1UUj+NXe_mk*@>+i=F
zF)QrMr?Cx=H{hjlmkzJk`B6{Z`=-0;SLRq1Zfxd!5Q(dNG#&KVE7}IOwA~Z&+MOr0
z>7x;q_?^go|8g6JCY)xtq#(YUmn7yvt!d7Dy$#`dl@wBk#IZzoIkqH+L7;><6$|;M
znfMIqvLZ*oT#3LV?LNaSdzC9<Gbl!I)$|wE$L$vXOz~&8egE}aN_=dn_KqU=sKFkd
zH;#WLi9y!Axo}ys(2WWyBCy29EW@Hu154JjQOoz~jD`j6fnmY0HC*Vc+wlNe(FNp}
zf_piLD1J-ak|8|)4`lP2^-F7}?`S1Q2F&!u@_X_v&zRLNmsph~R<Y2z7Z={C9fl8O
zT+JjUMfhR$wOR__r|(c6UNnxyHo)2sSAtUZ_0M<$SV8JG&F5Nt&{&1e>z7%q|NOB2
zZ6{e4({YysYLgPpj#rmB-amM!-2UTX<s8=_bj9t!NN&90%ue&wzklk@^qB`Ji=*&|
zKyOxtt3=(^XfMOf(Ol_`8M!DIrtvQ!DqlW7xKnXswRI%PkBR>g^`t(aQPN~O-e>by
zr4h<XTj#IfaS-FqJc$AKePu(TY~au}N99dsR?RA%#Fw8r+$fO}yG6WKJU8)G=ZV<5
zu2y>NmO{@H@0{1lQoG;Y=6rG0Ydm7Vt{eySntC2Sy#CgBMWlG`Ps8h1&%PEcS}i0{
zi<{k*L?k>f{2LW6nc~^&|2y1>1Cq&?ekV-_=BbSEw6fCEMuK@IFcal^O^D+c{2TTk
z!aLJt4XZvXZ{f-(n(oKHsFY}}e0HT(Hf{1}vKe;NEevRa(nD6VDigPAE!s*<(hA=-
zO9)RY$o(5+nJxLD`4logU8a}%QmjFN{?gWe7*Z})lCp{e4F_Li>wIXO<r?gDXUJlY
z=FGcg{X%TU5nPIF&jsBCpM1b&{_uPkZMz`RIegsM5wlPF$Q=$O$`Q`bHqM3g-pk5X
zM8TClgu>F+#lWp6P=<FNJg3e2pM8&YEAf9V*jeYDo*k?uBhGavR&&7+9oX9acTbv%
z_60;e`?{F>E6%|`OPxwFOXGR<#$2||gnV?E0Id!EtS_HJ+nXa^oZ;q`j31R|$|}AP
z7x&%z2lhCyP}k_*;^l$Lc5cR;kL5w%pAnfMd&57nZMKjV#iVfiz_I_=yI0|#yN5X(
z=Ez@9sBuIu1Kt$H@4b|DkYSD4{Ziz$fTB+IQ<1n2nn^q?ukW*~Z>tzwChRUX2Q()1
zM}E2Ws%Sn}6RGmBvEMkOE=d{i*Yomcm!<|bhF;bKEG;@og2tPQg|~Slz!H1pM*n7^
zzcD~8IY#xq-b+|r^#$ielG_#Tl<lfdN8yHO(}OwzIiQh;H_J}va$B#WXJQ0%kI`kI
zkLNR(Kw&bBp{yM<t4_nVIf}eJd6KLhbtv9W&Nn<AVc&%2A<0RKQJO0~`s{NIRQR7;
zXbNCC!zrtWT98$tLIyiFhr_(U>G51&wHiFiiF2Moa-@%wRn<=++<GDiGZ3);zuT}!
z-k>Qs?d}r5!pnB-YHD##C7LUUK3xLyZ!18x?SSb*0Eqmch8fEfiCs|XC3=B~hOvky
zjv?*ta1x*W%1<1tAx)i)RXmo!-=j~lhbm;3=W;FPwJoEm&C)6*lvP_*P4PqWaX=4~
zcX$8;&-5-~YvR$9Fe-%8Y1K?>Y1L-3*bgfb&PI668W=`wa9K>|`q3i|_ZRbrL;^Zd
zVriW`Ph5<G#K_b>fn`3s*l8FSl~@3zH||qkCscxgMTO^F4iy3_8n7<_sha>{>f)##
zkWS<tVRzLkFT07q7h?<B28vG|yQZIw134Z9M<x#W@#$JGIuYv#e$cr`GQ><j0W&3A
zh^K<2jdsW8vtiV!VJrD$cFn(zFjko-&0vONI$qBSh|t>J+&`j6K*Rv*5l50c$TYV6
zNrSavfKc(K1>|P-u0P%}b`^1EBGdOcpq~<sp@HB$b*h@Vu&@<NGe+K>Jz|9}v5bfV
z*@_MQB&!0xND~?eDoi>KFr-3K9>oAspWJYGLN?k?JOK()$bNg*DSxs~9NGuzmR2d<
zB!PhpguCa~35-*HK!;=yN#WHoMC<Ppd^r6}nk1}FuXI2Gzhwo(U=&F#(WrpL-A1^{
z2Y?9|j)sbN%%r$a&@n*fSnO;Z&XgZsM6FZZ2s5`@wY_mTgg-+}L2x9$em3!Bi%=Q|
zlqC6KKjt5AS#(GV8tp#aBOLKt+M_d&3DDI+x^EqH1}TJ%T(M5lQ(v|ESqJ6^l+l8l
z3#DV3TlvS8^Z&cdETM)0{o<g3v22rh<1Deg3Xp@4VL~PAi&gU&8WZOc9wDqNhRolI
zr{ED*RENMQjW~ADKaotp<%hYh5eEc1hUm!%R{EnSIBO69l}u&}7^nwyERZmnG|&v}
zd2>bFO%N$9@FuKN36w$8#>&FoTZl*&{%}x^1%Df|h=YRq;1NUuahm`pY#<aM={bP_
zZ?ZfEK>)uCD9;Ao1|X4*(_@E%458v-mS~ejEO$VUcm^br0NR<r!C2uSe~5@)NkJq*
z6%yxE3jDwg8%u!r$Sh3Kg}fU9`DG4`<(CndS>fgRQouKOK^YvZZ82s-1ZENeNoRm1
zEcXC~Q_<@%G+G_O62Ovdh2WUTOhEv_Y<Pjw1Qz0CHC-^sU_w9wSjlNLf~KR2{-8cq
z_}Qs-5ca{L*?`^M749f|26wGw<Os%7$aXHPsmW3Q49*=&xPdcmBbO(;Wl-Q#SGrNw
zi%(VMyywWMJiAGJj1WY<#|^k>c_wBMM~45y!L0woeA40D9nao|&Tt)aj?>E`Km9(p
zyE@g0=iNL^TX!<pSy5gphFfWVF+T$ahPP`2M?=BWD)odnE<v$KGZ$!&eQ01$3^n-}
zrTwgqT#)l_Z0qk-;;O{nAEd%F{))Masv7#vsLG0ZrY2X(vY5xS%@3OH_GrLwn|@_I
zO}&;DTL*#?jdmSDaW2LW6mVQ;XRJS6R8<Rdo($CV)i)3G(w|S_9jLtaHt}k<&{v2A
zWvm?I<SK6=9jPeV=K1<SHJo~k-aLGCG|2nvZRwx(n*c22=@N6c&VKcsAF;I9Q@Yg;
zP5CU9>&R1jfhEwe$dv4PG8Q(xRj0(Edw~+*6TvMg8@B4)eD~^~_mMgr3Y0)Pe}3V&
zN9s30`6q#lPjBS1t;2eNTX0rDz-oooq-s^GtS?$%oH@!c`(KwNCp-rd;OIq-l=1Wy
z1TFZze0zQ7E)RE4tA*N=GN;E}8~EKEumfRYW!Qq~rFP?U?+GTydeWmks0Q{7nf#Ph
z>W#m^bXAQz)!2wK5M{(Pu66C=+P;rqj_@}Jnw!RVn_&G9q3t&>;daGQF3(Ixm#)eD
zd1%ETZDF!2Kn;vmiH+QU`b_iUwC<|sUaTwy<!1Ft-ZHdldH%1-2I~3Cu)&ebw+%$P
z2lLXFH|?DB17B+nH1lY-K)&1zj|B?S{76<zwh|h^UG}^Vd@|za&$60fkB@n*XO(#D
zchmeo{h{7HsQi-ECw67~WnYI{LUnn~XDALjVRfd{S-4K79{iA>o>%Cx0W~`LJ^X#j
z1HAt*)>mhF**sAGdSEbIZryCS?3hc3bFX3vpJ#6-o$oQQ@cs+Jb8iyAzX3kh99rL9
zcs~kyPP*0;eZzITfrDN0g-i$LBUf#pm&A6HRf&2_K=xG=uhOEr%D_LqD7$Q8_e2PG
zH{h|t>r8lhfcnDxF-&>)C&MKQ>77s3&j?ao`*wrzr~!D+M0F)kRs4Obr2Lx!(4odZ
zyJFAZ?wt8z$F*N6A;(PP$S4nC_l2XSbjm|J^ln|^Z16t7X~uhLkLTGjy|mpT#9mJv
z%C^$lT_+N`eERFMv&62e@-0kgpE^G%k2h=|CjEpp3a!7mSz2e?cE0^ZXt1R5yR4+(
z9Z!$XLewpyYLa!ur}l8ranQ>9vxhdw(TE2s^u@u~!&n)`Bm?~4;j2RpaE}$03$l@s
z#xc8EnJYD3%B}r-8fR{A^|;-e|IFaQ<lkCpHSrDJyAU_7WS(BR{GJcK5|Q+$!>^lH
zFwpX0uTshgtrma3g0^!;;f^cIi)&xQfLPq=jg~rHTC-2AvUUGG=l6Qa<C(ZOAFhf<
zdpavnZAavhmv|WQLdkj4_=Plhb(g^?XRbP+Im=xP=`A8oRDc-h`Mje#T8T6Ps$t+`
z2+)w`aAq6(trP#%6rR{?<fA>x@%nqN9`d>AEa<N<>v)|@-ozb;>wyJD0!2W{(CG7_
z(ZRLIUk+te?(z!1g!e1hN)4*!nlCB;_&qMTC5O8INo-x*4k@m9RhIp|%4K`SPBxkX
zz!{!e*sXAq(%GXBv%0hx$ig&f!E1%CAY29go&!+YXOO1kj(2I_=eTq$%r^vc$Er)?
zcolyZtk7T>0De&=7oryxihGvB*1>%FJIa<RY#H_(J?#$}rb**;4hUFu8>Jou3=f8|
zo|sjd{Ol^uNs1MZxL_T`4}jFI1#Bds45g_ToE+FN_LF#3L80^@zv7KnWbNgh9!oxi
zxKTkpgP*|DyneB$8b;{ozq~aYum`iOZ^(Y-)xLd_y#4BqpYAj9WG!W00QYZ@lPaEE
z6|559!~Gv9uO`}F=Dv&+7w(LVi(U6Qh3Q9sDp;n?%!DSurv-M<+ngd_J(Arv<K}8;
z@P_Ske@)g<Z3BDNbX7Y(VM*CW0wdaTsR0ho-YdIwMs}iTfM$qYEJ7&I@eJheX*?^Y
z6()1VHAsg1VZ67xkIsN~)YO#<ZN43+5-t$<*NP3K-D3i8CoM&1{L-zlSN#tmUUlhL
zm=zuYZ!m<JmYM)DGD->N3S%y!7tKK88i1!Z!my;pe8|&13PU~}%P+iU|CI~AAi}VS
z6@>WaxO>u55FpgV6R{nHuFeWDy)cKO*#<fcF?*DGiQRhUun#N9D%K8|?H*)U@HG^q
zg0ox56fw`C7n+Eh^hgQZR7`+gDA^sm_O_&8pttDk(h5p(-HW>7JXZV)=zKhL)uPVy
zyBO-2wnXO6YQZBevqBQ##O$W~m20-(tz%de9)a#W!XQANdDCwa6l_N1hn}x3(iiVD
z+S&u7&wrrRak%0|j(+ikY{mR_h0r`<zsOtcpSsn=Va|8y_1ekyq6uhD#(T`tCipO@
zF|I%)SG19PRJ2|(T%)3<AUx4Cf5nu+3`E!ae2yvarGJH)JOE0ZLizy&6LA;_lmLsK
zq0iwR;Go*hd0eoxvGth~bfz8v$D!wEI^jUk?v6SY-0uqfa@|nl%~HpevT)`K#=Jap
zH5dQ@6`RBIaw4}AoBSb+3=5|bY<8qwIOI;#TqpO)m&N1<Db`%#u|%U0&_a~eS+m)~
zWZ@P33VG`tS&ok?ckaGaXUsU)-|-6;m+)lm*ZfxaHx(VxHEV*bzq}rf<3A4=!t`>i
zt?j0wBt!~YW)#&N;?Bq+K?-4IuJZY10(#z@^LS7IlGU1ZjHE(?zrKrP)E3^b$wak>
z*#VR4YZxGTvc%Cf9GL>o+-AV%R(Z9Nz>wN041!ZRAu#4UZZs5aBHLD>@ilhUGPd$^
z5v3Mq(V@hd2<>HUXjYA-FgAg3h6wnKW+&wSk)se!8T5G?|JlZT3U|YY@hzRNWKSCM
zEP#QyRmB&Lgi;MgQc?glRYFz@W6u}24QmhAqo4Ec2t1?w=aOJqH97Q~IFu7m&fXis
zzFn>{2+OLF`U|*ikr%}obACCU{B{n0%kC=^F|qiJW*LeWf`a9Es;bR+^DSAM^~3)I
zaeJ&FdxFD4KX|v`%?%mr)H4}Nhzj_r7n>G1EynW6OYOSL?(&Rpt{KlXWNv6bd5s%M
z8nyuc^~+}pd)!^05M<9{kt595q1ZLULdiXN)6M%&O662w@OwP_;M%xgT=NK})t2En
z%R<RJ{v`Cv&0AAO*Js5>Om+2YZ>6_r?Qu1He9!cK`!=cQs9(Bn(t+m?;~+H=@Hzw0
zY2-$8RlXlzh$aU{Z@m2J&{}XLb2f<3co;UfX7Ymj0X%j?G59p5p^APbBRGwXDEX%z
z);s67ZZV9jcQjz6&N$!{oG<c!pUkoQE4y2tJ+L3&)E8{yt}<0?m9rQ$_F4CL_bEKZ
zkS3O4!QsE@@ZoWhW<vQ)&c-|AT!F!>hddu13vEZ}`^mOf%pZ+SYa~=oIuwE??_SgH
zH=RK54_5xkOGcg4QKv3nCsb~&nNJWP0CTO^f?jlWvPL9vLYo1Rfy*CREKnfZH93N)
z)}ZuT&>TFzfH4L%$mDgE%r`Oz)0d`jpxG99da+8e{$p8nC%@bFFa5xh0@mjL?eKID
zYLEbJC?J)ng8i}Oc{kqR?sLb_ktz+}A3iymzJ&i%F$%9S`S-bUykzaFU@33BmT#+7
zl7#EaVmvd(Z~8-UnH#a6T|FOp^87?8<?Z3X>|~@7%7Ai`cdC^fyEP`8hxV0~bP*!(
zTszm0O+dZ-QgcwuzNs{jrMLF6^wlJlcTc`?Jy9m6dPDc!_Re?oHy-ly+Sz|Q(4%I@
z)-CQ-|I;`7KP<(kTt5#7x&In84j5S%k|5}dkUn0uzlFbQJPmi_A*-G$9Qx24j@*rm
z+h~~aQn84bhbnK+T3THCHl9}ZGUemW??4m5xcKt6mGSptA;o-XO6q_q4T!D^96N=R
zWX;YcFo!epx|GNW_2@H{Mb2%U^=jE@wt8~XJ9%8AYE{4FGkncX+Aw?+n#non4w2NX
zJSgvUanlIz&flOJN`Z4h2aFFc1n2HZ4Uo+vJ;I(7O6d<dOFu1^{=(246Wo%w%~{9F
z66`T0YS2cJaxn=r{m-7e$E$qx>(^^DjS3n3<9|&pjSR|`p{1QZR~ow~H>|lTlS&CR
z-`hUA#?Mv1?Bv^W8LzpS=sT8ToQ&$fSh<}RT3WOo91TAfEA<*-P#>Y(N%yCh2h}|G
z@>4KsVtX=ikIz1u9hCV%^wGkJeE=W7gT`gz2BV>(=3U06d|;;$Yge-SA4s7hrh3WI
z<ayO!ATTOuD3I9X$?;K=tlCLol|%+<HB=aPv(n3g9=L5U46+QdvDkoEJ1&p&$|uDr
zi5KBPQOj)<zs`}1n>m<2irOPjvMNE<j4-!^sVfiB(yLdhtacTi%J_}QQ5noGhn)94
z7?^eNV2pdG=seuHy5sVYOIyL^ymo8U@3p_f7hlZl)|tJ`^!-(3^jQQziyteFaRV(I
z@`&jlS-QRjIqe=wjHR=b41l)M?54V4V1iRQ59D(d-E{wTp9(bcS=>fpJ^z)ukLl=?
zOGrPpsmP2rcE=kUGW=^UOSTs}UUg2#E!#B6Jo-+Mj3S-u>v*sDQh(5>**epSn<&Fu
zc`6e9_<fea*2ac;Vsm*##*%MT#0+u`(nb)&#g~1N2Q76lK9NYv2b@@+l+xXuiX9Qa
zqthQj?h)^(xdQJ<vN(|GJwp>xsJpO3F7K2#Dt~eZDt07->N&^jeRs&h-Kzj=?bQKY
z`ME{m^udbaod(JXnW!h3!@QiusC#=PFLW0@x3{q8;^Y{aD)F=;7c)!-Np1A#3$Iz_
zY{L>N0qPb37`Q=m1>9kHkWs<=EU7*?F^571U2rlJ^LEq)97Y4PRyp?2)m3Z#IAAG+
z=!_=n5``I)A7;*F@&g7a7N|jzH9{H^wFJ38bAom|fONxmR}P2M4UUGnO;+e7Y+O^0
zj7!-tpvnMH4R%4#1LWqnh+<nfwjR*Mcj)wHouw7KP6$Y%h_p6w53@_GT0yY$1bQw3
zd=%r}%%usec;1S6%rct6I29^uG{W4uWA`T^z&JyA#i~^@(3>^IPNBruJuzHwnC%0>
zBs)gtiIi`hlvhFP3Ib?nkuoj>C$E};n3nL?D9e}wf@yM!%`hE%7pWN!Gzh|rhxUxK
zSjTdUvx`w6aXUa_B7xz592q6lOWqam4Or_(EKy`~aiEYrB5QpNQFk8r^n_94Kx&!@
z9ikYXM|_!Aq669^3<2P0LSlDT%r(vbWOE4*ga!y@vgpF^Cq`h*0kTRm;Cv#)?H-Um
zfZ-rRSO(yDUCM?E?*cw6FO12-VlMKZU+$SwYaMYIW*m>EVi4?cbcyEyzo*~3>sB!Q
zBtwe&$uy7{Pn;TbAkL@>M5%*|9jw~m?-;W)>DTKL>tU=W$pd7G=NJUlKhqZ<a{FlL
z8#46npn6;sVW=1n!vdWoCU~zDnVhj)c6+0O0_=P<BUZem>1N69^Mn;mY9K;I<zg$b
zPEBwV2xp31YlC#!4(b4}&D<j~jAf_PDJVdECz3g=xi0D)4YF`C3hEFI093YkoYPO8
zV|1qH0U;c%h7d!}<#rGFB#D^V_nImABG^1+vkS`7lfLE-m0)n*(3$<E5*Rq_=h%}d
z9#8fF1qe0~gXgvq?+63zEig-IELe&T{)2;-zYEx9#6bzb(ZhHar{{#=uo_FY8FXay
z!9wRAWBHrKtI$veyYs5(Gjqwzko#K}&1&q>axA;Lg*y}^gM|`-eCX=`R1%9jyWajf
z|1)`+seq(c&EtkT;haF1r#w2qzzMJ<S{oJc=Kwj?lBon3f<#`UV>z7wr<Nnbh7}#y
zt}=tfnI)|?fj=VoP;_E}PbOvz3%0Vs+lo1YU||*#O+YX@;A_BKP9R8qmrS^l9BAXz
z+No*tn#5s)1C$<_UKks-&JJfvgoBg0&RaX8EZ1yly<K;aQDjoJoSq2uf5j(k>SmBu
zlDc8lCtdOxBy*2dtq<rf5D`_vrvl*%z^e8CJubq3t0UN0;Y~g`(Es|&|8EB_MyBmS
zd5P8|?ccQ;Trq&|u^St#rF|~Wmn69}C@obQxNoWi?w&ZwesZ%PW+fMvda3U?P|?gP
zkoEpazH>`Jz01en#wuOu0ogylc7$9y%%c2Q32e!f>c}#R84xxa9r&=Nq3OLpk$Ug(
z2ggrFC@;+2g#D`LUo4X!eB>Vef~RcamKx%XBSs?a-2VfC((?mYOXGfy$J+^}-yzr(
z;ca4*9>i7EE6o~+Hnr8O+yR#84`husN^M6Z&uXFlTWzd-F2lZJx?I+SP3H_5yLv^m
z387CIwW(H#?%&hqI0}9;^~)U9_`UOa^lRj`Xq1Jtd0>!A5^8u-yCs~Ow*&PZn7vxP
zQR#W4<T8FcA_%4Rg$O>pvM@eyDz_ze@u;KU><svQe@XeP2CeowvsakVjjy5h7<Vth
z;dsM3gU#P95_X+BITu>C$*`Sen_Fj^>~76o9kzWwYbX|7vvq8|rTm&Bdf)Ly<Bu2b
z_Lb<zy7MZMmi~hwAuPe0FYHgm6O5WKWF*3t<06n<;HN*C&4+r?ioCCDE$&ZI!ze!l
zynPEr#nc6mN55^p3;fD`RY_IQ3fx}|PV!)I_I<qWQ1D_Fb1h-xqfOmKyMLkYtPq|r
zOPKj6{)8OuZA*jQgDPL?1kDXszpUsRYF#=ss~hFhzsDJ;d(Uo{_9uz7MIkJFt3Fe_
zdN3i)SB2D<FS?Suw(fii*8Fo2rP7u*J}>18u89%#7@Xt3mhqj(K<kEF>~BqX)3+-%
zn!2dA#M562dE_fsm=+WxY9Dyq4UHAJHIf-6a5W!&8Yy<X{->$-vL-$VT)ebXW!X93
zY@wj#D$K%-p7ANXdUx1CR~(iMzms7U@~K8Y&F>G)l4*~z$U>NMBj1c?f_F`4zJVOq
z^0ECt5Jz|3MBv!#&7a+gS8tl^++A;gwLJG`ovu&6>ZpgcJnliC+1BtEB`*I55<SFN
zkL@Z1FqsTR%Svxt*Yx@*-Ku_%4TT#^?~W^cEC2n@qFYj{DB~+t($47}N|hmC&?9*w
z-SgP`4Xy3E97$mN4H{Pycj1E<ih8^CIUg^+39j32IyiWZ0n@?Q(a%*Zb?#Ho?zXD(
z@%HnlGqlfD7q{ICm#@#MHBh-#(OeMi_;Evy82jj!T>jpjAmZbQ7CSm`hF;4J&nI02
z=R9H_nq+J|Q02WbkD|Z%D|6L1;KwCdPF{19x@!H;C}<sA8h7+{CUNmM%=m|QU}qOM
zoAD(t@%aSCjZ34XxAz<rzds9)_0MyAoTxqyKll++{Uzyp?z&_htdi<?9u{da)G0}h
zJ?Op;&WalX;sK%sk{ZdM*%u==G6na4vk*fdtE&>1oI7mh?eaZ@{;VzV=N-63l%Jv8
zU3S%olTfN$+5Tp~H6UuCfUH%&n)$A<p<z`}@7KR;Q;iC`opUdh*dM=tgBEX=jj<9I
z4+M$3?ex`b@fFi8GbUeW@?D)OlS<N!((OXs!b-2^Ie&mDbXdzPbU2<_V2m5ta=+Yt
z&K}ca&K*N@;B2?oF?P4T{2$2o;T?qRR^_jkzTLNZUd&PW9~o^(j2Hlg?$%#t{F-jr
z3*BhPT@vaS%`yBP>!!cp?DMUY22wibb@3)D+W#GlM~)s(SQvFX!?)i!pmpnq@53Z<
zL&g00YKgGvXL96TL&aL~bm;2G`H6DhQtJR6vScChQX^fbB9CT(L+@6oxy+G}LNnf1
z059ttjKN6Ve&%Gzxutl=`n=KvR{6qox!VCJu5R(giuJW;DF`lEyltMz*MK#I8@E2t
zIt(+ZVD!oKZ`L<JdOI?5+bixBHau?+U!qs})VqJNi07kM{6D0<Wl)s=1NOVHG)TzO
z9Rf=u3(}!dOM}uPA+dBwH%PeBA-GZkOQ(c%w^B<<N~cJ7{LcM<UY|L0W}X+kVTR=%
zc89(9`hKp@rC>r`dQj~aR4Q4{73s5*cHRfC^*_JZH)L%iL9={YM}121#LBp}jrk-p
zz*Sf2tXnD5JIJ)xWg1dj_0o%Jr}5VYgVa_*Bv`GfT1ghgb$B&N@`=IC6NNKETe&J!
z%kAUB^M!a&Z3rK&8!ODN;l?|;+@C*nW0lp*|BEA9VpM9HE3w6zd&fSYA+6>|f+8mG
zsZEKPdvdkJs6$<r?^;@+i^AGBnUtC27ffSJJO7}<3MCZEi#2P-?>tB@#ej-h`N1+-
zad8%)G7?jESk$#}amAGNgPgL{M76}-prO~a%(x0YTU(*G@lcF~H6w<CmhmFDh{^K+
zE;X4hcZNmzepiE&tis4kVk_5%4miIe^5mkCnf&%~E5*s)=mzVB=(n!t6+1mBi|0`P
zasN~GY}wt=P}^)-Tv!gATC?cR9;?^t>o|&TZWk~-ApJc6puY<)*O*KA95@vzSV9u(
zVO@8kA6-o;mMZoCYaPcy2H``#gF0;^*&_xI6k@~=Af(zR01rFiy)AL)pb!(A?O1V?
z-ZQ!OQ#o0{Wt2|Ei1x0#No6&`LAAh_^Ks_^Lqy`Bn_>mD@y{}4#|!OVW~Qd2(LyJ|
zLZl%FYrm#-+D3d@;M>Jf?Ri1Y%yqide*>7(YR%zaw7C{$(2YvJJhMvko#~qtM6=Cu
zk;jB_fBbP=uc%e|p17w8C1k?S1rMG*{R1z8aX#cCC-R?A!DrFi-wlijE}7FEq*ok<
z$9?BrpZ}WvBpcpR+Lp^GP2>9LS<{`if${U}sx0bjCu}|n8t(D(fh^oOi;a-u!=q3W
zsagFv1OEDoE<B4O@IJ!EwUk3<X<Y?*6C5sgMQ+H-Q&ClwdXR87!q6KyYR+}@-Boz}
zvR9lw*|O#b-o9#v9au~z>5#z#>k<|kv%HuQm?K>GcF7X;35R42-Bg=BBRm>yxwBN}
zF{?7Mg^`;Q%N11EqG1hA^LDb6@{rht`+JqVwUifHst_Xa4c30VKfZh1-s|!vY=cNm
z{4d|{eiB?Z3r&Cg_+WaKRR)QFc^yy7ybSvtL+6PiCgtk2#1|<wY*^4xK>s`y3so3%
z0HOP#U`o1tM*SMKSbZ#>yIQS&#0RTT$g>LRHeoma$u9iad0@N_<p){6nFv#evbaaM
zC&5)9-nmv-NDV#U@DoIfoeuLV7}W&PUF6HPLEDbila>=n2k^c|XhGT#q2rAuuO_9C
zH1na%Dv*dAlPu1JpFQ2gA-?o6Nvb%!nq0$geix9a0dc4cl;8p_b5>A*&4PyA*k-HL
zGk9tcbP&DJ;y{USHx+{YFN#Pa)Z=;jAAw}VmDoH{O1p4_#J<M?`aO2viW@L1Li#t8
zbYhS`%S=0N3_8wSnSnj&<6r8qa42`qOlm)13vT!uC{X!kbrmDTIk-;2NWWBnWw_2T
zPK3}T=Pr-MRkv_kkd%a!VsWsynM|%c`)EhJy=<x=Iwtv$*5-ICXBzb=sN(a$QGeq@
zUHR_>3X#wz8KDZ1Y0;Bv`4?}MO#;b}B8!;=XGPa%H0(|)zPd)W<9)XnLKCX~2g;89
zC9kiY{9MlX<UdezdGIGx&7-)@pE%*&YX-8|D#;<dH=}=E98D+bJLb-D2t8*58huqk
zr4rR_HF2`tM3n~k!_?W}WAogr9}|M9%>N=oviV9UgK@7K&cSA4ZN;)#{Xh|NM>Ih4
zpe~5FqQ6Y6`sZ+Id!<8@!YQ%*+#Y|)RDE|yYYmrt&i~o2RqyhKKN^@9GztmU2;n!h
zr0Pw#fAdb|?JKdT3)nB7aWBW4;{FQI#=hd#)?u4)&a8UD?kZp5w9r>*Tx=>UwahBt
zL|a5Kp#stmpR9fy)U3Vo8VI-M_k14Mq22NhZv`_bs1wf}uv4Z`Uu^`(d9ayMzk#U4
z@y&Gb8HsR|sbgPtKXXAMx@Qay0Fl15FS^gzR2jTw!6W=ULWqY&U%{*b`4;~E2g;`U
zSGq{NbiJ+F)mYDG)-OW2EJth#Bm9)VQEpKNJ81(;cjiaah0hmVIlhx@RSP{x&M7q-
z&#6HVlERce_#@|sRU{zCwtsq845OCr+@{fhV9pd*`!e2<^mMK2lc2|A`?WDI$X^<{
z1mW(8tyHp-V)IkYAGenj4+3w6%&t0me|$OhQlsI>L;XT+J#3`N{vFl!Se&qs%WFPP
zkLDNM`ePa{?Lt?sKK3b_t`6V1)AM0W>@=p~d@;B%>*D>x+QX~A`1MP7UNw3K^Zj<R
z-}&$k*P|++>@&kKx(D9V*D<8n>$`gV#us_rO;gK(`p0jU4{BA&&rEuoj<sVBLuMUn
zEzXG+Lelh4^cm}Mt@MAA0s68iH5V670oh*|%EfjE5qtFaE}-`s;ptSwY|lOaO)9S1
z3U56D&QHU%VO`BtKq10BZCtMeI*7^X&v(|dz0G$93lRuQPxgXHj{B_Z&wJck*T-Ku
z^H=sBI^Aq##EmT#Z&cl%>((7Xhup8|du#-QUBB)t|GLP11YlEB?w^5dtKP+}I#{xl
znA#JN?i|GGVfQ$AQg&nMw4MFc9!qdn+jLj%)AQ88qk9reJm~okAx=3WGeqyj`pR~X
zZ8?#MqjQIc;+|K$U2&XJ<JtC=!kv91^-GHzt85N%B?usxQZLu%^BupKmgT@L94sM0
zKus=iF!f{~H3W<-PleWIT0Fcm4l8!a18_DPOvdbS*vYpMos-2ATnW=*_Y-8jmTT@C
zYOUOj4U$*RL2TfyLV>S8aFX=UF?(uq(~e}iiF-=q^}i}IhyP?Lzq4LMwKhQG{YsPy
ztglp7P53#NH<~A&o@hJWVq%t}mt<zDe`vMsF2m!e9dQ@a-_SjuSAL*Ra%Q{~E2M;c
zQ}Lg(So`Sp>)2*r%T(#C>=ydmwmzPoXJp1k#3>@Kp1r$i*Wmg3GT_#n&_h0%ddDtu
zUgY#2h{%tL2apM)*nTOQkxJa?#X~#6aC|B_dt;dQsrpPRfV7&FQM#cSPs22K)s-UM
zJ+<~VIWjThG&BIpGQt#~Urhu|fi0eoK;=@Sm{aqaN_cihqzT?y@a!(YScYS*OY%DL
zs|xKUySCyNbr2w?Ids1YnoDxKO`g@_ybr|6n5nlGJAnd$(DU|V%x9F@XP_4M<yh-B
zFzPu_Sp!4<;c^8`Oaj>R0PsY=*wusp!_IbiiNP=+td^P_fQ-9iau$66&Kt@g_Z!W8
z)@F|tk+QEgSub%$Taasceh*cFD<BlvR5WxzT0Htm2P!18_SlI;QfIlsCfM8AXN@;H
z;1>ZFn61<sBxnFQCqv+m-(uE*CKzZdEXKYc7}>yaAK{?|`Rjn)`y~dyMTx{up`$^-
z)GToQOk^iTvDU?q@m3+Uj5VWA?sMI2UqDwiRuAI7?qkHn>M>fg#0k@S?yC)=Wu^29
z2VkN4le@axTsb)}RDD@dpyvdKaA0^(isks57OAujxbqH|c1-e{QG5>EY%7!;yszq>
zJ=G{V273n{*THJE&FF!x&n~01{PoGRa0NZHLwL2(OqyVldmvEA)xov^;N{|hHl}D3
z(SP>jp1(0(xtU%C`$!A?utSA?B*DfdnmBTU2&CJ&abB>WiJ>R#%*D66+sfF=%0a`<
zS9Gvl&hG6GXMv925iS%A;5eR(X9X;2IG7dBKQIDmJ6OT?BqY=-MKaear-JqnkV$X#
z0jw2?Rt}srWC$>@v4^|o_=Cu}Wp^&}D`*Q@$5z#+Jg+gNskWgs-*S;!XJ90N)hceK
zb7QA8$pL95+<kXfEi=;#)`^c_Xpa;2&wt|TbS7~edp&a^r$6@HdYCGZeYM&GW(pNo
z6Oef{P!2xFhxx47rUOQdPDqZH{TS_miqp98#y!Gw2f+ho)DckxCh6V-fD}+5HUFJ^
zv6dp^2~4`0Ph|zy`Q!sbfRaN6V{K9?KVY45bziyw-w2sMNCzPg$Dah|6qdjAaRp}-
z>Bjox;`FPn#k#pG?v60E=&<=)<E7NoLA);tvF~{fl!JB&hxQdZ8A&%LrY`bxN1%{U
zf~7yO4?&{)iV`E>nb5{BXLma?8(ZmlNhxYM*5`o#O-na3_<crxsIWZ{c)@iK)c`^Y
z`+r5oECd2-Po8}S6bOSMAg_ER&sr#vi3adV1Z1M9gkuZz(4<f%&e%k_%&CPLgev|f
zQa~&gzo>`Q7{^k<#Al}ljAH>q>?S-|z?Sg=@QCF05AWT8FfAT%ljY)!0PDQi0c#Qe
z>mN!HNfC*TKtM#Y#Sj1cu@M#x;9-E@Cw;36^dNci+aMro6p*QTLrFCBtg?_IN&}V>
zkh*}$(5*xaIdnudA3M=qiwR2KN2~<V<A>5>Ch0$LvBA1M;l8lNt>S*g<>V}7Xo_X)
zTB;XNzeHkpBRwiuso0Szs=aQ&>;s3+|6Bj?|L6CxiOam2fA|`Ic|l_1I3)A>+tTh2
z5+hNi7M_jI>r{VVtGu2RI1iwyYr=OVYn4KN8Tf*A8Z?7-#xm3V_R*c#l#BxP*6ID@
z@e{IRF@L7?o*?mA-CGUJmwd*UFTNw*4q@c%Jg*r+d=eAtZo+r6t4w@7I)7_E99o{X
zh&(A>Mz0?58S=V1ttX}DTcai!XP6E@)oIFI{!M>|OtzLBV99dKqp*>Y%^v_ozTdaV
z=$EN6H$JB9a+~9OGncXc;Xe@8%Es+%k(qCiN<+-xWz4G(AJmB}^Ht%3VaJKU(5*0w
zr0n3X@u;rqXE&Ck*nNiSCE<+Q;c0J8SZ|9Bkr`?3`wCw#(|2_zk;^(Egf5Qa`}%6M
ztAw<Bnx1e&PJRK{mx=t2%svm%sHJN|c~5$QpZub={7wpT_5O|@(s_RlG?ve;Q`E4<
zFE@S@$E&EU0vw*tK2r=zt45$weFsb&m1_cu9N(@!nj+JfAzEa8Q(nZ~_VV=I3b@a(
zwX>C~05{chrpjIpIwd3GdjNrQJ{C7-C@yc|OJUreh>|?efBW6f+@go_w}*pXa-z}X
z?43<W)v%s2AHIA`Ie8=FD_v(h&}PW88Bq-vC0ORXvn*|)g_ykhf%5f+W~ukoKo!31
z2^6hn=3P)nh15>Le695|5m`AaOhRH-UZ3oiH}31VlqO64K)-LNJ>qIw>oyr>;l=t7
zB=By>VZC@%sa;1j?7aB6rBI&ek_o&L!PEG#^s~k_DXFo~b6McZr_i35zrp9){-*yg
zA@g)|!Tk8=zkZG!q`3(d{FE{(5nW}^R6HsEITSNaL5#TlMwOxE-Yd2RNJ-iNBB!Ao
z4_V&ly*SB!xv`Vs2QtW4Jio7_Wh3>l`6)UpYdeFPF@T76#_-bB)hpS0UJAJdXIhe{
z-@U_MJ$P$4v;Gwx!u`{|S@%v1E#~I{b$b86eq{3>DC|l6zwQT{$d1hdJAARdkVjrw
zb|w=Bj<+$kngx8;+hZLL+B8?e52xJ%Oux!t6UwyJZ(9|%s@os!3D7SgJVMLkniTgV
z-jEsXSfn(K`%ZSFmfOpi+7|g-Bqce;LwHX{LVCznH}U+|6EC*`8Hra~o+Y8qhI@9}
zx;gI=4N^=NZaSlC!xY}`CeJ&jCZIgsATw&L&nW~S%X)npQQuZ(zOOVTP{lm&C>b~{
z?`4qthW^A@T+v#z>2Fzzk%W4UT82kH$&tgOCfds3KV9=nKY2rJ%?j7!Mkp;_2YGfi
zM|~)C{6-gZX)amve#1~o((4-Egs$D3j0^o)?2b48QPZB1E%F82MG~@UFtAki+2r;8
z8QvNOFZqc~b@3D1c$Mb_UJ|U+u^jb2PGOiLQ#BvArw&Cq?6Khv)+KOq=%95c@p6i0
zOv5wQ>waEBV`T;Q+>9lxX8R{fE}NuKBv#30HK}!cz?Act?4GhL@EI{Q_Ph|4?xG3R
zMdq>|^s&;x?%Xvb$MA|Re_s^9EKtvZGaYMKq;LMnfUfFWZrL^-tO7uxV}^SER73*@
zvU*k+pSmeC4vvW2`%;v{`y%6e(QRQq)|^LD3(rcLxv1#_<&g_|ZQ<fa!z1jxjln_p
zoC-1O3*yXE>>@mr$eWy)JL2Lik5^H5_=|GJ95}P$7o@rWfv9DvzkV`BZa&6Cxc7OR
zGhewDJ2oSxm^YoR9>{;rSD&+xEgAi3YjtMoe0z;xaM$cYyKN~e^H^bT*BgHx4)D6)
z!#XSd{#X&*_I%3vMM9weRO#P>r&}#wS?G4gR@aLh=%om!y$fO@Sk}$>s`=d~xhmb%
z2&F&gw{CAMo>Mvgii=)0n=xT?2;dfrh>81<p+vD1>s{(8vh>#>PkeE`$X&mn<kBp#
zeX3kI0m0#eUD@-fHfZPt<$TFg+}o-~|0xYK#uAQ2Jxb->1d3EyKDk$~gLz>sO(&sF
z6#GbPIH^%4y&C8!<EOqB8Attd7g=6a!Efp@^J^6R($N_rcVY-L0<#h)KJ1_puyt|O
z^VXEr^_?hFMc!qsZi{U%zX_|mvk^z$z;86}TN+52#c$W9Oi!uv!IBkBPc^lcY#nJ0
zj80EE1phfW=|MR>vs2NhGZhjV(o(p#P6z$sx3BfS$k2Zc#fa>~AHiZT3pZjt6)2$~
zThsv82i6J_V9P50oQG9V=_Q^aY-<!F8j1kL30ua#(&)S_v`R$g3e2_i@HECDo8Ple
zR-H@7z5JGCwcP5Wh%7BQSXt3`A7jtxk(<g#bBQPn%G!gt$Ms0`Q1bMk5Uilx)Rq=K
zyZ<4{b^wb$6H4Pn=fVSNT(1W`<0?=YFtL>=+|a>!u*65EC4iakd2?m-r@upCxRC?J
zMMB(}R%Ov$Ob*&2s-5y#s?pygP_ZSDBhMl9WiB4D1x7UpyKs4=lBpwFbd>Y)oQ3qw
z_j#oZL87QflVUp$k1*#WDkkYh$p_^XoUWojwc^fM(tKMMH947$QxEpY{D0R1UPu1F
znke&*v{0&O97AW`p+Jr9_X{)JHpjLX)0HzbPt+=(|3ftAp#3ay#Cd<s>Md%WYO?uQ
zXQCp%dRZD2$yCNc`}!PSLi8AkJSlXu1E%PS81T|1VT+z{Jn3<^t{S)+B$N^J01Nec
zW@-0&xh(tX01_WBy2}I<us};o$>~D&Ua}<kB=fXS56lQoKx@Rm){@tMfo(HYW%<L=
zRm6n(>pLCQQVE>xZx<y%L#Md=2Knt%CVe*M-`4P|i?iU9D4U&~-|XM8(`mm+JK<H9
zt;w32Az@QhChjatT;D%(#Rk`X&`-_G`kkz9**LbU0BPJH@};FKq0LxJCG$tX@VCQ&
zj)0G1A2*Z3ubF3`2P@p2IaUAk_8`N;*1{f*lF3YJJ;GTDiF*bk@o~Tgum(-ld}3e>
zj2<7x4DHpUhz0JoCe@1cwSl|0=K&KlfGsvu5?ufu$E<}iB=pDX*C>lj>9Cs56<I?T
z^?+t%CYcF8R@zcHV)&_tuu8qxGR<sV#nVwG6lUJo=&sv6_I9i3Kx>QP=XIs?imC6{
ze|cwRsged8eSf}bCu#6ImSS3|z22}K9Pd@<hpK%lq536b^Ct0ojecx=n&2ZB*yL|p
z&zW#xWgZT2rd9aQOgni+lmTzg<W`ZNh94S9xZ$Kk60dDh-%)g>(rdU=;au=Ws%GU{
zg(XYf($=$!KxVRm(mc}UD59Sx?$n5%C}6lJVWye*ZKzahD6n1l<3q@ILU~NufOS8d
z5o7ZzXhn8^N17$n1V$9RR64}Ra=j(;Al8I93h6Qkb#2IAjrQ@p7cr>h*aG>G(`=39
zmVIv4LI>VD^Sf|!7xr?sf3H1?j{GZf;Y>Qq(UQx3UQztgV1=K$T3LP$?rjlRVR<yx
zPaj3%&p#;pjsXay(6v{@YhSY}WG-e_&VPEyv%P)!^<%>EN&tzz`rseGp&MW~GS2v6
zbO)_@(UPM}Z+$a!U(`89FrT?N;_1;dU2_-dFG%LE*<N?8^Uu@!EomT4(fZE`%ya3X
z(-5h}ACvC`C_ZU&&9FWEdR`v3tKN{6Xy(>rvnG+R__r=<%bO+SB;T1wSF4-NHm$j-
z@UNBJaT%5`nurIxDkbw>io%Zp*4Lf507O9*Si}SsS0&?d*cm#|nqzyQ2Ni%^TR#L-
z_4;mW`MrMerT2{wZ?Zi6%o5C;S3q%K_PFDP!kFX{S3(fNnX}R+o{Kfo|DfS`XymP3
z82%w=Y_OP#^IP=>oS&XVw;MWr9>T5fi()d*UKl?MmOt7|l(YRtFyP!>Efg&3>+(B^
zafFR29L10CAyB~aZ+%~j+Qq+`YU5c4Gb`vmzTZ%`why46=)Lyy9}-*{`5tC8rLoS)
z=92snB3F~l>a^{5!*UgGMV10z9>3Z5^koO~58QWSm5zolznrT_oO$q6v*<1QetKDp
zThJWoeSQt7u<o>gexB=D<6L^NKI%GaM$N+}+it8(AGg%*-}e59G|_hJpFp>XRoWl%
zYNm6JIjvWl-rM)|T?4n%o1XyqRY5L1XVW@VGOx?Cy5*{VEg*OKZ8}lTFM}tuv3HsQ
zIijzURBov<YM6@>{N3YdSfnPaNk0F3SlM!1_(*W>AKKOW&*N{%yu){MDw*a7F9vf{
z@I$@YMP8SOh)YBsQIho;6@!CLzm(lkaY((98;7~{WHn7-X3E$moNd84S}!Xju`4({
zKj3HjzGyH6>-!+`>4++3L1jjXR$|}CX4CRibzomXBUDxr2&meB=qI$DiBU|gvv_k{
z&DbX-g+sdq-4&?6zRFlpE^d-_5N~e|YO)|a+to0NlFN#dc1VCLh!keEpVr(V8a-nv
z&r6>5cKC*AJ`*mv?GB~<d2v_r()hek?9MThDDGTH34&!ebO^WV+N%Adlhllho#$9W
zb{zZ)tE>jJCokm)bL_I<WBoP2h{5NcngqYDWP7`IR}yu>Dq(gzV{a(mjp)XgEluUT
zA=+t}-Dcqhd|KYck(nRB*}RI@{lxF4ODTg0z1U;oe#HhK7t$GJ8%<Bw=>8F7pI0vW
zH}i>5T)l!))Sc54<rcSa6(TilYQq$%T3x(iP=+_?`{5n2pXz}&wH^z6nnDOIp)5K`
zRoc~?9`m&C;{!(@yg_ZiWPDy?Ewxg~zIx(i^GNFFQ5mvyF`gd^tsve`$QpjVBfZE=
zsn~K>Ff9|}!BFOX2_ON(uA0m9o1=XW^}abh)LTbtMI$Tq{GxC>^X+B*Cy!Mni!99)
z+FQqQg@RLq>;BTv8=?ir2}cBYHpoUl5v|cnpQBfp&)(@;JWg<sILr0a>Lxw&VouEs
z1|kBskK=mbz#RR0O(B~+uUs3h1Zlu~G%Z-xo_u12R<`6CLOl@D9ZF6LfG*k<f`0od
zlDQxuKz+O`iX<EX;RH<99BKl_9@@H`nRGfJNl+Z{=aKBA11d<L6ak1SpA$fVvg?4=
zOZ~8ZToAVc!d+o^vQ3Z&#2giIps=gRWRDfF9*a41sY|s=>>FV&I91tH0V;60K1IQ>
zi3d-uTpUg!$nCf<no)-pvZ@JLO;Q*DDr(*r`QMm!RZJAvHiBfKSU`Xii~x-F3LqIw
zJTx;FIBK)UnuBD5cNG8ulDjJIQuf0cNe}`gqn}D<rX#FB=C7|w%MP^OK%yf|^ofke
zidIS>=?-}`>x%9lq(+KDA4k!*f|YT?0W;m%1|BQ~K)r-+w<7}18OK?{V95d|L;#S@
z0W$Rb6h$zssh}SSLP;LpXN3?MaIj+RIAA2t{SFmnVkbS+)>29?ft+a%A=(Gd3Gvr(
zS0Kg9B<vIRE{c7J0dXhntHma1Sq`+p#<3~;SaAe|@DjISy=?0hY%-X$5pe)nl1KCG
zL7QX)bfmU2NH_HC7QW@n)nzGxK(;CIQ%xW*pooQ+m`R!nMw%Tf5GqIlbPXni2t;g^
z0<+GZ^1sz#l@F-kx!6ja$kY*0U6<L49d{o%DHvdC2aHzh^Ix;;8qd(3qdZu3))4Rg
zne;ypk{6ix%yA`fNv>ti3D2lRS3W+BGJA0xI|L3~3VsDPWI`2)p>pxP_tiDQ*>xRp
zAf_E)J##ITl9u@__`Q$p2yLG*B^}ISyF!2)V7~IvtdO=6DImDi^Fr?`D+f%1Ai<LP
zx%(=d^a`|>ecWbNsh$HYCeQJKLKUZV5!`&KL}Vr*c&Z;np{gm!vm-SQ;L-{=7<#E2
zJ@O8HwFG}@uYAeBfI|x{1j{(fWpr1-T6v#~lF}PzYbv-y^rPGX8-aB^R0YP&GXM$I
z*W_kT-yf^zzTV0pk|>~M^7qGVr6hDG5>Ix(3H!J-nVPpzAW>y|nE;e|DWDT0m72KY
zM(O#ELJ64f?P=R+J+H@uFMMIyjcAE~0eV1!^+?EpZ%g|n9Jp2}4|!dx9uOjFrPjIq
zPhiDEo~k#YKnN7=?6I&4U~Ra-D(Fr@J_@8~UoZxUv(%M<)q{#Bbh&`1BQH619Hhhs
zc(;}laRs<%A@mjy-36315E=qnEbly^BsifypGc^#hU8%i4^v-`4Tj-<=;Df>YP>5h
zWP>8)iA+F}`SslE>PVm(u_p>VBj>#FQ2Ks$=fd@D2NU2h88NIZr5B$$*?=Ke%rzjH
zXj%RWygb)J8}FCTnu>QjG4w1+8XT~?#@u%{ep_E-U)5RYbEjHBR_b!ywfexi40RN$
zhNvJ&v}LGOHn7hM{y*f||LC*-i!Tx#`vO@WaK^D~j9^`yoKi#0mkrA>Ru-Nr@YFvS
z7s1WX&k3zFf0$g#GdryP)S@mesLN+)<Lf!}7#&C+C@D!I8KbFXk6ivG`+Ms1d~kkQ
zd6l)prJQNtLI8ak>%3o;(G?pgfcW}rqRra(4b7O7!kVV=H$SK`z3X+KkkyID!&_}W
zYsz0~o5Q_`o`DmoTSwQ#GzY@s9qAJ{y%lU}ds7CS$$w#lU%&PL({iP~)&aFqT}^!^
zt=rMx!V(osTHmfbQ_tZ1i}M%Oeamd+*@_#V!~5w<J(XYd2|d~nL<4|^qb7`{|87(D
zFDePNqRlMg``e3-$6{z+j&Ck7$Y3g`fP?9(Ou^~OEd=*}AftieGKX$k8T(3)-mvpB
zf0ta8d5Lpy&8Nti&HRuxNXg>`Gex#oIJM$!?cM8r6W1Odnb){&OC#wQ{&xKGA7^*x
z3wi$%3-7g49rvePI66vjwExyl-2sF5_`)aI8je0!iM2PO>3XtCyF3T#y|dYl+P@s_
zDwm)aoikT81btlTwyB1*^!5kjI42L@JZ5K+&|heC-s7-!jhcOUlJRDjI%)T_^WbUw
zX-H>)0a=V3lfwh!r(ew?KWTi-GpgQGEM3{D80#6d)<<F`amq`WZ_uyad94R=n;cEV
z4}BVbqZrpua5FVZVP$_zXFacNt@F%(xox~^CDd#%hmYiZhYx2oG%H6~EP;n1n4#rp
zk0!#bE@*CeQ3!rRyxLzuiq0Qy_*_O+E@&N>YVF3fzlF7-v4_5^`1MpX2!FMT#-5qs
zD4df<<Y{MyMN#sfd;fWQh<7mbSfD8Ctcg3TD+Td8Yb3C*(l^T4^;Pzk8JWnZH2Elb
zc*mM6#h#qVjIvLy>MeU@fT0gdcN^Z%?zOE4t8_l*?et*0Lx<@${tpvtqU0wj@#plF
zv<6xCc`tl;pO>?fD${yiP0Mqh_Psls2rJ4rRthOLRTBH<{(S6oW1R!jM%mjz_TJH%
z?BFJ7IOT`WA0V|i4_R$2AB%COzNgFOmt>NP=i6~SjBaO{dhdL3ltEkgI;rO7eFd~%
zz`;g3n`V^-kBoZ1!^U~vmE~qYv8&21XJs}zq_*J&mfEzhTfnU73SrfIP4kQH$-l`e
zkRlKG!rLRU9s2b6zjZ%tpG|!A^S)o|YPu-f_+H(Vw2>4jP}6a%LFjw@r`JeEvvcX-
zz&z!srN_X8I&qgFy6Mr!wyzlUk=76EwH+5huJ0erl&>D+Y_piuRP0_hQ*B?&q-sQj
z!Du)8%yWovMu%ULG4S!&$SNKh@vUm|FALmf%3C*^SC9>p)lj)UpFQwe5P?am8GdAU
zZ7sT!-G3EVk;uo_xMQDeQTja8kE2ZjtTjUQOn~#1v(&`)>HG|(xX2cSq2|1(BI|p@
zX1H*WH*$39PRRzn)a5D@3LB-Y(ynkQFW#e-;0@UNx}|Eq^E9v0EjNg7=z+uclO|FP
zw!cr6lwtEE0kwZ;x3<6phNt{;J85Kl<@r{0&!qOx((sA2T3hYnT17xj%hS(Q&*_rr
z4d+46=X96L)E#1<GT<*4ND`;qOexMS(B3&Rn?53)tmnIbtRlXd%`Fdea>H*d{UIta
zy;#c&S@sMMm_fHiE`Mv5mPWW3kp|WYAdO|7tbxk^%+autdRWV^8rn`6if9CNa__$J
ziKyGLo~G1Is&EO+eku5y*YQO+GajZ@<Bv`Dg{iEf7ClsA>8wmn_)6DnwanVjIjEWK
zr}btLt?|+~QT@J$XP7G3u9I~&5;}oLHE!p#I^S9xSF*s3$sB%RliBoeyfLNsSi9a%
zFYp(6zvYhoa;d0>i?)faJW*K6b<^(5*T$Ny4_Z<rm}*vc4TAYE@d2+sc&d7%@S;d1
z3nlTge+j$mqyX>UObGW8kY4dNgyebaxW9geyCz^LNDU3O=RiG|EX4OZy6vZb8*O6x
z#%gS=KJ9yDDWU!!vDv*28YfsM$I(H74Q*gWtqU2Z)xuqSM|!5Ze67Oj3C_|#e_(n3
zfq$fUKgq;5YI(-gI9_H5Pu#FdDE#h8adq<>xw%iVchL#M?eO|n$rg<7ci(76)tCIn
zp>B?xaxb|pf%ZKv&q@(>Zy3DHp;01>4itNesK93bMof8eV>l+V*p2Q{KXn;eYp8!q
z`F5`~>Yul_;`Dyf*K{k1tvvL*=|m;zJ;%0Y2lotX-@Bek_tNNYL+YdJbVGuSZMx#K
zF9LbfY>u<<e(d~eEA#22kF03bePJoJ+{4oYWj!c@FIId{@u?XSuJ?N^`A$Sxi*Cw}
z%Ia35y8dMTkB(^)w~b6f#p~N=8LfOgXY7f_Fm7K<olT}VevQOPEodBz7*DgpS7YTv
zT@AbK;$jM#xut|*QSDoqrv61eze*|k+Q;onqgn{uK@wAZfe~U>^G11-%(?q~fvuJ8
z+|o<&3fJkbn{mSA=#S&!3)=NM!6s<cPo$&{+O;jvd3;E}!R~G!?+;qE*Sp*9{0(5D
z_ArqVI4(pcv`MpCWsvR~{5=%p-#lggGCQrf+Cfx8%Rg<Is$2)sesA|>X_jQ9DNcza
zHZThs>j|&|3b^s}4rMv3BU)brkl*9Of_0$6&;l1z+7c%3;*!{}?js7Oo*tg6`0Ssl
z7(Z0~)Z<*%51L2Xp1$=KNl}QoLBfNVp&6xEd!1eomMRD?WCkz^Y-dk>tp)Bn0aZZ;
z5wIGn+7Bv_WUd1%fVM&<ceQfqLEg&%$*7Q)%E&UDs5Vx?3L!GHgg&#)93a+s7X&4n
zK}tY6wa#+aVo&?<kqQ!eV5A0SobBh(##*@~LB6YhS>~%wJn&YD1vK!LhNq!iZ?^f$
zM!n&C9lru>j=;JmyhI|M)=6x~AawP9Qha~1&Fhd9`8ZAwKW7Z;;PV*#1+9LYNVG#b
zhb*EZ+_$um0!s@Ir3i76$Tj4Aw69f+H6o)HKZV6cSD2IptX6R$dUjR$U%tAx2h)`>
z#HZ15PSSqx)QV+u&5^h$OzGp1D8z}>)gJ6k@PCh>WNb;h<7Hi!LFw%w2n>iSPJppo
zWi3rUiul4recEpbQ{wm#DUG#eA%X-l_2TCJ6V;@oNY;1sjfz8aL|VgJIO3;fYMTrF
zCquJN)?CQ}#s@h+o5EE;K3w(rGyMuC8~561te$$3{8UP5B7{PBKiT-I(vm9;!P!q)
zpD|STpj?;6Y;>Ji`X&?F)cTo>SFPwX|2Byl6&)RRoo!Oxg`*Kl$8ghk1H37gZOCZw
zlz&G?+Gcfs0jmGHnS8NC+DCjMe(|!>e~VzX$#*qXot)b-{><r7Y}k1bZXYRp0sAFu
zFeIM?a%c5*rr_IRQv6guH|+G%Q)7OhUYIVsy$-C+>p1|+;c{=X2Qhk&JW(w*3T$%C
zEfYrkNY|j|lblPiXtQs|&d@^umi@xoBm7T7s^mMfVA(l>2d@dEyT`{ttM_Lj3lU4d
zL*Rna%<i@G>2}y{sL2bzDKl_DSr6^mYwkO~;IWI~@o%il4tm2ul-Qv)r#-ml<)Y`6
zwcRyW{wIqAB@2F@1D7@eJ;79m1|0-4WOi{g3DV#@Ek`Rdf-B`-EYfHP)qlqkhSal)
zurH@k)t_%Z#5ot)?_fAAZGY&Wk`?lNzw%pKQk)%}_$Pkk$$r365u`@;yL_G4*~a;C
z{9x#-ijquAH@WbruRgf%e3f##$*7hUz$SCMza;pRsrcnrBrAM7?D~Au52W&5-gj57
znm4*W@$BN>*LZ5yp>ogT6HvqXc>veuh^4zB<C!7lsQ>-n5Z;~gb|znL4ao#}{EPoU
znxu!@rhGUD58uu1B}xpYRhrPl$QC+RME-987!#indH7}Vy2kga*FHuzQn|YH404qE
zm#sqPaC&T2a~`;f_MZ5GvUo{O<UOI?2hAloM!GTTo%j>E#SPsShSD{pJ8KD`U49o4
zD?e~!hw`oHhUsVIYIi(+;QF5w3*JDNyd{iZrfWfh3Ds5-OY&N;BKe&udq>9<VO#z0
zLFCE-NZn#L{Dn-st(q42^@LXuYx6I5<mpd7b;LKoRqJb$T095DB7BZJjK7%voq;m@
zKb`}^uBE<j58M#iiuK!*gwb}VmaF`=pRHkTiT{CGj83oed()jXnp@ZJXIOPDn$9_!
zqtcz^13bwGE>YhrTY)!Cpr-zuB)%&$u#NwR&!gtG6F<{w)VEs+Zh_A?nUmECc~x>E
zzP975T!JCL&1N3`83@4TG&LSxuj%tGu8*}iprc~%`Hj^_O`IJET$y1y`*N4zBC4n5
zs%WjOV)*+2a{zJ+I03_sFVM%H9z))#1oX}q<oc8Hi6agx{jyK|WIs)9TA7#Q@rpM#
zya-=$pZ|n~KNsedHIj2Eju^84bcdZ*mHYOhRJ5e{w&vkImc%Fd_g0zg17_2B(_Hdi
z<N!G3(Zet}hNcF;Qv4^^lp8Y@I4V(Ym#iYw^6-99<bgwhfopA%45f7Q%DKdpdl)S8
zAISUr1?89tw&xTQ)as>p$LoHmo23_=%X7!u7^8P>!5pBEHR2;}cNvxcRCVtKV-DPx
zsPQ_q@H(kvvkxSSupUGc<~-E1HOIV{nWVo~QOrhQ@q9`dD!P8H^QXg7S8O9X4k$A>
z(zA;IF*=9xZD*LVraOn1zh%<L+x}3o*y<wbNRi4_vvt(3Yg8s%;+c89!{Y$9H#C|z
zWGyUPh^YIn;n*MtECff8gLX|ys9NbO+Z)1B4wDP-2l>HQwm$N}NNrsM^zJ1p(Rd&h
zP)@0Re`EBeFXI>vwvLoIt6+1<&ztOJz36kOb}f-xq6_B+v|-a@?k3?+AnitnCj5-5
zUcXlD2Dnd3l#&zP_E&yjDp~M7FjXOjyeJ?3WS_sUC(s-}Z9z7gN-Awo8ms%YcrXw>
z2KPx78Gxrl^6FkqkUAy&?1w%lO7wt=%;)elMSbW(^TkiCjzO5U%^k}5J|aPVLJV!Y
z{<;>8U+w#~O?Y<CiY)Q){eelpKBk)qi^irA=BUJX^+FDK5MTxnq_tc}0o1TqcSo?(
zmlFUw2=1z{)z!z~J_#cL-R%ri+V?>~AN)O)MfcTXt>ULTHT-q(*R_EH)&PV+{1_7s
z=zUaRp&|niZ!~Oqs#91pcN^F$l=0UADcc{aIEVtqqkbM4cg59^?!;{WNpf%WUxc(5
z8hGpM0X$3EXd$=){=Rw+T-#rI9Q!|zsDj*7DtJVgrV<xBk;TO9Ru8m4lZqh{(ZB_U
zdzxqqSp3r=p=RS+zWK4XvDP!85ce??DI}<~pa6hkaJdkQeZowg`7*lm;c_O=De2H)
zK;}-yJoP@;I@-inLgupgRExzt6^m`peh+~UHvvi9OdO){G4bw51uoBJl>cPRTC5IO
zg$ddh23bzk!H&Jv0rEt}F(CMXtpx2hT^1}U4EXf%9E>9Bz@uc_s`yxAPMDM-FdDYu
zGr}VSaB|?WlY%kX_BuwOpEn=MNXo;AR3Mc{Ll62u(0hdF0*X{c3$T!To!v|<r;;KF
z2HZ7XFjPSn!=a`rsytXyl!`Lrz|!Qnh^L}tu0^cQQ+p7Tzy5d6F}S@0)|iQc+}DU@
zq`pE_SoWgcds+L@N8p)aTrl?6@zZO)Y=nFkwuSE<RPCaG8zps~Yq_r|_Z!G@fYlyy
zcewKZ(#Qn}2vGO!t1oAm0xtUjm{->Tgz^OAp<;HbKzg8-JpchRJFsktBw#vyp{@|I
z9HA^Sjs*V5FUEDVr}Sd&0Fk@Yse+7-wk!e{OuA&>hhM>Hhr(m|m<JGp7Whe;MWm@-
z1#CqTC@k!(*c*&Bp#Kkkwc>e?z~$KrCDDOmjhP)QYl3KRw!(##a8Qbw+mc0YG>j7i
zn0Vm7_KRyBEI@LFN#Q(2i6TLIqKa$r;j!baFdYdde?5vnuqd8wMkH3(t}4FF1)3WI
zvV*y+!6kDo2QOfxb)+gLWdDbeI#khBd7%Ny9M@!AuV=&%gZ7cQbe9DZz_W0u>^=t6
z46_iSF8_hpfh^G%;srpLIE(<KCnXY&%hXu7fx(*V@z?R)i~~Ku!o%=?oT6piRS9u!
zCZ;B78}VXEbb@#DCAShmjPDBuWD$x(Xc?bAFgXcx6aGv}?&Sus-c$t($wq{V^xM<n
zcfcBfI;E6_9bEzb9Fu)NLiM8H&T)$j-YFZ$bb~o7kYNPsye4oSa%&XS^H52cK?QC;
zrNc+4uEezSzrYTQXXOTn>^}4{Pr0iDcq94%1-y8*hr?#l0b6`N@H*!zAcC6J6DL{2
z(&V7nSn$n&r~K|}$c*AXWkY<V&y(&RcO@aMI(@FL`9!@5%%>O)Pc@_u%o=9q&F}}6
zWPM&#x}sm|f}kaU5Q!sAp!CL%enSg^l%FTptT?n1Dx#l+vP@Vm-EzS(LNh_vM70TU
zX~=9}lB0B@3i}|HdW9nTkYgptCwLdo@)XVm%A$A&1#|N`O4!xob-BRB8v(6IJXX9^
zxBrV!?*A*$6RtlbnY;Q>w7{9j3&qk|mpk8F7CCx$fuk;47sv11eJC#?mv+!=TlVJn
zf_Y5eFDpd`7o8x4n7h%n!@hRg;}5=Xn66&)jXM4bX1ub$^6Am#%>DGS-4E-pqxY%8
zq-$%fz;~Cpo)Y45<m9RX$btwiPRy)wtZqoY=hj{Hgl3Dbv(%jWi09b$v(P^wdY-vP
zC91i*mzehh<AOq54KF0j_|`Ko%Knf!xBp!E`9xw<Z6yHXre#RXfU?aYO)2cL!G{vz
z;#`(J9Zr0X8D7;@R)ZZ+qE_2kyGny1Mv*%Lc{yJc9=t3(JIDi#9RsN`zxnb`TV`5I
zU!k^+R2;$TeD}Y{-%YpdikH1hsPOOTt|By@+x;^?izoTdZqvxKJ_zcf_S08;H40r!
z)iL$@?<P`Vf`eoW$baNm-%u)jVQY>jZhRH^U1+&-uv#}+f%$yx53S(Alh#nBr>&(0
z5Oep#8{KNrvAY**YUj5_sMRky@@y{14tPk|*{6GJJ;x=k6P_ymKRgL{uSc}q!e!@N
z+WHK>PrICzowt0?0*FH%pel07d09mssM0=pR`PyHUDMvxn8@$bu(*n@Ih8<HvK=S0
zsYHdWVZR~jjQPzR=@mF_!+_Sx6jg|Cx*EVj?u*&dWF{U@RL+(DVeV+Ed&N<O=ohR1
z;^O1)j@&qVWP7VH75t}g*gAvc=|xCIz-(kYtMR^+nU6`_l>0J!)()x2)vMUko+BY6
zP032zw&+nJ?etleI5!%4uU?uetI~I=;^Q^{fhelpP05M!{aG}5fz6=fjsMTldbK0U
zS@6RHdsF=j&PkCUi=y?OfDEU!Ms?#3Yem3Ld1`I?T!8;4r65Q@J>idY04t`hLK$R^
zlP$AteS&r4KhxmeS?WXWgz=mCel2<_G2C(69hU90-Vr74bMbw7*S$bA)Hs!_)v?><
zuL(w<xR|t6n2B#MPFn{x^SdXAFzyM1+ywbz{+_g9)}B0Jxu8?_!@_ICTZV{tR;g)2
zcE|zpK{r*&#R6}!og406XPdg7!mqX{8_nY5?D|17#Fli`_wG3U+(c|o)LuKyPT^%=
z<s}7`DkZH8fz$E517a9%z*d%7w_nm1d}&Crr0Dk7tet3zra7)}vGmfTt{`Y+`t0II
z;qLcc4}lE|Dgv#w`jhRLN8k5miJeb+%ZKrT_SJ^+7&V2+d@FBzeE4T5dGj+{od>Hl
zk61pQCs1BxE$=kd8x79OZH4r=Mt9$g#3z;UIT%nZnbcZj+SI;PxN_~wex&~9;<2fT
z%Vuh5ROMH1>S)Dcd;5`#Hi?RgJ#e&Q=);K4PBte^in>j3O;-T1Gha*8CDn*;%D^)k
zd*@aW@Um)wUvhubYpM-Y*1wwj(pjIMVy)ME9tE#qsX?nHj^ED7Sx*Q`YgIf(1Dlfc
zm;9=-&Z=TemQ$XJG$-#-+&vcarpckD4uaihW2fU-W7Up4uRpVqZ11;=D;LB^P6)Y7
zee|rKoosL<)0wUh61t}ruwCgk3~NE_&j@+FQFd)`AlE4GVNK&maM<3?+LrXA3qN}5
zX*5%QT_?Kv%=!Jru|OyC*2sCTn~v0Rs#R=Nh+tRBILf%9lFPLnL#`&a0pLKu_<*)E
zqiOg{A4#f(JIx8_x_c?Qi3_;IdPxOTbNHEM&33y){7|5h2g-ZwiKz>94RA>D#_$z#
zn3*J+WIGR8<5<}6Er6*`o#Q%|{&~a`!#02C^Y)0<CH&Ev-#>W2>O9kPNN+3Uy^wv@
zl}$5wC!60#)y$!)GR7sz)oji9&LVGplIpZF;`rH{?`h7TpJa4U6tx9(L~l=3)@2k<
zvm>RW>3aQk4-a3q6e93F6OVuNOiigx!<<a_2z&ygU4k<X&4t!9?Ro`6zSjpdHT1h-
z$p`H3ztvx?MYpv2F5>xBr3VIi+<fkk`G+j8iX~kto%$M6kT$BDXZLm~Hca>a%b;}1
zaWMvQ@Qx&!WBd|wEo7pjEWXt=PfWEHmLf~mSWJ{OQ-EObW<bB}*&1O>X6xKaLW5oz
zOB7PZ*BRm0rYwKeSVBJ2ukMpYFi4XECUbQpXiCca^SnDs_T`tUz(MU0v|TF8a$zYp
zAqemMo3G5V0zs$su4WPCPyygzc*ck!t><=`nlT4HoruIcc*UV)f3MGc<DNmQF@`Z(
zW+f1nO^vgU&F7tn-=`8PtcF!AQLk&ZzO8*)N5ko6bTlwu2MdWbXPd5g^eeVujv>v=
ztJ2eWyy`vQRzs_qYGzr<{;PH83Bmq?i&?TjC(Pp$mX_MYo|$3?6Q>K6dv=<*F>CYM
zqpv+C-es$&ekCHGy}2FJuTul)H`+PpO^h8Ml-eeTk*yr!2X#_%2ZJ6n13CYOcJ-kB
za<A`jIlf18$cLfhA{fC&D0by+1LvZD{;v!bhwuLi<(BkMBs=hZN!A0cQ}N{GM&r+9
zE2-j5GwnV_hyHWum0IR+bh52X!_sCdNn#(^)k5h|I!tmRp&#Cc{F`*OiFblHMd+)L
z`wm)OmX=rZYk(vHeeD%HF@a0dfq{h=iy!Zoi~<{FUffpqPQC+mk0k#SRmDvYZEc4!
zSqa(#{!t$Q_2)boGbxCYk_haVo05T-3tyLw756-;j-6A1tb~-CrzvD^jN>G6O*XE5
zkwJfrIGJPsh99)F0pyO8ITbqaAILn5QHam^l~qurwm_{Zk6;m3D90lFtT6OmiD6Vk
z54%s&1q$k9%+{vjclZ{@fpiEubQo7%7omvFF?kOCNl$r_xn2LFcBUwm-zf+Y7C{fP
zH=BfCmXva6;H?0ajoorNC;g_vnnIE22)HalbVP=k2U}Z+h(MBxl7tyoLK;vmYZKkI
zph9^A^eE0t-gTv}xNEYxFJ}zaAo2a(A=y))P1wb4YL}kyb<hqruQ|}Y*h;{Jl1A49
z-d}(LAbmZ8gEgNjKA~Zqq7XWjIPiIY7OkRXU}K5YcqEZD8^wWAOJfoV%Q5-riua4^
zx+O_5HG4XPD%M6DF7-^z##9!;`Fg+wu}D;~T|qY@QGyp*gvl_2yqh}i7CF`D0LF=p
z`U!G1o+GhVUOhJXH)L=}PzGAd$`)0KorzrMOp`b-T%WI7R#F_g<Bk1(9XAe=Eh*IF
zz=s@)9u<NJ`VpN1Is>2e+Wd+W@UmaKW3q7TW(^5(DAJRfNmH@N(O{YPH`6UyQYXE6
zOAB?TS7xWEj~rZzVZihTG4+LmVF1Z3eVNC%cPkbF2C?aS3*D4MyaW04qi!eSYkU&R
zH(^+#(4RvUnhZV7pF7++4Jh*cLVRob1dCP=)L*99+_8x+X=B${({)6Wd|~l~t>}c%
z%EPngO=I3YHSHb^qLV0)rkV!r6a>(FxPH7FL??@%E6+PxF%g?jbN-=Dk(NH2qw911
z9SA*+JZ3o-5P?2Gg+<h}dp7MLYW&6-wIW0O9-7>oH?!q)fjGw`3z~gPt$d4iUM};&
zV{UkO|ACD8r9YVImJu`4)=*pIm#o;eQNG|5q*(WI)vP~5Cv?3fG_f8<{3AGb`d|Ka
zN4UxWlBwW=5*!MR-0jYVotPP<Kf@t#w(&lQtSDmvU!ku519|2xGM+7dAe(8g3t!Nz
z*J-#QSH{mHs=3I+qo4{7k2k>o)$kTC(9#zaV017$qYOxxcliGU*;N>rF^m|{M!SXP
z998)|d-~&;;;a~Ok$Gw=kO|b@=bRaZ-nx{)+K0m4Jj&^2!8LYXvOlf<_t&wy3uZkN
z|B~iug$&cGrc45d@{h$fVpgvDHFZ8OYz7H((hNn-Ih0PlSqbh?`|tICxVnF#aqfI}
zTk=`Y>>RLfCaa^UJ^Ux(HQQW;#OL|gp==8W>YHWWC7}?%cW3$vbj?T^>ZijQ!&P)u
zGLv2h{zBxOPoI6EtYJ0=w4dcc8LF|#g&UUPj|^&$X1>^npopzFWtTpMNC{$h=c!I3
z54ej<URu2Ffmj6o!hLya{Nm?m#GXAiqi)2GL)$>inY5CCz+WQBrKM4N2P9C)W?&)T
zLz)}*x6czz(X>;T*>J-AyGpX{YBjIhNRcr)Q3`O;{uxmJqDF1vH&8~;k6-smdC!Qf
z0vi5g6AeDD%BpM^xXRv_dz(T~E}cVnm3=5@TfCqB4RI27c9(AA)%Yu&K;&WCX7Q@0
zr$OO5y&7A7f$HS$$9(F_^?YRSmxI=|vY;Fv!GCk-4*VQDKgT`=)73ihca4>j%*y*6
zV}`T@_zS$wWeh(Fe8-kE3#Q`valsP#ztGO_xWgcorPc`NY|)W)e=QyPZz?ibqITD;
zBPl|gT%XQiyN{W@&1tN36l;&7#`r|tM}jM0sDS&Mpo2Aim6<+C!}_5Fj?M=|>fHM^
z)BAO8>cPhOP^-+@nNmE4;2>VEX|}Q9sEo%ksxqf=R=G4?zypE>Vm>E+yC}cp+<t~t
z%m%PlrKBqc(q>wVbdOZhZTB=mPIcAX%SlSY%L|q6r~VYiY)^gBCmm!CpmArouy5?W
z1J~5z{S@=`Yil$GDFO@H-e`RpI#&M@GrVMma#NfQLp~oQ_=yDBGG+qy#Yn>aYrU^A
zukMep^dFr$-f>Q1b;}_F+uf0&e@KVM+LUKUJ;(j^EZ&^-L%p&7P-V{Qh4|--QZ7z{
zb-qU=_aH5sJ_c;nJ`;V94{0~8UZHn*8ic)h>JOB;M5;2tk-D!VTgwsq)@&DLKuq^|
zn_?sYDmlmkkE;Z@M=Gsmzp;@KIP82tyLY-AHYZrFn{DHLsFptP;%cUJj`d88wL#<7
z;1j`3@;(Qn3Wv4*ou;fa+7<qr0_zU8N(;`d$d7m_qnO&jzobgVS}lg&TzQY4+Xecc
z8cW_frVys+sj2V@h1<M}v>Uy(`Z$8THwMFNxGde!Ze|BFy<_BrzG}AjOY+#shRn5`
z`Q)-hvmWo2fQed^Pd)b!yd0iNuEltS_gefJY29DGP{va=t&NG;8{1E~y%5UzR3Z_r
zPHqR?u?n7ko<pr}5Kr!eLIfa%-G+Dp;-u&#^@!{#KykIN0eYxw{9pc{Fqo^TtRSNs
zfh0Ik0Iemb>UQOV^eziH?SR0B3=QIv<&i+I!*Yr+p%AP1dni<K2sr8**R#W~2S+IW
zKg_*XP?LWEt{DiuiUtLw3IY*9O3=`QNbjKsM4CWAP&$Mn2%^T&K`>GxNhl&9N^cgV
z8%ltHG!c+0Qlz*4`P`jzE_U}~FV5`jMJ^a;Li~~#^ZwrFc_AQ=U1GkH0XlpgK{uOG
zBNt$Zc$E1NAmg^YcL|K0Fw0y4U|lbl8sAAv4F=3te54gsB<>sn=(LeEl#EQp2n<&J
z)XY?^j*QoZv5*Wr6D!acN-m6J(@-$tg0`5-X`NVeIB!>H7R6rJARGo0V$=tsfw?_P
z<MDU{cWwAG-jWvgi9}K05<$V24FD2OpP&4B)qqR&6y}-AJ^*ODXt=1>Z4Mxjv*6Md
z!h{fE9I9;0FiXHvrv_|Nr;3<R^EpL1LWm+LAk_4ddQD)C!!x6FfMAH3t^gCTIF0Al
z%={CNMer?Ro!sJZVMKT*3Z#J5$>-$nkX}v!r1GPXT<&r;{y8{FNSY2bS1t;u|M_9=
z1^0bGW|IQusDM?&VL&0;T^vVE^-|d;GsQxJ7g9Y67WJ)0$wHj;9G0E0`%y~c$@&2X
z?r}XwgZWBWX8P3pOc04`Ik2~k;0Kl@o?4)l`nQR2h<ma${dE%AAKE<E0uqzV*qqJG
z#TzjRe<y5BXSOs_&jumrI=q=7R5)31k0f>gDEkXgbnWtxXsCvoW&W4s;{l+%h)e@)
zVneyX1Y}yf7<f7kw5<QHn>Qfe&al`bD+x?7F+~))FPj6Y9t<=%I{qSauLw9q1UUhi
z>H24)C~}*?&{@t5E|&|`hX4dz1|lbqQ%-e&8ImUrT0@ZgfajE96Tx`xr#?n!r-)7;
z0|&hSB>8@ra2`~Z$B3Ce=d1dFDm7Vp9T<sB0CpNz^-(6#-XL*^3t(n|vh)F)1OXjT
z&TCNv0TVFL%kH9+helyq+J+g)%@!c(e)^2^YkUN7J&AwCyH80ke7%6I0PGQMcz2>$
zNFW3ONah4sD3Xc+fQSwje@M;Gj88FQV(<_E^j@8U7^FJ{#HCMt<lV;z6&(_A^TJxT
z3#OPLfwtoLZ1tm|Ami!SbHx}7IPouW6F@E*`6*Js)7~|kiD!1M4p}wPHqaFm;L^<B
zPGnYDHGC8ac;dMi5%Gco@<9j{LheEiQzSAbxPB5r6hzV~0p>U|2!L!CAzswj3+i5@
zRm75Y?e0Zj+g581(Z&h<tGBpG5=1VF%$ab%Us|0`&sN^*ERpho69)9qPj5=MLuUdE
zyaAU!URpAa6|aT_Vqipq2+Ak`k_ieULfD{BjZjR|?Q|}MxBy)`mvvpp>mY-xqGV8p
z8SAP!7;u>37;GRb(j*^%)&xNk0*rM*x7rx20+3l0$#D-j2OA)@*MojS4zP)<R~cP^
ztU!5PfC!P#5+G0ie{!Rv>=&E)-J4i;yP5XEKZ<Ll&i(HB0(V{#nCEMg?OPXcF2^BY
zmE#wG>+LXhC7DF?f4_Tn`P|7HgK?pTU-jjB{79CrZRPg;A38%?RZ@)}XWn!F^dp=?
zSo7&-p}aeWx=m^44L+U7n16|ZjW#Prl{qBTE}l9Vgo_w`85WcsN>JfnHK}py?{2?K
zapU@7zd2o3_D$k1<^9@36=%TSXtr!%ov{D%@VruxB_-;TT7=}A7HUs}kdGjVDQgis
z*IadeJn<!e>b1kMPrMm^KU;K=HIBVDxG$4)VKO$CRrtrl7hcyiH@x#aQvOy|_Q3iE
z@7vp7uP;y|p`j)a_;yLcdRp>!dapzRzl4`&ISsECTr_arttq(cis5eQ<KMXN2Mw$1
z*4g<Zfj!V-?q50!iaVC0TLgA|RO;pNiwUyle`gAw!ydYSin%selXqQ>U3Q=s@EzBG
zZjYi>CDp&U@a)r48-E4y=e*^|=WdB;f1VtF{l~in9eAkH^2w*jXml9(UwB1(vCe@|
z{`LX);0}M8FlzBnO3zE($lfO7V4J3NWkYz|wsPNo@~Dw1*X#mQviQ5>-Sujbo<{VV
zO9PIyLBd8VE;J;W|2$1Ad2vu7YAd3s_a6v)yiD+l_nsD2z3}W~wE#o@NQ|D@QM7LG
z^wrJ${B^H4`=PeA%~OeN3QZ>~OEq^A4$WTOhs}lt;F8w%d^>7b&dMB!*WI5i{gN^L
zp_y3vN<+tdxY=*+gq0>$V{kEPKDCo~u~lrNh)np_T{5Gx_+Vb(<4o|TOB4PYm+7T9
z$KNjg@vIE*6XB)&%8QwdEq;QMSihJaF-Po}=h<%e-pAbX!}Lwhxg_e;ysR%NNSwD4
zfJF(qBy01gmoU?uFH(coWc0CW@HuPot8EQCl_L9f0rx_x4IB(7s^i8+d5gn`zM@Ru
z)jhEYeR5P0gzahhSU+6hyb$3)@^4TcSdn}w>tubW+ECE4R%pUo=)>*k(YB=fCUtcm
z_0P%exV>rJ`4WH0brAbLw^S%8a`DSY-tJkobM7V8rdL5AZmV@Oyt%DqQ_0eez0<Sy
zvx(;(3~~^YF`<>0%%5mpezDr+cupW=FUN(uqcsae7dL=hc!qK;Y%sg{Nt4N(eT-l3
zddqxn6ZZA2hNjTNPTNMmFZb(`#l^4fj}n|NJmyF%_5bDjCCX~n_~?$n_1B&Y{Nidi
zKW@^EVX3N;hdknA<?7JaW1O_{C?2@e1#1v~YaOz$y4S9GB|Nx(&fv9$uq~j>R#(~-
zp7^>H+&kiH+)d|H`m^;3ttn5$DBh@M%avh%zG}sL-@Rmn)F=K0h$@@4!i084+MFgU
z5&AtcRM5CQ99+Y<@Zy92LbrW!iIZ$i0=3q_S_%|W$<nwXTs7<1+q=o}VzX<$g9UIR
zx5l}=mH#AC4g$$DF(T8Az8c-o)T9NgRF@UkHrR3$^NaJBz$#f+Rgc~cT^-kTeme!k
zrdFTv!c`@g*VYQVui#v^wJcGgs<)G0a%bH|Ls&<7N+3U^-wtjrl>VHu)6dm^=p`YM
zt|Dk_Rl(g7Ewp)eu9eE~;(eq2+e<C@Y-?!l*>5usln#)kT-Gn4lW)uh%w26W^hYj#
zxR5qxLi?sDA-HM7=WzyOOUs^}x?}jk7w%<OE0ZE;nHznD=QVEd-pr|9VJZ0)C2bzw
zdv?<LYG4rJF*AS%TEv^1w-~Uq^gg<B9V84@^NcfKJcb5FqY?1A9g?`zbSi7^&O&^@
znRJKh5KYoOR=WP_H;)Qk%`=<zFQgP21rvpmyisVXS_;h1+-K02WyU-!9=bODdiWis
zT%@z{(Eb&4=Zv^a?5_y=+Uj*MWp>r(WBrIG^?C1`T2wt}SwW^-#aMW}<Hq5;s!R!~
zcf94QlYK*q0kxfW0VHm&yhf>~DCVUNg9(S2GN;9f3GET$uqV&Tx$9v}YITt`F5;Uh
zpV2$s%^6YO<nQoNtXVF6MA2-JRMFSb4%G0BuZJ-;66R>K?1z+{mlle?ycL$GzkRq%
zc<l+|HMe?Z7MX=d5`HK(pe5|R_zogUsFFc#ZdtOETY=D@7YlQ(A$na)n0cg2e0@l<
zLI5rA%;W=IMeT*GOtyRXer{oGUepPpNuYq-0fv-No(IhWge~=y(IrN6xdCXEqL)OF
zbt-fAQ96}tWCDFEJXCoskfA(9$koqCY1U}1>1=-f>$p6B?2Y}n8MSu>GGkNpVn%XO
zVf;J)9Aw4}S`RL!&jk7K-^`uaCh(ZqFvh|cDjjRG8vg^4v_EQ?qq0Sz6BEWEqV}V>
zxqxLnHN_yAUchVe$CQwa+4$l3(n09bnF@G2%Gl;PH}uDv#lok)#P9A_Vz--ZRK9zK
znnbn4t=ZME3cY{!CEnUS>2GfEIx>eJi9p^i%C+;c&NefdSC|PVvAwP5B_!&}kAy0M
z)@>eK;8nP5|9RbnrGm+auM1pm@}ni`4WVmhAoXlh?q>T9^`M)EHBWl+hK@mAytaH`
zyu{7wPYV5H1BuJ>=r|s$n`!Gti`cs$6?0`*(q+)HP2A_=KM;FHaq)89AC<gN(d1!D
zHHVRonJ8w+o6hP*Dc_8hyC7cgGobr;N$vxNb|4@E8#BtHFjJZ$dQNbc%(IX;oedn2
zGOdAEb;SVn%%|I*O{Ftn1MqpPS}!~TuE~r-jIAgcmF|!(r9PHxdwmSuEUQ{IVgDQG
z6Z}wne}JKBbF{KTS_+0GHwKw&cS^XWCa(3Xp^pOL#lQQf0t$@M)zIXlw1!TXqS&gu
zAi=mgcbQe24SoOU)naqb)v)K!Z_6!cuZSxb`);&#+z40`utY@GP68*o=of@Oq4%9|
zi)cor`!$&If=_qOPG;S>aOMlQQ@(G^=x*4(_^`JeVQd8_n6j*%aC<%tU1N^-+N#|g
z6v*?z$I&8Q8|T{O6>HkR{^gknWnOlq{a{t+zo&iL_m}1LZ`En_&hPX3-|&yuXoRX)
z&+vi7dA1g4@Y8kV((fVX`5Qp^f5%~bU#so9{gGyp56k*59PO<w?fUA|dp}Ju(#2(x
zT?eksVzZ{62wEd#v-qxuXiR;%@3nYMxkhkw^Yyt?{EdCj)~q87XI|@QM&*i}WJPEo
z{lKQig&F@kw+@|(^0FJU^YQ<IXyx1cGDUsUp5<?yowb?*PJ9Q)z5KVoe2X0UK0eB=
z^rC9tW`?4k=*X?|<apa{<fHHFB>~Lrs8Ov6Mzl;UNbd*AsU%F&;dRQ>pGh&#4Mxo{
zg3(v5x(s4n;61-1-1n)05fT8*HD~taVzPHT6b|^X2?U0AHAo@!;=ZXtZF+uvJLo2(
z9H@-GS0ticEO}h(qw3~5;!MD*o~}gWiwu9I%inZXMzTZZ3OK)eMgIn>SZr5i@KZo|
z*ReLp88G_rLbI}OYQ_`sqr!&O{^Z>&e2yric?>qxHE2Y)niSj)M_t$SqHmV_JC|H8
zr&|;2w0+f=ZGE;9`{y$&?7<1+dGPXiEK7&;U6CZaY$Vms`lUY+6w+(go9!&Kd3pVC
z4RyEQ1OB%Aa#O)c^xD^#Dk_*z@bYS<NVsQLmhadNE`oeT%-)>&6TdnZV*~xW&NYA6
zzmJyoMw_8~?>!$x!0hcb9<9$cx;`#XNLt2!Zr&fPG*h_mownE{I10LS3_Z1jP{Ek>
zSrP0y-Bgq~=XV)_XkS#bRR4$^SG3>|17eRf_Ix;Qr|?Ua6S4ke{=L>Pl|6VOi7>pT
z&ZZIoY*Rk;Z!I@*PiM6J61Q*l^_Fn1jpy({bk}JX>+r(w^Rcj7&Ml?0@|+$T+v~^S
zht|#>N!?*8dj!t+gC*U7NbAq{2RdHM_WPcKfRM}b!lD7^^<g6OFDJkOuk&3?l~naN
z9-Gkv#=97Vuui0&Cq}-?R+0Ph7=Gyp`6mhU4noH&7qgxGP{3TeR)u2VFA83dw`|!q
zP9mfkFm9P)kWbCjtYu5xGcEUrO-s6_<Cjg?^DUV10ZE7z8QDs}1OMiF-k56+P#mk=
zf*!3}zRIy_-9KdOncwavv-}RXE%yAfG~hcHHzVNsv2)6Df5g>SMx^NgA6}KZ^XZLs
z(c#%&Jd|kYa-8MGQv1LiSJ*73s?^TZO!YLRu+21m<!ir^!s%7&S%Y;{VLRY|R~#p-
z0qv?rAj>%;o{xQa<-sF8A(?wOiFI@4Jlw7*edft*r*=mbZVO$5T80h7a#y}%^pT#7
z_ss0mknfp|4=a@wzl+X^knc>y>Fc20s$0H#+w*8pVGn(JGj31UVF{{gi_Nsu987(R
zSTo~^Lwfz2+bi9=1b~i2kN^Pp&6Z`c=V)(39!Pg+ENMvpVt@7n($YYz06Ix%HsEta
zHI)1r7F;Bzv8l^XR3A`~hJdjaF*yXe%M3BWJjvU_nV%R%S1EGRK>o5@h(pG88Zq!u
z#EN68qcIi=_1g;ojCVMg?0qH=pv6`!hiEw*o&MVZ>8StnpU=Dwma~A%4F$}L*Y0CX
zuy9zO^qGcTGP8)0H;@E?%psP?rTXG{7bzbF?N7_PAilyBBQ<~r1O7iVSI*Z(00ooQ
zSB+CJ3d;s=VPwIh!A=MlP()&rUjFAC+U`d|%>kj4E?`4nZwE=0ORpNz9x0+@!w4JF
zgk*0J`BG|-86*};0zRJmpxiLfKsd1yV@1PR&|B(BA1?uuZu#{jEi!}!Wl6aKU&C5>
z^PN_Qk*0vY6re;8&~{cbk_Hx8zPW6Z=E3Ib73kana1}NAB}up_yO@6=l}*pPL&-=(
z+D%u1bKP7BUX&j#O`poO3OK8H@Cw}o*Xdj(Q}v<8AZc}KJRTt4(4f2}p>P7#0{l1s
zn3@t`Dma^~Isonzhdf}ugylvduA$(o`UkVX_?;7S2lyUD1?fZ10dbHy4Hsafpsi8A
zOQ3&MfI+cz(qhl4yTuzmiU1T=s|aSH561e=`pX8~@KbBh?+wgfy`XjmfDFV0Az1U7
z&~wZ+@*KGW4+ID3H?)MS^Sq@b@RpyJ4d`PdARde3$=e({`^XHeD$)xeGNp2@0)wyt
z!ozKN2L8_b9r43K+N%b@^-G`ztr|rLT17)+&qg8_v1*<;AOuU-1!WilfH4b!kpMiH
zPV<fotvrzMHb5EzpSRp7^zyQ?;dHD(IJsYtx&w%5fn=wTk$-U%%i51(mKdNLPr)dS
z($bPZ{6)YhB@P+fSpyRC29#7oSf>GS$`mZAU!8hRznq@C6AJ|t@60HT((vPDwE=k{
z1!J6m{6hhzFaeOs5s)h`N%tuMSL2r<9;NvN%LI;_#sN<{kSc@8%rx8~(u)?yju77V
zTGf*V%~*H?<t4XRdN@gZt5^^jC`~7?fo56A1>#?~*fYY?T6thtGjPZ5<G4k@>2@>C
zgi&)iAq!X-0Mbu9f?0|WsCtQ7sLsLu03(ETWXW*IZ1ghs9TW%wr!XvJ#{zf6l?!x^
zIC7D58)U&CTHI4bX^Kc6ki4-t2T=sUhD};V&dtD}rBr_A!z)0uO8zuBbB-cO$G5z0
z!oZYW2cwJE2431apJoQ&g#f3xziOZtQ(f(jb>pzi<v@l}pz1&)OcgMFSz;9q2I!M9
zNMUdCzv~xM9iO;tbU}7HR^`x2K(iNuq{FLJzR&=YGvFGI=dc^r;ZdCQ=g49Z5(dv~
z1TtR*Ud_@3AX`fI?oc7Z2@IE#hl}w_2s+41vV?^$JpiWG6CP9(EacfK>TJ5p<|H%(
zh<Yx4`9J;p{~Y}PAKaj<0Q(8-KLRfMM*zJF2f)w->N)IH8LX)^>|1(7F&ksRFcOSM
zvHh=378C$f>AZ{n93uY^?9O9V2NC~I51BzjH)6D1tEM6!C)r*X{^_W5x`oTZ{TX}L
zPwNoL=8Rdh=Elq_dxx`K#S6eeSi*<SicvXJYeP0+nZfNJj}JTEhh+$!`41GH{PFSK
z{gj_Ae_}VwD2uS9TKV|&n5+VE$<DJ|G6pKW!dJp)zx>K5_SsEgKNcAxQIUS0*L_Qw
z!r>G4&T<>dbx)+|C!21~iHE^UG6n3wz5YaY{>}gg4o#n>ox5Yra`FKb7lRx(X5kv^
zPqDZ?vUdEMac=nyiF2r@8KQQ+8%3-7@$GuDjy^BpSX*_llhNHSUQhVDpgn_mp7EkN
z{h=6{{Se>E<(V;~)Gnr9VljK<@E5O1E6#$$$F++3>deo?yN+dOF&z8&J$owoL(415
z(e?9+`tZZOO2ek1d-n&(BX5!MCp%0fWr9+1$9Bw5tLLjD4`y1ELf?M~jBXEu7Qg4l
z@BTWibdH!^r$gIb?=M*nipDO8f27;cIL*4*KYQU>up>kuKS%Dhg@S56aS}Mj>$kpc
z60<h-<%I9yWBpy$s+6^h1;=5>S3W+e8B^CLX-Bh+c{o*jY!$coDE>hzYK!v=m4Mq@
zrSf!)8j**Y)Gz;mzL=?vrrdUVksY|9<XpUIXEJ>C&w1ll{na<W9z+~{ssF*ekKqj5
zU6x8eFaGE2B2yuz=}hl5c=K0hg6*xyko>6$iIiroj_N3{O|fHBZ@<D?c|Cnw5#=Dw
z%hcrOr57!7a1WS*>^-Uu5?KyuW`WMjIo*7KuO{-tBsIVJ)F#rHIya&|Mxkn7IT?t=
zCRF@ZeDrqj9O?Y#L57wt#SnHO^lDic_X`TOIC0jG+a_JM>RXq7A6zT0Xaz&2RVh~Y
zfXwUF=BDd@8FI~^sUAJo=Eud6Ua!kM-PFs?7~b^dgMPUqqgsq7Pd;&Al<{oyS$*{&
zhO~>)ZB><e1IG_%Z`;DRVLawnpVv4g=Py(f-5fQHKi@gC7KQkDw-tInrWqnd*P1m2
zPD>51WP12mVC3CV#IU%->3<-8!4q_F<<s%?$A9|rN>XY&^1`m$$0!q%b_BBOG!~l6
zX6+LED?C&mXG#yoH6oZ*DxT==zasdwyGP(@R>w*l+<lF|(l6$`$EEAF)m=(AQ!A%8
zQ&hk4v-0ul;T`^K{_llZncA5d1Dx0R*a%z?6!2|{vWlG+(EDe#)oKkalRE0GH*bxk
z8$1xvl~PC2Jpc7I86#h!ScGk!k;av3Fa_iQf#P;q5wrWU#DZ^qG+Ps1<!LoWhWtm(
zGP7T8nQa}!I&<_XaXSmuMH!~mt~NDQZTmmIdO6cP8j^axv|VJr_&DI}e15pHM%UNJ
zIv$u2lf9DM$(&nZFNzAo>HNxi-Qn~k#b_p(_xtv{ogETWS541};v({ksYMEYV}4^Z
z25Pmb)`!B?2@hnx$0&NMMw4tuY4ZB~zZ~6;?2?6xakd#xq;J~sBlQ$JVe#X+BJLa<
zb*`%p)t2(NCfYBu^fB`;|KM)DAOb-ro*qMz_Hn_T>a=9yhU%frOVspTN1KBuS_<VF
zug-a;qfo}tCE93K#9z$;N3!4k^R^2p&gwuXM~18W(@$_Ve!e;l10hm1_?wbXI4Yhn
zMnkh>M2BnGVb!foN^Sg%VH|jWRvCrso+aJwCOo6H8q3Q}zoy@^6hHm`%6n0nBFh*U
z>04}7lQL)ZGEDHCMRW%GSLaU?x6Nb`<-FAAdg`3L6kYL5+#lsL4LNN0bB&`mm6B)J
zu7g#+hY1yL6-(g6$1DW*%5d*YMGeY#Ge(uqec8Ou7P4Ko096!aQVp_o$zV+<Aaz-7
zdt<DZ9d24*SGb&ScVI^s{n)14YZaTPhvsnSFN*c)>~|X8Oh`%fDUGgf^%b1kpjbTn
zm3vQAkPf8~e#hy>SLgDSLp8bI85HNC7@^g}_D4U)qw}qgCV1cbB>j0kdt1!W6d$pc
zanb08ay4`(6~}K=ccxQ9Fu;T%c}KECE3%ZdWj~zxbkF0&TS{3KF}0k+F1i$e;OIby
zxx>B$7#M0mIUc_1Cd=7}beD_-VumLWYZOssb#>B|$ZmbbvrYs?*f)3RKCR=@w>Ni=
zX9)#%&3P}I+xVnnHDsjDk6pZAdZtTJ+VwO4n}J>~8r`Tk&Q@H_=xakaAvdguK;QSh
z{^4GgL9#x${3a#irlyE8IW}MaAY#?zuh~EgVyCDV8aA5>e26g=`c-A^lxRzpi>bgV
zYH)hI4t;=unXZ(NSr$T_O-Bzw@}!7yO5qg@r}M^RK`P6}2$*mt$crAg*aE|wCB{Oi
zkyNUMqCqli5zh<QekUx!1rI`06NHCjkE}XP21MBcj17bywrZ)u!IxX_pmaF!PF@g#
zKO8~Xwz9ideH(S~sd}j5^8H<l0mXvsGz7LuM&yaGY_rYQ_Oml0>zl``q<8ybv&IEG
zTiT%hAc|<!uQDKI`GuQ#cWBpa9|f+~<9zr=DgP&v%$s-nhBHTk=WCU29Nj|$g_C_;
z-K5@qm!eAT*FUB?Yilnk*1h*^t*YLrOT5Q&{qXiX*B>qvAHCWKDN~MmA9aaYk5jU)
zwhHXO-}9$jLa_V?dXf83b@{g@b9nksh?7P$dv0zn{!nU-A$kP71m*Y>jXsiB5AB^1
zD5Xrld4NeUd5BuN+RD1`HWsgDsv`8<{lJdEFNin&7CE%*%@x!Cb2Q<1zz36OUF%Ym
z<JCY;8KW8}9d~-VrAGz0J(4)&z``jPW*}chIAr7O7Zix+gXJ-*F?O4_VKPjW6iPZ9
zAOUzFfS4+68lwtE4n6of1J;c#FZE$9Mk#+Sp0`Ywxo~qc??prKZa4eawp7O!A7547
zKc#MijyWSAmkG1)gSqMZ?}qG_bq~X5B)qU;;No#^OlaSgyVYYLIS}N=cjD2I^dbJH
z%p4y2VMWy%tms4#UUSG6zP|A*O>EtDQq3R0zN|TRDR8}iDMfa{h2tCO`m0S{r%M!<
z>8Ox*2;G{u=_0OX-{dfa+RR;%Jhk6X_<@+>3ZV5alXkuDUN=zVI(3ZPwCNV}F!;O;
zXuY@Nbpcwwd-U&{trb<>cap{>og-zxdMhFOiAT>u96-CXA3X4fKR+nXQy+dR9rGH#
z;SArHdJ#6=mUcSuR^}tl`C^Tyb;dWDlab22q<YyGlRvER59(~R9>iEX(5>Al5c-{c
zX`H6F-PP`TJL<tmF(5hj6(yb!o$pnJexlD6@Ba^k%1f;XvAY9lwhZNy=su5ev6UUg
zs_RF71AwtTwg*>Ivdp$V@e^1s<F|f((3sy62`d>N6Sl89#J@N3QE`DLh1_fA*VFd_
zJ@ZQq);_R)Bz&Z+P{Z!pGe0c*hHeiTEBo{zTUZvp&(F+uhLJw!+MgT#cH`0B;5$9+
zNt4m&Bng>45~}OP%IpmIYQmvAHU-c-`_}wwlne7L^fMCcqx#+emOgqGV&$%ve2Pjt
z4Pp1W!MPV+()=1Xgk=;=1E`b$wdmz%MM9Ke;88_D^9_ost134+2Eb9xC+MgT`I$pu
zd_^ZU0bl-_Ts0Ecs4wQ*{84W0+u4b@q7*#8^(EDQfGsu%NA*uK3*(@<W~JB?xsI=7
zm{H;i{oS15K;0zG9IR~VSM2|+-Ka76Ta8if5A7fcmC6FGYmknXoXwBeca07!6lBp$
zfxqd%wp<$pP>Ayvg}LrgU>|rUX`enkd-(X_70$-wSev(38=p_y>S6(2MADCL#w=5O
zpB}kyk+%-Y-Q)l0RNR#<tK;XDuR8rJFvx@3CbK7JRX<4mty9s%?v@u(YD-mKX|`#`
zPyzTXTrNTNZAI;pRzi%;l@1^mQ@3jOF1_URU4YPO6grK@U{N)uJm0=f7%@qcyZT$~
zq$|Lcu+V=@mhPh&G+K2)`kj;2bnF8(G{{;M*ki}j9a@O#-hjir1d(Ay^c%V&&xplF
ztcMo#LHfnzkbe**@`&oSYyhr<G-yyRU&DaZEc+rL?$a3`C3Bd#Q3`3f$YdrU!eEKq
zBUaXGK($GIK?r8&VIJe$9nu;iL8~tl1aN5AjNIvVAnpYy&CJ4BuI=iVb1=_XE}&Wo
zRe>St)CK{<1^aK4O$|86X9Fq48RDh;TUZzuvLOR8)%8Vm#wk6ihl9%qb{t;8fKv|m
z6=vH4CX4(8K<os(qE(T?)eY@{zz3Fx_69NImGBCP6)1=Y&oVb1>n+GJAYYhG0EX$c
zsoDHO-h!b-U{+6@pG4MBDFpU+>9k?-<@6WmljpEX#(+nZh&9<<LI+VmV9AVCv!VgI
zlpd^fCoPT%%2FIg`m}1`<_>$Z+73qsi~^=;Q|Sd<aJwiVD+<c@W?nXoH%4$FF;*Ye
zO#lfL@IWPmbB7FyLqy79bCR(fA;n(!`wu%ZLxi_Eoc4&N-9-4BzR^t%5LBOGFn61%
zIR*idHVrVFX6tK)xj=Tn2@fz`L1Td8%<!Xl<K^j8mT)3jE;^jF47e(5q58}KjNSkN
z9d8<O_ZlbyVj{Z8WM)|5s~_cz?-3;MvpK9bh2MFb2yXR8fCQ0T=%5S(#{~kIuMf=}
z#fCH|>o=_;xPL2XFQncOTGsA#t_EELLLZ8t7c5~>GLF5QDHX5hx<90Iz8x%*AA}Ij
zjNOV9pzGcxFuP?nhL8j?)O0gA0VE73;1No+WZ+%Jw~lhIp4=tPfs1Le0w?Iq@_rrs
zeT>_Mx)vA~#mzsP!vf_(8vwvr3*cx1;wGp*(1l=%hJp?il@N>Xh=7EPG`OmLjE2TG
zEMz2C2NQr;V@)s8!W<@iK=@Z%!B`^J5N(21W-5eq`0~2;I$$;$n@w&3UWo}(AOKm5
zhCWmUfk^Fg582Fr{^Pv(h?Qi9Abn~q7^tnxX0(9dAtYFIkUmi0_y{|P+au&6xvD`8
zQZO$7Kr>maGhz~oE@2)|=}107KLvu31*{w>$cXtq4NFH61tV6C^L544E$Bw6@$Hg<
zK#2vxnvtKG7i4xAvQw1O5lfe!w;X`gdW4HN0d1i{JAg|G!45RPVlpkbI6)#=%;GIl
zK1z6yrGcSjTsMW`;bAGLd9fIlo1qU2o{fv^^H#?@6D6@sLK@3zF|Zczbwn)2azDU$
zqD4r<n~qx>t65)|dc?*c2l%0=UU*J5oO4kIa9Vn59T0B-O7{LNWGY4$@&@s*aG_15
zwumJ#mYdLkRRcwHlqG@%E}5B(W?je(YX|WO;!V!!W1PGIc{*}?4r_via4c>V!J=R4
zLLqLg);n)+@RK^3avAvuwil;UI&yUZ%YY24K1xAPV~O`MvDLd1_;U#3;}xg^R+>WR
zLaYISjRD8F3)O?VfU~N9D<zr9f!BDfqI)TwS63Aa75Kkx>HS}~_5OGNtXw+Gg9oLA
za!SK^@Fqdp;vd!xyooh*4`Aa~;~9`{ZcKoBXwg3k^e+&cXO|Mfgp6~CA{QZSI`zLd
z4NPyqEH0dnM-cf53@6Z_<0aBM;t3X|ZLF>Rk9z}(Hvf3N|9PY1*Wr+7zzCED6xmOK
zq&_4fw3;844<a~|&P%XhdG&pI>xTr6Y!YV|q;VEOA}T87KGJ9MRD&yYI`NkmKA`XO
z;vz}cYEt&}%R?a+=hexr5J!Dt-GszhGf4Vu^9}nUD(%qQ^8K4mhMmfa8g1xMk-fX3
zQP0hiol3rf8Cqp@>#T9TduaC<lc_b*;6?Z=NhsN1{kGlH=F5>kj}o!J{asimFO*b-
zx33vKeWPhBNXyj0EN)jc{d|%z@m1jW`zeQm+RH}%{&9&i)SCN`YORzEizXvD>`ol`
z`AY)o`3vY@9Gu<odpdq!^gmF9qexH72ldh1DCL35V;R}$>}dZU{yGxzPaPOHN=z;)
z^>$di!_#~%=ppmOTmHR*7uHjsMHUZ6FZ?t=FPZ;Dds9%Y{NlWWU|@dd#B|HloWmI+
zuJpGrMY-~^#Y&i6w&%};_ewzflI)#FD^yM4Tt3uj$vLHb{9Cy4`Y!YRU#P~~Vy>*>
z-T?6uX;Q2?YPR|EjE3M+iD#m9{hhR~)JJ?)>W)7XYK9!f9sXRhf&aa%B`cZL?MLiA
zzCC*}DJJa2&r{1s;{8(<$i9Q>6Qhe=+1L2{g;xCZZ2tC$%Iv(Q@!j{C&um#u3#w?{
z6n^%$raJpYpg!DkfoFiGSKFxhHCiT7O4k1C+KLt%R{y}<)wDO~rW(MNqLQWt{Pjc+
zvF-}$L&ThGKTIkEZrbv-=gr^Gs}r%JksX|`z2xFF3vTL{aFWezwOkBsv+-~#=HoT{
zeNpwf=|f|`tDl349+IzYUZRUP-<WRB7Z}a3vcFYzZ@jH>^pZ#}82i9Wh@02vo-Kg#
z+&N#qqjB!{A*SoSL6bx4pC6dTDE4SKxuVwLYcG5gFQQbq!jFCX63TzH*gsM;?EYJ{
zHQ&MPGc=(Pm^b=N`L>K*Q|OSJLDYNeRE35XUnP^x<Qn3;^EbAxl>P^@rKCA!_Z0h_
zi<`856I$A>o?M;h75O?apG-RTXmnh<WAi@Q;>k;K!8qrJ*ZY4Fqi$A=EBa!qkYZoY
z=DMHis&}4V<;>bmPOnzy?~&8$Xo}YVDfcXp{X6VMdgzrv8OPGg-{4dCF!YU$iM9-w
zcr&JEpLOlc;>Qx4#kVJKPe@JKTu#)QDlKo741aEZ5OP~6hig{x$qs4xj;CEs?c%!_
zh-Wj68;4gB^Y`<=bf2I_t8v*U{(RYa9G!JvPsfm&zGPSPY|KnTq2O|+mS5YYX7ky^
zvZ%K-yT)M0lu5ii#?G%a%4*<h;S^*cblcL|anAf%{8xG9>hn)aFiJRlNo46?elsI;
z9m?GhG+(8T=@BF4tDe2fbi7tD)r4zO4*vU!n(=DWjr$)o=~l|A?__xmyOvWdZ!;%0
z-?{e0EgWb(1ze1#$@I_J2dSx7%FG35JiaC9PAyftXH$U@PO112{$gtlIj;69SoEo+
ze?rR73jMDER|Q_(l+~n2ANBY=PTHZp#MId;<&amRFRonaC@XXF8KsXbN%QRB&x~Ga
zuwF=RN+)`~#xu!S-E2xR9(}uBlwizZdh}JJ-RsX3HMbbfT<($g^4^ht+tzm{Z`#n<
z8x{#foA+!@Kzr2kM%}DOjBv`4xV_hrm{wyp|HP<DWz;)b@EVd%IqUa1J-xtWPPD|{
zt@iSl&)ytsY@Akw$&QSaqRE1_D}B^sx}Q<z-iID08?{s4n$uQq4~XI(vFyH8P-mS@
zxh$b`HSN3ybH1uTKp=YZvPZ<?^V74-*AJsc8-r?EKiR(qTJxWM&Y~|!#D4W`Z5h5Q
zHvIN(P3~O@WHIlov-rManZ1*Gqfhxavv3O)Fbu!w>`~+1E9V}*rA@IqdpDXhbhH(;
zsUEtf+>v|B{hhe@PKDy^IdEo3TYS%<t=ubwX3t=y4sU&ugZZR}57l#0SR+~GZ5L55
z)Bk9?CPvLuW~)Jb08d#`xQmBgh_!iw(GD(Ur;mG8r3`uZ2$;)#x$D<Eyf|Joqx_P@
z&yyuQ!ckQ*xd=&rn=0rrOH8Yi(?@x`WF)|0zp`#8t72@FGLZUvK{l?>l{kht#+>{}
zqDoe%QVuG$S+{g4{rpg6ah=wb-GTW}%T-~~Vdd4V{8O7S%eZQH<rkAwI#f{4Bx$Q`
zGEcJ2HOa)|^Qxsj*RQ^ZY!4nkMs%MJlxTV`QWNX#n9-9m12MeID4QWC!?HHW(?xH^
zYka(SW~CnAyBeY$P?(txWj?Hr<dU&5t^do@mr=F&7HmQAEJ|j7X8Fx_3$Bw0998w$
zt#gPNbx&OgctccYi%cqfp^&ZuGt-+4YS;b4;QC1jO@4pnwBYBOyG_ERy?r-~edN=p
zH$&ge(Nfs~tXPw+qKZ#9nIcai9fCZ_9EyAel;e3hT@bCvz+qI>Gb<GoT^h&ggycCK
z&glY9V2Z$W;8GRBI|*ba1V|oK-T89^bhTW_Y>c2A_j}__!T1b~QuuEuh;bJGX^+g^
zNuQR32l+q14B`Qv59=a@a>5L*nX#ucigEUng?uJMapgzt$EHSpMCTp#&w+)UMYy~5
z#f=fcl&_W#B<!EfbBw%V7{Vj34UTcenMv1WgfH?7X9<0IlN(1%cM0Yxe$oTIEjz`{
z|D#W4SpDKgiuQ2%1!R*U4jI*ZF4vFuC#^2!{-ugQ(i~H3#YWyn#+Thcxl!>cUuxdF
zo8)(XZsn!!9tc>gW$(Y#E-xX!uRU<Bd&c~prk;KEcMwIt<=Lur;RV(6%~F3-HM7o5
zc7<Q{<>kP(`THDmN<8mTKF|K*MwR9;7y6c&T1*IPZQ&7<w|Z?Rch>Eu0mWH;^9gL{
zK#1>Z8%#Cnz1~WU75@x&QcT|#yn-IHyJ(2l$B%36WV2`q6bDo+?SB7zUz`unJOUn?
z;2`7pWv7w;uh%$H;Kp60ZJ*Bi{kEU`IZx{h0*+<ySCuQCu0LuDwlX`@6=|1o``8nI
zXMf{eTGtB8+sJiX<9xtbd?*!jF2i^M{kwQ<Ped&4AcwnLEK&Jak>&m<CF~>Q*fA={
z);<uET$7>o{MaT`;d<#MVAn3d#$9~HtNz`Sle<0K`@EL*o04&!T9J`w#79<tJ(H{P
zeSMl%>I4T)bcUHm3f8;DPf*Y4wrhTT?dNcqzgRMs{AuA`Me7Z33y+)pt<Rk~u8NC%
zF4$`*MGjslq}#W2b=rAVnY{G<JPj$LgY9V8AF41Z?*1^b6y(GgyA6i?2a=-Ci(Qh7
zxx8PobZ$2jhhgig-_(D4Uuj__Fy-!S8A~jL!E#BOp7nA|{ePg_5o#x>LSNI)?7-;p
z@)t>F#&M>;uR=stnW?d&j<@d2Fp=yvn4sk)2+d_#OU)vJP{~7qtBh%U#Sz-iBtIk<
zD=dLZ=0E1^9gT??foNO9!KBNOlNm-g*wBs3V?%)k|4^HkGghbXto<JPUnsp#_V_(F
z1Y5s`2epRC$E<h>QErao-ooj8-lb5py$P%WyFdG{9k4wkXLZW`h$D{^b7xb#1@;zV
zFaAB3Zb<Z3>0H!qz*z~b>1!j-CP)!hjl`85Dp}R(ENh1Hx9K8#`)R3<g;rIH@2?~8
zd+xv(Dd!}NyI~#mPlMlFyq%(B?igXeQIPY-GGj^3!{NvUj77IbZJIbj9jWBo%1s45
z<(3&2)D4m*>M*#z#fGv~a%I$TcM(A=ECn;@O6m%6b6*GUwov6_VL|zQ@*}QK0P0k0
z19A}<aXCs|CFVP#U+tS+v3Zx79A3W3!b~V;un0f#wV#>Q`O25Jd@rEkgH_QBVm!sy
z4_w3Gj{olJ)_7+1y2WkH%cp02KGo_9F`6f<3YgEfdzZBHH>UH6S*Ri(gOGSv<roTk
zUc4~+2~%c1y12;u7niHRE38%gcpNtBbpXNYodV)mTG@~d(Bs5dBj@s=*tviMY6|ci
zLp%mRs>!-)LZu%c%SoRRR--P&(~_$>RJUP~gMjJ;m`T&)lrmD%jdjk<TMkN9p~oUb
z;X6ba00(>(1nR+hD!?>5oAYoc8?ea)@xtEZ2%3(k$VE$c6WjxU9)~0_j|rO7Lo0RG
zFyk4nIqd+Lj2={;u84jQAV2a-R1T?pqzyEesTi!K1k_(6XGl`#8YTo$a}vPQxj=!V
z6mw`nrz<4A<PG}t&(y;NUC2<!3<A~_Iz4IP1_7a`D`n)InX?dk4i@Q#!&m|q6A%}t
z^o)i6PsAqzSP)6&HnK7S^B2Yj<qvz|LDD1&KMDM#Mal>uAqd(7z(w>-F+;}+Gs<2T
zL4hp0$fv@Y1)aKLiI@SsNb1g^g$6SWl+(^P6N${|_c1xLPzYMriy-v_JN1xU%Y1!E
zo;UDUq-9iI0%SA^6j?Ds5TK9IQ!>m&0+<Le^`7T_#tUl(jAwxaoB`ztH;PGC3S)*g
zTt&oY;B~sm8W^fbM=V5y437>k3MLD(F{xXb>lm3qm2wB@cF3d|<Sqpy2ZwM~zuW`t
z-OQmRiV!CsKZ$-Jj+RkeMHB=c(kBb(`Mmr9z%m4Qe^V6<KNF~DT6961hB(ZC>VSei
zY*wWm#v$B1^z5K%031hwE}J-4|4EGH!dT`<kR(&n^_??8GvRy1Y|o`&zW{<cHbZ6k
zkji}z$)yX-oeJ0wdkjCx(B^}&JP(*Fhu?tUK(K)a7y*Q7!G9ndhWS9~o1h<fry)9n
zZW3s20wSCnOc8UXh^2G{EE~q*5v=R&YH=NaWqF4TY{$i}PG|7JIGj&D7)9LMG}S<V
z8u-Mrh)1hir2rwxLTX}0KC~zki=Jzdzpz8F)c)6}fYJD2bEfU`pa;<<!kHwbXDsAl
znqGJjpveY*{!G-|p4>F+(-jp6^USV+_Gv)t3E(O+ATCxHaAELF-6m{mFSdxD6OS_!
zv@%?!rfzui{oV@H7o-YsV^}HjTuSXyI@-hv^iyt>Q&c?#%uiZ1VC*mj#~ZHd50UA?
z+90fEX7I5zAAs8c>>bE62eiCREZ!fa#!ts`6&RVBGR2Kz5nwXJ6E_=6w~zG7r53mw
z(qieB%}%WcX}G@#=1bW%u%RZd>QBzwnZ@NoiPCgxJ46WA^l(gdtXVEKY&LWA6q1l@
z1v+l$Tb)i;IJAI6Vl9W#3}SYr*J$yhK+!}8v7=?gD0EUnr!VrP7^5&TU^!asqmTi#
zb3j4H6Vy~LG`G`$g15L9N_9gTJRJ*M@YU^Il4f;$aV?;6r!J;ZUl}9V`+dyKyhR@K
zFOosBLTKRa&ShRhe*u#7dEt@w>NKzfatLV5Q)8tmplhp!`QGjP?I8FWbDx`$n}(l>
zA7Mb7WE9IHP6a43I04L*$;SN+&E*a1Q#l5P)rgmH0ILLeh(<Ta9fSCrT1FNM<2fQ;
zJZUr>2Xz*EVD<eX)(H^daKfxg2(|)fg?7!<SZ{Vtadk@^Tc~t9{X43ncL#JhZ;721
z%QE`{XL0@_R)GS%3fLH3>4#$5<rH)oC4ef({}#XX|Eg{LztQpBM59@{2uvARgeer*
znl?$~-ysM?TR7DOEo9<8uN!WYJ2-EoAsz!3z90h?^0EnttJ*Eu8)gp%Xf?GU;7tv3
z%Z5$j?*JaH`30b@g$iFbs1^gVH|VM^7=om-p#UKnfHVEi8`7T$163nEfw`7JpkxHJ
zP_X~U4XOgEwqR!76#ueTz8n+Xto=(nai=|MJ=$Y;C^IdTr}I+l=PN=E_8!7AU4F-6
zcT1v-8x5^t@}8!}O&%hv*1+Uu6uX0!S&J<$;jf{sc;&%t%aaz1q3SYIC`t`}R>IAp
z7Uw~W<s<dHi}nVpK#&9rU)6;_f5x3<IW`Ms_2y$B)OylymsK6)fSkwh_J~7y!OQZo
z?LFT9JI6N%cPM8g9V}<E1|F5K{`TqrYHDu%M9;JCb}GDWKB_GZyIEGI;lL~B+!y?;
z)ibc3mo$NGsZp6|$chRxTZ@lH@ao>h3ER8aF1#wf<2zdF=XLS=T)dc|EM`1Psk&ic
z_R%aneXn<7f${WeNQL)c&~TXg<xl>)w!z(!E!^z|oc_&PZ03-KTT%;ZzVZ1Nl6r#D
zl37SgJzx_OGByD`mWCU7lyLG3vdLxl;4`^|a&n_Rd(gYm<<#-#gO@^ODX%bnM+a^}
zokrsy>Qp@8bF@+)nX^^UUM^15Jp)1>W|#o(3owylCX3#yP$Bh5EF;Dv#9@6!WP{Ut
zR5yt(Hcb@Y8gsrzY3L#~Q!MNj!eQ!5iD2&Vv;6f9H8Xi{s#C*l>UD!ZGNbK*nmiwv
z+g`l->FZeYGzb@T;_F)T^!HeMl(3|;I)zjgxp_M<X_uv^qmGFf8BXR4AB@{U75kN=
zM<cebxkiQ1CF*KldsdwzhZ^@COTWuM{!Imvd3g}B2>uo$wXABJeZ`4g_hgSj^mBiC
z1Z3-V#ysC0)HXLZ|4Qx1H5%=EZ^Z5BvR?d6GiD>1+PAp5QlH4ecePY~-nE$X)Mk;e
zpSL31YtS~DL8%5>sExq=Rf;)BIor95@4env(HCa^-nnSfP+{nMz5zbO<vKYg5n#>t
zlFI=oXu~<bYrQOjy@`#tkqQfjUAMQEa`sg(nZnk3{54#}p8X!wT>|BO@qLRgn4&R~
zJCoA$wt=lUmC@Eg32Avz_XF)QNM5DX;~vghA42ziU;MM*EM>?rwDexGb;py%O81Q)
zZEClLXKqjU{5=DC^m1;qGWYGZYq0MowRS;{8Kdqz_(AjYtEqn`-b~T2bvdvsG>XAV
zcP0K{MpK#{%lEA;u<XY3-ar1N+;KVu>hAiTL*x4k8alT1Q-U)czk{~0GZi)LdD;WF
zCz~3gUl+OG)=g>SKDT1~EQ0>?RsB?+GIMm8$7O~ZuMyii3+IW;?agHp{)+r&+GT=v
zy{dLtb<2(2&9_tEZQxr{-DW2;P1IKPiGmE9cOL#sOVJMnC_}${c3(^hQ(%^qbNZJO
zZTUn;<Blyh*v5LU!DbT0N0k1`-dp_-bg^8s|APTiLj8W~0~tz40k5;~`zH;pY43xo
z6~J4h@uHTWDna+2DRZ-+mdE8=Z*VSN!BzbJbKhu@_RChD>|p*{NM@j!y)4|}m$7V=
zr>+DkBlmTA|I^V{zG^DZ)vGfv=YI-=<g4>8D+k}quT}T^QRYRqJ2GAb4W~1W1r6`K
z>A8O5o8Ix2A|wCx$t9vo%9jV|gp76-x1cerch}{==sWwkJc9M9l)63}U5}~GX8YEp
zE4jnam5|2x6{}fe>%uJ4b4XS98&61fnUvICk-23_cgH793^*O#Le-ngL+M|hdw-q#
z8@Epw9nTjpQT$8$8~4~UFGbH(C)e-3olG!AKaBABQC}adcho&Law2laPwv<866aUN
zfbL(u5<D3hW)~H?G4+%}0kwX{<?{lkWf7O|)aG%;7}UjQ{1Byi;i6>y2tK!TqUtpL
z?dNC>UDw6exhzk#+wF%#UjBJ~rpxWY$IfJ5J9z!~KbM2O8rXMA68s(<@dg@{t`!<5
zvUOr>c4fTd)LxCo+ZPVWdOORF9xGiO|8A0RxY&~w$mr!GfNOmGJ3FY=Bdv}n#nr;h
zqN`Km4J#L_lv3kj>6qe0fz?9k)B_MEROt_NlMTQeu&;nm*V(IF3k1C@-<e`1vgo}8
zN01$F4JD5~%ieVt#oh=Swk{j6=A&q!N|-<1F-qYT>p&AQNV<kOrdQLsdQhP5;hMjF
zF3pH35@;m4T$YnwwH2#78^{N=f<a1S!?ev0-<pG!uYG?6EKRswx;RwhC20)9x?R12
zdi`J`yi8%b?FxuXWMITGZnVf3#;AC(YSIxY5CHq7)<laJV*f4q!fuk0fpOiK|8kQ&
zNvz;*x^}Akh1^l9Fnu%6zL{d+7-~cCm>|rES#P_o_q|%L_JvD*ANYn*i2<kUY{&)j
ze7(0T^Pd^P6in->=AgJs8Y?+tSQ1gGHJX@>E~{@ICT=}DdOpg(Y$kFBm?LfbHRb@@
zN`7*Ge-t6~R#R+KuS~&M%_C80%uc~?ZnGkBdekm5<U&|+*ycUI`pOFp`&AW`G~fHY
zjiDN5GM836FeghVyT!m)=nB8O11tXZ40hjJ*CNW^fK;X~2MUXhG)qayIohNf>Z>F@
zw@Yqb50msvk6``t2feBNF7Kt&PIuv_;NDHm|3D^bGefRkNinNk5z45CPfuk(GT)o!
zS+igDX{vMa*ehc_BUAz^aM--Ob$Vo#8O>=O>DVx#bi40h@p2Oln}P|oIvS?Sggw@9
z=-!caY!#`gt*yVkq-ncu(<=&>B-Mns4!?|UC@E<fs-si0wbQuHdHuVr<*rzl3cSMc
zPTk|Nw>n_KSQ%q8>iV^{_jTXi$$v(Lk_%4~Cjuw=<rNYa8vaBxpoeg|PL)CZ<AMrZ
z8t6jx5XjMDaJ>sB5-sVzS5_gnbb#HMfAuWLdlzyZ7vdtLb}wN*!@&KjJUS=a^c!2u
zJ}}vIC311uM*VfZg7$NDo_3JQc%tU)0@3#X<46DMm*5dH!hLlO!Eqyu^B-Vw@9!DK
z4)R@H^)$=sK{>@40g&r7CLLWaA|&nGm5CV=K2h2#2N}3Y30nSgr<Exm{4Ol?{m%Nc
z%7A^^9x_F6S@<x%qH`SFk=4KHnIoV(=lmAF0!>`tS@BiBe;)(j3L4xrd_sY?x1(>h
z(1pK67r$-O7djeVY%zc>N_d>w_~3xb!7bOOjG_R`ny(2bD~*lb41uNwjZrSa<>v+N
zWh14(DXNGsNa9rH@ZTLJz<;ct`@{w+p{|Or=v3geA;tTg8nTzw=Xe|DOV-SJK&rOS
znVyBmpRsRP;WTQz&#(NxD$?pJLika&y?vojs7Dc=_)c>~)n1SI2S<CFA|ws%RDSdN
z+zne@1y8KL$WP>3`nQikk<`s)RHVeSU0j@tr8x^|8To*bUj#*FFi!nM6oP(6Xh`?N
z&M$wW|L41q7PKtrNL99Z95B^Tv~x&3FI@eq1v<tYEIjOA(u)MIn=oGh^b#Lwcyx=d
zD5Oqvn2HWERR>H0-5O{p5ce_N5M*PN(=g>*Gmw*1eQ0DMuR^3|FPkv5^A!WaP`5Zv
zajXJ07f#4MfyPd{*9f68fUAPOo(f;pg)Rd_^6arNIzvDY0Oqj#L1q{PoCf|-Mj>Fk
zXEu`!JwuJ7fP@YO2lJy9^xX|{ZaK_8CbQX_Bn@xgc;W4OQnzF*nuA*%FV9TN-hm_p
zA(#MJ0THhPOq>H}$Z3dEYZfJKq6SoL(}X_xcyL|ci0SgR`#wer09Jrv#xNT>&0zsj
zz)Byb1pK0U(vtUzx4H%W;QnB4j8LgYX>2HA3)ln7jCBq$#+#Q*^AkXan})O(@xT|o
z2$DG7s?*4<+8zu{HY;@+N%Il$mhCr$x1-Uq4TZS*LBu26Z1S<izk^3k5Cn_|^|yco
z7h)kXnYlb2-hu;MOh6|As|W>VpDpOAShHiSq5^_l?;)EJ;8J*axUBD7Ex<ZQi#?ku
zD4;5!2n98eR`q@8+UYMaWs^n8T}5=`*^tcoJ>cx!2(4;a8^@kY73q5<eOwB%&<84*
znZUNw@iOZ|o*ol4Hul6@Wv)i8WZ6{fF-Y_nQ0Zrs3w;#OfkaX>R!#fMp(^~#2qw%S
zbul?J?|{4tXnc{2z|@rSXAx>DBSfTJ3Innl!gDj@&4#@ojGfoa(7G^@4xot#VN)H<
z#p+2!Qt76Wq|COxlEX<|nwcCH5oDnV(i~ZO6~T4KIdikST^?8lqUZRl2VcdqP_F49
zI&$4%;B_Oth$281@;``s@2Do*u-o&YBT_6uilGTY0#X7&=>(7#dJ{!N1Ox(t^b!Oq
zf*NB00g*_FB%w&NfPjLclz<vaKv0@UFVX}A5q;17p8396-^@9GoLMvL%wJhcT}YlM
z<=)q|_iqdGl<I*gMHboK7G-Umjy0%_Knrq*lc7Mi0cRgi!oxbVuQ`x(X$r~E%@=9L
z(+sJE;ljyAgQ@e}{$dDNffh9@eaT$5S(-f_F-E|I#Nz}wM6@Jp`FQkE7&)OO44<7C
zJK5G8>%N|dm?m?o{odZB{joucG6Hb2fS<c?-OVK3ZQm;68vw3kklp!vLEwhAVae25
zx4<Qi^Ps8eSZ#VsJA}|euMG5RFWL6gNgsUaDDK3{DhINC!0%W_eiSGpFj*kzzi|`&
z-D_92WWgau+1jM-`A>jVz66M}tg}cr(bsi6#pd)uu+p1F+H7&}6_7>?Hoy{f9rj>R
zt40d2@6zbV6@(ni!4o!Dh%?BR{F@y?@k&N?$86H*utXD964nkjx&iLd5B~+Dy#*9Q
zt{1XFP(@*RS`@BT%O%kM<OJ#EJ8oDKL(Omyg*E%IFq<7@SH90?X-Q$-LCw8B1C*g@
z$!Cdy;?)fbNe4`=MA6Cls4N?WQaO8$#5wXl^o^f15Loh5iNB6z>jJ;Ss=1Q|hqlx=
zOR_tDGNp@R%;%`VN+LS?>91qjJ2cGV{o&iQBn`56LxBxPjR%5GV;h(x)e3I%hhz8v
zbA~DQma4tm%bqgeW3Tg*Duw02a!Ty9bM__e^c8|c!|c6W$=U~EluLVMo$|@y3=<0@
z&dEfPW|eqt8V4)_G`;s!iLEjvo|_4V4kz*1aQ=3T?%60#<k+^Leyx+RV`WJCv*EYU
zf-y^5l(}OW@rL5u@l;co>j%ls{{gcx4iLU5BQbh$;$fIK_x=Av%l@aP{onn_%Ty!8
zqkH86-LM~&<XI<`R*BL<Z3+U?bL3|gA{JN=DrJ_i+B8P9C<709l)~5ux_$js(nm5J
z23Vv9iWeaS-DhP%Lr$|CSyBPqTKo<cI{z01ZxKG6cqj{93o6|D$Vdn<gsNZ>6iI)G
zyTE1<8BTz}A7565L7=Y9&BI@`Kx63~KKQOc&KUEHdynq@6Zk1sU2O4#WP;++TjOWN
zyfQkbuT|=bW30$E5~GLQ_4X@@IjzbkT-tGcc+oxPAINH8IwoVR<>v3kGg948H7|-R
zWiHwW@Yvk%o>aYWT|T^2m{yY+sU9g5P_58Wc<fWe`Bw-~j3j>zULD>!*|=b!#`t;Z
zj>5T^u0;)JmA@x`^%*IAcF2>s)-s;ASo`gRNR(Ah_iy(X4WH0j)sIs7%Wt375PZ!T
zZ@3URsgiXvT|fK2jWDa+M9kyvg_-eU&Gh~IU+w$IeYQ2(+=!I35nRoBQLc-fnHe=P
ztkSmWI3=?ZxO2Tjq)_UYcRk_kFKM>!!0Kl^A2gbqTu)-<R32Lxs%S7{Ei*_vKWQ#s
zNo?(x#DBb|&KQ(845F8+4vaP4?e|?S72YT%L@Mb!ImcE8?KSL%pqLKg1s~4caf&=f
z(H?2oSaxyg(;8(TT%pBYxsjz~$m5TftczJ+5|KQg#&_$Yf57I89o2734=f4ia%Gdn
zn;ic72<`utyYg&HxUTe?)w)5J_z3N9n5vyxI006ilQgR5{jFrJdG|}JOvs0VkvLZ|
zy(?@AgD)j6wz&@f`Sr57C7zDqA$(}4|9WI^eNjn~q&F;l7@oD{Xj+?bG}GE=j*fr}
ze&V{XSI0q)ny6@ZJ;8vJGiAN#BwX02$q&oT@@2n3rKLF91?K)0=#wG3!n?m2`C#(S
zdC#X?*Hf;Yr|;acND5jx;9e}SemIS1;R2!|^;72i^;RWU2KmTymD`U^;tv~mUuke6
z61H^H@2CfgU;R>5yD<DME1>CGMqqi^hx2)_iVbhCyWw_kHTA1xa!6EXo*E0-(7kIr
z>#MS%@n-vWm$2quu7E~?k)NwC@IvSDXlBV#p0f?-xRJjIqE@i|wf8hoCm8o^%ttru
zS7zyK4?^8PvfgPk(eFPG3-Cm#nemoMp?l8`9sY8>v~%vG)VugV?T6i2k|h=V=~Xsd
zZT86u#3%Z1-wGQ)4bye8);3Jl@8%upd~6pv%kd=Nk0@@0vgqviMmW=O#3y<2Eb&et
z^2TP?Rc`9}>#EXQ9>uRSccN)H)rpboW72*^5i{K<7IRgxJfzy4E7$D8g`YTxe5ezl
zNKK2goR^PgG0WR^ByBX0#cDfW5!{(9eK-?z^Zs`p{BUjkx?oYsy<P8z=5VpYaQuLo
zKyEnKTbB+s|GG>{(Z_x8qVLT%s$6%%o%74(?<Urjj~^dVI@#tjCArnV<2RZ1=GzCS
zz^ihOBPHy&T`7+XdDr&vC5^c7h@Z;=_axSzho`%3ON4*hPP^PY-I#nd=AFvV%aiql
ztB#kw-|jg~DXkv4AU9ObmpUEmEqvoRr)23`g&VW<X96`AVyxsR?G!3~c`Y@sbHZc)
zIn8~_D<&oXKm}&@ct>3Knf<i%1EPw2Q#`}j`O!;mg))J%)nfvhq5h@&QW)RP@vFxQ
z6F(Ix@xDq4QkVskIG2|p1p4Qxl7M43qB={|%B^1=A^vjDVw&F1eC?36>~QNtbSWpo
zh-oFJck=m>6I1>YkLUjkhq`z+hCLF^+NzM&t$(joS+HWlzUM`j*|7UMaz-{0G5U%B
z`SLZcmaWqFEg}6k3gq8zwF~$TW}ZB}tcVx>mU{4l%ILK7QWPbA&*3Ae*t#(5T^}fK
zXL6?axyb>X;Kc#wA;qj~^I!BAk4N6}mM_w5F{Vf=B4ZY;lvzQ#uF8u6LTWjS0&vQy
z=w=IUL7gcUwNru8RVtROYC?V_kX3W>U9ldX^*q?ytV7PnTOXNv=f(c}D;jROX97={
z1m<WxjvDDR8}JNWa4k-A`d9$kNbjC3k~4{&vBOt()o!$3wWhof8hflU(!myje3T7A
zApsgg!Y6KvN6Z=I2%{49`qQA2gG?DY!DfGUch6Ak5dDBdjDfy}ENdP%3<GP_S(;=G
z!6j=~nir^r0}YcI2VWSK%n`DQ{c0NhWKZeo{-43KRqZqnrpSXbdi;K`ieJa&KASW1
zog1N+8{v-BpesLw>du~JFB?_IO-~g|(?c51Gv~@npRagml{6*UqHK)ar#;z*(7ZN}
zfPs|*e=@M|ucW`E$Uv2EQ1I;WoQE@KGHQf-c519xC+cqA!8RUhdDC_@WY@R$r(N!Y
zRLwYePgY~J6Luohm8AyTShly4(hCVxUpb?#so&6H33m=KE-Eb5XcO7KBD#AJ+hQvv
z3wzq#cj%Cx^_p?MOU%rudQ91uXl<omPQ>$gUb5#scu`)nWshcKWc=kw+Aj=;+C|&I
zBd~WH{ezXpZ$*b(sv3IBea*P1h%TwmjMZ)RAD@0Gn=0ot@CqElMJxDf@EKR!BT7yL
zn`<f>Q`bv4qDjX6`wes^OWDln>Xu%2ZiXO}4!T|{XtRHszv0kTKHLG6`GU*zU@=@V
zc$dY#W9^ij8X4Ll<i-fP8ZxQp5*rzJpP1+z-K|agi7r(+Cyx&<%&iaMdU4M-^hZTd
zb(*rl?1&|5++c3l*2=e`hi@@g{hZRf>v8o-i-C`=1gxBI)P4Hf&J*>nq1x)a$&!RQ
z!YqhJl0AF-(8Li%Ej{vkjq}CC9;rWD7o=`q(~pn$U-diq@PoFeK<x91irO$4SCeF+
zstCvC${6kJV~^`a8ei|GmPsuc?K&$zJ}>yu#_K?wGW#jRcY(p@qVz_nE?bdZUnCVp
zK3#adm>9p9k=j$I`sM3j#TVwLLf)a*k5KcUcb&}^z5juf#dE)x5;GEV&}Zb&bO`DP
z<m`K@lWA&}k-yiG8U1FAbMSlA$u*S=VXe*TIAPL3_TNcvm9lXeOR}O28GQjnn%Q!@
z|MyWvpTwzIw?5B4m8azUq}F^w<`pwrOHKL{Av&9OmG=#T%+Te7zCbWLDnG*uDo$97
zUwHkgxD~9MfyI7NmoMWq4@MDFyJk>VOv^Or%X}Q?^unu91h5rd$_`C;q_%6Rg!VeJ
zQZ^z>-zz2B;(o`M8|v7{PJ9X@OePHgWL;5##4hM$nFwXFH7;59#yLtNp4<$cV%;4W
z<x>a6x%(Tkut&)_^uw|P%Zx!{e>mCL6f#8LB>UntFhYB{M%tK#4Wz5LVPT8poh5pY
zKj8LXHCnRlZ-&J5k-U?+Rh;%5q2>WmNFjM}wx)`refaFEK!Y+K_@o~&5pYLQ$_Ccp
z0h+B{MF7qAwMwF_OOz54=XAg!9dCHpXt!4;Zt`IZy{B1X;g)fz<v<jjp^p^uFy#;o
zwZNJ21b~{BQWzgpoRp?vwZn=4RV=_}y<jz-m15OjkA)l&+q7jC5%k4&m>yRFUhM(|
zl>-e}Ao4&G;2ko_kZnpCnok2OAj6A~b99`|dQ!qRp3)6!hm|3j1+1<AlDWrb2P|}}
zIK3ky70#MMM=zP71|RHu3u{K|*duw}Oxjg{&;U$;8wlNOzu}~t0Xh!(`4Kc8?nDu~
zN^H*$5NhWkc&dc?)0haLf67rkZXVe__Us^_P^TJP3#w8?^SA*tF&5qA4NK&4(*-N=
zpG@`xVTfgnR`CO9n<{~r7T4`%Gcw4dqU|B1PL|bhQac0|j6;P;o+0k^0LWu3RRW3V
zVo&6QjuAYv`EApZn5r8zAn5&J2hEVY4(7+Q;8FB$1k|;J6+#a?4AsC|uK#O+UlYW&
z{P8~!YVPJ9%E}^bLJw%AQiI6|HXz@9903WM*vm`nu)}&ln_%-_hzun|K+cNk3qW8S
z9|8NpHk+(LFfopVMS@Kj^1UFgwh;|YsN=vDl>AI%F9e%<fR<Rp+nbA_p`yF6k}Na?
z@*9z-^jN##xnL$Uz(vhsCEXcL)W-?ciMG(#2%s8RW7!HA&-=v~gM~uP=HwW7FGs4X
zVd^P5G~LTSN2<L!j|<bs?Q56j7$R{YrXxyHvW5um8;SmGZ3N)7U%*-bHTnSdE_}Q&
z48>F<CDcMGMeB4P^yp+Zyb4kc;8JjlfqNywZE>X}zyrX5->Tl471aYsmWU+_@YRv+
zgLjN5$x6w$=cxAt1Kq4aV!DH6CWhA%G{<a|9`0df>}~>XBn<8uYFP+Kr@+Avp_mfQ
z3&7ydcO8pke6#wBF5GO<qSot|Ei*x33cNpiqTfh{1SC7B7HA!^QRR%JDHPEm?uW^^
zQC9R4hSznCl5S#-*C37Bv*X3Vog~|C@;j}LKP<v}m;*Y&+;}3)4`@Lg&p6!PqK6JZ
zi{6i@kB()FL+YV}q|H30GP~gBgE@epQGl(WFtbUPg-sC@dv;)&XJuIu?b*metc-Oa
zA!QdVxM;_6;SM83tVBpH+#+V#+{vno!r2Al4*MpPIy+Y}JPu}Bv)OBG;4O`56PrT&
zfxZ~B5ksrwh={BxwF+=Mm@<6a=8q^W!DgI(BZb4z%{tubEiAf)!YK=*go9jqD8Y6-
z8%n(Pxd&D%9oK7KC)yK=;SNKBdTtuy4UAXUD?1Da-YcLrQw66r58#u91*sf@1KvZ;
zAe54(ju0)_WqE>;jP}&Ae_x%GIkw1s?Z_>-JzFM0V;QTjj?jywaMHAxDzQ|35b~H4
zgB5{MmKcQtEX`x|?O0jW@#Wz5drR#8q-oRt#LsK3Vz_nt$Qom13i*>s++n!5{_8py
zI}!!Irowzkrt(@2AVb2(4Z+EvUx}mq4>ELtsb<j2gpCh0*5v3v@~3g%|9@5C{Qqdh
z{lBsX|IdGelfZqMe27V#+9=M2ImsbWrpoNVVWYsEAr84a5ZHiI2=Xr6^p?!_lK>$k
z23-}81qJJT?ktd`nQ+`sqH2}Qp}mqu!AZ{=HUTQ?|Lam81wfsn4k@<9iAT+l12?>q
z_6=vzwFHs86i%kHJPL#6b!Yv+ArYdB)+`51wXP<dbVtn36Bem?XOipFw>pgl5WBC8
z>Dp7e@#^By@wD-KytjVmaiE8vH6D6s9v3)iV}P5vb;0bdpa!|TGA7H2@P&n&$jq}9
zNg=O~0UTX_(WzT&4N^ZoPJ|CX@oPdr9=!AWeV^W!DP7AOdp7vw=Mecu?vdLwr$=uw
zF#3VVCgiY|`uKyN2Z9np-%k(+<J$*by}sBm)>)l^C%Jk*?KhdK@)+!}lF{;y3KD}8
zW<2}~#y<Fkc2)igJ}#8wC7|sWC8eHdM~@h{3D|eIHZk&w%ZG@Mmy)FJdSiux2j+t>
z-wG1Q(VHaS`hKOS#G|>fG5N?nLx;0JDo&61j_#Y|t~9C+IASO#a{N;GhEf=J+|Z@y
zZ&rU?P0xMzO<RpJh-fj`dR9VTyW@SQ{?!lBy)PF{9NkB$sR*MUcc+>r?Z*p5t{JKs
zs^HyoqD|M<vg737#Mx7Fs&DAVKAGuXrSVS2LGTT%cG;8fdIyczGZ0(U88jMY?CDn}
z6!D(!yiQ6ZuXbqI7uu*D&;-sKw<sGC(WYlPJq{i<-&7_1#m&;EKa`3FAJo=m;}3if
z%ikTCXQ7seF7M9BJ2dw1l(uuU<z9M}>Yb*Mnb}nxI(hth)rq*I=>+twZ?~?4!pD`P
z!at?31;-K1?OJ@^M2?rmt=1&VuyFe)qv5ufQnpIAX{ZP7?yP^H=l#xi>yBT4E-V{z
z;qCdSvdzZa*WcwIh+d3gR5>0Tiy<-IW}S^4mirit{RgTr)hj9upn{@<o5MwSE@v)}
z1wFd^<YVmY%dg2%yUs%*_oGA1hP1h&H-7B8HsXf$OR|6bxhHp5PM1)|(Ci%zif-ha
z%PvY4@6IaCsU4a*>UyhR=}+JtR+CV9Ozy?PzLJOod(UhqUaSCMME`jsZCN?|04|8%
zQS8uh*I=4pok8Dud*`jj+1;z}Bs8#1^{+Q*_bs@i8aurSa|ZG|FL*uUk1(A+%3dMy
zaHO<s*96@|9TWBniC232TGjujPS8ikk@gqoj)vE}lfqqXUF{k*&iMZjJ0(dgayt>R
zUKVh0MC@c*mwf5{K`*NZG>&R)W~NJr^R{E@)Aq3Ervn2{UM=a&cqNN+Up1;v$NIR9
z(>ag927*tYW!#t3dK{$tk<vtL3poWJ1O?suza9*D$NI=tKZ_HMAFiDqE0)h1{k%5R
zI%d~#ChQ_3tZW}+RdDjFTial5kkh;EFx-ZnV)^31Tb!<x0FiOIwPUn{a**0DpVKV{
zjlypOciaEIx~6h<hJPYNIMDJq*Q{~0@1cA(qYrrJq<w~q%piY}pZ5ELw)US6VuWE)
z<QjaJa9g1Rx88c~&+2o_A1{2IyZbJ~RoK27UdCBZ5vH&z_@2@Nf6Sk<Qyeh~hZV)j
zd0gjk67ZnAe>nT2ITY(UUivBW?AHFF#`;<-m+QZL>xyPyhYwaeJnvQUKhN0kt@W~2
z4S3|IN;bcO|J2+T-Hv(iWjef(+gy{sPwIJLZ29Lj-RC`YQ*`64iDbq0a7DGh{`>PK
zi|eN9I4}PmbYxC<N>wWbi&1kpIC|)p9bo2)imD}wR2|PxchWw1mAyawd!U#LN1B}^
z=fOAZj>h9!AwRt{DTfsZm(a5T5k}`)g0rEPeZr-lH~g;KPTtB9JXvbzR$D<r$WQs=
zJg-z-MltHp7rVB#v@2u=_K51pn#)h?j|EHCCQ>!jpQwli&(Sq+$E=lVdd=D_q;*Nw
znd3XYBK2IPl{y7i@B{GyxT5R9@sHsfM#hka#k`pgD=Ud?BrAy!JGf2T3ovekjWxMI
zGjOLQ8b1W8{th9g$d|6>BlL0R(u3o7N=IJNo>`E-j+JFsR*N8paU!m^r#N7KJGZ*3
z&NitYxE!nEUSu75e$?z_*#y6*^Wi`A{_WH3I<6WO@=6&^PtVGargR7@NlseK<`o?F
z+@v=i`gOxD|Mvh_@*I2J4g9^&wB#^TQ=K%MmT=pzn2f`$+9w2KWkz8R9ZZ&YKV_fD
z)X{tJMW*Gdw@t)o0hi0!X_9j!N7zZT0BYc(Zeic#1*zXhTNAE%NYy!-Ma!n`XZ$X1
z3b2%DlwE~SiB^}MUElgyQ!HO_A~+vnM2l9NPCK+zExtdAl@GBi*OQ(&JWlg(MRqRO
zn<7wC`iiGtrP^1ZW*hUW2s6&V@dGDrA#kU(M_3QegWTa_<Alo{qdUX|y-yLIIxY{R
zKQ4wYpYM$#A3ou3)Nr?PmybOBG4<%;HI--$h({AXOhoZ3e7v3$F|>12;!eQhW@OKa
zP@#f%RhO*FK2D{zpZR)XI`xoM;S}9Z^o3K@DY;LNJPywqG(LW|<oFNtK?{6_pT*^-
z8Ugg>-z_cNTQd*$BGW3W@zqBU%VEab+d|tk$(_e(XD%gwPbk$a4w5lyQCP&K$vJGB
z;<nC3di^ZxnL|HpemqK`grHo0`V2Z!y&5~W;VhroD&<!v4cwkfq-@E~z~YV=;=D`N
zZ0>IUWHC#y_qy}s$I_4GRqoV#B!8=tGr7`v@`br}WuWe>D#>4}5x<D8yx|Np$+Tvv
zWt~%P1#0GMqz@jqLpb2EMN@x}f6l4KeDMwl`%(WW<=d+d^R?xxrFpGg_rmamscC~N
zKd?(17VUSVb;c^@#igHTr{)H?fMM{h4#SR@<xb|p*k@U<yrYsZ4tD!{tQ}LU=`gQp
zHRYoyLWZ)ILY=Fkh+605xEbDMxr-fA6ELnkh$EdF(Vu@(eaON`uK&o%j5Wo!lihQ(
z6E2iX=~Q|1^3qH0$-4F_%7pM7u)U^Tef4Uclkdh;?{3A6g4RStM?&p{LH1s#v&_R#
zAjxdBHg+7wlLSUs1?g@c1CrToqHn2E%CH7TJ?uLhQQRR30~R`5OqCeg^k3lAg(!Wm
zhN_NBb>D$#$p|^JZMNU|9o~J^Ix!ma$bnMesYHrrty6e>BsXu8ZaDgpt$W#5KvTA5
zQGoRZhT*4=D47FpKa?rlaq3ti=<n=^zbmoRNhN!-C+mXvHy@{Dc7Gz$R>MZ2P9{mO
zKiW4r+%gkX7hEDcFr}vnG4mRO87-duWeWriV>VQ~1Xw`loPKJ`8Ab5~%h6d<oa0|~
z-WG*}QZkuqn4^%e*@8u&oBx42z+#3^!xU0Rv;F|KTr1ksm-v%n&xX}nBAb}1@skk%
zb_ebDnL7cZS@HcO3^%HsGZAGun6aL3FEh4K%ASk9F`LNIxnO?9m)HmL=g|Pmrq>VA
zIXJW_4nycfF2p7*fjh;T{T`9X0ywwycNvjXxn6&^82D`VX33NST`QjeS+k<4QglwQ
zM8N`_sXRiggq>9Dn?7en!rQYIVG*=;NEsAia>=CObT_Q>B@sOm^9T4)zZ@eeQ2=gV
z3}nXe16~1y<mN;FRm^^Kxn6{!doSd_YFUKW=mP6H3qgILpB!=E{p-&FgtTyg>;gdr
zAvdE{qq%Ybh+nlNI5DN!5fhtKIBSyvg%kS*GY&79#WLt>{PuXF<6ND*HjN$71<AgK
ziW;k!!#-a5DEqX{(v+4G&IgkjNrhTlbO{8LT{NLKtuWs76byRDE8#zzZ!|{^7J$Th
z@NPN|Ah~0MPQ=gVhv2lB5Slb_kf7VEz3T|c=J$Q2!|X+1@xzhQ^d1<$Mh}__C{0)-
zpyIJ2Clf<4sj|I&>26>N4jknO__WhYabLXS^g8Bd6nb>SRu<jAjM+Dw?KhZ_kX@X?
z5G>BuandLpp!9O=<`Yns;BSB~N&OpfbDgdyZa0VFj-mCy-pr9rc6vqNLI5CW15WS!
zA=*?};<r#MFknGf<4*3bW9`^UJAiG#1v2<OFkl%6m$xvX_Q8_5wWD7lg3YqW5gA|3
z1%tfOC#YJq>3c{hsB75>*4Tcktb|=08x_9OZ|4RfV;3xk36Rb<EZh<h7kb$XMaDD0
z+=SRSo_HXCiz)FZp;ofF+>VC~@%GRW3pPB_0U@0f<H?M_&XGVhjSoOK!Ywc`zakdt
z&ELnKP&h$IKD`z6MyMM7@n1x6uxHGPih);~XitDXE|#r~4V40lP>swT1`{Dv5#HKo
zbNk=Rx`E-1fjj2g`vY^eWOg2q)5v|3fNJAoj|>4_9W7d-+sj51j!|@lbh@<QK(-IS
z5PC|ybh2zmcA~urkVd;$cf5ZKO)r{;@@Js)TDB>m=K(XD&Y-iWvmWeQA{%xiy0&14
z0G=}ailZOLV0s65-5+Sy?JLwrbnrCG$7+Kuut76;m4_1@N!bwpY_fT?m^M|+4HA%7
zi(iQI9!&WPF3MjRb#IdBU6`D4Zy&{YiVVhIlNpj4m{yL$l5DA9|F;Y`@F9}IzzfwW
zELr~Qf3l*hZ8(^+MPo?J)7by$usC|EfE5H331j}~<6_$7!@-q^Mc=rdX+<z%Jvhsw
zzYxP1%&Ncmp1}TgJlT8>Gn)bKXT1Mp#v0BJ3kiua?C7FQ9=aH#3X)!8WrO!aB*nNe
znK(^0c)$cV%J5GFwZ_f%4=x7Q5uaye31sm_Mf~=WBun5pCtFW|Ia9A1QyCq}L{8B;
zju3dT|7Sk@KXc;$e?795Rvp(OA%(D<3IT|AW%dI^2P4qJ!W{!jGK8!hXOs4&gNqk#
z3Mt^-`z(hO1rc2fpj9Obg!9l|*?hc!nTS=7FAoJkXmBT`i!)80TamA#*_d2{|0M<g
zAJ5K&1;Q$M6xLxTCrO@gHKEoIL}T0p6b4v;+>xE#<bdI}k-6$7Wb1$IL0(5pPwNY}
zRASbzG;NVtSp}XV?AojOPrjGoH4fjE#+xF`_DhH+NzO*?E3yrI=X+toz|OX$q`A>)
z(W_qF$AzIFm1+iU2>XO&qFPa6?QYp-k8Up!idQokcKA8d`&$<UjQpRDw#GcG92IC9
zgg@0&@cr6Rh3*mE-%KDy%~n!=TOY#^MTUYy&yW8D@w&f_O!yOUNHn_2>ed|}5@vJR
z`2`1K0ps4^8zC|Te&504wlK*O&<wWjmlhEyhF<#2c`9lOm#L%8aPT;L&oUsoRjK3p
z7c`?mAYHqYKfza4t82;aU8zdjdp(9pO$<36yLdX;@3(wd63Nz}uDj8f`^9Azx}Pq#
ztQqp7>;tmhlZVUPqX1{qsQVNwnHa46N*=dMVg}iHEoF$f_fVG>NUs=-jXT|tl_5-s
ze_l&S$JNB7o>+~pH9B?ayl{Wal5P5FlG1rgvS~s$H>OH<f5q)u5>FZZ53-%FFuQ@F
znRnVR#WFui6D7?$fDnD!`3fIycjiRQB;^a!2DIWVU~W63c7?E?d-pUdVlwk_gWu<i
zI$V?Em1t{zt@}am()s;g6wdn}&AtH6RW+0*T}t~ST&7!P=vC9VC?dzsna6xe<Hw6s
z0}@0(MQH0a8~63SX{u=VJsS3*kOwrOt@EUPzh>$=IE3qQxilcYUUT@G%0R@sjp3Za
zQNLiGF+f#9szyAlYn)LZo|}b>-#9(;^!z<HUA5az+r$wybNr_74&sOZn?S<)_>%9$
z%|u(BGY%=it+RUlr`HPWC*iO2uK3(NkGn>6#a&&CYg?H4xc2U?Z4`3)Z{&9awzUCC
z$zCraFkgygkY-<gC->2LJV!U0g}$ZUFO+FYv#e6>FL?XB=S^AlO7G~c_hX8|PKli{
zmzK`pi|`>Z`pNeW2lB;F@m;8O&b>sL9uivL|4u|wzV6ofmog^z<-&<lf9s<4xqO$R
zi(9S8R}LAk@r1kD)G6~XDr*{e56(6Bxy4IP`BYXU$?KfCnp*20*#kTG**zC!S+FQn
zcWzKJ$j;?{teHf?gSmRmc|-1Ns<R%W0ozKQy55`Z&i7_zu3Y?Nz+-Yu78h-BRyI3}
zytpU4wm9-G#8M{vLnMOj_HU|W&RF3a>{Ww?a;NVn)6wfUQ}@gt_voJ2Y^dXyA=%n}
z^ALM{*8S|bRZ!?*Zj-uOaE^<n9y@nj9$x(0o;;}DI*W5@7;#^1YnI=tbzBHM^64lo
zlt>=5pY`}T8*m0M$#&xMc@BAUdR^23O!<tL+?DlZ`@>m1RUzmAT`_lZ1&VVmrb5Lq
zs?CM{yurXE!8nn&O&?}kHHJIZo&69M^ukuq)J`v@%zNjITjz(bV)R3EjZB+VZ_3)I
zTAk`Q0tLM}-x5j;zPc?o1x}m~;_meLJX+i5$(>$aW7xkHSS7z6{5_aoLscp|M3eqF
z=7YoFW%JiwV%%(Z5)+DFly*{A4@|B;x~VE?Zs(==DZlH$ua_>C^g|XsW2A5!Q<YZM
zQ*z@Y>WQ~ZhpgEv1HWUm%JwP?W6B9n&ffgxbo1hZt>=-v{7;FMLRH$L?CPQB#{*7E
zl%ExNrB2cz1$_LNS$%d*Tl2QJR+@3Opb);UY*dbNA}DijLH&wt?$6380b(T6-D>BM
z+IW~$M`N0!o&G!rPn|B;-4A(`obZD@vUM(JT}H(A0xDI?MmIGh<!s(4rMrt$l<fB1
zZZ>s+{A#d`8q>eyT+A+wG#|?tywYzYD~Y!kolQzNTEe<mEE(7T>z%vg?#P#0R&oWn
z;Go8NQ{*j4TFN4V&qT0xO|0OU>6mPWaQs5BY<b@g<s_WMI^$!YWx>s{B?sJV@gek*
zgXS{TbU**fC~w74BZm!7Jb9*^JMR=q6Z1QoWM><Q3~QNvu{v`HXI*Ykms?x(iohzo
z#W(HT+h)g1B7`O}9Gnz09tNJjbt~m1H9^3-r4X0G89_0P=IxA*dhExczx1eoQ}>TA
z@@~$XyqSEpZly!BgMpUg`}(hxg>>S+WD`bi&ErbB^IN7udcHZV$lrl!n>TX?KRT~4
zPPa$pvqYb^So8#t(Mrd9O9R$fG=lZZ^--7pDDpAWhtI6fKf|AKzBkk0{(G?Pz4!@d
z<6(7;TD~ns$JtL}9Z~AV^@URp7#=w++>3YJBi?G>g$<9_%*y-I>1S1-MWq0k^M%gx
zlb=!>A1V_!AFG4~So-*S*Jm!de9pXJ^Wdymz@=5AE9-Xl`-FuY2UEk3{Ok$dQvLjS
zgQR4(ADwW<IR2><&4}k?I3pm{I@s53WC|c^ozincnI1Acmt26K#D}liIQIQLA@TzX
zE$LI9gdKk=xjyLX&sW(gq3N+5-y^CgKYaU{-&=Wa^kaLP1=G(lG;O9`8xHI5(N%IE
z?UM0GGh>?hIP4iWpN`=<Z84(uD&OxoQzf0UaDT(1cu<4X7JjbM8h@-gbLQ=Kd<)<W
zI+^nSXgIrE8Ww+GsP6dPd=q4l_#ZCE0dInKapY<ER=aA|FQL!Wk1}gN>rSC?tf?0(
zio-ir9>eD<-=*73HV2>Nf~B@F0^*YU)ZTXJI5+v+{O%PSe=})o|I8?>^5XYpX7IT^
z^>?#z9p1}H7d&#BKB(WNn_Him4sDP~_0u!8opPS~yfL$;-%Q_hu#&r1{&y=PB*w}z
z#s6gJJ>4AU`GE<$7pH%`2<;st-+G_^P+Ry=`Keb(Q(48S)6Y(ZNvCNrE)mxM*nW|I
zopUhc5lLyx=SR~EGak7R)0q0(BJT%FtV0K1KDm0v`=a;JL=fQ>vK8PUZ;~*KUohWv
zI@HTHQiYgeB`uj<*YWaxlOxj(`8Y0v^XGVWet&YNg*l9?ZJLaF3+U7wJ%Ho25V~qL
z2v$A59}8<=Y1pyn!tIagH_Rp*DrOM-E#59z^Y%2O*T14StdAw#ilHrI6KYu@NT|uj
zmsC*JGh^=I5A8Z8#?9u!uVdY#DV%SqKj>1{08GZaZ?`YgB9;oYRFV;zUE>du2HcGD
zRD~Bhj#-xXko>`+!`b|jHZY1KTZ>n|j-$}^_xV~hR4CB9x>`%%1STGjSRN-vwaZLw
zSR41UwM+P~T4QuV2XkS0lS!;Z{sc5I2#;u&$f!Y}I1TtuJJC*}1p=JwrV=>FmzeIR
zrbP(}x9|jQ$YD4e>FIT#C?!Gx-4dDTM>f``ubO*&E@78!1|+Ay5l!9%dwo+Gfw!Ou
z*Krygn1$RUDcpbjm#l~m1jx2lax;Po){QA!^hE?9S##9j-GtD<Ic<x?&^nheVDn{I
zbzId1NJ-CLcCReh)WCJOtK<3zHuHbemEEE3$ln7{-WC(N%i?335~Xl)0Fr&Kp&PIg
zCl>qz(N*32^#D32L>mn?+xi;}6mTJB(NK0HQ-;PsLyeOeTU0u5aAFLa`i91nG7!)z
zW_pse$+01h(aEAiv)R2$``VA|f?Zf0bjq+m!c=q>BLUVK2xW#F2)sH0+FX)ZLTxhw
zq7dVLv%~?coZ!CKuwV&%tc?s{0*xaZ`|rP#zuVWZ?+*hr1R(>Er8Y*H&wv`f-CjWu
zjcx&<W%-Q##CV*cxDcptYv$6n8_X-jwag}|y8z$DU0v<6XQukL0_^Zuno<{iV!d6}
z4GKoyi0&%qEy-&6H&m%%Ziv;{qImV&;p1gm3|WasySC7yVaP8_DVF`(b88e%9yC}g
zTTp<Qva%4w*>Qm5cG>E1mgqJemIjjwH6KVo+q0*45U}p|!0MT)g7?Y-arGKED3m+v
z4PAj#(7zk_=-Ux`z2>EE)^WWuBWXBuSRcUyICg}3BsUwkCLb<X?ew#SSfZntqMfuJ
z&>N@^xMPMK7%5F@zKeDNLT=VTuFma&?Ju$4R3)~H32|=G<_xhsz$VTCV*{u(la{Up
zOaLV0;SZ><-G(`0JzxX8V4-EmN&={?;lu-54D7{RIykfTlOYh0CKwjT12jHIIv#7N
zWBUi->R3W_KJM7Rpl9k|U0U1UU#I(I!Qx%w;d=R8o(38n6gTq5pc}fnuZvr6Q}urM
zi#BZU;mo+?LlDdT8x-R?SR&{(JeF1B&lcVj;2t_m)<;Z<mayj+(K(W~mMwqv#?L=#
z6`QIPT`<Rk1ueIRx#%{fw~Y_dT{nwIpn<$@o@eru(s@!l|J|}`w@b|L&9mVIRO|xm
zK>S%=$8j<voD4$aMOba>k~zq;DqM84R|DQ&P_+TnPyh<6bN#Nubzo$UT?YLGegGxs
z3Y^&zxDX3CF`5G3hK+LU^rFV}%X*e9%$a6pq1K@93AM|bO2?|l&>$U0$E;-w2>5PM
z-ToX<xS3Fmd@cu?*Die5UO-Gt&(Uwa1PZZ{N}}r7$Lay!06c=eO0W($|HYJsNxAKN
zziydcrRpx&S_ixrMrc|D!_8P%9Q@dSAd#|?Y0}rbs#r*aY`xAZDC9y*1$ZJSiE+JJ
z+tj2XG{3H3Ej|>yz`mdpA<5eO6sDMbHc;CTKq*E|{6QM_pdmjJf+^vTZqc=Gi*v99
z0$oJEUBb@IIs+FzQU~$82{1PBXvSSn&O-B|zy_3+tEGRP&tx!>KXhctXfb}CQAVGZ
z3V<|HGPF0*pr6U|ABc_KGq!-~d9LgD*EwHspzg<9rLqFdmw-VO-y`;-T7aRP43?e9
zMtaW_roA`|VEG_71b{~JA$hR>5e=p`gV~jt|NjOs{{IBNp9QNG2XAQsB>dlwj!_3f
zl!hh2=d%e56pd!|N>i)g;<m|&92lk;8jK;?|3(~Sg3y|%BSFW(;*yzvJ75CnIFgVC
zwNwJP^8cN8rvO?gm{5mTa`UfJFQRYKSt8LMxigzV*!QGYJ=_-LOpvL`q)jg(XrQoQ
z)*jiUAIr?n=?FDGtXDKCv3Jkogde`+vC}23(ev;j^0-y)Gg9KZ2V=^R_q>PMZp!FK
zU%Pzvud0&CO&%+flvh3>En8CrrT*F4%<fuWpO2P$YXK6px$>=wr{_OJs<&R<52hHr
zip=rU@`b+G-1~=(3!5vr_8Fv(meXSJt8L``s54KqHWIdeBWj8_i#Ty-@N!37k38)>
zq;@lGP~@G2q|#LZ<!=|qZLI(-b^h1v%iM;_n}LPe>xbX!1ZR0}4~AYj(W<B;zAk^E
zDdV$2llbnPN#%!QF>cpY#oP}UVSg3=ICk%p(5v4KU60AL1fO;{>kki7df?8Sa7nGL
ziY39Vd9%2K1j1QVenL*tW#z<PN{ZtY4_O_An!S(KhxCLy95B+<>W=F_2fA$7?r-!2
zMr4g(*RjoFwn}bO&Myb1&(-*BNVo=&JKvt^R&??0HlMLw8RWk08~NS*n~NoATKf?W
zk}Yy+ijuMAIYwG#uuxZ7qjWqJFrxcDv*!4S|6KFMEUSk4`&#tdHy^Zc5V9<v-UHaQ
z7fH&~MS(Yc(yNu`nF{al%FA{6>3(t=Ehd#=6-e$EH=JC3PF~qjwYX`vHdfVSl=xX)
zboQlcmF5At0D>B{Y+Ii73MmtsX+LVLP=D{3g&@rb)NglEVOcMzbv^2=zvA_K$L}o;
zRTj%-)H+P9M!wZtz!szVnt4RaQSCBfj|<FY!fq$(MuIu9y}2;Q6Mnvs5;k%O40e-s
z5Mx-t$r25EJajT-%&bc>&FS+eVjmeda!E71ZSTTb$IRAM9oFT`FLRHAIm8?jpPqKj
z@ai|F<WU6o$r`!Bk`mJUb9M5Kjlau_P6#H~c1>10y_AvBaS?E}fBvL4`c<~#6h)8R
z3wIVd(|4hzmnr`8$^5(Q2t46Dyygb_!`Z2#Gkhb}5`^b3&Z-0^?$k}4y?kRK>J;Dd
zz2h$W6*cRwccj;<lAisBCw)0<CgOi_uKn72*_h_c$07AKmi84t&3<H<$JK<igRZ^Z
zID@Nh#CmOdaDe<?MH+T?zBcs&uV05^Q<?B9sZi^#6&$qcm_rbc+onr<<#XG);j}~_
ziyegbX4F1=Y@YZrL<7u`A2)=wmd&Br!ltnI-ydMToZf8rdm{TfU~eegy_nWrEm9%^
zO6-<RJb?*TDW?=B24WS^buy!|+$5vvWWY<}&+?oY8mG^ZEBWN8_c2Z_Z%eN*@cRx2
z$udZ$wyrZ<k6wa7zAZeIY2c97vtSKRvhbR4k}#f_TUf;X19exOd;B5(N?}AuaEM+P
z&;G5F#H33(689|%ETDo#Q>D}9CWM7+*7bwE?{Y<=whsi0qH46OFVng<OOIcYA)WQh
zvY*a!e7-(NRRFa<K?a|Wl_050c03$pZW$-WCXGt$HPQoL=;?R|>vjt&SO~PFte&Y<
zo$kLX`-&iX`JP6`vuac4;o=9(&-S&^hh6n$9d`2M8|lgqKP#8J2VcID;%@r4N`K+U
zl%GY;%j&Q|l#eVO_gT@R?RHerN`HQ1!536A>Fp(Y0GXz$O!NOBCcS$7;g9mFZ!yzK
zO4H@7-cQS4zbCZcHy8Um<^9X)K9{Mk<<{);>|CQ~mJrWO&_G85_n%fR9%25cI{C?;
zf0kDcb-#R(X8!qEXPG-G`~LLvVRTQbn|#f;vTBNkIXaVDEG)J?R^%4?c7)BDK<x%a
z3-?g+HgeDHFaO$rV4ul#K8X50KGl4QylyDIQ)mbaEDBEkG+}-1?UV2e;idk0<rhzT
znny=p4xRlnW)=MBJxZ)XJR$ROOs-=FhI3nB!(!$0Ul)(@eOFZ;y+{;Ncjcx09_lS*
z+wqpXS$gzNW3&fWqcNssv+^70gGn7{BnAu%&)z+iiBHx>71Z6W51$B&PsNwEJr%CM
z<&*yX{m}mO@v9Rxtf#7)6%ytaN3MSfyc(WZp*}@W5Ef||=$6BnE718}jM%H)gG?t1
zzIH!85%)T$;C&<e$Ei~6eQnYNqfV~3n4dV{Z(J|2Sj=;}NV9?A?$j67G;p%&W&co}
zjTCm9QUeQXehbOx>6x8I9L4D`OkDfw=EycDd`9?Vta5en@iW#_4Vw0&)<mNai>b`>
zA4`SPV}p;l3t128o1&}lK9bv(JwGU6e|S;JjOp8${*k2as)^N=i|mnIuek3syy_C=
zKHykjw!QDih>6*7d{y1cT^D9+@b{?7w%ovAS?MiJMAMY0)~+k<g|?X7O|d1HQMe>-
zc1bVD@GhqR(C2n``Ded0b)%*s@T`8`F+JqgHnIMq39EfNyj>}n4UTH5vG2cjp7s#Y
z=R-E{V6U_(nsL`^s1KBYkups4iG_hGt^Tib!i&OfE*?PN+!ntu_4{S&U*E<%|3I*D
z963e1KkCu<6{UOV>CKa2PrrV{$Zl0GyVv9#J$A^%t0C4vHsGGZO4TFcKTxe@<<eKt
zfbBlmeShkif1pCoWTms;O5-geh1}|W@4<A{LWfJC#4pmJqeHi(4hB?++AUlDOvk5g
z-6@r7YJM5MGF!7)==0n4^G^Xo`zLj8vM+ocX^R(o>ZY+%(R%-jdcdvE%Tk&Xvwtj=
z_bz-MP>x_c(yB_R60A(eX$)=^NzDgW{M4Fmi2R=5;QVm1Rgq1QbZ6zq^{t8zdn`LC
zI)}p0MwKvMAf=H$x_Z?Bu@rsuzE;pTr{$N8N@LhL`v%+!9DR2niBJsNX6ngIk?QKS
z%yeb7byxH(nR+N`r_(;53JW&awx8_I3Obex;|*D|-JkD-*)DeuwYIi)`Z>2?yC0m^
zE%ZY-DJG$$>>FVMT7_ffv<cq_0!jpXYL!^ej$@)7;JApE5<Pv%B7+4j;JiA;%BX)z
z5yVxo9tij`QAOGkNYQ_*5+EeaA^*3-*JcjE%^QxrIEc-bJ;R6K26>o@!MK=U(RtXQ
zcJv3n|26|w0J6SJ8Q3CD3w$YEn#{Mw-QDTsMWPts?2cI&&S;4$6%^z`!?#NTen-%d
zt_6={3F7cSX)UN9ASwDL^<+kyELnGpQkb2$UBW(>V!1`Fk{oDLi34?8q-4<L)T=cM
zI<SCXM(p+tCjnI}4jC~_OeF+VG+HSB2H9z(@WR^W9U4kVmM#i%nIO0Z^OHd08hPlD
znEd@LZOUIwW0CwwdP%P?i|sQ_HvgV~%O>bugWaq`%%K5Ss%XjxNK(*~nGlhf04qsP
z7=XYfo6BO6QuJ-W>gmD$f5A~mi3Q3uFl*^xkZ}8$Eo!sOk~K7&!OH3o!rN`I64}EL
zi(rbOhJ(Dxz;nnkNYEu96F~$u$&!RHq(eGc@MtO;c$*7>-xsvJ&5<1eCydq(s<dQ8
zyC`0y*PAItZqQyC1Bm{EU4WY<u^<G4igVGum=&Cn7=^2+P65v*F~5LG?dFmPX;yPU
z5P$8zU^$-q+Mf*o)tk-n0@5IuE3}b`*$X#AnX2(=Q|$4e`Kng(%{Pl!j>2roW}x^b
zn{jr7Necw61#ptpU@9v-r9d16jZ9O{aBI%xo+a~HWcV`K_GXndTZTUnR&Lf4fW!3<
zB%fm;R^mrO0uOPewJ676!7EL^!f=v}_Ss&}#_f`<!cD>KID46!RUks`sK0<BbBj%;
zVE*`bm_jErX0r*#YWQ_)&JLtG7O^nEVhhENPG48N8e9v;DUjAK3!s~ItN6Wqk{C;1
zb>16;F1jl%lJ78_m8@@2d$^}gO#-wBoHE2l2Vf+)RE;eAht{buUICbQ;eb8+I#%FR
zmEv!(Fn)o=ft$O5`8SE2oyQo=PKe;Q1@Np*T93ia;oQWrUo;v0c^;1OWIM@h4gxn~
z$!bU3wsn}mDcZtL^a1K$9v?~o-dgICCHQo4bDtxEHSRKS?`wnUh#79*)*r-^{X^`;
zLvbt)2F&j(U7BAKv1&CcZVl!#>_op|QvNP0ngZp=^;^*8vMekCn2J41?{BuFq>equ
zb0S$|ML+>mkby7qsWsS}yV5-RI7<q5(fe$_HTptfOvwfYqW5^<bnQWN{UU`U%N%yl
zs>qE~Mgdfs<bxJ7?{&%shK-vDUR#zVL*UKLei(+d_3y?zi9VR4^N<YFNNjXbApGNF
z=-sBGzrt|)C=fvaCb<XX2EoHd!F?TI)A@Mn#M(Johrx!Fr$o^I56%`vs(k?80`BC&
zY{58jREiY=qrjfj$xig#{&$MO%9w&RF7LAZBoJ&+cL)-+?{!X-*(e<2NoGh?(s<Gx
zVDlEo@~|fjfspYs!FpnnbdxSRZO_IcX2j30GPx7kSlRL4w||ywu41XcJP#&W#J*nA
zSSk-`An$D_Am@X;_QH~p-uf>VsTL|K@n0P$N_}7@6;37!)<#m{v!v3}84NdA-g1z_
z|9eg0(yCQfKf$g$x4c9~*CC65TD2Si)VnPvEKEQ$8>$!@Pu5=AafG-;mn<GxbZ*h!
z{-k69)_1!E&lY`xZ{OTgim^9$N-KQbh{td+u^B{ulPo)fH}~MZ7>+6kU5L~n;holj
zp_7CnL%4Zus<yU1&SHwJ104E13L9_fiWU?>;G8(jBRSyBP3*&PV-(02YtX6}19;#+
zDSlr(Hk-=<sh#gv_$U5E#F7!r9>VvAg<F|{Y(oQ$`UbB}Q(G`cM*{mX$hsrB!2ha(
zGok@MLnLhUk3WTLY5}87qx7N%hV6mFp$y>VeDB>);$BooB7loW`BbUfze2lteh*X(
zIE62PY=9e5W0NYMc!XdaKhI<f^)H#t1z;|R%>Tmb`cG!p|3{D9S?nMnZSCkyh=f5O
z9S8|r@?7js#%dpwPNm~*-e9>dp-hpYbjpcSQh#6CBQbPJ)L~ey!~e8wj{U!M<#EcQ
zy}%E~!5aRJVT)4hlwlx*ajd{bK|bkh$Ix>1D!Q>M$n%`IsnWd`Z~dj7s)WPi?iNSw
zn~CyfGk0SR@8SUmF>a6$bw)kJRc-U)z6Bk)k#bOO$RdNBd%m}-?$zNy#Z<@l42c%)
z_Q1((e#bf7=(SXRUE37v=cK_eC(Z68YOt!N26O4c$}d(J?~Ou(BnFgWR75K$e(0c3
z;+3g&>s$}xhrW0GotE08J2Db&+yk`ct&(P5BX-V7mL^n{z8vYWzsJ7*vZ=N0FZ;kX
zZRDZ1vyAlDRqgRc`L3!{uXwLEX&XN5b1rNsDbjsz7UuqV?tNJ6hSapF(UWAn>!s2d
zbH{b%?->j0LMrOfR-Xdy*8rom;M%#-wpERSGFbd#F4m&jCp>1Z?r7k%f1uRRNz~<^
zUCP48I-<6#gRRVN=N)}qKy%irYv^yZde8Hj#c3aM&b-bIftiS?@!Bz;XjX9P^=TYX
zKIE6#^Hr?<pzHoZg&Chc$`gqJ-|B^3uD_M6qesu=c`v1})s$8KmDow>@+Ijy`_JgU
zXz2b*H~Ln?bAIQld-IPhHM^U3xv4*^9Pic(f7u8s0*9<ujJlh)zJ;jV^hDDr9iew0
z{&@6X3*%Kekg;wxAijI}w|HM9TRcoLYbsD}zIEZu-E1kG2w##f$I)COA^PT}Ve56n
z{X4p@Ykq`@`#;!@S2ma&n-bd#9Cc1}kq$A{D=`z~r9*5<tYSx-a{}fK-s~A0wjhXP
ze<3Xi%L7I;-$kjg=CY1>fbF9*RkUfxlFkCK2|)*7Il+fW2N>!Aab1Ptl3B6>tvFZl
z71!ehivqR}-#ch7$N%Z0vr|6i9|#$&!<OGqn(p$ywlKAN=tXn+vzn6&Iq5SU@!{?#
zGBqU4Z9mNy%CF7Vmo1%gJ+N>}(h4<_10O_73Jk8OQlB3=WcDNaQZIfm$7{5b=v}N8
zTihCE48C8Irod)vvpZ>xYSLdjQ9rm89@46^ytKUFVKg;%Y{+IEzV=1>Y_6F5iniv%
zw7b=*rBx)}8euW5tty@uo^76?Ho3M97JL2sV}1Oh13vb4>yh!BE4U7L81j9?R5KSp
z{10yNVI%!Z`qG7~H<~ye$2@ZklKt_>Axkbl!I_I>t#BnFJ56t>EZ`!aX7eefAm42c
zsaV@UK|A)qE~$qqIbkqK+g2;jr)>|Ir(2XJ3hl6qwQmI61KkGP-0h}qWMm^!HfucA
zqTfCYIypPN)Y}@_Y<|BrL;t$?CGWY~JK;gyc9e3mata;q*LIZ$6cHL$7=Bj%5_HZ)
z6`sJ|G#E6~Z5v;%eonMSo358mkCHsF6B<9cELJlyAY)UNuGFwQbgCS8O8iW@a%zu;
zX+~QF?bw4W?E4I{fl_$OBwNK3h59&mV>SI>boP9z!gxW(>j8e>uh_eZ(&Z8XzM(0d
zWv84>IN8j4ZFMFJHz&haErj5Xq{&2aCp6cUNjl`0X_aX12Hgn3g)-p1MhYD0ymmDa
z>2>o5JRGpc2JQnv7@-XwIwFh5kZ$_f`H613UYIPGk7w(#f*a==pS-Sj4!q-fS8C<S
zw0P<zfxp6^+T$MYe352(K0oAM!R}$WbfM`DmueNdsLl$Xeyn6lEPds#X7Iy#tRIQ@
zNjM3~?NBctzI5JI=Srr<;`JL-26e2Ri{Ik^fo^YhG@rA+j^d-o9LtrJ=+-&9eY%Zm
zh<zj6k{Q-i(@-J4dZSKCXiPM?>V2@BeB5tBU&>pzHgUuN&FKm8J0jdc(Pm$sO~~Un
z(V9o?nkG6>TP3GtkMlCzw}d6*JkOlYdcXhln<WYT{fAwK(cwe5&31hwcT&odjl$ei
zm4WZOj+z^npFUep&3>8s-Zc1T)a*hLe)p)``s+;ZM@>KRIR$SIuH9Cj{v#MT_m%&3
zrsT7mZuihHE>FB%5v%%>z<9^JmSQtdMK!z77Uu9q^3#y{w-K-7ujfuh*Vx5Xj9t*f
zod|mos`@c>tMW^*2}+u)YhL$EciC>7B2BHs$Ckfuld)A9U7t#t>AH&Vpgp`#mph|)
z@8tJ{h`Wa}f2^Noyq8c5K#<Q}^n$-}7ynp%@(yPT*}IJv`gW^4;rgk-WT8jp%ik<l
zWN&neeAJCD`nHW;^}79CeK5t)eX_DWE7NVL@MxA<?Kxr}^YEthc4h5_X9qq0N@64W
zwS6l){(&U5=Z0zfhpAdZP8=7IVoy`e^p$k&iHE-{*>5nNnlJPn!cXRZi_o%iY<~Go
zAJ?8ERW|$IxO?+xs2lk2`#S~`St?T@gD7U|N@SGX$YmSrj7muoUCdC*&PYaDr^(VN
zOqR*aSSl@7T&XCfu~cIjTd5QZlO&85(e-@#o#+1Jety6EpZmU_=RW5-C#Q~6qxsHv
z`7H1E>s=IKT6EiQ#fhECEt-0gyZps&63-hW<yA)WGK*VkS)q)(tgYq?y;5Hvpg82_
z2bwNKUXi$Lafy!lUS=LE5nhyhR5Wng-!RECT<3~kG%F0#Hqf)`$uL1-tSmm>!)BQj
ztrD#;b+{jN_@61a+NSj{>y*kGqf0A~EOa)1_ct<8zc|vp|3=7z@O6xl+C!^$d0i+<
zfA=NwRhQd8i=T#nd~tnm^NNcOFTL(OQ^R<@ylzdH;nVLMHoROD#pFzSP4C~p-hA{z
zZ%sAXisFT5*>B(bwEob(*fV{%o}Q&&D!tV#B>!Qe)YLQ|DGV-DQL`g#&FH`SajYaN
zwzVu!x7P1hkLSHVn<o#74yLDz6(TNZUQXHZmr+i}%$*NZBkq;t1HGpyBt)$y@c7K%
z+<twBSfip33OI$`QTY}74eM7de;QRA#b2(mfjnCBrEEAWAYpONiFV<t2+z=panjyP
zI2x|$#85GBmVZdAeCaGt!4@@;n{{K5M5Tk|`lPOv5K-P?=c-2~m`!-1vplJ+z~Byh
zSo2^rG9juOmZFt{DOqWQVd|t0BUDFnYd%$a3JSe<`>DayJ3?ZiFUq|)L&mQ{tFWhF
zDQu9rK)b1iqq~wxsTDkhH!M$1FURUDzdV41MY;Mgpmmj>Pbw>}r@M<*m!Z5Is&Hdi
zWN9<Q6PVIgLdEox3RcegT3^f6*8ORztct4;G_5YpE~M&utv(Gkd&;kEMaZPfXF9W7
zhzw=5afnawwy+^Jwh|JbV3i?$O;LT=m0>+R*D1+Yzyj0uZM{Br6gok?LAD~Er)J4Z
z=|F(UvS^eT`lXDi^p&4Jz%pkAqi>L{JG(*msEl_AaM0cgCApxDrpc2@Nf=_jaGn6e
z!&JPEGQ?3saUCtm{7&QxHF;>v9b&lDV^(XHU+60r$1AClmuLs;WzzUnSVY-D+mdgE
zMPR9A$%jL(fOE#(?`)zYxerfZDu1VxuLc+CQW+!&;hPBRI$`Wtp?pFaqF`d~Y~&2~
zUdA+CRW4hJO#wpiJk2QmoYbQ@7qYO+z=9d%E@*%F!SUT(hdxpFLA8ch?-5A>AmByL
ztIxJs@-6v9bURrdi#|s1Av;O(7r&h+;Nd4?Lo(|+#{u4?U_9vJplm)1i}x8y2bDSt
z)H}HhktV!yQ6=;EPf8}NY|kOSkQ(0ETCU=oM1*89>Q9O!69XI18$J=fZj(Q{9N`mN
zhW03S(3SOw@o>;^3lO#@B2JMMqrG9B)jlI6E+R(}noFF#<nkM5d2s?ren#tbcEkyd
z(crx;24gQPz?=6|@<oY<#+GwH0Kh(qRe`8A_wT<U#5ie;9pNq<#wP?GLmT3kHOtdU
z2TEXVX}pG!0-&#qYO0*85Sen@I?4(<1@!6i{fStlphak<li?EGvD6Eq%7%^djJS&U
z`B>+Z1S{e}{ue>%V{DulnE|Y?0JBi?oQirw$K&j!y!iKin!Np)z~qY45^I4td}$Wh
zY0lTjQxXkUTzYg%S*EK@*cR=kfJUegM=uYpB~ZlU__}4>Mwn_?^5v&otVS}UK_FZV
z`@*W#!&0)BJ~mEPR!oon4y_jx#r1o{LuHm@b@50u@e~WMBU`{DPcvgMV7e9jixg5d
zpqrz(q>(q-(N6<Mx{^l?XCX@MWV3d=3Zgm#QP^NygPRhgSL!4JoU9p}AZUV2L7N+x
zboXPbnmQ~q62>o+U=49_^8_Cvk}||G)ExJaLStl!MdTD#gZs8huNb!I82DQ$TuK`q
zVkr!m*kXJe9ho58f5Vi+&;Z}$yfMJLT<0hjiGw_^@01=!2g1<y@fr6JYw|*(LGmy=
zlAE5H8)_Rj*M(X%4m7UJSl6k}EHa5OJnl7_DXX{fwYx<^G>JNJBdIXNB@vg7law+`
z+SsGFhH}+j4p-?5;Mj~em(j-i^8gj69_+11XH-~P+F1(bErp9S+EBA)W_HXG7F8Xi
zHA`fzx~_`I2j|R-FgF-`?uKUKU%jo8({|92e0v{~r-cpA<O5&c5L1kw@J8b*E#c|`
zP&OpS?PqX9m$2i1Z41du@Cp1W$;bhvZkU6%TxLq=eIRqsQ8mjlZD1zRn+MwYMx6w~
z=+qpQ1Ghlm)lT78wMohC0p{&NG+Pz$MR+qLpVy?O((g{X-v=^VLQL%l$4X$VM^@rt
z!n4Sp(OC?~4uF-*p_{!Q4CTT{Dv1xOC&-O{r=fPIw==9I3RqMLG_FbCWPB@P;Xyv`
z-W193QwROUXk}S(bu0_I-<1_Y!KB9zUpd_*5uSMRV*1Hg_uf36P7-Dm!pNKvc}hP(
z@!;L{vVTX$Q4uX71%P}eGy#PC5yNYYey7F-CeTD%Y$?U~#VkgrdtoOS;hpvMJK<Ho
z2?Z0t(QoAX2(2L=4haDVwChnkBGxL+q#*)6NI^{SAbQA!l(-=_2%2G{26+A7uU*{+
zsfIXbBRWm<KT*KI*ZaTxJuwz?0sbey9JMq79zX|eH!P^x+VTk1@0L59>U^C}XSrqB
zT<Eu7Z{M&(WT9%m+h1#!qPpb9(777Qg`(EzyBz-5KU|CRj}9uA>utvP1?`<uDEXyv
zaAQkg%in7D0{`1fMX`S;g{;q7nilzHdDx#XwTH{==}I48v&%6ZBlF=y*sePBJ5g)0
z51^SxYX*l&-JcJt&L_0>&VM**im6ID#Hw4JI8+s~$UttDCZ>ILv+*nLc=cP=T~fv-
zdZ#}A>K&siM{c-yhO~2KhZM$x49^s|seZY7Ff`|vh3rs<3@=kxe?-erxjK`Y(zCGA
z<)6+2584lEZf{GfvP~Si&0$H5o^Cj;h;I;zG(};1GT>fct*mH*p8%2mPHScR>Qh`i
zijLRe28J+IsG->EY86jv+)$A_5XeKZ6tJ8`$Yb+|^04_l5^d7M8MO}+5P-+3n7Now
zdawfI9_y9SP4BjKmIV4$ln(BDNZGl?UcF;-?M3>v?PZ)vw<j0>MaKOdT@-9iWNplN
z*PCPT`cmN}eP@$z&WVYjw4sfvxXtUIY3{2%q(7ngBSU%4RxL97;hj7GBFD=jt@teu
zod2?kZ8J@~pnq$6^u^13m(#o2l{2b5OgM=L{3lklFR@#ES+6S9yz~gMBQA3CpZxxj
zcetm2HDP}$*AM-RC^ZgkSktK7y!>$?e`0~4)-1Ny?M$nl_b7i+yK2paM8z>z;4!wf
zEnd8HVq(Z`_}tbL6xNS#USGn5hlV}89P&RKUP>!qPoN9?I+Yh~r^b-p&q>@u|4t=b
zziP0_^6AY-*tvDblfC)x6n$_zpOxDfeE#WlKW&j>y+02vVXKVl%t<6@jHrLh*U3}Y
zH{_tb*v%yYKQe+OYq~b-_S1T|I2{vAuODw4sY4IRc61~aJlXB^l=-kX_e^;1%RLd=
z&YdM*_1vEOKcYwurx>X{6K`ab(TO%*=J8=Ty3Uc&+Oj38e<g%%&p~f<R_?jDzA(Im
z9I9aap`~oo+PN-cEp)%|hoRq0Z2wi8^T}3a*-a%3Z&gFRsx3y>l+Yo?Mz6ZJ8P?!E
zOL{qS4cVKf=DM`<i)HW9{WFi|Hd*36`XUDfBiv-6ZI{^&^o3jQg~h6tDiY-W&0Vpx
z<-w@h8IBLie^MtkBB`q2p4`!*@z6$Y%$_9HQ>}v+2erK(>^gYAQrO{Dob|<E=2=~B
zwb|C64-P+pG|IW52kD0T87+2K^E>MdOJ6n~vb7F>8P5L8&1R?GmEy>93e&uG_UeTT
z=dpg_Mc>~xByfcvYPxrwuDkNLd=TH_HBe5qgGy8(l*xsK$XzE!yo*8>=x-|T{&UUV
zkNy3O;MLot1dmhwoLBQxt(lI?KlC3GB~QruZuZEk>$6rRHoaP<=RGS;TUO(dvR74n
zAk2}-N13<TUzj=3(0D$Y(?);FKfd(h^sVrq?oT(O>crNq6Z}JiIWwXVrCsN|j5L?#
z_?n{YW2|B$_MAB~U^Q}SL`PPU7(B{4Y&DX<LTLx3-f8K$&*{paSC}cvOq~V0i0#3A
zE1u^~7<osW!y3lTOVNa*Zeshub-o5gV~Rlnjs8n)UK=LbD|jaGfN$IA=L#*OYj%R1
zjqN(8N$mz_vF?%K_QFK$iq;YDQQZ2MwuC|4D&O0g&D*=Y%J@ruXzFNW4dJqegZ2zY
z9<P~Fz3{x!z@@6@G;qsi*ZwW&J>06>r&71Xd^^_sxozTLO;>f$TL0}1>vNUgmM?#A
z<CZ;>!JS(_gk5iZV&vEKWkdU#nfp`g54(7~q^^JQ=m^GQPs<Bj<DK3z$La1rOufi;
z8yHJXLpV8otQ#?R&)%ro*@p36r*+b|=a$j-JHrNoBKN><UuK;OqkFm-v%Iahtcrc7
zHif=rwPm}(y~SR8{vw^yb9!|Ba8_=7*-3m%x#B&;4HlbnqY{D+#9T%fy*an_E5*Ua
zC9?1om1`^K{z_6aG5cpW-co+9XDqBc=fF;b=_?8hb*2m~spev@9V42pmgme)EUZ7y
z8nMELrw`PJ4%RWHCh31~KYcwgw8l=A7HQ}4FY<-;vc*ACR(H=q)*HI8UgODwC6d9e
zHQZI3u3zz<_>@+axZp!tZ?pIG=Ch{pAJvzC@T)Y5OL)4jxxH%Dwa8YBrBrhf&CSVN
zFK^A)3gvSHJu<Tw(}Eqgk`tr7<%?y)m+id;Yh$dyinV-ybMfmg&m>EMylo=DbGf-?
z)?I3@_2^Z-r8%fk+wQv~rCe`i*&GYG(wfniMV5<BceJT|YBOAAaPs(Yj>m0Gjhmut
z#NoY%+On5kp$?~Wb4?Tp%I}t$eWz-+b>|zDWPWd=8TT^{42{^~#4pK^d;<KG)%TOe
z9RuH?eRNpri+h=dg#P@-FO}}YlFKnZWJO};5O<(j(7k^S9)cStyo@qHi5QAqAgJ$U
zc#jGp&KAMeK7!z!$&xlE7B%jz@8@Wg$3+6EaYDhoNMEg}Qb{Hx4#*m|+DT36PrBTB
z^38Vzfc)Ue6=iVgLLNr_aiL`yGo`EH>-<NOHKpsaaMG<QyNSCGJN$`mo%Kav+FY;C
zH_i$`l`-*}GO)rz=y8bp2S=XzlTJ^Ce-YbGSF9g0!m=}SHdA6L4IPXAg=I#Ql$}*y
zK@jl~YOwyet9Py%9Uz#qRFqO_F6v*TmybmX<&uSy1KCrK_Ob@0Z>20sVHawpt>hQ5
zWuo2W?P7pxTce``=p8YF4a*>vp<Z!Bm>-?ujeaaAR7dBdaTmHHKyWl_aAP>|6`~*r
zn$h`o9?x@hCF&N9jrKFu$EA*FTS}V`Q5&(sE(LcgsPD{*b7TLb)e6t-MkwDq9eIdv
z+6BF51L+)31wHa2euZGP9zk15!IJ3b>Jy>3vG;s#D&1OwD$BE#%nHN^UJ6Fyf|2Za
znQ-zI7xC+7N4v$2yD|_felbW7>CDh$;2DHGUM{k?nVA1bgk+4nSiOrTWe`&+b3k<_
zU<==An?oe9C4by43Co8F+yz1kRgKolL)*(@#T%n!!OFqL5UZjdvA2zlA}O%}t}Mw$
zl>}gZ3}s^iJVVF5Khn*>B@Ay~AePfBWJogDUG};B`H}SViE|V$OmD7*oJy>#)HSvj
z6o0iXWjUO;+-O5A+v+PXG}aZCj<A|O4l&v}?PYiXrb!8mVIEMLKvsP~5`0q1`b~un
z>JIKu#}+&ip>bSq{*4cAK9KE;K$zx3Z#ppUmy*=5s8?8Yj%!)~NiV>%i8hZne1%0G
zbTgxSvl#d#^$V3Tu7M*Q`)=TFVLp8O-C)0`p410?&+#0QiMe}&)Fn+l29H<@(TW_f
zZyDN|0Ux<-(eR95PT7iollRBQL6K2(A2E@q77Y<ovQ~cA!`^INOaP^Uhrq&eR%(+<
z19@=0Pd#FMMBCR{-_l-o7nW=J?P-tmbWd^;btDoL26B9&8|DcwCyx=#GT0hG2AdTU
zyPCgKzk=5|7*xXTcDKnu@J7(S?voH+)GBCq66xz~^4Aj*Gn0w+KHn)M)n@2@DX$cn
za(DrzPsT3^qM=;(O37+2<`S-z@LL(=UVVeCT}2R@<7kGnJfw3VSEWz}>&r#z_P=uX
zqa+z!*J&SVD4)PkuIDg!tEH6e3ZNpiZJM<=xH<E_@X$!s7hb$b-*U3O21i4A<C}jF
zix?DkNd(ErimwaX4x1V+Kq~#d>biaLfIe#AWfFX9G!>cJmX@$!t(9S`j}nnL)x6-a
zi@@%}+^E76qqFMZ)aXq=(*b-c>#kevhBt&pb`>b0Po+Wb{;7eyTB0vH;Udq(KBES8
zcT54^qPc{lm}eK=pEW20G_E8sy+b`Bq<DeWZs#nA%Vfmyty+naRJv1i9}C%=7O=@(
zD!EjcFi&gmBR1LCnTd=hgXvbr^91!lXzUf)Gj0xKn-S(pEn*nwJkX1ap)DEhztrYX
zWnw99fn{L05YC@w{Z4lA!y>fGRBw8NaB&GaQ12J?HgWdVu~3@wX8Ku*CU$hQ&k!B&
zSX_i(B4GTgzLfk;XqO6YDq3fTq?GP1TcD>wt4(@hR{?9Rard{NbkLP)a7Z7$@%kZ5
z#A>`msA-hWfqRe;0Q$$9tV5@S?<L{r3ej3*<57AvBv5)6QWt3GPxmNYz}&jqj$8ks
zeVaP5R#5J1W|k!cI5G*VO;AO2wDCe-2*q0fB<9i#xc(h3tQMB0o7Ik7JP%kX2kod7
z<-~e341;WH?m>Edo`qimCs1!@_sNY!wOo{k<k)c@q==z`wJb7$%?t_|y2yc54MK<(
z=}Sp4PYK1UrT8kKf+yX*MQc&}%t`zjJPxv#B)QZf4os#ju_!VqQnbDaAfpJ^%ZiEy
zvwSzWy>r80A4&qS(|`83{(tZ6<rTu-b+y#Z*>c7W;VH`a*iW(USqufp-o^rV%{tl{
zhv)5smQgMgXE{gx`hN#0{f16^hH$|B42lP}T-cxfmr306VZX`M9<WCJ1A52*{@q=B
zRkY5gD5%djS<~WPc7+XB0((^*m~aH(<@9bpHaXh)zP#klp@QnD=CX*0-%kf1iUDEa
zVt)d%`ya352M>o+gBk<G_57-9uBsY0-s(Q+>7x%2x-2%V+1qS=<@oEd<`KU!`X1Et
z@idJtr@O_y<DUC3I^>$>FY);h82_sTz(vcXGZCDmbHxj%3Je}}I8IK-1L2w5_qF-7
z$>&?sc{ZzTLuyC+pUm^8D>$qFUKl%ORk-`^dD9pEh7}dEv1`}kQ<7>3^OrU|*mVEp
zlXv$Fx?_8?#`;X<ZUgTU5yR+2*&?Cj&`_;=Qh&as?tA|=qgvm}v+jaC{_)kj2fIHR
zY>6!i2;Fxw)+yt@W?7DC*Vd3+wu~o78%r)jtR>fDEcrTJJ$iO@(>0Ed?BA?2wz4o)
zS$W4oV^+W<nR_r*l{ZD~sf!cuTw*YJVddei&sRq4D1V#899b?Y?;5J_i3*SwIc|5X
ziF{l&NWWfs#@{Mh@}TvL_<q3mgf=6qzs|Ty12!1O?Cxz|9{Xi?<Ai?7_I35$+{T+<
zY?5|2C&Uun*9smQ+@eeu_e|(-i{0IPnCEu)QH!0(vaNla+DcvCK}{(uUVjxyH}~$f
zm!%y6PL4$OVI{kYtvQWJ&;HDK(h|Z=IQ8j0@NE0qwZ*mn^q6emr?zSwl=n{_o`{(~
zv?QoGJg!x{WW!CL;h+=)E6dRHHa#IaREpKmEJ1UoB!ERi4Oi_hP<DC3@Q*E@w>X)m
zdi`p2<)*t?M<3T}US}MRd2zp(_Uab-8mV&Rgv#@!tw@ff;O1eQ;>X2}Ml~lRD|g^S
z!V^AKk9wT-5O`b)^W1b%^-b#4Lyzxm|K~E}nNiu-yogu(w(BvfXD5{+58r<sbk#N@
zL2xcTC!ndQr!`FYE#2sn=P8P$N;~A;p+yCj*ZqAvHy$iFe$&=fvwt`$Qo2{}<*JR!
zyIfw~zL`3hv3pDZ_RLaV;49bFeznW26sym(5_CfPZ5KB<EVkG^L4CWeJ9Nd@&Z0+w
zF|egI`%XV}^<~o>!zFJ?;U~jY3%7$#SKQ)l*Q7{2FD4Cc{rnNZf!bfx-(0d=I*0ih
zA)R||x~B5mdFt}?IhMz(?vA)KYG<m}yDFRQT=UAvE`2=k&J&RGZR0%ScthA_=s&TY
zCmj~HkKCin%^F9BMea|_|7>3e!CYPL1y;rUw2Hv-qsvn+{mi@Y^*q+7vqYGTYcO~>
zZ23CbsQ%K<sg<WT)af6|8`za_MeY9S8=A#lT~R@(k$Rmq0cY<XfAgZ*_Uk-B`t+BD
zhR#fu&|OdNeks)IbzN)LxH#MVi}ZO#ovc}l<tTq2DoeZXyZ?-tU-<f+c4Ea)VpG6{
z!%8B<>#jAlGy8D__ebw$$S#ViSX9XRR=&gfk^47LN#(n0F77<Ip|oIesLIcTzG4-B
zzjt&`#xp{clFkl`qIaLStth{NOA%?{sb5Vs-YhRTH7cU?2>QZq=6vY=wlQwS$C`sa
z&qPi~7r(GpuS!0AiE3RKm9-&7sP-sx1cMoOGg(q>CcAc3(z&;-WTLR!z(prE=+oM`
z<iF3{yQABvD|>LbDe2l?iwt0HwjYT%xc>gdYxD4%%e8XDb(C9XO0x2)T5o?o&fnQX
z-<G&sBhX-uE2i)KR`ywp3i*_mtP_7lZ1nkVSy&!$F>}wSdhPTpOuRCt81bI+E^#DV
ztr=%V(!@?RG!bCi>$_4bGg|7XBP$<f(Z}5sgJb)%(+h`kN2`oznuWeA$63Bs6JEy3
zHXU-eQInn<9!)xq5l*D@<c;+f7-zD^9iwED*k9NN^<MtI406+@;%Lxq>sIH&uSaSQ
z0p4$D;}Rxbd!?P32bYvIl(o-IVH8_`PjVRFK1fpbGBS7PMjJ7gu+`{-nSsJ2Y!?ah
zL%gLPu!N9bf$mLrw8ZAOM=0WjI7rX%MjKbDIGwP`cr8&omX|}7lTCOLhdtL&HBa4O
z914t~@6ME+${{r@yq3fk%g|(oHe&a)gAtD{X!t5D(|^RHyoDhoH^8wwIKDJr*&#0i
zgPQ{K1;tAVI;BZ>F2z&68M~D1Q@>UpB{DuT3V|zb3W}T>Jb+b@A{yV8!V1<qhkq9@
zXs*#}2jik-D4TkI5l?>n7m+$_C9nm^=kMrAuu7_v_X^jdg{#jtd1<u*+!d^8mI9%z
zWQ!k30WHLNVV~%XuysN*yJOu#bcXU~_?IVK%t$C6#q|MxNx~!-FYSktcq!L9)-?i9
zA;VMr-`OSUfWr}K@s1LgHqn`3S&dVIHalrDa2vUJem#06uaqMz%~oPz0>SZh%o))=
zmK!WNT9!A!M6+d3OcHZ_QEX^%CS9UQiZmX@Q=wI~dbAg;K#TCwaaXd<3=m4DK$2w+
zrHc~@R8<U$oBTu*-4WX1db||KAPPpb_79#4(A!ui@VSUne`d9|ISB)0E4E0%#8Mzf
z$%^oMG?bnBg9ltt#bXeLnJ>cD+tKSJvQ`25wny(JZXkPqSo-3O3Ag0t2qnJlFc-0g
zsw!=rQy=F$$V2lX=EO=cN6Ex5Sr+TqMz?CR@jE>NTNd>yY^b3Sy>fo!JR1ZI5Wz6^
zrkxx#uj2b#nuzd?GEe56rz7!vp}u${6_4mWWzq!A*hLA5-91V>iH_;QK0JZo@Dr{?
zD2N51fi=QJm;p4kkkaIE!H5y-N=5>IrH<(ZcqWW{bd8flVq-0tKqiz<l8|@QZ@SfQ
zVF~zYreP$zQ^rr&!Bhd-t)*@^U}HP<RVO^4(5&|%`&zZn2+Ul)PZ8_AjJ>NfwB~*%
zjSQtXC5^C$AA-4+g*dvCNsmS{k1<t7vZpPDZR%vtDL15;hD5(k>HO|%lL0i{EXN<d
z-qs@-Vw?h^sW~o^53M(5*Z@gL$M-O}uk3Rh%pIk!RhS!4DdQfAF<QhW0Emfh4p2nC
zj-<EI+U-jMe9bu|M1~t{f>P2@4t7~(bF<}oGa_Ov31x{DjHFBQbh{CW>%Yhqrlp}}
zc^przeheAm=xt7|^wIq>>7JA6C_wx(Y5g|wd?;mY=Q_}}?P)^2Q})$wUJ7)wz)EOi
z97RwPv^xyCM6*CFI+P*a0xnnHtbq6KD=!4NH=KGSAE>zRHuJETZ}(p+q`ay}2v&S!
zoYcX3PrW$_H9o+pw?w<c86(dZ>b?|eY3jh{6&g7|x0boCXX<1-%jRK{sv&2-Vtt8_
zpotYEU>6<QK9Yxa7<4ukqOmHzrnJdP7n_dNHjJN;Rca{}BWpF~yRv#YmP1Sp+>EQH
zaLjy;@`{MO{<W=6xAbE66iKd(5hWt%#0_P~3qRpCLBm`=Ep#B`ag7xsJnm+!dq?M_
zn}SY?wqsX4ra~;2u2fu0RN;^u0?fw6rs|L{k||?w17TYzXmS_Yel;G*kO|B%RwKE^
zDYCN9#5#>Wow%~qZkD!RT!osGUE}VrsxUbuM9YwfV!GZT`+)-ZSS(2|ES(i3qx3!q
zoF!36eC$a~x--yo5r}%4hY<$SPOK+@*H^QCOzNhJH-x@Ihe~CU5dw@CK)a20jj$|D
zhlMg(LG$+{1Fl=^&Vk=XXL1m@f1^n|&Bz1-iMP+AP}!5>=v0AacDV5rN;#HTZDcDR
z!&MTavjUJrM`t5i>sMHji?sOmxri>^wH{kk%lpIRKiUOBbJc(74o8Zdk+rMGz4>y?
zRj+zk(OMHO0M!}DTSHw66?d#ltUC)XC)g*wm9P*{Z;lGB|If2<&Hl^nlh(xlCNXHi
z2<S7X_iDY3=wo!fqW?4fkGEWMV9t2piW~g#{{2+1*vM$*oRe0A>2v;)150-aUTi^i
zn|K}GyW|L^%u(PIez*TqW&b%16}=}rVop)aM|TVU_<{LyWx(n7m4ya~V|lmZR+dV;
zv7gvKUgM<ZuyE_2x;caD$2a#EmGsw~+vPnt4N$kNrrJsE?=g*y_r_oBeEp+hWrBPA
zVBp<ikA&%=+VeW`D6z?r#t|a>bK2>`E^@<*m!bXnxQI&x49DO2!q#OA_tXRaCfa<h
zS$Sw*%*_j`^_&kPo6~L6+sb?bPVj7pg|rht{yDg>opGkY<(1gziK|e$vcI=nw`8BL
z^mTNxWtCmzqkxB}1dA)Sc3urt8%E2nXAMRP`BHnr7VT@LN}IE8x4ezhJtf_v*W{pi
zy)2u4acJdn(`@fdwMhz#{&$uh?V{16;J4%)zYkK@=`W@+5h1T~4@ZBbg&2mo3b#J>
z*j^ZqeUp(Gfn<EX&IsOq)>l%Jqt)<nN5+!#Zlyock_NpaKejJQa@hL!m)V<{O-h@X
zlk3l?Y4<9B96B)VaC~#Z-`~r2MxEcJwM7ucoAd9y#dB8XD_bHv<cn21&%I8(*!wo@
zF8jm&(>ZgA*H1VppfcSi{f(;jFF9NP;vH(jQHS9RG6=_;UCxT|TsnFAZfdrT9=U|u
z*1LcDlg?buz!l|BZ7I6Ap|^`8E`IB?zEo;gC()RWA=%e7J}qcnF1vA>IC}5P^PDFi
z&&#)j>G-#OqgY*N*z+NOy7WT4c+znB<ukEbgjs$6+i8#2|51!mupm6G*22FFEx%*I
zKB~FEZ|wYdkz@Wacg^&R_{pFGp|o$Mz0%1Jw%6KP&zob>{$#aP8UFT+FOw&uY#pza
z6&<?pXyH@-*!qEk_A8PS`aG7bT1$WYFLJH5Ez<R|z4GlZ)oLwAURA0EZFO+m<BjLI
zkI_n#9U9+a)@GfySYNrJ?-|Qadw<;MzX(Jg+~JwrPp197<ev`vZ+q?zxJC?Qt~r~~
z(=^P1=dAC?$T%wV#qdu4Hp&Sd6xA1hO}ruaiezX1GwbJHR%geBtP@+jq<EMiYVLLw
zq|U}8lyjFJpO>f1m{KD%yXH4W4^FChCC6;<uDp=Vo|uokGIfJ3yPD#D;7IzBCrdu6
zFYbFd7_?XY$@&YOWs?1w#wR*2n%%#E;e8XuO9BLKg!(<15#N08)}3uFc;<55O|#ia
z6e`wV7INJxtkw7rZ!h0kJxh!6pBBq6vl4Zi4N6x1l^P*;ltOjx=y~E<a)aU2SEUa-
z_2__XY7Qy?UH9E#sb_A;p(@LmV>fe36*Q%O$DhuPTs`Kr{Y4ADoK>4+aP`lWZ7${m
z)vOHPIwy-AYd4+0t{VA0C~0Ee3EeV?jy@le@i=;dy3<+XV?w7`_xsD6jzhOASBdhJ
zB2xB#eNeDW-TK$^mbS&Q+oO(n2v_Y|v66d${g*-L0^w_bOOe7gFC0X?<3tL(_ugyS
zp72w7s@ij+x0xLgBe+*6F}TN;#Xq`o`EFI(O6T{H2eXEB(sz<_Ag(0I@MI*lLswQ_
zF5$bjSuH16+{%9rn>^Y4e#wbPSC;D95l9v$on%G)lIJOs6C)*eGIM8jI#!3AwK%A#
z;F2LH1T<qvq3Z$3VFsw6+Gv2IBxYi;pSyc4jSD-_>bkN5-CXUhG;MV<d&*~x?(6OY
zZ|GQyd)=O|wf)l==~=`@J8b>bA<8}0>({pC;PC<0R@%7RA9^6c@}~P>RXo3f^5hlq
zH>DB<R-Ggn|E&y`)5Zg!5y}V7K5v|C?W>3pZa}t_OE|zH2iO~W#ihayFD+h3C=ucg
zq~0*&WKqUhn1OON`l9W_c9qd0BU3_5DqY31%N>Tet>bPX+E$90byQz7f@2#bv9;H%
zw&I~7$K9$lvxsool<q<jv<Ijgr7zCOVqiXyhFHNMwduXc5t=FB0ijVuL($!^u^C+N
zXc8uXoapBT<^&K-K;@;cR+?EI%eCnuX|>9*0tv7=k&{rygGNUgKf;ET47&=1-^(5q
zYQg-sKkG5ePqg|>Z?4MJ!1+8@FvP+ty&D!1_;()G=qr0hdkkb2Ntx=?c=R;C61XJC
zan5?Z>0&)-E__|^;??6Mlsp8P6;l0BKA7Hg*Q2yCYbwfZ2y)7pA<Px&y(}kBWQI(z
zp+aqmn0*fer4tu~SL3b$J~NP0A(z4S#kbo^G$ByqJw?WcfpWz+z9pD(epMr{B{F^&
z3uQ+`zVajqLQr}@BxTl&SWc~)BH>sOn>J|i>)~kkvMI#`8{gG#ZI(QB&kj5Yr(A3#
zG8~~AT`WU<y|B9VW118$d>><99r_QAnDQ%^2^4*Y06!UTYf5JZ%M4;E@|6m839;_v
zIx5o62t3cA9tF@U6Znv_2LrN#Ar@jo`CamMk}|kvT=Qlv-Z47cA;3D3Umk&x%U&$W
zXbyGn2740vBW(%qC#9ItVQGId6R#OwW0Fe18>_m7Kt*qCOoXxaZ*@p!(HMB9)XFk*
z69q=uYVBC{D!Jbn*RbqmAQwz9gP#|YRYuc$-^uPk4X{-xF3yM!T9Q6rK`g33ky?d1
zYOfOn=mFRXp(e>{DU!5eJTF*5zJo#G%3~9GDO1h}epHAvb7#+`(qm_VL<yp??xK3a
z<McDt%E(ae`%IWu9+J8~Abcl=f=nga&Cwv2YyHy~eOQUFDI9-GESQ%fYPsQ=&a3WI
zN}QnktTB15BdKgYiZ|wn^_Q^qs*w1ve7kyls|Yb6kea`D#rAQ{MW(p#VXzzVdedBf
zOMv0Z+rZ6>;pfgP^fh}`@h0=NpLuf--q_$QbJ|@u_tex-zIxDIVOuO|adQ<$YmPw;
zpZTquR4~N!o_k|SJlGs4*-S$@&ePRW38a=`Y(5rblmg>dusYzw&A~>-KX2W|{Dv)>
zlkq|siNfYP#QKzwjJXa}E98K4uyx_xorM54#i<i1U;u*j48L}=Bb>Ogt`DNgj2Tz&
zw`X|r`VzleTqhtE@wwimMQwC7N1pufb%JBdxVzNj7!;l1U0g>Gu4i<A5z{i5fB^;Q
zM{o+_DwbpzJ`A7&;8VBgL2f(`U9UNRH1{Y`&D;$+{8C_aG5ae>GVjAapjXgjCek$g
z-aJHz79*O1c>-oHBN5H^)d$@b=Q}lRk(AUp!<!v<Y>IVkA*y()(H$T0ZAZ&e=?uL9
z#JU4EeEO15h}tx^?;fbG)ocUBkss2Gt7u9Vwh`39u=XprP><m`_l3alMUuwdVjP<C
zxSojB1jJYxWABcRyEAPh8Dd2KXSxTM&VT45l+#HX|KUs6L`eBLl&=>y40)szZj8QX
zy0yR6rW6TNO%~6C^A>@V2ih_v=ZzE(IHz+<vxESdaUJw7O+V*AHuE;LuZFN3H)jXk
z?tI=KM)>AYxQYM%1FrJT7}$#b!yvSZW%k?nK~l<a2OpA3l$B8QA9Z_kl{NT6z3Vz?
z?L^?{FsLwn-+;}4(RjH!nTD-aF>4SCq#iI$&xdyEKk2>v+<q7STd?J<0Q_QA9ag+%
zDO2TtSrqoaLs<4-yhcjL|E$vN|M~CSxvn|X%?Xy<wTx<UX+x>P^rSe*G0(^{tEG@|
zqMq&*n<t`U*EMUiFIo&1+fErIo!Y+exa79e^woqzjJBS6k1LVq3pRfCF#htSswPq~
z<?^w*qs!IY3bgzsOIJH)+eIcmdZ5y68xVE0<uUej@NJpV&9$m)3X4;(zWJp>7t;sb
zP4-qj5o85|Z`k{j`%-C|a-7#jQrZNK`tgI4?fGHZ@<HzN&7Bb|-46&?@2~;g<zDjq
z)}Bl5U#@*Vdok}@a=T~W^E=mdJ$2pMe5$P0D;0R|PVigReeCWi_w%Zu9d}}RX@7Y{
z9>}2WweY_qshvIN*0zp%$scSUEvw8A+M>7>-n%QUD%a#~7^mFSr)oB@^Lb8SRlKy+
z^CN$J<)h*gq!6#CM)cYeIK|$~Ey?d(ZXbXjyoCD~Sw|DZu3qjV?iU{3EC-3I-+oSJ
z1Zcl52tDt%PwAWcJML6!!qfi7-S=))AN=|ScWGgFy$#y5Wln<f3E9G6LweAnNPVl8
zR-9_eokwq%zYQ{!`o}i^LCJda*`W?S*LU*3nz+&B(!I)c`u#oK-#XrU&|{-MQkd-{
z4$A$Uf7p4eN?g-fe%oYIiMYQ-Nki_OEHfAM&!Ou&9b(_RL(EtgOP-3a@9!NevFi~J
zz5GJe@TZDvnCHXGtNK`?Uj9#KaiNxe0XllZU-kKw1G|7sK>7Qpt;D*iA!^ZKufGDm
z$9jMHlKjVn|I?`bZ(8-v#qokeyI9J{Op_H)Y)*ef43V1e+H-9@!pSIxG`2p3xG3G9
zY2$AvkWLE56MbD8KXHCdVYBW5h*Yj{ptO8Rb3KGM4X~cS@MKUV7qi*$n85W~{P78y
zwK$hDbZ*_#ZLamq^Dp+*{gpbN|2-r8$~lXXJ*1i&PP%Vu=N)gXNXeek%jbW?^q#4G
zEdCgK?|f9tT&dMEw?@9)wM~mA$<J?H4%5ef^h!R}xL0SFSEz1Q@*jr-FTc`-3V)YO
z9Ps^g|J$#Ar=Ql}vI~yM>i88OU3O_&uexLK=(>;AJ9`qO=_}s7f9lUqE9@(NRJrN#
z!Ow>3za&$v5=vLis(owvHgoi&5?j_UUGsz)FWzSSQxs}Li!gh=uIO>pz87;nLMxwu
ztA`VA&h>R1(#VOjymGwNmUZAy4Yq88DyM5|2A~t;WjR}4|8=WHuqNz0tNU1e^MGQG
z&oiI9KY6l>j;VGF_OsJ>e=K}_dgod3h24Bc_Z2tYp2J3eKG=sYrXP9A<cQ6U$9Fi!
zZPF0CD~j%=e+yl<A$-!p;JIVVfu$|>vzvNUbtm?pwK(omd)+m{@btAhxt@`WdzaRv
z*qBAFKIT=2v5Tm0&$9TLA$t0!`ZtaF$Y)8`=ZYfg4pwf-(tmkX>2S=^y%Fz~MsHqC
zym#Ww{4tNKCv!6kt|Z^sTBu_f7Tfyf^<hg3+e5`QyNSGB0Wk<;RA>cbtRA-y`tg+)
zJu~YGuP<rD6K6fU*CkhGu;WEGoDjg^c~g4%D(XjmcC%g*pO9<x7uKyco)*5zYD-@R
zYg^_pw%y!VC+u8<FZ%4kk<#!ocVpXa3O~k4t&MXsp?JsJOoC^=j<5W+Mx6WCianKD
zGqV*h>&Ni)5LYrFV)(Wa4H(JWP~+{!Y`IEbiHM$1O90akBzhoEi%*0SOanXU?t))Z
z7e2t2B!KTWFsllYXpm-kPPg0`P<U(d6pIPwVuBW|+^Gy-QyzGAeNn$+y|JBQ8zvCY
z-up4X3b1^DU-7GOc-!CecrsmR+{@7tnA)8nPI*Y+@q>}N#1O1eFrlKjyLu+@raaNb
zFL;@FY~ru#MS);+@s`E$LHI*)qdgK~pJ<6TLb!G@ff<J_5RPJtq{z~)Y?z3(V=v#2
zB`v}~66#38iwOv&pXF-?dFqHn0^R{#1)S7}*x-!^#9(h`2^q1^EqMw98UURY0=yi9
zRZ$OcxUj(}6_3bx9Sp8{x|{qYnITF12oriBty~^TCza`s(VDN*_&6z|=P3!xv+Ydh
zB90#5mrTMocvpv{_h$TtzH?DSc{Rpl#BY|*HJ@}#3kXIS5;jG0ESV=SY+_J~a}#7d
zv>aQdQ}UZ}sBM<xN({?x<ngC|bH8+^X>DmutgY%1!5g&{*%CDcoR|KR7&DLl3<)y^
zk4h34Wy+Khq<z>K4S7rG8nnJ{E`@~B;(rlqj+{?dv=Z_w__iZ3U&9!&5QP6Q!0bGp
zhn^8*k7DC^`&eck9l8Vz7D*INxCZ6M5t*JUl99~n1i)i=bS#p~vlAP40Y5>98V+&o
zo}j)=1tkcB3Id{v(yTy9bbt0@Xm})`HUJ(uC9~RB4g50ZB1KM>UI7o96|K^|DIRPx
z%$(&rgEh`ui8osQ{zPziWL}!mS<C?KF`}vov3F_f5Nm)jxR`^!r~}0zLvsiai*X8z
zq(3e~%S(o<6qy?3Ra(sqK$efgN&->{baP=8?u+WG*?6ca7vC_Fxk=rUCqLm@W0TP`
zlHMK7mY@V7Omz%)$c2!o4rs!z;#>v$+@a);gvGGhczzUnusz!4BNadv>0r5EXSY!C
zhBHZO-GW&Axyvf1eF7zl^J8+p-*M6tAP2s5+oPYk(u$|Ua&$R-*cq|0<lCnBB{h=+
z)xg_Q$+sQKMM=dN&I`yhi0~ZA)0%X3a+5cfy0?mL<k%rht#(_=ucY!RuG2uiYLge5
zwfBfGzIKtBi=8w@#;+Ix$ImyOiTNv{p5H(&90c}K_qJ3zNv!#9xC&W4E7UtD&+tt$
z%3tJ)gSc|7F)Ln-HKejlf92~?Tz>2GU_hVV?&wj-4eDkd3Mvrj=n@h-T<nfkBSn=Y
zUMju?G~Fx(TuMkbd`jT0cYieiX>J1<5-=3>rYlYK=7wvbSw4)QZWSd1cG_G8L}rA;
zO6wL}lCfg_@?e$yC}$je)(*-DxItVQW=uPLEk=G;Wc<JxKfZvsv(`qu%W^{pvZMR+
zERC(^Bug?l9<R#mq~^0i*jDsIJL2KS7-FJ0l04g=e!v@T6^@w!u)m!VG*De9@kL^2
zI%=|%G;1aO=s91r1Wtz}Hhq4q*%p>BAb8SI-rK~6U^(7C5jGS|VhE$NWzw-d!g8)_
ziL&=Y^4<t!f`pRe=t$DJp6`dt;nd{`90<G_N7*FlNt1%Sh6{ee&C%Pi%2>jFSJ<%v
z^_J^<IB6WzZc@jx74~iKB%wq~Q{;!NK&#R`7>p}<NI;UKUbPmmeMt51fI@Q*cQRfR
z?a}Q=!{BJJ{6dL0Ac{clE2P4OEL6;_PJ|IVD1kaqF0|7Bez2{Ig`BxZ0+DsL3hV$~
zKm{ZZ+A!?@K%nv;-wy+kk3bP_j0v=|@cumFq6BB`KvBi~@1JZ=wt^q^TYd8X&oAX~
zcYi804LsPLw(iHX9dDL5POdr=`pr3Y^`@1_{tR64mp(dBE$_=~*K1{$D+1TBszw%N
zr>(62v!`LicFUK0lRIy(<Q6^aZ^l2}dUYmrpz?dk;E93k(v;1S6+VF`i{|?7p_p=P
zREKY4%!S}Zc8>fU)XdQn?{NM>wdeSEa{ibX|4lv`sP=vK#@3!FlcQQ=H(kpE&*ty?
z`a^?B{<damP=OA8nf$rs+Y%`0fh(VsEOxG>Pgef;J2`tJe)lo_hkr`Lv%d42xerhG
z4A<6D6k}GCOdYh}Z;7&tNU2d;9b`APtzeVOx>a`zERP(vDsL%&syQz8#qVGLDC`q2
z*8kwO$=Th4+qZ6?cYj+N%H6RXPS|NH-bRC($$7ggQqLW~dM*dQ@}5dBi4g0v0Tvxz
zaYUzM!XmDY_0#*<PRDlc{6DE?vg_08rx^YxXMd(LBr!RUpG#c+Mc(Kyyk_{f&xPHn
z80#YTr@rrf{${JL`rwX@NBpiu?Amhg!jnrUO(i-<_pB?G5Zw8%9_WAnw)N0rk3*4h
zc^cjh@i!MFHdA};-0>G)Ho1IG9w$#jnj_{iF`(Zkw!~n-UGAH+c+ckzEn8OzX+fsA
zz7JoocJ4AQ+TPi7Yu<w;ts|5LMCh*TI=InrX2YAd55K<Qq&r>BL-+UjIVm4$H#~tZ
zPYamKdmN+z&YJz&ZAO{yIY*w~vh7|OB-dg4%=OMqw_?Kf2hKlV%wE5VAn2OF?dO)M
zFeIJMzMrtrwPKmSaTuPlyELplZn&x)jq`d@b+qRA*INPK&qO&rkoHAMlCGo|Ie{F|
zgZd0VU_AHdvb6XsWABx#jyQCl4M!b4(0$YG@5h;^)-~$)*qsU36o4-k+*)5a<z2t|
zEUm0}DRCNCQJ*~L?@l2uwK+xWzB%Srz9MIn{|?*Gz&_hu71Fl6gg^e7=sryzsvE5O
z{1+$q1ecmbs_X0d#ClefyWGxkIr*T5XW{4bPmSzi?{KN)-32K|Sr?6NcE?rjdqCS^
zbfz&T`9^qm_@yUDSN^lhq_jHgL->WvXx6juw?YShrdq|~J!*bX(40Acy}`*d+B-Od
zjlv-Mr#;(-9X8b*TI{&9_2a?s<4;y(Cq>6iPH38hPygCQalE0+irK6}_$GXC&*RnI
z@}2X7oNtTL-)-}))!2yU7XL-KioK9?^Z1X@%pQfuE77zztI8N3##Y7@_uEi?7pJ0O
z5t1m{;dG`&S{%{WSF_#W581#)`G5(LQJOWXofwacq$&ocT@i0B%pw<iCdcp6<UalD
zNdjVF8$8U-sPb89$U1Bk%2HJ1|J5*i6&bp4(#4DB=r-lv(fz5g+moO|qP4+uC9^u0
z>E|_18wNYtzV97ss-SLk(owbAnORogUh*{mTEMP#qz0Bi-NK+HC8S`piDE<f)oF!o
z%QE_ltHe++Pq#LillNxU?Aog(q#q41Sz$C|?dRFE_j$V=L0I{E$J*pg5q7V;7RN3S
z?pLPkM=?f@MSH4B-2&3Hj0zx2W`vzC6QH<GC1e{(Ncvf+`vRV*3sX$yl!v<nFfqP9
zHS#~HAWm*mHG!E@UztqM=8RZ=9d~Cza1c*H=L>C&ZvB(`u0yWFO4tna<XpegWy5e%
zQXGllwldxy*!l1>g2G1PBFIpYgt87p5sW?lb%N|{EXjVdHrmU+`eA_Q(KzJPWf6v}
zYLsT?wy%Y#3<B8{WhB9hmzi2=UJMaXNGQu3bQ)!=qs7K#B@m#*fufWgtU1CSVNbcl
zZqr9|tve;`;kW(S3fPcbpn}2ll#pZqt6vy@8No9(!!<zt1`!N$)Qsi;vN=f^GGav=
z2i>{BSn3ql2Y6_}>v7~M7-h%7xEQag0{>g{fh-0|lLtBiyk<KHmUXBQoE*&!S&;!)
zB9^(E{5*aV;$%GKjk!TX=UGUQD!2w=tY1hC#q?gx_LX}V#!Q9+cab@1v>tdhh!Oqm
z38Q4t^Ty3dvI0n6csl};0LNS-UBbB&=%@Jra*?w~@`Q-q3EggZOC5-7fT@DMmav_H
zY_%H$z%%&LQ8Z)Rm>3Mrg3{atP{oQdRam)2ysZ)qfQXHO04AT0t0VzDy2exmsvAT5
zZuK^1GMJa~4cLs5h(HOdRyfxI*~=X$md%VawrQi27{Zpb7=h94Sf-!Y$iA8~=d0h0
z)wZE_$WbN=VNzaYszxG4|HGz$OL)-&{{3&mG!+G>0dxuqCT4D`8%$L?-C2jB>R@+f
zTKigeSn-0ros9?yosgBpReB_BXeWj+m&D414I&eQIST<v>ed%R)f~`I8|3=Mx(0P4
z^Xh&iO7X1b8tO^ASU1c&v?O<CVzz9>Eb-DqZ6r;Rt+GHb7{*D>Ju&mOyrple%qwJ<
z&)5cYNjCOyw8DnG57RN;L;1_1hS;OaH8HlcLfGe%Y!a+}y^K&3@JTAP;f>jycfJVM
zixAV1W3eI|1XdMFZApB^Jlz*SA`dll=|9Z3#3FA5+(6|(m}plZB3uO@&;laFmjTQ+
zM8}t|^aykTi>#@|rJOqf_}axke61<H>AmUcT0`tGPB~)}9<^w$leISjlw!VK8&>N`
zkao>d4lY?JHeD&>6(;fxi|J~BoaxQTqyg?c5RvE<%RW&=D^UVp%m;F^?nAKIN|;#o
zH!KzKqUa1aI4^Z_UQ=a)i3R);l<U!IK>8iFuWo`3$!|>D1PAIqdNemMMM6cIB@pJW
zqYPDZG>2@X^D8cqp92|ZuHK90sJhXPqk4m+c}reMaCo6)7OPDnoc23!*3Z!rT8=}=
zbVEF(Y1L~E6AK_S88-)2sOF@L6)%esf&z8ENVhPUl9|iIz_aI=9ij0u01t@ycIQm+
zJVZT$(#&v7cQ5?eA@_c`3IICklI$<A7to<DO$RqR3pFf6Fj1*v{O@DUSQR`5mZ=^R
zj_nK>SZcotM(rSFn5tQCqfIbxt}=;%)&mKh5<uM>MTi}9mQyRsXc5cLxVPaokCYv=
zVL1Vrdcsq|0Yb^F49n|ru9h(F*3HdVH228zdCK9C6=_S917S6QsVBglNd0!L5Jcgj
zx)-KLZv~gKf=)7T=6@^A{4RtGrj?HcJeml#k4GKK(-P=+tWd^_w7$Z4-6Tn@FSJ!w
zMDv6Kkv!bz0HOd_MVwfx8KJ!Tt?*EP%9g}ORfifu(<E#nR44E-2_xC5bTb!cIV^{T
zY7xxSen&RPdi_?Vfq`e+KsDS^L9V0)g|UvLQv{#jZ!!1(=!>Al`;{9CoHhKUOHygN
zBEC7ohQdW4J}wgv2MVv5&x;2j*8gi+$^R`g`Tz9qbYn~uw2dDdrd-eL`!Z12bzxWe
zFU`bvT;xfQy<ubNKr211%=7Q&zWwQc+d0P+Z~R`e@9J3Wu3gtUZ5H0WXkGp|sXVA;
zch8#pT)WISr)(mZwS67vqp%{MQDPAX>ypu3<kY3;0}@HfzliJ+;q=Dmo!1Yie%#<p
z9Q*uLI$f7D^{w{N4VNsJuJW2+J(ADP*ESgim|`=2Eg$t+THjN!v?KX^sMt{1PP#Vu
z*2leyadw-2t$+2bVj2Cy*Bb?GitDQ%^c}GoEWtL*CpbJTkh5thSl^CbzJ+<jxNJ<@
zfEXkAwrqZyysGks)%T1cEm;<BZBy}S-KDLzXY67Fc178pn>?GdCt}CuY0+QnUOCU$
ziqnI%{@@?85;Gi5+y4=il+h@mx0nB+@(ykAAdNg@9E6#*SawVG^z{2^U(*m$C3zTw
z{bT<fMvh?3I<Y>g;j{U`gVOJjya4F{=GGgP12Y@*pWLWQDrxlEym(Ukm1BI^oh8{$
zihCNO`{s^X$YiFXgUU`S5jniaSJ=q9q3g7q4|>=-tG^DZto)~QO^j{fV48|QdeFdM
zbT3Hu;?G9z>?Dh(mX3~|e!9M;I&W#xS#Qp-V!wZptyd#j+AC#kN!V(U)j6M=<z2-8
zcJ@MYBsPq>q<2HNYVx(M)G+q$`6uf}?RzR?t#`kwyM7oOb~_ILtZ~DuTN`YmVECAM
z<~HHurvofPb-B>-va5eytK{=ex#nk43j4o%eKwE`XAZt;jJcGz%2jyat@*munoWa+
zy$-CJinwzt=w1>hE58qVJDQhYTi&-ZR*T#=>OzRT_@zu}(NtXabK9{Iy6H9(l<vT6
zH(K=P(9kFGYWsb(Qr7v$l@VJy>Af0zJReal{)qMWA-D7qJ?vsyd37rO73-daT-p3U
z&>lLHr5!nWV?6eC{^N3I<X26LU3`#9SFoh!{@F<SmZnUX$h>`b?pRptf6X?$h0b1Q
zkr#ThDZ<sWdrffhx{yzwDK+v}iTkogdj*e-`)^YH&)i<MB*NwX-Ry(QmVR3Qf`86y
z*XNM2Ri3Bp{7V9aW{XXKJZct(FE3~}Y3}0|FCw=n%}4&Vr)~EVX$9ZQM=!ukj4a^C
z*5B3nwBv(zCE?N4a(V4C`vvE%rMAWEXc2eY%>7)FH7l8Jf5S~w%60T^US65q>)GvD
zC!3Er6799mnR#so*Lmk(6|5PSlOeH-y0pD&^?W6kIOAnd1gUv$Ar!#UhCaZfXzf+{
zBDBy<4Rfpfl;t?<Y=scg$L1ToHofn5(pM*M@msv?$0=LNeLMGx8JAS+jumU(i1lqp
z3Vv^NZyC{y_^M))*mmsa_3CYm&O$$@Xb;%>CQZ6aSe9~34NGi1R>Li&LyqGpa45oX
zNtU`aDTplvQzQ%-HBaLc8#d8n#cManfrMGn3yJRHQo071%UFrzLxUv6<T8%8(RrrE
z7hw~P$QuQ{tjN;O)u<4^gkQA*oMc}FW<K78vSYN*c$5ILO&{kOaDGTM!-=O#Zd75_
za!&$$0E$fW{`9vJPUXl&&?nHO#WKc7eg?5#3ZiEi-NN8QS9X#qN7G?p>}YND(|aS#
z;b}0=LSYeJhWkJ!>^c!j76V1R3&W=hq0xCj`kVqMBu{}~gHyndWGj(?fWZpZ8kM?4
zI~#$jS6N*M`pp3Fa*pIx@V=y0NJ$8=k7_WI>_xPXgy>!lkBCqPSnA|pEl`%Yz*2Y?
zmj7a$H5b8;un5dVevOGK-Y9#K7p?-Jynr?8!2jA72H6g-hFFRx$&wgK6i|H;1^hgI
z!Uby6COV$S_BF-DdcbR!<}Y@f5bJhBg#pi5(Z*3XP<KdOr-f~<5l}_3C7oRo4lqOI
za@k;uRE9aTw@e_3A4y;A+RJ99R_H-!PA7nu;Mg%qgxF%5j0b-?YZMljDV-oKINo9A
zjhAEMhw?$8N4Mz&QYWS!SLygJ8vId^_%SN9so+0|B^?K$ww12z6E&_3)%Smq_wHdy
z=l#0>7f?|%t)xQpn5B@TNz&vAg-TI8f;E+yIoT-KOl6)Dvp_qNp$4Uq2NKYn#txH~
zPFZ$9Yi3kL#~LdubyOl#6V1w+{dV@=Ydz0e&sxvE_I2&+TI=`wqpN8;hzfk(pZk5^
zuN#-z2a+LPit!xm%HQ5`q}D>J*VG+ls0j>%4#@MvL8V#e!RU`M5SH_@LYE>)GQ+Ti
zTx<;aQqz{@i8}-SI-EH-dj$x<UDcMRR3+h|H34rmxAd@ROiAp^3F_354Wq}QG{b5_
zW*bGtduRj9s%=jb_kg&)m`6-*g=ZS#NK6{04uIaR-;DdN8MpoOx-$bsMnZAjJ1L8=
z3DmQViXm8;ij(2s)|HFj9<U4}0W!%9moP5#QK5uv2s$z!L1s-K3q&cn@ATwmK`mz-
z8A<CE16D{H;WixVfO~BYxi<>YOFb#a8t@HPZ~|p-p}#klj(Z-JzKg+mMVKSqR;aL(
z)nYLD1PmyWKx+2DkI<vmbnziVmox(}w(ql;P_#Kz+xb=78Pgsrfc?^fSo?j@MR<<~
zaCoMNh42xb6n56#`65v8<+~D*7~PTEQOt*OpZFqd6an(o-Fz%Li_qpFa{@V^%Y3A;
zfNKb5;W@dcbAbOqR^c8P8%Ag{!*K@{_N~ysQ`%{}ubm2?X_ru3Vuq`iV$PA{XRdBw
zfVR_&(5VzQM1zmUOlbolfosK-P%)J|*)3o#`I-)XT{CTvYShb8&yi*U`fp632bndu
z8H~Yw7yXwbAJlOQ>@8r!dyMoHY67`x9S+GUR`dDvNTpK@qzWyx@7teyYJyHC(bs%p
z<851WB!0#Os8>pOuRci%DuV)8vPn!%Pa!TxV%C7TI8rpBPE4i!ad12L2*qLq76k&s
zhvj?(#Ba+rUBa7@_yc|nGX<EC+M-o<xFjKw^ghDRL;xkO0d#Ii+<P^@d26*j(qz~g
z>SE_fmX;DQuRnOR+PAu9+7U?-cnu?sGAHuQ0Rgh61>XYmGdhO`L)>b2_&vm$=qs*?
zK(lO0YaqE@*Fx0L$Z1j}DLBv<(j-XDnO>gffXF8T1>uD*J_BAJK=B%ewG{*(LF-mA
zJ6SBCETt>RB}6uKB*6+5)>y9aF60hZT!TUh7;(r55UhMVw*yNS08H-GS^kb0ihn4w
zV*V1FW(24IAN+8b{WEPS%Q<^&`Msiv4VlNiD}`~>E57tk?<{Mk<`qqczHC{ux>)ga
zug-38aXkn7t3P){d2E+sXP=P0cK5RBBG2V9>z8c$c6XN6$aw|h+N*--wLi9zzxv_%
zt;fx8J~{uE+OV~8bg$FHj)S43++})O%X}yPXtJ7Tn5^Z8>_|Cr?Dw2EMCsC;$cC$b
zB6&NW6wyB8@&$q&N9yu_A)gF(K45PBYoc1SYT(JRqk5O~qMZ2@=gU*+FOD~)e|5cc
z$@<N+GFHvwUZYgqxEv7>eq>s|TKg`k>DtMAJNp-$dW5*J_qM%kAFaI^nbAvg819dK
zq@LSUV7E5ndjn*C(?0s>Yi<{BywG`R-Ov4_6wX^*`?xzb;`98Tz3DH%x^!{qLKQvP
zc*)K34a-+v{(>={&3$xZ+CGPQee|4g%=pR3vz?nSnr*$SaLx`maJS9q>CjK7rXMA}
z-dp&<^Rr`X`u>fVSRm%C*oYXxqVcP$jS2I|JZYoq?b|bci6O>6S-Im&%Dk7Jeo^mi
zj~U&*+e&SHWN_0~aew=Pwut?wp!Oq+j(WBWR<GOF)kZzMzLDB<ep!pdT6kV!{^tOB
z{*NT9Z<}*XR0p5sW-%8<+&ug+*znGCN9Pzq*AhdSu>tbKu>F$!;AGcTfzOGP7t)XK
z?s|Rt;xQuL<k^C10K1<2{B?Z8wd)p=l#l}%ydRv~tf%(e=YLsc8ua9?_0!Mu8~1iJ
zdX*KpDqO$cX`KD5d~ROXO)mYLpD$dF&78Q9RB`H^`(Tw*+^dg;*E*}WWqtnU#>*co
zEiMtKswbT`x_r@BP#JS0=x%lR==J*xC3hcI_H1d=3!EQ0b*uJO0q6ACPBY7(8z(nq
zTwvuc$iDjR`?3Jl&DB@$W$pMbZ7zPUV+Vg^YpBLCxnlF#GkPaqFDi0{hm`1XawTeR
z1Q#U`*_<kVmF#SJcR{+f|0?pE-wG~&mG<LRU(p`Btdkkv)%4wR4k#~4-~6Dil~!qO
zv0?-LVbrfXQ;ptTNpRg0o-AsKS60NtT%8rXDc<>)?<}6gTskm%J^FTMW&PR{4jC4w
zw%jn^(#+du&|^^}?pfiZE?v(xu2Oo&49pE{Zb{~-?>W=m-aZT1Xqn4NU!fdWv&&hk
z_oh2(E92F3lW$k<n&+r+IG>X}I{dNeCySbDzd*IkqEOP7^<fS|A5rA%uG8Nn<_TjK
z26V6MPZn(c=GP*Jo*Q`!rjplN${(pYdp1*t-(K_``r+(>S+9mIpU(Drp?vf!QMn_`
zr}m5B(}x*Nn73Z)Q}+^d7n1LeG1lMt%K8Mgx1lJY*+)(Z+dzIZAd%$+cXa*K8+)%@
zwBGQZ<QjJVSG139)uEwB=H8#at(ND$=!_n&RCZrI{6}D2B|oe}xXv=>w<|}t_d<Dh
z?+SPINgh7bZJcGf6L9tcPfa=uD{IMbIVSOhW-g297HWUY-<1^91d;Qlu5ft6`>$NN
z6k}{gwp<N-40em%NN}eLGI!JrOs&(`VJ}=cbj2$5>ElOtlk0oW7OMw}4lQAUU1(>h
zD~AVU221xg2JvW2lORM5nfe3EwlczM5EPIhJf)V*Hb$&1EtskeZvKOMko*G7!{6bM
z1S^*9TTbS95Y?zloZ8F)rvidkpoPzf1k~L^1unu4D~N^^osk@!DjyDj#XA2eH^M7k
zsBiCg$o>d7Y?>u;gRvVyi2^g3#Vm;dUhZS*E&?Ais&fywy;DL&wbi1nh!jq8L69I8
zmqV@qwKs`|i!%^q6L~U)wZ>aLA*JQ5VQ~9dupRWrSwiq1-wRblh#5sggb{2xm!KV{
zSFjN+?Q;sCOAOeWfZc=^1lVkyB}1sp)E0|@9GW%+^BxKp8_vJhhjhGzk<<r8bRfyV
z#u6)F7+8QxHDm?7X%ambdmN}P7<`M}3so5Cni1#%NeCQOi=fq-wI6rbl|4f9l=&S(
za5Xv5eXZxp#>)rQkSL6Y%BKekC1PhGqj;;5BwjPN+gvrsL?$G_h@H%#&e8<#F~gM$
zVwdU_1Vb*5=a-#3si1H?`)U!37JM_=l->L?1hI^c&)>}fH=*G`;dC#LLJZV_v?G{J
z=!0Wh4+sVd3>@h-ND}l~n&EmmF#c5IDoe!&)u`QWME8JXn2boF2+Ldo!n6V5PsCI1
zK{jZFmIrQhUyo!nIl}&caY%oAajN`P7Ku7b6o$=X?4nU$ypv)v&18O^oDxcaXx%h>
zIDjoj+nfPk1y~;t(-QVTZhT>76cQ2-DZvSFH5U!H5M(^~Y6D~fGtSh~{TK$`=Z1*h
z#)uXs{+beEU|+YW7H!tV^E39XfbR~4LshzRytrTtF0ACTeLCRL-^SJTo}I4pcf;ki
z=Caad9&!{_nj$p^VBe#L<?sYo5<H_23SmTPp##m-Hj36IJjfaZXJ;mKIFON=ZF!CD
zFgYeGaS1*7`^hFO5BU>8OmFUX@LXu=J8Q~H?0h?s*YSLsbgYYK>>iMn*$#rWBxHPq
zt_jNN;?H7`I&f!(=?54F)<YoC0%mn22>yvIqL&Ia9bGC;V$ip0Lw)8_XH7+9*n%lM
z0+YuDJjO`yCpOARW~DA@Q_Nfk06SP21vC?r2rlzvDDp8mglZ)7&E|ov7NU295>jgr
z*?4sp4EB9EmFMC@bhc+N|Co>yuFf40Hsu@al?ptYqo{1u?mg`02EF!H0`dy_E}l=o
z-BL+90^cOl3|XDr24*(XyM<K)d>*$W6d`C~5Qg!MgP5|L0{i(?nUz%p$ve4CUCiyE
z|3L#ggJGmdLKtGB`H%v(_wcQ0@VEX67!Xj^=^?AEh47oThD03>ZgHDeh!*X_y;^M!
z2+5KYt{elfflJInjNRM7y>9~C&5B%>jduj9)eKkHXj5b3p=c%_J~-_u9c91b7Biop
zgXfvTaW|Xdsqsg}0)8o(-hh~gAQ(nw5<P|kiPkGpq1Ri2(hdPvkrnE>kZqN_O;`+^
zz3FG1M*c`BBq>Iyw(NHQ`EQ#q|I;b)AWIFFBMd-b9N~5Xwtu()s$dBM0FX>3J<%%y
z@ppCOP=<gNL(EjC0<v!gMp^)IyX8@4z%GF~G=PoB8i?RWK$!GMhCar;N-+~X`#T9$
zKBCU;<t-2iyi9=&h(u?q_JXvX2J`Rfvm=0M@n2O*evu5V1GE3V%lE&kq4)phaj|TH
zbBN(hoj4c0W6wrff>Flfva>%51|wfQ>&)N(F5(#AOO2i8zs3*x#OG$Jlj^Ll9eH7G
zPVYGVtlFVYG}WKKU9@iLR9t!RMTK^4=q>mD$!DMEKiyV{+k{%Z#pdn~gCD;fJIZ+7
zjZJJDZ9e?<XiM$=ISloZA9q>2c0Pa>iW@^~&-BiU%y{|nvG2Dx*Y1-^I?H)JvU|41
z=i&t)qx1#`=9v18d_UoFPH4y?h?gX~eeb;v(%FGrmfA*)`gz~lEj{y!_qhGM$2&Pj
zKdJfG<dPSHcYh*Bmu<egkQNZs?Z@2e7yViKTM9|^F0Z0ylh3mS?c-fbKd+a18Q&j0
zzH9Vi@c~WtfuY6Mv5bI%#{~Hc7WS);KbWc1gwz@P$u~O|t|kkfg^xIXiyDqP*kzl4
z{j=Tp#&28-F|QJ(we`i%*Tfhej93zPLN?!(fRRKj+r(if+pPL=N1I7>`OjmASk1Am
zbj7}x1}8Gk_xLO*@Hz2|m1)w}_0OLy`i1Cnr?G$`8gljy8=X8WeOxsBUH+AiztX?h
zv9{yH8PVbEJ_#?Iv*Ujn(-Up|Vl3-a4iUSnC1%2M*!b+RZjy+(vAg=_w;$0rk2uX|
zJDPGBQ5zGj>3~$`u+IbXLEQ_+^>PTDdcqnZGWzq)TlRJ(j+@u5x44&kWwPSb?<>**
z4h>wX)V%m~@eO|WiuAhq4-@?s>{}Jvnw@^8@Z<42(>t1OCR|7??7n~O!grgG?hhC7
zxQ~`Dxfs;8q%^Vr<?K~%dy20msJ#5{UoxE%PE;@Nq;7n<VAoH-J^!}m<gfDJxkoQ8
zN)k*B6&H_BeRWIJTe54-o-bA!IUKvCOBle8S6VcEm$J0Vf5G%7!|P)%(}~F+yBa5-
zhEM!p!7X0@%g3rqZ{#<M2R4NbICNFrZpbWnJYZERn7z`h)@Q8er?@MSXHH%pZ+r8C
zaRypi*BhcPy)*YnWz<P`X6pPUS<d)3(Z{9xWVIft754Ax+^n7306a{FCS}7t#1q5e
zN_*+{wUMC=&cO)1tdHusg8jszel`9eD|K;6AY_K^wf?voq^LKi)jI-&pruZgQAygM
z_bdWQ5+D_F+_-8~GhROAkAagjm0S-zVnqc)A=06$;jBpFF4<-+iMiGJ^aU$N6tWuZ
zn`I>~BrGFZ%@QCGUFdw8qzTql*wdq84vT7C5Q0MK=!t7ECCu5Dn=mF*EaxH|sU#9c
z5kp!aB)3|?FgP6CBeJNBYe4Y0ZKp->w)Nr#OhIuHiUv8NSV|laU5YYr3ey!S+7cOS
z=8OXjO}tG62h}95?1VLYn5yg*CIwP^#j&tm6yf#|{Yi+XOPFIJQ(!6?2<5zt3~fXo
zA~O^k02)KchEl~f#$Li@g1nH)QUTV$faGs6kUt42j%wGvI{6!7kdmaYm*j6T2=fGi
z-0)s%(}@%f2>edrkhoeL6MzNn0?K)afj0^KX5N@FXaTBahT0?_(E`xAhPPea4`;op
zI6fyR7a&&>BbiiYJ%sX$B1~(z5abBcX#E{c2`G;Tiso9JF%>@vArP4E=9HWt0+a)y
z*DLTSFVZK<aH(<(By+f?L<onQgp37G$kBzhZst`GAhIS55s@>}{yw0Pap9PR3`iS=
z-8Tj~dRzEFMBX;BAOxagsHC7CUe-|SjMS^wL4(PUfPXE3Qaz~UNunZvTaaVPXDTo^
z+6933d2)-5U>(oq1oxcIKiJA%(pz}D0qD?HER-M#;7sOv(AH3hn+d3KRr-3F>OPDk
zxLdy*59-cN241!sTiUK2q2^eC*1FW%ONIGqLJJBu0Yx35$w#1fX;vU%ga#;yZecc`
zz6%aRCQN7GR)8;@59DERCMqm9L=E`nIyuHhXUc^&vnd!wDMSMTDBMW_ZiE3L_%-5s
z#I`?+Ea1&jfEX(Ew&kjG0@1n5V%YJcg`tjNFz!uC^(pSqc&+dB$nTJ~hL?)F^||Iq
zHj(Bj2Qb^`l;lz|Qq;T?G(%zrTnxaXFd%{_0N}Z2AbQpS$~AC@hYGF_6^tzXER%v@
zDoXR91%!AosHV#8j1kB&0`McPpOr4R{~a$^I=!4~2iI|=hKk!hAR;%puJCT}=+5b=
zc5>+AVcPn73U%@(e<G090M5J*#I8EUQ22GYHuWi%Gs48OfoTv}Vfm~DGvyv4GS7`e
zDlOrJ?<Dx%j6@kW`lwS{Jb?aP4eo7;;R9_zaudOBP(lT1n_SoUx#lpa@*8lr3TyTp
zb9k9Y;!~^%O2@1!=!^wNN0>Nm03=~!f(9(cUa--%4b$xhwjw6v>%74L0$QB>2*Pe+
zvxY}xSV^y#Z8v8g0gD5|dmq^ZtLC{sm$=gpRHKc(<8uNtKp+0tp8KJLZlkNa16pc>
z<^Y3Gfp{n_CZsyKj~W#yZ+4O}hXb=_Bd(qm1rla{5(D&UWKuys1Gw?ny(0|Ift)*<
zpi&N!;M-{m#oeT*DzZhhk6LZ&#TqPS<BwEMslhEFq-Z>bsk}aN9LCd%RZtMx#6|_-
z=4u#jW*TZE2%kB@`JqnOQN?f<IEniLGbR<S0m(p^L`?mRnV&=LJV(Io(pqH8Vg3ix
znhuxV`#0NU2-2b8CBp&bI*dKUCTH_-mSLf|2>axbpe`ZhJQ<E320T}d!@2GOd%^U2
zrxMVK&_-oVtb?c&#vHhtkd*?T3Vvop^ORFO6*3DD8WH8cpSvQ!OKNU4DZlfs5{QDs
z;2G{b7!PZk2vRWhaC?{%UV8}!r@^c64~5GAuR28k<@3tdDdZFa=Iq!b8}pkEKjsZ?
z^?ds4p-sWF@98~K?{^FRys*Jm*Lo}I=HV5sTUK~=m2Dp^Ys#AYBH`IfYrpQL*tZvR
zcRROzUKDkDR6dV(V7C!w+0-{NUP$IwJ++s%?A`y{MOXhH+6isX-#-3qrB1q`Qg}Pa
z?cD5yv-g(e9Rj@KP3m=S%DBJDL9g?>#B;lU8XI#o-|pH{96$TqvCTZjXZ-iKNLR|5
zY^;N-<F9SJyafO4N#9zz1EIjP%3)Vy=`vqJ``Ql2UyceN`gMC~w~!0dM$3A_EejrB
zZpmoo-L&1Yqk^7ca5eeJ`w|C{arl1c8`*c8o?Ty)XcKnh@%GR0<w+ZstvDs%Rtj9m
zAJbw*frAI{Z%6O1O<oh^+j#ZYvrEqoI&0PqoP0aDQP3JF6F%Md9=r6)<`=Qs#6O%W
zVBSdI26q$#*`{lgZE7iNoU!&;?S{&gv64hMzt;?v3)cMaJ@j8c1F!1zwa9P>{dKIM
zmGKw0Jn>IY_`=*S<r}-IitFZ&-^VFeB`_boc@x;A3EppgLBIS9DsqyG+7f;&W#sDK
z!*5;AtzWXtuTmp;eQV)f$IUlJhBJrgzl-Oeh)(sbVfd)yNl`XIlPi!1ySaOu!vjZ8
zU%1$EP3`p9)Ag4o=b_<Ujb6S#9@Sg@O#HU}d_VWA$r8mTO<GcS_uVSX*)sG|#ln=I
zlj`4Iyef+x>R7bnhm7OG;)x#)TVT2xcJvvP%)j;hbwhr7v*=9*4ES%4;3K;lx>*B)
z1l;Lsi-8mt65}4;CcRkqdi(v)UvzHp86IJYgthY<-zSG{M%#~sg-unMb(Pr8-stkn
zH$xvH-zG&g?Y_CLzPkPB>;5!3`OHJbE6!0;PGA5h6kBa)Nl*NG{!%i;HSgAw@2*(J
zA|B448;2_zP&nZ367a1(I+o-+N3v@&q-&t3UghWIXY3t;Hh;smEm>ZTmwO)*V55M`
zTYe`Ac4NI_8*#Cj0#+7-_42j`BEE&Bk0dl;6}bB@1e{np9-@zvCefpq&DDB`iO|<1
zg=Wh*Y_)e)ugHSjz>PFVDP7sN46GD}6p2}k*v1n$GER!+wSadDVX@RIbYzvg(xL@p
z7R?lZN`^N1$n4}sWZ+6pU`&!}VA4twa!9Qllht7v<++1XoG>=Z9d@&+EjZq6>#OiS
zJ(K-mnFsd(w+K=ydu5CHM!~RVYQQymw+HissQOmz(?b9~)wlkseM$wpDSr!~RblWD
zzol6~eaf2PVmQqW*nra1`Xd%v+Pm_cwnPLAhmVX;HN@g-i~+W2eV%MulLlH?S1wee
zfQ1lPbS~EC!3#8@fPXI5T>@J~09o2actx1u;JBXv<6ji*0l1oCnLy2vBFRdERdT=z
zqQCuY2Xav*%Y2Ht8x47BTZLCP8|B8K_KJLU@q9jZRHmiLt~a<X5HQ?3K%#*JR0kV%
zf3p1SZ&h6A5e%7-zhXDT5Shjv3AIjQP=-)@IPNXh4MTbos*4@j)ZYbhiV>G&j)gVX
zIzf&F?@5l6Bw0YT5IuKTLJIbWO&>ix3fzNe8&Jf$1u>lv_?}D0*5V&lpy-LT;`TcA
zoQhn400TFe0LiLx>DQ8QEh9rJK@4VF^jV*`hEFI}c8MGZT7j_}d!koZ0Y}wvzzPme
z<^e87eHR2%)+FpqFVDw*%L27cmx^lyu2pF#5Q>U)WM1@u0E8Q8&4znvsth)0RB3Wg
z?ikG3WAp|q%P<fM(vp?Pw)`X&EAMBXX~__IyE+YOav0J56H05U4(tX9Q4`=P!{X{&
z>`ZS)Pzds7M;>l2eOzwsD{eTCz-!CVv+u3Kg4~F-HMm&xik#r%j!WD-Bq2JfF|zfK
z0QLjmB)h_PI$$rPo$*p*qdrN<hlqs>1Q4jX#5KT~x7g_5p~Q5SfPD~3T5GlmXjEga
z`W+O^^g-v$Y_!-`ay)mnyTC6y=RGR|Juwp0T?n8dh8K7QLCi|%DfF!=W5m>JL-by;
zUnFURRhi7j#WTy@aCN@!1!Uyah?7-&DPfxJcdRnjl;fQl;nfb_J=DpC9hv}cZ|)fF
z#aIvMC!TV=lLowIm$6z2GXN@kP&(;uaAE|jiwwg(o5?6)30n%Cw+nA^DkTwYtGsGE
z(<A4gTZkTINP&Ql0ILmvrXUI@*GpI=^ZCT~0Z|rd_|VI9gWYRWZoh!)y249E{{_4c
zA5<{AABc)n=O*=ttW+p9UkQU~Zd@&5hp#mC(#gS<qAoh*+sS36VkjKAo{^MTK}?Q-
z247ET0xf2JRHwj2rG5ZV8=#R=En0~I9B;4z)tIdCcUe`1tE|K|*;}-c>jr(=gJ3#!
zSBsMa!)7n{lz!cnKd2yRM*>ijayusjVWk2ucfblE!$mxx&>QQ@x0*4R7_2c7kR*l!
zJaZpG#Gc>ZaQvc~52TpsG3tjD*|`=%1-6^a^xt>o_21H14Q7O?*?1*bn@~`AD@EtF
zLx$Y;lq-<~H$FP>RuN68gL)=dp34$MHo_AV4Y#_Edigu49#+U!I0&Hah#5>Z0(;Fi
zxLX2U3Z^IX0tNtC3BCN|-TWyvM&b^F^}h{n|MhEI1{Ht@{!ZMO|3}E%yrzF6zQO1F
zcVgUs#b3iKmogjKzW21>s(aTj@IU|XsO5U>NUVnk@~Fe>aqICkKaB`7IX}I1AJ~`U
zfWPq3iQ+$EQ}|-Geyy2tGug6w;wlhGoqqN+zMXWAecGh?e)pM%654k2p92<ZB!w?S
zq*EaQrctZDap;h|-6b%87Swy8z}wq!(`wA8j?bYx7Rq+TeOa)kX<^io?kijLjh_gk
zv#Hb0iyv+J?F;GNZzn8z58dXinlIRNDsR!Aphm?!H@v}R@!9kM0pVR<_NuYqZ!!`b
zs?Kb8$<gp*?mPFlq4ys1S=H;YD?TXZ%l8}Y2X4taY7JMOSn2xRuT@sZ3+fq{r(czH
zhwM&MeRpM3ZP3#_aqm~`2)nHFUVb?|-SCV;|J|GYwbx5)D(iPYjut?BeD%~Xbk)+g
zyLKA?a^lJQpp|W!GTax-YumTCpUVDfmPyIOcjs1zVrx#k=3-J57(wjrjdA((`A&)c
z)vE;rxf|$Ge<9OmewH`6_rUnydu}STqV0$1M6MvCWr;%V(4H}(-Exq*gmko*dh{l;
zEQ)yT@ehvOq--L`EOCvGsL%h}kjpoNr&9e2F3l6~yI*=r=cGKpYG}8Ig>QV%t)^R<
z;;)P2c=tD41zLNa@AoyoZ%o!Q418<0LpRudh$An;2d?QLi}sv>YG+B1NA7QwgMyj~
zkHlC?747|z`E8vY=k~assq%_*Ja_a(Y88LldHZ%{Wfrj>SG!gKFBxF4%z||igR8;>
zKIoNf7^`d-a!_;EggR>@-9|zk$`lyq0%7Mi#WxQ$A>YVXteB1KB^pY%rQle6i5q+V
zeQUN)<dv@6?PJvFZ(K=2;*?y8N~-hh6`iXr;0NWhtnZ^mwcfiNaC2uiY4q@FU|2W#
zyP3adeTclGbnVbp*x}0yZKI+i?9d_`opd_{1kiI#jAOD3uMs8(iVR4@45C-NPD<+$
ztRQlD9n^jnMEZ#)VPZ=|1zfe~SbDY79eJ3*3<a3__3UJLX+(Gzl;mv7<Azu3!~BpG
zNJPLx^F9JKbH79m^VNVZF{aR@GkQ)7;DU5AsT8qfO2VEIvot*DW>VX5qzlR7IvGe$
zsS0bzCIos7O2EBI^Z^_X(%|pJgo`_aJ?9{+BdF38_^Du7qR`0+PThQCQ?4q^tikTw
zVOXlPVxi7}&^jBj9&!|2uZ4SK>%t!4bo&#5H!KgWkAV_|94^F3SrI50oA#6E!R7$R
zEY+O>K|=}MU{2t<*~dx{)-XH%L@tFOwacS+0<iHK2dP&&zFMP1^Q<T2PLLr1AOzKb
zW29ju%`^hNc_44IhQSr6ozzK%l`&0MfqEb#1FD9hPt?-jkGc`P)ev65#t^Kz5G{#7
zJs}%|lLjE|{mkw>S`QC&1TVF&TtqfxhBi|;bVu<x_5NTNFi@DV#JaQ-8pdV>ITRUE
z1CgNX`P($*WB-6!cD<w!>Ryn45{+6Aq_<F7Az%@anmO!Yf6}oYac-(y3Q_L*37G(k
zh6N>o0%#y|Dj6{c!6-N=gnA%~pn(U7QeY+CEU4mci^48Zc}19JagenB_HHrICSjlB
z6lEy0$%f-5%6lAQ=BQ?F6e9{!7okHOwx0EDi^V(=^xH-ks{te`-JS}xLv0tlOu^Tl
z80D46KvrkKd^vso6=W|9{TMT>bcli4{+vxTpuT3KlBu$b#BdxB5=6`n2?6mD1(4Kv
z8u%AIHA?&>IbG3;jiefSj4;9#OKo%r2$<9i1%P{2S#=zVVqj}A3r-g1ws(NISIlDd
z;ou;qocB~Za-apG+PZ-~tbuP537|$ADtt4PFdhR3sZ?hSyS*HNx3O6dJS)Vh3Li)n
zp@?QZN)Pq^nnotLy=tVHYD>g4iKYz>AfOu9t?t34HKlb@%ynxvwzNhj)QNd9<syhj
zL`R~$fDj)i@xoByTYo(YMpriCBv_Fgtbzd)$J=R$t5af1iQGsOiOw)}7Z^#msgng^
zI`cMo(!Z1Hq^Z5YRYKaV*-m5|f|Zbi6!lR!;K&lX-)WS$dZkER^*-+x+a$xcnxxZ0
zZ5_M|uwWF)DOQ;P@P9&TQ(7d2VHj{-T(xOk6DR9D%Bz<@A*)niBzhLZRB{@)W<hPz
zw^LXNs7swZ`_+TO&Xfvtae9kwS8j5PW1uJWWC)8@S?pmt)=EWkF9o>Kn-an@lA7n|
zg~IL>+h89x0A9DR0nDBm)<Zt;riVUQt~P5D^R@JG8TJwEWQ!nFbAZ8y`DPYG3KC7}
z3_lw-;`fQWrZ|}qICxp^^DzSQ{6g%0&Y}jZQqTdAEQLRA!!M<cf47kOhj2-t4AT=q
zfW(0@6~c-EM1Ys+jReh*z(B+y(J;X36q~4RYNVj2;^M`ubR~jo(0I3Jv*)Ch3nA2E
zV85gtym@oMAz)2pqhWFXzdvfc0M@!FAy<`k-U*7H0Za=MGFVpy$SS79Qzp<Ocq&@R
z?LB;9c|LS&z~|?`%0po=1OHE+A^e#0CGhwE;m8CJ`=9^+G%0$9SzFGVld5R3fZG}P
z6=9!*E2)AxOIULLzrIS9qlO?2&ux11?(g=wXAs(E<>akV?i)+>bP*Qy&DVt=U*~sd
zgl~a%SMD3kxZftsxUkje;Ae;WsZHmfXWe?M?k1;xOZp{l{`Fq7L&<xOu<ANpYxM*2
z`_~><nHE2yjPkEdmHy%WuDtD)^V2K&{#JMJPv6hFFL7XhxH)P1M6#gim2%_8>p!ou
zrNzj`-0u}$^Xe}YZS${--@eRazHD^-rM$4?iPkcI{q@L(#m!sS03YP#q6wdi>h6K=
zy*qu*#Mz(Xf72)U&~Yz4IP>L4=R-qd#81TKKC9$gqt0f$E+^*hcJsINJxR8vRL2!P
zL|Zl2?UAVqZ|tx?U-M?;l{+`<?M!PVEhCfrPf;E$vzSv**C*LuGH2G3#{&T^-%MS<
zH++ec?QwKG|Bv-Qt-2x$`;Kw-58r)VshdlpJ_kSSckQ2OW?X++He1VWRp?zK{enwu
zeBU4Il77o-D$#YqDB-skq~=AjtIhO2JUajTMnIxI+{H0&o@as(4$S}E_)9yr%bVfv
zzH<I0&)47fz)t6|`YpSfzWm9tT0f`p?L&`6jN;_tue7fgjCRjDer6tSR{il+3|8)S
z*A;;`{MVSYKMhzSpbp)$%ZXg~_{LKhxDEc@^8N7Xe4W(Pxi|G{^j@YQSG?PQ-*b;A
z&TkD}3Irc=nv*Q{+3%;X&%HeDJmCEsarc7_>==D+-NH8;UtVk&_vyEck*WsGg0(Tl
zrWv!H3=V%hB8e#(dL>U&ZX#6noC?*8m0&}9>w5+i=j(T#^38g6GXejwsyUq7?YIJG
z!)@;p)h-()o?O05LFg4JEGl;|fFLIvR3P3kz>eG_!ky_8tN@3Pd~t~+1kB@xlam$0
zpf`{t=zecEPFiP?yc<kR0a)^A&5a~=u>rl>Tfgbsfx=z$?W{c%$^~fa(#}I3RoVT?
z!O)dDyG|3hZlY>3R{b4?efhzcy@mLdZp;}R+LIjW+(QbbAGBvWbo1~F#LLNVbP@K_
z<X{1d!dAM?F@*ydXZTmlQUFdM#*E1t$}(}85uPK#uQ|M)&MZ!nV6~?lofA|n0Yg<%
zPzxTU8iNe!xW7{(Lh8;<4q!V-s8~rzW;<05bQgDlx1|AA8%oI__Y&nIs<EkuqQ!}e
z4cAg<2|y5+!rN?%LEg`KcZ*OKIQR>I@9^_7f{-nt0wthS?S|76Z31<y-cZ4d<{yKb
zy8_;2>@>k2n4R%JMMB4_XU_2mI5u%dEMy)dFt5oSB+-*(o(lB@oI3*|nB9OU*Fb>M
z$kl#c2Hr_`zy)z62bNE!Fae=@bGef;2$%t)SPVlJ0v=&*igb)>m?8Z{3?GMx8mz9C
z57K&zi~>9qaybf$i$JksAmNEI{#cE`3tS-MO8gx;+-(<D+n!ju{H;`PAQ#vtP6nro
z3<zzB`uG_Q4%I6Z$Mcci9B`D&fQ!6Xs4I>YP?D+l1kq#Kzzkf96tjf+&>%lkJ@HP8
zq{uFTOtV+I8U&Z96&x=sH6DT(O`J^DI}Oz+=)HPS0HFp`!Z1x5ff&GI<|AwS0Eh(^
z(zk>*1p!RbMN)8r5s!MQ4B+BzF*9gZ+gUM#TL~y{wXkN6uQ<X@W+5As536|#azToN
zjTwLD08{7YMkE!`qhgmk!PkvG#oC|Jz%hiCZbG$nxMs$lrI{)J0c2nkz1ERVPSeRL
z93DIcF#O<xYx#ym2zKYpjLp_lQe%BM5#Z|UE+Mrn59j)|vQhd3gKT0F2nkpQt<+1!
zMp2b`d0SWEb(|pq{QeSxrD<_$d2T#tie?HIdordBI)0X80Yzs9D9i<@zyT31p5H;{
z>0|h`53F}mOg6ju1;<_K3dsOr5<Mh>;6O%7=-lXd0c8j(c#ELlR44tqJ6}DBgSmy(
z{saQaVLE8Y0Y8<%TMZTq6ZZfToeTpu=!N|EDl|sIq%({_Me0u-3G_1d<}!PV4CsH*
z{|Ml~{%WtnCtg%mNw(S(9)-BWK2sb=0R$i>vpuh=5O9%@`$!{&LWmXy5V!F2<+&eK
z$R79vN_917fa`^aHtg8;V)GvH9=NN7^{3$yunMPW7|DUQ4SQ`p_zJ)1&DY7Y2@VZ*
zCNEN3i2z3}Jg1XFkuZGk)F$du01k4;0?j-o6q+a1js#R#hI~ZgRa#^EGy*N8zYJ21
z2a5z@a4cI*D#~;2NcCO?4TuMEIp-BP{ewfK;6PLECk_o_0yg2vG!57wwIJiZQ$Q;?
zXsy&keXtsb9-<>xa7c|=lc>S=1VU_Lk94x;1xg{JI`^R*YpY`QOUxY9{Nu$i4%w4;
z4&u@#D%@I=B`n~<pp@33_Om*=M9&??X>xej$zYlkc`VKybgD(Li$&EI-dTrGm$P6I
zEVHfF>lJx8^3YK8%X6nDQlF+s&1%k<Lrd=CzuQLqqx>b70jL|qF{$e`09jyeIx~o?
zE9Y5eK+wIe1->v;CAKmuv>rT;;2DU^W%U)qm4?C81`w>^IY@(bl9O84z=pUM_+YSH
zf*f|y{!W84v(d~P^FMzWvSDL)n~Q{)2ZhOjoSzh=QqdJ)Le-O6rbmS&bo0y`a8ho2
zH{S?eSs35~$luLiowgNv$gPP~B?isGY9O*42N9cbxLJZsiE_*x4^qMNQvVg9Vz8qc
z6zxuyDG{co8D{3+eC+@1zm0M&X9Lo4W*CG){$C&OfA)9&OZ=Yw5Qk&7hH6o2Pjfml
z5_xgk%JFX=>%U8nHTv+V!}6y$?Qf2Ja!-6;F}>|;;aR#t%~qqf$X>78hvt1ZcHEVF
zm;TDRCtR`b)9Azd`&S+{>pl7>;`KpqV!p{wSs~Bj0&2QmD{H$AsCTaBt=SNJUC{N+
zjz8alR=dtLyQ2K~jg9KNvFmrdKfUOycn_?gc2oCFbmqE;O}}Fzt{X&O+j6=+Z!$3|
z@xX<xz^k8EKQd?PcF3q^<47*QBq*Y)_|a<aqoRF`(Ki>Wx7?pxuxnYs!37Vr!(otj
z486h5s1*9FH?93a@!LUBz_ABTc2$!<INx5N-7wkPt!14IjQG?M-ld}iGxA-Ae<)b+
z*)hi1aBZ?mHR#~Gc9$lG&`CaXO4_;eTwYq>u_;?-&n@xj#Tz>=4yoGoAJ^@cdZ&0c
zCv7FrF$*IKu3mX<u;cM9vmLW4+8jmci`K?}+w_{$cCIqBnjyHVn!KVuEj%p9fu#4p
zYEU!(E!CChP%Uhh9t?kZW9q>Y{ARxH(&<#n^KT22ES#=)3O@W25$+yVLWvN(U$cRF
zUHD~j!lhn+?#6{Ox{ZBi)0!7wW^ux~K_m(4J@?TC%<0wUEz4|f!r`!NqI%xa`HK$w
zcAk0IdwT0cg~V+B!Rssii}Gx0<9yb$k2cSbO_``(9B1FC&IuVpS_muGo-`(&fsV;^
z4OJ6r1&u4vK`q@Tpjv4BapqxnjY<AinJP>gI8|}wqM4|@65m*vN+E!LRPz#2LlBm;
z4g$rWAEGC-iX#^(T|?~_3EZ+c&&+C9feJ4^xV_`bpU5luD|bm6er^zhyDk5-U(^=}
zN7gMKpD5=?hr}|$CoU%=XCN8K0p0{xohJPRyDfA?1~j}-?}Hx(ccx`2X;wZ#s|o!u
z4jtUYes%gtuq3=SAC52v2QE;8aD|83e3)uP>uZ2rL0GeP4XQ!kLIFJ;UHL{TX2-Y;
zQ*AwjPnd~KCXjhyK`jKFDG;3z9Dt<dgT9@O(Z-}e_kciHJF!f~_06D6<S{%d5^5Kn
zK>X~0Go?=G%8x{KMh1aMgS_q)`KS}h5|LisLdp<a>r05?gH(iU9sr$?NmSm42rN0S
zD~AfVUzC>W0S^`l>%0lqP%4qPAD5<~X=rUg5zD`4#mtLZo#nsWdI)(yX2tS2K~l5`
zmN=9#x&d#VI6ik<4m=bT^q)^Eq{WjJ=yWZE!tS@6ZD-!#nl$2X)mvnc6mY;eoUyeD
zLX?u(R-g27JQCQGdvaL`z?<k5HUP}5nG6m0?rpVt>MUZix(LfadZD~#l#N(1yLoIW
z?GyWf614eF$ogf&$jF4m<p6(#;jUHMX`v&CTm;u*5T;1}F6cSn*(Lg8;i!2hgPdpB
zK^BTz%!=nzJ)sXTVH(OX;Isjcwb+;n{g>!M$cxp>s!2wVS?$0^NtdH~^6v6T-7`=Q
zrV`B$LFd9=kqiwmOab(w;3IsClvstu01wxv7EzMu`*q+8E8`Mi9SU2AuDpBX1R)#5
zI{Oi&i^WKAvC1B#lLi-9aLu+3h2<)+M{IOCIbo2&#FFbFra8jUhkn5Xt72B4qsWhe
zfI%L_o`{ToFecSx3!4hTJY*_PkrgKeQ4vkB>Jta+gaf(8svQbl06=kq;1@;R1FE2p
zn$<4c3(7$koL92<su|pba(N<1yT~>kIGTYyQ`acF-CzJ7ewOJTVrDW`j^3^wguUrI
zX*`gH)8r0<2!9Ml4Q4gSAqoi)i#3L=ZYF?${|GAR=7S#v<}RK|yhsq8a82JH3&td5
z@HS4~KafMe<_#kUET{GYF_~&aPmJk2sK#5x3J7h{>e8$#UXe`N%Wv)jbl#i^sR?k<
zQ>1z?(#f}DIx|^uqf)&OtiGPy<lJrf#paOmOr;z!_GTqWU~Y${p0W2fVRpVjrVRl?
zpjO5t5t!vbV7om-Le@*xz}Rie2<a`F)svq)*d;LRSGoDjrC(z=PDpLxMXpQLQm4;1
z5fG%kfaVuP)IZponKDBCz=Y1EM(kT@W<s^AZ}f}>9x-Etx8|wZfmspFY$F$&9Ebu_
zG&;^nU1&G{02c?PEo7uvJ@{Uo6#QhGfHI?;Z+3Dlv|`2c5Z`)PCGPgmc};vHYM+3q
z=0kB$004{<6s{y~AX->C)6{C}rE>G2usyAZu(f*d^wy5h(IQF)bTvw`f;3JYJf*2v
z50JN_j9Qjc;MCG{B&qX-H+zdIe#Rm5KxWiSm?qdl990jjiJIoETqA9%Zo9zjXWxS=
zVAz3TrZW5!S<El{%e*vr@n3JdAaN4ljUA46SUiEh5TqDLfc)JLmT?rsJN)foa>vai
zQ-Wac_ScdM)^Gn*sQDMk3GkSZ5l6`Cor4MwQzD6a=%E7opj;q;2I7xiU-fdvF2@oz
z&yuZZ!{xx0&mfDf1x4Nx+@IJnsQ?LY&4n-wTtk9%(ggC%!WiBHf!)#^g+xKOCcz0-
z?L;WV{F_Oo^Z!JP`fu@P^n)j!RXjCYw{kqJJlp$7$lPnUB=uXmPUfv&IsVm^CWT+6
z<hi<fpA%*4G0Ov{Pb*Ih(<nzTm76iQdhDHlZK|iS??RmJlB_LJ!~iD`?gaY#M7>$N
z-Lp4ttNzXCyRHv|?+(6a+8~rrvSSSMkS!x1R<KcrAvd_`$G>X&G#usP`EpZHT*{Hk
zm#a6Jr}=cmOr1Kvaj*P~xj+8C_KuBXOmu>%g?r-AbkvE1t9FZiTxa5E`SwKQ%j-v1
zLfiJ2uQJo(Jvq4Xyq~XczJKh6cW~CSSB|Bt>v9kG32tnS^S-*H*#`e7a<DM;a5v?G
zz4)6yk>5w6<p=a#jKOEWPsnrO#+=>rj=OKwyk!@DI=rmXWAegYC&}R``U%^Eh26fg
z*~5o^ZoN|Xg_m{1)TMQn0VPQ$0l|UA=k>nqp?&De$B(Q&&*Zrg>Rub4TSpk8aM<Mq
zw11#d>ai{kS!dBMoxZtw*W{MO0o$L-<C)XiSH;`sZe6i&&9U+^{}-QMfBX|c*Ij%)
z>o?iix$VX49zT@NR(`=7ROh4hGjXk+C?Cmso!p6B*1UNR&EuX(%j{Lu`3Q~{8{f^8
z+`lr{JF)Tm%hxi7zv8#73#nLsk%J}M>{VQ_BZBr(ftqTcC>N(n*YL<pjX$!yFMvpD
zA&`+GrR@pVjB;@F!O9yivjXW~j95mInq$CuJgXFD4!Dk<t(Rh%6ElJWylaC?7vQ+H
zKocq!tZ6}<xPF#isWR|3UJ9$R(RbZnbFeqx*efY8+@oCd7UbB`EW#`JK+GVBQW@ww
zddgkEQ^C*sM67SCwyu}=zmtAJ)C2_uL(f6L0S2j!49!lMYFkDmSdYO-3Pu@EpNLSz
zpzwB=h(h#(T=WxQ5O_h;3ddwC^w5<MXX9aR$>}Pz5<-nf83SavZlU-HC_19xK+2GI
z0=6&vJ6XmMG{aAGlKibYP$amhmu6|OfcqC1!rqCvn}D=J#>KDNX+p8M$Vfm^y816g
z^Z+AOY-t7#;_)CMXEz*rBcV;4a9`-tKp<cShf2B>LuSPp2*rkG49{tTkBSaSHL8|Q
zqs`#>$>MAn6Ab0OVjVE)2LxDL$$l{+ZSTqf%_-KE(1w>e;gU+(C|@y(L1>woVLZSY
zhIMYiKte30v*&Q3o-h;-#9sK$0F?|$z?l@#@k)%4R)OADc)nbCcm|n4jxd0&3&)*L
zhYIUd1$>{1P&gY?7z=PbeWx|S!GNL)wPt@{na)NCc*QHiVqs?^78lnAs4ac+M5PS}
z*b7D)<#M#hCsPfET`<@0Cj+Bwp--wbj}a25@kcL&8{r6@8@m*|)u&++OOX!;LrxF`
zI-VIB6BurA8jz=&0Iy^^5a|f`bTB57;UcX<fg|Xtx*w&^hZElK6f9D)@YLg_E1Epy
zIJnvyz*#y-KI73hrf7mZUb+l!!qD)s8?0o}?PXC^@+jw-7qdrHi@4Y_NG-M{V9v>l
z0wx1YcU|I7e#YU0@NACk;y-FYUNGB#QlWL^2sqJdk;YMWE7+(pU?FesP+$P1#lyjk
z+%`sR>fPRgU_|tNYSWq;B#Yyh&F@s_C=u|pq4{uGhEm5a@mK)l>pmy@BXM2XZbZba
z2`XR`{GwJLcrdf(#6YYMkgrfXXB7#D8qMcVgt5kWH3!%t2*W#>zM23Ft_BN>7EsYv
zk7ka;^DV*RMLVpVcGg(NTu|!ut1xtOB|Oc+a+fN*UJXgHdbnz&Kzfsa@=_fzCJ6~6
z0zK=!GLips+OWU?Tuakz@TDP>o^mbigL<q{s`qYCL+fXW0>k%3AO}d)zFLGe3ByoF
zwM}Q7Cb$&Hz7n&oQOqe;LIKqP97n<oh?l}^#WWNg=~j_-cXL%M5b2-Dhblu7>}<?@
zb+Pa_%MuN+)k}%EBgGMjJJsrAgh!(1OxOZ)rbLTLumj^|7a{`NCgj7^S-=XxdT2|<
zaS{YVczN(%fbERWM`6dMtl`G~{WWDUG5R}2cI7-$7g}{7Sf6%(Jb3CLd@G1~7LF@=
z2YRB6%-Tah$Z>qyV4W-p#0eVEA)e#}WfPXf=No4@;7UGe=vaIUq!6~L_IPRoIR{EG
z=A*LO<%#Zrs}oA=e8p$<!^{{ll?v-m&`IYhEn_g4pEx{o;d{9?1R4xHtcfPHuHqGx
zDnIjP1->=I69gSL2s$~B{;8nzm&gNMlHM%n?lT&p@8m#f{J)qe{_SP<?|v<0|24&c
z4JZg+Gsf;9i_AzPEX!ynz*$V$6d;FE4FlK%;3a@>x-m%-34S9Fg`Omm4&sRuyitR!
z3(|FuSO-t&rPdmMdn>rytzlpx!^>c#*V^Nd177aHZ1W@|@nQj!<{>qhz?t1(%uq(K
z3<CPE*$d(q{|BqH|2BU{kCofl_er$%%PGEbVxhz3Q{!!Q$}B?PyIs1K<As9AU%E!H
zaqb5gb<>XX_b>5(@!sb)p7Z<2@|C)xewTg9mjlkdC&+_ko(FVGFI6u56!l3zXkBx=
z|H=|(uqTSn;#eO0vTxR~$9I(mvf8b#U8JYN(1d4Oo^84K3uaz(nIy<NFY%{$X_KQn
zGa~=6UbTmFv~jHL*dL><rB~_b2iv{ZEcjTdiSbPDYgqj!5?yoicJb<KBfo5}Y!M9a
zx9f?~rkx&W3%tqh-S%tS+~)Aaw-0}C-RZjTJXy=%eeaE)XT?+5&Pb=K*TZ88_cXDW
za95+-uA>&LF!DQ*u`qYyLfgE=&;u?%Tv==ITkCG;>!a9v4U9({a+safeSxdrJieE|
z|CDxvB=pc97w%AM0=~q1GD8DBH~ZwhG&{bS|A#tt(eIcmHq=wM!lk-PiMEQ}X$MTE
z-Bc$9>W89ZtgsDlduyvxKJB8H6288*x!Pw=UGcsla7O=n{%U2pVA*W+e?WZJd$VJ3
zm*Cp4t>DeIu^T(~<NdmB9lK;Sr9?jW1W;^j>iVWGT+;g!*_+(^rH>?FLK_-=swp|x
zt|@V)lP0Efl}FL%XH}@dYFt_MPU<fOxt5ny6N`U%y8MBu_xhcsza8?glBX>>atXWg
zyZytF2VZ{Qy9cR6JG!{wr`aP>7RMO|occ=B;toVfkT((OP?4jdelT7QZecn@4<m_Y
zu?BIC2mqL-piK$Q^M@)RODfb*L1sRWN#EaTs*gBz39y%Z)V(}pwpD583t|RE!}~Qk
z0D67o$(q1$m|x1?5_}?)six#35GEFQv5@I1_rNfEwWAp*$X&VMIX=m|+`w_CCsKy+
zX~ThVe(VKP>2h>Vhpoc#%}fef$O-eZWPq+)>(nLe5l13@u>NPN+9gz+xaJ_d4-cVs
zbKC{)N+%k1R#*NQ)dQCRf&Vs~4U80h{s^{$19;Z1{C*ZP0*2>sH7Mx-mOo<qDbcVk
zkw(1-V0-W*#+vu!>o1QKn8oN)he2qr#5EA6XFGaU*rCPHb|CRbT$AWbe^+<d+vHlN
zxd%}Vvd*`%6(ANUz)_5A3`tdJ3VL#aI;!E+J>f{uD3Rq5TF&1Nm$aM!0=$JT0r+aJ
z#2un><onoa=v`~8Cdx@jD<^Y8I^GRmWSdZehYT=TR0D!^fR|j_i5%%Jgi+ks9XMM^
zk(GK<X${WMi3&82-hgj$+{1=dOjsZU>mI?`VR~Dgk9Clwg)7J(K&A#aZz>#9q5#4x
zxGOf}N}E8im+F(Vp=gbY8kW!i<E~4X?k&RhQGE{!jbsp^qQM=I_~A2v69gfw!BKey
zdU8@ea9Z@d+RkKv=PNdjPKMo)CyqBRz;5M&TBF}aP60YksGBLIeQcgG;ge8r%i9lE
zJpl>qPY)EJ1?V+F%~fQm6)PXc(4b&dL>3o<(^!eV1=)sZ2<K<fJ97OeqNfy5dCG1x
zydzP`d`$qyluhP&4)*Z7#4K|GVrJE@F7(x<_3{rP?UJx2-a@Fsh?rUTw8c>^wB3aQ
z_c92cCHoV}+xvQWb3SpBML``6%ek?*nqr{qs`*%M^aq%U$UL*KniO&Z4pR!p9xjEP
zI?V8dRo(0gVJD^qy7Ce%KvH3)=_=E;)ce-EiBM{mQa9qyGa77g&6<)mK&t_q@Wb7O
z4UQB7@}a#Hk&|DxAofZt=2TKJ^`Hij!#Prg60=%(ORNew&{T}QMZ{Ly3%r<}ObJSg
zL?A$BYaz|*$$3<bS6Z`C0UR?5`&DLpAjU@(ic1+H@=V3X?h+5+16zRxn9!B`k)>x1
zo?fbk9z(#}xHqc>SY0_E_0Z?D81S701V-@v^$Kfm7Az<H0OVB=1WzX@3xJKWtV>wV
z=Uc%t$JMjN-b#gj0sBZM^`J~)d&m_!k1*!faoYz4D~x21dU(j*K?$>2EgF?V39jEM
z1CfI0cM1XMnCOFg5adM%fJ=nwK#jz%2>|88*qix5f>5qXP<^-*g@cb8=`SVT91qU>
zx$t%^#ym$$wVLS7$4s$a^g(UgGj`v_y>cr+gP29FUMLELv1fe5A7gemcS4%rByk73
z7NT_YV?-xdspo!Bkpf#V9b*HcN(1p8NFk!Mfh$O@BnI81jhq8B9=EuRYf8Xnu~Bra
zD9~eMN)q8lX{d7l>~CkzA0lRcQ1>}es@wrp>yv^5vk$0G@La^e!qn_C<n<6&f&+{g
zWknI_zMMyru-#C8X8?f(vszr5%r6?O=sU$n8t@OLq6ZHrXAEDEjctR)CP}bn;q9sR
z7OWPQfDtHBqa2#}bUq--nKuB0F2w<=i|q~H*Z1ab6Tc`3gpeDmZ?RbSB3=G)AXi{O
zgz}i){4t3c4c<^SsL4|}=2kcE%YShD{ZEIFmjAUU!jdijx#;sBg0HNH{?^Yt^1mjn
zzg$T{pxo%i^Z!<R0^bv1=Fcl}|80hz|MY7JUvrF^{e{5;mUdg`Jez<l^u0^!TgNEc
z!4aDP?9q#NqW8b^{9f3!GM(-%e|Yu2W%A&g*2+H-oB0!ZE<YKzouB_!dG<Z`l<ZF=
zEy6!5h@HOa{(;|d*^5puJ5Hbcy>-0E!Q;vAl1pDL5bgRtYRl6lEqbR<IInnlD^=Rr
z^>GR6w}Y|sHG+a(;p$mUKhRePaC9sXAoqUp#jh0$3QNxUf7PKYvKRLR>8<Xim7U^#
zB`;V~b>-2X50=*10WH7#lkc}%y_?g0|C`cv!j-Rn-R<0ZbL*IQ*pGr8E`FaD$FE+M
z_meYktnJvPOA|YamfVcLzQKDN-p=@?W6{IM2*snK|J<wiXD!1En=C7j)cReI3N(!S
z_#pZ1<x9-=&nq8qY0ZDGdHdvabK9bwn9)nKA~)#j`;IWLWpwQ0EW2X!`+%(b+NYP!
zWt)EQxs#PxxZq8U(<1&dy6uTg-*dOCo^npVy^}}GpRbIzUUue3xGv=1{Rcyk-U!qx
zR9I2O_ohyrY9KxOu;FrP?H^^9U(c3BJ>ZUfgMC_cvDl$@-Pc=R_?R+t$J!d!-YyBY
zf4K8$r}LeOOFO-bLo)i+HYLO`;_MWQD@!eo3ofWqF0e}4w<oO+cf3+nzuR{1z2ELT
z;J-KCpLoNf4=vbs#x=R8P=MPWIf{)rRh8dJ;iPrEEzhq5O$ON4@U!E{PQskmc~M*L
z)mLmUZOWc)XFDV4bPymDZDXV``LZMFJ!`tI0^J{1ZGn6Qw(A%am-t1+luJypQ4zlb
z9cDSuGv&GJ1p_=AQ*iFBU4%PZ-{Q6;UTz?J#xNzIe%DjOTikwf5gC!@Zp%IC#o}_A
zjW{0BOUNd}7R{)P5#=6`@fQzqhCP`AadvDJjrI^GBiOPx%s}kBq(U~*s!#CgpecYb
zk|CpLGGsF>lTREHco{_0Mj<x|oF;px*^7DRPd}$HTOf#1+R3EOT(A0sl{mx{rIWu<
zCDDAwA$(P*4ag!;ILHBgJ6wVTE*1JfJ>-fe3as+JexlCh5n#7dnW$$$t|z0K8D0=r
zTBxue;1|%>fL)p<<uYLjUM{K(tEsQB^WmyfJrvrYGKc`xlyJNf8W3!?i<1Ym?DPUW
zT@(BqSK3)WJ%reF?oTldUA~5j@{}vB)FP<XOpK9{i`9L=GS&8Evo&x9Tr{l-57!3e
z2%-VInEQcQ3hoWUKpxC8b4RE~Q0S8vWu}I8kO@=>rN}f4;C~yHaU-W9%+&c%<jU;K
zY?qJ<-~u1lool7?TZTXcAGVvoV5*&I!vseF!_VB`b+6LR{8ED}xJ}FR5pAGXilWtv
zSsIGqN7N!*jkqyFe<?-~JqW-g_}KV~@_dxs!O0fr*Ui=7DIS0amiMg+or;r=sq>k|
zHXL5V5R@kY(8(ZgFj$o)helRM;WN;F?2Jit8!;Tz`pcu-l~%@xdue9^XmcObDwKex
z17@gEAAG@b0zE4u*mDl^N5F0_h{Fw>Ec8+B1+@a1C>Ne7&o>CQJ!K6^`XU3!*gy1P
z7N;-fEiC`U24bkctG9YiQJ+t{kVx;5DM&{~S+T6L8&pVeQ{@)TQII%NIXdm<GAGD2
z@jOd9*)k?MI0VUJPsm@S;_4^mXaUi;tQuo`!VMOi&Ec(uzMUl+q+ankrKb-kjYM%L
za1Ea*8kE!~LyiK%XPd$`DF}Qxe1Dv=o)csDi&W`EGl)3)Z&vJ;3Bo$dvw6D_>pIyK
zEE|!2*nw0=5p<txtUxRp4hqvs{s(*S9u0Nl{(FBI3=$niA>$A+I*5#N8b)$H52YlD
ziqV}+<J35(QqwdDsmWn#j6*^PilTHFbif#*qjCsil7vX;xqSCtd;OmE`~CKQ)_$J7
z_S$Pbf86W7Q#WGFT-W=0zh7^&1iZ904@499Zv4X<fKH8&X@5LFZ~?#IG7hOY$38}4
zhQoFh+~U=RI^(4jJxT;4R{d{aAc0q3)f4KB#LPSwsLmaq-!sIZ|I5w_Ox7m=2I2WF
zWK?A520mc-rz!BjRWYNoq`;uv77FW(gbuDhccpW_yn&t}yilW|o$RynT&bCCkbG7#
z-4s9pJPk2$#9D$mMu$q2awAj59GOOd5fcx>^46Sa6FEUC7)-b$?)7?K1S>-D2w2j5
z_m?X{uxh+z$?ru-|6ha<B8K*ILPMVxjSMs_f;r0ta%tec(?{JVwu00Wq6#4qxhVW8
zR5#tjNC>M13^q7`K1soOknXbR;%P7ovf^T6NwmW$uOf$p4k#3ev`#TEfXpV=O$WwV
z6ad<nJuU&O`d0@x&=HaP61H4KU&?2lq?NOR2%bp+SJ&MMAxe*g5De*_Qy6)3IGPpH
ze9^Vnvm0Did>S@Eu}C=KlOk~tK@{-y?)XT!)oT$>EB6DeI2mYYxg=CG*D71L93|G3
z6^+jd>cGp%j5@OXRAo&SHE=IfA+>pbZDzgMd4{{tu^SYwI<b6;1Hp_Xp;jNmmKz}T
zYjM%_22ulZ0&t&;Su3^CjED`Y`2~4u&kD+QzQIoyq!#0g|7FUq`PU%wZ-<iq_TOl(
zv^f2Xg?nFoki+9;O<^wogkQ)ndhlt*&%tR|=H8l9$1^6x+@98gyPKr+pTC>`qAdNd
z_<eB8{Xdku{?GbzV&<$Lo6kC?t@x~m8q-sE@p&|D+-tSM+rID0%#%aAnnga?E7`8?
z4OgUDE2NYh<l{{%Z{Qmz@MVXm7%IP=g6?@f={+6q&bGR8ZO<*!*UodL2F$^NP`YYZ
zI&;)5>U|ArBTd#JaJf$VixJ1d5XZ&u-%f(Vt&T9+GNXS?yhlR6YKpe=U49?i+i~o|
zB#`fS9p}X^>}0TZ4vhG2*i&dd-)Z4fJ!kWS`{~#1qsGksUzxW~PgT5nx}cg$<X^iJ
z(@#cTpOQNn+m8G6@x1yb<J%X`YN2~_Z^spDGk+_Ns;{V9rk!oP$+Gia!tC=arj>dR
zZr9vDdhuycI5m}IQj)vrhE7vmoT19i1m!d4U+wNU9!R%z>v^X5k(u2Zqxfb{Gr)V`
zM1YT-*-n=IB4l0m-)W^r&DYcCdx>g^{fTP+F~KDI`}YF9oWs-dZVqk#_^@Ky`cxm`
zI{K5pt&(KAeol-wF@6(wAo=uE)=LH4%Y^KH!M$x_1&#H&o0LqT9cSoG=3w>f!7vA`
zxom(**yTd24fg>tjT-aub~u>Im5Acb!G+qrXal=>&DrK5ddWw%YU+%8IVr#<`sT>$
z<^1dw0|WF&%%r$7dh4!dRG;OK{HF|LE-kr@HP9>0ANo-=Abx^d&Pajy3phL3BnT%!
zN{P6{9*Tw8yX3*Y+nz)NU&yGPD<&A<V3gvV*Lj5t_Cpkgt$wUr!?NxVDeW2?^(X`k
zIecOfijvu)iJ6P*1oiu{)p|o_J$a_h%OON8Z?>HgSqyU#)M^7B9AYrOL`_0TD+S62
z1s(=1m>@1>No2ax6TCh1b5#&H+k3cbg7r>MdTw~V^+=+bArWcjupmnzPB*d_(50{t
zIKgKjveKMt7(8U5<Yle|8D$ZM=Y}EK<ZDRZo~Yv47$1Us!xg^31ks67Sxi@58i0#K
zn&C(#_iHfud>V~BE1(+y&CQez)ET!<NNN-AI>4bDFHIy<9eWr7U_Qu?;aua0>@f|d
zc$Brtb+8bF8I)$kLM*G;G}3aG8RS;sbr4E6AmA_SUta=a73vmGsRfgVhJ(2oA7bHn
zM8y!+dnjuTs>do+E5Qnm_OcIkJCma}n6%<jdM;_+5MB>S1A`Est3o2JfB?R3v--k=
z0IZ~HM)waklLoy$NoFKKQ$xZWD2n(<cEBRXe1dKWeI_aa`U+IX1_Hq75_1K}H|m_w
zZYkCj%-dpSU>ePvCG{oA2?F3177PXE@CrUuk2MDZIsyX$8eNVJ!9pJl*UG&$*+CM(
ze|FN}U9q?(6qtAr6ZV9?Ckv8p9T`MXiz;+dBEeE=6}aJe+@d9QmM`6g34&H{7<c((
z_^NmqI?f0dvU>8Xkm3}3C5TuX*dj_moD@>v-}uN`zB_?j)!@f6i)ORHXQa^CZY=_b
zn3$D{iG^TlRsbA8@$mvDvq^YyhG-Xaei$#Gp9O~k<sxyhj&glMi4dIO2n=8eco^-$
zw*o9~14@V5q_p{TTm9x44>N(<6}F^E1R<gI3ZXEARUK3>*EfhMTokO}lBE`+3Tyr1
zH!x*x!tO*rSD#8m|AhW=YD!nykOPvB8+k_egTpV96zfU+a$FMYz8xo)Xh9mn7vza2
ztrj`Ra4pobQi^Gad0*Po90J)&1@Yu5bL!WLuUgc!U|Epb?A48zCpK^hMlC=r8dgf0
z93%D@;kdv;6&rwsRAy3S4fZBv8dH@-by|w(n6!pisQ7nsO4w2n+yS*L&PP5Jj5kV&
zafj|tu%URUUy!tNqR>K?1pU%_{qR`2!o$)?86!}H4t1dl`^$Ch`qM(A-8xeMDb<4d
zP`#P3#a36V8k$|Cu@pLqLU$|l05TFLstpPVfUi{8)Y8lykkv!fVwyyb-S4ybK=M`+
z%?R=xhKfVM%)Q`>k~eEl2LqXD(<GZ7fE7yWn@n=X*+g1<KAB+T>=59N)q_ghR!RIt
zptB?O=ANzSpPWUT$vmzNCh@sp?Jq;(Nf_03#(cc6R(py&z(TCn?*|mr;7LnR_54()
z3SZ!(3c(_m<X;ucH23^WUy73di_Fu^J<P&!vmW9J;#rY{naZPZ$OytTC}0jA9Zccr
zgosgCXc&$AlHu}s@CzvjI*Up<*CuBH11m^wB#W6e(f0dyCW$qgsH#l{u>f08qF#<j
z);2kXh#IZTJi_(N{($yP9EFj;Db($g2?(kgV0N0vNhKxhcOp6v7OIds6+=4(_aR4y
z8X2j7*uD_M{=;&slH^$p;ZxvNh#Qs)0fy)#Hslk_vR*GKlBe1K7b$mU4sq9Mpx!eE
zrWPko4@V2yWRU?_(CId_0=Uwnu{BeLT5=R8DM>g5W+!=^Sg2Y)#*z|a|7j0Es2y7O
z46UtB>zJ5Y@WW*q;MyKnE1Kaat~W3peV_6<EfgUcHTU<ViyJkM@fT%yg4Bs=Od|x|
zf=8x*lDk~P&pkf&gHGS%S%K$0uzk<lh9qQ9tRi^rN_$#6y4vrmS5-!#$3?ACJo){{
zoNd!lg1JYYPcMF^<((X|u~%&V6xtm=LpMK^etDma#Sg1;>l3lZAG}G+G`bn~+2mKt
zswH{ln4~$jpp)@0(dgd@O@kJD|Eajwu|7|zu`X$JpJc%t?Ky=(e=%-$rYhBHf*(~L
zYxAIM3t@f!^YRxZP*Za9KadV!hy5R#o&Ntn^Y6b#aC3UTfNSJDXHR6V3YRzUzL%&N
zGsH7k{e0PN|6Bc9mHVMt!O!f9_wb3GBYoQ)7dA3{I(n7|E?_#&i3aq6BarG5SKD7x
z$*o(ene*iRk(HSPl~$)6?5UB~Mzy*cV#z|UmEO6I$080Zhxi?6inOdQ=-U)Ne2MaD
zec=s1z3m^U1vYNo`oFeq327@bsl<+}^Uiaw9yLQ(ADHF_D5VKWGl_kT*@p_xjvcIF
zeVco|=lJV4X3@IuwYt@8FD$8*<&+vL*8N37&cBv^SzPpe>I>9eW|xFcZ_wVj_TK4d
zH_<b<MgEyz#?Ja4J9~}Z<@GCeF5tO6dN`#0+Y?u#s*Bn=VdHtl8h<)3Lri9OYVyd2
z)qX!(^D6h^qnAsjr(LpDrGL1d_q5R`wW>*gkNM_T`ty#Me_wUTf2?7Nr%z$3QrWY7
z^yRn%NqJja5BX)MCr>?T68S6YOZQJyUVF6BdN5|sp;n99osWyBD)YZfz0t}@3;p#&
ze=^PT&h)#2uj1eKlrrh3j+2`Q9G<ClX6AmGd?MP1Yxam8OqtS2SI=R2?Y(YGG-?ws
zeKFm#*MCh{nd|iY1y@)4+1I@{I$fKbiW$^h*EN#g-#OENMSm`eyF$fKXpKD*wCp3T
zJrk1LU<g%}CzRS8C)W-#_^4+=@C0NRU%KdG5Ym9Ye3&uBHDc|12aUDl;|W!*b%41}
zfTF@7ot)oZVh#P*@U>%tD{dG+bP6jfp>EbYsHAxDPUMGP-nsZ(ui`gOJk<o8;=_6Q
zdZ*w%b#S~Z)5_Nf5=3I=@|_-JBZmXO+o7uQ58nZ9QRO;PdghS*g8XqIq^-Ay$FL>m
zN(}|cLQoOJe?jLTs$6q=4yROa7Ey@G^%O9(kjG9oe8?`%m%f|jqo_Qf=TAY=A!=<>
z$Si!aX#c9qT!1VBBOKUkFzPWwfY2XNIIKr~LNK%o*F*9iKV?=yVS01h3||ZgbgJ!R
zb|w%gVvIwsSIlsxec?p0tj&{OKsDi8skn?YWF<Cxb^`g&kcR>liS9;r2kj*vimGMd
zauA?n5W^)9p!pE3RgP@ts!hsDw;-ysp566Oke$Lp^bEUl2&VWXpx+=sM4}mvL9CY~
zh!pX32q&O&(ladqHw^tW$SmJPl`ka;gX{~Qa-&(MV=lvU#zTB^K(IU+n9lW!SIzF8
zlN15ni~%9*0zuBTLQ^Pihte1z1voZy`<U}WBv?GN6jM9RfpNnsTf+oX40~l8{_-^E
zk)d-N7s2GYi)VS}#}6Yy;uL=Q7#OV}`DWJM2_+?baXCT%M|iC^g7`Y5$K!=|IN|%t
z$l|oDo{jLuRrWVB^Q(fS($Rj2W@tfLBQqAxdse;*7&&P1OYn|_>Ti$ZI81|C`z#--
zz?(v)kXh1TCfMZ#>7appDA#o%r4XfEaY9=(003AaCL*^vJrGfb=tT0Cr6@*+SW~7W
zc%}xX@V)$50ip%h$7#;{Br$kAsL1f(C|BE}3pU?ik-cS=oZCVtI|!_{Zj*H$NDLmu
zoK(xhHDR7(B1WwTrVGbf;NbBA4yM6B*hoCZ8hRMafN@<9asM_yQcylPpy1~U#?mA+
zK|)s0I7hh<N(Haet=ncu{rCo4KY@q+p=YmEiBGZ~b#m31ZJ+TFb4pZy$`FW?lfI1$
z9dM)0X%HKLn4^1R)`GXRL5McXE#7?y;D^a{7%5D(%9SLdTX0rR0TK#MR<a6fPwF9{
zUoNOS`MQTfy?t^={>gNCa4FFP#euhOWbX$EAbZ3Er`9BuIl+#`=Bj2kvsGLQX#Vx&
zq`cTkZvXwSPUtR36(Y*B@i?slnja}Mg}78JzbXKlR+go_2Z794XlFPI;@L0g+hKbG
z!t5k?u<X0w!H2jA`k3(3wmjX8w9IJKiRvVy3eIkn?%IqqOZ6#0iZpFOwq-aM{KL1S
zbo}7J-vO*UD`8nNpN619V0w_!)HHX&41r{#6k{Ne5d?#?|0MY2wx7U5vjv!u1MI<9
zzuy<U*6J@Wr({?Q=T7Sh9jw|QCXrS9;urg*7zfA;r>OReNCUW=HmMa{&_RUOvnXo}
zqW)9Qj0Mv^UwpjDm(1JT@BFzGh(SL%n3ZFW#H4%&_Usn{bU8K=6J@2K$<)s31&1L}
z;^dNoEcjc@`+JyRvO|EjMi_2I>p(Bl_IOv#X>KDhqJn!ai!G)kl3SGfMRx9$y`XDj
z=P3?ul%~h9Q6dLP2w36q?3B*-8JNCh-cl#og2^HHxw9dn)oS5Rd^~1Yk2uYi8dB!K
z@{@PcTo43_I*<j~@>b<YMy_F@cyO}4lb-_3hA8D;j{<Z-n-T;&7Lx{<YL82S@C}lF
z+5}6UC~Tsci0qGrBCb810SciCzAh6mOnP>J+fp^$E`&hPV_38Hy*2G)1PL7rp1sdh
zs%?vF=P#;{ri5YW&qN1nakrtcQt`rA&rWq;32c1GCVQHB2VxNo#jNY}wCOftqq82?
zsB5O2qJ%sljq)JLvTWS$?jfl(gDqnlxlz{!x@8LIcHBMhwv}qobG~ZZblK(cLv^=B
zJ~-^XF^%L&#in}tMN~ilW&f5>Y5oRBvEK{EW$>aay+^qR({F#smzlm<_E`xZ-4Y%0
zO?CWXw6>4_QMAkW2YTAKs|uf5Y%*>X2hk>)R^R=!v8B$5^Oay#?zCXu$&D%g`PNm<
zz<v9Xyxl&g@Cd#w9@ilGWt#gsgdMy2jO9k(ktNvb`MUJhaItSk1Oa*a0eb=icBU#$
z?BizHUff>%b%46>-i5xS&MxO)(mmQ~+dLiLI3Is>W1w>7+q<K7_T}N1td=FG9sT-9
zHQKA|-p#s0Tz?&xN1j+4Mj$J9zn8K{ZnV9vt<U|3_iJ5$I8{7icT^OH96gv}u*c5U
zf6#R|i~d3o8QgiZt}j`}vfAm{p4zM4byewzro}R<TSG*Ij|q$WGUn7?a|O*zE!~Sp
zu4@ry*mm}3J+>C)21`}G{fjhZ?RP4!WC)MTUHEjP>vHt&9q}c@8&(Zpr`u}$pQ#Ai
zMOsf7K(nXsdM%2y$(G_Fhp^Fx!JTu%iZ4oT49>n)n0n=6cA;iL$I6zizxR6SUxaMK
z-<bNND9;t`kjr1a*>lfd<o%AxQ)y)+tep#Gnbid`svZ5c*{PxH?80sLwZpv=Fi!`$
zis{|ax(mKylbC1JaEJK`kJVdCZg~2=#2gcw8ST2c?zMaSt$3l_rT<N1zr^<q&6XQ4
zu*$1ai!VWNvHK7G=dtq{VKsM-7Jl8W8uisJ^jhc3qNWR<Uve)i)S-Q6SNGnlB<r61
zmfp53reEyL_w0%9T&0cSmeX8oNq+U&jmNZiM82JAaVg4J9j{P48h7aWrx5`;k?j4z
zE2+GFA@y3tw!X>AVD5*@+L0GN4-&W3C9WU88gJXn((4NveBRqlX>%H>vl(A?Y<WnK
zTTS(j>^;`u@8&`-I9#|lZ8BJMxVIp>iz9b)F0dZ$IAb4QLViK(9)Di(FiA^y96zuA
zB*?M5-B>B8z8Xi2@MHYxN@yjaT3=|UdIB3=A@oS$k*@BJ6K705Y+PNwZ@kJkLgn{)
z*YmH=Zf-@pbXyjF@2}rrV(@YHm37yqsTQ3zqWC9RYO0cPiM$<{+K`x(=Uq86L7bFG
z8LN>(m+K3Jvd>k&9v#_v)H+~K^Vb8dR=(Zwt{ShhJZ&XU|5q==ze$Sxm(++>#J@1H
znKS3aYJQx4U-Cl91WU;%=rEqx*So=Jz+jBw!!J;@7@M)<{49)+3Q#9&X`##GrXvz#
z+)c1X{*7X>sY?^jzTW*#`{Og^!kq6v*FR&fmqEXz?(4c^P}BK^lwU=U0T&B}aKz!_
z6St*4xp7k_f8JpF<z%>C2cB2h?m0CeU$>Jg^xB(mV$6uv-@B@$F-Ax<wP+Xag@#@S
zdjk1w(|!T;jI1oC*|4IkbxyDk<m)*W5@KK$)wB51p8Wn|N-}XtYeLq_6!2qXAFz;U
zCzn4Ylyg2PYv1^^sUj4!v-Wzwwp7+u%W8R7{W;HY9R+$+FFhr?o8|G*W5bF|FN!i#
zJjcK?v^y#Ut)1V=@06Mw#-^@pkr?Q^%5v>QMvTUIcrc{Xkp!|#i%y6x2qh${V|OhF
zpNdE70_jFAnihbKvA1?O0Z@b`Ea{<HfQSbZN|S<FzGyIXz^fmhKwgrVNnFyC7V3l(
zvu^5Q&O_Q^GaiWqIMnqd1?Uqulb=+>i7myVL0KdrB3pF1>VykQ1l=Q*_~=3ed~`r*
z!T_<0Q{Zbh50-SyxC6u-EZQOHaNobGcGTY25T;SAJ*J>Fr*g&<-aNr=;9vq-VzC1C
za`n@THfKV~g7>L-GE92N<!MO7E!NveqN>p>@Y{<G2vngF52P?%p|!+>gX?Cn^t@+&
zD*20;aIV4OmrsJa8YKuY;nlJtRRssZz79ZCPe37oFB`WOkjoHRG9&e?b>_JlIl~yQ
z7eC7)Qh1wbL|uGwK{>`l9MT*t1q_ITN-#|m2|{Wn5si;xtJ0;x#4dEC`%MmJR)E&I
zh~<p+P*7S-`HeX{IIvM#THq~Q$bw32c^uMciirf(1MMWK_7{1X$$&8GFV17k;|uG=
z<#B|Nwy-SK!6XzN{hNoq>-_$*i~xufqd-AYo@C3d6ePEWiWQ3gDmn={6edp0$lf<n
z1C|8<0RW~+iV3r^eCOr9Br0(*N!Aw!^Mg2aUPN(6i6_&+`Ibx+0<bH0FvseG@{0iv
zv3#-_sT~HPA(jhe0ng#8dLSn_6(Pb8conJ5_no#|HM65eTl7uADFAlxac}~F%g=1U
zLq?ab7fTZRmw@?x(Jn2Y@Muzv7OqGA%+<s^R~m%Q8E9;{pdsg(=4A~)HlVvF-~o7A
zB*vKakmlT%%DEp(L;{A=acyB$k?aVdyZt_#6dwZnQlpORCVkVz90QVP!U3YxA6P+<
zf(t05oiCtEpwR*bm1UFxTWV4QK4KE0zH$P@*FS~b$B5uI;pM`5@@QUnj2x##cCO;9
zP2nqI${m6E$zEcT%frF`C}U^TmGc;dhY-WkwT#1gV=O1}UVdOEhV2QNLj;O)1{qOo
zxHepwZFf!!b)ohoC#_BCq7xLH5IsGIHX7Je5twb2xTDsn&roiP6VYY*7nd{W@1cGt
zlVxC2Q3a;?h<m6QnkCJaAShU6OT=|P7Mz4d3$K>HkhP4;G6b#wzHR|?YNE3p@}5+d
znXG?bdYUg{=J`S`Yo#qpzQ9+S4OA|OKIn!T2~t3=UhoE!T&_T^mW?dnAD=6ng8Tqb
zB3k8fg;L3~u9}TBy3sHsr-X7Oqb6UQg37L}h`|dVBVnXxnUPZRt4{F^pf^A$vnV24
zr6z?SBO(2Og{bqe|4KxrFg0`10GbG*+qA+GmVA#{zZCh?&RmM1tCw`;SkU;c$hLB5
zI``wlXH~B(5;}eyWEQxWYpk9s>c<ow2654F>^CF`bqOWYMW|A%rwq9tu$|;nfGan?
zHq&&}$=yP5P=HwQrSWQ~Cg8@+7ju2mz-<j#yy#~_t|Du^QO^+6QN#GVj!q`R_bCgD
znO3GL$FdPTzDe@#lu7(SmXWp67!mE+B(moZy-&&S6p!^<7NOkKOZ@W;{Ec?*PEzai
zW`X0H`wMEZawBxo)gJesjVn($R$v-t|CQdi&W|$NZCgG<8d=?9G_<asy8AB9_~(}F
zwri(0()SEi*y{Eu9^6|NQFJyd>IwJwH=>u)q_MWf>JjTvk|HVp=~XosPKYYi_NCpV
zVeiiS5oICsX^NySFO{VYij!qtIs+5z-#MkeZJC#Q6fw~{yZUloKT-0}BivxM%5Mwr
z$=;GX-FN2=cKz$S@|>-?zRu*hJ7DK#g7~s`|Jj`7HriW0p2INy(LT7#<$S$ESoZ7C
zt!0C`K`3@P`EJ2-$)n5<E;Dr2o(MU$t$_|`?oRi!`wzeQT6fmrh34;^wAPwqx@c9e
z=Rw#zN6Icw)XKky3G^|!^Wt}GZ+3zgGrR2Q`1+re+x{*kBZe*EtHQsByKM;UQoQg)
z==4Q694YFX-|PJs*>MT=^+nTV6AhmmWSg+7%YId^Z$Eq}&qfzbpS-%}%o)u0!s8ok
zR$XANFX=pb?wMuBm{(aDqYRdjcE=Qvrz>^ogTXxz+Y;MKmT7qLCAQltzVFo%+o!h!
zV<c$ZYszA#KAP#iWUJYd&g)*DoXXc}eTV7qDQN4eb0fsR_gw2{{pI4)fA+-OTlloF
zw<z1NeSDU(^BeCqtth^f>StV;=HT_~>OWr+Um0cY-TKHtP_dVsas8ORQYj@Q)ZW_G
z=j3cxFUr>9AB8_V15_tXOL6}aoH@q324~H8$$rV5_1JK!<mQQ~K(A>V38s;EYgvTC
zY{UB6Jr+%lwgF8yTG6kqi(bWUOc~2yneL`yB^6&)kG<=TV}7KvE_FY@cQ<M6!wY|r
z9!^$Vlf7;5hmo~56Gye)xb8=XH*3&$DOEuj_cUggU2TbT@$-v~*fS@jaVY;J>tU*&
z%ff~S%n0iv;p2}bz6tkQs?@MzPq0D;TxuIA#5GkO@*)5GMC{TLS(WAajTPS19e3?K
zo1|DP4Y#KVojj2R6)yD{_TgQlTYi5L8tb<9x%z#VV^t33B%f9N8e;U+im@y3go5VT
z<MBo=b@@v+hS{X>HzA?(H$Eo5+F4{gdP_ZSr%Um>x~Y9HrNSk*JpCFrt*%{URfiKF
z`fv?|+XYN~t@Q7p#FwS@uQPf!`g<u79Q@a}v`)D+LSiz$D(!dRbJCi33ZIe|@VAe}
zCSH-P_PD$4b6BEjVq`wLpNH(-=A)gi*;I>fm=@eqw2L1ZM=9~lHp-we;>t@0ns-pQ
zziaA2(Q{wl{1{m#s=@^t(a#(?@3>kX!U7Fsx#V@(Yrdw>FSQhT$KvD!ya&e0=4M^-
zukSp6`Kz=J^)hqk_i7oPyD{7(PHcNX?cJdAw<EF^SCS4dpuco66IFglPc3z8^0+L0
zFhb#Ht;vB&%j}QC{u>|cwtp}4vomq|n#U?}*K3C-cWo``+kmxStL&NQCOeejdv1%B
zP0E-fk2z39I(+FrOuYV&{Hp&mzb~$Ky{@CLF6h<mtS@mq`+omRH2Opv{r2~ca;3>V
zR=y=+!Cpbn!a5V`4&Qar7aX;ftlzNf$DvfT&^xQn4QrxRf57XwoUk{4+p{p}KsowM
zp?R`wwU4{eq1HjwU`5w9-{kz%FPqP8?tT3(^yJ>FI>YZi-HPAPUh!z{%=&(pi?}ew
zCHmXX(tX-!@fUiEPhh#ZhXymv?T%1MKZ>e3Pb*7zgOmSQZ&^so+e?RgUT5~SZ9MV5
zHLAcfU+?zlMzNvy_vXxdmwaA<{~Q#P7(J&wv2XwBgw>xy??-!vN|p;gerr~bnVoRH
zMCuGF{!)2%Q?K1m{f!roke&^?DIfV1XVtgCYWdsq54Ep&U0b1J=&#xLSZrSm`N?+O
z>H|L?Nt>2|9X)O*rT4>M<c@#N)|G0<jlSNm6qM`UcDCuU$9q$pGIv~j{)9uR-5ssC
zPU_l!X4SR^+KE_7U(539dGT1>+l_^Xj9^pAzkmIsu$yEZxx|h?e!p0^>(Pyy@q3>=
z*maM4Y;?tTyCo4OvkQ^kXP!UsB`|J~hAcf;*n0Q+U6%~BTBqhj)id1Qn!0T_lLKWN
z#=lFuTV@ZfICt)MZiYYo`KJ)3kKHF{%H$Z&WWw`9d@HS!v-TlbwC1w29d<;op$~vw
zIjFD2R;RRTcNL}9&WCRN(wUx_zd^E=^R`N%+#IWindA!J-#2|5T&)baH6Up~gSwM{
z=St#pD2n$4r8i0balb8E3c@FloUpn8DTZXr$;i17oy>c{=kS0MA~5ZvCpdWMlfG3e
zB!(VUtMc1u9!1_3fj`xEG4JWKi4375=$4BmHMhR;6-tXz@+TjkD-sucpY5P|0t9_j
zkU|_}W}SQj*-Jem$l^(Une}uq`^9a;OM@>{{WSJAWPPpj^dtiKF(N0}nn)|BxFTy+
z7>nzL6j6)1uU-<WMQO|#JfP4nFVmA#!cqN0@(f=M`65WBiYG%T8E|fJoR$GU8=f}B
z_Iv^JA1RWnMJO2(PnWhb+n-P+3+NGi9yF2Tk=R*Mf_H5*2WnopV-RCXT4cfjkp$ul
z6r#+>VAg(cRKRCI>p(_KIi*5t4&Y7y5d^QzQDy^Z-69ARgptQV+7^i~HJlMJ6+##3
zGH53oCsV+*$w~wLzA26`X5VkUn9+uau;W}QFxjN2#5r689*9<+4z#H`J({3jCut2Z
z;uxOHsw^OJ&heo-3C4J<g$LlXoeL>M+$*45Jd%w-e#lyVfNuo!m>`yU;H9LMlUz&^
zDa}_x>T2gCmtY1(6;jIJUI-^bX$>;TMnXn`DZJ7I{0b8swa!S`EntNLPch_1abj>%
z;i>O`c^Mg^i!~22e>dtG0Mj+rL*5k=#M&;_vbm#LnWu|K3i4DVp`qvEWgbr%jkyBQ
z6r>m*n5CisUV|?lVj??92rr3X{{R?`twvumc!YUK5)L{nPy$9Qv|em7fLyFHKHgOy
zx9qZnCo`mvPLvP?<yTcvUBpkuT!%-ETzgt58lNbMC|g!7QfDDQkLo6bsC6nhS)REp
zHqAv1gWE9(T@4Ho(xk|N#@FEK0~G~W^ka_v_JXI-fApBE+&`x$%>`E`JWd!<*V9^)
z<WFXa+3DH$x@?c=OU`AqKUupdlv`G*gKbhZFsB~TO{9UOoM|5_wV4LThTmM+%p{dj
zTr6&M3_6oEP{c1Z4|jZkiUgF#&#^p3ElTU4>1l0phsX_UWM^XG1(uc^w6f6gLpSz<
zi3(ApMXA4jlRkJ_q(IG1^9}bWgN=NuZHl8B#Zkf(muu9(azO-?uKaTkFc_JzQ|JM@
zp;jt}O!A2qjb$n}JQI1Gh6l=4VtEfkko-PLg`C(L0tjAyl7jeE=9OYnY+&*klR|=-
zieF^ma0rwYVQ;g%PMXXK4SBG2w*5o3#^O+>{lGjEHaUTJ+N(PW67UWIU}zu^N(i%p
zU(g;0`KJc<Pa~q32_};JLgFXcOg2Cl>K@<`GPOuOv*B%0Z_RcGlrMguok7Y~v64mX
z;H%=s)16=kMz*L@tf#mHSX$|ZX$$r6<PPa7QgVlSD+BD%5>MJ@1SxGU9`;HcSRBR4
za7Xg&%3+JZfbVPAqV!%$QXkaTbxN?Hc%}eBx?T@yG-*Mp=V52*Qu5Dp^Qm@ldP8AS
zsu4}mduBs`AmzhiD~f(kftw!EFp1}YjenMp#8T~!6GDWGk8+KPSpoEk(B#RxB}9Lb
zZg%W1uEjjK*&4#Wn{Zpr+tYrM;dvziPs+E|k<?f=HN}-^PlMGIdZ@U{U_W;uK>-B#
zhluky4bb(?Vm&`|mGG$=9){Na%G#b|b^z|BBU{`BN#S~qLr`UwCzM0`shCQ5C=6MH
z6>D@}QX&DPX3CSiE4Z8j_ITJypG<MlOsn-aOFw$lc}{Yag*?r?Pfza}TF!M!Y?gey
zK2ESg{Sje(nKQFixL>2K&?W26LBzDk`M#;5SjKr(xquF}?F#stTMo&(nR%bRaZxU?
zv@o@&a3d{DWPAC0#4`KAhN$Ij#+QxlJ1Q8qRAno({5Qv69dG(+WqiJL)warqQ^oGb
zLkUaM+doz2{nJoJ?J8vYoc~H2JX%qBFDGIj!F(6D<<-YVS-I(kvOM$C8*P|p+B4(g
z)EjSAUY+J8nw>NkUVHf}L%8GOIi>sM!Lm`btDPmqSm|&D->8rMn1_zVr<(-TrZ-(f
z3m%#33VnqurR>qgp)b!hU0yR&7T7ZF0_7UcB?M-UeRGD9sD);Ht>pogHSucsJ%`((
zu6pt3->YqYcQt7lSop4aLE_F1eKo1@#qK91M{W8@x2*1*xv73P_#Va2`Mxf_zg(w?
zwtKgo_mr9WF_n?qjX{@e<01l2SoxMwD?ffp>*@bte9B$-EB>H*U?`#L!a}+GZL&a*
zT7Oxb+EsNl!gZBUyzb$BT6N&T{7I>!k7K$rp1%kSwop}T^0Po+-x9Vl(To<OYtM+g
zFJJZ+{Uv@w_C7nIPv}dckRdSs+90v%d4qafR~d%tjLc$l6IKc`(+KCjMRyK8Q`tjO
z>78Go_3}R6G#Yvt)3}ZF;>7WnaSuy<2zH^5ZXNt_-2Qkzw&Os+_`VlwqHt3jiNwQy
z5ucLgA;$O6pXc<Al?nzPrWgCIaGVp_Jexh;AL?2De84W|$@losZ0C&iE6#}wKEFKw
zYD}%DT%W5jPVw$dj^lo4UR$_IB-|C~t8%*b`{!)Wx(wa;`5XJ!C1fcrW1c8VXB=TP
zT`buhyEDj4mBN^%zq|CQbI?NFBeXDM!$C)MKfUlp$jv)?*ihGxopy~{ufuk+kL;~U
z5dBX1_{Q(*O8<mkt;BdEf8`r4zaC^aWsRyS{YX`+Jj5Dt=#3dXouWAEzwPF8K`8Z*
zQrPb^-U5{+R*Isn>n+azc48*~uK4h*VCC3QJ+o^>HC6Mtg42Z2(e=6C%4iyq-J4|W
z)vbCR?h0S+t<`?};m(>8i!N>ex%|9&oV?-Q-_4~#Ysu|^=<R?R>o|e8V=O1M(qh4B
z^?EnchQW0Chjk|fC~f*RAHEMn6lFeLzbA@$zjJuc3B?P2dH%DrtM1*YihA*(x$o8-
zp?HLK@LRV^P|K3YcPVL4lk-!GXZqH>$nbyH?{oA9rL%kYO{|UlnHt*|m53O&;jKpN
zeMJvrkIno_6B1Xn+hR`k{%7Oh|H`++s410fB=u7)e2@C~&Zu9d$JCzxsSXXgx2s6p
zop#;nY2)(EmpMyCBv-Or!!aUdWPR9Vm6%Ecy{1VmYa^~8l2{t+ffEzgr@;ZgflwOK
zB6h$)uQ0$X4c~=NB40B}_u5;&wxDMdawPH9=BKwRkFAo@ykbufQQU?TWqTvjD{q(?
zSP59--&hYcejoCq7wg=qFwI@Llb7|6DQdiMtHEC+B3S5iKxy{Wcop03IF;dJ9xM0R
zT>FmP)RT%g-};wKV-^(M_ByzGt9mUT`h4VJhtA3-iguW3D{cPB_4Y@4BfFBd>Mw+8
zVGp8n<2S6?ck7~K;gX*vyyJJ(*S##2pzEXgG~MU%Ydk(E*X%xI^>j$F`$K5dG)`H2
zm)eaZ10~ZAAI@no`>Ox3uq`ED{EKk*w=^joZss0*<{iJQ;-(4yTlXoU)v9CV;hTFW
zwEVYK?tfX2ww*c82|Zg=v%I$dpHxMC!kNOT&YioD9mqp%5LckIxClx}(Q@;l|M(dE
zpgQllHA4QCDOYD`u`9>Z#%3|CkQxq0z9s+BJ>w+Ytq%OZcu0t=e0ikTsJ<il;W_&m
zpr(wuTTfMN?hBOq@zzABaf3M+X}R)A#jS%9l#g%BQ(Z4N|3y@)Ph9w{AMXBjpU<<;
zON6w!ZC?A$SCm)jQ{Gbdc%N>zzq$q6L=WP~Q}#`@C4Zm722SCfcd@!wy;q%VyIqmE
zlfOCQ-Rsr61X}V-j+)&3t({6;@$%<{Tiu!OtzN3_TfZ8AZW|Bse%xWnD<$8XUUFYD
z8BWW;{xJ|0lsjB%nke%MvA;35>CNP}u563qyN@VI+v3tj{XZ&tU)qV}7e-g+CaBFE
z#>V;^x>B@tw0nvy6?|uPT2V)js&2w(Vw67X_E`D0n_ursbw9eaGhyFzz4gH+krF$}
z5l6Sg%++oTI7pz&@~@xI2`tZMsKkjc3D~7M?U9?jtK@p}fAlT*Z|5c5aexIwbF+K@
z>FdT{bB9g_9%_Tqjc)(V>jSo_c0Z0I-}gEIcK@HX`x}^v*)e$f6Ndv6u|Ab&e2T6-
z^L+1eQZsp&JYQOJqS%My9+ba*CF>uKUjC!W{>FGc?WU~Io~O2U#XCN4D>p9nQVW=@
zNGPgbQW8_Vvc)j5RqxFmg8+G3B@X8CX{gwBY5#pV3;g5I7Y_4Q6V1kY0N^I%kQXhw
zLk<VvjrKGtO-!`Njx5HO)DmY=oMD*~<3KCc6=2fJncx-5u|ml4q}ZE4BW@80{hgmd
zx9wO~3x1E_pM@hhF*2E8=p-*Gz9Mgi<O#Hg796Yr6rxxmkZnTxlF`MOXifzVEtRwy
zk0NsJa}iBUF$17;%D(^zz=gI~=v8gC_l4C0N^*^O2v%q%>kA4wps+HmF%5n{aFb9q
z3-eJIg92ruzC_i&6d3Gv0ZNBgt4e`1q?1|u`<!w_LkO&N`2RyNK_WZD7DV0G6yo*^
zYCy|n;#9p52|)q;WpGFfCYT8{a|EtrgX#Gv*nIKKQODeI`+wk#L?u9DQJrDMNm^MB
z4VvW!7%z8Bl`0fc&6S$}&^rO#M3YHwn{uIrid!dAAHt@a^EE64@?`g~j=5e+^}|p}
zD-@(7O5g`Kv<DvwAO$$sVL}XB0%*2|qt1N3IG8!ap#4SK%e7gT3*E8F#Ans29>?{}
zfM4bLk;IQ#yjZaL3cfar?KAzl<+>Ig;W)9k(}nDDd$7*K0_22)&^*;1NB~G)iE8_2
zY>BFeMl*-258(uZVM*-pVzaPE2o^BqMq@;vmqWRUFXC2JGuz$+ja>$^aIjPB<Y)lL
z8#s@EyUfa!b@|2p!q<c)Xq;}-42^v8B_ewe;(3@zn0}$P0ro)2wvt8M=@$T?PC`K+
zbCSk4&=qH}2(j(_aR(G${Uw9KQvwqYO!9(xJ@a;#?F#^{I?Q0!6e6%m0wr_8e#qX}
zlu&xsoYc<n%p{5_V}bH3awa0Ge0VQ{FLJ=FRO`Ib%*CXZBhW}}FLg0%84j6(db9fV
z$z4$6CT2tg0*A*5;o_Hv+0z+`S15*K-ttU)KT<L?D~J_<wa1d5{TR%kMa_{v=^>Y;
z7!)`+PA=|`5m>UVj)5K#d`u`+6<-K+h=|h1V-ql_WH*#lj;aR=sPn}Exg-cu0HC2i
z*@+6&o?|o{ksC@p6QU!YZdx#VabbPquG_pn6y|yrn^9*twV;SH4rB)&e2mMZb_ROD
zz~2I=KtYgpU>@8ei0A|yq-UgZO$$*D?BskIu4)2iIkQvFCEyQ<>b5D@3-)sB78v6d
zZ0xoufKN<ljYnk=(Y^LGnWla~RU!Q>YdR?e*0uu-mJOdYM7IV9(PYhJVGGt3K~F*N
zA*PT9ttU~1a10A#*~|!*U1!dRsLhcwiBB`R5>x<xAR?%7<Zadtsz+1-TgPAshVXey
zHCE?OQlX)Mf7})&PGK5~?ERwH40sZQiy+G-f`Ai!z^D;I5Ilt?uOP*I2ZuOV`OQ2F
zoJ>V&G@>#>I=E03oS(%}cM3qAo-WkYRVr2w>-^jY4+Rm+#<?q9ez9$?zlZLYwbDT!
z>&P9h%DV#|cT}5Bx;&6HY!S_d!hu<@R4b?LQdB|m8AG`JYC?w~w7MbUWCc81)x$uQ
zlqs~;1swxol002NlIvQ&S-bjn;czh^K7HjWE+~sBeBlB{U?S|w%N_7AH0zhjqFDEf
z98apGWB<7``ui5qvTo<DT=C;Z`x1X?n`PG>UkNJTXXE5@vX*<B_MiOh3AYPrM|W-U
z7oop4DX#I$4Q6<onrd`Nzfh&_`I%aEh!Z9KG_5h+5Bn+R#<L{7FI0Qn?{^OmMZ{<c
z&OiTSH|TOq?Tu8vrGM_ucjAnIK-O8)tyJnU=3x)%($Vh&r|nw=<$ljA9I@`c>}J|>
z`t`8Tb)$JNB`DSNO;bh3&g~vG#g?tz9@NBLVzdozYnc~bdfl$MxWi{G0dqQ2m9j_k
zt+;iuj4VT{#s2Pw_pBdgzv;?%>7T0J?vt(5Wx5{UC0NmrUth+(b#)8d%FAB=+NeHL
z&@pB!VtudbU7%m7Q28Jk#EVur(Q;>;7ZUh7ZB@}fcck2mSQFDtp_9ij3X`h+C6%U8
zrhgtMRjmJuEFTGYBv$*vf-fU}wWAyAhA6Ct?`qOkPG&)1v&8h-b2Y>X!fmJpOp3&x
zj&R2>9ZM9n3Y-kc>{+_UGXjxISyIz4#gIE`qLm)6XEf_|$8c8>KX>J}$<M1sR!NiW
zjC5kOe@Y(x5c5;(XWPn^B8JZr$jpa3v`v)l9AvCJRn+ELJq|cX_V3GtCN5c@LtcAG
zce{Cant0T>Apb5tZUfkd1SUD1Pj@Twf9=T7R^I@8R)aNe-?Ik{L+{`FQ}?h)`A;oj
z12Lx3^X-j&j-H~f>fNUTe{3Nv?P<Rn_Vts{x=P}ZQnJ7A?4@gz@XYPoU*y|;SLk}^
zs=lXY)%f{B<=MgNVy}Xr{BpEAb?4||^g6{R!JW#8HA@<Gjs#v{UVotUeV6ygdc6<X
zGl!(AYfq<{KK`+B#fqa`Rag%y5{91L5q2+sv973p&A~1C1-`#@?wqlHIy$>^$*1MT
z!(S>no|L!E{JBHLN<nA7{N9)sP1*O{H!t^xOi&G@R9VTm$+7og6r=1ZhY{x467;I~
z?jhU}@^?krx229F=!lEQq7U#{>9>rpa=-80(drzO`{rqrv4(o^`9CRLH$T{wrQfKT
z<k{6FdlADw3Y4#wJxxkoG9fkEQx!4qrp)$!LgH|}-<%CuNUgReYa2e@+QGbj_+$5v
z?OUGr3q9_YFVhOmWbyJ74R3dnjI%mE+_r!Jj4ky2gAZ<v*gAbU=;TAHpxg)D>+0^6
zNvgS97cN@fkTCUWh}G)EE83)(pHpP2eDJIF+>M_P9(?!8a4eJWhs=e|ze_Fti|DrK
ztp5M}pJb(Jt(Et?E>|0Ougvh26femjavSv^2(}KB8i`{g?T~BhrxT&t4I?megS_+F
z15-t5b(Ymea-9c{<4{hPfpZ%e-K$l~5^K92nw&UOtFR0)Uixmt%xn94t+}e3&niMC
zG=hG6-6_uSIlg_nbc=VKTK)RZIS-Rv{^)HQbL$OC>t3<ru&jyJR0aO+Sk!NsNuBz`
z)3$&7Esr%RTE{7!{wY}4&b^(#e_iIO){na)M%oQ@Cn^tF%G^8jMA!2A^<$|j{|pV0
zKIduX8xNTb55#)k`=WN-&V17N+wD11f!D&m&No#*^e?8&yPDIRE|U{Bcj0}kkH-Am
zp#V3=?~{r23!2uYdrd~`#WcFU`O9}`DX(f)s42^cIsU@xE4{x1<L6g&=1RHH>}Khv
zx|au0CSlc`yvQ|4M)dx`_Du)k$G6j;&7Azwb#f#9@`UuY5&X?a%@lcf7LY;JR0N!O
zJn^Qfy)>%U;)U*zXJAFdnH|`DiDm~LB%j#Ao;#BNbAC@-XZu$j2%`UfT#XHOZ{?VA
z*;c?y+@*1W%1`hfJ<m*`Z<KoctG+1au$8sT(ZG-Lifz4nPFv$o6P1et@XTt^c`vO{
zVTe+!HZBFn-^<G%<vVxlhhRg)x<oT9#>ljNA*Hg{J36WGw)zDd<Efjb6FQ!={0*$&
zo%L29)lb{ao*uVw;{2#MF5>O-*sxZ?xakM8Iyt)U>We44f95ZAO13%Osj173o@bk4
zz3J_H`SLp3^XJPNHO8g5<jr}CO|6F0slLL=zsOm}q20&6wLWX_VA<3PWk>pP4QZi~
z)Y*h;?nqE1m#;AYak~7_rGt&(q7gm0YTF$-(oM?m<Ci*j{rC5V|HP&yO;aeRz!Pz2
z!4gxHw!<lf=RN^6AI<SqG5tS2*v;L2Fsgp`#+k(ht)Zf0(@3<>fgcZ_iOT&yIdy05
z$cVd{ksBrvG^;Yiy?-w4lkl_gyEwhhwH;HU^E&=v-T`SIiL;Yeq<<}0vgGL2H=D|X
zmN!1ibFaOrux94SpJ<0;nyW{b=RITYrulf=frwsPsW;JfI*t(5v-!-kJyijPac4yg
z)}+<4IsJ}G&I+OR(XiF`EO%9udHt9#x)ysh{?@uqc_jz5HcjQ7md>S<0~XW0ZD;iH
zGMjnd_6Bc0y^faVafEO0<%DAw-UJLa>c9W<kA=Wd`Y(36lw-q`aq5Y_dYxBZ%%?{f
z&bs3Y4-~H9Wge>D=ZO-xJu?IjvBe<zcbaIw`D=sGR(L(>J2IR`H>+plV=m!_E_{7?
zr-;VrZtYO~7}GFWxmPAJIOt5}^OvIOv&FwGs~Qq$3GqA{{+B_Zy07%>gY9(Bm(?NK
zUKT308pe9+hJ~uzLWg3nM(FDe=9AAc4(G>=`aXZU_cWTmoou^D6MR2Fe2bUVkhj(K
z^`Js<7rD~F(N2TZE(SS#F$XmJ9$2&L#Tmhnu^>L@U`Tz*=hD1fi#?z}lfuK6Qh+k0
zN^4L44WU`n>(79p1>hA5GplAWX_@R&{cynH|8BS4WGLfgeVrbKh<MN&msC?T2cmN@
zzQ(djdOHQ2WE5ahB1wlCa)K|3vn5S<M63(A`EWvl$qyQoVe3H5+UYVp<$u9SP%Quy
zg(!0i8YE~HBRlvY5+Y!cvlad#`w;P~ZljJJ)#gc_bHf}{*s~-tRVW9E7G<E2+fe`!
zW5O{3=vx=us1P*>9Am+K9^ip`5Q#r13yfGqVwzJTbbt*N2n<l{Yp?ys3(-k-W<Vcz
zl364hiVA$qAl+#zL9sI;Lbm1#fWg`0ExLgA2U1I-tP|8*DbKdIC=CLv!Vi$(94;R4
zE5%(&;C5?OC<nFPIk!F6lZb}*W7GtncM?R6@xd0JEGZ;0(;n(3IjWI>|5tF50S0|2
zkUvDuEGHv4-xOm~dU6OMy0_Sf?3R#)h-fyFP$gdk)z>^kC!{e11GSR%C2gwhx$;?X
z42$5H;Gv-bsizI5%gGvLK=HN&Y>+^IwFCYv0k`&2dVUN>+Dyf|yC*BS9_xxywAI0_
z&GOL1!2t~BcU1j4v-C74sm=Wk);i489x&{j1`dq#;*u^YG0ww)3DPKE&zfT~S!mHA
z24~FV4oEvnbGYbCTX9S-d}XQjHuilX2oIeB6%$V{OA&_q=!P(^qcF9Fgr<7f{`@DS
z*+0z%@{fC=1G7=jaWJif9Vq{(GXj4&eTt2i@4O=7DMA1FK@}IO^9%snnlSY++kYyB
z!YKbokD)Qg)4DI|K>AW0L+9Tfb|K4Ttz@mAOmeM&fn5KagUN-C3JlWQ%qiE25jyE1
zG&(pkMc@}yc$%X+&6(hs;u|2NR0e!w^J+wC_Hc4jy@W?GBM=IkaBL4S`_(j>a4LtK
zJ3WAnBBdAZfKN$w!%pxtR!S^Hu!Cw_z;VT8>u<yK3ev)W*lhS)kj#>b^~#Q6OEGbc
zW?s!>?=#svL`khmjKQb1f5V9(O$lV_dA)Z4luKH}Qot8dA%Z0Z-Ccry#t>#Xcwr5b
z$E;1b-^g~Z2%Z66y?P-6K;E=+%m}RW9cfP)vc5KOylrQh0gRC-9fQd;!Spj=`J_TQ
zMmUZ;Clmw3&|sF{5MI^_kjl9U-nqYuS3Vha?#^rxS8lU>%0Q&KO>rKH>upvl5r!?~
zai*<$v9L_8WLc>|cM)GafF@8OQLG6iN_oR$PT^#+BC!m*7vpdy0JM=a3@{Dn=RzRJ
z9iQs~XWbdTE!GVB6i~{%%}(xu#e=0>BpXU86U_NEIuTXC)t4E<p9%<<T)Tjm^N3NK
ztTj;{WSPSC=Z9q$62-w^nbQjqQ`kSwA(Yw|huRQjoG+p=lBPxQ5Xm}xQXv6KsWcUI
zPLioVp}+%@%iZ;wllaIHV9ki}Bq&a>rO8npoj+iJ&{OzDkl_8$&2<fY3#Or&g9o8y
zDcvxr)iPnmdfrPumlV=e+n4o=qmjZx$x%hlbeUg;qEUEqFa-o?qKb<Ed167zaBwIN
zE7WvA)SZX~nOQGqN>8plPAQz)qU*A7nG=1jFVpI@0U^=7cKeMIH?&`8&I4~>R-gZd
ze5TL6?1LB1HhGHnt;#F4iMX~zY%`_jQPh^<HaCa9sd*`a(GVlOEJ=#SYS8__n!5T)
zr<>$@cg0f5gTF{>;4MbWl2sm7Dx@Skd&8Pw{1j!TbH~7>@+3z>?$^z4p;syoY<sET
zCG^Ql`6+hus>?ut>aLTmoUc#XswJ1-`5qYC>AoT(g|}N*BR_Pj@>G#y4n?Jc(&CNI
zO!oP%rLQn?L;v*daiY8ekff)0$ia@e$2r%EH2Ei$<i=UUH<!;196ElYg0}J8>iUQW
zPIn(jnx9kV+2~<gbKm})=z2Jc4}6!9-SF<(X|M1nil2nX_3rw|k6gau%-ir6Suxn3
z>%*!YVjB5p_C=|``))rSQ)v{`@i?^id7ORm$r+p631=6flR|w!H1kUozIG_Z6|X>X
z2+VXaBdIqssa?skv42R*lbw#ko^StZjJQ-z(qfzClrrYAZvc=4zQmL~;o-ESo2oU_
zBq%K=od^5rVk1UG1)e5PQ`nV~3$e&EUmD5+@8esJCavn$US|LD3w5_?ldqjJc0|~j
zg>BDs@+>LW;%`#xTP;^u<=T4WuwZ<hru)+2BW)4o2}jmy<}uP&GV;sznMq{Zw%okd
zT`5(s5~;W&=FJZvA26#aZdz+^e>2{Zc+so+?i1q@?PgKNE-Lc_oxYP%+N`KE=35?J
zpr0;%+Iv}*;9Y3h^2ljLt4(w%KYwqpl%o=z<mvUhyD3kEBq{l8Wgph0$dA`WDyGDi
zI|i>+w2Ntt4!TvIXS4mo4ae|hcvAeBZ>3JQ+*z;h!PWS0a@UUa9ohHt@XOL6*5}N<
z=gJe?2P85Y#^_%Mf7DJaS%1dng>s2@yEfgm{ow|+#;U>Ef=w6Hm-u}fmwcVM;*3{g
zzd!4ysuW4uGP{4}o=*dDJg0o=zMJp&&766zaCbz?7WLgxkZB#OmKyH#@%AMCwx8q5
z)bkm0jw1gki=E|rU3`Cj+GBKS!~BNp9Tr~2`*6pM4#ylyF!bHC`-0p1_ao-n>lCzZ
z<X^w(V{*{*+~^>x=78^|Xpw=8?knBlH@Tdn7qr&SV}dc>tNw3g9-y=SPySk57T1Em
z!z`2)?=LA*4*IVHJ?-V=JcC+e#oeDjDEto9yKuv|^v}@G>rak<RV0r5n!iI%-JNP-
z*LYsCW&H*mK+bk_J}b{Zsor&7c95rdHnQ|=^Evx|PwZjQ9o#H<-}s(>AC9bs8;-Z@
zjh=#j)G+z2ek5KnQY@KdIasUPc}!uh&g#DL(etlDDs~SrYp*|{ZXYOfbC?^k=qn@c
zeYJ+^UcUPYPki+RR|#~X992FdiPfX<pj0hMFX3__PxFkC>jrn;I>gS_AT7vix#xXM
z!^2~*BU_F{ohS6&jrc$p9%TmIblpEs<7+8zB;718bWY2`PYr?%eu>;(2yZ-e-|cg!
zFTdX0>+yQ=XFHskC-b%ZO}MK4<t70h;?j+V^nEGSX6Zn2_(v)W$Cb*7M7ABXfQ6D2
zQ#cC%ES6_0t`*l-kC@1@^o%CiH9$F)5d1P;<G`sYx_S!hdtOXWNm*!TZS41n_lf8E
zu<Pi}<P&R>yD_`<j~F)UrD^yp^^5#23|&}m_cl;>p5r&)eYR4cIh2k9{nPy2RIK^2
zsm!IH!p*w~pU)p~xoJ42m4D=H?7hQsKUW>|a@htE+hhA?=s$%~sXv?U`@TNWW4BRY
zxT%{}bf^t~><dXeDh`S5aHi1D$FHejqd{2xq<8hMBa7&8QRzcm*zo5byC)SXuH%==
zi%z>62A`umKlOc1baj@LLYJZyUF~n#IwMiH|L)6}SBYlA(IMs`g(GIokFJ(IaZ~zf
zM!z3i;!pmj*7Y;w*W|vB3EpC3YvUC19E{gKxNpOn*reOH?z!{Vk?^w0>CCwel^t_7
zg(K%5^avH_w|StgZFl-)6SY=su6DXF-K3f_Mtl*%DaXkD%YXZCfDixKuWdSguEcrg
zdtYi%yp_D?_85;w9@+2;hy%u%M|CyNgtEby_~Ltos=T~jk9uAH=jZPuN(R(TkAME5
zxiieca;8wg{B-y=6P;T-C)~1p>iE{-jC!K+I-4-->a%~5TkAvZn&CtL`!3o4<cH2U
z%PjjqIxWRNwl6W2?`Kar5gZ;E7xw-W+EnC!&cpo}_UX5*u<Zt3w`chew;ZfUyApZT
z{LQ_OGXaGa&cP_%xeaL<&Rb)B1doh<9KIUO0aE{VnH5_P+&$e^v0-RKr%d$Pp9XK6
zxU?Gc<9k#icV4kq->TQoHJJa_v5-C7VGtNDxjwhF(6Z_Vt?PN##{<npOo!rE)6GR{
z(iP;efBrAV-ZQGnunX5r=pscWC?Hi32r3c@NGFK2(7VzUP$3{S)Sy&FjSzYZEtrH}
zM7n~aNYzk6Q<?|}1_Y!FqTf7zv*xThXPqfO{G$s4;Z5>Bd*AnUHOlM1qpVnT^o@*G
znn;P1!3{;ecUnpu41FQ01%Z0blFka?qge%YBiq!lKpGB=it;?N&)P2w?2(1BW(>WP
z0@+|@yiLLyvWoLf(cK5FLG$LvDZwNM1idi9x)HqI1z|pmRHnpM;`wtaK8p!AiCKOy
zA5!R<PI)=hvozQ>`_oOZTrZOdYs0r-KHn*DCNmC*tFp<0)Gpuw0g&F)jRf%W7Un}8
z8L@y*GkAdzQ85++v?gDTQ9ueL2|I3-jCrg!WT1l%hs9qeI=K->09Q{F&W4HDCMWEG
zdzu&>fKti>2La*V^x$nkkxU_iE^>jV*h4V6k0rcI4<&_=*kTMC)Tz=4pi~j&l<fvp
zZ8f*Fwu?wNK!G$cO9wZOTsP1>Q9^2Y01?fhxT3E%G+assC5~swN&T^&z@P!g@S<5E
z7adG2xJ5v=4PiV8?nNoZP-CM6I_P3k&q@c-(*fI<!Er!O^0KC99~lJuoVe~b>HDQ9
zc~41X!FD9rY2d8~sBCeo|G-m4pxt8ueM`cdfQGpRbX8w=9kp%<+4yCdN94iM6F?UU
zT3E#{;t5Pt*+)U)WPzSw_3z{oP9lU+G$O42)<Z%_xGjAwKz~BEDce*TST+r4ps3Q^
z7e@x6Z>fMP{*P+Vya=pp1#qY;iT$P(bblz1Xf_SbHL6s0*qyY}xo8oBR(f0w*5Ixs
zxKGuYwcr8Q1+<fyDvyyp#tBrL#tFj^a+SmiP*^4(#mkCS!62caV=oF=kes||MV)0?
z0e3(f2z?gK1i<P#43w}n)bk8sgp&nCxPbHtaMDHC!J#J(z_^kCz5xKcjVNM$cuSOm
zWPxmV6`)3i1EK5wpg|L|5F8W59M}W^cG&=lJFsA)3-LNQEyl24@mvQWF7S)MjseW)
z1mFsbcy_bzgUBNE2_7sgJ-^F>V`u<9ON0?&A)&ra1qxtt8$@=g0q_;_;q21UBJGTs
zXiY^Fc`TXT%aV4MDOwmDD?uxLzJWQ-1Yp6AyrnJysu%EP?9OX}NY=Y(zJv&?d66>I
zPLaNzIFFiDL4dyO4G>^eIj|yxQ6V>@<dg@QB9SDB3XD852<lL$USk3Zy-eIi%07de
z<V$d-IHEtyr#sRU+Dz@@Ru>%+g4_hJlVHJ;dA!NZL1qLIVJ6uIu6hcW70}7P_aK_&
zf%7yHOcn%6+zTD9@Z5(-zukMCE)=kI2-o_)7=3yGtvgnTHwg?tadparlOWcpXVs8d
z@L3vIx-b_+(1pQ+V^<B(5OW9fsBgyIIFKJ?LGrX9NdZPg$dRrvptx%)X^;oadZ5MN
zEu}~@fqfP)5S(g$-vLAkPno1Di6?P7+hmnJvc@1Z$pNM1bqQ;>Iu?^SAbe{mVTcIc
zEYge(*Z^JvipC9MI2NN%iRFW*dE0_1l==r;$3U=A81;@&!T{Ppu=Ei?hL9`(UxFUf
zDYAuHDnrK0Al>nyXqEMu=+lE1pqr<!hz8_q_9X*4LEUNzJRik)mA9n7>5!W#EB`bz
zi+C1@g@1&FnE_SC8g(=p^wa2^sEatX?t$gYXxQ<IEN%21!-GLn1rZ{YrU=^fgpqg+
zB6KmE7xV!42TzK;`bkk`1NK$a(S+ZCe(CX?#^PRe2803w3{{ao01)JcuFiK1R29Ts
zS%D7n7AF`^Sb>7sqp_GmYf$$xLktcJq&F|YTK-_5Y%!wo8w&0-sR})vfMR?_?#GiP
z+{3KrH94BtQ1cO%@)NpS?r|%2Yn4T>A9N#nTnXngtUe?J^VgJkJ-lVOrf>6;+v)aD
zPM=7EreDX&v5<nh&bXi6Ns<@d&b6gR7+!S!EF)(hdoFM6o}ve9PO8*`M~PRN?sI*+
zsRiUW*4Mjwe)5IFDe)4ap`GpyU3hd^Pd~zLex#t!IZfL2&N4fiCS+{m*;sfg6SZ<Z
z>tvTQ!*Q@DO@3QL$Y}Nbhri=qcQAFSL}}{*$X<z7V!&<yyaUM9SDjg8Q$Boi(pOga
zmgF^E_dMP+War^{>2|qgi)n#NpUobu;7-_1^|<rTIo(q^KBD(4QZoCm0qbMQlpD3{
zZJ?4*b@9u5>Eq|!Z{<pfh4O>s%}#ZkVPLkT)~Ct^3}4gmj*@fcc&DBI*IPflNp+)A
z!(D^a<S4nV$ug4-pJa%Eu7ktnCk_LDM8AjEMuqK^^uJ8{{KdU|EV#7#hcis%TNo`M
zse{kie6qgnic|_`O|9^lJQ=9MO?;9g?3IEFO4r|A77He8t1`@1P0yqUI6WfCYAj}{
zB4cA>)vN@_D*cMa!=;O9c{^myI#lO?h@OB7Xqg_F9gJ4rKE!Yq)VC~6q<awEj(KPj
z;A*?1q%k~r`~F)$1@Q1~%%VJI2vdRGgP}=DywffPIx=Vj#x?oT+MH|(rMDLX?CxHq
z4u4U2b>4Yigj**ePG{CSA<uc}QY^7f?NxYDt0nRhRCaaB?r&D<;fzV;Iob*Rc#Dm1
z*X(tRy?&zmUZ@a!vo%*<7f6^JiJD1re60-86h79+QCcGC@UC%;E085E;m;S`$Zs!W
zF;~YtyXQM7J=PH7h0o6BswF)ED88aTe5P2NMfaYUXR}wb*qOx&V?W`-a6N~#F)|XG
zw=2N@!F^lF_E|p9=QCWd8*1@rH`V<MH&Y1uV{3A+7`KGqV|S_(XA}Q!GFvp@{{vy>
zFK@049RB=LSOb_8ivlQ<{YHrL+BMb?bIheBmD@YzFC4n2)Z8kvok}G5Gj^W*2cp~R
z&ugm@XGh*RS>Y8j;7OPLE9J*<48(N!t$mRh96jQ`dBb~N$zHmvI&J><so>bXkB?L)
z`YG-!&i6vcQoCN9eSiCO5x2|j3k~(;r6&%l>MF5wn!SX+0E;1`f^q?czUPt?`7Rhg
z`7%EMSFb}x^DyUa*;gGpmO3<El=!Z?T~=!lK|ELRV&iuHjE<Z@u+!!_D-kog>t+vh
z8ysy`VV#-EzpG0&O6bp>WGP^PxsG}VjFte}qksSV|9inI=X?d%?WwPNS~=(4uJv8k
zWuW*^+chyqzyBjAJ@!m+l26#mn9^uOK;2KY%AD|wJoHHdGWN#cLPNuYVY51k-_Mh}
zN(C)~Z<fpyD5tz-v3~y4w8AWMS@r<$v77%{P@R3yhBcfFyLLqA?~ekhPUN(+!lJc_
zB-ncofNZ`|Ze`*xA=jB{=QnCmB{&3%>r+G;>S@iJvJ!$Pv&eU7fyD}5d9IM4LKYrm
zR*uu32q@k%VUZ-7lJEgY;8qu~hdto3E)y6$qs*{;elYT2Yf_1CW6GN8l!jfa@MnBi
z2y<CggdMjV9IDj(=hIGwB#W)Lb;fQ5D!}k2T(KXHqRGobIt893fVe*R*yYt28li)J
zv{1kwI5)F^d4vAcFbx5OrAITn;nya5nQRsteFzrzBJ;UT^$`}WCkK#&Ij+tDd-1rD
z0x#yh3fjecdRUBh=J79*s%+&^@2*E3as;f6I#IR?p36MdzGwY<SZpt*=JIgxWCi7H
z7suR7P35nPEQs%NZ8`E(LWb`gtaw*k&CbANsQzHIT-vv#YIi|!9yVMmV{+#OVC0Q_
z`gpzMhu-Rks>lc^>doDt%2{rWiz4vfQWt$c6#8I?@tC%NWK(<F4xakdgeKUZR9>Gm
z*l-DLT=JB56{<XdrtOD}P)S?8rGf5OOtZ|%)igB{3el!Yn1u2>rLbFFjdV{Ni(bPO
zU>3D;7I^lVlD;QP$&DRB9hwJYp-)#^+YrT1B5!(|9b^89H66K7JnG{zBC%knguGl5
zk|ZsZ`XV#P%ksQ+AVIb2g7G`Gcw!|XQCxL@;~G=fGUQ$l5%G!GGt#JAx>ShsOvY2W
zKlXeq>fqYmEn{7{J9*2hb(eB!AeZQ$rn!8qwkIlNUb2>QD|o3|6MpSB=}#REelN7#
zbz_Hm9XP$@ou<3RGE|felx&O&`ziKsw<)aAQ4SW7#bo>G!Qna-Z$IYqs%5<B$n0li
zd$O`R9scQS+JZl}IhZowr3h|4{=4U&@J?)E^W0?XRp<PH{PI}n{$#lQP;Mxr<)v6x
zYq!c`esXu4xF(&xJHybOa3aS|Dh1zh?I=3H|1@^|@bvN*AB~jDwbg~@8-L3@YURm<
zMa8$0@x|<w=ke15))lG4tr)V`)pNZI#>3p5K`Ce{)X%;baMEp}oP;uu2zn$YE=ZO1
z&x83t?4<uYB=e)vn#;eQM_-?K9p1~-CceYJ^oHL$B**(Nh++J<!}i|yRJ1xip4R&6
z`{@v^U?sQjfnOZT#6AQ*nu=00iCa0X`0^d|-}VY6V|0|FQN8QT*}t~_L9oPRP~iOk
z*lYdIJ8$^%v9tZT8kgk1h4m$SFH8rDowLg4ov}_DNn+e^R{3bAnRu^iULZkK{I%uq
z!0kT{ZCppEg_|Fidz_yq`hQoUB)byeI_)(MIX&++l5n=OgHaCb4xdu%=l9~DY05>!
z#IINcSL1St-EQv<m@1jL?H+6}?6f(X@7})9NddQMtk;?F+MKc^R^}B$paSdyKzxz!
z-AGWMf$WlD&ArrrZygB32%!)JI0&-CNLDcg|BTW{@Q^M{I~JUK#GR}&bf`zuCi2+5
z+>S|*J$K6h1_^kLSQKv~sm7BGofXuv`H2LZ2iAsj$zASvlaLaN2x}+>Xn-g34Z|0s
zg>XXz3|2<~$z@hB^59Nh01-oC1~YAnj3iYSK;i!)d2x!s=LGg4+k2E%bT|Mxy-NrL
z@c~}I9Xl)q@5_jPC7n(YPZAK>QTC{Sj0TSe%q}cAg7MTtcmSuC2k@Nq#9;^45!)a>
z34SQZ9>|E{0Naehj<-OdRFI&w;XXqs214H$K??OdZcq(CYy)Tlq@7)|3JHZ#-@v<k
zCIcwy4i$C>U}=Hl01$TT+jWWT#j+F%)6aj)o42F_a0CPja4d=jfq0aWI4$YPn;@?Q
z;JWM}MFwJc0B+0sPk$||ogvr@l3#%T#6(yG%aW66Rcr}^;_Wa#8Vn1#C0P88Dv8G+
z7l#X>NCKp<rlO%%dTYUyHDnn)aPz;2+XJE^jn$LHTD+BJ4E8a6$P&B?i12}%Vr%du
zaT*|x>&f6C5K{1B0+3sLhX(9h8e&jqOCi9289)IIw*>bp_*^<(r<cSGpd2o-coy;5
z-$NsoUtm1x?SQ^IOAn@YigUR|dxA|Br1R{>Gf7nD6Pb7*6ta+|$$LU%fS7>X2ID~J
zs~ilWK}ZcEWbVa_R^RA^uy6)Y)(u$|c&04Tk?G((y+H@zL@%@aQi!B<mH@IoA8fTQ
zh?L0+gphwy#WDl|eRqlgOut}96zC}<1E^S@XJWvP59qKDh5+5lf?YHnI=OEFcC3J>
z!7&fZ_Y_`Ch5)-31DtbFvYjHb>n4yOD(LtJpuyTlhAkbar!Dj#OaR)-rUv9<(7fR?
zwR>%421u|jDFRCiU=ig|ql2Gmo7%++5n$kL|Hv|H2szvo0K&y)Qlw4uTrvk+6sMB~
za54hAp7`WLun~ndBO$yvrwB{DKM1Q$>MPQ-CL3e{QkwfMthwYkN^~R|1Dsl#n1u)n
zHdcs17a-b}aSj_I-zy3h@04*+Iw6W80jAyT_~e9LvLCWNNjQko%`dG&ImZ}F?mCXg
zsL(X<7y*U}%fN>}aBXw|rArnHNGR+MQND0Q8cqCkg79{63e6Cpv){rX?W)u+(5C}S
zpyu}e08<sJ2Hjn?n2ARXYsgL`hRmp0;!)DzgWtVMU~eu<fW$^bDHfO-;W19Tz*opX
z2f|VNZKd;{1`#Dy5bIi+z>-#aG<YDI#<1a18dzG3lzFb2T;T^aW-?LHkZmrVQ<f>_
z5&FntoY6i&R_g(4b;2wiEUXLEEFuO?A#})kClFI4;S}TOF%QMHse%IzyzC<ukW(64
zzXkyxB}m)~2jaT(qHi4hHSXk&19>bIs7ELRKsmsURvwfvl>vtNUBCgksb~sRP3()F
z-GEEY(o2I_KVAph%42~5OSxd>k1<*T*Q_wk3TjMG_-g|uNS;*j`8ELC0PQt#%LFV<
zZ~>%QJEg(l5pOp0x1LMk5(cnn#$g5Zh<G*}kaH3^K)n@$`vb@7h;9o(6qBQ<klCSO
zw$x-OprQC{)$_#^(qsBnikSea@BV}u*0|6Y!_!@EB*t&M$)@el_@aU*&&EpJwe#NR
zm1J;<J?hgT$@3`FAO16XLp}`$UzFnbwx7JM+3AygrsV;fp!K>_p7#$0Z+o*>$_tbS
z`?u!*Of>iOTOj9uj-`LyEwu{Y537!H8m#)teIk!dfW;o`ek%J?;iUuoyA7qv@>dzB
zF`5CyKqLHxg5cfLEB5cL){^M?yB~i07Y)7u^&8HO#?$!ZXU2I+@9N~bgozc1Nu<XL
zeuy5NQ?+0b{$N+T!z%Y$L>F%h>9csk{!I`1(@!C4vel`p8t*51B80j&c!=^opE`Jd
z9=^9V#(aAoI8-)yXymNaT03=B@U&J-ReJT~)W(wZ58fBv9DM4VPr!}6PWYtGuDa?>
zAb+hNz41{uZr>L1)qp;XYh1&Qy~x+<N=eBt>uo$c%Z%@>YdNC)InaKb-Vhv+?&SV(
zvE_w7qOhx0*@Q8y&QhyoKT+%$JCCUbWvwd5Jr8jZuB(!5fQpMi*UqU9w+y4(>Qi2*
z4H3(@`{%c8pJNByol+B%^iRAz8MCauO9C~|)K0tJ#aKndQ~$Q)5Up1F(sxV=@Q?BA
zlK`;vk;V?g`0$$WTs9B4iZJmeiwEqOq8@XNXd4Fdb{zI2|8>3SYd{cw$OMb5C&gmg
z%pEM(4cVFTmOZq~NG3H4L`RI#uUY!i7G<CTBF(EoSGX{dpErLdZr_6KA)(%9)b*9=
zP}I?+HsW{Jws&!Sw|UWXeG9?!^pd(aEzkXru_yerP4ZeMKW<D_2@ue`h?5ERj{JVO
zx9$KBIoqu&+R#~CwV1e(fJ;J;)Q!Z5^Zl~-UH-oL?bN9|AquJ1N^Te5*i_#57~@c5
zuvgB4KHM#(p}izcbQKLTfMd_XFa{rWkmllayJgZJ%&%wBs!@DzFXZREs!JIfUx$EQ
zho*O;cg2TpzHn00o*vGZdRM;k_LG<VH3D}cjxuI-2gg#*677i%)2XX>xi<1Vh%1M3
zPs$m+iachQw4Sw29DG}olz8FD&k$ux6B2U&CJw#Y$P%35AZ6SxJbdd#y#AjB*O3I_
zak0`v!$(&~X8PAYKQCD){N1T?onK|Qn04x^nmXBe$C8aqx?d2u%gCPGVygT5ad$O)
zA;pkE3&|YM4Bc3q3Cb`ps=nCSM59hg*r;D`X=m7;lzxg>9&e=eT#{E8dgC`2Z`+ZT
z_-3N|$_3mh;phK>ye@AaJ-=YPA0snU8CMR}<8#K>Q#_uyobbOTQV}A?cfD62gay9t
z<m8||VS|1gqJ+_VmQ<J0l0M&N>{%cD)2q>5JUu6Dc4_QsqQkq<%SLLEY|S@*ysEGb
zeNbzzv*OfMIewzxG81pq81;3Brlp20xn)8=Efn0vk8Pf7?&!`F+FvyMHW4mP*ctw1
z+|}f8-O>2jt;De2O0u;hqF_MJuC~>9<!Zqtp07Rpw}kN{I{#Cdhh4Kw!4v8UOo{(f
zKvJC8KQZfe&GHQ=t@-C_Ye^8FF?6+|xrzvX{7oL|e1|#r`fNH*OQ&4Xd3jgn&qdRe
z@!uO<<5)wKBzp>~(%&+y;C-!8)BE|lYPlb3Rp~36W(7I?L(>?C`?H;$l#6Q?cHB$R
z$fubXk7u%JDqm)b7R@^LV(mKY54U!IQuWtsKYvO8HgCJ`_8N2Z@7X)5Wosk_VXo2A
zsmvdq;Tr(%k+zB;>?8;jEFrs-^(n7z@><*f=-G{b+X`aDm^Ph3&d!L*z)yVAkqyFG
zyMwZq3|oH>{TRg7VOJ~0vd3qhI{g}5%|0aX(yKev`iiphMkA2s^><=k`=MRiqNvus
z_1{=_OMVQ=SDbJ7P_QFdU?P@Hch|76Pp}QV>N1poncCB^zE&rkiV4{oCnC&K_*SJ1
znp9Wpi`q7;TA#O$`XW}X44RY_V{83${j5Dqd*TX?Eb)_g^empMKE*d5;r|$P!qSip
z;|WD|3ha`RJOJ_qG>=%oXEG+Dz{d%!S;|hnsPd>Y`l!u*QyyX)2`zs|b~W!eaI!wK
z7=6JZPj;~xL<U3Fk#@e#?^-UTtvcT?W3EBZy_TFVdJ&71dY)G3+lDEIi-wn8*LYFE
zZka;B&6UY#No!%!g_KgnQ-sx_O$}~!hLPI|Q9_>u>gwp{S&YQD;zXv#EsM`cHroyC
zR3Ghluu$d}>4qEkrXUnW-(zi_+?`+rOZ-dFJe!*yE5=PRj*@KfTl})>WJagGE51(b
zpd6AEHh|`O^nwoR+S??y$`Tc7N{=R^jdABYI4*_9C-;T-mNp&3S=}PKo!60Y3ojPV
z(ipz^d)n)Y*4;q~dn6@@6jUNcg{VQFJZkfuke9NnREd}7e}l=ZK`&JX4Ssrs4Cs67
z%>Sr}Key}`?%n>CdQPp_27zx6&$qF<Vo6_vZ#-(`_F2>s9TQFna7x_k`0(&C&0EDy
z`@wj<`A7AzGj-pFpDElvV!f)@>Av(KU;d!qd}gvo!Tcln4C&ORtG}jGrtF8<(G8g+
z<f{~SdW$!B7Y{i#WWo?IGMCe{NRs~TWb#F2a@~C5AGb?rs`aO6g>XWxlrKmjC_1e!
z7Gm8c2-otR%~6V|6UpDr?!z^{w2#`pBuZpD5t@}QO;0xOKQGRRU0}$|*=CFGa6A;b
z-1W8XAy?|va5K%)TBFRX(Mb-;3N&kbnV7;ps@1npmOw?q$&BdwsxJ83a#^~ahOW$?
zEo%;WUM=H!2KsFPZuk)zH{n#k!o8y;_sN;3%;4P7WKMsrom-f3!Eca(HVsT&%4on2
zIpbm9113$Z{SPJYKZrUE_RPh-BR!>E`QjQctzW;h!OBGj?Mt0fzo0lLRo=@(^?NmD
z!*KS^ug2hrY>h9SXL4#JPJT!|spqEJu2gXFz`_Z3=>uQQ>GZj@r@AfM0(Y1-6n0?e
zOQ(O{=MERmndi28Ykzm<-i_(Bnk8qKocUF)z2jf5`cO3o%=;-G-g?%JFJl>@j!xv7
zVyxZejNkL3+wG}%6zId(^Zf5hs{d^i7O$S1%G*#7w#P->_kR4VfbuI?P(P%vxLWLZ
z{*4DebJJ32Rx*oMH1(Wcex3X@dP+r=xrix+edMoLlp?Cm?^@QrU5V?pNS>R2PYjzG
z{du?b%WjroIHrCSczga&4AcLQHSoXnu(`v2?wpON!PA;e6%14?rKULQ@%TX0$<_Cf
z@MhOTOE#JPC`spRnf1EDWAz5veX6?@fK6oRED}r3v=Jln?!wjayl7r2yZ6VZ+|N`5
zSA>dTsWxCJa~Vl^|8vVu-_+*8>|7OmekPA2yEp;dP1G28owHV$%S_t`Ei;G!XiFKi
zK`yEQrEm@?#dO2Sgpqs<2$iYRK^3f}y;A|kX=$`>fJUj~Eqei$uYI`r5wuf#yO<e$
znhH^GV8I%_O!ynb;j$f1bYzB2e@1czASaH{6o`-z&jA=cjMN00d+R!sc`*mYeG7#i
znslUtqEWIe)Ko^-C~q!(3w4Bu(Enixth8@C<uU3*AQrf81R7rIAkev@4;a7CVst1_
zJ%MN7#2DInLB<6n96iC|4%Uu#U=`f^7n6HOc!mc=x4Gnib=n09B!rp9gjXDkh7qqQ
z8XEz61*IFwvu&ZUJd)i@RsH7!#B;10r5U%cq8<vcB`46qe<B39;4b;4f7L*pNP`HH
ze*#nz3mNqEw6=xQP!JkZG@z-gSwNG31t=ebvxfA5DCbN<Wc@KV@D-g*NqtErz+SRq
zV2xM5101vlI5mPSNVdko=75zpTD24W-XLulwSPdx8(q;SfbM;eiI7eCE;}Gh52i5f
z99T}^wW$iQ2+&~6p}_%r)?^6@%6cH7`o|N1|7H#W9395o3FCxV_bet`;k6&(0c{;^
zfYzZw1fJn}LM@nv@ah)eU?@PQij*QDd5aIp;zI-Uf0KtDV2AgDnB~I_(CQ$H+6H2|
zG3;jBQEDK$oYa@#k!Jze=6}N|XEH(SkIG)dM2ID%x65{3^fIvkmAkSqN;eoom=6=#
zK$avq`aWC**;ZB@%_Zb?)5>E5jAEks@CY5)aUhNXOmeX6wFEJ~M|iZ0?7&zIbccex
zlLfklZtg@5>M9`K8Mqtx;S@|kN0J@Mi9khffkhu2=N1i7z#!uEE`klS51B*?Fu+}b
z!1V-aGH8gC6|gT2$C)sfz=GEGJ;9GWmp(*KD+9trl@i1N+GK~E3N8Tx#=r#wr2>}A
z=QUZF1ssf1P`!)EQF+7h3JRW(5-uxdaGY){(~+_YW~QoZ%K{Cwmjz;nbbsB;iI1NA
z(2^z#8Dtk7aR(o%(2|%K6#I(tC(!aFjF8;&*v!2`6b;?MCfT~324|m$79_xx=U1#^
zCMVKF)1&Y7Ph+SED}XprzBPOt>NFQiaaX#WX>JDBXw=k$T$x7TO+17HtoH9laB4i$
zRNXEKNO?%28rKQXRLbYaqR+tq930u5)K_(^O+BPoS-@YGsn&uAVJfMFuu?RIK(~uo
zt{zjf@{wtjb16)e@G@cZnQxGFQM(gsepB(kaC?->AtrkrZ7OYE;s8-zj8z+S1ljMY
zP!e-dH_i_SUV&l2C56}S_mqx9u>oLe7==3x;CLV?8t~GoAhQ{(s7{RpIxkrM0{b3>
zvSq3furia0hnTg_rB%U&H!(*#A+X|PF|<|K4h2e2-ligBqj{o3fm@kj=*E{|d0+_`
zEkp>L&Wetpm;?JhNN@8xa6ALom4G0*N*J*3!<X=o8zqtHL;C?{B5)3nYXvm=nKam&
zw}vd;4FWWI1<zTx>?8UJJz;ksGk}R60WX>>0W_vl(s48iF{hy(VGE`xImoj#DZ0Q9
zuu(9Z*$!O+fd}?)dSXS}z(g7I=?HRo>JCAD5C{-6L`OvH>z&+q()qq)crf7Q!h-vo
z-iG0w*N1bd|MC1ItASTfL$S(yGX^i&8xAP;f&haWfC)7Wgpfi`#mWwNnQVX+K@7@i
z=PU~^E>zc0;4;p#e!O3_R#0#mMg6Y0j@Cadf>8$7A(U&&F;?3lUEPD2^g*KB_C{90
zcKnU!WAc?}X9(!|wStUS;DE@vtX!;0ws`MO$mr!47aoEYUxx9yjV_3_oqrQj*YnAr
z+l%c)kl(waf{~{Fyg!~yDQOx)sh20W_exmXJGt=YW*9Ch&iTP%pK7VP+`zy#I>qp<
ztCi-9=L5Q{dR@K_Gf$F@{o?vLwkxtu2>J*&75jUqHDx*q?sX3qW(zG>uHUU$4Ou@b
zE*#hCRdQc2H?dL0$L&JG)KBl6;C)&sakbJoPk3RmMexE<UO{|q>d07LwFeVvvC2U|
zt%uz_3SFUg>BOnA;^C)N-NH6Pxi7AVTV`3O94@Q){``H(`_3n}rqj=LV5y%RO;6us
zy%)^S7n?$rTjQ!upxm-4f6vp9w?Xr?x%tAjRQkI6T=UXVQHmV=$F&QD=Hdk*lck>|
z=H7XHoX!_BjJ6yqV23Keop<Y2fXR`swJpt1^5YcU&rV&RJhO%88iQzN{HA4_%^Gnt
z^<S_(FXYFW%k6J#Xn2SSzO@#VMbm^M&Yim%E0hu=S;9Z9oaKF=&-LWxRi~~Js%ddg
z`$CCJVPA3aNsAGB<|QTMr2)ThXnn&yiYiw)NjRl5u))22kLUA>kq%q>f{-pJVgQ-5
zdk9wqWUyI(*#V|x;l&tw3_*}#T<GQZ^QQ`xnYoN|ib)SyB_B>jLIqL{bAvp7?v%N`
zChB){><9{5!Vt*W+P6E^ME-DR!d*R9r3f!v(xd9J2>uV>Ht0=mzo*7elli=bkXAq0
z!q%NlGq$k=j)4H@gbiY2!t3dB#WAXH245(}NRWaICT$o03q*nrE0PoKG{|&m&FXcl
zeQH>RN#^i%4CJ(w)I1fpsOXeMIB(L(rnij1mp&=DecmyPF!!qP5e?oDHWl~XJ5lTs
ze)S%kE}O_m-u#M#v8$wZ*UV|cvNblLS-@d4x9UPsPRu;Gr4<@|lf#_kn(E!xs&l9O
zhna#Jbf<E#r4n-}lWG@YpOG!o*SamJJ?GuDAu^);;|(T3Bce8KqWMd_`|S}to7Uag
z-{VH}XTF@-5%xf?uES>H)%Bj4OI*?wIv{qB|F}CJcRw%g+Y)mF5Q`z`WzHvA<`c$R
zDWb2wVxWUXGgCi=)5aR#1kHa7($;nAepszF{<SAbU-ptg^|_BbtH#blJB~>&rqQ*E
z-*ltomb|UjBC?Vpt8r6y(j{Mi$s41!T+}!>&xzp=Rx6%Ool%R6mu~a!n0Py0U*DYK
zpp6K<N&iGndo|=wdrnXn`rxDaEE}Pdp-KzRnz)-f-81MC@M^8$POo>FZZiyTyFwgJ
zxg_uMbGJ@8ebUbU)}3!+C10JZN}g0zcZlm>hpf|EJM>#pSDd`Bf8{`=5O%)*yw=TB
zJt7=R*%lHhUODG?esJcMT-I5Um-o-P2CK^mIzEsb5$f~y{IV`9IrE}syN;zGn8;jE
zVWgl|v#M^gp`eY%jQX%2*4L=N9{UfZZeepN&fDV+u6RZ^sb0?jYkTWlL7C5eztBQy
zi%wj^NWUOiT={fu4ZMED*CCiVW-eRMyzW@LOsp^Qm^`%ss~0?3HOCz|_SZ3t@<6WO
zbl%*HFE_@g08MpvrH83z>XTDn*L59vT#AhY{p#|A<14mB%C~cUbl)SAl>GJxuSCMC
z1P(pQCb?V~4Dr8*SN{W%E5QWT%4B{z^!k!39LJW(Z2f$==1u)w`s~$>c#+dpj^()P
z)~=!*DfaA2tpCUqYyXV_TiwD9UgOz@)LY+sFZLd;u^{$d_SgZ!GG~5=YGiw04gC^y
ztKeMjs4LXiE`Mnvas0#I5)sW6<{NKb##o(gJYSN!V;OR**Qxhav#~l>GWf?i!kbY_
z&g8v34^pu=ab>FCIugArQjt^eEr~O-I3L}1j4`zQA?vd2+4B!$G&^jM=3kjJyZnmh
zv!-0LPdDLjgSBNw>V=B8mEnm~C-@tlzA`%HUc0o|yW*@|xB(S!v<>@v69;v{v848e
zyAu|(ywB&G^LzOSzQh!?_{^`IOW7(j5FKrEuW@iG-7M}9`zqb4A^(kg0Nvmh9N;@=
zNR`v`EKmNqr@7RBlidaL^$GvtOR>a-2bF5^B1dm(;<%|FLlH;L`1geODAjxE8z`Zz
z;$*~^#23^21WUFC(CESUzEfNywRj&b1Tp7_vnDN<`C+FEDE1yysGF%e(5v->iwt1(
zRv>tGf_>gNVO(ZTP|5M~mUzm&Rsu&^dSx}cgPB~zcADPZb<Wu3bF|Z44tVA9fXxkj
z%c=M5u}mVDvDfb3Iivh-ROv%F*FbI6K#Aq`kiOs>$2$V0+7q_A9lF{!?td&3xBW8=
z9P%r6Qn)`0><d<!gS(X_&YID?b5~fo+5^VQ2O?M`jMcWjC@op6oSH~1PdlH(yaXBZ
z>7*V0xbktiqD$^?-DlPT)0UBS^3#vCO<Qpx442Tkkx_qnKNQEuR~hD2J`-WY#d9pE
zp0izAzFlR%@@KZt*KcJT{^D-Hc~tR~<7yR?M%*GEKeH7Ns(j)zBfbC7$7J^1qlw(?
zZ%^*^lUpjn-Z!4<(9pVKEW5`)fys07sdhIpzD999HM33&dKuxi)!aUyG^$^ob3*?h
z!9t(gK<dM3*KDgN$$?JxZXW8o*&b}gk0X~WkQ-6=?!z~xufS@uTPPDkCh0_1RsN$c
zlV#eiVll<{UkdvQYU>zWI(6<m&$CQlM9TGXhbM+xT;`GyHoO%x8rM&rILQucd!|?J
z+m+>#p1oL3o$ipG^nm-_E`yHTpg#R8U0DA(LiMDCU@|_vM#(|8!F2y5DN^a;ryYB#
zeH5?L$jir?=}+3V(wjT={^V3B-ro^>s2OBx`FdyU$TqC4ocH#bYt8AR87-Jz3m$J)
z4ec<*%l*1#NQI^6o>9^^10tG{VT2Wd&G!W*D10CWQGA5|1`jCb27ZbBYYn8I^rNw&
zYoP-bcKS_fM;5NeVb!A5@<y2}uL&ssDZ;K_Ph~Kv+}L~3Y&lq4BfN2zMyoD6Z)q-W
zl9UyNo=Ft*`f+tRumEgIO3v#!1P>H1C*CtJ*5^=!Oa3X}pPF%6%2|*UZ8+YN^LjgJ
zfBeRX#>ckW_0_r6v&N~jX$NEcYj2)?2%=w3pMGhdD43V3`+T5HA+OQgDO4$-UB1#~
zWLrf42KUs*e&<symNu;eTn}Zhb8J^DY$7I-xd<60BjhQ~q6z7uug#}}yxI^c=6)x>
z_q@7#`ah6arT4Ju4hYuFGGQL}w*(rYAHqGCh%i|D(Q%(uV&mZp-qhiroq?yZIxcF~
z2UJ9ak%;53!L)~Uhhe2jiSkEpI+lv=eB_tFD0pR_EOZ6`%>3)+pC`<2_=ktqWd(%T
zTE&0uzBd)aKjcHanjQ!1{|Ay4vu|Tsd80RJJCk|PE=sb%lcw#;I;i^jc1?Bf2d57M
zMaB24v18%9wO(;jgR14bmOq3)PW?RWpCE|z3asIVs#9OS`OuAv(~<mb3Hd#}Jn%Sv
z+T`+YrA4>7^hCxhvP)-&Bh_hkhd;jrd-qYo=+1zyi)+iBvBe1Z<q4XU=3o7}m-jDs
z6BEm>t<5_=aH&@D>uVAJk|E15^r*zVmZvL8AAh2eWB#*=zvc8vi=mf21*2cd+#><@
zKZ5fOOd!{%GAs|}jX7_E;K+E~x;f2X$nQP-Y4?%UmhMY>J=N76j>9|r);@u+vOO?J
zXqld(6i<%mvjQGH#Qz;d!~v!(NxzbFTjjfBp1_tis@u1#t>=Wo3y!}O`6*Y_lCQT`
zs5PzZ{C1_F;fmRV-?3f`^YR@UJQ)Q`{u=Xmc>`U>8|dr*K-d`Iv+2Xx>hz#$>#ra7
z3pi`<MzIFFQzft6y#TW`BmoK)<p1$cnxsn409E-qIVKdnT(Rs4-L^hMR3-DCX0x8M
z{{DY`9aJ0NdU;;sbZ~ms7$oZac#8*dlQ&U0`VV1V-K^W`ukFyokW%*>Up3TRqSO-A
zZ0c|^V@2j|F4Kw+32Sg(WJ!&e?oM^Az~}u0tgZTJZ#bb`sIPc2S>zNi0b$R6ZrvvN
zaOZ9yVkZ4a_S!SRMn$PsnLK365~Or%Z8H-*1=`>`-Oa@X80;533mha@wbJv!%A6*<
zl42@4avvOP7c;X}$N>AU5p-Y?4x6F_^%fkvQ@lo*)_bq5L0{rO?pFl`y$;itX;J(q
z4@?)MYvDHy94-efKKs%QW22oq%6ow(ZK`-CVGH#`TV)L>>UaexH1X%J%CJOVPlgG*
z2lCdPT;o*W4Wmh`(qQq?&r84<LXajM=m|BaXH|)VZ0QyH9nhu(i(W|24wZ6Ps(}Rv
z);5gnA6dve4D8B90DwvMyB-{bVFlOqWq~Xm!pnwt85!y&u~NZp^G>&enl&^4NZ}X=
z<8i$1DP+FqcTgUlBpxAup(kTeoZ(=yO<53yV^JIkG!9rhz+!X}&#_J71Xi!10>JGA
zD}FH-Plg^ub}l)>YKH>&_)ui9CPvY~Wu)CoQK!ojc^r=dm?u@T@Ln;5_p8Cbv`8q0
zX`9k*VkL?JgPx%k;{>bF0c5*VfFa2LX60EyBj%F&atkoH;9_XfJqvR$lOZrja<5{+
zjz#0>fXJ&xl${L#`+D%5cjwWWQ6QJzDXsyOEr8hHCasS#+@k{YCW(Ya<1EyyAr#QS
z#KXY?-UKM0M8Moaf{dhCfyHgy0NUjf1>i%85Ji9s1$E^#1Koe2ZGX&&J8&Ua39cHd
zf*!1uJB;+t5C+v(Wdi|!z?FjGERBX4sE5KsGjVSznx0Stwj?jvRTE}m%LGfJRT!vj
zgH148PXbhwnc{#xShOBepRckQLlaO1MAF~Z5%f*?W2Y@c1DEtbkXaeD0O|V3Ac$!F
zO}vX9%Um`Gb~r{)cn%MNv{Oldj?A--HB_8zyZ9B=Q3B)jP3OxC&|?N~rNsrNf|{jJ
zpmy+&LYw`8>yWO@rQub{c!;)|(_)$m^-K(#Ds>G`u5qw5WL?+CDC%QPSOKXCNa`SO
z5@GJhAYjgj&0+~6@%Dqia)$*o(Ci;jAVwo(ITqc5{Mw~j3>_nY%sD({kck=GW{~c~
zQ4B&s`Yd={$Xpg=hdN;@Yh92IiRSIkV@F%0&ptvzM!}?{ghwAUr=^XKN-s$pOFkal
zsqSOQk2OCX@XLxxykr>p^T86q%T_XpVLqeD4Y`s6HZJ?@swGD_4y+G53i7O&5J#EK
zuN`5R&VQrH2*nan;xPs|7DL`Pc_R^7sX?ZPwi-P3iAlg3s*o2-ks;K#2i#_uURX6U
zm2!(d*2t<<*aW<OAfx5G*4>~WY~HkFnfU`gxxegn>h6XK`^g15d+8^lZ#V<RH?P`T
z+9Nz1ikM4C1FDxUwL94crE`S|JmwA<OTgy!xvVuZ$6j?=*xwV%b02Gz5Q?1Nr}F`G
zU2$Z(*e1ph^xLn1e^ayUVHi*0ul&14IhPnZOGGx*E{SEbuu2*+C=?P{|FDi8%>?bG
zOs35wRSBxD8@dh-vP!Ivfc|(r7w9&a42^)EJw(Q3q<(6Pp0!Pa03{?E4MlP|-ATY%
zd2EqW0gdEL!YvCm%VDZ|f_i{{m<r4-P1p*G+93-p0+8^P0MyY!m-?VC99<YJrnms*
z3wCn|m~2!bmXliPIo&u!TstV5i?qSbC1D_3(>)fe3c@@(J>X*1WR+HkphpIQiv+Yi
zmy$qdA0~uic}@YoPBm7A<E4Lt-k^01Sv80{BZG(n&sEe>BO3F6-Ozv+urH)DfXs_S
z9UV)G%(G(F(cskO+R_Jp_AqiOlFO2TVsr|!#m&UT!_};|T}JYMTS3iDh$eG!d7${B
zc3@eEQx!NY)5P(Nw7ZnRO5y-S8Fg*vluiM!(zTwRPk+2?#_D;`*k_(?7wc=ueas)n
zxj%kdl$d(kwxuKRb49?%>sb7|R|N0y%N}t1`rU#Z?cjLz=Xy$~3A@OIKD*d}U!xee
z)~10RuXg5fWY2n<n1bXoT%~!96O)y(`MMsM*n=-!zRqT|LrDu%Ha*9E$xs?`Sp)z2
z1)Fn6%9Pz{Gy57q&T)oBhRh|On&4Gj+c3%e)J3XYp;sC_IfnFUF<0dm-W`yA>-GlC
zW_=ziJd*MuZJcOb-1p>F>2B$jba5*|PZ9w6Ru4U%loYeH?&>?_Lk}$kw^PnkzA8?L
zcQZrKT+I>^W6uQ)7VVbGJTNN(&2|Fr+8ZIC7cV|GFPl1Lo{Bd)#<5e}>6a7gk)&hg
zNeK$+|Kef!DF_y?ZzsClBgR4YV+pR%fkm5p*-6xPO-m)LcOkCXhiqOK`Tj*RGNW-%
z0P1xz(KjV!->xj(7h^__d#Sj3F*SJN3$BWZqcWoHlDEv3q&iuvu*2&5GGq>(yEwqs
z;$>C4Y*k(C6$<-tSl_O%2}G5IhLj<Hjf8DY>`Y@&+imf4{JoMdTK+a9#tm90$rN~_
zgM~%ogW>wm>NGhgzKc*UWk|{y;M$}traNEU;^H{e3m+wvD8<F3{$x&ll!u#pIqB?t
zuOUUi=ycSv8gzcJQrWy+hgsUoOFMo%N8RX-ycsP545uyqAyL4i|Kj*7w#%tgvD9gH
zZPw1EhB|>Ro}126`Qa_}D|q87qr>e>hhlnfr$EnugD~qX-%jx+yTjJ!Wto78jfv#n
zmU)Y*F?b-_+3NS~Vr8y^24MBg0}Q?y;(mJR!zGcebdM>U+N)a%Hcm_U6L(ENC6OrI
zO=H!Kxq;E~iI1N1ABnYLfw?AG+I*Elmz}CR|H;e8<I;W(V*7w|rRri)*x2%f^ZpW3
z^CiSvVcVzbpU>Z(Ddh~k;V_fo>nz%>EXh?KF*LQ4>*F#Lalf;%$=~aCfohiQY?9Zv
z?TQsmGqGu5mDvj0?(089oCDprSDaJo><!XXnqL`C4j_HY8~0MCcm#a6D+Ea?STooV
z$Pa1@s**R0*Qo4BNJDOQyF9X&?TDldez>%n?_*QYfCc99hS9NZ^`gHgHP03Ow4Hrq
zl_~AoBX)6#c5Auzv63p-O~qJJoK8Di!FiZY@DI#)Vp^}_G7cUk#7&8M(^{>M+<(s%
zT7wSdbBu2X`GQtULBt8@eDiMQ5LemH9lX~GS?1D1oW1e9>}G92^kD<-7sryVd($xg
zc-XrOW4YskI_-yYU*6m6M&A`HU9nv>A>;5brc_~Ff(tuUPt<FeNzUBIJib+a;bYWJ
zg;#%w8><OB`Aw^RFl~#cp{V@rs}Kkc+txL3tZjInaL4pbL@ck@t{7AG0B`r-xvKE~
z28eN)&W*X98l#^I(?z9c@*4H@@^&k*QVw~qty8u<s;t#^7C8KWw>_y4npho`0i&(+
zPdCS&x?RV1gwFY$^b4MpbZ-mQlG@Oi5lOsr&7?Ni&(+0`a>aFnzrM%cXz`Vwh{59b
zPnw3aW7ZCtjYq|v3Y~q+G{0y1MQN1rTAbcMIKO7wuNaNJq3C>FBCv?<6#Z4<gZ-yA
zIY$)$N?hjn)T)Nhb0@t`u5smA!{&B|<BWE4W#$jX-fsT>E0a0e4v$E^tLySVKKVQf
zJfKf|H*qPnDlAFj85dS9SJPM7S8Uemo4@%=-l#f9=yEPe@FOMh{Qen;9c#RB7;yJz
z{L4q40~*-tY2OVy<QfW<A9t(?;|?tSYbSNeJ;!Gif(0wC(2v+FIMrzFEWTibA`Z)6
zWr@JcG<UK$$>GO>cVPPu-AC^(j3NhTjL9W8M??RfP^bI{a@{v<t#v$W;#Y-LooVg|
zvEAQeBU&o&&#sYrwnZ>ooZS&(Pb9IAT*a#OoRh2xmYW~n#8jWTc<lSQEY}0QmWb_&
zfTu?7-VsG{Q^MBG*M2<cY~d}Wp3VmFqQjN+O+WI@Au~tO?Y)s;7Sp6=+%fo+omzes
zk#h^cQLA~@eqX=Yb*`<|oz<IXZm-ia?@uZE2!o#AzJrbFx8EwxdJN5hMJml*CU!sh
z%HAK&A(Hx{c)a2AY0=GF+SC2A%wG!DMzwa{yDxh=My$Af;*(&XdF`Kj{pG!LPU<``
zP+VXfYs&eW@oBB94jLznH+`67b*ZbY_2nwFDlNR5aOli}XsBwL!kuJm!D#4~UYod|
zvo3lgt4yiGE3_uqzcV{8ufWR}BXHtFpmWaF2Vr7#-?dRo1;6wS!vxcJ#kdh-X6U9I
z+#s7bVBOSiKUb!x%z}v<Vv(x(=o~#8h7i6}Z7TY8b2RFF1+&@0r+Y@xHiR8<6ptpx
z*8lG!WrFkfNM`(*T}h=kMc!EsHuHjEykF3roIKnPW(bC<aw9wc1prfwEMg<ytwZgz
zRo6(jHtCLv8Nar(f6wF3m}rB`pYXONo?^MIG;a1XqTs%h`qRPMI70f)teyQt%~79E
z*p-Q-`Y(CW59a?6TWn1Fk9jU5JEFZ!ZsHf}f9EzA2K98T&|jX5$jG=HmsEwV3;elD
zWmq`UgkSiakiV~J&t*_bxg_ZX@+>~S^0S*U@9zhm^WD7F(Bu(188b4TyBvvVd6jAC
zW4W;TAIKAS7cUuPa?Xe4Msx3oM*FGuf(#21Vm74^{m8zpz>$3ZVH1ynH$3==;M;|0
zoIMM<Iu?oUsbn*>UboXSbf3DRx!m0P8(p5kdB6Nr(0NOOVX5aGYG&z1-&+CsNEf+x
zGgG9yS~g=LNld2LZzqqec`a55F}}Zb3^+=Rrw(5A^WRhy`Q>ga^{SQNWGwC0{b9R2
zcI9J#*a47Id2W$p`w%NuH4zF@zr#W%R76MRE*UYdHyh5+-W&OK_FUo=Gd;bm`C(#i
zX#7bQ$hi{wF_%C4A;0lon=;*}INz{Q2EQ_|iUc?eSIBxvw)tp%-s5dJ8Svf9m|Jda
zwjOIFZL_fz=sl2SpDGx$C9pKpa3MJV%0}xe`#*a>i421LCV$G93&XB<`fRJ!Ysb{f
zb{}!9m3EV@Zwh_G%hgUk^7m!k`CVt6z~fyi%bBt2T$_d?bPF^c*j9CP_%o$zzxUFe
z<7QJ;Zu}^Q^DUw}I(ns=YOvCEHbF4&Tf>8<)P2c#>4k^w4t;?{?j(a+<;%~{k9~j0
zYo<09+abUZS{nCp`@F2|5R!XxNe_axRl0ck`t@wut8i+PoTl8LXU3LOjQ8G!FSR)X
z1VqjaD2YA3bke*|{>VJ>WpJC7@wMu!wdws!H@q?&F5U!TH+Gb^oHfm(yW;x&M49k(
zrb~L)nnvn>Kj0SW%iHCDmg*X47o-n)F1Tu4enN3_qU8pk*KtRucgyA<W}bfo5RE;~
zlrOD@>?Rf^r$5&^Z3iO8a%0AtX?)jOu>rn&F1Q-GUyF5Ly7+X@XR>5w<a)Zc^S64o
z+&i<V$t&krDqX&OY7jG4rO_JGFUNgmWb)dRTj@RPy@8&u2r~!LT(*t7mAA>4i_=0g
zJ1!_ab+#IsIDr#wm={Gjc~>QwWgm>!Iy!!ym|T6#K?^^Xn4(|PEE?!t2l=z5VTF%e
z>z3<=_2*Cl<L~rvRfLhSWHVdbIE)@nwNA4U@0FBHa~N|G9cf@a;V`-Xgiz9U`=nd~
zY9a94WTdd%oA|GhZ!QKneZp6#ho|@_eqOQ+lXOf@m{=9v!Dxwi`vyE7v2Svp6nl7a
z&U+w?ksBe|IseO}@-o*(^nJO3L%C@KUz3$rqIvc;03=pgcJK|gYq)W4;1RL2`Fyj#
zI_IKq(C=I$PA8o+3OoGUnJV2|m2EdVc7@trNo~l_57jzab*oQYed(N(-*<B)vVs09
ztpn?sbw|2ach8}v(R{2;rPs(=;D>|^G9OrK;Ey%mIJl(efHs66wJ6VPqwrn5hKceQ
zeKUW(+l=#UCD87Bc1`%#*TrSp!o$8ip2_U2y6_*!P&d_+`Int^uJk8}Hq}cir$*W_
zpS6gH!{Zg3c~mtYdQN;E@Sl{3HR1_K&LQ2t`CzB)<QX$a?{+ou!&|lVg>ZarncxR8
zhO<ak%-u8R&JNeV;9bk(3}GH{eX?-=j9oIJN6}%|<<zKrPuR0C<-@+!&Af4{BWBF*
zCdUP`Q|M8<uE_Lj9-3s&mkp^U6Af2pgHehH<5yMw7ea#s!|4lQIO>5P@1A|=H(Jmm
zs%u!6;>CwG77$};)pEl3Cx_?vN9V0YXH}IRsT`HqUBG{T`L>xSW56Y<I+^e+h2uc|
z>#cZm7Kanqg#SPkok=yCztpvJXGcwrzqq1$2;6(PW8Wj|6D6O6-p_w`FaLuK{=X3Z
z1WSw>>{6W&DJ{KTrdpq_N*O`?X(_LWFCDSLb2$>%9%~iHX1N91+Cou~Af|j%-3+#T
z9SJ=csL{iz>A|l1!&1!zi7mcgT!Sp2y>#JMU-YNXs^3N4Z1er)XSjX4#$6^E)ouvB
zzvfhPQv1DBNET}w8@Jyh`ZL9fO7j9S^(gdX|51%-=C}PSH2b&HE>k>g8k=y0vEj5g
zRq*jVf>^5Oq#ZP>*kKoZG#cK)+1z?ytF$s!RpRIHn5BD<{04nvizcB|mJ!Xf%}mrq
zYo)g<(&RCeK?F@4mWEcPfRiYR-Jcz8R)YU02PNK=_oST#1DEr%$UHv7BUHea8X}^3
z9oR(56lYR1liPR5(u5Jv&S_ILWdYy;3y@F=f>;4YvF9N-(@DH604NyZfWDJ0rV~~V
z>?zDdCo9gI0zKqyV0n!`)du-{1@Gh*eHsk*27vFC<xUK!B$>*fopztiALHU=H%sS>
zp(oHGz`GR4gV7dpV+Q;&MSVpSTNr7Z+#nnbPz!*Xt!|kxggP>OVD-mySx+R26LJM%
zJVr=Q=elv%lA&)Z0FKr~lgRq|9MTmc+5s@kM|Q{)fZ5XK359e@NT-W>f~nau&T`$r
z&r2ONhL)((7_7clJ;Vbq+bO6*Vj&g2O9v4mam}&-)QT}Z`q)p|WiTBA#;08>44mVw
z!6P7r2>>GD@&^Nf8mLkkK&{JM)G1Qh{l)<pM0vOYOVC~OJCqmZmIZ^31K1jPW~`2<
zfWkV^@rnQvIt0&)<kT5U<^*$0G_MRjnG+J~rJW%zK%N0U+@YCh41x%8Ks)H5*f5$H
z+)xUNRYX>6n+!;2pGgS^gQwWi0pMYT9tpcesBZz>nq}-vS{qw5H$*<bXd*g7$P7e$
zehjKoNZ?sJibo-g4bUurj1H1pJn0b21TbRUBr!LL$S%Qx0OJhM*}Gv79y8fa=4x4F
zyn2HK%yJL_$m77zMABKu>(DNMz81MkfXpyq!gIr-UFsj)vNY<YDR3QZQz<KG@HFcz
zg5;G1&I&xgs#E~2;${mlpi1A@hezgnLLh(O?DQ-!;{!v{0HetwP;F7AO5#yqeg||*
z7ED%oOR#2e%pQhnbAs4iG%zj4320c3xMe2%b4jTW5!fB90r3xk`U7uYij|$U0P{69
zqJxFLx&@OvodBWEZ&1bhqahf5cyYQAB>Cp{VqCXqeY-hTwS~mWmT^tUb7>}PEL!Xh
z0shWxT234YCQ&EiyH%+?VZEigCj!jak<sbG4f1oi1e^Q3f+eg{+epY-8{=);0i8wl
zcl}PnE-V`L#lhm&nwRav$Dp$Lau#dI5d(x={;DDoBkzv2T92I-DT8u0np>JPi`#s&
zSDAqKWi#k88Sk1*ge>_EY}@hzjGK<4zq*yAE`*SOfYI1a`79?cXpekzVEfrTe4m9Y
zn4)0&t{|3tZX*A^?Pm0L@eBDGm~FfZ$6WS@6nZwEP>^4KDW}u%wjlDIa*PRQmlmd2
z8=XghH;d+3A7`85NvF4kmF4DHb0boo7ta-hGfeu`t)MDEb$um_`aSFqhWdZ7^<L3%
zJr3CJFnWz-M2Sw+2x3GXC8GB(T69M5HF^*eMh`{}qZ=)HNl0|jMvWj^j3J0#BKe*D
zKkJ;EZ+#bXVOeX~v$JjQe&6S*j?Q|mKMc^kfifDqE-~xhDmk{6gcx&KEZgl2;7>9n
z(1pQ!Nd&@~wQpDXDM22-T8sNSK*7QQ;PdqX?7)P$a^5EbVG_Jj`<aS^>%JNQ7bF>I
zy|v_?@8pzotW$shcY!=mr#nZ3q#?}8SJQexyNYx}lN2_{0XtR%D2sB;0<z&)6rk67
zB0H-DU?a&4zGE1rCpe^F{8JdAWPNcBl=ks?8OO9JH*Yf5rKrUbtVmhpdWN1<paAxF
z;0X>Q3Zp@8AP{GThp<~HhM@VdZ<DQnY0zXi!q86u*hR^<vZ}dx`KryHmk{qCsp~ME
zvB#4(xDk<}Xz^;1Sv|kuAONo}--5<rI2oZ<#6w{e%4em?TgN4Y(F6cPsi-9pV8Dy3
zL9%*%6+a_k01E?5A;ZiMfL*9&77)*5{edfKbi}bv`7j?sYzoq6=)=!~5F2DA21RH+
zoamX!%Dn1gG2_PIeVb^#Q*b9$pEg9ALr&0M+$?7kfab>?n*4&7SZ}<o2hP9rtMY4J
zj=%Ri0j>p$x*My_a6h$IL0sJg-mGVus$hp;i;<4DlW%32sLvA*P%_RRJTd(3*@`*Q
zBkrZCpBIcueo#65U}_LYEo;4qpQy{{F<O-P9uhqC8~W_KemW8UM-zq{`j1<nA7k&P
z@Y>GgKad(flN!iJsPN;g*Q0I6>?h(&W~OTbz{V<piI?bH_gqc?m>%=F&g_2kkmcc_
zP0I>hmK*e3>iQtA8b?Z>a#4}6<#5IqXL)I;%FE-VB<Eah^+GM66VGQa^ng{<?9n$X
zE2Y!ndmY28!}Jw_uA|=tJ*0Ns!P*Ol0b1)h21&x?x5j4WOT5{&%a0n-ezjqyO_k)_
z0&`h5!;+pg-*FBHm8;*BWv(03r#u$bL=swX-siG<e_%B&H)0=jrZ;k=F3Sa<E*UgL
zOfm<e)~qDiUK^*a9&M!JtcfRH2Ma0_?7C;qKl1Wm_Z!j<os6ixkBk>WQFC=A8`C_^
zOg4qeAQ^<e(9B&+*xz!3VN%tNR^0+gTe8Rpjdj%z)zJ_AA`{A=Yv}HHPUs=9YcHNQ
zZY^Xd`g)#cC$;s6AoEBi-qU>W6!QETF;W*^OZ!0#$K9#|Cbp%xXUJU^TAJl#4lvX1
zE8R^uzvf9vHlvqZwx;13hV3>UT1ygIRfJ#Gjju{*z>R>y0<~p|S<vr!p{WPd73H<4
zXPzETFJ3|)ai)JbmuSogeLKuOXBx1qxzhNKbL`^0#&`0<DAX^90;b|`T<Mvri{#W(
z4PZwKC|=eyTA{!Ew2iE!mzs3Hk3<jKZvEUTkKMHN&;0@Jx~OV~`RWeosz8^QSc{S~
zEE}YD)N}Z-6)m5T4^O_0;W)t98aiaSu}60*SE~uSU3!g~)_$=6r8sv-)rZV!BRvmn
z+zUzn5FuB7$k7l&+xVS`)CI7`0~Y&$vm-gM{6ORTAxhsDP|#Z?<H{{QbXf+k#+=tg
zMBo*t7%`lWt=|-cW+T^T4YYt2Srnk$l4x!HOdpac-&-4lfD3QmRn=pyt($E%?ou)R
zvsAwq$ZcSLQfpAi7ucj`JoD<)+Gh=e<;GPeOW=u`^-Xb3h4F%JWtrNOJUbn9V1J$4
z^j^yEt4|-e-zC5?j;9=HLu;k&p10P4S;#%8YwFlQV4bwR>$c$jNYyu8_iSB#7f1Z(
z(s|ael7fG{gmt5GG2<{5UVWC0VSV?nb*&HHl7pZB$t>dz;Og2J+C8$nr+m`L{sfmT
zv8r2B)w*)BzfrEU>Jh}mSjoTHbRdF|LfW*}A(@m|g_LuBZTMLXcQRWEsaLRK56I=S
zu<~v`CA6%ITmG8@=?3Eg|A7<=Ro|J}&Ch^va*GvvVLF&E&>^0?BC-><n75j~9aL=d
z@c6eDUiH*DnZEIXTk@rix61$W!8{K&ya-5IcxILrb=8M`^)0X5G!DgCriMMR3<7HX
z7yip`@kMfKX#^92MO?h@K5tL&EkbtBWUJ^wit2|g8pLC<JSmM40_PohxDNsvnol-z
zTA!`3m<0=Ge`ufbJe4$bBZq2{E0KXP#z|s50ztwOyk=6TqM%>y&D~$hY_||N``^EO
zR(NJQR}x|F@4;fx>Nvz$c+8Fs-&=;1p(pM=zxgLKugpX?Bc5(enW_iJ`jFvJ_*ZwF
z-s*^H$FoL+PyeGE=s#xmnCBT$u;`C;uR1o23*;_vn7gQVis_T6S<29nFbT8_Wxvv+
zUk>Tj+O>?H!gd&NCM_tU*KvsbK+5y(X?4EB=<_;Ur!_5q5sT)n!_GwDC+c}Kb02Zk
z4$c}Y%FQUX*_E33#kt;$l<2(Tf-L_N9d|?%-L!+mq<PzB!6p6Dt<oD<>?iBiFZiiH
zKXq2s2b~_iFNJaIlKrmYBdyeIx%ke&jjDBE$h+HU6KxvDO@vcOaWpU%WbY|0dpbQj
zM+g%$rEpC4SGTtfWibRl)#9iRIy<ZRfUo9`n7LXw9IR+@vxt@s4dCz#N;ZA9Oiq+V
zeT5Y26r|W<VmoJwdBA}P22bT{6!4PJhQ+Gamsx*$vi06{Fn9`{(6<{=Lpp2H?we}E
z-@%g1#x;*=d;RKQi`w$e)m{KNj7dp~k5zC5#dUuQ*kS|@#l|Uc3$P9{fc@C%@tFiW
z!*g3PW?P+DFH3U2k_)2Eju%iS<vYj$`)Un`KuQvVx0OC_o$(H{%%7zd#YQq*%AIXO
z`~(t@gdMzJnbEVoullah>zI>jGzho2`eK~meCqgu8(gu%{OWUK`x-^7?I2y51Ktef
zTd|u$sURp;Y>_SJl{xf$;g7ip^&)Ch;;(i61B&kv0@79;rSS**Bh0EpzXC{_l2*uJ
z{)RnyFUz0x`h{aV-`@v-Vd`sPjdECmB=teF^d_O?Gicwm+`S_`)oVBUsHfj}SreFZ
zn|*XZ=6piMVN8Cexs`rMIPT{l2b%_2$AJ;?*k3nd*%;QEuPy<K(_$v!%wa676=jnw
z5%9^N0tBe3ovD8?$cB2}D5R;=`%){op3`{**Q!T_Y_4l+TeMMOXp{(aSo8EO{eDSs
zgsmrYAbR!oisGjn_a@Jr?H$dn12QpWUVR7iH%%N*nKSRaLZ8@KO?z7L!?suGKZa}8
zm=?#w>t4a^wyq3KyH0IczYZ8&+B`Gs<E#XGTkBV|Cj%36e44N1xsIu0$bNiM6xE_)
z{&k_mcg*I-6tML0WtX@jOA0Q@%X<v7Vy-j?wg^)#+t{}Z{<i&oZ?*d7Q{qOr+V#^6
zslm{ci{#(d;&dl8w<qq*$mKVgL(B2#o8lXOqC0x5LYW%xp7J26E#~Y`e%hn&xQmi-
zSGX5`bny{Ud1bz?`op5o@2gC#TgxL8!t6=G;k@K~2Ar8gLjvy<bxkYg9;ZwjQ%@e*
zwCZbgMrK>T8s+1U<1zf{K^pIr*|1@GKdAe?Lwe?*V{>y_1Hjw=;4Xl4qPjBrA;E%?
zeY2LT9WTtRQRqkPJTU!Epv6f|+3;cS#Mf~M^$z#njqcW`H$ytG9G~k{-WHUfC76zl
z>!;8C(zM67^IY{WW%FV1Z%!Mj5@Q3F=6CJJZRZc9@+ot7l0G_l{B`FS{eGFcVPv^N
z?48dCaVzY*5at^Y@@Z1-b9v9(^=wyqt>b1fUI`=df%tV-Y#3@L)oRX*`_9|UxIV9h
z?&{4hF@O=O`1`}%WKe@t(Vo<K>~_QWkdW?==O0sbpQNaonZ4|q|Lisa%kLUX$yizo
z1KymKrtW9Z*1tv!`2@=3U~Y_mFcP`_eylhwhN}J2or3M<`&#jkaQ)V_2XCgb^wunX
z7WY=&>F4_jJ}Fr=;%VEQ=F$!tk=B`i`Q-*;mZNC<gyw-nYi-DVXL5;pZsWb$Nfm2W
zBFCvfSI^G_!@)WwSa?{>hYp%tp<7LA)BAOZ=Rs4v52!#pU6fPgT=3&HOEF!r=<r#!
zo98b0ajR38)srKst))fisg-a)?-PjW#Ec~o)y$zsV4Y>}i+c3mrDe0_Qj1$f4|vXp
z?^-(*#-ja3*7ws(`)gDlweu6@H`9h~cpNrxdVKw!BloIx7S4>Gc$LQaxnrHyVz=_G
z?+h_=SUKZF=*6RYGp;AkfWnoL-t3XEL^V~j`o-`=0&l!Eth{Cz^dn{4-&C%J{fp)3
zsat?i&3b`ulvxXWAW~P6R2X^wvq<`x1pj!%QDtj*(a3RZ8S41co0{4xAF@NC2I5;~
zit`5uHNqdE%>q3DczZ|#T6kmDg%lH;b3vI@0HEqhj4WA{w}Z|6?=hW!50b+OLv9uk
zfkp)`t>Jv1@k-O*SBezwSxFsjps-iSKflYF&_vU;Bt1sx(avM}RJe44dkGIIG5o@Y
z6WdDus@5GH{O{0x<dt7Z2+}@uWW`UYpuIa|a!2+JV_6v$UEi(y43b)tL3@1JEkYpK
zK5qX-B>N{%HMIm6ZeN?yR>jQ@o=)o&-KfDXxv=_l-rfEHCQ|zKMSZBD%u}!c*T;9+
zlHbP?%LE#VUzvc~7Y^w|uDi@Cqw|B4rcBKH`lsBaCj?lcQXYn>O5VxfX9Bu8B%zEY
zDj4X&94C)|SNkhdFb{RK`gwiW^yURk=c+Yd(vYXEtvFCl9l{_Hj$NK;fy$)YnF1FQ
zRM+b#I!(H?<t{3G*_H2UlLPDb`{l`7j@gPYzPH;3vv^8LtQ#l)6napKi^Uu?oP(TS
z%PD*wZfY=3Sf&i5q*DK+WPalk4_y^pwTpjA;rC>|i)0=Ygek47v!ID^9pslT%>`Im
zC9eM`!xb2to4wf(zY04iHM-}(t~u{aAuTmUuWaFolK3`t+wA>Q$4k3S-oCrY@llm3
zLnXEe?Wc8@fUniv<|#g(byCOSD?!>{S59`N+XvFWT}N2dRl+!SBU^W(i0fak(Z9PR
z_H)elY%t6g?HXSSWIdk|;u;;{z_Lqc1*XE8ZdU!5pWw_`$L9@!^iJl1pb}R!kL`eu
zA{3D2ApeBZ3$>(L_)Yk7%F>guj+Rgw8;4spJR<lH<fzZ>eZ7Y}DIphEg%_E_{Gyl*
zm~Q}mae%?8D7(>%uy+j?vZ1_41u=-@%|hk7&dK@PYQX>gY<C1rHw&SDA)cskx8>^K
zQp1z$Q-%11Ugg!+AFq&uUjd7u>Z_*({OlH+fI~)SbupieNOS2Dhgklt>v_JN#Bk|E
zHdU@&k1S`@6h;SE>i23@t!I4Yhy=%_TR4i@bjX)Bw=z|v8a5h}jyrq)2g0`QAx+;H
z-Zy&pPVGXfnpwgwfr%}lP=%1o(pCQ_mx}y*H*E?Fegay;PQ5olwZ7~7!-7m3hWMgk
zq9`Nlmk#D@0*O<<KbA2afujU#yk?*4*gU#^h7bC>KYb);Urm>YVO6xp5BY_7EcpA)
z9}TQK#Pj;<R-Cg+)n|&@_?xg-<9aP^#7!I-{Sk<GMZ0~|>3MO}EonyjJ1hQ6nQ^KB
zhB6Y;TK%RlUIbbk&%b|O0r<m#lrMOKgXSARlUGLrWS9cOO8{6y02tCs%7<JD1O(K0
zV-*BRctu^yhe82P2+2BNKCbi}0jgq5ahd?r6_Q)>7+As~=l-H21OUrlM{KflaXTwe
z_5m6^!wbp&x<?v_pgXUF%ZC9Kxt0A}P<}`W!a{5zhI|&o=P}zfND>nRd5zE)1wcOp
z#KMGtb72bN$Oh1Bdv`%xC{pOBLJ`2U2iTum1t76$pmh|frh#gdAQ7O2+=3V~+cItf
z!itD$(gt8_XP_}R0~iR2kCe)ep}7z$gDDF!fLaPn3Ge3Y1G4tpUC@!@K8jzyN1sy$
z_0o-4L`e~tYbiqX2?I(32L<qhj1wSUVCpx)r}V$BS7&Le8_X4SGaUtt6$Jo{XIb%3
zrgWt~A%LBobp1yG5`c@vXvCpFR{m;k0@NUZLH^CmR^a<p^yBXb90zI`Q9^O0Z37K}
z$Hh?22&J&F<<nF~0bdQ!Hpu}L;@l1bICda?0X1DX5XT{`Hq!toZW^!$Bbu220Yx(h
zu9!g(KVu0>`9QIP@KoIuNFssanw||mx`eo_1i--nuMYp88gdZi!w))A^Hn4PI6Q>n
z*jNG%>?N>0#V}3?Fs<tY^@d#ZF!1EnPCcZAcvl8%NMSSq5>dh;v%spL5+xOOO)D3?
zBKbK9@)Iz%1o*Wm*_kUK)FjY~h7)kbhL+ePEs_oGvsm;&B(xS{8Vd!aEYpM(HlH-9
z8B3l4P^W|(NERqE;8Q$%%0m!Iv=1$y!~@opdYkL|QjiX*GSc4_gaPHiH&c%01of37
z0nZ?nI07VxE!cwQ-5hI!S>fL!y0C#4B}GzbF}Rp&=uVE@G^Z;LT8xx$q0s>WaV9&4
z0|*A=hRZpC6)GTSf0|k@%0_;J4KoV1ohf!Bk}Ci}Nzh_o;2X$vfo2s~(*^cUsw$5U
z1+r*9o`Fu*&Z19sSSWn95Fj6*h`D;8*uQR=M$G}zk=B@k&ZJscts4=H$$RV+kS?HT
zHN#p#{8q;|vvdC1q%nF_Vn^!a^r3r#DlC!ojM8!e)pw?e-uS3!ck8t((x_RaNj6~A
z?-6K9$<KYoRgkvw%K-y8%^)!yBBN<AHjPH97%*Fz*ho!q@l6bBlfj}im6c7@A-_8z
zj<gn%K#&D0D$zG8B9@XY=l2|n=3EM&eG&1Aq9DC!{y}jVsDAvwfNoOI#dlKh!wA7<
zHJQV4F<!r^JXAEIrhAOk;ytZ%1;a4T;5rXF%hxK}#L3+N{p@RyN6wb@83!TYREQT#
zWtxDti5=+(7tMiAr)SMibygII-QXS$a?@hpuhG2u9S+mj`=ceK;6YBgbd9tpVMhLO
zinOB@f3VJ}<qVXR1(%x$-Pl+-h?xvzP=E~_WB~E?vVFoL*Uo$h(11pGy6Om<j8M=F
z1|4V>%&JP4P#F>|-3oLLl9m%4BY^g(Y6u!|y97W%n{eqN0UA&l6!fu$SsS4br;^d9
zf%8vBRDtlSK1*eC1R9e%VAdmzA{akQAeuLtK?(;+WW)g%AT$(Iwg`<Xg7cqkMl&4W
zR`d7&%L3?%3>aRe1Ev2!ywPw_Q27MZ|9iQJM^FiIe_1)WQa9`MdcaODxu#4208a+!
z_Hc4sFROalwLYgmLOVvy2(M<-k|1IsW9Wd*VhNw-fWBs%%c=zCpHdK)<FW!5NZ#jZ
zQT#~x{tuMyT-hhQA}O#j4&?@@%rWuc2CghWIBgqH%|%#Y!whb)1bUjv0Dk(XMl3)$
zW8l7ZEh8nOuuu#$$8s={z~W{?Dm2i<vRhdIydrFu-cbLWtsX}8qQi!4w4tzb&%6&o
z`N#WQ();SNYVG1DkC4=gZ-(N&g;@+{OL)RweRj$RH||#>-Vp#D5E?se1lgBFNGLuI
z%AiqkRl3(q5Hl4P{z6k7w3Egh$#l%xT8pVDiKe@BwClg9#~$wMp`iSu?JJu-U7jMo
z<Moz5FrrHSjIs|icg+`OY8G}3%Og^)WSsNEJxE4IgyziX8eC`LemSjQzNDWZTa(-)
zYAr>^1ESWSRb-maZEtGJ{Btg-QMF8~9($zrEg;{KG*GGX$Bz)N>xc1$C49K#B3f+j
zX-`V$Ty41V?~xpJyPOQ^(K_P-n}myx$>+lCmTe2drsj?W$ESSdaJo!n>t@<$M5#5?
zuWdo`OEqQdp!}^Fzv)4r{d@m`?(eNh+>_ojYOC5i3K;OSk^2wSB}8$^Sj5e;f4ykr
z9qJu?C;g#vhok?X{~FKWfb)ZAL~AWL-OWnF??t|~=DCkqzN>179xRu%s+XJGrOlr<
zv#adqdF0TYOt?BlpI#5=T~LNKR|6JBe+kb?%vdx0qgD9yf1o}$*^mnMlaaq}o`S!6
zYFW1&NK?b`>347-w(CJc>57=2wyZj;7q#HH%b1J$40j3N&M3MUC(n%pznoS#sZY_V
zJ=q|6u&>`+p+S9fUQ5gVZAr#4+Fv&#Fr7w`TD=tI%$~*4fGtY;sB%`dl)NQ3Tbe)a
zS%Ib=_jyYIqB^fJTYeRsE)Vg#nd3d52^pytt{n5zm=J>GTQW_DIPbWuLMnf*-wiWe
z$lS12wJg_IS*N19XY@^vYm88gslI5L@@mE<>0hM3-n)l?fIm0%*1u&aWH}ZUoYmpw
zBm#<0M$%x+-Hfe5XKiLD%EuYB26{Rno?jOZl7pDgc$KUs69%K`9JLOmOePbSQ<I`G
z^C8W}iWDR5jt4dzuP>YiWq;l1tV9W^hMZT0gq%qrpIRII6o$O<8K01d24j0=UQ)jp
z5q|)Rm@p{rHy8;XI!-v}`VbO4y)3nRu2!6UNBR~&z;a&S6-8`?1o5o|)a@5jt_>`y
zC>V;r=(?*q&Y*KH+BwLcNFREZ-*M$A+Y72<!){7EERB>|cYZ(Xx-4OP;mA}OSPqK0
zRA<}F^!A=JUi#?Bfj%nw*RuIPm|b59(K@yaYDoG_nZi3VtFymG_d8glR{VX_BEvY@
z=m<;0mC2`rrON~U0h+6NHNJ%+zHA!fe}S_sY8ou`qG4;if6vlZlWTsaO2iA&XENdq
zhpR^tNyJj!950{w(U1)ryfFP4R_37~7xC>*8tv6wnhp$Is?O`gUG?vBA(s@m1;XhL
zTLQ0G{b4?;g@bI^W2*+S3q8;ulB?Dm-?#C2f@Eb)&nc+JycN1Sq|Nc=9hP(aE!37B
z=^dn&_vW+ZS`2<>B%|JVr$EQA&Fsh-<Z^9no8ev-dnlXxg>y1O=zT2<RW8bEGhcBh
zd%$ilqiYPpMoa%y4>r-e|32%rS2lJJ^Dhe$V|Dnc0yf8gEKO4>XULfP>X^`GJ$}zG
z+_1mq3HuYF;@qGqk`9dF@&%N$!uvAjuTVkyIhiiep^wbWS6Q}h&#m#9h>PG9Cf`MA
z4ENT4h_iY<CQs|EZz3dsxu}wETg>~2&dlgVkr`W1u!!oBn$)#kQ0hRJ+%B6f7in>U
zeI2)Ju!C5SZF|I016`(-r0ARNXXAgj23=pc-x+jnV*L-q|9P}KT}}EiY14lohwqx*
zr5(6$AGAHWoQQa0YR3Y4oz-o$e`qUocaAb*EcF=NDMOktbKYby_3hamzN`bUNA>Bt
zyTMfcF~%DxYx!pu;w=|ImE&}4KOatHw45__EW*{0$_%eBJJ8R)3>Fy1>2BD!UN?Pw
zA$bh6p_$Iect#Vp(?UUu`XW$aB`t2X3DquY^tHQXM#;@nx6Y)WQk`ev9e$Cf1}i4E
zUUzvD?ZAw9>z;qCJ;{-WN`ili+-0nv+<<f1uOn1s<5ML&lgiTH3a}ek{v(oFq==hy
zZu5HNP;h`+s{RiYR9tTUV#$pVPeR5x1b+(k3K<i5+9yK4v#{TG@ubJ@lja%5X=~0d
z#Xj42tpld4-qVuXBiKxZ-KF%$LdEi*dzCG;R;swxX8cB$30b}ke=TU%bYT6u>{5+B
zC51-Pys=01k4nqe_i9R0IODVL6UH{gg<rmm@Hx|-)(>u;3g>h0x{C=vi&ozbE}>>D
zJG~<cX;y0S6AU-Gb{p8wouYrpIJiM&JoY}(9{z`1&h{_0(>}ApGF^rCbu^3ZSsg}Z
z`QI{LuV{!}^_OcSvRs!|dwR4;MUTbCWfiZBx}W0T4yCG&OTHtJO#jiaO#V#xAipq0
z)a<O<cu05K$#*eMkqP@v%-&2222ZIF0v9;9PH|`7);v+5Ao8EZlZ}5E-&*^Co8IC$
zQk2@aekb+It#Ir<(-Fcpw5WxvkxjkNrC#$SC^V;FYpqL<vGzZZ2k)<JoB468W5LFC
z9E5?6DnIR_vSGr*JkV$XpffEsr$6E&l60dKOw!aQ*b^l0J7u{!)q0X;k3OknD$l<}
zB+G1}T%X@O??!34Flmr%6b+T_NVAFe)0^^zl$$=IkHN^c(v14WC6P}2awTZ&;Gk&Y
zTcy{aS*ZQ8lVS;QGq~7vblkQ-@Ks8HuJxel(#T!^FZ#rzx+}&W*R1eG!2vHE0@E#|
zc$X*NiZG=5^_nGBWUG=BLDP!A(L1V6b_`e&BjVJa{aCmFJwA;%JEFOov-vK#IwV=u
zAK37qtwS&fM_*aFs^t{Kq`O;O1+^KNlpDFAwshLolK7CZ8ZBog6yfjh?hDDeBj=X#
z<pxm;uUbu5^~{5D3l9bc$zX~~O1~S%8(f?qpYVI<?)WyjD9&xn8*|uNN9@0MS8n{}
zN9#7!IC~aOt*GNXGc+mIs`v797XwO4(IujG&n>Oa@1~+Wv@(G~j58&Cr)T!%G5fNM
z0K{P&k2s&Y_pQHbw>eex?<5ng#QJh_q;AQs@5$wPosiW#;|{j)dsmyK3EzSpA|qQH
zy!~zMPqry&G5Y$i3oDb4&0%*S{ULlmgBx032sR|x9qG~Cm+rTP$r>B##g-8fELZw)
zXE-JK#7Q3*3<u1#ol8OSfVc6X3=%!h@apNBkSkS-SG%MYmPzAUm#jvqtpNAC8qDIG
zI#iH7;A!q=WTBm~dNHCZjkgH)vszWV$SWsBCbrs|D_!JBUk9B@Jh~*|n2FW<=*|!k
zoe@5<1TI-O=2{o`^w_CNl6?B0T)kXr3-efu!0CsBL)H0v9-kHGf;1-MJN`y09%HZD
z*QzoJpJyH(4Z>eoJu<8wS(cu3FUpa3UMVn1?$IniA;3S2vkki_-Xwb*fQgUosux3T
zo$p_@(wl3CQur5J?09@#j2|$Q^$}I{61e#DtKsR`H_Gp=f#EA{cJ?O&@9K~>_f@WA
z&M*%e?pj+dU(=))_@=KlwYm@FmAQ6s#}Ye1+aD&(A|_S?NdkhpdMA>8c-4u9#Y^4p
zSNy(A@p|lSI{E7-qfdl;?yN*A?;xh4)pTS?@3gwEG~QwD>2)%^avU=d5ca9CVo!Bv
z(Jp3K;Ar21jrsU_Sn@r~AJkQ!0*cOut#yJgd2`dk{Fh7G9camsdc3LLn7&^k4bX~r
z=5HU%x|I6_n>{^wIpR4Cp7u3*$t~`fGQ3dH(yHZTnW(?NNN-qEQAaEm)E5<MQHPg_
z<E>`M2$Elqv@^09_x8c_h<OUl*;k0ef4zO$*E~E$*qrPT!8qkIyA%3r<_GA2J;j2z
zqk;CS>)WF|KB~K7(E}!LZlfwS#E0yhC~qBo+_4E&j{`kNB(@dkrZK=>hGoO`&BDRu
zfFYLAw$-P*?HxB_=as+g%A<R2VsrmgyG6Y(6C~IYDb`8kjAV?8mveQ6*3_hE0OSfO
zB!K=I3usHK!RpHR8+Q9;!}Y(wZ3hm-`ODXse{oNW%2Rx{KE3wT+JuSv0`-=PtU&rr
zZuGGNyQ;zlM`nXS+|44FS;(^dsSk<FV*OQ4-=)k#)no2_GSW>QW%MhkmR3tgSFx|n
zvvh24SV*pF(GCj|r@TJmnE2&)T^y0fd3`c-0+}J%0+i8&kr3S==#A3Jf6wEgiu;>s
zL$F2qBJlc$oc9oQcu?=FcQVG4x2&zFJMaB3^7DB6ALJIW^}1un*U!_ZUSut;v*lK7
zhxuzpR7>HI?sK9bI02dz(n36n$!8E_iJ}i=<FvvzNqUJ}6?i7ylOEc@c1`$rO_v?@
zO@wx=C8~&*{bo=66(}q(eds`4<g;2kdnObiKW5s}Lis>sqLKNx4&^|5n95t_2ODaX
zmNxXqDQEIL_rA*Yb5g7}er#QzEPeYyQf(Uc0A(>|9oCO|=bQ(jE4XLWUt_Uic|G<Y
zNZ1vf7c3G`H}TTy!;IYvueTn~L&h%jQ~O;jIX(%q=w;5RT;#v`$>Gi2TP^kr<2IM@
z#w4^<-vR3JV~4hxTN8M_8!d6hhv!L|oQybZ`+n|k93Ut^OO<FHZ_1(`TS4H5!e{@-
zJ0pP@Iux}4@Fy#*7a&fmg2jV)*Tb0gB*c?Xb%AmluvRaj$a&-PTCkQy)JsTq;9keH
zms+|2C#|>JO3mflk3+Vqeif*DOV_6Bk=NH#d?ypm>YsY>%U#rlqV0yqm%3xaQ9Vjr
z33XqMVE*f9zqeYw8N~WOf?3S!t1{VT1>`^X#I3)64fLl~{fE{*rCyme(Nv_@sU9f&
zaI@}YtTa$kmTSV_U=P@03spe8%T|C3OXZQ!BPaF!wHlT3IuCNxGnmjb1gKUxzGZ2Z
zjkZckLe95N?6p#~z?nY5{|~)X{}I@6prx)$AfH9BEzgtl%c7vj@0aPeq{EA4@1%Qr
za~mCr9x;B50bBbvg*E2pdrx^SYXgH4cdWl)RM=7~p1yndRx^g&dTEK@w{u>%&c1HO
zf|db~N=oV(G6NrG!Q875djfRo4p)dVtq@OP&XBrI^2Ky)TMjV+$bo4y!}Lk**gv{6
z0~K+O{|%jCg6}HX3(Hs476Y^uG`sb`c4M|*nm|>)z1MQs_B0?|lj0`*7+KN$@~4NH
z%4Wz{i{7suAR(bGe8<+!qO8ao@5fkL<q7+(R5w}+6$N1d7BfT6=(C#U-#c}2Cb*3~
zm&UD5Iy|;+z^}CS-k=`&NZtER!=>V?GT?b-jP9U^JrjEUvg~+57{tL6T$T<jUL&(W
z`cV|J22&e~WUf=KBB$jQgn=VvFd*PlCmv+n0)Qc|L+~Y{@2W8T(gfoK;T<Xf7G)Iy
z@6!iAJJlqXWie{op5}b-uk$TER?txDvV;H?M49f{UqTaRoQT&MywA8|7+iT#0r0~a
zCpekPr~U)k<N%Rp3BaVri0Fj@OIe3<V8^FX24IqNq4vO0g18{W)%Bpj;*=2zSYN^5
zD+;UW2!Tq4e>I?BB@M+(AaCouF?0m$qJjD(e_1;eRFPkxuOqMr)czP*1*8X=Hlrbc
zKn(dgvl60DFv+i=34{~&(GXu%sj|!o)~Y)+EeTowOLjo`|KZs90WH@KG8TY+-3qJ_
zL&LGbQ&0*JwJ@a6l^|?pwv_{z^%kx2mk+Y0fFAPiYb;@ZO9AU)HyH%~Il#j`FYDab
zDlTV9S0o1*<b7pVfT0wm+p8nY2r$tIkzyLjhFh?BQ38}0ur4cOghq=Eg4fb~;Qn#I
z@HU$;ncadKButWtSF9iy1l<?{+NeQJvM``*cv68Pk=+%L)t5Cufn;s~a{6K~q)!|{
z3*gjoT8d;eDkNFh{~_r4FUv?z%YlSc1{;G#{;dLNYs0{lH4YGgse=lFOHm|haz<T%
zC8>nn!ltE=T9iQwuTkW$raKp~2edHZfVXT2$XodcvjWN>4z~b4eqU8g&4LJwVQo@V
z_!~w82xJ#BE8xC^j{yugRt>{14RwI%i<UtQuJj4c%1U<LWkf>=cHw$**Z?#R3hF$s
zjDVMHCjaIqSnVi5w&dY%`KN6B7323cQZ2+|G=Nyo=B(tlWo0`6xB<xmm25Slp^2%-
zK)B0-uz`1OVFYgd70r!?!xa7CVpCBTKwxTgH8UG4rlt>&?Mv*Ik$Ib$$7L0OMc79!
zU?&F(2<m0@!HIn3O#f@o0m>&zlsKT7ehkEF<wq014P}%YC<ySF%7hsP07ht#!wSkm
z_pi(hAhE_lfi?4A{s}P};2$VE22hxE8vvc`n<`S)-O13u`~+c!amAl=X#|u;(PGy-
z1-fpJa32M}H_J=|3pRi4Nxco#JtD1Q@3Aa^zS<sjg9qQ7YEu#<YM<)<I5N3J=r5H}
z3Vvgnq=s1rN4mX_BxVcNor|8nYdaTfa_BBO#f_rw$3dg#?)t#sd+Vn!C<FXQ6*OPA
zr6>EImpt;Uy_|TV9l*Mu|8K_bR&6cwkEx1+0F-9f_`%O@!^3NT)b?a+KnQJWRmD?G
zn2+41d@MRhW?chve$GcfDDihTut@ulg!sYTcHu{fdvnCd<7`dbSI}QKlI%NM9Ge{j
zdBe{_&!NC%_nG`313OmBwV~(}!P-5cJ)xpgM%o^K)zigZS%L=P-#qg!-6DA7V5csu
zSAT`j{fT~Q)>JpUtl~<|xIj*i*^bek&v3cVQv3RcKom)wr1cN7dUc=;n6Okne`(KD
zw`A9}<3a+^`{8XmKycn!8qEL=gyxlTy^Y>e1{^p5qVch4Ib=2lI5COi<-mB2f(!JX
zd||cp@XN_)Hh+}zY=ea|76GzaM^J_v`6Fbol$1p+_cApKX0W*=5xb<ouG$Y!1#~Z`
zQ7XZz#WPjm(SXM~1h1+HMD2zhG^^Lx$gH>`0MV624D9hy+SqB)DV#>S5;x-@U)W>9
z8w#sgH86$=SaAm%X-wm=`6#RD`wW46URhCOzW`BQ-%eJBK$&z202WXhgv0?QVWKS*
z$mkcq!NjH=t1EX0?yEpEsQLLIphE%R*&T`0lqQH=PG7nN8vyAuP}9`?p=tFGl270Z
z>_}BO<y%}JRv@r?gqRkJmL&Slmefc&;L(ec0Z}sz68!~+>!Msay_}3Ne!u~m0mB0(
zw+Pprw810b4qgqK5DiA2Q8_S`Rk*US$znmUUHmzkCjt)m9ax#uE?Ep?l}cRZupvRb
z|3HzY)e{?4#@_wJ;ea{P<=F4{0Tn>7UgJ(SZM>>`sFOmzvYPVhbKYLdqb{PHb_|6#
zr)8^a!)t9p28RgWg%4+`Zx+N>WUV-qibC+#Che&$LZzh32Id!hkn2%tyquV5RQEL^
zzJ+NHH@n>Z=9OBR)t1woi`+TAuk-97>FA^9%&+=F>$;$Qj`ieq__I7aoE=XX#rYRI
zIB$q5`;jqi>9a3CS>~-=QhKB!&|;T_B~B;Be3c%H4LTdSFFCUxz-ncp$oj@(DExm3
zSgGYsJn3M4x{0z|E>)@T`qN+Q?em@h4Ab&)E&gI-(#aQ-+Wq~s(wAkC7WC+SV!6GQ
za8p|S3OmM4qkQ$@))&f7nCjlx$3_(SlKN|yP!j6?BE!P(!`5ymaGSp#b5T7u@stSJ
z+w1;R)>-`vb-(4uu=xXdMf2gwz4{<M!N)rFHdca1t;_#9F_aJ9b@X=-U2uJHA(E8!
zH$7ks<tD2=6p)OVxchLf#W>HxJ?IO~7RG4yoUb+iSG!{B;YT5Z$1fOIBePPdBoY0Y
zRH3BU*VGISsHcj`;G%PuWAf%GL?_-uf>D>FgGWSBMYSDO*lo9zc~+9o{G`t~%X^{9
z%0l#d9_c%BUeVSbpmro2E%mc|KKJq9qzqW&U9uss>Gqunc>O>l4^qf}Q{qwN%duuJ
zd%-K#u({+;Hb;Fm3EnN{)9ZzZy5?tMg<sZMV)Ga<oTWp>!4Iqi#rpTik8CjI(Kl|6
zR53Oh#HDih^deOf_xUq=%JNdSlE4b8h4%QTclW5(JxlDB$Y9mNACDwPuL>O{|Je1Q
z*g&7z1Tq4e;rA!WmtLdFB@^xVwjWh4cks@g=RX~gNzFC>`&psTV>eQGey3N<y@Nip
zn}P_iYB{b9UOsl*pGN6)4Srhn<v8P(m{tw0@)}+!Y>SpYt#dO4kP?r^t6-2*!v+Kw
zQRqbm*V#D5Qb00QhrxMG1939$Xkb8}*mwb|^^Oz8v3eq?+KjEA8rh9ZF&KaULi3X#
zzx=%FOUl7+{u6<7(-L@#o=E(!ZR*Aoy^R+iuAua?kbA$}Uj9mXw)(+4T=JIc5N$a{
zXX)D|pc;<IA?uwf#YoHz6@Qi#b3|)L_=K{@J57|@JlD04^1uWs51OSVTj8-JM<3D+
z)iw*|?eFh=+mLU5s9bj66EGO!nqN#juuG4@k5ny_=hTIOI~(*6M@j%+()4%cFF`Xb
zbUfw+Lb_bGx8K=39ITcZ$YL1ne{^J%?!UfU;Zat(Da5<gchayTJ$$L7{AK)ooo{1!
z0o)1+&({qzQ<04KdOtOC8&r4Q65c^0SK&QNpI`ZKdQA%9U0ob28);l}b6&lM4T%<E
zKd;g(>~oOFe5*PJf1@-gk?F%RJ7pCN3>~iLFceVeU$fD`g!N3O^?Q>-m93rXCVa8_
zyCLhxR?;>RZi9vU-y~OmF#Q?*N5A+#S;F9(&(+~GFj>91jC0k6?c>z2Y10OUwrti{
ze<WqQniKv7PQ!05cH6W&(t;)CKUV#}rU6+~0`EI9dxAYPIf=;L6q%C)r$Tej{fQ?p
z(j8vrg3qgMkuR-heumtR46ibAxBBKkRP`9pnBwitUblQ}mtcBh`oQ(~qtuV|a+#U>
z<7!3E)3w<7BeMmUzHknKE(U{z(J$Ts2R4`QPb)Yi?Cz69((f3Z1Yhrp0T?ysOhLT~
z&B7K}*S8jkx7A<xG5$m`|K3B_ds0cz@sWQfL?9VD1HrZD<BLLg>pvDvAP7;wgcI3=
zN&cA)|6xeqPs5Azs6~c8DSCTrQ#hA7`g*v!J{LbNX^?y)ta!sCeCc~$`BjLCZeMJe
z>`fg)?U*JzN^^m@x&6iwFd0(KL)KWIfD?HB`o6&Kn$exfB8ta~MLTu7^^OxtFGZLN
zpEf9dDV}V_^!V&-_e*q3vkr;bI6W+1Q6|Vu$1lVe?eUHuj<D8r#*c-Q9Y4)}dOxIb
zxQU)$hvN1pD}Czw{stzQf(b6U&aooeu=c0Tk0C;}s%n99^ZuD*VdEjrSk+bH@wi{-
zENiUY6hU18kL0xc7?N&Ly1Y7ZuL^wR-1bY(x?0I)r**n;_;-5p%-8#p{|3XIc#pmO
zR}d`{ql!Y09>e^NTc+50zjA54)vx_QDp5xI7D}y5_VxXgL2_h^YhSB3#^OyVP=e$O
zNb}YusAkumt@r#o&0({}x+jrH=fO(q_6}<GVN}s=uGnYpe)XH-s#+S+*TxW&5GKrb
zu$-xd<(uehU%VxW8j>UsM_&w0aJ>w!;5ulyX);_%T{RAhyL>hGq22*4p0;>qT)^|5
zq6ucaS+gtSzqCTtlOI9pXl5M<zj$jEcu_+rA`pAfUqUTaVrn%f=}X2C@}L86dN4J5
zq~Qk!(Q1<TrEcc)FV*et8n18LW6IB42jo4xvwpeNx1+y2#1@wAux$IebDKC+xE}r7
z&=oE55mU^R`f+~^eUl^*TNCQ`^HBGMG5ElOIYxwYd;LW4ZE_VKhT9P_@M<mVPiRkm
z_G2{3kr7%ckMy$3sNRli<)c{3_GWo=ol4D@*7lMSuU6fqB;$tngRVM%zWYe`v)00%
z^~-DQ>ps%CGZwA><u~SmpH5Tq*`6TNmZ|Oj56mM!Mp56jn(Y*hg#PM-QM-1Sz^P|M
z^Wdd<P|b|A#zlI61@ULm$W|L%@Cbg0Rsy~Vldh?uJW^hWhGxJ1{fEAWeD21%yvdJT
zxri2GHP{x!Ed{l5(umZM45}_mqaWVa?ubXR{wv&L<Pm1HqTwf;{M%f8j(Ouu%e){&
zeOzo{>fy4~C&tHz(PEm1OHR>$Zf;x?>#xr^%bO|~{eD)@#dm@}W#DM1pVkPKZc73G
z3_4M-3;p$cBhX(@wL4+f^hG6c*`#scvU}rvD-2NGSVD8F{eiaT$xe@`0JQ<NDv`XK
z*WF4%HH@*FI7$tpQpuZB-W5?^u6-9=w3fZS+~cEGrO`_lC(foPHSy@<ldg_;Qaqur
z+Bo%KZmT~M>yGGMBn_*;94^VTnL8ZY&fg%FE~}G*w@(cp`1;T-izDBnl3KFEKadxX
zoBZRIZZP=Wb3X`0$<wSRs;{dj!IA@>5UzY4<eFU|)(;AhunVXXDGg09Rhl-<zP(s5
zyO-}eL-#$U47_jdUDI;+lTty!T)XF;<mwGqN1=D?^GuM#N1^m}rxK?uTR~FXzw7Y1
zLlkM^D+VNenBHKDP#<G|M8Y#r)fbmuH-jL`VO9B#&HRT0NdI&bGlGP}LcwRoA|#dB
zWMQ(RqeE`4qa)O*m?w;m<UO3<_rF8EN6&7su9W+Mk9dgn)iBR*;wS%Z6+0LReeliH
zeJ(uxFEA5v=a_pU^H#OZ-nGFqV=aJ*hyXQ#Sh;W1)#B--?#$Q^`|vC~dVltdjAuQP
zFI7OWQh%r;e?0eV-2>U)THSrCPO|9)V)dP-p+etKFE5gL>B+T<F6pc^dhN=fP5-O;
zad^+Xy%hJ_hd0YlyVAk}s#qCC`|Zvo3Njod%Q}MjcJM2+*xP}~bNgB?!rRH=;NBPQ
zoe3&p9sTFk+lp{jN7>gwtg>^Z+u0)?h$(VXTN+r{T#Z&5#PqJIt<9h3$c|CG9uh}p
z6g7@F7;WML_v+^%s8=K6HO-c&RSK09sw$d!w&T~CN00~qfjWkN*G{j{Ur#}L3(Bg*
zTU+KH<*48P8iSPDtiT?5+@IKZw{(BoQN&`?@ItOQD|Hz0Z6;9a{X3Q16wEXVU;YLa
zl=jw0xcm7nzx@w>?pCv7SL$-*6#{*$uNf<nM<63!GtxG<ABe<TjWW3mn9zKmF|O8M
zrkMP58v|i}H&?*`@V8%O+)HhwEldXM0PT)vn$V9Y^$OYSRoD=szBIsHP0|0{I&ILr
zGT`_V@tMj+wxeF#?e8qK@)#gqw?sQYD|vhFH7aYouxLnv9<WCD_?6c(d%wBi(dZ84
zhV^5(RsFu*!9fE5hMR<se-CFwX%v7+wHFKa6d?0k3U(^jNuacl+uFqWTb-y{X>mP{
z)IWKfUDdXgB5x*5%#_`SA|L<z)+ySD8+oa`&{659G0K~s&&}AkufrX)NWVW@@t)1t
zzui{`C4Pp+7hA}h#@_3wbVkWw{~1U76&LD?kJNuLF}xuR^JE|ESXmGIE7a6;-2?4_
zF<?Rgi$*VZ<}<y8)<*;hCRy?e7ZN$FJ=ozcs7Q-rj9DGGwCvm;T<fbg0r&S!?SZ~N
zd#sK=okZ)4b-SlZp%u@Lhj)ZTxO&_kls)k9$YQMx);-o4%3-vWuoWLGQmk_|-hNjK
zll>$A&3f*$0ecNHyL{t_8h)cqyFKvWtLI=oYTe-q*=*tYikz0nz7DQH$204>WK(8E
z;!!dAxjQ?A(50p>{cx$Slf^;eVQ73R(zbU#IfMHV^~e-s{jByeeNojEYhA1|`x?ht
ztqC`u;{;@)OHe@^jPkMl5@%-LnP{N>gkztBJw?i8UnSAk_5WLh(?hnNVregQv<ybX
z@1;8Ec=0uz@^%!NRtKQBuTyR(g(#FVCjyEd>WNtPSOuhiV$<>WOO~{nEyBq?g=wu9
zboS2O*^)J@Y;#|Z0$_&gAL1A4%eHn>gZFKI-kR`E18e1y#{Z><|F@5-9iq=0k;g`e
zj5HMJG{1qt?S7I({7)o{lc}~XojK(e%<6@PBlf)^MQuz1VOJFU_avtl<JTHI$@IQ+
zf%ReR1nvxULK0}P%*F5%1;IRjHVnIMNx?)owYS;a*+5e=xzz?$&8IImiG<CTrS1A1
z5}!jPb-QK)UwC+P8QXWKH9QlyiP7QCVceK-6(%l42o%KpFMZYF=1j!Mqy?7HzPpX^
z;5=5jY$#g!!{(lrg9+ms<d-YHznURho}IX<Ff4)db8H$6Zz<eNl{n<Wv1RF3BE(R?
zkV77_bCRq|)m;<_-<X0(h?Z@V)m&qN@$)}(>4A0Jo#-}U-_+mbatPN0-7`#j+?|V3
zWR?*KhL3D<f##JE-vDyNztjS^@Mx;b5(?T%3?TMHh-usc9jN#rfGW@HiU*2-KpvI{
zNDXBR0tWfF5MCi=fgp9-Ye>nQ?e<J}x!64yV0-EY`vzecDIvXoQGr7}TY^cW`Jlv!
z_jKfnvhr^6;_CKiWqb(Tq86}9pOLD+hDO0O;r~<zgRFqnQe!6*3RqZx_F!mv1u`<L
zV|0HI+!z353)83F&^S`0nN)$~UZQsaEfZH}vab@b?Jhej@sl;Ax-poZCcM~5MuubA
zvH(n5QI<jS8JYw5++|6?t}6>l48Z8+O%P@wbQ7XMvNL!Tfa_Bv@e%MJE@#!V&~^lB
z$gvvx8pCenCCBPusRJ#PZVN!+Ck3PwtW`Jqfbv2h+&=m)!fHm5R6$dkFI^FRr2PzV
zKXl?C?Dc?b9burc76*tPSzTH2)Q?p_j62EGVTKNb(F}MEEhKP-1CA)lV2~H6ECM-a
zme>9uQ6vPA!SlnE1{nt*1LguUF(73VSL4wqEO3BC|1-9an*cEZd`Add7O3zqUayzs
zuWJQJ4;XNV0c&3J36U_e|GD4ym)~XH0$z7e#{@VIiy#)I;D?|M2}psFEQ>)~Ch!_l
zVL*;4Yq%LrGndCSNXqJ~_6i71EcAx53V@#`j345%7EPrug&u{8EB>z-$MC;ZK5uAA
zz)oSGEEb`S5XYvOzr>JYGh2bmMY$M(bV<NApr!|mnWYFgAEdLy9snYuC*dj}rjY|x
zU!_6TUZ8-g>N~*;_+NXgC8@B^$;>3O9EM<Z8Q?^tEcU?SpldBI*xbZJG!U*5ld=Lp
zPLvhO8`h-iO5i)JNsfaWsgp#rs`^m#S-dO<v45ROM$yWzwY&z3athgxMI&2^aS$3H
zk7Tznz{bJ>e;&XQg%kkUuY!dQH7}f+fncd@AydwfjTpp_*TQB(!I_FQfFzDjQyf8T
z_l-5GkT+ycT%$<V@UAQ4uhV^1cxV5<sv_edKYe1VuIpq3KE8_NZS*f}oc1J)pE@<{
zG5EB=aQlyaUa_Y3PTF0t>MtY8qO<%a#o@z2-dmQ73UMPX=Unrg2o4WA#9L^02m1a)
z8Z{RClv`uV5B&hablBd2R|>);wOKZ`rE^~H(<BguP3z=?d@aUs$^}4(6Yoo-M=Q2Y
zORyck9{Vn&wdwFm@n({|MSjLrLN@lbS@CPYNqoM2rjWuH73Sryy9bNRBJ)Fq@X60J
zO5GSW3%v35FiaTT*FjG~iIc?lHGY75p)3g5z!Fjyl)eBUyx~0pqCpz|iu*v~Z4)~e
z`{jdHk)Y^Y=g2OQ{ox>;Tg$n6<-EEuJm@4mMpt^vEfeKd<Zh<HG2%y};$&LM)#)4m
z^+@<cA>j6M2|n)W_eIE)^FL7ZX4lpwXqos~I14+*FCy?l@`7wfe%Lp;<#F*#&6pV0
z6B#oD->)J_N}BVp+P>W2xVYu6syUq5lLBc~U@U*LyMHz7r)HxA+H4bNEtn~ojml<1
zgOdh91%VYfsf#k0>@0!5(t6+~ike9puShc`jXnULdfZzB-k{A)Y2a;T0#4jCN)!Pk
zuS|{^WVDv4kisE%ilDUhRiq)^SC<JcgYol0scb5HSpgF^DF-0g*hwoApmj4)1P=BD
z=Xpu$yG)j|eU$<J9pqoUc!4iMJX#>SWDCJhiU)e1ilmCvypb)zTNqZD0B~*8du8ZS
za#?;hvJ=fv;ICAH>wWA$1h)c91OH(a8d{mQZh#Y2&hVb9E4!xcW4H{nZq~=b-40R%
z1UX4s(JJuxh=Jfs<vDtihJP}OS=)EEmjl8q>#t5DW4Luv!7<2K5+P$SU6hL^ymz2=
z3rUDMQXCweAT74gv^k^FJ?nLa6a%6Wo2<kJH?r-`)IQ*nd4s*D)y)K4*^2zH3_+0C
ztbfkPvTBxTF%r0*gA$9wLd+QiRBI<b`l+DkT<$)0xS$aXBZiZW*v!+#tfV0ZQ+Z-u
zN&-eNO(hwe2k=W|u(ybdL{#aQm{}2N>QOB0O_c>`KW+hO%)rXlvFFpD6;5Tc`%2HB
ziLo=6VB|qZoxiKbX4z9TO=0*>&Ic8L)|5}F66OU@)|$X2n0$q#n-)dz6Tr;o9d~1v
z2c?q12qYy+17G=zwAJF3buN{T`=`Il%WYSf$}xto?OwW4Lc{wn<&(T1ubTe_{OryH
ztpVqXg)~p}%~Nky*Bsw?pn-&QR+R8lpxbR<P=7vC#r<C5)MC%O=RT`!x~XTYDo>48
zJIfa4ep+hKr?=YTD!x>EwDlnpV<8{;=}O-{CB0cJrnYxBRZYJrTKg1Jt5q}Q&y3Fe
zP;<7r@DBX}`>W;64z|q4xWFZ5p>--=A71-}V>S8DVy^ksyPF|)F3GW=(R$>UO{brj
z#@NF<ICcT$Tl@+g*7C}r0m8)L1Y}6GuV1t9+bYN;YF|}WUc0pmHU3EkTV52&P1pZ3
zkV$}5?Wi!`3vs%*#l(F_l?1%4Rc^P7^0kR$YeHK^jBb(Cz4_(EAb4E-YPMra{3#X`
zT>T(|SXnqJ&8d^^9N$nj@E<5ZWZf<6Bl|Or2k@93!*9_`bde;rErjA}C1#~l8zuYE
zDd+T=!5c0FxsCt_^-7<*zzjw8+JR4M(74zXx#o<pRP~`HHf{A1zKi{hE)EUBA-btd
z?=~E9r}QqlKq+v-{!-~gX+vi7zR4zqPhAh`N}UIy*C}=%b2eu1nvjt*4!IY1U_XD{
zWq(x3fgH+C$SY$j=F-i}&Qmt4xQe*MBUYaXjd0A1Jj%a!yGJ9verl7wv8ti_?xmE}
zb<8;g;bQIKqkdNJ^0GB({?$ZuH7V{4`tIN3_LO}13(z4(i>*UKw%quQlott2NJ(bw
z+*Yo8679q`GLf&Lx_(Nh#YD8zif)wqQ?I)fT;A63H&yx~y}6~8lAygp8Ve43$X)%~
zUKB?B|Il@oVNL#z+a4W~3QBhk6iKBSD&5_PfH0adKtf7HWRC8hj3G5bS|p{Lk<yI=
z0g(>*KKJkc{&~US8xI-m-tBgMuIoIt=SwXY@4xqE^44l#G9Y<m`Nl$~bKs;(Zc3`S
z{+(v}uEp_m)SD{JcGmqxbMZ>6thyMB)CU0d!T0_*Kz+cIqmBEe(Ip2=g@e5k;EL19
zie1t0S$2{4;}uRHh|W?CxlT?h&oy<^%f~|~LG6umCcde0+R96e(yG2K*u@Y7QmO3T
zcw4mVgl#Yqm@5=gi(ab4p#%DCj&0(riaHb)VpLMjV=F{Ln1_e>^QNjd3Q~_QjfloK
z|Fow3Elu#3DeL=Tqz0!R{&dAMJI>-Vx$!_EC^>TIYNlaAhvo&4oe#e)?}hyg*u3@I
zDBJtPrf^4y?7C^=xDs<~D$u+)#^{=!Qg=76$bUV8H=&nALbSpb*2x7kTRozQ3qVy<
z6dYnyys^K|cO3NZZ%pVBl;4G>zkyW0P<l@(N|ZhJyxnu~=-%zAY11F<cSM%}h$C+o
z{8ofuEY+6joD_ZgV+!lY={&^;;vjNb2R5r^njV8098`{R?*XZ-)<{8D1}q^h{AhB-
zn_1zxM^Mshl}Rw5W1`zl5*3x&-<Z}vDe*&%IL4NI%T1l<Uktn?7p$@R@(79N){Wt<
zbRWOhJ!2$h{YhPo7cJoC)G{He_MGRR8ujxZmB?io{G&11*h&w+V>$`PDmIqo>b4Kp
zAg=fgcG{y*kupzSy*&NoiJRpQwO((9FpV91tTZN9rq6QMs>{s3n7Y*q^CYjxts(-d
zidoC0|2m7O%MLaO_g7ExLXr!c*}M&B3hV2dB_;Hpa4U-jVfo^<GwH3|&5&5ewb$&%
z(48a9?bJ*PkGAJ^_&jLV#;;oaE*x*zkh-R6M5E{~U?ux_e_-81-@85`xSi~yM-IWQ
zQD|W4V<!#11>q9I&i<0mb&YM1J+H5&2P7Ip_&4rgR%e}%>H0`^U-1hw`iV758eIPf
zUh`l65$%$VM9N|#L&Rc;cgDfdzNy^^Q!WxQCh2A%M&4z(oUVQSYfAFj%U|F~kDsD)
zVg5uvUA{0f1n<Zs-zS@*TE`ZbdkS%Og_5Hvb)7dE7u~XIvIY76D$6ZtzDhaJ=G-wN
zXPo6F4o29+-z{mg<7Y~jeo)@D87O@>H|1|KJ{Hh-i~e1hai|6$BFOj!Qm8KM%gBm_
zi`qDewkhFr&MnU|m15<Q`vxQSj&{IV^xEr*ya$_03Beft)c!C7lYcPVqXz%|?9V}7
zf9V_O!oR~2MIBq%ww1Gw>#S$uoy@D|7(544WBf?5-%t}t>)t)RTK&520NU13b*;lk
z8Lz*_&lPUgS=J!cU24oJ<!H6+uZuDD>0(IaoD>i5eaa14;KRCS+rB>crLfEcPfhMi
z@*)ZTZ89s=(BJFnU$NqiUW#s|L}XIkmJQ4*#yUz`Rc?X3!a)fKznJxo@;u)Nl1UqW
z?O{4CpG-b;DJd%<o#u&<vNxjRsMC=!ua^Top|p(AdJbM*D2mj4)q-m(c+i-F(QNWT
zW&if)bL7+cLiV}Ryw~79?zLi=U3;{cddi}hN66czvI^ub85!B<LQTryU*X>azd*G0
z9<ZetjJ}8dTzHM%*)q^qsvA0wg9CnqoqBDUuV*S)MrLo{0^aZBqd7KHtIA@i#?l>)
z&yBKtb5`_>IqclfmOZX*f#G?Cb(M5h+2g~HMA1y^*$xt`&Vi)Asasu#JKnYabDOTO
zxqcYq#gx1Hrpy=3#mqKcXmx*n#}!&|knP_|Ie0PFR2H@E5LnuHfE1xxFG(@A2+d-n
z(KUJ15PGqCR!%qg$)kK_CR0TgMLK_bu*0_2T>eIg-Ir|m`?P?wnL05Qn?wCQ_sB6r
z$b?~vpQxg{uz15Wf)3I~@ed1gN7;kPVi{h|%zGCGnY60?J4jr#&?1|2QQVuymBP<*
z(DJHcQoo(<b$*cLt#_Yq`}Kr&ZM`|?Df!PaUaa2}-&fVLX4}nfB9a!n72fl|#+NNF
zqsQsw5o`X;arHwbtPO1R*5<SDg{KDsugB~~a<jpFk9n!mWo64^JEfhqJ-;lwJsDA;
z_xU0#nBB@aeTL?-^nUH{!FGiB^t`3*gHbFGxt=e1Wz6&RCGUb@wMCz$W2+*Sl#tKi
z&M5a{8jJItY}~jgA%%U~A}>u|oawALNpGd`umHb-PY9>hNOQA84lf^Y?3+`=zi%R#
z#r-@H8zGXPbB+w$gqg8y6~4^fEU=1xZO)g*Hmg*+NZHS#BpD$L79ZHv6CNtz%H3qC
z#N2(}{u%qg2mD=6&(vZ&$@6s>qQfj#;%|UMarC*eASmF=J`2%ZZTI)PaS6uSgth$-
zE@y7$prepic$<F%3zBq{$K$4IZ-2<S^OSqnL<q^7+{OPHI##n#wlO~W1b-BfRKWj1
z&($eqFg)Y9;@>8(tb<tdqB!0RP3SxywS7~XA?fsP0C|2|ys*eKaEMpK+T5YeRKxkY
z35wDfthKuGaX2*#X6N%gqs-S6hE$x>FzhfhR(+|P`STFl|0=mYiD#edDHn(COZQrD
zH$){fty_IHbz7dG<KI=6cE&Ujl2;?zkNR@q$Pg16$!vSg?{X0%xI9)aFS+T5X<uUH
z{k}NFfg}dI{|IY7ej!{YdtR2f7;WPeCe7bHQ)}&MLa1W2<|Cl1VoMr$HL3eU_LSo^
z_p8u)RpIR~89<`QN}lD#PDZIJ5mF&&=i0wJXwF<Fv9Oqv_u+}DSG+o-&#aG>r>Nun
zo719e&BQIG12^Q1QOAmGzhaN3>pg7&`gS>fT`sA(A3dCz-#7A#zlC~s=d-K-21)mS
zrI3hGS~WK>;ZkBURTLwW{+Z!wGFsfn^dD$2Cjl!$l(Ha|c3LB=dH~meO)_v0-25u$
z{((5WWmJ-my(W}Q=;OpS(QLOQME?!%zFiG2n|<>5LI+pS9b&PkJyENnKO9y^Kl1i+
zCMc#y<6P4N*5swQH|zv&u1!fAklqbv*jTJiE;{Z!k&)h#2t8iG+a1taX>64I+m>oj
zSHRs3OO4@4%$<EjkU#Y$e`>idRDPUb+%VUGR25K5l8A=(2uK7QzM}>SDID1%ZjXOZ
z()v|O2hYBOY6k*X*_P!dSoxwfra2lje2=>Z`B%hBb1ekE1)_oVz>}U#cWquxU%Q_D
zsOdkeO72x({w7B{!1G}(URT%C?~xO0|7%56RVn($krshc8(uVFM3T*sIXxy+!JONQ
zzpvG{*1_}s)367q3hSVN2+k<0C#6ABUGjmSLJ-9{69h%C($^SyJzP+gdmRld>FLay
zunz~aH+zvyll9ht=V{QI-cXT-KQ^<4b2&NK&Op$WS*qi}<3Jb3kn+~#x|E^!r#-%Q
zTt}X}R_R|`K>5BRM(ff?<nFIG9DN}tMYkh$HEBHA{RvmD^DSO;9H9?lrL*$VH95C8
zYXT~Bo*j{ljNIHee{fC)Cy3DB(w&uV6~?W3;)d@l2fgzl!+Hiv>^*PEGNNZ{8eMDl
zv8tW7PES_kSt1Vj6`2)bSK;gC<^|%S^!K|Dn7)W89ev|2Ch@IsNY-)8r%CUR-uKuZ
z4#O|Q<9y+v2O?jOx=4U%@8xOxFy)3zzlW(loZKUrwzH9_$M~`S;>M+U>wh4|x7U9{
z&n^aH&I=X8Y5!EA+7TF*ZY!a}cU?fTN%;TyqA|A<;f$?o=3@rP#*)_RhT&2?^BNo1
zgKEOX^@O^iPA`%7qRck}M9at6oHG}`iTlepbH1ERvQHK;^Jp*W<N4+`(i$%w;@17P
z=Rz8znf55rP?dr1|MX>1heo(?c2FQ^uQrUPO`wmKN!iBb#(l83*GFW&?Fr<5h~?R7
zY^1W*k*gZh4q5hD_2|jO&WM!`LcBLTPiFESR(`n!UGs?wp6#>&)*n-#^!OpZUHbcu
zFGh)XL|qSg^P?VqD((Jkj?MU+5zSQnSFu;wLZh^9;0TW3iG;2QMJNgc<a8G}zrx5n
zv-Rv(IM|*#*A<{cP0fXC7r-@F0LSl|x|S9I3<M-?R(b$O6(o-#-uY9!{lDhYXb@0g
z8y*k7Hn`7O5d3WUWY9+du)gG{x<vK}Ku5{k-rS+2P^>Aik}SBb2LvV&Hn5o##b1Z&
zYY<?{if$EvZY)PsH(&jOjtB_-1ENR3*h<S2L39h#zBFQy)BzO$I#JXYBF#O(k-{X?
zD}?@oB1EoE0ANl~=9LjZ;5^y~+?!2gc2mG~wFg9&w8BuA#SR7lmwI*ZeCR5Wg@JMn
zN5ujQkwBP$5ePO^4+aU{`n8>KkOe~o1!q!EQ71szj~y&C!nq^mkV*20pS=a>Bg53h
zzyzllsR((T;}K?WCWUz)LP^HJ(N;&G7S>cupi;CQ1$6t6Ax4f2A-JnIDB^X5VvRcR
zxB~F1?4eMgmZ_qh?@ECI(hcPdtbh<ZSRE+)$)2Dw+?ag`2`LhoX3J$OvnaLd0s)<*
zmM$@F0}HSkv&n+V2ha>4BNwSwp$)*h452u|a0bK|SW)zdQ9hr^5I}Ak5Fm}NCgFWr
zcCD911Sde;+$skHJUY%PfZ35`Oo}59Uzk@g8gY*Yx$0L0gm(FLpor~^b}4^gtxn1i
zg8_;OV1;omMWMa;se-{&e-tr$$hh(VT9%;|;0)Gt0h>-a$@nQsQf7guPRu|rScuLL
zAS(5cMmzxWmp(UrEYS_n1T{LwrA#8^fLt&S1iUxSq|jbYNl}yC*8nWaBkUtYRLAP!
zN9fZc;8)LPbZtbV%W(p7jt3B=iX|JZgb#qMO(5fP0w}ZXFaSQ8)k(VV=X=>&GQf4B
z2(ZsCjNw|!qX7DH`JJoWKj<0olX0B5OlCjt5!6ei0(=TGKzs|dMpYjNdr>G*3f-Y0
z6U2bFb0z`PCW`E?xCZpr#Bcpmg#V#-|5?$VMz8@<^9jnYcsuIC(1(4pm7jQZ(pSF~
z@EVN}Pr@~mG#<)Jy+57@(k%f^AXZ1{;JgS^WY19#<&~q^fhs75cmftrCJ?2=4px0|
zhhPtf+)m-tbCn1z+^GJ2jSGb;y3&NzRo;If(?g7N$xZ4JkUhh|<^p_!CvNa9U*(PN
z-Kv6=6~VN@kRY@VmjU4pPr{zsA?B$}5n!mHbY(Mgj!=C-pzj9S(-mZ+v|R=s`+uOd
zKF+wuIP|ij&`OVdbgasHhH~CBj?`u;8#DgV!0n6xH?|Zlg1#9b9ewi_=bT9<^&M%z
z{d1$9wO!a#NcNn8BzlB-3?mR&G#X6f3i^#ZQ^dbNMN8Q@#%`x5x>BH(>MDskd9!ho
zFYiU45+7OSdg0Aaw!7Ouh!ouWlZ{)%k6l%(s^s2FF{&D&<w&Dh{_$6Oi~Tw0w%X~w
zP50$Jna*8(>1hw5Dh0nvfX~SDYjeAmjjv92x3CSaUd1rcL%iOiL!y9tbBg}FuSWa7
z+&6zct}h>$HmP*rHT2}i30EEB|6QPOwi62mKSg{=z!G7ld;<Z%K!IH<8Y9@q8OMB6
z0@}l6C`~P1BWyM*|L5jqK1H7t5oLp53NX!-Y)QNd9=LymO!Na+pS}#r-hWRc;DHP<
zme0hiA59X31_DVx!5Ef{+3Wq01_^tqVhIsO(A!RkAjD`V9{tM|EyG4>5LyBNSyN<t
zh|l-cXhKWwP$~;cW_ufJ=@K#|!Zm^vsfkegr$vXqTtUqpC#Y9G&`}`;zhbd}&>N^i
zh!KYj>iIV~WDl2e%m7%CIA3YWo)+~|69EJJ7>2CNIA+WuV7&s$o|5ws@OglUfjpYU
zYpxWNkVQgBh(pGq8_H`CQe`Xh0l-szI)JiQ<_H1qUlE}&6=tB03|yItFbz%K?3Zs1
z2mlDj|H{`u7Rmbug$$(@YzMfy;gqDnKSQPmmWzj}?A*8#OxD-1D_f<DG-GL|>LenR
zvdYa2`HZNVxad185z8SCC<lpuOl)lCqxq4;Bfc5sQABE+zVFTa(qH(Rli^yL^SdAn
z<cOr%`d4oEk5EhZDNiY7JHEhj&wnn)8#th$@*WB^$u`dxQwr=|*VbP55k_Wi6D4Fi
zr2JkLb$9>$r@u+({sG*ewNi$ts#VNcCDK}f6Bya&qoq-2Ut^Wl7WA#1UmfBRpx!6;
zq2NEAn<Kd{30l)n685f)?S4)Np{S1Uc=5q6OwxA;w~JnJc?j*y<Pt|#FTsr_s4VY8
z78>%}>KP~eRh<S-Ps?f8!@QbLOX=^gPrVbnElm4>6lhL;I^3NQoakm$NvZ*m0kI5h
z;;#-3S~L0fc}WX|AErNY(}=YF4PQ~1NvryFxWBSF_1g4=uzDnEp@XR;dp!PWn29g<
z;^FUGez$5m>X}pag(&N@@cUIJ1P`IN6)%Y{%@aPEEhYMdMw2de4vhURISX@aK1^S^
zU$Mz$vmm$gxuX+n(Z=;_R->PZxBAzj`N*x`Q5BiOIV0EiJO;3VS}?)Y#Nar4<0olw
zl|NcKaoDAl?WCfq>Tq^DaP#%~deNVK{CE3gw6~oY3>iG@NrHrYV7vA#^@To!O)M_8
zjq~s)IEaaS`_uTry9yLiK|Ur_ej`mX@|8Su;}2t=>qhw!<r?-psPu+=AzKU6=h*h`
zkAlQ!R$-(aUH))WL%u!s2hsQ~quSW|_9lmaO5-;=_ke|Uy98Md-|yl35{bgiNl#=g
z74DT-*D|@tP)}rJr#v4&717lc2ugoy9DUBIb%;885*yfp+ve^IV03<2ZPRVZr*k$B
z(;?P8Oy~OIPQSvy{tOZxL<5_R7m1ve#+vI)4O$Ia(RWfOlbFWz1y{VF*q`o|``=lG
z2d$>{p4YFz@TGDQxF^@T0mX0ku}5v(9UY;C3$DLZK;c&Hv~f~k3(~>-O&Vo6Q8Kqb
z6=g848)}nK(Pxwu5ml|PRm$;_35zz71qYK`)7%XS!AmtauF=s=6P3MI(l5Vg)fOv`
zlzC)JUIbKzg>!^v4W=$j4uIIg>ZKdItts?oV<WG^qq*mP-}mXtf{BUK_xPp+ZZ9bF
zfu^4v_0;aX<#HSkkEVzLha1(oms_F@o<4<JvgqYK%0Cig9;?!ts+p}T|JPJ7=qy99
zz${%Zka|v$S@irco5W!>K|+eaxZW))duLy2Z|KoTqtDqo_S3-R;R_gq#h0yj<+)ub
z7QZu^y~@S^?P&hnm+7P^ZlfZ90iZK`eD3*n6Fx#HLw>T;QZO9lcQ<|`%I@=8i5<J5
z;ZiKy+dk=GtDn;8Z`xM%)PfPae)6fWh1dbZpQN`pBgs%EcMynEXvBg{0rBpH$W<T&
zX}}v_&}Y~wuK9Z|l*D@S`^&;zB+oK$;!({kY4b?%bm98}ipAmEtg9&&yZEpA)ZGZ8
zawoWk3%a4eQ;w*{Cuq}D_N}~&$bIp@YBDlddHw}=ro)B``h3@q+b_E&XdIF?jwWef
zmnPIjd-n&!#)9?8j^O{?ycz9Y&VNiFw12;oENK&Ylwa@28#KVM!MuSqAk*<z^c{IO
z=9S|3*;E17xqh*gsp9`-gsr6^m%6L!BHa3uO)bqm_y0h5uQ;{RL&(z)hskpi-oiC&
z3Jr!N$PyylqNn#34o#W4{IEQPj`ga1VDT;AP?$ykG@I$7ps8r3<xAywclRHA)bB}W
zY$W61h}v)$hCrZG$xQaS<Y9$wcfLJv#+V#ej38qcF=&mhJ?Wb6j(rxb*i-~HZ7uyc
zBKNG8I$j-@eWlZ?LR$Ad-7Zc$*5pj&6h-5;-Lppa){^k+W__Kg3Cc_nX8Qyk#$zLH
z`lv&o`KPDd`l_6)0qrpG7PLw<J-!)XZV<|n&i>>dQ;@lQ`*JwmR_A_zueE@Q%WNyJ
zt53nV?qKH#*=BRoNZ+y6U{8kW>79>h=_7MAtL8d>c-UW{?^GB9PHHw7!mGa9eqps#
zF2EvayuwrQXg{y(H6JKsa(l9IEB~hkdjO)hd2*Hb)sufRDC)EivgSg+!dV=DzS8z2
zt-;nEx12wq<pc;DaaJ#;xmk_i07nK2^z5L66jQ%D87F(&o9(E5!9jlKq_VG!mJ90y
znr0sEt8{(ah(sFGPpEj*l5S*I&fs4B4yMIAS_h`zE)t05;=&u!P;ElBIfNQcp#MOV
z65x;14FL-ydi#IR%br{nXLoq!iXI-)3GXp&>JA9YoJkQd_(q#ipX);YzEG#Wm@X+a
zw^KDK(0}pphd^d5R<_)z(y=VP;4$YYw%@0Yz)p3frVJtW>7QHBP9Q4aP7?vH<k8gt
z%NF^K5Ru#B)&quGC&ze6L(7yc<aDf_i4m*NOWJg$;^ub7zHQgL$hW;pBE@ane2S43
zd1eb^k%{Neqjcz3-wYc4PS^dS0CaXPKVOHK#W#B#*?4)-StI?~-Ie&{HTDn#dE~Zs
z2FoUSGJVo|wE57#6h=YiGz!;d2?-fVCaazaW0cg~c?MZ(_W;-QlXXMIANxD(usxIF
zW&w$yva?wpG0nb8AtH1w#hFhG^ULh7hiQEIrgmtonlyEJ8rwBX`L^W9_epv^jhhBC
zfh1N~uiMffTU75%nKhwil9~2n%vgE}?WD9Pyd^&-ySv4K$F6zIZ7%YAzu`X<xLy~l
z0FmeIsT)bRc%m3=zBccUm{N=^R$Smwp<vCS(GcV(?E<lX#X`SEs)h_!B!iGKrCKUu
zoV4M=owy>ZNG;&w714)2d0lI9PlKSc*uip|=}^wm1TUaE;2;U#T%!K5<!$w=BHodh
zv&BMERFkZveBO450-}({+zaS25WkvofD8LGLp&?nJ&Q@Q_jE&%D}>*2EN=Rr!D2~O
z$|e_jgfm~;h;8ibTd1k|<M-eNU!%r6QHj`&*TptgOVIOvGu!btHTjv%XRO+9mR06`
zshvjnM=|m*n3d;7JSpbZ-FkIzhP~3J7t(f=>iV~nQV$g3W9Ey$H-rQ==!gLoJ-*K-
z$OI2u3SX&YZR1NXH;oTlT>ixa#|`RXuKhh0gtV)|AhooPg$U{w&-<GV_j~NbDk9i_
zD61HwpCx)M#qhRU$yP{G$(Q?YSE!1V$MqHmN(}!(OPgNWv&OsCIY?#ozsx9bG?4zf
z{6ZVVHmUHt#BjEmVatULTw>)$Y*=xI^H?^O2f1yvl=l<0Z5(RNRLOZMhPrZpHNC#c
zU!Gc=B)q}(mJyY_##=gT2k~8+2<=<Zm&tuqVhWiuw)}|{Q(aUfdExTf9-QW!vi13U
zzXhq;)$|-AeVfX1#pt$0K(15p#4zdG*BB2*!8zkE)k%dCG*8Z?6~8aPc>h&MF-{Zq
z_HXH>4|yL$^Y4x>XZi*v`|HW|EY>Y)KKkx+c^Be?19{V*b={5c`)iu*`bw}~9~?CW
z*!G!7Go6HGnM+yan~C2r5+~p1sn;NuNS?ZpW%DbPCZ62%kuhN^mQdiBR(LG<%-S2H
zOJp5wd$BZ=Cu{pNA+5w-ld8=Iv3ToW1Fv`<<W<9@c6tzEF5AxNJatGSK7coNC$Hff
z9;i8r!kazBcG%;OC1Dpc3ZH}rO_R#@(bCOSU&Rh}Kkj<pJc5xVED-D$oQI_a`&f6m
zJkAxk!_oVdvwL>dOxe*DB#4|@`8gQ)BJO&?NaeipH)}$jnSeE$BxmMH(b$^a+p80X
zvEZwc-@cSVBTPkjEm@f|IyB;U7>j0O_i)xNO+gy0c`wpdKSDs`yH3tW)A>HZS;UXK
zRhk+4@D*h(ihZ4Xyk!li_&xO;I<|iFQB_{8+<}iW&>tFB!yi8iy#BN4+#0^FJ4O3N
zxG1T{jEpS%=u9wZ%<9}n`&^x0|DzXNmx1H^ZE8#ku7&);U(6Us-TVJh073rynpczG
z5Z;CwL<)v0K#2(e<Mm0;;Ze#l?BPETZD7oH)B!9aq~n-T@u-{f1m-_1lZ#u9o>*Lk
zQs2CJ)N)xrO2Y>Lkr9r5A*dGF7N={GqlOwh9cnB5Mtz68Q!xA8V$j?4k(VF--tBbK
znWe7izCS}h%FwSqGB+E#7Du|=EB!6r4EAqyx>MUHx>trh+7lnf^~B7XeK@cy$;vn&
z82R(a3?rDI_~X9e?PbND{8n_p17)qxN@%#0$6qZ{IimUI%k5;#;g1XPurbD>`Z-#|
zKVu)0<r^Zrhd4e5R{lIlKO<m^P4((FCt8~`>RJ{_A*wX-G9DGt?q24%RT^=s^KrT!
zlru{VutJU<JxQ!?<BnSff}wp&E6;|iFC+Kr>`Vs313KWw_!T<UrA6_j`Dl-S>u_7W
z#tM<2pX>fEjV-B3<rWSq5~+QEI&UK>{%?CxnSD=N!Tb|m>FJc8Ekq@d4zd|Kkti~Q
z^_SOPaLNZKmQ($857d=1dc7-L{k=|6)Zsr+TaVyEMNL8d^Mvyriy@P!Dqw!lmi>h~
zgj^|SS8(<u^V`ZZJ;?}PXcGtj(OrRr?sLmNz`1bNQAxA2>2Wpdcy!04aq7GN!-f@~
z__lVf^#kjzf8bUfqni1*{5dXhpEqL67*AdvQC@0y$yIz)j;%P@U~Q<OdVf~+`QeR|
z==<<rcd3{3)--T}rmCvm5{r<pCA>brLQI-a)kV&f(FqU<=tFcl!KpOE<a0JrJ5$p>
zBPfyhjkZI(pT>%cYSqVmuLIn&RHD4!LvfqBeJKB%dtO5vp!KZRr9Um)=!bZ#4Z@@0
z8nmi~wfp{Yawm}_i#j7W^37N(W1wV40{Xu!5*W7s?@#*+1hZgz4-cIASh6WpMB}*>
zta1-MSv+CjHnR=)tVeupQ&UQN%U<$1Mh34#12<_7tY@Wb<nVgUY&_+{^9_dk>dz{3
zz!z`nXxraW+Slq9|1Qb*!l2GjmH7X>LEO7wS87m@cdt84Ak9@^aV-ltw7z9rH3m`i
zgz_GFvESZ17Sm6^+-PJxe!o}$6NbFk6MXUXy7og=?_hbS($qoSxZZA9xZDYMO%&aB
ztSoX|SA?o}MXQD<7Gr!&N#4UH<F>QwKK@PKxVA@J&bZvkVH^!uYS_Uat+eD$(0dS4
zXkjGKy#&~B30S5x6bp#VN)8Z1k1<3@_AsNd{2(x16M~2A>AX^R1N<M`i4@tAd)kK@
zLQKHGdHWqLFs_DxHUO=U5V}3QH#2%H7%aXkv<F0*_q6lDKn%$=!gK{-?4>~Ts(>+F
z?rNMH1}RJi%1j}KE0L-|i1r1;FRBNY8PkJ;&<ylyvc({<8d%;B4M>{x09W%7x&%dp
zurcgg(~NJQiJ<up6wQE+)WiedB3pkHXbBZZ5DN9NgJJ)Hb^#XOo8M5t3H{Gi2-N3@
zFcRt!B=*}*1l@q)2#HYOn_xhIEE)%xAJCtR2@P?8lVb<)(hx?@WMBlK)dWmv!1BXe
zU<DD}(w+ij+2L~bWLV}6EGZHO0qR+9Kosg53TS}(3o~S;a-GJx;rUbkMI&tEfVs#A
zNKbgPpVNdG78t6z%Ef~tTA@Xwl6&fSh=tvf(2i8D0hF!@&1S@L;)ilL$|l&KNu1~f
z%BVLbBLYF_IRr8LmEkM`ga$~Kr$uN!+&IB<f|g#YBZBmCSZYBYJ9KY8;z7HX&h@xb
zssTZ~5V`@n9YFxW|8ot#!uj=p*uObP1Rknv2qXZ%rhm}BU=q$~;5v>3<ldZCz!Ww`
z;RHppD^x^Q41;V(P+HOA5@~}$R+5@XO4$*DSDL`aT~;dZ7hoF~NDY+*oY;qus4rM{
zyvmrBUY-yWAO~mgLJ?*lwB(N=chsP~*$^K&Ah^p`EG6SO2|zg<tHCr>nYI(}026Pa
zy#y`s9{G<}D!9aPYS3d0*NxDqq`DNy5NJp?qljjZ<1}D`8^C)VrBbvj=ZC^EHTTVA
z@XBoG<cEw~XM^7CXlCmbrYLKHV0Z|x)M9?CQeE=^1E~1~EmM4?A_F9mGMqEW>&ajP
zeJ?11W{&_IubHA2E=MZAoS2Jq$^PGi%$A?@4S%d9xzfs2{Tt_;QqNqt`WT12@+%rE
zDU6`S0xZYks6AXN&=Vz4BM|`5i`NDkC#Z*_P<E(dtp=?k5JifLcP9XFSfc<GA(__m
z>VlbEQrEgS{lH%eB2B5@*OJ-SM1TMV)rg=mL{aDtC6L~SQxc#+xdt@K|4ba2PSBiI
z&uO4UKrRg^nIHoHyH@8I9G5fS_d<KYkTc9YOs^Bxw1ZI)4Q4ZFW{*}dX6%gys=6|M
z+sKeGlWsvPp)slGZ#z*C3!5W#srN^^g0g*9Npo+SQTcG-N!`G3qsS(%rtH`A^1(D+
zr<lW;Y&|&~=c^Hrg8w@9=UoAtH|wRQImWT(Z1&qVRTbJFkiTCsH?Yf=So-`>#%Q`1
z@cvr{TjZ|pNN+UwCpJ7w8HFu3=N#q4EgnxwPt#H0`&!}O2BWiN?o7d!TYQpddZi6B
z0|$x}D8-{x@P~E?*$$8^`Np1hS3+2wQ~nQ*I-7@Fs2#S6c(Ax?w~W6co*Xl9Bg8B4
zDf&Gdr<RfUd<t<WSfg+i6oR1U8m0Zq-~yP)yU%V@ji_#=;3p^|ft1N?it`@kfz_Qo
z9Wt8Ktc}tU(Af!EDGzvWfR*vTtsCB{=Nyduv<TBq(twSC{{gVe_|*5X$@%y%7&3M|
zNfgumrGaF}o`yPUDhvR#R{LStV9SYrWNw6h1+$oghye3AT__#~9QSap>5$w&N5!uu
z;@{(FT0v6pA2CF1hGn9eQA7-WeZh({!0RZ%yElRX1pg&;Qq&9kC&b2LF9h&Q64kZz
z#}IZ)1OT&^TTl`FBOCNg6Lp5JGE@P|)Q-zQcYHvR`hP8D$-d{>1zm{=S}(gI2s%!I
z`Y788W{jx^M0~WTCKk-{jI5psIQn5~;>-0fj66YK01SkyiB1Mb(s*CsbcWc;AW$l+
zQ!xm`0Lnc_MFBTEG%{QKVxyiL@pIs`h=}OmmNY{A5I{uC9YZ*xsxI`6CySh8M<;(a
z0iZd)1jE>m!aGYayRG%PjG>M@Q4yMzBEM_Eohp~+!|>WkjkOtD2wRY^eZWS+Oy$o`
zfARSVS+aDlS(|j&;BL+XvUlW_L%M$!X`PEoj6w)>bpjMJe;v`MM?~!zXcm2zF%`ty
z4Jk)|cH;I0-WWZ8ud<8gD6Gn)<&}HB<KwbZQ!Jf^JGrT`LkmW26JLk>IbO~PV9=UQ
z6{F<ra?@anT(EZ9Eh%4!5k)cCP8=YWMf~CrZ(()4-#-|pvA8kroF#B~#qnLdWUsEq
zWLG~yzaU~EMI)(6tRH?m>Q?@%Q*+pZ_WD^`pF@6*t2Zn_VO2xHEWHtJZPlIJ_2ep1
z!ZkhE=N;aXh9)EzF*!>VniR5wEB{QjWwlg<jQGBRRUs)#%D=$wD>9yoJoch~w4Dct
zivIkVY~_oTWLWT4h}Tt{3Cjyh3$r-%%zT*sQ?UM-=)1rD5d2B8q0YR_7-!nEKa8Bd
z^(2Fi38To~e}AAvY+d>uMojYX1dKb=bIw$RYn}JOU014pG11^-!}^Bs4|T5_6P1TJ
z?M?~_6;)0OI|QO{<AU44KkYKyCcZmPvc^_Dy+2%GO(fVPgT13`bg=Z|Ed%pTbH&b`
zG<aQmzRdm*S$`FH`i=J6(L9OZS(T8oMSZ5O$j0VFi?7_&O~`9pw7eHvuS0C%!@(YF
z*?uhcK653Xzu#icSF)GApDheyzy)?9m_KppdtW>ChiPC_4s~De<h_jX%bZOtQ}P0M
z2DU8tXA;ahS*KL$3`49g2#BL${kQdR7M|xXijZdZ@CR~`EU}^7Hwx20{B@5im5DuY
zy(PScP=<(Ox}Z!e+w*-R6~$ch!c;af%=f~cOkR&vZickn#nmZ1aIpKzzdYkV5Z(Ag
z1kW6UuRd`Y<M#a6$JbNaz7-nYZj>6h=2?0oY#W4(h|QF@%I!`^vxi@&?0WOD$jN}r
zft!1f#9}hoqE=_uT%vJIax;X=q<TfCQk<6)YeM<eF+SKi4ZHcgSw$)fx*TKDY>IE9
z=|fD`Poc74;8%Ny?fv4+7oUg3M_!tJFx`CBw<_#qi6d#q^i*3^q`-Pg+D=P}DSRrB
z0MPFbH!o{Wq<4z9H7u*UAJ>}9WPktD@7t61?E?lTm35Hq5_=#mG+k(s)e>dpVwx#-
z{D^F=CorwDp1&?ux~__OG|afOGFl-htb{h5ug~U*+Z6Kk9gc#37#HsDL<S{{>x*wD
zKMo`Gs~C6aZl3+1t+R5RA{lv^(3`E$9aLI#bpxERSL((OdfpwxhiO(zCaN$RaZ<OY
zE?^I|sZu_8oyK~uvvXL6X-8BB+auQ-xZB@p{7?-COuem;IHncDMou}e9wqB6fsa+`
z9aCV1i{UrIL-^dOPw)V_!l%{6_a$6#%Np?)bB}GVr=>pq_Fx3w?nK&3EDzF-c&Jyp
zvYbss9&>e`TY<tdf*8)qo>F)CjX<3ov9Eij2H5tybwWvnyE>V!lW*lqh$QVk_RBn*
zV_t6pd)(QLkh&}JALyPVL3nSg3iju%XJ>1VifGmjRVwo-ifV<*ivR1kGU50Rv)2B9
z>t=rUXJ?+O-qZ)Sf@I5m7o{c%wj|<Pg)O>ZNHdPs(nZ(wcTkg*Ifq7P;$9J=ZtWcI
zP8rg#4VcAa?J<sBT2X-*=m4eU_^oOCS~zD{GP$=zOU!cLY2_Q6N#16p1`k0?(p1Q_
zH|?*r%9$r58N7UNq<z2G8#Nz_jWJG%Jbct_;eT2v-gInI=lAz_*9NQFqH`S&+Z2^C
zr)<f}byGQ?bNN7bDmnJidwA(`vveBFojvEK`7&PI@FJ(D9L1&oaI1;UoC>&ssSYnX
zMjgMM1OAsnPyF`GBE8vS#n?a@;+rY}OkDDiX}uw9wD-Zx_b<hA2I2}CL{YkTgcRW?
z<@8{%Mn@k6vF#1kJ0)9S9N9fQD}3>gF0zlgGF>BV90Q+iswl_O+Y7u_Y=ttbt4#g?
zKXp0J?``1JK_(>Y1hahhsvM<yj`38Xe?8Ezlv+V*K1cP2nTvkU>Z=;dBJ9ef_64!!
zNfBF5ybwJxU18~9RQ_C<v1Kogy}zlv^9;;rXX$8qIjYP8O1LKN+GXFn-`6J}_HxVe
z?*(i>Ee^X_^Whd0_|M&UQ0K`g>ZJUus99#b)x4tf6m^OhD0J5A)ZT5rLgpBYhAlU8
z6TQ(3b<L1mAgFDxF4tO@Kp#ohdB$RG$v1y9V}(w&<xAeYxa2rhv*f+y8$^5#5A`Mv
zQuWC1Do>?(C(9Lh)Ee~L?fZ-{`utf_)&54)r6Y)AhqOXv-5tXkkZyPbkdVyS<F}_R
z8Aw;BMrpCWXJLZoI${+0ZLbz?_DrSy@`wa^=RXm+9SDjGkoqjA5%slf?Iks4Lyt%j
zF9nZzl=msCzgp`pB-@kOu;{4AUDWFRtva~(ieJ`vrL<D(Aw|%Q`(zu}{Ktdjqo)$z
zQbXHEzvBX@MW3QN98)Yc+3A8ACs@GFHd_{(ri5FzZLPvL*an@H+4<5zC5J&bEk-7B
zqFG$|Hz}_nWH7ycY&^A&xTO6l`!R&BTQc{AVY^oblSBo*arj7(l7P#M^$Pf8qNuo=
zYF`W9rH0z}#7X7)DI}SkR99kNMk4>fO=3lCN(T-Rlarg&t{lKLg0(4&Jyw<~@XBbe
zt^drWow<z2V^z%>kqnmf%A=jB70ArY(r0E=tlJnc<qHK%Bvn;wI;iZlGweYG>!6o-
zgmwVw&loGO{9BvR?=-^9s*J46<1X>r6;?8<zz#yY=T1-yyBge3Z9x>&tLFMqn)q+!
zSIPPqh_J{TF<aihz^lP*Wwg#&uLO>_6nuQQO_sqc%JFM;i|}qvb<DPL!Z)|u&u-^Q
zvFjkc?`%N#$amhhGk;>Lak#w%`|ru+!a0@iZu1plE4lWGdlvI!Ua-HtRzX^i!7^9q
zQE3N0pW55aY*j2<eD(w5CobE$&3m{~H=n6!<j_z|OXy#=HW_K1Ql?vf-|gul7jfE5
ze-#rAe|b*s7()a)uiICgy`6=xiN0E14Jfe{eP*x+R);Ebm!qs~R|ee4cH*$w=rJy1
zogLw!K3o!ZrOs)mRWDsXGMA;ih<Ij%FClK_&810(@OzhceGS6IwDb;Ns)CUZ(*FDu
zoI#hwpv!9dM=a`_USv9vo{X5K<6g&Q?u-0(P3lFb^BI4Ix~O5afFlf@M<%N6C(@r7
zCnbVHg5Q)nwgzTU`HDOsC5a`qI6|5}eZ3TEe5duO#;x*4(3lke;&auppDSE6!Ba*r
zHE{R7uNQ~->_z2GtN%V=b;a*l@kOLAWyp-JnW35<=CJ*7BY7ufm||3<8bdb!A#uQ_
z;x5I#Q!Hz!{y8hNui~Ci%qQ;74P5D%pEe^o<dmVcK<rNV@b9M}R$Q$H`C{(W?t$ju
zYN#-&+QaZXzdn0Twz#GURn6mk3lp~{_Gq12wpZT_B%US`Ax#noDF_C(vl%UN$4%@v
z7&1St15PVhraeun;`{QleF{@_{lHQrU${dTEq$NvXXVhnCb-VMn(K(o>7bnRFZset
zh1~Y6O?$fKT%z;y+F(nC@g~Kl%9(!gKivqXbW^v@S#dR!S;NoG-qig?J0RptrofUD
z*aL=qQUjcv&=)ZSJ(3t7njm1w6<nZoE%X~!1MAbrrL>ZS7)2kN5v1rN%wvHc*Q+?E
z?g(-{$2`C;6dYOeABaM!`UiD5PgUWRcjYep=~(cty#29dRxiBMu6Z9KY=PXtTVBfq
z5C&Db<Q6<p^EiFz>((s0xwHI^{2W!aW0uxHm*)yr3)*0?zXH0D9a>}pxhDHd3o|*n
zFb$&QU?Vuv?~DCiS_9|;gu3tT1mb_6b4q}+!mRn)xV3tg<^VI}KvW9uTl<}Acjms(
zKIx%Px6ByDQD>XWzeN8wOc%vu@y1K?szJ(kBIf$boV}muxG)|E#*L<0Hzrxf%Jz6#
zJxM=`4xD^b$}IhX%b;C^BXn0P!6|E0@!0My+ULpPqYY#NFKg(CvDhecKm-%#AUb|O
zl3knTwD2lbfX`l>dslv{1;v+jGpF{4z|g?j=A+Z1p{3k<=IpN<xgEU8mXq%@zY}Sb
zgO2@^0{S7J;<=v8)X@Fup^F%!q^ew5{s(->^O1+feXm|`cli7hxxc+u$@IM-@Yq^_
zuurZor-5$u9gQq@&ppelTg%HSb}pJMOt#YPsfny0P=fyTU75`)x(glsntBnS5lrVt
z$?dgLhCbE1_TQS<Yf;-kbY++Ynea(!d~6llVVqoCfTVN0!0jVxBAY5H|Mr@GbE)%(
z%91^r#G6bH%H=6rQ!r^qHRXzGD$J@dE({WAoAO?FpH)4ri<^0w#a!JAw`EWG=v<dD
z6!?|QV3Ez_xXwyWRvP-s^PS94ysR{<+Z)NAtsb_p@8+yQzS1HYeyo-`@&+l{d*77{
zmpY+1-6y|KY)sXRynS?z|Ji2l!YK&uh8}tZn>j7XVyo^7W>hFE%JewsiG5jaG3)h)
z&08#$ThkQCY?^<w#JiqZWa{(ep>FC|uR@qkwbk&kCg$U2cg3sUKb5tUK^4i#hkTrM
z*nRp+UuIFctKckP$A4=w^tH6Wt`+Gsk9F_w$KvN{?Y-H4*A8LOA;(0^fpT`*dS=B-
z6uBz42~SD1r$?_QS2&5MRk|#a==n}x=dx)SpX>MKxzcA3n5&NlJ8#Ce)k7zwtlA;2
zZc>-#soK(&5tzJ<7Yef8d-^OKp_~~W=We;O@UpLM8S-QNkNTR0`AjkovJ_bANRcP;
zCv}ws?5YR5Mz*Umn34mCQqcdt250inh@~_{q!4j}7S4eAK|8x!d}Yy3uqjpNENJ>8
z`tE{YriRRwfka!eorrm&ePp~cOAGz5R`^fGoN)Uw=RLL@6)Y1emrCxMDp5GaBL+i2
zd@k*z#wSwBTSA%#A>sAIpiWRU`s-30Z{8iY|FoSxrk-Cnm)UHtD*tXtHvd+nqz_rZ
zUvp_b_-5tk?;IOJLTQyY;lIh`Z|BJ0Tdifrxqh6+h8%o*M$WBTE>iCWGRnlptf=pF
zU^T%Ub-AQpnto&>Pp`}+7pEWa${J>eDVE8M4H><2H+ju<18gYmB91P{)umrVVq~w3
z3;+qxhUz0Ol!}@V>Il-^3&o6ZodE`KLm;H#q7+xxl9B4ruhhpO9U0mOqww<)_bLIk
zcYxAMEijc{D?pTcY^C3o3D}DXl=a;pGXHBqx(VF?4k5y(Fux|i7{oCJ3PAH2UQEo+
zL=Zvn>N^1Cku#0hAeaTv@Tf_^RE2;b!s#3hpf5oq%!mKLAx6ecr1I<WK-n>@4%Ck2
zX9uX4peyGL=Kt~a)b(#$xhN$O$}F<yQXPsR27wHY1y-_viD*PXUF+ox(g&!S-BZ_+
zO9&S4g@Tv>`wcq3H<3cS<Gc`Xb%4YZ1JMl5?_49AMt~K$s}KS7Q1fD3_W=QP7c7HD
zK&Z6~u!1<`>Ldtd<btpnC)iit(uBws0j*dot7p*S`&4HmY=*NKey-~8E?8#HXeJ;d
z{6!!+k1&Sp{9lPPAE*by60nbr0XMoInhnrG7Za#^j0YPoN6-NM<5L+RrZb!iV@Rb0
zgPajc06?HuZbDrj@S79fkJ8-@#0bWxQpruIiL0PM0O;}*&F~@Oe!P$}h7${7D(ZO*
z_-&vB`h);>^EUMzU}9l!g`$s94u1Pux&lByjm{s<;EysOytk(%q+sN?2kGJ5#7+7t
z;zPzkfefvxQui)`4djgIn$Zd{Re_-G%sc8@Iyj&=YN&ZSBBWGj17cCc%bpb`_5jCW
zz!n_908BNn!bYA}wKDH~Mv>eAzWex-_Z!G@!V`wpD<fy*I6=1LsH6(&1ZYr_Atz>%
zfl00IQ>o^{$Vjdvb*~eS)Hf)IVu)d~kYIw=Gboesw<wKJd~pP)=2XF!2CWpQ7Ras@
zFBg7Qsu&EYZXBzdMxlye`8TM0K)4J8X4o!@x@0%mqFkgA6pE4>;XtuY6cmJR)Y3!Y
z2!)t_pYb3O&)`#Gb$P!C`WC~a-a8o)Aq>YFacLbAp{1d&P3P<JFbF{pxCjmGg*DMK
z_)DAva$`A>%venptzbkW#8ikh0Mo!Bcg87&1OaxaLU=US1Er~mBTZoZ9&jTh6rlbe
zs4_k(`*|Njc&;JL!YIUWlHuJu_<x{T6v+mFAXO|S7;~c#+ye-rmxlS`*<L<Ef@B!(
zxuCva$$f-#&<;X((a@)c%M0AGjapWBQ|P_jXTy_$?Wu^y*0f}<ro*K_{vun`u#FFr
z3VFeXsW{HIfi0Tqj_g8z+?&lVfU-r8lJ8|B>tB>;4r~`RGT&Na_MiVmSjSIgjp1^T
zC;y<l3?Yy$cHq*zGV){YK!bKLY-@v{aR8ypG$xoW`y*BI1VeO+61oYMn`}r7wl^GA
zGR!;xhf2=m{(zE^0i?_h{CNw3b{=h_k4?acF2TRmz1*{Pl(`w-+m-Wy($%517hd73
zq&4M6!txoEp0%|#m!G}u<cxFg?oftP>I(4kx!38eEUOx4x6S(>KOK7IcljTv_|Yxn
z+Elmkr|CS{7XgDgJz4yo1<NL@DHC|!`m`sY=9gSWJ6t#SF}l?FrmV7b)idCRr^lVe
z@pH0iN7;{U8R*z@_H|caP<^4oo<g=A+_v!M(Gd;l<;f-o_9^h9{F1O{R-%6>El>Q?
zG%@8r5Ng)uc$nd7R>4$RTMSv<&W$SAu5~0>_$^qqGsh0{<14qcoAL)12xt3DrEP+3
z62Z-0-Vq0Zr$qWo^O|h}eFNb6qD;I)f05J^Ty-OoK&2KQ6jai$yvn&|{A1Od;+fv7
zZyEFEhBwjhF+_FJ&nM8Y^T@wE5Rbc(Q|pP}(pIDFM%y_4<dVe+&|a_=0go`x<NH&(
zF6exK@_d57qv*rW-T_qgX+zEHtRM8Aa-uLaMSsbG`G3KmD(}B_{LHq3`Y&N#LatH<
zplilT`7pfd>)VFD+fZ?UR@k-^BUK{99|^n*ova<DQJ*reum2DQ|KWO;drt3Aed<ks
z&w$mXzv$RVtXVY=xEEVJ{d$Oh@U`*7-1{+^F4?4RXPBa8S6_xEP>F(u9KA{GNGQ8p
zQucQ2jvfsSj<vwe=BP*T%U@JJYy_%-mN_|>idfATI^0*IkODQGW7rTXxs*zWc2l6D
zomN3FGCX8Gr4+dLA}Q@)z)^t>6>w7GvNfjfCLuqua%G?d+@IKi3-GBx#^;UGBCcD?
zXYl3JjVP5~Ib#AE2!@SADRo@kPMH#bt+KCF0chms30gWK30;u{#0VRQlzLGbIivwd
z?#<N%(jQQ-$pa$-#nK3xw$!M<SB6mt`EwM}mzTJA;u<m-GAtoc{!i3#E-+t^H%dv#
z#WCehAmrk+Fz3ZwoxE2DumT;N3+54sXyF(Lv6;71m=$GDdx##i15Z(W?gm4vA{aQa
zr;>x=wULpB>N^OXD<cB^XX00ek@N5L*R%mPial@)MvvE0b5;B{PSEEjp_GNnN4M7t
zXou72a<QrN(IX(T{V3dD$#^KyFF>Hw@0hF<;pERa67zg)=(IASH;PHV2FVdlxo$Zc
zeDqR$F!;krrur0jpJL$odc#}Q5Pyto0kk2}+inckjOFg1S|5A9-1r@SX8@HeNek0Y
z?}Vpu-jkMBzr)8r$r+^N<*u)PQFT_T&{$``ydmBBr~;#&DS2qkLYl{Fd#{m?GiT<L
z1+5cKnqk`W<`A4#)2nXPag+;vG|E7_C?U6#{d0Wd?;7Ya(*|SAhGItv5%O4<B9~Vk
zc|79R#?Yw!DK4Rd&1Jdy`1mfY591l=VE)O(#NbJzEJwYAe3lfeEbVaQ$Adw+Y0bCd
zL_2QrAv9^D7h}fllXhUN0C&Pr)c7o40iFNeo6By`#*)*D-e8j1_Y)6-=+oF$Y-ZWl
z<pU54Zl}-3sZ3iqKgvb_z4UZb@;2^K!RqhK=lur?YA%nJ5R+=Xj&P8)t`Uz*Ye~@R
zoxDiNo;1IVILE%KA=Bm<`sDMqmqy*Nv(m+6qHFkV=BVO_z{>0&v~&aP!7RV9C)e_s
zorCv~zQIN*H5z}(CVXhGB&x1U5mf?-6umPqU)c=_e%R046fS@v&`+c3YvaBww7QJi
zCh&yvcbzJjsNvQn|0-*pENTBxc8>VAx`V1TgF-w%!xOBE4tTS8)~u6~PEd<tgQ?09
zl`(@hp%aJdKaKPVkvqlUMK!{u$eAZ(O&-SC&=rLfY;BR3;JHmcz+Hyg*C=U_{mT}W
zl#+U=N3Lw;(a?{N98mh_wwNsh%2yoILgH~kgG%adpu%*csPWT1Tkk0B;7UBxn~q<~
zqwcxx+KCV&cbBe-l?E)?p+cQPH9K=NaH7XFW>K3y&s=?BbFy8J{G(1EF74AAS(b!P
z9P%oF>ZBX!w;E1AB<4N$fW@C?G66-0s-N1JVx}nMht4X+X$8xYkvmxegZIY-<J!}-
z*JJ41;<IGE+5iQG9?t9e0RE)NO4U~DaQ^}8M%U@1zU7LgIgV4<XBQbVWh<qQ%PkqH
z2ZJu@?7J3dDm9#{m8Ue~KDnN}X+YfSs|BE`Fa3ytOBP`N;3CRzGMOq`?xcE%w8>uA
zqb9zVCMlic4TkvA`J-=D2cKeIyf%!B8~6=&{C51b_kx%bBQWiqQB}_+7{rv+wEa$n
zxoq8oN=9n(2~PjGh@|NtUzFhpZ*{-X@^!#vY9cv%IX^qQ8u_T4QBf~50oieJ<ZiHS
zdaP%-m%#fES2V7#|I|kH=|hAIBBZ@V{{#L0D)HO9W#6uF=5vhJ1e3N}P{@UYzjuaL
z2peU|75{H_-eLByw5L@T?)<L?A8#2x$zvwlycv<_@d|qPq}JJle=3T-qaVm=9@7UR
zmf9|13y6c)IBo|e2rb4;PReHOL4g}+XX9wQhW74)Nbu&ym1)y0kEFe>lm2HW>B6hK
zPoDLXhPRHGW&9`svC^I6A$0BW9z`~a&1On{2{=?jPebOqYsA^e-3xaGHkY|+=C@*(
z@|rvKAU`v!-wy=O<x=>fN(4z8Do)*d9B-53+hQ2EaTmdU4$qQ9eBG3*-R>7LVUlQV
zqLMDgA1K->)7fNwZx?ua&IonONjSu60dhC@KI&d9)yEa6=WeLDwcHzo|CcN-|7UZ(
z+qaK_3E9Jy`RYxLcGHqdr62xozsP0TS!e5A<`st<2BiAYKK(tG*>v`fle}0F<eI-W
zziR4Z5L=?#mzd8K!5tu)-Q_6<XM|0z6U*R4;+<y3Krfk-FOOoQrcT)93E8MN7{hpv
zvqvY}r%it)j9Idzx22h>#FAK!F&b?ICTZXy9HB=Kow(*`d|-&b3waOaX*0avIwH>W
zSs`Eh2*QH!HteT0sw8TvHii#sA6<xO(~mKr5{*G@CyaaA!@}-kHxJ+Qq_fSUxc~KU
zWRDy`ts>s$31z-5PUmdVe!3{tZJdsO^l0Avmh=B{be3UF{%;>1IYq*t*=T8zmJX5b
zh7lsoK%|i&NC@a0-IExM(F21HX(mXH6p(I2q>=FV-2dkVFFAG}+dcT+pX+m-Cw%$j
z>APSyG`+0%(t&+MaZBy@n193K4ou;t_}-qTr_DXov>vzevzFVLtR3{nw9j2%eAT1~
zF=>{iVKMz$^!3$fZE5NjPfIT15$tsDhE%XXRS(J;Eh1_9C-#ef04lhO`QfuWz@viW
zLR_<@@z~OF)n$UjtoFOZ4)0CwG%^{sUbI2J<CPICb7y2Yri^FXL=UT3Y;bdSwE#wJ
zaID{X6a8~Xb!a?3c~1MXt<u+C)ojDt5<1z|698^-B#~2`c=Sbi@DWYoq_5RIwz6F(
zrXRFABWmXO6Q-0V^2-#PIs3(^M8s4qzEFbzKET(LhVJ`+&|RIkR9s&V$h@L>E}gjk
zJtD(24Dx6|$j4OkmE|X~ztaV<r(7WkF$M6(`p@i4C*^oNiz|y=nzpMNJn3xwurm1f
zgBgm;90IX6bF}>l{kBM?ek^@8BmG==aOCIs)$$7G?t1_JSThzdC!RM=x^%eJxr_iC
zt8Lbcz1z2FqV@nX{r2h+_x1zEZC(u(Q6nRK=<}hLu6?#mf4|HfudNs=2U|r6>Nuzu
zq1C?Fz`6WxaP|n>+snmG<U0mRKmR8%PQ)FHJj3~^_ViABIw1|WVX7tepS!$1mTGA_
z(W(BS3_?rV63R{G{P9>?;DJZw;)%jIThy8vBjmPOA{+!`sc%rXyo0=6$dArWcv)zJ
zXH{M|B-!#RxWi`6yA(&+AmYY6j9}F}=gF`x<vB0Yrw(Cv0j<hyO6v>i$aTWD_5#<Q
zKSDI^=AsAk7r$qhXqdb3nPgg$kMC92H-e`yt(1@0<0^zB=Pfh2H{IQ3`$iF`(*8fq
zzgY)yH!0W>#V}XhP54T-Ls5|I_K0+DN|EdJ6DNiU<x^qVhW+FVs+QLhiX>{A)xumG
zJ#X7z1{FtdYLS11FC~h9t7@>vjgxWcruLmY8E9W%zA*Di<aoJ@R_z&gJA62%68q1r
z*SoUyZg`Pcg!*VmHG=;?kna0j*FJ;5cZV^#Df=cStZL{!>$N9&zRs^(m1x`-JxBKz
zn8?lzJ-rvbAKa0%l-sC!cTZVA7khSG9faAWb<S)|SWQ;p%ED4<Sxh7+L@VG{fAo4g
zSnqke-|&)NI=u1x2l*c@_{>VKh$}vg^xN*yLu1bbMk14s__pomZ=Y2Ul^>PuC`?Hu
zeqNp~#q;D<QbF&keE3s#)t3>ef5B?Pk`iHe?^^KrVNz|0q|Rr(yS#o{J6>{nIRUJY
z8tKqA^MQ|l%b(ZZ4Cnw)z4=99vo0ZegK#NrJdA<lhYOt+*114vH<3Nbj2m^)jf|;V
zl;zx6gW+{*w^yY-we3_6ENUgL;4B|yrNtL=SCJL`rkK)!6Tt}%H-d3^N0psVkG^O?
zua>ZDbI@^x+qzyZii%?3-b4W$&Pe*W38Cr9)7KHYZz^bI&~aSaEBXuTFW^BDw`0;B
z9e!X@BHK7$IWe(*_0jNU32#*P8rfsgwt=g^oB1a!s{Jw3Qzbb)smm`3a1`p!Y^|zh
zf9!F|Lq)1rQIUUdZd7CjMUY%fa?J<EjvXLP1YuU+ITv%sWym_|JCgM!`_#%Am$Swi
z_bqa$95<1#UMg*UjLP2UZ^F|kJ67EyOEGUv?Uvi9wt;<HJASH$&YA6&P8ek-$gRp&
zSE{qSy?f|rzC=6Oo%g3+<{t9bmEfa-;_vxAD6_6@i@U>?uR;_0l$~g_Mgz?3X&NMI
zpm0bC*`J!vCC9QeWw>ks7QPldPe<_4EbsJDGTR1$p}TNq%hw;DtPyz1G+W)?V33eF
z*%1Pcl)TyzKAQU(3^8%<VZX_0&@lIa*FBQfUlZIGz&Kjmko;sRJ!H0fw(U{RnV4rj
ztF0ghZ^@ulj*Z--shp*K7L^3|$Ns+0)6bL)TE&-#<okVIaG_jWzC6%Ud2<YP*O%NL
zKt8^zilJ=2H6$})IqDR*_ruKNdB@6Ujnjl>yo8>YO-A-1{Z~EK<piDf*p|$dQ2(ul
zFAI8}<PSws@`{&8{!YG6x&=S=3;kl#WOPdF=a8`6qcK)GVJXI&f;Ix~MDZ2Dx|R=>
zwvE$H*F@kcdHZD!-gG8keYo~N5FMPg*maNRh%}dhA0LQ#7+I5M{BFOskSS>2J~PIP
zwjk^^wQwv=<H4@o*z~?pg6WS^<;Os7(WdkBiJU3N%7366%tS$vC%PSnr3sTco=dkX
zKLn<(tf>x-Q3_WcD0Nqtm;8S5Q!&O@Noez}!JC^NXUZ>3zI-2n^;?w{rE&-<PMvj5
z*CV2Bp~Ig!GCKd&)kbh^54?R?15pShU$UHPs${Yas*Aen<-|7bS*4jppY_L^6M5%f
z(tYty>Z`EWu>o@{5*$X;G(WhQz2n}SpW@p74>VPyelQi|`JBq$mQEz-N51fg5noH$
zNIsKz*t>rSE2Cw}%Xe|05nKSXH1VbJicX)Qm!j35A2_8!;hEDN$vBQa_?PWb#e64s
zCG8=HiO>l*-rW6)1i^%_+nxJQA0f4LxqXo{U~s#%h<G%~19Zub-Xrg`N<R_^=cj7E
zIJ<YxzXL59VGc9>_B!jnKZ|i*O2xrGDpYkeRnu$^T5Mo7)5$mDKI6YXUI|7S{+4AZ
z%B=4>n)*`REiwb4ozR%Sxw@ci_s8=9_Qa;O3xl94y5)UIP=N&sOMQL=4pADih^%jR
zZR?4B)n_s;SN!s+q4OG(@J{=15l}tWt2dwhiaCJQyV^(i(<*t&Nl{F-er_bbA=(d!
zlA<aRQx^EOU$IUKR?K+0Ks}vrDX!0UB+cs5Z`&k&>AMLD(95G&QT-anhHtppG~zFh
z{PnO^$-T<DDn}b&UED?aIfUP1_908D4YR}zH-%A?aAi!|Hf=Jn69;iT6~rqZ_fp-o
z%GB?RQ_aOswEwh<N;){Rw~74u6&42yfk38m7sL~9aX}=0M-)ig!TAO@v?N!?zSzAc
z-~z_)nki{l&f?}Ae&!S?N0;d;+f4^L#2KW_<~qzJF2Mgm0N&NJhb5~2fx1k;zCtlH
zN9Kdkb^8|zam43;w`%DV?hvGWE{J3)y)1+X4*|Qe{P1!Tpkj{$DW|<qG$ljd>|cqL
zlB$#p5T<t>H~|;p1L*&7pgGb*)X})*!-#P{e_8xotea8FM^8qiu*`DI_$aYs8``(h
zNQpO~cY_Ww^HNpUdw*jW6r=m|5##oj6P1{5Aq(@cbtw!!?JS>NxzDmdM=VQ)2{kV~
zUX8mJ1QwKx0)RE{`z2Cu-%tjbB3vf!DW)cTtRFE$c244-Z$$l@q)(7Y%6u}chRva#
zo?1VYnof2WQe(lj<UJ$KhIY=rYuxi@T|R*#R>H-raBlvU!_IQ$Z?ahX(x^?p-jz`7
zpj*IZ2aj$qO)j?*XH8iZ$<97miJY*>;qN|aep4-;yo&dSVLel~X*0WAlAi_BbSqE3
ze-R*Zr&i3<Y+ikf37PNoH@thCXTrNA?K|=}(`yZ1cs~odJNwDtxr2bitj*o;zYZxo
zX<LkRD}(Smo_>m^IuKh(S=Xf95Kl>5A6qD^v2{xj?_~1;v6^BCt$jr4#v#t%<`HiJ
z`PO(cB*qJ%3x+i{oL*L1W@-Fc|9Q;G;;dgC#sTBb%}aSO(^gTMQ~Z-Z_+9+=Q{Ek1
zmT``eL;N4UHog}q`4$_c){nL=9BHrB&!;mM=R+He_=XCHed$<gY;S1>?hpD~q^6Bl
zY|`Xjj(4o?nkcx>=F^%7*F4U76MruW4+1cc{KPuW8iBtF8i{aE!XW(KNp+}?7xcY2
z<RR=s0|Pm43d($GvS%1TiopO%W`Lz?Z5$8*!&F$oFoD}nF}Xk>ZA=2R1vSWx#RWY<
zxREvxpM<=zmQ>?aIlynwr_yzph&1NhR%OA^!Hfa>Rxkgu9twb}`lJU*QQ5iE-!QDr
zUdf_w+=y(<25eq1q{DH1qQ|Xxn3%ysBV8I0Spi%g4MZ{kj}@#dKpu>3m&1@176VY)
zvMmpgRJ*R>1eq$yY8}fj0YWK4MF^y#3p4y$8;BumV+O8<EDG>JWwYRTO@saeu}Z3f
z4JU%=gP=e|n36(NxwZfXNWPTH*lPhVoWfT@I(<`Gd1AhS0!sf#*GMYQgMj0@)ysaI
z?gqGp-04UCG-=3~_@_{-Up>WjCDG)fFQJ~a1}sI9)ME>YrBZ&gkyMg<T2BEoN3HW$
zK?y&#5x6S&50>5p*nG!sYdiq)DFk8JC%)FY1FkMA$zFb4d1I2<tiL7zwGsr=rGtU%
zKmxK-IVV7M95GH3QIvQM5Nu6DmPSd5?s%xjjwk5rvB_+7fGSB*^h*qYiP#_Fr%aP-
z+X8I~0P~+QRodPE6)Y7^-A7H%M@iIFvawQmU|mW;Yvv%ZNpH+anbwY@4>|*sS4f3b
zsW-<fd0kz^KsnsD&UhjKX&3@8Bokwhs{BwRBV7}<(~YzS97wSE+Jk+<ovaQ7ZN%;Z
zs83A~V61VZ1=!XkXGTdbMg^`shCl)<s7;Q6H1HIFj<y>$s(U0$Ukhs5KwX%c00JQ;
zPfwK*U63SF;XoDQmVAP7I>n|cZ9y)b((s^%fPhYYoW2c^#Eo#LwQ;dvWqW}R{R9V|
zb5|3*tkH3ESYQYOz(+VX(ICn5v0PJH4UPnms6WsRM+!Ldg>I`#v3~_Hrx?(+z_7=+
z;~{1M21=P6v}M5DxvRRZ4T1ozYP5pM|Ddi>?@=bX*Pb*G09V$uL=40%<)^3rCOzHO
z`8zgD0WE8!6!;IM1dO@psb!(tVW#)?(1xC%_E>1S3YEh`Iw*oZ5CHiC7bv(7XrOTY
z>~YB?OD3~1{ku8~k@Wwh@&twe%1H0-EP(Mi1|X~=g34E>#)bf;mlB|yu0+i#j-iMk
zMU*L78bPWy7fl(7hP|N7+6IJao7#d#cs@aDbu^uW1{e+6*LETUKpXp0xdH@fPEJUW
z6edE-SPtjNMBgYy5~WL0+~Ip#E*>f28&T(OI9?qj*dsIM<L@`{M|fQ7Dakh4T+grk
zdDDmL>Aq1f!k{FAS&8@eC3M1<SQZ-Fmaw;Z6=q{+@E^!-mDdv29@DBGa3)or{(Af|
z)8FYz8dG5@aho{;x%0o!k}-=p>t_CUH?Aa~Dww_VyZaAv_e5beQ>#)|K$-1j=F^iD
z*khIL;_eGKd}-HDzc}{)K!&I=y@Kn^=JB$h{)!uAL+jn)+ps2Ffiv!l_N41XN)%n!
zhsc0{syWQwmj~ArFr(O6|0Cr#9*!q(EpyP1LsODg_3yu3@4rBIZnC^-C_iWXNZ-QH
zz6^Wm`g#hUwfCz~rL6p3M?Ot#d#GOs*Kx`!2QjaKr+rhe0eFgVv+jRklKC+(>v2y6
z+aGh`|3K^x9vlnF1?!fKBVD&4K;3T9g6~TsVBsQuy6EHDH#OSuJVAIBR^0z{{CcNW
zm}L83f@yVSX@_}diEUqZp*FprbyI)w_8iVt)U&0(y%mmPQh#-h4q{HwW}kt@w(110
zD!U-V^FJl(T$tWT8`2WmdCF^`IlXUtezc`0t;SdBPiSb8lh!J2z>7+RmiDuEuWQuo
z-75IIopfeJKOXA)V=(6eSq)~{*Q6CZBz*k!E_UK-#oaiJHa*Tpd&BBQrMdZ1xX0&P
zwB)J&)^3p`ic6PhH3EWCgDa5?1PthaIbIum<ZHe}8h#%^KkaAJ#L~EfWhDbE{(6Be
z)uQS9m6<{I%20=%Xry&w-8ySY0bkC`KMjHf>1S77la4u9*%5~Rms3Aq)fTvED^>oI
z4S*`UKla&7$X;Icaq)Ws@@x46pv6bNYlIgrMQ(+c^=XD(j7=*E&TRLR-S(B7rpM&^
zHuXM|1GGw}n-c&%JR<#Gt`jOCMr&K2qR)Wbxd!$^RWM*g3iL?12}6fYKEXjY>p1CY
zL$RQcV)o-Uu%S}<Tgn@~Yyh)J!DCo^wGAWy^_Ytpmc=%}#bf@*4}!j?q6OxG=E23J
zNjPW|mSv6FDfwto>V_#Do>Pt)6M#C<ls%#Ec-oC)DIP%pazZ@FZx?{5gMk-9%byg!
z?Ii=Iw4(CC#e_Og*yaN2&O+3!e3IgAwLTJh!0HHzppTHs=5#;75p*dz@caQI%IT$b
z_r;hB^wA1yL=rs|kr_c`2fygbnnK<C-(G|wM=9cl6g7Y|E|tpr5=D#|;vxr1^q93k
zr~m-`h)SkYi4~<akOC8xr8rv7dVLdeFQ>y+A8UMk)+e84$Hl|(kozl~zr>bkbn)ux
ze&9)UcTdVYDYM<$Bx2*W@Pjg~#2Xteba%y*G`$^<)X4_vM9pbS+kDRbMGSSebKO1~
zY*@u!3uFFF^ot}!`WHh|)X9^yiG2*Q0biw=L1ikEh-vlWg0}r#>wFpg4!Q^-O<zYx
z%aORoiRtNjVXpWg*aDlQ^!;t1U|z^qn!t6pCk7S5(8;E{xuJXfl#y>YkSsU2T8`)M
zXT$_`fyPHw=G6_QttsOw>X-)UFU8f*d{nE30=ORuFO=Wm$@?tlmtR*bVI45!`r|f#
z=juXjTnHU(itTpbh2Nr2g&|#l-9|$hJd-I5?-N`SHm%{f*mzo{6ig?haVjl+>)i*s
zMCo%5^1k^$+SUJox>^4fmg_5z->q=pr`)xpXv=hS=m}xi%4e^?y~nZ?m9lM(W<xKG
zm-aW3Y7?Z_8)QA_+7J<~Dx)kP<*l*?>9P&g1NwxD_#WR5yRdjKMY$~*{Rp*5EF7uR
zVR07v)fYlr=cFV$r&XUisYh-<!-q}lo~pXZ<{u8$Ees~+k)8Q}PA*K3aR}#suc+p7
z`Km`&w!gnBN2|za*_zM3kuE0R*h27%_r`r^W`dvHzqHkGx8Ff;JE{n%wMgM{5g*o_
zA=ikOfDs%M*?{ydad)}L#g81c)T~-XFz~If)}1~9$I>cqU$0)Fd?k$9OHWG9JxD6Z
zrXg!n@3wd*;*D^olZBoldE;zZpDKH9W2GIO@@>IEpo1YjvaVNFK8Fr<T}M|6TGd`q
zsfSsEP2YZwWc`!gx~MO>3-@m(pYhcu%Uh_63Z;X^4Q=ye$@DYbKw_wUh4_$lxOj9_
zVbz>G_TGIg56&Y0r>i|aQaR%jue70cS)*)j&!^hw6W0if?@DT`Ty}ZbMZ8V~QbKpN
z&ZSXk-e1^YI6Ma*B&7JB*M_X^iK~cYbA^_m_%D9?(H`H|x|X*xQI}uMI!_3&IQJk~
zVDjFVFidr%y<%wuh*e6Re1!Ds8mO8N-`y6ItqP`=KR7AnMU}FY4v0Eq$E2-3x5v49
zOEmT?XB=0@2ci>`C<d0_3-BWUO7L?{Bt~9LH@*^`ej$3iS@-y6{5rs;@5(H#VD8*A
zIMl)!U)o<ijhHVmF|;=?8_e84H<P@dKa<PAT=-z7W=I!}uYI2i4fhwaXsvftK~Ru#
z%d{fKY09?it3^IG-ghxOAOFJ~jG^wU11AdA)-QdPiL#ATfk*49+J@+YzIibSN7s>g
zzSR=1HV9PKhL)Gy4kJ;8bbC}7{e+A$Cb8-km&yJMB7X2Q{~0|0i*r;;S@x>M7jsO%
z(t`gsr0aaWAjCpBXC=EOiHvTBoE%0cDhc1xS@}DW7!ri%5lnBUUgdRO`235xx<c*O
zW!5bImpjeye;^~1&()f*Um_-<QdilhmD^_rHXrUGqgVH-J__C3B1=4I5_Z4$kXMC)
zFwcJ>c1(cpwYs%bF(v7)m7;Fh|Gd#_r|){erp(IGgvu|Du$bi>eB8KC8_8{ln0Dt7
zryBae_-sX4kSJ<Qe4-3XiPHcLzMtUh^3{SLzFa+WX<R*@OLOQBB(v35c&;S;-7)@}
zdq1jSkk<(<nM3=|$MQV7anB*AgzjhJ%$^-%a`puC8B}<*_TcUHR_1!|7X0;h`DYw0
zQXTu_9)xPo%dhIDeXidn35|Zp5>aM3+0~B>>b)=gpr67*b>);)hy46@(etL{mRkKw
z5Mo`|Chk_TN55ldytDP$G&j%|$6LghXNGBbn#XTxSa`+ci+L4^f975tO%v$#>SUk!
zceZTpJGfz&pC_zpf0g%|<Ox#qt$&+slCJ%L+&AUPj7@FAx=NlN?O}v-63)%Tu5V+t
z6lX*?;IE-UD?u56ZhRX+OukozEfEY^4lRiVT}<55nJ{hAx$~1(BNRAB!pc=m1w({y
z-`x1X!)TT{Ld4KwjyiCDjd@Q(gg&h!?%0JSifF83GR&7Ea;Hvmd$D&`AIvS_=VADT
z4^sXD>)`?^=&^h*ZfMI#N(F?a^bd+=f8omZdJi85rp{;6yLP+W1Dm|=#HR6y9T-+J
zx`(|^h*3O4j;B;AP5m@1CFL;xd>5v}Ec0Qy;GjtVRSC^X_G!bqM(wp)NBQp~LH!!2
zgwUH$AKX~LUj8(mP;Gc$T}!B6>Wx_=`prg1@q9Y?a9vJ5)6?IRZ*?-1Yj2FzH46GT
zk*z6CDh$ezL&T(|$mkmCtOVSe#m!XJLg0K2{Y!}f)*>t%;3RyoExo20=(Nh~r{c%g
zBGB&NNhTJI>hBV(w4M%E&)SFbULcS~JH`N?>CLcgrOSt+1DvHBKk>`#TKoc?uE-*&
zGEge(PWtPtWVo(qcR;-=!mUOxpm~uO6=OZRHgVXZ8Kt^X93r9>tUQ{~4oRGx?DkJB
z8{wa7yvGIRfgq;Z;xOO3AEfM?-S=M^Cf+7ZQ&o0!9T^mUWcc;Sn%@rHcJpVT6^Afw
z$;Vu8c#d1&x@+>>NKC#&xX`UVh3^BuyB;~u=F}3zU48Os^c(uc4&BzG7Ta|Bip^1J
zm*uZY9j-5@9IzhGA<fiJ7KfX?=3E*Z7MTYR5@mOUS+yiJPt!of*TjXoB3bz3zPs8^
z&clMA=abb175!rL{Co}+MA~1nW7|wq3`rP@Vh6qLnUuX<R2JCNqnD$Y6)hN?*f<7q
z_l`&+1rNEb8x)I-Z~AB*mW@fKJ)RQ=g@jG4h~4wBOVJ?SA+N0U>pU&Fk*}X|4G*~U
z>{}`K^QDlYRUsbcIdraGON|jueq(I)sU!$lRpl3>xx&X4uxldzH~tXwLh<<!DZf(F
zaj6UWfnBjWt@ysqX$H;Vu{7J0^@!yw&v(r3WEh-Fp99i(q%MkQDvvkJ?yoZsF;)6W
zNzPTtu#h*`b9~A=S3e7T>$t;UXz5u(5<;_;;<FfCoqkmU<5IWsMr4!8sPJtXt&h=4
zLW1jV>DQj$1<9b5Pa<<7UDkYsK*bH}dM%u}8@1kCR`Ht-VWw#x2Rv`2)PLj+spL0^
z)fP@UfsZ2vipVprgmSY(c!R6*^nP&zP!jjQ_o%V>$GA?~3O^*8>2EOmi7$mm>&MEI
z@(of-)Nl?o+^ghIv=l77>(QT2)sNlsnYuo)oL0AVp*94&A(vA#?(nxP!wz)E{f#PN
zkV!;cnV`Myy7ua8%8I?s@!hBHM$1}kkax{b9CBng+OoP}26>r@El@^Hj<B|u!;(o)
zVeRadWg52=9`aiJ2XaQDGz85p^*v{Pzp`4cL(A2$nFc>grC*9Vx60?CXiRwbE%9jy
zd=MRbJoZ^Hl&6yVj)iXKQX+-C`Mk5IxC|okQ`MZove-NSO3`5wZ>y~RU}Fa>x!p`0
z3)SsU1Y=2kPQlLAnK4~-NmW!!9`G<`^}KX055Q?%>n!U)y~3s2={)`zD804tq}66v
zm;HIT#^LBWP$t{Kyoz&GRAg%-3=c2r9Ms<a`P0t+Ri(nK;{3_s`JHb-?6D`H`Ab=q
zJtO;eN(S2(z0*+J3>~^L8W`?I8(B`?(0`yrk%zw+W!_8H2x)J@g;n0RJji65Q{!7~
z?r^bUgW?7YgyswvpOkCnL~P!2_B;MzbIGb>Z8tbGd1dQYHjqU6SGQD_AKgIL!`4`M
zr|okSN00E$K&ZuAjvozRm0x~lHL)k9m(8zYb`AOxstCba`19x^n}7`;Z2+#D>;*Xt
zKyIaVqK{+VD}DWin0#~ox<*@NqOTp+IEiC$>Hp#`KuL#t@zVZNkc9I&Vha6AZdzxv
z|LJhecEqiT;}7xqtKVm|cr7h<x{N&~wfO^(leixh!-Zi}78AIR?WhsTdPQ{>1DHOo
z3f}2&w4CO0%Dh#~TlqW8aqh+@H(@FF1DBgE-!D9#v!E9ZTS5QnTUF5XiW=x{GV?Li
zP}a*!@um*gHTw=<Fx)y#RdD+Py~*sC1P_aXFD&1>Z5?+e?Q`EYSv?3U49va3x@`=E
zO!e^beO=?7H?Y($kF-Ia^%KBWYiWvcF=t{e9{h0UpQ+rC%<Qdxo_kL~>?H}R4X+hi
z3);y2l4-Q4vmLO?C(z!WG*P}=DV@EVDNUPT`gtG9^hfKGt&Z+fc-(pwhT?Vh^^#XX
zc9TQXl|YhFQ|3J>TN^F8AziHBhr_3{8i%PmS34#zQ!%8{KkQnAf7u2k#*m@M>W{dS
zsF$9|K83$C)4r8O`m-U_I$;E}Z_>MbZTjz?h;iKU2!jas<PTm^9ZN82v%tyrvIn;A
z@Iwf*5`6my4J2r&_O#Ts$0t#K1CzWWP9SY~Wx|^}a_<|GrHRu@*^XkDfD6`g(r!Fr
zN<`7=o+Z&X<Y2oKE3hgVFL@xz<^kxlr&RszYEf<G5!NN9k5oj6Xb+`!SP;c~^kV?@
z8D>mk2tlhVr?-JHZuOC`$06+5)rpTu@A`_*PfHfwefW*QjL&nC8~Yu77t-gKSa+X$
zLtQIbjogG*@grEx`YS{$UJdolu3qxUG9z}v$~Y6XMi%qfnd7Aic7{MRi*2ZXlR%(o
znS6)Q$)c9~1<x7O0_7sTH4a!GYLNZGbyQ7Hyvq2#QS!N6@AKnL6<tw^L8`(E#o#~J
zMP_wO`(jYx$C#G7#M2*`57~2N^c^dEzoq1SHoOv4efT361<I;Fe47t+-pt*UTd6;J
zdTX}7L^1dy&5p9ku1zz0jPxhh{Fx^={@t4@Ob}PxUg*^S)CWn*MX-*2)QY1|(Vm^R
zg5qCF+P6;O!op&pIh-~7@(~P^_|_>_*yH<_DO#psM4=1oE$<w=Z<>;Q@chC;^-%gb
zXi>g;%ivkbmZx7GE@v#}A&JIw*2c7OLyA_K$`+U1Fv%+cW~wjXsOn@oN&6=L8IFVM
zarR@9eM`u%o=<;{e#p8_KD>YHO61DoDVq(R@J5<}H}~<-5r>++;I>WkFAk5<hlM-}
z%g>U!Dn8Vvar+#EC>u6%ij$SB2uo~cLjDNb8k6g9USoS*hsi#UFxM0{G>5*+$UZRR
z7m_q^G5%WnsXoAv$9aUkDDA6<@&r3wo%dU=MrO_lO1xbn$q=w1EB)q7DzWEJ2y};F
zV&SMF4YM<QcX$3NT%f3yQ{Y-aswnE_LZT4|j;xL}lG;y$Y+LON=;lgg112;ufWg2O
z1K|%6B>r~{WehL}fQ+sU+y-(4ke*v096>7P05<{$$@~!@&|{^@&`$T5>7D7DR?>j7
zxxVS?cJKZFw{nSVh6~DJoc?j6Ox>qYNRXgkicUTdY>HA+fRBoqIsP>R3AkgZqRF|j
zhZHEVDDjF4cxBmrEm9P~S`J*v0+PVsV!kNaJuQd7#Q=qZ#19R^vH+Jza&Dp-S`-y8
zm5nO~P#DxE(`W$<uoEONKp&H9Op2lc!vQb`=P8!n84WbtopGW9+p0iD`#<#^@WZ*g
zef+=8dMS{zimsh0$8cgaASyHUHFyX#8j%VnTC1utbzmSOp%0V-(TZz&VB0`Y1A4&p
zrC@?O!=wNW`;k>G{ZWBo8W3e-bYd;L2WamY^S|E%OL5>RQNT_>8+`<T=0FO_Q393k
z@p=G%0<cs-+iEP>Tw}=;)$USV0D3GHMg(nZy?}}La%}@9H;>{yP3?Uk+3_IglAK_x
z<%&sSv<1k=&c{hS6^uP40)P;A832lmB>}#<|H-H>Od~=u;NaroYtH~}G9>}<5oQb!
ztBs8w7x#(^04lcz7#;mReX_3tOK5$UvFR8cl*trQ9I1{bC->{~)ZPc!Aj?{i5R6lV
zN~{332Bv>RjAW{VZqw-p166W63LYLQx99*J0P;*X6)A@?J;jh;Z9x^r(sZ;bwl)0)
z09;8w2IM@2q#z&jB@Oq~q!er<P51R6p@Gs(<r(b%lM;Ummcyy&8%xMx^24`C6iipg
z3$d~)x`xLf620mFX~<S$h{<53tzqrsVtybgq7IIL8(wRG#(>H>TowxiMbr`LtdeLt
z7)Wwoiw|j7OWTz;hn6=<d|AA$dTSf#%=_s8qc>1#X&YbYt{UdrgT%8GZFgzvP7ey~
zg>FGZv3O1@HG;0)f1otAt1@QyI{NGlq$(L&pf5m;c~6xDD@B5)0r7eCQIOH!4bXPF
zlWXiNsbxo{RK^Se&@b$sMm2a4KU{ndtwJ{(Lx8J7%Lp8+YB*--7j0my4J^0--S#OA
z<iaVL3S4JIt$!#a@OLhj0mM*)>E3`-4Qozb)_s3p`Kw%xm6#+&R1)q&+sRwzr-@y!
zKIENj`Cgy-_|a{p^3GFOEHrYZj9o{r=KHRpMa4jIQdyzFV|lQd&O-W;j<Js*Rx#*G
zuy_m&3ikL`vSu2f5g7r{waE-d067>^gsg>1Obh1YhXmwh9<qQTPm0}07bGFMkVU@`
zha?x=2Fz^5d})}Ks6<L2+z-M6->H|os!Q(lIlBblRsmfh#&XRh&&{H~NdcpVEal^_
z*Q~~#*5DXbMIzZWQgRQiDzFXEiD_6$PNaU3Wqd^p9f&-(7d0&2Q=B~5HQuRg*MDv2
z)Mi)Y!(2AA+NXJ(v);|7xj1No3~-bLiIH%c>2z$g>%DJQhUs>^)|F2@$FS#`m}|Qu
z<qHmQibp#CfLj}tpAHEJ?jYcH)Th`l&{Zga8OGOp?Con)>|d3GA#UmH;@U5j04Ddv
zc+(JPFBGUV)8D0Y5R@Fjg8&oR>7MG%mi+YMyrvaY(9k11NH$Fs3yfnx7o#KqiQ7+G
zGi+?sm?RgnWE$-WI>nKnY-Gn`+c>uYK+mnwQKMC0&!YHf0RS8s1K^h6ZN2GF81i4T
z8%c)8j|`6;Ssg_YM7Nj=V@;*4Ta*E_s3ioNWR;kBE#YyCR*}|I7Qk=J0edJwI=VJ0
zu0ck&|931GVA@iT#l#R`Ao&8gS`vcRh@LEMWE0?_A7iKy#FWmx*_d;H&n~GQkfyg|
z01em$Sl=azPVHMUsF;Ze%0>{#7_58zkSX_vv+OE9bRoQQqX=<-Nb>#pyQd!->Vnz%
zIkzP4TrW;D^Z~7e!`p937I`nMTvv>rcJC7u!T`#OdumKmyjlu+yH!FvCsE;~8ZNEy
zsSh~xZ+;Ip%P%Z*Rua~^Y^-W$LCr-gSmtN?8X*P`QVTw<COOnbF5TFuy;3>c(V0`6
z@&vg<sK!R)uk=SRU&F>R2`^Y$2;PmdPKaqn_YWaJx%KxeIQEzLnj@K=op{XNo-tSh
zqkU+5wImv5@xZ%)Ypx#tFD_DxyE+0EZ-ruBOd-IFpCrmpqzDed9ajrC%B+jnl5(%T
zu$MyKPe0&2Noi;llfIA)nNB+Q_bt(Qzy!2a)vPa8WY#w~id=hKKay$?%BuIZOb$U}
zI&0JDIg$5@-nO#OdJ)Q~A2);<J>a|Thty8;R@vGTgmF9~vsPur^6IqaLHcvq(z`b7
za+p_DY$<Ug^z*r4#1q*LB?@cy_w<jSGgE@8bEiqFJdq9H=+M1B;n4^8t!rHt$9=p~
zCyJ4tI*{aWFJMV3_&fE}XC!RM<M;P(Ichn|9N4)b@9{(5Ruc&upJo38!IMW6rza9j
z9l`;wJv(&O68wpQ|Lyt2`~@;z^~L!IO-Vr4{RUA891iNx4mPcZ!E3(VWzxlRY8F0O
z;^O6wzSEg1P9{v*#Jer;#W$KRdm+>IRn;y}UH+9cDXjN-@dcU9^yEewShzDtPm@oD
zeX9B~%_y(QU}(o0rVQuXi29r`!L6bA>SraTxoaA@v@P&gPDR=bZ*l&cvr1IeGx-p)
zRLK@;`7V|(L$;UXDfvu1v-#XY%eqUG^WQUy1Tb8U5X;GQ-?`-RuC#||!ABNLZ+xI_
zyP5;HTs{njMs;3RdCBQ7<cU^gZW@i(dCc2t^5j|l&Hzo*gm|1z(?H(WMM>`*dNLkq
zW@XxGQ{K>BY1Q-S+G;XpV}5}^`-eQdqvLN6Y4(lC*nUm<dsgL+!A<YD-q0rfpk4c{
zu738#-muZg(tR>}{`_#+j^8RU&jcf56`?4f?~$5x#QX*pZ)eJA<^)f&6I6u7&G85C
z_@8Z#PId(7<+6K_Nguy73{Gt-8_tkG-S4NYivqVnfWMsIE=3EOyR_MMJQm9}m0cFJ
za9%5E?CI9jh2g>N5#xs&xzZLt<6}E7oN5O)&`#=;OotdMb+dYvuyyv5Vw=4ZZ(&ln
zWo_(;c+HYvr7P9fb$wP4<W;MMLL^OX&argSZbq*eTCr<&7F%vl%N20?PE|2x$o#XV
zz15_lztW|};f<CLNv$Wk)4r4bvis*#NzPPZdDXcnrbTHCW`Ey2aAP27&#JTAl3zzm
z(Wx-k{JV((F;cF8v1IQNl=-Y$SECmhE#Ws5?C^kmn>T6G&i`skv-Tb8OuAKJ(BY?_
zeXhDV)vBUAVL;U{KVw$oUm0RT(%dHgH!^v`&$o_iTicbbFx!=#fD6TAhJJ3c{2d`}
z6MdGRrt(usc=$Q}e;`jg4CHSdTCz+5m}(|RJsoFQ^t>wDL@x)P&s`cX6+Bkj{rXY;
zBV^;lyx&Y)!&(W+;Y7!)I%WuKCQ>ZOn$dbjY^2UVu1mIB=jLCl07bQaFhf-3k5F-`
z$eQ!Xj(3pjlcfeWvgc<*7KsNIA;6A|jn#-qQfuyJLR+Pj0e2J0$D4bw1gLf^Me~8x
zo)6E<KU&iL>H;pE{K_XaUNV!+Ji9ji=&}zV{`fatm{<Jna7Gr=%r3d0E-iX8bYoI%
z=35wxQdS&ozM8<w15vGh$U(D>9`Fkj3-;g!YL-T*r;PO7g14`p24RQWTdrqR#CsVX
zB<d!gTVzBAOgMw3ld7r^t^a!~98?r7Y=v*p@G2}zXg&Q?mL_c?A2e|$qotb%<)CS#
zMp)ew{lXG_$0Z8TKw?y;8laT&quEl4nc>zjgF_i{7~@xwWd1Y}k)6dpg>bL<#+C-O
zlSPMV7<#%EDSk`h8y%Da=4Sd%&s_D)3@BjBvS;*Y)3h!34@?IHE_nM;$^%=fWwT{Q
zvVOyKQ%w&m<?oJ02PN+GXZZF;xK^Flpoywb!};Y*EOL3Nx${4eB_YKO?xC0@rwxhJ
zF8WC&YT!&W!Ds8%=@ZN@EVI$015V%EFf_lM$V~fIzv`T~BY!c04{Q*R=W)qiL!fbi
zPZAN6`E2cipC85adfCKk3C*xo)b-r=QCv7)RLKyYo~@rBoN`M37Fw|i|2C{JX~TD9
z&Z=!)`x4_?sZg`n{ApOh{7}?zeMd<sUF`Gs77S^Ptu~(LNsr3~@fJ%~vtN$QxMFZs
z_TE7K4TAJU)mQyRG4eoZb>pZ<l7ut(_<gL>v$=7()AA{CkqA9@+usdsVlqrq`3XmK
z#{L4ldLAsUF0S2zos?Azvmb)2T=`^{IMfaEeZOe<Hu9f$;*+`CKMBnUEEbme^x^^%
zQ@M*1nxJY$k7kYV9zTERyx`B`&V5bhyl-h9mGN0_HneiymUZ^|oVwU%J8Vnj_d#G4
zB4Efr`PCp@S>-MdPh|`N=YHRRT)x&%_+(c{By5-|9!ldj`;#F}ZYdDYn~_I=<i|_D
zw-j2t8NlnT#1ak<)%aS-dR4(3{%eevWNpNGs%+$*Iw#57dBpg8iAwe&I3u6-S>K~O
zozPF#B|UN9K@^?@#OP1voZ%b$Iy@T6VF44t`06pjeP@cj;-ecDBRK0M!%(IWh($kg
zj{PNnBwV(-Gu;uLC3suY+wL|t7h$$K^ikRAw{o3pb+U`ExW!rquXKKmA6?37KKFu+
z*)L(iC@q2<bl32vNqWh$ZXfaC*Y9cj7BrL^Ylf%GHvjBGDk`ZSiv$0A4fY)~NO>-)
zDtZ0(_@$=BstjKEB(Mi3y_(E^{*1RE-Ov2)?#)j|?8lW{PHMiAHUko*HtEs6trm<k
z5cfoQN8_dBisr!Oq}=bjHWF>ZFpnpnC7joJFDLzbM~1Yiq6{hgW-B`6?mlQ&ek~OB
zL;ZF<vW}sBHo{`0O)J##xtYih_F6s)n&n0EvvOy90^qD`e!lgZ>Wj1Qr+Lvo6t*)S
zO)rXv#6<8>z)t&W!rscAP{-WxWkaTS>=R^h$EA2;d^dHtS7t!kJk=vNS5)k((zOuE
z^jkuTy|9%3H(E-;FEE&j#Z`rcd98=0Yt_K_RAqR&UgNr<&}e-$r$yMsL<+&XmA!FK
z54~h%al{6kn?x`}Qo8;GvN`F&79kn>yt=j};(wr7e~_{zVH37|T$Vj_D~WVx`YcWF
zt|pJ$YLFgB_k(AIhj$Bbh@qtKw>w7|yyYwXm%SFP2j1DR$a@@W|6_oYC!7g^FNH0w
zmK8sX^0vsGFzhJ55>lBiUGm)K)@9b*=?Maj9%QKhcyi?N6-c=5+UuONHgI&c&?YIO
zz?D|O`4MRsFjcs+^A&sQC+m7{k9B;puxKgmrV@9-`+Ptl+<Mx1U&rJGnMe4w5+Htl
zOI<DL3m1DVocK~fJqeetHIMf(i`BzFns}8WVb+a);x6pYbbTn~I##>B?a8qwbRw{A
zw#R#sl)+$SRO^s=kkpm`;Q4g1;9v8<Wj;Q4r|$9Q%*x@0_!u9*bp~I<BFqcvUxThH
zguTjs?@f7po9X7p*lVyJ&oOvM0nKrxrO_4?g02hcnJL1tfH@ta<JOe;g+ZXDZ@vAY
zT&HDXeEOShW3{l7`}fb`yB;(7ofT|j+04M&aOK-SMhqoGo*hd|#|%SyUW!SFj>sKg
zEEj~`1JYT7U)@JvtvdI&ZMCHI?}|9u$XPSo|FIhi<eSK&Am#%9%wF_q@7Y=YrWgyz
z_$z;DuA=z)Re#!al!4v^lhE&ihb6L=bQRt7@!#Jr9hfKIR!r%;!jx54Yji)m^SDNR
zA=MML7_69k(rf9vur!IPqxszY`vFWjV&+xjI}H=_U!<7%(9_DqPeudvL<P5xX%m_*
ziI<62x$JeNt}g;YU8rRRgrpm8gghEl+F5&K;M2m*r5;S651>xcZGNvm@o0hb!I>(2
zesV!L+w%9s+p#PPEru-KF;3^88~(CjmZ~w~{>-GI!+<fhjtax>`-uZ9+qV67mmy`M
z`cp&eLu@?230_Zg!nE7;spQ-FrOgr}-CrlRvO&UhsnQ}=aRhbP_#5{|>!U_>>@#Nx
z#@#)8hUzpwXe%OBjLTd$5l4LWAmq8sZYoZ8gxGwkjjczOkUSQT+1C2xacAS=dUN)t
zM58OTlI@x6jz$ps!*Ogwn+^9X;ZFnkKmG%qSSgOZd6$SlSXQcj%97M!TzL(keBpnp
zzqmeMo(YiuWWmC)D)~_*Om?>yL5RXXua=ViQDon%>?7pz%Z@v+e+ADe(-%sjG{E|~
z`813Bw^l}ct-(L~IeXS&9T`OdwQV%oOWQHMsIM|nwk*J7I^A>HJN?zCd70PSY33?_
zQfz&=M1IdCor;_N<#F4~MU0Dqp8<ERvbmI3ll}K+a;LH-c|PmyliTg6RHx!iVs-~w
zZViG>>j^o%d(*N{f~m|#A;O}KE-~<XWsqL|?UtnGn<~VQt<l>fx-pkB54r^;&9kld
z9ou8^GODpD@ic~?xCbOk7^&vhsMg=4&8epJxv1@#*`CM!n}&<u)4I}BAF`2A5cuts
z{0e{0iu4FMer2f$8;b21EE{boTeCPvek)vR)?|M(KCkZjrAZ)|{DnT+wRyg0#-ppi
z#Hy%8HCWfgs7zWepH#xdXt+RtA=shduV>V*R?17n@N25v1=vHIRgMJrg&j+eM-Tpu
z6ygSY{ilCa8_~$|j1t*c=xn^QKlF(6$OL&u9al)47xk-2zz4g>eX*%VnBR&0wO2{#
zXXoh6pch|kesV5uh;uqCpG2vkj$KS?{(2wu#C>u<Fp4+$mNi1dozKh;&tUl)HJIcy
zej1)lZbxGIWzXT6=Rts0Ly}9>hwDl1;<Qzn<kGeJjIXU0ed(8X*IM$k(zdmv*N9hM
zbs|q>B%F7I-W0I$yKxKOXaA4{%zSID;Yo#}MM~IQb0+7Y;)<}snmeyivtN9;XT`#(
zzPFx#sabeD_Kd;W@$*zl*TmNz-HK0ryB^#Vzl|Y#De0HDfx$7}+Dz_<QrxQACA2iv
zO)gb)z9+w=>|6224(Yw{v?y9P<)?;|knru*-z!+uvtf91y5203u8oiKC0?7&?@YF$
z6y5Mpd{UkGsl2IJhx3~^VzRE{BLnRtvcHp~-4IcMD9L$MfhA(*2>iuVtt9P6l#ZTi
z3<?M>Y3Sn}hYdLJ_aBJS9)}cfg_)qqAFgY#6#o(cQbrOTRRV4LJ#9H?83yc5`~W!S
zP0$q20yINQ(zHwgE!T+hafH;U2S)-KB(%7A*aIj)UU~cr%mV<$AcZk)T8}dfn6{mW
z4qYN{B#)BDAXSDv1%a4PaTJJM-RnT~;T|JXQA1)>H;Vvg9T|{;0ZDC;6sRbTBaiu1
z3d<dNJLnWAMNJF>m?0)wFrXl-U;>1?0)QFq97CpfjAiD*gUhgB0L81*j|1~1gQsG8
z=|e8YK?Er(k_{lYL<&f;16UD1)n0&P3$$5PmrUI$v!p;&k{SRJl`^q52oqrr$~8S5
zA|KNRQrl5Opyml$9UapE<Had}ifdvz36c_IGBJuUWd%8011T)j^TtLbJ<(aJ<bO?A
z5RphFaJwWq2uG-6#yp!R`e^}(j%|uq_T!u(dOsvNWg@`C0LralX6;m}ep*wJWc@gT
zk^zLSD{aRY$Wt|-TT;{lK+FrCilh$M*HrkQVyz6o-R^1m)S4_rf$P|h^FAS;4oAI3
zj3UB4q>M>owsjV=8nMSkOQdNvl$mKYaB|A5sWe$q)IW3Tr@PvcTIxiU-*2Fzn!sPj
zB3mrgVRzeup7v%jkb=IHqOEm8szMDOaPF!NfuLZxuDt1}xWI^yr=e^w7cY=6X(1&0
zkBcH{=K;(z<P6JCjG|T1RU3kSmiwRZ4F?V1ru78Fz|RQf#Y#gQnI1a=BsYgdmC6Of
z!aW+nMtBw#7#(*qkt7U3bcz~+0s-Bgjuz}DhBQX2jvt}#1iTs13S+7iEJXnC`u4#z
zQv4VL%z7Ljwoyi@4ROT-P3j@~;&Bq$;{B=g<J00H;KPsfV9&t-?d1E+LoB`Y)Z#;A
zrETDRLGh@mNTxQ>5%6A7(1Y^I!%U44L=c!fXai*$pr;C=Pj8gPG6N~<mB&gHF*TAJ
zsG$R3mV2at{%<u!gN#*nPcKpqE7!|hEPi9Njs3Xk49mh^YYk+?og1j5ZCwo#U(&1^
zJS0k$KGHu4U3bh)@rPwc-V*3VVvC^-1FzrDwqErqPVl}^*TGKwIO{5Q#%y2|S*;D9
zTjl1OYmDe#4a^o;7%f9=XMlXuClsq>z$g-Iz%s<uDHVeR1^W?E<Ng79Gh>cSavO>N
zCUQtor$e9zpnvqaqw*&huxT(>5wN;NDww2<{xb(0XF6A&Ghp`;PdZri%8szd_knZh
zZbsXI%c10hTrT>+;2p1tPFH3WY$JMf1CK1#TXA<1PnFbZ;hiQ|)GDVO$!nRzd3pX5
zkdz?!k}~ctH2bko3ZX*r0YWb?%!1`n8&REQ&vN*UExr`!rdz!eXl#+JQ+S^^fmuO&
zN*)CbaV7Bs`FQwtF$%c!1Kkb<6&QFK?V)&K8q>=O0V^LH3lO9t4Y6p^EE&-oBRE+<
zVy4=Mkbf3)Q3ayh)ZMphC_^neegsH`XMAH|6j~@{d2iZClh5{dQh$0!>gP&QYW@<9
z055=tk<>KwdQ6&loM#{^27t4vLKQ=bmrRgA&l<Y56K1SnlK&EzQb7OJvZn`aMBWZr
z$(tCrc0sV30)QSJ&ZADu(Ya{|_U|ZZe(12k&O|mA4-y2vAV=2#(A-EDtV=E`816}j
zP>GI&AdsqI_f-2=fgAp{Jo&?FT2FuRYftgs2TUa5yLyXL$Q!`eh&|_m2tdrS7o&0~
z7&0(>0Ss(-4ERTJ0_3N?Oe7^)2Uy5O5?pf?z``id=^Bd}YSBBB(Z7lPEv^ryrbU>#
zrM;A058a}ms9!@{LF0p<f~q6*lWr=9{Rg|X6W=Mi9r0Cb>?@KQqkpyE?rAC|SR;ow
zg69}o2N8~%h{>`mm8x$M1~M;t?&#%-V%Ob#WLJ`@H|k$6GfoZbd2Wa)v`oH#NV#j(
zM7kjBx1hOuTpr}q9M2=SBAKF>R8R`v<2rv4(S0^O+7}KQ(tFfh8~tD}oac43xXra&
zf&Zi+gp1RW)u6jUc5mMy5BHKo$HQhLTBjHc4qd5V{_{1B#2)R<a>i1%AR!RZpI7?c
z0zC-vSL+SkCD}$Ezh<DerreBj@ckaGiLgqzSDR0G|IL=A+qp(}@70sy^U&!KZiz=>
zD~<0>8CS%oHyM8J>~46x_(w$QYo)k^&VUZ)r`48M49-fSUNl%?1=`7`<rU?*-D3=P
zT<S|o+CtfRE18p#qtNfn2zcqr{`v7KhE6fUHc?nzL*+o+@Wdbzf^H~w-rGW~MOpF`
z9i&!zdX4xE`TY@PDj05g$Sf$Y#z_*pQ~+D!TvwC6L6dL`^nGHICg}9ukz>I5<n?Vb
zo<tq#k@GGV#w}gRUQ?GZd<#!>-ph6HOXHzepx1b_lyT`{4fb`Vkv4Pm4^xBQnX?g`
z`3)rnqqJ8~660~kQ&yWMxf@yCO^muSz^-3^=}wu0u?nn-9yJ#@$Lo@KO%c+pGEhEV
z=ew@>kvTE0C7dmr>l=q|$LQP?_)3p$nqfVQ=Pt*Z*JK?)f4MuYq;hSs-oSGg0-)jF
zA{$5Ka2CJBjNoG8<2a$aHMxPC(%xFW2^%lNO06%ZZ;H6ShYmG;P@E3+dE{Y>0JU1N
z(u)rZi=!9V7uS=-);~>9?MwZBE^a3pNjIp(Ru_VJc}*ZD4}*K&0Zd!Nu+4%}j;RU{
zRT?Mm#qNKv%PSZ7*@75P!R(Xjnq517GKh@T*;?BhC$a0`ahz4t24AmX!H(6oiCqB8
zX_>R!kRgZ6ygVv>*jK>{8j<JKD)K)0DrV-a>bag)UFy`vGITP<<`m^T4HcG2C=_N7
z3U2cfGO@LaNwc{}ZRx%HUNFCw1elQ_CeWNe(27+P15M?Yio_;6oC#f>!mp*2j3ImL
z@_z<Q99&*TA3vs2r>~ui7*7tvS-tQ_f5kV!EWIx@SAOb=-49!Gs}?Q1`HH}(2Gs_R
zM9xl$F%Ks5zNquuTcj*|S#*#4Z=S-m+6KPcg_E*uH@HOabyKdtpP}d=y5i5L&3lja
z+!-ccsf_pjuIkO0sA21@(%GBQ)&gL($8>R)Y;K{*J25fa_K!x7+}WVNESdfsF|6iq
z`VM(|>_ud;+mHW!KOrtH;tpnTo2RQSt&?Q*jzVfKvHC&<Su57ELs;i!rYTwOYVgdW
zzjA$q<eW}^nBmD(Z&MG4fAE~DxdMgD7E`w22Id7`&damEv1mQ8L2ES63G;@|3hU8#
zc*&U%KWx_c89(jitsh!fCJ@N26o3yf`@46FHR6sc)G9Z=u(Xm?LO7?kbwYWP%3iaO
z&XT>3*rRNs?RX_vAqjcBbivxruRGGT^7GqTnN;=##5?Cvb$Fjpx>19b$^05R`Uu8&
zmKxuc_fx4N<7*{#GrB2g))sF&(?>OUoF}_RSE}2}c9xM<{0-tm?mSyNLMwa^Q!8&C
zK#f;~I2ARqpwOVs1J&WgHTKAVLA@Q1JpV#AnX3ssm;{EAY4j>S_d(`-E^S>gwR=<L
z@@IDOM7b@m`Zp0<0e1ZHHndi9Ylk!;w`Ii=;rE*=9&~q<8|g-qb(X&y;>x&x`Pscu
zaXL@+^-4g<$bnViz-9pLOpUy;m3{NpBN<PueC!AQ!xL4NxRy3~Q?q*cX%ZG5OB3Yp
zz}57UGf1!uSXiGxzkXTUffzN(li1KCYYSjqBVy_M9TBwW)g6x=R(H)3WPW5T^i=&T
ztuwu!|F}7P@Oy7<el8Lx6C1j5_W>`!ho66N=OtBSxM0^r2$g37JAL48HngFelV`$D
zuika_cm7J-+^=N$<z>w)p^U}Y<CY$k|D)(E!<zcvFg~ONDP<_5OBg9FHA1ANOBw-b
zkdDzJAahI_86BesA}t|EgCj;al2Rhl<^O+vuXx8faK6`duJb(i{rR-~UAZ2fFDUVV
z6!rZ~R-YvqWR|Mj3EYfoX~rJj4>I;kdwR!e00u`N?=7k5&r<dS2inoCNapDg>D<Sm
zp6FQ<kFB<IIreVq?=3Een@O<~QTni+Eco%taw0>Ds}C|~<!QBR)z@e($T7WL?N+kR
zXq48b#^a8EKCa1+8~Lr0``ri+4X}f&zeo5X>kG}%f1AJ;CAL+i=#qDt<4PfrH_MdE
z4NaxXH_ZwE3?~`Z-JPuZB<YDvuxT?HG9`*Ou0!Sz8)WYmKVX7inS_^mnml~rKWzV}
z+%B;gp_fbL+E=*j9!AQE^<G(i`pXNMHL+-1e0!F=8_bbZxWHc`1-=fNdtfBhO+NL$
z)a{4%h<uv0$?Kgib9`f@z>}yOW7RFfmfDGSBkRH>@bR0bd0iZ$ME*HbvWwTqHjI?c
zXfUfm|C~PvOJO0%FDyUhGyj}F#=Sw*G~RRw^q{+?syL}Ak8L%2J}pWNgHYl);M}4!
z-wbVy-0PptauH&-k*b_YB(pWORxgLX)7oanE&3Wij%fRa(ExR_otAusI7n?wym(PG
zv=Lb1P#m4x;O~L5K|QRn>ffvnqEmmXp>wT0JkzdKyi5H?AuVr7>Tq^SeM8=;LKhZX
zQ7gT)fCz0O=4W1i|Hgx1X+Wq5`tS6Imb+XZMYBThX<5PKrfj$mM0eX%xhf@i!zp69
z*D*sV=C`9NmZB=IcAc(>z?6XA9<70m)@lzwbWI>z7U^PIOR-mNbBQ^@y1fh^zdzT5
z5N$|ulA%#PCB(R!E6mNRBSp?*UUTcq@!+0`K7FEZuxN(GmD!5!_3Dc27w^fb#cd#>
zJf|TLDk@i+a}#N;vTxx%1;jd}ShmOZ^RsgPSZ!;(y3OXc*HV&Mgl&7K^7H(om3DtM
z!`Q+)P9dizXN%+_zL04P)uX2?3g-36gT$RwSuZ8&8PX37)Ni^jCK`~4_f`vA@|WfD
zB$egeAl^-2Is<52x!zYsH?Mv9UA)8(m2fnZH;^&re$nW<)7Sa9&GWaUkhl4kb|SI#
z&T_e#WmwwTK6UGK^$Uv1j`-ii5z-&v#+8c9|9lg*jmQ;8cn7^3z8ckYoF0^{$(3-~
zw>!1B7HlKFy$QS?(das@tbQe@nIEl}Wlk`X(Y1h+wxP$~%Yku+O<!!!SA?Ndq+B~3
z`YgYs_GvK7UgLM4YdtvF$xd{Y0{3}M`8}&)S(Ae8$<8gNP(&l`#qp7=>&w-{_XJ{0
z3jOE0_RLE}jx=|>zUatI*T1T{JFjTJXV!Rrzv?w4g0IdcAaU??2R-85j8lFzr!yUj
zPNL3yXcT>DW~g(>!!=nu{J8CLQitK}v6;{N9A<*c1$yxmOI5}VYna>P4Ii!hhiIS0
z&{oZG3Cs76*)OVl+Wq9|JkZT^H&zO1KEjFHSU+n>is$Fbnax|*ol0$jLm6MYIUP~A
zcSnuoArG;1#esrM?(L>E_|_be_$X1hJ;uvg5~XmV{z{aXt$Y<leYw`|sx#v-T#$8}
z6>wAsEOK?Ugj6l=G=$y@40FTkI(d8jWg|!xb2z7?9VmCbW(HJ4MmMzL$$<Pim?%w3
zdi0q>U-M^)y{YZ9EQYCf_HN8$Qzaj4LV~G(Kl^>BN^5Q5Zc{>X<3xR8Db{}X{xHBM
zmNXIj+@tCuz94vJ8uioT8bwI;P4h&WbFy!9DWqrg4RL+CM!TbX7~f<E59*#Dx7?7a
ztXp1leU6`0F29pc!cY`WOs}r_tK>|Q`QYa#KR#_3ZbVw{c-$CL_GZ_)-{WJ=<SS<3
zX>YD`YpB;J-$3TN$#=g%TbRAHNEMu`)Lb5NmJ<`8B|fIp@$SS76FqvZv=(OD&AdIg
zb}jbwM_US_q1-J)(2c24n|@$~74d!I)zo2qL!%1vyRIn9u(@e2<eR+Kg621#Ws?m<
zS2D!@>yL;ho`OQkX%C*m5w4P@5yiu>-Y&l`_OJ>oh3-dVjIlZEx7&P=5OcM77D~2R
z*{g(gEU)H0+d8QgYPXE186WJ0?CwS!7Ff`Zipxyor)=E63aniDgIIWPKf7PoH)lq$
zRTW`d@b!3Uv2l^b*`GZmzjnCSUgDsAvTw`QIG*0OAD_IgpKc{I&lqnp#Ko`RYvteg
z;f?#33KD+yL89}jTP+oJ@se2j=kH~O7hNin+y!j!3c8;zh`I0xb}25oHMMj<50Y=_
zcKOPM-%UTx;$?q%oy*_+$s-cgUg0{w+pYHgVkuzv!vfb<OHG}MaJT&QX?0D1q~ISI
zm0N6P-VaM!<Vm&p?hzzlZJOU`G@CvT{?46KdbGg=t$nSA5fwu*v<Qd>SfbJz3WDI;
zW~tc~44tC?PM}hBcr&+}SD=@(etl}LI+pp)ZXHYv#)WOv$0%tC&IjMc<&c?r>jt->
zkvL)G@-frJ>bFfjAKds#oeEH^Qxu&tITS%_NjxtXCHJXL%|jtRA|GA#>DibZ3%|?U
zlYGkmx5RY1N|M3@q8Qe1j+>~_E)4x7pMPGKWq5lehXhV!)du!6PS#QV%>%80AL;95
zgi=_kP^E%yv4!q89i*&_>w)mz*bAMwTp7D$S>truZY0y>v1n=)Y~OZDf<#>etUcjf
zJq*-o>nmTYwU`xgLU@ua4;m2hUCe5(Q|KYHxd6)nYDF;%yup&_I`mY{wA36nA@1Jm
zC0dddNN6@>d}QXmy!#OD9lLZaV87|K{imAH>`1<229-kb<&R{pTe+`4I2+E$BIX|u
z)BLmUV<#YO_4x>YD@h=ID&cyvYiL&7^q5}sY!5vo-6x_%9GDsDPL;O*jmpe%Ouunm
zV*LSS&rH>gbenKcsHbJrKZ!JDb+L(jq`*LTyIKeXc2MfTOsz+laHxq{#H4r4n(fs}
zV{p~nm#6!Mv0Giyg^sn46O0j2V^asRYGxjDKfYAMU+vb{26L72urzS;9c<5k@eh0H
zaz7Z)y>W7<@oukghnU`#2Fp~#-EwX2=Syin0xv$2*S=g0h3BRbhH4Ug%y9SJv!n_r
zV~wNR0RWj)Nf9OezE3}CQH8_LUdI(_TdVPx^VFuU(7s^~w+K(O)_rgOVdFN3B!uCB
zy88|FK#cv!zCX2f#M(Eq!F=r&i%`-6SouV0T-KN8UsF`d<UA@CMM&+UW{u6{+^YIH
ziM-yi2v5b>1^no)R#Ect_FDDB`3pRj-Pf&m+~^RS#>nRWeYT=+ywGzsnUFr|aKry7
zKnDMCt>LAsTY=pEWR}(B=3a>Km2?HJ%t~E7B=aRpKDsoQS5ysN^NM&(I+I^B(C2q}
zNmd$9c3ydj6Y~z)D7?n$zOP6RuYzB=k(8y60)h6SIh>+Vc(?2dC6_3}qUziGK$Gw6
zUg|WjWL2J1Dvx$=5ayWbN3?Y-W)B`-8*nCh<~`_MyD`|*9=!6wef7)q)=Tn=u)n0P
zTcxJCmRPW1<9I{Jub%X2(E((TXX+k~_GRt+Vc%DxYJ13;(jXs;zCW6<<Y?c`(Com<
z08v*%XW9gR8hOT)Nbf^L|DLG9tUyqaB-v#%Ns(Yw;#`et?Vt2`<|=f0N$H@S8AzHS
zBs`6(X0=`DQ0vh==Ya`hBu}(OnB${bK^DIrw4<*%LwZ64hVD@k@zQt(#wqQxx%%CN
zsjA>zxLtvM{N3{JzoixlPAcXWBt^*z+EtUJ&x>JVS_^<RXj`J-j?BN`6|8^xezLNY
z;>%gv&5VRN3x6J)8f`=*=ou&@n&YZnZKWR=gp5&(`(ZupfCR4JdC`s{G4IZFGE$E~
zl~+Lqkg}Z|sLS9_#qCKVsh~H%4pl%*<GIeG;`Z{X0BKr2RsZlmazvbX5n6%4mLA8W
zj88`>f_xR_0(!x=0FBxap+gdc83lvvP$A<=Qq2Ex5%L*$BYo8{z$6i5u$7EZ6yyPN
z#red&%r3I{Z6M@YBvlM3`-sLr!U28)xy)(tC>H1elgpeHA`L-1I7t36J~}xJO5oee
zMqe1M4jR)YEXxlu1d&8*Os6t{q&rUwkpQZ?nBed~*zz`Tr+(XD$K;GsK-u?eM+3(U
zq=Wx~88l_a?yN7PQX@|R6Bg~EVt)3K#zZ49FFh}ezW6VzYrx_HAfAC?wjJ`Hcq$06
z3j()6Rj&v4FS^ttxcLQx_G4IcK+Mip<6~papnpIG8k0}B0AL~d0L-==LP17>oD#&N
ztky21AVUcP!^cr!0OvxuxG%(DEI6O2k5U#Rnf@WNV+nwKD@{j+=!t~j3DEkd#redr
zU~o>YqICZC7(w<G!g4Dal>->=05u&Rb)rY`Uj~sk%$b0!tFttq_)tAe8^r7azc#QJ
z2ZD{nz*Er3w#R>jg94S+)!Fo<^8@lhtV5{M9j)G{P39o$!YmYT@F)PT4j_jzLq|6i
z-$wUBx6na_t5U3*FR}s3^tAzfM{24QcZM8=7jI-f5LU$d0Z*IiI}MPbbvH=5#KZO2
zz16_;zzI2BrO=N)Q1#Zh2!l3LF^#|V)fTts5eJo`U)W_76w~8CBpD4n<}!E?%$cVh
zYyeWgLW=NjrR5Ci!~OKf4D5l(a0!6m)_%-Jh-1bv|H`*pk5VUX0hrTb02GAqPV@>8
zyGFc7(F`sbyR!u_uipZpRAP3>Nf8Dr9?QKLh`DhQ`$f!ZP9zjuyoEekM)@lC+>`@Y
zYid^zG~Y)?KNk-C0<m7ElOh-t@EB^6m`6T9747{8qz=p{Y#>ZgQjmDeMo!7QqqvO#
zDV-Dn+ZQy+6P^0{Y+4mInj}>(DS$1G)VmX<7NJS)dUq?4Snx6P-IHPwHOrG;%ZZWU
zf!p0r8%AfP?n6s%S>PH?b$nKR(ypYMKbmQqUw!If>gK*_?%NXI*qR@%)#eGT#wyE%
zYMNv~#5SMFF@Mtf#0epSqhH@qf0Zk<l`UgPYHpeGg4BLGqv0u&es*qsWZ=5S<Y_T!
z6hbEz^lwE|CX5$YYp`aKL^7Z5y+~?g_k>B8+GaDnef9MrGrzg;7Wzf}FO))$OceTX
zf3=ZTnz^p`RdlcQR5zu@sGddzq-N@m-?|Rco_14&)+ejEMd7KAtii|jq)A`xQSm3s
zYfZ^tMRfYLf8HuJ$BZs<CF^npRAVhRNt&4<wGn;6eQs?ZxVhw~F8hL2#cQ8rl%LE(
zTJV!8UgyOFMW@Aw){sRghRI2M5iRzD)Uy=$o@4dYCf8BK*ghsjd(qLrc2=WK%bm$U
zgQd3no}UUuk_`Bw(fD^Qt|d;!);yVe<M%7IZYM6MwLLFN1ksgVGX7O^$2&F^uP`_r
zflG#=30vv^aP2FnMfugyY)s?GJWWa<eQyvBZYk#Y6azM}OGPL`ifX|3QGn-@zTbfO
z5m7X!xIwmuIAt5t$G#7!?>^8zmq6YP2jqIxa&|o6L5Wp6yXzv&wn;Cwqg9ViHDA0b
zUU(s@IQYW&LQWdHNWHZ4m+xw@SGOLqD?#!)X*8lQmD+XXV;6e=6D0*7%nTqsp*yIj
z9=;KrCpc^dF8joTYJJ0zhKRvBZoZYigIPO9Y*#b?^ls*@>u#uQ9qD#Q&c_C)(@)fM
zby5AAFB1Cm&vAjgtJ*N3w-6`(T-DzVt&iS{tN+nXQaF?@4=O9T<_^|)O_*-eIsR3Y
z8u*0YkN;^UNV7kI?JszZGx(rVhdLK@A!QYkB)2hFK2uApP`_B9z~+9^%<<bhgILM`
z`e*~4X~LvJ+xVz2DESvkCZ=L#{K~Gj6Q{sI*)lp9@$V87TZ?KsX&BaM{~cY)a{7bz
zUbuF>`qwy8RPJfrW}h0@NqJDYAN6b6LDI;EY|mi9F{(DSf6dz`j;WkWeUYc$|LAsq
zzvp;`jQ#D#Em#>!Ldrv@U{*GC<}Iz>!Q2P1LLM|-mrs`}P*rgNsX&(&o?V6StxI!+
zNJHikyktsJRIl1JUm$-n58<m-D|xp9Cal=?1BDz<rB#myj|M&u{)WU?PJ50oA^(V7
zO*gy965x1^vv!%1gdP4grY5#%%YeL>RFp8kWPBEH8ufnnQy5BBBa8!(Z{g8q0bG~?
z<5h;-U<>cLN8jq$lwweH{{#7}h_2xtKDuu60~s$>srn*NFV9tt&cQ98%)lpQuO85O
zN{!yBpBEN8{+E_w*XlWF2l^#q-Y2p1jR&9F1Tnv)nXlc*Mk1%er1G7XqIb|uavGab
z0%E@?9bamG@YC-&f{aL&j!_0UkYbG6SsbYH0|qL&HoV?luVqSxrVn&>jkxOlc6#}v
ztN3p70P}^!>*9<+dP2yaneeWOh|YJd0sGyy&vg8I^MD>|ve33YpwXqd^{wn7ZRETc
zX_B?`?ePfN7Qpp$Wqh&MwbnMG6nm#7$vt`Uf1qNXnT9}yZn{4cpQZU(RJ=al)Ulse
z9~y3VBYpeRZlU&a=Gw;ZYTk|L(iIg2MVedje;N@xW;(kvRS>~VTsfRxO?{w$(WIXb
z+HBcM91Zw$upc;9RUWl~mNQpavqDFIPon>MZx3gFq_<T12SzPUuuUbbYlF4KGddRC
zKd-=3h!EzwhDk(DvRnF?SEXQ&l$MHVmeYC_O|vE4s*XZct;iblvIvu`L+C?7>l$?p
zHP~cu3`VG*O~NE~p=!a@=;6fGqfys>)MeYoTz1MNLroRekBTKFn9J;o%6o5oU{{l)
z4+v5QVHL>7X%~mO$&BT~0eM)O#puQ{GRd~{B8#*_TT>?g;xP+%zS7SC^|c2|T>GX}
zqBs^IVwo9`4EMEKey`MoYQvKydW}Y*Pr^tXf*w(bMS20rZ&ZptLH#)?O1d}LW9Z+N
zA{i&wO!@L#zwPactu~;F1?&F?=OBL54YpmUA9a1^<*k_zXArziSHR=%9OxYJhhc;L
zQpwWK-YOjZ)Y+E$_geG7r%cQ`q4%9HuNmPiL_Hxh-la@kmMrgQTfF$&CXP4ogfT~U
zN#S?<sFz3A&CE@HmMhAD{ws*wy4m*vU-+~H{oxHCOODEw_rBIE!Y4UtN~H%#it;{<
z;)~<{!6p=z%1T*VJ-vIM$NHKgwP^UNj>X}x2NKhX>8ah1Ze0(4umtkWzJcQ=r|`3!
z_tW<fgJ@;n_%`K~mrZwl+)7%JzArOGP_AZkgv=ReA3@Dsf?`V}F$XPR0AU_;xALwl
zq>$UVToMs)p3{+}e7331+{YJ5z4b@rv~rM}KFrl1vN2=~@jM-IXRW588U0ZCM!DTM
z{;mYZ`6-o)By7BA<(KH??0wqkY{c(23Bi(-Qumy;&mm1%Yt$4IWv6j;@xo%6T7o75
zPy5Tq1cMo_-FqmCtlH~ucXl~X!b#m#_ML>Al2tf+5U<@O*o#I@O<Y81CXe`qCew#5
z&KN|?O$QQUIN@X8{Pc9e``SM$r+dC>Rxz#9O90Dy(=&J^&2wNDW%4{+uvufC*W-)#
zqyb^u1PU0*Jo|hD^FM12OzYbmq4Ycv@2pX{`r;;748bz)5C!b_wbYh(zKrIJ{>3YT
ze$^y%zSUTC{o$nA_1-{nl4LW0rL2vpv<}fD<ndD(PV6|<G`o*2mTe6v*$asMy+Xce
z2DdAlox`zwvh^{07vg)Mf&7aNOV?J_&LO;y?nj87HP_w#MDI$35gN+8t2r}){?Ope
zm+rg;RY3$K=$9<^4S7xe9oRfGfZ250-h0jns0@##Ob0uwBff8B(GN#Fl0(dNL^&!Y
z`<_;r6%<z$dnuJ|UpI{0mJVkPnE@}t7gN{1k}JzC?pOFb)HL}r;?cE-*0x`Zy;R33
z(spq0^wyD>C%UcEZAxjyNrQvk_su)w1$A1xGivKmG?721eoYr&($lT~gJ^$koJeRH
zUAG=~6nO(U3k8RtpKZhVW-Ig-pH(TnGHIJV>Mk!9t^d%nfH;nqx4CZ_9Vto-*Y8%q
z2HU*%#O1b&LDyjwg-)V>Yi_g)J$Kz&CZzRLg0&l)DgTQ7=DD0Hb54mbSSBIGND~D-
zO_6maO_z#a?ov^&E4-<i6`yH%`?E>zRYyG@k`!3oO@!p+%Cj_vGz@S54`fVH+BDQK
z+55^pdh@Nwg>l1MHhCkJEAoK*T@t^)P?^lHqL!cxC3O#uJ-oBe%@2P-e!F1rp*|_-
zt3gL3pFCLVisJjmoWpM{r%$9GoC0@juzt+C$7aI%8*$9~{;A2?n7ZJ|G+ROuBBMZk
z_^32t!6>3`A(5S=ZENcwyXl8IcR@?bsPx8Z#S>n^U4F6G1x21OP+q>vIRg1KMP(HM
z=g*`Dm_!cs>VN!w5X3e9YVqp^jTEHPbtrv(j67d=9g)fU!zvCYGjU&aH6D!mUKt&Y
zbC%PLlUg;7fQpRpBD&c!9J*n<Hw%dZNvAAn+CT5WR(<&2XyUiq-ia64`Qn~82r@Fj
zX6EfIPy1aLlPQnRa1Qee%C-f18>o^7wwB{NwO0)5l`N(OV-0Fg#JOe52`OmcdgTok
zoQ?buX7#9N8TTVg6-1c#?yM<d8vi=$tSU0IBTFMTjkaWMMV~77iYzrf<Vl&YbTtIW
zaI&;*)gvb3_Z>&M7bB-E(rlN01w8&DT~f=r{54s6nCfzV=~r_?6aVSba{fvx)AT!y
z?amJfU8O=?;kUW*b~sQC$$i~yGFmF3if2*<qoOgEb*yc#4|ZNkdZxeg>3d-5!E|2c
z{^&<Xws&MZrPWu0$E;}%U7TwE+>0sM6CLkn@#%Cg&EgNu7~b-KXDk^B!pf#>nH_$d
zK@Ya4$tC3fbuCX46Jhn1`sKpT=)ks)4rNs8I#lNF1L!(vPW{Fg0oVhnJ28yEzhs+e
z*ONF6T(|Ezic6j?^absh89By36tM3}R^1L*4z4JXvua*{b!cF2mB~%r|Kn4oNZ*$S
zQaFcmXyo_7<TfTRH!a<kWn=1a`7}bISA<`W&{i<-;HC?2bS6hqdoX(}Ui9uRKg*hp
z=!@eNbA}IP4NTjJ;h3nA-?7Q}(CBQ@6}5ZMcE9j;@qC@m%`12m6*|}%amLTG8~Ans
zetKZcaYVUq36eySw)+`0pfu-e<<x%8Rc%~9w`n(dlQsQ$O;)ce4;tR^jpw~5PeM_W
z=sUZX*1Aj(Db|HMb41b^At}oeTaaUQ-=@LhfqN5+ldOt<y0TcJblEe$f$Iw4ISKa#
z8qv#&s(hw9#LkgvI&iyEgef5?5ynTaHavk<ul<Z+f9NyPMu9Htie@SzH0%|LZ@EdZ
zR^I-+E|C&&Csi`=L4P}~7bY+Vq&C3u^`44|>UxPQncopVghj`9f(~7gHAyin+rmMt
zqh8r(oa!TDsOv!?xmrmv1-`^l+UO^P_25UQ@*^fRU6auRU1bk(B|7jBqv1!%cN`-5
zr9~jeJwJ~xjmZoGQhqzZ_IzHmZTOWj$l0#9yFfq-9tya3>&|Sx=$QQHa`p(nl)-xk
zhE3wV3B}Uf<&jvnMS^mz7OQ+umed_~^|h5Q`P5+-BT2ED2Em~R5~i}2-kQ^Fc}Y#=
zh#*H7DGHJhqk+fKhbb3$TB4}@>lLi~1>8txpPbqrJrqbAHNtlm{cy>VENZ8V&I?#z
zUQw&M&)58|VB!3e)AU}hF&M&3CQVZH3(qq*BOpxd7Cea34yZVaZtoxVjrsU9=8Hqt
zVBP*{OTmRqw{o*ffdC$!l49}A`5na}IL|Fk>X>xfP{1FSop_tI56h3w3t@YLD#@<p
zNQs)xzxMd@KhUtEHv6Pt|4ltzbpM!*2lbp*?Q8u<3T)e0s4*dkAkP(ZTj_E8Cp@*g
z$|5?_*Q{-nyknlVHp5<-utch4-~$KPmK;4Q^Me!lz$F3Orw}=9Fe3cnAni2x?1}lj
ziqoSE@&jGXY(&4z=((YIchxuNN?xZ=#%FP-E?M@ulTL^(naLj3G}Ar(#s(qzzl5h%
zxnZ$8J{^^ug#)9So^EIlPo-(+PC7!j_Jj=^W#AjB3j9?m?No!=GkEWX0Dq!K`2F)5
z`_Vch(ICX6lRqFDUNQRCRP$%z)v1lx7Z-3;vQ!zjA5`_o(kK^N3jy9?qvI8I7nQn>
zcZD=~8eI!=Oj47LK6O;JX3z9I#;q|0ZZ%5>xo@?8glKG4>9oA|^l^)B7O0Y1Yu^@f
z<{q(l`3f>f$XzJPbihWalQ26#GLKIux?9zqZ7Oy@o$w8l@zgBGhzM%3HYVXO>9+dD
zfLC<Njz$#2K-K?1Pv{ipl%WE?r)9(i?>DouPs-EvvYkMaBD5o)VI5sGCWK`b6p*`J
z1I!hFUPHFU<4JQQ!K(&3ouW{yPT2_ZBoBL+N4Npd37zNCgQxQjhNePQO7X7~Vr3ZO
zxP@EuwEvAbug>#y(itpmB#1IfZ-e9A-+z;(>~Db1=0U}Co)edyK0-a;-WsLHK4}_#
zLyb0T+2_L)Eogj}f%5ri6nCV`?CTDF6<+$j#!9Erknw=Z%SX)2U{^ytfs<VzBuQ5!
z*6wcpv;16QzZ9RgnV&!Zt^^s5xV9u%%k}NLUdGUet$Z&G@v2a#FA-y&kgies!*iB2
zZm}OwxJq%<O4s$`uKmqk$oGHzU;kWbFmVyXJ}MiGYs@xPTy$J@>$wG2ne*y*9JtK6
z&7A8A6pJ&D@Mlf>zngqh+}6w)VzLq&s!_5qdgh^ZYa(yT-wPv0ehmAQnj4PD$`(1T
zI#Bm$jli<d#c8+Hi|&{{?+YP0T+Yyo?DjHB)-A7garWbgVw>hcJPJ?Vj*fKmeFd6U
z?P#qZj59RXyBL>{r|r#)oLy`0?lR!N2v9ipwq^&qljbtaJ-*icf6lDt?-J&(wJ&O(
z(@L4FpI~_m8;?|a2NxSZ4nS6?Y~l^R`{l&Bc#j#s0SEm(R%>&U!me}OPN0tyOwHP-
zg(#Xlb!0$6m}f}LV@Y1o_DZ{-VczqF9rRx#ly&Mj4>%VMtk(}HysZ%z$e~4h40kXv
zGKw|_`CsWpkV_RI^+cNYRHaJo<;FkSD^eb08&}@rm0%n=-~iRf5dn^3qq7+?vyrBU
z2aPJfTzLZO3FkcOc~7*d2l4r8nHh(&_N?pH7L~KhDixX%;M<ezWGYn{pW*rw8d2Mo
z>@a>Ak7vLC{bboS6sVAP{Taji{UAL7dShDU+!(Hsx?B74>)jn=?xT{Hvc5s@z`wae
zGRH;@?4KI1sQ88EVzpnXrHw8_PqCc(pO1KAOm&hEY@3ZhzxR?1tZa7vF^&-@FL7<K
zteF4Jz2`|(&IuvOY1)(?z9V~VrC_RC{jTooQEd6EGUw0lw@_*ZK!hx2iZXIy{J?B_
zos;dnBoeevC_(xCjn3lKSIL+Z?yF3dV*6o++(qFOv`;CI_y*Bax@_JC{zaeUT4%p}
zWJCh%cPNa%ZHpkMq~fW0bLm@IW3`_n{4z0}wwEs%nxi)>-q}tykC+q^ruW3nBlV;X
zwH6SQJ(>VaI1s=ZgJkdqW4w{}+^9+WJtgr-F;!>4t_RW+bsp>llC|~vDj+abZmN?w
zK>Z~vLarf16baT)srE^VTzUj!22}M$z(iOtJT(j|X9xn5OCPGi6~VLzYSTdYxv2dK
zK9UxY7s~1@g0A#}ivAWxg4aIc0m=a&W7JWRx{Bb_`Om^gU!;%&S&O84`>_=K?w@!&
ze2icoHAx6ungAhkIi?G=&*gw<wZ0;0sQv<mcMZ9Y6{gX@Ld!6ilkjL-`se!)gN|=@
z?t(zq`2TJ=9Be<20LhR`_hTWeenrwi7`Pprc?BeS!Q}Gwks=3buF#S@|BQ0Vc7Q28
zWb{Aw0gpMz+`9f#FAp4KIKwptmD*Di2l<GoN)?|2?nr_g=N&~k{cHfu49OoyiybPG
z;WIF#DZP&gDGbhvN5bnnPTmpW129E-{{vZp9zStangBD{3bLQ(hiQW&ErIWs<&1VF
z29Q$klb<S&2?=meCVV&;fG-<(YiTIn)0mFJBX6P2BqFL2=Df}XqzXUPUEp@n$+8p8
zcV+y0pIG~<>70Zc#j>vhXy`s|X26j_#9qW)r`ApcsCHP|#(~`NMKL7*m71%$E->AN
zju3MP=QE8F^zn*mmhz+OqY)$!B0Sy)x+|>^1ETMr{#di4Da}(}1df!!vT8nq0sIi+
z5lS9#QIaN<J`?;chMU(5N}vGjFWO15kbD7VO44@rwT!YI#YkWrt8`^>gmMP;K6wN8
zbS8=VkSmjI;8#>$7)fq@TdSeMP5^K`0Lrp0Nwm_f3+#GKI3Ji4+X0vfN_Gf_O-~s2
z<fk^Prp>lGVFT$$I52N!09GI@yfRM9fWHxcUoE`e@3fczbz+AC<fnH*cvelzH6Vn|
zh&;hyZg`>e_VcJ_3@~ZWR|K?~sd^yq9kuWrmym0`o^U@G9@SDz52gbCpaE`Fw0Ly1
z77%71x}NYwP3|9QoEC$qr4AK~{v(di;vNeH!JL7mOKKp7R6MW%`NH-DbD*)OR7^0_
z07S(>m|Y<HzJP|30J|D*HFKHq3%o643xhoHmpd(M-OA02z<;TzA^CvX#yC@FJ;}(X
zI`vdO_TuOHj?bvG&g7kM*rd0&$+TM^wpPDFinY=F2rMe=6pzEQON{u%2>EKLI@9mt
zf%|~&DOM9+8ho@g)W}DZ$YPkw32>l4P|%1BgPs>m`!PG4pZH^MDlV2ZFp^H^FQ}hu
zN?Xk^TK8Q>qUXt>rDti?;w}}*8A3kXSYf0iPH@o8jv>2!Hk-c6otNLAxoVgq<1)U<
z!}5U)!;ew%F<}r!x@OE};>=554W|=|Z~i$7UTyE^!55J-y9FxYAN)2+cUq--*dlV#
z{L@8xV1Zg=DvwX#B2YJNUSrdegx<z=Pb88QCZZk76?3Pr)hGabv*F`*Ea%Ag5?u|z
zG>S9~<M<vmO-G|#sI8$pma*UUytJWm0Pt3^(+^XOgY4}As1xw&6hxeGpzymuF;YIw
z^C6M%a$TTLnCn#CL)&_+W2Pva$p&e+5KyyHP;LM1O<#MU{-57@Wd|Xt!IEbq#P-%f
zrW)^RGTcF@JQ7#(_rUF``o~g;z$~Ynbd}C0(b~(UF@rb!Q+_MdJ9-P1k5k?Ivzu`)
z{UzqA@>=ST<m0VuEUb{Qq;*9xig!M+0CX-R|8NY8cJ^Uw;xli=DeT!YogRgLWZ1)c
z_ax#kV1l6aJ1M=b*4<}n$t6*h-?SxPonlhD=i7o;?DVLDUC-DDt{11n^AXkWvNsG~
zmJ6RbAGbyj?*-nis#Qb;U(Q#n{W&-Gy&nExWOL?g{lQ_^gC=Dxu#$12^iEw+{KvVX
zA0>YT7X|Jg+DjkSVO$qN<?4dcN}5}IQ5CBEC6gOn2Kj_2sXg<DU&Q816juWZjki7e
z2T-r%2nzEdZ%yT^Pt6a%%RGOi{&s><M{(5rK(xo+x%ai}2lh;Q8c`X$0;3do?cYKz
z52_((Dkkmgc6JP%hr69p6xgl*b?E}XM3qzEDxY4?2mi8G``U!SJCEmof=~KXTq`(L
zsde~J1rNBAzVSd<bDTTNrjK$j@<~3ecdaMwm^EoIEK8CenT+cJAY?Z&{r8szopS4F
z4$;5D&RugzK+}7$B6P=Fx5?n_*RzQsy1ma~=85zfMA(Tm>v#Ti1zdHa$ow5Nrow7L
zN%S&9Sm^gc`Cz3BhsZaBs4%5)msue*Ly_wRwRN)tM$Ft|=VnW(?wSI%d9}kg<sFn8
z`EeimN#1p7QXjlxsxLcFNt(0a<uKpIHjKAVp?@COFkF~1JlCsu@05rVLmCHn@XSSq
zW|0a=UnY>hyS|sn`1gD5a%lgiU~WTw0f@8-6YSsL!@m%Ze2b^kRi4B*_2f8t&aO2n
zl0xVrOv(ng<997+P&6#ECeO<_+m}9XJf+*F4OKiM%3oWPIuE>u|FU^Rg%vmu$oQK9
z_%T<F)yU)v&&tl9i4rjCGW+V+aS*nzEA4%46KrTVtIJVcCvCinI;?RtsIwa7$n`R>
z+<nvB{sjitT6lT*{@RF$<lm`H*c&Zt3;js%v4$Y?Cei@vX|%Bp6{zwm?^B5VeCd&A
zJV<(SO^W#uy7Ob7xy*=qy0I~A1`7btTeDfer&eshsiw5ZSk}(^D{)8EO3z0##lmQB
zT(iH?iX&eMdcL$Di%1C0RD?%qp?Isfh<59mKlG13?uz)_q8F~mc;Py6qiIQlwzscc
znr=InV%C-oB1|zpb-p)0a3B=UVKdYmr<(vHlSuCnnx0nm`x{N0ecwz^#aBvRyDd2+
zrd%5{D;4yeDeypRZXAUSJ$8K8A$SDN-#WLuCiq8}=Z$r(6NC8Qi>2&)dUR<tT)Z+Q
z(gEw3BA(9lc1PhwX)3d+PFBlGf5*3^-j(92wF}<HiswslQ2-)Mp7~UVBz)5su`Q=b
z7LI1*4p3VkX&a$bom;W*n6_>yaqSQcnf*@0_if2ja)vROLt9LEU@0ZiZQB4wJFYLd
z;m<Fct4i#j@qj<bM^SeP`4QhHIsdDRgD$hna1VXrLE4iZC|T(iC_}UIga<2$kX!ca
z-J_sxGqRmpg1$d25^9S^qE9m0U<H<9_O^qAU59$5(I*2NW*o2jb$ks-O@F%3VQC7M
ze)Da|&jjSE>1H%Ixe)l_-jiLb(b>Oje$?3a*f3cJpffRX_9*RTPuM$ZDD$iUI0noJ
z%^`%dxuS5YFje-+k{rXB@@dx6GnhbdWg4LX&eFg-`1;H8>8~bJ-UtVeWnm4bZH!a(
zhdZC&aKM(E%b8K8+Ks{0UGo7HtXMyDOyjk7hs`i@oi6_aW$R{=Az_UsUTZiwh5Er~
znDds>u<sA{_gu4tzjIF;?)B8(+1@(eu}YnPm=eLd1YJ_38`+a5Z+-T<{*x#uNPKN-
zz`Is3iek=i0jpgms^Mv$LToWz{wqD>;W#+e0rk!};=v;XogWv|G*b2PKlGSLQ1-s3
zx0S+M%FfJl&3!2;&&6rgywHrZ1E#!CFJk|2NWD7uC2cGldPJqDy{-G@a8%#8wN+53
zmBz<IrkS!4jfs`9nNKSOXD!~h{{xMbaJ=T6b&O$#ibF@lP9*YC3mSIfs&-F7RQz!k
z7Z1+16n=lJ2|r!<RT>_%lXkd(_`COo1X#xfld;a6Rt?D<u<A8E3R)EHFQ|DwVJXL$
zc!d5lEX)OLU-H`btjB+1UQg&rFRDR`WtnC^1h<VyG5wQ>vJ2QX+5YlP;e4?ALm!{X
zk<A61wXbF2g;2pg+P~Y!70+Nkvs=?bc>$R+TVh(y5o2rT`qRnwe;Z!J+RB6;yp50<
zoc`HL6FmJV{(T=%PH18dcLXC!Sz{b6Uwi0(U$*#Ky@n+Ctzx^RHr=kE_vI<vVW2z%
z!pD!>bjZ0^ttQ0>FFz4SKP{F0<SWG2;pKWeWG|7!LsC#wpq^=6V#fC#p5##G+`w^>
zobjVV-s4Hmp=K}dqiIb)Q;Q8C+E6agK3MkCw@rH68^?qxXBMo{<F^|Jv6;eN%Wsg~
z7=N?Vvgg4#j@Kyr5S>;c+Frx2rtZ=s<{CcWth!^YHN=0CY0Ps=a1}O4YkN|9TI5U*
zQD{#q%{R44yM$Kcx#Y>Jjcj4taDksz*TC2KfHKE+$9qnte@L$e?;hBwsOA(nHpmCk
znIE6)AQ)$hTO^NaecH7xr0#qc-&W`TYp>mV8Ngf_dON?>qonf77;>y;nAhHDCbST)
zUajvz=vK`j0NsVT)wlXTr6B9$&uEO0?Rh|Pl-q!_w=Wt0`Io6o?-9N+j-*aN?Jx+d
zsSMqXl*o#<Hm&@HBjOHm;_K(4(Z#|WF@RJ-7w2Vu4aRp^BB?0vKz`!njnR;06Cat4
zvwqE!PeJjdUi?X8cN+6(PnYVqXAyhsb{sYs!WT6Wa$bFbDHEJ@6i>bByQHh~9_>bJ
z$2d4#dcWn*Z9LjcuE`L89CoBP=X`*>5oA*(%=Ja2Vzb-rk+&+|M;D_i+0=P&W)Stc
z?0AQ+M~Y6RI79E*o#eZQspPO2sUFmls@q*x$rs@kwbB2kULrQ>U-KA#ge!BmPO#Hr
zJJ)pHO|Cd3trN4-5hQKW9~0cTIu~cs5)y?ugW5j3;iM0`K|S`|ZENeD=EXw)tS4A)
z;WL<9Y@9L1;%M={Q6^8C3k$<kmBcHqG0MDUl6LuCZ});Y38w?+lS(cdO<n!WjM_ra
z4AOhQ_+<#sN|sUGx%~yzdG11hPf$meemdZeSVJoSKohjwPRTaS4C=dc)xvpPV;TM8
z<qEWvF0K4Vp?<15^b(MI=1X`#uj`cz_U#Ek#^T`Tu}$)MEa02&28+fE`-0~`Hxf4G
z_ua}HCj_w^FIN-v!L|e@Q#}TVVV;0RbYptWNoChF0Kit&*!<gN_#vO2_j0Np(W|=$
z8mHwu7$qhIC~9Vd=W|V7IOi^C<wrhc!TUYy<EkHx<|@5?inH&w|J0=4X!)FHd}*Yb
zIJUi>RBz6{7I9n`N91vPKdXEYw6kYO0VRAZV>FB3G#MzTITt@>*_zK!$+iuY7;}-o
zH`x$iBS_&K@qx~j3#jKPmb_^lf$=Rm+pnTZ+O;$;+$du@=8BgWe8L-EwNbk>6({CO
zGw-&4N;3);NP5WVr30rhnm36H3;!+Gp0v$~gCi~+N5=jKDj%ILXf^bpzn^bOYo@#O
zG@;nHk%i^$cN%W?#p6*4JCnOvdZ40w@MTRv-m-sHYr77ZixAyAFs0i4+6R(gjVH}w
z+P(D#j(_WvW#eqhN8jnHiwKK{Geaqofq%kcUh6-7kn(ghz$lsJ8*l%nWt%}*!R$6q
zbM@B){WlL)fV~foG#zePg)SEhwI;lot;!#AgmvAMB&a%2IfuTPE^hP5cr(iWo>jAw
zGc)zcPn=(uzepAvLiDyg1xg($W=i+&u14Q(RbGeFDbsXW4@x%pvEBU;#|97mHDhKA
zjH5se?ORGqi=`x_KMcp~YNT!Glb#sOKHQ|pucn3k#Nf2<y)F?`syJgx;!;<u<5ob+
zziAj_qq&_M`>V8UK-u$DA`cuTl&*S>?K-PGcj+KRsaFjfA8-8qD)t0YX<lf(xt+)*
z^xlUN-QC9Zs#0q(2+R6ow<AqsRm`HfPko!NSX?Yqhw$qvh5vztsU({!3cOmw@kRXP
z!D0>1p<O%SK70KR$zq!IWQFDrcE+N_26;uEH#$=o$#G}tOB;+~`eKZee!m2kf>#pt
z?!@{uHM1~2%gNO^E}i6IlivUbD&ho5vm~}>e8BeCw@+27+@FNkwOW>?L2kz0*}EYD
z=oZZn3q87=j*TxG^kdkP8irm59hy!5h3s=@5Iy8nNP|C$JECk0ks8=$7BQdGm>n|M
zR3oi4#}SRxFvchZ!uXK-b($aE`dZhm-IJ9)5Q1ichyH>@POHt2yG3W0ohk_XTt;%z
zW4+76Mof)78VB01{~2rBJ!_GWZ<UH{mJ-MlqI}ixtJ88Vn*%SJU9BDLy}_g^J;E>T
z@WiXbmM3>PHCg?yyaw)NV-oFQ4ND33mxIhD$s;Fzl!{}OXEHxB5?K8IeQxpgZfTi@
zor6@>WEDrjr=gbqJL$6Ojs&-E=6F1~-pP^iqa7Sk+-)Czn5g4zI69l`TtD{cJhY}=
zb%)7QiRq(x?)bJ~t-M{(0s^fq=~65^Msmwrrm3hetfrtyiZ6*}g%V_=8>mu5v;9cX
zb6+M5#9u)dHBULp@t>HETAfEo0dTqU{-HmEsI>mda)pfrG;>^?=mZNB2RD#qucgUo
zULi5usQrb|??%%xd9g+JquZk@iG0n^xavt^{FO;mefBOKOHcWKuYZGYS39owU3>R4
z1Md*!&1^WWbyyJc4cENp>e->0NfBKI*H~jB8EJNlX71`U`d}wSDMj%!(U#5<@n4&*
zcFou_>L7Nf6(KRb`Xn-WYZ6y7r+}fevZ0&ILvv_Hk;D@dTIU)@9}-G?RU{XMEPPVu
zu=UVe7iCwvB~ciY_^9}6nq<;^am$;Ag>uVSYu75DxHqmji)`}>d?V9$?giyILZl45
z(JT11ml9Isf046Q9&J8zSPyRfvt}h}+0K%@w#bvd84te;JnzOrv-b#Z!aB2r+EcDu
zhGqrERcs54Y@M$EJ|GXEFwxa%yIjniAit>?WEuJ=H9;Gj+9*q_r|_|UF*|g2pTGYW
z==X->6^H(%jowDZ?atYlW!O(ST*TSt0kQ7$!7|1*mCx6;OhDC3Drs3UNp<Al+*pmf
zdfDaCRcJ+1I+hkp(IPz{9$|00cKNy`wRSo~@KiQlo-1EY`4Vdy5pNhl1i6~I_r}fJ
z-!J`7kF}Z{`E<*l#!8n!=Ay#-<VbzP>?tk5&WV6z(aKMK*)6XHwRhw>ty6k9S*=}L
zZ<HoKz1FjzXm?t=P&TM<kDa<H=gQd9YmdXa<i*XnCd*nCroH$GSiv52+p-tM_si`f
z-51aKG}hbA`b*%UQxqLyQx+ek%KCXE3NS$|7T1Qp0&8q)gSoz^74jT^zBm^u2<>2w
z!MSQn62;KfmP@cdM{b~|e^_!lM)JtIYMs@^Hq2M=>HE{COv|+rspI#x|9+8~@%gT2
zp~8~Ukh1F{*%ZF<ur(aU$20YY>u0qM>Qvu;0DPL@i?280ee#9rZ<v~7fj9fsnlAp6
zW71Wv_{Rq|I(%{j=6qiJx?)_%mZy&LbLDKIma6cZZbZ#Ojrc`#rgWcKM2-zt2>G^u
zP2+(O>6IyuFjv^(j4_sZp6Gdqsc<QG{LTZ-n0GJTeR%O!t?R*9xdjaxs>r4?I=a3b
ziqDyLUU&E1K4dk6ALyyBOjj52^-)8rzLVE7ADh^3$vyCa+6f*!2s`dIoM(8}9wYR!
znvmgrtaA2b)Ejy8L}E&Kmv{XWe7>nWxm)OMu=qZ4D;Zh9(nNzr`d<sD!OKLXU4`l$
zi;Zka6-gJ0@>(5T&43r6UD<`-1cqt?m~M_c&4*^s4<fP<4aBSJXB2rD9&JBJ;rTyZ
zc^mn(M`sJI%#9Ay!Jme?MMm9cT=HGg&(Y2SgaIUO<|2)ezRISli4O;ymQ#1@&gu@V
zI`V#AyZp|9sH#2Vn+P&ka_Hn_maazWv-tT}#_Tx~tA?sPJg77O%vn8d<@Da~rMm}<
z%Jv&;{`7x1-N%bHob80_<*?p{!6)~Ua=l#Af13U2mmouOeg<DSX_*KOy@Zp$5O5ZN
z$`BazlRsokeOg;#Z;BLBsS6j6@TA-EELub>*Y4!rnc2kGm=DquN3@)t)Tkw|U2Q3z
z)7%slF<c(&97W7|a=5tn>30pG&+@2(&X}Eahs~Oe2vf$UCGL+CzW#JZmr^atNJc;}
zh4YsQoo-4xRKLKz4yu@c`i_V|ONf+tXB__u_VG@u<&usRFurg5qlWOieX1=v^MKA@
zYOC^TcY?vLY1YBrf)O=3fe3O>8<v3l<`XjOlU;*sX$z^U9}4uYCiCg#TMLqZ6h2&;
ziUx1B%RG5EL__vu0kT%b8UuIW{~9u=$a+BDY*+qFvPCXAj9RFHbq5M(nw)>n>O7+A
zZC&H?XGTfZ$}w3{nlQ{J0u&UQ{P#N!wOKCbFS`g!{Yddx4bn^MDc1Z?wH+&`@Du7l
zc4oAP{IX%PD9<o9PJsAM!i?(D*t-7<aVDxZ8Uhmy|6m|kUqwKpsrH58d^pQPa%{hG
z!Y&wg2N9Nfw)Tp0I*+-vY4Mj*S#a{cK{u{4mjdmvAL;(3CG?!kpeF7#SpIjW_eXz@
zj=0SHruR)L^svwT64ecle^h#S+U+54X3K(8_9f!nkECuM*9?f=X0VN7&2<Sb5K6u1
za@b&vZ)58t8iDu1A;`e0y~>5k4|&|vTTsp0Gd9{wBe_1Ss8<VPf1Up^1tFCFRTEb>
zu27zaJU#yXLI)wO=Z4>J(6Ik{&5Y|Y6oF7>JN>DgN&a+Dd=*$0G&f*aG}yBCsFC4$
z6A5o=5YpjoORuk3uZs(O&_ft4vUoM!6dxY;?C1OLM=*ua2EB1{H;-q1!JocpF^X=m
zNR=CeB;4<2Zo>`HF$+^#H#Lkmtp#r~!b^Slg_a@goZh3%Di-s}*<X(*BueYib8)=W
zE;3J|4+ndDV&eX!bAoT(zRy#3q=={M#(@$81FN6zuSpXn)v2y5t9F$RN0i+&jrsi|
z>2p7Bu-AxBd(hPh`l*dJFMKlR)&+MSiDPG#fJ1vzP`M}V5mzU@I9a-{qIO6^V+U60
zH7t3J)Q{Mbl3q0*+C7uPUs4stYgNx?>9RG`dy(U+&RG5T`hZX7ngJxD0_Y<Nl-8np
zf%-yV(T=)^)&xeFU;?a1jioOp$iqT#KpY(h=`3mhK<5x~{S^%G6UNKy%<K%h8b?N{
z!u2BfKu{PItOt@RjK*<06L_oKL4d^2fE^JP2L{=L4V=)Vz-k6s7)iLJ3f-FqI4acN
zk$0f|?EtSuIK*HZAp>jy{sVK5iaSk5g8lMyMbvD}MQ|YcVvrwZ=d`HQ93%y>sSh*&
zui_{;cd4uo25cD*6$uVhcmap(f1QUNRjK@AMJ8%ZkO*29f32s$K=hayN>~D11q8N3
z#iAxH0e;7?{}y8PnQI6|u>NxNXvFtV-3_d1;Eoeewq1&N5jOy<f$l=rP$wXkR6iV;
zR*`Hz{p0ty)IdSQS5<*r6TqXdt|e#uDc%Nf-v@y5fCsXb!HNOVpB5Kp08p46pww}a
zPgpaJymbLe9&!%j7v36xgYv8xzzu{$d%0yNK%+n``?R<p3~C3M=e!|6tX_6p>#g*T
zx~O+l_Laf5x+`V;l|IU)*UKB_LgG^DwdwpqUll4hL6es!-Y%UFAO8sK`~vdv_6Pz_
zd?ba_juL=kR+6s=F|qzBf)uZ%0$){k*U_N0tXvlj03a{jONctjTnGN|i6l@C)Fc%p
z2xK3v_EXgdN(zv=x$Gi^VLL%Z<@tnr8k1WY(!ff~L0?t6m=g^0-$NRpl}7QXoL}_y
zEZGM3W8>KjAXz^Em>yIlr+4RgKGDDdP5NKq#TyN*cPK%R0j9gTg1I970MKYKkRFjL
z?tA!&Y;0U>Y+R8H#p^xV4(W&8LJu`p!8yE2#fK`L&?4Z9RFkC$-A#2}eAEYo%z05e
z1jqIu0|PQZ+lpu7@9Ufv@2L|J!dybe5inhIkgOi15UH!OBAKSIBGZ_vHi&KOt&18y
z@ko(uOn*7!^IBvuj*t*2_KfGbDnh~cb0=9+eGzs5`A=*V1CYyQfkD<O0Au>p$E)52
zY$hEO{cwVh*{GnTNd2+#D8SCDQ3P&2FP0l4Kso3CSIQwkE&W<&IcdK6#g8E2rep?=
z6}>p<ZAJqW+<dbGn&(}JAiuk?oY>Q+!dC+~kQ(e{IU!ZLQC!CthJcgiFM#N`S9!K~
zC*8P?ysfuo>ATkk-UIWC8>VK${bQzEbJ@Y(2J#ss{{scQ2XYO4ygdM%(mTnL$C<(M
z2<Rk@qnv4}oVU_bfI}aH>1Dgp#}Sjhf$NlFp1|Ft^hY(zdI#so&q&zF`==TPs=%tv
zE*AOB71gaZ*k-p7cX6b5(yS@RK3-O=amzkg7k*7q#QxRTttM%GUF4=?gG|Wtacj<2
z+U#%XK3~L#rs>2K#kGz;VSN*|I9_SlS|4IIz&8l#WhV-#q-l54RiEUl`veMCUcrC4
zb@9&o-XandWXIe5Vj5VchYp;yYGImVEG|Cc4F6C`SF@^3p_h7mHmHBP9tdt7uP;h-
zIXHfM`ooL%yHVZjRj4F~guS1Zl0ps$rHf&%{2}vvv<93LK~4|XKX^gZr@|T|%Nm&v
zJX+v%j%hPff*@U$k~P<zAybBvlZnYy!cezo)_q4l_Cz3Wqc?$VTAhRv;bLSBO9F!o
zsExHRhYeN?%Zt$wj7bCJb2SaaOFR55R6H7Araze-#L9Y`1^|M((b=G)=dlkQ+KdNB
zh~;gVf8CdSXvU?mj}83lv+wK6`Rt#lJ(E-Jso+~$H<SiROUTN52Ft`RU2bA5b9Cm^
z?`h`y^vqgw+tA-$OEx|dmHi@X5?+$mymUB&Z{fa35#ez}N8fG%VoDSL6_kWUr(Q3S
z%RX;Ewd_8RI9v$*Yx+XZ_4j^WE50pB&Z_Ert6jRps5D1mUN6JRde%XHgr9%KRa@`D
z{ay3y0uEI+P-%*R%Zz@OC4|N{(DkS_>-rkQv2|r?xy@M7Iw)3#`%z4Q^sKz9bNxR6
zV?mt0*B7)$xXq~9!^_@Vuhr`pRq+;*il6DI<Q#mQ^Ik^Fxw6d7^)!GYo&Y%Y=BZ(=
z)Lzi_i*Fogv0I`^JD2DHT4cWwv}lU~4D45o^v!u*N4MZ96~0~+eiZ(%5cY?8fAJA6
z2>UgL(d#2raePX>iaoLE@pQl>^sXa5w3#F8RqQE~&d$b9i8|XZ1a|AkVcxQ?d|j>H
zF!OH++D<lcn!?@r(e<lT;JOLUM!E4Ou*w(vN^rUCaaG?{)F#gR`-jg@oYfCnT=e#<
z<d0%*$&Aj#Z*AScG}6U~I3Bna9!5<W^rxV%$pZj510T+mNyafz^&iTU9MA-Xk8UXo
zk|~FetuA?>Lxa+mCZinprK$n@v-P8SrXFcUF<4xj^`kVHr5z}^tQ)Xtb43K?QE;&A
zk=Gwe0nZeJgT*d6=8KNNIG~zPF^psJqZC{O?Mx>e@lPNDQAkHY&1WWBM_Hq5LK|qq
z0N4R=qL%ks6a1SaiB#w7T!b?`JC#n=W0D0DDI~MEC%$XXbgu7nqAeq({@;-kV00<z
znkUqL)n<5%1{+VUa;2hQ;uSn|0~i~)UX(^E61~D&qHvfijzFmb=BYj6D-Z!Cdy0?y
zLAwqsyW2$=`zFs;lEOA-B}PwLf%NE)-ib|h$3)2+UXbWBHzNkTQ?TPslLKJv3O%SA
zG)O^21Kd|rE{{B4JM0VTRg5gBq5LU<h?;cc0z0V}-zK*-ogY$_)!OOAK=aR9)YG)@
zFszcs3g)_7c<pUt8<-DVQqW}>ZDo!<tO@rt=WCEc#|dwG)H;oXSR~YK;#)GMZPRfa
z4k}!cY9>>)%8|M@T=zAdd3&*Zu%9-0ty%SFynHI{2hyuHoA!{+x8^>TJjJM)*0_0c
zc+VNF`%7|%5A&mU9jl+6O_QDmM@2pBV@T8n-MLpC)Y5D@N$<4y?;wy!iJW!yu108O
z(yq!Q?u(3bUF*pksmCDpu0zBSG!23?5cz{vZGuFR-WzsVIcS{x**|u+1^)oq(PjsH
zUBz+s7s}B!yvI5Fr1dqmVRWJvw|2-QidQR?++zj$2TiEW>E5~RYeJU(0~SJ&z@$lJ
zf_H;B<0^An+I;D#4UXYuUbU<$bY^m=)Zstj5!9iOG!rIApv86C99Nc`eC5Mqr@c$9
z8@(ppOPD})3!1`T7|k1g_S@=fMrL|*UPN^FCyqX0UTdk{MwgBW@0zh~;<0>>7*iW`
z#@@Be>*d%pfO+UgtqBO&Mvg!*>(9L_Mh7_+=ig|a9Bq`YIulmyHEV^Gd6Mp4l|XwI
zjKOr4Q|X%Wy-9a#S1t)0o)5XM&%?UxPJ$MZeqn+;)9<_`Yj<|{5zGTOEtA%vqK-FA
z%Ia}B#uquSY|ww>#YK74J`nOJ5(z;d@$FsKhj1+*Xykn3j%q;3@rvf*Na>s(psr>S
z{*ag$?^}K`)D@q6e=rO>S1Dzy!!+9+g1@F}q6f5CxN9i+<S$BFfI>D0AXf`%uU<g{
zc_6xvO1T$}Zd88$#zpPG&T3@9v~S}QvN}4j=aEt_p=zIf_Tb|cp583e-cqt#m2Tj!
zF-P{!jdU>FW~Rfr(CO2|aUt@UFzD5Z;-3mc)~|VC5Ld}(QQoJp)wKIYW{uZq>`hp^
z@m;Y~40z|RXs{<|bI5L>VV)}{XxMhH()K%fuO^NnG7jy&-rm)Zb7PG0Qqj>FoXHFg
zCgv5VHLedzsPSX9E>ii(Ji|ben;_Z=JPNGyaftaozLdF2Q!GhzcZ6JHxvdLF47k9o
zMU3PYtqV879>$AY))O}%1sihp_O0DM;E~jWSo(Few=Au-m3s_zuFp!+qP36hH$N)%
z$?sh>uv4k4(Gg!83VL-kEUnnYCzlBiT$-@AhWGbzk1o+qE#0cCNiL>CG4gDb;C9_r
z<-JA*-Yg_b`q!sR2?%VD7QQlbW`y^Vv|`%W?0|5@54}@q*8Xw<7s(Ojq&@2<+$Gq=
zTtpAd*!?SB5LOV2^2EIWt>qglBa5B4sib5`HpK#}f`0k$S_yO&Kz<ElTimPS)^C}Q
z-E35lU8tDaTrj{mSFUN(QdVfvHC%QJ$X-j9myoB@xl1N{KM+Wgqy6lLJrA{ZyNqqJ
zPr3c-Nnna%H=sU@I#zCkS+cJBl4<fRt+{v`YfiFkqK?td-W9p6MUfZ|YnF7JS<woL
zMSJnO&QXrl!fUwx$84`4jw`*q=GIS4SC(s9fqPk@3DLOc(zE4doo|N-I#fNz(On}f
zk8C`m16K#(tz<o%FqP)L0@!BV4{|C>IqhQ0?a&DB5Hg;|x!aEp+o(UeP{-Q4O<s5{
zV^^KTX`E!%VV=@ZyKWJMWiv>el%5ubPLZ$URb=pzs+C-TeJi|8nBqmx*R3{4@z@`w
zNk^Wa3{Q`iX*lDqDmiqGO42>?T*?CTk6QE}Ba`xGn{xt~PE!X598&|xrSU$qX+M-F
zU`KyiwHL%KV%wI(f$vqkLu5vv@4&%09@S&Qo(;M2CEza}+eQ1#e~al`MlooHZCLz7
z)h}6A-o@o_MCbZfU8df6pHf6`>|q)=c^jX~x{Vvd8g7GVkz2r^sOoE>w>eG#{3zsz
zu5$L8KB&Nbr^-X<hdHe^(FOo>$F*%|nrk)%7C~}^I!sWG3H(i4OL&v`d8e14xB`m^
zZ~=M@P)MknPSn!brUb>YP2K5Hhd84-6vRoMDGL!y--<%nG=@D}-lPpssi)?EB?gS-
zRC)T)8h|rAPam7%>$KzU9M{X*p#AgvwS7^lpr1>*i1WHLUI_<-W!5g-7G#Tg8T@-u
zVW(q*x3!k(ia{B7&N1qJtEtfb8tS^3NiM%}5j>}SSEy+I6VmipSIdkvgSqCnKGCso
zssJ5@J0vGI&TB{beWhuNrezYi?rWuvC~cQyF{%%0W6zWAO=(D6)47{01Cz~0Ne4MU
zg)}n}`qev&wTnFDdQoyo8c4H;Kyz67jifS@gN*j5?sX<P*f4!7Jl#9zCyGs6xXw}7
z$JDf*OCx8sa$1I$c6V%y6&+1?a<On!p0%4i1h2PDR!)>nm3ba>cWrcx6fXmg1yu6q
zg|`H4)!kj$gY)u9thwynSg-(!Ud<xaR$jHgdGx4*x9<i&3dz5?6W+%mA2R%;=dD;z
zk}a6v9MyRtStQ+zbDUQzrDK0-a+Ulro2~fHMP=OFqBh8o4|>{~G-mnNrDI%MAYwqr
zwQEgiM5Iw?X6x3G8*3j*S4>kjo;y~yGr0HWKczkZm>c?gQoy{N@}{G~40+?V12je3
z`DqLp1EKY;M3ro8ksX0{Jma-uTF4WT%X`$ii!nrFn#NJPv8-fm!6x{hzj~)MeoU)4
z7{x=T-HfPw;EYzpvE~wvqmhwQYdaOVi5a`IW(YT9psf2Cyt|g&>494MKGtbqJRERp
zq{t(j;9#l6B=<nkjdy5t{Xn`Ok((-eS8=9YhKe+h1uUC-^{!)7fZRkjjo2Bd+FeN{
zl7je}CgA%~Qtl{l(9ycI@~)&@4TX*|QrJPV-b-fXS-8zfZ#;U8TU&|K?+VnhwIzy?
z&NwErdZSH>)|z?Ux01g7srr_f;?<*N``n7_bjt;BrH5YCZ&A`x;@gf07|m-6cSk(x
zS)P5P*l$I)<d8wft$Gc$t3r!`#@^LKN7E4|^D)m#>mY!6L}RU8IP0mESzlun16*qs
zNJq-8mK}|B7ci~G+HO&_sok2RZELdo&I|W=&$VqtnfZ@e-59gZd~M)Qm9MOZR|m{N
zUNdoLCA@`tVDJxISJs3qiM7T->MO~7ci`lL>|I-++aWuKIQrJwG-S^tQ<V+cq}{o3
zo@&kgr`gzmIO)Yyf)|yDUrNGS0K@HCHc_LlcjJ-Cs()jYpSsxkR)wXscJ8J6cNL7<
zwu3A*V}ZLOty|gKNgEb#nMGEfSV2BkaC;hn$a^+3=~(K-YgrUGyAY3*)}a_~m4T$3
zY5}-870|fmyRhof9f1HXnwegpUNcCtb6qhdnA)sl-f#dlZ%<vY1|($CUZHtL)6aT!
ziZUq-1#&n0+YJ`mo^e{5cQG7RWBYMe>{}7G1#VL<PS}9@*Bz)NUuluBHxt^rsU;1S
z_O2^dFBR*zYReF=h#_}m;GPXvbB5q%p=nv0CA-zzS3!cqIIc@rWqqt0B`ID)h;qDE
zgww36wNwG^Q5hpt+aMn|sHMyXL#HK$L%*C>l#nmp9FEmmNMpgk=C)D+kw+`8W9Jom
z))^QdFm&%!5`QJ|D%?7ck`6h~V^cfy0@JFe)~B#wF5+zR8mo(_=V9^y-lC-3uv|oX
zfa+>e19!%Qb)~uN$NE<rfx5e277f}=2m7Q~6nG}R2e2ajx<ZN_j^pW0BrxDrF)&a@
zGCNX>t-r&Xn-pz$e)cUpTerBKNsOI@D9PjzT0S7uZgq*ov02Ws3?L<b@Bk0!D-TAx
z&an_=UV43N)#TbV#VZ>9z<O6Ks6o}|dz_NN!d1P$+C0Zb)J~JE!+2vZsgUS8)~oos
zX*I}inh)JZcwF<0Rvx`G4N`5PSDpYBl5QBDzm+<;I(22uBxhFxMy*e2C8^g-;>(Hk
zh_9L@DG@tk&VMsgU3l8=dq#y}5wjDP4V*1;9(#_ak)?cf6`%HfChpOT%COIu-Pr5w
zykC1^Ya9t2OcjaU&mi`!&0ko#)hF|3ae>iCL0DdE=bBCJ_*SsN(uBE^)Y_h3LKF6p
zj-{eUwKR}DKMJl~icFLAuA3dDfXX}cr4oQ@w{Dbkjw#q>r*w7atyb?zk_n?3%{u_S
zJJPFdV0{fB!4!-Smc(&P4)akPyfYurS2Bm1=_he7g_MlrV8E_iF^#w4qJIe^_MP7_
z+s!qm3dKuQv)@ND1t<X>#aHs-nNC}g(zt+*O{A0S%}WvUlW6Nz3gf@yQo`Xo)38{u
zmdva?!-H0m6nIKH1Mg79Iyc`qBfVLQ?lkF!tmSbOCLtSdN`M@<9qUqP<G9Y{+It$H
z_HxF=AlyAgG{D)gu(qDnjPhWPF`CSp#M+iI$-XdnH4?SNL>67YT6B_|nHC`?3H>V4
z0+i^?+uJ<)(QZUChsJ$s?ajBAyG!rKHAgsNyk@S$FDph)R99o*yM}1xjk(%L1KPMm
zeS?5absiJD#-t)0`8@s=P}~mpO-yQy#y(oymOe9#)<uXTRzuqut@d1#?_D8diScS;
z(HHy8isbI%@~oS;YU})DapbRk;9|KQW?w4E92|6{2P#(t=C=GRqo%W{JWu=tRv3Kr
zuCw9Xfi?1nxZPQ@k<?4zNMLl^7IJEP?*mvan(_!o13ZqE=tew_MN!p;-7<bKF-Wt>
zY_tn@NgrS(dy&bnPVjw|ygn2-x7tFUqpfll{{Xwwvw#RcoqDdBZmHow00ZPaipHZg
zi9^B~t*Ew^DPIg6jAQQApAkATLg4YfuzVo?O3Rd29%}=U?_CzWqwI*md-SCT?~Y4C
z7M#OkthveJv8L0WX@ti1;TW8N8v?dc5piMV1Nhcd@oQ->mlQVdA3)^xuC_!xjV(55
zN;Fco_D+m@)l0)Hva$Qydm7NOvv?CSHe8NzOuDd^NjKZb7e9CrQ*hGeZLpFll4Kh>
z`IpwUbrxf1^7TEcJ6$^AWZiQj5IF!=gGU?2QO0w{E@TgMU^8B{SW8%%5;-h+tNJi=
zY*67;9t9xLBSVC`nPdLu?25k%LvDc)z#pwcs|C9po|+gsk-AI9hB=l3{{VJI6&<qP
z8RLfH;yafIA(e1NbQArK<pNF>!ur&49X{9nPQ^Z=vz981cakZ34Ah{KOE2B7S$eHx
z8;fZmBwP<P5A|8+HNE!xbv#H7K=+m<!+B}D*KK0+3@ZC*QG~6k8>Gb~R)jwr`RCHP
z+wBt4-&T8@#JDLhAjgt3_*Y7GC|4gL$EIngRF4PbW17xct`U8*lqcB0(exWQwLi64
zq^P|=d7tZDE!0L>U45#nYOBuJO)%=OwZKlJrAPMG5q+X(N^|IVr;4Fybt{p#`2PS*
zfA#5}4Nz^bqx;`Ge=4)$_wzMtqs}?!^37*>K737jndHA8m3r#3bkxp%TNWa-Qmd31
z#Y$`y2MhRBsCbhH`_+5O4w=Podx3=|mIvI&(x}|pvc}teE2J@T$f#$x9!rJe139XL
z_lc6w;N%!{O{wnJZ0tSzR0Q!}yiP_+gXO1=l*rE%@=q1KOxR-`>KVY@Q*v=pTy+#n
zV2<Ps(x!%>H8dpWHHzHQTNX!8dOheIQs)(_F%0ICfz1>MP%%NHG<7rpohe5&oO;ob
zKnss*Oj3$F&;UJX#TgW4fCI-tMmgz5aYkqW_N1kw9GU<+(MD+EfDZIgo+u}io|FI%
zD4<dAKm`VhGe8OjAk7rL=m8BaCr){ztpFIHjL|_f0Cu8|^k)<RQQm-iQJMe%qrETV
zNuJaIVvvecMkoNsG<Kt*qJR+6j=d<w0Ahd+)MkoK!=(T(ezbNJbn8ZQKn5}?KN?fT
zCu#;9@y#9mX+g-Klbp~3eQ4y-+lo7SPys;pqmn2+X#jfBMIAY&06NfU&L{$qh4!Nq
zW7n-2paT??w4Bf|>r2i@6qv!IGyrubgUv2zpacSrpW#Pdl(?V-#Tep@(V8v+^`eYX
zKnE0K6j7Q0Q`VEc0*v}|Km{QH`%&JMjtu}HrR&y#^b}GUP-rLCf!3G@dNJ=u<3SXJ
zA^a$%%_kY+m<x`*DCt3?AkaGjql!ugy&(!XJW+}W>+45aV*}_Y$3IG5)KUQeCxANB
zw&Zo8K_>&fb)FsYHTJWKpD<hZE!5WrGaE|}3(cLFY&5D%Z3#3#4{6OBOMY4N$WVB$
zjN9n8sf&F%TesX5E9p__aV${zv*WvSQyb_EV{9Nf9IIF7_^iUcTCP!>vG!2G(TrCl
zPH$7v?JrLCfW&=3u1itVq|@B*AG_@0y)E-H{m?#ws>!CqJZ3rL3=ewsvi$!5*{)i<
z9N4U~m3Vuq(mcbhC3Tv|gqjl4+GMUXjMptBZxa=DD#Nj_uEOIfVk6B>-1$sK7Ia;t
zM}b8yI(MY&U3WP{`BD%`rRmsFPT(dzXyhKWxS(|7tpGNXosK)w4rl=nTv3eXl!`;g
zYCr%|k6!enudOFPod5@|0+X5r04^~{Ui5VSbZ|RR0%sJtG=q;ybpSMdDQL+wlmPCg
znop%JDG0_+DGXlp5s}3MnlnrU_M@6J>qdB>10)`3#(1N(08j#Vqa607?Lp`$0Q%An
zywdVLX*$pX=Z+}{JW+$3(u3a=fK1RveW=DwDH#;NLq;+vqqP7SqrDV+(g7%=G*ALj
zoYIa380LY2%_ch1jztHdGyon+=8l}wcj-&gfEJGQV~QvN597@zdR$Ox0C%RIw7mr`
zIQO6g`q9>ptr_RqfETSL1o6_7JWv9PI*ybK(0byK35;~3)|B%{dSE6f#~BniT3mBL
z4IfHeeiUMski_dr?deJf7^5S*0r=5y3}fDmW`OISSW<!*WqBUdt~)V0el%jHTWiSx
zDQ7#W?hw@9+1i4p_OO^Qaz-h0F5zZV$Mc|y+P3hvt#*OZ6^&2#+ONmpJxz!2ZsJd%
z%|opP)TI`3+ezz66E)M^cq-!E2l{YkKkWCd8!rRc$r3%x^2kr2z!fhM5Kw0fKp4pa
zlPU*Le;V}E@Lr7=`Ji_9E^4*^0EYD2W<wpcY8YpcQT3RQ*`9VCNdR(vs%5vhbBOI`
zV~_3{^_xo@IPKHQwv2JtZCg|dKH`tUvv{t^uV#4hvAzTYXD&}-xUDF>DXq+)i*!)m
z-fHi)6vU!I*RZW9#^{&*(NOUc8iG9KJPWJ0FD<%#2{fPZh+aoHjqaoC$qQbT7rkX(
zCflVw4Nte5A0jX#_<w8nrM#8%*j1$PCXk>L=dt%{>LVW_`_stJN{3c`$I6a1JSn9^
zs4RO6C_Ndgpoc=!AzUSd1L~Qm?#|6g2Hw2pwemKKiOx@{aYZw03?mW48jitN6%5BC
zHF{(6bmpl~%y>2Nxw8KNXu0j+{sOT$_oOYFF~ueT?Otiz9r&fkG?=5DP$9s3^rSs#
z6laPG4%AW_GsQH7BQ_0ly8gBHc-|NsZ*HVj?O#z#J7(_9z#g^2Nh?huk;l%*wS9g=
zl_`Gys`NaJ!xrQ2L}4t>U60Mwnhs4%6f#XB#*322u&ej_T3AFHN6Vgo8v5^VO-)n2
zr;F_5*D;ljDcBgKJemz|W-0cdesrB^#sI}J03w&ADj_H3&1gZPUe6Djp%rnRr>%2U
z#L}ky_hU#?l>QV@>Fr$xiL5d@$1@h&z$d+6%?z+eQdHV|8fZAdQ-%kFT)5mFJY_Cc
zZ9=rDO!WAqSx_>OgHOeA`c}Q=m5y)+Z1%3I-sT&K_alRz-Rtw*ZeLdmHyJGtq@jq7
zSlu#gPzR+P9)^M1yyKuuVvuriPUM_Zaf${6W4$3C{;GE*QG=Q;Aqd4e1_(c;0ASMN
zBQ#u16}6$}>C&kg%4eGMBB)0z&U@FX-o_rulykXAuQHT=`P2@LUvrU8_<J4>J~o*V
zP{SO4R4B(m(u`xh2cG7=+n#V^y(TeBjPXZYQOp({lbUk;&Ch=H!%4dx_!M)6jXN6$
zzF?4mSam0$tux`9n1M1pAPT^;zk5lUgEH>!4MC{u8ieyYz1x_G`=iph>tZIIk*q1F
zxvw>znG=M#)uU6~Al+7$$HE><88yqD{csZ%!xtO589g#-Rgkb72Pe|8Sc;AAU$TkN
zUBzOOm9x2$Xvadrs*#hAN{$?X{VBwd-7C<9u8bswKD>I;XVB112j%K2?oEX`2hxmv
zX$u3~Qf^V+j$|tfKs?iY#T;i8hGZ1Iq(hXG7^AI3XHY%qrstlNdsv4nEPfQ74OaU}
z&m0;<aL1hDm$gIoY_+#Ipj9(Fo;Ol?&x7++`+p((GVwfPr`C|4aa0S)dy_}beN7(U
z$bQVdyPl$u$fK)OJU5~I=m^K4%_mwx$cvtO;L?4eIp^`J!roT@0G4g_#YnbuH~h0W
z^`-4*K2%6<Q~^ylOPWJu;~7vsw7+5FJJ;}|o}&vyX}lw+G=}Z7+Mo7h2bTP)MZ9_8
zNi=@(hq^`f$vMX~({nF9YS-D1Q66zpN2kv(+=P+qia9E<=7K1FreCE7;$zhDT7yNs
zlOMT1%BCJ2x?{=#k9uCpr*P+ihv&=LjWEk0>c=(Ff5J9EJLEuqw8=DUcvQ2_zd=dS
zmsT}WCN->6+)K3qV^%I~8rgu90$6A7W~3%NX`9H9;P(|A@)vFFa&gwU>L(U&9ZLHb
z9RRB~uq3AqAXEpD-k>CUidgO=hCuw1I|`U;$0S&NCQ~M1Rw>R2>rzLd-MAmQIQ6S>
z>$9?tEfz7;J!((wtG>lR$6;QbI&ik9EUHZFt$b6h7TNOc10>+_T@|N_F9dm<5IsB7
zf3WTm8I~`)GsvuKs3b`YZPOfAkz{q6m)<Z8%NqXx3HgOx(DgLbA>QkS2ZDVolNLeF
zBp)f@*1WfI+1jjeC{8*GiAuwaZgm%W+%~FKGnW1nSdXhss7<uL$^2OFTz;jhu>lN+
zB=SdE*U}<px63)$-0nS1V&rtjnYI0-vbeX55=q8=YpjYpcx?hM41{H}YnQW%2r;n+
z;rvIF`PRHL(&jIay=s|u!i?3}F1(ilMEQDgR3enA3=RmZ>K5`A^3K_mWRHJQO-Pp#
zO;1OMQnoTcM((O>i;Udqm-u0~Z&b$yx=T$`OG%kk@H?YY>SEJZw{}GfHa{v(MA&2+
zoL39E4j6S(d8NEDUs@GCK(0FJ=dzdOA9txe>h+$r<{;imzj2y@*u~YYC9#`5R35nL
zQrqebVM$Ptv~ybbvcq>7S1NZNzLm_#ve?~p9$S7Qi-FS1ap&8l;}`;+rQdm4yk~$J
zc_y=MCPQf=W43Cl&g*d#4lu%<$79fSSz7l`WB?3~4RJEr_1wQVdh4t%1=K@v$Uc;k
z=@3lZJ~^(KPUk$MV~k5_BXwmR4Qa*};S6rQdm7yyA6DrmDUadDjklzkHKoWn>-`cX
zJH&f|{{UvQPL&`0^BsG3uSRVuQoC4uzV)9jfiPlY0IdQzrPB%!=<FQyE7VoU=G0<9
z7V1ttYol!z=|RL?ezgpmT*^uEh#>T&#$*2gX==a>PFvX2>8|Su{A%9SZLFV+p$8f1
zO#3k$0oTw{uw2Ny)bH*ci>S->@5N;Kav6T<UO6CgeXFZ$U8A7<X^~oiBDT;9oaBmO
zbI?35r8IhIYlK$MJbH0m0$AHNN060YO1id(P6*N{V7&!E+Kt5XvRg)W^e%s;O9I8!
zhMJMLoQa=$=dSeVZ&{YkAcsHQt?2Z3n3lS1?(JG}Tcj!iC|XtnmACM8EW71yYQuO=
z40ILKk@?bNngHRoPXx~{C)4f>Gos@-2S0(})?;{oRAnnQkIp)@Yzm)#dVM+i*QR3~
z>2iH(SfwV9BA>#VoAk6li4}vXXjisHM6m_Wa&wCJk~3UCkBoNKPc*6mdeud0CsCdo
zs4S7qvEOw<jkmo;s$Y56C4n3ohAV*Uj)YZIrn(x_o%b~(lsEX+g@SHxHGl}c{Y_%V
za>xfcBE1UJK#b_3dxqJyaugcd3x`v8kgMW7lufS>U)fyg?Q-M>Q-Ynrtrna6LP0dy
zTUhy39A><`O}+art2`>?q3EO5wHsKxxY=xlvfUI{u?QYTM%%g2>i#2nTkP<Bu&C`(
zX<A+N+>uW_#Vu5Go~=;nx=LGYxx8Rs8B{&1f6ks}ML~g_V06V++9NBP_WKqA7{Wss
z@7|?bm1xNv0n;@Sz|9&*&=0*+rMM@N!q#Mv4dJ)s?>>~R3p)g7E1VL0)Un(_6EuW|
z3USX$tu^}X-kB}vD6oyVWq2d<q|2e~dWunU&^OAVqCHggteCIbPFp7(YeL+#k*tmU
zU5#ZZSftGqWR*9@ayyRVq#r08@#|U1BBaHj`KD9z0n_oV24G@YlpG!%Ju3+-8m1C_
z=un;r>s&vGbVrT}<c2-NJds_wAY;64K31j>9a=U}LEwYjQsj#%RFY?$_-+|h5Rrlh
zPkQxhZeT&|E0ldDBe?$nMsSEbb^2FRWWd{nKY2$YxT?dEo%H9<u4njy%`WWrKSRN;
zE&MwW3aHFB_Xn+d9qeLAN|FJ^VNYzR39eb2#N}U0ySGPp?xfG5ImKs*wKygJ0FTKI
z4|?6WlIBeLP{_%+u4;>0y0%?T<Jz+<Bh+<VD@Ne2y;%O$)b{@JA@vmN0L9AeDmWuG
zu^p2;1p_&zgw9nwJwJ%GD4%IqddPA5SF33{UAC2GkXy#8sykI{3na6MU;xLHinJzl
zm)g1(#%#4W3r(|^B#LCt8ajr-$CyTXP$O8j22Dg-mE2>kLRx?nlSpL6M$d|mJB<KM
zyENrB9yp~9iU5-|W|_a5UE+Wgkxd7hYd9j19F8agU~x)KF--?F0V2N??BrEqaB5I~
zS_D?UkO){GOjj^`s1&4V5kcfFTh?^|j$sF(tW!CB=9wk4b&@gOfpU$ID><d~p&T*f
zQUgbLJocu2rD8unKE|uP*2uPuaap$)McClvnqn?p>Li`Yeo@8+XH9eFbk1rSPI`2x
zvN$vfz|Kz%{HPI*ov3F6jPhzRxHzCJGDSO&pzl?r7zA-v<!p{BjHL1nB9T_%0ZjE3
zl{yk~I3AU)BAfy1Rc4KNIHb)HkYMN9nI*Yid)ARvR=^b56g^=zb7->>(Ek7xW!=NL
z@G)H@+vMQ%HJ@{805wroA-kO0Kzj0OArUQ{VzuSAz$7kexQCu`RKXRNG8Z*jly9v$
zBJ$xR3ePLK$*4@y#P*S8LG`C<NA92<s%S`63NcK%P4Z<=9+WM?=uo$2iN-6YvAX+Q
zEgxAIrE{V@^NO0vc`fBKCu5vc)Q!rgBcMWUuHusfeB6q&ty_6)mr4Gu$IVeYt>v1{
zAKx8CU$%6<(q7g<`@p<cE0a#<=6rZ~0PaRHSmd-f4i}BJpf|ztx85B`y;izhmSR6D
z-9CnIK#8Pg6Cv9oo*KI?4_1y=L2-nWJ4x(oh>A_CjMlE1JW@)L%Z|7??ODzyk(JM6
zv`Cp%;~=T&iqekU7|QT-TwaMC?wc|ZC!KD@U=z?+acbf4!|s~al&*5tR%K{3!4t7g
z=QW`edlzmg>N%$<JFB9`4T8d<xWK7OU~$rg2R-<wu*a~bNW}yk)ooJEZ}j<4^57D=
z`c<%L%65^)bK06EpF8-UO=zWLWGKs$2Tm&oPum2ACF$#4yYUx9^Cejq0cFk(JNj3a
zHG{`1E3ZR?iq5jok(25%!ZxC2s7ZO|u<eSsHl3fkFgpQMB#X*s1admpJW?IYg@K17
zsi(tk@<v;pJJl4IXvbkv$9!Xrk#Yg5<pTba_|*b+71c20Vz|v2!)j>9t#)tsJu9Z3
zh@^&R6&S&6d(_ILsUb^o&~j?9g6){>wV8%{DXkS)E!c84RK7b~Bdt2Xv0k~UFSLzT
zc+<+$?hbmLl>IYC)+3R;?K*#KEpSf}OWOQMxY3tlQhDaIbmhvwur!is8lFB&36J4d
zbiFT84&qBG)qU2r`rR+)MLJUKRY;i0{uRk;`%UzUMhUM&8eRInO_aFy70PN}8q}Xq
zX_mrrJwWSO)y7h{#EAA%>~W6?4aGh=iVdBsr9K|j3vs4SeKIN;yeq7qnRLl(53SPv
zZ^(YiU5sE%pLV2sKQ%Wg<aOq>lf#<g@%@<~9<^!>4^=^lG|PkZTFzLCeI&mC_A~5a
zn1VtS@s5;5XB?}NeqT!0ywG)NcKLd2{0x2Cd^!fIkq`6<{+nriW|~*#{6pBwvCG|9
z5c^b)c@+q;n<t^JnoTECjFUZ#$_F{cR+kW<ApJ%;6}&MDS|@QjazzU(31#2_q<Z?)
zvRlfmfw0(R{&h0lY#Hf_of)1lGz^bQr6+wzv9aQDyF^Cqz|W;{=Yf-5;Ga&_G_;21
zU<YxWRd4LC4<Y&FM)oaUl9Ff+B%X1RN?BBAHQN|GF$w7z$318lo*RfAv7tVIQFI3<
zrpOmjw<D0PxsRZ)V=`~jMmiK2t}-2OLl+2<K&9J{yIoqbeLS+Cm6s|jDwet}9%rsc
zB$|_zhC)3+&1Q=$wkKt@g#Q4$U3K2L)-y>D*}UDS?}65{o5izkEA~yN-mOUx%unpQ
z_9OicN_f%r1HiOz#MRk+X>zT!+hMy^XYq~u{n(W~`qR1#0MIoy#votCs#WmTq{Hr@
z`kICOORNOk5dih7ui|}F<QY{>FtMzj5!4-j*2bslQ>TLO8}Ho2KMLo6;UU$}{Jnlc
zrd?xHk$-u3`0NEID*@3bf@jaodY_d{JQ9HX`iI~Ja^q9f8L{@sHq!m7=lHH=IrpXQ
zEF-D^0E9BdN6&xy)4$;r(v<x7-2VW*T-VJY8Ja`u^HeiH@nrd~N1<w7*bcY;5v>J&
z{nmfrbjHy9Hizbz9Dlc5Ul}{O`kDg9=L8?lk7@^Ps9))px?96<HsAml&TE?cL{|}<
za8GKekU%-wGg57hc>@&^sc;=7yDWS7!KhYMUJYo$Zza?uCphg*O%yy#UR{k?b46|=
zJ*EV4O%0LhM3H$?G9TeM$fZSI^<zUfH?2(*_vmRFG{$L!W8RAh(Ob{mfZUN$eW}Cd
zpn-Wb=@jSbQDGLRo>`#6fr`o@m9w~m>MBQ_kl-8-YJsHP_|?T&XtQfEl5MiF$7*bm
z5h*=ISBZ+qIjtzfZo}pVo6uw_B8t(`ZxYj1idSL~aB7tHgeyrNFge9T2`7#+IOc@L
zdo_jaxx0=}IWXAdwRF<n*!|&g9tTmH`P=O`NOvsF?dU4N)vmm-3%*YWn$<`wdLN5*
z8)@%iM3o2(JNK?f#1{piMMIOix%qA$R|LCf`BY3;H_an9eN9!wJaJtYgC+93K?`od
zZa)g=0n1jmho?(@VksShuTE(&N71oJB!yerscXDw*By%tW~yoW=A3NP%)Eto?!u|~
zhr}9N=`zI~>`crL-E5wfH#J8s3i;NM$Gk4~<eK(<G8F#BNLOiHovXz3Sfkcww$tO6
z=4a%NxW#&mUL4e{Es-sCIR?>yuhO~dZfg>zfv3H!*NW?f6B4|0iqqD{bj~`DTF#0+
zZ%??9ytTPj^x~q{b=g-+kk4rGkPbymcPWuu-^&zb7pJvIx{UqGk4`JhU*a3v%ILPv
zaL1a7z9ni0i0sckwZUHljHy3%t&l2|*F)7s^zG5VN(I%+3<v!y$sgh_w8!MNQTWsk
z<IfPkK^oRS*!Y=zRhWBte<|!uEcxY$rWcTpng0Os>hXCzW#SpQ^U-+iRb=rFzWkj*
zhtO4jVBg}YAo{}Sk8d&@oVfo0zNw~Y*Q|&>ro1t=U20#ysLO-tQJM88``5Fd_z|c6
zuhRQcVfBaD_cp(_Q}bL#Kj2jv)wJ{necWU5uMXLA;BKB{{{RA}n@1;?kgvN{tb+`<
z53ES`r|}+=oEzwe;wroNyF_34eT@D!<EKwkj;HaX><CZ#y4pD=5q*+<yw6#e$66F%
z=5-`?s?z*K(GfupyXXyhf7n!XMWy>54t4|ErEIdSD*FhZZ9eCsOYt*FQg%ln{{Vp1
zR`{W2KINpjBdJ>9MYvz!0-NOEj+Lx(>@wO2msVZPomTceLFBkZW#7&XVd;8=mRf-F
z)D&}rSEXFq9A|-8=tADb^8vNNHRwhuM#g)cy|ej>ul??8Q4h`lteYRYm8?EfnxPU+
z2Ia{7>Z_>o>qR8qryrG3nF=xPrkWEt4NZ35%AjCw%~I+sOIKW9N_~09rDmR$>_g#4
z9JeKp+MEff(D6?ltD+`sUO=WyK3>%NY{M~+YI4{kxmKiytw!Bx(BwB2&bKvt7Z;@|
zrm4WE4%M-P3S1mfj%e*bgS{c?N@&Lv0AheJDLc}hv;e)SF-Lj_9cTccangzb_2z&M
z^Z`W~$@HKDnlVRuGe89Z=88H{FwSVeqK@<k0sN@N0*U}TQH;?+98dsg?dd?`j0ylK
z&S_~V0HD!EO#mGz%^fJ~Km{FgD5DerW{%W%%^A%hhgvAb2c-ZVs2ym}tsPH#U=(7G
zDKkI|oKR0Rb?r&dGytNL(v(tQj+6ku#hNijd7~Mi12mqT^G6w@sGtSLX$Kvs#!Udw
z0n@!NT28c50HdcgV*-!EtpEq59`sV@iU3T}OOJX_!hjTYqm0o(=b8WwCt43mJ5T{Y
zpwgdu08W&-qym&0006}x$F(WuldoC;D58wg02B&8ogF9u>FGvsM|wFl02&G6mppn=
z)9FA6e;NtJ9XnA##2nGz6ui-j05On#DSwqFG5An=Pyk209XO(nv;ci+DSGvz88iS6
z0qsER(vH-1>qrAMaYt%9QvpXxUV11j-G{9pu7kpwNz`=(k(4xXw;x*K$717#r0PiO
z!q9bQqI5nE@Nl>(d3rJr%&FSF7Up>EVf#J46+pqoM1^cE1Zjo9#w#_XGD(t6eov0Z
z)y7tHlhFFg6eCVHL=!VSnd?*k0Ac;IFj@?Zed@6kD7beS?^?}s=fUNvDUQp<aZ0qJ
z{nMpMt&ULW;x{WD+^7e*G>Kxcu_k#X{{Vip<%~v1^!2I}$%1+5T~Vtk#?6n~NscI`
zNFyS-jeo<@+{9iL#Dl$b3qIa@`&7(QXo&T$+zvXf3aXS|hc$XJs~%Y%J8=_1DUHDl
z4mqfMkSnk8PLQ!NyG7`@BDoWQ)%u1H6C6b)IG-bm!@4tZ8;-PcJ*en^`t)@;?_Fmw
zo%>Pg%_;Px&pG`l0dtB<2TC(Q00f#knlt!O^q>RjM|xj+LOGxViV63m&vD+4L7)ZC
zKJ*$)^GlDV046a?I(pJBIT)qmGyr0gKGeD5l<;T)G1iXsxxu8(APP={kxSl_p7aa{
zIHMf(qnbK3Fca{l#%RZH)_^Dg$27R410DFICXfq?ZU?<DdNbO953foIp!DxXJ*j{i
zN?x>wkH&xu@j*OM#%V~+03rHNe<}#Y9QC9D*BsIHqn@<Ar~x|C5Gltr)5)UX7^TNv
zGe#*0>qW*cGun_+;{zvvI+IP`9zOTvDRUsR9iG&mg(~H_RCXWk)X`ep+-J$RmO;>A
zX>*{nAvBrAUri5JkbJs)xb2gQe4ZZFqK|x*s-yk-mr^~-QD$i4ie9zQ+ITNgxrjSS
z66AEnT!+9H2br%|=#>t<7gD(y$m5Drz^<z6!Aonm{VrC`Yg>39OAxN}Gm<$wy41W(
zP<u9c@gRTt=*p0Kes$@wcr!&o{{SAOpH?}lmmVI|ZSR!@vIWmVDn7Ll`!;#vvXRD5
zuoWW5D~zqY#Cs)r{Cah=1=(#7Tz___TUhb_tw8!zeQU^m%<;Ibu4ZLOtz~8>0Bx(Q
z;q7Kj5n#hTGQzzKL*?pfp#UYi0b5>K1E=dsSeYUFBzaQ!OIcx-hBf+})9rjEsNGIu
zGDjF4$j)ojj77bxCIs22k)Kd%KC?DIW{z4vhqE8`m*XGorB2=ff;gFt+@-qpuH(zY
zb)rO8je$L?ez88|<VOvrcrwOUkX$pq-odMKKL_ZMpZN9-kMC64eire^@e!KVC30y>
zq`QYIGAGb<c&%G)lzCr8qeZc>h87XqN9=air1&tf1FD+M(Vym-ah0XdE?vsyMxY2d
zR8jO5PgGL&L<Iwp&0NXt#Y1$A_R;{k`Fd2Q7Axte7R<aT2NhwYQrOK>(-KLQl}F8<
z^`e#%mMxrQ_o7>YM*jdFK-e;OXYi@C=G|nY9SNx}?8;idn<DY*Y7H{t&N$=`a~S7<
zTAJ7kxZ^cLR7EhRMsa`zT$5GOA>vEufgORYeOJX=3ft{Vk1?~x&T~X!@30z{ExOe>
z=B!|v<t;pSrP<ry!z&)WD3jt%kRQ3Rk-oHhIrbMaHuWg}P)PZDRl6|HYK#X2R|Tke
z_Tu$IMQD+ysWnM_X{^T>SmcNgaat-9YhiPv)O@GU0M=Hi5R8U?53YJwp2_0PZd~rW
zE1&L+RSESQ+lKx1<j?hLrG}7uM0*Sm3qq&PLC1EcNqJ!b%$Kkz_iFK}C6-0`t|cST
zwMJ8L!6f}nKdSkQ+8&pxYnoJd3jY9USNBfUFZ?E2Br$;V5=Wq~FaUpaQ-Y9By*G!C
zQ0F}@d|{^EN#wyCtle{pzU&?y;9wrcywgfMbr{bio-5KLJMB~b+W5@&l7(es+Q3fn
zASa4U{b(bTK;ZSS5cMu0_od*PN>0=WcLUap;+sk{iUu#WM>M`nWyt^zwBypSyg@Uq
zp+q>{>s|SN8|xM024P;OvxAY%>X*-Tc_C)`7p5wSQTp_t4mwq>I@zx;L|`0aC53*G
zQgFjizeIe>Qma#5rv8Ouuv?ksQV(8zYad*=Hy7bqh9k}ZIj)aVnQV075c}J4&2dbj
ziGFt;r`EjeqMWKXh@VrZ7}O%EApIzyXEdD;wR^{$2kA?Iezcuwc<N0lJ0MEthLLOb
zi?wdcp0(dc3al!HMgXpR!**q25^cfjlU*nWIrXp2v#evSiD^9%^!O?~l+4{nN`~$>
z!g59{kJL2TtYyJcQ?ai@12qN3ymO%q7-B{Sdsg{wc~cK)RMsS7un?=PcRbYcIn7+O
z)MvDP=_$weeJe{<&>j~LY^Acitzj}U5*QUehqZl-Dq-=ouev;E3b=V4mYd=fxlNL(
zR~#G)-d7F*uQjwJT*effmhE1FW6U9raz=TtiO#Szu+=|z)b}to<yJoNZ1L|w`cdAD
zXT5kwaD$3b$)v`5QuLq$6ul_T08#<c0Bv8s2NmX5sj~WU#y9a^o=5H)yt`ff-m@}i
zpGx}9AFF6d9yVbcyOqme(iRm|vBwnB&5HU(QJ!BZZ*b^Hqk0DW)k`c#S}?@W>M_{2
z=P0H$=~YUSd(&BQQ0B@=nWhYS)NTPBnvGX1Dq|i1<Qn6s?#*IEB37vq6haQ%;+~1e
zL5g{gj=d@n#cB480a2OX9cfC6Q5I{mo!OL-&o#)+H+y>il{&!3qLMwS>uVwCy{lyj
z5p-3{6G%fI)qGjXc~uoMY4Q>kimrQ_e$A84jH4U+8h4b~>02qL3=Gbqr(H7HzV*r7
z=qkOCokU=HTnzU-P$4C;@6cCBmU?7FZgRzV%~)2`VI-<4J;|r+MePn@ZCtiCHhz^d
zX}2zTfzR@;l;2o|$|>W~X&Y3v94a{a)ha~$Lk)CGo-+_1jZT^qobPoQtzYd#{us%o
z{{U-$b|r3cRqRRjjG_I97#};cf4jvm_Do7}mhRrUtN#GnvYwE~kEJK}rOD`n+lsYK
z3Djjp(;Sde(FeUqG`pPb5yqMJsm<;2BZ2q|Pqg0=)w=WotJ$J?*wLb0G3I3-K~7%}
zx&HuLaz6@o-9d*t_V>jeMe8@p9FJ0I@*w75z8;4h+%d-;Y3ZVA>PTkEJRBN{tZzss
zX>9r$Y18i5<6#5+>aJ3GnQ3fvn2*lG)00m#X^<%k7$ewbsDEYLoPicG)0z&MdH(=B
zN%~W;u3T+O(m%NXBl4)<T-)-b01AWqCiS=wWOt_x4*kf@w;x)ThBdXx$>Box994OB
zTbDTxgYCs!{{Vz<Qf%TS&$*`m0Kze;_e9Uuq_kv9b0oy?Vslm9o2E}5^}7BUzEvT-
zvG~<_bRwDGCg%SDXQgK(%Z-d9_qjC7kM(?atqJUeV?DFn)hVM_=QZYH6HM%;P(0J4
z8IgFPkU8y7hlgBb^U!)$5Zux1XvB;c09A;sXPNe-ZTVH3T}IyCFZlH=dSviw@_3Ro
zQ?>x0dYblW@^bsk^XJcf5%jy;!7YyDMcTuRSCQ-9WO|gSi<Dnl^}R3;>`P=kA1QJV
zt}D*<<X`P6eo!)VUJ5(TP)OzZQ;N^jCuWgHQU)udD2>2T`Byus$Fl2bI5_D_rpAyn
zE$z+Lrl?5Rqk99~dRJEzfdBvi2LKAj(&7PTlbo~T@*n+r(#|Uubi~z$Zfiyv>z|H7
z4PJ&*>rmOUM?oCor;6#Im1RtBUtX1q9H-W&SxKq5IGVbGM|lXjg>fL|fc36rwMVy<
z<-lz8HLn!y8)P021bWs^vu3w}q>WW%1M{Y(VtFnk_ps_v?PXo!u%u&eDI)_19V;H<
zYt24jr{r$l^x>?e-|NO3)KzX}Ya7dOuNh!>e@coCLK!3$cLO2$NAxv^_SK1rSIU}(
z?&TyK(aNyo5!#UKb<ii1GeS>M!Kmehyvz~JWoa6x+pYYkAY4Vzp7qp-)_ZXK^4RC=
zKv>k#pUH(r;JE2jd`j0bB1>yKBX!{LX|{KmA~(RrTbM1{?B^$nxHCDUkWUh8R>ZD%
z5ynZzYGLDzWd|s~_tkXo;MpXPb_v~F=A)whj!!JEIL9KoQ#sg0@dHp!WrQ|88oE6z
z#?N~ee2^S{<?mci*vB9!#XblmhF#IN*6aAyi0<zEYAo9iZ0w$(R15J3OD7T_9C}qK
zE&knZRz&T|tSkQj4LoidB|BMu_q`^Bc1hzM65|<o#(hpI%4=FB!jO_if8avA-F!Q_
zl)1*<MP7?ax3ogVH+Rc(O3Y`Ws%bK*Kf4|Itn0V4c|t^2r{`RRw|6Qw#^pg=3|3pk
zb1cZ_W>?$>?EBLL*YrCO2>t1G?ho*q?4W`ulmt*Xu4}>eZ5EiXAq-ds&%Jd^fGSu9
zIi<xeb44H<jL=0dN-;nU#V1OA1W*GAu0zL`Cs5K_-FmR&BD(@Yt22-lc_z5e5bKFP
zB7_aU-W9zHZgMlJK2&%ny`asdv01RpPI3ic2%Qf8as2DpwMgx?B_dP|bGxl`bLf`0
z4#8LF$I5eFjIgTO7()=#IXFIbQl`62D^O#ld3O?@lzQ=8{Q7*BHyC8X`kHHM1{-&b
zHbLVRo*ta3Pg82rjYw!tu8*z33@9-nB)RNsy@OAR$`Ipg%>3@hO7n|NChA$CxETZ<
zJw<m~eZ#C+n3rW3&TF+sP2A#}Nm$vmvlGp}cgp+Lx=9Rdq+q{qrE|$~Ghll9RLLXx
zuKD|;6>R4^2Gme95I#ldbJnOnr!zwG4y=A%zLi=vD`JhDnK|aBFohAP_eafBU>W4i
zG-`yB9D;M{RwdaCN2U{sY_}~9yGh&bii%8#5nK4Vr(qX#<W`G(j1*^~J!<s2kz?gT
zG5kCpg0Q^iRp8?k>q%P;kM)jmNy6nObapZ<Q7jhYB=YWh)}6G;8yFQ!lby${U?s@2
zkIIbx@=SBw3ebl65+{ZxUq8z{p60ow64Ne4a*EGr?a$sr*n3hf$}v-s!NIJHSrYQn
z8>RmMSqtIDd-OGY#1=pokmHPc(aT|6ve1a-enBO3SgLQ@=%URaaB{r%`c%=+aUJ#>
zK2R9Rs4n#qo8H+8o)`T4)J~T=v8^hu4ArrHKo%EZ9sm_{$`ZFc({$ZV9bUn1V!&W9
z>Uyd4s|r7P^{*bR9A##Duy<DnwTTcDg*o6?F{;lLcUas7W%%=5)O7dq?T=mo9gTT|
z_>)+Y;Sy23*x&)pWy;xiJ=)6N8KFrOFC(>VTU!W#C#`b+1k<nM)0X1#%QNyr9-h_K
z$l*>q){%vYlP3*GIcl#Qgtay)(Jyv80lTJZ$u2ngYMrquaKp7-or1<|KH0ZjH*r83
zxy>Osq|OC5GypSHd+^kx=9n;fpb3L!jMG7-{OADOXx&MQQfL9C>B!W~@k*zhb3hZT
zQ-f4s)4I?DU9f5^i;pVV-y<M#PL{HD$^5N6?Kopi63$Zg>&%^`Eu53drlry}Wl!F!
zGRe5}O99;2%><U!w;T?>l|E7>!#3AF0jkQzKbZCHP){eFkl7-TgnN+k?IdTdFtFWG
zW4>}}tmH0wP%^>!`4tR<XyTGNG55Ms%E04qr6HBfyIY^mnA05Mm5*XN)K0nSObK`A
z6&1`)w7T}{DZ_(?9EwtMI?x3s8P8gRMdR32sXktuia@)DN{m#plQVV_!-|=0HzD_{
zpJwmHPaGdFT9WQ%2!=M5>E5$%Asg5Mftu)Ng@7as)=k8DCpn-DIU)fLD>2ZCa8G*Q
zxQA?i(y?V<-viiEXsEIsM`}ZbJmRs?l0X%we0Q(QoK|#dLu8IB60xPpfhPbSb5=|&
zI*-Ppw_M4`Pg>FlNzGCwMK3Rol~OWexM7Ue!^f4#{Hma}&Bpw79Vsw|<*hbT6Ecsu
z-HmHN%N)mH#(wT=D%KJt105>Zj#g}RBaxcslGN%?L2uOgh4GEYl4>|$6Re2blD%r&
zku<jMjgPyW)_s)zRnSL0_VHA-S0eW+2zIsz=|K$~;HRjqIqh02#=-)m?ii)LwJR8u
zE(d-p+PV^zndn{-z8CgBT!l=L<PULOrL=otK&R!e7Vy@kC8g>*90enClhjwS>Gxvp
z!6%H3r=cAwQPV;zuBGmcjQ6SH<nvY4^Vbz(Gq)b~(vDJkbb|m7T8+73QU>{X=BPtR
z@7k44X{7N<6o5&#fFaei^wjJc2URVCRO6wq7T2`dEH2qfkgRLnw{096^Zx)H+WAap
z#$#@CQ#kWP&7;dj*i^$OPIHREyCO@LWh8^mZC|0471w|{$7;@k2t#Gh70Vp}pcDa;
zMIc}^#Y=VN`K*JYo+`XR8FrJ3+n~$3SzqlGBjqQ7?_Q_jy#@8lwcWiSOmA#;uQt=6
zj9jkVGY`(bfbg6V*l3W9{Oq~Sd6||u;pn#=&dfDFXLf8_X}WciDo1M>z{cV^s+ae0
zBN*a_FnyM+&2SPXBDwh_F8i4BYvKO2UaNfaJxX+<N%pq~f<Gz+>-$x6&O6d|9MU>@
z5o_(zbpDi|ZkyCqeg|qy&>V=f_StjP(i{0n?NzgyQ9yD;vG&<LzbZp}DH!AOs^dAJ
z=NwQzL|FS|xb68+FC_l}BCGbLqQS_C&D_4<l_%Qd_WY^?MFQnSuW`9>$gTAi&UlZ*
z7P_UgO9BY47oV4m*6u05;kmAgHK#^OP-M=OWUSHQR|;T~NTpmnXAPQ&T{<SjY%iq%
zUqPV0b>2JDg|4mkl#B?ZTrnQJS1K&k+bj52+hMClwIx32@Uay6C1Mc)nZ8~L>xxM&
zN-*9k><~Osf)07Bw~!l{!z$$aS4XsWIgBwH0ni$e7n}(A^~Fo}H&r{bq;{*(O#)e%
z<Q%R}X}JLvoFT3wVmU_*UYl)??63hi365*Yqq$*o2}S@ki__~~v!|(TDGywyC*GWQ
zG>XvSwI#*TEIv|t)?Btxmh%wy=~`ORBK4DucB(5dhYDRzX;ivoG-X}G9If-<GVm&`
zrMk7q?}q8?SM>xE+yIO+MtGvi##FjTJTJX%N?HM-HJW{t@Hp*?=5DRba-5Hp^P26X
z09s=mv0UByZ#^(8r3j~EVdu;9Hr2;kvv*=G)NF0T6#G&mQJTIax0vl@<I^?CQc_YA
zIpLKY)T+Ub4NG|%M{rdE3cj^pAP)6gfnc4Bl{DwQSGU+l&FfV+5VYu_l5FivpREZ2
z7UD<Nr9v2B(<X*UTM{7#k$Uy216svEA>9Kh^{W!ti-#=;$FT2NFx*Ihs6186O+r{F
zSI^2jR#Hqv*78kY8a~AKsS@Gk<3F7?{@`3m<^|jItoNM8+mXI%j!s}Tr?p9;Vh7AS
z)*B6sS2@RemR&+=hSec+>BT?*2j;CI9#yEvw3%E}0VE%#HG#!T6i!Y+s{s;LM)s=)
zLhJ2KXn4*kF!A!rK&cS}MVIx>T#CXns>G6N7i8Oz)QfWJK2uLnEj6H#KXw3NRnZ+J
z+D9YOrnkPsVE6A=VqdgLlwNa;)V4AxB*bMIdi=OG8AOelisL7xZOd<`tN|sD%bboI
zy=9w8ZbNK8C?}KYNdZBKJb~Vsyf182i3F#j6OO{8c#9r*2d!wB3}L*S3<`~aQ}?r4
z5<(-kToIGk6`JGbBQ>HKAb(1;Yx7)00Lf<x1yV!JS&BxAMU^_C&U^k8Fh|gS5by?*
zaiYZ6_Q9vdNepXSTkubZ-%s)(wT?N6`AF+r)|2CF-6zBF+}&8o<rH6;I#$1jJWDT(
z?<GrkL?SE_<aHI#c620Z=zbp2{4omO7!*hV4I%AaAlEdRVlDQ#!1rpBO9*Du+TLIo
zW1QC|H-ggQ=(@7(UVzj{q;CtzFBph!BM48gTFUV@jT`8<4wI6_4^zcf9uc~>Kj`ih
zdscR(Z>iha&XP#(gb|8MakInjVa3$hKQMEjN?;)uoC>pcyKW|5_RU%F{j3+hA%Yv6
z6vl9RX1y5fa!Abc5dQ!b0hISA{sL>=VDRRQkpN<ck5DSW({zZsMIYA{rHHxUf;VIG
zK`VU_)W2l9*c<F~<J~LXJe?_V`?&M;qVm?&tX-ps0tXlsGDAm{>HY%oE~5g?29)MD
z`=qd6=UbNF2>eeXg7I4?`_Eq0;d!2Y3If0a7aR)NT#lx>`L1hY!(#X~uAjekXoJ|3
zS0eZ;e}TVLflq(kX1$({{Y5*4k0VclZU@b+0rZ3a0IyH~0EH%m^Q}4hMUU%Vv5$HS
z1RI#~Lu0YxF#INsd{mlc&HSd>;W7ta8-h5k``?1vKbN}N?&({&W);)lT*RI`($3-g
z$Yf0Bx3v^^vvrK&@(46@1&<+rgVs?T%RR#ntv~)1K7`5g85RB7y#!5v2;szoxM4`z
zfGhr!Xa;)isa0AIRCp(fGzjz?kF!P&#l{6<_&-Ls)_hU+Tbu;)%W^vNUDw37isMj5
ziCGvcXLsR`=Uh*Ot{&6IR_>b#C|Bk<&27(k+?yRXsi#Mz>d$8$;;NyAJ2?WS@h#Dt
zT@1(-yrG;N=Bq_KZ5SKIMQIm!+)STwL6K54LRj(YGf-qQ16E;f0L@U22VaE8df5PE
z9zPnzVb;2D7N*;<eS6n3PHWbqtP#mSh!d?%>rltmrUQ!Uj>b|Kw`xfSV?0sThW`Lp
z#Z%anQ(@Yj9}P%&IiypDu70N73#-zd+L*m5-78dJ$7dZV>N`*k9<;<5qcnaL9<%@s
zw05M&AJUGWS^!*PlZ?{!r2cdOcB7>(Jt#B)cjl6cJK#_;O%!9>G-vam1GOFKG=hK@
zj{MSfpb7*n6n$vV27!la3B?`yicFtM014@uT+(AScBBH(Fa;;+Mh<8I{AlS%^P+$Z
zA4*=7b)>}t3}%-&qaM^6V-7Px=|H3LqyfzzT0a^?k<9=Aa44nv&}o33`cm`w(o&8E
z02EQ28cg#@12n#rgNisb?g5TH#V=|~4>SOG%^h>vfr>iw{OJH5e;PV-Mlv%-C;-kV
zJv!0ejQh|5(wC(t(vE_F3IU_NEdVBS?MGT#Owa<F0i@?NV-x^TM-&P&Xc!Yk1DY{F
zgEVJ~2h%in#UKu&tu83-M?pXcXrno!sGtM28K9b6b)aHr6m=94N(}%9-jh7i_B50L
zW|N9u^cp}E4sk|v#TfLa0q;lBgT*d+9Vh`i(b|DQ>SzHo#T_$86r-g81FuRwX><5e
zA8siCl<GUu4miyWV}^P!EO-^_J`=JQI(&J?;sH3XHn5A%zJwEzyc+dOIaVkTbO3a(
zh~lh7tr|%B9HN$vY}LA)vB5PALoMx9n&3+(8RD&{%7VTkQL?e_mORdJR-tc7%vmzr
z)u<&H6^!GdB$syW<(UOwTscyE`&UlK&V`h8#d25d5<)AZ3ho7SAq~l?t?qWn0mjo*
znW>xcUWB5gftU4#N$q4pGshL?H!zqkWQg#f<$jgv(SbAra3;7f5W(c?B=laD^_($X
zxXO#@c-g%a;--vo!K3h{$ju?Iu|9A@XvY+B?Mw8aLJ>*QgGat70H7ag4JpoO0XU+J
zXT2HbkO0Oy(jK(Eb4iK-PW;mM=}X>@w7_rjr!P*F4&3oT1El~2<I;eAX>pIO7|Emp
z6N*l8nht#_*q~wxG0iC-g%kjt4F?97w;a%T>x@tU1sJ2J)7F!Euki{^j>3_F??D{U
z9CRH0Daxis+KSA50`o^Q6^4Ek0g=sIO)pV?QpR!*a+Nsn{<22@0POh!`j(~bBiwdo
zZ)!q5xvh&o4QjXKszK$I?)~dZF92%}!+ek^?nY`|XfC5rY~?y0w4_&GFT?BDW8QA#
zZ*8@2Oz<7O#2fDBeZzya;8Z+B7PlX>X9!tva(Yp{K+Z-h)8g<Rj}ZBzXFlZ9bsr1q
zw$UTSZ5}-;KDQo)dnS3H`Hs~DpJ7t1rQC<)w4H(Ic2}=i*jpu<6oE&}&lPA|qJIb<
zg=F!Mu+<aBMxB0U5&e!(?fv13(~rVB%)pZpMlr_Y&3C$-UR~-Oef~4)TMHI&%iMa@
z%N0I_swneF{0FJ99%Rucy3;MZ89bN98E%(q^&xB1{IR&?);q=JYkP5zm{cr8*!_|)
zQ@|EV0?TzX9P`agd<mr@7X9fX)w<VX<thFiedz>WnW%NA+<b`Rbe{}qLU#rN<mZRx
zx06V*i-fd<4`ijYi)N<YpEnh)jC&7CQ>iBR8c7*9RuG$K#0kLcwGNSPf(B3k+TE*W
zSWJ*h#tz!d)8qZ*fDhNbE4vJ_pPLm1p%VR@f(Zt$3wI|wKs1*&j`ofU<LOeH0v$3f
z_F(!kt70r>q0$f-U2~DTv`iT4Req+JBNtVG2$9M4$g5UkHmFJG6uPt9MP_`-W8<E+
zTE|(^MX$|$2tV&rv#@Ai2m$F?I-p-U8LHFxn?i_XucJRhSbEQkw4JHsktxq(PB4?`
zE@X7^g3%$yatAc+tWOKga>?-vO^Ovpf<`0L6$AWBw_NP8a=nSC>}qxwJWZ>}oizn~
zaxq%sIR-P{yxRW&$9GqA`LM$rc>eg#X|3@KSpckS2px{v)7VXiIz2bZa!IUNB51W$
z$;RgOt_E)$YtsTg(HeaPW=XB;GTa%O?n3_nUIjSerPN;09@1h1ac4oF_Npl)w2gmx
za~Sp}yjArp`9AgR&Hn%cs2*uqgEZ0-JzAQ=zN}u*^yJkv*fk8j<b3g*)#-dkqC!sV
z=>Gr%UO+mW;OD6{;1~O=`BnW{cNerhI_t(7Jbx^5w2ka54%@~ywzpD9*76i@myW+$
z=OVI{MfQnM#{e107~-H^V%j1aJ0T}*$bVYSUd9?WQs-x4-w|PtJ1ofqrdq4d@fPxU
zWDwb+XN4r@vF&_Ir!gsWqe4eOdYYkqHLS9iwuD8ys)NNkUdnG^mohXX@oupTvqx}?
zyZxGuZxm~D62|$5`=g4;&S?Rzk7o|XcV)YcQvT!>n(|jx`@?bOs+S~lyYXs6$E6i^
zNLLdIPxYn1AHp+AI#JMe%>n>;rRXU!k?BP+4CCoa4Imw<Xb@(Uaw!W19J1z<dXvKn
z0>i-OfyF9D@*my9B%kgfHDxsILP7Fr_aBPlmogefU@&RGRrS#IMnCcAv)$YZo<9w0
z3^OC!$NuwXvz179DJE9a&fB<%JsYX7N4G!diS({I*Tanr%Otvt0|%n6f30>_@rdpA
zqwZf?`0gO(ZAl)+UfR%r@W+a87^gTpjWpNJ9>8ZE=|37w(dkSD2PT$~QPBF*7!S^>
z-&v*F6=eq_6=;t1xhI<1m041foF1gk3QEl5W$?Y<n0%*FI~Fyqr09oFR(Y8Whn%lU
z+~{g4Mk8^Yan`*mxvnD>YIPomG;oyZ`_V@u;!Ca52v8IA79jSl0CGBFwDq+Mf7c+6
zwVRy%EA%WJ6evYR`OHk5sy4v%q@eYn^sb`;M@-bV(RueV#8*3yH3;kNTG|92W$|Ny
zux(uX{{Z@{gE6n{aPpDSg{RL^BeBz=SgpVVZcjs3I-g2nU?2c?sX7Y$wsLZllRmC0
z%E3hgnmX2H4Rj7LaBC*_!_Zy6{o5NoK&^p+?MGg`S5*vUY&*R<Sk9#=R92EO?EEur
zYao@RXCtL<Duozc1t|i60I08ssa{;w9oXs9jWuYX=|Mi7X!>`cb<JQ{ndXE1>1Z5|
zXc%Vz8Vv`f9lhxYl>jl3+Pv$;u!Ytgwvt(LO?oUml09pR@oI$BU@AB&b6-otwsj>I
zd0CE;xyyND(v!;rwOB5FDGQwPE9^a-PZyYr%l`monqnumDnlU@(#=P+LCi*DA$wp{
zE&&~CVoo{YqHgsL1*s5~!Q!Kpn0LiWz~hQ+sf8Z(!(CaMMU945SLB{+K}dDu9M)(|
z8og{z!JKBWLu7?{KU#W`{n|n|W7e$OTY2nPaL(oHUHDlm*vh7eXmf$ZJA1JHg0-X3
z(BpIC+*Op)t)m6p=hK?>R8B`T1Uuk$r{Z2muNBaxm74I%xau=gFWBN=l~nryntY`5
z9N2<MI)dKSVRYN61{NYc>vd&_=VV-uMX5)eRBeTaAH`M5$>uP|k1^!!AB{}9D}T>G
zJ@H!@orXM+zgkfY#9^Hi-i}c@8Ed02KfL`q)Qh7+4ofjLqvb4re(fqZn#3G6=*a91
z9H>`h3#33gf`1x%>2}Nf3JLV3I*yeaW6v+@38h_cN>D=XCq3xUc5HI#_Wb;nDp(-<
zpng?Y_>RFwV?mmU{8EZOSabOEMuBE($EPki9DOQv)0LM4ZapiRlf}0n9g+TLimd)6
zzJ7NoG_Hrr&d6D!oN>o&)4Zq`lIxGHa1!e`l4s4hJoW;sKA|H38fS0E6)vPvUd~6N
zwDu8j^B`)C^=&l)-86o+=H}_j{o~iUsLjKk!ll+orAeNK{wC7n+!429t_47RUt$5<
z6JU1&xF(s-M((s_+ch5F$bQJ}+s0PoqzrxP2l2b9`7PA@*CVu=XhYJMw3Fypvx(F{
zjju>MZQ~xFHCBHZYGmYjc=W|#2#GzZ;vPCuyxB=b7v}LEqdz`w-1Ws$n^C-x$@5MR
zP&!fMl4(pIFIp`&K4_wuX&ij#ajW`DE6BmnHA3-G71LSGyeMVIO60^-cDb!NT<A@N
z9ivhS^rSYiA>1QXBhXe_c#N;e@G(7d4KiJRcllw9X!U+;hB4IW4Mr79gO10bs*4s*
zHr1HgNx^9_N#vT9W60*cs&ti(8BL~rRi%vS5EGr=SSRwYJn;bk0Evs_W4(GNl6=h;
z*#7`}A)4SkMnB?bCtPES@KM@gD*WJj(s++Too(T|i32GaClsN8anCvLUF2~r-Wws*
z5wM!6Yzf%%izu-Z5HXhif~RQebW}^(VO83n!ZZGV$f;zD0<e-g;O<gIIjeC4QL1xR
zBU;IwF)X302x_wNQ=zD3*s!LN#(PtfnsHo;R}NB@-j!>qLf^Yk<EnxB*9EHhdRs|L
zM8jb``&Xh6$l=i8he9bYtYW=~%|U{Cspt(gD-h}2^9XEbD~u8=PRl`sftu~c!O=x@
z%i+t380=i<oC+@Cg3PV0$q47StvO61PRB7ZwXm6f%@9Q%g10Pn0Acx02bzZSPlj7_
zvw}GURwB&St~Q)t_n|wEaXLny68Ve4^{rcbh7Jg9HY=NsaUy)AVE+I*(6)Szxve5|
zNglVNTnozx*~Ty{i1C%It9iKy+)3iPp9Z@fFJlk7IIO=GATxK!?OVj;p68u3Q;*=y
zDhY#dhwEDc5uR6yQLzULTiAoF&_2X8-P07_qX#sy$!l?O<ROoCGx%12_F5ej%#E?}
zmajFNP`<OhW=WX3y8v_2r(qt)ZQ-jq7k*PGxan3u;TE+c04_a+dH$2)OPjk~2Vo$<
zY&QVb){UrY?W!=6UGcUymhH_aaid#S@Wr*gq>^prS0s^K3waU9!;h5XKKZX^)R)cD
z<lF)II({72lU!->{jGxW`_d2RNeuOG4NV-{QapT(qxn{|90GHS$nexYR*?@UkUISZ
zYqI4?#(1HDPwmkL+vg}Fu{7~|y#%U#vtCi+txE4s*BUtU^ABHo&WpuYfs{!cm?v&U
zNY86at?i7Dz}2K;de@(LPV#HJy!ou-JGtyVE6@~orUQw<sHC|_ht0sLNXV{xUb_$>
z1pXDRDtz*>6PGHvOT>O4D+iNqcy7M+!OL{+a8EU6{%IziiQz|1YKTncy{c4H5$9B^
z%*v8Gp(nLx+`9=kDdZg1grJupfi*_rCUb@S>r!IVGj&}<?NJC^Wr6BC)+BanXD=Y!
z2^?2V9*gJ3^7(+U{u+|gLU)lo#M(OXP_<^a<wd(zS7_2D;YKS;3u3WlfXg10J)MHW
zGq4Bgk~&r7w)ye5g%z&HJf(81aUI<;w~DZkk1bdDq|I1ZGmm<nIPk^s_c)|T7;^E0
z_fQTglF5X3$0v%kVq*vcA>=p|!DQy*IJ5GvFPc{ZvzC$-fq=$ynvPB%`BnEs5=kNC
zDEVrXYv*1?5C<gW{V9lw<w8J!ADOu{wkKqAOy}<KqNmgqVs_&k;0lJ{$ttDK?$qas
zt<V=y9c_Nv#Ce^8rGnxks6i&)7;QB|`K~6uhC68hg9MO!)NgRH>?8eTZ_X+?ZdJ~X
z#TE;jm{;ydHz=!*Cfg*Cb%lm&D(37*e`9c*BPmw>D_AP-xPu>gcUL^oNR^Js(BKti
z2C&hL8l>~8ZiZjHJ?ly-S?r^H=WA^=<O#BMU@*%>bQz1Kyqa#Xv%@BBE?oJM`}2cc
zsDGFeFms$&03(vd+DW8P%M+JSJ1-U1>G$yJcCp-BzCr7X<Hu6JzK+}-O*vW5_|D00
zq(aM+js<0SSHY=1qSse2{_TF~HP~tzc+@W9LJk+6D{2@cv$j-4#~k9k_?=~_6(WUV
zL4czbQt0iMH7&c6$2D5?{M_;BQ~?`)^EFFWK3&8zuO~dyR%cfkYE4h)u`D`)nnN!c
z*{z08ZnU~!K4Tua?^)Kem$o0ywKU)n3lsU%5u{tvo7%H(?~HC0KT5p}o@6TBDKHhd
zqz4rYvVhp34rl_%G`q1;_T*Da6VQ=B6K>{)HC<tG&zNblEP#FL0GoKHtBln(Qd_C3
z3cOGR;l)a|Ul<iEeJBBwS2^NI{JT{L8Rr$!$_;UzDRTb+CU8{a=~RhlHd$GZC-JFc
zO^1#_J*u*yJm)5?LfAhrpn_Y5D+nX8=~WD&scvO1!~=nhVygqwH7pTrI2i6}t&WYs
zs8E%Etw_t}5$i~zAaH%NPdk}^!js7(4ci=#dXVP;U~%a{5EUnkaqCQBv~{awjB{1p
zOE&-!KoJ3z>zWf8r1_P)V0uu#{Y3yw(4kzO^$3p`1F@?JM&3D~AO}9Q0N9f%LwBiF
zLg4lGsTXKmZKMn7-lVd;<M(7^tzz6nNcZ(MyD#0W`J){4=771+-m5C~C+S$z#z`a&
zE2Fst{JlV|$*qei9E|!?3z!n7Mi^5T*aO9CHM3;rtxFA`9WzqVT*X^^P^+AN6=`j<
zc@?4dP^vJrzD7Bs!E-W5hI&$4zzblC(0DV~r4ZYNY@E_)E<i2BQtw^`SY^uw0;Y8D
ziWPRBdWQtcRT?8;cDK;h0JWL*1z@-bx4m?&^DaHQRJQi3jH>+9C=Z;iBtl3~IKvEb
zD^A5BxKAcv4t`#JDL%?rXB4qS(aXCXF;9}h=Lq~M_I*oyeA~VP{{XUU&~$rGuv-0`
zAD1~E)k91sNKk)wn%jf|Gm0Y}ZYfl4SeXF_)~rVP7{ym7VClt683z@qkz>p`?NS5s
z9`#=}G$3vKDTrdf7&OK>Y}9PwS+m&FQb1hiy#aFcZMkz<y4{N3>C(ryB}V0~7>M%D
zDK`NB05RjeG)p`yThqi6NQ=hb;Wf(LLo{k~xb!`ZdQXmQWVh8zqLR4i7uL87fi=Ri
z1Yk#UE1qz)t|OafZQSRBNMD-KpH7t<e#gP>ifkHlyqS?mUuv#(VUSo(%c<JoxG#b;
zUqRU3m9m6n{oa+~OKSvoP`ZLy8;)z&Y$bDL7pPkK%<(D4Ha#pB%<0zW&9^@FRGMX@
z7PmR|r<(a!8#C2_XEc<QP-rb3X){appkef)ke+B1#2qN&iYW{!X(;?@h+0EHG<7rp
zb)t^_D4-61#&E2<F?Q;>=DfMw#C~1?73+Q|i_Gx-z#VpzUN<2pjMvoUuJoGoJbb}>
z*CvYWnJ_WUXhk^;Hk@X#b~fTiZ%V&!D-DW%_IUTNZN(mGZsJywUYO4uR-T`s`H}gz
zKX<OvS2VpO=j|6D1?#u@RZVML1RHyDRC<c2#T_(o@~G^M7_@B-8CZl2IR`b+TIzN-
zw%$mTZN@R0@{@5sIhDER?^8_k70;OC@v6E#6_@#*k8x|G+)id@Qs=&Ew7O1>E;kkY
z>w)`3*yd;a==((3{{UM50G%AjU)kPga=skWA09{t9PrhbduMTBI>zW)Eb!x{U|Z@}
zc9X2BDLZ=}_1)=ujkdLIvQPtm5I(h0<!3G<2P#^e{lFp~O<>&QFFk9s)vUhH8Omi%
za(A!=83g**Ts21n(60(9i2Bs9!l8*L1P{`p`;hKa#YS#-AsN8}xoXEzG8>=uhrK|n
zxPj|He7W!Spg36tFf1*ZY+z*jRhZ#xa;jHoH6@(u8v@<=tv0;1nn1o+Znd1G#AjSU
zCyy8e_BB~FnAsc5eWY`mxi(f$kx5TcR4%2Fl&X>x`_UVLOrb^~9OI#@5Rlv+wOD49
z93GXX;Aw3RzFAz<PiBe1QUz6t<>Qbz&P8fXe3uZf$^l<Wjey1|RgY>@owa6kLU#j<
z`qfq>bgM%X_=QMi+uozWG`k7nfGoo<NG;RSuQ^MI#!myaXNB51?^m?zNv>{@RN-^Y
zOA$_cM=$aMN3}z@VZ(7=pJCzKRERU6IOC^NR*r#SN!<#cV^*U+!_e~BqK(+$`CfRd
zc2k&GfE<Ez!k%l>BhoBT{I>A|f7z*pm9p|7kMg70$${oGTuUo%@}y(xRMMM=NXR)%
za6zvB09Kmb!pWu)N4bB8*15~rW7Kr$r;;^|n1&S-rsKHna|+g7vgHWLq`E{bcK{0-
z=`=qI4Pxudw%{+`Iq6Q<{4;T&UR!y=ULxb>D?}O#9Msl~mix94Nbgx~7U7lvH>G+n
zh_u<4OO8ahI6ZJH&*h2IQ=av-b^^M`u++-lURyj4l!Rc?4u`)TDX>S<-WayE);=7>
zvLd-KZ9IEbpM_QsTKIZGh&TDH82&Yt@TT<KcpN6*xw&gs;f#(gH5erMSuR`U^sZI8
z&~}oi?#**jc%w?NylY#FfMh2hFK?}M8m+{(dUVsl5t-F;5Op=<*B1|{-+7biaz^bZ
z%u4j4LrnFRnVkfQlB_ZfL4D=Rr_H}^aaQa$wS)s7z$=9DJeL-l<i1n3#*gl9;-wUL
z&a49Jw__b8Z|7BX_h_|?Srik7&IM1Zw*5-v_h;!*X{T<pYDw;E(1yn>k7~2>XS9vB
z0&&i2-qZjL3d+(OFmdTxfxFe*iv|=Qx+#})ve`+Fn5XfYhU5l?hBzadO^qX_@Kx5$
z0SxXHI<9*Py(X&#(UujsP{TVwJeub;T{vof4i?VLq^3AHtj!}zwea?+mvda?E<smr
z^~ZC25?)+u(cP4aTZ126!E;?-grvEaz&+bJoac7#y=r&yW{{R<<LxSTkGQ>Rt%r&e
zQ=fH)n{eyUvjC#2VI4CJip|w;{>K8NA!8xh4O&?)hy>f9_VYRZRaW-)1yqje1_h4+
zhDYaAz~g*hnDuQ2;2aS+Q;%{#!o30~42n9Ocdi@9q9|a}?%5BQ9m?bmxc>kmyNDTH
z-Z>MaC^R4*(MJCOc@+K?UTr=ZdH|-a<C;U-s=_=|;)ap-TZOpWg*n^)(c}Cp%5<wY
zyzwQJ2pCArPFB8v_^|@EhYYyOE8u%(yi>yG$??va>Kh00s*Z?E-q$p_^zA_weg6P7
zU@0|E$wH%!Yq9u_ci(B;W94J~tCCZnt!)?XiH%rFFUrQ8vrQS!bBdX0bjA;AWSq~6
zKY8V`>Nz#bdg8k;6UCclZ}W=dSRLlQOgp>|TAvUg=B3XS2>ZZvsmC?f6DbRdTzsaI
zlnxDOLMk^T(?`m~(w`^ZH6MJ}Gu+v1UQSnvbuv8Q8h(E&)flkPJt*%>-i&)wBu@0X
z$)JyFN&sBqldT=-paZ9+FHuR&9jF**B963D_MijSiZe-?0ABPQA9_slK|hrMFIqrz
zM_MQlQi@CutrP&gX+7z4j?|vmpkk5uQQne@09sD;xXJobcBBG|DLp71dQbuQQjWBl
z^rNuN04@a>$)Ft3$e;tgCu&~3MHB#Iib`LtA4&iXAT(#S8Rmcr2LhM9B>)8Dr5K=4
zO#mMFrRZp&@+bh!6rCwg;Xnu|rRncR0PR2sI(yMdN9Re~)_@L%j?___01X{IDD6Nr
z3<VSuM|uP(G@X8wXNo8Q;}m1oj<mc`0r=6LX$L*1&L{xL$66_JDGdMvr30lc8Kf}j
z+KhIittWosfeYG$NCr<dW`Gx{^`xa7P-qx+pwUUx&;g%XTv8m;^q>IqpL$L+OP(nS
z%^`sM*`pn4Paf2npaOx{G<T)x-hczrljt!=eoY-{5N95lqk<^wN=5;oV|#N;jP#?u
zFVcYsDNO>Cr2qnf$fW1-qa1al#*G~rcj{<2V-@HY@_f5V=Dhnz;`w>!71_ro)*PDn
z9wCkK2i4^*dlOzPhRs|1Slf=mslh2RdewOk-sc9sWy6{3dWFBXD!1OL7X4SF3c_bO
z;L~?Dahlia@njurdXfnCm&YBep1+hl#H#~Nv$kuN3L65XxzfxmK5fMMRMU(p%GWBz
z79oW&oEo;)QYz;hR0iF<gIlR0O&bOVE^ChQY<QM87{+U_vp|uZ#<@QhoS4WN0gZc{
zHtmX$=Voj72QGM|G`OU%zemb2=}DXlcX~#^JkfCoI*L8<P6ItV({cgEK<!1q2NY)q
zr5n@^xjiXWS@~Gp{{X;gIU(3X^rXdDhSKKZO^{m4BX<FMRp`7otV@hpFv#xJE~Hmc
z@-rtKQsA1}lfv4pQSW%sS07rxW#DVem;{nsq<QpOhh7V))j2bk12nsT{Z-sW@b!P?
zt>d5fYAe46Tfsa_=1H)hnC|4%eP$Q3E7>!P$Q?-hXap0%2E9%X1?dr@pCdea)yTXv
zr6&T;A@8(QJY;(h*t5tN=3=9gDpa<*kPj}_X9v+M(=D`%TWwULLl|7}0@p&ev93Uk
zN6=Ku7jA_rCyfmwQen7Q%m=ustb9MI-|q75@T2?2y?T3K*6cQ~O3u+#31(0S%Te{I
zHK6^HI5_+bt4et>B|d)yU)vyQE>oVtdRM6I8-A5nQI9rGanq$o)@m}nlujDQz+!kK
zlH%cp;mWTSqZfd5z;Z;S`j+cmK9~bpf!A*w)xf+|%DqnDsl?%LydS4p%MjYeGI|!`
zx9$8hrNt8B)*>;~jMa^4M%Z72jt*+XY+Bkgp4Bd-n%u5LM;?`8oh@R=vegB#f<0g4
zg*xLn?OKsBEseyHRPKR>`ZnX16qK9lI~u|?RpA%%rx?Q{1JfMwQkCcHKwq1=1Jbj&
z%uO+vUPzsY&MR2*I@VR9G+MKJ<Y3mZQU^715nAy#+qm|sS~H&_SlH!*bv1rwPc4J6
z0FPS3((mlyo@F-?g$I&N31}mHRV`ElWw?y(IQ;1!UD4tsHS}PPyw+x=;_VtcR#ltK
zEx-btAtv?<qgzdF_9y@+Z_8GS@mxKp#0yJkN{eQ0bJrBvekG_lip2ZpoK^b?_7^-(
zpIL>9q<{=#gIX5Rmx4Fzk<z@&Qt{rSewz{{gpXcxRTIWq)Nz#;DZ%-ETEDB!p?gGn
z@PW9<{7qwOs~lIzOn@J)d6b?h)}_g7`96ZPX1uw%Wj8lc%11(4syJD7V)lslAGFzp
z4)-yxM{`x=*0hBC*YM}i8u2%goMEJpfzvE$rTFhx^-nQ-L)2vPPLpk^?-OoQ&lLH-
zAZVy~NnH8?URCn)LZ~C!lsN-}YW}MMdq#Rx-x2Hrvcqd3Byde)L*u)crjkhQRd;8G
zHOOVXX*XxJTEoE;?HSm~@efyTxfBY%n5uUkHrDPVDAOPZ`=YtN^k%Er!?3y8qPpIu
zfb6}IH+98E`o5(mcj^}h+j**AogGD2vyWk2lC{+G{{XC-NB;nMvr&`oe>!OE(vQNQ
zDiD024nG4yz{$tyNHOV4f<BZ0pwbhLooPCX2;zVfB%D!<bj2y)P-y_%XEb)8oOL)J
zw42lW%6}SHDO@v0Q;I<9dImp1nvo%%U-ee=KhbGj4#P)!Y=rrE93ItnEhAK&a~*`d
ze|zQrbu##4Ta<zJb&uVo6_n~L6&RCWYHM?$n76QEpy2neRJk6t*GJ(EOn|dp+oJm%
z)s*l}x`XFxNLSHUy?Jtur$Tl(m6WN;HK3^8UgrF(u#dtT3Jl3{ERBxbRg<Cke6Csv
zr6c>!MQcK83{uqLyu}&$*B@Fu#VxcQ-$7mUT6T*Te62AX(|OPHsnA=(GX|e*pGB^p
ztwnS)<UH+3bA*mZJvdWVqp-f1?T*IbkGc_E__>`}U__(+m83J=ANgu|>?&R_vLCZJ
zxcoh=NssgwQR>Vpc>F7>vYpEWe(wJO;ayuvBcGl|Z*0>~BfUe#PoR4=bFuhB=%3!|
z7U}d{)T`k*SN(3HSbwmXt-LCez@)%A!KiqejIKmwFNXBBQeJ7~B<CRFr5YBHha%oa
zKJIHkj4d#nHy^D}x1Vt2L~z<^@eC%N7aiN0on}bB<+Ka*N{?~JG}8Qx{#6d7pHcFp
zS!>z)F2(vSMAO_Jvz~n_GdLf@Gw(=cEW82u(&j3{J2^i)ll3(b`Hl}yb4_sV*wj0l
z+JTm%!Z10mj=_uDoYy8L3)Pf;TDpBMM0kEi2abT(gPm(l9oRi2Ng%^DM~-S)hwmyp
z4A;)1*c;SR4h<>mNmK#af_<n2QO0NidVA0@NHb2wAQF+s$bH2r=zVDpO<WzMn4ZTE
z;t0sR+!WyEvCVWoBtind56a!EpC=~2Q@~H34;Fl;DO#%=(EC!J1v|cJ4R)O3aw}Uz
zyN=%EtehA7r{1#h!RM_ik`Ce2bmqA+n01Jx>At4aDtkGp9+wn?KnNr7sX6XzkJ0s}
zjI2_T>62Y#GAyaM8vNfKfvJR_EVe$M4_-B6bV?~l9MS**qdBiQ=oFmM)X~z6&;sYB
z6mmrwqygWGI(DP4)6$G_%`g!Aic!r3W|K4k;Y+}#=kueW`ufrWSg;?8<$PUg(oGYf
zB>PuU5!&?4W(IpyDxffK3GH7)!>j$Fo?d0}9&9w*qtYfdBIx%ojHW)Ox@V1*zG)PD
zmZ%+}0PeYreGPr*A@jV<!T!dVyC~<qNV+m(nLy&S<himzgLS_hK&t-$+8Sbx7Dpr4
z)U<&%RytjpefK2Qc`a;{?q#q#W~?@;XU5w?eaWh`YUiDhM!ucuA1SPEQ@M^k#H!-6
zrW^{pad#}IlYoDORT)Qo*9~;6Zvhl$p3misiezp8=dWsPubkHrsQ&=9F!igtWx#8k
zNc#cC2=&f?rDXs~;AX7Cj<{g8(L(W+$f>Ha+5Nh~Rd-DO=7Ff`YTUey#(MUyOcu$f
z0D5<?O;>#mS4AC3*Q`<@vfQ^A0Mi@9#Rd}52jg7U81b4swg)tOX$P`LK;9?0I4c}!
zgPN}XA-!edY;)HYljWZDr8`mWCd1jpy(X=9A<4LZa4HjhG@V`X?$uv!G~fX2XuQ~3
zC~=v;gt+`^rOE1`{uH2Qj2vW9X$8>GNEq9kQ^zN@CJCc7a<N=odwx`a6OPomC%qYL
zQOd&NZ8U{A9Mgb1sX+BOqmVg<`FZb2<%3Va=bAe4kH()Ma}n$VlTIipcJV*}cB7Oz
zgxlY>E&$^cy@qJTQi=<JOqzP9y#s;ToEUmlXe)}UGoCtA$OI2+h_@7Ek>BY<X$r)r
z0CuLcrySHLdkoU-YR%0Llvj}es&^7A9060huwG9dl}=ts99K1Y-X`>;VF1r0b*F)W
zQK`uz^r-;PLCtyS>A7Yrml1>>y((X{&5j#CTCEYoXQnx;01V`jk7HhiDw46z;*YKL
z(YH@UAaUBb9}}<oa}QD0yZZn>$fK=rJ}3Eg0uF1)M@fL2Re|^GUG;}L0Uzv~*904D
z0(uT`E56f19TAjuDtW46JeySv*Aglg4j7Sxf(>j;K3b_gzWruE-8W$8y=Y9oEoCF7
zhQ@YIYGfvxvznO_v60;o;F_8~w9ta2Km}&aELw`J0g+XsIH}e6sAI5<f|f6omCpy7
z8L1;Vl|@Kck#AlG+JqMLHB$FZk6D|2#7vEkm9vVge;v=5CAVGdy+?YzW2j2Yn}pep
zxfCIpacIk8vLSNoj_sP@^?6k_IZy%@upI?=y5743pR?JOGIV3<UU#WRQsLeDlg?{s
zBPy=QyQSSJjhCZt{3~wVh@C+Dr><+4)0+}w^UZX2=l6-naaXa+x#|8F)T6P8#`z(*
zs-7d%Qs#E@)1kqwFALZ~aSr(tECA;|)l0=zX#}}J+-DWhPgHT#_>NGW%z5USw{v5)
zPS8phagDL+1xBP0+er65mAhmeotmrYJojFe<l3Ac=~FNm8{0Yh*RAP`oefHnoxjq&
z+fk4GGEK)k)F3jfx4_%t<35$$_*+vKZl#xN2Ez*FAVJR@0C=s>41Bk1k+gDYf$Eno
zB+`i=#6Mn@<=3PAB3u%@kWG3_sKU>mO5rsdS6hiNF`s_)k{RfpA0+8f9<`*$0<%0m
zLDH0tovTUd0q5Q)(<8am3zZ))aw`%Y9zQr`So6j!xzw#vOO9A)y-@zo2`b1Rf!dH0
z=yq#uDzbn$>?^MwE1$9>&rk@h_2p<7k~m12+oFt`^PO{8-F+zG!t}1=TDTVaa~;^-
z#}(vqNMw>mCncPk^srR#?;Mzi&~&r3z>>d}HF|WXMu!>T)SgZ~tJOFeU8CUo(;$f(
z&T^RwzMbmU&HmLiaENs2pQ$|LQexPprCS%1o)<j(*1S+5F354(saUB*+!ybDb*mI*
z3XF8-i4Nkb1UzDw8RNO73!lcMzyzFQ6(SLSOq2Af;8nm=#(6akF@fK$HKhylW4<#$
z8nG`XXB;TP(^weo-GKR|=uJgyb>}cn%h>m=7~>Zp&iD~W(z9;cfs1#QjU!R+^xYX3
z?GjA?0Khn@u9%y7ZVGVO3z1nVKa*!KUPoN>S|!YYFXb1PY!j6Xaf)mxe#<SXP#dVM
zNUmjuM09dQeL=08%e83WzC{^e75i3}wulV-OPSTmNTqzY+nn^Pg4oS>A<y1i=7=V@
znn|N8w8`@W?@(zPi!Q6=J~oe+CX@0Rr+tB=q{DGBH*Z?$A(wQP(h^CMFty6x&#^A;
z+>MX-KA5fRIY_Xxa5{dKjYXx(Cb#AtLLtfDk@^aFeaR6x%O=xH7Z>*^NZQG|q1;89
z;PD)o&$VQRCB$M~I#^jVo<6l(MsMuRX>4PU5lp+6KDp#o@q(@~)0)4h*vEG@wdh}%
zCPy7JQC3TlrfWj#YR2L~iSr7AcikohTa~b+)@W?W&3PxJPaAAJ(=VbE#gzNQr6anh
zCyILPag{YAIje@1SnfMm9@RQbWwDSs$*HekEUtPtUTdDVyJ+QgZ&C=LW`&i}iCQvp
z1#3ffl;GDbZ27t=lhZub>_03yrURyx-eHs8x+`;wRjyqa$#ROmwbG%*xE_L#5i!h%
zik>>C7@0ctt4MJ`iMgfPX%z8G$sK3`r*NnxXRA0k>s4h3o@fAwob{>H`_*{;YEazM
z0%B?LNruHn2qK!`FFeu$>wwGBxK9)Ds4^44?Omi3hw5`&2Z^OEt4o9Of&EQVA(*+^
za641MA$dQYF@Jd7c@*hJ;nso%2HeL#Tu{;N9@NEOoHrt+!Dbv}RI-r}KQ4VL#BwVp
zbA}zNJbc}8$4X+Z*2wAFkjcEw%s}r=B!N;v7GD@N`D4QKOhtA)@zS2Cfk_;bNC(Y~
zQ-BKCJWvE?H7q+)yeK*jYF+{6n$3(3^oB-(LjXoIR(!Q}#}xyN;87f<4>_O<1~9#8
zzFi`@mj^WUA1ORi85<})xvG=G3E*O{>^-@~MnawsQ9#T|?UbSRs#04oOmkfmTdB_(
z`cx*%E%#^xpB8BB6t7=uyB&fe0k@Az)fOtaAm*en;G7N(CI&gTBY-%n#sVC!E1))@
z{c60H*fb2lcyZH_>rz8+oYm<dBPVWY@I#d#@Msx9pl+Drnr*#vTPbK;{0%kjNL&&4
z(y)wmhX>ZREp2lU-~&=eYJrCA)##!DaJ{GzS*^iQ(3+Y%4az!aIjPZ9HC%;3;}ijF
zPmjx1IPF@9z&8hvN~0V53{>IB&mC!ja23zYX}f|-yHCn`)qgM!Y55*kT4b`|kni@Z
z5i#l0(x}GUv7BbDMsfi(#6x(cZWs~6RBIMnJG#{O>cvs}V;QP3N<sOKC<9JBig6ji
zra;*Wz~mZxWFKk(=lox%$#rIvz&>RdIUHA#>QcvTJ0WEb4j5OyIxM!&6ZBz<`S-`#
zP1cpH6>v(sWH{(XF;}_~QcXb#`K4c_NByH72i(PScL?a*yJzcFn4Y_v^Qmz~on6iB
zMGO3y2d}+)Zj~pQr^HF;9la~TnVT8hdgi^m!;B7%Z_aQ#*MpuxdpNXr;P+=!U~_K%
z)h>U@sC42CatfQhd~E(Eders<>q$X5=|HJ87Lzo+=%52MP(NB)1SWgZJE||vcKvBZ
zah@sGo)+>UX2~4j<MppkE6Zn?S5%;5h_4zD=aJYX(Mo@JDzWYX=AJpPD6!TqtZszC
z-T459a@<#^SzWE=oKvqG*EsaALptI5nQBwL;><93*kV_^xoVJfqnaz{4$*%)JBm7r
zDFH)W8?;N1f4YB_c#_8DLFvXT+;v0`rCcfKR=j;8VyCAE7&Y|S9KFdeGs?^ssG}9D
z$tr~BHP-1mB100-bOAWvdQ-G}2(47zPmlI<+Nf)~<4nyAEwwrmn)(%~%R>(8NOrle
zZzkH=wyt?K%&{%h<n^GOp1I98JkZ(iQl%Pd$WEQ;JQ@MbCj`>5uxHwgnp!|V{Zv>5
z9QstYmvdQMB+#}Bo=2#tNI9hheJCbTQdVc7>3X%cvuEVYL1V!Otzv8XV_E#bW;4;N
zn}T_5Ci5Y3r`o%{Ggi0Otj)aR5_BNfMLC`(F9_l9M`MYS9oFo;bgYL{y_E?fyB$+W
z`xCat${tp-A=6S;f0TyzJ?TzqJx?*K7>YLgQW5BC_3oPRu`9{%S;bvW8zbvYNj-p+
zNcbF(MO(M?56tbF&d4~cwz7oCV@gO3m~L5AuH1v`P`k!Y%!8VS8M6CS^{dGoYs;u7
z(AEz@88<OU9vKH(rpG6WyQz>Q!tg49$UgP7b{S$Ai?3Q!6o`89?MNpjani0@L+8hi
z=7u7HQq6{LDdsg8!Kr0{MC3Uc6<xAVT4)J&g*?*bMln!jf#)<5b3hhDZa5;fv^lY=
zM;_91SV71&tD?+XREY2nIi$)*szJhhwH$?vo$2=9>QmQkCB*9jZX+kK^{&`#OCsAL
z{wiVKi@5&)4<?wpi@Et=IIL}JUwdn3LY`dB_kAjaQPgIWS=OPpi2m(Q%xh0uvrBy;
z5jY8g52h&azM5f&?J_7WC(X@V@f1h<G@JqtT>5vcYb(UKvp2x^jccx^ZalSP^AB3-
zz9j1Qa%u7TZmm3Q99J1_Z3VJ@syXv2^ikHXTljnXb|#VTwy&qHaK}bjzo2-U(_PY5
z3E3897%N;yiFD+&za}B_H$zEjrOl&jhjv15+N=-Wt?v?AiL{Y$2h10}bw#3Cz{rEp
z(_)FFnIliW=K`mYa>A$4#@%wyC}jEm=<h^{Tb=&^!`))%M}qH9kZtY;Yq9ugseP9J
z08&|mgh@8+<083_9B7l<*xKLPTFDUy4C}@PdKbfs6pzC(N*^;g-21DZ$4!pB>NfWX
zQ9fp2(z$EvCSNgRwj-W0de>JKsw9EN(tSl!*CX>G?V6bsi8Q>M7>WMxYUTVxYP0Jb
za57V^bvju806~vEmaw&W-0P4q7+s_s)RcHXiY(2py*yp9n#r~dH4A;9le@64tKtk>
zJVwM0Hgv8<CR=-`Cw3~aza&?6H+UTKUh(UiJ@ioN`>sEAfs$Bst0%<TMnbLPF+G%K
zxmd67ue9<l5ofn5Lr5#6_*J6W++5vU%K|j9$%QU6wwF0JFUNOvD=(L(U9vIZ%y<=}
zbK&0*-CLg~D|nH=zQ=WU_bRJub|@I>iXuDg{{RY?GL%kN!~PDq)9i#-TCD7?%SRJ!
zP=2+w7lt%=_h!vxW<0c{u|J(&f=!VQ^v2YHVmz`j+|=k(D;+w@I|(66SkwS;0*Zq`
zQ5w3cgizfDa(*lLooApdmdmzVhRy=^uNRx*X1^ruG#8B!Vt!G@EqVd<iFH%UDEgYu
z){s7%BV|J-8A<xr%98v*@fF|t>-mqcd{d?PhvH|o`#b6qJVav*f2~)%7CrOFtR?WA
zPmz_88}+W!PCK;AazD5$<plB8t9=YsI)%Y_S%=|@`j^9#EzgJS=2i@^5|BsIniDl?
z4FjbIrC5$H;(R`5g<ZP`P=6DT>s||@v5Ur<TlY5#KLXgVq5OSs_KykO0iTqsaqPg?
z&QU+vd{1F8UBxbA01p2EHbo1lk68Gh78gx*>GK2nR}2ORO6|TOT|LH^Vq}GotcU1F
z{{X7Efz#5phr%XEP8OsibRwh4BOPh#eq3g(Mn{O3ewN3$^sXNVI5pmDOTSH&XAS=V
z>#i10zt39qu&>-XYVI?mRKU~(^HV9v=DT2G#U~x9!kRg!Eog`<NyLVtH7xu&sE<x-
znp>M9++TE5*!t8Ef>dDUrxm13rMOYrmlU6+Q3243Oy-t?4FDJvccZlw0DDo6)O4dD
zP%y`(9jP~VrJw_~B`zrZr~v6j8O<dC6m_FHG_(Mi=8SVjDEw&v8an+bqJRu@OPqD2
zqJS5z7~|HChJ(`-0G!d9I*!zJ`p^J*qa0DswIQGd$Ec<H(ov6U04YZll)uV=4^Akf
zG#);*02(NuPyvo<I#Q0bcAx{&j?@Y}Pyvcg^rP<5e@Xyf=SONzX=nh)){J2BMFep`
z2zjHLS~13G0Vw3sla9Tqy$u5vgVQun2jxJ69G>2kAFUY89S6N27LZ`l(j3zO>qp~C
zIi#Qiy)6Qa&;f%;eW`m=QUK$QX>o%<8R}^dN(XU4qJS_cKGX;gG-KY5ooL9QVh#-l
z*EGK3f%TvRJt#lqQPz(10A`9h&_{7V26;4gqa0DTkid=w0+$qej8Fq|Xd@kI#Ak{^
zD7aWoIRsLXN)*zS!S|pnHi`(KkPkdk0e+N(W~7ZCRy!h){T8l8q-s|K_cjx`J+>NL
z$pwu14Q+qIDXy$uYw5D854>|#wEZ6MQ@#5ox+stwF@B3no*`yu4wM0!?+?P=S~yIz
zTt&4;c7a?~&9hqENelhx+^IgesZ}E_nOv<7uwfnaXWF|Mn<%F_;<$uwE=6vbHP=|m
zUKL_PE;z+}mk`mk)kEm=iTjQw^{W#eDjS2fh^4cWj8pEDBO|SRmeW11g(7*U#+jfm
ztyqP5=xa$z$Shm4lgK-O&2B{;cepIL#bU;Tjw^Fc`9*p4-`ZQ1VoQr;PzC_{R#dRB
zKQ9%rJ7=$2%eml@S<-Bq6&X=b?eAP)iD9^!=y_K1Nf;T*3hhGgkx&k%wuQ7`V=3jS
zA$sDz!-t~jw^g1_XFJD`@q1kpQoa8GQE0?>C#7h`;GJ$vW;oD#lbZC6A89jyplv@X
zQN?QYJooQkSu9+-9s;6|CAjcTqi%toRQZlG=~~u*4&!)MN$%bA>BV;1q7!G^0QaS{
zlQt>GBaSK_CZj|4Q8{?N9_fmHc9n<w{8SI&9Xj7sRocvhA1ORnVy}{Oip|u6E!1-7
zra2WVtlv_(BDxaApy{wT%V{6iXsQ1Ivn{YyU_ta1c~0eDpftVkI@WyB?mHu%(jbm2
z`Jz~Yp1mt<L<d2idd;_AD_eEw8~N72=N|OutGFVK{2Q%YvEh08RC-cwwE3~PF&!%X
z#0BkTRvZ=UR5YetvaguGd%IHTGWOm&epQ>R#GxW^2sNc7_R$~ST*RaO>d4l$ohmC|
zn(8-X<N#^HEwN~7Tj1M9Mo1#11E*@hwDDez9jYvsLvoIl48A<kV<%~nOdsK@_H*n{
zGA`amV%B4lwsDc|UVo{0=GuFtlG+kgc;=q}01{*zC6EWUNUQb}cF<nZCwYp<)0fNC
zW<$p8@my@*5w$nZl>}-&oYq5luU0n(VJfL^qZM((PRw4`C$V{Cj+G7Kuh}FF$^jio
zuO64g`qaec@rSaSrzWeY%aJYQtPlG}sbMADpK6a<(k`tchD2+W&hG72<khsuv%dNf
zj=`(Myw(}Rzddlqm`>x#CywT;>X+&s)b)L9#9BCmV%)2;_7z^&#`-jN;T*YT_OCGD
ze@aZ|uj;X|y`w!cPl#GdjHD7ZWNKbJH&ev+_TMV<LykppVYsG)@5MOb;DzlO+_%Jw
z<z2Dbp~rJor1*!eI{d2&{{X;yS0Wn}Zsw^`rn(c)BWb)xs>yNopR@&&o&e&TCcmsq
zcRr&ck3{0B=~l7o8i(2Co6C$Q?EW><{{X@zV&v_)C2`Yvshvttc4(y;vz&cG@=w2e
zaNk!oQOc9MB$MBDbz{QzMEvtQC;R+WOWhk!f&$4aNK_mU)T4-|-I5PyKBqX%l5)iV
z0Kln)<B^QhSmBO3P-~**b`_3I8SBkAno~>!&U?|CFi&h!gMrNe1o|2}^`MW)ngPho
z1F(NOJxw&abu2#)w4u=OGIQ-k&{%dbIiL@wY4OE0yhU#-{{XtRWi*XeLxr%DKIas<
zkaCp|CX*PgWbo#*CO27x9m_bW*TPzf`|{f+JxMgZtQSz_W*=_!6YpIT_(oE3CZ!4w
zK(#b}5VYwotPlICil3}g?mkD@<_9PG(h{nE@ciqu9u?9NF(lK;gX>me(KI+YOBR3k
zoREJC&ElYn_H5vbpyW3mqnb_IjubIJO7wMG3xD-mb-Ew-ML6mXIF2ZQ_7$7PE{J}~
zo_?Br{M<)lI}csB6>dKc>r#$1_5;+g71;j(Xk703WB__?sEy6bbLNrk4QKTL96{s0
zxpp72M>w7j)!Q4^2)&+9@T)1{smUI0r*9v8D(1Azk~dii&ur5Q?a9qc#Z8S<MMdzH
zihr)vT2Ew5Q;&yq2!IavbDynPGhkpIYCXld+-o;pqv}$ELqD@TJr*`;@;UziY0XU<
z>5u?o(_tRuW~(?Plg%)K2O^==lj=THUTe*~M+6Ezm!&nY=Lh9*K8sZ_Lebxzl)0N9
zDPZ5+lg!QdQX7d_a_^s9)pERar^GUTl!s!(a<gD^X&H`s8dP*c&ILy;)v^uGG;8&G
zL$L2PhjBoZ=aW^RSkj|b-FFxK1m>x?h;*p>Ow2u$(zsaLSuh6`IyWD!a_{2XDE|P}
zMJxOCs_o+-RE4uS_j)cCJ1;Rn!6WHGnJa~p#y4jnZQ@@{oYhD1KBoK$5q^nE<#L{b
zypz;sl*koGBz4DH^Jz8hPC?Dn5BEkYv)|rJ{<7+0{{RCtTr7H#nk8SE!1|i0KB;2?
z!(GA;f114R2X=G5M{lcUrMQK5WDMiIbSe$Qn4YI=Cy4a4AMy03{n47KCyKPiIS(VB
zWUdnwW7@gh%d$Hs@r|fICA_Ecs*?D@&V0L2Ki)OW;*4UXERE*zW$R~TP_Mo!2Jtqg
z-}2QL*ezqy(;0eAYf+TtuAF^1s2cL={`JI%{smBUpo#!_X&<Yx`kM5=1Ik*~A;I}c
zCp_1gFHS4aybAkvbH#aiv~NJ_!#haq=jEy#a50LrH#n#{74oT`${0m8g-)rS!xYCt
zItpowhdAPl`ePKNdeBBm%}|9Nv>GTp6U`xpIUG__=hK=G*P3WYJ>n<}+DJ!SWE$jn
z_04zsls;vn0zRU+7mv$!T%H)>zeLDudrT@_kDSb5%TnV`FiHI@qS7>rTgW`d$!uc)
z^saXwFK%n1@but*=PWSBwa#i)r9+;ZwT!S)jH+5jcBP~>jHIUGp7ovw0=*vM1h|Bw
zC_HsF#_IZ6vu2TbQhQc8PH!Aa<e$WCjKR8o^ma1A!N{%c8(C=NSY>SX1lK+oHyQ6v
zR>23*<YK$=*eZCcPBJ-g_2oud9+wP@D9W`;2PU~~3sWuxPQ!5db6r9(a2q-Iug)=;
zN#UwENcwseRao;Oew3$yM{cxYxQ&CQFC2<Hb3x?L0n(713JK$i2R~W>P<o1A(wmNG
z_U%9l4>Y)@k&mS)>C%7|a2#Xutj`xaE|ggx8+bT1ratigbxXu?`MNZtxn9-kWc3_z
zQL)91jp?(_Opf33(VOaNrbZnP6s2%+NP2o#->znS?t@Dlb3q5!^`s}7Flq9N;t@??
zIT_-dah{yh8k30ABl&U1H4MEtsrK?sM#F<xRECC;Wil{vKm?y^bBr9)1+EUJ<)}x?
z_3u-tDu1n4w>ck5x)&p+E7YZKQ<{5?P=5nQIH@-A%>)sF#cO0m#*EXlK%~dh@HC?s
z<C=CA!}us4%A6Gc0QIRh=j%?wxR~cOpn6ag;PFlaBOv{0h(JFYObT28Gx^iT2*_cd
zN_P;<QGw}C3fSmR&{Nh4q+zxhe+11JL1G{VX?Bd&=(Jr{U<`V7%MRF#^H*T-pNMV;
z$)r#J00IPmF-x5a#v$v^Y5?N8sJ<R}qEIoWF#52o@O&%rOv{r5F`xFDrPYG!S1UM;
zydEhCUrO|7{ts)-k2dPvPoOn+FN3#3iM4oB*mF?p$GG_!<-2!uADt$`E7z0Y)t?PM
zv60*={{Z#s<Ua{KI~n=4JBIdO{{U4ltkVx>&lcD*o|I)W4tTG4hv9#Op<kR_OnpsX
zhrm7&h<uuCkM+r=^{5Zov*&!M>ykZ%Jy$#c{CX*`q~q|nhoCr31sH#{D&%@bmjKK<
zEuv%83WtkbiuO$TiC~^az_*zDZL4r;I+Xa?r`$UGC4DZd6ldkMvX9@2b6+fdF09ac
z3|4Z*U!h8yK6FnBYtw(K(e8g0BCSR6`^6LTx@)TAqj6sH+Po{1CaZ1-qT;GQh;+0+
zKCzto8jq|##d|Zy;`mGAn}q)WQxXIH_Nmw4j=d-P>$_<G0N`K!YV`@cQ=%^qeDC<x
zfA~wZ6bu8%`1y@Ptl3I7I0$|RN`QT%T!uFEU;hAIU5ntxl%MhUuQQ(8MRgMR<3w2p
zmuT)t&QAmLs2|6+Ymxn&-rqKBK4F<Ld?oO-OS(-$?m#;2PyV%N#qj6Caj+&UsYvc~
zM4u2`FYa{M^XN@P-w-tne3q8$^fgMPmdsqIrr7Zc{{TwhyjC{q9lCVy*1PK=`<!}L
z3F6Rx+6eWoQ&XE9u&)0AMm}bWI`XHl(!BT*4stl=y$3-50FW?ToP_K6RRO?WM(e7+
zasISmk4l<R^3kcM{7mKcG?JXAYdIsLi_*nI)|5Uw)J||}BK3rk-3DF~d(*?#ddX8P
zm6J9_^^&C$RTX-bUbAB@87WdiBwl-pueyhDi@5fr45_N?ZKcePv3a>}MP>Mt#Rlrd
z4X`m~eq<egI=gddx6Ov<K9!xV=>p$R`;E9(k+)Mh7`_@uxVd>>JdWo$HG5aI1zCXk
z!RzZ<z82GrRxL9pEy*;u_TlnD_UTrhr!=)W2qI{t2cB!8wchGB@Wa-#?jZ8y+CLi6
zu~spA=QV6e9<||%sO{{LTkkOIRy98+?m$S%KDC9UI{lU%yz$N}S=*fRT{ISl9dC$z
zqd^00k|i<cIjfg?9+jy@zsXI<__0|;=dEh#S82P-m!aai8o7<eMW&^-n?$ej<ALd3
zRjXNDE}=7+$yQ=UIu1@N+2^)l%5pnaJ>7&eD+yv5J@H9FFuCNvV4U|O>0NJzEjA;&
zugtyw0Htn?2GtM9xc9|R4X4?@RTva|Fy=Pe>NmDjIL0t*5=|fN8<{>~o|R;h6P%A~
zE$?0lP7eo+QOX>~rilTyu@JW#PXN}7f>yE;?3UcTRe^Tcsc{|7a`Bz@Nz-}s1JG7I
zz3j(SFuQS{2YTo(Eg7#GWy#NK#QP-CYNk^d!EEGpz^LS7<~n;=gmVH7Z>s>H@CUtf
zf@azoP7keFTc>rwG}IXGQSp`FOFfAH05M*k_2-*#i;qlJ_lqu>=8ho4hQ<wJ#HE`I
z1_gUqSaQJgtIq7P3}F*J>9RKe0F-p4-H}QckLz7WF&t44q@T{DW?^CFft}n`>&1(<
zGtXM8+(rg)1t2cz>KVra3tBJo!p9u96_sHw4#Cx%oO)KQ?UpOqX*L81*!%@a&;j_>
zXo+S3^vzCKmUrwI6o7W_8M^kUSaOI5J!z&)s;c8XO$hC|q|eHuAB_XCOy0G;(vy%s
zhaQ!$W3NSU_SSQ_K>nHes}klRu}kCTVN~^-VJ*}$+Y-A5c;lKHOla-3R2N}mw=3nK
z=N;>hy=|*3Kf|8YXGQS{TRALdVfLJmGga?Ejevf4diSSISy)XOA7uvSG)HfkeB9Qm
z1$#NI-M)3{io(f@QdwhSP#ohqt&6@UNxCeU=B#!QN3z)_M&dpXH6^q=<oj%75x>*g
zpo(K|(!%-KCqC6{L}nKER?;uZ2`EQ;O^jVh7~Mwy0N)&p*F~nT-3<_P<&l&0u6dYU
zYy@SO(APz!Wwhzg4t**o@QbN=PIWtW;E5w69{&L3Q!%;=xQ9?!fID}n{LQo2zTx-q
ze<M@6;{JG#S6<&r!>MD@vMu+2%WN+mrn+r5+*;VAeMlJ3wPfj5K4r8<KzBymeJh|G
z3gE<4zq*df6z%Ua8JmJLR2bq)mf_EsaZoot#}&qP4`x?P6P(jw+LB-%wF3r5IDGq6
zIc`i&GDS&7t=vF@M?GtWzHcv5amUThF<nU13n1=24RX5L6MC|#Ja9!YA+($RCQI`S
z8tJ!UA9~~L9h*?W>FZr=m<iXlFeb1<({4E8w^{KGW@*vkGm6lZ{FJN&QT)cNmny#X
z1WS%;W*k!y8M$D8r3X>iIRyPEHtOe^U$CJZ8bB&)u({fPQ%#a(enI2fqLR%}@HbEs
zZ*C|8c$gk4ZYn6i#XYh3(*kJu6!{|#q#A}2Y0}NHaz_*aR!z}9Mr(uC9LcIk`ObYS
zwYj+sn&L0;*HRxtOo<gzO{WH;cNsfR;Y%u#q>TO*Sw40fPbAVHoHlAjE)N|kvBnhR
zsHcSI<vl4BFtZb$ho&k>m}dv`sH8tRrbfqb>GYuitfy}ul|59-Ivk3I6lcccj&oKN
z6>JW_&VVblCO63(R8pZW`qjBfVow<zMOJplxD){1rx_IOicU{aQSS%6OrY%@X$+0f
zV}a75D0gwlHEEOO9kER-wtyNUD#3@{J*q`=k4@cxf4fQuJt+Yr5!7@&sxk)PY3QYh
z8RDMM?Kz-gFU>(r0y*csNReZ|6)%=Jq%xMyIj6-Qc=oFvS2(2DRN|P5?HLW}QMv=g
zTXf?+ssqU2b)+*oNL+*c+8~c<`G*ytV>^CoK)%9&A^<QuP7NVaLC$KzC{kE-`ckrP
z9Vh~m!-2&{fs$tDuWGdF%6ZNz7s&e11o2=GYPkvyp{qJK?ZsP!<NfLa<>fm%9MzO0
zrbz4BsYNJWqcvzaC>V60M3~C)N*I6?_oR)3WQuD^gOVwTu^GrGrCqmRR~1DhPTgvF
zq}<qE!kCNqF?p756#d_rRvdDMk(IxM^IOqA==PrCuo*U8P3gM=fHf`KBztrfJ1{2%
z^X*ja`2Lk;$X8R(J?H{Wq{e&kn&AE<>8DW9Qt1>lkseQMcg=V4VTESg+edY6b8PF8
zARuO`2>FKc*nRwPYdT2BrFLE*(i>0ICW+LiILB|oxx0vV9N^-aNtu!iCr*{@-W6@y
zEIF?qVU@*t&x2ofhaWuvuNOLBxJPym;%8^3o*t|ozO`FSKQoVNwA^!F5mVwldSZT*
zV-#oJii1$iEhQ}g9q7drW`Gg62evEAJVNF5R|Sq2wR)Qk%4^HKNgtQ2&76GL>0fcd
zDSc*shl`y*+@l=Vp?E6gr_sW;PQ$k*y!4y{UH<@rVJoGV846Bo>bR{(`#N05my<X3
zgQ}-=6w%U_za3}Ri$Li~OWUO&AiWu}n>{w-yglZTZ-|YXK42I>g?p6aeXOhg&3I+-
zXmz90<d}XUzLz5VNb|AFW3tsii$+tPcH*-%O${$&6I>8;&IsvRI-&mni5kCspw+Dr
zh31K}G6R9P-oBoiMsaeDE5u};9MZ1g*%|`t+;D52i%GV()SA}!?tck1$*#2x6H<Nb
zST;bam)e}Svn#(0Dx~7N9W-H6`LsIdd^Mxa!ICv|j@>E?pATs9#=~kO4tN+f2ZLsn
zqmfz3!w?Dl>odeMx@wM!>;^J$YVRIP*v2ub?RhzgwEqAPt>w$^Ai{?NwwJ>?K~E$E
z5`p)-)S4GMADTY%E`J*4ZLa4U+7kZ&dH!LX(pF02a;Z5=(%6q!(N33f@-Sp>nXSz~
z!#aHSD=f$e#&X82_?<zpSL1L4pIWhQG2zj)5rN33$hnA>dCHp9rT+j3u9YxvA(S}j
zwAKOBrP6hHl(ETvG2B&+25XV5GM12q2O!qYycFMBk+<(;ni^IPc}4O!dzLlVSgcja
z1o76nh;EQSrEd7Bh0vEha5=6TDGM;mRuv)4d6hRc?_M`u%hc5ei7pfeUzm5Rainv{
zwVwv77~Tmsk_Z)=Rx>G2rtJB{ap_e`6>spZ-J)2?>GiDR3wfIYZenqP-n5NQ;I%79
za_GXep}HAXZ_1(m$i9)Xma-CiVx>ABs;ju#HV0ptrc;CJZR}?H6W>HGaU>~`jz^_t
z$rn&~BD5`@;?1z|FhV)cN`igU&AC@OqAtdAgrm8gwS#fZXa<@qa51z~0_<=*`&H1d
zBqe%r-l@ogCSNhm;?%&~dew`FUfHoA>(Gj%&6mwu0>_zxC?uZ13Uo1vG1`d}W0n1B
zjE^5TwQ1>*Lml)IZacG#R#x&46{DuO`$R#y?p%I!q%+oS8+EF4+L?X+s2t}VsVrM`
z3G3dSea*ikHPuhyM6#rX(jD;}eQS=Ech)uN<8>ZVw_jX;`s-g`)J3+Pu^ex6fGan{
z)}|IoB<0xSBvpv+t<XnqimQMI1yt7t{WZbojw<wAsQqfTsm+U=6Ybu!sql>+e-)&v
z72{?tkJh%d%gOA^Mlpuuiibeabq!AWBUoheca<)u(z{Eqhi`3Y^9kLZM&KH}=9@G}
zJrwRf`gxfo^rKYsrqfz9AP&1&cC7fdIPGs0WcffmlThoo-h8Og$+<Dww5NO7gJ(GZ
z0Cb<ypJ6lG>bA2W%SRw?l#+64vywU7M?I@|u`6@y4L;fr5qMcratg^F4&K$Lq{SQ-
zg4PsK97AZpuRZv8HT9Q=7H>Oz44Z<tBvt<a4r`i(n%(rMh3wq&3Hz))D+F}d?w4nr
zah=~<sjTP901j)Ki^T5!D|=Lov@V!pKZMkp-198T4admc05vixBUaZ{`!pLQP(bt*
znLe)_#<-FB5&%cu?NqGojl`ep2^jUN#(Ck@e$Ry`s33DtQNesnjIO&ADB+aX12^3`
z8SP#7#I|<Spkf&~BcEE}WX|5WZlb%W{0BV#Bh!2hXL%NY=_DB4_cL4m2)DoR?xj0j
zD)}=V#|Ncyo*(f<!%Rq{8yInu(z=@qok^neB#~r8>Nz5`RMSA>)~BJ~_?Jk698GqL
zNZ@CaRw2KDS$U!V0CdA4jd+KOB=hBo&&tZ(2c>uRn#j8F$c)B$O}ValMW<tVQ%ahV
z*+X$0(2|T8dm8g^h~6?9G(TpxlWfd7inFKd2T#(ZN4U$V`EqN)yicgy>KfG2O(~Hx
z@|@Ai*^x_7)F!;SX{LSbPI7BKn3MJNt1*b1mONEySS#UrR+bQ(&OIpJYBJOV#W52h
z4Bc=IeJSu;#i^@!fBPbN7wtBjAkQqd^E$9!t#rNx@f&z^#TK`!%p%?vKtH-_C8ncV
zpJR@+r=?Z0yoXS-hVBOs6sQ?UJwdA^@l>73W*>|Zr0}KsuU{^{V!DvqYWC8V8A*}<
z01;nIc-PMV0EAxi%3uc0YvwIgztY2W+UnS+9mLON@$|lLhb)+(P-Go{-8I1}&NE&A
z0F5UT_#z*W?#hrruRrNp!{HF}eqVZcsKMf&ocq-Xt*J&D!c*<my#8VHx3zjL*bQeO
z#(3#od33vFZ}*6=LkRR|Jz@jROrLh5JvpfsyWn%N;~-M5LsNUxhX<u<K?LLGs9U8^
zIQg?s9+l5M&111*1IN;=WOb^rb*o*fqC|r{QQnF_DzXI!no!(RaZCA7A$J-x#U?nT
z6u>(5q{p=#4>SruAfvxZUjEdb=oq~PCt3jFj{g9KAOJa|8TF+ccBJPNz&)uuQqh_K
zKh9|>f0ZEoDFD6cdKyE`6acu*AnQkCOF#iMnWdz~03VGl7^5@*nf9RaF-K2qQP-sa
z8SE)(DRYWoCr;G8sWD4H26^p87{^KoqyT;B#UENZpa5`aA6h9f+JG0IN;$|hgc>{0
z0o$b+r5z}s0*vH}PW>qDKnin6KU!ST(tr~mg)i6gqd7jbP%$!19VtgX^nhe~&;inp
z)OY5W6bLcJCO)*i2YO0CFSQuviVXl1AH78Yb4&xL6dEy~dME%CoCEzSaf&DaqK-W&
zdQbvTdeM(+Dn<Zejx*kr4rn8aU?wr|MmgzD0OFIWq`)zPc%{aA3fRy*GkfAWN?JN1
zf<b0H*7mLN+V@A(-s(%SF2T5<Tvl$Z6Xk5B2|bP{2S0X`jAZfkuBXEu4Y~0x*UV&w
z&3^I6CcC@e0QhG@)0*PtKI;AFex{;$h{f{t9BIj(MQdeueC2H|rJS!&tJ0*KPrI~`
zLvw8;a<JiXn(n+Ot%!9gEHvvq;p979o{CL+U50^g3yYhSNv{}u&clWF6_rd&gVh%b
zS3C|c59;!b(doAgzPmA2^xp~U7y5$R+=FDe&SYLswR^qRxua?G7$>=fB=q#D+8Yg0
z+a)8K7aTIyFBdMw`wuh3yh-4b;p-o?eW*%0oYy<2X?L2%;I^@ZyOV;zaGzTAj~{q$
z;?~qnZ9I){k@7nh0=ka_Xb@=nDmYBfCK-tx@GDQO^3%TTUd!IG%W0noQIQ`~x^n$W
z$Hi*D!hIXdAq<Mmz+&C&OUC{ylf(9^mfX(#0&A7<--|p|e{s4iRl0{b<+0CxYc6`T
zT-Pg-3v(Y{_;GusA)eX%_*bYsg=F|X(h0mv92Za{fu0|?HS3el;#<fJe_*wNTd8;5
z{Hx4kwx3Ax#4R?#z1tf&6|Fk5lv-rY32KjMgG;crh<SFgF4Y|tvTpoeplS28EZLEI
zgp8Wsjg_H{_GJXtJ>AEKwELF(OIjr7mdF{dB<}S#wU&oJseDG#&8&$Pti*KO%Yj@c
zgzrOm;7QRgGI9Bu?0i|`EdqTeXssGKCE7sPwdWojltbb>33?6qBD(2CdpQ|Y>2v6*
z2b*l;oD}I_I{2y|E5w&;w`c_ZJlD}S>|WkH{{RwKka)AgTE?TVO*NIHvN7%e1M#TB
z$wp4))Q#4Mo#T&M+|ce1F!dl+%Z~u-*4Ey9(4wdrARcO`hJiZ4g_oX$H*RV(3Nge{
zX&T_`x)m;TR`LXJN#eB#S6;czL#gSnX5v&_q2&8i5L^`){&o58B8;IcJ<qMBQZtV-
zALWq8inR)0RAc5DsS&^(YnDy4YFUg7<GpKHoF;RM#9Opc?^a;EZq?6HoTPx(nY)u&
z6U;ZBMMrmeAw$kSm4`ItGVaZ{zD;!DFjA`}6h%p>M(pXd=)Bpto>W%AKmMxV<MF&!
zaQRW%7Qp-4g+VvOE5;wYwnZNOf1Q2q69GC@loCE;6N!xG-OjU2%4!luye~Nwv#{g6
zc>e(WC3=!wNpiB`nElFRzAx4#&Tg4c`!(o1B-zF7qK{bAV+T)^I{-1BO=s!T+Y3bx
za~gr$HRV(5nvB^JUP{1>6)bU74Dt>Gwmb9Iw2l$mR!gne_K9^(9y9abLO<YDjji~j
zNJWfAH<^R9?5{0$3_fF?I#X4)k=Rwo2^G5~)n}-$#62oF!ic4EtLch@Ux_x#NQ%Zo
z?oD~HY>#R)oOP@Ev<dc-I?JCM-M#s^iZG#i0>AxwAL0hG`PySq>9)BddS^6e2i~jL
zL$JBzZ_ncGV&F18+W^D(c&wp)dCo58T>3p$$^5Afa%$B$t&q8!EH&lJa@R9A`_4^7
zWF#HLwoZAbd(n=yR!EV>w{{epfcu~ir5VK;&N!w4+ccvhkaI>eNChP0r6W;}X>p#t
zXaT+Hazz-RoSgQe;}aw6Ml;%%8KgW8PAC8?#U==$r9gRM_)r~4`EqmU4J(C&rR)t$
z9i8mUm~CZY^u<|^Le?ZdEs-DZ98|f*6p=$T5;2O|kHY%1ef5Gd{?pX!;R}};lTn2}
zi<-(+q1>ewVB5{*T&tEKV2&!&YfEg|#LiD(^|HPWwG4dyMcdRM#XtTLO$iV0JoyRr
zYT&IUDP0{A(8OOCs+>KR>~swEGkCh%;@rdb0U17=irbGs&>~>VU|f&yxgxH`2A=^2
z4LSrPzR_91+E*KQH~>SRlrhhs=BHabxBHfJk^b#^2)n_+hBO|_PB${J;Qp1_^}i!8
zXLE&3A61ZimJ*Zbc&iZjYgwG_`zppgUF)$E&E1dTQ%3INpXXBXa_EEE9J2T-`I{47
z!k<B!n0PiI51XlyKiOL8Svbz(N$piiV~&*%6H$-Zqb)oyq#^y}v&cuiPMQXWhl^Hn
zIr*5?!a&KU768<HX}+W6LZzOW5dk#Ve-Trpi5dOfqzjIpEmsaf@5MP?h~!lJNp~MA
zCpU9r?xOnvQ8mQ)B)uHSNgXMUjMy0KQslzK5?#xjdC!kPYO^+2oz8Rq)k`E;%Vcp?
zp8-x-52>YctUMg`%{>m!{{U4~YrAzk%!BG_jjUKieruS)`qH@UY)3PEym9YV0}{Cc
zx#sacl^UGRTi7Y6+s3+lV+j<`_*1x8=v(INOlZmaS1TutVkh@@kL|ePt4-r;rd&m9
z8lP4<rEsy>05QoF<N@0m{HuYJ#d@Rg3~BTgR!x6YldaKT_dpa}IZsEL-6L$IibvL}
z&e5pmR2}&>=P#&U&G+u5KHH5z%<g_?WA!u#Dc`=KXBorYLOr)sEv{*i4sKNc0J<|=
zCfYU=(u**%J16ljoV=?@{{Te)02-|?itWk5TDyHtE125Z>BTO?igshr-+vZJa3i!p
z2dStZ#TU#li4uMptbK-pF;A6-hM?DVDVzg1QQv9`ON*=aO~&$EdmL35K34{`!g-N?
z9V@yNBPxDmN>*k&%Pa8mx%#z6ee;@@RArEYF--`4D}lt)<1xodTzgcZ38$<*sN`XC
zwm7B7wraqS1E(~*2YRn&#d5CFPBBkdnDnb+Bk4{ELj#T}`yq1_+6Gb0Gij|>Qc|hN
znCrzJ&7s_m4jQlHba+0MMMl=EsB%4xcVYF1DV(0Bbcwa`Nw%%bfIn)8uQka!dX}U^
zx0*KbQtack8#$@=W4R8~nq8))+A%<0am60YE=9JKElLxLa8Ios%vT}`b6tmmoUFxj
zz-r}!*GJ(e5#M7yTcvrqoj>+=bYbQ1qtfQ&Zp}lE^)!busmI=^M_xKt#UtI0#H-Sp
z;2KPyN@?f?1q@~8nng%yrmEmG7!(1K(w&U^=93uhRd5p+6qx)e+2gGzUTL8fZ*lf#
zIIlmuVs7Q^0sfWU>XNKBY+F2z1#mLInK5jA<6n2fP-=sdJRH%kbcP<?Yga;YZkc-H
zn#vWm;q)zdSZ8WC%zrBH&ZL$WS2=Jh^-<a($^-3H?=4c|7E-J0{OZUAAQ_;7Ml18m
z6{SX^oKK~k6r*N&=A&TNcMZteagR!-N&G9a*X&Yza>@@GYU7H4#Ai6K(z4uN)@Ui8
zGmE3_sx&?+3~~k^op*Xg$DIiW&~&Z@42*X4uBXFy8Gs=tcR$aH@wk%?oh4Bnd2Lpw
z%5>w3UetYPuZ2DE;Pj=)A6f+%pakNVIi${MK=z;jiZhP1cck_mC;>+uXdT5F;)Bpo
z0DF2;YH=BK*92q~BNU^8D$85F#k)p`&&NgPyK?z*;$U-PmFcs|PwFzfQ%@Drw}N~^
z^01FheWi)!tw-?Z#PWQ`&Na_s!oNgSBV*>J6OY+Pm&Y~UNARb_4ncWslkw?Sqxe6l
zI*&V3iG6Uidsz1-$C?xwq-5`p&b?wEgK(S~wP_o+BTByy!M!0y9`@<JgB32c29rEg
z;d<bGYBy-e`^%rLd)z+>JUEIsB<+snv6{CZ!;cEWGHe4LpFE%addgKI%U3>bVheo_
zZfO+>KP+zF@E*1F<bDzGt+51Y_G^ypYV<aK8MPlQdU~?=IId^PYNUL@1QQeT!72JB
zYD1-Ja_7s_t{WXbLtjT7Tf<hrD3-~6FryUK@qU2{lC#7}AHbEoEAp#Y&QWae2>dOt
z%14)^+@DOLtq8s!_@Zn9rIGcoX#W6&{{Tl$l1SM&;XnG-1fLQ#;ljl`H=!7+`pfK3
zvpl{Zg?=fSLHjgO{{XzzqX)sy5J<U_<_NuqHQP7D*g*MgCO*Z_HC|7NdzHMq6-FHG
zbJml@%zn)r<bMTk0R8r<3L3i~!Fw_P03RC3WB$O!T9e`}^Bk?6xE_o-s_pRuT6}~^
z6VnS*^@)$!qTGK6^aa3^P`Z$M4xh@d$MCDd@niQl5BQ#I3H)uXxBRz{KkSOG{wLOC
z<*y%_pKU(j$d1M@hkh4`bEPvM_Rs$SUarUCFAhL3G;3^sv_*OA>za&@lXoZQRo?#j
z%VzFE4{g-Fq~B5UBh{Bo(ILT(!o@M`ik)sW*tm>Xuh3VG8E47N(t6-EFtf4w-H+o_
zcE@CULDg)Nt?jCN1r=UT5b3cN&Z{3CLZ~(5DxtcJ_NDUF<N<;8q!vf1w~KUj&UGmy
z_FAa^Gtt!izi5!3ezoTt6>)_edr(z@pms-m{yWpvzDp?|+`U(Sh&ISrE|$mYbDH8A
za=Z#cqcp(l<oJa-Bg)g_RreJi{45<yY1?lAIqWf9rol_F=9PfyPmi^7IM_Y*)Cb0T
z<b;uOsqL^<09=}OI|@U&t1pSQsSbYH$?6Ast0u9i&G+vmIq$gDOlPk&iZhx*Bx|du
zQXb+%yV0r~K1uUjo|(-_w;bY-4s(iPA#~n;e4lc2OS1>9Oh+9vKvSHNPQ@Z6k7*}w
zB;?b?SV6UFMMoTfaZgoa&M-abu*&{lsH7@K6=<j={K`KXfU5VAKBcNTkXUN2e!i5b
zxuqKbB+DQD^-1R2j<-mrj(D!2W_x5(vY^;bF<83JlOCc}@)=0zd)4@6$I5DF8;(XX
zTJokv&KB!HxrR&y;f@GCmDc!uS}i3~Z;|nWKMJ%}f$PAgg~vgPPMTxpIeX0?exmZb
z<y(!RYQCqZh;7zbf!H{1IvVPxgts7b?^Wis^Wc&v18WQuo|L5pYZnQ$?s?q6f@-6Z
z4QbuN(8}?*-cmuV$%ZS2X!NPbV331SthG$G4JeYZk~&i~R%)3ftksgNM<r&;xuUO6
zF|^=Dx#aR{v{`Icm8$JfO-RY@tb&1o#a7pCzS9E2hXkIrqLKriM?I=|Y|?21KS9XN
z1W3;ositX)z4r5(%$7Aa`;R8Jb!Oimm-3OC!@p&Y6^#yDjGECL%;&C^Wxd!vdREMK
zo=V0C8+(IM*x2ovu4Y_%3|6<6JiX*&Ju2==t7Ul&oMqVjn?_A^dM)*iwIA+WZUd!x
z_3OyGY^6E*a4QGHnyt>0u0=9%ukyYYx~RPd@cz;_J(g`XqmZfN9+cIv!3TFv)Y&{m
zZ1AL#5HdT}fA~o(@x~iH)vK*Lo@ArS>}^GTJ-h)V%Z2DgNgUDLAZ%i}*YPE;Fccnr
zYPj(dK>Lw)gN{1Wu_sdYp@|^kpf-$aHa`=@%kxHk*k=`CJV$KfJ9GL_1%|U?G0i~w
zbe&e6{{RUMp&0(PDr<I4kDD2w1cDhO`CJkYdXif=+rAgU^rc-=&Bk}}{_RM*g`w#$
zPijC>23(&pNXJZ5j9bqulUI%05B~ryBQy!2JsC&7c%}stZdCNeGE!iP*o*)xQ_P2q
zu;<dM>S8vqmz-pEs*1ZMyCcpuS(@)s3U;tKB#Hna9+d^d?YoexV1wSIjmsz`4t*=x
zg0yUT^&Q>GqEbiA#&goFGJ=B?sDT&X6e-&uYNIfff8t)prcNrnmXiIO%{azAYHO((
zbjbcuhB(K1r#1B6L5+@3j8<=(p`s?z2y2re&J=X5M3;Vge8;t8Y0vUW>6{9@k_frL
z9`!^r%i%t5!@Wl%{^w_QsU#SI2|T|_VFS*<>@rOuqLry=q?dk5fyQdXzS|W&8Q=7%
z$Wv)C`B|N~#Wq33yg5C3&}mY9^0_7M$qZ2-_sOa%0KbtK@T0v*(-hTOB~9BGJk?m`
zGF)7{j1Xy(bGNaWwF$0cW)Hg{=bToynR)%Ia)|6oh3o5C*CkE7@|NJ|9CWBO8HK(4
zY}{@K6kMxa8$V})Elz7xY#qClnq;#(K-SD~(eeqZ_p<EO{?Z2UP6$1POM1Xaml6HR
z2n5v%#L|_#)6tX_nF!8LL02sippiyN+@NRHu`Z;0Nw>y9N9P8&n&Bj{hGbwE5u8#B
z6|J1bt}I6(SoE&DPTdr<CO%det~eEKa?0UJWnvWbz^>T<O+z5#aK=5VCJh0=wT%A&
zc1&irEp0r_P+bwjCMy`m@>|ImAh>*~_O8CoK(U3p?XEmT`BA+Hb3IEDBBu&4Dn>Y7
zwHg{7uq(@M?DP>vVhn`SbI<gmW&zKwMo2vkNX29=(z5UEa(8~UsIqOS?ipP_r6HWp
znqp(xs@%vWT%3M&V)$YG0IaKtFh(kXmrI2{(9&Z(n%V`PWlZNMpsG4}5yQM-6WX-2
z^X6WI)G442j?OZ$u2&pWra7xYvZH}jB_nrA1T=$=4KNo6?_^Vn`F-jV+|UD=<XT9s
z-A)^=H01vPg)pugIHU!kaLm+i$*2N@>MBJXQv!836!LN^5J426;(#n$pPQPr@rPUy
zRV~3J;;l6B+o5^n3Zj59Z{RT&$4cX7UGg*fn%~!aO#@yFXgTAku4d|1A())gB4S(>
zSaJCp&5a0ShU$2vX<5|##E(NvjP7bg8gY^3fN~g8@wbYv6Kw-`LsH4|D9=MkqA3nf
zJ*pI7lP@_Lrq1kgR{^~$7#zq{W7>o>q>JZ_I*y=c6=hR^bInz;ltiHV40F=0Je!v*
z^`=P#r!L!m?`opi^El~OUk@M4)~Pt#k(~FWF@$YAkHW0OF5aM;&JJ1e-mk$PaqB=9
zqd6EOuS!RczA8jPw;q(~SB1~zND3&eovbOvNEyMY@DE(mNY5Rq0Eluo4x_bPO|nPS
z2FFUQunoD*IR-n7^q^$1KE~MndsL2d7{>%uF9SO%&V7YVvtYwe0~8W{X-cl*4Li%|
zM@n&DUbGB?MB}AHx8>wwt%11osNFa;fQeUf^`?~@sZji)mHP2aV}>!dqh)scoPkQ6
zd8xwuyk?bzR6H-uiqD;hkZt8nX|x#(-D<4R7hI?q6j%y~aKny0O<hJ%-FT{kHUM$Y
zT9z!3OH%^;OdRp+R-+838RD~{1UI!^iOBCjizxdsOqIh>8*t8PvMQ9yoYN4#VvshP
zxn|%1d)9ntyM|3%wr!FF_)rG5yvw*L^~F)Yi^{re4jg0}o;F>;(W)=*5^lrg{LKOq
z)Qo~oMO&09P(@R-!*Dv9mgQRrfa5*r0YvV+Aly$MN`_$QRfk;Ek>)kpc|N9+KwUCA
z&<6qW8%UB^W4(=Yk@E!{lU_}Jj3Zt!r{)5_iq!3fqoU0V47#Z+^{)liqfv1x5EYS#
z+gH#L%ec<(>t3DUc?b3?^Im5z#UySA9+l|60&ymngMvq;c{#jqK<>gneDn<^zj*w1
ztBgKliqF#cm##-j(P8r*YvF4AXR%CWE--r0j1Fk5&46)5Egek)0m-C13UK7rJwo<7
zD`%CQ4WqqpLX7KFRN%E@l$2H3LtNJ5)1fK|GI|R0d%KsqnVv@6%yLaw)inpdx{_wx
z19Zu({8#LG7EezBMSnBg`25Ej>(7;JShBK~{^>2^<9AlCRMRX*pJf%go)t%0^KAn3
zSnAQca*T0|bgxrZ3<D|1Jm$W0jjL8%l>Wi#WRQm|mr_oYnavcn`O7`=MH!?flc#z>
z56n^y+iS)3`v#9!xS2j>GJ16BUeI%~{{Y=J<T{o5uDy3|>@pvY)$}<J@g$BMYWGpE
zsO0!{cH{15xy>_Gn@qb|GJLk-!L8fd_-=H=4$;tXYN~i<DYX9pv>|Q#az%YoPoWrj
z!Be#QoA;KMn*N-!CJW=`$E|QzHj-LS@X6IqGwWOa7dMud{{Uwp#9oDX9MqmMjy1Sf
zLGzpfNBQ@yCb^@jR3+@{@^lXc<9xUW0l54}HJ#!@KeZc<Ok??)((qx-lX?clW_Xm7
zs=j*dss8|%WyAgDokoEF0P!IlU<LkyxfoP`ZUfHmFy^|y50fs0yE$#Ru3iXc8sSz$
zo&NycBvbn+%AdzGrtv7wlD?fXYVMahN1`Lh2G(4krYet#c+!+~$FFLZ+>iK2bK4l=
zuJ)15%X(`4$WMs0=t~&m!>I4px!Lu3H62<PVTIrF;<6+kG5YnV*nh}E-_vzvDvjuR
z5W_|h<~q+8ll_Yy)1`1|7&bGHrFT9oZQ3#~(zr6%Zbl6=!m05V!_8{qMQr+mQ=M1O
zIB5D-drOtZYW<d-_K*>B%+-}g7^|^H4Z9Xi%B(^94|=hqtoIjz;j?EQe8NA*x(zeJ
zkU|8vzq~vUotC-;RgHE=fGFqyuPYIlQ;p*dPgf0sY4gaZ6JG5A#utv8MrrD|a)PD6
z_bXGpW=vxs`%{!j5a1K(UPG&QbJbcIcUm3v(H*{1?j1m`W%MiC88bDkiZl1PKgzq<
z@7YcrK_0%9e%AU48*Hi>dUUSZIfS6CBy!@g?zXo)s!t{<OE~0vP|S_WoR2|Xf#N>}
zMXDp-Y0f<0GqbL1%_dpw?%E54G03MFVT$!=)s1C%v&655l|9LBY+mef)C}_2thKXs
zeWiYE^sPvyXK=fK%}gyOFO^-{_pXS^tqxNo%90lf%Z&6jE5-8f>r&q|izr9q9R)`j
zF1W`vsYN#m8=$K;t`=ys#vF4^k_7~o<+|}z*o9;#qPm_ww8nb|l_vWrn?J%ol~}xW
zTUKc}Us}r2x4xd6Umn=3zY*SC1xq-kQ1YF)#dOm6MI%1a%ll(kc4FUVjPc(!*TbdT
zz~3ks?axZ3qG=+}Pe9DxV-8MhP(&B_{{ULllFF4uz;2Ztz!Jh$c_*-@7|?$oN_<d^
zU>xJ#vZ?Tu6TI+Nl@_0($NQz-oae1?$88nF%#x<%VS+0=!;$$qL~)iRuUyu>xgTm3
z!yS$6V%>Z)@Wt36tUzPjG5-J>@-H5EBmNPKk@ja}Zr^Y*{VV9uFl)<xGbVKVM*je&
zm_L<jh>|=SUi?*Q1{ba><m>Y>>7Ht_Qp7GsP6b;tN6_C6H21pjbVy$tkcze8JvQRQ
zRMe~;!z!>~aqCt-7XJXqs}2r${<W{C#pL*w`OopH;;^yQna$Y4abx1U_+Aphlrp&V
z^#1@pm5Xz&GHY_%U%?_|<q18jyP7aOSS39?t){cQRcCE*Baoto2dNb@DHyie<aUw=
ziXzB3Di^hD!{U7sNdcBElX{iKXK8lU>2?f?2(FfG8%>=<m{;?tMK*aq#OwQ8+3nf@
z7;eVkYt9-ck+vYqo&|UR01_<Xw$z|V5s1k+12xCnTHU?c6t$Irae@}R>8X1=q;tux
zVe(pD>3VkTkb30ws@C2p)-BU&-5tJ%rFUBAhqYVH97k`bO7b3d;<;G<9eAp5yQHws
z_oN@=U3q;^X;1g6#x=Bl>oM*%o2!P*_eYO>Rm(pUYBuqhQtgab#tF%<OVK_Suh>zq
z^w@;tati}iZ@v=SUBpCI@ms%U2mC9k)uVfIne$H8JeKELxSBQwc{AzSxtZi=bCP&9
z>$Ch6yox7(?R3sMZ2ti3*OhA;blN_lEtJkAWMVgt^~;D+Zt*mPx)g+%<24H%&(@m6
z{{Z!=y=#=#<eR81ii~yZPR3{fH)VxNj?2@nFbZ;vbf6EVJ`DKM-upz0N4vREc@N5p
zc*yOF^~`(M#F`GZHi4?!Uqiu)K-_;{YWlB4@zu7grNeL+EX(s_nux10$*s-b5T}`-
z-KpekIj@v;jvSnFTX8>)eH-F06~q0DaIvWjRE)CM&6?z;%auPb8%J^Vtzfkwv)uLN
z^Zp#gD)alaZadeW1C<9oYFIp3c|U_8(~QZ&Dsa5uRS2#bVpVkH4x+9q$VI<#Psqhr
z^N_DoP7W|T(*jpt-5zVtZ;&n2oag2yyXil99^CaEYlYOJ@@}0nGFY{C;P++~ibP~n
z(D6+pBAlIT(TU8-I#PqkpkN9PJ65C-+zvBUjai$N_o}_?8k?HOVpw|BvD2+nhpFvX
z6p|=`6Wm@XqrDZO0*Y`MrH(h2REjT|*x^Qc*Joq!!^9VM{&9PFm4-kkH4>=^d`xOB
z>~VxsPaIaJucS|--WzGyIUmNOipyioQj%)uO*OdF){Id_F$O6p??+BEK*i_UfzEJg
zI(v#<^ngzEVw8ItI`*JKXC{ugqL0Ry3y#^N9+Y?Vp!M%S2z%0=DCU9G(ioVd@TH>|
z6bKJa)OMrsp#F3WFnwqT)`~(X0de@zj2@H@xTQU45Qd5~%?5#qk6K<R8K7sq00dBZ
z6jI`V6R4t$Q9uP8W{M~PqZu?~J!tPh1sUd!DR}iXfK1|!f`iDTuQb3jMn^Ps$9g&J
zDF6ZVqXK|EDClW`5znOnVvJ^w#+AT3(My9$Mg<oEw0FfJWf;p0`cj4f<2?FOxa=6C
zlTt+!&T$eux1x%-9*?NXe|M+d9RC1$a4LDy3ls-hTvn54dZMzUSjep10j(>418Z}T
zSz?RobDB=97g6#vn*#=vsU5RjlKeQ-cJ6D`80r;ibpHSWi;10XZyyWB5MrU?DXydT
zayY^;DLU7vMey%POc!}y>eQFM4AJc&4HdtB>`iC&$aF8*Nb>xEd*|s>Bo`0&ZRbDm
z176Kzqu4`hAC+$(Pwv&#wuJx!CC{!aIb(YwmLJUVIJB)o=0hAdk~8(g4Yj8SgLS!f
z?tvl)yFPJVjU0YPuv8$$Y$~5#DkY4ULcM}KvR?vfFv4V(blN|<D$SR}`7R<4ae78a
zMHsI|yM?5-eW0DboYY!k?X~%a2=%PqDt0T_#N-p<#i8Y{rawc9#qlSGAkh&XGb1S=
zWb=ykU_d#pN5{$k021Bc94Q&9qh4-lHWQ~66F=cpf-PF+EaNN=E7o;gJvB>5ww17r
z!Nqv5!`c4N;*~;w)+i_SuXcA4#?roafxC*FR+R#W!dBC4E%eJox3-G`2LN}kDEN=4
zYO-F4E)k-(-IXJ~b&&i-fcSy*`Qs7B7^<=A)xWH0_MRcr$~aay$~{CMvzIi{Z&hS@
zx5BlF?`JQDkT+5}_ODjHcN%=n7zMG?yj#e<@IQ#W#u79P*d%&py=O`B9-FILquboa
zyr|rS^Z8X`7roEWntEt>MzC%Ur*O9|CiQH4{{Z#t)qWT?`{*a_A-uof&*xn=#*d`l
zPLs`RZt??=#}zHsr>1E3z{xyOqW=I0qNQaxsKpecXL5&(o;C2)`}*u8RDKQB?e!fN
zAsoA;kA@!g=Ds)ao9nJEtzT`jwj18LjUQaU(60p6GVRaaMm!qQI9WPmN}^Idlg7Rh
zo5WBDw{Rsx^5(Mq8{wZ3Xp-!bNK)H7h{ob-g^$I}h!*P0EsvR%u~S@pUAJh@*{!~1
z>z>s-l~j2wK4`sedSGT%8}ZF~2aeQR_@d5a0Q}$q?oDCe{6W`l?-q2JM5FjY<MOOc
zQ(C;$<ykJ|%P(~}ttjE=2X<#tq*}5*iqhosH24@W$WRY8n|<L;3ijphFCh-?)R_<X
z*M`O7oni}rCOhdd*zO>Y$kll@y;4@pm(oAE&T3W`Y2M@ZsP_Y+_)5ky40dUb?!f;5
zI`Z!pPo`S<k_(MFlWI2SF;_76_bz$4pC{4HL}hkjS;@~+ThhbIF7jkbY3z@0vG|Lj
z#izn0nYV@M(Ehbv<KoVd5oL-AT&c!M7_SxtZteIALfem0O)siK;q7F4cC+zKbqhHy
z?X3##<8yScI*RsNd%v|n+a<|4#~(_nPJ7Z4O=}uZin0@&p65p|jWubIM(+_!07lxe
zWvs_=K#=S{r0`90l;kX}@}J7Q%x+amymVG)eityEC$7h!#_f;2#aM_tzSYJ}b2?PB
z3w+Ft$MIJ6mDFnBy9{^drF>Q^2`Vyb*FL6|Sk#9yHSP3ko0m{N@2IWYe+{&0hm<$y
zYbx7Zh6Nuw<Ji`k_?09ZM&thKlU_YYVw<#LHta=rqsA8le(ZGyxE*fOP`J5xVJeWX
z8=H*RqQ^bu`j4{NO(Abo$Lm?1Ch*1Hn_}98%olGZMSV6$3beiIi&M|X%}SptXPZ8O
zeH=b)xC!higTvQ13SC$P9m%3^5lU5~l2&x=1ynlpsK2_A)k*1JQmfWyg6Y6DEj_F-
zT2T2oKGmL0Ues>|-Lz!&&R81E2cEUxPHs`VIcFO^2{(4n;Yrx@O`{^UBEz~5Uur|s
zG;XBcG1r=R3krRx92#$!gdCB@Cz`!OenO699HgJhl=Y^r_h71ybI0B5^s5o+_wt{T
z&QtHV9Mton*^pp;X?tMR__PgHL;nCCg#qr&D$@8~`LVu8qWYZFy0BeCk(k_OlRTQ<
z{{VzvY0SEuYCqXdX~RL&)o}NcNuTbD&EjCXmF%V1=kh&hBoAuoS4+|mV8tu_TNNT%
z=}1E^o`m+x6H@Vz8l@wY5+FF;QYy(I#Bn?Q1$JWLVo%-MM!!X)?Xos_+m66iPZ`-4
z>`qm5y+&WTXDG+0s}cBnRFwY!sPg{++I9d}L~f)!?{Ch5aV{`fu~6}n>>kM&(fCsJ
z#$>s-kJud4<HAYOO-z5lW37~6!zP?mW2R~zDrG8hGZ(`;VycOznqoM};-_5?MvRTN
zW&PRBTrG-Faw|7peaiN6B3pYXR0wP#3-8T6W!kukD5D?jpr@WkYH!`_KD8dwPpJ72
z8SY0${VG2)b~tBZKD99*j=zmY&5_3<moQjD4&J2GNWi5sCOYHmQ8dtk36XK^YI)G?
zNEaXBP3U@6Ni`T1vAk4mtH6MK#QI=V`$#UOa!Hy>ayn7bYaHuI{3y+zPAU_wOP`hi
zKD93q1X86Vc|jwnr>kLq!nwBAu9?17jdSWMyqcBc{{YKUpYGKCW&!MGc9E1MX9w$3
z31e2|p!{pjZm;irvIWbJp~Ydn#l(zvT+H8BHLNGku$?y@&tI1Q#x!8}F@yf_tm$=~
zE<U%hZaue(^6aq~XJQXxYep+HlGyD4p5Ru|rzf#4$7MH)w3zt&M(_7VYJ|Qr)6@N0
zNdExv8slzbSk3~0PytgYwCu;B*URH%P<*RG-t2KzB=M!wXUn#YPpLVsaQ>8-rC`w8
ze-`SFIB1jHFEw5KNvlcL@xKKh;aQt$Leo(V3s0)*51rR?<onfjo^}{%q$AypAVO)|
zDCA*s9kd1dRQoA}VAACs$*p2X$z{kDHN+c}C^3%J6{*H*+k(kngegW;^fPj^Ge8-o
zBdttR=b)u>`#nmz2H$F3fb<nGN_NgF<49K_5&Kg4e$_gsYH&)`Q74$M<@N%cu^jZN
z_TbaP@zSkP7cl^fjL>4oO0pLRwFPPW5pxwnQ&|A3TQT&eFr?{~%s_yH+O%L`Qx!u4
zHDcW1hHH8~iIEM`W>fuY5S4P}a@nRu9^=zBjH#t2H7y3JW7jn-XuN_mQmiK&kH(x6
z4??CFDwO%Tpe0V}&IJJtXsMxd4OPIU#v9(G3&k~tR)<Vi8e1!lG3`~Q<ozmUs9YZP
zl%QH=d~zz>Ju0!yPYJ-Pp`!^8nLGZq2HtAp45e2CBAnr<lNpKv=e0bFTvT!lk8J^Y
zr-6!Hze+g*;{sEF0B1Dd271zgfzqEKTxKw9Tf?psQQBLcF<F@BioK;bm8ihn72Shg
zem)%3B#o%MNgl9=HtUm6=LVf`^VxzuDTC`@pEYKE4LxEzc5z5rke*H{xus)4#{^P#
z{*(ep#V1+-Q^4Yo(sZTIBbs7pX%yBtUMc5{^VYL<d+)K@IT$QQ$}6u4hn6C$rxQAr
z6*%)V8^pKcKW9f9_TvM!b0Y(%YJ8G3vplZZEOKf-57xg=!QtbFq@fe#Yt?lo<i+P<
z$6tEu{5xf~6DGz5@LP9oE0d1`L@aQ*8?j!4rmC&5L>qRDVD+z^;#%@hRM%6{%IT)u
zi@4^3I2`7VJ5pzYE8<UZqo}BBW?cR?=gvQP;}`*muSUHYwjgyi=eGbQ)W8qo?_YPr
zQ@sX{2Q-bOnIBK3ZuoLdueY3Lu!kqLYUl)uq5&L_<z3m_6tJ>6urAe6-S#}v=9s*y
z`}0m8m40f^rxejeC*eq9_Micd=7EgRMkoPKJt)ox6rA+M6acgn&orEhQ$PnD>uW{6
zOEzg5HgnhmSiJ>Wv?F23<F#!<Zk<IWV_G+jjk)}L3>OU&SV+WmCAiI0o8kq|KX+ya
z*13z++jSt%dVp8jQ<HH#DMco9a(L%dZ0wFP-=$TP#yZRLlZEyQKf<xd7^ay200CMM
zYPXAZ;sE<*2e85ZRSEG9vnN~my?8Z1CJs8#5wpO>F&7(C)F%YVeQ??T0BaQ!++4F0
z_K7ff!8xeLM--uR-}+Oqh@|ry0L=JagVLIrRwUq@^&_Q9V>#XY=<?gtP$7ptxb~xH
zAH$z~RH8QaKT2_ojO1t9otZ=!`HncC0tPcv00}|%zHGt94F)`QAbn`Ch=QMd(Xitb
z=4jXNIsiRdqHC*U`}a`~_!SmlDNZx%M$c-6^=&mi_4EV&1yH|;w3Hiu*oWx3r^>?R
z;FR#at1S4VNX7-hKSiN@QKvA>aL*^W0;)9R_9e>3s7~M-a2$II$$t{YSLCpipH^@x
z2k{Gmxpe;k{E1tAR;OZptb3cJDLq9VTJ8JFE0mkXvqZoxif8?%s;%PvOZZ~9kLWW|
z?4*jh+iX?FKMHA9Uc?VvR}kJT))}~XP<Fy*qi+%G3{GxA`YtH;Y%X`9T=Yi846Tfn
zHRms^>aF*$rRSawDh9p1a6{f)9RC2*Lr1e=bb3H%9P#;zagYvPNZ0DZyv%uya?;4d
z-OXLKwnEupex#b-o)%LwomCUOYs*N1^DiJC+p|b@jU^YG=+DsCB(O#>c8YO9i~uoR
zKiT?jW%ZMxm&Cd}V;+9udTkX={8goa!FE4N=WZ?I9T$$+6-lFHJl8bvyr$5qnbg0F
z?38?#^Evurpgu8O-z|e+^gHXCDoOs7g->0z9>EsobZz4qv+~)1JqgW1-Z8&?g@Pcy
zgjNwwM-?KjSaK?(L0nwspz$WHCU(3@?x|KG)wM~!_2C?U3X02(FgWX1VZxjq1$R=z
zN2)pMR%>F}xxHcYUrc_SRAf&e!(7bG*qIG4YMvrDu0X&&>Z{@4pxun=)|-~B(YMpt
z?fk$u<Z?|y*85oIKAyGH>9C{PZUpm><w<d78QHPPug<IDTB#&`1vvYt<&C~i3VHXb
z;IT3=82m9?e`Dkf0BU$Gc5#ZrShH0V);7YQ#-lxjD3TF?Wl{LokGGE^X8!<R^MAil
z{{X^i1CT!0LH2bO_DV;Rdmq}ZNBp;5PkLit*{|N1eQU_m#MaUtE|~YmMNFE^GPlV)
zbnevd!pEsTt6%}d!H?xt=G7rFmQAGe_O1des9f%M41GQQD?#peL^d!39jaSpBuA~!
z3ow~IFxVA?B#9#KMhvH+2O_p!BQueM=~XUt=t7nsCOUv?o^k4R!lGIjjz(%WkyDmn
zqukRqI~n5NED|_D>T3a-P2@N^HOnM+LRU9Vp$fLuV(sX>)r)CvXO(cci#+4{)(yD=
zQC&8jDl!Ac7lV$~gtRt`H!b4;4^dhQxKDbcZ!(MzZ(6X|8%Ju)vEp5hHxMf6z7gA#
zy#VQxSXVa+0X<Ksta;w<=OAPQ(FHU_mCftDPCuDchB?MXRVFBZdpmv=i50!%Y=3q}
zJ7S-0qiPzJ)+BSV`W}^cGI2DL{{YUoBREAo0aM;zdCsbiR1U_h#o;-jfkHEXym{iH
zJ{P%JGLN5QM>zeN70t^30A~~{)q0+l$H2^&N%P|jJCj{*p`~hq+^^YO?f&TMD+<#{
zxJ%VD!ypRVi6*zh&wHIwii}Rh+d4?jH*6hhhU^Xr<W%#v*cCbh*wsP#;=AB@Rb%fq
zSkE~Jr9B%2VAXKg&s<`qLzCNz)W*it2lqqyRN3d=s@osjkLgwi*NTx60lV|2gabT&
zTvCn(DSCYc05nFSz5cYI9C1+GUO@zVo$zyt<u#8Oh*hJvBRTc$R~R{LBdmLv;r{?x
zHqXYW&*CdM3Ey*_xF-g@&ih=wy;cRbk48D>vm{5AetBKJiO8;q;U>v)Nc9ur+f{6&
z?YE#Mk2Ni?jG@%#Yh;|{jN_$wA+<(3nE^GWqQ&HD3h|s1$KhK;2`Ia=B_z?_$oant
zPT<EKYewEM3W0zHU|F{L!C{i7x+vG?;P&Rb7Ka4ONV|z6ie<`$g_z(9nOq`ckF7;@
zwo5$ohCM|BMN6p*!vbv>Q{JmenB9|+Q{A7M0q8o_E1RSNqd$Avgjr(Afs`izbtbeV
z1Clyc1*D|i{I$MU5vED`sR@=Mkh=ve2tmeaIT6hvAa3c3sk;U6dT~f4Cfxz*Pc#a}
zmWRuN1<o0dK}hkZ_K-#=<y_*4<Y%~rK^!kN3c+!6cQm_~0Aui^1Z{T@+NRh>dRAmI
zgjtWSd8-j=?8!XMfsabAum#g*W*E<<1*0D3B|2+4Jof^#BbA|Kd|<CNwRsja@B<OM
zipIS{s}?c_X&NI+2TO%g-^4#!XnnqAu{i+bW}(tHwWZ1&h8&JL%|f>;AoBxZ*Vd^q
zG-_FuypUT>_mFNwS~iDlGr`8;$QY~$?lwsk(mqHdIP|TnxxUYIvkc&Y`BM=VpFZoz
z<8E1BBX=KK^eGCh<-0M?;fnKt7yL{FiOTT6F|SmzvKNusP6l?5l>63Iq@u1k$C=o%
zrfKBdO49UZ%KHl2W3n|>=}iC(0o%PcN6E!_^=dh@(5DVmN{xl6rI2En9FFwaIUI_>
z)Ph*U9QUM-E@{j_JQ_my??_^peRELD3ERQVI!mC7oYqzLv>;aOqtmS*DC#jXmT%$4
zKN`T0d6O!yAR51MtNo{N*l>GdqOpX$n}|Jo)d6=NTp$DQ#cAkpvq;6eox-Tej`*#;
z8aze2)4#niHu3`TRhZ<SwJV+~6U`wFXZd>6B=b*diLr`6Oq|l54OI@su~yKiUU{Yh
z6US;%p45kFrBVQ<1C(*kTBoUN7TQ!`&da#}012y7%(n16u0T~4<NhbtP5!QVO{j37
zP*hdUhf(p(<H+A;!YJbhxc07k_r&+};a=r}_Zh4?W!^da)mCQt4KrR-t<o+H#n^Xc
zDtd9=wk}h8<TlY*9u|qDR+KP3tEp>!u(5XS!89|Lr^H||#DsnoBx|(fkF8U<m7}_F
zPI2C>#O7VO>fNeIFQCfq7%NCfXz<x7(<8Mt5=clZ_ekUlF^6VSMtH>{idPC@lahT$
zy*AOeK7I2=>t!*Tj?X*rdeDKLGy~=At=6oL6ocNNi9k&I3XzLr9Fa_snZf6Zp)(aE
zG0u7#y8J0DGwdrm<-;#RIHWQo!)Nua8#z3|gMihPu36Mpg}EiO)9|1TXvWm!^`+{Z
zifll-;+0R#P>yH;tTF)=R#ZE`*{iJ%Lvz>OqLL%zoOSo41$ddj;P8EF!9lx|!K#Q|
zatOz_rBAf52Q*j<NWiW$f;}okaC4q&oPR5SjaVP+0TcmcSP_l1?VFd1YILg$iUvd@
zE7qcvVD!yhC`$U&E-~7W%05^*IH;a7tLs+WcNGJ+(SywZLd}v5T!Dul)~S|Wn8jI)
zVRJx*BL#rR(y2`w<kj840!>3B0uM9+l*Pl~^rmonF{=}l368wgBETLxde9=&PQc?i
z&0B_E_~NpnkgJa1)x?u;x}KB)pc}3!cM+aAs>vY)XFSx{3_bnnfa4|&Sb|k!%T{!p
z9<?M4Ffwpx5xo!v_&+UMbl+&`4t*;k37R&+IUcpGZ7?8%+)xE;R@%cAYWW0^D~{cH
zs`%MEf!Vr>w;;{4DLfhgtB_WtPDV#+fg5Ma-73Uj1mb`qUy^S{ZVh<nj_j9D*QH6K
z{oLO&oN@I1E7+tsdglCbq+9BmKc6aP;pZZ%AaQyxgtT2s(l?N-Zbo|6t)7c-qe}5x
zV5WM5T#d||Y!t&Wi>KW+tKpfRMSasWtbX?9&MVK%*ZVxKb>V(9veUog;<TUdR#u+d
zZc{xgQbU<5;A<~<_UVXe1s(d(csQ($MWv>L%^Bi=25^d4_OCqgF0j{ECK%3DdXClA
zc!vDiS+c7IX9Nt_o-}IiOFEZ5YxF)4%GJKLQF<N*ag1?Z$^}OJ=`rt8$bnlO>OL#<
zWY3qq!FXkGc~g;Inc<y8U+GDc`@|SE=3rLug|!o7sjMWC6uo)=D)2aqFZ$*VNp6o<
zD#Uv#ysu_@P~_xNifH6!m$iN|D7d>b?1iK!Ii;ZRDgZ;k{0(?-j4ZBO#B<9XyOE#0
z+P%z;!_vH$#gN_&b^NdOWwXhze<78tKSPfiy~7Jkp6$<*aHk8<p7qq}+Sm4Kn55<`
z_w8Ji{{Y(2f>X;sk2P^(x}Q(|;(qh^tLu&mc5jwj9gLnJ)1gLq#v7(<j@7j{)UG#j
z5l;a3ssv*`-KnJDb5Sado~;}_DZXTHcyCmO!buWtH=mT%O=|KxtwEkLHj((&QNs?@
zx#JZa+F0Az$Df?r(6#2%7{xYPCOmsrQ~kH478eVG{Wn*g56*$X$N(Cs)M&=85)~!P
zZ)=*<Y7e$DL}31vqXxTbG=mFgJ8^+rhEH=q>+MIhcezgu2NfQ}<ZaB@>6((r6Mq0z
z$=^}O8_eMmcQLNVN6}-jgY7o}2F7xGQ5AAA6=O~oBJnzx(+~yEt#C3D8oF;0>Za;O
zjwTyBW74^o<+EDscn?+ymyuC<Vt4|*E5lkiv$R>{=11qA)yjBNP5VvoxPCVD&3Zz7
zqiDw!;%1nq{5YPj3lFC}hkbfe_acvahDX5Q)Fw>#uLqXrre70rfCVR+yRIsdNP1O-
zetGXw<6#y;Lm<PiUrMiWV$p*nWR&&vspA<nW;qHSjmnyycM*|k8nf8k#_V^;k&*3I
zynCZ*o+Z(R{gNzqk*;?t@_nl^`rFHYHa>=>({Gs@%W_Jd)!T=~N|v$M!o3L8N0E6_
zM=LM!Ms}Qz^?eM{!M)!D)K^X7pANLwhUUoOU+*Xtk6{|yxr*Zs2N*T<v?i;;O&$g!
zi>E6b<;<@0Htv1uF)=|}I?5v5Fhn6mWQEUK>M#}LEx<IuaC7PFPx(~P8|Y{m==ycn
zk)te(;aCp!lcd@{uc#Zzo8(vd2s~DDTu*&z4XSbp!LG|o(w5TI6moDgTGMujG-$^H
zssX>{UIr<CLVooMfd<pSq}qV+LHY{UoeIMK>pyy@jO`ncfZ5`q3ZKG+oM(Ygg&yYO
zD`=v8$<FP#3MwZg)rS>h&~(e&`+GQp+besD(~ACOl_WNDW7mpypJZ*c=+;?7ZBR3c
zdtckd8#~OK7qPB8SlHHz`^-?r7aq0d{{R;5Be=4*iWPY!54#F8fr_WDd`<f#?**_#
zhXe=oH9vwbUt5Lm?$Km!ipRLkbW?@(WKHOJ;nHuWZ<9~DVto+ety}mj#5ZM3I#h}?
zoUsG>*U^g}Izof~15+etsUUqTepr~Rnf?LO=F$8$1-;@dGJ(o&&MRItNcASTFP!nk
zL`Yuwq%T=}G;7XFG;p=|+H!hgsp}Tnex+`)Pm-at^0p~m!0%O^qxPy);wLs$hfmS%
z7_@P@Z}yIAQ7xoxxfO@EYK})ja4Hg49Mz~tu^jBPCBzKdj1jT*D@_-{IF1w_MXKAE
z@T4*U(yw7$w%V=6-U6@Tny)smENWUyh|qm;Q8R(kyz9rhmEE=2R7rfX$!Ps4JqxEE
zd06e{@mvw`btKPRDXLO<w%a-Td*{>xULkd_NbCZk&#2A?R{KTe*~Ae@?A=14tohEr
zs;;d14%YFn;`3p;c~OV0d8dwa3v;U%kd}8$jB$b3{)W0Q0NUQz>3``e!HD~Ztyb~M
zyIe(dbF{CPc*YMTetiB_rSBb1M;l8+#cplnww<GpVTa^>>I21enyf-~JvR=9x%NT{
z7{L{Zq9YvCfC1i-S2ZY6Kn+yQIQ+e-Nx-O?vp@<?;er7buc!E@Sko;&&24kGG539|
z7%LoLQ~a(y>7)mLr2Ig8oi<BNRnM8u9G<n!U*5woWk~@()rMnlV@Lxi?TVyLj;}yt
z<Z{I0oYzqf3|~s&G)wVsD26~ratEb%HpelH5Ob0-Rd6NPHgGB+g+~VfRN#%hL8#e)
z<o2Ne24TljT#mN5yd>~QIj)tpD>&b5lBhpg=XJ><o_{ha118?0yRfm6md8C;bY%9W
zjQ*6>IR>1E2iCm^oa~q$IHHc;w7AcD*vw>^DOE_~t~kPVs%_S>s%a6?95q~1kyMc3
zs_OEhlm#)=6F{UVty>_mr?6dC$%q7rM+Ux#({&lmnr;i_Y~a_;fy8sd{gy!0?^-qY
zpQ6I+{mfUDj_7sJJoCqFe%{Uq!EV*Y5;4Vh9x;!4$lQ&mwQ$5_@m&}xUY&@qA9y;N
z1t)rTIj+;3F^mcaPSl<0aZExJjs-4g{AdG;00&Av=%b;aL5c?+lu?c;g@xdXPSgrh
z*S!EC7^C@8id<)<05lFd($auv?e9Ph9cg+RF-JI{0*q#ideMpiN;^{WXvPg8iPn#5
zT+!Bm6X`}il<xF|g*>0Y(zplEQPP{{M~=UMrQW9iZprP6T)}236qRBtE6ackHgn0I
zge_TJ16pD7>9T$-DSJq+qvd9QQ|U+seXCN}!@9NOluKns9e1}%)rY`(v*XR46!jrV
zsCD4Fl%UzmQkv>6ybpJ24)?tbzJV)J&*AmE#IHTf>`2ZxU{t(JJCE5&;PHw$2a*MP
zT6{gyKn1+R@8%k*ZQ)HSEkUD^6_I!W-y*Yk$QSHndGDDXf7UPIKy@SlN%XH?hfUDo
zB~)7Fdkkb$m%44F)(p_Y85qj(QT535AFyYULj}a(811K#Pjo_R(rCK8tGRUfKt8-z
zu4#7B9X=wFDC4Fo_<>h|pneq(82b;{o-ZDSs>^V&{gA7l?;e$@7lAc*8EIi(!1b>~
zxP(Qk#zq33yjGx$=RN9Wi=RRJ6nS*M0@NXd%GWXcy@J&Ge}KN#51TdIfaeEl;=Lkx
zvui2q>MD+kxVM!K30L~{sQS#>E7?Tm<M?-`g#qN5y-x161l|kNEiYi<%9D+x@m=-+
zTFlk<q_Ink;BYEEyx&p#IF&8@Eu}!1TUfyK+g8SlU?Y8&aE?0d6{Nd%j4xqM#&{k0
zsP>ZXK2&4rc92CIg@t}nFfm$-8iT?Q%Ba|>Td6?xHK-Af9e$LYnOYed!fjYw0l}-n
zRq}%d>^f9B#7?%MznwbT0`{?f@o}^RL)if$%ahYNtjifc;%O=qjxqtQBN|7`OrQ_;
zs|;W1_WIL#x6r2_#Y9!p26SI8eQK_xq3mDUt54!R8U+O3BQN^{HJPY*&q!N$NSMgP
zbR1KSIbUJ(ByZ{O=2@ZdR=+yoEq){0Tib}no^m^rP*3qL=$7(rqEAEA)qP&0=ufnX
z*4;+yt0M$F;<moeAvne}UOlLI-&MSk9VQXTz0hD9sXvQ#snDz5K7EcWU#iWM?NRUX
z!)K@1Nj2@vK<($6<gGPp2a;#|TuT{qw{s4a<C5x^*9(iAxn&2lImJLFApERX=xUY?
z+g3}gdy8wDQgCmfKEb)JU&Y$?n|Y=*5nL>;dkXVLk;vuCcjVAyEIH{~)57vgn&ir@
z)s2k<RZS;dhVoS=FgBca=DkMa;+~8wom9Dfy$I`GExR-m^H#MeMsDoRGjZ6_)vrbF
zp)~571GeFYt?eV?Cb6X32r!bWt`(T`T!!wX^FcVPl{iURpyy{puXwie#28DG3J!iy
z2Q`Tl@>;QIBzTGb>tdh>(w8Edgi_^8K{+;Qe{br$HhsQqV~n}~02-}veLc<$)5z`W
zTfJ7!JJM$zC{*IMLgr()k_{naNlBAh2vA#hQYamIpISdm(cg*&C_da8D9FcJKu6Y)
zgS{A~q|Q%T05Ez|fxzaII42Yn&%FZ<2|Uq^4k<E0rj`bf4j|EwrAA~?)Z_7^%~Q~l
zeT62_>`BLZ8;H&`y!1ZwvBNy4Y;a2<_ET1)(e+7o?X!Nl=Au$b4k^8lX7Cq<^sP@t
zicLx%F|o)s+OLDWFA(ESkMXW+z^x=YVn;gdU<VoRU3|9*82R)0SAkJQw%O^^l#;R_
zUkrG1K2uDH{Y722v(s#c`ZbI(`-K^%EQ-sKN15+gC_uhx7nbusbrfUTvOH04ny!I!
z4BU;Ur&^p$OJf{VxmUN9TLckQ_Rv>%K1kI!!>LaQhD@t%01B$HUdVn+DVzQPYt%K3
zK*g+GLbmay*$Cx&^Hfd!$vIywN3z#iuc4HwyPSktPOWopg)Cd1yS`IXN8ycW*a2u0
zJ<NlO>P_v*;L1nRn$yg~23E(`sbX5#&C<Duo(|NQ4>DLI_ReZ$@NV3Bx|Cq&oF!>_
zu6nsN!g4)mc&UrnqL=(4`fNmbnuLwt0;f$IKtKsuWFU58Dts>7kPRY$qdX6#Pu3>-
zhqH*~w$b7sN2dZuLQZPHxrKk#*}@09)kDGJmZjC7a=8&}?UNDm2+(^draj#5Mr0s=
zvr(wyxTftSoPKp2?T?fh<YCLRd+w;5l5vxdtxC$+rW_vXG3!Ob%xKF2?MNd$oKR+o
zPcklPrt$?KZ^<VZ3!0ZWuA}8+m{NqrR+~_U79oSE^(b*rzP5+%L|Yy6ikDgosQsLo
zqqA_JCJuAbvOl(D$O@m<qitI8o8&5^=}_?zE7-}K*dDaufz^g9oBMU^^_b)7NYczs
zT4(3pvv{P6`nx)TA}ASUAB_#DTSlZbpkldSE6fKh>`$qw1*;L98qMPhSaW^#i#6PL
zla9(WRoh#HbV7eh%oeZx(@r){2MN!uX7Q}k*dpV2fQ*3y4}8;3uX8RoqMY`sjb$c7
z6*Yd!(+&ygSk%SIE8L|<CWLx!rFjRN4510_iow)VQ?zg<m4;7IUXP*xA=)_$+uE|c
zZKeZj=U^)iK^4bOA2(ByMf)h8eq@!t^se7pXiW7`exj|%Y|?hX_03MUIXNn8t<^&0
zGlW2l0r^veeFiIGblt=FcKg)P>Av6&)tj!6a+vE0JwT;4<o^H-bP1;@^e5L8@nMtO
z@~qw=50vK3v;P2hkEJ2Ca7KIAPHb`fG|{J_2ZQ)fu_!rCKI+~4u0>)pV4iExFD!tK
zush=w#$MW(nU7Ej&3jpV)kMx}@v%i$J!;jwj~FVCw0cwkQ{y<0dRMarW08f}Etcme
zty9HlO_HY-OK&_>)u-=V6BB77oT-pFr-6!cgP&TM(;djdb503T;8KCdTGdk~;{pm$
zoOY*yPF1S*Xf8xk6%>n#wnrRdp_F2>oiV0G4-P%*`VKfXK`<l+wJn04z4})8eTbP+
zhs{GT%~qwi0o$Im#*1hlH4}xHCRWBj`qbbv?Mi9b$?Z)cv8pNIc<VqM^rwN)R;dug
z0A`d7Q?bn$tFVDb<3R&G=~wT1Q?Z|VEFvrljIISvR+v`+iq1%+R@={dbZxb|(m27U
zu0i6IG-E8vcP4!)_J=QuU^!fInq+OU{{R|uT7jg<0*Zx{hvylmB)gYA>01Pzdh$&q
zfQ~_y%`{ZZK3{rf2jyBMK-_fqrm!Q5lmG^O=^SN6Hh`+iY8Mq@hcycTJu3+#L|0*+
zYDms0t=5$fHJo&1GTOG}$4Y^RJXFw;oN!GNs1kNLt);01IO+VUaYj9<arxBPp#Y`Z
z?@v%^#dDu(s|bt(PQeuA7^Nd3iwJJsIjL<9+sN4T2AD?_=zdw#zdh@Z6&urN)|=Gz
zT{(%dPIL0pn~Y|wXwAC7WAm#m_p9@2iq#rEj*q|~Ui6sc^rgiiJk%Qi6rCwYJZFkS
z!KMP|G?ZgJ&;~^SCO=xu)im>Y11Dy!KE%*L#xq?wY(((&6-aJpQktB3S?4#JZOxhe
z<Y#ZF6;qN<J6ELKTSqz+krlE#isrR141(M33xoaKWLMke`SmKvLavfLEJj@@`_MV8
zau4NQK8dXlk}3ZH)&Y#3ojI;{SS7cSl2qG{hdpT(@OLi_>s|Q#6+CS%PJBISP?o2q
zB!SdAjw#)1pYZ+Ml0p@q%)sT3b6o%#?m@54aTHw|jt`;ql;_VCA{&$YgX%f2KEGX;
za&k8l)6@Loy$)bJw#dlGHRsxxKiU#EW&;>C^?Wfuc1ZGbMX^)))td{SvfKyb(<ioS
zvFpI3=RIrct5S_vI7?&5rzZ(>BfqlNEar_zoPhM?_pJ!!iTX$nxI9;wjNss~`Y{z|
z+V<k!MP-&pQT#0D{A=X#Tr{<nDIUcf&!my*Bp=F*=i0I~eMH=*8>dcdU3yo^)}<;_
zaF*!x;UzfpAkGgIr=B>Z=hBMAprfT7MJGMZXaRH00QI1rD9;oCy(-PA<gPL*p{ec3
z-RMnJSG<Uy!cf&+W4O!g86SACsxNtM66Nk;U-zD~{9S7s-bXV7({JON!CQFo!jHzk
zMZ#cZQj(R=nXg?&Z5=~v8gR%radGL*K`)3j$ijxaUVRre$<1XLf4C3Ut3A1lk+cAP
z>ser&cOo@YI|lJCn4Ed?G4@)3_`1M-#JGRM70DQe>|kb>%f(OC>|ZiEi9BCzleW%x
zKkYCT2mB^XzjsX;_mlqstz7QYoYR&v!k4iZF}!?dcZ@BhYwMnBNc=^q+zhI~fb{uu
z#bL(>=T~h2T!YR%E4GFjFXB1s)oFXCulBa8!~Q<iN3>$0d)-BsKW>*N*i#QZ=|?M!
z4Eoo1)hTv4eZ2a!D(3G|^A2wA0LBI+HBj7Klk;54PI~UGiQvfTmG`PL+ki;M52bQc
z!*ab2s8+fuHs|}!&Gn|NU=Aw5haKn<pTe;AY`${2MZh~j{3%rjOab(%{G9fwBZOx)
zN|nQ$i6G#9m7{MNN{JJ{HEI!#{d?DC3Th`cT8)!{cGH6H9{#j13(2RU1-Q+29G9`3
zcWeu10Q=T^!L-)>#CcKPv*e2)`d1}dDe84os?5(Uj-r&It7bf&DLlMaFS0iFg-<Wo
z(~>`$td#mtr~#)MLUja=I=L54d8pI@Qzs2wl;dNba=AFA13hUvuVYJ&dy44X!LgE|
zWjO1O1yPbB8=BH!7;{iE^UpPnN_RG=GdZIK_6C$k$7-0WhCL6~lNHVE&H2boV?8Oz
zgdV?zOhBXnb?Hq)!sZ^IfvJ}VrA7y#sSse}Ij)E!IkL(QKf;_a2`7aV#XMAlAQHT{
zVMT3V$cMyt`XYIjNw{|83b!;TlZ@3r3y}5$=E~sXJx()P@-98A@*ID;h>||0j<8J2
z^1$m)NY~P(b;-%41B2T&$$Off9%2EB1D{YR5#aay>QW9kpbjhb-(w!fg>oM+2ZnL$
zgGxNnf#*sw+j*%m{uH<w?kRf+b{dfQwF~$iO5DkT>x#c`;+;z0h6yV7-PBfS9+aDZ
z{Z*W>@MS3-wv*$fd6F6P7;jOLT@&lpS0D)HN6(=j%Dj-r&#g^nWm}at`F37PgT->x
z!r0a_JyKa#TUN*$4{GBtqYE<>UJo_UTQ$YaqIt?t<Dtc5U8Y@zN8?^ib!K<b(HTL?
zx2L^nSl*O8u^{@@6AOdR54fo!QW$m>&d#WvBv)(z*g(&%X+?I$K5l*MH&1~CVT11^
zbv>%vkc4&ot0s*}c9~zF%Qdy9SRo4ARkP4~R!zSncWUcAHy7IPptdpjk&}kN{&XdG
zVr1-&tHVAUvzpuOR~D;=`>Ml(?^ZSK7S7f*n%*UiiN^xEnB!QHQ2+{~01C(P1AgW)
z)a0C3O<Hk`4>}bkDwjEk;K}*ARi%M(+zMily(!{eM|$P4+k21l@H-!4&1Y*3X>V#|
zk`)d7BNd?6QNtN|2mlP=*8{HV=TN&ibF&{VI2f&I?sj1C&b0N|tM=q}A(2S+4M>dy
z{{VC4&#h&7xNb<>Pg#^#TAhz}rdvj8%^FPx2Na4nzqj(L@ZRnDcl^D<t7~wMdBFDq
zwvA5biHXSVtusd1hm<{PeER-%hdun(%epiyqx-d1KN3DjD9w(;HGIjQ4Qwq+QnZoQ
zV=2kw+OxG?VjVU&CB{I>9-ob5KZ%{uks=|s<B&yjH_LN-DR*Oo)pMHCnoa6*w8(WW
zdglGvce1CZYaeN5JB~^3T1QKp7+=?#L#8_5u_}G5)}tyhTbNBq&A`c}$Q+8XCAXKx
zcYETa+k>2E+PalWeayLJFpfG^izf2!k-HO$j6~$%E^5WSrOV8X9AJexC7Tsq(iYrK
zGCK=IRb$U5j0)I}O@L%p9iH;aNa!+gT7PH?*lNYInWkSaxRaWF$pcJ{@N>S1!i#5@
zh8W|Tj{65ljBe^jIjICzo&NxN4{&{ZRV#!NJFwvQt4`lKaz0Vty;PT#U^Ca63o5}f
zM|67}RrS`?+#;|WcJ&?W7D5+MNVk3Aftr4^Y4%y+l`^ESLD100V^{5;Bb@i87lB$G
z&xI$ru67Hekw~YEoY2~aHXeBOskr%0x*Non_405)>MGusaFN4vB#)ihz|C?tT8bH@
z4%=9+b5pdpt6??7E=uF>`U);CL#B#&hMg$~EZeb~%y|N7U;+Vd=D9!kNGAImMIexK
z#?ekX)P~M91QzT^1X8(thSl0;&K&c&_N=X9+y{uM&mAe!>ggwttVRbM_Ngysj(MV0
zWEjRs=8KNTWwfT=;nX%VxjpKt$dTMJ3O2raRJw@8^OOLt1_-L8W-Z+aqV@|Lx_l8l
z6RMo;=O9(~m+g9P);V~`-cGozjUlA9mNtL&QejWGHKi(jlIy0_et=cnRxfCUZta;i
zmUP^p_pe&fHpQhRXYj5Q!Ma2Fle~$AW0k<;>0RU_%1wiT+PwT-RQ=PcjXP>vGJM9E
z$2`<qy3ks@)^!i$^HDs8GuE2&x}E?uz}{yEnnN1WlH6vYV<Yq=4{Ed(K<1U5LjM4T
zNXiD;q~YAwR;Q$a8x>+3A9#){YFXkyNp6+SYMR=|n8TC1jlJjs9X8r1V<|F>_iE5o
zjZ~Pzipq{pF>{}-Urel7su0#C-9SC-sMCN*O5?9QS1oR=_lh&r*I#W8$i{i%n2DXZ
zsIoCjApqi|Cmrbl8@>*DR3-Nk2Q;&(Vlhlen{Ymq0W@pKJ?h2{ByJM`^{2Cw{50$Y
zWb;qpkMW=(H8#ZxNdV%2IG-PCa@gtOC|O4C3C<0972U=sS8NX0^{%VOx}V#17lef>
zgyTNmmBdWqMf&v=%_3_nWd>=I91l_4R2H%qfOo}Pg*?ds11Hc^H0XC;9kmwvbZk*n
z5I7y_y0nr+##Cdoy7m>NWfzyGMY{l=ezlpXoQV^$9Vs)4TC)Y6-S-j>O>A3&$PZqd
zPHPthB*soNTNZ56AjjPvl^|#<Gp>4(L$31MNCkfI^`(h+x7LfIBae1=`_dVadO>Uh
zf;%4d9-epHsvbMiUodGi@79^7HgyEYIP7RcI>^t;MsVG+LOWyT!S|@Q7REY`^(Nw=
zvvLnwWQ}<;JN+v*>;QMEKH{!PC<(Zc)4gX(>$QL<j?{pTGxLwFY(VS5$2EelnHSc!
ztxBAC_n-}H8GO%`k&~a|?^hWD93J&j-Gbw{6>qBJtqf#k260v7W{zFBIIB!BIn75Z
zs3L$VNQ5^uESSd?JfLmPYO^=Zf;gZFckbgH)Parx%~lLlj2zT~sR4c$^B3me`&FpD
z4{D<p02uytawpuvfGh?h{3#hju5n5LJ@ZNj9Zo12N<|CTtyE<nHfsFIlblsY!8pOB
zBR!jI^yAj8LoV!&NUE0yWS@9r(9$F4p~V1PDhC<-DTf0is6A<l<gZ-*H05kCJ&gcT
zxrbvh2O!lqAy?3f)sZ(4N#dy7+o23qhXQ~q2?0GS&g_ALMN%<=&hNsdNqEKp^q>oB
z<wve6$CyuZRD+CvO0cb-e;Qy+;1$g}GxK!s-l8qX9D_hPAdK-qjToJOz4gs$+b{>~
z+OPv{!*;D3S#yF<N(5~*LvqNOIqOL~w%mJCTg&pFZ(5K?zbtvp08my8I@P#Xb6La@
zbjj1bT!liOC>ZGwm*Szgw-+{ZTame4af-Oy9QEx{ZrdWVo@u5Bfq0utxUjpBB%4$*
z1qWeAfQu#E@iVdHb*`i0WuMt@9%N0TQ=P-Pu1~=Z!&bQkNIYOy9%8SDk=2Fx&rY%j
z?FxC%Y*wKJIn89+lD7yu`qtEgBx1e-zLGt<WMpTIQMCHgy{R!+T-ZRkrEir_9jS56
zQ`G1CJ)5^qJJ$GmPOVtMbrhYI&KJcO=IZ@avD+6TKg4O#X<;-|b#gNy8SA$dl@|NW
zOKBr>NPmltwbJ;KPa{l@6z0EQiu$xD;i;c0(yHoKk;ggQ#+iXmCp_YtpHsl*zKLj$
z5v@zwewA^ld7ow(+1E7$kxOTBvHn>R!Su~`-VL|%wEgGrKPNQr6zINk8>?)WURVw*
z<tlL$A(%WJPlWelmVV(?j^>AlwRm+cJybaJkbKFUk@c;WuO_m;n@zk+i+(xz$6Sxj
zy(dc5A=NDsXpS8H<vm4wmlEW!4>yUW@JRLY{9>yfNqk7r#U(GcX)EK;NOJYB8u8S#
z$KoF?9IBC#&3ho^;Qm$SzAw|GeQ?a+H_L@n^{;Crm9ZZqlNs<Fg_W(zK6H~d(asvT
z^nG5{F22Wc#{NTgtb5Dgjpawr_n3C}tZ@mKlw!=MAdbeq#`ipqYaN!m;r)#FR*UkU
zSbtjP2+I-Bk6P*cJFiS*TU+?aU%R=f`u2b%Pqf+p0KK;zX*F}v!s4y&%;e5RCQfQr
zhD0a#QVey<nv4v#HnBc|O-Cu}b0NK`r)*>V5)R*R{{V#;`LVV0*8xo{2QnMmr9KEH
zxR4}DSo>4qwVLL2jyR;;-44<R>s^kSrbDH|W|@~NKJ`+G&tDN5Ys`~I(Ic^hPcn_i
zpPIAv-C3?w#~Irg{c6?5v@Z~>WEAKRt#kLI3R|mp;<_M@3av*sc4FK!4aJU5YNuYt
zu1vd!HC{AtIyDQNu>7c=h|W5*&^#{?gH1p{4bwi=w<Lsjti3KX6cG-qx3yZDLapsz
zC12mD+4QvI%LI`jke=e3za8oUC%p|Q12vx^MWlQ-GgqPHgIIChW<UjOS~w$?109WL
zRt+FDm2jYnV@kR8#Z{j4D(y~ci(HUv2-0kKHH_;dOr+<~RW(<Mw*@47cB-p##k$nO
z>O=z!K&=!UbQv}Lul6F*97qQlt_f0k?q!%p#IeZ&yU3kok~Nc+b_zvkYF-arEX8+d
z50NL|PwQURP~NdTtjaqx$h8-CobL>bI*e9p5L>NuzAOuGen<=R4wcHY7AL3SUh7so
za%=*$)l3>{h7}@~IOFlD0?o9t#Nfpy%pBIq@eZo05kNe5?^tS8FbTmYsIAy-V{36D
z&i-ol1FcI7jE`H?Ct{NBQ_lf^#*$Nfspbi!80V8!<hQ<_;7bfLNQ3*MKc#dL!~Xyh
z^3IHh(S|8CV&kcM!agIO&hRDDtcuuC#{#`h1Z%Ccqy!9PVAquB7B-5z-ND-3GtGMT
zk8~SKQjy_f9=&NNsYRuNXF#Zo-o>k!@r<vf=`40UJ$G}~yDbw?7m+-|CL0*8KO9#D
z@oQNRVz44IHsh1{8rlgG&l$PBXK7vB6Owv$uWI;fbny6gFc*+I8t{i=sh&^CkIuc*
z;mZF2#W@=h$v|s#LpyJ_&)S1`IXK)u3Wp%)psruUUMc>~f3w?^^YPU7rb*Trt`Ao=
z8@r#qApZcqtIDMDHmNx!?l4baPCqKH+Lhd+=DCo4I#Rh-Jz?iX`|_ywEmhl4vO)7)
z$IrcaTTdX5CTGa^tZhbnocy;E5Z~>QnrVxa_D9yV)F=HVNgkZlckv#UpYreyI|}gT
zx|xPN*T=hNp=RFMW0UmFQ75)Pj5L%y%t`dB&*SYaKI;Cz{d)1TN&XW}2Z}5+)+P9l
zr!PfPJp)!%{{W8k+tk}7y09PK99Nz*vHmKCK*Qz+iviWi;>|5w1+z|jZT|r4Q@`OZ
zjR`T@ryqrI<buQ;Q~ba%Gmm<buFlp^h?j8y5kl1q{{R?IsX?~k!yzE^+uT<vAzu9Z
z)N1Rr@yD$u2-mrjc55nV!?(RYJB`Q`=O9us=QRx370i22BAf;XYO;2S{$csmcW`MS
zXklEAX#yzs%`QbWwknAoyB|t7W4$wWXw5LN;(l68{duI%6o8rlapZgY*GHmwhwSVi
zx@;-oUb(E%!KMeOM<Ps{<8bQTF-aiIY!4h)1E=cO77j4v#=T?5TI_7KOKnCC=-BL3
zo|RF0lF`pz23x5z02!+8KXz)>`2PS(Y?4oUtPc!38u#hz6mU;+nD?ir-lSC}jz<}%
zgdzFsQh}1v{uBX`{V9K)Zf3+kaPd_SU!`0<4O4Cjtm+jJsly7ohow^fA&R*f&1V73
zc{ntNjN*{;D%l8Q{nMUBdhdg7e9amzNo)=Uc^(cu>(Ra+PrFZKCmVR;y!>Q+%bgTn
zr5_nyh~#@<m}l#g)84p&fnD#8?Z9N0Z&t=@g<*r%uLhE*pjW-b2Ojjf6b@<F&32sP
zQT*w^dm0H<>QsGAF$tfRl9aNJth{^D7ffSzPoU<DptB5irN>GG7S1DM^ixv#7dyf=
zw4vLeD~ep`RwBoxC>&Mv(6xDSvre4-Mk;^!MYZ68&Ya2zT)3s}BD#;2nK<Y_N&xl6
zZrON4S-u5?NfLvOc{QaU!@X3K=3T(J@3$tU*QUCU*~#=d3}AJo1CBFYRQ>|LhT=Gl
z<amGL5##i&h<+JGg)`sG+<ySYOT<%MMyX4&=cG_b&)ya3ZSdPnjwdE*n1P%#{{Z!=
zbe{$2vP4YQ;n;t8nvbqPuVW+3iz=R2eQCSU4!rc>SF}UnT@DZe*hToJX_}6eWe|np
zw~a!#_eDq7W6>0-KBtgHYj-eTF4p1xh<U3~=$gEVk*7{RtBUrBZQ~IG<*CT-Dp72N
z9kHm$>59qYUt+z1<2Jq<)o$FZa3o}P^9^c6;2lyy^ISr|?x8i_>5wdU^TsxD*mkXR
z4NS3f=ru(iRde7=%V4b6frA_zMk`w1;mxB)8e5r|kU0zo^sd8LiAAC@2jxAx)$3p$
z-ZO#sMMK2YYjVAmPCY&z=@GBZ6pY@!VW{-43Ta7sEKh0}j&mT+KRWK03fZiiUCXOZ
zol9~JN41+<mB|&*WO@#tAKkQ!f51gn)ik?kt^CEdkL5qzu7m@RZ%V1EBQ=8+?axYu
zIXAghL{_%3n^Yn-0FIcc#kV;KF-D#p?4$Zs-?GX`+A;MMuE6K5qeyi*RFFP`v`+_&
z)G}Ghy2;60F&yWb(KaJ*%`gY+Lm8Q<fNY4`KBlZ#0M>AxxmsJ{Wd)4Bb>u2>-KvJ2
zuIP5wL0?gi<;XPDTUrI|bKWnK=HBTV8DvE1u@4o?nO;$X?0w0upT)YSov9QyQ;9Z^
z#{;OYPs<^W8nSBJjJ>D3$8g7cbm^M!?E_1rN(WuPDeqo&Zc0i4=Xbqya(JfWNwE>6
zLH7(~tz9^|J0VG(W{k2ulP<%RayhLvx0Ha}7}u3S@ds74QmE<p$Div-FT_oDPq{Lv
z^a=%Zye&q|y`)b=)UBOwt>11wwWc88Hs#0Gyh{7T+ODAJWx91M(5oE(0H4CEHnph{
z{{SEJ414CU>XR3?N4ZRGqJ^4Eh*V>{)()MkX!g=fl4=mHPxrgml0Eg*gqFCGiT?m-
ziipbRC7ri-JG#{@A9gQo<a=bkD9|7nZALc#0CSqg)_h%~GRO9LJmy}?NBGy3`HTU<
zKU~vG6Yo^8kwW&&^%eM!rmSkeWR#KW!~AL~ekMYn>U8t<XBFmK&NwE3*d2MzQo_KW
zX(O`#0EK~n71K)uaO`8yuS#U!5cRnS%Oog&*aH>Ej;D$<SL`YF7d(yYzZUB^vH5e|
zhEwP<{HmbVwJo7O-6r2bpYg2C-n5&5&$T~i1<)?psxB^FOV4>O+;r!k)~kKC$e-UN
z?gw(!pDoLIdr9J`w8uHkdDSb;O33L{;?}2C_Iq2%18MTM@9vXX^P|BbjsE!SRCJq%
zO+hvu4tG`ULT@(cw;eD|bm8ktdPvHpG`1itPk+{sx#>&?@uk2by9{hNeQ3w|%^3VB
z{Ar58kIsTKMsO($4A27Oj(MfP9VxqoCjNR+aIqx^lT6*8r5o|>MZkV@N(eOxke-Bo
zeJKpe2PAdJ28*HDla?N|nH?%6F6Ro4f8AWv>0^5*-L##v)8ymxrObt9Gc*%g5qN)A
zmjx_b5B8V}ojfb3o@DZ)!S2;Av=>qGHe=-aQM(n;CxqJ@rPLKqqH|Nn;d>NZ&3QDK
zJr!|K@l@ARy_CBg#&bb+9F`T=E`_A1{{U4ypYO31Y8^XFhn3TpKCIcS-ZBWKMn?_2
zb={T!0B4$d$1DBFBy;E&HRvlWDfca6PxuWy-a4-v6#ELv<5xsiusC@1jZROwV<6A2
z1z3;6I=l6@L>{d5*0t=c2;cIbN@1Epf7US`o2xgCmqb^vM?9Vo)Hn}u0(}l@Rq&c1
z{qCf^c0{dbaz`Z9XCO60##AX$iB)_#rLQvF%>MvRDZ@<BAs_MYEBlu@{&Yzx=ri@j
zL`yYgEJa7urA{lMWq-3_Q{`#VpH0U!{{Zb0fQYQ%j;eq_#(Gmv2C{V~_hzaQ>{<TO
zydQC*9@{D@FRvUQ^p;cp&lMN)sM<gqXgL)e&6Q+&Z-8f#OFuG3W^UwHcOxsNNyT}G
zfbQ^2YU}cyxhB0GnO-nR$UUlRY+XNyjcy#vv`RwyRPQ?~{H>p@Qb@5QKb8drrXa2`
zE0*>;noXCYxI_1yi+w8WE?;tv11(`HxFg!NEhO6N#eQDqwv4Y68LKnL{9S5od{1&u
z9%0?cte|qeb6Y<XZno?3JbO-8kz709&OYfIeJeQDiZzsOZjuXo(y0cy-?!YK<Hyuy
zwDhZKwFwHmtPh}~c&No)nfn`;S<z2gjix|3<G)&$Q}Ddjwyijs{c)P+mLR=4jz1dC
zIM~TvBl@|xFQFgCwAR$%9nZcNvIHa8(yRwPIi&Gye^*8J)leLwllXH;b!h{9h@jPU
zwqi0s{3=-OS-NzrrHheDj8K1S-8c6tHoUub`}q1|ttE?+0A0=KDsiUwWx@RGCyJMH
zy_)Q1G}E}|R{ZKRtizH|<67fQ&tv#g{{XW#^+HFkD>sQNkr=5PF~-r&Yw1?%w+SOI
zcJ`@$zyQcn53OFZhhu||wS`*k$3m15(n+G*T<PWfq%KsCdh;DZ#M)m;2*@3Q73{i6
z^DUJQI{McQ;!Qhds9dj6f&k{Z@R*q?H6geoj$3EWdi^TIcC6<FVAjlbJ?hjpSaJRp
z)htRQkj9R|k5wbs)tL0*pPTXmx)iYEJ9+f05m{rPAB|%yLmw&6$EGh`zk#c9X@R<+
zBi6T)(Fd(b6}SzaMRUs#$72;V{xOf%oOI>sw<foZztWmv9+)+swqvo+Nniq;t|_+m
z+hiXtZpjW87#Tj*N6Omd)%#na*wWJ*Y^&5(p0#K$^xv5`9ldKF*|tcn)3tPHJljrA
zK^-d=?WoT+j>rN=&U^7zQpjWO55l#kwFz|~8P0zSkzpHqepR!s#Ntto&yFw+SW7Xt
zIQsEdpokHHR#p&rtldT{8H;EKN_W`+?OJ|LDW(ygf}`32o^6!zj%kf(F~~KjBFg^&
zT4P1u`cqW}V*>Kk3`dYYwdZ=$I!wq$2U2U*uHYs!w;zbFHSruiTj7RWw{NX|7D-a`
zvpKOV-8t-a6sy7X#Ru<npmndUN1VwC$mXjN^BT2+M^DP2afhNx;0nA`)N@FngT+X_
zX~h7$KN<q&oJT&iqO`FhZR52lTzx3TIB`{B368Z4ql&Obdx23n$UW;hL};c47*>=S
zU^bjqc^GW)D%1=>;Ps_PMibP!{V|`;qL^hp>Oq3J<1{+vCg^=@da=<mB2vZ;EhaxI
zQO{b<6vZEV(xe>I2Pd!PPROkhBe(~(E;#h08K9mj#5fQ0nsr5-8kZo9)3AicbImol
zCx9v4y5Lh=r)r5Jky=56QPi@Gd(>U?Srk}@80V+8B#X7_VQr_M&Yf}rDn(NPVsqb`
zv@*-msYY>DLvi=N3J{qw89;gFqv|?-wDQAer8B>!YLNg>JabBV9<<PYzl}SnBc%-i
zS;l+R57+5dWM9IoFz2YOW{o1qjwu(f6s=7h8pZBeY7>X&nv!9XDzYD#Rgz05YT0Ut
zAp`uHcplV%eQDx=90orccF;TZr9qsUckp(qu&yuxL0;6P^Th@IsIXjM2OVhng9aT%
zF6_|Xcb?VHS~r6(8=jHj#}8t7Kb>euKX_{!!jkW_0CyP&*0!bl{?+-WE<Cm5kE6po
z!4c<*O!G={N#EA6Iz<N}ko2YfXe1NXfD<Nx(~h)#e@adVN&sK!NJt00E^$aY@j!#E
zG>&@;cOJMD6W=+eorF@m(_p$xI({J6Id|ci)ycL2)b_(?ADwm>BaudV=Dj>NZHdFK
zSj$76t`e19WQ?5`NP8Q7(txg4?tzRR`R28_>yBvtbYmUQ<6Kp0%B<YwyEcRr6_CdO
zt9s(N{a;DCmg%I983_Z03&(2g&$k%#qrW+>+y-S+2HS!%#9`xIT1T9XD^TP80)NPV
zjXY@jiymwyz&Jb)@vlVaFbyC*K5F#8)_h0uqmTP8mvew!3sPV|(4-%V{{W3kABMFz
z!Sd2S_qqPH-4Vx9C<ENqQ{pUCyB4y_D9O?^iR@D|%Nrl=rE89~oOGic@OiHmwOLi0
zoVRCmAfUNWxX*e_VAA4`#;`0qe_A;n=86wA08##Uqa8bDgVf@H6R%A1Q(K?jf$LFV
zcBe$eWnA&iR9&6Pp2jzeVZuV#&&|*p=3yB)=bG!hRUeySyNs_n705!^Bfr+aRmvyN
zhl@TtFjlI^N}iQcScx5SewCphs_eT?bDyBEN~A7v!ge#7F7$#wZk2J6VB}}knin6#
z`qwL@bSi~I9y?O10(j@ztTObbfI#=C_Ij1hAVKd^#q!c|)2Gsv0Vfr;HD+f$i(`;7
zahiIJw_ZJJCFh{0sOPRguEcV&@+m8jII42Q4{T=@pu;1rSC9a3I-bU+aJf*GjPoBu
z(=>uS4l2VaED59o1KPQrI~((mG7R*gM?HY4h|fKJ>7yT7T!G9vc^EY+@sCPkjxuTM
z!Q!=oB1G%YdU`Pp{uLN+N^q@=8DdeoK04#lsLL1w>sOm_P){{k`qGjd8A*`triH19
z$)pNT9A>d_Hs&E=NC&?)Gmd-H20L+6$~%gqij@aFF;Nd;Qm-9<ooNzePw$gTykk7m
zMgaDw4x<&SGGw804l(u3K_c_dKJ{P>tw$j2f1M_W7E^T{O(rqVA6k*H38sB{^sJgT
zxW*aHHAYWrmBSwRri0H=aZ_Q6ymiGqA5Qe#_NRe^pVp}o%LoQXKdnfZEPLXkP`i56
zirFA_6jWD>C1}p)!iW70Mt5z<$oiV-B~V!B*15k3HtTcHVaVYB0H0dwCIn|aM_T-k
zH;u7!KA#QzG-tTxnm8V#9V$sd-NiE%=G^H#WLV7k!jp=SSWbE`=4+<%P(MW<LsA%!
zuHE>@PAm0ijc10VbD4`unU6erVW@pBWL{W(Yo_}&WA2<|nm)pW=bZkPKU|TbrE`{B
z2WH0Xnzasy^B=xJ^aJ&-fY`>Io;%c*(EY06ZQ%ngS<4$UvW@~$_obpSt$aAr&asTX
zdgNmQx|<yq&rgJGLBGCzD*ct0*aIOMVtFLf<rzO(<Ex6Cw7IXcg7{HVP$OKS#(Gyd
ze575KKU|+m=wytR=xU|aubvbRB<Kz+j!xw*4t1koPToaA3n@9`x{;%?BX$FN;-+l@
zBm)Yd^~qYzo5dM=S-53Fr9!_s+nVSS&Ex=`+4iSt`cbi591eH_w_%df)-26|k>0ar
zrb1cFm<X(WE7Cq6Xr|KD?=Ao{xY`Ik1$mCE;+th68&HQo#f;YPgFIEO+Y*yQzR~&1
z3>ErTwEf?Cob_)d%M;kH?vmEsrE)kG$6o3WbvcoV$6;C5SN9jP?`aq(WF0>mh&ILN
zAX2MSm?+TY)t8oBj<qAp4ZL1$!-Zdd^@n$=!(_X>#Vy!pJl8F$YnK;~uuAyONXHd1
zS3NvF2322?rLXI+buo$u0wv*>p1)e=Cz}uQu_X2OG|6PfK_Hs0TPHu3D^#p~CLa$P
zQL-G;XWQ_k4n{NEnrLE1Is7TCaB9uVOEY5t;A5`AQl!kIt_4s=EA;wQn~C(Jn3G8^
znE?Y0pIVWjj_UzO&yH|7tj{n610S6NckTZG>Z(&YaTrQ<qiG?tK{NpRKn1@|wXw&&
zWl1g6as><rsjiwEl)8bVn*vOAJ?j?iKqhVFayy#ZGP&`X><qB;@+mBmvE_*-o}xz_
zXY#3%OGW#{5-ND^Ee8sJ0a{%1B#O&yTZ5mbXcl9#)`WL<N4PtB;-`-8$6z6TU#2Rq
zNt7))&z4B3<BDj(#!h`}P+Z$LK)LkID^CkxFH_grt}}Nfp|<StDK5C<rDo55TsG63
z)w|1t5wOlZ5502o%Z6gaj(S(7rD&s%mhGM9ji`B=Gb5b*#ANmBS8kZLmk&aF78TFv
zfHsoM2UDEZ)#v<!?bL!twQP*!tj9#5rb6Aj6IL!FvQ0hOJ-dm?!Rl(P8%&G8I0CAa
zLj;b1p<~c-nwJ}h$+{(VTVhT=VS&234Sw8D9kX-5^sEc0_FO>hGC{~Vt>w8}s9;0X
zaaJRcyo|+g>OSwiQGMG9J*%eI?RH+P5CXX1g{(w`1(qTSAZMDHMA9szla!TMo(RQu
z9vHladn=1+4qGQA_xe{L@G-Y%0DOnmlGf%+TZNJ=52>gv>U7$lhlA<wG#+Ps4@%~5
zEhM*&BK!h7_pbNDx}sm{GuzLVkYsXyl~&aBw4TKrC^&9&{VLpUXUyZHI4?1k({acZ
zI@}e!Oz=LLt6G+v(A=u=f-(TC=Uta4e+~WG&tqN7Qoo%uW4~-v3`;`mlh&PXP`muz
z^$WU?{NvLUnCxunGX1AXR%Q9uJu6ZOj;PQm-0v9y$m@*OCx<2TF5|RDT+4;$iuTVA
z_*&aZu`=vdX$DxH^r}@*h~W#e_LUmj>F}=`w)Lwl`1Pv6l}-l&lg-cgSC2Veov9W#
z(ib6fP#4Fw22wgUY6=M?Af8XstC{9g!4!`9Y?@~A^u-~L7f#p=4t}((uP7uoKN_Vx
z!4q~rDqB54CT)!PU^*H=GU6sAhGyJ5S1EaJvR`8#FgeY2dY_!Iv!E<~mC0DiCC09(
z;BenJdT0&EY@~!Dl>mBG;sPexnnvly4l1;{BMK^nPo;p@gFQ3Wx^o~{#w(fAkcY|Z
zn%UmLaB)Brv*iB(g*Z1AQ*rmHQHu^UNI=cG>S)s#Jt{sBXRp$nk{3AJKo&)^xXEBC
zSycuBrA^fw-3c_nRbWLysa~a~n>393epB_PqhRzVu>5Iqv1m^iBY7PgxS$Um*DluQ
zP?kWs-N+`enXpJbed|i>`KTLq4_x}zJgjq$rl{2#8ho3hAYgNjYi~wf`hqTUcViXH
z*~{h4fNQq!g^$|rjPKDo0MHV4iQ3HNU|7N7Mg}V)>9VXy<cigqJrChnm+n=_!2If2
z$YV}-Gkey~lz(!nc=fD_NLH(MvK2$Mh~kjWm&sr{XVBAT`B38x#~_N&vekkTvvlrH
z0~Muks`mSp!0(*qkkQUxu0H9&9jdmIBY$ZiImh#>I)N%q;hb|+w3q(?iL#!f3}{0-
z_~cFF(yWFZ4?)5As)|&o<DR*tF6!G`p6cGT#4XuXJOyPV?)p|N%mZ!biqV{wY!1Af
zdsbZM5)s@|5SGJqp1!<R<)ZBv9gcpLiEi6S$6DXFIg6(xew4t_jRc4?dG@Q;;ZOnT
zS@5$r%DkGn5Ml4_NG@Ao81Ya^6A^|LC`_+fRwbdJ49u3#7^r1U!=+s*ht5aRqjeZO
z^q^%#EBsi^N&u)>;kf3MJN6WSvAB+%D$S|f-D;ADJ$hA`q}hy628y;Sc*tNd4O2$l
zgPaPr2?*Fd4FD@4^53Oo%buVRYjm#Qaa68i+Z#6A&;|s(c^Neb+>M^qqa-A$II5Dx
z#zDgl^nhYLJh2}&Mu_Y4@8{6;sR_;q1Kdyp9%4t$$*S@`;nTG`WOCmj<a114nBexH
z3T^V{mNE$EtupPHF{mSNo9Ai((hHRT02+F+1HNjqNwibhhBMUtX@PBWdk@B?8%Amc
zRw@p0o+?ea_Ml9gi58`{^!zHgU<L&`ISg&qfg9FyD=7f|Dsg;~NL8DW!4;VUfr1TT
zc&g@WZB1S`AtaBH+v`9bT<Q#))rJV-og4A}YZFDiH+D$H_bI^y^{u$qdX2xSpk>7y
zlXp{9<QN}XwHWy-2@V>7IX@j~>wV$Zm62JZ^<42@RpB;u)^OQhW5s*b%t>)+EF_Pa
zNUs#MhD$#c$!`4?M#FmZT=>m!@;Ae~OzxmKnLTq`vK-)y9xI=Lu<A#zdf##auhPFh
z#4S&Hn94KHy&WlQoZJVcW^2(jx@4O&K2yl;T73sJ)=<Ey83wv=)!iDgs=5(4bH&8-
zpAK6I^)V?Ri1VEK)4W?VJ>+rc<xax8&$C4UW<UmO%{AE!nyl_yCxPu>rDVC1%<-Pm
z*5yae<ESh)ACYx3$?evV^Ry16f%?)Dp60A+@p;;nx*zX`{HyHhOOg&pflfTrQ9VCI
zfI+6hpmVpH(q#+?JrAu#Zyv}{dJ3Aq3CCA;F;l62r{7Y7j1*5l@g|Jc7cFrg`j+?U
zR{Rvsl3WAI{{RWjdkX8XEh4?P@@C!j2CM11OgdT=izJhrl5zUi&`XHbT(#k<tH|Sy
z1CtT$W3iz{80L!j^U@A0&%Ao(8>HGZyNr(9*PxC?dH0XgH<094r<F?Blyc(N?%Bdh
zp_K3sH25L_lFSyaC8M-}uHB=PlUlbH>n5A$AsHQqO8Zzlo)L4y+IO2YXxP~8$s)Y~
z_-5WqfAnjYS#i*uit@cbQMs``Vxu%{cLV8KFXGGLDtR)P-_-XNdY5xwR)!rKL-xXq
z2OEGDkTvZbup1Yj_iLK*E~R&SGWqic-PjJ*out~uJ<tr81CA>7?pL&Dbh_q>{ADrt
zQogIEsNpz0!tq#Fx(qhTvZ9VV)hSBJ7R6=B?Mr^7x{^lxn%$IPjA#Q7TnfR|wfV19
zAj%*;D=64ZK4BOK+N;VP8H0B8r(zvO&WlZUcnQyb^&P`8W(Jv~WZM&r_U5O!Pzffq
zM43|e;-H20+{ga#t2Y=^RYP(+5Nc|CB}3vzrCFR=#(k+J49!q!l6jUf`l^b)i@C5d
zUn5i9n?9Nv#T3>iCje90&PG#_$E|8ZZW=%<W(!pc4%M!C;yFvP#ah`kl8&K)#%oeb
zSBXNNJ?honym4F>P60gu?^WfSb~DMX9alRvN>&r>jpgS*twLkkIW=Kt;}k#4GI=!#
zwYbXo#V=p~09`z-Ar)5wcsZIJe|%S`Ux0izs`<%GSD9IDH;^lI-U&6+c(cTETG>Se
zFz=5aIa6M~Q%+KovF7FtSsqQ}D^nHTR2`i-u19HJ)!yoceO6e?DDsHp9&udur>C`{
z92QW#wlQAx;?vad`HYB;_QpBw&0SO|zjPmZjZAp=^{X(lODd*%upCw_3z|De4Z$}k
zN-)MpYV=<Z_-9JLU$r9dZ0;Cr);^u#OI=e<Un*^v1B~N8rCZYPrtoyHZ76vF<#@#w
z5$XD7iD7MT`?w=g$L0ZXTpx=ejvY!^&~5onIO+a)uD3_=WLk}?n`pt551CI<T%U>_
z=Hlyoh$DPqzMiy8V`v(F74W@;+G||8mT4DuazVv*x^=3<Wh5~Hg%|_d6^G#RAH(s1
zjucl<rwo};^y!*}Szp1>E5mT5juuzx^{y}DHkAxEP+f03T(Dv9{z0zWK!W1R=IA~Y
zw569FF<xEqhgiG0zDqYN<;C*=4`1`mZvq+Q6a2x5=y}Jrd#A(K{{V_|CI^C|yef7C
zG3XB%uX6Z*$A@9(KPdkIKdo$tXJE$=yMG8$YskDqalciQEDs$qUa>L7te;Bp-F=DG
zCBYQgD{`VpLvdE3JF$+Hm!5gWPZZ3*cA(I|F9Q``RYy&vXWE)(BxH(=&H$k?nU^qm
zZO0?&RrWDG59M0!!M}$i+*DhAu~p1Xibf|}cOePlv!I#Z?=C$nfA0)-tgGlmB(eec
zccS944n|LEhGrr@DmAzbjof=vr)Ki^V*;+?C>K3{T4{2Al!rObttVQ|vWFa=`KLyu
zqi*#O8;(2Hg2b`foD6rM3LCbZ)TrgVR5|NYM7$G7XmRP(nvITW%+(P&rce_}oY9_o
z(i55h4Fuwo9<+q>%@+Z4gPv(~?M&%FIG_i5(Vxbe58+Fnr2srNO9bz3`{He<zr8@J
zS?~r;SzS8$hyoMOOq!^Y%^`C4L(Fms$68WAQcpSer`c&&SUdJ1?l)GWcyi;(G8y9o
z8R2tY%_{IvNwbP@Zbl?TIXO6{$O=DP(FiK+q;xo?m~`v-*2`6L9^`=JQsXp{oTo~6
zewC>JM|}PjPEWpS;pA004jUCUHYy}!;l*2w{G%XML)NUqMlo4HsccMnqt=rKmb5Yq
zA8PD=A5XUGNV0e}#^b$o{sfpqt~wqAD6U*oZ%vxge)2nS5$KmXwYsISj6bVaC;tEn
z<5gwe_fW5}Qft%-0Kl9Yvb<vnpFv)297LfWSe<nsrMcvG9s{|&nWB5pHlN^5YibXM
zmg;jY%+H?NfFGrGx?3OZOOcH6(-pCY=oLr3Z7f9lnR_UnZFlhg#@1NCGGUK7Zq>I3
zfV5b!#?ThW@i8K|HMEq$8!6gUo_gl5My~Op&lnXhwC%Y4oJ<4Y-6TZ8boeul4$)BP
zdNrJWaxJ_;k-B3zuB1o7%O0JpA4-g+-P#k*c_+BdN3@gbK2(dTV+xEcXff?sdcCv}
zO>ZCxoxpVOTj2*4m#*6ef+k%3?EX2W7TXzdA&FFA55Q8qQF$^AoDu2XrinboRtm%r
zI#c|<5AOc}J}L%b=<Kn1=ubxJ=~u<T&j64;s)n5#3#*0Ps!7i+`BnCaCoMV;t5r3q
z%>80h=i9c-XB_@Dt-O#r^salvSJsfl2z#hYhQ=}pAB9~0-LMd>k9N4)It<d5h!&=k
zoyh+H?wZNb9}&!?l6Q5dKZrEp8FZh_z~}{X*1kEgu)VlhV3!2oV2m25Ma?@3PTQU6
zIqYhdtQ+h=uVdc1qwzORRVFJL7?1BaAEs)R{{Y0bxwSFd+K8C?^Ze^b;p%oF)Q@w$
zv<2;B@AB29fzB{1$|Lxbtw#!?tZR-qQPQEC;vT%`<(f4I)N}e(EF{>ytWQU_vz0Zu
zi7FMBrhm_^Ym0n+_eCD1g?K&AyQtktWs>E*!gIJWs2^0mbpfvC<I#`!)}K?8>QA;u
zw`%fOMP$YABKb~w=BwH3`V!k9d-dF-pk8am4c)|mhq;lDp=yM%CkLNg)vOxo#qIo$
za+AgW9)NCZz29CxopZBz?@G4S8hEYVMPb;A^5PJj1O)m4ntLP0Ky+l!KvxxU!ohCE
z?WB5?pA@XsPnD+}`<l+a_?<n~yG0GCh@OWT$Ln5sllW2-R~#)gPqmrY$MF+ci8dpm
zr>@Rw2|gfe(q(?qP#@w70sO0!?aAhs998=YeTnvx?rGg?x`o_^Np9q3&Oy#FY8TaS
zpYL4A-&0hD1pM89I=)Eu7c(a}*Ck5*rc8S=sJHyZiOU}J!^rJG>+Md-2Qx0&w&T>`
zcC9r*jOXyIiy}m))YiOM3DlbMF-p@q>ARt0{{UJKOd7SWjoNBS({4Gcc^m%##;<Av
z&C*-g3}Dj3zkLp-$0o#vC(?t~g4yfo(vu(#YuGr&Ii&tnZWyH9+odrJk506dZsL%)
z9A=QmepsTKSdYSxK20lyhZ9GxX@QSS(r)7=x^<<@I}alwkepOyurgZ%)|%5Ilk;Tz
zRCA%IlN0Uu)NbDO7?8ILuE)?WYGt&&n;un_%Y)oTYdKU!#wA&X`0?CTaR)igY{%if
za(-7&WgqRZ1l5TAAFVbw#{^&RxA<3?QQlWNqoOgRZz4r2fK6STsXcRA%iyb$%4XDJ
zTpmCbY5X5xz!`N{&$97XMyDgWGgmpV>z<;6Ai>8$T|9ml(PM19w^Du}RfW>DIK~#q
z-`SkkPuAjP?3u?IKtFg2H|L-&k4|g2NOb7e5$Uk6yDn-}oug1Ah8V#9;!=3T9>ttI
za9mHHCfa8suv)bqjjBj8EL?xQz*k^yu33NAV0s0nIg$SRxBc}{@t#Gh2R9#vbvX`P
zLlXZ0wA|H{@SKhQw^M~b-CX|wTHHvLeKYM(3IOR@JZ!oYsG}J8V#X!RnuL$+sZu71
zqyj&8JD*+Et`Ky^D2!&I;_5!7dl-}xP155(Er~zxxiw}awv1*Q7}MQ_PGdfwjWj1U
zo3A(2J(PP76G)_NL|>xPJ;ll7%lIuS=bn_O9Xk6|`$osgkq~EgJKdY=c%xtkAfL{q
z$WhSLQb>xqE~DzyUg2Qr%?i7@2CL0`Z4!<55iWgS6;-wEJ|aV2AjfRe3mW(*t7exO
ztO-0>rlBEj3lZq1qF)q2C?z72PH~WG9Fp9n8=WTAE0B5grWH^*BiF5S&#yZSBp`iS
zqB_;nbX8IHtllChwMnz1EP&%6QU?0hF#3(`gXW!ZeG~&xwD&GPX{5*d#}%8!M6Y1Z
zmPrr~zPbMZdZ3cx1zfa>KN{y)JfD4urujJNrlI1B_6ED^5H5aTY6jHMV;JYsv&=;D
zdHgB9R&&Kq)>%r5E}c|ogeH|PrMNp$KRVA4uwVuSZfREFvgg0OWm6R>tCp#vq_*0M
zlFJ?tcLK7_<mluxb6%U|EycFpq>ORJdCsY5ZS^OQ93FF7VexLOcPrT>Z+J&qO*Qw=
zm)*-_t$MD9;_EG37@&=n)3b{3yKTtZM@s8F6DUnuWDkRYde?ks%vZ2p&CK=#s3z<c
zVffaKrM<n>CRe$Q0PVO}pWoT)4Kqr*kr5yHW(O6=T;H2LZYy(e(KLsb5|N*+R);>l
z4_&#rSlPD89>9L~b6i)7yiI**$hNa=K-eWZVu#c8>DD=>xZXz~891yD6lyjsBDRKj
z+CYBlb6M5WIvsd8bJVnvkEr?g()qJFk-F!pswTvN(z+XaaWpE&9VyLbGq~s4yoZRh
zv9(AgCUYNU!TW}~Eev^AF&>#=QCwP;JpOe(pz_L**o;;+s&mAYj@IS{xYJx8;`J5f
z^4UChQmM!x&tI*2m4u>8bq5EIYm?NhJiS6rpf?~BT)0}iiK47?>14!n$JVUHWVq!1
zRjD1Z$4vXxsI5RFJl4{##bZ4zK_egq6>2LCjEo;~T8VFl1g<{{ogv3g^^B{E#!Pk?
z&&$WHPL?X^j4`ccgkqeLC~C>pkXXqUC<x>7rwc>}rfXEh0qMms#qCn6u(6RXs0;T1
z_Z40^_L1JUC5tM0^He;n9`#)J8MUIzuw%ESL*i>ib`tI65KShTAc|_$)S(kvo;k;@
zW6jGep`3(P;kt^o916G?=z7(N<L0MW)Ybb@SVV*68L5^XqoApxT%|lNDjh))EPs_a
zNAvcng5$LzTrj9?1Iq)_n(^Rtt08iL<E=G@D7aXn$OmfAkuf0#wcRuRHJ>_u^!2NZ
zfP@?Y#co*5`>;K+Se*J*>p3=_PZdvLjnpB<&f$zyNf-mAU%XE_Lt{Pa1XGTcnve@`
z7~DbU-lq}rX^=1PD#>4)oP7ljRuK?Gibh{Snx7f=q}#`T!l#^8D}*@4DH%Id>IQi@
zrm_+{esxMfXU`EJ;{))oJ@Hfr4tC=?9M`7GnN$8X!g#9NF*wM{&*%O{dwD%eRz@||
z;LkbgIQ?h`2ik$k`%+ikBgtgS-!By$pE1u$6dYrvE(u<0gfT~RQm#XBQ4S4ADxwUV
zuca8pIaevtn~rN#NTaPN#%Vfr{U`>VggEriN?|?oQXZ6nNj~*00%a)|4N^pYTAq7+
zL%SKMAn)F>T1cY8$a|7%Qrp+R)~gS5Q$!iEstaeeb>8tHfw*ER2jNps3&7!B2;4F$
zn5>Y*6($BfO*0rY<*P)F1M;BsqdA}ou?dd-Dn<LbsPbv+(wGhcj8cw8I3YQt&=jTn
z$3Lw{oK=aV!6O2ylf_{pL`sd?q-HFYT}}@}RwKg<cJ`)#XeOpZo;v2D+lI&Ur>_n4
zrY2iMnD9r<nu|Cz_<rUojlr!GAW+{mF6{k1MMem~<39B!K@`}A)n{BBb5^iV6$GnL
z(MYP?W13;$)Q&16_*XpDjZpPGRhXMO7#~`yoYjbdG6BX7X#!ZJeB2s(si(YUTkA>(
z%T;1-Dx4g5_NVdRG=L0xQ?bS~nxPC}F-<r%AYSwlfzRthKtWD9+d&vO$j5$Zz;57m
ztf#SYXJz3DfkX_%al+S4Faf*QAK@tgn2cu)U3}v|HGXfJLzfpL=x}cI(Fr-DBifLF
zI#Q3It^=@D;*&X}9MhKsb)W{|ib{}<DUJYcpy#~^1fw+N2o7AIz)}+#&eDGxViSyY
z7^65e<tP;H&V4C=c27AUg##n%X-i;WQ=BgEmo%L@pazD|KxjSqr)NC-Q9uX>f6|w=
z9=^199MTvLD9(7z0Dd$cXaFM}X(*+}C;>a4T3m5SM;?>_zl9%#9XnEklhT0*dQte&
zfk}+!fESF8w0|l<Flm0A&;lGDoKT#&$27En@+cG7t>PiSNtY{@+uFF8&&&wNHRu|;
z`I<{(vXfqa7zKd_zf0ljm%~K)JkmCqZ1u)!HeNV9`&5ClxXvl8GvAu}MtI4UnQ%EZ
zA5Of~?x1$4k6x9Gk+fMGU<}lKa0h<%GY&od>L4<4o@*&1WW^%`tqMkI53i*IuQ>c@
zh)A@&u5b-GI`zgqDY2ZbJ!`5bGbaP(7(Hq?1Dx|xrz!7EewgFmil&H9Qllu%G!ODB
zSMQ388T71Vjgt|Vf^mvq81GUX<Fzo3M?BONAJUu+H`1KFeX&ggCR}aJJ#)n|27mhW
z{{XFOjAU8H7oZhghi;WBg(`c~TygDGLMt+^bCa5nXdd+|ijS|QX3?@^SaDJQ8L5~Z
zyb6f+^{8c_9^Gl`N3Aq;rvs0r2uzq@(}xG4rX@TQ0phhrY?(;Up`;*_?@mmQ#)tkc
z!`i8mnN~rA#tlc0OjNS-+M;2TSu|}HBXsC0KAdKy$II8A)fpHk{AvqBm#;siJRa1+
zl5tMXKC~e+bUakResx_B2dOn+0D5=zr!9zEoqvPn&h+RJ{{W?SGj%<=;MWh~2i<WX
z3IWbo`{Ro49}SWGBy|<}PJFp>Z2D{)y);mmfA#T91M#V47(Hqsk&rW9Db{ey2R|=L
zmMdmqkSY(}?>rFRo$Asz*yG&flZ@j%YxH?L9)24R>ra&qHo_tM*2i)wl3d3c{EL!$
z8mTqQ&c%l1%|cj{oaV4~52wTB^y#H_sVtK;nadt~R`-Lg1<t1?;ghq2T-iB3)z|n6
zbX`s2BxJA3$MK>L^3=R!Ek*K|Z!O*_-CKqP@G1bjbCF$L=7D)UvRpF<Kf<a8F<4XE
zGza&9C)Ts68#BU$)R9BW8OLg=b#7I|qhUeLYgk*7aj@ijQvH>if`G4j$C%TRGo8Ni
z47O;XMjVc~?@-0#C)@t3@yAN&8$^O}kU_^`&ML${6t-Ylp(T1}ZYegIJd%#g<R$TB
z_aLHYEyvu&S+;{x)Zy8glppVUS7~eEXv=N4vt~UxAN^|6Zx3EuqT<_*nLJ{IpF|pc
zrg9o@h9H5r&zT=N=e2Z@F5DvE3}69WC5MFGXw~PKsXxL6SH01uvbYF<K3nA{(zH~k
zEx}fT(1JTD{?5{(Zc$u*r>owO@derx;}z&vx`*~oj8^A{W%&jx%5QZz=Um36S&z=H
zITT8oiRfkSQ<eE{QEB9vw>y>{vrR4TYBuAgG_g_bNcy-%C7|aj#Bognx2;9goO)A%
z>5>IALD)Itr6J(;6cf*_Ga3H?^-~ZMa(idBH_RaM&{CeFn8%uuMczkxdO0GY1bb7|
z{M=D-7wz9`0^Ko>$BK_pwTOW2&N|a0eWRcvth)&<T(>2AR?uggnqk#iFS(Fni+A@$
zF4)xY1xGF2vbo57`z~s^)NS*D8y~H7CVV8|)3YvyKy$EDgo~a4tl_CZIwYID0@H@3
ztWWNlPI0#!)43Kjgs7{zsx{OQ$cTrW)@-_%Acaz_I}uP>2Ya+_t+%doz^kXMk|pSk
zjY?Ky*X7T8#ke?jZb<5De)c@t0l~@dT;zu`I1Tw4_2iC7orZ#Oq2ruqgIm|k1)M&D
zurwwMqOUpUBDXIv&_UnUw2#7!r@1Y>WVt!ORn11qMZ08mHEs;7GUF!;)Kps=>_`}3
zvFIt8vlj7x(qkCL271(%Q~5Uwmi{5qoqnKS?f&e2O;Anopf8N)nqYNW)v7hj53~~N
zTz&Pig8ET{H+ollF-wg$(nTPED+5upEvX%VZ7cVWtpmM|ZDJ2=ENxkh1|koho|Un&
zpq5yeu^^B^<WvIRb)1U5yW*jvNV1-tc=mH<G88vbYq-!aqtq;Bibn;PkSl_g-xkd4
zpO@06(=Vsf?t`NZthi<ANoZ7+&aYIn{p2o#q34R_uWZq;=FUdkkH)(VHu61E)xzg;
z^XyNhWZl5as4;LbdsVe_D7PIM#+cb<d>s7^R$P@iJm$A0wq5e=JqhjiYa&R>E4DZu
zm4ua!r0!nu{lnW|th;$e4ZE)bzL3#18+}hkh@`nYbM>#7EUrzo=*ykC`GEAVOVD+B
zEu&SARzP}JCLvxoHl}(7%${7#ySx5X0l3IK)-vh_X3H_$JD&9OcelCCdF<%1w6fy>
z^V*pt*l$lt&w}+sVU(YG(H0Y2$Cy&2b{Y1Ju5-;)n&<#Sa68d0rR*+4!2EH?CaX_n
zcPaw05J=A>IHUwK-YHg4+0PiRe&bM*+UcGbz|T|7Ya1(t7?B8S#MEpy?kKn;o_%N;
zXHoHG&)A4iS$5$1)E*DIeM3-bn0Fi=)y~T+M20pBbJ$lw;CUm8?YB3}oR7wu5#CC<
z?Zq+5qScF#n-rr4thrdpCf=f`My;XRp!cha?Cpb9Y@#AH9V+rFr%X@-)p_SNAdoL=
zi+8;^b)*CGTed3HBWmWWq4~J00PYy3B2xSu8m%jwa%y5QIjCI~fuINzB;`osn)5Fl
z>aTrvZ9>XCv)iGsM&4ta+PN)m$`9=aVS~S|Or^@MT{v?}$Cb(%8|GfUs)fvI$1B5E
zq}*s0*AZZRr`oxVN5gj(s?W5`804H(D#@KPqS3|)3^V1rbj^ClgTlq7d8A`^e_Hcd
zwBI&mOr4v)Y*(x4aIL111S_AqD^&D3D<>TpYDs=#eJdjT<+JP7v>XDh>sZ&0Rh!e+
zq`?$rIFO9wRQAUR!=+bZ4`WkX<$E4!lv`L5b;EO!iW=T)Z<;9>{{XyrH7&Wv9qPoH
z8Rn3TE1So0`@w_WjUcOPs#iG(O&9Qt7UGk`*c!BioR2RU6am$5F~zx09dS+GdLK;E
zCSCE)4;ZO7ZCsv5aYF$ah#4c0D;oAw=46k($*pNVxgOo?A5eTd58)jR09S@$Wb2P}
zT}GQIAOq64<bAFQuB%L7&><bV&?9M3D}uSL1puz#e;T5=$5B&TN_Ul^jJSl38}p|>
z1Bw{#P*<%vl;fHJsOZDys2xr>RjE+ta3>y>T5xb^0<$L=9cdO%&Y2_aUcCJ&sM%m~
z%^{Nc{Nt&oE2}U8s<zReN+Wzpx1pd7c+T!PtB7-hn#qnrPE_=(_V)uAZV$BpX~h2k
zC>Z={@<tg66-j60cdM#Pr`CWoCXZ`#ftsmxZLzllkZVfrGq)gQilZ*#0V5co4C5IJ
zX^|YZ3CSI5#J@4fsF^UqhX#-hb!B1cRi<5xNI52~G5ji|#IpR|yU+%G!xNucrZc*<
zB?R=W>4_3#8UVE$ZX_O`TDAZRJ#(7RibW_n8?ntyvTt4+6v3KHAO|CwnLc83_*Ezl
zKyJRdtBMN@iU|-7LmmxIqbr=|qAJWVNX<zf`o6RQG%iuF4}8<LyMMOWq>YByeL9MP
z3vT(l)|@J`*~*8UsoS5W0A}fD%a3S0R_r4r9OAi~X<iwQR|h_|y=^A=`J^*p7!|0d
zJ83PC$?f!~OgB>k7{*_op7rNGCDPKz#c|H7fj2qrUXB-@I@dkpJ5BcXS0N5#ep}FV
ztgEZjk}i|9(UB1<%aL6Ja~cvmRtlUj$>dh{b8eaIiv0H!tt04Zjq6E82a4r71GOKW
z8Ka=>Kn;@yHsiH<UbUa?D~>bsSE{!t!@euayh58bd9ryRabI)6QvU#GoP3WHI$ya=
z$2?Y_hS4O~ViI702>{k%$Tc;U%URyVa)%7375YXlo1F<pJyG*mX(-i;ea~T!g#`YT
z`lqMfM}1`#!eb0N3b|i|VyQ}%SwdT*?_kqcLW4ynd8O@KrH6Vu&<`{k08V>X72~T{
zo?CMtBp>ju+PQxhN#qD-Jptrbep@SIB6H$@hR!nEOuL#Ue5!@&D>DA(YfE=ctU*6E
zJ6BM;!lWA`TxYqeX8sr%jPM3S{?2ReDC&3*b00_5p%87j8C~3NIQ%N+yQo7op!+f^
zZBlRzbNYqFyq8XGQ)FkA1Nqe_o<>p&R@N2B9!F-&wn+7@Zw;$9sn;Jb_*O|g@+)t{
zu8XKf0RaC17dbTE!$)VSMy+bVf%kGN&Tb@RxNxL=yjQ1cDVsJt@xZS%zKPoMMT~MA
zkZD9xBNtO`!9SHk%v(JV)`AFZHUShWZakWz4b2h1(a7t~T(}FrkIJ+3f08D^?^fn~
zob;<hDoq~lImfkUv_)j;--^@Vw|~l#L@LMkZhzo3q^>i2K${lZ9l6H>x)=x!4?$dZ
zlRuR(SIUFj^sc5Uh6x=j=Q9j5gt?bf-oe&VjhWHgz>HOwp{vulj^6{VW9hnrDhQvC
zMm28cc4fwLwct(?=hW{rt{Ab;N~Ha2^rPh_sxp(DS5zK?WJ{20VA&NOF-g0xTDPer
zjMx;ybI(d?Cp{^J{{RZ8#^P?pt0yaRkBoqMt&M$@=+3}oGSwY6$jSqT$n>lF&&#B`
z@%L-%a>^dcD(8WYtL-JB%;^zE_MpBF>~%Dn?Tj*M%ufff6^{km!oflOJt?=kgt815
zJ4YB5+lf}2JoJuOAS^*A-yBzUplN!2{kjBI4x^u~apK+PmCBB%rEO@Y=FZ?WJU2tl
zax#xq(DbnaZvX;2n!Tv#)|!}8aT2j!joz?yT}JX_g!`;Hu7)qP;1-ccJ+acM2-nlB
zZQzYOxPp}x%6QH!ULnEfjQ(}mSw3MIu2aVV2aWp!`Q%cT#?UNy8co_rL+DBUE3mNn
zq;(u-xUT|88pX#<1IOk60N1Y4#Ny$rBv}rPGrp&Ejr=+5UP<v%%JSo01`B7DZS7vA
zr#3a4;2R7`tPN&IlIhE~aqC?)%;tCmnr5K9HI2afrF&<?^drOZj{AF$rBt21Q^!9_
z)$p{ttlK#D$EW!fv6;|ZgZ5cImE)S*=Tw`q2N<tmxncH6bDz6jH>wXiRGV-2sAF51
z{2qp$h)Lq6dq;*pF!DXB6_|SFvNR_#0=XumF(@SUr+MEfs9nC40IYC0?N#1=y>Uv<
zfI;NdSvfsvp%G80#)SObj<rhS{5Ts<>XLg{q;5uPfhhwpY<2BSLM(_$+%fo5XS>Sm
z#Wn6!slp1VShG+T9?lr_6w-O^NtzEdfRX|PgFPziNUa+vIpY<aG7lAI+vm*ySLoq+
zB=+xCNGh1CR@a8lD5|ZVq}6%k-t5PW(;6XeDl<-I2APpS#3F;~K{=%BNOuFxCw^%3
zq&;X5r;e1IfBLA;wH+t`Jv}HiXP%T(0!SDv@srBty9nDcFF75Jak23#@!q=IW-n}}
zfinDD;DPO1(XX3kz;_0)Eyn;>{hJRb8S7OSshc>9sDxLN1zdB<s?&14t4C5zm(qLI
zbfgjMUi5whaleRI&&nzP09@2?<j2<)Aw4?Q$cBLNRVLx8-x;dY{r=Rau;aN2;-`o1
ziiC`gDoCpsZfQM>KJ)-6RnJlR)4;&3jBYdzaa%qYQkv{<g5NJn$puH@TmB7HxbY-$
z^!YRT*ES>IWz+bP>Gt}>Ge{!YwTDtoZlu=Ap^e0A-|ur#U1;!sXSqa7?aoJ9@f}L`
z;@<jr(rE&#9t)cCu=Ks7wa(g;<ySpQEmumk)}}Jw#Dt7>;<R7H+7xS(sYQ=tUK1tE
zk`JBPyX2l~GbVq$e;V%kn(lM^ZzI?>uNdf!Y`#>cY&Li`1YZ&~Sm9OjWhHv{uO;3-
zv=-@A^;i?_WO}UM6SVX{y0UEhwPHu{8Q{E@XzZgZ-Hvly5n^d~XPTvkriJY!dJMl5
zug(NEv7-8w>H5}Qq2v8mQC+*%EOa1OBwHh;AvqM)3TvRfq`RFk@z;nJFox-H1~LXe
zr9nT7wVBV&eB&b+T;uuH2R~X}#;H<=VCI){+0-tCts>7NvF;f2QMKjE{rj0%d$m^1
zXa^r!t0Wg@rk!}HAx2Hdv!1o0(um~9MJLx4ho)?j_^Y-RS2b#T_@j}dA2!y;<HdP+
z&1a$4OJhgQV5F!y#w!+fkV*T%K_vC>Q^Tn*nw!VTpO}u-XI#0rmMFw34l(mlgQ?3a
z3bbyFjpsd2G@H*n(+gzLoL8-Lj>ETcNKFEhITXNlayaQrk}0InSPp0dqwwC7W2&(i
zk-0g>Rk2=+XYi**)NRAt%`^@@^Ze`2JRfpmzEm9;=LWskLbyR~oZyZt%B@mrPR!mA
zPjk-?f`8#3)fau*+;NS*SW{f@jgeAhP>X<lE6{bTmzP;$c~RQD`^Nclq#gksX;7%$
zO-q~-j)xddDKZ<qF`S<C-N)0K^*PbZ(Jd)84s+>98z!GR6^TisKT3=mGtU%r4#UGz
zmgA_X$i*Rb7##irmoQkhY=3?QZA7_FD+b&#m=#G5JMFFLK>&R@HRfXeE1fizkT4^Y
zT0{wS*HAgyYKa`yt%M?bVvPH8I@dip^2+7OT^vDN9C}j;#(gWLe-B!j95wS3yY8ys
z)X``fQjeKtlj>{H`rS3u=k`+Ua%8S~IHVFGI0TdE1$PkXT1+G4umpd!<kf^|AwRja
zg$Mh!4;v1JDiSy-(d0OeCvW%-TaQN6=l=j#VJYXM3}U-qwcG>2jX&L5KGQkm%HPVe
zmOHX7Vf@ZjJSnWO1)z>G-+PQzl<;NKW6iy{kJ(0RdEJ<TT>f;!v=Vxn$>Szkpp3Qf
zd<bzisLlT5c&Qh|8ZtIsYl)Bh*sTEIb{~}?ZhO{m6H)aav55>?E`<{h^agx)XC|!(
z^yq)pX|RL-?MJ(hdQ8@Cte;Z7oKazKT}~o~1pfelQ`=CwBOYJ_*i~RYxTl8z5ssbe
zd7B-OG}jN$oWh}ZX8X=f4K^F5KD84%pW`1)(g4V$E~BkN*APa2X;6Q>YP`C(n;+l1
zk3P&OuowK!Dl**GOZbmWQU1K2V5X}-i!9eWBc1;M04dlGgCrknkaVt1yj(MsvpN3&
zX{rbDb>RdgF{iy28QUlr<0R6t00Y{%HSrdyD+T*PqW=K0l$TnC`=`rwAoan;YwRTB
z%r0ZS5~yBS4_um#OXwr}^F{~z!o0#undNM}^0(FMB1t^t{Y_=aQR$DbX|T2$@;*Cm
z2CF}dbhJ4VvGx_`gC2wOr)~OC?84`9FO96g{oE3`s*-rzF*_|7dy`z2+)x&)*^1{w
zCycMjK2jnNdaWmlHD^ET(S3r}K|_;_Qf)N(0_Ev7twut3UA7Nlz^bO|<;mYXr$6l)
zk7rsj%~F7_U$s)}xSX8llbU7RSs;#0I?1pxR&En=WOlCiO*k3fQy{Jh=qpQ31<pT}
zQ)KU2`W$=9t}}yPJ}GiS=S4TEdK+hDtC4B!#D6N#wY2O;D^d$}+&KKJ!l_=zWMX2C
zFpfwyBI%>kis*%^oUt7JX$`UTu5YY1Y07i|0NLyG{3+jI1GR4bo|<j`UV|c^wqvn?
z)|*d2MMCz!?AJih1I<;E5$Re+psZs3pDZ}Q`c}rD5EwNPho(AJ>vakTr7E+!5wU5|
z4&K$uc&gL=H5>!S8LpZJ+lry$cucm4;DPf3YYa4;YS`24oSZNWd(?AFJ*=K>yoDrQ
z;<X`!ao;|bpM0BSV8e>_=*isZ!&*tirv4+=Wl|pYL7u|1rY$>fm6_lB#Pd@au*7u~
zZ1%3Jm+Vp^-!pybWFUXFQro^C=3;&O(YKma`CJ}xQuQ^b9!GQ0bYLa1UNA*oczDfI
z@T5<1WsI&cG0ktjpCIFUXX{=iOg&zAWO3D+=4J)tUm&WnuG7-DZmkB!4LnQ7cB%<z
zi}$Y}{{X(~zOPlUgwNVU*V3l~HRO8cq0~fE&K(#t4&tJ<lGfQaz1(Bmo+{MZhL~5I
zut@&ulUTe3U$TSRM5>W-QY>IN$nQ$G+G+cfNci+aN_9IWP9eEt=oD4QFT_5Cy6{~~
zYaSOqwJ?jnYNWc%c*1G7PwqgaI>f~Mnp<)G=Ic-UD!V1(AYWADntG-i0<+GoepBSr
zqK&`WIUl7T+8VZUu-Sv2K2!cRYbUDull7RIO&RV#N{N%yei*8MY}Q<I_Q~oNEdKyn
zV+~$LB;RcwixP^s<g@D{ezOwHu`nE|ABAQz;p)s0UZb(Nx-)aY+l*5#1{~yKy!!Ze
zLVS$g66RMM1B8`NYTb>@uyyQfoeVNL&1+iDa0Yu<EaGTa5$%xr`c$DXxWzt2#JSFQ
zdQ-yIBOd_Vy!NRA3T?M>(xuzY1c|ngt|{V>{n~dCB7kBZw2Y+m6zIpv)}4+iTnet7
zR(;yw=QXV0<BFkm4)o%#3=FoD9`!w}o1Yb0NXicNExE&1$PG-EO}&7{H5b!7)Rx3E
zls#%mV)Eqn^{#1YB8Eru$T$^jkCv+ef(aF9a)XgWVi}4y@zR~QiZOvmM1RNHk;Xs$
zRQ4EQK^YuVxQeq3sRSD2d`}3H8Cx72u^*jwj=3DyH?Kq*-a-Dub6%cXK3dTtqP$NW
zejNIqX$L;lHR5f$lK>6JbwC(qzek40j>{1sC~1ed^fZyaIsGUsOA%IyBgf2X!>_$4
z88q@ZszM|}e7<Q2q+ayB`c{aL&S)o|Iix>@8PBCKAD%g-2NfO$I6Tlv#~Auh1;m*Q
zO&jumhO^iNn1Rxtxcbyj_l034W-;S~Q`^bq%#EIhwLlNOJxB+Wk9=0qdI^{BRLCQ5
zz4+B{B<<<=R{h1Tta@LY8fEYf<5}B=JxwTTgl6sF@rp(3SLBUcW~rF=u@z`Td-eP%
zJkp*GH#qv!5M!Eh@zR=2DmD*lU_DPFtwK4$Kb=(!b5g6ak;xv^z-`)<Wx&pAl!NBR
zD*V8>3^SivqU(;iHI$K2A><mKHrhb_Y9rUCDn-W8!Kp<Ou*(zHoENTX(elB1Rk3fC
z%~gnOh8}~dC)ScqxfMF8MhAgWOTgo$XoNyI116LlA9@MF{<MJPb)kVOa!zR;GI;`)
zGlR}6M%p1fB!3nvSQrv6-+F<oLh=tKy5}bXs4zLKDkD_IN|&Gi098V`2en#Mc8@y_
zJ!wIMC5}z%H+?E_gB4CMl#0-ZZeF#%=451h(srv476)PPP~!)$Gyxt!6vFxMPGg?c
z8;o}%m<JtkPafH*f%m7O;<J(|9S4S`+k3Q(Wa7KYcue&6uR75f$9lgnQ(lhz#tG|=
zmHGC24qR3Hp6&uyfnR8(00WXJ{3!)^$D~S|bMpa;NlFqnj2dX^NsRhXA-!lLr8o}s
z5zl%q789tX?ZrEqLx6ZZ8ekkzfuBkRFBE`GWKn_ippLX=m;s|a(&rs|Q*l5BF-Ct1
zaL1uEho?b62o6mGotiq(19?95r>8s$rFW>Mu5vgW98qhi!*~9zf$m3o>H4i+Pif1c
zKGHYkxpS{-0l~?m9*6R!BX1SVSb%<Xqw}B+PZVH-%>V<XDC<j#P$>Z3hJ((1DcI(M
zIqQl6j3%3sIvSU1{uG5r)`Y~z+>QEcfsB<k=Vg4U*)h<Z=Di)cvth<CYtHVF$9pjU
z0BqOj95GV#E!g>-+BRvHk-l6Wo`RUm&rUt)jDWP`*S&p-^W8`!7#TGNJLas(_i$J7
zs>J$Maz>F5i~~^o+4T3T2at16FaZ13Gd75X@N-GrdQy@wDGoEnDp5?aA5JP!_i6~S
zikJEK#dO5NMVQV<Uft<ilTC+}#Vc?)>slFgAYp^oCZonpNZo2P#%n1fR3RA^8NjJ~
zR7^2Y(P&I_*R42X)|<vDz)~4Be)S;h>rlop1xucJtx=4N5&ha@cj-=ug1F?+>yE;x
z&#7JhwGqjwnxa2URJ3go3h|nVj2e*S3Ss-zn=J^VCp79#ly{*4G85@f9Mn;qcc}*r
zS|d3VMhWBj)0?F-Gsgy=!;BiEG6ozGP?67CnohlH9yfnF&PLG?uN>55cBzlOL`e0?
zs5Ah3Q-w4hdV@+hpb4Yx)}|ciy+EF$ik*2p8gF7cohO9cuA<4;AangIzi*l~_1pbx
z&U`g4-9#b&CCSg$y%=Z7PhGY7e-cL6qv)^>^pQ?c$>e=15!S3sJMryRfgF>H`P01S
zR_ew=OeAG_1Q2T)dBmq6=N-*Tbeml{3q*F7>Ivehwi_H*=o6LCLo1+^d4$aw`AHO|
zK<U%oml+kA?j$0TPATyli)q$-cVv-1=@gNu&1z}Z65d@$3SbsJd;S#B6(YG^&s6X>
zr+=wfsktK?M#4uuIn8e!0y*_lb#U2@mm3F9twX0mx+adO=Oiy&cB>j5rzWB$EEp(1
zAtQn-qjjnARiwS6aoBC=hhdeJ+x&z0fvcAO9I%Qp=0qL4mNg00W=&jM3uZAN<MgW<
zo!pRFJErbE25NaD*vp<>$)K>Z3`B6oG3!<)vbUBUj*E{`#dF>tX{44*nO(?k2H}d;
z)otgzvoYJsV{G*taZi;8Gkr^Tc92>}wj@xezj`jO?XA~q5uW3{L1-j~(m3RD>;?%n
zi>m3DcUQ_&9$SAFe(eG}YkA|I6_OSO7-u4xaXq>+`LZIOpqhrp53}1Wf87|YpAzYo
z(psCT8*Gt-wC0m`E}VI!qH<plby((+ZP4&L*PE3<*uVt)RlP#x=D1@cvoIuNoYf-0
z;O4oTx%XHK9?Fu4?Co54s2PhMc%^pF8PC#?06P*X9*P%k-~PQhNXS2>H$3#EU&ffn
zbQGONJ5uyLDTL<~2uA6Oix~jttv$E^ij2}FfEeJ@gAC(1rhX!n9-Th4fS4V_4b#%C
z+Q^K^jJc{Y<brtOtw7sY90OMtOykWP8M=ktwVl~nBI}Z)6<It(V7q^GGB_=^toV}L
zOKz7NFc&IF>+M{rO}%)*t<$;j8HOL(RcPv?@g<y!e7IUcoNznWaii%ed1Lm8Q9_<T
z#c=)@@OGiAx11zMqdbGRIUfF%=~CHVXgW!bNlT5JK`V}F-16DN-Pl0)(=ZqThyxud
z(b=qIU;&D@4(z)gSm&iVK<m=FaO(3$6*P%TR5C~vdapcJBPxjQCCSgsd;8a7ud~gS
zx#Jwy9eahibMIcnj#xcTv%?G|(!%m^*yg$!({o!VJo|L6U&3;2xAM*pIU~1P>}Fl>
zZb8NeAR4u?l>Q>X`7NA*obgSPPxVWT3}Y2)*2nE}>~|5X9`z=#VwRV1B4n=KwLHr9
zBF}T3kZ-@ZVgXeZLh3v~di>lP(IgbOesPiwQ@+oY7CZV?fvu%oqiOI!&9$RA0M@Rh
zZT^vN;df<v*B+Dk2Xm4XbHJ|lNfLc3)^uecV3K-bmBE}<<*{4&d*`vN=n!nUPI&KK
zzM-YY+JtfepD{S%xk+ryS98XIge3K&ai(P$huEfE`_^Q!GTVs;4>h$H&m7_UvBoN!
zMn1zJQH*q{v8rTRPNw!3OUd%tPDf!~3^JwMW<~0~E0C2j4p;lau4x*BT3+Du6OWi0
zr0gjxmgI?r&Bk~q(y*E$ZJd=Wj@8o^7gEb20fWfTTEUfglw%}y9`sH(6eVL3&ehL6
zS4rWUr;&sOi(qaU<mS2gm*mL7tsf8Ev^O4RGlN{*sopH;jIF8P3zD1`D#C+%w4a>*
zHI*&jnA~vHS?6V791)(G?_OP6P7Lj*H6(7uti8OM!mt&$W$_^_(Gl&5Q<0AU09y0u
zE*Xzr1uzZWPJXq{%@0-|6tvkt)<WR+`D!_SB<VcuQ~6hzeU~8RjYljhs(wJ<T0%Vr
z^T+yZpzT#GN3Ls>zwumGJG_)-z~>{aU`rS$p!!vLW1s}R)R~EIKu!SWx^Ducmj`o>
zS+kC~7_Kg0N|EY1*J0pmpD92DlD)H3gnA^h7@`BAsBKS~ILAtYdAE%5Ry54{neCdP
z9UKZ(2VqYqnuQp#7|uFXg&YrB07YEXs<;@Yf%w#bQUUANj%vy-(UVZbr#z3&rD90p
zn1p#bJk@t*Cypt`HzznEqLqwifPS=qjzSR$VV*0F)Mqbv+;Lr0u6DNL+PIs?-*n{q
z`qovpI&j|+GB--JgLfFn^fjLo9s%iE5HQbd4_f3sA{&nm*xk68qKOxiO_$|gm$z!x
z$Pk}Qb*x#Kf^sXam%@2i&xnbe3Ul7E?>KIpR-~*eF7cF{;<QH@K#(}*r;GwPHBF8i
zv8ynigY}@JRvn>3a4L2q$t3fWS<%U~fP3~8E67+J905QX_v8d`T3-zO_qPs7;BC)p
ziuCc<In7`2+!?f%Q=GS2VmDSjr;L7d;=~SdpGsjHbI;0s=|J6_o_%ph2w8w!epswa
z(ppwhFc;UoZb=ht&))aNVcuZA{^Vki8I2|ny>z-vxs5sN+PP^7Ry<bLgE=v6VmB{J
zVmnB1$PZex9A|K4;<Kz|z!^L@6{fF_4;Y{ek%Dp0TAYKQUe#XTZvEZ6)uInL#Q-ss
z6~-!r@$-^!1zyWCk(~W%v+z1lG*Bpv+~S~h2*h>gtzD8Z$0LJK6)ZjJ0bRnLeJUbG
z?9}gtI4AR}uG?GGP%_*-GoC8qoUav@v$oK+Y8THUfHfgyCkKyu)Q1e4LCs;t#ens#
zSV2#pBNPE?kTB-6ZV+xO&1sC4%~qP-2;GmyfH9<q4C9)CqYd7!%v1t8nygn~_V=I)
za;aW1#%dXGP#o3QIT^)Mb)*+4OMnOhv#ug+lZw-ser*1AO5ip<vBdyV1Y?d(PYYpl
z+M&i<k}6o60|1U`h|+=70ml`28GT1JksO;P2yudIRwY(lt&Gqjb>tk=)j7uonGnWQ
zaz4E(#ACB&fFNaclOL^US~D|YKp^qWR+W8u_ou+&Wyd`;NM$+VcyE|V_etOm)vIl{
zpy}SByo5@@$m1TBHL~yqdQb+e3<8XF^{HQI?NCL+fDS6b!Qj&w05~+;m_^mA!pErN
zJo8e?7~91{7?0&i>V&jsB|W=9O129Q^{W{_V~q6Tpw;8@r($wRIjLbev`ludh0Uod
zb!?A&3qELuXwNhO??-C#PT)N#>p`QX046dk&HPfEHHOI;Ve;3cV~XJXXBOM2+dcY$
zUt7WzIWgS5(dFjQ=Ad)-I&Aunm>?r`eR!&JMDa>vejRvW>0K9t<O!-unc=y?@5Ns6
zevlBG*w?qsU!YXYeU>?4YHcl#0bqIX{?;3zo(t8PW|GEdP){mJ?Oo=5YsTQ8?3Yp8
zE<ufkaoks|Y1fh7*uyk!m1WLr<G9ByP@2U-Z@KK`_?~)x&Re4AYF^ZxdQqDAGujGV
z(M13!L0q4XRldO)Tz%o!>s?{#T-S{hoh?~LcCaV&uG|B)c$nfphR-^e&WVQbSK5|f
z?`lbWw`>}Isd6SLN7FSDf5*8v$sMci=<IkCMgv4u_5sH@#U$|+$sN0jl3CD9dJk%`
zJaL;gl^^B6;QQ9(8ClB@Q^jm(FiN_Rd|-58x0=kez|<|vbPt1Gy9Sx1-&)5kJ5u3!
z$m8>+CNzle#%#_r&3WbQD;}dM3=V73ZzKNzL%|~>gI;;5>DQ56Ji7}<-3~fY0Z7c6
z5x;oArmSBnH8{7PR@#W{-9GLq%^TZpNdd_99V*ByX(hjUIT)*KnE(+%?!F}Es%dTv
zl7pY6USW)!P=<xDZzoZO@tie!eY?WYF8Gm)5AKTd2nZKZf4n+ZquP}=@$z|4X|dS5
z<yfD+Z5jUnfLAqs5iaBruGP;$(zm24tHv^G2T;RY?)I$eLNz1HBU*EG-Qqxmlg@uS
zw3nt7*jqU4Y4%oeUV@Im6Tm)|759d(EnG6o=0e@iTJY=Ttv1%ju}2vhSu$0-6JQ()
zu#j$E)XNPql~lGj4%M?3og*$l<Lh26R~l}|YcS`wbQuI=(-oTcB^!>%n(kLlh#^@}
zu_LbIT-K|jtWV~`Fg-ffxOqmSu{W`vw_-uGb*m6Sq!*I_d(-rLRr3o;jQV!PY0qO5
zx$F<Udw6^jisxqqd{(@u&yq!oBCuST$?laxbkwes$rG7Fc4Lgzi)irf>fiU(AK2&z
z61e&r^r_X9HazLWn8p79gi~289W6_P&kicQ{u$OprN6V?f$g{o?X72)-FBHW2S9sP
zjCYSY>NkCBe{0Y289H`6!E`NNIWRP-fc2~PdKRnZ1#3A~N$ZZ4=;nE%8;XKE{M4fU
zU^gQQZp3n#`ZbN+tY$ZWlhZ$iZbY{Sk06i6p-o=pK;(W^BJ1}-he7`U0jUmCYRnXj
zZWtq|u4~5Yn4%!@#b_^xCOu>Pa4QeR8mHS~SiHPvztW~#6o`BmsKIY@EHf}s^K<zh
z>s{@o-K$N$JB5)*&lSRaKAIoxDWQ`LS&syC$N3fLvfEpsE>ovGR!E|y<k4D3CEPF)
z`*Lu4*OBYKJ4o)%ZSq4M!?^q_)h~5xKe5W6DFu5P`RB!8%dAS#U@lKV)1LLbB#<g@
zZpgnck6uM!uyfdY*P!?+@vij0KW^R1IIj>E@;M{FY*(~=KmP!b3ZG$HMpq`KDO23*
zr)*lxIUuiU@+r{&0Bp<;3Rv@AwKIRC$<sS)%kBXF(3!LRSgK|ywsijhI?SKF?dx2t
zk1AJ8V`)9>zP4Oi;B&ZhTsEe@UZEnK20Y@kv3DU85!li^#I7+>9%+Z3l<XH3r8p$j
zOPL%*%!itM(yUAKWY%rf=JB<0^`-=0Yn&W;gYv4=9nF?GV@=HlkP#eajMS<Sk5f^R
z&!r$6){Nt=Eg>V;fEOaIS)NGG6;Cy4(YBVL2Qk{`xv0rz>)xK-a%wg|T4fEzG}DQu
zW{?PI^`j<`oSFbLnlr^GQAkcG0mS-J9=y{tPXp3`04aL^0QIQ-C>R2O91h=`)1E7<
z(}-&{!2N5J=qsqvTXmZA)`2rlBa9qY=A7Jo-K!NVUruhls*#&HZFY2m^zZ&Iaaj^x
z#={DqoojfmAN0h2F_YS`gnU<}PNhc_k&}#fE<oGR=Zcp+`_wkzg*oP?>DIj}e+kb$
z!!-=xRQ>wY6ZWEe3M2$on`zoLBiGui9-V4PYX!Nawk|ZT!x<u&Tdf^?;(|TRY+@$t
z*G1qjpT)6^<M)5mS2}uitv?Ig3ttmk%FI=9jMp|J;AWKfK8BjvZS5s}<mGxA`SZjf
zMz=mci=J!RCf5GZX3HNXmb_!cxf;t8pO|#7HwOOzcy-tK44N~|G`I)elX%T~*Eq=l
z<E<DKADE($%sS$Wph%a$G?@C-W_~HAd>`pYG7B<sK=rELd89Kr?~0c+QiClMNsoG~
z=DGea%A38q<o#-Wq8}qImIJ*ZIBKZO-lmvK_hV4%c@&^pSqjQ9*fn#89M&^4kDGDG
z^rj2x*Nx`5F%J5j5LPx^4TO%|(^^n$m7AXUtb=_sp;G5*>sl~J9M(*)C{h97ipHF+
zBBZn;^Vi!HeWsu``($Mt^VC$U0}-93y*SEj=4vDS{L*>E)5WtK61b<WqqjsgcAF>N
zA@f-K&>gYTtcw>Pz(q*5Qg&LdNfXZ!T@vA-)RInvxvy`~wMbsee((q!?ynQJvXVKM
zBOUWyBv%th9wT-D^#J0$>|9(WsnJQPY<D+z5?$U%(2eV!iPpJa8d=D;DJ+4($3V4S
z(^|T<l$f6$$E9eEcTu^I_m3IR`xVVje6zW%mC@%B+g#2+b89n`+$~&>L)GK}t%QR=
z-e4=W`%LU`Wd8uZc%^1?GFiVm>v+z{$Jm^Lcwbd>mq=nC?LKP4cv5U;OXySRnf|rX
z6$EllJ<T{E+r>l0&!E*5bLruGWh2bLk;kH@Dpm0InHc+%$^P?J$z7(HaC=sNS*ZG#
z?4o9_m#0Q@ESDqu%uPIOg@1PpY4lpM+*Mgu9Oj|bo9aJj70`xjsR72}k6}^8mOO(^
zmLN_^$JVB{Kt~^yP3{BT0**RW-7&GfaDA!<P*=TAr?$y<deQ;yfg^E>Qb(;+ztwCk
zt{Eq|RBpR#HT+klu5lwb&{8cMxy3Y+53O@A<12h+Ev0X-{{XJ5KaA!->g{pr8K|)C
zb>NXe>s%}NyHa9y`AeTcRiDIKq=)`K6o0z3a)Ib<06%zCZ!AfY&ZFOTd91pP^rI48
z$U*cts2H)%UC;aqj!?PjGHP}(g3?@|{A#S8BhupQa0&LWJuAm1fydIHC>^|>F0c)?
zQb+d-O`FA`6f}0M%j#OV#Lh))MixkLM@s3Xhm7NL9IRcJ##bZ}6})Ic?rMylDb*jO
zh`IC?mpW~bfl&dP!NSEC<<|8nzWvi+{{VLat2Ncj^|+Y*T-12ytvn|^X{ZY033mI=
z=jzl19+fbU9`xXxbTy)+7b}Fp;+=!mrw9S`r7FG1`c?ZOT&fh(?KL?I>qtU@$;Cfp
z7aI`T)uD~hpXpQ)*LNJ_&{l*#V;}-4Fh^uH*+$&1EY4TCl_KIpO$*Imp3dc@`E4gB
z{<)f1w4FvkHdxGltBT>|)Y9b;ze<%-w3Ea7yAh2&$JK>eUkqymb8LzAkX5L~17<GH
zw4p0`d@ZS;yw>T@cd1vxcbVqq-F>>^tK9A@vz+qjJi6*v!Ys#|%xC+tnxFm<v>+3G
zFVsg%njON@eGWLFG{TrYE4W_<T87Kda{mDE5Gq07?KqxNbM<UgI*{%)8Fo0kU^k58
z8TGAMVqYh(LC?~<czi3R#K8TO@%`zITU{ecLNjX+{{VVJT77B>SUrrJJmJEIAh5u#
zZw_s1rr2}Zy91|bK;Xk^pF_#5D_ajOSM1^l*RT<DTsWRu(B+AwZwYEaX%DKL{VPf<
zcOUZ2zbbOUcn1@*p4dT77WbdUJg4i$c@HhV@;W}TVs*A=A990g;B&=5Z0=YL$uas$
z!}`*HW=PHRGdKIrSk(UjWUj0}v*b$F$En%}u4*=g0On}d{s%zQGs$1pkL<8N)vD*$
z6{5<Zx`);o1AUwxZlV7GzUsWoZT|p0!3Vkx)pPqgOyJ0%f4NUxJyiV8Pw866FQ$q1
z@-j?z-@@$QRjCBgM7av@?TXbF3F_4gX>b#hxSy?Q^%`A?_VP2ow052?q&WWoXjFGP
zl-Ch?e`NrFwArmDv4ww!81$w|1WKI%G~<J%7tD}*X)~UACI<rp9RRGW;zI)YIqGYx
zbxwXv{VJWt;xLfp`kK|#M$~aGo4Lp`ox~m~1bdGav2g=46SMQ}RK#*G-j5jfsP<=9
z*JSo93uiu`ol72>Eba2PJ(i?0mFPLGO(sbm<y4`-?^POT%6Q3|+E$Y+P^!Glp!L|;
zt!2?-d}dh>u{o)2P>9D)D*AEhTJj^3Rb00zE{Sgt^&aPndg-t)Awc@o@H53bW(cRs
zjNF+?EMN!j55lZ1q+oE1QmTr708_B8LLiKP59vxHj1hzs@_JA?Jt>k*tA+mn3Tv+8
z^K(ud4o+zsp7^E%HUq{e1E1+n+y2!i4rma75$jJKX{6FI_n>G=q+Eb9Pp)e|_BJ^q
z>sRDLN}N+>P0P=qua?bpt8>xAzjVU~2ftd<gp#0+Dy*?>a6M{kb}QeC^DcB35bi#>
zt4f1yL2jj&bz4>Ap{_~kCQ#THY|YI~!<uFYlvJ<BG=w)FT+$IsN!RO4L*Y0CbHzWW
z6%;u02&rm7Mj0ln%DEM97$4H3kutfam>F_LrB5Rws3_V&#cD{Qvw_pSP;rLEZ%$pr
zS+|#LsKj-xi4aK`ZVh7~$^r#xS=_rtw4)4hob{zvI`aj=;UHvmsnCAxP;kpa9HFcR
zAso^XnhEFn(r)L{fe1!<psxayoUJH4QvxSYM?LEoSBrhDfb;;L(zjR)R&Jo6+qf9X
z9qY3TD^yIDj}g`oN2oeup8o(}^NOHrZ^TGOrpE&ZCqCyDibf6vew#twnrDqQX)zS?
zKD8!!sD(&ID`EpRAUPEo;8KPotyRQIt>|$<>DHqRGfEFM?kf(#Jt#TB%^BmZ2CCo#
znleXDw3(zQ+NeNkC+kln`t|KmzD-2NhxVlhu1z(1Q@J9gFgGF9W0JvPl)D|c`B#dl
z9Xl~UT7HoOJWY%qbBd!NWST`inBx@by;>!r+e!lGBB~e3B-04>%^mYv+*TaMke+|W
zlpZOEtrs1I&(fT{nqc724rzsl<c6oCeB6;ycjlBFd(#z*fbUALDga39OB}m#M6LW;
zr6HoDE)FV4+m0$c<kXS2IQ6WCO&Q&fOxBE2ZcKFJ6_$=i7^yze#A6krWVBtDMNoOi
zy;YI-9t}j!#9*GCb4?6L$A4OP3kuCiyl0wgXFl|q$l{BR#PPSy&1hR*`EADnvO%e%
zgt*S|2d-*GV(sKY<$T@1F!!vfBib?PSD}~!704&C^{MBz7ZH|BXRS<?#*8d}2DL0M
zC1epa%BmNP_o@#Iq@^4TgW8-EX~7)UDOr|SmN=thiFYyQJ*w@H-g!9!v53P}yGfaN
z&lRj$4I5Gv10TieYJ|iS$6s1xvy#A$l?zN;f@<y|NhD|5m`^;=Ty_3c5p0?+G2=Py
zPg79?ns6W=YMBhx(&X8ApPhP4N6oZX{{UyLd3}l5bdSY)WrO*a3H0K=ABgGNtYmu`
zd*~)Oq!`a!QP|Rx*jLUTumh3nP0uv65tH?x0FVb1pqdHW-kZCcX*aMoJT6ZlQWfT#
zpL#Ruz<xD;%6)~*g{9-TH5qjSmr?lAeWnq|oS&UnvZ>jNnmx&SP<i&M=K9eN8s;qe
z7p69&W~-LFgedM_sbQ->vc&2`xoiyQo+#)!HAnkrOkRH720z~w8*6%4{{WZRe+CAv
zV6hKqKe%4nn)^nTBXW4_SzqvxX(J%s#!t00_>V~+^7fUg%W-f1UB9@GtWsZS*FRsv
zfOzXz&ElOTf6ID}yjiAag2(7ZQp&N9{#~&=RTcJ!>*yNL<luKT#>I0iEtQ$ZKic5d
z?x*5QTck0=6o)((z`zyGZuGCZ$}n@Mg;eWA@UfNDs&he`_8upi0Fhi|u5ejJbk>@+
zt>D5<89ngT=Un5~pB%3d`5cAr0j_L!4^XY|QukSSe9CardY+&$jOVQ{Q=HckW8!J8
z*sROBF@?wf0Is@gEn3p=?n*a$X1+%ml;UvT6m&hBIJ$LqW{@0uQh+hdBCuu3ur%(U
z<6cY9>I`CnG17uPDSC5A2At9`1oKYC1XDoCV_d?+BN*>qeW|G$t-v61+0A+!94&B~
z=-aD5^Y7Na--T*>vWfHAyhv^NK~G`dwK4!U0h5tZ5t3`}*2l~}$XH^aBc9b^@BqoG
z%uecw7Z4*IY6r+Brp`q|{e3f7$l4=%=aWg(6utTDNuJ{s2^LKe7~`c(f6gihk3OQN
z&MSBr$et70p2MH;rb2xHsfheDTcZcLU5BZtNvjSrJ!-i*HJpuN0OveZZPys)pN#!Q
zF|ayjvn*~uN>FH|=eB7Kl{u+u6>d8Il_=y@q9jWhAk)dg_og8v`_!&7D?=7Q!z6-g
z6UXCIIK@KMGBt?P$o(mXpPzb-xF<D}Edc38eQ5<KJkT;k>r!T+T-3mPwP?;n(F}@{
z2iKa0GlNqQ-&(UaS8zIW_|z@erB5eXfbdVHM2%u0&mx%I)Q6glx#`lgW~fXId(w_6
zqMQu^B~oxIWhS6OQ=sOVEY#4Y5$chb<8qOT^%P<DbU4QtuP4(Pmr=K4lA-h0@~=~}
zeA+1F<BXH_ug*B87ObRuxof-#=H%e@{#8?^D%{xQb^6t2<n$ihtK~W#p~Buw?I1#U
z?kbu4+~b;(>5E;ma6s-VJP>Q|E`1gr3K6mqh6nSf1q5-$HL7(VFTEqSC~B`2-h4mO
zzSXIjnBil?01kQPxJ5f#xi#tE4CHJ+M;lHE6;Rcjd5oMWO2?sI*rnaSlv$S@4L;J=
zD@YbJP@#P*KT^2V7Ul@7*W_dKxf#ICUb`}jCn^504A(*NOl)_Sv)vd`!Iei$RPs7U
z6EuVb@0#YcdkLh}KGgfvE^)iPZt50eP_t`xa;o3m??8zlF-W`NU{~6+^<87^1yL6*
z=xWxPV47{9fg2!mlT`Ix5AD}WH_fo{z#eD=M^C#;>m-~FtbXvS_j=Sem(kiZax=Nc
zLe;BFXzcCQD8|)M(vgzU?to=RnR(}^pbJdfP?6UeuQc(NzcH7|$=T0J^oeFzVv<)p
zD9w0}iSH8cRglI`6z6HIsx#Kgu>R7oGuappz_;G(P{`X?AEhjhfO}LKEZyq^?O?2j
z#sR56l_HJ2QsRR^9@PALbDC#E+MLbafCgjvcBsi9^q|vE)M9`UpCXuBJYtlCnoQ!A
z$pC3GG7TN+3HiS50wq&{)9|U$#_oI7Vb}7hROHh`E_o?=6T<k|%Y&M&ZQ(d&*jcc8
zX02M17=E?Z=(cglq1&9D!!@i~^Lgbhri~8>=<?}A114h%I3x3`zBQd1$7p5Ujzw5&
z%Uc9ND}+6Xt~16O)Hgv=7hjdR_w}ns%gD}1qa*Ku#S=y%w=M`L6`GFh-y{3tt~bvb
zN5(~Z7)ah{EoY%v$GRj;@=qqYomvpLG6e&JitG$(s?Cv}g0Qt)EvnD=i5=_KYeSAM
z(ig&{Jevn3H+t@Ff7ikkR|(-GzVNOv#kyCbNf~RLXB$Q+TM;+!G0kr>TSer_vG)V`
zQ|9w-FH1<-*u3QQt8Nre3U0>L$*4&K&tO5~mAaF5bIpNoE<3rZmxy*i2Xl;7=Z%G<
zvwHTZE_pBjFe-*-T_G*A(z=}r`+kk&zBeX5Q(XPx;$oyQBi54Ic7dB|>N-+o9)ltC
zE$!|Vat0Tg&$!crYI)i*AkP%-KHywvB{veta!zYPSp!+y-6jEC3Z02(5;WXi+(ZZ6
z&JV3+M`~SVQ~-4ZSD?>ir&1GeJk`J$tYy>o&2bn)2+t;{YDW&%o2(=Qjih~RGFbe$
z_h9^|71u43q!&DH<knQSfwb1bgYyHQdMs#}mt}Ts?twpbxT_2!nt3su%neYvw=r7@
zmz4wq?@fZ|$eCE5mX+)cT&ZypP(TM6t2$}(ZG5QFx8$BGXJxpVusWK(p%u50nd1aE
zN}g4Fj`|lYH2LL79!Dw_x{pfQpG}T?j5i!rbk*UFb_lm^Z=k87)gYGqd8DGaz|XBz
z;TbD5N|ckjW*x<&hGQ7q6Rs+z=SJ&_?zG4(BwM71A(xJN)K^{{j(b5m6-Ukp9M_*$
z2DgdXPZYM1#|xR1=XEKPNxu2y`qj(bCgRbGy6$1<D?R=~Mt!T#ohe5~b*U$?_C$zf
znQEQP$%Bqa^rev*xMn!TM9CWU7_7!oky=97;Ct6m;OKm!#2x|UpW?24ok8tgFNK?Y
zVb_{yM_k|Ct!*wZlXYdN%MX8A-?LD$V>LoFVXFWERpL26txuXjNC@fPq>rv@CF33H
zRUWhmvJOT7sZ~O$EY)3GYVk<_05Cr`C;=L5xdM}PPs7m|8^+_GtxqkQN}n$VfGAx;
zpJ#Hd&{v#XoZUJ1?Ou~TzRPKOCjz|A;db0h+vh!ND%%}cUx<+$U<}rb4acr4G7-<x
zwCup(n&z?SbT3ZWw@^j{cdW<S4_wu~LO@v*e+cPWl0P}kb){r@)#uG7M=ImKYcB5!
zed|%5aP+Ku#tg)Esxc`sUo+mN9V)SGI5lPv7$0w10J6U_k7|G2UbR`Ajz5(=Hdm9y
zFe+ZLE5PQu9T9x1P@EDDO=1X^S=Y?L3+Y-S_*+VnMBp-v5soPVw>(P{`G9<<t~*oU
zNUk7bzYY!xilu9*#d8q=s|Pq?o>rueV`X{@;HGxBxW^QLvnsH++CVt&E1JJS<`*1x
z=e=|@+@z%JIL%>Sa;!V`rUn$p0Q%;w=(B~q+FJvyK{{us!KzWr(A=Z1P<i@L2clTB
zGL5Z|YTCE?un#qXrOJ|RVfRYz2Dj~-3`b1#phcu#DY!fy)p{J1sw6%tdvfdapbHA2
z8z&VU(SyjT56lS8Xc+>5nUX7IyHz~rC%EleR~)eeilES))B#dZax>DICnyFwRk;R6
z397|-!Q@f`AV6xF8)+S>g#qnHu?B&fk-jlkqMLF7xM0>aG7vp6SK@4e>p&Y2$aa8v
z6=8z1V--dTeqoOFbqVj%fHS7I!xN4woU!F`j<vTedFlC83zYKIHqP_`n9+Qh=~bnV
zBDCaOrbSYd?wryCE?9c!ip-gEHucSGOs6fJ;<IO6qon|5I&5xwW|08jydEk^jylvx
zdw!I}T}D<1*0imh7{*R<Sy7yv3~^dk$^cxDLw`C1Uq;%&{{WR*OuPGIBCEteToL)z
z*jJJLC;{znk=O93l@&>=B=;Gpq+e=4PNy*pbB-y|fF$&)=_<n>U!_W}l4qPyGW<?A
zZR%=t`HoFdft8qJClzQM98fYx9Zf_4!Ks1yao(b00j36iw+EeQBpk5$O;Wc10FN*+
z&27$tTX&4`7*;|jmk|VeSIY4P4~C*WOa)J}Mt!)Via4*BJ#gx1?MdIQFKS>XIj%Ft
z;1d&L__9rQW0PDzjbuCGT;K!EeIE<Oyuvm-{LR}A%x?}p-FhtW3Lcf|H_#=`tD^za
z(!AfpOTS)59F<eedSZ;B2fcedVN=;+>CQW&mnn}m2Xo19ts2tp;cOgsuBX7)#KkR}
zWQhLn(yI8z%twBcC>;8FRc{BoCa}x=EIn)JaWal!lexaf1sJ?OH<ccc4n{>UT59yC
zXWG9bk@X=(6cf!z3(!^{iqn3M#PkNX{c9J+MZd7*AQDGv>B9d28a}2~wSzpuO|z>e
zHsJiVOM5D^7a)!g6?tQldC_6PW;ESW)^(60rX<_J9qaDsK8Mb+H2nw7ohF!uLVob=
zTV5;CEbR1SG9Xio<#^3u>9Fd^QZxjv;7(6YYe&X9l;=){)&Bt2J1G3Rn(FEY83`gl
z>M(Pf?YuvJ^G2v#fTV$%<Sn6TSnWS|l52lRa~!=s;rW1~MI*bEhO-&q9<{Ti_%cmW
z)6Dxu26_eUSS8q54aWg$#+mUTX$S1mDFF{cDqtpcmcI_S?o&P)c-$A7&%gLJ_P3GV
z@UU)x3{=)17VO@9IubpU*1CLE(%gU%fj{i@t!_^#<J!lCCGf_f_Iae<tbSJM_*Dr|
zC_Lu6KNt9x9e-X89yXxieQOb8dx>@+<oBZCV>Z?~CA@_r&UfcE=nCx>q<&!9cJqT+
z7P?DYI?i}u+O=MGG3`AuQz;gZ^|}4;C*}00ZuYd99Mu+|%5Hj7mgCH91JAW6?lx-a
zM69D7Gt#@a(RB-}1qh4NBPWXB^uzv{2pQ#uYtn|HHM}v##A6-mYfq7CX-1zr(BrOr
zGvY}8REivTWqMnG4)}$i4|5zN+nVnn)ON>$yR+|ET8#LRyexM8YsjsJr$2hftxlxd
z<z_s77u87$`jI=h+#}6xN8l(VwjXKKW{{DNFa=w&GRdW)!#FHYIW@l$ZGjY=kUG~+
z8wpA}q;leG&1jByPw-}$Vpwf56Z}qjtQ}_34L0}5bLEEnr1Y;tL?x?|_>S;LrKw=1
zLHXCDqMy2X&ArZHmKPb0L~hvzp(&50ai48`kC~94PSv?#E!?)nmSD;|Q1IdHY-zE_
zK}-^mc;d5vwWNq*c!oM0broSXD>q-hRG!A6(vmGyOuTO9*|nc4dsM5b+grnl<l1{0
zrn@HPB}N}w$kt+lL=iNuuipc$3z=>wV|45KYLZ0x`czHgZ8USetA+mngl|=u$Jni&
z<w(l1o<&)Mz<w&ZY^IjO{pKIzR%YyW*82UO&-$m&){|Fl(5oCARUHH2--$lm3f)<(
zPy_QgagqAhdEyTSC7zJe$1@)+ZYp`=lS4-v;W*gq&R1{&JAHcBtH!p|z*1?5?bn*~
z&xeW^U$|KaEKnNs3H41P(*FSLx27Opk+^YLq*2c5UJ0;Nl50!Z#GJP+kZZ&|L2fN?
zrG&Y1jkhPgeL!^0BJ$owg%E-{Dr@I29$Q0Yugwf+<?{%lTOF7m;vB3fW!}9Fde?wX
zbY;gX6pyd@=DeQKg2?>hy;r~l9S?)YY<+6*@7^}d;<+Nuwr}+k{{Xsc%dRBbsLs9j
z^{-Hr<{5w8HRTtKf43%#V+7{9nc^KLp3GuZ#%q@G8U?;2kEL|lIotsBtS=g`ku*}1
zfu4BlP&1q)8g6iE1-MuHtU0MSWqm1>QoWWxEtQT9WHXMvt4{tP;5S3l>sc(E<E|+T
zP}FkWO#(a~Xxaq;DuNFfq+~eGDtKNbUzh@YYC~}tJRm<>1W-B7DLM@Isb`bSZ16sn
z2|UsPMoAT7+y%*Mg#l*3sroGg7DG^zO3j*KpkPffoSF&sr0YNdG?~vzQZqro6aa+c
zo1B^rB>*@Knt1l6k6Lj3XaM6hcA|_>0`wmB(dZBUjkk}MxxD>rcf-%S%u+ZM37ryF
zww6Xpw>j=>DmB5)X;@^;7<N4=qc&uCvMg<2J@f5c(HUCoyh??w2JggI9ywa|aN5Mi
zW1=`G-lgNyiiR_W^{KO7gf=jcbQKiiijbUkrbq!od()P}MPPGJi2UZ6pURd$^_9%G
zHG39;$A7|}8Gnd=R1Qxxr9tgm7zzX})rg^ESY}CLm*!U8Q4|}pDFS5msFW|EN!aTl
z@x{zhEGufKX#2&h8&IBYQs?atg>IOv<U><{!yMK$@UVogi=AfGgf?yuRs89{V`6&&
zPTKhEMjO_;c~Oru7;Oh~DL%@hxTliD@tQJmM=B0xH|(RXX!{`SMK}^O%{&@85c!!G
z*>mYYvtMIYRN&LqfLsbWA{@-8_An^>AGKT#qJt{qwI>*dG>U&?C$PmMT6<NNoMVcH
zNw_@Y=}_X4NwTxq0=$~anl_F`U)HrAR?ah3ZgQ!*xG_sZu9GML*&J4lf@C&MYdE|5
z)$KK2Nyy!fD~2Btv)I#!Mvaf>R}rDxjs<7B?BJZAYE9iM+Jja&B(*ifkgs*8eWDx_
zky!ibH-2@mG9#4O`&2`{C)*<(xvY)n9cV01b4NJ25v(u3=M}9RZ;T&NT&FqbkzFl=
z7q(XGUUoZMGpi1*aCIVa=~}Rmsn)Wt7H0XP#~o`vO-k+n!zBpmfnI!I-p5JQM#RaU
z)hw={b<g8ob9b(4p^y4WRr(6glTo{u{bk!9p~Vg@ZU?CupupcM0q$wD>bhO3eD`sV
zIs;x#&$#8JC+gXz7GLjD8R+u(r$|wea8IWOs88b?AU|}HInO{bTs~K@&*4%mGB+X_
zPJI%cfazuNkzho2hyDa=q`oM-l>D*AgY&GEv$}A0+RQ-z0A$xmq4*C`)?xFW;yYwN
z!v6qzpC}m8Yj^SzT24I_S5x8VlIqoDcFO=N%ls@crexL7A5E31rTBPg@d!=Sav(o@
zr5YkwuNTS`Qb8Uj$2?Y?k-#JQri?e%pjNj=3}wmBWvK&&@w^^g@-W(Z@m!`*bT#g>
z4-Q_&rs~7Yd~$rIs#9rx7j@YVleN1O5ul`a((=4y(0Lg(=%>LtYs}B(+<eWP1Ar+<
zgS4@e_7@;}%4*es^PVyHhv!NPkKz^SU+|7-@qDdg5F@VVplRAHUv|>af4nnKo(Q#0
zZ)AC<V;$-00mcI#pf%~pnqm)^?1)E9D4^ZgM!)g(68#WV`)X*lhpP68=7Qd4KP(cT
zq8d?UcIOFcIr^cmN*cDFfadEzME?NmRBf&4z@Oeoeu9(4Q!QZYKeBL9=$fOSmcmcQ
zwe0jAP^KQxuN~Z1MBX8>2MZj{?@=ES+bPQ0NPe{8j!@XY?Ap@%Cp&ZDJyqq(#}Hpu
zdTMwxQzs84x_j=;bWP%P3-Va0`n5)UQ$O(AM8Az^EL?AMRh8FfN_ZyZ^}dVnTCko9
zOaS_W6YUwRE#h0wcBCu#R4uOG9AZGfN{_DCwUkzSlP`lUJKf4p`zuq$;SD?wovtMO
zaaql+Y7PGYFAP3_Qx2ti#~*2v^P}ssEBhLKS++bWrDy&<oc{p5B}hCmrK<k`$DDtR
zmCqZSllQJ9IrTKxc^rK5F{A5q5A3UH%yg@vX;BbOtONb#%}e%8Dlg%)Q}4}k9Zqwa
z7y?iAsd$;O{{UvwPR*T&xYHr~v)icu0A&R<>pFZrE_3d&@mziv&~ZQuo^et2iJcM4
zDK4j2{vojb{GWo<P2wvx8-mWm+PRPxl!5J1>q(j{zJbs;h^<aG+PU{8qW=JdmNIy=
z<J7fbZ4?p56&})k%@zX>*xWuRkbTQY$JEmgiLXC~7+2|7v~=c|JfBl#gTt<dt9XX}
z`ZBN4YBtvOCLinepJ7?qJw-1jmo$r5dJCa#wLL+xo4F6<Dl>g{-EOA;0KTdWH8?5t
zrmo4U3Q*`g&v480O(7obQJEMoF4*<WJdhf!*xXv$7J01%?0RnLOi|@=x`}hcF?pJa
zR*3BwY>|xhuT72x3b_Cb3iHbiap%<*F#^R18N%0nZFT0tHvwI=-QaxwJvCbFur@Co
zQj_xV0j7eaeb6YzSB|x32@^hhepJy;an_MXY?@#w&MA*3)6+jnSsP+iZN!|=1Dbaq
z^2pN!(h`4kN4cp3A4*fwfCOUQMlnrt0r#PqvGV4tP3E^jKnWw@;Nq)HL0r-_Qx@r(
z8s1{05sE`8w1GJ9Q9R?OY44}XPY!+ZGfg^tndV}D3PUN}uHlucrVY`Nj!%46r`Sm9
z?0vCL`xXe~oK#q(&S2PFiAEJqx%94|O0a0rS=4X#s}WiSVaMWYLKMYP6J+qN#j8p8
zd8lJfc&i{2R3XX8r~4i$n+Z9k*~eO99#iGcaZTs(r7e}mYEHBY<0fsOY+U_mU}xKx
z<Jz6ZIi~`lc%TI*JY?}oIS2aFGm2=Cf#2ysiOA1-TmW-Wq}g6U{Hb?j&;+<#{pww+
zKZ>IRJmgWHMrau$w?HXbH%HAfPE$2H4bb}6%x6l{Ozy*MW!*q=yV9#$u@YnX)}_eZ
z6DjXmfpIQHc<|KgH7tNESM;lc<YQTu(s_3ZbJwkDN=TDG!;aO3MQMy|k`2J~Qb=;E
zj%u@<jyb7`-54W^OhQuAcTgMBkP3$qROF4_>aK9$)a2v}8UjJql=JCPhWb+O^`r%P
z7Y;xMv+h&(hZUi5G9<e*&#hFPfZKrUTShHzA+VAYX{%67Baax%RcLu{YChv*Ij+S{
zGxu2~rIm^A^r>NTNflWRK*xHLCjIBNan33-aTz-?%^*GLAMaCh{{ZW(+8FZL9@OM)
zk6MrV(3uW-qQV||Ju0>0X5Fwmb*m&`(_C@WJXW-wqz8+5x-TzROk@V#{W1Cq=h)=e
zYvX%QF6keq&B;H@^R6k7_OH|Ma^|5Hc@>qW#%=)9_x!)skV5R-4z)T!$AiUmnGj@^
z_oWAle35M&FsMg*1V6PMJJUeTDdX{~5b)g6^!KQNH1KFZE`6vXkTz-AtrHN;cBCNt
z(}|{@l$aqDaZbS^gy+3H3RVMKLJrL;sA6-*1y$5yFy6Rtyn2eipk0`5yolpJFv((S
z4R|;9j^q4F4QCA|(2U>5G=$K26ol5p9nY?54FK?cXeWwd5`oKcNKGi~){B7V;0k7G
z&T=u*qcv9oMPr&*U}_+7N=YJ<U`cGK@)eWtspo^sbBtr!sH+t@9cozJnfYwzv8Vyq
z=93hy_lHVpCp6OlZrPw5nrS>{oDMmv0Z%mAQN<xNTm|n=Q^iM|9x2Lm^`hVvJXbE9
zZsMR}_)-IdNDDGd803Iz2@c=@>E4=KBQ+a0ILXatA&x7GP;t_eJC`}8=Lf9_WT2l~
zGtDBYW7tr~9C!7qxU4(yrtbHo1mc><nl2U|8=6qVH5by992`<?W!rf|Oq}&S>(jJp
zJk2^Y$UAGwqHV4T=sB-U@Z75|pTXpc`936%xfvdoUhN|DaM+|BX<XsYw|Z`W3i&hI
zBq_9VK&H}lq#t^KxG-Mz%Xo?Ai2;sQQg{RsE2txbT(^m1F9tzBD`vgyfkomiBZnN?
zrJ>K6u2_Grlpg2IKjTrnvmEAWdH(=x(;1Y19w`ebAAEjw_tB?GbVts)&$y(yZN^DH
zyN?uyap%pD=hck`hp7DNyVv{Gf4f4w#lS7N^NyUFUWXu@{b@I-95?ApkC@~f{V8+O
zLigAX_&=2)>(EoSu^c00bu{q=tiuq=`BL`umsCDUzJy?4amS?%$mEi0(6hN5h#dVX
z!%n|)HrdKYt}1@FL4Bk@V^Q=eW|t!sbZGjC0~T_94h21QEl~6JHva&=g-6%0%k824
zUa#_*_~MVln!ef=sG~1v!F_iR@v1DP9g)<lslf)iDPk$rSA)3|r#O5_G0h;QG#_kM
zj!AB2E(zxp^kW+-Oy@iwdb4Gw-0BU8up`b3j&WUvnV{QPC?ts_>ymr@E5OXNoIM2M
zz3Cp769ZChOJr5h(^Y&t#g;z7xzFoe7|uC4G=V_vflHqC@ED5T+M}JUeHA!zM#6)N
z2PTZs-nokueQ4t}qnvTllLIsemL37FGsN(O)fKQ$%h$Dbkp1ir(z#C-04`!9xUa3@
zYL=-eo;GU>z{j>cnwY5~t6H9LYT)<h>tCWnW8|l#h@50`Rb&`qJJrYMnyDzm(ITQV
z7#aRm1f6k{Qxj0ic?Pj&$ZmP0KgyJKr0>?CqDX%ASjWnGRdgRWUMj%(m(w+@HZz{&
z(2=_pGYo(#v}X<0tz&5wx-gdHE)N2$w_a+@pU$ekTA3FS2PT-q2ac5RFe$Cpvu1;P
z`_YOqOY}827^rbmgY~EvIH{D1sF5OA@w?WhZ@cuUQ2g1ck18u<V#r&jYP)bcb*l_B
z=~dWfrbdwv{do4M+m7_`G18jjwPei@+~$n)?MN^>QP9#EA`F~Vz|<?)_7x~6gNmd?
zi4b$vrXcZ9A?B=O3UOK^CPMsrRdxe4Wyci(;-#8IZaJnmYI*5QV_CCQGrccLLB%@*
zG=@EX{Z5!}arxDCKQ&IR$I_V$vu?$1p~eUA7x~wz>HOI!<A5{nYszCI&Q9Ml^Z3`Q
zX$SoQ26L6Kg5t<)7JFG^(V|&LALCUI2iR5FhE}OC!LN!(u6em_^E+hay?aux-v0m^
zjy5Em)Qi+t-JelUU}~_3<s4KG?Ng`R6de%|uWl>WJ{`uZV$4$nam{&A$OW<QUajCr
zB$q&ME0W#8tEai==D)yaUNviDcrA-A=IM`GyDZV$M$*jT5qgtc_K%@5-kZyW+T(+o
z=q~J{ynw?uD0^1t#>h))p}2%g3kF8+D=S*nUe6K654i%iZ0usQfI|xHMXL8&G&ffZ
zEAj_b^`JvEtBEeGQRa_p_xGqL)t)U?EY{jbR>oWo1#6^93}65iRCcK2mKmigjHTD8
z??4ToazN~zK;pSOWWBuAyv@V}Z0}x`+P2hOwgC628LjQ@-en*v^O{A&S7Vy-UZo;g
zn@Dlyu=$AXUP-Ay_VXVx)Vp)Lxvjqt_?GSUsUA0tqx+>jKN{ulF5coz%t5YcyR+*u
z%r#0@(?YbZxwej!s--|Qs+eum<Ifc*zJwh1r3WWG&=mCSY1jaDpkgrt=}jl*z@WB8
zF^(}n0c@ISAoZkUO=F&E64(=t^n>Q?e+oiDq$l2xhjySIdQ&%ZO0D@(a3vjmsmgic
zqYaGH)bUJZkjH4+aqcU*@T9_cOl-lM9DWtRspr2H()d>E$<zQ};~@V4O1PeOXG_{p
zW~Yp8-gsh(I<sT^{&na2mWz9BBCEfer=dQT-T3<ASTyl0EJH2|5$l@aqVW`$>XFPB
za*XHJw}J4oRtW4bl}6Ff*0d2wa?imWAFW9R?o@4Iij*<NJ$bKN1iG9!htQ4CmIZmo
zT-7_6jIqg{n|Q0OIE^qtC5=~^)@9g-<yAR7>(Dt2{{RJBvDRc<eb&u-EWhi9Fbg+&
z^REp{HJ6AOqO&XKApZa{UW0OTc?b?qaw!un$=WUYfh6FncB-Hv!!bPxJk*PM7`&T)
zckRYKYMi$beU00vJxwA@Hx_}k$kZ<F&b*GjYQ6Q6Ez|*53>UAhBsbfh&NO_kMo+bA
zvU$3W;mWATJt>U9xP(2^j^KV3ks=jUah_|gSP+Yuwu6oZXI*Kl_Be-f^upocxv_6_
zj85Ql&2HLUq?$vaIoRA*1(YVn@>u@>yqyhP({CdX+(dK6agk8UHusq<A-ErT8)>29
z3wW*o*&@{qHsH;qO&MSc9%|}I_Kh+rMgytG9+ZhPKE<-`>Lwjjk($9<Y}s7Kppd5n
zHP~FPCWhe-Rn+AB)-ysD^6E3Y56G)ph0aQAB|3YB7~9^k?=2oXaW2qDQ;yZxBuZ_k
zN6s->az*B8@^-~H6G+JAOSDoc85OaoEY}0~c=>rFHD312Nox~~1`WxnbpHT0&5K2h
zH(b<g%X*`F4Lb$A!NxjPtU67xXtJA!9cwni{^!dkNSA3JF+b9-zP6j9ju^@32Q_9l
zHZ857x1QiegK-!puG?hUIp>EJm!(TR%-23(RQ@GCwWVey7B>Xo;j%H<R7eXV-Z^f9
z%z?pP39KDc!`9Ns?uZrhl^q3dqa47@FmZ$VR5!Q}k6aqgQBvH}H6<O7JG#;?Vw9jv
zx#R^Mt1jlw?k2;)M()|KM!8S)lHc7Nn##Q%bn%h^!Qj^|Oe8GYI_Y91C(3#IK=~W6
zE35FFeq0AVPtE$)oz9PCe7xaU3<FD~>0?g}o55a-$3b3FlIF4K&Yvnapi=W~J$>t=
zw;N&r^{gue-7af>5K4k-%uA4r^{H5M=}|^;#Y#CefRZuIPPGymloBz`F$#WKjo;<q
z(vW1}aZt>nF-QebmK@dOW3XV>Kbk{~3|5pf29B5sIVK0=BL_9+7hwIWPX7QguS&dj
zOKBK&0=(j41;n20de${gtS;jr>&<G~4bAlLS<#W6m7{I)BRKS|V6M)}va}l@x|B7;
zRY?y#b53>z*yIyc-MQ;sM~e3uGms5sT)Q#PPpxT8PTc;Ln>ifktpY_R`_(i|M;)rG
zwq)(~spD~q0GXQywG70L4k|7A&T1BzsTnxU04q*bTBj}PSxzuVxu#u8QNv_l)f<Tc
zk8m^rsSVLt2hD{%;Ck0Z75E^0z@GT75*wo#+Ik+9trgeGIUIAELpry++;Vu&rB{|f
z%10HK9oxEqUp=!^d7FUwsfdc`7Wus^In?u7ZbNi6N>RxjO#(Vi0_6RX4_00cby3^~
zM1F+VpXe71vP~OwCxcy{p3caFu5u^?qlmPej@3L_2W~2rqm%$=2CqjpIPX9f6)<`0
zK^t>}`O=5T$m>o~xb>iAX$ln}<Ji`G$Z_)4tkExSJ?f09wX>7?PzG$ONy(^NrCXow
z`c-BFX~rl5EasCO(=qd$98`b?7#KApCWN5sYSc~xjPaV!3dtZns@!22IWz&U8QN;}
zGUa|{{HrP^Ayg06uR>Y9sez(Y6v*#Yrd`Q`Gwo7AC-9R`kpW&gGy#nyOb!65%@IAZ
zj@7Qwl6@*ER1t~*z_?uexa-AaUB>IqG6!5&O*|^CpI=(exVQNmjwu1lT#OuJ6;P`w
z&TCffHxfNMR$=)L59dG=ME?Lb52am#O`{p+vqJ#GH9T_Qa55>9Zo@X<H-2@aZ7YTV
zoU2wHyrH(0IUU7pTOL5paoT~J_VM7bW7nlJPzPQGIyVOjMI`%7WqZ;CBKF}BsLpqG
zr&(QwQO<a*T}t6(zF?;T2HLY}BNS4-k2J0aPiTL6^{ZrH<W_x)=LA*I`%lflG{#LE
zWMK56*P2+_e9U&KT|3hPAiIF77fH2Sj`gArI@No{-)_epJJ*++Qudf>Bz0jW%TXBT
zr6J~y=99gA8T1GbT3pf8QVu8>IRIpyE6n^)bM~D`W1{eDz16OM&1CQTSC?GOZY~}|
z-D~f-F9&(c5d9AiI;&_X8{P`G-+eUr<#;B&0c()(InA5lfo;biS711=D~l?*<J@0E
zuPlcy9w#H?P9Tkd8-d1gT<3?RDX&6CK*6q~#)CF$%jzqW(VPA!miRpLUssX7e3_@&
zo>ntVbbd#wFC#SIeQAh(P%%%h%jzphpG+@m0mTB0RzN3FS$-m2`W)c@0Cd)=sv68j
zeIj_rIa9@SVcn|7)QX=AJhIkN6lhfZ!#yiz4KiIwpF4DHys14+T=0&L_crb3LmTWp
zN#?dLt?_WktF@D`HTMwS=g&=QU_omoq|YAgfO^**;+w{})KyqyBVc=1RVBoN_0`D2
z=O^B{eOb3^lOL^iz=8U6ganWX?oD)hUA&7n{fo7a<}04FT(21GT`rk)cdR%W1Fckw
zM^30so9CRZakti?@0rL49Adjjj%<iH{41BeoI`#|P*n3%5F(1$ss;)H_Nx)wy9U}S
z)w>Ikkfa{<qAhktTNoIt5yrzCjaWu7OCCL|xYKmcD2K+=*Cw*GeH=ckCBuSITjeBI
zTa{D&D><^#D{2viw>w8Qmk~!BPB|5?cER8~jdJZdie?$W&&oY2QA4k7+BVNs_NtcP
zi-XwXzol)%c@4yS9ED~5Y6+46cd6#CJBgPp8*R*A?+Ww?74-$$7y<?`YtHoM&CEkT
z#a)y$n|AqRAl6u>m9BMQ<9pcYbj>?tF0(ND3Q4RZk@n+(=~T4+Nu%az8U5;MuAOA_
zKz+X4=As_W$3o`nDH2;)LuE4gIRUsT4;9hJ_f%IKcXcC5vRk_;1RNhq>mZ$DvstEa
z09=z-2}L_2DzTHZWS6&*X|_*sFBlmW;+`t;18Va~?ej((0A{v)W8$aO?i$+GO|Y*F
zf2DEWK$&&{fKN)AmAN%XeH;a-xyy4kLr%m-g^yeTnx5BFlGAi)BC7+86J4)|bSUA8
z%Pv`$xUVenrKj0^MKcA!CxcjEvtMsj(mcx8bro}Rd+8_Y!|Ey(cVAlMEw1j+kR@zl
zrcV*w#Qy*~BdFl#t$W<9M(rFuPTDKHCtat~klr(}SLe{zH*4YuX3pra2UAyK)+`-?
z6R0P#?NZ<uXLq3Lw-%D_i($`W#dHtjElL94A_2}j*PBCsumcRChg^eNcDms5$hiTs
zde&~5A2U6V!@8V$t&~qDqqcS&g*^>u>$*+N#*aF#p&`ni7z`ddSBHJB85}*m!@%p)
zX{(d?yI!<~t^WYDJmkmmFCw#a-$Im)&jXf=#g867@*JG~Kl;_J<2w^`u0%m0cJgb1
z(tKFjUaFUm8oTlttE1FBZ)d8m{$p%?{-9QTl0|bGc6!J5D0D)^FvAVi<sL7+YyDnn
zx~V<uuWN{IRQY!bN%yW7Tt|-JyCV?9pOtf2xU;_k<Ik%xf!bJ~O7*XYjt+pmGhR`;
zHdBH#iuA7ml6*h3A6}nYx(d=dGd1oj9mKONaW?l=1bWw(>NYnCtx0td4+D1wwJu&q
zmC(63W5=Z`AuzRcv%@TD4T%Bm)~Wd76_ZQff^a)j)+}SVz~en?--uvajUAh*Rip=w
zsoHw-Ju6nqWoAP*N@tqHX*N3sY@G3dT6%4Ut91E>)P(-@zbL3|(lNQ!%W0-w#sENv
z*QH@k;TgBH+gt}7m4#@-px;Eh=D9_{<yV@0yz{L7Slr&e)sve?bZN#*W0t(qbt^&p
z+fvKiq0MHu2ONSs8uZ4wDxW%nJq>bN&DFf~{IMdi<2~x(K4Th`6g9ceka6ok1oRbc
zodElzH5dhsdsc@z4#Le(7Uwx`l{$bqJ*gf{&;n&qZ~zq>Hh=omjNX*e+)@D;^`;Y=
zQgigCb)W;i1W+jnz@z|36w-L3y*C`t0pFT%q^0dZ4hEN@`qO^2;CQAN3Oe_qiU3;J
z@Z)W~DtQN-RxmZAqA^`fap{T#&ek~cYW=Uu!mA)4)w^V3;8P)u@eB(3a~yCvIP|Uz
z4mbk6D_4c2(j0I`-gD_*ZdYp+;Nyz*Fpu3ZnAG9D>S66rkG)e41$q!>3^F_Qrm)Or
zpUyK#+$qVbdkGZ4{{SYHavF~O&;}a0x|?(@sXIp}@TUV!QHA!U9`&+j3|_PjX$c+a
zGCQyzQ%>S0QHq&QwN?@@_lM_B^8*op$LO?NR%NV;LI4#Cmu^-$4u9A+Foxle7SkW1
z8hpr3A{<m~Fe=*V_ws$)Nk8CRQ~v<5^*00k4<A<)ok;fu7G|7-OVn1c_8y{o!5aSn
zy(K611@?I`FZ>HNo2v!X(lC?gWR@e0(iU!im1`Xab^FpG{{VDRABT*MgK)$C0Ba|S
zhw~aLQhf|^=NS}*y>s|iM7|YMo!3%l&?YE87mGOaCS&W2R&NzebuCbzW12a~6&WOT
zIIg*TD{Y*4Q%HT}snf!igZ^RVkG!U{mMRQ>$@NDF?mxUSQA;Y6<$<qDkHYq<ylHWa
z_br-`_+9~xmKLCA_>(n-O3{+Bq+-$KAg8bCQ$}#Ws>z>FroCD}5BW`%h7s$wDzz4q
zAmbSK*ejhhnWgS|TrtftKe?Fy0Kg4fi%h<hWi2H>#c}-W)CQM081oN4fK;POa(Q<A
z>!o6?(8bcfQ_W-W_NON+YJP=)tBK)FMY(9u4&OC;9C|9a%Qzm!oOFn>g3F43T$f>c
z4>N;L2~5B1C5>~`W~N^Zz&U$}$I`ojrNTdpihtN`lyX2mpi%Y7_77mYoMLDe2thM}
zk3=<PY%LXVw-R7~auZ!*+uDJi57v>|(lNB{B>Pr1E6$>{jUi4j*yZEXZIqHt!{_~g
zwN~fD)^`$@cy4*@Ulr7bgti&D&q}zq@iL4KJu4LCwq=|!@P3-$7O`@F+LY7N!Mb7`
z{{Uwv{0c&AybvxrQkYXX+e4FMIG^}MwAIEm_!N%ib5<8av_Zr$FSw4n)`BuV=%~%K
zP5dIJz;lVBsb7=JQ`-@WfA(F;k83_ucM1Wng=19U0g9I++Y|xJ$EBulRzgR8)T2+B
zF;up8Ush`Am6Na^l`co7D6p<_k7F_%3ot(#jcp1O=0=D;xvsIow^bjFMdYA7AU|3x
z7dg>sY(_+{^u<jDjk59?*!?qGq9p^BAC)~+1Hyq$z)^zAJY<GHQHrv*k>eez!h^ds
zr;d711RrFKe+@@*0{xxU7pSX6fu=DGq#8|VRX>RyORBq#LUFmUAEED52+7F+{uQsU
zM6v3#Z5ST4lvf<rpDoX?rx<c3M~riT4FL1dXV_EQ891h3d(<;%@_{GXl%6RF_oAfJ
zK}f*s#U(o<6vN4&69Y-!m!%~I06bFC9+Y&X1A_rh55-1LG-jBYF8T{(R9W_=%{!2(
zM)wyd(vvx(G?ZK&7~bONJ*cFkwJVR=raL&|jnv%IQ|2MjB+sFs9Mp8ZsJMF}`J<_(
z206_cr*d5~Y_B4KDlOo4r+KvQjJYMz5(UBHl$;K=7npNRENSxz(ww&yn>3q<q|G1F
zp|hei(nY;Jh}2;|rxogUVEvXe{>^zsi*3KQ?emKDt3m#YAN#f4ht?<0X0f$YP673&
zq04>hW;ykw+6Sd?W63Rx27EgZs(a?5nIVa`A>EFqkjo)Wo6bEdyM`I#ngCY{=N&1Y
zPy@9hm*XH*z?^YF$hP1CNrEa<Olky2jME%rp{Y)4CdutU#sUE5hG9y|L8cYR<j?~c
zWYY{-sltvhDIGxoKS990;8Gb_AOkoVr};`(r40*~;j#3leU?&kXE^i}fRQ4=^{Xit
zZ1GXY7>}zH^{J9&27oN8qNo6KOOAahsVWhUGfv(!#ZZOM6a({93yM%l?LZFQK<A18
z?MgWOXb^;RPf_#~%o9#kEszH^0OGWpGwDVc0iH;w4t*%N3A6*#G#q+TnoYShTm%dc
z)|?m-nnJkuq{R$locyM&MBv-G1E*T0CgKUsK9yq8w?fL@5Av^{&LMRcc40<0&Wv%4
zR&x-nezhms{Hy1Tw&gvlDG2j_-ZkSo5~nYC>rUgt@~1oln%0_SXwwbavy#|_-BT4I
zdscN}&8itOY^HIVmNS?|LJm@-gz!ddnT&9wwI+F^IqgUUbKey)IZ;qQ-9D8f9LG!t
z15VFsj2?Q@=dC590~1_#7g3n=l{w<AGj6t752rOf^~yqvy?FJ-E3!*$9eeh#Mx^<n
z8>2p?HqZFflMkEHtHN<G8S7SMUEaTiXBk<Ii3?zn`qbdzv&B|k4^Ap<@C{*C<G9gf
z&osi^Q;EnF+RO(Go_MCKVa91kN@>WDdQt**z^I;31_eFA$4rb=4I8#_r|DH4z~Fpx
zq@XzHcVf5)KQSN9y&uLf5pGV>PY3x|n-V(u*XcP#`S7tkyh^mkBNZporVM2*>s7Ok
z^*y=ykFe=psmwNCySKem#t&M%FF%j1RAGjwu!J<Hr2uh544Pme>rSTkpmE-S90pB0
zX&uchWCA<Wor6^&5%eCk)7F&nO(zvVIR;HkMg>BI@9R^y+@u8d7cyGjM$3X3utBXK
z5FjE64<s>Ce+tEj{`x+c+$*EkS2|)j#zD_DoV1byoW~r~Nau=C&(ed^v;nlZ<20DX
zDdvE%hw`LT?MvF5k4gZL{KA;S2R*67g{G69)WA%8;)c#WMFO5wu<6o(A{6Mz-afR`
z`HE0*b5aEEF@sUK^))n$`=RUBtGVN@X#jES&%HTvO)wriQm!hK0p$DBN!)tSNzZCd
zw7@%xa*<3p#%T2BfF&mxsLOYxEPd&@rEnZiG{!im9G|5$@leJ}gDX*$!y1wj2{e*@
z<3J4FeR-pIsiu%<rE!l2l>I5Aic_CjcK{>~lmo}5Aw1)X2TDu_p&PmB?Ou=JM$MSP
z=Ny1*&DR*N<H3{ejAyPZ=X3bq4|BH$?K7y8{b8mP%|2Xtr`DO)zA*Pi&J8ATXeTt<
zU?@EERc>r8?*9PRuJP%bwUe3w8R=R=q@eE?VK}FwGsc6asN&!9V^112hIqD5#;){U
zn56{vt$w#(`QP40v8Vi{QKeXe{{SA*{#7s7EYyFfj{~MfPmp_2Qt>sO@_%_=&K-zF
zrLgG)fA`3zED<UBV?qA_0jWka)Ot{AU22c*G4e;S!5R)WFa7gQ3ZwW}@}QHRw4icp
zH#t6|vJ8RQe=0NWOMyv_eJXjFSU(C53mmODdS-w*JkiV+D_nwLZKH3!dG-3@{!TJa
zTJ%|lV>^8-n3qA4`uMY~k;VT2Jv%jhMn{;^!qb<vXPb`0O0Bt0ZYW-P5g|?P-*rK*
zmrL-@aV_W`$T+R*9WK(w6-d{12UE{AcRjIzSY{dhYWIaNb|b^(@TaV`WN|?p5s2bY
zsyb8fI#TnFd8E!dSI;>)YR^e4Y&$#(Pr{6fKMIkGDROwG=M=f(fEPJE=*iC%nWJ?p
z2(bY9tDEtBT*Tgo70|@zHI3rmp3omhucP6qTNKgd=8N}7CkG8zNi{+bm8$Pm$*<F?
z>l5Q@d_!b76;@6ftvSv)s<L(UrotmVYAFUsYL`4yB>Gk|Hbf((9jQ9fk9vba$-x|R
z>sHh54u1-!xZDL<Q^tQv(gt%SLJI*_x!Y9}s5NLDuThHK7)XigyAHXl5>yZAQzD`>
zjEZY;bL&qW(_5uv%}~lr(o?aYts#mCClxY``cx~%DpeWv#W;~7LDsB~yMa}ZWQwu}
z%UdHE5k4?RGHSb=995|}9Mx$Lekn+(k%3HZ^!^IcF|66DBmF6O%^Bi>Qc&THk6M{W
z9<>O?OuZ_R3~~$_vd03e1Nv2kY_2%15tA6_k9w@#b5>;My+FeUz9~q!k)E{H7!>o?
znBKy(HA6a|N`HKsZ+}`)aC=f1<*C!AI@NG{ikS{Y1hQrO>5>54E7Wu;1L^S|`v!CE
zn)1e0+Su!ifNRq{Hv8-&Ozthsd}kHM_i9J2mOWZD=j0zsqT}cK)#<ubMj3No0*`F-
zIDi4Ur>Myl6df^+I`dPmJj_?zpHoj^9Zus@LVAj0FJ9u20aNWkzQv|eRDefJjMuDq
zLsWvpMO=bOJrriVmNU76=K;IdwD=U*K9dw6MrBd@)|B@=+}-}*>!NQm5hmPZXBCHW
zd3AHBtS}>mR^*P=(Ey5^oDX_rQNy^rU~}A7=f|;BIEU_y;C{7A$#0F^jdOt?@G8{T
znv7O)lE$57c(+gq0L20#)e>`Uh;x#9ii1be-qnn=HtAcBpsO<KkR{UFa$UOtR%V;Z
zh_D%;2=6Q-y^Kcf@{Vu~aNaf4zq9Px&IvMDbO)Ndt$2oeM0Zb>m+te{yt7r-Wz=pw
z`2h}l7OZMZq3z{(DNcOy*r9bc=?`<?6<=uUNxv=6G~>t>iS`jzRzOWO4AS?f0tb2v
z5PQ>D^PgH$`KZ~6??AwjO((4(JbTkfIp&a<XFcf;CW3k5j`^fW)9H?t8EmgwbcX{V
z)n<?{6dB5PB?lza!*f-U^WLUYnh8_6IvvLqD)#rN6yl`^f!FIy)iPL*O4ZTi*{H{!
za>M!7Ong<#88%(VjAwAFMmUAdO{1vzfzFH@wg(mC@Ue-P{hSUf*8FEG&7or;{Jks4
zv5b;ycy4?JRcSPJdS&UI#9%J`{n6=N405qJWFrE(4-KhpL!JiQ=hnLRlVHge?qJoS
zbIHU%c#3pc9C3iXYd&ZlV|G@??f|K-u9_$_vvFh4Rev$1l~vSjUU6M!1^XyI#UI)q
z13mlJ=8-7WbwqH)l^j<ksp?NU`3MdhxUP@k{j{xdAz}A=RJIm1uC%+0jY4@M4fk=t
ztQkD<X*4erjjTpZcluS}X1a}|A>(d+>nh+a-kWmE4tF_Rky51jtWAz$36?jE^Tlge
zUx6g~;IQeQwU={i<i`^LF`b|T)|mj=B&RsY&oy9lA8J^%r*hl3HgV`Gt@f=1OK*dp
zVO-74)XieZvNq7!z%`X|bs@L;xW`&UNa(J0M3+}r3>Pbm`&F$rbdu^+BofQlHOI+u
zosLf)wJ5rHuGN-854A~rr)yy&M%OX!+&SW}>635MCqs}yt|r%6xV5}>avfT)>AoS^
zEy_z63VH>gPA6X!k0yqU!0wH^dR2SDhKA&1h5<;;W@-BMxw4)Ybq&-h?N^p)uC!3d
z*(llI)uv|RXH6PIc=3^)>UQJOvKk^5;xo%u{ro5ez1p`dHWBSvw<;sP-_c|oR)CIn
zR1IiT1B!~!VNd{YIIRN?$>xVW25P0A@EHdrcB!#xn(@OVqhjPHJJr~%;I>#p47Ned
zQ?#DuB^!dU_pLR)f#!jvQNbW)f(te`AMr7jeN#BCEiO+s*77yy2B=v)CsdH_0a<#V
zUMlXJGOX8tV+0e&<5|eGS$vClB>o)KH|>drJAqCP=E^On<lT@nP)<L6&NGTaC|^6g
zGGm5rGgT$p(64>Ctrt~j$Uj=knl=&2z~EL@z6NiH_|Y6~gPieKBa|@f(y#>PB??cq
zUbK;)C0nh0{Wb3%<yY>VR+O9uJ<V?>I)0Urrbn_7k?)$;Kuv6Nlc~t$RfQe-s3QkH
z)nx$+4IvLvfGR*Y3S#x7mf;X}=9m(*>>O1qle{08=AI=7q0LsEj_xr?2p@8q(zPVT
zS?)4A8oOrr810H+Pj&&Zmp|RFGP!I_bB^`tw^{ofr~QLoUw4sk{{Zh3SXMf)+mDJv
zky>jnmu7nw6_;#sM^RU9n-GN+6qcsAsah5)oHlAQFby=Z#xqH{=LFY5<q%HXbKbMA
z2sL_Q6|hfg&YPT`)D0C64^u^g4tiBbd^JxKg1m7+$s2=;tv4(?)UP2v_^2drl#V|d
z0Hb&FL~&FR@}(H?eQQcg5JAOb%Dz;DjN>`xfEHy0a56pWdnRIs(Rio>h60ur@}vcN
zPzI9SD!<?4cB@wRJoWhxtz*c!B<BQE7HK2kAL~FJ5R@?B(;3MXj<=+dyCWTH%HAt?
zq$5JkZz|**e5CVTm7UQZSO?r1^YJ(z#a(8Rbe9&f$-B2&E*3irdE{(1bM&paO0wa)
z`qw#OIAzBbxe45&fU&Oz6?o=?aNG{H1OSX+@mDqyv;h>0zA#5xr0iEa#}%OEm2rxz
zI)+n`ObppTe2i66fMgL@9SJ=uCPVE&8S+P;m{dv%)#m{_XX#anFF2_f#CACZ^r;k_
z^Tjnz)~7ob_M`>qCVVfoYC|sUb*^z9MRnv6>01y;HV$xUfu|c}<Go&t@H?8!jkw%;
z)%e?i+JF{SAe?kHQdo}Mj%!7LWXF20$$|YTftM<hF^Z=u;Yym*nSNY?DvZgxCOzl_
znY@Fq999(Rwfga0ZPa;;{VSZhh#?^TMF3C$78PO<xBMy+R5d7@BhrwIvCXxCQH*}I
zt7~}M#yc9oNqXnjw5=Zw8$4owI(uu6K0N2YIH+|CkpdTHBWUUCQQ1BeW4>!I#aC?#
zEGzfh3;0k5NteyIW?_uCPfFLb^d6OiZZdFB=UcYPuw<UKBRWku1st6Btp`<ncC76%
zZaa@cIISK7XRS~UMe@(JScvZ6ny#mJ8O2VEwR+G5aviUaT8;A2vU=3At8U#)_wQ3U
z^F^jq9i?*?McVAXl^Lsd!)*D-TB>^2=Xk1K%Cw+;B`I@3F+0-HNNbqXr>WWfw#niL
zYY~d`4MNUaD}xiS<BIjZn5>O+MUPW~nLrZ`gjdw?=5_TNp3bMiBhJh)e%=>bqmJ;F
zryYi(&`R4@Zd9LI^kpE|k=)x)XLhJl_mQ|^kF9!!mm^Q7#LdsjIj>8Lu+*lZi>Ce~
z463A*T`BZ2yks+{8sV*H`z`Df?atQ0uJgs?I$8O#gI;>zj=g)=xx$fC%eh~f=jPII
z#3>`z>@V%_t)r3|RktYMRkOjxc=fgQ&4jBYGLRRIy{pvptD|{i6vXn#2?D-Ph;kQz
ze%cQ4Z1yl1)rgI{qWvAH9VqQzCVBykiiYTJwUGyLQ+oPSB*=}wt!Yi#Ns~W>;B0PY
zv6^2ZZH!p_zO|vHJ>|}#?RJHC^gWF?N3^$Z5XhHmJgkkR*I%r`Yi%qK4%H;%j`jCc
zY|-FNYI&}&0kqUEQAfy5@6Nb8gPVtO*LU@=Lh);Pcd{|`;=J|7`9VD8hHKD<#%$cT
zfGAu5eQQ%jP;S_JW~j)m3`#n2$f>k>gjcN3ox4UVp1^idoI=WLlhjjv_#9((boS4_
zGQ*{FxA`|p-S=@(0A~G#uplrP&1$>=K*hRrsI=IyiNB@=Sk;_c+jqgO7?GW5<z{tW
zF;~lDENdFhaArGBYTVNo!h?ZWOLIgQ6Ewtx=CZD=TWKP;B8)2YP+d%@Hh>KXXDKwT
z6O<%^DXV=jZK3yP)~{+d!e!lz9+?$^_IZ|26}bn$dZZ?HI%UYWo;jRkFKX(bzqY&$
zBuC~PFs?Gp?tljCSM)ux+}tMMo4QouVa*e#2<>)uv0W||KJV7G<C=ST@=7wFdh@I6
zYxv=i$#=Ohan33Y2UM2!IW6S9`D6KZ?)$aRPM;#VrAhN0#;bS`d9jcjb_X@hTzJP(
zxwCj2h0hrj$t8x;C-W}1j9_jx&NTbUD!}{FZ&T91QH@WCnPl9=oaFT;u4$4gU8!zB
zH9#EG{NE-va(Gdkik7*()_V2gy^~1v-5&17;ryuF2{HE#d4I%hH_O!ImB7bpg4@Iw
zhV=|SVZ)3Ny{lWrqT>5Y^XEbv9mPf(g$fnZj_1hNa&c#x#-tyuXUe#hzO}5W?^LIY
z6OmtOI%-fz@)Wfa-7tsgRUJrn7|15HA{aFZi}#1$nwpev1d&QaYSTdwDCKZ!Xmy*|
zo0&JS_eiCce{@HBs*&XLT-9h<q>4=2i(hnAGbVj;TNXYd)8^c=xej>4cdkx!%p7$U
zUKGoN>CH__4NH{;&cw?Ugfd8^dzyI4k80!YLo9=7AOXc((=IMd!CF=*4@2Iwl_@E5
zlyuQZ=)-Gm^sO6BL`N>$fUJj%);tq#Y-2p)wB*w+qqi4QAy~SDToT1njJag&YwYH=
zMfvPBtCb`{8#lLF((vuwwwZ3$;x-A`*E1O-gltv&X<Y`_>H5}@oF1u)PHkF7%;jF`
z*?A0dD#}_;V`8yoan`Z7u{j2tcdA_5TAwaL0PR%Sk$qFkZQ0sA>uN-f>qwF~&i32X
z*DqrvnvJk_Qb%*|TNWuIBb5bW?NM=@jjoGnrq3nB(QlV00~y6=rQOZcN9^zwLEjjy
znV|jWn4FS%s9I^Ww;B2h&Be2}m1ssbF;16zG@re=D4lUrF^1ATk(JML-mFR)vKShv
z<VTae8$Pu>jMwWBGc{YSmafCDIIcCxXJhJXv()tDxKH)6D*Fn-eFcXrdH58qDaOY=
zYKl)o9FCOmdR57Edx-h-V{!V`Ng|Rgd7FN<sn2jN#wsQ`6or5vcxUTOGB0-@g&~eP
zrkX=4dY{UZcJI0v{uF>i%_rkht+m5_+j)rf2x;r5-oM?mxIgyH(P3Q`$;CGu)`IAo
zoAk1ipI$0d@XoN`^5#d?$N14;xs{4cR_O4SuH9mdey>sw2I?e@(m=oPDl8W{?v$Z(
zT`KrC;G8|=L+H7y3E-W_okQ!0{{Z^*0m)<Wr2~$&+7ATUC>!r*C)fc}$Kb6zwmj>W
zK7@(}aNy^?10;nXF+BjULSF}Iaq!VIdhU?bt6vXkR?;lVYZm3?7JSm?k8+eG&p%Bg
zQ;=me`<4fx^37;z+CHfT{4z^nG;96mQ;PKj*340b65B4{#-W?U2+8x_L61->eWXhE
z6(2&9S-+O2Yi9$sU$eI9l_IIOy=}<*cR%ckjkWlfrPQzN1s>KVeNwCYCsO)X+pO9l
zAVA;6Ty4+8o6$S@cku;cPb*J<5!&aOE<f+AR1<iP*}vtS&FFWUsAD~!!pi>6t1q%-
zUU*wlvbixYmoUb6hQ%~!I*tZoh=0KAMYa2Kf8)@x1G%O*h)Dakk&ni@Bbr!0v8z6X
zH1PfD`_BUXTQw?pYHobXqyYZ_b#qQWB)B=nykqdHvg<eUK78PV(N>3>NVw#cdXs;`
zB1t6QH@+gN2ZP}qZzm(!DyY`A4j0dEeW}M+)DZsh<z9b`5m^5KX-wby9(FXN@WrHR
zH?_n4PAWz4?SVYR=l$s`3QbD#MnCBi4Ae&E;PPg2ea$DB)b1sczNb*SE}EZu+CRoh
zU$E&3!G_d*PHU7hJ9T1n?@eG2UVgQdvGre5su>(Qv#lT5aF3O(Q|Kr<j-I_Pkbk<B
z$Y6U=00y&o%8#k4$tfeQ{@SoykF>GJ`!v(y3l;u3o9SGi28x%8sQQ|$qJlbh@g=u7
zhF13`qHhvHNBnu@d$n`4cc}LB?r5^SKVx+GjDdx;Kt8n_c#`Y*V1#}Zjh|`-ORYE5
z(Pj8`(AGX8zRy^|^b1kGy{ItaP^Z{dZfMW7E_rt}SV}AGms?lV7-Q`(O*)nHf6L6D
zom8L#NTtro`n@IgPeAZohJ8PCw&nzbn(EYT`9R{h-vT}@q>S|3de>*4di1Ef!1-)^
zd22L<7zFW3ImQJv6X+>Htqu{udH^XH5HU^%(t<@WAv^bWpsODEr}yhhezXihAE7i9
zJ?ZLkPdz>80udNA!v`j(1JaO_ngm9%0BMq1tb`J^I5`yKNDT34p|iAA)Lo*K#tkmg
zxS(UU@koBO1I;J^jz?MmX&)%4%A8c>eiVdK0uq@3fkxgcbpoTBFx(ve6o6{3Jt=5a
zRa{fZ^q>fi6q;w+3bx&usY?B60swLcCV&|vrB@(SD|I1bfydIV?8xSVgFPq$ub%$&
zG>&^3v|||QK~P5mfG9DPbW(pBe#RoM2>Hz^7$9S>6b?I{SK<_8)LVDnVVcM+K(3F*
zF@)5?2L+39T-P|}yxH!3ZXO)e(-WYj#UTWCrR`93+S>*_si&<eITV<rXpmAGTv8E0
z>?TbuB_B#d3NuDBC^P_Kl9xCXou~n5qKW`0qKXC-Qc}<XMIq};KwLY}D5E%}0YRfQ
zQxKF2J?Nl8_|Rye^q?*Tel$_mjOUsJ$sjnnfxRRKy>h_j#wPU@<OJ>7eHe3IucS(3
z)1j{XH^O)sy45pFpzTI8PC%#cQ;AG*T^BquEa7PzpRG9K9qEjH=oq_mnnRI5<ME^3
zi-4Vb(@rT%DDP3cv9Iw0X<Y!l1vHLo7QBQXyid?mPN4v7eB}QCxkb<xfKt5FU{JC~
z!|xh5E`N*bid@Kc6saScXiOg1r!#^$q#5@7O)g|R2GK{9r<{T9O=%ZAZTjvN15XP5
z>7xhz>N${EmP)DP`BXblG0j0HqiU&>a}fUkfmKJ<boKl9$xEFFDYFA1YPbMBF^cBm
z)U0#FvJsx44Om@9Ct$Iei9V=BL&Q^Cv8rvGfMoWk1p}!coo5GP235Zra2Yw+YZs29
zzR_OBMfWH(^N-G=^I>1TCM!I@%ExU~I))np1uLHQKiU*~mFy&K3#)Pbd8HTdrg5Hq
zt1fAoW84Cdpr#2QXkm(%n9>ic$k!KfzeRj|ibHdgg+~0VIc{Yu%Z&Xh!b;B=%bLnr
ztt4O7WLXnAKkAx;B&P&LkF8e>LB`|x)T0d8=O0?edCfJlAJthPYmfQo7#{6Onf(xc
zG~8j9r#LDrC!Ma5E9$;wb{8%&<{-}*6=n!Z!?l|^>S$b4z~EP(ip-sRd#2Rr@)#l{
zi&9WVLleoXmk6r)6kpk~x{hf3cJ-&+M#`z4J5t0{RTO1%qOEepzs(5dowqAdS`x^6
z)qp-zT-xkV#XYI;f2<?cqFx@K8N{{CC1H<l38h|rsB?y<=A;K4kwix-MmZE?ifmth
zZ@n-aPu83X08<-=$4UXD436ytma+rS6_uvl?ni~WBDP#*2<~eN3n{IyT%J_)VP38q
zl6ZMWOwL=P>YPcMwoc^EDx)haXBBET4Hy;3nL=RW=}%r$G}1m(NQdRAtEeL2JEIhs
z;}np#V<Xa(b66BF1k+{X29zFXbGbR7MW`-NC=8=M^=L?vdJ4-`20UVwO8_yNKv3~z
zfVtCOW)A}+@vjh?5}Ss3Qdb@8-L*aKV;~%#TJZf!HiuBSL&;a`>tB1rwRxyG_B{Mz
z)iR#k8k#ICbKauQ6!m|Ye>(akaI#n0TcuQ&@70+B0-%&(g$zh$Xzf7$bu362k>Apg
z$bXKCbFK;ODY&2o1c6J|leHB<1QEqI88qrbGwn<S9dboYf>xq6AkIZ04Ll!UYo@x8
zU1((RTW;=anPct6bb4}`^n!;c<RIpvr$z@pI#HhVF9eTHD60Vv;YNMv???s*Y5)x&
z89tQaG1`#y=|Bp<c97BzJJY&T0fbfiEVMf|<mZ!*YNUF4R`!Uj(K3Y_zokV<a;t%W
z>9Lq&6x^KggI2W|9t(~}6rK%J2L_H{E#$O#HD0HImjiGnp(6y3PV~k!bf+o93TWes
zQ9ur3P5N<8Ve-^@!RDwydFx8N5t>fDMFWw+pao$}@0ybtUX;vIU^j84Cy`FT=9<Hb
zmNCi6>rQdaHZ$!{ZboTb2+vAfccVOYrsuabhCAs<)SYNJ#Q|Y5aYtG@QjWBk3a1_G
zuJClkO|<pr0=XWwx#7!&g6wYNHRR^h-0<$lP8r%~qR)`yJXB=kp0up{kT!A;dT2H9
zmOg<yp+V+@(=>IY=|IH>jP|6Z$20)Brk2Go@}Q2CfH#)yQUmQw0|erop0qKGOPuDD
zIW%WEsR1_RigDtK4_XETj<n&^-kL=K^FW2hMJeP`cBP~O4E-rjJ!tDoj?@6sIHkv5
zT2L`d-hdlNQ%XQ0jC)WqxaO2mON<HtK}vek?WD$dpa70KQ*qXxNsQ1TV>oatp7B(t
z_i4N4Cy|=yK@r5#NOq_lO>r8%=i2WXgKkCPO?`(9VVj()wV~qXwO1!8LNE1$By;In
zBd2Q4jO}1+L358v`}%tyDOYi=!0T1qb5<B;tGU6eWW<Z0sNW=1ne9!Iv5~w=_~Y@T
z9MRLQ9V;_I-3Y5o$jwz=y?WKCxk}QR5+0`*CaoyQs=vopqu~c$ohx)<F^sttU8>7{
z(VDF%Et*UsN7ub0bI0pSI#LnX)=bqA^riQt$318r{pv~-b*Yf?=}`C0N~8Y()M=t*
zN~b2Qpao89s_|B181KQYk%WYC%~f$$m}i`tuO>%sD3IbrX{}B_Tv8FoTFILtEDX|t
z(vXg6dXIXNg&Z|byo!T0G9Gy~NQOKCRtF-h@tU1a;aVd(2yu>T2dUfc@+t@Rp^hw!
zo_MC3b}_&-)Ag*GvLnYQ)YA8*^`sf(^`tRIaw>Eg#X>zlTA2^a)1O)iWQQdmX(5W?
zO?nrD-CIwEhDH+yJ$)<Bi6f_4?tB|A>ktky7^yk;uax4deAsKAmRkMusFYw4)~G)W
zMPHXCjZ>9y)%na%c=FqJ&T-nOTxW`>17<_$MO;zRzUs%+QkI2)GAc90Iam(8#Wm02
zNa);>Bl9RdE7-gPr8n4x+>&JHfW0fmqjIbYk+^iPYWRD6B+*I|Nm{ylo^EY-htTV9
z?V9e*;Sw@#?mZ~6wib5cAmzTbfvk9+?6V{>0$XqdR?VIA-C3;LSxM|`p!pdliu#6^
z_RE!allMpOEoi|SK@y^H6jm4fBuv`TuuEnkd1v;kdbR7@*t@4)w8^ocrWcut?Jm7Y
zsaix4lO{F}xvmRDyS!~k$;yC!Y;p}~_?qT*(cR;dYvZS_OteM9H<Cv!<E=&qxbiLA
z<zC>|p362{o_l7cyttN0*vjWQ<DQjCoH5U8<&(Mg*cwWeH4;@h6#dlzY*X_{^iw1U
zG=SjqQRgE$r3ab|xZ>PXPa~x!;Ydi$Ah;7odFe<<$u$eP9129a5|>f!Q9S6U?{ie=
zc>v*0*0LwMkywIyP;uAAdoy-v!Bc~ude3P_><Y{mhZxDJW00}UI~-ERDw`US5muCp
z)hLfcR#5UyD;;#@p=Db=DpfeDpy$0zt<F2pbwQR<fIRf85jhe9qmX*lH0Kp^0rQVs
z;+hJd3odwuX$FwMwtie!p6>Gi@0#>Ycqr0Y*b+8&t_Ilwl|lMfRWsnRKg4GL0ETU3
zX(e)Sp+Q`BJl9O}h5;C1y=omk-Z(A(Q;dqSDUF*M#?Ios>@xk@JWBrn8B*tIkOkx*
z^s2VV_ZKJor-AQFB;is<4aq;HK@6`B%n`pi2DdUbpwm_f31AqJo@=e}d}S8uZ@Qpu
zT-G(Du}G^Vn|Cn9Shv<v)J+PJvAa<ABUW}6-?`JInT8pTDocfoX-N*;w4<8lV(~05
zrL1n_a6IFot7l(<=e7BUI0v4UlZy)$b*&|S&u<#Xm(Fkna<^8mZKym9gdLs5cJ}(+
zwbrN*xeK(Bky3d!H<wb+Ax8Ag3T<e@$C_H{(@wLaj2?SZL!rF7T+OrYoB(UkEo`h-
zJBbTN^Lo=FwzH2(l|0}~hpu_6=0myXb9i;1O-XQ7!(*O?nRVgW);Jv_0H0d)d2Q@s
z(qoO8TR6^In|_vpJ9Q4e<WQuCc6sF99i1-WDUw}!9+dC+N3LSk3}Ja;+n}!Y`de7_
zD^efj1DsS+>NcZU-Mv7?0eKuvr-!B&_Xx)vXL##VY3Xxo4blKY1Iabi!FOymN!xfE
zmZ?QOynksd$}`73>Ff)cltj-qj7cLP<Y(5aUPy+@8BPITTB@3i5!g!~ni~Y>sL89s
z+G#>^bKG~Q&XD;TZ%}yB<~exz)NVDKpDz3=;|wYbtxXNOah<($+OO%+$9UpoC4%vh
zO-V3uX<XApk=UXxNgR4rl($HPB4rHyNCTm(w(|KXaD%2gRPs)+*@<UBtmoy;HfCkp
ziR9Frd2E4(7mgd6*U_!!X>Ox*Wo~i1ze=+{p|?y+%V>ki9u6_<RIfG1mf9=(Xq(ML
zwp2s+PkM$?qaC#E2iezd^=fIcnp>cmRc@Iz&0qMkXM|nAj*JTAA4(g=kzXQCleBXo
z<PHr@$L!hBHkd`nl+po{j2gt(pnV?M)V}PThCS)}j=cr;nl7T3Z1Jh(dgi(N-Es9h
zHi~Bq-BpcaRi_4x=tag?F)lBRvS4yOb6q})H>6y3#c_!cX;6N3=o$nYgj^h8aqnIv
zRgYSvu66dwwl(@zgd--Y#;0QYRhaoTW+k*4IIAeVGf+gh`qi9(w17z;V65rRShZPp
z%V5(P6~FrQfTSIP<MpQ&&pgzwp+#0{0B%Mo88CbUnwH(i9P?Gi8G6&ATsA3ze&%2-
zCgf*jd7aB<;qjak-n-2~%vyBK+^z+A?1Y&KtScQja^;MEY@iHrQr)ogFbzki2T;xr
z0CQ2vCg}-1b55GFGsVj8!yQ|<Lro(Cnhb}xN{&b3v^fYa32v30G>0ax%O`%-pKw9s
zaY$t+8FF*i)}@a>{d%lU8yr;j?g=YE4kVQ#p^zG#$?f^nG8~UjT3}U?vIwd-Nxd_Q
zxgpD7)KXxn9cTk6DOSf!)QU-N)cI59qA2p?9WzX0i<2XNcY#V%CxOjDEW4bZoc67o
zC>D4`hq%oE%)=97IH->v*{*_H50q^mg=XAYx}0tA-j#_n)!Z;3n&`Ygd*w;w5OBxk
z#bWs^hwkR4wv))XN9W}^;+2MaW}h%=0B(Z1OM9T0?xMJBJApE!x#~C~x9sO;$IZa?
zphshEI=b;%aIi68^{!UdR#^cbcDF2UOE%8F^Z|XrBav0704{M?<Xoo}PD7PB%>ZXg
zF`c6oPj@&yYek~Uu>7i<Ap?=kF_q;5Zb0U$Dc(qB!L24;(ScN?LauS%kQwuqj!;44
zH1%LW%}(i&^RG1t!RR_t0pN^fdWydUp`r>#4P~PI-D=Vuz4}rEdI<w41XZQp21R4q
z&Zi1kR;*99FbT<~1^AzGQ(1G<y+s2B9CS5jf-)(AP2mGQ>XgxyZMfm9Ro4|t;xco#
zfH5v%J6K~lu5$9+s+^4ToY!MKEX%oT68Z)p<$BNuBPwlX^r%4{Yf|#xA2vExW3JaD
zr63&}43KK{65x(|)@V63W(UUxkR3gQy#{(7l|#kW?k*yka#BSZ2eGEvT$FG-9CKUO
z7Q<E3OhAJ)e6DB_#K3Ue*7cj_AdQ2x@M|VJc8$s~Ia9RpT9ztORrmcU8Pe&+w&8mW
zR)B1eLMk0LJ%iUhYH6Y<{BS5hAz~k`T82TKRU(-noa9uB#Et=`1<5&6imGzGMNEfs
z{{TvkL7q0y27U76EA;JDzZ%rMjGJo9>IHm8bxV^Ie&@e~mFa*y(V8*M7{SeW$7RIr
zMlf@lQPfdP3~ggVi&A8ie2%T2D@M`*ZEmrSfM8XD(vGIOr;M#SN|c|vh*aXAGDc5`
zG}*NcJft`>dRHa?00?fOCNfn)_OC<dttKnb%k%732A{K}^f{~GsaKaY&ILRVcFZ?i
zE<Fn7yB#je>=tPT{o7OmK<aAnUrIVs$LE-=bU7<M3ZaChLs%dK6jIVxiggLvn<&gO
zeJS*Zqi3glRY!44W6!3Q;nbgL%PT4W0D8L1twc?2Y#V8H<LO*ih^B(eS@U6$i7nIo
z{VJpQiM;5gB;gOHc(1&}(`pHyKT+CD)A60Z?~IOcHva%h^VA<ae(a+kh_0Vn@gzE|
zYKA~K=e1?n=`&r(j}rqPa-emuN)gb>$mw;f5;SP#jWThZfz5I@_vRMf$BbaFabCM+
z<j1E7F3^&ogO&ELCh<qv#<4Hh)R@orSGlb{n_G!V9lnz&lFL50;<GPC+oi@ZUak0a
z=T1zI;m<v*KUj`dk-WI1fA?0fhT~^lX{g&<!5L>#-~o)(T9xWwMf;=1E1s~?r;-Jd
zWMF+UQp=lVIN*xXYQ)9diq-s^#s@hkp{=M`H$AJDhIVVh<mW9~Q|dt>*&kEEBC%%X
zmCmBEuEgZ~RVV}8NK0}mrIoG4+Xp$p^{ugQ_IQGhz3Bl)bt*C1u<othNp&47p_Br7
zs*@_Pri50qcJhY)J*tMMEbvL@!0aE_Ju68REoW+qNc#1wsjN<%61@3Yk2blgP72F(
zNX9dYpps7$vqvi-W0Q{NtTb6_Jgin1JH3e?+AbNg^GL@&wbN;`d65o#S3DyFoL0V+
z#{qNRvzj~bE0R_=*NVNTglm*m83g`yQaIU<0<Kv^;_VN<Pd%$CEe}eoT&(nKD+_4g
zM@VA_9ff9i!qiKpIaM4hagS=;vH;n{cMrSkQ0s6sx>SHJa->(u(Uod=#e432%~+=v
zkDldSlCT_L)jNUn?(S=5{=)GuCjS6Lkg0Qm7O2UmUqAf0$zQP1oLwaDeC(B^Q;Bgy
z51y{YrD_C{ElB?Wd4Q>ohp9g+ZiD^@RqY|%c72SuT*hiB(-pb@00{N_41VMv_o-9D
z*QYs}A^2vpok~}|#-lFAD~-|AF(wZc(<g<dWAk0(=^aX*4G;IPB;a#|#YFKGuX~iC
zC(!0D6MoZ<wKbybkt?Sj5Vj}*xS!?YImJy6hOBMm+;_Rp@xMyWc&a?txoVY8#-4?w
zEb^%<@}HaWuGd-9mApOWfCdIQ^{hQRQ;x+|VYgNzoP%1DYuC3>7#7SRKBB%S8G)}`
z5$z+f=|Zd{8#52Xx(eJ(l1ib6rada3h%8>$S7_kKLaWEUbTD6PcBc_T5&{0rL3DL1
zxqQi1FvFt-t!ZF!3a2w<O1w5OE-kekKGkj+H^-lucI4uyUEa0Lx&Ht|nNOfY&2^3a
zt14_SxqgD2x@FNHGh^6Sr%shs@iU%sgV@LLPNOA}Xznb?k9YA5S9f)H4EBX$g(Fk+
zu6cB4J!CoS)}Q^4o~}>)3c6HUF)_6%H8q&6x0AQ2$*Lk<XyZR-$DwNKmqmpA<DacN
z`w|aRnyUfLBi;;o%@O|qcAl~CIe9Vdw>8s^D%}ow{Hfzkw*>sOa)r)S?O>1{(zyfC
zDmT(CdKQ%a71=GE0z7OO^rRNBgZBj%3!F=6c9J#(GN1SrHM})q=Ph8&eOZlnLJ0c~
zY5NgC;+T#ZJS$<5{{RxW{-&m13t8vo({0DqYp#}9;Tdi!6}pN0(7?c74WjV2uqpM~
zQm%tC4h%nn*53AP{MZJVWXBt+SPY?~-Hy@Xo-}EQ`J4*BB=5Is6II>r&p_sj0SERe
z&&@EYQ$&CamLFPhj_mX0x73=NJA0<V+4;2=0=nrIpq<WmroNqInJniOZLMw(R9t_(
zP5TUoy64iE6p!{&54*fm(oH-zQVf0-Yx_H%LZ78bmOKJ+_)%afJ;kUw7JJY8l-Z|^
z?b|lqUI(RUHKUwuYynJ?(6lZcv&U*pXjC7(d4=543yDE@IAg(Tre$*3+<!W^sm5c!
zoq5Ld)~OyV&7SAkP>gvKu)bpx$>h=!PkywV=9B|jogAn-(}6T8B9xraK2!vZ=NYLa
zk|xH)+B?)tDYOSFCs|cvU}FTH^%43~XNoiHK<tohBy^ym&q|&WzP!|hGTk`!r(-zO
zQY%Fx!z#$Q+^3Ay+x=R5=+z_&0{RMqP>Q^Ds>ISOmM>7v1k*(rprP5M%^AfdAQqB}
zC;+3q6i@=u+LDR@T29nb&;n6K6vPzpdQ&k<I?xAU;AsGsbpHTs;C>a|FWs*^@JyRE
zDRcZp3iL(bb+1bg@E<9fD_3Efa5(Ki9MX>2t<N-0^b=0oO(Tzb1SW83&op4ufZ~gQ
z1MN=-G>b}j6bw*t%??g@6q~(2DskuEG=w1FbmoFFN_ggs&@f)K;uMV2bBa#=XaHgF
zMtP>^C*GBv6>`mwtpGTaicAtIzG`~X@7>VSU^!0H+Z3eJ6oP7Po4WL=3lZmzl$*X<
z90d2MgXD3FU`QY4{{R|RZa5VQ51uH)`ry%U9lf`8sRYVLII5u;kKU&nem-X;(Qquh
z>fJF+GO7L{P>5GP)P~&&%>Ya$PMd`SMPtFuF=2^E+#a+9Rr{a{296iT(c<zp&sR0c
zH&b1wj#C~~q#hV_?Zt5>yxN*cpIw4?qJ_xrDG8)Gq&cWN1?xw8Zbmx(w7CIE$o%P8
zcS7fiLr54C)KQ$A08V`c7GcbV^`!4kRboI?a($H3(%#|z<+R8C0BGcwVqHisq;yr4
z({%^V+Zq1=@0yTknzNsl!e7R#l3j>(=`N)n^mCfkUkz(5($D_@9;p+;ddr{n5wF$h
z`ziJz;^?omV;_1#YoK2T>Zk8Du=>3{d>MXoy5i7(!0D<p6UNYAXy-FUbpyeU05a-O
zC$0?#!qzB1d8{DETw<TFnVZZgE~hU>Yo`9h@cIwl>sk6RrpaO9NH8B#k%{e1VdO*1
z=%bs@6l8je=!^I^5Hmcke;Nj-;ONK63qCs)t5{hXJl2{y+^Ft9I&YYR_=R+T@R0ak
zG|YNteTWpp;>`^{=8n1dQC6^WGkLr_7$D~y6ZECQCxmi+l-BzA&dZXTOl#?yiTrR>
ze3mf}ZM9!gWIW<MjByO-rM$=3A*mL|@z2X=a7X)wub&;?<K(u5SKWX5^$U38RcwsL
zzeT6@CQHsdhAxq*xcO{l{6$K>9@X6QX2bpBD!cgCSs(#$zxT~SCyI4>0WEsNj(}Bt
zNX_Q+=#4SqomIc(lxy{Rc<`>KPd{fLSFU~a-BLh9UQ3^2P&TE0+(~sS5BH5fsgUz(
zjOtH?Z@-G-+<OMD*G!rlJ0y;2;to6RuOBy84nAq+C%4RMH)lMVB+vWCv{ZQ(hb4Sm
ztNcf}uB&6n7jYAg$26x>wgWzA9=NYE@VvQ;spqbJtE)!HuO_}abmZcYp+!kt-~QBq
z{{YKIKkyoB>X7Z=Is7XRJm=D$53O>%#;Y~<5H(J$ouYrl(_2#nf2u!=R#`k!XNsS%
z)gQ2lqHl{6`?aPUxij}reicm{2A)`RSxXyP^&hc^Vt=(u{=okLfYVLH$DQ2=YJ+za
z;Bqlg@pZeE?Bm#Ex0B=jYYJevmD4_B^ZwN~QJjj2I8&OXh^Y5r$q`ydKl0K40Pm`W
zp+`SCX8O6Q32c4ZRr|TcbSjc?dXnIU7I5S4anr4Gdd0t!s4^olQoVE1yAW`quyweU
z+^dn=w82hJc4SpaMCW$o@<}7!r?UiK!VgW=Wg%RgE@{aEtmxS2z~;S4$J}Q!mZyKE
zZCF(mKse7eb2x8G&C?%t)6;OPvM~}duac~qn^!#;Y*<&#O0AG;lF7|jf%i7r=V+o7
zJi7gBE=JoU1M6BuZM=2<_BgD&&-nO%&b6nw8U*jP9P?2|3$D;{MXPVO#(APFF73S6
zO*gAdmI1bt>N{1dcg$a2)kk;E+lV=<Hjnq0^sah{q*+$We}zhfkyU}`6*O&J@)<KX
zLQPr(7=fy7%KO!bj%~T9U_B2tAZ!Y*rwvjA&{VDU09p6QIQz8w@16zij+FpbLSGzI
z_Y5A-IOJ8!;?R<uCDvXK6?irq>r`#dWvirOMdrFWn-IcrAr#@mie$(4f`i(*>Mcf#
z56KkO=d~$0Kt(hjYcY=meiVtsoKQcVAo*klfFArvX}PCLK458stq1|6R8q`vDIk$#
zkg||{>b3fofbFJfvTfL;b6v8b%R|~CIlb!^E*JNwH6_0bf+^PsOH(2xTiUr}sY9e)
zq|`B<G2W+}kyTU><ae%z1?=u3+zp)dr{|i65<}Fj!&f8RV}Z_irEXT5I+}Jkq%e)L
zzSQ7x_|$QXF&(M@07?LD!uhuBJNnm(_?822s+GsyVl((xwt<u*sK-I{uPO1}u!`zA
zdCAE9{{a0}^?Wr~-;@qaTz%V|c{x3(R>KNzFgc|IBNg_Cmdi3rkPg~{Rtz&!1qM2a
zxn6)!A}~OwBVobmOzF~`I_8kcCHb>Z_3cugR-?u!0Xxy2X?s#<il7eEhwoDU6rCsl
z$2Br8<j?b{v*}Yt-zF(B3@cp@g))mLM{YssSO=d<(9$wykw-YiO;3ahQ!dMi6lWWa
zMomws9h!uT>&;dyD#ir+8V9{6LCq+jL%UN5?N1rSH?0E!LmYe2-j#-WQvsWfYpd|R
z!m4akQrzI0<%iO=G-;k2;1G}vV_Gf5Mb8pQ(p-dP0B$GotUo6m>vLZYT_s`<V_0SK
z#~{<DmnafMxRb92nJB}MIRb>`fu)dV7~-vrh;Y>4a48Obs6N#oJaVJ?(-?E_PD4oD
zYLfxE%^CEh?beJ_xDQ-l(=&rk2P;fHdeLzKZ(33^Ii%y#m$fD_tHnK=IK?y`X-`Ul
zjA|)J?M(uZ3J)~l_i4ORj+Cx3O*iR59MRU02N|mt(-<xiU~pI3pdD%5y3|yHoLpH^
zm7UK>(zPVIwO)Sctpt;B<YVhzX{TzkY163#_hjJvS97Q8cK6W+iH3f)@i_dxbSBzb
z9@ZNWrmW3cP~6mEv5eC0=Denk#K-o<9`xLtQkJD*i;!psC(@HRGy{W*ECZ=?#V{P4
zQj>$yiv`Dye+oKNJj_yg!#q*S!<iD3icoSYEy0ITkF7Z#GJn=6&%GRvu$-bl=|DdG
z(^>7%b8#Q%O&2y`7JH=6r9WpU&|cCcx#UneZnaJID<E<9gyN!oYfg{vT_E<VSbC43
zdq{UQx=;u;j{YXnRN&pNeJT^;-5r1B=kgVz!Pk35i`!FOPJs2zAR{%;f5Ky=_LaD%
zH;r_$(8zmmDwbb~e_@jGG?!DP$26dO*DL=33ALu|ExgT+;-)?>h~xbk@s72;GJItA
zft$wAUufxZOW&n(=f&r5{Cl6zH3N9gRzEBOf8G^qBF4Y6NA`sd=V5`?mmTqn;v2>{
zWbq2ra(Ke{2EhyI^5&^zIKIOE(V}-Gsc(O3it6st#v>)n%Nq6s@@vm0@m{4VA!Ndl
z*0Ls^TejVB?IUM7HQj~b**AKu#;#)<d#6dQc$!U3%oeB1wj4L9tmHXS{cAZ7&A`Q8
zgc6><_4b$?JSbD-g3$0WH62NFGF8AMCpDuP{oQ8)hVPothdVJ|r8CZ~DI<eWIN<a6
znwh;gsHFS7s@V}M=k%sOLxWGob4_d&1e(R0#IKHhXvS$<if9DZMuOG2xj;vHrUhDr
z-~rBYT2m%Oqxn^oKPcv__BA|5<^GkrIpjHpR;x%qDzy2<R*-Q`>=7ZLj8H}m2cfK)
zsv|u`Cwf!XlNBWZ`qatOH4RH2K|&>x^!nA9+bAl&JJj&>=bF_R$Q+#Ys3bY>RtV((
z04jz509vLfvbh5^huW0#X%Dqx&CwMt2hdU4q@*uel?HvPEPK?k_2coXM6yD0%}*cQ
z^{5EXYMLyC#b}JAIl5JOI`kD~#(iqD^Fs)c91%$0Oj4YBP)`}GnYto9XzkPTpp2R-
zMmTlrQ^q~<RqABqejHOJlY$2$rFI?;KP0L#fO>oN{<X$~#&L@3JRK+RWK8sJ#CrFy
zo#IGyVOiamyHq>5NXhHXQIPz{zdb7SoT6j<y=s)B2mCAZ3t0Li$gQ1BryWIU<dL7!
zu;Y{@<D6vTwaXvIzU=qt&!H~rW4{#{lLwPg$oP!ots}8dLSrUW^In1Q<61~A#iWmd
z++?>}^DXQ<)r%{stge#g7Aqohq;{e%%*LwruyAM4m)aCJcfNn{6Tj%ys}{)OR89aD
z=5`)Exgy#If=1jzmd0zcxW9L^ca65O917`+x$=0NJn72PFMX=bu31sz5{{$2O(dvM
zk@-`{HRa~!?X_G-pEGzF&o$gRnoClnA@=vGIb^I`fo<)<NJ{h19V?gduBg%2h|}iH
zSJH-|XK^>$*tho^JYu<z7;6ZZ!_C~tr#K$9okyY7g@^AGIl1M*IXT_yRs6s^({C@5
z>BFLI80M<^gR!n->Zw({ORD^JrwMW1sEKjjo#y=AXgVWQyd)%h(s`9sOOEur`R0+L
zs*796??E~5Rea0}1fMq)iuQ$q#8Z6SpO{o-%Ti}F3C`rCtFNVJ-C3iKoYkxva9?^Z
zXE-UVGnt;;#NOVt`+rK;zJN42$4bhLKs85`Iv&cVhKw!pfmYD)I#nn}d8>$WMI*kG
zCIdaHM5uxK)TzZIx(uE(gIBHB=T7-O>Vh19TG6u^b;f>LXez&PnmX!(q!c`Sq<)p>
zakj}7{{Xsq#d;pKy|n2*Qa)3I+PwP0#^X@A@?npFPWL?*uNB)u4szv3z+zv%+1=@d
zrqiQ#?NUz4v7B{!b-D{%MYiMp>Pc;x<wcJS625|*d18^`&E9R9_b~=kjdt_NrG_Ol
z<o(5>O~OWZ;160zot_p^-<qK^8MP*gL*?=XW*tsZBQR~i`u3|g7VMyw=y}CtI|X*_
z?OgR_(XBL#OLW_I?>NqJQvU#IOo*$$C41I1w>w(^jQUco*E!i-uCs~1vrOpX@jTY8
z<{|m9j%pcvSE|D^`Er7i4hDKxGc&s7vyS+vTK@nbbI9WrKU%)*e#IRVc$Zm>e3v*z
z>J2dXqgYtge$oQxy>o4N@5Xqk>}_Vhk$`R#fNEYV%zniiQh1|QXo5A)Q`@aFZx?D#
zgZHEr?oDKBHd9$jtMdgTsj4_6a%(q=pGH!n6QY;J_w08GNj~)izAC($P3%}7_p1+R
zqh}Ql5kBRrQS56U6KVod=_$=Z+V-O%+|#i36+|w1q&yCX6+Yg5$LyonnY9a+7&AUS
zGfDRQox6O-D?~OIH#qX(b6S@E7P*w>R|=hg>S*?|?mk3hNqI92Zamkh_)5}SeIhXY
z?gOW4<sk5)EXd8duzF^@%Q+Il!9W<=I0W(OUXBIc?VNbM5=hZ$;nU#rCc$_6tM6IU
z+)u0ADSU`j5)@OTwx3YFhD(3~{o=lrdN|YV5|qGD4R^DMpGlC(X*?~19tJ9ni8eP<
zl0k{Nlpp8%R2mGVUc4pn3lK+Y(ULJ1rz9i|t~2;l$fQ@i(_xBD@r5wSj=edqH&)Q(
z)2<69(+rJ~fzhj^wz+hk<3^Rq+Dk-FVd+@clioq*K|jtE@M|V&jB8OOQ#u@kVZ~UE
zJjt~1Ds0DdZX`?=L-S&^G}{3zi!_H3jz_(6){=$Js%q?^7M#y<kc5HOyWIu`NLP1J
zSutH%MLcnd6LU7+E3daijuqLAFwYg{M^mm%bS}oMcmp+dC>d}{)k|BHR_Co>Nw?Jy
zN}K>GU4Rt1!r;|;T#`Vf0yC*@)SPYhsP>%y09u(7DTCIK$Q*&t)d`N)IjfgT<sMHS
z^_eu8&olu%6M@0$S0Rx};<?tGqm8DtY%Vw8;Dhf>3);!sq|5ZpdFvdtcKYnN(+JPr
z;8zF-&yJkpu&KG#Lq&5|G9$D&&&)ZhPTbYm*h6lLdg8O5Odso7M`Mz-uOQE*K{IyE
zIh)h9RcGYWGDI><v$lS<PFX{BIH{!0K5C}<`GMk)$fN+V?@Mk-eAGp|Q{sP`fGrov
zs9z-UO3j@5RAhj(z^y)Nxqn)o<L?uSs>dRbz>UC;^yXhKGtLb<B*`RmRc>AP1B}%o
zkzL2maBHB_oBb6xa0xgb)y|$pY*@*+Pswgq^r{?|hg%$IQy^xkT-t`n$4bAaIGWWQ
z9Pa5>Uf*&aDHxob_SigCUnm1z1;x7U;C^+PEMO7{q!%w}v;4kEJr4r9XeU%E4@%<T
zV+?@j1KPSMCM_DCxgBW?>uqj8UJh5<wyfnWs_WEst~Sm>tT{ODE2^-V1;<c&Vvrp@
zjNW2x?mcQrq8*1`)k4xzju=*`B1OvcK+LHlDr&RGkVkshnjyC}p7G$4J5v##<s4&m
zR+b_LbIoaN4U^ufN{+l9hL9AUnYds+wOT;{8$sm0wSo1k>=f`tSDGa&!K5;_a%svw
zZ04BYuM~<->O(F<cD@a1!8YIlHI)(hhEElGCQt@w3mVa}Dn4vhglsnTtaxNyzk49n
z*k&W;?Mw@fy*{-BiPwsqeqm9PGFF(15{-tl?*Vn?dUvg9qTJ!T8m)B(BRC@zfa5P=
z3|No4dsZdPTVEjL8tiXvQ*KwkQC#iiyBBUSG4h&VV&iG4V|=iuNeLf#)EL^}_w}h@
zYe3srd)G~+%v5gRkz9?uyVuZ)*RY+VkP+698hY-Q1fOn%l85go^{o3j6<BAXuA<KI
zWm1v=QHB^1SlXtZY_0@|%3))bpbnQyUD1*SSdu1V?OFN^`AjooJ&$_ckpUSQrhv}!
z6?)Q`)bmp~%KOwn5!R>$Mcd6XYIkaD9m+wZ1a14+opZ>nR{%L3g=}uY!0TBvp-I>u
zTKTRZr|!mQtC!Dsk<pH5qZRUpsvYRXE-2^Lki^Cf1CdKcF-$@lF-zKvdQbvUid=GN
z&!qq+C_O29(w->{ZYdaL7=L(ToJJ@;57MeTiJoJvX)(T`B)>W5Bxj0CO$OFTgFTA3
zY_npvb!0znoUZ^>V^X$@P1;Bj?de~o;dP@I<b2(4jg-%aEkk^|ZLvOut4_mCTR7Ci
zYi^7WK-JFM>kN#|CQeW3R!+VL2^;cy;<|2PcQIZIn7pfmhamIKWM1iZW>6q7DEel(
zc|1coQmYyEJ8Hh1F79<fG?xsKug!tS;Z)?>1df$$MYA%7&piOD=z*u^W{hV)D62+Q
zFY`FfQ{KsN<rP>C=CDf4({n=N;6-n-WpXjzxotw_S;{-$`c>KWm?Lej%Z{BYqiU8?
zx6Ii80D#h*;%y8)OK6PPO8J;fpTe(26SRZnKb10D`)G(LLH88J*A;mQlm7KZ;%>0j
zU)eV8yx5pzkO!??W-PprKN{tm#0}at=eBAl*WCXA%QY1|(J$(CdmS972dJvgu#dh!
z3g_EenD<YnDi+mdz`@7iM=~GOs`fX_BDdbEx{&h`e7u(Q0<m9GxPEuz=~2D)%M5vk
z6x`ERE}j~tIddXYYd2Dq#)Xg_*dFx@T+B!M#;Bw+GLl^5)~7?FQmBbbDE=W&hUh~e
zkz1!~%xsg?({t}fDr7446Wr+k0JoTZ*&9Bhtyyc1vln@Z`ikY_Q&yuG6%NSjkF~13
z=^e^=wd0HdaKqDRsoTc$81@^P2*+_;9(d|$;OC*NoMQS8I2iRhXYmS2obO}mY6GrE
z&+fkh)qqLGC<eCn^R=#0%jtDC&bql6g?}1DuP`|fr{!4zc%TZ0R(;JD0)qP{nb#-J
z%BlhFiec9;2>aL`)j)td_oOG%lc_G{tQ{ZaFCAX+@#i=4sGn23ZnHLhb5%+D&^pv}
zvsH$szR5FQ+&2bi$JUx|W+VM;{&gAkqzj%X<}2AjbUhQn(JZ=ZGpK0-f=TcGb6rS`
zXN9g$z^q$Oe`Al-*JKp*uS$!&Pm;#Nma{}=EaNnuSk5uUPqdD-nD?ztG9efP7{xd)
z1w0MZy9oBC1bb<_D#FG+b4bXdkPrd3f-~t-ouZmb_ND_ioKj;3r0qy~pazkVNJc#=
z-4y=-N@jWVphLFO913Y-0iu{0I?6ne{GGcB$+5S&67|CR*HX}l7Y&S5Yig0PAw?mT
zlHBK>O-?OxGHS>e?M?%V0D&My9<?`?xZ;#_qopPT0^*bmQ-`nVN=F&*Kn*7+9cg@=
zj+Gga1b`FPt|-L-R&?6GT8|`(mgZ2ZPimkp$zm}@z_bbcDXcdmFHEVZ*5`5Oij=Uy
zJRT@xj^~u?%ePpZ4ukwnWuJQ6@hSnUN<ig+&0-OX^D2By`#dYXBqv%?MIfj;1<pRS
zXP#&SrfER-re^Ql3F9=Fr)L72jMA}j^%M>{q|PZ%N@+BUXi!gTQzK)oHiMH)l?bhY
zn4Ywmqa0C+MFj(zITU7)3rRtufDF+|jM9!Nh$zh%qXf_aMK0O^pajJf>~YqRj%ct6
zM;N2=qm0l2MrnAX7^VjAgdDE7j+tEkM1PHXauB1Zt$9y}r1G`Mn16TriuFYMi|Pgq
zcj5j6<}-Es(rj@?a%rIDXy-jEpz=vc`DvSY;Lr&xNrFW%6B#t4p5lNp+)<D^kw`-0
z9Zdx1y*Da<h*ODQT2~l~aC!{VhB>6%o!X8MOrOGwh+Wi#<n<zt_zQki1C#ep<4WkO
z2sv)_5_@FQk_R6yKi(9caxYeleOyv<L18w6Ia5K5KTr)s`h}t~-E#;1_fbB-rALtW
zumU~lbD`LuX5NYgJ$GZEteHGjqbK~tBjTya<6RvO7vuf{v~vZHkx{;s_DL`{xvnx#
zA89Io<MLPb0-<k-T2d(DXB1ub3mv$(cNu5r>qxO|;IKc9a1wk?vJLXvI}fcvFU0tm
zVm&yY_!cPFuvqkr4E^9frjd+&3y;9pmY<1|4F3S20qIqr;!dNJ<y%CejY7w*Ge!>v
znkA1o8;{{$RG$$wnTFBjrhTe5@s_tMVQ%sCQA?SHk?T9ue+zz8XO4#+_2g;dZDY+-
zE#tC-$Q)E!w!Nt<ppNcPt<T=3uHJ!Udiyv78<c%mQ%tC%nIj+YI`ElwO+rW9Z)V4)
z>WA&OWlnBoIqq7u_Hq@^VAri}wRPC{u*3(Wb6oN8-i;nN>Z3pJ*PZ#2lgzKv){&Wr
z`|f-4)h`a2)eLP|N0u)`(Ek9k{5FK|)C=R$sh(GaA^Z0($KJg3qL%10*EygnjC`V+
z!$fZ#S^cBXe%0XkfB{SWL8Kb*gk$@*Dt(Gq1V_uz3TeO{D*mk#H;bzJo#F9^hhpL#
zEf4$zQ%{dH=<*}dBLmkJ!XL_-N$O1}LMWfCP4zpY@eLD%(xL<Nrk{v+NA6j|qv>2Y
z>rWgS6)2MG$m^x}g{mGBDA(|+t>c|-zvZxBpcT$B0*v;pJ(LOdk~dF`HP;w7UzI}s
zB-P}|H?j)JT3q6<k}IIO<X(MSQhv9yAI6|Jw@mw*;zE7epw4J)Q%XIB%*h&gn3B^-
zevM7u<mY>n?$p`|=C49-1d=&pQLq{5pRGQcdizwd+-?9hDjZ^=J$h8Cyk|8baBjch
zK&3vSldVt>jrQ^U>f6SVrhC;TI6q3Tk{KOP;~um&A~JF@OvPE4B91=wRVIs!QUEm4
zDNQDGO5h;tO)PUy1P`r7!w0QHU`o8Gp#9#oARBq7Fzrc<=sYyrK?8seKRW9Xu)K=o
zJT!1yCxFNKS6HXzua(9x-m}r8@RAnhpSvqilY`crKJ9TDk1dJ=debvWlR(J>VX6DG
zPz>%BCwf3jnmoX?#XM8ChBP2!KKoQmyBLo3XvPviI(t+XBlnzhO$cAT89nKX!gEqW
zH!d?wakLuVo9HGA*&S;?RgXIwt|Re|^#-7Y?S6+f(}Q-ZWmj04O1R)sG<ZBxq0Kyw
zM>Xv|QN(mwW94Ew;8vvEx29_sOgKou=M}Rt$REnSR~Z{sXQfHr2yH$YF(9aO#VYXN
z*CR%R*G;zaHWi<IKYXXuRqOnN3-shwE7AV1*Ve9>gtKfCy~sS&@vdb9*R55x{{UIV
zT3?o6b6UL^h$Q(Y#ZPM3kl^;HuSVI_`id>GCR&;7G+tsub*U8bQ8x|ENP~*P!zTyj
zs}{V*!mEm&(BQcAtfZ_1v5eD)9MD(h;*OOlWm#@>CzcIeLAuYcZYrPIRqry-g~v~N
z&`quiFJWCcu3b3^Mq)D~1I=FFx-iugw&hy{cdH&)7XJWy6qM7Aghwgh9+a8N(#y;}
zb4^?o?^)DZjIkNa9;8!2#%W<cBMNO|GDSR6wlX>IOa_(t6ahPrlpfU)7^kl>b4(wN
zAR6FoIpkFvQU%iX#a?byj8;gK?Dwa*CcP?GmL5qNzlhqHl2)PW;+8p*W%m@uU5B}@
z80gC;kbJ+^s^=0KuruXzRoGyIT`O8`2$nO60Tp4nAk{#6b5>6%D~+v66c8#vfBkh3
z=qbv1>rw!x_q}QEed;5`fYh(hb3h8G2Dm>S+V8gxgDsuIKb3bt*E!<omVG^e_B?%S
z*~qGLVv&t?cr(WV>CS26pyGyAQ?zgwjCxWN#eRsH<Fa&MVj`Nu0~}LgJmRD{swAv)
zxYM!EY7Yd_nnN9oif-DKakSGI`%?j=U{h(#d8Xqgm<L)9J?Ti}>q*{#0JQWtrUQeT
zdYq}G0_Lyi=+a*lUh7%sk&3fnA&%``TL+~n{30jTpfKtgY<$bwvvbc%+1HSR8<Xvm
zSj6*6FWnetIi*vMDW;sJs0VhS^riaJW|#>}if=imsLxtpH>ExaJgbC!;AfLfd@1Wq
z>%|XMVH?_`M{{5Zb>6rluyN`tPOH~6g>#=ui&+ehIH_3)T<1L0Smvx`c|A=4Rz9?&
zr5s|8*r^x;=|g>ap?GRm?betP&_|^JQTWpf0PDpeJky6-YXj>*gx&O~1Mf^CkW{c8
z{B*skwCv)L#62mrr<3?odQuqd^GZ5XX~2<40Q%B;&_yKxC^Vp&Owv*SJo-|{B#=J%
zBxu{!O)%#;qM~q8R*_MYTO9?DiSOe(BxR6#nzH^jk|_$cm~VAz<|6}m&S;rHY>M-0
z<=A;U@|_D4Q@Pf!jGkEXwqxjDrAB;Vat;NekA2n5+cJ&WJkyJO+3QpNmxi~(Kdn^m
zbqnH)>4yk_k6N4iYf@zg0e5x_(y(n^0UUc)vN$Wp99I<ZbYm-WkLxubQfc*VNJsL@
z0qRaWRy_LlvK)aw$UE(=Ev+l;>zY~gOQR5zY1!xnZBGkJ`9<yL+~(!i^+t1>ryuUr
zU)uVUFE?`jbta*wG&8wX;QCb<=TwNU#U%HweT)~`UvRywpHkd<uAt7luO;iywRF)l
zy_)7m{Q0gm8+3r+XEoQ@znNylf4V64QS2^xcPO|azWaaQRU58xmSgzUiI;4IQ$#?4
z>S?NR>@Id!*~dMqGNDxbpnKJ!AE$api0yBBwE|p>cR(a388qelzLfcf*)dHXmEQ>H
zV<tG#&<1!Woz!NvQ8Tz9!*uUjaqzX8qvowBNZ2c?j7(}VPpw4bbxcMHIH=rUcCF<T
zG|Je)p}y@shhDUVe3g?%ibYe6)T0Bv3^02dP%9*jE<F!F)~~|ACfcC9V~V|Qc;>q3
zm{cYmb64T!FmqHk^H*)yDq#1nx@Q$#i5OH;jIISve(9)W<kpPNC0>S*jH#tzmg`7+
zn#G%<y9^p=IH$?fnr<>{BT;jTu@S+l-D<=<pHo*2$&oPN;-`zHLP5tTCZ&rY<E?It
zBt6eRUX>Hz_NkkvH3JNNDw#1LVa_Q23Nw>OTFsjwjZ7Im>BpxugQaFt6miz1jQq6_
zJmRE}k8@24lL5ya>S#^{MT7ZNk@^bOCK4rK#~7$(92&60j8qTE#ZweY$BIM3)0?d{
z)=b$EccsTPj5(lkYDyFj%B7E!)}pB+2iBSfO^TKgfNCt$;^5VzDH582_{~n(s3i2J
zD3BBN#Ri5yF`)IV*|H-%8cv6rRv$4mfbrI#q1n$Kl_H*)6&R@#fI3qXB^;0|q41*>
z)FcNZcisFeo(CM7+3@Uzb%lK3Y%BQx0FhokcN^hkbl}~pqthJZanh-{!yYQm34s`A
zrB{?-lloWW`!ng0;qy3I26_t9S<H}!1a#|J6O27rw48ZtmG>v98QGT_UO*<0$&u?-
zoya((564;#g;kTYW2FL9gHdnK(wfBbM-+$cEOy=))UD!`Bb5$&SE5?p$2t!!!4=`w
zS8s1Juxu`KUV-7co@te%JCTpw>5A48IPtVStUaVo$zruz#h(hYXB?X9*hXxb&t>cF
zUU{k7Tu&Gg$OEf}9@W~w4aSlXoH0yi-nO~mP8K-bOT-Bk<HpN~$3y8}Yp&gWvr=}>
zR2~g=I{l3H^G)UhkZ=#RaS!u3&tiD2YBSf%sV|6xfIHF?ig_GyQL*Wo!so59jA^YW
zG}dFEN@?e<1oIE`4LnGFY6^Pw#RF0%RypfZD|*xb8j(k(BY3i9I5i@HnyxzcsTIh@
z2C0*daZ1?W^r(cNOo|Md7zd>zM9A*WV_}NMM$1->+u}CC#bqO5^Hh&F6)$}n5MYYG
z9snM-nG~F4XX{sDB(TSN4d}AaZ$nR9{c1E&M_QQ&L5fFoN3L=`YgbLfPZE$w6_|jY
zgB7Evu!?xy+>NX@fI8DfR9AyK?P|~dDfvEKxL!Xh;yg4JWw;DL8;Xo{JpTat>(X^!
z^q&s?=oc*?MH%g0Qw5~ZyBW8{yN}9vCz|x|O{$5Xp5qt9nbb=hg|ImTrYbKz?ctD)
zrjtya<c+2;@-F~V%v9TMU~?mJUh(4WQG3-`0y^ZktxpZjtXB9!3->ir_SGDw*1^Y0
zpt@Z1+=UVj4{FMDv8si~>e`Yh+A*APYnHmbEc_|J?rWpH@Z{{@D9A06Ph(g*m65ib
zE<vv=5nZ>T*G7^^g5F@$Wz=!fn>5ZGfsh3d#v_qSgSWjp^+1y=(AOiIXGbYr-J7YX
zN(|HRL7=ZSH!8yd;<o%ZaF+MvKk*JL8HNWuRF?7>u3?dKFx`)8E*3g(6(UUxbE2FB
z)K@IY$*$t!6}!@3Bpu6~S0@gUsNBotLumQW860AzF_Z|%;-!Wbn+St*dRI$f@c#f;
zzL+DC41T!gy1P$@BTrc65*B6q#P<~L2;%I#F+7Ac&9M&{9Zhr=UK+NKC&@Cf{vs>0
zgGGe^FVuHhxv~gXjQ&+O8O_C{1q*}&(~6tyK}XHbD*fK4Z)&HN&pcKX+QZJ<VNM&c
z^rv!KA0jMoxbOu^*Y=V_=DdKR>?=Cp$nfFE)C$Rt$=*yC3OZM(gQ;c8a@VKKb@tlD
zq_>H-R0AE2XxOYWJnkECt}@!n#xw-njIIY-w+^{&r`$}dKgz=Z6W+ZKXqM+EvV9FC
zwl?y-sgO$&D@N+$%#zx0{2VFArE+n2hS&#L9G-u@Q@@IAq_$Y1T)JZ(^)jyx;HXT{
z)~(oTu-rqP>&{1NOV@&El6N2#!nSG)Yx%Xyh}IlNssJSW^r&@j4QdhH4fhAhBX$Q&
z_pB$1hRE79B)%e+o~d=IOp$-8U%iThQNNX+$be!s;MTQ*{{Un{(W3c`+4+xpd>U+W
zznd;F-qpcUZgSM>icwk^{vES>&15r-2(WYb*Q_ZC5-0ap99J!+T1OSeQ2^()b;)TY
zg-c{FZYwr1AVTlQBDXE!*&a<Loq|H3;8gO+0HgyL<l`VziD<4z&PFPsmum{W1o5^x
z!TQn}D%nH)QWN-8hS~%ld!I@O7|0^4&oEI^GCSdF(K7WWuq6=0+%0Iz44~q&t|D<E
z&nB1<$jab>82Zv%osx`Ig@A<lg;$k?Ah)M#U{lua%c{q_fz($zjvip6sbDGEo$sA+
z{{S|5s`_%7Zxz3Veqw8xyU6X2y8}k{LP#Bl9MuNNJm#mplQI%}ny6(U9CfYFHR?3B
zIqg-XeshYMiDAuGnUr;)3e&JHnyTcmKcz`C<&PW+gtix+w19=NnnXB1N=LvxqM}pt
z&@$t5ieUTQGeK|{>q+Kd`_mB1frYApc|EG!tXNbkpEi49ganYT5SnC`>frQ0N}+Rf
z;$g9{qwf!Tq}rshN_og$-nB-NG}^-l<r)69X3pPYN~fa=%8Oq4zI1QGwQTQTx;s(2
z`p{F@*U|2TEbu#Ebz15pkxJt|x{me27TYHsL9P8B`CT@#<Z+4)c57T)tD(n3ShrTd
zWa7G1RdfR&{VKK1u2(#MGzl}4F^{GzR?1w(wDF3HdvJvI#Wn}n!jVSprOv_>{&mn;
z&zu!*-7Aufg9_8Kx!B!mMt7Fe6Br`3tY=`@ZicyyKKB88sIBNF$=tmt16|az8qSn$
zY#+|FE#(p>4+qkrxQBUaVl#>i@m1#FbgO<#u6W{@@owPekQs8u4<o6nuNwo8TGW~y
zr__4Yc8N&c*m}?gbH*Dr0UJ*vn$eQqC`jN{X<#IJ40WW&K(CXEvlBRdr=jAjG$C+9
z^HOi<Gg3120}_E+@RA76O29`d!zZO`!#?x?w@PC+VSKer(e4~o2&LKwImKO$P|KQR
zm0vm9YBpWSRQ0Pesb<^<H46p@IO3QYcQ)IydR9fvrt$BNmDEWVNItbv;?YkaV-x|x
zUD+MS^Q@_3A<lTkcQ;lcvz7csVqR(d940`d&=@c_*(**7%x7@sv!{ikZ@5K1DRRD*
zAayo(Acb^n*5ZV{vwLSyPBNcb<7{qxxkh?psji;NaNAvdXacR2lUhm<&RI`W+Ph0x
zgz$m<Lb*L@f|%~(KO+um#*3>JkyXzb>U&cIq?#?YR#Fu7&0X_SX!F-S>ZF~`Fd;2X
zA26uQyNO=nmNprn1UX!uywyAP8~5X!Rk>J_d8*fOmWMu-=4SN0rW#&HUJiDuQ0YMF
zKs09+@JGHK=%b|>6aaRhQQm<_0*q1k(vzIxm<it$0a#M&OJk`uy~~puebedEw&P`F
z-h?t9j4QUj0<{Q6q?U|`)Qp=*dj6EBr64q-xJw(-kKm_u7^FV`0If75lhqe><izyd
zkzDP}L(JrMu8&x6^w(aStBKb2DXrgZTwrofdi^Ia_ptEvK6eqNMowcueW^AKaa`2e
z?b@%)gZ!$y_=@=O89?@~+Zdg2UO3G?8Pt5d3gZ)8y^+7x{uE8BUIIUS-uUlT%E0YB
z$r$9HYKnWAE$!Tg?Z>@v$5Oq|`r}jCUe6?rzCz2`8qRA&qYjg(lQd<O<U5(Oo@tpq
z%^@I>=}1q#dD1?z2_!FmlxH-Vqd!WUngQaF^rZxfLPaqNoKj~TP);eN&}SegnnOXP
z=QU}Z@<QgDo-s><NJd3f%w(=Y>&HrHT-4=Bp<~5W&R0rKdJaUusnlRnD)hxTa4RNy
zl%r%B=9~>C4mwealY61yWQurEQGzMq`Ji_kagMay^Gsu!Ku#)IaU>>_AewGzb5dBj
z<1}X!(?C4XG5PkOXFO9gP7Q-VncMghPu$9bsAG{`$T%7GuRib_VtIWsYtbVgD6dNo
z@E;|aD_3G<@F@4CJRAyeYy-t^dBkPN>%gamEIH{>pP18$`6vP8;CH4I+nQ!iy&0ed
z&j*@J=e;2~8KXVLFde%K%{QY^4rm-T0u{RZQz=-}XaPqekHUaGDpgFbb3hCLP<qmy
zDW@6spkiQ(QgAayMK9KX8W{c*jUfVtUO%lcjGnZBiRO?V7L(4Df(}Ja7b2usl%9G}
z1{KZYM|8h752aoEbcF#fY8^t_5jU8~ay<oDjtI<S<=}eK11{?JXF1-)_o^RnyAop=
z80%ZoTOlWC0-;+Gx|#xoz1-3tpNw~{J9c(c$vNVtj?Dqi1zAXyMg;>$oA{|V>RW-y
zBNfk_3hKON7)#}Bfsw$jP?3&EuR5ytkE_8y+@>x)=+88Tmp^z?7eo9*HJQ}p$BGY1
zXPBV<;m^G|N`kJ&Qf-U3G;QXT7i028BY(Pt)BKBrz_p+7jL_GSDYf>9@M)xE)sbU-
zK*gQG`lVQpL)GR{vdzYSym3dfljv;m5KCDZ_@u>buZ8uN=j`aeSE(1m8nX|*Y`<4O
z;Z^LV*vsp5mh(my(@Bcx2ZMDH_pa?%{so$lcs^AhyuXBf4IaWmc<L*u&EpiO71PJy
z=%j7G+Dco|YDVyumjE7qsN?jb*htOhlslZ6>qj27)eQ^7ai5=2osZO0#-HJ3<IH!*
zsWqy>)O`%zZ9yD{<<C(|y+?6faUK_p5H0uPtu*Q$9)x8y^={mzYSsd$V>g`9M<!%n
zT20*aBz-Hb9w5=vgwf;rY@|LevyHHtRAbWutNT8uV<(-{=#E)dMmR{MbN<ScQZ1$9
zpOVht{{Y)FT^aGK;CXg2Ekt~4dCu4neJa*nHbc(WL}MnGsY&;2Xa4}cDpb%lc~8q>
zDEi=4@Ayo0Qcm5gQNN1yRyq4l)9H%8?AaMS@%9*=7S<n+vnU_!HA=n@)!6;m7wXkq
z_>)y}^IZNosD`zu6Z2iUs##+)mUljen)oMDKYrrbe;m}G@P$q}Yxq{NzqIb0^KmEV
zNY_(2B+V!1TE{G1Or@PxI(sh)MP+ce2UJXgF~@4_7g4c|2K)HI1GRZjnTX}wel#`4
zJMrjiWq?uYaaPApv%HT}ZD&kh`F}rx(H6I+OEN;YPSQV2E-T7S<_-o0Skf+)b?ZYU
zim9GSqF899xss^gL)n_j>tJZ@-SRR9>{1IIO!4+8!T$hiZ~nDuT6mL3j?F~Ug5d^8
zr~d%LU7{>F$s~St#^nTRl$o3TpK_M(H1I+Sc1JCm<0tW&M(jSwgKkGBy>~i~jkJTM
z&atl3gU&kF&$oJ_%X2G+#^yX$l$|GjV0`HBAIDOE1+01Ys85cszk(!OR{(Vt&s@}P
zsddI{Z}xT2k9_Xr@xG?Zjp`4sDx>(vR$-5{kHWaKsW)LvH||bAAB`_*L39pT_d6Hy
zR;J^dqxscoHT^-){Cz*ub#jLGL+MR7G7;3&y0p4PYBK81#OhZv+k^Ip&(^3(bve#t
zC)TRzleCtM2*x|p+c`P?D~3%sb5v8BSr$h9;}3eLBNjh9vwyu-u2*XcsK?g2AhZy|
z7t(@8c@&LE4N!-S4#V=L;1BSo53M^C0KZC6O~okSQey@jQx8shQ_Uw@Rszj{-zL*q
zt8NZBti3dkwAV_Je4RR0Yz*d$9V!h+?x`cCYP@*%tnEl*-H$=*P8)%e=O;AG(vDX&
znXa-x8gV?+d-bI~sSI4=lRu>>qt=>Y96C}SC>=V|nz0Nco|N2nr<JCWkF89AN^msV
zRq0uwj$@E10pgr_T+?&KSPBo}OWu%EvBdx=_n`Ajib5%X3PLkVDSJ~w89}FGni+j*
zg~-iFy(x?-!luAD;}n^rwG;rE=M><?9D_~4%^2dC602@MG3J=d&uUKe5@-M-nngIA
z(@3RYxYO2}Y1D*fm4J~x?MS0E$c7i`QmX-uDq0!4;pG8}`tw~<u0}<38UWofD}jT}
zb!wff<+BYcv(cgOk?iEt)DpcZ{#`jEz%}RG+>2!<+L);{Y^87^0Oq74<s8%eymL<p
z^3iZ2QBtYLJ*WxAJSP~TJwUEYJll;r>O3lu-lbUbjKK0JoNkO$llO#Gh+yKRBjh92
zk|p`6%%?4ixIcJBCHuruTrTTkI{hidaU*7)erTJXaa~j;YKV#aCK~<jDn?!fC-HtX
z_UJ3$TBFZ2^wv88_r-6wFy}cn&S}ISm!=JLko@-fubRvis-A`&-Xu7s7|+(9v%N0b
z^Y3$FOQD-(ZlrgrcX1YsGV{e+X_264o1QvUHuDGhWFDfgmQdV9I2X&59@TPX9%7u+
z9^Y$adR2*rVpCOnffV+#NryqZj8aEuIFL5NG3#2eoz{pu)v<0ov4Yj>Vem1lPnolx
zrDqpoG}}nn!ql<ZOv{i44;<F)Hb`O($peE^C6W#{l6@<G?7BvOSdosJWY|A<ik8<+
zluUkP!R=dXZh>$qV1hAn2OQJ>%b*`vk)GOAiddN=KA5U<!eVd<&wA=7jTEj&Ue$r9
zrY1v=QC?<agQr3X!5dMk=JhhJQ#*Z6dWt4{X?Q;)brots(yPuepq@FeHcd(i8y7y*
zWgLM|iaqGZdFQof!ziov<g&IaJ!7!Qwq`aQap_USeqOaY^6s@-HQLM%tqt4>?T^gB
z(vyQth~iOBkbK$gSuu}Olg%j^9`wL!Oz}tu$MZ#xPfCo88g;vT>?!*JV?Yp=+CG(?
zBxK!u%ktxcTFnp3k<zNP?*jphgT`yS2{|}QF(PCr{#$WYgsSVos`qF%`N_`iwG2}N
zaC+7}s^c^mA15@>s?dUZ;)ow|l_U{QxB0iB?Nd_lLn|IutuHY1Rpec)!lZ$>N7k}q
z9x1@n0p^?z4ti1nAA_HIl%2{dC*)_Sr>`qOTv1ut)FN966pZ8_<yZ4jTn*5$&l^p4
zU}wo*ESamto)vngJNegv^V9@qwQ6{VFDq7+K;V;;`G1XN=D$v+?-b7xTaJ(KaZ)n#
z=};-d=BzTFJ?laW@(yV`aZZ<tZhh$tnm&g-R7CSm6vN+~(*X&{=87}vMrgPaG2FhD
z9(kt@5}BT8xC%)fsaK^pH03yIKrV6Glrtj+2bDRb&%HId8KZF<T8jy+Mi0ygZ(b`P
zn$TABEFTS@ma}u#rW*`X(t*^{3Q#%gRd5^)2bz$l%g0)cv-F^0{OLjOnqj8{R3Uox
zq`(6-gy5Xh82jdd69O~GK~7#f)BurE#0xO(N<a*_ITRtnkxJyNVA4jrjx$m+CKQ6K
zNfs2G)qS8ELl->Ku=#Rny=m_Iln+5b5grXEOj7hThx4Wbm#q#kXkMb6;(-xTfykw!
zIPXb}MjJ@yG<6+K2dx-5%|HMg^Gzd~P;hAvN(LRNK<A1<PR=N}0T>k8d8Qmv0Hn_}
z9-V0c=71MCq|erroYH5Gl$ggU!J=XEW{`W+oRYgmM3Bg$Y&SJC5zup0fx)R1<aMb6
z^_c^c)Ee4`LRY0>TYRnf*44S(gVPn~Vl<IRok>;=+;pz0!sB!yK_r3RxlOqkt^F{T
zfM?Sg6;zlOuC&{0(81IOJ;3i=hNIzg2hOpA2V4%-+bIJWp~A|WUy+W6wXhy(CZ4F}
zLIonV>{DzTI#$M|qwgX}fF1FU)tzk{ARzV0sFKiSOM&~-o-!&(6MT3dtu5FhLfGKq
zrn4KP&N!kV$c%Kxgzi16{E>i1ziN!foSLFecKHHLimU}*)gvJ1-xWk>xvt848OV@+
zw79^a3Q#$&gpAlPTG6-rf~Y7Y)%$QUT~v{ULRMOh)~74S^r+ZzTeM=CRl4Gn8C+A?
zbKZ~*pw=xK#g!NkaYFM>kYVsCtJboysPWpaTOO5A4DnX2_&FUbdOMj^*t5{pyK}&*
zm?ZjDt7D4nfyYx~!RLyJzy_rvqkf!ptyz>xu0U?4m^oT>zk809+R8^nNLzuAN^X18
zpXtYXXMe3=%@E*oQpLkm6*OEQTBr&|ug8j#FTI@9K;&T5k@di?gmcK9hAJ5crA&RQ
z7d#55u_&(JdpI<d9%*sKX3bF>3TfnY#W|GIM^95(vd{{0j2<a7%_^K8xjwWYWq@;1
zL^5hIz^BKZ-u1FDkz|2^nubA))ZAjCd}G$B>_RG%GsPkLQn%jbo8Gc!=#7s)l$gyc
zt~sR5NkP<9k(`=mPU4({4L~w*KD8ozq*OrT>rX&)R*cy@bf{k^Cp9r1^$Ya>01BZZ
z0&-~q>zY%^?@8SIR&3P_VUG0NW9v?Sl*|xCK}dgp>rX>bV~pmWyk>zG0O0*AOGN}~
z$&<!ET-Iug4h>w>n69G<&sM<|!I{UK4J2!Z(xN?DCI;R-j#nVm5{_z1RtC{PIqTM$
zAo;8E2`f$9`jxTaQ}Rti9L6aD?cSuA^VX`l&3(c<>N`CRCOf$uDlC!Sp|zhQV;Y%;
zC>&>WIb`*xZm4M8ibeAho|vuw01j)?X}4&s*<R%Ku5WcXIR_$xNL03r_ZQTln#5hH
z9FLd^-_Wm;=SW$DfAy=z^bK*q@+Bh-F@w^*FT-z*G2=$a&g|CkmCrvLh2&h(*uwFa
zs|3o>0897nn)A2jy1y5NI)Nh@2Dv$Uk;P*-c6vA(T(qu2#|NG&Hf|};$?Z{-gHUua
zq?&GNNT!kaP-ZV`dY`2?9QsnI=b8qQD)Y@ugFi}y9Mp<&QglF@Za}0fjMI^WRO=Wb
zgQ_sOQ{I#id)1R{4KTyAk|-(CXwSSO%VSw7%YHSrcAqK7VOeOL`cq8uu~gr*CXDbZ
z<S&Y*i;sG;jkcMsEeq&L9kJG@UJqKNlM*-;IuhSXM{F5w91begyt$S!j)XVmR26&o
z6=E}t9)xpD-*sc(JUT2b{5J#2V<1KeC+S{i;`>PTEp*EUKF*^U9COe3)+Nu0?``yx
zYL3en1CGL^TiIucP7Y5dy_~+y-2C@8p(<5cW7-vl0Sf;B7dRb_L2%if6S9t#U=n2B
zdMK)Lx{dQTa(Y*)+2eBDtogXTz+eHu<F$3#R*tdT`MmBuYn0QOR_z`5G8_*|^c!}>
z0FPt(SDT8c)`;$-1!F$yz%sW09C43Y<24@+d9$?6N!of>pffW$Tpntq(IXr%=Dg-~
zEe;T9(6a3+8HaK!F7w0kyx$=TgVa}|Nn{AlMn09BabjGR<w5I;l8-)Z4bbJB0qs@f
z)AnR3&(ggZXpl5#C5>e#hjVh>PEV~NoI%sr^Mm!PHrgcDP35d@&rEl(NVf32Y{M(~
zu<2b6pQl+^mCA3E7|EaxcSG>Sz=9+(0ze#^?rd}mOE~h#rcY{?8B9yRX4M@RrB=Gs
zrQXCc^v~X@Y-YMc3a2{}ewCGfs9V5{k0Nbh)K@2}_=a*gln<?P_qwynaU_i1z|^)D
zJs8UXi+akNah&G4`~7Cv600sq>yFjNMR$2Sh%GnraqI<kx<7^;w#|6k{{V|=rZX{E
z-bh*)S^4UF)#&Za02WLiOjlNxHumvsMF4gKr9n58s(2kcifByb=aHCw!-4Hs7tu4j
zY}}yZrF56K$>ot8JfFg_+D5pX;18u*n~uR4b2FK_)8;@}Nc(ft9%_TbA(JO8$GJ7w
z&ux|I#Zi4c6Og2uk8LJ&dl;PJLg#_QA6nA3w)ukhCy#SihMSiAg#9Y?b`Gkfj`{jh
z_KlRO*xT^kjFG_C5U$`(SL!RMxM!N&2O0YM(&-R=n$k4KUNKd*-9<FOs#iOogGD)B
zM?Fo9E5=p33%5DsRkXm3df*OgnYz|X%p@OpA4+HT-N6A)2==a?W1h!(p-P|H3OFnd
z2(L@FwL=oNIXE@qUKF~SZ(4Z|0l3d<^{X9zC$?Ut@sDa(xXo!}^4F*1S<(_oqFr6z
z<=e$q7h9X|;+Tj1nccI4ij{55cq5OcD%_|Q6KV)sZ%RyL&pV>xsD_q#Na!lSlg;Qj
z^{JUmQ8TLN6(b^dSR>_gS#wFb^Nbpv>gRClilyhF2j<D91(kj4&oz&&$ZhQ#jAx;%
zB61||N3~)2qU?l3Q=E0?l--eZ)#P%Q6Bd+_jDK3!(g90WnZ_98Ry<LOWaQT2Q5K%N
zMhkk@6xHN(R+XSsm5Z?_^{7beNY9Z>X54z#?DN5!sLnA}W;}YDbeYekSCsA;&OPY?
z5pLaT2@MbOu))v0MEkSN10iNP>qxDZ6i9Gss&YZ}pbG@#3T`>;nnH541JC0?iCATO
z)Kcf{@?!%cr^Z*_p_NYFyj3F7F(qs}Zq9viRb`D_?#*m6BXGltfZD+0IVx(4v5?TP
zr(4e@t;BL;AzS7i)uh^bgT%DPwNdwoKD38pd@9PTA|4x&NgT3TOT8PO;8N*3Wq?E*
zJ9s&%Zel1sFf*DAB&^P_PQ6LtM$aTxu>qqU550NbmwwP(Y|k0!Yq-;{mQ_{Vo;r#|
zm9K3wHwF5N%XoI2^!zKWFc(9U$?sXW7DI9Q4t+&288Kv@wQdu&){w!lb4wltNmn+k
zuD);y#dTIvH$`GVt{&a6**|u=T{7ju4t`Te4#L^W;GVU6i6g8CC*v$@TGnmr!vmUN
z5)6CQMmXS(YeCm0s<;8LaA*RXDRKTaPI$=ck?mSiE;&=jrB;vzQ=YT|pRvb$ie$0n
zd8zV7Mkyu9N<%W`kAuxXTMhK9%^Mu?QAq-o$?M*ghE{2vMs|}{Vv(2v4hX1SN{kQ)
zq|ON2#UY&qyo_<4^```jw}J_-W(oQN_%*3-Atg?EphohjBQ(SE?o-l|2|iJtz3NAd
zH#I^lk+@^hpq4xWYRFxzGg6qt$B$Y7#dx>%s?BBzZNqn`wQIaw^u{VCU9F#50Ohar
zVEHOP4@%~)ZC=)FV}fyBmn2H+K^2dwXv=YI?4NjZKpbo`eEjiS+I`PVbnjTQL}6ki
z7$erEx41Dk2a1~k*ofl2vy$2HcXGM)u4P%RW@z6zQ;gO7OYOK}OX3(7OK9)o$j9FF
z#Q<K@^_B=#j~zPJkK0T2JReHo?Wfx)!(%^{Z(3Y$OlKH4>p&W;;7O2r)Uo3ms=P<c
zAo^9X09+bi487_(7cmj*PcmYo-;<7&m1y(9#JW<n(=y1xG=4O$Hp;@Wb$w*%j548t
zIIn`Ef~knF>}jn}qIDw}b4b|-nhD~#$vkBz8(|-XR+GjTWl0zr?Ox?R5y#7WBaT_7
z9d$dxaZ7`amFJD(-9fX40-$daYElE2{8qZ-!FZ?fO&H5Kpte0MgWn&WG~f<de>(F9
z*EI$?X=)eMZy%8{0Q*->J_(!nreyP~eG#|f!lzJ1L;NIhQD|NweKtjcX3eqbpW&<t
zCz4Z_V#n0eGus)jvZs|&`l`cKS4i>RK5DzG1J~f5DdAZneaOQg)SzO#!$j7uG^w_(
z=Zy7C*Q429CGE6xMhI6>*gdQBJo_S^Up{#227NXU85~4(+_B#@8Z(MRn)#%5oR+e2
zsxTgzt`Ee+GA0LKO78XG6II+gusN<H#EXEhp5S7?NXhlX!1?T6m08Kmrx+rt6~V0;
zS0L3k0=>Uxb6jjZKfO;X<ug#A=xWQ1rZLB*UnYXNNUd41;(tL=u<iV*_NNnKv8fMr
zofv6aq)ju|G?~pEsRnx2hb_;sj>CljWYP`|CP=9$QZQ*hr5VYhn1rM~X~feF1Ti{&
zXw5D&#UT{Tq^=pGuX+f@CQUMVMFa7t0g6HNr-7PRG*BNK?Hqt<#kuKB0~ERAts_+w
zDQY)lQe)nVL*+rAN)%FcrS%kwNM5<6rvCs+GlNK><C;73Kon9aGesszpdV@i;`-*7
zJkoMa9S=0@CeEwCvVX+NVBB%j*1ato<@K*E@MM8?qPw|e$of~O4lr^#_pd__q)(U4
z7w?IOBbsA56spQcBz|<8ke|E<<6Cnh%djsats@#nbR7t$85DItr5wmCFH^-XFfmOG
zr=Vj;m^&*`&V^tjno-3CuusT-w42E1V*VzYcMAdF(}yOQWN-Rs{{VdoVVr_~=hmnR
z8?Q=C^U|R=A%66W_zGdYfOVT6@EUe~g>um+6ri>$tamZYNRDS?{_Q#3pyzdGDvBCN
zq^?*BO(6%RXG?sM47#~r_o}OFkj5|}V~<v>{k%%#X4Y}sQI+TBU(UJL@e1~~U#@Db
z{wVShm|I41Ladm3Hg$xkQcJEqGf|g9de@#m#2H9CE!9Z&s!!wHL!F2}8rR+xk?I@Q
z)Y6H-7{mTm<j>=sRmtaXr_E8H7wYUexyE||MWihcS$l}e;G-YHnf9pH_&+m>@<j0t
zr!(w(ql4bGbp1b7)!$@SZLnwNCp2=%O{985UB`}*kE>HY*8n`r2>$?qSDflvHlwAm
zTZ@TZG53{-ts5^19Y)zEOWANnahk7XA#+6Rn^v=o9rtj8I|G`9{7I%pr#I1LdRLP8
zk4c+LzA5KOz>*0k+ORW$f>@8OM58$FTv}(UYgc|A)TR>L>JODU!kh}rXYhP0%+Dd~
z%Nq0IGo17FrNFG(xz!v@;<-~h#?^czhXUVsr7`?L;gmoVPgcR|R96fzDMwx@av?lT
zN7U|M@g|7F<kI5Kc*=^Hc)ryK?)1o%j@v7p@co<@G0Q8j&V-EnQ1<MyFh01Wke6Oh
zbD|zLlW+@WiV5_s8TGmU0JGlWB7lX?HrE=k5Xy7jwp8OzWjQU33Th-ejD>t%sYw_<
zU<cSzr;9aLEDgp7(z*D!3_9VBOA*8L&3iOx({N75ElShwY&VECM?dlMz*H}*U&t``
zE^47YJ!uKWb*eP~0F=Sho9b9=>!O8?#EtEm$$duWaor;k=uKZEF|e$c7;{`$%R=0y
z)Lr*FUkTroxMiA50)AYY(eZTtb)ai^EZ^*NT&A1ln}Dow-!;&nwN=Ef?f&VnH<{k%
z=QnFD>`quh<w?l|Vz!o0>zrVopw`{JjkUylBV+xlhVMj$erR_g^c^d%jw_Q!V^W_v
znYn$btlV)^e`DPrxOX3VgxKB1ozd57#z5zEBt}6r(;IqJD}IS_<gzh*;}xl~%I9Za
zYOk$Q>dE#~GfE#yZZLXQiG|o_<x%fZn{)@6qx|bRV<~hkQJGH!@kxSl#TNlkAK%Bv
zp{#lC<numB4n2)#@vtpWk+N_HI3HR<=)GNkI_J#NG3DFyrk8B;#EQ-1S7N@e=5!5n
z0&rzh^r&Ujp;3e+o|TD{j<kg4qFC8Iic}(vC)F5?53NGlgr=#|V!7pro9bw(#THH6
zr>h!ixN^YmJa?!mb5QC@^(&Plri;arM;fV%aRag9kodlQVPOmS*EL3KI}~&>c&g?^
zE9I{v9M%+)86BAMo@tq*prL3W%^CKiw*r%#(+dkl9Qx7TkOeIz6u{Tgd5MK+74)p#
z6y=#~VV6IJK#a@OA%~?<f9G2lvF1FQ%XP(eQdfx#tiv4BdYX~P<4gmZZXkdR(}3+t
z7M+Y!<pG%XrvXY9osKBw7{V!pb5aqCX%w75p1|$ATI(Qh-QXPNxeH^q=?JdA)MYuW
zW&%hu-77y(P0%(vW17^Fd8#*Sm`Ur>ly?i9((<%-qobVC;8$AMLJ`F-C_h?JPQh_I
z(SeFl*Qlc%>DWS3fW;?TaNy#dfH6&F$f*DVkcxH!5;>(&N>_>ydem}&pb`x-ro~1^
z54Ao~4IQcDy(THborVIJ9AbgZDd16H5DHvzMoxI?N-C@&q*9T^DFT%6wMhtzwF)_>
zb)XCyml20zC>&F<lg%@|D-2WkQH-7`4rxUe0Ncd`WOS!>rN>$<B0PFfY2b54IHzDC
zJ!sq3q-Exl6j%u@pn0+r@y$#2Ntco`J*qod8a8DIt!PIxDjq?p<+!d~&{>lCV{S61
zrFQC_@r+jqrbxq6Ni+2o=y4!q-PbkpnY?)_o{kybBwkn|gpUUUy;<4CBCpNGc>Kpv
z50}paG;HUkSitwB02-cPE0w3J<$6@x1vwXrIe>&9qh}o|#?U<}3gU$zAb}eWw1xsu
zo|R(M6C;f0o|NJ+jK1|wdV!j%cknr<vJl%%F5Ru~>qzCdsmDsvEJZ7n+T-4upoKW*
zu3n7nJZHUEMI`gmx+zQEOqnAVQL^F3=}*8Si=YL|dYTmFYv}3xCz~x9Z%!l3Wv-UQ
zW)=sna=LqMzFha>x~l`bAbl&q&7<$!?ZZ7RJ88ib;Jnm?VDmsmJ--_9?sYUl9h*rr
zvhuj~s&a;kZdU|#6}@7Oy@CBIhNEqlX5%%t)*VM_6JnxHU#|kMNUGMJwUh(x_pK{m
zp3R4FGgV}jz_V-%TY{sSiRQfzfpn3jKGCrmT#z~Du&;a)+Kt0a{i4VS#?fB>T`ST#
zE3Hn3-tyzg+V}B}JGCR<OS>Q1@gX1WS2+*Ecvyb(Q<sjoH2D4<Y358mp*UYwHR+tE
zM!Kv~t9iP-C+gJz)wI!attPfMgOH*4sw?p0MaTSp+&9sO_*0kR?uL>sW|_a>RGUkv
zj+Vz((x<r*!>Ebm>$Du!mY{)<AJ(xn?+Ix7RLgN}k~E{#)|R0=q-BR0?OtALl&Cio
zrw{QN^RCrrBjp1)sO}=&ZMy>lwM``LBxPIzJt-|NR(KjG94{EJn~MF{G1_8pD%k0Y
zyJ>L#X5QGVjcW)zAji_9OLUG<z;o$Q8mnszkw^ML1ojnPKo)X6d8gkNSrSpf1GQB$
zyT8xRy+3C8dBC)|4h>5sK+X3^soR*r&1Aqu9`x+f0Y2Yaa5<?O9SOvZQWhbq5Zh!G
zB#q4gNGIFxRjvZa%69klr-700Lnc7L&22)jvz^g0R|mEdCNsySLTo~usH++KI*rYo
z(i?!;#Ya4wxX9s*M#mzb4pw#pr8FG1D*Us3Yf6sl><H%n09e$p9(k!Q(+!{2p@d=j
z)+<y5o$2avOmXuX6|+bOw<(GuY>G_r(wh@}#C7dV2>>-5fIMsurAT|`nBzYv6{RO>
zrZdSrX$X&41b-Io-j&Z_*I(nv2ijwhWaqf9H+DU1^voprsYRYOXxeOXt1jOlBdt^o
zlg(HIbU%f57&18qMMOGOrG8A4QR0D$2?m;TOVrR;iY@|Db>^3)A^d0o-KnOYw2U#w
z7@!8@ng?1AXcT~O{{T6ljB!U{M^j8juALZrR>|izl-x+e-mYn>ERs4SkUc6JwDRtq
zY9qTD2<uCcNsfBaRs^a^1HA-{(^auf0|%OsjBNB2ihghCX<G-SH=Os)JAgL?(`n2O
zIi?P@?jc87ky~K(%}1ZkgY7^LW-ZC5#&D*h9Wli?cQqhdmAej@s;z*=r45y+++dD?
z`cN^s;LuML-^PMy0M9g;%^9Q}DFEPpYIC<0A5tlMb49|!W|SUjgitanZUmiq=~GC^
z$O`ak6&r_MDM<AFDGX%?nj18f0D_&zdT1210OL$O>BO8<d(a@r$26Q#){gWHT25(k
zN%&G2QiI1or6+0$#{!TM9vYsciff*IDNyGXnM}0~HwxRdZ{7YltQgK46|ZH+d-I%E
z4k>C>OW^d+7~-~cmddct0M<WGrC-w~M3W47<knQ)qh{`U_M>nEG{Y(;cQ;zFnyhgu
ztT6)JG3#9<kt~~sLyUK<yU2ij;A0iA*Rk9yZ%i=stgF_~dQ1#U&N}xsC4mR8IpUjn
z^L=|!r<@bkltGtdT=x7bCR4YLm1WfMIuX=U3h_)v4y-bTyH-FTn%>o;%s3tE2v=<_
zQIv;@kw?w+rl>x(C>gG}BNo66dR6On<E2y!`qj%|4RupS6&{4=ij9VIj0%{q6vCWV
z?HHz1a5IW;81|_o9Mf@;Sjig2l_VcA%`^d0%(x_)jBrmKYbK4ZJPcKc1`qVA{rRg9
zaC6$Op5}AdwZY=2w?996hqX-sIj*>Fa!+E{d}Q-XWzTw$3@t|aCjz!+D61gr?NJV%
z^)$R@q0c;4QaU5B$p%2EhdpX(IW-VCJk~7L3I|$zd^j~2=A=XO3UL&ReW}Uvwnu7W
zoYR!^TcZgUNg4bq7aUaI!Rt{!Emq9YU57N^N^^DQo6@sp$ZHNNJXDX<>rCDA8qJo1
zo~P+d6a$Vqpc!Ngj<qVBeQE?ee~n7LMQalY7J<m9n~ITo3XV_mYRu7ILC$HMQ=Dd*
z?^&~SG3m7C=}o9*iU;RTLP4gEl%uXq2pM1u0sSe<_o<^KW}LlnYSEh~{vT?IjsXL`
zN(SMIiNVcKkz9{@X&E`~Phr-R6`M3fZA{M`)Q!b688rolLE@xN4;0L2-khBCKohUs
zJ!*Sq#oR5&5-I&^x^(8IP&~-L-(TlkxX9j&k#s&ZdcBF=Y01dQ0-YcOKEAbIN03XW
zqyGSTL)Di!75M%mO0q}PLs+B1B;@Bc18`5JPa(!lKzo||M0ZpoM%v+rV_FJ##t5wQ
z$@Z(3Y*`t71u|*9Y(EByb8(ysXc?(D6B!g>iheOp+D}>vQ5zJm3#%c)2O!s>cu&O!
zD9lneGB_Uf=j#zQp>H6GS7^fy^czK8a!Y1z>zAV9`bWVVs|rWYYEv(o+1<rB!;wjy
zk%zm>5}`Tfm_~Zytu$EeOevpgl3g}Ij{PYy(x)lM_|r^y6v*Tl23S+V`ciPd^zn*C
zMkA4Od8heU9qD5r<aDcO6_9rnj;eI-Q&G32S&nR|&svb%gVTzQt=I}IbSiRzWgSSy
zb5ANCJXU^QJ}Sc8=K%5VL86uPWET-_je-2@9Htoc&2)}c*9>?yjXXYFhq$2Q#L~Ow
zD*$oRtxAYSJJNtEMIlWzV4#sCYC?=vlnqtHwK7OSpxy<vO!HHsDCe#!qPaW_p7ko0
z&w37|Tb3A}*pk@69cx<HBg4Kj8B}AfH$c$g)$WXU6K#lm#1Bg8^`8vd=@t$4Uy)DV
zHR)k%`!sw26hZ60c6m)swT@z9BY{^VEu7-BuU~4cKy>R;%M{U`x%$?1#INQvIOe;f
zji)oicsh|C4*QKl+8C9KD+WJG^qYBvNU^(Q<DAz!;GI1s6JAS#TaTr5x7JNEgA-wa
zu3SY$C!uuW*5u)1kZwW=sM^rG4l)H$g=V&p9mmk*)}mdjC<pI)S0gncdq0<fflz;D
zyYxS$YQ}er)!3n3oYb&6xit3*Ry7CfQd(&3ynKf~q*p|+#H9M3^h<D%MpiCZ_oPvt
z)-YQkdzqAR(3+!j;(aE;F%S;^!zQch8dUePmurF)uPAF0eHJ)>i*YorG=^$^GPt?Q
zLl7xg6Ka}_uah9!dt$WZvx+`|XV$BjRFU%Iw*sJ}9z!(w`^43o9S&RRf}CtUPHUjB
z(VkWhw3R)Lb-H$rmWT$>r1SNrBQr+u^}U2D+dq0oHM9}%0xer<A%GI#41N_~`%zi3
z3S{P(h$Oag_x}K$XI>&8>MHI2q>&-setckK*10W1RousM!1ksCFCHZy!cVPHiZzl#
z%Ai$gZiKA9rn;XF_+sYz(dW67WLe0^dM$HGZAVsOn>>Iq%{eSi@4JfXVv9<KLmRMV
z1F3A+K@WrNwOc>6Y10G8O!4%kDl(3&+uOmOe-(;``O}`YI@k#=6<J2#de*wOYfFcQ
zW!oz7!xa<(O~Rb?IjoJI*EEs#$h-^=g0MVcZf<sbz%Jj`wXS6eAS%F&)<1~mTct?D
zgi+7EX;0!fY8)fmZIP6K3LJ6Lp9CA+AHt_(EhgNPjtTXvP@sx7Ju%H`HfE8hrR{_m
zgATnhT~41a!Z#D?Tuz&EWWCy;;0{f8R*@Gc=HOL88aD;dAY+=5ZW|Z?^HrdU5rG4m
zx_~MBr|VWhBuK>k%xXz3A}f%7YDkVwaaMe$W#oZUGCOh+b}=A&)q9J}h)W=oayMhz
ztu?c;$si9}&bUlxb8|q<_6+Tpb4sfcj5Ri2m%T$8?_={CU|3a9+*c*yDb?;s2Z7qU
z^KM16zH&gXJ=JFOFJG=#iq59Sv{s{S8-2>D@9A4ttTrTSe(0>76+Fw_o_4Nk?c3%;
zefv>OXig@2*r>!*Y;o3=oC=J-b5?SUkdi8_goQa3Vchf;N@gnEc%(ABzCM)3e2h}a
z-OfJ>iO;125za+7oKSO~w9$}HGyySTv``x+qZsc_P&W?z(*k*&mL2Jg)p+lcUzS`c
z_03HzqCdPc4{E73vP`7JFlvoriwzWVa;yk716q^FBB&I(fr!D!txXm5n}WYI%?lr9
zlpb-4U$T}w(h1$Z?kNTQk^SiD1&exoX42~+PS(J#k?mGgKP__0se!k*u0?fPRpMVm
z!3@KLiVSK;sm$NP(96c*+ut>%qUv%*AdTCp#!YGJnqZO^bzHEnP!>r#5WwdYSj6?4
z8J1|n0zQ>uNESeNt|vm)SSq0;6&S&;+Q#uFjAT*~LTe@-=Bs^_uQ;xhz$Hw9Ri(1$
zrah^Fh$A3p7^_yYv_L34dR2)nh#2coh*=JCO2BVf&RAfRpGw=Zl!o*IxqCTEvXU@s
ze%esSaQmmVA)OX?N0C*e;ZAzfZD;IyRfknzNuXsio0qLd@DRDH7#ww>fx)0f5QqaQ
zL6hFA%^y4i#a`MN`_ycNaX=JVNKd*Cwkm^=TW&e6oDIYrRcT=algHsjfXrw{+JZ=i
z!RwmPmL|bv{Hlbg_}n^rQDNL_9lRgTuiD%MP&3cHWtJlas#IVU9@MNCI%{j7$}o5}
zrxe?lo-32Hm@gZ?m8%uQjAJwbu_^`t=77Wwyi^cN=C3VMvjygu4Up%xRDAXHtIVO-
zBCEI?IqOA$sL}z(Xi2u8YK~>Yarx2|Vugkc77>%K>9NiG$dm<P&OK|HTS-vhjw`(u
zk32;Q>)NWF6;u*eIi%1W<)y2-@NrwqZRY7yLj3%_4|=(2r>gO{j=2?et<_;+)8#zS
z2bZLqS(m2Mw-u#nb^yWap0z^pRvkuR*_$<H+i5(0RV5uQwaXR*x2UZYV<6_RV4G)O
z&b4i4&uU;=W3-&qK%Lch$r7(TRe2*ZH($npMGL{UU~$&CzZa0PN9bRzcK1NY10Uh6
z9a~3_RSG41BIg4Y^3<!t1DbnUp9$>pI{0o_o@m7G{(_KXo|WDwgEa64^(;kCAB41}
zKQ+F7we|Aj3<Oq}XOsPpS-sCa$2cSMpfJY@=jf)rE<X=xk>eK8kN6E)T{6v2%L=c!
z70W&~!>@)6wUSS)k1YuA(m6lxgHo-n!*qgQ#SMCr+QhvPe=3n;j2-~|tD0PHzRfcK
z0I>VW@@Zg_6ShdopK(mbe@g3oVvD&5PzgP&BSg|4P@P%Oh=)HndisnuaZaWUVybA5
zHl|-SU)e`e$A@$`zL{s00>q>+&wlma!4g3jL|iD~3X0a<E#g?vVOOPC&INvDo#zwG
zD!=7hA5VkAM-L8FxZ}+L({o5k#ds%S$@r5CtEV5s{uRggkvChZUQKo0C~dl=C)oc0
zO62w6O`-mE`W{Cs;i7mL<@?5Rj6Pq&skr&Rm34?JaaCj-*V3bah!PK_S?atDnyrp%
z!i=vJz=67)Q6CZtR;H=MfRo;$YU!HNcA7N-$fWPqoDul_+=q8hmYyxH801^ZbLh46
z^MmF-#ua1AwIj#lMk>PT_pCl!Nr?JXgGba{{{Y9FfK>8G9eQi2NcE(xCD1iC96$%u
z)SvK<YD9g=^X_Q&av|brcQSiXTT%F4`Nz*JDeO6^m%>*BjNM20EmyOV4;e?f&m2+s
z*GfDmgNM66fTbQ8v_|>vq&~xnYLtxLHj3(VILV+cJ6BmBhIIKG9%Rf%`&FrL;EOkK
z3~tPQT8UF>U6K8vNZ^3SQZr5kagD=1)#?fG{TCnTQGHAQ0QIU#ycPCaSCi~;e4{uG
zTwhwl-rVS~uP%{imJqnkMJ~*Y_WD;xHnC%GB$54!Fj0!_s_o)f6Yf~YpJCFwRW$W7
zd7@iH$5>s*%NvpGhNN2yw;5YmNdEwKx;;Btn^2k<<F-Xv4&CFmdL^fYa<R)L?3lnM
z0w@*9ip0>ve-Vy3gyrzW@x{_L83)N{E<H_1x(=wv{yhl#wR=vfqg%tL$s{4es_@n1
z*LwZ*Q_C2BkBaEaT|9bjmqRMqol1WaDzAq1LVwjD_AOH<g>@$CU{mhKsZFn6^%Jl@
zm0h*HMZWdR5$r43SwxOUom4jy!Z&1m_g3m^LE#ornQ!7BO6OZryJqHN_|l8X*$!km
zHKNJ<$a&3EqaGKsOnI7<aC5-|lz4kaULO8K{{RCO$r)umWNKqOHc4aG)~#gm?q>69
z&#Bn1nc>LC&2a7YY6LzQfsZcP^<#?STavj0ij*Iabil16l|gkfmS<V@JN-6Y1l`1z
ziHUb%3ZC`f!J@g1OE>|Bdh#p8G<i%q)tmab2mJmu^gX+8wTZn)TKSG6sZ%eEWl8RB
zho9Ci=24GCjE-1i=~DjyV#AO1pN`tlUTMO<GFj#={iCbcL$RCvkq=Vu`BFBS5_D$z
zR*A(nUX_#0v2X2<*u$}de*w3F-ZmkC;}y<X-_3B$Bz7k}XSH?r>RR3XF<d3KVZLS0
z1;4F(S$;CDT2Go<qdJt-UWU{x&nCtsimN*na=AFqdVDNI;|)>Yf+h#lSJ`EA=C#i&
z7j<&1j8E|q^f;yoWnM$IDFuy59DADry{AnkdFpP(NiJp?*_`{;c`mNc8x+=yMTcS9
zpp{Bhav`aV)30vgy8{Y0b;WL7O?t>m;1BkNWLmPV+-KjdbyBLbbIwOK;pTMGl9A|P
zYF$|4ZrbRv-pBCoS$76wljblr(_Y3loMVpFhdg*0KZSXRQIP&%C+8-sTt_P@8OoZ|
zb@s`qWB`twRmIp$<K|tmGWt|RaaV7n5zhU~9Mv<$deGK4Ihcd+r;fDIN~bk;5iBjX
zWk02QFM+Qi*(7IbusN?bErwImo~F7>KMv}z7`d{zK+Vr}qQtYX@ul1?ZjtX&$F*PZ
zbWa|TrbQs1TIMW#E2!MvBkFf5QBLeGN&RcQx7lqH#xb|joSI6)JoCl2-)Pm|9ByNS
z)2AJ4g1@qs#^l2)<M@>OSFmbY5x&(v)Gl@oI0CW!W8vuTtOT);W{hx0Q&Ul=6pD_A
zmL9a3%_|HN2;>}60h;DC6m<8e55kg{r2{$-3^)?HXYY2a^FxW7(y(-E<g>jD;FUaa
z+PWr{C2i}_&`Tp&Lsiv}bY%uJ?@*{6s@NG^la48&9L&0P&6~(&*|nP^YjaT`#GNVg
zysvvIyOMLjG@BhyIj>(2FL506Ldm?0Cw}!JTDXsJXFj{BysjHK#anG}%!tK=UNM?g
zr6o0HD91t&zabToF#X}JUpgVyRQhJJt{qIosm*1Kl5tv>MKs6R?lbKJCbyC%iKBLW
zZRCSo+*c+S+_fy4tkO14KM`JG(01vqA`lse`~+2$)@_O%>f`<cUU)T2mHV%cr8Tu1
zx9c<G>p&gcy62SNx`}q4tlU*O^^qzRA~Bw%8sd$_%yQBb^)$mHk@vWyGje@K+6QNX
z1!+(5pIXnGR=kks&MWM-NbWsannf@sd)eIl(>eTVGb^9sG~V=30%nYwF-wX7P&lN|
zGy%mJB+vnxN_xiUqLcVjmI;`QA^fNUDk^hnI0Ts4K=l<Lmcy+e8%a*sXxMQ;4W*!r
zQ9uCiMHFIy7pU~3G=yWl6acyAj{PYpJkSD;xamQp08-EfmW}@aA19tj>087c^y0bw
z8Hm16KDE<hxbH|zsdEu%5A&>f2V7S4%b1U9#FapEk6P`+>WtY{*N!SYb5pYM$6AXS
z^sU@=5UMFfDvVO&nmIrKqwuF<leI2Uh<FsjKPq_`r2Hv3jA{%_hul|RVt;l!=D8v<
z`PWmXK5b)e{p*^duomT9cB+>se4+(ietH^$ZX;q3%m?RLt-$1`8)tAj6H$;V#nNn@
zhv`tB)!Q9_Z)$K9VwGyrBur9)#V8r2$0O36g5qL~VwB|KmmTTY1Fb2bFW2cxMLtj>
z>N?Oc4h=sX@zR@)X>y2h>M4YCQV=-LT5FDIuv~5^9Vn*(kwt(hdiJ1kN->_a>;Z~C
zl%R9gml!npLgH~j9Cf9}O)27<LL)TM)}M@;0KuZcad!8p$g3NEQJRhV(r9-h1BwM0
z#W)I903NxgcEunRb>@o<2P6toK5Wni9-KxW(u)WJdt#W;;P<J<0`5KN+`G2=&?2h*
zt?62J`0{q(6It$=m?*|uwOxmF921tuYLH~{Zieb7^kJXQy(Yx@mZ-pSit|%3BX%>k
zy$eKdGSNPrtLAgqZ6mh_E{2}micNquOc$*t-cL32H$4jsC=D}aO-w+|E-^*MMX-Jp
zsG}TIyJ;10X<SwqSDI@MDs7^Wuhx~og4<}h!Q(XBr`aJ){#46|B*BpwsrKttEQ`%>
z#n`qNsjo&Db?n_!H#<8I11u^@R|pMA>w`gD#%rD>6(?NA53N8r$4Ydvws!CZGdu%b
z2{_u~xtV>BJ9aoV3K4-;wG{c3`ubHRI5@APpzj2E^;f)Ew;^s+*Hx!5^FJEo5wR+h
z(>SiG#q!bg!LKVfgR*AWXQ`$@4r$?lT4bCxIaf9Fr*P<JNT&?>*mxjRm+>Tu9XSWq
zp^yb!<EMHA>d|%iYPniUNJU0~V>qcSlW1h;xv5JoIH_&8CaF(L2!hFTJ0l;I@(njt
z@g9?+%&|_6%)>t@sUbTrdUCwgi=86M?bb_+DCS|tSaz>#Dw}h0W*CL;+{90anktff
znLqEEr$3MM$v)+z=ie36!Jug4pX|6v^eIy=nP7+I(xFrT09@<dQAZ8VMh}Qqmg$Ie
z`Mvn555%1P%^`{RuDvYKIN7JijP==8+RXxtTE;zoT70n%W^&qpj_&W}iWu~k8_o-D
z;cKY921{UYazHq%HnF&UvA~Ku@lU;6LUYTGrnqwmudB+&)IKu<YZX1Ikj5cKamnW-
z)Y<&IRZE9;ZN01I==<=LPWDQ-d)KB73Q2HDs<Cq1)tuw}E1uTaWVgw>1@BZ+Ga7u&
zn$er)x5($(tFnU*c_y`uR-wqmH>y<VcSY@0RAnl7IgImIv5F2&JQ|OU)bMjsFn$O$
z=gClMjCiNxbYRc`l464^a6!d0Z9i`qrXov_8WnF!tC9sy{{ZTC)qG_~dJqU1gN#(=
zwz8Ac(xE_iRI?q(D`xJj28_uIS_U6`6_}tboKvG|RWQ9h>MW4egjImCCsEH7(ZJ@E
z{lz_f>45(LIvB@hn2oki=T73A(Z{6#NLvlf1+$z|NzXpC!I7G{=)mH9dkZzWbQn3v
z{Oit%<kziu#t%D9cE(Dsc<)|Ij0}2L=vhqp@Ugk&VwI*D?^8v{BRQygRPZ($y<~EO
z5)h82pw3NLJd^dR$A%)94xsg<9VyK~4I+-zyq@%*jQ}cSu%&)6-i7<Zhy7>)nWHoj
z>qmM(K9G!5{#q<xhRYtK6&Vx=lFn};<w+-Nam7iffYOKVc&hNW%Y=T)YWAfhGDeE8
zmd<z;FG&o~>N7}4sqHP==1q&~){DDIEo2JnasBFiz(6_aPR=Q`dQuo?Jw+MrXa<bX
z0^{YV$;C(y%S<bZU?+NZ2^4@)f;}h@qL;M_dsB$x8597ja5Kjg$L5}+1Fbdx06GRo
z-hgw8Z$VB`#UKz0N>jxlJkSA-X+iHzr3dRs0Gb5^dQxYK20R*3QDoAqbBd4@@M#Wd
zSaU@HHkUu0H=kNw)UE=WZ8&tMnqm_;>q-u3G4IU)VwJ`?diSI!ng`N@(t(CWA>dKa
zP-!qDbJmqQiXW{tPAe{@7Gpm!J*!sDu;V>Qtd%$;iqf`hWBFG$C1^Bk1C=!dvOFW{
z*i_N{$_V12odHKDo-2wEQo<c%${img(=~DpTkO(qDqB3`Ju8wVtcJF9)fa#vVh(*f
z*HU*AIwsbB(7{AOeT6LKnEwD;EOf<%gEu5`lU6Q}2+7A3$uTYfBRS%d$o}yCYFXDQ
zP}!2Q<JN=>*kW6g=}{Bu%}m2`9lo^_f)|`|R7shsreWjLn&%W_jP$Oe^+UqhIPYA~
z@g8$sxP6SKJx4VvjQiAU&u%JY7|nM<9P(qp;;h>aYPbhAW&!h8RWxBYp=g?8RHSFt
zn!_fyXu&d^fD_k>j{`M4hzQL_6n-^>M$u(?SBiviYQ)2eg9KJBYHXO`IH{rF;-Ox1
z{OV}<VcxDAihCBuc7Q5Kxo`=<rUUYdbVujKbwuTnd#LHfF!jf3esH}wrns$)I+Z2r
zYA`S=X;(hA4lr|A$lfC)<$kpR=j&D<p4DHe^sJe(6dZ9+UK*MXJJW#zk_K8sgr|<Y
z@$F2Hm8Yn~aa|EGkz@?7wMO9e=qc;Mel*q@HEhXlR&z`Q4)pmBX@h}^&6^<`rAPQ?
zq&XneXRSji2r1o9tv58F;+4i&LxEDM=An%Kew85Rw26$1N<La+50{E`dB>opwsY-T
z8Feek!)BuIQph=|@ma{)BV1s0sQXloIjFOP^{6yL^XX0;nobWiX9j>}l;Cqu=s~FC
zCuygV)6%UF$(NPpn0corG2W4fzAA`CcNod0XM<8Xrh%SwP|Z;r4n66eJ!(cdsOkzr
z=O0>flbT@UQ<PEybUEgw40DWUIR14Cb5F_Txd*jnU0$0VH)$T7pf>9W&U3jsj)t^d
zc<GAB@T-N>kp_A7JwMMivnu19*W>uu^5SNXsiUkB;4U*zFzZt>!No$}we{zrGA0<S
zwk!Ncil$CEtCoKvGo0fb3Z_jzh>}B=IHggNF;O$_W7@1i7$-eyS<@AEIZ&Q3F;WQm
z#wultAmgn{v5!uDYEH;gB1k@An$yxW#?)`t1Q{p4rBz&G(!B@arJQqWGP(JgM<*RB
zqOQXcHA<6_!)qEu+GYHakT5y{P(t}!SEPJIw}4%vqK(45?{3qIQdVNXRrZkP5U$}-
zGUw}70QJQ+hI>>Vmo3V;?MPE1r(`)ergWgq!o+4Q^HG?vaz3?bNIfb3TD1dI(=+~H
zc&X!`Y5sL9L6g#>FzwAC_Hv8Rw-w5j<chSCAsmXuF|r)?^{1u7E;-IAn^UjSMzM(`
z2aHu`v?Hf#NUr(M6>(-(Ty`{$k9I`_+=m#z6&29khZy?Sqr{~%#Z$P0_hgP}BBeic
z$}8_k5SlmO@=krJM1%oB=jqg$VdLpmp^bWzRTZSq9qLrxe>!H6vNR)AQJ%FqbPLCN
zq?y13)as+T%`>GlV@A8Ug6*2!@K+f=wYPt(-Ce`7<aX^`=9wzRFdZ^~I@!DcH%xJw
z(LZ$g?9!d<CTGmp>(Ev;+k#k*$F*r(5>=1#teGM*Fi?4B$26jOvONdFffq_$q-Qze
zx)N|bYd1)@x3kh=Kn_Cn??`nhgKRna*6j1;xh%|wA0{zXRfhb7gH|^s$}vXyy(>Cz
zGABEDq$6h5=#P-#R)Dzqa7nIe-sHOs@M}y+T>|El8EWF~5pbt*`qeolk%m_Q&|~e_
zG|BGbv5d5hjPNQMNRCU1QBL+IvM#T|ZMa<HsHMErWxG3LI3Bf5J1Jy;T9S(6ebk#H
z8?jruUVwK7n>jUSPqK>EFzhnjYQ^5Hk+1H?9CqzY3;zJ<)-gBT1byx~tjmpNNt<LV
z$MEr4f$nt+j22=u(z;zcMUDu>(~Nr>1ZUe=U0%Lrm6b<xRxc$McI=jx?DBg0)w{i7
z%GG?4Bx|?O*FSOMi&2n}nGg5JK|mR|Hrj>bZg}=*nxig>A>v0|j&Lg6-X)f7h@k<8
zezlt}p{UHqujNkQDACa+3|tHzGJ02BHAT15n$8`pSuw$`Qrg<$T$y_I#YHu><+RHz
zEtO76o`h44M46+bCa!GQM6%0?*CcxS*H_`)VqFGF*fDE)IoMA_-xcSr;%_76lGK?o
zoPot>&El)MSgP9`V~kertXyni>|~kR_>*0SQPkRa^10(4wNFdDihGiw_a4>B#dS5%
zR%>|`y~k?T@cdE@NS9ra?EoKI=4l-X$w!pi)JTp+QT^)V^~ssFB?!l0UX{}7Og`MG
z56Y;#d*s$d*ON8Dd;^X#Qk{(CW5e9{r_7U00a*Ig#<fOYlZu8H+ix$kVy+(ah<YN%
zho`-}Zjg=aa%;2Glgur~26)ADwsMArPw@_>x*aZDhQR656-oQ%u0OlE&|AWRfIN>{
zzrue2IjppEjt@?idMQ9%uUj*muvve)2hxu@SDKCGLcI-Dc@Sp<fl>sw7rAYV$I`Rr
zMw8|&ed^*%8vW?==~eC}Rr|lKA(@k|TLzgP)il|zP)U-*pL&Si!Te5&-&$Z=ySiws
zq$~Gv&3UcVjQ3JA4oi16+3GrsUuASjRF)ON83Rh$`F9%5rl$0CIvpAxF49RbL2mSu
zw?4IIGGWtEI0pi#NclCY(HxZ>=Gg?C9zQCFJmQ|`ImxKl{V5QE$icv>Q#M!dt4w}c
zr8hK&R%bb;WFKmC_3N5u;%FFT(hU9-xH;z(cc2FXK&Qlicn@A`65L}PRQBnSyPzFu
zp`mUPIS*f&t0-uX9Ey>%yqxqjgmG4GknqUs&tBBWf+rlWKBA47=|<8`A(04tvNoEK
zg>i;neP|)Rv}Ex>4G|`Kbgdm4;M?B$VBkAv^r{5=QmbttvxfDc8oB5o8DqwIYUQ<k
zHKUlyxIA-#Te>yp+O1WOQH9T~Uc0hcp(<A+9OjwFC1!B2$YWr`BD!58R3Vfrjorbn
za{AfquDrJUzNVJl+6+E$eJL<Ut!etIG6d?r^`{cWa0zY)wRxVOsc!>ofWxt_rqfdS
z1MknZNF4;0h!>7(q|pF6WALN<NJ$caz#MbMS2qQefz(qF<#dg}tEo6pHk=yAaQpXl
zt1-!yQJ!f5(pcX9@i!6IrEh?*7+`wW6>k1qfSTy+E=g6-Oi)p2*Yl{sbz(bIvM<e^
z)M0wi1yHy-rP>cC^Q#O2UwUa!R+x&f0A}6zRBa9hI+0fKj)RH_<0gP8HNVPDR+iIf
zJq~><RhQ+*YJl=~b)ZHC#kZHybDv785QQJsx;bD6u&n9rK4LM?wE$;E2w-v2wBebK
z1DqbURHn~*K+dcf55j?)(8vf3xUB?~O1LAXb8yP)Ps~TsufcLu4b9GJ0j(T>Hq+}%
zC_=ljRhC3zD#|*Q=72NgQc3xE%|ZbSfGbhgoPZ5iU<uvO&;r{o8}-dvWI3v9aw4gg
z>_~V&l>j^)y#N%+n0ahZOd3*nENZpPq+7|3a-?xU9(8`3^$8!bJW@crPX??=1k<_A
zIygc$O+y)K2-x9GY+4<-?rT0Z`>o!t!N4t?P=;(I_&+s1LFOiVRy?;mNDJS+Ubd9&
z#(K~MR|*72n$N{+O&;ZMrDYM0JBs-n{tZ=9J*>W0g@mQ=MrjH3ub({t>L{c?Ps)@~
zFd~is;(^5(1oxm0e_hks{^A(IHqhB-ABPpKXJs9gvc!M@2TGi;Ii<~a)W_DH2++T}
zjMXS9Idv9}b4N6l!e}iaJkoPXo|Gg9DdNlxLe!qUE11>(dsZCqGhGjiq}zFG)A9cR
zKU(MS_PwiQ^R(CBWLja-;A8&)h|WVN9+g^7Pg=5m^LlPI1b~BIQxnf2J!)k8wGU2e
zSo#`ZM#Gay9ELej#tze*9+c<fG|u!`4z}OK>l6w8iU|X^N^$XV?Fb)A<|5CR{VA=-
zTIQ)nHa3k(9i^X$WxHX<(dk-=dnq3=BzspOq4JE(dCvm6bOB-9Ys;35=;pa<E2nur
zew67X-O;})tcq|*8O>_h>4lE@FitayhQ?Khv8!;$l0{r=MGMN}mLie1-_n)B<#7Q&
zDHV}_8HRjgf;jiCmF9^PB~KkqbNaN)ET1PBtET<pXRzHp@h2ym?R56rJT4pN<C@^?
z&+i8~HQL!e5*F{cRn}L7Mlkr1*-6V}Rcn<GYbeJXPZc>kkqGXhn8PUFO8mmFxn266
z%yvF})~!r>#m}bmf&A+!<0Cz5tnodv#o`Nr+~u)YZx|W$uhKA&nv7ZIRnlzO@XCai
zHvZ|aZL~YAVL9zyC8DuR;PkI((;P{rLix^CzI%xw?nXyO74A!U9{VX&kKyTF1+By)
z)b3LUJNlaX3Q?F`9^$+&#n70w*@5GB@8`$$uC5EKYO;ZzJ$siqryO%p4z)C&bLmiL
zKDGLB<B}fSQ=>lA(TopTbbol7V!0c0pIT`(BM+LGdeQ-%>OuE@wHta<)9z3*#jJ)q
zh~!g(j2oKzCrW=eNVZ}9-|(-TP~hjDmGlpVrt`c%1N#B=uZiO-Y2j3lOD}%&M%whJ
z^`<GOfnSxg)*8c_YYeU_?M**)(14?IKXSv`xG5LO)SMh+b$SfLDtnsXwO~_Jaf}g)
z_wspPnkH3tEDj__%}ag(3TnA<=#@3e-4dKv+vPLS9#$=0<u;{^?K$Ft26I5**VNCs
z<3JelNvI{}r)(V53@MCcL@dfrW18zwtd_{$)yI>yy{oCRlYOFd+PsX?H-eGff_k)O
zUoTq1xEUustE0YLv8)S~A(;BtgpWkbam`nkg{x9?Ri3E{obIa_S(M}2vlw~`+SQ`V
zD|&UTX0KX<yb;Yk#%7dsr2HrYHK`+?mE>_<mWQfbt(v4~<p2N&rE$lnd{<xL1s5<d
zf4!au=TRgEu+(px_}G1EP37C1mvdSdOBJGzkjTfiR5$7Zl($}b=9PlvK6TR$UH<?Y
zV+rI;9FRvtQ?{njsm-!ywhb-5sT|U(GAiyPBRwdvu6ee-Vl6cm*f6Yf(}HU(bK1K9
z02;;x@&I^k$Bxy=kU^~Ei%d=^>p&nLquYv|Qrr*TJLk{}Rx0F5Hnv+8)>#nt%EP#>
zejl-h{{W9^rf<a8MPO9gDOgM^pSr^oSWLAaw|ci4G=wfHqMmB~s|@qfgh|J1t0lIi
zP8bvXU8^mwr8)V@{A;w;ZCc`Tep08g6`0yUBZObdv`vjz=M3^6<1~evv8^d|SrN&|
z$81#zU@*Bx?Na2%L|C5m(!`#%AWy=lj@4X_1}ZOcl=DVwU;8>RGmO(#(Fy1&0hQaK
zrv+osAIi4U+A)ldYQTXukCamboe@ag5Sn<kow`PAcgR!+j<qrZ695t^0f4%7%l`ll
zDn-(68w6sy1q==d$JV3|l^m`<qJTN|(WE>V{Hk%G41Cfs`U=+)M!)jW2mA_=t}WA-
zokaj=E{6(_nV9?M6r)OoPu<Vftu_6a{{WYOaoAK%s@V>V=jbQ`oz;|ZjG~MhmeSQ5
zlh^4{-0DzDpdvO!MGmTM&j=2B=8(<E?I8eV1xjLxR~Q_7RtxL0G2$cwqHSt_;Q&wu
z?bg$3<8Et}k^W=FS$$gOPOVhhOwa+7&oqSlQM-yv=70iew7E2bfs6S5lxH0&4K8Q^
z$uv=(Xvm-fjAy+r0i^HgKn5@mG_-=3wrB$GlyQE9aBHqb`D=~S$XnFTMo((&qx-r2
zX%fiYN0xEcu<lcAtUW8CZZqDn?-vr2U6@y?oQfu)+k;b{w8AT~qDH6y)3HhT8gL(l
zRe&*(O~pEa>q@{k6w)}S_VlD96%7n-0Tt2dF3oP7j#M01I@|+Wnmc~wMsfA7YRIdb
zO_HLaVU_0<F&G2Vq1%=<%m+8ACN6W2ygJoFGC8dsO#;e2YdaVRHQ!HEOArG}C<7*(
z7v?>yR4afVT2OIDC<7g;tO49o<3CzaMmY7SVE`1l#USfNFdO_>q{lSkDG1Fg1;xk8
z4K$33ct0*EBP&Y4MmVPd^`HuH98<6j@69a)8dFZea04ctjC<2ZYIr!s77&=l6s*~#
z6zl^}T4~KZ{pwISpjQ=nN<+$2k$@K;jVq7co+?1Cjwwe&Mm_03%>@m|y(<1Rq;pCJ
zN3|9KJC4-(R~Y9$^v*NwQZW7AXt0QKaDOTRA+t^^?MaLg{b;bp=WNQ|NcF2eXfh6X
z#X%}y4r%D40QaoY)C+5pymhYI!n27i(SM0R6~scscFlC26S;J{l^pStkIKAU@|QIZ
zZpTIvR+--~N($~hDIz&gc&FmNCFpv>6#!9+aU60uqaFKH+y>%>2RNtTW|Qeo;t_@k
z=98%FPhpyjoC;SM%Y+SXz#JOHu{$ox=ZseI0!7>FSu)$3d)%s%yP>aV4N@--;Ufvh
z-b}FP4aGbFV>HH%_J(|qYIJ!3`d0^`p`AQLzG^%iel?<5S38H&s!G2$dsj!aa<#={
zJ5XH48=w`KKN{J-Oxm1vtaTqZJlD`*<$6fruD#$R7(HvK)1Pvoz~Z@<9C~}!{*q6Y
zJ$)+-$~UAuJNJ$G4sq#Hp&0b0Z4DCVt|?>aJJ-ue9*H9W<7*zh>Kl;|P$TCZ_S5B4
zw~8)e*>4#K-!-#Vrimd@@{VfFsml;*uv`pOkZwtV1B%3Bqy%0v^O6D0ZCXejM;|Fr
zezlK2M4`Q^cr^nS)G-1FeB!-4x~yqU%1p|%d6kj5oHzp<)a*xGcC0g~@(7ReJt}!M
zOrq_8XX{?e%<${&9KTnQsvT6)`Kni_tY7UCar=Sw%?D6?aT*GTnqm8g)#Pm3x{3b&
zGfcl9BYV~)dZpBJ?nH<Y*o@S-8m;X7N>HzCE-RZ8n9!+8QAU*L$vc%tE8djCCO<Yt
zDY?k0V+62KUpA^ZUdLHNNQ74fLEuuB{HgN;_J#+oAy5T1ASQ{POK+G`0L=*t)|(lX
zkg5)zrk`k~a*lb;T||<)U_yZH!RDU{!D?4Hkb#Ot;qWUqz+OQ#qK5n3XdE83AP1#O
z8U5ZWK7*w?E(yg005E;16oio2p-xROB$u0Wim4ggD(GF&zZFtG9D+><L7Y^r%sJ0A
z$rk|AkZz2OR*8V1<{mkydaq7>>SzEdvmb>-!wlW3I)OTpVa+qBJ*n{JqQ|8rNWgWb
zziLo<z@>hl)_@f9qM7Ya$I0}jA9`pEzYs;{>9P!SjAU1gy6ljzBiPruUm%jr!5sDD
z+Pq&^gu|>|FZ*5V?YMre=(zSg{9JWRsZWdV)L{Iy<ZLiC^oZePhlf1%sGQ-dL(5Yn
z7(F?rApy-P>7KOF^rh-LPytA2KaCwtFcfi0+>W%+b5B2|05FVu(Ta8{G5-MSqyy0L
ziWqU8^oVe2`N-`+h>7(ShpjlN>sRe87F$Cz5Lkjh^r@S$$TZ1}S84`+V~Xi@8+4Y}
z<{4qqxoA(9GPXK3b;&22r*0#hW17NuQ%q+bS7{*i98)oYQp|T;IqjNZ70?8D^`e}5
z(jEw@00*};q~OpvKUzlVOaL630`NN1L8k`ir2sb=qa6Fw^O|o$DFGx|JQ4@in*GHh
znqOW!Py-GDqy~e*{U{iq0lHEgeiY-yG>i{w09;U~2c{{sqJf8gDGfOCDY&Eoij44h
zseg`|!v~Of^{HSxxA@X^rzql#98zE~($ILMrEnIL8Ko4U5-EWh;L+c$DWepIDB_Tc
zQJOKH^Z?W8){joPr94t&){_D^88iV(!<s?BtooElyo%AZY=Aq~a_1Ft$-ZIy>l{M&
zK^yTLCfX%ZRN!+>wjh8<>r;?RZU;5xr)Fw%*Y<Nl=1qjADcWVz+uW|vob~?z>sIEe
zsM<qj@MQVLP7X8ArE+TICVG7<vJU7>^y?`Eu@6(tKIu0`Ff-WJR)cls!H4UPezmzI
z4<tt&eQQDva^R91f)Bk@fb5q!z#LYE&jj>5^{N9Z<&PjzTZ1;o%?LQ_QJy%dVjG|g
zYBpS))uKw5i-=A+z^-Cd+i<{v_*YYKprZ^N<E?X3t|xZ>@%*c^3}sMi)T_^K^&0+0
zq)=<nfy*LLF^ZlJqqRf;sbb;9bwI*p!NB&Ww>cdRNrUP5Qy6pBw`V#lNHPx<7C5Qo
zTn@DX>-}pPBWSWYSBkBUYSe(^wO7H(tYo!1A|M#4P<+F%rgzOqoE~}_aS0a}?t#rY
zIAKjw^3#;yj+N6BmPOS$UTGiNmNAtyjrrEcIRu?51JAWslQ<{!s^`8dDI36Ri~&%0
z>G;)y$*Sju_N<wz4z#Lrd87iIIHZbYh<Qqse63K#cs=TG<E^4$BE)Cq`qNvAA{4F2
ztqi)A++zl!{3=&CsHz#PL_g%zY;)SB>a`KzR&2B<PSjwJ#*6{hgTbj8JbBs(!Knvq
z^zTtddJjsNeci^iiIj^G{n}RonIBF%Q_nqXRAbbyAjL(VK&hXlLDW=8+9O}}sIiQ3
znwfybLTff?g&(ahezXCRLF<l`4U@)u^c4K$=bB`Ejw$tM&624FM`~8U&%doCV-&4a
zK?`^9QJ(mz9AuwrjfOsz4ABf>-l8=zIX_B>^)&^c{3%w70VCRw$&;sEYD4{MH1*=9
z0DwoWO;3f2JDu-@&g(!2Vo&p~j&65ngXvtCgQaGR2con7K9$$VGCgbZOxirSxgSx7
zcczb@TdDV`PZ`Zj`0PzW-Og+34^CqU%M5p`hvbV3RWpOdT|i`2&w2$*ayZbp9<`|i
zdn2YnZP3-ie59#op-P>#Vtvpl17)fMA!FX8OoPd!bYA4ZWMJ`Lq42saMLYihe<X2U
zVHn>a^!Be~_-+v`7^vr*gVwdCwLI+3r!6j1FUER(&BfVZGC8gS>fPaOvH}mGub_1=
z?D>94WQ<Ra21ZSJXN+{w4CYi0bNN+Njn&RfuM*=vMsYY4fZ)^EVZEu1#d9B35env^
zk|rY}rVKu`^Yae070b+Jw2X(IzLh*zKD9iy`?7Y`86aeCGCq_TN)m&*G*VSy0pm3$
z7tmHZ%F27ynC@~0Xf&r;JsEZ3St_&Iah!8grNGC0)rE9!XgB4AjFyP2d(e`!Y&xH<
zYBWgQ_^4#F1&LmUf<26uu^Aoq20K*3WN-mECaRk@Q}T*$ks|Ytr6Reem6|Hf7AenQ
zPDKeSgTNGCBW@e|_B9$O%grN(S5jqxF#iDS)7DeF8-E&r06D2p=dDoGiP6~fCZ}BE
zuUdfxPKSyO;$5-|vjW|ZYS+1UnR}m6SP^F`-j&f?{Ll>c?^V#?%xT^#Mti9$%Zz*0
zct`tWDx)Qux1J^c0PEFzD=pfre2zOFm2lko`kEuMw=ON$cVSfTA`&nw!K=3us>Y~3
z=;#GfQq26C*`9Hh)6Z<-vcz{C>dNYoNV{Jk_a?1L402~H&uYuMu>^dihW4Z~+;XD6
z<sgr0oL(^Ke_H3+q=(j;Zy0l&d(@2T<Gsv$o<&+sId7ue?|^v#_pUGdS)&*j&#$d(
z=>8zs!Cp-LdepLw_0S_+Y*0s_6q8t+RNNQw0<Oob#HgnqHabxHl3Xqv06k4e&U$;f
z5bRD%aZ=f6w^!^P)zLjobh=KFr!%zc``7nuf%qD?cOCu=cF~|7y@fFqAhWX5A{i^Y
zp*X5@>vmiGxu)aO6s_T#`?lRZ$zNqWRFQZp!FipGpH`uW%bNE=BP1&^?}~+PG@?RV
z+Gn0HyjMgtEgsVZLY#W2s&{&gg_tEE%LDu)G=^u7ErwRvSB|@SRd+-uXhDi?&aH89
z`yz*8{SP%}1>S*(!x7CXI~!7`%*KmUNcUq0+M4#sB9OouxOq@JR0Qokt24INGbht+
zrC?bG;nJ%ugfTu<7xJwM&c+Q;yKWw*r56T<q;aqC3YA$D@Qa*qY9KS5R3V$r$GuWB
zoK=b%t;-~g=Nt^;xu3POJ2F2c=V`4iYJKu!C()}A#z_a?HC8xVFFvaA!r38QbUw6c
z^T|DgvPg2<yACs07g5b~B85WVHZnacr?IqaeJ{(wB#>}=*7V_Tc!tZCavvmQ*GZ(^
zBuLxYSAcSBn72Za0D6k6t6k3plle|pjCAXo$v=GQYxiesf8!lHP9<cJZUd2;z`6LX
zX%<XLyms4OQ9RR5?9)3r&+$|}{VQ{f^vQlL+%|Svy;Yauo%@W4aqJCw@Hq9S6M>pR
zbG3ho`k@~zAbm|ypW+U$IBbwJ+jVkm*)-hIV7a+Bi#3Uumbn=81B$68xv9$EHPaA%
zt2;Din67Q;_tVLA-fYa<x>rx8!S>7LO!7{7u1i8f*W0o8d9L$7jJ3l_w;OxZHFj*J
zXk6C5#A>J*U=G!lDapvIm#$i7?xLtUC+7Z@qd3UPrV>G=FP<q0%I1*B&(^9<_3Kke
zcO3r!Dy<`abOIo6z4WHzno``-6W7|2LJ~*TkYt})Q_nPQ4Bqs>a;E0?r^_fs*eW-W
zLmoP2t22l1O(NonOu6q$B<)Zhhng^YgH&o*SM{fd3_8_N821E<cr8H7A@j%SNsxO~
zDsp`)P)VQ%Vt@r8C;tG~QYK01KpPrG&yw3S@*HvLitKG?7b-#M-7#D}f|(@>oRPs5
z)7wb!ZR3g#YP*&-O(8B~F6uXW*Bf<j<U1+OduF{J8MnqkJ$-8@R?*g5a_G5iP-U^g
zM=6Ft>Uqs{7CL~JXbpz$D-LK{IS6GceJUk(jl(G*ik6Bym@kewI2C#uyth-$arRn)
zejlxG+FYxEr>!72<33^nGoMPc1U_fBDy5exyE*mEYQqp#AEg2ws8_G&SG4K;sW!3s
zeGNtBw>(sWFbc3<lnmZ19x%h9rT|8HsI8?kMlg8mPi7PhlrhE)AzYrd986e|gZR|U
zIL!hfWFU2=9+{xF53#7^Y!FvGb*2QE4f51SYMw<(4oG1`1wS#M3aq5J6xkxm4a8N3
zC`rMnIo-_wQI_8ab~vp0%SPQkQ(Nu^+<sL~YhN^Q2jf7D#h(ko=A}u)DC3_&QcG>L
zec!D>B4N7&y&yCom~9#2twDGD)s4EILw`!mjj{l4qrFIE3$*%orUv@BVZ|h{i6hGJ
z{c4;Of(AR)<dAWk8bdQCiPRn{1(#vsx23jOl;f>tUD$<-0ZN(xuJ<g<@}4Rft|WDq
zH(sLynqtQwKQ9#IEgY&y&#eG*QX@e;ibgQ!`PA_rGpIaPzQ3m+adwE<Yy*y!oe@M|
ztw_m%+6Of%u{}HX6&kK_v!Sb&sB@Ayq%u{7SwU{J<vV`q;8fCZ1wpq5+JG#HvN2Sq
z0cCG`cPjm9vkbVepU>fXDqd%&m&;a&=`-s`ew1{tkv)Js=M)dE1o27RtpEe9JL^oP
z>xuw7&_x9L{*(n~Jq<7rp46GCJeNHMA7zz>P6y*gg1HuH0p}yNP4<1fyr>7MHIJ+6
z@YzPuLffRyGhH+&&a{+Zh^bLUT;n`lekau90A(Z3^u<(|`Ig{zD^O}|U4)H-dSukd
zGijeyIIqyK6n%{t$FcL+ne$HPCQr=3@y|-HFAP7GSexazll|jR%sYzrBeBX>J!)9F
zQ|(a^QbcfSfJf_5ky1;Y)e)ow@btwboMx69Y{wbqvaRr!1ETQkD)5Kvl5<@S-P~j4
ztbYuJTMlqNYisRM<IvZUQ*)&kt)V4GdJ4FcHNUA}O3kypLfZ@D@vUF87G1&f?kgry
zek-_Tj03<TqLK)_&FK95)_J#;e(zCAqE3&TQUgXbSrci;=UJM~iY31E;~teT0XbPY
z^s3sE$tAuSfF9LQ_=PQuyJW<htFE&pZH9C5*BKm)vT<Ezn{ry;2cA1uM3#p+-NM_f
z;W<BWQ^($_+H{^~of-Tp$9nwBFpnlGOU(9Z>lAqRjae=A#&=Q!4Y~a5m20SpJm$SW
z#M))G-lX1iN<#G9c&<-T&@BA2P^2f-R=&S4#;;`<oOP+bX3YII?i68`3!hr`9S_AC
zQrSgsCCFJv7_TU8Gzi#7bG-H&a4S>8z7kDJeY49Xa&;R>#wznVbgNPQ>#__!l0BLW
z>sz$UGKmLp1$hUL;bhjco(~|3^luO7!$gswb}yb)*!B9?74atBS5b;g@z4t7;iVc_
z-dH=PRyAIk=Wcf?s{XZRKtMSaT#EflJ02MDc%?&wO#_3)3J!Rx0c9UHX@~WxCHuqE
z)}tqy0SrB9$lodNieq)B#(zpf9uFL1z0bfm9(RVL=PW)_evMujqoDP#V)$n^{UM?!
zkj#Ja>iKRfrO$zFbUUyP)eh}VKB8046)3OAne7N^xX7m(LCqj5zZ{-%Tt|pdCZq_@
z&C<J<9M>D-uw!JC10?mYXDF4cSkAA&QD2(eani2+`)qm&p=lv|d^cXaR*k6!7E{;K
zzSAt7n~OZ$LeQcI^Q1WZsn67oywq%PYwY)eXN0tqLKDZWM8n#jNJqU0Y_99YZ|RS^
z+W_>eHWja=wqx6z8sN-hdPi0f+C<l?NIZ6~e(VhWYoohgmp;|c-Y(vp*Uh8UG9(zP
z@(it7kaJa>627%aY{}G<FrBr4MhUK#@i#)tj-Bh9lY)Or^zg3nIqDHL9q41tCUadT
zV~0xWJP|(Irj5xQ;Z1VteKS||Sz0YXZD-nXfSt`ufb~n=J#S(Q=CTpdf##u$Mv6H0
zJe!CePkO>@i}M~*IoUITmCZ~BputPSC-TK4BU()!)@H*w&!BpU_;SG)aX=4dFU?iA
zgHaa>!acA506iGwR)y81_YomtrGd^nPzML&coGTi!Z08o>0GQathX@6%1CAd71wy$
z7e<H7UAXQ&Ym5)JMPb2K2R@aYi$|zw`c9Vxsu5=!9DU-v)`V92YPMF&9Qy1P&e`j*
z%V>(Av#+H#<69Aqen3tECZ9Hh*y%1UVO7jf#F*sZRu$@uuS&_6#LSJfZa(C3Qb&LG
zv7D(m=N^?VS1QDq_p6W$gH;!io+{J_C!f-!0&Sz*)mM=fYCUFuvfG(P;sL?I!LDvi
zT=q<ldM-0|Ntpitchd&2btv}BkW~AMgz9p)Wdqn$4|4M`1msZI>>`XcT#k5?o%K-t
z-n9dDsRM9oHsNqw{sODL{kC#}vsp%yngYhR_Nu7)W2G9?j*+M3StG4EcoYGB^?Qfu
zw0#9abt|6IwN}L?08H1{FZZQm^)(ruQ`OJsO~oOkFx-2ZLP?{w6aZ$7^GQqIfDH3S
zNurW~7c^&@N+=k)%>eLd{Ad`U13r`yM@mWnS~JZQPy$lXNk9cJy%dxHx#Z%Kic$K|
z0h}5E;*yuO08MIfbs6`r;@ED48sQ>4Wkcw|*Lh~e;70WnnG9D#7b3BB1luE5L`NL}
ztW8clo;a?IJNL+DJ1!}Nb5l1J8OK`m>_C|3p0r~W;3&laG>^)Tl&9K~fD^C1A*D2j
z9qL*rZxyGbzc|fhky;u{e*C9SYnrOiXHU-FPg;+;ry;_Qd8YK{xdvnE%0b+I=;Jk#
zM>wsmSu-Ae#}$l0;PkHQKM5>g7&PO-q$FppEo_81b*0-)9G_~Cb5ux}%_(1%PDLDJ
ztuB62DS*sS1}M%=F9X(?2u3M(gT*<3D@+`E(-p@A>)wIK9+c?G?MS#U^L})!7b85i
z9XO?7^Bhn*(ioV<7|kjC=?Kj`0F>;Kw4S}Gz;RB%H#8D)M^2q+!9Mg@LDrR96a^!b
zO(z|x0W@v%cBe@A1a_$6IgkUzPa<Kubsm(2Q#b~kDP4Iq-u*us3IZqwl=0S+kbbnl
zUwWH4j~LDcL-<qB;aF1vH+xc&xZ@QWJeo|>80m&odeLq31B{<)L-Qq1VJLu;jo!7B
z+zBH%Z%<m%(dB5hh`BplVzO1YImS;lrDEYO;m$LW{Ogk)9%>Ryx=zzaszAY%U{u-1
z;Z-b->vTS%t=H#OJ|o(W!??#eqywHPPzd6ey=E~0&!r#7OYKK`0C--1!j!~>V2TG!
z(ic6r_oM`JKoLs^{3^Ue%;ld97o|%qgrTao?7?&TS6Xk_lFL#@y-yt~lYFg;x+lj`
zRpwQaOsz#X+zP}gf1042DSQJ~T`+KJq>G04#cLKKwaVre2C-L${A+SW`CsW+jxixq
zo-62b`Cb+{u^Wom$GvQ64g^(@2NkEJI4sHA6}CDzq|E5QeClF5t=5$|rrVv+p7iA$
z*T~5$>Uv|QQehw*Q>1<NNsw{}r9F8V#ZJ-x0HQGloa){RBC(#MDk?=BgNkHFBOP|r
z@rLikV|y`@U5qL?=AvaAb5q=c)})R~_7sYtpakcwCp(OY4un+4lo_Z;PPnO*<}*ov
zz$xO9NB;n>o!gpM0x`s+H8j0PVe3(_!w&T$50D>PR{^7?Pi}JKIj9u#Q^s(@rdt74
z<ZZe?r77qtOYyc<JoTu+%JEdS5X*NfGbpJ+D{yKE@+TEx#@PY&ttGG#%DZOIT278Q
zrIdX6??^`gnvf)ZqMJ(~`9TJn4h12O9Ssq2Ary2p(f+U+U_M3po0>t-H2HdiO;eLY
z0?Z?VDv29rZ>?RoY&T5%)mw$zK6_F?4BSx<3_<TrCnJg>Y(HLWNQjaXwo^pME$>Mo
z#F?mp48(&}>AQ0Z<o4%=9MOytF-(Zzxv3lPb6Bx}8Ryr%HToP5Y27G1k55VfBjrz8
zL&^1}L&^1|INWKBV-3+T_OBuFTml_gvBp=Cj=uHmN;&Jrd4G=KDSDD)*c0`yrs3+I
z`+>`fjpA|Rr8!T%G<E!XQi}U1o?9k81u{XCPYt;_6vsa=ADvi+Vx5es^c5KUwD35^
z0}k|1ew2PR#0RAvF-J5SKrJcfwKI1#xu6A4z5f8#sniqOAbL~);kx&$B4-J;PZS7&
zo1WFJq_Z`nCf?_o%WiYUOK*84s<MDcYKn^JWOH#l40LL-E%nT>`DR~}9jcs?G_n^b
ztv9bzPS+Ua<BD-=j-9ulssX3)qi$#;2ilI5m<f(Lnh#v&m*4qO{(4k^%3g<>TysF{
zieM=Fy(ze-bQ~IC=71azH0)y?DS-E<h6Ho@&;uL*b4@1(pCaT8VErmQVvr6!DYU$m
zq#}S5wJ7WFM;_vV{zV`i*R40DI~-F@A&R6aq>@d|oMMpD5mLaB7~>rNG@Feg@k(((
z4P!_##wcn9ND2?NNC(PIGo?LbDx?aaB4bJPr!geb02)E%z78k=9<*?1pwa*%KmB?!
z$E_4|j8bDFZoO#%=A6L#Qvm0sWz?ifzjm!!oHyfD7OdN!-VD^%SBQ=KLP~?uu8e0L
z54};eJdutn@{ga4@!q^znlof!YcQyA!|x8Yk^#xjYUuSi3no@KX9oiVu7CYihR5b*
zC{>4JU6h}?ft!9Gx$@-OoRB&7BD#ju<nls=3tV25KX~JuXQ-_ijIkcA?agdvY0HLF
z(x^Gan8#i-RxO#{5xjHjP)-6!Fni*FHZ7QWD!Ir5ihohkqO!q@o}!+>_Nyh3%D@7=
z99J`VxSu1Xbn-6;AlEslDf9El?d)r>4Y`d%veb*zRBCELg4O82=8-y#)Tl7rnqu-j
zDeL!#wRObjnRPiGsR-lL)02VI@uUNa+~**WWE!k`^H!w%D!X8PYbhGUjfWj7zwy<k
z<W*)kYQ{%IL?3pZ52YtebD97@{<=tPxf#mS`}H*(dE3oP->r1S=9cBS`5Em>!*w<h
zmFFLwIE?dJqX)SIj02jkMon6A^70K=VT0D9M$j03?sHH#E$AxA9lKR#Ijotg40B2;
zxHzW)_!^P2cuo#GRNQv_>IgdHH8Jha6|78TPYK8!b4uI}X|ZtLwB{c-f5x;%T}U6T
zL{Bw4<2-e!4n1mFq(lcJG{QOcsRnvy6%p@QvqUuWON`Oi{3sk$jFK^mo42(<y=rmE
z;<SmJiQ(vZr?x%KG9!V{H6g7`9^?<xHC&prFWvO2$KN#)HHeIOs9UcUIT+7cg@-kp
zH9?X`T2Oh%T1<1^mz>fWG-QG6QUZNAsFOXo`qbFqRiYUpo;eh)`BEUy{{UK~b*nQg
zy+lu1nm}>Es1F}ni5f&kUPm<>b>gNOD~`jOg}GzUR2GJUNv95Zr0vq3)Y2IA`?%(&
z&piEVDEJ*JRRbK*_7_vE@O*(}ar|Q^+Xw#u)m_A(ZX>OE_k|=P`b0c%xcBQ`fO(7>
z{Hs5YE-jx)gLkBlpPh1gf@%^PrFX%_M$KON>`aY;9cxQXUEt*8=L6caPdUYGY04vo
zTe;3@+$bx|zHt(Aaa3fTq~IE5%;skc#?`07nE8%B8kTqS-$XtoJ<l~UI26&1)b%+%
zX&R!<jAmPeJ$diay@SA(zhw`HZ=2NSysJi!ec()RF<!ahON3ecvfT$H`quQ%7c-sT
zDSKY<)c2Qh-9>pMajyg?TE+1lpV~C$Q=Q7Z9M=B7u06gIBfp)jxW;QBU9PETm0SV$
zgLM_7S3I~>aFUVa_Y1Z{Jv!8Eqzn;^`qs9ovfET-lOZ#>kULa*wbh%XV$i7`sw<L8
z$JXKTeD+BgkCdcKkf)vnPRbc-gz;=VXPT3~PEpkwDIjGSrxXNMLR^@R4@$ia;;{h!
zbQeyvXQYVkEq5IB@0zG>-9~pB+DTE<4b!zUOI_bX-hiD1_A*tNU~^Nf><1iE-q?fF
z@urwa9@LD~B@$TfyK`0+<wzN<@}wU0pp+x629c>HxvC|Ny*;QUPi$hdl0X~S)ax|{
z@u-;F)ZG!sQhjSF3H(KC$slAQyZ050*-1$Js5tRDO6ZwMK9w|Mk<WUrq~fecl1FS)
zFplMv11IZK0qIbvJ9%!s>SYIL=7Xvv$a(b@vuh#pfbHp6sM~8&%1z7k?@bwE<9bZG
zUn+UVYF#07sPb|%(yGXRDz&1Jmrm?6#sz5&&y}sSIySU3Fg+<6#IFJW02+t;Wf7HL
zJ(XfDV#-s4GOcLOIIQ+ks3aWKH;!EV!|Pkib!#a*W<%^LC5kCW1RgzU4CQCG-g!9s
zR(;i>jA!_LtE#!N+6hs}=LWFvkcB_ppl2;`3YGzlUeaV#a?Wr)del?HxzDeqK09#~
zIVTNLQQ6r<E};z*h6kw?nc@rPu|WbkCqFZEBDvcgdhbeiSn|O7nx&{}GHO%1$Ugbt
zb){fCUj|*?i-(makjC9ZHfzyh)S1u|_q&iQ&b$_gmWqtqf8OG|)o4{XBR=%R%Z+sV
zdeu9Nx53N)RLKc{x_=t1*6iO??@|O)Kbm=JtoG2c`G!xeToz7vE7qn>FE}S4dr@JS
zS4@#aLUBy8oG{1ptxZPSD6OT>Jq2;Cc-GJI{{RnqmX4|iOw+`N=XC`1sGZVIRM#ta
zt&*9^By~QN+dX|jK5Nw2={h@(P;;NHLZBMO)I3EDP^pcJ9QN&0<MApqEI*66=mjeQ
z)Ud)52jf+Dsb+6ZYnG41QkhESS#yFtJ?mQ3+}&yBSdf-(r*}%NiI%9szJ1pc43ePn
zil*FvqwhBrYFk^xSCVUDoc9=}TSMkuE_w>u8ne%+xlKD;2w;N@ftcX)>sO;7L%_#1
zMdsMSLk~`S)woV=#dPdqF@VodD>qjmtqPB=US`2+g6i3B;Ar2KBi9we-KKg8UI(7s
zMiq$|IjW7vy>uFfhNgg%6x)#U0qdH?p3Zm<B~k~ybg3qA&JH9Ssilvt81<ybtx=e!
zkn=#IkN~CYMkzX+Qv;yz+)UE80Xw+OdS0DqmU?dDa>Q2`;oCnZ2zkk4>0Q>M-)FLl
zJPt=RmvX8*M#eqUf=)k5pkF!WpEF}8J$a~E@+dJBpL$~+4F&qtWZ+T)HzbS?(yKN{
zU(ThGzq?Q|#WA6TWc}c2pmXm|CmE#2%Sd+v&uUV_72ns|oTKF|+$gGda`}t$XY!^r
zh@_Ca6Pj;OY9d&6$)^WzdZScIt%{Lb(~5;y6VGaP?4F#{D40D+t)AdiBLmWu53k`s
z%K(lu%_uqN7^pxw9lhz`@zaVxN(lAEN`oXS_wP^!6?;tq?+_lD=9n|2(`{1P5X5A#
z&P`l#p5mF1ybgnkXp^-EB)2tf8wvNb^{obprGNp>M@r`6yV)>O2_MR}qq}9uSK^h(
zGPO-4Ou0nEdSja9CboE8k;WN%gI=7QB?EA*O<zS@gl0jt{YP2^aN7tUDXZ3(@<ht4
zNglNMEaitW$;tk8RjrtF+tQVaxzt%|jNBIo+}BB`>d7D*oqn0GHi6nE&q~y?yZ~dr
zrAW_Lw!MkS+Tp!LXrsjIfVJm3Zm7stlZ^MSzfaWCbW^wn92#J2W#eFD#yf*n0c`H<
zeX1Brzs;PjU4$+T03>)X=~C_leJNTXS0nSNSTgz%Km!5|F@|aR=8S?fOa=jg?M-8x
z3VkNr`_KadWc2)LS{&r#@Tqp-b4ocK#Q;??dj6CwVP36yc@zkF9P>ylQ=SIfxj3pu
z7h{f<wdLgdQ%nloxu8ZdgJ|QLf%(YBF<ZvgJ=n%MsNTUJk&M$BlM}k_&p6;#v@)xw
zC#6<vLXvU~2jv6%-6;X0mm6>cW~a)!^Nwp6KHT6{nC8OdpQQjvJ(ve_3=c}DEwLmV
z^sC=%1YlGTGB6{*pr8lrN$naLc}!y%t`hbyvERG_vZIk*gI*=HFC(~81$o}7s+*lg
zN68uPDGeL;(x_jpUWthOYnigTakY;i@m&pxFOk>1NX-M5$MdNKV6UxDwO$}QR6#)E
zm=xVelO3tEp~%3^OF3k5#|E-Bt$uwfB?%t#dRL#B;bn-R;~mbdB~?yWWziF{#?w*@
zS--jm)Yk=d<IO<s3WYfS_x}J|vMxMft4bSW`*J&+*UZNw#XZkW;~;vWwhPP3gYl@^
zOGv@ra-->9F*diUPoFaJi2mpTpJjV+@}DwdN$4}hbi;@0KZ-;=bb21VZ?xs<Be&30
zt#xdX`JGqXb6$O5l3Z9ipk{SB&Unpq8g=7c>46`KQ-)kubuJ&GzBx8wJZ!ob@4QJJ
zjABKCGQPa#ooTPheH?CxBgp70p46ZwEU@`UIK@Y$>M_MCMqAhn*7Y)6Ej6Mv!{Q}V
z;yXbjvVG!yrmINK2?eo=b)>5zoxiO%<#zX}SSk_PCsod4#B$Ds8acZ4827BDidhEY
zGRLVs>t|R^(XMff@lA$3(XRslSEYxe1s`=Db}CIs<@Jk6BY_=;2XRe+6J?B!7Poci
zcj=D9jC3`DYT>QA<QnuKtdBlU=Qnt}Z=@do0MDAOC*7->m&<(Krxiuc7pSj78xTOl
zp7iMWG{)>{$@i+nE1qgIQc2dLV@L_0Jkw`CHapP?!KTQ-$yiqGX#=G2{l?orEOj4v
zn$`fwa0t)6bJ_!b@uM8%^sbQExxrTCSDjs2M)4fFZO%8N<LE0}PoCldwqv|idugPF
zaM(1m-R^vLu69|q_N8I+oO@GRPc&^Nvmv+)0L5PsqX5+)G}@+eWj}$aZezqOH)K_v
zs(_DLt#cv>$m>o!gV@6-5@X)FEh22L-nGrjesV|UTbe8M&l#?hot}xJIek5WBZlc$
zzgo%g?3<yPJr8=;JXhy=)jmvHJ!%f{M+@V`cpe!elVNOSMR0R7vCBIXn)H7jqWyw5
zVV;0jo6K^)_4OGaEb!^r<;2}ceXC`OZVh*y9ze3f=!5U$CcOUG;j6vy+@azL-A+KQ
zGl+iSvT)DdJFhG_3~+1Dz9iczw~kB@R~W^56h!$;^sYbR9k`cB3<t~)74v*QQPao8
zGpi7<O`bU*>+4ldTvf?P-gfk=t;1r!W`n#>o?ti>9;4or912X<f@9p|3XJD8_WQY}
z6N5kq+~+u?Ps){#PSh#M=}2S2!+M<8r~E3L{yt*PNN)c1<--K@uKxhxgvLE)RV)tW
zR<9R5r|mFPUPo39+NwQxb*U+UZER;W@zTE#lCwSFJt+k)Kb0qXkRx&FT(65`-DjPo
z``1|f*FWM^-=@Ak@abNbTPtEBO-*9XV#p6HkKxBkxop_YP_jFhKb>8G5hwJov%pH#
zT0Hv7@gtBAF}u`kGC372tFmK~aC=lloY&o9-!&wB{aq>%?I3leB-EdcF^9DX2-}~n
zUea87<$GY&GCvxzr=7P$-nsEny*7=gJ4n{J8Be8QU7_4-pqu81)*ay8oDasnRQ60s
zMjMK$CvjINUUF)q_n`q!<#$F$Y*#UGHpoX@dskH`AxP_7&F~95bA#z#h7w&2Y9gT=
zQ%x&Vb6v((6gSOQw7ERJQYOey#{{0$Ode`T+ia+K;N+i5i3s*9TiZXgC-0Q-I#j=J
zvi=D{Ca^TE8VkKXH+PkZ_r+g24W8uYPnV`x)QEN7uJKF+5yZ>ie_Db~V)>*3HHB33
zf-_d+(yb+6%%rmSr#+>*u6FV%=m_(l7i!Yp-82rWJg?TdVsI;8#B!v%#Kjn6Xa^tO
z=QWZ1t0v76(D-f*(MtUCdYWBY-KUQM)mb^@)|ZAY@uhEW=e=U<<(A-$-!HeVK7#63
zm17aAd4Qhy=~gs?t8nO!PaP`^vCmUl{vU|E?Bkpoft?UI<0Ca<+~x7@Re;8GR$xE8
z6wr#A{C;JN3gM4j^sf6@UDgudXXLI4#u$P6QW_XZpdZeXmXSj4Zk?$zX(*%y<XS))
zIl5t&BXBj3k8190WJ{d@oulsYTwqb=kjMDD(*hu;y(m+TD@|=-AU1eC4Ndk1Zk+uo
zh{q^E=}jwxS~EhaoCEmP88eyyi?uY<kJgf;V`!!5X*<vXMHEm1(M1#hQg@=3fr;Li
zBQ#P_0-8?LxuY}yVv>x}KnqAHqJS5@6qHaQNIsNy85F;zAw1DxiAzQ(qQVq#N40la
zWAC$wk50A1_pZZ2a{7E@(A3CG*mH#$ti3@uM1AW~hDW7RyFy@YYg!N9L^GRlie@Tl
z7X<xk5<e>T48R^JCo~FE%>W_iG~U$gQe)|w1R?s<Pkt%K6ogV`3^iv>A#W6pgRNFI
zEvpf7rvt5XR9Xz{q9m^r)7F;XnCO1B#8FF8UDoaHF<kNKT{Y5{w{9z&7{DF+S8gBS
zC6SSWDcz|UdJ0f$ppihwYH%17fYOSjAq^-zVvJ&i=~N*H<3~ye$>xGcrUS#_Hi~9(
z)|{jt{<RD{;)VmF`I{8GF#B;)p(`LGwM`>rgVQvGGC_u@{W59ncYD(h6p9zGy(V!>
z`OpqedY}XAk<BRj(j1y{iUb&?10Py5gGf$KTvHJ$sBYq-E6pm921O`(mN5chg;|ts
zM8_u`YOr<P)~9|{Hh(HYE66$L6&V>lYIzPvdW4>F)`EbFOdRu4<BCE8&;)q*H00+w
zq$dN?g>S-`gg&&Gr!dD}X}HY;9%KE<eDP7mkbNppsL_%~H3+~yhO=mQEF)mm*jRb7
zzxPgRg7ea?z{MF`(9~9sH8z1eJD#JZ${yJ}agHlddUIUghpvUqoNT;hLF27-NOA^i
z^K4B%N{t@fH+ZH>oUH`<(74aFDIE1bTIMVOq{qwjrvX9Zr63!Uex8)Z&MH;LDMI^F
z0--|6Mk$LImbk0uYN=!TRWopt94;$(!fqGnCPsOoe)R;ON<e;UkP>0@3ZXicezl<}
z<JPL&s1b+nTR=>xM&)mDSaYu1hWgg=<a^dN_ZL4=UhY{f(aDHf5UI^y(wk-A1Du+m
zzjvisu{gV4+pE&VM)cY_pzS1e_DAI_Q)8O1YTrNBtezV+@zrB#v(=8oiO8!-{-MXU
zRYTscKv&Bln{TaiO+J8St8I23l<oKenBx}>O2dj^T?9#L*g4{eFk@nR{{UKLk<3MN
zjQ6T@T(lB-SRfO@tD{BLlZpoHPEX8zDoD9pR7!L7sbR@{de&21x(rc|%A5z*lN6v-
z0NFm^IO)wzkKGE5hF2c7A{@kM0yP-#`BaJb#YQ-%uU@pJunxW-D!1oQj1(1O?RVRZ
zaaB|OU-hQ85d@h@LG`P0a;j>yqY@8lvg0uW>057P1amMOM|wgsyi_t|u;!#w^5d;t
zT0YE4+>l_!NIKJ_!H*u4)1PX<p=l2U8U}OMtqeHDP!c{$gHeOf)B43x4m(l;%tsC?
zE5*wprHuUC(%%fkjh;uPE}%j_?ILAl>yM=(l2(|f6Ap3otzoMZB)SD-;Pt2>Y_G0;
zYQ^9!A5X@q+X4aI*1a2F4$R)=v~8{`!~N|3wNzwnt1fZ}9M_dC%>>6jl<xG<d(*Q>
z1|t026O2=wWd8t-E>7>QER+mpGmO^><NIcNWq(G={{X(Ly2-9*#&E3KW8@M7*Rzq-
z<iw*Y>hNci?$0z2tr)=C4IK@A{7)T{pc{G`2pdmYMLcJUQ_%LSM3D};rS_yfXrT;T
z8cwu((M&>$UZ3Gj2adGt(Qq5h1A=KyB^Ll4MN9=jQUjHs2cK$|2wr&vQS#@ps0qbs
z=yGE5xf$C^a<o9tyM)@@d2PY#P?J~n@A(PtILT2|IHgVAHy8$|1Db9JtvP)v#0RZ3
z_3KU}6wLbdqQD*c=A1sXfZ$V<<Lgsk5Sl^PtuKDUlRVNG8g439LKm8gy#N@cAC(}d
zFKPe|aZSxUj1TKfJ!(J)G>3{a#UVWPp@4RxgUuMEF>^?02ilC}bmou=Nz`*ooYGW`
z2U?XEa}0iU7k<?BEIzadNmpcq9DWponqz;gIn6i@X(5j3nmSSn2&xc<ic?8I1uiK%
zic)9*?deU%Y1yD2X)q&kfu7XPhNN+v)P1WLxkHw$N0lIog*w!zd8Z|KgEwqR+sVk!
zdel>n^^<1X$nC{xclNIqveeck`$<wT=1CP(__JK5t9Ng4eC7d_UzD*OYhLVbwPnB|
ztD6x7eWN%H+v{6l-QqTFXiyiBafNE=O_oOie=4h>+HHq;IrQ`bw!#3zxURD{WqCeV
z1L;(56ttK;VzsV84t~FtW?YOPdXOz?=Ly#xO<N~9sx}SOb`^Y(2;!)cynylrVQNUD
zC%tdTNcz?$s;jru?yjse_l)XnWdKD=qncm_q+WmhRq90JlO>L%U%gCDI5hFrx}sqs
z>|`=?N@*ecy{YY-`+HXFW1p!5s0-^=n<Kv!ZI2aMhc%pyVn*L~tFYQ?&wpyKBIUj7
zDH}vUPC5MP!kdnrso?!hN-2}Xc=V}pQA3h*f%w$j^UZG)2^MY6a5GXd;;X`NM>RP-
zkZWXfy~x>d-0@XiwzXMokaJK-GTEq+tO)mFp^yM@F;bqD6ZIdZX3da*^Glp{=9)RD
zXNrN6#f*=_tm7SOs&ae#Rgr+8bDw(FCUYc+;NqUc@iiJ8p0z0+`K=5Y6Y@Lb+N(El
zRvZ8-7VA>YA~vF7&O7y~f6q#5b>g#Th-V;wjRU12%_!tlls!2$IN*9!bm0AJ!nSJS
zXChegxXnyOK!fHLIXqUV!bC1VF0}(ynLh4uimbz)^)fVwhowT@dQ`+_qH%`g)@;=Y
zo@suRgRLh@LnVyk+>X^a=brUmKk{n8#yZuaBuN<}r9Z=iQ7a7QpN=z})gv+)2M798
zM}z$;cLVQ!m0X+}mRv&_^{7~5f^aHcqpd{T9(nrI8X><fahhDwjGszgxabe9A&*Z^
zqNm98BCE!Esq@o06f#ZE3@}|xobb#S^d#4$lbDpA{{S`xd47a;YDjl~3lKd|PwQTs
zr}rZrzFPdxiDS!(x%5~E`>P*5x|5$uh>TRFi0pGrEPX51x$VeeBQs*OnnM&j6yl(P
z0xtIasTqs6dM;fx%1ds$pFWj;7(8$)I3d{|r9AP^r6aDIvJ@JXP8*71t}0|9PDtrN
zsya^%S&5uV4nXWHzR==WuebCqjMqKkSmOHvJS&jHpsTj}nTK2QPu<QiYo-fB=JAu~
zsLsb((9WR{k|FZ9QhN%g9+tK!SNOY}*0XET*lFTdjFcG26xlCh)GfurV`FkKD$Xrz
zdGCv~t5%PB`CqRbR|LUO?HmEvS8w8vwM}rr`w{>g<X06e1svoM4*->{Do3gA<yHB8
z*$r38=9HCjw2TUATsJ*w8z(s6*E#gjozV@&fN)wq^_=m%ZO3lETGmO59&z~8jFDV&
zR|me{^bsl%o~v^nJIN8g^BU2%)bMay1Ja<m(~p^yBOjG#yblu)GsOo#Jz7lZ65=^m
zC%rtzg+a*Xxs;YwIo@j0U&(+8%@#Uo;}iIiv~ANK)QxHfr#_t3Nc9C}0Fm_-I$kLl
z$fCzesZK)ujW-T+NNtsP$K_Iq)QtMk=PAx;E8HPyfLsd8)FLsR{MN%r3COA!*m%xI
zG>&XcQ-*~I+dXR3OaaGwp#x#U^%=k<)~rxx2l-PtsJ>zGxGU173;-15hYAKNUnpac
zKC~UGEfDWeIq6rer$roh7^>zmjwuTHagsR4G|`=V`!;JW%t10w>04eMF-<#?GCiw}
ziOlf>#?xIlg&!9ZMsc~h1P-;V50k`vEbJt)vzPCvKT%nCx;?bK#sas}wN~0wzz6cF
zR?vfn?dw+0IO3+!FKx&AEX))PW3^IioodK!;#?l$yXhf>5B0bn^+si~8U6B&-t{9n
zA>y0FDkryY4?;hcP5r%Va~{{sWcD?ua++{pUC{H4S3jv+>2hvtqV3{=kladwPm^me
zu4=T>xs2zE&7B(1pDJzZ*Cv+VRaseLnSckOpa=OaaW2p@d-tnIww4XKz;{u}JknfU
zq$m>D24ly$H1yFt$A#{lvRiRe{HcM_=ocSoi_S(OA<z+u=tcA@*_KS>(AG?lJ6fz(
zXfOsa4l6yhJwZWf2M5raOb*u5SF&@B#MZ=jRz-Ig0DIS)rL?f%KJEvoCbYEeGVcBM
zEK)3767RsN1G-I4%2_<PU0H`X9jZIcLMRo0KQQ;=u<qov(Cxga^3yQJPjg&-_N{d@
zKOnAgfz1O(=BcWgq+!1SdK%^KS)@NN0G`y=x?u?~kjAQ|$sFXLr6zV#Rz-X0WR3#s
zlD++_1I&;y0g0}*X}-~B=sK0>wQ`8LkP+9?q^U8JOy#x~CZBGeVL0cuJJL%FM%i)i
zfGei(wvRN|0(M=otA7&pre@?Oi{V+WE(G@~5;6P@*1A(?e`hAx9TpzyYf|cVv$K*!
zK+LLkfx-5!CgWVyeB1_8pW-}zl`N`K*5^ZiJipm;`OyM8Zvwe3J{FAuEt6BOzj-{r
zWRxqcgS}jq*U1XQkUjcWO&Hr#pA|IB%l2fGJBLhGt*gfNsEH^gMo1Nlsw<o}e(BE8
zeX2bwNesn^aqLGGvpG?^!{+EsG>i^vMQnqfzSP$^;~ZB6{v*?;@RV*Cjx+Om*D<XS
z@SmHUo;_=#ynG&+=DD3sx8#9WPjedE7)-c0=}p1*sT_0OnO!Fc-jrgNj<g6)hNrWK
z&%A~))U`r*uAjsHA2TA}&Tui50+TKgyE?rVEZ#<|{3j%y)vv5h8eM~eqtct9Sb0#%
zaOypcP}C<rd*Bu))`U%0c^UE?9A`M=tw2f7)}(TMFlxItX%Ii3{{U4n_ykZJo_|_n
zo(VnafeW718O=DJdeR&o)BzY7^`|QOu6-%Wndm#!d&`xEJSiFby=WR6dp^|&q<ZmL
z{{U!V)05JX-#>U9`_x$-f&8hOqJOk!wE|#A+|5D=&$qolcp1pWJB*iddyl0&C?sN_
zSqD+iYH$*j+#-<rVGRIU1HMH+p2T939X|GQHo*M<0C-}qL*d<CRS)HC&tuIO9m=4b
zb*J_3#cDy}eL%0zARkEc{c7|+7G1cWW53gOGx${V4(C09yq{XRXEG#;!H2P~uHVC!
zFsK`Ip1E>!S_`Mx!c>b?V7-q@If0oG&Ln_3KLk=FxR3&QHKD5rQrYB&AsT_44wcUf
z$mC)b*K+pHHCMUMBxpQ@NGf<Ib_eDFip!GY3Jy+t)I#va#PSUyY<4zUiUk4BJv!Ff
zG;*Nsr`Ejo8}xPOBQ>#Us7$Bja8tOTn;iw_haKuOMmD$Bxl64kOJ`+qlkeKP`z=^1
zfZ#CotpJv~gnJ}TeQA<;T#ymU^Pftp-ehb>KVECoZu}z@+n(L|J*%6(@V(4T-zi`_
zgy;FvXm>fd^(i1AlblxNhPbZd5@7Ig=~;8=(;RL`8TI0-eTG=u06LNCw2D0z-^7v)
zqDg^IKx=l}#8J8g1c?W4TJmdqiK4*CIO4P;zhQzIhB@m%9?fH`LplIS-Q7=W&?QLq
z&3NUOvpiD<5)irFk=DD*9ehg?F@4CxsqIC;=`b027^W+QI3t5plKoup#f46!O1rWM
zqTo#?%<yqd45PgsT9wEmml>c1X3t6&Aa$k{_oOU}GFVVDb08ekeB6qzE~5u&{&dE5
zAng4p5qded4x@?;$Q!L@3!tn=G{?L^r@5dFZ!u4PwAFpBft*%2y<nxW)7F8iL{RUP
zF5ag!hhth}mG`RbR1L@JSr6h16hpdY<F@QpUH<@$wDeJiUI%&vbl@osj!i<$Nav4p
zUUhZxHrCz$0CwDZlaIo=txw`@&BK#yxz7g+&-0)UUbwu9+%b7Oaf4j`q2o(i1>5Gv
zWISVbYsjuVORZ`xhIa}_VT^vYUMOxQm0spnBpl#$t55^6)%<O7c-sKPPr)FO_*ED#
zS+M)L^sN0&hm#Nqv~kE3S;*KK=}J+s(bsAB4Y(=$tbZ!&>?RTI{{TE!0cml#1^cJ@
z*GZ?|x&=nTQQor|+`}@u^{1XI8p7wyN7_b5Kzr4bct^_I3SuO_b=n4Njqz0A#=PXH
z?Oj#Nd6A|+8uPCeY69N(%MFlwRU|ZX(=c`=h7YwscC%ugB%W_P)L8k4TB{dv<^rvP
zIjQYo#KWKmjMb%#Is!#SbDL-x#|O1L3gw7(JDoL|5anAqtKJvX<ZG*hmjttCAmbH{
zX$;qJ85xE;<aDa~OxV?(H)GqSQm3WEnCvx6hMGW`%5);I^(#p&Rb@u`Phr$l`h?FI
z2cN^OKkW;9YKTT_8r!3@39-AOYbYXLIfp!QYeM%}wNyX68TA##T-&TlyABBHky%pQ
zN?5BoC(^k+lWgvFV-uy-HI$L|NArB$t4_{M_UPF8NXYlBog+r`EZOc;_n69(D@M^w
zaRfiZ#dguB%8xG*SDlU3hW$2Cp1fBrVt;l=80lS2@hxX4&o#<faCU>#*2v{Cbz!#a
z(~h;DBXL@~(8bJcoSsh=l_1D!?Wd{{2iBEN4I$^&m3ePU)CWn|gHalqLB~QW6Ol*<
zN6UAl19Km0R8q$Sy<4-i-#FfX0xOoZz2jIRuso1BWj>hZySod`@%xd@a{|-}m2s2p
zTaZG^s>9Q*dG%f0&C;=<Jc`arl0B-XNn&bM9&2p}HF`T_P&0#AjIRN8$H+&$Xh$v=
z9D_(s7XzgV0OW!7qyx!k#(4TwX^MhIYIl<Z?_#M)>w-be2xfHr$i#Q8O(Do-8NsZ%
z{`VDkOMS8o*Gkyuk?6i0lNSu6oR#TYq;p)}fhZTL$1JtdH&fcaABdr9>7I@i`-eH>
zILw+OoMf*cSCu))&3gxlV)JxaI`<XiGK>}&@7ldy9hK;`WsF*(kpBR!UqfBLgxCEw
zlykUr&wAou0L&|~@U**i6y);4y==l4!^pyew9(e-x{btoq?QufIgc3<bC2avc+%g^
z&}AniZRuO)H8ZT3`L>R0Kg5xF+BC>V@Se5t7%I{F>?D=7JsOJeXMoB!HaZNPVyd{q
z6IZTc@}`kG1Y#6bDKWb}jeglh-U#{GXvPjGJPHL2NHwto@JwQ(JXE8Y`qW){paAry
zj=iZ^@z#(YdFkm$WP`A-x8eNWSBR8u#_R$;fUZb(HMikee7_M{wttV4_*V{L4tzZ0
z<ZVIPqG!-K`KjZIiB9B4^-)s_{35)0X45{1F-`AJ=}oLaYmC-ju@3z{Y<=yutU#(a
z>$=ia_O7fXxoV~-vFFwt1>pL1tr*VPv6{<@MT%#SpOwhYJ?l$=%EO%3+hN}=bB3b#
z2i-1Y4eBbhRm-LMRe|RfO}h85y1>fx?0o(zHki@%ppXZ>M%)j)Y8NlhQhh~R(TQq_
zn1DGTdr@mD$8@=6!KzOjvJO~d(-e{0GO#S&4@!!cacI&SGpLsK9hfiMoK_9p{3NhI
z<R4L5(OQRxcc&j(&Aqe=Nd6((zEY%ZHjiFA7&jLOKPoOg>Wj}V<A9^}tviSUu>(G}
zMdJawRFqPc-J88(Y6`+(xYtNy!t>Ix^+>q{bt1a(&eAifv5MTET5c)icg-eoUXg$R
zC}ECAS^=daD@lRr8V;{&nsj1on9$>m&x+Fi+tYym0FUTD@3CHC3&PQlG-q!?igA+E
z=j0u8z^qtU^oQ{Vn4NE9&$Cu`r{cQ=vXjZU+}Q2ZR}gM3*OgA6N~wD~N~3D+BiE^^
zxk(i#m(7{vY;JS8fb41(=Zxbg6cQ=XVXh(vp>h1^8R(ikA}t{lt_vs`70CF3!MtuU
zitjCu$EHRI0k-7Vo$GRM)FmE`jMHST%+tkm-WyC?J8{co8s;(0b-F5uwB`5psT(v%
z$4ZhPyecf^YDk+0=~N<H<lSh??Ot~xY<66OgI<p?EeFg#Tw{@5dwm&>?nOB3&{Pc-
zk2I90sidS(Qh}3!Nl%RJkQxSd8dRd!Nf63L<`tUyOfM@DG@Sh^TO;<UfCG>^RH{m`
z3~)tY>)KX2V}^2%F;3@8cpwiB;yul3>6&zqX{|iRbHAr*EhL`u8Da=Fj`g}@jWjXF
zIL&m$-5ioub~xL}`u??<Dj!PdZXw?0s~aH4lR%Drh7C8rO5A-lSe$W>#;QrC$h{O}
z){6}@G}2Y4v~}zJsuql`CWmr5DM-a7A&W^zQ%gXEqLe9P$2B6t<m06<Bcl~;T7&#e
zpGq3kXSkxkQ~YUa*V&iU)4tBWlvplPrN`E;2mm~&r--=hJ?YpA0a*V42{hpop2Su0
zAERVYR~=0j70MzP$mve|JAu?yy|ip3^rFC37W{QIzi0Z@u^WGM(d5W^2uIe70a#m)
zttf>-`?Y9W%6hH^NR~2@p1(mwfT$r%ecI^sBZziqky+8{<goKH2e(?((_l+^ST76c
z)iYWM*FSeX>YUgr!!>g`U+GmQ877q`4CiJTk-Om4axqsfmu!u|s(owOrtXYbgM-aD
zel*{uDLFkWK@Jqw6syG{?kE9<lljxlG}N(-KKZ4L;zd66H(F>oBkNd9qph@%7!Z@3
zfOAv1=Bd~b_IS=adR4a>AcI^Fa)_iG(U;n}h8U5@q2{`>xnI(`sm9xhIPPn&4#djG
zniT#bl#cY(IIf}x_vt|3(5F06)~G_`G^^=HYE-~(^+-doq|>$!PAR+gjs|Hw=IKmC
zsF80QiO01zRb9l#_kHR$lP%6E#Lxspbf@;9nqC47W`G)aG>5NBairUxX$)_@E_gI!
z6qx6wFbw`w;l(tcYH;F!40GvAv<{+!#U^u11p^%^gnQG+T1KP;G3!>5cSH^<wkmkJ
zUU~sY0zvZB2ZM~%?nc}$c&IbhfsW2cT0(QzkxHZyO*t9nfDF(xM;?@8nm`2Rj?|>|
z#WeFw2QS<w)}bGG;-wr8l@J{N0EI&tDjXiam067B^x~>1#aWHMP$@Apv+#|_?#ci#
zyjN(4A4>C&4NlQtY|7!jZ>4%HXL5qwabE+Q(&Vor*TXx(6NcxlE^>L|n4ob=aqC`5
z&`F$8yNX~v=-tP)07#~nb~90_=9hL4tt$Y_hCWMUipaHB5|=x+lUrEac><bHY&hb&
z;fYbC>DZfURmN!#^PrF^4>g5`Ik}Fq?j&O%8R2VC451k9SyRS*)6%;z@w#b}*oC+i
zn|z<W9Q3UmXOHJpuaxCaYV@-GDp=>NuM(n+cB!ESW>P7!At$9wBV}+$T=%bTYVkOc
z(pr#M8oc~BQCXI(N};V5KPaz^#l^;}N2^a*il>TP68`{s`Qw3_YMPz{wqe}nu!Tnk
zRf^LgN%`(NQZN|BOQ?oPgB;XE<YJ=t0&51t6wlJD>QJ*>FU^c`Pqb~fIK@qNyW2I>
zgr6l*NnH$8#@>5#PKe?2nnlYlJ5Vwl9M)KvT5NG9ZX22b$)>sazX~^Fj%%93B^*-3
zdv!GsaC%dra^&q(`Bf-M^Z+9aPfvPso^U8JIVWl{_oplplbwWBdm5k0E0Q@cY<+5s
zCo7M7yoYpb52aIxeC@}2$6z9zurpTBd6w86YQ4hce!XgIHfDi_KPuKe0M3SHd$)~;
z0<Hnpppq?@0~KQdN2Pjr#mxxF&OZ|!7D1-4!+%Ox&LyHiH`kVG9{8b$%4q@56sNy5
z0Qk9x`+8FjLB&2JpO>0z3>~!W0xM#tm3LcJex9``Y`|A1r63@QgDpn+Su>g=f0&Lj
z?M#urY>`(H7no)adG)IJQPkq6gA!Y3ImoPOUE;Ypa@pt)YVO0q&N3yMN2YxZO`qM0
ztLCdlxXAXYk+&sq$~Gu?Z)$Kk#X=4mpPUNLz&VaOaZ)kdyi^3|H7fFy42+YS%Gcua
zbjRa46{y@*OZDAm!>}FruIvo?D@Btvba<V>+i@b1f)6>Ux>fC36Aq;}To&k0Juy^!
z{{UM39-F*VJZY^*p)~&h*Xc}CgHHV`WI-E!>}Q%OTpaeM=l=lLNCiKI8Kl9Zy*q%k
zpi@Dm9=uQjw>YF6QuU<H1p*L`DdX<b4LvAK1wUG~q&qI8fk?sYRk4xMr_&qD)KL12
zR8;sziM8@g>YR4wvw_D!S~~k?;y%20tgvxYN$569)KagfT4z)JY0LMx>06RJ10M9l
z)}=ppoPHG#N(3K>%^drRPtKREA&NLXXwFFV%_rqYZ1?u0GTieah$1dMYNtw3$j7B8
zeDtIN?fj|AX`T3`UPS;sc^KxR#t&MU90S)i3xW?cm;fK8C-k5mDG8~#>@IOhnoM#2
z6rCvrhv$k7Go>jwH8&WYXgxis;*&i4RDcG-9Ac~{0`B8ARFVx$rz$f}8i5>#=Iu(S
zG?MUWLUEcFj0q^D2A4VSR)hwS()G<D`cnZjONvkPnqP0{QUO5E{{XIz)MkJ~U!kU8
zQ=ih9I@U7Wq3iXj0mVe8nv@>+%~wD*>?GO-dgSq1sgk+qYYx!l5T^$|mAx4GRCC36
z_?2lIM03Vo61{k=m~A}E;E0@_{{YgqRZGXWceZNG5G9fsbBQueaqC7KVx(=^Y5rZh
zDJX-|tjVTItGYQA$EU4f#d#$1h=Y)ES{vlGKn%>w?_HNODP5xiK^Q&#t1{(BsP?T{
z<?{jWp7on@2^>%YSqvN=r?qIe09JLQVs1y_T5PyQJ&gh(a7|<Ck^HCJWLDV#_pH59
ze{lW&T>4i=9olAfHZTFsIjI+|Fb<slboCtbUd&Dz5}?Sb02`@^QgADHn8>#VHgu^D
zGsjwr+yV_udiAb_vCl2YopNfcjGmQg{{YW5UGtiW8bpk*rB{9%nzAYh6laRcM)4y9
znsEGa?MNv{H7KHJxIVRG6<#hXa56joRkARVG+nr<+nRzgkHfW24nW0fj3v1lADvfm
zhUr#cimxEgZoTP9xRJ1^+<rLpsd=d6{HrEvi1L1veLpHOOVo2xS{)hr!9SH+Q^o~U
zLxK%iUQlydM9yTZ!y1<d1D<LG>&|L^g9H=!)`-SLPtu`mV?AnjIUk35uEXZ!RLHoE
z9eBkx`uo$cah!2YbJwq}W?Ca4cLtaFQUjBbOVm`9Ie0ZVIqQK{*Y8z?;YU2xM41vr
z%XO<DaqU&32Y0`<SO8<3*2w3U<ZeG4)pq;bRfz|&{A#mx>r*1)1DcJ%$)|%+$Od};
z2D3IpdI~#G2c<7lnnNC$`U;!^7OSDbsqs{Zks@d7Qjy24M1XqK#N=kI&5^%Om05|&
zso3YOM8o`wmRv>>a6#)(zZuO++|wL;ii1Q(I@5szwKo~1?Lf&CfzqY|tD)!GryPt>
zBL0@;HCP83Z<J=ePTc0$Hc3C%HRRTABfg2c0NMBGYt^hyY{O?f59?o^aZD{%GCj<>
z`-g%zT0w%sk@M^a)|eTU>$1ntxfdlP017RlXOnU1Oi*P59qUrwAc#2IkwLs8cX3GC
zNTeW~Q`;b(X)}RA(uGhlQ$iJ`jUSNA0jlf8O`Iqo<LN-#v{~xf1&mhKNRg({%iDk{
z*BVNj^tcWH9aN0-RD2_UEcSj>xXABTHJxI6TlKe8%y=0gbDze#mdDCfZOxrll5M3!
z4aib6(T#1JNF#%67zx`I=J%IZ5yQSP*&T34O6dGCsa)Mf<rQT>nEAU?G99Yu*0;nN
zB2vTn_SY+~=&`Mt5ezUK6iVv6M-}YW47O)$`U=I<EU!MmQu}F;`|hb~<<pyk=0}-K
zn<ivG!|PFzn&`YsryCiJ+fFbt0O{{s!^{=7@=t6G*DRxEeTEYi8kE$9c!B5!DlM#s
zh9Z^bWl_{;)}k^q9>0x2*X?7_yA*)%aD8*l4-`@iRW;mu{xvjt1Yxn74HZl1#yym0
z?&I*NUc&~jsLwggI}`(@2^ni^x4A!Bdd5??<61ib#V*0=_)toumc>O6+N22i=BI2g
zJPiBOm2!oLE9;&pD{iHKEaL@@LvbD<KQ=h6t9>I-xg*Q7nX)sGx&E}-G%Mo%T#4mv
z;D%F8MYEc=CX`c7M;u5=Hx5AO>soN?F6aU%z~i3Pe^>CsT0^+VTo4aT3eK^$@|$a`
zDwDJm)~UkC@s>5IS`2a2E_Yx?Nj(YA<x|_qsZ7CEKY#wUYg*~s*ypM41$0)Laz&1e
zG5DIr%EkR|xAPo+H2^+%4<58!Tr^Pma)wglKGofub@KM`2fcG1B8)6JA#x5q$Gs@d
z?!hc&URyS2SrBdeW3_1L*QsT!#_V}NC>^UV)tl^K^)(z)k#`XwoHzHeis^yp)OS5v
zZBpUl32O&FtWR3Rx|dm*NZq&8VEnau+fhGeU90>!Jn>M=sqGyz&o!ew`)XiMrfM@C
z&2#?%eAO8=i_jR0nL{^F8-w}RMB2TuY)GT&N&T&AbMl^kn5nSNU;7H-{`)^ZoKhVH
zBU~K)J6BUCqYEbsfGalc^__r7$r$=kU@+yeK&$}z@ruB{(^GRW7|(NET+&SZm<Uf%
zS(8RvJHWy0C;@yI;n}XPJog!nHu)49?x(ftHjr1o+U7hbsLg47@x%V84nbb^=uzr%
zPi$oJgF5g=DTwA0Jyt10Tf*!|p%vHYi>R_<_9T7WVLN_xg?p{t!GwkYqdX8ZRDZWM
zzq=j+p4`%7Jq@(IIxI^z#UruBX6jnatRu;WL|)5`S10FcEgtFa3C}oQDj4*uoB0@w
z;QG=7RzqQPAa`|X4;gZ5t<%}t$B>K;GsQ|Y7_|7BSzIwAq3N3D^$X@%b01Eaq%>q}
zSH5I~M0my+3abt47*sJh9COyBx@47!C=?!WYP!M+;~720BcW8WqYcuS*+&Jq%{?@q
zF^@RUJQ}2y(ka}H$mnZI$>xp5=KKXAN~OzCXmdyh$}l}mbXrt$+hJrFB>otx)@<^o
z<*R#&D>LT`Gn`Omb2r4=%G<yrPrcmYy#Du5o<`avU<dK{tGfN&)$XYxs{ZJII>M1~
z`xFw}cQsriaQ2+2*3y!9DRx|!BO}(kNW#r$$oaq+1F1E~X)>E-3RfWVd9IENfWQ@E
zGtU*)m5zBkk<S2mFn;f*DPp#QHp&7!Q{|K*5=Kej3d&oeBqIbI_cWM9+F$`YPCpuk
zT&kS+sUkb0>+eY~3!31c#Cnwe6k*@K(noPz<=+b3b6eM}H#Remdc&SKn|M!~9OAX6
zj(Xb}56L+7rXG~%7-9`Fw>X;+iZO#u#UV6=J_sbanPP@Ek<VovtI_oLXszP5VT@r<
zHHqPCi#vN)<rZ_)oD*FxgrfUWE~GM{%L7R2inMNTUCH)6F%fv&I%c_Br`$=coqppt
zB~<%y+PTRaE!Q;8N2?pZj&n>clirn>nvI(n>p+JC%`!~(Kdm@7J^uh2Y=blb2?Uc$
zvE=vTsi%2l_596K)Gk6>G;6~S^bC(s)I6mr3HiIWYZ304zULvotwz#r<kChw$&oYF
zhcpz9vKZpIw2kDCYi-6UzuB;n!skBqZV`ylNX7+PRbQ#8Y_lloG4OUAdhV&$On`B;
zf#}tJQFGIplVbk>`lz_d(P{SU(l7z$ufrTMoTO@}zr8RF0mVFea19p%>Rmc8tJeCy
z#yij)@seu{x#&r!2lb=}Sek?qbLD_)K_m=5?sHtc7aJe%5n2m&I%lmRn$9hcB$4!}
zwr)Qojic1nAv!STkVz4K8w`DD0h;N?ktjdJ4^O3egWQ<zS<sEO*?6|>q-h5JJCW&J
z69KrNeznm~KIx2^xn-*YHcg*m1z9(7vgKQ!dgc#W0AbOO(uV?0fwcufcQ~n`*3uqC
zocfC8*>TdF)2%L0JqpjnJsBm>`#Z6U-?H&a2Kk83vsaJ_8G11lD89Hu{;{~}%_|DW
zzSww%JB&KaoQ(Qb%vyvO1LoS;>PJ7FeCGzab8gG?5Es+s{#DRf_~Lj0551Sy(vYls
zMAo*G{E8G0TF$xf>{Ai4LB~N{Rgc67<i=S@9e18_T@9y;?5+`6X8`B!=M-ElGJgwo
z^&NJvKhCJPhaNMO1PbWm@g2P66CxgZk_Alq)wxmkNcJ?vW0e|Au^jSGy<f0};BC8{
zFIv=>ShFFOmuNMaE$T-mMp=DFN<%m8@0k>WR<t410-Wya&MS>Nh-~r4y)0UUfp+g3
zea|%@chTw!$Cm?+^nYnbk<UNQxUs0m5`yx8Ki(At+WnQe%$Hd{??BGowME^4#Cuas
z+q(=7y(`Zp@!p#Q6yB}3xIHUA^Wr>go1olB)_^@mM`80jC?8s^+J&qDv&;`-1$e#Z
zkFRFjsT&39*9Nj~{86Y(*p5=8uV3?;c41@NFFaFYXj#@p`F{59YXejGhi4NPM>su`
zy?FGOmlrMj$()bwgNlHrdb4rUC#60>Jqr8cOul4|1G{{@DO1H_&Ep&Esd2b+IOnBu
z{#ovN(~+5E$l%lD8L4rtUdo^A$j4$&<5`567?&l9>z-&X<nu@g2hxvbz)+zZAx3LL
zB+85}QCyzYZYOd_VbZjW87-F)O5*~o2T(aY`c*I_Bys?&5kr;)vE#LBqD{rRn;|pC
z-`1zLD$1j$H3iy_EOF9{X2w0atZJ=Fi#P1%TmX1(*{z7Kc7-|lhkEAiw;V7%@m&m2
z0;#>Q4Pa5dVSWV49N-bfYovlx)bm{RnntpX!>1sc-Hug1baCrIi_>8&UH5<#SBUt6
z@#NIzG7#MSrCSEQXIHvtG}hWl9+l&ozT1nZa5gg@am{HIG|O-u(2Vn%alq!GvSJ_$
z=z7%c^)$-4w`zf{k-fh<OY3hs(`N(Rijz+}tkb<M=0&sfgN%&TM3z&A+}YYV--O5A
zu5nM5tj8$MOID4i+U1f|c4kcV>zb>52a|OWBdO0mmD45elXIiE%SDamtayIY?GlUv
z%Dfz&^-UvrVN8+tM{4bSC#EcD7%0niKK0KirfW{ChQ}e|m3=zn9F6|~m1lT2Ol@CW
zj(G;?qkLC&<J|&XLd7Juf=Q-R(ly*gUhr3i=F_y;WM~Sz5MOw~tz#I*Hwjggw>NHd
zxS%Sl8sl%$xf_^T+Tuj*oc$}*pHE5T8;RRo$BDcyv6D5s9o@k>CbLFo4Rrgh<Q}Wu
zxhq5dkic+vS6@6XvAlauaq|k~VO_Vfbpv*I{VJ>@J6ZuqY;Zc(LxH!c6}hgiQC#5X
zj0(eSV!Ek(A}gQ9f!36YZ!6AgU?p+JI#fpkzAL4F3z6aBs660&q3~;!bGkwS&p50n
zR?9-7u1y@GHp=y_n>i6s$nG<W#EvpZ{<VHJ8#-Xu9Iq|Tm@68#QhlRPTpk5<ldy&m
z0j_UAi*>`lrEOk0Cy&;-=Cvq-JGPC<%YGGl4M?<$lsNBMUS4y}U$%o{hVNMcujYqb
zftmy3wlP&94ZGXDO(cOS0LkR!jOMD3nA2o&l5>+$3%KKASTV=<XaJu*3e?sI3^}UO
z-L1zU6+c>*$+I9G>!Ldt%X7WbBq?`p;QMB~2j#1W(-<>C+0V=?w%l11`lzpx;#hn#
zJ8*ACikhr`W|cm9!kY29#@S?E2v*x(({{V8rXH(aH>fE~>xA2kNKZ6y-2Nz!7_>zZ
z#DI)~4_fMcJ0>sSZsg-WwaR5fa(nl#lShBvM#CI1JlE7>73s+wFm{qXX%10OwN}*A
z%+uu`?3$VqS~X+bQrxL~cU)v`JXhv)-?PO0&t2+|o^?fN^$Ue=&TBSd(zpCc7)@ez
z+5;1kN7k@q1Y^B^=YgL+2(#yFD@~COv>rQBcBMS?U4}!{<w)dvQx6oeb;oK$-;i)=
zfQN<ksQIY~rW}(<WT5<_uIW<wI-RRzfFA_a5x6g3!lt)>E@WVFwX;}Pjo{I6(n$J3
z(f8Rx!x$^nRi)`!nlzqnk8IwloYs<@j@9^1We!YC<K}%Nb{st^4_bHYO+Vz<0K=%L
zC;tFe{{ZfuwLfZ#KuVte)ulISCI_0$9?e2@3yrOjS9-?0(rSsbSDbO$h>rL<HTG1e
z@5V<YmW>ljxuFKCvB0ZjX58~sdi&SjWwN|a0~oa%oV6%GJN`7_IO##;99Lx5ykQ6K
zjAf{g2Lhzd1`RQX8S6tuCU06D_N&hzRXf%F;Um9uQ)!L9-1E|#crr(|e6}t&s?T1N
zybgBdKw^7VbfdWyt#r6=t!2u*lUN!Rp8~SAG~Eg6J*!oT=Zc|zyQ4VfwxaDMO!hgl
z2wIHi)~1kQkF`X4SFUrh2jxmf9WzJ|H1SD*ir9^@)}k$+YLN~y4KU9N=Ogm2c2L53
z?@>y_H8Hw}(A8;JGZH)0jBn>w^vKMboC}Qn*~hI@&MRZXarxTB1RhZ5>(-hEclRz~
zvTk@)?_Ou9FnhN>vTM>cXU3l(#s=PVUSl(dna`=Al8D0PfEmd()>@A$#W*0~b*@?!
z-EkQI0BBcPaD1y}P&y8VkjpW#F{wRGO&=9b)=lvG`_-uVJc^+g@E#s=E6??GE2zny
zr;}a$JVpLB#rTpinvr3^VN$^ur>ztdlSxuoQQnF%K+Qcm?&96Qbft%-Uy|bPa6(#z
zB;?>^)qNe=0VAydFhS40bPI4=J){--9&3udMHy^&(dTis%qwf_jWS7<j!Si1^sc7T
z=j|G9M&{l#k4ogVLH?5GJ!`1adD4bED6YzG@wvlQT2>g4d6MHC)aOrrs)rt?nz9I_
z+-YUj)-E_dL(N&3$FX(lhnj+0QlN$$4tms6>(fZTA=~SUqWAMVeD25Ei;RNxS2+Xn
z6_X&z#c0nsU{6n4&XPcB0bPeYQ)%Sn@F}K{#HXScIHvchp{9YBqJ==|Qi$<O42YoQ
zXX{cMz`X`P3ZV=UvFNATo*{G5DW7d_ql#zSUo>0^#k+e{v1#H)JMIKy&<<*gUC2f^
z@##$$5B=jn8ZueHhaYKT--SfcLIz9p_o^mL(?g8ni-Dn=ao?Y6UpfUpcRx{@q8mI=
zTNGRi#^y49Skz~}DW>a>xTEl@CQNkVnq<#<R|4t1e!x?H+bRAmeGO7F0p6Nr8KU4`
z`&_5^%{X4py(Kk3OP<vAeER+rTnlFIVb7Y?Z%n$8uhcQh`<lycYQ~&M)FZ=Vam7rw
z1Gelq>)NYGxO&k`SCJLQ06nu%O=`)WbM0Bv5zb#B^Eu8>YR_ofcO2H`^kGWmbL&~p
zBSzT(epT$y_zYP@f~|stQiWsMr=C}khHTV3vMXdD1Ds@iX{R2vr2hbsNZo0GhX=lC
zryjK9O(PX7Vh}Oc@urYE^GZf(dXIX_MI8p1b8fgKiqe0()Ye9j!^>6ALCtEj<a1tp
zw<!$-j!j@{Di-jA#dI0SBQ=Gqs9T`;IBq}B=Ud_5ye3fYMKirjR|cbD^H+7q5Ot;K
zC?BmUri3jR^`z#E@#$11IljD8a4}9Nj<lS9bO0}{4b#$r!Rt!>d7uXNr5sapQbso~
zQANN`Dau!2rsIkMA#vJ}0UT3E?@PE+6N6L%ng<4q=hlpMpkn%SKsoJ6+K=Zz4hIw-
zX*>1JDL9}61M#OJ^rlj&!9M<!0WtZqI#dJKtx75;>(Y=4xdwtT*rZc~#Rsoi04T;N
z29WgPfs5O{A>%Z?`qB~j)P;veyW|3yDtU7-BL<v=sn2swbu4;{h66)$R$^{5#Z=gR
zYQzi2U(SJ=npDO;LN-&5Yt$_td}F3-$}I-j)TdBu(=^FL+ol*EGhZjf6#exhzXvTW
zY6kbkIIyU*k=C5Y312tLcHDO1noRyx7DrleY*XZ8xgxh9Q_lz1q6`aD^OiWJ$nGnP
zo+;VNb;U+WJw-Y+c04Jk?4{UODY*HMT4wBb{Azh^<Su?wQJZNGeWto0hp74snF$+=
z9&=SLm;z7qtAZ_n?v)4Cg#c-xzkhiieFImag~C+k)mX|^B4wYumcaU&ie(Z<_p&`j
zZJXT~Hy=Jfx}?<`>zzK~Mg_oML`;7=?xBTr=gea|iN?lwUo3OYN`uTCfCWsmY5RZF
z+!DP5W14^45b%~jf&5Z8_*bNIm#ovxiFSO$rxl`YrYZnKpQU8m>NkM^x3jlZ^vN}3
z-Ro=)-y${bwmxgkt(L;9xsI4(IaQ0M-dM-Zr=HlS#}vhe(7@-Yteu+VyvcjFK8gqQ
zrT)&;AMffiuqUSMS3Aj~-sSyh+rPDvMNTqm5pFT_OoP_528ixIdvPlUJsGo3It{5m
zIVbAIw2n_rZcD`$qg!~V-uJKt0~stj{&bhRhL*$web1sHG?D0*BMKqhed@yL_K^*%
z5|3<GL^8@zcSO8QnNlrZN{D%WY_Fe4&S?&_WE<qQypVeAz^kI(5O5<=j-M||aEd&S
zkbNsxm(p(XMEiLZpIQt*cc#kN;AM!Y{{Xdbe}heof4t0prD^$SI8+~%3cTP9RmTTK
zbS2iCGk)K#$fPB`vUA-|DHdII&-{GF7(R(wrFwf(;{ba4){2ES(4T28=0}sN$^NrY
zll}sre@cYuw_8}rdpr7q=C?}V@l9crZ>1^Gk1mL6q^?I{Dl9}ZbmN*}z?9=SJt>xm
ziy=qn+N7TgZ~*9gSH<FC7*ugbqfOljFx<ZMSf7yp0F4qKlu}w8yART^T12svoK3i6
zIH}%skr(9|0-(DaSn*Y3Y#+UoUY$wvVbPlSi-EBysU_@qs-9s4e_Ea7%s|(e(Wtrk
zY1_T34cR`F@WV8$1kpAm?@Ipwc+?8pTpF3lJf3NQnEa{h-;>QZq4uQ%spB5hm=!uo
zNAjl4z@?OdHV5*gf0=5K7OY=%TYW1pQeCo^0~tID(6AsmQ~A{mRJWQ@bBys_*jZZW
zmWZO5?EBwZy#wcu=ULGyRT=(uZU@6)@N-<U8DP22Gx^hlam7O+1?Ua5^r)~FGsjw*
zCd!(mA0zRp;e7E@&=MSDsphNP?J&3_<?qK@oxb;aidD$NecINOw37$1<lZTVW~6u{
z?`P7mx*F@eWd<e^44(PMF<gjj*XZ~;^U;itBC52Q;nt)B<>+cL)}+rB*o;O<NcN^@
z6zN768K|*P#y>uk-1C|}sOv?*GfoDYC><!chm(<mNz=6e&}yy%b@io;{M62rD`CY=
z^#ay2#X8(#?lK2MOeeo4ndUk;bZ$Y-T}60;+`q2HxW^#lZ)(X?(zIs3d)Nv{27lSC
z{z0y2=urOMDe2Oo%{@r=t>YqDV6Io5zO@m+ILH+6*<WgAd94v6dKv`>gGxTXoeXGB
z{V3zsm+_>=KmAoB6dVs)F+e!#Y28jUNC@%Ay(m1>nLX(TOi%*jr(9HWdeqD^GHNLY
zG^eo8z<<stCqC2wXgrTf%wiKw=z7xQ9q6P0c%!ugpL#vIQUNiFDQOQPkj4|w_|(bw
zd8iw$O&1{3r?@bX9l0GUH9t2wshnj^RvaAX@}gQuNU*fOg)vTh)4}wsLKmO}0r*l<
zj+CA1fJ$CJ8c)ub@~HsrNI5+zXrKt%qXUYaxg7DDi=|^N%0hvPk$I@I$6Aq2DWGPJ
zgAX)%;<w;Az|U&uESZC!QhHZKZoq&$k6QAvYu+vewKzNz_*JJH;l_FIRb%$atC247
zMgSF#75mK>BLU);He#y4=OL8y_*C|0@>xE1l}8!Naa%&s8}BGJIEf=%jAOnly2KTv
zQy2gqeQKoV_ie^bIvSql?G`|t`+{m0<Q#KF#6fSwgdBbqu*c<5obg!k<V&77tznFC
zX^3h1eicIfa|!Ftaasg*{*_kjA1L>3)wL&SA}6uRg&97*IH#{4(wgd4XCCz6YubUs
zB4s9|1Dc65nwLF4t#m}jMVJp5?^B+nRakgE>drZ?g|W{q#xMl)`c-)c&EBjq<3G}%
zkRM8xTuA=_&ou<Sc;==(Mk+ad`qol5i3lLl{&aw2k4kU{>rjhh<KT?dvB>X%RS@C7
z#;pQ&_N`)LG3a>!e=4()fzRnxk+5_5;;e(7GDU3@2@O3z#;dsG^vzf!E9+1{dL&dx
zhB|kqH{I(_!N?TG<F6lD$(o`(QJjHCw-jfmKZQYKlRJSp&v90e9fRrD6;(jU9kbk3
zsKDEv=B^}2c<L&3C8GoSQ~(oGf(n6JqX`k5W3S;*Fz<s_8<KHV+<R2WsEp`)(;Q%$
zcpUNh(_C@Wn$4P`F4UvbG`&6PGlSZsp+V#PYRVCSF;%mkrmQC;j@3w(NSM#PSX^u;
z{{Yujm#NR;RuKH2^{OzK)+5%dxB{#<xd-V`KNLuC8Tx%{C&={0N>3TZM<CDB+Ojr7
z2PT1xa%nTy7!;$ENTKWZyVZs0I@Mvxt1+;^^{PZM%1-Wi`qbR*`-dL25|P@a>@W}E
zR%XU9Iq!;r^WQ&}PX7Ss6$|isQe{Ms@cikFdW?0aoaUJI28fI4Ksi0BPh1L8NgQ?h
zQW&ZZef^DCP8O?zaw=p8uRPEq#0|FU78u6h57V0UJv8pLA2v<{1MOZ?a#V#RbmUj4
zXm7s8GRgtiI(Dyy;;MJ$k?du!Mvn}WlbUE;upYGL>r>gqnSo)zHEAD1BK57l)L)cm
ztz8On=zRr5e|OWIcBE<C<D6rhP<j;Y7?Kt5ij3fOYKBRhZv@nNb~);34`@zLVOMNz
zKHW0M_p|D2J|!gbI(4l*HHu8d22cAvXiHN%vV4u6jiA|$KG|ajEO@KBjP|Ih=aeVZ
zbrsBLI<3@<@m#4~ebyqG;tx5tNDd?ZB5S1is-GFt0SwAEox>H=_)Zutp?J~qdXjpY
z^F0b_Rwoa*C-C;JgGjo%v(_S-DG!pv5(YF}gU~f4SYc^E$X`n3to56FtCqJY$m)2?
z<8^e`sx>V*qCYLjuRVuGxrbOlQIrSV>{$Mk0yaEHq$SpwD}2KXkZZ?U?QAbu9Rb>K
zN3DGhma)%jVs-gsUiIa^Bk+%tsJVycQrSMW6OGQyEoBSFTO3W@#CK8&5jKI-H3Vu%
z;AiPwj2;nZLe6&o0J23wo*qc0!ZMMbaansNdJ8d(J=mk2NM?PZB6cm@4AjqUEC6}2
zNQ2dv73%sNdUcd4jEYGEsOeo?x(1!9S_cuUag2dg?1e1iYvD)FvF2F<ATH;PsmV3d
z+V~$_xQ$(4RYEg^$*)R_!a8Mz+FYb6vad|7b+)bqY67UI?4m=?D|9>-!@=6s<?CBD
zoRN|IZln*+x(mOCH@4Q^WOA2r&pik0UcA%5l7%}_&w8=daC#a&nlYYfh?i5wygT4k
zxYX18M5_fk2%QCb1<!-D=(P8a&e|~|kCjN{HM*A3Loswv38`7Ir<$%*j4ER))OT#j
z(5zYu1&-$4G?jQb85PfXn?Pr{W{M`+Cq_=+{d(zQ*6j`Hw=NZ`?d{Aq*0N12e(h9}
zX_)&-UzqXTb3lKwm{_yz>64y)Yk|he+7hRF9lUd1->ThPUfHy;?I;xU{uSf5Y!gwJ
z%}u4710Iz!E}XSAY?vtE@OxIo7a78wWqm6y#Rlb7Bm8S}2-I!u$9mwI=|$*B*(z~d
zpNNz)I3pm}TOxp`p0&$sOO|C-9WXQNQ%~X)*`ML~W0Kco$~P|rAEi~+V20g+j19eU
z(x^=L7H#s(OCG#cIi;3&V(v*j$7=3JG@0oBAG^1{)6^mRykz&Q_Zm`3^B392BOPmv
z@T0my;kxe4cNXrG#t^nxRWp)Xln#?_2>H3BeLC4sI49{&)NC$Sl#?iW<E?Y@#dRAT
zvjz1zsS&zkf;9kb$DpdWGg`p8Tr;=hSj!{E{{S?OaoC*Is4k&ySZDCX10tT{Nr6R;
zfc3>tdpDCMx_`Zj)Va8S`DVCU%bH1BB)&82Kphu`Y@xG(rPx@L*18nbtkP8vo_$uS
z_-+vTDwgQn)RO5c&ATTV=~N?r2sHc93QB;tLNF?EpaL@#h(Fpj&Rghd8*e0!b?aIY
zwZu6-e7}!1AY48c-zv4u%Ce5YV1GKZGg;}76p48Qpf#S?leYw%cdA!1i9Yc(hGXj2
zvR}$^ke<hi%lkTmoPL$M@JIRfs&mAfaHkXu=Wi`?eo#Gttk#UH9ktNU5pKlQCx8>u
zlL9+TGVN}@rmp>-L|m>9J?f%HV{D9P-n8wfblMv~g-FvU)8#Qpi8FkxdkWFit_`)L
zo#b(heQLalHi-^0r*=<DZlf%7!okjPI*MR%mqk<;Aykri9nDj*w-b4@K5$M2Te(yS
z`Q#&HW}<@W64ewANXv8Hwx*2cS&Gy!&lO@k+b|=aVrh^``?d5uijlCxq0Mv{mN)t8
zNaW+CV9zV1;5)JZ00HY;Hsca!v8Zlz_L}7xdIQjRsg}jZb5;x+bt9=A>6dQGoFA=Q
zhA-WPWyjL0-h#1_*FCGxd!DM&Co_ECe<#0DRgL0XS-Oac-PDm*Z$Mc-ZZlEIWj)=9
zYgi<kCmBJS=%jJik;}`=l6&^3`c;dl9tpNe2q(5NRqz4EYg3c~qX#q+DLG;lK_u`1
zqy*N`%X4y&LOypj>|Pkt2AgEC?hPg~TO8Lf;k_X==zQr^G|kCxPipL}CE6K@zyql@
zDczg3%LAU(n5E>v^(~soV~$2ES6N{_!?-+(#y?tY<rJTMnrZ1q<sQ@m4FEky%S|JJ
z^K(FNS_6F8pk;fhyr^3pYn+<p*_(0eTDq0Ws|5sPdR7F@xw0vgHIFquoB`A!z{$>P
zwrhLCmg&8&WKG3>@3jLuSfkj#G0uBax^$pFoA-uADJSXeP|FlZyQ$mPvF4zVlB894
zC40~!_n10Rul`MEi-r{8bfoi-!ixc+xG~2{UCKc_x$RUw&<-$opiP577lfGa&(f^L
zHht?P%y(lIAe@8O9@GrlS0}&cPg(HTagps=3vdV@HAp2MS^2*jKx24?np>5_t_P)a
z%z;l@($ua2xNtg*4EC(!xvRDdL!It04r$Dtg+3^YJx<An=Z|`{iMc_OCY$Ax)MwtW
z6k2}N9OLw(kU5Ou5%i@opGwhPp|jGF)HZ2*Fy=FSquPy!(yw`A98&~&J!%~>+^Sce
zK&Gzf+j16D>J3?BIX={eBaW3W1Go)B^%#+G^<_LksvsDgjCyyffhaNKy-y(SXs3y_
z6&NyP`qTda;V8f7<yJnXvV>=*Da#KdJ?P{SsC-YU5&pApxD^xlhf-mWKk??O3w&dq
zw2c-!Q{)SZ+Li2#OI*J_vT8p%QZc=UuwzmzLxWNXxT@p}qPEiDWR}ONq}h+d(ybWw
z<I<6ncReZc1;|un(lTL){#7(X58IDXO_Y5906|59<Y6<~oD(9Pi_bLi!Ry|O0D%X3
zMNCLI<J?rEuUbYpk$rQ;G$E}RSr77{0qM<Iah4?VbInA{&00jZG$<a`JW4V2sL%?Y
zJ{Pr7B#Hw4YSd0K=~W9<(GiSLA@@ghxu~uF`1C#MOOgJL!lJQa;YLQ`*wz(IAZ}Wr
z!N=DXy9`evMcT4#REc(uMmtwcrzv>U<L;bSJ1nthYQTWmt=QvDyz@+gAD4yqt0jVc
z;-ej@2+8pbZT2-Pr`o)}`ptgW`&S(F#d?p3ZiCu+Nt1!rxGAABOmMl!bJn_OtBA{v
zEsL}t!j+fws}jUxd@#YNSo6&(t1^+drySX@Yz%Qz&ls6P6Tzz5V}GLHcB?MLE<mLn
z#L4Znm>`cWz+u?eA>vl@uHp&&E;;oT(uwAA^JP?V&wArEsr>1iJBd?Wa`;I{VPXW4
z!k{w|fnJy4*o0_+sOG%Oz;cVLt8|m*T#x>}dvaRE3n@hdy>k>^j@1Y(S2-A|5+qTD
zP(7*9N%Dc|Pb6fIT9(E+aJ8L!o?$KNSIE!!RePV3-QS=c&lDyWIK59tjhah{kcY=X
zUQ>Aw+4XCP$RV?u_KV45SX+FGfR3fHURUB<bdOgOMC!rM&9v5+xh&?jq}^?jxy4`~
zyUr`5)zr147Ck*Hoa(jFN$4WG9<=C2`GSx!){y>mM%x=TwBNckZ`^AaKiNOo%<HfX
zxgMUFte24_fmg{u!?<2)vQ6i6fG9}DI+0vGEN=)1iI(Y#oC0x68UTH2ZJ-R&HZ(MR
z$GD!p)qZTT2fxy)X^Kj*9k{JEws#;NE0(9kA}eS&u--@>!n8teAOnF)BUmHA#X=aD
z_RVG@;R=!90CC=_%;fzlSC?Yrxu~O(J>R|!k6}_Wz78@eo1+bhaBD@L)S(HS`_&tm
zV`RuVZ)yNz+a!NHZSu7(u_8gxRXCg@><0p@MBls|;<tvzGCM6a<|OHnitpn&wu!&l
z9V^as);><&!<zI92H&Q_Yv;I%7op5_;NQH_B!C#$dW=_(Ymxan#mcUJ@glv88B#k}
zm3Xc{D_L`n8;sYN!?LwmMCiq@aOX;$)w!jSy))n1u^*G^TN+`^YuK-P`&sJ~&0C(m
zWJ6lVjCAW$Fv`^(8c#Dzi_~OsSJ&UAeq)P|CMrpHJ&3!b#C&aTA=hNbPw}o&QS#S&
z@e15WsfYQuH(}DaIR-`tPip;_B&qE%kbXyjidLw~<AX|iQVwZz$0EIhoD;5Tag5M9
zkLyDoeJBCEXVROF^ts1MLV2KL*QZ)l<cyqiO;M57o;vz_)^pfvbKg82Ik@oUzJBmf
z4RkBkxbKHkdA=S|yE|C_06Odt;=d8ksq$m0Bj~8R(@c}KAso`uH#Op#iTo7Cr;e1y
z=~W%T;k-hgR<v`RGSy2%`?em2wES3`FJqTD?fO<tl!#<y9Ou%$wuG-v5;>*2FT|Uo
zY*jEYNFx<;(qb8b9DCJyMka3c_jz3IczDR@M@_~JI+}UwUbRDpp2J&_nuxa@DpmmT
zOks+W(V?Y2cPHsqF2@<|RJ5ksa7P0ow62#cUptsa)oyy2cX%A_*vm2eGg(vj?mcT}
z>}5z^D<WZ&Tqi+I#zj-P03q*J81ibo%at{xHx!OqW&PuSym}gihHB;7?3nxZs%M(^
zBdktlH?J9`2a)MWIHR0n0)_}cIcljjyQ3B*arLW*hTv5x$yo?B&mxf*dRi!{7z*jU
z8woe={ZtQ_{{VKmkzKcfA;fY?kCmG_{VBvxV^hRTQ%{jk@eEg-9$4cw-T1O?wxI(N
z>+UOrJRj1A2(hO}=3mA?8s609+ZH;Uaqn3gDsR8f_eN_+Sdb)PKOE8qS<<E7YtJV<
z`&Nu+=Jgeep|<E*dXei}NVLRXx8*C7@l0E8Q1r;nb+&xBpsXJlp$i*hpyY~75yu)z
zQ%O=-QAHF1y`(7ef#aU_vw_YHP|@w2>HD#OeQQ$E&gSfug+5XIXQgr0p()Df?V(yR
zj;02xhs<57NhbkEdh4{iMz_;dTw%8Sz>2eNpxZ?td6-Qg=m_9d=~FS0#@ttBIP%8K
z<f|nqT^!BOBX@E=D;DHozgpkDLNa~x$*c?Da^E-M+Ngr7N~_;K)miRI=qfijs91sN
z_*9H@N?WO@n38EpruU!(rRhPUfDVSFjQwgldUd7@vbiIz3{5o;PAS-?0uxA2)|Asn
z(vSu-)|7GF&_4=X&;j0zA4)q>_|pN)fk_}BW`(E7GPHzKC(z=M=N)*d3iD0JGyubz
zFlqaFqiLW9;--xH(=p9S7y!@&gm5ZLcG-Cge|7UsJdTu$%c(qodKyd*O4HmunjGZ%
z;-s7?9XizwA@gFJPZe@<G0*E*(|U=RnzUaaVV)}nMh73xx_w7uTkXeQwadr}Cm)@A
zIA?g6v63gtkVn#^!Kdx{dghsfT>=}9X;0FTxIJhlfD@<Ekka+0{V6ek9AsjeT9+8$
z({MAM)s%`xrjp>3`qtjuu=nj)8cTlsqMlDm=>XilGh8(^Wg)7+HY+Du2QiYMirCxp
zVzV{0#h;nS6;xfM49GmTdsI)uP!2%A;*t7Spk^<6G0%EI&|;h@0eYNL5ziEJ){`gc
zRdEZ~){u%&MmfzVQ%>L<XT2%KCp=Nk-t>TPr}L>HZKsh;9VvT?0FaT+1veC9k~yU0
ziej*IJ!uIvcgIRG$8W-z!jAn#1bfgjXt)YF?@5Y!j-r@PUPTueccuOwn5G#N9$0>K
zd8j{#QFIm@GuNP_@aNi^g`fRgQa}5vQmw7yFxz8td;b8dBBz-Jg#!ngV~(b;MWt#|
zk&79Ar;4(CH>tY+0IH1-yHvW7T|&k%1R7E^TMOY$MTaxnC*xLA!V{61FOhTo(VCZ9
z9m?d9&V%^UlZxrn!SOc_eKUW$wPidXVaDdVZ+zBo6HRp~Qj_R$!NAQl$fNjx{A;?8
z!rEj_pR>Dm`P!_mkEKPDY~UW`)VyUhQlU4{^T8@-mg(tEZRZ6NQ}j&Np)7h_Uocx0
z1HREuI-P`H^6>~i>@I65V_;~om0v^8658?jOFM=>(VDkyqv~?Yx9n0N^(t$$ZGONL
ziR5GGqZJc)j?D)GcKmBUuP(-m16JD@F?e%VW07tY1KqGqcN!j@b8l#?c`PA-;|<Oz
z)1Xa4HJEN7`kK;R4kB_wx7M)4!D3>R(Ucpc$-mLnerw3Sfaaq&HVeVIk<X$=$NE&s
zq+6~y1L!Jbu!Tl3TuUvb*wgD0D7EFLPwwtp=rKrdkPnj1L)+&#tx;<VkGc4o1QCOr
zR*M5kbQiagkTnZ}aUFzt^)hGrQ-$89NyW4S)2(a>)N}w)P*#fzNpvOEk&b267>}Gs
z?5HX?k5+Cz*&z1X1#7gMKZ7+HxY`cbdU~3_V+GKcQcTGjUE`AS&oh6($Q3GS8@YFK
z#B~gKtIa&G&dht}gn2XkHEIz;=4EBjt+?OMu^Fl3(QLrMA1L(Vt}gPRlS&Q`tx$*#
zn*dR;e_BCjY`iu;gjJo*x6-Q5miMJ$5zA?22tHUe=%csV07Uv#Db`nTs^nC*_U?=c
zeCO7f8YvPe-~sqlrM>y6l>)9ansx>$fM6d=P(c3x8g6(r5^?uUASDV|cf}^!bZ$y|
zQXH{7;+O)Bt)3~^$67Ig%`V*c{HOt+tr*2WF^|4+_2Q{rY8Ehqo5+ScZlDVcbNpmd
z#xdNtzgp+!*5DHmk`_^pSDMnZylbV%M^TLY%ZdQd&pkP$&&}*<a!T~1BO{Kq2u2}C
zUTL5b4m;DtWRaS3f(I%1(qk#d7)zC623Mh{-)&byyq<)SM5K#>$4Xnlx&i%b<1+|y
z;u-1D_y}3DnaviA1;#lU9cmRIrYY9!1ml|F=xR@TnaTcDm_sQ%5C=-uzFpf1B}aTw
zslg0((a3`X+PXcmbkqfHZe?#IdQ{=JMn9!j;CH8?%44l(VuuI8sa5hSwsA_W??)&W
zgJTt8n<z0^;p*By?tmttp%MnhP6bG!s|LZxYOsydik32+(vbamp#9(JQ(dlks>7$f
zS^`^E+c4@WZ!OI1838|DDmZ`>F7H~>JmVZzk&}+7Mk_?hagLOzaMfz|-IM3f4OGVm
zu4rfpTZ2qIRE!B)ZzBSb3a6z_ZrGBdUOyUqY*s}*su&j-dVW<C{nJt!iQ0(h2M^;&
zw?QFLKDEJPIsB{B{7(>jGI5h$U{r?rzVJP3?{bQq*mQZAm1%&dC?53Dk<+C)Mr+td
zD-u9<@;^F=eidQ4Q`_rR&r?$%3Omz)$;VHvD<<FmwIPfhI#4>&<06x><j^5<MJH-p
z((G*ePy;E1;ky1cF2Xxg9eC%8P1t3$IgcWvlyRO#EC(n%igbe`=~}&FA{dSd=8=~z
z{xqt%dI`gIu64M^?LCL(N(MU`c<1n>Cbv<rfqm(Ed(sLs$F)0%cUmxU^rowKrOr+$
zxCztLQPPxjG?WYm4m(qaCYnC=IeqB>6G#Oqz{fPvpIQKRc&51HnvgC=X{<7OQ9Xc&
zbB>g|X~9lCYFNHbYZ8bG;P<BDuCjTUJu^@=TTf5MnpXlGb5BGJaBwqD+e?BwQ{@%L
zyg^R{VxuZ^Q)APLX&iG)lrC0b%}Eael0k|i>x!6ZA(9jFnykx)s|3_C51Z>nP(!0Q
zsR8^d739>Q)kGMp_|bunUuspxYE-v*e(u~3xvCKlT07I32qaP-X$Sz#CNL>L<E0_s
z(7;ZEiiqbt)TW|twTz2G4_bPTX_(2UuldbXL6+^l_{RiSM{L+!j%%5KlH-9}_N}`d
zf%5b9t_)Oc%897BC!oz~THua<EY?(KCndXnb#f`zHqL%uYV+wyMxmoLN!yN|)t9O2
zscRde;K+Ev=BR3V>co;PKR60Yk-_{clb=#!AvoN`?q(-BHRv~TY;8d=nK^lOmnS_d
zbR0$pwt221*7c;gRbk(X>}~#Qb@jmSK$z7h%;T<oYhp3-jNoRm!2(tK*0r(U7bm4s
zB!1ElZ^Elx^BEZJR`Zcm?tmz8dey=E!j{J`FvRXN&#fT9_o*%i`a`ux(!I)i91|s9
zygJm_>-}mK814Af;Bn1##KJ_8WM>AgV4A3$8n~n7_pRfx&n?Cgfz4N!BaYQOaC&4^
zG7O(eOmQKor3V-TBBmmulkNeE&6~u79kEUwsl89VIDT~ogVV9ADa3isDySzoB;u_h
z%8yFYCNmzrf2~?xP#weRRRQOUwH`JPde$Z~1DsS3-!(ZE1fHDG!X!ZCnqzgR@to$G
z-1Et-*{UGO{5|L#;Lt}s%_!;q6$XGf1KO=ZaJ<z}Ni}96!0albM2SGb$u%<aoxduB
zJk-eFE-}`%MlunHLz;nsKU$s0<Ww$4;Y5NYT#uzAe8U_HUbHtNvSz4<jGR)6LU}Z2
zBRwe=0<1)EwE(H3$E`F(i4>lsin4?i;MHNA^s5o)6{<0itb1gNfxtC8bgJ#p3K-x=
zj&LcGWO`G{`HeC0kF8|Qkr`iVQb6>i&NIyz$)r%d#aTg-z^d8ir-<ZWjMX9}N-DtQ
zU{zz+{3>+G8LKm6U-QjC<2?mV-raLhx#~JnVG=J<flXn>DeL|;*64qwL8>Do8K-fA
zKUz#=(vFmh6n*UDBBoDF@lXSbnLh0T9>*x%{!?C+;mJc-E(s-9w_5X88`Xw7*P(bx
z^J5>(OKdqkGhZLYFuf$v>SeOkqsK9mfIkZAd@G?zs@^Io`9?z@O2D&$r=4R&C7kVF
zt$UAyyfHSFrL4gNT{8T~7^hAhS?t%Z%c40wN5OMJI11o`I#qP=HQmH!Lxli!#d<vE
zXd#)dvSn4k30M(o*H38hz9TJ=205nb#K~i-?Q@Es!SX~yd8Fg@t8n;g+884*yDTzE
zHKA@bA#|`v`;pl4I}fc%tXo`&K!}p7)OV%If#Rw@rD=3KSmWFZp5U4+Y~zW(PW<yy
zT17PWepJtfJq<p>!fQ~=DJ&@EM15kTR%{NTZv?v>V*{!6tAbdjkM9OU+*T&7rN~=)
zWx37;UDG0x8*Pr?g)<kZ{{Za^Sm!XLqdC9_)~r3_+b;DSj%uC8pJ*i$GJz-es%Q){
zqePCZI(48&WuR-3+}n({KfI@?tGb4(XC1-^kwdotoN{Z6u#DQdF_H6itG8A#U&$N4
zB|39VM{jR-7TurFaa_IC<g#iz(Rc3S0P$M7T#K+F=Zt*SaA<LTpiGT~>QfXA5nb9D
z^zslDc3uT>cDgp94coQP+&RW`n)H|397M4B61fY#b|HH3x+;R-D^eP4$Go+8r4sJK
zdj9}+y$`}^GHHX&R!~%68t0&v2==thtcSL1v(lx8TQz7%De5VT=2wZVbt{L4O9#f&
zxSaI%tNL@!EYMtI&d1G<TANnXVzIXy@>#k8)~Z-v!FYk<Z1aX5hthyDb#Zqc;5(S9
z`Gz~!O{GaYY4QD_A29RJS{Oqj{`+GA({)%}1si!7?MN<VY7pv;slhe0xPX1-t#XCp
z+ni)#sb1=F+3f@tB=pT%x4MSv1)3MiA6~Qp$KL4EjY}LM&RNHL=)8}%SbdscLJ_o&
zTAFLCf3_vNxbs`?j^?Dg1`9bI6q2jjkQu3?TS0B*L=+$!c&{$;uZQBZX)bN{jAg!t
zyWJ-8{^sPvI6kM?=cRN101#}hS`hK6W!=yYJJMw*W^lHW?I=e8b6d8v2@nu@tQ&ZW
z@M~Jk1U+klrst;zp{C<8lhZ%Wv9C0_uX50^-a3Xj2DB!*0XFriG>0#6%s3s5Itue9
zysZnIh1Y}iNmwCFjPT=vwV@ZoM|i$z*yp+)wdpH@2YQp~#d<!@Cz|WYoED$qTa6))
z3{%`>{xxYNdue?uuDMS#-bKy{7~;7*;jo{VBh=K+HWHQhG?mh5w+=z9>&tbKPDWcC
z98^{pyCm|M;2twt(#5_$x%V}ZXCrlCo<SSEYboP+ob4fpsIIc+)r)+;m1SI6ka@)e
zGgeLCDg5dwtxSWA`(lZscv$dy^#YmZkfdjVDFNtS8;GWh8o1}Mtrmj^HD5rCzLOJo
z_UT$Blngf&LMuCLP7PPyU8-45<Ht{0iynYe0mOW@LT;zltjR9ltwA9322DWGMavKW
z09{s*_cl2C)!8k}3=Cu5tI2P(EKkerNM>}y1E{J_K4G5qZsGDubH{q7!!1Yy89Aw-
zIeuz2ZYpGtIB$9Y(sBeRJPcyF3(Z1!uHPRroc$}J)GmCxH9&KmWLGnE%jJ^X`cMU1
zsnEx?j5Bp3*0V{$<BW5GR-i+2ShE2d_o66##$(iE*7VHePir|yl`wV=F;;}cdh<~&
zzCgzmq9z>Y0~NWMW;yoq&BbZjzuG=%#zK*kOw&9+HPI7XosjlZ)YnF~(WGW55CM+W
zGx$n}#8ilUnZV6a)P@1|>IG{HNkPK>?DVSIj+=4izsr}vBNgYZU5`!Fjkh_yKSrNi
z)QmA9Fsb>UHSAs-(RA%P#cejJ0AnY;a#{;p>2_ywkon6HDr=7y3v84lk80?Sh~cR2
z%x{Xm7`B2Bwpt>oP)-1^9AzHW>mDibQ|kJ2!dDxYk}Jv_<khEhA(*S$JaL^;BOy3b
zk%69SiO3ayNJo2zZg8TUwkn^*cfV~_P!SjNsnb#k3kEpNVp|--38?3r4p)(i=Zmq|
zG@7w`;$b5;4(!%>Y-XTqr&i#f#+ug|Jmc$Ha~!UniT4BTO)u|NWVy-XimvmV)44v(
zywe5#AzAktu}5@N&!MR2n`A71iMXtmI6l=#O;~)>nOKr}J!%4TK{S;@4A%FD9Fr;%
zNbD;Fo-3#D-MLG1D-rYb9@Lo8&;|KclLIF|ohqDC6Pkj?FaR2fhcz)ioYZUwGzhNa
zf-zAvWd8vAs$#hvIHn$)XOZ53E3%)ZAl^SZoPd7{ZU!g;f!$7X^{G;3JQ`*fGy*X|
z7E(?rWs~<u7!B)Hl=^k25=#8prnd%STzvDnJ#)=D7ml1$=NOdWQvvN=u{oJED~-nj
zl41zYN?3+eagoxbnJ~Q75>(ntQ?~O@DNj`ACYXqTBhwz#e8>L)uU8TfS3SKmNL5p>
z6ai31$FByYNK_6^Y0mjLU(TAKvgar1NMbT3dx~k>O#tV)`q7G37!aiN#W9kk3z0}h
zDr`HEZ2alUg_v+D>ws!_ky)vOV+s?+Mq(wnAEjHBN_{FA&T>yCnKvTxuzFL1RNemW
zX{>RIU^f`eLPiMUq}%`;^G#w3p1)c{78MM{{{VKNlx9;?!b<0@R(8vpl8^(BN^oF1
zR9}rQa5~Z%F7t{Q<<o#ZYL9kl3CRN|)`1sYu-z%0Pi~Yu<PQ9Gry#-RsWMs-S2Zdr
z#VU09e>!m|J#&uLM2&2NPDwCEI@3wr_4cKXCXzq~1s4KKiAc6)Ju!}bYc4y7Mg>nI
zuWC%O+3Zux8pT#Bde=Q&S-m86);AYH6vpTL4RrQ1YOKMO44UM8KXM&_Ex_YpuTjv-
zOBf1q$7<r7+C2(%BGt#*M}H(C<d+`Gaaos_Gg?f=%V*Q6uErSlW1-`vbG{<7A2Xt{
zAY@{q6+P`ssX{!u7&khu_|8cu(x}@?kGT8ytmh@2vCSe00}_Lp^ynUB)r&frQ#jjH
z8}X;RxqqKIsLx)1Dk|<IYiVu!mKpC?m}Ghy&(hn6;;&?dCmF?O9mK-%{EIS4!!YAD
z#!qV_7jV31oYuAV!_9DaV1f5@+Nn);$fZxrE3WzyZG1KP^|wrLt<%!Iz|V*4!1b>e
z_->(fDJBXASf8zW%#z@B#bVJ&(o5mVGAixr4OG1Gj+0`*OK_~-fvbVmbxEStq={Uz
zNfto#`d6OaOC*<4B#)2@8!><@DHe}#xcG%;5P1baJ<oct;yqsKe+|!Yj>_9|0N_`U
zX)|wvOH+c#z=Q2xtm-a&5`4@qBj&J_nrPJ{%hy}Iy0zHzF+Gmz&x-2mTcs1W@HhuO
zD!!XPm8wY-@T|mb0<Ygjuv{Sn8=D!eqRixn>SuME^Pi=2Jrv`&t#r4mx(D>fKGn@0
z{+_kjM`IEe<JN@$p8o(!80D$ajGmm<wI8}%71<&$JvgZcEz*Ttaoq4RQ;7C2J!_2X
zNJTqF2U<MVp?xz<eoY~>e?%v0$+xeqbVgz2^}+V64HiJQ>JLm-q00^iYnFSGIp2Aw
zB4K#zOo<MDY*VCuflX#28J$<}8h{@&qhsq=qK*kNCQaXsHLYyMc9Wm2A(X|l1CuB|
z!lX-4C*GZxo`R%wR2W8FQ#_d@A1N97&;@tW%u+OqFPW2*nqm#Jb54<O;gE-A+3igP
z`GApHz{*EWrZ(Z%wRgHBnKZ$i4X34f-jgO@o|xjh-wwX}Ia96<Ys${y&4p&TS81BH
z=KeK=CaJiNzLn_!^P1s2aT!_Se128)85H?(Ry%PD^v)TFHK(O=pmwb3KKB)SN;q~W
zrg6=E_UQ7DQ}FDe^wb02n%Q1h59eI}0EOH&qb7Lt{A+v>U!3OD`7v@mYEJM+nfywF
z_mNBK`q!I3PfGQViBOi)QdP*?)Z^N`o$yb#EA;Lcsn3Fm<YSep6*{-|rw*Uikc>CA
zD)g_WIK=*R=HU9`n@&0HOhY@<SW}Kcp!T3*r%sf;N2N77jOLtr)W{E8_+3AlVKgKA
z=K%d{&{n*+;bhxxWw+`EI{yHlt$LWo?kn;RE2YVea_)QhM|wz*b)-C+1qQxQ=@3&}
zj%i0)54AK0CF2-Fz>ZHtn&zwkj_-~O3hcaBADN}IWA67A#Kv~rA@{GTz|Wr!k<U?k
z#?(h`zyxw=x=ph2-@QbH`Qfvi`qhi22MjCh@|pZMJe*{7Wi$1rRD|SHPeETxQ)9`e
zxYp@W5=~0Nnnh-d>PcpHTmy>OxaBe{4lX8B=zG@do$w<9er2y0G>+0e94pes9oXRd
z)-}T9oL2SN%Ms~Vw=45EHRPRUa||C!uOP@im1af3s_)Mf&@-LX6ZgdSHJ;-JwRJE&
z-PM-on)Rs4@JBqBq<`l$qt=>uIiP)WT3kbzWrtd@Zc$?Z#+mwaRnN6SF~>EGhD~*J
zl13CL81||Mtto8rO#-thU-O#p{3#!mrVMpqpX*!zQdlVNabBUKLLt)Q$M<+2O1Kjv
zobi3gGKk3P0Q_r`>T7?+GVjzjmK<|j`5@9`TN_#c!^p&YW}U3aH|-rwOQNBM)V>BA
zo@$1xCi(Jv0Z0pa1fM&mM_%>5j8(Eadsj1|H~L{8!``|)vh$7&0BPDb82vL@ek&X7
zbF?3NziQm|>M9QrD19;5bRDU&BhQbuHk^GaDhm>pj;9rFD|pJ~hJPAhcG?U{{gi~S
zBms)qhGdO)ZrBHE<E{0Xt*urVzzRF#nyEeY;}&F?ob!V~k3sunApQK(Np}H^{M~EK
z4y|~Nk1~*JS4!K9f=8_v1F^hd%v<<#*0Ao?a6=F?S#PdhNVwdi*NUel<nsOL82&Ve
zVp(<qagIBRtjGTV*Gw!=Q%5uaq?%5ql8OK+MHCLS0KMr{@+qUIG^2_Du$jd?o;mAL
zMsjLWI5fm19VvQ>F+juumyzp7Ph8Q808X^H&w4si&;Y%9bg3A8oj(d->r$#^Kl=2<
zRx8h?I4bw%oN0{M_xe%-MP*)!DSXfNSMU`9lA2^E+JGjJ@;>iA)f$hQnh7Jn6(TA8
z=mJa}Q%aMZ9%@WsdQuKe0Cv6}aQ34kr&`sVF2j!1&iG<-BXlQ?-79_0<UX~{Pva9a
zZxlVb$QbLM_07siTyitiS5rFv?Y^B2b2E%cLF-<|74$NZQ?)lf^!DPTC(^o^B2h<b
zDO>}!H1(%v-kVC}5S}T$DcM?U99D8=7PQ92@cM9l>#ny(XhF_vjj()QM!iWj-P%XG
zCHJm6yOfH|xNd5mtbo`!KXk8e=UVc_s@Xgrde78RL=KJp(m3zMC_P4T=*JYSa=zl2
zjLhVDZ@Zj;Dpa+*lz#5c;fG?Vab5S&hq)N`{VDm#s|%y*t_I5q{{Y}a6>>ieYYu>z
zBahwR6uqQY>{c^(V~TEi^II$7JxPzxacdvd^Hay*+4$e6$NvBTOw#ty?pL#CJ-B9+
zkSnNP2V1ZD%h{O!0J1So9u(8m^7l{v^8r)!nro=lDL#iOy+?o6kjS|E!;aam&3rke
zAOyxwyGc?DJr)o7V``_>h&2xxO%|~AA47!`DE=W&MRt57Qn5aWYq&{tSV#Q1jCv(V
zHJvUtA!Hx$6auq&_#;(;toj^iv%GWiS=^tZaZ;|4s!DJyB_8ZCU1NBL(0$)D{vcE>
z;#31GZzFwPrREEwG+AwD(7;a(YR-9zBp$5wI(SP{WAj{Ep!Ez*Xt#+ZC*`(5?&hO^
z5#6`kNSEj<CzzW@DXhxt;Omd$zleJ6T-A}__(03u&fei_7T0wa2luK6vekFg?^xvA
z$@o+}!bY*l=hd1~cu!9sdG6aDtN^PC;msiiKFnD9yVe6;-7vwpl>Y$0%`nL9Id(tr
zBU!w3*|c(Q?CKXz(V`#m?`ARG@lG>n@Da1@DUU@J$>5x1^!KI5J!?0Mn>LP54y@}=
zv8Eya0FQ+K0Dz@L-XO38D$=)Z1#<m6nod0{H;9`yj#Wi&bf?6yFH3ud`mp~18io8#
z8)t2y&-+HOc%{nYrBAh&b7hxMT@7~e9m5}%2v_PeQ9iwX-*m*EM6Au!s;u1sKS5LN
zB+V8Miu)zT*0mSwagU<ZO{m{K16;^{jB2sS?adiJ^tqX$!_!+LLvcI(>0FOZ#+X!-
zl31Uqq|F&8){B;*70@s+cn8-sfPalHGHGdCc0yu<)3+4tW|Sx*ns#E6x;-DlQg73M
z1RQ@l=)mH*&j!j&Oq;qk03U^Ridm1{!q=w_Vtj5UJhfzn+r>0+dehHLQg^CG1M!ur
z?ASFp;Bs?FVpGrQKoJ>u^`<natIJ}hXx9W)3AFPo5@cY#uxJ>qaR^<;Kt0K-?{^C}
z(Da8!w;#tLA6j~8u*ATC#QV@9SXHDM9MjS{Gsy2#K@m}bfm4L$fFTO~v6=)fPc2h2
z5HXrnT%NRmX2k=kH5({BYQ{01l@y4?=Yc>K+6663<$*|5)w^PVPI)Gn5}_eaS_6`4
z%EPDgrj|M4fFxBt=@@ZHtmNZAjYiiI2HWNWeKSZ42rwziK5<Y9zyswcJ%FZ7bYmNY
zaxoo%rUlkseRDziM{37?W^ln%PPlH_#aK&=_X^E!i|kK9KoVYCwbB&aRaju+vy(u#
z^EWaE^~ud>H{0YtCzL&R0%~-IMH!KXeE_21RfkNsf%ha)sr3uZT*rS-)bSWUUuuc%
zgTC#~HuepQ1Wb%J^Tip*Y8Pscr9U3jfM}B)sNC4jKMGPk1vW=0yaG)jl`cu#81YY=
z4{PgH?<HnYxDirD`>jbF;8)7#@cr^=^f2$;DK8lx%9R@u155)9eza!{J!{Hn=rv{=
z)eSQFGi8iZfz7ZZwLai(vBp0ds!_ba=g-ShLe#Ap9Vv^D{*}Kiz;Wx+fk?r(8hB3l
zp}+*{Drnm)%|*8ZrAr9OBC?PPyB+G?yn&88`c*bwXjUk|kItdS;Aq^gV<Vx(P+Gmb
zO>TXEl~D>+h&^aaKmm}zj@5l1J91AoLltTql)>ct)q!hM0NN{Y^7SIIaf;r#K_!7+
zrySz3%w(?us!u=wGMVc}DrA6|x{*xs*?Q)sY6N)Zf!93`)}FwqG{R`G6PXUdieo)0
z{m%U<g>&yo0hO&MnP%SH{uSjnC}X;jPX~7*y>n1q@W>A%ZFy#>o?YaFzH^%U42pNA
z;&5Wtw<%PyjFId0sE4tqp~)GqqDKoJ%Y#rJ39BSjBvTN8bM>i|29MsO#t5mDkcN&>
zAYt^RBOGF+J$i~UimpH-0|)V|8@$B}=~3VhN_w6s<O_@|$MvWr7!_r>9Pv=fIO$V3
zXf(vPkwRel)a(Y_RXC5%MO=>rb3`@=xd9yH(bA=O#(UEla5$*7m<R|0n$67=-_Epb
zLW4o1@ARhu?@|Cd<AF*z{{ZXI2Wn6;{uNdj5lMn6)b6W_ECgfprwR&?XvHf46Z2Dg
zb5Fta;8Rat^uTa5V<Vi?LFS*ImWCk$)6=gM(B72ba7H<)<sHd}?9?vBjx$m;fR31`
zkJE~!3ku^orO6$QAmbDsyj562=K}y!PHA(INJT3Qif%<lhX>xBCTWZJtDo%@iSeHG
z6oa3oP1Ju%jmI4`RW)=pMx&aPb4&~Mr+{iuF?t$)eJQ_zr5p;PMJFS@F!k?C){IjD
zI*LqUm!%lR05!5YRAl3=N_*2Aipof&Fdk{^)KfX9sihIJ#8?emR!yC?f}<ziwyax@
z_#?e@Vvy0T8T@I}f?;5zo|!$Vv6HkN+zOF~Q;vA)UMtc@$m8_`<ufAWlib#5Q@f>U
z->Lg!ZXLL&6-%5d*QXsxV{HQ^#Ct#_u<KpLo(;b^^{!sh%1yz7<mcA9dsSqIW-7>H
z6#`MuR;^28x<7GQk||f<oceaF_Dz)_=bzG;izk!KL2{s>?~1T^KD7k-DsfdE#Li;y
zAGEjfsD)b8P^5_av6`q4w>9n3e(E?XZb+x`sZ`)%pvTsy1B&a3gC&H5MtarFxD`q>
zk_}u_^7C6n!edxe4m;I`=bn`egE{o3!X;zZp`>zl@lGQ&)*N-LnX)VLDSDa+!Ju*1
zii1JR_pw%xWjLy;G3!=iJCoY3CUPIwgVL-a7#XVg!O!%m<L0%AjE9_#dsI)!;-x)J
zG0*EwlM=b(wK0Z8J%(DE-*-JLHg1aTf@l~N<{VRa$F)I1_svfq-TKrE$f=?{ifEY=
zRPpk>^{6^yJom**5#Uy+%0jmTj<pMd1x)L~&P_zar8Xo(oKhT-(wB-x<EL85nxY~G
z?kJ@rno5$z8L1HSQGwc|PfBQpOb%+qM?TeD4xOrahw15BqbUwy{{ZT!AFoQCi0z-o
zp?}t!6i7(NIHde>PHvquO>71CtXaAuBa=vf3J)LSKsYpt7p^LF;0lAaO%bX@$d{_r
z>B5{XSN$qw=hm$mF<%Ff-lB1zN|}HQ>P0}^dE*o?i4n-irm&|sT5EgMGgL&~XzfZx
zA??LUKn+h3?fohr;r{^ZRH@D|4>SprDfJ%p+xR*|_I<g=*2WK~t#J#;{VS~SWSM3{
zafe}w`K}|U&4*`xUj6f(@ZGqFShg>Nw~@_#0cO!hYZP0#BY|H%=r&SnTCyTJMO8T?
zu4~zBFXpj$(r=kg2Rv41p;6u3)zs`3P13XB8~AIHeGcmG{{Z)C<-`sP6ZeK|y|=!!
zzb=rF{$2xn8fE^WX{W|FoI3-+9GVQy16qswCo#kr$lZ@Q`d24)uip!U2a}#~0P0P8
z;@w(bS{bK{0Q3cUta&t@Hd~Lh2=L@|2a1xeaRTD!$`TaXJAyh>jr^*c&PZOktDYg$
zV2JrK3}EtWGfa?PGb=Ao$kMRQm6$vmz~dRmddY`bGv0Xu0Eyq8MQki98iZbpS-1DL
z_HEHeOq_E_2WpnGT-yMIk~7DxWa&27Fy4hAZC<0jZ`j@?;vKzL?+Qo0iEq{ql}Q-p
zfeoBpMI=oS1wV`$k5ssp7`Gr~9oTiNdWFx}p;LkLa0wM1t;|=@?PHVCsfEoC4Qmf@
zq8TvEyl2pR*GH&o_x8&Q+QYwb$3B(J>6Vb%%)%f!IU~Jw_SewEY&^}a=sVCeLR4$3
zJP(z~>0W<zqFgQWBgVmUNhdhx(!B~Pl32sWL0@Xb)b;B)E|S_-!yW*~Q%DSpjWMn)
zL<QP1K;>(s@P?lzlWOq1&meAj^sJlfrM9(shA;+y3Op;~FE;6|reT(EmyXoH>NWi}
z?`^!;)W}eBqpmAI!@4xKW$qv4-;a~hx<hb~MAAE9RA)6-%T}_~nby)!<$8)hR@OAh
z^&2A;6BwlG2sL9xvY$_|SSOgu!}yI!dw4AE%iv`6&lN{S*HZn=Qe!#!Td|-6UeXQP
zd8iDXGM<%ZMzogJ)CqWV)DCM+<XF_R5C^SRvD7WK2-&UV2Wi7EaX{`iT_)Ol*zX)S
zn;%2Ev``J0Jw5B5@eZRsoI}VMJY@RSod*6}>nAe|GB(~j(h+Uowy~Y=6;w0v^{!9G
z8oW{1GXl5(j(gU|qorM3>ak2F+XC~C%ZlfGb)+x$drK2?Gqp#!q{fdrR`Vm?oil-&
zy9vUa)ms>!%T(*{S0PYj!LAyco~1RQlAHm9pQT;U<s#vS_j%{(QO=0m0rKOTv!h|A
zWkkl&oSJxljL#A900%+%zB8*rLXLT<SDJ}%QE~Xx!1`CFc`R$M%Z|0o>QQZ#xXSus
zx`J}1uysiBF(-`rRLrQH#ljfQ<QP8Hqo(QxMe?OTFz5$*j(CHUkIJ)TMutGi#bC`&
zg5ftNS3gR~o;KWaP7PkMycZFaINgp$X)aSJ#~jp*!<r4<d8~V=N`}BBS3u)&+A6%p
zD3|wyW8Rp~=fdGfhv7rjR1DS2h_@cKPr~vEbcG`rC#7gl^71$|#8X&bcRzNSa_JK7
z1bgD9mUj_1^Q?&_48=lVev|<W(ibPMUX>S|P<5;0W2oYTX%lwm+Mr|$D#*D9JXI^_
z2&4`w<nXP!ouC6*(x;oAa%l|5k&8Banr1WJt~HrfG|>xoQ~6PFE28oMtEmoD4#J{X
ziZJ<m)u|*A!MyeDKpftoJNekb+BnT+-AGJ}4i4sSgM(cfSj5fdKW5xL>a_Ndwb!1A
z0Ub%83@t)$u-PK60etnSG|SlKDx`qfJ?fsbarT?WMJHnL0Uc_LaWZ_-whlX2MI~b?
zGr2^Bg)1N+^vz$fvNsYdBIg|Ru0KGE?@+rjw37KMFzipQdR3&5+C;IcD*NZHI+b~L
zHKRwLRx3~CMk8a&imz{V<xQ43@AanYBY*Eu^z^7KpUhxivFTXKrQu^wVecF9-V$;E
z`~^jKs4^%eIvPdVxb>>{{K0`-v5lS0-56NFzST^Hkz4_vyXtE))Jc7OsNAo9^;1=C
zlgP=`oYz_4IIX6)D{#skn>Et~q03QNuc+y8N2i^!sK`0U>t11cyKbak_KqvwJX7I|
zi8Qy8#IvwdfDL$Fp$yjdZ5_mHlBvT6tx<z1eLB{@j&W~3MmZIbSZ1`e>D6I$&&+6^
z#nar?j^UCrH=KG@K6^Ze-jf-J>s2$g#(AtPbr#*m?*9OdM9-7{6&p7c-Nu0qX6L;(
zJo{2|X|8s_&DyCEBviVWdjJmuim2Ub>~eb4Wb<1inm}nOd(vl`WS~4(Q{n#rFj{Ss
zBb=^%E0<I*!A42+72VlIvd%Tzw*sY>iSv`zkdySLvD=UhMqZ$%OSln^^n`*l%~ok}
zbDC$KI%b%O&#|b_Q|KwCU9IXpsSKIzOavmBPX?5};CoX^$)o^#(U46c&O6g^a(=wf
z1exp4G~#l(H5eSw&4ECS`LbtW+K>Pj(w!&EA*N?F+_pL7PZ$oMXODi=TqfLXeZrq>
zZzSrwSLG+II_5Np>;#fJ=Bsj9PkT37Q8TEg9BuZbr(q29<=yE{-du8jI$gA+4z#Q>
z4>{?9OZ)_Liix`MO=%7=DS;>=kdP_@<aeM+nvvMB9Ao-ZOZKS414)sd;*bvv3I4S#
zas@qVIN^Delo`b^DJKUai-B_D<TN-PeX0avtJbTMcVnQbH*tyr#NtEinrl9L)Fh1c
zrWWJtMZ&~{?mcj6t+{i}L=8L4C2&T63Qd(_LikP%KwBdwhi);7h@8|mQbWP!pPcrn
zK^@IIJY-RDu>AC-WAhH!rh~;Wo=4V;fp$p(qG0tDi6_nT8m#S&qco`bAJ&A)XxD`|
zp1H+H$;L%z!7*H5@;Vb*QO&)2b6p9UvM(>3{*<e|8vuKCt4c!}up?c*rk^Tg+``ns
zFsW}|m7BLCwQuVoWPm8ZAd1BNE0VU1>ZJ50vY6Z42hSb(uS4+euu;?ZgmLL!Y<kwN
zlYG!hqjpAk2DvIm=Y1L5L)~pIOp&XMVE3fd5J?Ds?$!r~^#LLPSZ9tiT|*#}JYyk+
za%^@UXRTP9Z9(041e4~cSxambBN3BbR<oxq&6}t3r`<T|Tx>3|P4h-RUI;bnVCr9U
z%*E5Qx*w{?3gP29&w9ym^Lo~%qbx3quo0Teat&=;bCnu8S?!K%K>gF2%+k-yaqC)t
zg=B=v7j}s%6Pz07FNle-9An<MZl!3|$$SA^g~YN+Bc7i1(|rV%r=fTZBD8!CPf=cx
zbs~tzBPX!0C-A$qzMl-q&N=t4hCNPs?@@frkKzZdan{7DZ70<1qlJ}Nxh{oY60=2p
zZFBzK(tkSS_3`#=^q7y5PW9IKrbIRcfcck^^{z)%U+o<#DU^-Mz57;;-56TMduxMX
ztHj)Fkl=&B?_SpIzwm~*QH-JDyeZG0ro%WJq>K#ay-Lqk`$vScxZ`F94PiaetW!Ls
zOd!_0$8oh}`Irv1&}*{AErPwdAg?01o7D3z?o<Ls^U}2}*{-yPRtIvDK5q4P7b9ip
zrSo+1;0{#RI^b_3t!imo*4jv%=Wa2I&71|9{R0ujc2O{#9A2en7&SBtl_sKoPfD62
z#w$vX-7b>UvmY&!Pm%IZH5#3xG<U93s7=^446*>+)s<c<l(_RV??V$heH>;Uohw~V
zF@adxDgOXQY}TxI8y}3~xo5cywAfYaRm<*d15KK3+|)=5bKbLHi?Jkc^33~BsHuL-
zZrD>JW46&%3vT&vbM00j)900U<f3*Y)ZApI#@t7gXFkTNOKB?u<Twt!jZZ$yafNm#
z=~X4UF`eOAzLWsNBa&mAa<{*FfzbNZpY4bpw%oy=LI)zN+{qs7#hs_1HKj5pYiURK
ziYvVE)8*biM-}J#Yiwa%w};zp@CUlrE@d8UJcmKrXzB<x$9U#4ZPHf285yp@k2THs
z&L1;O<F_^N*<87CQ9UZE@MoAz=gh`4SG2aoz;^Fd9d{kw1y84)w^-wv{T*z0=cRa6
zwwY7ZX1Y=Ju1mt~%XI#LX1dY!>t6@N5Vj`gr-yfe%XsqK&7r?=1$d*4u10tqSH1YI
z4?jYk7w>H+o|WL!3^M>R^PlHmX~ESmhH>n0W((fAO~x6yrBi{5Bp7bgi}$PTk>-Xm
z(wu)kdQ4H;m<{jJhWnJAX-OEM2CrOG{i&mZaZmm)T-33hx5HU{t##8RZown-uVn)U
zyeGid1}_srr2XN6{(n06U^xVO3jDW>>Dv(*_dTowy)sa7N`91zc%?P)=Wx;1gUux=
zpbVXTH|WzS?kmpR?U7g>{cF?p1oJfcm)g9-U_m{(HT0QVZi$Ue&46&I`Ri6LK4=v2
zRPE0Dc>a}n<1K0(YwNPAn;vd0T@<}(y=laOP3YD364ob&9V8*9o<YS))|gM_Ste;>
zFiQFw-hqSLt~(4@J0!6w`JG4OT2`8XYfXwWdV^kOWUm9W3%JY0`_+eZ06w1erFlKe
zvkj^j9YtbXMI&xIo9SK==oKcF0p-SOq?ZFfDEv)K*5n_XtwQnh$f`hOYD~;BYaz#_
zbQjSNCAjyj7F>3(PY(UV3GPMpr30D>r5!7BE-4%uf^{BVefm|A)2~{JQJC7Ys5DW}
zy&qaAtcoSKkIlJ?G5k%6^_xh<T5^HedRLfe(6qX&Ab$znUasTIwJKW~Qa+qku-J)i
za#z+iQ(U~#MZJ%y=~SfhAp4L;G40J-yP6>1JAe<pV^4PzHaFy-N{1qeq|{p<B7lCC
zi+LfD^4_(i&^sVu^%aph{plSDH6tx)4U5r+#zqBofpgxt+XIWl`qyXyDl<$>v2H$f
zKc!8p!@EqAjNo%nLUKo?Y092%pCWcE)|(OKBoKWmpN&|&U6)dh!HB4MsVxW(HGU3I
z9Muvk?Xk*JLS+3-Dv+l+q@y^d11=*Hra<|JrDqYek<%5Z4<f5w!_mN`z@<w{MK-03
zT1r|<04So009rawDSA)=iaJqCKoUpys=(=ru7{CRiee7*8ah#qdQdR@Xf$y~MF0mB
z4@xo3D4;@$nkK;+s6ff7lyg)B@<WBns5^({R3u(_ttf7hMjgNvD?tN|=*#nZ8Z0ZA
zWlm@aO>7$g-*p|ni%v~4W?&N1ch7K?a<I9R97Of0)-pR*x@dZX45pno<Hbt89M&d0
zS?&J-d4Q+N7cm)ddh<-luAlx98{)q`#k6neTQueHMay#flnegiW{U!49}PG9M2b1d
z71ossxIe8@(>yB$gn~&grIo!STvpkN!Fr{`S3k3S_X8qe85nU~z4=iyF5nx|yYXvm
z<dw6XzO7N676}}`_GCrR_xY~sH54ACG<lJlKktf&$_e>$et_4lCW=*lT|U`Q`;|Iq
z)3bfZka`5Io+Wk{Ddcg(aV7+I@}GURYAqXAm=c<8$JC}joqE90B?IQ02mOvJRnnXf
zn&M;hV^HxPLCSeL_-|QbgK4mOvjI~lgta#rd2Nt-m#<U)#kV6T%wz7=D(N<{oUOPm
z+_g`)knDM4cs}PJywoj}f3wM}3E=B-k2g?|pY|6O>I-8Mr~(MU{{VKJAZ5<QjD8g^
zw3zI9&98(kA(dst{JVWHE2oCm7~xR17Yu*fHM+6N4^;!$RI3wY{Km6#Z*VZg6XXQa
z;S1``{{YscHg}A0E$r7P`<boNZ<YQd^fad1Z}6O-T0<}wNV(_cw@mj{8L38&<mBEk
zBm1BX*78ETdja1x?T7~ePzDlctAGv6%zbxOHoC8+0Af(%)%w?Ov;){zE#ml$migdg
zuhO%tqPjY;X-cY6IO%oEqUT^l2e!(tbz9O7E*O0}Re1mnflS90z~;}Wjuw*WSZzY>
zhc_~PYBO;&pPp$O*s-QkWOU6Y%~cv}pro;E?mwL&&M5q84J($R70_L@V~PjmMra*_
z7^LaNI39VVJklM8l6`0#iYY*#EGBV59`yAY=ZbKTE9+LFa|)P<)7*<ZQf90ONgRw&
zW5-UFUd+Smv3nv6^GT9wMj1UQ3H7AoV_4!-Bh4IsCY)CtsW576YwaS$?fogy#?wd<
zag#_v^rN7qVy|)X#A0%+S0m8VRfy<u^rrGoX+;AA$<JC!KROKn80U&mDN%BJQ<!s3
z#(etNW-5DIIWHZSJbb-LsPTbK1(cGk!#r?l4(yU>{E19Om5TQrDVa15c|Cn;!vN4#
z&bPr6fg?qb4&$8v07~>9`D8t7%RDc7wz`lTU4a9I9qZHMkhBOuJv-N>OW{6CFpaCR
zz+m%84ti83Su?_Bq*D0lS{y`!r+QrczVwPtDGHGJ&lCX@?#)ITPDXGl%OH?-#Y5z6
zJ%2g^!_|OXllfCw(6%v7BWm+dxgCuFSWq!a8FN(2ga@3{e%l(iB+>&&Fe8u7nJ36T
zQJk8i{ihH(+Rf}LSnmXbgfsyS(bOFPw-Np|M;fV+26%$!oDz7gks&MTnu+ELF}8ps
zKtlY@lSzPjWKx*`OxAVH?6Ec?LJz6wObrFK+<9mE=BzE6?H_obtz$u|&7HC-W<Hgz
z71NQ=Pf7r?v2EavO-60v-cObR>%ghuniInwY11@q_c~GnB}Gx6(u}7$J!u$i9+b}A
zsJa4B$&=QA@q#(1z~ioJG6?H|MZmNqjei;hh)Cn}s)dF+(s`&lxC7Re!o}v5KpcKm
z8%yj3S8KRcald!dnuy*;212`gZKceD#lb1ZY}16CWYq(B#Ni;5>rOWl5yW4eE_6Op
z<4Geh*^E?f&Oyl;s%<^MJOv+(HQMmDR%ph5*{t1YE!kX*j`lejL40GcTCrkE#8tg2
zgK75?${u@}2+u_wD|#rAVpUMzh{3O&&FaCl;?CSUX=-D-kt1gvbDE8^YURrO`KnSJ
zSC@O82D~l4+m6*@FP_!Z)f)!PMSE4K+zhX3Q22nPZI0td*#fvERrLV2aZYH*29v2~
zGMu)GtDIG4fSTJe2_pv;6F><R)mDXL9KgV5ueBs-M4NgOTOViQoAzZAX9G0-rS}UN
zO$>$4%00QDTgb=m@mp^K@$!NVAWWZX&Q*}i$fIbK<BayGT^U<E*1N_Cs#g*I@Zz00
zCWKKnX5F~!gH^~X)hq{}O0YDO_m<>zBc)deKU$jEvJV|;yKva3sQuIe#DMX(k>e+d
zd|XLV6w7m2Mc8E*gL2h*ExYB3>w#K(M}D;3p0%==ig7~Bx#>>(H(qMoJn>Ft=RK=F
zcX63lP=4=fkF9xEiQzD62LlU^4SNjWZ6~PDHRZlEhh@sJ9Bw%^^!z_k)j3XFRBr>5
z@6w#O;+xGVIOjF?DDv55l~qPaB=)N8dFP6MOlLJ4RT4Wnr>hO0N{oJV_4LhJ5K)40
z%^9T}cB%m}%}53XHjUg+F;AeVoae1b#9-p0BPTU1WD9`&)ucG8?6_)`dscAl47&_z
zA;Im^nQ;(C<B{u8qY=m?A6k^$p;Clo`qPws;T8O%Mn*AA*_xdOds5>grD&;z%Hk4g
z(%XX`>|>7fhyggoO`V7U9CWAb#d4WW4>WDTs~8#nw1f=P<Q2$v)0J{5*v}m*SkU91
zlyZg0O3)+EUe#sS1Y@6iW01XlDOfI6VYZ?m<KCt?Z1MD{j%pe#XzNcLnqcOg-|0vN
z6zp?I0S1m~p$^E$ttL668R<*fs6&4$LOG`&OjCPypaX$TKTK1wDF_sXM8k@Y1T|SI
z2<cI>;MOvZr6wrkcc!q-I1iSBGAL@`3TU7MP5|xqqQP;UGeAF`J%JR@%8&<2PPC-r
zlOR&K3II5x0QUT;0i!01j6>5L(_5cPd8Uz4#zcD4m#qy*wFqRue~oHco;uc2@-hu*
zSs$3MIjpe@-2`u2pO+`SSsa2n1ZSG3ZcAVR`PJ0G<2kPmtZdEVVP0weWx<o4Snw*%
zmW*bZBS2W=7#OarPSYTrT1k&yIIEYso|~e@#=t`3j<x7h_)#pOW8v5>qVsOY&y0l6
zN`m2`GmxBt>DsV0KNa0-1(w_8i#X3r)S6Q}Mhmv)Jl2G=?B^_VpK7;YduFRk>r&Xa
z?+D}TOh$tcO+@D-9nDPK)GTR;!PO(f1CDc9%6+S2RReF`<bIWq2d#TJcX%U;s?=~e
z0OF=o#z$(0KU`F*f5@)r9MT@A2c=w$f`E_KsjnujM0mz4XqZTQbmpRSQl7rm6AX_3
z09tHFuEXY}BAmvU!-~n9M6So?CqJDXO)K!<T0p#d)EWv86=D<qO+cpynw~RMh><Qn
zZ+~i@E&v%72_R(RrG)-fv`l15agO4nVUK!{^rkmH!kZx#h{JkQNc`#SG4Jh)V-5)d
zvu4PJy7&J88bQSler`no=Z^IZv?|oGWF8Gf23NI77Dhd(p-7)UkG)F~`M9Xb$@=qB
zCtP~gsK!H>W3S~<zc{JLIQmpghW?b<F)Og7#}wiQPxPc99_F)V$cXjtNlL?-L4Ya?
z7wb<^Os6R1Q$(_K81|{7ZgEj5%JivF9Q)R&%0#WtJPL*X02-OPVxf=_J?XL{Kz->t
zbfqJjPM_mhGocU=LHg2+(zY^lMtJK|Pz+-gEIgWsocdIe5D#3_LS=wzRLKPQsE2xy
zcsR!uqA`%-Gwy08;F_55-3>(igP+QV2(EbInn~Jtr#A<uG?@4NF;LAB8*pj8>CK;7
zKx#`4)hciWMV{uRL64`kGFdRk^sbA-FaDc1bGc3l=yFYS*&BHot*;CaH9?L$pU8^w
zbGm%kc6H#TYKVV;?dF?QK2mOzc1g#|2c>$`X);{gVqiiqZM|!g_-Y`q(>%u|q>%0g
zy*}FEr+_z5Yk>5Ooj*vj)2?KYzS(5;JW;4YU?(%lhiqq)owZ9;@b%`Ssr{j6WkTSL
zG2nV)v}f@7p4LPxM69F&DniFIed1dU;uzgA(>Vg83}2KjwY!f>h93mYJ=rdpRls5B
zYpst*OM68{1&WLU)B)!@mxr3><Vd*+dV@q7D6+S8kL6|<CpEupnw+}1ifdAk?jt|l
z6@OK<NGxQR%NvJJY5?P{ZRdb8O8d@uKGj!I(PX@DHY1V;3TgKDZzb}eeagpyT?O2$
zV`b;eynA(|GaE$Fp4A-7kt2QVR*}(dWV%_HW<}|mv!`7x?VDVpk^CfQy<{$-GU^M3
zW0uARF&8yWG+tY5$=<w!Svq!^HMGpm!0z-Iu8QvC$cV~N@mYFqs+xq16;1)<5!#Rn
zwo|S0PLg3pcQ36^be9H1*js0Py=n{XNZHF8xA8VGE1<ES*v7KR%jKS#q%%`Nj!3Kl
zes_CfsOp+Mtk<#Jz66WYn%lR!f@lGR40~4_;yq4i?>3Bu4aPgt8L2gz&u(Kq2&(=c
z(2cG8OD1-&+{ISX^(ii4%kBr?y+2R!8l7NS$sCFg8^^6su6h_q=8I$UtT29+Qp-oO
z)24T}1Qz7v)DvB_7IH|LBra>7gI>9c@NUZ}IU}y&?MM#7_R%k`{HN{8{c9si(B9JT
z&66J^9e{KdxfFq;SvlsjBJm}(y1B4rVBq7Y8Kg5_NY-dtCmBW<BC6^7b-tV(ZGlx|
zmIUUdyPcr6cL-R4oOiBYPS);DrGg2Cn+1!1Dgf!V4L&VG*^*3yjAo|O?NZL$$xqDF
z=4MzVWCXt7lzY}+hp%sLgvRnRn_Fneq%!WQe6~>o!D4HM@twub_F%b;?umfu*1GL~
zPm=N&-V>Hq<W@GN5Q9cop9~Wj1XRyrqq)P_+P9W~pdTm(t-XX{$p}3&Q>(;;<BZg$
z)#Kyy6~QypiJLNn7{)VJbkqwrf4$n4TT<<uoKw*}r45gpu%%91vrH;Onl?Anpr;d5
zH0$)cLX4$lUfHYLvMbh3>ge(32M1;@>>pan)R1mceL7Z|9M*oR9_Yv7X);lXBIJ-N
zoUj6?j%v<IoO7C2UDb;<Mla88C~?-cAi5V3`X578?w~9UP*!Vc0R+^PTe&73*cm6K
zbGLh@cHG>0S4PsT$)5F@HN0rsx(Wd8d>Fv!s-WW>R?WdGq>8}sUCK*qDkgTX8TYP|
zbS#IAVt_IpUFT`&YA1vh;B)U*Ufbr+H2Cey95nz?jwjqWIH}ta$CH8WS0`w#qC2?y
z8t1QX4byB=0*`)bSjw7~s+c%zj+K`dsG?8_z^iYjGi2?^&sxs9(wSF(BOHp7jrb*o
z>2j<I1GOt6N6E!<c9&9F%s?luaD8i~id4FTetu!jC<_S2HYYq0QIw8QQNHi3AWiM^
zjM7M=G|4!iMLYE?8IA%o=~;S|#?HZue5~9G(ArGl$@xWb`t{+|Z+3>vQG&P!gH;IK
ziMt}bv`|XGxa9oA=cuiiG|OwH01c$~tJ*G!8Mj$Hy}dSr>03ugh+u^w$8pxZYIO8G
z%9UR+n{1ZaZKszX%DDV<R3p@!$^$VRbL?vVucyqh7fdoQZuQQTF^`;|O7rVcl9B6S
z@ey%I=nknG$MZRFdfL+>MvKe{c{t{{J4mFsyif@$xFlD36vEaJg}V+bno7rHUCZup
z*%e0kv5dBPs_Ut5kcQj&({8V0@|Xe+MM^20j-rL-V42{YX1bpXS+%a2x!9I&0rWYp
zPWIz%_m;WqjN`p}R)Y*_V-RKBdg8jH@Sc5F?-wn#-A36RB~^QTU=!B7hsIY?UTWq<
zO|Oy-drRqGX@&OiHuSF)@r9wY)}1hZZ{qc)w=riofN4S6*#`&Kkn>H)HA1<uYcY60
zKZPL~WA&;Q_XZ=3{HCrf%Eyz<XDFQzsd7gcrVh07RE`d5y)(vYENGa#f$v+^+FD%b
z#r6&ExvU|QdSbUB)+4pk_M9kD)82$V4mwz#IT>5{PkMxkvvV=HndIZ<JqJpzM-{Qg
z#?n%nI#Ut5;XOI;^-x4*(KtBwuKxg8v=;2BgK69NRwsZhFD;bZ2!_|>XT5bEAd#Ix
zb=uhJS+}WZ<lp5r3$_>1r<0S`tH?OdPV@l-<2mCdqG3*dm+4V%1oxl-IR^rjX9KM;
zmHcWp9sAG)k2QNznQ(oonHcRrbL~JEJklRMy(tWb*A-Yb1&;&008i#0!jYuH{Iw8r
z1x94!7{T<QPhlUI<nz{=#0p&G`qLW+{{XFB%VV9E;GO=;p;&;Yw-lc<63lZ|qL*WA
zX2PESl&sGjn@>KJ)3A$M7ik<)c}AmIn2u@RY4XSpYST=S#@)_%rWhP{t7)j)1|L0G
zOUpS+WtSecS_s5+bv%lVw_~BMf#b88_-+SIYPH3@c*=l9CWe`dj1Nj~ea&5#6<+mS
zlbX$znH?w@_01_l2V+t1AY!4hlBDxM-y>jCo^s2R_o}&b>&+(abDEohC~sO)_^5Yh
zy)No^0sHBjvrR3{ChAR$kT*2Dfi({7P+J3<n~ZZlNv6^U$)c6U6uHGTnov2QLgt!%
zXr{F=BzE9nbfyO&(7cRNPz9Lf%T=_SXCRzbP&hR_auP6V)QM=*`)M0aYepNL@NVc7
zbM07b&JJ-_Vv+o|RT-^gA~{A}%x09a&MKd+XbX2MoxJ0vP%3grHHBr=-jIaQk`!Rs
z=|o7<&m16tT;rP3yYS`xoE~!&c)F4}HHxPxE2DmE8@?OW%u^!rPB!HK06O&>4NWD4
zHvU5PuL!ZYHtra72D|M8R}#h)wj>=u?_8B3W6`57bayk}A(Ov7>z39u8LsX;`wmt9
z`j1+@JngYv4t;BPz#>ggQMqR31V91D0M%jJQzsIaBe~~ST5R^C6GtMR`?^&JU8cR$
z#<~OzqCBXpy;rU)#4Z%6KDotuH8s@n$+XY)%sO|iP<rE<$<w%>6|A_)#}%3rIn8S4
z%5aJ@Yn`|u!xr!9TOK1&FBIgK#bJ}jHQP>|<91EX{{X{qfuzQtfFia9myqIMPT}cP
zG&BQ7i;!@gN3Bae?4}aE03743c-e!DWSc#lznR8K5$fya*~ky~b6mZ#-)zxz+DOH9
zKkMxMbCu7va&VT1T9OhNqn-{puDCvGYDnXhA3KO>_5tI&x0&(IR~@T+!`B82Sv32B
z@{hVtN~dLSCAO`ZG7yeOV_R!wZkIk`Q@g126{IQi9_AY_bApwQX7V^b-72De)6NA)
z6d(tS3<D3B9V?~OA&ijW6c1rpyH#5_99FK8-Tj{%YGm12T|${Fw~n5bm2wEVlj~ih
zAKmXA>y*_Y@~;~UfO)Mc#>bPHU{yGC#La#U5xyHVOTnfJitfnqsVg$t&5`d?FC&_y
zzk3;}OzfX@{#DI$p|ab)7t*M|4eE1F`$2BC8Tp!>$+^;LEEeCIypOt0D>q8RA@*LC
zs~TW&T=U$K*&Bc&r&U}4IvT7?9>$d%769-oHU_P_+rq(%{MBYlgCcB%jQ;>S&s$WG
zWH`+W1hBX&dVAE2Y__*Wj^#gqs9k4>?eb(f_N{SwBMdpsF{hUqOk>`V9KF)9VoDX~
z(wz}I25VC4Hjr-ParLSmUOMrL)&$7Wuz$PPgI%_a;A#*a?eg(lC5a$_KPv2Wx7$1o
z&kQPY3!0RX5YkBP&186vJ=#N_PAgydN7AV3=wD5ccERJ{75UyD_jsl1dh*sMkx3pp
z9@N`nQseNcCU2SeAc95>Lj!-MCVgx4ntH_Xp68%=Vqf&dUscU^fbrJ29Rf|aNORX5
z*ME?4k3r3RcM?P2jE_SK{nD1PADO01zwDa%{`-r$R~XvtG5FWf7fZg<Me0h|&-%<p
zEmGxi(cAf&_V_M(PA4{Cv`opDuhy74=B1EeR6t<Y=&15VBPNgzIvP@aC<OGyFdN?{
zjAdy}B>*%K8l)zfif|behHQ9dLm!Ck9Djdq1$_e%4H}<eUpVQ{<?0Yg(`$y!eG_2Y
z>>+Gtj<xyc8q)V+Bi75_jTZ+r;y9)+PHFY|!#yFVtp<k82c;k)nRi>vz4o3f$*<#(
zY7-6Zv^N#&m<J&A>0V*1ua~M!G2b|^pvmR#$r)89vXFh78R@{yYQ)>^@toELh#Z{$
zRkdnCLM!UB*J&IWg>+S6hR3HB88~W{#vJyj9FfI+tX=7&z-rTCNh59Jnt_%{4^k>%
zxEVC%QBaYoL|c5^^PcsyrCY{PfKgN!a%)3LkSzN<w`%3aLiCxw9$xVKyLDXSr%J@S
zj~%(LlJH?`2Jvv+1}o;#>6nuaO;wP0#ax(@#{#NINgnk=DP2dt7Orwt+Qb^^<{!E_
zu5#gjczN$#*j8mwsz*N5l;Sz2itI8S)Y1jq2<matm3kahkuGH%W}--C6KueA$JU`_
zD0!~BI~9=xm;kq}P}Q`epiF}UxB{>&Z-nFDtf|2`{{RDCgR4p8X>v0E0CT-@z6pmn
zFE2O;j8{kEdxH*_AqN11pUSjaM2ETNb4X;F*s*Mr)|S<L%c$1`^U|U|m2*jqzM`FY
z=Zeg;e(gM)UqY$Pa<d=aALm_euG?)`k4ofR<&6MKXCR91HX}bU>s_o|#I2m>xI{RS
zPob{r%}ZKGgW7;)n7J9PxD(8?e`Ph53}<hzy=+>Luo2Ual-VbhYLWSRjl%jrTBYk+
z{vl1ew47r+=CThJB_PdOwLDc(R&7oXr8Eq;)N@W9X$Rv=x2`IHPMxX523@Raqz;*+
zE{pt1KN><P+(YFz9V!ade=bzUa(!`BR@!MBYC$Xi0J@~o<z*0NlC)#dbvaMTV{(3|
zMOj}9Yi=?$`2ha_Xo39A9Fhy87MH26jz0wI?z@>`kNx>7#C`?4KkF~8Q2GK|j!?bM
zR+hUY@F)l7)It9Mu5lWbd=+Ax$#Zi4%AkKbT6Z0vV~C>z*1Z8dC8MYX*5LmDy!fft
zL(t$H+rlyb06iql7msnOb9*Ds)qtteMPdL1=i0pxN1{M}SZq{#CTZhW(;?wr5$v(i
z&jr-AhpP68=c{dXA^9xlVd@aosPt`GQS#~2{ws>@o5WUUg?T>#fl#-Jp;Pk3JN;i3
zKH8b0!PkFe<<rAD+n@OHEAGxJ%J?@`JiNBCXVt51yiQngY<c6C%~;blZ@1p04;I4R
z4;0mCH)K=5R#E0=EItRhAQsf%AMUPdbnrwt{qCgff7nb{qQ#~}sy7VPnDqEb#>Ew}
z!p}O3!J24a-c5BU<5p9_`a+H^rhI>S>(E7%OVJjbAVJX=@}O5ZnEW}XDvg?KfAB6%
zU5`uI!r5A={{XIa)%i<~6jJT!Kpg7W&x|TYpG2vXO}TI5{J5>Xxb05cjz<)%1}M^8
zjI@#g)9+M^q9GZ6e!SMX9nB$`K-v)J)_^nP(IMTO0BXR}VNBpDsf>;X%DmN^W-T6N
z05_&-0Yqu>BX$CwEu&vdQ{_n{Ew%7Hsv%~?WXR(_^bD8FjYT*F2dyz}R1W9rX+#N-
zY1{{8dmPekr4fwgowpRM14HplGN9t0fzptwnk)ouI*;Hq({uj-Oq!)A1~>+rk6Hj~
z%EW!bKD0E14u+qCeJPSDGyw}wDf^@k!jWEbe)#;UN_+E8P8xs%9L>*~!;aM(+qqx$
zulO3crz0HHqBZNlG{B`Dx%<pcea%j>af}~Ilz=)BKp7%{8@C*PI>+%W22C~C4l8Vo
zR(7zyW}7EH6!BTr_zsLCwOF&rTZ6}HZh5KZj3kZJe8kiQV!YGrqp*UI^`$wa_MoeV
zIi)$I9cgI*1M5W{I`KsV0YN9)ieB^p+5peJEhkz4k}@%hdXNt_5)cI`ZgW<hj4D%8
zR%Gue0;4a3!KjJJq^9P~<A;J)BoCT)?kW!SySSs69Rx{`X?CqeyA+|b>%|u#(R~N)
zq`^ID193~djwlXUpxf<Bu$o=|wC^y3j<sIsoT{OoLlw>rDZ&B<aZBbo6xNitb4R*I
z@1Ib?Ri=^Jke{s^s#`aw3vLFIgUO<#-2kJC0H6v0)6gW@tVPt<twO}Wpq$r^>2Kxg
zmh5qY-Rsuv<juMf(-q%A-Y3mwk+oZvh6W8r>hIBr`cj4jb53c{E;y}^EM!XRm@Y~6
zH1_0m=9%UJ-xL=cbNs1X2d@T)8R=1pTR8~F@TC&Ae&c>MJj1aZi6I!yDy*Nngqa)<
zdbaXAaljtts>$W&4?GHe3sUDp<z@xt{kpgfcHMsJwHB9<%P!OsG4(Z}G&*Q)(p+2Q
z_ZZCx`eX--lplpltp&R)l3k0jTBhC1593x;1s`+@%xzl1Iy}$xUMauZHjV!PEa&>1
zVxi)xcOSB!V@S-vV+sWzW@DFSz^rHS6ibzg$=!j+&e#;6+P6}-%LTX%+>=v0WjOB2
z_7XLvbbgLM3aas=cO=$S_xJF|#Caf&auT_D{9UX0j)9eMNXQiF;v-Yx6sb7wdJ3Wp
zA1R6T#Y~vz2;Yr)dw7#qbwBBBGx}An8&JR0FScD>&QM{14UE&NTarA?QH9-)OA_I8
zh5D0G%XcWiNnsrHtou7FSBRI1S-o54H8NX68<LTtljtkQshsO%j+KQji<W$EnQ9s2
zjC{>Jn^*g)X}RaxnJCOmKN`>bUT>jaRz-O=D^v#!J9~jhx}~{osFF5+ym48Q5DR10
zpbv>uf!{T!*XpqL5jr70N`VT3-2pW_1_Wd;BeiEFyS6&>TB{<<0vz_~SW6jQ#k9**
zVc0;YZ>P{y$sXj$b_d#`C*`T_`Gkt|s$+2$_>Dc3I|9T3>S_BIrxbBUa%-L9YQMBs
zBzp{GMPc$UUrM^jn?Y3qsmO2#TCyCN*N&B(s!8=9DjpjPjPXwcJmWQ7K22GO<$dcG
z-r_T_6Am+3)2=IO`FX6{i1Qw6rkfDDYv7g6YH8#!uoX_o;%xd>g~Vc0)Z)5n^2U79
z0?Z#YVD+h(e4g}{skSgVshxgPUVP>6GKWGl2*}MTTu}i92=u2PYL0dT3W7bUj(}j)
zqL||;#R_j=99J>aL}UK|)l-gRsGF@w4B8JhTH-tqNb6S9lhUKPT&_iF2VofZC<A7h
z0U^N0TDLl7Nx-U#Fv7Z2u7J^pf_bMOylM!W=27@nwophuqLojC1}_dOR~V?z3_i6h
zaf-wS5lzQ5{Pm>I6u^Z^Noq%I4wV~l{{W3Ojwyi2pZ8>DxE~nXsf@nReL?MA)Po|q
ze->Mpvt!pa?PT>iF%dDYuLgO0c0B<Zriycsz!cHezWOJQ$w12bnntBY`AGhBj4@gv
z4HWgJ55}CeNr+N%XatH(<k6a|fc*Q=PJO9>)5j;ZCdMW+O~pKlOlE*1b;;>UqMwZR
z6mgoHSU?VG$&PcHN^%iY05T09N^lB#H{nk(vW)hvV<K3^BpQ@3<Pt?gj8lX1Fe-^0
zag)s<`_$6erWQW9pe#rfWK`(GZZpkOE@?xY^`ysQ#IoSy`Bi3Yifg&WGbW&E5{_5i
zqBs<)O)2S8${UU;R+5b4H6TB>X$}oEkSGVO06ZLaqcni#kdQi62oE%$l_={$^rGVd
zNO_`@y&xAnP<iV>IqgM57>B(fJoTfHO)Ve*aoU1u2NZVnpaGbXOv%MK(rv8R#*>pr
z<x7e~QZS%;QA$9d1U%732U=1+DS;CX)X;hQ)83dm)_q1yq;Xelh!3B9@l;l=TKulG
zs;_it-+=IOR|4aK>FZP?ZU;<Oj4E54WLJlX(B33>*H=*4?19PxxKb;aD>cK3E~b)4
z9;b@xE?4(JFz0P^gb+_Pwi(_4#8unE8rag?EHXH(jw??}Y)C$CM{jECGiJ1d<utaZ
z6AE;LImb$5Ew)wq&`GF!9)0RJ8-YD)Lye;p(lMV(qy|2uxPi$$kyxwst^4)NCnKos
zSUALny=*S9IIC_us2-If{obOZ2k@yCtG)*_9tH@<BCW;9%~S{Ut1)98>v)(<k-ce+
z$fvOccfqDMN4;Am5I!?Z=nthih8v|Y^sJe*NMEVVG#|pBAj^Byf9E2zH6PcL(x!)!
z4tS`43YIPyb*e<jobyse#FW#FQpQf<?^?vhMUIA;_&w?4IHorhW@xP7=M>(&)QmI7
ztwu(8tfXraC*ql&^(2E0(xduxs5C;4K~f>+qVG~C280Z>I(Fip80YCxjFHnc^{rxK
zB4dI&R7^qSihE}RwK2yPOo)}wQ%Sq8r8&<|I#Ul^n$4S`jB-a@QgBTxe8-$qK+b9k
z7p*G(wBD5Up$U^ON|rCZjN+nDeQD{#R<SaXXz|vflO;&0daiqVR8P~Iqcm4xOe9m=
zob!rrBo39EIuR3n>N*NmrjOE~v3pdJpPHitA8LGmdmU+#%OGKC>&_{e$sBP`UJY6@
zWQV`4F!jLePjU6A-2PP9kqiCfOz0_FC9_R64ABw4C#@Z+TZ8LO9Y-{a6q=GT&#f>T
zkq!yuQWGTrd*Zb;6Sr7SzcQR3ToGA(AI7wFcG;>#NEkeRHRtAW=AhBhg#IEszXe*8
zqeHxq>UhboMN8<dEI`Hy>6+#|8>b(z10rnWD5t6SuCVFROc7)pDawlR+3F3^u4cP=
zUP$p8oGW7)HDgoNV$&51BfB>MD68m+6k${<s`^w(HNDinQj}+3n+Bi+g~afrfi~_L
z=hm||En?cs<<95y&2E_Z>0F+t;b||grE<W=!-L!pN(NuFx`R-&NuvN~IbP~%m$plF
zZ1GB<h8$+6)3mkIt;A|c_pDuEHOAE=OEty5;CFh^BAu6optNBo((XDE2NinnPq%O(
zn_(@FmbK(rVzYTV$g9%08@caq?}8><=LL55G{VP64wn_YZwe?_uy7W#mqWL;ym^^2
z=cY|+U&%eTlf6-zKtAeqtX&f4QM;07yo{m~@`Kb+BHXY?<*}FU3ZrjnXq%qgbUfmh
z#7!h9fpQd@&CmtQTst}a$ser)CDk;)wW5??-YLk<TZ>8atp3gBl>l|9b&W!8J~U*9
zaAv_HwMj0Z*7k8pf*JT2q%)z?bk)-=L?}ZJrSsmXYT9g9z_T1N^s0I;tu)g-Z<3k&
z+0H6$c6)`fb8Lm5JW@yoTHB-xwO6Ne)~(u$CA|I*I~AFx%W-jLOsTP(u{DKvHOgu@
zMR6*gG1izKp$jar^Nplq6;eG0A%3?3j=*?NN=-I-Ud>s)@LJCP+tlONMX0us;3oyK
z&{70;F{*?M+MpIzM)%ALqHJ~VPV<;R8Ae+jD~q_)ZvNWxDJbbC(4n)<AV+>cU{!`e
z>J4Yx=(hH^W^}>H`@3qztgP0^@At9VvBsyVw!UqQKe#;Z$7%+2EZY#VI0C9!>NeLG
zjc%@@LE4>uuJ&#dIUL|uDWKWSCaf+o@~>7sbDn4eufDrWD@UGR^=sC+t$S65`%m*A
zCu!r4TJG*`qPw?}IhS;74r|VQQ4AInBrp&Vo}Tp+*tl+BZf0JX=klvIQZg`J-_ENm
zf~V4<8j@STJ-Z6vl07(^<YW&@Y{`YkN~)LXDyv4ogU>Z+v5_|pm77JF+Ktqjbdg*_
zaq|F8bh>T)ch<s4*f2ePs~YCrWkVc;Bi^v1x|hScrURCN`l+t0JzHqVt%p@(rstuC
z$7-p6^F!&yI@antyLFN#$Ud}8p`$<6yPl_yD7d>boOQz!+Kh~Kt2Yr9$Reu(Gg(Nq
zMJ^a^#sz0x!}9hdR->*#HBG=E)D&Zh*&7FpQ>Jy5Gn{cwyo;Q!c&Z!O7#`gzf!TOM
zAG1PoPG6sD>|`6GIIdSrA}d&19eU!rn`ZMOUWEEkz|UvP5t>K2jwHt6xYQb@yy^3&
z9M%MvQ==WqanB~C3AIa$nTPI|^Y2(>%(8sIh85H4*YMm&v54c>tz4H*x0yl42el?M
zo3y?ug??*5>~-95Ml(}Qq(FeU#~!s#Pn7H&tw~2es@nj;)p{P)9-DIUx08+=j1yY-
ziX3gMW`oL~a-3~B;(#}x{o3cD^{N+-ynMfpy-d?Fi{<J?XR&?lBc2pzngFS)UW*$8
z&K<%2Rn2JD!ds?hk1Nyyb5d*f#^{)VCl7#YTf?v`ebL(jy0Fo^IqS;NH>_g6l~o}^
z5my=8S|SZi9YIamsdUqJk#8|J)f;vS=`5|IQYB^#*zaDN*z#qoIN2_q+DA*Y*fYjf
zvhQqcC4|h546+bF2e08?jdNvha1QiVBzLY~QSg)`q>wk4gV1)RD>Y)FCl_;@({#kP
zoH=ihkJh#)w-Tm7%T_(iSDJm%h=yhCaauN4Qn)`MC3}0<mx-s!^gY}qUU;1TqF&Zr
z*k;M(iX)KA9_*5*rEk5XOjykk+v`|!Ml5D{+mVt*a-DZ6Pi^K*hbNZ@k6QIDI?ctD
zEf^nn@UJd=v@WD6I3d3yUa6wq`TBG_Saik#uBdz`4PS`Xg{6%MY!i+!E5`mJAR5Nz
z810eoUd*}3uO0Y~!|lKfZuO*$nZU3#+*6M<+}4DKDZt=xX`oYy$E5+WD4pY61DZp3
zCu53$oYR$QSgvMHmr{o7`Ox!8Ao-8sQGhW^iYy$=Z7}`<q$7%H9CW8)5fD320e4j%
zwCsIq=9dqfe!G|DUU{VS8b_gca{2765fKUFjMdFz`L3bevu#$lWLVdp1wQTk$VgvG
z!up!n!I1pb14u`qsU|pLDyx&9Z(6cL%~RL6N@Hy&Ak<EBO+wjRkwA%DU>b<Yj8ja6
z40BCl2=|}|nFS{Yo@z5lO9P4kkaoxCno!3z2$vm2JWMl_KohHEW7eUS%Krcl=}N8v
z>rzRwMdO+TK&Nmt6=T!#G}I+eJ*r=|ZR=gM?9qglq%5YSj$fC{k$N5)o&BK~_bOD>
z?FhrJKDDKyPNQB2RSY>_QB~bT95*$5PipJ?sTEJ5H5o9;{7P}@P~%`oq4sUZ<<HPl
z8q!q<gNnH76#T3zKQM#WH6tmomNUyRAMa9|sldUJvGuEsi4HNy_NK{ZU4L|hnp%NO
z-9C9@X-&%!#XYq7f#nGHrkf{R<l>d2R)Q>~XC|6nm+Z~gbsuJGR$+0u28`01cJ!cI
zw`wfH;sZ;&-jrK8rkGrJqRccM)|f~X6=Ca9wsXxUG%oy_3shp9PZc8`r_l7LQwOCu
z57vMRQ^f#Lk4|Zb0OFJ0m+49d4FEI_X?oMKkxe6>C;<ScE_YB5tvP;_&=wP%Rr^_E
zjO~!)zD-oOOaM<(YEnikSQ1{EWC`+CV<;ygr}ID*f-vCYuWHV-xxE#sRu)+Apm#V_
zaK^UvzYsOux<PIam;70*Qh{c{<kqdmnvz<1h`9N899A)^;H+%v^J-#8jy-E@MYwdj
zUT^{GD;MsZcdNR5#w&zA{0ho?qiQm=ta^w+CZ5|5&9kqicE1YSZj~w#f{eh|3#CjY
zu)seyIVQVrhD5A)vFGl{X<^o-<31F2J|saehwc>T8%=!ec(|2^Ko1r4Ubr{tcR1(e
zJXg;5{7Tsea3mV+dmdvWvN*UEv4dE4pYif5bOXStTawOG#EMPAo@)T`K_k6%o+cRC
zisqXode@^%;2`v^8W1$t`Nl^|y!uy}YR|l==s>Lf8bT}~X3tJ*qLx^Vn*=>YdG+W*
zqxX)wIEm8ICR}!l4Y*Oz3dp#(i6;-RZXD*feAvSB-1=5k*cmJ;;}n-FJ97EnzrECb
z+4CTdML&&66y9tq<Y4Wp@V@(2L)28Z>x*Pl#?gw}p6A)&(!VH|ExIBHQ{J;3NUay=
zJ*u386{OCo(m@x_n|&(_T#p1drENm^kmrsoBU?L^@zVmKGsMi}`<Wd4pLU_nIH{kN
zs7U8E6{6n9$3j*dAHPa#Hbo|VX)Bb`%Hu)7;-rpEr#_V#&#gD9G+djT`W*Y6fc37B
zWDJ0FT&95Q6y=}SwRATcv@kC_j(Ff!b57$-xE0uRsEjUq56-fNyA-5_ETDgStKDmi
zszNwE)t@UF(M7#S4T`%Agz)c!^sWVU>$T(+BvX%w?#as#DCA*tzjXth{`sRL9JsCx
zyiasM8OZmklf)Mcx$_2b(DbFq$8)ch!3XDBry<DdE17+I>-({RSL|<%$R&u#9jc=i
ziIX<0oA<cwU2ThE6n^W@YmT!7N)2`PE4tGivD%8i37XvQ;yHmi>Y(PKzFpQ*^U+D7
z!S~rA=hCE@ZiT?^q*vz^*Cr|Yp2T&D<M)b8(wuR;)c_e~91gXwseu*z@!*e`n#y7G
z_3vM!VcqGbc@;F1I}IU$k`kltk<EG>M|5g^tIYI?HUL4-O7xpkx&$EhubbjXd$Ez%
zgnOcA8H|rw@Q)S2<m<DjKY5Ag(>*KR6l7x+;{H5~%hw4b<!q1VSHaaSiIjVb9~;v+
z`F`$d5P7NP<tn{?rnWpmPf7>S{b^4)rjEUORRD4YAFU~*??4DgG~j+(Y3oj3&XCC=
zZITD)gI_~<eqTF9wsFv<eC(v|1P)Z@z2CtTdEOm>f=DVbO?+P%)4mZ)%=B{i?=*Dj
z%{+9d)byzb75Pg&ai)XPgGXvWB7j^Edh?$XN9F46w~gIv(Uf6@a9%P(w~@)8uf2PD
zJN@H{omHWgVBfsOYuhjmRMr-sIvd1XgS(2_LAK!Miu#NjaI0o<R@NhKa<gNOl~slf
zT(}3!HBM3a*W2Np=^hPrYJv`(C>?1B1JaxZKN`^z#B83GC6jq~h{uj_Y9cY-mNT|h
zKH{^kuLg}NJ4oKTUNhU)urF7su7+?L5Jh3$0l+o#jajqUxq)!GB=iEQ$S`XCz%@=l
zPu74cO1WS0u730ZDLBS!qHsv8O-V5zJpuKuyfgRgXHd#vO~p)CnujBr^cjfd{3+>?
zBA&RYR#?kpaQtdTkT)ro=b%$k#*UuNOF+2E6#JPXF__r!Mmp6iS?>*|$ZYN#+$BWX
zeybt*bouk!HOb3T=E>8swc$%M0!sM8mg1uEtlKP>F3rY&I^WRjE+Di0>Im5Lw3^EC
zE`xcgNESPbWkK1GHL}>pspiL%TK*l2ecQGN1HEb|f#q%_)UDL|0h3!ASB7mg^=~%u
zr6-@2aZ=T{F3p%)+Yta8xF@A@<Y1cgo4o@_xnR@1!vWB40;{iwd_5m5jz{}anoY;K
zYMh?P^X`Vb-3``VJ|+$b@9HYT+IW5+^>+5ekM9k}uE(ufTOde$r311jYM*HoQp41J
z38Rm2`@fZ5hT2Ap9$bg$D=~aTC2}Jy2eRU;$>J#kkgqQti&VPNG>#6d=wSGVLDa4_
z4e(jHUU{t4@Sd#vyh$JX?klE~#1j*cnLq74LfYi-)gvE;Pq&X_b(Yp<GI%=lu-|cN
zzemsXtM=Xuk}?`g^#jooq-|d4{{Rw?qSR+mxngrG{uI8jx+7JURDDZ};VU3PlIH2Z
z-QulB;hhnG)_tI#_N2vPwdBp#M<e~}jiz?$<o!)g)>*7_d39$<G=C1lNfxM2tIL{x
zG$@D*Z(==)<ku)kC$4EewLe*rvdQ7qooj0PWEt4D{{Zj^sjcE0Fg{Sj=%80Clj}x(
z>Ruvj+BsDvxzV?X&>xmLkNgi65%D8q<b{d<0B%gy2*IEXRC`&zri(40x*HAR3x*s;
z68^OdYd6I4BxC56o6?Syy`;OE#{)rqlH{7L^Yyu5>;@_(zPW$BJD>O!SIPCI?^Ddp
zRvwbs4tXST^GNJH3sX7+=}#bItww0Me$ES^xu9{}^GGP5e5hRUNktv=NOl&qbZJC-
ztSsjpc{Q7gniKo@^T6CHqU_A-#_(wM=%$Zi?P1cbM<^e_Ptvlq+jVP1X5^8Y)rCTR
zJ6Ec<J}RQLng(*reo`nKg-HDL9Mef1DUcv1(t>eI+K?RcKmatMyMIanqZ9z7@#&gF
zz@#TMxy~s7y(tgB6bzG2Jb^&O1dfK6ITXM#)|>?ZDKwelf-y*Q=|B!2jVM0<0G&e4
zM@1ymZ8U?AFCSAt7IVchv5e-R^Jnd|@uobNEx;%}IHUyo!1dyj%nW|%#Z@-fvi|_f
zWL)<Gv!>9m<dC23A~V<mC<AcK8WFja6Y6RSZs1UJDreI*fj5P&q&aKnY<4E7$>B@q
zmvFc{e!u;CEC)n&D`Cd<C;jRMp$}0sVz3j!7X?DS)A8AOss8}s58TU(iBlepMVK3d
zQ?(0|az6@*bz2nqe$Yw!)f-<2+eG3?W|Be<c{RHZpJNXZ+pipF6vRgkrDn^8EPX~Q
z!rexGV3KYB0CuHVqfz$<<x;87@K6Ouz5^Rzl>6eKyt#8?__uCX)1_z<K>M`GgBy3i
z87g?Gn!HUZJ54jlbp;D~Fk#N_l~asyTDsf|4x=y~+c~Vit$EVi`wCHRDcoiTdQuQS
zyHCv_H73d<57L9vr7lSwX$j_##L3MB01!d%zS4~5mte<wEIXl?paLnxV9-jAq)}kz
zLUyK_d1c$2=92>)0!Of>qRIA%L7Gn0I$B)0!a*Vb0D#nsrRp+$%Q;WfVyoH9u@1F0
zyD9P3lxDP}@cykK09mm2BvqC0rmV~JMvL#7e#%{p-Y$~+Mj7c#is+NUm+n4mm{O)+
z1-hS~QH&3zKVu^|kD$7o)M|ykeB;`mAYQ4EzV*@n0KzM#!~VZlUw@kvzu6uejemKl
z`JYFs_6*JDRFTUZQ+F?R0=h{X!PdtOBRTZR%|>;<3PFP%tgnyuYLyF_ywaazpWeUT
z6mA4%Lmu1;-+vnD(PTrWGksK4N8$`fF&37f`{J}%R$(mGJrG&=XH&ekHwG~hb`904
znbI{a?x|%X;jxe^+4zyDGL??jAUgsol)gOH82o}1`U=zPjr1`7)tV-c!`j51ESP;*
zRh00auO<P77d`V>&*Keo)aK|9pv6^x5bE#2zm$CqHG?JQ)97_$!Pmh2*HEQActDJq
zbvRS<t}0DN{#+Nloxk8_pfb+q=bA?Pn!l<eIc9ZVQ@sBGglkQWN1d!jPqP6`{>$+6
zAL}(D$NiSB6t3=DpRF#?6M!lGSsA>2SJdt!pTahi34YSgAUu4;*1GunMTJ5km4c2i
zE6YewItp;%cohAL?sL?yDxVSQa(qhDRD71wu=f>OZ;8kU$*1G};a-27ic`oV6x}4z
zpE2qd{w=$@gh?7(s9~O&r?$U-RDmcN{_5hmy$<937h&p$7_GE?o@>LcI+2r2osfiD
zxuGVpsS~&DZI7iybu0GHZsf<-p=@>h>N8k-Nj{~hq$6BhyJ6>Y4}8>tvb^N|YB0Rj
zsNl#M=i0NCLaauQfsWMRyq>jV$xXc~5}SXB)?D{0!-MgGPE(J1gE%><6y*1$1c7&S
z6?)x%QO6>p({R%;VV|vCG3|T`#-&F6(u&uLOiVC29czZWw*LT2m))`jdIiFKzT0b&
zzKDIXk4^_l^)ks_G;`uMGL{jHVz21gituz4<%khZwFNI!f!e(sL~l)_nh)MPtv&e0
zep6F3WSmtUIP8}M^&RTmhYWjjUm;R9lRY)C@N?3XjH?f7iBBAKsgUG>-lt)hQ!Zt2
zJ5@&D){VmA;ehYjv*llygI$nhGfo!*-#vh>J7oRPZ1L+@w(YtcS3{@bT{qclI+YwD
z>IhZo)}^(40uE}b$&pgqzwh?;Jl6!aG%V*71E2oAG@qJ*lg(xVxytcU#@UCjN{F1T
zKHTm@p2rjbpp5Wp&8z1ksgi0~Uu*ZNk`Ze4KXe$@Y>LJftx3OmYH{gQ6mE%!@~VV{
zWW$A+0b2XMW&X92ep$WqT0@0KB#P-`HINXhY2;O9n26B(RLc3TN{Z4bbO#PaJ<dI9
zBw(_idRJ_*tn31VgVvGGSFJaH98(<b;;8{5Kg)qpGv<;mr!*DjivZ*#eQB2yfZ;pQ
zk~&lq5#|i_s)Sn*`O`7yrDtu&(zSm4S?!9>Jm(&@bl!kHGnG9m(>DUDDHzWcDe0co
zqtyW`Hb-8SChW(WgE?Aqwouk-0K2)PJbLD%Cz?=cun7-6d7!REHG!vR<)j2mzb#<+
zf-xnV^f(pJH??N!Q3te;5&Su?LjhBkv{^G(M~X@|%IJTEh~}6&Rjc@Xi|LT?#O|ut
zuhJmyj}l7EdeWYAO#l<^P9qheBw*6|Pyhy$o_f%j37<+k(Lmr;fDTWsJ$R;c#wp5i
zKo1xm)U?plpyQ=57pdl$#AcM5Ve3hN?2k%N-RYoYW{gk-fxeWi<%izQFduq8w8ddT
z=8ebRlOB|S;;P|c%rWcDHzyRN=9=7|^zIfA(~|?#(+^4%;+4Qw7&Mfm=R8tl0~w$N
zQ_gWg#yO`%k0XRZlS@1=1BG#e){|gIN(N3xN(WkeeDT(#1lxg{WlG#|IH+<>ARG_j
zNP5vh=}ZGO5sEX-8K48D1b59HD4+u%3PaO_ONu^}n8e0u4@!19q$38PV^@Z$Rd;=A
zJo8c^=9q*j#WXK9J~Ai^_|V~SxeF-Ar8LB9$xPB?1FcUWT&=ehZKseypmn2^cOxU3
zL+MfwJ!zkyp`as>RAV(OoQzams|UG5#aMx{Agbxfsp8;{nf0Q2#0~p%xly><MQXx7
zck=yfBHM_Ddseh$1>pAWUM3+MMUvb`THN%`ILWS7;B2@m0ULUcdg}AOC(k@)xt&3F
z-4cI`=EtQh8~Y_Prsg=sUeZn{8STlcE7GpmAK#9(=oz!6Wx&RBP!1(uP-@D6(Pd71
z)n-4u@797%QS&Gy(^zD2(v~xrhdHG@Q$ce!@D_=|C#M({fI$zBO6jK?)wAhb<jaYO
z=hnSUAHs518UfGJoSdI(Po+6eHRwd-W5rpA1J@N?atXyx3Hhsd8BCb|AB{BA*x>WY
zrjc41qO<+u+MAs8r?{pbxaSp{HbhbmIjHbDV~UbaooXK9vu22Y6!`vA^`-;OIZr((
zh%(M;@%`-k_oidz&mdEm?+$BZV<Oi<O<(}^r)LANT0_9%sK~DUI({`6IODxbCjz1O
z?NH4S#^$5Q$JV5Nl@Z|Lvu3DXF;5>WVB_$p#&SI=P>@G7kTT+)I#ZM7IPFY~@%0qo
z4(iq>Ot5f4=AwQV@Toz}eR-(d<onf`qPugRb4(pEPkx7rXgD0!ayCS7gG}ft?T~Ry
z>FrsT6!qg2(a9o|aqCP)l*T<N>OOB=)N%4MY3gx~O=%N37Dq~BQ-R9#roK;3YRr*Y
z_|FvIdXdI?rgOz)&WMn|Ii%}PkPOsd;PPrq9s$Q%dJmX%rVNi-a`1g9LS=<G98=Tp
zaZFAWb5bu}YSEJ(bNEzjK3bO^ywq)+9@Ru5yHjb;!KQU@N``2Lu;UcKGn$cy6w^}6
z3}jQ&ftqRLdsCMnPz8lMzLjdg<50K9Uoms^s;PiFd;T>wxhr`K4x7O>$&HUSDH~zk
zrjMbtt9;EFPq`SyXr-;g>K=2;`=$G+JJSusI(?XYU}CLl*Pm>*^LCZ_vGuP3p0$Q*
zkj~bafMt(rt)uA=XhgEU=c{e2Ks6C&GGxVHW>iAQfl@NAr7gr3toG3PvUXh5b`Nnq
zvc1egIXkU1>sH@sSa)^r*j9)G9C1Jym-n&RFFdvjRV^=5T}7l#g-GOj5n39Sn3t*p
zKEe-C>FG&rX$6#fAxwIjE(2#|jx)J}k9x+6%H9`gp@~6eB;uym^r`h|5n-6egYyq+
zn!`;tmT|)DUueN5fHCzO=xr0{VT0SfNvEtg5UkMQk-Lvt%GdPS-uGhVi=3#&YimK%
zB(bvzA;CQC{_QaZ?wxOY0>wDU&m7}5U2I{uk7Q^79jcbOr|R<RP_?`5w+APjR;Y?b
zgbe=kZ*xExw@+;x!DQM_anG$J`gB*31S1LCn&)q0yPo;u*u{hV+~&F>v&Cek0m`pT
z&;*tmWL7b-UAw(ji_4_9jf;*w2YRcazM(2RUmzbh9<>jM;FQ804k8EVIq5*lc9$^S
zD0p$rINCua$C${W{cAJBmb1kJNa#lMkiXWGP_xvIs|(w?Sab6aN&xF1J7ep|wJPd%
zpK3@QfPTb^fjq~yD4d<6uUg}zg5|ILyps7U%6P!_qzLr%IUc#HZKGP7<9D!cZb<A;
ztu2q3mXU{SxKKT-7D+X)_(&BOi%j+Qqz73Vg+MwAfa(_CYZm3ln0iyB-1g)r54WXq
z31M|}t0==OhRJVXK+ffP{{VE;Vix9BNZEHO<O-TNw!*8=O3${^Qp);Ul#$zi@RQPj
zENZtuWYXrBIKZzU)TOz)S!bM_hByc7#d@}?i+5($@(sx$<Yu^ia>XLDlNk9%J-XDf
ztr^0;q+{cg+wrVR?MVsy$IJw+Yh2lGVicSP{cD@oBKt4STlk0TT#agaN!c9+fv9=0
zruNG9&$V{8`i-!)*jR4#uPxJV8|?o8DfvTHld4M*#_}*a)Ji3(9qr}(cIPJ;Bdv4V
z(ob`3=SHkTo~zoqtDR<h+$P+B03+7B%@O0d(abYo5;6Kx<*~gv+1$qP=ZG4{;b57G
zM(dNFYtW&YE+JP|>*-!Us6qBkLRgit&f$*L(D-k}Z3$azhQgEAJ!__wUW{1WAGD9O
zf!oZ1)Yeqclx_uV#OU~CJAoBe?%zC*O3|JztYwpx#%iR?g*?@kIQFX39IvfN8Pju|
z)iZ8okx(93_N!M12BguW6Y7Kgo@tEf?c?(8(KC{xt!miaZEPM1s*ZzZY7qD|*d05n
zTqxYRth>z-Wnyvio+<Ws2XEfZSh&>Vwp_a}(3*fb_Ru7Z<YSLRPLgA%!?s4l4%w+L
zyiaa&k(4LevY7q7-M44!NM&2yW#!7L;Pu5p1@U*o91nW2E|SUy&<~|jpHG@TRA<)}
zBQIT9ypZ{kI3$Y0a6=q}$6DCa?k*x_h2nCjjGDhajjXYj#@5eKK<;5i{$wGP)^@9N
z<yyJ{mfKTbPY#}16>-NvJ6AJ(e)FjX@(y<q=~Sa}He|;X_jhW6vxApr>0X1OS;K9#
zd4TQcD~Hll&8j4MWmC>YdXAgn=vq9?$1FO7UWOh$Pd^hQrm%Y>8O+h(k6NAD*nzTT
zRLRNBW<jD@sQKe1agM!ez|w7|P4OM$I3qm`bsR>VUt^9R^`MZs&T52LHq%^~eAO;`
zdQ#l!i58u;0Wy`^cAjfISlgnj5>$^$1#r~t5>_nWWkJCe&NK~ea;I)1ZvOejbW>^a
zNg}jTxK6`4%~5L`mA*j#05pAgtm;8dHaaL)lqI31aAA)|Z<R!wazL*yy)AV+0NKIo
zUVttZdF~+OWq7U;;W6LNoy%7ruva}5h-EmecT54t(!0G16BVEe-zhc6E9{#%&O29a
zqkQ(ukGtzmQBjSNKGDtUZ9y3%e9esd*OvT4g_8C%53dHjUJjqqyyN0TKoxc5<Q!Hj
zakI?GqZp+=^xW2jh)yWMJ$h1wr-AK22o|0f6mgmf>?i=nDCUl|gnkqZ4L2OqyL!?S
zKn%y}TfQ5KJmz-*p17<sYqRkB#SNB7$;VuEtmgDIf;EF9ebM<)>;UGZY2pC<pOr%-
zs>2w?VrXRCj&s}Ismc86{m}WbR2(11wMI;?%be6_j+HSWH$3}PY%*vO9x^FBzA5J*
z4Dm_3CV&~Rk5VZ-vMJ&7OTnOIB{NJZj`cG}Tct+PoP8(}A0v@Rm`CwqhFlJFQ7|Hy
z5{WlAG}#n>6<oOnr47ABZ3!93LlT-{L<ioSK{T5=t0Wg-?^a@-73!I)>mE%zXSFoM
zUrWnA3qm&vb6(rB{E<}@hn$neTZ$ATpTiYGB^Suc^25{Cg}ReD3xInHPc1>GsZrPp
zq#<9-d}QLHXiI(LRu)f}6x{PvNdULo-!%UKD<|nsCyz>RnYX8U1_l+T`AhhUkVr6c
zMMh=KI|||Df;v=kLDSNt5)(*6H$lY~3zc3RcB<0Caaubwl4>SQ=Zt2eP`OE&Bo#D-
z<n^g1U9MK570&cEL&2vdMh*=<c@%(sDB#j^XvHxKI*L$u>qsfUa7{1(a%l+WkLOAU
zGzEY!N}4q16vP!Wjib<$h5FS2t)y7B+`OmAqa>QrmrRA*<z2r@=`<Z2TIed}KY1t2
z#;Z>b$2@ab(y#3=%4p$j&Td^6Gq?@Mj^?S0V{0zfKPl{Mrg)13RPJqj$o^6DFRf`M
zbX7TWyPVD3L(T<yclQ<5L29=aDyRY6wa-m&GP^s*!B?s6SM;q@$wiIH>%p!{iKC`6
zOv}}D-|YL(yYka5;|($qT6*2eUq}x^y~ldXg^EnL%|3+Fm%et|Y^@!bDsh9&dKbe9
z!_9VHMBdHPyu(kNeVF#i=xez6c*FZba85F6s4Fu}T&|KmS5yJCslj!@Q_{Y9)P^pm
z9eF(~+^_eYK7Fo!?Rb8uyDugg=*GI9$DC8O;^`}V@Nr!91TD;G-<s%Iaw-9w=ZS`5
z4u3l32+G%A;z<7h(O0%>k?&rH9o`0KPo#L2V73t4DEW8<3e*1IhD<1sD*Kw@2&Np5
z;yI-%DYBD0v#LTz5~=)Y7f_C4ut*6t!>gW|{0&*Mn5FD{k9x{fZL!&dtIJj=YYdxY
z{*|o)hl#t^ew(MwsWbhb1g~o7wCyrz$Cq;GjNNhClwGwx&+9blyS8F9G5~Od^Hk?T
zgDuC_y&^9U=-x`S_iRWUk23<R&1K<>bvz?|PH2@#vMOhER>ztwiMV{=?%-7odKO4k
z#tM^Oi+etY<*<S%hqwc+aNZ=A6KDIp9QO99jFV@Njm+a(n~YJ&w@zvk%})L54D($_
z&Ndj$47n5nDc`|SDsf{{A}dL^8O1#FR&>(<)Fb;-VjiZW*hGBCPvK1&Ay2p5aKwC|
z^r~JY)l&B0+M<Zi9;?>2JV~hAL#4(nrc%It)bCs%JKQ^#=c(^lHGPM2Zy+z-a%!Wt
zGm6_UV9<ev$n@)3(#IJ&L5_M<x@<X$=$n+0)Knx9*0e374KCkN(y3e~$(?=cDJwe^
znGmHEnV=k0jF3pcV>O|p%4592ISu?ZnkwF%^4`X11G%;0YV0(lx-S0!O5?5mSpnj@
z?H4BllUP=M=+@_Hr5xBO^d_ww?QC*-)h#ix6EC^quAJBB*@l>=&sLwpd3T6mE2~M4
zH)Q^`gvwRDYpU@~B{gm25D2bnSlF@0KGpZQ33E`3Ji5x$X4aFD2;&@ArfJQ(#xtL4
z^KBUkhyXq7(DZiAk6iO!XAnmCdz)c?BSlUKuPOMC0bNBHovV)B>(!Lug?Y!sxN{QA
zjD>IMUQY{D<i@0Ji&v!2FOb!9jGs!gBI7*rYPsP1*X%La@B^ZNI5cz|P!ANG{c3=7
z9(r+29cj!n^Lo>00i<^{<@>aUr7Db47~#S6_pfO9Yd@Xg@W0(8bM>znTodhHsqm_O
z*0V*DK5YKA^L$NDp93Se1np4th4iThJk(3a6(`_p@y8R}5rqSqQVH!!vAH}Ury5gx
zAh{VF=D3fDaS?3{%e&?4j^ewvh5PLvjdOl5vU|G~NX%vXWw;gXWb|so6B$Z67}kE{
zJhw}lNc9-ls}Y|{?WF$zTBqKzQ%aIH1+J~rY3NODJ6aT1`*e9<yhl9O*;Jy{Sk5O5
zXLvNlxCeOjs<N&s#Mib5<@01>I^b1zytBv4Z*t??74PAz#xS!y%G6xtbVdNpDz55q
zx>7z%IWyZPoNg}m{_f2`;6k-{sG>fvA|gJA6y2qW+Jv8_SXb1XAM|LK+$}wA^*Kfw
zc+=>$62&IAE;Jf@n(?HMXrCuFn{#D5=j6cp(^pK?3jErHfO;(lMt3=u?q@!kuOd_w
zrE|4P$jX~cnTgB9nDuI_CXfNkU)!Mk>!JR|w<qT;!`_3X+QxZ8d(%`9bDY=qOa=MA
z4m}Yny~l^NxySEhxs#sUS6(cw_i&XUwYN|*oK}&CE4n4SoI-e8Lj#*ThyMV1@m5pA
zmMAfAr3VA1=FN4B9lqi`vB!FqSrK-R(zWJqsX838X$Y7JV{0F_%+;0C<s1Zseu-P-
z%Z!tO&w8&l%9qAEQo9+LEo2{g*dIly7SkgJNeKS{dZv<n*y9+aSq^&A0x@T7rzAN(
z?M--Xfxui;j^8#vN`^>_^VHA-lFr$f5<e>Dd_ft4=WH@EsU3}VmbPf?`_~|j)zA2{
z(IP7%WP!zJSK&JFTGg@2yS^}8kJQsR^v~9wMk$0>p4s%&=-5zk(vxwf_suCdG#WZ(
zi+MzH0^JW<j&=_*DmbS`$YbSxZ>>hh(t;yTTZ|(Vl)0qIskyp<xiq<?6sD1-hS8c_
zW|JP20F+YW0+Y1^0m-6(DM;dw2n{VI7@z`*D8(@ctrUKAbfg02ntIapG<T*UD5IJv
z00N9sgT(`y06Suyr)vV=cALcqrxehovFkcJ8Ej*0^Z{#K7vBcC-wRA+(vWAG-&4r1
zQk%R_io{2jtdS{Ep0vyltp)k@qz%nkfcy$DJ*fet&*eZ4IQFAFbfhB`XEXqez;VSP
zIG~Ku1Bw7#nrE2j_)aQ7xu*pKy&;v@&HN#M8Z&Tvr{z;S1s!TLa|q7o0E#XJa~<n9
z`sGpR7M!;CBbK^j_*0GaAmLcI(w>v7qkwRIXacmh(nxY{B>D<L0q9+i<5vo0GAcah
zv7iR5VR)yg1Em-wa4CjRpISgp4mqa=$*Spb6MgAXezhpLwo*TO57LW)AX42qqsc$r
zG#ynTOe$o0?WkK+GXDU}H$O@)1ff4VQI3^c?M}qv2mER`dGVYm{AqIqi}@WWEHRqN
zYpKD>o)jI)s3pIGGnsV=#(&$T&WFm)uQ&>NN{793XI9d~eENzUb_Sw<5$K7P`%^YJ
z;L>#v`A(8ssG{oJ)B{k3!wmC^<)-nLg94oSkGHmKK3|BMTzL>#NPh}<Z=fv-{vnCx
z)C=3j(kbjKC~4Qv!rHmwv|r*n<M(=ZKI4k1Kg28j-@3Jg4|S~muYQNC48~B3NEblW
zAD^=jJ=&~C;Z0gmpCMQ3)tM)cb%*<l5@*nKs<L>)U2(<HQ~u30hVm25DjgztGf?X!
zsGo&9{t*cjo%fM}>s)-EAl4>Q9{yqUYN+@3vVW|*nStzDtznFwV^#G#_3)*VsPpwC
zUtgOUryUc+kg)T0A(j6CrnToA+_vVG$@gkuMJJJ;tv{=oymeR9^mb1OTc4WbG5-L2
ztuggq2-~;%oyXU0dC*i1ouZ^H4^BRUnxp1J#ngRH_55Ao%YXG&On!<gCh_fpkS+AQ
z`;Y~2r2aH#j-QoUqZ2=GH`MLh;uQJBRuL#4-W5(?h#IrD5*QGDIj&PYb>fUwsxTqc
zXGH!t)+AGhL_XC<UlQw5@Yl`<`!$!0@kT0@IIe>Bk}sWGQIqf9%t!mx3tikfCGKT!
zt5t7m4>b8vJj`=5Gi1Ay?$q6*80X)bJ5m~UL2(EGV*?Zb2TneeHwKp+3Xr(8ooFL8
zqpeVd0OyKRK;oAMs6%_wid<2O013?$rB2-Treul$c6-yam8ikVr}MPZV?zn;LXs&l
zidCo>>QT=WgXu~*G+0ILE^j9IE`C-$y=$t8gA9*a;nj?CEB6Mv?LKcd1S6pp;^XPs
zT*qYzX=6|vfGNQ<NUP8qlOHX4Eu8}lXUrQ#TS0}UAm*gtcC6(ql!R`+)f|b1<Gn}*
zd7;-SQkcq)C_{r%NgvCaU_+c@tuQX>&$j1`XB`b_Jd5US$T+Nc0ZFphsoqVp0&6+a
zzq}VO%5uG{n$(jMtB(9)w;DoY<kmi-0RWDf?_JqrwCrPu)+HofX@2aZ9eruh@k;B7
z0me>i+^DY>jwroOlFmWqAm|CL8Ar@bWZ9j@KTa!Q*P*YE#4cI1da!qi7~-r&_k~0k
z@u{QXg>yDhopzYITF<;spQm26wS1VCGmf>Le;xqG0Q9b!QX!GpkCDE$y`wn$BPl%z
z&0*OOoxA&1o}Qabskq^ZG*yQ(unLXWJo8gP+b16N2wXAx)7P04^IWruW%Ku`MHr_K
z^NQyILgZ3gefA#o@Cl~I3eCj;3_fE{UJo?)8(7k9piH$J<^z+?Dy_2ak(bcau?(pl
zsyI&DmK@VbSVl#{`F95&-sd%<xoAczuA;kV9`!U0y56^1pe(aC#OqIvQb5V3l02R{
zBBG6|Dn|N(E${u{sa*WP`qe^yW&U+woQ&2j6ew;e4augCv{ZmAZF+m~$C{5AZ1YZ&
z?`D_=dsSPMFDyhH0i4yGdWx-kxJIQrS4JIPRuLk%$&B$-q-;n=c%)g}5ra|4Pnnb6
zmm^NVT8(~QYE0rfhBm+zAURs03a#?ctTy+isqODbr{>4=tkB2jsHI*hItnv`Ob3z0
z3-?Vos?tW?YHR|N#}!iLH^k$dZ8d1|P{=-0*0!MeW|*1dJ|Kt5)uzek)7t{GYoqa$
z20cU)IBo$Q@m$*;I#=m<S@Tj%@#?Ehk5kPrdSK3J<Y0YksKktt4K8y{f4xdNQUSzd
zQc{8P^GG@MssIPplu}Wg3Sc`tb*BTGjP<1*X@LAw8?Rb-2bxA06o3KB(|UEFcjpvP
z0)i>P5-FXyr;1<(gG=pA&JQG05VY2%<kApm0Wr-3826xzU{E<cVweg*#UMBoq;u^_
zgW7;DY4QZPVt>2VjYYTIj(>+d)p#3h$_e1r>+5w$k;f;cM^H0K!KbHDO~wxt<>)8@
z&yJ(5MbF_<F$G0NaX<%CONu~q(v<MD0G)dALF4H~7~+@+GfPN6N?z2i0os%wY|>_o
z_2z<u1e{dTTFDxDgnYFL{VDG&x`p!?sO?a|jP<80;0j}Ppc)eb%CJ1sj|QtN5Nc5<
zJabxHk;L)Vnt7nI<GnP!00l`H%{7KS#V-8PG3TXA7|!(4X~(TGk2MTq8kj{q@@csD
ztRzwudQ^%=az_;q9Mp%}pFlV5IgDebI-d2VZrhOJv8<%bU>x9d6|HR8IPKoNj7&{p
zT@D8ao-tTDv}Gk?InNcjoS)@b+R5N^&$V;m^qFlLS-|3~S;>o}9`#JIAYfGXU-9)9
zJh3(Ckj}m^&j?~iBeg>yA;+d_dvlvq`gW!`!RbZFF2FMo=j&2q6$P_=n`&(B`c)wi
zOuR52mCoG!vuy&pDOHM{rm$}m3Ap;#r-OYCYWo#w$;qVa>q<DUNgQO^0D4rh9%>Lz
zrAraZd)Bbr&SjkEgG^&j;{urD2dCv)86qhTO+}iK&JS9TtwS|LQgiQ74AjzesC)2h
zHfn|ZDaqEF0H+}%)2#>@WCM)T(>tlFgN|q%9xGUxNVqu^)*N*dh(_8{0Y6H!5-B}#
zlTiJ5sh=3fPkM(n5;Q|tV0~%>%N+Vt@5tt$Bc2Ur%}@?$z>;Z$uO^gm!`6`5YCK||
zIW-)7U{l8pTExahg&!_yt=62JB{B2wR%VD?bJnBB)}(&<rgyC5YKFHf?@<whQ$O9$
zH4ZuAvt^6kmmMjc$69uNY5=f<jw(guijF_K>r$u#6{<6lI**o`*#exWJ-DHde${4c
za<ltWGmK)SmySh6?TXEt#AAb;_oil~b>pTfho?20C_7V>;L}Gd=}M=bdeDT+Dliu`
z@z$7!pw0zIyqeV+vP>PHhe~6NkLgkmyHT;p>560!$a2*cOCaW>zyx<S2B=}drh}83
ze_Ci6J!)A(^yZWwYDN61z#g=Knm$+XsiOI0LOO#{MmX!mNTi1zxvcA}!Iw?iN79pN
zi*+0-&UPnJp0%qKX$)B4DvWViR@WDgsq8Ug*e73BskL^TT7KjbTa1p?^Cz-iiYOja
zDkAS36W*tmFES#PiJ)3tM5b$oY`0@tI+fMMt+xAkeCN;I6ozKO;oz4dXJW*5t;4w^
z!u1_0I~k<7wpk{O#^iFRwL^WWLuN4N1kwXC(rsP!SrX<Dw%p;XM&eb1Gb41VEiNOy
zgh-jsdRx0uaRWuj&w2pBi(21wskd^o?ICM%hvixJnk-hb7yHb5=CmF?=u@U?gDQz_
zr<kHTw29Xg>7+||i@Ct8?K?w<Ot_Y0c^TiiG~Ip)r_<cR4&~<qy#gx5uS0Wq&<~V1
z+&;B^qspF~S2d$}c0+czQ*T0zxkh-dmi7s!vymfgI}8Ir8SMqDNYf&zlc6BhE1Rfo
zRJq&qs#;}*=AY)Q_a0+0{{X&fzO`dC>W%}DI_>9*0MgSn7_|m5f)-FR7Oma9Ht_G9
zfV~M}S-u?5C4s)tG4=cfY3sT-_O*|aB-mG;JJT6nDPl2~Rs}m1th=p#7%xO;kUHbj
z)~?!VzhJcxa#VkK^IYZri#(c`+MgqT%Sr@xcG5>QQOz3-j5h;MQ)c%ecSdFDj^?Y_
zLT&95FHV)42Zt^bTo=aR?ap>~q%?I=kc*SR9Zgjl?Xul@C9nq@s!8CIYd4NI!!Y8w
z=yZF#olHgLH$QpDL4!ae(NF@uqtsN9`2uXIQ7_%&twn5}UAm#k!s4-CN;cZ5z4P4g
zepAwr&W?M8f)<g^6>E}j6iE8Fl$#8DxgGIWui9J7W`q;Zdc?BO-qup=8Qh+&+nNB?
z)~;?}Pj$1&kl?8t)>ZsdHj+)i!<FX)zol(7pJR)3s!8+}Lt4Lqw0T@M)*Y!mhIwSK
zw&mA38;SjEpYcFL1Ymb+>W-b}mX~+TdHUBc;#WfH2;rBUS2~5{cez>ucz!gv)3-nO
zy(rYI<4Flq(z5jX#<Er$oQ!Y>N_4j}T(-qLp2NL4(`rOUdR(((5HcKc)zU>PSlW(B
z?Zt9-nvz&Ck;yDO0bM?uZT-D!vx#<-`~dW*bmYyURx4Iu+}%k$%<qCp>s84o1RM}@
z2(GeU2XB0dis!IBYCrfw+#i-^&$*}Uq>n~8>O8i&cf#7-_X^QT&clzbcH%^lFl&&|
z{5vk4aAav2(2n@6$!2IX?ONK)Q^&<hoa$Zz-dX_rkmo(C66v-Ymg88FNe7RmWy?RD
zcXayFxy(l~-fL6CYNB~~`G-ST?E8;e)$sd-zG1kH;+g}dC*?V+u6p$!N|Sa0s955d
z6324U{njddY74D1?a?c4IUMkM)oEtinzvzf#@*bGGf=?guXMSs<zhE5>w(sywz{~p
zWh=Xb(W|n*ggWml&s>VkXklUVf$vCVs|{uwl|^+So2F}9Y*^iZa4VZ=;DmyQ815<Y
z-g)1-65#sgkjvNljjSkAAg=kwM{4G7Wx1VCmh7grhK~EUbv~oLB-V0UjIt2FN~k2>
zqLZ=0Ut3)yjAlnX=QWKoHctmN=`&j-!)uI#Sr<MXww1#NV0!Ue`##1z#s`I9chsIl
zLgaCbSFhVcGe;Q43XEd7{U+FHY2?6|Y~`5uHMAtuS<uE#*$+=cU6izm#fW!jT@{LM
zUpD0v+cjmIOt4QXDPvO1TN}Fj*DY<OTwPoTySbC@?btZ22{emv6Xs&TZ8<fm%u3p&
zmAP*=V0p<kPf^wMqZZ|nRS4aY{8cE??BHCnW1sIDt#_r^2oBT)g}|Uja%<LbMycj}
zr|$gKYR6HISmu>qDh>-8$Gg+)nUsit3OE&VD4?~{BxFnuP6Z}wO%x#1Et^+X5A#Wp
zS-QQCm8(38enuTV>b$TZyB7#@!MHWEtXsUWM{u1=;;@;~2649&GD<>`$5UOOg{CiK
z$>cUOToX^Wc@U04#diJ^lXafmqdCvxSxx(<(cJ5i!l`20c<WwO<LmJ?;8kpoYV_&9
z<K4${I@gK#rQ|x)%K6AS<I=HPnzIdoKGceo^3>cD(x{Ne4k>q<K!%(K25EqpYB5Wm
z)P8gTVwBPjD9$JVJt?I0r9C+m1Cv0<M!Tf|b*|dV5RfXV>&dQ5O^nHSykus(I5Jdw
zRuvhn2jc@6qi=J~Je&$nm64%J={{_pD?VNiOrEu=a4@{qbb(m%D_EIGro(m(K<NFm
zinPd7@zR^rRT5O(d;YZFGo0h4S$KnEjMOaw8Q{<aVoYM3vj8w?F}Gc$(g?}zKoa@u
zk9rKs!~AM5B=;1B7<Qmw?!4#ps3c*J>rzOky+YW<F%{V6rif%zY`7zeo-vBF$zVol
zn5Q=%ohM#<*2D>%9<<=p!f09qN)I(WZGbAUH1OCw)gnu!`0i*Db5+A`qdZk6BGG<n
zrMu^)M4{h-Q>~=3E_ziGM)L9RP?lrB1lF8(3AZkAeW)VZ0CK~MU{FYAayFxWHDPS#
zJWzFOc+{$?II7ZWbIXw$<N4FN3mO6ijec?#n({(}8^ve&S2KZ@Z^orfKMR(Bo6?%N
zg=x^9F-#{Xf+}GG1^1?y`38nGWnHc&s<n3bVo~&}ee05^#BC4*oYaffm=D&J9%@j@
zLF26l6oaUxBfT*RPE(QTP0c9jienv&`wDOwrhqxASD(h13WJfwZuo0WeM?x0HZg`X
zxrp`jtUz&$edE(L>Rt%a*3V8^*nIMQ**$vnt~`Dt*imvdr4DHwBSaR*%29w6Enr;0
z3!XU@(=g!U(z0$K4#yzkxiX1!L7HL}j8ksJa5Gh&3}=em5MW?rR5Cyb=Dn*N*E##h
z(i>SF{_fuOlc(u1+{5O~2m_kd))&vchQSXXd5ERC{{Tg`@>8pDPkNao7qQOVK&qvY
zPSrRW^s3Os=1IqD+AH$yAe@THw{NrR1~b6VA4<i<r8bRNqiBW+_pal>IXa0zdB;;+
zYk|CTn&0sB?{9pPMsdjLPAbE5a@_UH`wOFKCOI2VO7R_9HcRQlj1b1XhTFv?T0B<>
z#e((4c`m(i9mb_Jk@PNWSFr{xCle|6u9+~=udQ<!`MB$v>ESz|Odiz&W-p0UHIXOM
zxTE>kplcS!;>t{NM@sYZFzh>u?!$ZrVVu-$)}Q&)58^9e0ZLe|)*KK)8T!*fG^deC
ztCbm9-1R*VP_nbMNz&z2n0);8sV;T<C+E&A{(#q&d9o^O4#9l^scqzQFWw~My>rVC
zeQtHn87c011anV#yNu6*f4xinnmndr>{&;4%~a5z_ak;rM@rfa*U;7+sKeSbm_y~x
z$&vubz^Zz=%qN~3jMcZu)MfnYwyHnT!5+0yvShh7bId<lg!MH)Z(4=8V_is*1v|GC
z+ISpO0fb_Zec*j5NT5&y$;iPZifQBUr{j-$X{kfF(NCri#-sw2z>?GtwJuFp)KDek
zW4|>$wpQsqGm1@A19S-f?Qqxl(WFf5VwV))xTmUT(y}Oz8L90UrPOEMlV`0e;bm6N
zFlZUw+Ks^*K9$&LfP?tgC#A0VBjAJ9yL}!OBmksm+Pu6~dn0;u?sT?aE0KUI>Fd&}
z!x@c%U_h%S;|Jy@zEcx~tzM@*B6h)~tZ{xVjEm&YMnPPgF4+k6uFu4v+`5=Y;>V?O
zlIil7JFcQboY&Z8v6LuAGtrzFg?Z>}_;EuC0q8ncYoldhl~1m5?OYa>vc^JZy+;S8
z(Oo6Ci7f3u)s}Cq8IB#-qUoTZ`DJsg>Uvib@fI+2&Ck;~{VPlU6N@Ow-3LEjD-XmT
zEYo#Me<DbeY3-Wua=f~>6BMdTWOdc|;L<#)<O4gIN$6^`Nf=@abo8#prqZG$BzEiV
zwwe8<WQsyZ7JU^f^i`TtNb;5ntLSoZtG;$d>^(x7nQZSL?%B`(0DRX(+T2PG*v<!_
z#YT1Gw1te1t5iJRJrS&O%Fm&aG;K|WMVk-zm<p9VJE=%U<%Tit*{g4@&VK5k_s(i2
z)vk*0_#VqyJl*t0%PFcV_+IIo=e@R1!!<l!69DF2Nm+aBN}~FW(}S5?>(ZiIna*=G
zoc{o|Sj#o2_BD=B-t5?44e4qAvg&z0gbL|AGkas<>7VS8$sl|UrL$ZSk<K#h`PR>c
zn4L(gHdiA6*CkwB>&KFNGiR2281trjdw9O_n-J-W2>$V<ZxicsAC@R19{DubqC$Y4
z81qjE7tq%<a?CpWCj_w*AZ=g76LPl*gU~HT(`yoP_wtYTaf-M;>A<Din%X!zE9{W#
zP4zQ=&3PgH<?QYM00OB00JAr8(z6rSam{M%G;OVw7%h<wq@PnMbZce)5${$b(rtj^
zJc_!hma7<0IIRh}oVHLQ&z34-Zw@*S%BE$_CI%^i8$y6_`BD|`KRS7&??EFlb4sdu
z)6{y>;Ltk=N!x)`?=MB7?qQHS3cZX9&eRoI3K8;}KxLm1311MV0rjg<+_a~0&1EH^
zNq7ex>uTN&$_VHNDGWU0{3A5*C2`)Y$83b)@m4&rtHvpToNZ=2jkO@ObssZT!Nofn
zJc<CJ_Euxd(*1}P<mRpbanqVn-heZXpB^~kkXWEOtpYzvjgBY+r`aONBz31PtN`bO
z^fc)s^P?-0JqW6H`apth{{U#2y_vYC1<xf{qSra%)Xk_n2wZ1A{i~}A2Ts+A;&`{|
ztZ|%kk6O;B!gS#ss-w*q<kL+AU>a_7UTO8}_8r=jsierI&w2-9Xl4<Dr2)^aF}XkN
z(?Rb>c%VWs$7)P*#W=C1(lkH@X~vpQ6jB)AF-eL}^q?`x3V82K1f(LAaY%VIfI;=6
ztt}WdhAlTV>Ple5qL&n6fer0JrJ{ieMJ*WOfD^uG&w5>?^zBGSDcDy4X>*>moO<)=
zLEH!2Z*P{LD-)7ii=I8`2R$lvu)BCf%WWr?MnT6~a%tDn5w_M$`Vmy2F2p*p?spyu
zm>o1BJc{cxisO7EX?JN0t;M^irFFoP1|xG_^z@FW%42NnHxd0$U&@{_nuwMiP>;r#
z((OMpBK=ygnH+X3?j1W*mjv>0S?zso82Rrl*Xq?-^}RAMOX_fO=tVAcK2~oaPMFOy
zQmTGY#d8w)w?sqD`Q!VwPJbL|F&z1mIURwi_K19p>kBO=^&IXM#L4j!NKu4>RzK}k
zNq!|;q5aK)Vd`l1gXBE~T}98%xgE1XxIyZEg1pK8CSD))c2O_BDhK$7tI79PH2Ml&
z(T6GO4Jyh%)w!mW1b?VM@GA0IylJh=_ij~3d@d>oyhp4_a-vJw3Lc`Dw2*S1#k3&e
zDAVz#J;Fu~>xdKT)#j7l-59|)GJ)tCv*elF^6uF6H43Dd+DEE3uV)gGCZ}u%UJX&3
z#F{Kz$*Cb9?3(hc?6Q2vHI!8|)A6m;Tk1*c)A-lJ(T;CqZ)K`a<IM##wmIM2*OiqW
z02HgmKWF9_@;xF?h<a+|LuDbs{wl2}#Ign<)5jjYD}%|!A@`^3&|K{$_>-u=32Per
zkyK>y=C;||@vos3%+dlV_HhfF@_55qkYwER?NuAZ8nmb9zLVSrHIxlM(=?nAT)5X)
za}2f2r2hcDO;vNlv$r|PZnZ76d5CeAse=67DtS;`sv<7jsr>4ruE`3HK=n1S6P^LA
zyQL{|z>HNu2*KpiWcH)df!4Q3knhye^fV~TQ=0(Q2u{>ukPd>3Py)Bz>rDU?OT_?Y
zfq~<SX*^T$Nw$Fzno&+++K_Y7qy;?EahhIfK&n6{X+X^`0pfwvilGiz!98is78f+p
zPAp2|fFi-o7^i{wQMc(uhDVIj5yeVYnneO5$GtcVQjv-j53MTznE7eSJ!x^*6c0*v
z0YK+8Fv+Fq*wUV9*am@`cET4RQh-3GHclu3sq^G^rjWH_Ex0+TNEtNjA)r!$gY8NO
zG~zg+p^y>J^rT$V*br&B=Ay&6qpck&!jOujgdsWNx(y0#{{Xws-RoTb1!(B96uic9
zn&HROy*ryxm85pDE_!F0m?#6KG69&^p0#6cYvrcTK?sSJsRVw#Y0;)fT976yCdwiU
zfIFI9hl-tJ%{76}IqOStmE?;H(xKWjT26z>=Bfn2;+kS25&ZN>KX@}!mBFS;xqSLo
zx4c9IWh#a0W;)R$3Ncjfm*i|#_!(NFBCo<`E`2HO!sopU!S|(Z2Q~CBW6n0LN%CX%
zt;QKeHG`#{&~sf3V>aTxQ!tIHv(ljN5sEpf6R4p_9Ey=fNB~!wY(c38+ZzG%2Jclh
z7`IynUV{~-s3!YOz;Y^~LoJpMVa;n!TM3zVicFdH?^?D=iHPV=HJNL~xc>la6{`>;
zY}W1SA<mm+J-gDL8Gf{~{{XJfdJS_=a*KogTDPq|Dmac|98`<mxtbX$6womsry<Wy
zXl~UYK1KPnOdwRR$R4#GJ*Wamj>iWF@T&5&M|cPW<~3q7ha6RXKzVY+{`IXrUnwPh
zReyM{dgHYvnao>HH7)4#Al=StwVPpxtrD^V{{TqMLWd2Coeosg0AYxyQ{g~~7}V-_
zM^&?tQ%B5r&0xkjH?==G?NNh_`cr|;O@LN4BOU?fp>Mm~)QWQ$%^(5Oo+=xVS`t56
zm><TG*K!eCVdu*=a57>WzM`LSgl)(p+NO#hE=CK|mh5kfkGv~Nx=n~=KyB|*uX=_I
zZ68XUU{qWN4yKu(-ilMihMIBaibE!DSo+gOOBz-^I~oVIND4U5G$FyD^yn$0trh{t
zhN#`J53Neo45J|P&1nEQ4;sU_58Pv#;u!qZ=^iq+GFUeUJbzmAR^WqQq2+T^!=uW?
zt4uwqc_S3ibJCxh^p0VUGuDAh=9&)}pa+hWgi?-_hl5N2(bukM&PPfy%`pdIMrml{
zbx;U8)5?6ArhXNpZ)$EJ%KM5<*bMMJ{{RY5I?^1Yl|5AAjQ5}f9clE^aZ8`2059V~
z0)R#{NznAF0YJ?m9C}mGWK&N+g#sFQpdZ4VN3}GZ8US`Uru$QdaY@d3paL)qk?uHM
z!zQ(_nIyLPc{$G&lb#2?YTDVE?HS9S{d!c$43aU79+aTx+K{dtho=-M&wgkD{S%(m
z8+H6@b-`XuLck84C<Gur^x$|D+;Po0PY1mKAw8+I<~Smdp0og+MLRqiPSl`r%^`{2
zj)t9q`O<Vbpkf|q&mAdGT1t=@b3inwr6QiRfKy61G@U)^X@I9BVwy)ic&CAZ)A6LB
z2KB`$^`*vX2PX!QSVO?39MjJ})Q13cqy$8Crjzuk4mQ+H#bq*(p!-yVps0sxlv7&)
zsi!t^-nHW4&%I*l(g7h2-nG%PSB}-@Viv5@CDO#MFmdZy+L!`7;En}oE9E|8Rd2>^
zPDie5iW*GR<~O&Y=B2hQE)ebkL8uAABi@8^8GddvUFe2)Rwp)*_sFG~5Na(ox7)9%
z994-&b5v$YXmj<e93Hh=*OqS8WcR8O41kfrtX)BN$i1s=&T*Q@)R!e#<a1s4C+`?y
zJ`#cJK<l0<3Fp><&3ee<B<;;hA1o?9l=%2?D@d70wM{(zX@7)LXO6Y0kqfVSi=nC5
z;2MYc>o#hJH#y^)gBT{Pumoh)axi^r8KM*)YE|jQG;``HbCXDAr9Uq`15Wx=5amA(
zl<qU@TExmlq(3e@)0kv)OoU}>LO8`}WJ1H`$>~tHUs{=m8K?;79V%H!Yjmg^8;*Y}
zu-!hD1egcwSu<FS&OtQbKb<!o^x$}@DU-%eN|18Lw>1<;ECz8?0qcs^CUQlD<aVZ<
zVu;&42Q=ovHKCDN_y(DdYDqW-q5e9}njmqNs7dFFnD8lwn$4Co02~T%?M68Dr0YNv
z#!fm^ihh+EW~AtUrD%-gSWml3!y~BrP@K~BTF}jIK`G<k)KodeO(>{w_*QJ*BN*{a
z$f*wly+hu!Weyw~QPz{UT08MTnPNUgNH}3ki-FRg(-;+^Gi2c8d(#+aH1!;F){**S
zp{gXUAiz9wDlFjC&N$<rtw3|gsb+`?<E0_%(wtArif?~vhERQJM}K;69Vx@0%^{P=
z#wt)odj3@s8kqg+Q`HVTpHEobLv_E)IoNj9i7u_<kz#jH@6mJCsA$$rX=c7=42}1Q
zt52rePj;6syQM+Fua;-FUQnvJ915v6rv!4WOyF)ft4y1sE1uQPHjO;mhW*<HdghhD
z>C^%^tj$+S`*B8A+qSeKQyf8k1}i2#QtayOYWA!n9Em$(kQa380c8k4#Gd5UeOlu7
z4=mcm924_<R+CDonKhoey}R6qH;j|F@t_IeXJ}QOaM<K~);_VS{h3)5k&X^J*FYEL
ztozL_8>s_6eZ>G#(r)Cuw%qIU1C08LlKW7$uvIg*Hy#JAX+>&~#u7CFM;H}PP|__m
z2T!yiI}Ug>!o%X(Bw^HW!!?zw->tNJP=I}Fb~qL|)evDv09G!ipd0I@IsMV(iU6gf
zr}mN=Bp-FQ)~&-@Y0#;dqJ!&KY^))%fJYMIs%pADwx-dvz?M$H&;+O=c$K3AW->8c
z=DVw#U{V}#-1?g7qk&?GB7hZm09QAu_;>9W-fr!v+>$!xfd!Sv+w7J`Ql}N2F0E-5
z^4c^0^^Y7^M-7r&M6sautZR=C+CHK7yk=l}dQ$=OTqUF>$>~{|e~A3c{{SJIdUQUb
zwXSRh#k<CM<F#}8Z-?fJ^ht0RD1J~o`_MDKjIO}r0CmkWE1PMiD;ptk!NpWm-)>>t
zKqDCyou_DNrd-J|k)(MJcN#!$-d?4oF79!(b*@U=#E*ZgeV=e-&KP=o*2bl3*VeBJ
z@^~N<R5V=(Suv7TQ#W&p2ce^=-JL$g=8hvH`U<t6Jhzq$J<MfUxxuN2lM?Qm8%M2Z
z+q7*T?vKmuNDOUnPnL2SS9E>A>t1u>dzQB=0DKl4gI=SlY9bHZ#=E5EyqCn*mls#;
zN-!8I6#oDhY|u2!X*@v<jjV-;%8mi97VhxhUcBdaIxg=@(blb6-a!<IK_fUdl^iVY
za5`1fg|#ZBS0!N?im5#@Ry;eteOqI$<q6l{BBEskVAhv~AjRymV*@zPtz6NHn?-LD
z=}m2LmoaC`f4m3trg(Q%n@qkz=3*9XA6o5h?3VV;p^#)Sz^)GN#jS20C&??w%}R)K
zGu4dJG$KT7<aMUoTu$7%Zfl?Lp0<WDWpGC2=xeHycu*F`aZxP>nQqaF?sLfZs<)Df
z7?t1}Zk?$|JglF>Dc8)Kh#hlTvXO~*7;c^GGD1^|-eeEggH$f9)byxjnMPc3ioK*<
z71Sd>p0%AkMG2&|k=E@o$nQcK-TA!wiW#%(S<y^S_*J1GBPOUtYr}!XQ;O-JkT4{3
zS7cE94)tD362Rc(`c#3?TU@R6j^3voYZC1FQXgu9&PlAM2bEsq)~{d3_L#i*c_d_t
zk(lyMK<;X(6K~96v+62lVmT^m#8+`dGE`C-drA9xATvG{amRC8jQ;>=ws1#5#%q^-
zUQM}Eg&nI#&sQ@>suO7G&w3CvMJkZz1k(Wj0PEEEQJCc-t7PQorFKVDb27!OMo0BN
zmC<RgjO!e|vPEIo60At)J!?`TcZMCSs-DLcea-cFS067bI*QLS4>hIaD;`1ZO0swA
z4OF|FM!`=2)`kVUxubhVB!W9}T=X{&9#x4br@y6Wwi?)}<0MvKwt2$~V9&LC4CaBQ
zb2jGX<)8Os<=y#;)YKviYLTxTW|L0Q^$Ux?`0$Xbw^BM*-Oq(JTbq#OHbSa6C#_{U
zBX~ulg1LymHmUi8XBDSx?{T3&nfKHh-Jihj13SoadY#me=_zFcL`h|C=CYKNHm4T1
zJhIbCn*RV+`O$<<YtS@Z9z8BSv9V?MrIHBZEwMoQRQh~{q}W=rY}rJ-*($@(SB?0_
z7mrtGINC}5YuGNOOM7;9ZKt5G9Pvfx+Vv*E;8tk1bL5QiKyPX`^u+)#tx+Q9j<kL>
z(~S3}80pP07XuVvdeR@Q9A<zQ6dG>>y&1&=9ZAxFXzxH8`Z8^8*!iocg@!8+Nr)^V
z{cBxMHO)QE;)@}uY@TW)H6SE|S(Za^GM`GxoczZbt(jLVSyQGP2e_@EXCjf2)aSRo
zBHaG~cnox@9Ah2oyo-^=QJG~fq6&D)sSV6~FjQ7p`D%FBFrW(t@;v8mDmJ@}=W0-6
zQn(rBqG*bfng%%C4E@i>qG?%=Oj7Ls0B5f>Z32KGeAFkcO(P7Nhqr2CB64?+O0<cT
z_o|2Qel@KGd!r4=$fhEzNAgq$fzq$MC2E|g%Gm8%!H~#}AUxBGlR-{u$pAs=no*K?
z$*0DNpP1sNGC>F3aA~0n3^GdG3{~W@UaoUl$59G?Mf|CrebvtkoK>cUW^8?;)(&#H
z9jdIl&KQW0AFpbpmNK(`_3>5~3ushi<oBm`D<ZkOx}P{Cf!GRqSWhWZ#~gE-v~OU9
zC`IY%P@P5Fgi-}CB#%!>-!8$i?N<S}jZQc|)tF_LQ=jEh#|b}Lq$XK6NxOlX1lzJP
zQHa3pPbvl~$rwrYrjwpcNPF>2IR60a&<1Vz%%J;KGtFJU$DM$90;vImTvPasqp)@2
zlyS`<IHd-q6i6@)2d~nbns#$c08);WgQ2Aqz;gAe7pMZ52Q?s8Y$_j^o;a#NbY2nB
zq}6qJ*^o3SaMkSZV+ER`L@~!AxnBj@rk$rGY(IR%aX7B}J5{@|G69JftpEZ+{l0PI
zX!}}jCq)-#Vim&?`c(<W3F5V8jK?8Tb5v(cx3zgWRK1-?PDZ$eb#jmd=AyZEwzqj)
zj3~`oDYvCyc$P<$!KcJNd3hvuucbIl{TdT@H23fPMD5REQQrRc^?>D8x&v;Sc9^J`
z3X6}%uwsjT=~(i|IH_Pzm2iHQji^Vm?m2(G^5(ZE7?Fl6J5Y<vx5ybQ&1S%}Y}?@t
z+;Lq8hNX%PK@G?HuBN%GDFUb?m36JHIn>;aDo`WYB9BSBv?X?vx7NIi#BiiKtjQVq
zGo05^Z#~i`P;F2;isUtRXS{cAq@F8Ru*`x$V0z%!OK<+6I^wy8KQ}ehT4k+M=};m<
zfyo}#=Q^B59Y$sCn)GIEtUFf?;yAYIOyK?M>%%^TGZ*!wJt^HjwAS~okqj86KAot|
z2Z{hg!KcFCy&VNG(#CNA0Hr6e&gVj4eqQ3Yh{_t~v^h4hAME0~C307#aXrR!x2j{*
z+w`j1m<G{^;QH0gNkP?foDTI<P*81q`qJtLG{b2%8+GEPZb=!a&rU0<ATv0pj+EMP
zrUEdgjyqG2G@n`kc2!5rK%@brZ{4G}(M@RSGHkfXL~)Km9V?<b`p1Rx6nllNDp!p+
zskJ&2sqmbXRyWe)%d(xlGMKBe=o-X}#e)y`oC@A=5x;1<d*Y%#A-FllN8?ya8yC>&
zj$d8$GUD*guw_<g;*THRY}Ki}CwDu8CHxEP^5&k}-OKa555l5tPVYQR`3mQrCNk)4
z47RAN;J@$cK#%rg#ZJBx)0c^EW^?Ke1yO6;ht6hyrfM@IvhvJ+rm}dB$mot&KCIRr
z9njEx>oa|1plO;6Es+ZG({U!U1F)ss$E8o!8LG;yyE?mVa@y4bM6qFdVRKfO#*#)b
zj>G-c#c_G!ipo}f3yuaU+nDTR@wME88>Rdk6;f{$-AHq}`R-o1wHf0zCNMEcX|cD|
z=`GDUHS3pS$T{_@((2a__edXwR3f83l=+%2IBGqM2T{2r@0yLSWsr^T$MLAKgGEi*
zy2I052k&A!nn1*7Cp6kj^F_+`aa$r$$)qS3ts=2eNX$(a7bu5{N(M=%5raXZu+S+<
zsao1)i_9@L&rwj5k;MU{*gfbJb4F<eh3{Ja9DgrXj~M5!Ya=ytNqxGsB$JHe>s1}h
z>#Ngf_6X$Msz;?f8n0^Gt)o54ik`hhd~CNAH#DT;lYlx?v5`RoNh9ABnJ0|mgOX?i
zCYTNcuX<9%=bB+Xu|Vd49;BaoaY6@5jAT>%#xwyOfR1SfPo+OO>&+%Opach+Qhy3>
zdI`k<Jhv52>P6X%W~7~*N5HJsl$ODy1LA;8{BSEuI6Sd|)7qi5OepoMgQWu)PAFM>
zcBe4;bJnBVpK1V<6+cRI91lu^rVS%V<YRB+Kn)WO#4*J@%A>t!+`%k^<iI}l3X6aO
zlRz3xIu7*%+{6#w6_+GeEPnC#s7;)Q8D=Jg2EyEq#8j&~kSiV=5(ak=N4;K1+kj0l
zF08wO;<L52EvL3Q>sO;)qn@=EqPy%|XB=XtTBBMn(@gStlMX@bY7#2d+U>cMj*i3i
zs>EZ~yvZ$3v8N>9gdCbsJ*haQ1X3-q0MVLJgVR5iIZ@dBvAOyRu2y9#i3}q&n5zqG
za@g4fjr6ILO4KADEu){U3Y?!n`pq@FC=o#ETG9A_RFnQ)7=2Anz7y2gebid7V=^8-
zg6d(6kMOG|@<xC|fDm>Sww?{WBj>qA{3>7gL-vo}Un2X{_A)Y-V?gDPUX;^acl;w7
zS`p^op*?>6MD`vSxBK@<asJk6`wr}%?Mht^RFFEHQMeKY?tQDIH@*|M<n4Mt;VSUG
zy5c)VY<evUitc9fX!J)oIXJ=3(xnhgdP5@*Wv$cW%@#5Hy*-cBYP`P@q5%0ida3m^
z{faV{YWgENY;M~dZKUVdik);#QbriFZhzXS<@k$!PwwrYU#O~*c=uUz#F4MjYLz9}
z%2};WhRS$PSA2fy7xB$mkHI>NefgtbY*#A&G1jC%HPQSysUp|)E1)-APFud#s#Mow
z7n#+4PONw)RUf>*jC$0g!diS|_u7(w-&M-TdwRrqk3Kql)nzWkP5a4DuOh8eU5ure
zR((#9JUO8z?f09{v(x_ov%EJE<sMVhJet63`%(cjE`6vPjj+KJjw$k)yj@qjHKf)&
zJ7VFJPmq-Fwxg5A`bcc8gFX)@9V;p3hi2{EeJe8dG@de%a@ag=qm<3olii&Qd_`Ua
zHVUiTbyt6gm$=MU(69Uln&p49E)P$`ihAi6Cz6hSf{sQ{wPxg=KGt6(6pz>nttX6i
z+0It%sP?KK*f-?iEuFr#D(D)rkNEWK=xOp2=W){bgISaiZ)F+o4OWu>08o%(OUaMX
zt3n+UR#Ss!2=C2WUkqGIz_Lh(&~&K_ocm2X{pqAR_ofxx+?F`$lUwt6R{J1Az@PSo
zG<ZK)ECCUZ!hu}DF@U+I6@N<Wt$Z1&AU=1NeK@ICz}K$%^MVgy%`|}HHaQ&)J{xJL
z&z1)swc0ns>&G9vxGV15)w?eO-P?WZglzCZp^YPkdnut$opODuu_aC$gYRCOCxq@J
z0JO=EOjJk0v9jfvAL~)fJ05czf(=}=g5u(J7V(!OziRHsg9O+q8Yt^m;qZ5t4&OM(
z>$8d+v<n=a(mYYBKi<b8s1kEq+O?0_CV14A+uYU@ji;K*n-eQtXUjOvWw5~JwdYL4
zdy2_%f=62Jr?HzNYCsMt<Wh9SY9V@3QPP|R03{(AH2hLyp0rp7;+zLGoez3D=9Pfi
zu^+k4+|=2_ZXrPF&0&dMR{@9~l!e^?01>I>19jzza!Vqd<E>-e$g<2zo+<)K??<gQ
z5Er5MrkZf;O*~eD7M+eMpyHltfI&tnz;jE3MT9dHpi{Xtl<XG{w1m`&x1HT-t}-aF
z5fX7iic&F1qnbHDaTEbgAeuqeoq$|(%`XRvP<`mZs<4Fjr2>^jI4Lw(25lVUr7i&!
z{8D2*sO1Zc$25g=+oeCappGf>fe~6o6(a&gHAl@yD6SnlPzFsnFEr&tp7dCE6R#t^
zC<J4*I4>0=sq)5u3M>RbeAO{k*mK7e)g9<81LTb2oq&uUw1>WF`O9>q*hv)mL?8s8
zT9CxsI#YR8z%?qfFrvU#an5<B0nJ#HW}rM8n+#GgDW;wdMkp)I76G+Ao0#sAhf~Ex
zflq|uWvpw%nwv#I*`9%5Opu}W>sl(A8LYh^mbXB9W3_Fhd0P0Y-t3w^Na}{ffD_)O
z36q+1YBwG@skR<QE0xI5h#~1wxWnVpt}63Y<&FH}dsdXSxQflVnn1rdH7tv@sj4@B
z4RuzH;G~JZqV4%}iiY8Fu;Q(Ogy~UTF69RuE0QllhzBFJR=82Ig<4c4bJC%i2+w-x
z!#h+&)c8z5Ij6P?(^wUem;1a^$jJIv)2&hFJ<Tm4vKdE8>8+0FE0xh(7h64eHPu;i
zg?+2$vsl`t&ipg?M<DuA5kHtVh1*jF^{EwW$y2e?EXkV&J?fpZmbY=%wNW=)vi9sN
zCf+G`x(CN&MLo9>o8<(!$4nlTrvif_=canqOPGpW;PP{dxS86uz3#w$(&5(wttQ`-
z0;IX*r!;_YD;WVSJjc&!k$LS=+xMwJ#{gDLW1|?SxZ;{ReJNXzMMDB!v4hr{4G0O3
z29SP~fO7D9({&NL1#j-sf$vVZMr%`^aoVn)l1xQL`Rz|Up4C#{i96KD`&O$$Hcz)b
zPg?7!xmb~=oeyfS(qbxR4pbHIP;wiS&1Wxx0WLBPJ_E)npa8T)-!T<~D3F|SPF#v>
zee+5P_xvdU?BrA9KPNe+deh-N5#FQ#U{dz&Nzh`9=N^>e?Cu6}c7o}$PtDIYY1A0=
z?Ns#=Ov#Sz%}ont9D0iH#zNe(T}g<@y*pIkbKaqd1!6tw#yi(3MR`WqX)}{ca6Wz1
z!P7Lroc-EpI5fRusKGrBDnOSx98-IPKs-`0=}y2($BK!#YI)@aH1*GVNDMC$L?p0c
zYslG3{HHlyGHcoOXv5e(S9S$>_1Xlukxp_O2Q~K@9PdYz^Ra7NmHJYOKN@<0n)i+&
zhov+Mk+2697kpD-NW61F<o#(EJW{dApah_fJ?NsCh3Y9fdsCDSl-zSn11B|R3)vu2
ziN-}${yK8?q`(}OV%X|v=qNZHC>RtV6TJhP8;S=sz$njpF_Zmh#ZVK(X^+DmaZZHb
z;)zBGIG{ra%_ceKmW+E-033r!fIHHtBme~%pa2ZlMWG;;#k0>PNc?M^&l#<q4(P{k
zBtd@b=QR~J10v~mT}&~68kjofro3(UvNkcE)edL@>PhWPehocaAB`iQZfSuYdUvNO
z#WZGsd7uX|=cPCBrxBA)$3I#Cbtg(X(ZwNyaY#5l>CMd`A6fuTO#+>dm!&eHj0obI
z4LtHXQvt^mfLt1SC?}pNxy~s)s(_S?9<<U;AnQ&b4s*=_Hj}+ACVi;@cBY&PQ_TjD
z5s}44!!<Gb)NT3Ja~c{uQ`hyTW14uS5tl5RZN+XYe7POPU|V3$J9<{~4bYCh)x}+V
z#YD1=k(zDJTHVwhHua{VAzO}psqzfK<EItp&00pN<YX9``6uQygCNwGV6DpzeQF)R
z3hRiO+UV`N6glAatMdN<5bO>)tc?ZK+bHT(R;+}O4QPlK*yc*M-A}Dkw;^X-)xyAz
zIi`fj+;LetlAWK8YPmI?se$F6rFCItX_-}5iHsW~(wq-97voP+&-AZmEaH+U>N)F9
zPrXbWj8m7E?OQ~~MX~pB(wf;LgT*THJt!dK6|spEecFhewlPyl)0&08^=BhUjVF&<
zi2d%BE;HJpZV$C)Xn=8^;+Gg6^mpQv4m#39C5-SrY5i%D9y6MG9M*`2Sb*ersgFJC
z2(krED^y~}u>4I_b;BNN+30<$tM%(r#}TKe^{7wY>zq`~J5)?SYR#IWGJ1@DRC7u|
z1Gh>;#Ys$-Bbt~T)DfH-pFCsrtq}~GEQ*kx4M!D7PD$dlF?*0d4Ufj4JRJ6`4r;mU
z?b4z~kr0AcKD5KupMnK2_37TTWrlN_1tH*41JCuK3FGNffK5XgH83RcR)}SY!2Idv
zqKstYo@!R$;<Pg>$}`usM0)yEvMxqy5^5xC5v)!sK8L+ZPI>gGi6@*^Wq_s6){u6k
z>U)|2lf>8^>RxkEM%bwjBR%UxX33-AQ&{Ge53M=4HAEHPr9qr_spaE5=Ab<LRI@}4
zO*{_t;f=K1<Wv+X8O<F|4Kz1OcI=My44OQX?^AJ}bM&ZUA%|L+@ZQv<Bz-+`dG>o2
znO8Vm)^3e^d3C5W;Q1KCXQq2%wweguB9bU5cp%ia*3sL>5+DNl3i(6a3#+*7?b>-V
z5qjWMb{dQtj6QTcu5pqvQ%oT-v~pmpbq0tnqJlk<BBFKzkj0+nJ9OObijLmq8?aeA
zuN9xJ**(R!V+U~bs5C7$;?0@nZ<)Bj^q^+s(TQRxdy40+JUq#J=DTfGY=Av|YhO^m
z`vt2{<+JVVqmxe4uZ8`x&*i*(yD*?dvV=u}*0QZrQWx@lqi2!)09A|aO)OBBCnM66
zP1NJRLPrceeJO!v<&1F_QO$EU_xF?PU@GV4!2_n+>l~?Ho1v<(TEP$cq);=S1t29K
zEMT{%YRR?NKGUc@u(p)|{x%#|w6dgWmN@pR@w8I>>4WYmfLz>&Au=A^*Cu>Hb0(&W
zgDbnHI*RM1g=USB##D?}ZKjKFX*Zeoo1&B0QUc*&<?r^%tQ&t3M|Y~dl0xHY#^chu
z231sIa2Bb@ZE9T25~yR;_of6Ig~+tEX*-Vf$yn<b5^Bt)S@)iK;YY1@w-%{$1IFqI
zKi;gHO%e+h^9BQY&>~CAi0thicT&oukOgFEy8IfR<%Au|bAl^FQJNpKI!S^Xu4@+7
z8+bXlMMcj=rZV28tP3c{0StNfH5QAlo5@-!TRp)QUr@69Y-_juV)UtWjWulx9A(?R
zA(}e2sJeBjlVM}+R`ffk)a=sXk&}00LnXVat-w;g^}A^lDQ=!tHW9`>DFKUrXLl{y
zA}%8XC6BFXL>EuB2u~xg){^5{vWn;Itof6s0LiRR5?{!%?2mUToR3-oBU0YpIpjAP
z4ZEDvbvr8sxASI1R$P@PqVVK%N2if4?W}hu?x1>AUm96?`V7)}g-AodpiJ<e8c33B
zPLU8mB=PCZMWorJwvsttm!4{sz<Z5GL?xZfn{(~yUB->!_f0j|3<{1jTDNG}mU-jH
zwaT_~7>w5c0EX@V0Cw(1GT$%16`88T_FYa`x$BN=d&BMKS!dCWUg(ox0;8cL(y_I@
zC|$-TiE!u-*0!<hQQVY@EV%$0kUa7US_u+V19CUgySpt$JNqS*KQQ~kxV=;$yLlob
zV|K@SsRi7yNwr*sZoJj|JB7}=*7Ihd7B(OQgPNaL)=V=EgE$$_t#al`1Mf#8zZFvE
zdFFO3`N*g2(D{zTN!QZ#+7=^v_U~F!%B-fm?@LFEQb|Jb>JNJD4EbF4Bd4WuRgIaf
zSWE+Esvz?26OJ=eJg9n9TlogEDBO+6BW+I8VR@{WuT)?fl6m*G1_1P?1(v%iep6NC
z)aH)|XlkPKbHS#TElG^AF1PamD&y%^^#1@5!yKDi8&9obNSng~D?V7A0T{@sV?71o
zu+$fPQUK(12C}X+xuEE!)SjZbSZ=1a{{U3%htL|<w(&jWU@V_M)}#xD)=j*|_^mAt
z38$Hz;wub&3GQm5c&^+h&lcnK>ractvH78P6;G!Ift_Ub0_gx=4nHc!p4p(23@cYp
z*KIB=&c_~SrAu-kxsT>-vFD1`6V}FZiAPLSKY0Dq-nL>;>=74}#bri{fbIP2Lc--y
zkTJ>NXT5qb_)ZFo-!);f=PiIJy3*}u;kow)ta*TeQI_WdvUOxyqXN~QgJJeyr8ge=
z=C*9DEiD&pP$G{&Dvg8w<n#E}g6AAoZgOU-oKbi(4pCHn1vW-685yWmyHtenQF6@7
z#Qn+dT%Mpd65T7axlmKyxlLXoGmbG*2O)e&k@3LISJUOi*sE8-1M7~pnQr@U5QBlA
z&Y4EmvkM(QM;u^e8t}W`ZssA0R&qvb*L+p1n+-U{%N7^_SCCven&ID|CxJ~8%Khlc
z^rvE!05kJbu!!@H)ZlYY!1WZJC;%AE1T84(Ntysq7Xadr(@P&pGoI7{r2ABmjq<4P
zOa~&bX|NgR<b0s@q{>F+nzV6&j&WC&vr$C57v>c@s-I(A(l<lL`86OM_oPI@>rWV|
zC~KUKd)8&h0<{heWZyQ@G2HW7K#3IHvejLVSaVYoP`SlfnG<04$F(#awB}rAy)f``
zKo(({ax#A!v@qSltgYDTR-m~f<!S)3(Se-RIotq3)RN9lMN?y*^Z>(5CyICQQyUb-
zLgPISE1}cWNdj#>IK^N$9V=@=olK@T9=N6=-OaI3&DyfAP?8OGw>FGo+%f4`lfku!
zJv-Gw*i9HM<_~&dSr21ZW<E^2K;s-5f$ng46|tERhDPA=Pg`XGmvK?F?&g3Qk37%?
zjqpXnCh9)ez<i1YF)gw)inSaFiYkzb%+pB3u{7njb{Rb?@5#3Sb3kFV)uc&YJ4Gx(
zsfD_xG17wMHfeW~YJ@x}T5xYlkEo?wj8jNNnK{h_{G{?QX$T;7qyvhgKn#j*PH|2j
ztsD$`(;1h2#N<^>X07T2_qp||N7lHid`8jOUI3*O-)eP1LXN#De+of>X~UdV0KJbi
zqLZT2faaJIARyOC;cYJB>i+=kFu~@cjk!HDn!vS#?Kcs@y8=fFPo;Zyi=vGR!Z>Zw
zn|R&38LGX8ku8Roc+QOABB;qwYq8Q*QW;R3hU@jNe%Y=IF>UxKp%v3;7H$mkK5+j4
zcPFJqNnF({85*6pmiw0;^_3!S7{@iau0=9kY(bSBb6BpY9`)ekAm~?(NSnjnR%JH1
zjtJe`7*Uh$T+WnNRn_Oz8Oe-s5Iw0pS$IY);ASr`8%0~uY#P$lLFxxe_vufbH#p|3
z#n&VSW3~f#m^*f=Nd^=zpzBUD8?92|zlJlk5my!*in2~}?MlpQi-O3?IVQFBR10u%
z-m;so6%s&ZTCfqae-v+u=rpMSxrvGrxz81Z(fL=UI(dU|t!*kzvV;ebPzj!qYjI~H
zZD3a-xUGIQi&9{XmF-(`0wY#su76iz*Ez|-tvU?JZ@ts<u9Cx>MD@jUt@pEC4w~7u
zUrbbiJb)ezaegWv>EN$Tyo&7Z8)OXF=Nt<2?Pgge)Ffv;c)&H$hxmzRaml8?9kWjd
z6vhD8V<crdo7R_{QV@oO8Fj}z((NSSRFhIiZ!0(4+vrU$VVypR{{Xx=87H-MAc6p{
zQ%7Bru1_F-wbU;tJ69XrW-hF_y;cJt_p0|uO|IgksT@`PNDnnT4z$U>Yhb<VTN%YN
z?QD1VrZCS=ewDt~5QZ#QCpkRRg}g{U;1!~)U^(TAS6~)5{6$$?8;1T24^vxVLj60_
zl}|tj{3vyVW3H6se9~jsRI8+?@ovx7wj+X8<Rg9}rdugrugRK^X(5?V*`>0+-bwFO
z-|rgePMQR4%y$u3Hw&^>UrOS|UFy$wDQVn?>(+v3Kb<9U9^iDP&M6N9f!2T*J+n$W
zQ%L5Qr6Pr=D5ir-DWH1_Pta3GG~hU(jMl4T%c;#8sBj<}kT)OJqaO79)E%y$GfYxx
zy*(%+G!exkWUMDzHqrhxVvyStZho|dX~V4q)pD6itXAV_Ij3Y&XB1c!Sg=!rO6PIu
zNuPQN%_7rG=`<UrHgZPky_fREVBNR+Q{gs_!nCvoz@I%o`rrL}%eV*5e&jLct^6l7
z6>72}KJ*S-{AkA%0nI_xadGKV+7h>rk;lwAred59##Y8kkkrwYNhX>-drxiFQ4lh?
z#a;`ND=S8mcAFO7Yft9D#d=YCA0Jg(Y<4-tDHs%snszd3jK-g8Ok`7vW4$QBrXn&k
zNxUxyikyHuR4#?60R(`Wcwy3_+EmlW&DV+sKOFsOamTGj4;{rnJa?ucr|FtwXB--n
zAk#}O4ox8y=aJ)xlUP>LJ;l*4k%RhH`@9XqNTQ()Zl7=i^b`!502KfRtOJgjs-J7e
z3WU-2#{-LIE%mA9NUIk;b5S&bPCu1F_Nm!2VhDZOtDAzXcTF0fb4#5EDR<1>&{Kx&
z)>G<mM!z-mE88^#>(&T4)PeR|T<AGX&>Pbg3pxh*m<(4nFNpM*`7_Ah@G7A{j5K)g
zJc(rVJ*egj9jItX$z`bCYgOaTO5#_?R%S#<Z7^8v88xys$7lnrF@k+pG;=Z7*%I4w
zLw-V>Cxmi~BY(halApx4(G~;C$Fg*+tIrearZ18~^$SJVSssWk26(rS`{Yz}Nb<(W
zV+siVCKctUU)5w7Gd4ZV5dQ#b>P&yqrrV$4YMaTFnny`<;hS@E@;&0N<D3TXOd1Z1
zgZG#5^ylWRxO6*?T3<ET_jakyl<}s*sxmS7QS8p2u2tKZz5Sozm{a~fP~-iq)GvGC
zn|?!v`d2lp_*U@|u3<Zu8QLqBW!l7Gs}2Y~sd6+=)@Ju-rZ0%}7>N<vNZfVBM&2#4
zU-edhoq5vERF7(LyMJ6#<z%|8o%;B`UE5%_jQVj^=kfi_EwQbDJ@B=|i^-SnJ1^3r
zc^XE`5>LGxr1PC+*TfA<Rm3OD_ad_-@ou#*{JyaE6^BO@`B6N~(|vzckmawYKHICU
z(sdiAut7TpW*N&@6{f(q8iX;h%9G7{g{7ndB}IoS2i_vBBukSrt|yVAeBp^4aa;}N
z;d1_FcNVW$xUz`G$8H8XSC;CB{XS8gjPXMR%01{b5#ExdcNZttj+A$xW`F`PXdF`W
z&lH$60HUqgU44$>WWi<6%mq`%4LBXX^u&5@oQCERCz1-V&TBz5_jMSyL-<#i!K>d}
z!R1A8%79=GO4+gTuBB=Kd`bYuXy##KxlJgyCJ2Z81XI^YPNpaazS_>xykBj7fie|*
zR=evK$D*<N(sN_5&+L8c(LX9h(Af16h3<RO9c~hKsH8gUlYqEdj&?p$%IJ_MC4o8V
zim){6P`m<bG4-sTqwuDGY&J@UrOwA=Xj?)DBAy|Mdt$KHR+#<Y)KL12?l4;vuENIp
zK@sS=r+I19Vvc<)n-|w3qnb~)Tpl;I0CfT=mz{un)4aq|d9F~)aNO^D1e0WLb~vC8
zoXVxX`hoSM&V%@!b6m%q!1CPGidni6X$<Ji&9eUh%T=Z|^aCI{{3{7mka^~sTLYE?
zfHozb7hjdh_02<=T!LR|^sMDzd*+m%n~rILtS(kG+Om=9Rf+Qn-+3_ys0WIqPCMe7
zWC}j_G@1iDS4CG~yNc(z&2#dmTdj0A+=6QkWx&trQBUF}m0fbARy^spQ(Huwjw>$h
zaW;KxzKNSDFu<nNj5~8t{x#9cO~RCYX?D_#ntY*gamQLi#VF>CQOXw>MHu|)+j;9s
z7n)q5ahqtxKNzGma)8bS6yh_AOj57{`q12(P(7&|tyP2|sWF;h>6(-btx`ZVb5A^q
zW-;3pAO{^O*h4xB2&dzk0OFr0hJi}mDnS{?Ow(9morXfnNa;wR=By|Hobyp`1-PYP
z9gminMMwsFQUEhmVGUkINCs&E7^eaV>CHO;3=XupJ*mo6ADCoN#1p{9I{?q)rN^~6
zf@tr}I|yzl#(inTW11=02+9*o#tlo1Eku6xD*-A2xKxa#Tdg%P7-O|bJAA_(DOd=}
z&otn2ywhpwnHlt=z#^$*@`?z+=~6@)xLQ|Dj&sj?b^^E@;PFmjhU29!cRx&1h!_~B
zVF;;_lR-O2JW_%qZ(3n(?av=dECVDvhEH0L0;MDJrjESQaTvkYl#Xh6!j|bznHTs+
z6uCumt|`HDo_VKj_NN5ROrxPmou7xL4{iYHyjN2ajkU#iY0lEQ_r-S5WtTPZnE3Kl
zX!WSO#Cj$grYoM5D%7EW$*(!HVTz{}9K&f9K0DM`Bkr6U(vGZ5f>?v7&w7Yk?C+Yk
zK-#=h3i?)(sQDB{VlcR0T8?r1v6{IYMbzS<yNHNLK9!nf6xXLphCzlPinObR?NG?S
zH`2DFFL;(<T&^x0`twZym8q}S7aeg?Ai(vntETS+d6QO=XGtY5!k#nEYp=98l#ljn
zi?w2xv7W@&XJ*-9pW?3*H;39fu&lGvq#Y?6?{}vGUpmp)TDKqr&urFwKrQP7(>?0^
z9JyZPb*d78nv#akCaN|O2BMp875nE06)bUYjAN#1O-e76ILFJ)Ewd94UrzO0@0141
z9@JdWgDZ-bWhN7zqoqe5N>{iKh+(QiFvg=^7;{p%<PTbgFjJ9Bnir)tfvEymPE^sJ
z)Rz1bDGL1NfFvALr!8v6p#rCfjf}pu2*=MP3Wt@Pam`#Y{`;qXMMrSEB?lGNQl;#K
zT!)okr9mjfxW!8e`2{lI9qMZfj6i8qiD?wk(ZwJplN-6>kxxoj=M>OLsj$b6Y0+@h
zz(C@FK#*pDCOvURawuX8W{~uxkQDDAEh4^n_o<*&$GuF*k{mZmt`C<wftu^BTiU^2
zppvl^gJk4Yh2(O7DvIP{T;r`t8)Zdv++<fkaZsqp_Nz0DrfRYrin#0qk&Xxz8xk9(
zJ~NE<=}m48062HWDL4ncGMo>}X#pailv7E|QYqljPptq~xn0n(=jmQSt;8eL<>Lju
zY<`vOGI9?*VAqy-sx6wLxgAu3YwB_emTo5=EnYV{{?#Cig;po<sPlu;mvwzwJmJJt
zIKx!A<24g-)YylN55j@~??^I7wJE@+0(YeY-jGs`O#mp(2d_#8wG`6<q;uAsIn5_S
zMmg(1fQ%0OPzc9N(nvy&T10G*dQp0ea|{mjfYX@#w7_ZH2Z~T>w0l*EmNWAKQc5_e
zSMOBpeolMR5eOXjrx?oh6*ix>ZiadJO(pNkbB)~=gakbR=94sl@&;*7CpADOc&nOZ
z!a13LyfIX2YiSk<M2rdR(v+3Z66#5^@V4K+GsRQ~nz4IyE?Ec|!r;|x@lt@1c_Nkh
zriSL82`h?VL(tLIj+7CfN&t88QgrsE2Z}>L#OQr<Mm}misP9Mz(TsGYA9jr5fETSZ
zy*iqBsAClIQ4@yarAkIeOw=#I#Xt}1N-3kJX+brj5TM}F^&Yg|wEo=C07;}GjQh|*
zq{cM$rN%}*XgU7?>r&#74cJRycc|n>Q_e9~;UB&p)S7_9De5a4jHFQ_o}(h0pRGB1
zQ2-~6eq+uuF<bWMbR*N&un^$&=C-U`d?Wj{&xk4|wLdm0O#bci4*;5lMjL}u#u<qK
z9!4w9s*Mg;QeX7Uj-*v>q>oct`jwsJ*FWgia><XpLepUI*1vJgdUT+Fv@u)9U}mR>
zNimVv(zfJWk3sKQx>kX#>G5v7w=tp5UbUt{E6)|F79xm#^i|{jMNv_Q6?6{t2w@o<
zb*eY(m`~HSXm_fYe8#{J#<!uQ(G%F_fccF)4)l%0jI`i6#d~o$BuEYgIdht5=}NzQ
zCbmX0EyjLMv}1}RA14G*Mswb`F&Ny`B!FsiKMH|{53NLvA|rG)198nuoPISMjPY5T
zAt}S2)X~W6P6H$9NMqBlwN2|#r{hx|r=GQFmQ4Zquxi2Ls>AoQ-mMdnTBc(mu5dW2
zvURIX_iD7CtqdYZ*R4eSl6q8`BPOF^$6Cpnp@$ghNkAOZ1Cvr&EPlPJ$4_digo?5E
zR0_02i6TESs|-d4KPs;o%VW~4WaFnbsxV{{R0jgAKOIF^BNZ|<h@CprZTF52YEDmn
zDmUcTWsS~84Fd$wIioa&OC3%Ds_}L9s{*MK$>KPtwsLAH&&|@OZV!6V88W-`P!Y~*
zc`=__fsa0wGBk+NIH=fSq&+GoBi^$t260AlNDVG?iV!krx^q?u&wLuK5y{3X#y~xB
zS|d3UMtK9RNZ98X`qW9yNcBV&<mts%J!-=PwAFGj--RY<fO=C~0Op<By&*X7#X&-L
z=8TX(8d1rl0;CDz>r;{P)p-8;<JPQgAaH16KA6-kZmz^%XSni|AD<mfYQUyA6-mk4
z*15awX{~NNv;c)TW1f|_1;CmmagZ57#eAXf82X>uzS_~FIR_X_cCGzCc(qS6?_<3|
z=RqXfH=&Sr?^coUw1!u?)h(^=65dwY@_pQnwQ)9;$mvw)g4X6$c@bIH?wYf}Ob#dk
zlFtryF$Xl{RSE(QJ*$+|VZ8fuq+yu1KtIO1TP2Y#QDyts=7AOUEjV7P^MVaKPt&8a
zj|tSA)E9b{#l7-Ewyx;R7jUgT-zMq+tEk$|cWz^fc8QPi3VnsU+S>@8Mv#u}S=U;~
zj^$!Qmd~YYTg)biJ~2QUI_I7u{n%rkn?*N5wYj%Ol5NAx=!dmyOK}3oB6d*6pfxA}
zFC8cYJ5{*4x3g!pi_CvYH0drSvsb!Jl6P8`;{F(4YrZqbHDPed7;+DK0Ox#1bv!Zc
zk18?Npzzwx#pQDTQ+74cT-!l#swP0ePFFO6Ry5kU0)R3+L4R{&Vj9{LBbLV%Qo{D;
z_Ru}ldmX!0mF@HqVmB&FQlx0n?o4ew=9nB8iKd;d%qV+hSD>n%9b2-lBvvsFK5n_L
z`uj(;)I76s5N1R2<BZhM=@BA@R0szH6amEQ`jy6=v&n?Edg8imA{nl&R##oD$_^_<
zZ7mi;jEYMfWY)Swkfu5T*iZ*6ai(3}-k7%)MPNbpu9Dpayek+v+f?M%tXgJ?W(Cyk
z!0TB0#=6#UZ&YK>IG|>$Y1YzRHNvX-r=8VdwCj10d5fHS*Eiw4MrrPw%+Ji-52bBu
z7WdaS=$3N%XLd;k98v>OR4VOJz~hSGJ|=7HXJBm<=OYC{``vi{Roz)fBsS5BiDn$J
zuM_y4dM4IdBs~T)I%hP|Co$o>Lw~L=@=5|rW4R|k(!FvAfh}Z)Gy#=xE6@HP+6R(b
z**G6{djsoT<T0lCb{y^;)lKRLk@&5#s}{%JRy8k&r;QZG#E$v(=9%K<3#u^3D_FME
zvNlO0o}#pdu_c|{w~)sc^7uTQo|Vk%T8mvV37wT%d$y3{c_ZGdG^Iz@wTuX5OUcOv
z52svJF(_>NRm+ftMtas{iqXlQcAovHmVk|Dt`tC3xo@pkX@ET{s+^EOsTwjyanhQ1
z8EOlbf>7u)&2%wb31bCYHOj_D>?sDcEN+ZPXKdCrsoh+-NZT$+!0S=GkJ_FX6%0C4
zBq0>@Tt>uVLJohGUW!JQN2siql!L`S3${kbtpI39`6r%gAvjY^BXBtDRoz}T!vZM`
z)QV{2J6HjphNNqBameDb1F*qUQ%89sbvdL3m($gU(xU#(Vtwh$s9^G$%{b}=jwuWy
z)37-|g-!NUkFX}AO-BT07|%7Q1ooSh%2x#SG=@iLuD1&DXLqJ+wbLy(!VJv7u<hEj
zwD!{2hRS600<|AiwzV5WecmxiI|D?mrAD)~jc`^o*qUKWD{F{|k$3Oo>qx3~s3uL@
zK3|lI!;43Id(~%^+^c5|UX2QujgAViw61q5cPKwfF@sHsvl3^L6bgB$W~k7xZ<O>M
zD@j`-vTTSgx1K9e2vbtZCmE>~y=pXIM-=>b%}W9)xd-W7)~=kjbnG+Iur)}xGY-^-
zaCfIJ%ZkQt-OHa!=x<XJAA0AtDOT1OmHJZyobiR|nl*@$+3Wr_#4_cH^{qWh^v^R5
z+rG7&*=$t^i*LOsQR`0Ij?@L_fd~<Mnq7&E?&gA~nqwz4z;+k=)M0T^h>mIAS)d01
zx$8j-){|x_jM$_hS+=PnyA1-#7fkaCfX~fwv8k3+Kr&geiuEfS23;)#V+4-Al<jfe
z##<pDN<n~ltN#FEl@IR})j4C?ApqvNWSZRQgSaUKXE-$d$2h2QgHox$s4Q_LpXXTj
zptOW@#cTpIRIkx@hO3DZGDK_#tw$<t8^21@3Yf=#dZBZ)Hr>^snN;=ZOdt|^Q;8X*
z>OCj{0_X6jEPFsC)QK6u<F9&=)D8szK>ay25gGQWTO`zMaC6##Az_cDMBOS@UCo+}
z*9%PvkT+VM%6Eq0U3(g?PEYvL;y7{Wd({Z^%{A9hu*&e`s2;VCsM@r0vDimqO=f7i
zl$w3QxciNO-u2hqBpS`D$!`AuKX5&2Z)P)wzPAMfE=D?<%rW|k>26^t&l|5j2sMK`
z?2wLe>T75_naL1@0-U6S=|H2Yt0b9Tq(<iz0uDxMRpPA@$+68e9%;jsq+~s_R!H3D
zq(PDEO0g4Cq+thBRD?A~4k+7C;2H@PLI6Ho&_+%>8Ue_s9Akk@LvRHLicY_sA``e~
zfHL(HnW~LwYKj);iqFaKTy;Jpcx)YMMty0%^q})umO7j}3TQc{80}0$hczOOK>k$4
z<ond9Fxfl-R*;V4;jW7YrLIdY%H<;=SJU3T>U&g<$M-3_%Upmf#{3U%mU?#eyHs~M
zIImUF^*3v1#LOSCanlr3i&~pS5JeofQ-+Lf0kGhXYero|`zAF`g}tj%&KM*P@RZzs
z_pMXDw-Ua`h!8pxS#DVk;A_Z4$iTiiKGn`$D1^JWMI6^vZ6A~scmo|Pjq&87($%eD
zSMx3i3yS2%QFUNkB$3MLRw=A&lip0n%8j<ipVqn^Tg%gQsa;6iMi#4SnryZjaw5b@
z#&QK`YE5x{sKaK7BN5Am>?@-OQuO(I9Mx8#V`?L}4oA%Vnzb4ZK;%}4vAFWo3t2jK
z#YrBUaw9A)WY4BL*I@@2u1B`uuccy@;<~MCM%8XEH%DP19r8tGpAGAT@uta-_k~1|
z7<X}ku+5LUcIKaI!aJz_81=1dj|=N^Y4R&+(gMFQ`NdF=Nz|@veE6)SA|uW_5n0$r
zZEYJoN`CU1=QX6;ba=o#^IIBbuM1g5vl5QJqO!HCw7HvdkVmyu$}t=eYkNs=^iXro
zD+$JUt<58wPp1_iTe$#7pVqwJQ~v;u`2%De*QHE1K;zoEIrQ|F;Inr<>snLgcO>Q&
z9l9y{)Pl}wI*eC9wuv9z8KcYW2kBcn?UG_Hl*b#Kf$dhK)1pjgBvzVQO(#UhrfPWf
z*;|<i1KOd~lLIkrqaSnuK~zq)zaEttC*&-9RZUk(F#t*x?SWF*%61Zuw0ytCT{1R6
z<MFP3#>B@e0pHTPgt542{!~0vp_y01aZYLn4dsEF($s9GiXhCrc=}dz97n<S%>YLo
zgH4l@_*Chof%o~Xdkrn-i5N+=5uTNObW`3!e+ptS6HbW+a5L{yh*#KRw+@bsc-$M(
zqZ$)83qA<-6zmr=cCL8EE&;70qOyJI*CX1Ydj?OsLwzY&WfBI~9-_Gm^z!cAbH{4!
zn$^c@<aLO=yTUtq*ES`4r>~XD)3KU!NO`B@nrU8Z&pwEJEQvBSi@7t%6>k1ZRwL}_
z7mn3O7^NdVlqM@(+-ar3pbQ>qXe=;$WYNf{bfoJ*#L4YOO(><sG|XyIjP+uvr)P>_
z9Mh;NX`t@Zg!@&yEjHs&Vz6!8Jxv!@7ZxwF;XppeGzT)jFH)H}G-ov-jgQ@2(+D}~
zK~@-Zjw!ff+*F%>w7BA_O2<7)3QUYI<w^&=II@n0jlkpOVm&~j?UJcRBS811#%e(n
zjg7H6&!DMN%I(j~Z1njg`WG2O9ZR|hcbZtovsF9T%vVyO?A3P4$5Vxi#cacO8O=!A
z2BmQ>^B7$9+-px~Caq&1Z%Q+A<}oreK*!Rz<M5@^5xzj4{8Y=~J*P6?41c;P_7W7a
zv{%|W>~Ts63zLt=x<&BrpBeq-_#k%8Jv8kSKb5XfpZ2Pj8fG%gDD*l{3(6+bQ;+}|
z#dK;HXgj$2*E6AM@mwj2z`IA#oz>8%hi7H`$h?0O6H!+iOAqeUm5&yrJ*?cKJhW;)
z_!S#mz@K_#{OZDZVZr9&EaUs8ryd?qK6`>seWMk{EcXi^v`^KhW*hrl<ITzTqwSIZ
z017)+%4l|&`S-CM^NNsZHh}%t$GcZN_>T;>)U||>g7<85vIz<NDTd}^Gv$T)wKK++
zX3Etjw~|EU^lJ0TFRsZ0?G6XOdiAilwTP$B6DiW=c4wk}rSZ$gKOE2}aDUe?;I)IM
z%4D@hZ05C8f`Hbvs`I-tB^wqE!P;{%CZRK-&V0uDHA3U`rVeY?h8itg;+=N1Cl?W~
z@IT`8t#p{m#y=iv4WpW29Q#(Q4NTA5$e7>C1^|qIz-rZ-wajIhfPIE5G>>Y~(z$6D
zJ^EKRDwJVOxSP?a+^op%Ln$M3eszm+D~yfqG3aZ4@qT0NT>a9J#1GEAPG)x4&zj;z
z;7H>>^-5V>oR=i}=B&@fP>|-SFtJ|ki$vM)$*dWlb6{`>O5B~kR_C8e!I*r+=M~jK
zq9j7ipW-}w)JG&^JW{&_&ltygSRj__K(PkF{yxICY=Xv`GkppHkDIl6AV47L)N(76
z(zL|4xmRFJy)&BYWnh-)o}RRUqOIkeNoHkXhR<JW$h^F^Hr`AmGv^0yKq_n9O6o-N
zObqGhJJkkR#BN2l&N|eLVnhsV&D)yQ@bt<WL}meZde<i|sdWxxETnYlRqe&)+>9cd
zW=>liPzS6m*3NdV!WQ(+0y|_o%!&`GuQs>S=C_y3H*D?otCC&a78sbQ>547~eD^k_
zY%;0reJhCZPLW{2t}Wz6kaYvSP`bI9qhM|@dtlZ)@-bXI?0rQS0*M<>G?e!|oMxHU
zki)GU8Yssc(g87wLrQwlObrbhZzEHQ!h&<&y&gSP_!t2DSD0DOmiK8ZuH{qGy(dl7
z^xLQtU<I-FY1~YG)~735NI2=*yw>r&$>d}G?$znKtdWf}X7YmZ+Pu1E4CIdVHUwSi
z4_aD7nnMBBm!%*h6l78XX+<V@??5yFy(rBk1C#Zp0?-dM^ogGssRg5F?@$H3CS96@
zMcCt~72HQ89$4kGTs^!(Csxlx+O-!_3NeGlOBy<VGT09E8;fDURzCTzVCrq2X$Gf*
zQ_5A&oXc;(+HpX-fm`m^Fm+cs$6s1$)MUm96j)a}v#3Uch0QeTLAeSAa)(fSbu`m{
z{fVN%bFBW-!Os+bYZ1WP_*W(N*$C@RH;x<c9MNF8)xNIT!i*D9Hl-^N8S#qcn(>(O
z>}jU#{{VRNMS$u~qCw^9PN|RiY6WtCYvYzboi*-5e~l{+=Tvo&ITKW8SOnzBk?mZs
zoyKVULB|yA7dlqfxcMb<>zW3)fy<I>nDfmv%+y#8m9@4l*Xc+0%AfBOT+yAV^P3b{
zE_K$|e`-V2)8vc_$IxaiD<M6zn%tF7rDC*^B{qz8?OAv6ZJRmI6|7g9&%YVL;=8E7
zc!?P$a%qKeRtn{~sEFpftY$O}P!}}pWKx08r8@wdd87+ZAdYiM#(AQ^Fp4`<h|M4r
zSOmocbj>>)=8e55unZ!T7{y3O6x>p<36E+<UTMG@59><6HAP6Km?~IR448kr?MwiL
z#wmX4)rl?QNcW_<K8CC0(^`p$4rysY=7tqw9<q^&k2yJ_f!2!vnK-D3!_<UfsfPim
z82)ic2_~E=JLZ7~DZq0`I#T=9SO*+XC>SD?Qvq{F`QnVzy(xgu0HYq%r>`HKAtjGA
z2t)c*OgTQ4D`&2AQ9ex;0(4ahIHhBr-6<E86oll8RuBr256awBT|H^&#5NSsVUk6=
zaRaSL(XyPA%~u457&RlxO*;W2oy(E|#X`&q?H`>)Sf8Z>igpkllnyBRQQx4Vz#XW@
zGfq5?lmo>L0M$5ZusK?;2Q@eVuUu0=L`bCukdA1KWq>>ndQynZ?+vzYHUZwf2HPSq
zab9zwkeA>C#%t0n$T5$ld?s}sTI}^OuJJ4Z$f+^!NIsP&GNQaT&Y_s*l3*G>l_mf*
z#~D-2T`!0p#c)4#aZ#&fij&W!Sx^K-XYs7K<RbNlZ&O{=>GM*P>_c{B_X%+%Wnhq@
zJ;gCZ!T_@8jxu}I_<-;EQd|Jg*C#XBqJpo>QAjWbGgGfhicx{mw5Ih2V`@qJ)%>ce
zjlFSKbtODE<5}Z1^;lV6nmpRd(jKf5baQ|KuEx;dMT5!3acl|4t#!6CW;l;hJJ$|t
z8`HV28R~2tp1zdz&N!xZP-)AbTKPtI6UM9@Y(I@>-%I|UiobYcKaFWbNnus>IME~w
z23+x<!mcxoni(dbf=f(+&swDluuum%tqD*19zgq}jMaM+^0M{EH8A)@1T#iMd(?3Q
zf$LYC0*BYusm4EA7Qin?savf^!vIvR&{AMDd((;LkaNW-OrJqWV#IdI?M{EaO<p8k
zaZ)(R&w4;KRPYc1?ND+mXo%`?KD6SlBA!6K=K*ugGf+{zTOUevrx$~u+<VlQ<1r(E
z4QToR%X9m&id&WBW|G|D2OpI_=lxzq079pVAEs#+njB<QuqI~R2<R!9r$_TdDljl9
z0Vr-d(h>u&^QME(6frr?09b5s(vv^rP(auX6(a-lduE}QJ+h$P-;-7s?^IVSi4@iI
zUqB<fA1az4Ac|X+CLl*@Wx3!FN=slSlx0u!szZZU@suK{GW_kuTtIR+%}V3u?@^8z
zRE|Dx=S&2p&otc9X9J}GJsalsq<oqb;L@?;kP*l}Q|XHH-x=Gem0X-);}z&l$owme
z@svQ@=OcHmdzmcxaS0e=72wVR@EDpyO5ZTu{qAW!tL@R{G2g@1qI1nmr{$=m9+gZ&
zj+DK6(-i!)`al44){drvC<BUO6m&For2e$*Vwea;DygN#DvYolIiN%`iezWz#aX+z
z@{@jZRaYUaB`<igbI7Q>nw0RoR40b57>QMeJ5kp($j_}wj1yLvniLFs)q#^A;Z^%{
zR%1WA`U(UVvaC{WJ*l@c31=_Z)L6kHkn$)(3J!26?M@tuuo;h~E`8|l#RSj;7=uVD
z&B&x2eQE$zr}bWxz;Y?$?wVjmXr*dS)PQ&y2bxfum<np1F`84?G%=D*Zezw+A7N0C
zKPq`*e)eg&#Uua@F~u%8>}V9AW~c-s(wOI(mlVetAK_WZWVY+({Hqyb?NMID(YMUI
zezm>f+Y@;yMUhZ--QKn}&kfl}Xwu1W#e(nybTy2fn9;$Z&ILbhLWc*QamH%E`qr^`
z6GCH}J8?@&qde6B-n5``P9rp6@z$k`VeV;1IOdcL&=ZP4Np3SXD8I%>Ju2>*7FFH3
zD^#@-zH4#^JZHUg)OwVPIKihaCjfT*Drlgc@wOQoaqP54Kp^0sdepII3y|4d;-O6{
z<%cL!9<_4b(d|@+Z@dTftgA^hR7qA)T&-V)@OOH1R6@oNsm)w~dUqHV!!%jzejbJs
zWSE6{8P3|=^1e_)0rVAt;YroB<s|SIXs(aVUAPh_{q<Iu9PfyroY|bB<Gp#@h*0f4
zYt%K#VE)f=^8!kq0k1M_G31hS)Yg#`Dqx4nJ?irPz-pw50}8Vk{oXUhQ2^Kg`qg>B
z@<=^u)-rM4p`8Fm^{r|ANSSPN5-;zV=e+}peaPE8W|%Qv><$Tz2Z2t`TAIBn!x*hm
zi!8=D&T2zZL~&1JTcaj1sut^09x5kZbI(4NGARxI3W<i}QuGxQpL)#E4e8dMk?T#x
zJGCo}dUAQGG6h1tNam5a6kJ8PpXSG{T<z1+vf+Q9t!W3!uN>CUcScnZt}ximR+M3S
z{xxXjkJhV7IOn%&rb-|^F-&X&PaxAAR!r6;SqGXxG4&Ku4srbIOC&@1;;ks$G2W^t
z2iw-Hs2~76Dv=T;QHJkR<AKdqPrrdyKZg~fF=S6w+pSF}*A)pPG?_?2OnQEOsgiL}
z%R>R_(wDfV8eHV_)}*Tvp&`0+Ru-zM=BzFPj@4+EO%_S%Q#S4@6k-NyS8M>?%~~^L
zQu9zAJ5;XSa(SqYCR{}A#X{p9_^GqT1w{V<O#N#%S{X~4Ly`5QB#J{Oi-rcR162@^
z)ofw0&o!bmW8>k!3VRMIktrm8wIg)*t3(jV?rO6P6Plh+daTC>=~E)&IDSHydJ#$q
z0+Ekug2d`6!=R?*XB49Yy&xrz?+kUTK-EM%=B-9ol1BoQ5%dktj@KHnxnujDyM60+
zB-t22&{Ze8Z|#9;v>4TLTR)|0%O96&(kUNzJlD$H_l#kn#5Hg26_NMnJ3Dl(Sqqq7
zXWqvZi*0==)B@$18TRATj<wM=B|$x@4V+wemyus1?`^@b$?si+au$tA;E~N%`z5is
zX_XhvCzIZ+sOEqoOS^d{Xw`#Aokdv^g&gA*lOBa{7OMC0yY6nQo-<dch{+40oG}y$
zk}dVDlLQQ<x(;f{Wgv>;VzIexM={3SK6f{2>Vb8S)QSLxZ6+yhmQqjBw4;q<P@sNQ
z&e&>tl=t$a(5k|$S0}HvYfp60+q;f-iUcz2Nw&GWN!$HmbUCY~eoPAF;PDN>zEyM^
zOL4c7MRelnc5XZh2Fwf1D&pe!4#T5%#c$g}VTDlhimz|1SzX*1VwoC6>Y&xRE)poq
zvA`Y80x|Ebbs4od<&NYm3;Y7KSqnx~9&uU2#4tVglg`#VcXq8Uz>Mw$PzM32+234h
zWmU)-=qs$!V3OX&B9N9V#!XvhwwcE$&N~jYl3Yb@h24MywJ<TSH0@4JW;xP*w#qsR
z-jUeA+Xu`BYY2FfDXtbFwB+OObgMGzX$&Sw8)|yf22!>&OLEe`05&<R_nL?9e4WI6
zxF)h&SAy&}+20@@cGecJsx)|wI6F%dNM-v=2;;kwSl@FoB=@bA)1kSxVKzu%)6%%l
z58m9#co-A0htI`ydW5=+(TMcq%M<f9d0GMPYH3<*Hf%O>7l3`MM*C4q7`<5b6wNB$
z0Odd$ziVq4*6H_4kC@d>Url?d71B&cpO^#90v#r}jit{v(xp`Oub#Y1s2lxWX-t_=
z#klmZWAS^(rucSY8N*1PxUUbjh~MiGM;04%bw9;`ar~;HBdF3Pxw6wBjQ}qp+sE>*
z>d$qaiRVnD&5lp4J4*1(X5I#N`Osvq_l-y5JFl?Y7#L%Wao&`Hv&p<ua`!r$$e$`>
zob{|oSeM3X{--idSobHtrfV%6EA`GRYI-6Wd>ns`GDGtBrz?g|Mm;HkT1MI{dyqiL
zT=YL$5czAh#^8Nw@QY&f?N#JJL1D!WTnbW0wYNvg{{VKaSVk{hmBIM{-lM%l_(7g%
zx75DJGrUo#FV{WmKZK)J?&ic>{hbg;BJ?$k>@wJ^DdgX7?8N6j^-e`(c1IX1$JUy6
z16I>h{oj<wpL(CnEPCd!k+v`(R@JK{k*?poI_9~nQ?{tqG91bnR9;>inv}2y*i(a}
zdRH-_Br=vj8-^X~+%qJhqnDq0q@_1?rE%STXkclbC104|wN;kFc*yw)1HC1^{E;_Y
zVzw=HXePjz1wOs1Sj;AZP@i-k#*jw%#t6-I;?CCWW-}Qb$TZnBKt@+-9@Qf`F$-s<
zOB`U4mFBuH>=y@sO*wQ44o=>kC>f0czTgn!jAVALTWd)d_ma70J;|%-qRg1tA4<0d
zhjS|c&Lc`gCeyE82iYIqZnd#2Q$E+==9zC{VP>B(R(^qr=A`>_GlW$b>5*E|pDQz|
z9%Ns(;w*9s_BA0qRB<>eI3UyVGhHmfD;BJq6OO>vwh8sDC?9Oe*l*^y(m+6|7>l`T
zM3J*k8)<m<sTk#L!m@Qm!k#}G)=s9g^+d`s9qA0<H4(N$&rH`7;;C3#{G<x*budh=
z>0A$rq(g78zuh%R4?cVe8<W<W3H)j9Ib-YVO(v?ujX9%h;9{McGe8J8Q@&wHPqj6U
zO&}DuJJT9mawys;+A}~5G7~@<>rW^s#yijiwn@KGg?ang;=OlIY}zh<_A_2-;mcpN
z>L}-;H|t)N56c+9;<Sn-lH8`~8>UFEBJN29?bLJ7*KEfsew<e&szg?1Kc}T-U1)7V
z>tdSR$SMB-YGv)3tCR0i1M>d>O5$gFiY6M0h6R)gm|R72zb-2+;@UIV`c><A7AP6W
z=kHa)nN*5Mt$8Sm<plaxYY=*pYRt(b&G%1QV%kVR<MXYKQn-saH7s!RoOG#-5-v_L
zj@5D)3aH&e0=lNu$r!4#I3(kWw{;?>cAWZFa}viUfDxM?Q~Faexb&sljyb6kJdy8A
z1_Z!0R^;P7s{D(z4(6y`a@}~QgjEOLm0Jucq~eV6R3mN-JZo32uC6RweY=p}osZV2
zX}`RWn$}nqhC9?Tn#p}(tE#2WA)m26wSlc@vspQlK58C>3YqN+oyu4ocA`t0m$NWR
z`+yuVs)Mr>k%%KCU~x<2=8{J-z6d{!Fx)xEYUsK#CrCzqV~Vg56>5i_A;mj;kTOkL
zVl)-edN*1cRSWW(&*b$q^#pe&uHr0-n9v!IaZtzBq^c1v4%%?WI*LUccB4O?GD!yp
zl&=*M$VdMGUX;1^rU9NfKb0!-!lT{C(wv8Lch6x>2+!3<B^8@mdZ;2mJu5W&*Bx(&
z-Wv(tfz1@PnL>_~pkz`CaL#F<9=r;>r@{8C_#o%^kI&&$*97}lSKy5yb$wuYl6hh;
znQ%MRpi1oZy&uDxJXTS{<q)!C8?bR(mYPI*ZMhcm?~6GA^NP%h!X{rO#!B=j(zdL2
zLcUlSTwr=sN^*KObSPMw(&Z5E`;ud?tzK)hAnK%646L!SJ!?AaP<WX6PmX%i<S}wO
zp>oUf@B;H(OfyO1KNQJ&;}BXBhzCM_YPPfEC$`e0idG(EpDHl-t?vuNXAXvsZzyGx
z=iGSb-leMtF{LD;7#>#I6&IY=H-s1Mnw{RF=n6{PQ;x!$;=M*VbpHUd!rP{t?7%e)
zdeyInbTm!i%Bj#E^t4+E>UEmtyJMo-7rAuYIw-Fq)&4MfS1%o`CDeEIt|!HwE4kOM
zpAs;SJ#*H%Vsp-DxE`l%@s?$oO!j1_d}6%^!@fDvJVJpYnNnl?3~+1ap0zE#%=UAv
z_VToHDad6w#Ua@G$RXXd@~!Jw-WOPHZuN~hz$~&E7eC!<;=Bv-AMMbK4NZW!A9cUI
zRy<X#T<F)ys@Y-MRr1|OaoVXeS}-*wFzT0({n6%@A4<<+dFHXst#f;*OxFaglAM5g
z)~rPA=ab&2s3)a_ah_{;NFTW47_36PdRE?zmO`X~ftsK%%A~|V>+4wWr^xaXxB**i
zK3c4JJ;A1lGuKT(MsuI7PPV9=1Q@Ga=hm&;**wY#$R40phz#Ym+yF((8rQSX*@o+r
zu}^Bh98g(BxP>KsYYzVa#xO@Tv2AuLcHsp*g=2Unou3h>IO+#Afvz&nco-e4GEW#}
zVk>6)nx!_sJ?1>f!hSU_L$M{fDJpu3>#d~Q60;uN>x65b`@br<`nwB#sQ&;sADt_X
z$6I|UlGkehSKhG5v)i$XgWomE%dTIuFfstR>(;0}<FPFAxy>$N*z}7%PTC071;T~)
z=CsoG7d%|ABQ@la%1O$*amGze{h>X%%FO(B%^bmF)*S9aR^@m0=DB<O{bB}q<5YC@
z9cz*vAi4f24M;pmDC0bzS~-PcdyRWkS1U8RzIf|W*?6Av1SujJKiUWUY8bV9d)M-(
zRRI40cfCtKjHW*})?BIRy=iVTXYn=Una0!yu@w#UGThsJszw>cO=4ZaEDpicj8&U>
z?wZp)w0$rdv8t~VzX2{<m$?wl1o!JwEv)W%iT?m9nKY~S<!ze>yAUgnl3kCWRjIAn
zRDQI$tt8Md+<eih{{X<NO4mS+Bf4}9{{ZbjN@|pemNJxjoY!75e;QITU3B_go4`@#
ziZ5|gKe6<r{{UNjTQvQXGg*xzpU)JbtDrW%9fV<~4t?7ulkI*Rhag*med+raCz(^|
zj1@bw7bK3rQ_38D$v^LdTlN~hmo3MWZEO&V=%BY(VYOob^PRPwUP?;xWPfP$d@(pk
z?5<=PNF*!jR~0;ZRs6ql+5Z3@E7YuXn56(bt`GY>R>$@gnCs>o_YI2kr<!45y9bM_
z(kGBxXu7;o86r<Dv5p$7%c1Ib3>s-uIP09(s()bEWS=REdb4J{tH&^2X_}@j-O?_@
zwrcR1l?+7rB6HQm*7%9-^cR2=J<LH*T+%j!W@Ikc$&X6o9`5{}Ze-0mC@<U@H%TH9
z$lcz(S7o`&^}4s*?QQ%wr(EqZywe8%0G?`1Z(8^w8P{^yxL;OmX0(1BD;*dKBLV(m
z+4|RNqXPqlubal_a-&t#gmyPlt2K8c%=Jwk%RoT$S!I1iW1W9Wh@F;X?e!ejbL0DQ
zHkLaKaz%LDjh4wLn)=L*#~VZ1Pjk-2Rh>Cn=R*E2ff)H#p+{`3F!;J>QdT8gdsi&q
zdzx|+>-bmD#|24rIG!SJsktYLZ`iinD)z@(hEEV*I{yHzV108~{EB$xJJyQ}NpvCB
zlP<omc_VW?m>=zTs2=|4^3%wF8m?&@rC+gv=ufnfD4E>h-O2jXa@oNo(-7f@LrTXF
zo=32!$c4<$Pxx0kB3pI`<;Uxq^x^lb$Nm`4w_2Gojldf9_3QpM`9Bv^<i=mQ?cn8l
zWTKI&M<X<hFe~Jav8r)M*q~5(6u`joj6QCL>~Zq?*Odf}5#|DYtJu6l7?VVppWy_W
z^3Uvhlg57&UwOmx=EK<F#Qa8vmne7&rwS`#9%I3*Z93KM2}e05we5jyfJYsx)up9Y
zbI;)(<LOKw=A|ox%`VSs`Wh0vPco|1gbG4Asqu#BX$tXMn3c{=S<=|8+k^K=s7ULI
zb))%LYR94A*ES(un@02<q>I;!$sOyTyBKQdFWnHf;sD1}T!yWz+QlZtV8@{uubxq7
zrc$_UXV*26cX=Ft#m`zzLgnsbEdz{W<^zLV`B@!;;feRH<3e3T<XWEnn>%n99Zgn_
z8Lmd;2Or*Xfm$|p5UUAp7tCzrDd;Ow;&hrJAC>?fmAZn7o$h8^Y1&*VzV>rBJu`qR
z%j=p&s3`<H{e@P!hSDY6@u@!b98%k^c0_~lrXt7o$J#z<U})3S(<Rm~&J#P6(xi-|
zbpbQ@RCB5-{pAO*6aj8ca7AiAc1t!t3e33i9P+CwLI6B-Ri=E56I5h>n}bMWWR^)^
zb1&gfww>+YH5TuBLUBk92Gw8tqdwJL@8_4$3Zlm+j+Aabv;iZtu>`rO&t6)SG-rwc
zN?Iu>7*Z2Unm9CoN+=@+l7JnLtw{{hTgoJfu)?G5?L`1@j}cFCZ{$onb<JcvC7X_F
z9%}8b;~g;-O}w6zo<sUpk&peVLl^_CFf+V|qsU|b0P3sTSJyPF7-}ptKgnPze3q>*
zAXA09QUfo@H06f0Oe(+qdQT*0u4n?P{GIVn4B78i)-(gBH1L2C#Q;()$JUo?k(^cR
z3~&WBu6?Kim{+AS$a)I47YjxJALBsE%LJ{!12tvs3@SH1<~_YB1fdVgd8p*Lcattj
z8S6|!Ix-BfsP>bdMLK(hbB@(teh*v<Ku@sx(@JBE)P89l=?uN|nm|7s@k}e4X_QlZ
z(MV&+0-A6szHVv0XA}V@D8@Qeeq|?_KoZhq4)q@MnoZq}FeN<DDm~nHqjBv(jlU1N
z{{U!#&)w-=RD<O_R}rI1S5%9d?$69Jd)F-0stn7Keq&W{Vg?U!S`w%Xar)FVplA;j
z+e>mJbBv@Kjm8_3RwNr+pUR+Plf`;S$ZZ2Tr2x^2s{rO&Kn5vs+LUm-3M>R=NEBn%
zoy92p=&%jN80MX}jAz=NfNnVBG}@CKa4CdTuoX@z?G{&XrVh0>{4U<LAXfsE4%8?E
zwLI;>1FZ-I>DM@<$@HZnfGW_1>TqerX`h8IPBFz$0Td1fXfy$nK!iPWOmWRh!w0P~
zg5r}HD8Qs6nsW5wf-q@_PvfP?qym?vFdQjOG#n1JA5Ln3co{V#E-{*oTak*Dj(Q3}
zGZ>`fG;=}V)d1!L8O=iD12rpj6p|6J06CzLQIs^&Fe%X-ttnjQfsy8(ze;EwX+Y$P
zL2=*3#wh1FqXZguDS;6f=9~zi;QG_n7Gb+QQvxjG>p|;E%Z5JGn4m(QoKlKa<w(T~
zjL<QpeA%aijw!58<I<k0jJ~Fl0ygVFG_1Hd>qrGQ29B2}mvtG(Ij>IBn{+AMV!W;i
z79xa_K42@;v`61+ho=~?kKzh`@{#D^-j+47QUS#`2OQJKPipyQcL|KsSvMi4fkD6=
z@kAulu7Q=1g;E&sD=@kn;t+Ayn$fvrDt4aTs~*M)8sxUt9M`W$l~9zP<}&z^u^Go&
zS@Gqc%7t8UP~2ynSDSmA5H0|w$}&1r(;#vwvVCgdxQwkuLAP(EWGUwcw=V!_NX=o4
z2Ct{UO7zYQLidNb!h_V;Nu<fX*)h=ZT<!sn>suNmhsi1Z+|tY=%}J9%+GkXwF)lk&
zsis?<_RGykg1$0GrcDt$*V>t>46H<+{Y^;``IOUjRn4Fyw@Q@t0FRqiQgfWuTVsg`
zJ#$tgBgi8?s+=bmP0nhT!Zfz-4OJJ1Z$VcSWOwGPFvFTx0UMF;QUSU#Od}$vhXOi7
zu@b3KPY0Y*lSmKJhQMp^MNHiVLi|+u%wYGSfP$0~4+B3+Me0ADN`nnf6Xeti7cu7X
zcW0WO@dw%00-1g>GPkLzry=b}(vD`@xQJ|`5~nS+nv&)%k&)NwRqSO8CfwEAoS2XD
ztyPxbX6Nvw>(ta^j=!xNvM6W?;UuX5eiWRJ2&Tf{F;PnSQ_VmQr9CrE28`#e09lWi
z@Ms*=cI}lQ=AI9|OBo{5E`ivloWELa(f!x8CAbktOI!Z{DuNTV`qY5p4Wo`Kv~RTg
z)|Su>A<EW#z=PheM%iA*s9ZKB$Gtd!#y9}xrD6!qc&HfEs(*J^U<~7mZgcBKaY>$O
zSO)|1`&5UMQ0AuN0McMF_~yCa62OvLZ`+o^u7#U5k*&w(Sid`a*P)lx<gFHGQC=+a
zcT%K`W7?wpYTeX(ZX9;1xW~PIffsdi$dIad#Wq7zM60`+j&;KyO0r0mszHj0Mh!>~
za5<y`o+$jObLmJ&tuX-P)B92Z$4XI50~k1^PnE%>$I`4>MkTvdVM<QQ;1`S<HQ;}R
zW)eXav8|#-A}V9oBC(0d?_BG0i$LXS7U8ORvdhIqIx;^svycs6&Zh(ws^H+%@r}Z&
zEKG6fQ$je}4Ms*W+N6Zwfs<EqM#;ld0OF;Qes1*{<E=Y@nCFUB1di0W&!tHmY~2SG
z#6o_QV+YoyDs$ef+gX{TXC=5D1r32gl=b7SHB{A!6sh@_Y4kM+89h0rae&DDDd-6&
zwKNXZYTW}9O5$Zk1U5Jx)X~LQx(X!ubBcsgxW!srbj1ogRDn;_Vwe%)j8%x>X<Q=x
z<5S$}lUl~E><K-Aspdl{1<fwpRDlR=4!-o@g}QU}8K=yEhaZJ0UsG2jvYtf+V0Iq3
zsn<!nlm1wgAMI9hsFDj1X{_OyQbtZXgM(U)ZT5&rc_eIf4B4pcw0nzrx4WY8&{m{&
z`xK}>YZ+CENgN|DmvG4A?zSs&EJU{1U7+KN(tixu$tjjqa>t*(de)2<s|0>jYO0;P
z)?U`nL7ZuiVIZjo=~At<uD>iUbLcCtOJTectM$cBu_~S_{<6hmi(NAAM!<{nsaHe1
zZmOVtYq1Ep{zjTY;~hSgFA*Ww<=4Zrw+3Wf`&EVT>LUK~<<393TkJp;6XbD@wGOnx
z#&jA~F$0H_4c4R@Ww3AcO2^cSx}ytCECDz*n{Ab16|#YU<&tsjQh7)hXj}u=0-PT_
zQRW55N<dbTFx*uui2hTK53OiBCsuGPChF-J1r9!LgVvEr5vT#U1JbR-%M9`=lx_p<
zC#_tFje{M#R#GVJGznxxC?#S5>FHbHTkkWI^fk=rb0K|!z0c)cFa-Wo&=v1SZQqO^
z=UkkhE3ovg!gXO81bg#bl<3PV{G?>`HE|S*k{_C_MA?iQuHcTfG#sZ+D##@V6%^+R
z#Qv2b&ovv3+#0w&Ns-Q8BYmKrY7X^s{YaM?HB<w@uX2;TQNcaO4n1jegFqC7*678S
zV&<Gj&79L9_o*AxHL5aW3H)j|>xz($d8RSv+M6097(8-nCmzD4>HZZHj%zk(hK{tL
zQ$fk60qIguqpx~d1_w$(?rH8mT=k>`Y4?XtD*SF)b6KjtHC>E?7t_|Rn<AnujN`3A
zA;`~ql{#aw?@W+j6N=cz#bfj}8v&k!H6b+<HU~=0vsjVmADtmQ(q}va-inKwSdk8D
z(jK1GRYx6a%KgwPlO>NpH&o~D`&D&6FslPQd95PMWw{F+=cPdB2BdcDP!|MJWh6Lq
zX|nOwkUn|cifoPVP|HYXH0<~9QJPJ|9sQ|XyA~6u%~(=M6<Rjj!?CM7d-N1@65>jS
z6*<PiRpUoy`9|-?tT-Wd<EL7_WM<;ZvN6p=&T2^(LP=D1Ip_s6L2&#mG86QvbB}VA
zSY+d^LnlvKvbHzuK3iFM_N6*bq{9nqC*xVVknU)r${94Hp7nWrKdQO^0FPq7?;4#v
zF{;1(vW<V>RUY08seaB(&x--N)v?nZ{c8Lk7t}xHtH!?g&0Sv&&78E$^b1GUsjj5D
zGkpwHBsEOH?H-l3o*Ezw&w>wNYEj|9!woxQ9YsH`(p^b-d7Ql5cdCwguFL)rOH!d)
zX?@P)%`|vZPtQJS`njy7j;75chmpqa8TO=U6rQ!&j|=H&I7j~gzKuM1e@#LE03Q3k
zt(wi_pi;xg;slG&%neAgsa)<;-y*w_q*#H0Zyq{|df3^HkRs>NDqcQ4iu$`acuxNS
zyWaz+dcLr_DfxPHk6P=zhzH$?K=u^yi^vMUOm?aM(DEPE{LPVnsa`Oh=P3CjiqL}Z
zS9pw4-WE?nD;Cmx{Y7hAP5ZxG*U7rFKBL(~u=`cjZD)>1?t`)%;rshnMHi0@R_d4b
zGe*Q<xEqCMK_U<{ntPbaka^FoQp8Ca%8Xe36U5dMYLgi+hnD>n_^z(%_Sjjpkxqw>
zF<xJ*XtuY3ys@$Uan380ySCKqWGe;izE@=2O=}!Y%$^xD+H}oR%(?QNvKaA`Thc&P
zcXb_W=KC)ZYdUPgQ7bkMcDGvVEq*TFEIwV;qk3c-+uKCWczJX^YTDupr;tS9oemgO
zk{>M#HUO_4(tak|X}7XGsNhQ3V#lR)7he_hTgygB*oQn|iltU8&QxTM-rnjvwrzuz
zH8aFzjgYQGaBI(WPZq@Y3oLO+Q+FXncSpo}e9?uCh<08+Tw<@88Ok<fR{AU!^R(Z2
z+o3&&rCu?Dgde+EdQPh>momk6$P+n?j<~HILg59j<YD+zxU5jN(XA}5UgF(;cJ572
zeH@ool178(BZ{r2-)@<ra!&7F)va>rYi{!%LX7c19LAgB?X!880Dv%dk6Pc7+{+V2
zvJ}Y1M`~`Js6(niWQ!|~s>1|QYO+18w&W#q+)yJUPw@NLUA)b3(z|!XSk<g1y0dkR
zWq`;YwPQ!SH;7|){oosc^%ZMSpZh-C%_6o3r7%3+-oob6>E)6U8iVyFuiro0teOTp
zGPvftn5VbZ?fl5lZ8=gvu1CaHEoCq6<SQSbpnBY|qiLyTFr1V3iSJs|X%XM1*HAN&
zp7l?|_qOcG9P)y=`AGh?t>QgG3q3fSd4O@;b)!Mq+=4AVEMXDCoq5Qr7ak$F(k1~Q
zFSzqh(tKT}%WsRDh{U|~Zq?5CtHpX+I~8<b-3p$jmog4UdQO>hHm7U$f=CVgBehf2
zwW&0VxT9#pBlj)e(!842;=}1tyir8YpSlN1$<#c5d9Tbvf~lOQdaW*X&^au3KN7WQ
zXVT#jNTI>b&bi{e+eXx5vDBlT<NL#D#~garW%i{#!Bm!3V5g@~&Y58On>g#hQY%X}
z5)Vw5$J56;Gzdb2#(Gvqi9AyJx-QjaW*>VMg|&hW!?#L-qGxZA6YW<@o3-RAGKA_w
zF~egy>siYG0KMm@rEA>6{##^WvC^>S`DDP!t(vh0j`wT?<kpR{gid+KdZT2yjb!Vd
zD#?1JBE#T=&sw23%1G@~nGYQIs`7?zII0l?5J#<5Vb4s}mm6?1oYXEc+v`%sheq33
zN*rMHt8+#!A@h?v$KDm4yX#jir}C!<_*<=J^eC&GeJV(0DJL8Q-le>Q$$v3UV{@OS
zRb%N@x($sI?&Bb_rtTxwqp`YFkgSWxu4_}viebPx_UT+zA<E5TB8Qsep{q9c9EE;!
z)C!UG<^wCY^Qiv9>T{9}VrWd@B)=~!+N2DuKJPUWt8D=1G~hVRASQz5YjcEh7p-gA
z>obNbT%E(ItV{-8X|c%BH&Kc#2WJ+oF;TZ^sYbPOons$`VCnbD*bUFUZ$;(EnBe^>
zG*BIW>!3l;Oi<db^q>roJq=Cvanxgqo;U{$w~pqd3h0weLrCrF05z`)>{M+0!;@72
z2uEyot2WXpa;Nd6Gj<6Cw(9=fDomW5)f+q`JY9Lnt3du0(@s}L5>_We^AE0TVir3F
zc+Fx1>sr>$x)6HtS`b?j<GnadgUv(RjMC)ir6HH1e4JHl;0#TVLrDu^hpjsIn2kuz
z3t0Jg<F<NNkNBcylJj9FjGFc>Xar|$`u<hoz9Mk?gKg>8HBkc)_3uU~G*uEEdeUb!
zrvy>>Py$i39<*~!A&H;|5C?i;U^~(j=8&MI0vQH4rWQCf@VuHrpa4d5Kpp=8glznq
z66G*k2j04s999>Gw;eq>=ZuQz6>(cFiDORye=6s-$hOJ98QuC<Mn+Fc&DG#CTA%L@
z)fE-uT_<TAg8&J|IY{e{O)HFNBau-D!S?j8Ii8$J3g?{CO)I2hgS1nFWMpHC*tWKY
zcmnSmxXydkQ{2kF#sXbzJrA!+1>3(0y=$O-5-`~=G3qKM)8R(@=rDTbw>b>R(noKY
zU{YPp<)#M(dE%|!-CJ5N#9&(=cvm}ddFC^7&(?q>bCOSP)WXrJ#&hdckjXOQFvpKd
zxelEpefBu+4FE=?%sgiv)nF)wJhnLXsTf5H0-RMDWHL5SPpvTxl2YyMRIVH6>DH}d
z2B}=1-XBV6L^;haX))559MuTa(wLu@(APx@laE^E^tn8{j1$4)y4Yc6z)b!%45V9z
z1%AD0WYWCDz~I%}OAUZLkF?d9^&3bFBRZUQ1GOQX2CZP$cT5VNPhPb|FML;1u3W=?
zAMSa_d{-_;JM&#IdKj=AQ-K(!espIwq9k41ntHJn4m(qq8LB`|2`%YTj+v;GRDh3K
zv_l*TqXg2a;+%Li#4s9n@bjF|M?Qj`kXIs@h`{EgQ^!t~7Cvf~0X%g2Q$SSJ)PC&x
zipV`HZ&Hu<3y^Xv6plSBnzHweY3v|0pyrZ+#bQ|R)|@)iY04>qBH$@z>5BCq0O=Ag
zly4m!T1LwKJ6D<8L+9MX3Z13gE=7Gep=q(NhN6l!<}?@s=}o;0hW99?rNmK&jFX>V
zTF@&ra3jcf9{3d2xmY6!Ayw=Fr>3uOC9#VDw>UZGr6XxQ4Eu?W(tSN^4&q;&mhD<M
zvhscT#bRB_gl?Sl&2DlWX1goi>jK-Xar0ZY7n0jVA@f|r{mkOAVYFtyp5|_)@)oT~
z`y(f(6)a_~UjA#A7d9waEx2)>SKhd-b5^;#A3W?sb;lf6bK!eMy@K-DoG02dwfzlO
zy7)tRG^OLz)1Jj@Ic^D_Sb3&my(#_=YUA$SM1SBF7yK#T5g)rPx%_EzG4mtNuz$&=
z#d<gVDbEs-_pSc`KmN5U{21{oAH8q?0DXV;sN`YJk2{J<AeknKipYl`iu9XJNp)=+
z-r{gsp*ibHzXbe9Pt7&B9-yD_tvg?Z-XXKKYiQ?yq4mu*1}8L8yInr|-+j4{&c;_G
zrB;hiylC<*$?fuyTM&F5*GS#=m_r|}be10rHM?{LwPaI{$xoC?oCJ_b8N`vgA8}eb
zI4Vd7t$JKP548e{lWNg8@0bNyUxs#w!T#SOzwr<UG_1Rh=LG6}vs~_{s~Z-}V0~-S
zb?*xQ0Aj|wE@YWlWMxMc<6bX)x2U<}Cz?P@{{RVuxXO=iR<Fb2%fO?1;c;AbtR`7A
zgMnJfX)LR}M%z1aO$^wR#4}DwdGZM9RGN6EVt0JUsjBH@NgKleeQB4BkSSIF03v`Y
zT;1keMfXR1(nBn-^AnX7NmR)u2U^ip+Mof_q%1g2;AAiBOXkSkuzFGeeJLe#8fR%F
z^a6pE?j_sDbK0u|mK|_SGDmk}%@l(@_L{Y6Z1Xaa9Gv>DC<~TjDv;&9DwNU|bKC1z
z?rkq)jdN)zTB6Y~Bo!y<DS-(YqaM`qy?XIR4tvr84o9_Hwbkw|2Eygz^gXJiqvg)h
zDv>!IaYzonEmG4^U5~dXf(=@Mq_KqgAy{?BGh8}+t(EIq_8PO=fRd0?>q+WT(Abm2
zS4!B}x%L#WYWkJ!!p9ciJD$R=M{8-R#Ipq)j;D$q6}DZL)U1l<X0O^~v4vjdK+m@)
zCb=z7Sekj6p>hD|D#X@THvpHJxvG-bq-u9QO*;#jnNNFi#etqqdf?Q4V{?~t^=ey)
zS{ESlGt^W=-j#=O`Q&<z^q9|6pRFfqN<njD!)d!#$?LYgKGcQT*8;q&M993|xQ;l*
zdM2NA#x=`i_sx0vj5(<tIB8l(Z>G37`c~SUuc)qTOPz6w=wl?PuZ6@xsUDMLgRObb
z#CTWDM`6hzX1x>|<2-#5ya>*@Is7_ix-yw^;-X<&;b)ag4?QYt8K<@-Qw#~t7*z76
zO)@0eI-DN0_tJu#EYB~R%<TL#<0R8uLw9en82rq&>6TZv+JpjIX%*GE$ZXe@S?M3z
zQ87gulzhUUVW?dAcI{=0c#JpiBRxL~`E17lPNd%_#CjBF+;uyz7sRt@t_e87>0Ti?
zWsrg}a(MKwYrfSjb*~RRmh2AXZaa$cd!T;PFJJYBzLSKM>C%-sbU1PS8Ae0Ttu=WD
zpD*6_rYNtrN0=GQd(?^dYBScKA4*~xcw<2yEh})|^qJ$<h67iEJJgH^aZz`v3F4C(
z)%XH-hs1FX0=9P&eXHC$F!aTI{oz@5c#6b~gSem2*S|)<pgzLCHRDQuy^N1%0R6^^
z$4XQ8b4^fBKuM`K;1bLcM|R@A78Ip9S}5+h4@T`nRcUn#ICGh|u<VtcapD&v7S{Mb
z?TYm1WcZrDX2eRY7VOZ}(Vt6@5ymUe&HORtSe^axTH21Sc`7hwU<l_8{VR=}m6M#3
zeQWG;yuMgUe6nW+da;|((vwg}lwnSN>h+WFdgeE6aC2L_T)A)uCl%>(T3p60=xq`=
z)QC8y1o_7mIpAj%=}?kUIO;@&m%T>Zb*Y#VeJPBgl=IDNEJR{w8ZDJs!t!y0RHwW0
zpK$9*dpM2HQhfzs-pz5ezQ$49n&hcoQrPH)E>ZfXt3ArFc|C?Y3gk5lkR0zl4teid
z6Wr}qk;&RK-npBrlQe{!;B>B48yno2E}Td<Zq0NM#4aLNWci4!Ju27Ekj%jC9R+j<
zLaKpU$3j?!10H(Q7%GCyeo@w?X>z$FW7e_tTh2VF{`Y)P#8cER{Q0mx>hLN{6$M$_
zpzdm%5WU69#DkN`C$Oy}50*?ycoicgjZ#L-jHvae`Ej8eR8k_Uum1pAl34@^xaa+v
z24~+gAt*Z5c;x!jvpJGRe_C`gAH7Q8G$twu8$AtLnC%^En;f1g0MkGey{PLz35r@V
z#UY>tq@y%v2c-Z9wI*_C$G$0hQW%+~#T`d_KMG&~cBz)#o38?!2>Je%Y)BMS5X83w
zuQfWT6&arthH^Sla4h!gO(b;1Rx>g0NM&q_0JbqpxB*o6lir$Hz33UBB~Upu(K_a-
zb?-@>(gN|BGe_DGa%z@oxikTI-KeIUzTj0rGfR(Z0I~L`J%u5;erf<RX+Rn2Ko2)h
z>rFE|4oTvhjG98Y^`Hgb$Gt{a`kHn>8ca|FNj~(MIHw++DKX6eCP?SK8OWu<=7OiS
zAq>qF;F;}9<(dFz9`p_={#VkJMrat$^kfQnkBV?iiU5l=rli;@LJvv+hl&97sf1@V
zqCaW?b&Q59*q9DOS9=Vb;Y00QBtVIfjy9gP+E_7rW$T*fs=e!g=|)<ajmq41=~7Av
zW14JyaqC?)*(~R-Q*4Z<J!+e#-|(%gq*HMGbnjXB3&$e8SnOg`#s_gmDc{42ZYscV
z7#(N_B9|1M`_Kb<29yqINam0X8g>hgso{jb@RB>!0<6G}>BEIumIN#Tf0me2lTQQb
z%{90+AUAFWAslf*Y@RbmClstPwB-BaBZ1a|>p=&K0I_i}l!a9Q0gA1RQ_nytp=!{C
zr2zU-j8l}=0Ma|=oCh6E9VsZVhsc{$b5SznW}hL-jC82mJ81x@IHh5OO^vYF^{2Yz
zieNW`)|84*=T;#Rlso?bIsk*O(u2=hRv0)2o7${H!Nxn&!wQXk>B5)~$2}=Z{uH3+
z)`Q6FK!)rlJ>RWD!-}wZOjA6pscplK)BwnramO_zfPiVS5*zWUoyOvN=71~oT2Y+P
zI@0vTAQX%PKyO+PBRS@q`O^W%lZ@2SG0rLvUTSDbEs6k+L5U9(+Ll!)%nw?NtuPcE
zQ+j98o(6IJsR-tP8MmIbBAik+3BjZ>?l`7_nvsDcr%H@<rXp4J{&ndd8JBgM@(3L(
z%@-#luhP5E2gpn%N$J|YXNVzsS37Wz-a8Np9V$io(hs{%0Qy(OHhN=CF~BHu(-kW%
zAsOpLCCe+YGlGCm8TP9&#kB$3jMH8`Hb)gFJ8NpSF7y?M&NEcyzP1vyZtAW&3cOe5
zroFr*?r8FAV<psO9r-*{9D~}N*bYGLQ8RVzTEs<Zhwk6$SVl6eeQSDCpUSaj{{UKh
z*U)9M_iS<E5ak$J(b8LMk&mTjhREsCtZA-A*!j3T5nZ^L-kUI{?IX0ZAi#0WOgj5j
zOBcu>W~}3!SH#s;lRZVTG-vmVo|&r`i@MFnwO5UB)oy>9(ZT2zu-S~yfxmP5)gt>Y
zeQM3KWEJ|=TaZMBg=qzFHezh5)H5g&9=J67R}B}ird$)hr(X1|14;RKr^0e79Pla8
zADysGD*+)mqz4|fgmP#c(g9dyYFN%;@A%Y5o+?OkK?j`B0*((gEN7l-Fn(_T0F6kM
z6W9vciN?Y^(}Neb!KBo%A>2m-p@vQHp7o+$>H@v7Rl3>-IjxD8b-TB<VuQBfSa3n<
zTS#}?bk0R+w-Jh44#4*9NB|WCt+wg&!Ou#NHCsSfgyLG3UbRj(#KWE{<b*H>HJd<3
z-j^p7W|MKpN)Qi$&hj~_!NXNpjwQuUAvxo{CWcOjBhsS0;t`DImJ&@R&^|~w=}Ie5
zD#Y2gRd4Q$)pBtB)8jb>O)^Ent&$Ob2L&^bJ?e$zzc|Mraro7XQVL+zd*G_T<Gnb=
z42T@BJ-DgkB(EF_s0~RI6OrDk!nrR|_4S~0%^=C?&M8U4idGAXNIX=Ea=GhK5zl&Z
z9x!Qg+yxv}EkJIxla8SAR<~ugj`d#Te(AoI(Lr)e3F?n4)K_KXgB=?cpO0GH*CQ!<
zeq07QtVS4PUwuMXf@hCCBnYIp9cl8xFhb0PFR!IO+X*VRJM^s?UF3@ebL(33G7JEu
zH#Hy_&w7?vz?AbzvmNQF0Krb@6(Nsm{b&iAtAQ6jl;KhY#&g!5k$`z0g$anRYVMWA
z(LGAkES!!FU(#*KZQyt2l}US`Q`Wv~p8Qs3&`oRVqZd4nrDqi5p{$W)kPZMHYFo&k
z%MRUryHhRDh7H?2>qb}%)})_G8xevk!~&Ypgg7O0^{FCUxC0qJ^y51NB@5}zJ`;%s
zMOuc?yj#uy=~2fR&PO=oIjwoqB(V$u*!y;(D@f+J+H#_&jBQ`9dX1OoIQ+#&H<(zh
zb!@QA%7-9RBVwayTG5M6lI08JW2Y@qn;DUcg>OPYt5pzKqRMmF3ed5cBZ0$kNWi5U
zWz5{9Pxy+nZ=z3)&%pF1l&Z(La+wzcd*t;sOsU*GYo|H`yB25T&>R{U!_WhlcgJ45
z)VlE>Da|78{{ZV&g_J4geBk1`2=tpsh{6+(TDF#uCkqT<`h~3CAURG__RZQ>@?&${
zVymW|blCp@MvxCvUB8x~{Hg^ZM#oc8^@dj|%0;2xFbq{d&weW6=n`WL!ncp7N<gf7
zW|!6^7BVByVPC&Afc7Bc6>)U9TZfRa>6Rqbzc1=dJV(uD>Pdx)gHE)M8)1y&`@*JJ
zqd+i-K8sU`{<QBXupCtLG1#u$p47~d*zs39fDbg&8i08et`;i%#B|L!=L4lnB+;P8
zaz~{kY-S(2idH=^7K@I<Rovq=rJo};b}b`SnZI?W+-Loz!2Ig`eiGMbW&Z$0SjT<L
zD7aY0UD@KCqt?2ce}}rPqZ8gm5cV0XYw+qQ$M3Z%T>k*DyJ=i3aZI@6nqwHyjL0$d
zuSAEydRSb^CB%c!zAHxC!kQhkf5(EhIu|+qbX;~koXsB~Fh7Mi_tGET+e;$$Dl6L~
z(=@gDQo<GbD5-^&tZD#)G3*5^j>n3_r)pO$$rX&G<G96Z!{8lu;xO*<L%Xr$iuF$>
z1s^0Rze+%XUwPz@Q$@#P&7$~gbDUmkSQy3?aBA9oJksLgTgl`;nXc+Uu6|?IlkCv-
zDk!*E<CDRf3=B6y@*noia(+G0>}_<}64C(~19&REE7uLQEOJy<4~s10n@W5_t%W@Y
zY=8CXTxWqpXN6X8nBaT!S`dtFQPQ5V1wuUu9D5QefbBT%O2Bnq8!9E)j!z_4c9yRD
zNR5d0t`EYpV^)b6XXPY*73@$b@)3gIkZ22>+_qB~TlX$Kh^{MBg`&J=b;0znT`QDe
zdy4Y^0240FRQKEtYLJ<OB7!?n3GLdH@-do7@rtHNF+SAO%KCk2*e8*mXxaY&>!L2g
zW)`RkVn-Mw@v1;^n%C6rZY5mB8DpN+Np#ERZ}|0-9lBSyLacce*~M0yzJ+0v(Btb#
z&U#j)S~cn9$ARc-R?)8*@ep67Y3<?M%h|}xha{ZT$C01sS5rd03^JjQa5$+Bhkobe
z3cp@!MTw`}k7F*zS>)!Jz#7*+8PrPT%MkoCPX7RePWgxYd_+Is6uz}jxc!9t7+`u-
zO@Un({316*^LUHLWu;#ROn&wF_rg@XRX*jaQtWdh>rWZ)T{8GM<D0;L3{=bD=tnJd
z_&nBc7fp35*vRE^N<j!uBv)EIC1OX-JcpjmQ-8uOr<K~$Kj7HSOU6Kc#zzVp4bYsL
zxez5m3O3hXo)gi*-Q_XIt5wv}boAk23bdn*f(M6_IJIHa?H@x-oyG{<IPG20)2whm
za=klKMYWooExcg*;;;KgJ&9OWdC_)1by)rs)>#|wqa5@V=>$WcmL<k9QL-l8qBS6P
z#bWXPMyn2y=O*6dx61^F@TaY<?&1E4FFiQTdJ?YCK~>}0gTUYpY92ZEAFxLXnsxIq
z#jKb$eKeb*G3B^!yw_8L2dygm()#qf2i4Kc$D>`A&cWBe6=VAz=%CsZWaFCO+6P{=
z;Bb8?`u#zDT0Ks1_-f`u%Y^z2(+7oTJ#LrqO6kKe`=_lO<Gn-1)qP7;AdYoBDy{df
zoA4Dc{32H1{MRy{p{>qA;*^pH)~D-rdym+}!yXc_&RL~zt5t}+Go~QNl*in$tv-XA
z2PZhFc#4mx{gg^^=o)&qQalmRnzEX8vUXp@RH3=+%?jA-QSGPPe$FB$pK1wzEq8k2
zo^9=v{{X9BtpY>Paqmc9JYtu$o9aG9JcI*<2OiX+hCbjP!l5mLPFV&h=3}t&!98g~
z0N_(Y0y^fb+rb;7G?MKdIir|4NVnkh{b^Qg9#`rrDddhhN`stqsEpXDxN?@vpn>T~
zW>9LOm=V+usiqlMJg^j8e5K(&J5lzII2A#zp-=&p2h`II>?{8OEmQNQaoEu}1OrSm
z<kn;Ac4%<-3LDa)I_91+{+AwoGfS8`O>NmHnmV4j{3{grmrVmdX-rg7c&AN9$J##%
zT*KvN_bk{4k4jy;N4;||<4rau$b6B|3a;KcvB}yT5BE(R=zND=z*=c_-&|~-I=9$%
zBe5UDx2;!i9b-7PW5>z?qn!sS=(fNI1lGm6-~}GFhZ^S_kGLS#rM#sudXH0HBR%6%
zHrd7wDeoZ)YPw1tG6z1?*;uOOPagFlVH#1If>;t%IRieTnq)h(?b4--=3M547BMcg
zh~!hT0MA@^u4hrxnhb^K2cYj>iegs!R!*g2lEU98C$Q;?)-old%%@$fLBT&t)9{{{
znx43eGJ=ux1ED_k7NrN5aNF>G#dRMJZSCQndzpUuZb>!M4NiKmmM5ay>Gsj6M1@yx
zbrm<*0VJ*$C$&6Z*{c5ltsg<wqL*5+iGS8*tD{4JnQgXr>E5g=lDO^Gxtq@s!xQdD
z+$xLs-Qrv<Y<<UH>qWxHXd>rwa7TKX?i{H}B>)l5PZj3(J}$qw;dsYGy0PchbxGgl
zxbppR%`S1+^@wjRtVuE4qVD93);EfLPq$2CZcDJ}1$nHuH}ZVaTsg;Kz%`#g+F4(D
zljzOXlb9&#Y*~Cxztg4;Exg0r2F5E!_v0j&_N{LvgQ+8ePHW9B!QM^?HCJ~v4pQ!P
za>eR*cE1v@tW>47x60o(Gm53Dd_dH-C_s`nQ=jhxT#r5JTY;SOM>Fm>817zeYWaR>
z?qpv06&%{`r7CTj>6m+t)lBrytw#7K6kJUVX&AQUmPJ0zij2tnkIqhgPH1D#Ow?t+
z*)-7%QrWGa4%<f|mPuG=ra#Z)SVa3`x(yJlI%Lu|IX~pqutZ4DyI^l*+N2%Za0g21
zbS)okv)oI$v(5<Visx+Od36;k33BDYJeKQTpRHM@m*MD!8FwZ?JRiH#x*M{wi#a)2
z-J5J=0C*IU{h<a#L=4o)eGyPVCqA9(M!Zhok80>!88%S86Uh?(=zV*Nqb`Dm*UgS*
zX6~mL6|Hl96DuO*w@hNNrj?_Y<Zjp_G@hV{Eu?r8$z}Ve7^@87mvHY@-Td}B`{VVi
zwib^nyEa0g??RP_VgzjC3=TaiR$+rlGsJe3Bc8&ccfjJV_Y*`?5sHDaQ#*F3nB$Mu
zkP$J*wK*ig+H*{9wA}krXlA9eiK9019QqO}q>vcoAoLv#GC3O=1cEz?zTfFK`-TLI
z)Ko11&%q5>tuI+d!ao|PDd!!<MYw_p?L?!@hMkUzEkr5hexTLZuWj8<RH^z`I~1Ff
zH8|j8isGDXZx?fW%(i^|)eMoxoW$F`#bgP+v-s4|Z!!l)KTPpilvtPL+e!DAoKxpJ
zfWXHcDiC=Xpa-M0Es$|rntl5fUVdfvtU|dSw6NSXErFBIN(OfjUnwIw1JH9?ak{w3
z<Qn7bZv5YramTH6787xUxQ|-RjMXTNImIy$D}pe2sZub?A0Xy{Fx@E(&_=|H{{V$r
z$T%XXLUS7PgXvZxmp>=*3b;EmB#SC=e;U%VebMop)>!^ke@|>~Q^Bs26GT(M$fQ9}
z7@!4Q?gOPh>zHaVMHdbGgY-2cI1dv@(ZwT%#s^yP{Yp<V@y|Fs*R%M|{JR+rPfnlC
zygqj?CgO9Rl;Q+^=*|Tud8G$E^H*|1JW-QJQ`(Glpg?m;%`QFZ4@`4I0ld-3r6)X7
zNGGKsh)oEFNn?z4W&;9~2DJP+Z|CdQ>zo8Tsl{E1yDOf9qFb~UQLKnnvEH?~z~Z!i
z#lFQP3AB#>wLzC1de-e&%}V1>Cz@>W`H`?BbHzI!l{J{;aZ<}p#}$18MR4eUgw}H$
z9zR;?wVOeMF3z1zbCRas*gn<4QZ|w3QmJ@}12aewN6c$h2;_lxyJOommv0o!DG>q>
ztvcXe{HV-8?@kDcv%ZF;*H3h&KR0R|ay_d(^ogC0+sOz&H#JaN+_xq8r<-esIP+xx
z02;Faf3RbB%-4=hT7yNfje!KY?t0Zk(xz;YkHx#ynDohFK<_pVdIq2i&u0uV?@ggk
zpsdTJa-$4!p47K@ep@OGvG0naZe?ur!K4Eo-Ond9!xjf4^r=foS2_GCg^ow9Fe6|Q
z3B_f|a>Vtm8Q*M8pQbA*y82ZjLV$2R=_zx^N}&^4xl5G#^In0cTqJNH3%T){^V@t2
zh|i&}s?JHFWSIeM4uYYL9U-&SwFw!1Wsk7NGgct*p(p(zh#r7<rPI7k8f{sW?q2oL
z#jL|J<s)IwQ&L%qd@XJxV2QZn(-r5Mt&7=TOB1f#HvsjoWm~+jEEP!ZYtOuI6b(Au
zBdc+eKf<-8Eo^5voMSF2pk!0Y%_lX`jD$QIL7dW_v;&L`)d4D;)QWLYFItgKM_RN?
z9x{8>n=?_2b*a_D`_&R4h1=8dsg~FPH(+tzqG`$K4rzg2LP^a~iCLqMr!;}V?Lxo>
zKWC*e47y$Rjt3ldu6erVx`3OIspMeSH9TfFDn>c!SXV}r*%m>ggGfyn?OevAsq4Vz
zqXV@{2g{SswKNAw;N3b){c#-;*<#1cqaZi`0II#R!usP)xJ!NckD~&46@&0|Pli1h
z%EK<?x6Rwz^sc+a8X{g?!6Y*n<s1xpQ_;OmV=EyVJ6%p<94_S?S2j`$eO^mtfrN|E
z{Y74jPt+`>%<sEt&&oK(TAFlt&g9FF;v%a^yBEA$GVY|n<EgA`nL&_>)w*B-JsYsB
z8-bT3Rovw($+UE;Q=__IbCc4ikeq|soP%{p&7TXv5<$}=)3tXI<S)H)ejSfwjNQ*H
zYphIuRDhXD9nD>Zm?k$KYJ_I5LOxnUEg^63995{8gPhe=9Mzc56(CFtf_dvuZ9Dp!
zu~8qr=}2U;jw*05P{wLu(vS`edr%si-i*)&2aMYmFr3$h>bgC?tE;3lxmP*cgI?d`
zMPsJIM?HA26V}_v*DYopcY%@CsR*9mz=kQ8Wy9>q&lS=~;eD}e5AycFtte(9C1mag
zH8R}FeL(lBxE!Xd;hVIN_X@ILe5W`y$6R<@TbfeNsDsdq*RB1fxAMN#BTp2ulyn5q
zaUMTw;ftt=X=OrB`y^Gr_(zB%eEfGCYrVg+kg0oc53#OtMAW?E4U(=uh`$vqqcJpl
zX!$#j9Oj(TS=tTisq*yCQ&(S2xt&hyp%^2gul1-C!@HX$_mlnVKrDVEu;G5n%rn_~
zR*GxZN}naWZS}_#S@>;9P)JeiD%AcOv{=|QgrCZo8Pn@F*E!m&x2Gbg$rZe(gaJ=s
z(xjKes95ZkfTkvtV#X(KI~oAapGvcQ?NSfcqFpY{ALa+AV_LFVKm7E__NtF=kvGgw
z<56%cy@iPze60Tfz^a7WPM$beNYDFKsH~<yFm}^!?KeysDHNgWO5-wO(rp>If!Gek
z&1l78XKq9Nn*?+jsg)ivwNBIPOP4s_<&V8Z<T2}hhzcm$zJizSuw#*v?@<Lq)p(|u
zqYc8<Y5^_du=y2KRZlDJ2lu}*>sJIz)F`KIz~O0#!_{p(xPz+Tde$#W>+fR^Y{c{H
zT$F=sgkbSZVgpM^I#SXZqofbs=LWjVNtqXtGhD`sGFiPit@IsgYC%di9A##9+7-_1
z1HrD&-2UsD^IZ<$q>4GoJq>y#oZF$_*p8l+@)?#6N`C4+Ds?X%OQ7*w=ZxYKX-;vH
zqda{pp^djKWq6t|H%FCw;MbXkUdtAfE_%hDM=D_S=e<S%45uTlT9FQM*j07}w@=2u
zLXNRKc6WXZb^BP1oa6(F-0>%eKGzYR(*=hmaa_lQWb(BL#!t)#HR+)A=Q$Pe`PEra
z#Kv(w3_h?t&Rsa^)^csR*yr!Zo-_2W2J$&$nVMXD-Rs-6?+wAIz|+B)=TYi$`B$0h
z5||!HFCj&ldJj=wL6GKr@7-FQ*qS$5vyqigrADLPuU@*b!VREys$;Ev+#71_^4hRB
z288>=y(_64lhTNeWmO7Uk6<%Z%#eYG81X<-R<sjIzq)^t-)iIUlZw3$hUFjYu5djO
zYdP11cVp!_;xKvR>r*UEEML1vbLfkj>n-#hF+OLv-sh=yIjzfYBH03}paZZK$x|N{
z@S&(PkkPb_PAx{-<?Wg%<891at$Q3EAhugr#==+*q}M2KP^k!*sG8xQw@*s(a|%?k
zw)U~u>!VUs)`wGb;#sy8w?tg`&JATxeRXui$up2gVtB0Bq;2>)t0wL^KK}sa-npq@
zs8aZ1Tdg;{CK44DGERz_X2A7hRO4eY$WjMv)+W6ZZW(4=bBxzVEw&=}HgEO4G%Clx
z%#id{?^)65*0;lZM$PnWRSg!wr4J*F0nlgp*42>_GbZ7I#}v}Au2s0w;))NF4Y=-2
zL1KKV$2~e$j;Wuq<rvl?N4+;T;ysNf2VWT_1Lp(QnD+r&EO@FKagnWu-rMSGW(dP4
zB#zWwg^?k<EIv+s>b=8ASA)5aVL@lz#{!&RXeF3a89+wkEh6n6=CO5~(C1=ug0wYl
zO%XP$Dvwjvxhwmf>d716w^L5wW9l~zG^GJM1yzRGrju&%>T5x45<{1`+w28iw}#T$
za3uu$ieeoKh@l9Jg#xAAPtu$xwF8#H`cq8y<L<fqr~<v^$CDO2w`#$ew-U##YTQJZ
zGVXWdrxcM|TSX@Qg_v|C^q>gspm<{p6z^fz(yd2sK*{BgKJ_ZyD!1I?oNkx<pOqjO
z(W)k21M67#mnLQ^0Rc^F%`lZQjw-L08vMdE40`|!LG!-S8J!#~=kD?CQ$8bJdsUev
zTpX3fXU{UR`ADD$rESL}y+%bpYq|MWow3n!$VDI^*+CwZ=X_HM&#eF<>q$yZXvm-h
zpztX(M{f9_V&{)aI?_^)VL%6ZF;5Xle}TU$Um{RBMjuf?ghPsuHcv`?c2hXc(iiDd
zuA2Sxigp5?Y2Njqx@qI({OVQGfjtk_ivg94`%>eMm9zbqfq}=?q)jjb(u)Cx6^X_v
z!Z-fut>I}J{o|i(Ql+9X0Z`Flm_ipLk&0g;PwpD%zQlu|#V^>v{u%<uJT0W@u!?`!
z<gM=|6Rs(xW6l8>qy{jubDx_Sr8Y!&HLPM!y}3p^QyGylmLHV>W{WKKZ_=0SKx31d
zywk)x)DJrU0Q#r`vA0kM2l1pa0otT8hbKAwshjcGngEEVJ8?}hgZNa%usIwGK5l+P
z`A`HNR(num$?a2Zke(3!RK84sv5tKx0>6}K^3Qs-wz9B1Q<lzV>~laBJflhFd)A6+
zvc5BsQVk*f2^0a8BBc=z?+n(;=+1hp6W5B6Xr%B^^X)(wdlYvR-Jn-QG&UpsNF&~-
zO#qhv08*vB#wY`r5tG=|i*C))YpWUqE;50AIK@nw7ft~u(t(_R*`GKIQVVAEuF*6G
zKfulJwAGlrI9vW$$@JK01BP2k0R(pJE2Ob3mgoq^d9I2-49r*Mv|@cRP~T|R7DygT
zW{rJKWmN%}D(9MmqYQMb67VV!*ELl3A(>awEK@c|UTZp8jEY7o{;Gv!#(3{pm?phi
zZt*f?V9|<P{xq9_t&oKjVvrhe86K3xAsh-!RG80tFbBN=G!B&_w$$L_nd^!;J!r5C
zxE|R)w1iN^dI9vLX3woF3}!hMC;+FuMBPEBuic`+As9U<A5OHd!wN8RDnL%u)6$%N
zw8O<T0**V=hgxTPc;=`<){qV<#*mKK6vQKrDm>&=&-ZdTs7GEY403RPtw_g@TvR|{
z)V)`w05&kL;5ScNno}BKN9R??UMWvX1Q{5lpkVf+y;=dnoTr|ZA6k0#rXpGZ&#eQF
zDM|UL0PW9Ogr1_LVsa`!<D>x>GAf<{HGXKLiEzI$1FdHCaC#cK8s<FYoYM;s9vIT+
z@%E%64bK$6jVp{!ooO*jGH3%h;+O*Rd8Y=!_om|n(&wM)Knm<h^`!5bT!K4NdsDE7
z1H~hB=|@gzZbz*EAv7Vwds24(lrP=`){qjh$n~hm=B+eXgppN<rUI$wIj+mW&Osx0
zQ~6gKoE+Cv;VD1ToPQR23h=YY-ww{aEBDVwLzU*GQ&7eCM>Q&(HGY22RB^#Hn4~-$
zQu2CI85FC9H4>gG#G?!ARac>=fN|<7KmkslokVyX)Kbr}c8uq>XqCXFaCY1^S7W#y
zl^pKNIShHE-;PanMG`f!&m7iG;^J!6+zWA8x5O*t`q!<OO4G5;h+gRmZYPSG*W|lj
zOw=*9M-?iKml5^my_$;gXB>Ar?J`WU9@U}IjbvE99dXjN*yQIG@i>}xsLxUk@h6X#
z9jfyHZP<HN2uNZ-8qr=?9gT6l%P`aBnbW2{Y8#&TsV;$z>5pcp=Q#qp6l@~ypC)0)
zOw_l82>3kX(x}+J+>Z4%<fqByaZ_Q94aZt^c@hIqM!@u`6|o|kmIb%!DWRxr6$d=i
zI`dKlooVoW^W4-*IHy8!C%qPI366JtDd-9I_Nd<>xu-0NAKqXy>s9Qe_Cax%svaG@
z8qKwkY{hKKiuUb;o+|*1Ov*UswWkku!X=dAO4hWL7yxR<U~|^2!z6`3QTWv;0Z&zM
zw~7>FlT1koT+}-5=;n-`x$98d&$&ixM+a+xdwvMxHF21jf$3S`)yUj=Bi6Iz3xGK1
zH0<ZGrkBMalP!ul0B~)R0!>_F#ZoVp9+h*fW7?CAg5V}ZY%>52O(rCW{{VE3^-5UY
zQo9{M&pcJkgpXqK6k@fN7}+?A=1z7#D3QN9Y`cZa`h6&TR<4*_6`0{ww))f;@|cRo
zLw!$rlXlad;;8E~?u-@5?oMl>jvt*8=VDZoaQ3O9d^a_nX*iZ4j^F1MYBp~(0yz)V
zQT1nih0a?tbB@&YZaY+RLoU+ZTd@BCWeKUEw7ro7t+Q=CvCSV;sQ$=%NcRz>RmOYK
z8>#iF&W))!$h2?9q_@yDBPTZdN4pB8f~fw;y{vnci3)Ryt2y4RIuBatKj9d>k$!n&
zPu7vV7V?qiU+wh^Tf;A%?#OkbwmhR<g{Qe<1~&Ard9BL!ZaUYvzr&q6SKo1R@)~@9
z4YUP0D#z+`UqwQvBotZ0Q{HzxJ}8@a3dh_E(2fZ<<e|s4ds_G>MuIJfjknlQ2Z1y;
zV&>iQduMO*t96LvXM|kYvq(y*W1L}oQ)954jEiahrEBRcO$SY|La<pvzW5n6WWj2@
zc~Fn7FK#|V=Ch{Uo_^19{{VjIk4V2`@>txTq;>Rjn+S8i?92L9d39|X)Mf7Nm+=(-
zupZ3t%MTB_hL-ly<0I~<Ls8vmH|Ao{>GO#F3Rkn-_`}1o^}3Az0Jx>UkgVB!eWasp
zhT3WU!hk<opKj3k4=RVky4=_crpfg^D}PMzj=dCrJ)b_A0=kKQB1_WSOThJc0R1Y2
z-Z|GM&cwHbeKKjvyrs}whD-c6)~~1D{#+_gB%JYAQ{ghKKu>oYIPZ*9QtSHc;}Ys_
zqyCww2B^sQQyk5GbpHTZDm|pfWLUWPY_{$|)ZzoMC#5uaLfsT4#<2`)JC5~KTEpLS
zA5!L}NTNgXpa<HYJcVRii^4t=jX!;V=C^aZ{3w&c-V!(~D|=v?gyU{Dicog)Fg}#I
zrQ9ru+ey%&j4WPbuV4jIeJ@SODQ-X<;F`0)I49D8MkwZe!o^p%gZN_r4uYBXSbL!Q
zVy!v(a0NxR$0Sj4Sdnex*@YM$f|Vgy^R-5O=@W43aZb(#I%1W_VnLtpQ%eDipTd~O
zj<o|x7k3_n(Q(+Bolkm&-9e#BNy00$9)VV@!(n+p`n@{gj(QX{TvjWF2arD+H!<g>
zZCm(jTbF^S>>jS*RgvJ$RFUUTZw`GjXt-GCfP7$J8g>s%*INgH->ll3bJ{c=D?%Rv
zX)FG=N#;K7j8Spe;EE!Xxv@&JLI~vkRq3&KS3-yG*ef6Q{%_}3pwsMa$ntF>PomPe
z?0FzrWhcpkSuxjY)wncmV&n#gPm>?*V1F}Su<*u46%~GhqmCDihs<`;xLEVJd?BvN
zK6HjL=vuEu;9K_}z0_h)P>GuFOoylFDZcbvEOJoz2GkY%Mf|Qmy1WBd6Tuo1bx9oi
zv95&m^`?>sN-jGYwz?*jW=E4_AJnfkq`pjJ2^4GFfl9aonivDz8dn{KGhqJ!g*VM(
z-k>h%_&q(UP{D_4E*2Mm)`Dor6lXs41%=Huq;)@cBh=FVloAQ*4HpXz4yV5~Zeo9>
zHB@Gi<WxN7fF2m0IHfO+)Wu|A2w{UxEUUoh(t(X5f7j4b1t8M1jwv#I=m8mujz>z*
z)fdjOb=}h^>MKidDt8LcytR?7-z-2Qx7Lsz8+jj*bu@U#e0pZ6mie=a+wlxOR<h`O
zuI&E+I>V6qcIqmLX7-74Ak=M~ZX~!|j@9ip4$|2pXFPT8YryQTJeh+6c=YdH-J#3o
zY3sU9a5(9j1ZldsQp&{Rt$E*yl%?|S$5Who*Pt}&NgLFCPAi4+QBya{Rfs*lrkWYc
z98(m4#0=D=8i_~G-|?y>v<U!Hhti?OM^B|ngmXv>FrB?KQi(lJN~|OU+v`tP4g6K2
zVzD@rIl<zbB;aw<p$@;^Tn~CTCtUut?kf`p&w7zhH43ty;{)nyMRg-Plw;nGV6kNz
zoYR@H-m0a{O86`eI-KH_?qJ9I<@#ohVc2<MdVaL=Ar)8cP!IWP2jfZh>rwvzEs!5`
zMai=*7b2Qm)kf4U6lJ9Wf4q1U!>ib@D{~q4%^b)%OQ4b|Rgc!F4OY;Rwb{SjT6xqX
zTo96D{li7d<u8&?erW+=%}_d-ImB<)qisS{(j4QtrEujmcjEw>2^`i@y_}!*YCXLv
zzihh4-A~4gi<HyPG?+d5de&gMyCd(Q{3r(LxoMCo?YBJAxLDIC2e0C3JvkMc#j=0W
z7msRY;to9K>BcEsb~TAX$v;|QkuY#YWsq2W(@1|xiMFrac@N`7$75W|pWg%OX{~V{
z2h0GhZ!jLe&YR|B=AFf3bL|QJ_4*S{7m;#z1B$|Va1R+Bjw-v&AqN@amB(YCeNNp@
zH-40#+P1N;&oCca<tCO=4kg-0wPZ|^E>7}E>%8WdFzk9XchOD$q%@yFPHUIW1-ysp
zTppjVU)VCCmNtlX+k;)DhQDif2;U-uj-+Cx)M&0$$-dEWau(UY6H?~zV{NhbB#N{O
zvVuAu{c2P@PapoO&DD`gnka~`T=0>vyEQ9Aa*7O+L^IF|)C?Q~L8yyEDLC859`zpH
zMf*6FW7DqZUBc!x9fsZ1gGae$DsK)wldWr8rr7w%s}V0bsrIsA?9r1RfJh~-<Q}6K
zs4n!QYXi8NN7|<f=Zx1)!5#kq8moAL?Pdoc?d?_0!;u~_f8t$E8>fwBPyyg`#b>vO
z^+zW+BzpnHPvVGtopyheZEtGEY=8ReRLN+%b<ITeyKMU6qis_5LGxV7evOK$fk#f%
z5=?I{SYz!IelBUI;$k_PQ~v-1G|UPIwF9ub+?<vt>c*3E0l*x3($aJ4e;Ps)Jbl&t
zr~vW6r*lbzlR(1<G#%cwV?8N)&;lIittclQXu%wu(&HUX0DTo{1Z6(x$9^$a4U#&N
zx%RAUJJn(adHxgYTUPf$_$IuQ+B2pyS~1^{0qfe3UaYHvaz2%>a}S!hZoZYx-&oB9
zG|`-|U!@_Ii;zuA9Hdrk5}6oh8TG9g)bWu*0@^Xa$*8VAb>o_qTjl1fTt3*_(y208
z#Q1_C=j9ZhI#ilPjpT4EhjhsKlys>zHS=a2`Sq)j-ZG+qxFBPS?4YiWEJUrKrrJVx
ze8s(LH?z2Ixj*nDQnkakuM~ZvTy+?&{h7(kS8FLxDxEsh6&ZUPv}TZf(MWeTGAa8o
z<}0)=pd9dhDS<LG&0kR1<#R}21p0j__G0ELsR6ef@$F8X#HdEx@!VB|2T;8!e$7wW
z0-3>Tv3YZlr#;9Oo1SZ?@g<{2DzbsJ@DHtXC-khOtj>r#fElOl&L|7dT6o}-=~8G!
zSB%swPDmAH-yh*nF;o6DT$Wd027je6jB~|KN2lRTAatrkG(t!fb{pR=)I_J{9mjft
zJ%UBt0Uq@|_=C<30Kj3+I#$p!k*DD{7hWc|SLCh_>(A&b()@LFlB^KNf>Q*a(!A@y
z=)+!$MaI-8cjd?PuAg1FH(JARKu?#0*N^_aZ5ZB0QY+a*2_q?<%g0L6TN`FAl~BI@
z>Yca|uJ3O2>8}3(c5#u4=`tg~wzG~V8$clS9qWp_Tuk56x+|;CF%CZHJ^R-=a@*Ok
z4k#KR+*Id3FzHi8s7{PIVgcwX2IGoo`C6t*<r{_sySMvAxxxM*MP*3XJ;&Chx4V|r
z*K3`J?+!Xui`bQ+^W*4vAW<C&W^rux%{AK;Q(KYRtVC?y^qqUtjW-67LWU^SW(oYM
zLuUZ>s>E}}IT#FsP{6Zw5LWXSqjbepJXNSqn;({P4{EI_+U0qsm<t@cTCbz4ugY>O
zD?Yqci)qTR1m#U<Qas3{%aU=|r?p11x;8;PRg#;>AEiL?{eG3k(W+&LZp?>k@$Xha
z@7L>DB<(pJs{Op;NWktrX$-U*BifahkLyvZVx?1>Lmy{5+gt`ecRc+ot<&dOR6Kdx
zTx%~pbgd04?AuOJi7}I$W~HKz{?<&#gUwD)PSurVI5<AMn$QingHSTsHWsGdBXGl^
z>s6vZDfO!gH^+|j(3xo)BPSJV+D(#U)~Leyk82KAtVG|u2c{2d>4Um4k~d<LE1H{d
z#b!eLK=i9o$y7;abv8l_WKh30F-)5&86?tUJm1H!<=D(K{09}{Z`T<7F<!^<5`XkE
zrF!=V72{6ZiS0rV%;KB~G~Aj{c&ZTY1t{W>bn8pgiU32`7^CpwkF6m%6aXLRO`w`-
zGyt`;;Z)zQrW+U>RxW<Ez2PPi>d7Y^cGW|2XYiiYrcPvxMBr?!{YuHLZi<}kKQ?ii
zx2H;qg@FNuJ5ZIbBl(6{bw1U*Iil>$Onx-b38@Ie^rIXMaZq#=br^TRe>&skLaad?
z=DUl9{n6xb4RN<Awr2x@lZ^JRTIlMaL2o~kHb6Z3R^nVhS9H;H>rv_UksE#G2|lK-
z7@@{7ikR#b9;H{CP6XyW`r?>ou#k}+6OT%;)^L^N52&UcGR;($BxBUmAk4Y9x?oMT
z`2_F)=~>Tds<At_ZO=d}peto=2#<Nkxu}k+;Z!6?8N~o|!%w+p`Oxxt^{0(J$76x%
zT5{jW2KE6-<L=c-ukv=BW{}F}*_7ZBpL%1!5d7UU!KkIYXKp`QgUohsz4%iRQu<8D
zRB$s?3H@q&l3G^JZj}e)R*7Li%`SMP6vQf%ymqeFNMyOTL(`@>t|z5*T2<r4Y`-=!
z=~Bjyxh(DB`P>G_Bhrtw-4-bXM1kwZD?Z=E(L)##N4SporoO*<e=f^tSTFanflyhs
zZ@<kFT}`n^@X~9Irrg*V<HM3ZwUn09v0t@aZ1oGttvfkvqe79w&nXxTdCdz(C$Z=3
zxMDhc9@N9dX=@O)dV_9_khjf)S;TYFyHSG>(|FD?Po|NIp$}H+&sv#!;-FKCm^L}8
zM6zC@q*0!g7$A-*>B+|xq9l+g+nNE|0HEZ1(@$z*B?r=!bL&hE$GtpenIqM*YZq0F
zCEiCyt)*R~(~6_2!@dCB*S~t2k-SQS)Wjzg13?(09M=)hD)l|8#7X8bUVdY@k9vhh
zD@RH(MXFlOGXCi#%L=%lJ+tAIaa-Bp717jk7}rOryzh0s8HXK+sPw4qj-M3vK|W;2
zBfk`B5nV93Yskuy$7%Ne03x!U=T$33YFf0N@9o+<nDHPRRfj|GSkkk{8zhmHDtq^>
zy*=WNM%vi{iq$_71dU^57|72Qp{pit%R`mCmm;y{Y?F^#yL927iqDbqNfpv_5V*?`
zQp7gniein%twxwQ6)X;iKujz8=Yd@!6O2|Cikl-R80R&+A5VHfOuQPqZ^^1^colL3
z(vZt)GDTR7a4H3<ke-zwPQ59Z=9~z{ChYrAGD!OKikMU=G4-i|<Gn}@3z|)|pwj0e
zfI06N=le1*t$3ckF{!{oAw%Sm>0Zs_Spw<y;PfqCJ>pAaJctwTvkrZz1Esfl1Th%o
z1$f|&m2BO-X_nc6+?wR!f>@&3)5`o~JE{Iakxt@B^k&U2Vytakc%sG!DJ{f#9e~Yd
z-FVv38!<-mf4a3oOFMAHg$2L7YOmSQ9!5vfmoQkc-aGR{2;r4~0aeF|p5>43CH!zI
z$CYXa`mve_g;e1bQFc2Jja|t5kN64(tuJWbKA5LDOnue-u~7!Wzyt80MW5|!fZsHG
zfbUYSxiO2C8@($%n|IUFnVu<#B)qwK3m4m-!lP;K5Al*I#FPFs5C`E!g5wrhm4gRi
zO=d025=}ghttQ->IYQ)nX>xrj;9`I<aYcZP?gUa5?del(0CoH+q+s-?V7S1%=8k<T
zObk+Rdr%h`ez>H`_os!)q%q^GQDG6d424L@u2T9xF6EaTX1eu{bKrCIte+BC#{)*_
zF}tk;Inns$gH9{WBMu0~A)6W|4toz;-i^aH6|-1+D#IeMd3H8&f-9xB)8bK)bGZ6q
zfF-kbON1k_uS3%&GFx@$>0W-2d2%TS^RClGlsqMSsOwl%rlq+`Ryr$3+!%GisP%;3
zrb<1D{V6o_^Ek&^v3R+$lmVZYrF>>%Pub&BJsMA%2ailJ&ZKdZimFCBR-OI6+203%
z#;CIM^slz0?*z{-TbuqKl%@5!0CS$T>WV=MM?wX7{*y3<M39~lvtEk_iLFFwglyn)
zNX2~qb(ht|wCSU>4^lB+@w`E3UmRh0`qz#4!YK~0QDSKr{{VD-YtSw{Nhsar?NmL0
z70+B<J;Rrm1)HxG(U9OO;Hq=X&l6QnJh3<tqhH)8#2Y`~spIgx*v!`$_D<i8b<B7;
z{DoI=Ngkfn^|Hpz>~JU<cKQX1V7vvKcP@FYSS_vLU){u@<I;sfc&TGRt(I`O?OgJ&
zId0135GNmVpRGK`fjg7*sNU|{7Ws}y9jXbnXm%A5oSufW=40g-%W42rU!Cz;^4`B=
zihxTbxb5vyQbwy?#SzX6Q&(4nF#XH7=~>}OCnlY+8U}7htlI@A$Y6f7HnDC<V{gr2
z6Xo^K<xMiGjJDuDlvoY_0PWDL#3Sl!KKk@s{{Z#tG~L<%02Gb+QVYvj*epedxu8c!
zqvUQrqM)AZ?6;0~XWFIGfeL?>P}Z7LZ~|lBGyy%vs${oh@`%XqQ)n8jFf&DS0<sgq
zu6jAP=gx3XP6ldwcSev9bNE!To#fL;J-Zl`BKivFr@N9VT|;y{R;7cimftrA6_2Sw
zI?Q$^@J}RC0y!_Gey#a&QH!?+<rp;Rbi3PtNO+?igK}z9q2DOn(!fCPnl3Y$)ve~Z
zkh&>zoZwb#SzV9$cRBis>zc|!#Z;?$?L1N)Hh=CY_uWhmHSMn#AL#i10D)6Yo%vjg
zaDBs9W|~xta-d}QCZ<giXE<h!PobtGh!$FlFZ#4!Vrg2!@B#Newc9p{D)7=PdxfT*
z84m^9@}>tEEH1msgWGOuMX<OdnKSfS>{CO4a7!@y^HZjk7fqjuqR3Y`Z|u2==4a>H
zoVq-?`|tVJe41<v(ltL*N7>_F^>Lv33VH#;e`0O`Ge~}>p1K5I#IhdzlU<>Rlk%t)
z34!uUk&mq_p`4)5?Z;bv#B{|2NJTrA*%#|wIS{W|V+ZR|v)bpG)|JrCZ0RmY`B8q9
z*3pZC2_Jy2f$pu8931<KtZ!i%&QH>n#bcY7!$iNyE9cW~G<al?OH4<#Z?>SJc!{y^
zQMRBzhAw`zTr6a-hb`0%<%sp&igM^S$bRAcYQ&PuBktsTRD$AV>4C?mG+cHo4IU6U
zjX?CpJNqIGa|mK8Z$4%tG{W}>r56hbH0V@g$pBJ|Xw-0uKMH9}hW<18(hGT=xnf7w
zfUw~TXD4W-D;VUmnoqDxj!8b0_0t@Wx@Zd#mVk9(_)~n?ha#=6lPN!N=dd*4q&Dmr
z`p_#BlHma-8>xQMr12g-t4L_XkGoD9IUe6y2V*Q;vo;bU#;5XiHyK+4x7T>BDD;^S
zs|N~4d{x-(ZoIr1i6509Ikz_m+hm9-6wxHacg=Jyr57cecO6OTN;I^{T!K$cywE!w
z;~CFJVN78;9ZhwMpqA*2Pp~ySei*rOHbB_-2ACXChC`4tKD3`^lh(V@;TxyMEu{Yd
zdacFa%f}-&q+`_51I^8xj7J>$;)AC<9*thBAAv4eeq_P+H9UR;m#L9g@CJZ9k#xCR
zjk)@BPhB0)SoyDEi@>N4&vsAz092#Fw&=iltbMjoaUMRp9E`j~--S+|9+ZRfk?g{~
zia!WhD&j?XH*?A9R^sr+of?nyWo&<WvqjL)8IQxRcq%^%o<9#c&&qiJ0ASa&CW~br
zHrqro=qk$DLaW44@z^aFLOfzW43-1sWB&jFIIEF(Mphpsv#{;*^{-k`rLd?5I-FFv
z^c1c$$`ip?k^#2JaoL)$#o&9=qkJ)e>6-MM5$b7nZX}UP;bYI2z|x)xjZd{sJQl0+
z`KSr$^7CE8?T><aJ*WT%<wrf}<^zz6z{$9Iw;zX>R};aOSoxi?T{k_2C{j*wnmK^L
zkHR``?3j<#nz0{-bhQ5fmtaSst)QnpDG9;Gd83#tWgR0;w#M5y^VnjgOB+$j+Qbji
zulY;6KdmvXk=vip(zwVL-3BonW9TY%P`wd<DwQD!I28T39@Jb4<Y4pz@UDNxR*OEC
zUmKZu!0lZlDBa2YDweHovgxt_q_!$0s2(pW?Lk$6+7CllFBfF8DHz)1VyV-ou?)=B
z6zx|$)>j03n%mU*fqL;+pma6r;q{4>h#QJ;y*bWg!Nw`42a4GeIe*BdC)$u4A4+#x
zu?g3`7&LVBr6=*G0;nxWexj6qRG9ZP0N%e!8zh=BNPAGgX*DcgFvq1tI(pRbZC*`H
zz-x>g_oV1EQpz*P9D16JcByP*cY9J)$qPukf$7?!U{$C<CNoMYGfEFbR3T5}LBODL
zD8(=aAV*LGQ#VeB6$WtBm=6SIrVWsBP=n9CN(f<|MKBmoJ?PIA!oztK?zCJ0ahhC>
z)Pw6m_Nusr$j>z3am_QmDEujbGM*^TSW^c|aP>7p9NZd&=QT47j+Gk&k6}rSVHvAY
zGZ^qV6;--ak+JETKoapF%`|^1bjo&ysMWZsxXA}zv~;F|DaMO{9!(#|MswKFR3IGE
zjwx4~cY1dQHyJdfanhfFdeRZ@X^3Vq(wpBsDNo}@2JW<gxE!=#bQr44FywPqp^TLT
zezg;+1d=gAU_=PUYohS0V*K(CHP7RU*6{S(H6;VDTJke^Ibqq+hjyAhQUZ344NSSu
zYOic}MyJ11R)EV_=aY?(VGaYF8V~7C`ce^DjERTJYM}eoZHES{sQHh4dez5Z40jb8
zTf1fW-S1MI)KbpzE^(h>TERE4j2%ZQcZ1hGsu28jrPgLXa<N^c_NsBsk<E8TB4wTU
zHCp$ODs9=QF23Nd>>ia2D{B(8f0atd-|?uF;j(j2C-kp*>~NhWlY${TvCb=Pn|C?I
zb5>25<9rf*E22^iVB}ZG<Kb$|^k}=pwQO?2wAb$r{{ULdwE(vV6{tSw_OCKfce*vX
zi>M8^Ad(JS7^=_8`_;WcNtYw=s$^kvj@8ta&<?fx_@~^L^1fs$zNVXO!Dhie*sE7$
z8)na1T!4(&B_DRJgV6r~D#MO_j8{B^&1gq9<OejRNsQLOE1GBkR8h(rA&PgHxatK*
zv0zFDIvPNJanhT-5lnei21&*bdbm=O=px*QCp{{y+bD@f+?tw60Eu6>TFkt>LPGDy
zPC(6im>M$XZpJkwWNyTN(N#KQy<<q2nAVlN;97H*Be+_o*0)p0T03bzrn35_UT2{F
zq9APIty#7g6h4)IkM#uoDX{5!%FdxJmtpEl)x!Z&T?Or8jK34%Vcy5?;MOgz%48kG
zA6oPl@T%$&;{0$wg-s-W1ku%ld2f;LT~zYvC|XRHh({o^qc7e9uE8eg_&KhvJQt;Q
zh57fZaQIVAiEtqQ0KSfD{{XXm$@<5U#F<BOe=4(WHk}kjrkDx64^dr^&@|Yve$5eK
z+~Sd~G|N-IM73OZBc*E$1Y)&hy6yBhlKX*l%P8j}v?6C{6bR()$raHZTSJAg*H)^3
z-dahuJvLpY8<<Gz*Mm|0n@#l(Y|d4q)gDceTQF1HiqeZtzjO=bfZnWn*GF%EZ1Lmm
z5u8xhwyD<UAV1!&pQ+L8L#;EOe+^wq`;Ed!&m*l3;kFC|Pm$j%&1}i9X;$R<nuGwK
z_NuJDFYx?X&FZ)Nyw;yrqx_`%N%tr}h2vp?JcrmVT(a=apBL{ZgUxf#&&VG^+Nn+P
z7ek0*F*LvKty7ocZJ^=}K6dvjT0#(pkwS8BbFE!I&N1>@#s_RIO0mM23lgtBn63f-
zBi=I~FHclX#J4|{RFlWL#H@CCG5QQ<s7I%m#DHcbBmLS?g;Z_YpnetP(s;*Pm>k@q
zf4a3!U2|5L{MwAXcT<Wr1KC57_nk++>W1d_*4+y{@q_;Lc%#dED(!pQhWf~AxwI^P
zc_eSEQE3SFC-EMS9(UhcsU3`hsNDGL!}iPbUMqjO&3Qvxsxb<@5rgv@Xtz*tv41LR
zGU^vS3U7(}TDST&wDNm}s#E+;x^e!Erm^&AZMDXTlo9?FG7JDH<PKwgPl#S2mnxR<
z#yw9z)~UCOyiD0|w?>)l7ykgQS+5`isUJ#M*f)B7qPcQSYh9cDW~(MWhAOF^@&5qU
zUtF>8i46zqNKP|O!EwG)6Ov?O?#7%FKjDpY>U&ZL=8rR)p#v!X==?<@_26QZoyLIs
ze~T0V;4n{rdT_w)Q5%Sce|Qc$^G)-!ov6$QqUMl`3Pvz#cZy_o_cE?h)=d2>%sM8k
zF&Km(J;~`#;6hkrREl`58-EJjGiGf<BnQ!RS`hd`&mX?k9lzaOv|KE6!PI@`z@{6h
zNBpz{2Nl`d_+!J-9LUB-?~__FX&xGb8*NdTdZ{#<9gjITQDgvE=h13djl}JU?WKHr
zEqY`vqucP7(XY{Jf9)$&k0}`+MWu1r^QiP)YErv2=jZ#xRmglHu1}9JM+ZI5Yq@P^
zB?sjrk4kH6aOD2!=(t$rqVN^r1J2YV$9ymU0A8(s!U1lGJp0+04!Zyqwso}_#4bN7
zc-F@%&^rU}D7fro!{J>IaNh)vw~eK%N*x<TgABTKSqC7M29dAT<lZ7GI{q|$w48DD
zqTypkKeI=H6|w>Jsl~#M1bcp!l((dFfsb=e{?Q6Ev~%f7;bT+nE<I_ouyy4|ed{H)
ze2gM?>ro9>Kz?M;<3+;8q-B+`d8y2sdsZ3M=FiH64@w5Ba$n_)4EHnzjg_A#8wozt
z?d)6b)+y9(daD8WRA&0~IrD=3JJ2(AnoRM>)KgEIN8bEEtRtvhV+M9%>z-+!Yn=6&
z%>Zt&ojEO$^r<187;JNg9+l30qF$TWk8@GUBewzD9@GKVGoTqVr{_?#@c#hMb^Pm=
zC5ijZ`O`=zx8i66r)lBa{=5&ZNA`<<`T1UbE1hn7^NLX*QG~}Hlnm&N%st$n!kTYw
z27Y$q&{hF2jNtxsfSiuB0nje1Y&iLc)Kku_0O&rMu57U#Xb+B^edr4t?W`dG0G4du
zQ&7IOh2k-h=~%_H-klt=q0Er8{S6?osM_R<_aa6<{8B!*Jd3x;h-c8&V@eq16CQ$^
zW+V7FQv&3Al*r|Q9>9uw>vtu-{A1{~nD-l-Z<NE_Q-o#z0EiE*0AFoh==5dBVpLOG
zRlF;YH)zLWREXMo=9350Gy!k>M&uFu=OfaZZ!Su<C1yURs{nZUX;}LaPQi1}{6-vJ
z`I3Cj+2nsp!EOOK&pEEE#ZaFzHzS<qfzz#Wk`Q>td8R`ofPllVx3zi?hwmAz)COao
zNZnp+jfTPCp7q&yT6btwK?JS?{c%8!!JM+-la9ce!qo<G{qI3rTVH7`+~c)i>N2BA
z<(%=(dQ(GYS#Okj`&3GPY}S>WHV-I!sY<W+dewbP>|)?0plz$pcV{%&BR33Z6xKh>
zr64C1;7)lIfMbwX=5nLdRjXSYJGBfZkdcCL-D;Ho0CT-x(25U{n;rU78YVhC3Vv6V
z=hf+_Oo4bMkGAU8Z!8YKl|tlaj+9)h8UFy;w%dQ@q57IZrdt01&m0eK^>`3X1(bSX
zmBPg%rrQPkhv}My?cy2RY#ZFxnVups$jwAuN$Hd9X@!jCwv^=g5k@^!=9JkP1{)uT
z6>zsX8RnYOFyeqI4L08=D9nA>)S?K`U?Pvgq%xcnQI;lv3<Vt&eiVh9G=%51H2Y-G
z0<#}_VUf1-P6ujUfYNY97ZB1(rsoGV^0^%b4MulliU3W-deRrj$74Xr9<+r|rbPfF
zHgI|#;F@TDaslR@wU5h=Y9?2}9FOs!0QSkvH-Y?A?T2U_pTji1LlgH%_B6nVgX@Z8
z5~i#Rc^Lh}k=l^iTr&aWzdoXn6-#dRrZGEe;jp+Me(#?29XfCB;LrwBpk~cimLNy1
zZJjPsdSLs~HjyaKS#UcF0Oh5F4YX#ftIuyP_+~M<>IHQYXs!qP!}yA!HjOcD+weUI
zsc3g5(|k)T4h73$d$(g<y_Tm9+)Bt)40k-&n@OeMm2;m_nz0St-JAa9@Qczh{cAZy
zw9if_Aw#hX*8{yxz5y6jj1PQQBcto7Bx;uvZIJ!)#=5IG?Vd2^<hql=HO$tgshW1`
z8UgxJp~GUH9wm$gWyhv!6?HOT9G_}PWw0~<0N1Fl6c}7&aw<^i&&)oR8%YZ`$9$IP
zqN?Jt;+``=n$c!myO*_dm<0Fd*1hs?1r16;G?A(gR_pmw)8VDK`L{+?_1#vgq)SJD
z?ZN2B@TCw+Px`4p@0$7<J|5aexDvvj@EW+D1k$sHxLjkAflu0@a-TV^h0An;P2EC~
zPa0+O{o7YQ-7D#Md=sGsJDo`Pp}aYvMTGzydI~+La-TM)g{jH^04|QdQ&T5~b!h;_
zu|Mwfiuye?-3}JYMi~0yoCc1c^6&ouj?(s_%6#fPC90CZM%f)k!&1lK%~{l+DMk)3
zL9e1#T__GMhaS}Sy|D}eTJHL;F-zKyl=<mA2dgmzsrDgi+<y*rX%1VC{{SlVuX`8p
zqWreW`BRRg!Nh33;8OOiIZq5vhFXdH+mAf}Ju2K^3U1%;Jfl8?rF$^dCG4sBQZA!8
z{vZ$gwEd$WDdcwgu}Lt^hREq#R=Tf3TyfM_DKrX~9d|cub*oU>P32}bAa%g+`PVd{
zmdB+TT<)RN!=@dx^zTb0#_`wX^sai$OB#ITx(tKsS5V2jZ#W{cXweUo3i(6DShl)w
zyIACU)GKa4`MM638EuV<0Ms)P+N#{kxlf?{s<X~^fz#<#CAh-(=9r3(zHQDb+CZbX
zy;rkgH16MpY6S<UZ%Xv=@w5*!6EAqKVFh@=r558njw*0{dQuLR&~n^7g!)h-1DaBL
zbfr*vpa3eKG1t8&(N7zPZYaUYqQWBE#~G&(eX00A{d!O`r;o;%7`pAJ+AN8{%JZ7w
zrHHJD+}EjGKqZK$_qa9ZTC4&ar$RA<gM*H1o~r6}QjtV2r8u_@>xyo1-}9#KC(^mj
zk_k8G1Fcsf)Pj0d=3X;{%_GC|{b}5mildX<QgMzrsU9PqKU!%Udgng1NRqQ0o}>z4
zc2SJyo&`-H2cgYLV;aeO2brCMMJ<Zxq+uhe(CuzCEj=&g*cxIuVT1m9)up}{7q2v&
zGxJvNFLd^@OJ<ljRrzv8Mk|w+?d;vdKKSrHVbZ!Gxs;C2bWa#`ZNQGksNKp6k+*3a
zb6A%8gmVv-@O$9Y@;fs1CqDfvV=^n2F2v*<_pIr8ZNsHmownyM_-?9h<gR^b0UHbo
zgyfUOJoOaPaoidP3fsO~w`Xu-Zz+f<{c}`0Hbp#u$((aZg^BMW@*ml`6<lDgUX1;w
z*I~(Z92%q*fx}ZkF!j!VN(WA9><3_KHyG<o1Sg)qg&=GmqJmGQH1(-qPLdU6aqCiC
z4ay`?aop8qJk-%Xa)j`E8j_0S^GF+M%@Pf+R-2QGR|8hoV<O=CW~F|oHB(O9bJuTt
zR*S|tBN+FtS?*dWNHBT)D7T!#{{YZaq(XC*JX8jtvsokzpy#h*DnuZ*I{VgS65_5z
z_~)E@PzBuX#zrV?t8N0Aua)D9c=^7xhID#8_ETrgyRoj88AGq$$j4k)pIBTyyt_sY
zPu9CDDb$6=a7HU8ibmXd;MK^6f5xf7hm11wnz<K2`cfGt2yTZN=Zcv}BOFtcf%T-p
z2Lq*VO_|LXB4e~-rw_OMDx7>O<FBPWHZl(awKFfJ!y|mXeJWWW%wK+MI5sisQ!Kp&
zAUx0FSw**H4pfe&yoHWQ$3tGB@hafCXtT>5xgVW*dmM4d#WbuYGxMhp@@Y8w(u3bM
zLLJhK^GyeyKROBZ%>W&L#*UPk_u`Zs^rQfOwA0r#;(e*6fD`qtzYFb6LwoWwo+}cy
zv=+tE{c5ARGuZWuOP}Hd4xKAu8Dv9|g2K4VX~W8gco`TV8tN@JzSUF3ZgUl#NMb$l
z#YKbv0PC)`JUef77XC8b_Yi3t!ef%MW8Sl7@i`e6bY)1cGW-#6<DbI4UgN_T3mIe~
zv*<XlG}kO-v(y<STtD65aadJ4D7{DNQnV4}hU7dBYh0`o46g_4RP5tJ8mj@)tcb=v
z38);kV@;_i<!Vo|xax%d6#a~PHa+NNomYm<ArXipQU3rQ<LiowL_wTJxE|FhY1AKI
zaZoh(O4%`?6oyxp1(Sx3vnSHx11;3m`DeRv_dq>zPfE_3E5hZAkHmE}&@!afkf0-s
z)?MYyR^t&5nDLX+v?jBWj$TZ57_2=;C5~P`_BrOM36!Kenwv*cNmf9;xinEh6aZGn
zhGUStQZ_U9b6Dn_j#b7B522(qb#EPwyq`JTN3~4_<d<@J7BClV;|e$xPRh~-K=;gB
zu!^_sd_e}C8pma52w#+Z)dd>bPlRr62c3LQ;@|4j@CA0ZdR?`YK~gmUcRg#7u+(+y
z@(4tM4@~-3Lu;lpVXkIr8G90Wsbe``h#G8dvUpS-z5OfC9RTTrUe)3qIVaKGRWpk5
zi=F8+hEND3W74{5OG7E54B&cGNf@KQN>d*0d994b1D{%%Hxb+Lrmedk)oKeV8HVfu
zR-(ybMnE+6Cw2u|j?OgYm}mQ@mRGm7P)X}rrD6uGQZdFj^{EZE0OvIuYL?2sy9A$1
zVynriJc9sWeJHvWi|Gmjf<Qj>>_(#*6_m1EO5VfU6*^kGa_)2KnrVo+xjF{HsHa7i
z-IuTU(#HS`^L6#7>>qa^des6shFmr}Q$<gA3nk2oK^Qd;mes{5>U1V3#an|Qax;;@
zs8SL+Zhfm?L$!TFShu!`O9f!ZA6lfWGu`|jwhs?mERu4n4o}j$i)o>mcy(?ta4U$u
zg|w|2BxR7s6e%O9towahc-t^a(r2V+<;7*}+_gFvFLS%pY>m4qw@im@w%#k9@f6Oo
zA~pup$6ochqw1e+(^hGdYmTbN(z#C%Uwxwdx(p~7>r(}3Seg7MKRfLux%$?5a>uWF
zvvk>94o_YxvI2Uk{{RZzn3Kj1YVErG)mk712d_%dw@^Fe`U;RbJsLmsP~H72T^IDM
z%_L&YbH~=TP-cK020iN39YCm53{>!BN#7M9U5}+qqnc!RJt}RyV>Kf~vBe<k=|DIb
z%{UKA0C=far9`8TN{~`x9y(IfM@m{ia~?YRbeIl5kF9xjrg3v0ve&8j=nw38$>(d1
zmF2pq0H?1!Pz83m3b-{~+-^DPP_t*6YaEYSl8Ks7ed&!L6#?Vgkx8P!N?w>xdQ1{P
z;+jD{DcA*Lo++ELOR)FdiUJW#LT<?C^rOE@QZRnByKz8-#twL-BfqUXW(U@cQvy73
zPEnrUjX!4wnpd>|CI&u~fpdy?G!ijD3@ge0l!SBMqyznuXb4E_K**aEfRDzcXmd!g
zqMVR3Knou)hTzi8Zn^m+4VqU9>N32J^u>s7`9%Og(A+D2>6K5dWNPwVHq^La*zJy$
z(UY}tT*j>+lJEk0X99pS*?zSV;;k`7T%3&iRYz>Gz@#&0L6J;`Bj1r-TqA3*&5>Mx
zhGSW^U5~qNIs;ygG`nFRm@}T(Y5>k=ApF9*Uk}Z@k8btPPJv$)siI6{kYlAt9gG(#
z1iXfBItpdxumlo$Q1TS=aa9$t`?}Q`@KQiCT$L~sYR{f)Qq^fiSsb<L4Kp}DeT!8F
z9`&Ph7%ahtFlwBT?H^wC+M{J;V%^IYDo>^>NJvM}RT~fpK9yfl){{?vFYK~N;PQUx
zq%>@q449-Lw(>x(GWW!~v%W2@#6bFxO<~;K>ldt6N0FVm+7A@&!pEaasMy<v^KKM&
zAXN6?U9XuN4TrvK&-Bj^-peYz(=tT7;ZO6f#b>v&x7r^#{t?!i3mV==1`CDvs`6RJ
z!2HCH_%+W@u4->4AhabtSFUQe+dM-r@VfEsOh;67yJugWwvS^~r?j)S%P#pyA9k?g
zI@UKCj(e^uPqk`81>7IQGz`8kH1VC*>^SFxM7Q>FugPrfp4i1v{?nEm`Kca#>7&G(
z8;ApX;){W%s@E%+;V4gIPX5liX8!<>g^wM!aaqgar2vm3IQ8PDPZmN~=7rbT3U>od
zY@}7e`S3dX)NgBaLBK)(00GTa9x9I?Eu@F*iW9{O@&t~~V%~y_fgrTGPOu}NU@4$n
zJMA{`sL%KEMQU5!+)kvmh>ZIAnKc~RWt{F>WE+oPnDbKD>`AA^G%|eVJRkO{_mP*G
zT_lfa>&;UB%CJrrCg-@3s?D{nlq-P={9M#I50s6gX$BT8`07+u31XPZh^=KLdM$L(
zPO&0|i3TW=b|jvkN?gIpRMT2ihzU@t<Gopz_qiG1j&atQSh34>rW^ysD~`ou;mcY6
zV?67gxNOtcM1}=bN14F>`&IjQ4A?zt_>D;UN8)I>Sj77SM7T`j=}NY&-+oZPtzVza
zRy9gfA;%z41X97}5w-UUsd0660L(v3nzj}~I^@(&gaf%hI$&Yk>zAT3%-F}Mt6EQq
zV!g~$4X(Y|;-l2G-?Ur5m%%D}R~2y#*7qbxpfa8apbu1<?V$i9DB0u@RbN$~q9U#<
znb5pU(f<IW-W;#@$m?B1A{)e6E#yX4?Np>qh#L0g#!nxGR(Fw?nKv5O{?A}X-XwJh
zxu<_)%y3c(8|b+-?kgPoiE)kZf!j3+M+d6|^{%Er58gi2TS<<4u*Fzk3g2=JA4)?w
zvmA#!8c(yi<fzYT?ni~MnYM_=?);2ZxcnV)xA%_{pJGh|x#uR)&+w5zv2uP@&3b6?
zTqUw+Z2MHn;EQfIw50VE0p-i3vFC$IG{Q~-W8S@Cydhy1GA=%i{sNXS3~7pYeVn(Z
z=QIV+C>m%7=4z2N<bDSBKFCda+IW9WLxE=)#ZJ0Snt#i>QFIqPk#tSor@jK3nmrMp
zgtd|X0N@y}TT5$YJVKfJRG()Ba1lWC0+qt&lqQJf!mYa(^xAm+D#Cbb{m&Ln`HJ-w
zfGX_@0QTaKBp%J5trrU(aUX>5xc$<vvk_L4!S~IL%>w)KYrb1_>#z)WsYGZ-Hi1RJ
z;Zwo#DEY2qR`m;-vmb+(7;DD-5LaR3u0N$eVu~&YD!vZ3&(CtiW2QK%)53ac{{Re)
z_}4}w1GO&CK}z9c0C-nRQ=cUMJk^i*NA&eylGQWWm}a#6l3Q~UeX32Zx2NSr$73=L
z2EsPo<RNq1ing{euSnxj=mlB|MK01sD}h*BL_dUn0-mv;?NYcS)O*qeAau$1G+Zn|
zP_uK8Jt^f>3<bxvIgUQ@Rr;E1NeYvhkWp~3fMeR7w>dki7Q3}iy>Kccs9GHV0Hgp1
zpeBH^FV527fT%n7H73#j0P3o3s#y=aHh%+A{{U=S6M?<GIK=^DLtxKZP@eUab^B#I
zMZC^)j4n?<l{o8&I$1wX=M<RiY3xN(#GXB=o68&pHJml|$NYPL<Mh+w2f;DhqMv#K
z#;A`6rYXWMYY^-AIcy>-_TrH1*LVl_dG*BsV|U5pJ!&~5j@~fRvkdSsxvVzVFIZqW
zUv*KMuO_E;Bjx08m!$z?rj8#lZwPtzr}+*KAY!>gsa_F}Il%hVPjxd9x#T|Ok2Hs4
zvDiD~^Q12lw=Sdct}UgI^=fExrv;nyH0%dv*EXYYH&Kjr=Arv`oftW~Pr|uVFEtxV
zr2746u#Tm*s|Dmp&Og}|5!bCb*&L1d*ED7Cj8jCJ?U72rbT8s4!8>i+{`#n&#AJ__
z(5d%&!Y+4ky(#<m4w$E5nx|i%s>ZAO)HfR4<ghxiUVDLA#QV}0z&QMAGzS@~D}AO`
zZdsc-HJ8uQw{^wD=Z^lBg`Baa0vS^Mb8g2O_N;Q1xjJShCb3C7k58emOA9WBGBfTt
zl93KgE#hs#{VE9C2d#8pQfyiy9@P9X=}{@jsh6Hl=UQAtN-~aU$;CMHj%mHBgdGhb
z9Q38gqZGhQb4EF(Kb<HY=`bQA2Bd)g^BsMu7*nD<TpUyY`N<268mz2w>sIG|(2<T$
zLsV0i_o-t<;n)u1kdSGhkSRy5O$cF%2+b6^st~F$I%b1P4{8rJLK;Y@SYYw_ROXmR
zttK)sPtvDOMMgNMCPC}P3t%fuaWTa{H^`=3f?qwVG<~M9Q?n|?ywFa2(-pEQ;O4hZ
z<gle5r6xr#a%)5)MO>Ov2;fkFu>zjU&-AJ!2P4v$>zwmb?ZWn`*nFpq(qLD|e)RPF
z!=)xUr$#=1YLbHG@Vj_5U0SW&uIR}F6`nDZSk6|FNftrK_owGQ4L}ZR#C<vnYC&LJ
z=9dIhf^|IwNE7ABs!|n*fXh^yc%Te+#XJwjuH=mX=hl}Uc&Dn2e6-*(-zKW!E3o(d
zDFTf8)a<`EwIE-cIH_!Ag{p3d5%j2T6XqZaxnMB8Kp5asO&27dGg)(_$I4|D+t-S-
zra6aFiHYHkDeo5?;M8%9T*r^R4@&37$}^=TX-euxtk^#2RDr=9)y(wjGgx{};9E$Q
z*lyd<brqs+<J<r}eQV%qVdc!vWit6ZQJnt(iK?dQ2OEL+r8iLp&zQB3)#N*pvE#25
zS0iz#X4Iex-@INu#Zwxssd7Bz{7q>LG}72EYM!3e425=k)hE`p=+p+fKzj1Rt4ptG
z`*Zflg8u-$n$|dZ_9e*~z9VcXY~zk=1{;ttcLF}OKZ!MKJJ|e~XDyM{dR73FXa#b8
zv0kk#BjiR>s*a*NoPZSM`%~p$>DQl1<>R|}+l2@4tFdYlz7xyf_9nKahLmS>Db!6G
zsxo+~7-V&*p(WSerD8T<XEo{Wa$M1}kcb9J<JPyKxXr4!rx+E>+Ov62vjwrhKDCi1
zrK=;D!hku!+rY0U6@ztWbFP(W#yXyh75A2f(=119R=hXL@di9+)Yp-<{;>UL+3uqs
z)|zM49AMo{eSdg=#<O{1aZ1JgVke~PdaNlX!6ae7QYx?7qua}%9_GB=tuESK^4z~a
z?V1+R@Hbo*!QcXE{{UubxW2HDL0wY9DYrf3OSh6YignM3H2GDdOO;~7w>TBS$7{$f
zBOh+HWi6Fh9nH;a48Aekmx%0a2`x)A{jlJkfogB<D`>{iG@pXjKve{seiXSMO5f^~
z`w{J=Z$qzG!w^<!*}Zo4saM2yEB^p4_hkP7x<AIb(A@nhMJK-kpVcY$7q*eo4;0yh
zfnjidxTl{L+2cRibCcWVu52*&qjwzis#tg~g!@Sy8S$(j6>TBN_mlqstxNv^3Bc{6
zDE|O~3g-#Qq#$P%s-~92^RuR3h*u~!#id|>zyAQ%r;ms_i8x&~6#AFX^sZx^`%{3(
z;-4UM8|~x0ZHLQk05s3|PCP(I%MGyn>kujRr5VSs)}JC5Gc}vWo+Ll>@A*_s;=d5T
zTZota)vUrfrBV3(C~!f{%|-E7h*?MaQVf5yO>YwTf=|7u6d&xUtne}KOOE`}$b*@Z
z$*5`*ljmRDwtw3oepL@F+nJoP?pr2;GwV-S^Hs`)b}+<^)kb}3$!dU>UBmIIf_*92
z>+4R!xnIa$c_%$`XfQ{E!+v!+;B}`)2|alAqQF*bc>e(BnxCkrt)k;A5|44kPVR_u
zppSgi5;1<}ki=-z9)s|x*%z(}%_n}e5^;>s1Tsg1o-^rH9xRNL`qb0OmOnTc>6)g}
zam!M$$(4B==B>mRZzr#<WcisqGn1SSD#UTzvwXJlo;Wz7!!(IirWr@~sjH{nxB)HM
ziS?-mhjm75rMjl><+@W51d{@ADh8Ye>6+G03hE3&mf|GO_g1Y%;LYk<OXHtFC<C51
zOCKc(A6j3wqMo1**)`Nh;R^&`-aL{K-==EZULMk*#>iXixaNSd#T%%|7|Rpb8kHsm
zen{kg*i<CfcOIQ$hbwHE^<kQ_sS17AlkgN=c0B!JzL%7+l#aylRw2@LxdHzGL<$f0
zjw`z@gZF<*Kz*qNjyXIzs=wZ7qx$nxFNCfcvo@jlEOplgJ*m5iJm>SG;<3*FPeHK0
z$KfkvQRZAu^=3Z}>GAXBGkr~L4yK#AvrKj?N2XdL{I;pbPAYYQ5PYzp`U-aA^faKc
zA9{h<LaYx(9@wCv;|KDmXCHf-Mj507LgW7cuR%QUDaWR1o3e51Knf4xK`a5mG@C&7
z`ctqt8OZNI0FVy9ttdJ4q}sIQ017}i9Dh1qpGtnvPf7^w%>Xb08}O%Piu1)dI)V3d
zO$<rJ05rRk-|0XA{c22(o&71GP%%Ir{{UZF3H6|H_|oHy=b8i{>?sdFDB_ghV?UiB
zY#ip83PA_nj6MehQnM00kEJu9pa<-KYGG*wF79)hUCYy@0~m4-si2Z58*}eYECArr
z5S)=owTPwMeF-#WyVC&*lg2SjDA?;q%ntz5gOSv8KnNo{c|1~W=YvxDjO)qI<4wmN
zlnh>ria-JFnm|eGP6TH?s1So@e(z6uLaNy`{HYu+J<VimT9le?nRxJf^FSJV0UNgQ
z>zXsSwRu#&Ik`KxJmt4>jkQ_)ae4j82|deWG*}N_GA};AN{ysJ=rPv3jCkho51k(e
zxqQ+$j;^@ck^$`46j&~L_-)IPfCV(ltJSN=WbwW8kQ5$z?rMzqw*B{Hs{_v8GK&Sz
zV{51hz?DmVYP|Y{Ht1i?M#pT|nA_{kJY}87sRy+_;`ZuwDHeUP-m1d6);EkB%zr6R
zuSFra%|zZPyk^Kq*Bw4;^YiwIiQDEMnDrRv)}w2?<v7fTw;kxPu65d`r!DfG?Y}*R
zV@SCf&*fAtB)MsEB1ix|NUcx-Qb5ir*iDoH*(c1|$8TEcJUe`r(uR?MPu8%VF~W@d
z3Vpu~@~&InlR$bw@eP69^OiW^V-<@%z`B!o1xG+Dm1wmVVnxEJJOHa(HftnN1(ri0
z$0YjGNE<9N<EA<3P`*Pi9qPe+j@1n7y+#Qb?kR|wP8Y9kf}NcD(nrbz)|V87Bd%jV
zO2U&?O)}++@5m#k0jqeAl=rS<SkvC>Q0c;tyb93DMwP#eMZ}vUPznC^T{`Qk?vrr?
zu&!DS5@b8ybAPjpR<DyHj!@7tS^Q@VLqBJeAoMH!YP)#hdBwAz!~X!UO?^Hocs8e=
zP8ypYlW4p(o^i%l=76}3<CD7|V?27cDi-mz$!x`Fx%J&z31wv(@ogF7zcnI7YZyBq
zjedfFxt2U<shkC}2j~rSx=q#IqX?2n$zn5|xT?{VRrwJI(Q3>(i^2CBoPJaRul5;8
z&z9Mz4LaoGY6JB(C5E#M<yL1!Vmj8c?3q4C$UO+;QUevVyM-KuG~evGer&Re+(@>c
zx_=W>tP#1%IHKTl%cU{SWFMAkMvzW_dNcm*ZnSZ(X}>4}i-C##l9=X3^yx@+rR^d2
z;<gx##{pF5ieqxch*LlrDW^t<=Vm`nDp6r-7`K=6de(`->Y|uHrZSJ%t+*=~%`e%b
zQ}UpzEg~aw#F|4Yvf*-j^yxql2vHaxB}01Ro3wv%bL)zG7Gs^K6o+?Bln7x8TOmOA
zq$}S!rOS2LO*v0LaM5roISRjbJkn>5m3B-tWNjq+nyDhNJg*dhgn|Zfk?l=jdefd(
zLEKbkM`k<|Knb;nKgyz(EyJ82txvW?(0+7{8)KSaWlv|7Ju5a_OgB-H>MNm^5_+~i
zl}cMZ#|8fYIxGi0BpzFm56#$vT`!0AD`%L)ag~w1dRAoiV|EK1`U;}<?58WZ5ONrH
ztY=L#M9*Hcv9g*mBxt=kAXbbP@k8>euNCH=AMrfaZ5%g`oOCC+_pd^-)vT`K4zs5{
zfz5Nc*wHfaRVO7!<v<FjAOLAMBYoFX_|uNi0WO&O)D$!};(0v#)R`mKk9^cc;|Kj>
z5&rcJaSEK7kPmjE!X*cs=k=%VCj+%mZC1fY&3PF7YBtui)yX$%eSn}1G0%RTC?kQ-
z*0P_(I%;*fCp|Wd)DrlsONRu>AqT!WrZZ)L3USlkt4ODIMn|<|j~3WT_aeA+=o2)j
z#A-2(I_UBJ$~jmzYbxhGaqUl7@PEd!hlpp9eoZRq{{X;vqx(-)l;Je8eLs1FM<WZH
zqJVx=Sifx7j{`~_dU=aYGI)|kIJUQo{rAm2Mk|}Uwv6r=GzmsIZncDA@iVXAwoLmI
zRb{pDGZMaZBi%Eae5`jk$>t3yKK+GVw7WoX_zT<GsNKiqOxua!v5!iEH`;NUi6g3<
zu8y`j(Xd7_jtyN)gxWb6UUDmsisO=Vmc}zyQszfET;j24-se(p5&lt+!l}tHB<&p5
zK=b5ac|O9eBDh?U&$-P_g5{Gi+k;eYor<<HO;3VP-OWPKob=+VC``YmT0fE<i1~*j
z-n14issa4P7K-0yL66R+!7H~MSFKGY6UeEonGsAJQu%!Jr|svaKD1+xTC*X7A<ZE{
z*kYyI*V2ug(iqKv^c0vFsj<d0Oe@U*FbtXk^&AR#UMWDy`?SPFS3iYvekidEFPsP0
zj+NMAv$cCcb7uR4F#{V%dd{M}O)0xG%iRL8^!2GCRNaj8R_-mwn#ANBk@WVezEcJm
zJbTw0JCSZEH~M>3hPO-%ATQG=tyPKkoS(|3X^&jgjHxBMAvw+}r0diHpQjaSNpeW(
z&#gv&U{B#xiD=C!hva@#qV6~!<WdbuF;IEq@TPyDV3Mae=xe5%vCB|w&u?=c{{Sm%
z=brhf{KXNnhGU+_nKZDn;w8t@tAoI;l#E*>2Wt|i8@(%54MCG`PDVTW);4*o5u6Wd
z)-0Bd2Aq~8lY>#S0zIlRgVvX?de8;x-7`%*^PZil*!Sk6JwWT4E&?93M))}X8fnS&
zG>7y0P|y|;{F#-(IUbcY%xi_6SZ!{ms)pQ{$2DrsP3qR?spMvm70BnUM#CIblEzWk
zR7XChoxoufgq-tAee+BwnwBx!so}X&c&M{a2Ru|Uj+kYE^`@kI+XJmi5Xb--&uY`N
zvH=4c#!@LDvbPZr;y&1`#W*d`y&DEbMNWvjNFz0qcPz}Ec7kzKWE_qwTH-Ks#y=X(
zWyeFsNX4^_C6i-5+|<Qh8H{H+9lb?C1MQs;L7w%ssap$+SZ?Dda2$cx@umfIY>agF
zs}T>B)d(MwbDVnB=nhZTkP_o-2IB+Pw{-dTsA4h+>+e`H;0lt~;GxETUwVdGJqu5q
z9g0p1bgf9oLEk;Aj?*tT^&=J3+uW>?2M4Gbs3_16fsf}?#>*sm!N{sXw=W!2w(eDc
zJqh)ygR>??#4@keg^_`&f&w|gs3t=h;<`*ni9pA_D%>iZ9{ggdFk*Ah;Y=tMU5`v;
z(-G!B5w45hh{g!t$@J%n;Fx`Ds`0GbwMI;nx1ZLzMmQ#!B4?k*oC&D&PhLKh#4mb7
zoSJdzOgxS$0Ahj1dQ8zwVuPAOJ@ZFeP&?8A57xGHA&E1Llj~U7;<YrUWn{+#JesJJ
zEsm-XNe4C8=z*lz3z7jG*D-0bW#C}vxUQQ-n8hcQql3Zbw?{KO`)lZJV8ik|9+hG}
zUe-gyp!yuwIJ#)mm?q=T=~BOiBmj>*;Qkeq&8eLlY8J%vC<D^G+s2W_CaW7GWERQ%
ztDrs@yHWB?Mm<=!^{icMMw-$AH1Y>vbJPC-uUSh|Xy{-dz^Ru7Y9qk+rwmqRgrMWS
zE?c%UQSy3Iz$Epl7!u%a&q`|+Z%%4Kob~74n#t?>Pz6~43PT#FFhTdYHF{LQ^&_=s
z+z*!@tuQh535r1=LCUWL_O3qSLnND+<esEgTYQ+ck&5I2(zy8!Td6-<v_l(4MJH-n
zqC$?8QPzMA(y7|O_Y{CpKpN28y~#ul10Dr-dNz-501m+KJo8?6YV8%oY&wJArFuq<
zGtP@4ASvdhmX5;BHm=m+eKT6H-~m{+jLNDHUcD<`7T{KFqST19TgZo_EqIo_VfI~G
zWZQ)-d9QCn!0TRP<LiI3>Vi-{L(c-WqV=(y(Z&lyoa6yggA^<C8mTqgoxpMQs-(#$
zcKTOeH)95i?|z8KW__wQ)h1vSPT!?fSQwsj`BkW6L_IV0s!mK!!YR9-_?s0vY0i0e
z=B8ObUKbxqnPhf7N%pHzC9)Xop;8NEpL(5QKrjX|PmVWp(A3LrN&f&EzET?@U7@pz
zofmNFfkCyyb<Io@3)oXgL?J15;Pj~oUs@k%1E0e*#A9lxi6-NWky&PC>?><kh)WPX
z2&``-Jm$ITD>Hg;LB4Cg1#})0)Ei3H1=p5X5ERxlaU!rMt!UZE1E3zgO+~acTC>^g
zJ|I|J!pm_93cN94Rc}s*s>}9^X}p<7-tyYH{VvTWu|_<D$<1cm>Apm-EATV#n!!#{
z*y;9Zo|j{CmYQFd(+Myz3F>Q<x}VII$mgE5gi>i0b3A|!n@JUY7_2yAPaNi|4(+y0
zO(V)haQmAW_NK(YFTcG&(upQG9r2S^;ZdHIce#N&4o82jXhZ<Ucoj-D%Z`5vzPQNs
z6u{}U(f)>qy=cekDvgqnWgbBpT>Wb7Cp4HAm)5LCI$%|GJap&Mr;De*wMzo@WO~%#
z@l~QVWqVQ>y#+aXQ%wufkP{EBJabG0Q^ypBJWweCrKATn<6)f$`iB+f_f~6l@|P=)
zgmte=@u9|sao2dSIh~|c-4`@~qy37R`{(IP{fM~x=kXMcd3?vF-=#*^cYyul&#f&=
zBpMul-s|g1G$iB)W1qsPKBsUvE=N77r&pZu<{mw0)D0!jEzdcSANS}Q6e>9^IsW!*
zDYbioyhwj4Xw|L<@tplJMxbkr8XSx}pQSalX!FMGbjhs0?Ms3_`wDAnbKvBYOh%vf
zIuZV{iKF`&bDZPU=CTf_Gk+Hp!+A3dZe!m$rUtv|aG}SWlTbCBO4u^-^yyiRbt&(U
z#}v~mk;@;>ftDsHhYH(=uS$e7x%Q~UfOpTi6uy2v{b&&(k0YFPr4fP6KyC>*#V4G{
zzfRNvWPyy(PZdzi!jR5$Ol6|LbBY7|RYNO~deF1&Zk$je;)Y|w=B-6)?0#+qQ5uA+
z_f7|F3UBs}&p$EG<v<#*X#{Z@ACkVc#oq*$@tYU`oB>+5clS+h>g>!9LtMPq#JjF>
zp8e=xi*nt@mgXdlcY2;{Erw1{6vmlP@fuWM?Zb{~4A=1O%vN{h<tjZ1?rYE&QMU5I
z^RbcKb6#YN&<;&>mPqXu<|I%C-RyywFg$wI-5OA5P+N>vGabr5!mjDE6u48n7$Sik
zv6Ui#yoVfDKXb3g6S~J9PI~6HE`NEZI8ZufxM^*%Ase>f(?Tx2<6OC8%`x9`=y6fo
z01i6TvTRdKM7nv)6+Mkm@eSlw&Whj?#NeKSv^4Mx#-rD)(q&gFKPo_uGE4T5^vLVQ
zO=ER-@@$0w1CqwCe`lvx0Y_|#HzXjc{*;O?o6{Y+1&bcMaw>tmexoG%nu<@Kr|C@E
z0+Zh~&=!BSZdC0IDrmKvjogv!PB^T>pk}6m0U<lPPzCFqa^yxrV7IBoWy>b5c3bBx
zt?n1{r?3jgj-9E|%oC^SKokvzrIYe~2yE1eWqG)7jB)<eX$#OtdUD>3@-aY)u*DQZ
z7ck_W#PqAlJ%TUG0)8T>$o^|?BlDz4^FSKusoO97u^)yiN7i5pyCWca<E3MHe0?dn
zq%*$L^*AJjQ_aI;ocE?`CRaoDX+UngS0iH}jzPGRE2*@e5}Sz_q%#KQ^6EVKj?3>-
zX<GIi#X0Z6=~{Y*mY1=)PnGe*R}Xb-HlK1*Wngo|4u+FMx#_T6dB7YKp7lSO$XejE
zy>>_$QbzfID(WD)S(H9=p7kTSu1F(1QwYKKs3Vhb>w{7Z?&masvV{j2=h)Sl?n(?0
z#cGIr4wU}@Gy%w<3)4v)$W=)UYLmer$EU3#%jt?d_Z&A*r2r!%s^kieLhiU`$@Hs9
zEN(WFwwm#%JabG62@<>E#}!Lh(QPl|z(B2z4mquYsyXjSBSzr152>ed9$%<wv+2_n
zWn!b1ezk8))+V%d1fMI|S95u19I9e}om;m`=dOGnWSF(R!l=*64ow3){{Relp4L@F
znSckO?Ooa=4xVIUHdD}!wc!??8@|)oKhon04snBBzKyP2>CGBE-eM2ElS^S(^bo`y
zsDmHgse={+a2!=DeNxVQb(enJ_3ujht)l+`%U{S*aIt8r=Y;}*oc$_^)olL&=c^Ow
z1tHe$fcZBu9`syxFSBjn55kjiBbv@S%xrkKZ2FcI*4B2mKF**H`?E#D#+Cz7f$3Q1
zU2qQA;~x0UNBy~UPYW0y?$WrdZtOkQqB0=J#%m4ri<t%;&(I2C)Gh$w$R5Ih*yvSp
z(LX9s82<nbb1i*x$M3i2O*d1MmUcgl0b{A@)Tlm$((h1kWRL#(6~?^M5^(Ia2axbz
zGy&I1G$4TYDfA6d8~a560G8^0oYynB_G9_d_xt!h)B(|*Qpj`X5`6$UsE)U2r--LD
zfDS*1pRF&L2XjCha%-b*Beh_A9r>#1tU8>SGJSKJ%{MWq`<XO`<Q|DdfYv(n;NT*F
zdL6wgIW_yd<0BrR3e6V-AL{W<XWTl`VVB0Wc*h=WpI#}is@;%4nZGksH*Kc0ta^-4
zBGYOYJd*6*xngQ2x|y3l)}sta;+j~WT3|?Bi2Lk5hMHG*Q=g?U<aDI@y5x!nam=s%
z;wTHpCqGk6$=%kICp`@Ta&G--#z)Q4qU3a?P{)vj{*(cwZL8hdCdkZtJ=USRy?dz(
z$P;nvx204J!Ff!5O(RK;sNY?tfCAfo?=){FkOJ7kpT~-N#O%Zf+@E1U4BS}zdWuq5
zFR!&swpS;Vw~*tosYai8-EE{E!j*#MRgshtj8J4Fl0Pc8G@HUR<jM3nr>=>1%yNN#
zuS{1nx02bV+;i5oSHrWOS(E8bPY${J_Xr2DG*~WVahjBHyaDyCrSR-%yH?|G{05{N
z1S9@iKj0_}ocU5aQk2N&rF2o~mcfB9A@|)={{UrK#<^7`k3*i62<5~MdMQ5i{{XWx
zuIJ!aLNus<jJs#w6(G}X00YZBdbVkS%9yd+k6Lcru~GTgUbfcD(iI<tN#&pz2$=r>
zbWl5-aEZwW%VG^Fwz+?~Y~+10U5Hg)in;a}rwCIVib6ck#5!%rfK2g_GtPTg7VC)*
zr_#N{#1KU`l;ddKjtCXwccT(E;4&E0uZT>gFZ!}De;UDWmB`?F*8HOgbNSX3!xJzg
z@vh7}_l%@cyj}6`9YL(lLFTqxW+on$j^hq%dXCZ(CXMnjR*>XYcsU}i+sTz7kLOxK
zcN0YI!uF>6)QHfG??0|7A8M1x1Ju@>!W*8s%>#kbnn)P=g&UXq%6^8cm_vZi;Yu=1
zC<-{|@}`GS0OtqVhQL-h<D60syiiVg3diUvS8!koF=N|lsOBAlL%K3MRV8dOtyddj
zBg?@fjxkwn45m^RCnWy>vx<q!P)K-eif}pYnn7)KfIiP5snW{yul#yH(C}%gplFLU
zy{b{CYB<QVe0uRxrjw|*{JOCGML%f~ScMdx)cw7{=BHgNQC<bBeqyXeqG~MM#jtwr
z8K><d+$>Y_8*WQ4&{au64P70!nLI&+skq~{QJX}(c^H793F4*IhjG}*2R-V<5v!gE
z&%Ik79lawyYLB3+Fz8n(aL%9aQueX7<K;3h;0hGro;#Y&=xeRI(5@~JBF=y)>PBjT
z@U-OQ-ADfbeAhgrx)h95e_F7Oky=0SjJl7S=w$T5)4#A9B+uG+A5FDztzk50fyFos
z)a_+B2Wk=rr+P(!!TFSrt#m5UBElk&!yPJSOf@<<K45Bghrd%+s>DqYZQ%2oR9uX7
z?^B46@fwymSDdqR*iw~fuArjK*%Rh8*wF9AT$0tvKA)XAAu+IGH&$;E1Xn8}Yjfo=
zJQ~Dvv5)t2U6KWy5Fr418gyD*Sqxx{p7qO8wdHcsIOLT`<o*?Y-(eYW;2xP=b6s3|
zd<n{1#H95*M>O+l0Qpb>=|{E;9Kxm;0x&y!)SEZ)gT-$cQZc~K)KrkdHt~Qxg$}o1
zvCRnb-7*Jyd5u(e{{X&oT}P0Z<Zyb@tVj+OK&ADG3zX$^wDBB={s3vkpQ77IT|+>M
ze&{~<s@DjS;F6$vQ~Jb%kiaQ&PyBl@{As2;&Vtzg0N+)(84BbIayCyq3eDA%>ONBq
zQ&lGjrANLEJv8lBZ@($Y>A<b<%Zy+OnE-5JrsFx|qu!hYa069{berfHvfM;}-a%Vs
zKyF7gF<fAZhp9-;7Mh%3pSP;#o)?;hj;0$wZ<G2}`EHap%rT&d*lm*|Bc^$*ohWuS
zRV2EZZ!OzC-|Y!lk4HRywK7`IbA@}mh6AZG8jbXnNqo$<+~=Cnfst2gt_2E|I|<a6
za<S4OKPycujC9;_Od1`i=jS>1tvuv$$Gssgys0DDRr0RHbF(~X_J~f@Z^Y)5X!iN(
z?~2jGGUt+g>L#2*e|T|D$S%mE)9sV^KOu^dtu3+(AkWg8FRh)MWPytI2CJL9r;xCT
z0R9}cAhBhv;n+6Dzl~LRwzmirQ`%dj9_i&(PeD~Ay@-+f#U_LW=)UeM(vOqYv+br?
zBi;^2wOv^-pRHLW_S~}%Zi1_o*(+fFbtR;jnD$}~QoE6&yedusT;shaBHl5cM>HaV
z(Bi52pb&8(`YEXrP4Bg1nB%X=X%tzKIQcD%k7}w_44)|HuL7iWxOL*%Zrp6-(^Asx
zV>Yt$*eNEM34n*MTA2zEY5xG(SMm~4&BJ;gKb=YaiK?~$vTyhktuP@NJt?Jvo@(rR
z2Cx4BKHEpLgHk7jwKi|Kqw3UL4A8)uc$EiQ(>@f`lwqWVQ<K71&-bpPPi?vVX#tjG
zUwS;jj)t|*gl0c}^ZxlmQ!j(xIcvO+K)?NZL$QP#o}!#v1F!2_!@=lJ&3OBLHq^=B
z`!UvOTk*&8pe%D@P)$8$TIm<UI%qu|zuq~iKj9bB<LMUT*Mdbf!pAUVQg}G`p=LmS
z@aDSY@cx<){Ch5aPEAg_MS?dLvGLy=(R3C#x1J^H$MQ7av>-i5K7<<Xg_WwV1-gDB
zo|f>Z+=&N0mVmLsB&CQ86pT-$JxuMw+e+E=T-SO42Z+=1qmXz{(vVo;#kQi~cEU`a
znc}5O4OP0?I{yH`g?6Qw;Pmwr9mRU{^`~&L$F85MlYwl0rK&~IwN@OWjQX1DvPtHn
zWoZvCcKT6pvCWMGQe(8dOYUl4_(pGd4}OR}mo?E1tI<HIlHnJUfwSI=g^pwX5l3P-
z>I`$&<)C;%4tHJ1eQ})ENYiBHln&I;>ccdLV+43c!2Rc)kGq<1@U4QM`D%WyYizIr
zjEqrn*vVfH>4Wb<$g2?O+G-z`414CTfuEX@y}Hl@BF5Suxg30YEkDYL1B74u<W!g=
z=qb79=}2T|K1Dxn(a-@-98e0MN@5$g@}(SiH10N<OyF{G2fY9$-Z&qvH*X#4LQhVk
z*A$rNfzP!7G$*YaNdC0sVC{t<<IvKTB>c31VFZp36rDTfq*Q)DRzHP1?9w0M%>YI-
ziVx*di+N8-+MX<@Jz_tV09V`q#VE!(t0zvnKXxy|oVs<-If#sRrUhKDT0%!$)#cJ|
zU!O1PcM3nUE(yRwe;NSK3<<}~KMGULXpJ7^;~`d*Xwrk#bKK^OftF*>Q%SUXR;y^v
zI!Y=Nrbr|Uz|REckQ9f~f=J{j&1{VkKJcEDXs~DIn4hHpV=HbLJxv)MGtaecu8(Y|
z{bZj^)6Sb`pX1NgfH4;vedy`arEL9z#Yo}F{{VWO_Dey6sDBfh0LMlLwG2SxAbVEQ
z*;<mhT;TSpQrg*0RwT|SxE%PCJa!&}m`*t=arCZ~#RwpID?mup=VJa;0nCs=$MUCz
zkx$${y$y7uAKe2zz^85@r~{W}W>Via-%zB}0`4Cu-CbmukbKI&h^lQ1s|}d^Xafmg
zn2dRDc+X0aZDnEpsDt#a)kj~w*V>hd9q~*IFYNjA#4Kq}pFTe01L<3tY>v4UZuOuH
zRMW0mfDryX3R9*|PA~`KTOjkCkxmLT){q#ZOS>cPr~|%f{{Y!{2d>b5wW%t|ha)6<
ziegE-1n_+*12}0jk&`TA@TUzfOrM+|!nAk&Y2olXQE)Pjj;HU-*V>-CRAUFsW9^F5
z-cL{sA?LUh0iOD7Svvt=dRVmUF_P%sXZM9)1P&>f8?p!EKo!oNZUMsQ+?wD%CCDvw
z^9*qC#{}n!^qk<}_UD@NABi`sEXe{(ziWbV&`_8hO^1<$62=?THMt#@p5PI089nkV
z0w492qPJ2*AMWv!>MKG`i1hnzqTK=Z6*1FOZhVCmfS0#&NPp5DbJG~Dbh=fKYuvFo
z<eFk7dl=MU!x{eofYeWE8xQpe7tjDJI_>Vsd2Qw+YVbX45w9=zH<@uV^TtmUHU`bc
zlnWL`+n&sMsV$%E>=IlNyOZ9z<8wF|Yncu|+Nol?EyKy}lSmHc2;sOu$^&-!jw)ZW
z#yMpN+PM2m=`Ec+x5{Uf82PKFvesajVq_tQQfY{?EZ{%##ZPWVX^p1YxFw+@KkZfT
zI^3p5)L`+7p?i9sN%DwhUN}AJfa9asx6S45_uWV|n>Yp*90AWPO=d&lDXmu$LbBxX
zgHsO{F=LxB2l@A;1=de0Gvr%ue#!+^4{{IBYbpYM?$Uo+c=23?vMtp?>BuIhPZF7l
zS&>ue$v;W}t_;C*<jL3jrkyg*5EBb8)~=0N@sVvV-}b7V?xgae5ZlSMhYkTW0I<3B
zBOPkS;8#6A3eL4@81jx7bMvk%MIe}=VH=U2tSACK-!?ka+R^13#swn5K6B*A-$knt
z85C_O<LW5^RM@ybFgW(6+RJAw{z>_dbt50GT(}n{2u3P>yVo~$qTiVsL=5DgTp9*;
zKiSrSepNs}-lSU_Zrcg^=D45i{b+okTz)d~{Oa0inz&#2Z_i^fqfj@mbXaGNnI<aU
zig>OkRk79VN%F3mNQVF~Tz^{KO*d5BH$yXhXXEj$NbRnI1aw2}ImhEb9&rub<kE$E
zhXbc8$gQ{_Mu;OwdUY?!u7cykR@VeKD*ejmCWw43Z4OGx!#&HI0OoGA>xi651<Zhc
zCcP)Z5wmHD^W~X-VtUp@T1Bi}d8Z?>JXXD>@7Q4xB=IV*spQbcbPa4vVTlLnOj|IG
z!NIJT*SQ<D1<#-&p9Z@ejCR~^9-@_i)oWI7uhOG?R#Tt-3aK4x-@LdUw6JP$Tu!m1
z`EI=CiwL$Yeq8g9T0?8t=O0?ww+kd=at^|*eVQ&fAC)VVbN>Kl9AtiUeVf~#rE~(>
zGyWo!!4UouPrVlz%{7+hJCK~x3kLuML-^N9AwkC9&XdRl=V%nJ2RHqla5||O>E4g*
z`9UC|71D^tdJn>sN1gzp;bWN^Y@UFMQKZT_>-DaXqXWnCrv%S#Pqi*!vCSPWPIL2n
zV~S7gi5Pv)%vVw&a6iJE_Iwge7YiJ?(HkFd{YunrqRq$8gI!Zw_v0SsgB~%)Dcme^
z(rGs!<oxH?Jq0>F7HLWS$<8{SmDdu9pPD?=9iwr?+kYB4g=3dK8I^zxIrZ&PH-+}_
z(?Y)3u9?=~Aid9SfYe)b?EUvA{pO>Xb~%Ue#ByNy$&YoQcrqD4{{Ty2?5ZoN2EZN{
z-zS=Iy|zR9xXX6plVdqk@b=070M^dUj@YNi@bbYMBI@9KXCwJnPWqB4$cf4H?@9fr
zdHumY*{OPr!~Xz;G8hzprd}`|7k&jkKMdF_gCpGW$1)R|**c?uHpB<lH5=baA;5w#
zeRIt#1=(FZF{Kb2W4EzlY5xH5jOjxM?AiYSfiV8GsdFk5hQ=x1Z@I_%+<Vbs+>vxW
zIY<0?#kaT1QjIdnPJYV>Z&H;^-AZ4HoRdrEN!QF`ed*XPXp2Y}<XB=KK~4V8vkklK
z@Nf0N6`Ea}_}lZQ5XXjnz<ScK8iq7O(NuN-3PNH+H_n6c6_?0fy+>nBF(Kz*<Gnip
zt>?l?-8cu@o9D)Qzv)?sfM*NVqz7rmAT$lcW2+K+bfz1q$ruht(yEMO6q|r1orGEw
z9#|>-O)0r&AL_<E0jj{{P!Ic9rDQXO@dcP$!y;$r7{zmBu<M%bb=ZT*U%9SMNbvlO
z)-_e6bkX=o;@->xZqI7o)9p_z;BG#(pJs@!@~=)gu8!J73cH4Q;<=`EBIGb2jBNuR
z;+}2tcmouRD%9%vA1_}@i<Ckvk9<^8!WZQq%C9rB{{RoxtG~|K=QPu>65D^O>G&F(
z1o~7^0=WjJ=hXfc>QR;8k1D)vApit)_Mn5B4o4JZ6VG3I)WBSTJJM&Kv@xJI1poj6
z)Y4=hr5m%KT4`Vn06LUoG|j;K(ig%0lmO-+aZGda`ySL2%{7?+0QKktjo0kFo2HU5
z6;C+tn&*p=*1L^*J@%~FEW@D&xQm3^*zH_(V`g^ImC(a4Iq8~;NnE!Ekb*P$QLvDD
z@mU)YF=qFv7_u*>DtMp@azJ2vRCfa_j-N_ovohiLWPY_pxg6E$#?@{(`c)HMRQ5RM
zxXwtUG!dTEm7$Q~%}WyiaL27g4_aEZz`VTU+N2+bYNRjgR+WP<y=<5V=xMF=#VZ_p
z(@D?&0A8KMHyqGu!yj4?Uus}6Nmk(VQij;U*YA4fqsgUQx69I{fp%~7n1sl3N8YL=
z9(q-qNdnE~H%1u6MR6NPD+B9D3hZ%A&S}T5T5b&{F$m;S*NQ+Y{f&c9FlSt#=CYiu
zQbnCQ*K&zpf!ei-4%i<`d~hlzF-~an&o$27%@Gifo|R-K)W98SB1|@V)qx&Q)7Fs8
z+0!45Wy>GTf0b?BCf53Otf|wf!9KJBNUj?>Bk-=DMca7;+ewr1?FZJm)?C)Fhi<%!
z(4ck6VN`*XCxPrQ-rhjKh9@VXtJdeZ9`&i>y*nlw#6zFD*!T6U>r^3f+<MU@D6wt;
zUOCD2s_NZ3j%sU-r01uos>6={^_wjlHZzrF{(X3^n#%WUFU(Fjz^*pc$YIanTegzm
zfuFnIH4L-0w3tbb*{hL-SvLyiY_6E&=f|<Gg3?hd09a&@DFLe($m!ObAj+K8ff9LN
zA<jEhX>-nNrVi-BO2uMVw_1i@k{J&i15*LHskbSMNeBdmT-A_xSBj<&tjb1l$jx9A
zn%eO*1Fc+OW9G@ndd1Ha#1!G!nrJledQ$+-N3Y{S`cmXl9+ZSMib_+~n~DHldr)#{
z>N?PI??AxvJJ#Ngv3X;6Tviz4>svZ{6o@eDX~daqbvE}25CK;w+}4Cw#d$_ypFvm_
zvxZgR`V)?oyAGQyh!|ylwYoW^b-o_drjrbWh69mWl6a!!S(Kv;5;8hgCW8w>I-pP(
z@mBR%nmNzQ?oAU{Dx8UA@g4Iw47e4Is_NG_C{g4jXD1_yc>`@_>I?%9dcmDYtLEh3
z=A>61wNH1hMM|yyO=8UpV{0G3QmDszsE>?e@~M=MQ&KX>P)}M?00W*Wi-AhV3TXiZ
zpa4N9ip;piKRVEyhB-a6#b?}(KBAb+Z9#|G*b&rY>0DXsj+|Fvs(iNPbJx9b?f0tD
zoQBf#MI~7x(bkGkC=gN_QaR?69<%_XsKKv5@Z6iU*iQ!_R{@SY{VTNa<6_l7@69G!
zJF7`@Id8(XpmU#0Rt2LB_5AB<*zQmV<5@DzG#iu}<US!-dG-r390At4_)is2#1`V?
zM43wGXzkvd9i&XQJTOETgVc2gwE&KB#Y=Rb=?|5|XKAJ?W18-X&c@)HnkZS1@}yQ(
zZ)%h6YM<)YCbdK|<ThlVo2^?|qd);7vm=t~R^xC7rYiIrb;P{9gbK15C!G{ejnvk>
z1mZRNd)0-~(MQbL`qil7h7dRd9@Rt{n7fzmrqSpPK07JdzIQz<MoYwvO5_Ig^{R&P
z-vB8i)KCI7p48_wh5!^}ifoNL9yt7I0FbT^^Qr<1xVKv{9Y=cSOimPTu9i*95jplX
z%}7f~a&yV7YMRpkK&$#((Zh7I%rcAjhBH)AGI|=j3Mw7h#yWG-vfS5W)U?ZWmLJ_t
z!?@d3^?7zkAUP+3TQ!a0-A$o|mn``i+w1REF7M&Hk+YNU{VSfPnjKJW>PBvY$Riw#
z)tThm3lr#ib*w0@@o=miun$0MM(#kC*w4&*RYlnuRC<(Rxpb9&P*e|_J?nbW)_Y`;
zKI>O3(*r)=%-2t1n=O;+oK(|p=4IGd=IPS35M_8BO;dzq)zst;wXhvz3;v9rfpJqt
zxNk~ju+6%C1z17#sRCsg0;i9)K%D{RtR)~U#yK99WqNy6X!#!XW-3D-ewn3SdQu*=
zql!R0b*HJwri>bL^rSK1W|yrXrR_)#W5<jW!*VyH4wdHe-I%S|gWJ-*AIIZ96}Ug$
z=Dfx-Cb3@ZRB=EU^J-5fdF#`Tl~~OqcdbUVQrotJP5T;ubPsw%Ge+Xv(v;3?Pwbw<
z@}OJer{zV^8Gciq+)yIMc&%TvG3`oi0O~2+43dOkj<h^Qmx0Y|{hvHwWKw;TJ&)l<
z!p1tlRCN4JI7G|qTHj$f`=|4#ErWk_ieoX%XO6Un2J2g6P3_k-t*1%Q4E-rw3^8uZ
zd**{|!MO(pwiivgXE=sJGt>&Qx-Huu^$vd?Y1~IY_HRK!wtkqdlluby02%u+RrhLY
z=$eC)sRC#H>Mk>#Hk^IlX$_lmg%#IF;hWY_SyUR8JS8zFbn3r_7ZJvNnfM!XN-cd>
zyJ6uK3=3VcKHOA;!WMf*`5n*Ji-E&^l|au*X^sWty?3L+dU}ubIrlX2;fnx2)bal9
z7YiPBB3sD2Nyz$Ejjo&FsO>z-ppHpDh__np4~J~Z?GX%pD<=N{!8W&&D{f^~>Z6U-
zFHq3Kiu=QM@A6qdJ7g%T8tZA7)}UBhB#wJ3;<|M3E|neuh!g5btvhW7!q@#&D!3eC
zm7j6x*z#*#3sROvWw$C1WBxVK+h~`<KlMjF!8PBDSXAQ~`igr-p+bdFK9xc^3!6Eu
zllRC6(B_iJ;%syk(0Gafum`~DgIv@sQb0#0iwNyfK`pQV^%a_QAnm!PIVYt{WivEN
z3F%s~@}ScZ%irnZ#z0k=?&B3j_&xGHYkOZI)j>Q~3ydWINn+o>#z6HZwC|Y`-*y9W
z`qo9GV&k53SG7XFWe0!<Q%Gp%uBI+<G5A$Kz0Wly*ASN>SZ6rvQ0@(kV-yT_0sjCR
zVUHwpflnDdIs9qG$pL5)075#FYUQ*<sUxB9Rfww*KbA75pRE8_yH72SR{_0hra)f5
zty|P&GD0#39`(+&?yN^zE;D6VdkUHiZwhch>0JK++FTyLtvzofTw#b5g2ziNY1Ct%
zN@}JLBB0X@*U^O-XC1n6T2E^63_9&KKvreQq%rZ&H1fFXOP#|Rqy$PZ-3?9liBsha
za65LTSol1FQM6}wQAiEFJ63)a;E`HVS;MMFvDfD81#)UyBa}Rf+|zY;kDn~>1G(!+
zW+tbi-0AY2%EdZ^jMP>-gw`?uA1Zqq?$+%u;@c!@<c^h*ap5RtlXA>q2lznE09vrr
zVx2?%?`-p0CS-QRc>~<m6~Bho$@eAuaB@c8wW_TIKz{cp+*FiVP2KbO)S*Lh(y9Hf
z1p_VlQTEiqDarJt1+tqPf+`83Nia*C`evz{*K^PUJxxa?=G7(SRUWyZ4QN)~R0j%w
z-ZV7U;PE01dK%<zHE0>RxkKrL%}IA@aTSl+$~=g1fSmC~$77+A`r16<@&#9YW)ve}
zWA1B`ON~z8?Y7e<U^*7!r%fNkmn=5hM*{l03Su{(Sa}O<L61^uzxJG}`7EpGcXX;L
z;C*7{Gjo6C?(Cwj+k88SgZ7)*r2271g5_(SW*F3&E=Esb&+@3@)@@~wMvh&NbCF#f
zUI@{m0Go2;cV;!KXQFAgpm{cNsrAJJAEgEs>4Ur9+O-56?!XLbk)p3m4@z^p5(zw1
zfhxcl{NJ5P_H<vH<>S3n+*_gIlN+1g-heF~gV36d<@va%im>Rd^}(kI<z@L|e0t)T
z2b_H<6CT<6Ql+KK^ohyzBA&W#qr2s`KUQ!B07bp2e8Y;j{h4^j41j$NO1dPhxoxU*
z*|SB2Pz}#Noi6_XUcQy4x+I5#I)VP}JN^;q&I!AJz)%J|5uaL6;8w!ua3IH=?e0`_
zQYMdVzw0u}duD(z%(&@HGq!nL*Gje)ig<v2bm3=gt;M=f2QJd*qLWAqH{DWxmDh+N
zTw*m}!!)1;BWPdy<WmEZSfxDqZhbhZzRhrYM8>+zu^nj+Pjg5PX*Ao%$L?5u6y?!x
ziTkUM_p75Fb4!2+N?>#2L%w0Pf`Oj9s$rn88Ijhu%$WZG3Jy*<Gy#nkgS$JJ0oNz|
zDr2A{WBnwr{06k}bM5a&C<8roD0tmGg!?EIzwnOQ5;wE9J%wmz2As0vf!2$GL9|^y
zHTlqy?r8>@r4fN|pRHVE^Bl8t^`!~NtrrnlbnQKQTCP5{{{XUC_O(n@<PS;!$2gz{
zEHMG{+r&TMG~lQR#A-4A$ft^p)t`**9-@JZC(OG*3!gzmVNhXI3TKi74!@l|AkSJ?
z0p4d(%>jVvND+9*rxgHZi-m)BN3}*t&mBE!uJ||#aqCJB;ogggkTU^GxRc4nAU~BT
z>qWp*$j4etP%=AH1dPq{sUnMx!=DN}=7`j=%YIZH$Ba{eWB&lwqTylTK%i{*rUG-1
z;-uR7<E;T=LJ(AMG--|rC!iD*!1>4n+|x=%8*zBXJ?IM)s6x5hic%DH6;<vcRmqu0
z<4hN}x&Hu<l{n&yfi2<(w3K5!SBvXV`5KJKG4h=8Uc&l~ipI)i$s^LdtHmy@s7UdQ
zDHRWJvC2(0Sgv#Hij3L`eto$<^;S%ag2z2`n$om#RAqSet)SW>NUHj9W%-r1pH3<z
z(5+pv$o~HTHEzi#n7uzLVz0_ZD{pBgMU3R|=AW=1DVx_VR$}npn5r{u4t-dfyBpzg
zR-<sesdLM?Sfdw*^wXT%0rX>14FgSIyKFf1HLDw-kCpst6DCg_QudPWD-;foV!w9T
zSKgQVHqClL812GUve*?FlP85gg&xvf!<43M;ZBh!{qxq3Dll`i{{S5oVnkvyo<6l-
zIc$3NrR^B`Mx-gffIljkZKKZY4Et0C-5Y`JQYFD|Gs&gS9Hhn-7{ac8l&cUuRdN39
zGt6A_<AY8UAiyt6m^n$7J-iLSl?6%fO!MQ$6~zrSL#%`FqnJ5I`FwTF8#u=psJ_{3
zKjo+fnfA+a-|L6xOPD!J8%_l`Xy&V%=tE=71bT{TzqSFtc%%<{Ifu$v+5qWE<%9I9
zPpaD|8}aX&i0by>f306`XyzXwspY8PQyD^v%R0@lKkJwCsNY<*B>wl2>CGI$%4!py
zX`8db6_fqBZJ+hI{3(sD+vo2eLGsh)4pUUB1NU=L$Pf;dmUa7O7$vjpwAR;cbB(Tl
z3OR$2zRHY#=rvks6obbVSnH61!Z+nnHoAxYSs%`qFmf`)acn0dpOOx0h}M*jA$n=n
z2|wySoYBrcQ&C*G`MQr<oDc`SVhvo5iTcwHviRaZ{CbXY@*AbMbQH~lf>yCVwkG}+
z8TaOctXy>9deY_&L!^cA+O2toln>=xdDd?+jIKVE)2m+N?}7BAm^lu}&Bt1aq++0F
z70De|@SK@3^c2&m-5#=>QOrI=tztIio0?c<1ECejo9W2^09e>Pd86&O2dvMJN?hai
zXKG~yKK>0fP8EpUNgjhW#WmF1N%LQ)UDfHn3yLd^G(VOL70WT_Jk=&kiIUTX9B!y5
zMwLg%=l%j~(bm>D&O}N0El435{{U8_{sUEUSn~yjYyhxIbN<PxVYIs3Khfkl_ODFx
zlpJke%9KayxTSO!JnQUNt@mu@KS5R_vD6g*0LP4kSAG<ZohkYJsa$-g0&MkH2WFl?
z{{ViTG<{W5FJ^Lj0OGr{`0q$u73=v?aoF?M@b<dxnBYjyt2i|f@OHN$%gVVu>(O(8
z#U?UnxLDv5!Me|TxX-bxk@!mec{fr0HrHlA&q@iR;bWCg3thH1UIicQtw`P$mw;~o
z{{Vnyx?SA#Ij40}!j55B<`0DaY@6vn1)=;IWgz+Ha(!#39eJa6Sn--J7CE%=R+_7U
zB#JulYDDmkn5(e)jri9@q-UiunL+8zD~`q|{304Y2{!p8(f<GleuxMBd4rCXxCn04
z5#K#%xLDw|Z9Xe0l_CnG&>Er#ALCsQiKE)+!x#gRis#qn;}uEVi6Uz-qUj0en(b_@
zt)zf6K#p<FMR3uUR#Ti~*1Me{!&>lq^FtCY2xC?GEzl1@v~0l7mZRvkWmu>naZMzK
z;2&z6nh=293IX_2yte)jJ$h5g2k&rcLlE0>nl1!*eDZVcM%N<@20bcWuH@kl6bR(!
z<ut;?VSb{V7ai(Uf_M9nxu=Uel1J`{C$Xh)u>+=7qX3GyEUsAXDS_)j({6Hh#gIGX
zPz7AKttjWMT3ssS@<{fljV6A%LHN)G5=LnSXpJUw{7PtD9$u{~3INUr-=!uF?AE&I
zg^xD?eHNg)(+#|#e9k+PD7YEm;B!s{X0N7>7-gmd{sU8u8U<b)k5P&M$T%Gh0D;if
zx@i`>u-mceQvU#D+6BhO9{HdQ0$5UlNyh5v6HT)Nn92IKY2w1s21I=KG=Sz=_P-|?
z=~4r@b?ef)L2qmi`lK}B6}dSv55Q0dGB;zn`cM^*Pu9AeMgaZN{!|7EKH~mV0nGUh
zf907!g($XR{{Sq`f8DN_N;?6%lsG+cKpdOw3{it_>42ov>1itf5(zo<7_Iw|Ukre5
z9WW{I%>GdikZ1!J`zq)t{m2LX>QkiLcK{rBHMzehj?~@RJtzYmba{_bxIXms(H}W3
zpH8)@oPcqPK*Rz~12fk}UNY<T6z}YKf4`5`t~*Ev$Z=J~_X^)QO}XTX1T}Q10Oi=9
zr8wz!pY3s0l0{_%3Pw2?z@Q4_PP6{uC*0GP!of~Ox*x4ckUeR5&!sRGZLO4XZ5a9r
zbK6@yMSQeV>IFA`af(8~_329BRgT#seX4+g?N-(Z@&2uTxTyZo9Bqt%dvi__k~kCr
zDu96Emka&SJ@HY8;+G)M1IsROarshj+HeLbgemV$$X<<_0GrG!l4=FIC5Yq?b59My
z%W+lZK<||_0dIaN-bGelm-zXohWF3bfFv#SrjkeTQ%TSN09um@X@K(W)2F>fBqC3~
z<kP~b^~F0Yo;jch$H*|R#U=|My`QBez-1r16$ElII60&Q{WvC!FRdV4`p{RNlmMWh
z_NKImr>!o`_Q|9%q2R3mGC&=70)GQbZ*o<(IX{S}s0u#l$Gs*2Z@ZcRvF0!EnnLP1
z&*@d(b&PYKeW^U<BP-L~Pz8Y?UX+GkLHN`=v-G6|W`G=ADb7s>OrDvhj8cHB-!#C6
zThNjOA-%mSb$sB|az`7c-u|@|arrsHIQO6nMY!ZrZaC|Tgv-xSnrV~k^q>nFKi>Rl
zzG3N_j5wrb0)QqH0mettnYl^tQSR+d3{)Ia0o%?;T6THwimf9P&p(|yDRSFfPz8<T
z_WWrJ9-Tgvgo;lyY2y^YT(@=4;Z6=mQ9zjXV@c+U0IjIRCAM}{`GEV`uLbcGuKMM`
zcipt&y|=^{!rMoiYZc0#Yv=i-X|83FpK*6%%?JlZ$9HfITqot@CbQQ&g<b^tXZls#
zk~rkVpL(?Ik`UREh;GKRQ2ze_>&<8l#OHQs5z-~4oROmgxld!>r;ozAZThnalnnFo
z*D|xptFSrS>08<@+{{XO#AN<M(yHJ}-VD+ck0nX>6*Bm1N=M?_B6?=Ee$MPpBsir@
zS5x=;(gU2hvCwVbWU;~<up+BV4vY&0xbnx{+P$fsD6wcABs`|!yFRtffVlN1-iv|N
z+uUi;kXG=vIPPjz)U>H&R5J%Ga0bI%fglWY`WlE_GR%QT8TpU37X!Th$J1v(<}By%
zr>=>m#JM)fyS7f_RV;4a;@C3)Ffs2^$#)C@8D$B$@tR^M8g`l+FKrno`@*e76^uFZ
z;se-LQPk{mOI|{LjY>7GJy-rdqsOjk4Bw6Izvq(YtuL8u8~suq{{VKd2Dzt(`L37p
zq<;}<%ExWm@!FNZ+>-t~Sd6I(lh6Pw27engcMln{-M7%ym@gu`P4T|qdjVXowQnRh
zgJP1clabrnfHx10+<(kC{{Y`r6rMDmMatVox%K9`Qb`_$n&$v!ft_WaiKn@g#^@r)
zr#ppjEbhyd$35%KEoCv@BZIfp`qzJDaAmbZ1_%@gz309##8ZCKM*x66l~k*qdr(!g
z&q`oUW+$yG%Oaeq{3@wCO+8wGCz|3}BMNXUD^rd~w#j@Bn@1U~EEC`GsAh~5AoTuJ
z0mI7du2G&sM{UNVFN3*D0z2oLx2eEknBh(d>Uvckl&(;Y#Qo#D{qAd5LcAzS90gOK
zm$<A+8$Q0Y>p4t!N=F^26Fm`TR$PPEwNDFTP{VM?rDfPiWQTq-K<6E*;xQx-=|GOp
zO4V(|D-4o3+wzQZO=&i#Y?;pd4{X;HZ6iWUXYY2cXs7cO6;>ek#X~6@jjh_NZOfl?
zz@-}09O5=D+tRW&sp`L-C{<pA6pA&@uzqYrqz`&w)!l|fNPixcow|jQM+YSJ#RIXR
z+Qi#ISde=2?@_j`a>pPj^%&_?*_Y|*MnU$V3!mCoj6c^NeE_CC-0pJIH|K#>!2bXy
zmji-N;3xt^bvRrJoDcV@ziXVZ%+K=nG{!4{1}ZP0pb3nU6T8e~^)#7r{BQpNeN<ug
z`_k_Obj<)ba6Nvef;~FYWM_&pXaPU~5Lff0AwcdaH!uT=0VlNpI06q``(~sZ4hJ;M
zw%%z&oKOSP+*AHgYO!OUqwu8MPkKOEIPZ#0{@;~XE7&ooEJX9q;%EYW_%z?WoYZ9)
z3Sr2`X@$uOfZux_)S^wSc>=4FGI>9ZARuR-&VVin0bXf_VYdRS`HRQR#V4AdS^%8B
zNZ{ub;LI_`DzUg8*rV+L4A2DrV}(18O&(@VR%?{UsT9+7j+9tM!zL8}04i(D!MI*3
zn_U6P9MXNTs2If-0_WOs_p%A&ns=N}A*(&ELua@2sQ%T1+MR%hTV6ru=HOQ`IQ`}i
zrF9z6{mPI}UZ?3?+~dFTcdlyR5z|5Yq%o3=2>h#F-h8O%AJ(zS!N+XW_R<o;2OibW
zBy~lb$ukl-81<{L%0hElkQ20jD$s>+zvEe&CR;}j_rD6Vkf{T%Dy(ak{(`Q@!1;|K
zkvjQinqT#)CT-oml>)9-yKs`|aN?uXcK$u-p|i~^413dY?_I|T?D5>>&_x(H;*YHY
z5R8freL7K`Qf7b-ov6qk{d!T!^rR{eN&pIiGl~Gmu%Ic&tpFcN0Hvy;J&cM1jx$^Z
z#}Z?YQC^R9fvw$7Od8-d2)wynIa8iSYo59~u<Xn{p48<T^raE=!2IdKagVKY9V3VV
ze_YjPIc|E@h9oKJRb&~@JkW`epLTY}NUZkHy<WTNfzv#LR9IwJT|JIEn~W!#OmR*)
z&r?n9S{VmXOU(j`U@m#%wOEcoc&gp0z~Q?76={KUIi=5`sFAk{m3aRE^;W5fa04AE
zBNVE+&-JGgF^ZreJaI|W>q^|yPZWTDa6_+AR;MO=WsycokD952k&2qt@wztQSX3}7
zW12rYl10OwGf#peESnHzy((KN6Iocj<-*2?uO~It+gJ;D!i57J=+d<R0I}Puk@Ghv
zBDD%*sjg`|nj(RVC%$Qd9%}QZdB#4KAD72Uf{5dfk%7fbR||p9)|4l|6y^hOdH~M4
zLZ?0JE_4{l&#i1up!(*src90p=Rg^xZ8^tUlFDx)_A)sHfrCjRV1bMeN{4pY6^Y?a
zO*A9XFA&`5$DPCh*101xgux5XO6s(dX41zcvIuO~8K_3qw-U#KHa0LiR+HFK5#M`%
zjV3`oDyVkuahj23V!pMDG%s7W*W);?%VD$tOhL20DF?PV?_API+qzb?7or$bC#OJa
z8AkAtV;-DRe{VD|wHuuNCb{!<H12kE`gE-eYeE1c=994XsbfcFpzG4zd1)&h*&%qq
zHPOt#wn6J$eTAplQDv0vWBfjqp=aV1j^x|iVU+#Cf0a}xXJC{ru8rto$<IMjU9zQw
zxlz;a8m0ZFp+?=<Jq9X{qp3>vl3?T>#A3RU%F*IpC2#niT#!1k81xm7k9yJ8pUl*!
zZu_~c&uU^rg*&x3JkpMxX@KF<j-rzkhp(+60rxbWeQ9&}QfDH8hH!h*QHm%419Jc?
zptFl@x}1-vrC~sut|MM~YV4xZOWP`_#(UPZ<8vyG#8&q{OK%IDcExEA5KewnOlP<?
zS}hiLkyjuN=C7`o1%$q7A*3S&R<<y@IxP<VW_1z_w%^vbZs2+C49)yKYl^bHm2QGW
znaLH~MR6i&?u?k+I5ah&uV!Pg&(g8=LIj0!Gm6%5cW`l^O2*YTiFUIMz;Xq1%<X}k
z4t;7=%|@X1sUuQ)*E>d~ggq*CIUH0Gg1O?SO!`nVWjqgRar?B;TR(P{iQ9}+fnHDI
zsuOUvdO~tDR3<piPJWaO!PfA$ua8U*t#VF&Z))lMLh5by1{;A5kMs4eS&m6Hsxy$3
zQA<=vQjAhj)`1Qqjwt}=6l0*l{OS0h04{5@&|sD*6u-)?&{rNZF^=A~*=Sm%Q^K~+
zFvvR4QaY<J#QS>I)w3!dx%R9pc^F|q;<YWv3=bx=Wut!Gi*yw=%q=yPso1SWXhzZ7
zHFyEFhJQ+xpfka>q)UB9SVucp<29GLf#^<avhk*u4Zf<<ZO53|+&`6a(oGC4@~(ch
z-v@MaGB~W|oaMen?rTOHYfDxP$gS>0WyyTZa5MM{YDF}sjO{+Av`?`N=#HTbW93i}
zU<F2XX9sHXy{eV2lO(%xKvUF~=C$I}QY0B)%CsSre%W&=KYQy_#SGG~B$9n<*4t=D
z-^~fA+eMt5fyFXNe#Iu=x@qZaAp;z9=~A6t8$Mc+Dlw`|#BGRuDcn{O?B!FE?esMg
z!6tdB<h!|$XUZUbDg$$HIl=cBpa`YPt0^680&@z=_+Ohm<E3<RN*plhkzDMMZ<)wb
z_m4FdHAavaE<RotwK@{=ILSWsBvwGSPZecijx2N@^@*j;TVM=81t5BgkZr*o>Yb&*
zUOKO!t7Vc?kQftOwLT-VpTa)TF>uE@_NnDQY=91#?@?REBP@Lf6*a0fjKv0e{#0Jk
zB5LfT3Msuj6S;s~`qx<sZH)r;1DfWo<8SRakPP7N>s?Z=&;T`5%n6}VN4;Kze9OiU
ztyGJi1zUuE`3HT~upMM45ih1H#Ak}EgasYAt0~f?Wa-wXQ-e^(xxuNzh7^FaA0nqi
zwAFZq2TGlK(itIaj@0!zsPWL#*P1{}#%Wj7(|-zh81G19$0C<MjWkobia>LoHBJ5(
zycp+c#d&U&1KCGjt>Wd+hi*Xr>EgVfL_4iiasrYldk0fP?C8g^slT&g#^X2PvZY9e
z2BzpS)K+ZKBRtrEO(3yQf5xwp2R(;sKsOF39g1IKOm(1IDDPJ`9p6e^XNoQsC^fPk
zPgCtr5TcHmt6orJKta1`Q=ZhtVz7-d!qSoyecsin4w-Q-Fp8>1a(dR4u9A^2&Uc^o
zg%=AP{1&EW!B!dcT-Lpngb_Y|&dyKqHEZD^UzJHCpd3_TrIGhA3+N~d4hiyr5PlS<
zJPt4oJ}|&z2kTE@-2(GKilPF?El=_|#^d=^xn*o)2Aa-C-*487fYEF_(lj7&1uI=f
zycq!c)DNiJFIkjPa2(d?dVqekqBI|LoP9A=Cf04x?cex;RbO0zPf|(kObuxtVc`aS
zO;=*X<knkj@Pqd=$6eK4O?(6LMn5Vn2H8AysF;8`HGum3$D)P&D!c1fEJzKGds7k6
z$oOBBXX{Y_-^4~MoPAR1*B)yRVTyt8=Kdz2EOkuE8<Y7|QcV(!ysD$z*D7wMJs8tW
z(h^HQQR_fh)7S1HlGucO#cPv@;z5zlYeMCi#&T;hPw#Wo^`<6t`g@-*`c{KqM*@)9
z2hi4LkV%iHxu$AzE6jH1K9tD~TK?YRFsq%_kX#i$w6_Q3sL%r+S^<Pd_p95Q*O5e)
z_;lQaat&ml+bBN$YiW75$7(}4yNxE+XZwgb&)ux~d_08wlgNktmcXuofDGIow9=!s
z139M9XJ5N`;QOv=pV>NsoGso*uFC1c=Z>_v&N@&BEOh;0F^!Hr_@<kEU<?=#{x#H)
zbL&nq6OWfX&=xrfQ&QN<_Q#(_6+yJ?=4}0)g?Gj*o)emQvm|n#od9{@((g0#M8cdj
ztDt`4SE36o_!v{{YUEl<GU83Yg3+KHMuyL&%p{&C+v|+hwf?tY=Wq}1N}B6NiD*=O
zoO=ofhV=INo&+b{b4Gz<&RbW3pKeNzbu}QqwLkLNKRWbJ_(rtW{{WY8$JZ1ugmk7E
z`y6NJohZ-_0dHY%lt`r0#L*w)=DW}MLG-sAS%Lom0nIhO9%+q%_FR1drJx)sWn-P=
z2i~W)UBs1^HOH%0W<D3#$a1#QW7wLQd?&RSI~_mZbZ7@0nw!Hh3nBnN+N%?5i?{c;
zKp*bz<X2%A!i_mjNYB;k{67vft8t$qCU5qMYMncd?DJVQs88H?fA?3KjddHTm<Tlc
ziF3wJ73^025wf?yMO4RROjX3tt)l=8pL|l#dY(BQuD@^rhfFb#_MWc6;lB{vljhyW
zZU^^9Yu6J<fM+S!)}$Iuuox-3-!xqYr<5mwu3YBhR+Y2a1`qSAaQGKWOc@N*eMzrT
zOABb%9#F@j=A3Qg=oM9cHqp#8&uzRbqr?Z3U>J^aMr%$x1%@FMR>x@Qp=+@6<B#q{
z0reE|xraFV0ZFhqNc8EmkpUltPBg2w81nEv>!b1sJw`n!F}MUT=St%__0jI1?-c{<
zQVkAM)^%KV0=AYX{w^v0Szh^~;xU&&O#JsOK<pNz{>X?PU9s(2zDV__2viKv258eQ
z6kwM>T5{>uN<ZV>Pr0jSX>1@l^`SxPdr@(e+RoIs7U;P2sS?uOKbSz7>}t+4)1@Ip
z*E9f#+dk@n_*2$KIqoVV>Z}JOo-it8Os+`BwE!`TwtjPpXyJP2>r<G*^O|T11}G4V
z$4)32ZuH?8JkoDK+eUIdr~$xn-kL^!?KsH2a7`hQc3NO4L5^v`GI;4x`J@c(r+J6c
zkP-wq;7~@v^DYG<$ikwKNYCaMC)o6&;7AB>T5v!!P>(Z=k&1Vkp?P8X(QqXEDBx9d
zEJeAL55|LYYZ~OtnflNLphhVRuX@Xp^43F{CO95~m2d4;cx;LQ&|fSz?lbFBhZT|i
zrEU)#(|@*OUWn8Iuw>?eAR~@zANynx%sBr5fmBVbxj!UW9;SdcnaSXBLa<TOKJ|tD
zv2b6aW9dlxwBdmax$S{K>~sciVMmw^b4OLUWB#)qyi-2ga^wADeN8a2)a-WTRBY|I
zpm0d8WZlks$j9EHGP&+^^`I<uyTJR>rhc@Bc);dl{OgkQBm=qjCW2UwgA@qsKGkd+
z=DCiT*Y=sfm=Zk&a-d)eP{mYr;(?tzYF4Y(U&9p7?OR@%bNE*>caxB42*>_f5k-Q>
zMs<5-JRv`gC-%%M(gr{9D(8ye43kGe&VLg?8?CQKIzj>TEm1d!9G{i|0Pam?Dk$nW
zrFD(I=s%4BUu|}G7{ag8qit&F02P!D_!UH;^rR7hXs{QCv3TVE^8oq^YwDMo{{URr
z?^OU?_53OMTw@fh0=}VgdGlQRQY`NO05i=XAKl$Z(VTKHC@`tV6j%nCT%YxlAFEI#
z{`T*tYFOfderXk({gF+PRh#8qqtciHw0m-~VEU7qM+{FR0-TGprau}|aydDm2#Ps8
z6USj(pNOF=CR?v+><<GO=DF_>#yp(kG?<S)x<MXaprnUW354?V*mGJefr(zVpL=AW
zZ%zm~;;e(DveES`n1rG@)lWQ{vOGJf5zED#_N~1JaW0sI<n{p8z~Opzr*N^zuZC|K
zj%P*uDa+xTz{CA9Kktg_q$KnldenH6uLtQ*n0%)`JT-H)@4f&ZMW&Ao&5&C7^z4<<
zsgMtw0-RSgt`<i+z8Dz!uH5_Wr;iLpx8}Nk!nd|@%>pJp4n-@6DTaJA2F507N&f(P
zy!TkVmcvkz7>)w;uU#lceQ{nz;}{t=l6IY~Qp-rneO~d2!+}w@r+xnbKLmXRRV#+Z
zX}GB!i$_qsX54OA{sNkB?oS?jRdY$V(w)M^gL`m)<+IZb)XmmbsDQ;O1L;6mQ!}t2
z$i;rN7A&|dO8Qb_m#rWWaC4KMnau^hr}3oe+Kkcw$?y8olSoORW}U!ZohZwC@kS36
zVt^MJ>q(4JiU7#%Kn4KqM{bm(fky_I3EqtHOP|h@@T3+KKdm^9D5U3_0>O@HMm;E_
z6bwv&D9tWC_@&$U&;vJQ&<-i(ayn84pkiW_^rhRyD8^_3nD;cjPZaV8r8g7+U^0+<
z*Qb0rm>Ul%a8Et`E6jkvHR^u|VuE;ONmp@KJk=r@+b7C$a7`i0fAy<g?#dG|2)l9H
zH8gg1_#e9;T6YnJwEaG`n@)R?T?n*<^^6~_JX*pB5w2*sT;|5=HnG720=i!zK;akg
z6v1w%ISM}t0Ot&BTWA?H<+YUm00GC+x-Tvy2Y^0<nsTnu?LZvqw7BXcIQmnCoc+*`
z!n!ip9ePs<2kY-Z7$(YaGE~y8pKx3KTN7Js6F)KLoC=S-Kp2asT$cX;Q~;>{$2^a*
zP**{}ZzHWjBLT|}GfLoQu8}zIr{6Uo(j5KfABAay)|9q7;+Pp{M$QSF9>7!AMBE1H
z(0&=K<%j1+@0NfmE{hN&GZXZue`Q7oGILiDHhKK1w?(3WvUR0#9Dj@Sh|^7HizUZ@
zdf*gdy-Qw6E;Ly~WaJTEUW!HmJv-*A1jtjt72fzfLv?OUi;<p{!a8xB*I(edu_;p7
z&Kr)y{EDU|cOt^f40&hsrE5!b`~&D|`@U@Urul$%{cAgxR9I3wki{~-;<Om1Kh>sw
zm0e^Kz7q|OIHwX-h{&SgN;cyG6OU>@ew<VxvN)w2dJ14pA3Zpuc4{rlNM+*`fP1#Z
z&tXiCZNs%A$_nkrT8To((;1)(Me#vw4!l$f-;FPr0X!Vj0!{w_g*Y}k8i2@8K}`%s
zM_K@|Sm%mIVIutFp4AeQny+-vjliBd3IMhg0fA4>0jMF6n8ruvN@dB$IiLwLN%W=8
zO*e5P{{XE@Hqrt>*y5Vb2*pP71@%9LBC&iB7!RcYH*2f&$f>txk=tT?+59Rsm1G%C
zXc;Iz^rI%2K|N{XkwAdszv)I)cczdi;0geK&;~~}3r+-qJNBoSIq6Jz)tojyZ(0UD
zUnGpu?&;4I)j^7I9MBd5dFenP_M{*Iic)X}M;}@O!fqazrZ^0}IHz?y_4J_dF+hma
z1srjje^F4%q^ahgZpc^X;E!4WaSe)Z&G=M>&>Uxq14o{si-5qH<n*QT$UV(Jdirrk
znu39l%Wu7YZVfipDI;PZk=u%&%|q1FOv*iI0!_WS`qCKpXFruzYvd1rgnN@xdBlw1
z0YDOYAW{VbwMNr0JbpBWSI0^OSPB?piUev0N`+(~bBY#Ro=pHG!Q<p8#X2lXyl~y<
zcir;j5loICr~9L+#Q;oKjAQYp;}p{2G4p1d<|#A*A>eoXDWUrFQ4@}&kEx|nfc@n;
z?V13Wc>edbG%~LoR7}dJ=5-&9Ms6Y*`Nl;9EHtsN-jPSt)J=T=$Pz0bYNv8wkOw;(
z>NAQ+r-UxTRYd??`)qyq_Mxv6JY@bAQ|%VvzWyoy0BpAdXvz8t1X=r1cSE10J!jAG
zpRH%fc^Et)BA9gmazbF!14dZ{i_)M)kT!9}R~O(Y+=7x#R3h(Kv+QUB=q`B2<w^^2
z-m_O+$iR>F#XI{|vM~@D????5$){~|+<{p?+HMYZW}W@9D}266uj4=(dw<$AV?0(f
z>XY^>$81x7w5K^6lyT`y4OyabouqzM6l%xib6Mk2xf#Ttr9^J#`^C;p1F^Z~F&zn`
z$-wJaPkAd2WRpIdsz0?kZ0>G-4FWn9OnTFTs|x3S(*2}w`|6t0J04xJ{`CNKEKoNr
zKAE9jKD(Fmu5iEmWSWmE7~xl*xD)}@`LGlIv2#o^LO<oI<J!5R*~K?@*7Y>N>3-1w
zAL~?9PkU~wkun^170>S@zvD(vu73(ZP2y{qWzx#|fUmc$c#MmQ<mtnnmFw5BJ=8k^
z$6kFa&9$u>;>Jdo=5)?YFfvD4xgK_8)kOews}Yg3)e=;ePcC9J&T93g;FAh@>}xvU
zW>QThvD-cdPG}LgxT|woT4mcsI^(JBippd1)b`T(QY(5MJ?Vkn9YB>EPJKzCuN{a!
zo|Q(>Z-^C9f;*a(*_30Ur*J6ijxMcRe}3NmD~)51y<ObsWrWAHWc1B&+Js(B+>7^4
zbB|wILm+7nW74WgAuM?Ir^s=T4M0iF0y^&wT<?r;`{j1y`qqv1lO5CUVYnV^l+kW{
zn~|3Jw|uqUTeqDWob!rcV=snm_U<Zhc_TGeT^`CQ8#dtMu{F_>LF1)Yo+LSUJ$<PR
z%7;d=eD1bSps8ljEaP9@TPVoqy<CpvKvY#Y#aMh3)`1yzN9^)!7*IIC6#Zfi_U23<
z!ku#wibCN@%~@ggi$>#~;LryS&9t6+dekob;8ndw4<hDHxMSY4i8%J4VYv3ib{ZA#
z=#>lSw>8FaF<Tlf&L&jON2Yq31a|^Vjx$IbJRIZJg(~U}2;;pw8TFtD*>cpOLXm^T
zJgF4WFlm7GY%VBeC#j%g(w(?sfH3u&64vGNK2UL7lbyVBaqC`%aJ%4j>&F0!;B^R^
zJI7ElNTQ?3gVLB7=PG#}DIX!Zq|c@)37x)!eVCOBu6B+^Za2!_mBQ%PEpIaHI6Z}T
z7Vc(^T%Fk+YJ^yXFko?-*R_;|18VW#HIdHT57MTB;KF`xN2NnUM#zwnM&>!J&+Ux-
zq8<lE%?qq$$ijif4|<oT<*iK?GIk^Ks2Sx448sStR+CeWSeLkk7ryL+Q%R`laoZM>
z`CYpxq@<q3IJ8c)XQK*}c<Y+x*HTBzuI0)5rlws(Jsk1xS7I)721Uj{N=?H&Rs(7|
z^`tt11Nf=(h0cR_`&6E82PV1Ud|Ui!4ff&7np~mGbOuDvTv6vn7!NRWT;aONJ9!?Y
z(*?_dIOEozD6Vw>0BVbOUMU*(9N;z&VO;RLU=Dv;VYw$AO+HcF=#HTn$19&oY19=@
z01D^6&_K!D0jSOP*9x21pG78@DizL%>N}4h&~J0w6@;?P-1%?MQ%~C~o{vwIE^Ga;
z{{VOotth<CMpm*!GBEFtdO>X|?0EGwxkH%OH@N;U!h?J6aqU@aZ73h(Px~ajhy%Ey
z!?}Fl1N=?Ly)fQ;ll3)I?9H_0vGkx@7Gd+_6znUO4c<NewAQ>Qp0yX)$m((_MUnpc
zj(sSwTzA^WK;4hVkluiJIQp7Vr|0G_w1&k=`^sprTx(y9pO_z7iS-!s!}C*rXTSj8
zjDwyH2Tz0M!Q=T-uw1TnCG5@lP;~|eIjN0|M}ol9MT9xP&*wl9i^(6LIQ6CT<YAmt
z=T1iZxd*3Oc+%s?%;XR~X^g03m)LveorwwMg;;Gq6+3qv0i1(MkU<&wl(u^kNTdb5
zSqZUs10{M2<X%nr$Ln3S+82UV9d@28jA*vW^KfuDu6#n&+Yb5_8M&*Lp-+0Q$%i~~
zQb)86yz)C5<Y!_w?b{tjeJfH0E`II>V_Qf_03X7(ZLU;jAcOU&W~kALLUhO0q{atc
zYNA}{1J<lF?q6DlGAYh+#W4<72bx(<2U?C2F^+TfuB;=pj%-)LOH0<59PvOHuSoMo
zkPQT5wK!urq&;y!hGQa}R~=~S*R447??4O-N(Vzu>x|Gi=}ZK{?Mc(?PRBT-6ady-
zuO_%%ZZ9t64E6P{^BfcWtCI07AhBYZ8><@2LuxM4Iifk_W`Z%=k$?x&6cf|dxY^n=
zL!L2I<Q)4|$LW(*rW_h^CPrQ7OmojQM;vsk*Jpq`ilp4;x}mYhQ*np#6rS{^lf7tU
z6tsel^uS)e*ry6;{&Z%k0V=)^)~rTD992QhNgM3z-mNe%D8M-b@T6`(Diwhggy%J)
z5W~~8M8leuh6O}L048v1XqX99)IPNE*iq|QO^lvp{oyL5vUmfnb-o?&>xj(rC(dv{
z_NsaYk@oA<nnXJnoch<H!5YIDMHu&}8Zjh~V;l;Fx#?H#(`=nO)h7TobF)-NNgnjg
zy!5B`&L}E#NMb1Bk&g$1PAb{!NEbb58B#^hYNImk>6+A*KDD1Zfx*u{lz_~caxsh%
zRNX=1v}KGAl}bp)eQBUN{{Rb4B(!AedlOlnDYRtNmPS?D<G-y-;bsXxm!3BDu7g<9
zhM{Pw)<pT29qVgeBt03z!Dd~D9971O8*H`#_o;(4LvF@K?g;5nF%CxI(y?f?%8wvs
z`9~Ekv=4CGPVKqpinRs0$oqEW`c}oAvZD0K9V!_`?Keh`$y1dc!nYyQt?g8i%P)GN
z3Hu~_%P0VKHJg9pRA=(-dG+T8vypLEHMI+rM)J|Oe@el+Vy%$bWx)j0QQSP8ai3~g
z-{m>&T&{1J?2K%Vmq@y6i&gVD>Z2X1#-NW4w3+ASBZ|ebQx2aRXZMW7_^rsVmg>St
zq*6++HRw>Ob!Kqar)^Q<TEWh%a61Oa<5VkCUymBi&tPAHS(vVba*O=w!`hqHlpJ=T
z1s_}*ZxrfGbD988!jhDe=}j~Myig4w=9Yn$Eb;cJ+tBo`wmn8c2-}`3nA0G6?*K(P
z9^6+>_U0&zZlEv~tvw7XqBE-9F+V;%g+AVS?rszlzO#Zl^cky~e6qoEvY-KnuS&B!
z9j=av1e=;PjsF0=-j%s`sar|}C{*#*xk#>>_>VA*`gWwdmJK@DoSeBF0oJLqIbF*M
zs)W4qS(h8}^s4%^B#a#hB=yB|GhMsfZ{c(A&1*$>B=G>)EBq$8rgp&($?ck+Hexal
zHC;{{lU5@<b<JYUNzloW^Yc@nkbe=V;^c!?0_0K{29O`Wni-!RY1?o<l-E2|jDkYl
z$sdhTxMBlizjIezgLNjU-F&I*ni2z%*QDPvj9~Z2dc!?yOIDN2yI?^DdVM&o%GDV$
zXrhXuLV?8;Py>PHo(SntjOLs<pk%9BS~~>4LDN0!GzyvtHeE*Ej3{G0D#85Df1PXF
zxX&jYD+5ZDJSsuYY}Wm_RU>~Uvt^^Bv*i@lg8kf9ZILXawkrP9?@}{?_=%^?VOy9E
zR2-ajuQWE(NXH5I*Sq+F$}5c_)qy7j*Nk24wUv=FPI{W@qpC2dtU(2$Cohkos}FZ=
z3XA|;R&<Xf&4mV}k4<*}09ldv*HZE^Egfoh07VuDwMifLjoNb~4)`>&Brt%g0mrRd
zj^TdjI2A~SM7noFG{-$~D$I6vs(BebjUkhAnj=S&Kotr1HAI(U@)w1Pc=Qz`Tx}!-
z0D1vLHg4X7*P5`}a%2Z`J%vz;l3X#1YWJ!n%6g@1u(W}3v>bjlM&|Jq{z#5H8UUpt
zupcn|Ydx-EU#(xB=#WOr$&xVAZVT3;WufhO2q6$uCCePsj95J}K?(u&tXZNrv~3~p
z>_pM?AS7a~zLR+ZWv$8jR+oT|?KWP&>o5<uO6@QkIq6*07N<=)*&b$)-9s4@M~vqc
zcHAwsiIMUSGt#zvR)_-ZAx;K8`L1T}^A@EG06h<S&Fi4s>OV(+KUkEJ{3ow!>63u9
z$oOJWE$z&MJOI4cVw@0qn%<hSFf2s4HG0uET}7W<RXE2?iqNtfuA|4OHJ}|TMSv>I
zV*{l`hj1KXr5x0Zl{)pS3&(1#pGvU3DFHfq)rIYffe$q>=~6O7_i4%NP3=xx&;-3t
z6yegEDb$$9ie7@64;1Y2NDLnqWcYsMV?Qb4yrW59F5GqG*Q@xi{zdze4<s7%J5>?E
z7{)L;p@K9}<v^z%y=js32A{vK1!m1qn8E&(ql%2NCX_JEARmHH0GhJ}gwr<w0qSbF
zxnvwr*RnSSjW9JM(rw}&y>P&soV8tvY+wX0ls&7PX$u_Xv-PGk7XxwW%`qKIYF3ex
z%H(zSs2^8>NWtA)*_3CkM$-~cGy%{{uBbmGUiAxjg|osS`qm+Hjw&{AD6kt3uU-?w
z?HTAQ7S}G_f7dWIl4S!p>rp(c4;)coG+$G=kaH;?O06a2r12wtH&s&k9`wTa?@qyT
zV?2Oiq<s4^rupo8vmdFb8T(UrhW`NTQDG7^ywqk~j-QPt+^<IK=}l$YdSKH5cX3T;
zr+HGa;xa`aXP*c6W`PXfO%0lq*<2I%KRN}K$^H?KtpRcpaw&{6+zPb1eZg<KKRRFR
z$&V$Hm|Uhn&ot6%+0$mv-V~qNQsXSdPz4zq<v-H0=9N*&11B}pog)a}yd#d7>s-y$
zTPALY27wxSedETtLEpVeDJ<K)Y7IF7WnT5TY*s}FZ#eBiCJn$Pc;=x-0eP;1Z6p{R
z?c{nI=bkeYvhk2<p^3le<ae#OH$Asp<W?E$(zkTi1|gBbqy;$<iyk}FVka&4TNTl)
z5x*fuDeG>a{n`d|ixW59Q^&PDTFA|fr$0*R79`FH`qYBnIU51H<l=xiw6d9-h*`e1
zX*9{({#oFAn&{)Ri~+|^^=d0k#A1tq%*CYKJ7a1n^{en`7ZQP&LG@bdAhuOKGn%*}
zAO%s1R~gO0;h5BBNl9b;BD7-g{k}7nZ>?-aZH#fxa%$S39C}i?Si?;U*+=@U{SGS9
zX!eW$04!C0m8-A-aYjEnR|153ZKQmxDUVE5l(&IL`k4O!1*eo^eLbn_wKpAxv`9g~
z+CSOikyJ)-x%}znNjw^E0OZoR>^mlc!lHL(8&d<`oT_oj&%GB51Le3F9`zciLH;!<
z9Mg8>^`sU6M}BEZ2iBNKR@#2`NQiOLknASq1E&<uSm!tt`3By&6%lkDarw{$%2a#O
zmjv|Ysx{1D@<k`w;qLgyr8EWJDkqc!h2^RPeQp;aoARhmqY50VGkb~x#o))kS~<^J
z&uv|Q=Zk0SNhZ0pe3schrMRFhX)2uh(vh`t+zQA(AeaC|5%KR(ORP@p9PP-W!DDer
zeBg0T!5-rk&YfcL@w|Ri*3~Xw8Go%XIxwIgttLS0ispXZGj(I1T5DWL{aF46kR3U6
z2k)r-YBM|`4qbkL*D_g)XL0tysMziRGZWvf0CZ;J(OfZ<Eg#wz*#7`s`d2h~?r}<s
zyPi+horZKLRJK$1*q@~*_PiUuSjqaDz-@{3rum?9D6kt>8sj$66kAvIsDHIte}gCM
zSzcg0sSKIzPQo?Ltmp2k{&gAEZgPI;`gN?ea>s#EmSA}XfG>?o;lGRnLB6;@^4Y$%
zo=BrDj<f-H?UR$ttZ4gGr2X^ss(_KjIJVQ?fGqu?*kg7+hL;jB$ax6$%~TTO`qhJ}
zPSJ$V$U6Z=fMX#&OCQFNt9qJLna{NzWQVS3urLZo@S0t(*KZV?pFMwCa&KnA=}bZ-
zPa|PtW<H8DLq^EkSx7#Wq%MWD9#ytcoA0^mYN-W|OJpBf0IlV_45}PcmeN*SkX3zZ
zedR_F;*q70^<qT;NA@)xUYcOsHiP)op!)MtBnr#D<k-HQ=mM~{ISferDOms*=qb!`
z#z3g>zO(?sIpF?uV>#xXj%f;vbf9B*E_frFF_G7;E)X7>KD6wpJtzSRfG{aAKD4{~
zam_b>Gzda@;1f>H2TDOFH2mZm0F8+~2540$wK%yA{uHYyafQkE6byb5M<`jow89DJ
zpr@d05scCh<ZzA8wIK}(eQBf`ltn2R5lCnjw<m>!ngERu2B{T5<PlQGr(L&LPCJ@=
zX}2tJu@gWQnnDH-=S|=3R>qff$B4i_gwp>2WnK~n*vI?|ft3Rq7`A<C@zQ4p0IfZA
zTaq$nQIGa$12mT%0pgH4fs$)c^r_@vqGSj<lC;0rQ3K4(ev}Bw-|1Nz<VIUl#dY7<
zkz?<-wO7>iNEc6b+~*u)){_IrnTkp~Q8r{l$7*%pSnk~i7&zvIY_EFJ5Ow|)l(wF#
z-9>b4q$oTJ#rSh?4a72uMoP%tO?UqQV6s>L09Cu{X)=+_76jvPq~(vwYpVM#s341U
zr55pI{^>FP?JJDsL~KCo$@Hf*L>`P!pcU4LqYI6SJ;0?vigUF=`cZH>Aqy4Vv4Hm!
zs~nihBN6Habkir=Crq#I*Y&A<pcE>AK9sHpE-fTHge2FO{6N#Cx4cP=Y`pZZc@gaB
zFl)>{EL(22NpYR6z@*AYjuj-4icO^UrQTV09CJ;{$fPjaN<apaar|j00KoL46o)i(
zK!w^pXvQhHCyI95nm{fFD9!~Y!$v3o$fcy)-j@TPN&rlsN-}68(vpA|wG@<Qm<x`5
zD5jS7%_io}06!ejie^n5`cMRvnFHRLgY=*&^`K~eedq>|id;|uxKLXisK!ny3iY4`
z-f>B~fG9KoZl%s?xTWhr4hIxwo1bo!v;d*G;8&o0EWeJ{`ekxg<|eol9<|i?4{!V=
zjEm0-*rq8S_2=(9)prBj)TsGfbfFUpfPvE#GW+pNkxSrlL356{q*Xm=$9h)*ck{tC
zyO^F&<w!7l;8Lu6&sqR$jlz_+)y54+JjoP+I+I8o6Vo&SF5-JqZ6x;kQv)1kmwq}>
z0{KAwY05U7W|`(SF6v+;rI8EcC(?*n<c}vAJ*rKi*O~--F^WJV9lrknN@6i?ybpSu
zu0=*y9`pc&<KCPH9VsvX=Q*Hqb3hVf0OK^$p!MhLKsh`fDU*Y<>*+uhbwY<tmjOuw
zrFi=R9GgMTGn)13U=MEVf_Uj(ReukYsLY4^)leoxM3R{mz2Rv#Ut>7rRvR*`cwV)8
zM3~2@F90s?wQQ7nsU)Z*_7sc*##4%HLv$+S=Ockl+ra1X6`5o<P<@(K*f1Hgd8<s>
zCAq~!>?2*&*yTqVC-R_VxW^-kO!hq~jQQYD2pzeg2NuNx29qF~Fa;M7?0l!`RpXVJ
z_OTs$RHi}vRKU@L@+R5_PIys@KtLp#h_|gb%wFs$0?Cmn3#dIR0P1}y42ljnb4Uw2
z{$EOCKU@sdK57N!z^Nk}#&-@V0Ys~}=HS!8!Odq~&WUl9Y~rk~%wjR-HX9u%xE4zT
z&uURJsH&1*LmKX8+P<VzU)nZp{{Ssd{qse@(EC92r8fXo0e@&Si8J_8HTAl#1C~CN
z0d`A`%eRhrs39I%&PFp?^Iq8%{o=lJ=~b5Y*f+?MekPb3`^$F}yPF2G7gX~4M!5RZ
zj<3M^GyNz7OvptjmmbxO+OzKAK@{KZM?HY{%@zY(&x7kr=I`|tirTEp_e!36)JIjA
z^<XJjE^f@zM<DsIzVyCp75mlCNvKOA;pQjwsM`8W03{>Roq*|sA6~TL;2dt_>s+VW
z<SopN_!>{NklEhcda<Amp{@Wp3>)ZaQsiyrmycGiQ|$%#-S13!bH+|RjR1ANbVrXd
z4t?pLXp1{{pg&sWM8Kco&w4{B;{!dYupM98U;{hFH0l<>=gd$&O>+KjM|@Hly(xj!
z4MN%f0Og_l1x9b}iNcm|!nva>V1G&k&M`%R=>Gt;AW@tWeJPEoz*}()1z;@fPfSyq
zP**+Zuo|}-luV<_jlUC$i8WVM!Ck}CHIFRqkCbMSA0wJ9Gi>Uw(_sAR4zVccsgJE?
z7wOI^GNAqM){6+#8pXqL@&Qe4QsZ~Z!|7SO*Cz&=9Y^tIivgr{E0NEbN7AB_{^YPe
zdyi_V<^#^*NM%xb)3A$UP?+#!Z^YAH_Hr@ix93$^lrOivG&&FB6j&}<Y2C4xf6k)w
zoNyhn^`;5qQ<B)EYnVqy&(Kj}+?RO#Pf`szcLUU)a%!txLOQq<3;36$fYD$s?`+`n
zN@pw7aa9)jJZ{Lqs3p`RZ<&q(J!r68zSj(T3{tJb;<M8J9G{zydK*xK95>-llvgyq
z(&0$Y7^aJt7{_|g8l)@63ws_Z4yP6~gGVS_(evD%lnGt14Q4)~qbxFNGpe4RS)-MO
z%~H5LADinymB-7UrDT6;H}`OHNV<vsCCAc^Ru?vet`zf4E>AhEvwZA$7@@Cj2>~Jv
zp1je>#dA|U3PJf+ak`Q=0mdnfs5m%YMLtG5nxVGwo@qB^eQP0g7tTuXDpk38xyp~m
zjz%k&jz?ae^z|#6%zK@g1;cxag|Fp3G5FEQ!<gGR^`zswU{)x<m(&lSsUy@%GVfjD
zpCb#SQ-$}ZWGMBli;YQ}<w)_5;>}iT+mGRF52YNTbAKzIxuh%r=Nwl&*Ox4Fyz}TP
z87{8C{{UG30EZNE1<shvfR1rTo0EZ><6h$MgNa!4`P2<@bWi%}KRSNRhcVl;`&E0W
zA-IQQ?djIIc_+LsN7`irwhdR6?>3FM5}#AMnp})7Nv!A|O~X$Mpj_pFtaMUN1}bUR
z=3oQOD=(pQP%KXq4CjvKorG1n1zZjZG}~ZI;PNWP#@F=CLlFw=?NSED+{QX{KwLLH
zs6+d;=xIp+5-Et@(QetkR&r0*wQcNY<kugjOjhA>*n$AA+T3}VJJmt;6afK3Mml8o
zu0zDI>}~7Rb6wogz^Hafxq$6l*1u?y*_^2@oMe0PNM{7cBQ(v_gcbP-$y~4H#Ru`G
zGR>ofog18n73dl)>piFooS$Dz^{+XL=3!lrhHg_EOC8I`f29ICIR+2bpq3#ZT=nf&
zq}m46=Oa0)uDwM7W%(?#cEJAtYP2JW7{TDxSs;H;Zj~etB9R#x6vQpuWz#;D9fO7?
zJ^EF*Uokm2tk}y%a5@SA$?+wiLFOv40M{~Go|vxlSx>au79azT)xk<OGb#1QG?>O3
zvt=ihC~r=~y;UuPQbG5<y=e&aO*-Sxi-DXDD?|n>ou8d^dL_ZwaKo_cT`q8+TA>Uv
zkU8d=ftsJqAY&X<WwY9Wj4SDy0-sJQRT=aY9iaF8C;|skRIfG3c#71bnRCeOJJ({z
zIO4N4TYo;?_9Jk(q%+T0=bAuysV0xfnb3j=Jq<)puX;l+Te*#tf!tSZq}~Z33aS)z
z89nQUw>cHiX%l&D0XQmhqM8xesld<jrpY3(=x}N<;gswL9+ep+cBfz<niC^+>rlR$
zWy>?R2W-`n&cytu1EnX=o&o&otQRZCqQHRg0LDIQuq+^7xQL{5AX4U5;~yyXr;MI6
zMUb0pjM()3@b;zq0`&8ZNK~3a8AozGy3ip$!hwGIG{4!&pS`;twBVCB-A2KwlHO)s
zWLW;Z&=)KHjwKxDpF>X;(1VWHsfD`k{{UED-=#<)MLUY-kj6!3vJ5KzRcL9%4rA#=
za<UJQ1^QB%=6~X0OHdrPNW8lA>;+Z3mfqZF%4R(_ftr}CtVU&WJt;h%a(nio%w~Gt
zM(jUwSJ<siE)iFRAbJJGSr*7vp0>e{-Otv6Hdpi2v9U-L<1*r{eVh*6J!#8szLdmN
z6AS`HI9%h6xf$(KwZ9(J3x9qo41?_}oOGk@DozJlur1Vf1bflssO{E)ka_FRN=1_(
z;E%$kHtN~=MJL$eUPec#6ae9YkDY%CLC@W4jM)}%k!1G8IBC}aa>WN?!jKZ|E!D6o
ztslKf6_8wck{10c(yVE~9Xpy$jHBf<dg7e6+lSuz;;qT^p3C&8yq72CBm8Ir0}?L;
z=iZTy)AEig!G*EwNNw0R1E}px3g$^L!GBs~2W;e?eJanE;kjB2G9TeTT3}Yg<b5e{
z*y>31shTEG2?m0MXDgZzGUSo&Ql#fTwaQ;aVY-ku2?rw;*yI+;{HvMPqW=I$&vVb=
zSl3sHr5EoQr?<T<c+X0Zi~~&zgNop1dM-fZ91cnCTGshIXNts){Iii-mafdW%}Yjz
z*N5c;J$<UyIO8=|0(NB8oP51{)@-sVNCTc}urMscxTxjanLTMNatj{3*G?DXIk6uB
zd+ABHid9~Dr((TB%wuu&=7FB{;l&-P5+>hzYY<PVr;JjNG18dG)KjoCN&uzXk=#%N
zagN+jMtTa9jkw3+X@dfQ5G8ZoBZG7y*mtgr8RD}wl+BZL^~FU`gt~6hJn7CDie~H@
zp5z}i@H5<suaZtUt_FGlTRHw!T1LwrD$9&jNkPxOIFii!&%8LQWO8_`mxr8H5_4T}
z*yEn!5lQ$^O&?0LFr&R7Cp5GG4rm`r4HU#JKd7kr_N5K#Dw6`la&5q?N%IPz8x>{=
z_V9mN(kuyF08K>QDeiMo9(&a`Av^n4mW!uJsoyMNPn4&Y_o{aGvR+6djBaK);=Mn^
znlkCuYrq8ZO=QMs>GpBiTE`kEE8JDwWE0+nj{wqz>}df)^>U`NoP5>2br@vnSkfc;
zgmYL;8pMDuDcf=Q`&F3j$;N5M5xc%>3MsGy@uVjM7^_Vl8{VR2`cMT%49(B2Qk$vA
zYS(1}Jw2;7bs?D4vW&TxAeyG*2d;5iQ%9616+%Vl{AfU4&|D^<MtZLzyYx_Tft-#j
z&2;%Zo78X#&lTy~b=|B{q_-d4&#*PsOH&Gt+MM5sbnmgqmjwR+tj2R(+q#3#9`(?C
zLDg-qY~qgIKp9Bq)0*=axSTio!gJWv)rwC*r6(nJc5q$W+c0@t01vN9B=JNR>fT5a
z9=ul+9%o^eC-JLR*5%3Ilh<hPT=GXubv14^%e(n8AYceQ2IC&$u4(rB*%^-~r})xZ
zX!*wR*N`*Q>sm0|ktPNetDdCR$myp7+-MaA2o25DP>lZowU0`aryVNQlxT}AtiN<%
z8t0Cz=$44G&NqC&aeh_$Rh>HGI95e${KM0V%z0H*fJfKTx9qJ}J2lApi0CV}gl{XH
zHRWiYL*hpdtjx*>-of^)ir(=}uam6L=wCmetP@>_5OYBEqcl(hg(f+rpil!y?@ToF
zjP<4w%>Wdll9qrwPXSph_f0ddM<8apFA>C+$j<x>b*!(4pm|Lza5KQC_`6q2xSj-Z
zrA{kIyAdUGn43{RPalV+FlyioWd1dj>R9k|ijQv7NzH<R(%SfeEuT300%|**PFvYo
z+vNw04wZ)%1z8ej8);pY%8M>R>MM53KV?&laaa(mODZCOS-YNsyBQ!B_OWhIIO-}U
z%SBPwkyFRlIjBHG&ioTnpk9pinPu3{JC179Y&)8%7nTZw<m0tnMu;DprGR7~{=G!!
ztywP~5A~|@$Q$?q`-)d6sLW4pDm91g5`@PmidSqmDr)wQo^|SsXKyB|B9X&*s>AGe
zXxm69<@N)pu5k6QRPnZwZuIdYt|U{}KVR{$Eq}d^`K?)q&eTwP(MSS{DJg)Xk&0C`
zlnMuOVAKQ1Jc12I4;1A%pbq;(xy`yZISM#6(b_SQ)V*=O9DUYc$WB4Pu9_>R+@4tD
zJu5bgM|Whng+7&VboZ(@C4?wQ?N>u&RI-BRF*Tgg`l;r;KUdTK&#6k2K5%|o_cY~z
zHRnDy(x81vNSF=Z-nF6eSjwu<;Wr{2C=~BC*zH`OrDzR4IKbRG_cb9A#s<&;?_PpO
zD>Bm7;z#?0XSp?{Wu%9E%^?HYgLM>Rl4<FGAS58#J!*+;(~D2Dwo=TXp2fP-{iX=P
z+6UBC4>CzQvoY;Xj@oAEm=wt^eYLtR4>XLYE`JIm)7hAAU<cN%$7LG-02XuWOh!pv
z$BdkNR4p5`U?(2+y3xZQAOZELCYA*UC2}c&hVU>4gH&EX8J8F$wP(47QHcD-V@&&;
zpI()nLr9Hx%|gruNx`IYbHz7l2cByd%~9z-2#iOeqafs-YpY(ku1~=(289?IJ?p34
z!S$|b?rR;6cf~t!Hw@yu{{U8z)?fiR_O9#1O}n1sisJ6jNccaEO5AcU_%{SyXFuyR
z`d4Wfu3N&8s>eRu09%|_Sq~MuGc3luX0F)tbfT%J=4(Sw8?Kc4RRPjMyRlNAm#s1p
zoK>xZ9CK1Jh(%db+M);zN{j2wASaCERO`~AjBpJ~IjI>arw^qxeiZfVKo9Ls98*O<
zuQY}@Que0M4+fAJekv#X0^@CYnjA*FcCSqFDBYt<2=DpVnW-QQ{!}n6Td~N<;;fyc
zps8(i`DTe3Fahpr$kJRl&m}`G6bR2sZZTSa*(r<}82i)LON4s2)Y2Wyc0RPmY<C=1
z_|xrFf2zs#CY&v8kmNw0l`y%_Wr)twN79$eb_3)iJu_VqSi$>>0qiQgi@P{Dphh9L
zlhTvymkp2Io@;4iP<L@i?~atf#}*T|GPw3M@9eiH?~2q8eR@+Jn4ANFObqYru6}1Z
z&uVzmBR_reD%r?6?@AlqkcxlVR_p%&)}(DN*k=o$_o~xK26I)O@rh-QFR5w(L1k>C
zA|X-;VPCrn55k~EkhWQm)3s0LQvs5LpO7m46<pg!$L1T4y-w0|QJDrh{sMp$U=6(~
za4DJGcoa|}uO<&ded!eX(94re`9Y^}CHZ)xDoryyXSFvt>CFH+nHTSIO!E|<mzrw@
zVhtc)d{6_~fkH9#u18b_E}OM=p_N7t>s+?6{{SCFfWXB94K?!X>J4<!I8_{V?_8dq
z-@gOCYp96kF}j$G6G^%w$vGI}xf$0NEsW#dy4=N#d5UY6yCH7m!N@0y20-JvtzA9A
zh#yMJlcyNXU(*TlhIurA=&gq6^Hw~z$KJ+$Dx^0_2*VzgIMgA@=Q*S@bb(kE>J3R{
zrbPoEEl3T?9jYkrq22cw)ws1dQ>0&sG_E@r;<p_=D$+%QIO4Luws1}m1@)u*Y4UKJ
zf2~ODbTQ!<Z+e*+hTvB-{jGA~?Ie5RllxBapY^Blq&pp8a(fzSl#_)YopNn^bmy5{
z9+bg6q;gN!G=_FUWK;7xgY~G|?htvIKRV-#(v>+s{d!H(6ONPxj=1VJsxsFLk5NpM
zRkmF1m5=-exm>z;>qtp%q|gUS+T04c!_yAAZcoUkK7`jgPI{cvaZ1BF2G+`xu`~G8
zM_ik30w6xUYaMU^>r!r2UX)l1=UKQsj0$q=7cL5tI(8MAy-CInDM=WoU@X1l{E;pX
zprBq{GUeTg{{VWc1NqY99cfqx{ic8K5`MITc^LC6eKSd)YHmO@>>^`3?dwVAxBT=!
zK~askq$7?f89$tHg7llle)+{i&fb&)%Z@0pjVP_*kO!9IU>%1!sAgD0pDsXDcdCj>
zV0U7NQU?Z@77=a#0F8(g=Zf46pvfKTpCD3XiU6N0&w6RVAJU@-wKoJ%1h^;AP(c_T
zW>2+6l6z7DM?iR>2@ZRjG7nm2NIdaUBdA^gVm&AUyHtA8fB?oQ1ha4$`)xGkic)?^
z<RkslOaMi=@R&5dUOx3oE$&Z9Tk@xi8@9$EbDvs4a=DBSGAX7%TD&ydv%rU+cEvbp
z7l#=N2f3g{05DEC`cb<)R+?y+0R8y>rk*ru0U42c_7q$Ut)o3@2**L1+f5L+EjB)a
zn)+HRY>rY-cH2e3#~BTeTAXcBoMf8Sk4A|`US=fr0-TyuN!KUw=|C8ay!50B-`%c&
zX;$P6gZb2>O0^wTkK;wa=T%#6E*l*yp!)@)9#fC4N|v^RAG#D=4s{`S8;Qb-es+#C
z^{$KT_Sxbkr+HBS0M8}Qt|{COVc)UO(-eWbVZNBIrBN4<i}_Q*P&iOC?M1-lm1R8@
zvHtBLLQgw~;ayhXbH)uuV?z6xRO8x}z~`0;Ke*WXQ^kzOkT8ACZ|_jpz|Yc~kWWEH
zz{473&ySRTbidhiXXaHN`>Ss_IL#<-G3!OZ#TrwV=ZsVT0I|vE%-Snan;Zkrr92FE
z>qWrLO)y5ke?H_?qf3jf@=wyPpS_+bK_-iVKxpuKo;|7KNwytSpP|KF4aZ6yf+prT
z1J;XyTxr%|U_*{QYB?+{^R*zs_03ycvgVPqNw6!$r@<f1<*9Fao5+ZcQAzq!hfcJZ
zz|8<Bl7k;8AB8v~sQOSj0+bGW&;YT6+L`AkndPr6J*m#+mum6rOh}SGgPH)7X*9Uv
zn~}vEvD$zPVuQ)zlOd_<6m@J02Vpm3uqKem%rHp;s!MRMC&<_o;Q2h9(hC-N9A=EI
zK|tX1Oe|R3D!tkBEhQe*xyb8}rABs@WXE3g2=QHRJ({GdeRG<v8Oq|cd{+sFS!{jN
z-m<OOH+t42Gp_I~#yw5q94KMMdW3iayobXV0^eFraprgWfBNgzK`ev4M23qy$8XA*
zWfZ~CaY_*fH6;!*`clU)n5S>&P_nadP8ZNrfbCo=;0gejc>@FSrSljrGuEKVG?~Gm
z3E9p$HNkvKht1J)eMje-?F$@w*D>SB%=!zB*f<@!b4iqs0dS)W=rK*;Q`#U-bJx8y
z%K*@d8^>xX+dZjD`%oc-iVFivv}S;Ufep_c4H@E}uzFH$qyu+ilYS}tK<!DlngDL>
zng&fj9CW4Qt|$wPA+gqtwC=g2JP%3$O`?o(#V%+x!sBtpFIo?3O!G_y#T!7N9yz7&
zNCS#J=*=9_VT(lpN&3<ej;4zMx&Ht-riyU`r6vUy3yaPvF`RKu3&G-(BcP(eaRxeZ
zNz_yRP$>>QIi?pG)|>`uG6^`Nb~?}lv0L5_oLcyjDM`RFk)KmoAQm{qU(#F3)gWS|
z;N)>dgwLYwuME*6A`&)(nz82|<2BCN>gyG%0~p8yBRy(w?Z8ROs)5s<wCqW?Cvn>b
zo#*b(Kox@8;l@}lI~t5@zJX8UO2BkJXSF>gDl$6yS2_K-?B6Iu?0V8Zvo_zC3TOjz
zNJNu)hnDrH09UPZKil%{Al#@v)E#r=;^Yr;KpjT&j<g2{rE(`+%YVn%KU#6|0s*w#
zDD}lVFuB(Uq-h6k^~Se|AP1X+_)`yvq3t_2;YFAos4UzLDUeLUQVZuDiLNvL5(u-q
z&6Dz|Pl#g#uxWC81*giw==3i<cgATv<vk8-&d-R{pZRT?L$88x1fIDjj!6a2Lo+6M
zYHLh@{o(o7p0|khuOZGmW|{v02^b^&RGd-CAzdDdF5^-6*YPyhyM&+hsgHKAIX)sn
zK4@}B_o^k=4l)#H(9`6QT^^42*5Ww<lxJ@kuPfJNR@LQoZ<V?Z{c7`gjh8Fs56-bJ
z?#<1?bAz7r)NCfj5`4HgHD^qeE#N0S9M)?#8<R_Ea3Q!y{sY#k#Gbirslt}vHthE_
z^QuG-LPjfwI+e>tzFQr*;7~8G@CV%orBAbET<zu6qG<N29FbKbzcC!5@!y){e$#sU
zNtlmdDSYeg!}sh*;YYIzou~G)b!B34)|z!?^vBk?!!64U8HuKoGq~L|Q}$uZc86Cd
zkgNFAZL7$782zh|*(UGxu74U)45yDVkG(%+9LG`psVN8MT%P!-#pTO4`s(M6yrYum
z{`#c*G?>Qr1M5rKhcVDS+@$=|5`MK2yE*>=T7U1V#9J12$3LAYvD$yuW7{<SpO|wS
zLgzWm*#7{5QvIeb@?`qvu+6wu>P-d=oE~ZWHQYIkroFZp%-B8hX+N}WfXAMGfYva!
zTw}F4ZDL=WI6l;SG%jORuaI-UJm;-Mbr@bv<=D5rYKVawx%$v;zyk)4W`mf~I)q=u
z=a0sl{i6pYHx)p_2j0avM40VIvxsvR&ZQ9d^rQPx2Sp;OnA1G~qiU`w<cM<@4y3FP
zdaiFuH_MY%%7fn&p;ULL$q{oBwxIt2-2#{UMY?S#@u(OmreSmSqmm=$WwEJatY<%3
zY1DFfTpz7faG-L33SbCm<%nIEj-UbzCq2$;xxSF+p{8sZ^rSJV;~A&R5nPa6x$HkW
zLw3M)sQi(UL5*|kMWQRRPqxXopv?mIY#+Oyerb$=eJQ5^WQul(?#WI3>zr*K_@*1_
z{{XyA0BJ#%zBC^(TL^HYu%;1?u{YNgz0vAF?YAQXa36&)+ULjK=hmZBxsS--_su)X
zk&g(&(;|;_H5A>>e~i<9(>M3dY2Hk`f7Oy`@+QyvhCfO@(9};pVn5b44{8L`=kK*A
zk#I@<!+tdHB6VD}cs_%gFBA&n8Rb95e>yQKAAFj5hHMX(h~c@A;6+QCA!aOc$gPq|
z_NxxfGJu4FeJD!_&m;luQb%WSjx)C(T9;w!QDZW;(#MK#?+-~E^R0Wx1hI{{-|bls
z1>%FYHT(@Uz)-J`zQ^&TA-k6R=oXibKKRdiw;r0|b0qxw3Vg^cRRw?pI25_hR;f%8
zF$!kq*R4Eh;GCO|J(iASD>6Op{qu@r0uMPNtS+1Lf374`+f8Ttl9BIEm@HGnV09k!
z1skgG_Can9!*l6K+Da+nc@NXQE?}`qqUWwfG{uZ(rCT;i3C`p0X`g0*edmz-152EC
zAy_gA3`ID?SO8n_tBDL{f4fZbVJGG+ew5UOVyj#29YOk1d1D<wtB#iHI80O_AtxQ^
z<_i#c1GyB25!uFS=}1&y##sAPGZ;BBap^}ea+Os(2J1nEfCQdBYTEf~awGgI!Jao8
zRS4paaq^j|87Bjpc(juk?^BTQw()^PH<C`kBv~EF;+M1zQXy+1{{R^j;S8t#TOX!r
zWH)8;<o-FPG<TTdFT|RB;bbYaels8+T2<4_oCyK?P`1}4es)zk?MSfPqw_w|+zMRm
zIY}2smAW|3v7z*NQ<CQ%#-;u050TD&X@%z;H01qg=MGV;rswYreQD=RXZxJf*6Lum
z>+Wi^UfiUmk=XObXy*=6Z|qr!$x%wWJnNmS^{2<HUJhNmbnR0eV(MfFa6#aTIfBM}
z+6df-ZbxBJv`0Anja<miSaV1kB{*zn+|syMs<y1&l&xk*92&N=LU!%P=TXZtsmNjV
z%`RZEPD@FFB%&xDhcyq`gYZBE)_~MdE*oLvy)aD_&GIP8^rM_sD9NUxrcAj0wN6VU
z18(ekn%;drMos)<9Su}#D4*tL!S<@=3m7kH5@+|B`qVFLZrRJ^dWzP#)8l48K1bH5
z$!v-D4oIp4HLR^z{Ks`tpHH?8@)9}8_pOJwz{u&|qw-S+Bvdijq^q?+9Vw5_MtBuF
zvMBmgWT^y>l!P`iQb6mTIj+x5o6UfzZOyb3isMm&pRIHn70y^G&mD2;)_^yN$6k1-
zZsHQ!y6wrwO1F%^%gUZ<3NtPS0W`q!tzy-!H3tj|`G;@^^{NEp@vlkL^oXt`GP>?>
zU+GwP8Z0UoI0Mk9dP6x_zMX4lNt{D=H!=CXUOH5-VY6`Z+m7O(Fc{?FxirLg&_3&Q
z3&zokQjF(t>GY~vMag?`k|^A{{A*Y`s`J;drUfSs4|<L$T2@>fR*S_f>yWt~wH$Dm
z4-1c_05sb<Ty5#=Rc@>uBvu$dO1?~><L03e*>_2vXc0l})$R5;IqGv<KCPrmF5S=u
z1-b2Blp#_%6+-h(Ghl&(>yEW7XPbXzT%6%QT5s9jE(iguyO&3lFUq9;6;6Ey;BsN(
z+K|j`Hh(H~d;oe^Z*4D~5IFa)P4uZzjuDiPV_goE?6C!9?den^`BR!qRQnl^-J~!-
zJP*!+5EF&XHyQ0x7@RgTKRQff_|$$h0Uq2O<ce&I<|$LiH7Sx6`_iENX{O@MMqXw7
z=o!o3=n%_r&yq<w80}R*u%c6)#~y~eCZ51`m2i3MO)}|t+Qm=dNM{iyo?}v1g`(WN
z4j=V3*q74EkOG19s#3$JGm;qNumXTB>F?&iall%)<&1w?%Cwr&(a8ovJA9`VZMB#|
z{{T|wj>4V9TM=$-08Kfqrvr${6`%dOirGjT*!otTo~)CMu;scRN_P;`X)}ZSzA8xc
z$(^`d4mqn)-o)JPEzcPBsYT$=`lHWkF2JVtNfc~eLUGwwB-5fqPE`-o)z!URaUL^G
z7brO?k(yUvK=N<Sax>^DzEni~+|}i|vuy8QsKrRXVUX~@hAG?(;ECBrJ!#uh@vHv;
zXVcrCFR#5YX_|348<*(VqTp0exZq-wjomq`tzl*c5?3EqrmmlCr#^fBG+bmOr)p9%
zc<1R;n<#>kvYh%<M#fTbE&%*GQFH?WbIGTL!Kucc_#eF#{{XPctCKK4N;!~Nt`vP~
zNKid0U$Zv@BAhJv$;anK!o_f*y=mJ<D$3gAV4PEmBtt73JuYCeRU^svsg~5Z>4EBK
zdzm^dyJye=Oljl;8(M&{rrI?)XJS36R6`&7wCB{+B0@;WG^XQcVfCa0re{44J%vVD
znYpF=Lb=a>K}}W#v+Gm=o@q$wN^#nblz;)_rxdgW%`Ok86u?k2c&C*ha%r6Q;*hr1
z27n!~{xso{k@!<LlZtR`b>lRKJ7FW<o&zu8NF9Ff1p3p9XPkaiz=V#2sV1@Y=v&J&
zsNsA1*3dZm)m=spHqiFl^BS6p@f|m5BavVYMIzyj4h2}_c017PoN>~;*()B5NFvT_
zR?vbmR0M0cJx{e?w!j(hQq2*w3H7Uha1UysZu#~#bx+DMS+dBd#?on)BN62Hr%c%g
zH0v}TSpMyF;XWgq6Yv(W4Je}kdQxZduT1k8H%>XGoa3kEN_eEtIp%;AQQDiktpJcQ
z??^+ljwyM`#W3^F^Q8y3tpgp<b3<btDKVc~L&wsX3R?q;r>LlVIWhs@j%vv{^!inM
zpjsCT*V3k24m+NCc)z`2?^R0V)$7E?!{@H*rofgp=gV`^TM;k~Rpc1WSbT%^sGV>z
z=|U4R?@lC8YKi;RqkOm{9qT=-t{WV6HyV8@DRW8RHKCZagQXO-2nRG!1s>D@W{N1q
zFcc3;e|lgPqMBnTN8|d^oSX$*u{Z!!DslK%PvI>b>Ni5=!7+n{TyyoSxU6q@Q$Y}-
z+|LeVJoEfD+AMolifmTv5(QPp2jx>J+eie@=}SwDjzu9H(gBPEaB7iN4UBRtM6c&n
zCyQv@DkO@FBj5^!{d2`vxV;cBCy`mLteoI&tX_tutMl8Mh1VyFpf#0dIU^&|ri%F`
z2PYLHu=hN4s#1*P{*`T|TwzXgP;DnTsbe$dRtiQxD$JQVCl$EyA9GY@k0gUa12zy$
z@neI#@vlU+wp*P#G>~)Kir`P~rB?pwuSD?u%y)L<EC63x>7%)gO^-kEhL|j8k8U=z
zXKIS%h{@^Cdh~CI%L$bXaxQWP2e0`R!K4o<9$M}+s=G;!io6EFZqqQ^!1eU5hfK8C
z>br2o_|0TMvRk$=MRXcd?PDW>n&hb?vYbweEiHsO<dfE!<ODp5w*}Vt#9;2lB#6T~
zt~t9MQAH;CdUIAvmD7{4W~#H53P$Wz%z2YrLcKorDbS7Bs=FdBH%PlTMd$wjSGYK?
zwkVh`F`V<oIx&R<k9<_P+s%5=f{M`cs!hqBS>xLg75@O7Q<mc*xMt)7(!Gnunp<A!
z?I7fe@%cu{8GpKJjL^bprqY8*V$eyWJaI{k(*P%mX*o3FIHW(V04LIroKohIhE&i8
zr+hz)HUWx^5Nkum8f~)auQEnAmE_Yr5f;rYdShs<4-|shVF&Kws7H**86O=zDVZj$
zT(9rj>rkqkjwuX$XC12C2&^(s;Z?xE=~f~PJ5V!UOo3#+i3d~q*JG+%AhcC)y^alY
zei*iCwIya>x<LlIooPu3G6pL-l#Bxa>rPZs!y_~WU}?$088syqqK$H=Z#^pfY6|_{
zeGOE%X2oAYk)KMIG$Bwi#X#yg;-_r!ii%u{KxfKuz<So6fa)#_w^PMt%8i}}(AB*l
zvRvTg0gQuH9mLLyQh_e)%w%M9{Hw(^Ya?ZT@Z$rne-bO)Rd+{&UU}oa5z=#c8WOy4
zKN{G`;7?jgk%t2y(+J1bqy~{kN>lh!QvqnCrOf~+;+&*YF-}$Hft??Q-^_BE<2|de
zwLoNysp!?f=`u7|Kra>D=_>wwZ0(<FmQp<e&9=h4aqU)j^H5oxu>C5)0QIcPBt~2w
zYs<W3(nG2<Gn{7~Yt&XWC$X+u$C^ABI)9#14i0NdPSPT#$CS%=GqJ-Rw2HSAk(cA9
zNv6CKsrgfnN_<hy+zu<yiOS1SSn@L<`qquLya9k_EEcokw3WGMVeM99v%uPCZhHGw
zqb6=ETgQUCbL~gkV?8reqD55LIX<-YfcMQY4tuoD6|+FNnT`iak~kDM2nng;h@Rk6
z5uWKYjI*3~6<SC^z&UTNY_cF9dYHmJpwk1KyNQ-Fg~0R`n(U!}m30$^Z16bfeJhl?
zz?txP2D7TPHGvDsxcgH#AEhDAN2LUs=QTYq!DnuZ8xT44>0LOL1~Xi@g=J6dI7c`g
z>vPUcr=0e#dG2ckp^2@xnGEC}Lv5}&oy4E#T_&SB7I%F7*>1JQCEk8P^0z~uS|SrV
z{{RaQ^j1(gFSwfOBOL{Eo*6>6IVa|7>7oY%irE>HAoQ&*HFI_NRRte~Xz3$2MB|{U
z1avTD4Ap>1s38MtvsB<<)QpjOij_~bM473VnoJ3h)QW$}sMDoLDn?6;)7Pl$QI0A_
z=|B<;flmUMIH!tCV$vVFY531-7;#7rf5gN7B(ihfyxIHY;=L!uWBw$q$MIL3Fa)-G
zPzLUsevbk~vH(<Ifm%Lfc=?+?`L1(MwuL`<gXivZT3eJ3-;HKbpk|G6lT0^pXA0cb
zT+JEI_86*&_M%PeH$J(bX7f#-yHPx(^P0^%j4Q{SKNCtW<B)uk6YMAg;g>vSlYY>D
zomPoAHb#FMv?4os98qu~GqKJT_3ua+u;(>n$j7xIgbH^8xnsxcO(BS)N7#PnKGj{W
zr0j&BdM*RrK^phXQ5waWkjLhzV0Pe|l*w}<AKitjGx&be@!n}qmm_s#qTp#8s7T7p
zgnzwFE{*dCOnqwr_+H&x<-e2h#YmnSh5BDeap-AW4Y0~`M5+1IQcR1CK21@J!w|&&
zV_eAC9onzOXKesos928dXt)XG%O^NE_n=#{o|R}!N#J6b%uiFAcLEU}I+|$;I9#8t
zJ+nvwr*T+fk6MOY#=C|O)}L~cZTWvHz`wh>wL<4O2dz!VV?s?u(Qr`I4XH}Khc%sT
zu3OxVmkL)s@m9<cN;ks$m(r;_h*PP{&|;c(3C|m`^s3B^t$?J`ZrjvV2)Fjxh{<zV
zchX4iOSXOLz}!z2Qt*+AVjW^}a6L1QYo$(YdUJ~9tt7;w(z-~bA7&knI#LyiauN%6
ztoLk7T27^jKDC>6r6izWNHup$Y?3(caapB~->qEJBncthGnxR|5t(1EDrB|Cr7Rd`
zEmqY>9E^I@mWt^Fo4Lo<t;GWE`Hv>6$*I`FO1$bZ)|%SYf&+=r{xq&K@P#?xRG|Rt
zSg+zcFx!0P7^qvtR*FFLhA9EkDB_#|2c~P5J}I|vyEvp@5v-UI$XhfF>qLmXR8pA`
zuRtr8{?e8Dll09Xyyu?Y^o4VxX9c*$0CAe<E;Sceo9zDpf3;?x65rX#QfN1*8O~@O
z&e!Wn&#hwVz9q1~Dz4%uIQdxDQ*EX#&<vLf2Yd|D8AFN*1J<>Z!|EHGgY*KV8UlX}
z!=G$W1};Z&P9$xuwa{PyW!pZ+pZ$q!4hS#xGzh@R+DH@?VcNP>(rn{iA?g0rJNq)!
z5PXFscc2bv98hG!^u={4VQj0!2tJiKf&s~e5BvszIMF8Jah^S?H*M;|yJH={mPe2|
z_Noo0KxXq=H9mripgE8ohsqfJ1xm5Zf8~qUR3SjTAQd7;7mw15fy%9|%W>p59<?gz
z*Nwo7@h273d11QrsNBSd7$v=^xE$~HRq;RS)DK<Mzu6aOJDCULTkE;H5(PVNuQXf?
zMA4iMX9Mu18ZRH~vyRxUkbwOu!asU020G}f2+XX13XybsZg+2Qt!b6*nn1f-r56IK
zX%-Q#b`pIv#YS|?c43Id&^>EGhH5>&oY8P1OKW(>78Mm?VL-ofG5-JosL1KZ9<?Cj
zlbS9eLV=&<PA87Ez}cgN-j%>|f=?L()}6N)!QzlM1t#p!1BuNiYH4B(1;#z-0sjDv
z0OO@sZ!z5b*k4MKM$^)OBxAT^nqXC4f|od?Co}-y5DxjJ;0kCSw0?k70l~cmILY$x
zGHR;ad5l6Y1G%Y#;(!^mEteTJARKW`X+IihleHiwQN}4q^r)4xIHztSy)Ybj9+elF
zBQ`Pe(vzA{+~aAW1S^qF$j7||;8bI2JPH7FHVq(eZYau%YdFpaIG_g>pgvC(9vRyQ
zg{e5(fk0e%Ip+eAq}r#NZ#c;&oA-?XNF?3((;3}Q6y;3x2AWfIWbi#r04JFsIov-g
zVP81zmjn)!&Fbxd!*8x>7$b4J^PmeJdV#la7^BXIJjqo=P@YRC(3*bRbOZO1k6g6?
zSQ5m3>w{7U2C4b>;{(o*{`#aha0bA*LHN)HfEhp5pq_7-q;Jo2P<^@uTz#f9{{RB0
z4dsfl-Ekk`Ko&t|{yfwC!|$4=bxkz~{Cz0;(tm8}pk!R`9-vSK<&lr5#Wl0fHB0+%
zO;P^<A0z(xrvCtM>BFR_kM?M=7s8X;nnDA}$*jpdQDT6Fc4qB`%~T#Ivq6&_jK|uJ
zRu?xsm|K$?)3&0Xg0V-5?fYB4KC~YbTc7!NKb<~C7dE$kR0EJJ1^ibK7#7*6+r;=8
zTT%Z2eN*LObE7J8N#(u?Q~A~c_<_QQc#(6^2F*h!h~{E32>fW}V!6k7?$q1r2`fHw
zNHxpF@?-0Y?KOmbYG2=hk3m_<qQwyCNcT0YV`3RgOmPmWZ6O)Mcduc!yE0oNDt<NP
z>0umFD}}=;$ThVdyQx7Mq;58-;{v8pY-sNM*FCB^?);d{lKiSW*AU(z)v`~T2d5PT
z+P0&2g_dO?f3s8U*;hL|TkDI!T>(@lk9xYkU_Ab{=i^e;V_mS^>|a1BKeaV7+}<%C
zN<Etko{}2}*WQq}M>zcJ%?_b{Pt9{CeQBod^?=RHzWmYb<Q&NKtbyG}<5-?7@}ESO
zGRkr~R~Yl%u?NnWpRGdT;$i#Nk-nynWW$*A$zpeq?Tvse$EUqR<xX1$C$9eh>>YkV
z`BbT3fP=IOrAZ6g9&zN(dO;!jEjU`;6OXgWpK)H4Ef90%f@oV(IotYE_Hh?GJlt5_
zxBReheF&$2X5N3#yM7huk7gM1pQQrBxZ~JS?BX2k^TDOxk&m<fW}Gy8{&NTGUWN81
z9Dh1;*)Zf{j!1_&=bzZxf&T!OANchs(C^zgjB)DK=s#p^<kE{KAaE$;h;uW~*Fe;t
zvVl+k0EBk%@w{fe09frkX-&98z#m#UVlHNIW5X9@aO3JlN&f%{rNJD|GwEHyjhc@n
znmJJUju?1W;hP?HIQUNGPCVuOtG4p-+L5El$uwC7*~G7e=0ARJo`7>tUk5vKW<Q;F
zs}c@>oi5RgcB05G&NKcI1yS?dF+PHncuF#J=14o^HQ1Q9a0fJ=N#ngcAi2q}g<&7w
z{OU#UwYl#3`qxllV0fnpFgnqoT;+e^7quMilRxiMm%~=M$Ch*TuB*vY)czELB^>hK
zN;C_zoL>#v9vTr(J{`4H$Ur?YT{>CIAv+<E`{JXK6$uWXFrz@Z&3|E94v^<PO-Py@
zuu=Pg`BvE@KX#<a9F9#F3z$Phw(Sbjzp*W`{-s&H>v2eKqX*ueCPY1mr*JVBM}!Vw
zOrH4WoVrX){{Sph{Z_U<)PSFt@uge1m;gZri-DB7WFs4*P(GBR#TOeQQI7S|+G+FN
zsC0<zZiLcZX~xt7$^g&jOPEF?!o+Q7e0o#X*#l&wAEjOSMtKy3=dq+RyIUb2E=RU%
zCbV<(tLi;-P6`R8GNqgnMK4^{yS8Hn&Twi-n8lr=A6gj<@*pPw@lkC?WPO)7#{!-9
zChB>vrX3C^kL76#9;Xyt=&)JYypGPrdE%`|lb8D|XWE>Wxb&+*8IRo{9+{>QwYcV=
zFpB2QPdF5-Xtik<2j<OK5al-o$fKAH{{SHurxXixCakn1w+ly--%4D-KrLe@1b$SF
zY@LS{ucukVB+6zv_O6CaD$*E(JW3P~;S`-q1&$cmCVpk+nrxvbIIZj3i&u%EvxF!-
zGuCp&fk(8sSf%}+0-jJ4O*(bC{tS~^0wbPjL?Zy?)8}DhJZV;^@1|+TOR_=29%}Ii
z83LEeElZdzXa4|ZSdp~EPt?$Ky*zW|dv&b?Zr+t77KV9NA;&#^DRU0RL@+4|sCf3`
zoWZ0UVM0&6b`fZ%-rs60Y)`dj-&jj+ndERl=!2lC=N~E0wT0R)WKF)9rU<0q6U}NH
z=D3V*Y^kP5V?ep!nyz56L_>keB+wxT7&TxrH9b)nXPP;Qu}{e(sp&z5{YcGU5vF=(
zmtytrPT^vlP_QF81KzHAUnfISz{s*Ga0v7@x+025L$YvsVxh>SjzVOSTbz$!QGn;E
zVOMYe0Cji^A==)w23@~*ilremR>AE}+T*ob#_zhc;cYV!ur7Vg9Km9sSM)zhToO7~
zhxT-U0`e&D!JybNZ<a*&C8=`-jPn$XI2CHz#N04LBQLP2n$}o`10#JZc!ZH1$+RBl
zG@O{yDc@+*LN{fZSE;Pk-GhVeU281Y5N+k_o4JB$CL_ruO-yIpb|6Tdj&~ZFZ5@Vp
zVy1{4xjY|AlokTC<|f1|VHixjq_?Ih`yIb`eElk8y^qb(n969lSc#y3asv`+o>X7m
z=Bx<tY5xFcR*&Tebt{a|mf0m3L>a101=KCdDEe07*-m*-52(#wTR$@2%WwuqYKJQh
z$1fa=!<+&SYIgER%UW{jl6|LSVM@^^oFN%<276Vh649L-F(V_2e$vOGskUI@Mt$k!
z7_S2cox;Ns9mD4!RAp2?!Ox{l<ggs%3Sois^5=>MUbc-yY_0cCVf3Z)RbL&dqNT!+
z1N}u^wUzwLNw;X~eJdxSLK3Rj0O!{f^58E@wjsBe9L}nJb5BbPPIGvN`cdr=>`*eR
zU~K2snutR&Ju6YHEI{4;po6*TRIe_qtjHdCW%i*|xL9FjI2b1tT3JIlU4$ByHG3xw
zwN5>0<5IL-W;Q<HW}U=mOCUpltWUK|ZF4vn^6)zoSB9ylsQ&;``StSZ1F1k{%G<fm
zeY{WvnVFY8y{W!T(sl#uR^z$f9ySF7)~n5S5lKP0howGX5ZO#{HvvwIPmst9V*|IX
zQf*&QEyN?!k}1Peyw25)Gmr06xEeFr73{0@q>jNEetEI%1yC2)<ow=H{AxD7zt8%}
z0L?3bJoXT*+m$+Z#Y9m-#!W!imo6~VD9@m%OtO=oI1g>KfYVh}T$+^}ZQxcpmGRBd
z`lzH6GOzr7JA2}t!p5u27MilFaan?IS)Grm6l5Om)b1lxg(L5PDnBON{pMQCF+#`g
z$aDVPLe|#BhSWSB???@KQWad60DBsVXSRstV?ujm);mK3H{BnLQtY)=#v?p>(*ssZ
zt7D%rk$r_%H<oHnCI+bngN!VA6c&gt%253U7XtcfHn_-d(x#5)DY3L?-m*lB4`crT
z0jUJpQUPJdWyUB2RNIrzK3`g`GskW+Lm#C>Z+_vnknO<1G)^Uu3?nelIHWO6+(nP>
z<YIpcY<Gbh<$>@$YO_ah2g?MF_|plQK>gMap=tooYv*JBt+0LRR{8UT7a#9c0%jN{
zBnSQaZf7TjjA#9-cM+lX*^WR+$EI4NGs;eWKy&L<$dq+t2iuxAJ^(Tx{3y5<n(A%X
z-T?HdnpvM8zfu1H0j3iBave{&T4CS+06koN7Jw{olW#MV^c1ZjBbGR-*v|&yWB&jF
z6sVk@UB0vdDQ-Hkrsw^p{OPTM!z&Z$4InB95I5&Vz?TV+<3CrZ-4LEseQ5zLkKF<F
zG?@PYrfK=na2ml0{t@`oa=+}<fr_8I81&CHh0Aw9eT5Bx)3oOfqa6hzxlWQ1^c1AN
z327G}?$dJE`}z7UA(o@LcK~^^H?ga+TQuO33Xgin4(f6wdXn1aNM!`PkKC;QU6#ee
z9iZ*1a$6`QcO7eH-%*xdkU|tU_q$Tu+Q#JU#`>;cvCPYDoaCRvt2MKQ^{$PqNPpgb
zl*yt+Tq=GfQ|1dCrNxH)uw$RfsCf+*;hqI__ZCk+;)5J?sxoP_1t38qV1IY50<n~w
zx2H9J!sG1MD*Tl_YLxb~K+TvWP(4<X3HF{rA5lmwb+PN{xWp}rm;Mqo118v(>0IK;
z9^Ch%&Cg0eZ%M4J!j14?cITRa>ai|Z+k?kaYaB>24m;CM*)fuNqTyp;YZi=8`Zz3V
zC%m;`fo6bbkZUa?MC<v}n5I2*MZ(6ET7pBCiX|P?8kB2N_JwonSfrj?BN*>MxZB@7
z>D)&6*RB<KRR_@1B-ic;;TJvfI@TxJ2YzYaXbtH~;A?+w-jk4tidNUI$5_E0)s!v*
z_Q<EL(gTtPDclVt*Y1&t*tqwlJ|ej%kU6YrE|G!gK9vBJGht3>1EBu^gpTb;M9nbx
zj_HZ{Qn8vGs3m|uT8PgYIaZND9kWOczwL{c1hG@}6(9D5;4uxipU$#c{uE!9L_du}
z+M*BnXupjY17)=vmgmlIY*P*Fueda>N$;A%ZC(&C9Z2?|YZl$uFXL1rXU~*>%SS&}
zrWOY!j&oTb+cv=c^G$tb+;SN6_|OK&AKo|~^nj&djbbd}L$^JJNOh$PkFrWWqpcPL
zZDvL3PxH|72(ERtXCvjbln-6B-|b6)Hm#HA{nJI5&Xal&azGRZUs~qY{{8w{%6)>G
zUq4o6J8Y%F{{UdoW(P_eCjii0M;n2zc^h3L3uh=En`su`UUS8qr|_b}IuAKl(-pO&
zFp?By9DOU9()8_Le*2q8K7+k?c6P56X}JQN0fAH^Q?V2l9Q7MTBoaG}n05}^k0z!T
z=OdogGDDT?ns)*ar1s*NRD+GD)~^d^BP4#b^KX&UC)$gkGeYE^DnK#Nb5@PB4B-s|
z*n`{irUU?X#XWeZnD*z2W&rC*Vr|I(02*Eg9Mp)r#~C=Gqubcf0E$WZe<4akDdhfC
z4o(I@q#*9bc%&B}8?<ee;QG|fJIF@zc&h584o+!tgGG>Bd$0R{g(9&EIiLzqI1~lN
z+~<(QQ^UCLnuxctH03k}$BAE#cocbu9S7x1$Q>xoJ!t@}`5!Rinl>E%?M^+Z*#z`7
z;5{);z&Fc`@DvZFGwj25?BM!T*ubPD`cMQ*67J_BoMA)8PHDvY(+hw)nm{3iyGzo9
zf%jw0$Gs}BW5#M=qw%CM1Oxl|sG2ek268IH3~~n|jhyp95G)QyE(g6lTk-QZ<5O+T
zD*U{3rWY%f+DRPK3rIhNW7@41P~9m2+&WML2*xrg9WuQ#DM==fw`_Iyt03er?f%bw
zBztj#P%<73Yip5hxJkgyMhNek&0&?uuR5}{k4B8Hh}Y#6G%OmSQJw`!7{hvd*E>25
zdp9A6b6To$D<0Lbb6RmqG4-frA<`y!9cgVc5QFPT&%va%d=?n3@UP!6#A^cQZoic@
z^Gyw!kTC6Dq2>(51aaD(nojh@$oAw>j+G`j#WaEi050Ep4+fe^0P&xCX<~S!1e>|*
zOf8yd&v8pY4JYRA4Khw*ZoJgHX|IJ8n9;!MX|nQBjNs<8h$Q3Iwza5sUb}k#0F7ia
z`kuAHQ$}~g;UP5>0na9;agKtaenISMBAJzbgsyvv&0*`!ZOnnyl=IrNCbeWa0FnHw
zqMVLek<_Ya;-1KJ(C5$&wP7^fLB>|fVn5xjlQC$gid<HLXu6z(KVxz1c&UenHD^EZ
z;=p>A;+Tw#A52mHHMqVM)(QUrk97mrIjL8{+QSq3w4%Z}?!QV>E2)dXnxn4i3V?cH
zPHOZY4yTdV&Y8BJz+#<(=Mj!`&{7No!OzmYE+2<hs#Lix>~mWdz7Eo@j^he5kM?QU
zE_rsDqh0E^3Xvl$f5hZ|b?bUAkh*26Bz!8aD)qLXZ)!0NDvQ$stq#4ZgA*K5fleo$
zlwkT$A*50T=AVqx>?4Cf4f4t76paXF#Y#A(C*`1LKYyZm(+Ll5)sr@n0uqGt=qs|3
zwkGblu2)l<XOx7Evz!Bu*07p2i!!Fs3V>0`$mlAhmXk($zCArFN*QlbPDjhoiql91
z+UI~s=xZiubFoh8joJKbPTF5I@+ofg$5Wk{BC5g~-bG`;JmAt9qbvY(*0U$KJg^u7
zw_(N9InN@i&uyH6){q>n%zW@L)uo}%%QGjKV^hv^QC{1a*q&=D;4-TyBxH6qwK;OT
zktp9n$B0qp)i!yXqTq%nH5IXj0-*-qdZ!d`BYgh=g<XQcNO8Mp?rWa4PG;HDLZ2*2
z*)6Vm;GWp0!)(cs8xi!W?eys4!Qakm>=BLNAm_QRUS@SzOFK#9JNM*+n!5Kc>O=mO
zYACT0FY=sLZOh_f6ymdyNf5G`rd7{Y9qVS(YwFRD?y0QpIy{qcC){2IYv|E5lNp#}
z9SN?iG<7+#4@00vBkxq3!Ctip>GM!J;=MD?F}zuK_I)|KWpQ3Jam=N?de@_P{_v%`
zz&Xx4*P5}(K9wv6=8}_kD9(G*0pgbw#cWi7`qL28$I_Z=Ok`6?_Ml@kNW+e}ryjJ@
z2?BsUf5Hk=NnSCKD?i4%!$A+((B+$qR-c7%nmlBXK3;2?@p~lK-zno5C25G_nTs**
zd(xr9b5;$seTfu?)<0SXJUmCONUXWys|XMpy=w|?Tnw?`Vu781gW<$3>@vgFwl$>r
z1Fw3I!}g7DYNeNM?rP4uLAM2P2<Wv8q|R+wiR4qVI5?=(v3^J8PxLhmX_qaeJFr*r
ztrU?0@|B-#L0~b{rD~$(eX3Z<&BC9%5hkIU=#D(E#MQPO@Vr%9gM~jR!S6_;GI^wb
zU@C1CyJ~w+JOiJ`qL}1!R<tz#08b5$n5u~^>zB8+Q`Kxz{>|flPBH~uL%})eO(Q)<
zYhyFRbxRp6FQkRT4oLw0YdNu9pN?Tj@0S2>J^S~rG5Y3{5YNJj4@xNvS}4sZ>p*~1
zh%jjsWb~;4;)XI<rSe@^=Y!h4Bg3<OsHA{o0ouILP`Tp0C&9pdm@Y>ZETng^HX;Cb
z=A;3$)YWL@2_H=2o-SCQyNZ&_@PbI@xPKe!mvGz&T;dbJ9<|y-Hc!&1c%wy+R?;1?
z7DXR=st(d7dmcXbv4<^;=h~t-p~uR&s<T^56wIAUoE%V*6(E}QBPPy9i}6h(pS{gn
zgXVvj=M_p419YpAob;^`n>6j!dCwxO{h=2jSM#j++~XOkmAL6tNk7^dvIi7KTR1fq
z?l`A_Kovxiutfk9lkZgIxdU+nJm6K9UCIeOj`bVFgPc$XJ>2sM9e~DLwP8rxoyqyR
z>T9le(*%z7&T4kT-eZA{-!*4eIvUevdmMJAgV)$nzw@Rs`CHeea@gG-f#F4!v=lMn
zvQHhWv9N+T6`oKS?L2x{HQ-W%L5CRb4RntnSY$nZTvs%e*|ON;wTH==AQ;a8R~I@d
zRw#OAy6eezGo8n4F~`!l>yffq6dZDRHE4!+z7{*Qn2vhmAC+}c;9|L73j#D~dmIYt
z;TZt;tx*J{u5(&?O5xqUg0l+oiq+B=mcZ{+2K--iRN!z9Y6KV^>T%OGBP10n8ig}b
zry`RAVa-ap%`tgeco^x;NXZ2~b4(nHa{EvOs%k+|tw;?fG2(;LlfGytD@Y746@vOm
zMgAtP6j-1nb^6zD;>p(EN)tXdsjoSI5m|$s<DS(rDH@3u!L<%JroFt5r)-$|)>8PA
z$Pd5Iy&v$C*a9--R(C4Jne=IHP@~+i9@UmS63%yhzESN~hl*_T_lYN`6yxHHVA#m#
zp0r#nKGVU_L^sKB@}A+32DTy7;I&LeA0G9H{wRty$>~rJ7{j#iaZ2E7-s|@IWV;#`
zVtqSRGvj+=c(#z|+NjIoJ4=lDkg59jsE)N~kUq|t^q~!!U+|k-;Qr;5j=wE8{u2vx
z{{Sqc1JnwF8>r<6%C=GXR)Rwa0K7@`#W58RifvuLi$CtvtE$g)v`21mPhU!y!)&AF
ziAFoptK)>=dJ14zSly$`yA1XfUF=ZxmGSOr%`1`Diaf$_twI91)1c^AaQ8K4DAF;t
zR4DWm<vWM;pztVQDPDTe5HO)m?$qpUG=N}_X{V8ja-H8wQWSmTieN-z&m)RM83&qH
zxQzxglTp3d+khyz6KqmCb5(BbBAz|6CRfuGvE0bdk1UbvR*nkx`WgYFhtzy53mI)m
zQhK30Rwn&JN}WURP(KiB(~iTy!S@EK-Rai%Xi`)Rr?x7Da+ZD|hFlAftIjj)S`u1C
zdHcvD4eSk7zwoPVceGsd_bUw_P|~KuD<ZFKaZgbl5w>X84S+>ey0U514>bqAX|~$z
zH!=BlDg!qetBI!D+=X<Nw)-_Zh|h+_ZRFn9D$D)cRqwZ3MHme(J?R@uvx&J!I6ciO
z+1Q5N_F#MDngYWk)GgTIS)1r8wdKrmON8y|TJWp~g@rcv0;Co;_}%27qTyqnJg*t6
zT67ahDKV!52PERP&9qD~h(48>HI}Engbt{Or!-tf$w{Lit~2SHWBsN@+FT6#))~{a
zrXTV2ppLnwe`4y)K6}i4DOjR;{4}>RZkFl(fvO?lJ7wq3WAvnL6Hv#^e$)*L>5t8*
z98qR5@_1U#Fbhm^(;25Phb+JY1;5}`V%taAw99hx73Y)IuFW!AE<)r1NJe1r^^WoT
zo(E!T<W^9?K12$AF;T~@+DLZp+TFpcf<%**IpehhE51f}s7n$~?zMMjM-;}lJRP*`
zBC?!&Q?|t?$m1(aot7`W*!*gvT}a$Sxc4*ww|Xt4g!yM<<AN$XTitI(Ikuij0PJ}b
zBi_d3{H`0Hr8RXXj$BQJrD5Fc^k0dP5+T&$cw46Yab3NxuW6_#dub4c864M*Ngbu?
z<oRbc4ZJtnQ<-%8w#WBPLx*A9_f_EMy*qY(mF5~x#7moHSoI5Xalv)2$4>D^m8xwC
zau!4UEy1a2t;TN#Blv$>44Zwah<AO{kVhQQW8B{}E<Mc`7#Z7k7o{kX@xdQjQX&KI
zp#K1Y3OwkQe)@mkR0u%NpP2p>?Ee6@QN7F~pE^Izqc_%}ap%YQPz0{z4zz*E?rN)Q
z7R9)o2jfTfg_@paQSX`nx;O2ndeu{^+4KA1_$?>)wVr<af8R9h#9Pig;*>u)&1bf&
zXO3BjrvCtI*?=&z7Wz?U2A*+DGBF?q#bg~_3v#YN>?wb?QF=g6)v5BZxvL&ijOX5@
z-bbxre{Y_@X4{_IsYbZi{{T{%_cU@axwg_DUTLC6&0-yG@t-LHK8Bce*}C~-@u$eb
z=KlN+MKH-Uhh%CLcWS~q)xpLU7x18KSG}2W^rMl5&F!UE<tCS74CnH$akX34AL~f=
z#W3nuc;<Gak&5R`10IH)GBKVjil11%Pm%{>!@XRw)~}7e+k{fxpS>KRbFFn)*K@k4
z_oxNTI6pA_>y(m7rhU@L&7V_ImD_`pPuYdeyj<I<=2ZUxzNroEuo*KT9l5SJjl-U4
zKt&h_^{4E^nClLuW)527F+tUA{{ZLVF<h3!&q@ef<Wu%yxz#qcV55tmeu9|V-kjqG
z;GbZ%%U}*VQ-X>;nhTvO>soT-Y>a(^(+7wwH*zKV?XGo~9Xixx7RMBOG#tlCFNrkq
z(PTeCP@fXnf-wY@fUtqi05lkRr|jY!$3lEagQc0l=y!^*{{RUlNoKWX1F&kxSnxe)
z*@Mtxj!1>gv*Nd5l(HLr+Z2DoRWTe|u6-*M3{wd7qmm(WW&BNYNX5DejQE!K_+vmt
zWo_e=O(WipSc>M8c#~4k9$5S-t*>ewrUUS-!g$VUH-I_dQ{{+VnnPE;Zd&F3fKyJZ
zf4~#4thc&`Gt8<F)}I{0U$`BIs9G%$yEI0vd<Qd=PHkHEw9Eji1nuofzuKLm7cRD`
zdU8b1pIVAr+o@FUna+LjPzNWq89mc9Sp~@z<i>o-KBbK*nZlJ0{{T|e5oW;X2c<Q#
zGe&~D0?s<f=kcUv+;CWtk6LQOcW@8c?OE_~lfbJ{>6(dLn^Fk>0BVcGH7fZ?4td?5
zT2UD3laH-SEw$CT{qib(4r;lS=YyZ67eT2e!~;F^NI5kbb_2a3b^zcLk7{}a$%K9J
z_|vwGV-*>jYJJ!L0KQE=B$|F!89?`3QFH?NOOAk2c|f*6s}SjzmsyPgQ|fC`JSs$A
zzPo(moKka0EMlsUQJO|XBw&ozjn0U+>6oQv?a8W1VRGl?jgP$?;bOT?X$pZ?8&9}V
z^MJooQ41$M#(uQ<fPiB?sa)WXTDH1v#xfK2r5a`1WVB&^txK3JQZ2<fetwm7X>&2*
zqxxp8>AG1<g7P}IU<D^2v6k2?@}VC1>rgituIf7|6mp1j*NV;5w8oqMJzyJv?a<Ww
zLb*;)atcL}82qBN*TZ^~$(bXC2m94K_-0^(ZNe$VS1~p+K|{$}8MDx1=qmhv9-O(|
zcNgJOwuiTdy<GbWIfBMMJye=FAH!Pz0NGKf=IjqnDUGEgV;4*K(abv;(IZMfcM)Pc
z3X|-&4bt8IxUHQw$~#tNSqrf>tn8>NT|x4kirZX~pR=|p8aYrB$^~s-o0g2bxJbdk
z1Gua|DVY7@MI6@)4gKdJfmT+~GzFeTR_rN@3*#Yq_oZkgJ$U*WVzE@aCO}Yq>4oOq
z_eEV6`Q*|Ia85H$;wf&QvU5{gr1DB5+m}5m!9alg+*ZDg1af7zWwFI6O2s5o{=~U#
zZ@5MLGgR*_MUw;*`H$7O#w)UGZ<p@zj@8R*w#yyCeu2GeREJ|2@6Rnw-5@+M6?4m6
zX9x190Hl4xk6cyUf~v_P_svKFKYPDwm0di*p)!2{%~%n?Un&0p@0tcv2w3sboFkV!
zFXL8~TcM6YkM<2;)9fxKxDHk0MdvKPdX>V(J3S_Axfgns2iC4j;n!ZWfIS6tp>P2`
zt3Ob=lt;1^=lGhVnU2RdK9=!x8DH-cQ43CaBQ<7C&nGXF?rFjy{7!@Ms{*iq0fOKk
zQBM}ASDC*dPH+c8DPi)7K5V-Ou%JS%oEv}R<Np91rVDFqoXmc>r^uGX9h15IDiN?a
z##<h=t_AB|5iW54c2N6sTM+5C*3pDW@<$mpTTaz2A&nw@gVTXqcve71dWkZOtLeVa
z18hRgw}2~+n9T0XW7=5fp0(NPu|D0YD2<Qt9@Ug|n_!ui`*WVPQ4>ct8)^BfWS%wZ
zo4vDIhefk3{{SB(pHWJ>9-a<lxhFMu5l%a+MaE$y)a!YsXAcH{3cVJOq=Aj(dzPsN
zjim+RV@l((1b3P-1xzRMt9I~dnt~R!fHpgk#%h_<bmJ!zH$AIkNqcKYF)QakbW}Dn
zTO_-L6_zm?kGQC78(O&EF3&F{4wcq37G2%3n&t1W;x`g1+XBnRb3y|Y%Y*)_@)aVx
zu+NkLt3pF7f2rG^!lghIe9@d$+>(hcj+p!?S#k8OKQaVQp4<^gC$=3eWA`SN$6}J)
zCVDBWQCzcp$!s_^6t{N#fU%5zl^S0LJ5k2m^c0%|sjy=#YS;se@lL;ViUxT?V0LPu
zr{6@%A&YQv>rK`ze8|L-46x`kP&1yqyL*{gq8}kVcBo?v4&n`43;a8AN*FH~tGKKY
zAnM#zp)5+c3%l6WStSaYE1V9(tBdqgffFBXv|Ls$yU8Kr3O%YZ87G#g{O4o^V>vyl
zCZ6*nY$yk=Xt?ZaSRh-J%K$Uf*ILCM6%2Bsy!m9hR}F>S2+mD)wt9`4TB1F`57he9
zF`0V3v;siQFO&huRUdk?@o%0P&0f`nH<JdAP1}2#q2yqF;Y|S`TX1;X-&%2KHvPu`
z0KTdb7~lrtl&UD<vT584X>n{iz{l!ot#JuFLO}L4M|Mp;8C3kl(Qq^t=F|_K65o$n
zu?_8<GHy$Kq>9NdgWS@s!lBMN6qp^XQb@=eOpifTuI-xUG8#O^gV()bMXpO39S_vg
z=J6b|s7Klcdm53GNq&~+%7WE6;IZ#jB)#5AF(*FNPD{Zn5^#SSiLMjael<yfaL$9W
z=jlo%-I0(7YR)pmU+?Ch_K1*jSo#38Tt(u!?^YnPl0@H(4%w`qv={rK{{Sj;Tuh{V
z@(gqU(aaV%7e;nn%-H%>+iOROLV2L$)Ymipqi}zUR>!?C-aC)F-}lu`?lYy-EnpVq
z<Yjq(gc`t6#y0*H0lAfr3y*Tt)|O8}pZBOvz{_Q53yP!W$<N&X0KTaVubx?dI(HGI
zFi$3eyl_Y7S>I^D&gGy?PgnewfG_1i<^KRGLh3rbXSDwS?SJF6)}J^V-~Rcg37hts
zs#~tsV#D5<cd12j9v3Pr3w!79Ii=ml3nP0}fjn%9#!2-xD4jvTQfi{Bu+Nh((6tBU
z<H~XMYM?B=-=Y#}KGU8`<LYXt2Y1|G#i@2={mAqF^#U$OHsgcG<4<daL;kP^tnP!N
zkH)5p%0GM{Zqy8!wHHu)x98kcM^?JpLd+EV3W{iX&zKZ?VxbC(c#xlPDn?uv(}9yW
zKT3_RrIRJ4=l$A>MZ%0bAEMM*3cq>J)Kw%R!pk#p=M$d1Q}@0{&iNHpWFY*aL+?@o
zf4cegCYTa=j!Db8<E1c$W6tdN=A)2&r{y36{pyP+jt}QZ3jh#1{w+ZxkC*=d9;h;U
zlpmchUdlbG43skGJ6Ati8IuHIKMIQ(>R0fj>7Ji}qQP<CrcO2k^r55~#^LnEC~Wi~
zf52&_@$3HpeA5e#N!Pg<_F8jZ<X{&35~B+vV*#=17ME;;vl;|D?F@eCZ><e?F9Qr|
z6i7zht@+Sx<s+E$^?XraA06bZ%B+OvxoWUOD)6K5HAulK{{YK0ANJCn8qJ=ukE_xc
zt{)u$s85;*+qdy*y78{i46zgSs?Tmg{{WAemp;@Cg^kWm){h?ap(ZLndmitlN+2J_
zatG0BGXerX(iy$N&>=$12R9M@HqtP5%9;NF@0FpVk3Z|A&-=825OjGCJyxBBD1~v4
zIgjB;){%~U**>(4nd9fC8*;=CpZ@x$1I40e@5tZqEKqIYUN^t}_GzNn<nT!zuZm+?
zu;ip?>hu9IhTJYj;(y<!GFzz`g-QPadZ7@V+{Bn4?No~zbuh$F){qV@YtQab3UDxI
zgpcy7=kMSJA4+yyaq{~dQv$)7KFFgTfTsDQ8Qb|SLK<Gg`gEz#NJj0=`A{LgY2yR`
z03D_CTm#E~6!EzK02|VIZa~iS_)`KB&KQud^`}QP%0|>KPhxROZRBo3NrCH3Yj-R6
z8z1jd8Eu;3lZf%2+qzX|f@N%&fjREg9BJf`0v<hHtt`?o%LEwrq%yR-l>F+8^lZ}u
zbNnBTOwhgyl?2pfSOb$9{Y5YjGjDVhEX&SWKPrq6=OKaj0-vyB{{XE(4)c`oBqQjw
z;z3jMx%?@M!TZPZr{JIBV@w7R5BJFS6driQpUS1r`%ZC47d?#vD-hW~D}E-N6^f6O
z^{XCU;rDU%H5(xZ8$kLR0ANP$qw}L~?h3AcwEScELHEr^B&`~pM5pOU1Pc4Hh{ikh
zsTCU?SMU`acM_lAR2}jv)OkO}kHVM`u-*JXeiXqQe|-J|tPpo{$Dc)|026}pAEMF%
zt4817Z>1n!ah5f2Vv+v<Ef48PBOSv~GN3~3jgEgBy>8_Q9#|ga(|ok<r|Ft$jR+%P
zBd;caH4<cg;;pT;b41150qKgtR`Q!G9Bb|kU5`>wxRsQ915;s>`F=}oOpqz<c;R-k
zW8W01Jaa{um@qx*CS+*Ju;(3U)fKr`Ye?@AzG5@i6_0!2SCw}{Uyj)3w_%DwAlsd!
z`c~SeP!>NnDwM7(9$znowWR+5QrQEbJ^r;>v_BF@{{Sq|kEMFrug!tLsdi_bywwS#
z$6rnH3ZZASW9f#)LYjYwrI0GwpQ$zN3vImR>OpD)eZ|El2adOgd`79g-X#E5JkPGj
zBgN!4SE*F5dV54+$_lLZ5VlUm$?uAgJT@zRdgOw(vp1n56>W5n6F2<3W7y)og>Awd
zc}N9Fv8y)GjQdl#Sn-)WKjJLzDnA25cx%KWJ?(%$ySlxg*`dx*9QC9Ya1KlW{b&*5
z2SeACatQwbfm5OI?}#pVNZ*6~?kn58n_xfGMt=%$k~JJEt`ABFW5v&d{6q)bWBApZ
ze*|k%oZL!dUqIZ~uYIWlADm?R)K7N_;N`pUDcn{(%{&Ic6D8#2cNIK;4{g|guA86l
z8t$HWorns0^TjfGNsR1P1aZ=x(79R1ufuCR=3AHl0KTfkUk~(X*9_7~-lW$-8oS|{
zo0_(WfOo1$gP0x#(YJ9CKaD(iKSzxGwy1yJ71afZ4?|8^EuDU6=BmJRE8#688T%|>
zg4C<woh1%Z(h={9=nODp0o(GX`3gtM)Wl;Zg<yp3hB7*R+LUQlV}S&Jh^+>XW`Csv
z2Z{iux_zoPL=l7ZsYRu^{{WUr`BeDlv8S)z#Q}1+*rNj~7xJfw5eF)y{VLYLIHWNl
zAeGGkR|<o$rv&r>eiZW>6Zby~f0lUuRE9;hbI@njm3I0AflrZAEEg(1rlV;iJsEwm
zK!+W<^rr*I0A`~Or_z-lBdMTc^3>o!UQQ{QVtuK2&ou0SagYVTB>S3bjFZTuJ3VMn
z0OE@QI0K>Pkc1r+QwbRKrQS0|gvnM=tHO#=At&zVH5PNyq*nE!z(3_b!;?*Dl%ABm
zaoZFU2Q;iPg4#1k*2|y1SK6JpXWE^SjOKtK`z|_4e;PcO9UCI72~Zw$nmp7w!2Brz
zSz(a3QA0&KjEKuslPZcqDvag7S_V@MHtcx~N@rogh>Ex7BXp+i3_31p0Sd@i=V_!f
z>_2lqK~fPX@PK`)ctK8fjo!4b##d=y8Ccl<6$jhx<88A_s>k?8TGEnMafc%vFe-yt
z+p}e%LVao3upl><&G#nH)}0mAs}q+Wok}d=RmYOQT5D;x@75Lk1r`x9Ttm2k!`B(9
z1EJ+uAEBy?rP~e!U#(b%(g+FL0L=p?LAc{0rPw$In5huwXIfSugYutB1Uw?+uUb|`
z7|uFXXNPkGmt1xRfoh<A_v8JlU`@0G+Ks9^{VE?Q1C8Y3l)_kit<5fEfR8lM$26J2
z6r(5G>sCTD^+?2)tU%>?tSG@~@!Z!>I&X=={_hpd#DGle&eh-(*0}L2soRHR0)y>N
zROAnOl0^#KQVzbqO5!_FcHa!UYeFctaw?Uw0>Ju;(u|%3LntInFM5jGhBabA@*1xP
z5*pVJ@tIfn8D^AyX)tk4=quJolrC^+$mvPfnnTur6t*d)zdA-kpK1c)n1gjM`Qm~(
z=}rS2(gD1C&_-#)J$RswC;_;pmEFJ;@;Ks;yFeVLh+)HS<CBt4aa_?j9@W}-iUB3L
z^dq%$4hG^qD~h&~J7~Mag!LKk(yO>XHCT1VDh33vzoll4Sy{)gdW?<3{AyQH4L1Py
zHKHMxG+Si2)DcQAu1$JXwX7);e&l3V58+!+Ht)>AC%X=vfBMzvDl)1uz^<x$9JPKS
zo>X~1ApEJp5HH*u)A2^$!n86IXy9xZ>48eP90kYHo%nM}iU4pY^Q9?~&jx_Kc%=gr
z0Ma{Vmv0!S0fRswPy%foDB3ur&U=1zXBngdfzLD&2<b+1OSj&D5H@MTfV@&<1I+<p
zX*-^jd(&lj;!W;A6ab|+Q%$-PlB-<Cv9H`27AtHj{{RuH5o(u%m6s%X))gj^(N3FZ
zRV+|Nl2v|{pEcA#{Hm*p$~u+q-`=8(b6J-f$w?2IhaR}%vFA1RZ5?zvjjV(TPC*@M
zXVR^1z>+sn^sWMJawl$1G20a!ULx{yvUdRRd8R8Jr;sdM;eq-ZmO0~P`G-BLjQ;?H
zo+!fkk{9--$>TIb`>07iy{NMhv8u5Jaf}R{n&z3A=3qOXDy{E`E-%<Aiz7S$YhO&$
z%CfYB=RBNxQ6~T?LDs&?wJH(jW8kzb0mWO2*}=#-_04EO1{5l-Y*=Z3Xn#;TlU#0B
zXJS?{V6c`|`HvavT?K}Z_GrsLe#W$x8%-`C(h$xLK&(wuU)}OTq@P1Wb{Q4q#Tc$Y
z9jiVFzSBPc0N_w^PkLyAS-*R5?222Fo=r$urTxq~2s;k6LY>(%sbWcHYl#vFR|$@l
z)7e4fTOzMvj8#oPPg`G|{%KEEBD6~cQp|7#dK9Vhqk^qYeFqcJ=8&*ZSoNq4)L{ML
zQC!?0wRQ}r13Vs;wahGepNy{l(Wy8LaIKyzlw+U9w6&QGy0qkzw|4;59iaXcghY8X
z-KM75icOTjj|5VN=bC=bdUHm@KmxEm>D{qSC`BPWPy(L6g&4^L+*3)XNAt>y$5B8Y
zmuqnL`WOgy{JHB~t<Y&*iE>!=HFo-GBh!u_x8YpixgeI`*WQ>G&9->lL8I)!c_y1|
z=H<9^?rUPtOG}0xYrfDq#}v7c%y}a~JpirW4ruaAa4v2ODlgnZF;}9nwzoNo43Ydz
z&1hLH`;Oqi9)hLH<sA$mRdJjTN~No8by1P>)6?#Onx(2E2*VCee@XzzkpjQUX{aft
zMl5*9?M_An)G?Or&JRl1jFTGntgCUHVzi)Q6P2XOLyO>h)oGoG>E5ld+%N#<s>vHK
z-l!RyE&~#4LqS3Ir*`R#;<KeWCbaZk0X~Nnq)BH;KJEv9N<v6H98^K@anyCCX#nI_
zre~e_^4-P4%Y(FaC#7)D$@*8Q_|hRYfhBq5gZNjMu;6;*nnEMR7^TK(4Im6s=O6uQ
zGm%Nu@HwCdDd)e^uE7Ce%`)EGBXd>nF=9=l8TFuKOq*4Qr=@pZ3|!j=9erzodA_)>
zL->5r&0~k*sWOq+Kz6PVJk-XtBeS*(pEXCeX&xIiUB&)icBm|^2^sViF09i30AtFq
z47M{-eWusU3klpkYg*M7Sc<*~B7rl&Z{4H2nOI?g$rVAaPI^~U<E<$zHHLV|!)JDT
z*CbR|bRE&nBwB)IY*o}|^{Oy97^{iSD|F1Hi?Hy(p1$>cPDV~EE+#o1)p|C{^{Yl~
zoHh?imvJk=sB`ku(oQjovPo2A9MD%Q#Wh>no=!m@tpY1bpko8QbK2kf<n+O=j#MRc
zn#R@byx2qIk;P2a(RBAY#wRq~;O3RbwKt)z7ImZ0d=dWuAW_K#Gjaa_0{;N(*HbjA
zw(_3AbBf}8BR`j>HV^!?Z|7YN&DQH#0q1bVWcM^V{{Ss!m<bPGO6K*8SGT>8lsiG{
zdSbdubD1)F=hn9kj2HI4UBd1Jb*o5*QSh4QNRP4Wk8ai1Kr*}!#<29u6|jIrhmG0#
zdsg%#<*Gs?BO|79TDmC8zib-K+v!^RI)Mv!+{FGBKx`<$`qYDw>?$$9AIh9R8jvMk
zxvA3?0`cop#&Jjs3UN{n4Mw=)r4=I-8gQoL@TUp@l~1imwF;V<4-}Zk;*q*jg(Lmi
zKyqF^aGo7~{Rbwz4o$m@3irPrM$>34iUB96HR4j}m%EtkUBAQ4OG8BqYguj|Y%%BD
z^sQ@e4qi&j=E#V?tI4dky13KZZz{vEJW{T^cvp!TO-+hBn{5KYQ|E{l9sO#;=z4L+
zZQ~=}y!31L{TgOI^uO?sUj^nyKJ=^yqm3fLcoxu)!jx$mct7ePCcN1Aiuj%-G>61D
z_|KSVu+L2zPMrA65S&$8+g&!&5=0S#M_hETJpSLl{u!7PNcz3q!s1B}J$>k~9ejG7
zy6~78?^dF`R$zAmD}Wbnr?2Z*tu->389z#)9q64HW7eqNUCj#siN-lKlWnUg0C0V4
zPAkZ+6Vw_k27I0&Xe0tacAogHJ55e2=)*@MmhL?(GgH!1@j;2UxaPU3t#7p18MZQm
z(62eAU_A{aa56cm(p>UuiPOAIBy1L7SuyvGbk_Q<tnsTWFU&dvNM@ooA9i@D9k(yN
zQxl;X2Z~=f9y34<cXc^T(yyN=$MdBv^3&mRM=gp#BHEHN&CNYfD&Q_#r!^;-6SjV|
zzGy$f2hxBV7D9UM9@O&+I^q6mP)XyhE+5nAC>au4M;F{pze-XLdQ<YlsKq!QI%b%N
zafZ$fR=c)>?KVvqf3035H(^X@!90q05yt917i_cIH+=0qF<9GgwAns=$TN}YUX)ZJ
z`FN_gcF@lj$x&E!=|#kH*1GMysj}%XPkM^`N&8G@TN%jR$X(nTn(xEt@)2zN4s-KW
zi%kbnwfU0bGM<gvoxtYTPuJD9q-1-OTN-tx>M8qv_9vWYit3b@q5boqZ)#h2hIcEt
zW~o?C=1_8j_i-_&iEbG43C?SG$X%puAC)vjM@6c#4NNlEMX(_znX>)ch<`I(5R0c6
zrwH-%qd+;Pw!dyRCVsT^)33tekvR9Rhz#Ijq*%**sxron26M|}cCCh7A8N3cPFLqZ
zezm^3ebaJb<JUCSw73KPL;XPMOF%gb-wHu?%*uSS{{VP_-lMnhwbi?2FY)X}b=wHx
zh6tc2EzKGQnU4;aDlQseeuAZKF`Y`Rq-VWqgvT_~!whz!=qzHN3)^nq?(D~m=A=&#
z*{?)w`j)Mr8NQU^7VdGurEsy7noY3B$PeQ~Xx5MSp;Ml<u(q-l$Y0K#_DML)C_a>~
z7BJJp`h0J^TPEt5X?Ds!SW`8x_A(FOA4+RN6mowmE;|{gPqt&0iBGmDT{hk~+>t6C
z#0tE@RDdbL0qaLFScG|sFdgyrrvo9+?_cw&yrG^AI6|ammVstLw1b_@ex{L-p6Bzc
zLO7T26ZlizZNT|AF{gAEGsGF|$)yme>MGc1z`+KYut?k-QE^$2`A80MY1;)^4GIhp
zN%o|YdvqV_WOL{iozPj8!VGn$oO;#B;`2s)vl{!JY3pwmdSv_4<_j{06}W61Q?_xy
zC+S*35C;mi6w<7DRRedeCm^vw{!z{WreR3rijc--eB&h3#+f{-Sz#C**wM~A5ReGt
zpQS3qPb72iQpS^6WM(0sPHBc$c?sRtj$p8!Nj(N=HqX23PbYE>tO2GexL3)Tk)D{P
z%sx;sH~`{<Z6I9ZG&^0E&hS+B#Z3j+jyyjtOPz|veU77*#V~9vOCFT#%cF3|ZWr8D
zb!_m<ntHJgl0^d>g+kNq2aqakASd@CoEi`YZGrlVcCd&ed8Ntc0QyyhSr}j|F+SBP
zzjcpfaUzO~`$FkCUA%SzmDmn8w_o$gzLgr=$|S>~1bWqreOFPPwk4T&C)X8nSCvjC
z3a{*QQ0B_zGA^+e2J9b7rq>Rqh8U?QuzQKi%PI8Z(we$7Tff&y^vzmqO$fI#vA}L=
z=1GAEdBsZ|gfSk6KDA^;)8xpfaTE)=Y!XgrCDdn}R*|<+_wWTO#<D)uPCk@eb~532
zo<Na;&z_Y%%olJ-h|!;$ueEgcI!&~AlgrrWsjAwY+C&UW1AEl-Ty`-U&PBq+jLl2-
zE5JVDkE>L|>j#IXo3cl9^`<5<Y-cU=Ix70+tc^A$Q~sIHsTEnIW83hknrt^el{<*K
zH0X?cUgZA(yHw4L!S?y_{Y^2h6c4-yy)@jSj&j8G0A_%(E7}-7XK>%{^sP-Q*4Fwp
zK60q&%0(uXroGdNC)}yo4|?8hF46^Jkf=~O09G|G(V9f7absm{jpaiLIQ!=r&2y8>
zJd+sGV2kv|D@Nk#6_KG9%tz@|XSXvPEG>iDh(Z0JlOg*YE5w(jo7htXc8ez8wK4VL
zoHY3tEFo-q)0W)r`O^cXZDTQ1*rM|8!@0#wC(}kS8y>Y?(kRB&i}I+1A&z$9ivgm|
zrArweVTh07sciI%TZc&!X&yZFHJB|-tf(9&Pg7lvon>!rZWcCTG2GP8LXh~NNTUjf
z5Ds{%H~N$o_)YuU&~&SpvYmuR4&&HYD?PA;7L@Goj;6Cp<rd|=ww<>%w)}MFlwLvr
z0@(ro0CusYxhwL*%su^Rg68r!3}p?D#VYM3vKF1qsP7YT&8XwKTvWqQMN^wq&1S9b
z#NX=(E9eF(((ib;eb77Rk9)9LcP|Y`=E^_^;ZqGww)1Y^m0+#J(LPbywk#6z?5jM#
zCUJpENJzhJs62|^U7H3Sa%$`n`QV3*ko(qpiJ@YsIPZ!sT3I970SZSrtn5)!RlR~a
zOmL`?$KE}KX8p3@5wb#~+MOaPcEbKN!4b`Fm5~gJNghrlc5kgSa2zQDtociyyPB~a
zaG(XO)xR19XNj19%U{-!rY<qOpI~ccX0iis*rOiUsZwn>?=`3c=}O};0=$idRwUO$
zqG{7Wg_*Js=~F>>r^?ul*@5?5R-9~`2Hb(^QrSS!l^Nb@ocDf6I|k+*vsUE=m+x&J
zwTp3m1P`$zGBDtiNe<-;tI6kV$XuW9rB-KfM&*BQwRihfh`_g1KD71J*aQBKtbNT{
zCU`QqAyKjJDGXB;#>PK|Y7Jr4axLRrcFiyL>*tGg>FY(n$?_)ve&$c06sF!|jnKE{
zTPxxnr<;7AQBSw=6G?Qa)_{Z1^`zJrG}|<a09ih7e$_kMhUh;NR?D=YH_EGut9tJo
zEFfUgk-;6RIgv>idZ*b3?&rAyKe{T2I&&Y9+aA7^WBUqun8`fR2gW^3C-x@Ko9!{L
zq4la$k8tIEh)h<y5AUS>s%S0kRX8rk)QX7N%!mDKZSPVm-o&5@qQL$fb)%UJm5%!z
zp=_6seFaLfX|O0SHc36jSN_u~N1Y5~+!})OP>w|T0)Tj?BV1c)vmnL~YPn|wP#{?P
zb|$#nX&Bt8lH+V&#07MTt!eQ>xtRJ=V@TV^;5qA9ceCm7-0YAvl7XF}b4{DX_Asd-
zhAR#HNogd<YAy+(0jC}9xo_QR@-e5i)Zf9TjC<C2@e-ih9>Mge+r%;-<21=M{?~Y`
z`>RM%z3L;YU&q0Q4}9jbA6IAOmdWo>olKK}3H)h=jlb<{^WHJ|Rf}C$P?m8X11bLK
zu6SOP{{SrW^=h>iy)Cc$sA2?n-${(_Jf~2*x}Qqt{6Qq@o?HO@$Ed8P@rC;wZH-5>
zRA*e8SqzNoT>5iJWLsrK`PAp$l~s>wWSWD>a?BY20J~9(mhF-M00FDHC9xYGF-Y<3
zA2$_PUAQM~jt{QdMv_S|Op+hMmB5#FKgN_2Y8|qH(oB2Pc1%Y`{OGtER&bZQkB|m=
zCc7Bk%_9NsQ#kdnJ26Z-D&TtW#UQrb^OREFrb?Hn&X--DIi(A3>cDs1Rqdg*@<UBH
z1dc$gF$n|iNBFe{CU(I{!S*z42S7f;zi=}jV@#6f)*tnV7wT&wD?=a5CoA-*r?p8+
zmzkTK<%V-bz}^1U(^PPZed#~7?J#p0J*x#_RXoT?{05)7BOFf0-)#VC&#6Z#ArK<x
zjylwKx2bD!=K#!oF<Io2IFdv7QjCS_=N-*3I#=;f@(K%A85>PvnT)Q_u$FF3QYVaI
z&-@Cae=x7h_zn1=4RySlA@atc`_xZ;a`|Rd8SD*bM(nr-G-K}c_Lw*Pv5)@xGy!1F
z>@$TY{rX|J-ND<A<24eM2PI>r&IjIK!D#?yHtMKp=*XjhtMnBZY@fgREiOm*-2GO7
zEk|_dPRU(=-CA>9%{B{7A;+kyd&ub|pMan_&o0J`0d1#Y)tH}LQg33TA&=IoyvR5^
zkK;}f#Jq@DpHlR!1%+Z;?q;kg8-C)9b6Ng=8~sqn`}J-Mq-DVhr=|rVgGvbJZ|6uP
z8+qD48f!9!IE6m76J6s05->e+KoYde>Xg$ucad}Ss2X=;{5byra-j__ct4KXb`f>1
z5D&h`=(NSS$@}tS(`7;=n2uetKiS0qTpznEzksJ;ED3UWFZofI^po+ZgjWZtk-oHf
zZ=Q|$(y$T`*f>Z0=?rd0JfrxvHLaUz<Np96RDWh3qw$iM4rs{ei}<}E4S)*ApZBRn
zx`EG@N4sW_+rk$m;R1jGv<=701bfp<jE%(rrBt@<EMxGeW&l?b=l%mlfQ-tY^U*Wx
zDol>@=jbRhTaGuMrpg460g})E0DRB_g1wo~`~rm}j0t7OrrK4xj3477oG#)Y!v6rB
zCNgLw7zn}n^{HOcFE4X5bH+DSL3a_s@?4Mis!@EBDIaIa9R})F0fk~l$CmBe@6wMb
zbhq2j_o@jmRx^WP&->K~)LokkYY-mnXaehbK!2)UeN9Cp1NUNHzO@j$an=MTgMBs#
z5TGN`Y1l%x_Bd2bQe=**qwu9mtD(;1A4H||u3Y@j`7IU!RoeiAkN6EJX^$RZKkyoH
zd4lro`BY`+JS({RQvt<gZ2a%|3PBXd_~bOrvk}X`=SU-y9I^cA0U(NDo@68IN+5pf
ze;24e%OE`G{`;jC{EXxN`=%mhwI`M%KGIW7r}vpXzj;wLyeFz5{AmTeA->|!GGS{N
z>d}Gj)TJ%cq|m9T4ZIot5$%e2iWMAS{T7&k<+TgM@ssUP{jwG1rWp1asft1~*!v|h
zk``S2_&@B@89aK8oQ@+hxnus#K6Zr$L%I4cYJo`AzEo~I;;q|D82L&u$?9ngRJx2V
z2b$kSro5`hh-CN4sU~Ql`L>_<0jiI35AZkQXb~@-yMN=^&-@CVyc`i|8~z1VmR|l?
z{OL{6P8J3K0KTb#VWnZnwM_e(YRKoGv&22~Q45wN{_RF;K_*uuqKaS)@6X7Bs=dX?
zZL1u74!EmgMA}=<jN{Nz=B5~z#ytf9QZwEhVORe7pi6z*ANR#t^T|9p+v&EHPWb!M
zasJIA74v?_A&U9{wJJk)$L5wz-om75oc{n6pOrVvn4D%xEHQ=)!}ny6eQGAOyl=fL
zeRov*rahSZW|Rq(WWq@L(-~0dvt<78l6&u|BeQfrK3nSbDV9)vTV*_SFHI6mf8~T@
z>huydtl5ru$GcLkqN3#O{OQ=aVUn>gr#YzFIiDGL$KgQ9P^xrf6>=$}JQ)`?o8%C`
z>lZ%4o{*I}^NOFPD-6+SUP1Cn_ywxFNyzggA4R9y%F)U5Pa~gAyjHP+WrvTIk9^RO
z7*EGp9R3v;mI1+ePt%IIai%im-c}&?2CA*BDA_3^pLV7p>m);<kdJdgF}5;|{{Vec
z{>lzE#gAgt@3M@4s$Z#UVzC;-5&r;|L-A@-v8F$9AL7)$Mg|OV`(>#fAiV95^PmMT
zhpaG+`_Lp%1{NXo6$aotClnuD%07aCCNuosdNKb10i-kSz%sAkl@0(o-}qviyc3Pb
z{`sH_2I+8reBbxQI9viacgY@=0B{C3KmGGdkbmc;ARJuee9md0yBy*}@0w8KBlm89
z8c^WyVk4hgU^!KX1xWguaX<$n^J;3U1^JL3d$lfO3;wDwf8L;DAIkvzk>}jgLneRa
zn*KE6P;>jg&Vg`>yu3^4#VZBHS(pwPLi^Q-l_Vo0Aol{Po4EH9vqo{(3ra5}QS!_{
zK8Z*R(_3y)v3BFoRThQ$`CQ}un!jmyWKfLKK6{m-?mK`orNH)}W@$oyf%EPu;ZELF
zzZ#B7C2kpJC*GPGW6~K9)|iRJeQ<`HBPaL<J=&@>$QS)fmh|07e9{N*SEqNT1<xh1
zkg<>W6(NHdKf51Rs^MlMh@%{LYCx0j=g1$8ASWnCR*#QLFoUd!KMIR$?Higg^yZfb
z9Lj^}DcA{qLV1}-(P=k;*jY*X3SdNRZn`7rwDgA5WBnp#_uEKU9AwBKNaN@!qz-v{
zR!e0cDY!pH%{R&pak67fU`qc0w0{~-Gts~As&|qXk0w%2eACw4XCG#NscHmAlu&X%
zGfE^tGv&vRtw>-Q{{W9j{-x*<0(iH8H@naT4>AS+097C3P4kdv2@v-caH=OeZPfi~
z9gwL$b+{i&k&q?+!G@3p{{Urb^|j=4j7C_U+jF+5v!FcOLOroj{ip`{Z$S1zK+cK_
z$n9lOFnI|au;?o1?rvAij!mkgBzo612B!=pndXvTLRPeG=8F9bLP!eODtPT#xINP?
zGTYt=pJNTf)~v&IkPZ(%wN+6fUztN6daoiDCAkCCRP)X|j>h^sFvwrRrSn-3794w4
zO_lR*^7gUyHK1lv*k%LkTPa-$pnXml@wz8sc;HYkZ6B6KRXus9t3{ruLHDN!VqwM&
zGDa#`OuLzj6WDhYik7e+-NlUhntNHGY^s29*A%U44_XE}Ha8-kVpcsVikm>%I(DfH
zn?_ogh<?p(r{*7(IKgfPL|`0I=Al1#6mD#tt3bw!c(KBP_*2EQY$IqR=}<~$$6@rU
z<`+MHX9L=cfpf}$5rxfGnWJX;wx6v)Z3zQw%G~<W8!1Q3!voyX0y$$3%xVDks!}UP
z+~<nX5J<mufcjLPM)C9VYLl@oT+C7!WSW0L)|+!|Vr|L!RB=d8-WyG5q?wyU;Db)>
zOi}n|oq{`lCY{A#<c^$DgyNi_9{f_VOpd*184*S=*A&)<Kys|a`_-0{`=XiVwgyHj
zYy$$$qvs(<dX_f|dXtY@iHUB#DZt{Lg5;uOoM3)brQGx0kPtb=J0ov2>;-qXNn3M_
zx4lLz;$PwCwkq!7oQgr$BAtXlE#WJIG5FSX)}M1DX4*_+oEEL2u}I(=Ldlv|8O|-1
ztq?i5$QZ^NteCYl<y5h)uuyiPoE&5FpbQXoZhvx&y{dTMQWyr<ZZ)v0mh1RafJM#;
z=|TfF9_@e=M7z7<rC&26DT=WpXMj3XK$F&i4+jbf>rFCk9Pv&OGYsSLsSUfca-4da
z0>x&zMgA^n=_qC3=A>;s8;8L9Q+~v;sVK+kNMXr6sS6&I@e2>UMJqz*2c-ZtVsfDH
z0qK)WU;*UPm>pZGBhr{{*~sLN#()e0y-g?qM{LrqpZzu?+Z5w$%luiO1_P7Up1E#)
zDWWC@oV%B{MKKbnBa(kAc+Ey79Q=*NFWOgt0q5F~$KxZKFgkVm)M8=Pmj;mBqV+hU
zz*rkV#wa^^9V)9`0m}1AE~5T713jp)7Bi02naTQ8YjYb9yfaG8>O})34eLq{1}eXr
zhxn=J>fJNekQ3)7ml^k@RVVA*(vqq<Ka~I>8SRRQtlPhK*v}m)T5M8@TNpeKtt(s#
z!9WI)x{v8d>{OLGq}|@EfMp!|S3h>1RqGsm?)AFdp0$^%N43@cu~=7);B;Z-X%%IR
z6$jR#RXHEZuA=UQ0n(unlE%El(nX7Q+PLjnQH+6)N~Hp08RoCXFtnLNm|=GH_oyP`
zPL(-eLH4L2$D7Xrw8Q*p%D2GFL4e|d-;G8{2fYKQ73&^Q{=Cu6CUC-+cjG_`0i+|E
z1A6tP$e;tS9+c90(&y<&PAP~@z*C9*sW`<QsQ}=3pz=Lw4o6BxZU-GZQxTo4E^Ns3
zt}bEobj5c1m@-(t1{)Q{&Yv>^Fa|iTI{TfNeTs|;2B2}8vivWtK<krOqjpw)gSAJ3
zNC4yOQ!?>QjxzG10DfbN(IOex_(s=lqdz!1jz>?un(Gu`dm7BqZT`z)3`m<s-u0#q
zJJ)1Yk;gq)yG{l_DqXzL8`IK|pI-Gui;n!!NDV)3O(6{p#V-dKq$!rjrv=3@4s-2I
zE0!Ip=Yj1>zXpI5MmlGjO_(^KFsEc=tt*U9!kxedn9jJzKUzZ|#TNoXeJQL4a%lvB
zjDyWY@{oG*K<quFR6^MtS39a-?qY*1aaT17-IoY(0Oqk73FVG`&0$umNZy?m^=4oP
zdmec`>fAAW!Lf>DspY;$Jkcf6gafVyD~3|LJ5sRgyR0cl$KzQu5JxyC-kou9Gr{~T
zI$Nw{(5?hm5JudQjP<Omh&I0;cCN{C81hY5l0ZS`wvEhZVv&r{u;+@fSu@g)F-J<$
z?9RolF4KL_m{@#+7&X!@)E3c!yB||rid-@`$&h`jMv`e?nu$fS;WUoc4Q|~N1mM-N
z;*yd6<n7~(R}l@nI|9$Od*-!ZYiJdAAU@`@bj>}XuPx=~r6yg<sNgZF(V(_LxbKj4
zYQmdWjv<G94?$Sh8tjh5LU6r<4r-%D?1|Pp2fA7Agkkc`+yT%E==AGIt(WBc+0O3f
zyvIYjd39tbasDIk&3aPYe(4Tzk4o&PO(T|d8#FF&Qpz&UMt#k5SH2_j8)^^+dS|6$
z_={C>Ka-MMocdQb*DlOYbL&l#j>G##Svd^Hw-s9NRFXS){oq=_wbbRckiIu59D`Eo
zx{bBmV_?|*2=x^OHeg&zWw>`Fl21}<9n1|qfFzo3D$$!9vXU|DQmba57!>XJrXqat
zO)dpTzapb2BA609wGnL65P9N`)PP;pcS((A)T379b*eR|ps)N*BR-rOXb(gF$G4u`
zBM+Ay4Obo;)8jev$FRj{MC2w9(uQN4lTCpHdQFlp79cU{Q!S;mKy4gS7C5GoNcz&S
z$<<>YbX1~6szW)aXC3IUT)XFhI&)B8N#;h~IUOn>`85>Jxo{|GW?@pS*&I`qK^$kA
znn+72H3}#VS+a{TqsGIqt-Ds<r+1}e#kdR}Yg*e2)Ks=oCUq*jRSTAKO6IhgcPSN4
zSR9kbT7j8TCtAOzxQ}q?3FezUx`o3UY<N(1*0jixujk|I>r88q4Nwl}y)?7d#$;OT
zsU?{Q1mM?}%9uSd?de{JtwiS4q(vtK2OhP-&e?VhxH-luSQLmf4wWHQCV&MX8j%?f
z9V+BdDx93t5=2fhLrh(;xhK#H0I<`9A16NbS>G+4+}5p*i!ACMU{p6n6>3io$B&nG
zeP{!mEKPO34%8kbWLMj_jw?01JO}ZxtNJdQ);A2?m0^RLOr&;;dvN$3b9z>ty}R6i
zS;^16W5N(1CAw9pZ)FaPA3@%ryPI%XD3j)VdwSO8ii89LdH1e<*`3=MJCAzkY|!~&
z=QS*Qo^$aU0GB(6;F|N6Tzg`@kH`9On$2!8xT^9!YsV#gxxhHCx-z;koNUKNaNX+k
zZ-I`rnx_XfdK2Ed6EKl&A0T6jy9pq2Ydr|vS7Klkb6O)NT0@b@sbV-aSx-GpNRPFJ
zUCFU+dF@jGHdS<+AbhnbeBf{@i6VABoj9r&OXgd;{{R<izQU_Wg8+L_IOuV=Dr1?D
z_Bg0{>?-D_g)bz}LUIq~RI|l!%~_q0cSm30%ST-?WG*(b+@sjmoc9QjmEDtr-nr`w
zvkijA813{usC%!QHG?!S+MLOrc_8AtizAr5v&C}OJig*<sj>e6R5MnIWw^#2PbReE
z;9|3*>OQrj5cxr?LMP)Ng>3067StNW=sH&ZnlWa+{Llr=(}PnD8O<OpA>;W~sQT3;
zJu2L1fGSuPkZ>wxsAC_MOuSM6rw+83=ZaB4#{<nwhnj#Il~4Zws*?h7O@2iv=8^dn
zhH{=bpX~ZVw{Df>((0hbSAT4MYtnuuHZ&DJoY#hKU{2zGnW>P_>)AZ%$?7VwLMlRX
zO*^h?N-OQoX?E1X1qM7&1%8L81BwgNnQ(ciSYw)E6u&$QaBL3UdQ^1tfDJGW$`5iV
zSvljVrVnaE!Td2m7FO+}&unvA7Mjpj19(z;8pSGGuS$%r8h|@XZAi#+SaII865=_K
zEPywrYlDL7M10n*zNm0MZU?OcHSc^q9l<j~>l=D@tQ(6v-6l=S93G&rJXY<trX*jz
z_z_x>PZh*i;EseE1anqCCXx`b%*Ep!PkQLBHJfXpkidR5Ls9U(o#=LlF~3}nE1bE|
z^$k8<%A~Jil&m|Ri5<XY$Rh@<172^Z_=4izKqlPD_edl4uDeavZSIg^z;2sOCI<S9
zijh{Jie)R1LG8s&=8iE)WXf4SWjLw+*vA`&Ppwch;*?I546`(){%VhXMANQ4swcQo
zK2t~u{K6<{@HroyX3cc5uiwe4XHdyFZ_a==UURpB%~zIlj=!B`J@YZBTH;sFGzh%c
zimZ7Q#?+bA1tzm3B%WxD9QsqZ7ALupnx)dFaeM}P^{T}ghf14H+%MI(lg=m^)&BU8
zmP~#WBojB^xNQ3hmNd%chcxmObGQ#`cO8g~E;;iF`qTF97|lC+0gTf{%qYM+WALSL
z8e-fy&V8zA<S=85d(%zbx}W)JpJX)jx`IRZSp8Jf0qc7%PF#hl8&jQ=%MM53P0A7S
zM~}jpfu1Q0g^6RyIVY1&5V1|%jyuzc<nvD^M_dwkpiLEz%f?BkMy1$cO-#1Z72vLZ
zwD{w?kBrBI*AxLF#)_Q@r;oext|_4<BL%k8{HMn*PtZ^TZ*p;*((Gb-&~4ZZ`K?g8
z%7b^9PvJm`in5H8P_YcyCjzBac@Q&a@u{PYMhQ@80yr(8L7Z-5+?uek#8)0z&#frO
z7+O)!V?YtK3Fs+O6z`ADm65T~esvgw%=_qZ)2#ql5kLX^hd%XE>gv`7`Pl#+DUw;F
z3RnTp9Ga#qt)wc`G8}(+^rdhjI;Dp1`1l$26=pl@JY-0C^jdj_#S{RsV0IK{%{wUi
z&;!!$(2Td3eLh-y-@<r_7y-t1)P8la&&(;J_RqA)Po*#>Nm@ga593esSx!<VKT}Yf
z+f3j}quQ%Ye;6lYsm(5E_Zd9bEdKx|(4S6fHG!WT;;Jpc-JBjN<5K4w{{Y`KxsV!h
zK@>kWOE;;h9(l|@TvCN!VOZl)e={CTgnH~WzuFGY7C0m)-AJRI2()b&jI`Zp4xGhv
z_KtlqQX!D8NTxO8MV!XPSK6xML}JF}e~B8CdADKak;kPAt0bptq>9J;%4%P;85b@S
z4cDG(B*uiA@+7r0Wq9paZK>I-9n*8)6>4n;9n8jgFn`+OtFDV^jvVGsty~p|kTvXW
zg9;ZOq*a)unUmy=2m945Nfaaig9Fy2X5XKe@)dU^tt`{R1LZT=b*DhrdV+)UAYWQ>
zPIytrtv}{b{n{=7G|RKzGEbqaFzDAoftgWP*yfVeoJcVFu8!4ORRsQKvy`k-L_*mk
ziAsEo7n5A|^UTs8Di&^f_N@(DP$@G*9K+@GHImb_obJ!#L{;?$Dq7t*2VxIQwKn1@
zt;h%?eDxu^QkjqpGk|`zUTer>8F%8eCgUV~_u&Gs`(0|Jqg5-iIkuluQXP8EKC0OF
z2ArC@T=N7{KYzJE46?Soj$-r9Txafz>@?`oR8kk~Sh{trm(n4SJW=PKIU>6Rwuag@
z5Oy8wImsfCUT}8#Y6!^dT;2AcZxrlaX<g4g)wQVVA{1Z-N#i29dz-gAq-1V?yUh>=
zJz=*87&!XVw!*z32kL7%uOvac%5&^im2Rgz`3?Bigqo=;h54ddJj-nV0LQw1HJbMq
z9$(8DZ}vr3lH&6N7Qml&qTyq2&a_P8)-#^uRJQlY6E4eSW+wm&$G4H(e(@C#`_-?f
zixikiJ=|-7(=?kJM?nftA|$O4O~bV_QI=S3S%Z$9DXZcQDlxI{hp`optm^hRaRh>2
zFgH_JYjXB8&C|4jjDWX#f7;INqD{X;S?acXu=(5UD(rV!L`)y-Vn$wtl;<_8b|-S#
zG9)5q&erLgfu{_|Ah)(D)9dYUc|Z_!8#+~X)pLeIK^}`qN?n4({?Q(G`AnzTO*e3E
zHn7jNM*6Ih5A}?r>55qOQwwfw(qp!2xtOe8v$YdWGZP#z<c<Y(n>?uYs^h;E$Db3*
zs5aX#{q;niD!G{%OiPS*YKdKxjVsM|7%mzZvE~lvwPMXPPa{bzn~CpL#mc)M^kf9}
z#!X0OiX{2t>*%?vim;gsvqu|Xe8<>kgq;XDiSz#LIj-QwVh#`cl#PD)`AHu8YWbNY
z$t=g^jtLLdaZgBZ82<pN$JEtRsa@mbcKjBFy}damQaf{jO6&`U)_yY)=hC_z9tk40
z0&T1K*Bve8_W(?P2NZ_t^B+9NKAvY4ElG_YiaeFi?~osJSsJr9mF3$?yN^?xVz}dR
zanXtq?;)jG7=y}#{_!-F818FFrp$Kvx2qqp>r)#zqv?7NsV1;XG3wx-U}-nMKfEL8
zhObgiiBiCD_oN?c8Y?$oe%m5}+PUD;9(>n7@Cs4pu+Nz{(`5j3-gcQ7`|fe=O>507
zE0EsVu5WCM!IEFboGsmsUw`7@Qn#4SqCINCSLKfYdJ2F1B$ko%LO&Yh{>Qn#=^o}<
zPqJ<2VjrxPHXY8QPZOhp1R#%dR4z4WB?OpupIp`mMBW$6kB<4xO(_b!fS?No`8RP$
zbphx<I-*Q$aNAGeNc$9RL&y8ILM|Ol9)4VVQx2xN;r{?irU*Rczwg<njeumdpM-P)
zWBXAzeB1v31SXYrO^jMEH$9J*MOR!F`AmcU1B!W8J!En3O`t3tX6)zpmksq8rhjVP
zfN+wMf7+_dK5kw{{AqwF;|_kUQ_6>Ochs+#oa7Jp>OZz!9(DuulB0BpeeuWp^(sfF
z7|D}3$3HpZosh1`{?&Bn9$a7#St;IS$?9Ss@H&A10A%j|B0aKmOSZtc^6kdo_LR^B
ztY%@Bni1>{Y7%A-#L13;1*uixi2Shy{{V6_X<FbDln<Z!<V6Cx7!T2<`Ms8t%Q@oW
zU;E~!4>KS6Xn6kZFZy0SSmZxk3I<h@$tF0GX-NM7cBZq^?G{g)%x*u5o}%!cVtjwS
zR;?}OX8Di-?)=gi$#lzBQ}Vb2p$$~Uq(I;+kUd_s?k(Mr?J9k@R%=?ae*|OeB^MCB
zL~Hk=1bekNYy%r@<NpA@sa6oJ&yb_nbtpFA<joFf0l?dn^TiM2Pf-E;vBo}vqw_74
zAM}X9{{VJ_JR=|JE06anfj;<94WR+=^3W%ZRPJW_2<orftyyvQhx+++hVI*^n<+o;
z&;`MAzryZ6;1r)|&sUKC6--^*D9`WP@WnIj7WpNF-<>fRjHd+daw!boFYzC#s-pJP
zt`^c(_bpMi(&r0dxkpU376RhP$0Yv%=v1u4{{RaA0N+(d&p=1|1Yn;-%`e)Y7#4sZ
zYAgk|m;IIe={(<;7*Hy&+HOzXwjYX8t<CTs>XdyFiv`O|D|RW5_i9y@)b{@XzG{%T
zzG5(g@LG47sUB44+Zd%`n-LOMCBI6FcPiUP?`$nWY4+vjM;_qQB$EBqpxC|lZsw50
zkW0_{!}S!!M<;}1Q27_c9rNedwIGUq(*f_gorKFuvlH`1--}WoG~@(d#p=6S76*OK
zG1*>_Sugzd2i%<12${q18BibhsWz_M0TBANMz#?jzc4<+m-{-`Co=Q?<rV@=DEYU>
z1s-I5=8RK*#Q?z)NuT#A!q(Vz^AFW&0Mk4pkF=@w3rqHt<2M8kWT^$6w_h#W=}Y87
zukyzK0G$9u=dbX|C;jtIS-nf2(xed~IS6y^)TS=`5RZ4DE<*P)ul%!+{xrin72*~@
zQ&xPmAM(l{`|gdg{{V6TeVa6Zq$L^op#*(tOwp6YvY*DS?vEdO5$T#z7yf!gKj1V0
zOw8oqLMnJKCyn@tSN;Q<vaX0eS(lGRq-j)q-h7{eQYe~hshSaphJW3v4%dg~*c5v0
zt-E=lczE**da%V;oI7U)$I_4)MBcE#b_3IGFO_~<@4ZS{_jPm4JO^Cm9OvGch<vM@
z4b1-liK#?Wh41*aFe{Uh9)7J)5y{>p1J{2v#2!?exySwYO>1cn@hBhf(}ZPD5yzkR
zsoQWfvOJmqu56s=biYxWQDuR|sgI>u%M9>>k-Xdwo-ysVfFS!Sj*<_;fn^_gSp62K
z266uYEmQDHa1tE;`IqP@0tL2(Kjox^{{Xp8@}lPrAwKC-gmK53{PWU{jh<zafFl<1
zt7mKHxuh`fZ0vG9YGDHvCwqQ$G)j2Of8SJqgv7WzVSM|wFOa21U<CgFv}xug<2nBT
zzNjdkpREHSXk-Nb<|QBR(#FjL9jh4k%}Npy4r5=fISslJ%@`-w6o+xk7?C$NK59md
zar?6vAMVnPLfo-kq~nejrCm<Y5A`Jf0Kg3bD`9`<qJ!+T0=?xK_FA2_7$uMdMjqZ>
zA(2SP{!{^3rNRFITOl6HQhCZp5=u|HRGGm0q#ADiIaBzWU_s_9H~h9E=}+9JpDJ&u
zsZ56-bYuPMQ7<2LGCKU!fQKWz5`HaBU~z@EBj0sQZqyukQU3tnblEPz{s@P@>I7AI
zosTj8W|{VO&U~2v06LkkR33@>(hIcy@(O4KSQ$t9n8)K%?I34z4{TEf>L21Cg3}t|
zbJf4^gG>pEmLKa-dt#V3f%3>cp=vKVN&f(roPV%s!f+4Wm)L|f0PwRM=5`-JLq_M1
zG0(j*r)|6}zm+siGk?n&54{0$PqUox(onY9VV02ol$)gkm|rK<(?d-E0P@Fgv1&s#
zEd)ytLWmT9c+;*dESu+N!jD5(%>=CZ5urVCyS-nG&op?MVq6ShHgia16US*Aff|PT
znu`ceD73O#$c|6$)q7;rKuMqVk&pNdFtIX-&pQ-*)0Q~@0KC6URctu_0G5mY0DRNc
zn;G*n^b`o3d264TepG~moP9p+L<^J5t)F2_wTJ`lGLNFu0%0Ry4crewO)|<CA3xHV
zV|;UQG5P^a5a$^)Hyw>35-F8{`^JDIEzW;BXW7@L*?;e&O*Y`1glv1g10}%(0zX<t
z&!Xe~>Wsjnq-uVzK!zaS>f_JWm<IL#0A!!70_GvcVh7yRqTbkY(Lwps7~3ZSU;=?y
zVZ4ZP&lnWdy@`k4TzY{{GQo`bkmK5;Gu!j~)cgf79xkKY2bgjG<v868e3CI9%TT@5
zxXvdh*J@HN-MK$2P5%IXjUj=$ZP{NpKkm`?nVT6i5l;JbK>h26{{Xf|gLN6{6y#_7
zw3rqV-G|(e{Y^Gl-)?-iC)ueYy~gZW+%O%_6*t;sm+sl^{{VTppk;ICAi=j^uKI+d
zmgW@t7OSq8Qa8(KkOy7$QdPZ1EA})v?q%yu2xtyZFv2nD)gp;`Ke}JTG{GI|T!<l7
z_mYzufEd|r{{Vee3dG8?<340#{sBl9Z~5;T_7T%JUHZe*)1@<I_ul(VL+G5)1NP0k
zKWGE~0ZFm)F>^QIf{_yJf#zNUJ(8Ybx-F4-RDX0W0u)=xoc*G6LqVJk(v#fgm|(g*
zeX>k@3Td*H{`KVjJ5U7QW?nduf&SGs?NomQ5$^QG(^RGm_e6E;O&UZ%{{YK(`n3Q%
z$x+Bf&%4r<PI9qv*tIkJE)0NC{{R-GT{_uLe4yX&H2_XlA<-@W06Id*z2O+7TN`Yj
z+(pm0rE6PU1=|7+`7|+&`&3KTXhHf@(((|$HPnAaT0sqrXC_Nw=rcz91!X>TG=Otz
zaUy(|5)Yypo;_Y1bLYr?c6F-XYtxlW8<?^^Dg&u$`S~swpJX(wGhBwb!y-N!t4xn<
zFk@!=8m|_y5}%Su*m?vtdM#QR{#CS;<GD_0458+d2HQ#BJ@ZIpl>Y$BjDQbQS8jaW
zyVeP@{ne^+O)CEY%bmgYr*RKaI}et@LH_`0=^88UqSoC<yVPrOF<<!em>+T|Y3_gL
z$0PlxrUaP1T#}Zf@t~#Ce;u$s>rt%tWc;>q0q*qVlJsYER?GhY0?h(sqC2Hr8Lh!S
ziB1t*1M^&f2lrN>^RNE^gj$2`N@dia?@t2z1kC~@5zK$(`N#XILc;9-06p~Ndo4A5
z@IGtE`SgyM!f?bb^Ks~u0XepfpZ#sg2e&mLvy1zeCy(zDRg}yD&D`vN-N*E%?0FcU
zKIy*<Pz8^$LR%&oPqA}SeU{x92E+4egj*5;DRfW!*r%*asy}l#;?xX2&uR%_Wf%Mj
zseGu9TU%^<oYZb`f7BK}=9nWaaxI}A<*5TLW+WV>BRvH~-cu%b#-q>*jG-9BaIev+
zrSYC&28#g4+TA5kr`nMONhkb#zfQ|f-k8Cj5%^S2$%D2`{RI{pW~>^F3c+2ZWzQck
zTGkRo_$MKAT$FC$<j*DtqV%f~T`EXR$vgXPBB8{qo95wFu^KTRwBNK6apg8oa%!cm
z>=MhcMJPQo-78)zc#M8y$$~v<IbT8Z6X}g?t^4b5Gqr9c)*CREzF6!>70o2BBs*J!
z(yXn+HaAFcJu2eb+-(|ncM%0XOB|1Cq$QUi?<ea`1AaD=X~_e*z$Ua1{{XZ$dCdmr
zI0b(yW7$d9&OG`GMS!nY27n}46t+tK6>29(`|c1`28GD^TQvb&g~7lkm4e382pzDJ
z{*?@nMt~71W9f>c9mL7^q8Rn5(sj?znm{?7k$M5|P&s)QjE{3uyCDOQ&Y@=GYJ>Pw
zxDlU~al0m(p`7(4sM#SODih6540kA)7U6T<+pRRjS9LqGdB<vuEL*oS6IVXXcKzdD
z_i0wavJA&@^c2KH43LKTqrjz_*52g&lWZfkT5B{T?tm(*St^z*!S$lzv70mx3lJwB
z+*1QE=-K+!*-*#9UBvgQ#RDI6+Nnq^F4s6YA4*PhOk{L9^`sB<t3+6vBpwADuzl%(
z=e;=W&U4LBhY3!39qB~8^yZO54yTHjFt6QiXaRw<%_)2yyiyXK6pDzhdQc)=$DyD}
zgW9Wz+_5=0rSgjOG=^H<00ND}s5Jt4YNvMQBhsWZCuq)n=>aI`jQi6;Dmfyn$vY8^
zxD?bok2F{dLPQ--eQ89=kM(0dwOcAjemyBNae>FZ76RX$CO%va)a}w1#{U4o)f1oZ
z9x12HApGYP>=!hF3)R7?6oXj_<^!D7q-SBz0+7qAfsi?+IrKG1PVqKZ29@sSf4%tu
zNDFz*2N|sKan1-MKGg5D5yIy*0iYC6!-}LX%8#3hkX?ekvp|VT{xlGA(xEev)}#`G
zD7X#-+Ksu-6yH1!dsABJ0Lc7lTw|MP7$TZBGv^(uBXpawf^$eGCzW2F)LaV&D2U{9
zP_?b7z`}xhXRR!2$Ifcf+{GGVD>MzzyYoO4yr>YIADB?s+rpBxxFr42%}StWy)YtB
zLCyfH5jNU3j<}`#DOh9LY_<k{=>`eG2c<V5dvi;_JW*f(tBmK4!j!200QJ%XgW8?B
zPoVnH7b#=r%?BfjLF=B>xyM?fL{>Zx)}X#$GS!LfcV?$-9MfeRpk?IzrlxA~WkX3L
zF4?yr8P63Uk1y916{q^#5#REy4=;0$I@gf&XRfv%Zyp6&*@2pLapYjr*?wP2hBC7O
z=}@ow?0%JHh8C+1W*)Vr7w@AwzY8TJng&HU40NP5>>gX(G3$z2K)D?a8*%GEfDF>@
zz|U$k&lFK%2sspotu8-0Qn{c+W3DsBJ#(B=1m~?k1J;3tayjCdS0~b>$7*gdKoxHP
z0OQ(EOji|jxsmcZ*J*l3lKK2Aj<^|a*&J6MBXh40u|<<B(x4z_tv?v|s`7F%=~yG7
zm89%5S9FVEKA?e@D!kPfBX(<d!qEdeOO4I<MRZeFW)&Td;sLfaAMEt0K-}GhK#rwX
zoO@FFxas=WQOR;}IL>iMNzc-&85o|lp@|&R6D)7qI`p7UIvTFr{VBM{dr%_Lm<kNS
zs^s&NNs>BIVU|qU`cq2|xu^*wd(>^mQ$>KZWCx6zVV4*=<KDCHuKvw#ThMb{?4BV&
z_}!nzv#C>%+Lb<YuQw<UFHaXSw?`Gm4Qe?#G^bQf&yU8r-XZonKCct7l4L=<ct4G2
zO?*K-)*M&p?Zk)itBT6&^AK}b&k-hR8ZkrWyWRXp6;-FnIW*~nA%0fL9`%`az-OMG
zmCogJV(UnZc_6K3OrT_g^3@q`oq7@lQI_@hbDaBCD7Gf-PdwPqwPsB*>6{9YoZJwq
zF-kP>NADZ{0xNjN#uAyH%t`e$(2m^!ty2UjJ-z7^#xT4Z)XMiW*4jcwMI%JRjFVc*
z6CCyQHCkp>I0Kp!xS2@-R>>KwDKd_uiiMt=yl1Ulh-{IsHs|?NGHMdH3566G#GM5@
z><&(LHagQ$Cz+I<SCO*pSo+d~>sS8(vL<ee)Mq)V6GNPkNx<X1T0&*t3&FbSrYdl}
zeKB3?XYBs~g>(8Xx>>>#Z}AdyTJkY5kP8o`Ykdef&1OcIP;l5Rxg2z??)~d(`$)W+
zc9Iyu+)EtxH46B8{gje}KGlmY8Hxsel@#bPpGw<b4quFXqaR93j}KkL36Zgne_BZm
zvz<IsO-{p%Z6NwoSgi;nAev32)T7>?#wiNrU<mf7j(b$34@zkO&=(nwDKS!Gj8YNL
zN&t+3is-y6WMsH&h94*#6IgJ-_g4vT7|XfG73x|xik6mWgef>5g)kg3fzLE|#cHjT
zbn$5r?VS44xES~+wIL7KXWF*JF^}OC?=CQY;LS1E!7BT(7e7iFBnOl=y|q;E02DGQ
z8QVxlILjdD398cxRSRI?cdneqnfr@W^#B^#x*uu=j7v-9SJ^7%eNSq?HG!1`mfKrA
z;<9Cj4V+ZAmsd8&Xm69SHIp<hM{RbDKXSo+O>5i4M0t~H;8Zc)Pcnv52&qytI*}ka
z@0x}(8=L5D-(YN?L0OXOw-fOiZ3Or9tvib-hboz@`-svg_*^wB46JS>3^x!>Y+Km}
zg&TGWtQ1nx0(s`QW4=hC8;@_wwWf%XY+9ht6rv<vPw7;Ss~!#sC)$!b$DMvqzz)nS
zQ!?a{LdroI6~gOY7L})IZ4?D#n(SP-PEIr0tC<^sO+5hfx%3O@W8brQ{{UyLR9!yt
zjsz?Yam{*T9MyNX4BbUfx;q>+8XeS`4mOcnx_*rXlZKE7VcxfX%!-6$;B!cA(2RE!
zT?K{-S7=;d4@wB#%JiwCw_oC^NRBo3rF1(LgdmW1=9zIHmN#~*sU%JJYAd1UM}^Hx
zW3gHZS-wt9Y}qc<-2VV5@0!DitPQ=+)$f|6f2~V<D%je6(r`vP)H0H}=$Z>1UgXCC
z+Y)iSkG=G+>eEh!6btvU$0oS{01Lu2`#7Q<hJLlz+ud~Mn#r@a6w*XKBGKTv(dNQ@
z%BL0ceyMCNuH=Y<3b7eI>*^_F^R3z<IAB4qocv*C*80`J?Z1M4wY>>yV~B^ka^T?A
zxDI*gRSD#b^r>QQ)!P%#k~CF@ed^3iK)^qpP>u1|rA!|Ukbf%G88m2y81>CRcn7Uj
zjq);0NuNXbRS{y`a^!rt#ZIJ=ilGzYPC8Y@Y#wTnEehEOlTk~OeQLoWu~4}EYK3E-
z*5U}t$GFX7eQT%H<1cDR0E|~M6b4oG^{z_l%;}}Ep%5&J4Nb7_9+Z~L)32pkMfCk^
zjkBV~%VJljEPGc~V0S3`S1kwtk6&8pG^sE)9y7&UNoJboa`DY+Mm|tF)^Hec*0e#w
ziq#TITjk=qojwirQ84I5az0?_E4T2x(cJ0F8D%dR#U=!AZpeBXk8UfcHnFnct!3R<
zY$T|p1q9)}s?<lCt+1<Lf-zG<er{+2@^C6()e3Z_EmAT~)CT7@5Ndco{<;8^A9|Hf
z6<tp}RLFVFASYADr7IkPO;TxFrfCe|eksYfL_x?WxUUUqls6xAde^pmSjp02QOQ5y
zUq6{R1a$SOV@8;hCY+|K+cxO`0Hs*~15!}_f}9RO^rmhEQWJrW4Im^TU#Q1wh2zIT
z#Ylj=3Yf={j?@93%jr$paat`3j@hV8IXI_qDBy;r01tY!@p7OFZ<UeKs6}#f_|%ZD
z;gT~-ur_%aKDA;bD;@~ND~zt{qyGS{OxwDwI*@6K05n_&#?Km#wRYc7FqQd_6<o3f
z!5Kca5gFuXGy&6E>ifV~HKiTwGM%{kn&N>e(DPOyzAE2&v(lIyJ?4pFe!L=v>+<nj
z)#r!rY$Ybxv!`6=n$Wh^3b!q{+}A`dVV=!fAiwgUM?0omYcRIfg^Xj=*8F!<5r_Ft
zrDi?p-c%ESaZeJq-1^k9nm=kFoz3}Ee%1;3Uy98x?A+5zu|4SwyDjS%BPZ~vp7F}m
z8w!l~pp11ChB01AGq~_-LWgZCg&l=SzBC^^h^O4r0uvi4=~Biy`?Z&O;vG8B98Ko1
z{uHVw#9EE-%VA+52Y}&w(?E1ns;Jz|h&}kK6Kb}0?i0>ekoFZ$)5Ch^uKB-tB41AR
zxoPm~6kUZwQ*9R?Al;oZ5Tpd8n+;G>LKqDy-Q6K2Aw9Zb<VH%DC?$<_NOwp}H}7}9
z|6q5|z2`aS{AvYjmE{LK9-~nbO^)!raS;CDp{C#mk<6F%hq%w8S64iDg$wM9N{Shc
z-<Rr8nsG?gC&&N9WMUjLHsPm;L0eAhd9>>c6?0hg*RG%*&TF8MXV8r3TeCBF#&h#Z
zvXv@m&M(t6KfA?Km&kgiBVZWOckywaE#afSLJxh)z-Bb#?9AdWX>$`7r-R4i54qso
z8l-@$zumD^>l^aPs2!!Kv6Tx-O`fBa;7IItuAvv`q9%D4!4^&o$pdARma^A^3O9-}
z*ptQbWFn-v4;*NPhZs-QXDIGl+Wr^062F{Dy@`nHW}UBogO1+$dSk@vRZ)}XPl-c4
zrX2%>d_HmVA7~?tc{-ce4-~ILGC1_*5La<Ptj>xC`w$6niBe6Qh!Iq!jAA~Z@2$oS
z71!8;`Iso_?&Cf$W@C8tzfNrd!zFMl1o9>O`31(4;TP%FlBc<*ujvGelQ9LP+4iUZ
zfnJLnY8)P9ik~l@3Y}L*A#m}IE=L4DI1eShS18`h@hWkRb)@rT&CEbpl~3t^R9H+q
zN`IWKaQuc%YgTqqs!-w7bDSj*AgGE%HM*l2(dxDW#3_g^r<P=n{h=vUFC$W)*ABpZ
z!*g}|)Gh;^H{@oqBNSDOs*$;iZudCiG#il2UTNw3Y3YC;HP$rbW=D+y7chp^eDhQ;
zR(y?1VI+M&qwL}Dv%_T`r%_rd>(3%O!iwrx=~Wfh8>BbdH_ZLAJ-kdngR9tIa8Y@$
zMoOk*i{z%BEpgN}DRz{T#-A}SZOd~kV*le?c4hCnw1A7wp@V}Zp*`?I-K|3fNVaZx
z?)Qu4&SEO40qL;L{~rh>Y+Sswx8>pFhJLS2@UL2LqxDyihvE>Cv==OJ%0rLa;?6|V
zL?T2;ztc6^dx2-hy@lL3^utGpwjjrUActt3tbh)wB1m@cE23RZ)_*F>+(is%+OK!g
z_+z}D&8oVI-~UF0?i8yj7djBLR=4h?a~!`a`CazMKES73!#seN*Qw>ouIVnv4ZI>`
zzNblFp(XgE`My+5i<OBiISR>o)rG368U(gOj?DfbyEfzQk+Xi+evKtM^X2aWb52Hi
zU${)&PNP3`oSyY|<Vumn-1qb7m}hRiSNk~*J>JM0;a%bR23=F-#A$Ud>m>+@RiC@0
zbkZOd?4Bt6&bb+)U%XV)*#PWRom62ToN)jawh#3I4?D$BOT9e9q?1=V>v$A{%3I6M
zYhk*@kF|pU%ll-fm}DunOQdLTgde2;p>Bd2Qc~_2K_==;n&UV9;#GqC?jmuqhp#u2
z`B4TCoyI{bi8D6jSlIiHa#6m=RROdYVsP(-<!wi9{+L36<OGs5!Oa#y-=W>X!bBxr
z(t3Y6I~Mfbnk-R5h7AhmjjDR5f;wwe?caGh-#WQI?zyTA#_tsTNRvHZYV&7+$<M+1
zcUyF9Dvy5D74pd*j$}DBr6r<0!5we1ylRZI-i7k2uR+&5F;pVkvXuH~_Q|+AJDVHx
z=`BH}!9m{}aG(wOwDd(Re>{a&<%Z8f68Dld1el)wGPZFdHyK!3#;(nf&)D__h;#=3
z1AViK$m0#C$DU+Sw`C1{R{w;nwsN!mE&Fdu50j-8je!P|rHtAI%%udyi&c35fa?D7
zQ<)^i0TLDW{*`=Q1I$Q()Xoe!#FV0bTEkx6udCcTw?iH9U@chRU+K<Yr-h`2O2D(k
zI!?CH&fEAp1)r96s9@j@M;qV?m}`TM4T)!iS<gxMhZbW!Z_5gmI`1cT=U_>bmh|3>
zaMhP!OT-Nd4n6FZF@}%ICQULRt^`%>!<K&yj}<FaN;kB2wYm2H%SV>{D2Z^g=nn*q
zFtxH04T%Essfy?b`&PX)qc8qwhM4B~=dA|^Iu`NR$xns>-s1wHD@q!q>X4S=^9)Wj
zhDUuJRC5zUJAgTbY~-JD1BUgCod|D~DbDlLL^^O~3fAXy%#O!LRMpP}@aZliRKmvy
zShDfDtOeD}2S+OXbz^SEST40kEd}cHAIz5MHe22Dm;+z}4$5gaQgN*Tr|hbE`Fi7l
zte9FL^?nPi1E(|@xc3R~f54!?&rAra`20kH25QOJB_HW8_MqjB`VaKUL-9WJfy=Yy
zyVR`@<B`hLGGjLOtO}^|%iqxZ#n4L%<g2tJm!LKMGO2s`2^-)HcsqsoDI^p0Q-)B9
z*UcTn{IQku$lT=!!N%=BtVTv~?#>v%B`#9``42uIFTsjIvp!7bIwfqm8=MWnk3Ckx
z9^a|xXLy&R!F;vYtLjyAYY9MdB?U`K_@9So`2^>5BBFHKy>B%d^@3kGy+oSt>n1La
zY+5Y3PiG~@ym(dHJIryR-^&-70>8+H->+$9^xJGf7Rv>Sa@cn+#>vsK(Kp<0(3Ap4
ziwLH`H<WVTg}Y`!s~%rRO%ZIX&OaJ;Nve7B|JL(MH=E^DI}IZ0>Vtk<k|yf7Oe}tp
zrWeW!l%N6JnSyf`hh#0L%<*Hlv+@()TAb9!c;9oYslG;?MFSASJQs#%a*OKj+)FC7
z#P6cRR~DZ>>&z9zWl+T#07#d;n=3-XENH2Kmu**+n&z^X3P1g|c?&2Yi==2lYRaT;
z#!~Jb_a~jQD&f|uq6O0=82rcd?kVOkQ7VU^H5pA)GNZo|q2G3=l^6#&Ehk=6)3hZ#
z@<*57UEX3?Fk=@aWq9VQg)AiQP7kW`LN@xYc;ChaOQcm^MI6Qo{mNV1|F!gKX>*js
z@ybt@arJh0tb|Q~xL#d>&ZIJct~h>Hd-UK3#vZJ6;m3FKLoS`DZR0ZRe`T}?R)X74
z4Xu=P^M!dI`X8``%N>w9OP|29Iypl`qDmV1`SParxcigf8$zX~+9RnZNlQDmI{w`t
z3Y4_?!(Q-&J&~Wd5OS6TI>Ue0NKcG<l2+rwc7E{7Fm{Q?96NTu^plB!C*ib*?;%;A
zwygK3^Na%~NjT8u<3Pi**lY8}FBpO<;<E@;im;e3ig|OF1!bZznAULm*Hw(;-C7|r
z@4w2qw|<@A5CDl;0~`ezRkmHs+M_zePOS-k^ID_6N>B%YcD@m$x<4a5kr~GFdZJEv
zqVOH{eO#xcF>gLrvh8&LEfB~fgLNhCO<ab;INJr}x#&m|@1Qauv#<P`PeHNmJ!Xu1
z+TP%$u#-{|3r_>0%DQ+o36#(+=`wwv=Ce7BIaun=?NCA*PX?9M6fE0M3_av(Q}VXn
z0*8w!hhF#pp^%3ZTC{cb<6oes`(m7!|81mKmmM(U|J(4zdh<HzF5s80(z&3E)F2;p
zzGUTS(%|d3S-PuvGIuNEbh!Y;D&u~f>2XK#<fTw>!u;d9(BW%IGOd-8Jrqkh`K1tn
zMkf5t?Nl@ru<LIxE3W?69r}c+MDZVJj7IT+C>XrGd7?-kV3-A?9eNA-Dzwf>Ey)c2
z$EA@9`VXWF&?wPbWdE4tQ;ZRUw>6aAXEyuq8zN*@&t^1g3_<UQ;Xfp<DAr#jUn8Dw
zipdlz;KG1U7N?RkY2aZp_y&`Sm3V*hQDiEVfZ<hE=+V$45~>+3>p}cBJvuR6OOb}2
z6&y$Q;d`vF;=W;7)h{P-t4sS%l$EbGg4=aeQ1)%NwVTHLpHn}3H9(sKXUwkG4po9~
zXCVMpn}8L@wPtKkqiWKIamy1<xR^1O)UEly^2jsBG7`viHETYD?;FT6M-A0AfH-vo
z0}wOXd0?t0of-d*;th|I!I#)k05KtbokR0@^+5IIP?6{{fQusamxb!GA0~=B_s5=_
z<WW8@{crc{;$9{)Z(Bk><@mbaJwf&A?_*sEfC5j-ucdcf3)xB4?3a}A`zbejxJ(A%
zh(FaxNP#ju$$!bC9OA%#!eIO#s9ELAT+%G;@nd;aJ}a2%_2+u6Y!A(Id9d_f^v+}!
zdS)P^87Z`nvdJRpZ{ot#(HnXL#747&eN7qe#xWz(ZGqBDbJ;!7;c|-{x|Xyfk=aIu
z*si#7EM8@t{|S*HWaC--AS(3`rK_T_UmhXjxAl#ydErOpf1u*9ev^iZGH2(s<2U>0
zTC|*DA;W`-YKtA=288<FR#9G=;s?Dt34CHaY|`=|Ole(>(S*YIM5UlL9jcL@btfX}
zzh^jGZv=xnOVN6P>m?2232S<sWf{&Ub!Q!|7&WlL4u+|o$sFJSuws;wOrU<@rxGEG
zG4$7;v+RwOxgKidq=%=lGF@Dhf`dBu!lSMgsu0V>v+#y^S5_Inqw*t@{a-xbHCxQ0
zB!~yt5LDyTg?&AsSU07$7qtPq;bE#@5U_^-qu7qI-7pF0%*UorkYTe`gf10}x)MnZ
z0*UiE|4zWC|NaBXG*Zu-OIsuW3vL@U!#fakyCO)%`YP6PUQW4J@^Jjx7UxbY+eVVL
z!w@9v7iK-|+%rXYM38ybak`(e*d6#G$^Ar$Ir#O1zbNt@5G?1`^EsjPt`V4$J1a@a
zpQg0iUi1$;V1rkR`MJzV`ZU_KXkRGv^nG5-{z=`a$km|VWt`Vn9JeAM@&<?HvAkh~
zB5_BP*6G(|YM*sw68P4hF4mj|MdjA^dHcQOQ5mkKb1Mm?JL8;T4R~?$u?ROqeK!9V
z!ugm7f3%2SsBU~Y4m{|GU)w@lg8l@i^q?ylv5&TjUm9yguA4vAZRMCx2Ghn%?c5!e
zQAw9WgGBh}ZP2JVzW)0SB#E=nk0UMxte5xNpnDCE?%k)V{LJflYYbQU*cp^9RH&zC
z(=iSx@rKAvq#FDD2DH}&ph!@;1oPEfFUNtHn{=S3C+K&dr~9JNM&~F3Y&ZI-phBt&
zK~ZHL^G$X=k7*ET!;EKEe0&7>m&l(z96^7K04qlkuYf9`jV71*GNT}s{TW#OVtA55
z56t?%aUS?OU=hv+Eg2?sIZ!+CoX)2IZjN*LxXc-Xw>+O5B2|3<Qb`zJro(RyI6gJz
zwn(>n`AdA|tBj85bu4MB7!aY{3mnoVgd-};q>X#d=w0k1m#KtTO9otC#ivCMI%^!@
zrG=loFeo0&(P#-i(i(Pt&C3%5R-IOMDQE_Z*UrW2rcmQ@+?ugG?!V!udso$~kcT>8
z<FNdJ{Un{Qx&N{0V=o(PO6NiFjJgq&J5|ZxYnxSWXEEU#3;!b8)8i}p#JCYBs39F^
z=99fx1Qx`WQwn8C6Ty(TxEJYUWuEL!wmD(zt)%e~h7LDX;a+<9J&v)L^~Py$7SKrH
zMxuev%lR+RFojB4z>Y2K(&^yI5*?fVhtG@mpHtT6#qU)T_sKFS76{y&c^4AR!qp9p
zif+&KaGsreGD8N{&_$pJ)~rEO5}@iWxsmRr)-kUa3G+q-q>gNg6*IkImwLb$&}mCx
z2i?y71^$?VrfvH#ysK_^xlBIg?YT9PMum1S47zXq@G;pAeCsK`mpcvWvMQpfZv<>T
z-4@m?-Z*r;Q8%S)!fXh-p5ed?ydVKItsv%Dc6MNqoGvupN%}SBpJ7UaIa5FAPFsUF
za4!ZfD?=oJHfegpL%RIT`Q|3sJD}|SW68#vlrQvf%J3LyHhE<3cwWSDTrzEff0`e+
zlr7W#0T}H1WFJ4E%c;y?sd!L(+p}4wDSndU)VI7fn_H?7oy>rVEn@tit3{i8Of(a(
z@r|<&mjvs@o4oma88eq3oeKU``EoblRyd%C-*7@$rN9kwGhHBqId_fxWRY9ovr&ei
z4w-ZQ>q1J>cv!@}1jh07GeqLnum8)UNi9Ej<qU)RT^e>0<AWy0%_r=><96OB01qpk
z2D{E<zMue|ZGunl0K!<C>MFZ^CX~ym8*(uba)Cl0>fq^T41O;lpG17?$TKWDnH}S8
zUdx-4JYGxD$KB89(eXv=$VDvA{pLOMs`bbAxAPaP@0$1o9B{_2vl6%~{Zv<ON*6fs
zgDSFFP(s0oA=S@Kr1AfO_)(aji7$*?0u~DOBN-M4mb~rkE0W=LY(Wclpo~nhdBXDO
zxRPAO0W;bQL+eqZxBR=0Pn@oT?)Tx0;bp;vMqgTOH))URv#Oa}yv*1(k^EY1Q1L7f
zcHt!V7C3E(NjjW45oZUOK$R0U?pdlnHh(`;0FQWGmX8Q}+*>n7b5;o;ZhaDg%UcMo
z&5=J#KvU`3iBl&}bS*;q0PQ9G2G!biNHWtRjANo!=IF{SeL7o`?*4wnC5iAi=vdH@
zWS^P(M8uv#<vfJNNQvUgF7H)@1B;Bd$6)26O|fIl<3W5wq2tQtLR|@AgOD|YcX6~q
zYP*-JU#JdUOsW2qC|7Z;=#-=U%U{F6Xd6kKGaWJFWzkz#73v#IWMUMjyx2l*SjUab
zq(_%_pz_!6uf_Is9go``tm6S_eef@o%Z~|mZBs)%GyTnd1WT!{Ls*A(RQA&-N=IS$
zqMVe;^AJD)oi9s>YGWN3u1m9AP$f)s=Q(H9H+aEI;^2My(_VEp?!ZQ_xADGDKE+rT
zNn4hwy5%gtSZdUj#5QZI_L%C$iAjR0tV_PLw#t;|Ul{TV<opu~Ad=VPKN;vBF;bY%
z-m#^m{v)g_7d=wH(@$HJq04VcOfA&YdRudQH=ErF-Vxtz)Iq4OCVhQ&ryE^B#mb%U
zF>p~#`}z6L06Qp`f6$MxSkD3{G_VK;(Ts}T%fdrfUaZ~zM)6dN&zX>&3hrpv_(m4;
z_(nO3oQu+{<S!bKl#Qddyp)i7RT<C#c66HXN8iEXg@V>c+x5+lUSt7rR5Vj$wHL_9
z+6z?L=8J@!Y6|@~pGywaIYlsmaPIKZ=)5KWag10y;*T6?n2HT|dD6DSj2c3nZ<;Cc
zK?1mUT0;ItU-;Gf%Zf3&n0AFZJV6%I&oEC$n6}2LU%x8Y+}_AKXIewM)p`FdKfyIi
zHt#=BW-<S9`F|k8U^&6*=p52L6+9q?3yaH~AsHsf)gSh(`KKsLZGIwbKxkmV{Xms}
zGsmhDtKScD3AOsNg$|?U&bc!e+L{&vx0nQk8){)sri3~DTFDL5747_2YP<0_Bn_LA
z1*eUTOQ7|+?cB3_3zk;4ob(B=(gn;53ZC!HViahii_E488Z9XN6pRNh$}fEG@f;kL
z(C^aa3I+ldlwBZLSTxa+cdr&-@K5CjI~M%XTMMY_go%(r@UAfZk|ND;^R_k}ZEfx?
z(xGJxuacuCrib_=<}(w3g9BTY<|GQ>jC}*BcBxV5!M01TZ=P9%FM22zjM&MDI+l|&
z85PQI&E}TU=semFmRGUNB2UO3G&vbBl8}&8Gm2ZkKw-n}tJ<r|cU*&=8)f8C?WsIH
z59Y!;V2_v)o!4>XuyxDP_J%cAMHTE9KT~|UagP+-<DV{2C>6CZ#*{%kBAm-2+c7_p
zwFwvMV6hVH7uk()6&SsF7B7<&jAkQ`B3dgG@No)jCuV(5L!OmB{Ji&d8rppWA#GMz
zuzallA9gYNx#+#iBr-ng6K~4l0cG~+_3Bpx$N81fZsZ4xC3*=>(ssX#sf4v)@sheq
z^QlXlcY5~g*_2<^wXnqxj5W7h#D(|#=oGF<YFrB1^ge>!liI`M+WgJpiZ?@buM~_P
zIOX!!^z=A~wC4gidjrbd^q}hs+Wr$mo!_tx@$P{i<uWjWnTB|UpFopw9<53HaYi(Y
zVoJ40YHAxl_6*qH9KaZ*0QYldM0_g#NTMPK4c$oJ_=L#RV%9b)ij_U2*Yi6v!Fk<`
zmFxDtyVc-=P(_40zOv&e;80ImMeWcYcdmH$Z{Qv@SHUszuhDr)8jsv`?tXSaIpV5T
zcUwT(K6ldUwER=N_zQ7m8h@)Q{IXO<fJ8Sy*KM96enH88l_T%o*g<OWT_JCJ!aoWj
zCN`qL=-_rcqGPn>)H98+u>y0eO{Uio+eyf?pD<{%aeQ^XnVK_J5_^-ZO6NKKYlmL3
zwIWWEWFH&BAai7TgI6KF2j&82&o(lT8{8%&UkE$#5RyFpCWejJ6~^X#b94FwvmjAM
z87+M94Nh?lnQePJwGn%Uy{Sd7!$LFgJX{*IwL%|~x**&8))6T!3k~;rhhh!gF{}|v
z!4SjPQy);vVXj4BbGRyAeeOJ`g>>rq2sJQxpxE+A>lA5^RFe~$YBGq-00Jo2cyzZ{
z|8aEL$p^#E-~<>YQ?xL>tNNOI&7NQyeF|p9#Ga%vdFU!-U7HNxGTSF$)1r@}%A+vh
zpfoZ1#y_G0riifAa+B$$#>c63+`EI#i0`r`AK_pR-)IFCC9cH8_p}MfmS2x^HysnJ
zT4R-v$NliUDF4$;(`+V5AWTgO=V_1a_hfxHW4yIf@r-pQd*0yWCAavP*k0Zx$iaO?
z=p94NZUL&K$*&1YXZJ2tLy-7m!ywJ60FdXXXqQ=hSvnW0WZ~b50{teMHp6z|<fFOx
z*7nQmG()L7IZrm<%t!H^MaHsvw(`201m206Yct41*Mh^m6BI0|6Z#4duhvIxgfj!P
za?&CxcUx>doAx@N+gMatjl5oz5+{m+z=YV)*ul7B{281DC1qCNKb3=aH%0dzu)v(Q
zh+uaXI%Xd8=?|T(7-3OulhoeeQ)G!&X2JW40c3?o)4Y!r*j%X;E=gu0d|`b_ndsug
zDoJ`39q}A<*R<V?GIBY-F`IiK>}A{MWH!Nt22-!(@6C*jhEu<0YmwL)t>UA$ydKg;
zBG<fMCzENB=KAAlEZ&Xo*98^<YgZ@lFzj?I$*hSP{d1D#yT8zW4RqBCE}|oUJ=A)q
z-8bo5^4<j`EvQ>LMM@shGE;-{bR<*Z+gr7k5p21e2@dm%t{G6t^P&9sep%GTw&@iv
zKP!>Hj!24i66ci6NvC;qxX|Wue89ewB-tyhlV~42|0&%+*18*rZKe|?^G-PqNkJL;
zGPAd%{Hj<5u)YOdZS2$%D|wpdoCP6AS<j$$M{6)+i_ejE?-fg=)hVv>y~IYej0TTC
zM~>(DQZ}#u#H`v<w!&lGcVAp+WND0i*Jd*4uv7hxOOfhy&g~W3NCCO_${TAEvrVxz
zyzn3IYMxFmzd^2Ux05lm@fU?ZymXu&e6Yt=I#3KCj<#eaykSh;{V1G1)^RSo9<N-5
zgIbuc9PxZRaq`?%PcHB_*VBg~CdYrWtdFxgcgf?rnDJ|sUsN89mo;;vMDey(dpy`3
zhDEz|Sw+rVBu`JXfzs{w8;e%|m8d&@1b8Ip645Zs^nCUxfA^<E0}QxW7QRcYB@joo
z)7p{vCo8OJT$aC0_}Ird^XIw3s|20@K<~6olW5LQJ`|PO+->Rc{Y#w&OReof4ZFXO
zFT}hC9NPEP-=qn33jDOidgD53KW1$Zh(+I8wJh9<y-GRq`LFEW&Fo4hpIM1g=aZ)^
zxrBbUd+fz!6$U-U5*k!xIBr0`pK{!`Iu$LlAEZ0*d&tW2Gb2vb5!K<M%D3XugMPmj
z2b0XeWBM|dpYNQDj2bMY>NurSCQZBy1G<;He!AwhRFJ*-;qlE{<u$T>Onh0|@H^|Y
z<FfB(x&%&R+gov1bfJk)@n2UXM{g&^yH2jSk>&4Yw{;xoBy%)KegHuI(X@{rsJ)fN
z`J~P6ZA|xufu80-oyd-Az{y{;4Y4OfmAdZ(pDe8m6J?LCC*RytvfQRc2`j{My&0Os
z7=>^nZc^B<+w{iH!H9*QtDEHEQyc8fH+msbg$m0Db6Pew<F%5oyP3Yr%6qmU^OXiU
ztWQ6<@Lq6hsMuIrEy6N_FA7=dn_ZP~nY4bK1(Yx3M2A35R=~MR^izlu<|TLH^u3h~
zh%Rb9V=eS%%7A~=HhAZ~p4d*|tB5|X5Bshw8A_MvAq1uo$m7jw3h~=o8P(V<-e&}&
z?z7o($Vx62k>%l=Y2-7OKhOW7*R!p0c8P$yD@*DxG2nhB;vUH~o6@$iy4YFap%{o=
zUB%zxrIyL|=93v=a_>L@L*yNY9R8LrzHuKhd){0Xy|e;5Jfd&)Gpr>B%bLtOkI?Ry
z8?D?%>tdYBvhl+$`}p*yMLBK?1@}3;v<S~k3|bT~f0`J^Y^%b|WlR`EJ|&vJYjG0U
zJn3mPv+U_A%2GI4kDtr>r^)Le)9O>_)~wEG^EtTQKtr@(u~*G`J=<pfL*9p#_?bq`
z6ip`F9HM#D5VhE!pMR{KmuycM18Q}7Jf7>pm@lz$TGtKRD76{T`rBaB%$si3b5k|n
z-q-ybiEE)hIzq%N(+W4EFD{nqC%wd&EYGMD$FoJ*UFbYuV$zlQU}IT=<6eFGCYGr<
zSsOdQ2`*8lv4X6sWE0GMkZIxENh`KyZYG?+DhElBo{Qa?<yg1SqOG0^>GOV|%L)nI
z+4AGT(0-M}idu>ubrw6LAwRxBet9?skiykYn;PS3i6YWO`arfUPg=pJGL4xEv3Q8{
z>+=#c*K=-bA$`5q0qrJBZ-{~pO5WbZ_Uu}Gl9|yCd;azDTsfulevUCpJHfd5v4oQb
zmjoL3*7>;pcPVz=j1}#D;ivnJxYi?HX&;outF(>=Uj9Uv|3F`0f8Mw5H+y6J1(ll#
z=2&)|RBDDMPQmp`hNyYo`MQcNO#S|~Qiws|2KdhfXd6X0;mO|&Y7AIH+nS;Oq$W(4
z0w0JdNDscp|G3p;2m;6^)J}MdrAJ*GDd^yB{=_3jTYX-^QDF9hVJZHEP^BpgUis)P
z5zLh44{gU|*G0p;33&BJQp}qc(oGZ9ysjo(L~8d^O3kJXt-&_*>2q4fDo&rS<5l8=
zr!Cd_B76MtM)wW{tzMJ7p>U)SiHZ$4H;8llypxDXp5xIo$iskhhFlxMSmD<(#44^|
zj4=C0__DuzVjQrA4O)Vw``0P?pM5Q^#J=xF%4aH)V_do#vZ@V|ar`Mx$KL;f)L{=N
zzMU~S1A;p`Xl)6*Fm{rbf;!K2OsNb&EPPLFD&{B9*NIrt+vTgaVF1HhNpVW(mk?op
zCN2Af4XHzH&@g?_{c*B8##!;JyBQ4#D-9w00~Wd3y-IRVy7*N@26as9{`&y3%pK*a
zk;SKd9aj-WLf`&J!Cs|&#9E8Pe<1&8Gw^pa-|ra#6tMQs=bkQsEyzuq&UlU9J=&aL
z$Ow5*2O9@13$N>UW%_+r&08g-*1KWNL-r@*!_MoZFR?MdMPe>?QiDAb<){1U&1dRW
z^&M&4?Ln8l{AdSTy<=L1RlOZFI%|F}nSo1dgC?31{8kK^UCH3kc@>$JTm0G7P)1@~
ztLQZ+6L)=pYqT=PbBg`>TZ{id9SW8G9>2ErcOF>EhuEKJQA`(ma#e#)mhOiZ6>Qs0
zdB*GJ*%!s<><kI3G1>%4T$i8vjNiX7zy48uf1f3z^zr05HQ<hDxGPnR%~&6FSuPU6
z1hUD8!m><^0#Cbr4^twdA~UKv9i(H6r-(MM^Onq~vTV;_h31cQam-0<+n-Om=|BPx
zi9%9Ao}9Q`t@jG6*DNLEZ0e8+Kygvl?goh5mI9gZK&FX$h(_Z;(xA(-?hn6Wva9be
z;d>hAxCab#m&>wVPH$<iZ8^}wzDoW46`;TwA>E&Gj0*s-8K|^`(#PN6*oMD5sl+6U
z7*9_&=&$RFL$Sp9{Asy-g#Kb++rWYxnrsZbhjVMH%P1Wce6isrASo^d6q<rvY+~PU
zjbsw%4~^V^tXO{ilXMu-5hdmX0PmRaEB(FTQ${Rw;u}2J48v(d$bTT?y@DOtMCn1s
zee4S)Ew89M_t8<Je3+sBbGS101P8y`gCt=8T56FJuZoD7R<CPbdarzt$$_8V;|@PD
zU+(40<ev@{&|!93dzg3|5ZiD{gOP1-5`Yjw<JaXmj|5VPkSXzzF>w<F?&ox7J#U=O
z@@X!1LfXV{p+K0Xn2=b1E>(aw%+)FIveUUxvk`s`pWuum1^d}zKLB*~b0+bgDeI?J
zZD-f9;g?;E?H{2fIA8|jcW_IJLrKp(E$LJFU|Dy5=QN|_qh^49q+-#skJ)uaf#j)Z
z%>jy;S!T^^K)u!f7u{6QdgqH)z(R3M+HC<Y{6tuX6x&3g^&swHCZ{_p;=QX9)&Lp{
zE`89C84OyA&A~<nZ@*k*6AL=4b172l)P;)X3_6FTVrGT6ClD7PPeA`ppR})1^&cn2
z4^xWcI(q*vDI)2Tybc=VR6Sa-<v(ab>@YpC_fMt_i1j`BXQ6LO4dRUDzTQ@v8jz6c
z-_uHN^)W_V6;t9<W8Xkewn0Ka;(ZP3<HJko$MgZfqH}N67DU>_a_I*dN82{td@Pb7
zxEJ)i7qXr&$zLp6TQEYD6@1(Lv;l`q<2SHN_DLrT1-pbOZ{WyF4&Z;O?IEt4g3Qp0
zt+F#F!sM6y+x1$YR|C<Yn%cJiKn#HRMvebno)s5%;S}al%r#_s_3cL1iHmQ~SYBW7
zOa3;7#@~o9(Mgil+#P!Y<{ju|Wtrc5Huq<|=5jZ$?UeRfTk;7p<M4tfNf*;fkr6mu
zJz;mxFEPguEbati*M3M{VD-rDSOeWFQ5r=0_#HuGw2ktgHZYFuu=NPUA_EA;Sl~Zd
zS^kxy9ZrzRMkzrW!ny%q$$U?BtF`AZ^}H?K?$gJdM-mvx*~I4mku#ffa;ZRnJ3*X-
ztFo^Xn4$wqF4nCqk6kiU?~vF6*6mb@#;(7fq_jU-JTnjIg0%KZ8C2^iFFs+*;2ArC
z{lSLb8KJ?bQ#<SV_auc_R@X_1YyDu0*j=PWzWHz|?E>_q+&K#socQ!w^D*lMk)z|+
zSrza3b)Ei1hobp<CA3`SJ(@c@7p{&#rLr#^(~kobfhp&#n(*`i*q;(~x|gBQ({pM_
zitl&<@Uey5Fc;g0v0||LUa4p@{Rhfxxl>G*!M`ez;+_oZG%q_9FgiI$0XLFWffm|-
zpbwmvFC>~>Ju2)v+EZnoxZSlhbH+HtZI3m^wFiC&eOdoGMoGQ+-r8Xj@r$CvPVX6i
z_IW-&jq~lg=*A3ox?uAl_09$Mr{j0P{WuZsl$iJg*r>Whyq8VFIX%Ac<;CrxS_}H4
zVteo#$94aL(u={c3x2mJ->FGXBq9S{(_x#e`0@`g)XDFc6Y6n4-S3~MT*H@N1~9~`
z925^EJJ2E%;5F6E5cDmEaahTs|DnOyp9duAi}3`}hhOO?kGyx?84WthmANMRQ3=1{
z5&EF+H^LjV1S}EWznJ~E<ea@%PZ5qa>B?XFtXXw65cYp7WP&q^BV1@}F9wUGa^IlX
zrJav)Xe46au+Sz4ajAvqD^Z#QU#bi4Ux1JT9cLrHmws|z#m+YR@2BH1()v?6VkYq&
zf`&QZ4|u`s5!5^hHTjo>S|56aqKURQ0oJoh9h*q;y9>K4os9n2f;(-2#4M9U*ZaBt
zb}so_5SEF$cqg*XSkPq<uGY{OZ5HU85I~iM?wKTuSZ#u&oJfCpm{L9oFE6)}4bRw=
zPRsbb0}>ilteZ(1w&y+XnG&6`kql-~){)KhF+gI>+j{-Jq2D%_4|kgzWMFyn_{swQ
z4y4SPQXqQj0NA>ib#vSO5<rKmX-U`u7IF&C1PKg)YM-*oajo%toC)~c`y1Hzr-^!g
zYK&0O0x6D(HCWyXoJiqMw_eQ;hFODcl~e~8b|AT1Y1qF43yjKg?3yAxVx>MV`9uYs
zkAfEzXy9z{zu)s$h6KT)WXeD>n(p?3T?14N#BMA0brsxZ5AA)u`F4^sasiZZY3q8-
zHIdkFU<sAaAL#rKRGD+{SS*0nwaqH*G$Yl+)UBPDUC#2OS~(js9myy%+7IcOq|v}N
zK%?rkzNy!YyIp9iMYvreyOo(~f&+Q9AJTbx0E9F^3mwF(_|UdkJ+bHNrm+Ozjpdz<
z0Bwf%YIi!56S@40p#<O<hfK9Z_Ag-51_x50M#LX4K3(@JZvm2-gg}p9XS>(`?sH%y
z!SAM*O7C7`8aaz<Aqt~?9EjLd?>4eqLI6}CX$q}CozMFJaEqOc8{X~YH~)<+B`e^&
z%j|eo!j0$^?i#zN0R1ah5FOpRo9a&^UP?fCmp*f~czzAN9_3WkJ&3K`l~xuC&ZuO9
zFN=;hiVny9;XzM6o}o^6@_WO}A8#0(*u?MjbZZClSH!t(A0ytFo;}08ty+Ijw;g#V
zl~ykYU9eM&%-<M&$=DZ6Leq6?9tAkB_zphagj^xXFkGEUF2qs3?Vld%BEfbb>n!|$
z?XKN$R6rSdQ9?iw()X;kQ$H=Qnz_$VDzD3iR=T}lXSjYOb?zV5P}ckXpzVT7kdDjb
zi(><o(}!1Dzr6eCeDx7mb_%?^i`Q)BCoFljYKU)K6RH2ahS?ygxMchr2I|tKB)=iV
z$E+;imC_C$4XWy!tQw}okYOc_pQ49O8ZT7uh51<cM?#)rJ3?V$Zn5C{&VcLbFa6+O
z%)p^cN`K)H*BDg+#r;?dn(6HL$35xmPMSN8c3B1)p$nF38Jj7in<bl{Ckk3QP<rb~
zQM@@C8Aw~qTE70xjPa%{lPNCn5dWf7W$}3FBX~4}kf;^BcW^;*beed+n!C~+k+wv9
zSpzS5u{0l=?2>Us0m^fbNxaHz|MWIr8CwJ5erc%tqtS`V3aWIjN^X>Vz0LmAO2^B;
zc+@p$yZD5myt8N>d5jBbExA{Hb++Mt5jk;H8vGwf&rRb#4AuhD&nDnOnm%1|EYh7h
z6f<ULg}U`08;u6kYThO{uQaA;q4lm4_9mDgPj6=rIu2TsjKQ*Ec?L}6Q^NccIK7sE
zJ^{`hU>K5?FvyiO(MLQRp{P9=FW|b84?l`@X{z0PMD6MQXlv!Ullw%|DTbav@hshd
z!KnPnlb2PBw%}7fs<C9uGIpA6^h&_sN7%>tos1}%4C0%+IN!sD;wImACVw7Xk!z{I
zClcwhIC~c~9#3jWj4FPFj{fP@pRrQI$}^OIng0Ln;)QdHEmk-#x~GHY{{!){UBNC4
zpBd^!5@e!S@3kD_7MXXUak5uJ?C2Y7#Fk}&-5Fgit&Ev81;K#Tuv-$~qinT8es%~H
zl#`lQ#Fy#Vf3QMO3Pn#w;EE}9T<%oaZjJ}r7>C?M>`mSOK=sKDj_~WUezm3(r_5`i
z&dR2Q>QApAJ4LB4K2{S?ext`X?P>~xdr<_W&CB*Sw%jGk(6$wR+KBbXQ_Q6J{H^s)
z7dariL+^Ssz9Pd^Z&cl6yF_qvvMht{ST0Rf$(tVrzsQ77N@O2VwMtrkeL@$MZEM7b
zH?ReuPvnQ)Yl%SY0ZDQ&EbWrISPz>bCcv&J%HrXL5MqI9DUo$|kF+FzSko^4q?X50
zTw3h|+rH92Q;a`5J9P?0v{0_4jt5Y5vvZ|`V~2SLT$hrCIqOwI|08MbL0;phfwoPN
zXu-$bUJqrDDdbzI@l`2rmF1j1hxuPZY77Q>AM))+pho>&^eHx@5j>t@5$d|aXE$Hv
zQCsx;O*}`c_#<TsUBFrSHvBu{N{v0$JID9mw*YEk$neT+0+0}l+3_lr@H^te#qlcw
zz7+zjcG(NVH<aC*qQ`+TT8<qoRdtWHeXphfLNW;_beXnrO-{>;Ml?Bb9}pGYvOlt|
zm#td2^-HAKU#NVlA6wKq_}hSHa43p#znBDRK@tjMOMa6+>-+XI8?E(HT=ue8fro{K
z(AVW@P1A+Nh(p`yY%VX8J<Fxxt5nzBR9`kW>pQ>Ie^f>HB2;2n+x38Sl7(vGTaY_r
z&`Q~}cOhqQWiIWolEKiw=K=3v>B`~pgcVIe3;E9^UE^x1XW_!sPlj^D_l=ewEh0I#
zf0d7qG@iy{UAT|>H({=Y<;zS!hr=kjZYR!LH3qdCxX`H>!!ZtTZp1!NVqPP^k_T+c
zhH!)Is-N1OyCoW_s!T#tvlOJS=mLA5JMna0QG{#~!W-X8^EL7W*X;w+v$O>hX_2gA
zHr@Wamjhz~$m*C#wA<>Od#;%d2z@v@d-_4N-t$<;EjS=ke)P%5%~^K{5~;Fo8iP2@
zU6hY9Em4Lq5}VkyhUrjU^Nh_E?au5SQ10;YRQ-95>!(XPu*&mu(eHB)EQzKzt)|7<
z>_5<>pLn=wp8R^yttU86O5Uvk;N*%7Ur=mliw>56`(%|~ylkB+{8WJldPDg;1H8Zo
zv~HHR1hTFjy3U<wS{MSc`0p(5+Bti7p<Q-Bft+x8fr~4(KSh3seFGDDbFDVA7}RNJ
zc5eRYSqMhjM(oJ&U)@jxhe{g1C>2oE=3)1Yk4!PyHNLo3n0;X}e|p?~bOtLC6{nzH
z29)4nU|5WVA0`stMhpPU3Kbp}ZkfqG>@tSQ$3iM&{NXf61sK5f-~vEr^?WukA|}?Q
z$r8$&jWc+OqOroiZ<7Q@<Pdi?LX6<I-q!m#CCl^zA=Z)>o@^1p*6DoWnjpx<niH&O
zvAV2Rsix@LriFsPFyCU+>di%*;%o+*0nK)`8O;U7R0@VfQurmly8aMx8cl$UVe$DE
zevin_NwUm9QQAwUCKOA^qN6%5&xh2vNgdKD(Xna*TRTex)+LHBH$xDOMipK(rLNCM
zp!GeA>hm801eITqpOp(BR7T-24#0+C+I&Hb39pf;h~f-0dVLTwlZ`aA7_XOEN)BC`
z%^{C+aW}C1s>?cEt296K1w`>gA~YYok#TnT>AOZvIn-Hy(Uv}Y<(uILR#fUU;Qw$f
z^TH_1Xjv!ThJ6`1(kp68(^=96aqibJ-)_O;D-4(Mc1$H*-@1QqhI&<w-mh-yl=rBJ
zFCbJB$lhhfJR~|@vt>=Gojb{Y>dUJZIjX?DuHdv~c{nriw+a^QNp1^9VYHTg@&SK_
z_f@_l4+n&CGMWQhu9xNLtk$b={>Te96xDsihdJxX0@K=v2@O%zie^(gZj4;fTokMS
z)OM2>9<%CQR=i|&26l6Db&0K_S8V>RYCe&>O1GeSJ>n*u`)V@(*3TP~>a}yn$KT1=
zh~OUMd|V{nQ+<oQ8#8Rxd2Cl4$f)?NWU1(JgV1npzq5_NU%SK8JyDhWefHa=mqRO#
zeG(gmRFf=0{iA@@(s-hlJlgFgrSW|E<FDB=vIz_$<M_A3@hN4`ClR++(>u`?yA1x5
z#l?&+uinZ7Xy0T|v=pLBXy`O2BOCGsMa~dwvD?Tsq*EVqqv`dG-<TTg+W%as?AeXx
zb**mNP5y167ALfU<TH{)F~7u@;M;3cDd)1V1isr6j0L0tQ*O;TlIEJy{2uZ<<USbp
z<XvWn%roqTR0BoBoV_a`P@P<7`;0nF3?o*Dtw)THg$Bvj%Oy~{mlZWDP7f7>8k*HS
zhR)b%g?tZvPjAykjXj<9sisds>Kd#fYc}}o0)ufU%Y4nL&yLiDvi>TQQ0xt>`F2Y3
zz70N^fd8r5Vraiz<;FkJ;l>U+x5xUMBHFtN7q+fm8n!|~V@@cL7++wS3>C7V1J#JY
zOQ1~X?hEBVhkCCQTdqp!Va>X~T3{!={OQfEvD49RTw&g`qY7-sd3l#yBV$+@mHMwn
z1yv}fHJgm854670>~j*}lZaE$ez#7R*|MmCs>qP~ZAA1iTG?pfjzA>6GU8%j&mr%B
z>iC?%ehUx;eoR^AJ`y`vsH&=~CR&6yDz}m!=a>8zC^Txj(2`f>sm<*%m(ng6e$5KE
z(}^V?_Pi_>C;;r76H2kG#LcZhn=X_VOJ8j-dZphZWVL*?ygsH}gb&ct6bo{BqHlRz
zR5Wcm;hw1e3`x@;pyk<vb&*5H6;;koB~&l|+GFTqWSrkllQRX(SaDqS<|*x|`Lx4~
ze=qG+EA-(h8d~sgeUUesX2H^-9ka9J71_-%M;@_qKD<ngiab$Fx~~n@OH8+U>F<GZ
z9@wn%k75*R=7=-~8~TKwPMuZArb8}bJFihg%KGxje<)}I)Ko>N?&l~3dBs>LZe`-k
zdzop*&I%AYR+$~*C<|t<YD3k{Q{)Lo75|p%W#NDqD^Ik&3P^m-Q>cr}`eep`Z`!D7
z>ath0gr*`Dr|Hn#P78PbX9b-ONasE_!L`p{*RyYZTrXMF*Z5+c{w?bDu(l<Q7zW$7
z7OPTKY=p+HoXJp-$CjS^`d(O;pShTv!mAh`8b*8MzsgGMGXZo*_R|s1^<7(rnbe6H
ztj=Nq^H`6H7f?=7QTEBQA(9&5g>CcX6xZZ!c4#<<<FEKs9Me%^wj?F?M0awK<PIuF
zTv=W5Barr@vAvb&Q`s!aKln9JV#<1&PPm)HA^xf1Xa3;_(UG=ehAh`MJn>yfY9@my
zH5jtJxVlgo$=4y63>)q4**P`3QRg%a_{DikSJjBE+spCZXIWA5d8B2Q*<xLgL}j0z
zmf&oIN?&m9QdZPFg^S>c@?d-)YnDmM!*PGknvU1M$0E1k+u4cbydmkm16((dWYk`C
zVupQz0sBkAJ+0@E5gBweqg7M9>>L<mkdC07F(r5?MzJ|imlAu5($phT+j@A!er^~*
zVNf(Dx@;{`|AA)uaIQ*Bm%6DUD}qDMP&`SDGx;xW-D9=6s~67-f3>33>wLInOeLu0
zH|8i?9mU?>lgm^Z+(->BPut4*smiR~2bJ*UhFq)ICf5{p5=12U2D?upXsns|chZ?$
zY)El=nlZ~{oKIjwW&42Eg@%>~-j^Hf$3WC!=-bstOlj;ZTf@L;dmlV1C_{$Tbt3B|
zF>S!ku#qTpY&(bP1te3vuXOU;3a}gc-WME_Wp4cZ2QOgoPNZ~|XS>QF?W!{}21&{D
zWeFKUbL(>OC~ro2*6$P(9r9HS7U!5P59aGhO&)Vn?Z5w(a~>UM;sD5nuj5}K>HQdS
z%Y$q|0bQy|!i`>Kn6Z_C2Nr%>kCpJXGKH!a9C$I>FNzkvBTh@R1X3-Jhx7EJqjJEq
zTF+Em>|yVwSsPmv6!G#O<}16g1l7!3Y$@P+O{T0W_jPnt4+ZjWA8CI0I_k2U(YT-q
zPb;8ohVk%TGF&5b?k3JKW)s^@``iy?aNOZPvuqr^g-W-L=#>GpSr!6cAE1K0dLDM3
z<wqf#qkTZ&_zRDYX4>3Y1--}0vlA(`m=M><5vL!|xkwol5nP*7jzOkK$tux~u-O{q
ziujnXgOX2F!VT5td0?lQqQ$dz9VL958)vGKF&)!uXz-!r=J}~cfMMTXGy3q=$En#$
zgB!Y0-P=tJj4Ea5m%}x!0la4QSJZ+*X6}CkoSYZ}u`1G2r}M=fwD$dk(&|3P_xdqR
z>*DM|e-j1lq1-vAYAYBB8O#a16IW8?U5?J$iDgy11+Bej!?=IG@-R15B@c}PpO%oA
zxGk2^kFuO3HJ~vWubrx5@%_?PpOey#{kF7IU^Cx(qQ#HzbP^3r+YhC4%h(56ILe@1
z3Y?hXvCq?gTPOl@l4p@rJ+DjnNEC7vIPtjhxHQ;fcan!$FE<jpXax^c3<5A!qZn+w
z%^?>fk^Pdv6d4n=FBK_OHcqY`itl4}28}`5blu;%S*2#VS6+(KWa6@)R_HcOEhW_;
z1IAP;Ya<-;Qah0E8VFmo$7BtZsmIK&a@S!3K_%+GUEOp`9sfLwY~6fa&^ui;3_Zgq
z-zwNUUh4RJ#k%*aWDK&YW+$HSl-XYywVHV>49#T89DERs*}yMvJO4u?{JWWF{Ly|E
z^{Q8JEUTV@nDRy542~Eoe@k~@B%RrTF=u9O*gQV4F)uEH(utFQp+UjnhXjTeGib)r
zOt%EKQu$@}fundeN87)yVX{XDr@n(Fdbnkxx|)~GUzo;fm@J_D0w4qLR|Rmb^~IJ~
zsvp}+tfG}bBX?N-jkfG!4{I(IrpwHlXc^hNPN@0eBz8f0-B*zM3-Z5X#!7tqO}D0U
z<){|^-X3eyO^kcuw;ao<G33F#x$MWc>b}Uo+|<%=Yy40}CU~Y$RKsi|XOW=v9PQa=
z&5NePVpf;H)G)M<#D=p|#jK7P@f~rFWV91qg4>Ex=Z1+n9F_j6>F*_UzbP3OkfpI+
zK9pOSQBTcQaE_?7_9~IpKQtQj1-72Rj(Enk%ZP~7lqicDX@`mXko;(00NOQ5ir7&7
zg1{#Ew=tCPVP9muJ!MBVC%z$!Ou}6T2b`5B9$;6dB@wGt&@}?G|Mgm>IVZX=e2&!6
z6|!Y~Da;~uzmb~J5yA1~{83U54voO)7w^2TwmY3hobtWL-J7#&iTKceQzKnQut6O0
zP5X1w>0!gv`lAfPSMx)vHdC-PV;=Q$QH;wn+ODRr<(qM<aeRLbGqzqIeArFtZFhno
za~%7P**B(f&d&??w;swvr>RhJuZ?KY3P0U|RZiY=PWL~@Vx{d?yurhAi9y=4SN%3W
zEs;<tcTroi#y}E!zu?1`|NqjPWViOt5s8iam|o7#rXv-Em#iw`RVgFIa5ZP&KBotL
z6>`x_OwX{^G6M3wt@#5iB@o>O_Rn2UvkhEt^a>q<uHc(6MSJcrPsZEAZm9{65gSIH
zZK=EIJ(T?e8aeytv}#q65wxvcNFxTfo$Hxa&85_Z?RQ`c7b!T`C@Yd%5kbiOCO*UN
zB7vD5)3kp|2>eQl+x%}s=eeMD#U?%N*IMLrQ61OcL^9QyzfB%Dplj%bR%jiu|EEHS
z?69azk3F;kzEPj2$N$n5kBl@V!d+*7vWn97G@PEBZznHiJ#*E4B0BfVj%Xe81nG_-
z!Vew!h8fyB_^T$vydD-(Ud7YVjJ1BAM9-R+Yhg70`W!8g%QIXrTz+$=yfY4HU3I8;
zmABihuU(_LpP2zFT>@kOsUD@EaL`rR7ru`%@DB}Z)qu;WEb^KDf(r?_aO%!;^KZkB
za^(6JV+$p1_}n@7*Mn#*C5_?Sv)DTx9iQeTD&PM=Cy6k8QC2I3{@G$uZpiM^bZqtW
z3{}B*ulz;0%<^9YgW=n6VT3Edz9vN52Tsdqz&ITt$;1f2jt=|8cct~meYy8JXOYA;
z`5CUcae#cUN9cPJZan#A@eoFLcZaMx*Vp4p#C0F1PS8RARWB9ESTE?x(4`9yc*NcC
zaEOWBKDDCwxPXkekHIelI5q?NA22!JM*C~roT|9th`qV=vt?nDF!~l?oMmIi&@8k0
zd>(M7wr~l%qedkZo5Z*ujc^@4m#Tf*pCV<P-Q<@ExZcTOVGXJX1$+a89fz&wIo}4y
zVrK+UN7Il}bK%U>+$m;hLME;w@8n^J-n7K7z^O%B&+F%q^JD*smf=&^Uz0=>>ZEw<
ztTj(ht<@`$Oa8nSrXMI`e$u(5<Sv$#UhaIHbL>#Rl(Ri16QI;NU&^z!^77iu--Equ
zsLXFr1ExF1i@7PzS0fGlV!~$h&7(9OO+=XQgxH^a0hz^Klv8eZAdjJf2!8y6!SLsP
z2;do++y@mYktIP3^1PYuDm+Yhl*?)(cYE2iJgBcYQ?_am$&0s`ycaw5FgJLFxYB|P
zvTrFvaYpz_19Am?Vi6W4xOCvw%O2md7%>cf4fr*Opi&V|5_~`hM_vi8_8;i_gpx^K
zdX;flRbbSwIP`H-;XWs*LQZ-cWlH9PZ2*<hig3SvgSdJAW=Bbkzw6@M_VZvcyJgMT
zy+L88`rCa8Hh={oDrkND=08vnX9ahO%g4C@D!6b+R~GlZqLSIMgJ}^Q(vxKy(AuL3
zAd*6~^@x=Y)KE&-EB?-`HR}nneC!DJ@70qMNn$;*fmRPNO1fjK4d4YN;ks}Q7BE7%
z%aAK1zVHalmDf(4OQ77={7VQi*u>K&Xuh8-S3h*UFO3iS`I0$l*G9~jcveL&xNI#@
zVCGFjlT?K#^h7IiLS1A2yEOoC&lT|3t)g_3!i`+N$QQ7z3ak2>*0+<n&cWK}&~6R*
z4^wcOsvW}CnSo72mFOs3>REr?3@2~AYrE%37(Cjh6}vLs`Uy=Yju`S{?l&S#JI{@%
zN_5JKD<Neo_s`oq$6lh|^Y5?n{L_0ec(N1wX4ApJ$cCN^!27hkF04-~DQLyd2X78*
z_62moPZ#~eB%{ynQ`UQRASDgq%Y|M_JnU!_5Ves|DEd%W|EVCKTa`s&=Z!r8E9}H}
zVl7{-j^@93xo+9~$)sUba8fqpaXKG&FiPX0j@6Gx*b?p~8B~`FBpeY;x$iyKkHDF4
zw`CXqE3y$X*G7<bul+*ou1aL%uRC4w;!inkt;LLdh(Sh>#Hfuic~}ekpFj>QgV&tm
z5R<#fiosD);H2bAeaWb3<BjiVIseDeRYpbCb>SgL2@z?Dp&KL>BnDAB1{gp}>245d
z2Bf<i0qGW`r4bk!q#I-iX~~fqzx#fFS&Lcg-h0m3`|PKV2oIOH<q_*XX3r!?3&FN%
zTduHQGp^)(dzm~U%T4%>M@kn$@b+*5aI#hY2L|i^$k%m<qd0lVXj4GbF06Dl25>3;
zL1WsA7Id5QzlH2{gf^T6;(Tz6aIy|Ou?i<{dDN(QyO6+^D;8@D6y^utl4?Di0oWbD
zLU>R{-DRInqi>C~2)&sJ^R((t+Rb}YlKBTZzX~y>V3f!X_FMl$r_r6sn&Cl(3xBUf
zy}_CdbDUWXhwSqYAlhe6m@?d*83C`u7s3p<s?aq%sGsm{3nt7!w|NzrR0MblA4ZS}
z$_k#y5HB)8MJVt7fu>cbyB+)zmPuS@*6YiEX|4Dh<dO5Tf+Cu3%8%r_+Z<^KEF^Fk
zHnhni30+@)tuv@q#>H}?aeIk1RjzoOk=O93BPn4ZeM#^t6T0zGesfsR!#xj;C-VK1
z!V(9%PrHZvD)#_$|KG&R7tC_+F$65S%^<oMX=Aa?3>unmCtm+RihKRqWwiXK$F6dH
z3njA)XWtSJ|CUPC#up@CCW}&HKjPapJ)W6n|B==-QRf3fEVhDvkZfKQERtIvHkIzr
z;=mZDG2sAov#?|Ji}&cUZzr@^BFNssKIqC`E?>wskI^5GxiCiXmOP-p;x!k6OiLs9
zer2kqPeP2rEO?nP3#TtQ69UN0vur-s$2S>TFTI2_4UOG$9h|X&SX71k=0U!4GMVo2
zFHbP{fTdZP&?f}y<~K0Gr-n`?kD@TrCnWbkZ2N&msGH2<Z#2hpG5cyC<`@9PaQff)
z)qkFP|Du+<2+Pxzc$oxUhHWDL52VSld0A|yN$&JXVEx3Z?1!_%onjKmm#SJsF-d@u
zIuHkkPbnsB(<ML?S7CpkVmlI<?f`DB6lV6e7U)*`2ePZzr^sfXTRzBo96lr<OD@{g
zdY~yfeoWklgTYbx)VfSuF$GRQOke>RYzfYr3VgLej-OheciCO9$~}F!wIVIHPE>u_
zBvlwCRXBdp3oxB)zj#6AASKy_X(Z%j>lS_wG0D5P%gh`SPYXaSd@+ls8v;BSS;zy`
z5|TbvFFMQiY1Ufbzrkd#!$>KN6JUUYRPL*Qy3tqvK=$NV4`mf@(hk;&9}fjZr1%>o
z9~Q$%TTp*<KVRwB<*_|L$|qM7S;(&<4ebH(vCjb6&KV#4x9y120lNAKIi>uXFjun8
z@}>hMmiGQn0C@=h#EJPGkZxMac9fQC4jjSH1a=o~C?cYEF@}J~6q_-ad2jxHw)~Y0
z@&y<0#0Ij!I)gs@%LaPTwnEaR{-b4yyMH!@eTCB78}s`>C-~EXVP-(KEn4VJRDu3B
z&7PK~_VO~$8Q~}Yy%B829j^Lg+fl}DX^$TOXh*6Lld%hZTN3!{NgW{71!~Exlq2%=
zO^6Rw$u>MRvhH}Xq@EptT7}h>@Q`Jg$_+LJOCQN-K(}LCu2xm!9?LM#t>El0loNqz
zZbcK&>x#J7f|v>dTZ_ZVufO29p!*RWG=91l4ueMvusfz&27@M)3ZQbuOa!OU`?Gd<
z%mVcE5=;-IXv|LB`Jb-aP4YY@i^J<HTw$Y)pgymmzAaX?#7T4)haAHtFFBa)lk*f~
zsj#F!;$)ugd*xS!Tz>ATS3jo+UvGn6jZS%9Yi;EG19_5n<GQs@By!zk$p;PX2m|LY
zyjRgZf&<xFOnL5cD;d5}TZDtxIxao&5G^zv+6*~8aRA?5pzL}6FzPVmT5>NAirG|S
z!j$<1Cznby2o;<F0>xWGS(e`693LIyZ;JTO_2d6i+Kts@w?COOy!hQd6H9YWF1{=T
z*sZ_CLH{;fw6{EDG%EAB15;$PJ|AIH=!k?F5s+cGB*$3-d&JUKXl%+BpWBS@v4tI-
zFS{M3uZbIfF|xtKHmOe>XQw44&onEM^f{$%>F&2vMYcwOfH6-mp)i*`);Qq);m5QU
z*9u-QS*pI`!BFwpLQaIyZL(rDh~}Z2|Ep52n8c=~t$6pS?9h<q<sta7K`^EGtt1EZ
zNIOFoit3e>Qh^6fs1N}SZW(qPg=!xA;{d?j(=~`(ynIyMTkSa(=G-ivf6MhsLg%In
zs07iW5qKkUZ(QPgi{osKC6?H(2(>u#@>UFhqZP$EEQ7z|&)K3E^SM3KkmXx3bQE`M
zjDsN(cFzAifu9j)-ckO`d0t}~$M+~1BK`0YQRMxpV%=cZ+0u6WZQ&gk0?`I>Fq2Bl
z(TVJ7Z-M-IN<B#Qf&<9ODvEkY#aa|{lbdoB0@RV&9*DAiQ2gaQ_)k7z;wxcf!yVul
z&$5t%O$wCfB3wD<)F-Xr4trtmmTL(unyfz`&rCR0_wp=V+_cu|JAK+bEFZ>udl;K|
zSDk$8Q-1@5nBpos2GI>Ul}>x$lWUG%Z2-b+jaVt;Dp&KFM*N<)f0+PXqZu1M1>MSz
zF_8wWZ~Q%XTm_3%e@(#qoD0E~0}Y^)hF<WUf0xuJINs=+UryF6OE0yUbVgv0(f#6<
zA^do~kYXyVfS>s8o!ea-B3-u4EVNFvlJ`qCEy1jjkvBw>{HCjY)4P*wAdbAp5WdD9
zaEWd2Hr8N6!YyS#Q|@yNPuhQG$De?PyfO{vK1-MSALs?*t|h?nl~BylG)nCFeF#5b
zi$Aw@?^T+b>3vIAiopX~-TP9{5o_nf12&QBpFA0S^9xe2NIjyZ$5Km)g(>_2BUCeh
z-=$8gQ^Bg;8!C%Ge@IHWB+GB2?cJbDNx9K(U1z;x3U&FQ=rpzJ57CEsqKp~RC}|)=
zO2(<pKL_IAs@QvIk{toM&{QO>bh5y)Pre|(cE~L39Ur-<x=1^aFu34k_*C7eD|&x<
zAW^%qnJ}ER{Hqo%^tm(T(<;fSs_TK48ja^*dm?=DQNu(%7P{t`WD@?EFDp6kBF5iV
zEwxi%h{fNKya$`4!~NrrY1>jl6)TS2Hivr~tUS}EiJOFgl3ZTLCX?6H3_Cdvzfcfc
zj(t1!y66V7I<%P$h%&7kH3)EPx$!#6_wZ_=nyT-f3(u`0o9r~ronGqkKy*u(Br`Pf
zk|>JC3hwtz05DDO4auEX9~W^E(6GcS3SQ=$%gt8A@Sa*PX!(C%&(8$6C@1n2f}z&U
z0Lo(aDyF*jf=&a^-PcL{Rwb`MOS;g>i%dBn!p=ogkN65Doe~DbFsqRKiUI}NX*`N|
z@&5#mD<ru)Z3ni$Rn>hZ-Sr@pz<jk32b0wOVSEWxAxb<J+SJOjqLtn2qd)Gy4{J2U
z>c8l_!JW7$w$J#1K=$`so&5vd%wRoiO$@^eX=Q11g~g#Xbg?Da#4+apL(czIt8)P<
zj7kF?bt2s&64;Wo@6@&LsDa)UE88)=T5V-y{m4;GYD8(gx;VUuL6cu=!Go`~`mV-s
zxZ6F?{AZgO`gRgtms=;>w3K6ycAY=Ex0O|17z=p=XkjDt`F~g*Gongn%lbTd5vXkd
z&DG;^&E@?CL{Px566a_=fQ#fTmR^rQH_&{(s4c#gj1lsnf#OmKi%xC_jFWVUICq`6
zJLLZZ)yYJtQX_9He~=i#@tV|C=kcp(_|s3`%K-&XDeq*T5a48G7=67`j95`aeqFP}
z%fXGQD!O@MXErE(Rn&b0;?!*hK<6S~bHKbSZ}DnXE+@R%!1K!goAo^y0@oA|ouEqh
zyA<h78|*PqLEb$L<S-QL+8vkn-&6Y@1bE;y0l5kC0Ta#G5(Q9FHMvHb{?s2YTJs;y
z@#Wm-E+RIxztrXZy?B55Xu&=25P4@y0a{sKT)F7ED52sY3xysWDg4SpEIs}@=8b=%
zA*hoo_&Lk%*<6vP0Iq)=kgyS?fm_LI0#Krsl7DmhX7ucABX6U#B4}$7sI?i$$I`G4
z0G34-S)Ui1(Bs{ab{hC*${f{K+Yzg?Kq$}7pb@%Cw<dI}h9qb^y&8V3hiqHGnl#bc
zrtiyCG3`|*$(MW@6zpMdpL|S9QSZ#^E-$<0#8OUQK~o)_6fm>zFH?jE^5VJ@&)&CL
z=Axzq?;B)Fb{ZbNPzQK6X$)cezvHjoR%=j(yub~<;zZ7tuNnPbKRuz6{;ES!?R($Y
zA+1}?<8Tm!w@l&}1IHdA%wOL>db@9nn{LA37~Y|K#sodv1vp1yhJDrjLAb7COq8n4
z;yXJFu7mv|E9w-8O;e}N7UfV=INIT{?^DDgFylz)gp$b+Si6tdt)qM4Pk#}_>?h@E
zfy!~+iSU}5jXsX?JPfA0PkA;M^!WOxBjcJ;*HnTeQOo&%R#zWpdWz|-nv5MZroM%Z
zZL!4l1~Qu3P7HnQyWB1>Jp2-1C_d4tZl~~>7IG@2eT6hIO?s?wr<R>32QYBshmlXU
z`)>0v9qLi}e&4m?%P9yZ9KtcsT`ROEhCJ7@{vzvF*D8KAQBKuJY?A=iiPHBi|78iy
z6QJ}}>ntqQyx>CtSp-jdX$fsVyaJ%CMc=go9vx#X-|2$yo$w&hZ;)a*EogAML=r7B
z`^G8j{W^M#l49()(=Tml$1ThItTf&8^zGC@DY2?oH1L6JN(pz}!p;s=uEr3?lP-}g
z>g9;LT#Js(S9@o(@@b49!?xt)_%=f&9u)>Fug+i!gWn0#N(H)r56gshpdcULh%epL
z_1uqb($&0*EMHL|w0`8!*a-eqUpsbwADmA<8RVBKMk!o-8NewZPiU^<rr;N6+hzay
zhh6ZWewGOme|4k8rLxzUaix{-7Uui5y@Y{6O)k%7E6RM~gKasdCu7`07V;0<-7x_9
zaeSobKN_sIPhCFJO@Yrr{6ObHt$DDckAJ6~CVi6mQ_COLHR_0JO6+CA{4Ty(;Ihzd
z2NCjc&en+jO&J<X%V>*(b9~JFxo+n1cWrYZ@Fyk-o<OT@DV;$<m4{;yt1Js$?AL$z
zg6}@tfdnA-UY29O$LDRjQug=Mz?JyLbN=3_?pW|<+H;wt6YU@sR2h8Ka-BQl8+Q@P
z&bYI`;*SS<OKgh{q2g$IC^CQMK2{Wd08jN8KT;Mx7F67!l-z%lynrP`>J&R4%a^^9
z<)XCMsU{At*_YP?9Bhz>F}fLYwHvGI{y`#GOok1}8~RSc)pA_4-4D{`(w`OdX<{a4
ztI|Fw5mKvs$Hwo@?pfH|2fo<_*I70?Quy4zGg)OTT`FK-s)V=5;tz+6SE8~W#t7j@
zD<?qw%)S&Pzi>R#7|Nv2lb$u(U{xi+2JO;wht?E+7$;wh=-w5t4q|mE9Mv$a;bv3c
zHmb^HO%pInW^#?mZFHlTopMqUG#?k%f9vX9?-a*I09NKRU)UG~F{D0JXL(7^8L%-}
z-sj}4H-v1o{H$S6LaHt$XV@@LjqTn5?3%fsp4jfJ5w6>)6#^YIlCh~g{uYjyfuA7S
zPVQhU^90y0T^1RYp59<JuQd%t0;!6GPwEBo*coP~fak(Cb|9;-e|(x4d=HL=rP*jG
zs>Nd;P967a!TN6n+*#5(T-WqKhK!4*2ep*3*L9rR*}!a+AjHyhFd_1*)u)U-h}1vg
zISIH!#PDvJJV3`UM<J=Kl%X-5{fieX&x1%EFECw}i5_NH=&`r4yK1^hL$j6>zkVLX
zl|)qCFnjO$^*2lZIBroQbr&eaz?{|lsK7bt;Ufik@e=>q52R%m?74KFa{V01WV!NO
zSiDb)Fn=#fl}u@w&QgLe%XG;@w&*)kt+?uDF8AaPVO)vsj-qYmPDdTxWx5I<m$!#b
z&Yu3(m4S^5!a=2z5MzUyk1(!Siqz3EYQ|SF$9B3+O(D&hOzyuM?X|)-br#8Ex6y=a
ztyhUh>!zXUopyyh$13ub?}`-Aq!o}8bM}1SOiL~LNc;-EUOJQ65XPuZZN+2PA5Xnx
z)d+6E1hBcH^N4+}z!ejB`O)bg<%NE)1J_d-X}8bkl5N4;r6;d{mfzRsXy6(eljoBT
zm3n6@iIcAjm<7@mF6Gin&ywUuNe4)kM}G+YPIjY#+jnzWQg7lrt@<0b($B2SN<&@H
z&12f)koVOmV%hMCifrt$oKizA4f#b#vlAzEUlci%R~bs+N;olCc~R~clWRlzruy6o
zs+`sxRH#)LJW<S8xAy9O<EonC!(yn>qYf@1n0iVAO_D93OyKwLxGra`^AehPma#iu
zY=f<M+feK#M0H+j(h8VchcUO3el1zb63G^~rI{!fWd{s$!k5Gfevsn?pSv&R!1>TE
zWs7G(m>1vO9w@feO?YNnMHw1TzTrNXn{O8QEcq$qJIP$acdWA*9Mw4NgQ2~(V&5lq
z&Ysjao0XplQ)AC%q-Q3eIlI;Js!HhWsCPdlLgk=>WvP0_Zokx;UND%?j8Hyu)gpY?
z9yF%R%yapbp;6s?<&q1T^!%yiQfKEZZu;*EcNNzJYM(jPQ|sildQrm6Ii;ZZ`TWul
zjkd`Cw^58W4{>LbjF@`QPh@?9-^!(CpuolW4v)BLKSXWH#B#l!t0oqFHNFWr8XZoR
zkJ0Ap=o!d;Y<sn@CeQzFXd_6MwK<X&k63oUEpAP^@vE?KEeESbuGGF}ij<t(_OQZm
zUab5ORF!V#T%gWmWHD1t*LILi2XIxO<%x`6JDHr#I4pu)Tc@4KEgZ^t*6w8WTvLy|
z<J=pVR1<{nj1U(D*1?C}+?S`ySMj&q19^09lcY(bA$Aj9OY%b}dT#@cV#|<g!m6yn
z6DaK(GB8CobE<P`u~w#l>x{=&>0Q^PpA=g$GtXi?up2U!#7vRJT3Iu-k`^8%nY?3J
zG98ZsQu$Ixmetva8)DA5*c#4m;u@a@R!AGos|ja)`JMLddhUQl-09^`t}fBtNs?>7
zyMahNYpDK^Mj?yjy}gJ0s0qQ5`tKbM&gj6vbFJd`Bv5Nlnc3&byp`jdDbb6>a>oqm
z%zW^WMP;6V+e>XOTb!m{*l^LUyBaN(mY_yw(ck4O=M>KkEs9VcB4cji!l`r%2jRTl
z3Z^G?Ly2p}Ld#{nf?_40k*8gx$K<n3&*Egu%L&VI$R`BSsEdRwo0{W^n_U?iLg7&N
zD7edhA-CX(rs$o;A7L3XW`(v?NUYR$=pz=uvOerJ)3qCv0N1kf<H4Td!=>NyT>?YW
zpDKn}6qQI(f6AMWdKTLjCg)Z6<wpa^u@rVWY~I_gy!z-IAYoS7-sdLA)ZV+n2U21~
ziV+5Bv~5{r#k92oF}MolrQU4e%z-RI41pMt5?R-!&sUlYW<gGm+-$K3u>sxpsV21|
zhP%E|v(}*SqmKBv4gDaIgV#8hU~{!pkyLrU#4eC8@HmHK?XH5k`1Z`sof_IF-CE9~
zm>%03jYZ_bX`-}KWx)^@yj6M{pgqm1f1oP6OD|p|WgGAM1l3x`@Jr8JYz(B&ii2(`
zNp1@|&?u9AwYDDn?DG?b-8~s2*T~=}KH8_D^cA%oF=_Y-Yx3dr?$cQxNei%RNR*2!
zjCd*C@WidCZ{Tt_P%VYJikBUua07>)!3&WGn>Fv&REOPs(Pf_I#jJgidUZQro?R5-
z#`614J(QS{C|ivJ<#eJ>)Wph~O?Gl1Km<Kk_f9%sqYZLBQ6?li3zm7h<T$;o9wr<-
z%`m&NDABHX+v4nVzO3!e=~#O3POWj8m$NNmdFoTmhhOqShFPgJ-rPRA4?2+=h?ib7
zGB`AMwoyB$AL#e0-5$G+nZ+sq38FLyL6-$R?uJKe>o3YENK=cQGY>@8L5fRCSL72-
zf;5CDa^a&+eIGr?lv#T)se#So_(F2Z&y35(%6-TiUuILYq?|b6+rRTG>kV0wK}BsH
zi83a}P6TrQ*iQ`I$jd)5nob?R(Nv;$@C<s3LqUWNFul0!cYCe-%Ns}f($-n~+0A%I
zP}SJ|l%t%k?u5r?9gU8~Aa+UDEX%tdJ^a0RgNX*$=R5npW;I|@t)ZL?BO>iY)x*O4
zi_HqjAb^x4o5O~~B34u6`rO!7v1f3z$Ubq~QEZ}&ZtiUk76+YmqsXX&RliPTtKV?P
zUi`}ke@Miu=F-9Ccl-FQG7B7eKDvZil^=p@5ZvzX$|&NmLLnXzW6!da;~J`XvNrF<
z2He##KXErsqlS&@KxUsm`E$kXBzEFzJX5}4Ij!J+aHQ<%qiNFWalD8eiy|F@PL-Ez
z`ap&osu@i}bFfL2Gi{>c3Ml1Kb9E=b1T89_w4$PZw!*lE=(JTN;ctGb{^gt8Y#mDr
zqr6&^Fgbsl|D7u+Z=muWs}k3PU*TmHW6$S$v()g$OP2nDSS`B@I_`^H&zgk$U2Bb!
z*6)30!#)tU=9sU{2?Z(3kx(k^6sQ&^j=ZHqc6dHbR&clZT`G1V+OPb)o<#Ygb{)Tz
z%{U?gqTX<6uDO#!dQp>|NvTsSKBgb^ceCshR{3VSJ&|WMnXt{YtQRJgQF2yqo3}eE
zr<E?*faSRXN#dADVpgPK9N>zwR`z=KFWqM22k+NLDI7R4b7I}12$l4a_V>bV!Em_V
zw_mLbVa;MDv@A;*XHOPXH+<nN4nb$6hqkx%-LSd#9gmfWwih4E79;nvnreqfQsd*R
z@z>t}{JLrTpg7#A(H-Vr1y(Cb82CHTP0VYjW%9T8qMEsHybuOw4T*2Zx4SmKGtz!a
z<eRG{n9xG;g;lmHiA{3mG%tXgF{*vHm>(lnj=g1FTC8eN&e|cN6XG{TeHM_CQHr<n
z5}qown2(R8es-=^g(#MS$G6E)WIeHsCWRPGo(<9ONrtf;?*wuq8Mr6;0xQuST;Xx6
zJaF{}EuwLJ(6|~?uH)t|U-@Ita{BLY*^h$P&ufwgghl7-1fmpEwa?SW<=kRv;ODBr
z^HT{!ul-3-G7c{uq(1g)+8uw5Ig%72MQ7~(v<01Hb_H?CCJ%tO)%df0#{Me6h@L0m
z9$gq|V3Yg#ujS4>Sf2%|Te9>atMJiD5;ttE761m={l^$-w!6^T<P<#+L28CZem0K#
zH;Cv-=Fjnu4KYGbK~{ta2zV{kaq$oSBj4jn!KGm(K5{!LIoMW_>*vxPsZ*InZG(ZF
z+(yn1a;R&#W!y*VM{C`DZ}^-BTzNBqo)`Xj&q|1&U>ABg>;8CR)w#!RYH1=q%R78K
zD#1V;d9nkIrNqv9^NNU~i#ySAB@c*8k2RnKU1oM4e7e}K*KuM6cRiD#z-y}oP}@?%
zw=}<?G~6SG$UAwKONU9u$d}&KfZZY%&P5-?R)@Gb@^tyXIk0XV^u_{KTQ-Cfm``Gv
zkIQI%?*K)Q(I!I>c~`oLUs;SS**Ho^NK3CHG@cKI-+{@yWru~&2c;ubR~|w;f!TN`
z7slz4E1Q_2_^<Fgf*|5y^Y{i=m1Y3JPRo;>3A23Pa%YgD2q=fjqYu6(^qB4juA^7g
zn|wR}P@_f4%yd@#8byY_3ib+-UQbci=st1znd3XFo4JChj6N7DI{(v`+c}hlhk|^s
zCp{u90zK8G^ESCv&=fhz0U=JJ8gl(sb}S*PT9U#XtfRggW<jaVZLXaf{%I+ZVtvij
zH&`l>V6jB+-)c-&;P~0!kMjg>*X;cb(wz{YT~sAWhi<w|#}*|bZHAB1Ha=cYi1frW
zepN)>y-(mjxi)w5##|~~g`)7+X$}`l?+a<VV|IVq)IM;-$EBR9WP)wPVBP=J%v`xp
z05F0+n<uIO+k&t6RxZj!B4ATparYa*F=xvJl+6`vJm}+|i-)hy#U-5L=}8Pgw$^l2
zXmI@Tv}dasg%j;u73+IzV_~UtUGs(|p$g=>NDZE1p*ivdx}j#EsZb|F%`ur3C7bY!
z(dptuo8NjJQ_1~mH!EzI|NSbfx#_@(jJ?$2v6oZ__j6*VmHkne>zM5#Tf@Wd0pAY3
z0i92)D2J-V-IeLmmh3NS%v~p%9xlaMthdmOmDx9u53hd(dw%sP3K6UFV#`|bSL41G
z8~E#W*zl)-KPvclYw@|fv^C2fg~S8AUWK1sob~Fr77CT4uv@{WGCIg%G$cfOL(k*(
zHKJQk^|kIPSOI`E#*3-K3!(?0fh84fG5)!`e;Bn69Z*9VkgFUGrry)j^VhC<S2^(a
zRsjKH@opDCaPtwBs)$BDW+da*4=d<eTE+tvV1TSceKTmYv<Ufq6}~bAd!PhmYpx?w
zlOq2LV}+PznK7MhaY`HN+>MD+Y9Qub<z1PN=`qc^?|i+(mz-pG5!?YFCs5!djt>3!
zQ?t$k2Ch)$yh}8A1>pD0l}9W7aL)7m3w*n|B0=T7(e$qTeEjWG%y-mYl%Gb!nZr5z
zM7dazp(G0bV1LYjvMKV(6ZylN4yHIYac%xP=<J@QP8?Z=+3x*!c9TLIQj)*)T3-1s
zuvD94fD{0FYax5r?>uoYQoINf6I`^uZz_H83${@YE2INlh>ZF91+QF4Tr%_VC7bs9
zW%c7-xY@H7K4j6aRb*E3&{*C6miLvl9sL;FlH<=e@mC8w-%HtDm;}wl3j8;Y+~AW{
z%ws@A@21!EdJUh>uMX?3Us5DHXlzaR&QJ~{OOW`(_};Gy{^z0itu;OOz}|z~d0a$i
zL4irpdCR?JsY{)HI?d=?F!X3MIk~$T80|VKXWkV<+=Tq!+lB6iJX>kHv&?^RS3Ysq
zW*Fx?_S#?+$xh3NSW3vE+?j>(n03Y3!J3vltQ(+z=q7RPotaCX>p%Jj;wm!HcD(`y
zs;=Co2<N=iu=OkE;+LN|R)tWrrejR0KZdCy&F`4Mym$Y(b;n#Dx@VqhpLobz6t}-U
z0kPvb{$hjmM~=%iB_q$Ha*RAGyJ_&jZ@jlkHC}!2yuXhr$m_?C^6HI}q*%K#A3#Zc
zFrkh~U~0KpDPr_X7g#@RD&Mx3*%$KA+eK$J4}o#G4fwusCy0m?2b~HKG^BqpteFMV
zf9p*#RBGO7{sz7;7ry6uy3n;2)(1JU78&4PmiespQybB!JY<7pU4Aj26@LgI7zd<B
z>R1{G<ZQt|(D#PGMD|E8-H?0A6eD2qNc}e!mz*(sLzg{xeOwU4>pl2AwKH)NH_t}L
z`LaIV^kLBpuEpaHv8aSWYQ)#?P{qA!Mi!b5mL*}izzjvfg!vF36Rqp9C5hlmQGHck
z*zrmI^bRh(cQ=t3IUCDJH_u!24^%L^Ht<T7iVUg(eE%R77-_5ctvI7km&i2rI9`rP
z-rIaUd|fT+F$Zva!!#{}T1WFeT6wZb_{tF0e~r<eqIbo_Tal>055!(pydNt=`p<rG
zFjowgsBj;ct@y)}Nv=jmkee7YyJ#L$))#`c&xNI{D^FXHk%vykuJBGG!rX_~D%bHO
zvd^|`d?d^Y8HsBq%PY_b6a0J%2zg!@0Z5MIWH}3B#J35}73Gq?1HAj_`olUn@yH44
zD24>BTb8)FI)Sh9jZ3ZM5W5+?(kP<5bxv_^T?e`M(O`8782J!TN{-imi~Xpa1I5Rp
zFAKW~fu4v;nI(qb`6x?&BY@+WXL}**JE*WBwY>|(&dza*KAsEt^rj6g_a~S}=pgd0
z%>W>e3>)*3Tw7W}H~fH|!jB`Ft%upt%||n8U|Vks1|4$CVxxBJ;g_Y(04L}fCBR2B
zGNTOfNcFmiE3g9Qy(3D{lUbDsG2m*{Nm<|q!5H(49W?O*$_`v{%U8ewU;6)|=fd-2
z;#wQRXqtJvEHx_19np4Q9j^W)Bk+4}r|%RV@g14_{w!mdkPA~gvV1d#ZyLJqWVr6n
z_<$wed;QS~I;*6Wt+(I@!+N!vBe`A98<`8fEd6vG9-Hb*2kn%Y=IFdj%736g93=^X
zK<#Ws{j6B2tqOl;?U;9!n`PdObJ!G!=ujmH)0@cwaINv&bllUO-opEzTFwvT@uGI`
zD>Qjfk&bVFx8}=w_X|g+OOGhdKPtrEH$oL4Un{$hjlTH@s!jO?IHg#dVh*hWxieQt
zGym^{fw;Hx89a0EMAVGxgsqhBw6#Ky`}6kHM#%c+OZVuhuv^bRpEhmR9jObd#dy16
zM8(uSo!X>VxtS|uhF6X+_|!K<%`@Vd+>Z^(x1+SYn&P2HQc{jR2hM`P(w!15pd1R!
ztJDx|v!Lg51b1cscm67t5GjU@`ZfUc2A2jM9Lk^mgp*Ctv(<dS3lB($)D~lGUYNOw
zitLu`7{%GsBDAD?z&nq@lZkx{e6Xy%YM!`$S6tS_t8MTkA6L{O)~YWD<ZuS#2554|
z%7EfL$@=y-U4!hfwcwYTgcqMhtK4}>zy@Bw&8n^L#wXRzLb_Q!bp0>>D<Hg>lGwn0
zusWTJY(?oJB5zx+yJF6zPZ*OVxTk^HLq2{7IOQ9p>os~cF~8fr?PbyKpL!mkrqme$
z1pBo&((`gSqx1fOzABr`K)0w78)`C4;R5@(S|Jw=?JV~t03&6RsX#cUCL3VOJZOQQ
z@;3k|R6x%^khHM*>faLTBIHoX?)@$~QOd)x=S%v}X3KvZ(FPo4<(X?_u!~vM2A?LS
znx>Th1HEp5=yOt^yflrOu#*lJ3EPx)y&43JLj*>{BM#>=VBobDqT8)hUMb4byvxQw
z$E8SZ^{-GblH>hTzHF%nOxtvBCLiH^@_2v%aRrVonguL=Kx{zn?OxS&ZEya$r=k!{
zW<>NMzpC=dPvh<Ry0`;t3D*YWBt6r2vy;k<drmxb(}?#oOnTM__RaOKocs$$V#gS*
znE!BTj=A-WjbpMy9tdWInuG7JimXG$&yEMtq7QN@o&TP7I{C&yKZ9Ub@ABj83=!SA
z4ZK8&+kTZ^$@CQU`o9yUVOM_9ZMR3dhez=7CsGZr8|G}~SY=N^P+wMiq|ay@Wq%#r
z9B{-K)OnGDN#!``m8xv5xYyfio1wb>Oi4!s0#@PiuQbLuCvLXHE-09lc!;v?1-g!)
z04bpA;b)(Yf=2^ox?H^|mJj_3Wd`1v4{6ym<7<X}jT8Z#x@dXBhu>Ci4<~yt{HJXY
zRs!Yq8sc_iW^+>@0~-~0E0|^ep5MFE^g@}q_r+b;*k3lDz%UCAX|*2mvT=2}_GSNm
zfeBIoI%+Gth)Wr*%Jw^$k}4GGlN4#IztTm1u_MV@X-tAt&KR0H!IqWKT3r1aW&Mr6
z021k(cqH&x5<mfMN@-(<o}Ji{++I=#DMEgy1L_P!V)8!_;{Zg9v-Z)V`yyZ0N&D3G
zTLQOfL#(|hyXAyd%s8x&6lUlxGg#LQ`%A$HqK|(;ignm9&xjb=EJu@Hl7;myEj{bR
zG~72+iyO+_NZZgDdqK}117<`~px8ltj653f@oHH;>-ct?YsYBCaqr(E9jJwEmQVr$
z&?bVJZ-VXMd%D^Q-Kvf$Ap~;E??dlS5@BRa2w^GXM<WfP%Nf!^^@Ty{**At?#O!S|
z?(Kf-nzoE_h|2yd!VMP5N7Tza@lRU$`urIZofUDEEM~}h(<l@3&E@=ES1nv!u<#l4
z?(c{BNk1D0ua6v0k7sFRyAjC7G7#X*kWVTbf+$pX-=EnEdm?=G;)ZN4gG4*Q!ke-S
zJu8;}zROBe^;S{=W17h^6Q$`84G6e@%Oij*{DFob(U-S7t${vRvJ>k^nnBChDQ{Lb
zhgW=_0LoN5op8w6i4Do^%meA!7^@5G($(TyBaZ5e%nR(4>j*K*Zjaj;ltkH3?qWbn
z77b~eJl(rhz)A%8UAUGGtJThBo5>fzd?>Mo6)4WdePAc9E;}5Mu|kUnQUtW|CwO?Z
zxfMTmjFfJ9+*MO*()rrYMFIUbSTlQeHP{;pP$&$HIg_)+4FQZNmin$qAA0n(!s!>p
z#~%3FAQ9TKx~VMyoKgcBJ{B-yi$O%21(6RUP`xDOJ{A0%;`g)D0r;6amCx}$FHYQQ
zA2RPOMp8F5K@=(pLQ}BKi7z+H@vjkEv|PX>Z#o#yIa#&mQk0E~pxr*1m*uh~lO3po
z5RIUViX(<&wRQ*O-&e&1`<axr_!q0PSQbg%LX?-_@6`g5!QwM3&G|S0k;HJ+<h30@
zJ34B%gl;dwTE_&5h3HK7pCli}|0&iAa+z-iuak#bLwpPoy)nwJ+1aj#;sxDrbg_nw
z-a&!7da1=K*p@To8t=rdD#&p!1lUgFG<;slxC50i?Ku*<l)J2-kg4C&e~)vtklrr;
zq=&rg%h|1^DG~x`X3*)n3qoZS+pSc)IiU^mw1{$2!eVbD&nHllW@l&P_NX-2L4m|A
zphAucThl2*eN39IUyQxi)!Koi#*TPyT#?Jo^|Itz<6}d{?M`&W=S8HnTnE7!X>2X$
z<(SMH8}WKXxhSo-TVA@FnZLTADq(AaM-oXXdG9eT^X6msMZ4BW8Q|ECA@b}Opb?^Q
zIGSGer^No5k(;g=b3<UAO(XtdLCOa%*%sKv*Vuwy)x3r~-_~LsUYFpW2#iZFK4bV)
z+}skYKKDIW)?ZGGM<|!IiRMzg=)8tZ4DiBSC>nU5sVhHz9sIGU;#`iLr(?TC{3t8-
zS&^*YNXzN(f}%{K$?F0I=dyAdjTKoWEkB7<BfDc5;-`gkrOsRG>yRm|eLPmJbga&4
z9^jK(mB~l3sup6{#sKD{h_`Dhb*;Kxt%syYGjPy-m<k4tsk{<oL87W$Faww}G2YBZ
z$78@TALo9*N(&#?`|X<>cU6H(NZOp4l-{|jT)x-%hznwE3~x|;onZD^-2m+Qlcx!W
z%<<{UVES=9kRcUO`+WgO!ml7}{-_1g)StMgQS}J?)KBH;d-_l&c*xrMBsmISss;m(
z#sqvSd?5qL(@cPv_HzNefmc>tZ~xn@Pq)n3f5HmRWgax!=^=_&Ui=h>*&YEFWbU~+
z^0pK;3xI!15a+6xa~6iLvp0~%n{WP8v*QIE2x89-uyLy2OX40llfEj*_rcN>(Vdch
z{}04bNB$uA=wk=~oTeOMuFI!<x!wxt=UK8ReyP(uH&zUYRIFWaoLJ&lJZdBXa+RM@
z#4Zc&4N}dPzg8gyoJNc_W<K#Swv1g*_*biJFIhvZ+o3wl(V;_R@Q&z+qYcf2teLPY
zrH{O0)Kcm^Oe{f$II!=ItIJsp2@OsRQi73}R{iY4>iWzJN{g4w-*$w*(6Y<Hj|?Ao
zUhXWCqYB}%4W4vL<Zl=T62?6zQUv~iV1$1)ca+<+cchD4c+@v1S+E@Kv1oq#>L9qc
z1I`Rfn-DiM-K9HeyGLhaxxwUPf4;Taw{;+KzEl$_;=ij7CQ+uebpd5P<|GqZ6Qc;Q
z{Ysm=NdCofVT0|b^liO?m61nB$j1YntroRgM1#5R#TYhEl?LAC@LuaK>-5yx6WE=K
z#nA4K=(EqXAobEbv|tqM`3maA*>kDylQ`0&fqvgLr2D2vVL<f6-(;NI6)lmgpfLU&
zztcdjprfG!myz6=$tT|KacODSXdm!0X-m{k#M2l;As5qD=WY30OX%sY%diw@Em>Fx
z1ZmfLXLDYo?e6XbjFhYj-iBg!QU&k2268l`P4*O=J2|mRc4QS_oCYhi@sixBdR>yA
z(ycaZAzMpBKZ~n82%p&u<hdSxHD3H&Dg_aWt*4x`x(c1Ds$b1ZA8Imw{ryw(?%zXX
zs|c31H_4r63`}jgOi<pCL2XF7Z#F>`a{agICg?Tco!|WA*A@f(*VwFTZHK~wM*#Q2
zIEr&8na>Q|c2yB3F7G$?PN9j5NTLqNc@QV5Ay%9g*=mf0Z#Bl`mGDR_vVyl7!V}l3
z43x+fOk0!G*F|mkzQ6l}g(@$?XYLm|z4A5jcUNZlK0)XhHJkUN?4UIVRr5kud+y_;
zxH0puaj)zBgpg$~#CBsrJlaQNauw3$PXJI}AafaMlR1gzTsI!2gc^$dK{S{vt_b{X
zsC0f#lm=<n4qG6iO(rNk*)H(nI*w~UKgK@`0_%`@FythSDQ04sDloNk$7H&|&~oqI
z-O6j>u{0fXd5-pNES1u`D_Rn#;rdOut;@`O;f03s58m1RvDSFKx*X%<s!5~$oK`ag
z`0>ZQx+Wk#_9cJ!F-4}P+saa<cr9CuAGhMm?Bw`kz-EYB*wZ;Udq~gcXfuJJuH+<H
znE<-fugsE|jd}GmfKNwl6=+)1GY7AfiD%0pJ{!ps#RB}_)=apU3{m&{*sB%i^xyK(
z6;UvUJJuJxU@bQ}<!TU^@`>MCX*Ec1Y{I)*D={Y9ZN6#4lR4iy^7~#0>b4K=1@^ph
zu+P0F4@@m$Lu@e?t`NwQGuPXx16^I{S5@<^`f%5avhiZ~HbT6X|I%bAt8i$S!@4m~
z^-3Cp*$j^5(eNm<wRd#~c6q8A=yU>rMGhQ^SVdYQ)yI7~5f;FerG`gFw*JerGgPzk
zPUz*}xHAgpewcZduh4IzLW%LXF!8ROm{v%(PA!L0b3j=6oQaXuQ07=o$M9Bv#@mqv
z;!(<lyZh_{2=Lnp{odvgAcglX?qPbuimsXZ?-teIBVFdMRPd<q(SbJpr|eIzJBb&?
zHkOR_(kLA=El;!FC*u1)I;m~m`0CQ1GVnR#k2gq^-DtWZ<ro44+a#y&e#W5w%L{I1
z6SMII?A5(vss}BvC`<rl|G}$R#hpN5f-onQ7pQ*aTC(v&f9|~|dE*o;*piuXqSy@_
zM{;>^tlPn#t9QzDN=Tu+T5nB${2wUQXC{a4ZsjSiIkEHsAUfOkfrowmu+H@X=4!AN
z2=u@H$1MdL7N3bI*U+$o2A$s`3(T(?l^{oSS#`B|D}Ck*QzG5w<REX-+~)+Z9bU$9
z#d_Cy;*Cpe=G*U4=cM8^aba0nB=J_Tn)uAU|MKv&{;E1+fx<$C#k2It6T?Uzh3k5@
ztorRqLX$8?O^G~R57g6u@SE4V`Z@Ara6MG!>iL(C+pz}OY<)k3jTi@h5BQp8I9aij
z*c<FB>K8H?<ND627_1tK5fl1mHA*C#CS|u4NWh)x9&<M~y!bitUFqrz25ZcaOcC17
z)qQ-R`lc=?msaE|fybjvJLf~cgv~f=+=ldJ#dm9Q@=F;hLDg8JXTxIUYF!yEN&cO{
zvkQJv7)SMsynb9tT^KGwpDi_1cBbyCYTjq^Oat7(e9gJ?ed{9yZJFy(Nwi+;wR@fc
zFJ6yJzNzBP)O{ffZO@(Emu4M0*F&yy$Husq5FcKuXH}WtEUg7mr5|61zsCE-_~)O^
zgW_cb<wD(6pUVMC1h9-fr${&87)CAK$UKNFrzz;Ry$1N2(=0E1ii+wu+-52s`2a41
zFnZgU9xTjXlHLC70_8W;&3BTDFAOJnVk(_6=3FOD=icUg`ilubT^KRKSw1bT*doj2
zPXA2#$OvMWpbmbW1!`}a?kg3xRNQ#Pc}BC$mSbH;WIJ%admV+E%W9T(cZ}YV5_)O%
z&4*8oV&Qo%gi)C8a_6g|zPC+vz1WE^Z*?z|=k|m_dquvl55almTvr=eXR7o&eeE~;
z3it)7S6{KeD)zwRIzp|D6iGB5Ue>74rsf1s?CPgGM#4(CN6!GmsJn{vl=HgvzggxT
z5$_$?$<Oa93Xp+gEW4e=O418nxDcO`&A0D{X~Fr`h3Y%-O2=^8cxFrgyWLzb=I=cA
zUtf}2yeIKN<#{EuDRRs;S2-6pH^#oC!2GURqFvZ5J1PG*Javzn@Y9L-5=nkU0P|n9
zC*RLcZd5VPif!a@FcGLJBy)+lq3<%VNa)iJxCA^3`y6Fu0ji2m{`BZnf==Ck0B$jp
znQ7R#)IQDej`5}5s=lBRxx>-T3{pdm<6+M2q(pM2(`v0UYHy6esOS!P21G+F`G>r@
z=aFB1uY>!QBS%*&Dbn>V&ozgq<TR^hLyT@v=#8UznZ>uv&NB)c6x~iMw|48i8fPY1
zpOnumm8{;p%+k9bM{EynW_hAXxa#Kjrdr3m6BDnDniM#u3e!MXT0Dw94Hl?sc$<Zc
zyAC<~xX&fQAh~(94z~iG5Bw|tqhtS<a}MckFxGihia4d=U4_Dxj8f#A72&8oN(^iK
zvlVNG)b72kz!!Rhs74Q!mklNjmg+C9+8AqMXrCeMEbE>MAl<}D8b=hnq@mm;de&Hq
z7h__|A&ATU)`vTMRl{8awg+AmirwNT+C-mSpa$=LDTrLZ&iKxzK=+|+$mmpuXjmL*
zl_y#85Ft-_srVkIL4U2P+9RD?sVVg8IKXr>U#6X@i%nWOExw}D<Es^uaJP_IulOZO
zC#$hde51r=w+`Ino+pqrD)I{t00a=#QP-S{qFYVe^Z&vFGZ$M2r0O&jEqGF?nJe#$
zC$Qo-Y^x<R|AF+@Kl9-A<Y&~G^-aHVe+K<h(tegagJCc5HeO5pv>le_ap+wlJPsRO
z^;gs8|9gx4S}ptt#!<~f)Ucx(zvg;q`*;v`)2%R9`Cu6sS{gGgcnsKL@oaa+DmbYL
zaK{}WU6rnMF_&V7{B9FdfmkuFDvc2bmm*bPsN(Fvnd34V;A#Q7;UaU_JFZd?Y0C_2
z+lRZoH*V$$YJx@|H-LC4zge9D;bYrSI`^mtVm&k>czxzMbY_X4E(QWpI`ze_eY6hy
zCGZBDg1RR*ZQk$Z+P$VZ=+0Nzx2dgp<K=LAS@Im_VmBgpQF5(ElTXlxqGrWe(IzXi
zF?RnXnALKMqH_h32p)XI37!iS=jmr~<rI+O&IEIawn`;SFg!&16tl%tcq=Dn_B|CJ
zdrwIwAYsn2;;#PGq0gOG3p-4zi(5yv(Uw1*!!;_Gj}7e}DBYS*^tT%A9uw6@{FMa<
zV(>FweW7s1lfssFKwbf*O7QWI!^O>9jNQkeo=VbX*9n;NXLEv=L>hR43AW2|0ek)L
zUnMU?m5qF@GRS4DFeFn&XDe3+x?X!tpOc$1*)+bYpDpJ+P5HwWl87PijvsND4Q-Bk
zbvw`as70(q;nRW{xzDVv)hjL?iNF(mZPC)!Msfr1Yn5geh(T?Wk41X|^1$e3g?l4T
z@Z>Epy=WX5@BC;xRH~0BttalRJ{wftFIu}w9`XqBbe3xHZTQv&MQX+SZT#uBCK6?(
z$f1nh>p}7KvI&l2r@beKve!_7jVNRzrv(jRQ&ZCZl30tSlLW(MfknCzOQ$+;ZO*Kk
z%^6g&{^Ye&sz4j?4<tHEA7@KNDYE|(uCH<0qK&V5#!$GL`!#-`EJ=weGTuyzSk^TB
zr|aIU<n>Y?tGm2EML46H$vGU`%GjYts$jaDso2suSO*B|LS6pa#NRgZY3+n~rIJ&L
zWW75;VxjFIpGIAOKaJ8waGu7@s0ngN5`fy{ux<<Y3?|DTm-j$4wM8n8MPsHBBr6ov
z5`nD~6fuh(Vi`;EH%$QjDK|3%XK3sLRaI5)Y%rG&|B8vORhZ$hPDa`tcfHZEqzl(G
z_Ei?gyVIzOR>`cw=c@dRkKn;-=T@1Y7_C1_g6x=EMcckC^(XV=2uQ(<dvgQdO^Xb~
zjm7i?=QfVoxm<hl3V@4!us@H)hTt3+#YY@5@Z|p`$X(^Bc}jP_vKz0g;Z?+{@zVNQ
zw<rncNL{yQoGb7Y$Q#gNOJ_+5>Nmu#y|aJ*yfTp?7<aBtIEnWwy_ZOSF0lZ<luwqH
z`p+D*s%Wxjj5kqfORwpd%!^-<5q&t4|2RVXadn)lLt`!mh`*?%^g0iUv-3!YoK4{z
zQdZd3EfT)bVS+o!Fjtq?(+5L}y^riXm|wa0I8*1Za!L-b%W&#frF=+c2(qzn(*aw+
zAr4x#q#}cTd27js4XfR#hk`%|Y+Ez(v62?wlHd|wj&HI|TwAXV!;*JA=&qoVpG9VI
zVoy(+Vz%n&OBPSYUG=!4Xt8hQUXQ2zcDMt)Mb9BHIVxgzx>(oWZP4P|P>@cZ@i*|c
zetgpszHQjvTy^iF<XdTv1J^mOdLa5H;%Fx3)eB=~84u0#sM^FWccZQMoV9d9%7U0N
zqv-x68ybnzlPG@tn;%(;rd5I{DLM}ihW`0GJLA7<7a~U20D#clgK4P2zi@e0tgkp-
zg69^0N~i=z`_clEo2mfT#V`r8co16T7;Gw?k?gm~=&POn4OwdQt&S1z^-v8vYSZnS
zm$6xE!xhk|y)v5nisHF{&;CiKhvd)EW@`7y48xpntCdI0u~R{L-ZvtP7x(9CAFb$U
zq@%b31^1HzQm{DV7IF@g{}`kaw{&YG`phaql1t`$E=4ZGw8U8b)j&p%f-(AyQikHp
zLWrkf62754tpzNr6|TI4A$TFE62oeypwHn9s(|b=^D5J;Ps2BMrh@Gw?+9R3U8JaR
zS^)6fo?ef-Hqq_YmIgJdU*i1cc4LWjtAP@H(x-^LUeA-u$5tBrCEQGJSKE@>LMSk}
z6>_9yCcK8C7lX?*N8}uTN46!(7?~yxf0FE#f|0MZ?xKN6HC5(_7sJ4$cKWW-c>_6H
zMoKb15=wVN)elnIWAG<xgr+w9Np#1oN)Uu^8~Vk)oWy0K_TP^1O&eqX(Z+NX-npix
ziuzd%G;MAn2?>f`0KR1DRU(8PV|emL5wkx@+B1GKWH(j+$W!S4N%9!${cZ3?%p^1Y
z3StD-Lkv=x<QoFei<#oZ&VzRl<8*RocjS$Vd97If1HAUqqPP0eu`oj=Kxm-Dh5B1m
zO3DOwQ;WaKD!lH#{z461^GOU|5<7Srk1ie)K5QGGCgQ`KYY#b1nOqBCp26j8pQ?0?
z#7j32eUf@faXUAM`Yj9>LO$qiAdKtNo?4Z(k6A85@02UK7@bRX0aHrBqLu4gRqBg}
zV=N+!+s87H!)koht?NRDFWi(mA0Zv7T^r<BEGiB!jaK|AxWe8H;HCpZ8!Y5S$pbP;
zfY%*Z%4vF5mbVuD0OxMSzZTGmNhJ;g1DVF23A2k!U7g{6E|!_;_C?`fG7|KPR_$<z
z*spx#?Zm5S=-Dty|GqnI>rfccqa9`IBrNf$NvB=5bJYj1K^MwZ*JTe*Gj-3Ucn7Oo
zo#`-N(F;Z`!JZvoKawlJlZ4H5{4aDvaFWBp|NQbH?8#lJ!yXc?8@P+{RRZ)nflM!+
zFr-sK<Y1Ua#+Fv`kv0F1B!9}!sI8Bv6c+xY2UHw!<0J1>A=BHNLD4&d8=ssXqRZCD
zhVJ`;uM-4Myc>E>XkSa>iK6hCdoU@SfV$rSSmcX~X-v^6sMay*3pHzkh8GI|W&CIu
z4>C`rvwSWrwxC(EeO|v?i~prAE%!=a$;wR+UCzfsCOBe(m82kYtHwI`V)%EVByd}P
zTAUObf4GH~=q}R4E|Bdyy$bTD-mI)kXdaWQBmrik2c<@vzd9}Ii80fsnh(s3ukEd9
z7u~g)2ur-bH|ktymp`%523~YG^thVyG2?X&^Mqriy3le=z|HGrLM&i(?fH1xgM^!(
zL%R2+ZJH2ryCYdD1s*L=o`BBNiH1z22qgkBX?d@ra0zSUFFgxcN(5y~NGO}%_ySUs
z_qnk=u2;S*zD-=?F^1XppZrzx?tO5X2=MV*I51f%s<eoxrBSlgJQ36*RB%bJ|8`oT
zy<3Q5T`m0JKc$KcK?&o!I}GxNH_J0OsFroQ`+_i8^U|amKeyN)Qmh!se33LH)wFvv
zT}vcf;gJO?crDW+>+)>`$W7lYxj&~P9C1CYn@Y_Dk9h%bp%u5O*)yo;U2{7}39bo3
z+2-?K<nr?Gf)Z0Ev0INtU?=hde+(Vk+|}fmw}KX9xe4<wh&8uEbxT={YLSaZh<Sxd
z9*fed=23su42+K1+5^<JU#7)`XEJm=fub<%Pv8@3aE%3fp5XU4)P_bkf|$m9bDh`U
zaKWpUFAa690Q|-f@HmGnTIv%YynrsER(1-By~9Rtd^q=IXC`c)TsBQl?_c0Hsaos}
z0|5jP!AC;o#AVBsKAa^ygRr|$*c~4CV$u^KeusgVs4Pu)Fsw;NsuxElYRz=uQSk?t
zmjxt$N(A8mdcBm~To8<*@Gh+fv!6y@DDFRRkA#i5e+WoKT$a(m9DG~-HRHd4Z#2v!
ztkG1+xT60^W4A_3&E8qz)6NEVE4@m?`?wzg+FeJL7AYp!?Z@gV%urEw!?x8~!C^L$
z)gmdaIsP&wO2fB0B*ve?3{eewOIhLl)DmFD`Tr;B3!{2Z+1uxDC~DCVf*9n-_BT+S
z*54Vxi;Xb8D$3`VWoZWm9H^@LOn+MSIOnC3>YYv=Cr)jiPVfm<_ui3b(4U@sbgzbG
zM)F+d<9+APfXIKK`F!55Kq@3o&<v}G(8@~k=-lEZp>qAWA)znir+JZJw6jQTNLLH;
z-krk6cJWtD&B|=00<B__0<S;UJRR5lcCT+WNZZ#U^0{L>2mM=?%L;_qYEJR#gxg<W
zgEM7g8=`Nla`>7}4m-s!6XFkKD8>>7C<$YHN8%5ZMYi}_tIeS&Bk=!mbd^z2b!~KL
zB}M5*kW!Q`fuT#fOG$~5?jDd7fuUnWLSSg5Q&Lhor8}ghh8Skv@A~~>Ef#QxbI&<X
z?EUPGj&s?h55G#CCZ;-A6K-OwQ`Ow0nN#WX`89nOAPdO@K&jAcK#OLs6qgT565q^J
zae2m|=2uq-&;v@%AIwp}BB=;N>Rn{ObBh=vS-4oor6D&ASwj6c>?`ua(E|kk8xAEG
z=K%y;p(r`5J&?1;7-&3O=={;ySo%XPOomL!p;8$5R)qcR0@&3V!*!T#p~$2J;>EDL
z5{rEu5;?uDWPo;2+lhwwwenu@x7i`%CU8O{!<f(bqyZVO7*X<fA-r#pFu|RrfIzp*
z0=!yW>WF|O73)-(<kBxKl$IuW0jaaHrf8F?LxRQaMRu-l@q=Bd7tGS<I_?jV??dp?
z8l_B1&M65-ooxo1OVer9tSVU9eSAyvYW;0#YU>ODyAmN1s*0%vgP=8Ddc^z~<n<8M
zt7d~IQs&;Jm_8x*>>*bg44{raS7yGjJjzL({>(iN2M#K{=AlM=IjzPv5ackQE{hFZ
zKZ(t{L`u>x1>JE9P1`iV8kM9!jnd=L@0Ku_j}Ls)rPX$O`I2lMPi(%Q;66nB?ip)s
z6W|_e&ioB-jm5Dka7`a9uOCa<aj-1DKYXD<HTR2uca`~Cx6sT?Z}!xf2|x@8Wti>l
zm=E6HW%RK$fkK_Pz^AIZL}u1lk5&Z$VN^w_isRgH`{yv^YAA~_n=W|bm|#xLf}0=4
zF{=DqSYUpM6dv#$H7Z*lBT7Y8a4=*3KrR)>snIfkkWRs(-4jB;uNx67vbi_}UH1}-
z?euw#cg?F}`^FuBSu%#9-4Lag7@qG-41rH|kfG9-jh2A=^C(wG1lbL`$q=aqf{cT3
zrA9aI6repBqlzdPl;x8D-%Odt9TT+vNy4xC?o!rui_!6KvH6cn4g0Nty^Eh+O>HSX
z9H3l!3t?{B3J>%huvh_pr_7<MH;!=B@8-BETs5qSu}=O`U;5V4NPu#>-%R*>!d(0D
z%RI@ClDE3Ssue@q+$qSwVpo~onK;#C6ZX|cw<ibh!YEFGmTqGpbWI#%U~s~ovLm6<
z&3sB(TrrJ{<(0v-RD$jLa$Dpvqm*)sI0CP2Wd!bbM+a%>mwx-0CGfr{iaLJSQKSI9
zO98<}xsVIEzL@cqD(!G*fI4=$uR!?VapBCiwL0@p)M^fhCWWqmxkD_4u5)1}ad20*
z_HiO~)5c91n8>>-Q-tYBwvWOCoM{me9o=gs-8Wo$gvWI_q8TFuXu-ofU4O%3PSN8d
z^3I+jhZ9oprc*ehCY~s%pTuGa4Fa2ncL`&>mW%qM7x{zz%-J1qun)i`Zz3?xszWb+
zSTe(b9lsfqqM5+KjI|qSc?7?`Ks$zv^tu=Kx}$G-$ZD4aZP(sa13DK)pP6ibc-~Cl
z_Kbd7b^_=?)IiwPjrkg)<7frbSSZ`=?*%9Z{Y*znP*a1tT5TUkPtg|erXz9flms!m
z4;y2XySgYTwe<VsTo=b7dx(;mx`FiNg}v*n*F4$G6gFimln+|e1zvdvxycmr6A(yR
zCbXrR#J}a`)roF@mz1v(bscGj-jJcuTkbebzDf)BE1BDnxow~wpCJ2N-b9x1BHp0@
z-5P!TT6T0a6MS?bL$Qc_)EBbm=l%z{BjUeThTDwI*h)n$Hvg{Kh9b;j>2(PU-ft_Q
zh^Mhb+ZsK?@W1sUu>m7{0;+&8r1L`Qk}f031<(NZ=Ehqe3;FFk?)n@E*NUNWD&epr
zRA>IFE_UrJI?3om+4j%Ohk#zWAckVvFSGyf2->O$(yacaHB``FfG)<)t~M{d^*Vfi
zEnwg-DXV`=J*KQlmpEc8j>4M+5-96LYV3C`w@yd0jMx9Rykxsf4m<$0J!|#R6a9tt
z+NW5cMx4$=6g3))uc>?HrjC?B>AJK4d&%t8B=qizR!)2O*9?lfq*1N1FESbScI%!y
zj6d06qalI_vm+Y7)Y=;Xt;OSO7}UlE#4C>h;Tzlxo)!TUQoy6zP{o}1KriQ>6JUlE
z7$4KRBM$*$iI>ftHpdqn@7Xd8#fHa*e@6sq7Ix?(-aPQ(_oct!4Lya%(WjgA(ST@B
zwm#Sa$nO)A1KeYSo<yZ`cO+|BrW%vjB|M?EU{$#+Gx9-(@1j^dwB$bMa_Op66V>1(
zL)u4UCB%oZu8OR(SS{I@7xJ~CfkmQDZ1he5qp8cmlQ22VCCjK;iS457$eJVtZ;lM5
zR0>Qh8(XCJ&p>}T?(aqpHr5d=pXuXtX;S?<8*c&6W!OGTI2NA2Yvitfdb;@1$l<wd
zN1m|QvIv&rv694@fi=u$9j+Uyd<Mv?`SdI0IwuCe4Y6%}@;rU9VGynQ?`T}=gKt?o
zD%79Ngr)uh_+sQs<@=gCrk#J09<=u(Zc8FN6k1#VahFfvcN6b^YN3v2+vx)5#BTPQ
zBj)+AIkZKFyx|hK@!tC9S~}t#DI{uaFs)Bq1T}v^c{9y2pInTU-V$1>yI29TAfn0>
zyI+uh1S9I2Z4S%;%9KtL4Gm^0gZZeWNRRp+V=js+l_8_1zr~Cu-JbNM4h~?fboN#{
z?`9$tS^ooB_^4c}NtRI92Tunwfs0fK>)rs^VQ<HZ`@ug>hg;4@hkjiHD4+>=v2eDg
zQ^s!T?FrV;C3V@T6va^gzzR>wY@6TSg5#~S*LgrFvu}Tu0gz>>PCXp4S(tev{7*b%
z<vA`Ew&-oyVQR49tQOvI!(-9!`mvHo0*>VMX6O9GU<X?L`r)|?%Yh=k4Dk6aD^q!F
zX2A&oKh<?1hvMKGsdVZ@40egrm$oR*I=xtqqlVcvsZg=fh!oFH>r5!eRi}uHKpLb0
z;%UdAO818zGIJc2zku3O2F-DjVZ=PA_btE&aMZtQ&j#4|iImBY_`mpTY6YYWMuX3`
zM}h@)t);K^Y5?6B;9RO(5#INFh)Y6G%aBpUs(=@|NHeXuC6kN6RuQCoJ`O8S?00{-
zND#UktI$MkF<lztCl61}t^M81K(pTRnPHvGwEZK~Wsk^i@yacgg3mVB{{z)K(EK)%
z3|S8*5fUuEZ)~vmF3j5C)_Jx~*67HD9ll!|0mxdcdX?cHHfv2fB7DcB=d+L$BNW@F
zW`vSMVYgOI%%&i{=h=4mux|i2MAbm~K4cl($c>vp9AH+-oxBbmcKByE^<;zq^X~Kk
zQU+Y4pw<HZ(FTC)h&2ytj*}MwAnyM_4wl8iiy>ZE&x%hwv|g%{9&4sA4O;uu+<9sX
zPYK*NWrA1rMonws4}aS)zS9*GFMOT$hD~(z1Lu|ozv6HuLiKpH9`TW{us}t*SZxGa
zvwfPrp8HObpCGY4q&Mq`L{gb+-yS4=8e0Vv=tSpV0G?h)ys+uAJ-2(VrUSWiy4AJw
z`u#gNo##NBlQg1i6MI3Vt}!qTJXa`77gpPE?lYhU0v0lXY$0QrPDvSu!x#(Ur2fe1
zA!nU#<f8OjDbOWA1!_5Tr(yidEg$Iwbx_Lbf#c**Ykg+gEfRQ(+he>GhWQT!Y}Qb^
z3j}zZ9Uy<=mHb#&!9EAxLl;Ej8hUXG=`<WA5x%x<WLEkYeX1Y1$`5Oa-*f8^{2pm_
znWrtCS(5<pp+<{JwU2+H!+p)*lL<WWr=NW`n=<bmh+ONT1<N_h*#=om9=*Y}k_q))
z>`tzo15VbNkCI&cQN)!?DdUH7F#``RyS7?N<5-e4^Y;fSrWu=AMDn?jTe(xAERV`P
z(V2qBdX@F_SWZvPeb;0^axkA=d4_sMn%bw~lXCoETk{5qnXbO1F<C0T4oUM_aHR>k
z><SAe{Qy2f?s$GqCNtlrOM6;RuPyJk?(;NpSWo`>*TJ)pH2tL&`&U9@Otbk8H;aiT
zWyKzQ42E&7e$Beyw<9t8LK8I19e-RlO>IOTu7tF85>7NvT86!0*Qq&7Sc}x5I;oIb
zVwH}pQCI)$@wM<kDv(gl=8rc4vlh@EF%g-Dj{m^H;AuQk2k)fS{9hd?Gd5vvtuK&&
zz>N!kobAbS)1HyK-jnOf?)yI|$$8GPCV~YA>^u~cxTwPQ_T;WHEK}ZRb@{@O_|?6U
z575r&V|}oUZj}rqv@{^G<x`B<zN6Dc9)}9GkWEus_J`j8-pf_jb^1(z;n2%<F1Y8y
zZssBwF8Dq<SX`K#@Z?P>8NeW$D|$-ldi5I@6$@$_S_Qu9SW<hfd)m85)oCeb0_U-^
z6*Uv+{MnLsh!Y;53=%(g(Q4EHaf?2mbnXu>xp)PQdgHFy`(oKdeP9NzNBm)Eng*z+
ztgzZSInK#%^cY>}tMXz6=k+r|?g)jBJ&K;O;?FcSe@H-bBl|#=rFTh_Cv8Tc_q8Lc
zn8TjNOpN-#@v-=ik<4Qtra4UDsx>Bb38M$uN(kUhAG|+6B<mfQvUj2!+o}jD1<l9?
z8kAcNP)$C60ObzB{DfEhq9B6V8WUerb3OGD?bpomOH<{_ZoW7oh`9Eyex7?lnZvYZ
z@vT(a{F*F{_rxw;i-P3nMXlN{BaCbXL1`ak#WahebMcvsgr%p+E2LlU-b_`17iYNI
zIuQe2BT(F5{?X*uI)6g@=7I8zfuS?_rs|~TfM%xb&Uj$lZ|`8H*VGtco?H9xIx8M`
zy|s79BP@9~omSh}RG3qEr%PK2yKAFQCqQ*>$b1egBKe41y`h+X{vCgFEf?u-F!_x$
zo+;?Ab|yklL@9M8paG=1*K!-O@EC=MXzzjDLe1}Z<wB<LXQ#q&Iw{s)i6l0X+plI4
zzI+siZU;&XJpmhzlZ^|^D8G@;siO<%YG0H8;8p*y7h}y-DD_yF(Ow`dh>*(6$Gks7
z<46{9OZ_Xvk;T+E1zOMCWR{P7mm2EM|9!1KtNl~ah-FZ#ZSJQMby4+B=}IP}2}1Yy
zu-hva&~YChb92oA(t7)vBhAo&xveHb^qpxQpA0^<f!(!;>*GWy-Q6a@{(SnG$$9F&
ze-6*p2O+#NA<n;q@-0#9$j&=S-v4xXK_@*>Oj`4{`mldXg#g`nlR$@eM;PQwjk-V%
z4zw%qUUq+M6s(qNq)RkiNIKuw)M}l;Z)hyV=`H!qy4FT2ix}T&z7>7)Tlfp(4>!ii
zeRI?$WdPBaEPBX%g?!5^6+&nF0>L5w7ax`_^`*UG;vLOCmu$>aO{R~2UdOfI<UrE;
zYQK?juyacFfoylX=R=Tx_OhuYCoHshVJ~;uJt`oEqA|VxJ_k}u6w~fL)TdoiN)o|5
zRX7Hf1Y?c5_RH28d^Q-_5v_cdsTbE8*HxR^0ifpM;G*f*SHxs861q-uQI<tUs`Oee
zTow)3YWru!HNw=3I)%6gT20eW({@xTuzbal6vUaI_i(Nsy=pv3BagaaPUG#qmg2#-
z>Q}#JN7V>LS`wU^H%$vY$UVA_!{2M7E#}QG^KS{YpDGJ`-1KN!bl1`7bi=7odfQ!w
zT127*AH$E?qsXxhj0x8N=-)NKTqL`b?A9oG$CUbsA@BIDxbk-^nW14bek*k0NI>#~
zl95Ip|JLS2)T<l)kFQ6t8{J4(Jk_4g1l&>`%8+N&dEmb^lMan_Ih2M@o{$Fnmt(JK
zJLN8iC-7^cq!HBkn=8sC-`4e?J7#}*Xz@o-mn2U5Ei0^zkK*EkAJBberRnDm84v@D
zRFnXX-nao)Hac_JHiq47s!Ql_Wb@s>>?rBjirDv%Hps^ca94kkX{TYR%0Etmp{Std
zG@7LhQ>d2<Oc^z6O1~e%Bne>!Q_NW`2#wetP?Pohfzc4Fa5XtW_S1y0l4|q)x}@G=
zn08Mtu|4?k{^y?$xlsrGY%yC|9p$a{l~)nExIR<dn2T6of@DXWz8P6sVD5$}>sfPn
zFWw(`r(fG&V`ZIKM~a9L*c&P1kF{(`(i#aHXrd$>F_boba;ihSy%Glugj3@!N49)2
zIxFU#L-tc@x$)pSG80v&?8icr1W5WhX;0PdBGiup4Dx<>4ByOg!wqQkU=aQEca<qO
z6Zi!Rg6CkNou;I^3oMgi*6XWXm{jP&0#e9W@pC3Zh7jM5DVh@NBG%53dmJPxG%Z<N
zzIUjtmOnl^csR-)rICii_N-mC$azfMwdb2MQCQsce3ZFY8TrG=ZK+=gT{HWS^R^!=
z${2J@V)U^`#Mt2SytlEPrfx}E?gpC;py;4%uiNIbi{Tfq&inc$rpbM@R-asuYo}Vy
zbA}xn7~Xz%6Ig-#l58WYeFR?I41J+A9yis-y=gNrmuJ??+?^XVQxj8V=9>H#mN&*l
zMB!3VS!g)l{qXV--jmi>ZrRK>1K)pH;dI}_9+%FProInc;J4zJ?0UO3FP{<lKem0W
zvdJd}acx{c&p5AMLL_vDT#TUU5_@98!y1my3gc_#cKpGj6x@d;*_y@2X1}-HVQN-s
zG5wp0o{iTh@ijM0Uq~GLyt1*4eRn>*x09ckH0)xyq98TRi=T~V<gpMW8akZDF8Pv-
zr3NAAY!{O@t8ySpc=zM76lbrP5-UX<r$KOpWs9QM#JOcR<zWJZWue$M0HYsj9yTr1
z<3G5W`_Tw=RqSuPAB)dtTe_Q=P7;Tq<QU^qL8RSAX};FRK6P&Q;3C#);LGuo)SIxc
zQW=2AQ~Q`@(<#S4?AFOGlCoj<!a3BM2bDV6>U7gsD%eQz3@<7T%86@A#2T;$YLEF7
ziVb+`*$sG9<+}1-_SrnM(u;O(m|2*A@g_90TtuXCQh9qxvCj2x!fqAUQa9jr`p$)o
zoSP|<&OM<(My!iL-zBJKW;Tjm{xM(hp}?;13puQMh9~eXi3cYxjfq6Q75nzqA-a&)
z`;ryk?nho5I^Dq+@_b(x9u<7;G;LPeZZYnBQO;ntyVY7M3I7%RW-Nu-8{8J#-`t*j
zVm-3VbVZYEeMGyp+7vJNaHgfi{Ed6Mi*y5Y>=X4fPh-AcBc!WR2UC*CqN!zlupq<F
z^7Ijz{sR2ELLbGVZ*)~%{@VEWseEdc_D5F!xmVD#W^M>7W)nheJ-=4Dhgg@QC;M1=
z2v|Z47Ho31@jVEh!(A7Zug&1qgpc&G;F1jlCF2cP?jP4}P8x*2CWuMSjIEPx02wjl
zjp|11#ycm<%Tj070;8YW&e=mkGO&|s^oL6Lx`2~Pfx+?l9B*S2g2K3)Q0hZT!&_41
zvh>anjab0$mx!;UMgrocUz<esaQ^V?NX_<C%{Nv{J%{Q}Ui$06Y0o$<uG0G7Ewooe
z$V<zeiys;{Fh#|xcO*kz6a-nmYNE{YrQG%<@Ngj(;Ct@*v$Zr0{<?XZP}=Cw$eRd7
z6VRHSAjP#Uzia<6(CzHyuF^oB@YuVR^xIDx!6XhhuwJTj6$LhosWXEOeAC4nhwYIB
zQzjyh)G0-~P0=E)?$|^_1UaTvq}F))+BMN$>fn;j0X16Z$WZB&XS=Om`?!An+us$l
z4&dL4dR`PqTuMVA-SF<$C}p(Hp_$C1yr<bn?4}5(xGyaRHeccggmx|jz**%iZ47u$
zXo=aF4QmOHV0=h~JvLf-2e6J&U;6a4K7Gw<$Nx_M+j2EKFP~s9J@j+2nuzCWy<#2C
zAlsoX(K`v7eHq%14A<hNRHV-p%<ONpie4=Y0z7N`%Ia|_#J!2>DoBR1R(VfF$4C<E
z#F4lN>BUq(jqN*X?$C`nCL!=JqIgj9RCXdnzdz3BzHBd*AjGjEFQK!Dg$v*q+s9fF
z9bc9g;qmpWF!sISrucQI>m(JuVPwkN?ieY<pi66D!+tIjo0z7Plg4IyIV$MlnWXX{
zE>oOg#^nea5nHq4o?J+1^HTNpfe>*xvFri2k8R*g8_ianHbCK%t+qKy45=?trQJ4&
z|9Uo;SgaG)$4@DeyrRV2^KuWnVhe}))rJfkdvd2KsOst9f#ALhD<`AOox#U_^!C=&
z$6taOIA_4D>Vt4tyYj-P5Y3P@Fad!ZSk0rnW=qPyPyh#Oz|`Q=CrP^s=cR*?RR5ZR
z8DWqz(nIF8lGJ{(Y46WHi!S|s%QfF5b>0i|aGAJUr{9uT^)tNow3n3MhQ@sOuP;j$
zMY`xogSoK7>SZTDTvY2`L<0@)$i>CZ;i*f%l!Eea2tj$4I@2_FIy+%Y!huJ%HfWQf
z<5;}HB|l9^EQOa?TQD_`@81k2?FC6?2qvZ@Q<|_M`O^$MLJswMNV8{?EN^zz_2T1l
zeMgwCSo8^%AwFcL^-eUFr+ND$KVJ`Gm#yoqr0-o6O8GH=HKih?N55BVba<VjxheQb
zY!5qAb4}J1W*1$vv~Tc5D<bYZq~4r(Vds};f)t*us^Ie+_i@Od)joVVHngWn-F_`U
ztM;qTqBll#K7!J-<D78mm3mtSW{7J2SNR(o`O{H3p|1)+VIkHpHGX6GGV5EGqc`ot
z^^}AL!_DI&ODvamP<eVQ<pxVzKh|~}Lx^_)Q~Zvo{unqaQaxm%OJl^JBsZYJl}0kb
z=K{X+Rx<qS@U894qzN9&mD3d^MC92})?e2F@@&FfuRP-7srvL~u70u&&GW{DE8DE%
z(eBrPpwf~^z>^z;Yx$hrOzqO{@hzEHr`k)dpNA?`dh@Z>)-N88ks%x@j`Y&T08a_>
zLQT&La$Vf_>y3)S*(gGdl`$^tU#%sm`TS+RTf6%J1F7MhAJY%t1y0~CbDpV?&CJHI
zeA;Ffds>H6A|*y~<C4UDdVDuAz&MuwJ^^nll%P^C#Q?V3jb9hP-W>6*Mi&}eipbt*
z8s&%VCe6}59bOSS8UXXYw^%NZj}f(*F!)khxgK+x$i*ll9Oho3P#D8DZrKx2#jQfe
z`x*5!d|n@K;AyF<&&krl0<2xhzU$QJmyM^qn{ZA30eSb!o`-v4RhDX6;+w4`B##E^
zZ=yZ562%inUsjpO8W(g|<UTfAUS7DZD5F$n@vh`rRQlK5BGw6JfW3dY%i_#QS#OdJ
z6LGJHTMh{e{pwEe<ILfCtO1E(s_f@c-*&$<2=3J%^eEh|e5@Xg(`j1wgbop%KWYL?
zxGGdhvK9Xi#F1?#)VJY@(Ex4Zj6K(veacUgjVxt&?<Xg_na6N9oBFd@e19>MF+KTj
z0~|Y{_kMvAQIY$TID7`)J;~u(dlYZxu}yw#rgPg%GFiiJM54j&)tg%Dy!j&6Q<L5d
zWBgsZeihnsJN>b7l~V8og3oP-L&O06RAdz7xwAK~r}S4-!Dh{y=c9gHKNr@fvc(UZ
z?!#61g^C0P+r&$5j2>fQ1lzn`Y@|2^F=A?2TJSeItu&1gt4;g_Px6;wcM9efk@Cas
z9D^N(Q(_6Szw;^?;gPrns^frEx#;BSllu~Wn;+2!j#$(S6BpH6%ac2K;DZ@7MC0pU
zt+~)VC}Gl79=^3OZf1V>5riX|{MTo{-;0PI`^az%DnHGPq3=c;&s8vo5lkr0O+btD
zw{%fh9BYerKU}BzCvi^aiYW*-+Kn@sB0Z$WF@81@Qm%>hU{Jsw{Y#)L=-Ybkd!QFH
zfumlYC^{D0sMies$$dACqgk8@)PJv`{ka|L&~neKr=b*N88J&|!Y={`R3-qxX_hWp
ztoO}7JfeoewGFMW5GV|KnsqKn!5k3*3>)Wg*}Aqf_#uz=6sq%v{nY~P62~%o_2kFf
zsb~S^v83jblJ|-EJ-NO5n&&m$-URcypsjF8z}oeJ;fv*Hx8O)2c~*1(Yj)^AfY4``
z03AFq?MlJt^XE6Gbm{}eu&&KF;VH|zIjkX~4^6)<&foTR|7*o(TE6YwbnUm18GcH<
z$9!`!{Ufn?^HpD2amo`WYm%d5c$V{~Ua!w^82SJNO^;t(38~b?qGoBYLF(wlY#EFl
zdfz)Ne+H(ctp*yXu|0YAPV>ean5^x0Q@6=BOv`ui54M<wWz&VtT`~@8=&av=uYW}Y
z-}<ZeL0!z|*{W2kKG(9FEBJJk`<rIS&Q{8yifyHU2>z=F1BP9rqFkNbVDM^k=0mFy
zL0CBe73}NhL*a{hm}%92ura7v>e1N(JeQE5|5B^iG)K%?B2!1}`cq-LpYuh-F$TuL
zP5d>e-n>q!cmn=$^U64Lwz8A1n0IRgYt6pi>*om~xRkoGuMB1Vnb=cYXXrBqJN2iV
z49yF&dZio}nQm%HXmwV}{ds_fJIn!gqhm#C!k8dAM9^A<tEL%r*!i!EO!!#NGyMnj
z8}r}%tS@ZCKfvbJq0L|358YP5S}eJlXfvV1=7B@8=HydEu)atv3m5g5fF}S*vQ)x}
zhWT;{=;LaT{|Zly#^Akl;0Jbxr1O8EbyuKIRQPDGLd5?%Xv#(|^q_!aB+x}@pvUC}
z(ne}<RD6ohEu<%W)(AfhMABQG3#g3p0!{ezxu1XPJGtMz2kWa<+Y+#=MgOVq&!VnK
z0I#Tl;<O$&JzhpD7%(&eIAg$V`=q-n`<Q_InndnNzY=%3xD%I#Z09<=_5(f9U!<>K
zRXe457SifMqJ$A{Z_7S7FzNl^9UQnGrwsa@UX;DXR8O2h5&Mk8PzQ4+OwxC$CWkxb
zx6DKId3~e6%kXYiL7pvdoHGs{HDJXk+0WA=UTo~3y8AhU^Z6vrnW@j5s!Q8-Vf>P(
zyQ)<G7%pGZvVSTTJ8Xx``1siUz=Be>a&pP@r?vR_+Ncob%#F29J5Z?jo*UPZmi~*T
zGGm>Lv0K8J<W7Zt&ec;I0#)a6RH+I_%(+V?7;p6TXe5~^1iBpV&5!?Q;J%4V`F#xY
zzSc!z9PPh(ce|I4#1l48H$5@O02{?L3kjUQ+<1AW&j788P)7X3dg$%%qhJNUJe5N9
zs0=EB%Oo+pzYv4s*JPcyADp3I@&Q*;KWZ^|$J?@*lg9{6EilZhXrYCY(^!36Z!TMy
zPlt4A><*D!<EW`gH`eED43!bgf4KoWiK&$5(1A+e8VlP+IJ~51J4)~U57fZRXEL6B
zYsdp#6FQ-KnzW1a%<0J)0*9aFVTCOCSPwJgPVd579FCcu$;?b}si3&S(%i73P_G<a
zY5oV*ZL9wRPj^15pR?16nyH-rgU2@<K31WODgpO=jtqkvjNf@rUM^5Ui&PmN|5`h{
z4GAgH*N2Sk5kY-c|9t!|>vVj*-C=bwQ-zB}R)oGUP6Q^A`_pxHUfl=&0>t!(W0a;c
zv~oa<AH*xSUKsx@4S5Aa!#{^gC5!VSeR&T~;jRmEe_sIALRiCd6Il+jh3_<h!@%h*
zd@C_4E@9KzHb{1bz;&gtv^i>&K@F+I#D*9jJvl39(+Z2iPjewdxisg^|D*@a(fN&6
z<W6PANX}DNw7Lx-xDh9mV=pVE!+7ixXnsNq_F1^QyAegbJR;H4Hs+TkYU@Ur$+&Ey
zKH8(CiKZCY|3IqQ=%>Q&c44g+CS>nvH;YWj^`XT|_|T6MR@Pz77Pp50L-(XF7He=*
zO8X*5e|9&^DEF8seEhFs?!LNc40z{M8>|Anrz$)F<L~$W2QQ?Xi;Lj|blywQjw`-2
z)n(19)jlyH^w}?gxz-dijirC=n1^ly+f#o58jLPF`E20c4^W4iO;y<<aLENg8k~%O
z$^iIB_8OMpMR+I=Z~UIDV{sL@{n_gyQQ+2;X+YAJz7seiK)(H6WvZ^H@guC-NoeO1
zAE2gj@VyBHWSDom0(rJ);@<~M?wmT$1VoftB`8^SNJ+V)e=kGRj6ZyAcX7^uZL-BC
z*1%ubt)$Nyqu9OTsVJKuMt(?5XqrhnI@P_*IP6Fe4Jmjl8U59ix$GI=BY9Hr)_)-F
zdjJB8RC!Ur!rTCHB5R=}QfmuwhRB}8@(7=sG(jCL2Ep?TA*o$8$OoM*!1A5`yLgMC
zc0B|5bL(4k>IQZyLjeEjt4ZA-vKw6@2hbkMq!R~2f#u*RlK%-a4rC(`Elj(l<J?b-
zxg`!7Q6{%I&3txT3ZB`7&jEXlG|g|#2#BXs*k?^q(s*BiZw07B)eJ-ieI)}tz^JWz
zo^NIf%TQbAf$L>LJy*JH5`hu)zX+_2m;R#(2knw09S^sfaW)8fQ~qB1r?9z<V3<|$
z_c>q%!AutSZTq3Hf7ppO6+2yJHM7(v^R@nzNTrh!)qxANjgjA$rz^ZTY|WuKxKeI?
zc@Z1DfC$AecTGYa7F+_O2(1y%THZ{7mxUkB)by+Ydko8bN~Aa}JYeBc<raY#)gE2E
zaH@sSqa<5ONu#2UK=V8)<p;c*y`aayt2a%3+s1sAvCXV<0~i=_ymV`Iy4}x!V%i;+
z$O*%d4*GZ5vqau4$r^{qbgerFenXBHxKMYUb)b`Y9#IB$3NG`X#?u`9Eq#q+Ks&j7
z`p5v4ygbV+;P}O@wwWczm$AO{2Z*w!n|U?h1zy7!-IPcT5$P-Xs-oPhy8!gVvZH65
zUx=XP?W`sg(1G+EsUd&|@^I<+Gn0jGlitBMxb&2=L|L#;ENmq6)kEu?%`lJkxRv>S
zDB%n2wA3?n#VSf$SIClcwA4K1sHIR;Z2LeY3#p^=VVeQK3i`FG5uj>TurM+&Bvw(1
zxAJBL9wyyff}i(A(_0ki9`K0F<VylSXf6V7O*K}EUf{(S$T(eMPf|s`5djOQ9-oW@
zo2lZey~#bvH|Xc&qv`m*YGxkDD`1r&!Z@-{M=flc`zv2!9jhB{a;rHAtnUqNG>D+X
zIf%8e|3GvyR^SVw4(Rm-MhL>DW7(j-**`74t=A-1yi;GxoMz`C22)Ce83h;^jX`U+
z2mq$c-3;-Z>bYm*WJtZ#Fli9V0Ld_CU0)nIU1>Dm1iY?7ZVw65`I4)ZQ7r2<Wb`O7
zC!hZBkP5fY_SU{!3adk>9h&4<eMArQ8?gi?hLg}pm;KOnAQAVbcu%ya!v7mG7j*q+
zJgU8oX|O(T8F%H`)GLHCWiES@`n-njt8WNLW836a<s8nL+$DS9d6`YJ8T770*Y6;F
z(~smKaVnTUg|}U=8;GKSo858V=ta?>PHx@1n(HEJF$QDv-2V%W7#J}?i&jPNai=n^
z*nGbRjyo6XSiX=NuIX`%^E^Ovhpn*yK~4_52KnS%sr+|MWffIwItLJpzg|GQU^i2=
z{K>wz(tUOW`2in@Qo@jd&jwIlldg|&FwX$RsCrMdqhevO(Hj5`f@G31JK$i<gE0^b
zk;4$;yO1??xIu$9zR-N=6-Un8_Zj2GWQq4B*wk?CEL1QYWdoke7x+tt%(hve4mTtg
z$dMkhC2O-QG%hy4vCGLlfn!npm_Hk<m`7?m;sP-CgxVkUQ{ZqK97*KZ*Xb-3VeK%V
z-$JB6hI0GIKzFXSITyj027u6^zW8bD|LmaswE1-iAGC{_qd<@qEb`3{vpI!t(Cf11
zsS|W<Cv>SVf4;byTTYi{Cns$-9Dc$kw3EXJ-P$|`sLEY+#V^#LTMLQd<C&g@CqW4I
z&s?@_2){C)??fH$9=9h$VWvEPLw%N18v^0-0`FNs)T)iNm<vF4>)EPcyu^@nJdl@_
zd$w2hhN6=_ua56#?IOuEL~Jk@VQ9xtyxhFT8o+W8c(2)|o=xJ@)B8HNTuRV7@k=|3
zPCIt!pujvCG8f4BR1`v&zncy7Nks}5<pK<dFs<4tB6DJ(J!1^>_{U{XG*Y_dJ$ka{
zO$9P~LF(<ziB6-K=pq@=Pl~Q3%+`3}2VA)zsd%P9o86W=k|PJAM^vBg4vdu1v%q5N
zt6S|OM`h4YfF~I$&aK@->u_cWbv&OiG}b*rDo})$*Uq2Y%^0JKflrz^;N)-IKyZiO
zXBJq_(s@pon6d;!??VG<;}TAI`Lbv&u$c()1%JhCq4EEsQq)+ZB^`YU4ggKe6kxjE
zGuRKhPH@kKdYh-$a79aoLS#l2J}BOqa=(JOhvPgil=C~Vpct2)#`qm@9+0SfcL^|t
zkYSMS_xquJ2|Dqu-pRQ>#mB7#7|Elss}&6_nzN!6=4;@jUM9q8>Zzq96joD!&R=$q
z37r9zQ)v=HC!@KZSyn&t$LKgxWjU~pFqzAa03-XCoB4RsQi8_Bbd4FJO<?(YM)O4Q
zb4u761<K2n3;*0^z-juusuq{EtMg2hwlDA3#VEmn!8C*W#E=iAKv-Kb$+WQd2u=eX
zwgGm$+WxIk%jl}nCk-G4^%pJFqM74=|E(6hriW(Zdo~jw7CpU+o}0<v%b|i#Ew=^1
z3qKrDeeIR1++dT|ID~ecp&e9oLS1WC7+{+L@;}z4OIfc0w2*cmUEm3OKX51$T?w~@
z_BP66E~e85ncz<HXk<xHA?IF4yQ|C0gJaZi$XZyTfMK2M9f2u;>I8&;NJuvf4TQ%n
zEG6~41DEnRDi$?so6hY-&xJlSHYWM@T;WbwXi1IWZpnaYSc7W9erI}5x*uWo0C{E!
zUe_AMeoDl`5{y`eb~&0X81X_MF*Wej$xik2c^+y6+Tq$wt;k$K@Z~r)S|qAg*Isg6
ztV=R#DoJNDZx}unms>Y8eRWT)d#fiB@<#T=G?XiALznv47nG}5wC1GwZu6|}fW(x)
z^>NUlHlP*3Wv`XFvREbcS{u(>B!bi><`NX^j^bi|VZ?c$q0aFlBv@`93t;07y969K
z!esDR<6<{yGO?V+ZKm5DDr?n5haIvQ1x+ena9_K|T(WqY8j8+U{u~l&VGOF}rZ7qt
z{+whPpVN~+jCJnlc%oWqH0vbWv$%ZLFK6gHd-da7Ag0PFCtnQlRNx|#^N25e9!H(b
zd-|xFtQ>A3v7GJi>lBh&Vi3md=p%DQ(Mw--=kIfKHLeD|v++Vnz+4>VaDHnxOK0r~
z?V8B+I7WoeH?Wc)w`#i!G0SkB@0mYwr$bFgJQ4WX>SP%})m6+}vEese8GTO#95@+b
zJ#O&%BlSyQbdM2Ly_f-3%a$*}Npghn&o?j`=H;G`bpx_5F9opMjCMN`(Rh5%pEMn3
zfS`4TG!PopoD5p)M)w%VproB;kpS3cgiXf5c3tIids%eutO^!h!Z|<`Jw5ghyip3U
z{wARIALxPtMB0oUN<CONCfOEsHy!!4)1pq}ra=^Z^+X(biEtraQYwB<2TC>R)eITn
z+)``gUL8p~)vkfLjzZmUrwMz9!@d2KQ2?tmstza2{xQr`)6A^^fAPtc@MHN8O{Z_A
zq3x~NmJMv!uX6_{o*IVQV5E+J|AD;mcKF0L7{^rXZ4mgufQ8=dlh(D05RsYNPYLth
zTytI828zb`pDU#Ux)F45KDRMYMybeN1r(7qdy@|!C^a|AUVjmal_^IQ=4z&P$+N#$
z>iGS5Z#Ai?5oCwfl;S357h5Rm&pqYKTN<P%vU%WI`8>v|t)9@clo>Gz@D9BpKN<_f
zEUv{c2A0Y`VpNTmf&W4{Tygcps*!1@PTf{%b0V&2_9r=daFj%<4m!RRm@3Q_*yW!-
zLZ)b%#NNiX+uW#g2z0GGh;5&BBfCq6<*z%&y|lIrvrYmny1?sCGpAJ^u9PW&A93Tw
z$jB)<y#(5-KHUjISz`Oi+;mn=UoFXyQ9L5ea^iDZ8;zNd&$0dkebV7XZ;VQ5{LJyH
zCO}=8s#a!N9@M4)00?bm6xNIjnQKPwjtt%Fmjn0BOJwB$Z(qNa6C+g_{qH`m)DIdK
zj2rio54=L8*Q|W~9lf-hM<N{i*Xxbq_;oyIhEMn|eAXE7rTLdRt>3u;eqjErfG9+W
zSKOWdGo@UwUSA;PG6hZGZxes{><tJAyxRtPzuPjtEOup4^<v-!K^rMGOa0i1uvRHb
zOhuj^w(i>643K5>-hj`kfS~WCO@lu;IYIVQm`}jD$FT+oO97#Dbv=ayv+ULqk=Ru~
zeeLGspQYQmh~d>4OqiE!X*Dv#fM<T)JJ11=)cOXcBj10lPAs25VH_X!{lQWDACI_)
ziNY{rBu?|@quaaZezRz-&17F?5BZ%yJ)B%<&G+HjjhYEkM4sdE^18A4-WvRO<~x24
z?r-|XY5hFeIRPI>p%0Mz8myEB{Oh?#3-pXNTI}RWMWMkYuLA)wio}m)Xo;!Y>aAC0
zaRISD*!ZfMk6TRxNFfe==dfD>8SuLPC^G!yzyrg`{p|yvfa~^n5jLk!=X!8D(9nX%
z>uHAswOK;&eoS{Qy1Zn#i<=Iawj9_-*#w5pbTwPfEEO!_T_ZlfSqBLGU8nW4!AJq<
zFn!}daD~Iud9s_o&93f%B|^{YMK<IS#spK(+djn7SjxPPr@$7MI9&8g%Y|R|La;xn
zZ5ei!XFG~p{@aiZsMM8d*+RavJ^AB^J!tf>VCy%FZuAeWmZE$MPqi+Vrbd#nQt<&x
zN5tY_(`cX%`V(!R@k%Lql9f~OO3AA-(KmszSAfitp-8LW>!78^`_Wem^&4T0dzf2}
zV(?<ttzsG3bt!H@7F+O6ZLSO#_NzMMuWgktjRR9ukUrpU#IJ!hU>E8B2SVTvLwtG)
z-sk4ev6`a=@Bh%!)J6N!*<k(opft7n!L1xWozmC)1>bX_`%b8tHrchix?K$USLaR%
z(80*X8|qVCDO3Pqk&q@$b7RvowB2|@Bs)T~HG8b3U$E~(pSz7jIMM5^xSR$ymZT~+
z_eOd(*Dv1FBaJ!<tM#ZhGsn7f6~W*5b?kN1-)vA>!%Pc86LcExZeKZ@7<_lXeON%P
zD(A}Zd>pVV#z^kjA@%ML%opRBk21zv32oEkkJ>r{uPmJO-kp)XRnmM70{4{nmuS)H
zeXp}F#Dl$+q6obD)+PL%l{dWP4KT!_EA$t9|6^GM+SX@mluKjw0M@9eMt8`3w(rzw
zm`5mW`(VXI>pSigZKVo}ve)kS+l)*GnZm#++V5nlyhdw)wavu_3p9UObVi$yALQu4
za98<OaHM#*qfu{P<3kqz=#dT6$Hds}(YW|m7ea+^1^xpKN~r=a)xXs>N%LBe2-;8P
zUzPMuB((WATw~9y9=ZAy$6P%oyAuMT=qiyhHLzn<%>aO9;Jf%y)Z83A_Ze?kTC=q6
zWa;~s?gMXK@bBJ^+p>4>GZ_F2wwdWBlM+0uR-bzfD(q>qgDm!gM`8P6>gTQmtFzj{
z{5sr?&zl#_`I(QBly1Up9reKX1VTU!A}@}*Yn(ie{Zu&<)@kzoPFhfH)wY5kA%^RF
zeD#grlcvYf_?lO(OBIstbM)rmu?qcf_<Ylk+9U%Tqoj)&#B)Zx!xH9&GlV#($@J^9
zS-ISoiw}TCzz5(8Q?W}M%V69eQo@-q3|f4f`g}xJv}DDwvS`NQa~5`-m)=w^?~keV
zhl%9Bg;@CEi@m{1<d;G}Njf~yUvtoS5Y=Ke&Bxw`z#l7;xeM+IYdw(;rpk=Xu`b7)
z3}PJsMoe{$BJ(&Wn%t%{_&nY;1I)g0Gx#)OoI2JLIN92G)z@L*t-1MNGvKpm1b!L3
z8*q{8-q*hM@mpN{4C{v@7XuljR=US${waJ)uC6-osth!8ldLRd)5lCITbRZld*um!
z2_LY4rySk+(-^xvl!{G~A*B|jR~0QIC_Pjc<#eID$2s6ptgrRm?J*L=?0}EvhOfPR
zS$r4kv2>~geu|#LAfJ!Z|7adAkoxsGKKKUQ$##*z^bAGWTYrt0`~#-=?;H9`x-VR$
z%agekXESjEmKj$E;By@7FAaZzv}|-;+IYxPTpsKzhK{@$R=|B0-#z}eYbqGQ!RC^|
z7W{;H?0ZJXvVW7Q$B>`$eQ-B(4QK+7OhCqO>dRtI^1G8BNBc9jd&o@k;OC4PoxtS!
z@di16%*^4R&76;{&r9muZNryhE$Sd^KS^5AN)UN>rvlzmDuDDSOxxOUh|C&f8lV6X
z1v~u*qHIl=r`WBT9V2?zlX*!=-dcC`TQ~6Kfl~UokMwZR9y)R6NWjl>hV6@2(^-A+
z3}ZtL!z5!qf?x*6nEP42XZ*`!^tRTSFps%hbbzC7uv)CVgpeYqxULjk;p0fuEzfJi
z7Xg)%EFAEzfVwbKZg0U7=a}M&3l*Y$a7I*|&Ecpj5_PMe54*N$-YgaFQewEj83T2d
zQ#HBrSfypmPrAoS?z$!ktY(#Np-lh2xJbAyF(1C5S!QJf7%i($Esq$k2E-7VPmWvO
z-yW;w+)t|umhLi-Oy_re@=sS42*f)*)~lEtzQ7NHHq2#GjCe4w<D3=Pi14*Yxf?O$
z?-o3hxxCIJ6nOD#&0FSh?wf$Qeayg~=`(BS<`A0aA=NV*)K;$SVptMqCbdA-Vh%rp
z^RB3@wvZW&8n4afX*$g>24HY5C|tLz^|wwA4XB`9=9+vs?HyHqG8TAMG7zp%pGfjc
zo8>z1p&;>_7%O%_wGUasAu1R&?|GzwjrsK?x;ZY_#whvhov_1=uEeyQ;K%W}2bxE|
zm9GPbGo6FJKhsOd(~V}ZPj>t@AejUUu+$T1@!?=dS)QI#CE!Ua?li5oS?zTrXb^Wg
z_iVmc{7hUpp(;wcR5w2t^>qVfA~4k>cp_F-_iW}RAuf)Te>pz#`1sd*qwJHX9~IiC
zoSeTvZq)%bzNfWCQ{U`JdbYw0NA&ou5h6A#&4v8x<<UtRbdhmy%1ta$`7&2!s==;U
zy{G9&^WQ3qek}x^$%QrqMS8hEV`RCp1;Qo+;6=J}J4#wh&K#EHxBGDhsm3bH^ln#W
zhX{F>|3GIa)KZ>?X%y%Q>5mO@RkpKHnX|C9MQ)6)O;pjtW2Lc$vgUBeclz2ua#^dK
z`VG44t;ICwMXlC2<r3N=_j!i_h_>qCtu8t(gDqt3Z?PiwcO%ZjQR+vRQL5E72(1R=
z3{_+O`rqU!36DHHbwEEOeawNR=c)ug&AzF0XO~_;$veTMyv@BK0!s^lL@YL2Bpd3T
zs3IOzQ2;7*V0B$uXZ@Pp!o@JT+yN<`WcpMFTOir3d&j)KH``2+NDcNLC@msm1}x{Z
zJSs0(gf9JQ&OkaR0n?P@Hcb<GQGe9BsFvaqz-pZmW=mZozhd)ztF#QyJiD<LquuDk
zaE(aH{2DR0IpPRu3l<P`@VnHI=@28gh>!1LdIozu?P@`OpY?&!;`_?d5B?z`y~!GG
zx@#>0&_INir}6LKWzCB?qT=0M6~SLe+l%7cmESpjO~+}_qDR38?EUFIhi(iZZ-m-{
znunpSJUt7L$DO=%pa2ie=MFl-F=?7R(HRc3PB@3^)Z_@!X6c0zdZizWYx`UbSL>T!
zKNM=x_>YNUSa{H>lZ5W?8)j1fmc@1C&1QP*k&RQB+`(16VmdBbZDwNYh5qQ<k8VvD
zY1Nfj2$5@icX{=4Q%P6VX?t#lM{c7uz4}4MgXKVjzR2bKuZM_if1P+$&KewrBM$<K
z4O*PEQRDMxj1Th6-sF61<bUo&`^V8luzS=P_1fh&6Xy^2CX>uE5d5%HWO^TC35RWR
z6~#W9Jncet{Wd_lt@TYeSG4OXze!`=y;V6*bX0wdwL4y^()rw;Xqhh44{@xPB9u+~
zrTM-*ABsCK${RnBjISshL}ZhaDBZSnYb02hv%7rMXF+ShWBDUeON<fEIJ)n5f-E;1
z4thE9IfVJa{zS87tX8`POrhp;at!qQ9LzfUm^Oth##=X{Hz|&R_?iOdUHJ|?vMvYx
z;X&e3^%YXypu|5xr~?VzYN{?+U}u`lUYLZ-cNmfegg0mFr6|OcZiT^|ek)8Uh3DUw
zw%HJX7-k(lwWKg*8o0q|PcL|lVOsjk{<7nyQ@@Z5Xvb!wE^c@sheG<~OTI1)r8k=*
z4o$H_V%p+lBSFwrxtg=~8SQx0$@4eKa<MVpVN#CWpgZr)VkXTg1r}!W>DoMxtWn&=
zvX5(iQ;7u~%9UzGZXvQMt6z7w(S3L1>b5MT%NQa11lhe+#6?E^2boN)+!s&@TsbX7
zFt_YDJ&$X>O%k2`G)2@-7%DV`B1%aB8ag5GyeZ&ly3-no<|aPp8tl5~CUzY666&c?
zRwLQ2{AoKy%Xs(PF7#3V-nXgBx+e2&l)mDw&F?S`Uha3r7kwagqzkG4y<?7k$pf6+
zO1XDBW4`utSsmI^?eG*@wmw0q@0l?3f_Z}3_jcj0H$stL7^Xld!Gx-)jG^v<Om1<h
zKB1IspF3S_`3F+QfG17Y1JqAgK+MUJ0|=17VHX*c_$B=jZY3w42<w5XGL}BH>*ITN
z&boCSuVNXo$IGdiIwJCV$}((FC_?NfX#47_;C)HILFZ|iT|dk8ENDFz|25URl{Q*X
zt@I&_m(JohhqDQ5IIFdUbyy1JC*%06JGh6$z&*~sc1#T0&U(P~oQR}-1OJm3gKIs~
zsYM02L7#5)nM}aH3dxgZ&SW0r$3d~Lj;F#UkcuT|up(C6lz!=YkWlD-H<Sl9I<9jA
z|8VsOBJj`!D^H<P1RoF!v6JrnR7idT@FgwDv!`hK6Zbko>iwG!;qLKTvMPFUbRaE0
zCK+%%7kl>JS-#%%RVk&CxFj5;XeXt?WlbUm>bTs@kCH8=rL|TjfQt&hrjcBqZv4(b
zXDQ=rmx?U~al-1KE9}<_uzpJT21@xF;Kk|sZ5U5`9ywr(z}Sj~`agY~jmx&7$Ql}O
z4ZznsFJ!|#13nG=mK&u_a-g2tc7h@+`GZETcieG>jNdBot|>N~FZ15Ja@GD-(%>r$
z%}vEnx<dBuxqr26Wlv$_DsvK7UR{<dK(wGe#pgajdn|fLR)$zBk1wVqE&De!S}v6S
zyH(-@2@nyGdo1XiC0JG`lbIp1k{D-Rrzz)Ss9=174VYJGiH}kFqLQ&afKZDo={l01
zHfkmZ5a(4u_WF)b7!JiGWC^WtN-c)+n=VJ9iubkKKUdQz>zRGS3jZzrE!>4nV=bOf
z{1dM$+wP;0dCZmla$iLUDWQEH+1t_vIX;6<9Gx#Tfv@)TY>foP2&TMg*Mjo+uj~rn
zKHVl3>Av|L<Td{ZRTdmC?sb!DV;!PTxQ8nQ2;%DK^%aye!`~Au8+pC3S`>V2KSKzA
zPGeF%F#x-Ez)7v2q;?(NNe)PXFEmapVi&VS9pSlr`S8ITSLu;A4GkizYlFN4kx1Fg
z@eEZMs85}r({H=PLNg>)E+5$RxB6~|4nRUa1&ub`m^OdPc`v@g#&lakCUiTWwaxBZ
zQfHdT_<Fkge!uWcg$_<G&{S#mIY~b;+;D4%QM}Un4KML#sLUVf)YxbojzR-D@xeQ~
znGu)cVquqO&c$)Fx^4kp#RJc&yZ7(QLJuTGGq15n=4lS!@<b2alD@W$GkU(!gueWe
z)_Tc!SY|lJ*ZI|b_9i}0GU3KzEY8Xk)me4m@zT8oYrIn3GH&2&c}`lAt-I35!V(i$
zqPFyL{Fsi+Rf&3sDo+%j)Pu5P@8@T`O3Em1nPDxUXu?AC2;80kAiZ3b`{5-;(K4yz
z&l_#lo7+(IKF)-;$aW~ly_Tu$uJ4o3z-bdZHjJ6gv=HHTGYt*zKszffBbZ^vj&ooo
zWgm{~L`v&^m1ms<JHdGUj3Y-?OD$#`9pQ@%z&thh<2<aH<3VhaRy7^VxoTK3%vUwR
zpkfLhC5}jC#G*V+_lkh~9}*VwqBy{fH{@gfhX_uZl)q{zJN?9Q!J+v-+KbW987!Gc
zSppu9JpgS!KG$}}F6o<M!B=uGjRU;KceG?9aR#%=0`U3YQrO#OUfRgAZ#mgjRN%b+
z0q6h=`@Ht^3E!zw1nI_#IK7vfDMFG;ehb!6yO7w?6^m{&@Z4jPGqa!B*2Z=9*vdfh
zF`w!%&f8(R@Q%GEg($u>!#C4j%`E-YHLT@AP`epMd?6s7h<T{)D7I^IcGSS-aF*Mk
z9QMb-=CPZd&$YoQ$bkG4J<+p;(=O~nDooP58l*M2QjI+nr_pTWuEPGFyE`#ybO{A_
zQh?gB(ZsGp+c_N9Y!ew$w^r44O9^NjTMu;wlzeh)RrV(T(9$-E4Wtn<`yyx>bFT~`
zukUAVdud1-Rme)ExW6qY3R<})gX0Ka;1cGF7%y^8*kw!W^&&T*%jHkGsl)6Yz=Q$H
z{z<4dVT-ZQ8uO>s<Jn}W&nmJyFzKzOhem|&$hN{6rS%Je5vcngNtb{JZWjWyC-64+
z=0V|e+C8)|3}s+H)a)WX%X+;?a9OPQ{;9}bj?%TuW$1U3>Lj3%KO*%8-r88*FMEE?
ztP2?vdG)=)DD$Bh&)W4I7dCBy;rL0x^FJDf<m-UtLW4zVX?(W%u8<98GH+oi6zT~Y
zmz==G=PhP8$-7z@<*Q~sKXbh#(z~TPQ0lEEm~Q7_wYYV5;$ISql41Xcf|mf^$+AHg
z$nx-nU*Y#W)|1ufmD$dXQBGXw_xnhY%u$}F@c%fv>bNHRw>!E)q;m*JgCLEJfl7BH
zA>G~02oa@5OAqM~q#FSdkVZzgbW8X4d++D{n-62$_cyNVoO7Ksx6VW3kX5gKHz8XL
zG@$kC9yrsRsQyyg>3D{!=6fE1j%Q&#PeNQ7+Jje<rsD_!w6&PUXB2Q)@#=rF)PIJ;
zQBLCpmf{W83P7K}4`*@Kcfa!myixyUYc^~$xE|9mmzJEjZV3Enq!mjEDTmKg2(mr<
zf)1Gs<;D^mcXRdJW81%<%8-|qcQXp=!rh?)cZw;6jy;=q&!Gd0E=&6^7G^$g(QRFQ
zD!WUhbn#P?#=t2wn!Hm7oDu*akM%$(00~8I$uSaZ<q0g><RkM&aLft{-NeU5=fMaz
z1@XL!>+mu7pc=E;t%4g@#i#YA&z<d7?pxf_SCO1lh|p|BXpwWSXZ~en>Udi$o?B3|
zmQmsAyJh?c_AAk^Bx$uA^z%diTJ;FLuD|LS*$_+K8H!T2=Pfl`sTN9EGjV?kN&W4G
zSRjLkUD5N}gXjD5M}HQ@USEu&j>OgQDrdIam)lGvKTALEx^Wi|(Xt`j>E#PiCh%>g
zy7!x`eHw6N31BX=%nwIh@pI>Ik-8jDKa9xMh>uLCrqert2cqfYDB5@WjbI*j*=_<R
zQB*0!{y`4efaD;f-7WNu4jo%)6KvK=>@Yt^UdY(WW9~w{eE?JzT6p397-CcdYfII5
zSG*L{73cqeA5egc5b^!dx%&s_#llKB$Bh<LVeq`PHa!!VTpqUGqmnE)Uh@VJqBmNc
zll&|kf?i}<LCco{j;lHmH$bpNj;NMVjBB^cbk1ePM+AK?Z4+JS2#BkentFlO+wEHs
zU{h~P-m6MW)?lIUi`+0hs_$gpc@3>rXR2AYTYQt4vullVoX3k}*I%BU6>6z)viLy#
z`vEg~+52rq$wm7x8~S3}+)5sLwr$n@Pm~(tp9jUs^5XZYPyeu(D)?MNt<`3{ov?HA
zM5eXpn;cBoJ$VXEjd9)L=m7%H=uQ0ZugWP~`M1W(0$&rtoU8h8C|eAf->ko1{0hkn
zMEh!}##i`v#|IbcZZi#i{A!1<*U{y7wT0MLxoPg#_}9|?AY%fH)^;ujXpG-F>-O#a
z0KZyUay*}mDytB$nSuV*OcO8_Z~h%nH@&px%6a_(Sbs@ohxQF;D5q4BH^qz7-EvBV
z<fBr^2gX=Gsxj~}E5SmslJe$`hp>KeC(DTxrEKtUY2{0f0OXYd^U?I}vHp_(HDt&V
zbw_rKtc_uq+D)MU1rF;T&b$#8AZS3+AUVtS4HR-W5k~<YfjhE}L)L=(MGI*DY*1--
z!g|Oz;{f*(jqIAQxin4Y4g;`i(?p_eIupoCs2wA+<pAsZwJ}Oqe$uGamv=!y21$$8
zsv_s@$rjRLzvKkCHt<94SQu7Bh31(ZE=~Y12NOY9I?Wr}=WXi@BU8|YIRDF1@mx&`
zC!7C)T7M#Tnn9`WUqk0*p~mqmCY<~=X5bq`0M(NHh`tQnnqdIMZ4Nd9n)e)~Vc-7;
zTG0K_>;<CGn`XR^wnlOFf5jFZs9=Hq)3#s{d#W-Rnm4|>R02@DGry2lw)lKvxmPKs
zFk>5!cdx8OrauGvE#ldx<}7T-ozQ$mPIS<3bq?$#lm4fcmQfewZf4fYm3(?P#4ApL
z8y^=j`!o$W>q*sZ)t(x%@0Dw6t_oHFrD&D!lr9<vc!#B^Z{<4|>gKjP@P;5qYSp7r
zvdhw(Kr(f4RXkK7cLakIF>UmWt71J%34QngtZ5#64ICvZ)H}~N)>Pwzbi|jK>Pf#0
zs@ca{ynXR^SE_p7dS3p&&lMfzgKhrPw>~QU_N7Cfc+P-(DSGp6THVu&l(gC{2K50q
z4(In~JK(4^0EWcw6u)rW<+rbt36&QgZQ}=q<098iN_fYfNto&EcQ3<5j%aYsWe)cJ
zW0ub}Y!w+`^^6Y<dc+O2EXxO+GIap&FYGF=%kiymo?Je1dnS4%VCvcR2r{}cF5Yo=
zSTS@)-L+maPTv}hMD~Z<LHGR24#l9?PJFDtBQ@fjZBwU3aX9fXA)<;w<%=OK7W2w;
zMamNwCDgzehx&)$#<VG*22a+U@GL8W0j%>}`DjYi`2lrhXqwfhBSzS$%%IFUU|q2>
z=SUZ&%3MSl?w+~6e)xo}Fw)5=WWn4fs88rpue7OM7*wWVz|<V+v{EqtxNLHKnJ7&U
zYS@w%YRU8Uc<3fJuvxP=>@!=t*dv9eJ441V8A^w*_TM2_-t52zF9cSBPoCg+&+BM<
z?foYh>1Sfk?_SwbSH&OfQkJIz+>EUSz(r-h^lb_I{ri@hJ~doEzvCp4V_B3pTBO?+
zj`J~&8+tsX`@Fvb%-0@=auN!4(m=YGx9z9E?k`R8_?svF_LAZ1<0Q`_O}Bjx<p&=u
zbgKG0h%5ttAE<LLu8358W?GCO(Ql*Gudm%~bBU!_{Uz~aANb4l+{0ityLinGM!nbu
zvW~*HWL3<tbPOxeFIv#RBdf=K>4y}_>2HSnV@g)7Sb037L3UA0*92xVV~W#+wB#Ze
z7#B{n>#+JPkr{vM@!CPA6lwivxQ=u&eGq&+*HHI;s^fnC&m^km6Go>m)%hL&NhXx6
zOv$gi)c*%s1{7pQD`90j(?`=cjJhpm6c<jDQG2bFJr&mhIdrb?Izo|X$}?xT?(;z%
zZ{Wh(wsRw`g%N8#n^>JW0Rg@O4j7R$xC}@Birp`iY6p}D(t7esmUX(?En2Rl4<F(;
zGMgt`cY+6)7y79&1Nfh)l|6`IBpxkPd!5wbDDk%*soOhVC((J79w!DVPqm<Xi3a=z
z34^{A<C;#5ZaVcjHvn=vHB%^oUE5)VG0nYgdwk9t;UGXzV?2hQh__8ub9+VIk5%g?
zIh5ZY)_C@k^YIry9+I-Rtb%d>PcY_XXmskyqVf0U3p6E83=v>exW@^8#8AA|;}0Zv
z^VPk@KvO+ymKa?4_WQVX3g33+mw~MB2)zI`o48-U$71o;0~xxB?fnutAd@n*hY%8G
zMOA=B3t{ct1Vp{<ExLO;;dO*7CKRcVhv1+oqBtEd>QlsZgKidifOyi?QETzbatY_}
zA<<(rm{75&Z4aVDOo8QnOX6cFge3DfPn6SO9{IrG!tYDK!)>;hMlAZ1^GKWK4K*MM
z!erA4#}xU|>04xXf}0MW-azcUOFnNxYtqUeDoH2*j?t6(um$76Wl^>sSdp5yPjq@c
z7jj(Jtm!98tAqu<gvh~Xx(Cv&)fo5ZY<#yf5xep~w{(7d`yc4w*kzjZ$Xn~nETtu^
zLGQu0N|Q2RQz@y%b?m<_+Fzq*ttijgX5m1TZme#3zhcDlFVb=EOR!9+1`gBp_p2%*
zTQ2B1e$(KC8jpVDVFl798MY{bVfPc$@TMh2DyYOUG=ItM-^=yHfuefh%u_)0Bm0Vb
zUAHvFC2U7Yc+H=R#onAxX({6*z;GURRV6XxvKFk}1p|WUt|~8@3r?2)@hLwZytGI2
zYy6Q3*LwNoi_6{UeQFpkyun!f)Er^ms*ikmeAn~=tY%e|5&+v1=tIqnX~h-}Pu7I>
zhj`DYqD2aaacSv&SJ$qAG9*FGz8TnRPRn5+9lqKYHmxq`DZPb)$SpuIvwSA&25;)}
zM@GN$2^f4h;SOJtygRw#xCi=#bz|~`?5I$Goz|!$PH9KKwK&2I-gi&7jEufsEek(Z
zGG(+byZp<ve;7o}rpY<%Zcn)xJ)}UZL7F_Kykr@@!VB3+akWA_`<wIhjxDl9Zn3+E
zvd!#gMJ&+cTpc=IRWC~Hwt88q6eo^sm%PP<Rw~Yg5}@#9$&tHqM>lbOJi}NjTi{|&
z>#<{BYP;eiyVikA@mW6@ctIC{ovTKD8=vDW&wMPWx|-F9_ni{ww^{~3h5uGK-F*NQ
zKeMF`KRslS<&xJL-6bkISFr7kF-KFgkKq05VVN`xQ(D;``b4t#QfQy!jN{(Ohq-jt
z^n~%h2|8>D`7u>`oWshxM{W%MrY=NqVB98D43=l6Z=}H1@cVLHNdIdJmcU$B`V!cO
zl*EzUBT)%Zwerx@Av}=4A`+ZjI~Cw5sJ951S_kVIx-SAoOZ>kay8D=AoyITt`WPW+
zOrMDzFm|T4BB{rx$zBh9ITBBpeFYdgMj(k6T?a-M@E$%E>DqZW4{U*7cTTd-x3puq
zxttw#hzzQxzXF23$jXAsWkxB>ksOjtDij)tjBV~mJJ5f+<PxgULl3sC_t|Pc6hs|D
z2Z076`_B(SkzbNmW#4quu^z<Mz{mMGEHrr7dD`9U5`gv#&INquXYW8)OFGb{%=LH1
zT-Po-E}a9!VgT8P3Dgr>FQs3bVCl7SBEcvpv*v!-=Ji>`KOJ&lfPe8t35&P{=P|Vd
zUdSYt!7COy$M1-Fx6;-++uqnycnI=CO75mk1K=2B%hN4Z#vJP1FG%~jtW?<AOS3&S
zJ5%0iFhR;dCccacOPSzrQ!Uv8yUtxkW#FvsBMA$K!&iup_2uTHqjl^{=oUFW;<`>h
z<l(7?uXCg@@-f!2y_VS1-=impLY9V@xX8<~xd(+K%|8U@&#S-Ru8dtVviCb2SX$Z<
znP{FD1_SorrDV5LwWd=>C%qd)&wzif>}#t6!|JTiUYEKZ|3EHmd;Iif2)Ec|M8x&5
zWLfCSx5RRJHe)NAu!S7)URW>x_1gIrJ<4g>*6pi-vtSfm@3C6SnCUj(Ul;E&L7vZo
z3dbs<;G;yxYR{+5CI&nZ5M6PwKdH)o-NhhQ3G27tp3FIJo&&~l_#SN$7eL@hVBKZE
z$jTB>4E`G5ia>{QZ@cIIXP;UR>rkQ5gRs_Pt%+a|nJzYXdiyQ=Fp((L8=s9WaJGzT
zf)~3lcN+1gPrV@pGEpTU!A_ijmLHyLA4R5Sx3K9$=a^zQ%E-#sckWk0PkF>lW)CZW
z$%Ok9;3gHoeoMJY43!@1EOj>+)uK7d#Iq-&s$B1x9f?)?)v`Nd=9$_GF!b+h(mp&O
z(*+nn`$@z;IPGES%q(sS)!cw^wVZs3lfQgi`Ggh-?6!yliuy0F<e5H;tnq5Oz={^G
z0L;hWt#_bTkH4<kl4UDg?6|9b+K4C)=bkK?pE4*0SW~*qP9(rgQMJ(3n66RdB*A%&
z=A6ICkN2t5M&oOz6lz3jb54Q+$ElR%bJowVXoZe&^szKSM@SBdE7P4MAlPN7L@BHi
z2lOs5PXX4%27DGqziflrzww%GxmZH^mIS`DC0A}N|HsJmFUvYaa7PUH9HV48h;VG<
z7rzAj&+d84r%DG-tt&SQsnn1$b(ag-HI5u&;7xc_Vi-HPrha~LA_sZt6#v;K;Y(K=
zSV4MD<6we%lQQ^$Yo|imKX>C5koeVFK&&aOE-muK1rp};h9h1UM_>!`<H}(eP&j`w
zi4V%14*rfSuIhr<1=3q9;p(aDv_$Wh7}l{LO`YH$r&Zk{=)`N`1*Je^PIHEGj8G5z
zZGx7aW9UN0>io%A%;qK2QQ(<OzW-4md?f!2>-LHRuNLdS{(x$Rf#rW7YY+s#iYrx$
z9F_i*>?B39Jihkiu1WFtaZkz9rA;iYthxma2TT~xsfD7g3(e$NtOs2C*wqoxNa*33
z`0XCkytQv22dIc@aU5MA%|Ae559UyeF0|LKs9U6vNfs;B0k7GqiUD%#P?Oc=m#V-I
z+F0CgnCGU9pf+ZB+&mVmI>8Zn6PWMrI-qH(wSo0PU2I(}>{{Y+Z!t%~XUaq9qFRvC
zrvooRon{(mqtLSvi=&=$Gv2@WtyZO>%8*PZ<+V;3T232rQ|mbYR+mdUPkS;9OVli(
zR#NKMcK3oCl&7`SGOs;^_ecVr&h~s2m)~`e5+jFo@%tF6%s+Lx8$6u-yl($`saa-u
zr!l0XXW;?Ty7{mMn1z}Ad-2M(_i}=gxQM~gvX(7xqI62##l&o}K00w>Ax8ZyS6_^#
zs5s*wR0z2C%LcEnE!1b)Upz=#UlovWvs?h;fg&y@&#AhdNZPGe-~2;KT;wB|7hX))
zU0U!+7Bnx;x0+tFPiE3thAhK=wO|CfQO2{c3}jJ5l&GXL4ri`7^#@Ozc}SXvJyBI`
zSm+rV462=>1zS=`#ri4$0u5HT{u=>`|9tgiu;@`MbAmd5X)3&NeC>_e+m0rz6xJrq
zH`zkvR69x(dqP_2$Tg_w93=Wha_M&^H_bZSaAs(uP?Rs|rk}-mBh2+R`4J9lzeSfz
zvE-g~yJzH}8;!bGkhL2Z5&pSa(Tj@mdkbBg|Ab?XPaxT8CX3|~Q<<TTWJw9>Nd2%@
zbXreB79+`GaRP805xHy~P*AKn>-XFGGKkDiw1FnyRFSlY)=oSyPU7G?3j;2--e-Fz
zA|)al(7Bbm6J;l)eCNPcV>5gWQa(1%NdS_$#7MKOmo8iZ-%=3bG$9^O+c@X=oK2ff
zK=wc^lXmBqIQV6U=Y(zHy6v4oPo&7g(wd`W#Z&xDTOUVZ^x{TMXz5<<|3K<+<{m9K
zJL~Z>@T9c}2H657I8}uxIadeYo-IMtb5CC5JSodny$%f&S%fjiPrC8+k}mSWl%TEH
z(_8@rrgfLn=gI+%d5iZ_v5_Xg<bFQd5lRm~mI}kWm+!MKGoMWw%aQnJ!+HGDq+qv9
zS9ipkJ<7$O)^dN$do>Kfvi{#uWFki2-w{D9s3g0I_Yv@)5H{9)n&M85aaC!>Js<C+
zeX%Ds+dtgL8WZdXbFnLjF8pboTDaKj{Nrg<b?tAScf~dVad`48?7H~&5?iN%wb@WL
zbx)U)uO87>6oo#+%<H!-B$Ah28@X+EEak;<X_^`R@IMefC%8n7y^AeDit-pK$~sm7
zZ?mR>T)?L?snqD*NY#6pV|<^*_C)rwTLrIYcXS)=HD4c&iPY5hWdL4byb)&d$@-Y%
z{#dofX$(*L+`c>$=@8W-wQFHs_f)RGN{jgsp=pJK#q^L;=9U5Dp-jPD;e~tQC|KvP
zh?QKx>g7c@dHbAlG=Z%Y1ghIrQy$2pl{w;mI7tLGg@e7{^;1Z=T26ddNyzw3mZR%^
z!T=tQi%!saaqdY4)E=JVn{creyoW4wQ>?j$!OpoK5&BQj_>?u9FrZXArjY+RFz^Dl
zdqDg@P=^LdfT3e|gy-~!Z`Qu0Zhr+xAqluUgYerg%QC^oA|G8uhVi6+sRSRhehp+9
zH#fAtgGJlr<OmO5>-~c3mz4|)4m;E{-tYn`Ip;=Esg=;y^0@u6__gtcJ>0<3xX(kV
z)wt**6S^{@1X*D9#0RDPjEf+y-@ogjNrZ^g*Ev_bdsj1GeZnyPlHL=c&-lC;Yi~OI
z5Igecf;?~hRKpL|Ap%vMOo_fop5<m%m%zG;_amuBR%R~b4<mYmVNS>K$jGX|ptfDF
zZ<#<Gk08!)N#S3<wAxEXeX$H3xd+UTmz?lzGvfMpqu3tZ?A9Jzu=_*O8;vAz{$*kQ
zW(|x-vL|Z1L-%~)7imyNKjy{_LuXvb?p%``<eSI$iAvQJ=qDgxh1#TkF|K<$l6#rY
znP>^s#)?xcE*}4qBRcd}G)-5Hxa6c*;*ygxbBbU?nSH_*It9EAUC6a8dg_BUDp}1g
z>myiSR#6(`9pa3QWFk}ZE58cIloq4$?}bNi*|-GOf?Wga%fVYcI}`7|10BYD@G0eI
ze+Rsg(zfgK&*-$j0cFp8{6a2qKt<ZgS$we<{xaUV7um$^S`6`D+`MzWCw2`ocC1sf
zB?sMbq#+NXE24^Xl=zi%Qr?{R9i`@PvSqJ{mr~V}W2_r53?gRne;WNHYpbAna4+h2
zrv<cAsj@o!Ah1AU&=s#vk>IvS+5}L-U+EpXR;&C9tX25Ywv*pXUm)Qsj{)RT$B}MX
ztb*H0f0ix(r$g=cRW#3-nuqmNzA0T3U!4)U)K>DT@F193f|~*b3SM&6?snn~Y+dgk
z+dJs_?1JJ{=Jo9GgUzhTetYKZy@wi;@+auAK6}6C&YS^zYT(m*PjxZ>UyqB$)=QN6
z8u6Wg0~S+Xw)>-UCg#%}Ey><xdHrb5jbT}6;5X)AVyjI4X9{;$c9#3en(usUA2KME
zG%cAO(XQ~fe{4A?2b>hWwo9(FoXVfK+AjvM8!Sux^7n9UNQk_A5xZ-!#Wn2k4f3*y
z=fJ;L^Gj*^wNGJ>4-rMHfCSTphCc5^X7TPxqO-u_!QC|7-?vPWFyrZjFYe=gGFb)I
zs%}t@WvprK>(A+frCiCsp&V2&9tRs(S1fLv%1;edvJhkzoB0Oz?reEeam^b=84#MP
ze5~t|SX{)8{L%fUoUVY@Z2(4${NVIxVZT^qA_?YIFj+e^q-xp3V!Q<6S&oDy@2Kh&
z7i_U`(xLRt@gs?{S3{*aA4op-a@JDzRI(;3Jv*1XJTxFbR(tbt1>WwoMc~XaYvX;K
z!ZWQ}7OC2YoSThcJZ)-u3g%$NbJ6W=alv6sEb8(pz0r7cp%@W=%JrZhUqoCav*JKL
zfy*W6!LwodGxlWx^W9EX$fxaW+H2B2Dpi+=u>ChDTo$GeN_Ka8@i(j`7vN@R`kmWF
z0RsxQYbG2y($;SeHeMg{qq5&f5fIo&KmDaoPPJx)WNWjY%3<7juRkP{Rq|2_1@O}0
zb$7i#ETB@26{$m1#$xunbYC++4oDW*rFWPNqHDL10ySy1Mp)KeS_b&brDR=7NMa!K
zi<RJ*+B0MQfp92$ZOAh|iOkes!HYyj(h_g??a<ZXYd;D@$uqB#ApZeR%|yB5TZ83U
zu^W=S^6Ith5`k<hD7OwILB>x&SIl`jQMQVLR4Tb&tvzapdGbN-s8e?*L0c){CX`pe
z|9m0#?Jta>(qc{uB{%e0Zv~YyR@rPV>&zA@c@ZH#VE@t0w4e0&jaR=SM<EH1mLqqN
zP*_iXB!kUQcro%k6)kE&9v~BdZp;FC>-Dul6pcNydbZAvReIjN*zYOI&Ci{F)vy@B
zITn@ZXhe{e`M3o5uiEU^I0>^b+E5(7ZcqIOIMg5m3J%C0*SQDq*|G<-uhOU=`WEZi
zXVR2=Fk;U1Ju9-vhF?NgYQR=L5Bl?6{G(s6%VGSQU(r4f!9Ec!(nH*j{d!6#c4(%8
z%U8~?S9=%a((iU@sfw*>letZkYv!OFedyt7d#yG`o-jm-S>l`pMq5Qln&j{C&?<8W
z_4r?HonA`AyI;$`FRl66_;I$-R*S%$L;u{y!qQX7U``rEmR8v&rYZ%h+<2(e*bLs6
zWhhIw<(ZOr>n;fejQuf9VcI>6_{y#P6=!);JPn>m#bo4#sMiXv#01lYUf!<}9@x0!
zFVBg6b)sY)9vlBk_V7A9I%uAx5)%NgW%7t?_rJ2@wRsXyij5a*EpSl(8ljSK`Xe%&
zhgO^v0^!EyYjTzx#}|o7PI6Mv4S;W|YjsA=O%t{xX^@B}E7ATI`KX<&fT6RNuJATO
zlRdlrH=fH*p#_=C6g_v+JVwPg1iZ;8IaFR)0!^R9im$wR0a&Mz8X~F%#C>r~5(4*c
zk+Kjr+C9fZW>`$Dp2Yi1Q5Lt`$AckCF5RhIsk6uZjt&do5(D-NH5~SQ5ICA;Tr<cI
zE!$H(E;ndQfe{FC{3f)Ti-k~8lw`cZj4-mq!vmK9fiP3Wq_P9vDn{0lBE<G-bl$By
z$ySypGL0p->&TGN7Gqg97WUXTbevt1;T8+aiVvK)Inf}Gwa;UM^k?bii_(cuT^*qb
zS;r4gf^;z1z|xziA_EDUK}o4d$`89u&yq4@%KI^2==MX|gS39#6N2nh2PKNnZ~xYE
zKV+gsJ~Ri#CMT!$?1ICK2Z8T`k-2`c$0ekipGItf#r&f%4I?);%UYjSk`hj9-f^eJ
z%65J#&*q&kleUAm2G><$W51y^#qaT0ej&<2manLyjX$V+hy1|8T*jRB6*L*RKNyrG
z_GeO;`RNLM^rxsu#a&sl3;av0sjrTopf4n@E7Z8w`o~yWWI^j>P8RxsS#WJl3Tr%%
zd;KVPx&cGpdn8Gtb-_kBn{b8Bn@GhH1<n_bZ_1o<3yz9`%!N$`M+}0Hh@s*;<%&AQ
z--#xYh<Fa}*#3~S$w`yMnApZ-It&(4h@-;%eF5icIPVK~!eGUC|FV|R1;BaW7pW&O
zoJn9mfT>lv<wGSYi9Y6%fYftg3U!j|1Nw!A#Bjo-i$}eQL4>iah;XXL3UJ2$9qM%-
zPTQQ0wGg*yE2v5xg61jx*qZDIZF<V=gxAsP{vMOy!mAjZP4YZckS)OB5}u>{8Qb@L
zS7R0W$u6lDxC?QQvAQrkBO>5V{z$qq>?A~oEb-#2O;OeX^TLy|53=G=6@x5FrVoES
z!xI1lQ=^#uY`aVTB-&s-O<sx%3gr&A?ny1yKFmi@U@0Zb&7%{fU-6A<=Wdq}Dew6e
z)?!vvzNd2MMz&GnGzgUmF-WD8SS>o#-nx&Kd~~4Qc?KcjN`*MRgzWVeyxj!ta?b0@
zV%zLwwWcOIOfW{N;n}|aABftq46m*<OFM8RluMa>9JB651XOn}IVK6Wz?;pji0FBA
z(hE;c=?t30CWIr}c}D$uYfXvu_L7gmf{%_V8pDF|IM1T^+u=#kGLcn{F`VE$>=b2b
z<ZHk~P?m(PJ^Zd1`{TM;knVNvO&P`jktl{I<tx9S-A?VQ>gu-UPj$)d@pB5pR782b
z@`2r-PUxEOuu})=s##TqMr?AgWYP+@^xm=WQeH`3j%l-JZX`5Dm9c(-kmz8_ugB&?
zetGIgK%9PYG{!y8V6)#J)2P(MEg)6keyDwQ?yNVOWl_Ll7v3#c{ws^|Oh-T&@1lyl
z`|nTs)2O_-L>#|A3gNbfaBoxSM*x5L9L4r*-3{Bn=I*U4?VZLen>l{>Ppg<BgNS4Z
zxAe6wz*5V?I&|=@80#x!vWi?FVg=0UpXFUrR;-H!icz<Ne+_3?AcYebWmb&&Y>yT3
z<GL9SYe{7x0LcE1^KWdsbi^YYrTYi(p?fVHrsDsBChTrX1`JPz6=$ontdGDVAKxER
zq#n!G=q)Zhq*zZ+TEXtN))I`Lo*}rq>1C$Mid7NS&(anbE)dT_B}TT4e4dDkDwxy%
zK$a54;;yLQ@|Y|}c0<EGZI6!C#J%td{6`+cwzL}Y*U)uQ?37p5KDE23WgS}D+^b~8
zR?3eAc#oYD6F2g#8Jrlsk36H?0>Yh}fGsg~&5C^vSS9<Fde-w2nA%K?0y&M0#SK;d
zxo!9MSLi=_Toa>fMEftKF=!<-lz~c#mkM|^9{?xy9>!hA`)p7n-(*y7*o$mEWHn}r
z&eCcnRWF?!BFIk*hHbqXLGzfSzuwh)UFO;VIG5KF`|eaE6l|gx&sNivD4)IuK?$)<
zbsZ5IN+W(fW6x6Nng0j68PgXAP{WKmcnMcJ^al*56sNnfH-%=5{hnA?eWjbh8n8VF
zG{n++%pL;-UrtS@_<j?B%qWf;O^H~Km3uyV3Gb`8>kFadxMi+%M-8BSG=Yy5ei_#2
zI1lBMv3`&#O-x>M=H&=524J^OjD^P2pJBJ4awWWHn!b(&M9hQ5;8Ql)!LI2869R|K
zy>}DmrA;fp!6LIP*5&X22g(ztaSl&<SAPFz`#odowP3KNL+dy3<J44uz7dN;W5Na!
zZb;iM24@WNpQTxkIVhI)>LgWmWZfRh{(PeUa&!y1xc$VUco2>0lsiQSCh*aMHLMnr
z=O_3>*9((KZLJ2;GU12l+ReK^Ewl{(<+zv9>U-I@b1r4SVfrBy*F51XQHu3g2J0ZO
zL?d<8G-z;X6=(Lb4S;C-#XZFJ7U%txh-dd>8wEmFmITY0>5nn|wK+%9%M)m41Jk_@
zAD8JyuikyCT%7-7+u|``Ebw1-52}`UPkh~WjhST1#u!@4_n?LS8A!6YR=xkTGX}q!
z1<0u$Z<GUV>098ZnzxwK8pE{WdA_&u00mI-VM@Wv-DR-mzp-hg`fthc(kKWfhR#d=
zv+m&QLDvtuvJ9=w-B5sYKb-#I0X;`aGLHbiS1=qM*xG3kiX%vl1-|oY>qTF{&x$ja
zt+(pv+&UJM8rj#o&hVDwbxnpiiKs3RHxpOIIEqL&6Tf*avOrJmyqCLRuW7PC*!_(C
zlZ=V^7mSzNpDWm!T2gn#bQEAqA~i3&e!$xr*!?~P?fPF<CD`M1btrFtXPUOA+~z8B
z^3*R0^e5kyA#*uX*?g8vt!1YC2Kil-W?_y2;E|<X|0N~e2nGoo9M4GCkK6t}lII^V
zY)lkuHGd^>O;z1y(Ift}{Bo(c62N;tTT7&fS|WW7FO=DQF9G2;A8*Q#z$T(`9Iqbf
zU*THnJoV~SUc^ixYPb8fl#TBDYY-5+yo>syj_+x7ol7DMm&?Xh@{Ds{t7?W;%b~uy
z$>HAbp1yYoj&uErMwYkKPTcC^#>vQ84&)xAA2TNobwX1;02PO8tIY8`fOcwL#}`!u
z%pxjAc<QmK=_A0$lIDj>@<o=sDbzoEK?g=VQI68)ersxYbE3L9@W+S~g5$2%3Qx}g
z5r<6hKQRZ)pQ2Nd1^dIV(kXw~POh)M<NU!x^)ak_L98-#F&UU{^B-|8<9M|ZN1R^T
z#<FYJY<@#Y@1*uW&^gk?G^nte)Sar{M8)6=;v}B2m*`6(1@(;O!$!M2PxOuZ&xXPC
zek!K<@On%g9Z{!GTpw|9Xps3okPTs)CM{iPU|1}5CYfKe2Q2s-*fQJVBd#e!sCw_o
z?tke9O~+Y(o8n3bZ*ZX{f@bfm6BKp5(Y+%0xkf)1`V%%oP2q<Iu8mc~Bl8kB$(3m|
zV(Khfi^av)e$ocT6!L_R8HTRtyCJkscnfouU1mQ3`~UEAv}Ij^d0(rqt-OfP=j>ki
zJte@@6>Ya{Dm@6De+f`_F0r6CPw#*=k+u1CG96g8uDCcB+Qg9ulAurEVZvMR3-3XV
zOYA1Eu?mM7K2)hBUl-KlUB176X^!sVT)IHq=F0sK1d6RvBrQg~Ty#uMT&SQo)AQ_B
zH7|8|@;6KYW0nAVw1mt)Vzk$uCJklnLF+$hotC}3B9YWApj;DsB)cP7Br7n+Rhe?b
zqcN@n9}U9ywOtq=7dLecRO{C|=Qf#p<<$t&SPsQWVe@0uM9H+?e?<MU8bmo4l7HCM
z{Q$18(iF1o_F`7X|LD5gEg!<^y6U>SkYl;C1-%P3!XKtiJqg@D-~!${MO81PZ0jQy
z{&Q8(MP*NE$V^m*J&(DnpwMVKwhdYUgx{0+n+$MjKYTn%N5I-=7rS{UPG#jpSO;cn
zQoE~?a|S~X=eDaCgyadI1q!1a%`oUSD80opgpf{`D94dkZlL!IsHZ|`QLehr=37Wt
zSzyh|p{b<gS>xk^MP+jK%`l8sD`k)s&#v)>m9KAwF4jg;(F4#DW3PQMuLbDJ$;KO(
zGh~+Q)suz7JwLXVPQ{RtndPVjiK^<rr`#{DQwM_RgVe2C5?<q64gAr!pFWBiVy>Wv
zTXD5xHr~fm2%*OI!ABKTCKKVrHHeU4n+za>AXH&Z+8G13qT;@E{NGbD-bbYip|~b-
zbMigf)wUj*M23VBcbI6t1$5ev(B{X`7C>JHu=SF~&6el}ZFkFTD^`9_z}iGLBzPnI
zh4A@)hBCmB0Oy=u_>#T<LX!gYlt)V|U*zFD)C_(*iKVwzHp>4EOLwM8;hz;kMIUF7
z{%sj*ryr9J0DM_&I8kL|Am;ZatLI~(4^t6glIW?HdtM+^52vvb13lEl+}|J<YYP=X
zSY$l{VdKxzN7Trqev%bop}2R%EeC3VIe>#NJ+R6;`Qrfx+*{a)8APVb0rPuO%)f(F
zG08hst;wYp{@{SsK3`*w(|mWAUO-;q_{~j;p^3|IuP~gOw%R}R;U`4K1sPAh3sMa6
zUP;^dMn~$GXO1@?`&tW}V~`0~v1&6pntWybAajhmo*uDfmOvIm{}HBrYQCsgX{iO+
zOK1KX1@|UQ&ACUeR(!sqagD6VfV(>QRI_W+8+@}`PFk!QUa8dqZl!?itGc;SK8(l1
zH%F&6it~4ae8E$#L-f*LL;u*<;#J$KaFC_C+Yz8Iyya)ot0e6jvlXwcoa&8D;CIm~
zGS!GfC4%{p{P(?-ek<AXNr^491bYfR;0BH`GiD+5|3D&DHh5-Y)1i*@0+3xTAyk>;
zg!x6boG0%3paFa@PPT<d#!Ti{kUbUa^I_NsFBhsGBz&yo1#2>Qe;}U<JU!V#12lJK
z;A5rSbxL415K%?hQTi{?0k3|Nn$^()1aES(-$$I5-X)Q3%z#lxv51$uBo%USOSxAj
z=-0XT#9G)!(MxfmazEO@qf?-c&-9^4SmzAeON`WtZkaf3ktE=#NlG8OHnsxSQXq~7
z@akTuuv!lxE!}Sxzk+R`K^s>?CodgG`8DN2R=Q*JBDbR{qJPdC1GJRP^p*ItkFG8X
zkpCt$^=7&7pmtp{+n>;ln~cP`B1<vMm*LG*%ipyvVy2tr1xGykaz=1uW}cc1;A*6-
z!y11^;k#HXeIoP10YS=gZktT>&ENKOE|RW_N&q-NPE~R`l5en%wKQ?jqEC#P#dm%4
zUN64Q_L)$*bJU9mS*vR4vvd{$=;}gj@%aSqSmf%<fL=+;hUHb-v_Vf7Jg=YOTxRdz
ziF{Cn`3OA{^~<__o4BuVUlxB)P_a<6RK0@utG@E`bTO|UaJeD^d<8}zvS<<w+~swc
z{VL)*N3w*32iTI%+=HQw18uK0j*Tqt>G`l)UjHIHs>-;pW}$WI|9W;XHukJDCS9s{
z6wd=k)V@&??B1CQ@tleS-I0uRj}*QAafh4x^dU0atoDYF=Xv(1Z}u%pc#PzE-6EwE
z$-fKT+8QG)9ism9!cb#4R7=C)6%N}>We5Kcg$L*BM|GBupanC5^{6?|0wS=}^n9Yv
zBT8K<p+ahFWr5{N8?mdeLmL&+u2yvdyo2wWCcX=ZqqJpMr{Yxs5zkFsi&R49<z|$2
z*J#O)P(Ns4d3k5yAf9?NTJJA0;$qvbyIPQPRM6iU=tnx@^{j&Z22gfhnpgl*OZep`
zw*M`)MetOzbV%8JTK;AD2Sv99s9UG!8t_z9lB->_{2AgNgRtQH8t?uAM-Z6Wnkl?|
z_54(9w!2BQU?=qrBfm?}zTcXmlR-<9dxtCF&0!t;$xL|DuRQCDma^MXe)quwh0BfM
zH9W=lq*;gS-wt7V25s^1Vq|EHr~<=-jRehwuzh8$W|J&%sA+Tz7HE;3mr_3uc$)~@
z(7}hOT2mrjBZZ3l;JVEPDd+PcYYttD!QQcP#|9IFIYFztz9Ph}Nuy&QkgiXH&omus
zB7QC`d~cJ)yEAaepKr!Cjtbtc*t;%XfA^l^U=7`gBoB$Z1oQ0gg|?Rd>y~)oX@mE`
zQDrqRfQw)Yra<hfbFkow)O01{@M1VDtCfKlsXt#@W;35y0#w;qs6i$7=Jub-pk2z#
zcZq(E2AinOSiYB*(#Lc9^4h2wy8qzR)XLxUNBES>W~l=R2eJ;m*g2HUh+X&T3v?5R
z6F~q3ju>+8Dc<U0H}`jMo^JsqFYF#*D8(+tmzy5BE<`!^uALwR9N|xf9F&+{4-s<N
z7>%4bFFu`U9B4n^GFl0=OPkF;%FQ!a#=6x4t=U;OxxSzc2DUi8bcY@EoCG0Lpr<Z^
zxTK8_)1#Z_0=m#uvhsdGK9>aDttq8z&T7_Q1kZhZU4U*;P2V6x?BRYo2E1ayo$$Q<
z3{~v`1ms~9PO2CR?Pr`l*n_9OE_oHW);8^~A-4617Fx_+??0RY%Bup=*xj4Cn8WrY
z`pKq83(Dq(_(bmxS`^PhN2}fh!p;0o;NYQ=b{sC6XhC=~WTu+x!&BLB{5HM2IBf-Z
z3^{paK1ptaewE{M5&lF=(D%6VVmm+Qy<9l>g8sHu?#wc^(yMj)a{>!q36Jg{EKaAz
z+yYeoxph6yN|bg_{l&tx0JLHL#f`ckkQlH}a2uh=D!=>BIq=^49@)~9E7QOMBQ#oX
zrNvTf(LPz$`}nE`Z~hpsy96W`C)j!Lg(1j>{x#nP{FrwZs1JpJy-+`ChBKII2Wio(
z<3HynbeRqoWfA^mz!E<euzbx4xJw&RZ@)mSwCLYB&q$jtl2syAHB5H8TgIhu{%c6+
z6pt3Ia#0_TQKwGwahlQsSwi<w2Ay-DUEOHS@_rTs_P-f9a~B;<s>JEgF=n-3<WH9U
zuUmfOT+Xe4Sm?L%;I^7cmG{pB-PAoUa;a?%+(bks>zB|$SDv*!b;FD5kFcql9Hs$B
z=?CEy`m4INY*|y>8#kN;pfTwA&n&G{lw|Fonr44Y+a!)zS+xbMQ2cVf0etytz#UK?
z(-oNOOpII`6FFgh%P86(;3>#o6v28B_#5+}njO#<Q|M6ReSm{uWlK|pHn*IBrD>@T
zNzi|A3eNs^ks>H!6<W_-<;ek*E6#9JomQHH&yN$U2VUZ}+Paz`c9-@n$U&rLfKY=*
zwD+2*|5zJ2Zh+;=JazF)0@va16BQbGUzhYdtK>OduYM&4{_Xzxt!cL42y<!aA@`gI
za$g0T_!dygD&&sADZGLhq>P+hl3eitN?XUuzC3xQ|ACakgD#7O&69xx$ZtKEUy$`d
zG#j4HTLh>d=$%a#YbBerx)L4LzSO`ruVk-!zJB;c!BH92?Z$<1=<4JFZLoQC1f+Y-
z?ro)sK<6N<1!#2sp3QxvVi2*gf6#doF)k!ajg3c3A7pWDsX<+W-~WLrXoi21yU(cw
z>j&lJ`#w5XjqUDryCiyk#scDZOJSVgsr0v-5jf@lZW>U$+{IJ9gmZ@cfC|Y;&5>o-
zwHI)e$;KS0iklLwGcLH|&(^+<w;pZLUR$h}o5BOzw>~CFjFeeKSbFq$PG$>Gi(m@T
ziTic>KC4h(l<bOOj%=7!6_l7N8Em)9+g-BW{xfuAgBceQpixOGia$7&daMO#2Hk%X
zR_qjD4;F#TWgUrA8qP{(@G9v+jZ^R1;kVf;VF+}kWyT6@8y!Mg%r9!w3FO%QiBRJJ
zFpYN#kUH6?CH>*xvl}1Oz4)!}`;(!itzd-4MifUOa4|hw`KM_B^x3;<gs%u?WtcQ*
z=j=vWWDeCG3ztXFOl=TvVin*fA+U1uTPjtmrhVEJz(p2GXQ2GmCA}dJK>4{V_eeGJ
z@2+@bJNU#ay{~`Igwn)*n>={QSiNNtypcrQ15D(b4xWCkSA2{L3Ytb({Qw8+%HLb1
z&8t5Kl`57|p0Gmm!glgYbE^Y9!g^_T)v5XFDNyBjwGi&_F45gv+#LVjbG1@zJkUO{
zgX471$^nc49;_DRR%tap3Hvr(0<@|7Kj$<yQII7Ru*V4nuy>EEZ&Ln*!8OOu;oWXf
z`tsRqZ8mYQ%XOP<$0%iz(G-+IU;$C|zaEB~>Yi&#3Ljh(-3ZOvN^{#OS-N+1fMQMK
z+^6rxwb%u5Vi(SLmr4q2ERw!1kB=X_I0z4l|9-1y#Uvh}-;myYoUSxfR+-SQTettq
zXMigiV_DP?nxHTxYvS#c!sv?;bF2H)_yl~$V|`_u>cz}9CA9Wjo;Sj@tKcU9m5dJ7
zaDP3Tdv)@HAwTTOjEvLunfHOG#zjr@vAWo^BXt_`{2Qr20KH0WdBndedC<sTx3u%z
zldA@cos#nL1D8oBcfRWdv+FTXd56VCAa)(QFLv1x(a-WnPqRZ1k+FYXIuXm*HUgpv
zCPl^xr-C3tP&MW0&$W&zn->QLP5gG*9<a$@7Jj1ncHQq=W)H&h91C|&#Yjt@nEDcO
z6L(4LBEB5$$sH(HzU=%hYeKtq`Ml0p%WO#_q#@{B;z&~DOY<ulR%MJqMypJ^Qq`gx
z7hu$}KoNHHV~p;aqcHgw-p!ZPa>#``g|RT>s@iIktnv93EAB{u-u+3%(<P&&gzKJA
z0C9P9Oby@;@R4{#weqgx7U+CM;*xzMf+iuO66NMP8BA}9ykY}_vhY7Kwd+G)sc7C=
zduW;p99Ww<$|5cqzT8;K|1y`dUC=St{S-{mui$gD1n46j1}9-x2UKmfzQ2(saP2Xn
z8dnVH8J9QER22~X=w-Bj@hu#-z@n?34mX^!89JdaqQMB~{#wDjt{3NXi|tSsHBU8o
zS%Cc@lUoVfuob#qQ(GwhPU8QH49IDX3-;?&EE?$ONCbd{WhWOPB$En@V&sodN9X|L
zLgjlQ@7D7^u*aZCr24z?v0NU9@p=r@vdSw9y9f;QD6J9DCrP75b=Vd_e|`3sP|0*9
zc*g8P=h4vN+2U~lHr;>l)53Kj^*WXWdiT=doFLdFh5uI;J-am{kb7tR{RMnq#Z?p#
zmI)CDpA-;$X!yST=Pw<ws0el3;z$-l+jmjlfYPo4h46vxaIFMGsmPHwD_^GJbkL9s
z`S9-cOL)fAOz4PKgOh{u+a@5sCj!a#-$SFh#}k3s88?vJoHJhH?2CxF^!f)W-oL%x
zNAHilkJZ|OOAA4wz1ftJlvvkAw-?4z4pT??M0|;(3**bX=f(OXUy??6-9BzQFv-!4
z*=t<9Rtmn9l|rcOJ>8Ma#Ggz?s6^hVNA4SrX;FIV5n5P$n*;{us-w`il(VhP;~Hgb
zWKJ2OQa^Elz_@2jAUgEx0x>_cutDBXy~$_Q-Zp{ab0mq~K-@Q72hu~_%+!0nu3~XX
z)6`yr<iGbS?>Zy$Z5Nd+8>=2#RK`$43SD&LCOLtpe%i7|?^nP5gsYS7^kO!jxX1oM
zip8Op_UDBLJGf45{<szyjf(gmDAVR!=w@}2fCi``I;;$6hSa$OJ2-elv@L|X8~Fy=
zl#{>#2e#dDP=S=d6D#On<3iQCKLuLcKYULBU*KhL)GBv;(e*=kcgNK9JxS|V_a^=_
z`uA&2UG2A*-7Vm^1)l*;e^M;>)c{v*tkvPWFzNx38;%H$=CLSj<r4+Pi;Ch*Qql^<
zKsI~y+|G3FcMl=?$So7!SqSUlG-=vS%N(tz$eVqQ<fERUjxX+Y<^BEPv=qyT@$l9J
z>u<nQgKuN4rWqY5K5JrzC`bUxMVCl7_@BjOoFw;**?qW<!hxkHgIb4o<ALp$<;^=i
z*!(W%*o>J1tUI=zqz;$`NzET*{eoX`7bG1cQ&i25x&5YaL4Gtl3am5bTbjVB3USZs
zit;r4IT~O_t{>V{LGFhC+^4+HK6hQG)l^-w@t8j#?`%Rldol8Qc9Vh4Uh*(@)ac)c
ztqcF${|_QnXdTogVS8{WN=WQvMDZ{0iy=SS$89rp@lu};4=*&MK1g0t)g}nW=M1HR
z?MjuBH7{^i_E+N~BCA{&c#EI*p^|mKeV%l<oe1G~kU_jE8}V(Ktkmarv5iC7m9Pxf
z;5xjaIi`4V-^K5FBCph7o_aoS^8Kq*jqCIe27@H)TvF~I@`zVg!I2R0jm$VZbt6QZ
zOYZ%Yz5ddLsvBO5ap{?3AVbZL_hIW4c~R6w=cr=M0k-jZ6Kj;;*C%YP?;S&O;w`VV
zWHKwe&z=wXX(%=y=%a_tvqTn_!CLZy95(WJVYUAQMOhW5@Y<Op3{#m$aU^XUCPoTJ
z;67!apZw63cgyQ3#<6CKBWBpQVLDwXe(6XqFqrKPzfLeEk(5+t7CIROmY&8tQCtan
z9~R(<oIau!UTAD4YF_kXs;7&&D$%vTfLdm??bkO(%$T6f)-`Xb9Yeaz8sH5tX2XR)
zTp#$AW=Wcx3*@(8eAHD*3a*bZ#%0nY%RX75nb&)-zQ@1oB$Rr&Q7-Q(I>8`v`KZBt
zC{xsemfkQQj7|M*IhtJvzykJkr6Pg=(^vKE-YSz|_h49oHA1m|r&wXuM)K*~qGiIU
z;aUTnrgy?8(-A(^eW;fPELW>e#+bVcSAK_qE<bK}3bGgPlrBUi1^{cXw{9XLmOHA_
zF{nZfF6RXN3aGsubBP3si<ZGL&by+ONvMM|sgL+6caE-s>5Z57{j`;<xSMrdh&?<l
z(lOuXS>g)En*lEcM-qm~0|RVq)r4V*b^Y>DT|sj1TSFnH-h`GnCGCk>OR-J%73R3M
z&gR^jujQZRX=a?_JfD-v>sL#0r?nC`61y<%z~UtaUpp)3vlKkzoLh{@Xvv(fW2A3#
z_b1AARYNUjkHz{Xc&yhB2Bnj8NXld7u215&=U&vhjtlF!fS0v2L-d1{M};1LS0~DN
z4*pfoe|(Bz2vEPKw&}}KEX<dv9_FAKa8olWo6il$S8?`kzM=!iWrcEE_rH|IH77KO
zMqbONuo1}u=H2Y7>ycSIu;T~&Qs9a^1T={I8bF<}mi^|*QXV3~V$ic3XyF#gLNlv8
zmsfC})%b_va!1FdzRT)45!yGJlX7kIZeLI(6^?CUpG)-KrAVA1s^03%dIP?3BrfDL
z7Rr<}1)QVyPKe*$6{j9Jjr#eYMGo&N+HOr(kj!JZM{m}S(O^^s5u#Qh(Za{I0t%kv
zLTbS|aSAwJm2rb(^FkDf1dtYWh=1hrJ)caUF@$sEwkQb?sIzILHlrd!V<<m+P^5n%
zT@V@2NUd|fvS*$y^&Oz{yb{IedNUudRY6(g`B?F(HW4fI-_KI=s(3fLO4e1OpY`9r
z7AUgpZB61v)W4RwN0G>Lq%&4EAr2I&aQ6*~y6RLKl&V+L!>c(W>=^h;hBhJ2FaN0u
zb)N+J(e9fOWX)S!V(n|!yZ;V*rQ7kkZiJ|Ue<ZNm$3CM<nJe{nK(pFmW#3~gbs#u<
zDD}1evsD8=2yG3HPSxZW%mdDm3^(D~yvzZikKd3^v1_jcuOyER*_y)3xp^&MO@<R*
z^qkU(h;+eYX#be}HKsD^G8U5X>WD9DI}PwFIN>EF6vV*x+sUn|4BpbS8`oMplxa+$
zT-eM#mjGtztg+DKhqfV+8j!XsqOyTZo&x4PURjg+=8&nLt4&ILkF~(o%Wr(zX8c=3
z(VUdPtvfVM6s$LZ!}}|RIXGSiNciA;*}bqPlg`p;QBsd_oc+aqdOD67?~O{2tn2U1
zJ7fkUsl1AQnn!$CBhG;zVmuCmJPvCrg03Q@mTZ|7&UgLhZW0swYNPCJ??c~eX7Wh<
z5mY5Tr0;(qz6QOdEU84P*nlA>C-#Kl&>7}mlV%$(9}KG4Ysm)-N(CWAl_)2ya#O|%
zqqC*OBuxPgeV|Z3!Y<W((aPB+wC1rLBht%;I6>=OEw8PVSkM<CR08gTH&06zHP0|q
zBcbtH#Mb1AyQjra|7u7pnuiq6khZ|qZ^G$w;w$}+c$`Uc``Qw8+jUB|R$_p$R+z|2
zm$InPfKZBKnOpF*P$8rn2rKH6)PxWeFPBZDMHsEOaX%0zQM)jbAE`^@v3RM!d`XK@
z7g5Cu85-0KDpdL@1pcd{eKux9?g9@}fEq`X(rp9OuOPLAUg+-QfjPHsx(mEomN7q|
zf-(sZTVM!UfqDnKL_eY*r|<^VbUTsxo`@2V`0!2?xO-RQ;uDj+@HpqbEa~|qEaBC#
z_R<v)I1(ybniF-4;=<I4nnV)fvc)6m*VD%(%O8*6?Xm>~9(Xt&Je)&lddrY&X{2{Y
zgAQ%6eJvG3zVK>tR=ooLJ@O^2BUP5D1B)?CFQ?u^=(0rVvG4cbUrmQ(N!?T>TsI4e
zLrpD)FQVW~57~QfH9PA8?w6m7@nd+dXp<6wnJ~qs&(c2S3u_Yi>X;lC!qb1cX(5$u
zj(Cp^BJOFI3in9NiQhp{sy!2cRetE2Pdsv9gP^y7psyTFAr~fb_)iP-p_QrPR#I|n
z5<B8E1W!f$X27vh^4?REApQ7I)>MvDgL~Bu<8faMF`P>tA-&rK;_^~7)$R%}!yl61
zKhK{oTz%j1aqTrX27y0gl;S@I3F(K}v|n<&B40s__98tAuG?YCn@Gw;F=FybpRX+$
zzc;>eE$>33L86)YLBUvR{HZ#h6uVv|39V)0c#(dv7AcMbg61O`vUN#iP74IyAio}J
zHx7sIUQ`ihN^HPi?8^@SfQ=#9^&;O3wTOx>6Pj}?Ul!wd?bbrm#mAB^71`#fJT36(
z`XvT%Fu4ghTu45qzqj(xf(Lch!BsHx=7~~|xG>wRHj`B_*ctUkX<-=PXr<Z=hI%~8
z0X?pH3ChnDLM-cK#?4q*H}V|&{xJOF9%_6fQl_z{-w@-YJQimSx0p@-$E4rv{z;&B
zO3aak=bxps+YMzRi+C^wj!@j6zF9qoOO_br&@ohoFm3^|+rgW&JuXcC%n4#gHJdZ|
zK<RqKbdb(w3+Lf%X6(=9aEXac73+Jw1%?=8*E1WYvoX;BadZ}LO}=j%-)IRDq*X?#
zq|yQkBc!`a>Dr_bkQgHbq`M{p5`$6FU4nEox*KWf=KDUs_aE>$@VR&2*L7a!^*P_O
zwynX?4)6YPnll~9vMSJ>XIY7C<#GPB+}3g&mS(2}cN4@CvuJpaQE4C}!{4>}?JF~E
z)gZRN`Tu_WH0pMI)Sy)0TBk(pPu=k`f+NQHncR4+&!+!NU7}WZh0_<Qrk+nE3ztuR
zlw6Gk%3B~AKt3<L@zGaayEU=(!ysZugOjAqSjtDBr>|EOa$Z)ySS8oYgliyYsYv}s
zI9&P0$Gy1y&N-wpJL{QBc>Kq*#-c9q9?LdO-G<sc9sH#GSE}9;KiO!`^U$sW?Y~OA
z&epOkd+Mw$FLnPUn{B2y>4xdDy=~dP<AkuNwZ-l0#1f0-4RP>Fb~10P$aJ{174fFK
z=tyC5EXb>M45C1;^2ZqY4@bJx-*EB_#cXQd3mW3OZU#H#AECRZ=`f&q@@G3ef>nxZ
zG1^kYsdpf8mqG8RN}Ys#@-?6OONJ9%NJBmQ+Axp~lO$`=<Uu-FE@3`YdxcQYYmnQ8
z9AaD8vwegvxvkdMyZZHD%;g1Lsp}t-Knc6<aV%g{K!>4l>bFTPcVN@00e?W=C;}#+
z66%-qOQdPLxw_V@v9}!n*jkYaYeQj(hwR|oz%Mp=SN=EgkoI(A+uJ76OeI)steZRg
zMV3tTDs-av44nw5%G{<$1*t`5RTp%OA=$?h4XVzF%1&CGUTN~{Eb?Zd91G+`_t~Hz
zr^8jUCLk~g1`2sBD_)I(J!-xfbiPbseVWO|=&zGK2|n?>#-5b<7UTnIKLIJQ;nWBf
zen2sM&4l1M7JZ4&dhZTNmA7j>M1d@Otae>qmJ_5}s$cECWxOf^_r9z8a&3{Gk1OFF
zd5+`H=_MIW+Oj5i`jxz?mXx!{UYK+UKye)u`+1peOOhVv@Z4kOcHp|TU!!@b?qI<s
zfX-mZ(J5l@{+7}M&HRiNh;LvlFJX!zL3TGmqZHztpgY!(Lxx1a$N>!V1tjr|e{bzA
z`-CT1_524ib_$vzQ8D;_sl^wgmuHY>dT$Uk8`~?h9I28SER=h=nQ*CXSmx3~i73z_
zu^fo@XTVxQ-hI8{VM=(%_ag)@#SM2k&r&bj45_On1=l5b2()X1AIZkzd5U)Hy@UjV
zK6By!1{Ny)CY<Wn<6YICGGoS=E}v|g@2GKrX}V&Ag~!Z1eJ%0>CmyZK1#N4~1;~S=
z-eY^{Vk%Vly1ryRNK2x+#iV-{I=zdy6<%h%8YJ|IK}{(8py1sSYZbHPe@1ZVKV%rq
z`>ZDAB_g)7x+}EeJ`?>B4w?ca!O1*JVTHl$fTb^h2n8~ai&0Fx!<U>}-*p4HNp;Y!
z635urw}{zN1Sd_RTccL(+NggPftN|;ht?GZa}x>WoJ^VjEj5J!pK_B$;Y?daK)NKR
zRyosN8{BFG`VUl457o~{WU}H+bU|BY&|b;wl#Z{45Htzy8OV*(llf{UHkzD!goVT(
ztVB=YTyRM?f++8V3AA6?==?S#6NA2rD`PTHLPU@s<>LNv1xd?W1x*QtIs@|3xp^~a
zP_~AJ?+%r7cdIRbFeI00({i<SrA2pM_x`QP!MtB$hx;Sw(XIb~pfUmF&G~@ixtW3s
zc-X<K(A!JQeu8B8J4}ZAgU~Wf1!4s$+NsRIWh5tD)q5+f_}gx9QF&T;j35RG{-%Oa
z3UAie4c|C)KF2C#2|kPmUtnHsRX#UM6LnnI<sCIr>LnqCD8&WTc>z;Yu7~}aUX9Z%
z>E-)c+)e^3U?+2<nqDV7S(B%4N*C>LexSd9DYhnH@^RcOuBxR7{6*ZmTlKl{q?e@6
zs}6FI&?)mRHL?VY0A^sE7Stsp@hT+4@31ONPl<pJMuQQS1F?*4wB(L?5nT;s0N3I-
zCX?iI$<v$hkr}s*nvA+r`cCz89q0-9*Gv~R1A6(}FLVChF>nhjiO)eLomm$|cE*A8
zJbSDQT4>oc<2&7KVDzT0DdBgPdfo|k#rgAZ3j25`j@a+fL&sm_4F&g!$5WzhO_l2H
zUp;3|cJy+#JDHfR!onmRvzFxGQ9q+X)(EoyTqhU#c?X@qdqDU5LZ!^M-RDg~(+>YT
zRG9S;IvU!o=|=Kh=^1dmU>IHI)!*fbZ01<Eg2mb!ASo?7esRu&Y%_nj9x|5k(^UvN
zjREFD;td&d>p6S;F;^kmyJrBvK8|~zTz#MRx;)Q8c(8S2>@4O+4cX;SXTPNx2h004
zZi6zfkF?fTmfEYf;E|YwHlllwi@+es$ZdLVElLd96-(te%1=qQABdnyfAzwx_C{_V
zS(gSKDt`5Y&ZSnp3imFX^VIvZ65#<4=m01D6%GFdT?+pW<s)QWVpQRre8BUC<=?xt
zCH9Jr<@pD*qv|=9)QXdbE^{x^<uO#?^y{d^^pf+e?h%_*M;`SfxccdWeq?-({{_nX
z4*&IRHlE`o6X9JfzBnk0aXK<W9JnzLe;wsNU}n9Sycmr608~rHKD#b}I#wLx(7K}8
ze3yeEG_31J1OZ*OiXJmW^vW0dLfj~wB`sPm7&snZ!pS;=9t!bDwE%LuYjuJ%+r;x*
zpv;OMT0j2$T~ho3)mBxr$Z>Ho?XCvyr(52gNND4rLgifHieQOU>mq@FS&LlZ4`?Or
zUsW>33OTYNltiLeaLW29x;uwdqr{a!`@Pf|9AukP5HB^(oz%EbkES~mB{Yuo;kGEv
zS<1ZnIu}z!?DI_Jb48ivu7Zt=AusNy0b_A0uu{#jg4g7$r{o7N`jwdd9tKw+2wUJ2
zxOHt;T|JM1AXlzkc;i<!4d9B3xzsjRsp)>aqu#iLN>s*_b?lsT9EhT+o1iC*wS?0=
z3}D)G@e20{E&J<gVO7pvuN(X|WLxX?89#TH`57>s(g}~P|2>%(3z#EuQqJ8ozKoVW
zxw`<m(usn7$+ieZU5QX?KcbRE@}+qt?_+P>1fD7iuV|~eDZ0%Ne8TEDeaKABSD!e|
z2!25CKV6q-M&=1C+FK=M_O&uMlCFOLF72mGG6OZ;RccdXN_sFy?ax^C-D+VV*>YQh
zZslDRgQL1ThJsojSI()Msx7f8y!Gh9u{8u1|6xS|A@>|$!h$ug+zPG)6<iL(@$`Ky
zm8&)X%7U2crGQT@=VaY|sZI6=amLjOI08%blHVRn-3S#DKXd9{_@sMou0ovQ%eLb5
zIu(GJ0JfvTe;Fh@g#X}W`5M6afe71)2Q#DoA@-GkwImo{TmW3^k5~|LNjg!U_O1Ov
zD^0FXg#WaIg%B`tkbOV49=U7gy%NmCMv-;XU=RFiF*K0GeXRVNZjkhYrIOxETPhoD
z<|XPw?P#T1`%9WJE-P4B$gtJ~ONUz|B6(C+1IA6b)Yu690XcfjWV?TO;Hg0ncB92U
zU4xWSU2sdUoc>veXJ|?C$-85OOD6(9R!d*4-l-sqBmhnLVrLZLPgU^T3uL@&f5t2i
zFM3wRijKd%Ub}^_(@cY>)T78%-fH1!)zjVhIG%UvBv`!<nb;s~WhohS@pw316%gv^
z%o&;Kka&AelNpxX!C+neq!wOFwkL*VFlLQ3U3~mkU{JZ@PXC)dl@IEXX~KzkxS2Z@
z*c9;{+5c(M^c<LF1}jw><NneA3Ow(qlY_gK0mjqz<AW`O8a!|E`(|-G`3A~c!w(6E
zYJCYYdvh^=ToepXh8h8l+8v*ju6?B%BlXTD+)SY`7bIBheZZ0~HO%lC8Ku*SmfN@4
zZVB;E23eV!mH{T-JGcr-!4zIpgFWuEev8ce@1yp6Q}eaJeN@>~w)0|~=zNg3+dBQq
zJ7}wXkQs$9#Cl8f;A~K&<gbZ!rOXZiJkWU7avggxw-BsS^Dp`8bC{aAEZ<{#M>*)K
zxg8M4fK?N5(8Iq5%Sif@+U3TyC(3R3sS@xVv@w9pGwr}<Nl<C_H;=$WRsVthJw*m9
zlz&+NI>z(Jr<7xL5fEHYx%f^6!G@dV=Ajdg-=|&fIE4`6>bJh8ty}uOMQ3<K+$l%7
zc0!Lw_oj9gto7nM>c{DBY|u5viiRG>rhNZ_8~~rqrmE(bH#KmHYVqdg@u01ium6GS
z2SK6LO{ziX98aDePf(3*cnBx%wOk6Z&h6jKMrPFYbZVo74ht*DFB-<c#Xs*izh&9h
zcQPAVzGQe$vVDS!^6v)r^NKjmSd?P+&Rrk>&{~eWn=F)ao%U%LDXY>v0A$76MG$nf
zICOl1yb`wT=JjRiAFGPp=h0hFhf9=&ApIHXnss=sqn!X8M0O!eVwgRp`hmj1cm51q
z_&!waX_VN0z`<%PZBzg76_A>U3&2sfL%bB3c1CPR`80T%v*<svXag6^E;jjz$Iu}4
zf1pR~pf}vPj*~fzSr+N9%s{l0>Gv#&MqPBsKWPMSH(>9d;lT8E?~ka!xE~E^uFiad
zGWr2Aiv0Wi3tERAdFWV`u49N~dAa7n_&-PGM=TZES7ReK@@eQd#u1a(ju=YSw|0yl
zcVp!6Cevuc>&VUOcaO&u#rsIB_fh0p>~#hMHf1|CZ=y~Yw74e=fOFq_!BTPuypn%e
zKV2fPcj#YRiFW1DF}7*f8ALwu3(FbstNICMWnhSL6;Nc%;+OeElr!fD8%8>c+)u~e
z@!eB>;ARfHu(BKVW63qGeho}vy06X)2McE65-{^`N(q5e8naJAF?qh<yM1DL%PDVZ
z@`P*a;~;ghJeD5a?|^u0d&f{H?`}UzIOEA#>t|Gy=J3XHZ;G@C3%&DxMe~|}N7k)n
z+)r>)`9ILrWsU9~9Me#)p|gEKzDFzgWY+?@{unCG&+)CwvK3@;O?}JBU+beFR%Km2
zM@_jP-Tff@EyP8u1k3S6kVzs-15b+0K4sDpauA?g&Uf;ObSX*gm7`d9j(ox?n!fr4
z^i>?u^=beGUhN^~gXLXDm3_rucM|L#r;~s#Zj{8l7T50J7>RD~+c>(<^UK42Zub|L
z+QHTS-Ti*uQ)Jq>s}Iwvjoy{`0u9q(U3MGqZ?m-jK<}F@cVsm1Q~tpOYU_<$LXBC;
z5RNUUSlc4^d+av^J9q$?Uzcy(y4(u}GD#kvN}c(-$j`h+#u%#i=*SV8G|UWF`m^J>
z(W|Vzk6>->R|*qAEbuP?U=m4()gh}X$X_d}Oxp@#x8k=hcehxaUgdOu?tSE8D?p@C
zUUjZH=Q<NoF^2v5F<U&ibf`U88U<i1fIPQzDzNjboZ6VOU)Xm#*01?O8mb7Vbs#qX
zb^>m;zyA~B?9TFk|49H@MG?hB?KjbV?GC8=&N@Zs=plF6r_Qw02EVf@$!E51A5Gkl
zmlse-nMs!q4>jFafhoeB1hys===N2Sl?8X3<xHo)H>-2QXGMm%r~cw=#VZ>a?2Sg0
ziw@0?(Wf86hTLJ-7u%Zj#Xy}Oa|QIEHdPsGgFqEyWjStHB0aF8Hpuxd<B!G*&Bw6%
z?%9JmiQKU&lnr!pA#TrLqGC$44a<Z(C0N%g&h5~>rnbgOzSrK$rq6SU(mH2$I~P?i
zr+-mutJO71U2zi>4*PV}{=|LnOBQjUvgL7<giJ;!tdAKKmj`8>a8b)fZWMDJs+oJ|
zLq63)j65lHKayB~{?+a9PGSAF;e*$yb$)_ZhC7k|G;w58fB#Malv7eXa{VbR&W}X7
z;Sw=Ngro=$%j<V5a$xii|M)NZA@HAeF@eLjP;kiXz|*$h`3?!Ebd4>MWW>UT@>vlK
zsV~Y2f5_SFFUF2qV|7`<S=0|Aw0jusE$30@-<5#kOsSq*9E@(7^_Wk4r2yP(Dh~!*
zvQh{4eBFnsp7^wjj>p0AGgTj4yfVJWQI(rwFulE==RM<4c(4dWafy}srBVqM?c?4k
zc8{zUA+mpy_nI?HG<pGW$eHMsJkjeCkXrIzs!Dh~0++bj))v-W=><GU=5^GnuUH&u
z-?POSRXTWmuHbgwc4>do2pHx#Wq4HcB;9UygD=PoD`4lE5|bG~?q&mZyxuIm4zhxi
zekHBNDq0|}>%bWn5MqJVtuWCVyuvbw3w;AS(*3g6*>D$*{STBaEj|bpLqY28bDH_6
z-!piO`3-Y9Y{#h?oUV4z@PGcRS4=Y@+53ncIH(xW-gqW)b{sHuvcyMz>6ScIkqFD=
z`vE7*$n}Z9+N~hBhd`6&@MW-bPX_yL1P22S8RP}B>BS8bkv*dFHJr>2-UJMHd`qxS
zh;8cHKuh1XW9~@r?G{-u*7AA;I|Lj(snDZ+UA>Wmw`Vc|BQ~*f?SSo6h1^#(yZzN&
z_U=2Q-vRfN&^!pN1=zmP+r6BCmd(9cY>C|(jS`%l{&m}=hGgKzKg+n?`kcJ;R{M=<
z`S1@%!fMSM@d!%a?Ycb<zd_54ii92fw_s2AZOGBpqg;X$QL*@dOI-mc>)31#H9}B0
z+-SP!1jamEFi3-Q6xS;{9!stg9->GtGLHOTsx7zi!E}#!I5v3^e>=Y!Bwz0gT{YWU
z@)X3fec8O$mniHOvh0(&_<T-v7RnT0;dP#i|CkNmt3DlYPerMc4Hnx!t*Y>Ox{9`Y
zZdz{^iCpZ2TK8z)hk_)6F{I580*@c<I?n9&0he~P!z)p$Lpj`1eBnjqCckTi70oss
zA<Lop(7PAH-CC*|bdfyfNwFQQ)E7TZ<_ao&Z^EaXzdx}W*{mF%9Y1n&<l7NYATlxl
z4WIi4&4U#nZ#}lV8QY7Cl+=eki5SOe)4WZkbFftY!5{yDu@A+&?D#)~{4s)`%#Y_y
zN7kSt0Ir8hP(WcIk{FM`czGIt$7O!dZW>hnk?f3l_JC@MpW41ATMFIl=J@5t=gwOj
z$LWoMI8(4+4&bGe+qZhC_Ykr3^9!KNobI0rj%UmRZ=7O1(o7Zi72yOjEZej_b#!N=
zt|35v>y8urJhNo9yHUdg=mw+u{RsSD91F=@{8}6KCB{c*DJ~QOyHyeHKg}cF#=Ff!
zhGOs1hUC5rcw4hmFjqD#43+x%hr_BZ^2Iv*D2bhVfQp8){z>$*Mt)3!BJ15Udl`{E
z3xEStq_b^G?B(7w1eOQkysQ{9?XQV%dUNFf+L7$1>_S@ANQj&uSoZV&TW3oQ@Y*5V
z^CMJglRsgA-&}Ke<K_-wOqtB~WGp&&5YU}!fEphsi`ZgHk&bvQiLho(-S{Ji+Pix4
zo3@EjMogqbbvN2u+h|VrP$=tGK(@^xF}cRov8Fmj{2!Oc;<2Hm*UvWAoU`KBmuWAg
znt}F6d+p|neQ%+BZOi{&b+UQ~htjqav&dhPWR{Dwa{xenwm52zWGvsJ;-`d{`Q846
z+?Sg2|3K>2FUPUq!k99LvF^38j0h3P(F$ZuvoL$j5A#yIt{{(>Gjhk3JVzU6bJt(A
z@~dSFOvdD))*|lZ^2DQ>uLlX5sWCQLy?OZ1?TUm0RUAQ;l+k0qp?YfK=C!9)Wuy}{
zVul~mp8I;zqvftS1E~hu&Q`u<krBK}>uvn%W2UWAOVld9N58M5(jfnqB{kF95k@wd
zNW3~^(UFb^1jvnYf897^mt;H@3<oTBVJ+a(PJMpZMj|lXRrqtklKa^B*TUF?VMOa4
zT#`!}JmhZ6lIrLXVFl+$*xg8T5qzX7m&nee)e7nRE3@NF29m^X4|p~H2s?$YsGis#
z1*4EfqD9K$GdCz{@*b^&)@MKvDZsYRBFnf>A@#fHMfu(EJ~XetHV^(tUI-4Z4yK(=
zCn)Q9@fP`WHI<6S7%`WiR%h|$rpY3s@xgq9&Q<q?s!3N3a%+%qO$9RND0%aqlkj7<
zKZ}-zzhKytUAZgWt_3EVJ>U=-m5spHg`F&M7hDvQy<-W*;)8bVaGrmfw}Qo$zGe70
z`~9@sA6cc!QQ3eORAhs)54#E}XTD~Tc@b6JY44@+zI9Kpn6H21{(6}J-sZ!eB=F*w
z#L~yJM-^o@{X1HHgcdV-W@7X?A`&X22f*5Z4g*%xEe=6va;v?!qzaB_F^FEA@cr$?
z?@y7W?k*T&SsgW`wyz3C^AxQgP9*GhQ;Tmzf5)p&<`5UNDJ<IN^kn0=@_sJJygJ0a
zaTWqq(cmej@}2Fdy(QHqowY%({T{B59E<oN3hZxC)`|dH^yfVg>)4~)>-6;-(fdT~
zT_hMl?4)mvC){!V@$`uFQ)Np>VmV!!Bm4yuNyV&XX>cO`16g3Wt?PY#5>UD+a+>$0
zt_V7Y8mCgpE5Y3JZTY#^>Z%eH|5Jgu@ikrYKGQtrJv-j^8#R;f%~eqUsiIryg`qe$
zHjcsMzVXgy?W=*v<(pGa8W>hIyuByl)D$M{&$-8!6*>?yLrxmA@87#ARP5N#865!d
zm?mJ+jT^5>9Bb<s8-x|ic93e_d;)k@Ri^Swiztsq*a7qMx4hp>EoE+dl366JM*@Hi
zE?c^Fv6Hu^LL`dk_ptZ>u)~byF9^lu*vW02OE3fXbpTipWCWf2iu_fh-X26y<#%@b
z>C}W1lcHvVzt91mrj!*zV<oS)>e`+?5cF^0ai<pjt|b-ShLsrD>s->c9)1dV`5QRs
zt&(CI8MNJUVj69^ECB!kfvNC6(wP0U2jVVF1sRiVl-3h~OS?52gFtt9(5j}!eD29T
zDWR_$1MaX$EgY<TE{C4aO(<@LN%8Ljn8(_Mz_Xly#ey)LHOHs}sHggk?i3M9pYDEN
znSCKt+c-1%-SWf41j7!o<cw#F{-{63gSvhORh{Z?;iLXbJ*};?t$Wd#QEdFVU0w8&
z_d`oV4_HOAKFom|o&lf#DNb>(!)IfzjhL<+;f8Pax#hn~cN)VxXm)X3x4DK3iIbe1
z_->kC@DiQj<oJl|hOBr|uGPZ78N=zW&IJDh`LBNMw3x0R{~=Ny<@ZZ*3;xxGlvCc-
zdxD<F#_u5-_(PlUnJQFP&J@WfFaf?2#oZe|pDzUC$y7+IHyZA#)43g}r(3f379;OC
z7_iFS!yfxUa{8_UN!Ft6)_Be}h)>00#d)^kK1qA;n(G!V?_}npz&gs;uGDdlXIJ;Q
zv2)@qUI3V|b)3_zR4dX!&M~1kOiy_dfQLAN$_r)AYV(~LdNvUL3hx_A&GprXT9r`I
zf^{)L$&Fl*-Cn^Khf)buwygyhb>n>PuVacP3mo49IX(;7aFIqM=-h92)T_4NALaL`
zS6JlJPNhB(OoALzsNZ;G6VP-$mpDD3VW#!yYpovxe6THi3R9%&y?GJ{;_=NxT|YeG
z|GgZ7g|ppHGG?H&yOIXqKA3z~WtLMf!+65+$S+gm@)t03?!u-Sn~#tS1v5h6i!<Qp
zE@&z(GujlFs?V@=OC{$)=3a>!=%uaq=<~ztu17{#nLQ?~h~I{+`j^qUn?QXi?+I^V
z48vM%G)=*XHndQ68e0wKg~;%*=644sOZUBWWHqp|D>l3EIAmPI`+D-Lb|=x?^L5qz
zjHGb$QCc=-0kiW#*^O=b0q3F1Q*GIh&qp6Sxy+yIF=m(Ka_2Zd|Nbr`wN&lx^r}|b
z%sd{jdqwui$YhYCW3I2DgRIUH1)7cCuB`NOXfFKY3FT!iu?Z!)(9X;gwVjIxW!Ws(
z876Z5f+~eL2n;*yctkH>T<daqb(G_!U+YenvdOhQNtt>#>XH;4_PF9uYkCXhF68=*
z)e&dU#Jiai{`jXgP1{-v?EFIDgY7!;+w~LKKl})Bi(USpJs4SQVpH8MnS@o^dY>S?
zZaWfXJ9F@0^L_VNDyiJO2>k^nF73%dOjk_Bhl(Ux;>?2*>Cb40-$pco3}h$k+A}ko
zd&hCCzPY|ezsDKr{U$>=%zCZP=?Ehihete@7cX<L8EXL6>h>Vc$eMUkq+k&HO|-~n
z^0~;PK=Gl&Ek(|P58T}97okd^K5)qgd*U`1e=Z}E;5g?M`CEdb=aqcJqNg|+lY<a$
z10M~3Mf;zL32j0KumtKSR^4c?BIhc_0e@5(meTnv_%z>zerd*2a=oXJya2;mYkl(v
z;$6-vQ2T35y36zNrFI?ZvBpUx>az<c001*eu@Pm$#>?uh<6hcC_%E^ZZfCkk1pzg~
z8?Kl*kDF+Y;DPi54T&nSZnm^iT)6GIuj`f*&#r#p>`|KM8@+D0OG{1d2Wje<q7fSY
z&5<{+lpgU-P1ZN=+F%a|zb|ckte&btA9E0_P$LN8zuruvwZ@>SF5&uR#csk=M?JiL
zwkGYrxHD``2=i3_8Lkl(mdx38zMte`sR&`pR2#qQEjwoE=Klxl(^Ov=o~&fU9+)`^
zY)%{e$i-STr_m9}vW`q}@p3C3rymZ=<u7HzD>rLJ<ZiW+Uc{E+^L4wUrHB9;7dv|n
z-EE=k5co=Qe=K|96>?&2=~)5Yh)24cR07usihgV1xP+y+60s^jiSA?(1th<XR7ZH}
zO-aXv`lVj}jFomrB<hnq3uFDY7OuGJ40LDOvXLQ;a;3%Au{p~4;Z^V8yW3^o%p@9;
zq*1i&D!<o`Q7Lz40zOEhnzBpX@@l-F#z&X3r@!o(*u{&qP`2Cp?q-7<ksT3;ktr+J
z5NGT+T~`SpYB@3g8I(Bv#i(+nNT<d(JbU9j=qKEvQ7yAOj^ghvAI88<*Fo|!lZl-H
z7Z|j_LNIf{aKSAm4-E0Ooz{x$;^&|T9gf9z@pj3rXvB5Bv0b8Or5^UilfB=96X?3n
zK6LAp{wR9Y3Bxx?chczd9@i4DEP6dt_FzYHYcZCZik0_?|8R*CwS^6LpL}^iaIxrc
z$`$He!BjO9j||d*ekM?H*oZVxZ$7K^pl!lkXXh~;MhDzA!VaFfKAA^pM8v3<Fh8}#
zJ<2b5=c2=Oj1`w33!r;?J%)KXqU~>)zMAT9#&~*|oB-QvPoaM%%N*4<tmLAB|6<Wi
zZMPQ=3J$I2B_(gvwp@%Vl5GnWFPC4@CYt&scv#8)ab~z0r1#FP45iT+3h65WGepb5
zqW>zkYtiFM`}?l@Q4<e^cTzwZe$>Q;f6ER^Hygpru-Vwxq{eR;3kvuRfDgSva=Rm1
z;J85%iu5Ce4~$=^K>JydU{y{RY>X0~KgC%3Q%HL(DOVg&3E;hC^VpV(#a%ki<2Td5
zp$oMZ^s>CE3e-Zt^z_YpSo|N`nx>$f64#$bbKIL#{rv7Eg91fL-@&CG-{2}0@3ol)
z%wyX{9M!4(;eXCp+SQeGQ{ZcL1yR@<-Yf*{gSG!Ra-&a-L}a=bjp<_{_AV-fM<Xa=
zc6zpZYI;()9;yISaU`)t-QFu_y3ydXK{+{*LBYsh+CkfrlyP*sC>54~DQeo}Cih#I
z5^gw1tEb7|j;AqQvs~VOMAxfL@PN57Wdv7--(xeywpQYl`kX$OFGNFRZCimn4{Em~
zi9P~ADvfs>eTLUINtSW-#GHL%a&<15-jdRVYm>qH!^Ch+&c~giHtMS)*BW?>Iu!-&
zlr330l&mjJ`+oh<r@5iwrr0)g<%{dxLJ_=oJE4df%E1qTJEYxHaunBz6A6O+69QdS
zdxu;(?$j4>P;%lN{@>>yU$kA-)RsAJeKeB@)3tDT6?Vq!7H;Lzm5^SrtODp44d!LH
z3sh8N=#jV0_hz4jEA88X3wsS*Lr^yv_8BZP9QrjAgCVgk-Lc`9*nO<REy#i-=Derc
zPwfH2eo75dS9ThI6sNN~J0N2Qb{$rv&Z!0MzN`HMQ$u6R9)g4nb7Rvj-uYm0^ltdc
z&zm`Mx#FEKhx5Q6&bTg#rK2CZR)Hc7{sYnf&S84$J3gj<F_{2v1vtNW3PkU$#v;j0
z;7?!Qp57J^(>d>7GMK5jx*elbqwf0Pf7;ybb=sevoSYmg5a6?BDQQ9O{1MytN|`IY
z7wA+SQioiSLG+uK8*+C!hdi=^amGJkya0=9>kqGN6C0<2pJ3a-(T|QqgJenPtbbk?
zrQSp;lXi5@UZ?q=QcUf?59%`2J_%c&{E^OXpDnUxhWTz+SCqb9GXUuBViBKyd2id+
zYN_{e34dY_m6kfq7NE+qj#b$F9?iKvk{u0sQAiPFl<y`SV!4>BvQ@$x4bwR-e4p}Y
zeK{`thjv{Tyo$GPEtnYrKNT*dqX(8${4t$Qlm_2jPP`{lDLq;3U+IrWbG8pUkl@6H
z^c+r)w>qYUu&Vgc6*as!_=4>(JaiVt3*Qrrh@2~Y-a%~=;JsQm5xvpHhR8knU9$8r
z^OeT}@9aZG@n$ZuD8Uc9(HLc`jdhV{s!BPmkS2Q_`0}wMedxCO-OSCHVhns!@L476
zLG79v#k!^KmdXGw<lXdX9uGa?1HQGJ%Pf4pqo{9uyNb2&%y>Q(Za}itW(L64T1A+f
znstO7xOhNB^U*a{Pj1ca4|zF;gn1Xw>INGWbG1Q~MHHaoCdME+ns8rbJE9xImw9g}
zbEQ@3u)YV8Qn2EpaEt27(9Kz+3f%37au<}Se5!rPBk=T^7!;P^gDgt*i5y*z<=as5
zYa06=YI$E{+NSZbXXuI@-17eG@_SjqxgqlF>RY40QkP>D00-#hgzX19*S09W2j{SW
z^)AB6JcHcG|3Jk-SN}_vx~>p+h2h~@f7K+tcu5ta)E0N5PIQi@%VFKDkI7W>O#aKu
zz=YWDqeJ!^dxIj4-)A9n<HaR0n(;!KTZ%C%7OBUtZ*SWP$AY+(FG_Q$z-C@5qVdc3
zpZ}F*1bW=UTfaLJ-XcV=iSf!F-&a`vk6_G46UY+HlGIX_XHIw5#^yc2|1T)!w8s3e
zs;JRZYlj2lopJvvBmO0x3Ll&F=Vl@y_}8eCSbeBf3gg#s;!-e!i&K9%fgyhjufzb~
zA<8^?WBSTw4!TclrCH=&u5i^YWFsE85l7({m`VakjS4g3S=#%h#CRYwcjst4>XjG2
z=}Q(eZ)S-q9-Frct*>TW;rL)S<p})fa@B|bKbb_MDSE-W#pyx^7}<&EC%N2b6319k
zbtS7`6P1hi=w?Z?Bt&)=Ks-e5<q~Cq`ke71be9=28N|itHwQ>L?y#RHnM)=RG%Vod
zjLgY72OY9z{E5Eke<10IjC#1gumR+B@^-uPO|<<%&jnmk#Q{yo0<4zsk55Kh+t*HG
z|HAnmuWzXX5?oUsvV>qXmksfi^nba#L?0`neRn0rw<G<`$Tli$N5a+jdinVrfc1Al
zy#zVr#2owCOF{6%qsS;(rI>?N)NhyMmQ)0&$d$X$?+$gn0sAVlK0n8PZbYE_mfowO
z(aELzICqW+l+xn#XCi@<<LWRAUHymCc{ZH<LX~;C)MWnX+~@q-CV@8=x%%<*%>5An
z^w#qFm(cZ70NId}IflC64M=cv?U-T5p|sq-OXCHc0bAGDI7^#0Y|73w3p!AwR840A
za?xVcN>(#Tr+p@v+Bee9x^65>i^0kCIPP#9>)c59cu};pz*qOhbYt#%;(1yizvD}x
zH=KXSIg%#jH6Se<n(z1hB`+|{m0llcqt0=+qbAVrHGt)t?u_NPoF@wQ82rZeKM{2!
zYgur;_zURK9XXneH^R$cOEHDpJ6*?OmPKT&XDi3zM;HOj_}+B&=}C~v^Qn7_x@%y-
zBxRT7+hB$K$Ek_e=37Iv?EP4+oyAKd5Tcv-8rTnR#yDLOEsE|4R~sF_QtbO}BR-oh
zJG-`3p}~%W-sPM0Ip0DXMNQgA{(fx`owlU!IS+VGVs>TENdS8i+N%_DFYU1$-9{{k
z6LN{OzMT@SUcjbPFd7%LXUKP`XY~275ZI}jQ+OG6QmYetZ<;5LCt0w5i(<(v<!nck
z%QLXC&UuHM8@MzrEdmDhH^xbjmT{|FBmb8#wRdW0a(2e&ck=HIrc2*ija%+5TgeoN
zp5kNVlO;QYSN;QewO*gLB@9l4@J=f4?rS!ovK*cEbr77o;i3e{3M<R|8NzF9a!*;$
zSQg~)sg{{!g$ZZEtMW&XJ@$fGME4K#=JPoHmVU9?e)J5v@BdImD*8$tcMQJ~z3W=^
zaw01(2}K_=RjQ?Hgr^=OyZ3ju>Vyh+zaXP~{hG$hxe`w1J2KB{@&b$&`$#N=bH{G#
zdW*EPbBzZmC6K{#u;)M4UNS`5`PdX9N_tsTT?Ov{YN`+q;t5b1t2D9#j$7TTU?Ps3
zc}OX=EC17X4~RtB9->?owtq5|=N=;!^RH0a-V%0Hk#HAv@W%2MR%Ee!ixR56C3oN)
zG&8=33egjyH}hb7L|qF?>JEcC%zhm%F$>$X-kIn1_ld1G6NEU=_-N-DESke^Y8V2p
z8<A0vztdNO5$I>m$h*&=vlwlN2SQZ7`W?@|E_agWjE(SjIqbNyegJ-Sq_(zJ;|(k>
zXo-_dnS@$16Dm<ndkdD#g<0SoOd6k-6s*)hJcgKK&Sm-SuzeCbyc`#K0|HM5tL}L$
zEbmvSI$ZLjYo|&P74YB2|I`P~2%QqQuCUJzC4uA9FAF)C_(<HTpD}QHKOXDRwevNC
z#=bcN?Q*xgw5BhCbr##D>Ccp87ifWcmAnwI8FgmAqJebeE<HYYatoJwN`if#8r^gZ
z|DDXlJ3DhrluKy{IJkZ}%d0m7*1LRXt}4;1oRJ2|TBkB(4jL*OhUgEFQAcAqoeoX!
z@mv&MVgb3ZwArZ>^TC5VtC^Khty247=?-2_MQdHl58J)}yIHv=tX11jeS>T=rq0LX
zd#(JEWPTY47S2A#y7d!X>-kpB<JRt<OCbQy`q}m?D>;iCd0>cB-7TaWSa_6U<~hVp
z!IuWa%s6!4WRdTxoJ8}x2gIDaXhei)SAU)+oC2cnw0_MFD|5L&!}u?W^MfbyoGw7n
zv4r8T?&FTbx43|3MVq6Q@Y}xrzZ}H<N*edLCo_=N<NviE-u+@t18I$??Ky`WS7z+2
z#{@LJd$MbNO{_Y_wo?7p{8Ur6Eg*UR<lI3r##Q!3k0M|yX+U1g=Eb2&GWYFHF2TA+
zYfc{()kh0d9t0P&WnL!oU6<w2v_VqjV(#(aDYKrC?;5^7idv!7BttnK-7S+M`OZ8g
zxseJCy4f*WFaQ---zA&mk9&Kq`<$lH&&zSz$1!gxLw_Us=sp1Rfkck0b0=B(a`ZkW
zs)PqMA?@&;uA&iYBputjfCXYMIMDbL(JS>gA2T=9xFn$Ktd8WqpNqR90c*&N%RzR&
z>~YUrE*Hc!IZE<Jf6`U;mqcV)cFq8^9|AT!5)N);tMYyiRQ@j#jh1Q$CgV8%19>O4
zWh_|6CaJ2~N@SzsSOfgL4j#NLb<<_7YK_*|eb!)EZ;#y!yu@Wye*7knIV%3GiX;D`
zAKrvbbQ=)<U0WuRJKiHivo>5Ub*Ro~l8(%uD*!;n{!GXAyr8n?SdSrOR{-@lrz?CF
z=przRkLw&en;1dx;!C$>m>NIx;YG99&#bMFg-NW&HAM?=yBtjiphB%Hj@@fsj)<Ve
zX4bYQ*|zF@A4}56{F22wlpg>Jdz@8z!hHaoaN~|M`Ex9<`-7OfYN02Jxq!SB6Y;Cm
z$X_tSC(-nbCg)#4=iQJqb2X6rlGiFX`@kneq8`qu`m~HuC!dwcGmA{8uEl!Zy7H?x
zg{r{(&wjXG&NO@R?^kItm;V}_#q|O_Ei&B{Goc5g<|%$l5_`fJ;{QNPf?eZj#;jWN
z<QE1yif$x`1xgu!PSu8acO~O@D5H6%#Qjxzw#c*99MJkUQ4R3|Zb&|f0r*Hm6YKh@
zC1WSd_fB_eW6WIpQUhPUSx)5U{r;(io$@!CTi~B@%Ch&Xc4wQEH|Em)4+J%G5$j#=
zfVW1`k|YH$RNS`D9^IUvyqApQ)z5YNb>`gTT{evh@`=t|#;#}7%X0Z&i<>5mI!ffh
z+lRl@Y_MYAm3cor?di(3GJUK2?KPr~zQpj6BJqBUyZM4DljzLqc)rbG9R1p2j_ON|
zr+0CL6T4b=seDfRwi<8Kb>$W4Y*byf5Sdiq2UvHUhdd=yJO6VMd7gXZ#GHBLEO`Nr
zO2>YFuZaUXZ>NHASk_6w2a3I}AAbyt$rN0^^NKqoyAr2&nASfS`sr$*W2bpsKHt@|
zVVj!iNb%|==0}~&J@*>I=pB^ifpB+*p_6yJk1(f&i+TysJX^y*34kJ+GWWMIEuln?
zAb!{^tteSZ7kOp444y;B?&UQv^@9Xe!i}+9)^TjS5A%hfea2k5B=O|r`)9N3q4%@e
zDq<QCiE>w9i=F@HO#|D@e^eVNNs<>~MCWagG4z1di)ZAQXHQaa$20%s;dbnfZEm!r
zVS*P9Kp#05B&wM*wPGJ7C$GgAd6?<5%5$|ZNQmofqB;~4lB(+6?pK7Ik+AGYlFydY
zV_`y;{?@gc^U+m%_+$+>U$C$Eb}aKZI}XqZ9E?X374E=wmr_7jXGCfgfgF%~jmBpP
z!29IbpE&XzvM-0vCEIxL7j{`VVmaO)?`|;e4dPSYSb($^WnPl;$Vfi;lD|H>hP#8W
zkbH6YyDVJbew40oby0e$X~G5~*D21kCbxOL(zD-K!Vpke<Ec!;Xcw?Y8(#7vQ!LQ;
zZ-o1A3^Omc52^k5RApt7`oX;CYQEMt$?=3>)D+d%osS3m`b*S!DBX(Mh18gjU8#bD
zZ=LV{94u+;u-GqUCRK~j{^cmHOt=|zWJ2IWX7munfUA=QmYf6q%PqBMSN0Vk$KJTO
zEz#xMEToW^zFA&PcW_7uFz=pB;^B#b&g@8384wvvgOICk5{Qf(FTo8>pkg%cIE6RW
z0JaAFM9G`+z$HA3#if^vKm7XyU_T_5yq9F|aS}Wdz4%R9TL+D$#e*b176`U)s2gkU
zE09`eDn8|0C_iNz52z|@f?YTqD3)lu>bh(iBS3kyxrmvP@e4LhGyV<(@bNY+-VG*~
zWzGXy!RFLnt(GOd@{0**CBq|kG#)Zu$^Qaq-W76GkUiP!GOG2sZ)|q4nJPf&pi%yt
z^99)x%WVbsC+3sqauSIK1jSRpT$248xeAb9F=k?dgEK8j{*xfbLFplM%$9ByRZA0;
z?2|81m-RsJP|HMbXhC3C!AXd6KCg~3O9u(Bby(v0ea{#Yz|AQVxDnc7hx27?+)9K|
z0pu2^x1aG(cxF+^^nLMWbCjH4x7+2zs>}6HAz<zo+L>z~{Hj7evk3n1<Q~fP*0bJ7
z`Wu`2tFKgqlpp@bdA{%!^Yw}5;PZLSvK#)4x1PBKZpQP6X0zpl4I#NVT)@yFwrFdn
zQuQPsc@@&VU#DHWNb}_LU-@P}qVucWg5gVsfSgde8{h7GLcRW_weKRZLZ`6d1fpAx
z0R6r5!$53b_uZP>jd&?>ReXY8;8N`qGr}pVwTHRJ8#iLV>avKT))lNtNzLa8YBb5X
znJj8zzI8=W1Zcv37e{h5JIz$F0MCA%_>ttJlDz04p6BL&WeFxnTm>%(=K=h%YZ0)!
zN7vmfXO3K(V7={RCN=&diO*fWCkKRu20}-mN~CZwPhsZoQ0hm<7G4vI-DaoY7hOY?
zT~Lg@MZng2L3!wo5lX95{`RZY|40`8(~v7<Y>bp-Kk+M<&b*2{Rj!g==19G@qr!Go
z9s|Gol~ys^%$%6S=HH@!m9=q}Z=|$u8g);vFi2m*>waHU?r>g4+=n+?N>5au@#L<J
zYnr|KnaW{PUkf=1$2*`U^C7x+(fN7~E=#7g{Y9b*D@pUeAM$W=Q6LFfsf?-ld2NAu
zCHmx7S?k_7=cq#)))S$ZQL5Mu!%RIR!xhYGP_cLucYf4J4V}|JDDyqLsg|a%CjGWj
z6HfPgeWJ{X_)!etL^e_(zMyq^B%gYe=~%5Y4EL_?Ku}GF&N$JNG_()Ls7y$@e*_Gh
zb}hN1&det~^!GZAFONETtGH))Rpj%99EJ+=Sww2CFVLLuJ%!igcPA?E;bmJ9ipD#z
z-;V?C(zoX5Fq35ZAg{9MD=LzYI_pB~mROvCBwdZ#{=7257Cj<h&~3|@N^QC4on`+_
zQTV1{kY8E39l6et+2@aUqb4#o0@zCQZp^v_FWVqWw$s1JZ#xxkW#8;Q7WRa9N**@E
zh6(u8S&S_?O=d>4HOYWPmv3~DdzZtnOBB0RBsd;s0ts-sNzE4{_+_uBpO&<iqs4Y`
ziAx;o3%69uNQUx&#yMaNX}fL5U(26)NewdKLPiP=kR0F(IE(-n>R*Y>^>MjjdE7K$
z64z2dgJOTzR4iVP#w(s879G#g-0qa$R2Z(>QGjyVMM#;%^>t5e=2F09Ta*pyfGLT>
zK)8g1**%^XZ4Ene)xP8Jc!1#O*ze(6g3O4AeCQr^bRQ@Z5h{W(GR?BrqA;TiLOKJ^
zPVL~Do}mO*Z)*<y-W|ad#yPk>|94>&VXupTWvQw`po4gd#jEo>xWx>>LC}|2v5QuY
z&9}**ZszdM9(zDINaAq%44%{v`&X`Clb-ppzBFX<!2mcDUcZB@tDM_7d@x2SPP7?I
zXQ9k?Q={cOzvdtzT0(b=vabgUtE!2^-*3(R$xGP9!g&6WYzIkFX&KuA+b)lW??*vc
z)W0|LqYFNFi`8xnfq;F`SaUZ)jpxgf_s-KBZ3?xwGk$wwa^lKb4;<IsDwQG;a-5@|
z(#?OFL!_kM;7c+@D*40$TXz?IejkM?F8|lr;dd4K?SGZoR<}ug+EQ59x^I!#_tR^F
zFXL7Nhj21f*#LT2s4+Vv8ofaH%iFS_#%m&`Zl0rXq!lu&Rd#ryf%EOGoBNG4_~0R*
zx^TlBIN}@OFQLc68E>3g6K|Y4-&<p)x@R5fkWF3w+z}4OIScP40%K=(UQcOgi0goL
z2O30I<?Ebm78D*Pdquwup&O>pdSKFi$>{Fur;|P8Du1gQ4P7dTM8Vz}e<(lTg}v*?
z7x^e*IT!pQ_3>RKNcYS>Q+2$<7QDO@a~Pz0!qWy^g&(@70S44x!=FP0(QEg(lHjT`
zZh->jj3rU@6LEIvAd=&J2^FgXxB>LLO(+x9S+;DV0xmW1pw^=mPz1BYI#z{2?6!{$
zss^8$JpekhSl8F(S@S!j0J)IwP?EeVqi>d%!isfXw_x&ZP@No<LPv4JG_Q*34%U5R
zSK(itHO%%#$pfczFe&v(UKRP?Cvk>edVefE5<K|f<^{U%jfs489ZQ-}M%LpOJJ2ku
z5NXEg8o3O`;cDnWm`>*2@85qVbB&Ehd+Q^;$(26MnK0IV6L(R0pJ~^3gf2z+=Z9@r
z$WL36OviQV3QrjVRq-B@lV<ejWJmIj2(4(Z>P_cR9*nrqux$Y*o;i}@Cpv?Lb+hg-
zK*;JKHDQkxIrle!j|o31L1TxK;&MEo`o+`chD<3P{HXAtR;|QL%@-VGrRn-OM}2^t
zAtTxUX9rw11;j=N31ZKGUz`yUAUJ<kkB*xu>>*@Ecm%T~PD8hq+CJh~?-m5Q>~Pk@
zWPE3TUi_v8RgShFJx#ySU>c)1=Gm|iU1l&d5ReaO)nSb>vQ)HJdssMq+Jg?tBTXuc
z&6MWoIe&kDsN|~7wx31tuI5Q<%})SHWRm^q2NaK|KSSJmV&sUUZ~LXlVYufkT>wx!
zmdY1Ufn{HP9`S>{a1=|&st%zHglC>G7Q=5;dDmflej@0I@AF6Kju<If|AJS7W%V~y
zp-bj0D97U7HMO|VYCFM{0|{dVi6|{@6sG5RfBbw)5S&~~1EeSeflV7Kufnb@#)u?V
ztN4l?HkHlPtC>F<L_0DA&$WMUZAzRagQDr!uh}K|L&7wBOPT$i0z-Fu>tCz5e>wRZ
zA|T&2BmHo4b2KLn1BSr6C&YvG_v6~%a^y^wUg4|5N2M~WOp9Db%2xBdcs5KI79y{M
zB<YoDDz=hBj|5Mw3%6M82+Q-;VKn>07!`>qO(MZn-iu?=3-1i`=`Yn2J)-pi5<x<A
z)h#<0qn39&pJdE(2v+3@Yjz?#(KJIJ(mmn1ofd61^-d`_azYRzbF39Tq3%-z=W{Uy
zdK{S;C6^TSVd1gNfz8y12*F6&iSLZlXo<{ELw8E9Vs{6yRbz0UfhhD~441&|E`I4_
zU;yEa;ONES1`qZvCa^<c=VTZV!0pD-7GG33VzTDKKfBG7?vFVm)HniYQ+^%}O}Xu=
z0dI`-)*b!PDMn^V6ga7P8s2egET@p<Nhtgk9*%?HL+*9rc{Ac?d(pzMjZmlf;$rW#
zbt%V|e0ON?1Ry~_LU4Q_j&ONuue2R?NnBQ23W?%A-L1WawGZp~RkmfUrcZiqm7Gf1
z)lrn}&pD&C*tg?l70>%uVryJ%($2a3B^-2KFLRJ3;GV#3Uyg_Cg8{_l1U+<Z5g%%#
zdfoU)*G#uyF#YA*Gr1ve4yu@k8LddI#2D4_`jEE_MSM$aO3)dq#@FeV`*9qH;gOv=
z53QPil;6+%Op)v!WE(tNknIvLar6evdWDv))TFT@8pFj0*A#agZFb6iovc1?2@25i
zNtL{>f373fuEywXMvIp}3?f^1z7%l@MGn08qz6FHr~$94304N>^8Y}tKNx>fy;5P|
z{&wH!qO>NMUr~(`sL!Q;8q39EEY8CCbZBrFKn@m-m@W)wUM5#W&&^gzx~2&qg^J5@
zxPga>PMh;D-r)JHZ>DW*|NO`O+zAm<Q)+Tf#i&|rU8x&9RMQ=y0IaK&S}2KD<KikN
zuGN1_$L7TII-_LL-LE*07)~Dg4OIm$8NS@A50*y*!A$y;DqmDzI^E)FJa5qw-Y%4=
z{<P<f!M%S$kv}TSYG4v~GpL=PMMV@jjDadE#Cm5`c^MU#Bt<_TE)g+Q(B7K3I%kR9
z9<kk=$b4Cw%HfYl&|_tEXt+7cr7;S7x7eQRo-6EaarCNq{X&x|m)B0DfAKB(#os#O
z&%1*&4n{&*+x8JHs&<w)^Tg(+q{07zK6L+8mEXLyekk4O_rjk|41sz*T&y5px}sT<
z95-=hXbd@>%7c9Rx8ur_dmF{MWcM><P*`r*we`+hh%SmTr0B#%<v)-<{40c<d3k91
z@I<$~U`7t<meYGSqsEYcBnYkZ28!xk4VJ=rJK*M8ck<=Ks7@x*Ibfev_Fi#XjlX`-
z2crPAf|s`(az6_Lj$!bo)9huL^IhJ{i1#-3$YHTq(<Jqj_vU|b!o3=&G6T#h5q9LI
zeA|?o&ftQDO21wCHStTqR{M#bKG-*js*u+dN)m=yrso*d=oW!St#1er(0YI9!8<v-
zfb!%uAe%K6-boL5RB^;iZL2xF(S;)Qy2rBPyWD>#=p9bE3z;WKIhE3bQ5(YKDsINa
z!ZINgDXfi_sLhSqF#4uJ%?rr+<sB!qd=@vMP$6eT9QVy1(nxx=cEXRWi8+r9;hVgG
zJu-8nd6-_#W{cNT_vaO#-owwwvMAo=#~duL##;)_TAOL6+RkS2sXlR3Il7+sVsS!v
z;j<BCX!GS?V;Ex>iXz9>>p>L7NSOLFF}<*==eWN(y$I_6roGRw;a$toi=;i4jwBxt
z$LHm)C}aD~SfBsAv8N5B2LHZeJWb|rds38q+@ozTk9X~!g&(Wv$ZJe0&iTmkxhOGF
z2}O2Od59Mv&a{OIhIWLjSvAIKk3te82aXS(koJcszXR7V$gk;ZVU_*&4W1`8e@M_y
zET0=p6*&_GE4@wBXSza0J+@ed#>M(*DWW?BC=26aq%=$NXD%NaFZ%Nza&Ks+W=d?9
z=VfXImsbXh%ZrvyFozv&DG_{G4HFy`*GaN(m6V6;k)$^<^nde5(eUh#>$vTl1jYV*
zJbz-OFJ{0WUy``5vsrGS&%&#|t0Jp2v5|046^#I4WY30gkKFcA2522$zPSv3d?TOt
zTulQM<SH4ey8c1?`Y$&*wRhjUDRZp_lJRyv5IHdbNbL^sRM1^ssF4}>s93;nwrd85
z=EQ`Wt$-QA5)(x;lGt^WrOEzw^6)z?oTPc<q46jk@}a`JWLYx>CdRcqJHhxNa<E?x
zDyH}Q!QEcQc!;j>hLpG}MQ@qC=;p6)&#l1;^q94Bh3{@$w5K?!;TR_K5Yg*#0VCsq
zoOM=-klL?GBahD=avwfetvE1bb@X@JMoBX~E1wG5SN{D>UdVXs>DFof16L5+X0-qt
zD^Dc0DfH#x!;B=nNHt<%PW~~Mo5@a)(G$xZBty6%E+ye#PFfo#N`RJ4$n7-*S9<OU
z{T7K;e_09_rHxkXl<5V+iHIeQh_fz+>+@fYA>bJR6|2yoi<}AQ9ke~&F0mCkd6La?
zglp<V<hp2ue{#q?k$2`^yPEr;m_+TSU)MHJh9V-rquOeAtKD=RIc_A;?Y3mwvNi?B
z=d1?sbojTQFY~GXkE833r~3Q<7a5Vr-q*^^zCxMF-h1zPagD4HmqaCdyVjL!Tq3e5
zBby}mBAX(zv&VJs=lA~p{_>y4`@Y}jyv}(&U(Z1bSJ!t>wEnu4q!w7*cvcAz$0IN~
z>#um`)@8Yc6<9&eI5Q@5>cp*uf~~dv6&eQ2&hX<w?hesW_MnmTK~>Cp+``MTFYd(o
z`tDxe$l_8WY_iV>t^9y=uAHOq)SAzCB9N|fY6vKQYO#>uCMQ(oP3Z0<Lu_RHypMm-
zMX>&pDn7Sp=vr2<CX&=K_^b+c$`DIGbvIggM`y_FUnMcj1t?rnj#8#{H2=JgkY3*G
z<O~!(2WKo*L~$3dA+bFdP%53SgBWwrUfj@uH&w~HEaVBZsry3RLU~TC3J=&8q?iW^
z9hBpFzN^*|-M(x94ZrIc%VAA~DZigzGTrUWaZtUYYD7n*(QA75;546awjg)6i#H42
zqoS)SF8wH2U&u&J*Qh?oK>0Hv<PK%JLiMCl7xv$9BeKd5JoFCqy&PdIvu!x^d=XPH
zww2l(8}=;d7!&(wgEGa?XnC_lItnC2WLI)y>TEV+%>}xFuGpvC@clzlsInd!4q182
zda~rV9g@jdQoN-{vK;D*o9Su3fZJy99w)MA=^o5q-4#)6l2}0zUww}L3jKJ(^?F;?
z@)}18Jjr)&5U27XLzh;IU~bsOpu84>_}8DcP=>gem!*Gz`S#ggskO5z7wQF-&&~P6
zK}N?vXVV9I_JB|XgIK9SnP+#eYRR}kS9u8Ux6JKG3hBDl3V9eO(T$Jg@oUnK>YKTy
zpAZl>K9yQ704IPtp-pX$zm+MI1WHR+-bP)Gg2hEJLk?=Jki)ZxwT&OrpDH)6(t*5a
z$UTxFn%RtkRfQ+YIb2{R3gy$6>*Jlt0t*3$>}cBnKE;rV2Ww&1#>5QI=I*|aXa5fb
zKSs)I)g+njr`D>H=U(A9V~g<TC_0+MYSf8U=?W#8!h4A+#QW#&oO5Y)5+(86J%4nz
z$`qxPPeHYJ$((>RulI)X)dSVHaYMyhnp#@Qb4YSOr-S53(+KEa;g_L9mJcD7ftt5G
z)88sKm}fL4QC2IA%>-_R(_#mPtFn<>Xyk2ckqd^}hO{q-CafN~uZ)VR_?mAXHiSU(
zhDxa##_tT9DB7HU_pHAnnjy)~Ffz1GkX(M4c2`homo}Bh=k7N;he<DW@=J5rk7_dY
zWJvP17RtX3;5W~aR2r+eIs=}?8jBZt%lWve#xIWf^qZ<iBji4AuU&2wans6r^fQy|
z>QBjouYT}sGV>Mi4a)2-e;Y@rF-1{oz7FIIB+I8d4*?$oE)o?frc#6+SqC2TfU_j!
z7NO^_Z<>?YRITZdDlhOF5(W2EV)SRCr*eL4sOXxGfUc^EhyMPPbQjz;UUBGy`RUxH
z>8P-JYnKTpvgQ&j5@(=$&cQ~@+J-0`+wk{~^8ECtkb508ZNS4{vNc;4P8vBA$Jr+V
zww;~|C>=fKDEg>>Z5boO3Noi1n>}F$(aCSV_xYnSxBK!?fv?W8WR-PYwxsjAnq)LM
zRleGD=D=f3q?!{q%aJL&slM4n`3Ns6Zaos#`(4DVB*Jj(8PqL{g#DRsq|ajhM5Su(
zvBGx3p{3baoKdc_+Y<I|I7zH9QV7WA{;B=F{}oodFQQh;t}$R`gdw!5&n-A){wYOw
zOP333fXv-Y6nuDB#6gd8P*l{S_+>xUSpQ{XZ~e>3{%|wxk9;3=(mF+LXK5a|%FmGF
zcw2a$kO%MEjFk&NErb24=IejBc}8vd9_!j_w((v_xz?7_{_g8-Lq5I?9i7xc-YWSM
zH*ze4Tfj}TX*Ak;vOOV{J9<J=b`$<*iSmbf&zkwGpo^09(a_SfT%g6)>0Ar#d=<@<
zPB~S!CA~G@sMjK?5-!Zw4NY{VnTQ0+g_Wnu(XpYD5D~HX;h8kv=j$SG(Uq3+Y4zW?
zxewr!$}{)2Ija64sffjDJB*1AEj)6~rueuc5h+D78|r~@E+G-Sisor+GFAaa!XNk@
z40Aes+&b>sY(PtK5j>P$1`cDm`P*<Wu@Eda7W`MZ>YE@z`Q(&QKK03*`MXtwai-AL
zD8rrlXLf~e*_E>s=oQDMt}SB0^3r{iNYujWU=WuQnj%*H_Kx`N3pay@M@2CQ0C9y_
zR>qA0mrB#s^qySli~%quNjrhV%Zv2V^Hk{XWpX=@8x3%~|BLy#=pb!@IKzkbrNfZe
z3}=Vc9hVy)BeCo)$vZf6J&2#m`mEcYb``n(O)H&T4?}Mj^?x8GXYfBZz;S7Uc}*y}
zBjEDi0!^@)P~OLRW3TB@q<cg!OFn@ip^LphVUJYr-RGP1zN{VLUMG%VpY9G@&?}bF
zzD&2(3cFN@aOn!TPQRAc*gaR)CpF>;dOn&h_0mUG>X0u@=)nP)yn0xcWDHEO7f>E%
z7|x}?Xwe|w5u))ar$IMGJ`;{TqIDUJ?K`Wg>k_$X&5&rZIC(&H|InYkm4ud5=e&zH
zezU`6kyRk}0n4UHn7V(t{CD9>(ez=m=@>>(dkc5Y%cC!8ktX3x+HA1-!x8Yh{?lLn
zn!&Q4@Jv}3^H(2v!A}P@wnURtMAQgJ9GEMt3<&b2d}bk*Lr3L=9u!5S59Je!uO2N`
zONBmd8#r?DCrA5eW|=6=QzNcD(}&`yLO*x#;j;`EeR_m4|4dF}seEj%P>t$@Z9plZ
zuJoH`#mVL)U}F2XordZ*_<@zdnLzr}s*2)1t~z7cZ>XDvX;H$#ls+^)`C;p@ast$z
zisqL4NoCWuzp=OWQD1|}b`t8-e67bB`upPmROYUszw%<>>VZE>8mA!yzF$OwUk7C8
z%BM^|O5yOcTKVzHjEh5i;4X?TYsM_uE-NUPHL6Z9`8KXBB=~-r8-VRLn2=T!{+cDT
zJgwD)Hw=7#Q#JQv`L!!!q1QMcgYp^Y67~rLs;tR)GBU6BOYE{SnWjU>jR<>(rRb<|
z#BG0_L%rJovn6gavW+o4`Ssl7DvbZ)o@Pw+qbJc1G3s0wfug~YHPLb*HJBwn+HrJj
z_fXB~#@HXgvB4|AFUV9lUFhE51M+TC6S342H^pK@_0!72LYLWVuWR$T!$<YmwSRRO
zPVlHe%kMMr71^gb2Fn?M!%f};8kf$JwuhzS)1UpqSY@5-D<dlqQ6|NDgs26HZXx2f
zQds+M%zk%Ah0VI#P)_h=h0!~VGVI9`u=B5KR+VenFr8HQUcz5L9RYf5)++uy-;_>>
z@8K{*y|Xj?cgSiyWn4-PM{BK&*VF_X5iDi}{%2^KCNhG60l`uyqVb~gh0Fn$S6yy9
zEGLH6e#MDA-SGMyP<y|zqwVGdc{M}DVK#gij|3k8mc@zV5Ct6RVq3ecqU%raF?qX+
zc_nXvwEmy7d@H~+*x%?2zHRu1tZ?ILgagp3(UL0hWfYQVn-3ezAt~nTn!dLH^YPFG
zYJsA1iRz`cskgPFjJ^JlU6(U%(?>h^yY+l!uTNANZJN(vE72!jSoun#s-`vduy0YV
zKA6Gk1O8FZ?yn`>9fB8a#%V}23(oFw2s>t)posXwm+!jFh>+rJnyvjhRg)VvHxzYH
zbE0Utddy~FGUu8z#D6><2;ZP;{}0rxAsO8eh|s50T6m4SZQtD`cS8gSeR7H(wmmm$
z!kW_F_=pWehBjOyA_qT^_9gbgNsP0~lS}uhhA-|yOZ?MHzeE5iOhiq+DE%j&wSTiv
zofLf_xZW5?>DryqMm%(^kCVH^Bx18)blxA2HhuRdSnGNJ=8UsbAgSb4#(G!_cvD36
zeCxnl8eBtUNXK!50D<kz+G)W8hK8+cIQi-Vu~>!KdLxYP=Qd`NS3g{aaZf3qcTB&%
z3aJH%!1iIl6z-z?GkjpW+Y#{}NbcIN;D9y7yC5`vY+-&#Y5P6Qj|0|Za#P*T3JY+Z
zENyfe1sH)4c6o<b1Cfnr)0W^5z)$cjO_1@gzP<dxuKL_WOVS#ZD;1Zv_tx<7r=%Re
z(&A1j<%wpqW&frE*}uK#y_J%%c~}ITjG^P@;G6xA6f78SlO1hF?xty#EzFb_Kq9F#
z*PBlm=-jJ2%`86&X<f%Tt`l$&AF{N0iJvN6O)O`SE<l~G<6Qp3^V1uQ%=fauRZZEj
zTbOwwCt3VRxk(<ek6(P~ehr=pu^Uz+=aY^;qZEG8Md3_+Zli1IKCB)7z|a5f*@E{y
z=s;mA-e2mpw|aH2?&54#MU&CI@Xk%A`#|J=g}@T$c)7me<D@X6J%nqklSMk74Kb_*
zjxq%bKCmb$8E?vlQneZfb@|)3JkwYv>xGEh^PX}<To|QYpcVH?A5~y+CstB1;~gQ3
zL1({H7OF{L#nm^^JJsSL9#?rr9q?xzRqPXxJN0RN(WZ5B=dH^t4xLeEVLQnYx%1H}
zk102ZuSf99)WA!xcP)~5j$cWLBdk?P&NvaAU|1lb)G=1hCx|#EJ2qfZyeVgD9c(cu
z^kur~c-zDr#@OprXp{C&mTNM9%f9zq0VUnrIZLzD9H%t$J6^d}>$bmgIUuApFJb9<
zXOk1V$5yamlX2o>MNYT{{Y$#GaKh!$s&<8)k!@9xU2ea&APR7{BHO$gJ)Kb5V}th1
zKaWBF;9XqY(N~5UF2yiX**Fl(?V1Q(Pd{1IzXfaR^eM8PC$<RbO1$8WWk1(aY;A|%
zmePK}WKXk?z75=>WhL9%z~Nfy_#n%D?qqFi=vNuS3{SFyoY6~}&B<WC$Xr=Xjj28W
zb{voU-)TO@<O$Tdz_>%36EYdP++1XsAR2imt!ewgU4PG@J!nb*vKA(=u3U6t`&6H1
zg7ZDjGZsU-sR!XY?ftGDqBP8OaYt!-x(4y2G|RBK>o~`6Njjvv$z+dI;{4@MJM777
zc&iX`IkkKU#%Z?|p*&fdr*ji#J`qjwEL8SJN^21oyJa5G&oJn6Z>e#yg0mZC))YuH
zUNICcN9oejbVtr7SaSI4uW((BHD~!g^8+O*RqIcmR$=Q#aWTy);>hPrt+i)0@y3m!
zap#*`(^#xY^DS4*5k7_c0eXf;&98jgnBGjVppL1wyZknb!^4fzvTB2Q0Cs(=h>F6p
zBKf94n*^X*r?ly+MAQta(2A<;n-<-g8sRz>n;B7r3a6O?F#hB3a=t>!*|RC~s~>bO
zWqBQ(8ool0Xo8JSWG%P7hyh7M+DKf_rf6V4e#fY3;Y==k@^nJJzG3)HUEW#w$ZTP}
zQq8q%&MO7K536E@vs_mdgo!5pO{%Kj<&wTsDGMo|DA^WHYImjLR;iO7vOW`2{vovJ
z%e&rmRy(DV8~2oiBvr#TpE>Sf+b~X?RO)>rz{yST%G&XmU}kL!$@tzC^Q|~qq|o+#
z&rO7S+%n>mB|CRaw5t&^GrPay-cXgWa@T|uTa2dienrF9Y^-9>7sgL`QPwgH13(@H
zI5-w=+GgrOiR~Q#xA8f`^`T6=7t_1TX>o=uLWZ9T+t@LLQL(Py?FaUz_zr&2F86#h
z7Gh~_erLt@WLs}@Q6zaq{bnb#SU}MaE9m-|aWkj>fu6hf3H?EHZ1GluTl|YxICG;Y
zH<rH78&Sre7QtQbM<;QR-+Oi&KfWtzR}xb{nMh-Pma!-FD6xcsY;z6wOqdWl7CpfL
zn4>T=f0M`1EB{U(VK>IAjk8w{msN?ExsD&JJ%7G$7O{}KM=c;7{k&?+a&a)HlK_cD
z0k2c;Cc?grQ@g6NjOu2*%BZWs*~fl2D(wJvwEIM>UhZfy$yqZ%n-qoF*lO6!e0+65
z*ZELMPC{1lwXKprw^N1eerP6qgNG7Fr2T{nckTyw7rKB%zyJ5~;k|g{LNV*2);chz
zlsW~|x_#ym;9@vJdLsKI#_n+-O&jFYz@jv}Ek#Lt+wfsgaBVQ*AIe&+pjEm00}aj|
z<G~y=8iFou8SI)frw(|*{BC1%wkmZ|H%Y47D!t@Sin^$Gg5j2PWT*m~)nUJd2txq6
zLsw4q?lRhIHa2ROMirmpFQ0q_TBp<|i{+G>%-@Pp*(Ev^T7oY6P0l4dq<t1&H(9tF
zP+L(7xa=b`=yeo7&^K}+v9y)!&hw8-!H1?1mKs6$nt{+?Xf7p%j)(N%3(KN9H<qiA
zj-Z3)J1z$D@bR11z&5yg<oLtjTh(e1+H!M_3li}hkO)`cbQ!N8VUz6)M8@LDMFIKi
zyV?^dju&|>rzTd4_|=m;Ci|@w%rZhCXf=7O5Q)6~HqlF}h`0;e@X`wUoTl`mlLXlp
zlfZTwo-Gm&Fj{VnzcO(aqWYpFl_DK5jtB<|!V<#FO=-5S`C^MTX(@{2i4u<H%DLH^
z()EmH3DZMID(|Fwmn<K&JC=bLIsSrqxPQLBG;I(XQG~Bt<(ej<S*Uj>_eUtHi4Mx_
zccz2Ib8|!;9As!tM-r84<PfIP3kace2<ZO7C#}&cUc89f!}cwL(r>i`g=)gjX7`=v
z#0lN+$RAZ2IoiG>l6Qa&!JnzDK{j67M_6!qTS~{c%J<d;gx=f2*{Z6npy>|2#oC^G
zEq>QvB0;7Z4X8%9yd74M)jat6>(gkpB+&4=b|hH`vuPVkSlU)SXm~80ou7I+f|BO*
ziZQx@zl>?t@_Mcf)T7w-)*Wa&wv0a_m?KP<YI#BW7ff7=@JCY6S2#cYx{L&WoxGhi
z_q}F|E6q5fA*0>KaD2Np--EOrbD*$ing33ws&A@ASh-^R>#(6wPt3%b-;C<P65PY+
zvO>u{p9@kz1WeQ8=trRylAFgy?_1<;y*HdE#7Q;zJCz`RfE&)h&w*bdzzm$tl0~*8
z>D2+$wuom6r!I#-_OT#fIO;x-><-?!?o2y-I7VKERKEv7{qo!7o0l=AX#hRk&ZM~{
z6VjUH*n)M&G#_z&8pcNhdSGq=82J(w$P`?#e_sNrC%lX!t6e$gIR#R?s@ujw`N^j#
z$@H7r<=L!MDui-@22-+y>&BeQBT}l%k|T860H+v#xXTA5`+=H0I~JroSk46y9-SP8
z*5nmtQ2-0zo%M3sd4k;DxxN34b<xpVA>!llNE%wTN%VWoX*qgAa?K+PlDi1<N42Fm
zsJ`Sj_lt$(v_1FV@8SZNo#F_eh)!8ia?BH$gZnl52+I}!4Za^rR$)^X-CpVVXVADx
zkI$|$&*N8<dIH31hMwlV?W)wXB%Ub0<8Nc5RV`nqM~3yha{2UtCfpV<cL}CMTYLeX
zU)3aM(NCUdES_y!{b_4Ekt>wm^QjxoMIK@cx#FPql!@A78#@ow4yYwt8dQ$&<zed-
zJX@SPDq5o{G58wEKuF{6MdS>{tycM~kAeZ0jC=-_=`_WGQg{qhV^@@}Q>|}fEgYS>
zv#SX8>B(VYwH~kBs_RcPLpaG92IP&l^KB0r`Uh|(0agtn1W3d}qNEu8LM+dT-);G(
z_GQA4LG8>1a95SC(I?Cm0?o%X1z)w`$+B|F;Y%>;fl$1fq`{K_4#P<nB`Rx}2^F^f
zXSQJ6W}2Y2;%yhF7seznw%mzAnvx<X9(`o<=9)fi+PMU82hzO9DvzV39=8Y`X_MhA
zFRHPwPPJyqd3zm9Qt^7{qVFXavf;LxpNhO5y<g`{1ty}UH4kE`ytOa(b$_yzMVIjm
z3N=$-v`Cd2Ysl{NI2u;M>4b<DTX>%z$Fx^~7f?qK>uYn$+_<*r&!x3M;8vRia9q90
zN0FA@txFBy1t*YE9bL5C;yN=a!vIu};l0vV1=S^Da!{wo$y-^f<8_Qba0_oBzwWHZ
zqmRx$Omv#2<=Rl3-9i|LG;}oqtxs&0?i$QCe=Qwyo%-+5otd|xoRBR!ZIv~PiMDfX
zu(ZLYnDxt_`UU30-rtojksciz*v)5dUji;k*lOGw!~iqEW4xTjtE5?#oDl3}U<-S*
z@lC%`47@X&!uz#8IC94{TFxvd#9~eHRhs^fJiT@pW~me~+4{>Nkk`ib1&ZV~DHmR!
zxIWSKnqutUNO+A@K${-?>6hM)CqWJhcXs<FV19Dl7~kSuf4Z91q;o1_AoLldef5Cf
zh44q)V_Gh#iu<A}0#VK-=4!HI0Ma_|qW)#27o7S>cr~ESUI^o^Tq=ZSJTog!f1+@x
zZDs4(t4%&V6-e51>sLtdCFS$({565h;L{3PU;7uc>qnKJZHFoIq@vP=?Ma!L|MYAy
z!~v7+%3ae@bF6vPHKzGdp9!H9+)b{Vus&nav%z0ZAeKixX0kZTDsByO+tp>a`wvv=
z4Z4uE@<jGVATq9Bf+}bYcX7*h$1aAy1;y&KzS>m-j(g(G@YH2EW!1U6*vZaBGaRdL
z4BOLL3bkR!UK9(pzw7asS*-g;vTZ!UR2}Piy?R_jFwADyGR^vzS+Mcft+Zui_$NO?
z{MP$f{Obv{M(G7~=z9>M$<pK$U^;4)d*MS;4yf5fG@Mu5a?d9$z794KyA^vM5$38_
z9tZXNY+T@GD6-W1cv)FW7L6dcn?v2+u?7?VFcVMHTdN6dbxXrP8Q2TVo=Y_@lC=MB
zQl6@Ut#tY&t1Q(rU4J&o;CSR-gZd8?%y|FSEEC^@2_6qtS+(z(_2K$E@Rhn>;=ejz
z>QYJ~f+>kQ*dL`qTC%ZY<ObY~CnI}m^3`qIdqxNDd`c9u$O~rSuiGXBhN;l%tf69B
zuFX2_+@w`+Z1#q2<9dm(;;t#OB0jbKvB*|2`p)kmqDyQp%q0*1RQIuKoOPw3@iRn}
z!kMUU(^yZiF8_5>t6^i8N+$zRUFj7Jn4QM{APrFdN0X;3f7;8is(h0Q88rLrGyl%k
z&vS?9wDO&S_E~pw6z<0@g=v7~GMwxjC9B|MMHS~uq1;tt=JFzPM?|=;3P5?dYT#>v
z486VrA0ifkONl{eAImZY5;}%Dm@X{=AeZY?YUL%GLW|&%9wla?%~eZoc!ef8u9?cf
zj9jiURivZo6Q8e-spRR2jJDY6Cco@Ssq1E3W})7Ch5)jNz|iAXpt8wJ7QG|E_w+&d
zvi8K1KjdpCW$9V6`S}K>{cS=mQQE$%ib%k`oBiPoYg_p8gcUS|BP2botV(PpF+O0v
zXnp4P`!#)@raN~Qie9%;{rKU16JI?si3??0-6lD()}GrsFcn8v`LFA~0G|ur3C}|&
zEO=#n8Rvp_8@{oob-$U=4i)u#fe;0|W^-z1s{A%NK4*_$NFPx9^*2r-D_s4e1HC>S
z64=L=q<?-zBTI9hviJ;AuQVvsJ#80P$*r(s#hXR^AE>~WH@$U^(@@K{9&l%ScL1%P
zJ4dA+S_*D{N(1~D()P&|?lUV9RSO}1>e_8!mcmr-%S{xfbeilg`<yoT-Xa`W8!Bmv
z)Y|#>!iNXoY6g-FN^6SH(X3t5+o3MSt%0!XY2rycw}~|pEM(oK2I%Q{h^tn~YW_YQ
zTUdJiCvjQ1GP}RtP1)lUfeh&&V-D}BaoZlGMy<Gs)zU>TLcDoRU?196I%1<t@TKUC
z6Q?It+lcCrOdScd*UyXW)xG>DMXMbbtNI$Vjh}l3%`Eup7hLDQ^<OO1135P3+StOk
z5}?T!C;Bi!t>mMS;nr|t8P)B7>ES!ctN(aR*zLG7eNbSpnp&4KiR<yifHL$QTgrds
zVNug@Jg=XE;U?(-&SvlkBX>@mLC744pRZPX|DKN9tt3L1{M_0Bh_77DdH;<JvI5q0
zc9^>^!p8hWN-U*%PMXTGHDqqD_BrpbzS-UttD)`J%i{c$kEC1;m<mg_*4FZ?kPUUX
zFK?if)}Y&Qp81Uu3V!S817vZ2-PTgRMCCJRw)kf9VZndaV}a7Yu$x?;uXD<6(WG>p
zEKtz4qrnwZGkR<@P`5Kwvu4cJ()SC}P_;cM@6%aGU2d4{)=KSo(h>`wSpX;xnh5t<
ziYrvBlOKlFe1~nA$1fYusP#a9y5n*i(Ps*^$Q}LO!mhyXSkJ^%9LJ7Hy%MRI>X^%K
zPrpssn*;+t#3mdr0AG7v>uAu+nrCT3_{(^wb!X4$yvM0Rz$5}D&Z>E(8M&sUw;|7R
zqI$7xBc%>wNLV!vca<s%shwI{q&UBAGg1-A4crAQ`~U{hzS%U{zJ;B3x(B>D?e~10
z!aWcDqJ$c{?Q1`m0!;8Kp9-e>2{oHi>6dAK<rObR=5w)31+kcZrFbm$P!7%5kpVV-
z79q>YrAXQmc3o#mf1falc{{!`5>ts{i+TC(#1Oc$MwYYXmc$$s@=QkOa8K8nb9Smr
zUa0A-Pqe*Wmsb#+^DNx-rckzf7yuV9k&U2Pn)(S&057n;`w#RD3_3-TSVpsORF+%;
zFpT-HV9#=4ly<bTzWKX|I{AUfNQv1ZJ4gS9Cp`u4*JLF=m3yWR(3luGJlXiy=_9;%
zyE6NTh?9qW1<{H)d8q$GVpnyXDyoL*3i3A_u&4G-aV`<78*cZh3BkM9Q(uyIRB}p~
z0uh4SOKi97-99uZ_Lh`B^btt24uoTQjgZxvX~6=D%lhkcCp!3evLzk#=+DY)XQjF`
zvx^p4&Ms4Sg?@m)=a$;RFgVpbckD6E`WhXn(iCFS6}sx!qof2PMdS`3KB^a&{jdD>
z!~BYr-yaTN?3j4{`g^&;QhMH`TRI2YzX#ZQ#%`v7;>WQ6<Q(1MOa@Pn{`&H8xygW^
z_-cKdGI#M?{_?q8SNy@f)MbTuu9!cP(la4XSt-65!G?-H{r&YOb-uXihZh2CH}Vtj
zm^;9A$?z+h2O#cLaQ2?@F~pA1Z|}*8XBy2!ps^;j#Z%jKcS0WfTu#e^Wbh^NN0ppf
z)-kz(2^X?_d}%gc()S48(@8F#wbykS?-3P;;T1l#w9hQ6biSdv=s+&}YP6=^*K#$u
zjeIC5BJ+og_f^ISd)$Ot0AE~TL3XLX@Ua7*J9poilJJsSey#jQXdM;Ql&`1=@5?2*
z*zn=DAhK3tAnHZ0MVgvE^`FiHtW@I-)L>)cxM<do9)#Q=FuLnkAr+8R+s`c?#>$vL
z>bJ=Gj%o(~*MeBj7dKx2kY4hECyXdJ|8m|7R~jL~AU#4H*}=L=TF)fe5zf|<pt%!r
z#}D4t%t8Gp`!;!G#xm{T$m*Z;4V3OL;7x<Xa`Sa2k`D8)BdhoQ4o_6L;?W;0+D=%m
zG7Vlni-~Muco+oEefS`%2LftZP#5)Jhwj_RF{Rx~s0jWE%H4Nh2<GKBp<Ig$ML%sU
zQT`?!RpQP1UF)t@6-l?xAC&Row^yW`qqX!46MQlIw0D1_M=R{9zuW&ZiWDbB-y(kE
zW}jwaLYAdqPChqdz4X=Qw&2|KF1P$u?|J2|UB#)Q^!DK(Gp!fnH=xoAb1B_Rmyy$|
zLB+7$c&1Ij>gBnkw)P8fuW7O7wi87SxqXJY?bXP9gU~5M5Aantc-<0xKwV;I-x~KL
zfFuEuIup+nwWVi9W_pRsC(0Uk8WU6i$l?_waq@aV{<ONFL1#&Y%}0kR=4tOmExT(d
z>mot+OR}z5h?&YGbBPxWYwfK2wlC#D!=tBzcX(NxmVvq^`@qv@vVA?UO8O*D=tgAp
z9&u3GSRpR!#vz&siL&w-wwe56BE6m_qkQJ~A*SlMvQ$DaGv<Bz*b@E4+iS{fk&kuS
z6||vM5sk5$I>Rl*EQ~Y`Yf)x1X0dXFkf8##b-{mVWRNI~b+WyNmI90W0B3WkQAubd
zoar`dFH_56v<d$vjNkOWog+@wu*OkBBKn4LGc4_o!`@s~HW}I-$nwzP3;0G&COgoi
zBNXK$j>W+ix)VcYXI1{8ggfgkAR6(D-*bQ!)*bu{q;iYE9!=M5wxmiw5Jt-N+X}Cn
z^ftRqRmReuPLlb!x_AC3LvO5T^<Rau;`6kwD~p%&gahHUzMURjeTus$KUuHMY;GTv
z|3klXD<j#}_xc{=Vk%9W0=Ses1b9ABn`@6@-GF>z{EaEmSApT{Z^4-2KPMO6Ipq1M
z6LD%Ko96=^e3;n#$99BBxnJ6@e)vsUb}dnk5BY}})SE{Vht^q!YowGVb*6Pqv=rfw
zI}|ZgwQl&|{jI`jicdNGuT6>7sfG_PF%Oc-D}A!_9t`Z+NIv?J^`cbL?NI+Irv4<$
zB$=j5t3;|e<#K9ERPJ8J8KgId;hv#T@f?ZqReb$|WnL;>I$e%q0mCb94#t|5;P?yj
zEq%E=MoZ*#*al|JrBLK6L9Q09$>?Qr$l)WWa}A!{q>sTm$6m=t7Rd){8$tW}xTggw
zk~h`FQy#3lXQ&fqj(Cd~^VZG{gL1)gN6FDb#3LEXrMB{7c%Sw+TZeanv9>OQj5YwK
zL)Y*atrjI#BfluN2p5*V>V-e-8*{zaKW_a}V;#9hm?(dhv^x3lso(|Y)=`C&zf&hP
zuHt-n!$aj!@^`0Byr^Q|Fz99U_V3khYGSbnR9bg4d9RB6jmSMB$Lal7F%Tl*5dIgJ
z!z#9F5P+dxx3z>NUQ5khE60~~XAdck6_7*&w2{jcO=I_Cp#itrRAD0S5*hrClPryf
zkEiiNxx0_e^czFOMoy7W6GI8>At<`7lvh!RfC9Q}1ogm+o4Vl^5LcMYo4CrtMDX!A
zH}=kUTKlka_DsGEb;C&TE+(HwriWj>)W_g>AKYn@=F^()4@917`RLgEHp(FZKY<e6
zGR?t_r+xhp@h|l?qp4nP{p@zvN;%yMS9;aDD&1(vM(oQnsDR=I9;)XUmy&^H{U|k~
zBBIV(FbaOm_H0;K9(D?^2oJd-CGu4A*aDX8^MtYWyU>{L_<qv})6^F?IMW9b@dc&-
zkWa2|$wl5_Q6kmimGcTVhR6{0>s<XH#Zr(XQBraEDa412p6DTzbvC%&XkB$wu?&B@
z^#enT#Qz%9bTys3_dCy@21s(Xba$+8zRf#4c6H4LHC0KV=2kCSqr9c~=-%{+RsqYF
zSgCHNd~v7HpshAQ9WYU4P%oEciHWZ1ecerM=pGlLAHT|I>cvmLDF-2XkOkAA=&F%u
z)~$L&zGeKtX6FFTmNjN7Su@Ou_huOtcMtf&!U`}ln{`qdgH7N0ef-9*Vyo`ov!rk~
zLCp4%FLaK4HoXb(_ta{Ue^O4cInm{|1cn#BhJDXCx0=_Yh1ESG3Xc!XSYipJWv(pW
z>E00$2^T5W3*8$CIvG)|)nK62(RFb*`SwPrfff>U@522?_?Fc16P>G>mq#>Luq(5t
zfH-eb69}Gq%3~ViEpt{Cp;LN!M!h|#>&Q0}256i-HI!JAZh^w=o)3Rfd=P)hH}TZp
zn8PnJu!t)|0qOB3H#nHCR4CEqYtq)|0QUPkpjR7V^|=G+j^zBXlZ)yjfn-_v+s5I^
zFp-EdqK!{<<d@UrZ3>KNwD(1>7;e{7w2Npsa-45dbn110ZW-OsGJ5mAApd6Btty|0
z^aS9}bS`pQ*<fN^pu-8R+T7SefUJTRDw6brlV>b@tA+*GSx~noA0*GMSq>%?Ne$f(
zTiFQzz&oJiV?Eho6(rBG4tYp!<;IeI!Pw^EZ%tgS&G_AVr$LP+%wzbAkz6ugGU>a6
z^Epw0F_Xv7c}?R34@Zfs$b>q=G)#7UC%le|m&*NAV;{X(_DR}_tiVY|I29cXSEy&8
zpi5`IDZWN6Z<;@mv;@yKrFQcxv?lxkc_ppyy-<*yvJ4N-m~PYE*@M{`Cb-h`yEXDA
z1slwvF+o-jKKx$a%4IdjzDWZg9ZVb=$SF8o;*-Ow2fwLjRa5@edMvP@Ddin>in6X$
zdT?}x=1ZGowJYE>DnnZ`#s{<BcUFSFNnvuGi}L;v$yVsB)<tnwq-oWzvlKuwY(HRo
zSC0<^r|)zLBAke|gY>C|{-;ZgB`LD7$mF^3<5xJ)Mvm!>VE;u=5I?w`pFuzr0WfJ|
zj`r2ZHn)ZvfW)33()0!#thG>2bJNfUPSbTZ>ISrGd2cCDqQJZ|Hw)}%9yI<;>v}xo
ze?2zVfoyo8ZU{b)lG1r2r!&DVML*blSZW(r?+H*ko=R;SoUE4nDB?{2r=(;ur5Q^T
z9{s%tx}M<+jC;0_-1CoKe?WX5r?DRY*8l_+(XV><98PcaZFkx(X-wE(+39o$P>8iC
zxxP7WZMze#gCcufAjC0Be6p`C&R*`IO5S2BxdwFag)#DIy5%=w=aS_sv4XyDR2_aE
zr5SoN8@mxyP6*r8vzRCIOc{4hCKT<KvIy@NPmr#%%LTyCnt#KY=%Z0Gl}G0Lngpv*
z_0G3^#4fUtE&oSE3aua}mYwnQ-Ljc_7O)j>osfq9)!m?7i;Yg>e7k(?j!&)L=rTH%
zM*p5F-N^Rm|3FCXtHXtIudmbyW8kTaC=+ht`gfjr;eQ#-6WLQO#-Bn4<|Q-XzpzN-
z?#eXjQ~3Co_i2&uJdlFH4s9=}rxX0fgQ$N^qMe1vh9N%(+x29DoTdT98&JXC&%eTD
zuzyljhL<cG*qip}i>Mxw)Y5gsHQ57yvqPue+ozS$6@dO{w50uag>~BFkcJMzxrh<3
zA9b!VO&!Sm<e4(e)~Pqi4dQeHeDJGNfsb#*fswF@KdD4s*z3pp8PS6vPpLOFXL%Es
zExi2HH_WKW%$Z7qRkLV6X8bDQi>M5jN;8jBg&1g(R)c$ZPMqUzEF!QWjhxM{w7Ql$
zh%y>)11A<v3HIJ1Joz|WZp_5{@MCG7p86SDqh$=a=;BAyQO$PT4?g-26m<9!=ocG;
zk0$`x#FJ?vm$fe*f+H<v+ogmSS)OTf@L%ojd|5gJa(1yprz2TU`Sn7cy$Y^LZC473
zyEKJ<$}j8s7-Bsmrqj+fMf6~gl)7GtG6!|mI!vBh2)QjN8R&WND|?a}Wk{JU%|=Z=
zewo>Ai5|M_@M7IssVrX3-%EJ|_<=ra1+$v4S~x;?t3<24inEk+#FBnXJJQ+xIIFI2
zq03}Rc~!3!GrcF8o2w0TnQPPQnJGlXE{#}cq5Df!iE4CSyS3^0NAwX_Qp<y=`9Vqs
zz_5K+y0PC!RnA^OxGu=QmmV!Yd|{jQt#gR!D<k9=9%&88u>d<*1jq&Ptxe8~ny^bJ
zWZB3UA1XleMfYx{%GSJwY$9rjz1D(j+Wv{>M4tD{4ZJb-iS5lIWR&7Y%23J)eD(H8
z`8+gHAtxr<MrM`6Bxo*ByY&X46X2F~>sco8HZ2ihMZQ|IcP`p(k#c(K+;1Ic8=R(v
zBCW*f(p-@(NUQ^9Ajt7**cD8S87qL62J*Yl6GoM~ecaQxQR$wY`~WLu`U7csRE>a2
zxVy@uNGG2MbI^Tbco(1s`+)VWC}H(qJ@UyBgA5G$iCb@#Q4dOrjYb3)*P+$eqr?Ok
zVnM|&3cDD@EE7L*r~dw>*}y%`&)x-Gmq_&&mozK0h5uX(q6!s%8@PI&I}uuxY@GuU
z3_Q_CMq&{&A%*T$&LWD}R?(XOO8tH#?qgYd?Fwhf@drMaY=zN_>@H`rKJ)$-YB{_q
z!^S{V1JjYs07(Vv7~V5^Ql%F`c?>ByS=^{2jWAj*U_y4DEOI%P(Z#gzNqcmqY662~
z`Yghq+wvyI-W<3(!>`UN5g)iGD@7jWa==FdR4f@lGwoTI5Q>w-B=|xAz?p$iMjMJK
zokwihW&QJUiB=lA+bDI-hT<JF`Tz_S=Bvu8J|K3%XJNu;HKO?Ja)Qbs7$854<Fk!c
zzXbTTNHGW3dj%AGU7Atu7G=Tx%jYbNB=r0;sDBOD?^vW6Oy0x?@GAo~EJc(^n5~N|
zG~YbDm%|*!`8_6pcKGa;`67(s3ZkR3_9U5`!<!o)q)+L&oF6av=J~llyjW$Vm7_Qk
z{?)eF@_)l5A=QgPYx6GzYLOW-m3It8h;8@bV%P2NG=tPdJ-@?}bGI|WE6Zv&L|P_h
z6gnmg<Yl@Vo+f&TwdS+zw|s%WZ!v6Lfd7M9rJb2sUF`S_6fRnDjca3ev`Y7VLrFfe
zAT^wt=01`<?Nl)_O2sVw>%8*{2Rys2rQDsE=txO&$AW5(`XGEaoP3Zi&ZSNpEdJ`<
z8I=K36Ivc4X0@Z~(;-Pzx<ATJAlG9E?DCLhe;chDY-9}KNnA^*9KuM=rLI;$DS9=?
z$Ej17MbZ{r?(NU>(XYDHgv-pg3rmzv8s9_5mC3B+inKi(i*E|8c{UnCBiGt~3fMyZ
z{4n@h|4;71AN(80nI7>HG@LpOaBpr5mioT0J56(;1+L>Wily2GPO)B9M&=yY4I6*Y
zo2o1Rw7jQVe}$&W3JYBgLt|pz=llCvv9~}+00^^)x08<w^|WfGNGy~XzWx=6W{ESt
z1q-c$Z4!>~7i`cjY%CD=_q>0uMIY888Fa2^a;VEa(|6_C<P=H#C#(}|0iRiE1RyGe
z*TRF+gE@zuD#qviAHY|>-oTVKLDpk8%CF}i8>r@!s=413V6w4Sl{<0;0o)|w?wAt{
z->WUxK2=T<uB1wrURa<ROQ${P0Ea&{8o)##vXq%M5~4>LdEUis?k)k;zg{y++Yp$)
z8IY7C)G#Vlvp>?%%r#&6$(I_#&d-$ysKKh0qg~hV_bVTH&rhBwVCnHc1>R8v8Ngz8
zZD=Zl9Gv4fR~9Ox%<qS|hP^#N-PmT0PB9a#m!)o?bL0?aJiL|Ls6uAEGoa_=@Fifp
z^z@PD9v-Mq>SiZZM6WPKc*`t(&;w`EJO_Yf6N=uuc9wsX-HTJG;^U9-n6j#u4l<y>
z>XAEt>U&0<lf)Z}Q3j|&tV;bBP}ixpli<MrK>Pl+)!%3in%fHn%Q!`%FW{$l<Fx9S
zNF*MK8yaBOTMZujr|T?2pY=x3+iKb!ge}^|&tbLB^YD-3PAf&Tvv3LkKqqybltEf@
zn5B`^{k{%8eKOFx{*$)|<8+tpoM<<plD9o%cpSxX&8GI5B!$sv#wSdUuXJDjr}7!Q
zj^x@-EWsR9<NtaI!)HR+*9Dt^;;OzX-DV^&?IO5pom55Su5<5vqPgT`A`V=r4QXlP
z%KqKiClB^=6v^<V9uBJt+?sOC$IQp7VCspl4<XjnBxD~`J=)AlW~c^h-2VersrDq8
zL7OouKkcQ4Z%!dI9oVpcS(4imOsu|popHZfgc|pRD`(e(XljHeF-RI`_@5O+CE;;d
zq{{u|s$KotDevG+4MDr@l+@Yehr7?5!%jqGLvH0@ZHxFlN!YA!&=f|Wplcp2Htd82
z&on+Ah2?7f;a$_b4w4iFIFV}RX=#?xJ0Lm8e$m^yuf%KEezTb25z}FgU;xt1Y|EUF
zpy=xK74?$SVq<9h`7qj+OfaW{V#ac4{m%hCA|Xo`&{>R#uayh{e{Fx{PMR81+7Br;
zT1>Py&@kTvSEIkg)}<(r9qvVRY<CFJFM=Na-3wk!deIt*9>QG$Or8+4JItTSKC4Fi
z#OCdbAl)><=@rabTYsjoM}t;4&MBf&Ge;%uGMIgla)SyPig#goCF^**f#gv4=ObXV
z<>@&`i+r5><#@MI5WJ6NTQ#z{YSE!Vp9m3eEwrfjCeA=fhw6>UrY!^v1TR~J)26oT
z$lf*|e93uT7OWZT5LIlVCHJu7ygFeBrSSjhcSJR+-c)HTx^Q|OKv68Vy0hh~vI6lY
zU6;KwwKIPk^UmNzoGjdzq{^q-eTolwf{5FveG}B-s1OHbV6zcbIX{T_SXydNvY6yM
z8PG;uryY}$^m;$i8yFtBcYqH}3l|;B)#dkIG-@OYXHF&BndkqHJ4`Zn*Uq>-P-Ov4
zx9^annN|dEkgs|-uYCnc_ChYIGLCP5LtS0)-;KeU{DIEx1}+m$%y%PV?wV;EM;~b|
z%9^f<7t$)9`tW8w%tki#g=lr}xEfVn73fjr4dVow5e7Cx)Xl1dY<}C}@i%K02f_(S
zFMm(8vnj4#4C>wKawq0w?B^o6m(-f>%W{Q^gHz_fS_I&T9ocgZw%nn&`WHz_q_5oJ
zp*~~)tCJ8Xm9eK`&m_ka7<xx81~7KXTTERxr$JYQn2?vEVe*(?3}t6eo;S2{%~vCa
z{=S&_K+r7rRZt!G6~Dcm_`7&ijCYqjKEUsNB3thoJ}2g7^*dRop1Kj1bGjd54=!FT
zd`JW8mhh6s4@4i(X0!r1*}e`oKMT7;E{JQ`4U{zPj0^u|zV{9>j`&=hh8xOq6K7Y_
zV|kR#$9ZIk<D4_;GE+OPaq^myDaJ~jZ30vdoe`aUocmOupf9wI<`OYfnb<snKWL6P
z<u-Ta<mR}a(hoL61dAhNfR8>3KTO89-(&Yx9eCIb1o8X>JRl0%HfIG?bcEHd6WBxE
z0!yPl<PT0^lrR9tt(g)Fv|+Ra&4A`<(bj*0fum((>+hL|wJ^y0bL2ilr44W&Qx#mI
z1l3HIN!V1XyhYhSXs;GUFScZnnU2yYsDU1PvsZ2Xm8Ha`>Z+`XFcv9djM=F@_VYgf
z9e~H6Z--x)wwfUq_VuP#Nc}W^A*R7h#rpENm%6rm%!<%~o!wjwA1&|P>dCXx-RZyF
zPv9}IXqU6xJpi)1YQ&GVZge(WBR!-nUE2$jy?Y}$%aindNceY5Xe#7o|A8N(X}La|
z`gx{Q44&?&Hfg_xEt!AFOJbLL0%x0icPpoT_IAM2==Lfj4!(n(XO&9eIxWfJ(fijo
zJsv5kk4kdPCu?sOVRgf0iqrSSF6d+<bT0gJ9DX+mZq8N-ex$Py;Kg=#&hv<6<}*76
zthaz|tIZ6^w`R6Te&}dVlnY(82rm*A*u=>)`#-=rXIi64sbOfh&1pcqHVO?f{25HR
zGyMPo;@c`ti?PlB;4Pc-@2aQ8jbvN*!GXH_PG3xsh5cU*HCjWhdTJrU2;Z~0??B`n
zz3!SV(?r+Stjf`~I@I58Yj#ojK)CR9i5OvCMF2r9?bK2_`G<EoMPus%oXa<7`2`o$
zOx`s24s_SbL`CFCdK*&yede|DNHZL?t`0Pnq|C$u4&b6ygHkV9=DhNHqf&)yL^IoZ
zCPF&#!dST1@dD$<(2KnLx+^#5OQMfu`w!hUby2WK?c4LC3rKZ#*oOJ)kvuSfkXYB~
zov=$`zw{GyBkY5{vHkE7-r%#O=2wxxB_r3ee^*_gDb=8%A}Cv9Fiz3?@N&?|rfdhI
zes+)Y6TPKk0n%(YDdM%I%JD@&+J$#Jt=L#>P<b16oME=J-33?268hKNBCW|MPV)Md
z>a@VBiJ_fEiUtU>>?3~#$u^C`RLnNA^4okZDLO^pl4H4Q3BERmd9&Os^n+nv(+}(t
zw=6Q1CO5Xa$r(OeH^16{xDi%ehZ$PR!3Aq?gh=3pJ@lZ`F|$Xh@nq@uB5YfwCn+YY
zeAJmLeoU}j3~KN*sk-k-uTLvfzl7FEUz|jT7n$j6ls4@cB-?-OK8?;Y>2<3fps5sT
zU^4?!bj(s?t^oSL+b3zc5pO5MWUYuN=MICvqsr&ZVg^Gr@7Bm%nmc-CevY|3In?RW
z9KNT!d=jsHd+=4w>M@hb#SB>=gU4Ao;0KeS+61-vIyVxv1=ALX{NW?q&wR18Q6U;j
zC2AZo<HU7n7!?I<rV;Za!i?mS4axDgp%(6a@%gx_{L~y!fi)!A&tZ^cWt26%N3CgU
z((VHIrzfU$7%t7X8FPCK?~jdsO_3?ZqIhXO{f#|Re7ytJXJhI0%qNi5iJkp0Ytk|)
znFIJ#;p+q!lWL?#fZ&rMO9fz381kdh`)^<FihpFx-b`E&T27Awp#OQy+M$@%cl9X;
zwp|)p&E))<lQLq4(>04F8WxR!_c05fu}j8b;_H%+{Aql|dC2E&g7Jv0MGwe_X!xhX
zfX?YM*{_<OK&bXduBO<SDbS6uy&E&jw@71-P!S>GU)`IC*hs7`r=><;_Z#}ZUxZU&
z=!C15``7m+`K9f7xS`t!>s8}0^1Tf1iKk)`1q#zSM(E9Wk3g+Qjg!?rs=gviZ%%Lx
zGnO{8;z1iUvuG{vjMl3bOTVyXJ^qK7hnD#4C^q#6xzlfUso6sX{MqiAr?ligTgZOB
z_zi;P0`ip!Mz~9#da{pM=u@0SJ7=QE!=y{_6~$MX#en}nj!lEz2<5XqRFp!+aR@_i
z1j=o<9n)^z4*ST$dHo)6k-{m)2G>d`wbxMJeR-Q_b+;XBei?C>vJ0#)ODuseP`x?}
z;~E<it`q`YwRqidc-B5xpa383^8qO(MmDDjYu2N?Da}OOFMCr%p@#77I!GUir*HcH
z*34h%>EtgADgfuDcV5eA(xw%>=f)6g&?%iN;i2-67g~j5ph5h$97aPbcjlz1-k0`0
zn%b(R$$M(Hoy~CPUCb-BNyPGNvTU8QWY^niH@9Xo!j;J;I7qhROsNXbw{T+Qv$3KP
zof3k3{?DS&koSjrRR4jv=P8D7PHKgN&}ki&UzM8=Rjif7xSfV#Mev;?#|ZVUpW_UP
z2lN*quay@`?df;bQM5#7<zdZHc9h;4PAxhYX4(NGrqT6VF+iDIs<ZnJbP-B*fSx72
zzCLp03Hc}NJ-hwzWio*NG+i51D<`!*MT6d~czFGm)%Pztk^Km3ksM75;xqUF98zVP
zDr|32KNaTh*j%95L_Y!K@06YdRrS=nwS!ViEl_;hW(;l&xSV-@`1TVXGDiMm*6x8{
zRapH%_`(gA*O$dkEM^bB;D>1#x1x&Xxe^Z}@YYhCaRo;uAs$CXAz3{$a=JE)78HF3
zKaUzlZI<+oXw;oZOvETR_qcrl{RbKtO}n8iL(G0%+O!c^UKKMT$C!L_^ec&Qv-qat
zyGJi4fd;_nIMWn4K8YG-_-ai_Oe&cTzjI7;<$oY;65=VKP(I6lC-9Z%r&)U1lj+HZ
zxzx73=>BPS;|4{sci{IJYQqUTf*P>UUYHWAxm0Ebhq){7Yt4m}rF;2Dk?0eCzG)jr
z>7*HnqX<*kXsSxsbrQ%K@UVG?y?2Qnu$8}xO+Nt4y9r@2kkxNNMuZ=qgNI64DkW_o
z6(EWVH^MfWDH`$&cAvXs3gNXV%QLnxcx6g8;e>2UzPHE;wZ5%CtDe)4mGuLS=Kb8N
zFS4ywdQNI(^^?>5DkxFunJ~&%-|m%T<T~U7>91%ikjkgIC|Ctfr+2;re91&=Y8M^U
zr~K?>KZ!cGtBs&+Y|MMOP(^hN6~6pk)Fy}e6*8xF1FWh#n^Mo&>EP#8+Xi|t=T>&(
zVN7xCoQ#iq5bS^E2sMg3bw&7MU!~@KgASNZ583Z59NDJR83KT9F)fKs5;gEiy$~l`
z|9zvXMQ%WTSl!KGPka5gj}uY!;<2X!Obx&U>vQfi(JZoL{+x<on9-4QU#V0=Alb+Y
zn-9NC;+s)y;%_?04wVQ0l32>MCVSN96wWs#S!vh1^>%zMNiguJFGdau95!!!gxy%C
zd|4^|s@fX|pj6Hsj&^oJT8Fa2nvotgwe=;)fN4*c?asECL0Cw~ad6f&Ws(Ee5D#uV
zMrlIaSkl(vzV*T9?6|o`6wWgF_QG-7Zy(%}w<L#b+eUNgf-O_vgJUf>PD$aq^Hig8
z4iu)?NXO|aH0MjBCA_)$Ww=&lQ`86Z+FF}L{7Rm%a<_vNBfO>g>zsqaWQXoEpV`-3
zjyV~n2Qy_g<bL9r|ACUQsb%s`dActmf5$O=uWQS}N)P`qOKcKWgcd($taVzDLvbRY
ze2s%t@Y=8jwX^rVYWR=UfCZP5f|25j%B=nCet_vAhiI0NZR4>0+GFeV*ii{-wylw9
z!TjiimNZG|zzBleJ^Z1mvL;{q{O1N3@<XD9c-2~vCV~zi-cyeI{$}>OswV$qh@*KE
zJor`UT-L>}#onVuD)q+n-Q(n&>smLKHB19zPgCf*7y+SF{fMiHH)SDr5;h}hLo)75
z2b^=7vtb!&rGU!F9Z5z*y_$SD-FLQ`ehKaE-$@Sods#udEpiuk#V!~ohh>D&&EeEb
zYY|Y;`M)JjL)038j41g?{aSvc>^_}_zZoPtrC1I47PPdPZd4|*+$M2g21$I3qj_pY
z`f+i4GZ5Nu^n=e2k4lEO=`(j4O1IuR$7NR;w;1b3nn`i0gloGcKLTh@>2PAG`QP}1
z&%-@q2AZKvu9V(~8LJ*-1R&IE`ze9p1L^6s-#QT;tD!u}7Y7?lXO*e;!_G#_3u`{%
z%9=Jb<Y)I06*zO=vUtd!{jpmn%uP@^$MCoM?Ezc=y+|Sr#Of%Qe=5hh8KzDzKopHX
zqE6k{{pF_UxJ>+TJL6;yk?!cjALK!M-J%9StHZaSzdP{hg8p15xVoLZ|K0e1B%O6Y
zQ}6%w2?c3Tx`u#shzz6$DBX>uN{&tya12Bdk#0r|iP7DSq=585x}`%JHrVGm-{12e
ze+|w#<39I&y<gXL<y}S_F`1YDSpctyn{)A4I$ZWSWN1aj%~vYS7PvoEhX)m3_S01x
z6MaiG@d%z{2EEY{E_!sf=d2JZC<Uc|?EpaNC{5dg5k_BOtj0w`)@PeHg3rgwsEHl=
zp^`aROj#6Una<eaLjaSncdIAXII4ri==Aulo?E;k{e!8<TTIlz&UyFzGbG~F7KQn8
zBqz@_F!v2|WEiccVkl{zcwm_PX=C2{fzM<s@~XIVUIC<g?<F<~yaq!N$$~$vs22k~
z*S7@D2^KCCAOh|iRYk;9=7&EP%Ib%Ifm)i?jZRO_#>~Z*>#-NSv%LzGHh~<hXSReF
zbKW9e>&r5~Q#8TNjV(>Ff?lvmxiav6o?IAzm{zL1ZE{BBHlZqW@$<)mrNFxZJn0Rd
z?;L^^#l^^rKo5na6aO;lU-k0}$($<XtJMfRJ@>kBVIS44(<kiRS#jiN659q1i~}}x
z0Sb@(pJa0@B=gr!TP7BB-qFV&c)WB9u6PmjHX5(|(%L;^t2r8OVOzELS69@Gw;nuO
zOdMSO*l1@x@t`5J|4vt#*!{XN=V7!AU~_arhuk~8uj==W>bBP$X%*=>!tto(WRR^V
zQP*TV)NWfHrtWJve*jkXb2e$zD53LMk+80}l=T<n$$7#SAUCa=(KD2D<0CD<07kk_
zJh*WKwxS)*O(PMN<pEC@0buD}xlpwS`FpWL#I_y!{JO)rZkrGtSp%Gbj}^7(?`5Mx
zB!`=Hh9ozy3j6$qc}D?q-E%W5W=DNnZn{1#X;2?%%4Q~er^mv=UhlyYQT0NKxT(w}
zGcnV!?IiK|SdoqS7pvDC?H^N6wC~%kHLHmHu2TIyh5~idSovogU~;s*BbR_)yUJgY
zBRk$%6VnXC)Y!TbY{`1ad<aN>jq7gywYk`Tc(pfE-F#M|#&bMw^zj+{I{bp<B#io8
ziY-MOC*be=5N}^&(`A*P&&2w;1bJ`kIH)v5#EsQ^n6wQK&Mdbfq839juOYDto70K@
z4+o~d<p?pPj6eTP5Y9%WIh0NN*(no4+A>v#3<}-V5#Y9>`*kHD6Xg(7N;#4s*0ncV
zXuBur@+G&2X3^NyiHVKij=yHtpqipiLX0j4{m|4p;($uJ&jxFH@J5$v*Fd$@b4KAd
z%;<YW;346BTKCh*r`u$EE<FKCUgp(1-X>9N*Q-=Yn(A`nvNVL@*hmPomk$sp^@;I2
zd9PMrcmY<1h;Y#E5HWeMRmGqX2C{(0*WQ93;BO3#x=5Q!nF&*hFB*7<rq%izT%ZD)
z<XXZO=oqQhSGYgiI%C1Fww_$<8tQK$6VD={NZwQn19uYO)TM#6$P)fB>Xm88M0Dyy
z_$fH){FQjZ2aNG&Hz~!Yg0q#oI6i!(mp4f8R#T(NPzv#`!Of`dbCg2TSbFstFFU$d
zZZW3A6?R_?<zyw;!N1lJdX|HURCV)u5_?)gL+$9f4kiG!aW>5|UtINv%YtX|lbZGs
z6$6Y^T49+$Kq>uN#D93!Q!}B`kkf@of_2{zMWE$gL1DL$UMKHaa8gb&(=uG(g@BwH
z@zFLNXl`q-3)x?hP}n>Irn>^;TMKXAyKRT*K<o&I!gdWMdon#xV*0`RhWG{MVP8O5
zss=x|nK0-aVySt+vJf`)<0}6dKKn7eT&nA4HwuF;kn1oZxkRxvi^Xze21VlebbbCC
z!uAa6P2k(+SfT-*lp<m!{DaV2CK^a_CK%RKy0OO#n$o_*Pn9luuc?N~0iM#}2A&b#
zP}Sc)ywH9q(b}$7_=OclpMmxZ-kHWJWf_q?v`c}6`|T%INhRA}BkJx)Y{5wxW|iDn
zqd7~Ult;N5CuE2>PqO2y6=KGs!=jFpvGTqu!q1=uRJDRxNE1{uEF0QhLy~h}03Vw)
z-i%}RCX|*&`EMZb44XD+CqGA(#P*}q$wZm%p+9j^ZzIbI1<MTIso){f?LPA@;&G-P
zzJw2p8E8CylVVec&n58aG?|V}u8?bl@Ly3_{J7yKJuCgkE3*EHm9+N<Uhyk&ct=fA
zd(RqG5xRi}lxvXdg?<~HQKBVxP`pu+e!VqK<+H0Q{@Ht=G*W}u<8eZwQEarlBI_aV
z0{BZF@iA3*^u(uN#~fk@uizJ2r=baXZ2UhGk?q%pDau4IjPMt|PmRKf{|T!yv0Pi8
z6bj;J7Aw?|d+%Qv8*Y1Yi*D$M#;)>4`a}<G#}bZ@KVJCiZ{ZbH>vf+zkBwN<Rd>Ie
znvcMA0kmvzW9;ZWl^do%44(9|#w+UZ9=!m9f6|XK-VeuXpJg>WNU&=_VColr-~^JJ
zE?RssA3ahp*(s(>I0<-ZGX@mtadEU2!p`;!8;)4G<0n&9*k^`*h=2qspdWZGEs_RL
zHP$P#G4PT@Q6|KXS<Ze$)sB@+Y0=y&{}AT~{(0<44LAXIL?OEl@3cp*DgW#dw<pLz
z+v)!R6;<!iY1)wBRkdYQ3gLD1bK$)@F;5d(^1zxn-$W$=nQ+XM(QmtuJqT&Csmb42
zyIn;ZdTqPmxI|M!>LJQ*e)4J`EnkyOB&2`#JpX>bV~7VHs9f<+Lfq40M2R)y>2JLP
zFzwiqFES9X${`+^8w?Klwdu<!LDPjJ%4gyNQq)L>e~F#tY)qzaB|H%41OLwI+|%1I
z0M0>U5;-Jo2cnpR>@?ab$W^`sWBizcq2b5lWij1Vb*G3-4_~zmrj2ddr3y%loY4ax
z_#ckkRoz!qk1Z16{@<#PjngxuJ6)O1X)|g9+Q;fSL_N0eY_~PF-2cNfRj5}_GCI@V
z2500z1|Dzc*eQPhlKIYdD9_Om(k;-4fq?eMrof%eKrgf*vK&w6>&8_C1!JO|Zpb!@
z@6$Y!(h}1^`zy(lmuqcd@yFT^ESCNMq8RtP3Iih2mY!&EAN4qYB^;lIHQtL|8n{N_
z1uk*^Dyxy^IJeldOXrP#GH}mJ_K)D-C3eZKrmND1_m6&ZJR7EAUrxermT#}0bdQ(8
z{1GqyAgJ3$X=j)q_KRz#fg5d*@i&g<qA2`Fj1r1#<RY2?_T=9l>7&yQSGGU*!fa|Q
zUParg!i8Tv-D;~ak8(3fb)|eD4-M5ApHg@&FvyB_`><>HtThT*PS!)H%LQI)n`Dyi
zK~JbINb!_>84H}QRuXz4hcKKiDovJaTlER9y8v=8C7biHqHKc1Tn-Nr9NaPCEo0;h
z1K=GNmZn8{*KGPe^;Mk2#0Ti__Yq=e_N-V_fA;Y6iQUVT_&!nxC83-XV+j@qQp+LA
zAkw*Noqt68`Yr~azkH7?%6sRUO*yGrV-_9r=Ixs=^c?R;1$s^MMb11T16L!zAErdU
z%SfOM$k{V>YkK(0`_QIDZqUP;Le37~j`2`G{U|MSm=v>W>bhtlwuHS@m_yy9*u}fc
z20o;Crq$=TgsfYL&7EQq?6FmCIxop})}lI>X4&K4a>P+cM-#9D^+l2eH~s~lHTWZo
zozJnx+*AMIQD));P))L98{~AC87OF0q^Yq0-MGsJ5kP+kf8!7y9H?-CT`lE>!cJbm
z+Tza^Dhu$G?HVAb`{FR@Fsn4^L@4oY{l0qlRn*c;;@rqLTG>~5?A@WUCRPqYc$moG
zIY4lV1?;7{)E$iS8{|Nw6CO@*a6aUTNz<EnPl7vWm$e<ss^(`)Wk}4sTOBD&%S2qo
zJ50SgrLcDt48@^zzOUY`+$nKNRUkUMF(6r?)-LVN#U>oPq4+DDc)1hwMXaC^CpZ<W
zGh1qFA1i0^SOFCs`90JVD77NAq#5b`93-Kea?-N(JU;ZeX*z9&GfePdgZzE|)YmsW
zU)0(KLm3vh>Tk#&K4%M@epUa#=`BUl;kC)PC-47O<j_tCeb_pEe5g&@ZM@B_RdpC;
zG_&r{_+4}3uFND%KFt<!2V{NC3&FR6i?q{zY2$xGjC&G~6V@{-s@Xo6*}VV*90~9D
z^azFYAB9y;gm+J>cN6#{^d*ElgJ(f+{+B))zwhhT`Q_ywdb!xz#m<^AO%Y)+<N-G9
zK!qNE%_EiqP9GE^rtQ4xVQEB~7sJ0VWbfcttQwR_jt<?F2cvGi6_1Q0chts8H3!g=
z{Mjn$a(iaF>O0(}YZc!8h_HPv90Kq~EEIA5$WaX<yU)Q?31Zy{GL$n#{`B<gV!tV8
zL&R}?_rK-8Mu+>#11H9iaU!#L4=LPmlY3zW|N4^e>23^UUO@1LM{WSt9gsnQDc8jw
zuVtJMCJFwJMv+ciw~Z%_YRyQsQPZo%Pb>ReavIb&-GD4AvK9^m60tBEk&1E^CFbih
z(`udI^_H5@*c#yXy!&B(zTU;A`(ELbkx_XW#n}t)5!_h<|KeNzX`1jGj;{Ss)8LsM
z#iUKF2}`<%TcQugn<Md8K8x*h4~M*#8cqy&z|q6l;>2NoUZx$F=*3ejcc(*>$L_O(
z+(C${Fz;ci)LjERWp~Iyxb~tH`*h8zWq{qV8<lV5fH$g_P(A9YOsL6G!IXz)Lan4i
z{mYt>-o{*0tbFeS<RLlY3*ukpm_Nf>p9#%u)%yJ3j=D9vs{SQON666>w^xFf*VRrQ
z+Nej6K({pU04>C)Hkj9W`@pEz7jR^M-uOd{&o1oseoyq8Sx;P-&6CIOpuh0+xbv${
zXmF+O9K2uXFm(?~Yr0a%dJAMWJcH)yh!avTK3{eD6JK&^DRImHF<RRnF#_w#zyA?>
zr-~GZcR5peCfH3Z-kGADJ<rZu==aYp-o$J^A1PC9KJVjTbbO5$t0u>OUC31Np+Bkf
ziy)`n)=UjdiFQ2YYeoHI$Z;fIn$E}Itt@KH_<*rD4mGVSP)h+8_ndZe!^rdAYJ^I+
zG{H*|cvbOxPDq&vShb;@!7<#UQ_0x(M;P)v>^M=~ej@c~ZV}Q6%;g(Kf}2LmA6zmP
z&2549C6b62Xwexug8hjKYHyP{vgg!>bEO7++31-b*h{aJH?BI<SkMhlSFo^!O^5ms
zFODxDk2#9hT>JlmXMsG&Q1b9ez6fvm-(hTvh}O&24;#aM{8tM)wug%1e=W<+5F4hd
zkLiidH`)m~n>*^VpLIGk3m!C;c)zd%-kXlgpbD3h=9yWllnLm|mg+YhuEsz)UFqfm
zs5#dP_R9Ix48#+Lys9?U+WUMvAKenGC_v=ebq#Zo7;__iM_v8%Sys=>Z&V!u25kSh
zQK@dt$9+n_AZ>rtR#mvP9<c6v1V{0Qx;moTg%18KXLc?K$-LrSb(L%X25gZ_N8w9>
zj)&a-oh_cF%=e%-fsIDKj-4u~8;fjRe?k9CvRB#|=~4F0yXS_FP;`uq&EB}(!Z*yZ
zbgLlAO6prNgS1EyTZ`L>5>hwfr6~`Vz3_Y@YN<&PDwJW#PoEx%hDFJS|M2wBMK29J
zmt7es&J%u^G2QsRf>84hoh6>`gq>MPD{mHJsr}I+4*-D?q3TY|ss}9L=pz4T!8)9e
zuOoeVs*$OB4F<<X_OkJ%JKQI<M+#BUVei~--4U60^3RMX(=KX=-qb3}>YG`z(%0SI
zmnYa@zS0wp&l_4X-&H{q-<gJG1{UQEl+oQ(l&Ah7ED#?=ckVm^RDN0fH%}0zobv2a
zW2N}Ik5;;afok$20ouq_{)c<3kCxQwn7$}Ixk!=PBQ)NTWhOM8rhemQce}^iIc@*3
zzMu(%$bVbQDp|9lgPx*9;4PJE!dLw@yG1gh-*kqLz-3-YmLo4NOV2IxjZ_!k+YG^O
ze@{9o6Q>t&-EElUe0SV1IfgyJ2#b%RsaDV%>}%fo>2fmdrY~Zx5C;A^Aur$g44zv}
zj@u3E!e?9=F>lk<3Abie{<*w>6#!|_4iNL=uLe_UI_$u#+->Iu4<&1NRbLvG-IS0v
zVNR)A>bLSwCf(oiWAL#`;+|o$|0@}unBcVhdn|SJtV`C<Zy!tm1KPx^j>&-)@6vBY
zdxUp3Q9y1B?IqgZu50QCD4Ky#-b_>Ybm4a|W-A}`dTh8*J-F0VWw~klJ0EQzg4y~*
zwjrAIJwcVF$NbB$IDEy8Bj?KNa*LI6nybUFYnt!|R=Y#5fus8jug!#gydc%rAWa|n
zRl8bsrDI*^3k6IjJOmYB_Dc4`1F~G;#bbsh8MyrTI&hM9n(SlTLeAAz@h{+O@v5wf
zX$M40`=uEMSX-zR8I<>hf4cgEG!s~Yx>t4?#A2^Ll&y#is>$RR?%Ym)4*(Y#heMx?
zad(2r$FuSO-e>51-dxsL-$DVn8o6(EWGoLEv*|)F=Je?&tvtnkEA5^l;uF6IMBLPK
zgI;KD=78F#m3Z$;${4hGIfwqD;WgfRXF>q6rk#&*E1}+Sb)H)SIyH*J7j%|Jf!9IU
zRPXo+a4XXx)B+|MWJ!}xVJF%zRI-!4wIAC<4g->U?jpp}v%Xg7XtP5hTa?iY^|H_N
z{#uLBVSxUL{;#pEg2BWH6&Ne%`YbC(CP_kexOn5ctUqCM{#pG~uZMIPVFm(mNdyB~
zp=NNY&ZAfSvVJv?Re2ZNx;=Q`UwqslAe4A;e-2vz9`fDqD}g+J#y>iNCH1tqeE%bF
z^|xpr;`udJj8X7N05Zck%D|6setmZ#TA2U6?Xy*L)xyQe2izdI`NDah#A?LF3^ydA
z;P=-zz)MwfLFpPnGV=i2Fl@3ct4}E*O)0as$3rjAVvrg1HFwoQZ0~Sb3lBr8L|?{&
zg9xKx0@PqXJ;c#kY_VhhXpANP5zC$q1C6sv@JK59Eqj+?fOyy_ig?4MHXqMesP}!p
z4jE5Op>sp>x61<W6ejMUp!puiv2n_{@@Eb2V)g5T@~CO!L>;pm@E^M)f#bBJNCs_x
z_VZ6Y1sR&;OqI4LJ_2=zsG%myLA)zFgQ0}FuQEX}<tepHBKn^9lOc?DlYuP7j5x56
zg-o{1TBo=Xi755Qme;o`vZH7s__{6QIb&hbv)Z0~P%HW2|FW~H7ocGUSv`09(*>!f
zcn9?=mkXLA5@j2Mu?pR35po$+ZGO8Dx*w)pJ}qw9nUTohna%!pqH9{0*5<%*@v6Y9
z`hnyRz~4T1v7X7M!8oOmUI>dd<Z$!@MN5>`E1(V)FTqwMib-D<P=!;G$($`e`#y8+
zO&cAUMfbRvvyW)bJgoXTO#m_kx}pNjnB2-&Sr;se4@bavjnX6@MDi|`mzs1vdpB1r
zV`oMEsjsPyCEhXqhlff!;+zp3yos*CfoB-52j<<0*Gwog3WzxNDwOuq`8($j3_(|r
ze=;KXml{JpUd`m~0D;}glTH*Riej@SlC}RZF&_4bdr*bpwdt|ZP4+pk)jN>}nU0FE
zSsMMDnclN<9A0Gp$p>#@vd6c(J2+N6zWVssV&HnY!>2PnX1E7(+>AaWEC8Y2!Uv{>
zw!_i<`%se{TZ4#`jB7*1i(v|Q`oW940?+(OfO1hp0$Dkq7@6?zUhGz~h+EPvLI`<v
zRAIUN^!3{bmKDLslxIvf!%u!QaNxj7lv&<96P}XCrsdM2mCCEopsxjHu1gx0(fka{
zKN_AzZ_=9<MwnBslFvA0*q8T3MFS7A{J3H7lpPrDH0Lb3>P(K#1=r`>_fC9jOc@ft
zi+wy+VqE<3N26M<H1A#HESL40D`C@U#2OdG(c)w8>=5&ppFgedZU1osK&%4nyL=hv
z+{%ML;<1vmFuqg&+TkV3oXZ@?56v@-w=K%}$3{Z)EA9#s5^r+RCuc5CD<?B9U1x0k
zRqkEUNiqS5KQ(*sn1@0xLNCH9s~Gs95KGbX4>M@{10|V0%3_g<!}bw87Q6nA3$iTd
z_}WX^bH}qtWubTQi|qNW&Suv>cHX;c%EZebN(tF5*Z)c;?8@kRO+1-o?(*`}eA#OZ
zzCIZnA616o|KO+H;NjdvAVA__XS1*3qYS}+E2j)fhX(bZ2aa92VHB!w#?d~LtnfPM
z%U}@h;4{{KykBnjUy*`i!`$&#RDE(9NV59*-EFbKIh{ex^a86-dLdc)Bhbm}z`{^*
z6J1|;>a9gtA&!Vo5+M|@RP=k`4wJdK8`Y#E0Dv8CyM|jML@NhS>5G`qr09;2wv2RJ
z&>^#O2gvBt8ECXl1#SB?w*!_(yV?4da)~kV2nc2PC3FNf*BkWY%6zXqU3@_y<+0+#
zE0<sx>ifaoR#5YS%*XCZ{!ZscSPWz|xodl~WwPOz{$UN~GfMa<y^%j(d*yPpF+W3}
zkj#PpSlNZQY5Ls>6i*?&;CHY6UB?(mBn<GiHW-IvID9(T;g!i|HfI+14jR8o5YNlK
zJd71sf(@3SUohw+K|G;1<>oQ#H)G5)mCb#GxQ9gA0W*6r#r)G-Wxe454+s^mo`Imd
zp*X4{9W;|~RF)k)z%V62VCg#Y8<C`Sz^~I#xndSYs=I2zWrKT=qvrzL6OsouDHji_
z(X1cmD>tEqdQG}5weS_=vaafASZB-<thk)ADIlmwt!DZKl+VY~)bVmjvGH?ar$Ia%
z2v0Q$x3si=6Z`z6sE~~9B`|+dI*u&36o!CKAI2dK(PV7gA~rX%%?TkQ63P9LO|ffo
zBhyjutBYLXnG#s45}PL@@@hAlK7{J_qq_I31c%U|Lu*C#W6&{L80vW&n1P>Z->wF{
zy71IQypNzS5qP#2La^Nk?}jN_&~<w2^E<zy+boG@ca>4dZh`C}GeL#I@7|aNC_t1=
zDBm`4WAEi|Jf?OYT9G*aOu4Z8v7IW!A@Rh{kYz~}urIv!y>ez~P=UWMkQBcgBIvaQ
zQwRP6dVo~@xVrnXB}PTvl#euhcTc@_Wxk@4ln#?=@#*Sk63IhfH@@>fGOe>&C()00
z?79=k>1?v$ocxN8G8qmy-d1Xvm#RiHzYrXh&;KA=SPNs2usxi~r~z+d+)Iyna+*&M
z*WT<KFK-wuin+4{Zq$Pb;LhD2be^;auNG3Mgwy%8ZQmgjrpg*gT$$1F(eANJUz9Fr
zdsQy62?NafeH1Vs;|=Yf#RxX{kYPpn5Bc<g#UF2q<ZD%WB?XtXsjGLtUmWT^w*W+l
z-wIDK2>Jn2-tWDHlld}^CGaiormLdKRWqnWV%E%f=*16sgJp8$l3sJMrB=I~0*d4c
zjGTMVH0%<F!<01j%~b$frLJ?1Nyhpr>E;l43xA>3O{n`TU?}pJqTof0zZ2_!c)@XB
z%PVR$Aa38_q_)+2+QBeo1zBU;xdzQ(n90~(eI6E~O3ZVcxWA=;ue<w}(%<B^7&Wwk
z`-CiiDGXNGT&`C5vE%Aah6|FVDktQ|k^_suy<pD7g9o~{W^Z8;s0UyPHrv>8DGGA$
zztz06<DAmM!iqgEr{wTPbz!%pvtsQPvk`Sm6=HU+hcM%Do+-Tb8Ks5KsC%MBnSm>V
z=S%9Glb_-|?WOn6G7-o_W*;B$4at?JNlPt`O&XBp-lowm%X70oi90;92x(E={OX1=
zX=sjwWME~qFNdar$46qXQzZj89K>k8PUw3))p)!+w3W1IuHE`@<nofS_+=x-l#b_Q
zc7k>BJ#%XGtH;T|5g#eO)-Eo6u<%`ZWw$w1yYkpoiK{tr%hk_z+cch+<n#q2_j@|3
zBuB>92EYoSd(`<Z>vC32NBqp9{VBTU-3um#?Z^;Rb!&1Xt@AT{_+vMqV-W}vCTlH#
zh@`Y(A~Sg^WWbDtU#9hL>pvTK(?wtA>N05S)P34Fe8>tti6438T>q>PhURdJBK3?9
z4z%G_K=+D?NMuU7zrAU(tLIOAWf#jsb1q$YmvZ(4Z9-hnQQHCuGQ<mvIma7m8Qi$y
zOdXz4(|B`RtdsfqO+6=^Mt$aic&kw&4vWIy+$T<HiV7k%a4OUI4^Om+7{!mAo7t8|
zZ~lkZnFLGd^}*yLuTGP@;Fs@8#DP*k4&odX8!*Saz7VYh_t#H)kN$W(R+jW>L5+|I
zqbwWyEHq*sHbo7ooAX_H?-J*{SvgiZwEXi#=d_Lk@43#w^KAZnXHw#0vW*q6m7-so
z8nH<#4ri=`n%llYB*ItxPM6s?aY>)xRFyA*p0BK4ajdMCL29QP{Ewzd)i`!p9lq+f
zCiw~e_bW~Yx&j?HUbO)J)@E&?7f)hh3I)ZHK66DQ9dUSzHv{Fbo+Hd5!oa7tC<VL@
zJ_INe6D!hgVQNa5z^UYOMI~bqwSrd+?>>7MHc(+{H;Q`0{!YOqayK5b>FFvz<g>q*
zNlrS~=ymNL)zM!=RAPLj1FjY2B8yCx(87kD&ba}Z5(NNuTHBZ&70aASc@gIO-oaIt
zcQy?BrJOin6Q$|UE^ER+^KUi7-|;dpO~_bgB<`bdm=h3gTTw|LZ2b&axbchWWw-j>
zlI%KE^q5_=u7va0|CThzm4RInXd=%0F*Js7sP+A^%K(VxyF1Gq^Q8ET0w5sc#$u83
zCU-NMIr?NxhzP24i3&6qZP3wfz*PTwPA%HBg_uEP2Xscj?sITpbxURmX5{P;kaeGp
z2rl+?3EtTYK-CoE!}#@aS=!hW7IQ!jrWm_g)_~D~S0#F~yrQlv{6o@q5sEA*JGOLt
zH&pZOe4$J$HDn%jZ^dEy*Uv2Z8`Rxb6E~0MFR=bVV|?MkZDXM0LDSqHrn2zAE_gQy
zw$4);1FgHP!2j^h9?}_SfvI(FL$DHHHWtwSmh_d28NtuV0y#E4_BNmpJu8o*#Obt1
zYp1YOvqu4y7#vAOJ*07&yQ<k@{Ub3;zgoVL)D_wi9PF+XdrO(;n#G1Uhfn;+{l(=S
zzc?<k7jv&<kqkbEQ3!TDg@qYh>fG}~$~Q@nzi-gY2+tna1EAnTDW&dRAvJ8hFrGw3
z*s`kU4{)fQ0@ae^@h|X3vDlhlu6(s-W23HuwJ1<WOT==nV#O^odv2tw)h>p|@5DPi
zwsfqGbu7G<(Tp_kE*0ZFFesb}5nb3<!Kvr?8BG1%H)H<$*HF_--u2O;%ugw5)o@hk
zh2g-c!$3~{GuLm1kXBdL*ad=8Si`21W0Kefo&Ca)?)$Zt^%ARBD-1%ZE;;XbP(AFa
zjhX8|jg51+4S6>kqSde_N<znrZz@yef4L-LMK(h_4Y{c<i`qY1xMtag6nkDzZ0(gP
z+;YvAL<@q1T7V2R<0;g_ws1*<{Bv*9ZzAyCKZ)DDb)Q`vf?ao%09CQ*?yDYNcxQam
z;S=!uZr&EwD9{P^RJf{L_{@crxRI7F33>A%n2AnbE$?Vpuf5fwh*!<%O!|KFRpD#l
z2URNyC98KT5<hAd<wi7S&#@PTTDby;4-U^qI2WN}Px~@hV~-s3NiKI~yX$Wc0__6w
zDRN_z9pamDCq)!TnZbvNfF4yF8RueJ@)TjGu)L;1k0<WDMEa|T?M$&{Vvxn%>JnSm
zxj+-!TJRLmQX`E@Mj_L?=|Ge!rB=Hv9x98=uGzv1eQ46Z^kfj^mrOg2zIcLdv51<u
z95GZKnzNH1bBRyLGSOfGr`X}PpaVw9igPHupxgR~V`WtkPSFV$eirM|N5dcsp=Wj_
zE=pA`78m<^xTzVjQ}dUd(I%%KUvP}2d(^S8d4C-VAO*T5pY%6!2emaRjVbAfR?@F_
z19k~WZGA8%S9CH7$`E~~0fZ9~u7?PNna{(vTEECwtGm^!VlfC&Y;FnMo+bg45vMBU
zk<^oC5&uo%)q`_U&7NlWb8OkVwHbTYdijEiyGP*|nh^B9tYG3iNBqgz;KK2^UppOb
zb(0(AO~DX@4CCMGI0p~95ZtkZ=GL%Ie9R5<-@Zw?(}Y`>`GRlYbUwO_+dZDE6{J!y
z^ekf+@hp1ul&ZK-@$ER5l<YUQ@20zr4Oyz!L{$F}l_E$drW+wUg*9kC7q?_cWg-hz
zx$I#J!QHT0B90J|UMc+M7jERO+SOZ>NKr^u%g2zw0DtHMDB3SGy2Y~kN;A+U1sW@;
z&XFDbSBt$+*3JVNiW@J?(!9;2koS>|NxFGy#@tGD<CijkP3D_ErhEr=Vy{DCO*~uQ
zHeK)_L?oJ}EI*`X=TE$5Z$Xvb%Df(Er+}3;F4jfCp!9719p}|}P}H!ckMH}3F-X3G
z*9?cumz0LAfm`XF)^c@2?H?FX9qDE4EeTX^hHwYl1j0Qo1+@9SxsvLiZT*3Mg)H*g
zcZYh;SNY6>3gq+g9D%HFlXgr?%Cj`JL6=`lLS7VVe}EaB?6J@>PK|?*hHmE|c}>5O
zXHq!VeyP2eNj<2Y;zqwYj{z77-k<s!;zure19|HR;W`y*>?=q4;jPT-9l=v3CH5%j
z+W9?J&c<<n!17opLoFrRc7Yv;G{kVbh^MeGPWQG>h{prRyBMRG0#vcAkkZ1!>-_s-
z0XYL#?q~m7`|lqmNox@)AX`g`O&Ykwb~9p86G}5ype5*MDsRo6$JVARkBxK`77{Wg
zh&LQlbYTp10()0cogx`^R2J~d7}Or=T+Ss=R!EuWu^P>8)8%fYbK4B-#|Bc0SFR&g
z@!voEyh4#hJA_-mwf#}>#wx<f^>cKU0QPO=9N=ktYUCRl(<GtMS)ad<9v_@c+tBje
zzl}`W5u^E|>bzhAL;kkv(CsKU5!Sb!bWoqiTAfGW7`3sSXb1k`DY`YUqf7b-*=nM4
ztHWf#?LuW;CuCzs5%pW=amu`Y*k5UYEYh}>9WhSew<BxC3!Jo@_?Ej0RpTPSW0DA#
z^&=G5Oh2a^&B)mKiUG^sjk&zZF!fFO9KW2^wVUov7vOtz-y}s|ZrgeAN+LQ-J-*A<
z;+{-mE!#wh9;?2%{;S@RB&89lh5qP8#AxJ#k+A>|OS_tjU&{N_#@mk@)wKBT<<ok2
z!L&cb(82!qEMPmEqj}>9_^im1*Pri+%OUJ`gM|c-is>Fq@&J*1)O;|ebT1FfJ^si|
zRFF>wX+jWEb2NKNUFa)Fvzam`zQJZUCWz2z&@tz=0@RJ+=|o#2>n3)(uB9R7sf|+h
zIx3-Ce%8ggz9AOGAsn;yJ!U;(Bg$tML+Y9)t9?_<tzi!m=i8nvjUcERu55REEma3O
zn;08kN6egPQnHN#p63SY&LD)H3_qlekgb@!V#c7`Bu>(MUyrhMni1jM6y-G~%8p8N
zh;7^WSBxKHFtF%-jyhDD<Sk@+OL01!e36fRX^+g*7i(4gb-I8sAbk|ehww@#+1Gp6
z2k>Z`cuH=c;l&_LKQGSP4t>HYS|%d^fGp6Uj?H)nEBVGvLvA-@VZg}5ZZWY{XkDoo
z{~R{Jnf5gx0OSSSL`pSMah+#{_AYu-@G(xcc07oq-eYK4b}01ITeaJu4w$dzsGhps
zhW7oR@}%3#sg?dH`ZqHKeDAqpxsVnFJ+r`uLzrPX?=`$b+~{TG{@H7g=KCZdU#*P(
z#YDJ5k{jQ9S*K2d6b<g^wENmrMh4(14S=u?F-wtPm839%_HU%hT^5Ru)Hk{nWq5D@
z1z8YL@CjaxftNP0{ZZ1=%S{-A@Ua!!p%BpNqp((5cdHEq)JZNCs8xM04S{!j$a(oQ
z$$u~>dA|w`(-YN|qw3Ik95Yl5%>BLpl=Cr-QlqVd5LSS5+PR6!@ql_gWE-1S^bHT$
zuFeFRzlAQooP#XVdU)UB8FOF$%>PN4=er!j&AWA8c*OnMz2vVJ{?CDS1u66eC>l>A
zWz1k#$&C9fMxKA`zR4)@IyBtqmwp*+gaN;mTP_7;r5{ObmNRt6DuC3U3Rv_pJIlde
zjKZBqM&QoMj`e&L_mV!@NZa=@Ffl2`k#)`_H^e;aPtLay=QL!}2ar|c{Kt4e(_A<B
z*RQQK-fw|JsMJHTFQX@l1B~Oymi|m4A_CB8X~t}7DQGCkTD9lTu1Z%1=wLDi9%2HQ
z7yl`ZF}(Ys^w$bU`=Ew02wyAn9mt}DcNF5!F~S#@{2!k2HfM;CQ|wy)Ti<M{k~P3=
zG0f1%cc!a1H&zJ7m%N2D(gx(kE{7RB*cATF%UPxdZTGVKd6jeT)%(?eX2!x42PUWW
z^e457Z33Z(Ci5B^+jyjQqUFDX0!Cp__C1KQjsY2$=(0X+_hTWOgA&m1bnKIclbd38
z#vHn#9UsN;0({SJX=$v*#<)JG5eIH<gh<~Tn+s$t3dr65`8@vmGu8Etog&q9vY5w&
zC;3>Vu?GV5;ZMEWN65%|S=xHe!T3^f9SW;1`Xj%di0h}7qwNEb(Ht>L;c|r#3z2&Z
zXQ9pbC?>p}{Ya15>c)fKq9a}BIp*_*zQ?4KYMBA0NKKs`qW35J>WsxV?s3RKAA0%M
z28siOBupzeMq0|M#`SWwp;y%U^rkypwD|Pb*Robfmp5@vM;fLxvWa)&@?Ty>GSQF#
z?bqo;FRBRmrAw82@kd=8Q@BUjl-NqLMg~{vc{k981al$1okI50?-7Tg?1o?1>-EOm
z-k^LG>O8-L_CY5(BoCVHuBd~-ts?UJ#tQDuxaawfpR@0Uhdzq<EAJ5THat?lbAN-5
zXeaRI8S@8c^X-E+48jgnSGe44HAVSg0C^or7Y7?wmfw}z9#t5*9wz_^T{OMc`#3&K
z0@=@ub$KEDlS8=e!&QzBL{H%HwISZ=>YGoK$U@qHcN>fvl=4uerhdpfK0#SL?dsU>
z5ax+4-QdyQJLlO@uarXKOy=Ohr)t^hypy?piR}{uSk6#V>af%K(DTBic(d>JB?lQ1
z1gE-u)Q|UldEm=AB%!HtFBmb1#H+l@6os@RQ(8ICcegHYT*6q9qap0YJ_CQn+%ZP|
zf45%g+cl%YsYB~YicrZst3C0G59@ZMEk6&;<Rl#GS;k)*6VdYG<Oep?$17G+I4Hy@
zEz^9%6!gmZn`#Y!UemDx4#U#eC&cYMcR=<IPC0~CR7m&f8R#_ye@m@AXL5VPl-zi`
zg&d9+R^;@J8g`$MRg}7j-|6|ffV7B+)w--BA$r`?`>KMPs$A@Xn+pU5>Xf?n&H*pP
zobwb9$*A#}IgayRW?=a4;RB7QAIiUz7%uZ2e&7DPiWnDc=8rfjJtQ=&ag(pD0Yd6Y
z2UGpr8;t#Uu|q0BnN_KKgj9jUtu-+(!oR3rET}t0*YY~{@m#Q-*_2_Pgi1?BXzVA`
zNi=+S{PJ$D7x0%W255Wf@b`NC+B^xVFD_K$HY0d$SUCR2X`KS7*N#r$GlRS5Hbsam
zZy3g?-m^y!zg=sd>~pKJi$cVg5u7zf`X@&BaC=FW8y0QHsCW-%6*HoS5%q;H$CtS7
zkItj1!?y{NO@wDP|C*@z8U-aK$0|=4!Kwxb>E7a|ZAKN1e2{Gv-t;&~&D7y-(fBau
zC1E?)tw#2$8@=rl(xg_xV)o6{r$dR)ZfJO9jftdN+wg)S2asmrr)veRXOHCmeJId4
z2cVc4r2~zM>z#Tj-j49*=&rGO_pW?7D#Q_}yVi7Hn~B7Ui~Yu?Uckx{PL%!_bTn=C
z=_<pmQ*b#4oDECchw0yJ#(+@^d)``GW7*(wh`?KJ22(<ujny`aU*XSNDx$U8T_6D~
zFwk7>dNTI#Sun88T+Syk-J89eb&@*=hhK_cxjo?yMBBSuuUf|1863`hcN%H5?G8=6
zE9koMn}dkyJ!jw`XnAkbpKF3{(Fl5YN1xOOIIJSKfenLW=bO{nmkKC^Zi&}R$vt`g
z)<?0=O(2R;QuCtUsi!mt=lIWWwUh349{np2EXr>5qUtWS)7bO0SNJ(1v7*kJnug<v
z8`h!Q_+PJZV2A*h$LcL64#<eJR!!z7kh1p(3NuX^{avBb;Cr{H2!7Q)jBNa+2;fIR
zm$ZZai1%aLtCC3p72-jUr?U7aBj*bZs7%X0C_Vy)3=IbX$2g>;#Dm7kLB>}r4FM9b
z7p-bf3i#ODjFHezBWx>UYA4wI!P|zZiN+`S<rllAW(OfBg<_B+v}jQ2qtl*;6I=Tf
zzdk5pj0k=@=#%bhE94l>sNRb`SjwyJGvT%1$|z#M5vs+197&g;8^}G;R$03YyApnT
z+gt$gBs=~2pw9{Hi=T>4S3H-XjZ@UMHT6F12$3M%i}9krk16N>Y9!6Gz7+iZe?br4
z6d`ti0!2Kj3GB5&H-X6m@Jz&8FuB=4IQlI}C0~&9gr_+62VFMTWCS2dl;2FS%DB0i
zTeK4H<&WR*|L`18xk1N~s;&&uFoW1h&DWBO-l)WwbPMCB@L_o&q<d~?sEj4K1h(ob
zAxSc>tk1?#p_wPUR=s%v@C~gOJY15Le5EQM{n$LzVT$3XPZ~I9BFHg;n*~YDQaH+b
zr(l#~@6)gyDAi@LN6H>V2A^)Tr8-(k#=abRDIiufFU|@Tfh;QuOvuE$$@W|eYn{<9
zh)_+&^}q0Snf2tP^;8znO4myve}kv+sd&VWH8a19X4ix>Mg6<#Sp0m!uexuhClP*e
zM3AA{C)#2In#t-9v!)%T4l{4h1b}c}^<VCX9t0lh?}HviCU?wto*ocaNxZSI{pKZ_
z2Qn>5P;oivtN%ziMPd9|`DE|W(~&wC`T2rx5{$u{rmL9hqWKk_z4<oe=cFZsIz%#0
zoa$=tn?vVwW9hq#5*+Q6WKkh7M*X@rSzP0+mT>y~<K|Q%mKv1&#M8r>V9;G9242r;
zn~Qcje4*f2llPC71PmnNlParWnR1q(UAKsrG4dZ<%*bdGKHp*%;9cfMA4`QCE}(!7
z)70>k{3C)p?J6eUvYASU+HR55j3CCZfOUCvd2QrrM~rWaWjOItsk+rl7+|q82Sg~t
zCo}nK%vJ*OWTZrPG<l7SpZ?zcgYF<)U?Y;7*`3c4Ew*6hjkkddd_}(z07`&#SPv2J
z>qGf~1JbYskWp<1@N>Wd;Bs}VljiH|k@v@)OQq=fGWv(n0Utq)miH%y7oZq{m+l%J
zN68O^68J3yyTtEm8QHsxc}VmyBSD0->&abJd1gQY342PZrjZ5LmwGz2gUg;f$5ufY
zcOmU$!!0K1w;ufIgg3+Fia7^EQ-hwBQTB=<@fKS6&%d%68G$IW(r}Ep@ooY1ROE!N
zhcZvdnMuadD&gayIsQ(*(fl;zyGbJQvV<?EN|8=z6Jns7;A+gGo5kflODZH*dB4~y
z%b^>%2!Z=yS~z(NBVg_UC7%5$3l7kmhOXr;h5it`65yZJ))Q3LyNS?V{yD-W8Pe|I
z<Y^^VJh6piqXU#M+2?<&T8tF~6ZmIIgPp$mC}=F~w}g7<2zomR2DwXo5Gh8cOwL1!
z3+75Q<5EH<ifC~w`F5KVe?74dni9aQhv)MqwpU<6$Lu=4&bB+2S05+1;PC%pw%uK{
zsbEDBAlQ(A{?Vviei@EUR2e`=rY$T<4ZBo{PC(_p(SF3B;UTnjWX~RZ7lWD$MC50U
zqDN~ppL`a)0N*uiW?|;WutNMbaL4MN{fF=_o2>D&filDiXz!5t5BT{lH+kp2JAG;L
zM99sBU^p;K3r`!#DVA<-hF?E2@TztioXJuT8V1q?(i-MbXPw5Msot1qV|cZ#;&+>i
z2PGq^hMlA_pP->m2aQcP^#z2pq|xQ}17nqTIAWbwb+=gv<KIfhZ1NuNiZ@^;y%`x(
zCX)IF+s+DwpsWj)o`TAi86M9oTM36k;VVBPz{<!`bi0t4g?LB^6ucI_orqm-%W5A+
zS6l3?)qIyl_M%S;u&nU6{mmDB&Ocp?gi5gyN$+?29>@P=ORD~Y<+^`-x?Vhru+mn$
z{CEnZovH7dvAcOqkA<n1tP6jP)0!`5AbiTg8EpN~?m{!*gC5xrO|PH=E6MqN*1HD$
z?AZb=WqIQjqD&K(WVA&W`D2riW``JQMe3vRLB=_<GoqMz*x<OVaFzd4|4!y$MJUGL
zHvznNWNbLUU!hDug}J-(_QS&C|D_(MOmJZ_Sp0+Y31}hc0<n1j%LlY*ZMzxuEm<XP
zYS(*rSTG%n<<8B(W%)472I1ZY$!uSo1ib?{hwEHgo0ZyFR8BxC3UH83eveL-l0(o}
zfbSo+JLgGO`>J<a-2_1bumLk!hyv{YTC{A0XgY0fBZ|p(<nZlegK0l)Xd9h6PXb(|
zFSz2KjZQ7OLNh-`L*2cMczK2wq9HJ8y#ObQxMnZ94}vbwF>?j6C3W{fxYUVx^_$%S
z+r?7VcsXCi-jdJ6AvR$nAf^igO%Z?5wMipdEAo07HSJMYs7o?YRJ)J|D~1&@&JbAn
zZ}(s2Om^+Q5M*P1iO)@iiwDsr63ah^rQ=AMWvz$-Y#ptp%KL6U9m=uZx^v~(<TD!z
zpYrW#MkgO~O%g%o84ERh{l1c*`qipRccC9n-dfJ~V9Jd%w9!^4CH;A`hAm9i9>?Dx
zCwxjbMk8D0{R<Ch18H<588*Ua9-S6o$-jQ{4<SYyjVpTi2aoqdND23!u?GKDE2c%h
z4&hrWb;8}(m#>crm<Ig|48*s$bUB_0^47YfP*Hn6j*~EPuj}(f8pL6V!R4O0hb$GD
zKvqj|%xhlB_a#LB>OgJyQ!DzL3$EC!5>Z|y;%}^X8U_8IyhwkoWXXnH)C{alH*J?1
zO4R3ODgfx^bxt%1<nO%dErqmhjCVu7(vkk;78y;NTL#Y7YC8r54wskmx%!&DQ1UCK
zCqM9I`MIWn9CsWT+I0ALYKtJpn#pLZB@Q^9QC%|Pq*+!F6K6;WPlVp>J;R%;4=iAP
zh(Pvh@kt#TwO<L<mxbS>S;-~J4j@aV!;*Q~;Lji{;{qU;+VA>*)eY5%R0}Oht|=$^
zCJSFH%cn&0&-7(r^BtC!hn{YLI^!%ehhs4*{7ug<6rX9Q9p3~*_=x1&Hs@6<Y|y!z
znR!?Q*|T@YZ=iquY!8KXPyFTt)h%uOolI712f3i_-HTB_*ipz$7a^dJjON<te*G#h
zj%On5yx7ftT&2`wEZHq=xonZ_BGyeens?WDa!xzMYTvSRmY7bc%De%xZr{Tm9hv+%
zUV4U>V$zcQlFgag<)Afsq$LO+QU0VO(|+6dBQP1$mYjcmuc27nt^osGB+J%C4QzFO
zQ=3e4J6@<LLSBs+i8<f&SPcPNH|I&v0mq6^;-do{{qNzUn;@jQL3R)AO0|=0Jqn~s
z_bPvUOxB+J>L)5-o|9d8)9tDc&&pLjX#ZK_;S*)|gR762Ho%`>q_PzifPG|FD5!)6
zhfe9-zKeXVcL@`M-RbIde6k=9<d9n)g0DK3!rh^Or15kEpd5|D+Z|$4weGPmI9EM9
z{I@FCmXG;_ZoQQuUQF+3E=skv+LGr75Xp_+hwf5S8@AoaX=Ga;;9dmtju=8+tZ8`p
z=c#<V*ds#<kK4+@Hw>$F6qY8Q&Cmy)S2}`XvtG@URbqKV@WU*D<yS{{GvV88zx_$j
z^(bt^1Tt6uPYagMz9A~`Qysp$C-H6Vc;~|$!@Cm0r(hMr4#g6J{a)^<{<KRAvJcT?
z|4NYE-|;^#F5#c<oKOuVdw7QHUAhs}ene6~8U`XX=~pZS&qjTM><xxKZACOsQ%cS$
zE7XNs+h=n$5)|Dfn%R?jh#j#bS{(DuwmX5bT&J1<;Y+PD<joc6ix$oFs}qS{^{mSo
z{fWw1`<2YVlv2qS`k5ubVSY)W`HMo*vTM<%pSZxx56$fc>yQ9hWPzh09tRtH(>Cs$
zld8XczDTVms`33ADcF#-HPz>5@3!e&0K#V~c@iDV-mh?A*7IPzI*x-KMo4A8s_&4u
zhGINb1GxJ-Sc(SeX)C1lg%vdLDfSOCJs&qZo&-db^s51_m_e52grnu6g_xl?v6@z%
zXzq7cF1FRzFta;H70#b)y^wym%v)v#HM`Wdx3X_q4C8ZvM{9L>jYu}?S%nvWWdErL
zK7Rhf;B-#of<&d?Y-Md#TBJYC>E8~-NAEVUlEg2!^GQ-Zyjhn)k`R^71A8}q|7F{_
znmQT03p$`b5$^4DQz5XuAe{6Oq1AXxkk4T6)grrbH=)w2Z*8O*1^*?-iV1=0mKXjH
zJ6stQSZ&LSSjhi^85cQzaO0Oewx+ou5bZLjAy`O-x({}By=8U@&F-#%<r&I}q=oHI
zCOb?I6S%$Z$|2n^U3!*)&}I1J4tDv|d)pEihC8%okXe8aGg8C&nd%!@$-MhC&zX!}
z5b07{_!ojY?rIi-eK|}(0@I0^va8PYAv$pU&5Rz%_3J;{gI0WF>;2F0ffnFn_%m#T
zyK|0zl@hI(2m(mb#H2)aj-E{9#PH@ly!{$UvirnMrTu^OPnGZLr>h6AN|5$#+)l;@
zVe_cQ+67#z@zMd6<~xG+k(BCM8XIJBSz*<QnCJDKZ7)Fam*)P5r)max7rIuW&9ccX
z0c|XHz4J(cuT7s(P4fib(AH2zAt_94M)T8rlYvES!K=z=F2JN>P+KNAK`P+{@Z0CE
zi+9#YkiWU`y_V3TPZnr!m}cszG_@F3G6-++J+Mi1`kKo`IR`+#U3v$z=^a5Et#iA&
zsrL9QFksbh)P3muMEQu@t`M9)ZpNtUsqGm0z;6T`)^baOyC5sviS!XAQRr}h95M?e
z;$ng`pxyiGI2K~hd_VH2S36lcGw@a8na1%Ko4>YCz?bcHyY#7&@(G!uxd8BC{|h#x
zPe@b8*bfP~c1%5F2T|Y(=DuPj_|VE>jhb(EPYt6rmBucOSmD(gsAr-L&PBSytUz7O
z$~?2Vl(qEW@hQ5;u;a}sl$iaz&|v!c#}<8%k>NcxgK8TyP2d0U@N!(Ls9N)WK@PLj
zMK8jp^pq}sR7xaH&Pad{I3b5lkoRgI;mw8=hO4oOYH#67sBiUKqnzK%<v`RlKSN>B
zj~5|zq6=Rp8}3x3toN3TbYtfcM!mc^OUp=di-8lH8~~Sm2yEk+=)H=r!2K}qSn35F
zZTNy2{3arYy{Tvfl|N~RHBp|ddgx>`O8#!&s0&dYcT>}!*Dzm(flYuEDpM{|6<Mjj
zG1Y<q`-|U7E6d4l-_<O)iZ<dryjvWist7c3u)G(=sn>QsdONLFHJP!Uuv2lgP~_3W
z=q^Fz+i0Yif4P+ey(;T@SLOw2)n{Sji+Zw8bAX<3$P@8?_aC0(`4o*k)Q7zVNZ(vB
zW)lO_Pc+~}eTI@PPgzHJ7BN#DBR?FP<8VAhDdsW`EiwN5lmUYYNw1(wAVc5tgwlvQ
z022_JD_Z#hAXGxWhl-ELtXT;&1_5L_IPT{Ur>!Qpz!cOs;550Q%7!~6+R)m#yB`ze
zmUAC|aG&vvG1g88s~XZKvJPiX_9){5@uUv|s7#WLvcgu%z)n3EC)VS0DXviJ!U_S5
z_zWgj{*f4!uelvgX2dM;F{F}>U7FhhRBB8?A%C|;eC#EEp;5j5D>r*jShBe7lE>XL
zf~p<l0kH0@c`M+q5SI!3{tRH_88Y?9lK9IMH^4xdwoS)s@$H(ztkZDoPi0>lyrw$T
z_^Ja&c4xPgpTS0izOd)U0fobj#wxV2zNG>iS9UvmRX^*s*8am2F}IsfkzF!~rT=iX
zU{LC!+xs<2LbKYHs_~BJ$pt|O^^yyK)QXhw%N@FUlQ82SYdvWwXvIPB*!FnC&skxe
z2t}<e*MaD&*aCTuKdhkTUU~7E;_t2_D+;**=Te0kuZFVbOTU~`y->8&Vlz&dvi>sW
zfU>f*%?&=nx(05Qmd6|bOY^P0gj8dd$<5JR#@wE&p{u+3^V`q0*HeArx%+1>FP-j6
zQe0i1sf$-#$d-VsCj;B}k)@N2aQkKY`xn4*4hE36_PV;dD0N^*j=XfIAbzffG}{U#
z`Vs~EafUlVJ!a6vw$`&}T^WUE5L7v$pV4mLzm|A3kc+46A$5$1QY&~U0~DVBcm#KR
z6~m%0y`Od7Kjk+rewX77jPX&(%mDlC%3<|#RA?Ac@HfRTlFXX?D<8bGg9G)dcd)S-
zjWOGH!!nHhOPaUai%<C5YdH?50Dr*HJF+NC`TOR_Nwx4cs68_Yb|A_qdza+K4MbRF
z<MJFC1KyTCjI{dUt-NzzwRh<_^0_netZQQq`X3(D=c@;z2fCxen<e%ZQrkq372>n(
z93gr4B?E`Ayl0{4^+?yVNK;ApryR8F-BzZDC-uh$lEy{j(-1b@pC5FDJCEb|n0vLd
zT09{5IzjD<jr87jixb;>-2dSfMZx$_Lpi4D!Wnd>_qz>Q_Tv<+pKe1I^G&Bazr4}(
zlG)|*?P(l0cui|-Q&X+;bbIlAK0{!()Knb%O`ga9qv*WD*?QkF9;;}LQq+!Bt5nsV
z(W+T{)UH`1sG_J5p{i9ytfKZxY_(TgqeiHjvG?Aib|sSE?|lDqU0ibIob#S@p7*)$
z=W|yZD6ccYb1nFZklR2~APMbewdFxgEPbWi0ej2(ECAC%OrJj=+B*m9x=lCGueD#7
zPE#=M(G+|7NK6(!+9QuU)ue9_srk{lP{LT;z&G8@FIR?OS9r3K>GC5X_t6vWqm1mz
z&0*X=xYCV7@Ht!i+6a4V8a4ZSEejs!%4gAsvd@$-lml&MmxIqko}Kp*C&1aNA?_|$
zeS2oJz2xLc8q_o?Hg?I8VVHRt$(2kB8>3{Ep%tSm7Ux{aTH$zFl}B9D62~+Xj0)mP
zs=!|Q);M~M2I!n=Dm6&GdiVa0i1YM%MuK61XhI?XIQDjzH#94=;y)_ko=0&>m#xqE
zWsw}a;ljy@&A4gmp0088Y#sOeC^XrRpZCm;QgReZrrn|OHs_^~`Zp5*5m9C7FMHtJ
z{;zkfew>IpZK}d#jUm}Ozs0P&?VlQ@o`^b=TmOzvcB<448na~7dk2AQmqEHlaTpJ%
zdQW`fgLDm>b~?kJQ7fL!n8@b8zUs}=YMkY7Z3iVfJ>GqMhH~Jz*z>!T-Vz$A66rEE
zr%2Yv9qYQa`z3k|k0lJ0y#jA9n^w~*R&2?Sg<ndy&)yY7to2i_JXS;_Ch~9@q_Co`
zOIX{2I|y%nN}oFT7zZ4bxr#VQ^}GA63OODA$A?k|EVKRisYK*ITETZ~G`LR3bR*|)
zOh@$|T8Gi&!Cs}RU1h3)FL>6_BE@>+)SCpY6*UHcYjlk3XI)LO+VfOsj)ogbUtlEw
zcN_G!JG<>5vCa&E-W8K<pJ^>Vwu^<kd#P@}p85g&<mRp{>4SeBqvak@2$=*LH`~>R
zinrWiypG<`H|}P<j4>uQ*lfdEu=OZ@_!=W*uC##N)>fcw{!H-0yNv*BL2^+CTqF+N
zIeNH$x!SNCA~No|#r4tIR3+|5c`^t0!=O^GKR2-T*n#=FMB)U0S5bE%fgct#lKTwn
z_&mwR6X|C*Q?K2}H{*9G%wQ|~k>TnkWlkP8YA9Z+*Jnsy+eTL&^3ov0v-s9$8GK_g
z*{Eo@W>bbb=oc+;q0{hM`sTLQj5-}xeuI?8p9KVSfGMp8o}bD8#5kr{_tb93X%7Bl
zdApTwov`$V+KEGTLG*EuKQh^%Qw7OXaAYF1QKJF2CS3;{th;yjIsB$?s!oN1=A6S3
zihwJ#)R`E^9*>a@YAszB^EjGJxLr9}G}!Z%a^7^(%Q8GP$`)_hKhY0S7M0X?nqc+w
zWAzN!7AA@HM+<p61c#1`S<gLSE2M0>ks~g{S17jz(KWAcy@elqws~%?cFV2&JI%bX
z!ogU|j&;@1qP+;)zNq9&DYt;4E@WnwDf^(@f#Um*@!xl1Q?{E9E*l;dju;c7HRX22
zbN!4m?>|BWg$S*laoF9DyeL&IFsQE}UwayU0+8dPrQ-^qGXpTXusHM3N?IFLDCD{H
z-H|V~Ov!s0Vibue_Y%~L9pt1g2SClS&+$ZF_Lt?tM#jO(?I_XRV8yI^H7djnB@(Db
zR}EcR*KtwM8H*>?C7!{E)~Ulc)gY|Yz|K_=-wIu8n*}}pK05Nn=2h<g*xc^LZLXTx
zrf;{@CaOq&LB-E^j2nx?hJo%Vz-Tpbrwy@#iA;;mJ;anv7JPr?=59R2{QL8uvjD09
zSyIfA9biBsT3<n_q2N^P3K8wg@X~kb4hX@Nu70x;*no`L9-fn;lccW2uQDVY(>ogi
z1>j%r&gY2e?meaByFPyI_U<6%%H(t|13hW6b+nYHnu2BiL>{~Z<t1Cp@@g<mdaz=;
zV+;^2b@xtp$?2V+5i(g6#^rG%EDV+2NZOJzf+)Y6<jT20+lOqz7gxz_4Pxd_vF@1G
zA8(GO%ao4C=qgB1srJ%eQD<w*$jBgGl{Q$?GjV3cz9L|omVx~J_wUe_34D-;)vLaf
zSi23BNN=`2YuIjTd8eu9%j>N4VLA9A*3nDbyhLp|@Jlpr>@25?%bQD-$4@%Qm2-|1
zRz~6?HRUzSh~$5S&j;U%OFC*_2h%ScKT+pn&&i<d_sBI&s}!EtuhyDQ5A6LN;z3f&
zk6q%=N<n99Zu!hPZ2d)(#=YQa|Bjt+vh_q~>jr>NXkWouihz-f8_w9dD--xPD;J>f
z2Nhio>ykf&-Q88ymnmJnv`p}EWde@@2l8o7n2)vdd_jA}1J(TS>`0Azb5DTgNzvti
zDdwUS{7}QYlBZ^JK6aQrelra(WR{S983C6Z`yi>On8u4n2EyVh{8@%xjiK2oMtccb
zs`X&{5{N2__x!3xqgzevfuat)8qcmdmO`VlM+h{J$hW4W%iDr12CElB(}(9iVF0_v
z?_!-M74Iyh{@K!g2s7t`6xi;1qJ4jXA&k(e(gJYU=;<|YSRoYkZgg=)HQiYAquXo{
zZ%}f0qAnsd#hffQOAddHIW3to8C~`4ZpN9_OXX!82P`LJ<j>JPa1J+4_C9;YnGdr(
zu03{56Fe<!EGznC5~xMh9r?5J5qrA#=X++A0R|x?CIg(eA^mvFQ3jM^(3lT`GN@#G
z@wUS9=;5>|g?+raKY5P6BnxYm<aKFz5)?%7lTf<*o;&5&>IM?VDhIO-o!;UeFWz`H
zZ^9a`T~1{B<)Sd)V`y=$3FRQq5oWt3EItTw<2);UcL#f3I6$UUO7pRgQ9`KLy4cV4
zStG{t&1x0P%>@II0RfOp^WgnyG1Esi@+a-qpTa#?88V_ZBa{6x!QN>k!?<VM^Ut>w
z?}=*9ZCs+I-SCm8C4V0JDqjH+KArSIF48nL;gF3i7u<N*3rN)Cqd`r_CeBwrdxJ7-
z5x$*8s`csp0nLXg>75YY@`J`<iz4>}sVs%-9TJcH^*reodB`I&^HdJkFlS$Vk(imc
zmj7vpV)r8eA50-r*{;FUoik?p{>Hs^0B+BxMHgn{cLjtCC6Ex4e&DcrqnFu!IvYH_
zUivBytia;4Te5b#b0GOfjtX8Hy6sCp%Vcupa9#(t*R5?#to?8TLWdV`b_bo-nFhT~
z3pmk&eXUG-#OBO2nfkc52W;)cyTl2Rj_bMqV(#JZbv(8^$!o(|FdquWCytG~==(7^
zsU?K0<|iF8QgM45{21R1!npU9eG9oyimWC%&<KyU?WPyuRV~ag4gvvn(zdV_TRd6b
z`D#wzg0(xQx`-m^)t8PLn#eulNJ(dWDiDcQ&3|h+Cvq`oj81D7=ojm%-@ow{u@RXI
zQ}>5l<DBPY6jFfV0W80T(%dgbDlLYyHp!7M+mP%H^5*!(KB?cJQuUV3MTtn#S;hP8
zsJ*8T{?nnw+PRwj`Pz-a=-X|ckIwp!)Q2A#NiOZQbV`z(72OJqf5D@g@<IFiN7XBI
zGBxXrh)@g&fz!=#MRJFmNMq@eG|?GiYYDIExf^IQOim086!7Cz&s$o+CnI5IpZ)y4
zZ>2i`=2YDpa*ii=c63Md29N^BYK&JSfQDbW{@TY_DxdW<=2WfGU->EICd=3ppL!#5
zy@A~GeZ;c407IA1(idV&@n;<nz97f(b>U5j;*EzrUb*eO7lYC$^!}<IL0^{_XdqId
z(*?M6V;m%%8-$|!i-R5lTza$Vvq2^2Z(6pd5ss5)K;)Hn$P>V;@AM+qbv5NX1+WCd
zee@qtUN<m-R=7LpXL@cD6C{|~5)oS{!R_yTT|2<{EJ6%04UdHnVU+l}C#c<Z@CSf9
z_zBbXpxOXWf9{p5YJEQHev&ipCi>;)YG17vBAo@!iMMiLPGUi|BCP%>D*;#VPtt;T
z=>W3de3jyP;D_pJR5jX~Ptj2{$h0p=0D>y{mtWcJ#?FTPi8es2sh+wWb%h=>)J5I<
zrNns8XD24X?OTeJ=2UNhIOwTzwT^4T);KmiJU%Jx&Auu<^;k;9`(-cSE3$Gk5AlbE
zWKey|Bs_;b`4)R*t%l6H8n`lL10PNm32bJk422En2HUkuNZnKm2lNKm6WV=}ZYrpp
zJmxUGm<dTKC8_$ZaE^6ZK^k;$!m=sN<Z6&Bd@b_PRkEdI?lxOj1}NwOB2MxQ&G--0
zC#lU$#lxR?q)*Kq=B~3Z3=+>_@iYxYV4a|N(~_8!DxeBRhGlP8N7s@lB*Z)!B_q~j
zyWgLMn{TgZ#xh3J36m+9gEuUkE%@t<NbVumOqt?9kOwPR8S}$UHj)&26mRN4#r>uD
z3C@hnM_wnaF{NADTbqdx5}nQJJweqJP!fw9xLHVsEpAAX`Wgl}jB!VkUpEDVGMOx$
zq6NSw!^g#r<IYZIVZMRsjqsfhZ~eM*e@EQOm3AXlhKoSn2F-^PM0o{5U3C84w14zS
zUQ0fYa@F9Zc*8(}%gq?6`)x}TvXQ(#;?lRekcpKh5j<WDgO>>MghAusQBU)md~Phk
z!gk&*s}(Os#6Rka{0R6fNwuZIEwfBXT81Cyopquld`YhONyE7|H6o(dA#wcrbOyYk
z1en-7MgQC05EA3&7Qn$FIgFBI{Av^t?W6s&<H~Uu_2g+!-R8HkNX{OuBZw#{ZO{`@
z%Jc!+z7-QD9c`{Pd{5*4FATx42V@uTFSOZ#9`IcbJ2V4Z|MupMr>QWUjBD(0Y^u4)
zyXB?4FM08PXP66iBS>m++IZT;X&Nxe?r59P<+?fl8v(h34m@i9vAe`)SFs{1dA0F2
zcMNVC-tz7|&wHv-uy#2XcB4=nT%Oxok&>SE*`K>N!zrZ-NYYE8sTg_>pDY>3Cz4&6
zqhnsR3zM690}Zex1C`PU8~)q{>~f+imiu1~t7CHpjfsR6g=9h4DNP`25&y_heOCxq
z{p7qnhOfzlf1|9)=%Gi{$h9FM=N-pa-{SYGU#4eZ#<tzHVlnE0gJjy($379}_ujK?
zRu1~#EM79U@`E-0&J5kYlrYV(VBP$@IqYc`llA7ZBK4R%D=zZ&S8g<#TL4QchkF`?
zxh$oKzt!t=C*->VN!?`2o~(Vt1H<adVMaR?VW2*=SfeUfxu^rjIdZ{i_jOX^p=o%~
zfwj>>f*QGn3RCoM1xJFSdC8#(@36RS{9Pq}qn)9At{<u{*}+j&VHY@$e$~KVK2glp
zR_kADukmJ&Y{hJkn*%CK$2KO?Co185sv$*<c7L)ztrmX>ctg|7(bD60d1)v;!wQ0r
zh$PtQ-6MN_f7>G@ovSjVvWqFHfpqW{)jO)bOXj|rMZF|4e%giTs+jv5IS*aZ22|wH
zeAm89TLiObrsBOQ4iGmp<+p*1K`U{}KT}zVp9VKN9vn3&$nW=tOXqk!jcDEE%~^rU
zEr5Rp%kRYuTkSJB4DdV8V>5Ppnk`YD0X@8Tzs|$=t`Qxj^r=UKr@4jZ{w;NLk+8vB
znD4wz{PWJ?6>Z9^fRLacUuxzR@+y(n=UKpxcs9ir@)vq`?C&?*=}yYm$aa+)05O5?
zab+%lhSDt=o50bh4Mh%kY!Y1m-|g<gDQOx<*{-O%VBgvgYlZ^&n1m{{)*ZE!P8L+E
z;K>7cDNVxfWs-~Alq04Esag)S8KSuHXB5j2m1W4|=eIGpRsDYx0gt4B^9hC(tjqPv
zC^QqoUMQCO%2MW#G7nbbRgt-Q*N=gCl}9V*aj|Uov=Gb8V3TusylxJz-3i~i+(5qW
zO_ldF17w09LrO_HtKkps@PK9WT2w!z>-u{c|9mSg(qPUZCNK+`DfDfc$GQwx&5}z-
zeS1F6i9amn+xZ7P%1SNi+7)E@*dngp%p-o9(l^LG6JY9y$~Ab!fP&~{xXU^d?Y6vs
zRY(Varca$^03fy1u<t(jB7!?9=%S10c*1~9)UEx+L43TgT2KMcH32L#+EH5gmLl0H
zV34FQ;;aW`0qv3-aGv`qZ`*g9yiP9!OYD(dX(dWV3{mjb#`)SC34wK;ZV&rX-S=jt
zoXwcB=pd=Rhl_drZh*u3`oCT%1=fQ9z+nD=AcS;>+w3`ipSv2yHW1w~2pmD`&OdQo
z&2&2Deva+l#7qP89T8w$oP?zLr{Cb>=r)C@@?h8Q(=ZvHq>gtQ-<wt@3ng4i8$62u
z#lSUz{^e(gY|$0aAWc=$MthYbq~GII6c>9Qd}Nse5&xEEYQBYp+!1}q-5};tW22IV
z;IGd)7<}4P$)7&&5S(bnpK*A9bW=CLZL;WR^Wv2;5~cpK=;>&*kdoy|2)h+i-@~u2
zWq$+{+bpLqOIM$DbY0Q_>n2g%SyR(#d22^6Cxq+!i&-t_ZP9?7f3hrtMP!pv$;M7p
z*pZNo@;kmsjafF?s?JLs&{Yp|WvFkM$n)7X%f~%MH$^ID{}A|_jHff4`0$=$Gx{7#
zh|liD;`7Z)(&19m5zn3LC#W`87ZA(Rl`q362N8_G3Wr9QZ|#aFWtcgko&&G354{VB
zMd>)^F;3YM$vy3nSFCB)s(9-J`rg(Bz6R^ppKXus)e<PwFFY778$JOI$*TGS72Ysn
z;r)=H4_|tpt;4pC7S(b!N(LJXf_H0(X1&C&VcZV#nz}UV&BJ*%t2T6ajl}dJa%mF7
z<<s-jb41qO&hIRlnT~M(pIEW?KU!+l?C)`crtuphpsg5exc^60;>)Le*e~rtrGJ+G
zN|~a@IokADo~W#q5+?+g(zGzw<VGwaUq-()w|s4@fc}1C=G7zQ?UzxXY}Z1V{L*($
zTEuUui~^`MKveCcSp({493OEv4P`NL8D?8V5{p0&kPk&GSkJU^FYZ#m7Tf&0RGQ0F
zGx=CI_z#9d+7<YK3PPrZ{DL3Vc}LL)j1leE2Km-AW;u5;9nS|FT^v+}+#f4#`3MX?
zoa*skEN9wu6f?F6yWeDU?(r-3E?uaPHQ(ufP+d&bxHTUWOY4Q}hqXsp0L}WfFrYG2
z8^^vx2@mYnuK%akEL%N<&1_!Ghftt7ytK2pOm3@0Jzn1q51ksqEb1BxJqDl50A>d4
z9Wg@uK^U=#^_oI@_Vje`ALNL{JZ4)sxcwWO^uI%C3f{1xL&QR!n2MJ;*&V^gE$mj2
zhnG|#>=cZLns5v<s2*kw{x?H%qZAc!0u>9Z84aL7)NOz6TGRv56!?vGSl+c`l)}U<
z5Dj@`mx{7W75+RE#Ta&}uv?mWM$~yxtTBK((N?N;@!)kv=+Qs+c0vt2RxsX-APmex
zaU`O7ic4Y~>(9Z0aR66AFO4NeRi6PlL7~t<3y%OhN5h3rm7n~k|8g@%hD3j?^*TcY
z_%sb^+l9j`X@9cu)mV?g>(@xYNc6(-L(3=Cl#Ud;T^Gg-7m;o2#8)!t4bRH)kQmtP
z?%?Io7p**$VnD%TU?*KQtLKvA`je+4enRBQ+wkR})bf93WZKQ0kM^E&{|_WXsb}j~
zp@itzef927t(QzKD(7MztR^b;vIN{-*4_TtoG#a;=qjWBD|eh}mm|76u;EV<sl34E
zmtL!wg=xog{qA5+lK~j}!#k!ThwPbvu=$?*)rpo~Mxn^xJ)N|KtkZ<vbjF5Qablfy
zGUR-+z(ZWc>~LaJmFT7B_IKJdDlx5CU3V&ni}p*S-$7$~_?&x3_U!wQkh8IbxotIv
z1qJZY9bFl&n~)ZVKZyB4yuJQ#KMDfgzv<-894cE>`bbvk9n3tr3*<ZyfZNPuY4EsK
z)ZxyRu>Rs-u=jq1=tvwCf70!A)V2FM)c~k}T#-%g_%=H}O+ZpH`)D@K!6E$`ax(#D
z-Aqm^33ORyZrzU4?Ev&M&x<P&P1J3OU<@8vV3IlLo<)d~+=f2i>LyF{Vg>$tgp986
zp(iH4MHMB|dt~f)vfZAotiKA#o2kNu;}Or0jKI8|6+6<$)F<w)bsxS}m%d6wWAjHa
zbd(H0kHC*NU+@t`J{nA>ga4&RsL|bd8}&cX#w_`D>AxxDv0B?X<;9B<s--dqIJAA{
z?gQW18UO_%Mt<O3B`0_Y5{dJukki+c!QFHm<#;VoMx@yG;u{fWg#A>I53BE$tY~0d
zlC1<|nc5v&fS8nU_~RlkB|SFqtQC%3{bj*2S+F5^vDk;sgTffU0LA&8nmH}@Y0K^I
zzm|+U`&aqKjoUtJjP6&Jx_6=ar2{STZxMwbT~e3eF)%M$u5A5K9&Z*&n5<;u8$+$_
zUu~g9zh{fGV5ZrA{@P3}6!9Eo@_MA#wV2FK8n>tytKth=%60$-v3-?7Q_gcHg4p#U
ziKHS$J^5M(?DP~~F8tfju&Kgw+EhBs6!Yt)IWnMMHxF0KgS{^1>!fU8A^mpoA?rt+
z^yzGl|L2E4pg}m4HGAE6FMS2-i&7J~M!czEINgl2<pVb^$3Q0)an($PVuZ&6cZLJo
zneLdJVp6>43OG(tZc?D%@*p83Cq?Ck+XGZ-VtV}q=kf;hqtPViu~XZX_2k1nN<a=J
z)01s&R`3`wHqB$(gMV9FuVX#G731D|%)4&$ZNvJ7W<e0#fPy>RRCXcuaDs2R;pW1-
z9vSaDx?#IKIJ0;3w=a`R&Y4B5aI$5TBcpXRfgW_tfO*CA)@@oPJMXWD(U2D+7P^y`
z*Hgf+BgQ}OcW~jli>Ef3*%U*Z6)TFdTX{Dck)@KDxoF7Im~7NrYVlJ4gJx{!SPJLv
zqpZs%J?BEVuj}%=y-(chZX+D^y0SGuJCh$rJ`DL&2+gJqj#?D<brIIIAJjVz%~0L=
z{LuNXrl$Sk3m|{Hy{1wPGv_O^hd}WP*fdIwj{)BdTH82YzqlZ89l+)^G@#dbWjAJ_
z3`~M$@1OOjMBdnsZ!USU;>F9zAzrwnr~h&ud`1nruok1xIg1mW)gQcn|IRP0bKTf9
z%Y$j$MANuH%Ep_Io^S3!RTlzO4->S$F};7h?v8Jj#F^9w8{->+c5G-4%zWJ6XxdK1
z+|XBK%pUgVhb0Z}ro&Ulo?vUq%O3KXEu!)?fiXYnsGH_thEteep&YjWhQ(N-20{pS
zuo0a21a=hS3P)Ge1Yj+l$8VOlcLS5rzeo%$uXPCrlj$tnyT-(FT_>d^5L)cA8<<C?
z95-rQ<aH%E6dwt^|NJ?|T!;u+yDqgOu_p>j04|>ivR#oKx{9TM-^{q`(p<yw=q*zX
zi0((cDn1+6tU6Aj*i&)&>_5cPlJQ>KJomXeUiG=Wmw7u&{@J?5y#`H0p|K0aigyWc
zAKQT-1|k|iukcd|5&QQc`_C~)FfHzgZ5tJ3&c*^D<tjf<A`?Iw&c;H%$nBp30Ck@=
zEc4^adUJmN(_F8!rMhi_Q{RJ}xl)?8W4FkX2;>uBB8NvCZg|eDH}?;2U~NSg)aj>=
zaAb%#P|=s>>whML#{skXPZHDg`W8x(&w`8WyGj#AzdK{4S3*{%|7sM1|Ix})^dPkb
zl7sjWwE{9uvq!p35dMClChLNX#aKFLY#s0dtmJ?{5z-&oDFHa$=WGHQRjEa(V)SF>
z{gqHmcv9Fc6XlbZEqy(>Xk5>JLd%jP@o;>|y_!bOTHfh^!SyIdpC6`Z;_C%Do`vm6
zk-Z-S=WIx7U1aawi4!6}6ELm*7-y>AYhmbwm@j@%<8`h0jPng)L5qMYV~9W>NYffx
zfKTawaO-^v<Uy1ZDU{KV*dq^n<*S*n6f<E8uWae4H$Kz=!=~O6e*0;pvmhE?)x94>
z5{`kF#M85}@Um4qukWI`j3@q^_*x#^sN;OKKbL(0G*UGjt3T8TEGlEId>LxM5HqNV
z^wEE~7dLrIHcevi>w#G7HmCaSVrm&cfy#MyWY#uZcKO3Q%pFg0of~{b%q*$C8{nbe
z^rnX1L_|5x9r^D%8bHU-p%fH9`w<tUp|z4%=XcIsQ4SLDTuY(NHb8TwMVEDLj*o=g
zER*gdy~Z^U<AHw0%c8u9vgI=Y8SQ}sXT(H<5#?ltC;F%YgjlTbTOr68fXzJP+hq({
zkOjPKKV8@G<NG%vu(-oX;8_uzG5L@V{M>ozV@X(NzUHGT%3M?J(v|5srD>vIoaVE8
z4TXYB2ePb(+y!<J19AMIiPpub2>x0XvXLo=m7e@QG9KE9S&9jc2GUAj(h@U;me2Fu
zxRW{MKl*KD<><deO~zBQeC03cf$mHh)iHRvLY90Yo*B=F?xBBukEP7jsQ6&Vo1R^}
zrgA^8IaRHFm$`0R@%fu3S6R%(TmESi2P2D-l+a_q5<$9|Bk@M^%QIU7V~+Qn5WDdj
zA;uW)8@8FCHE#U-?)_{n-RD=*7@=`-IXtW*7V)w#2srOf6*7bPH&{>+ec2uSPnEk<
zK4r!NpZr67!}NKH-zk(m1ai}Kod2uS2KIzd6+FSN?^;J8yZKC4YOx;4$d)2-w@FnK
zV&V--XwUFOCauqziZ#!Acb$IeY1^4EPxI%B-NV<?KTO&RE4djvDSwL2!8$gMjGRYI
zWU9~x`v1sAZsw>pe-5g=b86EKx#=-nncK_<aAjZDv_nFSf8m@W(6-J(rm!kArPyb2
zZ>u=F+xD~#+O7t>9YSs<@6%8Z<tHAxvoIjPHt^@_&zo*MY5wF@;hedFOVss}0h}ii
zd%9wkbpU|_=Z((11yUFn0Lr`_OVF%+4u=V5?CXV1{*;LT?yxvhh0AdG&Hq5LDZ>)#
zCO&?-|79%7)d9wiKN>%WaF0=k3SK(@{s;1o2|M6{&v0;mFRheKDNOB9ULSQ#jFX+0
zr9&GaW{ZK6XS!hHn~P}3QE`u70mBK}KrzBZhM2^J6ieJ`{7gbRyOS5%<U-Kbx`4~%
z-Y`)+$OzfBHaSTxI-P-z?gog3*--M2SF$j;F77>h|33b1Aosgm-^npSiki6u1p<uP
zUoGY-3#ID3X|hQRaA%82_Nl-;O<q2?k^f9~%OO}?%D;FKFVzTVsRY;?bs*{enq3u9
z!-iduk0a94^oCiyjR|CJ=*c1qx@xI?<@xe_1?E!%dkbXKzTTUX2CVD5ZbaMh5L1E3
zKmUdN@m^EtCjIa@fg&Q9R)WgU@Y2ppm7)VxK(%Fl_r-^ZTNiV+fciu^mXj770Y0HK
zK6sMt4G!Ra%s#`Z%=hJk@(Wm=PjN4V-LPSgc5D)$JzrOP=D5b*q-ZR!-#qp^(h_yh
zzBf7dkIx>)<sZnCeEV8dq89d)YpTO<HhnVV6RTo0_n9!N+BRiw_b1S<Z_soa|LlBl
z>&i$Pk2ax0O~pf#pgr{0@2PPadEB1<Lf~WE=Ytsa;-wG$?PS}ccbp23>>IW4X6-YL
zD8w4DuRdx81y%nLA1cr%(@zVqH}1bI8On5Q2(*{S^{drkDF-h8Gb5Ccsuxu)T~W(z
z0%*7dAj^cS4H*+xDP5o%bQ$srEyix$#0XOKM>&Yepz`GLAw&t?5ojS)?j!P|tSPPN
zaMoaL$AC<OlJ%OZ*x{c0n-50Zr++21`9_%#m|wZ&rpgBlW?@^ZUzt9@xhPo(aF#FO
zshXp7a(#>0$GS}!%4E0x`D8>M1Y3AGW8f(tE;^1c3@j#~mM&<x>T;U4UBnt+xi$_K
z@44=GR*JQb;bFW_O<z1<B7R*Z2mk01*oSibLa~@pj;yXG%VI9QQCNK6ZC~Oa>V-!O
zzj5Ozwdw?Dd<%LrTlsj2$?}F^xvPapaTDQqP`kB){t_VgG4)8yeY@piSq;|JY#--z
z-lu76cp5RGM(LX4w-cjYuG4hCczx{i=X1b;@dA;3L*M-PvpE|<Bz$6glWnfJ2|&^;
z=C(Nao#$shzbV_%{sf9T|FFa45HiBsKFbcEKTeHA)!}712|O2kajhk6s`fuQWGuj9
ziKXWlT?b7p>_nEFN~Iq)SHT%t6MM<b^YOWW>kgcLKv!Hwi}Ef^VGoE<`e^y8^7hsk
z5I=W-$z-LREMieigFn4PJfJjaSLV|Ch5`UGEY*fmPbsU>4e@1~6n~&+r9)o=k(s7|
z@2p5sHpmOmhmXnvNlDPVvF);X5E29S=LJEEnQ&3{A}wUDi9m>~C_k!eme2@DzG^h=
z`YXUA1X_bLL4Os^%{3A~0EY6#w7XuogsAY=0ma?c9x^Zwv=be6z5@QM2*rxmH7}|j
z<_1T26(N86<Q5vQZ?^!*JOjwAbO#jc`TE&>4ch@P>KUyh$LG{x{8>=2Fi{Bd3AIr8
zKnKWcBipyuCE(G(A2g-kQcKRC?ixTt57>e+iD&soZ_+XSB#^)CdJH1t722~&EX9Pf
zh2F`ybi{XacH*C=!<7!qB@|L$U_#n8SyZ6I*w?t(G+fEhm>Lt<t@u}DbTO6u)(fg5
zeW^zP<)=SSy=@9DdY$?MkJ7r>1I^$c0G*np1GNfu>n-kgi47lxNdJITO6Q;7!^3O5
zQwQ7fVP*hqeY9BN>?*|Ee^PLGz&+?F#%$u7fDqv>+4xN-aRgKnBKQ^a^FAz%SLYes
zg3^R@U`eCoE0L$Tuf5YuaCf$s-;Ty_i;c+TN#}Y^Jd}hLlz;Vij@;nkZ-iC~mUZ}&
z9I3H{EtF=t%J;%cY<`+0r>LKm9aohd^y@bli?J7j`Xc9z$Xg}_wnx9!Fy*|c@7heg
zhck1UGT9;s`0r)dSKG^Pp3#huX4+Yvw;KF}hIN(R_6yDZ^7IY9NM0_go!x8<<(Jy#
zpjuC5SYv<G*?!HmngYc}obJA&&y$u-`gpXoMWl$ik>*)GcmzHgAqD&dcVc%Ry@veM
z_j&+$JWhPJ&nB_^Oi7o(g^e)2P!WHN*EDP?lC&_amR|_s1q`ktHDjZ-m$itc-%g!H
zfWBxqj31v&){I3|_3iZMxm0=-M6qSp%xy_8@jnJpCM3^^!NB$Ik*uQQ1*ck+szy$b
z88rFw+aOEQ{5aAzb=r=dD|5twiXZ^x8OEpN&dJ`o^!#*rUne3=#rfGsf}X;#k443K
zbd}%?jTcq{_KP^zB+oGI3om;*+3m}i+RWqE^Gxl{SjtyTGxkD%<>#G^bNA(HPt85g
zIWkvLqIu5w>RFUxNjH^&H}F?2iv&qB0|BH)9xU(yWUV`L+N<)`aD!$`G#SRxs@-#9
zrse`(j{Mp9IUL?@M7#wVifWr=J@t%H5&0%qWx2|Y5OrjqlcVNV*@;dWu2cYjkJBms
zcG3G#&-u87MsabGO)7UR(xWu-58fa+Qtb|_%=4A4$7kpUG^*Fz%(c*lOQ$Xq=(%gp
zny>zynjZdU4NAr<p4HZjcXIVEo?#t@DY*X;neXh>h6ldzReFOW4ro%s`}=p*jmRUP
znRKY;3xby2m<n|p$%qh3p!p&@R(blNRYkHt4=T&!SPY0WWOI7h*P(N1&bu!P6ko+t
z6ONV7=uHr=JEef$Z8*{hWx?p$w_O9vm9=qX;&hW9y_-uEh@n22iuV;!&ZX~Gtg<K_
z6wZBY|HWxx?_`WrHuvd5B6|%pYy0R#a|GfjBWub18c~=P?3uT;lm9w3(i>lItLJu+
zlg+w0kNihz?Yoy69-f+&6ZuMHr=&yv87D5ZzI~RQFh@U@4w{<hDlJx3asY-I)^pPg
z5WjOWzI5UnwQ`LO@U8`62iYv743#kPENBIVwEdp`rKcKh;=}hz0fBo(Fclq?l}uso
ze0SSbK^G5R^E*ER(>Q^PafEx5`9=-Hasz%0M!7%9S^UCQKgoGL#V|tdhKI(p*oHjM
zPLXp!6v^6fCXSU<<(2}H6RMZ>oWDWlY+&p)u6R$kOE#llH_3%32Va(gGjj2&^8$RZ
z%Hu}USDxH98!w0XW!?@t@C%=!mnwNAhu+akgstNnz|#T!0}C&IGOgB!#z|M1XgXs9
zU|F+vnJ?FafR<kEG@6`W2iqR+Ylt6@)E}KX(re*_<KimL-acN~1Uu>E$;On&eWjeu
z?$*E1zaf=0kc9|Np}nCRrhbs|-VWfc@b)YF3M*D+AbSdu&(M78s`0Ap9`Vym?Jz8J
zb7bC7z_^=jt>Je!B)mTNZ-Pd@9mI$0N$hGmBO2wA#5i?4V?t|Xk-qQZT`*4j%~rBI
z*u%Nx3aVLN+WIadj4p^qnAH0q<XifKEHy4+J1tYpfWr-ykntO*)}CJVMmjwrY2D&u
zGZyDX6p`@C?~a}$Zc`2XvW;Cz{Prj{=i~daB)5T^!1ITu*3h<UoZi#L7tPC|qj^U_
z!Rjk@(am)n6NwkH^KK8$<1Um&IKnD?amWod#%zeGiueCOiXKpl_!+nv(%SH!mN#qY
zY+^AzjYB9d+2w-M=%E)oKT^uX6Zf%5QT*NMJ$$b3*~&_}IY=jT@ErDbM7n0c?hf)|
zhs1UVr)Ixsw;u9Sbk-e&s2X-|D09O~zu|w=foDP4z;7w}-EGdJl3F=;x^>@#P^@ma
zd=Ifu+P<0{SN$~PV}mk`{bmjm98}O@0$10FYi=A;3{8oAj{P`a>wL)gEzVxsT-6rz
zUw8kbT{T$LMnrW$<J|`MAOzkam|^gCXf^>hCh@ybUZq;p{-1Wf_qnXr35tDu_|h|a
zO+~o+@b;eE$?Z~Ci!7G=V-38iK^Bj`EbQOs$GiSLzIX)W@3npeOc*=bbnms^iy1&!
zRth~2JD4+_eFA-#+6~40!r}L=yz<`;D8(8*8f=*D?+*(xpU4cnIfFs@U7Cv5NAQX=
z#T$lVEBz@KLGt{Q30ypkbdl0YlrI9d;=fQd9Hr;muH{S=MsXQvHIPZMRaqXhT~lcG
zhw7YQzsWQ<F<<~M`#_lVWR_mLC<O)u@*RtVMl*Qb!YmfW4BMr61^x2Nfvemve(6Bf
zv6(z19+8zn>6gpyKf)h6gc(c2i|%w1{+gfjwUP_O9-D;iOAKG#bQ<3f(D?+A;0t%%
zwIx8S!kw2ezs9vFTI6fkUAGrwZqw}J-RY>YHOXGq|A88MWKw-etJVBw^G&W4tf+=j
zmUQnCWj+VmR2d5W%a|)u8dJAa<YMsy$W~&}ZwXbM;RZ7P+clhh?O#ZRxCCOsXy~6l
z)q|F6T4_nlZFY4|6I%qP8xdaeM+5j0I)=ZCOuB(5h3H#s5Mb}P;ZE8dRTJ?BBKnx3
zbH!T|u}~>d)6*m<GsqL&JD0?xFUicZ=<{w$nIQVdvu15D>&}6G+JQz(oa8?2VO=VO
z4@=r*_{xC19c7Wokf|CHabQR-zvkk$B)yunyo}KZFPq#ZAzT+O2^Px!MgA1~qcS})
z77zJEIT=?~6nbn*n%)$lbzQG;s4p>-r=q^K_uSy`{2+M5)c*C5t0C$>)whcfPcN5*
zh(joCLq2>_YsHl1(A8KEstK7Yxy++_&S8XDo5$)s3}{kOff>rmU~t-lGN@=yc-|e8
zN4%UieizO=!@+SYwv6JfI5V{663-A!HfP3w-FerY<lQ{*9x#qLGUTM8N@K#x<lFW7
zA+5c?x|8s^o#i=SsxCDbWW4a?6mZ)Wm6E9$e#EG>S`_ECDX+gwZ~cIz)$f{t#DLnr
zcX~?jL%i^feTB<j=s>A}7AYGm($k1c*OumpO7$Izf_~9KR78e>FZaxql>h@Pe`gfy
z=Wlaoa5AA|zDFHj+)}n-mE{_0N>gFuQ-||=wxwOTS;r5|E%<0Yr+5I-wHx!nZw@|9
zGr1G#soGN7Wy{>($abJcWsdkXeL8NW{9|1S>^Y*p!uc3HGFEQ4MlkbG3y(gIt+|G3
zKaTx)E&M-_-XR|*)b!nA?wT4kL726p<na~w7$u2@Of*35T5URrq_>#<*;AupkRqb~
z9X-~*^r3^W-~7Gs>IS^D?O8J5iIN5_hrfwIN{rox=2+QZ1qpsIqQ~LLMNBAhc_I(z
z9YH->jW?8s&ct3fs%5vF?Wy%&G=q01GoB@B^+9erHmLb+YQsOFXqn`9-C56Rzi-YB
zH|V#?5M@eeyET;^>vDD9!?QmTMulc0SpJmVc>0_6;h*U)+wuGBiNyRkVN0FW>Ek_(
zaCQyI$&$~7^swZe@|YCCM;fI)!WIj_nEcWwH2E`SHRPh-jsdiw&kmzH!E<_pa;8WA
zM={Z|1pGUk=hR7s?D*i>CT57m1d*-BzTDK8xHXxWv;MF@KAis%ud=$JkGAc(r6obs
zWQwgbNm4Dy?+<_)04)q5Hs+cXip2S{qNNVBU+5vKz+ZS0PL!|dVW3+EI^F!FX`zHw
zHIb+U<T-}v<8MGtD*<v~5Z}2d9)#=<H)!B1Vt-#1`UAq;faXiw2=8H<fq_6AJWg}e
z&X1VPEva_G`F9BB>_%lY?R+jx0(!Sa47;1NY*ccb)vu~n%KlP4N>hfR88}cej^iQ<
zq#~$2)NQg{dwc%skLriyAx|I5S057YI?yLkkoZc7J~-9ZLhst8mMJVE*t6Jxna}4G
zl9R6Zk|O*Fsb>?0q2(GH@ar*Q!1cXNVn3B?%GYL2Z(}{m&`9|v>CC^7@e$>D&Y^;I
zt9NS$P;CdcIq>#$@uuznK&5Ib`cHLl)6cdBGIJ>NC%*~6C98eb!yc^4+(_pRT|Tg`
z8up|dlw#P+FnrYam#go*U%J;)LRO7Y^z?DyFm45tUq<vQccDlCkPr8&_E~eW5o#=f
zO+lC~eOKW5hl~xAq0a^3Q;*cLgZKuoipVl7hrv)G?hgqm3ik%(^?=sK@s5EN*O2O;
zLckPWr{+uT3pM9Sxy~GJk@0eV{nf0W>)5z|t1Rv_cukF}aWuZ0C_VN4#I|fsiDZ8K
zrMK@Bo!i_+SnK<Zy|0|fR7yzV{F(t*Lq0B9Un-%Hz=mM=X-q2xKt=2<oeOX3spC$k
zUpM|1SsMnh17-z<CxzgX(|=>{qaWyF?+}D<C3!WU#f8;xoDN&v4wE4XdD4CL2VUAz
zF91J*`{+^I>Z<+eLRzauS%@pb{fsxKk83qi{{sO-Q@H{1c@)18!@cyA8Bdj2vW~Z*
zo%!H^Vd>?Cs4pOOVqEU|AL#ozISa(EN^f}c3Ft<|7IR+|Fd@K%On&zo^S4AWNf@WO
z9(*teWBQ5_&i!2=Tic{%toG;AJq^e%a>Lxl<oo-umDz_%t_>S?fu2ESstpEqLP1w(
zTU<=Sqm4-!E2-9F;@2`0LqFcDL(Z+7hT2(n&dv3;9ql))9YRCSx}APhADmNNoeyE|
zd<#5%!)w+{Gc0T631MIE^d^RuJ%sNRk&VZ72|=uN#7)${$jh*2`AeTWS%#RhikGi#
zz7ic1Mi$!#!xVZRL8<hre4#TGn0`s~jjJ+O{f?}y#f;zU>#<lXOT>8z15>+H2sSV7
z>*=(S@u!{V;$6I|A7j+Td8d7bV1&ZMmbic<dX!t-JWKh7SFO3ro}QK=b5RInZCviv
z7gu=_9(bbPp=kXLw@-fZ<is!Xwpl8(G2~X-oZxeY__K2I{dp}`VD5#QK_2fo?8%<|
zyG~7RK@~Vumx5b~z5mkw=2iTLOaTKnPgpvDo7ByRcrJf0Ua_wWD;=H~c&Jom=JeqN
z_j7t~&zQmG?QQMpLw76j;Copqw$zj}iX49kv`Vr!6<U*bGGNiIaf<5k|H@hB>=o)H
z6A8QOym9+No?=Om>zin^4-)A`x!Kli28qJBn=w}3bgp>x0tR__i6c$XYx`qzZK4&}
zxj*=}9$xQD80K0J$tQ2I3%$9k(UQsxl=r@6eT5O|mTS?MIm^N`#SVxDljtMu%}s_g
zv~nOB`O-JlciG+YwlB6m3xKVC8;dY}@`V>=@v(-(CCEwzzNY)B<Ca?^BacSYO#8qs
z+-HQ0eA~=)z<pV;=dQSrjMPMzRP$`EWc?5H!$<A&p+sHe+jI;}Qzs@47eml6>&=n3
zf4H@XQg?dDGBNy9i7LH^)jrcio;z+ap|Svoy&pUe4#UF>*+a5IZfbmGy3T;o&dKN9
zDBH;oziWUg?P8bRStAC^!UrwyK6<A$tycQ<l94`XR&v{&G+vB}<z&MfMm8rRUz3ja
zsuZ7^UzP7XcmhakEyiuk=c}J%2TvWvv@UG30_UEaFPM3b%|X;eXCjSx5U5{mbI?kP
zP2bD@+*cHLNlC<~ykyJ(k>TlV+I4MBG#pC%<N9!%7;YldPIx+`BBk-G>k{^Jxrwwm
z;(@RA+V5N26pv}B$&NhI{CD2LT$|rF_JlU&mA>lIPJPz1==?Z&_r8R2#@lr@+w1x9
zsU*VJKrN*7=~+c7+o1r(k{|bGt#1pIEGUhJIY{;V)#T(3Sj>6uNWZaK?f1!WxDr`R
zoq%k#T*KtJ%B2aLaAP{>Cw^wmgcsk#4iA~^gNHLP`d@}*1dW0^U}kk=&d3|bx${{Q
z`HxOI-{b}pAE}gnP@tzYGNT-gdTs+}&~e^uZypq8zioR9%Fz~(Q9zy~oXclt+-9#?
z^2gdo!Al>5uQi()`w##<Sq3&=&|fypD{rQT@%1#tb=tIp*Y86VO7G(7i@);Ad8dy9
zCpenadCZbvb~AWUisnJ)9GZehw0t|9p=R!{V3yDr>AH;)#X)1`=g;%Rqi1Bh6#Rx|
zKEwzr?hoPj3EvIvThOuqtQvhnN@6E7JSwXBV<NmWh8Y8|AN8qdzsCoDtSu%r?05MF
zo2y?xmAZ{g)5olsBDyy+k9z6HkhLBr;EY4&wQ4lEh-%@@>{R|@pU2-PEaR&AaK|Q%
znPqZI<7&8@ZWl76_cG1cibyLm{(K&jx!_BAP#boZ5OIcXjC~Zi+YUrpbMY+zkSFJe
zK6*7emf7#%e}qra-eF@f!p!hjp$C`r1G*y3xA<}RXH6Av>VwN2KN^bq{jIQ~wtvzb
z_dsbARu(g*zXqP*dtJjMFIz_iGYivCst0%uK1ka-dZB&||JZ$`U4#h!c4h4wj+#lw
z#l%cL^YFjj<tDh84Lx1xBI&G4Je|L(_E^b1GeCLigNJ<A%Cg}QhDZ(@X{k-p6i4gA
zFU&q{&d?v8L0N-Sm`F4<-(|&Z?doecDYA2l0Zqsb*y_9zIPEDWpT}&+&zEwbkW@vR
ziE0q<nwTT@nXcUz75_hwp~lslKlt~RWPxFr%U~Dic@g6tZLAfL5FS8Uup7|4*y?zO
zPvO$9JAnobdo_3pR{NzdbDsrSchRxWgM-P{GNLZ#ff<~~<1*gMSSC1ZYR2DJ)uY@W
zcN4j9o%z~dnDDpW@`1U>((R@NY=Y^JBgSe>GU>#Z`X9>(50Wd>7o8Ik$(9PruYEMa
zoqARkm|o_CtyQ~LZyR_!+vhQ@K`F26CtU!L3cq);+vdbeeqyWXRkY98IU0}4atIC=
zK^E=mhvR-l96bK`v~vLgB&F^0gFj-d)>V53Sx7KiEkaup$7j;mg0kF24=o}N2%#Rk
zJ94+~Aud^KwjKl-mvSZ~tI;XyhjXANrhx$leNox!(RQQ>plgu<4BJ@A&(s`55`(+5
z?)VJn)HBJktJshG8K8}Cz@)o@jTgxrw<AOgFe))9nQA2ejj5P>VJHR4&`PB|)($uM
z&N?kU$nbiVjf3-C5P%k3T$v2Ul;Cb=$TiR9)}i5`vb4LiMH2XI1unmFAKhgQmBpO(
z{OT_q`*#78wbc#6Vw?m4Uz%$^l^KN%z#r@51EZh$z#@;C_PgZ{NUU_XlN|mB!YU>h
zDn-_5d6$Ar+3gwS{yu42AB%3-?A=T64Y>)Wz`Xj|F;f_ePc*r|8{sQmGIh+%VYMfe
z92U9w^+MbnIapRkppaytzvzS<AAqidO-E%a2m}7OjFMKnmDetlHD}VQU$BEylp~yG
zHEA&(WUM(;C+Jq#0rKo0Q;4{0TbkFk_4M2}J97Wvp5c*95cPlV#BjS485Xc?F%=mh
z#ydGEH}|<-FiA|&q&4-B_qr!wCo|@-rx#IZ22M1ojGBECWtc%@N3clABCFIVnV@!R
zNpo{$xw}Gx-d?@vXYI5+tD~PTO<;B%L7(+qFc(FC5POxH7CL0~CBHGmR(8+U_;+Pi
zo*evyn7ig!W<QoJZOFdSw`np(!G~^N>vnsi($v&3>F`>Z{Xw}``-8;qL{eem5@umc
z;nLV(Z2#{4%(%M{K1Mjzpmx$U_&hkYN~J))_}eFMYQki^RtwNj(f0q834@|2OIcCS
z3s&^z?WG4ug-akh^MrL;?n3(NGCl{_R$C5iBCJ&3<<g-l2YH^?PZzhKpp_jtLz>?O
zDkI{w^ao-m&^l}DHoTaU;)11=r62rjXr&3AJ68TmuhhK#_sqxx?=}I#;y?yBAXR%e
z02U^TVu@8r-BAyL#w*k581I>e0CJ87({nV*MYdxzp1l+|mfp~E=Z5evT=Jl_B`mk6
zgybx5+MfKX!EmsoIeNCs!Y}Q%spi*GNr*IA3~g3d>V(BH%xyXie8Q@6t^nK;qkr&G
zpQfHoSR5|?3dhl<T#TJRQH9%quFEK}2an`-m+`Mq9^yRoxh6nTMUOZxzPs?*ce2Zj
z5p*_B3t_WyDRMO*uNqUlIWBc&;;c6Jp*5gKDJVkd!vBYNWJN#Vf)$o!e+z_y+12cx
z-}VCe{G8*?8;_{xPps9%nN-t;hzk=A^b!xxI-&XR<QAnEmi+J2lEu#UEdj=j#h7%`
zUwZLbryA)WseUN`Xy}d&Lq~!?Hj#X_Q9hU6XvZ4PW7qo+VvI{?kl)cwt0E^+K=I|E
zS@b2v%sXUd`&Y!RrV+D9^YE+(DeED0B0wg+JU+t+(>nT_!ux=WgOxq>zr-Vyov9w%
zEp#<tC!0tvvrSO`DX_I;D3_6=xgaU25gy@hqw0f}RH;p=EQ<}zFzy7z+=^QZW<D28
z;J@tNv*!i#HkyTmCE`yOQvT9EcZrW3VsYl5?R0moNYOcW=8KuhllK-v(}%I7Rcf=z
zXxj?6W+t2Feu0+pi`<2tT$Ba0;bm+e<D(EBE~vn>l`$ZPyUclFCVn6h8EjiZ3A|lB
z{y^4do+lnEtA*{}6Wzg;)3oKaKh~bLyF7+jf~`YK9<v?adSF**50l+nKlWjdaTr61
z2Er;-<J88?K=$TgDqyDly8;hAXfMBkfJ~NTIQ}|Jh7If4MLU}ekUjK0Xq7m3#gUi0
z759@GvrB*>VqQJ~y5Ci7OO`s}chFWK%dWk=)YQCWfam_i9y=fArA;AALqAvo^a?dS
z3vbHps?cAb<zZGfc&^$@(MNy(Dkm-3Vyo%!_i8#r4k1fLvKiJ@v^ZorHuQ+@jNuM&
z+NGD|)M$Ik<wkW1I^?b0*ZqPYwjmANr5{n^><uqk$8H@^%i92AeW=NQ-Y7NFR*&X`
z6O-y*ME3_i$@^fGaPs3>0~h)AW%gwJ^M19tLSVUt?ZlPGZb%2oA}=I0-fO2>(|8a|
zm;MfFOT2Lfp*}N)FqL2}Q;-YWwS)i@T0;}(l+kJUThwnQqz6HsBu>!)F<mleT1!Tz
zmk_!AMQH9koWxEb><t!Pl^}@*hPDH4AwQcm@o$U?T!^I{9msbI;dxIKUy9!Ne#`*A
z7wb$U7ugf~#OX)T8e;4qNStUU6Df2il39p*dkZ}2opBoedr<MWjZb-##G2*8IwF=0
z-8FtP9VkwHWXNF_@};aPkUfU?;jj1*QqhLN52(%1rXS`3*am~yXw>iU%s*2znhs5D
z2il0H^fyiRC=10`Wj@&!+-F>(S8W#+OHuZs433VICx*FH+^Z>bds&F04wYkbNKF+h
z*X)n15CHzNW1)5HvH@y1x?Roke9Eeq{et12iEM6J;wjAd^uYXopqk3Rfv_ZG`53}^
zC%+a~^xpYL3RSiA-f`D%>6H_5zrW_xgNp!bx^R8>Bl84tP$^lVteXAmGh$8`)aKa@
zJ%#B`A7y;Icxyv&EiwxEX@QsfsPuapxQy68-0Y910<URC9+|oodv)z@aTn+s)^2wq
z)&()dS<@%~pqc>)DQ&^O%RBT$MR$@-E_znEZa8~^`wwNqLEk~-bLlm|mE$ZMvU6Q%
z`)J3nndE)O?DTMY+Wd`v{*jEgKSn4Q#3T>&+0j|$jVcQLhsv$KOLGtV#!zI$7HqYx
z_r-?~)ZKbM+vxOGbWD}*9Ax>6#6^t6{1~vOZWGm*5HiO9<N~0D-zUGMGv``j?b_FV
zY2qriTN`r!?tBAKYw{D{`a4GFjv)jX`=zP(Rh08_{?i8!cmF<+-SLiGddWMXAdj_2
zYLrq;qNM;I?qLWG_I>Nj3$X;ar76j$(!maP+uX|@`?|L8DUKCCe*Bg1G1rkfSdx|$
zjWFe%M9K3Bu<b3PVy88-SNq8VQR-r8k68-}<<KHER`c%(=Y2xsJ|@ca8wquyL>1T#
zmxkVYojK3+61_H_#Bhf0$dQQ_v7<}Q7rilxZpr3Fwf{x+x#xwLs)0P3Hwqw8(mj<m
zn=bZ_|L5qu!`b})Hy(S_p*E>ftEjyRT59jwElLr4Z$cHV6}yCr8nO4*)+SWdh&^l6
z-kXr`@A>@x#dW!^oIK|_=YHS!>(+8+9-nnJad+b_(8{^nH<3Ox=2CO@MFA#>$fH6T
zzbZu%1JF3^z3t%+9DdoRfA`fj^1DIOP1s3<C8SQ=7&})9o|XI<?&~nHM<p~1jXAUe
zrkqV_^11P0=NP)nAdvBRQ9pH|?k#yLmRDx5wBzq2L;dJj7!>#>bZ+m0W2QGwfzv_+
zLJ<Ee-*DJP5y$=i>|1StV0kQ3H#ZGHLDFuP>}t3*SY5B9!Fyw#@y=9y3QT*c(_c_`
z*(!!#T3CR)>)m%1Wlvz(35fr|v%A*&5cgN?0H1I)&GR`<{sqh$+ayb%;p<Ge;sR&;
zta;b!B5m;?^deT7bpC~VD;Z$xf2Lkkwzk*9mhC9BYE6h4Wb5?Q@NFfV;}1Pm1hrwN
z)9M5OI!v9WQzx>fN#<@YaI%VYby!8XF?+$<EIyP6WbuiXs?FK<?pHwD^RGa&VTWG<
zZfc@VV*a^&(|HjNGs$A(3cQrUM@6g}wM3h>H(5d&R=oYZn{{ojURyOeQ!1E--|~iy
zRoLe0)|9r;g<(p<@n<8nC7DVA53_zX05rWu^uX9?LdboL5e@rUZgLGQ<2>2>GA)pu
zwKYV#pt%2I$uxP-ZRKszhu`;Ok~_;V+if3VB9;#p;;A$D73oPQEjL4K<)he)%L1@k
zwnr7~m~&OI+``Slwl3~>ha2I#!%_r&*htwuZ(k;Ctp9A|1IXI3Q_O|@a&Z0GFo|j#
z<mBqrEh(lZu7B$GX!;EGYrV-rk7LVO7R#h3d{K*h(_aWzfn8tcQ7HeiTAi53-4x+Q
z45tlXU1c<TLU@Y-5GLx+WG+8vx`1yBKda2Ly9}TSFZ({+zK~`<C+<8CvKbe66y_Yo
zc57&&hKX5fHB@|%Eg&4=+`oC(rZ8Br4l9DN)fuX$7skJPeY+*WqzI7%=B{}CRP>PJ
zBQrQQ5S2Ej*rN$3fch7#RJtP7R^~t~A^!Fc-o6^B{bPYNVUR)Anc(0xx#gCUCtBe{
zl0vxX$J<g%;=2NsL3RdYk=PEC#s_8FWmg@Cv2^Mg)A+=Ra{nR@Pp7bN&<K(XRJ_8O
zEF9Z_senRyTz=eCn$x#AO3}TMO<&EvD=4mBs0Uw;(2_>^#(}5>B3M5$7NaX?YX%xN
zw{@7lHovah-QuOrtLP9w$y!&+QtIx1_xWp@tE*)I>sG{*s#%*L*KL+`mb>`}HPp{$
zuwbD+LohN2L@O?s?VnvcS-6^CY}uKA)1MJw|K8@}T5r1>p<^+u>qzDhby-@2X1;qB
zhH;4%p1^QUG%_gm^61uW6#7o&*r^uYFj;F`pT!E1{G`Jxt#GP_pDBvs28)=YEB^<Q
z^F~9Sa(sQGJ3?+dm!?_fDiu#-t4#|1J~=yct)vKGr{{e0r8suzfbH>fS|mlHtWmCN
zi7sWqj?+hDsBd$>M#LVU+%5zA1_7d-U!06Ylt<wV_I@d2uvPb066318Y0aWg*JY_(
zf^LdEdB@vEZ!F)xR_7(;-e{ZFp1N~)ux+CdZ+7rTzaRtvP5LiHw>?G%jmpR(ufwD+
zP^_FK8>gpYr1@gI-{O~YLLJ{oSl&*z-fBC-?7BCz$7$*fV0LEJG$Ee2D_T4?=w8_Q
zEXQnVv9{7>6-Ai1%eJ|r%U#Xd^zXbGsD{q&hh^ho;k3lBpk2PI;Ekm1rj`v4Z<8=|
z0p9OCU{fk(npf3tX-kql$Y144kojG@C{(aVM?NbEWW_|b%E%0_BGsObO*XT=0)nWd
zjhOVX|AD3u?=TZbs;`3TFTOrLi+8=z6KwDbh?F{P%8ZTK1KpiV6)oE)mMw+9PW4C8
zw7QR==Aap!UzZ&K?)m{C#nW$6^AQV}zJ5fRZklQ0RVl2&C0|MtNJX?e;-;F`1(I#g
z7zzPKnYpCqixkLr<waDOg)Oq^nN#9$dR^!CFyD@-6rQWh4fzZ1Xnmf)wlfoTq6d$a
zg?EjJ_Eu^Ha=@3)%2O-<3|q<Xqd6+MM9O~*cnMq*>}znhq9tYw_f6gg@AtmsASW^4
zt2kLM#d~Bi?NLamEkDa>;o4#DjtmjShD+}o2u$TEU2~uqeYyU;euat6S9;&EPRO|b
zUy*$|OG1k{I6H(P1aP%SF57Ov(6pUz5TzuZ;E24QkiaEq@&5acX>xs{HQPG@#WS=y
zNUr>(WA_MZ{_D18cwi%KPKV?+G$oYpdCkB$<s$3PlZnotZGZUC+x=T8ywH+&<l@6B
zaKDU;3>rSr7MgjP_s}1XMu6Ty4cwU<iRW)7qsBQ*kESa}%8gY2Ogta)Q9K(lcc1k+
zKspVwRT>b%_sR{zf|Fhcc>{GgQi4po+|^5EtE|tYBngrBeUxn);LH>mJA@$chx?qo
z!y`C(ZHYONS}>Hk&Ewo`S(V@*6>g}kU6827t&pcjScP~XMD#xp%ed%P&%a+c@v*8C
zVjc<>t}_=!xM>W~+y=*PWa2Mu#dWC&;P#)-`{Zd9Laz3?FNTx4G$CkL_NgRf$_T;T
z9I>2}@%_^a*sWi>ucp16S?y(?(p_C&%nie4H7%xm;gKwV?U}ivg-lv-n5IbRr;>To
zWRrij;P5iw8iR<Wq+oBs>bd!vSl*@4bcYL|%NBF?8aP;mO$4eN$wq$1G5nEc6wgT6
zxnhX?ABeTM-l_N4xj9$I$%RCX&L#d&B&&z0{-W5D)!=i8#$b(1QkMCK<l~%svL?zI
zJMR{sv!$6j$OGkgUy^H#RD=Bc*xr^&Y^*qk1;a!ZGXyC-BP?$bPmla~CHZCQ^@QcV
zYDKjD3;pBh_#Co%E<z*Llefgibjfl?r46I`C9{b9ll6o`HXjyTlG~vXlCkjha`Q-R
zVzg7g{R&ySieeJ4A-UtBO!R_ASk89FxP1ATNW+!GUbo<H8GW&6NcE)4wDmhdVt-^Y
zRAX6w)a9mGELzn>hX6n1bQF;=uQ_<iwLLHHu-C?EyOCoDYt*nEH7U1aJHvbJCT7|R
zO1<O3hQ*e6QopL=!>F&U%l$<v@(%gu<NI0E0wzklmpcf)axjOVt|G66dF|_Kmv;Sq
z6V;-^g0O?%Imbz9tmbHLx7_s`(yba=^e5LgfjFNX<4oUwQuD>qHv*1=6*1`;7PxOI
ztZ{RItcZ2#uK|H5)@!9e)@L@f-P~yhVD|8<p)VsU^-G<&aW>J}7yIx3&}$JK=c&Tx
z8>9cZSkmb0oZc$-tbcrt9Wn<yPGilgH+V>Tb;qR)ceU(2*w{V1B6I@84(pvOyzJ$$
ztJUHipBQXVpA1zJ8`+1J`rAA8Z5|nFPkkP20VKemz>VphQ(Y)_ym)4!vdAeOw*I92
zj5g-gcbm`R@1!?Lh{IdK7euQk)97skU>N!5eY#}3pm)RDKQ&p%akrx~=KAR5CM`aA
zL&F+^yFa7Ed|1DnstZ@b=-0WW)oe1Cyx~^0{OmS^yxai_kXON1*MlRM+j#X*!EE~k
z>`a`49HK^0pb9j{;U!Px?a~g8%hjE%H&m*GHpLo~&NHC#BM_<EeqUZ(Ca1iDJb$DS
z3el)j9ww&sD~juVXHUWKILBk+dc)sfl@-??krsa=lT*lNF-i@kE+|S=_)~di{<O`M
zIh!SN2_f#QtURYG@AxPN<~--Rfbgcf)KIG8B}8TZ5A<Qwx3mRptI8IqHrJo`YS0F*
zBdTT0<@)ZQ8gCJ#$`9~mI_<ptAhv<m_O4u_w%nCG11u4QH7LUUFiOSGIqM$t;HOx0
z&5l!SJ>P#dC%(aWVrx~Ya`7{8{!@BrXYu{&0acHVbPzl8t;@aI$OXeW0WbHgDni>a
z6;;>9{*lAlYeSXjs^9YmKq585ppAlB!o25hx4V_Kv_N%&;{7={TUV)0a)~-z1k1qi
z7Xcl03u;GQ0||q#qo&C|>O=0SuU*)r#5!g?-2fwY+Q-CyJHmM{r9%}{&x>TJ5*311
zJ+~%WllEk>bUjzqrp={J9vHDAu=ob-ukU@Jb*)2u1znG)%@p=2bCJt)*_Wlemc4!q
zZ%BiAXJUmdhN*_SJ%=rA7{T!8jp!~yC0pr5(xdj6N|w&YsW0Qt4Gk)BpC5V>TTH)K
z^?gG{bCZlzY|YzklVYG-x~*jCvN>^@b2yq~xwsZqYwIhK(tNV?Q2-cClCk9mSQsmG
z@%Frp>X@9ZQ7ANQF%5R+lYS%1J*p>OI(Y3fUa(;F%Ay7A)mw8;d$?bIFl7za(j!fF
zJN(C}NymC*oSaw!oSF+<#gOw%^)xB-Y^|v5eft-Y4EpoL>9a3g*%~Jm4fnN7#e2Aa
z&%8amNPTPD-LDXxRd0sASwVoN8XKN5Wzl}W9Ck#r2oqq77G&&OksPnzNm^R_U)P#c
z3fM=|JpHqlyAduPlW93nOmbGPw=BkqkM`B4U%5xDB7H#hI(K^=@|ZJ-oY>cMv9N^f
zFLpAr)lj-W$b^PyzK{L7M%U%U`5l#dY}pqnRy?urX@m)*wD?=zH)<m6?%zs&%yJGY
zlO7IhKk8?u{D>VTOenP^#cA5<L4J5?tGXS`r!sBMRq-dMud!Sd$0$t@C?42ly3a(k
z33+NchiaBOqEW#UNY^I&_X-XKas=8~J4zXK3(L-g%Ibm642ZY3b8t6onrE$2&AkE*
zRlg`n*stw>k`+^_J=)J~v3z}_`wQXfPA1g`ul6)adhsNY8EKxds`lA6rrOEcP{L%f
zD)opK;~spUsLBYtT1hdfdu_eHt?j&c-B%Ey=Eq^|<$<A$^?pBEn(f|FD016-mvnGh
z%wGjq8Q3N)NqZT&>Afh&?@}Qr*W4OOn!Hljr;y<spGL3-C}!`I5Yvus@2Efl$(=X2
zv@~QlC7?;SKTX{SPrxO22K59|*DEE`v8f@jpD4<ibu*q-9l^0ThPUJRJYe~x|Nhk|
z7xB`3l^w)Tv8iE;un=2YB;X5gWk9+A;D+;uLc>vWqYmq~R~Vw7&9^7Ei8+|&w+}B@
z!BOmz4wc<r@;uE+q*E6FOt;;l9m=${%z%}NRTc~c3`~g#?S6&emRiN0A)s#Qk~pc1
zpsx-{I{jXtq-o-k#gL`p4+qF>#wx1E3*i$zqD_{i%3lb&;|*!eQg@DiwyjT_bmGn$
z+V_}4;v|t!YM5_cGiT4L7jPl81b6FJs=no4+t<As^UQeZ#h1hZR1|?)4KHokCJjTl
z|It&=9x7V6ks?%YF7yAI2UaC}X4Y=;aU#4YQ%_2o<~?4hH&=^gSB8UwkMsX(Z)z={
zjH#%%y%^Go+<sk;_m<$Hc3;iE^!nThOO?vs-q>?|gc9yqlF_8Q$Rt1^3OXx-3dG#j
zplea#X+2Cewo(^;&(s+<_w6F)%I{D#E6r}aguj^Mf<Sd_f*p=dax;qm16iRfl{x?D
zra+jCGk~bF;L!CbL2nZ}70}ms5i^wTDFsl6k=tNZo(GFC%KK|g(C{^WX&eA=L79>q
zsZF@Gp?`nAo_Jr?@3)snrm0N*QUIaqgT9F=;S5y^or>F1;S(&;Rj?AnV^0C}5J3Ru
z?(rD6c2tyL58i#_z5Gb{{ifiDr29{v`Nlospy5>_<tv;`kI+n^^`q^k2~P2x3l|XY
zMN6rm7+FpmoxYJPoTE3@n}|6Xvybv9$}mD(NOQa|kU+j~7VlZqp9;mf{<JvFqlj9r
z&TPF9W3+R>b|RLY6mpHx{T{0tY%TO832CE65v{tt`B%^Kxq`>qa;3hAVhjc0#~ZzV
z5gh?t3@x6=ugK_3oKLQgEzUynktu(K_k{tG>?JzcQ7P}`hNBYr=R4iJLMScGkI9Du
z{R$RtqSIpIZu9VZ(5up2ExT^h+9XpP?T3I7MfH*oZzCfgyhE`6<XAsJSM8YG7s{1`
zl}q=rh1mU785#dZ_a&0E!77U8(Hsj|LBBMLu-#EE(5ReC_kL`79Tv>-ER^mm$y|?H
zI(ki`N07v$Fi;a2lp(@E)umLTb^PdG|IX*%{G_K%qfdUP>@ipx3CQ<QKI6G{YDt{I
zH(vv=Q_;Pin~=ZSAoUH6#rFi;YVXtH1OLLEs&Suc_a8`v(uhA~AX{lY%cBrn(J|km
z#Eu^tesHT%Xw>Rs#Nm7Dkh#Ni=RNm46+dT<N=gdA&28o6!^YRaLAIYR5^AhNc}v3C
z*f+w#*xWFG;MP)VWO4jE=2)ChO_5`7H+3oJX*S~t2QB5tY@7aRh`H8$;!Da`C_a0j
z^I&ET9Q8Qkl6yTt=}_@LaZF=<C>8sBxJq-FsIjO|r%eIaoY9T!-&DlC81~wW5QERA
zK2Zt{->m>Is_jqS7{DRrITew(EKALyC~N5LLGzLr$zmOP9l=)6s3x%De(hqh<w*FF
zXo#i*{5G@r)4?aeUe8d>Y&y;Uwe?WjG%t=SgZsF!pC1az8u}m$yqx=igOe$VRNv$8
zpN;m7Au1&ZHMI>gnia(dgEjE0tNE)5RoO5kbirFc>z>0Mwd#oXQf}4!3I9MJh&>Tg
z>UT>ep3#e3liJp$5)GYK>QmDm+;-u`Gkscuql0KD3+RBNK3|r8J%DX~C@nJd3UVQt
z%gmx?$1!_H?5b%b%)3Su*S%>5p-4*ex;$RpoB{i2d@c8#GEH~Ffue!|JTGrv^N*X6
zAyql}r=P-yOmgFuwkLlPa^+RO!u4EMb+pHT<o&uLiKI5N67)RP8;N*n)t_ot;D}Wu
z&R(A<818cK&#`H6qY%D@g1QS?8pl_&n*DEoc<viC{`>?Wzj`m9z_}JxLvnfWsgffi
z6@+)7*)}9upKq8NhR9ef@a4BDddcSTM@6b!(ZCHz#z@m%3cIZFopE7#$MB?715`jN
zI$Z?P7kVje#8u$>V_(_HIS&2NE8JnczDnFMp-k5IEbpbi32*dkMW#Bgqzp#6i4k7g
z=|?)MoaZRvmpQ)0WZl@wFx?;zhK-0XwwcZHWv`P&PK^lO<)*NO@_zbxlIw|pf{;#8
z;Ml-*mg8;39!7C~Q>uPm15T-hW#K)dH%)c^-Dtu(hy1dK280$w>ZG$*h{eXE=<fk}
zT}9fFi~V!ckt-vgW=$m28A+rC)J#;ErK|($w$$CEq{_>w+NzeH4xnvJkZO}YPt}SV
z%|a)9P@x4z`;KvYjxG1l4=6><2FSJz`xUG*et!Ux9;d$1+Yj*eW38@oSZIKISX}tI
z3E}@h`FNU5_S+!hf|Evvw|4PC7?liE50y;Bc^(CxU{Ij5&a=?mTD-&8u=>O7!?#3i
zS*4YGZ}1*25+C-lr*_w;U2iCcCh&hx4{XujN7$Op-%pmg^EY<ho(tO_hNa@p9}E02
zXdRqTz7y7VOf6r=X&Xglqyha$fET}Wo2osLMnv{b8)Qj5sI(k<-6-~zS8+K2#z>{~
zZ|m>>KxOvso*HA@fg`ivBlCApMWD73!jJ@2x3hd{Y8ZK<lKT(R{Y)Bd6vBj%ur6to
z5a_MZB6&hAbzq$CD<E$2%u(&qT&*a}0;g1G7ZeeT+&4jXp}cXUD1557Gxr{hAm5il
z8cm~T-)US(<t^;E6ws+LkEdH0r{c_1bLYJkW5;*sX}V|pc4IkOCO^Ohhe4MtlNh?P
zp2PoI;q-|s!mJtqWRa_II@O=XIik%8!!KArrOSK4$HoeSCCH9|$SvOGcbRv0n#o%;
z`F|DJr<p5~t5<aB%)1z!`?M}-*X$}x#j&ZlJF(eW;OdJ_f^2^)1o;dD@3$!{`0okr
zB1_7HNeDjd<_v{VM~{ST;^vr~Ew-NZypaX_aV6brN^bS=H71$uxH+3S3kcGzkiKF1
z>iR>0-fvURcd*>}0wLdZxA64Fmn$Ou@2J>y%q{H4N8iU&>CG`NHgCFLxp;{Ll+(3^
zR<@fnT%=!?RQdWQ{P_4HcTb+z(vR)XolLD&VWZRu{($e3kZcN-$i*rzejP8#cwTb?
zcMIv*AwiCjq-WA+xzm5^wenHWt|HBQhRyJxrV`hzw-k?TcXe7OpL2YypM_s29x7W?
zJ#B1rLvVMVvAhlxcV#k~bG1u_^wdk0?N?b20g3uzhz4;{7|mcIOYo%Wi~euLXk58w
zD*R=hlP9>fK>e!Z5rq?CN{z{!Tpw1g(IJqdsZG8HbcVjS2f*~e%+xOz$StzA8Phl=
zSoOwt?ARC{Dx+6bA#$TdARR&Rx-e~V;q$zvCSs~WjnHASt}4Jx0S5X>O3bItl0t4`
z$upug6QKPP0HiI+VwdrMAPYADGy@3FfWD1rL8Cm?<^p%Qsw4L%EZ>jRI}_UOCsnU#
zJF{xRvyD{#o5_mWxIi{|bjNl?or|OA1@qM}gOqEbXG19>H)YAYeUeyNcY(6MmtAGU
z&_Xxa>dyo<K^}20cBY@B0Y*GG?oZQOD<c<Jhx&!Kl<;DyTIk0{GF%tMkTh-om!7VG
zsF9Xo0xn_41$fi1WfQR}ZGr-=&1KIb&9A(#4)!>^4(ltyE_ECnT3>M2h3pYOAdG)S
zL%n0=?uZpaQi9h~jX8eA(|pl@p_Ur{{rtjh|7jtpgjP6->s!J8FEcQ96}~SZ=SEhX
zp)fdAnf+7q3Q&s*4aj_>xh3vDzojm;y9YsZzpOoJJ!te`zIe<joQ%|X(mb(ll>;!i
zD&L2)@RtfvhaJlEv{1IROb8^0WZNYVZn7BJUz+)L)y6xt??mpI|4MX!GO)(Ek<5Rt
z&%RiKzSg&9aToXUyf8&KK2Ehr1-*I@jL^3Uu<~i^Rr`6=_zZfyw`ra#kMmRw7h`os
zT@mpx&C^`nM1*}PZTd>;{q?O5jq=$@4Rni4COeF3yh3Fv(ijZWOU%9qRqAJctuj)i
z7px65wWtE~S%P8i)B?aG4v+CZFSeoogY>|&pHjaO7n(VMDAc{GVgm*ly$Q@n;h)z<
z^g;ONQOonLvZP-t`4eC49KiOA#O9%_U_<*GdDXe-kA}}|*nu@SK$mW-&A>I1JNA<b
z3FfGX6a@nIfqx~|J@<f@dHvZHA{F~~239_{eiLYIkl<#Bt5%V|q$L{Y*$RgFrGWEO
z)$GPeZrcWMNcQq)6;1)a9Dm7g>l9UVXbY1}U?#|S1B=g?>?#lI(iZ0dee7{7P19WV
zJ_38Us33kbw&DDHQ^GThIGkwWjp9jzA>4pSt?ldPkz;3=QK#Gs__@dPsWg>UZn+`y
zJ0hybEOYH;LJu_vPKv2C&0yCtPwv!Ep)tMByV}BoW0g?OPdkE3`R<4`V|g;9eOpa|
zdoB9jIaiV0qz){g6$N|0_~^Qkj(fINZzzAE4t$k0K;oVo_n6aX%E(hD^2Uh2ZEQCH
zK(+AUtz3J_EgAtIM8N+*3386ce{bjNv5`*=)J&cVIcZ;>-xJ;LqjL81{A%dFrl$Z$
z@%%<4L(F6*T#L3Izdt0q6nRa){y&hdy^BI^B<@aluQKL&)!F|*ZkbJQSrq*(X|P)e
zs_JN?_(5cW_%l)}R9cz8GbP}%nXs}SqxN^AUYg(WkQ1RE&FUO^p;33`8}_=H6M3O6
z#D0H^Y-mvpH=iKu9s}7dK)N7umK<ZlEXaTvpI1Z)wCCgaKZT_?&nV06k9KTbyue}5
zHT_XrxRcqh*#lL8I9)liF#dF;4Nq}mVa+XeIg#g|qQM(0O;z`+46WeMIm0UGCJ0Kc
zi~Z05X%M`r`UIn+U2b-IdE2IFRZeb9k*?Z-e>Z&pboU=7v6-V}w%|U}DRXHDjoh0-
zPnLE#PR-ml=|7(=`A3n=YH-TomK63Kx@kDkF9CIekp}|e!KFY<Bah7J&c**g>3ClB
z?Nh*cG0DevTZ`WO*oA^8>douP*i$j-OH`(>L124SSe#0dWySmH5d|&hJzlcu8NjzA
z4vtcrLc~$~8UeNtm74Ee%N1eDUz7R;+JCGGcrx7bnN~LXCAqia$@_cj$!F7aRI&IM
zn({05?6_@C$a7nZ7uIK`0bx2JTil|9CTh9W#VOND*;_x;r!G$-4~-)M8k!(atJlF7
z<As8}V+YHJyWsFbT#vHqoy{O%eMqx#<k&b}1oY>mzP!YChr2VUk78RH+*Ku;;Ir`p
z+~D|^!yRsht+%K@;X-m>6mG`@=N=?CO(089gw7~OhK);zNglMF#qjsu@)3tI-I^LJ
ze=D$jIn8YzkmJ9e7+FV(<Uls&mt9_po27ZpG55pPz@3xdO3aD6p~VDu$!flK1nU^G
z8*)%d-4?jVZ2>^+#|<-D;N(oPX{D;wQsD0x(KFi9QYXUOHtSnQiYL$aDX8b1H)na5
z=Y*mb#9D>7n-Ny~tVTI7hZ5S*W>cV=w7N+J^knC0^!hlMZC8i>64FzEaBBatiIX1<
zqdoE+Ef6k|KaN%MTy~i-wS$7fj6$nT1x~h|uWAbK?^fPghZ$jr+tdNjpB|94NOzdZ
zmadHg+D<Lr+K;5VHH<+kYoyy=vn@g^i=Ea_VOLC`G^$`o&@6ObyyJS`{ra{0UhwT{
z3FVzO`<P(nX{kggA`Z_re{x{s<Q{CH#C*iSCSxMmb6>A2dKcGh$UQGs44~I<vTomI
zQe&xxG%C4J%xuvW>aHL~c;JVi(_xW$mHPPd?50%Ur&<W%cbpkQi`2Se(e{mBYu|+}
z%&=8zOZcs)0F?M$WA4V$*!6|7JGQdBR3(0jH*V-Vu_BLqvu3$%@x@zbNSpD`J#T+`
z&;Kq?J6b)@0*38L>MQA6O1C>zPY7HKp50FCCT2c=^=0Lsl*q$#Z$pX>s?zRW(cM^u
z#g$I~KxR0$HUF<FxTieHYuT79ZRyHW>ZJZZXHI3gqeh`XuHxQ<sA(}@h(P2fu62|>
zp=3**s1{v^>1Y(Qma4bEDUxm+x{uKWHtDZY0Utz!+0uDOT+{XlsEbkS;F^bt$fwUQ
zhD-2lG0fWyM&*?Q^v?<guTXqS70Z%~<1}k(?_W>d%k>#08Bg2&6J|92`M;NaWSP^?
zhN#;<62mE)+aCQeROTn*Mqi-0rynxAuX)#4vYGIVs|ah~cGVZJ2o92442-$Syf;pf
zEKv=hxSr99U;OxQGJxSUioreLxHaC9FVzT$0JKE4C|$rH40b+#NRu%@(`(oqkRJU~
zue!GMM}o(ZJ3Bavw`nSPNB<Nz{ERZv{qulaH;Id(aZm5>YsvcpTKtVxtCL^A2jh+D
z*HW(5VFa|%qFBjZ?!#qO-l3vh7llw&p-@l#_H5~Y=S?@%kV@4y598m6-ohaFJeAtQ
zo#no=67a!P!p}%F=>w~b)QQ~l=nDx)NMQL;;@?4YI@iLN5ij?7<p+nK!~nG_Uj5oC
znaGQlvXT5wwAYR{(6;hA>$y*8p{VVQ@%x@FuLs=*<qPZM`1<*C>`%`f6y{3{w8t+)
z=He6JH&CP6l~LGKEuc9w!Ln95MVmQuzkfzOnXMhIO%2%GeJZ(!0~-zxJ=}R)c30gK
zyP(tpztEQ3F(+pe@CKH@4Br^uV{QFg7Z~|7{t)Zvw%BfqtaOaTy%B;fpnx9F?L-9&
z3E;XfmA_hZ42hl$hymdF&qE|c<HBGIVq;aN)tdj^M0jD%0-vtMrhvax!LxxhhzSog
zjNIZ!O*Ytc&m^B|&|7eZwAlhYw&i(I7Fh2O0U>$-LK9Mo8dyFe588zSVWqPS$kBZ*
z+(H{6O$|<}IKlY(#1<H|4?m{aZ<ZH}Sv+Vs+z-ZF`lRrx7L?blj<8{&s8fq~o{o7A
z<KZ;>u4?h9EMz6mgt$Lg5ZQno&pHRrGED%+H87W*Ul@OFy67<{*1ie$Z(QbuchyC+
z%B{Dec4%9a{(+;A^YG}J{0UDDp8I{sqNxh6)jfjC)ms(z`suGRhfVR`vHll+jgxNw
zeM)tBl;*oRSp_7lB@%OE*y&heUgGp}p`j(bkxC(`KN{XBS-dn%_X2z&@ZVPb`IG)x
zsfp&qC+2g*h(Q$0W{IsiFBoH?+N%8hFpg;d1%bINp=r}l$ll^k;hYa)NOKC_H2-AL
zd#LM$FU{bk+(wos%1lGewozABsf6**S7~#lW_{ZOaBRT%H!#e=b~n`o{IZEK!si}a
z?^#K7-1}U2`Bt&fdw_Fs4rtnOlR15L;g^j>9RCNosJ+Xw#sgsHD?z7fVvGD<)BMYZ
zS}%!vG!}<@{v(<u6m3O?LDj*Bh}sKz1_x0%b|<QFjFv?$tQGa7`obY*8fOl4KWYew
zaatC*UH<Vj{!#gGHx}RVI4A0934YTsM>+5NVuE}iVcs!(R@y#RR0>3)&}?akP0$zc
zdZ4X&lu$X8)1&6$6)?fd6pefLs%kE6VMfreJ1pFA>R>3|9QX}>O*_Ug*+uu3I2Efi
z7`7h=&W~-l9AzV_TJBE88i;S(Chzg$-J4{$?MtN$s+3ypm$u-#d54ne>L-dQz#8~r
zn>4S+@d?Txu2MC(y#2U;U;foS4l>BzEtSS{V;-@$cMz;Mft7h9EcPWMiChNdrD>0S
zOHu(>ue3O1zEN;$TT2pA%%}!Pzo+Lf;Ae84+7EVs`;}m)!^A}QriuG^mVnJh!TtA{
zcB%#2iUa=xt-8VfC3O}2n#>FtpvNG9ce}IOfbT7|qOJUR6HoEc@1RT)PY_mr-RY^v
zNFTs2;m4h9Tg(6@m!15SYk-HwCZl3M=Vi$3r=-&ewF@t?k9XgGMhE0~6Pm?YE_%q?
z7qwgP(tav_7STm=Xuznw=jJalpWKw`A_&^p!ac%^{0CI)4FM^9wY_nr)Uf_cU}v!(
zZst0Q01{eLBa&ISQ0*T|O?M@0r5lk%2;d0w$6M=Vr0$y@NhkThyzSA5;lJP`zA78c
z)v}l8dC`67Lb4FLHIEEd&p%st>7a0^REI%>9l3Et`q3CY>sCNlsDlQw)cg1If{tyA
zh(_ih$2<D21(9%B?z^2&!$rK<cwW?|7U#aQBffp48v6HNc%`gcV&tJ6+uuoB@8WQ>
zDEP{&`8^qmkUMD9=h?G7GSm9Qcno2ihx=E58tuk=lP-^%;=Eww{uhlXb-Dz=Ryg{^
z)3c~rQy-l_>VDQo6!i@_eN~7Dz&1y?a>OIQgKb}^y-zMR14+y_L-xjD(D`RDbo|Gl
zk7b({naGSz+g-&eH{oPQl17jj4wKMkTEmuE$n@dh+66}W`bDK>WM4k+G3JZO4{n@1
zdbI)18LMFoIbH?r_krD7JmEF>_w}e$uT$?-Y3e3iVdb7pk2qNUF!vpoETgYoi9Ina
zqwdd-qZ&bXe8qF;hR6kpSNY?21*SI0XNk)Kbd0w9GS#<7mImTWs65=d!`!#!N=aEy
zU=v1t5=RZZ)8VD8NnP&1igTxjkhwR2zm-L!Uvsin@CEq%eC2oj^~23WHGh)W+x6?e
zY_kP>H>E%*5siAL2vs(18uZv*eo}7b_~!}OK3AQ^dvI6lCB&{{0OG8aJp6p7nzjBS
zIRd>@LY-W4<e#pvQ6QszB_+vObLIqUm<yffSqyEUd7%$rO@_ZGD8ZYY+P0bnRd+wM
zw>W*lk~PzuA;YxspE7wTHm}KtowH-!p+`#WF0V^tdgebvoOiX^SmA`?qg~s>AjqB&
z_zU(0!KgR~^d?Z+`44QlxH@J(yyp%4Ph_6yI^7Qv);b=1Q7EdU>j(I9l6&^-TZ$mw
zNXSHw3TC>pJIsfbLqqqc7v!+a+GMtfN4f<sbXcA^_6L6p8f$cc@p18%SUWFd3X6sP
zLwN#)6VJKgg^UgsJP}F~X)Rj{jdm7}pMHS*qheli{&l-RJ!wW3ZF0!!7J(fxiU0_C
zydt%LcaAp4k2d-ZXOi*4=CmvRv%9*U#-_i#kcNr?t9o$f>srrZKnT-YzC_bb<#q*G
zB>%TYfQ$T@Wk^$Ds0#N*1&@M-qIx;Zxmmw2E#|-E$k+vD;lJ150=ccp+LIBs309k5
zUz^O>&SCo%#3njPcsmV9mo|B^1EAl*05{u4688x5LI*e7-qnZr8-(vP*#4aaY>l6`
zWM%uWUIT=3KU_{G174<%*f%(8TdA{o<Kc}$23SGARGw~`<ZT^XdRvW(;%SN+EC9cj
zpz<N~gm&QzUUtj&>u>b?z4H(6Fo^bwJezrv@uc630`6<cADZ9x=Ll5)LS}mJT8Ic9
zDd$L5>Sv5^`agV3QawB#7oldloP1Jue)#Ibb+_g>nxKTZqOxd&^X=m^vBSOV%+oLk
z(>p#^uB{VHxac^-$0Fm8;1SJ}>I6ym=cNuaXC;YW>De0}geAo5d+;R?d-yZ|2;M}%
zE*Lnne;@DaN*MRZHsS+aj?D7%6!bs2r>V3^{|Bo128#5((i01&wP`zZz&yznI7?@g
zw7Us88)N%KbJL9mV&*<^L|TlehiwI}&orq{EpZJSGJNkN?QRU^7Fl4#Dj=TPv9Um8
zak*ZNW2BVpvbj|Q^jWyT;0+~UDi?!iEWpe3@YBX#*VizmNQ~i)q<@ENSa;N^T=NeB
zEuxUd$6&7^f^Efz%wJi&n#us$5e8OF^WA;Fd&1UCW!qX;UaIH~^z$!M%FXyuf@!@*
zg7sQh9}jL^E2J$X3lPk{VC@gDTx1aOJBVy>M&GLm4F3D}%y?8TjEz@iaiyQ1^byT`
zV+M;k4_jstR;NX2-i2gEO(nuNj9Ml022XQiXWZ7cF8=1CY~_3d>`k)8YbL%4fkjR?
z@i5xJ8e4yR##2id2|FF&Q8C;gP_F0gCxAN+D^a$Y9Zj&SMuD`Se8DT)PZGj}SfWV#
z5^_my<Tw2Of1vkH?g=-MpkO==F$)yS5}nJ5x0-{R;5*Rmmi+095i;!}U`W#iSLWpj
ztd@L!sqM(Am%kPQ`@E4fz*R#}ZMCl=NooC>(Pv2Qv_n7SY-rHpajyya@!75!CLq)y
zX?TN<1nDG5bia5ur+NMokc6BgG%|u-x=~ISp8x&%V0)^hk1{W+1XeG$3YZV$kU{?V
zH$5w>YnR#cthqVmEC2KY&~MM*%7*eWOz;owN9y*cM*%(?U?oD!dv-)@2F~ZTahTB;
zLYf}Bb%y!bFW^#+xHN@=g0fs<`IK;uRP(WXZ(Kr()PRO*<2=2kN^$E*9&LGrBXG_c
zqC8#XwRlsz2AC(C=pyi@*XBQB<`pvY0zP<&w7HS|WS?50IGL4ZZJ~|qrBpxJ%RHS5
zr`>J-sfvuEotkPi;dmcTalpfLx6LV-E4+)KZZ3`A$Mh>Sbb3sjH?6pWE(?K-7R_RK
z*puwL@=Enzvk|(QKZCU1O$Y|38sL`)M5`?5jOBjaZa4m+D=I}YS!NmVx%Rhp@H@oR
z4K{}{iN@T7q33;N3uOCc@I!>-c%%Je@gcnBjZ#>BV-v@n{HsQ)qFt(KJ^Zp&4jJ*Q
z-Jn;a8;CZl9*MW-?XAWC1KGT_-JF;S-ay<4Q33G{Zid6QxV-xzB8j@$0lm3@C(u1X
z!Jzj)HYeDeIxghfPHy7BSC53YGl)DcV+bZoTA08y=2FURTS+qi$~cOye5FJQ&YcRy
zh8aS!K$^F6N2T`Y#y8dTY!P@a+-U&aPrw9uQ6l2_^`1LP%OmiYl}Y!uip4Z0-F+Gw
zWz~TRfab`^X@W3vZI{Ys%X{5&UatK+xf|_yxNAgjJ{G|)kk#>5&Zy%kX{J|6lY|Y+
z!&sB2B`M}4&&wnzl?Vxm{bfbVaj(>=hXvnhkA7M**poc!Fqik!2dut?%OiFZ>Agln
ztk+rf!5+0}eC%Y3Y@TMJHNnV}a<S&*a)~}S;7THrIq55DFl6t+BNJW6@Ui}ePON`Y
zoFm?B1<rU`M9;L)+E?~L-m&Jh++E-w3Dx%NV!Ud|%@6N|+%(Kxllm{b&Ml~1r7wI)
zh+sU9G;`K@{JCg<`|@3oGc>66kNYFVGuvSyi`|13tRh>n*yOlxeorWl7&;^P{6esB
z5Z(-6N02l0MCze>n^M=>I&DPTZ{5|otJG1=F`Im^<{2J%f1PlXO=2Yz#SW{?1E;8j
z2fcQH)FZFDV%)L9V4%9&FMpyd7TM$Hc^`W*QtIUQXaH6xmOKUcyIv^OjNh|C0(I$g
zjxzSD*PkvQ7?l?~hO_)GX4MqOZ$&&Fn@;5tp7)hvr4vmm>Gfwp{Fn-3dvUp@(4RT@
zjlD}aUf;UaV*iFe0RQPo%Qs(bA)1s$Q>=hFJrid@k1DY1<zH%%928eC=687!PP%ph
z3a_5}xAXLb8vY}Nbm57!N$`#m+t4uklz>Q=fSm$R$!%GB*UXW^QD<{Ti<~n#0Mhj|
zo5tCuG46CJ)nmZMdNoj=ntKN1LV+4Gv|}?jhW39TS!0ixW>An3a&G!Deuj(gcy8O|
zwaZfgTD>knSF?kkcn77*C|jtHDyJ&hDa^5OAx_;7`hFi<bh8@XiocD>f*hZw9*!Eo
zY@H~>f}^?RvtzT6X4@yO2cCNA6GNxMpfQ`pMC}I$k|ZPOHFLkFcB26QLDs>F>iQjS
z@HWXQDnaH#*?-Y{4@$*6L{;m$UTT9uB){YbEwo-#g^JCmVJ{zF_BnPNJR*Ig2J%K^
z(>gtK?I)8uG>rQPe&)(>Ua{V)>{sqr9Oo_-nIhjOBz`|KysPar@w~{X=0VwkjIVq-
zp36bLcIUmgoxsw{gYFK22&9G<>AYTtA#lAQmoKdj4CL}Rg}b5}#&7;ChLpY^qS4n*
z!F8qLyS8q5_PM<K*z{48)Imk{Fm);JgAMLpXOK@B|ES%n-|l!mRKO@YeVyTKm`ivB
z=G$?p`5<xf;et~l+9jC<mv$&Iz(yH!B=#?3r0QuY!|+@(WS4_r0W-h<4Ys!Wyc;g^
z8`vDBb*D1>$8KJ6$uk(%Py=DuwL9Lh7TO}WPlG=Qw)KcVMt)lQx@nOdNr?Q!mGqF`
zgwtVvSIv0s=Mj25&+k+G(`=SY{OtAP^yZK|9{hLX)L%NoXs4loNPs@Y(UO{(+^OF>
z8BxYU#=OtVYGOOtE>pnX8s9+IRh%xD<-u=i<HT>bg?5u%!=<*MGb*b09EkrNFLNac
zG~eE;O*+^nhW*Y<^wc%Z&bR0n5>*K=8FVBi`X{~l^O-=VVLEK8GD}eJ!DIdNLXk!5
z`wx)s9PzUS5+ReCBef+1b&PktkvmjYiGfYwTO>6_0gMw(Ml{}P?};n|!`2-LCJZU{
zsxa%d3g>neJJ+w`9hMNrN5E&|*azaCS1v1Q3aWm(v^HFCJB|{vBskS%xOJ-M|DI^c
z1TvCE4?3!!lN1TgMw84^6RT<qF;3tP^jgnLC#%TtsyyT!9qpi-`;V20xa=7e^w=gP
zdIqt&|Fln<L1CDjSdiQHJe=1{);{42N4@}eTHIw7b!f>f{SrN=0Eoy9uA+1hQ1V-n
z@Wl3JJpI$%_I$46Gba;bdxEKm`+KdH;m0_m%_fAh|1kYj+6%{5K<lT^4irV9)P0=^
z%=nS-l3+vKVYDBX6c-js+0NDzi5SWM>x9Hm)iRu9({_6PmzIP_v8_hy(NlSe@X<AY
zl6b^G<CMhDqu~5*b1M9v3x_};x{;Ed95Sx0M%3Y~Wi&*|-*LPTSA>2-(JhAyGNft<
zFlMGDmtD@T>Zmkts@XgCKX^p46wZexNm*I<Q<xNWk{DPPU7LvwY)wv!{>=A46S8P|
z$HPe3d{O6@bh)iZ-wX;#Nj~GM`Y<#}e^OkUR87&xMI<cV1}p(1V7~}BKIvZ8dc7=g
zjLgVxv%20%!y~if1)iJAbJR6}-OUuYW+W!d@;uL@gbn$kr^4A!?evrF!hV+K`k--^
z(>r{AzN~I(Ku@lZT!hchz&;@kGcLovHYVegqZ4)|q@l(L>8^MDCGGIV(A3K3?MTIs
z!`qzupI8iN8Y2hc3KORS$lJ4&)O|YZct(XZOOnzyv}j(TZ_CJSh@e7Rmwdg{Oa;{Z
zU{d#{SvGJZ9KV?$(nI2omr`pX8?b3&wWxn6&WuPG((CgKHZ8^ql6o|Q`+U~6wS)gV
zmVgDr(n<pojRY#P6u$DE>7hoxpEBX48TYY<iw^XR=Zf|I(QKX;w;AgDrONn|$|Uem
zv={tEtXG3vvBmOKU#_O*daSi%$mwZol<=XJKoI()(Pf_Xn6l|AivhzZ_+0vy*VM`K
zl#ORTET|2B2~-mr0b^H4G_NvC>N>nXb99N)y#@S5!-~rdwSKy-NIC!vh)QYib*}x=
z?N9#p&hz5SEdc2DUG$FFSNtrgp7;qu4obUJ(r0!Y9Bg?fpTHiy%pge=TCdXG8!i1^
z?p?A?DuW2X_5C<M3%_<-$1=&qNo<+Ii|84pKEba8l+<36STv%GRMzL<E3nGPAO4%1
zaB)nGl6vxZf9|r<fAO?~d6NS}`%lxl#gyvtiK?(`G6n&1&w8Khz&UDHOLg)+<LnW8
zGGsG+Z7$hTxU-pHDdK*`g^JGW`RRYf*B3AGYnoZS_*9^h))v)&`QCpn)Xg%YDI#Du
z6Iiej7-{G0_2jXBDOD(J9TINz{t&NwpyiSl?`dx(J)4db(f1Y(UWc5sJb_ucUr2Ka
zEzi&4BkjDVwm)|B1DXjiOF7)_9K=MA=u`HmHo*y!P*%4i`4arl>CFaBbP#F#!Ir!e
ze(ghGT}en-x8=(1K|c;74%Ntxebk1#c?wTZ0vSIzW{lWfIHXPoacL+`A&n{>`7MyM
zJ-@#dSf^pCDM}HrTS#As{hhj7<;D>xW=zA+EP?YEGy<GX6O7{Y8y1f$yT@d&&|Q3L
z^ERWHEfS&cRSd5Km(b#wq8&T$PTO*xG|!Q#L&$Uf?07Zx92cD)4E~y@3?A+LtkU9s
zbzyr>+Y*1);FL5HLjU9u+e|Up^Lc`I5qpmKB2}-3T>E%VPfzCJfsQBv;E-N+WAMpc
zM>mJ)F$2>scqdt#J@E+M5<cGeb7RR~F;u;{&s}E!xkxPlQ=@7;o=*x-Y?L$Z4P6bt
z95%HDD_@mOQ&7Y+3MXFYkqkKsrzfk}za<keYRPe^DP?=62b+fXm5Z7sGOU^;oJI`D
zmnb^uiq*9`ybF~stLkJ6xWSm~{5XBRWS}Zles9yw=|LcBkV__s=+#Cvn1>%WOB?-J
zgc=$aS!7jrgsTkcd0+c_H=`<B>&nwp=CHkmIVeph4X-zHL&&r%8GcmF)wCzaTeV!5
zSz)GkCg?oj11H~Z)9aPkvS78ybuMeLWZ}_A+bF^%#uXmCwQOs=+vt^lt@^AL)Bf-(
z=m|>E&SoMduquCvI)<xJV3kx#y2zvUYjFTgj~|F(517;Oi&~6Ao9KQKN+b(HW{Xux
zH;R>MinM>#alXk5DJj@$81#-!dzU;gujVHOrnj(6zZ;5@{^R^9IQXbn{I`=ljnnz_
z2d0((;+`F~?7p?|Xmb&5L9BnF`XI^1qx=LbzWgGrVX86h$Q}LHG4RaC3SkNFFEBfs
zUFRj2i}^{9w=rmecX)Hgd|h0HWExEN79=Tus8Q3|A=Ly)kkCB)EJ<p|fdb{P@u#}q
z<5KsK-;s8}WckUa6ju=$$uvl93}=p0=|_egYJ2fUu*azBx3VX}t)ZT%l576;?Ym#P
z`<ew&+B}f}Oz)sj+5$xL6QAbHwJSQe_hzs3$3GG>RP9Zr@^l;8`Q=8^NTmxQXW&`i
zWA4*Ju)i+)pN`pqMNtylM(JnqZ8E~{4kg`tyCjE;{qjwtMAZ_v$g4}0%Uwm8NFP#~
z@v=-`BB04!q4QmV#HH(H_3@b#KZl}Vo=ii)jh^w{;N70>wi&7`?MtZoe+u^J%1X_!
zOGEab1Q>$Xl~r~AZzA+F?Lcl55Y|bhiiWD{VD_7zlD|eDX0&kL9Ex?0-B<kqWLw^1
zw^2)-sU3Q^1gB;jx->6)GTg(oDFRo{-7~n>?jp4)_z^;G?v`s!ry41a$<po(ZZ|1T
z?4^!Bf%dB#E+}zrart|nd{vo`w0P2OqeJ(~TW+GnI$XxT;NIk5uYE0@lka1HJ_VFu
zAH!*jwr3|$Dukk1TOvZ2&Oow7r}4>7lS9<_I!Vn8A3=qamWLQhKQZ9Y#3lE{(chA*
zpH-EYGG)#bWgDl@aB1Fp;mJh*CbC1L@`F|MMz#;eLh!=lg$I%5d(&9wYyFx5iOt$R
zgVt7cmh?9rl>)t$5+npm*>p(R-xUEG$;mGrpvpx*QYb@-TxXwg@CxrKq|2ya8&y0z
zOA4cRhwdi6fhWeS1s2*XK2<tXx)s+xLh`q>r{dmx)7QP{1YiSZg2`3uTlgt<L_#GE
z^&i@KCWIi*{dUibYo=>)P0PoHOt8yF?*BZXs2&~02ToFhgF~2F4yI)@o71JvJggr7
zIZ(}II(<~kEKeKXxaD4$&TPKLUgt&zxO6ftsfq@zvdz%#JGN$}gQ4!8ho`Xf?e%~_
z#RY8mo`u+QV?f}mA-Yw_j2O|t+o_r44QJ|5g&<pV=pyrf#1{N=e5~s0g{J)mpYH!s
z9oxUcEV#Ju=J*LA4r5=Ks~lji{YhPUo1Ulhr{%omvo+UZKs|Q5%JYjh+jR^l<cP_b
z^;f6kGeFKi>1Y-^=1M7%FjX6xe^T`3o%;&LOno1i_B39DxiVo)(l3?WDtf38FPguR
z3hQFctMDC%k?(0&N_Kw3*18lg3+da29w_`Olh>wWU~U~`7&}^y;%RHAIDwYuT;eAU
zRm&VDSO10dCq4f}Eh+anl&6N;;-{4y^cdbBA<=@y$*=0)mMRQavV~1Eh0-Bh&i!n@
zD!m#tsKeL4YtmKwABa5GXgaF}@mOA18%uO8w-X-9+oSd!BI@MYT$(>%XJtEW7QMSQ
z8bm&-X_3wlT#$;Jd}7f@2N|chKZR_c63r6yOT5k>AZc*@m((nG@w8li&y6wBR|HS~
zQJHL9sD#;%{x%NGMhVlhDtg4nlmO!^OA5Pi5>4hRyakFZmThWPug^)`gcHsg;$Be1
zHxqnw3WC`r8uPDV#P-<pF=~v9fk>~3e0eI^zot+f=&pCc^IsWt5|A0LLi!sw1q<$5
z+dM(hKcf@Y_pkK?0kn>MZxDNNXw&qSSpVZ3JDyTHEXBuh3viSy9>av#I}d@y+HKb7
z^Jg27r}2Q~59(8UUaiC>&$(Ktxu^zUJ3c#F^~d3v?nuNOY^MMttG3teB+O!;I}Vp0
zNwrO8)n4$RTb(?<n0w+-w71@>c`q&oJFmq8A&-jVzMn{8gwMrJeEa3!SzS@F8P{!Y
zv?hebDN;%@H6LyNQm9l1YOjH7OpfNBd9JIt19R9?Ic`#HdoEGIRgdN^uPK4dJlliC
zS5vv4E1PKq+OTWlWaCvd51isjO2m+}kHJVI?%d(X+pYVuFUlVdpJ~YB8?wzCK~5hg
z=+;d<fEwHV-O*vVJmr(Xh)w?S<#NAbeOxPRz6_(QYQNQM5+#yttZCGn*(&{Tsq*vE
zNOf6>0H**nVoy*ui}80nbN+~vDluRd!Xi!m6;AxiI_!@wMB9uR_q5HLwJDQo=H)&H
zMJh8EFmDU<EC!iIOboufG#5)w3m!>3zAPiFItwVcKkWDl%kFePFkg^-Cgbc{RFTT}
z=mgw8{2!l(;mb>s#}5yjIwvZq$)WqeyhX3Akoz$-;i_b#^ua(zD5Ezn_P4w;CSe2q
zox(YFyQ%n%e$t9h|1IyDab^U7K-eI>$RjWJxA{(i5{8`rDYE$P<5HEW#DQ(Jb~3r$
z$9w^sCmaGqfhInhQZdk22zo=COAA0S=wN*Z0R&D_&c!g5cST)7#_<Pv=!;!Dc#2?J
zr~7;(i#0S;tjD_?{{3Cv1TgCd15XBvL8fp2`ohbYF-JTkbn4f-8IMBYc=_%)kAe~J
zmBHN?GY;Y-yUSuhWZ9!lJ#<SUUcD6rO-g8}#Wb_)m33p-QCF=)vExR9+OZigUQ8_m
z_mwb&!j0WK0s!(Da`xskb}pP2J?=#s`WimgX7oy<!IB=RowzF_)bJVV7P$e4UU2La
z1210}oH!ZgY*gL##qp^yU`>@G@IB_ZyD`CkQS=i1V5cXs>sV>Lf@FD;OyOigmGvRZ
zB6Y`7Nv0#Y_a?YI^MOPbil7;*mU~5`--IlvUh1&jksRyj`RgD8{^sQ7L)Url`@>~~
z%0rbR$1eYaWK8v2K6j3uzuxz65y(e(Uvn&M>(csVJd^d+SD6)i?(hM*4zG~znMN*)
zNms01DD{p}YEP_CP4gO{#`nc1nnLSDgZBPFdyM0~5OT=N&f*gCW&|b7Yb+C334^MF
zBG=A3+dbn<@j$ize{lMECk|&q5DF@?!Zf(a8Xe*s-CO*0-|wC$Rlt~2yJ2!d+!mv*
z2U#j+{^|376rFcGmG2+M4?>ZdY)(dGmK=K=lD%i5kbUe~_8}SBGBdLGUdJ90hh!bc
zUPak^bH?}g{QmL}FTBok-_LztpX+*G=k@W9gq8<MqhY1ufrP|FChd}^=NVXK<t@KZ
z+>#o@GD_4h3X{GbDj2V+H^FR*tl{fI&pYh%_nK9bMr+`<32qHy;ndGIH>u@QLmS<E
ztvwJ^mAC6j6V>nIN!j>2VYdSWod&D{LeF*r+AVL$2rhtDtoYj<E_O9KRMrXC)znk8
zv0?FULa%&PVt)CWayL|DmL*RYhy=(yYWIIP8xyxWB<GjExLb48!p;8ODQt>0G20{w
zbCmC>-~KDB3fNP82t2FB9^~u-y2iAP*S)ps<nzj!{P`5jnDzvgvM5Dm$_RTE#f#6<
zBOb8h*sF$aX^ZPWVY%>s4&5m+!2g;wJbH6-^!Vv~kj#G|xhr_zHsOHTP9Mc>h5V+O
zdrDE*nUf1ZQ+b7X8aX8I0spO%N=2DKnAjg1#-)^hA@K`v;TcrRgSo(t?{B3_UU!L;
ztUcDGy5v{enk2e!ei{HOO&fxlvdOb}%})LtO}Iz;(9Ahk>hI|5VawhTGw33Xl3S%v
z-p{2gg`L-5uD{Ll%p+>yWD3fVMgCg5CaZwcG{b`qMr-=X+tU_N=k&&2aat&r5SV1J
z24&f1UYQ9K8&+%&9Kr?@n|-RPcLqL9gOB5kdk=z({-XXr<${sad71x3i6)v=MOX1O
zxF@D)B(+-8R^`6zgb(w31*f-=G*yrQraBY32mz<Xc1#BVE)pXW5z~y|reM|uxL~)H
z#xr%NB1P(nC2yol+jK~Pru7_QtRnJO7DAw1*JAP)MtV{vbl4@*q-}hAW-^A1mMJC-
z<LO!X1C9W_!n}&k25-ke$v)(*KL`~92KRM<y7uF$t07oKTVxM@c1DfmBY40Y!)Pn0
zw4<%5OWPDQ!FW4U*SLGAh;f@rIA@X5O7ImbTMXqir=m_i(`C9GdxY}6!p!|Fn=~BD
zy&|~KP_*-m6EEqMJ5#vt`rx%}t}Zy9NC}NN2v$qp%kr3Rm@{(0AYk&}?^<RX0sm63
z!jJzzpF;K#=7x}gKS=l9D#;0qQDpxlE23PTZFD+hpybP)3{3Pv4*=ctgT1cz1*l&=
z70^FSEnv8b)TNXA{JG-n39txzHMl0n;i!8P82hyTf!;r?({qvN3APX?lBgmZDtIU0
z4m|Y{q}6=Jy2X<Ntyk20m=Nf#v2XjiVEeA31Yo)joBdY^t5=|9tIj<Z$b~fn)0uza
z4d-`eYg%>%t-f3Drbe2#C2H`07>r<#ef@!S0Lx1x7oqN1!+%I?+RN7P8s$v?__H&Q
z$%FwPNLHR*Wn2B$zVP|B6o^X#dk0n9V9UBb_?c}`z<IKuZ~Er4in>ZZrklfijfFz;
zEleq`#fu91zCar5H{6IsJi#wn6KGNe8Pd4A`}~uAE%8qmKZAH7zJsFKPt(P`|ED`*
z+m2LHa_-2$UYA4TAGHT!U<5ZlBhaH5!|Kt0|9nuSs0yBzijh!+71$7!>creh8}h3Y
zzFgR6#vDKDGwrR3D+)|Z(Uv@as9z^G<et8uurH#)b8-(;|KxIzo^b9mp|tGZv=_f|
z4|<4dKJ-#7=V<-ez+c^;*-by(<ZW&U6qu`mt8(mDKt&U?c`}@e*JKmsZ+-iOF$xE|
z^a0<Yf>DVkgrQGwvL?Y&aUq0BBh?S^9na*R@qb2LL=Ekw%P;M`dO1TLH0Qt;3i<f2
z30G;lZVNWkXRiWE%gm~9;pG?3-*2)gBi>U<yuMt9MU1{+Q*4*$O)eI1-S0i61|CiK
zeVMR{#Zc%Gt6|2=v`FS{2ecTyf`-c>Vcag!SuuT3&|>t}_fiTX7?0*4-Y80`6)(`T
zvzkepZQ9Y3uPT?7YQ7jgUbqtM1ep><gM=gHh$VMSoYqcG?_F|+itoD}aK;Vgt8c51
zRFt$MGKwjtYXzWMkx!@&mpr~RaW;?7J>o~3+CQA>&U6`R55(~o2`6;hOR;Zukax?=
ze8R1Z=;Ia#vZghfGe(yO*i^h@Y&a;25<axc1)`d74URvMz4r+l*YsAwJ%JN}0&ERw
z7#4ks^<D~-)-DnsW>V3#{xi7O+&A#|9q?{0(gvRn)(1P%JaD2X??YHqc|5^SHsM)R
zuui%N*mreP(S#zpJog5!XhyJh^W8*@#)9HtsfadyF3Nq>h2O5X#Q-{`euOH;qhcKg
z6M{qYKM25`o@v#Tv9|$CucWg}PU5%BU+;sam-3X0rPBt0alV4A4{$aq*N`@k+vt{b
z%6Pp#PnBO5oBc)fk{<G}qeq3<MMsV=jK%3y)ZwBh{!g()M*${1KUn!SgLF3d`Vtgq
zaFf-}YHpntT5&mM)q0y8cQHurTV3BjL<wD}GQaSmI!q2JjN1cw(1r@Q&zi><JK&PF
z{4S#0B+9P{Yk>Xf?>8-*r5Z7-S=N7>@hZ|}f_KPWs~fSkYgaSS{Q#staH<J2+JjZ5
zvA92klR=v<Ui5WeLn9t>FuRrRrGGucUp$#QT4;2D7dYj>vZ8`jk4xE}UssUoOC5zP
z(6Dh{eZU5NgDw{1f3z=3=rAS*BsYJ}#NMV5t!)-do0`1YZ3J7R@0&Jjmjo?Du4Yb{
z&C$<NP-{`jq?rB(T0s1K^$Y!(3$cp|JKvrc(Ci|{6n%k#ns&r#Rhu0?l#A(T6Rsru
zk*Q2rSV#QrX^4><7w2`)$SUzIhn*o?N*8<D^6lL(wLc~?AKUp20S!mcCZFT?xC;1D
zC6LjuFbe|uZ{?qm|M^`e0m7L>-YDthl~zD^UL&o%wJ<yhAvl1?5n~V}D}Ok>7p{Jp
zORP%PJDy2Je=7`~s{kJvFhbl46%*}C$q(*&aPn@K=D0W8G0`vlKSBUnDtdI37(nm(
zP?bx5&=J3gqQfFedXgt^@!7-l&qbj7WFSM|!h{AeW;5}CjSfCa0x(a*&6-L7P5))b
z@FCwsz&F{qwwpn4*v_XQM1pSVPyI?$z$(Z7<^JW8+Tu2AZI0)8DcgG!Ob3j8$&v6~
z<?H`I#3|Ilv>6x^Y7fX2aIcJZmXIX&*$>!?A!+c_9krW7g>vK3BR7x*(ix!IR)7++
z13k*Jagr{DZp;`3Ccp}T7@`fP(+JQ+?`-IGvO(r<vpjmc<plXF+UK(IZ>Q<p=JF1Q
z!tq2}<WN^Mqo)lbN4Q11S11cyWnCFD2aG)u`;%*0`k&j!QI$d7kh6!B<z!l04(0Hm
zCmfM~j3T}@14nx>5%ll`z(38lt$1I22ja+QzAtp{hb+)J7;}9tBAtGCKR~C_$gLCE
zqpjj2b6V4Z5z5)hQncRD){4t6W}h!mUWXnXaS7no%!*}Y0yegK9|hWH;+b-iJI*|=
z#$oqYG^^f$k9d@!N0-GCvo>M;4(M(NvuzW^NuC5PJ7&Tx`FxK=lIF<;M>*T4jwGEv
z@)981UqFA{N$Y;{tyfIhvv9uWwHt!g`>L`6C5Rlk%=h0a5n&c`a0<CB1fCxy04>9E
zAsqbSqVjVA%t<~lNf$F;MnR>zl9B7Ve||UTdoj_O(;e{bj<(~uEC3F=9aX(_i;QiZ
zFi@X(ngwf~G_oC`m!U?3$}q&L*r2WL3#JqWieCd<XcUB*8dJwuOzrs7PvqN*sFo7;
zKM-X(<~Ifftl6l!q;~M(G^1m2&?@kOhi;}WZx4&aJ=rIv8{$JZKPq#1jiun2X|{8}
zAlgG@K7}abX|9E2ofb86{53)<ltcAvcKGtnz2rVl>vWfewF{b_;eHxc?u5041Ku@;
z*G)|K+?E4`=n3lTmXedLbZ1};mO6x{;xeJlf2x+)iL;vmT#GPHbh5AOu}`RHPssne
zOy_<3S_XH2`<I}URu||@xum2W>-M87vS^3C@549uv6!OY>a0k{=pM-Foi`x6p%}O0
ziX|)cTeNfK?iUGcIFPyoDOEcC@N^>mqu4tOto?GpW-Gb6t35FfDlJ*9Uk?7ndAkMa
zV-9}zy`SKmu7B}o`Qxw+OmmHI9eqClz+B$Uv7fz+EA}t!Q(-W2U*}pD5-{DP1*g9N
zK$4voL)IZL**Z~oFOcrn*ZSA%DFj7YGiUg=oWvuaio)rq)^-vPm}LIwYM3<7%!AKs
z+PA&+apC%gm{BYSRX<j4trz}*)klnCrSO+{DcUBE)+wSUZu=%{TavfE#_`vajRK;4
zp0v=PDK9hm-se74?<*gQUZGf>+RIw#^*j7S^O@_7_guGi?qgN+LxvWRHha`vu3ueu
z&dX}!%gS$RzZ0Qj%6%Nw32MWzunm>zqBnA*4-U~k%$SAKzPZh9TjcnxFd5-*fbBT2
z#TY-1TEF9809<uiv^C{8jH8nkWF36z32j^pc&I060cfgekR156&EGAV%CAw%@lBhL
zkQM>xT_47i{<ATW2TZb(WgJBlwS18qiYDXe+lVox%UmknQ3c(QCk$rNfEEf|eZ4}t
zr4v3?iYH<{0NWz$NtcQShNC>Pq%@Mn)o)zVjI!N|k-#P|xVbOMxx>13#GUKGc4}hn
z0;e11{--TW>i0Uct$$7ISUunEdbNh(gS27-T<-(c(riB78Q8|__h8}7-<X<vb?p{{
z&m5WmEs(lqRpJ~8%+0$jNOEq@2g$3P4DQE663a{D?XM&;4~X_+oc7GhhcVB={b7L2
z;^<6T5=n)M?4AP=xGK7rycBcwZ5MAy?9cLL3vQ!U>G=l)EI$rLWdC?Nd$+G-X`OyQ
z_Qu$^ZO+uHkuWf#__Rxr&+sx-P9dM1g0e$(jGw9&pgmVPWT%cn=AFF~vx0ys9h8`h
z?MgXV!%E8sr-+ouycnb?UQ68se*5`DOAJ5ob!>_e5d1PQlqZqeXLt%FAPO>nC6we2
z3=cM@gIXzs)};)yKKTV`ugU$5TJx0)l3_IL*+I5J+Eu;X$d@Gbs{EB2#w?`2Xx}3X
zrJS#I^$}3E(jM7pA9Nh_ba!Qpn_!arTv0!~iOTOv`lXM)4UfY)g)f*6%_sjg(7o!I
z9kt9S(4S0M4nTXE;Yt+!ScoQluJY|A6IGNkV{uzDO=HC8x*4H;fm!vJ?`hQ2L$@%<
z?q~8bqHX!|VdVt!3k5&&{lU6lvKDL8m=8^X&fbiJfak(@0z<bX$7G!X41$Kh8FQ`>
z&L-z9k3T{qfO7poKi7V(1(>-n#I)i%ODiN>cmb-h>-z~V`cGE}gCY+j>pz{?ViQOf
zy`56x4jSBR`Sok_t?0)Rf&mYd_m!*Yw;VlAf=bKuep6PP?x#y)Dte>#1cP!HOZk3H
zjIw&ZZ(p7_Su{sJYMVVfU8<3pn2Tj=sFkDOy-cWUP771KqT2|rem1Pk1hmBuZCECK
zndT25ri+|2<D&2x>?P3Po?T1h%kv$SRIYAg%1nHtM?{iW1zgF%aik3;%;Nc5R~gk%
zX8F;|^v&HAjEqqT`@zZnb$;@ILf-qW?)OMnbd<s(D6kYrx*>p`O@?CXIX5b69oT5$
z&xKd*ALL6K#uz|vNhX8$Qj)jNkM;#ffB&Mw0<6iq4$its{<5feTAEqojkbIu41<<#
z_aiPqTx*_U_{{wY-d6#fYs9T=m$w#^eY&L*f9+jofxa>f3}^ldR4rJ~bPJOD_7Wb0
z{#@p`OR{A^YQ2UEcP}7eqB&U%`{)!vNE5-n_E@eZmyUKxnzFyp9}+S0BQO{<33PJ?
z=2;U=+67F4e8<@C;-<kE2VgvLPY!saSGELq_gI{ly+RdPaDvV;xlW>Wu#NZg_mHm5
z1SPOaO+WF}(}`Y<Y0RT!#WU*GtH3!ST<4v*hn!Zb3jC(NJ4B)Nsl5LLR~+ld%*&a@
ztP}1{D4I4obyTv|n`bcXwYK<(dyKuW95-@fHQbusO5k1LY@+P5fgp%7@RM`kWU`8V
zGIWD@x5TQl?h9gu53kZu^`@glSAICYaDDW05Mn?78)?h42D^eeOJc@HSLOJT8bDc1
zOg_>R!*?8<_IobHsK|3C#SxQHS){$-mNsePg}Oibw$v2kIO+Qe+J!ckN0Yl#Yj~YS
zfcL|){HJ}(cKj5MCLnkHj?w$xJVlQ-W=nL*`=3pe%izoahMBcf93X_O{S1iT49j0d
zd{~Y18QRd)r_UZh@IRZ=o~v-uFW4ahjpYP%8@p4;0<da#0(SJ&9~u1t3-O~GkVWuQ
z6(AmL)@%4!bbpcCMhN1%Zz*Pur-^-n9P`s{Vor6GHc0&DCYM!yFU{xW+oeC>51rsG
zj!#58#F17`h1<8x-yTx{8YiH&7rvBARy!BUN`G#75KIZ}hz^O>7w;~9@{=fe$(2j@
z&-N)H2YX?ruN;{?4V+j>O;83;OHR1PeP5l`&PjZ(D9E+N4Zcv|8_azk5xw`rK1VE@
zGk?(jkO~9oOT>6{KV2xEa8J+jHP88iuua~kc=I;oS&`kRO!oe-xOT3mqgET!+y+dB
z7*##b(}ib;>Sd2-E9V#7udT~m%`Tc6hpDut6G|%bI-MDz@t{{vtHt3{w*d5yvJnto
zr~_-vB^Dbb)u==0)>@n?b!1Dx8rFO*k@eW4@0XAwwV6!sXJE5NB#=yX`Fs%bE*3DK
zw-7@$1fTOkgw!)UGHI#2XETGKe*ZreYJd)MW+EHWnG|!s=COQ5+T8*zwM&UA6>K9e
z%?>R#n>thoXJfn5%M?z&i!p1st(K90Ykaf!T;6!*ttL(9K_>5N($tjPQ4ZzaC;2vr
z;60uY7th6p{H7Ql;BiV~yyBIrVXWPV_IxfH$ga&9OLAz>grBhV&Oyai%-ihCc&-BX
z-@kC=FTaaY+!yS5cbpAEptvu3<xP_Ad<OK$pk{2TPMlv(4mN~3M^GGt6=%a>UMxH~
z-4-5zTzHz8j*_J;i5GL|lC=LQdsX5rP>9`qNu@yiaxthlZa2P-eKYMRkNQzI-t>pI
zfOx^xCy&IMmxA?e(iw8&%8&()y^3K);DwU(;0O(l`@w)V1fie9XM&yRr~e$3OM;IK
zwbSZ}q+@X(3<!T?LRKHgh0vW{PD-_D-5Nh`ZUosMzUavYwivtVByUd+sG%0Qd2J#X
zrUxs2L+$O;URk;ZU=zQgaz2cajB4?6kE9$b%iS@%Cm~bUk2%qJ6og$Y^}8H1qL)_h
zv)<Zu@+{ifNQ$2*fV{aUKmOJem+uV(-uJ7c@K9a3zRjei`6Wb9sr(=H!oVsQw&?4f
z_{iAMk58tC_PTJ|a%GLt6jx57^D_#wE(17bOU&=dMzbf6U2I9wB?9^MFu}hm|2ny8
zu#jn?a?-0`%FtiU{G!&tV?a<0t9ixP2u))k>=X-gU42(fVXeCArCMV8VCmq-MR%I9
z<jiIpf`#`vwmsxd|Ncxj6KbaDZAGwdc+@;IEl(mpBzb^Hns~-be=o5XTEakB-d?|w
z!h#4^ES3<L1bp-hx4u;$*MZ5MFbyECTH>6PJiSC?CBGLFt8}&^N8R@2KqV3$hrlDl
zD~T60E&`A)7b1yHj?QE4jvEuTj!fFM1*F;HefzMGWoYDhE#!l6>}lDC-lr~;#rxKw
zoD8+|oWt~x$iPA!LDel2ct~DwihPxdFr_G`VSUW1-JxF-;FRX+fu3&DVT^NA*tLgm
z^|-v2mkAvSLAPNRoQn7hF1X_vrg;lJQ$!b^qnlU4Y4+>r?2W|eV$#n}U&1yK4#s^a
zXFqq-FwR0UgqB_sy8=snc}Y5x%KatXnrGb4G#DP$Z5i8Xrn?AMimc{;VH5!t*i%Gi
z$WI2my!rMM?#GcpabXhB%|hOleEEY3fS^RE{Yp?>chY~HM|_o6bJsdJ-Dbd|Y_=%S
zpU!F`ub|?`tRK+Dwe}J9RY>vXoi!|s&@2iJ*_Tf}v7=^PeJ204;{GIniZeuIx0~~)
z|M=ELrbUu1BQ6z~zJaSvJ!+bNGVzt;)}U@Q)MY#*_4k`CdRKrDz<IhqO4X&z7deoa
z)Nu7s>MYj_0grh0-G>D)*UN0B(l8&fE}Xk7Zf+Rg@L<p6C4;T)5}9o5GOL30?KI6>
z<#N{Vnw#e5^aDWZa_wE$yWE&3^b9NgdUu?xSAg4c-$t2}K3CmJ<3x!TB4aeJ`Sm&E
z4EEkbYZ$Oo-6b9z_q?R8+J*g`BhBNGt9(}mFcK|Zv4<MfFD`RE&Gx94&zbTNco3k#
zIS=BueXS8R+I+Ets<jrwOcNZ<ew9>ba9ZAw)%Q%glS&IBVmmV~X83x;trcKhBCeO9
zJ<Y7r)FS7WeO!D;Fhgz&gfV26knLI%(-Ay)F8`iuPs3$D(!+c@MT@M4yj8QNun5Ct
zn-T;kYeT$O`ogljnRgjT{hU)MVKa>G<+FpEx_baD%-`dQ<kxK3E#EgHOK^$?`QHX?
zd1w1;z-r0I$a`)&?7|{kZpPQWUlD$UZ!F3GF#5;}xSW8-Y|xlP^L-<Mr!5@f)gu4W
z<)qAJXxgAcZS2?i_of<!Qn$K6b_93dAqZvcGx!!)8unt)fDU?_c54Xgg!YHNUk_ti
zKtk=yhy;9Ek$+xcJJUD#<#z5%C>=@W+d<D0;8W<Q-4edvDKN!SRjbP1!F!2+)Fy%T
zmOiRRrYPKgLju#1aDf6iT6b}hrINnAWQB-~j0~s_UzqOx)hDkhys@m_Ps+zbp7S$l
zUsgh}zrjjcDf|1BJozN*ckOQMmW;cA@(6VDMHxerY;YO3?`GD4RZdl2Mh!^C$_qNz
z+6$SwOUm;nv3yK-bD@@$cSn6|fifDP6@ZlgD&;i)V8>2!AfTr+O$WNpRn~s3HVR+w
zlJ5V&@ewdZ{-V@TFXLaLN)0iskUeV^aGkUzT20mE`+t+TT)7RWJJ%6J`SWGzSJ!mt
zg<W^$`>fw}qb|WsdhMN_;Z8X|TQ!dWibHr}Q=Zm(PKJK_jnG-bb$M6p#LaqWzysZv
z-HNB5K={;s;zW7FctmerfN}a(c`GZLqfRsUH;KrY$l`%HyQ8%ujh)3F-XB027q28}
zgvwQBWO#)bdUOY%g3|&1a9)Zb;R%C7PS~}<!**VrU-gvB!X^&jA<2FsKU*1IGgEMk
z{)-&*B4$^Y1C}ClK_mKp^U$|sbE(BfQE&;7&|O7R+%uqfOHGLGFRrHPKpXS0?M>1E
zfZnSz)qA44l4E5+_*0qH`B(MoX1e+46CLiPTK**T16Cz2DzgO5Xj>`qgy87>d&NDd
z>`lR6d>{V<X+9!ehW{2LNHelEV+}B*_?5Z-i|AV4N{~(EyB949G~%Tgxp_s;xKOmv
zkXmKqgvSP6E;)Edi2JMCWXB_|Q&?Ehf1taN4^e)(X;kkFo(@zIyRW_Z={euxW~PHG
zKh0s6Cd;_`7wsfW^3sBA%F1PbC82A!r8K!zp=h-A1*s0d;+^6TkUO@LQgm-jgpdt)
z2|P$k<XsholA5Ti)(8vqllP3>YvL~dsehLf)!29}FVGPEdz49X+YvyDgJGW^qUoW2
zEne{B2w9Zf;qaYv!rDbY0i71W^>?sbr!bUW!roqH8C*)e!RY4fL~>EfK48>>2&2;p
zGwc?c`$54u_Can~a-T}KhNmA{P@Nq$s&+MtsOoY4WLZ&1IotDGoeLuE^&o*@f2QB^
zy66XUlf+lq5=u4lVKM23JWUI~tAR@;T1yTt#L1XFynp)m{EN$j{Hw7bl;DMC`b36|
zt&L!R@mm(-cZ1DgowVrJ5mV=wYXIWuYD=?R6x0<zvzhhd*0CMVcRxED%5UHHR#XjL
zvts*9t=o(Il|D>tgzRx>#YUaedm6W;{U&PV9?~MAH$Oasruy^0wXr!Bmu@>aB?K7T
zx!N{xP~VbSIm-RrUN(2TJ<&rH0ibEGK7w6-p0}<Up#D5m%Kq&JeDs&iHh(pzZi|!F
zl6JApT8*&p+l?#Fu!Ge?{KTv-_D3q!73`HR8o7$@<<L_8m^E;InhyLVP{&c8dP|@O
zL_yysN6k?6LZUSFLV^_&v6M-)>NXY0W4BLHMdA{{mU>&g-H>^+r)xcuY^`Wl=i<C>
zKiydkP+Ikey0P+ya?e>F(x46)K8uO-u9^X9uNQ5i$MB_M>TM6)tWBO)7AR%k%wR*J
z2FR{&W^zsex@lrp-c`l7km%kgCL=&#rP6V8YC?cSw_}o1igSw0uGE?e>^J#%@&V|J
z=Q3HNu+LvTlTjf5tuJ2VQsy|F8+NWALqd3^41Q1gE}=wQ;vh?p)IN_Z2R<Q-j;)mO
zW>4B$qdO_LOf%?E%)dLW*JO-aO}#$9XF#D((7%1^us|&5excVZoK<vEnjQcCg}CWZ
z5u19M2dkJ&T;fwzI5Nhg2b~#|WkS_yKzsuHz3F;!S7My1>-TZj49CSp#6u0qfT7`>
zHDJ06=TX1pK+WD>K|Aq-YV_?;uX2@#BAkZMxqP0oSeSx{+@#ylXuP~;?V)T^WBE!l
z5Wq<|9%K~ND*hIl)z{IM@(U~vI>?IrspdPK?N9Lfb$fA^eOrWA-+EI?y833{--H&3
zpMgYN@?u);bEB9S3&TXKEgZ_WESrkgGm`(BJU^SN<a_ar(WmxNwb)EjX;eM%a;`G^
zDqgZX6s)*eDV##@wO9qdW&mt%IgcjkelG*Q-X2)rb$~ddOY%<JG<npe>&Lu2{iKbV
z9p&1DP`94s-rqijM=wapA4p&-VWZ`aeSgi`0eRCtjE1pU>FnM@1AeNMev%7{OvaB?
zsT$X>obHUP0^JZ5lp)$8J)KVoTeFKAmK&t5?!tCFOAl^@xUmM+wH2aNDH_($i53}*
zrXC=zKa*PwdzgOsOZ{}7-u=qIg8l-;;Zp{@qio3nEq1^DoPPw(6{)>w1)m%+C%)4n
z#WgHRPMgoWvQ7%us%pzAmI`Jq;P3V_i|;v9CqMnocmFFdT5V!pj~SNt3drbw$>N+<
z+dLq}-Z2arseppr$rGIv)O4zs_oMkPicc?0+%J*|&dZl{dbl=csQze4+x8+W#AW_e
zM0{RcGZG5-Wv(k{oz~99d(G`KoR)J>TNCB#DCjD76gsmIOQz`CbIs~F5>Ct?DoUY;
zCkl$0{Xyw7mU#iyu8@K+bN<8l3(=7&!*I{JwJZ`d`e%GM7ckxOHGp9wF6fT7#oCrj
zY<tGJ^ESw$`4{O>#COM6qd1f33lmkH6NHOxwi(x3-d2}r=l6)9Dqq*cnV!0^8A>fX
z`L~ceD{rpMeQOZ{#ru|;|L#$IsAGP>v=GY$HUpbBC65b^(wuJ=x|;AjLYB&e<Hw%0
z#lwp@|Mme0yD3~nY22Mg`}6+k$TGmkYdMx<Wf)oHhrBYg)EUaWuWh{opV`@$@!}h;
zrXNYvOxZO7JZuF3^QAD%w+2dx5~KS8UYrXHc`Me-@3k9H<pCL-=oTpjzz$ofHpltm
zUC3l+95G0CZBNi|dhTpJX?ZV7#%06uho0434(oV~jK>ptvr(#V=T9!_?)s-#zUzMx
zj(`z5_x-Eo0uVOz(#aOStPYEjD0g$W1MOZikR{ja6wnGM29?eB`t#T=p0G$7lHKE~
zqaXsbVHWnW2vzjJSM%>dn|$vFEfxSE#YNW<sbKw{Ptz=F_29jynR$i)<bqjR*y5}V
z2gw(PVji1fZwqeSOX0Q)b!%wG<lXa+a@2&8e`)YHJfX6Zxo;IOmK_OHa*GOXj?NA?
z4O;4=CcVAqrp8pR*qN1(&~WB==q~yA(|$Gf&k9t0e=fGh|8F~ltl+^qUgq*cIbyjq
zDqPK803f5bvzX)OA|hCP%7gmNwo+)qtCJGi9cB0j8xG4i#?ii2n&AivvApdx&lbLo
z{@T>#tM#Ox9!~EYJ_6*6K%!>rVr{QyURf?>+r*l}RsPKB_|Zq;@hUb${h+jI$pZyi
z`O3Gg!e91v%jv4hS7^nz53bPy<<6!zkiV8!@eoVr!v%WBo}o<oc-)C3vm^UC%a|cl
z_*?koVdVjD^w$smB8gWGTFB`6<Kw4)6k^qZibZTkzvz(;sksY&^N##xWwhAY=yDnM
zjsY&k+;i+&NrC>OvrEW1`8g91F&~$AE|0<zR>B>2%Z{8>vKE!kJZ`gT@E6a7vRz+C
zL){e*8naw{4MKv|Y;eg&<FQgMi1LBfRR|l6%x*2E6bC@n3+=^a2exj`08OvvI;l^`
zD#cf~#FQ|UlfgLc&upV;*Ww+`s|&)AIyDNCX$G#43Lfa%phz?3F=i1ssH`m(;j)Wa
zNxE%-()vQAqQOG@<0y>J&}(O*XTb;Ry+;SU3qGP(N18UXX5qt=s-v4*CuQJk)j6hl
z9cewzSBT@qi#+JDs9wjlgQN*7ycx~ZOib`n1|O?=nM()oet*O7(SiD9rE?A@<aE@^
z$nz)*?hJNrH?t{eSP&;e71cV@KH^qn@sIQfaAo;KVNO4&Ugq!KN>il|gzq+=RVfe*
zhT`~&UPrS-&hmWM!xFUJbuA3~60a%waV<A(iDOYZme!tQ4!MDw1U|p-T|6vdz0K}t
z7jS&_fva0PH0?s5JjL7eowK+*?a#)8w~z)|O6V<mug1_MZlAvDg4{@@raA*T|M_Z3
zW1!u~c`+QkvI8%X-0hff6#-C0!M(=AxT)JaWx-W%lL#Af;O#N*AC6F#)TV@$4fUE4
zZ$)Q%I#XXk#%}lcZdhtKw1X3|%|yUFQCQ9XgbP0UM4|XUP)vLiW_WJ35W~~4Vxg0_
zN>`>kJ0EHX$876+aMSpG?zuoa9}GekoTH?=63<F0xLz%t>GXXYtbo^FnC!hLorwp@
zU}Q{WbJc;y2+HgV>JLtBbZghD?ynOtgV=k(!I&ztmfWs3DKS8pNGI7xb*!2?@Jvfu
zsrJL3piu%6u<z))Q~W;rz<5bFbG&Z_STO(kVV|^7;73DgdJVl)z0NPEs}p(kdAHC1
z16`}uc#iG+U(gK{%zq?bt$;>=UMz;BcDAmi>|10Z0)Q#=x9#MejuO|WS_YziW$rb6
z^{5PJFF<Z4=+TWzJrO>-e#kQc)Dn&c62khCDy*{e69r|#*)LfAy8@@IIAB4~Yr@GL
zrZ>xC$3VfOhREQ^;!_B<q`OOuG5!bRF1$v-KkOdbM_DgqXbVq(O2NF+95NV=yCf4e
z33pVVNcBFXgslgIEBkbND2Vvj%tj2o=Iix$iRIT`C#a_h`TR!Rvh%MkLQpEBB=Q)i
z!J3(li5@noS)BsJdKkIf#VwCrvz~NB^+L-+;qM(xu#P~nb5xs4m+7UL#qNvbzviTu
z<Z2GG-?-jm(sux};#r;Lvl~}MEdTDxTVX<&R!=wI`kp@YgBBLJ>}C1ZC@0*xE4nM9
zdWonua*a^D)S6B1orxkZeY&M%9uH*2|BWzw+n3fOQSY6*dt-CwKhPW$-_5&-eSwSy
zBnWTd<1tsf=)Jj$2&vKXu6xkeYIeu=Gggg?I&lzI5~R*$+f;{<Q4z2b?if8&zYB<!
zB#oZg(a1?XhUe)M7D@4kqvuYR`#|nCXavNbXjV9F2n{$<=4(QK-qO=o;I=DGt7)P*
zT)R3gW>zUxd&(mhp4H<5v>msIy$NZawvjNIAqgIby|H^xxYqvYmnUH5qu@ARS-NO<
z9~?7xCLUrj!p1}9UyzPf{tk8|Y`nJcS;7Npnc~S+W{$?IWCzA764Yq?ZGl|R1<ACw
zOsr-4#Z5(YIG$#3sr8^C#_-SR3q|MQLA6=HA7^$Pw%1W~>hq90Ha{d$%_b_!h19$a
z-(_h2V)|kIRW$UsY5B<Ut;nya<1yasKYwzdiW6p5T8s8yNGN{GFO>tGc{wZ*OFJD^
z*){h}i9Mi1DH`@uWFM(h_QDln<#i(ZvqKdQIx?pm$p&&B;HN6<JWIZn{|$Ip(X&!K
zR4G4%Tyq6Ifm4yNGRSqzcGqBO3u~HH*=Mrpi^?R~-^LIf5?g9!|7HBx=PGwim^4O0
zoblY;ZK9Sx_jglkY|!k_qIqvamh5u0>~^K+<XKF?hiY7oo1;?7^lDgIWSP?k>#=CI
z%Qz!d6NF{A)z*?7cMtE^kj?DQZN7?i=N*=N#jWeW26Vyw;WDd-3}#@n;-pylGv@uy
z7n=o`N?ipM+Xn0_&bt6U_xfBfSVVzR+vEtwrRffkd33O?Bc&-95DHCG_fGqw<1&EH
z#>>gpd&~?AEi#x<xjWsT7y!Ras8z)R{>?YLI1MVyX2!4CH^(sy==IQtb-rKjnr?uN
zOA_|XW&L4!s3O2U<DPQXSH>dblXy`Oe4=)5cy_Jv=^P_~Ole#mVV6%cTG#`2FytA0
z?U7OM!r}rby9?(?=-#mBdUZ%0Naoluqx9f1Imad;4SWee6E?fK^OR6&&1}l!X4r6`
z6V|?3mEk8JwDCglT?=3iADR^IyQ#|rwD!see=uKE4gh`ls7Qgnw^2BosTUl<dntQ!
z)53L~73b%(k-f#c0?5C|iAva4W%%2CK~iNC%x#8#0u=;qGcbOj-LTC<Cme1c4`_kQ
z=l?2@O4ALIU91;Od&+$_Fu<H8Ug)=Pk$uS~>A+B_Tf3XvT=Q52|0NXoRtB9Z&qRbn
z-jTj%S`V^Bz+Q7|Lb0RRT>D{w7V_J;lagJ2`G8IiyjA_*HVnB)M}S`eSvGw^K^BOx
z-N2CC#5R#Xinl;4+zsN#Lq#{3d4AI<;D*{%zy8#8f4%rlXFK2z71YwZvJlAla;8Pw
z;FsB|wCh~aea3uW?Tbw*L9LTgN&hc5Ly9$DB1VAJr|+^Boxdw>q@L_#z715c$%7MR
zgwVIS&3~$4ie89M33=X-$q4*(lY6H5gBXulp%lh?>orCF+&~@U;c!qu4X5*a)CpS?
z&~*P2X%_BD*yq5Grm*4tSI=1d*6GpvSQVS|l3*`o%k&BP0Xk5WacZb?7Ajt6$6s9Y
z+Q`8yjq(Vf<1hjQt$uaCqXwT@qB#KHzMC-*Ts4hu(GL1(z%Qd9KLAA);#bh(*p3j-
zy+KK5X+S<#ye8^_fsPQnMR`p;YaxYcZek9|Lsje@BVN7PwUUIj051#Y9t*Q2(#fa5
z6)HAN($#J#sE~Bh5V7ZaW?P3K;U{iCVeyHS4V;eki)iD|&pQOb*(y;cE+78}hHE=(
zYe!nRP^R{09ls$g+JzOedA7QLRW0QU-LMJy5rR!DGStZ}mw_Xv*wN&2u+Kk!2im8?
z0-A#Nz5~83%D0?1_=^$nv9w{~%2hW`SBwQ_mMu;^f1C0$OX!5SXQk!#ugKsdFzz!S
zSZ)Ek%`6I_KQ?fcl@OL8D_eACT|T#Q#1vbk85Z|2@p_V|w|=r>&2Rp8S|`eBnI#EM
zqYmgjm!|)L%6caeu-@auB@*1fL)|%GTUQuiP-%E|Q%fD_R`nin>smyj9u8GZA2VR)
z$zcQ|eghy9;Jb7ZHKyO?sJVYe9v`hIF(01%LUL$a>=^SPQ2!Xy(gKsssNXL7b8tNw
zO`v#{>-u)I{tm!j9HYOz@4v#Mu$K;bc)S~zCrIV3+t!47?16far{7mu=kVuuh(AN!
zRXL%3_Q2?*>a_vVGoJuoBVXe5P?th^1^OV1{%D}HKa^@pTZFc!ppXL-x{<&DiLc(C
zvY}2s_&0flXaDrCU<)^(&D;~JLJuCWd&KH{AXs;socN+Sc3tQh)%7K?HNe)E%peZr
zuK$4&P;79G|3G=KxaRDL*nn}Za@NyPr@lZTh+pmec~i<>n6^6&tTIFsm_YU^bNPK4
zQzL)J;ciC<I$KxvOl{&l0eB&9AqUCw-^&57Z@l`A&jJ;eBy8P*qQ$3ORN;-Ya|Y!-
za}t+;I77oXXo8<R^X$1W-RL7mY{xtKR4QuA<h=dgMUxl#!cr}+2D+VgX8~mXXkRaq
zQCW#v$x=3VL$DW8em%*lV>ChV1y1`J^_pMA=fN+`^jAM#h6+72^4$PF4=w4^js<d8
z#>;$*>(7bwCsh4O^hACUi7RnbdVE>|C(wa|6n*kU>Sq6Wq5#*@uR$-oe+F2G@;r0S
zRuK=!UvRX}NoR-lpnqt)Z27GH=KCn*lkyeqy%@?%&pbf9@;=~HR2x4$GjiXTP_9Y8
zCbHviil4DJV8(F5B#7M)pW~v7e0ph8l$WjVf@0&mh<*xOy$_6@!=%eydl&Ce{-uOf
z6}}D6YgIGH6={)^s^-qYdV<)CTbu@A&i7?LylYDQ+FtEh_=Z==4>|e3&<qBn>-?KD
zyw%|Lq<++E=d#gF@Hf#ibMc~BI#JDUrY+(|Z8z0-*3oPWMu4@h%DZ&l#YH+{fHWrQ
zd2gc-G-lg(m-!ncS44s5J@i;wci)_b$7Bn}27+vqz6LO8Z%2;4QRsbQ4oNK{v>dA-
zE{&slt|Iq+P^x)}Aonb6IZJ+^1jMM(Yp`rc%?N>fKjV^L&(itSMes!?Of{wG@aCTu
zWu_Pp1oHbiFguOLj?wurLY36qd_E1)0T&c8&XJ<Tb(356RHo*j;Heuu!pDax5x9|e
zOMlDQbT#!qwM<}1l4~JJgr6wR&2(FL6i&d<!}U<EU=3uPnMZJiN(C&paEY`QRD@B|
zUim2j-9OQJtE)RizmV9o2vV$32n8VX2l8#D@phU)=_`R@y3F0tuD!M{d6%M!vqDI6
zr;spM=)^%qT0J5t0LA9EmEWYVgP)75H5qGA^VJeJ8S7=fBZ{%W1}_<7`L;~ao`b!L
z^9F2YhF31SbC8Jx&7N5Ws;hDWc=N?8=<bVK`|!Z3oS<Ypxejw0MgkkayQR8#1PA~h
zKT4lyk+9?%#g!X);#SY6g=>EiSe4-xla`&L7+W{klp#IU2Wg)OjsQQSo$tqd|9mQo
z%_OC2R=1?&>F}6TxXTA)_Uj!5{JbFLD=?s~JZ*5M)IAyoe6Q30fttiPm$Eimy|caw
zwfH{|`aTgLKUk6ey;Jf?VR%lXi$DpeE!eCcwBBjf<TYHrEFViR1gw0ma{i^U<P+=d
zB%#7^2lIBx_fj$m6iPga_rP2^w+~G6Uws0NrLm2vbKmp2`_Jz{&0cdmx+=YWSyf+4
zTDyHu;?JOEhH6{^`+L!mWvBefN!H-157!3N+dkPK${i!3TRoq6CMj5${E-^O+3LBy
z)Xr6fN{W3^hUJeKt0&XVM$kRFJOBt1%tj!SnpmUaBFF`XG?cT~=$Z#}RsD+0{51Zh
zc;5#Zgtk9Y)A>+<v=TLJbgU$diVHM&4s#-4e`SFtAY0qvA2c?)!Zeo|PDc?yxl7c2
z>|E+!td6Qb-b}Zh7;RmEg+>|IzX3mPTDtOyuU=$N5}9x@Dl$ab=z;F*y4Ytf4&{!|
z17~AUK1pp2!|`IPJm4U#cY!-dptIC2mQ2T$+j)0%<T+nirlS+DDIU?Z#HREwY~YF2
zaaDc+udOZtW9%>ZD3O-*-!QLqOfQ)dtC+TW&p}qi!5o&4V!V1elMY8pH(mRNJ^laW
z;yniVfOGg!7AWw|9>|KnVqbhZUE4F`D0zuP8ck}{!-Z2}0k1%g4urIm=n_GcyN-m4
z>}{jJegvLmnKaFoaJOuwOS`h7EnQ|T<80RG3N8#nHf-kT`jTK~&G`g@7rZ56&F0@v
z5d~aST2oD?E@{G0etBd~J#mS3u;hAdXl#*YFVD$;AQGMu{J^lx;rte2ogcbC_Acrc
z)f><6xR^24Vc@;Hj3OBQGygDhr<Kavgky3)|K?MX$Dxi>!IazO!57awy`fz8Sc%7O
z555)Wpoq+fBiBd+S~p%jFwqI|9eSov>!wSofeG!=D=V)Nk{(*qeS(r6{wXq2JoSq0
z12=<qocQ-`{x3V1`f>gSHtn^aEc$*K(~Bm|myS^_F}RO{Yl(@Tk?rVH*KW&Yo@q4g
z&@}lcSAi7`dn0SYo8o_99%u!#e~0>u|4EPv0DamudqI`Xh<?xF$UGS7mA-Is!>48T
z!U`^$6+Kc!N%WCmi|&V1OQ-vvSkUF5NK0nX+ck$<5V7XNp+u&ecfiZeNx2&pwT$3B
z&Q~T{*RJ}6zz&yD(Tp^Q`~@5Cm~rVhJaTP<#!UA%*UXiC1}w{<QT9jeyyPyFFrAhV
z-BHJ~W#(yD?a*IlFlY(yWyHctlQwrijFPBMQDyr&30P4_B5Sm6IFr3vs%m}DK(;26
zahHOx0}V|544J_%p3r0>&Eda?;0tAp7fsCq2Xbd-ByaV5^y?jFlWk_yFx&E_pZbc0
z#3Egq*mJ%(zJ(gtZ`vRgELvzsjnj1YqWb{9Ta03{Wq68DD2B|+As(#nIX1!mwS<{<
zTjVn5_Rx+0c<Qj}Y>mCAnT_xJO&u_L0vWw!x0&@r0;hU46${N4()x$*&K*C?)Rjm9
z-j19s<-$5_@PoaKd=>xcNA?qoy|lzojQHI3=6$&U<Dz#!;{D$+dySfqk1gQF-d63j
z4@(<M|H{a2i@hAso7xenvq@0VaY6xQ^MgsUy%l2MC5YN7^aGM<45S**DzQw8%4&jX
zAzfq|c7PBPY`YIzUj1s)K5KC{dvT2$*w$jK85a{W*a??<f2Xn;EPTFad!s++E{o1v
zN*DQPvg|n*^BMcfB|ZW%Vda-^*LLyMMnU$o5qtPUFA5X?$o@Ex`})I}Ak9r$TC@aW
z*W`p8`BA6=xw_A<;<NO%A;%VD>~HHh^pIr#)<jUAqvM<M%UI%UCc>6GuTp{s(&a{u
zR0jBd`5GMj<BXU9p+ig%SeYUEno)-;&fMuAJ$?2~b}2@m)mZ*{E|thc2b%AZhIv!F
zmk^E`TQMB$7E^lg7clR~D8xFnGZmY|siC8t4v1C0GqS;x(p7PZ-TTPdwDa~@imSs{
zlb%L^OgoS}N3;_Yw|(1*u-JfI+GzZ-QNr+W7WWj0uxGcG!fh6|p8756VjQqev5wN!
zHD@c}zD?i`_sROYmb-^^4T{R`YsICMwW<moQt+Xg+ivV#Fe9k))=0Z$QGaBKhO7{|
z_u~mU<PGGFIz5VwU5sqdLlT3Y=84V$g<_Z^WJOD>g04t+dWxCZlUb~OnzO~)XFU6X
zu}Gj=PUPyA+|4rhNJEVtEp?1NlMUZCEBZo3(XW7;gS01^hGVP;Skhjxhw&9zHW?_y
zo<8Kr7}%ZHr<aT8L;KJ{y`HNoIJWIe;A!uE+}f`tb>ru%BOM=g0SDyl-YP;nKg(PE
zHgd3R)UxKt)9#w4&Rg<Eh%ZTSwUAe>KF6jf3}pqW6XrxiiH2aK>jo+&YjrCV0g6`4
z36;yZw9uWfv8Rg{QP5pAxwg_oS{+5s<+`!Bh_R=a7kgfaUu(*c{UJW-u29+psyez7
zu^im4V#ThG&O9X?*l1gv>iQKYDvI<$4YS-*XAcco5C5Xz_D;58m(}n5nTmNW?4)8@
zFULjB^9O2s)b6Xc57Jvby_7p~>7Lq2kk;$CGXPpuN3zDKG|m3o<FE)w@GGNuYCKAs
z_itS1NfQ$<mMfpqEn2?0!7+VGTBK9TFvkeG@apGM`~d5F-V#+@te25{mg?n7j9~wk
zCg;L|Oj(jcofwTKNk3DG6x-)2O>YU6X@;`5H~7>)o*wrE%JOTpVi>1?hIMSXV`|1E
z<0bisxi@OPU)^c7L|Ro{pQz>rc*k<zl8~g-|73AtYG@e28}$i2e8!P<>)~`0h+B$?
z3&NafSQ;YfJx}4?sPu4A#A5xOB@I=KF=t68llYH7>pFt+#xqxH;DllLO#rEN_W@L2
zQ!({!vzz>|4ymU`gYs#Zz4t!<NJ|ed&MbuI+XKCL&qk<A&g2~u2%BIgp6>oJaTw^T
zN*}NvGu$A4&lEh^AjZ3OWm${9_z4oQF;F@C0-qwS7xOYL70DB}eRaVr_S)5#HRx*N
zSYLtCBv&V7IP`Lm>&@yG;S6beX?M*TyBNVaKOaTz@EfsPAh*-Cm`xPxc=LZB8XT4c
z^#(AH$<-wj5-W0pV4IXXZ0ZAn%%H^4nXlf_ip3(kMKE~<wwp3?6;fV(8~h~&UnCWf
zX99X8Lm6E!=)rr|L_1pI8DYJ1L(ONz6{I)_-j~Mw;hvu^n}i-w&zS!=HyZ&U)izyD
zaA*Y92piAK2`)a{Nzo?KHb&+s04;eBTB<kl5QR0o3sjZ}+uOfJ<UE<rW&8VrJ=IV!
zEsp^YcC_ietmX27mBWLan7G9<L;qIx^9fOPO3&OCSZOdMG$@C?TUzf<yjzUA^SFF-
z;i@3`yerOU#W)T@3hs0-foM8)MKgwJ-TTJkn^d-V+~+`C$)KkAX!#V{0Ru>q&HAnT
z`vdL39`UvjG-i*STn`mUMOc`9Ak0Z#_`kFG{=gb%-IBVi50W0^iTgLG2@yepsX3PB
z$&{Xpl;)Ht&!6{gWd#7FvS&#fxD-RVc@ryy*8Jrlx&N~_HOW$ied_nqpB<O~4nUXb
zBlIIaFX4%dDGQ|jRG%O<jJmtu4FZJZwYSRjAb;1#+}SEX2I~tkmt7TA|F<t|-;~?l
zpjt0;@=lK!ky=^ST+79OU;lr2ivFp_O(C23Gl|W}vk`)W_3eH-S4IYaMEN%Mx#Z7R
zn&kIQU9Wg@fu>y(<dF?K2Jp<UbhJWu`2LSJCcG=`IR?<G*I7y!F_PF_5nQ2Y&mq*s
zI?K9;YpV+cxN}~vY6E5f#zE-MF5}-X8GWQGYutTQu_507A4Fy|2JR;xso6(s_DdIF
zVI@yxI>^SKfp2ht;H5VCbj7(;^1=x;NwW;TaS4}Cjb|NfZwKAlH^q6>VG%)rExZ{H
zdEefE13;6G%am>z;aN)T0V{Z>>H`E5;JnpE<;F{~3SVw4X2$jyP|7b&V9*io^v_oC
z%}arSG7&eT7h<A2vp>8(0TV95*MrZ2v&aDZjRkD&-OCZ-zX4gwxkBCudak7w0jK2O
zcz{;TOd?lzAha<sHVoJpf>nkT>zg)MlZuVtuo#n(hWl!JF^+je{~Cv64hBJDwLTZn
z5GD1?QHs7hNe!f6z6yz9FOy+f$ufXwb-EwB1TiHEZk)XDPYYj@H6UN|{JE$O5U_?c
zd)}LKa2=PNJw3sfid_HIBZ4<SaHn@o*;DL6YD&CQz4hl30lGv}g$s4DP1tP$`rE(4
z^nCyjZ!SQc@CTK*21&lk2LN&9k$}qpI|41aVfP>G5_n$veJ`fnjRJQn@GH6dCuW@}
zT$XlM5B6^C6XShAC|_10<c9W2`3GP93%Wn{`~E$TZc%bw>Q{A*ayy}u8NWR28E>a8
zSWf3L26cZ_Mg`%>9p1edn6@Nq%QSc>>8`80`s1TUISP*EOy4ej#bALXd%*P%?@wam
zJrYPcCkcylesiCt_h+)pI(Jm3Td=m~)=r>zI<l?mcxN`{kvpGx+<}vo9l5{<*TS8N
zsmh-_cPWGB+-po7|1^7<P|8(`R&gR`T7y?3QwTaaLW#L?GU(@T%p{i@0N>u?mv*B4
zYSDw7Y2s;`)5ZIkDGz>d!^J{ge*}H5mU1syn?svTM6<qT&q>%1px9U$e(t3*>XPV0
ziSiPHYveJM)N>FW11CVXuDjn4ln5#FPWL6=Gv+gJ6Sx%3$D|IFr{Cm~1oN4YSO3do
zCj9Z(Vd;lJtK@GovXu=&YPm7ZOXqYTIHVv)%-5Ll#Z6(Nn<EMGp_rXZPfnTRBL*4_
zx`bS|EPGz|fv$@7Ju9i_igwLHxy0vOy2gtpr<w2FvNYdLN3@iWV}5PnDiepN4Ud*j
z@E0JiK48X_Bvl%m`Hf<WEnxbr7(U^(z{JE$H!b`nzrka*jqa{(l7c*Lfpqyq-?io5
z*xH^+#LyQU$OgBu`t`C##2axR&s6$6L2v@wYO@!kfFS6x_g+hWg<rB_AY7(~E)-*Y
z+gz)x*WNZ0ycx9$kMIiCmV9GItq}j2eWA+aN>etDIMXt?+X+9B>iUxL01^7!7^OqI
z(384<!|&-bAQrN&8Y3D#=dsTpyS5y8W1Yx`gb*;cw{zj;#^qC&$A7qnf@{F8U0`2o
zGWyf=WX$(#GLS!mUtcKIKW%|>1n6a1^;IqMDu&NYW|Qgc)t&+kqZrA4@8@FijL@K8
zq#Fi8-5VEe*m$w?y^p<OQ@3vUFI9g2Zg`9)gVn!hJWJE9C>^ok_j1d`0Q?a-b7(vR
z6Sv76{b^JJCfNiK2<}>fUE)J8{sJbrDz?;@zrVFu!2&|ovJ~@XlkPo@5o7EzCc9=+
ztkm5w9}T)mdhjhz-1}AJS1YQuHRD>J18K!b?Q1zv<&Xc~Uq|sQGqT9fnCY^=d7eaF
zP$r&Na!TAF>wP-o@6)NG-^dEsw?A&!o^)eAat&`(R9Cd%G~Nr^Ke~-c4}MnRnxr1K
z&0jSC#y0Fu)RL<J<%TW#h<iA&LbVaW&n5Hh=5(NK!VErtNQJHcA4O*!*3{dF@c|-A
zqcp-OMUa%yF+xJRMN&fP?id4+kQyZ*AR*n|DK!z17~S37Ft*=&-oN4E;@Y0`oNwIs
z=Z5F%s$MZ<jY1)YK47Xox0PFyJHoM069L%FLka&$+KZt9QR-Ukw@*?;x)x`~7r<F@
zkY97iS?1ObxvWrid1CsuLFG;Ulu%c=*V86}V!GR}6&Z}Uw$?*d6Q4pDDQS{M=vRWV
zpUWXM!%S>Ju)P=q5f)+Oi@z5_?mT?|hZccXmAW7Uic?0tnLIr?SD<m}jIwR0i~i-U
z{g7=P&iNiY!gQjyfLGx8KL549C5x$`mP=Q$u#%gmDZS2Hn2L<@!35)reunLKw!M43
z><{DL^g8}&76*<#uu+PA=dj0Xc+IDs!SDutb30PPr;Eu}GJCMS6te?zzh&zhPJf_F
z-Rk?#Mi)rYt;`~QqMdaK`!pKdlk0M&Xe%Pl=U}qpul0buH}|Jw!bD;~=$piwK;B1^
zp11V*XtUIjREMMkt`}|pH|-|^>ef1C94``D-qA3GOJe-;uDocyw{!^SVBl-v-57#q
zz`UWK8}Pb#)&kif5%OlAy3`%g^62uFynRs610%J3jKDj1ebvb0q8HNjM2jEes0W1p
zU%YTVKEiomXS17S4{x*&{W2cRbf`gNgaTi_B&$8uDVfS7_OpleGt={WmAhHdpnOz(
zlT4ix<g#@$$8W`_f*c}&DVcZrRQfOQ>0J~o438qb-7UNc90vY0jkxcS5j<2EcP`;t
zy_AGe|HKY-Z7{wE0&!1s9>=CM_wvAKFF?Af>XWDE_L<i>cG0WXJm>aLS}tCccNEQ%
zXG<o<`HAK~N?%&CePnk`ca?B6SyqOId_i^)t?xJxo24XIolMZEWVyP17MPf5G#uPA
zNb&|TmbM9`$PfilS-w;ldcf#c<~qZ!Ltw@7K@mjB%vRmt`~2x6$>H8D>2GB`!<jEX
zw#o=ByBL9W8tP;?{ve8sig>H?HI%+Hh#s_g=&=GsGUL!cHj*dx{TcGnSi=<N(*e76
zLlo=4JPrHZb7i6Zk0zBrUPvYDvfEsR$9HkfNM>c|LcW$6^4)a^)f|Dg5I4%~JdyQ&
z#?bBY<h`b|gr>Km*K5I)4$9J7Da*kH>PD*>Y;WTOqHHI;+^!)L<^zbP{W$pgAAtk)
zS0Q{?DL|@vVZtSA@*aK30Jj#IKjM)7;LBmdSGR?9!OEK3_AgA$BbPaNhyL@8Y>hEG
z;nRkjeGUg=`2<G4ANnGjwN*DAc%>a~CjJApl7OI}nvutfG!tHh45n@f5rN{%LRgXx
z6t1g%v6eh*8fUKm54O`xg!xhSt=FFR4t`ext#z3V$GpJ+UeRDgSLri!BfNrRh6lMk
z`RMo>(8w~p0dgV%m(Xz?7Lq;VRtn(HPqCA496fvTGqzk@FNxmU5gac`kl8?RtarUF
zIs>+(PPcT3NS=|UA9Db?XD^m}PZ3#;7!#D{JzKHh^lp+2wL)ch*V$z#Fhu4=P)FuF
zCrSSY!uSU-?u59;*MN`oNJ?#M05$*z9=g7}7Kl6Z+_*cmcQChoeC~wbkvySV4y05a
z4Y^&Zz#5Aj`0iqbrTtIvnR#TUnw05Zy?Ax>vy$7j4+o)Px?O}@6m{50ESGsl`i*g*
z48qxVuo?W%Ra}R5zCuy;rG7!3M^a2wp%<V&_R;uOgZ*bueM+(sCO6L~J&-P>ZXoA9
zUn%uQG3_bIr;V7(_<qgBTf61C);#?A!qV-j91;InwrjutTjhx=TpNYmcIzk&iOlEd
zhn^8V0PCvodW}mP`y!{QH2+T1hSXyXiz2-SIJkSU_!>RjlIf>n6s&hPlv7TAsdTZL
zHB@9XUQJj@c=v9tol$SgvPZp5@Jrm0q)HJU5AwByaxZU7jhxUOaUf9Z)%nx`){`%y
zk_e9627-trfY1K=K=IJnKCXTM_34rP-UeT>qYhuhvnOV!%2Em<SPEZ{<|Qsf0W-bl
zzDJ6aUObFGZHnG|IYS>BI?;6!H>>FGa?2QWC~BMT9@EjyHZ7W?U}2NTN1)|`KKgM5
zCkst-Jqjwf_b9Yo?iW7J(*aT~c8G$lbrDxPxQ!!Z)ZM%@hr{4gjUq#9tKD;bM6Iu{
z7fVOeQ=M|a037rW_>Am9rM#Y0y4a`{vSU0onmOi8$GY8b`|sp!`y=iIq*qB)UZ8qE
zNw6W&FVg6`=KWPNqe*}KA#^<@Nf1>fz5~5dHj$G)j8kgWiM}xC*<A?Gc6|vX?;)Eu
zYjEsXr<va3DinI`DcD8t4&rzY%<rdXEd{i6ZT2Zj{j<Y)&nu*;-8e_d(dd_3IMs7x
z$m;0L=wK$gHUC@xj<C#)_b1p|U_j3Yf)jHW-f0qIgDmOCRS#0&_@lL~GP+p74`^9m
zU2dffmM8R$ao%aYj)q3goPvS$8l1er>5QAx3)V^^*gHCr-Rx@xp^8h%4|{~t(K1oX
zR?}(3BfvHlepy2Lz3dsdKJ!0NhXF~&*v1~m!iwIfDcQ`u*TMneAYELxg1y-5BjBp{
zPeQ*qj3e2HFYB#45n?b}B^P|kJO{7k?Tzc^gKTk%<XbGxm-#Px>9uo0hL$nz69W+{
zgCxEc^Obf2d6m#{kBh-P8FujpIB!MT>QFC|(5!!Lyn09%72cRDfX`;IgmwiN!KyCo
zq-ae_{Adm}l<aLKa&;KDSLuOEi|(Zmp~+4+W*ocfTLf!Ul*Q)GSDlRFHe^R2meK^6
z^2Z|~4?wu2ievG1ie&{a{}?u5&NxGjYR%Fu7AIV2a~`nCX!ivofVG8lIN4na$0B{E
z*N*bKI!ITeEyhZ1e@}siDuQP#ieSk3?eQ7CF06>_zSXlLTX|1-s>tOwJci8tKaf7&
z`!3P`s316CY+@23^0@XKtif)I?iu_MMHTP>u{?XN`~HQ8B_CP}VDj&hDoW3H!b74l
z6)n~2Cb5^@B`B>HOW|E!f)*;>;VIRRPTzvc(yO!QYc1r$Tuk#QyIZI>H>yG`nidia
zHd;DkT^oNPcJ+X_u$N)p!u8kY^I#HLo|MY<&2~w+ch1M6*2%|ArkO#vg@O)h%X>}}
zFnh$TP_0;^W?z*1ZtLGrCM%pB>q7j$4j}jt`Lc>OQ*AGkCo_yIWXwy;FEix-;+mIZ
zE{6B0LB!pjEmd>{b$MP!GoS+e$-ftiy!wo|c~rVB*Cy$Adu;;&lc@A&`~?Fd2zuQ9
zY&I=|t%+nbF`<>wQg&BaDZ)Y<-ovlC)NWqoPY^-=jA8P=7-!i!$r=0}U=<^*a4{H*
zU(mx44Pf}^y{MsnXSD#3Aop_sRMxc{Sq>$R>7nCO%%|#`1Ca?!Mh^DIpToyn`gyr_
z%oJA*95WL<1v~Ozd9B#J&tEnlC?e(6$QoOK*t{3%<F;%Sy&-!ddSw=?n_{n#NT{IB
zZP2r?Bgd>Jmkh<NRFNs>B#2u(jx7b2_LDy%r!^ya^qJ6b)E4P?;85p@NHdHq#$?(Y
zZ3WlRO|*-*N2Z~jAYF5FOwjd3U|Z#0psv(AR%swvg$AS$Sxg2GjAPKxX>iNumJ%z%
z8sfp~$rIC_V~HtGn!t-?6;-x*UmD%vi-nyng_SC^Ex;9{g%7`Z>-a9Du;q%2%lcH3
zu&Zr60{~4V^%=<ErUyn~aXHufPS>HcwP3XZW;U0nhudhLRH?@*F8A!y5AM^QVW&}<
zz9qeZ>AEoZ?;PK(&5R9{hEzXK0P)v$`QoSO4pEy4k9QSE4FQqY2XTU!adADZ{idYB
z8YkQ&%x2lyqJ3#LyH?Y#((jLNoxOf%Y`k&X<Epxfi1Zk41neaeOZ#l1_2xrj#n6U!
zIdQw?AJk{$u)02O-^Tgl5DmM)H_Clh%dELhx_yA?pEok^1ULfJ$9=V@n|*l`r}{1|
zI82-gaox=q-BjX6zOku1oCM7e^xpqpbEs$T%q7CaPL$oi3&R})qNIRuJ+&O6DI5#{
zMikl-MQgKR4)nDo6_H?j?PDFKBHwTgbDhT*bOj$;IIeiB-!A$k?RG`E?}&fZZasc*
z$uLNTw{th;HyNicf~GMD0vmQ8_e<b7U@7L;ngjj=4aTyZOrVt=upQ_6@KuI3mySx{
z>Vg^>ob)D~JGf+F-~;j0Wa0C<U4TB+7C4K}{L&7<VhN^iext-P-)L&D$Tn6gxVi{|
zVe})f{iQ7|S5Gb*g90W-Dm^sm@jsI~PfPzS7KylU<#$=^xE_W4z%j-`$rxjju^(*V
z)^-3>j&JBjhY_kIKfD%mwfug#=*Es=yLkjtzm|G{r359t&Mps6a%iURuMBDb&Zi4K
zMtw1RhRBu{ytL12>aknY#MDFAHPP?F-UUa(1r?B%KB>KK8@JsndghKNGuvWFM$Rsm
zlh!Ko0r(1K*Bq8swm;JbI~yeyoZv-9QgrfJ=^1B%cu|D%Tul~yR*3wREMmP|^*QYU
z8|CVnDNE2+R+nkA$>VqLMk!otz=ge<rY>&)p@fg<VQmiZffT8;;daB9A(y98wb@DP
zP@ucDCoxw~QQ)6xu|Pc@c0zIw2-zNf?<}nTa4M4V0zYdxi1d{)T4zrg?(yX5u1YVX
z`}sU_`>oTK*k17Y`;qd&$@;;^K&sKa_9P0tqn)&;{&B%KR4+>YSxTgd*W8z};wLX!
z0D9hEv0oRnI<dw&U=J16y8l3{tdrtA(Lt}&#E+V$4@y1mSxEH5+|l+%ZCQ|C*&ebJ
zLhYx8@b$?ouL|ER?*Bks-}x@D@c0j}9%t_>d@(|QYFAYFOm;&Hs3PP=?pqbRPFVEK
z*850(Bk-1^^pg5`aWABETwhjG%bY&`t;}j(rbFBQW_w#XT#EiDx$n0T-W-_S+H_wU
zG97gJK#PWn<&;KKnDUyE!JNGLw$ie6pw}E4w1Ft(e3(%oaC@vF^|IQenOmr$eHnSH
zBmASBsWtMxRbTU<!tnHJ*A06qx^ox3?RB4dIiyRJB%D!t-lo@mMMV#UFoJIh2b-n=
zL0V<nx$i7+8cQCAh(3VToWbWI_=DkJB}m5ipYS#ADU8-!H`uUY_7qO`!)}kQ0qe)_
zewLF1TK2^*sV1FjGVHIWIeGiqr&u8O&*q-(>cPey>GHe6SYTc;;7+U8tI*)m<rxZu
z+gR?jx?i?&NHuAB!dR3>+}*Gk(VcXA#xpaUMi0cM@|;GTqS~*Jjlc{1@K}yF|I`kG
zVzmdYa=1eS?}1Vwsv3f!WOBy+4@513GD6BmZ=LJz(FfDAjZSaA50`pe_+?bT>4><u
zx<vTK&*S?$#8olL>T)aTaqf$dr2ZGlh7jA?oyQf!(&yI!+!M)+W-T{cqj?DltSkru
z_9@J_K4ZxY+efksIuG9e*qk#T@*}%8Xerx0pcpbU7IpQ93XNw(=LpwJSX~RH`nlQA
zrzFlxUYF2CW6FN^BNlLg`X@I~HosDCUJxwv4Zso_yykiL3c0XjFIc+!ryG-LofYC&
zN`8EpA#4&&mNet`7E|Le=7?C~GC$1l`mHJ_aHxE@$9(HZ*ZDaujQ*^+$1d?H_K;<&
z&@G{;i>a);kc@mVAy!;g6Fc7;h>uDO*->DoZ|zw5Whx>D4EM8yoZg&4#%@umrV}Dg
z^l+y7s?t5aA1M}{$@l}n&+UhMc5{Ltn-gBW-Ka^};IQKK-KgaIC>rglWwwL8&hO^f
zju$lS4#NS^(|tPW30PhqH++3bK>ew2OywIl0J-*T6x`?NeIT24lVkOzlXXW&;8r){
zY86z6HKZH}?bFCVj)fE2%(lOgwsOt9ntO?BL0Y?x@y3B<f1Dy%YSG}Lsy!t-aiN5F
zD@g9%&8(P_{RyTyXf1I`hvz=bz@(Nm51ED>slOce;%`Aa;O&qo&PkU(gx5!26|xws
zw&@P9XPySz8(w@Jb9bIWKd~1YbIEvqybS3dbM{*-7TZQo;16ni<peccExT^T-vqST
zKLKKiSVqmoM22q!*3u!2e?^wW7`yEaXxDT5L>-FmQuENHgBjbc9P==ilgnzCn|t`R
zst%ZJrg&&EWd!XBXa(qP9|(2#0C1kSnAChH=x(47X7de%gg<aZjKObp&+X^VD(F0p
zK#n~he_y^}E(TM?X8Yi&k&BN_H80KG6i;VTo?>74Zz=bMslV@1RB4sPE=BY4UnN<v
zelp?fupWH)IksN-d^gd-eM{9x)B@q?_FktjWu?BkTU7F*5MOSIF*>|k>;h8ewc0QB
zly*PLLnLCIBeJu8s_o?dgT+&(A(<z@w|nF3Rxh$*i=7@#j*)>Lhw69LL+~Y8t^Et2
zXd6XcY<U*6MdoX&@fhWbap>XZcvIv>e6y-YR@!6ze@*#{NOE%c{tqcY-4@5=k$v^D
z`f03lAMa&7)U@HLZ`K%mb0XU!D(2>MzaO>c&2!FE$yeRgsV7Dcxo&=tEmi}C#Y9=v
zpLZLm?6YEIBnEQLHkTzS&mtcytss4Y!*O+R075h0X=8FBv52}X*h4q1*r07TYTC;O
zV}MEye;qbYP6Hsr!91H2%(NBXzaGBD6qSnKr@J8?QKW!w;NJJ?g}uR)kW|sf1a|M7
zM|0=K%V&l!uZ3Q=Ol!c$x_?S38GMUFzs^QbRs>WW-F}ektOrF)w+|yYz~6*2On%{0
zc&PBU%ONpp7D362bEl36F#vA>q(8l|YQ(Q(hHu1g9}OOUxdbCnsnm=V#_V)o8ChtO
z1HFzhlV%a+qtpZcS;<9We^M^CA_rgOT<U2FE9(BuHV;1`%n%+XxjXmoIDI1kNBJXg
z^?uCQ>Us{xQ5To4yocM77j+nm8`L5*#t>>ca7zdLu62wO3ep``&nOeq_;V`@!Z}F`
zE3UDKNjE>>QF~&p{SP+GW$R-hHnDLog`mxU7?u@H&-rx0nV_x-w|v3Q8((>j2q$*F
zrM&sVI6pyizA5JH@uAVKV@-dAmxS-2y}Y3H*uifGYeJZy9!jY(cIf+j)_j?zvBM{m
zANkv2R2foX?NLgZG;#IaqzM*Hua#S*E7a(nv-sQAyRV1eiR&lF2y$h?+wJyq4WCgb
zv7cYZ3OtP_p(U<QNF<Q&XVQq%Bq6^h5PGsJ?us4`&B`rR7_ZN9ujRj9lqu&_e^uWr
zRZ>u2y$lIP6ev5^$9D;CGZp5M?-KU4eU^B(m1d}zp{#fN49Lc5N>|DL5sI@@SoAnI
zQLtg8gmPiW4f8uWYXTHovU79G_9t$Ygk=hn(=G=;&eZ#C%1(9(4TcmRD{0<Zgzn1_
z(=Vk*!N>kdO{L8ph7dS%5me%9xIp?GqotO%fjY$-r@8JIQ*#ct9(Ja2ccaeVO+$P_
zwP&{FZiO&WU1c$2vr&tzLB{J5ArMreeHitDJ$<ca{z_34Ao2MSQ@(GscPlC7WL@@_
zpiuTI;)s@$>c?fK|NHNCN`_Jg-&MsbZQKIh5tm1~8V%S6!}Vgq*#x|BdQpl)T2^uh
zw7M=CqvLQ}`|VBY94#-RPT_g$fEeBJYc00TFN88IZBvhMcv_h1dxe{_FD2ZL(|<U7
z>A2P7T@*oDGd@J#NJai!F<7ju29~cl%4}1J;by#P-13x36C76Z&IMg+5{sT&3%8|s
za!mI7SJ-A}Xc)&#L*PA%cUf-oV?~3O>$C0VVSc;2HoR6nq8*@<tdRLl-K#6*><XJ_
zZ78Qoa1$VS#<@6H3Y|?|MI6^4{6C<o626L9Ac`Qwqb;bu^T!l_va<cl)boF2LvHRe
zCo?Q0iO}0}0x_fwHX9imkEC0+@`?4wety7Pyb#+?*ZpZsE!M)cR__eyn~k4wQOTdu
zK5aoZGulOdy@-DOaQCcpk`4tqMP~L+KddOswyA$AEmfirma;}Sz!~!1vqDfJrgzT>
zxMmf!5rSFm^qDhuWn<y+rNT(h3p&vH;tmDPY`yEe5BhAv&qzahm#vDU!0>TlQVOBe
zh!I`=Xs`RW3osPM{lQH3P4<pnYwk6v)%}2d&v4<Z4~ku3LRFpsOo5ARUu8x9>X1>?
z@ar8*zLTb!W*aF1x*pazICDTK6}<K13N0i?ScJtJ=4ZuD)#;uY18J|QfvQK6?`we8
zYW#=M3=<2`rFmxx6@R{u2lv|%``cIj8v>7ql$s=ESFck&o(@4*SK(#=31&}gLCOUm
zfHvLUEc2jdBv*=)G&jh2yH5XVSQoq0G6x@PxpUM0VRqQ*!XkUo&)?!{X5J}02Z9M|
zJlP9F9E}F(gAYxWKT|UoVXCkV9P^h}iEOeL4})9se!Q=xS_iA?M8iIIZMG7l4c=$G
zOFnI8YSu4#hc*YF&7byzOofdagB(tzx(le^{cU#G+V0RAsN5#_D~Z*sa4E-CyrPq?
z#|g9(QOg&)B9O5ahZ2YYj?Q(eEXRiTCIsG0&HmbXd#3qras1{DAX9Ov<{^fuf8wc>
zjKau{Z4OLpp(n%EoSEBM%!kZzc#oJzbI=W0pblLLz0o|`&CMXwq*zBJbjWSK!3y3Z
z=t{YEsOYyCXFr)0%$zK-P^9)m$zC4PIo;y61s(M%_4wtu{u;@aa^N>?KOZd-M7Op$
zlT!BDv}ZSMTyUOQhwjgJNU`yg?sstp>30M1MVnuqxm`QxIK7xUTaif0E}}A0=TM1o
zbzi~T@dMgLP=4!DvKVz=0v1Wd<{R}(G;Seu=Sd;8KjG<Flc?CCnqj+idnkj=SjmC`
z3ln=2Nyy`URFoSq%Q`czk@73SqH>UDjt{Dw3PVbFib2Y$r^C!#(67(P@jJ=<-A);i
z_{{6O1{!twP7f5~Vbt+Ap{g>3Mr~m0!Wa7Dm-jLH7MAeEeDMmj80PnYc!B}AFQp#<
zb0&KaaDfkZ&V-G?C6qW%&G+2-?h<qS2{oYxY@2F&5vD&z25p*yAfbjGhaZ#*_~{u;
zJi3$lR%Pp_W{B&^%5ZclOG<wS8Gn-9Z;I0PtNh(d{=ue#nN{4oa-Ag&p?*`uizp+9
z`_e45KrWl7{`mww;N>hr`^__S=RCmvYPUN7Qv^MvPY8S^QElZZyq^0ajYp`F&MzG1
zp=m0jpKMY27BBM{VuJ5N;s_R69my#Mf>bT=9&T9chDQ_&T2vXr7${Mz^I26vO6wXc
zQl7>FlOdN<TrLL{QtzH9cZJDff@N(2YG>Ee?RSLxJ|2Arf;_3YW1-4&0Ci~LC|_Ww
zSj=}sbl_luO%@doEb@OdUmk0ivb`n1cq?D$yeV{|wX#!RthN{9^|Xz4*5jZ<x2%O&
z{8aSla0hZKC~jN@xKHbB%A{y$FQ+^sar7FI<E)&=6|*>Jb5C+Y{^-E+dUr^d*+KrF
z0Z&?Cj9~3^wl>ma;;;AWE({-?W~|2S2G=$tKe9ObC#VQj&?!H_$-er3Umo#R%UfXt
zok^dNS|O>xb0eyiw!Zt0u`=x=qt-P?<`na(P~jR|Q;^udCC=R{*iX4qT<4X~uWhU8
z!}zGVZ|5_{l!U%Z4K!Dvn+*#bjTXZ3o{%hkv;F>^!79iT|DS%g*$1U0W{%FWex<s;
zk2RZEv5M%jwww2HvUoQNA5|*>{DM^zS6+*b$DJ;Df5R!=uX741#Xa|3Y38Jg@t8}x
z;&HT*OIq&6dI4v4AE~tdoKkTitJkQPR*ukI(w+&5EZk-0elEhSK11l5L1T1zX@oMo
z*W}}n+3NsZT<epJn%iU3&MHlFLVT?<UoD@~!GgW-z-tPLbme@f-1RD=)fKo6Y_Jpo
zl2(V-ck6U{Sc;10h!OV<tK7sgM*2@|fd{jDM7l}6Du4Pby{p=EnyG1e?^wO!fkG)L
z8}mI!Q8*=L#R|Wr6d0t>bMX0-yc{k6=I$KH(G014?Vj~4@@&ivx%5+_icBdbmaY4U
zIu|=IZne6#4PAx^|M;1QYs?OBQt0XLI+P;ueI$TAR1_M1B^I~Pe5qfGH3+AC$>w5$
zH<c_Mna7}ox2w=^*>jVjCg&~Z<4@Ty&~9#nNO{OHrl9EJDJ1&n3+c_;H?JRz#zeSH
zg%8zfxcW-gn%|!^4qvjy-~6=v`+2bWAHSfw3%TK=LF3n&g@55d`^w&!!^`8Y`GFHZ
z6#IlxVdkKYjp>U{tcx!25|(EM${3fYKm*#=NOwedu8p8D3GXr5uoBaQ^u4D~se5_L
z6Nz*e)b^W0XC4qG#nw+w3%y`a_!-V7>8635n9ScW4%6;wx~04XX;(C=x{}crP|u+%
z$GdH^=zpR=)x$RtOi0QTuR-x5Mj$qU(QH_&X7RPtvrRk0<!^IMTns0r4||^UHRibz
zl(?zW!%`k&$K$V70p`5lvKI0_h-*FWbCSq$_QfSQOb0tsO%&ed40Q8CDOrzSY{|(W
zm-F#!sB@I=zvyja(&e3eeZ^BAUr?#--Z}eb>A;s>6l#*qCA3(7LsTl~ya`{rE}8Vk
z;Ep=+&Q}(01mWgk|J5`(wj^|xtG|D0Hxx&Ub{xj1sA!M;4<uZ|d}mpi*Zp*>O-`vx
zNJTYP^vpoLXiQxWT3buo&vNl6NtsBeqrTKF;N~+|i>e~6!vbJ|DWNyz=O3=4W~#}0
z`D7RQ>dGA!HOeeJ^^ry-vGneEUpapFkLI0qY+Q>YO4V+~?E_LONLD8OxA2ppB<!$6
zq+f)Z6h}O~Rk<*&K3Lk$BowozE>!s;298XEfr_60@lt(;)dO{>ziztgHeLj#=ZR!=
zK=+0Acp~>c3826Gae_}*4+nD|0_^NOQHGHwN$sw;=53T;0ElzrLKuVR<cMa6CXGn*
z0%T|8o-BJ)=6AGR`3+hS5O1;TgcQY4*dwvH9y$y|Yi?K1&DAHukF_|!A2k7hk#!9y
zyH*5cmkTghyl1SWu5_oIv@@WeWTZ6z165{znpkF5pjm$#8U42b?EM!cMV(O4q@7?X
zo$ICvKg7%AI^qbKOB*Z+8B!zzg7oT~!KdqW9L>cAPo93MyM@{HdwIk_Bz+2uVcKbR
zL)6R8oH4QLqijxzaZs*W_Escy=zgYN^}K0H?{L^UN6cj5m$cFEppPcc(rGF6E8kaN
z)f8Wn7)-In3zueF=x;UsINeyJyjrIsuWy$WI;JG9;crvp#vzqR>3;{EQ^NXYTd8A5
zTIK<r0or3%{{4?;2duzS$P;e=P+_$M;<&8jbE;M3G26(h7TgB-P_Zirc@@taIt}N+
zk-&3h%M6KlcV{bND7{O9yN2{EEz(VChC3DK$Pm2^L47PzoI$?@l4K*2GsHxK5o%G|
z&;CN!uWfgKQJKu!{pmVAQTjip=KaP3bXy_#o71oT;u^92eu*I*6--N<eN#ey*qV;p
z(l?E?Ouu}q>KDP!Z7n%`=CaR=|9WGjXZH8Q3)^-LM>ys(u3~wNaRsxl!UTvm4MT<p
z;bmG@HOzsBaW|09*J`>5maqSTT*s~sB}9#Nv#o(Zh=Qv73!n{`Og9MHx0<oc;yct-
zl?zx2(KMB#(vFoxIQ<Ms;J(w|3G1+1bAmKch~0DPbqz9jPGLBgos&H<nQqua&^r--
z_Z1==4$Pcp!<@jaQ{-KRM*5eLvslTJ5go3JPfB#Ya!H43#1rY%b3gxLRHmZlW%dY-
zbEKO~*aaV9m46*^eNWOiZ+T!#7PuAi<SpB;zuv2DdX`rw5BqCyldv54og46PB7de-
znXK^U;``AG=ULnn{znD>a{Q=&a|Zq}To(iZXk26aa<V&v<!*YAmKQLt;vNN8u!!fm
zQbFnQvkLBgLbLY70U+VOpn!it&4suJlOE@iA9VlHY`Q!1OT-XH&YIvaxcrH`Ke03D
zJKVak_7cmH%Lw>;?h1UZv(Bb1t;kKK8CI;667+;cO*qBj$Mo{eB_0!ZrEuo5wa>7~
zK^j!*h(PUA9<{$iCMM5MYA|Ph_wkh8Na3CwyTi*tv95jOi#!Jj$#t~S$pT<Bd!3!G
zz>eNZh>N00{e6-1fP5w#IXB2wNdhsp%M<&7n2hC{^VE~HM&sH^FXqJsc6OG@^x0nY
z(Jswiv7<DvjI6w`Mk*xDckv{g+%;kK%ZKVx46m$v7eW-e!wSa}IuC%CpXYeRKt>je
z$C2JduYQy0E9;p%y-|As)fc}$?H|1hm7&7#5A}@9uF%9aHj$<#_C`1Sd}bBN#)P(S
zzfR?UCjaRfyiJC%@ht-`4~i{wEiduT!Bv|Fxx!hbHEFoX-Gfe0<`wc;KiIvb1Qltu
zze3b*OaII}Kh6-XQH%0Ew5|E;R-899W!xTg0YXUKTd_XZwB!=>g1-Xg60GVpbXIR4
zBcq;bcA0lbT1l0FP)y~E#8xN6Op2w;XOj>8QCUbWju)4{m-+NgD2gp}^r;LXj|+fY
zSP7yG?>RxFUw0Y#TzOF49vj*Kz39h6kdvJJh}tMFqcD7}OAPDTTS!s_Lt9M<bIBJN
z<D8p`-KB?>d#)@j3P|USxrLxAJkHIM06IzWK(-a)2E$IK2!w`Z9JHG8f0F)Tdj`qh
zGh81X$8D(||HZtJdi;5kXl|!0b8vd8>gUd$#tZ=?sbIRRxX}qu-GKt=Q=}(toT|+!
zF!TTL^0!R)orjT}>Z9|<VHv5<<Ix$~*E~s5SQA}5QInl~uIRw^oH^g3g5mJ{iVSeh
zu$giFr(14VtxQoxUlA>8VBt)LvQJAqwl<FY|DkK7`Dw)I9`TFPMqO8J-TaM`Oli+_
zSJQ6?%ob%BPnC%`JChMNC%+EQCec1Az<yJ={?4gvFO@j6m_$oW2n6-kvzm(k^(9yS
zgUzgc{;63C2|eCrZr<bw*p^V@L{O#iF2p3GCi~hJH_3RPq-`^X%pL(iDL&oiN0Ql(
zqw&`%GVcAO91NAoMvC2z`$0OU^p|ng&6<A-)Ty<^nze8BL#*h)!np(DNBK^|(_pD{
ziutW!0g71iOSCytyPk~_!e=;Oq(H^7eu5#t<&)_8R&mxVX3*PC^8%2lUCN%T%RlH+
zfdi3L`yvyJ0TMN*W=}2Ojz*=xSp4+h=#8~_azKi(tK8S{3u=~(a{3t>yV?<EY}~<z
zg^d8oh|`U#z$VRl9g_tx4CM1T7L~g1P=C{v%`b`F4(xS{`w@x1GDaQqX%3K^D9tr-
zEnMzaS4+0K=MlyEBHod+)Nis)TT1#D2hokpfH-Hk%PPADSE@$&5q2Shfg4`%%A|!3
z{Q^#y%&6XirZvwa3>vlolF$jJ(kQ=g`}E8nu~jj0(*HZTsMp@{1y)ucC+-kD#xp3R
zX<e~JPnuojPj=%~jB%FwOnDt_cJHjup5hgiR8UyJS^83=5vKK*<CXFrLCr^mTOr@o
z3r&h88k4fVeHxz!lm~__pbMcEs(QD++$}}vq7HdC{9FxZ84gqfGrp?ktDgkYm*1Z!
z_`OA&O-OMmR@Xf1IQKuhDTGBUbMScpySjkC5Kzr-4M?z<|1SF!*f!Ud%QAWA1_!wG
zE2gv(JGJBwB2Sg=U6&Zcl!lp<7~Sn6bqjYw;OpA}`bCB3LX;K^C76B@zb6frdqgMQ
zlbJsCm7)h|C6fD?#aWoYeoymx9xEa)Dt3FWvcxuCmtFgGhVgTPq>@F9g3T?C#tPR^
z!GJqUlJq5)`EE&%kw~TYg!xIr!0qD?%GYd^v6a7NI4wcfIgbHfRg;q{0kDIS$vuAj
zA1KX&P~vXVtzyZ!=RGoAw|vjBkLcrlGbPSPmlr@%=5v^>NYn5&_rstD(1ef;2RR73
zScqwQ$H6K9NW#Z)yR!`}-E4Doj;83En}B{*xN$qz<f=RW<Fs*k43w(y_0i%x@Y!!5
zri!#&L-Kbrj4ONAs|k8~Mu48^`Y<^t0YuzS1UEW*iJ0Hq#cCEC=~|Rfoc~|%q1RO_
z^q6eKe>pTkYr)rlH-k+l=^VN)L(f-WD($luL3dwDJvu1nq<wzb|B(@Qhx$K|rc33y
z0qY40dN;I27U+@w4tH=g*D7LS!^LTmTbijJfo~HJNJjiqz@+RtWtf8B7fcO><Cw2O
zZ;0PbcYt_W=XR^DZRiHs^=MM7O?a)eMEvixro#_4vx12~FqhLIzPZl3(}cua<m)hZ
zN}IGLCnRN}4y{F^znK2b_9bkw`{1Hz`kFv(s-Ys$h?E>}dFk8dO$pofLL5tGgi(V}
zSwYls;zTB6GZoLj0;+tqL+Z1lV1f#5@dLr^RCSx}P5`0z@RX#!mLL6?qnb^u5bm_u
z<xy~igf*Ah=p|!@`A$TEWXI*CFXN{OT{Q)-DL%4ARGTLxw$wiM+Ve!Z!F6e`6uv$v
z5EG*tG+)-JTptU2Z5Q&sN+|Qbv6R4HSGpwxolkc~dDS*`hyMj^+J*6#xtq^yAFUeW
zQhb9n<9Jm^&_qSwyN26h7Z1)Ud%>tzMU#Mc^zG^UJ>&D|7jOm2M=`P$&yJc$CPFZr
zT^5suF$=}g1BGbGKm0B<&<f5b0P)8UB_5|U+_~Ns>moW#w1*xr{5=l}YJsjB47amw
zI>~2sCKoag*Cc5<lIFp1nbq;Y{+O@VyDFZ_-#P=@VdCT8>$Uy^o!<1tb%{Yft3Q=^
z)8BT|2XF&wDyRgnid@_$;MOx_K<Lj36BiUJ|LQYiL>s-lS1zxcqvopG<5bnLU$>Qt
z@TH;*DH6BuNX&(OPS?2ZmMSZp)LypoJw=EWAIb>`s3jwP@wONCIF}$I<d58N7TPF>
zezI}3Nj*MmnddF0edm!WcQMn?=&-MWi;s0Tn?!e93*$%f!M7d~?<U3d?8=u^JeX2%
zCX1^sIemp?rA`%kdRbF7Q%n;KKQHCD8C568x~GhVUX-#l2>xLY=$Nk1=+#jTiX7Qh
z=x(_Rr#LdS8p$ylcG5XC46j~?`uY@8J30L$<U+_s#mw(N$@GiLL&c2a`b_W+ViwcM
zD!5Gd5`nC_(96<&tMY2Lf3k-f*gumQc!vR+K-Lj2ZG+CDQ}+dH(!pGb)%U~y8x;%m
z#d&jINDj-OL&m=aLZ$uM?`KwYC_c>Ft4TZjez(&=yzBSqwu&-QtpAm-OMvxaCdQ5+
zf@ND|_IJNTh)MfK_C@3UuKu(2pqw2kqRWyD*?K&ZKsNx}Jyzcj7TUMM9OyPbvaDmf
zp3B<0wpVY}Lf?fx#bUYMpe`(?U^7QX>8G~*+k&qG2q2XYj6Jp91|XUL12w9P4*pc^
z;!dR4O;WDC@za#OU>?Wh_2y-gO4pm<13+GrG*!HX&l9jZMU&*vGs@WFo#?TUD?-0~
z@j?Xot;M~!E;*yIs{WrjLH@&FTk+xa;Gphz(xoryuQEg3=LEFxjqM1&9-5q5-vUF{
zc+j+^cB{lQEG3Dzr3X_++k$RH<obgL^?`Sk1;EfI&QjVKSGt~9zRFwz1X+ODf!|F6
zl)q`FFM4HFOEFvBfYfhVh?9Y0w;YM7e2EJ_ByqZ-md65rdw=|K!zMcAYc}9X$ZE;H
zIg#OVkoaM?rB(ZDv+6n|U*IZx{z=uH2Fn#8=lHL(?~kJP2_=GY%6wdx${jXMzqrT=
z>Mij&=028mI>HC(Co%?>^e=C!(|dO?4=oDAd@NIKA~9A}3`RFGnbBzjupRQ_11F1!
z;o??=8VX*`x4|x)BXb9=eLDO#G;)Eki&o*9_M{Ta(r(Ec`;Bev3xYjCEM#@{E5C?&
zqfFs{pdN{!;Z}83w@WCt^~;U>f#_msqSQ^!o9&)c5KbEh(?!{883Zb|zP(sd)Z6l)
z^QR(gkMBnD@LQ;GK_Z#lY!3H(Y!9lHp&V$w!`N)omBEmq(1nh7*k9EYtH;y(&4eFL
zuu;uV%sH=@fhkNs%JaEXq4n>>&de!s!jSVEyiR+(d|$Y;H0sxGcp)sJH(}*A7eF~e
z0(<&DXEB-)A=L$Myo?zpvNG|M2_mS1Ztq2OLw(`#?o0ieH`=cBE`j2qej5Jn-#D&1
zzdWRtL})dTWvp)gn-{hOLar;0;=VZ6rXr52aARd$r|R98pO-xYUdC$To1X>xlQTVf
zq7)|~)v~72ir2FMfuO<S%&s=mbKz$iF>nxm4*i_%JiZ2a7^}_zS?wDXZ6*YMk+OXP
zc*=!kOnKFpRpg&ypTJ**p)%6RzHZMMqa^|1%oeAyQ3pv#0k!TZ0ub9hyuwV_sNqQw
z_&*SkR0?=`3$O>((n*_2s(Xw%CY}@DMaMx-ICo!EN1quDG+zQsbCwwF#MEPG^L<_g
z!}Ceryz>`navkB_B)Uq|)?T;}g(E}4Q2^nxre@086!@Ga+2vt#;wL)!s?n!<v-gVQ
z7Q*XG^)_`=jo7_a@V;JW@7n8Gkw;xBxa&c~Yr^}ltH$H!9M-|RAn;XWN%*(&%K$9Q
zL%T7dtkDB_Spbb%VQR(i*VoG;=ov6zspc&u7!D%4C!VlT0Ft3DbuaLM;6=ids^QXj
zDEKr-K0|ThE%=n5Xl8S;urt&v<cEIp-O-C=Te5*e{fv8z9a8?Q|K5A)ZGZ!!7|Lc&
z)}py&e*_D%!a@cm#U2L&24pAjcBkEOuCc(@&Gv*4QSNSWf!WPDb`h5W;J{oaR+9eI
zoGb~IAI}p@!5C&A3yIa6lDoP*mO8u0Q#-j=2WALF*>}5Y+$<=_>lU<f_nwayH-sFz
zzN-Sn9S+R*288$}XJ7A{O1=)#+3{Eq$a&N`yxPEiJNtWkt1vC_brDYJ(|I=`pn~~g
ziBGE)5SnO<wuwmaE>~|F)eDOnCnJpyGE*dd40&8n+qD@<2heE?(LuqFXCK`iK)U9|
zx$U82(I5#WJ!*Qs`ZohZu%$os5&GkJWEa9v{ap<vRuttX_aER1u{Ug2u$km$A1PLm
zVVQE&msJ;Sk|h86Q<|+w9&s=zm=&U+&Jn5AbRU}U2(M9-X5lFO#(Y;mjg!}xo5p3A
z7{nQ)3ti=C)kb%)C+s7z0M_aAy4!4FQYdCYS1Hov^vq68`Qqm<cfbm=7NpLJEpStJ
z^3iurw=nNX@H#Y8I~-TOJ5|M0RJ5$C*oy^z-bk6NEPLf)4^+H3;D1F~$EF0=S`V4_
zqZ~!jdt(|}b1&vKMZ^dH>C1cfj5oy}=>;rPgd{mWy3l9<&$Ykjl;FWdTy<f*EdB1^
zh(*yZpA-ikQ-g19$gkE?`QlAnQrC7BC5tESPGwQ|Mt<jO=H2ixP8Z6{a~5-Z3nmVa
z;SKqd|JyIv(S%s*Q1#RIX3lv<m8ol=G}EuBq??D|Q3tWZyGp`<t{M>e8uXe;dFkF1
zyn9*6IeK{&*jSv0nPZTjLYjWS>Mb9{Iw9`EGO)M#PEYmSefG(Kf^_Ud^T5ee8OzY#
z;cfP5ZXjQf=15tibUk1AakNL-;2nVemb|fC&z)jtTLvI<$`8SWzs2{)ZGgGdw3_sj
znCxtwgbqdjiHM%{n})X;(_8sWG!ZVt#Y0CTx;S~iuB@M2|LxpBP4|c!?iT|WOBZk$
zzvv7-TULgz$fW|aZXTs!cMmM)RgCVcDfzY+`iLop^Z)#<8z<1Bui!C{9E681=<?6{
z#GnRt@MK4FkpqJ%g7eqB9K9FFzPXYA599=RE{l{;N@2SwEEZ+Z+smbNJl1uXTVgcQ
ztAeu##$2mlKPX|cSD#~nrd3c=m5+$)M-D}tYu`BjNjp^Jj~n*1<YDe=J?$B)=>8m1
zwMBgfoM6hHz!I`y>~6u^dm%dT&L7RfIe-e-`!~oiIopdh-3vxTYwWIs4v!9t;4R2e
zy5<g%@->Rz_t)W7_%7YW>!uC-XSSFMtjo2nsgDM7(C#)w#xU8zfE_o5`wxsd(<@qM
z#`q!78gfydl4S4=*&?$t>~<@A<Ab`Fqt=2snkG8O(Uz#+m(SgzX20?gGv{+&3dPby
zQrqD0M4`U{-JJcz55djgj!qLD+Sy}1r$O_&5^TfU2IE@ax(9bz;pM7QcM2`5as&-F
z!0#@Hul-)%RkrS$YfV5mejqEf3tBD(9%uxB6SXTT-qTn<-CO^EwyROrBUKS(6_p&D
zh*5&2dNn0Ohn1+R7u$YR<l;U7$p$zVh>EDF`46O*w^x6_Y9-y;hdrXW`IMQspR@i5
zx*|mLy~0X@oZ?W~dTMzL*1h#3IBl?^iOH2<v<lK`0JMH*XCR=|0&Y9)N0%wc;hT#h
z2AEUoW)dBS(~wtmcHgPH4R0AY6EbY1+2sdxgZ}e;BknjC50ee;3lMj2nKnjgnC=vF
zXkMJ3P)?2W)nqq04TEQmGBO*s0ZaerC9dGr`Arl^_NPh0xw+WAt<ysT$BZky=0$ZF
z{ekQCcNeRuXf*Y@+kYSp22E%9Ky(QIsJj3r=LXoQBmr4(N!d+xd~LeWY9f+h*k@>K
z--Kok=d-2ko?vdcr7^|u>fI6WNTRxGJWt5(WcDYX=^I`U>A%9JCQ9uhWot(61B0bv
zX>j2OvHX?KTeX)HIZ0!GQiD4Qumn+G>(!++0v7-~%dEKV;OiKFdfo@I1-5om`k=UB
z*_xA+Zb43@jJXg91@YSF3gXcare}JM;=^1j^z`kLMT~9?(lJV3Dw9R9$%Z3N>`NQd
z$(GKOs!V(0`&T!&hZXN_aYwUdl^CcDFaJ51{kfWW!u(mTE1>b!1Et&zHzwm8p%N>p
zOs=6P=a=~d4h-2sownvo-^(i$kCxb49juzh>$5KPAF_Uu^4+Sftm4_oxSsNWmJGmE
z;<-qyRKLnI=wJV)9Jx_})clzXdaIG7Kc*EpTKww%xvPS{lZOh)nK4<38E05D*;)oG
zKacN$@PvH7@E^27^wWcu;*m&hEo&pPUv|-J#w@^Kgd4uXnnpwRHAHUc!-5XHM^%7U
zl?k@ja{3JV>%+=_pxU3IYr^v(mO#!KHHFwI<Ls&<j&xh8;F`L&pD6_9kq#`6P>Q6(
zLccGO=Hq$)uS`#8*42_`KKus?qsDzNsZ=I_<9WZ`!Q~*nA3XS>v?$kKf9jIk1`P?>
z*L1Sd=ZIGGCp&wI)2nm(5V}6gfI%tEx63b4X;vs<$||fjYvQwe@|@)RNEOjidD6+@
z8hny(*;XwPOYu#SO@W(1-}~j9@8$BYz1Q~}Guryjh?9YP5r-1TVd#`N*dpE^6@;v!
z7@m@9E?(25Xy!6@X~r!?zi2ncbtE$(w4|SNZtRy^tVMVzT`86-GTmo80$TYVpsD0>
z{SPEtuTz;_@$`J5E`S(_6*Zr^zF}S#BdF7XTbaHfm|LFTD$zicE9YUj<6w40vXkym
z;I0?}eBHrh2k(KQIwIxj`CvbLI?bujME)IKRPv6`tXS7Sm^zzp(CIYTc@C!NZY%S~
z^MND0KsjxjrGzZPDI7Y!IFjq{e`CL@5wz6bmWdh(_ei|{*E?FX79C^h8}vJ*a|K~J
z$v^7ZxB8qt3w=|Z+H318;)J-474<cnwz&^-zPD{ArKe7!yRGzNe0^DB^WulYua<Yx
zTQwQI!uI^v&hKak_UbGO?56m-{t~|{G>T`lIIhs5hVv10sZGI9cGFJio(M+8xmJ?0
zV#0@ykM)mOP#+Q3oo36j%AbrCautKrzaNR9M0RR|rFC}%((A5x_`EkgnZ9`C{K|`a
zkMi-z)P494t(bKEM!w3c2y$nHxMbUHEa$stTM0ZSvRZ~rrOIL-e&KVIvrZsd6qY6i
zqBOUDV9E-q9vE|upds9IgiU`+Zgl&vzC;|o3JA-2^slaPfQU#-8JP8@N8Y4#3scW~
z!|*lc;$o0YhD@7wy}(njJ*Wdq42c!LXTf_Ua0550#BzKA-&|WEEU-eB>K@7j4=Dj}
zaGp82o!j=Ni9eSXsFPLqbBgtbjU;gL6*2fp**U{Xe32Ii_r<>0y>ksjKQ-sIQ@#tV
z-jIMXXgB$=nwhj9m9n?OlzI&*eF?pPZgA7{zH5V%p>M^r4yY2_lpiT}m0VCWlOdsh
z!ly1%n4hO{EUH7XPecH8XYV`#r0XPcAtVe{Aic^NjGXj}@1^eckMS)2S5(3Oz&IW@
z4V@~7Mjp+Iq86G8QQB}9^O{?3I5GGn=V8NiqzU)}UMQOXR#Fb>At!S|TlT8lUOv0}
z>A_3-%36(}zPwTT2XfF=Hpz_@?_JH=H4dxu7~QynibU^SKnBGzFDd8$zIen%Mb_0=
zJ;3D&Ieg9n!%3q#&G7t4BLJlEN^^}kMu~PERUq_nn%#T_+fw)-d)B{>S9;3-e8kB7
zz)6$VAxDvmL*2LX&2Pb7jksy!1ex;_n3BId6Xey3z*W|dA-zVXXWwm>Jv_GX5XqiU
zqewfWBX<{Jgd^Y>`?OEk2CpZ?*x~;RcaX46wWR32+$!ma%~Kqz|ExqjsWJZV@LBt`
zaT|q^&U=?=hd;fYvV{)??SgBhErVe%=?&RjGM@$LozEy{mWLta&-E<|1hbq~LPr6L
zbXsV*D_IUCPbEZ_N5uT9B;pNQc$*~|z|wodyzqD94h4*f575Mc<J&tEc^ath-|kXF
zpE5A9kM<!E3kfn~PVdU+L-x;gake#4G&g4f@pgf+Vg#f_{wcfa^a{Z;W*<7y#n>U#
z+uj9h(rh8nOQ%=P^a|45=du}ZW8c2!So2Vx5|?wWD@HnQr8z+?SJOQ?8qLy3-(O6b
z#M#ocT013XbP)oh5K1@Jrw0>Lh_~kL-FP$Upo9iS2r1kBv=G@<O7<M%UkRro_H;fU
z@Vc_|g-no%#|-f(3u(<KGIFbI6)T67wyudT%()H&hQ+@G7>KHK?ak?s=Zasyw8dqs
zlB4|A2)*v-xLR>ZHcEu;8BAU*r`@W+ag@_H<M<o%vldA079Nr~4N+VfT#4bP&rKY_
z*N2-gh1m9|+WZ>W_5`&_f~Ier-rf;{-1mJ{kQlnu9TK*EnvGMZY*#MXHIkNjYqvX;
zd7pa%y6uVIz+2!gtc9mh5;XId9qcJOjHfj*>m5e;c;`uapo05hgA>^b$;+uKMFC5<
ze;zV~pQdO*<mg~dva2Cp+*XW|5%4OY){fTs66ao+Z0`>^5r%4j!lYJ#C7#x+R+;w~
z3}!cES6(fami1@@v8w|sGjKID?o>YN;8bh<h2BM618MJ7GE`x4)z;cuAD(`GduY_?
zZJ((jA}o>BpoHb%?)&yZ5H*)a?%>36mqUX{JAWIqXC}JfL?`Jf6c$i;^iA1W8GEhL
z@zKtUEBD8HS9{F^FZQM%eCGwO{Qu&Ir}mwp;-3C&zr}uNelT=@rMUez9uQ615IlP}
zsd?b=_uSq4?x`9+wp+a!ZM4pmIVvgUn77?}3+K{2kVupl`X}82fq(d?C_UjyR+1wh
z7iy_UvU=xI#0XaZ>gue_fhmo-ahf^z?cLQdC+P)49V|70DLatxywbJrLv~$~{Soy}
zEI|%oqB|0CsI;8*TC;R3(^G<F{G*nrXpXf5Q{2PA4dhfp_8YK|h4T$SznYmdXV^Bd
zSZKgg9ZOBgw1#`DX|X<R9!t7W%DGhs)`F_P)Di%ntFG1R4)#0--BS2%bTpnx(*IN1
zV@yRs4zv{<SvXi>SKu2=E=2=5_sJO$?C?06e7Z-^vSYR2A6O5Xm@c<+<{5+@S>5So
z^if!`PRRfRcA&uBNvK%}mHMS(ez^E7J8|ASAaWOneA+;><&zS6opQDEcljIdgu3fr
z!=n3Bgz)vT5p;>nse0|k^Dk+@23m_>nx*|25f#BA;zn1ap?DA|Pb9C9teJtD*)1Qo
zrwbsySq8eb$Omqp-DE%$UOHVog|z;BM$)JXG4ReULFc2~b_F;PhHWc)nJ>-KK?wJt
zwfHAubEhTHw_o%{b5OQKGS+W0(o*06uw-pjBRA@|=L<ybTNi#<x=T@U;_z3W5@)+>
zea`fR!CC^kKj+dcu|T_J0ObN4<8PPINBr<ju$R<J++Qb0Wz0Coy}*su!{ZzL6qYjZ
zNDBHx=PXc(EfCdAca`gjaf%q0{C*9=AI4d2`{wvVhU-5N`3RtmT4L~>REz3%B@*($
zQ=I&vET}9c?XNi6ATlRC9e&BJ&MZOI5)Kjdy}2$Qx;Z?`;B&`aw?*1le9V8|IMtjq
z90VXDR8T~=p+{AW*E)2;fl`IvY3bO5wt*~iv#;csg94fL@4j~i_XBjg_N`oZ6_!J*
zZK_2QM?Mt)K)W)()jLB7?<))7`-KWZNxicRZyc36?PYU!$6{k$w`Ush73V&sM_}9t
ziZ~#ZxR@fj7~J^JkFi@GDne4vY#!yr&2vUO6d-Qx-HvS0!cl+ZRa;;_o`u9dS4(Mm
zOsY?3{QR)V%ZF&mmG_6&ucBPV2@~;-kq_|3zd3udYmif@B|ukSgn86XGrRTk`+gt6
zMQvTIW!|O4(c*vA9M$sr!OMcpD>+C8Ay1!=fu9$1FmgtiO&9`M$|nACK#>%vWLfTQ
z)P*_Y|G#oA9k=M?|2Vqpu%`aEJzCnJYZ6j|fOHN-LIg&GgrIb{(t|Hb!$4AMbf?lt
zC@~Pp(J9>xBgW=?e(%3ryLKIRKJh&Fb4LlaCW{^bZ^kSABqwKQxf@hNCsgfyD7klG
znvQ$;QF_4&xkzU1m-g<;Wh3a8hlV1$#y6VTZ5lAdK$-8`dL-;odq|bmMhg`|p5zmB
z{dSU^24K@zJC|ILK8_}ovZ-#-fB0fUXZ}Og9Eb8@a*V=4RoacKs`o6Ju0lKS*0Rdg
zJdw^lv0$Z{t*>3jZ2>#YMWOb1u=e(9$=@@JXA`{WZn1OQTIt{aksfJF<&ly^Z2Vk$
z-nu_1UD6yG{SWj;&MJUyGQPw)VfLKXxD)VZ^EGl2@4n(1V~<q)+_hOYBGRWIPq#=%
ztcxtA`Ql)VWIvV+pg>VaZplIygoA-gdbnuzv#qEnQsLqf<x>?jk%l`NRt%DOZMB#i
z2saJ5HeE#IdId)UCXn+E{0u-qjd`Q0^%w`_Z1lXGB*JG3Bv!P(k_khzeeoZJoN#LN
zaL{Km;Tx`x7L%6mKIPt7qd>M?0JlxOSmJX<&bno_%Y4@hhX~?6-AP?5I{A>_+&5M(
z2{~ca&K8ExkOTNhy8~4nxBP!a`$et|qb@Bt7T@zd;#p3OaBQqkbYE)i0F`kkY(3%G
zoR>B5+)q1Gm^FEHGx_W9$cj($MW5`w0fc^gb7BFv8RMp3SwwA_<X!#aTj6~RIU_fq
zbsaWSsMN6-7SDWGN37%Dy{i(st%9!S|F3SK^|--Pw{^y5gq<re+i+LzmG>j?h2}YS
zku2)EVzt%G=&>GtQmp0n16L#iFiosgoAv#sc1+56$x#izZ}}Vc(GEK1oA2vt5ROZz
zggX(wXydL0nj~}o-Lrq7%U#$i)09ONke_%dE<GjwbK)U#jEb*dyO(0_hB(kwtozZg
zW+!Cu948Aa5<U$8E0PRLA9{1|0Q^S0YxQyRwg28dIfD@GHsh;w%})SosN+bHBga+Y
z--48u%DdKH2wC@R><FBsbgZbqsbvU;RrBu#0451TlQxLAe2e5-t3yQ6=UEEJKg;!1
zCsLBdes(dHEQ8a(%v8nil)|^w#kh66Ly+>(!%siQ0tvnIOe~R5^R1KxhgQNHo7>D`
zTwfduwn(T3$RO6LL3OTkvX-?lkzj}wY#b6`9onvHis29e<*`ud3T15+1LbHEDy;}Z
zl>pf+<E$YaC|Lb%!S;B9<aZXdP7}r48{l@FstSEf%Xw>nzo1M(Y)yE6wfn-s$t#8d
z24oA9KP-)M8Dxm6A9eFo_A8m?!++=zpwILVqypwO<f$d|Ru>m!*Z34|lKhiE%v^w^
z?<>1?(?)#HM;f6RF7MRvlRlC+-}EFF)QvF<p1KOH4mE0X8CJgdndHoy4Jlr9eDst4
zTCdPKJY2!KP;H&*&rNwK5#9H?-gi!F7qnJ%UNDaq@#3Vfao=`pJOmNB&+o6*U=yYa
zDFh8$E(Xipp0qYY+8f>kr`E@W?iueDVZ-#ZpII{Am7CZIybCXml=moqjjiK&Pq(ZI
zobwKrUB3m4IXjQ|er@ZFC=A5NtI*+#RQgvbo4jt8%lV-*^GE&cfE*(zWw967wLbq`
zz6<LUab-e)lh3;)0c^Ceov;j6k#v;2mKwS>!Lu0ASE1`&*(wzyu5cmNHggiC9PqJ(
zJ^G`^4S_b}1$W}&@<Wjl7N3zL{uj67T<_U03voOdTMm&;^GaS|h;BdRyAF`Uyzf~d
z1h!JXMm0G<fz7BPig}x-86+@8Y&|sH&Vv=wwwQ<T7YzD%Q!_Y=e74O!CC5tQ!7lKN
zR+@3^%H)xv(16c06fbV)0CNLjfZb={A23L8CE|;_B!Es{<=p0hPuO5Na<ePcH&IDP
zo{FTKdz=0yB(=j@Knm1*$zLLSq8iimpJ5vU-UmR?Z42kt<m@)4h2Tbq-Dt(c2oSwL
zqAr$O*t3COL`?#z0Vo8COv)!5ai&ir=XO^*XKNn;ZPlefP_q@RLrdZ|l=DMg>|vN1
zTJsI$R5%5|qRW_GDku33U($rS&$=@cUEcTK`=Q_U{TUi@vFCsiSoN5A3jmr8i-z9?
zGixY+H<w745E-D3^l_HwNX9<X2W6I-erNJ~Rj0f96moN;=1j2%^D=c%sSWhG7B}I!
zN&g+Tu0NQz;!$aD=~k!prCTc7FlS=IEZf)J7c~h#ym~N2o*F$|GOqbnrl;^ba)y#D
zW-f^Ms@wHawm!K-DB<jCAn0D{(Kz(3ekozqTl0lrZg%%k>l3vA=Qq3j$gAI--4hMB
z9O1Y)ZJE1>q*}53iSb!5+7SfAy<8U$pyeHecdFAyw<x8|=Q{7zCBn_gEF0bk-SrgT
zM(u_oaY(pqGhRZ5n-eE@9Ny}Pwx3a@v+q4d40F;f%`VieyUQEuj@gc}GKg;|*&g_S
zyh=j=Y`>7h%F}-!&Asl{oXDY)@Pkssrn;M((z@1s@Gc&x9VG#<&+Cy5s_BPmudiH+
zdFJ?kEm=0drn%h$D4Jit2_!RY3n|jzR;aNAi@^r^dbbMmE?)t7+i+E(h>9pPBuFoP
za@5Q(C9n~npHc~Z*F=pwn)mC>`Tnh^)NZXx)G6b}I(9!Z4(2Q(eHJ;U^IRl22)4zf
z!m}XGIg0jUn=3b!x5(Q3^0;t8oJ+@v2%06}n!B$_w&E~FZZ(U9f24iS-RXXr`03*3
zFqGv{S<gVJ!heNd$iJ-H_V<ly^Wwi~HX|8my{kxpSE26*i>jkP+J@mK=DjlwQJdCj
zlNMe4iZAKS+~j7*0`%l$#+R~E2QLU>GIp=c8*fHyR8(CGDbJlK0rju0)zbzhz})CM
zFN6kRJL!48a(O9k>nbqm9kLRuCts2w%(Me+44+;_LHEHeptkItV3pa79>&qn0N5o{
z`q0FOBS}ra(dGQ~SNi888<Ms|It0d=vq;I!@3S2wufuxmb>vuVI*7HX#HGD{FSmE4
zl71`zfmRY$o&pR}iFBLl*4kN29FywA#WdldFQ-uPQ%eVX+?#~JR55ZayY@yn&m_<8
zL>MXdYav0JofP2XSk2xvo*F7}!{P;{WuH7CW%%wLK9!c8*_cm4=Z;v#Bh9l>6};cX
zED(GST_}jd?Lu2kzlxj8X%9<i=aBi9*>rv}__bR@x+AOW@xXpO`KTWc%`)-Tr}`gA
zFwdTcCBf;w+edqhcvsGA*1lU7N_k_2(rS?QchhD9sGUNVW6*_VdkF&AYOzZuu5(u5
zGlH+t)s8c<T$YstSO<_Kl`!l(OqlQ2)<!m^q|{}3flNNQGe&&$%D+;Tx!^}LPsd{p
zB~g|3gP7dOi5apkfu}7#0~O~BPDNoXfAJ<yM|TbT(rS9PIu|asLZ31EK7>s5L;i{_
zWhM(R?(mnR8s*N*LsDRNZ<E_GufF*`M%B^v%0xmsX%Kc@3@ct;p?yl&j3qO@#9+4Y
zV&46-ffb`Xa!OaPx#4LDQ`Ec$&C#UVWF{Q*d<wXT58=1FF$&0%h$poK*4U~sLWC_(
zav8pCSWNU^rRfuE?4D!exWDWaJiww&#@EHVu82VIss2@M@Br{ULlZgv?TdkTm(0+D
z8jx;`=Z^^k>)&3%8jn=Em9Pn+Lb=Q+A&m)#9Vxr_%U{KMU?riTM(YbxdY!s6+-o`>
zd5LqCZp+4<-thmH>fyUeT@$)qkCREV?+ueznFaTLbAh8B&5UkdF$H}B=$5@QIibvH
z%fPtBW%OESW_lsSj0Y`C$v$}$`X}HGXS0$TI=94<yp$hvlt&y~_-9R)5kgd~ngiMF
zi@wrvQu42oT>1{5N$ZogpU$u!hzn+50_lp6f!iB;z~}%2N=np#$pYR*>G5>*5TQAG
z>GgLLTg<HW3_~6s=OlhmTDSF7y&hi0d8;)zo|LK#I{Zwb+L)-JFXRK`C5;53h+2^G
zHed3r;V8F7m*~3=Z^PpH4{z-kj+kjR9iNAv?>$p<VN!h4+R&ET{N(88Wd%^8eB>c&
z<WQ@D-ClyxGWOe(TmYg`P8{p{1JU#a+1jrHQuisfKHqb1^zSaoky$9*69h)2)kV8`
zn@1ldy#gj`5XHdQ4Ic4yh6Ysf>!%0P_1}O&EsVq$>R}&f)2qCBhwZ9Rj2_K6fh(i+
zr5K38M=8-(aHX0Z*Qa;SSnh)<`A$7-hyuOptu}vQD@7NS@TvBC4D`&$WT00L@v;=#
z{#uWEF8Y5d0s0zx#s@jFM8gn_-k`w)JA6bjh<&PI^G4y%Q0~tFR6;5KMT5Khm$0gy
zahDOuQn7{SPdtH{QyLJeoW=g&Ww6c!%t=#q=YW*8r8MXL_ST$ZTmYFpIvyjj>YO0G
zo(Zx%d^(M3Qd_hx28sw51+#a_dwi7WiWRRJ0@hoAuiJp-AUMeb4OiA9=jxAm7b=67
zvI8GvDq&kzdJ=+FxQ9LAE4u10GQ`7C|3EKjR=({MMc5MHh%{Uq)BATLJE<sDr)9pn
zWJQi@y7dvTi5+S+ySD&Ji9XU|OIm`%*f1<0U2;r6Oh(tkgZpbucb7E?#C|S%3H#;8
z#ZW$5;~wmc!x%+$-*?M|^e6Vm{1{@wnpP~n=>Z%WUI-Oj6cHNJ-8T<!J2m#)z~@g#
zQ%1RTU|2q!^N*s9GKPoetPf`M9GMi&zfP7xmP@VpI^zpT{-n2F674V<M~=CP;>&FN
zzLhbGAQ|R<aeg&QGj6|n-66W)l1XT+1?l+_w2<;qz*Dd4EmLgLh)ig4#cx&~PEewg
zJLHvX;UHl+qFqx(Nis5YF>&J~hp2|z#k){JTl5X3<@v!cTS1u#>^GwRAyQJv5_Dg?
z+dlSC%A?849%akF*VLVu<^nBQG~DV$YRRAZ?Y>wU{*O3&9kA9f+^a%v)NxT2CGc7p
zZNv}0&kMY&ggJFUynceN+;NQ}HR6C91~S|FvWSBnRxZ5OXFNMW-eC}jO{KpqPsdnv
zZGN%>BWVD_g~<qBRG>?qt!0DLF*1eZjyRcV2%MryQZwI-4mQSx+<yeT?cAc_bBoVt
zT}9eYG7G+`AT&+Ekny|pALIvgB{IS1+mh|Ur^Bi~S!rupDp7Z^{;;HYh>q1qOKTu{
zF8KLj7Ktu_e8np<UvFTykzg(v$E&(;j<fdLLOER}6eSul4`B-&iH>}6@))pETlTzB
zq5^hW{m4?R-XYVxJ7aD`cXUAOF^9zi8{Y*V&zWPUE~>0L>WqZB(d(&LKUYEht5?rf
zj7Dj8#d(b*sc7_EK0Kj!bZYtdd%fB8)8doWr4h*dTIKhj9O-(VGlYi5?Ix{1@AxQ!
zFMcsfl&^zxl-#Xmcmh`y-L|V8%oYUyIP=ZR=N8S@v#^_5X%X5j-;Yk<OQ)aVoqcVa
z49_3dO*fph&MuO8*S+pRBT-zLa^tf}GL}iG;a-~!8xR9@gecES$t6@0)TLR&>FvJk
zb98-8Al2kb!~O_B^w$kxftlt#dFX7DC{Uok-<A^Z+a{ox+fqgw^ui2l<3ze2hTMlb
zh))k-%&mFq@(7(>gDzX*Nt*bD>h>vTbO_GGu28<w25y~(3XRlvoVQ`p$$I92g6feq
zIpw)veKPqE-dec+mX&j7LB!DQ1S{Q!$9zEn+<@lzK&t-SDWM0OO=iq6C>CTjR4I-A
z2jb4hA)CBD?mZ9q%jWbaK>W*g@I^JkxR1PGx8hCaVI6F@RD;+E*N0MuAt!;FJOqAF
zEx^)nb{jODnRAgtM1Pge8u-<(gc(ZtOw{8OHSm?cGOAvoSsxfvC?Va2QJNv(PeJ3C
zmoQw1G(3XVV?pX-SlIm9)q_q1;2C6s7=K6+2bJ9vzpkZ54t%}`(9CkMg?R*sZyRtl
zpK5y{A9gA0bSI^kcgjZ$)3lBQrm_3_>1HVCVk6gw1y=A$k_m-to%eB=ZgUi;l*0v5
zdPf*=eb(?D68Z~xnV4Kx9IoM;kvjB2emn&Hm`Mr$fqDuDUIEX!uOHD`_H9$FrnI%7
zhhctk)tfdYt0P&Qd2i+b5A*0tpv%wlgzuI1IHfSPa<QF8`S))?bbx!IUGZ;%$3LcQ
zl8g^j#pOpRUHb?Ro)4!TFVNxzzZy%PX`&%}uT=j0?$19^tPbIsil1oQ=^H4vWkO_@
zR)+sOg|2|<YSMpoFAsXRA=Tn8m(39Izu;6nkA+&{cTu4Ss*wId37G{pw-|Ue1S4u}
z<z04u_z$#~@1yl9>#D61Y~?sh471+{%C1DjR>QNLau(t#hJe5N#bexZIYzq2KuRIr
zqvO5r)Yd$v0`v^?@~cw8hQQo}^`Vheu<46nNdx4|`giA+j{qhDA8~R4a%eFezP6<L
zAE%5a*O%K^a3QKc{XM;)f3D2&uBNM`BB9-1X?fwT%=&9z$Yz_wk@WTr3U6hu%~JMQ
z#`k6y_Pv3(d&zrdYBvc^8T}@l9WC7_H@KQ2haAnP;3JBBhRFLHawh?0_!1e}<AKNk
zUTg-S#rF#kJ^Oj?)8BJf4r}zW(p~^Iz$cu~uV2wW<T!7v1v;cuORA?sOCKyq*51>S
z+Mf>qlrj&`)ZA0_VXIG?^)VgNQLGW7H#&4InGx{z&2M&)%aQE)Tm&Lr!~4h@KXaK|
zPeDr>J_-9w(3>1ewyOt5-Rf|tOs&eP6{{~Jc>Cm>zDq7mZ~;H0LMpjm+C}Y9X$jPI
z1?%LF-l|xv$t9W8ucJ#SgiVS4M}o0SaWbv7JU|RqG^1-eXXhO0<kJDT=6?(60e}S|
zJI6J81c9d9nJ@?lu%2uw5ub@-@q7pVyKfjj6K$490Qh{d-f8q4_fyj0cPIC1Dq+Nw
zJjd#WO%mi?2bQgM7s*CqMtemiNBthnDT>?rXt_Z<$`HSb<4_VGTfm)=9HSqNQ?GPg
zJ<1Aev_u-n*XgwL`I4K5`wRip@uU9xpy5}o2M(rTyr@g_ca1`Wj)j_&(L|T33cvX!
zPNt?6oX>%FL*=9$-(>j<bP{G-`S49JcW`U6iSM1KP7^!{arg#WzNCvF``NN}rX75$
zvCPl_4%y5IY!tq~Gu?B%2hF||n$B)}n_1*G*$nI8b}a14bO7&nQ9n<|kZXdrd?CQ#
zV}A?}O-U`cym5tZs_dM{jzl2-pt`<^`SriGy?dK}kV)f;kPtzr6^U>{sR<Ab1bd`X
z#g0J|d0V=dpiIZep2{zW^usGWnY2Fya>my89HXF3*MWXd(?VvIwOyf#afc4@b;k0C
zSHJeNx%~H&!N6oYNnD8P<tueO>5;Y4O#EKhf+_w<(}?#@3i!UG2t2J{^P+$Bv>etf
z#>Ha;Am`ouqHBVT+H}O6xYh}v2oHqDhiEChSkB@L@Aag<G&LxdKZU|*9EWf<a|=5e
zMV7S6@TJ`eL;>nP^}|<Vj(Rq?aeCAbEqpAVL{0)2T=~jL%Kcd;8{|o``=iC=Ge<q@
zvOH^8^CgF(#bX?RJr|l!1F>MQ?#k7oeIF`l@r|x(v~4x=ETYJ$x`gG%-5=k?2kTox
z_AbV{-a0}Wf;4-HP)Xh^G5VE$VF||CKm;Qjmv>)<n#zwz&ovlL*Iiw_(vc@l?6C6*
zk^|DMuQ0bJ3cs+uqm+8J#>k9#CbH*WY{k}udz^f1&I`m#47yi`pIOv)a3$_zJihlX
zx2)w!bg~2NANZ&BIyXov`(lR4{*gC2)o|1tK=S=38Y38G(iL*}83h`*r7-U~@Z!Rg
zb#j=Ec($fqk<7=EZ5$UkxrMkIB5TDNPq3?)+d?2DG2o^(*hp#j3}x2yk?UQf8s~IQ
zXcq3l9O=;BH-zh?WMooHvR)$mL&eHT{G+SOSE3q0LT)QCT^G3W3w-_6eK*AXGqv`u
z>`taSyPKnE@UbE6TBQnVp#)#mL#`e^XF)VeL(IuQUw=pzA+KtpAjgIu#xHC!&2KJc
z%YvCz1u;X@Kw29Pd9t(r%=;fmixTf$xYpR@#z^%6Se#?-+E?w*4m8irv7o2NljSDV
zdRkd)Vb$vHHzGV!Xp692POO8B%`=Al+D#<Q5Oj49R{WCtq(I_6!6g^!^L7LY#9mKc
zW89;z+<(;scMuqT+*rOc-^ofq&PIZX_&g~mqq@<gw|s$|7ITP#*cvKiN#_ahPB#$g
ze!K69dH}4GG6nXDqy#~WsEdTe>qu2yzy<F1#{P~M*uG!7pK*NWTyW$298D7Ks_|di
zb6UuOzFKtt(m&ASU2<5v78`pLzr-8w-1XaW;1V;pay8QorqRPUKIMuebo4R+Br1z>
z_OCq=PO-R$r`hC^YncEYI@>htk}>aP?b_2n8;)*jD4N1v({l3~_+ye;fC-}mV>0hY
z+BU$F03BJtb<LS}om%(+M_779bG7vET_L!4jK|dFj0?=x6?{zg2S(!*AK%n^`)u#a
ziqXt*Mv+9j>`~H(@iPMJL#E`C<0lWHnsyaKp0#l|o~j{@jFt~+M~_4g=PL#wQOVM0
z39^9TMp5JHEuZzL2yhR0UAOgAA4c=^dJ59ymo%cs&4c~4mWjG9JKvPVo;6Gcg*Me)
z=O-|&Jqz~4(NvaRCnmTTkgq^+6(z7$exLpcXx&eoA$abG>B_R@HLc-~&*x$Z={0U7
z7%dn-RdO|3TN(I-DNk&awskPL>wjT!5E|*N4=fjpd}ag2VpOpe!i>|*0EWIlCI<-+
zHZy?%T+Z4zz~c0aYnDXB%0qAu;(gX7fk_+S5jPrHV%bsoTLc&EU`hSa)kq)E;Z;Qb
zlIbnIYEFXZ4TDcU@3AuL?jL4KtC}mYeeOgTOUSNPh~}B_u{TO9WbHBBJ@POCz?u)i
zDw??@-ak7*0YnAUc-oOgJkQ^X+zx8ufM7(3)4=69|JaED|0~HK)+MqyA8KOd=B*B%
zofce!`90#C)iDp-#bC+IB*7p2;glT7JLV|le^s%pSMGq;AsKgnSX^z`n;m>84i>(-
z2U&e&9{dXmP+mq(+WvtEVM6Oh?@vl%x&o}A?Rt<%F&5fK1PNU~cJ<F$e?)~WtQzQI
ziU9eZ<5UoTB-@Ke2Va5lO5L4YA=SX_Wsvn*v5aK|O&LreAZQDoVKxxu96)x~)RV9Y
z2#<iI&U}Ki`BUs+ssnO0FD`#|UX_Xoc$=;s5T9;LC@4?hg`9pN{O04`L<Wu@rS{Z5
z`)Y2wN_-}QQ}dvC9hI!DW!!VWoGeBZJH-*o2d6iIx0fO?e+{D7vOY4WLuG?MoEkG*
zo?J7KX#l3uuxiz1_VEzc#O+x%b(^#h4zu(H+O`O`LR#NTX0+wf{E@phUsFJF<It!7
z7I<dj$R=NZP5<1iqYzG0MXbChQ^w-By>|}?VqM|-tX2AlO5Qm?ch3i!Nu;ox3Kxo|
z<K{z4cy-1=s%0sP=5a;z5G%Qh8#Ba2L9nx7h)OtqfQQx_HhvGPCGnqVMu7MB>S*yU
zGmy>m7pne=XO**!^?{;&{=5etRblNBcB!Jd_P5i(jJR?Hlk>wsHtMsyeVKmf-D~Y&
zQN*sn(^RdQD2wLcRHci4CzY&T&}Ne21u3w=oSfado*{r!n#|gX=>&56w?clzp^k#5
z_nE@Z9Wk%E+>3u8|0RWXEsbV2_Mp@T%?}&;KTmn?&O)g*Cm6<^t6hJ3UJ~aD`g%{B
zQ+vlK=5pDN4E(%}iO)aflM-ZF2eK(Or)APsGQA2XJH&m0HGl~1J;-v2cx}`IxFaes
z!O0NSxCNHqBiN6@UuW)V4uv5vK4E~P-tBrd7n?rIl)W1;w|=<IHk;=l(=MT1WE|%K
zxxK(Mg;I^)$%N;6dG)9G*`(YYEhywySg$T=B5v+I4A!Dv#f)iVUncDk1A_Vo)Rd3A
zC80NCxeT8aOtCXFJk=U<^3PUsZ*_AOZc1UlL{e{RZFrWh^N7Kej_cB${ei?qz=>)7
z`f0ciNvD(bYMH^Ya}!~Lr!InWo*<%aMAn`LG`^Z6C>lKkk_8kUtWV2Rz(Es0Um{)l
zd278^cZ<z|jdkKSxRmYZO$osx)iHzhVG1<{LR5d&>ZNY_?t<8Q{;vB~2?b~mdR_!q
z8mIM|aDyCAfL=qWqMx(4$rJBQG(^6N|M;>B7Ae0k=O`nyaXd>Bd|lae>S(kd#ig}$
z;$KAEX8z*A2h{}`8<b6ZDCK`7Y^Ag;AIHM#88+2Sb$uVHDpAIH1v}DMLlxp#dvkrH
zlI89isnHP;p@)%ho63hdltZt?teX56OT|g%<s?c!#Yb&e>2PpQ`>0^*sq+#L*v697
z8!K~a!&2rI>fmE`(#x~+7fu08*-zTw*Tj6Y_eR>SsP6(L|E4mY(&jOmNh=h{e4Fpj
zpwjvt;E^{0)J8FHUJ|MQ1KH?s<eiF9j?N))*QL}nFH2+XNApdAD+&rZJ8lPP`0U@2
zLoP54E0G`CJI@7*T+rlNY`h(?){<9<D@TBo{lyIZ9blkzJFfRS5feod>}qr?%Bhu0
zE~0D*5!(Ngf4G~vWqMOr%m2`Pu`2Kiz4rO^Nlz`4cQD>C9X@-dbNs{*O{oq*bU51q
z-RgI(a<qa!41nadWGwGHfkK<!tY^b+%jziU+t6c_H41rSz<TGzUxJRU-=NGar_72G
zP;}(A-n05DAbGcqTB#`(Bzhf>JCObV<Xep-zf|NO!{GB_S&Z`AcPUMT!6L8F9kA;)
zrE49Ll9gV~#Xp5jlv2C5xRvXh_rZQ8SsgyPKqMwWWiO?l$+*j|U4vB9-G|xkSKV_i
zOqj(_^3ih4pzoAs1@(!tu|s;*W)KsV4QzZL*lqBF|AB5NO~{Ay_iXH5_wzskKS-54
z`&@1lR%XRiAt0wsB3iNC0_b&mrGK_VM>5PifSK#miqRz3sAp#p8&gVx`{H`5_2|Cg
zI;v6mVMJ>Z0`v1UCSa#6$t7zL!bn=wof9P9&3(DhBs!fcCrY=;y_5R(l3}dY%iGWY
zI2Vy4iF<JK-(T~~<4j^VQ!}%LGHPDW<+L?c@vP6$k}!IW;*#B3s!jjY<YI?WSG#q`
z`O&dtbvv<4g|AQTN8ywM^G?KL7kU0!3V)n7kKnHStY2sdw*meW|1cYCj4ETh8}wAd
zK~WaNqqY>`1M(c241Yb=MxqyZH@Ui6DJ(n_NbN<<ogE}u(yC(ztoclvcr*D2^v8YI
z*}9t!BFT}>B)B#`$w;vjxdGDK|4pzf3mi54QvriiymxbBv>_khr^6yeC%0$)c-pSa
zYNJog78`{fO&`_^a7qKIMv0c!uJp%h2$u<%<Bn{n!P3PGN5Gi0Os==HT}x`=+V7bs
z+xX%|9x<!+OXbgzgr2>s>6kzj?K;>7KbfCzi2E~^fQeW*wGbm5p;{zj+$$sX!e}w>
z<5}13Byf&5j6rW@?NP4kGnpVxQt;|vk*k?foa-!vRxC8`I`e0OT*PR}Jbj-I?|hS2
zfK4^uw2u@jD)Mhh4z{bXd~LD$4nL>c{_crJm8kV&Yuqr;-IEo*h4=kc0E2T%nl3N!
zu%tQq;_@FTUG3H-kF2yWS)}{hV``U4*EQLG*TGUc#{G6$zw2)^;M1-3y~YQpE^0@P
zXW(C<^~Sh|T8a|%+OEsth+SpBSR;9#v#w)&{*}8YFOgjsd35eyJuuC0&+ppFD}0Ky
z#Ff<p!~*v&WVQL|b!HYlokFSCW}UY0xSBUfwWKKYp;6*-wqk!F3P3WeXs-b2efI8A
z4Ueqe&>9ZyMXMOU8Q*LhlLwc_z;<kGM8PkJI6{>nYXzwxe-#SLa6Ty4+B6mlyo+*r
zqf<OkaGdvHAMt*#5P)#KupakBY^xK-Ak7>JWJ4=))6RMI&1d<2s4oF$-X=;vG(v1m
zP69Ixamz-Ql5x47nv}a2*KW{<!US<fuKm#>6pynJn$6+@j-CSVLdI4*yoZ&<J9fB&
z8&7wr#W|loi}Yt&t%(L$YKAA53*VA`wkPTPp1&4+m*vrFor@3#Pb50d=bMWUVQ^<T
zKl8axCimMVzh3r9K&bC`0rOU`$@9WJP1yP^)QUlmmF$F~@jURzTGNOvmyH3uYeED2
zB~FEEJFp%rD<h7SfnVQw$tyD{=eIIAmy_k@wQgm^67-<=R>bF%cH>~Cp5qr6Qlfco
zH+@D-_;}|QuM*ZhOLK@pA<oS_*ph;76C4tyxU~t~)Ia#NzZUZ{wt!>FfT7ksYz8C7
zh}s*0>mYbp|2FyPO70&>RFTeTNKF?3QCKanr2=R;@{`n872pF4IhKYbxVO5`Fe~#`
zuKaR-y(URj0NHtm*<~?L&&|*e^FY{T1$(JO@TPLo-0rSx-s3^PrdqpqiqR<DlY?N1
z`b&QQ(x&nP7b$JXk~kiWn)jvzzWW0>(h)soojRW`cGa!T^v46ZcxoL+X(CM~Xkk-L
z@|t!<UyhYkW@DMCS}Ur{9V%uiN_Y68lEkqb9B&>|1b%50IaNi#zbtTK=PNRE6P4z}
z>SxF^^=o#YHrzXtf3X!R0H;~-paU9~<4oqh2dNYSHrpkNTX{@Jxuy7Xt?QqQ6&`;#
zTpJ6=O^iJ^I(;2>_QqQWxTjzF3%w>LSqW3S<MObMl>qB%Dm;nuL`%PEbA7CjZ+J?3
z{lsW6BouK{($rcha^un>Pt9`+$ha2&7U$yawQPMprNFd)yMcR7>fp!Qn?i)<QlXVL
z))(cEbf$+6@7DyJJ*PBQ;OrP3awtsrbcyAIG+%1{Fv}xpwgmjEpH<_k7>!g2W@z)i
zEUDk)e#zz8_m0(4*KQ!vol(aR=M!!)l|>$xJmRTuC1cq5oM$v(|A;?+sc0jN;?F{0
zlAdF<SiRlu#z)RB+Nvg<8pc?*>qWm35)RkKZ(gVyE8yi9Gli5P1$_Y;PnccvaW%uU
z9RsR>_jSch)7f`1g9#b(j-fLXzLGj6*KpTGlxnmeZ2GM<dL`x~+OA=xe|<-VV^`)U
zX5x2v=UPdaiRA%b6i_8D3I#O+WcGCsbL0ASp)0*E_-rxm)|w`E75nOUdYkq2`i(yR
zpAfc2aKI@+pfyeHDu(;5+Zfyh@IF^{fBkTVOXz#1*R|0x<P_H(@F-awU?aWTE%VP&
zW7Xz^eFq%R?V_8mDEO>T8e;A_BV8`Ji`nSo{Q|4I15ghv4#iTW98*Lt#kfpmf^hGB
z_TH8#FgO0h-X_T6X<AY`{-tP>kS}ZLzsV#F0#fq6Kjd3+8dI7tf#lJ0?3nsE=iCKQ
zrNE0Fd&1)a>xu~N^~Tv54D@sTXaJd@!h|6yvO=V^IxUBBz=rjETM<SfMH<GNyx8P`
zUp_5h^7jQcAZl0=^I=%KFY*K_?$Z=aPTBwDaRBNwI`juA$DOtc0bfn)eZ5@=#s23&
zx1zEMzrOgLyBpIWu0;to0Y(Ie8sZ%f%r-!nFm*E6Ns6pTnk%CC@hQ<dQQuc1$U$Zk
zjss=r)r5(x;g>uW{LdQ8q^;_wVWk2z<5UI4__LMCC`aUWj5~Uy?vL8siT|pqUwPN6
zVAI0co7Vu&9b@fR2L!CCQ%Ntj;D>TD<u(oDic;jSi|9@Fso3Ao;;tC)c7akVWkhYr
z3P#tBGYId!`h1ec2)RW4&n*;a=Gb9>-GlV7$!{0Q-Jc#ACH+t?&vy9^^sgZ)sA^~G
zoF)uteM`^#t{jiUaUSL634h^jWQA%}aS<jA%pAonOijKseDx3H4RpEMuEs`kl04Wy
zdW;i2wmiQl3KAjVafYo_J55CKpgp=)-lIl7E+r08?m&rqH3`4byffQPqvfWcKON(2
z-ibRT=B*osx~nCF!;3+HC>SV|Y6@Nt8GmkCutJke*Vnwyw3lUlDBl9gUQ7H<zM4V%
z?P?DBp6`G9J(FybHlkqB82w^%$Vv`ACiDHyI2BiyA>=@>MNHmDi;pGs>qj3cPN3wu
z<-Pfuyh5Ch`}OT9AXP0S=`y9)m`Dklc{f`APEEK<W4etWpQhw!uI#^^)lR#}gf0n3
z)vUtx?UaEI*a$C1GBO#ID0)1d(<`;O<FF{Eb+HvzwsU&gB(jj2#~qqoW;u~QGFGU6
z7M45v7XWs`O(rJK@&IU<1C<!mgbn<>R@qco0PF&|Z(^-Cm}Ya@Clw-C$9Tz*_a5<R
zegh8=auh=nL!y3Q<F5HJZy)Upkb_BBqsVoeqpe9c>Hr<JDJbPSVPoC)Q#f`*EOw3g
z%Bt(V3tI;Cv<w<$-bB~e`PrXFGRiILmsvsX(7xiM9A_ghLZfGDAtG45_%i1rZ#%`y
zb#e3SNS&oHC$$n{|B@VQqvSBRyNesyF~UP%Ag5X2K?UO28ZwgX_G7q(uzPoG%Du_C
z3VPIZ+C8^&Ui@(X0MAhH!d&+Q$Is@O|H8J_0OUdnQp~Y?`{(QM4nbR}R2kvh$1d1S
zlKLSXSKqVJWMqhnyee>UO+f|AKr4AA2<oK-n@NBn1jG71GTA3G5tR^KDu1LhxglHR
z!V<i;I9@iW{}SSRyy5P(RfOwrCi`gV2|ph;R$ytf>VF-MJKD3nRxuB2(+nFm2VAq_
zA3+7E=d<8PU$i(K+cbHoJ+r;fA89Et8xoREDgFJQuQ)l-i(ARQ(*nH^xUl&}Prw4t
zEKx3av5*et-OffOMB0$t1%aSfTD;>vvnOw@LP|ox*uo-?lk2PUM{mEyI;(mgm>9e+
z-c|1s{ZF2>JWl30UP~y1jO6{Fw;Zn{4L&nqh$~l%Qy#9v0|x#Jrkb0|o2ABxL(qo_
z*h0Yt=5nIwqtrsJ({9#ws;T5>^#cB2yPL?6sam>X%I^8P`a37X_?LlqDVDzy53H!~
zYwUe6ZHKk-!K+r1&&;g%8Vh|ZkZynPy-%KDb&9=Cc)-5!C>giq7}KL#Se|CC)DFN9
ztDXS!A#{BqQ+X}E3KTYQr4e`iZ54iWkWGDlsQGeD%Oz2+@UG%{=Dy^}XVEdY(X$f7
z1E-gVX42I1A0`JY_PuK9Z0r|x?Kn8!RS%8+=~69bQuqeF9YC%ROIhrX4n&^>(v%_&
zQCHUP0MGpZ>7#;;tW<~idk_SQ%UuUt{de`WeUe3oedc$zTJxSZbW>y66eIDG;*m;*
zIrM-$jR(txm%UYDNl6S5$ApLzINT1MJ{jfdf^Gs4PM0sd+*t@F`M5$F1)j<OkaTUo
znz2Gui#N#f&O`$)(*0G`6mOsB%-EVFv<~xMn{GU4I}t{6$KJ&K2SnRZ3+61nmV_3o
zi*-DfU_D2ca}-&U%G$j8&<j?E0=>P0c$`4Gwjx%G{v5xhY0SVz6T~CeOoNsoQ;<|;
z2*^a>9>~&yejsZ*q5Dua22_gGpB^5>vhF$UZ<xc_uSkVA>&e*@lxi<yQ$&0Y2P?Zy
z;vGS00?b|J0H2sUDr2$!ug|U`GrgLwDn4ygZDscQNm<vL*HXwxHLmZ4%caDo@AFb@
zo5#1wsBOI)TsVHycTpN-Rh?`mTd)?TdwH(h=3N9I6{0K-);n`XAU2Jvg}@D^<-2K~
zhL$WCBX6&ftZ5mpjkfED{9ZB#Bf#xhgP(*gW#8_E^%vqsJ^z73UeU{kTi>D>)?F)z
zfD`5@xR5d5rIBZ|_C#JHCcfb~(cT~#@=N)mL_R|oaY$l!^(B-CH##ZlS^nT!Q1*a6
zOZ!l1P@yL#|H&8F=!*6YEn@`NzK_HuM4X+8K)VeTUe<L-WT0=U-3mFUNemV-P#AJB
z2zy3t9xbACLzf3%21va4V%-zC;cVY28!RuA<KBFBIBO5tu!+l<y^r<&ba9+x>yUO{
zf>fUE&-cLSEina&BL@Bz*U{yUbi^C}mdKX_@Anj{yc}2M6r$njkYkpKF;b%V%=j+X
zAh>bifvML9wv?v?m|bE6BHbgSFo;C4{D%8I?~`^LwV3V!&Sl>ClrwLOavOeH7ZDG(
zLNPl`j=>M#;HMI0B^VWB*fJ3!%|_<F<eAD3TpF_fYB1c!;X5h4dzT%NVm*n{3<!D*
znd@Faktb{77V1VO2@#qP6sa&0U!Bj}TMQ3KY0k@cheE%7kq_H7w3!y*>JEIrVz{JB
zsn<<W{S}z~{MGdkcnvGo5aG6DjbVx!Dl8p&4Ax}?geLPsW_0e?l#-bDpyzGQ>t)>q
zJJ!R~NizfQ<v%bf!3t~1os<LB6sMFnU06a43Qaza-jeg`C%~dY4DNkgxcIgrSm=4D
z#5Y`SVh^$PUcg!?`j!(LilGVeMqt0P#m%NU-7<ou<Y5{l?+vE~RSjJhseMZ+--@8L
zlTS44(K)AXK5K=`@a8>E@D4=VA8^k62Rh8QX7Yvy=`~f$KCCQ#NTLZK_^R%{c9<qI
z>UO>8OE2N3z3M%G8qjH_#X3&O4W^-6wx_8*EcHxQ6zC2_p0#*sC?VhTo{Kl`CD}Jg
z7yQ-mrBtt_BfBR*0xK48q_l)T>yrkke8rrUHqE!QGdujEY~KPF)kgDZ%wHm0W|)f`
zOfCgP)pBamo><3%f!7LrD^*pm-KOH`%YIm@)SEq<yO|>E5@BA3gZ(O*U-Gcq$#S-D
z+NK@~p$4w+%IkSBY6N5d8<<55>2`zXl~EI6kC=m905<u&>jlXEMi*^ij>x<Mq1Q6R
z+Rr3e4Z?Q#PIjALKenG_2%F7D;VJZ$=PE3AP3O?%l#?oV;DXy>GA(uYaCd)kVw!0q
z5?M(%>olQ$%{GkA32IlS<x6jV95DK_#_pnS3_qX*8IGK1-eq47lr-g(<Wl~<8XEUt
z#(rV>;`@dwV6~-4M$YB=Jm7b+#Dfk=t0HZ)Xz3@QU{d`)j(pP(Ap@yS92g((Q7jiV
zi>(|Ci}GMa(s4vMasIiTZm)yoo1*&;><J*L1Am;)V}>@jI4`ZA!5tw^Rt;mi(V`$V
zNI+G_g<{uU%MP`M+Y%%6E>L8<CGXy!w_uiyM~7b=NP12;->9lxrJU>0kIxj>OJ5w{
zqCyr*`d6MrHj{~}bld0TvnAGA9_i2TtLS(-3CrI2td^V6{@y(>@VVjJhcQB)WvI%g
z0`;Ko2g3IN({=}_V6_U1Ny|(`WL-?Q;jM$^um&zp0w}`;Cm^X`*J<PWTxU^v?%{w>
zJY}UyCN_iqMFu@gz|#^>2yVlry1ZR^aOU_oAiNKMU(ZWouHbw!`&9A1L?thtK2)Kl
zSSAOD$K*|g6c<U?x9<BE7cjo%%mCQ7Pz6&tQbhZ*>MoF4wUF#;xQl<0`UXEOCwDe$
zRVS8>Ly1%$f%nu}^X}nLHIM#**mUBqhKb$pvn49Sl`<R2oFbIB2k$A5k+pFq=Ce0p
zwn9Y@XH1f=%o%h=2FRytGHOIpt<=kG8av$Hx07d9V{^*vh03-<1z!>M@ZF$WFfA2!
zLx$3Tl9`g^bxY#id~&d)j!$$baDruFsd(!ma-LtD&4&`qqL^Q2F*u{aYGS3Y2!W4*
zU1F%<&R1NW)(7e(_%OSN5;;J5e_WwltVlgv)_Pl4-u10vb$T6s^;r@lsbK^t_h*w7
zDJ&!g`0%ejPMvEpg=BWPNu$d{kOhyKW5Ctohdx@pr*Q4b(71)2)Aj#F=QK?E2XK3_
znk{gl&^t*RE{mSCOn&KV=B}R*nglA{kssnnYHNr%EgZ>P2)!5Bq34wx`>)?B{DBdQ
z9XHO>{+^d+1vt-+6lLO+;`C2RA)lq3(m;2K-aD#JqYJJ*@5BINtu|l(W%uv75N1k{
zK2u}8`_eqI6q-1-F(`OJ1nz0nIp?()%gs6aK9jqP6DQXcKITq?N49rv?=%<Rxq_=u
zDqrT4YBImI?|^3An5@lt9!(YqYDM0!-B#%?yG<)?=5r~!B`RUYx_*!KwX8L5bG=lN
zCI`!17D?Q;N<UX6(c{I>%QCaYB$Xex`sF7y+}YCH*3!N^6!)6Lya?N&D~Xx7p}(5p
zzeBGj{yAxD^4xkFA~zk!vCi;e<;bsmdZETn|A?tDjTn{&;71b~(LrCODkP1J^#(pH
zJ{Kx+gnTz|(k?LoB$<H2$9idht5CVf(hPU#Q<$weq9ZWwN-#5EC&AxUO?qFiF$V!!
zp#YmdQZ{vT5_vMPj;+!mP>sB|dA!u2%*IC*`yP+dM<gLYM_<j{?(aqSO+32{J6q><
z9sx#HjREY8?%%Vl+a>ef#t&&2_s%czjzsr6YHh_y(XA_lQG)Pi)On<hE~JY|3kvSW
z-54*13G^pMpSmr2{sIIVP77=ghyQ_Sw?dh|@91We>;4y5EPH5bg-LVq->KAQs?$-M
zwc*?y%yV*wr$ZCLL1Z9he^*3WZ`ctL{_e+30kee|)ybMHE))D<Nx;VC*FTV+hs0bN
z*wjkey_oF7tngN<ySp$jqvMM>Hz0{Mgy`x>6qcW3T9A2wzqEH*qGCNbqcqxA6IT8y
z(5@`DLr)Elk)+OYUoWb$bhAc>8Z8Vd25F+4atL+Hi~oV5zdsGyY28JNo6qlQh6ENN
zTl40e9#dbOkd*M^dlOe6Ar4BHMHub^*yauyu<`unAoC`-WC>dQn=LZQ_PaP5JeS#(
zOPK_`!*9hg{jTk{?GFR%@UvVUHy&(Rq#-R<R*kq?nsm=K!<)q-NNGIoa{cZc?3)R;
zT6KVg6gP#R9_?H$gjAmG#N}C9_o;J%?sCBt^aI`I+H-fMiL8;#B#MY35dA|XjoB)5
z9b30jz5r~H%0s3KRG%XiK4pS_(7%X|7%RfqmcPto=)RZLLF^Pd<wFDU02eSNI?e02
zAn~&?`VV~GI_y!+UgI8fimg^St{=TH!x6+8ve%mQi=vfL@bqdazlcTb0ynaZ2G7+u
z&;n^&DcMPVZ4hokR{dQo5$@t`us(CffV2V{YWq9Bp<0W2Jh6VZ**+1v{%T?KXSqGI
zxebK|ot*LFp@;ub8slarfltCoSUwbDl#P5B)9l^b&ar&6r2Y97Y-tb5uDBDI_aQy@
z40lek%YISYbRzKc%fdr8&Je<TUFNX($3hL6>*wDd93yaz;t@^V@6}N|fRvcuo@XOo
ztzE}8NDIJ{EXc5=c`EBv-zS%N!ABDe;>w9LkvwfNC2b$0V!cB`0|ER<^_$uDWC~!*
z#}TUxoy_(wYXL(~id^|uA)B|#m)3?6pUaZZoscJhnU;J5i_o#J^ynQ~A{CR;yYw!P
zrEiX4)#i8SZy}v;Guy;FC#nNRbNkA{s;D;cW%=)#B$Pbb`ojZuR{@ak7e!X48w5Bk
zheMmXRf*M~0B?Ob<s4oMSH{IC4TvYw<=H)}_y+GDqmJrtb7l9)%64Pa!3Vnk^?oMk
zFm9P~%}UF1An1br%Kug+czL0CkfwhDXrnz@!h+I%->!YXd}Xv|{akWD8Z<dQD3%nN
zAiq9&RrGwSC_?oC|Hj3@uBm(JjT0+6Ie|zpQ!4f<svP%wQu5=Br-*tX<<1AYGG)dM
zb@ToV!wn(xX}@WqGf$g5>SMCDwuqwcf1m<YnvWMHuRc~h|I(zq$2V)t&NN-vyx9~T
zd;>J#h7TyC8NBy?=rx#5mO|{J0jgA!%<i_$(?bJ}mdVR<(xHNYL<BY<(R^?2v4yZ8
zYJ<h#5XdS5Qm8?MJ`2kkVy?cUcb{meE&j_eud$sjdQY@%i6&BSYMYD`30RVLZ9t#k
zzG=f6{ek$&h?D7}Zucq6k3l~Fv!^QA`@%bt#|aGWcxc88-ZtM3zeMOLSng{9ZPVL*
zJE}_FO8`3YGv36ai#aiXGI4(b@5}B(qMntO3%paqEX|kivXGGDSD8&gd=6a!IHlZ$
z^1>b&y=F<S+?y|<44HPBzu!8K$%lA|=sih~Ty@FnHk%v-&eH(04gc|GY{OP|(_7}~
z4`1&CJ5yQlfqZkMMA{dRe;_rU8w15_H_@K#V1}uB`iK+?7lm!HTA@gK_CnR$LMB2*
zp*w|)Ic7RQRDG_En;ti;-;jnJP41RC+%KDBTY;ub*6%aDsCh`DFq=oFRpZ!Rk7n%)
z@DO>i|DpSTWj1~dkgK~}c=QISQA5KNPl;*`P(@f?{LmR4k%f})!n=SJS5r<62ts?E
zh*c#raSitVRL^iB&a_{pO|Q)#yu(QDoS8;yAp&IGJ)Rbiv`l_|_tCCcW@;587=?A*
zFJEcJ6KK1-D53{s(GJcdt3*+hJCOdGPctTzRY^yz65HT-N7Ke3_77U0Jd|kAfxn(x
zcpfxF*bC-1KbAd0Q(H8u2Ey*&6mzy3=>k=5l2MJ_Gy(kaUGDGaFqu!tYV{v2Bqs&k
zN^FQ4bydt_;AH8m$^TYsOrh6oL_%}og+JSL<O9dCUn?Z<x(*cbwqozS92fc+bbiR{
zml|(k@gSzjjw`pXqI{xul)5bWcsZ<aaa$;81DGs0)FFpflQ@qhZG$6Cqpsg_`~!)f
zqec?$^(=$)10Z#I1Q1s%>caOKH5$2KRG|u`?-$t(eeL+-@+}iI@1B|Xg9)*Jp!H7j
zBh!?fTeYugofOdbzfwbkre(yMwuIy*eD@8~U!5F0GgmKVt4=bCPm5d3%Kn?1pu*lf
zwhrFc1|lQ6Kc=s4+-OwN-E=B?-s<_^;!C^;S~-%W8OMGq{IK<IN0NzYy=QOXLz=wC
zp|v74{XC-!!<(+Z+)2J#<R6H>F3Q+CQsoy^tUYz4lI3SIoNVZp`Yv_pn`gw<)|tsn
zZij0j&E-{i{EZ-%gcJKa7UR|TTEK|#d`^Xbe~c4+o!*LU1d;T5P`8)f2O9ChUZsff
z(mG_R2JDWjg+WWCGn{7nlyy*w$q}so4>bM1paJ(k+K-@*v4HF4uAGU`WHOHCALv?L
zDC)-N@-~+b($x5hddMz(g{EH!-C08)`$VDVA81O;Ld`rKvQrj0Rs*XRc9Q80#ce)X
zaC02;trC{wm2WDhBM)mm#dC3i|36cC4ANZ0?j?O>K<2EqhQGosKQfAIwES<#F!ke5
z8NcVaB5@*RtoBq6{A(Ez+Mql>AukqyI-m9W4B~v5-#Dqy;>P?*@^m1k`M%C;szJ)U
zvr<En+^L}mjHHE^cNvkTljC@!G%;8|Spi9_<uiI;ra8xNMG~-0s)?)w-@p<B-7D(M
zo8%xL2V}Ct<-?gEtIS^ka?)d9^f2Xna=1^Od$TYj-~_!^soD6u<RSYINJxE%pyb8O
zr{p4ifnjp&vy#*7%fUS-q3f49B%}W9?wXm7C!dshnA2~q#b0nMfG4h4&&zHl__}6q
znXs5*FnS`hle%f!r?0aRJe@7a<I<{N#dRA4f*u@GbN<yVZoiu=WeAdd_zzSSh1HUQ
zP?+Fh2I(1)+}U!X#dz_nk(f!#Klf692s1xfEq1(nb`RVR(RSQcnn-32s{aQfD7T*Q
z@qqaYGhDjyS^lvh&^wvnlclXka%8kEhlUsczy@ojR>=+-^(f=dk=ObvwUIOBpWs*D
zRqlTEQm)C<QYnmJx|WI*_$ER*58^yW0gfG09c+~iPR8^&Je$d}_2jqx<|p85G<P28
z_;vn#Mf%?JS|1uO*jADWY_~Rkl#>Fh>MG~b{${d9+sJ>VM+AWUX$L>*w2o(^4))Wr
zr~hGsRxHH@vwvmj+i|s}P!MD{m83VoYM1fp4rifa>&xrTlepsW2L~k?%Y0MJvM%?~
zqmb0Mz!{!4K%F+efZ8Z#<BPJUdl(1k+hYXUDMn;)KUTaZgkh$Zhe8iz?1$o*fU5mb
zPSbOi54N1QdejdV)k7>Kbg!9=&d5^$KBy#~J_}GF^KS%%bO^j#KGjLO^5EYrDGu}k
zrizJi)J7vt!+m{sR{lost}pi$8HtD9THg3`QT<fW{UUUKGs)H}7?@dJ?%OsBx=?WE
z=rAMhw?9JP>%Id1I8pbf_5iSsXdO(`#MI?En(jjO0UAlzWwlXq@8=LRDdboT@Zi5R
zVVj>g_W&K$i&g|SwiY7j(H#u?mFmOl2p8SP5%pQ#_sefxB7*~o5(?aI=@0mT{-_wg
z_0<pQ@<)GuBLU%CF2fH_;&p(r?+K?Z#AdD017xJy)mK<}b#7ZC$*c|$!76i_)u>k&
zT<nXV)=KhoKo%+P-=Os-a=5a&cBuqRz4CDi{ueN329@N}8oIfKSZcbK&-@Y&Lp0Tm
zn&aVUg-<sAtVq;8zH<P6e9NsrnU&4!iub8W<{z~Hw);Qynm<+HF&~K@T#HMe9M&n8
z>L#;|PAB>WLRlKm5!bBr<o9boU-Y`Cy$z1)Q*R?qLj-ut0wh0x5dF%0Yoiw1P|T$I
zUm>Lz6>w|4fo2F0sEntVTmC%N))MX6@e2C3e4OcywvUKZa0|Z5Bx?Sg>Sg;ve)E6V
z_7<L2ZDcxP$;!)d<rEtCSJ8XYzFL^)voZL&{rn5ZYR^>zo==b$TJ((XY)|H?tRoX}
zDe>jk9^hQ5+1rC*BN@bJ<04*9++Z<o<z$We3xMDS>9v@oHs*jRxSZk8XW4Qp`DNXa
z|3K{j$I)3vMfLq%d}t&Ekxo%cDd`+Q>F!hzkPb<yVL&9Lk(3%brIZ#4i2-pKItC=A
zyJ3cz|8sxOJJyoL3-7t-p0mGufA+M)K<<44M*{W<*h!fp??i@=`|T6_hh5sGk%O)J
zn2gv#=69TeP4N2P?m@LcV@%8HHHr`T|LPvNulNV9a5c$z)1~XpyVRJ8z1nIno@UqR
zPk?*`CS!~exrKtCx-GsgzHhH>bbFsoo__xY_U}(u3jfZe1D!xiZ+1jH!u!5kamOTU
zIB~O=uyBda$B~Pd5A%W>+(cw+7U+i$l|*E(>O)*<IRK&PvKriSnI+BqB3#fw>XU>Q
z%I=OCFe+I;J#&2-E}>!mthKyeioD!m?*h^@K-AdjOI<r7IUA<&SA4u<H#hA4GOt(o
zpHduw-m(g>YnL88L8JGY`_6@WJ?c(!|G-VM{ZyYZQuNsHOP9&Y*>4({o7oxl7l+YP
zZ7J)3GIubY)LmC^k5;|;U>Ph|^l*^F;nbZXF9*Jfqw8$~)~8B4CQN`D!wvqOj^P;K
zWtw5Y-BvMZpS~#cb|BeDo>dP;uXBGu=aS)X#6$rO)&C--vHgJZ0JHS&^TE0(vd?iG
zyLDm6lJ1173#~0YaN_BB8~ttZ;SkrxV8v$O`=qweAv+D<@iFaLd)NhrnrC3Cz;(QL
zkBmM`?VWKr04t}05Z+Jo;M~ox4LG?6y&h4--gTi{L~eA|SEe0h_7O7j{Gio6T2J&i
z;YNS1j4EPkdk$*l4P=SPsB;75uRo{UsQTCSNS1AL9LD?JxWCwz0uG{)lkEp$m<Ro}
zW2Y&$k|_tr6u<5*$G)$fi7W~VRwA|&oxaVV_AI^e5&IO$b}GnlPEI4(7Cka#knd07
zN*K;axW>)BpBwb;WOD6geDKjl9Z7WR9fC=w54%?WuCWA4`6#Jz5MIPohH;Le0SNdo
zrH;yb@=s|uu60O?5%`#2HNLc5$MHh<g2_57V>7C(P2reKCxsU(4$;vJY^^2)<|pf)
zRjN0t#Y?Tn@$VWdrdGUMZ75kFMu-@}y0g-#=-yi4s;~~sQ&_pt_Zh)T8|#J6hAECZ
z>vY3-;h#>2=<(-YQFoFUKeymZj~V_hLk1TAUEr;?uh(5?(b$kX6cI~guEFs&8L7-S
zq4~Bx5~-bvM>pn%!LCQD9Zreho(jlKJ==$aQJb!V>X;&@)S&jL!7S?b3WAil27Lnk
zyPJxnK;Q{_WWZGJQYQ0&_XE=ZE=zvAo9{<}Olu+}sPx|>!}`4ehXbGJvFEmc{ok#=
zhX>Y$-j1&az*X~$Zm~;#I>37uWhfZ^odu$=1<K!h&FTHajbT1<N_RVsMXpp8I2;47
z$!@95j15~>6UG^sNLSQb^DIE(tcZ1Z=H{`#)MTRvWz22gjx9O2n8~(w_IkE~LgUlC
zyHu8P=Ki0>Jx(~ZVvA!yws1JkX%H>(vwg?WAzR!Jz%v_51j^YqoSPPq5aat5NNcZb
zIfXVS0KkbovO%8-h)853k6A<B5{bjV(vqM!6eCqdo_NZcdjAYaU)(Ci2pbPk&ixxI
z#;~`g;Zo<39?ZrLUq#5C_+7ryAQ8$831aZ*QRgWXfBJbr%K3z+gxRcS^n7geNK{MQ
zQ+E-kXpz1mjwf~XaEw8!K-N!ryo{Upm_x-+L!45ni1OXyj{>Z#dQAPbUjVQEajtH}
zRLR?T@=8#0xEr{U3yB6kF9OgzZgVny^lRv{y(@=OcJU7o`)@Iz^kFA(t>cHx1%hk*
zkbqvQ9qBPC91~|y7o2&`h->aSN#r@e7K4v-&B^g5#b-RejKi*yU6`E;|A_faRY(^F
zh5uET;)lHfG@oAz9#LTTdn?@W=J?orGtmz(e`HJdDhQ0Ux4!<!96y8_oAB9!bAf~M
zY2EsD9V-QzHYO7?oL*PtiJG@(6I30dXLNH}gyd(qvFIOFJYPcgzU$IngCqr-ro<(b
zJ1vI5i-W*d$76zoD=S0sb9t*TM7i>3Oq@CUyF2FmR$28^9SeY)@-Gpimt5qf&U-2@
zc$7#=PP~RYlp8rg=Lc6&cNA5|lGr{y6}KUjtxrsZP7DLR2o(i>S~9lJ5<`UClmUmz
z$!i)(jDL~M4q3Q~@&z3p&8+{#ho)*IM!eMWJ3)fqjT-b<IYuwOeZZ0gn@fa?lcpco
zz^2FBsbV`kV!=*MXb=(q+y=o@r?QZA;JjT~p#75Re;_rs&?mxIv&ml`EvD@eaiv0k
zX-V@;pJP{WKlxAZJ^gWzNP;otpA$b=^F*>KS}E7h*ZMg5h91(90<i`L0kTEb(EF~n
z>nvH|CwUIj$(f?3luaChuyqjK#5!O0vsQ@QBp!8~aL@K%h^+k=Y+aR}&y|;gQZ>Us
zhrA`t1<*DZ|04a$wy30^%Nn5?jNy^nDq}#^QeX=*Xr}*rdYb+ulC_1U0F+#qTH9p@
z59Tt*5=jcjsN`_Ge)@|KX$Y7d8vdJ6#$R{wDG*QT03R=DUPsPAY4KjAuopaH?bO$R
zDp|qi{cboF0u+n4)ih!L3kZ;y&WdP7=$j7jE76kc-%n54W9TTw$k_<~SqgQy6969y
zdNdSYEa*z1M#gqY;kN1VgnFHN%?p42bfArrs7-g~2ve?`?rP{dW=HlceWowU&jTvB
zx4D;$rX5drWV6;VXYH4eC0xMww~h`rHV=+Mvg(7NZtb@#id%J7EKQH@m8E@y;%QJW
z9ISm&BJF3w3B@#di8DQM_;w*s*mZ7w(nm4wz?(io{QcPf^KTs@V3J^^%B0>;p?BO;
z8~SY$M$Sbz5}coW=di2ElU+q@N41pyPeL7=9jGx-{|91`D>R@HCg=zY-|2>&xK{Q{
zviQCQV#uAw*8S*@iPR{$Gcovixi{rfq2f5`n)lA_<Df0&uG@1bWYu3?S*q+GT<w=m
z2)>h2@Ja_z^aq&6NR$0K&%uU(yQG3^Vy9D}$@$Cs5U+BGl(N}vg%Jex1^AVZ+{ZRl
za+5GJt2Pd|;R`$;4I<{ixTI@t-YJPki!O##O;r~X9CwdqUmWY^hmxhq%h+{cOI_IF
zIA$XwbwO0}U(tyMR1sx&P4rk-y{HQ4!!gMB_y;d075AT~$}yDD)4g&Lt-7Uo?>{U*
zE<wo@Z1MdFud;wwJ<(4f5!$BVA)eW*t`jig26A^p8P%Ifat0_`R`s+re;#=JI1MQ}
z9Ygt$Sf>$_#hpvPqB5kOWsc1a#7n5#E$-R)`+eS{-1h!_`WZ@u?TiQz2x%G7&F%m&
zCtXF2LdCgB9G@{v-?8@0>bt`{1;8&CNC8^l;trb=ai$_&6H14PC!mVf;$nVGK5*3U
zD7WMCrt8cXD!jc|PwO(5B)QX`Cs>iG?rFJjB7Eki7D9-S2}pXJ@);BY1tN$wH--PA
zzQKKvr)(`ur>eWsk~s=jN&OeKm6lT{`e~^>2R^#Em2XBxN=p|+s-hVHEovGX^T$hJ
z%<V<J8zQ20ujeqJ)?t8tf4IrJPxWcgXAvcBrhD+Vn@Ip|K3hMqW`H4jl-Z*2W=Q^P
z$lH*ao*T{I`H<A@DKBWI$};DBj|BC;tMy2F|CF{R<TqcMkZqRG*}F~)$0tH`tO0|*
zpX#*UseS>#v~Kf%mzF-*(iCGl_HV{T+h)zHB>TjguD*VGGfUH0Z#~Wav?~7DW_d>v
z$xn4(`+ITqgh_`=W0o5;n*B(=BS{*q){xq@t_8njO$o2{^(zw31Qxy>(ydxRI^IhJ
zZ>#_p#*%fWD?#;}vNy0}<}@G*p-K{ZiNmcKvY8v|uO&X%pUuWt1G+)sJo<@2Y+Gy#
zG4FFvU_UEN(p6;ZcwCvs1wOXV3DAAfb;CPtqHZ{S4^VqcksgLV4`AfKWybW2y#!27
zmO6OH;4Mb7(Wij_x8vT`L#D22&GohU(0DsHYO)U2r9}4HWJ->cPemS|GD26GN2#ki
z&*f73=~mlrkoi9Ggf6gq71U_0DBLOnxS8jSuP!;FSIyoq=mdUo^nN$}Op3*Cs{>h^
zOYF`YeTWZxzMXy`pj@;&61nY<+g-FM8FQsx27f~6<%T}IJu-zd6T1mzR>I*qMWNj;
z%wC^aw)~OxYnD;ki4-lfTMr*uSSG*iG)x|dQc8MIxf7Mer(eIPI9e=h^8j~B{9O-L
zQGM%70#??u)_u$>ANl=&AFpU)XE@xD{qDVtcr1qP9a+7)Th%O@EG?C#=QTgc6>~Ky
zV~W$UYVS8M@u2eoJ50RdN+~BnSnvg#TY7gq1NQa$PokGouED>Cs4GJrFx8;CQ<(EB
z*2YuIa$V=d;YPF^y-)1Ltmub(k&xyO+II8Qi{GZmS$JPHz8DZr8<YJ1E!_Qqr?zcg
z+o+|hLeXle^KAZgAUtvykW3BV3H5wR8&j=K-w~ibyo24G%P3Y<x6E|#lJzfo%6Qea
zV<*@LjM|wEZesS#ZaqyIFn|2e=E|-CTQ4g#r<<7MJs$$aC4X(VBGp!mjh^glwa0U0
zTs_KR%ad(fcZ4_9FkI_;(%&3ODFz|6M%t1!)xz4dryb~Si@Fvfs^L15_zbfFlJ+(D
z==)-Z1?pDeDtzqa`ZrSx-kb!1Gk){FlrN{2n=n716yqZ9b*7O5B2bh~%2=-ROtNxX
zRH%=}+a7P|4W+nxZO`AA?6IEs_X|urT+80vm_$pcts;38@T#I)8~X`U7w-5+-qtp9
zHlczx;sfvZI8NJ~%0(Zi>*B_K3W){&>DbY~F{#v=jstmtucqj(CR%jDzTsWE5v%x*
zejn*Tk(9Qmpd1fGx3hqVQId@({cXO}s~$51iE3APHYeYHbdjpW#J?~nN5<_)oP@}D
zv7P)#Hv3IAkQWmQeRUG*iBJSnX~S|43OAV6Bc2uzPfOi}39Yz&x(Ma#`yWV?`tnf&
z2UW$m;<(HuUEf;mTlr2{%{Z}7^OU^<E;S0f?4xJ#mDS7gTX#;K=-R&M(1oq9fa=L?
z!Au3oN-@r#Vn}2+Uhj1QYpw}YI7b~bYPE8b;!=BEVT-v<+1EfRejs?0`tLk@E0rl`
zLq|U+i^J+gXho?PN>Be)*=)l?GozHl2<z(IU;ZD>e0k4Kp85|1gj}Y6<3`&|k538-
zRA4K$X|D8)Hp;`+7Q}WeoXg&cJ(D80@Dn48y-kS6U)2F8Hr@Mot(b_z$^3v%1EJBC
zgh}mn64MvGU8<Q^33WQTR|Vu@S>EkbiaI_T6n=Hf&UyC4A)YcE<ucyFTLf4Z!t})1
zA3<3&H<+ia9CrNFpYBI~8&6B_fL|23{3bE+_}D6aNp2KuwHQH<ui%%MGTV?syHpl!
zgkWJ)gyLG{Z{l%kEFPkOjc5C!nhAF0>Du{Hll?>aE8f>0^t#Kx=kdQvc6{}^eTKOp
zxZNt0(7)fq;S6tL!Zo+xBMM@QnWM9a_wQc%pl3gzq`kioKzoC}n*BUw0a5lSE}3NQ
z*8TaXGpR-%K+-UoRVpdu!5&2Rl^bRp|0}!S{0M;=-Y_2bdYm%UN$L@2#8m$HQVt<|
zgc5#g|14SK--AI0f@~<cZhl_9Pcq|0nJsy0znB`sVx4uK#&ktkzd&zk5#=4)gu2M>
z<sCZp;#Q5X9iBoyaQ}g?^q$Xun_I0&c<?8r=KzpX7mjUUV0WrflXWUAWchTPZIFh9
zAXM)LEK`(#JguV&WK5&XQ%qfrC0V~mEAA$I5d>*zO}VPFrP?jSovr1Ec!~26+!e5e
z8*Wy!cNuQExL+68T-*j%B#~$&A;*w~@S;kn(=JWr-FIM1_o{mN$*-tn&F9BtPJkdg
zFFbv&-5BvW5UpXGJ-V>R68{C-SPDvez`h;mg2!SxnZZXtJaBO<rcwB4Y8(o0vbEzs
z^eL)TG;u^n0QtWX&i^uZP6;5XPphPCob3IK;7rjw&8JOghrZyy;59u@2X*6)lEjVT
zrvSj>;?G@ELnArx%Jw(BN)5Df!~g?7@;W!cYY%<JpVjbzz?|DR;7qkJeOi9Smr?To
z7k*xdZzdqn!03<PF>ubVXgO*Q#>lM#b{e!1IDUZ~&qMQo#Jf%{%#sWI<U8JxtM%}`
zEM3nl+@bn)J0N`eBv|{j*WgTncu8m_C{D@t)e=;I<dcx&-|OcJ)LLe2BPh6a`b}og
z5MDWMWX4kIvoFguty}GW_Cd#(Li<)Oss)|;UUKOI<vK59!~AduGsmk~l*^z5^G5p2
z)l&(4nr`7CWVkaGi}zlXP-kMG<?t2;9L+lB;yr8Z8GML^J7_i?{N#+{fnNlKBm^l~
zBeUd`$Nter_bh-`geUd=dXCM6KIN}_4nA|(_@MD;86Ui2{6_7}-b`KcKMz}A0qjdy
z6WDxbnmx;V#jVU(zqidvq9jP)z~mtvs6YZnPM0>UejrrA32L{J){?*Rw@Q)aCwFj`
zd~!a=X}R;#d#Oix`rnnf?Wp~J)M-g1sQ(U*dS9{E%g)kacDtpgetT>snJb*-8_(9c
znd~}mF5%D`v-v(po13cWvRZM}lhpP?QI?o<rq(j4Bt?#dahR3BoM(<Z0QJbgXFpA|
zs3V%E*wvi}`Hcu}1gfI`bg>ikmg$1=;S+SiHs@_9xRW7w4A=LOXFDV1S2XAuIPqY^
zgEZuVw_GO7+vDyT<&?}*lew2uqily+id`n7<*s-lhb-(7o(S`2FX3%TZ`e4)LJq59
z0fI-1=f7t`!{w48FP#PA70{+-p2Q+jISa835<<gdMnNdA*`MLNg7H8+>HSptrlq4p
z&kL)Vb7j4-oU`TH*&Nhz3I`sDVDh=^LLh<Q-HV#0-Xw=>uq0T3xTQw=mdUzXC3pHi
z`9Uk`MObYiOh|zDR1Y>bUb(_L)s{+UY&`qVjHZ@?b(MeQKQFuI+*`)wejMH~*6q!D
z5L39u(iNsTYCwr2i{4?}UTl!HTS;}>y#cnu_BUo?ZdXqdbuL2m8+Ij&YvH}R9F-cO
zT8048;-s%DUl{HW>+dSrB)WDk@H!?kG`jLfsm^?f3vK0Qqxk4>R?BTT^Z4;C5naC5
z2Hlk3*9Ye+@AOu5CaP>aLWtH<JldXtf5gZer^IgJDgW?EUIhe_DlqC>{^9RyB#Ai8
zX_g84(I3vHm@!3Q<6=a@(xOQv^KUD5{1?|)xsbxcCbO=;kA=*R<kNL&T^&;79~=mL
z0_0DJBGx_Hjb$yWB=3Ak1JhpLUSPJCy~(ik{1X`t4V}YYI5;qphLRqyw@2o{6m3lP
z$<eQSO9i}KOBqlRq6l3Qp9rnQfBqO9?394dDJuj^wc7lU(s_SMFT1j4^_7OYcaCY+
zwEq?dUpCuGOsQ0-J7mXEMxHj~>vNj2-NBx@2gi{(x}Jp)`!h@AYz1@X2mBHyHSm1R
zajoT3A8+uSCp}}WYZ*MP{e01fuB87Z<6m;>ce-L2`+1%<Z+^wR;Hu;nMmxnpNyrZV
zX@VAua&%7Mi1-|YkCl|kXVKH_mBoGQ10#+%$g@hJhPL#|k+xkWS|;(9A&(_0#Ad!R
z<yZ#n?C^u!VXdg!2mf16&g364K02RIuRgcx^2n_5lWGTFEG!B1&MQ0@wIY9OAB++C
zYY9b}H#H7rkX}g$UlrWind^<fWe}j(F3(c&t_%hMTD$1cuje(E!}C|GCfYS_c9gB6
zkq6U~#WlcYl_D{6UF3jU<R51C)_)z7x-{IsIi&<Is*pIUQKuhPh%9>L&bfW?Td^YI
z@rvXW?gN-v`N^+*!FVF_+&3Mwq`+Trf!~oo<jAX&a<mCyjR)mxhxeSVN8t$h5l?RA
zt%}*dRNb4+aky3r1xkyj>d6JLqH0BY)&?XA0ISvropSnuqpihU)LqE|X^5V(qI73n
zYFGpM8zUV@t2kCuU~a*$G!EBAAVCtUf&maj_le)N4}k8eOahw%(>gl?qCWbHvIoz?
zZ%Rj}PoNNXQrz*QT1sI9UL1Il@i5-ORVpgwkRWmj7$`MpkcX?DZX9xQm>z1hzK_c8
z=Iv278B6yY@zi<^i{`!3DXlN%3E2?G^Yl25j|iaBhm@qwzoLnPz@S#u*vz!^<$s0k
z(nT(fQr2@E>SaV}4zioCu}y{ZWf%|=QLUkG`_lkwZ<!Va;evZ!Oq5u_ZbJyzV)%=m
zVdKRjyjKX846jH-ur0$Ef+p6=Q{)e}VVE7`!{$(O%`Rk1KGk3}$OiZOW5m{(4c3)G
zzcndR>Ki}nC2^UUYt!AgSG;Tq_O&+JrAQ{VEKae)pF8*qFnv}?9f<v=Oe!~6PslWT
zA=){?lQg*sK5lf&4D9uyX-KAuN17Zj-#^*xJDz5?OILnPuj043C4R0LM<TkdaFy$f
zYQF!j(Rt@f8EB4~EInfzP)rV)IX6r0rofYh!p-*Y8gVS5T61U*_cLops^N|b0;_#>
z(E60(vLR5ns{WcX8*pUV?2cAjZYQ{cA66EaEfKULazX{^@fo_O?ydKIVm)Q7<SDh6
zwH!&q!L`x?EaqWCgJ%j1bf-1aoaE|5V#7tGJuSt?AE*9-RjYDut&~>m(jdM9^D{zt
zTZ28awudZ3pt|BBvK16}qJ^A8JF7_#YL4;tnICd|3UzFdp835O=RcuXrFd9FT?Z1r
z$~?Zi8G^3bV%>;vMd62K&=Y2MU2|7OBgeo>l9@avjR=w!3KjC7woDk-HxQ&aq}JT&
z*0UJREV)k+9CW%HPhnN-JEhj6MJ)WKE<Y?4Z!!|wtiNJ<Wn(O#WY~@|N}f(|t#anM
zaGq)qr^s_^N`9iEps|%ZzOUMCopXCNDB%&nowz~^p?saZu)(R&EAOjMho>vp60s0k
z#=lqc^|84U?(D4{n5=c5(I)tJc%5aoRhY4cWrJ2>1o0pRIm|iZZpd^f=%JDIy~my_
zC{;*|r~#z_MdF^0V%=;RJ-wY@2;zt%SBXH|aLy?Eef^rAtmE_hwg%}qG=8aMt`$M&
z;rY>4Mt^Bql!!fqB^MMt<#F$}K~wP$UPS_>ko^BZWz~wuxem(3MWZ4}%up^>d>4fT
z{u7L3MiQcTd!kymH7W5E_!Ql6mBi|68i<uHw?^FekCVBwnNm`)eK`hNId08&oEW0c
zSb7hdwngOvFyMJufR^`FT|6vnObt-Y4G4Q&CqI1P0#0S(<cCrOZ-2Cc7b>70i;2${
zH1n@)cQsHbv9MNZWR0H&aJz3lRJwhp&z_((<GEC2&CitLnTfwQm40T?t(Z|)ZQI21
z>^UF4PgQHUHZ2%W0~OuNgdt`BQZsaIhNLHxK2~3p$Oc4!CmhB~qc048@@_WU6b?*c
zzZ;{d7l7_z9V9Tu@+#d^s@!<(xXTQCfdE-D$PU2He&H+VxvbQ%;tm;h+=^3P!JkF#
zxK^y#IN*MgjE@twzOp;{_L5=Asnnw7bJvnO%&5imnM9Ty`vp}Op57~NQ^E5+fzok`
z|AAzcEa^L|y$dl7b|o;j0(7^n;V_#rtI^`T%`d#rUpKf*y%TPJvwW`|nPVl|M<6^Y
z0`OR@#{8RlkYdNa<@a6Dku1y`)k{j#o^OKfe?$C|JBr9Z?_P~9xG%l$eWOE9FVG{g
z%U%7XXH1}d!v6qt{kYy&rV{Gt0?00cmg<;kJki!km9Xo#-6^<-4B5q%cddU5H+L2L
zi>mtUR$gd$UXaeoDHo|^pP+@bxx^>@iuiv$61_r@Epx=>zoc#$)xJt1^lc=Dmjzdd
z>J=APZ?SjRxR#nsME+ikg4-C+0wg1ne=T9?VE>EhuPUio!EEo$Qtv}Oc5A}5jnrRr
zmtq1JlUkigx{358G@eT?U@j0Gs67&T;o+lZJRA4XA2jna*Z1_8H{o338!(^veD?<j
zx6d>cB7lv+jpBJHbXzHY!|JDis3Qa5pmR2qult6#W0G!0k1_Ryj<-%S%viuK-V$C^
zJpbXw{3kL{nQ?eb<57lo{qw{@cKvdTp?bvGFNUQwjfs67pDiLZo>JUh9i$hYRg&u=
z@p)l|@h-S}cE#fDmPcrm*0TV!vHdOxbLueodw>HHg^wZgnQY-<lG=m{pHvpe8FLDw
z#uPNSQVv3Y1y4U#gy$+L`G+1Z!i+Y09`a3W5#UswhclLY(%XaFuWZW|DMi;jMxY&j
zN<)+asy?{Ffq*`(@npWKt>>`n^5^}`5$AANNR0P4osW=mz#LzNuj$;9_KMwq>l@G1
zMMCU~;Ly4P3tdCyF4rgbe6LG4*C~Il(P75qwJN2TsK7|3egMI?1!E2hln@96Z{*U?
z_5c3sEB9e2TajHq`?pTYSS0D&le4!U-86RNX|I(Nt`q33$H}0JVG2y}jE`ss@#DiJ
zCT=;wNcJ4MU;WVLW{X9ff(*BOvH0e!c<JP*{N=)AX24HThu@ZWrLDhH_h<WjvtC9a
zy<G4`>rn)82l}fm;H!Z=-`qE78a-LyIGPpcI8{1(B<16zFf2~gC*j`q&o%#w2^dV6
z`eaN^kyOf0CfOP~oGl0|$dt=w)o9@V!H3A2k}8MR;lY|-7QO!qyt6SJz9JAJ4)-~>
z#@5rw<chq4fD{C)!;%5MIO-fSoicw|q}tGNTag4^#s84I@1JSDQ&J+buLs?@Cc&aW
zKxOD>=^x5R^tt|jT`s2sF$V}~S9FsN%lYvj#{x4TXy-&lYP`@(ukJQ&F_QtjrF3gW
zHp0TynlO7HIpoQFn0K9<Q5I^@Nxr&;?YR$lbw={~Z<##RZ0pf+K_Ph84gb6cjP)YP
zD3KwzmsNS{jSlCpA6%9_cbf1YuS9gp2Rxn>N-sMi6Y9Lc+l9?r1#MOeUQ`!PHvb6z
zSia(W_T1Gbkhg8(py=HWTYN$9zuAxIl!c8Uo6v^{Nd>dt!fB7?nwD!;mKWu{J_+qw
zm~=d}m#NU4Da#EzTBXWF*mzmSsXi0S-;lWf*&&EocaUx)s;@q4fjcw+$|<UFt{VA`
zl8HWuqR`;6Pe)d3X`5j5d?`>^VE-!hLsL=j4y8fftM;~RyYKIjG9-)@k1o$y_}Yk;
zO?*Wyyw}MyfHkX_r>ht6qeG1-h2wDA31bj$HjQ^A@QGV?tmIGN!hMD5@y_J-ji(+k
zB?04ruXMky>cJ?we-PKWKZXsHIh2^!UGO*t_ME=5=RqF}$r|p6VM%`PZd1eN2c@m|
zb;5(E19szye2G(R?V#Z#tNcV2?f<;H7E`nezFu<o+jNK8t>>cNp0`@<Dc?*nPF1)i
zuSk~o?CQuqS<F`~<pr`Fxp^4c)l}VoE7!BG#!8tzTU;V=r=pkIYjYmk#(CbD>7f%u
z#X$=I(rK)Pog~8(Tlz(>%YX}@&sO@8F36OfWh$F+S;J><Jzrdq(;)z<k9IX~jdiP}
z6kfF|(|w@ByA{BAAx;!eqCFl3h5v%tDDW<XDbN$hHeHX@iB-6qo_6`%$?a0s$Hn_{
z4}uIe!{qY?0Af*{kvNLiED<(VmvW;%5s2H~)d{U*WBKQA1fE}yq{}v(FuBV@z%dUw
zXZ%lxTcO_R4;}Y%m6)DUw;L<X`j^XpP%p9~Hpijb{-!j3An{eDtRn_LiN`{RYi$=>
z!F}#rjQjBp?yVSQ>;LlT@5S*zvo-|Z^+!Xla3-)tbMHw6!zC`0YcAEdGpv_=(<Q|w
zhj_7Kn2)i#+V+Ph{V<j6MtqKD4fyX_b`O7iGMft8>DGVNAoRQGG)7r>vg8=9D*j<z
zMdF^Kd7-$isf{U1!=c930$~y#4#yDh_t$N4IR39BCUHt}rtbZRXa57i+(5CTbBj1D
zfs}sm@7!6`hJ)BDx}e4R&+Ot+jqs|d;lXS{w`&@tHA*$w7kq$y(?|Qd5m`>6I?WW^
z8HS$jahiSgjd!C`x*Rt)^KU=Id{>7wCAOaB_-{ukj%LgIrym!aj9WHF*ob?p+j}e*
zWjcYGL%{1m0yq8-<?53aL^XjK)jzpN*GQRvhjg`NI%<^rN5{Kb;z|sZe#n|}u72ef
zQ_itsU9Rzq)dkmdk_PdKV(YY)`kM=$92DC}hcA8Cf8&YuI-Rn*Am!?8_vljIl*TZ9
zQH-p?D|3xH{zDD4<}v6^lp0WUQH5WE^sjUY0xe5<vA9gyiYS^T3g?wNPF)(=QKrQ`
zKdr~(4!2!^5Kaa%_E}r^JLBk`#5Sl>h$tG43vA_hi4)0Z@M4#yVv0+iz5}0*@!=cR
z?2?Hzo#M9m>%O`wZ66$_?Xsz3znAiW{UO9g8T+|z4-(Y4=iV}aa4RkH<@tX?Gp&ew
zyn4j`GwB8am`?6S!@;sI2a=anuz}XTrYqi!M*M`h@7QjZqxrTqUEFM;5x#2&?`)|p
zttbai?rO+(Jb3L<XWwE)6MN4;L!a~lvwc@e`+R?bTn3|QrCa|K1=-vv94*Vn@RVM7
zX2{dOW_zsVjcP-xoNRQRU;j{NGlx>S8Dpy!eYugCj;gel-g_<^iV*=-^$h|0E`9f(
z!mfhLMCXj$C)&@rROIeTiXGN@nFd@Bd`xYPPPw6@Z5z1`;P~?0&G<k&3(40{{9v+N
z7l2@3Jf(d~efqitbNJBE^UeaOd|3vc-vILlr<-E*-;J{(bHV?C-nx6v8Qo<V6|h+F
z78v#j)cF5|q!K`4j)E$nZ`}U?(5uJ;7oa;SBm#r_a#!6m&p_piD$4^LMe<TL(p)W?
zV8F~H9b~ox!RjerxV^`R-*M|9&H;Yn4a5IHuQP7k=xo@uJkZBg&^7un=&+s#^rwcr
zFm0;t-9U<2(LL}Q>o+8_N(SA+cY@1Oyj+x;*^@kJsd(;X4fJC^IT?&K|MB<I8}}1r
zEzAC~HY?`=kQxvWE5GrTysaQalK?cwqtx~lNp;LcrOLPi=8Sja35Q5qszi27I!jp!
z`x&#l>Y59DB}FlBhgm;1`&bK>n9*Z*vgCQ*?7aB@4Y^zx_2_jkN#{lBa^}hyd)`eo
zG`~22n*Q|(c4^Wt98J@1p}(g3Yxza?>l0Msv!^NOZLKiPqT=6+=ZB0HLd9$44&S8v
z;MYD{0S(lTBLDs4xN>Q?cz^eVna}o;L@`EI|3+K99k-ds@veEQVJFVFwVnM3pvHVG
z)n<Iz?1U_dH^)P)FY++a>)-H|vkSGrM;w4`L_~bzO%0qyHHyO%(4bCWmm#4J4Q|Bp
zLCvB(3JPNi^o89|Is<RT+W@DN5P#{Q4heH;^yO3YXDy+l=a?T7s({y&YGB;W{7khA
zHT2~mWa{yBfB{q1@^ca`?Y#X9&swK?1?55GY_sXQsrU0ug$qSQp4P9R9ZuA1gDU9Q
zPt@dYU(hC=4SNT~i}!nMCMj)gQr84c9xR>f_4yk5tyhzv<6@hDg*IhzQw6)VYaZ%8
z<*uitv-Q)V4ayvP&x<`*?fR&_c~cBW50kWuvw#7Q*Q=_kFxZ0*aJP~IFb9||_PEnJ
z{Ie8pJ6Z5idbjXV;7AY1sNm@<aHt`CP0PRMzU-;*+Rx{JQ8%2+i*lb2y_I7_6<rH{
zWs-6ODpREIvI|3)>GxM|8c|cb1H=>PSmfGY4R-H5l6oH{U`t<n=y%<s&Z~gnKl#A%
zvszOd*xV3n7}Up}DEmTrG10~D%VfE9ZNs#NkDhqQtMu*mzb}Gp^<=2SlmKvaS^6){
zr<B*8K*I&#jZ&O@j|kKSi3C||?0Me<_>#cd9cOrQG>`GFw(h&)1@C@Uh~_wn-%UuG
z%WFE;!`Z#Srmw|)|8jmAqWoqp0v4{&{o~B7_hdP-D=!Len->pMMa304Y4oDcRquw3
zF~Tu)*b7Arg7KttBN4|_4|Tc;SNz6#m^kivCr$Eaf@3K2?$_WO-sm&^1z;o<!R+uV
z=nZsp0el?a`sQSnz-`EdHYkAP9!ED3!}-JbQqz;O%tiN$UnVJaF7vm7_cn0B({=CH
zE({3W;d*>2M&sunQ#f80k(%2~&EY?#=SIn9N?=sIZ%#<qeot2#PKjvsr^>~Dl1P%@
zre7ea-y9_1NwA6ulx`%Ms&GAbLy{d~7zt*-&cBAg`*BzoGxh~;Wu5dAmETe=b3ml=
zXXWs=vpkX;GrwMvJ}5=e(>|r0Vq;&Yxz6|N+;M(KP5L3z>2ppzj}bQMA$~kS%~vpJ
zxQkN3q-%t!esxG71ivtD`@|HZnj&-bD{9>}JNmnlf@Z~|qB)5UU^5%&!n-Wm>*hp`
z*ptjwDDri{??T|fgEH3tB%JeBa00q4U2_Xc3SQ>{<TbJRM8F$jmp+i(Pa4;~ucyd0
zt;s!_0)}0bVnU6)CZcxC5`sYufWPfgBi{PRRmH6$uMbSYZ&w37Ruwc%FkKEzEW-0?
z_UKbmLElcbp`(trL)jRqfv>?`1ZPzhGc6yVHZ_JObs4f3f9?Fd87YrNDJq|{ibHAA
z5$jc#2yPce&bQkJh?m!$`>gmII~};@Rn%0<<>bE$7MEKP2jw0ncsd`K$#k++R$8D2
zNUjnhDV7VE5rA&_jAK(d9t+-V?oc2;m?F<qj}>N%*}r9k8M*xlr_53v-SZ&v0jNy;
z-=^O(t?*s+70th9z5P6FJr~Z02VJ9z^F>8Tc{Q)CVk9^e4q{KMSadp``8{6xAE?!Z
zS^S*3hZC@Iiy7fh-hlPs$gqt?@r#q>WD-Oea1ww%EJWG73rqZ?|5HVL*y0pECvKtE
zA7uN|6kZr!{9XNuDw=6)hr0CKQgruz(_-7>>)M31gZd-9BLx@ywTUoUVk>XNZf#kR
zi`2?eD8-E5+Rk@aszb-aM>oDaDpoJqd&!h^fX$Y&n%g(!=An$IyksmFLE5n?RT>$4
zE#QB(awPd$BZ`|LkP;N~zZoaB<6=nafbW_upFOm_xqb?a62Iojg-Yj$<`eHm&bEf_
z+Z8c^*e|)oj)XnvIAj;T=!eg!UMk$Dz$Sr@6K60Z;=A9z=}9Jc+1K1!arHB)k-Sj)
zy<g+%_B_juYJi7N7W>gT;rWWPQBJdjya?D>hrFbL)EGQgWyTz)?uLion{or#9nyMP
zz;Cvvg<OU*N_jU)ma`8-R46<IkCmv{pBRBRhV#*hhQMMH6V`r-;9V3CxYZHdkKl(J
zO!j<0<gIwqfnX=;e-O=9LyFCFrxGa0q6KnSD?mXaa<CYwA~{W2wY%7}G4UOD2m+qL
zJwXhWV2Qrpe?PLF)81G80pt_0O)jxG`T31j0sX^T`&wLt=mnhxX>6RtqorSEfa714
zYo<ktSD=*RV0!zNDJJU$M?`U$iW*P?8=gV7>3yi65!J>DZBm|=kl1#IkeQ~h%V@06
zfFJ0vbG9StcT=oDku8+3&Z9SQ9n7YH5Ir`j9wsDUdx$B~JTqn=O2>rU>V=i{?MA-9
zBh2kT#q`R3=Ks;+^ZSz;ME9vXDhf&%R8ikhHF6CC@T|oAx)#_C9%_sU1ZFCK{H74Q
zOI2Ovu=TV(<jG43-52jo;je>=UiQ2Nf(2zT_T${7X6#Fc>&eKYyU8RKY~)j3uomTP
z8MKq6nvTMEx2?YN`YYrf&@mdik-p`KVNPoBW=N6ZT~4b%4he2&|7bu|Htr4E7IPp-
z>#2L{!od5rin@tcLg$r@U6kDUvA%GiTG%ZS$bH_m!M$$*Y0y$)M3fktq~BN{IA**R
zcFctgtX;oa3Q*@ApJcRg4Ls8P@X$=c#AUlVAr%_m@Z_HwcU*y<^glD5Q(gIiFHGvd
z$HqeQ0^5)@i1jh3_$*rhC^=@WIg;e*DOc6I&fEpv4%9bn&z1eBxwlwD&o!_3OdIJq
zLcVqCZKMaZ;fOTQRu>ozPM`dVcLFSQUNt=hnh!H<{STO~tD)aYR`Uu;>|9<+(t89i
zLe7<FA@O}dVw?^;t|Oimyu<-_yRq7U#}5`w==YgV76O=Qv*SiCP<%{p-b^SVbEPlD
z%Up`Q?MbgC@}7JZZ4&KlgohK+^x>`jeaDYi@_2mO(=>(s(17XULl7$X5S7V2X{hFt
zwp^xv@b($0?NCHxUuYQ>@g#(gA=jYqe%AG(Zra6}C?kvV5S@wY!E{&|R&t#F@#m}F
zyK2_>5G<<UDlY&mnhtc=PWGjAgDUQMej2;lo^XwHv_%mO#~a@mL!0Xu%7oObAKuTJ
zci>FhjnDM1<9^KI+rMN03XpsETM@~RR1wg)tde5OdfT)jk23*a67v)uv`D#-5Bz%V
z@n7ieqQ*Dq>Iw2}etBZ>Y_H=glDt%h>3xn4@M@l~kjE}f6b6q?#fPj2I9!Y4z1yE-
z<g~1$o2p;txb@dc+<(5Y*`@^9!HuWZn>_?wdR!OXQ)>x<<1c8U4FWt>JC&I?rj4n}
zpLZBi>&24fMq$)Wf$g%i+7LJk4^K<D-diMtmFrWW(nm1!EWjRCCBdfdJwl7a&k10&
zp_TteQuUBq)<SzVIC1o%7W6dV+dE|NTj<D~)RWR-q|N&0JwauQV6iVGRq|w@w(47~
zX97sN7uS;9gWAS(!V3q?ak5Dzvua^*d%0-3LbXOXe;33obws|-@*HzKZ5)oMX&UZG
zg|NgEwKmdq)vtyC1&WInKAFBGZB`|kl*zT}39SSR)s?!_p8ymsIts{cSiZ#^-sJkZ
zbT)1O>4*N*A!X71X&4!@z2_JIqT;VKUIQtXQcs*sBkhYK0Hp%BSIKVHK3i2ldWI*J
z4*JcDu3%0G-Xs)+b&dJ`7IRJ1U1ts)uh@E&TPi6O5HG_NLi8vSQf4E>y2qXq04dJy
zB;Is(*$0<yv$j+=a)AD)pi$0F9~L$T$^{`m%<{hZd9~dkA)eJb3=Zu3Ia0mSFP}6;
z0MiP&aaBib(=5h=K9C1#JDDp{hcwQ18i0P_hnjp^yEKL8isGi6%2WCS*WN3Pt(1cd
zf)4Po3n2DNiTm2}Z}Qn?X#i(UGKzMkM=)1;4db~ImSWtQ!{mNNid+V@l?x!ti~mvH
z-0kZ&D=5eaX?nlV5Knl_M3^>pY(T`J*z326AF?_PL($Vz5mPCAu1iuJr63QNtJclR
zCD!@$AAtrhA5|VhJWQ6N+g?FwGy!;z)zgxF63yZg)YZ5V`c>jmSC1M1r~qaj0dkhC
z^#E@ony?2`3<lA0(C@TQ4Ui>#V>`Xq5)W)$`b&pIATCTMZcV~V&EUA=7DNP%ThSH5
z@|C)}A+Ghgf@p5ezN~Cff8}_59-hvAn*ve0@jQ)=r`Ou20nz-K{&h+w#n)0H539z0
zmUDE1DGc8%1vD(yzgyOEQ_vW$b!(eQB#sMV^)X$Ytt<0PEkfv^GSc9<>hO<7OlqM8
z$~J3;d6-|a(cTjL_ZuS|1Mqyz^*<TBp|FFPefFlk)v5fwF)qj{ws`nQnLbvrJap1y
zT2ngqWbnV>SDQR}AUdN0MyF#D=>cCdePn6SS1m<O<DiG3FHN@dKs!9N3o2ZNWi3VR
z#v86{Z#xZEBR%R2pQtxYw}tgHUNTj6j|Nerk;A65v&S}Jv;7<?9Ob-M1#1RobOg&{
zI%K;JRU(Yu@LU${X$vn3&1>n0t^sW7jAwAYNH?)6H=q`UROYZXf(tj)1Kscl@h@`8
zc8(IY@qtUo{G3JFbr14ey|PPWU{Vli{`HT4Z8Vz+V+c;>-(4H=NmumQ*K(Xq`Rm!e
z=1S)7d){6+Po6Rq0kA4ak5&n6WUg4r-kl7~e_GHBp)hfpd+pgCOvh2qv5>o%?3AZ?
z7!L{!GUG-TYF<ijmFtsR3;%IaP#`kXWih+`F5YoqS@U-MGL}>GT_DwB6~5uxB71lM
zyb-^GnJ8{^i%pv8zea(*XEpNMENXa^i8!^4AidpWtF=f4wR4<!eFTU46wZ4&(HS!x
zt2y;yGtn8lRY`sCPb|+nyyIzLb0CRk(u$JaA986Y6-P+hF*yK!pw`Tip&p0<M~Hop
ziUjib^pdHTCP?eCfzBSQ|1H3{wsEny*r^JdU$`u)kNbFR;(evERcTAEA`?2aF%|z}
z4MSwZQl#!P$U006seGxQX=uJ!E_{`hKqHePnB0ya>F-oG`vSpvK&_xxLdiMo_NP<1
zLXT?QnN{AU60sM)1_MN%gcrYF)+h|x;1ClT`Q2jE#{hZZBgx(OH%ES|y&qPLW6VSc
zYPSe(O?T`6eS&Vxi(U>sb}d&L(nzD*sCRRkuA_T*??6<;$=c1hRewGQ3q-c9s)fFb
zhe1BU6?)g(a4Y1_*E*y7%T<UP)XQ*pvr7^$7agatkjoLfYR6t^vw%<SvgX;XCd`Xc
zqZ3=^nAu9Ips}cDd*8Z4j*E%ym!Z#nNas!)x*ie?jC51IvruA37SqS;q^bW<KSG>=
zz%BE6p1Sl!4GjsZ#mw%dn?lDU*w%h@qYA<NdcMRJ_|ZI~@Mm>h{cDbn$`f#x%l!o6
z_R(`2{N)e%o#E~MTb;w;{${AG%WQ!BU8`XthU28TMc3sdYq+$7b(}C(Yqn`{k-DBA
z+;r(%#xje}b?G`KNb~>|#?rxo+leoJ5kMv<l4URc@EWJ@(-}Rn&CRnp544MmhjaP?
zF<XMd#SqirXP4KHA(b4;N(?M2fg}M-5$TuZ>>MxPs512N*V)N{E#tgjco%T-+O<Q^
z7^<@0a@)CfE&wIgZ8fGNo#|-$bge+T4Joy%e>3ZR_XzL^?0w@v-novfS^A|zxsKCj
zQxT3QxYPnBmL&i`_BxgcuR!_m^Hb3<+28nGNZtk+EWdip8^Wek^jcN|5rU)XCXh!a
zsPFjPKBAEI6FH{}HDstdh1y!J%MPgA9W7dj0dn7othr|R6F*LFyyzb(0U65+q3^|&
z;2-;_VqJ3m)n=tM+>E?Sr-cFtUTbK_9;R9{1fY4{tg&Ow{p$t56=4*gflbmRN_$dG
zZ1eCnOagphMF)l0lPpIF!00Ur<v0ncilFEksZ$TTwP&N$zZ$+;fjs9ExD(^Uu@w2#
z!V12+TwmZr70(_A_BvM*+_`u&tgsS(2iy3Vqh7HwY>Eii>x!?q(%fy9ZWkY_Mj+V*
zW*F_Pd?9%FIm-ewA5QT>(%Uk1`iDu6M6bEu97qGCckS|q-?XAPM&VH%*`Di^dRrbE
zEUp`i=XLF2i|sheK&mgSxiz@QQ?^gPNwUQ(O+tSe+LM*=OJ6Y3eU<w>T5eOa=}k^O
zz&zR!Yih>AbGAW{R;XDY|Lbmr;IY9+GM}v4sb?7S$8IYTTj?*P39#S(s5v`au1+Qh
zy4gG}yL(?>zkY7eX4uJib<NmUL%pt9?D_3Q<T&3Ydc2;PapF=_+LdQ1Xz0#lWu7?|
z^=gaIpX{>uziY%Am(ddI1<DW0Uui!3#NKE;tP5CPdo{d95ht5dt=Civ2~)AL&TNbg
zt#0#Oa~yRI+~dam`vZOqtNf7$L2kavt{NQ2CbetTIuZ9UP=AxJ60MA9(`aYu(vjIQ
zvF8n~eD_ywR5!<%?R@$Be}%#k@8~dsTrIN}G~4$z_W0Gl)PWzJL|zW@M;za%aueVb
z6R33z!o<AWD1C44_>I-3+h|cy><~BGgQr((4H~a8nh20+m;{i|P>@#KzH`&KU?H83
z6oPzLJ~`O-W0@s{O{U{$n&HTxfe<o6;VZ?Q4wl}dck`8$Vj6nMm5CgAxppUqB^zN!
zD`wygqlVanl;zY5+_m^3J{NI1&97*tjePrPPa%1HZpvdIiC$7Q0vSNJNbjP=wPPH2
zugS@T2vxSVmGp+M-`~12m`rkSkLYYSBE?CYU&;g~Zp_>iX_lyk8`HpL#&kKE(aX6V
zzd_^<a(=q(+>J&mYKSA+aw+t4o@ts6h0b{8n%zOV;9!#c==Gd<M7<Isv-QjMd-DH~
z7$1cKEj5%5)C9J#3gXi+X+Q>cQY!A*M4a|}kN4zyt16v`%gfKcNbk-@*6tZWMxXQ@
z=<zA?M5l~8^P}-JmbnR8t!YwhIR3d(^-~^wJy?E~fG<~gQKIXgFW5<4U9~bW*0Ja@
zAY4_IH|Uqr;Za%0N2wid*1rA3fpY&)&)W9B%wo5Qg65;|$WNCH_K#Y1oTtYnu#QnJ
z4-|{<(e;j}Yt2}2Jm2G_Hh3U@-1t}cu9cwm>9al5#mB>!Oc%DN;uG)JnHbkJIS%kN
zoQ>a*e1^#$U)SnCO3AkWmwY)~vhVA|{okCBb+)|xC+gAdgnZKC=2m%8JK}|g_6Q54
z_a*R;RW%$Z$yUOGAsh4NFK0b@g*jdi%!DS<@?i41y^7c~>ctc($+e6K+Xzqp4&z$h
z_$QG%Z!uj`s2XPXzvqo($}apmFbzFPuqE#O!5JD*2^Eph%P#8m)pEvG3vhd{U3vjF
z@dQ(sJ1!CB&SM#mCSE3Rokkc36Ju~x+WwGhb#PpuI4ka85l0~2^fxH{S=-Sk^tA0s
z>_W13T4709%CA-$-&g7tx~7Bn&a>i1e;s;R9T=<r2Wq>B8#5n8+KU<qMON_We__0H
zg?{rdd(9>yJ+w-s+Z&6c^_1f-b{OYFNOT!Gu={>yFU{OHql`&r%<^}FJ7~3{p7Z`@
zs8j`dd=oaFsv6MFTsz3AiUjpJzT^HDHZ$i*iGMUt?V#c9uQ3{S>a#l=Aprel{tixK
zc_wF+^5As`>e-wRrWCkBT-Gei_`ms}bk$oXi_5r29tHaqnG16nKRv5BKyyiOp!^L2
zZ*}3==WmSI?0Z=g?uqShuIC2SzTK@H1y<e6juOmc;`GPp6LsH;FIR{s$wv60{{z)l
z7I=a5(S&8xSNsiMiBXgv|H{%85n{q~sU_>*L#Jd7t9G}+JD;Jw4r8tlOt~|s${3H#
z%5-150{S%GJTtL6w$!<Y<821s^f&u_RA%GYB9me<pKRA3-_B69kx+S9Fmo__256#&
zZ~NdgV0^r1GagVdPoST-;v1=jE-Yd3zH;%t)>X%rSMwvUylt<(Yi%%Kti8GQGtzdN
zVT&?e9*@!MUsZ#}@)f>w)mk4>FA)H@i8}X?Il@Q}2k!LD+PwVgr|kMAGjd-p{Rw`5
z;6BoGd)PTU??XtAHXv-1lA@8eILORn+K&G!L4G<ANCs&$`RMMkBKzX9{2qV{F_W+j
zv1hqDw5T^55&<ulVVqj#4h+v%Bsdc+1;7yc;|dp%ebC(;O*kD0+3fBJWXhVMh8l=^
z0$c?<WKWr@Dr9K`tYy|R9Y=83fu3Zt4R6<Ef2kZ^nj2EzIWqfDAzG$Rg2?vf4um1|
zwX(fWz4)Q6o}X0zsU<i>gHpWjtH`fW=KR1)Z1M#wKz@llY%3Q*EoGzT5XcJtd7$|9
zO%v{O!o|Nyas}gpxnb(bGI~AryYQY>RnY_Al~XJ)_ELioLsbMw+;`j9RGBi_w?`rY
zBuvNcQ^c_QgsnxZu&Zj-=*B*b-)99|@gbS!(cYdj+AyjwKz-~#$e}jaSi^t+etYN;
zvLR2yqj|tUcZC4+hY|$FJbjPAR`U1^1B8mX3LwBT0I2*A?tzaxqYwR)E4D<`+l%_j
zBFqoT)AlYRa&{&E5bxhA{y<Mrr8_>?z2&a_vz}XB@*z;G3>~wT=<=tJpg#NxZ(oU$
zSuOvE`Xc$m9Vs$*S9%)&yU?wG_wfCJtVd~F-u`UvEWN1TrX3JVGRF-~1+L}lpr=YF
zJ-A2AAeHrQ6Vv{S8ol-+a(ug{c{Y<b{{vaz;Z6nxK{=8IBzMiox~F@&Z&-A`T(Y=*
zcVjj|q&zA38R$%x0IB2x@BD~6GK;vsv}5@=^0=?qD@?JdJ@yvJ<)&k7bx9~)^jX(|
znB7kqx^Gq@@EZFZ3W&C<4#zk4knp1nw_JnU?!iZGSih}&3CxQ`OBo~vpo1H3Z+?FY
zGf>6HtKHpBbKJ(^>B=JVB<V+xnD%P!+0moHR`YW4{pZxTKEEgNs9Km41*7r<HzXLY
zzJ#S!jI@nkR{sywB4qK_Ll3gUT(G{4CCow_w^J}D)^xenlk|uuRJ{_R$aTFOIn={V
zcZX+jB+FFhVGYwCA-SiDi%9kA!T{|s0|J=POU-)}JdJk|T-hejTYsIxfBr=UCfIpn
z1&jefPqT!i%BV}mL~!l*H+CN(t~;HJ6dtOe%k`KP%RMH#_eF$K%&2_2ls%G%uZ|_6
zAB!5uZa);W+V2q+gQvK?DBnY-TofOl#e?eGLNdO2TKcR!Hch8$?C04u2e@mcTGPF~
zKUBR9x_}GK`zzJkk<XVm7vdJAxc-{azG+f;(IDSsi%}oU_)g$O*^&b>?gfypgwf}{
zW5Izfv%9STCb{Z0$Em1Ie*EVZ?c7Hd+SB&knG$2LZBE<fxZ4A_yq(nis30|;*~nZB
zHy^{8k~+y2(2}Um^s2|jaEJtfFn&cp_5KdpGcNLf99?x>lke9aAPi7S0qIdnNOx`s
zlF}vJ(%n)6k&qe<0t(VdDjm`((%sVCFkpjy-{<%K#~*AT*zV_?b6@9*GKDWC#jr``
z0kq8cqgRDSIj_w5T$`2!wTW2NKyJTTH_;p4gpS$c`^^F#4&p27eCYms^@{JDB+Xqw
zF=<05Y2C_q$#;HDkcFV=e2UN_F(urQYyiJAr#!#dcXO&8h^(mH3(w8SRWaw4)A{&A
z<2x|XN-AiqBS(8wc)WuwtymM*IYLKT7(w`Q0Yru4FDK4>SrYmMH6$X_KQVU>?4`o(
z_aF4<0O4OAUTh_!cWAK41oA=H^XbUY)q=W2W!7~A>}G`d;JlH4A$>E?M6*+2#)Z@c
z{ftDePA9S|x66TP3DbvTXf<!lMW_AMZ0li36$2&@RhY?!obSFo^^lq7iKhB>c&Os@
zYO*kv4<<o*qXTbt#veE*v|wAR9=vl#V(N+yb&u_GJspNU%1K3K3ikNb9E5Z3OT!Ok
z2&Ww9*^Y*;h}5_%tshi?=c{<v*t%2Iu2T5>Y$m)){)RjfPujU!7orm*=Tt!kTxMv4
zd$hCFT(U9HXBWl6;YN^)D?AN3zz>(WLPOM>mi|rkb54>nVbaO^sKn=Onj}R|eNN1I
zMDd&L0pqy%Lg?GjOP;jQqk!3H(;sqgsiDoqBQ}#vcrq|L+tP-}id~;2vN`NTO0!3H
zFRCcK_GVPnI42Tr+E0@`Io9U&|G@{2V)#{q85V^=CQo~ckGy1vTqNJ>_pF8;84zk&
z7b++m=A>ZOjG~UTh-s8=Zwk@4rQ#0b&s62ZT=ElseT1*>Br4{=qVN4l|5+HaP`5R@
zpB4s`V~eR-ZZ2XIiW9Fakbj1p>XRo|OG=mar5;<6EK5Qgi;Prvv<LQ=S2lxW#Tq3-
zp_c8FiE&0xn-6P+=-;Y&rPZ-sZ}V#t$th{H#NKlA*Q*H;Gmo{igJ|lL6S!&F#tDh*
ziN$KYmWny5E9Z-+wtP3Yi%dhtgO{vU{}Eb9qU|5{jy`K0&L$qdd$jG00Pq4-nL<l^
za(WyzKTCLl;Evl<x(@_4XlILs{M8h8ddPch0w5bpelqmwcKZ#92a8EkMkJTFnvWv?
z1O1P;%Lo1Hu;wspsDY9ou?9qdx~}Q-_v}t9mQkdeXN5Rp$SDg8-X=#4He+`$c7~`J
zi`H4C9Vu<DmfrB~r4hatlvzDFLO%hc8$DWw#VYvbF2e$FOQ01`#fo`tS-}Tz+!G5{
z6Q8(<YO{H?ty~wH^4t~TR*5k@aBkP9-E)RacqWh(nbbA<Z`r2nvCvs1$s0R4u>1!y
z=Cfs}f8VR#bZO1dd#TYDBmRznIbkMV<P(kTNJx(~me9woIV1Vs3%FJ1;S-K6w{Ufw
z>_}F>HJORy@ynpU!6PgV=`5!!jgaFk3o-iu)u7*9EGv61l5*<50N(&ZpnusqfbK7W
zQ88@tAzMx>t_t>*|1r`OmzcT>cB)-7u4!%MaX7*pkE>4lovmKz?e~H3ZS3ImL<7AH
z8LeJ?r7IPM<_U_|Xg(7LEEV_GiL|DMF=;@UEBBV<!f5M1P^%2~!J>%?*PGn;WgU&&
z6diufTM41XoX;xeIjCygNjy{6tK{pB>QK9JQ`qq1X_l>8&tMOwme%ig-glg=vqR{H
zOmmeFvnL||jM-twnvcq>R-gJBSWmH3vd`4Z<zA5wRB7Dmc~qJKJ8UfmufxSu$Hj7D
zZfg^a5SGP(L~HP{(pZB7?r7TsQ@nKM^vg>VkF+q*amomP(cJt+Xkclcd?gAE$?4^g
z`ue_EkWpG}U-z#BI^B}rOpFRIiQ5OsN?Qe6De<7}ORw^3xe5Vk#}X;G9B`40>sgi@
z^48HV;01(&Z*@i^%F^ym$2PO%Ub=AZX9zf|8edRQkKd4FYo|UC$#@&r5Tj>ck+4d+
zm!I8-NAq7F@2hP76v}$Uwj+^~6Tsm3V%+&A-RX{282c7ZgkDkd7zF{&F|&zvjd9Ls
zcVt<!J|(_TIhXBzxc882J?~Q8&OcKQX)p!pue#u_mrwbRUWpvc8xN8vkjOe3bN00^
zZ1U%Fv|CBcdcU`nHMyn_oNk>^9C^om)HYtt{Pg!Pj>1P|4%*A?Nd%f7Dpw>m(#5=Z
z{sX1jrD*si&o2GtvwW9Vak=4*Re%=ymidD<`Ow(djxW}MuDa;;LtF2<Gb`(~Vjsah
z<<l(K`U_wmG_(H;AYCd;9KK7KSCfQqst9vyp&b55ZZ&uSX}If5zu6v_G;Z*#ES?m1
z9#0tr>||0x7b=?WxXB?Q98X<*G7&F@Zzv2LTZVI9Bm-XJn5AlpZlgS*UPBgBc<Xlf
ztxo$$l|YrPOt6P0S38qst5tOau4G8N%+Tv^dFOzG1Go9@NsV->rqGJo1*{JLo|CuM
z>4F!vg)^=x^x%OIH9*m63Uu#3-^5t)-g>Chu%bhPW#tg+^;&iD#>sQXDbue1bj|1A
z4baw8!z8SDd7|C@9G_x{MtG52Od(DS@YD8=N<DMpkwkN?#LWhKx5rW9PIuzREuq{*
zPdlIXUw>x!<y{ibqHL0pLzi%&M{zcjpOk&!aRuNg(#5>oewPqr1XBiXaRl|iSE^0)
z)k-_9I*ozGJ>d^vj@&y432Yj=8Z44<i%NZ8gurP>Ju<iq5^6@r=f2KzXg}NVj0xYX
zHy%1`v-9u=UX*hKrI9C8p`ecvGSO%7aUmdHrxx3V8kRjbpCo@;lRl8IXIXk{1^rA7
z9nxy($Ww4<dIWgg#?`H|O_9bK{=Dfd&ZSs<mijXhef(pyFM#HvVc}*$J+_a=do0@J
zSMVHpm4MGVt7p*9{UeRZBFto)tM$}t@HZ;$c(r~*q4UE;c?oI#t#a4eH&?^(>r!l%
z(gP*Ym*1X4>kY40l!04Jh{qm5Ve|Q$GbNoPV+8tTd1K5;=6!=W3P_H_o<p|RY^DAJ
z`I1k4s2nUuCw>8n(GLJ|3R?4BgPc86MDA2FCnxgKciU*<rieyUu`dkN7@70-^0Zk%
zbo7X;tLR)BhDM1gQ`h_>TKSM<F^`NW+Zo;NoW+2Z&Y>okPfzYu26yhM9t_s24Mdw}
z!P7Q4z{67E2l=4@5z)qp3+hyX?bTzIYTt-%cgigr`mr(GE5O6B9yRgv_2hNFc)IM`
z={Roq`rY#Vjd|pz8UwAn_;2X_jK-0)A>x#$koqb}GYD2H0-LfyQ36Xi{}3rJ&)3(0
zVGZ}dT8nuvVQKsG7B=n=btDRou=S^a5fpEH%HaqfH;}fWx3jI$LB2idU5dC5W*pO`
zBK#r67$sRvg);yGcsI`)z&p**uU<04=2qj0TPtjktH~^uvxDT2$uF?uX`JqKTqV(*
z01segj$f6WQ$IL(@K(F2!a&gf1KyN-4yvAS_4b2?AQOrv21a7<=;^8zRXf$6w7$(I
zpx`kyY#SST`NKb0ahMGwF->IsM(gXR(p@GZ#)h+Lb-gU?)t%JbC!EQuc6(|dQ6S@t
zl!3|eS_QVwJ~5XTotwXr>3T2Fv3wsd?qg2EyG-bT>B<A$HuS)_vy&eF)xo<BUG7B?
z_dm4C_psFG(*^-uo-n6lmRyrkMVItXdJuPYG*8t43Yysquk&~paZ=^3-37WXkq=?n
zk(O>im67kxw$-gVFDSyZ>y_U;rztLR0cX0T=DuG1S$MASqX#1`7hqNWcH_2(KHWG<
zH7oSCMRi@M4~h;2P=H@Q=Y)H@7d`@m2i*QPX<!JudR(`p?<TC>_>tCuQBs>-fI8(s
z%38gqiGAz2G6ome<k{Pu8*esFk#}tztHOutK1c&p(x+c7voo<#pj6{Qa5kJ=)KCTr
zoX|rpB;;v>sL3()?jv2rUZd$xE}CGE?VK1|y;;MkQ~q24+o1tvqj`H-&;3K%2;Il)
zcig@mM+U}JB9DU+f>7xs2kqbhS@<ODGT4VI@6GXgyqSE@0T)NdS+u!`U>U4kxioAp
zC-i;Fa=6m@!9eBTa12;u>(ORca-?MSGD545^Hx~m_vY@Lk1nNA#iz8EZ0UZKve1Z*
z7d1}~c0h&@miMj15=?l>x?N4oU!n)+fusF<%dExZ3CUWsH3GSq(<1zL^YfTlXwri{
zj;6ncin>|QgIQLPWI>tB6z<JhoSxp<!(XRd(KrlqRy&;oEiX&D)X4(i<1A!OlDA_p
z)*LiR1nY?fBqP@MMEVT$NnYqpgxYV1{q>K_AA0G0Hq!Hy#&7)@qzX=BKxe3R<iLQO
zy2cY$_{Dk3@>KrWwBhgyDU1;0ws=K3cxQeFz=ni2+)a1z`4Y&Jh1zE?ZW*ul*j=8f
z#CdT3^IK8!Wx>o(k`txhT|KNomI90tp`#1ZP!%{*JsmtEa5=V`=g=a{0kzsZl!=lr
zUr?GiwodjKr0}R(6zh5`04{c{tdEaQdmol|J}6xE>*X?R<qA9O%hTJi#E^@>q0*eK
z{uyqgT$$f;X8)d+yeV4n2)h}q=x?1QzZ_ei4P^u%%dcDLhE9mPqu|ElD*VRR*TVMZ
z`-Fm9Kqj(1O?qmcO9RVZ9hTO;au9f!kPIQGB^vGXG(=aUQ$Gq>9}T9=E-Nu;0HUQs
zrAuqb)muwzZf;a{)EmoP1{pmb7Jol<xP}~OlL5{yaluPCC>`wRnd@X?yMYM_o%WRq
zevmqF8TYM(ki8B6HHau9uihY7iuefY1@Nyj140s?ibkk+9DIQ)Pq|`<;n5_Cmwx0=
zsNfcGgAUV<cRUp*9k{~#`f>ZUTP5sVHSlbDcB;N%>r3?2s+SRL$?pN24kOemJE*=<
zf#gp%CjOl$a8ieFm(ka9l>E;*>qibS#cke|yOcUv9LppOG}95<Ene?Bx3W6zNsQxK
zum4tU{43{s_pOkDy3N&m`|;jg3AJ!=+j7!L;H1!E`Z8_CSSdNa{aNL(&1rn_SO7Sp
zN}0Bb1zZIxb!D6WgGJHfN<Sjsp-qTm_B1$!ymQi=aIoZa!F|AVc=z@@4D@4T!>bqB
zS}ZW9l!T4!*bDL2ltYC)7X&dd@MY9I-{Xi~zkN-F{F_^3gKx{|_Dum=wBJ47C^`RN
zFi~nSBSDmVzQR~il~lre|C_CvZq{hwJ4`72JRq4{WKrGhSZ7c1I**8@c;90^YtK&l
zr<}3<NkMR@u&Iy>f5-Oj2dVYI=~&Am<3ajiSGuqq-DTUp%9R|lM-iV@J?j0-vXIY4
zC*i9`-5ENXz_g41g9J>M6?X{s8<U_z4yb?{;V*J7tkyqPiO~z{bxlm2(yw-xX)uqy
z+zBZt<`kr8qWc5m^d&1m{-%CT;ChQB-=6liKMVP5e70{GcvJvf0eEp579*-E^e~EI
zz%hu$YFKPYf4$@swqGkmWYtM>i{w83^)vZKV^k?M*QO|NSeAH<FECZ8a~`u;J9Zx!
zjAi7Ub@X_sVG!A8GvML+N%HO!Lnyb#Ly;|cO}$mYv?lJ<2FU-dRBk2H9R2IQZzQ`w
zd_y(0dHNV<Fwo!)pRpSKLs`XQu_6Cf^gd>gh7T5tG<w}rD%vB3DmMtoBPe4)|7*BF
z)}O1!a=p%V;iFeoW`px;;t7%fxEWzgQ&n`avG6V-6X2VRMi;gJ4X3{Zh_QK2S*gDn
zW!R}%9F4xyb%UfEF12DuG~2bw$I9rYSZ7XAcPtFuUntAV-gf6BZgKga4F#6xCvRin
z)clw<Uu#tEPQeTcA-_E|&689;{T}Z|{flWp>`?;y<CO0++gc6U!AQa!qr*3zJ$Jgs
zJ`w0>S=4cn-duL;zXx29@<YatT30LD19<>}VOas+KL+d%)F@G#B){2U$J!5328{F<
z5UZVd87BvtgwyN41xw`NO6|_BUx#+vIW|>hbLk*KL$Z5WU7Ey4yJ*1j8gHVy3w*4|
z5K-2n)XWi;?QzW=lYs`mbB;?x4XL>iJKizzxRX@A3LQJLV|nlb!InnE?AM>;xpTsA
z6?q8}{1?l_O(SCd0mq7K2x(8{JOXEDuF6Qe=J-rh)=~^|!MYpY1YT?Cn<dhNzT6Sb
z`=@vM^TS(oQ9Ss28GAvn4|$Zu1v6`ia8{N}3O~2^^KYSgW!@Y`Ukd}HJ24dWWdN6V
zneQh2+W<M%^ZB|o@B>?JrQD0($w|K~I4^D;8E&Kku{6v{41cUwrDAkXSfK3Q7tp}?
z`C}c53HQK+2gf-iMJOQI+P^Ns^w-e4k`nUZ%Ah1RZ=9F4zX&1jw!HTB`!k9M1{PC8
zm=hgZ#3aq!k1^ML90YaWC)c)binCYf71nCEkbU;Sv2XN2e+p5yh+lg#;y#_%g?QF$
z`&;W))+k*yA6s$Kj$8e)w0y=pQ-xs8muk<zPA~ZQM^?(oKDn&UJo~yF>SR-uOdFqv
zN>U{$W*^GF$lnkEx4DL-POy)W4SLM|b}O1qBH<z5Y^DQvE)r1Kj72bi7N|R6|9O~8
z`pt-v8w3-KU#T#C)em8H_Sox~O%pbS@+8`zxf%H}<6Ys8Efbor%BFOiEgOe6r*Vvk
zDh<L~kCxF1j^e_HCSZ}J=1m|Fy?%ML!yR%<Fe1C^9L4=O{HVTIN|DMXe>yxzS8c<-
z5k646JFY{mBHA2%pSbCU78hoD8`68CyL8oO#K7tcJ3kEDU(G_b0@SvFU)OnrA79lr
zRj@XCa(tZAv3MN|du@bcoKC?k>AniEgK0a~8@sPiS=if3N5TSrRH-BZUz`E64Z>XY
zy3^zAf#sk!3{{_$)AK#TLOJZvrunP#i{al?SY6_kI7QvhZW7j`kNb2HnjL8!L8=x&
zK%kL_(FkXhgS&><p^|M-mM0mynH5R#W?%I5<ur?1&~NXjM$naf3)(q~6v?&jUK#4_
zhebIu?^pNO>ac$@F$xo|ErN*AMCHnw{(-SM3i8CmqqUZ0@jZv+ZgY~A=AowU@NwPq
z+Yrx!n;z<2VbkyD1XN%kj?B4D;pkC9Uci)$xdzeO|3EMqk|MENyH_LKx!vXTFk?pC
z6r5&mZF*jP{>`x$9jke73VQN*h&oZ@K~k|dt{+M*$9<UlwwgWmu=Z6`dRoGj)7xy#
zPwJV{Ve61j)no2_5?;y=5uh=Y79$E^xIFY@U8ef>Z_14C;4ruY*9{XqdcyGpTed?*
zq;!sd?{74n&RoxhOJ`1rw7l4@OEhf%&9k+#JX{+6tPdZWuh-NuW0PtA@5Qbhe@Jot
zZ1(-lrC~b5H*QS`n?z#maeyx07vNm}(iv%wEF_&k6al2MPXW_*J_~L)SxG_CwuKve
zx!NA81dGzdQr3S)6nE?$NB*QtZ`O-@bBhRze^tKe6ApqE7Jvmp1MK{axIk`FFa`p$
zlVeq<2h!mA8O0*7+{DbVoA$ykUZJU^;_EO*6TeXoEP@&D_aH02U}8b-;>x1@6Er^*
z&B<S~hlR0Ia85}N$dv!igJ<n#ahHd`WHvRmLrS5uT+9)>Aq}H8Py)F1o5B{wv2g+~
z`Io2s_SglZFM=hf@MJMewR&S|{eqKu<`fI*-EVqxk#N+EPgR}O2T}lyr6xds3aAc{
zdB?y;JpWcU_<~>V_Pe#z5?#WUd%YJLh<9!rj^n$=PP;ySp}34-xQYb2;-`!ev4kbb
z)|p#3H(T>`{ON#c9J8qaIa2KaP#RZ2)VDl29IMb~r{GHlRqMqvGe<w<kxZOu-ea91
zFCmlccdn9NSx%1XF@8&%aTgp0wl-O_WlWMT_z=~Jhsp{Im)ga(lj-E!NXF&<fqmuY
zpQoQbU6e~W;`{_4i+)l@HK-g-9}?0bs`rhw2w<;*I?%XPq5coFJ&$lH21a@Uq2U{6
z8@4&}Bj#tp8^AV)3%IDk;+a?d(-J5IZ{gPmIvX4|FyT)fCOUu#&lFTYo9XIKIloiE
z?p%<c>h+0ok@>As=KCd9U%a$7<)C}GT@CCwsIIHp@r_4G_*HT&lgZPi-V5kDXV`v{
zen{U2Dfm<~;C}7Fv8n}GeNU+pyPEq@TV4Y`0{UfVDb>zokjwz{c1YpBBn{KYMi*zU
z{ecgTOl5~uV;MBN)gxJo)7K5_xUaA{&Q8j{xzXjy&Qma+t(J_NDW3%O=*8beQ*G-&
zBH@*Im*$p(OS%1-lmn61SaEA1kFtPRS)T05g+VC>{~xxdK%%%);2ACuuHf3#GdK*8
z1+YFy3Hq#_K_&si;jOL}f8`sBT;@Y8KAtscb;@$Ga>N}RCR2w6lq~!T*O0(s%N6B3
ze|6&GO^C{H<dP1j@o_T!iZo}hk$Mp?^ZB3fiRSOoEmE)SK`T%oSuLWXi-(O7<K4A>
ztW+hxzOw%f_tmYPwuMIsSbVecRUF_1YZTD1=@EJLh-4Cgl<<-11rPRDL(D%KBY2lG
zrZv`+v~meetJkJYf0u>%p&!3huO&erB<=-pY_AyXmO18233?2oy}!+uMSZ#nMlZmm
zcEU_@>;sse{v8Z_IMNMQA4fh(g`IJR1-&3_ybo?z-Hds6R#dg>>Mn7SAC|%@!Nr@J
z3XnSkQiqH2hL>&7GuG=)Pk;hFChbXN*f3F1Ib{3AeEGVJ9d|U1j4l0|QAe#m`ffQ7
zx%F@6bEWr0{3IiarUK=fx_pOzecDoJ4PdLUwUTNP`b9KVu{q9id-A%$5QSChUF)@s
z5rddvS%L_5d7-y2Bv#|13HxdH>PSfUsRt4ZfoW11=|ZN!7mB6IBBS4LxpF%Dqc^$w
zv(N_24{LYA|9hL7J+V~yovxYf#~5XUJ<%3MGm+y{^-i(d{Hc6KsQ^Ih#}-{?N#KF`
zGfA%@s|lN#jQ5k%@1MSx$6<z(zw~T4@p_mBFyL<WzO(d!lJ8{@vxzWtsm3pzcfB-9
zfSLXgWoC4?*_Z5CZRMLH%xW9N_wV&JfM)3xAzGhnAc^5=;6CJ=^T*Hj>wrlQ#4&eD
z3<N-xk(ZcsY`#ws-vcxM&r#V#(v!PTYi~#uC<Wb8|BU%=Ud4bQdNTknfUwR50vn9F
z29;X>J<}Z8_>`F3P@Vhd(>ZyZ+>3^ZZ<VT#%Rf{?`F<uHXL+>F4&7P5#@rYc2fg(+
zj&%ils6tuWt$Y{P;caSIo=YOXnb!YYZ!Tul9F}%)4Yy9uD4tW6`Wp*;0G_KPHB&bO
zwpi;cA*|x0+lVMpWyB3fe1Vf6_@;5!HJCGO`ubPT<ENr|)CFio6E+~4-K%aA8}0A=
zF#T#(90h}<{V#W+0Va&Z;|Ee5s-<K)ok0jAeavbKt|GJ~%fi?kpK=sEM7tz(eHLR8
z?)d@rA1L1Ljt0$c&UX=DO{azA4%)maa(Bl&IzN@63Ga6QL59r#FvO_M7QvNP3v60~
zW(_9mGn|Lq*IR-rH87pCbnt<xu#?_#yl#It4K4I=q?N>b1O;n=ZQ3)yi)M%+9;jyb
zEE(&~-(-S=dVti;ChN-;afY~ixWqTDuM*N9=~xGWW$9ZFn*!Pk5{tA^5~5{qw1#>Q
z3u-o^AzRAnm!d|Mg8_IMnz?z?iYbXHy`kac{Tmu~YSdxbsP)(J7&9lVaH<~Bq#I{9
zSI?AKTvWh(pI8b>W179{O8NzrqzS7txKK`(UQ_Wy(&vY@yUS}nBOzOO(<a**3>sm(
ze<5PQPnM`?Ri~K0zvL^3aLq3=B~dibY+~3hTYf{dQO@T%(bzEazu)}H^k-?XXODAn
zKS1KLjikRIxkr(xzaLuR5dG<P0-LB|lJaV!92Qq-3B=P?aGoxBTkv5NH|EPI>ZlMe
zpX&Nbv*S>=nTwooQ=yLmWYe_W*U)D66xk5=oOYvFq`83UK<tDxOeW6lR#_O2iZYty
z`v_~m&Ub!mq_cJPpZ*5;I@2VnyBwNZ>NdI4V>@Y&P!o@A=GtAx*cn9>8CL2vmRQ3_
zJ#@!!T+&AwjW_JuCAQ7^{5*(o;C)3Q$|cWNVAhRHltBaBK_2h6!O@TN2t_l&AaDuY
z&Iw-*i}5(uIR;h~DN}&*WSHh%v^i~&<(O@e%VU$Ip1L?`jV}+cWHrcFUU@iv!kQKZ
zO@sRyd;b|RvXt3wgmP9#T{CwGjgDZ>K>$a*ykA@pNZNpHs==Qf0Ddu`wUf)3*VRru
ze2G|Vc!Dyq9P95O0s7YSC;PzRqDKu5UkSfO8=Kp%`zA}i@lbKQzL6DCq66Y0v~iiT
zUj4gz-_r#BvXknsz#T&)4_>Ur@lSV!1%2`xFnVph@hpB)9mum1v<!mS#^y?bXT#Ua
zg%^$F2G02_l8O$U-QT-wl$F3OoCKcKP2wznQO;BN4k%qE+7->}t|qR0=<aL+8=N>{
zgpP_C*=IbxaEX9hg;V&5fb~@Fc^*;PlsDN;ZxAuDL(o?|sUK9}LxX{?iyXW!GNbCx
zg#j0Rvar7~As^F1=hPGx8(9b3^EMNU3r$_S^$Albk$ArbBK|22pk6<oqILB5jy^Ua
zcUKG%&mZ&?`JT+NIgpAETNN*3t^W*c({vyjDrI<sl2y=puVeKd0!9{kd9|c>0_KJ>
zy-7%B@Q>2cfp`n83*%;#ypGvoY-8`=HLcaMuaat?mA!2l9@u|T{qkS_2l=U->yE3J
z(Vu)%Hz0j5*f<r<q%GZktfZbnv%LT=R+D5_y*ZEQGKqEenAh{#$liUw;2eqqKJEy|
z>|<{5T3pzEiiVn(avXNqw`Fe4IK=U><(;vQNdN*<|CZrr)le(vbA}|yWIg!v)jxcE
z|07c1rNV7$wpdFH@PA@?3jXc0D^Ro@HLGHrj^GA|Y|BtBTMlu3UXV-};DN^>jmzJr
z@i5GxI6W?qwRkw%(bk+AIQ3j@MwzxG?Q-vdbN-yWH`jCMC*sr(sQxZ%wf6vtSlu4`
z#Y8;|=9eL!znIt9wvrSq!1Ku@|CkoXsPz7SpvA0g1}41$i@NLfnZZZ0c!9`brtlse
zyk!$QR3oEK$2#p8s(%dqRvoQgcOYAgCvH8$h?!4$Vbj@<2PgmpZnc?P!$Vi=`OYpZ
z!e7c<Q|MJ*_sd}tJI~w!?{1?kE}sUMUmBtCrLn6#`QC9xt*$Md{?E>BZh%>ero;1*
zxWTO($ujuQszRx;M*1F2=3S&u)_E)F`bB9VkvRBCuIY@be{iJe=xb;jrf%(4;X7+o
z>WTEIJ@(wf)wY?L;I;Flf>7@77Qt_u^@@;)$^>XoAn`TFSsy|n1>mdZVZR-rkXe#4
z3Ea}<Epy=CeELSPU#4s<>gs$3@U_rYE0}+UQy0Rkil1#XnYcRwUeQkV&sJ5(+dTbM
zgc+OCi`?57sPa-r^CXu?kx?AyXg-3SWjGuNe9rC83Npu{zF??$Wq;1_goRCPMDjR`
z%Q`BKq>>v{DrK<bnO^ZnY?%YL&if^^LO=c+x<wE0T6yt2Kk0<Cd9JSQ{s#<8rH7e;
zqs3PXDR;@BwA0{H&tV#3gKr#HQ&DtIlqdBDALXGEq~?}DN<sfqrPGxxZ78HYP5t0i
zgxa~1E{XcJ3NKl3-lxc??MG>qG^We_PaF%$(#EKZtR_ZH-d5(ON%fpO4_77gk4~mk
zCFyQ?UNapA^JYJxDK!}iv}uhd?rBt=a2KRin=`qevcQlNk-W1+5AT4GL*$hej-VXb
zUf-_LZ~uYxy_)kh1D{;#c^D+#I$~trnv((WWjyaabHp+=&q5}#;;onFL$z_rw!M<c
zKb;<@gu)LhBwAq_md|p*-RfrlP@Y%o>u(K)i1>HEujqx0R4av?Oa?v$mBjNJr;=V&
zH=gUXKBkO{bOyh(z22?lMN%ewsudp;7Z*14=GMwQ{W9cA!gh64meCUszU%$vNt4v2
z%4t)D261e`2^WZMN=kRgI=^@w-F7nq2wU)HraV|T9S*}+zqM1QfJIqKDtR-HVt0FW
za4sC22dL3N&_LoU?if<*K3<Kd{6lkGfEO9S=%y(yg>QE$PS0jAG143#CILR-<AUQh
z32;tpr+{$!HA}>PiZ<<U!)B*PEaSo?!uOeAbt>r)M?8HOH_fGsg?{6ymsvh8hKPHA
z1?fu-d)@^68Y<LOK0<R#ICHZ@sPl8Zi>)Bg>DU!3C8XtylN3>0hS289Hy;(uzwjq%
zr!_^}QpyGsF(oc$FTA_?Te^ZzVdbRU`LNsrt$#Z*yQpz3^5D<uz~JJ4Mu~+ml6_^`
z7|rbdQ~ojH6iW;5{8`DeE-I_>YY^YxBoddpd~T01LB%^Q%T%RvK{%ZXtW~Dr{ISKC
z0;AR~Cz*ev9ck?KGlM&OHYh?X&dTDp2Rleu8BLFwG|#(pXWjm(cPx0@udnItDJ1~*
z0~(<sqc7oGr#R;O<%*mqqny;wboXH@rop*h;GNGYLu!X*I~&Z^=emy)I|C_F0elS_
z?j_TgDyWyGhjj;RZXM>MRrJtH$T^UMb6*ClEdjZ<r~MW$vS3G$nA1UyS+4tm=&9y6
zyIL?Eov#8`;;kOvwk96pj-Y{e;CsSYEORumEt_uvKe&oW=oZeM-nJ?J=(?OmPW2Kl
zx^Y!mFmPkEkC*|#_$3)xVmJPjLz%OCT6Nb1=>$Rjj-Olu5C`Y~K)+v491RUGUt+E$
zpOmiB*Me;Ka$Pw9#euLdqMq+`c&4k^04Fln6aAZMs;*y5S-12+l#mP8P)M31!KN7&
zwvlLWBxZhl%Lc6yD`!)i80TTtI$_8-qEWW^vFR(xU|&NK8DBt5G#VJZ{{NnlY>?mj
z(%_NVYM#$lhe^$0fHBv;e&^tLSmSM0Vodm($<X)s#?qI{4^c%5el?unvdZUelk3{h
z@n)@?z!`^nX;HV)O^54KnSrm0YGEQ=;W%-`YWl$nfAn#`4qol6IsGR1;G-FwIu){z
z&!7)d2sqBe8}=*2LJ#I_whOAhePAmMi@sjaf2TRgq7&<k{@^|JW1sDjaSiNxH1i2&
zVp68tcq@VLSyqzID_k*SIfQm9pj!M23vD=_%1g)+c9IoHAE5X66-xV1Zl70E$JW82
zh-?$PbB0JaRK9W&>GH2lL`A6R&avPt)h5C_?MZVNe{}eEtD-9zXQ}v?EJLNs2F#Y#
zhs8<Ytuk{j2k!lq;7>HMiELeGiN?^vj59pvNp`o|^p1NBT(k^z>*Z!OcU<PsD^Qfq
z^jk}=xx*38wS(#$BTkHWl-@Lax9j{=`Jt#hCCqvNJq;?})U(d5<=yOK&(__&;h5W3
zGhQ)8h{QAj`P$^c)rO46jo|ZQoamV^zbH5ogny1JK=TuqoqFTsX-K@X6x>K*EJODS
z9H1Xrm)~fFA(fIxMmwvnI?#H`G13$Cg!On9<&rsLdK2Q?G=7eO<C21FzjOrOKI;3{
zs@Gv3-@@U@P*Yr>UhG>UJu0Caj=J1d`A`J<m6j{b-Q97PH;vk|4mfZ!_?MF>m6qnI
zICSTGQ<y0q#BDQ1j)n3c`!KJ1_78Ec#K<K^hPy*u^%TaShu=TvZ3{4e23Ff(;W{-W
z848+R5r4xIzL)*n)BkrF&~xCWh*W`(U7llRSRD8n)Fv42@_SxL5QU=WsG%j~Q3_M<
zwjIFgTe|QCeVd@0sPh2g?2;`Uk3>n=JObh`1z3?jgS+ACB3ZKEo>(sysKHdCy*R%~
z*1uYCpdL!`4Rp<u`y`=cA;&JZN0XMK0QtbeR$VEN3}#a2BN3Vu@?lGm_K<m6Kl_=w
z{~1EQ2s1v}u*KK|QHlCH3C0sxiz4UlM<kd3PvVyO6!;eQl{~gDkLse{)o9$=fC0DC
za(GeoTU&-D4p`mQ@v>19YCs806fpKET5wFQp79*F0s7V#@O#87x9ixhwbJ;pQHYrh
zjpHtWuL*_fY~Y{qJ8+-~E$4PHv<k>O2UvY5ggbV3&PB`-Fa=zo0cjj(&yI2p{!bAr
zCq`+2%6d1$D@xkH1Fh>Rb#xZ1HSf<PlK57mE}sX{dfh&ki!opXfV0W$6`flbUGx;u
zPJ{A-<ELPIkSNVLx~3F%tfQKB>8py?!Aw<KLsfE}^;#7=eE;r&$0xBXw48o1m}1}T
zRyru~K7#R4?|m3itM7iVj90oM7qWFH`h-N422a)Uo0VKp!JM%Arh2p063<uoKa**-
z_dlBMs=yD|fFBtu6eRoy(VzBl6A$67{PGSH7SFtQ(FoS^gs%!!7n?Le_TzJ{W%n-m
zwB0g8r0ubc-)MFS-?>WcB--o$6_vh^!r*q6(39~;wXq#4KO{YON<joz(Pc4w1B-Gk
z`>e@K)=dmAQvy3QTE)5$22cO}7Q|6DeaGRu%VQZF!@bR@>@)5dEr)z-7}J2~^hAln
zzx&ZRjuGo(viMGfoD$B^1UY@HVoN=ccWK${$qZg|k>>XHq3RyDo_u~Qc!Xz<MKqgC
zf=cT`0wFJsiEkk49DQ~5>y{53A5DeTwdqp!>N*u?h4yX@u-NkGCW$=fHy@}xB`C_Y
zFGfWP8&-fNarUju;Qugld+f3~oqS`GVh(tHX0rUR5DLN7f+S1~{4`6>do#MC(QC>D
zn}w!t%CliDYy|wSot|4ZCdcu4bTg%4Vc?3atcYQiv~nR}1vt00ZKc+s5_ixN1`$n{
z4lU<>D7=425<AX{o?nB#Tv6PV8C3rsqWB00Ggwm5lEODXKUS~W5>i-xfvdCsj-_!L
z+wxBwdK_05q5I(($v4jrmG7+~X2FhB$F3|oU&N&k+8RVv*IrDR!3jZ=Y2jC<1$490
zqhEza4P6%$Er_J+S|ibO%UO2F*H(UOUi(>cENahywiSd1oXd#k+<=5fXlp5EP?pba
z(9OD!|0<j5=48kcGlNaH2+e_QuO~=Sma<NAQQ3`I!B<P@IXl0(YV4{AJ@8|#cqLuu
z;lpda^FkcP%(Bnr3>}ziY^ZV2J4GT{5@(YhbJTgSzsKc#$IgsioRVd=`MCO}kkmf9
z^Ala*bl%>p30=UvD?ONs4;wN-9x3Z8^hPpdlq%QNQLfa%UN$(<#&;=BX9Sr<web|(
zG8I`}R9<rdk_HbC<ypa<=B*zC3~pTZS(lc|ltjrR^4ukTNiU?V401~c-pGBy?=m;7
ziL+)X8)8gN9E_`gN?31pRubQnXP@)4bIA^2{wCbar&Q~l;Gz1)A<!#P;fsFAQdv^O
z)Qqn0h=Oq74y5%bW5O+v-)!h}=R(d8&{f2iom2%HCgPCHsnE6+ZE_R<-WkQa`JBiZ
z4;&|OgiLH;LpMm&*|EB%{c|$ngCjXb>*vN+nlw4$Ff1_d{`Lh5+UjV7|3Fo5Zt%jM
zy@+fcMJHX4@Yg+9G>!#owwW<n33_HCg=rm7e?Q^1YI7QM<Bmp^s(ZT0J`j{$jnFtb
z_?fPJ)<u>WJ7n;)UslQS9j0ilT0v6p*W`3OvY#0nB)77tlIUdpCJwiB&uxp)WbotI
zX*S4T`iyP8Jo`6<CuU;3k)LOI{c8fplfAm?C;PrB${bu>tv@SB$cb1@sE$KE%mKL$
z)om&nitp>znQ>glC9+0!>v>Fn8Mb6OVCna>&zgS~<=;PkS5;3{Q8UE>Q3-Vn@TsVH
z6z->vD+etvH1!bp!hgW|Ntx|)#fl2Q*omMf+-1Kf_XQtJ!rKo;gGhe?(bA5$R+isj
z1pk`)$qMczb-{8jgw6xuIHE4XmnZz%^dVg&LwLd68<|q_z_#U;CX=yQ3vkP|J6CfF
zxo6;-Vh9&1>DAhe4FMQIDxDtACDP(~cyJfTOFB6V@e_G*A9{aM=pbcQ`-^5GVAAE3
z?st^iFrM9aEV#`7$I)_*18HhPYG8f~!J=&-qQm>0BZBBa&G%!;1syA+4wY4o@8xg_
z6)l?c2xR>~M+uT0;fgIe?e2WI8=&fY{ZLl%EVKtYw3@nh_=}F`DB!sGQOCmK(%GCd
z{%MxOgs=kLY7<Hq<~&;)&IDd@)H4mx8{LKe@#q8GfAR8rFfj3(Jb$aR1h-7PYN4|C
zRZ1O_gCu#$k(2ed8owD)Ls=l$`g5-|Q7b@|$8K<c6AVr5pYT!mr?N1116+4lvJ(7+
z{({Ya%S5>0Em-6>cC_OI>Zx_|DJ%3%PGDB%t?hyC!`ANkOW^e!B4NmCXP_b7Dhj=h
zzYzz#pJ&JKr7|D>xdE0jK{U%d+rHnL=rG>bXU?2Zr{aMsduo$;e;2CiOmL8G4&zy`
zbqe)OIk=lL4?eJTd8!7bsMFtBZ~rt|V_@U7UXtSM@T?JC|DAfu%0$ujcOYTRn0!sG
z^Ia?Aw<EKm3!7)0UmkwQnj4MX(UB~YB3m?8Xm7bBCH>UM)>J?$+=pt+W#-F^;?Rrd
zcAqnIcES=HKRa&?88dnuzCM57QbjqiACvp%Y}w+3f47QbW3y)htI=*k9-D(VrpL}D
zY_q{3*}qC=o-&62^j*UD^_8Wz_`iWiK(8LR8hRT7U(VywGN)LkfbDgXI6C>~-z89v
z2dm4Qxdf_Gzp~Z12h^#IHKTxdq-0ozdbhXnD8zs?*TS9#Q+LlQ6U=gG^tj3>C2cAf
zry~Q{ClcV0syO`mpS{Ac#Aw@L=OTQ$7(k()wu^UOFBq*Y&DjKH8Ru5AAx{dIt1{mu
zToLZ*C~sIJvZ4R9xy)XsR*xzKqV$_)>Z8yt0T?1x%;X%g??OKMnJSN_G4E48@l*_n
zs)R@f)1%>B6R3El;D>6+onKst&}Wb8T2FG`aUJZBw_XN*!>SAWH??YRPaJc?-Is58
z;Qe)REpy_jBo=jFW)LrZA!jr)wg^JA#<gbHXF#yY8@@9dGTj+?Kl6dR{<DVYEih_K
zEh$eAfzk30cX_sf{;a<cSIN?yMH;wAU802#<b)G6(rCK&;ycu|olFz!$#f3K;mC8W
zpSQ9U=2^SaU1BA<gvL)Gb<Yx305Z_LqsDy%RgN{lKTdn%lv@vWyE%UV<n^oc4RP>F
zRpOlKpZ2rVe-m;7gkRHt{pq$kLc>-T(1;`=c(<Ely-+4X$x5T2P=TY46X06j;2WTq
zF-9PX@bt<ZE$gC;dKMX<*6^Ta`rP*s=*xgJHzN<Vi^>glnaSF|eY;kYUhn~dFugEU
zR1TuMd?+{%`j)f#nmKdO%#^*^O$c(M;E=!jb`*z_1<|TbQ~Z$@n|@%yVbgHp9n`d%
zt$IjRUfI<-+{P7Ru%C~biNYOoySA;O_j}uAQx_t6yz##!9({81)2`1bO=dA4NrTI5
zLvy;|KXolz?8GZjRTBA9`1*?ops44ON;{PFZf8F(&Q-T>8cJy1*?y-6fMW`k%x76%
zTUSH>dqiI}>4OZ&ZZ(7C{C8j3Hr<SXR9ouT(JhXM%2$p7>98%j0*2!9s^6v0E|wUJ
z+pB*_9P^h*YZPH~(JN{u0a?4B2ZUxMTJO6@g-7&gB1<bT@MnUR$|5jzJvZ+|vh8aq
z!N_Tg9rkJKnnS(!+1j=*wgB@!0gh^~s$Yp0#etx@>Bd<b?#N}ZSIi^P;7c;}HF#0t
zo6rn(h%zSAL>F#3>-VH-?7J|tL%@{Rjs@U#LME_}s`v`fNVI`%E#t&B-A5m``-9R+
zVJkd4PYs=R#1Xevzu7hdwtB4ezIftPB<?`lZq7$xQMK1AK;}da2r{E-WzEPH+Pjx#
zr+pKS)3g!FBmvLp%*pk<W}kG)2|;VWX9z3X>^{!<G6*x{Fz+D@7|XTn!(mF1p9~#d
z{mD?QB0p7U0d>j)YjkK=M_Lo*)>&jF`a6;?#jn947+(cv$Ri;8+$qZpbrUY%KYY0?
z^hISgpeTNUq_$ZDCKvXNf}Rl+ClTBTnGk%Ru0zX%o`M~{+Zk&&X@4Fz6lKvfYc+op
zJk~90oRqaR1-m;ui99r@Z81%jijZ6viK%d_ONAU5B7UnrQ=%pkvO6z(Y){5^DpjjW
zsHiy=y|Gezs#X7x*S}=DyIMzi*i#4}<_fU-itHdR2A_mo^*txc6n^Xqn@|s_+n%;q
z$^8|m*DS0?W(+DFC=u$Lt+TwBZ2zo^577^e3r-E+1Hu7iLbgk8X9_mx8AS-KAxBfj
z=994=v|f9uSQ^KXn(*;~4G*m^bPU{~49(@9hrZ4s#veS6(x~QKCYox$bOL1OP)0*m
zw^nD3vYkTnx_>EdjToGFK%gA0NO3OPI5)w@7ZmWr_FGMky9|#evc>0vo7-iR!J2)!
ztO%s9?m(aDr#OcrlHadxQ?$72odr1JKEvy`ARb+?qjMGR>l9#-J)f(i4ex$kzR6(`
zl3BWBGPlk4J|9uq$D2qb5-^O&-aekzfz{T#46woCmE7)SZ(lC*0XA2-yU~w>YO4RS
zlTLg;aBgb`Pfr5VyyJ)MX+)*c90L=+XoPv`h}^DIg#fYA6`c+iV5Wmu;{ygQFi^*$
zTtDwPPt#tfvvU14o}wcEKy%)yYyjs3)k%rEF91PPdPQ!JRROgomacqc%i6`t!?}jU
z%Vs93RtxEoS79Dfya{IK>XI9&x1LXMkeOqy`eg`!J_RfbyQO=86J@8v^70nvL{RCm
zmOcNQwbs_9BV4n{QGD><Kf5z6v)cZ)08h^BK55@*c2Q3L`IrbY&t|@6an&OB+fMC^
zsjFE#{}n7Z<c|;DfqvHLzbVtZta{=>f>>5+>(od6Y2$<KUCzdM>x!G&m62J^5PN-;
zZ*fV~ap*kHg@!f}fK}sfXW~4(+Cfe2$TB$v(^V1uNjaIGX_!dd9o6WZDLQM<?UCxt
z(ps-%x1fG^-bdH{)6`}><y3_P;OqnHO2Kf*#zHw*W?~N3Ms-CVt~fCc$#J<Fd5&Gv
zGX8p{0agjto*-+A<qG~WhO~{&Nh~=pq6~OS)=VDYCEwj=J0s*S9t8<27AY@CgSB>E
z_j8WN%B_5j3AC9^n-ICL=~p!QnZGFr(V6JvB5Q9doim#HV3ACQIW?NLE@*)HP(x0&
z39d>9Nc-U|>g(3hJ|mKT_W|Pf9J{^xAMTtHSLHogQ_nF51GgK9V>Jrnn^>v=%Mm8(
zl3w5APmzOY4-GZ9KeX-rgRgYZPV(}1PX%BrrL-oK;dT~M|A9O+$^R$z$i(?IZ4pSO
zA|>Zp5(}HGriZI9h0!2NOEY@YabtdYA4ZIT0Njs&IL|m+7-yMAaqe2!?G~vqchBh{
zrD0LP{t2K$0JV(vws@Yw!ty^5C=Y)iTG$rs(#SHQoOgga?;q6Noz~4gOML@caAN|R
zr8a{6AIX)n7iQPUoGDSHWJ9{-e|6R2Ip87tER)=>gu)5)R5U2biB}p+#qFL|v^OaI
zX|6@;@z!$|^t;al8^VwX-h16D30~+m`)vJl$oV=?F!sd5&(eP+wPKjm$}MIlw+%d&
zn@r@2IvTI7(^mcdz8i5&uZK7}X1%#C>GLRm%UPHN7#<Jcr5ErTIb;~a{Y}v6J0-!8
zzuJ$X8bMoA8y~kfA%ZrDjiQT}aSb<~4kr2WqY3A-A){kW=NXR0LZ-4>DKOXykv>m~
z?j^q)!!>MGniKf<2=K*p<4CMW_yu6Mimpq5t*%?<)Li$?n@jHx*VY)JP0BWS3+$in
z$2Bu6_w(v|!uU7xyb(N)PtYH<_GdFNWFzHazJAtaCDM_#acvX1Wu>EEe_Up0?T0Jm
zDU(F5WDxo9u2GfIcE|O+ynKA}rIa|koD?=Wqb6m)Smx?>(V+qY-eiyY?oDSSJUyqK
zu6|RHEMcRZgk%-*<(dseXg|Tzy4DQQCgS5E!drrzUjPa^8t&rzyW1N)VEnLH{sya~
zA^~EtS*W+K2?UQEqQ@oVGyknTyN%JCsO!3^5`eE({9G?p?wWo9(=XGAJSO+@{|_Y7
zpZGjiWs-TH2mViY?C6;Fe)PcOAVBYRo}o3w0rt7HWV}Ma_b>j{2*~~+Ls1jv&nJmj
z^eUfyASX9gUt$mG5Y`;h`om^YX#G-Y&+EV*8*|L0_$M}OP3Unvg}?|6&VeJvRGprg
zsn|`Shy?Tf($r<4K##eD3Jxn_@EM0fQ6Y2kL>~Pug;w4K9?ZYwP%~np$K{e`KaS8B
z=k>KIo2%?gX-C*`JUb+n1KIbEH=lPcng3dv9jy@477kI*&y2+}oC?4<c%aNcJ9c8f
z;oZM^#p9Iyw70U?zV5SMF`~nhc8R=m%EfiOAY}VvLS7s|zo6{2FmBSCJ}%vy74nHg
za6wmZOX%(1dPT%SUMmrNKPRev8=omYz>+l=xn0GyM)S{W#tF+OUR>#Ym@>FZLbu~A
zN$zWO=9ptrb}Q?_pAMsPpVInYl=!sv`?^3-1`n(1W2@IEM3PShPWV59g`WIaWy^I9
z8TH>xQiF1|B{lRplc0O3f7}>NQ=UxJ*H}qn0UEBx;{k|G5c*ub`~ARNJ(O^%zeC-T
zrShPtV<zvW-?0&SZ!PIOgwlzM29h<XsgD4Dcv87z#Y!kjhjpgj!t*-;y(eemJ*(@$
zb`4-W8SH7dZ-vPrwDcSUv_NZp`1k*T`qO;q)jGCY9-hNCb!oMlEqv!i0FJzF+jP^#
z6-M%eDu3{C|EV@hY)-H|Q?4cp21;=AW5nY}_{9Q?hsw)Yc;qxm{v_FZ`Ta+ClXNKG
zg28EZeh(&?O8DQoM#%ENVBD9dq-2;9hzj<0SJ446o+~SO&b|2S%Ue-V0gp9dkj7Ji
zZEHsKxWzdewRta%i~)_>D%9x<J}OIZ@;%$>ApD=gcVk{MvPkQzvUh58(~+whKOL>P
zs-lFVcALD-ku+b}qDU<W=7A4cL-^T#z~-4r_*}Re4Q1VNMsrB!=m8H?PfvmCTAhfr
zqu$vxYtRko$u8H29|Ju`Jt85~YhQs)Sxa-5sGVOBf8OKG9wT4Shtw=^)K%WHN=f6(
z(#8lM?2y2He#|w&I&HJWO0C~rR^kZG_kF_eesQRs9Pi&8O1*gxW@RLJ8aefw;g|<0
zfAL{2ZyBVu%0FWovy?cYnBYe3s_cCBuJ;4zg&*NvT6klN+2TMD{F%2@F049$r!~xC
z(VpO@t)o8+UV~$E_a*>YI@fh}-`wJsQN(c;oF~~n?dR9`+_Ycv@3_Qw#F<cue$A)S
z`0Q_))TLveDga`S37pWIfuXh*o~-cb+R7nJ($OYwzDf~YukT{?^3F!vNl&VDj&>7z
zO`bGAxZq#~{{2#r7FZtR?8uu}ia7;nGbnZ5lq~O|-b}hV)b3$*md?pfzP>&lCbX9u
zi@r+sj}K{ec;1_3)%XVlJDDCXv_Ife3ER*5>b-(v!DSufE=p=oX5e40iu0fz+&w88
zTel5xmra5>|J9sb<TewabVfR&3h204<~3PfwCR+Hjv#%ZO99i`{v{fnz#$iP)^EI5
zdX^(g#5tCaw+V!&g~bC!m^)9(U<jdIH??7a4+vCA#`O<13UF8Tx!X%9NN0rf_E{ev
zhsj*?)As&k-{~6oNgm!u8*=jPwlbw+uNfj_p1{%5OT%g%PKvThG#F;!Xc8x|SSW<D
z|6bK|7RUG$V%R4-A~Fz2N0D=dR0(KEtPHv0XJG+#E~+?h=1eKM@@HYin6&(MuE~KL
zMEjq_+YWUcY*Cgu7k=v8#g<-Rx_XVnP=K0(PL%&-HBiu~x6h?Ecm*%_x;E0;d@JDo
z6Y?iiF!|6#AGViy1=1b%*$`0Ro(M+HOl|Ce2E&#ZVznCM$qZZ?QgVTopZMV$o9lPo
zU?M^(^$!peWEp&2!n4g#3Ha-#fdh^Zq4ORH0NKsoYcR2l_N&839ZJ;BCG8$q7#2zp
zw5F0l>2G|ufg9DQ?uV%R4@s@FfT6*==rQBsmFtbK53$u0J7*sQP&%}IEy=r-#=kkj
zdr@sMA`6_m%|xmMc;S_`J8$b>T^|A?tZ=2+U9~^5l=yc=Eq!`8%Q)n$_^Vs5fatI@
zIZ$NQT{Ig-Pv?r^sB7lix0>9SW{uJZ8OZ8rLyeP2fQTgK2xW2o+1Nmtf@3Jf!O70;
zX*fXp8IxMQo>Yh9t_&%%D?}agqME609$Dp56gP^l;qf2zrf6%~_}i{Z<w~VXZ8w#g
z_wfI{b4mo)n<C^|;ol6SZ$_YM)CF<5b+r&j5FpjSkFTM2=$Ce&?M6DnHvc7E{Ser1
z`JQs~OgVfmuNZFQ<lK4pw*)AGNiXyL%{rfa5xW7nbmAq9R4HP+)FXBP$tMFiq(=kO
z4IIYZi)D{~FFoLpa#pdZ37JaqjtEqbhp8+oBohbqLhmSm(}-VO{FmR~>)R2$zt|kS
z`tnIej$NYUgu9S>ZV~VO<v?>8ZbEd(Z7j6ER^!vIbBfQH^JNSILncdp`qcmxkw>H$
z)l({dk(tm}mR<LPo*8E)!j3nhhmPPZFuv~m-~8a;3{LnzA^i4~J$gU6TN?L{v)et(
z&DGkuZp{SfxW>8;3Bi2L-HF$s9QFTEbk=cAy=@pD9TI|o^bioFMY=XZO6ism1nExc
zfglY7k#MAR2+|=bjY^MhhIBWK?S0ShKmOSEIh;Lv&U4@Qb$u^~y@iKz*7)#^GA83m
z3F`NeK)l3B{BHc%g4C5Lm}0l>#6tZ@eJiY1=xXJ2{O93_Dc}-0O<&sIs9yuD--rSs
zW8F(9FNXy(dryb4P!nB`n$Lg?i|1X`1?kr^?O1`9KEWWv6q|guZXY7dkt5@*qFf<r
zC6gAm&e!yopcQ;Vn%Mr1c)5uXHSILdNa~$=cU8g!r+k7wWu4Er_1w7hBJ-<Wx!Fj?
zKH^cobvYw44>YVTbKprVc`g&EZ)QB6?3;k$i78kSXr)Z686HGwxzk!ggn=zmv6}MX
zPDC29Ho772B*pRNX++Xo5g`n?`V^ebKdhlq$^P+1c=2|CXEkmDSnNMEbQB9&p{=@I
zaR)KC?|?~iTO4jb<zbbRqNiJa;H^D$GzU{$t$uBdA1LY%9W8aIHDmkTH<IUMf6qk)
z8*9UU!J*GH^|_6V%{wA9NM3Y0dr!RSc562P2t@ewRt0Kpb`&ZfY*dcon&sc`nJ}h5
zG<U@uD0?CiQ*`2IW#<$kzp7pQ5twN4d$8_gwdvjmV|yYe%;QG(c!>quit;nNubUS{
zaRbttQ{c4scj;Bb9}dxdjYfRliHj$c9UxnBird=rbbaJw4x07##dHp#=F@VwAIJIK
zpB`jiSCm}8Nls}HTGx2Mw;nb6)&dY#X+Y?VN9l#e4cMGN5pueh@E8fa>&73>-Mp^g
z%)(MRq<LO_46Wc9UUzowlHIg#R9pzH2oQM@6c>*c(zQ}(bFaSFc?_7(dxUNCZf;#d
zoD|j*MTJIufGWA2Pt51_4EkCduKT3ixVQOfhJ@=)DquzgH1oXY;=rM>^!0>s1bbfP
zxxr#@buXpI+y$9q<+>=Zl6iPu+aP=LV<znhs;IMUpWEHwDtw&t{tNQq3htit3KGXU
zxlgkGrhQzd8aTI8xDz1+M3ipAiyrxJcZ9k822{~v7P1mn`EZ#BK=lcz)?lxG**q6G
z07jaS$^y3EJ&!y6fQYxEghP2?ZHyfx@=M?lUkV`t=XTW~2XfGuaXjr<(bGwORI9!g
z>$7@hdM5DEMd9!ypy&GY2qAx`VRNkF4Is54Jdx$X3o<y!H3RTT`jO2)Q|7yDgMw={
zjrBtIi0`|^-waV~6k&Qb51ZqK)VbuK9II7Q?doOC?0-WjO)U?rWR7tu<jMijZm^RF
zQ=Wk+4$;+B&A}_v{#oV-fN$8;4*Qn?Q;Y({UXi(DpG-!NEgC3kUxpqwlurH2Cmkuf
ziG*KT;bDJmB&%;ofiP=$^PWa#{S;kZBj?AuuQ%e8i!dp}hs`N!?-hj})*p&!s9y{a
z$j<He*&I^i9mmB3Ikjg@u7yIkcY5S7gV6MxAiy;ENkBdo&GD8qz1@nk)6q;7d5-=w
zFgBCv>-ugs-upI1{c71FgFhT*Du%OPXnBfF?ho2ro5ALgrPo%pWw7~ji;V@`waWV3
z>CsG^WsHWDG0cmWt%f{;2S)j+XIS&vBaNlVjDM-@<P0C1Njo@vVbIOsF5w~j291ua
zyM>F72U&k(6h|aRwc-N}fuC>Qt3wnXB}+HjzIB8@UvzbE#uUoaP^1=fFMDav(nM%X
zJz)7=)Lc$Wbuw}e`y($GuRj*KB|H2~>Ns0p<FjGYWX8=S4tPg`UPOTx%M<SLY#{W6
zN}PkxA{XOiaFSDZa!z+SH1eGDyrBqP@YK>t8F`WBW<h_4rv+iC!>1q~3k(={NtM!t
zYxv~jVX0YIB#BE|V>Mt@yZxSwAerDaTTwFtrmu!7QvFg5RdU3-_2<m`cs%W|-H7L@
z<hmE*oc+_~{zCo^GFvwhBq1tZa7gZ`(;V|@g6?aBf|qnXgyFH-6)}gW2Ry(&HChze
zXy<}rSTowf@DQ=HIYL$eAoWp=boMC%)Q?^53YM4~oK4YXvDXjYm{z+UaTBlo#-5-~
zsCFegtuBTUHiJ4QU<e)X1bi**wCJAdNV1WBShyTKD$F~&sKVPwl=QXs+-Vp%RnFYz
zS2d5!H{#{KItaVpB(n*BCD1rPbp2NWATMWOsk1!OP2LCl6}i*)0SPVpPlb~cB}}~}
z%#)X!5S9llZ!NogpZwZS(E=9d*C<lcCK)T(<qm|a!v<Zc%DoaF7Tue1+uiyl<SkHt
znq^pzd2^u_eTCbV%O!9Z$@d(jXKLAQT~UMk@{cHqYxRF_CS0;-=RRx(xur^CIc6%D
z4&7XmLB9q-Bcykz=fm{Jarkd7ADHnyoV>i)DA9f}AGKkA7cpW_f0=LgXEboVwIp87
zGc&IdkaU6iK~Bxl4L4&JBfGgg6p7YdJs~I4nWBkrIxprS4VCNr>wlJ-WX|FH8srKk
zjuqWu5v!sFf7J2+=`R^M?K~!v${><^t*5^3q4oZ2tgP?1e6fh#=i!ahes^Lf7S?~C
z8MNvUf$&UTuS*7C&f)pxk9)=|5<gQNY4OreOevHpLlngi+c#52czmn|hgHAR`>fW~
z^tE1(@~QCU#HPMDb7Fj!YnCVQ=2JeT+fdzCH1WkLuYD`6)K9XkmlcBx^~WyhC$!c}
zcl!U7o@Dfi*L2+>$EM;U{So2}CfAhfVw6{63GeH9#)^3roWX{q1(gc;xqMbPW`2uf
zlE<3vv`Z;xrk_P7zZcJBuo8|_b_E8m?)FhN*i<{*5|;(P4mD=~8-6^A=;WAY`qGqu
zcjUB=yy)Y@es5OBO=-+x^(YJdV&R8dzc2kKua%y)0p{o&NxA$C<U68`X|rQur&j&p
zq&j=J95vT=kxxE|ywu#rKF$9y3RKeq@3f`;r49`_XT=Irt|-$ReD;?W|Cx+D)GP&2
z#UVdZ9=f`7U~ody_>J%WCW+YAgajI%Opy_;p$%UTUrH8%?GxW809yYL&0ULaX85b5
z4NZCOBgNX|pLM3&eH2>#i3S%$Rmxlb8M*BD4!Fo>({l(uRkgG@mbXoPgA6n0_)S*r
z@VaoYhCW|mLq*F}=oJXq94SpckpN`?UaoCS2wlFj<-@#Ne}x;p2SN|mU`6FpyYi1{
zXT!G~&O*wAs~q5n%~1NXq_iJWTWI$hn!?vJAf_K#tGLO-?TJ<>3HD4^v8c6Gf;-a3
zD$^DLU7>Q0y^7OB+`1gI+2bHlj0x=TON{3$pF_1vq^CM290t$Qfdw-<`v<OpZ?IoZ
zksY|4(uTLpd*;CT<y9N>oC?rXRS2)&PT`?dG=Pxu4yj<#f1x2N_K=Y{kmtm<03fGR
zhh&wxGBll+4^Nf5r7`(CvAvkB%kx_1iRi5X_Usa=L9_wrw2=GM$qTmXQ>dH}k@HIb
ze;~YKY4UQg*bvlQrxQGd+&(12-sR(C2kLZix-yddKSvbJCBvqc?mk}%T?yt&o!150
z_^S9=JQIdEk@+pF5$13J5ozt*SRzenqc4P}C_e0^nrI@k)$Ih<M=-ufX8pZP?Zn&g
z1XmGd_pax1^*_^mI%p`E#RG%qOU2>Es@HWQ1FsEI7936vt^Nn{IURMV8PZBC{6Pk6
zTv9F<4n-@>(ST{^yJkR1y^CJv+eU^gwZ%V`6c@zxnDP?&HacJ39dhGT)2Xj&0k0|k
z2YRZg75?!cMtiDQa;$*EW_TOCB#QH}eF6vC#^A0Dq`4~T_kktQCB+ib5UJ?%SN01R
zwdX}9+@-_vWZ3bE;lX+Ihgbf{i{iHe;dq!hBc#t&LP58><(1R7mip1)uTmFp8;F~H
z6U9uxwSb$*Pul(JUxdUT>+QWX3pbbED2HtH^YU5aMpDJOntPrwKt`8kerm&wIaQdk
z!Q*>Be;}Xl>^Q-{xjVF|=G%MS`HKs>ycNbQ_MNA{6#9zk%~!}_x&p&R*`is76rDhx
zr?!RZp3<kOQSB-`M&GvXP(Xv8Ef#b&x=0~+Q_Pr~?_JmD`5IGPQ5TE|71>|NBnH?#
zokzJ+M?9gc-&xaN6)x!rH73JQ{ZKqDiNH4RtM~dzk&_Rj&fmDDJ711G@UF_c^-X}a
zI|eV?cK!Qevnc95(|XGePQ-l_+PN5=#)#gIb7Z_)3I6Gw<1YJ}9%#po*X~Dpzwq2$
zNgjI7IKf<F>EQrfDEk_4(m5@ZT1k6b!V-uRm$0zs%686qD-&m>w6*uNC1<P#HyKjI
zLX!5;erv?JDt+hbg3WhCWx>4KzjYq|)&b}D(GCbK##BVK#Vv)RHQ#;o`GbWW{NMxl
z>;|<fPo6%rwPEDmP{$*+KR(IAW&H1$+3HI4v*U_sm|(m&5|J=hyS9X7DyxZw)rRAT
zd|&^0KD&^Ii6`lHZrYuVOOlh4T>datTb=>v%iP;<JG`FJlQWKZVv|*5j*1yAGXGUK
z+b3z_Y1ZgTm`9B<H{uSe-ZpC#|Fj8_0Y$u?GO+sF0<6Pi#|8PJN46mndQ2f;cM%@E
zgh$zWHZL_mI{;`5#KgjU+Rhv*y6##qKoMM{T|P)tV8JR&cRZf#NWPUoL<+?j0r5z4
zL98;bOBosfB5=A@_~7!0!qp+T;pO$ff(Nkhc9}vSXplgb3nRi=L*z|WkfJqOzz_WN
zxBXRTW>p_Ex)_Rf8@mx;s9khrV?+C<T4mWW07Iud)?$~+aF^{>SDx8#%$Vdn?F@wW
z;lIH@4xUTa$)vspMnGXt$GxkLsoJ$#!|*_xHn|@-s9!9qV`@D{;I%22G@$j$p{}#7
zRRt~V1d?*O2C8JJ^&_zAYz|1yh_gI&RfDJh9Vb|A+><+ed|vd}w2%rLlg~O|VY$Ev
z)JGYjpbOE;pzo(y3d#d!0gZqmEJ3f&SDoT5ry<7CCLL4rDxakvq7*uet}*OTePyMk
zjAEn5snv<MQ1h}=l(F*pe*4&xo7IWnK-m~E+b1a5s&G+6m}=@Is4l@4XdO|yl6r1Q
zI)EKH#j^=HwY+u&__|ETPO7I{;Y{H9W|rgH!`B$Z9OmD7C@nA~BgPh~j+INS1H|MK
zqU}yjG~f{3#VN$(F`_V{SnJdSKOm{*{6mvd-W5}Y%^_R1?+D4aO|s?lV<0auCx83!
z!R-`zb$00eYN~a<D+SKX!TTWnuG%W9ShN;p>#qDDal^Ok;$<LLp``2Tr461tHy+_v
zt}N>coEAJeEl-5g?t(S*?ONV-8O}aea)<vQL%z8q2s5cHae&ZeO6bOrODY$Xp@%$=
zHI(uUCT)0SOYoB*uihaW4j0=y6?S-tC%&9NyeAM^@Ub0w2IUpRi>kEi5FiYxML5m~
zAU)kbhJJ~M6%1(2MQIoK0_HY#!=Z?OEJH=O;$3w9jib`ccHtYE`2-PAAisPivk;eZ
zSRMO?Jn*ka(|45@B<6NujI!!7pQ-1-iUj08R{R=<fejd#2lgnFCOrL0G^YoqX7zgm
zQT2{9rXQFA5~jANqk<0doqncBQLP05t1xsuX3?&9DTxPO1=NaTg?R<z!lBFGS&cX%
zup_+7`x<Nf8aR6<9=y(Ge}*Ssb8sCk22_&GwuS1Bu<;LyqE!*4kb<v1slTI#IjMzb
z8NNGm&ffRd60RV_+h5+h;IVe_gl*T&<lI=5WB&&dot?OhLN`l-O*8(SK6nP^X0{h2
zsXgV`#ypiD)0hHT;ORp51sAbsG4`9lgGX6ggC$Nv2VGQD{o9ai(!`4#*RXRTEmhw@
z{I?c3@Rgt2odLztq|dfaa4u+bMFp%CGP-OpNdu<_qmE;TyOO=f5uhd?Cacxc>m-1K
z%x~Bk^lebGETd=C<9(Oi<pywO^{0?nZVIxA1NqlXaSTgXgzQ#PBoo~SKf6OXp8N}Q
z5nJ30n#xd^oQ3Xko?_P32xA%|vBI~=@QX;<YVGoGKFd6m{MsEtfZ+{CpoQ|PJgmzN
zm>sqbU2E|WmKK&T37o-}`(@l>%Dc_&xvRhq6E@p_^i+fGl7|KwOA=@s_QyDiWzeBR
z-dAn_$S$Ny9X~SCL!@Wi*FwMq&cO|2;98y1$kH^i&H<yl8@2ZfZLYwrnoM-p9J~8u
zIA%^7c=LGxLe1rZw$6+q4?QQM69_+4y;>;=JxpH>Hb~qsF-R~IA-iJe=Q(BLv|ePL
zE5he6oY@>*e0oo=`t&%a>F6P4iBvhbpPI7O>M$<srW2Sl0?6FlFJx}Vk6!;uqzSwz
zk!9tw2?K$T_2KbH+ROF9z$&XUX`XH5D=$=V8ma<V%E>eXUpFMy=e6%C8aNtSo0<(<
ztZng9XPWi&YD3Sg68GOUpN~$YkQFE_9TpAP{AG2-RpKL(HDKo`Jqn7Iu*u7w{-Y+|
z>gU0PoC&Rys0H1A1)Js!SWI5hU#f4Cr!t3h?4J93tSrm^ML*2`^c_R`!1>u+K!Qom
zz)urO1c^Do#4V<YRH944=L<XNyW~o{xb)>sB`AH{&tLN;G0m)YL<jy7p_I|SJMWZC
zyh2x>^5?aeR}f*pI$cDGVix`%AiWJpr?mcro;8EF6iKtxQ|4~s<VMi+@k}%n{mW6m
z6i~k+=h5bGxtj#|?Gm=t7WIoCXzCp9f|Vd2-p=PMg^m<P<Sl3G_v}*D+yWA0>OnP5
zTV&pceWOoJG4UBzp(SDLW*uxS6>+Pt2uq6!t;`ZvkK!2GB}imd+x8Izqfrrj^jF>G
z4<2BeOA^9~Q5b}c^PMwuNKPGeuAH#2kdO9EMb)|yd^M2Pyx9z0UUv**2_3_8E!@WZ
zR;p6C7k5zycF)H5?Zx%ro@~T{@|UWwQpf!uG2iAP+o`cuj$$?6tn{a$Jy27nAGMNb
z`hKx?C1EyI=REV%I4j;&Ckn47ygg}ykH@BqXA5PLWyXDv?PUa1<XZFhe`eJhHZ90`
zXoA#)WaWXDh2ty1cKOZVT6j-^bX2t&M*ixz9>e7Th*SO%b_ApeaF?$wI}3N?KFr_C
z1Fdg0^T10n!eDvNFrsy>Gg<lG*vF-l;lwk6!`u=@-c!Y*CVPc!s}hhefDRB%);Kga
z8|UnRSc=Z-6xo-L)mQII^SFzE4@8aI0pX0P=VfNS3-uxU-zn{+%8E|5ikmk(g74}X
zN%_^+&wv?P-+;m~qTaDo*%h3A{`E!ZX;}k?!o;tmZ{Us0XJ?y(E+Ho4W>aI_dS$0r
zxE$}ppZ<zf9;I@sPIY(YUV@DBBu9Kw?E;RUP0!0W?c;EJm{_RP1^<kp4Ie45U$}R+
z0%5Jl%Jm!}sO%ar3g1&$KV-one*rK?O-cw1U=&;u{H}M%JlB&m*q^5W!VHKuvY^sl
zg=6o&eHSH=dnbA6q~OkuSH7d>@dPa2$mD#d5%9px13F(xAS=U)H%v8XGnw7Y%9OzR
zjv=4)zs6?QFZ(uRm?Y37>QQx0X&OG=1NECrtgyh-sNkM)HcofKQ0|ODG<z5yC5@m*
zI`?`0O}b(sokd7%C3q2`cws1cK#d62Ea4J<yp{Pa{NX9hNVcgx>&HUr%l-RdJI|w%
z?_k>bYEME>wO}(h%0G6VxkWnct<#q(pr>EQ&?N{V-vZ$)E2dK*47V95vcB+^V!-?|
zq%k+0DnoQY^xW@Nr`b$TH+8vb|8mbC57p@Jc>$7xpqKc(_pUnd2D*an&H6!fcbt{T
z@NCh$^W+dDkW#zs1HUZA-j%>y_VGX05M2D;)NA@t&00%!L>)#jA=XMF#KR#Qd;|0r
zf7YVUPj_2@Ff64$7p*=?W?cQMXBmBC_a>6Z{cPMoe<BdjH>7$!o>wm$`*h5Lb)F<D
z6~lu+dcGb5$)B2>>T^$=dMI}{RTI0~<1P9QGABP8s9$gr^Y(o^CzjUYV%a}0-BC)4
zEf3rHWWqNCdU^s#AOe#g1A+;<W`<>-c~Rx{O36GS@2>fn@2Be{?>{r5NkcSE;(H(A
zWORD1Ec4K~6er~|J2$C?v4n4wsvUg!IHd|#bQWJ#c!>A)`q7?K+Hus|GeaSN+#j}Y
zVbX#Gi#al?EjhVwIQRn-r%9$ROghh1DvzcuWLcP=SvEb|Q`<^we++WzI4Iq5ihN@t
zD_**l4o2_Optz%wZGyo$%HU7@Q$&9`(Nn-hGS=vSUJKC#;qLdw-|JuvX%?aqb87#D
zuRZ`u#2#pI#OGfz{{sQp%N(kMBQ?OPEhmVpvE13|t`)k}0ysx%4ez0QYCvsZP+7dg
zH_ZXn*A_?M+sIho@8H(oq`u~eH-?^28IHv?Y^cBHUS9Gbcfdb6arxOpS<ap%FdCN4
z7MU`qLnmU{XY^*HM=zwJZC@A4S30Dy8)0g>5Xg26-r(7<1VEZ+IM_pB`u&Qse?Ehp
zes-03eUCU{f;r9H%-i>TO6VX}%byQ|Vs^Lt5a!O;%puhA;px8UE9ldY+fCkD(pU8f
zPvg!HoNiB5G9i0X!1d~z^{3+<Eert-ta|0{VoX)lXV?TyDDxDoF<2={;Dubp@%__e
zfb;<8350oN1{?Bcm*hOjC#F8`(-YKi2CpOZxntgs&eKq2hiki2zkRXhSgqY5=DVz%
z^>2!D!&A+MPKX);4S`qjr$gBJ`bT8<P5&lF)@)>;&E9g5SP4%dAPQbIlfFILU;XFy
zdx6_s+sGc!9vb*@z8I|?^Il5a%4P-8+ee<atkQMD3wn2gK~poHj@^?2bho#X*4Ihe
zE)q1wvM;3!;CZHotWQb3hVvBS1iL>&Nz9LKkA~l(#PVh3@Es(E6j%cG^-O!cIbUz5
zQ&WwJ@$FJ_k8D$i5Q#Q2yhh{x&D-E!(c)zY7Ix;$ij0dGC$(KkEC=6QxB3iPJC$D1
zRSaGuBFOGY#i)FPg{)i2)}uQ(cAD_Q_Gp5p_1FK5e%R9wC3EaLiC0rwh4I`wMM}Fq
z(6l28ejoTq7iK$OI+UxfZKKUfn@A+_LKuMl@HzPh41-OrOh5K2#fHK-n>QW*`3NHi
z9`76K_x!ZZz6EyvaDd<=t>g0b=GsY#)%N7Bc{MD=NxALhE~FQj^g`EJC)Cipz{6J;
z6I;ON1@s&~_H`{R5U=qEb%;-jH-GDaPM2Mg=yZPlR?c7oAlgf2dv`ozZu5yKsU4Og
zwL)+W?E6fuYZpnNC#0cc6#2ssu{7cBvWcIl@KnOUC#kz=k0;Q$Db+X^WMVqH4*Dse
z@Nj|5Hu~shkAVBC^CQKp!OKN$h3NaI<0z<I@SQax*o1lAwFodiWd|$d=K~aKFjC;j
zDI}={Gb*x|CJpM{C<pcixXJ}!lvw9!V~!`n!z^U_XK21V%LiRAs@^~KBT1>TpZ725
zRsyy@78FP`A@YBqR<#9eQ8!g-8h34ZUjIxby*p=epp|bKJRY@}*5nd6h5Mv(pDffu
z_S2>4X_<3Emq0-!)qtaRLWlq}hVCoyN!ejxu5UtH3OApuI-CNg`9F0@&sH}S1LWn(
zKl}IWP`Ku?1kjS4hODF0^8sAoA5Q<2C_i@8su)xM#`Af8(mPTh0HjJ$V`DK+e}nJj
z#gpJ5JS@!tVPc#!KCGyaDi`835%dDs<Ew4GXI*V~?-Ku=<DRO;-|xFg-Y{h$(g$=I
z`HQuWvnh3F>g~sWEH`~exm!(lu)EnrNwGY4&S}rmSO2|Gn0AbCAgYcCjpn)%1CEON
zNzow<M@UV(PqRsH(y|~0IaeVeXvw>91NB01^wHP~a`gllwn{v)yd}}htFp_1_Hl#M
z)<O*?N}T%=r_^sr<sE@BbIbi*LiCQOCWJmr9J0y>^waVu8a?Jk#I;?KsBca`#<F|C
zhf@z8L)V!a1V&IlP)6S-8Ww#XT%~4vsc+7xpIj9UVj;|V*X4iK6JM5(^u7l&Xki1%
zBabI8>H%Qp8EmzL1+1#0a*uYefSp8JbgldZC#nTA33EuW`Tb%j!Y_R_p>VqZMIR;4
z`G;tcC?zfKJzAULAon3BS^N8ZWQM4wgnc|(UbiKt=SK&teYA0Y<n}m{eC=k|Q$lL2
zEZ_gt63S=rgr-kz3V^TLB-j<A-99qG`3(wtj9$;6+~l4C&oN^yg;dF4KT*rS5P3vY
zY{ENceX}<ck8f!F&<#KdpyIP8vSq{as~>Pee95sO8Ph{XpK)MUCWd-cx<2Yt#`rWs
zz5fSdu2fZ;P`_;wz8orM6pzda?&_P!r_JbRboxQHu4-P*1K;?A+xw4Wr!k;m8Q<zK
z1}pk;vDfK_k1*s^B?4I#Z07PDUvf;*F=9aY*#;d~qwxA#J1^A^xmfYIjZ0*LP&E$@
zLe~78y3+O2eQW+roHDl$fu>_ThCqQKKJJmuxWOi||D~A38B4;aQ`??eeG<G`SCht5
znb(30ubO{eRng7(h`I24O0<+)BQLh0ZOsYWQwYl^aqdDTaNidCOF7<}5R=wF`G<$5
zP!|;)f_j{TXD`+zZcX}S2>!O(PFqKZo~S|6UOERBh|@}V&)PaJ`G2IR9~fue{zgl5
z&w2Ix#S`uwo;hW_%6+dWU`T`A;^}gqwTKa}%kvC31?>OI^c(XvA+06Q_~|<{z}C@#
zReZ)&<$oz38ZDaZ9`mMax`qgYXpyz3Nx9O$18RdF%O{d%9LJOJWEzHGRqkcu{YiM;
zO=|s%jp{slbKrcl@gGsg;!l#*LI?qlby>qH{phx6gyw9#{fJdaMfa%~S_H>|^e*+k
z=<#+XSOO+90=UALN~*IKb@nc#fexnVwc91@hz&VqW2Z&x!HXgY#|-J387*r!FtX!&
z&gDvENQ@`_Q6>W6<R7G)>@945y{aSLSS1N%Ti$J$f;IS#>1M-x08c+-xHFb2sQblK
z>ZOy@jj8#$DA364>Q}nLxciCMqOwWJkAA|US#LISGU<pSi>*Is50*G?_b}*UlZ_MJ
zGgeGFS3}-N9`<vv_}0fV+mGv(J?>h6sC6zh+W|g_=?0pJMXb(}y&HsY-vdO#O4}dF
zi^X4(mdo&7W2w|=Jp?IHKnW1}cFOZ<jrZKNaEY@9<?(wWWFy;z??)(VJ#7EFjG-u(
zVd_ibRPd^4kiWYI-d37+sIv(Afsqv@V$BAPBquU-3EqYq15lt&=1JA3v*-Ccfl{cz
zwV=2WZHhg!=jYjXN4s~EdE_gHpd~EO;7@!xexcC(1vMV$IoUuzbek$Qs_@<YM!6b{
zKN68Z?ch#gE``4w2Eb?>=61p^wb6S;9|b6;BiIL+keA;LPO>W~?~LVYjRo!njg*73
zs&=4}AIfb+H<91{7ll~!^_0ur;Iq*!E}^QVe9)5YxRT=%Rnn60#(2AO_{d5*7kKMs
z%#K12mZp8X#sdjrY--BgFZ_?@!&|BFFe{C@!8}%_TOGr9;{;uY0)!$xFDYw)1HH>G
zF$r<zm}#P{RLMXK`c=Yz$GMt@FxX7O-BGD01?!VZoo$jE0ipY+j3!`yEBLiz*W6DC
z#4&sj?K3dhU;yAwxG@!0!2Kq%2-_tLjR%hK?+atJ<UYL=#V`>6`NrMkSTdzJW->UL
zmQ3B1An?W0rSGcyzgohEYE5AlgLnz=o!H)nbJU7Gfl=f$2va)oheh7>Q@*z6J}DbZ
z$SPQ90|U=N#yU4yxulxBDqOVugR_|5Xj1-9<(lm->;6q1A>va^10Up+bBU}qEu>2#
zqamiBpIJC7Fh}YEQ6cYN!0)*}*gp|axC3A$0v&G3^<=*I);|Q>3V^QDlPUC<(mo)-
z=4k4yIG<r;qeCA4c}Ze2Gx$w8Dof#lZ6@~A=rhqD%1ywmrf>cD!~7iO^)r^g{il%X
zZQLopz~GW>-(}yiht>_0@h+eZYVTE7m0%kunuDfb49|U}ZiuBtD)!Ao<0NG<U%4PA
zMQkKvU9b^D{gu&RC!pI9)aiSm=XpGn6BfC86W#*CXo?-RD?jNOz;563_T01qr%Y9V
zg2eTRR<cQVH&vci@g`^Zwg_x)kgFY&iPNd2ZJO!dv^)66jZ&_hso(fzwxY^2oOs)f
zNB6FJswMmO$L*P8QZD+cvF@uy=Dxd1{&1al*rJq+Vk_E)<=31Ho3eM4)oK1r0-TAL
zPT`F?dRj)b?-Jl&ri_iJUt5)|-jK@>uhciB7M2grd{-}(zhUREIYtcDw|60w)n$7^
zG90R+8b4b>Lv5~bQ<QlwY7Al~XzuLlfU<zOEmXE&M{YmRSxUB!qlJHdKd$E|b~?6c
zkTXe!*;~yfI!aJ6d^^d3mEyy{BM&(lB<H?sV!=DOlKMaA{EuVeM3Z0nYh)jv0iNE8
z?b>qVUzIIxKk;@A@fqiJ)RW-~nrPM*?cZmV*NM-Cpb-M&@0Yz_by7Cir03MhY}F5B
zRXzW=$q!p7g;_gu)2ICp^jMU5+?{lRfcN^vi#xg!p--Y`p^heg=;?<OmwB86(kZ=<
zcXjf}_Nl$D$@6rOWRt9qCI(kBx2HV51&b64Dtw{BUfRM*_gaAySkzrcDV)Sfpw~iT
z*7pe`>;&!*M*%(y)IJEI6Qoh`+;a*$30c?As%@JFh<kXy&a){S&tx_yJTr_nCL+J~
zP<lE34>W%VV&DT;=|V`poXx(;zj=<+u#|cU#W+1`i3iS_vA?J&s|cZ#Qj%)wkm=lD
zS~@LsUN>p35JBH};-4I=xS5Z~9V#U7;Yk-$AM(FJ_c}|yxfA#Fx-W7{UX}sh09C!l
zQQnU#kd`kCfj?%I+2a}9c-*kXU~Do)R>=DC*B0489a(`A3RaEqJx6j%2-^fmMo;*-
zsetwA#1~Arwq+Y&Ylw7KQ-u1fmX4_2b1XdH(T5b5gH~@|`PAH~sY8$Swc}lc&$_p<
zczTJC)f7J349?PAPBw_Sy|e;Q83;ez!kaoIS-g~RZkv+`ib>fe<m*{TrP{*IvsZaS
zyNLLq2^)br$^Pf9xhv0`$Nso-g?s{*yG>Y=Yo50$j;P_@1m=N3ykImvbT9gcD2{@x
z)nCs|syt7lC#Nib|Ft)O0x$bDF@@g>?n^}SURh21B&&k}k0Bq~MBLGqe}MPJ_uFk`
zVcKU&?<CBg&&>B}zXIRwT;8EhJBtmu`NLP;Hh;>TbO$?71Jcz_Uvi&xf%!e&-<_Mi
z*i#K491k@#*f-i~6-TSq(EKWVzQ549lsQK+r>`c~VLSVTa?|;xf81i~=IJ6Ea2#h3
zOO45b9-V5a1Rxt{2bS;exJ4gyJ#6#(To;sJ*P!3G*Zx3?a$JA0uMgLBQeKXDUqe~B
zb(TfEf!}*oj<-^IgGY)>`5Jh>kxoLmvJ#v0@_I6ZHT|Vcx*A2pM#MuoIHJE`C4pea
zK4q`B+9m5iVsRs#eqDd`Oo}hY0EJ-&-;je08O7U|zGhQu#C^Gey$Nj=1YHlFmBX4E
zKYIv-(^Qr1S0&cCUgZ<3M)~S3Eq6@?6hUZ^q&e4?so>Lcpj3TpjguhMx|REW_PzC=
z^s%OAxcMhJGXWig8?b>=R_fsGLs^WIJ71qn9civKqc%sM)xS7EU<<fjsZzoPKFlKZ
z&3c4!Mo>1)xfin$eH4F9T??7XCI!-4JkeKH(0LkA*GY_7)Y!sTcuV<gPkPIfQb}3s
z0t;?a*~WRYkljD)%X%tHvqHJsA<zHot?2#I|LP&EWl84P=DiilhU8nX?ACI7?{4Sh
zaMHdF-Bq2%pTr$M!6rp#=&8E#FsV#F+`P4CZNaSs9y0v%zp|60k4h<tfe1D&InC!>
z*s+P^vs%=?_L&c@MqPjSz7CwEXZ37x6_FPF)FJ+F>*WZD_>N4~Lro<pLQib#qc&Cd
zAZ7uOM^@6%Z?j^6U+tWq4Z{c@==ji;NB&kPX^v)aR`lCFUeYh8zCf;AV=nU`JS}N0
zMAe`q(DX<P%lE}VCDpo47Yt@ymBLb3bA*jXvr3*}DZhy_$%)DLlwvNGqlA4uM#34f
z>}k1shPV2XvN)P&E*$U93(#)mbX#ODaXNliL<s&DbdMd+MT1n!#k4HmsxiImcdQRj
zoPVb)Z3>uV=UqZjBWyh6PJZxzdZB6Ht11+XgyE8~>MQ?-p2idTJx@&weJ!ONAb`)>
z)+Wfmmq}#zY?46;{shVfBuZal5ruafY3-`-^L)gKv4<~S5j1j4{R1COqVzeA*Y0ri
zo4V|Gh2)x$Hhto|=K<8za*j)c#hs;sOATL-!_@%l!F?>}5Q^|WHCaO$#G=x3UlYQc
z2R+?dHC5tZR4G~&P8+QK*6@1thYT~tAkD6<wh!bm({5k4E9RJaO}--pc84VR#3=Sl
zc62T9XjjRBS`D}1jB1t4TbIRM&pqoPb_{L6VsDsIlU(o_(tsly%B-8R{d{<g8Mtf_
zkdzQyix&@8MRRLty!4cN;WC-%lv;{Yhv3_Kj5gB{JqoupzE^ytSAtadoOFbG|1-Fw
zf%W1eOTd}d{aq9dPIV_u9rF?1t{x?YiONz6kf>mt12wlITHw6GDQ8ljj`H?p+a1`G
zcd!0bg8Cl7d?k8XxT}^O@II7wgyoTr*L+KIvt<Y1G$vlj*M6Kt0t8}B*04Oj@=Gs0
zQq41;>KrSnSi6O3%*p{T*~<41x*jyQ%a)Z85uC}<3Yw~6nx7aCUNJ6RDRLg6Vmj_k
z*;BU4d%)#!%~h;TqDXU;1vmGWX96!E6n)O%Q?yL`3mU=h2_eMaFHbs30)m0W?A|6e
z(3vnEx}{Jd9UkjbGe<9@{Z6+z-UkVciru8vT*^kHOI7c+0C8k_iDP&e8xD5XR1^de
zu7jTaHixzTcWnNR+a=HtF&CGI7E)FET^V$$O(*^8%vvFLlhjy=2i9XB2J;I2#Pb8i
zLqnM?82H}s+`TB`T7Pk?Y`LNM_dz_%*|fADgIINyZxAtGBzfv&1G`y<mVHmN`HTXx
z;YNkS2QsXuT&c>lP?-iK<cOKaY)A$-cX)pY%*_}4`i}D(3Qv-@mU%#BooL+KXhWSr
zh20PjsYAr&c3BDqq@ejF5!J)@dN_N01zkwi;n&ZZRIgP{`yoOqA+_HwMpt;2uc#~!
z?oiv*(#<yEnskiwqv&!8zfs;_r|PznA64!=|NAfFRJiFT-7oeH%cx4?D{5B-P$=*!
zu<!bxT%zC0ZDy$r^1}wQxLW;RRV=IpHq*eI_iQEb2WuD#bsl4>TIFw#)gfO+yG|0=
z{#9qel@<!oMwNnoJpq@dbQV@k_`DP{%#V~ashgv$Wg7?9lW=I@>uqY&(b<DZnIkHL
zZ>(0IknbxlIt#X_E~sCE*OkMXWTmV?LP;_LLRVZl4Y(vkWwazUGg@9FVSz_wqZwsX
zQ8^Lz)qD63EPNU|ggEyeJW+$%S}y~R6Ha(buLO3jS<NqgF??%~`GTIzGq(%hd4rbw
zINayCy{|`82M;F;xa6u(UB3$binp)L%BmAs4-Ujr9L%!o>V0_cq+2oH-%E@E^~=l3
zfzW4<ITmtrSpcCNOAwy?C+QKy$NmhKPE(ax*N?zCzg#<7z_6~55nB6w+<P*UHmQR`
z+VenqiYR6SKQcDU-TXo<AE6Aq@{j1R{Smn;{)es)SXFK06IO53>9^?)D5Ui%+W5$O
za6>A!|4ixJA3nT8kp0wKb5FRUA^XF4I7r{jc1Z(Fj8EjFWiQ35g&JC<+u8J!T8jn6
zM_5;G@>Qs&#r#}|YgSr{Bm#SzHon2g5Oc0UuZD0Hn&*S2C}Vx*28Y{LA82ieWT5Tz
z{4$IV{1D`wEurX^JEM62fzjuF95q+^fT4lS^7ccj=Y^><&1ly5+JP(G!-!XRf)#zj
zP>Fhj?SYs+>lLj)&$v(R77|Yd-VauK@Q^i^I$o!rxwYtk<ZegYRp!hCV0y}4t{YkP
z-OZq+#d<A(hHJYNr*ece5%iff<xfnD=DeFx#)dzgUjYBs*LkxyD<N=RpY02>npLuY
znDepTifX0wUH14%B<yU`<s&ZuVip(_dX6_GHu2U}l}6PiX<m*pa7(c2I5M)@{82Y9
z0(bVFqlv%!t8^gg*I=j}#3o{YfR91o(vPz&#mjTlaldrmE4*<oVywi0>IWva6pq3V
zLZpZ$KKGsT#4g(iMtpztc~nbVf2IW6jRdUvEa6U~_(`J<N3`n7MlL>w2Jz0ksz<K3
zJ0c@`BL2xI)Uttiy0xdmGR=K*mC9ZZHZ<SWuu3Xi(d6&_QZb?|wm&?50_E!?Y8}Ca
zQkC5nMdzYK4+zeF)`HK5B-~#)!c7)nNW1#}u2?4QTbp8MmQdwi?IzeS-$fJ(r$5@-
zCCWAF2UppEvSJ1&>qeq}mXZgnU7ErV7J4C&MJ^~WXa>#oy_f4$1p5zcg*<~zJwBmT
z5UqL_WeWJhRt=615)C`CMJU#&Fj0b}!icQ%yq@IU=IvrM&T5IX4EmAo@@Ubb>b4#^
z;kNro+0e>jIdRiZ+gS|$CVt?#!er^<XtBhavc3hb3MZtPd&*Y^OLdS9Y~CXm%Nn+Y
zC2Gdo$l`kw(sz@yZcMt#!1SV`_2huROYR^V>6Y&w%K8!0eK(2Qv+GF#SsFR)MEJDe
z1<#H`*9<K#9w>$ewWBwIw4VcG;G~jw^;3u4ueO%_+)@~la4}Z18{76+iM!hLo3si-
z(z#%zAK+MC<aCLK!7Y$v$%~G0+Q+D0EGucQ4WUu%IIM8p9Bx%8?+}UHi}_+{E`-{i
z_l^UuU){v-qenuse&phEGHPi_!!LTvjY<+JHCXhN^7Qo;STme^AU&$5jG#{qiEQA`
z!0jq+ho2VtLs<!c<eoF*?q$I8i<HBK!k`fflix$9YZMpeHrvyp5nQt#{{#K5R4;c(
zBG&yMC<$rX0HRoZcCPuz!AVP(a>4-zGMgWf#|`=C*sC*+bbClU2K7VCA{g&GjTCmz
z5C&}%XP%%-bVD_pbV+pb0B8mMOga}HX4AwCN!iF26JVoErzL_e6=9K+(E!eMiSz?b
zss5DTsS|3|R?$~LPW!GDHEsw9-M`*i5da<e9Ka^ovq;a99`=N>KUObvV3PvPt59uL
zj^hHx-jw9nA)6pWgG&NxzLj1r=qKE}$~`@aUJs$D{&Vahc(FW}e-r%axwBd?`^eb3
z>Q!GDOB45QoFE-1cJ*Bt|I_<&_z!c`zZzHxPqYbeZrQ#W7t2Zqg}|X2Q!V7uhjR=T
zvIvDAtKt38BRh^Ly;f`JcoGkjZWsQ>A4oI}XlAxCHSwqYwmPQq$MCf%rt`L(u(TWp
zK-fg&Ii>iL8*F1}o?R8J8Cxjz2|`ixkN0>qXJaf*o+yl&>yK<Tw>`i`&C*PGSGPU1
zW;jrse0Z|L#u?H-R<rSCaD$uZI)$<)#qzC7aK1eT5m?f0OEC1{P@aqq%Le*~;$A{l
z(lx0q?R2)tRs0?-uVsoxBGU5P&ak)Sm-*JB5}ya2FPhPhI*z|t;&<O#YO9so7u*;#
zw{uNR&du44FLowMZwW?=;R?RCDU&T43{=bwy8=qcI-#Zeg$VB*#|ZUl_1kLoL04q7
z3Ucm#mL52Zk-@H>4v)GoLPj*P-L|e<7u&O<#|JW~gk>MOMD8nsaY?id)`!?};*sab
zt|&PxPR^|B?MAK-36Q1W3K-$H+`B$ZRXrz|s1hET3i+T9s}t=<Uz2+7A*<Gh6!4d8
z?ih)pU6<}>mBaSPL6VLLowtG@R6Qw0UXh^4^R*97O6zFmwNWUeZoXr0>We&6rN=`P
z5jKAnLmMU$?5Szyh*UJ?D`p0uTV(*V*?m2FVHtw#jv4+oIE%;Hns4s#KABczrWiXi
z@oPBE6MIQ+U-0A!LS(QCq$uPgFBu8$i74AygO!=zxt0fakg|)%{DOSRb^F*6TptID
zMq9ob#+|drEa-oqi#S`zm8&(PJ6BmfD|qy3AvY-kV+w2{^=hQOZ<;vR7lHKJV#Xyl
zmL@k~&S_nQot;#_wdU?xE`qR6jl;^=f~s&iq)&(V9Mlf`mBhQG(|F!J8AH?BV5#Fl
zDs0?xSL3pp4ucql`!d|jQ`*tVRjX9EVfp&3+m>fM7hY?>gV|n<dC6tWvkQ(YE%$D8
z&GybST*+f@pdV{w{J};4>$agJf9S_b3+K;^sqxmU3Wk)i)xu|Q+F;#|;xArj<yebD
zG^8{<Qw)G5`TLZVvZn|}y+;PIkc+)w&%(4;euizBtCpJLZt$;gy5HJm-%Zk<a!|<D
z1a0N|YP!ZQIuO;CH2x11Ly0@D+JWO4HPu(`WgF{wy8H9^bg6V*6K&MNhHe@3XgByR
zHaRB<y2Q<lCKoXRZVZ^7`^Sj31z2y-9ZD*j<MQKfZ1l^5GsUWCpHL&)V>IjO*oY5I
znlRd9bzjKrqy%QaH}WfUEzdM?*E9+wflmqSmBuGWTem+fX~Fj#>8RtCR>+~YwA}7K
z@HRM_;<UbVlj<^`D3K6JCO6CawUmXrFJvG1cDl<GzYP)po!k9PF6m$vw(O$}!c&|4
zC6$?abTL)3Gq<HIb-<YIBYEcSHxK!;UTF3aI_VWO&Ms8DlTXzW>O<_qdB_?F<RiyF
z_j0RO6U~uLvL8dqlb!p#+=~-gNprgpm7FVNtpxh__Ku{`8PCgN@dXKEpa1H@@B|B0
zRsAzyNS8E8Zl=l2Ln$X^>S@8CO;1!x7y(HL!;Qby!-+Pp<^I<+N@UT<<extAf(}<0
zJE9@f0D-)ey)!J5_KEKh&<#IU?v9!=d|e<un2?0SJl&jb6>0)(2nN)arlza{!azvp
zne#XhC0PcI7A30}yWCWJPc`_7<#Clw9*qT`)#4gjz!dVN>0JcL7)l+}MS+S};r#GG
zIjkc1bvY!s?L`QQz82$5gDPF{T^gHV@oY}_ybT-cew^p5p!QNd_goylJ{CF4($d@w
zL81bxp~?^b2g2E^%F)AQ#LMbEz^H$L6<{Sx2n<s#Qo7)0{X!`}ghvl3{VJ``^%ne;
zhOdf5_KpE6$<H7l?L%jN-=$Op1(>aN5mUlYr$J_Kqj;yA9URfzx8LvGp*bK!?BI0P
zu{jpBf$(u&3utvgpYg6WPS>BS-%Tb;=z3?g>?85iNKbc+DMEv)g%b=S<Shz)XXQln
z6S;1FNPwdpOI6z4nn8hU6Yt2d-7%=Yt-n}=<8;57@-X~F?eQ2ZWwMNTjT~yRf)xuT
zB=64Uhel(qq?bMubx8Rn3K)JZx%<4#tNTqpFL3(=2$W_V@|xvFZjR&IYflU<Om6QW
znOw;|Khr1WiSbN+4`1Rsobpv?`ScMLTmfU&!4LA0SFzDw#myGHP-Zfs0<?~5u0B4p
zU%)54@}jl_rq6>AR?nRf8vcD!a$&FDol<;>OmV%Gkv1rCB?EWSscJd3tvY;qPRGUi
zu>@5k5qHro8J+F3Xpq<MSKO)gi1p8iHp^B#pX+OX6ZEr6sz0S^>@sTSM-AqF><!b2
z^G^X*w^yU%@m9h*=@F#hTb54JvYBlGhA8lRee9~IW<)iQ`16*|)|S*iIj|4#j>*y&
zMMj#;0?i5D%F9cxZjZ~EeZC_fnM>h{6U!NW+q+=Utj-%<+&YvG5c~F^dyZjcZd<g=
zT3&dQI>Zk-zNl8&_4{2?gsVeZq*nUqekN*vrR-0!GexL6l~=%R#hWY>yG7FHtoORK
z%`vZoH$xQimGZ~MUVJNVy_aCD5#<B?vqCPp-P7LgKS-XxCkSnyY|8qfrtp}+;BqUR
zPBl8ub2)GuQUZV{l!0u++@NW$iN<E=>3zU{zciF`FQH2gg*PSIX9lB`AIxe7s}x&O
z&cVBU)UN}}WX1dkx4YgQk;~p_o}RD%4LO&mGn1eEea;8IVPW67Q%qop8MJw74AhJA
z)LpxEo_cvCeT3vwHP`th(E0`%DFLPsGtpCUbm|Rom7Nu|Cmj_+cT?&>c|VfcWN{`p
z`ix2{LtftR)}CWu2Z*^cNL!Hc;I%!u%Ipd{f?t)ZL>E<u`T}n)!!5naP3jm8{X%a1
z%I2&vJ5a!!(Jhhje(QONdI^B9u>8p`x0{fE*O}X05i9qJZRVf~X}6*@226!*3I@D_
zvws9?H|{=b`7OTU83(EWl=c=q!#`0eGhh4*6hk%TYAB1feC2pxi6QcfdgLEoE95L)
z%K)6rQ@M5gs)*DbYQU?5T$G#|4I*Rg4Aw6$z^qOdz-Z<lD!v??(~~!5oN3y0t=H*9
z6+c5Z&Wyez4GM0UIn^u*vGzXDWIO#r@bNogCbisZ49S|!5{`~6fK2p_#cSf>Jbh>R
z)m24qp&+$?tX(LhehI+ar$RX1VQZs*R9QCGBJC0|CI66jcr)=#yO#t{nc-T(M)PhP
z7X7oV%Z@ly<MtE}-i{27O6v<YypFYAbeG}5o{JeHeFapAuT|6Us+~oh1KXYtz=%gc
zZy-#_@U43+(SL=xMW@8-5Wv~@L;5yxF#Qj7oS+}NSlxAhVd>F8+%C(_N8w(yc;L8t
z5`{CiXnU`zOYQ6>ME$quE?l8`X33kst+SzfQkzJzn&FsJau=|g3)$!8y39c50B6+j
z6Yl8|C|bzyU3T-vZNY{ZQ!gT5a4heJ1)!MxH2IeaTlGy|5G-foYXMhIX-75EalgRH
zyGnd6t`%MY?*NDcs|GAgidy2zfcC`bWhg_3{<%iW#c=sl&v}x@Z*q_&c5EE=Hs$iN
zm}<x5Hj>kjYQ2skcpU+#hWnwR+h;UUZ>e{1Ux*KCNFW$fdnkJ<g`!Y{60#vY{}GoK
z*%(?k!nher5(lU#pz}qp?&@!4Yj1>T&3Dq3wnUf#Rq?AS`P)q9K!i0IsOSk1rF?YS
zE>C3uyXI3_v!>9@k{qbY+lka8NAlc+LK$87yM6gS2ydf%8xCp)5v)(K9&eNT<)7v=
zR`vu+bNzUSoq$i;EvBH@_P4*go|dzr4Y&s=NEV%dkRb0vQ)?T#w$6Bcfy;dJs&97(
zMTB}cO-DxWSjr?XX#i1yy6+3mE7&l(lfWe)4a?92EVJk31iN;Fv$&b`s6NI@su=%^
zXO4u;<)UGtFPQ%a@^#kI)YJJ*{dY6l+sLr^{c;1I`bYMpnWHW8^_3Ue-XlgWQ<s+f
zX+JqJPRDrxITeJw9mu<CVv}goluR$>s`N$Xpe#R;pQ#6L*=^3Hg_@k-K${;BITSuP
zx_qMfR^@kq6Qs35O~up^%MSM1e0D)t#HiKr<o4L}Lae}QM&@tjK|yvC0%$M)nWF60
zrvlV5#MmF~>zBAhHKjj39sRz)i_E>BNuCnZ_;)-smR}_8dbCEqpO;^-@eE9y&b<2i
zrt#UydzPb3?rLx2s1z?VER^$JlV|*&oZHZKzOC@Ovsx1QpGQZ?%ag5iLR0U&>%DjD
zC*E7;semy2vUcq+YE_ijaa=U}UlIOYMoG?NMJ<Ne(@-bv8<p=8-W<R!YSv;T{L&SW
zfkhXfIMCqek8AX?tQWBq5&r{eXvvYAVEZSK-v9C{^<Z`mYhF*d_m%rp^C$^8TvR(9
z>9!T#8mI#Cr-O5%PtAqn<)WO#qZJ;&mp;omJfLd&@lC~pgW<}Qu%ih0gA@H!Vr0U`
z=6vy@@bKpg?@n-^KDlah>;>{ITX60o4^ga3_t<=P-Zd{r#ZDP)rUy!DdALmLf1bJ<
zr^FnrPik+Q4JeVPnEFR)XltwiL<{`kPR0BRB-}}1qlzj2!E1#y$~ZUmTc3I8F@iGg
z_>K!Pe{EV9tXhnhCndih#!DjmrdTBu4KA3fvu1}poo1=UWUr<@nH5W47e$Sg^+U0b
zH044!r0$==m={t1nz_=Vo;x$%E)XQi?TzHDlzR-0eTr_SugE(=y!=NrZzixPR_R`0
zu{78rVEhBGgN=5h3;aA8?(~CipV+UT4ezqNbG1x13-Y%jq+j6h^0FwX?_Jv@LmKxz
zXVMKbrJiG+-Kog=Hb}elm5qO;j#qG{T=xfHmdml>YQt<Q0X<+g{Gsr|Zc0{h?p$y*
zBvB0kY5EPDY?T|)XJwmZ_H+&3Z<xT;ZV;kt!f*6zer%b-D4qI4gSPH@h1cV+(AS^A
zA=8f+?^Sx)AsxH2tJF=B?~W7na5rv@Hc=tSB3Rdd&!6w5Qa>|TKkZcvZ)p9Ck-M`_
zneB^QYrTJlyLR$b&MiC7TN^^HYA!Z>Pr)Z?c9Sx;noJ2W!QEr%Pd!w}C(1@1tu0y+
z?nhiM|JTn>OA@~wJpX=tkP|X61>G=B_J_Td1E}~P^ys2K-x&Q8$@(0`{9lBa=(PFQ
z`rLm%XB<zCN>o-G!PO3|3`m*fW}vGQ?(e{8ZXb<W-bJZQQm$r(Qoh+=ciuwJCjO^>
z2NVB>U{<`3)%-+(qB9r@hCYEF+vW0K(DI#evrsrc4dw(oD9YYT`oLK8ksje<Z|*Hk
z)s~2k*^RH-Ejy>*$bb5!053Anq)R{vL!3a|>f9OPscA_%FDT-BGhsD8VSfS)lJVdB
z_CM<!f7I~GGpA8ASmfO=2^UCIcCb{j4HlvfDgHl2R~gpS+r|k2l^D`JN|98$Hv|ch
z?gjyY(JfM=L29IQH_{CvAT<z??vjx191Qlp=l^|h?K<b#bH}fC2|rV1>7L%z{X!~U
zUq?|xjI8o2i)1GBPyT>r+RH=|^9vugI94j$*UJ6BnD=MC2Jfex8htq9OHm(r3{-Mh
z<onaR+R?f|p-osmk$Y~+t-dQQaK}P&DGs9obq-vfEvdV*>Zk=&^nyUI>~1TZjxOa`
z_+`WHrke!zSI4*_LhZ~JjJ`_7l#1J3ptK9W*R{wb4)ko|lu!>TT*^XHrOJs8j?DaI
z{!Ng+a{b}JfEtLl9oczUT<n|`I$dIqZ6x{3pi3~@^!C^7V-UJ&@|-XQzAl)3aczYt
z;qUz5t3GT8nyrC5@9xi^2VXA$r{xJr66oH~<2cni#eAUSD|~Yd8eD8nv0nu-CgVTI
z90wk3tvbz;L$;?R3_0N4zs~#Q&JvM8yLOsnf9%r)`5zW%F=lyo>3At`fNSr}8f){g
z?6MS0^^)ylOF+eagf3?03>S1I#?)4U2TX{x?#~+hoGQB4xzbzYGXSF<e?#}a7-~Rr
z0FjY(k&;yqY29cVOzw{xmq3)L_-p$kx9VK_wera9)sYMQC`}g@O5{De&%b$~^bE8{
zvF}Mm&fyee7N^r~hyJ7A%z0^^S2qUe!j^{Qs8#3Y886!JGNBD#0JVj;B>?;)wK>2o
zIqLJ6S1J7osfauOyoII>P7bvml9~_neMgvdT-Zk3p$vK|;Xby3`;$m|sBCZ%jU#!N
zD1+nUqUo%<6*>(B7y1}oML?GO{iec<(BuHO09h`Qc`fGeXA^WA^WXWaf%ql7lgiB~
zs|_6zLmQf#XBL@4`-y??kfGS<Cc7uGrvP#rv+77qKmJ1h(=9>pQ=aJ{0ww39K|B}v
z@1`7DFT4$u!!GGjDB#hi!>2mLG3QqJ`_tQlb$aaClUr@|FwX&ThpGov*<8A5TxW+C
zwzieo5(vY0SH(sCL5Yd-n#epNn8EgrxAd+$@g7T;1H$EphG>|xxn!-nFsqNeK6o!4
zh_-xj-&2=K64OffYHP-FL~*jZgiQ9(<P&eEbs*KV+Ix876{YW-a`cRd@Sppe0p*-u
zyjdfjxBfp9HGmzdadM<9^`2_xW5M%;z-Gfs^k?kl`)4{Vty;VPVx*#!4n}oEji?}Z
z4C8mw@#5Sl?PP^1*$d`T{wLRQ&-7h&A={}go^NKKkJWIgA6AR;N&N*{`3{@Z){LLX
zA6PPTcdW##T6A&Eru1w#Y`aud%@MI>ZiyaOdn#1EG)_xJV>LicA~t_VjA(3uE>}QX
zg?hqbOoEYwTAw9eim#HqTq?lZu>lf{&PZ}c&JDBS-{pKF2Jiz1LF?KC6FOF$2xVCN
zc#3P{b`W<S`On4Qv04c78nH%Zzi7YJ-F!E)2Yw|l;^#g(v^Nw6_<3XuZVtE8P8){Q
zY=`~`<t((en%>Va_!@u@?G-d`VFh@PKYF)8pT=N}6~GBL{XQ5tl9_Xr#aQ&r&$F0r
zB}(P?5wLZz!+CT@d_B=HBXdKsGuI4S562U49?=lI_TG8Oo-A#32_akBKKS#JFp=0p
z+d`!9KcR5WLv3Z=U);GZpzjQ%JaF^@Os#!Fu|((R;SxNLICN&d3_DAUXe$&{34Q`R
zZ?aKeE(W?Gm!e-xg7E494oto^*l9K$iy@XI>!qmC3EJn1dqAy=we5dcc^?T@Q=8F=
z|HI<j%=6{J)8^}NyBG@mqG~;-u9yr}Zn`^K+`PdBJm`=1h#py$(Ngs5p8LzL4RGwq
zE*#9?=G31=H+g+OE!r}7B@iZe$V_DDyX-ko!bjRx<;v9y2QIE@v-1>$+$Cqvx*yQB
znzQ5G=`NY79osDGUMxH9DcSro_@YfF_-cHLeR3kr?i1UACcR&UuHlPCx7F~5HaYZ2
zQS#no!Y_Sa-X#&11W-j~XkXfbWX+pzX>Mk0U@m=**8ED9#db$dk9br*p3Bn}{_Rb|
z!|922$rSdisnBuTXgyO$a7s6%`B|h{U_6i*%bg?|nyV#h8cQ<0{&!k;dpB8wkT(E`
z{%i!<YnC3M*#9hCQsBOTkcHK+xQ-$jJWH6!T9KpfYs%r5wWI>a#$~jJZW=k%#?EGY
zX}i<?cCW%5(=cXHOhMyP&n>W+K11U)>G&#QpUk7Ti|LrkWq$9_9(3e{8MzP{04=%+
zTmmSTmk)VTVF(Z1xjx@7w4x-)sQ|zooO&72)IBZz-z+nU5B-cNngA}7>u50&(9C}Q
zX=)!R_gEIXCKTGMCK!_hYNV4JZ}Bu`W4_IiX3AXDi=|F_d^IXh9R@Bkxj52l4ISzW
zC<AK_VDb2xg<-R~Y)k_J0lRm9*uZhGeH54>4iWd9z<mN(5!DLSVE@}?1MdTymeNgG
zJ#>BORRwgNyb;6MUIG*VvtfMy<J^=%g+BTDK&7!-@zO6s!suUF9ez_;eT%-}tN!E@
zHFMD3{=!=FRHmJr>Yu2hs7)y?M!C1Lz_Q9VSPxovIWc$&GQy85L2NwowF%+|l0EEx
z3Fu;RAkrwxj3yB)27r(*0p@Ek#7ny~i>QOW%dYZ21BCSpQ+3}zn3n^A<tv%lw?1rj
zM(K;Nn43p34=|}1lD4qTwP>uWj;jptzQ^Ea6@ZDu++;%TGB+V_3|<I!9~2z3()wn1
z3t-@%Zwi8S{bh6Xmdf0@rX|8|<e0h8*s7uu8brEQVw=^hYxB5Kfj9ZZnqqz_maff@
z7Q;@hk5oud6~xnipHgoXjjH)7>;X-*s8zOiu|WHoR1vrx8uTBXQ69ibpbM3~_8tDJ
zU!y=MV(F{zWZeQ-UA-a7Yo`fj&%&Dtc1uI6%<CQ*iT<0dE{kf~9TdSn`j23hJ4PRZ
zCG9<fow@j@95nLr)+WV)ZVGS+1}pyn%CmIAx*}vmX_c$xk)<F&!NgYD?^t(9B7vlY
zYMznfHY`EHqFem6AG6;I1nNv}%xGdt#_sWhxC!&fM47Y@y%A~sRanm|ZYq`r`bF>k
z>Y3WgyVr%q#u89~J2B<pqcd)g1kewmMW3AE-%;(Cr6ZdWN6sjwARPi^11_RrIIn~o
z+s(04G2V7(ezGNR;{`Ked~UN0>eyYZ*#$)k(C3}Jdn_l_a`<KF2#Xzxtye|W?Y}fR
zxy{2%1^!+OD*`RJ{1-wSpJNXUMc>AeLF@hJR>mIax(c!Icyq*~cL6LM6Xi^FGw(*s
zT6Y#338I^mCx?-L?cbg;wV}W^Kkvwui22w3&J`ZsjBTm`4@~PMd#wfZ!#2*r+>57<
z=+iB%O#2KsqTgjqJ*@;+7`jfHM<aT^*`>;I>c`X(wiF<$=e~vtQ6wB1^ViDC@sBqk
zl_n4}AVl`!0<Z0TGH%x~Y-F8Y>$}+}f2Oi(4MX8l+$7L>S-NmL$){`$);k}GJ~7x>
zEkG8QQ>V4!&Kqp#8m;yew20^IwwQbUu0vXq4r|VZ2v)H&^gk>=u@d0dtAjI|ByCim
zrZW3{^Qbl#RVEsFW!fz~ou^=L;ZPG={K^Z7o_RSb<heV7YW_e>bq4>p7Ys=iu%oUH
zaW=-CDaSQ{W$LJqoIbu3cH*dybu@H4nypie;9J_hXw37?U6So+P4<ACm}IKhbk0%n
zwb`;;aY$F@Wfa;HQRMk%O27JjTP%Z|o_aB9`4I|a164H8{Cp7wu}BONE4}TIxM+ZI
zi>QN6+&@)@NZ5p(&igy(_#AWQ+f7nuYPB+%|K)m9x%ateA$R#HK$Z?~zc@SQRE%&6
zrfs*nDsz9&Te(*;mcisP{xr_(hd77;`nD9g{tfSM2SBX?-Vj{P1PcgPt;7QGjmW8o
z#qdtW4`WkeI8_J`?0W<9La0o3GUbXE;3IRK;Uz$kc``sWpE9pZ&pRmBBpoCP^jqUW
z70AyjK^O9)#_>Phv%6vU3ovMO@#@m+EvjYX2pT!q77Z%gAcS8C31e-u27J=OW$gSQ
z5HV1J#bAA=3gOL3ffq64eUHDYoZO94zw7>!V7glbdsunRZ#*DMgnS@i+D??x3`DmW
z*8XyJGj=J5VF#M?Y!}kSXLsIb1A%4&OZ^gw;IrND2(_lIxn>*lD{T1R7fsOS%K^;u
zJG}gZJ3AT~bw-hKeE9WXr5_L|(gsr~se0G@3UZ*IXI@8mV_=(@x&g#s*anANjj=yx
zZdY1$a1<Llxse$EI7i~v8M-f_7knn%P|KgVrwZYb2c$onvq7BcSKB58fqs@**QSoK
zLX$WIj=F<q?}wn9^TC+$^2jLD#wbX(hCs)>0}r-C+D`o-JXH#2^v%}mcRJ>H-_PN^
zeJJvrmZHqKox?6v`sV-+8wS~Jb+KGGX0gJl-#7OWzWJ}4TIlSXIg`rE*V3G7)#XfY
zO}pD=9!rV4Z)O;5K2(Atwlpz~0CZVw`d-f>&;)eDuec-};=_iy&9_2CrVzRO;ZhO`
zb>chq7|?}XwSfIjpJ+Du{-k}r7e2bX<<;Xzu9oCTQVyDJV2(gBuT~)|Hkx^Pbdx=Y
zUfa{rahezhlwa^`=FS*4W!bem<n>Wb@}@=+qjP^8ywaLtGUK&$1O+zLXl8df1v}CP
z+zRtg9m?Eh1A$dqrgZmtnS$BgLPheO3`~&Hoc@VGNnUaN41yX$om|tPb#Ks3Jhzxn
zpq|w9$U4#rJxt-JOJ-y<nW(V&1Omj<1-vBUlwX>s3-fV)&c;D=UEnY6=y8$Y>$xXG
z;_w}B(--UtyvGl8=Lg8j$(l&#u)j$jdjN*>VF}zdKl+-+E9UthUy^kgD9X{T`B|6Q
z`sa%HIQwtN(PLQN!q=hUW^F*PV}6>j<Z&(rR<=8P#3k_c&+W-<O$;G(nFkAGyU0)S
z`QP_6m)k*{tzRgts3w_qqylxo&r~*_*v}sm8!J^kYnYOc&u&(|&S83W>+l3H=b_DA
zW$${^&Z`@)=LFYC9Xr<X822!$hL@DxH-|p*E{8Wad70c!Y)%4m*^(%VSusT2s|;>$
z&wI{8u<xrEG<TW4^d$xTvIN3C8T2=FDYcYM%%1KW!)KuA22IASI0i=zT@&gfqAyo{
zx4Z`gF=R`x1C@%|fa7>P_Yn(A`n;`-hwg&Z{nv~OhMeBfgD5X#8nj8{5#ExpGa1B^
z)MuRV_qXnkD1b!;t!pkL2$;eG+D=s4H)ms!9Ykh|PwBRq)^KJ}+xq&0N+{;*Jfs>R
zb*|O-nTj)Q7eUykeFKtR=6-OV;n(;YZC;gFa4?azi?4XD|M+k1Nzg;KqO_V3$W<}Z
zJp5XZ>Oo%g2*Perj63G~vTmgNG!ogm-R>9&1fdMH(ZB!7)Hy?%%bBvt0vrCgp{1}l
zG*&`|`_{*PNlNnN$*58$Whcj0O8t#+icsw{ab$X6Nd-x8ZT<F6?GI)N2fN96i}!SZ
zvtJH}!gDSE(A9RId*RCD3}<)gEXr!Dk}>Ph-|joPO;rL%10_{kxBp^1nVFjP(Od)g
zdgSplw$5N))O7#0Ky;6_SDA$%9j^d++L!l!Q*`KeZ{j9c7^TZQ$03XE&Xj)W%y55h
z=QjMmJBvB}N*%cw;QOYy`r(a)gFEHir%?2_OuN(OAeUSlwsAUNA1h^oSdv?z8c8BJ
z)!t9<au=2Ga`1o%eZ17~ylcOitMR53jqho8jCkTrqm=JlQh*eX*wQm09<dNb$jV;m
zfKucWyRAFAS&<H|5H~O-Ju#ya?#La`bzr!Y-n1UZ_SFG~n$JfZn}3e^PQjW=oTa*?
zcc~YRND{}{L@{L2@{uF<f~s`070d*~gt^5m!qpGoOOQPavEJn`&Zsh)4xc_|27gT*
z)WD3-(%eVd9i<kd6`GmR^K5M<deJ_4YKSlejxN$kFqQGqueYPQKkabRB|5*QCcU}b
zNExVNdQ=8hv+qOYGbJRIJ!IP6KX(q)X@NVx#33&`cop0scO?XfPm;+yV8LT5(=i)<
zK%B@oKfiJR_kQ;x)u{1D@Ojbi5w^(~^ud2Ug7>!E#gO7mMRl#c7Ez32fL_)^ePt^9
zTg4iUscAyoUO<6IXFDC8j3M1(+wmG})~3sCK<WP4=~{F!IUvXrN3^`0780WF)p(_d
zdzz1O9yJDW@*0+!n#td8_XvgX%100nvn@sI<C@q}$>Eh)=;bc*Wj=QLn|NYKXjMLh
zg?<AKmu@oNp(R%W)#ob&PkP2}x|!TLmk~piVo#rSGt64<iUy~7?j(;-WxdUS-1mD-
zs2h3HmhyV$ELYhcC`0Ri{(RXtC8cMy+tZ>F_MmF4PSWd2_}6MO2HW<?NFX#ku6}P+
zY=2RiC`^W+uABhi<#}f)sB6lcUWH^gr8MEFA02TrSP;ec0GC&<zIDcYjv4{Q^!R1@
z9|OP=x)?JunSTB((nR?EKUz!T06qmOp8sLxHkT&RQnN8!SCwx}0Th0{KB!Tmi<4V;
zLY_Te2g}!gnbv=n!6lX}sOXKEL={Ee9_ct(Km*z9{Jg=+5#b7#Tr73XOgOWk{(!y!
zsq6<e-}uYE4Z>MlU0t?v4rr=f^Gb?6C@KA*r`&p$2Me9fl*MT$_@;PnR_^-<(vgG<
zDr)qXj6}VfdD?66xqsBOpLX0}$74?CvVCqRqR1+vySgP-rT{-3C#MavwSy_Jk+xS2
zAmn+jA(3gNUJHL(K@p+U0toW8-Mhna)#niRKM*CN7%uWDXHKaf0bhVIz^n<I<65sl
zanutuQ~&-Ut|AvQulQd)p--;!(}%}GA!FuJ^o0Sae1ew9@&rNOK7#rKnTc1Qz?XZ_
zlS-Fs?@k@(@8Upc7`^hWZ&uOwhkdLxG|2_3)*!E%Ygb>KeN}YIOOH+gD4)<}Uz=PZ
zCxDy(8eu{wBW34-qqwLpjh=*CBy}#g1U4~J-Gfl~0e#<v6(8b!dX76C(R7dAKYT&n
z2Qb`)%8XlJB#~o|Ki&$7-@uWV>BoZVO!VF+0S#Kx9-~y)#(mcx)DDW8f0%uRf?$0Z
zGa7{I6`_xjjM~TofzTRCJ}c*D45cA3cTJKlVZ!esds{vjSw?_NH{P9jd^&H2x5RWm
zTSez7auzhnY4xzF^pSl+Xo^ok0lHZIDB=$@Rw~7-iaj+4KYy!H6+d0cIKDrd5$P7b
z!mnQmT`Tclhwn7&<TPbKXVpo^y0{X@o0gqKr2yH7k|!ev1JDK{G*|}bWO>}rL^l-^
z*G~bQ^6EenD5Q3~u2VJYMcVMXOIa*I5PCl*)<3ducg^?NrO=a3NE_R)pC>99<OHeh
zm{~e{I&Yx^OKJpIqXug{s`kof{=>RCndwE0?RGxsvHUdVkO@2n0zX`-QROnps#)Fd
zVO@N)6W=c;=?Bieqg}KZ?!TjGyO_R$HxF}+d;dI%*W3kQQLeL1z*pgkEcNe@pS^Ti
zP(p5`EblTu^l#?lq^ReUBm%B$(R`2cmO9MshEHxd%lakkw&YMprNbVD;WTgddJ4H8
zSUx|qW%{Q47g+v_NOo^7%Ed?88Uekk$o#Lx;iF(RiI!OL^Dofjaj$A_N&hOVhfF?P
zKqnH339#OqqX5h`3RJ4U?Tp9U%g;8A;}12WG`tR^)}6i}138x;Bfb~{wYfkkFeKgo
zojbn1S~AnV{m(PXOq{^q|HHZ&6~0%;L7=YS=<RgMtp1y5SI_PHiqQU>o#Q>^xiJ5k
zQ`?^X&MxN!s+8Isb?LQ3z#0RXZ%~zF2ZWw&r(wv5<=ns@<&o|VmXeW~(tr_~qMSyP
zxcIZuz?2#s<9$&N)||??75&WA<Jypa<j_;P!o|3Os`!wx@ZG*2iZ9yBo#=T<B+i?#
zxmO)5?h`A(%0zbyxLewnl%`(Qnpqg>ui5_v8IRx~oZ9pGIN_w^Hxz-w^vDfah#?!r
z$r0m+lnva(H7Bs+tZ^kJBSx8rnq^@__kag(<i3aszgxz>EX!z~C9so~WNiAJxqj>F
zv5$v^GiI`KVR{Al4B0e%c9?{ud>39-Vt-H-dsCf!GiDO7&%><BtqTo2O<tn7C|na=
z?bwybgbaVH`yZCk-v=08e2qaOcj8`~25xs<&DrQN9AI$Z%euQf=C~>)<}eIYU3!UB
zIa3xgRS9A`i@JId#E$uC(S}y=I8YX%SVA-<v>j<OlH3E}-^I8mVYY|&&i?e_qsTYS
zjLt228Zy8tz|xQ$AT>!M(9=KH+m*HtH^;RQL<Rq9l&&eTb|x+_*+1udj5mW97HvP7
zu4Vu#v}%25H`_9hVB<YOfoNiC{{thULn<;f*6wIFcZHRuA=p;4{iQ8^m%V_@RXVCn
z0>K>&p3Jk?6RGY`Ek2FDHnj^aK-}AZnh@%BH;156<!WCFL%)8!C&r;Z@};n1S5$j<
zDdM;xxHs@}vdPARl*Pr_{!J0A#N!_hL0}423<SY>%c3~k({rE|b$JfoT;$iRqH`+0
zrKZ@dfY}Ya4@UaRu&vF{Bd%z`ht)ExFX~s$e{!fiEGDVyD=q4@?aTtDwa^M<nC<%%
zE4)+P5hQY+hav`A$f$R>JjM6&st>KjxZzR!*Z+AE^MJpSz*ovFSeafVfWG$1T~dIa
zt&pGZO$M?88G?qk?!73cUIgkLZ(`JY7!*5`ho2zo)zAj=lr_cvF6QD|#qXJtze+ky
zQ}US+?2KFB%w|oQ2PaNWn++q~&7$18m<9Su_W80jF7RK6VP0>l*GMjC!8o_yGheQ2
zrs{Y@3Zw;`rk|F9ng=RQ_NZ2>9j0Jd_u|~qB-xX_^9c)f!fH`{6+i9VC4KL)jNn~W
zSz$)qkT8|{G5NB9S|jNB*kv(J79;S}9I=Gb$xmMKWRE2%-c*#TI&KCd^9LktnpVcv
z)%qy*sCU47JOpl;E&xBD&1(r%P<$>N0-w!UxllthRgNI|yCry76v72@JN~s_+3Stt
z=GuNh_{IsXsHSgkUX|s5wZ#GRqMz47K|ZIK#-G1C13u#j!%YlCKv30*?lyANE%b0O
z!A}3th1+c=z9gDtSX@-<Zl{{y-IOTtWa#{b=5XQrrch6Ozs$I%=NwsInbL)bGMauc
z(!Wr7w&n%4oGfM`_XL7VfHT{RPj`y2Z?v^?u?sZL@4pcW3fuG5afxgJ@>P2mp`4UG
zX7k_FDM$hx!YPo=bqUx)LvENEEZMu7oO?T^z042Om#&@t{Fo!D1-rlh!>UprsCX;E
z;|THb*fmNQcs_GkCs0?xG@_1KY%rm0-JEmg+%_c!t;U>|#;g#2T8lzs%Y-qpHq)>!
zV{{_>$9HfRE-nk2d0Et#u@wuo=kzD1Z9nu}DPsZoJmLhTn3TwVZGfhBFRygB5^@=q
z=hRH@&=RY_>=BIxn{yr%bP3&ywwtY8244z*s+GLv`~1Hyl)`&ux9(dy{ibmEEA7K#
zm)wq<0vZk2kD_eHdBqOq)N@+;D2j|a#RuAf)kVD${_Wy&Sl});u*z=fs~uI7_<?q1
zU4*Zc5-aKkChRaZVRb3AEPqaymad>1F=fjr!kT<&HFW$yea6UH&DU~|-8%pD5g|Z9
zZ~NYpzeiW_2fa;Die2(?*5KKX;LUjrUSV&r)W1l$5ti@nr`R`1w}|F<4?#%qo;%6s
zooX4O2hCt6&(Jf9%SkU<k>hq(NK=G5IFi);CW-tQrWR~d#_Q?BI4a}$J|~OrDEP1^
z!M+G(qemcmZY$*>L&qjNMcFF#YfZ0wYf4C055#)0JCp9u%Q=Mh!@NlKXD{}@89mvP
zqqW}aAiJRfJj-~5sM#zd?&xZyIGhPa;VgH0;a?MBFo1q#jHuyKe*49t)Ohn_7yYyj
z?<ZSw{`0JhZyS%j85_C5z9H`)FXDT%NmrP7Grv!FE*^?~c~eO}heHj~=)HTYtC2+d
zWK>?bDrtyTeJ+~Um3RL4NF-2&6OA0oDc5yCy^Vjl$?&XKq9Zm9TZ3DKWWX}8^8z|*
ziM0jHC)1z4;ia`PmP=tR$<U*xqnPF9r92L3xVZlt%T6JGz(ilI|7+gBarQ%E3t)}K
z`x@1C)%7ndR@!@7vHxohV2jNNQFcd_F7UT30Pt^Ry(lBFQdKKdr1Jo1I6@~VC9lu!
zc*(V;cEHTg%ztk1Ywh$Ybe%ILF;2t+x>ESl&1(9pa2_oYn+tH|J1zhR;Ft}EPO=Wi
z$f<uqUp9!<6ndr%{OVX!BZN!NSkQ?tg`Xk%Clly#7n|@as+b_dG&d#hN1YWmCJ5Su
zdI}xy6|`|=y5*FFMn5m{y8Z%LEL5A`-AWZpeHs;XiF$JIw01Uuf+P|Mwx}7pqq8{O
zu0-y1o*Wo4sYe;Jl*K7FgRN(k0laa36o<Pu!o?iC=W@03ALie=a@-K$H}kJ<W=*oT
zP7+&Y@(O1`A{0Zxj>od@jhj^pnSK?Ks<h&|Q2pvKLrrv51$ephTUYJLXTo~8Vm^9g
zuW#66ty%z1RIKr<`__98eYLp9zdFx>DWF*uGuZNyvSi5oM4F1$3`$}Em;?Fx3X|E<
zStgCT@=xJa4o~suDhaR!7-b3_34w2|P|eKTd~ro=@G9B06YV**iSbwg#+8fNs)sDu
zFM*$8KD8Hv)-MNDH~=O1(-T-BhfYkMrc&LmQlP<j-7!^_@M`#zUo^;Z9T&gS_cu7N
z_a<Y)qbPQhhMQ!nRxl=0aW%R90t<+=f&uXp9^UEiZxA=~Z#%BCz)7>(W4I-F)XW{x
z^N9>%V+?ezGa=yIg{662m~hml>6-OZNe|t${_777%pPMJFL8CRgj2A1KW;9jm?t9m
zehve0TZ4K`by}kH0#g|!d!QhT%zL@}-Dd^7|Mouon@^Bd1-VtE_AX+)axnrqZ(fW)
za6Q{tTDWNWof|;Rja>@XIdbg&QqbM><!6L2(6s8}&s{N%$HNzdepc<r&tt<+q6_HE
z^onnJNCBnjYX_3ow3LeWzcEuYH{jF==w1%kX^vj<J$y|ppIEqQT0vB)YfF0|4js=Y
zL$FwXbKo?V^+LUHoOR9wUhVI75dFv=lHnu3bS|sjEbO@y!hgNzb};ZUAj<%L>%el?
z%u+wYaC)3ik_GV3@DoOJ=8{0aavsuf@^WtxE&GFX3Y9w#4uO1jbofQXNt$Emx0AT8
zdo6E1cR+7e6k0@{t{p^{tyPHwY)Qp6t+MH9_-V|q(THT%u^(8@=|WAn{#)W#j+3t^
zN&P30xfw4S^naoVyauN(E7E!s@@d+3reguqSE!=;trIOH7uB?o&#C{<3y<C@@;+C9
zj|Aos|MME)L_QSDAexT<lToZ41+YB6?Zf?pGhOe{A+}qBK&Mh)zsNO6O9gGJnF<1S
zr{dJhbXXof2vsR|C)D%TJ`w%4q(jK@=)^-$Z}hoBz=*bdO)#xwaqLdLy&Nlqy$QhG
znQAkA&e*L*M)YvoUjUHS7o4NMw*e#`a*PxVPI^7Nc+|Ac^qWG)8wfaU<&?cX*A7+x
z=Cs>;s^$`7zL{j)DHmlwRCKRQ{=3A>?PLp^_Zt<}?DMm>pUTUj>%5)tTuE7-n?+SS
z^$lXC*F=fO9AzUK2=cv`oeIC8%lS`THmc>f<^ihD-xukt?6Zt@U)!z+%$T^Q2)M!?
zsEQ!`b=sH$L>ooVH$Xj-c;173lW&h<vBDH1P{f81p%xCnfC9+%8GW)b3ZP_<bVV`j
z9urYxAGcG@`)l5;u*Towlt2X114drl1GwF*ZVNXHqp$f2mS>W=jFB}kytJtKfXzIu
znU`lamA6mIfQ{Sp*|S6|WJ6|2V2`+GK)^-UR_Gz1AzhpTWgg98@RWofyn;AwLywy_
zt9;_s^cEEB^Aq>hf4s-|4XIZIHbwU8AGL~Vfr@k#HO@3?4BSql9Y!}=!TzA$ARYw1
zN#cbmbk0lJpFF;mAa}5WCy?7h@YRl*u{wF9|5WmSwzqhpf1Caot!FKXm4Wb=K4l=s
zr`=#?%!xlUKjYl=&D0m!<BDet-T3lR0XcVJ3PT|gHXEr@j6jP$CYR@-`MzL3=`>BH
zTN~(KdU-2fkC-bF<QJv$*ui@_i%SLe{m!S0`ix|pO`#IM&7YVyUikh+X9F8y$&|4>
zzs<#%`dt_?q5PW=4N$d+Dt+I=?c(czI8DUQ6OOg+WGwBapBnXjtMxb1_Mhj6v(!(2
z!#U3{j$u-HL|j|N3_8%$aHH(wAHdzoa_XE}?%{s4l&mO88BT_Rk!UjC<0-Wo;b!x=
z<@M;W_4@jD-)#mj2@9aiRR`Bz*ZPOb7`W!ibGUv1-4m23`^!7w94d9V8a#dP1X6FX
zl-jt(JQ(=}ymn(#faL5O{Bqhb*1nK((g55^#OEAX#E$eK!-Wa@p73z_YZns5|6xg0
z6bBVc8CvkSkinlSoCTCF6Do{N)`YGPKt+?(YdGmn`hIq4lh_9VJmn|;(p6b!rC^#C
z_ZI7T6eHJ?edc3yEtv5?7}Ih0SI-CFe&XRy8H+8I3J3;HWZcF`_w5D8{L^u|?O1BA
zpq&X=T+LqS@gPuiyn{0~2hysR4cd|Ur3ec9_%+@{-0|r4hi*I2Fg6esUKVxqG^EZM
z&^B0TLfB@!gRk*9_6FX1t-yj8Y!vVDo0j^=Ygbzbr8$8pXi|s)ryT&Mv~;T9g%C`p
zUJ?7(J`Uh-6}I-t$va+(odzc6-&OoicgDx@@BxC*jB=j6y!kWHGf2Sx*%|LtD`_ob
zMNz+K(Q$9lJ`7vK2$ec!Cds(+QbIo}tGMSu)yRd^{&}E*e%{5N3T9<yNG#m#koa}G
z$u5Q&H!BFx5fvT~z47~cFiuzJ6`(uEWH^Rynksi7BEi<)Ye}z>^(5A)q1!vdTnS>H
zEp7ifXaQ@fsyH_f;z|Nhv{~B+j`-N(mlOtkTqv7UU_MwFt5FsAXLHp-G;c~@sN$N~
z{994wYz0_;QenaKS~TDORu^SWp`QBs$UZmYn}4?YZTLe?8^A7U=7LFV2J97&p{MQf
zT28BIZci9)hRa@sJEd41RqLuH*GS$^z1H4^<;_d{bhdFp?+3L9NWJ<%k564yy&S@I
zR1;IWG{jiT_#h`rnFx;bQtjz%H~%DDjUTH=`g~t(RIcsV&T*<YE~x@p0{znxXQ<NS
zwx{!9l8PQ7OwT5bRkk)yAKtreTrV_kQsU-RJo@6s>Ci71PsT~e;MOKi{_QGF4(4HK
zX)ivdtk>FOC)U^L8+(T3DQbi|?%`rG`S<C$cMR@q0fam%V6PDcELt8n$!s1m+<E0c
z37pDjb!A(+)1n_GMAutQrb}^y6xum<@c`lFdj){=6ageN5ilyg1-r4`R{+ES(oGvB
zU_{ByrK(eFYz#2U?I4a=zt|#i%aoB3&Jk+y&dXO$a9FhWjO19c*Di#8Z~K7Cbe*`Y
zpOpzLO*g3Vm-_(xMBK)1U~wCSHeeoWcn{Z<0Zb;iK`{Qd!m4rNdi}osvRF_E6}=W$
zCkZYg+z2YdS-YqfbSiu$6Ux-7<Ma>}Nnd!s+ZOvDVL2ubb^Tx`aT(q{4eo6sTI8x7
z{^xe5JqcL#EQ-q=6JveMBU`q@pTaG5Q<74J$eh3S0~t+Al*Sfu*iw=^7_p3v(cA+E
z{qq^`jil4rWoc{F6`2g_#aszsH78$~zxe^un=19LsGNtw@4m^DXxN3+fy6ZdjNVRc
z9<|18SvgzUdeKZj;Hv@kgs%zZou=;{OtLDXoA68ZuU9*MLERUwjr@J%yAEYqn7u{-
zgt0klOCG2r3jSVBJxZnsbV`@pbm1HmYhpYLi-d<7nNM)~tFJrDp4BWH55VY^mRm+i
z)FpJjg-imL7XCqD^3@Vo$zDL?S*JwuZYNpU-?LBBX&In0*$bbgoCl0}bIfZ^6O`n3
zj9q+xDcv|~zi4a{LS=f(_^xWcQ{NQ{!maIEoe3oVc${S?##TNcEz|xY*R%^wDyh-o
z%bMFAC%x0QbS}2J_)U0VU3=<0|7oj)>GWja7KQpvCB^B#5k$`L&5CN4ey5=bE6{D|
zz$*5wbLla+rK}UD{af&AWEZTgkEAF=UJeKk`h)xIiUI+tRQObXoeymKqtvcHLgU2!
zMMCp&Pb<H<RkhE5pK;q$*4AUlDAkmq*6*uiWA6HWr>!p&M?mIwpbHtR5)=DOta$BY
z?nBJ71elxrc!<sz0~?iIKRfP0e3}h!?pFW7mN%HNWKwHrLcR+N=7ROWN0>P`dPpE9
z+xe;jm=A#2U~#jQ-P|TZQu<a1TVk&qNhEVKYDA|RjmVT2J9K~o%CwGOa0zG~AA(gD
zN+)CNB+=h}ihYpTNR?H>`XSr*s;WN!m(s(w@nUGcikj#tU>;_&2z%UFw{%rZYPVV1
zhnoFxy1X!)lI{6uOFJ@>@brRAa8G&F0#<34m}JOGaG>_8AasJD%YnzoR4|yI_CO0n
zl#hGUlXxJX=F0PqFUcdA3GxFL^Ql;&$0?SnY_SkdQUDd|JJ0tqn{P4lM{DDFz>Bfd
z?9L99ym&dFUht<5DChaykL*@7rL_@<@iZd|(so!9UsL}~ev6+myke9TBT*mM+3f28
zW{a;^P(Tjh@rvV9d;ZfWm9VI#Rx-taW(&Zr((KDPP&`VQn5HPQ+aL>N#02lew?Kn2
z!B5V36M(;@z2`hbeI3mX+={(nqvYD{kl48iy(r(Byp&afVOP+-;;TwVqT6~l3PnpH
z{+-)V1yjr#6`V+wr`cxnkGQw-@1pT_@{IlL8n^Jr-smh1ggVbe?p#v(er~#@#_RKo
z4%U8a_DB=qi&ebJ6R_MfpYKx=(t50pQzNt}i%7M)he0NaIk)7IB~<MBQidWB1D~5>
z2={mAuMb?8t&6e`vr!-|E|v-ya}bk&w7ewVud)GANADQ_RtwI!S~GI=h&IB0!c<?G
z@Mh{DTC-}8jmB>2v=rZM_9SFO(q;!R38Gsq`;O0_yx0tFxoj4b0yMp!0j*cjQwj{l
z<6)pUMJO(u9Sf?_b=5ssF6|i+^cz`;dK|TcZa7I<IXVVL+2Kmr`+ko-WIHV*T(ME0
zQ4l*g->3yl%A8t1EiAukD*_N)mk!?f2RvrZCs(CFLUC$*&Du)=>@{ImpHdD2QlNbM
z18xZ#wWQ)MztVpNn$?dBlApZ0HiZSTEI)AlJ>#3<z19QAiJ>xO@p;qv++-*)16AZ9
z=K!}6+IVHN;~xqs6Lv+#+kkn$lkdvE#W1%csebd1QQ-aBc|Y@RECW#iv=r9%%pNa{
zr9VyYm~<@8x9k99!>nG=9fxyoIw{<0tq#2vz?5Q_Hb0yedt;xz-|+?fyv-~}9#?aQ
z)?+Ka+m#nfR){b|>>}N^96$9QDv;e&DIE?yx@#d}S#(?WDhJF2jd8F7@R$K9%VTt6
zG8cw5Qwl=Q+@<5qp#63cop<#{_0_%lh--n4cRqd|NfG4zD~c18A}P`5KHvhWKYJpk
z$;hlunr#a!h^6myYk~Ve_&xoOA6A#3S&!I|wy#|PhPaJ1fHJq}5bOOV9bwv=K!2uS
zp;{a<=Aml0=|0ect?T%q)8M}Si|z3YPlxk+(d?dFk)0A;ZqvP%M%O<SU^z|V7Yo57
z0KL#{;zhEgjb#8@7bXR*=!~>p0{mR<6R5Qn8*zcObupM;zzkv&pvLE@gQb^3_nAt~
ziB02M8?06ubzYd7a!u5SBfIQBPI`84xEgm0%VC~<F9T|3Z$L0>sX3t}D04jsa3dI+
zyi7gLi_spfNh+eZ6uYVH>y1+IKj%LIUi#x$AKJDT2{FVZiFvn{fESFFqTFy8xLOZr
zvehVi$e$f3uhO?_ct{57^wjOVJwS)RLN*l$pl$b+*z4a_+y}aIB%s6#se>Dm7pmCe
zKPGfPpA)oGj2%folNf$niXb-dwBd~p%2YVrPWzR3o~r}|0xeGH7Y!hrrF_y9-o%#Q
z@d`_c7GvQP)I6zx)(IsA0>FI`0z;O=kc|uIVS#SpiCW4J68K+XmhnqZHk$jrzW0+>
z1jh_hw1)TUmd5||AwRi9&Yl-Iaw#dgq)|E?N?7bxpy=?ra?A2~{K#b}ll#4U+#coL
zGQvR77Tn>%qb3WboChT8-?Zn@ocfRY`^p(#;sThqt~^gmlH0Vk_S`@Ta>N=1naQs$
z{TKh?&L*)|$PJOpa+$B-;gdK#wg7Rwu?N25lQl^v%C3l}?k1s+!({STLbJ1;AEALf
zcjNeObG76<#`1)y?Ly#5=4mDTHL~_?wrBjL2oAJEtZRz=0J?9YGejZq(b?J&+rvKa
zVYJSym)wn0^k#z6fe{!mTgL_ekh?N^vk~wTPR$f-hg0R-Rkz9Xj&VTsdh~7F@3`b$
z37xWmOv`v&aG{2ju_b-bvTs50AdkmNM}*Hm$jry1WA-nJ?t;tH=BH`0n>R3&V>KbK
zLV%q2GQhq6L@5zFl&sRp_NAC$v3%IJytvOwNry;8zoMq*`t#A0yMjq>Z^QPCi$2C6
zfdJ|`j<3JatP!Z2z<HpY>0CULbI#z~LTr%NuQhP9&L&-1getYvcgk48TxmUfJ=u&s
zYX|_O?z=bDKY>epO;^XK@b3rt)^#<e=bg;ph9Cm}sb@}2+}r5JI`GOU=eTpK>kZ$#
zo2rWqhu-&(Q$7AXDF&Wgq-J0u615%lsy33H9zF@`7P>m!j3s|fu-fqP?D;)=+?U<Q
z<zrF8pYg9Af6K+6Qc+k$*;yy@5v#1y$3^k%yJ1Ex;v957U>Z-K-2fp+z<R^#zf~W0
zlaw^AlrsDTP^u_aU;O?ph#9qN{!_L2;2CpiWSdb%DQTOBxuqalGbdSk`9CZJ;FF)O
z@hUJc?(0pqg-gK)Wjha<npAb&NY{WTTN-S|PJrum#_*`LkhE0XpVxuSqtY!6CeBIz
zJ1CgG>Wnk}E8bq#vlE#=>2`M(1VIXJAuy7hvbT>P=jlo5L%mAu1@e`cbalmtoSU)6
zy)*>26?VQsg|Mf1b2GCW-WpFybFS*83--&M)tE|2SCEgiK3v+%pRSyVu>(-8Ox!k|
zE5U=on-iJ#$<04z;NAx9-nr+l=eW6pq3iDy&kAb`@`*hvU@t{7EX)ha%?&51!Ci>>
zdp%#2vE^2$1LBR$_%q{3%}bMUN$NSXN!<qa*i6^C%ZDC3Vj#-(jaGis0`7#p_361N
z1isxA)G8Wv*n7WVe)GAUx_|bKk0IzDKLHg;DxLuDO$3ro=4~FKGl494vX~Fxp-8B5
z&Fagr;qSk^S*vOy%lHD_G6Be`(qm8ME#Qk?A&!>xn9n5m(l{Z4wy7b8D$BJMlKB)=
zHN`U&8%I{-^6uSO-aKM#KXj1w`+Uua2sRj&4sVft*T^XT&CPz;Eox!}EMNYz$cwMY
zc_8MapH;Q3NWE|9O&(u>qVRMhi+V2W$TD4UT>c(xtS#S`?L~J5Ee$IIy`9^UTg!Sb
z14y8|c@LlQzgVGo;QF>dd$`sst;UteGXgjYk#@N-yL(Sk&u05iir(WnD58y)nP?lN
zE2?XjYUvsB0K;!No4OSnfAD1XSGwPEHznd%V&97TC*Fz$4@*~cpQa3Lay$0rM#Kc`
zquF#<e#gWA`jmEk@%QMkEPFV&@AHZN*Zpta`fl3R_`8MMW8%w#*I?@KljR79G|stX
zbtdwRwC%iu3%ala-z+Aaa+*z8X^ysjVyj!Ll$%0<<@{-=lKbS#F|E%<7*Z59%dx~A
zwhm^lN(rJbb<I7Qx%X|T@1{&_2e+D6!OZ-LL9O8kgB7I!%D%_TLg~oh$o5;K6Z-8^
z<Q8nC<bX$jJt6e|?Ku8-pHC`syK6=OJzFtnonU%aYggjiD?ugwhkXaTPqjb2djPq|
z6s`kWQc<3ZHEJ_g^<}8Mc~_l<9^tNg>`6*C5Nz(I3AgSq!|Q<rX|R=n=ZDr_#>`R7
zbxx2s$?ch(@1Caq&E6?pO!bV?KQ4fVQ{ft3@jh2yjiEi{JgBz&Yvm8P_EpVa%3Fo2
z2&+i(I?k^uaZDyq0k+a@|HF!XwoCQjy;|7UpcME;xr?d^%SK^yda8S!zL6NnsT6u_
zcc$6^4Bap8GTqMHLG8Gr>q?%Ic0=nVoFu8vp-_$;6-zMSEoIE_;;#j!{;jm+2&eO@
zZy}&XAbdY9IHursKufrZYJuVt@K?J5J9(U3$=}eoAI#1NU;Kvcxqh?yTJeq2Nm*zj
ztDDl(vi`*^(GfbU1C4hZjGEbq6wrxot)x2cgFD#Xc1h?TLxN%{XRsNu{e|mA!zRN<
zhqTDfQQ|j?!oODs2DUm=Z=Om#a83JeaR!x33rIYrnUt_%V8L}6E3Zsi9w6J`3mB?u
zyGj&&(h4c8l_yjYJt52;EYeI*BP<{0oIihgMNqAkw5CBHGy00bI`hDcoQAy)syx`;
z_1?8?Waaxm4RtvgTCi14)=tI}Zn-6A-}@w+_4$W)WpL-ZvAb80J|VtV|IhDDiyo#%
zHNqq)!kpPL6oZqxVq7x<`@U7hkAj14%wEEpT|sx^mVV(I<#N>T<t9uploER~t-s6S
zub8|Bfj*tDXbLCTrM4sDwr6amaO0I?e*e}-4PNC{hK6NxpPki4u<G3Ngo-5jOJO0S
z7nOZGnX;JnVu3rmS+2lKTgFChzMRtF3w8s>ZxAT)z5s(%)th5uN^2k4|JEnSz$1<A
zuZM&VOsTX(Pu?cMc0nWHbzSYB7aYdjS!*Q(KdTHHO{TQf%SlA_xL3pgPC!>~B$3q}
zo&2dI?Z`;m)s{}ZkMitmk5_@q+8sErj?mb#R!l+K>R))!SRT6)Gu<c!o|Lb!h=4uC
z$fokSZ432kI_%uVha&PY_Pgk~PI-K>;6@{){Dg*k4?-3;Qf3#m6q4^^FP=d2s#dm-
z75|Sfo$WP>p`^g}a?~?~m`*VJIZK*?`nnNc&^F==ABo5!1in!ADoXgt6GD5RtD5lR
zOKY$<i$+UrF>)N)x>#XA^yb@sc*K$=&E@FpwF4Ce-n8Z9%vH?ll*UJqopWF{aCwD!
zhT^k(7Qxs270e^Y?zyC<JI7AL&5Cfos#)b~0=vP50Uv*6aisc3A^(uyW5&E6#(4Rp
z_Y_jA$n*FyS(OWC{v6Ct1m}WPTquLO-4Omvm(7O)<VE(8kA~)@EBgBGzDNzpj9DqI
z@@Ao&z7RCCoarw7HA-cxm#$d2#(A^8R1iVVf7H|r=u=uvEHwmm;jLb5W62z5f-*B+
zqDUeruJR<EFz=;9l==w=ZWs1}9$sl*(ysvVDz<<sF?3|^mNu@vAzo-bQbuC3sUvn(
zBq8zl7u}M{>S9YH=dyfCvlYI_OYD4Y-xL<2SXyz9<lcC^Yi9hg#BE>Tx8+$v-LcSf
zZpHLh2T@~wjOW?cbT>)tr%CufEanaAplYIHg`3Rl<;O*11x9gvSAUTYR1)b9Mj6hY
zhXF8pgPErx9dLio{KvWIe)_f+`I{1ICU$9N^@<80Z0uPgY^;ESQO;x$K0b{RGO$)q
zC*y~90I>AqPT2*UMCx&p8L{tkG(^UO(xb1kYWb0A)Y2F7L1D%|;gR?LoAa3tMh830
zCUG+#^2~7m>F}z8mx|XzLXYIb6dZ*!fHbeVn^O2k2Zqp391mAoi8YkB#cwW4Dd#+b
zS@Q;Ch!AKnKqScPM0js!da5ezc%5khNfliZ4G*~5vJSL^?>O3pg7CvDh=5$7pY=<b
zZWC8Lq^(HEcJ-2cMZs^R`%RzDHtq7xX9|O-{4lzNMB}596fe^m|3#JRxWhFBMbe_$
znSWA4@-kiion9H6hp%^@GFGEoiSV!27po#y_!ZDdbC)qcHmkDVu-XE9mWWqdPbGCW
z-?g7(9KMcK2;l*6Xv|mW+5fNv5H<z=93;ms)+@*M@WU@^(8*$CJ>aFIhGY8f%1S=%
zLmY5DTh7;t5~CP2r1-7dURe4dU*tT52Dhz@d|#-bm-~xoem~|W-x>Du^e8$pqi2&w
z2;M7Qh9d}Zh5k@A2W@>tTZi3cYUk%`XJrUT@74jY_%SBk4ZV&mngRxe0gF$em-cSs
z%ofne95|i!`hj$t=%WWt1N<D&TMdJb<h&Ejhq$7=4Re#@vYe;CvAR5nu6|NX<r{ci
z02=hYpuB}lx)$0wz_MJfY}X1kmm7HXa>9|G<A`PlJ^gRua(QP|+9P`$`#OLE&S1L>
z3n8Y4|7H<8ws$#<gFgDa48E=axM&v069q~C=^nv+&Y^RUqxS&GYHEaH?eKw{%|8f0
zoap8h2L)-7LRg>gXiQ$mYF@`Z!B=tH+*6}kWcm3pU)pIT;dy?YTNp$qOia!o`x?Gb
zgw}pb1a}*I@EFBz(kO~L+n0Y&Zs&4dsjwPK5o9+bl#fOF7ktf0tv`9clB)zhrEB21
z>=oQ%W}3m4U>8U^A3XKNEBtGw*ZlF<l7hz=PQll^S^S@kPz^kV#hUbNHqwA_mRX_g
ztsQ{A|9Gw6JCT9+n@yn$S#J-x@pXkNCJA&Gd-LZPZ02%{!8i$orog5-d+H3{9c}ZC
zPCx};gxYej#qz;6jq8q_fwtIZj^`|_*(%Q-s}jSUYPB&DLo(ny#dd~wm`#X7Q2y<I
zSW91j;I*$@mS>rS0g@wej$F=Qg6q|SdlB}{@)El3d<E4Eb4Q)gnsfMg@qGn;oBB!<
zy!5plj$pODDsuh;Da5F)`;neEB+pG7Kqba<d6p=qYL>AFk}*1uLyztz&@JsuZ6(y1
z>l_aZR?E7<)n;B))*x3Hv_+VT!3bEP1dY}T+KvqR{<Wp3e&`ted9O&xKYiusW-qvy
z>BVSqj6*qQFC#NtbN(nU`)=H+`Pv1Al2ojq6#qVpF<&VK1vEXmiez{M4(CtJ95D~n
zJHS2AWRx`J^9TsPo4I&sSX%}w$0Dm<izkAdQ~LGjAa&GG7yr%K0*Mz5NZ!DH_zxre
zHT{pYSy#m(nT@vOwL4k@L8qA7)q9NR?CEOx&d#*)TC)CVM5O}pNW7nA=Av2Q*7mjh
z@J=RHaW3VLF^QCPfX^_645!J<#b^b5(oHVhC+akRH*{4($9TPlx(k#%F2(aaEq&tB
z@(yuR&O{mMv+|jfb}#b>exiGl|CFHBLuL0v_TOVN3`J0pQ<0oK<Q));kzX%c1QN(A
zC{-_ON~HPSHs)rC?28^9T?Qz~8spSuq3R!+|Ea^XD0A=3qKuzUK~JVY;k-9wH)IUx
zaVhSPQ-AK_rVSoR*hY?LAKr{ig||i)AxFslrVtUH|G+}+*Tm5V_u?fl(f9Cf8IlVr
zNREme!stWC=^<S77>0Z^k@7z*AdG>y(5|QgamJed*o&9I<rfe)m|9HN6&retrHH2J
zwwSo_jKthkbd4025!Fq6AQfpZDgemHguahT5v21B6hVK_ZtT5P*$C|4a_Tk#|1wuL
zhRF8%svdlH9N6~X7#TsH^Yu_sO<w(a^!d}j9IgK`4*B0ajEn7r7vqVX;oNuc_JdWl
z;4XiBsI1W&RV|GrrGanqZeT@bQyS-aC0Mc@N5jL$tV&ENjP~~k)CJa^4zl0-T~0ke
zEf9{u(fH?)02y>4|LI8ezT<%2Xr#1KNt)iw*|~B3e@RwJKDm_WmZW6N5x|3UCxIYe
z-bGso3llq=<TX_K`c1~<_=Kh>kOTXeC&Gge<0p`|Vqi-42(L@d(=Eo{MupYhwGCb2
zC%Z&hGds)Q!=SBRR8odk;~I;9s{imH>R5y0Md&tbN4;8^Qjn9)7IM-{V0+(v-@YKo
zaO>WImb^$UH}QBX;AX97O0S(@tv=}2Y}7bW%WOHN0$vguFw@Nn4j~qK+wl>i4S4c6
zz$&;IHwmV74V&Jku^1-Y)l%whj~Kzmk|CrQ!vGm~Y_2h{Sqn$^blB_mq;%0YZW^%h
zHf;0<Jiyw^<1=cM;G37smlWOeMy;z75vu$q4N`1n9K76hH_j<nr^hMX{elO%_IdYg
zcQN2BO^dGnsmMq^->!lecK`XAE{g2~9O=po&m1b2AvI~Eau5k??2p4RfJ-dr<BL6e
zt>WukijSDT)P=rEy<AcCoM8Re+39y-*nNsvAR$I>PoEX+we>Aq10Ta{{8Y$tKm{w)
znjl~vK<T<1IuWa{X+c*@B+Me9ZLr7L4n|S{TQN`VrRk^lRw+8r2rl-f@ec?8&Qxv3
zb-Q#!qp{KtX1S0z9GKe@7t$ps;NZcZh8|_I2Ux|Y-+hhEj*9%-ge^8#NW)DiYX5nz
zXY;VwZBJL*crxWs>4x&CA=h87Z08?>plwNp?0;A;zl>wF0T$rO+C4f5Pj;2P5jg_h
zQ)Oa_;h-8o<Wpcv+Rq(j%kp2A14NtJVPq0Pn-Q>Tq8`L6C77%n*`QBaHiWE|U>Q3c
zeGKMTh>RC2ebOoSLjPARuq)7|?$_`6z{8F^2P*@U+FP$X(fFn2Ke_KFt%JIf?@#}P
zZBT=SD)OrJo&5AqoMn!}OChb5Nj+~~TK%7+^NwcwZNs=xRIMttiPdVYnza+EW{s*@
zTkY6;3)P}ls8JMAd(_^vHlb?I+Iv$mLn6QT+xI``kdxy(p8I+3`?@|?nD9h_ZRDi*
z&KqOzkr1ep3rL5*e_e??2QRS6R_u&7<6#$)v!bEJn@7Z+wUn0s`J0z*?kzV{Uf<wl
z;W-T%K5jlxzv~HWsV+#N@|OwqE>dp2=dZs=@F!c^CmB@4$}&3E?DMAVlMyI;800>!
z7kpYk_?afFoKQ{dbGMKX<X#6EZ{s0P5ykWMUbBdd_pYo8<<tq!Z0+XX%FFFrS=)=c
zrRiBO7g$ivmoitXfm=%Zqb!S`3G*Cie2pb){CJlc`yJQdVmD@p<^*G)C6i*QJiwHo
zn3?sl@R>9@tU*Hw(c}<@EolLKuCPXL8|wzWq}>M6C?(`?)avEqWY;J*RU=$pI1Q{@
zu?WwD8mOz5D6K5;p$2SK4B;>?d42zuNXpIIhVgDbj!^MVB;w&hcwaq21DO7QDV2Hi
zOXG5&w4?q!Kas`{OYjAwt4(q@0&+aTh>y}Z8mP8b!E!f69XlQ~kEc}#w%8#~k&q)x
zUFKf8O&cXR5d0boh_K(z#_|WPe+8oBz^g7u!ij%NSDF~(sk`vvq;^be^pU5Wm%ORv
z&)I>_kIHgNTtn;hJVV`Qd#cM%zW5TwHce)FqGL|7D!x9eAr2?!TlXcrDtVHy(5uuQ
zlmxF5yPS2)@Va!izkTlrFW;}YvYba24>*QDt(lcsw%&D+R<68W3f_>r(jzNz8WE|n
z#t~`)xp8Kp+rmfkbcQ`QNtmneUMpfC%B36%3{L+p69#_Ksf!z}sDo7^vG)>t!89os
z?TI*Xu~4d5cSqMvp4)xJBBuu-m?C7+zCu2f=dT$JvVxAF>m(H}^|dN^61MiBh9cZk
zWkY}DQ?Lp)IPSb(Q~ccI2jD?xmD6PBf3<dS_mt@<A;>jvMSaqxHgv*dDFK=#tvL{^
zCX#ABcV_rSd9B00KGNh&Ea!}8Qfx&+i6WWT#&_6&>E020>)E2f3t1_;P{&U<<hs>E
zpSAN;71g+HeD938$;yCqsV~clyVKl;es_jI0b5r=5!f>1O2^97VCIKxd00}GFR7}m
z!nfS(cWj-HG;iYz6GYianhS9wlk^Oy;jCv$9{{-pDP>9z$d3Jj5y11YW@eW<J|@Y1
zDBL(vcNRdh?*K@Pq^X;`CUc88YfzfaAk-eumIjzN4xToJ_*IcnZ-sRy9}}$CyYBEq
zynaHE>0hMy@s*(Pfj0P2^DcjLxf3wFJ0XW%4XX$?6+XST0B{a?mF*mDur??-m&w{`
zJ_1_~rNZ8sPFfcbAh{R%&9S(T$@5$pQ0QBE*35`&thw})V8psg4qQp^V{Yebmj!Bd
zPZtJ&a2}lChb)1D4?*_;%tO#R-RMB+-sxB^I#Ll=hq#gilHuNR{i;c7-kDFAed|t7
zT08&@mA{ACr>+|^h&};$Y)qrQ&yYDPW0MPgh85k83H}8Z)cfB(#d^?_`1ESC+3vG%
z?!y*}E2F+!Q+OU7d?^5P%*+KhGTcm3R;?><xzK~u<^SPKG?H+s>_=C_WNSfKFHgU~
zFXD_HC`Hf(FG+R&C`tzZv}A|YD3B6HYFY=3jKRnXF0|C8hZN6L=8GI2>#$C{<iq7h
z3uhx8>c01Pv8>6Mq0dT2Y!4f7Jd!03dU_uLDrLe(Ue)sumrs7JH{=tHuFohOQ4twg
zAyn$^0*C9dLvfEi-tSZ>(53ov5vzTY8}TpM9J2us{$J!SuSywNGVKsq8T2{LB^IjV
zE8D(!8<kMIld0bw0zGl4<ktw&wv(&T^FBPWJ?WR$kXB2Xnqk#6W6s=P{aRB0Uf{=s
zLuP~5lTq&vU#uP5ATd+p5?l`F4FBQ1$5;6B!dxXed{37r!n=3>5b!B!vr$hxY=K1X
zTPj{2krI2|$3ESwa8P&mWr5XcyHPkk%~EDY6);hL7RHp|K8)wyUFI0a+W;b)fpW3N
zHQs$Y0ZfqWD&m=6GT#2?zIBAvo$F%;Nq_+A5g4swi93+SRC=(!fLDA!>jvMjuQD?G
z!D6T$w=uz1jT`!1JW*-NvT)-FQ9U9o*T0qKj7$ykH*;2WSG{G)P3P+^9amQG69CAl
z61()NFLp!D<KK?Od*@@d7uuj4dc$+I4oVesn&<TKA05+eKD3jF5hu1t*0RG=2+OK{
z7lk1s>2D{ES5A^0*;&6TiJ{9ib^A?D3UiHy0o)bh_>ZStsa8!@6Y*Rma;CB==KOL^
z5vMo4KBUv#!!a7HOGXP`Sy$c|BwV50fP5;@xO)<!WD28SD2E~2cJ?&g7(W8TFBR}y
z{w9%9MDL;3_Cst5UCtx7YbW$H0{yDkt;Oa)JOIx1=!;8sqlU+ka(2YF0h9eF;9ej{
z<nW-BQR|NheU=0EO)}HbU*Aaaz3Vyor^kpqu!k3dI4pjDsyA~5n_p<xh?VB<e+&&#
zYdLzEIa7HI8H2N)IMVCSkY2k?1LXqWDp<S}g6+tn9)bRrCfXD&rI#|7c;E>w2u!Fp
zin=3FyJ`?ql+Vxnr+WC!vB-I*MGoE|e|vF-(k-0eJ)_jk)cyJW06WJ&3MJ1f8Vr<7
z0=NanK1=3W@qGO3_%?GZMM9qU`AK%kfT$E(Mwtp=Y(q7JbI0bDn^kUrPF#Cw^q2+d
z9HmCoSuuiauh(<sS+00`D^E0tu^Cw-&WrXl>ROT-#R&8X10jVh6MEKLka*r*V`FzZ
z*$`;r$xN9)MrGRph=M^>j4bBlr8AMJPI#RK1p5t3U__N)`^N$*0toJYTR%vA<JRw=
zphp(@<%cI^xj<C@&+f0E99#$Ta5WN8E0#C$#1Miy{|_(w->}gW|7@}5iWcAAE|O|=
zD^zUl`TH<zG&B>fJoli;9=!ei*#`l<>q?Wef;;6wxmC>fLx4iH3-NY_s5_iwN3I)t
zuAK1tVL5LsSq6kJa`B)yBDYi8zu-r=j~L)jXb$TmdZeY<SXCPL{VwS~|M;tjo?s+J
zv897<4S?*br$9NUzXiI{>Od-+3pVASCG++Uxyy$uF0o#H;7zU5rurC_y!({Cud%H;
zEcuXkwQ;O_EjUSaFz;JGI|wdzPLS;1LOS}##BCzqjXnT&dH~NY|NJUXr8~WgW&0a_
zCTGp>q!3Z%2tE+Kl$41fHvoOsaHCs{BssLPK^b%Dk8|y#^xUc(oUl58DMo<ccS-PD
z|3KrTOF74=KBfpz+B9-Xe-5jV&-P2ZXx<Re02HUN`0~XF5)rP;>757|;b<SXeHR*R
z>@$VY>>Z42t;pA_thW(#a+}_y=HAVlzK~*knb^ebPCN4};4jt4f_8%<WwWdHF}s0z
z%HD<3SKt5e-lShV<l@#txc64T0}F%aKUWH*v?Z+STJ+L$v;g_;tWeS)+8zu<Yuy;i
z6ryPS*^FitmQzih)b$sEn?XQ7J@_EI@h~(mA1u^nw?4H|_&W0Iv-?2OV++qjPNrcr
z^Iz?cH<K29eo!p|%mzXFGT+pvYXQa%a-EU~@l?he65pGTH92<!Gq^))(r<PiTHqd-
znZcjKK4;Qf%xL*8u*o?0$wXHN%K>3G=kWeiS*d_YU<bgG8H+J7;%jk%gUdB=)3aY?
ztngrM@<WQ<b#-1L?4#d`K_nVd5)&ZwLmj7;`%Oy8iysPU(D6~&dTgmF8R8@wn0bC_
z3Bf`APrfVETz;Zz3^WKxHctw>{;0}1YjIo`aZ&8Sq}XlnyW>YQ@GKW0NavoZG1eWt
zU9p^nKQ=I?{IX6WB>_p;|Ca(PU>Wf@R1XLXwG6!k7u9`vIb$P*(apk4jz;--s@%M?
zUMeBD@psbT{%aW;^^jvs%)j5gcrkMbc+C9X;P~>iEB6Ea-ChS%HQMh_wOcw=!t;ok
zdjm>|Q`gRSZ0rx-7Izz_OSNK4*zUKubnLyX3RDy)My#!2fmGS8`V$=0ASEBS|1*-E
z=Aj_H*wqU{kfRuWfr~6y`=%Mj>!}E+>F3@_o<Gd^_u5%Tc=i`qkaQ9gEyf~cJcfm8
z3b!2`LN~4Fzg|`l0iUSTQ;BdP_FGmBEy@YzD$cT74U@U2DDXW0TZxpa{JCUFWZSnm
z7uCL(%MT|_n70Msfo@pNK**!TP0Sc)&%up?IagfH2FpZIg{?3d`90=1Af`uUZRr75
zR^-*=s`<Uk=T+OiQ{;+I;v;v{cdAP&F9>OQT<V_O_*Brh*T#njq~1M>NqB`JrGF-5
zrAq1ZL&=5lE~;AW0;P9P^24g1c&O32$~)wc)UjhZainNB%grP~zJJd1JyJI-9T08N
zVn{}Gd0V}$tA-_2V8GXxx-<N@j?trFK*)bsK$%Y4kCF|0;QVW&$VtadOn+}H@J!Xm
zjN1RVM#vLF;7H!~`G-lUa^^Bm3($X6+G%hEXhgeVCmbZZPa#d-db0Hvsd#qJqW?y(
z55+(l|JrQ6C31Vi_X@DVQ)n9@*ML^K!xH7>xv?OT_>4IBfRVe$AIB)u=~043c-agP
z=-c|5#r{McFtNA3L$m@dGeIJy>4wjcX?%c<UHIzA=t3D-w0Xx-X*t3l-pTo9Dx(V1
z8Sf9M)Mm;nUS`|25(9@3CsU`mQ2ABs%5k6x*6rp>fBULxP1B7<Awghsr+7&IVUyD#
zYzDHWP7m0RR>0kbZcP0vr~4N)=xJS?>B>Qj<+G&9nqPyDrLAf6kjAo%1)zA+4MQBm
zU6Lv9A`tU)vH**0JXP;om%6B6#9s+@$H|7;mY^sW@8K6XsT4o}kGef>pz-ftS3uOh
zUyhr?cXl-H{lGi2>L*jCle>QyCf*YVYkJ$$Z>W~YuCo`R$tKppZ}<z2g5phCP(dxu
zmVUMa@7`sB76lUY*FX}LkbBK{&%S9`T~@ce)_y4NmSKX7nXt#NdC1g$imn9F;}<uF
z(WMONVH&ZZhQ{@oZM+T{EG?L+OfqzCf$5IDCK_Mki*t3V^_ol8g;V?{wGv|c^Zn86
z1tUG1=P^&*8{jVPe{>%m7Ls-{V_kDw9$*N(*KwQrfI~1AJ<DfZvi$QGLMUmHp<<Hg
zsINm*cxgnfKqNpc{g2jC?BBOdYz&_kJLc86-@y;tR_C1J%OLaL4;F&Z?VA(SdpKHr
zpI}kEjZtwfe{&?^)i5BZAC`d@y4PwjVDy|b|CnY7QlTfQr{H8ppr2C6B4AoSlK8U^
z=(Z=v-R1_aPJWOswMaciv+fes1B-%}GTD^%f&9tkXO&+nJEq1x-|0Y)`sD(Fq^L?5
z!2n4IE&d!hqL7lz9!I2;P5(+>c?vnxqUcm5u_!{Nqrqet%?)U<8p&Rh*i&W{2!i!M
z@fwZu{PvP?+)bq*gyKNt^zDcYU8!MrYvam=HQQfRN~G^6__e*x*LZSr+)gFm7mK_5
zAL|;0(V5KM((j+E#ew7<2#e_hg*F3hsMIZ|>J1=#N~Zg0b<~&ah+Riy*Q||ouy^;)
z3!e~1z5npauEZuQcAN3iuPcLa)XX18pI+<EcKh-A1^kk$kvE+ObBwEi9;=i9QZ!8l
zo8YLE?^bKi=SaVB>kY2Xc(old&^i+*`y<qq$?8sx-LQ|CpsR;$Eq!`ms`=tu9>zk8
zyOkodz+4hv#=oqqW!`IH>)+<OeNgL;rv#SZ<4Ixj=5QKqe$Vsloz8RO*s%EZW-4q=
zB4w5UC%Tg3irrIA^A)fb9z_b-u6o6d-$oTjz=c2+>>O@%?vU|?%uhcwv^-pq;D%f=
zGYCtwv2MX$m{kFJhcVs|nCGGqVmir<vWX}x?YydRJN)@b>eqviz0jUQ-m|8&Tss-`
zXFHHA9^w8pDay1&Yr)-Xce;5dP+|2u>}pzUVecL>SG4b1iTpcQx1swcQKRmzsIf4V
zURUwwwBiM!xQtT1w+EZdnSsICtCyq<@PsT~f*4b1t?L}|_~bIY5h_fTeYelCaH$5u
z<#WtCmPv;^?t&cY)nsk#fB70}VAfLvt#dL?+<~n%whr>tycam_V;KC7D&Gaf1vy@O
zO1)P9-i6{+>vKLpZy#c=B~eXSN!Q9VBUZQp-Pr?naISkLbJUfgDc$|}Qw^FO2Nnml
z`MB}vSn^Q`@bnlY`h1$?Zb#~iWzNZ^cC(fDW5iOe(*xUYM?#1Mk8H!PcR)HOr0X&o
zTUKtE^#bsdFwlkMC6La<G$?>sNIHsPVs%w!$aGGat`63xxt#+s0z&6chLT2uSDfjL
z#6yN|KRraL|4yWf-CB*TiLC}P&43^ANH$r+6=pu7tiA73qjfArnN_DpiA^GMF#FHP
zF5dUn*8-4jD6kmn%CL~ROy&1}G3nSCgCk@3iFN&929}i99*2OpojThn0<(t)t^y7o
zpO=mR5J6~2*>jY@Zs+|6$Ob%HShsL#TcYiVBp?Wp<tXV`{!;AOU)d4ua|csRjsb$<
zIj2o67dH0f?^6*kr(PEVoT_%RmU+_TVwOw<(6rHmqc1yUJ=DdA-!2fagow)Ho#>4y
z+c2CzF0ddHlKs^}T%K)W$`#&pvYi5L-C(2VS@Mvlqk2!9oIzi;r>#xgO)|2vKu{La
zWS-Q%5BJh~>(jj=%$1No6DC*{Q4#glC`hk-74ureR(8f+dPW6E8~gcG-=`5XOTyNj
z$mFypBhI+29SShZf|R6I;%*EK|M>LFnm(8DQ1u>mi8S8omjk?GHES3mkf_b=(~db`
z=5)G^+x^}U9(}Se?a8xvlQh~tc)n&(wL6CYm={cmn7W1beW#oG+hWU0B5&NXTkkYz
z!WJBbDmCdbJoMVhfy@_(R?;VaxA{c7GxP29<pZkU@kg0ETqhS(E-l->mrH#R4BxMP
zghT~Lrk9fCPH;GBSvRZ9-{&h(=jS!0*ZJ2!_hpvEk3;o8(FTbN)2TbE=WdZqd|N51
z11A0afp#U8@3jusLQ{GD0~o_sMjPk}PFlt}8TqK8ka}+)E@$^?#kJl=n7`w}8oK*p
zbS9imtGqyHP&Gk1xTR!s#(VtgMG#68SRO+8$(#E~^W>TFKc^EMWI90hf$Wu(V)L5L
zdmliyrLgKF6;!x-rqbuz9aCVFZMDv9$D+LG9%`(+?r#`Qn0zQz9;G>f<gq)vkkxas
zwj|}$BZv(LcB~)!Uy|&_02Q4(i|ieh7PParhI`uqwU?<~x3`z2$u_y~7;cKrwA*vk
z>G*W4Mt1283T)2Tl>d`TdNY-`qo(01Y~O%q(-h;TuSWNSGVl$EdPQxZvFobBu6@FH
zXBZAwk9;*O1nTHIr|q@NcGAZ&+bmp&QCRD<;|{4bybN#)MaP{<9lUY-(oo^+tc@{U
z0>aV*K_PmC&Woi3K@v&H^KwGt$=8uX@a_Wb2ac=B4E+5Cww5=O_){@{e=eG~6se4x
z0q8briyFX<37D(PFSiuB^HD%dJhJ~HG$yk7Ogw&9B9u$vv8LqFq-^y_l-aD4>1#rI
zh3Tf?SrK5L{p4i3Xk)wCRXTVISl9eFKQ``ZT0GcS(&A85`XGxoKc~vsmzPtV;_0cg
z*$!ZU{cr?mjMFS$1h)h<8qzZ*NU#M?+A*B{q&`ZfGAo2B#oy@}uKx4S{nq`~KhAeR
zF-(c(2O1(PnMK0#LpA;YQuK%@Bpzz)IAkeQi=1SXbIKNRdO-e{JA_x1t_&%~e*471
z9{P++iDwg7?G2l!3i&V<(LYZchUb26@@saxomU8BP9#vemMyenk0vFu!T85d%M12Y
zi$&>JyTr8LO;FdwIUOucGuCHhv>S#>KX5d%{d;)(l=#I~h*u_)fPkUH%YMmW9W$n_
zL_(hJsh)3j&ly|xx{4B+9K5})+J=55oLBhdSMhCyQ3dA8%F^?n;_&pw&>psuhMgBy
z8cGo*j=Vw|!9MGW`^Ik)81G)vZmgAyF$(tHOj-BLe2nx0MCgvw-UFjcQmm*x6~U@v
z%hfE9f?@s%E{i5PF<|q&D4Vm(WRvV7Z&k<4^EY9`qj%CC+7>jOxgX!llay54tzUW$
z=C<KJd-K%=gabDJD|%lE`EU=a={f(5=88r2p1F3LNXV7ze4Ch-f6RfN;y5pKc8ivn
zNeAMtV;f}*{&)s4IiiTJL8!y5%L<FeJz;F&`eji_ljbHV4O@C%w=lwR>e0qwQuP(_
z*UKe^^rL!(gf%BqfIQT=BBfT~c7IQ&gw1c2NJtbsSxSxj?s~p3k=>!sFWPx&&U=OB
zZuO*C0ZX3(88$r{WaA49ws`u~P7et57vNB$%Eqp6KiQk<B2;SG<2Ca1Bfx{eyg=1P
z*t919u%p)Ji=?Qq+f}R1?Z@((?X3<H0Bn+B)ogNKPE&bV#0!Adt|9^ztPa)=E+OJW
zLGja^Xgd^Kg7I?cHRz#P>S7w|R#XS{5GpmGM0Q?89EIg<A_oV+Sf*lEuQq)8Lq?&4
zu!m6pU&z@pJ+9u?sqeDQTH0ky28`o85s8)Ln=w=o6|X7I8cCpC(jCz@w*6~u2{eVo
zSLUh0jhYM9TJr{$Za_KWvu=A-ryeX`++W~x!P(Nm(_87EW_3Z3)e4I?13MOuR_<H6
z!7Sg>d@hkHHB_9`yWK(-IUzJ@O#ig~_Pjm4klr<JyI|LGe?F--k;jegP%wyJihK3@
zgEwAa=FVh~ak!;zGLC?`LOt{0DO=LfA(<zydA<a;HxVxQ+}R^D(#U0qI7sNXOj4$a
zq+s4W>r`bRp<&Z~HCx)SqMDuugqIFeY*~Q+`RMt00(yg7dd<sFQ1AEmEUMD)pRf?t
z9vbd_d{(;H$0FmXkoSY(^uve$_Wi%(qT!Qn;%328c7<_G<O&-J!f)cqG%dj{b5}*5
z<q7-mH_HetCLz}PpTajNI-WFgAB{e=V<l0)!}<f$pnhYXkQ?O#&i9eKV}oE69-!OI
zwDzyuOAa(aUHmn9x1#hhKqx#xsvxP}az(6$>RYi57yb{OQsHZXfzA<4K%Q;(HtMDt
zoFV?hwO;8T?HK@#ROMg#k5=cW;(zcNHv1Y~Fd~Q2GSfCm{0O$Oo~>{~P&=TWOJpGw
zCX#UvDxN&yDz<3T8ZZ>${xM@`7M;9<ncGh6s~BiLv%?A-53euDo>QR(UIZILE8vet
zo4)}8l)gV!0^bTR&~8rn)Xg|jO_!_vux8q!8;x;5CAqaYbOvSyhQGp)=<e65F1JA4
zPiDTcFP^q*%QH+jqV(dlEN{Hxrd0aq*%5*d37f?3>Yo&jj4^5cIW*3a<zWYjTBFL2
z*5y=h2f9c~hlLxC%zgqc$kcRt=I&^BI2YS0FwW7U1HfzXwlJ6d+6UjNgMy0?m%~s+
zglt$4QNGSs(lw*7|M1?vDUK2_{HvC^W7{%gRLfs$Ux%+jR*{IGX$l-bile+Q2z@7%
zRK-}i+=lCKH9cdkzeB*m5&MA?@jP#wkL~$GOt%wRUr&fRgmuCRrzR<iQu04WC0ti}
zVW?jF_E5H00bfuhoyffJxKF%~EZ~6bd(3|s9pAV^Lk%vfX70ZFoV<vca#_V}ueRo1
z?rBhdfM&i3E*lReNX9t5VrA6E64!8^_{=CcTJutd{xu%gCKqCG^cYcM=LdG4b59Oc
zEZQ`|>~)N<<I#^e(QbBL96S|L-c;$L13<${U0!*aD-4k)d#m(v{>GL4h3H=cL-`N(
z-q~l96_O6me}nA?My*uKzd+WweXb3Dy#Pl73m++W?|tuU;d60sr@$A<aXS+cReNS&
zYeSd_|7$kRW{b9>0mv#KInoTCBP;4K_oOfb_6u+g-CkGNJ?7qdcZ-WR__!^hr||px
zl%0ZEfP5-`o#G{IC^m#(ItnEo6ZVD?1PsW450$O3yd8$y=B>U6Rw#S8$gj$F01&Av
ztiJGB-{=E<=L+?#1+{ZN9f_EV@j<%Nvr(<5_@pyFNm=vMiu<iQL%6v7IIn+)dc6->
z^DP#pdTFgg7QzeAf%Yo-Ut}c*&RQ<BIp<qHW@4=>&JgOmgw1eIN+Mmv8-GLhM(&+S
zu`rIHH2BW1CikbcNcWyA?TEkn%;v3ReHo*eqIB_vVN7P<m&JPo8ybOQ)|fGcJxvGk
zo(W3`Q)<J|Oh11*{EcLZR#WK?*}HreU9#v#rb*Dn^^G3zZSKKm6M0Pi4RIBDlN}8W
zGZtynn(S=O;#n|cKLp4Pwk~6<v#pzIP!^}~%UTErx*56VPMV!f2MaEE5R9lkHx9GH
z(Ke}-TKcfZj4gyIsZxA3R8=o%GIV^M1(77zZfxbz^Rk0g@GI_SPhHFjNcZE0b+(Q@
zLJ?BF2sJ8xIIFG805K+5^^P6xp?}siHvw2bmr${d*uA*SH4tA|&m@qF<Am|#);)B<
zhgAz=mTtW=iK7IMiq-~?l?YgaN>fQDD+q=RLp6>faMN@Iy@C8|Mx<yYg$8ire4-UE
z(@07g%aEEgW*(QbtfiD+zE^YnUA&ddC9^n*4^xmJUoqDGX6Yi@$Xj(O_`N4vp-(lF
zt)OKX(->l$NW}(<U)X6*cB^|sMP=fRQDpKMcbfx{{U>58hh&X}5>=Clns}f&gR-8h
z<B-#*%JB{!n8UMwo$%Wp5E^59$@)|!%JkW&?@D;CP1MV}g|rk5%jB0A)m)XKRr>HK
zZl0|vR+XA>-i-PEm|167LkwR1JmuFW8TgJytkNV$;s67I^z;2}{`aM~H*pt4t$Nx8
z%16mwXTG%f9%;Xy5O{N4l&}d1oSN$`9q2Rn%)~#wY;y*56zcO7nWe;si9wsMIrZzu
z@7<zDman%{`tpnMkboOs{NAoF$@gmu-$H4v91-#!w{Or~Hb_nQ0euzi#`6SXzy8ov
zs!Qe6Wpl*Q*t}~>e#UDIT>+<+PXX_Lc*IY^e+qez3E_o?&jZz;QD*rqsT!&g%1j<)
z`Vqj6%veq0KzYE8blx+Pi~_dfB?Jzg7jY9&<Fj!^q7&htS%Y3_*onq%9FGMn6rEuj
z8II}lC747`fQI6$%V8QRw`c6`cMAxS(awh32@+PgBjF#foJE40#F%d%-sKcVSZSLX
zs_C3|-~A8IGd9{1MGNVnNxRBLe~i4_;Dvy?&x#dTHv-n8V1NzIHR*NQ(*mT4-iLLo
zaZ%%<HxNLZj@t`RdB90UachNc)JFJeP3*qwfR};Um(W>|RMtk9VSJshY4a_p_g&(_
z)mJsTV1$DD{Golg8^_gxs?Yd)gFo#bd~)wF%@lGl)c%Ke@Y+YyFwVG2tNpyRs^!gt
z@l!cN+UGw#1D<CClpNyQ4#PzJP3t{%SMm5}RZ3~Ee~;$-!)k)Dswv&C=06q{!o!X}
z4AbM2-^|Gtvvp@q97H6B-4JSNdS1T3k6;8+Q5Kg6nF6@BLtFNrINQ3<FN9p_m2Sl9
z<GCTWfXQI?g?Wo9z{b&E-Y^IGKH{1P6Zk5p1Haj5o03zW_pJx)a3od3`gd^LQk+ka
zYuXg+ig9Id>&!dq-XT`-(O{3=r^->~wQCKaiEq^YpGNsR!VBq^IjzGmp+(`zg5f0*
zBe~NeyY&9oRew6v%e?=?yD!9Z#2&PrxM#eEX?g@(eVfbw7Wk+BLG=qak}h)5zRzDX
zotm|0lvU(8QG$aSN9*2D5b7hb!Gq`qAwgKTlp{RHPVxc@OsA>|Ge#$U47DltnLjx-
zk?pmnphI`!76)^%DEZi@-}d(1ANR}c^{7pL`D?nf4<$MoO8&X?ZsqU4sZ<xYYcmh+
z-D<Jhr-lN8fV+)ZlLa=Ugx&AJa+b_339~heq1I%ql6RWKOi5oFb8ga5-(*_3P?Jz1
z!oSH1+r{FVGyerCr2r5s2C+!7rCl>@o$51hAwu47NDS@S+O62?7gM<I8&;6|Jul9<
zp!F~=>Bblla!c#>dF`WkcGuepgl;3^HYuN67`QI&WlA;U@3XEgKIPs+EZn>+B_*|#
zBNG3iX&FT@2gJ6tCORa!x4*XD6;>V2f3n%_CI8F5_cA7fZWw+A6<zmEW(ZGV*+_t%
zj^^+1ZB50@JC)cP4Il&GiRPgmW5Wpn30hG{^jvkX0K&Gyaz=pw$%NU|tB&=9M;p5T
zRke1u4@$q<tW<V~%6x76U}w})`l#8&$GYhr2^7d!NmE5$Y4t$-DeKA8cHT_A!+iRI
zP%7)up9#NqKIPR03YnhufHVH>Jn-Wh$yQ@h$2|p4qSo1k<DU8r+3_9!k2OG&N`+Ri
zo|)Fr(`Z)rR0fny{=G)epwIPq?;#HwA=B^**#-YkNWm}+5Td3Z5LXfR!9Gra9VJ-M
z*>oAuC!#_j(<|5^K7f51r9S)0`p7aAII>6&d8WxzsapdG6s}ldc`95t5c#-FbD*tF
zu`&P-nnBLw)8}v`+7A*g&~8XXvo^=wvs7Jvn4MsLaVql$M5YcT&&Ev!$-d|zfqyHm
z$oa7$AWS&M=6Kit<Z~@{R)wVU>A@PG{Nl(|wPR~X2IkM8c9pp8Ii^^d^eM%d%~T6{
z<uZNEJqdN~nM8jlE#0e>TPV#psI8W3D`s;7M7b>S7^iTQX=%#DmX^QmBX={A&7<D$
z$ANW{^*7%7`V7XQJEe>K7|kH@nQiKBJHJ>e%e6hK#0IXS;d-jT)<A&P0$+W`QD|9^
z{wclQu|t*?i8yRd2nED46pHRWAtcB`>A)%X#y^vPj4C=#p`zMTNC<@eR3(8y_jIxt
z0WJchvA$r?FfM#gOPVdF{1=Z_OQ9Lp3;q59Tv6h$(RCLg0z#@z;EHP&SFyhr9oCvL
zzL#SaH_>NXKzF-TV86E<o-)~MFe$VUCa3Ax+ixnefq<%h=YL~1XxSE}7?ZN30PQkg
zpoq)zE%cakhI<jXDw}Q;@ydj}^B*D&>)cf`O1qrVY-W5X9JAFBU?);0FVu4Vsl;{5
z*};5Y`O<D)o-I{tT0&KRzkxNrAV<+nHaY8NI(@ui$3RO?wJgq=?~8TqGk8)$P-b<S
z8-q*D*@8I2r({Wy4xN#(+><rqcX?cWbgJ+Ke4xjd>DOwP@7|f02kR_Na*#mYyOJE0
zW%}gm^U2WrQx}%E*QM;?D7zoQ2XdhIcaR9#*dRy^24DA>wqPBfLw8c`7%!mujX?AA
zO~_e{FMFcDyUUOkAYg>QlpaQg^3v5#)g^IYjS;u0rK<TN!Z(?g{|fd}HG?R~^tG(a
zJIc4Cw->LoX<iRfftQxgN6{)(n{H^VOh`OO8i0yBw1)VD(5wK`OY#Z-YlLr^=2}}$
zo*l(SAsb!F>Fj4ff<Pf8NG2yNir~LB{xUd$Hx!a3Q3=Iglbo_GPAXG6`I(o%dVSD`
zr`j<W7Q77#)@3rgOLc7rEW-zD<&QRHsH~O?%qR!QY2f|g_hYjulzo*$%eAF*5@JX{
zh34u3T;xE+&*bANn5|=eS-(o#Ya*RW$BaeVgcaYUA4*otRG$@rom#noRnfOK4mM2b
z9&s}E1^KOGI55zPl@B#C0e=9xp1jdJE(KA$eDc|kg_Ae$OG$30&jxC3G&-O+!d35)
z^Z|{0*-ems5hSJ%;@kZ~COER5IKQYAuu9&&Qdb5Lrr_(F!(2f-<ho1?v2s>Vjz}>O
zJLz-@dQ>So%V!YTRJ_447fQRfE<=PDdU6SRW=yOnT~w_yhzG2bPvc7t6eCD=7eB67
z0*|d-&sKsp`Zexxla_3T=<!qh>_?ZC#J*BHwd43xm0sK5W8tn&_D6NH?-Xe62e9ZG
zTpn^*vr*+T7J6jlYquqZ(X{#vmRA)orVEp|1bafCHpEV)mo$vXmD0bRW&jEHhTL0E
zr>>0uUT3-Z1PEuz$zhv*8yZv#W3o8X^x~n5=}@P*ie~jBC_V3!xwrA9$2jc3FHwf=
z{A?|@7$n{eFI2ol+;0Yny-U^Y^?a~wKRGtWF|>My$k`eM$XEBD{knP}ZumU(G3?qE
z4~UpXQ3IpsBvmq%?zBJG#mOgyKyic)n`C6&oav3kR!MPGsSdNBj8v)&hpygw$<s$g
zp08o;QDV=-3pp^iZ4JO=>x0D`*w2zdgzHo0uB+m-_C)whn81H{wtE9Y4`}{og1d_C
zw@rdWpk-)rB*Z0)P+j&xRK@1Xry`;n`@E_LAz6Wwz0!AVV5MxSy14s6t`erIKz#%e
z{;~esu|CynEb1Q$mgqSjeztHfe!wkRCa}6dw84!zE-wDSk9XY&N7Fgt^Box9hlGOv
z*&GvhW8*|{1ph`dhAP@Wt8X>M9HgZ;iGYw{ZM0gw4}=G#R5ZB0B;db!OZ4hCHUAmO
z;cAEjhBzFwOt-4z&Wm8&>-iY}b+-W@RagRyh7sNMGtVd=Qy#d7cs>nYp;GoE4htHi
zv(rT{i@2vHKp|+&M-bnx(Vq@OA$f$SvXZQwMHITq0w2?4;ZS}e5L)9I6}D$n>ii)!
zN;%hPLmP}Fu4gu$h#cQO@n3TsT&ECvqLao`L>Hd&4)r*nA0hrt;kcpd&a8xRKujFC
z;qJ6Rh6Iv~dgb6{D2F}+M(TV$@qzkHb*FZlo?Wu3GN_F^NN;p~oRHQ@7k#4#JIRvw
zr#of_r*iQIEOSZzxqnZFW#ZcWQK$mxk#1A`l<R+ZFQwSdCpV<zJ8P{+t@N!-qv!oI
z6>%*p4MKZtoPI-#I}1L*agwxRVD;_l4HFzkL!p+wK6*xs7<f?`QI!hWD_|RXfp&Y#
z1?1Eo#8{x!8w^cj%|lYA?0Yje5NYE;u4&Aje>1L}+{LfgRO6+vHL5mO&2xYcJT2q|
zFofm+UuLJUPP|F4VDDWU#&cu5EPwIA>%aC==Rito<P)o}8StM5PKXDCSHXR_lqUc#
z%q$w{G@5JQ;R3|v&(^0<t0uxTevtUrbU1Ey_;ZE5VbC8OcQQc2l^bS?jEur^7*J<r
zu>4EYK3J3EPfmrz8aR%N?-8?Ybr5rA$x3_&{#L?#RNes!NGS5*02y>>?TFPxh7%NT
zSM^a`wnjq3Yai$)KMD=K*a#(#tsa}j^^em(n&JAZWhSGjds;wH1OFiCN50hbkO#|2
z)qhY7iD!Z<+8@q?P(ad>SUiF71jk#_)lFBny}h0;_XiSY1EKX{?X!U_Ht^^8hmQ1b
z#wJ0sDluiU^mbI(V2QndSIjpn{qegMW4wmjrf-5^2PEwbia5HWSp<<=5)~=7x#7;4
z8Z1#zI&z$Ij`tUMo^2Vgwby|DRld3|QroIey_GU9AAPp~H!yxbjz1vR)_Q$ODs*20
zoR{ZDKj#~V$eUiNcKC$7n_tN9+sZ`w04$j=&!@Dmz<d0Dd@gXk5Vz9iY^@EXxR>t*
z6)oVEHbB~tw0jLsk~lX}+OVOoy?zF$twZ0PDSaxmW~E186*#r(aZ~=Uj`lPOk|NEQ
zKJj<%!@RYt3+P1+`z7LF8)NwUjsO%W)~2Eqt5EUm=$4UcDK02U2NH8`baMxcF3zQ8
z?qll0q!r}M>1w!99~8niR?fu(e%KZ~?R*pZNmbSgm@g=U^z#Okt!9JewQrIEhVn**
z|A+JFjpC*9qYb`?jHHM{LpLT9nc&2Z_4>E?78vbbO)NQZ{99Ks1sWB#vL-Zw28-)J
z^R0(*^bd^5n)evR9kKP6p0!MYDmugc_l1Lh*QiM_z+AJS*US;9IqZ*({@{3XKoiNe
zKNVkaa0(kTFo$(0`nPYg+?@&)>qmXuR-U%#504Sk^uK8B`VTKKBG<{b?y_do8AxJl
zn;h%AD6!~ciX79=1JY#rPG-J)v~PmSnE=gLYeWd<2mWq<9aW4EVV3F#>xuAnGqo?b
zP@EoqNe)e$rJvcwKN`S`rS{tm`zeE0PV-5O7=;^`qHGI&SA%VZoCSv|iiQ*8vZTu<
z#&f`Ky$dHk>in)#3a!doR72l${4q@mY5#(|&O21z!E!Vr&MtUZd`juNW+bmGO>d1`
zW}2sFv(FH@Mc;3dJ-%iEDL^Hxj3;Rs49KirAm{s}J%uV%I(T|Ccj_yMe=}!0C++4F
zUP`*B*D#)2Rg_rtBF&QlpmXT0`2>-pacf*X(|>`aR$oSDY9B5j*Yc7H<Hm?jCh9$q
z$D`PLIjy15<>M5Vk5heeI6UR#pgIL+I}jV|Q4e`m&CET61566&qbC35DJ4BPqwM)}
z$`~fgp@gt|KT6qCeHBwL#OYKE3<Hh;N`<iyNrQpY5=VO5Ar^XZo6_`pjqAGn4jPI*
zYlQTU0jjDaIR<yxj$fJcjfo_BfdAa2M<NOhpw~%03Jx$Pku=EM?O<yv<jkQzEs}^9
z>-;k>iaXM0d)SJ*0m0PWPvS6jJ5Ta~h>yqBtbmSeMQmfeoTKv-yxBO~U)fyLvm=!c
ztx>wYgMiXBQ@A~xN3_wVUjk(HM+R&DpXzW&>?cJk5_l6JvhE6mT*p02AiB7hh0GqJ
zpwkqy@U!mSca=2<ZIev@lb<Dfp0IoJ_8?kS@KN!$BV_GK3&?kls<eXcq%Tdxm3bx8
zVT_-iG5sR<9_S>+j1K4m*Z|nIsNPxaL~D7&<*Il>EeeECR$v3K!~DC(SLYka8p{4C
zfpvRlot;^+8I;^Ljsdx0T&y{9_Pcy<CULLTQkE8?E6+&MYj_A=w?6>%<fYbIdRV@<
z{Pn4u1@<!q{^y05k|<PxC=KobtKNkz&<C#2@7OBA3lwmnDf)=1j?2WKK>mKo9eATl
zhzFH!JG&eS5!Pw1Dm`Xj+Q^aIG}I8R_r~Ky!c9H2Br@MR--*5@!t)$1-3N*>aw`3j
z)sYGF21);><bp7BpW-rygc@k^1W&n?80FpejX>JuS!!CRB;e;mk>Dx9(x%_GE$lZj
z`x`UfbJfcVJV1~lbFV=VY|47SK5TP_RjJk(aGjMJEMweOTDDs~D(8>L-|3H*lyIYn
z8bc34X*+i`3<p*Y1W9lCywvDj<uh2Smbyy0X4bq?4Q`lfTq;O{Uw(`R=<E0;-U|U>
zduBDj!J*c0dfGA);-FT^LfnaUuum`bls^}X^rCO&kLMy%JjXStq61MQ26R@}2H4C=
zMX8s}b3R3Yo5uVs`V01HbT63or|dN(JRe6rw74;-K8IWR2|4X+y;#tc-r7qHclDG;
zX$aZ@Jyy|xa15Z8W@7H4{|%XbNm2oYIqzFqA8wo$m}%>K^~wgi6o`B<r~YY4$;EgK
z^;lgfG|k`|&3))@zQ1zTubpdbZSKS+L)}5GTTW1O5<f2cE8?V3n?wt;RbaoIGi%%r
zo6i2zHL9))t`B6#KAlt4{*V!Rp1-HsPUY+THA_IkwRJS7__Vmd7*L5^<aPc#Tx3~C
z2yq9F^F$JcV8TcMYLv@&;3#2CtSm{3csIjH{7CGOaJIX|UxE<zuj;usVSjAw@=_h%
z8ikR^H)AFvW4}L;N4Tm0)(W4K_$FOn<Y_MY4HAMnT@0EAEKg=J5ngeDZ&+yz2yx&5
z0FTfFd}&cm{w?f4rz5g{S(JUF9XQhNbEP$Np^9Md%)zva_H5^!^*KyHbeWMbTTziV
zl|$E6<8PpB0#uA!-;gVyVZBDz!cF7pHRrk~Z~E3do(FapQ79)C|B!y$Xe96+6#d2y
zuVHX$WjRNd9h>B-Fj~PEm*nhi<BZ$&U7eg~WoGEL!Ay&;PLE<kz-q<MB2r*OgKHjx
z1$Xx75?6$c8WS+3Z_g!>*g9mPye#O!<4F(XH(B6lLKn^q*on_`$p|(SNF?K|+j;eV
zj_Z<;qNi<68d?ryR(*>H*V5%Bvv!u#>DH&cv(caKH<|OU?+XjFnF=J#u^7m;M?Cz|
zbrs3gQju<{q>-Wbtbv`RO+M72S{qvB1!E!mxdF`2mFG#UGf;muKljhC`3^qU^Dguj
zv+aofzRu;%O*pw#gm`HD@Y<5+q<lwd@+(mRIg!|&u@FR91CuGpC56>?CAsP7ya)Jt
zqDA2x&6j{|Xo)&7dYHX-98c0{_%$QN`W%vAZjvfiG^-oNI~(Kzs^p^06X4Jdr^Y%E
zf&ix=Y-@#em+gtYbAbPUc-{u-A$+p@dK=)B{B2d>1SijU>R<L!Ly1gyqmh>mWrliJ
z?gH;_2>nw~dcaWJn4g~uKpEbJiIBuRL*epy=F^uS{j}6hK7+M7Y3v&txYsH}?%7{P
zenDI$rR9=OR_#-arY0X{Ivr$|vR~VVG-giXrY7kjLRcbEOpq2~%OEf_wZE(c0#-VQ
z(64821__z#4*68k5!!Ak_NTzx=;|0zxgL1(6hCElz6BJ#38<e{zXUEk`(?vZDQrw)
zSmVcY^&tn{XQUZAv!qO2htL>z7fsW2BJuhK&dYAn$I&I;Y_8WM`rIvXN1rZ@!++@B
z-MjMv6Rv7YReSKpChE&<m9avx6FCgdenDIx6)Vs1$_|`P3+uL?yrMWKNbStOO)blL
zHS~9wP-&VOy>)Y3UflP6<+L+P*RW3)*n;bx-fV~8fBX>u=s?#0o%x{x{o1Fc+Oc*x
zhV+CVKvEq457~-#W$EoOhG1cT;V;<v99aRs@TjhfB~{#`4%q;9sz9n}p9kPowmGqW
zNq_YnkXZg%an*+{lD|c~G?h?(?V-`J379j~SyF}jynDQa4hYT+Jx&#``uI-mLo)c#
zOK+sK^nu9dv)Qd&i+w?$No{>@Ebk-q_RoAAx2h`3gD0u4pKlR@r<MEIjEsJ>Bpvk0
znjOIe1PZJtB@31!pI>Q9IEY|8ChA6`l4|cn<Xrf!Px$I`Bu!oFyk%3a^s2EzI>+g_
z3sgnj7y4ZQByye<g?g%epLD7e##GAn$?o0s*x=A!V@&V3la=GBPwxfpj^7s&QmJ?&
zZTCZqP6as=k?-_-B{(5)JDtg5Zfpa=52_H+losy(ZqIh1i=)1EBfM(48V0yu(2oAC
z_6qqZHHZK3dT3$ULdF9mH_gZmAj=DC6)v(GNSNt`w%6hLq|3HB{yQwrxJBye{i`K)
zm*^1<xxlF!wDB(a58zpnedd$%ShKkFuXYCh-6*bG8?Hs&4}dEpZCoFYR;qmH-)tHb
z1NC<`xDGxH8h7V1`lfic*x#X^HE7*L?88l250E&O@5Oz6zw(j&WPUZO<zPg3A~swp
zXKoPD@L1tU_49n>(9$MlDhx**jdy3!^5!THLcTza`>`7In#kv8^<SyInVih_R7Um|
zo+`2HU^$2UzoJaR=Ac@x9p?~DJkEpGcbliGjF|crw3--BsA}|uK?Tr=yB^ubQW^VQ
zvSoF;Za&jkPwgyPells@zdH!ney2SB%Z8gz7pXLx%ZKtDpDZ-;QSSqhvX1w9JXO#Q
z^#61jUrjw+cM$490PnWN#2)ey8j`GLfOm&*N?cvwT#1p45$j0a2OO&F<k%q}g|P-k
z_J=Fs(0K=M53KO&*-WNZOfKP8s5gEbj>8XvI>tjXmUJ`~D{~#j!gWmcJo5QyqHFdw
zx%LAkWfYY%{ivgZ6@6)Gn}A_7Mc^%<4Fu;kj1(3ihX&~=xSXU_S=1On>cl{c%6Yj1
zA~b4yXL`Y+(L!Qmj%|aX6dn!4#xW=F(xuAkSnfaxR3^gHzG}F4@b~z<Zf<Oq_if?!
zdl)KbctqAB(5`Kq;G*B-Vq`>qPLRlQHdM-&a{Vh|%}dp0I{LTHQ0ir$(_r~9wR2aP
z%z7^Psp=F-^k&@2)9`eVX=-;8FD5hPt&_@jKmoWLSZ})DJ^)=jLjw>N)9;~1+UrlK
zspfoSv8Nq`xrI#TWk;z=o#5@PV1u;;f!bW30yYs(--?#end}c@yMb-@-wv>~?Mf42
zKxnkp-r4KrXX%OUZz7K}^-+%wKdjSA0o6-!Z6UGq#|rvFE?C%eMIuM<va3WT+U-}(
z={usJOeg=C+aR7v#=I`i9V};^5D?l+(gGx%J{q)7^=Glv$6u#V*A1h!FD6bGA2zBn
z#jYGP;mxqonRSTe#>Al=sheAp*}_%CU#{#Q{t){L&zpMYRngM@qX5<-&xAOM?<SU=
zA!Oy%Kbh`8{koOxvnibs>cUQ}s5>c?KPSm}9$Me|N0VS)`0CTqnQnh9RFAmpV%TfN
zdS>N&9rZ<Ne{!i1kM}~&Y(NoL5QbU9>XVSW^iG3nt3g`SF|yte?9Hk(LV0!(toLbc
zSkZBDcog%tK-76|PhHXo=oyr0^SsiR?ae<hQtXi!ery(IacNutW@t<D{etI*H%447
z?S?)781++*XCk#@=A||a+6yCERK*jurY-KO<+VDdXG^&|@1m_5-xvw^TLZiqlO{=Z
zCj@o6U1;r#Ef{a0|0{dW%}sCa*CGo}tv1feSjstL#r14nutex1C@_jiJi4xA=9vJ7
z_IDeqO&LKb+Rk)zhbBc_%grP4ANub`yMfm!c!KAn^We5|V>|PtZua6BXF0m;5vDpT
zP?zcxFwGlkvtOKvx@5~N*a3Yi23ns_msI59@vIT|>93Va-h>zzYHIlsz9Yxn%zQQ4
zv;GzrxK&zHl<LIpKG-%B{@J7_K!*6;kLkwABCfyWQ>5iaad%Qeh|FSNKgi+${Ltzm
zRjWT5;ei_o5kI|F7MQ}E%S!Mzm;)-eHsf}F1B%jsvZ|6l3rXAZB*jCz9$C@TK8^*<
zeq}o>DvG8D`1-J5(#<ueVmIo&0rew2xj?-)=%Rt!Uh?+5aF+GK@2b9H$qCpP{aD>Q
zNjt7r6@DmzdS}llhQpt{#Hf(!H!nq40uvfuh;Y}>6xtD}O#>Ul`276|0w%Q%x(XlE
zJL&Ai`$S^sia*tj*o5tLMie?o*MH<v3b<_J^pSsi5;t#O>F=PFmVFB=Lxx`hl??cm
zQXKV)Um%{t$?#B)8Pya(Loa?Uk=~P860BL0-1~%T+i|!O`n`o&;UC(YE-EsX<KAj0
z?es~xsP*WEY#49#^o8#oMtyBe%FI-Q=N}r}D|x2DHC5l$q{-3)_4Wt#EEx<lPo~8E
zoS8GIFr_iRK6d>FgDM*u6oBaMdFNo~p`&(`*aZ@p6nphO1LBkb&FVx*<aOlRW73Ny
zc~&0aZc=don13eagb%JpXU9$%(k_2?u8J3h3pMH1mAm3^e7FJOid5Z%;d@TLSwMTa
zdvN9w!FCau14>^Fa6yz7gQ$KplZS;k;y3L$)Bvn_YAxK@cqe9TWAb4H@VH?sQkhAr
zfwLsnEU15IGA@Q-yA3+eYY#RLO+lO_?y26@jq_c2ySKJj!ks{(o+=AzK3dWsg8&Z3
zd}hEhMpT5LnSZ*@sJ*7%&V(Q8NE`CBr>6!VSHGRuFA;m6T%gWVgqLQ$rI~Z=R)qJ|
z-}8^kv*djhb=_}9<+fjWX2R@({PT8i2MB<fye8X|pVqyOd&U$6f2dk%0U<C`$mejx
z6VM9>>V)OTQ&iYmEh=Lx6lFoD_uk~gM$2m5p<ZyjI>mdBRu+J^*XiPVqcra>S2N5l
z9lv<$BJ!YlyD4)=^M&x{*`k+@_+@s|Z%aSPK01a*4cmpRY@|bl(V@#a`6$Pz@etf(
zBG)Z-I$eJu#GLGB5$%BMKi2$w^cjsecNnG7&8*a=%r$FEaE|h1pC5HW9ZPN5H-fBz
zT_Iul5q8JcST6kSB-{nh<->#9i=?{Sb*JK=Kb<Vr7I!9UH&Ns@)fNJgA(Rf(nZZ&r
zupvnIzlOK@YJxQjOgaml<NAKZ?<eTwv)Pl*58fl1`n_UkqtAZ42~Z#yT>?-0q1g|W
zQkm?ueUBpzrjg2(P)_Y!h9b_tSgvsRO&?xDD!)0sLYRLiat0W-H;C7^{HezX@GOWA
zQm&fP%#teSx>iN9cM;A0+oE<$xRNrT8NpC;$v9(G(!D;8##zQ%+e84D5xq+ibr^Py
z;8`h@@^+D<8m^wfn`qcm8I}DpK}EG+`}E8{1t<G1UVcyOYazKO;)P?;tXdp-fIr*C
z=(9*SM&IlBoE;u4RPQ8paCPu{YF{*f7|w(pW#n4^Y?93+Jk$+N{RBL7dW8Wg2xxF9
z$v}_P&2ixw;miFS*<gB&Oy|ty#QVW}7Y~j68Sf%9>I27QshzVJV?!L5@SmV4Q|}@(
ze*#TCV;hw(B$IJtIg~ZZLo%T5BDVXJ*Q49O9~q&0v~hQQk$Dp!#s%`wy_U=JgEcc@
z8N!7az(rU1aZABijF3*7;YAN0DMUvHLH|V3=qqrc#^Y(!7Lp!p%!d~^mPXXz-Hhk5
z?4n#oPhQ}ki-8_Mf#S>VvFKO%<uDMM72p9XE#xcaaqzu$ApGJIq|0Bx-nE)o1V4(m
zLTx=+SbW&^5a4<RCTOq+z6oj5R5<-`Gww|yEl%MwGU0*N?Hj4oQUr`0ZmfnH@nA<T
z<Bt~=lJ0dS8xvu|bI@AY(2J*Z6q;X|3%C|%s!?<~`1+}@{x7pi>w`tdu>c9LOwKp=
zHj^nyq{uYrb3m^RuT&OX#P;Z7e&6dQF>jE#6p!$%pf}yFf4s@{dMpK7hIl`ITbf56
zGFrszJ1N$!ov|4v$ubG4sdo-Rcc>e`=W?-7F~1YQGwz63kQQd?OJ3kJ_z$o4JiGa~
zO~Uo&Ywr+#>d#TMF*SP78?B{fbwu9O%+(A%AEw-9w7D2&?f5^A&O02gu8ZP2Q6tgY
zC<#GCFlv|~dheo!Aklm8MD#LRLJ&mnC3*=_heYqu8NH7>%<z6U-(T@O!Q<XJ_uPHf
zUi-J694`<^@#r%+RYW{e__l}j*XE<}_OR71Pi5OyWBKOaLE344YOfRUxOiJUFwyE)
zX!S^)egw+~SdQ;L(BjOh1rW!hI_I<FxVv~duNhdO{t_0Q6YhdY>v3T2bKbZAQ*Lw#
ze{AyoRvg83gqcK649NUBAor*_St$^1JqwPJrY4NF#<iap@keV(s*9tW@Pesb&@PGt
zRQIat_sf$qW6;+P*jm0hdoWD+Qphj6gALUtNkg$~Uft#xa00v;LjZ)VHF&M3BNx?(
zclvxre$_gn%YfNuFMWD5C^W1>5dh4)w7A_Ly+qZkLC=QoaYA`SqlFE+MFIj4c104S
zKXl!VK5CW<JEDGcYpg!)%mQG$huvc-3Q~61>Rv%kk-@*auDgpN6*VdI&CzIl;XqXN
zUqwv7U<fhbqJOy)=L7f#i52yblw3|<7Gz6(VLrE?aHaN9NWsVb?MwmF6dUhZKg<KY
z9Xx`azC^4(hs!)@G|Z^L^p@Bim1|-7JePg|xGv?wr(cGT2;;|bRUD4HkVs%FARr4!
zXof8F$Zqgf<;97N3SIjGS9XF8+O^*K4#tXcs1d@ws%t@pik0E#bSN*o5=eyUFZN|-
zt`#M5(XXou0WjisFcCwpyHxqm2G3=?QTZv{Lwk|Q#w9>u8yai<*Y$$wET%fkoSe;$
zehc9HU6w_J+RWi5AK<@IXz9)RAwITJL6iBRi1O}Y3w>GD%8?Y`>spa(JkS<oNpQoZ
zOyK`4kKX+iZ%?qR2%4eF=ewrZQld62aE8sRx^`#~k!S3h`xcTHwh~9=?(4qSwY6R=
zftdj?p6*@3eL&q5oWES%0umuCEqqt=aw8BxT>xj>oZ~)pqi}}^{6v#;<rm9m<#%)Q
zlvhc9Cn`>tb-fy^;acnqC@aFdz)yET%u@oq;n>>|J;P>GnS0~^Pk%3Qz>aaK0#Kig
z(s985OZO50V0z$H`Q`VL5caNs-jveJ6M9iamJy(z=L>?`yX}f<v7eq^em~&SG}c5Z
zI{H1|Uo|xV67LXQn4qq=7bk~|DIthU_=YV>dSXOL<oY!E8k6pv{1g?b1gU?M1CUzh
z?UK1Kdjps%TE#@kgLdglJ*)UZLU4E$_Y~Md+!u9C{iTzUFdY2#vTUvg*>>*68Dxud
z@)vC3=NqD87cMtuNDldIiZWhuooc-n``#hy2u<i>(#7ePAoa!mPPp)OXE!v3fuf9Q
zns+^me<NtsIL+5Xlk9p_Dl?35u|Ww=h7F#mv>ogfl(Ppe;o?_cJ3pjK$&-vtxm$BI
zX%J*KaqWtXxT5N<vBT~}AzF-oEWAi=PJXZhUN77olz9CB0mhccs1|WC!tT!1A)J$i
z0}pnZ7MgCIVdF&6CnwsSpNnwY|HvMU*;|M}AI^)+%)5qk_1iA4%CJYpyutIjtlT}k
zzyrB6p|2`94-}%GJ?@Jol(xmOyTlKD<P>gI%qwC3sNdN~xG)q=-WY(^RbGTO%6aVD
zKQ6Uhg+G_exd<JDJeU30B$#@C#E;<wl6-%gqql1ktYmesH%h*R$TCGr2h~Z(kD*kn
z1<v-)YOnuk=@OqZcuTsb%PJ6k#;iJ2<(U*Qo)No?ogc%#9&MOuQR8X^2dr%X{((xC
zOg9YA9@6`Z1TV;<p?3pKakIsG#jEsQrrM!uvcHQb<f^(u8mL!1bVcJ2+ZFn3&<(T5
zcx)dMJAs2(OE%FJ)+9_FYmtz{CXO_55RW{vkQ`!SgDInkd-EjDhE+>YFz~hX!u(j(
zBl!)E|FHP1y7&F)N+_s1a@}WO|2V^6c0c0B{c98u+0UaQrtdK})4GYDYd!;VeLh7y
zK=c$g>-~^3FD29uMunSk#Yv_fNk4v(P?^K92Wz#r8~6H{*Od47b_&{rc^$GfOsU;j
zvY{}_m*z2GM+7Vf{dZsa7jv?w#v=JCR;Qm}7|P>TAJME+|MX5wi*$LE{AHf7(=Ly%
zB*OXwK)(Wj9y_NgLZFM*M1RbTn#{(BO=Y^VpU>)%+<<_wE7e_$Uwj()%C9Y*IrtKE
z8g1hAs>CWs!MGxU*WBf&zv8$qqwMVRbx{3f-uu4O2pCcgevhvKp_{@&@30){fuv^v
zLj-Jl=#aZ&{Z20kJpfQ{LMIsrzO~z!BKyTJD(JF^%wfUYnckm$NbZq;Qi42Ur$k<u
zr2Z-t6noc5gq>zHJ^j%^OqbU+<B~JKWm0ZDZM9j_)!{ixgut<56Rky%y0Qm9SyK3W
zlv&X($CO(S8>p!H<d}|C|L9e!ZcW6+VK5R_Z5Iuh%NuYF%u|${imc1$;@z@F6U(fR
z@Hcf|g3rJ2?yl}5#7;70IYX%TELlG(_UpPlwxi#Ab84K6=2F6i=$RY4)=tu**nWNI
zCEl{y2m<pDLIq+YFmK+6qf>%E2b%2u)*K>4{ENDNLIh>76oSPbDXMxyWmF{JfV7=&
zE*6bhf>Xk`&TcNKkfnRvXZhdX%@bq6LufPzX*6@Sgp`5ix%?goxz0Kk)L6aHneok1
zOEG_n(R|A1o%C4SBz@Wn$25%FV!FG=zS6fY3FKy6wZTYquY(QgDS&X+!Uqd;%^L8(
zegpVR&C5T;Z^!vBXAy@P>@_v9&(E;vA>X)DP}M6CZxO<G($u8)Y``)OESYPRRIHIm
zBslSq^<8-gG4Z2d`HYRM=)##8x}pmGdKmcn&wZ!xEracp@YULi*9ABkRc;5P87{b6
zaPZARdq3)*x2ayhO0)G}#LhyXbklqNvzUfL*scfw`Sw$szUR&JCDEx^&7%>=Cdlxr
zwlqyv&vnA=t#oih_c~+E#`ODtzQV857<slHX~lJQv|<e1Il0s>4jLtu@%Skw>K<Re
z@HB-V(<O!|-ml>B4NJW<!Nu&a<nX`4K1m*e6oe_gqm3vqqWXC*2wNAfqK<dPdbGw|
zGFbu4jLviGKk+aT0hlsB8<t6Z5v<ccl9>dDk80I&`E_H14wFel;9t&?Lmjf({G5sf
zc(WhL(C_KUb10I#lQ`|$QRy~|eU58qN`)6eHdaTI&B@?Jd~JRSEw%6}J4LeZ^nf++
z>fxf;IM;Ainm1UvZ2p%@gRQ{y^e<rewubTk_CQT!fw7K{)#a^Sw5R_pfa5YEobW9X
z>H1K>{)lk0Fab>WCNkctuH>#jj_#&l4XKt=I(L-u{$1)>F|&uyaML8^LF~Ahs)BA<
z{i(5oFMz4m)JQwVhaUY&XjNtRI8c*VKJfejZ{itVc{-VnGLZ_UrbjAd7rX*c8`!uG
z49T0u*oX4s!U<;gTQz$sfkxKBNA0zj{cOmHj6LU@D=K_|1$Ve?K@uDCwdym7BlxpX
zhaHi)lG5$86GDi?LfRx}IxK%yc-9e!G)W(vQ%T*y3feF5ZE{TblBoIJ*c_#NvSmu5
z7EE8vJ~!W(qTn2Y1!P=jwlb}Vv5aViIPaUEA9tAoXhQq0^FzSO(f=w;V6tXeKlm@F
zqPs1_(<zFat9KWrjC!+A_MAhom9IwL&AobR3TW^Bv^clBFBC-u&zB})<O7Oh;1SfU
zZIIj0@{<B)H=XFl)Jf$o2COdNOtRHXDERWa1V-^U`J9vJLOA!z%;NI%FSvIhgLCo0
zxspes8>cO<z9%o=qRK}_v|*V7tmK92^ALmW+OE1wt~IqcQfD4Yoh;MeYHbk930N)(
zLTZE9?>Lx8#H+xik*`f~kMZ9@BVEXaUQxKcMk)B{W<_4~vx?AzyH{3`1*4OxJ|a82
z`0rsvA*AVqxFystPb+z{N3Q)zb#c}^r?A<<30=#^4*UN8UZ3u8Jd6L@QW^``WDQ##
zOx84I*}}K~!i<yC=K2||Rkxfhd*i9|&8dy@bC-U=-j^k2mBa{b4rrELmTpfzx3TK*
zzQ1HkqljrZb>DlT8Psrrd>{Ht)z9Q~qr~j7`u*8$(7L7>qoRB_knlER>G%otd&Jkl
z0QdCY>CwdzPH7yTxLpZ65WBW;c2abvZ}WK4d-aw)c?y)8o&eMen71!t5%~%m`XE+;
zK$9tA>c)1oB-;c%I$59Ld`FG|nGsaeE{Fh3VAF4*%ZiWxVadw2yFcFLk*%_=3;%^F
zGZYpai@P+yrP;YhfdMKEqS}BKF~O^a%2Jep16(gF-wIXtMFSa_T>h^Q%szdjzKU>k
zM&AAk+q-W+VEM6aE6-~0=?VewG+#rsn<HX=s+LNAC+3N6?I2-UaU_zX`SzM{oVa5}
z=ru%D1pZSI*fvwcKiA`~vWN0!xjYj456k@7HJ|j9q%?xxga7TMWw8qbU`&DlB3zK3
zI)XRn3Q18hjzh+15?n8OcMTwV_YcKe-d$K}gJ{ja+~_=%8ev5m<OAEW0hAaANHL1v
z=YqT+!fhS~=09oLp#JWf)%KJdX7X)q|MGo(ZkUe8@+T}fArxO>qJ(rMH6JB^iH-uu
zAe|r^LykzVe*{fj-Puh?zd2_AXjC3q2uiwYI(|v{W-7f~q<m=@7}}3@z8sJo^0**T
zVKlaY1jM7Y-57hjGu=OuG_Oq~*VV;v)Z#VKGh=Z<?<0Lovu~%m>Mvsmhg0iAx?-`G
zfsNKfEgnw{x7tUytFEDOO^j>K%c44_lI1lN!B#<uveN$C<=ah#&Lr^kJ}CMNuN9;z
zn>qa3LW$TjJoWWjH|UMe9mstV?mO`<B|<8JEmLQxpatTRveHUzR5<=7+XT6bZ>hR&
z_S%SqHd<g`sW=yZS#%}IV~#3xnf8`}G#vYuPr)mJT5|<<N}ZHL+yXF6e?tl~^-iA@
zh<9K@i#gt)edGvHQ2as{O51~R+zaC(P}rbp*1&C;CWJIh5h#}Xu>dF2gSRPFq2xhd
zvIDJ(i=_<!ZU`W?5II$!T%O;1@t`#Rh7$N-`A^||Kt_b_riiZpn>AP%i5kKM;=1)u
zBeMzK+F0FRafhtaPi_F+qHAFs4j1~~h2<`Wm=4!i-#CzQTPArD;qb2Fcl&fSNG3jT
zhyo!W`WqtV?zUMb)ml21uru}tC)n$UBbZw9X%{$wJTg0^ATsX*hwsMqljpKX@B~6#
zE}`3sW87d(g8f^`AlIJKhjGLhCLsLqS#7)sGPu;|VP5!@t*|Mo-oRN;;2JA)*IZ|U
zG8hx+O*K)qYhQ4j8`OY320V`P)yjkC5+UwccdgYwV3(^O-^c^EKqR&Vgy!SNJh{~r
zlMHEB2p1na;`6=qL*8#G%=x3aZ>n!ENn-b+;=rYF#;kkXe|5u`9D=|mOd09+ta`u`
z?$#&QaB!zW%WqM}${fGy<PIxKT6b74wJB-^%Qvj+BonI-&Ds9KwV57>b<0flggqP-
zdqi<vcmN;<vicWj08lW-f&bLF^}3%IJ0tK_jpz!!6kt}eJ6LyeOG|DHIr?4^x3LHx
zqS2u|(F8t%9`rF^DOKgKd`W?d6ud}5LZ`l&c1_ZK%Hhf$c8QmTEZkjo0#|P}nP1Hu
zIH?-8z>j;l58%e{Je>KM4XBJL=@MVsaZXq`Zc`84@#K#L%oMXlAH>!K`Gw$F7o=Oh
zgftiuU$4;mEn{Fj!jkSn{krD(f0DC4!O;yczYPL+xkp&RM+%d^$x*i@kZdh>IEHN=
zJr^2)#htJgotxXF3>e|!C6HRC$vHir8s;)J7{ga5<6d%^<H#mwH4pH}pFS-;@Z$#Z
zZS~CmcCx2JJKpW3sw_Y{{tUzK(FIyRp7V!4PXefpR;vVQD3w8q%grFNH)a$jzm{1!
z?#_WX$4uhdH6b2wk1}xvPn$A=FILU7ssP5k|7(wJ@>cYW$vx#yX$sV>DWU|Nu-?9U
zbNe3_v4x5HW2J=FdFg#sy#nP4ik11`M)g2m&wc2m8_b>};;H_t>X@A>PQks&KnUSd
z<ku@Qd?iK>vCHzfbsY_|A@*G0;m8ab>%~6EvBM5Hya&mlYmp22+If+TR^c!i{Wm?e
zHebJ%{fBiLYr;+H3`+c4%<hx>T6dB%XTF&6=&|Gz!c%Hm;7BaJ+1@0j{_J!n+>3*y
za0*AZbhr1o5UNHDZM-PtdRC-p(ON=5VHYdzDzIzIz?l|a3e{D@I=EG-4$OPy`k5Zd
znbwg3@A{+jBDL`QJ?^Ew&%EdNxgp#GY0Bo9O2VZmTmTw@)K3EKM@=Z$Ym>)y6+RDA
zS0azDn#8^+6s$mXj?o!vge>>JL{&czDYcY}Ff(cp$bJ&|FIkaHf+!3avr5N2jU{4V
z{v~xa#n}IRzP~Vot9qgRuA-28;NkV2#{J*Pp=~fdBK8H1P{=xWI_PNuz$nvn*&zAz
z73XQa4dD6<Sp<4P=U6r%@8T%qFj`OVX;Ts$)gmo3xKz1t%TMo(*LeZ@K1fndEry3B
zKcCzlYCq#8jSo^Pa!c&^+0mrFV%2&@Kk}a0$}kuYFJLXUc7-#pEIOft?nDNuX7npD
zlt%<OfJWcIWiu_!9VWAh5~UK1TplZENM-|n@({zCZ20{c_!kF+)m@MnRt4_gAbb)D
zpn{?60+wQNfIToCsF}-729%1iHywukEV;M;n2f%Crv`b^vY1<s+~?ug_!G5mvFRU+
zr{Q^LH%H)zyTm|{Tn@T%{0}Qmk9)&pmWdsAPX@_Ss7PFJnkUz*FaxxqYh0zWsF3;Q
zYug(#7xv|WGG)~3G8pa>v+1#?gw4NgapuQsNJ8Ml@lq>EyKlHE0R|bfj>K#^{8$k1
zN~nwNx7F&NiAbeqVs%K03t_2^054L&!rddz?Q)sH@;OJC*(k{!vD+{eP;p71S^NxF
z&DR!7RN&x12S!ftJN+gYc)fW=(yjb{MrimX7y!5yVS9RlP7{BHZg}rBf_<GwVwPWR
z-e&fm38y25v+t?d4G+YI1ap>c>*;?;@|O(A2;wMKNd-c!JN&{~W}-cp&AN7~Pp-?3
z3ijg#jiNBbp(2d3lWBox!3}XmyNGO9->k&0MC!{|Z9dDu*vPB0Y)r4qY+P6+c;u<l
zP1N0`bp0fCt>h2FvdS8i{3Y$H_`xpIOp1u=o4#F&ygV|W=7~4-fX6)o3@;!T8Sq%B
zr|oX$+7`^?n#&Bqu+>}BWLx`?>AKcANC;+AK7^zd?zaAi^@hd1>{PejdKm`KbUh6o
zhBY#mG(Br!cnL`gHvAqROzkjQpCF?|bv|w&=qvXHyJlW-iJaG&mxxt9USd5URf+g)
z|I7Yx=NtAf0rLfM8Q;Q=VzUmfj@PPtM?`#63_l)gN!Wk~wC-o8Cj8{hEyat!IjG-n
z0E_(f0_kJrpM_GsWd)~~#p|6`iCKzNeYkxz<~`x3fb>9Vd_l?bZ8m2GG$nA~f`oG>
zH!wek0fjS6rv<po9(Bi#!y*W8qmEJxAW(d}ivnJ{f&bVG1+OQy>sx~8CcWwDk=C-g
zd`&y(hJ=km=VXv^hMmMSVA;{`Xh;OdmTb?v9VmoqL%6l+|2mIc6oV*#<XAY~ImnsV
z{tnjU=V%1W7ruBv2^%Pt$KLob5SSXKol7kadg2TDT$b>75+b#yYKzG4M`dEcS=h2z
zZwxVjrk6Y_&?<1~pru^+3@^I%kbC1?UjIf1+LJ_&+ed5ky9W^d82g%wT=`m$0fK|S
zpqJs?L9E?OgN_&_AejssAju1oo3OAiigO?C6QU?KikmcA3l%5^3s$M%$QQ}9FOp$9
z8XJO)CevS)X*R2a{skG9Yj8A+AN0(&BE92Z@!y?mXwvSz_u+AyI=;>$tt&rpE}?9J
z9$RL5Nd@FC*WSKxumQ3OA9ZknR3bHL{uV0?KxLFjr-G^lB$c4V`nhkPWP>d5-$I0b
z=sl6!1l+jI@lFI3X*=`eY1mprm7zjEeRpY+L^^t-Qjw+~Ds$;gJfcm}K<;s@6XQF}
zp#GP2hKd^mP9?+81j)Y#_Pv6GSW+WOk`4`S4_Kyq5wyX9NkOI9U6!*Mq~M4k<pb3#
zGE*$#Y@i>f0lb%+KH$E@qCf)-(jg|B-&nWDd4%xy<pq%oGNZxwz`3~TT4QJjtE9D3
zA1TxjW=1%&(&WhhzTFzmk_TA(%p9KIO%7zv77kdcZJyfqO$;Z;D~B)XYfXl_E+t-M
zOeA}(FRLgUeb2RI>EEwA?aXt_st#Ex*=M-BtjD`?%f<pIn~%)YK8jQ;=7B3oCt*Ev
zEjK3*F!r3M9sO5v;Wsn58|q3pN{Bf;Jw5;sSu6iq=t!eSgtkW$<0B44rFrBuTT{pw
zb}dT$sUb%+iD=(dRJ~-23k@o*W&E?Y_R~2rs4Vw165f6fK^{8L*)!B>35j3c*cI=X
zI3k7zB$5^KTqp<^63M#3AcDVP!!x5o2XfzjnA%J^u_t)dpKD&S$GxnZq#!m5YaT^R
zW_Qv|!8xr^3_B@{MhH&#pt2q^+cknLWPz3h2&D*~fsckrXs;*m4L(0YiSXu_NZDrR
zisW2LOy?a5*35=VJU!h`3_tO_1Q*Cm=<Tou3lG15RVBB3+&6MhczxJxh++<750$Vg
zu(bevg%T@HHLxo3=45AXcdawcY(DJ-=9FDew=0E4r;ev9h4LN9s6?0IPQm$Ouip|Y
zX6{5q3BP`cL*WXb*c$JN#9YcsEJXVNVR)f-Iu>leK|%><=FMh#JS}m*X_af7dQWLG
z-gTfwIn<2+8<NfD${8&FU;;v=t4eKET6rl!5dh8WsTcdhb5^Te?uxatuwGL(47Z`e
z>Q!~LAB!?>3st!Ogr7LfWwLH8+|)WKFMblfHcNO9(Fl?$d6z{}z56SaM(6_I3NSOd
zH9-gJvwBRej-LBn<oQZShQR*>>ltC^Nh%lZ5SJ=8f>G%j^u)1J<v)Bimi5A2HD~{I
z9gLUAZ4i6%N#wxS`9qqw`60_xh>bY6gj&kWVhXaqHJHXBs*+xV_^yMj^ZY>)?^|RG
z*B^b5%8%>0FrPxk(0%)&M3_~Hc#`^cTlh+2y7niF=dr<`B}n0^rtLAE0lJrq`p1&m
ze64qzV$7$!mJX;VV&@9}Oo^Yr`4D{be0kVfAoKMIAzg51lB-rFw<6{~|8VB>6xa*u
z8_fCn;s`|7XTv;Hk{1g-%`&yw42R18d#na_K>Ix`9W%R!U@dV0kh|UL`|<9Z%*V&-
zIL~0TW=z&t6#mvZ{O!wUhq%+3(+1=DW?6Zdez5xbg(PFhuUK!&Y)Nh3-jD4+M`ZsM
z{P`oH1XFvdCWP7()UFKA{Vg+uo$$p7gc5&g35LzN433SAIqK3Hb|r@mX^(&8m1$h2
z_NT&~*QJOChqg*d_0!<Q*)L?d(s$v1Z{$;B1-*h+FX?v!AB+FJ-ugxr4<vLA&{JkZ
zx%sxsgON%8q<T804jRF)0hp?I6$gS0iqb*{0wVYOuY}i*Zbz>zg>uv#K{s}Z9p@^!
z3qXVDJoISKU@X2;f$+-?Bu*`a{%@xcX}CBucbNY7nV5yncXUUZiEv#G@)Vl?umb4I
zqT=8EjjqZ@TLQBab2^%TDdxZe$-s1%{Ukq<2c`%vk)Nf)RE`{^_j4n&|4dFd1AQJl
zSH!(kWY9vAsnxFWcaY>Kx3N)s@Hju+R*}`=6L1xRBs`&M-(%md>-6)oDEqP$DvvOv
zN5~`R3CBJDWFZS(>)U#6$c$OX8~=hk75>>wN&VnH3s%fCO29Q|@>LKo1J9ESaN)fO
z#GG>mSmrk)<qvFls&cqbHb{C~E!XR&od3@?+j6B*{oXu<ljnlR-Ym+8(ifR)OddUk
zE(uf43CFnlv>ZjKybw}>63TB|v~o=A_n&$-4GRzFMtH0)_)ox3o&tI%kKVL!_#b6X
zit=%STa?ZqCAt@0R<?0^m#x_~JjC*`wIs_h342GW^AoWq>RauGvY`*7UD#3~W&Wr0
zkEKj{JxW$$qy^KrbA)s=#xh+aSU%Np8ZjjaI_iJ+HT`8@nEk=4YG^weE3#2`C{A=G
z@t;jw5N@xzorO2PH`{${T$gA^4qeDc(7a+6kv-2%U#Q~y5?u+=LnJzoHN@>{P+D^^
zw-iB`I(Z|_1BE<`+!zO>sF;EeW1Ydz7LR{XtQ!L5nHl~j|C|@=>G0u_pLOCuWop34
zxXjqG|8)tFXD;(`9Jv?U13U~W-ixi4beG#jnnbG2cb3?>DtHb}HThxLJp@7cFAp-=
zaeU;0<BX!Z4}U{_3$NLeC0REy^|)h2Shlc7b|fF${dPV9P(?GaJ1ufiOL1*ddKoG#
zcItn`R)VL4UDDqc=m_=J@Mr#MN0?BFOePIqbz(d91pGg56~}czgeIi-cSDFO8oG4^
zqn%rHG-2yTX6Mt0A6f+6g%FAct~-x_HDGpPq)^trjz`L`#DX=of1(;kdh8(aGbJ(%
zK4dEm_pTDdh+7hlN|*eHWwG~ls~aOPK({kMOL%NTQEV4AK-+t7SS-csfo4?K5jRfS
z%QSUZglvapp8zQC;jVqF?(5RUzU#FV8sXbFs#j9X!KaDgF8QTmhUv&c!sjboGlosG
z@wZrHqG%5T$*+%3>8mppCkyCSaqfspzaSLxC`2Bu8e0O#{Hk}Ihh3<nf2N~Bhp*&8
zkJ_|D3TrS8(Lp?Nv*6ECmSc@<*<V{{l-WMCh#fyldr`qly1eXh6uY0>C-DK=rim72
zKxL`H>Y)00<W7~1IMCT;(TV6n6Ef+Yoi>c&oJOEg$=!4etX3tVL*MZYFD}f{LyeSr
zN|@HP{!hFWei^N7tE00r*0rUF2}l1!N?5(>jc!(7MJRqnkcZj}D+&rFi2;)Xotmg(
zl5gS65vDGWEOIZLgC6Ah#=6BDKLdF4k9OZEy^PJfoxMxQo?w6AyEyM%>9%1qoX}(i
z1aBWH&$&iIzmKrK606qc=#Eg=Z<B8`%YP_!K>Xm6etpGE`!3S%W_l4M?r}d@Ry$bT
z@np`Oz(x-@kwTcqSMrGkV~)@q(`18ji`js5;nj)JkD)5=-y%T~eA1aA4_;df3J-q*
zic%(qXkX*MS)2y&W@^eP^JL!_j7!$K>N%Z0UhwZndJ$GKfdUpS1~!npa{2Mfhg;Zu
ziI*9f!9ZXl--{=7dm|jS3%%LTPa19+zBA&gH7<TJ4R9`E@B-9MJl~UZ1EbS{Vp@Jr
z<pCd?B2~i3Y6V$So1E6X7j`64+<q?4NiT|(+9W>eZw&6F>RF#o;il)hVO{2fNDDxh
z31dvL1~><%cEln#$uyXKP?H^x@_7Nqj<LrTc4MpYDzTw=eNjt6EsDvS*g{1(h=&tz
zuqrXkAZLYraz=yvm21QF_z{(7I<ibxrk?kU97i>s79PdMD>68X6@Pw_K!>tTHeNbX
zr44NIQ2MNZn(N9Sx4F<}-xinu{*hSg1KehGgJ_IMHls4WJqaWAZt`ZpBpn~FJBRME
zEiPZ6zSz2>39}g0)Q0L;cZ2@UDwDju{XBwbkm+PliH5-+WtZd=m0uPwx_nF6#|T@o
zCSNp{tMol*MO!u}mKCyX`(iWu>ncWrJ;i7#AFGiHlsdS~KF2*$7nN8fr;ZvoSoBR-
z2A%!YtSt`d(JU%sWC9hj3Y=HBj9wG&DgJFNfgTiNA?K*efrZNJK6azW)jvxbtj&$6
z{!O5DKRWxwJkyTiu7N$-(@ej`Z<S->+?cSR=9e330?a-dRpet~EF!f_@{odJMS0c$
zY5*K$KG{1J()&V>bXWVon~;2fvs7sVM;;TQ+>{x>%O^Y4BUdfDxdZjj$$3oQ+y3%)
zny_E=7h+KUx;Xcdy&Q9SS9F0kt>ULCtSFL1#N_7=KH_TTIDdxG`_-AnT0q<713NIZ
z?)TjpBq-SPM_NkKldm3!%{DlJCoFsa1ZR6zTkQLnjg77aDA<v0m#{6owYsFE68QF8
zMS(z?N{CR54_4(yIaXR3S^?F#{AmN8s@{{0uMt1eeV6`%tgxy{Io<sdW1l>A(bb`G
zqVj`p<6Ud|Hb<sHV??V3{6PBm9zhmMuqj2Alt$(^JU@WtebP|&-hKA|!(>U(2MW^F
zR#NlSIY?T+RguXNw<e|@(r|M0lbMi@&ZWphb)6(WXsvS@FnwjmmI%U7L?xC+Z7Xb(
z$qHsv0F`hfh#QzO<*ppWu;x*$V*Xwn0FVbc=+=7OF8(W4{^odaOVrBMnyzMo=cRd?
zz%6lDAhQcB(+B$Yvjj>4jvn}&k7om?X}PgXhP7=}bS36<;Y=z(BWz*BhR=H41@=@V
zMT@J0rGujLCvfRI+(R)<pMsQ%K}^48`m=%wt2`-D0V)YGXNaAJY|n3e3I=p{+yMpR
zsff59-v)S-JqJSSt;VC@YCGd|@0cSq3O+^a(0Oj{)>4#}9A8nwMPt3TbqwZf(9_}O
za~U>6?=ifM2^Z5YU%%5`lrbPw=zIGpO7nMLxN*IiTM`k0X>doP`*bMMnxzyZ-dM~@
zIJ?`xxaO$or#;t}mWuHiNVk9#oRk-`(6=AMTsB0+KZK0kzA;@m&SJo-e|9a5i~9Jh
z`H?Vh*l<;K$Dalj#B?I}8@bs{T+zq=X9LYy{S3xl89Dy34!&I)=2<(ex4Jjj@hi+T
z)^z7|=gZOm)~d!$C?6}=9l{tWcYqUH+CA0823ou4^-`jbTWnwtcgd#`(uhJPOkYmx
zk#0?-b<#Qi^hUO%aix-~$6kt^X3WleJd<ZE+c|kWC>ggF_3)gJg%Fwq1+#9v&5iGn
zr)@mYiI3=<i{1_1E7Q0@t88*Rd;G@JX?%?jh!&ESB6G6EP>G}<-e*8uZw{M<{|?pc
zOrs7^7!Zvu7p&kqq72R}-YTP*faDt*K=Q~P`gK939#BKc-E%nRstKNe#)QNu2rZO7
zQVM+Px`T7};pERhr3fT}xD&L{MC;dE@-s-9g0ecvOfoq+h_{rO?c#TiI)sI*ex(hc
zSy<uCmRxycyiSo}iOg$j>~h8b`B!(PG=bmLBeyvh9xLteG`v^_(P*=5`|yu=h~T?1
zY2R|V@@y#2LfoSu?%eszDXV)<JZsOq7e*|!&93fe*at~=y*=I*xH|$@!T{>d__gL$
zoYg|wF745IBj)QB*wBZMf~@!2{iT$;c%Zm#JkjRGz<!>mY8BiIm^=>yx@Hz?ni3HM
z!3~BA`6&NCbdFZVLJMJedokBW3a^|i`%f?O0<W*}ax(0{1qzy{ccj6pc=7*K73>w1
zsl}Qfe&hQ7@J`(ZME1-oD<)d1UOj|_4T?N>15)m484`+YF*ZXS<CA1iCEas6{P)1U
z62RH<_`T#m2_rMH!W{+~6lk^9TuIR@V%qQ1W~1b^+)u5hVuwP=78Bc}ufPDl!zt>t
ztHjvCF*z^%j|^%`ZGqIUcQM=uIxq6QeltZAtrsQT06iO|KvC1s7dtmtJHI6b8ADdT
zyW@5z1yCCOSwDE$<@Vqj{37gqZYwRz1-4fsGaV%w<$d>zp((O3{JGIVw!Ut@VW?Py
z9iu`mw4WZ*n*Yn#$w6W4b{<|!RnW&E$i`ZB%csYnkX=Fu7|KeRdDWaB#1#w8hCYEj
zofr)cyr*VFr7G~ZKMA5KQs-5$qw*7|gKO&~a471ZGf-)DV5UFzIczXP9Q~9u$X7Bd
z;yhFG-hUFHeq^+Z3>>T@xMVK>ZEiQg6!Ru=I#LEw#N3v0wV8ZmG_sLp;zvZYSqC&U
z8{f}(BCd;M5A7caGc$o!GJxzCtna}2>Jzrd)tfPNLwNtGkhO8w8n2wa@iXydmsn_H
zgZAjI+u<`xKuCX(lG>jgwdf?=Vft5WY6~9BtL4BTGe8f;FK%it;>Au3`jYX_bo2rM
zb+YaOzZ-yjH_LQwG9gZ@bT`Pj6*V#5nUeCwps!j<65rBH|39v&?Y|5j0=}0p`jYcM
ztPGFvU4sT-4(0q>8=%d3X9j9ob`WiH{k03r43w#G{tqk3A?S6g^qg@0@4rBNm9g?h
zoK^^8#Q@0R%B7O7>aQHRFvhd_X3|FvQB?~_R$P>nTWWYl@QTkI*gJ{=v(bxG7>W#l
zO?uyx&`00u&}X;=D*r-@j?9Hgw<3jHS<U+lGLX+pl7Ykl?@3^>$$O5R?M+%u$7>NN
zyHHUklu9Ah&N_6KnTTg4E)gNaB050{FAw}P_KI7s*~1JAuFM}Df;xeiQia?Ng9Fc&
zYd}-a9KdF9NLIWWZQ2hRClA0W0UzVb6#0IFq3+?6nVwQ^L!*T=uJ-;DZylke46;Er
zkKAktrJl7=7o2YY5SNGp)P!8Jec9?F&H&5|?_1x{_~&fF`I%F`$?)4!)Fl<^yVIHT
zmxNkLcgDapm2(F3Z9LFl^qmSrQr_bc&ZgT$pZ9Vhln6vW9TP$K&Voc4?0ps1nykB$
z5>dkbvwV62qUv7`u{RoKA6V}Xcd5|PUj@^u288hrkK!Qct2pbT@9x7J<%KJY**U)U
zQYJR0LQ<<~@Lvr6+Sl;QBU8R$6rTxy1Ss>Kmz8s;iQl?j75+L@f5RZs+<@!rEB-{c
ztM>A(hpQ%N6^w1+E33A6E@X9}0il{q=M6_SzR@JN*I{bB2%l##0Aw3%iBF+`<!{p0
zK~XKR6o{+vWM;Br2Tj&%MmU><hp+)#j?U0}jFGF$Q?8aVV>~-%4keA42e(s@-h#w3
zmrLO+pyl)R#>3|s{HHqTQ+|@OU+#H{H^D~}+wcC;kjV6*i703bqP6mT?ZDYhGB*OZ
z$6)RJRj!r%JS}FKOp|jJGCk$-of|#ww#yTJ+MmZID1KSeyKeGO!J30<2aE$iSnO<B
zFJnJ9s?%#chzF_ZY64aVrpKrzJA&{cZYXqfI@AHsy_*OoL;eEz8+9Imq)LJNkp~5K
zL>f;_@9f@BUVJfij!)kA9~XeGb5F^vSqBgU5rB6B&`$ti#YCN$dh@lA3hTIvXEO&F
zn-KGK7Je+f6`b+Upzw|$1Tm}myVxUNLClsa$nHNZr*UoRb5_hQPL^-ybHJ}!m>c>}
zIVu(0a{3#bUln3+YegpzoYq@qJJ|ik%4YmSQmoU)-{_m?0MrO@>1zAK<7hz<W)RlN
z`ab&*VmTy17Te9kAn&PGdEE^u<*uzE__{j7Rq@VNqu6EtTl0s;%B=d)=Tj@yB=fiU
zxVJhjhGPxWF2`ICo?CP8yInh2m@sF>7x)DFl<T}5>=G<bf*Kd`$E@Hsu0P2UqzMIQ
zia&gm_?J4}v#nkz1DhpEeB>pn*nGYIh1BaQ;C{3cZq)%ZXrYe}7cgVjS2cD0+*6m^
zj`Y*m)8R@hoIk}umT5i%Je)}K;?;8s=MF8rp@RJ_X}|M}vNx~0TyFfF173Y7uWqh<
zh0UByFI9R!Gy6CCj5vT&Ixf6-?oi<%ta<#g$_jl8-?>?;KG}AY;)5Y(A?+K$wYW~g
z-}wyZKP(IfsW@60!;R=Irw~LM9e|>ZG;WA6&(M$-!~4szS}LMR2t!2MQf(f}dC``P
z+j%K-*bHivT(?8H`=AV3*BHei`qU3_p`-&~pEc<0Jw1?;R$SnYg8$T0C%${bC+-cY
zn#@=Mb)<gD2zUo0$e_(qp28MSh3cxC38`>A{{#C_uDl+XLZ#|GtoXgGYn|F1irDJH
zjU_M>kr1pViUW8=L3G$>{aO@6@NXktoWTvC2PUAOlDXkJBs3&Iq+DQj?r0|0gb+L#
z=B6JNet2zj#Gi<nO7HQve95T*HOPCg*)<V`L5{6!f3s1Pg)Q#@rKUh3MTg%7-)mnV
zd7TG~s74$PhWjrCTl0jqdA_-7Ag>TCp1}!EYUs;2@PAl`RRqGLgJq;+E;M#GJr%hY
z4Zz;-h?7FyMQIGO9;ZdIW6Bc9Lm#l1ic2+}OH+lczi86JIR%K6k_IWASUuP8-XQ8H
zR<{yYgmUfcSduLYc&#%4{8$P%W}4oe#QUOjyV>rC<h{W7)Pm9x;KVLSO`IVye|<(4
zO?#k%sEfZfPk(8|fv@Oce3cms(6qE)TZxqliw~o^5ly@hd@sB;WItO<2Va1zO4&hX
zE?PpTT~4m1+D=5NED1jOJ<*}{{lE>56}CUqloE-XoyTW%D9A&vx<kOv>&1yA`z>*a
zPpQ3kGd^~5=!NN&<;<lYHjcP2v$rnwACk4!n49B4mKo>O9^Oam$8<YY255sHiYr-9
zJQuiC?JJ1{flc8^PxS)~!(JAa6)AT4uXz2ibhnpr$1D1w@Xc3F=xBD5J*ndD`M@(=
zIh6aD%WW^rO1mk{y2BY1Q=a>G?j$8}TuMkwBsHi#!s;Ydns)K^lnhgaXgiQ=*`{*0
z5qjtFe0L%B5tc<Ta3WroN#Ak;0*Iu6mXnR`FN+3qwJG_;m>fJVmZ+ll{p%HJXq3mX
z{kyy+#49a-Eqs7~Q-ar>>z}5X51dz`;YHTX5&WD_;}oPuaJ#3%U;+>F6zaMrWnGc5
zp09Uxh2`h$ZbwGFJ)*>ZEeK|ODM=Q;VK@*|Dsh}t$c*k<E&)-_JKt!>Fl+GSom!S|
zIO<ibKiv@}^eHVCR6q*nd&SD4be|&4njnVO_71)}kZZy!@j$K*kc*Rx<$f%ApuTW-
zTKG}|IRdOmpN7IV1__`?`rp@`z@kDAgJdoL<vegRvW49?;s~wwpF2Z$?UMgVof&UM
zA2`t6Hd9vt`~Gn<?CbQMadsO`Vjcz=wwf&etKWsj9{1i*9wjU%X&#c>O2parxY$-X
z6b~A%#fOn%ktL!D%N|F17q2~>zzV>YLB1{3n9UT(*=V!K#7V3TB9q{p5Os=u#+3N`
z8Eyv5Waj;1r;eyMP8%bBYfFNv_;QYNMX|}#clWX7fVjkC|B?q&C*l@Qe!<C>VEyM4
zxm%8gJ!8wKhhJXJBW9~01*Co-40xNxEB7Q7Klq&$a?EQ9<z$=Pl-RXgvdOR)h+I!n
zv;ws!^<+qowyl`blP4kduTeSd?O!H!mecsbp*sXwA#+0+kMC!>yZ$nSr=rWm@6X@J
zbHzGmiA}x#b@?w$mh828dl3|&rtskO4o#W{M0dha3NAyC!iy?ImAyOvpAx29YVbta
zLCY)8B~h33Sc~`a>t<>xi!+)n6};;~^6A^Q<vWWQWp?0wlFz^XdSpX%$68g|v@r0g
zXThC)Fix7ULZF8j2H#8om3$r<ufxbsIk;rXgT!!#^74oOjT&>kxhk9L{?h<z_{o1|
z9(|tMxHF&WHhy^{vFZdmOqIqyO#s3&Pj{9wGkgsO-QP>S$_({&(C2z&F9<65_hCyZ
z!$wM#VIROm4W0B;ALECnR<gl-d}7aAui48f2v<UwF;TmAil4GY#{vXc!ehO0JPPet
z&yZ^#-PD4AZKDg=u`kQRdx-s)hG4SNr>11rTS?~!(lo@j+!$B46Ls|4a1gS`o@1>-
z0MN9|>37woB-tzqaWt8)b?BHiWpuL#6l=eGjXdy`egIUWg)B6ak87X?CCyO{q0sRA
z+dSf<4KgNAwOnan-&1KQ)a_<jv>&^Ir2Uj*z5S309-%bhI=o@oh{IOzcxOSo6_d5g
z9W`KZ!{(I5-p~opXJ=}_5^X8I$z=a1x#+G~%nkU6tm7$ed4s762Jnvm+QOMfY`=ot
zTiH2piSbup*U1m#ukr|t4tzxInM@qjt`9QXui9h$u~B-eWp;fV!dU-d(GYN-IT!$D
zUfyEg5n4J`FE1tv&NVES&!1LUXGk8_31HW?u=U$_#a>jkKLDu!Ps{_2G;ytY;QB&^
zR*mN#FggMI>@PclnhowZBsM(Rmy5=#2r_Xj94=@C^!_oU>6X*dIE~=_%!cLsS%%G`
zSP2NFY=RoR>Nih?8%)%UkPA(IXOV~)8zO?FVdHdfh|rxwDf>D0?w?xqtt+BuZ0;Wq
zj)Rs-6XyY*%#NF5$viQh9N7Gk0DKWBS^aY)MXSYu2I$32DT{b(Qt<H#+g>{`748;n
zvK1?U(qezNZf1Dd#<j1G+da2)vYZ>p0N^+7^x`wdLw=EQVV?R|gq_`Eli@z6AXsKG
zK6@>NU6M<v8ZSKk$=|tLvCn__6TTt~nmeJ&p%P*)bbnLg3Xb}i+#2wegg6C?w-|Ol
z!g*3<ouK$OmClZKzhjEwypJn%>Yi7+L9}cALBl=wCe)x1LS6@JXS(LB(?f-21Yc={
zsF3AGGZy^0;0zsK)FiU28c@2tDK|&Sfz#j|yT+}^;)9dxO}C@AR5VxL3xF3){bo7g
z6+x7eq)<V%SakA%;uTFI1vfe2PvGP<Z~TX}GB5W-34f&52fT(@&2|P^3D98zwE{&l
zpuhYn-c=qu7D5@|pmb1YlQqTSWrX3*rduV(_|}e6%~8$Ft2TGs-n(qB45R@DVyALp
z&Ga__{4LtgCM!O-*p`GtYv{XTJG(&GOoZG*;-@Y+JtU(%_cWSbplvJn;Gb7b;^j*l
zaLqQ2SsaJa1R)lO)wm9`htm5SHnKyS@0vs=HJA=c)Kt``sx;Wekb)E$d!>?>!^8G3
z<8GtgQ;dCArLMJG?J$*}H0ke&orDN)CtiHEF!8n`Y%L@(@hx8>TTwK>vO^5eOw<g=
z5*<xe4HeI;2%H5|n*l>OCNIhrLSny#e)3&eu8W3ka91I0Z;5zLu0%eDAIpy@wFLwJ
z$|{j6Ad|fR!_q$YE;6T+co7(3KF~N)9hH6Kx;Ytr@od0bM(u@lb3&0?@Ieg_+Z%*%
zXET56pkEEP^hE<s3dmw%8NDr(=bgt>AQz7CSzeB-K}Mi9fDQ7(y3#cvE88<u{0uK9
zBdM|zfVI<OxUpk^M}-f4mMmm7q0WAATiLpZmwn4t^%dye!ZGx~&)J3d(_kSf$G%gU
zKDYj6ZbXO$2@+wjZu|1H{y7Zw)Tue{xm#c09ghf7s!WVWab21&#C{HxJq(FcNjXS#
z`>_VoY5XCn`9bK6g*y(x>((=%p;;tAAIWStw%S5C<;DGDR%I<K9JNuSjsVLh6NCVM
zO<R-WzPx};tjd2@r<31MfKGmC@LIGBQfaS=QsZ<CUe_F-%IbfEi_-Quk^dEHYh1%x
z=Te~?6?KVw4d1?GLz<#kpSkqpyHJ_c4m>Uq2V+0ptq=d`AL5z$g`dQ96mnL61>BT%
zjy9`L`nX+Gvq<LKkD|fYwm8=qcG_3IU-1Dz%6rhkK#=--{^(01a)Q&=`}Hz_B(Ief
zlLqW0-1b6RzA82Y&aYwGN}Z(g2kweLtrFfCYAHQR%|46FlZb5OAb+7}gZ^1MO&)bm
zNkn`9b`@~__ROxidCs30R)`dP-ygdN+}Y8hwVEW`!;_a=^1D4<0Jfk*a@(1jzqLU&
zO_TTUhfWp}kNm22R?JM*8M2J%>Ecsfy-{SzIcH6gmVp*w#cVd$^R*C#mD-p=^ykm{
zzXMHgPrIV{{4apt-eRm^1>R?pm7O?WW+ketIYGiaY$6q1rjVTf_*;2Uf_sVbtjR0w
zx_zLoAg_JHICQmSR~j)|gMKBaJ3-h8-n%8*ar7GDj}lI4S%o=abYLX=U8{hGjw5WE
z-#VFPMj4=}F0d;L6vP!d<|O+j!51b!{Yv;hHR3@0EN{nqWqm^|2Of|R!QHvLY$v2|
z<nZozseC1FqDCZTPXWjyc{>Nl4t7@7!k}YsEa44<v=k>;DdDZ_0e9FzDv(Xg*;xjI
zuO!JK0!5tOr~PWX9ZezBWBH|L2PoxDA#1|=lC+Uab5W3tGLxP`0?0(TntbX8BX$ow
zw<ige*sUN3EqY^4ET4S;<&p>WcG>U)qNIuycf&+SteNW+K)O}ET1*CbL}i*$eCeP)
z@!LsYjsQX6${qjj4MJAx%m-vR=x!*X`a6TjGy<iH*Icr==7PinrHVd_rJ*qw*e3Un
zJ{H_5LcRih%*gw7!YOJuPbW44$^KjCGJ^ENXXxL-#h*h*Tpo`~D1@lQU{oQ{nVlsT
z2erMn*XL;%qP)Mmr4pP$4@xWq6=RMWq3t^*#`;L%?KKh7?HVvJv>ZlBf1s&9NoY6)
zQ^EQZ@^~dFSXyXRn8Y{pLPSP)F|o19M0spE9(y571V9bw@y%n)f82hI%F@Qo{rr<m
zZsloLa7q~Jjr!FxEB|fj*t(L-MUm;vGsPd1wM-j;)a!0N2-o__Z9U^f8fo`r3@C%R
z^rkqpGxWHRY0}XyYVugJsG~h;I+4u&i43-Lx;pr9A@Q!kq)CfU6t1KVxNoL%xi-n^
zBwIhDCXDb;d^W{sC=vLaVLkh?-pL`S-iJg5tXut=>1dZrG2DgksYYJw@7@O4k#3s_
ztHT{Muy(PF{rrDn(d0B0A~{EfSoK*ETiaiOyKgE`%A)%i7`qeb9IJeZPRG06&V1hJ
z+S&()6gP#e^Djx$l<Ws+1sW2F%JuGzU|9mE0|&lw<%<!qJ>%hoNIOCdaU)|t0*^>p
z96{B)u|{#5XNwayA#6!53JcoK%p@;2{KAB8a!|*ZJ)<+kh8oBFmT%^;X`=Vz!t{K7
zjJ)^TgGPCJP%c`yc(^D4xs<m2<8BbpwF0&MV4oib8HaMD_P#m!XdnqwvGg@Qy)qvy
zggoi8aE;Y$WSzTYU*(ApX|szC!La-Mlr6nwusf~VIZYdDEn?U%Tzw|S5~dDX$Sim$
z<5ImK4NNi+nQbO~<$|ro%C6b$2!-o>)79H+&A4?c4ARum{UdhEPep1N2zt&MCJ4*`
z<o4_orUbJW(B7t=NdlEki(Qpl8RAvZtuA)R`eRwx3d^gRXv|YaPRTQ={aCYo_u<!H
zPoaOyLTAXyZ_ZDo<KR77PQ7MgAmcQY$jEehYZ7|<$A4HGF57_>ua1uWb>|&))<hR@
z(4JJG9g=J%$M6LZZk>H{;M3y7z-<hf)z9kk;Sj`Hc22|C;fNJuoq+l4=>cH(;ws27
z`T_s;w}d|m44{=@P=it4YzFVL_Jq5DE*0nxVbOyQk7<GJR5kL12C@giAG*bXl1FjE
zp9q0FC;YLECV#k#1G!XJ29oXqb;AY{r01M?<qU3q0~)r<bMRC1c6tQ$San#yvM%mj
zx&N+c$ww+mHL}b437OHs0iI1-hM@Yu>VjRrY8y1ett4UKy|8d+mT#hJ(qfyx4sMZ?
z&hX9)_#Attu(~8UInau4tdA(TJLDNlR4N;ZDCdSKk?bkQS35U2n{B)es4Yz_%de4(
zzo(}8UMO{T7=csskJPYE*$z6JP@Kz@b`Ys4^gOfNoBZsRzz<vgj^X71949HRFR-qQ
zSST}KsGFVHj0B+#GH{cK`zvgv71qhAFWR}%JSo2NFq3S+EUH8Ee2xoH4^b7W(eYtZ
zEu~}e4Wq8{Zufv6nsc?nl=3pqSER4zc3aYlJq{Zv1h4#nq#OE8U6TO=j{L_LK;R_1
zfm`z<amWqen)@71k*Rw#ju&#8X?#q~=JKbA*LM=jZL29{8PHlDP6=F(?P#)4PZ26W
z{=*W+<!Mf^7^UHapzRV6de3oQhcI+>(oDct+=H5Rl-H}6NO@qtCUHeHnVgsuNNkvN
z`Vk*ohbN9?FzWs0<`j0SIS&D5x3NUEO5ds$*-HUy<eo0<Y29LMOoxX6bblKCp=mU=
zaA(^PHVZo(Ve@-H5Zr(r1w7l0>)K8D^bi0^rS644YJqo4yo>)Osp?lV;Q;`Ts+!k+
zaJikqw1eSfNDEDUs3iqVy~j0jqRWLYs=r%Jz*o=Q19anWC19Uf%{^kVHi7n9r!Q_|
zi>{KSW<~lhrd*Z%_pOuTZkyp3#R;ma+6}7okoi1Cp}U`zOt4&zyPSpsqnSkUkifF)
zIJB<nsLz1X=0l$MNb=N&tb-AClSxc<GhW-!ewa1*<F(nl<^Y)amp0uEvuB{o*q}P4
zK=tBdx&f)SaiJ{11INBph|ru9KSpD@ZbvoyjXH37`eE@AJNLNSphrf|T-zKqRBTM=
zvemCbs&Y?@RQXJ^zuG_wgaHrkgQsQd+GqaOmTA5zGu(9<4)4lURO(d-Wg@HYgp@n<
zv9FU8iz`H9oG{&6R$L23EZpf^v7&!O^QTqr2;R1jzl7K=8(uMO{HP8T=Oj_|;eeV_
zc30`=9IrXs(Z#xa^{ymL+gZ{I-R`Ot=7PTPzvNR|q3`0@**kV94AMEqJvTutWfpjB
zh-)34g#j$p$AXW0X&t4_T5qRE)>V^-h%}2dIyt`i872V{+jDri%iP86lxsIPqr*CY
zV9UDhwynV9f>L&wf9KTAlGa;eZzI-Z3dD6tQ}Tz8eT_&*R+O#Hk~9x%0~xZ-SKC$b
z(Rv{D5-_B>a%U?(?2wG~U$*rTdX${dSau!E@de(=1H0;MgGUd7jwkL)s&hNY0qZ%=
z*2QV1qwCX~fHl3|?o;ek0hVQl=c@-%$A#G!Vnsm3(T%@&f3uy$5VvmfUhJ_*$TE-}
zzwqqlD{S20S$g05+V%{c8q5<%a-+Fcy1Wmyr&Y=5QPeenH_x<v>lVIe_!0E5&OAHR
ze@!PS{4G>8i}kAblQWETuhe5~3Y<G{9P(OF>fnDIon=6jUDt&P0a0KirH4=u5F{l8
z21L43LPP}Vlx`4^W+(wiO1hEmZb|8`p?m0@_dCz`k3TTO9p~(`_gdE?*qPe{X`FoH
z&-2mUQ>R@)5FNX!j-LNvT)a-ivoB#BJ&Wu88eJXa>|??8V0KaGsq_>L#*ln)lvJ*z
zmD7fF^hT6YqR88P&W%qxv`aJ-rnjfuVsaz6ne<c*1O`LBWx^Rm!6nXLgz@nv5SF$?
z;-Cpk{=J2)$vE(}Y>u4hQyx*Jr}Jc(rCe3U!?%v-Oeq3{wB}f(XH4ZI->|=$8ZPx9
zS{_T=nU9Pm`df*YXEJW}YaS_yphHEJ3C&-9%XC6l!8=mHM)Qstt^WvXV;aR3ntn3I
z>m&VNi^?oK>*)6#d-?H$mx5HGWbMZ{Lms3pmXS?qFUHMAlD>Cich&s<Q^@}Cj`<57
z&1~pJ(c{%OEJkUcUtj`{NkaShUor^syRG%T19|WfX(=H%U=ycCydvDm+B}6Wm?iof
zDE>56ZX@BDa4w80Qi|4^OXTR0EU{pysEuSA3O*Ymdg-MUGJ|+e704Q9$GD<bd!_B+
zZOF1fsdD(sy)<}jJbUA(Pg}lsDm^KjP1RA3$fHT#)l=^fyVc49^?Wz_W!sS<548jp
z8}+TG_Yjm)I~wu1d?=m7$RFE4HqL!dS)6f_^7V`wq!+RD^K5y=J>iBr;=mO=(4(m7
z96gp-7fXL6ugRU3Z5bxdr$h<<hcPd*7@;{9^J#$U*;ciJ%MgPfAaN@^_!OmTfW6g!
zfiKxGZAweRcVNI-x^s}80<wW1fRg2VE#AtB&C@omd%B4MAhm&pHi6Hs(A5=7Y=6$<
z%f9fBuN84=;c?C{1uXQxrXFzI8ss}t;BQv{KF(ji6QgXAP7b7@qRVtUt;dO7G#lZP
z(MwgBU|OUMzu7^JCvB#P^5x4%oq+4?1M&tvw(jYbkO2zbh8%(e7VDaI<RQVYi13nu
zEyPg+^6*0i;YnX-*;0XOxLwFy1A!M{f9IZ8P&^pPb<buTSjB&f^yqa^7Io)`UR%jd
zfmv4&T<7aM*MDc1xrFxmCh@d>64d@L({Z}%f2ILi>^%90Pl8Tb^Y5o-aOC=#Tjne$
zs#hAF0?}id*ivX>Yu&GpNtdxg?*z@31qXSCam;C=TqaV7#lDSWTaQGWj^y)WmbTFS
zK_h8BCyFvGL5D^M_QUv^p3%YaW!fxRXRh_IJm1LmD4t9MeTw9QzsWS&(Y`GY8F#qo
zy>&9WYnraUDZ$Gu4M9{YL%j-qy~zUmw}?;Nx(ytrPqM5UapWPjYfW%vhSrde4Jp+H
z-9}b-)th11Qs#=Yg>w#`ljQZd@>ERo%E;|(G2_bYuOpbsW{weVe>y_@o{eByBr)#i
z{YHyVXg*YXOtQ^=*sp;de#iLf(x@O0f@_lf7cYYh)Be^?De@Z)Ij{RS{D)6U_iw0&
z#R)#F4=;L}<%M)Uwwsmz;}gsh@^v4PcR1STPuE;nj9B$Y*-wvZ=U3%~9(r67pPcIW
z_7g2;7xY%k4SIMhI}|z+1ib(DR@)3^9W9y&`(0978GLD%?89C#S~c}~OflvB0HKc=
z<E@Vm-R^b!XhF}DK=Akz#JHgbIp*yA;7Q4O!7rsTa^E#fZAaR{wAabv;sB{YQz9&?
z=f!i)h(Yf^{f?9W3+qP2DcLl&#CG{Bq{@mDWX<s1da-=El)7JsVqxt&2|Q>0JqlY!
z2`Ycg!xvr$RKn&#)LeKhE<>j91QKuv&bpP-`&C>DTa0cfFWT+{1Q&WAOB$oG>8uQ>
z!h7skl0Dm#FmvGc)j$mXTslRLHGD^j$Ki@D+*4!$z=BlP|1gkMT~6s=rl3vr`|<#I
zx2Gbp$Rajm3n$;%cREd1jTwhW6wi1Uuueq3z@`wx(`HzQ-CuZ40N&uP24-{U#e(&R
ztG_t6F^$NvqIAlYa)b9<llgSv%pFN7NijZd)E37H`@SAA(dSmGPa7kBk|Qrze)~QB
z06ljtI3L2`LlZx#8~A<m=ogw;fEg!RtXvK3X4*ahXgIy9lG$%@_K66S{hh{T{&V8o
zG>8h%8{3=zkijJWPR($!B8ICh9gY*3)^DVMh+PWwP0&bF^?VxGapXMPmd6EuR_8IM
ze<Yq`cn^AFI(r`^^`V?f|Lnc?+E*Iob98=ehuecJ6DmlOto*1;J1qu(!hL%RjBpg5
z^MNgv_~$zcE6%pr`t*f)bXI)Xa|Nr+*b7rnFLWwUs~bt%)Cgxz6`ALYH*TI>%sJ7+
z!=j1Ard|{I2peyTko1e9AL8`QpJh(+=-kv=$Qn!%lVQG=p}X{oSiX1IGt^OsXLUCt
zB=^>s-q1IZKi{)9%cYSd9aj0H_M}H?I16{!#@u`9ER>xTbgzCAEv;2Rg1KQ+@PfSV
zRhRe6oBp2a83QA0Vw}+%DURr&cT3MIID=f-ee#VS8Mq~#tOc$%T1=o(@*@&#h6IU(
zU)lO}RgLd<Z}_JlQF$=eum@2;ude5cI;heK;`4wyBk6`XaV4Du){R}+Ftm+o4O3D}
z&X}r+GM-U-JT1$4ZSc#Cwvl_pI2`N<j%#e33*X_axlU7n?a(3r_26XA@w_BNM6thq
zQql8I_Hcp<v$R+p*>%w1dlbd*Ch|ZG>JT)En0j_cSDVX@A%0w+<A#iQvt_3B7ushG
znsvpW=&TK$P73Hy;e_ahRsUBbwC^P^_M9DHZfR>dhB}i5p*^Zjis^l>!re)_Ad&kT
zy?d6I>=H&s?D*QJSD@u)!W(IEkw4r>4gW=X{#aHpCQ^0(z<8P_SA3&f;$QVwam(xy
zlQp@3IZTt?_u<j16gVHrKwm>A+I+^$#NA6X=H!Gpx;`&2xQxorgM<5wGrVT$#k2ca
zfMM+ZZ$~EEa6BbW%S`8c(z$B=ZTZa>^X){@Dl2C^H~nnJ-U*4gj98_dz+N%QlQ^NZ
zh;j&6xurI*bD_g&EtFw+cOXFpyLd6avH$bZ1f9<D=^tX5EKWc!`sC+z6`pWqHRE8n
z&Tuhg=F@U_A_T;Y<G%Cx6{r;R3iTt*{1(b_O*mhkP=Thz*u*ggbhun`SK|z!evTE>
zTTF||IKRBHr!r1Rh|IQBz}1!~L*?$6z+Uub9DP`=nWCg^JlNThYjDk-UF36=&Zedl
zsu?GipCfuh?Rqc#XjRSb;6vZ&(FQZA9N)+T0B>v@%cgK05k<KAbV~icl@9Xj$g3NY
zxxAoJ?SD$Q2YCHw1oj;O<|KJsHPk6Tokqyv5&W-WE+={W-@V9qbh(+xwF?{?^ea83
zT)f%}hKH~A<!@~>p-0%Ri=rQMixBPD2cv~|*_n7-l*Rm0FPUG}EUAgaVde>jm2@EY
zNuF4B&Azz`R1be!Wb-=mD?5IZY+(v|6Q=S5$oeKLH2T{wbN%c(9%3selvQjYKCz*Q
z{?Ocikb>!Z?opo&B**bu2~3k4Y>ee1@5BG3G1g<V<qVS2#x;#$X6|*Jz|Ymorc$6?
zD=80K!ErnBD7C>Ub}rdlz5rBC46}IkWd0JON?m9a#@S=#lRLRK^f_J*@PIdDz))*4
zVs#nrfw~DRdfrQgtw;%iTftC&nrx$v_<hg48u3vHFyTmLsV<Jhw81}rJOnD2p?Zp+
z7u^^fmNyr^2G#sUIeY7;?vfXxS|-}ls>`+5V*WttZfR{Lq&4S7{gS6wX1cQRAP=f9
zm1S)XuZ=wu24V~gcmGxIl9sFNr=Axck7Uafl>JYCThnmcA3G|6$IMG}9)5riqsSUW
zJtnShH&XDhf3mU>W8Rwclo)!)+>kCjL4%;_O!7BVoP~^s$D>(8XmT*&4s6tf4)Q~z
zfSwsZHEK5iVvlYdfU!I*o64)7?6RGIy>^Nc%;koWDZxV=bJp0<9o_Q>YXMQ<Bb94S
zjTBna1q7O2X0IvsC*M*#>Fr*z9z25NqJKay%<3dzHrS&f{9sme_3k%_;~Ri0Pf{Hx
zJg>Y6lLW?;90BKMBRKEQj0ql*=V-&nLW3k5&!Y@{()JqDyGsop`~pZ&aV5N3&T*8Y
zXevf2BCO@J%)^45ab&9e%WYMcY~GT@Fv7%lZZt{4*Kmbu&TJx{m;YiHNcAe*Jw5y;
zK5(CFsIcQ6=j=cQ7JiPHgWUS>f695Dd=#Mb)z6;8jqdfT6FzFl2TG;I@3-|tBA?E3
z#EDW??rW5YW-}h|Wo;|ofyV0c+cf@z2ef8PKrorO1o2rG*e{t`2Rq;QQa|L*eS3Q@
z6Ked7!GjyQOvYK`U&yom#P^4!H}gZ}aQuzd-pZaCO=QS4S(m>0@88(YMk+jVBfpvN
zIxv=6Ce^NFCRM1`KY5uImj&Bg5Y&q=q7yK3w<JH<oru-t2;MvbNnN16h6nSXEF9r2
zR?2y^<p%bdfUW7dt$~zEqaStX-rOUH*Pr|<RgE55Cf{bE@*sqkS(&RA6A%4XpO2!(
z|A#>fXn$2|;_B(P38$-z%-`PnI;S7Qcc_L*_qwV5$JZ9=LLTxRR&AhMlZJ79+<|%|
z6Z>y(y0@Bh6qWCGD5S%mQCwggbJamiA~&6SX90Z#3kEpg*fb@WWO%Cc5FxG}XO9=^
zKheeOKeP`Gj>(R$l#8#sNB}ISiD7g)_=N8~n<G1a*tU1&1y&d;l2`C>)l7UMtGf=i
zs{pD+_A_%iG#{qsHrtR>W{>ZA-PsT~A3TzqZ{7TUF09G?m9?Pog+ReY)QglO|9c$n
z#T}`lw;tP$as)LfpH41~kr>AzMwDUi-K`1s?~?Vz{_#tm9@!G9mx(+7!+5C$$-$5^
zFIrf7VH<!+yA@u&wQ%r!9>Y`H(a(}zkjp1n)Ot$&)nLk4-QQZz;5!xXguWY>!aT#t
zJ`BCIH;5*0<viTmNL3Yz@2KYi8s1^t!mAby*g|^^TgNj6AoJ1B#yxBvE!sxz>|WR{
zzRoLHGiP+AXdB~X%i8?rIzZ0qBh#>NUx3d;AY(azkP!b5gMKI7SVuM@LkMfJx&C*P
z9=+@R&+R&L!lN+!`Oy2GaSd74P&1gYG+td1cDEyvX|nD>Zi&Mcn<502<48Wo>1^WM
znFk_jAfc3mm62{j1@N#uG|j8wAKp^F1KpX>oTpfMvjV5>P1vwS5CE$<wdizlqS|8R
zRAyAG$TLmJFc#&fp?)$;-<&XB_t4qUoF?sm7|i2B`NL5KK=lZ(#qfM>sZv`a=U%n-
zFP@B0^#gN+nra4F+t=+&V?X4HhN?IStN+NudZ1x?)}C|gTDJ~mrf;|G@Nqsi>Ak~4
zD2Ga}dL;=9#yM@z<iQ{Ew0r#oCnL|S<+Z0hye+Gq8rPnukn?D<{vi(kvXv8G`<j9D
z5&>^&%DZX%aKf4f-?Qxdr#U=Ti*{1o117WOvVC6?jtw)*1W6o^G+2Z9*L*F(qSRKH
zccD`1Yu3O4rXT!)G7}pxu_?b5Q#A@M!Jw)^<R<-XzBtub7M<3OSs@{wCM)hvIr<(@
zAg1$@8lZ2xMkzR7g;aUleM%1~fc-hs?eUd77eMfHRKfQC^!_UxbN94#SaN*ex+p<G
zBlqtooOr91DKlOXl=HgdOtIdt_fDG*XU+w_ILCEy?R#wo#7NubNQDslzaP~OaLYA0
z%I7#3616nY`gT3yS@!Dtr=PV0eCDGX80gWlo2o+b+}LV5R^g=}`ib^c0|^?g9w3|8
z*E(48{n^d^3_bgA?PFN_rDax^h(f_^mH8hspe^Q~0D*Xd^y!}2)bw#74oLba2}1E_
z<Ejs{SnpG`Y|Cas@aUHnD)<lhJuy7?R9+*j&Q1d8DkaFLyIeE8|C9p{MK?IcQhI6U
z1S;yHO`i0F+IA?14WQ-z3lz`vmWeHgnX{sX0kVbp>(3LINQ2opX-33!fc!->rz`|o
z#*Zm+^=-?7X~AR(U{X8}f@^@kPO_+1ZS2yVt;$nPpjr6+I<40uj1iHI6XE}1$QaK*
z@U5aV(D*_L9C;f>QDwSZ5*TntxiseL$1y+8$i8de+7+*SX6f-^Q=031%{_ZT{>D9#
zxi{`VwKtSRhUd0+aYyN4d9l3^FR+d$pXah(!UM0g1J_>nivzy=e+m@6{%gjO8a7P5
z{U!<ddB=clOR&QZFD#fW2!h;`V!_Z-Jw*@NGhlI%@^0d+O!2FfAQYjfWPE-YW^eYN
ze9>CV<;~%->L*Wdrl@tn5;w4PnqSXvtvUa^FyFcX<RdkiooLuP-aYcat(JXPW?-4#
zNBYI2%NC5Yk;Dg2;p?tABQw3^UAY92>H`u#5BIH|ZiS^sk*p(bY`x9zYJC}8X)-^(
z8SVY(eZcE<<D1|Q+V&XFo343PJrOW`16&>J0`ZRy>;{i*)p2)D*3-^wFnS(Zy{8Lz
zZBTBGdlF}Qj?<_ey3X@wAn-sbH6&4;IPCna)YCfmyAtzjMJGgJuSr%5{)H6RG4I3f
zujNTkAH2b0pQx+?5+!)X2w9?Q<K`=_#iE%}KF~CdgCyd8_H@*amumLVyH;NA@Om##
zcq08MOVp%Q-}ENZD(@-r*8OhIXC+zqez)7*x-0E?be;|A77d;fb$JDa$xmz&tArbu
zstW8)MvScolNhj2{#&P7bNae`Xg9($`bm0@{C#R3<UCF9VzFE9<(VnWb=mzqLs|x9
zTguB26R_~;Y4=4Itic#=qNC)gW!qi@)wfJiI-J^~lj!ClPw#Qv_mu-}%Qg$ur-xLE
z!eI4qE&jDgX_EX$3`a>onF4mbsai3LYkgIt^I7Mw)H!azn%BNJ!U@eVRb=h?&PM|8
zeh!E=e3)VE@nD#k%?Dzf#1!)`ywV*3sUJ7L|3tUHw-7N-&pIwisg&*r^pRZU*z_tO
z^b7~H*g7)fJ`|qMk1E*fLhifYu}|MUuQA3ynK3CZJU}YiuLRY$T7BXv6MeTuuTa+f
zLj1Y6Pn(!D^ceA5R3dMCq8C*&)geW7Q;ng#;U1HJofxBkl?<rzrqHN&-sTR=C;igz
z&^%2K4x(RmfxVoIP_T>h^5_ZZ;F|0aM($#mj1>rmopUxe<*a*ZYIf;Y{amC}2ejOY
z7JfqIP*!z&B`g5HqG~pKIelU>R{8706xH`hpKLc3%ZP%#IQX^oIsRCH?vyxn61L0P
z*0$xqs)WqP6K{YaK=hxU*U&bt+-hQ5KZ~K>fY;~ZjviO%uM7!JyRw@eM}<N8kIo2n
znF#IFr%b{f#;a>LA|uju_`f@2cg!iI|LnhMeshZ_ExppCT564V3)QeQ7<%AGVF~+F
z%}~E^=P7_;=V!d#b)tD%z**JIG^hMeXu*AD>Um9sZ_>kY!M>LBM!IiYu-P5C#}K+=
zA+BEf+zdg)XTO0jXXGzy%+_G9o`LypS9-^|GH=7*rzvaxVB4&!Dr-1py8wfOce0f3
zCqB5=oK2+9Li;YU@kX6<R59~KmxONAaO<a?-=X>YE`a@Wj^8{sJ#(`X?r+<B*P?hm
z(Z3QQG>*G#e|wlr0grG_o#|Znt5gRWlH5KM2`d+5fgKc>u1P|NiW(679V_m!PdA(X
z)M)-c5_qv}!uxFL$EowbAJt@UEtRqcpSfVXvFk12u+S%Qye;;m$an-nCfHxQB5Rao
zL>(hPPvW)gj#0~e3q<Q~{<=@ikexIZ%3Nbhr%rJsFhztl**j!0QTlwhmXpjV7@l#B
z-ppBCy=tTXAim6r@d*|s@Os0fcI(fu6(5pN_l$UJ+_E$_Z`8zaFy@7L24I(sYNci}
zpLJuJJa8}5VU2}nlB(B62*mJWwjWjI*o#;HegWf!*!+WrI!j|e47#|s43748hwCSM
zmoU;7eh<vIt}wBw#PE?77_AMf>fRy!<n~xy5O~LCqMH7F5<aTh+o-utdUn=Fs~K`}
zN^scdJBwS}y2@LQ%><iD_O>^x?=TBU=9OFn+GW-`)p9FuSL!|NX0rvaBcYP_s4kqZ
ze@Ku1|FpbD8t~Xx3p0&B$|C+Yj`Fmr8lZ12$5ZH?26M|GwCl*e&pueAOS~Sq;=>Zm
zbr~{WuMD)E>TA}|uZQ$i@phFmHecS<@{c2F0y{dEFZ)4AhIXMi)@*<61cwIY>dNii
z#zy4*3vr@`1*d01^SxvxYszYDT_ou~-?ONvD*1vHJ)X8GAS8rENnPsY>oJHjbQW`i
zFHAerxue&$cuMnl3wZkiTddS={b-yVnN7<0v7{5mWB9zo{T?Z%V!f%;<+E9MjoQ(>
zjNP?<@)~XN?8KV3v#gQC`_4;{j9|hKcXs`=IjBUeLhqPCLTYR>TxZCP5ZLWnoWK+;
zP$P;%*R<n!aex%zYKl-^O%)*0q#AKsOGDr$@_r})JDd))yPu&+EIaz8mF}HzVMeEl
z8&qm6nc6mU`x=D0`gMiJIu8*sp8BL)+~_E{zeV+1<}GeR^po9RyHcKVzrfbxyc4B4
zoKL(li>V2q!Ckb2l$gT;S!g5T@+RD}jqv}pozBEAa6Tm;f*lazy#MZh&!dE%8D+-X
zjJ(GXcz5;s^`2-pnpW%Boog0XxpQj*fsyKRPcDpojISd8VodchY3)C7g!=N+cG<$l
zOF#sMzk^Eg7)o1dW?Zm#&y&-Th^o9_Yywhx)(ZQ2b2j=t(8rLKvlOf}y{%UAev|v6
z?T5n~Gk;KGbZA?`&uJX*k>OF^dPHkFkfdpWOlLX<c<LGqgx<&mky<D7>>xZJ{snvN
z(vuAhf`eTU%&I~yk0pgwN#C_rgPXK^c4QClNVetYUT!>rtjhSCwnlD2{ur<vDUG#;
zAI`#%ix4^->ww?CK}n-Wmb)h%d3>CI_E>^4u>0xW*bCG?p{RR=rcL^*M{o88$}jGz
zWS8Mk1^bJZ82q`;V=@BJ(g=#z;L`pa+k8Q*`MtKV9=3;9n`rIma!-qSVlH+uDyp6n
zfX?aL0iGfP=7K#N*TTPI7n(RrwT#z@|KNht5=$@t7+t&B_%(vLV^GCldg4O-jvN8u
z+&Jw~eQ*BSkF3dGWobT_z<XP>ENUQx6cTuP_q@D*ZJvJ9p9eu`6Z1qVOLX0(#K3^2
zAQNWsUIvfWrCa0`iK-K$?kDAz?6vH8-3juqi2?KfzB<a8s;=(P($(^^F{hA*8;_br
z^Zoj1uxq7y(5&`Nv|3d|TIZMHgt4~e>jUwb-<axW${Mz9a&Oaqnt+VR!|HF$zpxj;
zS@y@`cMK0H*is&xY$;B{!p&0~liFQV+p$6ZyAPp)H?y|^CvWUI6S%BFzchW8d4VUG
z#ywEuSu9)MLF6dY>Tz(p(fO8}jQ|Lg<KyCc4JoyT-Fj&O+1$sj8;0DP@*=)ZLkt)5
za)h|YPI3;HqF#>@+@I4DP7|J7B4K|kVO1_9ct@pp-r){S6Um>H9cIzTYyRc=qU2A&
zdypyq4e$&MUSJ*?hOBUqjTBIHDhgkaljUj6|G3pOA4?t%a#t8q9dKfR9%-aMp2a*h
zB!zo!F^Xi72Gt=av;uFHTE+?L#ZVG7d#kBzM4Kt);5d?S<t8_*Z|Aqv?G$D2JCx3{
zTKHwW8VloO{dow+W`Ko#X;>z+!%plne~8>a(k63MG5J3i!aQQ{<tXkeKlL6ZiTI@`
ziEY11XY9*Cqi8mQk2H~AM<YF}KS2n0A-!>U&BETC`N3~A7_UGxy0C?QD^%`g>>BZi
zh%o}Y<!=W)Wz(=>Cf>NMg6J#v1?bD@E^0|9T`PL}sG7p=bP2YBqHVqZ&(uK-15}Tf
zhdVHx_^p!H_lRy7IZAwJm|F^O@&IQaZ_WQ&{X&rrevMk7Cr+LsI3y%|03v<gr9co!
zs!N~&Rl|v2<K*`n;2Futg_7>%cV5cw)%-SkWJ-RkNPNh))#1p+#{-p8;t~SD{VTcD
z=1I1YZf@+LYQNGs?c-vToX&54kKB(3*}vMEj(qggplo0Jd=OkKbOWF#saGcwF#Wm~
z+930LX8QY`&d%452NwCD$`ijZ|Lj)wCByBG6rk#p%-%1R4$yxcb!?m?=)`4QelE}c
z%CW|0=E2+q0kd-E0$k;VWe^%)Z5jI~OK*KGdgQi5i47es0yZX~o+I^RRrTqEX_CyI
zhrq({%bwx`(n3Y{v*pg3*X9nb$pT{9R`4Aj^cD0#>)VKo^r{JRso-H3J!|vGD~t=W
z^yAp2R#Yy=E{-jwbM@AffIX?22x{czgLG}OE@N2eD?HqHc-1`Bi}Jr7GeM?mAKYj}
zQ$xEna+cykUNRzYGh+sg3wPf+39eE6x-amRy_pp{qyVvpRnEcd?6!0$C0ir8#rDX{
zRW{6!`z+t(ljHwkgd^<d%aV~pv2|#2ff|=ozDNw={VLQN9oy3&&=PA@A`qyXs9QL7
zMjyQJ+N8SQ^Rc$L3h$(vfe`>on!GX9;va~Vgl;FZn*H^D#syg>$Faw0EA^z`Q@vI>
zx)2+XRCFNG7XXsF`EaUlBM<7t&ocks!*71dmRLe4+Ay#PTmNSHQE>U{>caK0x*c;r
z#HK%s^c+iN2T7MtYVXe`+1>Li9Uq%sfTxP%m!0?s158qaJV~Yn;6kxcR`ItKXYg~5
z>v1rpJUua>XwP5nemWl>VSGKxWc+*aaJa9xYzX1_&rUaTzwctR5K6lHz`Ld^eme;4
z1}u~EYyVmrl`$+>0-d*n;biB>8@-1AjxK?#qpP7G`uwNS*W5Hwsp9|IA&~~N_+*&5
z&iErs&O7mN{ZGet0Vfsj#M+8$r_O6uOBUtN^h0+MJ3<C-!+wq7xVCh}6Q+Im7r8ax
z6t)IMZ*+twyx+;*#9<ubu+EFh-32jkH(LgjLqm=oH>rO*Kft?pA`#xvjSz2f&||s5
zfb}G~g&Mlc!)P@g|KiN-B@Gk&lAs+Sdke+hyg>|<S5H3L+;bFOF+t2w5I&=HnOh!<
zA+7!^e_3NbmlgNWOyx_IS0r@-OPtEv!E3tRpgGQM8;(C8j@>k<GFzbI%Uq{lDpL;g
zQt{;42H@RAxIQ#$u^~x(k)DENVHvwZo35<)xuR;!j#WOialTUFs{4yiOg1Fb6?#Q*
zkOUt6>6!>{eVjhy+jijZ?+`%#`KKuq&4_Red>46F@bJ92;0`7l@ogO~@E%Rfkz}8E
zWM0kqD|@@pQ}RZG|3(OU(kXsb48M9i+}^N4fkx$(1%Bne^fn(=!wsz;ZCh`18WG9?
zu|-dR*WO_iuOExzoY=V$rA*|t>tsBsB|O9Re+688og26WXFG}j=NR89gO|%5ccnjv
z1LHC4oeEgZ*Hd}+g?`a8!0XmP;ql3}>4ed|hy&}RsOY-F&W;O@O+Cm2P`dGbF8ZDv
z2}T4;Z=*ch3g*;2H?xeMSpF;TANgn1e!PS*09RrH@f9!yjF6zkTtE=qBy0AbJ(<3)
z5MDZ)-ed$loa`N~I%&pNkRGk-re$~P=H@61d%22X93a*Q%BNM9+V*Rz<_XR5cVlW_
zTFlN1h>~*BugxT&iy6}DYZmp_(4BDgwa|c$o}OYlm@*ni;!WH{gmG@cy6pA8PwcJX
z>Q1+rDsR-5*cR$eOg~-;_}HAa;q^o5Cy*405tk-g8DcM};_q7%`yxpdTxKPq^~mXJ
z%lxr~PoX|SIhOnxjc>dDi%B<2CmBq+mVh`7fzI7#QdBmw=FL?8FFDPzS3Rj0smyk+
zU8-Xdn4tpo@<RT#HEf+98nKzivFY{<%c_2?c!+u;%rBx7@&bvR=KOhCr|kfHU&Cn{
zj;@wBDQX@Fe$k(9#~}r>8Ttlfr{~fH#00+21bJUlX7frL6#MR=&eu|OE~$9Ad<x$+
z1wj%Hdvo5$>&oeFf(FQ`{5OWWB#i*YumG6C0D5+c7DWZs7AlRgVypBr*uoYnti1X*
z$KduZi>^|GkE)u^u!7hrx=B<2QqQi?aX+^zzH7?+ev)n*Z2W11&OWo~-AM*M1X7=)
zLym8kjkvl8jgPmgue|0ZAQ~o~<DQ%TRF5gD0^*=G$`r^_CwtS2_lJMEa&KS$lm;(<
z=lw`T@yKzX({?@3<|+!mXEEaR*$Ey*nwQm6CZ{<L_?-iV?iyzL5{ar+owuF|k?WiK
zbB?!H9ipURM&pmeF$(T~t+9aGE_sA<Gi6Su?mdLN|I9PB>BG=JGxdXT(=<*MqFyin
zH%CY@84>NNPVE4rN*;t@_h);f25hMSFG4Vqsjnl(J#nSB-|p(hNl^`)H-i*4Oz{p(
zeF&k)q00vhOZ2KvO5)F&Upf-Aj&34ao=p((VABG}u?d-8aJTrA`cvWhzsOui6(c+a
zk%jUbdbT)gL`1<XP5hA@qNTLc36ru{NfU(UCdv`Q2KEr~=qDRO_s5h+h=TiqLhk@y
z`%A6y=$xVytmI4KjK_*A|HIImK+a_w;YpDB-Y(~n%iEvZoYp~drTLev)(J~xYyM(1
zc{4)p?&2T-WqT#fiGuS(zgDXa6p}BV!aK<ZcZZuq1L-IBL10SMZ_(k|i?x_5g&`He
z@*8dLhJr1xl>cFrD_-~*huo}v3wR1!rK}_jfGedDDu@agN0#>=4XNF-6v_`4t9W9|
zUbvPbVL~6y79|di=;_AYPF}BTg-DH!dS^NAq*W*Lm%Ml1Xgz8$+K)2)F1m(So{h8d
z@9cjVhr~xJwojFNyqkL}K_8j+RdO5XH^^Sl=g;0Fy}WypsbeffBpx)BidhZ1dh&DL
zmT`WFt{zFHzVo@hXaNwt^Sg*23Fb2sCz0FCb=46YQElp)_Z1H?l7z)L*hk(X9vD@L
zlz$8q$an73_VefkiYjT&?#SP@<Yr=SkFx*mWJEL3&lK_QOdYhr<F$-BRbMPr1dWuj
zq_#cYX>_+}B~?1Lfo)}f@*-BN4VqOI6io*Ne;3j~F3Sb!?uPM@_d&N4>2sdCNN=eV
zurA)163&7+7ki=mi^&miH+Od%K6|(IAgOX}Jv)WkdMh>y0gU1;&87_?lgjZ^;v*d{
zS^S^dx(><6&50*Wp>RT$koLYW&}~&x!;af*oo}l}<ELxpBxIJD|7dUf;p9U?Upl2P
z5u8S9|I5%LIKlO?%z9UCw4(6>>p6<E;(o&XtnGJ`IzIAmQgrJpa^@X1w!fjL(bd|;
z?$^Ys{1~7{z~3Y26bFIgqYe2dDL2>(4IUr;T-kIw7%w9w8&0*bAS9nYN!$@B^Sgh4
z|JnOHve8k+;LEURpKDq&xv_DL<WD+CsRh8uKltm1Tnqs%I27m7zO2R8UboS#Y4*Ma
z>TvRz?Wdq5_mRm0%tV*lelV@cVi0Q=z_!+p0d=`#?F5&#^?|<4r{K6JzE$aSBJOr(
zA*`dL{=L*oMRyc+^c@J7W}EcHnSdk2vPex@GRT<w@ln~Xt-gEEgw6pFj;al9AczIh
z-FoCw7Ikz(CkOqS-wacAlF@jk@a^0565%HKJVE&+_~Cz)Z2M4yD~vnX&6x+9*#(nS
zJR5>;wt<B?Pqg!<_^{=5yJCD%OwY(5hy|m1Dj1)9?<X8NCe-7|*ed#-D!<j26(e_5
zBV(~m#->6iIpS9tj~;(1OYy$$1-eiD?|@Lhb#L}>8=CXco@$OAS1wn49w2S<-5hPX
zK@5-9cEk3n9X>cW{JIY=Nqn=_TS__k9W|)eJNq0t1vmisne_|?pL{$=u~-6%=o(AW
zDoCNCoy-LSJ89$P%|Zy0ip*qx2C6TOG99aV3LglU5_mqAXMDmGeDuB0cJ*3!RZe^}
zCqi?=Tuob^HIH`Ow0?4eU_SOd!<1uHuOHjf7l?^tIn%{_{k4-#rk({3yI*iE1=kmQ
zrCOo!35;=9d$DUv7!lYV+*_PqVK23cR&K@jv(JY?o6b)|^qbJ0zcMp$7Z5?PC!Mt9
z|H1L~NaGnrx1MeOXyP-=D7_q@-kjH&yd-$zG}9~h>O85PL>_+mf;>76Mx=)wUx%DZ
zo1;&se<CAy##H~hX)1KhvJ!nD^L*;r%76ppL;hMao!iCpnCovVH>8@~*)vZB*~8Z&
zsR!17a;e(Apb)7v->e4&YTZMXAK8KFoRl{Rb(35caV_lo{r68A#0x!`)^F|ki!yiZ
zQ?dtoF9Br_cUcjM#pGKxWhf@{l6mig=9Qm@w|}H~=>+R{7pAs@2cQ7AAf79}(V#`I
zq+b?n{trW5@>HzG2ftKO^p!U*)%zvj?Npp*zSqN^WW$^U2_!p@#P3^yfb=-V0tFhf
z7PuUV_76WC^bwm+1sz9rq74{W&oYP-jfi*H8zcV(pVLm7tVJ<=<$_7+S+49jNc_Nq
zM&Y%C<+S%Na#Ryr>8e#xva`~MY#b8h+--x+2pRyB{KpC=FiQraHk3wLAQMuMO8o4D
zX>TtD#{DcG`T%<T%Yf*e=GM3^_m#?=c<Hjb5<P9X)IiED0^=E~kk302j6T>yuO?o=
zwnxtT$ZbV|#l`GB>-}zuyPqOMwCY$g)$%cdkBAepHu?09g|t>t02*cE_t{c@0$|0c
z&0=_6G1KbFzV*QFSe|<OWxb%U>OuKtEPtILaN9HJH_2kXt5nj;otMLor-UA<;qie-
z_hT+HAxgCs<ZQ{g$n@L4OmW6)&~Ofhc@obvjB-^;ukb$zm>9(qxUVdDJ%;}g)|jH^
z!l{lvD@&UvY2Yi^?u7FKl0|2+rDTg<me3iQe_J@X8H0mx=2zZ%dxk{6M3n7vZLWWI
zlJF>_7sg|KZ@B4p`PS&(*bh9D+L8NG6yd&g-PHTRm2S7uayw!$j`nN|@!9&~>+1=Q
zwAsAsySyz4p>2$8^&dW8+-jd(_lj<K>3rR8XbenB0fnGd1C@)xRlHk#ok?aH06&HA
z@`Q1wLdJr+Ov{3~Qc~yJ#ZHuk++U+os{DzUH%o}uwv;m%sSYj6koZ^gcB=ec+Mo!K
z`Rcod76M9)4j!i1cuKp#jf4Ljilw`<!a=@tAkJ?(TH;9_YcqyI%Twe2M6sph0!VN>
zOrY<^q*+U3>37o_L#sagR#VI5Z^qW2T-*>qa^J<Uj^Al3Annx2V;yq5)-i6KjBsFv
z9Y3<4J9o9Y_J5TLC`u5bnf&2370(r|qThO4_yoSq9F+Y<{k@2p^BHzQWz(}n2{Cd<
z37UgU-8hvtKTKs?W>q>9`gGSnz5_+|U|<`jI$r(eR#3wM6Y<q2nk`^d);O2R|1I1u
zxj?!l!QZ=XWaGog#p~>u!I9pATnOaj;m9vWfP8d5<VRhSkg8YC2A*6~74xh{)T${a
zjsUnf9|NUZlq`U6*B#j~;rYcu%E|Kd#-FUF5g)|rwjM|1p=?;`EZ=u{v_F?P%WSi%
zY0ZT<K9idHoC&U2T)W61WK>)GINN>WSPV}A*llV$zg;tr=P<C?lj;9hlZ30W6R-V}
zkR^GodTE*0c~RIU$hxDM7h*GGS_#SFX0j)fKn6LedPZJ_L9d?eyjKa%dzXs-nQh3_
z7T8PQm_N#;X6tQoZ-6-txIfRL@16<UYk2BZSk75}#qt$kpR>$x+SuAtl;DPbY<d%*
z!q@W#p?VPY&X!S2(AWC6_Skfj>Fs#a5U0U2=@dWLD2z?N>T`-WO@ExG9e%rT%13Kq
zh$T!bUJSi(Skk><%JflHl-Z-|@5Ks8K{Zb#6B%sd>Fd-@hR0BiI^TY)C92IWU}Xy!
zfBav=FGOWGpWCM(AZX0W#@CV+dRWT#$f$3jX;yQ`ptCFSw-h_Q3QxEUinDYfbcT2)
zy2`(&_S^C69TIb!Gi;{n)o=0`OVL>wEWhnZgJCbtXK+BJ?E7_eExv9bOTLz&Tn~mV
zIey$|65J7eU0AXvY$_B^n?h7={7Qf-VD2}hj;wiwy(Pr$<*y5N@Mc&G@LDL<z1N~T
zLNr4z0<oSu0wo|<a2JpLVw|e_T$Ds9|D<{wR+jaP0q2h#>^^Vrgx{{5F6ZY{pWKx`
zm=T}AY~VlZaa|!gTi)+mX7(G<{dRKw=UuV<Ar7I~?VrID?1OG~mhFElBSX&_$BL(m
zoc6-EP@W^F${c~`*-WT;?1KjoCncgV=Xuh}gsn)eUgbY(`Vv0|s!R3+my&r7c9aZX
zsrC0Kz~3tK=+Vi>=50mg?PxIV6kYzrtFiup{@Y~yw@<7-$B=qEb%+wnUnKB#a#XN;
zkC-yUg!81RsQU%^P%2IzLz&&#Y6eB$4D1oMRF=pvBJV*N{Y?I{;kf5@qi+PF3)~s2
z)qX8@(C*hdUWoX%4*_pz#MQTUiTh)lTeX&Fl~i+CaQy;k$VIdP75ZF7R4fL9h>$Z?
zUQ_(KPz;|B_;2(Zw?KQJCJDFt=`447a4jna{?^?y+5u2=Jbd3BOK|vI;>}%sZfisW
zfh?)h@>mI2OWxQBpX#D^R1Jw{RisQ{`(vYSywGmV3KS7CEmbJLH|%iu^<0e8MB0yv
zIcY>>#gTZ9=eS?x!8H^2`%)ey8Nj%EpNApcKO&_{&)lm05(BDf!18xe%Xk0l8_m^<
zN`l7>kHkPEai)Eh_ucq!>}tV-n>Xfs3}QY!O7?hjE<VeF)L*Y;`e~d_fPkqqn<PqB
zdJg7AMb=(uVIB8OYH!#Qwn|#wzYvbMs^HD>8RMfn?N>G{Fx;`-o_$o>swR}btpD%Q
z#Br-dC{HkWKm364;RXM{Ra+s)a*0b(jfscRwb?yRb%EP#C1sW&S@ri;f3KWWB4f&X
zk9zebGc0dCX7JDX+w$(4^Y9or;-|x7+<&Qp^;V<H6QyJDcHAG0c{R#!E1-3Xe>2LP
zff7$vC9c2d7P`t)dEmSA-N&l;!Yt<L7WW}&?fHEgm%*gCIwLFPtw$LqB5!ktcvZ>t
zj-?B1E{j@C#<bEAGrn50oX%xQEHm(qv<x+IwpyUvryt})PYN^{;O=vlgQN?KY<+z{
z^0IOMb7~#g5gYO3Y+Nh%auZs;)(Piqd-6nebkxYDH4uDOw9i${!~e#l3c4OuNsZ4%
zU?N&r*{WNB;CxU1RaojTPP5K=d(h;r7QN@e5I2Qsuyvd&^xdzsZoj~0^i~zJ<HYq%
z$m<f!sTIhyy}%2fxz$Nx!El!qTG8s8vT>vzkLIO_2nfD!bdXUlx8v&=mkoVI^+URa
zujdiUkfQG)tg*M%>bvFs3Qf*Ov0%p7IeD=*wKm)ygU8*x$O9hQtaXzdaWQ)ZHP^pS
zX`Q;6t@SO}`MBv*{yFg4Rog1ye=BJ@mQ@qc_B-&g9O);5Ep2n?RUf<%qJi^A0oAat
z&U45I@+=8nnSxRR^nU!j6-sjA?ronNBi_U#AT|jqQi3iCpHU6Tz6y7qw6U>E4HkP~
z=2L5Q+dJ5H4!yTB`EV6B&mdQ*O6ytzy;9)cpgP&;%`d<Ux9QmW8)FI}gnF3K6<6_&
z{f_A4ysfU{x~28=VGcz!NuvfYquY5eSs3#1murnB6`y=;{=6_1nKiKjCHm*j9hUE{
zChRE~J0kQR)BmK*2H&M#TlGeGh~weVEo+!w7;i;%lcTEgn=US1JAAy!!keoe!)%`z
z)XXE*D+N1)!`XX`2ctN!eIJirLCE;+S=4Xqmww2N9=~}3hpQ|#4EUe;eKO!gP%Mb=
z4!esIFi!X$SQK)7Sa-IlYEQI#LRxbcur0q<Oy{KyPIz6_Ad2CKONpUBY<3v$Heuf%
zEUpi0vZ?}IcU3j$Q$*R^S3aLe{tp9tM~A4aG-a*p_KPyJRT|@bLIvd+R&E=+``dkg
z{quRcPEFZB^G}L~hZp=@S!)!x|7_^{6{cGleRV`VQPM%IcZ`F$)J|tu*{ZmVdu+%S
zD}nef)w>5?<GNQtadoU>-59#yTBy)np91U0BLfUSuUF#da?)#jeHgxC7O$6>G47BE
zPlBcv(i*}#Wfsp*Yd@M;%_wU&+Yh?U@8i1+{)aJ@+A_&xi5M40au9jd54{O(66G{|
zN`tyORY;?*c!~c8-u$6Dcs1-@uB`9As($)@uF<d9Gk$+l5iK4_d|s(lr=Dch(bg#S
zNaMJ<s}YO2)ZK?kynh0gG`t^4(=YO|9p>kFD{2!l>6Fc*p2{=+3^Gk?n(}i0cn`nx
z;W>NcDCf=Tkvihqbwe#-k;*DhN5Oc`?`O8XPR~SnFjx8CjKjX!S?;W$H<;JK&VW99
z6er6(r&Qd%TrROe_f0@3qF9uz3e@1^@Ek!jvD|?7C6}tNRnW)(VT5Toct<{ZpRN#b
zwfX@*T<|J56A#S8U_TVn$ZC4@Enz&;Jz|Gvsmpszy<;he#Q55fkj;x+D4~Jhh=<q>
zXuJ!X(cGJuK$rI9@S$2`5>OF{Pu1j9RnEu}85pE89G|B%5BlBirh!hc>e45lO1TFB
zW>$0TwAT#`!}#=xK{4!Rqi4k%;U;_Gl9`s6C#D*nE7jZ#_GFfWJf~=^WS}R^lXlvd
zHbVdX7ibzPe4e$h50$=!jWhX!Qhb%83LA?GhA9vJm<=|(vVSjLpNWuIWnq5Z^?@ec
zncT>7E#4desB{+wM(A;SO_+CgX3jT4j1d#jdvf!s$FaN3Y!z1eLeM?NIZsCks=)5A
zf1cYI%!8!U!qY1o${Un^p!S&77X?Vi50}&z#|oZjVC=ZuReO}0sJ9jU!sy9v(5D%C
zueEA}4`Zm_MByFadW}$`qNKff#Kk98eQ$vFafKU$dMZ`D4j=CG!yZjyfPML-)`sZZ
zcUetuf;^HngWtasu0EOVK#8N-&LXl@rANO=E&B#FVx`BG`!T%kvhdO~ArWPdL}lYl
zYgVmEA^x^Jy_E<^i67O5T`8<HpjRBXMZn9cyW-D8JBpP}J#g{G{^A!|`lqQh6*FU?
z_uEWcdeN}{*!<$!oqzdC?noDl(J?KZEd%=&s^cbHXWJ4`pG}RMF)%o+;uluX+a(eJ
zd->(NP{+hq>$%^Qx^m)?sXL(vG2EThR*x#rLorL$5WDb{g~0ffb(B_5c~R<oOtjEE
zR7zsfC2o*}Rs5Eao2%@**<$@6wvRH<5K0ve;+2uBm${g&6sLlrgk`$UZQd~6a^xsZ
z`)Ur}&k^y2)zx3#k%P13DF)hRy@R;!1>yt6BJsluXSCq4hZD_}{WY_>8G{h%5}3&#
ze-nledKntM6y$yY=z_fkJe>pZEH&J}+thX*{UeuAcuM1f<d{O2#XtTu+lg*oZl*N|
zAR*^jbe^NQS(Xjv4+=@d<nlO66AQk@LO*eU*W$Jp^hpbGUL2qI3GuP@Iw3G7p6t*~
z!E(535?UFFUCsdX?N_4F`K}l)TW^Q`(jFRnEM}m`hfbu}?}L`TPY(Mz9DQAg?D!R}
zJWlJ17w+Z$#cOy1lgUb7%LLlUI?DMBSf`O2K_(~p(;dfHe0(Wh;nr6l`{%h1RZI8P
zu#>v=b>B#t(4OUh1*=v8=JwJj?l<^RQ=xqz&2O&YX=j6yZwcIc6f2#47U$Z;5eT*N
zRU;UL=hCkZ6z`+5WbY(QCPtlyp82DVek}_P$;%Zz4YRY$VIvbhyS6r@-<iPbf~v9S
z-*V>v4@0(wvH9&Jm5WE#s$k?8)#yXJP^vmd?Xny%%FFwl*^tkk({FH#{GOFY@dy16
z19A*R54?*i`%9kOTg_%ij=%7WN2;Uo#H*9|zsoLkndMZ6TUTg2=bTx~P3lat%6$v9
zH%idXW*L~%Nw?)?OVc9Uww6(5R@KlaQ6y?_(eJ3OaA!O<qzt@A-m`_R#aeB0hEuus
z;HX6@-m;t+g4C!nO!5)=JZs+iPjN3;{k?R;P#@Zm`}bCSYd>ea^HWkBJaU;bx92JY
z5=A`&(}5+Nc0%P}jL0dX94rN#D?&4=J{I=GANg!0azcy}lSAR(xh_&q%0`J^&{O?l
zCFL^sXX#gSF3XI~TsPyX;b*lQ_0Ir}mC)vXTpSd?$%a?MwtO5x4&8G+BZppmFBWFf
zfPDG*gDk0GmYrF?e(%Q?nCopH7jOjdKsDvOsf)i(D?zHY3`$&LpzN+fI~7U34clLn
z9`EBYa6uj#1kX$pI4&T5ct1C%KDbr-k@&~@kjQ%<`jJf~y)?0(%Wp-C;2*fzpZg)a
z!Z+0d&V-`%1ijn(`Tg0}Ds@IlVzZ~=PdgC>Dj&Z2&1EQ4D`xD-Iklczd2Tl_(T!A!
zeeJ2#?DWhPH-}zM^1FXL6TgTd!4=NM?Eqn&(MqhS9O5fazNng&dmNK={6#*(aYnjb
znPcbZ*1ZWITrlC!n-dkU-^4!4R#xon1ClXM9iuzOk?{keORUtV-#%k+HpH`*@fYI&
zO?ET!{6l6~ut4?Da~gVG@noe*_d6<cpgVwvJ*K~H&?;Evcpz*Y2ASLe;D~28R>w@n
z@QWAX>=j1WCM;gw%@*L_G*=Q@WCT*!ovqFWg%v6Xyw7I@{#O+fM2svk?kxn~HA6Z{
z@BT?pxtAYG%keMb2))9*SYQi~Z~7>^P(yXbf>?T0zjvX9J?&y-;S3Z-(a?-s?BDCq
zMQV)fCGNTd0`qOF$=ot0Ph7InL)n3DrKfUG*CAc#+N=s(XWX_$I>P*uL^oq#X-0P_
zJKly;nn7~LbNHaxn~6C0xDK(LSbtH1!2htn>58AlK|$<2_Lx%hDnvuikc3K?!(>B+
z@2$1SV0!xtp<yiQC3>c@SV0eW?9oRSsE-ID5(={$HRe<wlaIWZ>w}ov?fBW&BTrJU
z9S4UNesnuqt~JWg#4X$tv6ZaVJvP~oW(yv6atnL*F@9@iE&It;Y6zAT`c!B6?zt5n
z#SDF8LF;i6#j0%*>}V91UC%x8Zg|~gWqddmc-}X4+r(3JVo~1L?X^+9Rel|MPIo+Q
zowM~BGVkx0KQh2hF8`ZA(pfG$Ey(!vvsA;wUV&+kT12l#?r(dNT~MhtMk#o)We6N<
ziW5#QI$q@Wwy?c#r_Oh=uVHKJA^c$IrsqPy9OL!y#ImGt?^R%f%Z&`1|M_urrqHbh
zJag0=;>0*uJAw#Z+AI49*0Cqp%C|DD>5VSeYB=R9-UKwWJj<Yc7--=1>!<Kp{?pt4
zG{diSFDY}ZmA|xx8%uonlZIbTc&ZGZh5+p!$5BBh8$a96IT6FuW;ORpX`Q}oDiOu4
ze}!-QEU=ZE1agDBYB}MqSjnOSzlr2S(E^~bm}qF}@S%zVCBVajQ>PZt-s9$%f&Z4h
zbAWfL@h=nQuebRT>wzweVe4|Ds28vmrZ)!PIA`OAB(3I8$J=)c8+GoA8-d=#B=M>+
zd@0%MlUBsawF;jTc(6usk{XV0e1LEchiUibfpzeVM-Rr3mOWl(`A}D}s_|GhydA}2
zFzh$%|1!#6TJxlf2ffJ_(xtCU^+fRgRLPG(DwvQt=1t&#UvDE5={;t$SU^D2mG~@h
zy#_W%$G&yZ+eiJ_c3>eq*IOVrkzl-bRA{r>xTdl;^5Mb@Y)Y0Gs-ZQugdY@xJ~diS
zSJ5Zri_d>z)zr-Qbzb&CrsCG#2x^o(Q;v;H%y1JfyHa+;B4OZJxEXEXj;$<b6z`hK
z80U{!<gD=6o60?L&Tk{Kl?Cn^6FAvo`n5U4PHQu^N!3^WF@c}{^eKNvr)3rMgl1Gv
zbRg?KSS&CLLYJ5)PEWEu4qqeeFVML%u71mGW7VLO%%3qUzuNl;^#80Zn|#sFLAk@h
zN9?jFpKP~$HXo=WQkvgI1}d~=s*>e{A*NTYOvq`nz%G4NA#*V4GE40k+=|XAu0?_H
z@Dz<-i$-}jQi6pg&e&c0#_JSNbqN#&0+UhqcI+`<8m~2L^Q1hDwX{RO1M<Fb&YohY
zs5fy7Zw&bJ@om%Gqe9AsGR#zGUCch3#6T_(2>yHRXaei=m)6=%dYHyFutAjE5@&?n
zYuPJmY)#lLjkYl66NoE6A*m+P0xq5nEa>0IPu^yG3CMUmye}q(Uy)-m89r7gOyu!p
z%^_Uf>xGKOMqX@@MIk*XQ3Ny~=I83KYtMu~n*SkC`CQ!|`z`b5b)3Tb%AVY@*Q25~
zedSE<gfp%h?pyZR8W+?6q`st$w*P5)Hw;buo{B|!WULal`f^gx>ETGm$dyKGSherJ
z2lOi`<5Zd6?7G3cw7{T5Pa-uXBUJnyg<IvW<?BgI2T;}*JQXJCayz@s4(=M<kRw`%
zzT~RVA3r|^`tykUf;D{Ee%f2diC4Js2fmEY2$NvnG^lDs1#GhDO`AN&dxH;_qYlNZ
zNBFLOgfZITdeHhN47IQ_pd80b7(`%z#m+2b?v^VU@^U_ExK)MY5eMu^Uwgy{Xpt?s
z9i8C&UmHJJ*3UU5sE@CFhuMA%Mn$irRTok(ifglT^YqhBDOk8ch!>d)&iaQm>>(e8
znTJK`b1Gxy%x-1vdY@<Bm=&q!?bOl^JyU{6sFDW?et#wT#*C{sO@&7-FQ}TuW$7Bb
z=CqrK?vbVbOXV0~QDB#{&&;!S@H}ps1_7=QeRgcBJBa*(5Ww|}pX%!sH3JYUG|!y{
zgw2A|J$33vnU9E$6ncyvR*)#QxwcUjyl?-Dy!XJH(5Oweu<~hqhmF=V*^!v6;)i)c
zb2(t>C;7v$G1HqzU){MLXozkJpNqYK#M<nMh<qE^2-vTtLj4~}XB`#Q_qFjs1Vmct
zE=543I|f8jLb|0?x*LH3=^RR>WRUJ|5Kvm0p&N!8ddMM$@9+A)|FIT}%dENQp1aSp
zpZ$4o6T}9_ZW~BXKBh4VrT|uFBdl)3X$~$F=ywDi1zt`LZu}BflmeVh9rk)Bg&E=;
zfOhipPOyOR+v8PJooaH;SVz4Cvc-FBbw>Vrp71E3!3;Z)=93}hhgNd^*}c(yo0xQV
ztoF*LDRzy4g#*aH=_O6M^rHhG%%sE5$K_5pnBreFOs1YD+AK|C3*J8!@Vga6Ac0KH
zR+n@q`p`q;@>U7RShLKgcC=9WMblj`H%r>c#{QokI+yQLx;DK&Bd1Z1&PSXB0R+&K
zNx<>~Xq>w-d{r*j6P~zKm-qR8xBSeP<Pc~3H#-OD^9^7=rAbKln2e+OpM;R2!~j@L
zI_yjd<trSVt}K`tZ;6ELTajyj43;=6>Nesz#pxi&8I~yLG>HW1aF8_}CNSZlW8k03
zz^Wd(m}_??R~W{B0k~4PI`)<+FpGvB9SCWplDagu_!!-=y@@ZlM3IkQQFC388i-@h
zL}LsziAxhPl)$XJ33yan&EKgI7xKNLE)XdKvp27G2#Xt7yKzDq;Kk)IasAn}o=ofD
z*QSm##L$M25-`{{8f9%1L<|`kXl<gFOR5kw^rXxm*-C_+XAN6g=%%ZS3Ru1$3SAp1
zXZn4TN?9m!c+^7oLF{}Z_ifuB-B+3cDY{$jQ?fQsNU6|)T#B(i-tN@KVg|>=7xBCi
z4V-gN#q<uaX=Bu#Z$yVAKX|j|$vm6F1$)n3Y`%NAzb<(c?~!zW!F*C5;|I&a!1We;
z{G-<`Iqo0Wg_=$;hHF5UN~e-<d=-{kS`hFDh32@g4l*M+_G5-6M#~KYpjqBb>nfO<
zGG#^iVBcNaI&4F<IC!V+_UtuUVAWfF7<M&n4a~LfzvLsZo^=vh+Shii;ux=>4QUTx
zvYRNfKJY7qKAK|&MxIt9a4aD`Cs{}7k(#MGYW@i5wJ)MM#|BX79(DZqq80|L;PUlQ
zCz?WF_I{rVceU5gOYiZ2EO%K>cRT8VPbsNjLJF#YIr*tq(FIkn)9<)pwB8laP7WY_
z<zPhD_3i!hczOAs5*o=_kMhQJdRgH0y_-G3K@?*@xb-aKcf^mTX2ylB<OIcJ+KQ_g
zsOCKTz<Y>(_ZPN8`Pf_Gvd5-3yT*~IQOI$r4=`R93FG?!_?~3x{sW<S`gIv@;Km4L
z`7`Q3v0ls0h*yi>k|ex@LjRnCz(K(`<J_5Le)(j-qp%LOiIh|s9zu+}WT@Rqj#Kty
zwAK?lPgk?=Qw=|@UN$DD4@Lp#jrb~L*&u&-dB}R0<(XRNOx6l@Fw@0BVC&>KkqGdT
zF?8}pX}FNuZONd`|I{jlTR9U9;K5_k1Na}sm1OJez4gqKeaS>-$l@GG!j>Vo@tN>S
zX0EiTTcp&_PU51dD8g|FXJ!4@h$I$}rCCOD)F_h*-?*hf5{6mVYKw-K_p1+kWUKSH
zi`&QO1zj-XqP#M*sJB2sq@5OT>|x%g9`_G=QRj5B<O1hAARRi{nnArd(ia3tfEMl;
zmb9sI(N$uFdikB_HthosGA`pA54NV7B+kHrf}O%c%C)qvho`Qbh98BeswC)aOfRMF
z-)1&`Aw8gOYA}8d{?)GMH}PCETUOC+CM4??4YRaJ`k1<w0EDS<wqUc)c^-Y9>6|N%
ziyL|Z+yT-Yqq*lQ3Cy3je}q{!#a5~;Ui$tAl2AaIjWfC0%sV)m7&R$0^%qfaEzaQ#
zJ*ta&8Rn7K`+X~u3?w*<n=SRW1bjmHAE?zKAd~%lHSd<PO^rFCi7_k2!m6^f#3vT4
zAj~&YWzH<mA^kT?Kf}}xr~|4Z8Hc&70}BtYUoqbt(NEGOVTy_o;bV8Wse80ZY+{T#
zyuyXTJi<ZesFXwPcun=a$0PycxcqHXro<$j<Zzjvn5!Es6Am4?YSsw#dGG6+?2N2*
zImX=BpMvZ|C9rD;k=2~S7gO#KKYnSy3b!h|VzE@WIRKpTgn*}$b8JcnoBUPj$Z0x%
zf=4f-V!20s>&=ImA#}o&tC40S*YjDY{4F2e^$=yk(2r%5L-j4^gvtf9-o^gW9tYEf
z8Jk!M3{mE)U!~+7EBez$j(b6$o~M^&dGK96&zDdHHnSilhQKnV`zN-sAd2XVLg1#V
z&}~vAA}VdMU+gYKEPW3+-vrKmk1q4?fGlN%F<uX8U3QnZFc&(QWgvdk@1bW7;nvCF
z<?4_8n<HU~U8?lHHI;q+d=#Ufm-R&<^yxtUfo#x^;^qPHIzt=iyQGG@I8qBrI6RW{
zC8&ks<DHUFxd-F1<0Nm?)_Z*lt@|ru**8-B?j(10S_hKaBm~3g>)Gq6kqwm)$3FZ~
zKI8vuNNz$NS}zKL5bL5u!^P6F`HbY2GnUZe!XH70qk8=3hsp~W1W7X;(C%XOeP@la
zy2s6uVkRIQ>7OZMaKEi(DxuDCpi1_Fq@806Vf}I_s?3h*<i?>cnPYEedFu1aW9W0>
zi-G8Y3*jI#$+&AL*%2DY6=fre2~mH2(+-LlBdNhxnrZ$?I%!7|bvUJ>Urt4ql4_V%
z81`g=T+p{#(>Gp1n<u@&mgBddYTqNYIifb{Paf^73pmI!K4WNB%@J9Ztt0yTge0he
z3+<zB`4`Ld>P{o`sC|jpH~$nE=%P!IrVL>KWT^!!_nI$3sqmjj-@z|ZHx>p`JYJ1b
zzq%L($tQ~TZGxSNCC_9N67BrmPm=m%>d%UdUTiACjCY=@PS33`xQwRmwpK~~^|+tN
zA&&RNND<a5P6a~M2QgD11Bq7RViTWZFr`q%`k`FSS1SoxTrYgeB<j9_E`}O)8vsg?
zG|Lqr4#D*GPfaoru89BEkp7)RTr^tUe^*CvI0J1&cAZXG7YUD$JYM;Fb(17_QZe_g
z9rvOa<XNOO2}iF}7yd9;Q`=CEl*X?F3c`Z~J%G9G{5XENosq8|Yy3Zuvz;YmM&W#*
z*u=P+{r(z)ZG^v8@@QK<Z<kB&L<g~zZg7%AfG~yY_#B4_AvUCiJ<fO;RLW6n5nz7=
z`TE+|QH8~e%U<pfPjrfU5T)7<z<kiOgpd3_e^ADRqv(;@^!r~$@#m>apEJoUke36z
z>2rHv>1j!G*c!mkrM=*gQ^<T_QK*v^1hL-v6cCJ`*%w96ebyoE-q^R2*(}<vkKJfC
zwE6peSHX~xqV8DmHW8S=iv@&+Z_tZn<;OO?D%mWF7+_fN8{*zD>AY<9BmtSn+_^oq
zidL%c1%1IEtHAyz1atBXM1td`+ci1kHs}dwVs`!Ap=oiqI-Rwi;ScFOfKg6LP0|+0
z_F$z3V45})mP*|92{^~pp1X~u@}Cz08Ab%Bxs`#B$g$$26nrNS=gP9T8=Q_`*_aM=
z%S^L`s+%8$?k8zP?ERsX#FJ^xdE6whr@Gcnz;_|6YJ$<{GeRJcBhE4v4sm{=sKR)S
z0j7*M91KLtqx$Agmir3c&z~JNm^$2q6>Wt<i-qR`+f*Ren+Fmb>CcWbgYo8P!K$`O
zoS3T89co}(^qjy{lx7{`Kr6e=p03V?qzGAfOX(n{&U<O>tQ;YAx@;M=3FW#tyxBV+
z6=xUVo=N?84_X^%&Kty6X%WBPEUbLfP#XyB%3broe^sjtjAUekRDDwn#mof)p3XXX
znx7=vm99bn#1W8jsxAdhOgT55q#3a>`1s7&8o<;a+$_eyq^uLvJ)s*8!u?NhWr`J)
zfWwx0l=$@=R6z)943lCC%qv4fn^uzQmz_>U)!|=8%$QLhJH(>@10AQR%e)HZAZ=s%
zn4=^k6zFtnIG_mbutU6_CV3z(w(FxmkBZ|0!ctuRrmYA>0nQ?Pyc+T&T+K`3vTQbH
z&vm3hw|^PmGbM(r3^=fkhUu;5uP+K=)RG>TR<44whIzo2`Rm%L=M`k-U!7`vD`gRS
zKT$TaaV-d~Bg6nKNPJLNy(IK!K8_~(jSIES7L$&qIj(7=z#d73vXr@}3D_o%M0=Xf
zxAmBVOi}hY!}{Oa6+kAa4FGT~$e*Vo#}|lG3Vc*V4i@8UQpu9y%)alz7P&z@vWCBa
zf37wMbTRXgvL|o<1C0&daiyc;5tXlblsIA<SeN{KuSS@KseZ=*S#u%h)J0Wa5Nx>X
zsFmumXs<{b;!Xu}*kbG73*IrS`p5mU9YjrffFilC!AM+>jq!k$RQlR4v_&klcO@)}
z<=>CbL=V^nib2V765<1%SvLoaDl?35o>T-gX9Wq5Uf;k8ubZ$}Ke91cHlMxH?BG`;
z2KGoNLGL4o43Lr1YN$1eS41)L=tBRVJ24RF!KyABU1i|45Eh(-1PMB)xh%NvnbfP>
zECH{uwm_@*!XsoRpjE0k5v6{s;B{r<KAM+2PswCf3&d7UT9(g}W`ze9kyk4K*l7~v
z5y`&Y_%mTW6&pK5*>)=M(^6sonaGVEqyhOknlER}L(gX7{XxLMntx1j0H3BNe~ogU
zp&8Qp-mnjhrPY{M$a~Vo&Frg>%t9pXE!$PCzYXm^=<}zwRcxL<?{aG-JMI;|b<w<k
z`iN~wUjnT+z$H={NDSas^ap6<(A&j|KT$Xl{{3iLOB6$@(^Z~UwvvCo6f@wu?Ej6o
z0K_dN(hJ>Yu99~FrXPI0#CPs8xrx4gUBsI=AzCDljf=1I_x}z1zIEIgb$rJvhoIAT
zW&4gf`~`r(e-t}D`Z#b2MABDez%ul~IvH*!zrHZ$SIs0+(Dl9hD%O;?c9uaBr~9SM
z`T7F4oQVXv<c-&1XZ{AB8c<vWYqyKa4X}KU*qTrNyj3hC(9(bBhZs*W*nkW5x};m(
zY*+9^B)4z*p67V;W%h|WcA^gQZ?<z}xH_3@<)3)>dgiVwy@&YpKKBILmkCU_$3VD5
zWOTzTf!O9-FCd?OuiUK$e4JuN6UbD_wzy|25fM$jk2j>ywY_LIZE|lI!~&psZxHUq
zF?7}YW~4Kot{%5_=qdFI<QsY%VD6s&`q#|1<rOrrK!6i_UmbG<My7AHQp|dugW3IL
z{s4@hQQ@)g9BcJQg4u>%P2y)pL8Uk>4KuL&_a6uExcxPsn6#qk!<a7ZDNyXnT~Q2?
zlZiAcg?n8e3jm=K5>J$CuXz@jtKoNx;nurTZ-?~Pr(JC1(V`bycue*)e8{o_Bm-H-
zGFGFd#<Qu~ZRnOf?|~qa0CkZSrxWSYXDIf&!^Uo#vIfu_DK=N7mz_G=P`u&p<L8ob
z@9v*Z;dd#c?k@y^;9cb`(2vhR-6(p;N=&R4B|Qi{lRxD{xU4&X07!ymn9PLw{X%;R
z=H2i63oI)L`pxXUe>lw{fPax|s1uP1)Az8KNJ75Cg@oxs96LT<Z@P9TosM_Sg?5Xa
zDAOIj3~bZSr;H{UY^I=3;7+A7@VzejsyUe|JriV9WIg*>z>e@RiZE>@lp(M*>r(%W
zo-SCDp}}0eQ7NoO!0(5NH1gv_Kp)T3X2*+?>OPU!!ZM;!0#3w2VXWq4UEHaJhtZV;
zw_AtR+$gSth?B&w49n9_0Jx4_%(uIb8FTk749({pI33)N*?y|re*6&F>>3736l1*>
z@J1#4$0<eFJ0~~TSz;6XsDFByy%HWJh3Ob^$hIx^a5MVD;oY-uJ}8AA*(KXDc&IOb
zWn&ytm)J@a1KmF;1v<B$%hUF6PL}3q(tQhAT@LphQH)2DF$rct0{9EE=Rk~zTQF!K
zAK-}-pK{*W#Q`ibu{<foRc+3y4MzlqQL|V|4~AA^?F$%J7qj(VcbyD9&v^{ISz0(K
zj~?y5CDdjj9S#M5+Vs3GQ}KMOAhy&$^_UoHA=sRR1VkYdbmi`Y4rRvMQV|rxQYb#{
zy-|f*p4~hWR-w+AUc`m4LCD6jl)q1D{@N$W!+#Nb8iWSxRYn=w{T18_(J-vv+^a!U
zD(4W}2@_l~0dswbhNt$lp+vcg9MTWS%yeY3I$h<nJH9f(Ea=1|rMrO4Hu|pCsYP~m
z<}s&VoRm(g>T}I$7T%@??_AEu#ZF1?9_g^pc>ad2b`?zl7OW2ys6m%{fK#^k9_;7p
z+v|y^SN&41?X|R^3Z|~Ge{uudodNpumb;PRBS)czy&nA4;;~{6W4rzUisws8w8xR|
zq-b<`>(*uVx*b+xE6;Fb)b*W$nv}F#y>m4G_4L`sXHyG2KwZ%Q7OHQ8cRvdoJP!V#
zc31E#$B=m?peG$H>*cXuJcL7|*&ZgjhyX2fA@mQ>HBUm|2;~EXlcnLHb8~Zlt@YWR
zt0aIqp-Z&k*H{`G;4$?t;F7)N;r*6J!geqZP@jqQU@q|XGxSd;Mt7Rc6+muAE*k{b
zbem*Q#}9CDqf0agCxBHa0`6uWlfTQ~@AqVL%IuvxhLJ|Ue#=<Fe&+1?9JLsw*%bNf
zW9P;yMJ)S%&rUD1d(3S;`k)2tb4eZ1Ea=uk=N|4i=*Lcw9j0aZBY6a{L=CxW{!(DB
zPda1YiY(GHU2b`~{_zuYcD|c&?g}sWmb(Ha!;q6pfv6tQ#de}nA@9gm5##jRqipOf
z?_Tadldn_(%1W)X(B@v0bhz-b=hpjxnu|*BKrVfQN41O|lV$NwKDjh&wv<*g7~6j%
z3x4~?<Ges(D};KLMtD>yXC&#i{hs{t1hW(yLX1~vTOHpt<0LrrlW{7vhthtI7_8c(
zNvI({XRwg9!qCEY^gue}N0|N4hNMQe^Y%G51pvl3v7EmKC=<eZ0fMfo$$#^fOZIaP
z!2ACo&}_aD*lj>I764^smL<Ss$YaKdq@`p`eyowr!AHZ|qMl@3Z3MTN15o|G-;Q1X
zprz@f_&_}0Ft>t~RGf<6J3>z(-bklZ*h)eRQe#caoJ`s8^s}dQDF=$Z_oNX8t+4wK
zWMxv!F3I!<dXQ<=$u}xpf|csE*k^vBN>VAPeDiDH4cap^0q1#V;jWnjBs>>8Yeik<
zd?LB5*u~qS0Vc9>ivs>a{KhJ|OQ9Myj|p(--863*Lcs1K_w^z4QB%UtkRm`|!X`%E
zrx^B2&~281yZY_thYt_ceEv*|!y{D71FlB>a(7?4tsk%E)yU-ji2YT>!@*e8;AMGG
zGnVS6VOO4dIv#SU&{f{*-3ru1s{PZQH&bT?`%0h{PVmZ#{lKiS;+D{<WI%U}%VlL<
z-Sc7o!*Gg<XyAeUu&+ji;j`|TWlg!I(%p4|GGOxy3p&tlq-3)9Hv?n1aK(xWz~J2m
znV$oO5MPAdcTa<ukbrAtL~(&Qhw1rU$bq`r!na>g^hMVd_MP3A+xITlK5<NL3SSTg
z-LpqxzXH5BQCfpJ%RNDMt9vctCHIRPtj%Plh}IaFg@8B8%a8V_LSzRZ)koBXQaL*%
z6dZSKO&s^{|MFHBh|(gNK|lyRM|x#5_?H4(Cv`sdSj2~vhfDM~F#xf=yxH1){$|p7
zmgKHU4w;}J98s?rfc|xD4{|%nRc=1ZB1VgqQ2kNP32#ljXNxITtQHr|AyIuJkpesy
zH_qomh6GOQ7Fd|umg6i)IMYd7AC;vQuEcg(AWYkf%h@|+Nt_&IQwoId2$1BF+Sbu<
z`RXr)v?LtCe9sG92#j$to5`XU*q)_*L;B12oorG8J29Ho`zEz1C?v2yjNP${_z`W3
z1fujdPr{SdMmVIqwJ2fbe!mxF#SUm2D-hg{4@-T{g(9q=j}1$hki6$h;uV=D)Q71g
zV0IttcV_eTgHh%~9P!hNX3uYQIWNQU;gSjJ%%buv)Mt52@gfeNRl1hBEWGFqBs%Dt
zL7z@A9zaz6ViUj*X+~vj$IDIzK2=SsJ>@V(_)y?o>ZdTRoSI$@ju<dfr8$o*rAf=;
z0%IVLE~&9RSQz;1<`gChZFAhVJm#{w1dD9fYt?`K(<}e7;Or!ZEEeFe7Zczv?PO=^
z5G2#_Fo=x+!7JoIn9>`CzD1Yc3U8!@A3(3|Wm3!5Z@mW0MR&ytu`_r`MZCMD6&I4|
z<Q4jOF0+BqjrC%|uV=V^TP6M7`UvqSe8}!`oNsO8U&2`_k57vWfhK`w<|Ao=h<`H3
z`?)V}&o!N<^14L^1Oom966nt1#T&@2c;|oY*JcCOr%pseE_Mj@pmbj8PWL!TYaG?M
z2xn~0?**n_n9xCwiNs~n=oG=IxT^dH!!vi0kaJ^;aZC1qD7*$S-=JOt9D119l;OW-
zf^;eq&`Nz<SjGC>a*sbI(bn6-#(~MI?<<gk?gzyl7na1r_AOEeS>co1mU04}quLz|
z!_7Hcg{c#hI@9S0^~H8L+%tdODlQO*J1#fCz}DZS1I%TIa?05mw1-m~8@okac@<)y
zZwWQOQq4L&5FCqLUxYoYnai-bdp3~*W#7T98(YDZIJP1PZ%~@PLOJaO0k<2maeWYK
zknXb<@e2U?+|+l>%v&Q|tdU7`9VUOWkpV~6-o>z5BWpuwASdZEzL5n$MYfop#U(e}
zT#;G>A3S4x$U*->cdyayBK!eVAzy&tbIAhelqoGPIWH#Jp(X4C^U`viynRLhdoi>3
zMxI0;tof5J(|fy+bdiekE|ptKgT@KizMfL_MK;XBaVMCv$=rDI3(0CJOxrHD%FgUa
z7tz5P_1A@T-w~gZ@Q3&Zq2t2}zhKtIQ+eZ}9)DTMH{CGRU^Gm1=ZQ5^X_)YGM)(xV
z_L0o4UBp$7QVKz!o3Tx=gcg#`1_S?RSguoBAs0NAxFqkeYWcD48*)uocaJ3RFb6se
zNL*><3JRdVuPDg&v=2BUIK##SLeKLBlA2Js9@|+y+Zl}+sQw%I?D;Xx$x0ZF-S5t6
zm5W{xa~h*68MS;w;etPwsolaE>|#sPicY-f)z?ZvH&;bz{NFccN_QNjgd3B_;B{f`
z`GiT$AwU^bNHn#%WUM{FTad+`6<S}%7-qY;0oEp9!^RKqKbh0a@=?`Cc_G{zp9FDh
zbP4%-Xq#ULjCJgpqZN<OnwL2_0Q`(m@zcKVEZ`&f_nw=~tmo+*8-<CcI_t58w^wY~
zs3Il;wa(Mil^=E_Q4M+Vt)CxT&R%SfI?|mMeZcOIVBl|cn!76E2)h!2voK#GwHQpy
z1FU9U#<eg7Rp7h2IE-BWcqQPF43j3kgYz*Sju5OD%Pl-hyNxNHU14^+FNRulV*D*(
z=8t`uvlo@nlQcO2+*siK!u~=9F<;|h;#xk&i*KtZ$trC`p}T_0mmSaC`B|jgNgf1?
zfY&K&31;Lj633+kt#JAKTgnw{QMe?>(O^>@g@neDA3#=amJSf=?cIMAziKuW+MVH_
zb>u%3t1&&CH<lRQ#}_|-Gpj_KhIlkDMxUY*SAdBw;&!D5YHt$<!#){!lM6g1tu`b+
zzh<M(S;!%_g<;|gcAvx~jbFwrsNrw*&7>Iohq8d;N?(mhH&G|X;vo>#!pphu?Y67%
zK)C&vv`G?(u|8QOBSz)3*Ik)-0O#{Zw}xE)gw{9k&h@9SgZ$>B7^IO=Z4@&w+Bhkr
z{sPuL3A>%)SO&qE+-$12?6*z;#k6%gblt>CRH&A>HUm_>P?(xWh$0revI95P_n3cs
z<C0UldJ;FEaHQ0{oo`NJ96DPSp!MltY!&kGF9N&jAF08JII5pxGO3>KokuXS#F0>*
zVjVVzi$*F4zVTMN%TX#jOxI=OvviTC(=2w(_gk(J-&dXT8fIWkZ2>khpnLx#coevU
z*%KOXcoI7OfjIWyfN!;=pJOIP7W|XtVnZf>)T!wW@`a$av5DH>^-I3|Xg!;xCc~DR
z@X};8`|Gc^x7f%1Npm{y1BEzcK74>Wr(#95UUbJ*z?{#wW{&5Zn`A#@8*921CDbY6
zb*joi3KZM_rsq87uGmvhISoEk_A)a=o7g>F{j_dOP=>S@h>Jw3yO1GwZ+%XIqMf{B
zx$KZypJ>-wn9giJ^xo(+(BRHN4V|fJnhcV;c<P%m*aRMa=hMsl0>7buJ!I6MkcTki
zwh9YqWj6NT=$`s^t3xG4J3d?Gx-cwqDCcvG>(F4;py;xxUmTt>a?&ZF=t}fk#P<`I
zAY5s_M}#|nJq|MzQGKZUf|~nFPAsi@246;J!PR40y>a1MATj2}&2|BV>hFHflNT57
z9aOuuK1WS#f0Jv=DR33cJz1$dDpVQIktU#@m2)XFeQ82x+jTIt9Vc*n_K|uAtF%Ut
z{@VGPv9O?x!fLqDIcYs6_;W-l73Dh$0e-CDwQ25>qoTlgktuq&scCUbey1T=Z<)*|
z+Z>aGHxEghWl}3k+B`}K_G5k$l&N+~gfpC(31`ajv>v+f-6ZKI35+N7Z7fXtC|2U1
zGn6j19<Xz%aK|xvAmvRgAwD!WGt&3*ULLGrEV{(_`}!*W>TlJ9i2j`EzO{|#<QQ<g
zKnSY`u(_Lm9;B^0E8|>m31$+4g!4be<h_}1vI2?qaS|P+g~}L*B)Hb+b;EtW;(peK
z5nIz0F@^IJFqRaS#@BrCKNw-#mvCdlFjRx*a&{l7;M(*%GTL=_yOBYKgMoq2U^a=1
z+>>uRQ>cZE`{zygr;94t%izB9sz}S%VE@e<l<LB>)}3$GN48`t?V2F9OdopG2rD|>
zBdp%Ne=4R86Kcc8#K(6<q+J+U*w??)fA{De4*y1<Hr2u0|0k5@dH^6(Hpa#43cN|r
zpYexu9$DXtp2PAHFy1rr;1OWCe_Ib>Aq)CdQnB&2P`<`$%u&CjcB1PLdR0=$@I*#4
zmE;#TKV6T{EmUNUF<ok0_)x2JtDs}mcz*Tg&)bvj#1-2Z@l(wSyQn_e?IJcuBhVFr
z^1`=bTpysi!>WjwI`>+WVmm2>*dvXu8EAv~iGP+RLju-rtWw|Gzwr<PJXqXj4I?6=
z%udWVgyT|gfzFWI*z^l*^1%{;the5pO{%t$x<OUmnr$Sgio6Z(*TgK}8N10>(JF`2
zL2vCyYI0tFh-FY?q}>dit0{W*qf`KP5sKMxc!w^10!B<_#As4Lyl2^#Ym`5d71%rb
znZjQ8h5lS+EX#uU#hU_OKz`2He2Uo4&Ill^t95Th$VlouD7s_&zRAzZM*_qI5SsxE
zK|Z_+)qC!i!5;n~p&69=ARx-~2lC54KznZmt;J@CX)`>yBTFHr$aDGZ;~g9yeNL}?
zuTece|I%70!nnH5Fh_SYX{G{`fd2?m#}d@<WbG%>gfhdi9HXCBITBXRbb*1V9)sX*
z<2VyeYe0C3SE=1PHQkrfko`7_tXbnm2x4QsW{H=)52okZ+1>^^>&FdavjmKBiu40Z
z7pt0)fBYRy*OE2G?YqhB-HCdZ`L7ZuD}LMsuc?u=43=USNZ@8siwFQBu^IPUJiMVX
zNJdNHq!+H!;<J>!X;xeRZ^JJM1;;pqf_M91dBmDYP<PItu{@A>LxV?A_f3iof3Zwq
zD%u$n{EY3Te~K*KCX(NR#wpd`LK{=3C<hfFmd3H<jX3T?QeXB1f^b#<Z@}C(xXSpU
zqexj^6{~IJgk6!@q?jZcd8P2NDEugzNrM08aiXurdK3?9#DN0HT;lS3R%Bu*{IRY1
z6Xf6J=fIBqL5~UjW)p8ay*dz7f*0=EA~>Mb!5QL+&h4&$0;>c{553%^#!2h*e)N>m
zpXmBecEo{1FHY*&ok(7RAA|H!rq4P|>;&hY_OkgFJA;hRjxJbzjaR{v>LKH<TsrHS
z!kdvdI~kx7ppXa)Wi}zaO;R(b9`z;d3Hs{m>pct-*(Bba%9E{OcG&>{8;iX@VUW^b
z68|uC;VsP~$&@~7!gGp&6yv7sS;2u0V_RfRqer0>bGr_0JGr9U-<IHP1HmMYl}Y8E
z!Tu(QlOjJ_30~d@x5-?x+u)`PLBIgW4CH+^18d&J-qg9p`kb0#(ppLWbjVS&LQFFs
z_d0tC^8!1ScIGGBN9T_mNUg?_5<Z~W&;slp-mRDI6Vr;cAnETyV~6St-~`^n1<)pO
zNpaue^o|vYsdI_`#vVHUbUES(SGMwJL&b}M2f6nI8Hx6dZMsVMzYpWy3DWXl?ZipG
zf1B*b3}2OXhak4)7KL*b4#+48oCI<1dD;P3kma7!2SyAIOFEVR)2=v_ic~&fmJP>g
zIl6vXQLjHq!soY#nIO7$aSNC7v4-HgsyN5rUE!ntI%H8oW(vU%o;J-2kr3}acH4TT
z>7ojpjKfAb)}8XVlLAa4{w_MpOg$Q7q@6OY+{9iL?*)<?F{6fZhe<IV0hXe2AckwC
zI`9{j2XV2kGFjsSrDzTG2bVY!HJg8>1zF28-63k}>IT4Y5U=Eh@6xu**?E$@$BsBS
zhM7g;h7d6lwMwOTVZ(vhu~!-%?%hjM;KkO(z&UrftVaU{X4a;zU~h~hkFe{@sxQ@k
zKhpehdpS=$jTUTDKV$dmh_;?FCV!>?4%8ja9Xn9T{Sb{|A))WTy)irAWm-y<!d}Ah
z0*V-`j54KO>)uV;Or3DzRJQI9C+|#0F-;b|6HfW_?J>A#l7s+R8nk|sV#KC4%K$ve
za>t#*RF{;^exi|QBOp)w^<^IM7Y!^ELP=N2{1=r@?a~!|*Olp!w^PSxg@)I8Ufr+~
zA$uO;aG?qste4-`ZnAW~!4-f}xbFePa};B+$EyP}pHtdUg+*T~jiSFH+z#XlAMF}>
zexwgfBhiYHdzFf}(u6&y&veJ)a;N<xZ)y^d!YC3+VEvE{p$Mmnqj=J72RHO%->LJE
zs}FI-m*pQ$Jng|V;4S49vM^M-+aBi}QD~KIY0w=67@T=RM4uJswkv3q<jac7By<Y;
zOu7B9`6Tk2ue1G5EVt`lA)Kd7kOY_tG-Ew$l3M^E0@gYKLwkGoq92f5_5^MuYjp=G
zxXRYxb>3>JsQj+u##|YpTJ~_oF*U1l7@?i~mJ2M-A_Ff%D0~w@Z&WaI0Uy~CANka6
zmbLPC`51VFws6cpyj?m!j^gF(8%C~SE#&1;cp_^ID9XO6e06V*#J}uSP4N?Nxl`zd
zaLJBgIL9bsKY52&SwB?TJA3(sKKA#_-X>So0V}!?>=do0c$cVar>-kuxB$}Oj4v)_
zHp4DO5qeA=iBMA#2rw@ZeH#?W56nRQvo7eAwvn6%_{SHvdUs49nEc6*8Fo|W;WPp!
z;YB(0gDB!gT_z5fJFIy83WrI^5ar^YUbyE_Ig-maS@1j`@Ytw!`3-Q|;t66(s_HED
z%?rowf06iXQ0{#)x8N?6VVnFKbh2G08gpLrqiSq2m=7QI^pq9>v$y7rB0;G^h#mae
z%?d#pS7L~QH!HmG@9h!6HSw2$K?=-u&<bYwMI*N8%b>6dhqnlBhP*3hrOAvAftmqU
zeEh@HX`J*lq4*D9-kb)imD}~dnHuAj#1MR{8bri?WYMM+-{ay%s~^JIO_~`{3f<bx
z6IJux>A^SKKrbz`yFUX=xKU0*EB}K1O<BS);G~R;HvdKswU_6r0$})cZRaK6b>bEa
zk-vE-qg+6|>k`LJmcOo2pQufEI37awNl|FwnqLmgKGj$F_w^<bdRlJd_EKA)9J>)K
z-<;C^rS}0glE&URrgwb}Q*ox8?>(ZLO`<K99(nh;b}U->^&DB#RKdUgD`hoeE4=xL
zGFWKmq=)a-&L=By+e`_O0A&h3;g0l(L7<IslE&^*AXP>c=4VCrYoOG@iqpaNlM;Pe
zh^Z7@bftK4(%UF7G&Y;D6Mxjc|3?%0I`{kVY<}O9HR3%S+K`R_ahHTpl)d$C;+r5n
z9m6u>`ksI$kWGi(2HZGEb3sWO^MW8x^Oj$>E84DKT^2mur@_r`xNjtO7CfeX!2!^4
zbT?~c>alWXqM8Yl5Y&BKCWZ(Vkk1=U%fa#?b?$d(zrX%ff@Kn_JDJ(3U%DpNed`m|
zrsd`7EtIh%h8W9CSkOI}H@)!<!lW|Qizs<4M4T)S&`@#sw3N`a!|gbdOEpUh>EhWT
zLt_0~rpS|#gM|5XW#Al>CB@>7#+;i;9R8CI34V~aPll|sa!fsT*z;FS2>8mlrcZUp
zGKm8k7R(0tISz~g7kEIjA=OlUvcPk#`(p~~Y0rEqRZVzC8B>@lQ}(*aF25!t<?F?a
zt*&$O9z)uh<o4q(MqrQ*tqf#z>ww=iD5I^Gh*oU_vPH4971pC3BSt>;1B4g|TKPaQ
z*!NP^4JDnX6>f>vvtG~qfEY>62E4esPzh5Xq_VYnueSw#B!D)ELTAGzzo-V*=u}0N
z|L(iikbJ5QC7!#fkx4IPExLPl!lC@ZB>*_X&6&XJ2JF!%ml@(*a=?qA`n+JjAMtNw
zO)FwU$_E5D=~eA_je@y57~JxzYF+6;E!0_&trAVcN#FM4v|RZYd*=I??{*oVCn>X%
zne2Zoz!_A=@Nt1_?UdLCLQ%$`-w<*$i*H}Ry-3(es%aDV1FWU(R*FWr?#^K7Nr?#3
z0@IU2tglJF;<8{7hbYpKL-CyK8~}cWE+Q|>`W!LkkSp@Bdb`-MBPt+j+1;imBZ;}9
zHsOv_XuZ-tL9YM(pI6+aqQ<tHejhM)L5oE%mTzlU&V#q;3}))CsELDFKPB2rOvRsJ
zpP$BiRg@XNSYxIj%(%=*AL8sU0C`v)8(Ii%^EUp?dRq=giNc*6A<oEkEb6<@fW7IZ
zEHk}zHf2cK@IptBL5ff9c%HG?aEkTPr~0ud9=*C~>7XNf!vIZ(zPbE6{SX>+n;E8i
z<6#vf^goau?vO4!p@tz;bzX)$UgGuKWsYx!hIjAtz?sAY-RkNNV)o|fzeimU&nuI;
z*^@+-jnuVb&CaZC1_64qd5?A>DEh?z38&c?h4}-i*~hW<jQEQqmiDyIZU^)i{j~Xq
zEc8mGG+!#yTsd9z8l?0IaMQnDeGeOrSNzlzaS<0Vd3eKL+W%((Xh@C+#r59-zI79J
zm>bE4UvXyd)2iiokBjZnwRenUQ&%MCageTBPNgs}DVsws{#|ur8SYl1`~09lyZDW^
zygRb0sqNUPDnL1P+9x$WdAgcxH?&rk4W1k*A&GGzIZ?VOU}SG+zl#Yx)7W@=PnsSr
zS;VBxCASt0x~^2d5oSSAAgmwo0S<xAMdRpAA@g9ioAHMeXrV&zq~8Ub@JA`mkdalH
zb`M>}y1=Gw&#}U#Ne1(G^v5@#`UpG7pI6~Prg^`$Hg80p4ph9QJfw8BQ8|D~y*^Z{
zb97?_TJS(5vpWewK2M$F>ph<^lQeiG9Op%M>KpLcD$T`<61>lpaE{d~CHzTQ#&+x%
zAa*@k&X%!DgUUL<p6oI8N;Thc2HawrpA7W)uodu0V66{5={a(i)Qw%=C%d!38@Fod
zthawiIK<N5$mz4%@~(>Sp%;6MtY@ekd^SH$vt<NZ9)1~;EPF0I;@Hmq$?iW8E>bq)
z1Q6v_F3$(;aXkm~?aI0a?r=CK&#N}rP?a7BSL{2(-|uho9ZZrt{pGUf3oIn$i){A<
z+ZeC6Q|EW*u9HYwDoy82pJokc7Tfz9n%1scB_90@nT!o&2s*GsYhTmy;dsB%G&K<N
z%<M!&-3t-D+JP=-dFKB1C~!H5+syqC$l2i>Rdl3CVv4Bn=vHq1wD5H6qJ&DhMXPUh
zDB~rS1c{_FK_VMD%wYnKwgLxN`kk8;ZoVm~S@|i$IAwT}w<u&toOk<H*?cXQvA%Pm
zRXgrb4w(DgXwgI~dcAZl4r(dl4R@*ekyHlx{2!=7wOgXOK@y+h3oGB{j?m@Qdbs9|
zpasb~O(jHa{J6qdbU-iB8~Z^kXp#ae$=_naG7)f-nQ*K$fo@S+ozdmw?j=n%hx!={
zc<-IM^%Z8KzCVm|`cqQ!;4ivLlLOnD$=<`a^tYdT>_x97jL4LQ#)5yA;;FB*is8pi
zHe^g03mxR-n-LYW0F&iR=tib>mJL*)e6F4C#lj!CBNF2};I_wt8GYk?dZiy~1n4;3
zy^^V)L3wgXNPgzhwf^(y*9Y&L22G}LYptt47>P+N*h$(O+<<8J&j87-Mfq>vf1ua(
zsCC;|rd7UwO;<r@DvZZFDo!TKmfPwU;2?dBRym@(H$*H|{|9>9Dkb^}#HtYpxQ;Gc
zt_wL%b3S5k82#QRgH`a~se5B#{*t&)7h%FJ@P~U~?qUVB&$ICav1Q|+Xq772!D!Gq
zkGc%UuX}R2dsGGNz)XnIl*wtTbKc)7^!qzJ3tQ}`_fNQIwZUE~yHgWYt2OI++f6dR
z3$Wt)0?#yW8I$vl6~VL?fMl_lku)|Md~;Yl`m5vvRD#ssU1C<*Vq!{kglVMz<qLek
z^@R8R0ylBg)xkJF>-e=qKyHqcgC2WRda&k|hnY$sg#fKG#to_ZN=O0csz>f3cg-EP
zumFAe3b1N<6o}sH=<Hv{een<5H#1lideXfeDt;WJ*ExZ|P=SY3=-MK>FAI&0yrZh%
zTeVk!-n{9$ajI--Fr$^)`UyCbO(tGr&?va1ovFUK2uz<Xy^?M>Er&=iwQ0cyd!_Yf
z<t}pUFJzfKuO~y%t-ory$hGEgS_8eCP>#R$BVnA|+9l{u;c3`YJ304K&1!iy7xFpm
zP#Pqx)wY?wbZ!qXYY8!t1`jW|UISXLSIeG7z4|X@4CesZ8A?8X$gaS_0QEP(Cb*S2
z^Lg%ayF1AsaM9|AzF0PK+Ss=N4h4SS@3GYwIh)4rKL6Eh&iV9i(&g`6t`*7q3+Ex_
z_SO3&`Vf2skAYGwsR-qY+>sLbHp)b71D6r#ax`FKKi#D;g8`tElF-?mfX5i?&(I!T
zw=342#&vC(&cG-Cfr{A!?d)+r!-y1h34F(<ic7V8_0LJtICq-MoHiU1!`qWrx~ANH
zTi5YO1!3<&xd)HNB92;?lC~3l?RPKc4`Tq%f{XdlpR}vOrf4tTb!F7P#=%RC4u&+W
z&QAbJMA{V+uUSm-4jrq_<*^05tmzf@!l<K{pAw^u9}e|*k1Y3cp&e@gdp{n+2w^%U
zpx6blB4uhyaIeiG!1E(~Lf^Xy`pf~RlIuySC>^@|XZarNY?j~%*bOq$=+!o}r?6_J
zxF2B)IFJ2O>!1#XFp|s)j|FxbI&K?1xOtdkW}m+~B6brGI7cCWc<q|LaV*hVo*ZU)
zUdQ@8sGiyz;}BHEr&;%i5w*8TVP6$3&LIx=wI4X$gahtNI=Der2zpk8b!sjU8NA2m
zS40=6a_u6BT`gUV4XoQRh=%E1SLmWpcP_H%OAhoh%|NPAG(VsN0{0U4{JhN)CJ037
z*r9(ii+0wY_h1FoW3Rw4u>322L{)`H(d#L}ACcMZ8Bx2&bs~6wn-LWt&tvO+`u{*>
z%lo~2Mo86pR#Ln|@k+0D!D6xZRAR?(f+(i=zb%*)YN&%eJ5euQ^Re`o6h%&S-Btsr
z>&Wm|Q9AXM3}dQxCtmCQBh)vcy&z|mzyb~xp04wO9QzDqwV>TbiOce|J2sCeTW{p*
zuJ&|K8s??Om}Y5m6gm%`goy)s@aEoSTqajV1dbpZOJM}9BpC{09XLX0n>fGUnl;<O
zLXh?6aDP^}`$GV9>Ii7GzwI9Z@6YC?y3h1LvMJG<WoIG~5Vi4{xmnkxauP_d`PNLW
z1h_KY(Vv*Ek5q0ZVML1@&&_9oSs)Y&f6D~|-Sjq5ud{H%@0-gI-QV(UM!NvbjrZq#
z-x9y&@d!2-$<x;Ja1@$WYvcPN&HhX|5hMI|wLmR{=lfry#n7b2;5Yacd+wFmlrnRL
zjdi6V!|MIFVig0{4I!`bV=$a=4Xc^|^|!wavy|>R27Pdwvnm@Y-Lo$WP|cfB1juBL
zSJuOy#P+rP{H-AsuJ?Uu<sS0-Q>oU&a_98#yi6|knIE3pBZq0hnmmH%h2fJ=nOHe@
zairh4@91?b*Q<X~qBeH0_Yc8y>|wg{H_+MHU8DDt-JxMkauKraVjJ97Ber<Ir-m&w
zDe~F+L7KBLl_P#7UTe%=<~z7Sp6suIULpGo12#_%23esaZu&0T(BQV6!Q*5iM*aL9
z#*afHlD|B6j3+m)WB<scUZJGJtbepA`9E~;8+wO7mc8UEPb+U(yoUQWf+J@^-E(N;
zm(*s&vq0J6#oih2kTV-hw=6w+(u)y4I!Zc=Hr00aIC$bIa!DWV+c8ekjJ|k~E5jca
zI0xGUNQ?pC0K-oYaMYy0o;fd|;`^ZnB(Wy~)ty^vE|iT+*8)!uWl2ehS6f3GWa3A}
z19*Lv?rO~KbvE`xyS`|E7s!EXZFJlkMIH>fW1})@@nl=bmg1Fk8m>X<W%e3G-Wvsd
z3fU<8CiOb)f`gp6_xxlycxME7Zz;@o#yuW@JX!591WDKRzG=NLoTo!jA7JJFw)P8n
z6?`V+F-yL_o>n)!?2s+7QV7{<4bq(`+f$Hnh+jI-{Uf2Z9xFqjcIOX=MwaV@+W=CW
z=PWO#C`j{WBXEQW;(tewZcx*&3PNgxTl~sOhWyg5jJKfLrjtEzNOoA9W<p)OFpe`d
z`_`3V5vaf?$zOm(cWL02S!K5deJgb*hslk&F)tH8oPBt!9p37a;(2#@EIT^ybY3r|
z7|HO9^AVhsLLr>Qe<Qs9)}v<Z3=kG<Mp*v?l>~S**pe+qd(PE@y|e})`SM@Xu!2V=
zXg3iP+g!4Z;vBaP%;U${mON8|I3Q1i;Uw1W1nz!9Dg#7yiSJ}*-*j%=1%EJ<qlqT(
zo~$gl`ILVZ^iJ{z4N4?ST*IDIO5LR`Os3tlTx)$XYW8KY+jxUX_2m2I=u@3VwhVn5
zw>$YKhtFxmX>^)mtkGFvuM(TFvks-XwO2+}aM_~)&B0hAKnkCgIFP@q#9Dk_>fJ5@
zb;}qw{YEY$cT$8t;O}<j*56lp`$aW(r&C(yYlf8QlMY%R@q1#v7XZbSGYy8mV!qV@
zVBakt2ZM|E+^6%XA}n1^O~uAa3LwObuLUn7nK48U1ekgZ)WkyEj_ithsJ6Uw-{2Jq
z7Yk)t_}V<rS7)4tjy03G^%};RAC4%^@bAai&G0UY`St~t{gjZ75M#g9!hE;sv(`z7
zjEgbA&Ir`LyJ&d_St6gA@&cua%EK;kyi`6Gme2u)%BcEOrmmHp3M!g@Or5sNFZWHx
zE}iyed64k%e;_pjQ;lzBr`P7uBd=#^ZEv&9*MRqQCZ+~DB2;#$vS~K(XxTMzkl8?=
zS7_pDGbV9Q!j*oAQt}-hCkE!Ow3>J?v;{xHUkI2C9HW?kks`H7+SBpqAKRf`rT+(#
zHU!R$w%D-yp&zwUg&dd#^MlXT;OQ6dF=aV2?A3?Ox8Y*Nkx>WzOZse>ZZ$>O31<mE
zAXrG@1hd}9#$>7wyL(3YSAtZ+lQj{YE&=LcQU&EpiF$gp4c*x(MHEW<VKcPp9&Z?a
z{c^43woAl<Vh{gPP9xot^Qb>!^Sz83le~6OxM}F^md-4<79efOyAw;LGG33c`F=S`
z3RCazc=5n(y|yS5HblXSc9#(~wZ^P8DDTfY<~-E)8^F$pzxXB3Ty8HD<<1#Wo6XR;
z;K5yU16U<ZUdcHJhFd}$_j)_@5VMveTzmfIEt1}_*X{T9SoNOV3b%{#{PiYMfh*Ew
zG?f?nY~QHGx)|(|<8_NAH+izi8h>={QYqC)>o67xT};+*Nt0sDk;QB;5LsXbKVUb5
z?@N7ar?aZkCZFJ$^*lDf{wV^)e=E`ZNo(K;^*UD!#$k_g<9q&)jacrad!6k+3Hk8e
z<>Axj6Dn%*;9ZX*=35l3f;qb@`@JCA&CubeY0BRgX@GPQzto09T4v#qqR_QUTloFS
z;VKRIXv%%x-><JPuBvqA#Yw@ye*K4YY5;yu-TYXjUViSB(^gQM!5AO!2<AFwX+Y^1
zSIqwT@!$HB^YO9v>W}>j)-fxwhh&OW1W9wQFIpdD4)j**Lap@{j^1!w1xn~=6|Q$Z
zd~V-<DZqEVt^0oCy8r?8sc*1+$~Q^hE>i%C|LT6P&AL*S!ot^ospk1wu!b+|58zy|
zl}=|Iz}V^kT}a6)1Z7e^7^8*$4|IWy>}ija1r|)r$$fU7<g7~tw!&o1mHf0vk3OJ$
zxNqWwAs80YR+ux<tg)yHbo~!5K0!(nHLL6yT1SXGJ@oyw%1<GWqW5iFk0NA(>hlab
zH>0NI?k_ya7La>BkA7a3w72QqQ%Bu+<`5h1)8_HND|PjITo19guN39#z~7alH&9)*
z>RPa3IE!&#o$HaYc_+9Mn<M_IWrhhXNqD|ck6zXNO~NLQ%-Cbng{LI3+mi(75|!Jv
z{BDf}zqf6+_b3&%5fdbpu=rG9^7+o~<y^0$Ooe4bjceNZgFGh(b@}?Gl1m0#?3eTQ
zj`K!YAaMq)JI>gGJ;KiYO|eVi(uEaR93IEgxRkmjqqr4bZkCp-pa#^_<GXYFW|C?K
z4_rhPvD8ww({q{5{xVM5P#55k%U0Bi26hCWsUGBl(Mr$zZ?>fObk@^NT#oTHH?044
zAqs(*YEh{(<pBMI#qdS|RALqahx}2<O**aFp92PZRPw^tH^mr0g)m}d>Dqz(o;vTP
zV%DRDYT_28@!a2COVq1`*VTl0>;EqHT?KS7$i9O|uZvKe{CoFjbyvBo=v7jF4z+_T
z2-%gVl?XsA3VE45E&wcG{YJ~2;in1)(YH*!Ab|f-q%rxOF29K>I3I^b%Bbi=2;mRO
zcL7=-%E7K{0Fl5!&Iw3P6EsQL<Krykp?|J**qDI84Iz(=DbHkTad9S+UE!%W#cc}k
zTKiQ0&JL>+v9aWQ34nv0s8QR-JBtq|Y0{)DEy}%L@67Sw_31~l9ZUx4`E}M9KqUZN
z>&sSIq;ShkhPA*mlo{;qdO+p=h>K;z#QMw2rF)9D%OB50wl;2@3U2ii4x=)jD1Cg8
z`0s>BJg(g*zw12?Slg9uNWtdD3k0_F&&aDPxdfkQltR3T#YSJy=nwTgSyJ@r(yL40
zg71lDtN2<Ib~ng9yH6n-Jt>z6UHC!VR&c7XhIJUD{{a7DS&<%E{ax$s?LCDiklLmp
zUvJnUtx5|AToZ&v0$BZKoilmRo(wg!kE;spU4^YjC0UrSQCAwNvp|-c(w#qFe_+=1
z73%qS=4-<Wf(;^m(6zFQS%W#BU_@J)D3euykBm9c&J3w=kV9R*ro#N;H^}TU{&cGB
zuGzrmo2lUz{QR9X6?xV6Lp=SNgyZFE?2h5>43~yJm#^gXs21?e#RuQo-*U3aovm?j
z&1k1;&G}E*t4s)muF6*pYjYnpcD6LmJMCu)tZlY|0r7e%E&I}dVs;PAIA>n(xWJav
zDovjxAY&C@F|vI6d&tJ*LtW_C!9MDpqxn<V=l;p<2ac;Z0EAi*CDCGPED-nM$y~mG
zSc>^qcZRy_$1)>THNUf79fi^B4sBGFdYjN+96<_{c;nashk(2D0l)G?J_lK>op9j9
zAqre2^HSO^!5G<S6HLT=_e_B5x*}Mb&;MVuNXPxrqCK@o7JWv61vQUwgj3;u%G?h5
z1-u~vX7?D+?f1_BC2s`lFtl{M^(c4qpmyM@C?}*o(BvLMN3;7rL&)ik=!kbW@)-;8
zy+6VoW5X-~uwuuI(F$1d@B_as39Szg`{g?vojV|70G3OM*WB9+A26cF1vQY)2-o%m
zCWhQ^5tZ%#rY<N$!SPkQUjiSB*X{SM0~F059>C9R8rY%vyLFm;x?P@gY(6ug?`2SZ
zU}sO*njEZ~+$bbRiihQPRxPNgLG+%CKlDCvJy4Xk;Bu90b6dJ-*_~5;Hj2db*3z~*
z*7}cY$hYS2aF&vhb=&V@**f<F;-wI~S(V2_0GTCtqoINkP{>%OBdM446aPZjw}>K>
zHM^!`&B%C`1{me<uY@X!{_Z?C!oO3{YlUAhggb40WGke5o`LOY6x__4qSa6;=(H5L
z|LuMV#pxIgoyzcq2fY0c1ZGMX3SLa<rWEYBW@xger`MtSWBfrqX>7WTtR6<1h4mTg
z-t*Y}K;4JA;U?MtuCIiJE`I%&D1DLnWr_94O0v?DESR>}iAuj~*`t0ZIkJM~<g&Dz
zyO>YrP&OXEe#i)3Q@mso5(x(mp<`l^)m`NZCo9EDBmR$$&uRcktN|q69sv2(3v&EH
zrKIyM;w6c(R>AHbA0?@DO-wH%S%=GYkOw*g40K)fudA5g&x1w2bt{+#G_EVj_43Zw
zN8R{=d`7IGI4#V-;QR+TlJ}%pI|AS)@w|76ZA8o`6;ALX3hERUXjzxc4{qSMQL*%I
zS#28kd{1~9{l2{pd^_Qdg9yw;r62ZhX{gI9VDq?Po%aC=B8<ZzqpeX$=f6S9S3QKd
zkQ{$dqn8<n&yXA5y0TaN3s*A@X{w6XQqMk=Vi9V#Sqqb%G(@J!v!{){o68}PH=F#D
z;1AC<pZqHGi79G3Et?9S2zpvnQuG5`L*Y7->5wl67YL$UQ9SKt`oq<V4prZ38u%Ya
zR~^<=--dw+LnK5xhk&GjbZ>;DbPFg5N{57WN=c3e0qHJ5r8@^A-5o=^b1<0SdA~oo
zF0R4O`Ni|x&mA~u{o34JhZbWYM9aByGg~Gt&|=G8=HkN|4jzLd(|vh_yyC`=&ejtE
z+^n(LDw*2)H^kH`+ri!a=9T<EEPprU=O2JYs_z_(fisnmko6w+J~*BHWJ~vk(@U3R
zi}O2Ue8|0n%)J7ZmNUf{#em<+S9Y;?rhl5wM9^f$IMOc~aL9m!A9W$o+Z0x~s=NSM
zug(y2rM9K#ce|;$4HYd)=gcYH$ePe_{vc>FymVJPC*wVwu~2Ic;h2&J1ZZ{tJa*<=
z`@Ps72Y#+R{DyWUE(8O8d{3>-)>7Ed-$<IpC@4dJI{V2&W5@wHjgLt#=%u}ubrA49
zWUB{c)hUfZo}#(N)_1HvANwf=u2gyP_-BMS+^(zv46WEI`x6N%|JEu*Hfk1lEg4-(
z_}dr|;5mE6ev~JDQ;hdAEt`qe;S1bctnkVHagcn>6+_@RJJByy3_t%iNr!>^wD^=w
z7>nbh6h4I-;3+)-uvlYrxKTi&vS#sK{R(?1{F3j2ITIN5kuIq&K6Y6y#d&I7A$r%~
zvWi<q{I#rhYfFyA;!^ySJWK{HHd;zUL34`Rzf{SgcRCUDc-PY}{OdX9l53Z$<oPUj
z!`S8oZ=1W)Fut6$*15XB&&^y=u%>hTxf(9*%iePq^GljMcNMx|ZVtdv>r>_(l0W>C
zdnSJGHezzj+uiihtMz&(TJ0l2O(>1*xp#+-pkBwXI@io(CvnVQmX*Dd=c1|f_bXhA
zZ)gdrVXc-I<m?eV3v!tE5qn;h@I!UmMduVIFzU0O>(c%i;On6hG0pj9HIT?;AXl(`
ze2!k1tb0Z~9P03u1>#fF3OHoNCe~c`6DcBlb;xR2!Q-W%JTpSu@p?tgQfbb?^+o(l
z*My|mV*9MP+1?3r=$gc*e!D3jkqRzK?`Nw!^cz7UCbE;B)?B@TURy=#>>Bz#xQG(f
zt-`TSSv4wIF{e$pIz(V&x8Xs^_P&hi4&cBbWON%!?@nEaW(yD8&OrhyaTbZ5&qTi+
zuQ!0fue$PQ=tLg82qZy<_c;`^M~|-JlFjc}YLHXPpOt7Q>~QYzX}q9lE7@@~E*WNi
zab1Q3jN@Il9RV4!LBb^+hZvd<l!v9)K<W0w{K4H`p~nOG3dQiN56mv*3(8-WgV>v-
zrUD(h{ep0&lS&il{Mx`2xLFgUY@)a^o)novvCV1Kxq`vJQY@#U>}<%?8MULKfiYJV
zwL>NSt8H0FX1aZ*>TmlDAHf<JY`aC4KC%0gj>Zz$d-TXpwh8V1v~4mPmm^W#eKzet
zM{v&gwW~ZyC0_&PW$9dH^WGA%;k!#m2i^u|`z1sk7)1yZ^k(#;N*^#Z^fpJvc^4&K
ztLQeh=Fjzi1Q^zi0Vkzz_Qd=6>m2nX@oykU?`Jxvh5UO1j#;v>)g_MNqCO4~i-St@
zH~8a9%2XhPowooxpVsoNo%P4_4{x&`3_J366p{5*<P=GvqWWYP1mjw@1W8$^=EI4)
z7%;|ev3m6)rtt2%(MWUBO_q&xKkY~EI)Mbn!SOYA8YZr$9|KG?G;8->T2n#f?A2Re
z<LjmmFs)4mo}@5oJdr={<0ns3oBA5p#dJ9+6!>oM`<)tzhH>@xD0!E9HMoN=r1uEc
z+5u#Rl%8O61&6F>g`Wp7w$t#`MKl4kd)5>r;g{pMLRw2y+~0r$;=tuxK!6@<cbO?}
z_AVPR3~T`ro&@i>scSwlbNaogff&0eVQ|*VtR(CRx53d~FZ0M*eF<ca6?B)tFTx;d
z`euhjYV}V<t^Q%T#;@8N(OD+=hq`0CdjaH??KSL+64B5}=V5Ws+_dbc>Y6R_CO~5Z
zFuq@Pyh$dxj8d{<2;{;7uv!A(%Jt^@a57xeze}BPs25|re?f9rN|~{xaozww*1|nq
z&wP5FZ8(b7>i|^o^NW%Em`iISm~kKyQA`~ox3e%*Gu#81<j{unEZFS5zojf80;@i{
zh7tUBCfVzYL>n#cHcm8z*FAj5;|W*WzO%)yx=$#KE0_2rmTTKAgRY>2)};U~SKTgF
z-8>XMikiwfi5#B(?hTExp~;`gko)-LIeN+=gDda>4TS;Zk++U>>So7e&c0!P5-p*}
z-3~U>)UQ&F0VE-!cp+8YX_(GtfqzlFSR@T!+~`JH-7u|Z%rteW?;+;tEF>07bzwQ&
z=%!pcf-PJ4n=pXV!PKU>*L|OvT_&Dlrd8W%CX+t_k2F~O9sUaQq+zaesj)fWe=WYW
z8MkQnZv9?FfLbwRPl0PE!?ngS0d!d$s_#s;yDneqT5?hh46O!lr20XP75}j2jV<_=
z8$i&h@ef7So^*cJLY*T}?$3-;Wzfb_0L>O4TxAttTtY%d>Qh&h75W`(G&IGx3SslI
zDn!mXy2GFsi0C3#-1?jIl`OzlRs4~Y*{%tmKc~2DE@&1Duqly~4f*7lBhwvEZQ0u}
z5?~^-eIFw46`{+5ks3r!)Q30ahxGNb`s#>&ao2zae3gD-8yq7gTS3xdv8u&^nVY3c
zsegw88C&<>GG8_xPgap^sMB90qcen9e@kSy-}4j>TxzRa<vdYIs-4z!Y@G%;32H*0
z#Li!rb4q<Ea>3NZWohB6V^}<}@U$_LI{1Dsjo?zC1H0KfHUny|T9r{3_-UzGzX)m0
zr2wP{Sb8%3_i4SRA)?5RTdjIpB&S(j7)zti$J4**)J7luA8zD1)Auw6=96@Ws67mi
ztyFHbzXJ+FX&{ePKYnx7WzTd9a`LSdOj+7-JZXYR1g2`*kFVI`DFfH3I{E{DsoW;o
zcAP{mB_);eOWz0^dF}b<dXrZBix)ygnxrYjFFH#;^09|Tiy*zW=K%A)DZp?tKIgi5
zhX3>%nw|;k)?ru()uD$0%dPCIu3P3a62a-0goW>(ITYe03|=zW1HeFNj<H)zy?<iD
z<)KS>Kp={MmX}gO_@pQU-p2Q~s7xu`VLsB9jiLS0P2O;3j{j38XhNjQpVy?N2fg}>
zQ_8hai&D6%Rn*c6W1Z0(7q%#zUt`>dsZ>JP4J9dLywy1jm&^zgvNq6iVr2?+M+%G5
z)NJu|LY@cy4AxRFnS1j<(9ywT1eW4<8=mP;2l*)!i%<(R9+9wWV{zF6cwBAjFC<VG
zv0OsiLnU<TJhI{;a8pBSDd|es^D}xtq=%Y-6YhDhcQSoi3hYmh>+LFX+%&OXB@fzF
zc1g#+>g;o6>29tpxqoj7%=CM@JpU{Wl47pu$H3+d5_0e4J2@oc;vyIwU@0#Duuj5F
z@wT>v!KI5jd?9R$@H%A2BN+zmX`xT1-U)!IvhcTOZV^PLn*m^wnIj!rMCZ60CWRB)
zsfBmGf2#%A=Lbf|Kw>Fe=_PviW=03a{20&a19Y+6sFl=qWH(cMGd1^7L|?OzV>}YB
zVPi&TD|TZbe?&e-wB{&E!04SG7jXIC<X$75DlHy<ea7X4Gl*>C2QOLphXJClM|eHX
zj|btOfRmSS+%PvV*Ajpco)+Muqfui56?ZbfxKqMTq#KJN5aTO2EcT5Vp^ZyUh8SX&
zLck^iC#MB3kibHqW8GZwBTMM^bXlU;Wo-hjDAGi|*v1B`7xFzI`Sa>aFs`G^lFKXE
zJ-2N{5?KPcW+OxDlPdxT4?r7tzl=?L<kmCJQP8xGGmjoSwjs!;!^%d!#~d$zzM*Cx
zqm9#~va9S>a##c1_q<`6{v`}KJ#~PF>ZTcuV^cSVoG?v}8D}+~LhF4@l)=qfehSr)
z7Q%?dp+5J~?>jbvS6@0LzMu+TYWQ8;ag14ueF}V>y8L&k^a>v3x@U}xdt&t;?0$|i
zILPK62kwMg(4?bc`-=&xqn|k_B3i;e?>iMfZu<S4-|2?E3IUd)Ql}X^bp6J5!J%oG
zoBzfYg|W3_qv}&ZosaFS6$8fRkDDvmaw=;F&+!k_s&qGi>L#4+8p|r*nG(SgR6ijY
z=t&;b^x=c6E*U*ANAukY8{%)}&RH`ql~QtDbNu;<XYN!-zVfYFOJd*oUQZj=TiVx@
zeU`YH^qZHJuUq-c)CGTe(ix6zV(W}<NUJXQ?=$C~W>l~6PJv&!pa7M=A4LG5##^r7
zD-pxEmvp-Qq}RZbA}}}&&zF$-dTj^CJXzKrScnhuH=3k~q*}j=5^tv2?<|31Bk7Km
zo#y)tpls8>8*XzIgis;Ik5V&8QGu5`IH(h5;s*6>6#3tiXU+HfY2q6{7R{z>|6xJ+
zF^?ty?-HJuVau+q#93~~Dq*o<Cp@|0XtneUU`!%=5V^Hsa9j6|$W7;K!?V?)Nh|_O
zy9~H^d%SPPJIf-*hm%-0(Ioy;{U_mx>2G2JX}8-KO9d*PEe&6Q?l{BuwU=`wHUsd2
zYA3&kUgWk`LtB9tg+CHk^5v&#jqeQ|2Fe?}KSZkhuEW)hXZ+&kry6mM4ed)+7Xrd@
z#^{3Z!6^RYVAH5YGm@_XQ!6F^ux3>qzJGvuAh!;)09L?4Kpdcx+a2M|pH<YqNnO04
z82H9~kR>Eaa-hO;Gk%}u;ev?-7D-SB);^)n3pCsjA#H2n&p@&ga#pQnOC{qsvnlEj
z_iJ<98B$ctzY;5lFmEvCs^`ZRyDG#?j05D4RGJG0`xG;h)rMDrgR!dZ^izg~O#axz
zOcIurHoJE&pdHSLw-d=(t@@*IBD0ua>e1#?nUj&c20Gmxjz^ghy*@fwM=|%Duyu|}
zH~6kmPxowIxEyDnvJ}5}jJRAt))-zU0P|2irH8*S7L7iXl;>M#u+Dk3RQ|X4(P7L~
z#ro?n5OMIV5H|m*f30&O4SZazknwrs;ukB>vWv{gPrlc20Fh~kli3rZ!!h;_XnNin
zGK25z*iPyHtnNYLP!voj6Nt{QnM+r|^D{4W5H;n$BF8q`pE&Wry?Uo1F+5p(ELgH@
zm^)GR?%C4uKP+GB3LT^Q-&ig*pj`5Bw=?^OkWEDavVn&)iElJ@;m0p^?=f`~izX%}
zwV%$WGusuY>P2S1qX+Ae#rPXR;$4+1*oi|i?m~f1W}t6_VTV!6Z|GhrATmn!6hN;g
z5O;NewMdyMA=@lpX5uN5f#9MPNQ;(bQegx$Su{T_*~N;tdXT*sM)a<Lqs!(W))S7#
zxQ}+X2{56A%`0tS2^7($tZxo9UEnm6{Im)BXaPl+t-OuV{9}ozwp}82spFo|;1!AS
zD0Ec3h`9lJrd8Oz-A=YTg9dg4==&c|^^q@NMqS^n=&(3jK4*N(?E&dw&gOQ9z(Vzg
z`z*INkEh&O9h^g8Vd8b_RFdg^H&)TX!(YGC{M;VRkymNIAh}G!P)r0m?nI9vZUFUa
z;de=_>qUV10bl&uXq)c2O&-SE#w&iY)%;qxjV~$Xj!Sq}=)MVm6V1a<t>XNt0oHb>
zz&BT|dh(O;ZmS`!*Td!PsfGV8qW9!UpsOw6c3;?{M?5XG%Of}7NKO;2*Z}GM*a$H9
ztrrjb6s431h=xE;*Ts|qhMH~f;7@CJmEC=3sL@i0Md6wiPK1f8e;A-3{Yos-6?`0p
z^@o;W7sRm#ey9D7@)Lu8K*g|q4w<T64y*OPmgtvan!aX8e^9NgkawG|bYmHrLZfc*
zPsZgv1dsru7GR{Ul$Yxjcan4IQhJs9Tv+JgYEZ!`y<X&cbkbQ~3<o{H$58$bn+HkT
z!q!<jOpk2t+ibA^%Tkb2u{q6os}8JkewOPXf4dg@>jT#~{M}Kz$hs=!7}np?zsJ(4
zBEmME8Xjc;Sxv*i=uP(h*Cf?;w&%hF7yTogh9*;9t8R#z{53~7K{iR2qNI!N_pmWu
zT7$0raKuHmC)xs)b9p4YLnO49=G)=T5(bLb+epp*WN^#sArE!2oFxh|9P2D6FH}FW
z&zj_Oaz;fOt*w9C>%BE7sH;~d-!9vgp%uIlh%HoTK<EFgc5g9>0o9R>f8-)LaFh*K
z-{6%9;(vWTa~qa<NY(^7IF}h3$~B7d8@`!B%KkuTqt<4KopV}O)!S@~oL`@2!Zifd
zh#JP8W7Ft4xC1O=X5o=Ji#zoXb#43DeTa@>HA>O00KKM1#~BZW4b{vxj9`qmifQ-|
z5A5UDuRa8h8#w0;3)!X}xcxP?Ty!b<*wmc*BJPJt$N{JE3<csipCWYO!_jhuGYnd8
zgX!yVz--9z$B-#>E<ZLY-SYC^l>?YSZd7BmTg4}sLZh%cR*#!<vh^yxhT9ktADK@t
z=P#-F(eA}Jsa#7dFJYvnqd=eDL@xurBQDg$w|^Ef#JIAy75oi9M}0ZOm(Cx*2>mvt
z<!_68TxV1_Bhd_4IseWJP_q%eHhgAoc5Ty02hy5IUi<y<HY)I{I39f4i)j1sJ<NHE
zVMU+g<Qq~%qqBXg8ZTk`B3E$hJ7anwW@#cAk)fHps236HESMuKbI~X5$L`9Ho;%;;
zXf&!9UgltYH~<W?$q}=^uBF0nv4PFr4H4fQrlvmP07_Glx3Gzbb%ik_pZ#0EK+#0R
z9+%RobY{?lXC1_xk?ZW*A!3&M*~zEt!c0F+&3&b@lz_vKA)k>aXEJP9S;`=qktJyD
zmcR_9@Hme5%bmj0ldRXkwn`M7-2y_bfv84BXVi59T-DyICVZj(2jxB2{7EHC(nk$n
zs{}uOhnPS=?@OntUVTQ6ZxMICF0!X;JFbq&*n8d;Jw2&&TUv%=I^QE4di<~08E$oO
zqP@y@sts_jhb-bz+2=H8fW=>V>jLgqq&S0*mJl72L>-6&LT+aLWs2}hsAuEVl{pUH
zt-;r^O7hKGSS(1j*3>c0$)5wKF1y0*c~sH>HaioKooUrw!qG1lmSckI41-Mi%s+oj
zKMMF56dG!Ewis+WUI<m=ablKY+pPvJfFY-f(<STM2>8(jMWgd!W_UCGRq5Nk-n(KQ
z*{eb@M5L`;i6yotE~tvX?of^Gm>-<i_vt%ja)5Ox#Djdv2Hi2;PecVu(j>K04fN*q
zkJsItJ!S>j1KwJt?J*r)6vEZN^c@_(&})Ab=R0&%i@7;cs@Vvix-{4os)VLjmmRqS
z4tS*55ndF8Nw%_085E3RVFnxGg{{-XqNeJTKQ<@ohHpA;t6>1hv2XZ_GOzF{>yk+h
z>T#Kg(Ii*}fXv%dqp=4mr$lmAfvQieXx<OFIm96cwbhmOKEUuhbu6b>&-uIUpGBPw
zvWs^Jz-jBf$!f^C@YwNn*{XFL05-zm)q6XdkwSGKQT{PM?IHk?cq?{MjED8J%@uDR
zD6fNcVkJ&4UyA{jz7+L-y2X|_Z<9$Vc6*A?B;z?i4|WYTQ(lUV2G|DHT!IprV80to
z`V6@4DA{Mh0Qm$hAi)ompjvn@#`)&_Y7UV_Vm3ZsiOwGLcd^bSoQBnm4za%-QkHt>
zoO9`#C|ybe&>6gr&k27Lh97HcJ~9*Z>k81GEvwi^a`ekY$@hB$+C;URXO5e9oY;my
z(sp9NUeaX|u=F)fu&?p(xSUaH^BsTZ%L@7hac|z;5lOzV)a_1VK^5@Cado3K)`HKO
zt|*L9{Rd>27_jt0#tLtX`2C1~kG4549RIh5=Vx#m$4SU_y34L!$2wQDWl$6r!1>R2
zrZB6$(ScQQW0$v6Bq-haulv9FZ^ON+-tF3MvxHOFF=gS8__##LZp6wqEmI?lC`lWD
zIxar}s3EaPWH@`e6N1l834IL6P*Hc6iLjY`iKF}*Mt3_&i{Nj79mr$)EsKE9!Rz(_
zK*Iw^nvT!bJrF;i%x*G{+4l*_qDw|hMB_;0t@{e=Nc98UdOE<u(4RZm(M*ehH)8Eq
zbh+7ph7)8zShYt|(*McG_;uy{1-*WMI8KQm2lTSL>TuGM3b)Oz&-wMv<We`S$&Z-8
z2ywiWph;hDMX*53Jsy#Mrs~Avu|(2gl;TO>;=9C~FAReEd{WZ>4-_yH^MG9NA66_S
z&cI|PR=>$<kqI3+10LATG^Rl7wKA0e$+bUcp7mmmM1V$sg?EX$!-3AsC^`~uIvtzg
z#lq2a&|bHFXe%k!GZeShG^|38OP(s=*WM&_zye@W@&?<#5deWBzb{}X(s1hB)Or3-
z`VB)%@Jvc&<meH7HcDRMGs2!>CX?3XFR<}uJ8GP7Y#%?`U1(gbeL{6j(z48{9)l?Q
z6|wWnh`0f*IzVz+``&FP-fo7;dgP10x@+M4HC7-3VEe8LT~3w+-gt<c>E|jLWef)m
zoF{0${l+CS>ppGO2UvMB%?b$Z4;MHVh9c>!q=lm6@zH|tYdx!U2C6$&iNL!H9dHBS
z+oxbv5?iuL5qzKG?jsK`pA1j%?mRQf`Lq!~Jh>6=Sda+z111<hreWK8&>edUcl+*-
zT7<WgvvRHdeuc1+AYrq<llLx6;AwvC9IBUef8z{q3G$n9k$x@scVYndfv%N$i5w#&
z@?g841>;{bI;I00^hWD$e>>iO+ap0K@oI`A0Mk*sZImfV`S{0Y(C6_vsgxMAnXkZs
z{-K}$$_?%Tu(Ki;kJW-(qTB;0;*XX&V6j++P@X0ONK@xOtU$<reND^EE`a{62HxAX
zO0go7M91nm1J}vF&`WKO;rV)HA4c5%y3?=|+@Nc3VTMkZu29$0KkVqw@DsOzJdGAD
z_9|xK@cMkygpJENbF8wLn~kb^w~ls+!6QG-lZ`Fx08}H7s#Z$3hoD;pjuzK2p|Y6M
zu<B5oRGSjd(YPj@3?X~wd3@~K37U~WyVVvKSDA}PGVSe)z@`CXZYU-hX!{gZVBa1V
z&u68AfKnTG#Aw-$P}IK&6H2J#eSILCxS@8%+*~qw;1<I%YV7mcD2~o5;8*uHH+@yh
zr$1)`aWB-}B?7(@Z4lOD?<}_Hci9(yZn-OfAHOKWj2A0l%EqvdC*qI9P;VD)nXPtX
zj@imgy`1K$Hq&r5SB^7k7E)6AuYz+dwHXY0m|BN^`P39jW(|*|Gh4(<cCgltaMjd&
zR2o<vY3`rC$h&?E0`Ls_DNEByZCAe}H6{Kl8hk+Y@$@)|GynH`oK$4fk$ov}YNTnJ
zWpcu`RsFO-z|+7}hf)E_*dxUWuA9N&EkO5kVDiH&2*Yg>(dW^$P!#Qh3uGtgJ5i-C
zCCu>%v028_?kbT2Tu(tXm$|nVj26gaTg>8{KjL5gyHSxtDN_ZQ!@I7XC&K#Eqe5Ob
zWzzErt>=zrJ*K)WTkNaoeC3wi3B*$+fzIY@u5+=x-u`WV!H6m|>=soYOaV8Mk8f0r
z5icr0bZ0W8Ui<B>G9O*gk1=<nRMiNV95Ddfost@2^WdH<+AB?ak7;yTrBBE!#K3(t
z87xghgk{GU+6meBKsExNL^dUC&Yc9kj-G}ru$H@8HO$=1ylX*@Rukq|xHG{0brM96
zNaH?Qudp0Xhv*tTDzkTlC;Z(1`yP|r^J#-!>>=m%L-@9uwT=|Oxwj`UrGo+dU)`L{
zsK0?5c?qtg0y%PGWr>Jh9S*ivVOZ{vdpkJ^_<_2xe<|koB=%n_#_f!)jvsXq5UDik
zi|1}iSG?uR&yxL(#=siSg_0pIfHs4!rx<kZZBC+C?e8a929x}|d;oa%Ju*Ag+7t~;
zPm*CEAmXI*U;)+caT3jZ9pHJ$m}MyC$0-i$ghp$cJyZ?A5c_imw|?T`k);U@o+H$A
ztk_wvKaT9+>Nf+oz}w3u4-qK+;5FB|`?UpWLkbDPw)?gM+|dC|HOE|3ga+vErZ2DE
zgA+SNoSV5@ZAhpEVW6Kfv>5I#58%U`KObJdCm<HAPiQr<X+m$tO|#!IYXcXwsm%W+
zgT61ZguY&hmDq&+2C%rVi=<(n)#7|~AXMjPi$idq|I`iBpWPMNr{Xw!UjAAlNk!}`
z#Q$mX)8Bf34_r)?44f4k-bQzTgGF$kQ!Me2%~Dm4<wODS^rlFb!lk1DEmz<=OS}K#
zJEn$Z>@efHj`sBTM{t%ryD7|{A2Hu*%d<{YHY%Uh=RC%0;+Y+rIw#jtXis?f+7dkb
zN#ROeC74ZFMcN~4CK&y~ELB0vUtFkPWN1b%AUuelx9{-B-6Y%I2-R(Z!)F!7`8)0c
zw)q@35ogtJwEa-yB^+@GudM@1vhU%`k4?h@;&ryBm{Y_=GqMa2YSXgn9<^~M?l0J#
z&_0&dH0DJUBe*Q4SRH<jj<$g`+CJ<)6+g1i1rkTA{)}&40V!({>hiIB1h=R99xSBp
zv2uzFI({TqK+P-ZHS|kH6TLa}+v}%>2BjW*H7*~3UR$HmH$BL|GYO=1-v;l~+eyn$
zj)wDM-y?Yg>bzU+?MRkBN>AiL1%uC{z40#>Z1)73QN{*q%_OG((bUOYt_$UlNPwYh
zO6%LKgNBs$4!{v2u-jNgEacIV0uBT4X40wIEckcuI2dUoHKcm>TX1rd`rMqJ@__Fi
z-cFgFq`b-6pdPygxFh?zq`6Y!B&U*Om;H9y>qBnehJz0WDg#j}!gyi}VQu_CjrI_)
zs1dWPcY!X+>CVox{OINL2eJV(hSgLer0%&N?E7?4KfHMgaA582c~MJ42RcEu6GW7A
zq$z7?f^?giP-}BjPvPHfBR~FO^|2j)SQ~@Y{m%Nc<{?I12sUn34~K5#^nbhJ7N*a~
zFgN~<ejSiTtXW=KTo+eEGAvXSp`m$}OFZr9fVCxD#6QP}#W&HIRI=x^DwOsh`y*}g
z&TOS@yrd(8Kg?LhgXdWg6A3HCRQKf!b$6@M{=RAYxRb~lFQ6Q%k8m~OM1ttuizy|{
z4jG^<a0w<Q2R+Bic_-K|zss)a*^VfKNWY|;IxXAGI+<twMXt5deVsWK%tpsQR&L>M
zaHjy-=%jEgRmAG&BEywJD8!1DYRLu%ZGR;`as^Y!MP&~VM)--=$z;<%$;n2RB8oJD
zSJ6rrZp}WoQSz0bha}2TFieG5G77fN)1V!uq5+#Pqw6vF0`-Nz1DY*!TQoqP6)SP?
z{DSJDJL+P=?w1RWipD(YPm_FS4z}zwrDgjTH-Cr_IzGsJ;_W1PT_6|5-aD)CF#(Ce
zjgqZ?Q+pF{xm^Aa>&hUbZO(e8kTxK_!|RAK%OYir=4Ag#``@R*&PN%)en>^R_4_2+
z{Vq=Ys>jjZIhk^C>9`!YBBj$zqmq{fVQE0>{cUKBjr6Why%4WTYx(g2JLz`H3Nysi
z`Uv4_i#;NA{qA?=D3B?&k^Zd1?;t}baNc;&P=B)atn#@u_F$pJbUr<P5@WD(K|1jV
zU45$ov<kx@PTIjjOzgSJM`dUu#aKh6BRTTD^{%$cMyAy^|Mw!O_1yD!&~HA66B<72
zUy5Uy57V3m1$@J+I#4QAuL3KVFG?4CUGmm{qG<j87zoVv%(~Jiv)m(x)tV_bAWdDn
z!3K-Hry=8mw_4e3tnXRQQQ97qPt8b{Rbqd`XtmcPBQd0_!lHN22uU8YNr&53ZTQu%
zu87u>->=dA_nziK+;B7FY}iBfhBO@*SGk|o;WaZX7`Ri{S(>bvxUE-fi;nRpfGbud
zczFxCC^U*v^zh#g!@8)PJ;l9J+;&_wj=huh)9`Cs@+>)q%fI(>Aw_)^vCIQ@q=e@c
z&bOAW8@<hVC1K#fb<2A7I8E=~ug+v;3@_zy5cIWiF1(SK_eA4NK{ZAluFJxMO9Uys
zgT+ROC&0U=H&fq#r}Ab-XpzXOqaANpe`LMbbm)`cqOBbR92!DTy(#%8+2J!;Qo`jF
zgKfyEC%CFoX5R4~7V+@gEw4O3{W3?h3kRPNG92#w{k+J>C+&p<IrVXp?<c;8JEsI9
z&#9$06YVTF)U^&*9eT4jpg`4H_j$>98@3#iGm~-`4zv+ey+HrBfpOnyedZc{z7k)8
z4*AandKEm_osH2hhBkb+#7HlN0KDs+N6<}AM&g8a=ehy9sq?5f82CpF-7ZaABL)BT
zr&+a|Cmh!?v|+-0kK?4in(R}P`voO?z4EmjO;Dyrmj0J{LxrcK^pm!90scibM&Si?
z{2x}<STp>~&GLiM9fCEWnW2JoD-+WiTrF@Gbi33(El&BlRJ&11WYWui|Dm#6(($dm
z#spHQ2`-?(b!*+moIrgND)U~d<9gXBq{rehmN%Ae_S;IHwt3z2X6xx@eU*btJ@D_A
zgvj0OWK*kd<1fi6`o(oI0$Bp(+tp&#wrjJ>3(vS#GUGTY5xuPEVhHqspd4wf+xot(
zk+Tlk=kcWx%4v?6nH?PTz8o^YFt@opAh_sj5x?s*$<KW1cJRmc%OoSi51M5>><hoC
z-SuU$?=O%Tuu)`zy-D<=gqT3DF(Dq)MD;nf^Dqkq$*|$elcUre57s*u4NT|6s1Xt}
z(KNn(sNMXwT2mLJpz6n0ma=t;=XI=GN;j0hTkeGw*z9#z7Wm^=X}{n@ntdZscXN=b
ze;s&C7aq=s<A@Fj$d8qoN8_cE{JBE0hYd>}NWkuXz4{1lvmhaOE0A;1>3s;?2PKe)
zrZGtp**7%9kJ5eU)a?tBkq3<oXGGk*u|fKW_1TNz{1=sgAvv|*=qL7eTaz9p9Na;M
z(IHJO5nVL3IcsXLQZZ-0`cv>qJ=SFxMSMGHLgvR7t<Z~k_`U&Ew<KKj<?RDw^S6S#
zOnk%6i2~5%)q2}tyk`-hunpko>Sk(U|KqqVb>0W+ia$jU62#?*5OD{?u2NG&wi+YO
zO1^2T>Mu?7g4KRZJEP<ao*ItC16$M%7@p!MKfL}1FDAkvt#f1=JX=B}>~QKDPb6C&
zk|K-w)fu1E4Gt;$4_V(#MuZ;xM*fK>u_Et<p?%f2w{Mgn9`XAbHfwGd<Um5wch5oU
z_0#{Re?=KFeus-R#&|FG>uCVU<8z_eV<YnqY_}U}7*czp#+w^JQ<{vj)TADTojjkI
z;#FK>`e6Y6oyI<G6G&$4z`d!uss`wK+xUq+AG_Qi+2))??;=o(4DEKt!Gr-%gNx55
z7G$;?ATxDDi#L)plv3}5qrxF1bDiDFBQv{6h7YvM&`8iq@Ylrs{JGCpZlwn%MKYKd
z!NiOUFQLWtG(4Fh%ul4%4U#k_pNS{;B9_MRyieVANS3>)t;_rZRbx;!9P9^e;)8ZG
zv>x#Z7tzweeN6R}U~PNU#($QF8Im7UEB*1e;3zdV<o#nzO2tn_qU$Qb{b0HFxM;Y<
z9EpR)x1c^KU#7UpdsZJ9P<F(7{a9}jIj#0L`@U-evm1}&cd@<Ia(4fK<)6QpT@Ysj
zqDJMP!=AsWm*ll!<d_2RrBXG|2Nv}P*GdHZLSV+|3_9HjD(dWKqv}I5LHwD$3khb4
z6H=biWg)#1KhK!L^e!YxhE2eF6A`P;U;GWSKMm8!@-V;HQ6|Ulr=4jI_|QNnyLqsE
zGihc#OLuRoA+3+xMa_)QUVPZ0gTDlbH%bM;Sp(8gd6_>SrlsVTQaYufnwT~mbT8qO
z959cf50scUBirRXOXUH~IL-QKZ5;3mK@-tm2C3e%K2_|-miE|&6mcf?vL+IygX7CS
z+pFK{mXIZo7v2&E#&V(RyNIEqoQGKiLLhbw7x*7m_CCUL^}LAGD>xd*3N+<%uWk#W
ze612=^1IW6g&fGzF&F!l2D;A*G#0{%Z<vW7oY-DQkkc^$xCfvytf)ZZd%S<$NP_?f
zv}zQCebHI|u>R<$$vLm4myYdI8H4x%9ui(cSuJFjmmf0^`~VDb9%}J4&bPbtD;Hp%
z)JyX`1U0?8E3?6M$+vsnae6w6KHwyYsKX-OO`H44$klb~ut##sjJ=~wL58aLG)tw1
zNsYVnN4#tm*OV6Aqu$7BXK2@_$#^0?2k?=SO`oVLIbR;$?P^9jW1~}%b+lL^JxOPT
zKw-bCn4L|TT>Y{Zlfw3`dU@3}aEO$86PYzr=^5_Pe*&&4kP+nZ11zB!t-m(cK@m+2
zKAxo|O<t%c?|o>y+GndR*~Eq_@b;+0%RqUF-AW@f#(y$<!X1t?#SiMzGgb-_T#p#n
z-R^A>I@535&fi~=ch*R;(AM1F_mIf-PzVLkG=MB=@JGc1U|hqFO8QPeRCBK$4nJ+3
z7P;Rq*!yS$a`1XPj5S~h_eqcvxA3XVQNIjln_7_i%1d>h^$#nIZU1V3ZJVLp)vjHx
zX*`F-c3p;G4K2*IWAN^^(FcF({{*0;e~5ZO086^#{j>@8%l2({a_sR~5{<X@ySoc%
zXov;_3;dJ<P#9U;5%v6vz~Bz^T}dMu6X9h-LA#bUHCnG&nLPW%y3B!g`MIZcka5%Z
z1K$a^b2MRw_WJ&8%v}NFMv#OiDm5Qxm<l4R{ndSa^s965QcAVAl(d&oD!$&;Rv{xp
zv*sH0l?8q-(f7LDTtM(1ilNsbl2<poaU`XP1P-U=_5MlfZK;^4==B?xQ7+h;STSDN
z)UPQ5znv+FUKfz8qQP^v#D*`8YyCZ9Yx~K|+)I}4XJv*x3SZbZ-@8r3Qz|wTW9JCM
zEjXY|lMS2oN*1^>QbM^;CfTHIfu;}68gg&B7U&s;6_1MR3oxhO&ax<QCZ9hIb9EV)
zEd(kdV=&S$MEWeSzgUxCF&9hukN+y*_tOyNs4K1#%uoxYsyQ~F{~hT56%o#(XZh#3
z+gO5DN9glsjuVNREkIH=9H|T*y7J~fRtG+8hN+NR6<NFS3laJ&`KA`|a5a0h%i)ED
z#>R}{$(|<hcZRuO?q9C(CfVFC@_qMNhSH69LO1{i$%^%5>Ut48J9+Wx(>Fc!Q*Zrg
zD&!Eavu#}mbF}QO7)V|PeM?0_hcxUTkt2=<Kv|#ik&JucL|f+V>lG4f0~Nhzj#t9(
zkduE3mH&{SP4#UvmOtDBq~jP@F8c6<EN8ahvk74N`boqzs3D%oWk(e0Pp#X|IUrYS
zDkKzQdxv7bk+3CB<xAH2M$84JUQpPpj2|((o)`B?gMFssX7)%fZ93q_*(%kJ>(;K=
zi<46N#=S8)uj*6zvd3x}9vbH^@cgn_<jM5R71nSj`yJcx#HEXAk|dIS0jk7;?u~lz
z5<}Br`weN6pfW%#FwKQ>Jym`_?j-dDIDFpbL%AAZ9I+(RWlCT8Ub{ZvY7cc&$2Rx!
zaOv`DZz+SXN3y~8k)zdu`hYC&kKzL*hTnmgdm^WJ`Cf`l*pt86g?eq^1c5%Aq;sT7
zcgzWo!Rau9KbYldk;FGYG24(-H?9AgJGEZ;i>n*mTODABX)HdF8c}o$?o*ZGx1-Jx
zkUwm0LYCU=Jmz=Ly=BT5oq2!g-c!R$@XoCm-s7RFG|H!OIFr4?Fd4aYIN~-~?N~6A
z&altX^}w%3_{nQ~VsyPJ<Gl62T^JGebaixbeh?jKZX;~sSJgaJ`*PP5aRseJ9*s!H
z#NO({YCe@XgeRSP6oO41etmA_ehAL6jaG)7|EakY9s;W2UcaRnPYYY6uuF0L8w>Hh
zQQ%LBrKy@BLs-ziewf*u^8FbLN9gvsy+BFatEOf@27h4B=`Vzmwy~x(M(@|BbS`72
z$GiSvy>UKJfGjivUp}=KgHw~%HEW(K$`8-Y^%DMv6}1b{6RiJXO{)<_O34@W%;=)5
z0MN7TIp<;{`an3N{W0RMo!DQwjH>G^<n(6nY8VU9ql7kSNK1`KbC&dra6y&-#=`+B
z5xxG069<+^UbiDWl5+r`C8^OL&3StJ-<b~>;T3`~Z#E&OdVEM$X`XcWb$K_+M01o7
z`0u8fy>wMg|7K?Q?c)B1out!0;dueXdV2j<gzb&HEX}0dG2e=rQXuy=%t&@Ba?-^2
z<hAf#d9_<&z7M$_0pKvT*^7+_x8WNN9kmx)Bu9D}3Yy7ZzgUK%gs*`tQZlbJEe9tX
zBzQWo%6|UsuxsOaNP~Y{xutU<CH4f{yM03)N9bdb-msv4nLZqjVP~K1YeV2RvkQ8?
z`cN|ydIvEcPtu*-_`9V%3iGX!0g}Tf#hbnWqR9x<7@kJ%tVfI*37aOiqPkV)^1H4D
zC$S3(0N?0VDCAr+<(KXTL^l_C11>QiMKa7?R|48t%z0K+E*I}@!=z+PuzB0WlkT`n
zpnMZbShcr2?00Om9{ly1rR3Pd(f(e9_|<q`tl~nGCHs{DHb>OAPRN^C<rSex%+6;k
zXp4&)ROlyYvpzjX^?`XTnMphcX`@qzP~k?hm$QkqPYr?{pc9&?Bh#sZt=W#{SMs4!
z;tsE~VYHTlz;u14kiKJWw2$LNqbddJ0BZNH*hVCV4Chcwlc1(OPY)OG0gC`ax8bKo
zF<#udYyRa-l3PV)pcV1KrZ3y*ihDa2WG3)Md22ZkKAI?v<Cdc4xJ6sI&g>nNr({Fh
z7D+XB8Chqw#M_!tm#86U`aN%PFKo>5jWC_pqCO9%8J96VSMe70n6s-ni7{v+cukC0
zwkhdUcm#NO?<$}oOL0E&0-W%TZ(5sl^`m}-7(LVH?h&0HmXKXRmnlM>lHkg&o03e-
zZS|W^hgPO3*&j)?D1*!GtwWw|xlQqU6@uSNkrorbwKesjED7wUD+Klb!$R*hPWo0f
zJ^S0?oWG_kYWL$DvY38reaAtwSQ7e6`Q{9mNVU$F#DY|0<hmGFeby&djr{_SPyhiE
zz;z4vCS0#(+3(Ld_jri^3OUjQ+yOF&aL&ULo3*<#yMRXF9tLhb_H<rwlaJ4i@mCl?
zRR5Xb`7UoMn&&y+LkIsL06e%g4kT)ZUn{tb?_|trP;|$wII1?|{TOcf3*Yg^xZ@^F
zQ%z_Kw&O@ACLJz_nc{_>X1}mcPU?}UjIbYoNDt-w)lpiHmDP35#DZu53evGX*souO
znk_Wf3ta58zZw@4XfgW#_2w)d+uIq0IahXOsF!??iIU_V?gL>TbEibnZuAPL%Zhen
z8<{U9)vR}9$&G9bAG05q5F>uXaqHRIl#4P$0xp7voT-e%o*`XOWOwC!0IT(6Rba63
zYQbJ_r+!4m_d}ptTwRLWy4ME}i=$E><~Up??2Ubahc7Ll5wI#nzjsb}ln?P420Dv0
z@w%7aCs7~GvlTHCH|#u1x31HofJd)?7_9fp?#}T0KnqWtzi->yIq|O*7f_qKE`)d2
zV~10khAfRS=ba`wZY*dil~NZ6cE95$`;r_a*jc4;QvK~(l@ypIl;k|xHP0%+NXz_T
zJI#tg8xST<#aLuvc+;`Z=o5ChJu#&BoZ_6+$ZQ`S-pGQG&M?i|2a}ETi(Wr2)<PlQ
z6j!*L*b|G|q`Axd1ywbo!N@+GNfj*t#}P@8Otov(hJAO(Q#FWPSgU$K&sGBX4zEQ|
zokC?4C|}j4vIBw&ju*3hqn?L<%sGj-Q!Chp7k|`^!mBE8Bx-9<$lGeMY9E*Xz!n5?
zQde9k4v!!bV!FkSk}X4sl$4Xk|0Fvq%<x>O1NTrLWuA84Rn)$5ehKo-F7yRx@)^uo
z&ZBoYu^`=ew8DOjbkzVtj7vd4vGtqgeC2z&z%RTc+i$*{vPH*<@?Xi>0H<<+D&%ZL
z6TKECM5IAzvyj~T(?rAnez&LR7Kn_I+5|9c+9SF?T31p`EI)KGBevDVq6B9KnR9Ec
z806B^V;nhp%ff*;6$M~ezS74q7h1T_erBIRo56$wI!1>*+JaDXt`ONIp1(1*#d6YL
z*!btg+6C~jVQNx5Wrs`Mke(p>JZG9x8Z>Vpy`GNOZ$rc_!97iB<LmT_b;+y2huF}3
zAf$Wt@Hz%N;w|?}ukKGe1{0)kCGxV3{TneOpw2ul=cPR7BEfx2F(kpauc3)&8VpRj
zNHN?70NU8*5NafN;G+wa^Kh*0l}__9Nqi|P(Yw0<bshE)7etoN<&uUS%Z9p43=M^5
zp1iumRr#uiJ_ys4fz|5AM5A>4qi2%2`n8w;^YDqa&#sCB>e@e>rk!#!6I&TYkQZgy
zlO`Vbiwp%AV^Nwyyx*_;3({v9i&HG$1$FSvG|ltW?JRDkr$Blj2BmD6dHn}pgXvvj
zFyeXGZJ!GIeCUP~I-%iZ9T5&`r3pWmGWytcoxg^SUmyU<r18%a=uFR2ofci>I-1Ru
z;1E<Y46xA3BEm0<5Mb&3Zzk&R;`}NKvh!+XCqEfFXG;bjDO2CuOc_Y<7uZGxd;sQ=
zwq;bWCdPvpwJx`--2P$B-6m+Gn`DoS<pNVU$G$J!)e!rLAp2;;V*g>)?5Zv^X-VId
z;kHNR_#SL8Ms20_h~E7rV`&_*lU>hT*`<+IGzOw$J#>q>-x*`WjYD4*Y(qcPOTXZz
zM|texP1N#@D*$MjA+AgN)8l#ob4ff`_yTI46A@$eD4o@rkR4rMX7VBCekR4k59984
z+u_ngDOBUY1>C90O^Gb4cXnD;gM10#XkQifzt0i($(3E}9{mARKnKtQd~qPHmE`VT
zd~}TiB;ytGYTyQ7Vsrvv<{LitP3LZbz#;=i3Iy9462JnVhnkPfT}toN;QMKtmpmk|
z!tBxdpsL5k(UPgRR)9bYzYxGQ;1PF3PfwOOM9P4uooFmL;L!)$(KScw@I~cYHXJ1J
z{ly3~qwJR3(T!IRrpCRj24Q~-qyJ%n@&^cd`XWj1mn%}Czb28Kr)P`U2b!wQe$wwr
zR;&<JQeK|wW^FeFGFCa%qwq`Zd!S(22lAZL!aN;yU<3<qz$#{Kqa_-g5ennl?Hf*z
z0|KmGXY#j6XJ1BZrKXg67sAE#X)YaRWrPlSG#<DFaS|10l!QPS3w1#`z@~+3!w~o&
zAUEtPcRkRb&T`7CSs_9xR&((2?d0oUK`#hpJdxx<TX9XLFK&3jQbA>^!u~2}#cL$x
zkkjhWSB2HeXD&+_1}zhx@4gemo@)ta(}vyn-Hf>0m5a2rCv=?`vJ@}uDi#%%-(_nf
z+>|q_LK8Rm$wW<wZE#|X6UtV4e@OqvlLkxa0liY}-iI$L8~WfX2ZUGA$H#cZnxz7q
z=VE4d3F)E|(iacHT1Us-qJAeXYAbanZfMNOzac$k$a><CC|!8*fF7gQe<~ag)S2&d
zu7IaRfalg>(f)3rg(vQ-P@uKhi<`A3rpx6FfJ#%9v~?Cof@aI`GjyW<mIYE%#Mu=E
zRNjfWJJ{sod2fDNAB>KcGR>T$>UqbNd&a>iU>;kW)Jqn?989Am*WTGzO0y3?=@WP7
z-a?OIu;>HoN~Mg`m+B`H#SZ@)_SiVzcqBu7%(d0=&S87xZoB`jxg6r<?3!YAV5x=H
zz*}rZXYYU%;WBULsqkwb86{vLP0!Ihq8_#LLHV3mGQKVfq%bAzWyjq9H(&}}=WJr%
zY!JVE&OyVB3b<5)0v{8sCG;qp7<J}voaaoo68;ZMr_dLuAdJ(cG`+Lm0kjH!O1d6V
zniW$L)MFqsplQSkQD@*xW+r-~gvy9PMQE`mY=RCrNb{wH5S4>Rp1QL=YK_CQnySFC
zGBjETlp1{kI6D#-4J^};6V96v=CNjmU+&AE8~}(*6;IsdXAINSlHU(GtiuLjvVG%R
z@cSrfei;TXl!p|26$+S1#F+$+8bar*jqGVFK01B$kARJ2e0rnzk=@iM0Z<{F+}FD_
zjldR)B#3?x9$8&=R;$zzDO~--DoSxUkCG1zpt5aCx+n&}Z6>PS{7JeStd1G{IeJRy
z($5`_8EZ9n^B0i}4vvaFs-6Qt^~(XIl=M@EAG?&HvAto(Nd{D^6MBB7ajRk8r>Xz2
zB->Xx%uFX9I@Jzec5#oA3{!%}pgqM$h{SRjSJDBk#>zV#X<1C&c5rpXT|*N~^~P2a
zqdnFu&6sPeK1!OEM~*xnDOs<#;M}jM{}|j{@0&73Z!Jf{*Hj7yJP?CSiwGBZ5tC#A
zTY9KN93+o|rn$yy!7^euYJ+yVaQk;UI)1)_a%QsIg`T(VI_D&pc<Z6#hG`E0ht#HL
z@nE@0wP%gk@vzm-zMyic<vi_LqN4b%!Bi^cq~HhH!*9Q^Rq8VFsL%7RA57xa6=gZ4
zQuRSKN#<1pyuu|eDuF!YNcm?~wUU9&O}SPT_6x>wes#A<p^lUI-9@)1nM<*1nO)it
z`e@PpMVb;K0-#@dJ)l|40Rl8op^06O<Hxc0wHqQUAxAZ^qXg5zabci0LS$OsXy1pG
zZd%MY6|)3rlJ7=l4J<*9GGvhq{Dz;mcZ!<;Dg=?*MFW@gX@)DxUJvH81OPrl*o}VH
z=3Y2v=uKeI({1^_>3%8aP2Cqi{?bMmGcdWcISDUx={5H;AHy3w{q|k!*{!!#0aUPl
zIhed;hg;kaQeH;i?LR2Yg@PHdY^Bl~;;i1WDYx+y!6H<h@7V6><=K4S6T^%nFr-BC
ztvle{;vBrUN6)O}57eoEyd$>io=4<gFIjcz`V-+d)=%#g`29#dmfHT<UjQw^d4oxf
ze`k?9)l+Ah;Ush#<b=uXKj7r|Hf+yqH^IQL^9P=I6SXvYs-TMyJnROUI@Q<#((KaT
zv<Hrl-d_R61cnhPEMWH;M4_GnPZF`MfduHkPhD_|s@)c1vHmzynVDk~ShfQdZmdk%
zBB6Qq=2m^g=k-U!UC4<9zo#}D(1~q^FwhGi1(aENk!qGaq&Fk!o!<b$X{%v0q;i0D
zNm=^iTnS(30XD!SKthY7gGcH+O0yID4$m%&Xs_}Gzos!R8LG8YO=5Ss!LMthKAyBE
zhEza2qyQe{r&+#-|FFzjIs&B2N=#abfC5JRs_#=R%2MS~W4oe{HSpV4@%W(60S+z-
zy)FoYR&L-|7$o93I{;YDyV-)|y7o<hO|#sYmUXRAbnz}oO#k;4D1#SF#8%?RAKmny
zf<~CTUTf7U-jW43oVx|{XKe5$Pa|-CUxz0SJ{7t+Np4Dv>*Tb^e(3t*DuCnsyUCI1
zU_-l!@M>FiT-#GQu&Y?{_bZ7qIwsH<4;4-CV)Sm@6I*x%RcBQdOpz>h)KlcZ!_s8q
z4FlA?wpwzdQoeL|u=~am-XBjr>E&z->4-;L71xX>u2^_VT32JHYi4Kuw0>v2-zB;%
zHA_*{ETRn_L4}Xk!i9pAu?RMYvk+nemeArhhD#oyR9i-zp17tynT70(P4jM>Mn>QJ
zG;Yp+SW3z0Y|aSPOxWIsyZy1idZDFk7RIf3`(~dDFOxZ1UY5~Wl`Kf=jGWubSGJ^&
z0f%{4zZvbv5MLa?+&>{llaSsSd}TJik)Yb1#a*fj#9WqdSfA9+_0o@ds8WORLEt*i
zWY=B?0RIwLdR6xYNrp>vE?KiSGoVF?ilw8hiq#1&K0lfBU58b<NAz8(iW|UA7&)tu
zkKO?QXcpw?P{>qC%1_#lersN7UFANcjK#%y)bG6uDr$$SUj)!R3?*T1@>)MQ$ZV(q
zWsX9>`S*xR%7L?wzGOOm>s7Bj`4v~yW`3Z$MgCeO=Ul53Az614R9cF0CMjZ0*N5fd
z@gy3yt0&QRgwQvwx0};F8^t_lJ*=_24Q$zd`d&&y)&kqL#xgpL<Q-khQM&7oW=!9c
zpeWuz*;=u-R?L+gL#Hfz7eYkuyp)0MVa*m)Yl3;ae?C5W3c2_3I*I+`@JfuO9`FPa
z157aX0S=TKN%^VvH)nlUqt`$0y^1NxFr+j~kX4dA<c*dT9h<Bz3qY>m1U&f0M}`a?
zd?#Y%&ANyj8x}py@(Q$`!Mi3nfOY=MH!H&jB}oIbmG%;T*gC7+y$JO|x(Ma_`=?=~
z+gs0HX+7r)v4r_J+*)P(G2o*ogAZ`^M!&pKIn&)8W@3D55$N*xHp)2I6ZmJfXWVk+
zf&KBVM4tcpSWgQ6c$)^!5OApIa3`limjulXye$0*GQp5aVkvIx_)l5=hu<2iV?=m%
zxSzSNKF&HyA!#Q;X}SBm1PyO#nmPhEM-_0hx2N*Y?f@5Jj4l2Px}?L50a~_tlgLhJ
zBLGhUdF?Y%+lN`V*ue@pADc?ui8vKOPb4?KQN|YaFiBzWOegyZSBk(U={+t>NFMF^
zAN?IIWg++Lb2Hz~kSEE?GgFIdz@Ib+4L#GeY+-8}MJZge%p7TStd`}T{JnGh)6#@t
zV;AP_kzjGdTRL`Xv*YCD$s)Jdh8B>Uyl!jt4fxYxX3ScbFa>|A)FhU_V@tm5fPItr
zVi~osW-D~z^uQcF<!SsNjWrd&pkCctG&GXsdMN8ONiN=~b<zmZ#_X>k{)vc7>chH&
zZyZ<9NxEfPGU2DrVKFZO$Z<y#n8NT8EsMcK{mB^V9*v83eMM2&@|V->0t(<c(n-Zm
zC?oFozWOngR5;rT_zzP(K0f@$qcQFE!`Elhu-Dkn!SGK^j!YpoY9m{Uvjlgs$>Ux;
z&rk4uMgIi$p3fMFB=P`H1LRu{c-TijA6!dVJ)+IpG4}X~WI}7XOFz$Ml6K3m;D%7n
ze{K|~mR1zJnR471GCOLd-r-gedL#OaD`F~Gwb>x2#W^_w+_(`W0LYx`uo&PW`@0uK
z(C5K&v6bMwjrvu!Ntx03LNvD4H|Q*i`F|Z<Wk8c{7Y0d5mF^e{f^<l3Akrn>f`FuS
z=Rmq!q(K^_ly0dJ(%s$N8?e3K<M(^i*!|q+oa<Z>>*@Oe8*qtvj=cHmvDL_&>SxTw
z*O2tg*R!(L$^x>J;(enItcSmeJ7|*vn?KGJ|0S!vH9-R?<tXu^&u<=Kc0FB1&M%p<
zwSak_M#$82-U#^hN4BO>!8SV=)fWq2bAkcMj~ZO5p4Qd2=a3TbnC>U3Uyd&FO8M%G
zR`v+F1RF-0+Oxwe;-rP3qZnvJNvx;Ae`vX19^R5ow2wq?&<kR;^9tg>#31QGM47tw
z7|a13Bdl10H^X!3W{=^p5QJRZht~gu>2GwMWq8egk$bEQAvTb7C3N2;x%;$qHiwwR
zx!^#*BD-g-%Dy>)I1V~LAM>9vI=aQ5y?k@8`8?3<0%W>t0Pfo)$KaPQ0NfBc{-xz*
zDyxqSW%&q7aYxmCqgCYd-VNlH&HTx?J;vH0Yg18VTk_Ju!bE+wek|&`hL2U;7jQJs
z7IQ{k++!AFTaUY&8M^lti2sN7b41+BR|CW;-gTdLpxX&to{~$u3b_^n6PruVg!K(k
z7?NaZJ)S>@8x$zxc7AI#hE{w3t)3HaB;$jRl0uWHB=0pkV=-d<bKV7{)Kd;T^1D>j
z>Pvz!NmRgODgNi*VHea1@CM~|!@>Bwz+whc;L^POlR^~kRrmy;;Y*{LfIEc_oBVhv
z&3K;DS~Qnq^lI`_syEJwRLtJ@EX%$%A|;&md_3SyUFueCdnyz>|CY4xyqE^;XL>s@
zVk3XakOK~HmavT;E`7%rmkn%+26ej~boZJu7*;45MpMPvT5BwqB_4Dv7UN3O2V)CZ
z;o;2Xv6cwUe9HSML9*E0^S(NBVmGxpK>fCw)AX{?JifcRr^=S`S&)k;3Cg>4NqaVP
z7r9vdi@H|t02cm*0`n=41dT|UrgRO)X|0LRRxGM2z})50?a3R>j-{W_vEINNmON7Q
zd8pYzI+H0T$*7DHGPyVp&G1P;mM+Dvol7+Z$@5bjh9X84oA7%C6bp9!W3zVo<+q%t
zgm}(ytyS3+G~_&s5A9rz!snkYF={Syt+@vZ^vRVqy=nZ!WfHIFbtG{AL;DPJ#<N1^
zEA0UtW1)#M^rj-%g!u56-=H(ADz-sZ2ieR3&ZrZlMZetWxtyD$+l)AnaiK}`;TM3g
zT%2;mfJxf52|@8yQz${eD%yBkU;#AYD#tFBKi^Sgnd^V@=b9D!hrPj|D*fh)>yo?c
z(+$hd4ytMm{F;Vv(T%l-D3Kl8y65A??Io|yt_Ogq65x@p#Sd}`@j!%HRDa#ULE75i
z7184klkCa5-T-&7jxv6-SB2U#L6Ud$e%>^nS4WrI8~$-j$Of=!6R+M}QS2Z!at&cP
zBR-NzAU2`Y59%2Nh+DaUn?Ouu?Hw0Q2e1*3RbdF>j2~eM1h9lMST{L(oW&oBXcDCL
zI9^GA&Gj>7-YE|C#+bx-^2^+hb~1jv#RbS6aDg=d55Fy90^CYMnF<)ay3E}?ewEP;
zk`hxIb>ce^KjIgCiN%-IL8L38FB6}a5OOH0Wm@{?q+Da<g5Pu+CF0Tkhelj-pbRBD
zWIRs{-ZugeF}I3Oh54L2vL&?V=p_h)cii`Ndkt(&w8`)^Z3o47&*F+yUqc!N^+{8B
zl0=W=0ifRald%9v#1?&<M*4Lj#D(`7u#AQ--VYcdzJmvBIvwX0JRSXfysfUPy4Gye
z<D2Q;FLtEFCXF+lBr2}E$nF_9yifWnA`Xqk6%6ZIb8@|l*lh`$6*%erS+ng)S=!%j
zhRgiH(~ZVv*-E@&@y`GfAw2dJ(3JKs=`g9XuDd~ITd*%A8f75xJ?0-^&W0|0z(a^k
zQ1q56g7Zdi)No|$H}!a(-S1qXl{L!$&~!6WANBFgtyxhR@q7Q;_g|0}-odS?k9VKG
zp_bT91zS((h!)Kcxj9S?ftUSgH8piIOsSYzwyG&hS!Sy=neq~A_&kVr<niV_Tvuw4
z!^C$@rBjkkmK*BC2GHC3DO!XE7G$-!quwj}5|lVa_d0NUoW;eN-QtFFw<NwtY(U#$
z)Hhkb#HiVFlTS@qBil}$@RG2gLvLzYcHrD6;*VwQl7v(#3lPr%gxe8+)XVq_{F%YJ
zmP@<Rb5+)&qvdeK9DM=8E#DP)A^u%x+Fe}1vepFLr>m0)x;X3vRoq+BnsIIoKo@@!
zRzR^>SHiUH4`R;A^T3dtObpO6$$OIg08&%_5(UXSG71L&T;m&I1m~F*xK_x!ST(aw
z38S>wYQ)}89&2~FsQREUrdEC-eO8tvw%b%3t%XBx{|9KU_<0@=BJE0BFLoK=&tV5@
zsS&3HIwAH?8D<OBYUM6l<ubOgGXr!f&2!r7MFg^?F`vOt28)Ko=%Q6j<-i{$;%tSc
z-3H=jy@Jk0TvUFnlA~`tx~kICXQ*_T$r3-j%Vmozd9YIafTzSzD%RQkeepJ{4KWcw
zJB#^|)@9*xOXPUM6-c|NQp}PC2L~yoqL-qWYGEYAeJbz#R6Z}v-<xVnZKTV-T?gWb
zgyHT34+G#jm%L_>S9u@$#!>@bM(Cq98pELx+rcHZ_xS-OVw$_eAW>Xg&)n$|fDy<g
zHNdY%6<NMB9BZj<(ydo7Y`aTDY}ONpo1<++Zq*BT1&|@)woYHq6O5f4P(6t-jzZB+
z$^PaYAcuov>~tik=P?r2hN@-q7He=ynn(%uAPrpU!jagg-g$Nu>tA08N)U<a$}Vz-
z*iA&-l2J|CYgIiDyb-X*MxPbL5ys|``{)X!8p?!uUgC(5O%n1=$C=?EH&m(ZD~QY}
zODs6DDr`lA5N+GErW<ks{^iK7-rR($-^b*pPX;L;Uk}?^w%IEa^;B{&whANXs@ncp
zuvys@|J1FX*xAduSs<<5v+egE;i=CXwTNN6K2VcvhWY1yzzIvqSrG6~x)TOlb+{V)
ztj@Csvc&HKDz9l5TOmCrtLXCr$>sqXj^d4&w*S!FBl2w0V5eyq6OmPA?sm9C$?PPD
zSUA1pxIX<R%TdZ)<~H|VqW>N)j7nrQfF@5^w68!c)oQjDIj??yMtn93zEhlnG@jh~
z!>>^O`}T30Dn*M8&h}q@YBg0Ku-cpxY69i=*-$HS?}X46=l~~DJB9K0y*?*`Al}^x
zmTwwNvi)9T2I+pBen;Iv1JTBhv{MkYYfSL|PzyOtcx|XVZML!}!_IznXWdFA@AdIQ
z^QU1umV`Jzuj8sctve22&592%HuKo{J)c@=LZZ?L)&=hgDsFPIhVehzLTI6i&gbP>
z{EG5G<lyhj-n+sW={V8Tf2bNwpYGxO^RoMfV?0lmc{Kun(l22Wulo9E!>a}H%M{5$
z0B=<1xP;Moj4@~Ush5*)3d6o6*&O01=TJ6&-ht8a@b+;(f;@nqd;+Z>aoOw5sMsb9
zF})ZRn5we<;#5_*B@PQ#oP0i85`KcSOd~1oS8zYs5MGjpNC<}OQo3h<iY69}WH=_W
zeKjK(hKQ*mb|Sf-7-sw>7F1|6JQR~t_zlS}Rdlcqo$jAMi@(a)2)Y05peZr1bP&Z~
zM$+itQ-gLQjuJpvkjr^AcqjpbVgU}r-H1R>an)az_uMNYBhFyeA9Bo6Yl%_dvC;&g
z$gbNFE?IIp=&O=qj>kq^-bW@+YL_EwMIx&h&lCNEo)%w`ckzu=?gDUgW&9>NMsWU!
zZT)g4HDMJH#muS>kNR{$l-Nk`6M$tKbiSIw<5$cou^4(jn=x^Axy&HBM=F5Z`H$|N
zQmQuq+jmt4znr|IXK{oRafrixRbcn=fA<iRgm_(-%zti$%h;wIUmU<<s}H`)$cihO
zF5pteTaqc%DKQ|np`sxNv$YNu5g133b)xummb30m%n9aIGI|fT_AKw!rYg<nduwI!
z_C!u?-D&PDa=VMSYTdbJww6f<_w7Wt`p9Qvx|RH%%^%HH$=$J2xn*+148FnpD@r2M
zXBK&3pCI;LI#;Jpu+7jR&}<>jpSqeWy5t0a^4-fQ-cR+I8dgcLA3wzH`oJ4rVIotu
zsE$V7`+dUqUot~GO5!koVDBaH&)}md)^b)&R<4b=Hq?_GyTelH-UY$ig|1%YtSJJl
z^XZ+?mL!Rzd}F@eul=)c?oUcOl1*zJ$tS{Y7GKYExt?rE#ZbDmBiVVkUUG&ssGq91
z6{!6FEYc8<LXeh~=;s14=KiD_@-!mJn+Jn<jPWRpD*z1UZ9BL%l}J}{k2SY0G+X4q
zG4Px}@rb|n0#;ZVZ#c3t;0*})!yA7u(j+g~2kE-SAGbX(`0sVK7=v-{fW76Kz!WA8
zbQ%Di{U!!?IkLPj9Db^i+r`0XHK+QhfBy=8g65MDYaE`8m%|i8d}p)zUL17*<Vb@z
zT;m*{AK}Vd7-7uW^Z^=uLgO?sbozXb+RLr}_tr#WcnN=~J8>Zc`L<$N0CwC!u^sJ9
zM>N_QPTDv3_`b&}=HB$Z-S7F<@FB6OG+Muc%Ysi?j<<6W;(f+d{8`EPmO<rSk;~*S
z(8LfXldak!1oBjUvPNf&LGeXsqXLKYEM{GiPj125g4N;*Vcqi3buqhoxxLfs9S!Vt
zCsCgdlVl5j1Yr?De;(wFh*N+ZdSlefLBwaQc4y;zuxqNx@PVq87>;5lQ}HMOQgpxT
zK^gARNfp<3MnuKu>;=V9Mx6{d_)HUXtY0Y;2^iW1@tlZ&nmvvXQ%Q3M3HAiX;QIMq
zrTi6D298f&^wZy~MnA%oJN5C61@e6ZRXH3am<d~>RV(8PqUvc!T3In4qUv`$MwXiU
zfEZEfXiScw)wcCn<I`B5NwYOE$?b1P#uQ7tPNX5Qnj#99(qr#aHU;$IzP!Ui!iRSc
z(ECH_JX_2g_1tQ~ae$w@d=(oUH>@73xY5=i=Ca~dVu6kG2=d&1{JVSy?A$-5z-|9S
zWBMg@H?Uhr)0<X1Sg%1~^#B;F()8-aa!n>AqJTvN^_x(0VYmw-#msu(dfCM$xQC+X
z*BJ%<L#z#V1XuUzQ(R#QfNdK4PF%&e33a-Lf<v}c2k<I3D)Is4Yoh<{*8OC4DA(94
z`E%b;jQg3ei<h^=!^Dp3z>PY=8p&<`P(iGAntM?oWgJ8Qtl2de%zs0x6~CdB`XSfO
zh(Uc6TsN_qEy-reGzx8j_5;bU)1KyTz{zz<O*n=z;0r%A;(|*ASpo=B|5&Cg^z%Ww
z%il&;PnSKR?_36c$CO;OAkQ)-Y@FfZ$ACdv=LYfX1c&<vty;KL*FdhPxM{|qBZ+P3
zLfg*4lqui`Jzc%2q9FN+eGj?FMV%qnUC!SjJ67zf*zqEE0C`j;y7^1DmpW$YP8oY5
zF(?Y?ifN&+VK=%^3cA>t^B7yX(PIf1Y4irJmg(nkWj0X!=&vQs&Uu;>7mqCrhN1H8
zk0{Bf&3=z7yfWPY#p99rTV|xw-XXxf1QuE``dq6falKJJN=q<zLT?dFm$%N7h5A+L
z-mRH&S@GxP_%xs%A@i){99WiSW{-|{zupVcV53J%<L0*{Bsphlm%A*xm)jRB;c%@6
zF`9~v;b#Fy0OlsVFNAiP*?KuM`tFxfF5j*z?C~0e&}<9Ny}7yun6zOf-`}`N%S?qq
zUFw7)i}%FP9__v-3B~Y|D5|wu=708sRs+<P`~eTqvEvaz1rtt&i;`FIMb8t7XPk47
z^jpj*i||-HC{eFQz6|t{><AdWE2@nBwF6dN^DJV{#6_6nO1Rk8jgC>hbK;+N|5@gi
zX+uXBQ<UB;HX;_(awqC+g#7WO(`Yl_E}NF;Z_N{5Ck~NEF^l<O;FS6UpGn!o{<kP1
z@v*+&j|a>6(Vm595N}-d6RBx8ci7n`s9wkTNms2|oLZ}9a?he`^Iy4hfv#Wfu`K=z
zKZ*%WR9L}ItTiL7w{%}wpIsfQ3DCXhx(OG*GgsWK5o#|c-ZB%rP@!j<`o5u;coLPe
zFY2X*oH$yEWw-W$rla!I|6)SU6X#jAQsVDi0E&;X@Vd84uJY>&yCQuK3(4jpd%h8K
zBF2x|ynSLplJK|*CrrM?eVy+p*2WJM$7eD3K?d)-$2=c>0os`#-uwE7E%FO4e+tqn
za(>-Dby*(HH3$A=WhgmDSDhuy$?j97eKMwDzgn5mR1z-PC?gQtW!*#xIZtWo;jEIt
zmdbBaaoUO?4H}?xH4I{2K@~$Db^~iump=hn5)ILzF(jKDZFI92aZP(PWxzh?V=clS
zr)s?rMK;w(VAwfR&9WCIrzJ%{Kkjf8r1ZVeRi)CF#n~EqmSH_37%qHCf#%LT_uepO
z9pji?61H37L9i=x`)i9{>4ooiXSqf9-%WJu7ekCyA+?-yw6|q^UPaEdf6@%cz*d`e
z3q-9<-E9#anH=Tb#w?~KQKpG-L@Y-vZH3e(`2i@mlo2oZIOnAZ`?im7fLRMHN5=S1
zb62s%a@q6GAc&$aMyfxgHzY=R+Y{@cbKxV%jGx2#@Ma2GrAzbut1}QIudySCB?|TU
z9)t12E3jd+H(rW~%u{vJy~2A|L4QH*P0>}5p^~?V)I&Eo6_U-J+WPkk(uR;YLMgi{
zMy--Vwk$1~$^VGRU*m!%Qem&%s-eK$-NQUdgG>$Gt1S65OSHky2P<YS_MDs~-Zv+W
z$W0XyEqVO6uj&LMK-pah78*5gKMgzDGiT4SllsiYrZgmC(CRYP&fyg4&bS@vZ4e}4
zfoF7jR2ux0hxEJFleHp6v07uy@4myxbgb&K<-MPNL>w5c7N63DJC6R2I;CPszA5fH
zK>hg<j4J2PHNdm3K~7MYUiWi+yX^PL9nD~Vhi{LTn+BRppo1*d$)Lns;p5x_f($Op
zC#R&;yE?c_JD@1*uRNroXpKhbD(KTtyZwST(D;Rly|0{9qnkbeuJC8<iWjo;vAa*@
zF(NO<EQ>+*ZPG>V&%eqc`9SxY@sV}c52aoA$0MJ(GBIxWhzm4|)6i2tw6#Ll3b9+g
ze*JZ+;V1r32do(K%#SbQ;n*BJ`?q6ZoIK*!J}%ZC;SL6l52qnmGZ%i|OLVPScj6ih
z<i&gmgL64q)6V-k?0=thPB*9>=>VE8hFZ2x4gw<H`14}sOs@{Jf@d8PwJIhQf6<<h
zzwv!b=4LI#8921fpi>qeUbjP~Cog<6c9oykoXQ$q6?}m+d_y{W;eQ%n=zK7&Gj~gr
zwSL-22=j6A@>P<s2R()|eP``ULn`(Iw)6@>PpNWuj<CY1sR{+M9dX|l{q%;tD<D(W
zUpyIFdf(=z-If3JH>Fp`W1wfRi_aH<-1FqM28!prV|VhEwWKc_5WGRh^$udzPj^Wn
z>bj=Qf0Zh2tJ~OO*d*qJOT!AvYlceczbhUS)-icve((=0We%kaJI>IN7IAegf4ln4
z)F0FKHOirMp~uL1Iw;t<P$=<<FpGI}g>}Vqbaeo0#0b=$$#QV43t-Xg7%p!<a8vtj
zs_Xrxm!1re4-xz&rhF_lbpk9W7o%@m801Rm$WbyhG3)nKgdQd~$vJX6Di2>CZciz<
z>X{1Sjd9dRJyj6N8h;9GqaO4Wdzu|mrzIZuiSSU&`TjbG!h<>=0#b~ym#imcaWV?x
zwkki8v*A3=?JoTf?aRtW<mKSUbc4_Rtv-e8uzx+C6ZwB=GKPihWnnPeZt#orID%R(
zF`&pFO^<D^C^^de0J9-b@^t_ViRC)P|6lnRV76`}-OH_Gf*e<|JFn}Tpgt}Hd@Wbl
zj8%Aw{sXka-s&~1{lV!IE%e`aqS-QF;$CHTi(JD1`WA()A=0fRC!JwKpL4VFL+AbU
z0dg_Qk<>PC!wLhi6r)2wm&sYX0r;C;AJb6JTFJ)lZ^36q+c~dh%vmW|kh0eQaAa+V
zMusAu+9}qr*E67P*HfeE;6Fa5PVYoO$Tqy~%wFnZ=oZkgD_Y&o7VbH>e`l~Pa;jb8
z4!%xR7LXk8AfHT5qyPxhP0$nj_bp`|xj3aOY7~vtsc&7j=xR~GbuH$aXCvRqqMjrM
zq$y2sGMxT#jKBTXOy1P82%S6?g^o!pKge{G_w^QTm3_(ZB#Ud>Z?J7MTq1^}Rqz}%
zus6FmP@OfB_2s?=Azwis;5NlVnAO>@ajFc$VCJoc_MB?3rtPmWqBQRLxG-n)_7<Bk
z?4F|~DBKB(dwi%N3<IRMy&tIQ_S+}SjrjX<nhHhxBfitS;mqsezOf%z)?{5Rj_O|N
zLMZ-+*5WLUPZv2SAT_amAEmxY$moPudz8SD87y7DewGGNN0FW#iz#RK>udq^rciRa
z*y0PFl!7x_w*&2^z7};cPbGvl;7ak+C=0P7CJ)44@)i%q4!`~nts$&5Y3}i5hHXqd
z56X>!a)E7VNqH4sI@NveAUDj7d=z|rKATC|6+3YEWt<rTSLJ-RZZMn+1*p?9tZ|?(
zn<M9984WGi*?%rYV3mp;^iwnr_J76<64NnY3@f#eyE&60?#EXY1YpCLnD-eA#^haW
z^pc?Q>oVPUQ~baZ&>6bM939hRLT-%xfjO3ct=^`%1nN$-AJv*GvqhGdp`D-{K|!Bg
z{`Z4yfi0sX4!T#Nkh$aBol}Hdo++eK#<ldwqvGmaNKj5Qb7O(F)pkH}p><;X-@J>}
zAlmn<FK5xlhC0u*FihrN?$9#aX|#sa1qz+LRv7d7{)cE8p^)XH?j(%<)9b5L!YJ;w
zqMganB^LeXe%F|g5l?Hf$RX|>O;YWTq<CDR9^M=N{+&^0!nX{gDTDzZT<-L)>7c1T
zG-#zf>_TSkXysIUYZkLbtWIr?cV#f8IpatMTg^D0|Im;=r#q=>lxSAfr29LbAJulG
zYi@+Oj|nYx>23e|^DPIY@|>@h_f)SdkS$a$Hzfv`q~*f|X^e)ydb(=5r~*)N>6w_Z
z+ytP8e;v^0Vh$eVH*~R0d(N{6I$E(!yr4T}5i=Xg0c)ZJPO${fvp0k}@!~Ct9G{M=
zitnRcFX^a7RtNUa%in3D1dZEtOS#_%Lc56J6HYbU!QcH6=419{QR#lPLKo~YarwO3
zpD!E=LCctE_o0w2ZQz#Yo<Z;b1X_XIUjybkFJg&buz_1$HL62`Kret%5=0ia$~t{<
zH`RF#WRf#ZXC>ao5Pv33H!2=DkMVQNPNPp{hQC|TjkJL1R=J{HsHpsYSQkD9&fb#2
zH~9y{t$j#$&}B9?Ty;?pG?Eh6c?7%!bk4bLr_gonA+Gw;R<gG)=*QOfitwP!W>uf<
zaSl4u^N~PArZa29Jx;jWxVJ_?i6E@~<N$Jk;Mr<`bmuEA^#?c<LC)E^IOw{@>*_&w
z)&Wgr*og(DBB6%oRWHPb%h0WwQ{!7dOe!Qkz>bhxKn9;@*{6bFR55XWpS=BbLaX9C
zfAlJ>=sm0SSIgJSHb41brS~K<^FI?;cqX?T6C_Kf*+>QMHMobE-uT3EgkOfMjK$x@
z$}@f7A9X#F8InJiL8Vj=Hqb9yrW|I7#?@Fg@QyfFP+I^)Z)H3EB97I{3nAQo8OGXj
z!DuveSs6@VQM_9$x{U4`{`q#dTB=B23D+t}VXR15Ao_&|0uNhE!wd+p@d=>Bxbv4n
z`LowvaAm+eHWv>1Z3Hv%wStDa0^?+He0JLEL=ckqnpD%dBzk`HtPH1(@DCmAbstoT
za4KDbD4aJ7_0(Hp9;bWVMmC3yTSHtJ^7;TM;OXZM$aK@)AHm>TH+F?V@NN-#B45l`
za9E(=Qr|@mIhC3OuR1U@o4PpL9zqrk{>BZFAGKbUL4H*>Js_d&k`(bVdhU&`fQK)%
z`{NMKDQ%Ki4tu7J&YtJrt(<v)_8>EH;zYx@hrCklre9@igFTZ2{N`6*wmW`*-wABr
zZp!tp#rTsS#{CNgA-80Sqwm8HuLZD(;R@Ur-LfT9p8s@{@F;k0=5Qs}_|KLvj#a0C
z-SY$8lJhIbS|LAGn@lOjq(r+5K*BYaL#11-)!PdNnLcCS{C#K$8O^2-EqUy0K0A_n
z3s7$WY%B>-paf3Iwg(IY1Q=Z6haW9K@=e{OcQ8a#i9WKVY-p(zoJTM&mNj-e0%xHa
zn<Jw+yo+<b?TMG1nJbPpD~OO0GJZAm3Xf5P*m!vgBhGGkD`sUlzLKf64TE`CZ2)R;
z3Yz!{*;}!REnZ-bZJ0o5g*kKkg0USe=t~}>tQJ{6U8y-a_j@K94=or{U<^u1gvu}a
z7hgPt934o~5@+)YU+ut@$#-)f`i#=8(C&!(+cEW**o1>1>}G~b)k<ESXBqEmyBH+q
zcDxrPPm-+lEFqpFA0LA=&RDbvgQ(Gu*`;WuQF{FW6{;KNV;z4Nc3B5+j?|QF##X*M
zl{9NMwC?K7c!lu-@!*9rvXXri!hmA~K3(M~&b>e|-BZ$=+Uzcfc``k`YH37FVKMz)
zGhiIC1=Mg4j0Du*gz6E8H5sF+%KY~FEQF}5+j`2nuIZcx^fy9-rddiDbXoSr%%<VA
z;o;QjvqZSSuOW~bIp0GQBd0W1iBs(5F<_5o6Rg!tSVsyFfjEA}R6N*42fp`kp(~6D
z#Inq$&@l5@JQ=IdRlbiM1-@4FUd!cBmwnAIfH|b=j|#EIz9c45^Q#<ji8A^DyN||}
zmu#c`QowupxqBgapMz;~HwfSz6-knQZ_DTdq~O#}=QDTZC~aF6kN?m>chO7rZy!7!
zdkz17@DF`L*+JO>dj+}?;11)~L+;Nl)yoP#95;?aOfE{YU68~iR)=ipz|9n8yodCY
zUi#<w==%1tLG9rXa8A0$0$Xv;MVZ;oRjFEn;--zP8^l3u02g%#c-sIY!?1mCpFOLk
z{qQEu^I>_4sKSFL5_hXsz=)6={(d?>W1Dz3#Y>S<q=f~_K1f}8G+1Bq#k`31Hgp1$
zDifoK0^5!|l=Jt<u!YZLF1|i-yU19T_fO4IWAD#xyZ0V>#>;Kq{DZmX%CZONGo=vU
zotsxFURG)nCg7Ve2i8k~eL6Tb`<;tb`0r(a8&N-e{0$RIJb<)w-oO#F5nNP(ahKUS
zHv-J&8Fp04Qn9^jD$5!qa&pMn5;lbQ9j2ygVoBI8pa1<Vhpb<oauP{SQF*K3=cT)=
z_`<L<JeaINENz@5>o_fx-Dyf7q6xS2os6s5G(VSBZpq`dAoqM4@PrvdkdFdC`SX=H
zdAK|n8J$Qq1gpN4pp#sPqw2>RGRdbN08zu)Mp;-g2IJr4t*H^=VsfD$(Q@y+LU@i1
z1wnM&zog^u>~c~44OWX|BJ^R>s-lFEpAuOm0&FcZD_?!X8A`D5$9gyCfl;s&Ut#%M
zx98sbh{g?dBkzX)!nr1BpBF`{k2O39EdmjY*g7vcZI+;BCZExbI6y%992+MR3(}x1
z$eJL)J8$ta&S${$LX;awxxTl{5Qg{=JEStsUEln90x4rIl>>rjc92tXz9I}mS$=}W
zpX4KhZe4*cy#l))^QT{7Ok<JCtK!5e<7Z|C^;4CVAp93lVhtA?i%80>xam5&flQ-F
z(%N~PGCFn!xWaJ{+EX)VYp@z>q#-rUC;7@}dVC)ksL#9b-)bJo23qA(7+8JlhqU(b
zwtcoPq1~Itn>Hp<B^bWd0*yzdyQx4xNIF|b`YuyQ4Ci+@=WD=W)dY=JhM)SNKhd<E
zGx@TFE7d}AcNOxmt?f#%Lmd4qLFcveSq$K)VdvFqXDSC`kQA<}ts8zxMLw~2plmGq
z_bXwYh0k-PY!8+lK>3gfw|_NOyoeKZDi5140q4GSuQ0de!D=)0#lx!aP&)+y&!+XR
zap1N|AI0*Q-|4z5!~hzZ4wMw39}9hjg>l4`Rb7UXTS!IXyuKF(U9q{Z4UroeJ_K9P
z4In6XeNmCPX`qn$_Lu9g5#Win$UUzbv#?##VZj*3i_^fA`da1htd#D75i7dd0z-*k
z#WmAT3e|3617W`!!OObVG|1G)@~0hJPVA}aZ>?C7CDj;1gsX^>=o9aF-qLGf!6t<_
zzW(fzJaQ~otK|cpmKerIlP+b+s577{boSDwelQefFZX)1tBBKxyeucqD|xyGDlt*~
z*0tU36}0rG0_I0ez1B+*V8nJqJE!5Wvnc9*UEF>Rqpem`%uF@^=F9L*9y%Lz3d~XL
zPLuVw4~<yR1sK^xM?UzZ*~tI(FWa}cvcT+?4Kv5wM=^bdEjq`^(IzXp(K**p-%8?K
zJrdeytL{J}eLTr%Y}439OE&9V5qSL&;3)RcBI^fF{#|4~URGLLNZ$BToJzZf0w*2}
z;-P&1j~A*FjG$%B*5?`GFU$TzBRl?nO<)7-ej5jKUk;~hq^@yaT6;;uyVH_g&p30s
zpzx+Ml{!cZ4nFwZax(`xnUec@YWS_g5~G$Cl4I+5vb61jQ6({30A}pa#uNYm)K=L7
zdB_I7^M7dEln?{2bGxkF^(4`a+T89R#vaJ~fp%ZKO5l^`%Ikd`5IM$0)pOR)PpRP?
zBibIfrmxFR9>Ettd_{LHPM{sO$qQSw8|fRIM>`FeW=oEL+?Hd_k7L=!Ti+6~)KEEa
z>RuJikV%mo%OuBF+F7j(fLhcOheJhb9AxvzO<Mi;RN?4AqdNFF5NpS>>t?eitUX}i
zZ}b}6HWU68;lqdO+)`-3(OM;`VfPe!elx-XrktE;*1Tbj-!qz@<&Id|dnU53QI+pO
z8GwkVyHHY}KT-?3zU}v9qmS)lJU@-geo}kGLcKLw;?3M(1wxLqzZS&*nR@lzH?H33
z*D1M}8eHz$DPS|;Rf=`ShYf9<@j0T#JC(+_#E7Y!%RO&RvBa~efIH^}y0S@u@wJ|u
zEP5NjOeB8>#Chm!WZKfyjY6sB)IEJ=wd)N%D_7mH0P2wGWW!~IKQ<QY0+5W_L;1)N
z!O3X(ck=DSNQU_^Z%Rovqw$gxO+7h@SbCb$>)3<_=mK`g!;|e??wqVS{Q6*8C2r)c
zP1Ro<K9T!cK^=_t7xNsSdley~uUe)g8FBA?&^Us%#neWT&^8-P+!YrmuiexTPX@ah
zDp(R^U7&MO)J>0I;&W@pMr@nDNrHPZ;(4`9ACHyK;z%G`cr>^$NLjQm@q_Y2%q>|j
z=g&7iY=p{h7}xD3eD*TlfNE3%{>a@ADBOyVcYvl878`k8$JwgHjuTErj7|<ROlqat
z{Id6J=mIZ<vXdJ=1IBTi6;C`65x!O)9N&z=E8{!zFlB1;Zmd6eQumWP(xR@L6~J}E
ziAI0J@c2@P4LVz4H6{4<4dc~wr+M=+LGD|XD)gQ`<e`V8U1Ri@h1xWT3_ud<7?ea)
zfaM8FKhTetF#Qv9nNFNYFre;>L6Y$P1@GQohFc;w6KcaU29`Z=g?7RC@qow+=$hNc
z5B=v!F>1|4rZ4IFBRjTTQ9y)BI>um_asV0S#LqN5knos!{ElJ^XH3XxG$fWBKWbHo
z7I!@>7jQyXq35&wBJd&}PGOKPKqrCTEAfz_JASO4hTDU}lK13bpj1>NzYKVlPtTLG
z_vH<^NziHELj(eXu4zkMFIgnxg%EfM=y4f^_r6fwrb?CH3o;;f^<|MMu$1UCH?*1E
z4rgk#nr*?1c-a!liI}W8{hTeQfns7h`6^tVY^S^5=S3;LQ)}>+Hx`yWH=7?dL{&3N
z<R8mHv}--bEj8c-s|Mt*;p+QT#B}(UEx6a2vN&u|z(q+SjiCi;gEi{x{&0?M5raN|
zm4V$D0Nu$0KiCzih)&BpKVwjQ)est>P91a*^+O-%z3gmpPUWAP@?L6o*121Lv@~AL
zlyQ3}+#~lr0V!+i%@o16$wCWwvcu|8RciMOXcAwi0%j^|>>K%FOHkgrpD$xRkyICf
zLSf4vb5c%mXz!>SRJpil&I=(+gh9Kiyeqx|^-GeZVJ|5-rlRPjclhm%wyFTel5n&R
zD6$Glogh`7RWai9)@|?rp=)ha{)9K@HS-t4R?`<ho#YP`YJ}6KZm>-dUW;OBh14qN
zV`ncJ&Oy0*#-n{Jt=6ooiEC8drT2Iw7?JUkz_{^L6uG|l|3V)G;m$s|8?|eQjSB3k
zvY|h<z#+`7WPQb-phkFTj3Io>_ZCR3`e%&O{;+rVeeC1SO#SvQ=hC@<S@ETX_%mQ(
zrxG+2|J0b?W8K$XprG5+uw~sJ%S}$B8LOt}vNTt>RgRHwYuW$xvMf7X)snJbt%+6>
z7^<J8!`_rYj-jE}T#ep<n)Bc0Ho;E!v)X;_wZRvHKkEl%9tHg=3^+rT-?D2@;?FBF
z%8mBQp=*LVDlQjq?SYnkO`xhP){opmtZjVt7+VH{de--`kx~Noq#~E(kSUD7AM#J@
zRt$-BJg2$ymN<v@m#-Vq6UVA5_k}9v07RAa6hN!j!+QPGb<<xu_r@d<C^E5+3S~q|
zjQ5<3wG;7AmjFP~pyy&l3^3}Ey4!V9n`{ofp#QPuag9UwZZm5Ul^=%ONBB5T0(N!K
zZeFv3bm1H3oDT9Sxi^o#o6WBUD|S{QYsc<nB;8k}X;tF$3US;zs3#M#Ef_s|rYrIe
z*cS%JjFOEQZnKwO5cCGhzK$(3E<YvV5kN3F$@whGhPR^hTZtaR$!O*e4tm*1J(-(=
zN>_*Ac47Tu=qNJg5q?FjkyjG@O5ghEGUTi%E(Tytr4~X|<{eTn5pzBAxBOgM^7Fcj
zIQ6z4mkMiQ7aj>Qnu^@=Hr9N7wT8hNnI4O!CI)*}jaq5wx%4ORg$|Fd$i?Ze^;EKj
zrv+xv5WJ;h7wCN)wk`T5-&hEz>YaDVR%Hztom@vm7~c(*u<-1$R+2xTj#cdvQe@pz
z6Wz@UW&@N089P7fLc0(i7mwmv<2K)}{7;Z#LhLDApnQ6!U!X!OFucg|x&Ap=Y6)$(
z)<mHphQK?#L}x_4MFIdut*(lOLTnhG>zA<x_y_*unEx7QXpJ9xWREyU=B5LJYm6=y
zXsCP!S!8sI<HKP^D&9`mMQqEKBP8q}bUMUGG++3L^*#eD#DcG2Z>9Y6#BnwSaAI)G
z)l#tr82ZQ0dJISPJlChK`kk}B)FnJ*G}DKhQgSCJ?yIO~7-w9E5WN=o_6IO`XzyC)
zbVXPu!25Rqn})@PiDd;tl|p@j#-yioPfH0yOF?(I0Y8FV`8iN8mi|nxK+mdD1|RiH
zV@@I^VK}cEC%flK9`fNc-@kBrKugtzf(n4PGbGm#x)Je!rgj7T6YL0_Nd2Gew&FB2
z>i3%AcAp+J6g|9b0b{<7ca|Jwv!iZH*T7Zw)X8@z)DA?<)4ItYHQO1wJ21vymVw8x
zS&+R@ZdG;%oF@+M=Ciu6Uy}|qh8QROLB@Zcmwu4}xPpPxMe07Xxv2s;Pe8Nrj}1+G
zB~%5+KEH|6_a5cRR>`z6a0_x3bzIuf7(#_`Fa=h$YvaZC4YD#`6|P;)#r1U-0ae;2
z!40+}t+)q|<%rn~4?kN@((V^a5JB2(^?0`JeY(#$dfA-zFoWKnZek5$P$X%Ja~J3J
zWJD;V`(p!=SDMNa*LMXgcAsx(LaDG^uS*SenipE1?@4$}VF*ERMhzpA&yBQz=`upm
zwZn34`gu&$_oK#qPYg=H&_~|u8*&@Z@24*}&{e1QM=o{KK3)Yhm6U{jAn=CaAj^NC
zUUe=dF|q!G=my1=N-Ipoy<m6NO~<y?A)mB&HOC&_CAKj+^w8UgoT}LZTk4SD4_?N9
z^MJO$9Mrp*S@XAC__!&LsGIQFQh7)#6RA^rpPrC$#-?DOGl^Z}MNp*Feav)%?Oh|g
z_@I}>*BIg=nP@rFMgI<$IS_ch7@Tg!Cbl;e_jEm=KD9Z-x3O0E)V8qlZN|uLq-)(h
zG?X0U%K^2rm+@L6c20{!;-iVs>WI-MA_jx1@MYlGNc@gA*GHA3NXh^alv|&L=X1jY
zJlXjI`Ue^LPm`!~`S}Ok?9#-Y9wTL0AO_Ro4@4}tg4!Tz0BCf3sBm#U$z>MH!A?8L
ztA#}zwxPK`vMW?9^4mfEs<tWOUDuW^Q(enrl(3Q~*~p4wwoUn^ixF?w2uqVUU3hb8
zXrVI3Glemu89llDY%Ap*4flI4;bNiRMa4=+1io|lq)%BalDd2_f|T_@I+P!;T_R4$
zBI^oi!Myu~?^a(=4!bCsH)+@<hLVLd(z7ov_Fu&8m6*%1jmCIYt3ADRLf>QD&2uET
z$!}u4JTkhQ|KTCR4X4(sj}JxE$W?;1lq?Y!MZXBkV|paCfX8eCXZfr0UNHxcUf23(
z`FrXV8=W<7K0jD)MjAVntr|7@*Bbe*oM8o^<F*(Tt_RIG3QQFmVrmfNJqYSGPI3N{
zr71DGQtakvjC5G(oMyyXOI86hbyBe<0<(ejmBG^@gW4TEl)(06rQe^+Mm2*s*m{76
zjVeFo?H_?b_trgOu52%kKF3(*376KV^x>p*TqCNO95F<Bnix6MRfT%H>fcZ#(*Xi!
zC!FttBIB>BBHfO@a1Y*3+|qnLcmaTA3!O81P}txHuhG>T%1m`Ds@Bx-9pmpc^&e|0
zpl$rBNkg;3JulmA{X=<aRUMbGPPvHlw>6bL38bmGo}Tt*9JSRg2gn>8s6}v{w^9&J
zn+5J#F>EhypYRL$Ua2bC6|dLrNi;q;j$#(`8z`X@u5b=D`b2SA*yrKIS@_pUyi8wC
z(iLfq`qRP@+K}Kns>(6mw!0PjSk|qX+>O$v?K||Idj!n^HCOAnBU4nfbA!6wa&yKN
zHQwh#yvRUDaak<U6JyG~BUfh}TGmq%b{6!fQO3xl5KPkQ6d*}@X9g|uj28cX^g-fp
z+v7B%Ys>sRb*Oq3N5aL$X0Q7W6kNx45;OO~VP|PNK$~WHARG5!S<~ft{O5uZyPnry
zXoG@+41UbO)}q0^GoI6@Xan;^Vw}4EI{Uw3htS2>H5|5N>l81l?^6-}YKl=_yUn8;
za2+L+Wz&X@T%!+-d=2;_Kttmpy?uV!j5UOgz=Ld1M#SID-@BDpdU9YS5pO7_xnyxk
z(g$kpezGu9BU)lY8zK@7o-CxMOE*t@<l%U+r_mB8O_^GIs4$}L`0S9QkuU7N8m`$&
z0$8rU3<H}QP61Y4_ts0jMmIyjNRF6fqfWx!f|8<l?$KAj-x7G8Vref3iNUW=*g==F
zfgVqCW<8{_%n-Fx8S9zq?Kn?%YICJfq#LfTZ$4%08f}#~KvKDVn-H2}!HyQX4g*~W
zVMb6<7irVx#RT+yjvxwMM`jM=(H=T{&Cy%wbc?;}5jAy}LeGNZr~=2NfbYfW_8^e!
zdz>=iYVpLKwXhr=H0S2u3hDUVXBIR;qr?WEEPNPS>a};a?x$34e#E_06$7klaw&t-
aY*^xaHVeNliag`RWN>&*oXYUu!v6p{hif4K

literal 0
HcmV?d00001

diff --git a/tests/data/pseudo_mapillary_dataset/v1.2/__CRyFzoDOXn6unQ6a3DnQ.png b/tests/data/pseudo_mapillary_dataset/v1.2/__CRyFzoDOXn6unQ6a3DnQ.png
new file mode 100644
index 0000000000000000000000000000000000000000..018a53b3a46d2aceb3bac0bf457dc0829d867f0f
GIT binary patch
literal 75488
zcmeFZXIN9q6EMCZfzYvoNQod-1?*CSAkw8MRVl`60Xsqz2rUGaYlBF)P}Bqj3s~tA
zuLW#?2NfGd!E!`EAqWV_J12nmcc16|fBAoYeI7rYow~ETGqbZ34!b(r%1J9rBZTDa
z?N+TtNP&xx%q2-Oj4W)~$3TdTTvxkW^Y!(S0NuNH@Ak=)H~2T!hox=ZdWLN=dhA$D
zK|#T<f*b~e@hR;X+k(A&_imx)m$c2BZES4P!q&f=W;Tk@DB3)VYHHZ*(a}+h0*g;M
z3vD<zZjX*;3}x&{&_o4lqoeF!NNw}68}HyBo87FdySYG3S66rT?Ae>yISB~aY)-=p
zHlI9slFeo#<oc^XO&}1wdxwr4n-(fVO9KgJn-K!U^$2}JuAA8w76|PII)nr?8ZAtk
znB)KZ_x~*L|IY%L+;2}rLdbrVrF+<!ZzB&A=GcekHucO9Q_<!ww{V&{U|DN?VW=wK
z?HMaz>ziFCyxccmw%1zp&dKBclTF=u8dXn52dGMKs*r`nUteS9zWBO%d-s%=Kh+Pn
zY-f|#JGr6OgZJtU-}U&YIlbTY&sU1EY~jaM;z-T$$?!GRs?KLAP1>}Yjgh<J_0e~W
zzuFt;4RqG!eljOn$`{v17m1;4igxsUR!du;e%I6iOYU7cq0(hkbn5tmSs4TAp+o+*
zUfkIN1&&HrPGguj+xnZ*&DhwOz1O=#BeiCWNd}i3j-EOL<rW+7DwiJ&y>h89DzQl4
zhOrL_&UUAWv)ApCduOm|<Ycd7RQIM!k0*Pdrp2HBLJuS{Oz@4j@phZ+<&UvBvHPTe
z)4faL?1#MS!9#9Ck)P%qJx}q}s(Ej)ux$qVl$7<^P<6wn5b8R0?II0J`Op)mOOR2j
z&@QIyi+;A*{TbWDIwrRV&3brN1}(C$69&k4{=ltvrsx#SfQg>SDn~|%Lid<&^=jGX
z|Ja0!?EqwT{EiH|ZeRB^F#(XTyS2MoaPLO(J{zFb`t%Pmrnjo|6r8wLV5wzEY8A-n
zrZ8s(jJY_T7#jnoMVwcnu|#_jUMPWAl<+&`_bZT-9W&k7SEuH^Cl;rOUOtO@qW-q6
zp}Mz_7T-ZJe&@jYE+$yXN*vr25&4TLTt015dypaiOa{r|W*-wlp}Uhs3RUuK4bdfD
zcM2i9&Sp%X<g7|mlyt>PBuCj&UK|*%X8jZstYyiI7;YY8xD3Z-kR!gljbIoz#;}Q(
zXNczU+l~<o6~-7AC#zKf!vswcL!~i>&a7cEfrClH0HGn{&2y=FHr%@-JgO0z$7?$v
zqRw^76#NCUU0Gsefr*Lye^BN4I)HlqGh1Y}3Dh+#3R$4fs_nPh0bG?|h`6fq1B}q6
zbDtwu+<1_ukh^A#>spp1S)jp6_z&uQemrnJ_c`o8sBSE2vOt;TOrQ?<D&Lp71iI1>
z=7~_5fEr)NUvoyV9dvaMlO<5)2~?rGGGFSFE%&aIbv1$75d^3@F8nno1sp*22$ly0
z%4&ZCYS(JzeNyx6xp)0Oej;@3-U+DHwY)WHf>Q+7oxs)Pmx$|^Rm#><mmGlW!3TiK
z>)5&C)`I|fo>P*b3{c&+g05=;b<>W>4`y#DQkPbPu3EXEKyG&spi&dgJ0%J*KwZlK
z3k3giCQ$qD2D)h$Er;#=JPJlRW24>I1E*>hnZSv79w9*%oGMEoa9iR6lQr11c+;<@
zaU_O^U-eMK@sW-4{bq-@&KG+;wLQp+ZVTcrbwtKoE6l62NVKxzsO;9Ir;`|y{XP%f
z-9?WQ3syNbr9Ef`en%Ev{9@9o{_QLNdDJV>$_I|N4*evFF_TUmPIsb@d>?(ZH_(ZD
zx07eP2wgh=`M~Inygc=hc)J{d1I)phwG=GFavo6dVg0%jBPlL@X%&H-w+J>z$AQrz
zeqQ$Q2D&^QoJqDYQiAQlRQ=waE)>Q+-uuOh*l{|GVQISAF;%?0Y~MsHb&;y)NesED
z&qL*^^pV!9%VS>v^;uzx1Y3)l)!n^c_${OwqrB9td4K4dn=+d5Ec|xW<uA|jYEz}=
z*>UfxT7O=QE}iWUi}86Dr;yn(#XAX%C0)A>d0Th?_#J9hM-Mh~WH^B&y=D0%#%#a5
zp%yuM-;F!Eu^!;6_|JI~?EB0!T`@C+^~u_&DQV!T(pH`aNzZqbjjpR-<Z^QL6z_Ce
ze8i(C+mZL$?DxMTRwSBjykW=K2=>!kc!|VVr+R3pd&KN}&@;7IJ}}J}+>l_WF3Ik!
z>hJARm~nZs_Zje&U(GL*7~#7Dh6?*C`WJ24MDYZdlFLfmfpWGbjr!LOnY-Lrg<w~_
z2=ynUsvD=iRo&{nl9(hnneb-&R9_*1`f=@{!p@4ekj;xIgp2pvrvjr9PTE6tA1hiG
z9hgfQfPKBIZ`Nxhpw5>dMjOcoW>E%UQFrwz!)Sn<#86^WMMG2GRLTIXNz^{&H%Oq^
z7cx@4yZPhG29j6>IMfY(hnAx6u6@3vxz!u#FwKjPpGzRMxmg`8Wt8wTbG8C(2k-c+
za>#6r*~<uFSQ(w|LJSR+!jOmQ%eU0<GBdUz46W<914CY>FMRsL%1qf*VyNw*9I9|N
zeeqTzyv&3h4?{i;uSG)*J}_j=)`214yYFF$nS3J4K)zKE%+k0!nv4qFYkT*{SY*k|
zw;Ef@_c!ij6JrUzo|aj)a;?)X<rf7m{)fa)|GKqQEnZ71IAi7c+487j?XpL2LGdMQ
zIgX0<v(3kVDCOyoJx(06Ol1KCmg|8Fs!43Gg50oVHJ5maBCwa4^08plntE<#vqnur
zCg~f*UX8x%DkzM<l@oJOp@+Ezl}iR^IP@*1BLDo8Ei4rXavKd^^a9G+&8(P<@;%JI
zPz0#p)VT^!bWb+59EmgYQxfdvsN}ktU?lcu2krjiH)<~Z;z4l4r97PXq1ODQ(vi!H
zYZ}5yDzj@g+8o@Zioyyu?~Iu%+r#ul)gaOBHKRo@cny-gnDM$rxcrhM_b%^|&5%KU
zhnR)?{hHsNGurWMNPcR&(dBdRZ(DUeLX$ie6!k5i2hOSD$b+HWcc~;=!C$^H7o~fc
zUPuR6u6xRE;g%U7o`-D5o+Xx9SEO5~S<1Uz%=kWQZKF85<jA_q)f=~f>AV)SZ;<wz
zfqJAR`ihUxTy(^P(rEFo{jz%uw_K4%<O>-MEz%q_ziEPP9F<RAMSIPrm+B(fvwt~k
z=>EZUL5h;W-WK<3e|Wc_Lq-RV%pB<q=H`Wnm8|664R+YiZ87naKoaf?Qmg!6x~owm
zpu0R%?&*G@y*6|vQgVIh`m(KPsipkfuh$Px^Aksh+!vgv@`HKUqjafY@3rYpyiXd)
zDECP0aHj(|&q}PsnS1vfYp2HaM#Q$9zPfFXBFijuvW2*%{Kc<V4^Q(YBMA?qV^x{3
zp4Lc<Vtnc1h<5OxG%~u<aem<KYnsb4iYqv|f8H2scoiblR%Z5h6~5OylNQfkvSHN~
zKZGRqhs(y8Dz@Wn^cB?g>9B6cI>>?=1DB0-dGOFhB`=TGq&8C7C;T$+wA8{bRAaB@
zsH8Q9O*S6wK}I(&PW4VCb5sJ$<IhCxLrP8eNs(qX4LEY2+Aeq<xck=!WK^-E!Hd8d
zIQvmK`0Gs)BeL;O_cNMHD7l_ZqegEpK6EB*3o41*aefT#@@wVb;e({s83uCAo8Yu0
zNaV;_$`4~Z<&1y-gMwtzB?{HxB!2h0IKTZ%hnT?6_hdO0mQB`T5eT{bVoI=ZAF0*g
z*OMlu5$co-ZY}n7ta%1Iq5R9j(1uF1cur013g!8;sT*dX-RG;HJAD?bPohzO2i`cK
z61fhQ9G7=n<|kv}2F%Vsn-cte3#rxoltL489@-@p+*-JFZq56T5~%B3-xH@|vHA?4
z+<u*-(y|-1YAYwcW9p;J<7huRCD873oh44`V)bWe)aJ$OEEBqxq9FB7iOXv7(?K(*
zWV!ZNJtP#0ZLRs8(nZN3Tgq1~dLSW&LZ9uPmb-}b#ga?zb~mKiZkUd`_^&6e_7bZ<
z2(0vcEov+0p?8kw2h$TMISN4LbuH#hj0Y+?xwOr&Nzy`xqY_s5*Jw%4H56p%bZCRg
zWVSyT&Hv8ty`5kl&-KS{GiReFP$KT}Q1yK<kIy!v0W1~?HEUuO46dlBZ%{(J`O)9_
zL+Fbgm#psVvqIW`ChFove&P3`FZM9xw+@B~EY_z^-w*ptpMbXNe%>n_M0jBzI(^<J
zMlCTiu#}HvMvv&SwxN;}Z^Dar#IERb5^zDAhp+q2f8~=}Z5*nb5;{lzDHdy++%C}3
zDNZa?q_T%DsO*1RKJ-x$J<zC$bt=D=*lQ?(`aPC+EM3-L&`3HoyC$~n3Z+zo%Fy0-
ze)o<&g;7fwk{p#UUGK8Q5Ltf~voQVV*GBRKT1_n5?X)yHmbd*$rSEH(rgeE|(3MH;
z7WeXBh@nGni$3|!{}#}F$;%aemI|h|e`Ar5X8y_Gy2d`4;+KVb>|}~DH+bV+#9s6K
zSgB6=ulo@lZ>9^RI4U)zC0mh&|I?I+lKc%-rM25gDq1zMypD?!XjSU!((2Q!`<;Ee
zWLjyK@|!*8%|esh7PhPH`Ks05xXggPiDEp-^V%+CVfQd4q9VWX9iycT$xm*#@O^rl
zgru~rx_;#PGvlLr#g?z+lF7PnmZO~Vq?!F;ZiQv{Z%2_-U|uBmT`H*FN5mk#X;X^;
z{e+Vz`N&fqeYv>#5xx0&$L?!;HllK=U<PI1Tq<IEEc^r-91MNEYyrEHVr+EapG-0`
zDaZ(MS=#qc`M32V7q7JPeJu&mr^}Y<oMwIW+wUaHFtn6Eb~YGC>}Y9;rZ(%!pG${q
zB#IJg)CaER`;f)5Mjc{wVCj&jMA1<iRboxWeq^E3X#0O14IoB;nGbE1D2gX=D+%0m
z5$>@0(0+-cID+qO;QN0cHB{7TO17^2ZC*Zxd&sqli7X5isl@1=<NM|07^i8}L-h>M
z*Z<1XQk|o$qq92KD+{zO<z>&_$4DsCcUFkYjJ_Gm-rQWwh73!|@+jEhSLwn}S@XU+
zbzR@F9r;j<>#O-r;>ad+<0JaI=d+pu8($&+sqGdDvxXebr-IqusBv7(-ahwf3aopB
z{HL^AL@4Z!eQJo<<*!XCD<W>?7ne6=Rgx-Tr5<E;ikaS~psp>WN|B%O+~yu<Qwi#K
za15tdSEaxG(m*B2<dE-$d8b)#eL6E#1mMjA@jm^c?u&@A-DO$dtAnv{g6pxD`b8Z_
z5o0S1wen-lVW>XAgVEwe65Plt{CdZc>?awVbCzDtR--cZ)p-(h&Vc0HOBX|*zK3}z
z_|5oY!zDjmyg?H&loLJsYOG@u0AY3S5;3IRv(H1pcghzBF8T7}77fHO$oA@MZX~l{
z)^jfxOQMY0Jip5B7wj&euxnElL%G6@UftpIX%<}auEqYd5yP{4e_ynhm<Ax&v`rU7
zCHk3g380>`D^x;)H0BWm^U|pN3n3p&53cSx2Ze`7Xs1J-Bp68olaWA0^F;*8c7{N3
zOGI!Xy%~(U3!g#)t`@922;Jg4Qs4wv3ZqHr8`l8ROmZJKB#w%#%7{Glxns8?63B}P
zTn#HXAY{rD5tItyaDO`?BKU}P0D-NDAjPo|2-L<13@ZH*iunH`xSP*%{ox80x-X)y
zeji*Sd@9i7sOYAxpNrU<30tfl9!1$OHSb10F|>SJ%tH6uGrnihs7G#Ypdoh0&yOqP
z(kZ`TyIi&Lfdb`rulb83x4{fPZci6SIfwnO*1w-pv>0Ylux<)s-`dYxSvB`g0maz$
zV&Hx<n%}8=P@uJO2}k9E2fc#CW|^*>9k$K;5RJP1=BZ|6k=f~N=RYeAyyN=L2g{(C
zXgc+pSG))4<N0_{4yC-hbm05Pjnjer#eT>@8+R>PIV{0|Z`~J>95PberS%UgMn}QA
z`SO}7sATi`NfIUE-Vk>j`ZC@lf%vRgqkB#QSYX$Jx=B=2`{qlW<!<szSiiNExyw;d
zZHJlCM{@?GtGX}tK)R|^aV&0c7e$2NM>R%4&o3@j`r=6-TzDSNC8O#Jhq$x5CDMR{
zLz505+`G6~sbe=ooIr?4A|omwT<wzZBoIabp{V8YVx`V#Ml^_+qVxd?78o`#ZVZL*
z&C{t;uz?6B7E6*xD*X%P4wau(EDkq_W-R8YlxQy~C$U5PbMJ(O3WwF|sFRMZ;*uLz
zZC!?f9&{{L`kt26(!!VItbwR_uI9T0at_Os&}?q#Jzeg*(g=2y@3f3}NT65Pz^FOR
ziVn~+rmO?57kcXfH6l~Os`+{E+X8(J$tmpu54tUc`eqwt*)X4gDuvzP!M*k=zeED-
z!pDq~w<aUUgJuD3!QC7QBwb+uv+EEp`zI457d%*`jC6a-WNk{XUT>i;gLLKbDW?FG
zgLN$YyX6(W=fGRwzvZLbOccmCFN+n2I;3yqY^4|ntz%6iqlld;mcM>F<Jju@V>Id&
z$GX1|BmVe8yOw4>zf)4DAinOy*U6%9MQbGRx2Al@MV8=bN(|^nN$g!dTe!EYLRgEZ
zE+$M!pzVC4A155iY&d^1XQrk6G&_P@gXc_MclQ~!r<A9#rz}`A$msN~N3^Jz&%!|M
zKyWSM*mWiJ>e@O9e3n_B)j~^CSVpee10*=~6!d5{R!x$617Yr<&`1I;-I-?jOTy)A
zy+~bsUcdrWwDGzuwk&LIyl7Ug8uVi%cH`2=w5T|pePaT&u)9hqY}bF#H0j6T>hvG9
zC0GNXZJR5L^@n;U268-M$IhWAz+LIqKcH@2-v#YJ*Z>|_8=!3zp{-Bc&anYBEdovP
zKWJO9UO?OZA2e-xBHV;TXaRkHYX@3$$@{RWGf~*~{|MEkCz03z|3N#5X#(2T|Dfs7
zlSynH5t>fl*i88tEOXdS5!%|sF@xySQ%UUV|DfH(HUV0o2+cWhGiN_cVJ_5B*zqE?
z&q6!xKwH9L#R1yp|DesIXOP&o|3Q0!B?B5mgyxX=7v~Ugn@>MQVpBzEc|u+7Ku8Hc
zV%KM)f$isIU<*2@j|nxPpC+*jmzL3@BJ!AeBD6lN0nongQ{;7brI<gYKuVtD&oUvS
z4V7ISVN)iib23NOQhqU4tquvi49jUzA$iR0qKzcSt6qe@zj$n5*Ya*==Gd;0!AWu`
zvadh}>)&rvD6&ZXN|pt|?kh)FnfdIZXsa$hkyQ`1fkMz^Pk?ZYofA>R`TnAJo?Xjp
zy^#VbW!QwX@X5gL#|>$0*?#Bhot&ja*kY{$cJzxJVN@oz=rnQtSe&GW0Xvs-v?!m?
z%uek<IM2s<@dUfO+IB6^?K2-sDTBwHi|Y~WbfvI<re`;k!-8O^P0uB<4R6n|{FUI`
zq3+`91i_bA4W#!QHSAiRZ5wHmDv%1!$rPTEK(_}}DEN@E;RzR4M=n{8PhA2M;??Y0
zo`|32a8?30UHS!Bh~|$LzdQ~8)|&Pl=HQ60figu;o&?sv*ZSJIoWE(*^$v;KQR~?a
z3%IwBI$l#1hudMjJIj-d5=Z`y71Di^4D@utndV~Gl~LG-PjrKtld<De40HStXCX+^
zqZg6bhk0Y#@rCasP%gJtJJ5>ID;`{CD9+%d0bf_v0WvC1yP_4ingHcN1lWMPbAAHI
znUz3B%TjCSKnac9$qNA2Zj0M+c8fq~fGSyj4sn%u%A=Z~phdU|rxrk~S-E7?e?nf<
z4lKF|zax*{tt>lC1J81q7jKG;ZZj1uQ$SmLg)qbj#HVr0Eah*U$ohc<CD?RI91u;#
zjTO)_Jyi>%DWaX#hXib_lYAG9RVgf?BAetcH6^(874WI%$S8%`BPfAAK94RWu{ZK|
zP$hIAl;NeoLQ~b$2+Er74s}t8p@P4ReGe<;%=$(~Wcxh%V=i3s7HpF`QnEMM$B2Yr
zl%)0x30yHgc^Oz&89%FlWVKXHf~WvGL4X+JATj(faM#H+F*1j+lAhI%1b<_f$#)@n
z--2%gDt$jwBdD_areq0;X_b;U0ceS6TJxGrjUYMjO;+ngf_m%@SyKek1BUbc%#4gg
zpdKV>#U7H|AXI4KlYyaOlbO*x03~I8M}h(D8Tq^jL{dQSEKMR9t04%?p*NG*K6arB
zvalrSygXABq=0{qoecNcBw-L0?bh%!H-f8-?+LX|B-q7kpgw>&F&9f#MJ0*MAwdwt
zAZu0;taws_y3%ooK6Z6b74pOe$(tbVOvm$KB^}FR7`h-#gZ`YvK5ai1gB5wUu>PjF
z7$+7YAV&x_r!JjL3nO_D##Q@*1akaYlEi&a27?k+$$2K_jxGqZWD$EP<qA#d03j?f
z1hr;isuZh9gs_bu%-!SwgCY|4n8Yr3NS`DNS(X>i7WSdf*uL>iQu~Mmetb8{9$;wC
zN+F}rROi_>U{Wo74Y2SqIY@(LP9G<l!68;9d5p+M@&gb#jS=mh{kLcxL_}o=Y0i*Z
zh={!KF`|?#kmST4BU-~sBTmK`ku|<fB<T<he1jsNP|pij;t-3RI!3ff5(@D_9%Doa
zv+Y2Vhlt4CL`0O%qXN-}F`_f+S&$N4=8K5FH&@x-o`G7AFl8-ILFr&{fpUM076Jo_
z1XK*tRr;e<|9lVk?KbZk(no9=Yyk!8U;}M!2j2BAK}eA|#_nzU%+itR|9(F{uU9%K
zj?m|EaSd$?N`E~57v6B)a`0;-LRajnC-Gn><q0h$(97hpIk@1lvgneIsufqeCN>)*
z&qUrXV-s4zr!GWASz}5^J1A^M4EmVH!zpStNU$B#qlANcv*{;D?E5?`NgFtD>ewRS
z;9wHRkQIR-P9EfGO4`82QO806WMdM`P!WMnlGxiu3=$JZ6~BYct5$(OHoBbHH@o^h
z)L@3WYA=!C0Ctsp9t^F3hs&YW+GEEU1YRexPx9tciIi>yuX-smI?8-6I1c+ZUid}i
zBWIN;5<Ie+k)VnHSYkKC%F!=-Q7ebpARuZ;>X!28Omgkal4XFVSwmvq#k9y%VbiYQ
zsG#Ngstb(>9SA@irb>330L<}QU?epT(8MN_uTKDIO-4pUiHx8a!KBE&<A7IlRgH|M
zTFQfLMj^9G;7&270ZJw|C>Aog9qwdkzr$ylCy=y&+*f*;hDM;bWH4gnF>eceDaJWa
zR{kI4pZ1M1tHBB5&tS7!m-#awNZ2LrN38}}pIGwb_M!^mW^fXkeuhSnD_(R|0Fe1O
zs7%O!BRvi}>PWZ+n{iNy&=){+#-ty0Oazegn1)4V1Zej-=;An)Nck~P*PJFpBdD8S
z9H$x)a|1QXgx&<h{~M@cOxBoL9*<Lz$cseEi>Uq=WP^<{6jALSXUL<1TU5uRWAi10
zY4lel_FKC#8{!YaEH)+^7zP{_ZaWe<<B_qYuq*O}VK52Wm{o?;2>1JaZ0dpy_)PH3
z24kR#<ScO7HP{ca>)<SHaeDyGRW&r41?97}EQnw^;~+00KpfL;GBAR)$t)#n011My
zPO%1{nu?zUD(!Jly4nyDSYWtVFM#Ia4*{f^X<!7~Z>OC?3}Q&)!Ld?M7_wshA|p+^
zc$p`#Q)gjq>ZrysK;{VqfmxUgLX*<3%*cRvyOg&KA=-S^`9^aI4p33H@Ge`&SkF;;
z#cd`b_66ou!99v`(d<fa2lhB4_N0in96}tdQp^ob(jlQ5LhZZ|@lSBv<#20+{<d$F
zUJagd7Iqp0CGDP`0oUZEyigLNX=dshtsn#$l99!#GIs_E1SR=X5u44tAdm(@dX<w9
z8sS@s6Zb+V{2)SK44U+cC_v;`NI@0>`0CgtlEI94A#?@_Q){PrLs{vk-5zmd;etEF
zS_3Fi2n{#PanOGILJ??;Dq9Fe0AWhkG;a=#y5FH&1aggqx-BDbjLKlTHyom$4r5en
zW5oefJVxa_JtG^a90`yY?iq`NDT;-jgc=FcGcpOPZjpxGv9AGCD0Bu;+Lh@UP!9rz
z01Cx@V@pLK=m8R@cTLX#@BP!k5I`}we{4R0@`UCH&Eds~Zv}H^VjW<?69zLfpd`KD
zVGkJ1#$+ACAB?6~DT~ldd~<BLh-e`~2T~5iUx_aS8@jN-mj@dJ*f!0*vzqvZIFB#`
zPusqZJ9CI{hLDWfO6pba8&V0sVqTdC8B<2n@gMly!b+tlkn#;N)dpb;-s<>pCp{}>
z0WtBP_`=U5_K96D@23}5_WVVx<2Q^YfY@5JMlrkU=Rb~jhy`?PcnxRfen**Zq@FkA
zpZm8hCX#~ib&C56DUKk`;P_U^3zijrJ=c}WfO_jI{!=0~_#E#0ymHDVC^tvk$oK?7
zm45VSL1QeGI2egD;F+uBqR!qmeI`ZHAodvp>IeOO%MA+rsh$uB=wClWg1RZO?cBG6
zjLE?Ad?b`8ihmjzJo1;E0SKxE0e}#);qkfee4;Ay>TFOX8MzI(PCsZUJ{L}s{F1m?
zD5JXN+=a;b-f+j>ubXiL34Cv--WX_U<V*(}CteGeLEk-0j?y6Qjo{@$Y$;|cT0)Yt
z-`-^#V(i9^IIv5<i7plG*cJ-0wRPw`68j;)LGl-z6mxv09C~8VWK$1&WxqpRAY$yt
zmvfrIXl}&q<ho<^WFf42B?iTU3}2Ik9Ec^~QnQ{RK|8jWQVB{F3%L^LQ(A)N7YK0W
ze7LI^l`>T=13;7^A*z($A!!1lqVd@vYQCRs{Ye^C-j2|3`&c3#WWjQPnL9R47WP$f
zRF-QH7nya0hJ!6DARSr7awnrj4xcA8d#a$^)yfrCNT99UT8%FqA%DvRx26aOMBkcU
z+SeTxeGiMi=LGK1yeDoP<jf)rYu7*J#?|Y8z8BdAOnq)L;{(Xkqu(a6^>{;44rgTc
zTFReERck?lY1nM>bl<tecM1_<r(tyQyp#haG-|Db%O1p#$BQ^t4vxNDvJP=ef#AIH
zj{N+U@EyRnh3`b>jyrDitwiw85WG{F`|jw_3AheF557+_WA3=n$KV0*eU^FjYSAiU
zIy_=}pHgZUrX|n&(E{^#WqFfPuY;npqn+0P6gifQ?q;R@9mluvJBFZRM<s>0HNL}M
zJYZrkM!=0E*pIDb<fa+;n`YR*)jV5RmvZKVy`lIcb4X4n25R?u;brE3Fe;gidl%sa
zw?!B_KvKzU*{g`3xedOvnz+`&z^4UeOq)j7pbKy*SW&~K2wDBix;{|Uj%7|pGIpWr
zarOZrgralk*(A0&Zz$1{7g9<GMU%4N@;!{rv|DeIJOnIe6SwRqhM93ZUT+C;degIN
zkzfk8&TbDruXb{K{rxI@)&*|XQzX#9!tIvfY6(-@>)##SmVEmrxy*@y82fNLUL}*N
zV8yj^^Xb)&iizmUs6=Q5f76Nm*odi$rTo)x%FFT7@6P{tB8~=Vs>h!@hISWGj2B;x
z`M~RDI+m}4Gh|n$s+ZE$1h=lh)>rlREuC|BJ(!0CA^0KQN)u-HO0Lz-HaDH9>bmE3
zUWo04r?ekowl*K9#jnqM;QT9BT`%hrlz#ciNp9Gd2zb)d&&)K%hkl<6z95EFxblwj
z4mzE1ST2NY?BVShiMtjqje@+(3}5SIUJIGj?%Mw0i+#)Q(@FL)ytZu7>!jVUAnfa|
zF^a?zzq{QDLCE(+ty7jmb;mJ^@y?FLQCMRB0}{J}$?WkkSs$QXv(c@1@OsTAF=UpW
z;L>d0_*D$>zAj^XhS?yt7bf>e0blJGPm7;V*QuYPAcemBnpiic)i(4=2EW4gQ7(T!
zhEN?pnYjix@Po%{xy*nuwAE#+y^`gz7gE8m>LVmYXfC`V=1hFjN66s{`_!!*&E_D1
z74Dq5q0C|snlKy>8{fER1&SoqzBtTpNVcUIS4^9^N`ywnw`aPV7>8SP@6J7IFG7n<
zz0!D+=aZ}oXi3V}A~Z$(@644Z3tzi%@5+>}8$(NSejVXhtyL`*95#FT@w6~I#7@NQ
zBi!(UcDTOOSyw+3P0O-u=N@gpWMA!?_od&=)_<5yLd}kfU4FbpN%|a>EExsf^sLFK
zwUYTo-mocg+SK;%zAO#VwDw@7rdOEDu)k^XpE1pRs}p(IlTd3W^QXM7>aiQp@KP$Y
z`|8?`Qz<A+$FEA$K3xMIK*9{@Nxygbx8v1h6lSP;N7GJG!w+<X;pmJ}DH4iyEDrKC
zk+YvfNYWlzJVF*j!)eYRxXh_j=G44DD0Ka`<>zNI8qo54kjeMql7Q!IdP?-^;U5V7
z_A7YMFu7(q*oK?s7_<6!7!veghu_(k{Z>k##Vcax@xsz<dF1V5lKj@uOa1PY_U|iM
zCY2|L;63Ufe^Y5bvugpA6%2Ww8%*6+sGy<(rqQzGE;G1O+?By6_ccGMlR)$IRG-f0
z4JDkOOi(*S8T~j<LUSF8LoPF4?RDX(_}eAsC+0>OA%->1F-Uec>4GK+8Qi$<;iWop
zbV;}AStH*kK}w`}p809vRm2wO@A#F(yuSc$3xzzL7m9A?(@;?k(=9utYne8*DWwW|
zzqbElD~8fioIB#M_Ycm%6jQR?H#qfMAi*i@V5N`A>x`4M_;f7!YwYVRD)M$KyI#!q
zIS#o`*nE0{T1Lk<#P;Av3>{?hugZcLzRnBtMRXZd^fz<gij=NJGc;>9TCv<o=!sra
zvpWCou_dsFxoRE=B|9t|*n`j61ic!!c(&7#;0&f^aR2bs_988M0klQ)?ybwB#XI5a
z#F3GXUhP*nNe+o{Q#IDx3*AT?eOR6(wA%j2bujE(?7B2!IIlf(ADGXkUqmPusG*Tb
zRRnMt18CC0Ipof{zYe-V=^{W_OvAvFe%-xkb80rGZ%vj#4C%zRgYQD^_r8RNmh_)i
zvZ(cenndsGZnqDYV6Dub<|#oXgf8>Bw?*&%Iu0#9>W#ue#6HbBRi}8{<L~QYmhwY4
zvZ1xRUwH0(VPxTy0C=+4|JCRTf-Gi>bN1*@rmiLQweH`(;wdrIm%S%@;5T!&rLAbJ
z7RI*rW-o6UmBtrx;03~TUq&D>yY{-x^!MLpeyb*dqJ=*-<)F%PD`ME=M4qUQ@$JQ)
zTO{=EpHgUYnRE;~rTj+%RG?NQ4-HCDjOD=k=u;EKp4}<cvuCAB)|B=lA67dF9owRL
zzd=-l8vnLFd>3As_B$q;A@)_ty(Q4i7>%E#BBN<q^3dJ_c|<QlhcxcJSB7cw1JsZ}
z37bw%h8|K2)=v`J%<mQdq*3#pEtI678avUI;w}kaBZ=zQm3c9?b5s)S5?3L%IhH8~
z*&gH*i^b55)UK)CM`-bynC29ebAp*6I6^U2Nm5Hi=q6?<HW%6k?O2<|&~v+ZcrkpR
zBm6=^CAxkz!3JPwpXiF%A=pP!<m{UF8A4rgv|Kk+^pu)l@8XW&Hk(h{2|Z$~S=YqS
zPCFfmB500_!!)5ja+v9Zs8YcY!?%%;x&1QnAZW&m!=@^t*2J-Hp5^-Va1#3?UsLP?
zaK9j=NT9UT1ZocW<?~pw5|l2=l-b&#Y+4o+C>CNj(PD5<MZ(RHHKf;4a;TQ_@q8+T
z>O!U(qJt;{dOnFQ#lMTbfJfa+R2iPk@uOHAqs6yjn;^xsDidczHLqG!Z4JRC5p*)V
zFA>VZb#iXyZ?Yy##Fs^6x5>>zu_O`0dJ@~ze$TJ~;;2fxS_cx)d7)8^ATW)iLMUPc
z;ach?phq=7zzi8(60#KD9VVnDt05&9Rv{Hi6`)8gTrcNTJ|h={`X$0wRCI{z|1q{4
zEbmL)6gT2pY8i0^nJL^jlKop^PfEgMDy4|aSpR+oRH+jjiF=9*eq1#JtkZ_=Afb9|
zmIrk!bPbjW_an48%^xG~X3OVQY9REKR~*97<EY3x?vX|oWV}+vn@fwoiw%h(SN+Np
z<j2qg>do4L&~~2JUZSg8-qBD2K?O`prB!5AFG<vTL-<qfJ9yu_*l7w1TFL5`7=RPH
z5s!i=*g2JZ$!4%<MMCfq-;(`rlHeI1SeC*=GB156n@+5n{{qC$!`?0tKsFAVC?f%A
zqTC8A5YO+26ILl)DMxgS-NklL(RW8ysswQ$HsT-2$j<N?nl9pDi5MI4&Y3wP{ZC7R
z6R%uGP7w)HC$Vqx6t}WHiM45VM2yL}$IP7hmhw8h#;K6Rvuq{4fW}hzd~uYU+MGZ#
zfoa>Y){)qQy#Bw47xyzs&Fc_D4L_(vgHUaZH;E%{uKz*OH2@_yGf-<SW@;pu1Yar5
zn^9{T_SR5f0bi;9fkYX0hoK-0zS8`6qE<Cb#!zrU^aV+C5bmT%?2=l?LStlfL3l(a
z2%M6ET_IH4PYHu%f}owqz|N44jE)ICWrD1TuWob1P4^EVbwLl`bX-*u1!EEO1f9@A
zs!=ITvan#qif0_8#m~iNO@<q`zaNQk1xJMb6coh^^<?Xb5Y<Q)oA52u8Cy9jSM2uK
zqk0FHqd45E;~lZLQ;@r3VIJxL&tT8mCdM|w?@wcZKQgc{bVjbU$`fMqpu1TMmy?F#
zV&OTo1FUS%Iw8h(!%TJ2DD-Ka6Pk;oYF@evYKF#K?Mmp8Fvl-XC3-u3ll==3!;#fO
zX@#0vBQJd(3e&F)6#IUP7QX{4pMfG%n~g}Xz|2eVR2kH4UzmoVsS#Ly6-T4`d)Yp)
zIBQsBGGi~kYYMvoIHok;Mcy8)<CIo?h<hXDgW{;(ixoqG_n3Ia=uUdXZ3*<o(J%o$
zhjie{+uzrFAA^GvK9IDS%281pDv|6QbwC$Vnx~WCb?q)$Va7SD4YJ6KpS}vcfrRMw
z^`~FHG?E1~@y<zXctMH$zTL{?$9x37dOn4?{;5~^r#eT<pq=*Jap(ZV<2@k(CcSj@
zeHCjeg$AaIFx{W$)<Qw*JTD6b_0sp1bkpbgd&Jn;Sh+ePLz>Zid&}47%Sc7Hgcz0B
zD;3uxE}HZ?5xcmPL_8mKt9Ta@GIrP(hNEN9pJ;0P@={w1NuZC(sG)w~nYpPWO@-Q;
zEZj;JTm~hQ{o7E<WuXIApbGg{a`Pty{nZ9k!Exft|0}eF38zp6BT~Twb1UDF;K89!
zj=fHj_-Z8?l?a<91e+<w!>P@^NXdh>k<4)BsQh*)j6kwFmH8y2C6@9rymWIUk>vjj
zK?xy#1u+#XJHr5U3F4kQE;osNN$4pd2nHr6{3#?!`@&6#=!)Ni@0-N#!XlK=Q82C#
zYc3@xTPP-hR)FmJl`3NOmaJYeb|{b~`A;SV&aDg~2^2Xh(e{Q%(BdTjTc{O^oK?Jj
zYgE85o`+t+)YFA;BrQ$~S>k92nCMlSiMh_M^d<?Q$`I{P$VI+M%@<HBT>Mw?m)Rp{
zhwil~2)0``HZ%v>^3!!u3FxJOU!DS0+_zKFG*}QTRw)IFRLvB`2Tf9%7m&iVDvd}M
zGK41Gr;u5Se<~uLPpkM|&dA)Z+YUjmAz0y}4qUa;HPIK?!5i@D)8IaKQxg4xou^%S
zSnQI1r2@&~04+Wgo24fR#!gQ{6j%?#$_%l2nw4TC3rMsSFd2P;5G#kOAz0EDx1P@M
z$1hWn1muay!rRhD*}^h1+5{ZevG#~(*s|(K?6a_p8kJRIt7(<cC?W?|(64+T_RgDi
zlf)i^RNI1;DPD43xE2aQz~uztOLXvE&?X5Jx57JTw8~>UWYIgw$Eq<O19;q$kws77
z@-h|QqR6nrpMt*wCvsAV$rz;xYsC=MJioiM`o)#32sgQoNboDk<jwrzX$UH5kcgKX
zS=g~wkl0$V6SXR*keO-zs}VyBl4pm)2dI+gH3fMm(&8JjSqm+8;C>VYE%X~5SsoIB
zb1DxYfhfl;e1cwJ9pLgI=Iz3t&dhOObtBXaHDfDQoJ5I!We`FeAkWmSv?rfQZC(sf
zgkt;+)|w>m*bV8S1f*^JWjolF*kfon0%?`ltfhi9A{41;)NCvk=E}h&vJr9?<v<@L
z2If@S!Gj6}bnVIr@^Df!Gz~o_qD%8Xu{Zf%RFnhx(IRYUc@a;DA;O(NDaDZLnbbT3
z5edkdwC4KQL4G3z<!D*Td+|c|G1lYaBoqi~#u7YJHN%Ou2%$1aAJ(xVsGqq0Qiu(e
zCExVs53v!B-D1cBJeC-~ORXedI0K<oQo*|1W<0jsJ`sw>@SLX43ypxHe+ayL0^$^0
zRb9!C)e2=o_-T)3We54LLm~??+&L;ocwW(r<)R|DGuP^b@RPzZP5L_$I|8oOT7K}0
zObj~2OW=iK3pN{3_@Chk3qs3RUL2CNQ-B8c+Z5wz4)LV=H7w{$D%PnvyVhh9TMfGo
zxe@GL2YfX;<)E+&n$$Qd4*U>Opa%Ui6pY|HpIR%C<H>R+qp4HdUFZ2JSR5C!AqxWz
z>&rCQJBa=U=$DG$j%UCzOoX>32rG~H=fxn!gJu)Bkz7dMEdy2AX^`S+*PM-IZh~&L
zHbrE?wVH*$L|G0B{)i1Fu*D~w<y(&m??C}$6#){W-wuiE5xW{dNzRij4#NR~x`=~`
zHDe2oOQRy#LR&FwvAGV39*8|cF}{&(FxA_hl?BxZkaL!KRv?YVO+&5VYMuCQ;#<?y
z&LX0dJaDexJfri%Zxp0EyXNdwW~sm(bDN5YG~*>kBD>ioIwCeS8=P{Cmwo5Ma)mrv
zqvmWSvrg~@yFLlgpin}^-^AYG2h2vqxmP1zlpX6<BDSQZydN)udMGUm>gV98e%VnK
zj?JUXkPtL@F_R3`l-9G9#Sld@*v_t6;g}9xfrQGYwsTVxXiBy$4Kc*ju9-cr$-;;$
zTunjHIB2yV9@*yL`H<zGpv6}(#qQW)A(K%Kykn5<6er2fp(_H1$?ZlQ04<*YS=lX{
zB&#_AI>02~F`58vva=;XN+iSrs=tZ1Un~w7LZRclo!2B;jS0{ZruZG&1n90^z@%fd
zCqM~I>YYgwpf<bENwR-HT&Cn5$q5jY4<;R>(Pxs73CKzkfs#QM>`^NK$^HSQF{Lg2
zSqowMaD<KEg||ew8Kw{I_6%%3WiS2^rVpw0Gvd`08|QG>zH!n4zK$kzwQ^JrC105>
z>F5GwAZLm(bOKmSN>e+IP?Th_l1tek+B~{43H_SXZj{56xAY_~MnbrOTHq?2OTs`9
z1TLA4LH`;43<N;|iNp_)yoQ|zRiPPN)1iOTD!wfUf?p}wq;$>x+aVDIL9eK+p6V)Y
z%7h@dvcGA1^jWYRAgF*j#S(rc1v3Ic-ncd=L%0(JK}K4Ft)b}QuR##xbFuu3k}I+6
zAV>ym;ut!46)yk;L1=uC1|1uAbs)$91R40*OyXw2jG!8$<Y#g`r)q-TcWf7BgdYz?
zkYnzqsoK{2u$II8AcD$6%`5W{Xm+M8Bv9j^8CW<aY68?XyUDiRV*;dxMN#}FK)W?m
z?dshoK-yR=h5o;w^C2sf?OkjUTONL<V{O8f_;f%!B`X0TRmc#JGHJ&jNj=r0tHSz&
zGgibcl#`~O@?@ESRY1L^*ulj#oyCPhCKv|7(k`CNHZ$kIzi_yl)kE?zWT%4#snp-Y
z8o)g8hTDI_nfGk@*^~S{m@E~3ilmuo7q@q%o8yE6c4a3HePC;+t0f{tWX>m;8prQR
zJvE@Kk%*iRf}@S{-{ez%EHgOJaCdUXjxUy{F0K@YQAFN6lQ(Odl5=1*{sR<%nC)Y4
ziz%tpOJi-I0MvDhlM;Bdm*;5lszHGWP(aJiK3qO<@&tZ_z1P|d@_O3|{{C2MN;~^y
zQWog*6!baC)VjYs=LPRGkcYrxY5UpFln=DT2SFV1voIiMPhIcEG8aROLA~AB$>-~E
zsmuGr`qL&@oMvkGxks+NsM_+BKfy+)$-eS=cKzDw(3lBUZ|y_Zs>>w=UM5#m2_s>4
zkXv^0O!MQk18zK*s-@A@N$3<<WCiZJ{nE3^mqXYMb_!5zd<o0wQkHyV=a!JpnNDHs
z2FHm}SCbS6v#_MJfW>crT&B@!B(xsrt#H?Z?|o}dsbM>-iw_9dAPIgiCC9hQ|0geg
zTcllsYReRi43!7SEJITa_#NhEPQ6yAI)yV%sKMVBxC}-)&(!mKIe13fw9<n|or5fP
zfL(R{9K80K=a<UwQN>A8s2<WfABQ|_NoL*lg6lr^EDKmasC}kk`OL%DH>FR=rSpAo
zY1?XZTncD1;CFgJBc70uiA@C!7Jvrn3AyL7&-=>BKHjXAU}UH$tKpGvw4&_#mup2k
zxPS#7P>i4Gs;+h6D}2h1tvh5mK^x+z^MZ=s9ng!Cgz7!$4jFfbe_6qAyKG2)H!-S&
z2VnA0GL*(P_F4Usg>mu_Uk4_%iK8-Ovhzh@+vs$2YJ%OkkV~41p14koPN*alIL6p{
z+v#4!5=Sh*$S&8SYrvL;N>Yl28()3!s9<K$TGlF<HRMzCE05}rR3!G9i$kyljc-wm
z=jHBj;j8~Fy;3b$hfjvd!@c^W@NvE{`S#0hmF06MxMevnNR587D^s4+AgTw!ZF%lj
z?poaT-Nn0Wg4Rz+u)l1jKN1;#!(7(caa_Ws{B1UT^{xZCpYQyU;IZWB1z}v~i*FXo
z=TAtuv{WiJx?snfGg5i{0GK>H63p;yalv)KQmddPN)z@SOzXynNQV`*`|eZ!vBqbD
zzA3c$n;s9`ey!7Y&$PPVLG)ETgdcJFd6@9C&)d9SFzpO9IT1-HRsSEo5m}F~wP!!L
z+t<PDbD`7h<k@1c&`DkjsWIYk--aIp4u>pIYgo3S;QJhd%IC-??2zynEDrRTugG-H
z6&_bCUz?a(xP(1fO=Dak!Jf}Y^r9MH7~I>0AN?rzW7@b@)ZZq}j=1UWR;Fp%?N{hQ
z*byNYIKf-~9{C4rf9*fL+$Z5?;ZpVjHBI^)I1<nV7C~LB7j^OY8QJO&>9Yh%btlx4
z5SkBtD(5e+bZFT?)hWCBoo}<?K^!k0?BfXSGv78U@%I!IZ+h)5Txd13%@VVM?Fy-8
z<PWpQY1gWhW&HnI9%p9HvV--9_GPMP*LQ{e)@?Vt)t=K5lg8OYv+n61!=VW~xwiHS
z_K2NEF&3;-c+~gUu%*H1Uo4re-+r9P(i&G5Io(tKdG3yyHeHK^l&7?#`R!AF9{G{=
zpYMvv*?+#}+NFQ8P0gHH4sd$r)R4Y@6x&}FVdnC`-+98`Z&42??36OMyYa6d)Hj2t
z#y2Ka*Q=@U#Xoh|`#l=Q&!y|-k`1%|Hm|QucdCO}@`++>arI5)E{%az5gV3`J8yJf
zzxU>ecT+o~-;cX%@^k%5jr&(7-WW}77>^LH7ccqyJTk*#)1Aj-f<=Bo*si%hR>%9B
zjE5n_-~Qod>F+w`x0`>+3g-B~?HE~YyTSAilJtk0akYue;TM09zOpL!*Y}^OtzeA@
zFp`7c<wmt%=2(8Z%O7z^``%dB*_sUYj7Kr5?!J8gp)Uh=c^g(tFi$nOx5IEG3;(Ah
zZ#<OcV0c((Zp$LSQi}=Z`hL0}f0mgy+?3({LE<xZUv69E7d1E@GRf{`)1Ext7oMBs
z^+yB#<EQW3du{b2e*BB1_S9)fB=60?R^cb@+@05?IlXG<gg9wGmroB)(cOMH=1z#K
zzq!6E=fxrq^)(YnUww5y`YY4j`+oe<skYRntKjLPRCT8bq(>@sZNJ}`xeu29L3(t!
z>)Vy5ZZFhVPaqYX`BK{jNF#UtAk`fH_O0-t+mhuO6N*nWZpds}5?&xdO&-rF*vbLd
zu9w>+dc-W8u<wPv+NR|@gzkMhe~_jG6kM+&kQPrM>F&)nDc{lO-Dmp;Njl)%_456R
z9?^f0E(8^rMC|DI{`fDFSl+qo#fR!VqL=>R6r^ury5pDki}*jBI%?+x?Aeul@mJVH
zrV`Y2_`|m=KSHKwyG%^jz_j`F$j#_0AIJ_9d*xu;!`EIz@dfm(i3vYn{_YHYUl{LA
z!$eYLaq|3&*G}oxdQn#=kfxbrWM&G(Gv0VPCc<g?38&?9-22y-g*tjsr4whveQ0g2
z?c-Z72S4lHu0N~z2a{_1_Lg&9ghAAu@w9-<3^LojgL(V&Bd^tU<A*Oo=gqB^{im-)
zKAb?h5qfS{q2s%dk4JOIV{}fX+un$${WWy2+dIeOG3kxz^kT2b(JZN+M;a~)W9fuN
z$mcgdE4o_>se=z4y>17O$6eAX)0xFOQKM?IJ$|E)`!Wqv$AcjIQ|*J!nJrc6ltH{h
z@iyyUe81xOsL?F>;FwkN2p$@!ft``>)Ozbyv|Qv2V}2=>k>lZuw7%T6cxa^TIkN0(
z>3|<VB@?&~O<leHYppH)Ll$WjW~(JbhA0`#erfQr(;&uh$x5!GV(A<z%GIhNDVKW|
zmk(EZI&r<4oSsd`lEE8Kwv?}bb-$wNedl^B%3y-ViUAJ34&oN{pag!~-n=`a{3XxQ
z;GyWc%zkj?Q|GPX9jTP?k8&P<8ua<#TPL-nU4C_Mo%SeBZHE`9*)^m$Wm&~O&3>0O
zYIbyA_@az&19s5=6nHUb&$5bg=sH3raQCS9v~1ZO7J8LKE37<w?I^EW3t2!WTJH|S
z;h~UKLH8U-B`2SAyXpJy?Tv92zY+?rB&nq%1f2>NZqs9j-V9xo3Pwb|2swFBx^{FI
zYS)lZ7qrqW_Ly8^7*+D7|Dv^jjH7kB{rIgn=W^1$sP}j8ACm0R{-41kFxYngibQyv
zkA9gm%NHJvU@p5-7k7oI8&2@N;enO7M3ud|PummhvP98gg5}jykD|UkzMm@>Y%PzT
zz>g;ud%Be-MwPze)AsCh)ADktgBy1+%;f61CsFMk_a!8IY#RR^+_AU($Kz~2sh+vZ
ze)Z%!TuIM@8GeKr?r6k*djD$Ht4Z`*KsO|zM^dn;SN3&Y6&|OCU*D1Y8SDiKLH(Qi
zSLn}gD{_XP?CL7zpPQRE0chr5qNm(`Mq9CW;ZWh33AWV6b3ZM9WhwNG6o<9e${1!&
z02CXK><=A$z!`3Rk+8vJLZbPVzHiNiW~%Lq>m%z%6n#zTMkEBkLV#aO-v4&nP)>aC
z>W<8ECW|3P{FECt`ObSy-w?U9CJufnKw^6UV!~JbpNH+Z8!7@|Nudx=7CvA2AZGc@
z_J?YU?MP4nQ{B+{*KquA%jl6T$a0EwE#-}p11zJ@mW)OXN{jc;14h=s=wxJ!d%Ks<
z@cpCi@2<lpngKg{YY(l)FmK>!qh9F*`zP%o-0X`#s`HyJR1@r=#%`3_Zy8<oAXFm!
z+5GNGzVIGYM_^fVdzMufJ|9SawY#AWaxm{y8a2bgDPcu^=L};)`z;_eKjryA0?n{u
z%eeBZ`P;aoy}!I%Af*tTgG|Kzjl|%JzJKwVl07{UGXMyGW<}txOq~D{rpR{}4?p@n
z8d_t~4xo3_lj%vYzTF#*O@#^#oQsS{zLvj#bYPnBnMNq%$L*inQyI!tI|+}P1V8Dx
z3ZD})(0L2LL}lowT4ova)NM%n19ph3@Ji~g*e`nb6iJZpF}Eh>0)Hg}#8bo5=d^@3
z32P|m0$4A1t$O=ejhOEq_z5XQ{ElSx$A~zMZf-ka4KATTGEHIH;Q2!P#MOum{hJJf
zT}LXyle)`%SzE<W3P=dqHmyDL=<tt5UVt{TfWKg2l-_;$NX5RS?h^MuID^qG8ZE;|
zgipZkAodexR8u~zSnqFN2W;Wb1TYL*bPRg_fO{%;ov=+dqc0*M2T;58hJ4TF6M6sg
ze|pp`y&XRZD#LDi!nfj9ANdzK(u?pykY<1CiTVV-+6l282nkUfGxv7<ED%A8yZYl$
z|H-3f^u;8kPZ)+N(_@#E7Y{Rl<kToN(eiiQX6r1qQwXIJRyP+P{Ld$K(D#3!w<&|}
z|NAKcKQu>5;F>cY#nH0!YZ}JtZ}54ZmVM!WKKtXXn-@QfF!yI|7emvC<qDtDetlZ_
zzn?SOlmGn;37^p(GOY0M55LC^wCr>L@_XD%8~to)-g5bWhK|C}jwOxa;n^B4E?^3H
za%C74a)wFZtGF6qB>0br2K6T&8C-&L6KuT%Q2p^UTGi{S#`*N6B;qeVuuCa%6}Bhx
zs=-96#3J9dj4oWE;gSeEO$eUVal@Wq1Zd9P2Nr{#aA>w9$j(Uim`)F8?F5%P8FtHI
ziSW0!L$m*IJtNg~O=Him%~ib5z!@G&jMCe)xy4b}Heey32{cV+IDX&o_2t0BX!|;l
z1)by!gVIs?@D80JE&4L>iiD8J6~4rlh2ka5BZ%8_kvRB95Mzu^##u&R7x@`8P-}C7
z_+S$YI`|NDsG?-!Y3-qpp+69<h9CE>{$$5(Dg2l4w`KF^(%*Ip&WH_-M~sD3&hR18
zDGvvU55Fn&%z8Png1EWC@6t1#bkVA|BoOCPjlhkF8_xP4T-lz8|G{0INb4S0zJW*8
zK^D-GZgeurGWxAZ#l?h*`^5*NA_x^52o+yXZC}<UQW2us>fC+Y{-{$_EE!A#zun4s
zl0d5xQrmyP+Jc%Igy^SnW|{5yL)hlToVJ?Q6#guUfgTRxkAWDS>^^NBO|Kb=hef{v
z-a7fUY!62*Q9GO!3>y&ECmEmCUivS$rL!#kpA)XJ75;`9(O(XKRRe@9&E%MQ{t@!z
z(>`u`U&#vC^zh70enNP+chJI^;gm;nF?$1lBn*@R?f(V94}MSyq0he@4dW^<5w;gt
z6Z{E@Gr$--O~k_u9yXkZ>B5heGn|TPE=$5$OxR0co9iddYo^08!@IuG=>$u)aQJ}~
zT1{+$PafRHpU~%tN}vn!U$IVAv^q2BIY!!$qipRRu_hcTdm}98Yxpe#+lSx@HbBMT
zJaT)@YIca0!55Ho8|K%H_`D<`1Hfq*mrG0ljshZnv&AsEE-^TI8-DI0pn%@YEQ#=a
ziJ=BP*&!XB(Eh#~nlD%9ZQ_Q`@A>0;LyT&&M;|fZ%#8bXW&&mK=mzit$O&8$ZYI;y
zNT)}0=fb9fXA6eOXU_1>q|nGBk(-3HE@o(U)Kt{Fd{+DCBNc6Ne8NBGlQ_d~)$v)R
zjC;wnmgEL7WX|bGZVasTO#{l{;W^y{43Xp9&ZB{!)G`nse5TPo;7jad_*)DawQaPP
z77-O;)y#{Q(Yg;K=+6~IH2Ui8zir#meKm=}s|66@&{Mfd?V}g=ve&k#Pak}CORcDy
zSda9{oOdyQtK>X?O&fjHNN51H7^7^e<?UXDiWPHi!2%Ffh9{rba;qNi1OwI+k*4k=
zZPe$@raofXatX)OyQD^;e<1q}Aqbv_*@M$02A_@kulJeo;ZO2(Yg&RM{#G7^oC}4(
z%JmLTY5&X`w%S|0X*gb34>9hBYI}^s;M?M@O^`%5c!&=sf0KVPc5EL%rj5>g7_)sH
zm;CPjXWELlZKXZY+VmwPBt0VCQ>^^^?Sl=!VK=?AUdL7NYRB_o7k>%mj?VwfQa&h#
z*r5_XA-Ho?TD2iO3=#(zbympt?Ab7S&U(2_FcH@P$DBHtT{R5J#_o<y+znrTyoXRl
z$k;_0B+LDT-$%F>%p*3wg=sfu`0k495UaZ`UJ;EfN{ky$ogo8>zy<d-;uPj&wpli7
zWQrSG@XOSQF!!`Vp{MCl|J>0hCNQKzsPOcRbWcwh7%f#gBJ#$ZF$b*^S5X3~l?DF|
zO}${u$JZv(R%Erk7$NME`g6e5e$03OZu32^NWDR$>UyZQ-yM%VQ1m}2HJ>nG{{YQC
zD+@L(A9hauk!WEQN2TD#uhFG#Ta_t;lGbCeD-wfU$49%pq=R)|w2r<#Cbjs>kI6}6
zA=-m7c=7n?rufm3qb@CHm0Q{WWV`0R(5`74r#-?M#vhILdzt@+Cj|1T5%$7D8%s5p
z9?^2TE43?l{jQ1`>TFbx%=c$2IK&ui7zPx3(NT5Fm+L8<JNmX|Xvj<9w)4EAim%!C
z{8nVI-ie9)tNWw4;WlivYft3x(ZnsZ>E13!)hp>(os;@?k-Nyn=G3&L{SF;%tgf2W
ze(B1y#AY?zHZN}7824?{+pCIyhYnTQvHO*Of9d2#vy@NY67BiaG|OmL*5kM<*ovU&
z54lVCBoeVeo1?N223GLu*ju&biR;1tq3g@zV*b8|^HGv$Bq`F&v?)>{q;-s>O$}O6
z4MK=Ety9e~Nl0cY32msP9cf=CLPHdjq;=4nn)artX{K48`;O1|_x(Mu=lOT$+;h)<
z&%O8D^9Boz<vzajcqM1+r@hHYRPMhEZXA_^>qW6HKDeA8<B<r~r>babq0IOup#s;D
zucPzzNwf7vHm4WlPlgAmS=Y(3OoG+BnZ2KelQ8G;If$4;$<lDv@p$VYD(V6`o=M!-
zC1u)YpfNJ-RF3DH>9j9I*WJYr$$|r`JcyUQ*YyULMgBq#6a5Nua97mF$Wgb|J3-c}
zxkQ#-Z*_pJ?t>SN{(A499BDecbwo2-=e9eVF8&N4mhY2gdzv4Z-IJ;xz&Tf5Nnd@7
z#OSuql9B3`;vKMpw~9R~`gEg<4>)gHY3!+Z&pOl7!83-PHhlN0^NDD&buxI+Xyiqu
zm0bRrTFdXYE(!k8dbi_On};qd<_B15z$&A$gx9WoW-`gjfHtx%&+kUQV$|>ZwplAu
z;Ye+&yp4{^+nt?ST-P{->BH1s*%o)B&BKy4@B=*X1p(Q62@mCO?<UkGx`ZV7q#6^g
zKa@-wcJAX}+I1mC9oKe1;*$MaIrfIkv5*U;LBDU^^%{#SN#Lvv1euRS)n%y|!O=33
zrl?D+wGSctMEI#Z$wJHVuqM3R1o-+c;Z<5Ed>)!<>zC67f9|+#p#y5#LEEgOJLyN~
zYxR(#C2JUL4foB_&g(1oB#7bHc99BDf}n2=g0xunEKj~D)k5#qVRhKc1N_N#iL{=d
zKm3nr>0x44<WS-@8kAPg4ebztmN^pR4pbv{*ikdVilUrfK2H-k*Pk7=0vnJ)M0Y!4
z+JkWI9|^EPsqo4+gIVt|CN;h}@;`kWoS#t_&+J*;xe)5W>%o3{)~TsUqo=p8qF&x%
zG`~fj!dg^tR!T{Lo@7RBpThwE=G-6FPoL%CzD&=B{{rK2m{&-a8YpLvMf*c-&%@_b
z-0hku$1b*^o=mH;;Z3}9=KuN!(T36vyc@-dP5@c=L5WMck`WrDJ8uS<FYUUc|1pi2
z-F0sOG6(wEV)logxv-~6p;?VYB*tNUKW{7&3o5pcQ#h*uRl8xT+{{F(MLB)iPxGvC
z$!0FZjXG?O#%N;ZBk*Pv?4d=YH=1cNDKF+FLuYwsUk$!TFiVvp`0}$hI54{`n4RVZ
zW}mv-aL>66af}orSQNqe8N(yi)7vRetqC`P=+HoP^_!65TLu-x3{&69&nlMu??>?B
zH4P-%eTb#~P0QSBVbxC%cqvjy&C)&im-Q*cp?yi12L+~8&nDdB&4d#3Ie9vu+X+x4
zv+zWk+o^SLP}Ji$1LgGkpPBNA&*<%3n$zFuCba7Lhc*i@pF4GXaE#}5YjFOJI*uuJ
zWNieJzKo`&aoG0xoaVEOSe3hm=F7o<BCmh{%izq~=W_DS%CL-#f6wQF|Ac=3{`Zh0
zvd`f7oK<9TjR(AefwZMBY`{$wps?Fsmo_Ggbc!{Ej@nTePl#oT(frF+<?a4U`AH&8
zJuTtsFs>Gzs~Ewr;6{X{v9<zwGSRfW-gW!)Inrl$u(-8_6IsHtJbHUrefzwr0|f|q
zT9W4}<#v2oF2=gWmi9x{d>I=*?lmB86F1cMag;$(Esn}`4OV$<$M=5mh!fclZ&Ai7
zc8J7&!a)H)y5+}Two6C%>`&n2opE4=)yEr{i^}Pw8kcM0shv$Cu&y^|$goxHCtk0%
zAzizZLLBJnQGvoZ{(qC!usi)Xs`Z6ykGS)T{YSBsHYbSn5-iqMROS(a-tXre>oXTv
zVYJ-*nBFXqD3q;)j8eUBR_h2C9r5G~{e8yaOsG*)lGm4O<XvJ*BHo>`KEq!4alIsO
zEZ5Cj-<A|Lx0BTd@)U`xMOY$<)pu8yk%c7MlH`URR3S`G9LVLRuojm&Cq78A5C~E(
zX4#v^h#=BFa3Zvu+J>%Qd(n$u)?~^;Smt-d^kT}vQh=qlsnxG9v*&xidd#uTX&uFi
zC>RZCiPLDhcA{4TPhFV!J)JZ7`29avktN{@uvQJaPhx+(QYvvi|F&p*in}IVYaxI{
ztz(sktFbEY|7M_`{ey^!daur<lz<?+fj*ene<SY>@ghrKm{@!6A(|Tpc#W1}U(c!h
z`7Vd)$Y5kO#>1PnIk1UkL{9bPGBNv-MSHzK)+_N=n?9K2b#p>ncx!77N1FrQX-I%J
z1Qz!=r=z4<+-qsJq+{?oh{S*bRAyWH*4vJz+v~w!90ihf3FRzwmLtIkX~mB|rq61d
z4g?7d=zI`m!TPmJJDUALPsp<XuSg|8YlJqPdSuvbi*t99L{%twLkcF&yWLNzwMA`j
zu_Zy=qdE(r_b55ak7Zt6%wavx;WQILqcNDAhD)61z5Dsc4!iJ^X&{M(XU6X(9QV_R
zE-2C!b}``tJb=+HssDaUF5-4dE=CACb}g_R#3;O&%Q^hKii2nb_f-o7+OlS<5Aio2
zKEfXmgKf+LIyXX`{%s38*E=E(2844MUFV(t?2#N?Qfw|pKrvs=wgtxtHj5-$S3%3~
zD`@8+l0tGZ^9Xpknvw}3+WLQSVGPm>7+C^PQwq;*?9VtFlEN{5{)8hf*7(Cpt2V2n
z#)hwa_z>S)4BofGa}OqRh@R@v*EVkyJ`;l@8dzY{&V+X*R0~Vj+oCVxzXI!;Jh>RD
zX)<e*g&wgb{U*6@T#%U?IlYXbJEz8KI$_MB2$Dh6aMobK&y<qTgLRx$#Qppi?hbqf
z1Hjc)ZF)7jJ{EPy;%SA*fhmz?g&Bi|5>8IHXGG4)urz!Jm|2Xlmr5^jH86FV=)wCO
zb)qBx%Q@k^8{aWpb7mu)gf=Napvd(#&K~7)k0f@1Vp^hJ!JE5DNn^KMw<%eMwcAfT
zmMDFhQu!B64QCtCmOoj-=i;p_ZiyqNeETrnf9D1TW`Y6^&vUXAP2pupdy%Y}l=460
z^7ar^X+x9KBA*yTvtJh}y6n@)U);~=iTUK`hv2Q#cW{ZSC@Oh_5>a}>r%sA_&Ux9<
zW4=^f_Okim`Mp%q$lNq+>VWl)Q$Bh`ai`CW0Y8s2W7gb!hAj<ZD8kf}IY_QMnuJ--
zJ`8kh2XrhCeVHp)q=`p7cY2kkY8yTKJiyZ-t%fM^9(m$}_n08xZf`ycbhR8ub^6up
zDwuUMy-<Hl8&OKrZf<gDFr;(C=FfM3<?_(tuLA=hwT1~edrZ8}lWUi1R>dA)KhX`L
z4Ee{;kZi}a@jLKIVWkt&w|f0YaQ||C*)4v$8DGagXVu`vai?(Y*f>?;_HuFGlvbDl
zJD7k8om9I|Ech$-zIuE%g&3`oWe~Bed0vy(oJ8#Ej%<MT*=CN93U65)Zu$@6TCOkW
zbE!Ynu85lnpVwr57*SZq3`z+;JrO48x*z>7Mq&NYYy>gF5Tzep(X65!5s#$VC*>JN
z(wr!rzb*f=wAPCfA`;H%bHZEH{l5%wZP+jx_M)RvPg0k`32|>S+9%w+f)|!r`(<D(
zsm_zaRD0Kcub#>C*(^Q)@6W-DzI~nH6me8_p?UwNcWFy_leU?yqrwuiQ&ZM|Wo%gU
zHd4?WuLy;wY5MmLWNSy5lyPfk({oW5{^T32L+d7{P$e#323921MN={MY&ARcjIMc4
z;+I!#v#K!yvFUsQ>oD+&8)%>4lpc{O$%`w@9VXP((IX{!KU^oY0kopo`7R%U99ATb
z4rIqN%0T(uYHaJ!jWuE)1Hrhz^K5uvVqBykk0EWM1He1X{6G45!5-^KHLSTf!W(xZ
z&SQKd>niB&TSb<?rq`zcJ_<7DPTnB~#Gu9913tjM>=#Km%0opX1AFj&11VOSep9I7
z%->gl+}vhfcOG^769LMea_6I>DN1W1Ox}`oBJUb9?$zTzFLrx9?hqpwwa<;)DABl<
zoSq`|{CyM(Kc1N9Enps?h_f&YaLK7(#^<nJTxs~!tV$c(${<d#69{!+Z@5*|^i0J<
zbW=Q79_%v_DtL$5^sX-sYvH_b>KsB&&lMi|l{OQ8Z~>*Id4q6;%2Yjp>ec~f?xmep
zm2kg~_PK!B$-8Rq<pg!D5wl(wi})(qKO=vk4Q_h=4Rk-(al>sBo3{y^JpAV{;=%SX
z#W!=?uwLCY;=dttP3Nv=`x|DA@2IHiT<MR3q4}?}>@q8_?rIu*>GN48=<C;pX4xBc
zVMNl@%$?aUb2xHT9D^Qxu^r7tfxXZgb^75W6eP_HQf;4qR$BR@^eu^?{LR`DR=g@P
z%vXWCkd2xE_W6>$4)qDAzBco!+{IXt&O2~4a|G*^R+;s8F4wR5%?4{Cdb<06yfjy3
zO`$TS1n;q4Jr#)F9dMj|Du-=-Un9lKRrkN$Rcl_8myH!!)Mp9C%E@&*&!gb&0q792
zxd>0eZ(=V=h^A*pn)D8cMHeQtNs$lHr3u}G@Uk!@X)HUk7E-!V_o4(B9*pxL3z(=W
z;iP}bYN*_5o^c^Y;E|Y@2b3#APLB;)!JfAA`qGgH=DTPvdM&_;2A9W2hJxk=63Q89
zAJ6DWK~$oW=7bi)zhE0ZY&Gl_k%E%w5!C@uz5YjtAnA(;cS<pD$fm=7mmF49butV-
z2Fq5#&}n)8m(I?}!E$e}8;q_=!;2|s($9AaYf?w`xhvRCVAuXwLPGoIdI)dyj-$FY
zW!#)tLHE7SB^!iIkNH#GJi!KIOB59|1|MP;o%nzz)mhsG*-4QF&WUb2CZrI4dAsP9
zH_U)e%p)6z@AiR{LW$*mjcAhB!2R?+*O3?(=+wu^H%&boN2iL_aXz!ew#-tK(_CdC
zh3>nsS2o)2PW69NrJ1*X10A<I;yB0alfX|hVnMl8iR37Jf^X2dD`Y`<qLKY~@B7S;
z5H?dM2sXs3%VYs4hz%;So0*$Z_fKt%k%u~9J$x^bia4%_`VeT_YE_NKxI?P(yDr>7
zqgYvo;q@&Bq}6)eb9=#1{iU;WFV!awzdr6H9TC_v4zI>b!nV_UUQAW5PleL8>DHQb
zU)YLXsxD=RUWjUF)-u+%iV+-04AcAhA|j@4*C{S6?wB4`XvM(XA&PELD}8n@QGG(?
z^;uo1h`4<VGxn^797g6&fHe*5HDiuw(^2BSBk@x3rhnWAM>Q%LC^Xl9XS}&@K>9|V
z_j1ZHGDe*==Yj8@Vi`EYIa*AQ9Q$iX)U!7@&*YBWivkQ+DWY;U^0hivG~79CCK`L*
zH**UBHnMld)J3S`mrW&io(y5F6SwtY`?bi{+kB`b{pM7f`{2~Xow1TI(C0(qPNh6F
zHa$nTmkBzT<1NUGuIvVo&-YSkf;Zr%0X!EfjS-xrpoRt%407nzoBDpzMr%5dE6mnl
zz2HN;<>M~Ytkx;v<*0G1)yAng_JT@JZnwte=I6U%6yV+lpfDf{4pAm#p>~6ZAU*N?
zNgA!{kXvMSpQ0+_YJzaa%#Pzz6AVbtV2YG`+tIYU1GW6QSGwu7XaQAjidNxY9xc8#
zIAxmyRwwH=PQyC9=tOZdt*oN9{~(ycy}t}iyFXC-50AmkszyhtfO|upB?YGr+a%#J
zw_}d2<ZCV}F8^0RnUcJj_2PAOJefx~ny6_Wo45?jtc;%4JV8Ywtzajc+&hsyHB<VP
zz^?VJl|?$MLN`F9&1l9F&EL{EQ=PPOab(smu4j?H>JQZUUf=0iRYp^`4X|!R=8)$$
z3&Qss712ZQ{7XOnm2{XsJ&gD(#=umNVURAg_<F~065+)>H!!LCHM?wK9CD~w8D-&b
z+iSswxSgjvO~K`uL`$SH1WI;}QAy0{=*Ze5i5K_Oyu=V93NMs}9YeGN7Nw)2Gb>L-
z%~fdy&choV<(_O{@YRv8_#@21r9oD$GAv0k)KR>%wf}Ood3^9G)Z|Q{Xvx4pUU7a8
zcpEO!_zfw^n|j@+KT=96ebg*$qZ{k1e#b}E(8Bb(D<Ya_e?{B7%`S>VRcsH!fb(++
z@A-9*&p+I7YA2^keeh{8i8M7e+uwX9;#dE>L9U)>m-Kq#R|Z`O4(}yyUeKV2xwY=|
zK*_NCI->+8aSa(WIrH;{+%Rs#KHtS$KMR^aXo&EAvh2>jac~kZaqK)E9F+Gow2qv{
z5;>&FRyKntY-C2x-_4E<iL}n@uLLXv%pJ7X;DW+ii7gdMSmM)*1>oBIl%jES&d7Ws
zvvT&Cb>XYo3X6t6sFVMLIx9x7r?X+%r~xUjsJTsGKjiLSQ;*_@_^!A=+iy`9xIjq^
z3|{!hHGex%@$b720JoL1spNWN#*46@`}^jN^cT2neg9Utum>vMM#rz_4bl#F4Up3p
zGg!haNYYTBN@~gI;#(M>QxFkcNl3h%-AXsG9xJ2!t%LGJ_7^s9^6YQ>(mc9e)UYt|
zoRjMx5%@tQhSBa<$!JW5X(U+?n^c(D5b-;8d^~U1DRd2uSq)1-uvYhv1T^OB_U25)
zT|r>I5?@5N*KP;vnQ3nAd^JBQ<4tLp{=u)>s-)NN>B3`^Xwn^M5N}|9aMAbNVlDM(
zlICq`Ub%W{^-xNWj~{E4_^{z*-qb+G$U%mcquG!6*LBV#P13w3b=qVQ>-sVYgA01{
zta*(e$EkSxOptsFJFA*BSi{8JI&bag=cp5NNvUrU>{44I>kUIeQNpYHh&qF7{c0Xv
zI^4CJLaH0;kOohShKTtEUU^@#bK=t@8%qPLxg%cTY}2va-^H#xIHS4r?1G;>OGWd6
z6*bF%{m9pgC~-Q)alEs&b9kA_?cl_A%AEdYZgdA|@hqXy)vL}hvS~bk^$Pjif@mya
zysQ5a{I2+crL9sm`!=Q!^!6UT*aDvheDL*+w_&0dIRNuYO!egO6}IFB2l`hh1(l5?
zGOX5Ry}oQ#kEM2s?E8RMc=s&O-dKw^_|UZ%90ynA#zZ;|+^#J{YI)|&92{+Hk6cm>
z-^{iD;c|Bx8si3qDCvd&^Z54om_xDC_*(*?_P5V7Qyj?Rm!I;z4o}~OHmG7W#eZ$k
zpSI!7R{YirJ8EuMV>93MEiKPz1zQ$eDCJ8`GQO@#Y{2}pPKsBeURu>U7%xgi4^{_X
znD}h*+poadR*4m`&UD(Dy14N`#hq&$q5R6_>>Dk0yiy}_x;Eoky?xyM+FY2@rn93T
zoPeM#yB7G_U5I8LgtSt512hZJP<`-Wu<r!p;cvfu7-isk(|H)B&CbeeoD~fG7P@XB
zk0u(S3FM8_7{&ECN_y=>IW^DRmWa_280lZ>lRlE`Mo@|3RJ0Ez_}s*o+(ExQOB**<
z5OSU$Tn)?q=7j~>3(c3ZAI-9qp)7)c_TKC6yBzz-QhjWg5i9}9z_)vOAOKu_UT&2$
zK@ow|=+Hzr&mpiY3_{w6%@WOTjQhb7MK(V({3}sdp+c>gx*<C}IOCr_07Cc3!QilV
zU|XDBw=yC&(H9-lIeK(2Uo<q~NhRrigw6n0M%wz!E;3IVKMiA(%X?<@-`I96XM2f1
z@UsEgX4H~V4U_GCA2~WKbyY`i|IB4U63Xwtt^umyr@?t6K38L&Dt9o<;I9fZ{+oeE
zSg)Y`X7ds{Z&Tm5xEGX~G#2oyZq(axGernAqx`r-Jvt`X$RAK-VXHlh9V;C7GPx3*
zG8+dhCQI-&QY{>=kGk``dS8w|b=*RdM{-bvZlqHfvC+=+MYSogDtL#1B~HZ%jwj;7
zt2z6nE_GIX1@`c{Zys$>dKlYk!?+ynK3!6q0*oPd1_quXgA0l+6~%hM|AV>u^by~k
z>j72-BRblBq^LF(31dAzS^_KByQ>@a;4pt||AW&~#u~QVnZS>=<BkNF%)Donj=->Q
zo?6gtpKt|x&5qi&kd&3^5x7)A<xKOh%pMOzneVBwiyQcM7#7XjKe`<kNk$~!SA=eA
zdUpB*>(tf`$unFC>CFu$uwd@|CC!ws(s6zly_9BRXxluq(VQ`kgy+?leqQKUD#aT_
zJ)BMvfD@i$8~<o{+=|Mb(_oLJQU^xw+!}GJdC{lJS<2cJ?RXNG0c);hL31_picoRV
z&b3e{{(e_Z4?o=^(5L}sy7S)o&V01=rDx|$K={e2%)<5;odxv=!jyZCCdIg6m$2-S
zl?<1fjCZI1p!>Zpu>nhnTnmNi1d;Z%`mvr{6dvtQD28o6Oy_6_Y<*jf`oh*XW=+Lh
z=pJzyq0rabm=xhgI>R*JC~K1WeqV;ZGRQ7K)GG$THM>%LW`1HL0u-SPmIb@vKRuhg
z+5wxh*`0*H(g9{e;>@B-g9L<*WkE}lN``d_8~Pu>##}PUu5qj+4n*@lW|7GHA#6hs
zPRq~#K^#nNo584y+ZuNmqdhy^f-lsm%>cuWM*KeYS3H0p454QkyFi`P{aXo-QGwdJ
z^P6&wvwe1_j;KT|9tIRY8st24w2z7EG*ShnK<+JH7Y2>2hM14Ry^>7F?3!IAfrgce
z#dV8dxA~Dwz~`mWCK~K|lrVOwNj$J<Hy-(8qdmeHvjfn)LP3{afMe~Eakcb_v#=xa
zpNNFq3G0TAiP{ibaG~nn@*4>xZ8A?u6(`L+Cw=5s9wrL{EX%88T79YSRC9F=3W3aR
zQ5^^xX6hqxKnU6?H6Blk+{<6WD#B4|LYJ8Gr+8}CxhL$}?>Bz#8P`*dIH<a(W<S4(
z$md=6Uk7Q~igf4(pwOk@pGMz5Dk}=1l0f#ww5xn&0jkd)p7W3KT{f^wy)WDrHfes5
z=nN8KmKa4u00)+MTT#9bM6FiQK&PGJGImR;$SDp<`*I+~=#`7r@%732bq|1zX+^vG
zcT4j+G{K%=^J(7%5WX_NP4bM(SRhr*$CT3exZ)TAVQ)&`vQ$r!Q4=T^Z`a5v%xN2T
zprFN}`R{<g#djUi06ytc8dG-+2P)OX6aK5~_&A5ix($zR_+9;H$HbWfHIpY`SK%D4
z2L&NYNuV6%>D^-3Zh~jG(RC|cAV`}1XV#uqf=<c11Q|K&MB*+o5|kK!r>X=~Rs651
z$aSZ!Wu+oswzzI^emQm^haJ7b*4k?yg<6tiQD_7ldr8?J_Prz{KHmZ@R8W25U#XiN
zpOE8n_Dz|pB$m`&`^!F9TbG}{NI4Vmj-Q(IVH#c9{kcYxm#SUG51Ns2nW9Dovk#0g
zdqs?Ush=KZw*b~bxyhxM=f~ys@byD$b-q~8#b+9puj!9YzETijN30E?JM{PWGcuG8
zB)^Xa;2-C(qNj8qD21MGjrU$d-G%M%O3@Ra2FAd(;OCE(o1Q$%J2{|NGdEV5C|56X
z{FqJ!aspepE%%Gfe}3Su|1=-iMU`Rivl3nSf>|%l{k=BTEr79t3Eg7kc6$CmpVJ3g
zbX^XPzZ$<WB5!D-TFTI+%npJiPaK)#%j~asa1I%G%F3s2TyK0+2BALJr&FF)MgZr|
z$F{S~e~~nK2QnoiVmym+RD65Q14dhzZ%SO>&yNl^&0cucyO6#7BGAP^LfL_U<AFCl
zf(`?^senQ^I0rvgsVif&mymod8ReZW1V7cpzv8EQIUsFNG9)u_E85aMgzeAHVzh-H
z?P&I#uUL|Mu{4kK%|soL4Wxf1r!&!kwfLtJR&+FvXovajkdhVl<LJ6O<Mp=~mLu2x
z2;&ouu-I59+C#vZr&)UOP*cRy5PIScjwM~6yF}ZI6M74+8YRr}`3kd^=bZ?S`qtd`
zGAXgiQpE^Cw;6|{g1pNyb>0@asF|zx)5G7T8D9;aoJmF=v0l&-X)kc>s(YOK2eqS<
z1e2&9Q`eN^F?IeHxmmM*>r{cM$!T~-_5Gco-H_g<SdEtczJyU|rNQ$4MUvtnqDM9g
zUl_HIez5lnU&(?-w9KF1vdQX5E5Q;AVEudB`74;`wA~deLYUx^JkCJBU9F)3;TJY1
zyOhGAFUaHV3N{8W*h0tA3e=?^>>(r%ZHWG~l#Mc}bm9m4=l*!;R?kspbaYw~PAtee
zIwp!_N{gNerJ^EFfk<Y>+VQB6b6kT?n=vTkO!wQgI2lBZ$>)@n#&H@KW-yWFwfYgo
zGZeDmXG@;6t^_y5ORdHpwTo;ff10J;K)I9W#p~9v3ByaXE-&bwBgZy>Ct#VvS*T4Z
zVlB(bnkvf<EH|I+c5Abb!$-0r7T|&r?6K1#wkoJ>>nO}?-Y8*|+K=4BXugHU1s~=o
zPCOcWrbHunm<YP<+X^)pJ~NL=RDVTYwtrV2s7ATu%4o5)<M+x#<S6%qwtB&@cE+zx
z4}#YMpG{H`wMsaOlZ2mMz3J;51QLs6J?9uQEk`bvl7vOUyd9~TZm=dD&~*Hoh^9_Q
z06V_9-UQ0QA+h>&>ka{w=7HXrK`hQ4?0{_~c_|y$(aSCeiqT@ESsvgI!81F5q%?e#
zA~RT>NB+*7h;Fliap~6Y+MA0YMUc&sPqE?}F3VXnhgWT7&H8ROFM-tz*Pb0^L|VG?
zIjP!oDc%E<^yo7CoSdH0XPl~kZ5=c(U2&W>fX_s8+lnap&0UqX`|M0a-FB1(fq+uC
zMqgI3nqIW1Wdwx!eV$7ce%vPho(eG*Tvd8!(~LjL3S5vi2oIBXgtOP|X^UDEAkn=U
zwHf32J8m$D)BgiR7F1I79Meo^Ak1ql;+ULG@~k=EP39$Xwy3XZAz(OXmlWvQqHF2J
zS9Q-sD?u8=A^e0=1!@WH4r5@L$~g`PB+v}(6y2V-7|fWjV~?5nMo=XVj7a8;l;#2!
zHKW~OcQ#AyS6)IT%HDy6aE*{b903s1r4Ro<5SREF#A)4-)K=Qn|C-2y;H`}1n}aWg
zQFa{WKePTi!Rf*0*9MErlQUi8au6eM49;W7Hmzj%gO9#eqfxl#_KAS}eul8qk#Iyc
z$)d<;1pYwN_otj!Tdr`@z$YU0>CNp^98-^i+F*&D|AoefG5<=LF#*u<jKmu3AHilK
zWa_ZK=cVGDybf^B1qaIS_c#q(u5xMt8j%B)^0;RztopznlSL}FxI#-t+zhDmxTO7G
zc(4}tKg@4U4qjA|gj_I7RbU;s9B%B^9A<0>2uI|oE%z$D^;weVHUF3oXpSh6X)__~
zZ9|hSRDhV0ykpz^n@=)UeA`FxfL#DI1d%XH>{ohAB`SfgV>B7|%ai@Lx^gt0UjJiX
z6Cg&1Z>Zn0Tur#4$Pup5^L|&SGHvU2O!mJlVn5-yvL)XWd|Ofc8?)Eq&ZpX~S;0$o
zQZrp)?}5o|%Tc-tllex5joS9|HgS0Css8wlxu#FOfMEY6B-u+DCS;8^okZsx;^#Nt
zjxYe*%tiw1?0@X@->E#>(Bhq=+wQV*IZl*~(_SAos*-;(+W%u!`w94eNm5I;XXPOe
z{Vu-iQX^TI`$zuMyXeyM4s%HupUliWiC$cgo3iyE4mKXLXT>28K^b@5Or+xfg8RHe
zlcIjJB9=7@Iel{bQvOhR<Mko_L+jNM8mI3#zB~e`wBbMPzo$;;rbmD#2mzMGO5~$9
zG?{n>2xE0*qwtf)jXHTJ`^sbaoENZVPk>{2MAjeB6`_~rZU2HE`U`r|zWG@0zo6Q5
zgUmmmT2A6|V4*(`VJ*IGQ{I@%u|(*wEk5Xb#>D;=fMF0-DKngK|DOQ+*yN$Nzz(}5
zc?Q=H*kPtGt@3Z;Fm|}>m>0o*YU(W&QMed~0I?{)!=ok@SmREt$X@+6qs=Vyb?wtj
z!E#@15ew$%XhM%%A4a(SPk@{G<1cgnB6S2v!&gnbTE;MU-vE%lQ*AHJdK^Z|CQ-SV
zanQ8vdkMd-NIsVtTQ0-Kuet|E9?kw(t=EjF?gV$$Rc3iyj59_=(Z^<5OmH?!eSgeY
ze117A?Dz$;pmOhq+^mT0*SW{!U+yZpjdYEZY-3I1T(i-*tVwHd6$Tp6OMip?4DjcF
z-42j)X4S;YP2`XT{$w)S2eXQv17Mat>-ZmF*tZveZ2<7GRsJtc$Pw<^urQEc@=%}%
zR00Q3{)I{#Pq<C|{xTRNF4vrYY6r+oGJDd7ISRX#E#j$K4)Y3N3c=rSh<~=3!5vk)
zz5KO0>v)I_`+<cxKu;bDm633?Z7cl?NU2$Kh=079F*B5Ud-LmcFd!$#LKpz{zu_Cq
zX|U~s{u~(AS{s&+s$E+Q-ucB!`y8JRwa>}?xuzNX!nAFrupi~hu-i<Q9O560V@&m?
zDmuJg#yT9bfB3d&q;LnhSAP-ct2DI(jxF1<A}gAO9foDY&)~m5blqLcyzrK72BRO1
znMw=b+Zg45HMR0K5)a1+`;m2UkdS6+tJ=^k@ka~f3v=Q+)bcHl7}50<B+?U+cuQc<
z_6iW5Q<%+3mdjy2G|*SPZpCOCrhZY2zA=TuEKq4jS>PE^X~2JTkZ;@kdE!HAYQZ0#
zC(~V51dT{aXy?Rr!h&W<@|1+#I>MZ$p)jbomfjAKeK#&vfyCa~65pS2pmlrr4(|8S
z;v(;Lxu_6j)wc9w8@y5%tl=yRUFjqNI^g*ws0sDKM}J9Qw<a(sCO2+bx7LG;%0f9{
z1gT<0-Vv-{zQp%yoG<I(Ky?pBwiX~;sftS%uZH?yyP}<nzJnGMzx%eADPHP1v$N7q
z>o3Y@Hv!6Px3pUkFAvmhf{|u?ju8)cC5tD!#PdJq=WrGNb|_X){RD5A6D;+8!x2hp
zB#@`B0+bc9Je!k!>*2uVX(yf4y0A7cPe-gDXuB@}-*l4zzV<IU%7C1us%>e^e{$V5
z!5l1-nL(t$Hwmtbo}}Fn<befe8&+i7rf-KCSxG?dqHzq~YyxVx5f5}NW8-YWBC@zq
zyo{X%WcvOD*5X`Z*otgUliY)mi0PwZ=gmo(E^)z_j4@=EHk}KqW^4WlQ2HqSO%+&i
ziVPc96MB$;e7Xi{L<+|J!OLy0UJcdWFpJIsnbey5h^HW!$;twrH~??^;~Db{qT&7<
zR*dXnYJXf=b~9!T4>azAdzF!F7XVQq<BvE4k3%f{L_>WyT>b!R&@uKDH}EaV89_}P
zu+S}7(ZNB$lb`!w`)`K{_svO2K&M5Tr#W#N&Gipi{2=!0zz7mJ`724Db$zXlu<l?z
zB8_HJdEy@DiOJ)MuBB`P#(?6bv@_-n<G>2Q*HuZM%x^Lf>0g9Td4>L)zS>d>ylapj
z8;~SCgeRVz_t_c!2(Yx_NLwi!p8-oKjzKm@L3#!=Diw0!)hwX&Zi%(iN~p&+)8Zgj
zZnr}5V5c4sRICh}`wv*Zp!CM$29JFavx!KTW{%mtdUKHpz4E?U^dr%Z5sB@eqb~Jf
zfzi4%(c%qs+FXF}ON_K;D?!WL`)L+T^x(VOQoI&TT-Fn`^n>fa7mvyTr2+mTuLtmh
zXL_5sDZ7SqIX7PtVM=aEm(?~i6?xau6eX}fcn}NV*8q9cNb*b*1NcExkW8?G@o-A;
z`IniXlPQ3AS_^52<^ONkd%=9d*yu(M)tCjtVh9``!Xef6AG?XBp9cJGfw-CSzgSbt
z8a;#8o@lbC$&Rdo{P(apLkw2-8QsA5@vKxbPNjO}&D$@~Ql!Zmh?Xqi8DPX+4k%V0
zS}Yc_M+@75B5H?>Ti${t@~ak|ne&tNGPd3Nv$I&i3pX#>D{wHs*zs_?F*$Axg6-py
zi7W+QU*KNenFB0AA1iXN%41NNhvv?7ezI6(L~?5L2+?u4_5I;baMcR2G@|7pM1h&P
z*P^O~5AG`afrL}hq|LoftY&|msON=eGB2gk@_kB7Zf~%jq@qb4zgRrL4YaRkHxMrn
zmqJ&%9VXha%iGf?dvbn)Mk?o}5z<tKwj>O{FeY0U#0btN=23#(s5F-dLId!RAH1Dc
zf!~$f!HQg^N#Z+b=0@S%g)4{<tqV01H1WKDqQB^I|8F^y{n;iLZhe;r94w4uEi!_m
zZ_#P2$V^d^CkF^ri^_>Vn;0$Dqa)5<l%%Y`1^Rf9zzY=(a2&Wj5g7mn;Ffa=P+B>f
zZj^(fdCl!kZGXTQ&C`JDe^0Ph_#JCIWzG1#6nS_99ez&mX%C?Rj(VF5t*8^SSC=U1
zckE0ZCz?o~LR_?+`OIaCg$;Bg60VeX*)vtuHccb^i5VRQs!#VarFd;{nbrXfv;HNC
zVAXL^f_xr59R0b%S(@P-cX2;oGu2r+QY`#jN~`8Y5`L_xYd@~s0mw#V41qiH^^>G_
zBZ&*K%{^#fhR+?PBF^seu&cjnhhpb&*50;3{VXW4?k8bpN0h+)G@{VjWO??U3#~vt
z`k*hAc>W+i^g--o6ewhMaQ}J_Z6FutTixk6<(+xkBDRn*SXm+)!p(Ut#XI=#m=y86
z3;)i8%m0qKjy5oei+|U-pBDqh#9d_MRn*CbfTmhT?N#cAwBfC=LSy1U5+An&`ML`2
zbLg)oiw3Y>csaNB(tCVs^NrCfLEazFY;Dd!8!&z^N3H@lGX>`PfmW^Qucj}o1X+lS
zbxfVDu?MAb-+i+&V^;PzwdlQ3!4~6^5s5o}CJ%&AF`~6N)X*TBxrxn*ij9nv2gl63
zlg&LkKr#h#OCqv^tB^4X+X?*_8F5q2{A1xmQN1#3b-<V!wuJuhTOoKP@j=_Pe;?3;
zYshALTDc`wap&jJ%Q(BNW*^q{_muWPZF)T5rWxku2syp{KiH)rnnIsEX<D<+f^ExE
z;AurK8x5!#`$O8dA4pmRbsm*y>01ga5De3R==OrOrXvyU-zBG&@@-E`oW;A#PusdG
z6d<ea^q1ab52|H;0!+>ZGbU^nt|4f8Plcs}-dErGFFwXHp}TrQ$#phqhT;3EvOzlK
zYoVm{cUPo)m4R~=gi1$Dhd&v9d+sAju->|{BKZQ>gicc8ef4LZ%H_Q*Im;HZ%{Boc
zXRZW7-UMEMJG45#TI{!+WpvynGN#Vb?DmZJGdT+J{cu}bMe^COc{FK)eZJ<w$F-o>
zsg&{R?#_Xv^y~kbZb?Kc;fXK(kY}ba{S7M1LA$3!o!;|hsN}3VT?z;)K2*9|(`U_(
zMMl?vBR+}7_U9v)89qOhmxnp^%g3kZ9bkLM{q-*meZi5|(x9QAyD7dw8{{+nV}KvV
zcPm0d{=?^5Eu2V!;n(P(&|RH?^?k`2;rjsVPr$n<En|hHZIxJ%i&=rj!<oVZ-N{x2
z3-QJli(P50<r(PG&(P9LlW*V<B78gm9G?0a{1NJ!at-?YlD!uW-5H9M$lJ{ScHSiQ
zFY4hlRN5xC4^3ASHx1f>nXjJ!hBy{GxZq`vK*d8O_KWMO*m3KCxA$=$A3L4Zru%|O
zng`p(CUUxB>>pJ;svw&kSo!97#NqEtTirR&x&k)AHnG8H@+P?NIRNbkcTIqr?{6o?
z{u9g;t#{8Pdv;op9o64lKUZ+~wErsYdynp46N~eYHV98uRNiZNx@OG-<(OTEJQe+x
zNF6)yK_M}*BmU_Vz@yH!q37pawo0cK@xF{!C54jBY~HW0(*o+cQuTG<MtYYb?fcsU
z^-JTs<=FShOINgn?nn-JlZ5zqOZSvf1QkRvSy1DW>Ny4&g>K*jVxD-#?zpfd;viNs
z^wgC{hpSG$@j2Zb`&<FS9{T-V4@3{O#u@NT=0owEl+m?e7x(sSSPS<=w~w!O=vo-2
z>EG^4L^Cf8(7y-<KDC^@OFC`tBiDaepDq?1rCL^9g>Ac-zryG$Jkph#s<?N*bLgR+
z_Wr$7_s#@0j7mmO(~ZMNJSe!e5J`*_Hvhs?Enhqa!}b^R75@y|M^#$0cdzs8p<NFC
zy_1P&0xkX>mWdTb^(aBqf@k1n$gnWHIU$dr_*Ijhrr6qUS{aExl8!LNA~gX;HQ>0O
zHY%RahXr-6H4xkSflxp2*0p|_F98MR%6xXc9i8I%MP*@-+}}a>P3Q=(St(;kW(Y{@
z!zz5x^b@ZuJ7n0Wa}{R3_GQK`$!l_?;uEJE^Y*WS+{XFj^^7Z^c){nyGlObd7lT*#
zm#kplyHOYVsK2Ib;M33Zoic1sV_fI3?<I@~FBW#Okp2kv@4^Oj+~$v%wyc7z#rm>U
z$ll#En>Mp9fCde(JJO2|n7R1(4Ie)fSTQ0Q5vTobQanG65fKDp5uY}^9y*vRKuH>F
zUZ20`ijnc?AbMBD08ulZU@e>y-EbX8D+$U+(no7jVg%L4wO!XjflBkGlEyhp1u3qW
zWga2yw*gKag-<oH{UwBg{+jl(PteI0J+RwYHFL4aade~|S`zX70<j&wZVlK!)b@gZ
z{QD!zu$w)FUa?v$R3HV#h?)KMVcFIXKUUwV^`T-&pGMZu4uU)UqtFj5k`RL#-bfef
z1znS$H!LQus~YmC>URO`*-|SDGxJw)BUW{%pRYFB*gqXTdHQ6WXf(0T3#_%mU!>2g
zpl6k{x{}7P<3$;+7=%Z1RN1|~VCdOibk<{f;o#Yp1Z3>a!6PM)UuM-KyB^XGQAu+G
zvqe}@>5%U{__o(iE3so?mbCtGbjR95GwNVYqr%KQhlM%qs}~Ujn9^jyCya~%9pfR#
zPOwzxcN0Mmw16qhmtk$PubsbnHc+?LiuLg0>zVBrYCpz&`t9+4#pi)evG)*J5Qjs6
z=0t9*h)+5wlAWvZk+9#{uYx`n<elyD%#3l(v-7)&q=7fcg1C5WL&$zjk6ut0zfx}?
z^@wnPfbC4V&vGF9M~N{}N$RDUxvEAH%a3Gis>TA!l#)HD;ulWPV59)QR*9=2y7`?u
z1dIlBXv`IyE<`QU&u`$|d`M7q)ubPF!7)l|&7>1ruk`N167%VZU*%|&0bM*(R#^$!
z^s2eHwpH`<zuy=(ZBs6AJ8tD46LoF3>9?fZg26LP2V~4XpFMu*NPqEB$Xay2b_p*}
z9kUwhk+y2w5k0803i{;MSjtZsZYJv%Oqh9tc%dl6cI~+MVgiZ7mMN$jIZ`UcdTb5S
zM{pCuY!jCX&|;pyT2;WKWkExm@_}bM6*RE_(yHQu`z+55Uv?y8sOmC!a%}{j8oOCF
zTy(B07+;}u%NaD21TA2*`R@(ki1GOw)&iU8*7iva9-`U?h6oNN%Chm9$l=}8301|#
zQoLro7X6{a5fEV?J4gRoyJtqdXegSBkUy(baxvNk_i5|jp{C$9Cb;5@HCW$y8{6Ol
zX@e!Y>CS67v^@dST^Y7=2kW$xIaa#wr`nm&s-IVvfvO38Iw>-$K!|3VPk}~pcBjFz
zvcWleU||{?s!@JsR+Hb<$`>XcftKKns(;W1I+s$%N0USdaCLDeu^ZIw$ha`WuL8@^
zU1vsb)@KjDGybuGf=z3ZH*y7qC_z|JbCdTBf-Rm9JljNn2tKZb5b;M!hh>4TlulsD
zf|}uK<6rQIY<X=ucyo1eOp15e3AAF(0PS&yCYc2Wuu>AGWY~oTKEHE-AvoOH*?SD!
zErOHVn7BdEp-aKM^|^?U&u;)yEk8^})1DAcIM%jY`~)3ql3|<jrjOyXW(JKX4-Q((
zf#=edphWh=$Z{p9t-$RpHd~taz{<;9SE+Z<_DsN*9|d?RyobZ5&S+tl0Vx5^%>NF)
zWdqv4`^ZGDEum+*ly;IOd5Rs$LGPk7uPkX^Rl;|feA6K*?CLDF@XtUq!-0~06`<a4
z*TD?90yjUb3f5v@Q3kCow=gp)-jAc>5mxjao+VxH(_)kkh}fHP)QhI6+dQb4e6J?J
zXnTPV^jyV!S*Plzs$sX6N>dtM8|g-wGlK`w^y3cX^x89{0a(!!!d9ghijX&_n<wj8
zGR&(Q-$!{B688^GkkzY8Ot*6v#d094FJ%QjUX${JEU=w<u5UxlayD1h8|Q5H2-RGm
zBIjmU1{!Q*F>PcO@R~AC52*BwPZgSUsJ>CQdpTR}#+V>h-)ZLj_UiVsfUZPhAyF|Z
z(Xc;FiuZOi=z^w&ZQZ`j5YS%eH8OKvnz!_0sAx}WK4E8f@6f@jahvXh4QH#8rFqv6
zcW(qsb3Aw{Qi8iG%l7FgY{<+&qaJp*GKbjCZC2SZ$DTU%L5H(5^ymg{;QOOq^3cuv
zusB(^c1H^>vmT9l&;x)O&N!<wQ*+tW@=*Nc7cXxiq2p!S-KhQvzaoY}09hKe@6eqe
zi2M4AVF&Bwzm};$Ge1H_`%-fW8@l^ghpRU4S{zAN8U2Pu8ri2|8&qDBmam4uCVS;>
zs#A%{%dB$GO@5CE_C-DzdQ1D5AVJ@DX7AoA!296<=}_vfuU2G%XCf(Gx;av?kq-KV
z#Kwe%Z6UA!M<(coa~#*Sxbnu)C;jV3j8{Uxrb2(%r9L7c)nQTSS1mTBuODv2B6r%0
zJryA_v$ib)13nF5&I+t4XdR0l>%5`zq<_PRJQU}Gv%Cg4?6gWf*6`u7oC<U>nbWij
zEBY;FHnw3wa%oF#$A+BDk`FAs>os%ra9bj}w6)Tk`#Sgyc<BY(LG4->;ifrtox^yQ
z?ey#otUNVxRQ4MwW9O9+l<zlUe?osva$&#m2<Qg!W>MH^=H22@xmSS9GiZ8N@k*#P
zUN8_mq5zdP@LI%&sg`(h`k4-^KAqtcTg!*dUu1fNGVy@st9Ofom;HntComaJnHMaI
zF*}z;)Lq6lV)9Zzk7RPXa)+wwhVj!|%ZA5Zq{m>r)&)w(-7O6IN4*bB6&R1E2*@rm
zf^RhIF-jShSoB6bvt=2Oh)mFZ=fR6)dhMGR1>BBvB9nDci&Dg|Y3rJ{<WG<s7CFD7
za0&0B_}eThH6}`&oeZjTn$}=jr8+*QZ<-C-nm?=>O3DiD`++VUt!ncA;55g1Ha@Mn
zT^_<0t%I!B%~5o*#L3%=(1G35iypS9Fr}#KyG}E%wYkNfVP<q$`|&yD_AlmUId?Ji
zCYmJ`6|j@uw!VzKe%VmqEN9aX>=mZ|Y3KSuzn^oUqeKkG6uN6cS7<o-87&SApkkz^
z*8<R`LH%_5{%3EP`Wu|<dA~yfJ9*Y$tx4fFTO+A?Q7w<K#0^>aB|Ms!p!SPFI*fd2
zQ0A42vD-flloSg3uNum9g^;5red0990x4|6AnUzwgw(ZifYMyMAlr#OkA5P5POJg2
zl$dyCh)8cF8)F9DHKn&VoJmI`4A^e+NM*>Od3b^XK1p>CjXx6Q{=q<Wdh5gC1mpBk
zPopLh0@PuoT7W?&bOqYkVzjuEmc<UmyHjc3k|-M8bIIiO>Z~cLQ_XLBe;U9uJ<=Ge
z8F{>vJ*-|D9ZugGNX;XrpqZ;yLn`x!sFrTzC{@qJ-d<DO8*5$szpjd{9Y015^S#pP
z*vEOL2oq;Sk0iQ197?1uXAjo(f#z9hDo#{O96>O<OxN2HjFWMh==Lfw>M>|0*Eyl<
zLViD1D&@1(V$m4RsgOsYe<N7<Co#yC@{p;@MQ%GX&Vc?f5lzb<ZoKO*C_k~MW8Mfi
zGfM#XUt$i``zv~ae<~IX11p!<vWM~yIV#K>EZnvfrd^0zFLq&sim~&|EtB0;gm{vA
zk^zrM0VDM3xS8Nc>V*G(c-3aBJZZgt^g7LT{}Y0>Q9-|Do(%g33i*8hTF8@D<jiSg
z0!^9#n@m`%0_u_~SW^)$Zm-SX;B|rW%MG6N8#zewCJ~6klDz)ZlpDx7(4%I$l1|Bt
zOTZG(!z9^JagS?M$Mr==fPNf^&NHX4tJAGXp>)IJ)G*=mBcB(OP>^_dH56y`7#&x_
znOj|ue0=RxCoHj9y$%)47;$&mOO)!Wk4i8}?wm#=vH*Vp*m+h2=9!_Caj+I$+SPN}
z$R8$pNUrr8pQ|os|J-c8i@v%XCzt<tBYPyVd-BwqN74<7P@E@%?F1{wjS#h~Bl_v{
zIo~%o3rLH^{>7-5pV4^m;2}#T$Uy<39Vr_ObBRZW2T>=YzP`(-o&ojcuVmO*XP-qR
za6KoGtXTzFVvIBupb1*x5l&;|5}x>ixn1Sk$?XKJoEj%Qe|X*ZgFqGgW=U>wF?ALD
z5tMBnEN@G2b0n%QutJ!D>XnJekJ_xa%3w3F5)!%?N%+5J>TWp64GS@&+qZK##ar!u
zSz3Zi{jsnVS>&7twjpp>Hpu2db8UVDzfAkbiLIzenl9F2{C|Kz(~X@=*(W=Uh;sH-
z?jM@pPS{Z?^PfJ&ph;ZMUu0=;c!RSdn$b%~KU9KmCR6uN@}4vdUG#eO=7dFPw3{}$
zZkuBpbDj5Ui*2C!G&9<*`uk<spkp8sIz`v#S;1gCqk%_!vA*gk$xEBqq+~Yv3Qemp
zWUjzcE#=Jni}<d%YggjmM2*gsNb;UgmS-#lk<&##^m{2GsulR+J9t|H=QI3mxFQ(v
zJQn~yz%B1v%I;hMoR;E^Gu6c+jBL=-oaVMC4X={50IzCk^?8O^uWxyS{t0TsNM*h}
zR7&&hocBFze^o4R3X@T{gL(5u;M{_LM|T*7F|<53Z#Y@V)ucB^9UHO%FA+*S$$|$h
zrqdsR&~xOW31|E_7A(kzAa!lg#DaHDv2C)dGVD}lx$nS<ZpIJV8@Z^rXwpTtY!E%W
zIm;Q}o=**UcK5){rXnjUg;)0}8BLn;ti6L^XIl}YeHxIU-TPj!)niR|X!UOX?Nq<i
z*H{rM6dI0%P-KD2xiQP_sd>`8k!-MQejFQF$3N7HUgfuDI^XL``BJtTN(mTNX@hU)
z3Nm={BO6pz|BGD5*Ka-ZzhL;QAOisN_16on*QD#JbLm(Sdlc-deG`zS4VMi|uB5$*
zDo{GE2cA3XAH*@&Y1}r~15MlUQJwnOel<E?RYYE&)K}eHXwbhO{p0l3ERagaqft|5
z9~xpsKWi&gs~+u~or@+5#1*3-mArwWjCoMRF6O<93nqF#X#O41@(yj_`=!0|?NS$n
zY`qLyiP^DwK+OedGI=;g@P=hTSL<^C#NYXtzO4jiFgADpDk#q&LG1=|4IgY+X}S;I
zs>BP}jbiTHDiC0fq_d`efB``tp??RYuV6p2F^@jG{NQxafn#$tD~o;9tc0nznlzKi
zEbVWgf_sDqf@RErv8YqW$}1}O_s)NZE@gj4DsEcJE@dh@4d_`BLm))+H&wErMfUq~
z4rt||){G~qwoUy+8`N80w3ac7mvJe5b;waV!r^fy^3;_i?buZSdsytu+%I+7E;dfP
z3)l{cIB(7u3$wrp!`z5XqPW`e&hnK(n!TGrL|kTnPlJv_Y}@-Lc~9c!7y+gO+s_zq
zOBVd3<I_)Hl;%~6d7x`Z%|zJiCgc9CbYH)gA}t_F*!JG@(4|9Prekg%n0x@<yOTr(
zpO7?HNXc5n-`#>>w{;1uN5)q}pZc1$rq0|Nl#Y10;$EzlhaPNT_VSRWxsJ0ulttSF
ziey*w$`fhEpOVOe=veJF;M5De{!8}0`OhBBzu?s?A*qLi<J3ibj5cWHmDRARs@Y!=
zYTo2QZK`u*YTMJ+pZFit8s^$x0AIDMBkU;njcj`jQrLqX(md9(HeEJJ45z;v!5G~J
zg{1%BUj_Bq&%9S&%pvXvP2w=oE&&w0&YzK<vh2sp5X;#UUSL^KN9ahof8fcUYAz+8
zlyO^7fSn|77eyxb_fj^}D)Y;Lf>ea_RcR$&CH^2d*6IPUe5Kt+|HA4^MNBx?Z+{z_
zk+tduxShi*szQ13g7<VL@=Pr@^T3ZOtVjctFXot%viI}dhYWt4Tafm3H0t-phu_v?
z`ybNF2!h~5{90bm;;|6wpli4*a5|eX(Z03wXAkK7g@0F$p6D%5im7p7#$7o_7EHUv
zf=;38v@L9|^by-wA8<Ijf!75Gwtkk%sn<S@D_50(#KJ2!WxqTGQkYLo>#>=5D8f8b
zSV^xW*X6uQz9BHh%2l`GH<pTRmF?g5ov;As3Q6(Ueq%QS#B<v=?JJ8wnG|z13VKJ1
z7erItI_Jb!q<L{-d5HR$e|6cZZTd>EOQm=q*qJZ8x6n6cBHnJXrfMtkXoiu3lZjcX
z^R?(w@aA+|MG-n~dxw$pljOkqyN+P9oufsc-{ISXwkDY<$D+kdBuS1vgv80QQ?(C=
zToWff_W>fyZ+Nul-p%<p!61%kC1Cq?j~ul&W|zI(1yu7vT^trl&Dz8+%O)v89cxAC
zQ*FzF=!c@MVz;eTy2)}jcx87#rVdw8K?(Yz9h0~jEb^k&(3E+<F}+YlVEaB(5$597
zGM8<B$}ktPl9CZwek+s*?;@6H0Bf7RQD;fb+Q?4M7V}YRrH+%hL$gKe;x>1LIX_7X
zdIPxFv{_S~?mypF%#GNrO#g`$P2jMZp9dnaqTJ@f`T6*C2i>=W++o_w`+GXVoSxjd
z`0lO)JZJ;mpKlO0!g1bmD^PrI<}ocK>JzP2GQu@c%pC+9jtQlp&|+lPx3*fFnJse<
zIeV5Zeph|!!()Qt8juij_p=?_Bo`kxri;zJs9E6*n5~X6;UPvz%77uECf*rwI>gHD
zfU@g*J#Q1BQR-9lglp;X#mK?LW9yS8BlabV=k2M3obY3bB#|$wt#o*nsCO0=TIbhQ
zfx%~8`V2C*T)$%f_6j)lQ3ESsCDEaOD)HFr7LbZbuVA;e@uz5fzR`529J|xjOVu=L
zO0?~e`SUlN+EcI6e;TYc1XdRd61e)Lx)F_+${S?Zlj>q_6;{N=Bf;G_CIjEW5+3P)
zs|Xo}lh)=VyEgGX4UV7t9Cp(fgugu-R<Qj&@7HlPUM>X(p%BeVG?5r1h&>!r=bPwO
ziNM#<ZaPy&$N8SRKagaDwHFJ#uEc&&ftc*Hy6=e(dNr}gqmY=W2pu*@9t4MIpp!-&
zH#KoMvCoAzqS<Rdr0RVHNaa>OD8LO$?lfDqI!%+V5iekp>r%fI7t*b{3*6MQ!V<1T
zE~`7SzX%)-gRKRr<vjbjHQBCAGQuNK9QhS3c7||+ZXpr0<eD%k-uHg|z5?q|C1D9A
z!2h_>&3wR$$?5qCHIm-2+CIVt9YcF+oMHqQ?GN@3-~gKF0yeep(%h(&v9VJ*gkxnR
z;r>^&_Ihsl4NjLws;t3$XW7F(<aO<m5eI<ALa5rabMLYJW%NRg>jwQ^`wFCY=HKeH
za<~5=JP`^r)FT;Tm*j?7b^ES1-7*R0r*L#kmu@{P+6lCi&#BdXRq&6WlF<PeKR9cR
z_h%0eUS4G=6%m<80&M{^H-mmc?7(_jf-~j(65;sOr*)TnTUIy&KE@TH&$eE|?FYOc
zqy6>R2IdwQsF*CTj;?w&c+BxXV~z<+t~45`DW$St-pAKK&%l_?2fPc={<`c^(EXq+
z<l9S7WjW!m(V?M&qotuItv+>}3WAA$fSw3=X`=r-@oMDeq0=R3|BY-VFrt0tTN62I
z|DO^2XtL-@uW!Fjor6c*MNb6Qn`lA#OQQ6LPCQ40r`h6qMW{^3T_EjqeQwK!HIOBN
zq>_(3Tu$U#e81K>-|`yR^jdjr|F57B*T#!0_$R4;6=>QKi1f;p%I)x0l4Z*;FjHhh
z8$kxx4Xrr+e;9l7K&Zd(e|#|3LQ<)0lNObtk}ZbURFW1dq_T`sschLAGltQq6k()A
zWi6$K(oVKfiYaA^CbEr~!dQl3FbuxuIraL!-@niA^T+qkdCooeo^$TG_j#Y^o^u|E
zv0NU7!JZc15xtR%GG&^0(C`L=*e8&mMcGtFPl<4ija<X5ejcR#Q0I_qt0A$%_6;G`
z9+a>FcA(08Jo<M#&556w`cTBpDocDMj?8Dq{%Nk-I&kKnyzZT!(h$ZHa2b^BQ(s5@
zDs6OfZW=L-mWjL@l>~EpG+!4p#yh6Ma!5xnO|<qzuT&gMMa~Kvny6M&rfhmo&x&ws
z=K2ns=jF{0Zdmi-gfAMQ2lQ{LGYby8IP`w9ce{|;AuRbQ^>bgqhI-iUj=ew=Cp=dF
zQ`xy&aE|8n5y=;09iH3(`yPB2Fw#8Pk0Q5EY<q0Dp*)-df*nkaGBd|G)_EM?fGDIF
zml2hs1gKbW-znaeOi^n75hL#HacOO`;|6kh8$0928eq-6<Pm~oHf=BYyz3rm{`DXW
z=5XM?y#N(ua+0QNBw!u3^q|d*)gQpaa8Dz*PH%f0u<_4uKWwK4eE)I0G<Ne67~lp&
zIpQ>SH9%vg$jugPv7NqmfH7UeGM%QwDUaRbqTOuA<#+N9{2evDo_|a3>VxuO#C?1{
zXcdgQ_YI5+fzgnLZX-7-7@;TjFBOahg}oelUlo}{I$;-Dk|y;YJk>D|JTJJoD+<Ir
zoy~1kauo!8xq+cr3?(w$rFv9NG+DHXGk&DgdLQ=1Sh2^4=pbi22^{!JdFHxYk?Vum
z0A@Ict9u+iIAUGH{B*w@)^&~5!uz$@(PKw#3vVx6m&MyDai`DM2h)&U4PZU$Xi=;p
zRowd1#iLn1w6U6PTdkovmdwkZs_U1QyPQ8!C-G{(zX?kuVh5lEgTo3(^Wi;B&TAgn
zMkNtDt>+HQE?O$Hz&WyK(H8hB=r}<eE3#M)xFao)#n0J^7ByGq6~7w$71*IsP}=eP
zwrgXHe~aCba?I&}Dn8PUu!wu!MN3H_j&K4*9Tf<(K@&4xl$8iS=AA4T$=0@F;?+qh
z(g6?t<t2)i>v5|X254N3o4y0-;{{YJNPK7|{R;ChZ&pYzX<}b0!AhCA{^jV1K6Ci-
zuK9o_28S^P!A4>Pq4!$D5>dd<lXs4EJw6)tc3@Y<hJQKnLlfJ=9s=6fT~N)*n9@y!
zgyjRRk6b-H1+5?I-ECPOEVg3NGO0ZJ-`k8KL#DdX&hwJ)8Je#k<NCrQf@k<}D{J`Z
zc}I`f_a{phNRbg{whA|_>DW#4X}hKbKxaE>lsR0BePaXPEsf}+0E0-LU_n>YT7~v|
zFiRNvjl*gMF;>FI&H#*fn9YwiGF*{|(cR1Y-b(5^zwuZ4Jx7o64)+o<s_#L$5V5rd
zLmQY*1v>yVPs?RWWxV6avo>Sqj0u6(70?O{?Qv;yo%m+Ew)Ul^YQ<i5Va9r}Z9Pv}
z;(*ITK=!yx=Sbnx{J&euix_B$1b+xj3~OKJsZ^Z&zXWLF!0v~D+j5tVm(EO2_)fz(
zt`t0H4ZUToP!({~ON6zv=pQF{WET78h4fHmzGO{&mzdDI8yLs(l`b%C&cdDT@hR+0
zCuo_E`32L<nP&cF!&JJU>RIl<H=cV*BMSZCk8T$XSuj)h_E1AyYyZ@O@xG(40-Q%n
z7^m*Qcl0}4Mp;l{8xiM1^zLyYc!e1P;-|FBpA`{5K9BojEQdtWN~A~4BA?md=1sLK
zW;!;Exz5bxTAH>I_qq`AJx&@?Nm9%`f9zyUhXu2~z+NcPA2L{>oGj5VIWvK;F)duk
z<;RJgF*DcZwFPqdEeQlqXNf+~bG%U-{w~A#a4=%uI+Ub?#pB$gMcZVFa1bS*bB)q=
zT!Nb(wxu<3@Z7+bM>jm3_qXkz_#_JmrUD?B+gmo<H+;50>{h4ncYN;A*B4}oUI@8H
zl&)g}ZhAzod(TfwXk(F^QQ3q1(nljVXT2^#9nC8rnSF<}==<Otu6BSuI5kf15xTXf
zr1X&1Fd6eic_*NnDPoiVj(NVt1N98_BpGvDovUqV4<EQNE57YNKAb6Az%AIa>3%iC
z<mGs58is#}t3BHPeW%fCgFplS-+GVNpj!XscU+sRJ+M9IKeWoT1z9>X_}wPcjh*#!
z#H7d)VO{)*?{2d)Uti2q`iJt@h89Q35|b?JR!Rf~57R5p0yHr=$!vkBa|p^-Hj{d6
zU-hm%|JnWBeAz4q;UmeF;|0o^0~vs_OOH~uvbbFUMdBlO*~t=jUa`@JYAKafJB{uh
z=HCnZeZ){7#ij>Jb`=w`_xr(lh(03P?N8FoG(?s8+eXIoacw@FfYOl-PNO=8weFwN
z(OwJxWo`QD5rR^%Ieo%*aHS2?%y(0MwGHLlJ-BjnGxa2S+&Xhg-^cK`q4c^mo||MV
zRh~Jp-clA>a(dxcb-0!$+TS}%GQ+Z}y<<x8$zwlWX&RM1_P4wjW2_M@E49$|KjIur
zmx!Zo#Z(crrm4&p)a#x}!SG-B7PgU=CtIeZUy3gxqIUheekyIQUv|K%*tswibs#K|
z|3RT|=(^)1gn{{$33qryMR*OB=$p<Q$s56U+%C8Gs~2e4d1^&CO^X{FJaNd1al6Gg
zb2J9Sc_RFtH_-a?mxnp(_`b+q$-a$)D2qntsny}M#oXACiO@}f4*Wy7jKbZS{$)aX
z1R?xS|9|WTpsT4`rU)yS)wn)ONr6;jD%mE%rc6oTCf@Q<CGuG3BiGiF%AKV_s9ia*
zabM&eJMb2~<N3@ydBvp<qCo1|f)JcGRES9tHxzk;UpUz=u(r^&jl?dqEG?ZSU*Y_B
z76Hc+(9Pj;jiMDel!PC=iLufB7KDxJs4QO~nweG|MiX1^w>%$0L>l_l`X7<j9A;x|
zoVjf8b4#2VO4H`oI_+Y_3?s3!Kvz0OJeUj2YS@-@sxl$c&1Bk!N}fwJ`;Q7GBEE9@
zL&$;~`hE=Kdwn)8YSRbZnS+xS)Y35hj3+Q^?f)1RN9zr0+&g7B-tU}fBQHv#h<=nn
zRgU_n;I)OzUn$MNGG2=|zAZt<YsFu)n|obZAOjbcn-^{smb4c-Sxm2H;#Y{aCGj0T
zN10NzUg)owtinYRWjvn<n<O*WVv0KM^k?SQNM`QufD9FZhW)fPb1e6_7i}i&{)b64
z5toc_i`MWf8%1VO(N#Gbu6HF?vh#o$b1c4;6umBvcjJvwZm<|K!|esLu+v=%SS>C`
zJDop_n|{qy<qmb-c=L$VV)MLBubU*b?)6{eSA=M=%8b9Xk+hj!d@OZrifomU9lJxE
z6k}}2bn`Ej46E#_6s`I2&x`6h2JT1u9!4z^2d}QSkridj*>F0I;>cr-*o|F<vjnM+
z!W*l^u44m(wXJ%n0s7w;$lJHLayKr!Gv=@}Lpf?wN~h`v61+QBEai5$W`^L}j(QK|
zfq+XawY*6G>J<rk@?ZzXWIBjjhpI4~)c7a$gupufd~VR~q11#+1z<Ag`-7q%y5J*_
z3-6r=ESQA2Qc~!;L|)+=$Lf&M^-Qz-dZXyJG+{X|!;PEWJajR^z5wR@eL!&Z!GFn+
z<uK~PP>C|n=-iDfH&Gjk9jv;cDCjjkUb=};t-+{~I_@0VkKDoknJ(9<P2<^)w7}0>
z>Tu$L-T-y(PtD+lDnHk*f$=M^pm;jH0J{YV<v@&ol8%?R2~!Y!KFPGYjF0;H6Z!m$
zktM!OY<an!jjWd!yP?)UOv)T^R!AmAip`JF6~vH3=00O}7I4CoFsvU}EKPsEE+)j@
zcvT5_34fRUKd|i0vnIj-c9#}di@RYgswXH3@=SjhNm`ctFD)yFFqB>2J8|U}vaN}~
zs*U;=a!=Z3yf!jg>l(&aG4k~RB!j<m_NES3?!jfp#AG`&RIRykqEYk+_7;WGFUDn*
z7!~CIA#nW<!CA-vJH1sn*}mlzEzmmZ{g8O*y{1ft9@EnAbG^ZS*ivemzM?|@TGD<D
zQ)sTWcglMFw3sp0M+TBewqm3>^B@b-NLV)bBuaBCo7bj|{~jfmx)Y*T6d)!|8Y0Ag
z(s&wg372r?qP}~%BTq3DLqQgXl1lv$3;`Y=nre_CMrUV})L;nM-S<sx9yeUeEYvNV
zNQ<iH_TZ*ZE<XNoD9|l$e|kyh&gKs&r~iL@17=}n=|t-E5;*p2h#GFDKCEVxWqw2!
z|MwODgPl~K*;~pjDmf2mN+zyG?a}6P63vKj<*ZJ6>mX)rKdIrhf!&a?1bj<Mh*^8n
zISMl$lmz|NkF9fT6cq%8nUQPgUCba{)Q)j$S%|6fm6(GpvPRdl1JBKH(V|)>*UYa4
z?#hBP7B-Eo&Mm@l78Ghio$iSyNjQl_{d<H4OO`VU8LuZUM&+6^%~Gs_YhE^nf8i}Q
zoKq-7ec$`Xkn_FzF`ShGUh<o8I$m)R6h&vU^+)cH;igwy8?zqtb4yC=tdS?SSj!yP
z|KFO=;<>)<!Ek08^7&RlLa8$T&o`qnR)WCfq`*##JZ}rzmiyA}xx5IL0=>aY!u?)0
z|D1+x#$qnJYk2)7oHZeZL8;}PNmMI}MTI{E)~P%b0Kx{#aTZ!Gv4UwToCvpGV#L&U
z5R9=7rq?x~2Q*MBFhiHKNXma^)Md)ST!%}MM-zoT<b8)|j?G+t=JQRDRFzt^QSOL{
zIN{=a$?C|TxHm_Odz*DA(j5O(gBxKRl`?mxXDVd>jZw?w2&w2Zf2TznnU+dAM=^Hh
zQ9wV=Gtv~lK#f~A>hw54{*fUcFWsOW9sb{KJL!0(Y+Si8i)|N@QiGdrNC+l>!X&vJ
zMG5|HEVJft;Ru@-wQ593z)N}ED#Y+#-F)V6m5Y*ZkN!KsQpf}cv5n3%AyDNLFUF$k
z9_4sh^Zt*8LupD{(K3H`5?N#?(VxedHvuBQ);a-I>PM$7=9{DB=SkiM3NRK`%VA~I
zDzuzv(kI{g`dzpNnrDuRh?8tZG5@y%5_Iq|4M$@vtB`7RCL_Dr;x!UY-5tI6WeGD+
z_1DJgxY91qk7rICf(`=NZOH3JPBK94gUD4}d7|)U+Ntvx{`w@;nmeP&2ZG6gXk-F+
z^z8iUm81(-VXCf?dN*!wWai~6M@OtKLn6l%CF?zH-^BjyDgvI&>$Y7uPpm7d#k1!g
zoDp~aS=d+W3g5obVJrk=89K3vpTC9Pg^s><)e~U>Z6J|xRiwd2w1`0fASQDiH-6;t
zW2lv`B;@mT?w=XY9eH`0mwCWOgUikx+C}Pn&htS>*IB}Pa`lpIuNL?C=bfMqvop<A
zw`y3a)q|}ngHqjLgkAc;69L}FsdQZ}*QkYX8p=iSu#-#XdqU93oi3`2QJw}MN)}1#
zI<j@8IZb$)f9uqMJD-*137wM<NI9q{c_Vek(L5182GNH@PyCYAOdG6|(4MSoc{`UB
zjyk;!#6_`(8FI)zmR6^+#R0f@H#QVp?X0SVG6Y@C&LT}WARAYjv*-v6-~*Csm8+#F
zRXlR`B+2c;PWeg{K_{<23X{2hHflCqQ0G)Y8r4{Wu;nZ|4peY?HUVhR7hH(Ft6Z_7
z_ybl<yarL2<>hxR@WMEz!1|n2bdXCMDbB@lY6D{XDXTfkKf&(hWKc`<N=L6kLC7$L
zV62MI{BkW7;rJyWp-M$Ro$nc;<ieWRfsi~`!mGXk5@{LKU4zmw=Z6`Bmx%g+1Op@x
z>tP)&75#I5TSS~QYy1fMwGNPQ=41oOv@}Y6W$C!{gN%V+e@T|sPO0|>LTUW<^dvmW
zOX<8><}_VD0*kDWlVL`eLMSn0V`iQs{5LnuEVGU7L$b}27d7Y==*-!bHHcMPz-7l8
zq1Gk5&2uzjJCzzD8h-J%@cmgG2rp#&z+Xx5S2^#4M>;Y)hkjZvUCGQ#@`MWc=Lwm;
zbp3=a2#fVf__Yl&;%rz7@Yja(H!?NoJ~97D*f?*LC4(*31oJdRt;>Ad%hF(n;4rwy
z)jvy%HNL#YP(-YJSKSg+#Z}&bO{NPAeHPKvFwgTJc@kM4nD;<=?F-Y$a-{21p~s|3
zVwh3ZZ_rbyR5bB?>xpTOhR<}UaO0fq$eZ1$&p-5#FU>XcHLBv9VJp6T=1qYj0H@3s
zB}lB)gQRiZ{7a`B=#wjr8XKH`Cio4demxIi!4BNN9$+gsffWGQH-N+wZK1~^%&NjM
z?e3v5plFvy^~Q<eOvc)*g$O{+Z);=E1<BT;AYrT40FhVrU|E^3O|>o(Se2LLhVnW_
zO>;$bH0v2DqCp6J`%6XNQw)Z%FsjyLrqTfR1{muTS=9Fxe+SevC>nzVW3L^_kP5-y
zg7BdCu#f=xkX{bdG!3LLgDa#60GmVoUdALMr{SVytBS_bW(j!e3sCJExY}6=C(G^M
zly&_BOC=A5G6E5i6<}x&1Fi<hka`E&WJ7*|Jwm*~;5FgmX&CTt@4nCCnkS)N_R_x{
znH+rIKP7`|fwIE}h=JV7?--p1?4ecbn5`EBBn+;6SX34TKrC~)<mHGWuR6DQ+Mp@`
zVYD2{9x>dpI-o!o)qWjqfmZ};cU```ut61d+K!r5fXsH@l`GA?e@1jgSa-4i&@Y4$
z_jx6|+9>UnG<kOG-zFMJlVb<JN}A9p$J33F1~pf1H8=n10~#b%9<%@4-w%BxW4hwm
zF_2dnD`)>z@`Q%znuW+woYOrz3UX|x4WCD>+hbp7#3TwuSjH3~sT?P0&aG|Ms0wAp
zU~6>{V(~JU!a`tr%h{PvB;nmTN1+5T0J`J$pFya`mi|k1O+q!L@Q3Qq(J%>><yqW-
zL#R5iz9l}VZ&UzicXqVlo0x{qFM6v=%E+i_O;Da5WSc`w>bF);7#QgSv65TM!U}J|
zz&6x0M?}&U_O1QDK(ZuEmpaIiy?b9c!a*T$uodAu<(q_qen0uwGkOAu#Y}?rF1>4w
zL1|eeD!N&XYb6oq*fj}bP&Uj5;p%R_0MW((?BIVM<mCt?Y;L0sOVn}Axeei}6#~2<
zt)2tlQRsCq|GN$3WPVw_stl3kwqy{F*tqxKCnfMi4f1F$UhLQrXau$p&@sJ$C`_4y
zz~Ml#LKWp_P0ckhe~WOn>bU825c6QaM9j;Wu1lDiT8`fTc;Z0Yayx%q!lEs07;4gu
z8QH4re%2xB<wg;Pu&P*A(vhise}60JD*-BUV`c{MaiGzcg#^$j$ZkhPE@u6&G&PsN
z;F`GFrT@}kzm#-|h`v=QR7<pk5*aXO^f7tN&pI%7JxuxYMM%tL4TuGkmNK8?!NKZh
znEB5JB`F5$Kn^rXtLZ44z$?l9N$ix9LO}${@OH!t`ej94xf2Jg%+fSdKzXgFra{aP
z#F3aD6sAuMoD6R(!l6*{pfK=mgTg-0`QHeRmBUra(x?Nw4nPHL%RhhE$MLxYmar>9
zQwH^9A+8qc-$GCh@aPaV=1yrV0v`YNGGhM1{?z|tW2i5C;>x$S5B!V^@`;*g)RWXF
zdIeE)q@gwn+G68}IDQK-BU6nq15=}loBqqWXy7EV?Fn$6r^Xd8Vg41<n1fx*(liAz
zO{i%$Xp1>Z^2+~TpQ&@OyIGnhKx=Ur_QF6YE2(y+!*ZBiKT^6k28H?#77yvYf1iz3
z?7fRZUH{*nb=qvL4Ww#aq`7d2ff-fuiHiY&Qw#U!*)<N)2%f2E%A=kvmON8Pp5K0w
zpI!xuRgfqaXcdxO+KC0}ueuVn6j4v0c(ml%wRU14JX6+Ik~}j)+OhxFXP1o9U&*WJ
z%tk#)d;oz1!|L3BF6PLw$iH4-Pmi2HMITcLj#5LODX_?$@NE1vD%$1WXG)HdKR04e
zzYRx4oA}ATo|z*$1e(;#t2E}A?N&`&k3o4UQ`0h$X9n+#Ii~Q;co_;lCM3_6=Djz@
zo2+HsHd~EqA3$5!C<bGy$QA>EfL3Gj=jS$u#I7@e^)fyxvr$DRxLQY0mfE48sv8_D
z?#tI|Ed=nCzkQij>MqNOh5^hCQSEJaAZFFkktVbLh=CaQTdh%0akEnzfj$|AO2$Xf
zKI6JK?YwGad=h7&ip&7(2y6?p&F{R;4l8Ll9rK_AsEW@}Vt)?zpV^Qi4N+oU0ABU(
zfFaYkS{BuE`_E72EI}aA&Z}O%OBs5xz}2b(b4cZPmAPCohItlaEGNRR1%}q3+5x2*
zjC2kFsG+oA8%O?y`T*@1TrG5rMvC>y%R+h2%yf)AwXb}gAtktD5iotJQW_Od%U~x!
z*9y<vX@B_rFCusa0OtVQhJtI1VT3wIme?dUKE|P#VS}0~U|Ut^!fE9!=DDnhLxGY=
zS#g*y*jUi;#d`HQpPzXv!~ED$RK;Ah1#A|Wk6UrmNCABSNh}9TxSEDxnTw_q6$MwH
zN}+bnk#x0k6)xlSz|<7dE>6OA8b<yOL{v$-&tTZrLaNEdlsQ~VbtVaU=7plBF+h5K
zD<(rDWF&hGp@ifT5hS$+QDekD8)9{c6w3F}ciG-DsOx%v{@5HNCTy_F2**p%^=#1=
z6yVRnjb`(5$lJJDJNzqldTqc7RK=;k|9I0F^Ut(HJWSz}Y$?fFU(P&hUSf3lk&U>#
zx-w4uUcb;f_zM#iEvp!eaI=;f6NjMU$*6HbhYp^!Sa8y_{3E#+gQQTtaU!4Zd6`rI
zj#H?I%yPJf1`whlT|Ef;KP#YG-GM_rYTaBMlzow2E(e$A4Dq+``T;g@6bD#N=)Rjo
z<Bx_%KoAeg3*gv6<2#fEReF@Eo1c@kg6GJfAlnBSHh@-$l#xQoEoH(oORK>}J*aM$
z@CB8lkp^dIX7fb1RsEv4PbwFp4kTiLgCM8`Q*jvS_1$X-xsDK%k{OewzwK145~ZTw
z1B92ct>@G{h{*mYRg7G0gRL!0V%P$+Zvjj+9#T`JqK6a^Hh&+XW%dmD+D?yFHf36j
z?~+4`oFjCGxTt%~VUpNwBzrb0e+z9XD6=6>d=x2wT9`R+kU3Pn0rf-)Q9uWr3ZpC0
z7BK4}tC+0OagiPrldHHWc~ZZM>9{~N$x;mGUQJnqIuL__(ns<g@Esi@VPpMy@mc{d
zHtRe*oV|#vsjEKp$v)N?^#p}0w*vWk7I1z3sADd-223&yg3BLPv*t;3_KU-NC26#f
z8yipVHP*|p7>brd!10V=@k_K6L?uH$*F`ATrMf`$+it5>2v1EJS;P2r3?qeB94!Y|
z7{N)pYvA~Yy1bKC;6USC!sOn9DKW<(zidQ4LR6DN@JD40Zgb`w!KV+o8&RjdspK%K
z_=C-iMaUI-w(Q1kn1(;rG)q)i>|%pfMvGD?4jx=;8VOnH=D2bw9K_AkwVh`9uwyo@
zrW<CxX`Afm&15PI(p43RzehqAql(r_nssLuxTyBR=79RGBuMpfu*sE*o)qZn;nOgb
zjbXIvU$X8EW=ujnxhtvKDkL@q2n}%Ma3j2(wgticI8DVMO-EKRb5{x~N~3!rn9xar
z9~Mj{2T{eznAmOJvZ6L!RZ_Q(j|u8D+}yz9uO*nwEasMBX~SMEuBBvl-Y5#*D+=u3
zkf}VMTSD2?ojsZM9aRB=smSADIijCu#W6&_%NOBYEC=!WNo@e90JMv?@-ZBVQUS4|
z00Mp>8SGRRxSJ|*td`zVn56BJ$F~63cUT$-q2{}S01C9&@ngt?U_i6I(=axJv3GTf
zn=iqHB~tR5p%e^=_sBs`l<Zf20I}-SXbk=~D8-i++a>FM#*o?k2Uty=3u!`0rc`n_
z^mMt?nWjts9gmCRvbJGE8A~-$McTM>D7FIn%DYLm>dT(g{(-9KR}kET@l)i8oADJc
z5e4zpjM0LN7>X0*wjFKULa=%+6<u;^9N8Dn)}TdqA7ONhU>lIJfP+>N2K2rL?Cy`G
zyl@&t3kM8Bl_mTwV9<x=Ga~CAX2_HwiNk2R6DdKCtwUcx3)>_lkPCD;-koNAr4lzC
zByEcp)ku~QKnOv-6-4GlIZ=}ON&{xn)SIH*f$$SDD1!PNZXEd#OxsoX=39io)R=Ff
z73`wfKt2NR0By$VEbJ0btZ?N}hvaA#1DTVWY|KoU^m#OVY1@o<b?6j#W`k-IF!-Ao
z%7(+VE-vVB1=Cxy;~J}T4b-`gaL(H_m&;Je%E8!7AS7K6f#g#OW~|^K{w#*_Oq;uO
z!D}6#jc`;PlM1~J-YlX53Kgp;IIk%10mJ#M&P@hczsaEnKvrPy_F87WK>Bf$s=!7b
zDGxpe8HaUz(&xLZMdc5ue%Ix=Cy9atbfP|O{X?;aISdp?&G}q3)bz@{hM|~-&|FpJ
ztovj|m7<h+Ts!c@I}xm2!VIZ#XF=7IUGurbFsU0znS3X-2#R&+Q?;7X!rhR)iqQt)
zsQ75i%+dQ8$NX7EexCs}Ww=E$8wERQlnq}g7p-0zwr@bz(vAw7=blpv?#q}qH_e!N
zu`+N>k@N`_DtsU=>y&#%7_tK9;mV;T#!Waa!|7fE9t-%F_#2oRzv~!Q!mOglkP$qS
z{UvuGB3K3mX>tt^1OXo=2(~H2q}*7}WTY--rgTa_b~A?3eb{2DXt$H9!M4_`aMSN|
zz`uqWxBXAkTT7VFo24J$UcrQbZd3&ZEqaC)xf+Yt2IFdrke7qS^rL_p2+qE&%l&au
zO8JcE0?u@r&0(zdTev$K>jqJ6X+}F~3=A{-EMhr!l3!p0u1N|}lEtVfaDgasv}m~S
zSd_WhGC0=&NKGDesjS2OacoGG_slx&HeE$fnW;J1=#dnFYWGBo=xEVSs#p}U&pN#s
znXWDcq?ZPWRmctTosWwGw1cF`zH%Qk)M<l$++$|fGA17EA;rdKwDWaIrBVES=^5^j
zyXAz>5#5sEpI~X1FnE}4Z!U(V94`*|IRJo*-SXAeXE@Jc70<_&L+DA>EnM3wcQ}E;
zY+Zpf=pCrEQX@;OKK=7I4_f=gTA!(o`LpI%;-<gv!?nG1D=Jw+6@STvzY4wKuO+y0
z<gX_<o%H#!r}R(st;q(?=82{?-dPiJouI{1NsA1O<1CE<|1=C|GOn>}Ao#cp3WEAI
z;QA|Hjaz+0|I}c<R}O|Fy8flB*5(PE80K;zDbEc}bSOL>5+f`6K6cKUFd77MrDE_`
zF&sT+%G>j|HP<pZ6qj!A+zd7xJWU`|F!KtAvy2%6{~0I>()B2l*MgGLL$(9R_Z+V8
zTyFD#F4xXm-*0@4S35YWKI4+K$(!IvF~mY#C;U0wH=o}s)s`DHZ5H1!(D&+_4nPhD
z*AxXNiUMt_)y4w{D$f&achlqphwdYX3V0g=xa(48<*D<>+{v!<<cX7p3^E*26c7rm
znW~`krTQ4ErA<h9zr}^1Am~nribA7MHj*B}t(P3K|5J$`gL$`bqDKma0(8<F%b0{+
zLzzodr`F*dp4(Hc$c35OC{%?mm23~FDww441q+PrXx032z-~l^e}RI}<ZV=P^=EMA
z4!pxkn-QSA?0BgYD>4{`LaCxfSD-KpPG`tu&5CZ1pi>c5W8-{PtLb+ASQKh77J~<c
zL6D04N&$19HQO>Msp9i)HEs!haMH+fy1ff&lmaQd(8((!tS4ZU-y_or9T{g!Anvn}
z(K&_>5x+K4mO{0|`2?yGoEgU0G+3Thee+qi%)p_aRg>F3psz(4sPRU@ezg;30304&
z)Q41Z!%$Z(eC7gvE7_Jxz775w_b*tcy6Ojp!#v`^IuwG_XaMaYE0c2J`ZJ6VXYw9}
zvHVWk{H5Q<k@8#JZyCoUfwaCsr(mrhN$TA-!D|R}@FkUvTe{uxrgfz!QnWJibz;B=
zvV&HzoffzlN;awDX!WccLYrsHNwUPYujAZtzp%w~5YH9DM*Vi&^hO1ogTA9>`(OrB
zRZzNR=zM2AI}G`-Q9xWTyDQ~HAy@F?cPVhPy%Fl~c&=<U-ANqVS?{vW9Mx`$7C|QN
z{ba~efZzp@VL)6O#?exKOe?eC*%E1#Sv&rDIR;n$%OxpEolChQ?vPgsKI0-UTA0Xk
z6>gV`zNv@|VrISBdjw*2xEeNlXwP9|HMhdEWn@vuS1>hTc}?zJY!pMz*PH1Q?z3+0
zq>^#2g!iqU^JDe%Nm;0hPZA#Tvc}aG7le>sU}iG74b~1wKQpJp-_qrkUQhQX@v^}i
z7eaFk|9q(JEdb=KikdEfoK}Ku)KERzBH}SW?snO#M8|`|?MqrHW&5#fq9f*Vdm&Zv
zc1Od^ekfwf_TVhI9T*qL?rJ+(otsa}nbWcRoI!B3AC-*ll@m2T7$0V688WxbZ0XO1
zvxQOaVR(h4eoj_^Bkl*Zh=dm9=7)>%2^!qwna|zSH0(jZOV8^VPjg9{=U}1vld6S*
z<iI2hXM=q*eiF`fiPs~8p1Zzpb9PBmbvSY9G){%~2`m5$fz?j|gqlh|46);nCfY6g
ze{I>Xs-zMhhcwwmE3l)n7I2N?#C6qa{2*L;>ix)|PE3K0lGe4o$S60EQ5bu;FPCa?
zN4~yTKLD2|OQW}3Sqin)kE(NP4w^8N?pMu&ApW}C?x0sM`!AQsTFlP(IS0VPN0GOM
z8rK!-P4rRIbedjWz{EPcs6iUE3M#;!X5{k~pnVt1$cb*~F$9ZpL)>Wv_x*kQ(4s<K
zis}ky?RM~w%Y#={@Jm5}g<RO;qJpYNOPEWxhJ^+`%+N&quh4zOig7ott98fG%Z!JH
z19?G#3c*GBn_eW*GxQ}b4jMBZUtYja8r)kB4F863rmDg~HZc+>%#i|bDLxUy0f<+M
zug>S!i^8Fe>+tVJaQLz9biYlG+<jQvJ51M~(|-LBH~__IfI*}vAbfuB|B|nQQz`Hh
z_tA$ZN_ij9MayyJx0c6<{roO_a=WIxf8<g!p|8n-Io!dTH<=z`o|&%Lr>MeZOxLAM
z)uP?B%*erXZpSO>GqC_dr4dB{jy#3SWLl6n%_+1<trKG7pL<(OeVTm#K2o+%6<13-
zL<wg{MjjHLgH{;)=Qv!Hwds8o!EjQ<nxdkDi&IOO2P<cepKLTLC@x^-Wkg0>&gFu0
zDz<c$;NuSLT&_mONcia>yqe}#T8KBRUu(1`?<235t|8r?h(^X-4+yX8TnJS0$1MRo
zariu?9~f%dZDLz{lFQ=J`af-<m@8UzWWj8~&X*96=<6hecx6&~<Z{;bOEl$YQ}@UB
zM+)Ak@hQuJW~@1n$E%@hC`f3~BFL)ugai>c-G16FpPa2sxINv)Yb@YC-O(8p;o=c_
zP<TYDWnV9xi?C4+bGh<m6K>r1P=UZ+?Kym>t6NMN5b1R^PHUd34qo_H3Q@u*5-#fH
zc7_}=?2%INzIT3VxZ3txQOg}&nnvtzXIho>T+l^JXZ9DqR}kE-0>=t94ZSyFE6q6L
z0sceC)oqcy8dY6)VVpE#2%mxh^Tysro*4P)%xu9O{hWWkt$<|qPFL$~Q#&&5Zsa*}
z$l@<_*9C~Wj-ZL>=&@?tbF-S4QPZTzip<nZ`zoIR@|y~}#zI8kLulf~JAYa%r>1S@
z&)U%8dSx)V1i#?{@4OshFW1>rtNcBMJ908Tah^hQs7B%L3o3%H8L|D4*TqrnyqT!m
zG%1^ub4gYLlcjV|U&NYy)woMOX88QZ%ydoTHxq&;k3PZ72=MMJnf$JkX61p*-*|hm
zzRvXhA!nma$Ojc9-OV}1TFO+MU*yP(A?Ll36?v4lCTJ@Em@rnHsc^!Zrt*{}8~oaM
zS)yBj*4pHZVl=VtONjOL1!pzyEn}*h6=5=eWVaU0PfoB&>1J6@hHZJ+HXB9wHc@b}
zK*t6SV+)TtE@LXrd+mg_IH=-Z^*PROG9686=_%0MAv}&Mx|ch5hS;6~Zf|Q1oK8+(
zvQ7+{PSKmmq>`<YEp2HjzrGxAsb${h*!Sh8&lG1n2g*gek!BC!(IWpxfMM`DXrnEO
z2l0<`wF~tM<1qR)*`JFvt|&87n5<$!nD@grWfWnAS2~|txSUz(Y|}z8#@>X=z1?u@
zbd=Z<tV+1vRaT^VrGc{YtZvw^W;v%aP1Ha)n`pocgv^PDQAPaYq$iZsf}iICu3tiY
ze7}Qgur1Ek{#C74O2u0)P3G+6fSy`GPX)DZxG1-skk}BQ<)6IT7<&Vw>(F=n??7hP
z9B&8NEH9Ye_tv_*sZjYo$qd!<HE(!7jdLBN>O4huk`+Nn)M+YVr!5UWO>PVpb?OAH
z&K&JHd%bjg=cS3X`2X)f2C~Gh$UvIdBXxU#@J`{*5AmC61?`6`v2D)Q{qJSg5`~3x
zg%&r;{Wh{oq}s20rWI1fuh7ICp8h=U#*1x+)U<hyzovq0FEu{SC6_Oi6^j!oKTgxl
z&=uNc<^i%Ie?`F_0{LA|wvyoMIlczYp)|{X;#gtEuqbifkc^f1Smnbub%}mmxP+H`
zXw{xvDxc74?fo4XI`P)*GDiQv7oEtLZY&YmHf~%>XZqPs=fGLfmZY#YB|*ttu6GN+
zDzYjkdAd6*N41MOuB|?qVV?TA0Z}x@FSfiXUq7;3@4OhT8r2X^C&&R`n*za1AsyK;
zywcjcZaa+ALD<z2(XrJ8U?#m|%0o$Yj*X+_!ark*lyxQ_4><>_{5vL~jy*RF#c7o8
z)!pEm10|6a-B$d@1_=Vab=M9$8fIpN&MCBD6pe=<9E;Q>)O^){spoR<whYQeGV_y_
z1aFr0-TXcF?kwf8)u~T!x>g6>xjz0f-sT3&H75)IGn>D7k5EUd=&nZfBMg$N{82gZ
zOYEn`J$&ZJ3F*=Ifj4ro^&=VPGmhzIJwc7Zo)d5J(?eGH<jqk@vE?VXvzyWFiJn?8
zVUQ#Ik87zEu$$#b=``-$Ilh`4>*sf?hJVRmX35~TG8K1+?x%ywjC<7v`zjnmI_qOy
z%b;Ly_xm6NCjS(~?*|pmD(Xxay?Rh)YJ{cd6RDheo=;2g2<gEF4dFk2r*~!7s6~D+
z>pwRcVtZ=lSh=|IpmX2?kU6MDGD~+Mf{yet|7_F;!`*Fm<0?NIO>#Nvc!F)NmIgPb
z=Vf2NehbTBUvD*ey7YrHUqhm;)q>k|xl26-7l<EUoK+I&eYHFq(ws)zU3zgS5%6H-
z>jJ-SQ7KB&+}9}o`5~$1-?eZRqdS^m_SWfm!mvxku}F=iI|SzM@*kw#<OuWgp4H(j
z81ioS>)(5A=w<H8;}^fW1ZqZWlEQ$~+lQ7jBRq%o3P|shZkjmYJeQMV{RVEsHI`wO
z<ya9$7uPUfRqXOIr*CBKbT+9AhK%oo<p)DfKXV;VJy=P;i9d+1y4$Y(tSsmZQeh*a
zs|ZujKq&L3>~EC`-^ji#|94XEqeb(^%I;KuT6`Z<Ft-$U=1lEzn(DPqYUzP4w#v-m
zFr)T2&V1d!Is{GByNi@`jD1rJG}rVtk1q|6>FWd6YnyMXD&4W;UYKX^Io<tZ(mK0@
zD$;*#=AkXMbojhcPhG<lE=5js|Lv9X1o@|v-ho~2vjv_p<b9EI3-X8e<%*vb>kl5F
z7tZ;+Xm=|LUO$fX&;=J2wRBhabYrXKZT_X~U~!<W=l$VLK2tA>&7eI&twOoX++S7%
z?L`4mtvdhJ9>P+ZQH%%HaT;vmHFb(xt7iC0_M}4l1<$lsa7CKzxRu5tih2cE_TJ>l
zq}BS7x|DMRNv)qlteKMu{CM8oaQpNI^Ra3+mTI@JEahKYw5K^nOw~~8a+W9wHYGQE
zQ-&eQIqGgi_QXohy`1?D)Ba(B?Xbl!|Eso$Lr@E^ZL+u(m7;5M@?0RChP!69=*XX8
zy~gm(Ufs}3tWUDIt}ie2;Phqg??UP979Rgsd-^zQ;qrCDgDG+=nX}&aCoXO7+C?L1
z{qR-J?XI6!lM++>IAFpkFK{|Bmt-dO*Ah}NnPQ#P@qBw3vMx8y%A;k#{6(aSJh3{c
zEM%gOjI9)Kvod^d&s6djGq%v%98qQ?9Z<9fKFEC-iodabwS%VM$;zG8tX2Jr^#;Q?
zr;jD-+-z3QcTnLKzv^M+W&E;yz*Ckzy~W4@-W85J(Zq%lJU`E?seXmBBh59gNlV`B
z%To;B;(_vQ`CnrUFG~E!l)J@`{RRT*Zi2)|Bs-~3K4W5XP?M4%VlFoXFQ=|+b~2P&
zy6;PydGT2lSt4t_KQYYOdS-rvn{$R1n{aG6$`QMRFqiG7<fT*1Vin}}-^9SJ+Z^t&
zr(6m`>;_(u6j}d-%0x7gzrIY^<xC!P?ep7940dK6+im$_L+_c*><A?<>0H$>1(c^4
z2B@|-Y~2(wMNS`7+jrS%lv?VwJy47J?(^E!j)@=fHTo8ed*|+_9}?b|UigD8Gx8q4
zmKkVIW07=sQQC6A#k+aEW#@|ojM3t+wr&zWiC?co?F?EKq0Vkr^7`jdS64ja5RFr(
zgliK`H}r2y6~D9hR_C7IY+AJ(j-mnoG?a4g@VHq6zSoDHP7O3PKWsaITB^7Sa4gtV
zF&wd8n7!rd*Dh{`8dw5%HO<av8aU5Q83t_wd%}YE%$V#HE%&JXK1pvoh}v=y`yVP-
zpmJE;bS7yQLUs532yXg5ll@`IjHS_(>zb|`p+Db-5!fZOvYcy0qK<+ETsXCtqz)#h
zY+J!JknM{<4ghr6tFt@<_J%#<SHGB-f8e9)!=G(oZfwihS=$DrCWJ;n^Wq<xMvD|9
zb@1l%3oDqjfKI_Crj)esMrq?6!O?2I{i*{6S2=qt`g<?X3m5%^_o!t_6u%tTR!vq-
zH`zdmFWocw>Y{)Fqn-0D2ce$*3UXNe-QX8t9zn4rh4)DAi(SL;a4(*`0s?+EqKW$T
z*wF7xG%<VBU+tI8%tM_wE}31<>7_!V!?pvD72aq(EqTxufcmidKSR~{Ii{Pe!+Eas
z(v=snUf52b+`<0fYjpo;G+Rk6T)yNQZ>>D--k?}K0qKiw#T1%ri!}ab-_v?Ikjd7M
zyKq=eH0;><u~|6k$=W`3L{_nw(&`|5C8OX<i7p?HmleSoG~hR>@5R}EaIv!HJx%h4
zgxVy_k-8dTTbsl74@ZuPFW%yN5M0WHsJF92qobz&5JlZ54ZH|a6l_}3Y+f}}zI@x_
z+8`k7s0nMxKlz;4yz=0qbGm!$ul2Uk$8`UBKJ-_nrMR}QyIAR_hB#0CqZ-wzCQMyI
zH~U8K+I|ny9s3PB?LtMxVH9@6oc7|wuuu?FmyoDtm;uR(<C?Ll#>~t!-M<i$7L!xo
z4St%1ie9~p=3y01dkQ~@Dj!NI2`q~vX$|gZPHOju;i~1#ns<F2b2u^NoFOg2i!GXM
zj|nfZi%fd24QUpWejLIHb<pP76HIdOsWhq>7NF~}6{(|W9`Rb1ht^@JzR{GuHn736
zDJ}k%@Z-3mN15;1Y?7+9*51hd<)O!mkiD371RN!&p5Dr9cT;ps9qzu=IhX4~H4Qqa
z2-S*XUzNK1jE?>^?YeWcY(o^Ti+{kNhoLQ%m}kAzEPWB=px#xZTD^R~<1v-L-0E=c
zT_2TQG!4b3cWS?9397Z5MuXGq1}gn`*?y)T6H^`BAMgJb=_;+YC(=|W==eBr92aAS
ztvdCXs`)l^UDr>i>gCM%bNwA>baB>o(Wc}d*^i7G7WG@VOx}EO@a1LQFE?x0amD-{
z(QDbU9g02~n`xZA2Wf=3r?*PluMgVoB96D5RTL~fe7mSs3pY)QHD$OHln<DesE(b{
zJ9XW#b1dX{z{{M0lDX~Ic$I@xC&#7Czz2HFh^hmhkDYcJH$H9^IZ%WqCKT;%@f*Z&
znzH(h8a!mKe;%kWOTTzUc9&>MtNg$t`pheIxO1eEsrm38s`vtc(;UB~C<w~1Cb*}Y
zN!h&j?>G*=sy4N-7mz*WXxp1QIBY?FbZGyKzv5u_#JDfv_Ybs4Ic%1oHDX``&e}Fv
zKWQiJhC<7`M^R|e_N7gZLr&o0qO5eQ9mKPKUc<Wr;hM)2jqxGB7s-m0g$e?1jn=CR
z4N8;)l%klIyBu|HV2mK5*-d!?H&*ol?MCnAGr9wx*Em1wrcAkx6m-3-Gs>GOM=x-R
zY&mZ^`~Y~q0@<(e1?t?XIC7(!l0f>bWzmm+a8VuMN~G7dC&qrZecJr_Runm`ub}H&
zQvn@__d7+_9<vx`N?zZ3YnhI@<2!KHQOQ2QyT-+qH;?2L1tGakjWuDX3*;D+rvr~?
zA90~Xg$=9zZXp>DXUK1JjVwQAISi#FFKnQSkHpUspet4O(8e@g$G9oa;pVF57TxH5
z{Pr2qc)T?>!g$tHgOEkQi;~mak7k56W>%b{tG@Dd_!Ny{WH(|MIvp14zt3z4ckT<R
za>Pv(P54VkDYm{zm>$loow+3(eZFd-wYcDcpDDr%|9&=S?#$qLYju={kH+=FO?`X4
z7P0jY`RK0z3)*vlR>&bxE-q%pwh`W_Z_YF(D{Y#c-=Nc8*r?rd-<u|%zUwUid*u9M
z&y6R_Vk69yvDe3w9P!f~uBS=b7LO}UWdjN(mKg*e*$mUFC|I4Xx)>|3UB&iQ9dsL1
z38>R&-gUS~@$4RYNEKIfJ5F;bI}dzUkI!OE@}3?%TSB*fb1FS`AuehQwRA^!%r+J-
z>1<e&jCet5%x&>(LFsy1?d>-2%iRcJ%D27m+K4DK{Q@P=)L^=>v7n;gS=VEW`Fb1B
z>K(Wi?9kkpp?bDq5}oY07^{et`|hJUXg4SqaAgtqaO~H>ul(;Gt#5yiOPFZ(%-d;P
z^MurQu-%lNl>byKBNwqd{q^oNyYC08j@j&KPua%WoD?MdAtP2RJL?9Swz<25y1hGV
zv+aIDPmynbe``m?nJizUp-<}>X?#^7rnBfvv@;%uAXg<AcsE&}8e9{)=)etZh3?nM
z!uMxr49;Tv4`r*STQ^15$AC0G_Sjd3>z?wqoH`ntyPL*I#u&{TfAFUM%Q1J4Q55A|
zV7nYY#%f@t;+3I*)@yF2uG?TnZ**On+}`@C;vL;FS5Yeii;J>@GfeyQDu*qZXN8Tx
zZ#hM?R7Ftaz0BcbNtmnW4|naUfl80el><xtInp6?>#Hk*!xz9Sq}77yyQA}Rk&kl5
zMe9!96Z!BtjI#w1YTO{7?Kx?L-p6TAPA&pclTY&slb;2iRdmVRHf&*a8}=?L)k+|z
zWqc>lTUf1mn6=nSEwbt!vm}mFu52w!<Vww5-P>BMzr=5`9b+<dt<!stcYHU<#HjvK
zn&?2sa6(TVsb0d|c^>QAw{>LEbqwF&@Qmk}0n>Nd#NX~-*&%`~!&(}I4fRiXk9{}b
z=B395xZOmD#~8|&P0uUma9_UFF%4ZYahcaV8Cma-GWgKQxG|+DIQt7|ZOgGo5Zbj)
zzZeVq4W-A{uDiqw=`vNR9r~cdaHUl{_OA@k;<7&kZU0tT<zSn+H&UJJajcJ16D2ER
z+GdQOYMn0>m|Hg)?Jga*SH=s6XJw{M)z4miqElM^fpy@(?{;^idECg~XJ*UD5uFp*
z=c*3kR5dL%BISg;X@qOfC`J=3G|rPGjxDtsjU7Mb-!_{v)}!)?`8&hhr10`;FOGCf
zp0&>auRSeOS#UD0)Gs)8jym_L#!uRk1hy_;7VFpNKC<W=;k8?|-Kxp4JBrlO(ec12
zf?q;!<KljD``19L@>SBu(}EKw7c4v|lnNnK-=AKAvqlO6(p+ben!bGKHonilGKNwO
z9_5>K$`glrI1^(Hj7??REHhsV?`aTh-=#U_ALB^hrCT3d5OhM(VQhR3&eJ@P;q3TE
z1?Rc8`{Wk=yR6jmoozB!%pZ(~*}B|cu`|DH#8&4nm^6u7G*mU78g0IxzQYyNdxxif
zY<=wYBXJm`w0C1lzki-ni?O<2rS~}2<D8X$pI_*ry4Y`PD^k+>BR;p|tSf#{`c-Gf
z+fq#?M!s6kbfv<fy1wK^;MuRvy32hxz0m85DP8|%Y-Zx^D$8Hom@zmBoQG~gN1&Te
z&`r)%#D^rp=E2u$$IsoJ5$h&;-YrXFiKZXC&i%;NR=u1xfj-!reeI;GpeouZEo=WJ
zM%wW$a>VV4@7+}`FNQa^_jDWQs9v&+_OYKFyOIq>a#Lowy0r&#(gT?j6Hj__x7IwC
zr#okA`HEP#XQq;u^EjO|M6(vfun7wfwYl7%W*rxCww`KEwpM<9<j}=mC0xDGCck0g
ztgGHoIvjo0*3~xTL`Jqq@5wsWAXDa&xzLw>k+*<7JpaLj{8(EmPKW0Gv+$i&zpAFy
zl1RA`rzVy5lo!h6H%Uvar`r|QF<(;#9eoVzYF&RtQrhQ!@c@oU53N^y-+#M7!`bmb
z77yR%MlJQ6tdwJI&y|{@y^;yPUU=4MJm_t;u2%mxi_s);57eF)z4}y;<SsjL>WA>3
zS3LD2i(X1;KO&jRxXeg%=5mEix~AdVHYs<<&I})FSifdTpbUPn^IVdR`7Py;0shp_
znYf7?4;f=Un$H;n_I;ba?5(^HC<d9c&75yD%UoDz(s-F2mN7^~6`>6KO7Xzi#zj3F
zv!E1#K2dX=s@oOu_RZH5Y4EYCN+E|&=tWM{jqoGpmd+iif6{yQ1Y7=XBzrXIEKgC@
zY3eq)^D(Y%OwhRUh_YU84l6urFE^6g&zTjKHlQePmy+x-RY)0c@F5(y*JU&?c;4}?
zYmD{cGuSyf6IuuU@z-{JkTJB5&8ThAqgwq6Am>grsy~s-4yik71^1rTbIk^cHY#IR
zQ#y;YRi+v!<1D)|=!icsl;GIW5TgSfeR(i3#z<^3HQa~o*-NL~H&PTxq4ROwX`zc*
zj?~hmcgp0pq`TN(+#<gx#xpg#Q4?Ilyb<w~N4dcMZ5*ut=DERnW}v~zt?C#(7rR}^
z7qX4^(^N5D%6eTn^{3&Y-s9*%dwrBv-zxoTm%G{`7G<Jde(d1AE-9g?)@M=t=4aPE
zRMVWMBJlhD7r4?hL<?o6_rxNBXaz-9o*GXS&W6<aY@{d%3^$k!p0r66rloY=`spCH
zp-j|NUte?39zNI<Uvk`|v24chFZQ;ehrEYL>)Tkv_W?<mP-^I<Car&ubz*uBFcJWa
zr132DtCzpgpK|o?5|wzDk%lHd9$Yl{e2Y)CE1l9N-gEmMo9<)t?lj|LG=^2I$5~;0
z=4An{J12B;ZQ%5lzv86z9JH$@uFvh!@Rt|gHZCXilXf1`tlQce6wRSizFXxfcaYe_
zx`$tI?tnk29R2ipoxc@BL7=j)5QK0T$-mo~pI`rS2>*Qgkg!g8qtGhnM5D0cIWN=L
zi2Z#KMc2T*^RjsZV37Bic?GoG7e=_g{7_An5w$et+gfr{k~+4(+gyK$oWQu?Qs92+
z-F!XIN?5;?3aveEl`@c8w9tD>j3&Mwov)B_ElOs>o<^V*$2v|1-O1I~&OMq@@bktq
z-g$#7ueWXWZ4^Gq;c?dZ{2iFN#|De@d=x2l$LC(>#i)H;(LS>wgy|P|J1>75Hkr7v
zzbxR`KG#bJ4quZlbeS@^x7%M?6%v&OPH>U(HtfP`^`<Tx(jih}w>~bzh@hD%?A*$-
z+>}^@#mDe{*){uD5wb7NTd?-@QZ{3!^q*n9qVNTG`*9iJuI2V*zmpl$<HR1z9960n
zUa-x&rz<%lJY4H4xudGBjqdtrzhIx5{%S9;05)T5-PNi=1-gdUCi#K8TjWK*^a{#1
z=`>hP4Gq^3w!^9{=O&QrSWB_PgXYU76;#S<T#OFA?0c`b!@0J?k4}jQ-M6?B$;Eo(
zQB0e@+r#kaD{0phq(r={zVQ76EA>XL_e2)6emS3;5~b5~Gqzev6dTO_{FwAvj>hoX
zdNEEj^&cTCLFwLlt61K0-m2d_Rx=G=)<%9T9ntwlpjx>J9ISi0&ZZN?`+86BkoO#>
z-|$n=zJB@4-g`1z=+kHS7Hkab+Eccb_-r7@8&GcFxZpKaPo+<!UFxw}4cdz^${ZQ4
zaKKuPhFTO=8b-1WOfMS7Z@c?s@GQ=G=KjK6CwUHcNC|gBORoOq{@c%1J?plUY2*1f
zS1tU0ThD0Ghuy~lf2TxcG(3#0PPEo1eo=lxDwC`8X+1IbI&ROs3A=Y+cI*U~k8kMi
zpN~QZF$~ipo<S!rK|RyNWPYWfkoo)`|91$`zmBcG@8A>hDe?*F^@X~VzfR0qU`xxM
zkbgV!mwx-twIlH}$m(TjbF@1;6JDKUocIQx-bZ_yMQNE`VFN#(-fK9l8|;(s`RM7$
zp-qox&C)l|BMm=4S67#AE7Xg0A#_>Y!7}C72zZ*EOA?+(v9n~<xgP{(BdctZdRv}*
zZz=4w>F_*Qb|9wb)fx8%3tR^uki07$?`2!Y^K4g_9QItsjNj-maqMp5E?U<|&evSA
z)#DIWV&SIpIno0eY+sXGiFwtwho!1E(aqMT?O9x0-(9l8R^y{NCq{e*$xlfbihi{!
za2@Xpnn)LGN7l0HH;wg$=XPn{nTk48=3LqHn(RJr|H)mwedXO{c0Y^jKBe3Jp8L&R
z*GXBI>ni6O>1~ze|Iuysrj6JPdgXQNUtK5D$!AKhi{i%bh&H>G?d$9*j&iSm#=p7y
zQ#rFaVa}tCAzf<boy!Z~*P@A+UM&jTz-vSk@2f;iT+Pf46Z{z3*RI(S{oOY}xLNrD
zUpm;nrrgKt(xl$ePMpTQo0iFW!)`%l`D1Eaf7=Y~J5g_E{C!b?Nq1w^+CmKL%Q3gi
z!Qm&h)|Q?Z$@;oqL&qL@-d`g0#2KDw9KD=9S;Z7>-o9t?Yhw%ZOj*}AYKj8s-Sw@0
zU*4S0w+amX(V#E3%74yEEZB#yD|pdzG0*knuGSm0;l;18tqD)pZ%UMIy1H$^+4HmK
zOgv{9)YmPAjM9m!qPzaDniDLFY1g_EtSu*tGJV1XUx!@y4QHHgIvdqxO%yE2HSvp>
z>%yOft6h85bijFfCq>r`N6Xap5GDlKHTxB6hK5SbVp&F>84a>w@%rv|ro?FwDu2Bu
zCCj-yjZ0%c;VbSflkvPA_-@eUWM}QY;kALMsHG*ZJ|wRDJ=oNcUbv~hzj8++?+Q>Q
z6eCp6E~kBa!nb%xdc-QK33>9W?p^v$j$2y`ni%LGqJ8Ak(8~f#erQv3wTl+p#Ax6`
z#2KMp!u{h?uX7G_hCPMPOiP570Nn;u4Q_2*G||W3N!$C2l&OTOrFwoE+ZL#52tak`
z#IF-ypYTPGNm9?(j5Avtj<q}FcCHOPV~iH{{B*%%%wBvBy}I76vAD04?Hi%{ed>W>
zM2MODhdhmk?mzB)%|FaB$|XH2-k|!a;8|d9egAbc#zl-SBp$eOmU4X4x>tIuJPrFn
z%xjpo&gbv-5d97)%5^o`ck`oAZ(C(K<0;Q&QS^_)QP(0ZGp!p+A?wA%#33|wNvvc*
z{}^5NaE@VAn3+2#&-GzR$34A0Ky;ob(!I9IJL($IGE=9aG-3`HYf>AMw!XUY6|c0x
zKUSCBpYu2>XqI3pz2RcG@??}L+X*{=m?>U8e8#$`p|m+wj|rACK@vH1Zj@gfLfai*
zdm+G0{J=p!Oz1mVav?rSxcXO~r&is@zR4gLN1k%3$9>m>g~mI|yISqG(~?FDnR$UX
z17Fkz=Pa@N@uJ(WyYPc5FKCY|;|1kZ(X?y9z6_r25|7Gq-OWOA>$O!rq-#NzcRxk6
zJyH+^9MZS=mRjj|Ftn|=@I%r^n+JLL9}JU?IN|E$4?LAgCmYAoU0C0atU*7|yWG6$
zm&eF}EsaqBf7-jwh9;V5y$FIz6H)09MMXg=(mN3qk){G-p$do!N(n7=gMuhR1QewA
z5|DtXC|ywqH6Vs2RU##n&_XYFHoWh>|KNUlzh!pMJm<`rGc&uJndhi96o&}jZAxFT
zthWfbGOuj0Sru^b#y(PhXX>5NJP<AmCPw=(iL0i7m^(_+r<5D;eS@qZe;2Ywl_TWI
zN&=mU>_Vlh$h<Lk+V8cSk2FlA$c2lm_E*>iG_`0Q3lZ|Rp06LO=ENinZ0?yijL%W(
zea86k21;SEZ@iu?)Iq{iq{?(I(0aG_tA;h_*o-W%yuI@M^4apn4@t%w2Glo9Xpt6K
z!AFEwmR4}3iF!LwNs7V~a`I(_o`B-L?9QUOg~0tW#Z}FPXCICo^zSIoOGOYR=X=&O
z{4pahm3~e-wuV$CY(9&zEn7RYS(m!WRhgL=Y_HL^T&Ykl`=WJ9yu<Sv$l3h+0NLV$
zkxK=aj*ov!Pn%bX$Sar2X4M&k@i~_Z-`S5L&xRotl}S#!?=A&y5x4VB|JL1YNqcl!
zoDeEL-|e|)zjXE9i-Hu=aR=?O{($p~rz|!j2F`-iG)2WBByC$K?HLEkOTU4yBHLq0
zjqj68e_2pFnb0f@9SL`8iY+bN6cz`lEZ>EHlBm-UjagP%FDGiB=pni*^q}ka4SXs^
za2`N)l`DfK(b_XQT(LV}uQg;wHNa}<h{fiKL61^IsP>eDrR%`e@rfmuLXe9&IH-JJ
z6F7bDh2I}&Z`|+G;4e)|R7u+Un?WAWOJ>#mocqbA8$w18jR{!@e$hHP|0rI{mvujR
zV%Mlbi+4ulXR_0H^_bU>#CDR@hAoq_-upE4546sQ$=E#?2K0X0JF}NCt>$rE@2ZOq
z$}^DbbHTq;y1mbHGx?cp*&2sS48lQIK@P7({apC*SXC4`>AO__G{`}w1U|;AC?ub6
zcFG>E^S$5DbFG-_C704p>cVjEC}}{~b8!v3JUL3u=<+cHtJw3nZu469mBy%&EW0sh
zN41Q6=Y3;)+}_w}FFap}a6rCxc@1Q}--;m!#uu6$KT$_2<cK$!`5VueZ11tWubiGQ
z#hJ7BANfZX3}>)fuRwN$=8<(i^2l~5VT=tMbl<=WolNwrf6efh&0d|Pi7_h_X(#bK
zXN7IbK>v7L`ealuQ0I9?D8*EGP!1Vz=LxBJPN$~8)5SI3$p6Pb^{O#ulEUpIvv9{k
zmM^U0+$FHjykup}Hm>bd1^ZLw^o%VNMp1(<Hd@NsH;rh-q1Sq1?zE31;>gx0r+c6e
z4J2mHX~u(7APvM^OY-pEc{Q1i-rB7D8q2$Rm}6vPXeQenmY?0vnGIf$<feDx@v(lU
zqs~;>D`X)PsrhjxbbKy)dbm+8Wn*K3v5~LQ2N$?U%3LWmA1}tvr0huVO2wGA7i$#<
z(Nz?A;Ut6+w>;j${OuS@BxOs?J7X<$_S-6B*;?z*bJ&s-0`X>vUZxo5zsu=_4pXVQ
zaX?I^wQ0xc@g53`?=);RTIey-+!VWZ@qIEy<eP*8=Qzbt9~_B{pMsn7_eE78UJIL(
zZ}|uOmvzi_p;wm@B;_}I-dOPy#p;`c7;%hJZXf|#PZxi>ui8;c59^R`ISj-F$8;>t
zc+{9_pp)|iZqtm0UmK61XdXF9Aig}|_$u62eSP8lD_FdE@BBfYix!fonrMR`?@YE2
zTPmZ}%&Z>o+T+$~r?Y@rm<d{ukOM?N?<u>5Z(CzI7o0uv3tv`?1pB4483<CHj9tY@
z)lbbLM2Mu)^!=Db`JVQQKNY@FE*7Ilk;w%<k3*MK3H2bC4)-BKmQ7ca0M*^tRg|O|
zV#bluN>a??g{%Cmct3-Vb(KF6g&>+%R%s`kBydI+l__jhDNHeBvU^qKeU7A9)k?4!
zjZvD6V<wSRHSDhiN;1&)VIz_w2lO=pBh^f4^Be})`f{cJtC3PGQExa#VKoKkHDSMg
z=>bamvzlKYjRh$)q^RKEs)`r2!dks9V+qfH=WfYYxR1LOR@wjHA{R77jJ`$_%VYA-
z*nTk~M{T51NJ4KBoL=ZY+Rux=_9srnm%ci*&2OpdqGV=OadfZSVSAm0ZwJRL8qd7p
zGna7F4bZ1iz+W9Y<r*_S_cJQba?2X@)jSAfcb*byCB+tB!6aS)t~%R|jz!tp-{N^;
z9wl<M@-yQ)H+gzBTD|ksflM2qDg>yy8~^$7>n;9)9@WGbh4%O1V9Y{i%~UjfNpzDn
zdtv^Dns530aSJ#wpmQUhpM9h-R-spdTc*9@Wx-<CY-{UqVxYvNK8VTN@n&U-Udmlp
z-n5yJ-}@QUdL#6(^$+;GDnGPazI_%p`q1umbx5fKakNdf2aveKdXBGE=#{y>FI)mX
zb2gEh27i9!X1jLj2~58Zd&bwG7M+qg+ci7T*&~Ra7I=zqF!&^gmrL~0E!FcrLFfP#
ziokB5Pp(}}{L@)s`^iTr0qg<;A}te&Uk|_@_*vny0u<<d1KF3eeC$JM`^ha6Q5xOD
z+?lRJq@T>b_l3`0JWC`y<gLp)dHc%on6vwS7ADU>%>&Mxo%yWyMd{n|=W2iwJK{2y
z<$;j*#}8jE<5`fx=~G=re_I;N{q^)k2{&WTv`AnQ=fF@Rv8swAg>%sVfP;N<IIG(1
zE-@5MNG1~DaP^a%rh0!E*zpJW6LDQ0CScFhSFXbsF0R+S$a+cZl{>$CRWLdwd%UY?
z`Y%AY(mw{HSLP;_Cn6m7Vbm_r-gAgc6I8=J$C>Vnco%;twu}$KrZvm1-hUpz{@YTp
znY3JQP7iu7Zd9zV*T4@ymGf80d^j_YD;TxQH8qZZ*_VEbg@)V3HxP{%9J}Xe)*vQN
zfLW{YP4b1=hYu4F4u>&nNLqTtgbYETDXaD#iy`*e<E}=5sVpN7&?hA++2pRGv4t<@
z{)Y_2fPLx~k}Ld&&tYXbk-~*Oy7k8hw%@}mOa^X9`MVJ=Wxw4}J5(KFk<$8?!s@7j
zY)zk<P%G}ruL54+B7ep4xa(uo&bJXHjz`dbis^*gCHD}GXC1qj-6hQiAApCx(~Zeh
zi1|*rlgL*6gXjVZO)wh4$t5>`In1_lv4KnUt;15s!3|yxZ?)KbYL&$vFjkD5UsNDk
zz-CCWCoj)Oz8>V`5fQN2u6o9g&ibBaxki5Ws#$jZ{@ONggtro?RqIc$wSB;o9h@|8
zbvlSnq<n<c>{pmS2h=Qm<zjq$cWJ?WTSjo+1=tm}4#FhAlhv#E&l`>}(~vC}*#;Nu
zcF71i(0N8ZMAa^siKEi+&lSAC%Xh8px0`B}fo%0^f=wi|F@LJ%Ne2yWYzfYnI<ch3
zF3pM*&hj}PdW`UUH%F!ZD7}u--M5?P>2;EuNQ#tgpOijdLq9M8u9o(6OfU0TyFFLC
zNK@eeS=LyEd|x-evRoeua@Chz4^!FZ<?vC9^)=7xuoMr~K@e{K3imCWj^EW6i-^2Z
z`CR(|`Q4p*%VQpyu^LKu1WTF&va2*hGK7hLD{gzlb~S!22Ck4_N`CbDB_uJwOkgyT
z`h!gl_FFkBf=6QhuVROOV0xiuNG+&1E8$7yX-Y%BJWLK8^E>UQppUhx@`Tis-jd@t
zUQiAJM>-!=UzwR_@tFt~t&{mWl{2|!t28xd%~AHytkR4_<J*4ZR>hvjB5YKUn~T+q
zHK_I&I)OqH=&(Zu*acZM9rd2t^xz%O;*8*}XX;2PoWu_o)d#Q6zbmI0%s0+hPh$LR
z`EF_Qb6ncoZgO8@X4tP4rI>43f!sTPVmO#88JO4w8p}IE45&)34jB<P8s(0q;$rK$
zRJEysWF4MAKSOKz&Lph$2^>z1E&<E@cCKYP(tqE4_JawTf#L(l0%rUFaxV6cT@1g2
znK0^_>vH)v(olgG!TVU4yDD7%6TI>BR^p1^o;e5O6u+mt!vDBOInImVcpjNxDlTjc
zl{blue<Z%-{Q(<4f**cTpRw9uQAuIvvXMak#8mjpOI|-TrMw!#6!+{{b*4|x#p474
zyYQ+Kj**I`FI*YCfolu2b@{}rn<|$UGz{*%Q1e!Q?-QP&y19?(Gna0FB`uzP5``^2
zuNOHN5ra6DK|LLq$fK!fcd*tdu<B8Dh%s)E1wD|hr-gMWycFqUt1xEe3P~tik(<QO
zv?z8xtkoO2jjH)j^c+h2qRhtP*d)zSDQC?eJ7Mtq0}FaS-u;0ZGwQE8a}6g?l;6Y&
zyd~as?|f5K$e?Mcjpark78$OwDYUpI55An9BhcRa-U2keIQIgrva<QYT|;|x11{1Y
zyqwg-DxTMiW#EiP+^nVIYER<*othCBQ?@u%Hu(*40Y~h7+s^~S`ujF(o<|=SR$`%h
z?pXxtTQW&PMjjb(wRg6hBHidHA|U&$J*PTYqdKGnH^{eIwRr6|cKLSv%#j9Ho<SAJ
zt}KQeZHlG|4qDn_K?a5buP>iYL{#T&$XIT4$6aO9SXXynl~26BX*n@$toM-#J^164
zu0cTg#v_JQ0_m8@vBvzI$lD+RD|3Tjpr%lr_nfWmMVXbw<+hP}uulTq%xPX*_rZEu
zC8r;-ApBisfwaq#$qlAkfjEZ{?JDNgq3z~1UaqK3rX+XX;U7jX`F^xT59(|=4?k}<
zBVH0d;N*OHfCU}7d$pjz#5wctafTYZ_~#oBVno)*DS5*XGT_3N=wiD~5Raz(-Gib;
zf3b<`r+S!jFY9WGQ=lPp;~Z7o*i-nSGdSy>Dc`_tYQ$ci%{sq!l)A{K?#?^#k&~VO
zM~(5I9>r+*Jw<<JLg$N6TuhqJMtN_i(1jW_XUzdzxvw_uSJB7?td;W{Nm0pGYy{`4
z!us(-|9frHAxWzN^8tI$;6%URw^i2g_5vBTA|~}NVltsBP=0>v3_HoV_EQ2g`dX-a
zV7R$@i06cMMxD%f#d6Go_C3=iLM3f``Td2wM}JQ~)=`8ijQjfqa5*7oFdLsS^#qdb
zy;u#o2Z9-fewuvM!4T<jpA{|K$}H(;=+k5(<f7~0<(!+$Kae0rc=5bq^pqQoxA!$C
zyFh&|_n^@t5pmH&C^k2FaT2Gu9yxBz3w<;7TJ|N$*51a0W633pd~SmW^ZcKgSk!s`
z)vm3Rp)@aZFG}pW-d}eCm$RwT!Vc+x3L(JHFWV3z;CP+$!&gY*qsFnt7AtL^UBgut
zHoq_4_&_-;X{<iSE~f|yn(UY#3r<8@2-}38o;v%9RfJzL!X~FGq5I^EYyCf-;&Q6K
zhK(4Y7>hnpW(KaP%U8^vB~ZcPvXtkqG(<JG*}~Ssr#C{GBW!==QN<)$dri#19|H}}
z`@NxEHI@G~z|4zdUR3?3!*>HBHnXFxHSocZ7IV^Cgo;V;Zjym{fzO%%lkj6e;6UoH
zO!IlLGBt|aQqWxsm!t3<Smf`WFnTFSNJR}^9W+<Pl|2LBm20YUgE^o#raSgKEOX9}
zot%*UW??3#WQZ?L+WJL!9ImpuX+rD!L=hI&q8-@a^2la@QcQLn8r=m>Aly`8Upp7;
z&fjyDXH3zsv^Z(=SKDJYl~p0rt^r4qyc%Y!L>T4H0EPbJ)UQXu__YqTNF0>jtn*wl
z)@C_7N?!h@xgL=lF)TxFaVGHXhCbxa&|?T}h5Pnng1y7lMNCuP6A^3}sDp0rN>_QR
z;~Fs9OB9Au^LO020ZwL1Dd^=OBUK7B3Jo45CTFOw<`pyYxo@dHkDS;;I-(XaX#CSJ
z7lMLuGc(Iz9E#it_WN~|DpwFJ+4?Z9uvT?B?<<gJP!TTxy7|<i>S~!FUdx?e1Jn(b
z7KuGd{`FoI+YFtvlmm;#NdtIOo!J|`t=y2c-;T?@Maau*4xOs(lg}I%_;VK^BY&sG
zOCc6d9^pFHKT?>44VoVBf|^sy$`wtF*fAA&#}5A7WxxaCv;w4_?nptxL>l*QC{EkM
ztJ+Lmwkbgte5ESvD)O{QAZhi7dXE~{>YSZA>rOXdjQXrlL>#I)xHDi+KMF%o<#GO9
zcjXPYk0h`BT6txsVY_-u_!?|&JvFXS7ziKxM|k=n)@t&lWvwvEq+GJ)ekw*rc;i>%
zt796rn|F3<<WO@Z1y4aW`v26>$1c0yHyo)D=}x(Rd977qWZ(LHV&tRka1Khkub#(B
z1ZDo~E=WIJrCia}s1*ltPM|U-6>vha*>bH3SJg|e{fwRA6tyjz*C-2+kIdUUqfQ!D
z#no!EL)Nzd-DjSUTj!z%L29>7scWP%PRQ)8T<Z&l%6nOv&Xw<(ZLEa1+iCgeE6bf4
znJRud9>Y37S58?Otm`=wTGQ-=T<chS#r>=){IrUdu88_KH{o9&OE~j62CvF*+<=0@
zOw5+EDGfJ?VBh7#E2@S1_u`1b=&s8>gTGN#Q5wEa{;J^|?uwWRRb@O_DTW}~yoebg
zQb!3da-ik)YWM<Lj(Y3Vy05R{jYbE~_sJ}@=BW`}t=A3q>cfz=IH{#F!^h{%d-&K_
z#_!Leg1<hocJPfYSPy)<w#2iXSR5WHY^Tmi;q7rS@uC*p3OEDRnBx+Bb!dyH&tsR}
zY!n#%`J30TU*7stXnc6PedP4G%qIUjU`rFa-h>AcVc>zH<|ZfG@0quhY`&Xn6bv4M
z{4e)GkZ7dtd8EnZ9;-f7;~!0*)ZOaYwst93`zvc7tbT-`jy%H|3ljH-klkS4bDV-j
zT=ON+?3Bw5R(&3=>6$(ThtxBzY*ViNE6<ISq|5ID`!Sz>VWY{#y)<du{8JTuc%!}c
z-2_Abf%U}yHR_s&D;1ZVx(+g(u>NRw>=p~@e0V9L)yTe}zSt@28imIz`9pW4u(JW@
zxM{bT>Aww6#0C3W(b)Qv5Y#^#`pmw9&DX`V0$c}gvTlwa;i0_@t(gSkuXj_&>3%A}
z1+NEDPL;_c2WnTt!k47uT1*-@{<L-+UTqI9q&R|2MW>30;;aMhA2)76L1@$EB?gkQ
zyKO1w{3Fp`w}7J=>TGvqU!Sf1yzt?N|6&oK1=Sw%*f&+ui1Bhi19#tDQl-BZ?O;FH
z=rXjS7UIj>a#!3wz;z7Gx<39mmX-w!I@s+144S<aAPLS=;!x|)D9UAkx`nzSSLe&y
zN*5mtd$BfN+(mmGT16M9&FqNx0dXuvw=AQa1zpNe=@oF8TP@r{_Vt14(uL;T{)^+R
z>)*5o=?3|Dc^g#oK-O-gkN%fv$NGtPu_;Coh8f8x2}VXX5t@v>_p?4wr`5e=MAU10
z1D4vnEaulL-VX>_c2Gf(Sb97Zxu&k`g<3#R6_V>*v)5(Qldd<e_0B}|%(tUX&xmpQ
zcOAzQB_{iaKW<t>K@%VYgAA#}T?*s(#3tL9_otymmcR2@59{i<?)Bwp(2%IEvDdVj
z@!kL_KvZE;zl0=pxQl`<`}aof^V_j-W&nc<@YCv#xkQqbtImV2IF2_0@a^(jmf*B*
z?xX2oT+W2Tj1ajp1m*uENsY}(?9KbCPs@VLe%>?Cg4#jL*eZ>8r@iYtR~!LLTZYO<
zaDp)>VL$n4?c|t^lWK9y;=BHw;?0q0mbkIBxw1vteftL051m%55co?r&)<Zm){jBp
z`EQ$X*8UCylf|?~^ckx*`yjNi1YXZN#q@QBcKMnpIPROb11-?aG2ii{-JuP+ZCE%^
zduma-GYKT>`nlENGbgalE={x@_1HUAf{XXE>spck+$2EB4chq@L+mo|r7xO{123||
zsi))mmZXTnHp%s^lkHtOrWdG1D$~~?Ye`a?zd236<zXvA#9Ge5A-glhmHOk_H?!-_
zt~I4%kpP`S8=vgJm3duC@)U=pGbn8ug+AHf3@<8F`kCekK!1WSh#LuVHiFUn=;$A*
z-YO4`;c0RQeX<p4sfn@K;9IdgecaFf$7vluUkb#ne%LA!_)<KOrQ?3&E(n#+G0lz3
zd2kJ*hGG(W7&%Scc9nW_mf1wQiEA)frRIEOdshbDC|`W&m3uEZA-sW;T@R;xiT@b`
zb^uwo8tRu#w`*(=Rf~T)Xiby|&P{(2ZC*GSV6ksKGo4xZBEDrW)OX(FZpu}4Gw$BK
zAcs`DeKTg`X|3pXc}K9kq05N%(JFPXC+Orqc$F%vQ<Nc@#oo72O_GVj5+4aAFN921
z#st*)zVH2d-p_YtPlw;W8p>Kg+Oa30ZH~8hL0-ldJ!2-sPID&o=$<vcnT7`}-1F0U
zz=k}A{K@sFQHLeF9vba}N==05a{71K<{6k#Znx&ym+VLxVQX6zT%)Uk7}Dyd=>-m+
z$<iZ$KmZppg~B;F3S-nf_EfSh+5OGfE1=c8XTdM*D`jgd9q~+$_WLCSp1O3Flu0G>
ztjJ`QCyuRwO*f3LYsP=(vU@4r(j{ClLzP++b4?4l%>{j~rqpTV`&4Cv&)K0a4NviW
zl!iadC=a>Eq6Gds@jM1Mz;RxW$Uoxh%SWK15XyI0_(Ty8S<E-19;?IK+;FK(?dfKU
z+}hsD7rB)%1xK>c?N3PzTQ`@bCEHQlyCBv)LlBK)j^41%ITq{LX~Jh*q<M6>l`#b}
zchNl|q}^M(V`mH7yjXWZdU=vl9XK&37g%_tWgz*h@SUI|nQSsGlNtqvvkv~hKbKei
z=7ers@vs3Wb8SVr$$8qm4`-Ixmw0KS1U}pNu9r8GhKOrRu2z+bB2ZB_rA7nqQ&%T%
zg^iSsLq(shs}Pdwj%Jg75+jq1?g%5XZ)G|jS^nia#sIPAb4)GZ9GpxrYF=!?`n|5f
z>IB}5XCiiQO5fcO8je&s;ikD+Dg=S&;Hs)rpT@dlgc6;r8a88WOVYOCM+2}o2bS)5
zJkg}YH6$$#qQDY-;>(Hc2Z{tD>Ec$94qx*ZLtOm31!mvmBg|Zy1UYI#aoIPKMb^KP
z`#c4qnovqbRk}}Wh$umo6KCz7V~&n#*5SXizui{9<kd^kp{>;0;$ByZ`XOj5w{=ni
zH|8Xbsj%}tq^&yo%gxKXfFWeR`uFp<CvGGS2QEJU>$KaK9U6+JlvQQ={0upJ8yhM2
zrbP5Kf17Sjr|R}z7T$A<`xl&+Z9PJ_JH=w74>`#}U{}uMS`<ZB;2GcmCX}TmdOfII
zNI?Z1InOCW^gMUnYsK0Bxw7$BNk+&!zpN0Sm;CYSo_Vs(^@u-F#*;~!V>Hn{B6pIL
z!V5U&tjgq2@fab%VE3-<ofIzllZ^ghvgpgd*@o}DLUr+5TSE+Yd-WP9`?s@n6vR$-
zTLIEDlTz9RQilR&6Comw(cy10NOG*%_*b^2fpTCwPg^PHWVbm4-gD@(*PROyny<wg
zY`^3iqxx(+b*vWa_OgCRi6NcZ(hg7&JK22`u*3jdQ_{lqsXDN67O$+>uv((A7O&W9
zmdbeZX8#|NpCih*z83C+l<;K*Qu)cBuK@<jRs*-K51duxcO8euZPipC-V_=c^avZ5
z-tD^&8cL_UuPX5Qv(MlVId<36=+;)ZwSvgXKd>w@RYClHS>3kTRyqU~;C2Ad!hk^N
z0}yKII5gJgo$t8e3<yfFd1VFo{NykEI|5rDA}jv1lpGrGewGhT)iXkwxETsF$=J*$
z8$lF5n4Fk0I(1(JUHRKVqOJId88|k_0ufC6N$j|sLQQ0A$wEn@#<VEjtH%9@veI3c
z00l*|=uh>b_;8ceR5hDc7c^#lbo9;QGJ-otAV|?HiDZBi!{>)#)Jm?bOgG9o5Z6C9
z37x%d6A^I>sPD7%Fa??ED<YVbiG}*8`R|++eKIA7{>~Nwy0e;1Q!|ffO2g#nC~&J$
zxm?Q^0RN!A`Fc!k?P0+7B9U82IYEl<YEVNaC!XAJf0!&Q7C<I(#J@w-*Pj6lGS{yN
zkzV3*@GQvIXvdC3l?73}XSe%PC5=bGbTHRsKQdAGU!4&qKi|lF(UGVG-|uq*_W=b0
zRP=o3eh(&C4gYLj;3>7R6*bTtS<&lSa_G-@n2-%*4@xMzN?ZJUfUNdKg?QgsbMXO7
z>-8txfD-|NCUXrbcS+oF_cRF$@k24fuP_KBLGvnEZTKc@o+SMyU=<yomvd;@XnP@~
zeEW!DxCL;_>8!Hc1XCmHsGFDyqs%sGqOz>!;;m4CEE^10*309dc#>q}j;ax&<8zHO
zPvdQpjqe7G|KLa}*za&r3N-z&vCyw+oP+e&N7x*NudYc)?a}NDiD&1ur98=YKa^xa
zvR<etk&?=BMg3{}5=KpVAIGHWseH$`W8okGiW$em8}sG>nOqRfWZ4}&TZVt+CQn>-
zxl(=krg_Ktdg2<eSJBMI@TC=OZ>~y?s0q;~a~eUtvb%mUKjx!+3+h`Y>?_ovu|95?
z1?iCKnEMloayVcMwZIKwBVND%kd2N=Sx7Tebt>GI<hu*DD4UYVaaBDG`3WQjIV{*N
zYka*^fjBIyG5?^n#i%1?V5JWnC5LKoI7gN9v|}ONV5@*d5#BMopujafL(Gp%dX$iw
ztywwu1^lB5h$Btw-NPw2*=98es-9m9tKPnUU-vd5iJE3s?iv!mwNf_*G7K<4ou)z^
zGB}6gp5F*6KeMWeLu2Eu92NKXO)UF0K51$@tu5RZ@p}%2!i^gq`Yd_LbqZ8Wg%_XG
z#Na7bf&1w?yxLRUTWrM>L}&lmQ$B)#>zH&(D9cCqcE#TLt^2dr*RL?G?iDpy;LX@0
z*gLZSw}#C~FmXTVN5_1_iIb!S@BT@I)TLmrT_Ir01@FBm9X_4zHer_T`Ms(l{)xgs
zuZ72DoxJ4wd`o8Z1^x;ynS;oHIxUo1vliy!l3GOwv3q+q82AMOdb53wN}&&tkKdoY
zMF4tFjp)xQiH7m@EDT8o))hx;!URxPgnqi>9Og0LSX>OV)c5dX_oSP69WbF5Q;v-5
za-W(++!k3Q+Q0z5G=I)2xI&!0>N$THLen8`Rmk(56#G<DcVPg?g3v7noVQY_k~v~R
zB<osXDo(Rk?Gb<lV<vzg9tgG-1~iA^yR+(nV46xMqp8tfzLek!Np_7Fu;6`ckC0~`
zK%4}Ku;6hRF;68!)Rg$wH3iU4uxqdiJ_m@{1|g3;sh5+ap~AqncIO?$cRPYtYnjnQ
zmzY*>+UifIO8DE~!0U9)>grVAi3PqJill@`n5f6rtFfT%`P5zr0=16eZ-r1<_;5<g
z_$>{}kl7T>9i^6AIDUl`js9+ojeYaAq%94kw+e}CKhm}OEp>nsKT#Xu|3g@v1FDIp
zJdZF{Pbe1#*{#`<zjIu`rpSLc=lI;pQ#x2a_c5SvOL6L20|fb96KXHUIiTvbu{^O~
zGltUk%%3nVQ5+BtrPhve_H8mlkkUJqbX!y6=m}(NZpdx&ihuW3Sh*EoG|DkmbT6Vz
z^v#M9SoQ^vr{%_+VlVwZCm=J#?NtTt7v?@1zeieFZKWbaPO^OqO}~~c*SAm1>3dLQ
z-zot9oT-wQVM-ixtj73dN<R~Marte#%Va_k7o&#Tm;eL~#ZxdGX6k8pa7JZC^0P4W
zUfZjuWceR@$SU0V?(irOa3q<VTC@%0#1`{KkisduyJ``(r^W3rX1sgYXvntO_D%|d
zf+lgSDweeHfO#(R@YS~c%%^rh?2SF|5JDgM13N$Da*TVEWY@^P*ic2J9xt0b?`8H+
zMW+O0{%Dt01A$v6%P0)xl>cmG0aFz(Gb7vMtKpw&_*CC-%6e7rf}r@F`<v4uH`N2q
zur;#OTw=aG6n>^><E>5=)6V@6it^^L$Q-h*Z8vF<c;n*j!6)iHYp+7#`~0S3DEL0e
z;vw}idu5WZ#d=bp`jmj?+)yb5Y2{OV46mx^fut(arLrH6bjtY|Gfyv9;u)ZzyChm-
zy3aLdK5~0Blja2~A@@umxg3I04LsDxPA2{Qy&JvA^fh=~h_CoB(N6?|<Z>U49eXOP
zat&+dCzg1i;z+`B1>BeFrlqK;_p22K*ia%{#eQ&oslp00Z4<tp-XnO5P`k}owqMdy
z+p=#yfCGYl<vkiZeF&xOi`5~rOzr8%#s=IDH~>L0ILR@&%^bH}MC2Cd_&H3?X7`rr
z0&J3&hjPw@`YS-P_*E+`X_wM*7wx*O(G3*{8qY3E>{v{yYrv>24G%y6+^^Is#R)-%
zFqFEOYY`&Q;$)f;TP^Q+EDNASGz~?iKSISFBr}L|AMP8-)zkn%nqHQ`?GgVq20@kc
zj5Dvp6N#KqPynu6`D*NH6WGhm7`l3VV{Ky#Xv<SckoAbGT0u~y?|lxPwMwx<Kv1Qr
z0}40QpejN(3N&Y`v46$4HOjLOf+leJ%BC~FlGx_^zSdlW=da}}7A<*a#b(Z99XJ>d
z!z6H@!zlM!Un@GZ1gkkiMW?|UQS;D52lYPlrs@GO=dizk$>aJidB}?Cy)CIk7_D9#
zO1X)g(P4$OUQzBEzLB>5jZB_>TEnTUKH~r`zNXl<9@el)Knia?tZ@c>SV6z@3`gCI
zJ3exei>;W{8Yr&S;OS4?lm}HtXz&przp~op2ea&c&Z1bi@+g{7F={gcK|DWw`XYIt
zpgW|miBb=;Em_dNau}V-yT1&AaY4cbe+kB-*XrxHyZnXME>F2?T0;=UblHuCp=2>~
za69_9+M+0oSxPaVNkd0%6>rBv?Puv+lG0D$Yp&0kln=s7#OYL(*z$XC0o~(f*3##r
zED*?9_Ob5=Z33_^rhp~Mnu}E2S5N8zMGH5Wa}#2|Ce-9_o*;na0PNckbe&#&%lA+5
z&9(l<%EV;ee~O2VlRz=?Feuss9yoxfM9S-H%F_jSfZi9fM#9CgQ~wq(kh1!S?R@_h
z4M=Hy#Nt)J<V_bgg^RCx{w-R-#VzwaZsUev(J3mT7|z^x5NA?$hu4i8w>(ZPe^BPa
z2!fQ3pq+&((Z0QL%)pSW9Yb75ulq>9ZvwE}0rZB2m{~OVS0*zeIV$0Xt>hfz+3`UT
zC+SsRSJxOQ-V6m?W)RezR`yDDePab9r~-q}-u4h(URs>R2(D4uN8nCJn~1qNb4CKz
zc)TQdxMYChbUcoDEw6*5*^BTR1YT>-&CHCUSlz~PMs)3?*DMH|{(%pW92Oq?08cvv
zay2o2(L{12!Nz#!l|{0GhUS??N`T_1aeqDV{<tn^ca1OUX&>Nej98<=kJHwdNiX|e
zgCZR7PWch!WZ;kvnfgPZ*nw*$2QVowwwKm{r%Q-CpX0A3D7LBB?-V8f8Zs%9B|xqp
zp#B%`_7_$pN6%%Dx`+`1xw&r5XkoPr(*?~yi}mqku^oHeE}3@Go7-c`f>J<ogzck0
z^t&*U8WQ!e+Q~oZ&gw&Y$T=J!W3v?KMkroQYC$t8AIoc{t1&R~Lh&Oxba6XX1xSAr
zK{EFU3O^wI2NC>=;%Nw&w{$#S0@`~p5_LV)9QKp3=_+-aCg9rx#Dr@d^Tr6CHOX1w
zB$WVay)+!7N<1Qz4Ss*3od#2I5#>q5al#R#N7%NBIy>OIdsmjG4NSjc@u%8^2o|Cz
z`Gw<J7{NcL;O&sa4JOpRI8~K!M5s4OXzMoZJb-vkiQ+g)IARIjG_R|3K@c`WCChe?
z+a9x|VNP5Qup-K&-kk}_F^mKB+%ywVBc77@NQ`jA+~cWcZZepP2*&*#ElkQl)hr9i
z80dJ5dr<~>YhA!wajuUf1R+d4j1{@a`wLaRiI@_1L(sAOLJBiR@SCa5iU>&-)L6xp
ztf{~{WH(|dXs|kJ;A+>z;S1UuIh6b00{91G4Y+a`r?;U^I|i&UBf0uNg_XdJBnQAe
zjt4K(pc6k+4sTyk-wQ!)w>_*<PQZ4)02f%n1q<+5;uzf27lFCSOkl>vs}vJ~UHGye
zI}SI=jhK>UQvRO*XpWN<4IC~HzFH|EIp%O6Lmyr1Yw$(wGFBTy;oVVkC9CWMC+Ppw
ze<8s7Gp!9GAopL0*Eq*@2+6^Rv)w4CfWQp8MXIa>0Tcot3IS&ulzPL%g$gpXr<c_M
znhVfpx!05WeuG%eEu4cVS*Xqs@T)5095)ic5C{t707S)tQ6_+21(Y~R{hMzPAjvsQ
zdJPSQQsx7+vD)zzaHb9nU1Ja5YS3T<5Bexv$pT->fFeLj4b@2F7S<&|RKp`FJVT`h
z@S9=*4?a}Gi(}p31_SjZ7>c}F9>Fk0Z5XVI!NhC@%pV|k1N}xQoVY>+3?_&%7kp3v
z0})<wteHS;0y6&yANoWT)CHOiD9ktA0Sz7yrNU;1f>8@AEdwKSr_wQu;2U_Ius)3u
z>};#14<#pVauEnS2pZuc1A=MrL-YXI#rF_>#<5O8g!)QMxPqw!Vgb~2AJY-BpusLd
zh)@9uR(OV?Up@m@1MC+r#;_j&>BeyOL0GjRwicun0nGp~0`T*zGy{?YWZwW5?868?
z(gCFQHG)jaec^DsZvuQC7_kJ<+)2PdqelqChA@!+c`Uqv2ZG{2?%Us2V4y=tj?y$3
zND=^@gB|JwfP%s55Yz*J_QDpGaFJcOp97$~qJ&{#*ctjd*jjZu&`U&ULN}W|EXD}h
z8+eM|-c&H@B{WUYeK-y9V9M(to4szIW$A*Tg)luO1UNB<v!ei!3L~U-5VR=f5E)kU
z4Jc0gK%cKbhMU@Hx+2g?z73Of#A1M`dxst)&j5l3-J%QFS_8W!dXRx6$uo$L^j^u_
zPnNDG)1k21*jn;?`nszH)<9!;3X=vN=hoZlYY<w^;??xoH}e2lI*S8v7coG9VKH>V
zy@9T`he=sKn@)BOT@oYM9IbQ%{D+VhCr0pYdojJDJAz=dPaQ?SEP@fN>-s{!ym*9Q
z<5WqXRJ9Z_g3O&eA>%GeurWEL43C6VK*X$#+i{rsUN>IDs}b<pGOmxUy+PS=5bzlD
zwK#Z+hrlW-4QCI4027?_v!C?A1D+5<k+7$3fG#;g{}G7@Wr$&hSNfo%7{Nw3f^L8m
z*AHNb!^a6}*B@eGB`1#&(qiBa^4RMJeuG#5^zRfp0+_tTVQG-4Ck@U75cCm<z^~EP
z4>5wclQ7`FB5!~Q{N4;F`T<N0K;%BqNk;)LJPTfxq3b{daJoZ5Pk~4Vcuj;Afi%eg
zB^D8S?hdR7m=(njMC^gcvF||SCPwh`DOVr@LdxwNjB<=%!*&_`I1Jn;_=g|-fYm{%
zK>!*G+6CJS?SmCVClUYM_|GN(1;c;C;J=ySzd7;0)!_eof!x?;xWQ{L?KE?)7OcjQ
N?ghj1h3Bj>{{xzZyM_P&

literal 0
HcmV?d00001

diff --git a/tests/data/pseudo_mapillary_dataset/v2.0/__CRyFzoDOXn6unQ6a3DnQ.png b/tests/data/pseudo_mapillary_dataset/v2.0/__CRyFzoDOXn6unQ6a3DnQ.png
new file mode 100644
index 0000000000000000000000000000000000000000..a8b4b62357dfae32357067b4c55b85222425a70e
GIT binary patch
literal 75316
zcmeFZc|6qH8#sQ(3}XqEM1{tdP)w^VBa_N9mde&f(`})Z7^)Ell~%?sWvONeg;r9S
zZntPdZ<RJnm(n|hn6l^lyhrZ6pWo~I`~UaHZ(d&ab>HVa+j-78&-0w;Jg4KUT<jF(
zr^_RR6dmlBuR%zekC4J;Su(WDZw_W7L`JKe+*b&VjF1Qo=Fc3=r~UQUUlnK0+z{Sa
ze;{QrUwbfLhsWa$=Id_XevW4|dg@elet!O7zTRMd_F%p~o6Y`|a*Aie+bj8rbwBg|
z;-zfex^m^p6!;xj|9*-U{EZ?sinflT>QTvWFkf>pUt=(T`e6RF!F=_>{HcTas)PAc
zpmQ)^WiWs8VE%-`e1&n~iG%sd@Hh53_FtQPn@`#ES4Q2a7#&R;O4}8yi}JNbM|p!t
zYwM{S?|HnY*|WFiYt5cLTU%RuD=&M>l+jp(R&GrhEYKRftTlK=Yp_sjut;mLSPRSF
zdPeetVIs5&v$7h@*ZP0_iN=5L-y`@#=r3r1|2cJP%6<h}3JlI_D?-3wJwl(*s;xX5
z8-(@(LrJ3uG)AM*{2kE&dHL07wZA`5`2T<ZAJV`})HM~65OP?~bU$$J>j-PFp2Mx2
zZ=DAxzFx487Lc<F7d1Px)$+5RO&>9=Oj!ALg(<5|MfG5&%L63?XO9P`Dqd~Sn)ZED
zGw=Ke8Bz3der?F}G;j+|ExtACIP6LOTDLP@3c2bX4gZkR+~X(jui|M?z4^dg10xi$
z>5osT-}?8&<$PUCVk))nvUDf$EGO$$ZolUrv3OCRoNQp};h)i}s9%r%-T2jzmYv(a
zERk}QhDmmnpEU2~UG?jc$0N8UUBMjbX;Q<q>JReV(_U!pUq@HZQ13S|8w#)Tnyka4
z#hm<Xwwc7{n&$3l&>p>a=4M6LB+m!3mtFYx7l|{jA$oxqx#Y>(h_?PU%|q%Pfs|LX
zsz2y(mDi&*7j9Z5C*Y#%xotZVL}e87jm!UdB_-O5wGJP#9Xj+$@8m^_r+)PZqxr2<
z(WivWcGqv4J_S+N&74)N!&LH$KU<3E$zuD6-CagmRu87`km{J!7BKD6c?Gn<p;l}c
z^6firyF1CCcq&sVH9qqWqQ{BdEBza^vaJ7Hc~EK>0Bhp+6wq~t+MgSSe)fys7zWOU
zVOn58YG_un*7wS9?^^3)W>ueuK`J;X`=GS-+`2Ak%N71^tMx`}nY$%zReF*(V*+li
z-Kcq`f1GPp?a~t(H7acZh6JCE&(@#%K&I9KJO2HHpl5x?0TNrgylS|DVI5|{)sTl7
zNfCdR<{jZ=_7DPnkd+9u9=oW9JhA<c3EsZC5<Vv#YJrbKgEqlu=4o1t6cC)n2qm!%
z88H%q^T!CLi^bABA?Mt8g5bR|f;+K#HI#zwdq@zZjuCv~5Vr{kR!x!+JT*qpfDuk&
z>ucIc2-5d_p-k1S{=mh^>S!vq?@tMKeU1xz9`K&ch$OK!HL3pt8ilE-qm<`CA_COl
zH)!E(Mihyy%4i=dTx1<aKRrhE1hzmOc|H%S=vogl)n6K;YREWDVozdJ{SRmYW(xv5
z54!tb&_YAT5fWRGkxPIcGCBP>#S>&r|I<wZS_Yu^+p*a$>_s4}k=0QGG=>1>8lA={
zuK@JIg)IbVa4CQ$=3<we*vu%6LL>7S5Ww4)0Np?9bQvW@ulhrNU=She{#yXL#TT2+
zVmlL57XwwzFbP$T&gl!1wR>S1Q1!%uZ*^^GT|mWVIk3Hfs^J2V)et}{7FqAp+7m_b
zggucynUJ-9e<^^HtDfiBv3CGfLpo@{JS-PLD~2}T$eXnG94&_R#Tr_fW37GbZXBPq
zHiH&p{Dl!sVmo_R5wKm%8xE6f`1e(RWZXl=`Gu_`A0CFA#e{0vUY{EIQ7*7FJ5v|f
zy$Y^a`nsXsH@oV*Hd9G0Df0;`K33Q}(s?V>nq;oz41k$pwhYgMquISb<cGL-^kUWd
zxlE;o#LTCt_*5qO*OQ#g@cxLlB{yIQf!M`q=+*O}KO^4O*T?;`)mz2ZhcOs1&Vptb
z2E)%%GQ+!PE{l{hhRtV=;}g)6&lVs2Z;8c;1YN3xZY?T4QAqyPnvfYDV6GGfn<7(u
zScbPktl2#?6(BqIeYWM_mlpaiM3>KZ9U3jZm^;&IszLE|iToHUK3vl~az8dRtaEL;
zhznL_Rfr>5q+?Or*Qd%Dd~thzq%@4`!sl}`yhUQIt}bJ4_xT`iDc0n+fED-56;Z)w
zM$_ot&$sQAw#!|1;NRE(IBOA_Bk16a-Z`I}xmaDl*a!?tQu+&2oEBR@QX8ek#kMAj
zt^ubte(q#Z6xX?LsRH+tVWNXn2M~2WvrZAQzAShj(bXPraB8aD949c1D~<xug8KoZ
z<yllMlefCX3qgF<v{$J3+NbLyec??b_bx1wItj*Obz?4o7Jb`2dNZ>xJZJYQ(HCIl
z-nCB=Ep+Z_?l{=oemq4M4A-^6nq8<R)iZIVA*AWY>TB9kpu56C@(k2}@%h%#n;H8L
z#qK_emO^WOEYW)D(bm!1=lVjA1{^_4K_{2Pb!VW`=YJHBZmbDq*pxDP&A`dCC|(gA
zdc`gtef`X`G0cL=TMDgSx#yvE_0oojub;g4GBjx-OPIZv+x*CAzenv4GlmjjjlI2d
z7K11HzA*wcfe)g+z`Iy!%M5fN`@rSC&)+$rD2r(N83aw2LN1pm_izrPP0)1hRWvkR
z4#_X+{La~r_7hDH6QSt>G%5CQg3*4E_*Tw!NmEYAgdR>1QU<8fqxYfdi;gbCTSH_E
ztFNeWSO#V0oooO0i)W>&A=&~Pu;>k<LYqeWl_;x>8KMPI8r$pq4wI4V%V&WMC0Gjd
zBP(q+(1D!2NhNYUoL$INHZW~@;yfi}<+ix0Ih}IQViC`aV*d2P0}X;u`rpo6E6wSm
zT~QjJp0kt4sCLS;?y1bo&IxQXQ%NN+>mw2^Sfnz1#k#sanY3G{db82XdV>D;@Q!_J
zlW8%x-D`tT%kcz!#8a~k{|ns$5zf9n4*XWnztemo+R9s9v^`2A$ISvG@v0nW^=;S_
zmpdf&n#sR^*eKTmb+3B#KHM1e;)6m#)YTu>QjwO?w0HhTn3=H(?3qlZAfp*yXRI)h
zN1Ig_3^~W$2Y>67zx#%NLYWC#?s4jC$u*j5s&w&LTFeer#XiMAFB#sY6OmV{HgAS8
zc`R(&^w@hEx?uG1#|966?j5NmU|XK<lo?jY>yWZp|DZU$0QBU6Vu1Pj2ZtlHgT2wQ
zg0z=h4KQt+166H*<<)H?(TdosDm_4XhP;cQyw2gI2%{hmq;B)zT)44p4`(%skqb=Q
zbnoH!Rc#j#{qPCHu!^dB2I(BFdNWDYvMMb8q?Bl)(RT4WoaWk22{=lN`Iz*TRvBD2
z0Zq8{hf!q)ECVOhE*rSk_4)Lk+LO+L&iRO*opAng)#g1>8lEqFRSe7I(S*D|bSg9C
zdpHg#S1xevnp9`OCmlr3IT1M=GOM~?n{*DMsMU<c@h5g6QMP=}_jkv&Tzx64K->A;
z-8#|@h{sf&&|1>U%q*16K1_=VzS+FoWfKWK3=W@CsR`3yi&jv~=Ug7q3H&LK=!Nys
z{h)H#w{xxx=md63A$oEBmi}*R`MG4NOS;vY_gqnncPmmxx|WP1KbFjK<=_8%y{V3`
z&rGy3Bt)iC6LiZ!LO?J2t`j)?k;L}%H7M4iQq1c@l+6dfAbMFM`9K6ex1MxqR(0gX
z=kLW2NbCdcIYk6ax9yWfZFRfIqW&7i=5kn+GT9Ii4!_u|Xx{x81xUBA90S{MebLrY
z1+qy0-1NIc#9mRfnGvPYFMKoo+UOBd%VZZtABK`_U`vtbhU%sUX<osS1^f3?4wk9&
zwgZz51^QdNI;2D%;xl(}HhMd$P2_(ig<oEzfV`e>>&yuy`PuWy5ewHZ3#picHm;1z
zJ6j{2tq+1c_mg`wa18}a)6CghHkFqH#OyBWZ*6}fB??|RvkYI0-cD{4ZQA3>Z+xPN
zHm>M6b9S$E_B_CRxn25AWg`-;Sg3UycSq}0#=u720od|)`_7t3XPYyX?(Vu4^|f&i
zYO#2$xSpY8Jh4r5XV#4BijQPeD0s#nF>I8xp~67frxYou@IvEkCts<$Xd2b}l8?>L
z3L~_UbzM8Hkdm#yR64Y(l&2B84wa^?>^0StvzZBKm$r^B`IV0X=Iwd7scaI@1;k(d
z;McxS+ej_z(<fANbWk}c?PAnO>w8d-@P>LAz6_OtdQR65RXqYdvUbq>u}CD=t&W^w
z&=6N|Isv7wS^5(TLmWM5YJU|M1)I^>a3&YGLR?VAl?5Gk_h6!g?zMMMv+nMVF$V^(
zj{msWmP~4KJYmpuOEtXNi`+_pwszP(XOTrmUew%iRv13-FLe}Xy2cjH^e|OKYHKVy
z7w_&es8CgpgYlY|hP^0Xf;QTHEDkNdlLfKgoG6V0JL-S#8-9RV%H(|;pFAu763p8y
z8_2F)z$~mLr8zWS3cXp<P%)iOVJdO<?{+2eNXd$2?X1ur9i%N2+iXPVou$!3w?&^a
z3%|y6UUqXqzOsR|zw36A(EYq=LA6tVUflo6cs8$<Vm>jDQ;vA?FPv^ybqpTg(9tkO
z1R<Ec`PI!xG<)a6_tD-XZRNq=<XaF^sqNgx1&CI({c&UCi`wRm?KjZR$!#{+fCm{}
zaLjo>;#~gs&%s;L#fdcPHKP<obj)yCV4vBKgrSZZY9i|>4O!ziixEw*^>JhKi(Pw*
z{k_p05UX%|GvXai(B2>6W?FW?;vng(c6B6a${r0==l$r^oyt6~#y^@XPzbCbl)qRB
zeZC?g@TBvqKO4Q13uIHa8B>wiWB$iZ|1ZI2Z%XLAXB2aKR9P|^l^IP70tx=S^YyH{
z$TLbqec6W^64LZ|dYgKd`@uV8?gaJ%rqYD-0quyFDKFC)?Ofhta%YxIaWakiaMf)N
zvRNt}-TCW+Pw3e&UGnRdeDan{jTR{TY;PjbdgyGJG5Pg!J~?`}k0r`Z?7jGZZM{yk
zhGm5<AirJ)u$LsT^%B_dtT0RRYa5_DyBX*v{$E>D6B9e{UGRy>@*ab=y|f8nQxl`1
zwW($0oue|{=``xmIyR1YJ~hv7Q%`bF&iJ-|x`;)L_@t1GEX>V5Y0ddEckhi|JCG@%
zv$-Ll$@Zsdp~aWXZr2v(k?!hLM_Rk=F#@xu;zkhuyz<UNneKBmD)+$EqJ`_tQTD|K
z+wMrav)qCi-`33#xkYLCb=8=3_b8y2owt<k)oShe@~!iRuRn5?4a~l3cSm&8l*HTh
z##(0SfzrH^yY;d6NLFAdb22YWovn~Xg<GpMhC4pwH2w6noJH+EMx(ChR><!jGD2x@
z?>jR>HfO6bm2QZ4s=gMlK=kV|XSv-NvG@J_?i&?<D?se^ab7=Kgpnp-kn2*sZQ{tq
zWp)MJuYcMY08s9L76}EFR_4c;C~#ntZ%;3pgy^S33%G3;Z0rCaXJ9%BsSK3mQ%&SJ
z`qh!1>HYwaT3f*F>L8WN1!gC|+CV{0?e&FCeLHRT1BT$c5(&ALy?GhxqaX{rY{qFX
zS(NrN#=E>ZnI{XfK0j~-p&G|rhzlcUVa773+tFeL?3;!0KJyUI3p0e+F#Cx3C<)z7
za)EOKSy7-i0kz!ZoIpUHR?bGKNa#iZ(&gfC07^0WFVJxSx|G^vig=2cK0(QcTZzzO
z`&5D*7ax&AuW8<p8=!s>_9-BCG>1T#o$3P!bH@-ia?26AHHHv~{{RFX3BqGx10bCI
ze?eHh#9i4)%MmoPR)YW9TPe3<TB#kM{9w&4X;fTQv3vHxNi8Z&r70a{EQF|gT#r6(
zkg^8TaP_AG1qC$S+UVDvAld}dyz<+HkmH{GBS%dYVFVk$T|;Q$Rl}(k8>LcUX{=ww
zl0tQ_j=F!|uMYtlb*JjHy(n9#D4bZTcNsR{&HNZMw94OhHpNu&38?9cXZ;Lxskcle
zq2cH@pyzq#yCRx$FhlN5!F?l&`Kp4C5QRG4y?nU)<7QRR-pddk8MT-1JlwA+BKq?O
zC{*OaO_n9Umzo1xQ)qE20JS8k9ifZnjsa9n0DuFNWNqJ5BmjdG_Mw(bYGL&1J)-FZ
zg@!3q6nij}dhtE=G7~5ao(2G3?ml`=#uz{cjf#G9U&)Xg<q3df3*|t>&hp(sfALH-
z87Slp=>foj6qzlJikD$cBoDd*Knwu9Y81&60HXkKD>Pl^Vx#g?S3Y@#6a>ky+jmSq
z6|&T|Q{2*b&kvwzbP<U+l9_Waz)ak>IPQV+DbQED-gYw-@U(uRdRMGgbL)2$6%S79
zT=iEO6nh|3hTMd;4q2))>GDjab5o`@ArYyzp8Z!S_fSwSOI8M!RiYF`|4Z5qPM>hl
zEw1abUJQ-JCmRH7y+xwU09t*PduW5l3JQ3PB?ax(Ks7WTsJ?pM6@3!S^|}l=Zv|kz
z^VK_VDMjdRJW8Y1e4$?=@uX^>urCi;44)2wlj@R!@26zY2`kg+)qB5w?z;yE#g-e}
z>!+bh;=2?6HVf&W@d1u`0qY0cWzh5kt7Y(amIBrSCLAA@%w?P)@#gv@F$aGt;h0n1
zDPX{={R0-i+BSYgxoz1(m4&ePd$H^4=yl7AX#)Q)zR5GnGf=`^@f;cC6Y3#@4_W5e
zNyyFSXFfn8R?%ZxSVWcBZ<ZfuP?|tJfO||6baka^Nl>$GxKqi<wA?6KJfc~D@l5tK
zSo!wAwIw+fxZc}hp{H^KxXR<3C!o9C*Ct?Q2b^NIMuosEX){idcxpZ=%t0CDFLe@u
zjRd~)Q1_ot=G!;7Fg4TV(kHdq92e8!^c1>I2A^Sd$#zV*c&&#>6lD5@78Xqn9usa6
zRu95`*#_h4&Q=-|ZY6g*oT$p>3E^Jqre~{ya1L=>P|F#w&HReW`&@UGg<$E8@O=}I
z)pw%_Sl|A&aXX_{f^hnbSQ5{`=LmD~mr}=S=Q^;+j|J@@-0K3meRK0>M!wv15bliF
zN(O0#suG&Zw_C_GhK-e&S&c-tMSp_k?0y`Z<+p-QK7#2^LkHSC)IoEXw4PJ0!2Vpt
z)gz<0yZ;r=-LZBnYKfEx7tI};uQhny1oXa7BHXID?NJcvt}<dIlXyd8!hLxz(cDg9
z)qE7tAQ5gJBS8+LUz;o9jWVc{D-kZoZa&izj82NyQzT+YgsT$U&+;QI7ZyDYm9|TS
zOVfHp`3AzR=gx;?^q6qi#k6cl&A7ATwxgC<iEy^uDJlygj0?oyOhAWzTu{JD_B*AH
zO{)pyT6jf19LYLd<5b5djBxG()cvy8#J;&vJ8Vq2axq5+RdAc6@jI3RSBY?bG)5+%
zW`-~aKPllaB;%THALol&3Ua;q6}NRQ^d*aFDn_1;`oFAG6Lft$<})_cN5njW+$(83
z)bfItWR>{oFwT>BrkTOa!KT>HFD2yC?OpwVT-7>$#dX_356Sc|#&m()-<wqh{$JB#
z-%$3z_)m+E5#-#Z@gWO=?_wq#L;Um@0wAZgoH=+a7JutpcbG<<?x4H_$lY<~SL8)o
zq^c|gGvSH35#)R(3%c-2O*rKTxMU};6B%tfG&f4DsrhPYW;R49=?-y#da`H*zvANk
z!73GZl{Ono9I`)$zMIQpeL)*_va(ZvgQN0J;BZ#UzWJ%#`KYL6AjoV6m<>zoHk(0D
zmt*=<Ucgkd@YRaweQ&M|*0*ovwF}uq0O1%1n1!3>@heWcUDK4-2RYoio@CTFax7BJ
zIG12z2+8Ki9PIjZbfD#LhDr6A$lq9OYy4=`eBflrC?@fa3tHv!!Q%<V?`2R9zh;)7
zEqH4oc%Oh^oE?<{bXRd9b&;A<sPE@QbmcBV0p7TK)KBPg;l`4YT5^pZ<jlz51it1d
zU<JN1YOkd09AG6X>3w$Klb;Ew7I1{YEuw0m%ZZyqMh)>wy7u7N7U1`k(8gtD$7x`M
zt_Wf*5xs(=%uE7l9h46swjVwv$_he`_{{G}REnumq5(+-H&;fd3^i@&lOgEfYyChX
z9`=oVACy%tE~TQCiJe;N2{dZHkZO(SNt_;0DeSB{3^9qfS+I*LV^AHr2EPp?bTuvM
z7O?ysYr_y*1Ai6y0d(QQ{Ypk;hg_vo;DokeTV^742a90#A=qIFT7yWm3KNpmK)ciN
z^U7#~zNSThG<3xiUF_doQuuM8ZjfO?w+4@sn%Rd$$FM8p`*4KZf$sn;BX3Lk66i|G
z6cfX`P2K`s=8|E}X|$w6y6#+}Rxc9OVfV<ok}g9aIM>^XPM37`AW;kUNOA}>#3unk
z(?%=$9Oz2O>_(z~>^b=&oX-q#k}}%Jv<PK8ffLbZG?92L`~AujU`lcYxt1tE5$}$i
z1a2rv96&`TI^NcF8qkQ>`i4Z?1ohO1VBHsBiJGW1mNO&@0Oz!lTMRRv5Ia--G`Jx9
z+F;bO1{)x6fdl6>JP&4)RTjaX4a{^IFG#$T4%CUK;M8Csu!H$G$EBho!6O|OFQ=kH
zgA5zG5-{UyeMTZ_;SAZMa2is<dNok#1rFujY+$yGORS-!LYg{k#~S-M$YG^pniN~`
zxYO{>z|7s^Fq<M__JqVMa7>*z0pbc@fgP;Fbz|%1T!I!P$2^2?vOPf1kqgN)uVfeP
zYEY>mz8Xk)SRA3jH0S<Cni@sSO5zyO2HC#>$z=>_ul6y?JV=nrj?i2n>X0CL;A2Qh
znZRj<a13b;H-*?4V@MA8ItizvG-uF-kPy!USC1klIe83ei!275Jjak?we5k^Ith}y
zg#;;AKm{c4F(i%D%)gOHD3l;|KVKSJF%`9(;!I$I<+1LcH@zf6AAy1-4DJpwG)lrX
z|M?#NvDtbroIH3c*gOi{0Q9$pEZaLU{on6zPfi^gQANl=Fh>4Kx#0jDd{8W_YN7yE
zO775>o(HC6bdEnJrfZzc$LpKOXo;?-EgvG=EQ~x2t#us}d#R8*9~Ebgi5BjtycMw-
zV{#2AX@Mi<{uaWJ!6)&4{O0J!rIAsAL+->jU>74^E`z2fDru{O{R+1S7s@uoCq&JI
zWfUWZIB9A^EKU80q-z^uPs1ru`y^dk!J7TJW3_kGv;}ltxx8v2qF;G8$Zrh*OSM!G
zvk1}8bH0i`6ZtEy4;dvo#3*eXW3d~tXW@?{iMUP~zp99y>Ub{+&<0g$Gs;LjLqV@h
zA$a|zf?SD>ycVed8x0cDppm`POJNHhQfWh?dHA`=T`-GgOeOR+#bjC<99JsjAl@zF
zREs76SC9%>3N2-Fz>xSyL7c1aJ&!K;8(RxM7P$__aTY@A5PP!;P9QWS%Tckn#b&k^
zh%&31#Jhr#$O|U5@w6alcI;Dd0-*>xvolQTaGsO}UKcqPqKy=D8UUZh2Bd-j7zi$Q
zY*%;+z})`@KFcW=ZKas=iM{V3=#ZWTdtdAa8&${Kln#;K6P9ZTYMGDykV>4?R$L}#
zLznJYR{={Ix-5Qom5MilEzuk6I>{nTgyR_Z;!-grjtlk1BrK40E&JV7Hiq@zE=O!c
z%1y#cg4JkBhZwJb6(=G1f9ZPio0mi_#dpVeY0~L%V0-c#>pxv4dSe8~u$GPSvLVb{
zLwu)N+6fvJiw47YYD|ax%&&w=?3MncQ%!PELc5b{)Y4AEx^s-%k6NV0hA#5Q<p@*k
zEm7ETGU2jXes@uE!hp}wG^NjAD!q4f<s$Z4{6ORznC0u@%Ty$j9IKWFHnqahH59Rz
z;~|kabQOyKqN1aTd)3lnX;dxy+Czv<|J`*}{2H(lT-4Gaxt8hR8jjfNI45!du#Skk
z0gG><mIm>ekG*RIVpH&d$Z4>jj)?oIs0Vu^6$GnR0hdPT7|Tn+$&pVs6__DJo2xmO
zZVX9Hz7GlUiaFOsH(;$U<5Cg2fIW~>ffcQQ&qc`Ik*e?%!U0o310c<AG^Q^ikebMd
zcaBpidM`nmgwP+@O{qi)k~2cG4khwVU~5eU`$>qVn_)y>D&Zu9c*i(-A}K&}<Z2=$
zg`Jlo(x@yPvJ9V1HI0g;04~W#7V$c<3@H|L?ZT6xYfgq?u?$mbH{VAd@hY%0QoEpQ
zDt-mJ480ADAyctC-bVrP3V(Oa!fz5?zp)aVpeyq?!Id~<3_cr<@!Fj<h9#6z0D_)l
zSl&j(km1;!GKQ5W)eFPgF6lCAG@>&kT@o>_N?nI8PdtN=P}7(WH&?rpo8%C$>9;aG
zCBmCz7}LQzKo^Yb7gjFiCc%;nc}$<XlbWcIFys`Ao>I(<R}-qy`8^3M@jVDt+Z!l6
zg=6XrVX8!*bLgf(FUbe=$xrC6`_T=Fg<B3qQplzT|9UA@KkYbt%XK1T^Y+n~OW}+(
z@T#}uPQk*_Fi5}H|B<jPuXFldz_Pl2d!BXJ$J=VrXCQ@kwni61pqh@d(q3WJrU{=Q
zdfHR=^dMqyHSPHONkitrd1+ZR>f#-Y781|+z-qOu%AbF+?!k$^*rEOnIKBtHWwQ?%
zt_AD5c*jB_Dmb`aEx3q6%;T)n+aWMmRQu&ZXEIw3*bAN!u|fO3jW5b46Ip}}H_|?V
zS7n?yncooU0h!^GQ?EmWkWbyW`iDg^9OrjGXD7gx4PI)J??d&35Mu6^c8E|n_qAU5
zdW1a*NM1N}3ZjS*Gn2<YvQq&-G2a&e_HBA{p<Bp?WXbF7fJ0>DR+@L>&(x@7U=f{u
z53GKx|7!P&sdFGIoiW8}Jz|^q>(Bkwcayz>Ai29q3LQ$W(W#a!I70xR+qhyP5O*dH
z2x%KEPSHU4vw|3KJGVL0m|%Br5yuI3Aigl_7ih+ryONBqvq~m$K%1wr1%Tvj5t~gc
zh$OA&Nc0ukM}gcNyFh$O2F*&1)%^?(V*_z34fHga;4xm$A&xA!g{`t&$x75#L{28&
zc6Dcf6^mfCcP!j4_U77?Q4p(P5(nI~rbNE=WwF_i4*tr|#E|F(7EB2nfwN+$fbfz9
zoaxM^qXXb^LIrl<CNFZdm<FQ*5XIdQw8M8aXDV}3mhDD9IYv-rMtnnmoTKEsUGhDP
zxxsW9d{;^Ok8n(xGiI><`Hto+W?l)?HmQz`##(2fv}I*k*?(P~sMaQ0jYCq)Nn3MG
zz~kGK;hTx$#CM}xfW5;pg}|0eVzCVR#8)zYExhrUw0XcP?g7xDz1q~>bvneiJC{R7
zz4j$jtzOI@>)#9W>fohz2-6+=-bpz6KDFT&3&y^;laY#JiMj&oa4C(d<XF24v0d;v
zTg)F#9tCw<3W+eGh;#nxVa|~V@Y5MsG%>kluhKlrD!O3mU2xF))4ASzoD94hAsNih
zBBpD5YK__U_`+|BFwd^s<-|PuYIvm<e%1W9p<Tl(xv+yg-cZlluc?+;_(et1u#AlA
zS$&#b@ilnwzYV@x7g@d>O_;XC%sM0*#>%U*v4M?XP+?*gpkf}UZ(bT_aS8ZsZ>$%B
zFq^Vb_2m|+?_hbD-~$uTQ`3w{fpEcXxUT)0pd}$;ZtrLjHv|A7M7hKq?TjPhl$yUa
zm`dKmi4~C8fegSLos1YxV&?~li=Q#hEXFsyJO7R%gFI7Xm%nB0@1|4C7yj7UB<S)l
z(7LXMT5>saFqg837^wR><4iUPOWd$9^EN_e*mL`GPM;EsZ>#doz-7>7(+;y;B-H6p
zqI(1@w}ca(;@24#_?@tvXKB*tz???DyM0V2Z1_vJBEAT^`r`)&<Wct;3w?84%~CHQ
z{_6bI#0ot0gn=;<t;7Xwe9jx6BwCE4UAxO*Mdc-pe1t3o_Y*QOhfuhh{c<kN3g1w<
zda)}Bg|PbcX9(Rwl%h0FoYP?7?;^bBJCKl)<NjGif*B!3Q5ud@CS-|qhuyn15b_lS
zCB|UiEp(YmMZxLTc$IrAvhlI77%<YjvOuM+drir}_3ABB$SNh))!M${3wW`+FZ|J!
z?o$ZW3T7nD#Lkq#F{em;&W2^BheTWODc&0_TpOS!D7jGA?}#r2Mw=lx>9`+<<lo)8
zgEDi!L$zz1;0b3DPV<Js8#S)-dDYBGkUQdJndoX>7}lx&aQoL5zvD3!RBGIq*UM6y
zZALM-N=~ztaA4pYGuB!#ZbKcITRii|U$#={eSG07IbmX=FMz3}FPDIM;oJ;|vPEy;
zrhP%)Y6;k(_}JHm0^P)K02Y6Cg#^q1Pb$B~*?29B7Gn@qKgKlK<?TsFFMYU8KQPB4
zHsydl;?2OXm8Wr>1Jh|SRo8kYVEwbbOJNDy=gR_^72or~O2mu9&RgE)EL{UNDqHa5
zH~w58h3>N2J4>-fd)+7vEmoXBX+>uEGQ?BH-dJXH=vWHS!*ug(<8x<DL@m*rkyt(N
z6CCa84_C$ZgSiKxSsArl<WS;h-pAl_L(;tYmjMO!&u#p39llTxF4ec-XT<elWm(j{
z!Q!|r=4{W0v0%1%>YFS;PUTG7pR$(;N#GC1#j6JQ^i+{izi-}jS36qk#J29`T$7P`
z1Fa<Vgk=zDfDdk25~Y!8AD2`4Dcl0F_ux)@O})b=u=w{?a9q5%Gnb5}ro?{C!ERT<
z*}^J5({-lPNB|P$WB1-WmGzcFOyVlAdttX==?qjX;4CcRcUqdPB(M#GxBP8KMxIG~
z+t=g8t?2}|mRm_q7#*=!;87-tE*6ELHb{N^cyzf|8eN{<_`F@XAr>kv59ly*t<Q?D
zBA&Ex*I*Lo!8}E#Qmw$?rJ9@d6jYqeahsXcX$ArPhcjZq;Lbnoq)<wdOGgIw;o&)8
zlbq?k$+^!4iPEtn<?Afoq@AI~<YI|mV&7y^(OS2%>zi05(;*V--pF-toYzo~P=RCL
zPZiv8%QVmh%Qb(`cJ5Tfo`ip?FmCh(k9l7KUoDO3xt!2u$CzomCbvNZ=}tmUMvX0%
z!o*X_ux|7jut7g1nd~!kfr>LP?4mrFUdMA#I(ER2Q2<?f57xojPaW@g2_18Zj-0WM
z2JAY4vF6+Zxxm*nNr&LCbwEl{(&0GPp~JX5h5>aab0r-IBI^6A`)2QhLc7h0+Y{k7
zNWO2)!0Y`E`(9~7%THUlruwr}ruTW5+uxU$@$WBwma7hdKSRE~wb}5&x+q%Ap0~>L
z5$_~7t=6Ez<JffwP2b(ff->p`vEX9up`yvY;ZYikztEo|2xE4*%pCp6nazZ{*Tp-R
zJ|mh2vixWE|Keyf;c5=rYM|}Y$EEu!MpUtF6p{q>IkbJ;7U$ou+ryc}gvEO0ZQMe{
zV;yX4tvz9tv5XJpBL(5t6;aFNSm}cnk!+19jay%qwjy-&)`IGKNgk|t-R@T;G+_se
zUn#fmfIa{Ic08Vn=qYN3nR_+WGifo;FkNNDp5v%d11GF?+%^(Awc^-)bD+ekwL-k}
zv-d3l0}_It0jw$7N>KFj+Jw=I&_jNqIs}d}n%H$^L^IBi95yWlb~I$O(qaSKB}ya2
zJ`Of;%~(WRY{%7;LgM(&DQiJ@4D8}0lzoMhC0au<{~E6qkI-qseTpYcMymJ{1zk#3
zn!FZPpEstfg0fdyEQg5OQfOy@L=LzV>DS~o@TZ5RkVc}3atqW;3<>NE5jf#Cqy>X;
z<zA42bD4``3mg-N1cYNy7^`(EcH{m97Mj0Tfo(t#G?<G-26zrq0)lSbzopP{e5_mx
zc)d`efhj7!%UO;VfqcoCA|$$oeMc_<&Wk&lj5-{=$dDS2X~a~(zpflBC;6HJ#fspL
z&mb`r5|t3S>QBiv<ZNIyBs72s;ygzkjleQBWfYNkX9OqFF_3l>cQ-_3_9bW{R4`SF
zyJe7xi6%*;4t!HHKfsa`Hbk)XqBMT8;Fhd~i-j&FQgcH>B9W?(pPs1>mT?5z0w>g?
z;zH#KP!AoBe^5dbOv>BH4IoFQ_!OK0lYP1(p&AmnVPw?m(Dg$Emrfu^H;ET7Fypp>
z%lVqBHH1VHu>z}rU<tbjM4MCo7ddDmfd&V^Kd=r<;tV|`G$WzxN^z5t6Rf9j$>Gef
z{3^K~w6lpj7ojryqA#Ma1jQyL#CwRbEQr(D9ibNmWuFm;D9u^HzrPoECLy>1P9;Oy
zq<8~&6Wo#t%>vo$VBN6%6_L$pv5^u{-Mtt8NJ2}D%MX*GI2^PpPeK|gO%)_-5NiWB
z5g{e}u0{m4e6Q!0yCQT)V78YB)kt4cnjpEg2P;@C3L;3Fsv(gvu0Mkf%LOEX-F;ph
zqF5YF%;8xX6kx|Kl6mb+unPmTKf8PtSwo*-_m+f)6MTduVs~ud4j_cF7TQQlXiP+F
z*K$K;X2YT_5zmrBEXS^A=%a+S9b(VLk4z)(qK1ThlhNAcTn`yPa1JE=2L;0Trg&1>
z#I^t%E{nw5AuQR#i=~)r#QS(6NXnP1XTwP`MzDV>O0(l?%h*GKqZ4;Oi6<xU+RTHz
zQkB3=9hF`aD@`D(VW>hgxY!Yhe=5)?GL`IvYSU3^lK8CxT?>c^)u7VysQ6C>Iuw(}
z2peV~^^M$mX?3uVt=KMDB}V0cOKk)ts9+sR=+vz8_fi{=6JIPyU+9*<l-dYZM+Lj1
zjM{_^>v$bdXS$M0mExTfYbgXkae0k>(K0lV@53f-2UmPbypn>vg<f8~+p>X6bj#I9
zHZ$=IRkou9&<@qD<*t(^oXP@h!(?<Lp=k|iDtOx@@hu8^iFFu?EGXvZ5`5ATWZvgV
zuZ41RH>^MfO|kbEpp(GbksB?=TYweJ7QK}K3Q!AQtRydrfUl&cT)1Qw_s9_iqV0k{
zBlLP!d9YOX5n4<T)}e~-CN!Cm4nT}!j_WHREl1OIWMxqO;heZo8f_AqIiba%W*6>9
zDTp`<^oi=mC5Gi(l4z-;MoWT(z6h<|$URGGfxNqcu#b*BlYMkaOJGieM(++wq0h$U
zOQlvV2gh9bGjlE^Lca;s?9fhdS8ZXVZ~C{PI(zOGN;YKn`Wj7^y{nvzjD-7Fpy@EK
zs*EFk4Qgb_^y*LI!F9@^pMDG84*fs@%ej`6Y)BKCW$v-3R!F18tfC`G3>DB1dp&Sb
z39+KXCh}m~XO_P|6MIM*Oj{F$bPW9L^P`P;of%1VS}ZRsk_D1Cw#8V8ol&<Nw~x%G
zMQK>Sz2&4iI19Z>@fk!=mKCGC*xw_jLXM{|EMcId5J5$2cD#)AC&5Bqq|AFR7ue6P
zO}{y6iPo;*-Xpg_DZrs(|Hgz?bSR<eD=MABRO-TZX`s|(9~_nH5MS>!P(xzVM^p+L
z>%v%?a9!Z@H!6jTkO-ldB`VY|uOQK3J4OiAtdLA<(>s&~4+1K&P%U)P(R4R@3RTgY
z@L*-$2Z7lllmo+#6Ju174Q4zY8AB9eM+`+4|2TmcEF0LbTTYVVCpSGtYh!6KOR<wQ
zq>Tqp;CX=HbIX;a>b$wiWcI!&jc}Gf=rGYogj%2wyi%BIi!AK@eNcBKEoKvDtb_Il
z_nV-8aQUYAib=ec*psQq3L@=PafPhSO>v4eQKZ|iU%pss)vR(Kl4voIbTo}a?)Ijh
zs5pielZ6@Up<IEP5h99LU2*5hylCvs6r=$I$Q4`5iF|N<c~k?FWXmm}u<wX}Qiv+f
zVZM(E>9tO|8Og?wskBtM-w9<pm^z_4aF?5~JG0P!p_e{_tK9qkc(Mw_*_v`F9nKwg
z+#i&dTyY?UsQ>FXE{~GBY*IdzWCO(~O+vHPJP%=?HaZ6CVsdq**Sc_3q<G*zW(w8Z
zc-sVCGz2#w0lMYcQckAjVE*A0_ukPoAN4x=GZ0;!sgxz?^WY5#8Z?o5A}yvC3pEy5
zVWD6-z*ef^BdTmEToJOoFj6mk(bSedu>vTH1T9!%9dksg!c?$EP%+;pC|S=lcJN<-
z0#-+9bUON%ATPcT+|k2EexKSDNIIJ0!$xcw2>tC%?;u-8e-lKX#8iqCr26o#N=zZl
zY7BPARHTkQkw;G*iD+I^on~AvM4~n#L~c4lT80hDp*axfFTj)4v#*Q)kV4?|y4|^p
zWIpScC%`oW0H!waN$Xi%I;a>-X_3Hd8%!}v77?z7g(pvgOYsqe!a-l_xj{0Q5}GXG
z3_>yA&2P#k)i|1JAdwe@M)v*~vJ;v?<OO%;X9Z?Ed5xGQR6oI7oyN{Cf~4O^s5OEB
z*b`Tr(UL6oB%!ZRjeT95qu9NQn*~k_yq6vKqfEbExjjNv;EN5)L&?JlO*F)-m$;BW
zBX0`5s3`jcEk+j`T2d?!V~7Yqz!#WOJrkOyBHk=;8YxY6kpsd8@T~ewC11h*VD@@k
z8ayl1_L}1vnrY751>lguwyo!eQa|y1i1Z_vv(%=)BX_a7ASHMV-r(SSv`R0Dry{gm
zE^s!#36Csrh$C{vQ5r^q{h=*JSP<m>0B|y{IaA%6+X5lPq_$PM<sIbvj&YE{c83$R
zz$=`+1fK?e!-a1fFaD%_N|*5-s^KQKt<v{~*O`(K1#W4#VcLiyY=>JcsG<2Hh(@yZ
zP#@G%Mlqk_7(=RC&5eR2ok8{aH5L<jS{T&b6G5gU?u61EmG?mQ4Nm34AQD{rUx7Oq
zxxh=wH8R<rTo*{-sI;w`<E;#V0}*%uh4p1RydW$Q0yHS#-ifEd$vzIQjo@j{W8p=q
z*TzI;$|9hU3gKXZc!~^yf~@nAoGqwGPz5Dqw3x-%6_Qnw)?I`mWCQ(lGBiYL_;Cf)
z4IXkahLeVqwIGe$Cl~0amqFuArlN;{pUgQSdW_YpBBCPyncyVFGf4|hD^RuRXW%`n
zI6-VBjUdjjwZ)f3stTwOw!(%;cg&T4I)|~0gdohQ^DJA-UWvbvL#vkYZMWcok$HmL
zS;z)f+7%&LCWo(;iV)NrEKF6JR(eaEO+iq6VjGHQMm`t%Y9kv^mlAf99L=hQ=o^li
z3_%d}VM-?ClOYLOX5XhYVJ<^~gmft8;&>%3^>y5-QfRqs;AcI!Q@$ZyNI_8P$LGVv
zt}9nd3PD;@+gOuHj}<ScpwCWx+qGqpY#M$>7S+Lff*TyEd-j+c#PX09IS7|-@q%_8
zWMdYkA;UMJsoQf+fC3brQ;7Sx@vfu%y)^Ze<6W}2Ow{J_u7`ZM#aqdx!$|?Q%S2o@
zYPEo>i)>7zG*-qJ($tracTK_NqnP7eN8@W~>bB!u8n{xF_ITIB_)ePovhgk&J~3+2
zc-P7V6K!=ScRol6y!0ep2EYqyDUT9eHsf7$;0F1wcq<GaygM74OWB7%g5kp|xF>*1
zUMvxY4`J~|2e=p&j#Ef1)RtwrLZ-uoVm`sZ+je3~CM1F~WCPV*En;YM7*L8iII)eM
z$x&pk<t~Kr!l}~+*ND0-_5()n@`#6-Q`X_nfe~0!k}yd2n&ix+%v2&fwolwDv;$G0
zHgsiDr}i<&IACN=F+VlC(RO08)@g*ofYBO@V>H8YMmcbTT*F-qg9S$JxL(vb@or!Q
zZmt+}rp&|N03(Q%_6aY_uEDOuh`=$ESzeP43w(i*8t5dYQ|Fj{Eif_xMsqb+^7)y-
z$Qu}KEIUP`F=mhu#I*D>NE=6tllvfiCp*YewnIEEc+6u1iR}_`0I&rctt#k{wfLuN
znMGW7(Ri1>pjUR#aU9FGEH1lXylatQNVe>suH_c|?A-CL6#}vx_rF~$+Yir5%#1}y
z6W;5b;LsGG$~n(wXp)cxgx;#S&GclIbT_UAs04ygBP?>Ep25N^Vh)H0-fWvdVTX;2
zpAU|MVjwhlVy}iBI9K-<Ru8&?t=$msBKWW*`?xR{)I){0KDrt97xyh&z;cDbD#2jw
zEaGKa59g$e3&7{-Dn1}Nn=qhC_bvEbZG8Fk<0|RiTq`Mb10qpJ?DWEk)P;A%2Vg^k
z^-dPd*rB21$Hl*c0B}w>b}+-}=jw*BRuBMgnNkyC1@o3<s|u<>fKYgVq_62<8(_n-
zj{^Z9h=c-+gdUALopJbvghBzGdLwq6{!M|g;Um%&ea1`@5l28#j^l}aHU$o~fc^>4
zoyrpCYt%(yy}%A$H$YNafDCTrh!25y;45DW7UW&WRMvm%E}T0~ViE52C9nUmr)9-S
z);JlLvP5p)((}UDuEB9qsfnEe>**TL*HaIK;R7%_IE_4U*uRGAT;rFga*oNhmO=|b
zBV6qKi?tVZ*SDkGcr8eUULjryatu@tCO^CByYK_a#gsuK5w9@<nD{EAeeDkGGoSCS
zDv1*FKtu>nq=mM5e>T|d;M!l;Y@UpfC!=h*oK#Cv63S<3<$Tw6-hYT?uM9cMS1{bw
zWl1%64yJ#KS@;g0t20h`1-{1OO0T(d2)E#WAio@16QtQ>F-|iz$we4sk@eEuw<KYl
zyS~s3pW<6J3n$5;I>?6ZaxB57#m4TzR6q`RRnh=BDjJ$Iga&%ZhIlMyqUjtetnCP-
z-YOO!h7mxH&k7s3;V{TA+~+u)lnEL*4bPTVTL`oqXFe^7tUYQvPAiCI@ba{H^Kg<i
z<rd2oM)VL~U731&L<nj>l!)iS&CfDWDdZQV@!~=4Fd1l%{5Fn!Qa0CP@cXEI7Tojv
zmgQBvLV-9jf^SI)87DVKFUbS1s+eR!R&s~~4!7Wykba#zZud(kKt>~p$l&aOH%_ds
z3yw>>!pdFYQb!jC3U4@1;&0vXn6S$o^Wb7;IV^TKSDTLn8jT2Qe^^pu9e-21oa^Q!
zoY{NRg?eu@J_&RNc@5QI`#iDk-j^R{FPX#8fqet10>LZo<nRjb^)qE+gm$314N)4e
zUM#$bDet$b?}e+OW1u=Xl;x+da38!EyEBBQkuolv=h?%KOJADrsX2TfTL8jAoUKsM
zl`B@s@QBbkmyii#fS0Ii*YC3y&TPN?H~E7=d<v*Rtohcc)o^5vYJSc6zk?@2RR=_z
zmkW(Du-erZzpBf-z~KiuK^>6lhotbMM#1f?_T>wFK{j|WaOr8?lLE_Q*JB<pg`$i!
zcwA7CajHuEEY-;BxSQ!B-lR-zhA!+txP^C(Ni+;=eNgja%g0@c?87nkwV>x5xD0=H
z^$*A9;F~Jn*AD)1(AH`NcO}dw6!2I6>{~M!J7dZFSfS}+-n>j5h92w(pmZnWYEnhx
ztk{$--wG7jr>g9g9S|=CC_RsLcWmCNOTB-!|Dz23VUQpOq=YvUr9bldSYN}v$h~t8
z<*h#TorY_}3_#(W^_>|j@v~p{Y+5|E{OPKP2l!$>Xavf}Hd)nN6Yeg07?rACLvu~g
zN<e5XloiA#TMj?W@w4h{jGo@M8nXp0LtNVZ;>mWaUm3bH{%s0)kr6o3^Q2+n(~ILm
zv>cumdPv~w@LO0Lm8(Y?JBni*TtWDw6muJe+lLuj?&ki__ujw${U+azYWyG{mzW8%
zD9Q!$xVL$YozrXo=X>^u)rL*;f9nZ-d^~h>?QrDcitWD_Ch4(9->#e8y}QF+{@#OR
zcjL|mnG4D{zHh7lZ3<UiUcBk7to8F(4bH!9t<BZPhxX|8EkC<y$#3(HZpwGu%&61d
z6Y=r4M<Ks3DriWVA9tfwSpVCHtjag?dFN<VUzqCRI_5QO^3o6NDI8t!E%e(sT9VQ6
zhM(M}^-T@`0!1D8mffrSE#k*NKo*;dG{s>8-J;Cj{)V^4x8r6^MI7hz$A8#;*;*d*
zyf<E{;?QreM{>-_Z?Lwo#y&K-j!Pg^`Tmww>1*+Q@VD!uUg9kAxr6sP`I_*@i8~rN
z-Yze!<#bB@3uKhGp`+i)ca!yR7mJczq=SOIGxOSB{v!d-Szz{ZIR3GZ)jvQrc0q26
zGxL7_tCc*xv+s8F**`EnJI-!dd*bb@+iTs26UN!i<`kw_`u%WvX_qt(WC1dzu2l92
zvl<7w6m&WM&dy$^k9Ol>0B`<KZ)xRXWsh)^e}DqBE${5=b^k&A2grz8cKr?jMbO8A
zW(U$Nhj#V2D=N(z7kou5$9KPTX8yf<g5M!P_QUwEUkjgad70%juHT&+k7_!nGdxBf
z{R8w@{Fkpq05sEi9LP~4ucmW7!*k^MKR|!RfBst7xFz{tAR~?Znx?l5&w+n|MCU($
zz49R_IqM%v@){><YSOJee|#9H)N)t%(VGqL+Vib5$Jffa{n<<I>>A$qp#7f#*Z=I>
z9&shBpr1D$-mKaj5%}}vuk$<O48{k%D8$UyRZ}bPC+8oa?f$_b^&j^+ZkjU=bR=ZE
zuR)kr&d-<QamT7%z6V0;IvgA~jfXzyWknL+bnQy;u=xqo8yyeEA?xln-MUiWo5|Wl
z{~b{v&98Cqre}2B?ol1ze05Ecx31KU<QT&)9*bPiH%-5Hy_5Sk4qW){YpH%+tKMh!
zG6HLpP0#+09C$yK9(<eDT<IHi_gZ!R?^vMj{ncBH&Y`|uW_UN2Ty*ZYkL7(*diagm
zTuF^SR6iOR*2)_9(b=~z?hE~^uS=g9-amK*_S%?F2Ka_=dz&kBqu<YrC!^i^)ui>7
zS|vk=hJKbCRl7E>c=IIpx2wv&sS<prv52KOvF%s+UW8_VoqARC;@jc~Q;#Wai_F}5
z2Jv}ddZEh8@0)wm-k!cSx|D<a;#p9|w?0ZE`)W||okz{PUQ!OeY@Fh)%`hY(c%gt!
zXFPqU*i^J=Ip2SFPljn)CR9Z^%Leiu)_nT5tE(Y>VYR+FqJt%_d;R8a*te1O`b?jL
zwjQbWt}Mip0o%Hvz4xcE?<5o^@;bo5?a8Qp=ViU|vQG7`u1lY%<2yhkC|&U@$oAjV
z9{|w{3eW^;u0&OYeYpQXKI-nzqmNAzejiM2+@!;X9>)}n6LVG-e^Z!Q6k=Un&~@nx
zyu*N#Efgy(^q5py8+I3JRZ%HijMurZXtD15z7xD;iv>vJrW!f);@QiJthqgd8;r`F
zxErO=3l$J8S+7&YOl^iv_1TTH7$zk21yp#;Xma22cPBFxdt^%7IT_+oxI!|hCcQP<
z@xE%WDHKVfLa1Z8;enMZhn2m4MDq`HU8Lq12ZQGlN=<)U-u2``j$+^nCG->uU>171
z-R=v!{W_24AMB>@<yZ@Vfdt@%r{(P(4`gI}RyO?G7_@Kb@6@H1Ds8@d#kh0wMpK3<
z2|boftngcfxO@%2>&_osA1Ras;$O+=cpHY#Q102@;51J5W}^3<f-qOgK>WM+fvgo?
zF5?~LZtLzChh1cbw`{$&$$XrwQq78Qv0{c++dKb#RT*kN7ULZzHLBk}^_-R-s44hX
z$r<MucCO>il}!hiRJ-2jPZ=^T<#5?j2p%G!@^dHO?AbJ3z9+1~A_NzUKxd$-GV^uU
zHdOTc@u{Ius)Gt9w;|1!9$(4vw511YVRF_&MgHf!ZKp;9=+%kvo`6K8Sa}t1AM`7a
zL=O)$6kw%7N`pNsE^2uBzR_N>s(j}<AOs0~v|u2-sJix6f1+AmsV^*|IZ$r+w9SQ|
z<?`L2$SrW3eA=US+EUNfKDRro;|OvdK+b4p^l-pw{|P-8HZ*Zr_;FZ6P<H6_(LXjT
z?>qHsV@{Pcl*Pg=2R%7mBVyINxq*cAPk^bLVcvH|rq6*VzlBe8tf!6s9QIO%KG6k=
zxyb#k%s|PYh8ldrHJHfVf^u*`G7R|VR@g?TqlY(y#r`9P2eV1%?o8NnqI3fGan#){
z@&0$S#D7uHY|viLd@p`;xHoqzELMVdo<dLfii#gfl6y>e>5=BRnZMsS5XKJw<_FnH
zIKR4n#jk-U|90=-_c`{QZg7cnLOj^;Y@-Lvrrc^`Y<k4lzR<c7+GZ4;)jEUFO+tV#
z(N^wl`zwqX^GU>I126B8|Ef041Y+<CgaA7xw?*ny_ASEWL1R!O_*Cc|Z|2(LoXV;N
z4r_pe$?2%OLGjI_>Efp_2C!Y9ddfZGOI&&sQyu?-X)fB(W?HGkSU^IKz~%PB2|XsG
z(l>mu1#mwLD<bVl-|>@H|8yVn-_Z74&-EYlE74Z#+VC?V0x{zsLwj{<^$&8l!<GOU
zgYb!MS9SgcZdNr%qD5f6ZXe3JU0rVr93T=+V`b5lRS$CgVDS<I8~7FWNyk;$8S&tH
ziEY#vWtGr|p9c<vUOz6bu5|YN&$k=j^}nA%{92Fy^s@M_|NY#>HwHU6kI?3Oxt=p8
ztQd<(NM7=(&~yAhpNA?pv^gi<ZEqF+PSDYlsZ48DeC|J=c1&xBe?L><vuc$8553z~
z6M78)rFYv(smFhR&%n+VnVIPb9fA4Xm`NEZDSEk4tu5@oa0)$^Q_PVK)Fu<P$B3vV
zp{Hgr!*A-i#(_pGh-nRt9{yw0r$qc3_O&j|>f{MMS}QWO&LR{{5DuXZ-28RSim@0h
zD52}G$~`Pl?`~MQu)3i{93eGrKntW*7rD3LS3$F28K3G;Z`(8TTg*RH1NEw(oVbf8
zjwECP<!uDzgotHLKOcoV)Pf}NzKCsdFCuS4tHF>y1MZC<6TI4fS+-rt`kE?!4=aw4
zttV`MJZv!{T}e-EWQJeSB6gz{P}>?JGw^^*EazVEONnpP+PpgU!S;Cy_S|W^7k|@S
zV&fBc1@tovW_bC(h=bIFS?z<mj3p!ll}EfsUuAm~K0$dO`UJz8b)8Xdy0(?5rKdwm
zjeh1CGyIXn1W1_Pk{MVO^e<EOwuZ~!{fYBi3~1abj@H$`WRrkufNbD`mwsjsGyIK&
z??OW0#nJ=864O~P5qNT&S|=eeQM&Jx6U^@mOSi-lVNJv9t+b~{X-j`l+rI0#y1F2q
z4k&B>vuLY~HvAE&8!9cGJ_Yl$zU>=L4@NwBqPKa|)PVt7-%K4US^_@Q>C-m8n)txN
zNA=?ropNclFpYsyXbMc>^@EezRuD!Sxxk*ePE2YlyaL!>Z&<wr7TGyO+&qbPXHpNY
ziyP8~2?!!SK`A1AP}v)fe9vDOM-sH4f*I-{{?h@E3V19S-oF%k7gj%!Ow&0%pbvA3
zOrY@fX^tDeJ;91$0mex}P@%^?F&FAMY@jfSeio132=NjW7@+I8dRu%uI3<yuL?G#d
zdkE9dQ~4jZVuhZky~N{*$)JnH%~?}!!*r^{BU_?i9+kpvI8juO0-%7HZ4noJ_ZG1>
zL{OZ>wrGrcU%5>awGc2FV|?9!Z#|(BFHlL&f?fR4_K_llW)WY#^y-38FpHz-HgrWu
zLzOT=Lo@pBuJ~L#$i+iigPxJW{MGLzW85RIh8+fWGv~TNb=EMLDk5b-c4}YEU)qI#
z9~&aDsW+e6W|w%kHCpHk6!IoT4Z}8ahWcVZ{!HVZSml&Vu<1gGElQSRW>WOyRAz;K
zF34|VHb9F2&D?aM3`FX6^|K{*bf<vk)rRz4qz9UGy81T~YZEL%TFnTpxv3t$vf*-*
zo^hR7Vf-kR@j_XGV>Gkvmt7lr&?z%ekv|m%{tUv<<`+wB^1Av?fXP;V-FgD(JdtH~
zE?us)>Wd%0`R7eyIE3G5cj5aFle^CTMIgdapEqz$zDN1YT$pLN!$!U4nr#uR(94p2
z;108Ps6u9-Q)|@i9U%;{O|t%^H4injb{R7kl8_NWV2boW=w9X3W4jQZs?f7cnc<hK
z{7+bFwZhXJ(2}r$`71Z6xhXyPI*mHpL$yu$nx*>~d}=Q9*Mfx67uRUi(i64J@EcV@
zA4lxDJ7M7us<w448ZJ3qISdbiN>5y)%`B|0cY`fg*F_uM@K=;Z%OJ7DrFSd$z@~1|
zv6deAPRNbESt<9F6h%DOIVWvS+`^&&QdabE?Iw7z!+TPu*rUR*-Z*B>&#N)R?V?9u
zo|BB85Zk-1CWcly;QLD2TonBB2VrLXK85p_*8g!2l#~2e5{=xrzO;IS07i1jy@Akl
z_L(?l#kzs;k6G)WDYcc*)EQf*j}`<%*=sh(#ifkd-F7x#twDk|qs{iWjUJfPHWYNX
zEDHq9!?b1^J*wXV1FVVAEcpI652i?%AAKkd%nI1xWd>1q>E{W+FIqG89@P^r`$ZmY
zsr&Q33Rk{uvgc^?_Ki-_w3+9t$NJvTn(uxe9dTqT38xQ7oShdb!?0eKkSkfXCukA3
zzBh;TH&^zHHS<X!vxnujt=|)6<um5q^JiDjEF6xA`1sQlZZYe=Qj-oYlK($!eS2Jt
z+xKuzB^8BK=rW@ar9w!$jFEKHg;41-;Sj=*Zd20?6Q@HmQ%UGDCzYr)NJ_Vn(BoE2
z65S>m@^qV;rlz^S`>CAo`F%d`-_P26ueJ8tYp=ETTI=D(q!v!?=5sW&nkScbaG9h&
z_wheES4p1|d5UjpRt`;R$O3R{mrA%~E*IA&-16`luZX<RT1s61&~-|m`mEOEbri@O
z*p<?xj`cLPlERnNZXLMq4%L79JFs=Q?(#(W0J3;-7(cJVN%Rp8`8+L?`;~><`|<{v
z<-(r4zc8_S`ShGucZSXYlYeKyVH)>ZHxE2BXlBtX@4fFpwgOa1Bwpcbc51>_|J=MZ
zb&RzZaA+yA^J4S(xf?#_H#)E8&D?{_mP@q+&LaJzA^pg)d}e2X;vA<GyUAa~(;U<;
zZ|oo41+H)8`kT9m<9xg4MMci8aQg+1t2mk+x^TlkpEyXHn{&smEaJpv_HZgtyQ1nn
z1#cmdWY5VA2hBGdrtUoNu)An>x>6x7gg!gEb1?YnUsd!>Q&=n4r5cSYfHs1=>{302
z7`EVA4fHVs6Z@3c!D*j}f49XIrM5z64iA3|P*r~vTX#?8P4KTz$`ir&Cv<K;mwD}v
zgROG6f=P-HKk+o7L0R}#e^va$UPg`lpb7Wtl5FX_jj0Ygo&n1t<}vVE`~8(VuWzHb
zBs>%s*PQOzxuk51^k&$K__c`kSFkwn0!?15I4}6ouOHSyKR<Y^E2lIETES)CkU;5a
zWyje<>7t|jN9np><b`7A4DX-bqc_7=#oOrvpG~1O<Q-bx8xI$eUowhHM}MssbN~LT
zP5RmHf|{Rre>VqSqNZ^A%@=I<i@e&>p}ki-7qk>hKa{697+*z{x$c7y8grxA`8z7;
z`xohhbM2ZzX0Xq9niB=NYcif3p)tF{uIylt`B8q@p~TW$KK3D~T2WZceuV9AXP-PH
zuzo<hj;cQh=N+ujJ}yB@?@B#r*1YI|PU*Zg`9GW=1dASj3B5FBEtISBcF0a8RWr}0
zKbFkhM02p1m<;yr$!nVg6&wnInP@zR`=nB==jZyiIYbZEI#hNUI3InQ?Jb&PezAZ5
zp^&u<(i4`g8J5ky&KfcP;wk#@<)>I^Bp=_V_@6nNA0czNHBdv`;X{X#fJO`W{|x@p
zVA4+@+KowxARYQZ5`Vt3!e&Q+d8j{vdBHd52TvO{KMChQ1(t)tT(AH0C9#p3wt45N
zcw8Q^xECq(%*A#?^uuT5(GOCi=+8V2?LB{P7J|-N|BjOzl;n4rJfMrc(rkT5;$UwM
z9Qwt`-U*l*^Et_qui65#irF!N>LA?RvfL{jr*_#+Iwv5%aFxO{RZ2|?ruw^#8?s`^
z;e2*H>DI_oUV~r^WPD#RXZe8DmB8xUy<qjuLj20sLB%g@G<mCG?PN$D-IB*QK9Q1h
z8&swOH=M+{EN1p5`7)c*H%|UaUKW4)K7*{vX3{-)e616y{}=4l0Hdef4HIGf8s*(;
z5cow<237<)g8y6b;rrtC$=@}hwXZfO>TtiL6EVPT5wlm#kkytN9KZUyY-{=YH)9h-
z%f>P3pDBf0avpyX;53$o^N1A|>=E@oKF1Hx=S#s=fhU8+g6VIbvEqW=qL#-O_?h}+
z(mh}tsqFVR?^t<(r>N}lWxhD;j2?$w_x>xQfhyNyNlvixjrA~<wS~ovcrIvg%BdR*
znn9T43eUS?3VX43v+z;TI0`WUEEt!mS#i@a56LOvg}u37f6a|d+m}XSR*Pg`E6l<0
zfn<m7W3g92@~jEOFs)ScStYgE?<tzc{S{1;hmS9nlVxMyqFN4tUD%8z`F}hKmY{yT
z%;FL(sR@#bx1T5F)#LQB0fBkq^j=D;9;vU}$fDogSil~)sN+wz8Oh<@%Vdq>xniU|
z)l7?{d%gS8YMN}mxta7;Ma4#l@r%yq0Mp+HVyvmvJ{v5udi;PN!2XhLNH2t162Sd*
z8O?mm-~a9yO#RT#;*#8bRGwm%sVIOfLraU=#b<Ym6dzad#q6feDZS}Bhga;5f0dOc
zldK(}ewbFKHgkAy-5Ia4Qe~4Po8V?p0jW@_fF;GlT{o;)bVHIWS)<>>fCCH-V2&zd
z9nSL)zEg!YHOU1SwU>7^!^t~<m$8-BjILdBHc(X7paN?;-us%+i75v+2A0;mtX99w
zRdndNJ4|)S{+b}k#25nv(U3_>aI(-yn$mNF-*@NDA6S_qlB%3#427n2C+TL8#P_br
zHl+J4pHj6aDa564dCW4n;?_?V>fs;J3B)%>0%|F!8D9zYrF35|yiPg`TS!xE!*bDr
zL~yl4s`4)7SA2h+&-P@o=+Dv+OJ-6@xQ7)t+FHQI>`0Ss&jAjO!YdP~FE#iI!$f*@
zT@~Mi50dZ{KobIooBSh0Wmxcck}Ej`34ti|YH`Y38LtkxG0g%4MT$gF45+Y}j;4FY
zS{piv;zKOp<}r}Ut^oQT5FOwjn@!?*@64sbZs2DtfW`>Tt7;9SuQ?pQo+_*4f|^)l
z;lgX()M{7MhPSR{PDQ{f2sreo{VBv#u>I5feE3m5zma4%jZWP;{-e&Fq7eVRqBJHb
zOGH-2ZI3;0$~eBL#7z2?jFd-%RT#@_H)gn_R++hzML0yw1FYY=GMds^p|8KQFbZBs
zuyItCx1yk}&kZj769|r6YX<2c*r3W=w94OK)FKB?*VGaLvDDHu2UnfzvJrN)HDqGW
z<D<bjb)#7w_0*?1xO`5R4YFt0C|psy%h#1|T<k{XF@ev3tX<=dZ{5r4gKo1>l7Q)T
zvb<QuktzIj2zfG)4uf#J$sU$gZ5Pe=-z_>M&zN4jFPEPhv@HIwl2y`sa!`JakT>=`
zVO|XF*B7IBN{NZ|ru;y`lo<gcYggSEJ=OV|Nk8&2Jk85?@jl7<CLn1DOUdeGxlcO4
zEeAKkUNy+fIq1F%e4V-g(X)1uNxULaNBS7?pg<!FPgm|Ym3(SRGMVJYR>mn|U<BhB
zO4eCc(&ReWr+B;>2itzj`BaFwyx?LuyE|43vnKxZVVTf5MblzT6)}z*v^ZJm!7sgB
zP(hc-N<wWVhwhna##nDBSHlgq19b8t;bxg24L2bBh`0%02uR-T4J~NqULY$G-pT8F
zh0%Pe-wa-+`E8?VQ5Y`SdUJ!LgP_s~|1+4xoyV)gtTt1A3S3+ZH=55k?tbDJIq+4Q
ziI|(X#bD?x4wz!TU-q$8D3bfV&A=f?NH2UrFQ4qip<0>0P!6Aa^-+1Rx%^5rd+2mL
zN}YGgm1GTtf<0aZ_IL-)r?+jNWRzh|7>%v9tGuLZpF`!vVM$CVQiMtuf=*Yq@imC!
zIHF{;mvrJKmt6j_Sa*;!JYK<xseElcTR3rw?$IG~Fy!Fv|7F7LCybAgjEFbcX85Mj
zQV&w*$7n~f`*F-<kubF;E}s3cj}$;InwfT<T|gF|JUUpcEsXsbZ{Kb98WYKH_#_K$
z$Ox>3THttgQ{qw4y%`=x2+kyTi^r3Rb(~>+ZW^azh4gWG1@ZO8RJ*RP9YgVt{-Pg8
z<joH28I5ZDRf}Uog=U8RqZ6*O^$g9U#J77{H*33Op<xrhXXFbGBzFscyzdMgIZCzm
z<muRx(wBRMPDCXdGTtZdpOylv8p8oe<3RSW(d$m#cN-Zg9Qa-LaF61XNpDMS4)9+p
zS7Mt+Vo!{rETW4VJ5~^?4Vl1Au!^hhZT6Gp&LDrKbktBT3=fT~*_&!TkM}LjF8gao
zHsQ^8>XYfM3ynw?Om-w`b7C@=<2!rvObA=bDr^N=1*ntLL^b_d${n?CGwmOp?b_`C
zp;idz7vwYz4tZjZe+v~~#>(Ud(pUU7U~9M2tg7CelqX;q;?doa_QAm%dkQhSSda#w
z)eN5uT9GcI<?_1CliOf_U_}0n4vlb1lIQ8lMyyTaYAT@ydzlZcICKqwAJ3`yX=Mr2
z*$xwEN!P=1;+PpzPA|6)4&cCx<+(h<gd1SjUN7QWcYGikVopqc1R>1b3g;Y^YzC@=
zeu3x#cxN(~Id-+^)4+U1Ig`WzwJ9YPt}}6l&ftzdH}Yzn)I6+tb~_;0EVk$Jms$`C
zh`+~Q3rN{UD|^IzOH9(YT*HgFBG>94m5)15!SPbt4KUDv>>P4f+m=KA?cAWcT~uFf
z!j@O$FVPKR`Y72xV|eiW1V$LN;%S^UlxR8?aQ38?J;oIi%M2||ktxfH8*$`@q{(1=
zsQ9?xHg*_S2BOm2X=P7PnZyP|#%kV)BzZ*7KC(1fakMs^ru(XNT7iY0Nsg<@hYl@~
ztuDn);^YG@(b_L3*JFd*tB`maxQ%R*!m@f-I2j%r(ZijBJ+0W{x^ar+Xi7%ZFcL)z
ziJ)YamvcucM%-*Rj#yh@zEPHjX8*GxoE@|Qk|qM9;o_X|>!0%)n{^3|{5tM{`N`r@
z`ta<DZf`_LtJz)cFQkYudIh1$0ZV!UiT4N&MV~t6Ok=zA8kvvw(b|3vh0d&%9@#&d
z=G6V<iFM^!ueexAqVp_fIIZo;kb&>ilTV2wVD>32sR+_LJaI%Yd<;(`@8qhG<L;vw
z^E$)`O`wKPeW0zk@Ny0I5I3Bg6D63$kUPZn?BG>USl+}sL{hh4o1Vwc7G5&4yg#5g
z+|`nTmiIXm+0sli5Y77N5cw56YH;9VK=96?Lk|QcNMcfSBgYR2hG9P{W-XZ}w`usE
z6Az+hQ)HFa*^_D@^;E&NYU{mAIC`Mq>uX0Bxve`E2+a&(z!o?;+`R{sh^^v99Kj2E
z49qOPdQ9Q_N|VQh^+NX7CIG&-ZQ!1v5C3eF8$+m=kqa+ZRKJc)ka&Yo2DnOQ8LJ4}
zJl4lM?<|O;qRe@>e%gO~+f^f-$18H5!<+q=CNFXNndiz9jzHkz>UnP~4Q0wJ0$@!;
zi&TWgM#!E}4IgYdQi0r#33_WGR9ofBLhsv+AYku5mUBiBr4}dIn}VnY=Vo7nvVbcf
z4ply7x~VT+1L0m)E-&1<64G2mIKa>OAUUN(010jiYb#TLO`9ARe*6N3NKUbK?}@*~
ze$T<?tU|<jZRL3i(TnOH-sCnuDKo-nJWE)>X+>!7X;LN}(B{57<J#o<6wUVM7$j{z
zc^Qp@>Hf$)mSDS(W8OZw6%6&9Gcnm@#Pxr1z(<8}=ItrOe3@Ng4Rt&oeW;(o0T#0J
zawrTjE$WBn@S;u<YZ_PBs5m7MeN&>%zdt4<)NDRnfmkC69r~Pky_0*WX5m+%iOC!z
zuHK7dVA~USOs&|lnBy@p`6qZ*n9$-R>^Fh9@~-_!Q&(JRs5{NNw71OO;`LYau3p>A
zHHYR>Lns&{rZ^DSKKjiPdF)U~h%?~a2Qwt0s#X@e_f3-Vmb_D|?f!P6NWL;!pUOK9
zR}Tz<5ahWZwR3qtBZ;OjG=tMx3&JE!YZXGq9K+XHSlLs3y6j-Km>KY-x;q#MkY9Ha
z8c%PG3kH|0u|Y59WOb{>0=v`|6bWppGrg!GM<tHvj6%gMb87O3b>xRz?oS-;c{qm$
z9vBotPB&8|r?28QIfpE7LpCddzB5l&wHd0~T~|h?*f%}JLQWy*n21J^RGpes;f3-;
z4fmtw^nC0D5u`L1AU6WT{*`(FF(lfywlWb*THk0rK6=S_a};)RnZb8*ZC&ex)HX+K
zk^+?IuzgG8aiS=xd|2MpJ{%i|gn|j+o$<s~yc)-cP3BNWHhELkdDX*oM5k5@cA|<$
zVav}|@_?}446>iY8?%vZq%oDoa`4>|R0dOJhZ--#soRc}7$I1N+?3fSqQ%M0<nqr6
z?4XXI(}mM9ogbZ=ys>q%0xDB>e~2x9_K<rp5}v~x{T`fI!KDowIw32LZAYb!b}RZm
z9tzSV#hr|*tpyVKpym*^Zq$rR{5s4fe*YzS_#`5M9YZQkZix01G#Mf1n(&X{V2!wD
z#hJL~1U4=+2oE}VD6HY0qH$pkh%?8(6`UM8?$k63p3NNR@9Q|ieKwp07L1-0*>PXS
z2+p{FpRhnU_#_TnR~BAzVZ4p$yMS{!OOd52dtDZAGOJcm9IFGr>Hap*E1CC7>=ocs
zAwZ(|54%)((o5p15~i&7vY`ND9LkJ1M;?V`4v&v^{50su5SRyjwH+jVVL`Q1_VC0;
zh^jO!Lo?trPEDs^ne6+-gu|<&gdf4L`(|K2{|jpbS^G96Rd#D}G8qJUWK_KEfU7{@
zi{cI+O8z{1xRpp^v(jrDhC|JhJM|EmI)MZCM2AE3z!7YnfIQN~V+rFM*>TnHKR&Oj
zz3s&fsCpFrMS8a&B@R5NC|ntGrEv$diqLF=zf+R~EUN1h-0zw=y7x=)=OOWR&}bnF
zbL<$W8&OM##QGeQstNxPve5RhJ&A+c*7%$?6yL@O2>bB3Eo$slfmvK)m*)PZPp$W<
zBZ&Zk?+ekG^zvL_i4W3FamA!g|AgDMRaAW76b@PG$#Ebqu5ji4dWgPA*vH%jeD*8@
z7A!qy$Q)?UL)tt{U_uYitX@5j*Ro5z>QUxwVXl0)UXojez<7L}Z6b4eI{CHqDUzOD
zl+gL}Xd`Gyv#;qontYp6l!(s}7F3IKMc1-la-%Jf-5|euGqoEbf6DvP_)^+wEsnNp
z^~PFvU>cY0s;Wj6TYmMI#P%V)l{uGO>C{V55#}w&$YSA3Y6@QQ8mF<I322NjXQQtD
zS@Apb>@KfQ8G{>0HD?hCd8Xyy`p&1^fk<PU^Rz58a_%aOTtoL2S7S*QgoRkyIIb5I
z^c0J4@~&n>McBG;?m0^_5ObyQp02ys9)%b;+E{BNn$iDtE0rD0A5;XLGa@j1_cDCk
zd?z#-4M)NPPf4px3?-g%MTFwLvRU8}C*%YJgy$G{ooFaa-tDj)lERU6&*8qSZT)J<
zf&AtynSZ^bt{)_@C>Sr`5I63j`3CX%il9eHIP-KRXCGo=HQD`WF6!iM><C<sIGke(
zImD04A*v4Ht5Y*()>$`Qfm!J8Q&GT%%^h_egj&><2t&+Iz`tC(3EQNL0x|MXEpX8h
z%ndp%H+nuba|hVoryh*U3ATcyVV`H+xQ^~i+5{dbpaF~hBT740cXe2ndp=c1;NCYM
zJevcoyTz9Q%n6!qAUy08hRY!2$BD~-nn(Ksw&qF?oOs`ogxCjO)M+j`<)PVoINEJO
z;zzP-xS@O7gwD{R;oD%>91~l<+$aPG;x8jeXtbE4ok0*VqA6J_tcSI(iMOirBMx&v
zeA}?;=RLH_x!gJ7bw{;<g;2v;PnHa<1k^_t1jMCjY>akA7H&LqV$cWS906GEL~K2p
zQSy^49l*){&dOljul1m2RsVy`_rvbVI5HpTm|J&LhZ7|KTY{rxnX~TI?#jri&iV}k
zha(sF;!Jd3nJqT>lY>Em#D^*`9=v#SXVv41{)G{~X+ZR2^&4N=X>&l$IJPNth$4wh
z@eTTQ7Tk}+?$Hxb_Lql`BV<y0|3~JUB^)PTQ9C$9)nLzqsJE+cAxrjd{+CJz@q7-x
z;HEw>+JIvX_R*OYv=bc0U#FJ_jP0Q*KJ!+xp>Lea3zokV)q-OSx?K#~Z`siGG9Mgm
zjlzc;y@2~Q*NHavwFHm=8h3oHj`+JO%oS|lkmjL(H?Zs|EhDg>1aPf$v!1XR${Rk2
z;3{tTk~Os@JW~j`Z9fq#OyC#Y_u^ZF+yNFx$%`|``1SZ&6G{b0Y6@9R$!b1Dk>Gs5
zJ>R#l>Ve=mJu)K|u;v#1<%AtD;ki1(OCSvc$bu(r>~$mBlHreSa$%jX4Hzq}z6NOj
zC|dKR503rK?letoFs|$yLYRwS{M7xj;r*<XTIaEbFM$YNuYjm<>><5RCFs!Qa9uZp
z&=%yn<&oehd1=4^!W}=r9mzbN&PMTiNd2<J6%cqTe@t|4;y|<k40Y!<oH<c~$jKpa
z!gwZ7=JZ5W4!0e@204L=ew{Jw=>K;j4c?B8dK$bjM$=B#nRplK<LbX6{^WlAv2{}`
z{1h#h7)R8k(t+Y#1Ni+q4b2^O=JZ)EYy7&#pe-@tShbmp^Mql%=b!G`$gxR6_od;m
z-KNLVuq0W*O^>SkR9Gvz*B!vrHgO`SVBQu3%HIl?aNghAw3yR}y9wvFi2ezVw5~$L
zWN2sbXGC}(&IxxQEamvF3MX%CIs!j(C<^FKMy@cv?KR&>Q)pJmT1r*`h9Wu8lEc_f
z-rls8bs*l4S*PcZ2vUrxWq(9HSV!TC2kq<tvt1VVCIOL^HC?SH5o>A=AeTf=Bk#5+
zkfbY42uRM4Nnw#TXYTT#)=>V=8Y}`)+Q+N$#7SR?`I#8GQg%Pb8CU^f3pkx_D#Ady
zF;A`$m}bD*8^5FNmELY--MF=0zqhC&SedXl1#@C7jX|Hsa~}Hijivw5>Yumc$u+Z(
zxqsPoeLi-Kh8NvIObcYv{zV*oi?Z;}h2wGRgKd>JJ1+0*RzM_nGT-4d{FWU}FBnQg
z75Ka+f;$uZrmX4yfC}LssKR7VSwPQ?sPaz7&0{PCUUXL`?BhDuwQ{Q?T|v@--xSM>
zg^WUZ>i8q_dr`+4Y+ZHk{!XRFjS%N5D?K9}h%?K1yn*XQEMv!z!FGc`yY%g&qsj8(
z*<lBmXv`<?AJO$oUS8}B*uq0Jo3p5dBobc2FXgOoC0RmV;5oDC4^X0?rFTC;GIWZ@
zOh0uo9@v$Rt=+Tx7QH&Ny=pWSk#bRq>?nx0^kvrAA=>?r7N>KPfiv5?3i4u#ybNL`
zdmQ(6&k5DOcxGqS2xWRicey67Y>JR8=)PA;XbiKcOOuC__X&OF_dsF=_3op9Z;!{g
zNBp*ogwG5a2k-Ab9tiQsm@%~Fmli{1p<Jw|%#iuC7&0#1y`7o6^}X%VYZf&(fWW6X
z6h~)+Ot(}J(*nOOdpf!SGJEnk6SENic<vK*-lM-wpX!-jt1YyFU#YtSafZuc+sq;M
z)lJB)w+@iqOsP5ItgcL`f4gtxp86s0d|v!KSLfgz;J~@iTR}0q0`O}(V-|9pZ1;mF
z=4g2#?$PF4HN(`UFS#eSSMiKy5C^vK;&;Vpko{#u{uAUr9CsdA$ie0G48CnO+4Isd
ze4r=yGxMpmz{+x&!PmI_=KgGOTIwIq3nxoRHbV&#>d&_!-@2?_@7^lpRA?o3a)yS?
zy9l#@Vla;1#|7?WwG-gV4L^Sxb7!0@NtsEhaioGDDOKFg#P9WX@_L<A@rzS|+p&c&
zLXIt<6FlaHY;aB$ddHdZ+#w}Go)KAZT(gmUkMQb;c2-1#_0zlvI5Okvpgk*e{M5^-
zQ+I!D=?bBep)x^Q3jUTRXQyR}C!Q$p9sAqNY|B6t{){jDX~6t{_<ziglgM3oxpu%&
zt=>;ZV+td&1#~XURI~bJW+v@wZQXyk<5BgB?1uV-Jg&~u0EaNGUEm{9Wt8wA53t*5
z5kryb)0lud4p6NsjCU5fO!ks!*8ZP&Xz~oD*GRA47C8*JS8QCB9cN!)97pB**MhW+
z`KcDe87!3-mJ~^aCxCjFWQyTFuh_7rE6(75P#?UuJdAcj>0+cZF3nfwT!UI-16BX<
z5n(Ow)nC%B%{F#X!C|JEjfz+U9NcFV)~@&+qQObn3%qBZ9Hr0J;9V77BYjdo9{zm=
z{^w#=eVbR+l#o=9%KrwzAW*_}6$xsSCK+wE`_d02)ZiTo=o8168UW$aFb*Pi<xgWh
zu!Pfi85uAOjySbEzC_|olYgklVR^-^d*4*Uxu}xjSr<IRxX5`tM`Ys{`)s)$=R#j6
zU%<gclos-PgWamFEMtFQ^Ya+gnRC!PTS&L8)8i!K_NFL$FEe=4m9M!JynpmXxnYJ2
zHrVltG7KH7L{*6DN6vvYR8cV|_GN1D;u&k8S({fIybdbR)Wga?GvBeA<Cd9w)sB=q
z)0*lGe<P#8OYV}44sex)uQR+f_bHT`bv1SsXzF8g=9KZZaL#Xi7{s9k`PGbs8I)=h
zi0<pjB9LDU3dc`or8q<?Jw>B@I}S18$7>=c%V(soG>*nR_0y95&={iE#>Qs-arz9r
zUc(h-OR@WS7<R6^{G>5h(tidX3A3CQz92c8yq6=WJA4*NQ`+yEc*afCxqw3<`Xx8l
zN`ADkezXNnpWy0ml$x%j!p7C0b@uT08~l1>$T;Xa>1Wu{_~CH|J>7!&bA~$LHXlo|
zCJym8EBCx%`Ddj$5D;Ydj-}zl&*w*o%CAogsKo*fz3AzWFtD&&e(~m2@%%aAScjsY
z&g`FmU}1jP%=rjf4q35!7o8h$b3U_2Gy-a>t^BW(eyRUD&A)H4Ang?M)&I^$%!=$6
z{%{K}2d&FV=s!L2-XbOS{{k!vdT{{m1ptEP66(FiuNBoh+_uQt-Tpo5Jx?R%7Zx;=
z3BVpa`RVZ51)gxIAugi<ACqz=LQ+0+xIpj6bD=DI{S1=gbrVQxHQ?BPcEX&InsSwS
zXBr*Q*F|AuXBFsAf`7)_hIRO~X|ZY{-;r9{{LQ-7ZTlA4EwH8q+z?yQgel80EK~^G
zy(Mvs#eK#@n6-=1f+uF5i;$LIJ2e=@N*qT{vlgu1<jz!ltHrsu${jQQCDwq{JD`+5
zz$l0~#7%W50lzv?0M_@20t;XN?=10P7TL!C%yI}`YPeNo?uYP5u|Hb$p7AMYi+m|!
zA_8oHvg>&mF^`It8kTs{8gH$UelZ@177YQQDtWu>|A2BM)HRn$R{|h)-e`oKR3oF`
zyo)@PuNRlWKTsQBg4}M^1pzU0VCw^slt3D_uosT5+!GBeoLJfQ1v~`}Ad1_Wwc744
ze)WSbSlLhVc89F1jqKjtT?Oh7(*Hw}YvIUZ7Wa9-k}wmE@~G(LhUZ?0_+wM*G-r^l
zQ2F09D<S7J0_I4n#j}0?*@&%ME;iCgy5M)OY$ajHdVFIbOZAJ(v}CIwY;*bV8asau
z-Pl<*t7H0ri$D+VXNvG5Lq|~%_;Do2VM};jV^HSm9HKR&=s*A>W_j0hM;E4Qu@(nU
zA+EU@eaHb;J27)bfjV2z052eBE*yQ}3`O#u{5Nq;E&?(41bX@$PDA+ohDhAGwtybH
z^QPdS8>~?>bGQ*gfAecIP)Bz%SYGyb-o>peh*0@FeOFDPYCMB#U^AMm7q#Raf4Asf
z<28ci&ubd>;Q-?m@qS!ja@nPNep{E%zW7p=hg$#i8mWKT;qJ@+1?~^_S3Qh&MSZRo
zV;#QWpBGAO#z3(@=-4#9Q($GE{Oc@D`+UfD9V0?b$9-b_6x<*R0ZCEhpD;n~*?9iH
zbQHR*DL}<;Pq99D1YT6qT5;FQ4fR>YM@e|y%B$H&!D7`k(~`6}7^nTKr5}th*DUaH
zuL!yKd0vodydNrXBNR<1#OC|~N@H~lw~0K!?>yzJQ{CW1!(E(Y(3W(z*+%GR6gVIC
zkrWB%W?|oI1>I|>zAejVUwBzSAwD>~b~gg-&56GeR5e>Y{X)1Uf-47YX*bH>pxl$n
zGM|#aO<0+`(KS}H-9Iln*49SM(=okLF@a3$hwbiv*3z)(T$tOmgtRLOEiZYyVa8$>
za-aXfvhge2`(|T`Ly0B}+ud8)lD7!-ZT}CX=M1D8%iiyf^OyA31}zNw9Zhl`nI^yt
zgNMAHq8Y|cp^yep$azuy;DX;$odG(*M5!6>)oi88^W15L&9?ULvnuaKs8N?mElNCS
z^6OAO--^0&)NqZ_;>2{;`wI7wEC>0YAW@C4%60>fI2NYa&kwmU)x)$n%oV1qrSI}w
zYgCHod_IsHF*dZ&uCN*7e;AwN&{D_(1SYvvjLc`@p92E%ms|kaAq(;KTPOrSlWb!3
za?So0D#-gkmk1aJQa>I5Y)j*e3s5m@yPC=7uN_KKJ?nx}RmO!N4y^dhcxJaU(aew5
zDJ(DB>vf^bfBr=4xSFsnUMGko4dvUB<a7<!f7iTUdhr_R%fkqJ(TWx74|h~eMqL6A
zxhNzW`1|M_qe#+n&R-*a&gI)pIytF7+&&F8q}j&&k3biw@|w5I-Ywb%+FW*KXnVX+
zgTHr}M7qgE$CDA`Oh08>@By5qXndE*)tSZp<a^!ig(=*Fzy%~op5dRv#_`MSJ!e(s
zPxE`t{V>pZj;9Bk7`QMUaREgOiu0538K0Kj*8@+8=Zt6AvH>e|Vs3H6z*|KIqVKy?
z{FWOKtMfHrpDXf7A&4Z8cvoFaq>;2hiw@>5U1u<xGt&weT(mGOKLMZ7V{?BgCsqHP
z;(uq`1ZG<+GO%g0;6)50y9S;-$YJ3M6Epk8QWAz5w5*ceZTJ=QQ^{(yCSm}ADo6-S
zRea!8HLdqnLYRRYJ78x6r$*zxcBdSR+8|0F{|DKrZXeAZ%r&F_-XL?m1#>0*iuo?7
zKyz2dc+%zO17%7=fdMWv=RWuo;fy9lX7od5+}^0wml(1tr`42yYfkpZY<d6J1o_BU
zx%gYP)T9IFhJwYlcws+3Lb=CiM%341W&Vw8-7x)&w-|25T-^3>TW@!<_GY?xo$T&w
z<n3(^4+j+f6gCY28^>QU-4dNuFO8Dp82jYCg!W!sngm3=o`H9IFL1vcMg$`W2*xtL
z-DwhxyS#U)Ao#wlam*CLtN@pW$~pNQ9v#T`n}b+~<0;Ye^7suJ{|peu0_1zvuqp+|
zBQe=+_6}Y&GJB*IhSi?!1<D$^xR8lU!Ngx`N*mv!x_lnG4fL3`N+UqJ@*N{D6mZo4
zxfr32oJa7NS~AP}3d<|=v*59?IL=Jxm;tdM7S;5ZA=8|PB+&tjlL^%AMO9uvcJ(T0
z<*{sPCMLGxVEX5J-y*@cIlN|8ulBj5nVop9B)s1QR_=VzRQSHS`=MX{8E$JoaZ_fj
z<U3Zz1aAAh88v%=BH72aaKqsDa2tLyn(q7EIWw$15VwgUN#e)+kLPQ#q`bJr1*pyU
z#0SO-yOapJLDVAwRPq|0C6g}--4uVDqJM7XjNl=_WTOK5=DYF(mUqLnp0sTiT#mHA
zMM0B6Qok06hiyoi*0O*c>L2yjNSv%^2Q2S|X-<3ukmGhY@7v4lAlycRXgdbT&OBVU
zAp`u2a$5LxK3gN#u&#BRmwn9E?<Kx0tJ&gXU2)~HIXnGn7?ARI2?SGaxlHQ@zzOF|
zr$rItoehHY&HV-ZEA^!PV0*8sls#?4EE1kaQ+0t8`g<cv+-c<bs)d%iUO8K>Q}Tjc
z8+8WnMFQT%tWC!{@K7mCHJ<!w$`m@&qWpOUgn{x~+QLG;aueUVGV%|p%SOpt0`u_F
z?AC8vNgW@1xvr#9w0y}A`PiP=nm<6(jcH>b15MU-D~!wVL^%aq@(JF_TqNoHi0}8X
zxISDTe@nkUNKBDLr($G38Zp)1w4`(|@Ww9&sWPWMn+FYifi(dp$hcf+s|zOZk$T10
z4{4430OL!S4%cTR<I83XGhWo8IMgCL``}rXmo>`cW&s-_h$5*w?Nxwc7L0r>&5i$~
zPU2DfdatdZ$JOI%Pw96wIgpd=H7LZK2YbNXLqJeoVh|op1QPx4(A<&NrMC$)L-hn9
z4_7*$Zrht6IeZReu6XUu$wBrjvC{wtE?s~oI@1RRIgD{7>c<w5<TA0ZCD{jmR`DhF
z%f3wG%EB!WN=Nuw>#IReB1KaBre#d~T=6ejb+0>9b>R3C4mWZ{fLG-uv#9JHlit3p
zJ7SrX%XE_Qtj9M+doO%b``CsOw*x#a%p%!AWVdEt@MBTO;oz-+Mf=Lo<SaD`F@fJ(
zG2emp@-b9LR_6t^>(|>?ACl~)VN7|tUV(-^Kzc2<d>U2;N9-`jX3Z!^LpT=<sdnVN
zMIm-vDrTcDOMY<Sd8c|%SlL!nC{txJ$q2k^e){EItqV-U>#asmg|cIUddBfgcVA3)
z_M^n7`J!K90TZJme9LYb!1pA&_@P>V&KWk<<cXcSG0#x5h0Sts-FfFZ4o%}4L_=Nr
z>rs-mw}Fd~0eHws3*3ERP%8e+U<!Ex{&T%aG%$Sut<@SJsYfMhk_qdbd-5A=12rD&
z^yc)~dFc)uENrzZ#o@)?Y-$aeEf~<n$#O_CkpNiN^i83sslasq@IhXiUT1JL*Kzo&
zrF7+*0T-HXV#CwUu)@i8nr?K^D|jrR?NU{o_jd}B@q5f0xzse?{lnIoef@kMZE2a9
z_PTASFv0MeL*gM;;gcGz$chyZPKV%hgp}?%7~h^%9|X*IN5$xafi$aohPAde;QB9-
zf*7twXba<}$k~2X{Cp&}i+!~*8*Rz@Id^y=hoWC(e-}KgWySJ`CxI$2nwU*U3*U@7
zpS*$4eu(A#5G(q-GSY5XiI4(t^Npmj<x4c%Cgns8o-ZiqVVpkc1s+nY=!Q>i>wtSu
zl#T6PWzf_ZVw{{KxWPYQcg<n(@D{^pN{vgVRi!&HC00$8G-}(7!6}H$sTa5Fa^AP+
z{-c(8bmEyxL33{zpD^<7TcsAq3D6Ud&|{8m+8@iAMlMR3&=7U^ZiCKJ2ObvI60V3>
zJ8`;lXc{^8upu*sCPt+=hBbqCDXYxiIN4*n9~rorKD>BcGoGe+AT#fz36%8MCP54w
zxWwI-vHyiNz;-_|IDY(La7UrT8`lT*AD{dOm3tXji`O@IQo9X;!C`CtiN+gh?(Oos
zFHAu7&WRZc>9E)2v7Kc775qo6nuqrim=*5_hX5Ul2pt9Uu%)kWy8Ryf8O@!qd06UK
z(vXLGBpMrQuYX)kq>(>udP)yFJ6jWY*cum~j8`rXHL{P5jsXf`uU<lpyZxt)f8Mib
zCcXPkZFX1bC^dpQ776cY=y1Ra4X&BMl(0(Dcsiwfc6Cr{eC!t;`Ln>&iwwPKZVFTB
z@T9dJ4OgO;EZ~65jNBvxdw|jQ#P-^AVC(LBV7nP8(||`inT?o(T_&LkhX9|#HrP;{
z5k76PMJ7K#qu6!@P-;Rk*Czf<$!R7-k2IUy8{4NR*BlxIwH0<xY=K{y(Uu!!i3WG>
zaYve9-rw!{Yd#7TH2nDw39w(gDsL%Jg1NO=SqX%amd-C71sCs!Mwy{6CouRoP8rzl
zTJ-VaN81F(n-9J({8`|5Y#OIT1SeBUmUbl6HCn*F;8d%|+lpP3_~Y1l0Qs@;=S2iE
zX@gAyz}_g)$QkVNS;CBN-DOF!+cm%SFk#>Kxf=ds_Xyuy06In<O`yA;1(f^ZA%a8D
z%-Q=SXV#KkuP?W5*%%acaL$Q~F7ME`aZ0Og&iCs#g`f_Y1hnSPamMj~SeKO#-Y%Lv
zuUQn6v%~e&`c9oi=dh#K<2K_|2zStK4UdA3EWGN+%O&)>e9g9l<Z`fQ>fxIQkAim*
z&r@56bGF86f99`;9F=!{N!Q+1b{e|e{7z5hjVDbPUatZYPO%!wR|S>mzRua7hLPT^
z9#*r3e>%yI?7Zh1dz*Lj=>^5ZKqIhq2#1f$p4>|)6j}|$|LnQ>gCb$ebvWLox!~aS
zZ8D1P%Lu->5%9|o`)T_R^h5vH@0Xjmr%4Y3e(`T66i$p!u1=7!nLFfXgt{E>`}e@G
z!heU&;e}xLZ2z&U{#fjH3Uzyu^uWxpQjo1v5f2*pZ=9$!>U+0?Gb~{hKUj(FUbES&
zIdJ&=(TA8pa8Mo2j(h?xpzyF96%FEixqHrDRS$1Ev3<D7vQ{lD){yh@!cns~4{vLY
zzxZMJw@!5fLcW!XSN0ajI(S0ahVS#C_i~n%-pA?|cgyGCkM(80w%bRR_vO|PKhWYh
z^9emco}lh+SOj{{twvG?E+zl!f(vvHc%;o1g3?;sU0y+hXO2Fs7*G-}=@*}8%p!@|
zvfi>T`))(ddtX36?FO<v*#)Dbzv=cAt5(?0<DJIpzkhvUWRHF1y~Ny?-KAO_lfSvn
zGBQ)%OsC4(IC)+@HaPON9JC@diNv+=)1K`z4v!|md;M4?SQ0Qny;^-TVi)fp9IQ%D
zkklRU0*{Z8x?+ZsO~kHAa}SJ~{>JHjS)s~{g73xlyESi1%Qmk7#;WV5=6P`kar8TQ
znr`<`98j3@G}6oGuGdH&Et-ld$xxTD!1sV_3wY=SB|kpRLBDn#Eo1yZwgbhld}+Ce
zgCi$_M+|rTNI;kJQ?^m!(sF=d%QNf@hN)<LM$SFm(y`@_zkUt(+D+t$dtO5mD#C%l
zS`tm(`<DD+A*Z}z!dS`XQ?V@P4qfHy62kkNzOmZZH{faXJ5b9Q|IJ0ii<`vzEn0d6
zhSb4bWQ@nh@&t){imsB7-r6=H{dcIwo1oa0slgWjokw6oEWE{QTW0)fYb;ehb|w`s
zGHX^ACN^MY-)VR2o^U}=#Xza<M(Os`JNcijlK4hzj(taCkaB0Z{H@)blM@A<i|k1f
zoTDy>9Ulw2jM}ljCEX$|-@KAIbki|*0qC`!SpZ;*?NshZrFZJvlPV!)VYEtuq;=iL
zZ{O=cgVE#mb@$*<iX*En#|9iJCo2`9D_|qYvE-~fT3*aq36GKucZOqS4Vgx4cJD*9
z+@6BVlTU*8^P``C*k+PeZC)M^gT=H#FY$l^6Zk$@EP3KWryZ7b7qb3Qj;32ea>>UI
z#tt-;>qlpt72WIko1Y!30c7K23z}~9Vbha8_rzZ9u7(bMIO+wxZ|NOkI@SH4KRr$(
zoANxcGSNS)D(^6DE`u(3dq?h*mP`FkZx=OLCGt&6Txb<;%^&01V$^O8{i+1^qqG95
zkXU7C^2nWXrbtCdWnS!gcF7bvaM#nm6tXGcr%x@Mg2rFVxouuLy6AEH$1_@>d=SrD
z523V$nR(xLMKVwKxM*|Mf}dKjS-#V3IjbU61#EH54D4NfwA{XTW&bD=r6*U#-JOS(
z4d1=73c|=hO4Z4#ad7yrfnlrjbq_c-ClD{Y*q+YTGqcBb%nU7E#1YGHjVoeK2N%u-
zMns(zBnLGE7w<)ai=$~t0mIJ6#q#-OB|;`&>14#E#DBj2yqswYa`nI??~jRl-73Nk
zEzqv6fIk<!hpQIge}kv-B`2Z)cq;%eYE&kq*<)og=&g!S%G?h0j8hw^%FFT=y|TK<
zH!3;GL({9Fmb9`4C&PqInZ~C|(QF(Cyr^V0E=6%vz+*)N_}#)O$!H@AR&Um4sXs(x
zNrADaqMm|XIuiCmm8UM0268FHhI^oKoEzv(95HD*1!?vOK<<e>5>@r)?1w+Y8a#A3
z)k%Rgb|nEsNIF0Et{I>vvIN;S`E5tA6v;pQ7lTphegC|E^_LdMmnW{Ta~PnW?a6DZ
z&?kZxdrq{n8;wgWAZ~&0F>INNFdvv)>5AZ_ZuoNJH0)ci>#W5;gOjr@<yX*TpL!<f
zJGc<rw6Obdr4chDn4zr7GiIfQLy<WbW_K*KkeW_@KT47P8jy>>_K|<Gz%kpUYy$#R
zXAjt}2PnESIw`?QLj8wN<PL2?v2GewAM#FjKB2fX)#|<k{DV`Ign^=Y@J}->PGD2+
zTwP8yE36WYtqX|Vp;3*1-kAc8vHf15EGvL?)p)wiqTW@Y^DM~Q-n${H63t8xey0p>
z9-G*c@{6SmK2bk9*ZEte$E*yJHgWXSvuY%3(^|ld0IkDr81{WCnnKHRfTASygyExS
z3PQg<FrNlKQlk<p!F*Qb^*PCU*HoUS$-P7?)WNT;vb^K}0__T5<=_u*(e&G2CUC!E
z-I{l#nc1r+o`fs-#XU*Zz4khs=F2tcbH+06m>d+<YJ#GLyihPM4lWOF9zfG`zs`)y
zRJT`aJn2%+&jjOE#D036AQ|henRI3Yc}#Rt4PR-!5>zkN@{1UK9<*lflVW^?G{5im
zN1zaUH(djE;>gQVi<9QOpj~#K2MP(J>dH3YN9>`VdA110E#=@}wL+z?C-NO_9<ipk
zf?)s6gYkj_wh~UC`biNSj@0V*@wE(xUx8TJ@ihXV={|s@^EAJ|*e<x3JGAaO0|Y&e
z@N@?`Z(xPJ)=(*bjsAp#Vhf&P`Q}!ndkWY6XX%9f+hVWSB^<o*WW^;)C&;>1R<bz*
zD={<bMs_Z%UGaI$0qTVj3|wQ4Oal=NPO97i7+l*paNUR<@ZO+RSy*Ny->msWFd2k2
z{83aH>ZqR+4jR#`x+V&&fZQ))WgfEEqu3eZRZ1g*^80e1BlLGig#h}U_C7jg%ByYd
zY;H0k2>oxO$@@9Y&Y(%_a{DH4xRYcV|Lx|s*vt}V8vc6DUkiO>b*{z*P!Q>MdR=u7
z5+t5Ai9>P53*T#TykzoulEt9mY>JYN;?(0}e5e{cuPnzLo6}TrQt)E<d6_q78}<1a
zyp<^s_uH%dt+fdRKh$HfO)$B05mt8lrLxWPIpHGLit%NzxM>l~Hq<_oVyAz)WB5|-
z;l6*~0la5ZBu=Rr8ROWOSXm{6@vK;fmHjdy3mM8bS5`pxu3Pl)m>L>))V_mamwCG5
zuP*@+YW;zIu1C+LfIPHOv5}?az@Z7ui%iYA%EC0d5Ol6pz<MS}IA^%Bqkq!6J>Py^
z%=!3t$L1GxsaoFfHtMz{cO^m)m90&P4?wM72~|k#k28nn@lKk{`rfYsntwTTEVZdm
zgQW`;tDyC`?8{QlTU`QAXch!k4ZnzH432gfap$)=&sF1j$lE9Ii3t*^b2JE{xH69%
zI8FhHneRLIik<`Qr%_$!RekC#&BXT9*kZA&L;U>#J5>)Q;n>vpD{4IRd6JG4G&|;v
zS~zIUdqNlP{Wi63Mf-}{_Q;L|JHPOb#xEYj-*S`2KpHbuZoxB*jDNO~LTp}V1})o4
z9c#L~FlYPJVmZ}+4^?~8ykvtP8sUVRnntoVA)}@nFP~%+d&<yq=QA|6@|Yn-AN;<^
zi|^k3w7?Q5bbQ^|mdXK1%J^55Vb$h1T3g?wT<Xt>7sXac8^~kly%LCC4w$(-3`!Ez
zuhQg?)tE)evMo3n=Qbsa9V0v4qO#F+$=6&htn3_`+&BD2I)*v%_h?6N5Y6!%x-T>J
zF8EEsMIb!V%}+%^eRzMm^jj|VtO_AMNxs&LmZ2-mn`1ebcjwS}TO;T=yOU;l-(gMD
zw5T5PEEJU5Hpn#yc2J(CW_;EbXuwgDQBILGlRJM5#T~}VLfpa6p<gl<alBormUp8A
zvjV2Lp_5(zAt?GX+Dn%(0hZGO%l*Zk&tZVZ1WEC$p#!V1bysuGp9!A2NisJYRSs;L
zEqt&e=0uwZBXAOo7@JLqzrcms&lEY!)<WE|iP~Fe^3!!dFhL7xOTQ(3*Xl;WnGSPy
z#Xq4xQ5OEQHRgD;2P0Sn=c<ED!mz}9hLgQ$`Pff+=RZae`^38ndXy~@tC6fEbShBn
zeZjIu<O`31hsJN9>2f%iS_W1;&+TtNP^2PT4zcC#9TjSzlf<h<oVBTj%xe+8f!L`#
zb%#ZI_b$CTJQ!uT#pW2TO=YsK)Zk8RPcwz+>s6s56emy7N16p^f!{?W1I`<Ct*T9o
z(&DsW?D*kt&<rj&JIHqD_%k|q)mH?a&|a0y1JcV@4+)Qz)UdSAc))r<&jg6i@#~Hm
zL51X)Um$xEo<a-_k>xtV&tnhPK@}%=Vl^C9d1<Z{4Xsnw0iJiCm055ZO_zSnrE39l
zNZg^RQNRb&U&P6@zJpH8<xj58Pdl(=YKdxTI)64?FCYBMp=uapTS5Z^anWrWKK3KJ
zSXpQQ4KK0c+D0Lxl!Px>1rKtj$T=zZkM-d{SqC-vSDm2+{Ylra+TxLd0$MyaV`4|E
zB3YZ0X`smq((|D;c*hdAzz%-?fOCm_>mGT~fct}uP=+~g@T?=QP?bk_3dXUktD|o8
zpO4nyS<}nUhSrHzVKsgz3750{pP?ucTikiDI&clLRe4=gY;&G1l()oQt6SR8^-J02
z+K1j<@Y0@rK<re+<h$>&Ip!_z^VaCbp8)^!;|?SA2ctOh=Ckij;G}h+8~0WkHRF^*
zjte{HPKZFW+#bq1Rwe%Iw?g<~?Kw2Nqr7*KrUcwU-#>vH=)56nW&C(wHbVD=%$q{&
zPW)?@lCZnfpfCo+_hPWL=<9W(We9o7dgN7D2d-no911bC?W&L6NGh6X#v8(t{tR_6
z0PX87_%XV0l7kr8ss{s!;1Bb!H+PZ4N){0RT<i#vt=rFBRsp~4%TOX@^T%^^kPSK^
z0;HEv=O)bI#Ru7Xjy_Akl1_v==z-ZB_%UVt`#B2{u))dy12*&wH9lzrx@&;+c1#eL
z4gRbP%&)^a`=_Q90N8x5xear8_CdDZL(iIZIe2oCq(g2F<<bn<#_<;mGXS|7o5U`0
z6uU2lVtn$7aLu{B2z*?xu>A3g26C}M%vwkj|K8+Kr9mC&As;KL<-gA!24~9VOTV!y
z&jz)4_Ck(r)x=+D_OFp9;(G9tnyxv#P?m1gD_3?5XqJDm9P~4=axx?aFLt4Ef3@pb
zTHG-=khueV7IVBjNmvc(uTfh#Y>O&DS|7OAI#`FkvF9!nVq9Cdp955(BOJ{Z#>}PY
zZ(;Sy85+1C(VHoI_pmRGF%kM1B#(fjF%$%n*`qaijm}JTVvf%6D8C@fHGkUf-mfIQ
z_8X}84{RM1v;qt44#(!yC0S(x??DZA@=HR~d1nrQ)V!x*_?oJ$Cl@BY$`vu8G>n}X
z_~+$2sD=2RcV_WFz^%UE^CL^>>?K5!mQ6ffdjrkxEVot?0+k#wsUH4o@Qr;=UCh}(
zU^8&ClMrfpTb_qdh-cemkH1}R|I*v0%Ijx?=<kP)Izu_=?>~<vIN7xP_taL<q2#Hl
z#~-Y{g-oq?s3!l7y9((untWOW<{vf!h#x-d3Fb$*buCRvIP8At(uaoUF`#Wl+i=n7
zD<h2Eh+H2Bf|!m;_Vx}zv_i|atU$mv;9spdjHe|UMG6WYZvW}OEJVaMq8mekS22fD
zQ3jJ#twAG@n=aAitbI12FF$nMNE3JO>6IA|3#gl+UCXdE%&+#;rTEpnJY%NKtJ3)#
zT(E+5o*akOhzGvKgubQ<fp7R;8#p~@T^P@IN2w52`b1M7ZR5Bu+eRb5Z+~Qn3FN3a
z%i!hJZZtX95(H)F@&KA6ihN=<kKOhfQplywtoX);LKL9gm**_nb_Do;cM@s}8mTLV
z^(mOm@0&oc94XfXgha$q&YfAkiV1dS1CE%_2+=huHs{wTX+p{T7;o_NA9~r7$Bk5N
zWTe9f;6wJEkll}rRtsM|+?!gtu~Do-==tm2^BEU!HHBEDauFC-HepE#5|<Q|o-j@E
zz7Gw<7`cjscdBazuWfeBTJalPg<?0qNM*Kvh~(_Ht7v9(d%q!b4-H>@8vI13T<ow!
z`ptVra;_Uep|PHjjWbPiHP6DHln-fwE)VBF>vO8jYH%s?UZjK9uY-d4^`lm~X)~hv
zCIyWOE^>b57s5ZZ?HZc-zFlO9@#ZA%kPU9N)!}$(2QTKZK@&6&r(kcj2REd;Z_Z=X
zwz%U6$l*($!y_1K-3Grz0O<`rRQf8Ycs(f6l#7=9py<bTkaGuRiXk^<*!?;ejmj=c
zeD&qjh|jhgXy)s7Ly)TqQLjkg^AnpO+dVPyG_n`)mb!+RyP`yXi!FiFB4Gk>brIa=
z*aEUv@q+FD9kLk`?~7p|qTVIbJ3Lf~^`4f&5{@5D^HggBw(Izy<F;F9d3Jd=P^BrT
z#lkT~^WER<DH4opoi!v6^{#)GK3KPFA9421WixAqUq%ZmN*d<$&Ed(Mx*3ge;Fc^#
zQ}@Ia8p(Ii9C2dCwMO!acPoB_uZ2|l`oCc}EfHQ=I}0nzJ1$lx^s$Y|h8%dQoXtba
zN0>l{T-n~sR{kDh2RY9UYe0LA64xf4RU-5m$(@@GK@D77qihXQj~YZZH-mCB`SY~H
zS<zEbffeRhhf@EJ**4;q`ZY>Ia;yY2>IA*7fc|*RS|;<!u%8;Bt$pzKfMl$L>HYv`
zo3XNbJFq+UNfH#uv-3^i8c6fdUZIo87IFJ%j+U^Q>5F{sR6M}#RswP7lPA>h&n5{s
z*MN&|auH|T-eEJ;GLKaFHb<ND!9#RaZ8dB=r59)vG^*vka&OjHeaK3{E0U7~8WJoL
zHhm;ZeW4arnQMl9@vGbnzJc~`fD;lZTBZ$puwg13em)E_N>UMG9Fz%EL#{3d7i-tW
z#__*CJ}8kGN-h1guGM93+dmzyS(CpKvJ_=h&x<v^(O5%1QVUmH74TyOXzpH)TxtWg
z2&G%;LB)+;gN;GU?dR4d1-l$D`i<gkH1kNRX6(uv&>O6bDx?q_(`14|v{!||F+1wM
zJ|?fa+9h^vv3d~p!2aK3K--pmjKhjKeJLS^CaRztpNwh=x;r+iCrQRIadD)A4)H_J
zj(s%xn*=b}rFba`zL4g^o;nN{vq0QxX&XlorF!Jy37Y&63*^|BpyVIh*za(*5DHXH
zM@@bg9$s$$=;f8_!_RFBxKlc8o97ZvUMlgIalJlh0rvweNl1_|nG(;*G&Iwe3CflH
zn8{{PbI;V!y;rJ(pWpj;=u!@O-Z9=ss*=@>4UjDmR?HC%o=VeFj$@KtmjiKBvOd-D
zYin}#zULcfHhNo=9)~=R=RGsVcDhn(o<Q=^RZ!e`j8lp_Pen<{&%y0r8CMsbX>+Z-
zJ`;6oyq6$hG<oC@md~+urTKzIl!U8-DoTy$U1M)uV*m8D8eXc}cCBvg-LhJ>0pNYe
zTgzS_qAIzDs`9Fg<c<EI{v?H+je~ilI|JR?oU}O75?AV=>8l{rxAqzFFbEa1myt{Q
zmmP^+`L~TbEkj#4g2r3&oUtS_sh~l8vnkV;);t6Q_B|-mi@{%50q8-lfGwp906oWe
zd@Jm$W0ab^fS%2e?Zo68tOF?TPI;m0WoZnb&;Immz^G(Jd>^7wKA*XXH0gw$DSwYC
z5nNN{jx^2III$Y<radz`-#N;(*W%KHqTj?{q(~T|m0lRl?OCg#jwA^%33yE+d<fQo
z(N~eehnhk<yXIfdn4!LMAI;Z<AUcNb-HGkq52Rc27*G&fP$s@8)AOTw4G2#H0l1W0
zz3>mr%r0&z)!~%8=8$xt&3kDT+Cn7mRy*$t=o7WC8E*`yybta4m_KPWgZr*U97PMi
zj#fKX1XZ~q%M1#*EWrYlhIb4ez&aF8p>${6@E>#Rexr0(mA9a+ILIyM`13x>G7#%;
zOp-8h%EGU*Xo%|tO23%v|I||Ft)3$O`ljJ-l@lp-d}J@*-krl+mQh@*mJ`M@Nf>Sd
z&jd-5=r3x#hdTyAzDeHHV%uH?3C;zvGNw-Xk|C_a_k)q!#}YgwCqA^n6p3F7`@)bi
zMbZL;da;VxgS~Q)w}7juyqcf5>C*#u!_(d()|BaxX9KAO7F|6a|M(tCBX$dTa0W&3
zIjv-r+-pnq<lxK5<@S#k{M9vdZXfJErG&1$LUYNv$3IS-Xu%jpoUKD+Xq<`zW{`0e
zo)bYHeK|G&WYZwIx@Feh-`JhRc1t(47QwLR2=PPX74i}3$vi`N6ufNowU~9aXGX9g
zcz$nEUmMuh{^aU6vwr*@X%0qO?EUB4s3-5jhx*kCL|h6xai{^!_2rCXWk2|C6%#AF
zti!7yaKr(okJk5|I=vP18`EAedgWg5bDC3qb9weovehS=4LLZ#`!M`RvT<R{70Vo)
zGwc7+_3rUdZ{Pp;$Ss5;l_E^KI1wtj8=6xpgi2Cjrc$ZIxL*cC<CIg9kxJ!OB9$_v
z+|4M(=t7a)jmv0E?qghrF@Ec%&gb)fe;(i8pRd<zuf5k^d+q(&d+oKJYrUtzNUy{)
z%5UKtuVu{>4mklzTVMm4iDRW#O$A_u%wYEjA7Yk!SgcURr1Kn1aZ{M$*uD|Z%6<Pf
z7me*&P;-LhZ1##0;Lfvf=sA9YTcEV?4QAq3&g~n+I<upF0ndMnXzqI1V-bblOW^fg
zK)cEbQd?M%1<CwqfqR}j@OcsVRL{<d)5CS_ZP?X*s-=I~Qd?%|rUcv-r?paCVbT-7
zYiolPSj_z$eMW$~IA&8bwQ7Fa*OWQa`#u6jj(x?gHYzkz4};8EttrXS1?|HSBtP{B
zOTF$7mV+G9#MTq)*}HE1YGUqGi`}xjzjfpJDG!Q#@y<ZV0wjqQ_K0DHLt{40Qxc+6
zzNG`d8%V$6RvC3K>)!@o%iQj`7ZQOfved;w9o8HAl@9A>K1srN?7cwR8J{2`V}mCm
zdl;vSvRnnD>^jIG7A!<BjBbR`Xvp_GJUvV3m86#YOr$!uc2pF{e-lK#6%o<4{g+Cb
zE1Z734yeFg41R#6!=295^8FL3_?`~Cm&UK1H-lg4uQ{=DG`hS!>pW!TPJXeRC4WsY
zMPJG4<h7Sk0pUA&bh`~(x6Jf%vu1bOzXSwwIrH{rNWpW2EQm&rK4x}BOny+IgeUnJ
z9enMtbS$;hRx$4yFKh8?;(aW7G}z4svR~dtFZi^f9oSPYs?#Gm&Nw=&>}FZXv$V2=
z97kW<C97`#QmmYiRV-CKTS)FzxEuxyp!5Wnokz>LKg!bPYPHf!MPeI6^p?!*qAXBw
zSFFsXxM{&za8=|Y#g!+Q$LEGkH<?kN@pW_NzD>HML^q?sbvG%^Iy32{0tB@Tx@}%e
zVH;ejB$?<$sedx~Jz}y>`}_y(L5sltSpTsp(Xr#R-xp_mFCZ;fXn{$%MQdJeruW24
zh~r!^52j3amQuSyt(-#LI<s>x_{!mkC_@|O;%Hf!OLJ+?S#Yv<$zqD&hrGUPOY+ly
zbs*zedG3f~bFs1Hs3|Hei?FC_8fs#p%;ZCNAvJG<-lh7fJ)YK-;6J$)_2ZT4n)2K_
zGo&|9w5ZS<RhLwEqqR|e4MmGfnF5|%K4G;P($pN`BvmSz<sh@rjftP%%)k?&OV2*Y
z3}OPyj<CBwOFVG<y@>VtQ-W!lNT%a0^Q&eqdKA*040$Yky9$;ruw9MD&HYSuK73p0
zd&Ez}=XGCIWOt_i9>sUr=+Ov=4~>0!PO~~=t#ub)z(G#qcYDl`@w%L69|nI~1Wqcg
ziIV%RCkoTBtlYna<QV3;bQh#{9$&$FZACMpsn1LpGSXM_b9V|KIfht%jbzh8*iKIU
zfr06zv$4x|O8#Cb{waeM)b2hcQhU)rz2p#d#nTD-z1QsxVX?;n*1!@c<~BD63(a(s
zEmccfFK6zP6YeCc)EZAjX1+m(MCgJ`!!nozw@EVLFAH2hlFRcL!4_{t={K^g(eyBd
zWlzSK5*It1^(vk{FMmFw@9ZBcGOz{i|8^7Ce21WDQEzJidCfZreXgww=v>9ZUlSbM
z;n1?ElmAbmF*Ep0-24HVW^;I+-CcD-a5E9VtMqZr!i5Xt@)6|la|!Y-MN}No=~(Eo
z&a=6!x+Pm}V05nXwm<K2hGk^E9i-Gc!fCFoNF6@D8o+mj>UIXC_P%Ub2j-@rqZ!Ba
zUWEU!8PP&j{Z=Ank_7)BvxY5;9hL8Bb)oJBMDBQ_Rs7-c4UF`#$%dSZ&9+*}B{$8a
zckchC-OqanGIz2O$&Ow!3!9kSNwJLQJVO(#xn+IU6#7_iR`a8i)U3cC*Ss}RCpj*Q
zzqBj#7pv1Cv$PFea%6XOc?pAX_H{;0y)w&vYB)9tSAVPGO0>Rnz-E!VR{ztAcF<xg
zdSsV*@Nu(Cnw(+Bn|=cU-d579SZ5b@!OSCfVEdA-$-Ebf>qQmw$R~Sb{@}%mN+tQp
z_jL!yi_%{|tnrKvcTI?IE!4vicePL5GOTm`tSSb{3jbwI=U6H%88&n&Z=M{t$i!_m
ztIQHk^cLruX~aP*jp_Ye`(10BL{E_ZmtsvS@fXEAvY`3&im8x~*%5!R^va>U`}8u?
zE@PDahKRw%J=s_hw)s&lBnkd=epB&R6SxWH<%f_AOKL2J&9K6^IYqeA;Oyq{Y7rle
z-}Os?>q$=*Tu<$3Ml(|y%NqIpyxf(n`9e;GGod12)SlWGC)&OH_u?dlIQ-ahjNZh-
zv7fM;p4_d56<WkuR!Gkl&BW-M@e-7N5wUNJcANi81kvDyfMLG;EO<6|46I?zkxRET
z<Tvr_eVfJj4>YJ<DGn7OgIQt0L{-9Cl*dilB(iS;;AQe!9NYqu+PiwyncWyH&GN}0
zF}x-wLWjE`P-nxw*p6Qpi}Z=zJpSQ-`}DU{bhu+ecFj`9eF*jKK5*Hl%L^p<!I!Z#
zJ`(5{tr5wrPG^eGdkP}O`PKpDeyEgvzZX<2xW|O(z%`DS^9?4fi_~brQHLZz`Q1RD
zFPMUJ+V|ArDrnX8|FkNG&8_K)<CS$MxtWmESxne0cwk98vOy#IB&E5sxbn${5;OV@
zXSpav>t74;#w{uc;tl4nySr!I#y;k*ja<Q!PZU_i(^KzHw+ei}jNBcPk>ro77Bh32
z7l)2hD&n*K_t1$UL-)Hup)o^!1AhV?X=$JWL5>(Zi%kqsD^j@R$n?+GNh6({$zo4b
zio@?Np6o<N;#nM#w_6(YqSJ%=XW&ZYCJSyhrxi*~81z<C=3KPEKY_sLtJjORoh-I2
z=*k!(i}+ml&z4hpAG@>NOu&b9LE!H=W|1D>t{>odb)nF=T0AsIiMpsfoI@f$YyMwU
zn;Aw1GeWh<11v&(r=35k1g+N=>r!!d0aT7KidoWq|Mwq63Ixy&SOW5o6G$q8Jk1)y
z&B=Wf`rYd{A5G7v$Z$95{jlgPYt(M-L1icXhvszI&}B(2<7ItuSm7z%5BAL9MA8ei
zUPoMV`Q4d-(K_nIc+r&Ovu%i>a?8nnxX5O4zP>SUAVjMdvP0aVg==k!GyTuw0jSLi
zSEg<hvW>&(NW~9tk~GfYy<Rj)lEKk(3^yA%);YD7AkB4FJQ%r@J_8=t#Y*~Vb)EdC
zQNJjC8+_Pf3b>vizICHncu8iQ6xVs;3kOY_>eE$ZO`362l?qa!bYR;Llx8Ar3T{%C
zE-HVQEnSYZ8m4;oL-t9*n54HH*TKr-7-hQU=4kodpUC87>Pi|X!kUB_ND*%Gu(J_k
zNYtK*R7HIs)pA@J+jZW7HgzhkvBIo^<g&JV|8Kd9BU4#|)BGm5Gg{EUc9}_{<@|mu
z>07Lc{qzWL){79O|65B}BAlya0_R?UOnkai4H!Dnk{>>|OHv}VNMp2gTl^MhWL@#{
z6iu=Dy`-Mtpd;N_oHuU{H;hKhM??!I#ja!SN6xpv-5onF^h8Ai@Z;UC+<o{z`B}x8
zeiM_66>`TFYbI*sN!z+180ephlHm7?#a;fZczo4j@!^Fs4^Y?s#%%k6VK8qvP!__4
z6Nq!kSFc?NLyJTFd?!rnmJRcN%{+#&4WAm=T%p4ljV=F^L3rGK+C-O;9MJv=m3{M<
z__dL>$IzPo2aU6eMODW{*jt|Gj$no7mFsTxMOGYt9WYWyWgd|L+5ggnONi{PXD^T0
zQPGj}EROqZnGmpu81%Y#_W&>6XrM4w#C~JMFk+lOf(GmM#YED2K>_T7R`Lhg_UR2q
z;1|(6wP`d@B$&7@p3{|zqslJx(dBq9ny8n+R6m)_Q|U>sAPXklv*kGsa2>|+AjJOk
zXBDHFS)@lxTzCFwPdCl)nel)C^@(pB{n>;^;4R~C<S{7)0NwN>#i}B@+W*PREz-sS
zDXvj{ibY0xtpxw$25N_&4$k~s=@n7wX|>Aj;HHE))`)vb@?&8tF8h&4+Q?hVHHuHM
zc!&q*Ifq01PRS9k!F&GUe3)YAP&vPq{+H@x;ibypUKn2>{BgBWk{4zqKV`wtj*JZ_
z>80tbeso&_y9AmoGwdt{7rjUU+fpg{YvrC0)Wr5OmEe~o3;6zz+e`NJZ(7ow03w&*
z7#v*`xzlXw0W}yQqX_fSFA!&+!m3Z#Pi?3<?7bRQxDWr|RknkFp*RFIr3U|8#me^L
zvg_~J55{Q~Nune(sTloz)Hl+If9K~0z02Sv&wtLT;{Ov2flLg&L%o*fk#zy*EgehO
zpw8X-r6e+oN@7b_G+cP$Jq-0G%jYcR9-MnhRg%B2JDRSgq!#7(djL_$0G9D=AMRk_
zG3RE_dHWeN7K#tts9(dnoU?3a@c$IctwD;NJWR=U_z_eS9o};G=kR-fX&;m!^afc+
z#F5$9o`sjb4cB7Z8YTVXc150zXgTt8^u52<|0!nnH(uJEY#yPjblikdBY5GR^-;X?
z@LObSu5?laSpejElKwhLv5c(d<-6KZEHf)bLNvjP?JuG%q^uV=8Tx~?`T9~W?`cOg
zI&xo>=-8ndWHu>pS)5Jl=MKT@#MxDn>}6%)r#D%6{`d-Gl*5_DL&KXTh%7NL^)3rR
zG>K)$*D+%DZ$No6x{xzS^kO&4cH^a0!T_(ql2pvQx;D50?ckt-YF<%+7*51s5)#)2
zU8Suwl?<KTS!d=*$!1GOeT>B+6_6JdrEE77DiE9iMd@q3-gVq1lPwl?dpB}^)%!J=
zZW)BjSI`SJ?Pv$}8h;hq*XPSn=f5Jh58J%OS(QHEd9peEC{u~WX`I==XQ+Uuzhoz`
z4tgmKIksWV(457!OscTTK#r@^ojD^mmdj8b|KNzAtx=1M`rK}&3`BCgr|%Z>pEh`m
zJFRUy#KDSIx<fO|8f5a2jls$Efv}T~@#-MUgW+r1rw<Y{QDaAV4f>aO0_yK(PCb$4
zI@I5?xJvE&{KHya9yJB6Y@(zs7$8GFw;R7K0(kfXUsI);s0NAFK}`G6m<3Nn4TEfG
zs|_b-y3h{kRZ6E0i4@;rWqCl>I(#&;FgbGHe_79Htl5g%`jnNWsfU@1U6id2Z4D67
zfaoo%^3~0vv|=7h@6<RFAi}}E>9|R_G7DmZZ{_eUkM~V)7b1|&eD6Qyxx6*YP@lGh
z4qvr#5SWUUsKr!}^<wNWG-zipv{TgmTJulLAS5OS`-C)2?OL>X#1c_dflOD}p$13V
zDr7!TyJb!}#uMbYJdtIn{dyszQr7h|r+(E%_y?3Boen74VtN)*91iXV(h=t|)%;P1
z=a#bE_?ms{@O85o!J;oqGYo?$vv&zZ!!Xg2YhWmqP{vm~K6||4?WdlbL@ykN-Od{+
zF{UCC&=@Wf)wmQFvB%nBycAK=PBI}@7DL<2X!OuS`KZ0gafsy9x}_owx{RfQt&sBw
zs!QzdWEb-?^RJ?t``~?(pE-kY%{*dk2})D3TwqQ~lZD(lSh+HB{7x03zzbB;4b>e^
zZcf*0@W-x0bb#I=a}H0j6zC6f+@Zp(j(K(gZ~uXPh*0&Wm$ZH9BftRvgbHt$p(1Xk
zErkj(a&!H-op6zE5g-yZp;h)3td2wcCeHZ>6ofx~Yx}vP?;xoXROM6EQhNB@WxS#w
zgrd!rS(LmPPgg7dVGUk9be18G%I)Ew>95uMgJu4TNE!4s&d7hJ@(Mn^6Gz?I$OzpH
zj2J&~^rja*tVxGCS1FGA?!*TqP>+W<pwm7(sa>R;jf_UN4k~Xewr)KlbCC+-+>2=w
zIQj(xkKQ6tw*lfw0Vb~8KvO#bJP&y1Wl&q}C=>qxyFR<A-6XaTC0pJFb;66BvgqQ!
zo+v(T1~JygSs&2OtmbvF?5zFzw1^4ekd-D-8KS8-2EMfu0Q#dlMa*O|NFgRbdL(!X
zSpQobHDgVgh(c=Lm)%YB*hR^XcS1!;{%66%#wZ_q0^)>5+k|YI@8W9buPl{B*)LK;
z&-PP$r-XpXzwdWVzn^vC`)#D=f1jUjWpw_di_8M!Cyu^h^N?p|1A}ja$nw9Q|L=Er
ze&*<hly_b%|NsA-boeOP)E{0$T0KntF*W;(tINpqQR)EltjkD0#+E_)k!SyTcvuwW
znt+C9IDP!bb8J(z0KoNRO|6QG<dG!wDSC*i_x=AoTLFp_@?9eJS$jJmh@%0{3Wj%A
zw0+ZJ3kQ1Ak2zRMTiuc8LM-i$f!m#37O2WeKp|3u39iih;7w3RbrS)437G>r#K6T?
zO)g_c>;n{#iel|shx>umcr;rdSbb=fJv7CIzJSE9q9IBO3UvNkKoR=(&^mhrDUiDt
zDFFAAnU29>d=#pAJ%f+v>AA+u<rNXAsE>f+qyZ}Pit}xerT%g`zlB{aND8J7S)i7r
z9Hov;O+h<*DgF)!*|(fUvK#=LS>$|Di-2%`L16pq#qmHbf*$fh%w!r7$dS|!?H@rP
z$^dc=JG3I${-Eq%IEEs;I0F!lCSzea>&r7oBJx7%*9)%4_lHi|yhZl+Q2YUQWFzB$
zUOXNtVl+DZB?Xo3g}|h9Uverc!ckGNzz|q|m-?M+_^%f;I{)_#6lv6^AvB)9Xar9|
zTGW}v=CX7dZr30sQ6vP~*kw;mjerD!1qgba$kvG2l-kx__Ny~GSYaGG#_<2~A}k}g
zetzO?H45blE^Bwt3vgwdY(JbDK3yK(g>^@va@l7nbDrOm)-&i3I`h~$Ts~rYD5T39
z`DDM?)|Wnb9T6Ncy~CW)iAF`eUh3zK7(Umw@t%$5j;38<zfciF<*mlnfg3j#s>e-s
zPIfkql?O(n7U6}~fjJnunL{h1g(;^MdH;c`JoN#bCGeNf3*gXhmpwBg7%>r+2SS?&
z9MSLcPb<vmVK*!ZovTq%@1f15TzTT!wtx$xb)#v0^)5yds6{Ly#2$=vy=<b4Ju~q=
zP6UOZAi*vH;wTdBhdcSeO64Lej(}t<`7r9&7u<N~^#6PTHMFBdLa2Zpb#{b5az3={
zB^HGOwGu$+wjv^yi0Sa@SLTFP=zr5vKawJA=Vj>TL}w$n{0wyS$YKqmD~V0P^}!Aw
zC+^5DK^=`lvmqAv@PHFjm5H&dcQIIsI$?4K3p-E%nOJH1KDgf5p>g5}QWPc<<PthO
zu!4!fW4z>D4WywcIR!6fa^Rt3_;mQ>D~wOmpQxz*nIr}uf=ZEw=td5GqRz6SsG~Q2
zQ{QIJ<ILmaT@B?>Ck%d3XE;X%hmG#AAaw3rlp;xiweu=YyleDz<5c-=Na74G5=ey`
zi5o-cMfU9zcjUxTM*$H~6DxOXps9Pl%haph#dHM<frd*5b~2o!A+{9Q89#xF3Oo!r
zah8@y(Qn-tya{lQQAV9u^Sh|y-_zlJP?Yb3igE&}Er+)4S9VQaZsb*}R*RyZ_c&4J
zk{Hbzj7!TaOv~AGk2#mZmMujcjYhK}71XVPmAx3Ip`Cn($39f0w3rE~(StqIRipf8
zFhX!hLNs(D8ZCJtMXzRll?jTnj=={gVuM*$2y?`X*qtUSiqeI@6;kBZk(szO%@d8H
z(`#3we9n_o)S)wv466tM<|4^z#eKyv19PPPtVl%2e|^xU$B3wQNk_iJ-xXE)TFQ?G
z10L7AY~cl4p@mzCsS$@XDV7Cw0K$TlEizp!>w6Sc33hIzEMy8p<-tM@P*~rN>LTzc
zK7dAvJPjzZR6iDRuFlEIpo)#Li&Y>PrG^0gsL8mb;jzqbVYvzF59kUS9^qGdVm-DF
zq=BSHLsG9=fDn+304+}-M*+W8%I^WAU8%aqVI)MN(A=lyqzFohO$h9RK406Sgdm<n
zf`AE-3M5TKRqi3Dz{G_d79uFP=?GsBEp(F0+eK!mk@Gp6t7WpwP{rohIwL6KSBPF%
zgj%40hU@`)qIhUh!6@Ex2gWxkK?G&{$0EI!rZg7<Sx{(b1rnM)<AINWCX;>v=C>$n
zFGvFv?zS$rtEXdbv9>>stYBReKrZqF{Tr}C1TmJy*YOkn!P=QBhZRz19Y^ud=ew|2
zL5jO?kUfd;-Zf%i9ziYD|AQr1$GBt)F4gPr*+Q^v#P_LpS?;2XIt(yzfi}?s=k3mE
zA$T~Xi=x(%Q!JsGY_JTp%@p1nlq>(am{jTH@Aumn=~`xE9~P4&0i%m76zN@erq6`N
z!(Dr{gLecg13C(S9}u~H5n68%l6?Pe3W&{go(yo}>Ji?9>z%L5ppH6zMt-T{UeMs<
zbqqX&*g+<M8v1U?i7O4*UDuH4<I4SFCLq{v+mJi+p6o&k-#43=A^Ak1zQ1Y!fhfKR
z32sL{)?k3p9_C`Zj<Vt{3-}41_NP!MtjKFYARHBz7x+YpM1frx+JfyD;pceaV(q7q
z+MhI<F;uPzY9$RV{W{MtLp|TK$StBq`dDD*=UQ3r3k0M)Jpwne-Z`xXRe3y3lAopl
z%mWDbfya>)bshNWqdwIT5`eGmqGZ7daFRluut3_sWwM$TMuZz|%lW)1k6epeB2j^h
zjGWy^QQyoZErM=WEi&T&oDnR+7ivV#T8qbb^tei(R;@$&rHV|AduYhZ7$^sc;M9<q
z85r<{#Wxa=2Ua6eXaW@Ma}uaKXa+z)T{3+{hRbDy3Hyz7NPn~RI1EVLEjTi}Yo(Pm
zbC#i8)6oF)B>8ih4BRCn;<1+E_QTYugAB0W`oa+4FjOM9s8k2C2n9+=@PBATPOe#5
z-!bvG1d=F84|$Euk05e*C<sx1I|FVqKE^)@`9bs8fh-r{5N~K>^K*&v+NIno3@slv
zDX6V_Sehx8w2_>$1L;#V8lQ@$PfYVrZA<-nAIor?(+_YzRm7i1b(f0q0njLwzA*pE
z8h2Rf%ZYOo!e&Iu`=7H2fwq=nvdGu;Qm7T0N1ZTRte8EjZY7)!<6ym<oRq$Fch2<=
zQU_F61d9i(dvogFP?b(n+$KPnh>YBVc^)TbqG;?)X*Ty?h*m}wZ&_H*?*&*1N6An(
zT&1r&XjcNA-)~TF-upxX$x)$aPk~MO7X*-g2+dH^WDqb?Tt@&ihtg%y<xi0;gg$=c
zaDXtngO1tbFU~K+<9J_o$$6r>Z;CC}4F++thTdlx<BL8N`mgTT|6A|5XXwbeoLDvD
z7hhSFD+P^DLDK`f&{QZ5DR5Ck2M@wQ1WDF2c%I?_8jxarT@C=Pk)h*AaUrH35|kXb
zTfrKQ^!=(YZ<Z$#HK@P>XqzH?71sMuks4TWqEyBBZO}zF)*=*?<MB2J3Ss8GlRRdG
z0fSo2{8<RVx3Cw@Nrj|@$?~g^sb#;DLbanXO+6_|Z1J^)dW`nPENt1E7|oj)go>ry
zrx0hQAMXa~#_r2Y@bBPVCcmtg_d<1_65|8*3ZzhcQMZD1Mjpfc0#e*V(L*XbPYE87
zG5*;(*gKUz|40KtR=$HjHuYtf0}vk95`H4iu7O@Ni7Q!(Fu^@E%*cXv1xPv;^<Ijb
z^{cC3jE!H93<kg>*+Mt#*03<MOKw1<rZ@(!1B~WBlxC|DFG4af4Mq~e>N4(mgw@2)
zSfTF{Coz82;u-)+h5oHjmOH9>fQn{L$qc3u2l8PQY_V{XY+Md9T*D%!lpsjj7%@Ho
zufUXi0gnFhiU<P`nWe4B3a*=Rfl(>BD9ugRg!HtLI@~yV?#RO!wRZR+F6G{q;+knL
z<64A@#0*Pu?=LQ__oNnI!@zlg`?=(SY&3Ir@TVGas014SP=KCpeooy<VTP)*^jDRr
zc^Im|4VXy4Jvb+#Dt*b}U};YSO@o`D571R_$P=N#fP_M$sX72UD86>mf)S~{6J`et
zAqdl~9YMz5&-S7$SVUeULYye958eC4_y8eNktiNYFOPbJ%xGP4*l^X`0D(UxTT)aV
zLZv?QA(d#6@Y#PgV`<_<na=sGor?`y!hZN{P5WOU6T$c^2>M(i#@F<a=H3VtiFvVR
z@y}{cp~7a|FC+45xu;v@No49Kkpbb2Bqq0<m7Ze6Xso&f`wZZM91dU{1&v~%&BalD
z|NBNC!X1}jNsCLMu@aW1ixsvWBbO6gD}6a=rXbcPojCRtq<0mKPeL#3r|d#fh33Vh
z@vxKcU5o89(d{laSp0+4yq1Km*k-Koy>+xX1`Wq(m}To3NgEk-Q;3}RmN6dLfgP!T
z4(s3_tdD@Qnc7nX%MBn-qfm1*E}dX9P`_)*2+J1V5i;?zcysehwe%i<&9f*MiIP!3
zDB!4m4$_RGrWT*#Q?@c1*OT!`U+l@@PGo@smIT2ABx5BcogNg*0TMekR>jBOiTIzB
zJ+6l#`a05k*j*l}Qv26;Dehc)V}E1GmfzjFjgH(;nVt{O)lp!@z{DALkGH4*2F}aF
z&di=H$S(kA(t7HANUrz9$Bd_ymL-_xLgD?k8np-_q@U7YIB#U6-!);(U9np5?)lk^
zrA<bAs)vpB{E{J5f9f+@eTA-T3bKQ$rSGQwi4}eVB*Lw(#l_(i!u(J}jasOmC~_K9
zf~t;dF=B#boQ<piyOsx^f)Ta+_36GLBd6e$<M4{O)Q!8z0&D_(LF9Ek=4T5m4Erd0
zHWW)uM%iVVW<!9&oKt`=KaeHE8u>!c+e0D5rapU9K)weEaSod!Mnp6XQ9e%O@PlN*
zN^q}qDK4%h3!3WT%Lv;5<>U76m(9RuD}=tsYefvvV&IF{XV7m4xIW*&nEP8sNeL|f
zRzlw1@0g%$M`hGeG8&(VjvSuF(hPz=T&Z8ONsb$1Su&8H6YqgKu~GPG_P!Wjg<M{I
z?C6`WU@Mn@76Mpe&pVkf*xL}R5Exj5SI~O0tG@emyCq0*dv&^kltodnKzTyi%B9?w
z$4{=2WUlN%6PW!q4zNiHC5PLQ1*x%;{HeC5VJO|vnX=x;&m_e{C-*Qdm!P85#rV*m
z8Eg&<oIjUkL?$>BCObt@s2MAY9`wQYT4YQ)5B3kA5x>u}h*1;@1!pbW<t)Nd?zQx{
zr@(V}(u~B0*WNo2eP53iR=)=~-jQ#ZB}&0@=!KbbxB3cy_zn>Q@SB3J_15Iw%?N&<
zJA91UN4M~qiymFO1XT&Reb!__Ts_tTo8Wwho7?p?OiXtKe9)&P1+z7UmNUY2D3qX^
zdJKOP#Ah4NjxK+7D|phrQ{N{L++dq6`<g8a=1b&dMNr-F<4=G>plsA&X?1d}Hqm*g
zEj`BJO;LIt6p0ssB@5}@CYW!MDOwC>o3LXZIg!Jr1qkiHk|DQRjioAIYZ<g6lz9^D
zBAXasTEZvmG8S;hKaf+V)AZ&ibPi7D-hEiT09ccie+chSt_0v4+Ehp(!&2ga^M^Uu
z^HMqEz4X@QqS56{&P@A{TIFr4QQgnP_}9evw(tX|u3PF?&3`F$DSY<?9He%1wOY7D
zONb#BCxnmlkI{6MztJ9)GS$3L2cA5a6w@o(p6xl1w`kCiS<ce4Q(;Y8lg1Q-r;5?|
zhJ4Jysb~ALXM)?awYM6hy0?q*$<UI%I6ny@J7>*`H_wWN7Wt2*4o|F9(SW?Pz%+yt
zJF893m}7-zweq9~X!eT$O8v>X@T|SksFZtXJOv%uyM6}*AEZM&qT(h1BqX2A*2Ww_
zb$?o{-koXNcM{2j9%+gD5C(s5y@7$;;<lVq6Mtt({!bk%Rxo$<`QE5s#bVwRw7_nm
z3;epg!0Ns8A$4I^2eTr|_JSN&5m#`h$cJL-a7}$-92^OsGvrD4(d^W|vffjKYr~Fr
z)HdImqt-N3ErG02G;of1y_qD;1_Ky%WTr5L|JWG++B^LvZ{NdriA&)pRw2cme6GTB
zc+@)`Y3xQxf|#2!gu(2SE=&E4lXVnecVnu^f{jf2%ibx=`+5xRg`}_ICZjxQ?nH%F
zVf`^;X5PoHrEpY$h%5kgcD6sns<8m0+MbWJ;+CA=&cj(Xl4h@V!{K7!6PQ2K&P0d1
zK#poGEsumH(V`+|C}8P7>-4`3d4LDA6=}eI3JxUr{f#t;an6oe;xhRJVkN#Lq4Du(
zh-_$uUuX5Xw$;rtT;9?XiFFFO3=txvsyk-DD0*DInG`Gdl0D#y^K4(^EaP{#g|WyW
zAAT9@8SyJZgNDc{3T=f~&@s7(6iC__NyLhp1bFlWhd3z&zd@aUy%Vlvof``cx)2<d
z`34c;F`~udTDX@&U(diFR%&i4hGgBh_U)b4=9GvOZ@|*lVuf{5&@^N3(DiZ6ruTsc
zBXFpW$=Vf`!!s9gy@|%x-N({$48-^aKYHKZH;RGlDdDVkYO`dfrffH8yq_39Y(kum
z|NN-cNVNWb?BIp2wFFprs?^hIJ2>TCdYDV7q;GJQFkS$VR}K_QPhH)dh~TAuA*}b!
zx~a``S(=K-PWQr{W!#GVZD9$cb6H{O!cae7x8br~lqv@mdeCAu`ACQ1e_>R-pE4RT
zW>owB%*r7-Y+ajN_-I3D1)g|QL>KwfC}U~w!@*G4l|MxKG5!91;L0I+Y#s49Jp_R7
zbuc}P)fAkfjK;?~O7ev@ovU13o!`T;^m&ivvEx&pZKo$moL0$V4J=YsZK8(5k)L<a
zmSdUi(XoTiTF~SanKA<VB>|_E6K|_0Rtf7v(^9Tinpo&oCqQ6JhzUPG)~9gzC05Kt
z$)Em)kn?INC+Wk_zJ}N(KGx*$Z8DJMqb+1LtMzciDppL|Xaz%m`N5Z19DOs-ID1Us
z;^&eT$gDW*tbPZFj)EmQR)M7gJ7yjsp~#|b(>;$38K+~H`q^J-FJcwi4AR1$=2~p2
zI0`bJ_4wY{=b?$EeSO5#kgs`$&W^pWqrosq=w#k3(|W=0#msc`vy|izX`lKo!+m5m
zYrtrHt;OJEoP`=UHS=^zavB~x5c#zewp5MEm7sfICoF;q1m@a+1Fr$8e&XruosPZd
zo3bqgW3^e%D-aDhbw`HVXFY4en0Rfvm9fiV-_E8@3an3k9u`L;Y)2lw`stV+F8J1<
zE#qSa-6xm-_4A~dN&g4Kt7wlU_$4oYcsBIu;{{Pyvy@gNtQ{8%g{ZHkejjcRFUQ({
znIJ!(xf3wMD6%|#h;vy2(b+pq<nreS@V6PpkI3ee;me$h>>kT;=OPz2n6G{oA@d#}
zO&DaVbxeE**Zu4*oF^hhPX*S-Q}zBo&<k^Ok$?C6oT@zy&eM^_2PpV@Isrpq{2*A*
zYkCW<C#>~MkuinM_wszU0_&DmhbA8#+0;!IXbI;(#a_7xj*pSux$1`ZcoHZ?OYXcU
zmv3@l-e&CEMJ{jrG8eu@N7~3{1H;Iu7;RaQtw7txa1kw?otP39Kg~1}tz7w9XfO!V
zAs$Ut2-CpYKm3rY!Qf<>FjQnpXZnH`ewEtTd3z>aG#Jd?Tz>_Y)v5RZ6;}4FB0o}z
zHSx3qtc19>=yIKho|aw<@yRwseUxj1*FOsz7<!(Nne3lNoz2@DqR{GFeSRD$0Y~nN
z6=I=|yPZkj6V#28c;2YujJ@m^X!;f`ZqvLEGlf$t#t*ldzJ|_DY9FDM6b#95uUyj=
zJXvq)wVl(6^0A7qbAg1f<nsNqJv5WX=y|sUhwOlYls_2@UFUZMa5Kw-g%HnpJ$Ej1
z*MF1Piid`IU-U}2rH@I1yrIKq6<EAOD_AjRr9;s-=3muj27^E_rUY^R87b~x9JZMg
zWx<W&kR4LA0kMcoE6YY47UzGZ<j$r<|98!hLdy!NSq5_|`=K<KbC{6Ci2aK~?Y0h-
zm*MKgxsFY?3#-m1cFCfWc-`eIS+Gaf&PqQ(X?#E|Tk2O@tUVg9{UQGI^k#-xns@r>
zK5;yK*z%$&M^?ngO8&;L{(f7jp5J&toPY7dbSyf%s|Yjoyi`1N577bT`t{Mokpz6x
zUy$cSC1NCa!or;jY_#4Ytj5~stA`C)2SW6pM`n@u@BTSSagR5LRokzh@4}{9qyS9x
z{^77w?uL+q(oWs(`>0Og5z4gu&m){vXn#@OPUP~I{<QqYeb7FX?hHG%*C5h**elw?
zFJ$|d&I?}B+|;tb^m^ya`=i~3=?3Y%AO8;Qvp{lq`{eV^_i8Vjf&8@T#e4Us-_<dz
zyN-9Kuf^<K(=%}aPLCD8$@O{`$%X%tYhiIC$K_i+Gs)rGRj2k(gq^BN*QP4_59ixF
zl+1x6qLH594fP{i`_R`SpT_$82Z-??km$Z66#Q+pUhs>UA%g~dLerq+7;ZkOq+Q=`
z^y+-%&+^)Ts_x9IQNJg0Exz>C$QRFPAF7@9ZFIPQh?xAp^wi)ip#M_FoEe(jHS;Vy
zro3fG3{!EhaO2pXM{=$~A*IJ*TUr0sC_KrV3ZwQ}Dcz!i2e7gkk~N^y&(4qq-I#fb
z4CV~=5^1)8Q9)XketVRnRQBUbSZ_D}!}klUhaXo_j|?)>?IJTc?Yy~b--MsTXYxG~
zy0)O4dELb;S#Z8FEB@j*r96-{)WCATg^-_}4(lDvU45$$ghDvt2}i?0XY(S`Cw9Hr
zJst^~hbg5&{}bC)btdg)`%dxDeUoybC0<kIo7CRTR02+!VkrIS87yx6_H6OG+Yw((
zvWk}d)(tBuu5K>(Rz)@cNd<9!i?`D#C28(QlV>kA*>S-4di*C}tVOI{tkbtXC;YSE
zlH+3v1-1m0C>dfvhcq|#_(n$Zh}WAO+|0JHIB@tlj8LDorC7#}zX403M_ypQ4Y7R8
zrRnC&Y{IxaCsp*ff*%C0dQbDS)RPvUs5r~(F7M4)lhvV$EWP950XJm0<*KnxU;19-
zb9zL~lX*Y>6)^O$cB5KB^H%Xtn{kQI0)LzY|1j)4s%~sKwktj<GXILw*y)Bj$?j`v
zYm3N&46#r>=a5ghs_>2z6(nW)N&>~m3=FFA%0J?G*5$9>cy{*08k9$ACU#+eOJC{r
zK8ieTEU=U(8~MdPI{eVdRFbmMh3T5IRR67vy|P^U*$ueX?yM2+XXUg?e`~_JC~cw-
zB8ufKcIlLC#1~xj3f8u)xxV49P=4B7t(t`_hPwpSpGy5cCXr@KR1$Ih65R;edJApI
z{7h(xo>I<4$8YXbCrsB}LaQ5A>NV^g&yb+{)r=wpHbnJBf*=Q2jTIGG>~eu@=ofqU
z@Y%h$&F0NX+CXSjFGQ;w(GbF$5>#KNUh~+}G;5-!$nSZPh_)P_q%I@|DQBSTpLVE?
z8r63JL8&AVT&vFYVgGJP`(J`aWvs<im(h?!3;&>5+}L@Dv=T}e)m-T;&|}oZ4L`ir
z$8*2YU%SV>xoFzi(+5?*sp1|gci@e$HiK$SNuOQbGI`8Q_5ek)Y50atyN3fser>C}
zZ1zCsijRqLS8~0l3Ex`;sSZS=e;Wi2`Ix-Ef*|GY2{0CQ0-asEhd<CY>zCEn)#z_=
zFjOunoTne%)fa5TnHTfH%G<*-2`AAZqc<e^c8?GMXru%?7n&4$r9&X7&*6G6%yzs(
zo@wj3fwrIpT-+9>b(YbJN^y*_mpI=5j1Rj;Nsp-H&a}eDF|p7?O+Q+SFM)-Ofvp(h
zJ`haFmoqcCr*j@^w@;fHYzbxG={ksFPfQ8IecGhCo-o$5WkKN`_Ky@<)>dKegA#2k
zSnF$eA0ADN3)4f2tomz@xH}gzr_b-^r0pi!ilo#`O-u})F9RHXeki2+!%3J~dS`#F
zfa|EPV_(0wT(qUct2H{(9o~B^yi3;6awt?TdERONGA%IdFAhfBXGxj-7wSSDn!X83
z`aXDKnmxS37^`-;KtCu{iFIimCV!nG-uqzaOQ(g`<&EsJZx7Eq=u|vKoekolBE}qK
zxUdcJsE`ke?6QwmWMK`=+>4a3YRX@+)WRp`trx~J0%vubvWBcOi&j?teZ0P2a^V%4
zp1G17J~mHiiOZW%3|3A?%WJi+j)BOSj;I@<G^?iCJyp%m>z$vL;Po^s@=<3G1&}Oe
zvc>rurMQh<OU*2OsreNEzSZUYzS?*QOW9lF|E^K>nZ2Ph{j3|!I;LQ<w82c~g!F4R
zJ38_>1rFhs!?zb(Y8wPwV}#Si>#MTmxtdnF_J;iW^6U6~3udOMQf`jzsBY8~i~pfg
z@BKTz<NRr|`O_2l9c5Bn-T}FgV&E=}nY}UZlpAfI>~!u&o6)UN*J+Xi&5=hb_=Y7|
zwPI0{?^}-%gB>8mJUuM|Y;w2Ch33Jysn9oV%)`0S_KFu#Wo!ugQTbO=((wx?u_V|*
zU!TAPP!sq%+y_%$2m39tX=-n`;e(%;hV}>9FCT2`4?7$zRd$niM0B<L0G~gp-lYgP
zVLQb5=<Kio+<K7waC^oF%Y}PtZw{uj52u<>hT5M!nk)TYDL-c)!6>S3Ih(!6;!U)A
z|3!yR&l6<xCnwaE`0Vqsg2r3V5^L1<*NWvhWsJ!MZRY4mez6@B2xei+VOvU~XnJ3Y
zPZ`QDlig2|bh^k=X3KKtsMQHYgZ-Ga1i`75n@c0z?1}9nw?3*rkQYLKU`u@09}`q`
zsX_{d$??5Ku5TBb-uW;Fm)krQ@RvqxQ=jd(@X^v|yzioa>VFlPom5}N0;5HZNt1uD
zN)oz$b8EGMaN^G0^TzF+BVVHRnv3f08|o2M5}JOFZM;zG=jK9O5ZRGD`in>H<t))u
zPDxpuEroq+s8`uTmfNmM<n<G+M|BaB@r|b8ouxFMnwYV78%!3<EetBG#Q~2cM~!r`
zYK{eQwki6I(V&5zq`{39C7!3h=Trp`jCpyAa4<{r@Utv|cQZ<yztYWup|A8t)1Jqg
zuinUTzYyemm4LNq3^6Qee<(|6)+S=s+?)J4u4+nbJ&q;HFBzg(Y#$v`&PLNAtm9j#
zT18*+icp)cy170O%+vl*2O%+0LP%Dc5}S|z1tb>}EVR|z^gA$!;rUb=di2|=dpX^X
zs%d%kkAl}Gp&d52y<2I&niXvJs=uFj)<J!w-*xx*oEoEZ3#y(Q`-;|A266PcS(qx2
z=MDhb@XBX6jg`nbw6MR1$?d1atnliUX3Kzh+NS(4Sw-^Gr?j@qeD70v)#vv*qo-{7
ziD+JH@%ywM8LqapWa#wjkFMhQKO^5-$TI_7$>y0Cm5Sz;a_>p--X^KG&H7;;K@H)X
zw&#5BlX=DdRYUh}-oxUmwCq1v&MRcN*ll-8WN3$k|G25qMk~ca_q1;E4!(hoEZ>!k
z&n4I$H6*ByaCV=*lUp<GQQvvNx+-`h<OHZ1i*j>V&(Ql5kPzIr_^%0nDp(U{9>MgL
z;$APc>$u28N500k|E?e%D%ia$@8h(`#QO_QeMK89U+^}!oTvw&5gFyREIr%(l==x?
zM2$g+;@GavP2PrH6uMbPAy}an*1fu+O0!6&I(<~8>xfun#?yns((EYsFL~(5uzI&m
z42OfP)S8Wq_0mSZIioPt|8!-~<iZ-le1E4v&|VPQ-)ul~SrTij9u_!d{s>Kfpn#<f
zXS8puK2`K4>6-e>nu%bwBy{|r9aS$j$#6eQ9<Kd3dA-Y`Bk|b27XuL6KUw5a)1c=m
zpoy)zZ87p;IP@@<giQr-saUEatM6KPn}Req>aA+W#SApl*L-D#YyH4*73SXMPxncJ
zfi^;Y?rVJ0OoY_)O%ZjIFWCv;r=($d)f-DQd+#jG<;Rv!7mJ1N?3eR4fV81zsUL8;
ziD5ftV9ZXhTAnl8x7R50<kSlzkFJTzp$4`KAxzDUf<FLeot9p5dGvY7KN&SS9dBN2
zTFUK=aqRp!`Qk*Y`5HlcOxSjrzUIm4dJFEx))Gd?nmo%(O_}nA2ZKIEfe6~rmTJ8b
zr!ET4_~f*)pQn>Y`jm^LW}XH}8qKmTB^L|^hdmrS%O)!hw3e?%YBQAWyE9YPo?bB=
zmLGgF^g^YY_?-lcuM+Ls6vzVd2Xgs5ZO*MJ#Ns+lX5_$ZO26aQ6DJ-`q3GX6x(&fx
zIdEDlyoi?cXR^_w$Z4PY$0y${Uzp;=Sk9~(!tE_o$+Nrk(Kh|`I<rl?DPSQ4d-<22
zCabsR9t?}ZUkmn0+y=O*TJ!Te<I}YmM%PK~$OYS&GoATMXTzQ=B(E$6pM*QF-Qflg
zjE}b(BwwUOD~PJRlAOs3ku>5fz(R015Iuij&O5^MT+2n3`ML#RQk8bdi4WE)`S?p8
zt<~KeTed;+J@PYh`B1ORjx_np&2w^E>92^(_bj{kNv*r6SGFV5gOa4Whklsu!c<;m
z*uIxOL0{;fJg$2G*kglJ^-GcxEMES28JZRZkqnksIpp$})kN1RnUxmjC%0T*-Fz2Q
zNoZ0jeh(Jd_7%w%g(GWAorJ*8{+1zS0m2XAqo2<blT?NFRmODQF@vnnjj#1!vtY86
z`{3<fowUpAL{(l&&b%Nl6o#m>>WlVdvq(>cou-#MqnUhWL8gL>l5sw7ok79p#!bk&
zDY??(!uXD5Ynmz0aKB3Nn+Y`4%;p*|q=?p3bn(V@;c%5|nr7~!!9sESEfJ=vl|Nbm
zT5<y;Q9Au~kaG31i|?S<-1+uyUrMv;`oPk17v@iA!@YYKrh0BTtZ4q~#azO^WpT^?
z^u!ivu6C&(#lyxuzSKh}?VoLZ%6XE-2kDpM!~S3edhE-x82w%}`?uZ40j7m()qdYK
zZc{owe{mWI!VT*|8W|aAYPm@B^#N+hY~R(FziK$d+SNp0N~Dv^xv0%egPpVXF?r|L
z&V#A?o>p!KiMd2G(c(&-=U^tJNDi_aG8YRy+*<J6{@vY^QrvvgA!Z**BJ>CKeEYNZ
zoXHox&3oTK+ivZrePv(ItujvFjr)^aG@U8TbE&Q8mvW!KjL}KGy6w^IARqjzqi*wB
z=rQwh+^dseuW3&FsV8fGwYyMt&iP<5;ZowhbhD&<-y6YGGq1_zqzfLtJ!l8bnoUmf
zE@ms;_e>_C)t}V}F+(1ddRLYz{sqCQ!n`nk%2tui&%B~O*(cf6I+t_r@YiZ_dvrvX
z>*wkcNY-BSX?X3XW!z`VAOEh#SwT%o?h=bNeH3B_(lwWI2gdPSZiwZ(y`B@NX9(%u
zRoBZq6w7|xIks}h<%A!{|Hm`KI(`@0(k`K9Q?RrF78j<VyQaZ)e%$qI)%Uvhcd-$T
z!7@HMNOfY^G>kBrsY<PW?G@J*-u*qjIKpwoCu85Zxm9<M%|?}!dO1cWpwrL!WuqC5
z*U}0DwpU;0B-e#SsYFbTZi9fJ86IJNev%qQ{hC}KKDkSN<k~e8&F5#BOA2h#x5T!*
z5-SS}zlN5t`{}^h90Cr$D=}W2)7RHD8l_I7jAn<J?vLfUGd+<rN=*5OC*yFWk?5G5
z7Nw1i_6=VnWIp{Fk+J1$<DnD{Ms(tg>j|}>yW1F^7oPVLjd#~Jey^*htcw^Z6)$e|
zm{Zdar8xLZsn5M<MtXl%j+h-VS_rg5uE5P+5iYf6#@{sXI-W3(?OHuBy1?(gHT-ho
zP0eza??wj~GgbF1yoc;n-S*k@VT|eEzs5@rp1txYazQT__b6DM$!0r$#%$gjY`!&`
zC-t(>PP<W!6(^#e^5BRn-Q@G*W!#%<b4t|Y4vgo$Z`^ivpStM?Y9z3Y9<yJS<(MKc
zi}a1RB2Fk0=VxAWG&9aLi*Dv5y6Y^2bJGdOGR85&dXFm1Lo7afy$!isu*Y@VlMmXb
zoL9oQt4Hto#a5AOc;zRoMa>&}pY!zbOe4$3?eSC>)RN;tn61ZW-yL<-cm~lEIR|EC
zraMxwIEs6J(K}L`dSS?4)yoEAyv?E<O1-*8Y3k#Xl6x;%*UiV#OW7I~{Dbo(QqS_O
zt{-zH_gJT|@QnRFslbuaz9syD*~pkc==Vs-4wM0X*u3GG2-9I^Hu_QLmKxz5d}nAv
zm*7>JCCzW;>Ky1&MV7-qXLiq(xDpLzvgnr_q`2i%F*<1pSkc*$1#`oIWwrxFm*i(i
zZ=2QEetv8+&7ALDcsBd-TlySNF>ImO?Db&fPT6F&flU$HT@SpX#MsscrShD|?^#Ee
zS1@9_)Y?}(-#L7JnevxlayW&gG7~k*4vUF?^wqpZ_z^D{@99+HG|CSPCq`CK#rk#(
z5g#0%-C3M_PE9jY6O4ss{C5ymI@F(k@V)Y3``WwXf=ouuKv5(xR2pn-eE(CxPs{oD
zmX=|aTAd5sB9>$J{0m$6ROL!u%dEd7zPry@1Jie=fmv6hMK1r?Ib$<9ZvRI4R$c9b
zaRC}CD!w#5M=B0BF}aca^Gl>4HZqd;k5lPF>v~de>g?o+zpuE-@34tnXjZW6yT!|N
zwvMz@U(Qne^JsK~$(kK$a7nsa)o6^wjGxlgtT~yO%Eyz&J2mBxWzD5qvi5dy@-%qO
zF9$EVH!$ZWcUKu}Vur06n9X~cN3j-{$OcbR60ud_(<%SeUvhM6{=}%C-&%wA1jue`
z88LR(sZ{;T-SkjuO~#jFFw9fdk<6r(FM6NwJ~iJRi#7G47_AEJ<%YPv(O6Med-p3i
zz{U)eTne5eJ)ef|+#7kfFrPyYzj(S<1G#s8GXG;qd7>~)Pp=Jf@jaz(V>VA@U?FLO
znseUL%Zc01?tnZ>>xkanowW3y5%xEBU2~XKZ>yW|s38)^tA7@34>;_XE}~`~S;5ym
z{?3=vs<*AP=p~vF=9ZwRs7`oI#d0#2Dc9)<H$p8VNG+U-8#m@J*f;96$<1hbgcFDN
z48Af9a15*wAz4ShC{Y^jk;-J#-(F-|VbhvvVy_FfUo^Lr;);}d_W<<(P*)IBbK@W}
ztUD)5h05f9v4UY8$)eYpuZZheld1IJ-D&)rtAKpQXmn<{wIw|WI&vir++i(tHtUqP
zPb*fmf6aHOnRqQ!zJn|I=Z5y~3K-2ydgaAGevwzZ;w`ai&9o)&3$}aj1RxBN(viic
zJ8#@@Bc@UNlV0-PUgo*3e`YX5JbGx>>?7{$>NG4-<l6qpCPmiyVVMIMZPC5FXpK?o
z;HIwOxvO2n11*mR`Nt!6*-~BhH#=n<IhIv<CX1f+>T2~E#3cD3h~wiL4otP+bLk5|
z&#y7b0DzCkh@x>E(}73YTN4yf-`qQQoY;DER(Hki4;kXR8|EuA5A3+&0Z~sAb3|3}
zKDrUyAN#IG`*S1SQqMhxhoww6hpr#x_3axC3Ay-<|L#RaMV7Np&cvaE*;*&MI~tg~
zORWpXRzT~fDkG2J!m3BZ0k2x*nI@bKU1OFBxES<0mC$VUy~O$|_r$KfJ{&jQigV{H
zlw!4<Ohi2rg(KVcy}X<a4AiQYQiLx!k#0lDy(-*P&v!L4FA|yVIEi=;$RKyZzKc_n
z&^0mE@?hbiYiNNjwN-3ZZ}rM&y%P55`M~w-THk6W;4%^}<YvM#KX9b%)5ig9#Ck^9
zV0q&7tnZ0wbMr109~&jyM1!s2Wf9vwWzQNeZO)>fU~ROW-q2wC&4Fsh>A;c#d^nzc
zdtNv)Jx*1}+d%ij^q~8dBgBw$eO9+_886HE;__Xq;`W^B5l!3|nSFQv%Yb@~iakzO
z+-w%U^XR%$cFjF*8Ww5iQ)Y1bimSgTYQ$e>We^EJQb{SzZu0R))hR41qe>pp?)0b9
zubEq-(HrMCp1M%`1ry6tR#hy&ZLh|vkw~I#_x@%)Uh#O-wk>q4E|=-f^7{CR($Svr
zh6e=|KP>Lza-S|cZlZk4N`Xfal6{E3=)IPgUnY&GqX}EMw7#;x!p*-L4oiME1;^WC
z)5HJP@Zm`nja7FS_oC$banl>xGMX*g75rm=Z4Yo*U$GD0Ka%3|N|OJ#RT^!ZcZ2cZ
zUOUsRK)xVb@iD%ybhLH+ZC)R}7k3Z$ympz3nVfd4cJb}5ma$zg{Soqfl^<9*UHUf2
zCkLJ;ms5pi#3c2aKxRST(@T1Plgm7aFV5=wOd3DgQh9VQvGJ{3Z5<{)-*b8Cf$#iP
ztfV;zqf+UU@N(=r@%^C`H+Ob)AcB<gJ)-`G#~#|cw$W@(*8Mt0f8T?bHhr(AMq<B)
zt+-)(WaKK(mHcTkKZg@7V01SaRm-+LE`Oi7tFg~bwxyv=VEn=?T{V6(+$#KQIQaH|
z3%`=9Uh`@wtnTqyJg+_OfX=ZJ%|ph03GKaLOUdx6PX1(Si0x{O!a$cBOD9^#5A>*<
zivI5DO?<d%N05j~<{74b{*Aee(|vFLsQrLRd^C|<tnwp5EYu}oTCJBq*cbbl?`^<o
zA?ZRowUdm(uAZ8copVDW54fr2R*juT75g2PE68iV<PG1e8jJhNmi$Yywi<IgZemTb
zbRBHVci06NSW7y;<eG0gjUOHB%NvOZ3U8X+IKS^>oN<MXzcTIbq2|2dHQqPkw)w31
zvZ=M0%{@0&jThKwpc(96GF0&@==84pdi%M#!}ZqI_IcwRGj&yb9LdY*wly(flL1M#
z^~K5d#)CxsQa{~w_n-#+Y*?A17+?4`i*TLr>T^(;^<L+^F?0R19)#(>=OYmT;WtBk
zja<_jV|P4#r}fggik7{bC}|!<Q>b#TeTTXCrl=e+)2m+F1zk3YX{L>s8=NB$R+&6o
zuQzf<B@o(Nd2CP6g_h}|Tev|?E_dy7onytC`crp;y~*LP3QKgiv1i(vQ#~YxhliK%
z4gB%G)2H5Eui@f$8OA!<xioge$F`vc`I_xFFNba4MF`c@WJr1@|5Q$t%M0xcJ^STH
zm#)u|7+i;J(kM^kv&JjGSLa%$!xM3pxK-h&bv0Xx*!p94f`dHZ1YBi{N8`^WbF}<#
z<OQ~dUidcEb#dmPYM8%~Yi(of3MH2v_YH>T`ZJp^{5es{7oV64ztYLAqXOFEoDP?V
z;g(ci&E3xa!zC#-d(ZIb=W4a4TBG1945nh=w%W;zJykS%9`D)y${`=pn{v#<ZO!En
z^t#KyKH%Qwn3mEZbAyY~1OslS9KBQ}ca-C#tXqC~1&AdHf<lko+g_)4v`BMD@BLs|
za(HHSXs$kcb^DQ2_LbqW7gtihag>VCOjvEcdA3Y@B&Pjz+!mjL&+~S8GG{Ql-ChBp
z5|d~+i$>$mmw&81-Iy`)HcyAv^dQl6zD@YJCnFt~C2WY@Wh6UC!f~uCPz4`3;(b%M
zOqmn8k2WwoklyJ`T>XA5cSrx9$*WS8s=c^zd)9vABu&Z7HZSnBCKGWhN}*-Pef3PI
zdw%wMErr?NCenfdx%2LKYh45OR+m+&Y@m8EtNxASJf$aVN5N&uHRQbc6PnE9?boUP
z%O~hfAtsxoQ~@{MRj=&*UTltOeK}xm<da1B#!s=QQwb~Y{6%b1-f%W8^GXEMfq3W-
zRtkQrSN+pQt5LrT<nWj9gRxM*kk)tH@kYVP&!H!~4Vg~{O;SlN%)w-N&gJl&Il=a)
zSK{#Kd7ioZXXCOHZE1&-lDoi>275odxb3>A*HM4m>XNTToZ$W0_$K_a_-nj2lC#;>
z6o;y6^>KrB?`-^n-n_&-olWinJN35v9>pEE)?;Wt%D4Ju6B-Ba+S8w?-_6(|q3hN8
zz~uFnIOc*3_WET15cy2lp(dk>SS@L8mlbJBcrLx0sDFbubARG(%V(NZlDp~r9nz@=
z;S*d#ZghY6jnOc#pfjsd3uNvLAG?j4)U}1Zn#G&Rvuioy2JFlE$q}(~*#Wbv^WQ?B
zv09GHscq2Q#@VF#`AGLCVf_N%@=YEl=WR~cWhZg|VJlp_oVfIlqUbd-#DLn+lVje@
zjM-cE^hbCTaA_GkCEK{m-P>`*gL~Fuw7Y0wV*l2Q4mm$_gTbRcip&{4^)_G4%@4P_
zf@$;wli4^r+-$GPlK<1!(4>}hHZL(X_<8sFFd43fL2yN^B5Qu-CvVLO*{Ok>6K}^<
z7jQl6Qb~#Qz}M&)yCDxX-!6rK;INiv$Q_M+<2E`=ljIAmNWG}dciVA4REEE9WMA%a
z5mvn1WjY_k+({|epmKk2O7OD${v{6?G3RMRIy>QtW@}OBC!@A#+yAe<FOP@vd;7nO
zNVcTazD0`=Wf@zOvKH+s*`iRQm}th5C|WFIDHTRCNGmDJ*i($eXeeaQgt3if?AvqQ
z)93R%&+qs8{qy_(``;|rb)D;6=Q_)M?sMMnI{u#N1)IGtxVbx}5i%}jntP(OSucDR
z)}>HQ+zN-@bOUto<=f0(`N!2hN*>l~bJ|(A^Oo(h<(Dl<C0y=Xsb^vYYvt>7BQNi|
z_fBC}X41k}=Q`Ga<{6#g)MNSO+ti-+8^XJE-YHBiiq}FRXW{fdT8OX?tNFQ{MD7uW
zQ}|h$s3^Q?IOJ~MAUH#fnJ{<mEB$%HIKy+z{A#a9&PEe=CnEh0KD-(yCoNy}O-Y7Y
z`0{a6M@hs)z23C?_aiE@i(7Ay|J=2-mjZxt<?7I0k-m1ynzPTi4jLRFJn5U3r}iz!
zQ)yddRyF);@5XmbXhaIUpdI-cyR=TvYXS7O39SXa$X*fNj&)B}7rC~Ni_l-`l{RqC
zMvA06_2dPgk?iW)!<rK@;c0Z)HfVN}UrOi3fsA*Xt0aWIHl48i#wqek<GHca^|Py)
zK=UWV>Q_FDcYiv)c$<rBKqGFFT*?zAfk|m-iiE?`7VlH=pYgtDuWy=bkx=$BD={HN
zXDCtUGoSnv5js3kB7N0iUqI-45_`JqmXQ)}PQ~l-zd^HnHa-=|bKgIREl0B?`X1l=
zPF~_kZ&GsU&A%F(x^Hpu;^qi+Xm>?UyC2_P{31DCj-^^$nIp<*KT$il)}$BTS>?OD
zK`(kqPA_XY$g=YcT=e+KiL^@E%&EX#_lpYI>u4h`#7&J>tQ3;+zL)9OiHi+I(+$4M
z_f_Q2Sj{~crFL*(0wUbxsb^v(Aq5JTUa~r29BxmGzu^^J6idNNk_Ur?{YUSmdw4KC
zKgsLT`q=I151}SLXpWgb?EDA^GW;ywjWW3L((@)sKd+aW7|iM&*UDpCcSqaydCyTA
zEFpb$(eyQWX#c7pl_TB;G@HD}l1<)aN(uKZ%x-RyYVp>~c()IjGA_SQ#h2mpu!|d>
zPIKd3n5#%Ojzp`8JWAT-9{W6O;B$dt?T(zoUmlW6`J>zoNey|=*99l;ZTYVEyQr|C
zoAM1CT$ICJX*CRhpUXB3r5!}0in>9qj)ucu?vP6bqTCIV8nn{HP!+n~`w@Io&!t0K
zu^rZgfD9klcGmlZyRtCYoTXHMCBHA>{-EhiajBLYm<&~`laai$E45Cje2eUj-Wpjb
z74I-N;m5E|i}$@0T+~tSX!Wf1DotxcQ}hx>@BJ{&(*DI)v_(uNs9)*|rJ8KdN3JhW
z=u|E)(g5rmAtAq&?V)}pnfc-DyzZ34Vcv6(PMSc2L!|2bI<6P|QjZ75pK2}hcO&1p
z@dXt<b%UC}<Tb86$0wYbX&r42t<VV=d#OM@6DL{Am7&d|w4K)paRQAzvv(t(x$z%+
z{?$momvDNjb@cN*Xl&UD-5oUKVYmwLc%AsOTrQqrL*C?jzBHsr|0W@7ay=hiZKTMf
zLSJ3f<!S!CgQbGBBHcuzruQCb)1=`Qd^;u!61{etJUI6VIB#0-CBglGNVTV8f`7{s
z<#@<$9sQP2QLy~R9j?nib$656;st7<?{BBe#s5)FYx1!RE;?0{KS7C@q8><e?YQ`8
zK~ryX++C#@E@?m%Y@V9Dq!n6PTmJlE$B0?D$EMc-sOu#$U%R~TQcvzajZSnK*X0Wo
zC;461w6>eSC<__9t5#mH&o-lVE8K5xC&&Ao4K6y?nm<8^n5sVj=fDa)EBI+qy(3!X
ztFd*@!KG&Zj_VYQPr$4f&;DvTs7Os{NSk-aup(C8%D65*l!D*3r5dkT8sC=JeJ8`j
zyX%tnr!kp$)x@U|a2mA#w6V5v^mL3}%NaQI^oGl7P_x-+LWXMbxkT`tp3akoyw4D_
z2M{tKkTJw|m=PRZwo(W82<yFRbr7x%kx`AF(=1}oI9qm#%!@FTzdq^>E7XO1klfIf
znAekjWCr{9tTu}NZZMkV;iRuAcoG{JS<O;pU%4^dU7c8>>Vr1^uHqM3zB<^t?W@OC
z=rx$kPjFo9SEeXApv$qnlHe+49_mH<N2$C#vBYo++CO$zz}~&S1ulKIwHZbm4t5w3
zPAYAszFIG!_o~xDIKZpg)KX)1(YZv>(_jB_L*6$4w}fiYp3me?!HHjGZagpZU{V9@
zemtrP`fiyhvw@2?pw(=Yd`>-P;#;6rv}c8GGVKrh<Of{{^bj-u_vO=k*gAMw@5S7j
z6f5)YsK)q<Kqq~6^;UVETE=wjjAqd!^PHvq>3JCYzmi5WrU-i<$@CrI#%HsG>&%Gp
z+r;q4s<Nf#826#wr{?+m#XAah;~VmRiJ+ck2)`)Wd)S=lt$4ra6hXgFfoicnLNBxD
zG*sn_X`RM=J9mkIcpIsPS;$%&oOrOM;oV6)V%-6vw+dtkVQ(J}$fz_wjRhQq1!trY
z__aY^hc@J^u~d`wrM4ikL^ul4D^7p$c+1}Yb=*2GsnkJolb2<1(Y_XH2qto}nb%r?
zu_vdKHmX{osMY5+_eigDOve7BUH<(IdARB;ypJEqsK(lT-QK<mZ<80kc_dEom^M2R
zikd3lz@<|=G_5gLlT}-romhe?ogTXLzE6W&=M`m&<Wbs)xX4mpk*&R8chk1J-iaWD
zmKNTloYVQeU$sIr4@xs$w5P?+CrKLaC+57U8DdV&^I!G4Ut~;>%m6;NhmrbeeWp<X
zSIf06HRdG+m(<;HekxJ<=DvQJ?ozj8T#mZ5HC$<05BKiyci1~D&4_s~CH+jBqNV1#
z?q5s1Fy$vUf1!C`>fDI$E2;6bE!rEQQF}WY1oK234hBXQ?IVa};G`K1n`Zq5kLgVj
z-^%N=%Qy6B*Rp;0uxqkfh6~OGevw){-?HZg+{Ne&FxY62phy+A*F`*r4tX73f~&I7
zV&W%-1M`=-{;HM_`D$@g%g^Cjg^Ew*8hnDw1}xn>(gL&y;c+f&{-9a~peviJWjbR^
zE(96XJijs2Be=OgMfmOJD!%m6!j#U?S`XpgioB8f2aJ@wklIzVrOB5UU7Mc`F59OU
zYpo7i8B>HMj48sQt2nge9zAG^ipMvn=EY~PG>=R<cU+qlD%RD+Yp~0K#OTvj9jA}(
z0|B0=gRoN@3lx@j75l`_t!Etmp?<!|d#mYUSJ<Foy;HKy?)##LZu)YS3hK6zzNxZ$
zQu4mY`lXVADdJ+jqSC;0ddKXVRgb@nC^RuT(>8gW3NAYM|I(GJO&%FY*>vEZH6MK!
zRrqASg3IkBPtzdLXhs-0{tBpJqrMAkIwV#Z<egtXVRiFnPl=!(0F|}tS;hX6^L%&J
z%(Afk-M%3HXvTb6ll$4^kfN<;jl+G@xtZ#7<#SOJU44(j&(ASgp3QlV@$C6$$r(&|
zhWN5Ur5f+Fyi>?w>-+=%Sp_TAmJi&sj!B`0r<NV17TRKt9x_~9jF{6LiVc)zv&mQB
z_^L~k#rOqDeAJ53_FD?}l<J1Ty{g#2(;3~udmSG08s<5#&9PcWQcDEq$@Z%Q^oK~m
z#G2R>v+y;t=oQkuKZX@;_XZ!pHy-M`MZL>y9l2>VOib;oleCS--Ik1-LD<gFB)aPD
z4yipyoruEy*A53>s<Jah_F#@NnhuS#%@d!>7`|xzKXrC@h8ELV;Y%g#V>U$Lfoo<4
zc_E&X2muqvP<l1amaw<GK(qp^im>$utHz=lZ-(<4=3ZPMOIuoPR3ccI*11#O|5D~7
z8R__*7(Lc#;i@2Fs+oaVTt-He1<x#zhpDr4jVFAptLkU?dEno1{2cFC%6{b%UifWp
zdQ3*TwI{|usDdSoq~r9eb**QY&1eD%{(|Gx%ircCMCkK;JX_R0g(RQVxSy$XGkmG@
zjy$1+aM3H)fh9MCCq|i$($1$5WOu3ZA(rWx)F|WG+$c*cL7@7PpELZlnTzMf=<&<O
zyC>R&>5GL|O|MMV4Y?#0dv@LPT1asIN-}9pK;RD8;qgfN@d}#^{&D|kVM3?~j{vJV
zY-7av-<i^BgVx<yIK?P-ahs+BP;4$8&b{t(^lArJ)@__`DUl@Babqo`D&Ye4Zp9Y$
zQCW)kZi<ui**)QIE`f=GowqkKO{E4)bC*84d*fyza00@|ykBr-QE)z}s$HQg(RYB@
z9reBGZi?hw{mW~IFf94WS-B79O5?6Q%XYatn5W(zyMf~>(_oGS%Ifbe0(NPBJ!5<M
zP@jIISCzX5KSwq6_#Kgvr1qp$%;n?EJx>t~xXNVzO6&QS$Ov!1_impP+x<aa`mAQ;
z8KuC)fp^#loTLdEm3Lb{6|jbDUjfe7FrKu9M1W(;2^YQ*tI|!UWGQ0mxqp?QD$hN!
z**NhqP|~gyL~POu=kKr^M-R9WX>6CDHa5;NVf}8@W+8vqcI}Hvv)3-Iq@1OMJJB86
z_jz-b8UN#s0@ZNK_-b$GZeq6NOg-h=A>GM}#!%ct+$P?%LP~jL&tY$_tlYn0m4f>M
zO*0yUh3B2WQKt=!Oq?onmyP(Vb`Lg2HSEl6CBM?%(f&hljqpAsA5>8HOW<{|Co_7t
zyayrFl1K2$a>hm>XL_cz>poj)qQ~znoVC_Ay_GAv==Ao*{e(+1L%*?0d(0}sKMZWa
zY~K5!J^8E-(X21<S$0bCNy^<Gy6vLf4=gWIW9~c6&&=%Zm<(AkFs}?BeUmDB&ZV*0
z=jNq9`z|IeTsv01c$N~TL=+n7d|9^#>5Bd9&WN7ScxtV>YdtT;xt^Mf(Js9n8gYe{
z@d%u%mfn`s5tVlN2G3V<L`Ai|U6q^>D*gaqPH$cDxf)m#F5cQ<wM&wk7;AV8Q!H&!
zH7Y^YLeAMy3hhm;1WQ+s-wtW8x!Bd^6L@KOpJLL|EtI(cbH_#Y<BG2Ff2!AQMwE7c
zgbg8GKW8JE(1wvW$(uNSnOB{;ARK4Os-ny438%q9@p!lgNY|+F{fITV94##N)0np}
z_gj7U@O<O%TZbqJS6ah-Hjalz9#dO^q=WD#=qXyTy%wTj<1#ek6W~5+deJuc8pna)
zKDrMHK_)EzMhs81AEdnon;WZoKh}4x7@2Dxh(1)fx`K?_TuDp+vu_1bC&Q^d57yvk
zw%e{fgxh`wx&8_bZ$GIq*@4QEWfMAq&k>}L$Z<2L$eU-j<9meIPn)WXAL~bDM`jzx
z!KA=nlS_5|Gbt;P#QmH&)&712ID4rCR`cthTMR!-CZ9EoA<;J5*Bs_J8`y_qA6bD|
z%5loS=w<}~uAbpyQ;DgB!TQ9FYr?PfWK3-_t8)3K+N+5Al2np|xk^R=d6pA}95t)~
zJw@lugug@SQXg@-o#`UA#kxh9HSv8odG|iF*}_<_g`|~{GBa|{d>WhadVq{A@x)aa
zPgbUEe>35HV!5P&8CD`~9K{@%{yzJoO%Y9s3g1%+rD8~#TiPp*5))69UK8oqL-Ic1
zDe>exMwo}qdWTtTl)rprs$$R(Q~Fe#(?&CO17-2th;|b0dTAUf5iWFGi#+6-L`%i5
z?U4-8)38r6AcX#D<0KxGA!xr50l?lLi^m9FKXdjIg~c1iO%y+T>nqn|j=>#<3>wK%
zC(k@%+KD-ubh09T6+oK-eL*yd^kwz9W8^m%uq?uOBmGOSNQ4tl|BN4_S0J8S+uJ<J
z87|vZgBMJ%35ZX}g%F0za6f1D9=qrp94E#vBy{|c)~_ab#Hp~9=<T|19(nR30Abl1
zD6g;2FTzNbcwD<bnP=id)vDQED|gBE)xc#T*IwLkX*L&vAL}uqMQ_Lvz#4qL)uPOH
zQ>!58ZDCAG>wgdSi2dIdF-%6_PBmAmI)cdcm>s~L(8pdrEkg~9V5V`!o?!;6^#q12
zm}3o^?t8@iZ@vA@-*DLs3s3e=5|3++`G(*-;QV`4)m|ab+c>;o^hk%>M}He6=(zc&
zX&WXVrNkN=_)Oba(66dKRFIjrc>K(uk1~2Jm^JgEvO9wKzinGGy8>19jjWZZVa<lI
zUp#noOo{P<?6?PWpAUDX)y&^J0bs3vS|No`V)C_2t-hxLpTv}v^T&kpqJeAJlAfGj
zp-r^^OVpZ@hl<{T6Nq6E{SOyK&kSEw3-)K3SQWmEYUj426eXKZj<C;`>_W<(r1|-U
zu-DtdeC@ET_o#47giPn`cTv?rBduHU;OQ}dMtbxP+T$X#twT=VWYbpae5+x^q(>-t
zY8}9C8=Rva?&Nq1(58O|!BZPdo|c&veS@t&HB7L-U@@n;y!J*Y58k8qz5!wCPC!>W
zi~eWvzz)DcW(PoisMxk9kd>GOI77e0*t};zbk*$0_Mx8XAiJp>_~^dgx4o&ftlZ>w
zwk_)TpOJ;9C8|gnGwrfpEL*|07B1yB-w>;6X=jND3XXR%9{RI&HcrPTlvu=1i)I4y
zZtEr<M7tO$4q{1Zup_J?kW-i-yK5a|t8_rjk4476-efdQfj4huBwNLSg?YcF7$YYl
z!;Q$*7JkW@$g7m~JJm1pU1~xZm~{fPc0JRpko-^}k%%Lu*W~-aVg9-?5g{)PxXV0Q
zF)x&robbs4I!k6p(z%{I5Dmv&@_b0jc(9gH-W}nsk$VeEO01lUV(FCydWfl_9sRzq
z$D2;*g!}24#U}|QfaA)j)NHIB<(_SoR&x$oY&&H~DVAQdfz=inXa*oc<{49`n0QK1
z6Hqy6R|-)2Sqw4##AgZFaB-pkgVe&k9-d~}m0sY@NjWlZIouq$3Q<u``jwETG%y74
zxVJtpN{uE+0dHhKBX@bULw=|)cY;2=c;p4XZ?9|KN~AAFXn2^eaUJE&;4{wgz4$&b
z%I`GMr7yoL!&l1DFfTLSgB7;FMK=Shy8+Qo#kqO{H8<?f1ca&G>+IRcc=+|=EBciY
zjstU+uJxL$5X+sCzgp8=28!NFFlI##^-P!1)-wci&W$w`3T36X{<Z*ypp?0!+GqN3
z!`24#!PnI42OzAF<Tv+EHU}=p!!u`#`$<Yf3C_=O{hF>!fnU#%ve`5ZzbN*(Bsx%o
z1eXsbJsz=(n(74>`G;TAU)9^rr1i{4A6iLsYV74kROFIc{K$O+w>y9WuxqpWMeI^p
zZ}hTXeaK$Rt33`o0tuZWQ{J0yGG_u6V#{MUf7Ad70W+5=DP{pi65HX;-SchQxuyKX
z0=q<hsP{OMJ~)5t058q4F_#;8t7zLYPj(qR$Bn0ngln|NUf?}G-cT5sm24&W_$`Zf
z-S$K+cdM01d|c#E06pirq6-9;C&&BjT*6Q_JvDP~cG0+**0=Uh-?a5DF-!40*%d)G
z<|b1H%odC=w&VKh)I(FwW8dQhpS7-@pIsNiTv|HsFYFT08UaWdY4U!_Z1<!)GAzt(
zr>W(*0+O=fQ;G;%%u&nUPYr0E1XO>Mui1zo`6W0f)<e=e!2Y)lyGp$!t??uFhhT5N
z>l%~#%Xi!LTtDH0Zfa8QIT?=_Ar6Af&mBAU?UhDVsJ>H`cV%g6kCUQtH`Y`cx=o56
zFg~swY-cpoi`|sYwUG1OHgUI?=t_j&OliuFIr|iLfibt+BNxe;Qg5!R@tPdh3AS?@
z`r{~`&c6_w?I^L^hkqqvVYX??gUOeWhzieMWF=Kgoe!49Z8@(MHLsS`H65BhcEc%8
z8p(Qwb7aMnvH|<!t<mEvBOM7tyT|4GH7Y%%w9aG7S%S4a<;I={h{IuK8C<z_n!wl-
z!P$UV^{S#Pds<=-sohp_8tOGuN*7<KqwbTs#IEB)Ha-#>TBK`e?!<QZ3dA1z<rAw<
zl}LRd?W}5Lvs<z|uX4lqzMecu1XiK;(nQjG9lr67)Vo&A2C@3z{*m+J$ekSD)-x@E
zlx>MU7khJ3lREvwczFd){c%82+|xIUihiW+JVy<w9waR%$|p~OLB{Ttx<W{o5$0W#
zDXj&^J==v{Wt>+NZNi*2JudK^5Z+!yt;F5w+<fw@Ja?`*pa?LF4CM4(VnrCy-CIL*
zYv2Bn8a*v4kV3dCS!`Z~3tiTH@vxA8XfG0EMZX?kN}#6$s#da_vY*Ljv3kqGpM}e!
zmTI>LWTz%5(hZVJHN>+cyRyC`h?H5=q%6}c;jWDIZfe_+sn(Aji^<->vL}SIlbiUS
zjEvfca(i3fvgJWWPf*@QnbCg14pyI|qRBPt+sP5bzFCntkks1pL})D8Si#%ymLy1?
zrMwX~w`!FDx+9H<KhJ&MOb3}+Eie3DF~wHd+912s5Oir|YgQ=&;KX^8Sf*P-`MgZ>
zj$jwDnuEia%a&qEOS50NhL~3@(=8UlmfG7)9K2T`?hic%L+A~Ud||)op;A(n*U7@(
z8=qg(O8O&2PxS{JOFzC)IP#~>$iZa=G8E%6m`b16=+h0ic&dgH7)v<@^G~(vtWyNf
zJn<M4E^aM2=U@$T@hXEAbWxbpW}Q0~rjw_t<BP6S)&zw29kxk#T1XHPv{lN=KoBAG
z_(@0RJ$}qdSbDAZ`K4Ra?h-Jv!87UY{!-q_=W-2um!uartwJ15GT$30>tEX)oM<&w
z=QZt??Dr)h<5gYySo-A!6m9HT2JVb>JgGncTc_mbQn37iR`k0z=cH@v-3GWmwgRD;
z`(6)WH*N*CE58kEe5b6uS#HVr;#QYe^|`Vc90Vcu!;t|VW~R6m(c5!b**AIWNmHQ%
zWx!n`2Y^QM^WmY!)T-SzIMHt&>=#)Tb!=!jd2#UBq&7gtrR7k}2;-rcqr_?D^?^F-
zwZ(k_9e-4wyivC?*#*U`sM`KGOpnzf%Jg+ayN&3LiK_b6x}R*(a|hIvs{zcH9x<dM
zM-?f?eg8b8hBn_0CA;CLEid2Wn^8cTRe%4-)`>EbMDIvP)_T+KCF4InxcG`Xbqz3c
zf;Ny-DMtx&#%mdEI-0e%E`hy2R1)5<Ypp`d{z>!zrfTLOYXFXW`C_zdCDH%i0&Pz#
zP^zv#PDTIy{|#^tZaBJZ+?|j*(dOCfVmC}_*^%vpLVG!EVWxY;kxELqb$lc1yz?@X
z2_N}gUVVy05qpBJlVd4o2rG37(u~EY4)G$<!7?oE{G}-YTL7?8R<LcXrHeKLlH$*9
zw~@UQ$5nm)xIb*(?StaQ#Nm!=Sy(wJxxl;H==~LX(@$nIn<%*49Yb4+AnK>hF)v_J
z%X%;lS1=BQ$X&n-PPAR<&9EDySMSJnVWY0?W<K+XCzT6z@Zg&in>~(@mESp%3J)zb
zKCsm}vv(@o4s}9FvT+st_~~I=qHknyt?|jP17~{+svt?4?|7fQ&@=-`S!D#ezO9V@
zosS*d_~~uUuIJK}-?}{?bO{*v@;2d>dSRt1#A;()9div+=QSHc<vmfZ*|X!qmBSNl
zj&w9w1ut`0d?=RAeY%dVtbW*aSa%V3G&?(_DZg<e4fgpDK%>0cKTiVaNaXeQq=v2Z
z*wc)YMB%T&yNoY>{rao7z`qg<<<7dz{ZKXV1vE({>m}}Rys6dsdz-KZulYN~pKjlI
zIkA6$4_d!f@dXor?%D#-B45&X+sf-dSOqw6Whyr=yQjZ?eJ%ZRpWna_kHnO8`=#IB
zz9{zKAdF}cY-LS9pwg@8iYR~b{{7EPm878=<ZIQG-`&HdOFwv7D6-(jN0Cf9rkneO
zGSwu$d}ojD1xJm;YyqbilC3OR&BZxu>7oZx&^~7{X|KqA*<WI1q?389J_;WsveX*(
z(01Sdl+rGgJuGVHKMJJYfGy07dmBTl>XG8b%LtOTZ@w?n>Ga%;bV1^RQK6(mjZ)EU
z|1cXm(g1zC?N<FL6Mcd417dndcdy5mR2}fvtKE0s*vGIaly+me8}Jhm1jH2eqr>#p
zjGKz-ol*y}8olFsG}B8UmS2&aJ=~Lr)|YHVu_P!8!^Tm{o*U0DDjW<sQ>iDaH+)`N
zyg4IVa*6oH(1BlH2nkXUo)cqa?wNUcNg>!j*{#?2*GGdrS*lLDbK6^Qe)5AV1bNbB
zZI$$6bzx8Nw3z=<&2`uknsS5g@L8}GpCY;VSkmzKF0fVR%OtAAk-q91@Zwbj4PJ@g
zlj(GeX-V?Q6c!vBY>o{47AZaU2$H)i3}<X@PW$7N9IW@4CwYSq1W%)yQAcSEtDJPb
zT4m@uXm!IPiVGRFz@+X>>+^c$7E*K-{ClU9?n8fQp#Hil_3{k)%|FF@GQ;1-k!r4t
zgy@~&nciU{N1cA^bg}OoQ$CfTPI(mdYepUrR1l=i)Ebw`cJ{coiSb=M-x{<2U`f+@
z4a^^m^ybEi?!5ucxzb~i(6(Kcl;@YzTqfSM%FrH_C;duUJzkvtxQ4H3wrk2yv*c%#
z-?C`Ov1$bIkBRI*%WU!QQKVMDWs@7*f{V;9P4(LR84qY)xaE0sC4vk+`YU2a)Of|*
zSP&?kd-Hdz^a=ziOcSS^CSdGmBpIT2u#-nleBFLH@AIU1c9&@90ylza%eB}4pij(x
zdnc2;P2g+T^JA87lno<UBK!v9wN?lcWJKq)-KC!#wJ0$D<kPc2<sE;*(``D1z<~T;
z1B$lwf9RrfR6s;v1@}1CJE9^NZQ7;8vwv&YFQaAb_$%^bTIL-M6><72(yF4H%`mbD
zjA%q##kPKut}$0_LX0=T8g0gHd0?)S+Hxwl#!`8<-r5jE&XTz(b_8RVKmYi+qAOoW
zCXZ30Gk@y^`BVP=gUKMUi@w-~C763Iys=&>EfB&NTBdx_rb|lq{h~(a(rN^8jTz|^
zq932D=_E|fWUJj34tjDZw@g3RdBVkG7LbhU720X~<UV#`=?`A4(I)au1MeqS0(6I}
ze@3;jjS%G7QB1O*DUGSs9=uTR`pJ;gawxZCGU5H0sMgYYF#qsvp9(z|bB5@06LUP_
z{NWm{3*Q58P6J@?vojP@p{dot){r7XOjp=|<e86u@)ndqC-!Zh!SmyU0-1Ltnf#;0
z@;h@ENXfhiB1j)@GrMXGNNS&Hw{7ohIZu$LcOi%a8K>*JE`e6Vji3Ei#`Q(~y&G*_
z5kb`KC`r0}wY`V1c1x=L`wM;v;;+`sV-SQG>(OVo&Ko}k1qk0r#TiM>dCZz4$l8Z0
zeIAuoe@<ZS7D0jc&V2TwU#}maFzurx7H-jx1}LP;eVIuso71iu{S55$*F})cinev_
z;YpPM95-B1A#%O&8p%@%QZEin8C(7aNRIp?=E<AWcYoIsMi3wKFmIEJ-mK%qP2q=5
zU&ZGH0$jAi1Duxc9#@`1*dENTsGgjengw`oHA_l@u9*5w{a}A;S@#0Qf8Ku?irb!4
zt1tMtWDeeJy5@(DdnS9zAV_LjPQj~=*gQijE3ja7P{j_7g=#H`KE=Y?+d3e_!-Y64
zDWD8sy~tHT=B1IBeV>O{kCQ5bR-uEMikxI^z+^&R1h&Hy$wKke$}W&o3vw)Tase`6
z(e*Tncm@x#wQXnOb^JClYy-EAPTOHeEclUqrj#eTgKAFiLW(Mcxl0BcdrDvnhfIzw
z$Q$SL+rs!`C<ypmP^u2odE~7R#f}?4EWC1rJ#ek_9D>BqzqHx@an=_c|0=!GABD2b
zC*#znt+lLa!9^oVh%j#O8ZcHPpXlXn_CF5k3yr_D;w1qLZV4<k$!Q_@pcwpIYt?d7
zfK=r`b5BVbf-utj@Ik?6=33t^*IbdRL<i$@Hkf!5R}#6jc-bWAl0Ik6rFI9W5>>Aa
zz^E%>8bkO^`^MMq5>=o&7QNL62qWaNG38O1wt;@IM5QR0P?nRdags;^u)~V$BiGOX
z9iV6HRc056Fx1fCIBaE}mg=E?TkW;k5^4*}i=9#L{mygi2q=NE(}yq*O<Htz1xthu
zN}}L@K}_;-e4K48Ffam-AyO7h&(!-Gx&2>b2bssDTn5AcHI|Os7L{|w;9p}WF>zHb
z>f&Gw_3ZUd$*(;{$^76M+LRj~jWD7+4&9Ln>qhHkVc{}vs;UGOZCBB$<V%_cp1i36
z*xvF-U`+<qJV%KMBVhQ0C5#6<dr%Q(+D`oIDsK=$fk}~@@vsczgkV%wvf3#i065@7
z1p7H5&>@TCvuIJOR7W*bv=qL6C=3HW@}GC%jwFI4nqZ<$3h_9skdq)>1crLz$^7_y
zdn;gkK$8qfM!!nac2ON)>_*XF5$$-KY}E8{<|-Y5y?{^*6;O&5VvIq}72)5m6r40K
z1jX${)J~{sol<)h)Oj<CR#@iE+%E+zoBMiTR}QkxoM|j&4qu^0h@FMWxG6+y%i|t2
z^bO`N<JwTC%{H9+iduw?Z-eS@CjIj@eq1J4VvZlkbRg#&>2LII%Y=2van|zM1-M<p
zfI9x}NF?fjrD}UkJD*qojwX(3js>r`XRrijO)p1vCB3>WUM4K?Ij3g%!MHus3e=Q%
zcaAFTS=27B_Uczi;;23__4NkaWQ<uKM^&Bvr|q6hm;rt7QvBbZH{1p-`rqHp>0>~{
z5~f1my(Fv8hag9`CDA6ib=XA9F%~@shWs@83fsd(BVp$HWfgsX5KvC4|H!R_BdUx^
z(;GnG2VKzCoM^<$T(`VkA4a7kDz@M6aO*T$_|B*@@4@sYM3=M$xc6dQ*fP*hAV|NQ
zEgevx|3|<8RzgNZqXJxLr>WH{1i{5bGS>u4d`;WAU`*HnV|xP5GEbBNhP$=s$6>}@
zB>PdG$b@+@*T4?*8nC$Cwh@45<1DOa-mqaT*k=t(eK~5%Im{=|v_6=-F&5U>xv)Zi
z=psut1Q^VpmEulG1J3$6OvO!e8UX)=M+*(Y(X%*<uo+>d8#wJqcMAwdi&(czByqz~
zxkIwaWVP3}cz8f$nt?zzJV^sRqZf1IKLWejn+o|j0)GQnk;d-_=;f32U4J91W{1h1
z7GWGwZT~GzkA=YTF{vF;?PA=6o2IbugE*5l`~aH!zZHnE!}bP^bmTup#^KyNq1{9N
zRbY^9{6w)rl4P3&Bf>fak=btBDh`<-E7{XYM!^Z+(~B1YHCGB6_b>rEiHx#j8w&*F
zZ2u9U)2kPs{!cap6~qFof;14Mqd3=Pof#?s4xB{xM*Bfo7`&(g%7J)X6g)2>Gb*+n
zR$xkzGYBDprm!`K@~LwWr-PE|V~ckoVbO8pkbF|7J)|}Y>RP4;pli@_9q1q5WNo{W
zp%3l{gzhqKx?rFQu>$%Ff+!N-j-q1{I^e3^g0z9L4M3j}MAS5F#wu8X2VDZHh2ZW3
zRKDZ0@0`)6D;pOM`~;4P-JCws^#lM~{^`$pboj{;cv2BW1GrcP&=215A#{v0Ja_HI
z3RwV{A)+RY72@Z7kjDze$FD|*8HB~>m7i<M86=wb5i8Q}1fPomcX@&(RFpTO<1eDQ
zmT~nA>UOUpwfi}z#+Jm2gWDlUkCSA=0Mr6Z12+986pyrvn_CCyDtO_A0I2Dp`gOo2
z3%mlbK!bs|={YI{be8Atqe2rPv=tSy1cqWjxCWsO;9CkRbOMAz<v<APa#aL%pw5_B
zv3DCP1n{hz&?&IX9fWS9LOCELhzeOkl=pHhp+aNoaq!rP90F$8$?Kef6@ipHcP^PT
z>efR=($J~kF=WwBbc#^h4L)uK%MO<y0xyqqa^Zy>wfiXnAo!sib@=&(4d>@=3e;`@
z2ZzBM2AIoC&d7#bf_TP6a@yz_WZobe@2fjN>A4F>sUM=T0XKXNjlC_v6_(chl?4=b
zrKUm@4H{uXag7|i;Fahgyl;VOVb(FOo?7J0$NQ{<B`n?caoVgO26CoAH9E%tE~1zA
z6YO7e(9e|AcT}O%LbwdITbT#$@Pqd&xOEagQ6&IG5m5sq!C67h1dTYY_IljfFM&=(
zYA`6=i(qm50}!^yC*?Rk3BYu3{)7`WwHTQ&=4~$&cfQOaSfV#(kW;!7pVwnkwZFoU
zwqmH$KOwQ#eMf<Z5jDUZHba{Q=o-Sdb3R1Lgz+8Vfa>mpzJyNh2qY5`oxU8721~qu
z&q;h4Q=(BE>N_;wYBbjXFI5N-*b(HBB2^Y$FO~h`*165Gm>?6j7BzEOltDxj&A}~L
z;uso9;L<VTBpkH1DcbF_V8-5!8aV|<jN$pM>?^kp;Ln49K-en*kBA7rC}S;}(hj!4
z62YIfVfg?c*D+$?$ptX7?l%~Lnfa(WYGf-_*77bGxzDZhEoDdkLy%5{xez~d#RDv&
zGy+Hvf_jFmKnq1U3n_#fEe~0ZrU<eYh5SWi&}|1~U(kOP{u8DDq{e^x!+%DN{|uG?
inIHbYC&jL1F2w@}XUm)_;b{v&%nn)}c)Q;r_`d)jjOKp;

literal 0
HcmV?d00001

diff --git a/tests/test_datasets/test_dataset.py b/tests/test_datasets/test_dataset.py
index b97cbae3a4..db4a779906 100644
--- a/tests/test_datasets/test_dataset.py
+++ b/tests/test_datasets/test_dataset.py
@@ -7,7 +7,8 @@
 
 from mmseg.datasets import (ADE20KDataset, BaseSegDataset, CityscapesDataset,
                             COCOStuffDataset, DecathlonDataset, ISPRSDataset,
-                            LIPDataset, LoveDADataset, PascalVOCDataset,
+                            LIPDataset, LoveDADataset, MapillaryDataset_v1,
+                            MapillaryDataset_v2, PascalVOCDataset,
                             PotsdamDataset, REFUGEDataset, SynapseDataset,
                             iSAIDDataset)
 from mmseg.registry import DATASETS
@@ -27,6 +28,10 @@ def test_classes():
     assert list(PotsdamDataset.METAINFO['classes']) == get_classes('potsdam')
     assert list(ISPRSDataset.METAINFO['classes']) == get_classes('vaihingen')
     assert list(iSAIDDataset.METAINFO['classes']) == get_classes('isaid')
+    assert list(
+        MapillaryDataset_v1.METAINFO['classes']) == get_classes('mapillary_v1')
+    assert list(
+        MapillaryDataset_v2.METAINFO['classes']) == get_classes('mapillary_v2')
 
     with pytest.raises(ValueError):
         get_classes('unsupported')
@@ -80,6 +85,10 @@ def test_palette():
     assert PotsdamDataset.METAINFO['palette'] == get_palette('potsdam')
     assert COCOStuffDataset.METAINFO['palette'] == get_palette('cocostuff')
     assert iSAIDDataset.METAINFO['palette'] == get_palette('isaid')
+    assert list(
+        MapillaryDataset_v1.METAINFO['palette']) == get_palette('mapillary_v1')
+    assert list(
+        MapillaryDataset_v2.METAINFO['palette']) == get_palette('mapillary_v2')
 
     with pytest.raises(ValueError):
         get_palette('unsupported')
@@ -304,6 +313,19 @@ def test_lip():
     assert len(test_dataset) == 1
 
 
+def test_mapillary():
+    test_dataset = MapillaryDataset_v1(
+        pipeline=[],
+        data_prefix=dict(
+            img_path=osp.join(
+                osp.dirname(__file__),
+                '../data/pseudo_mapillary_dataset/images'),
+            seg_map_path=osp.join(
+                osp.dirname(__file__),
+                '../data/pseudo_mapillary_dataset/v1.2')))
+    assert len(test_dataset) == 1
+
+
 @pytest.mark.parametrize('dataset, classes', [
     ('ADE20KDataset', ('wall', 'building')),
     ('CityscapesDataset', ('road', 'sidewalk')),

From dd47cef8017b87c0257032ac79c4d4a3212582e8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E8=B0=A2=E6=98=95=E8=BE=B0?= <xiexinch@outlook.com>
Date: Wed, 15 Mar 2023 14:55:30 +0800
Subject: [PATCH 14/32] [Feature] Support PIDNet (#2609)

## Motivation

Support SOTA real-time semantic segmentation method in [Paper with
code](https://paperswithcode.com/task/real-time-semantic-segmentation)

Paper: https://arxiv.org/pdf/2206.02066.pdf
Official repo: https://github.com/XuJiacong/PIDNet

## Current results

**Cityscapes**

|Model|Ref mIoU|mIoU (ours)|
|---|---|---|
|PIDNet-S|78.8|78.74|
|PIDNet-M|79.9|80.22|
|PIDNet-L|80.9|80.89|

## TODO

- [x] Support inference with official weights
- [x] Support training on Cityscapes
- [x] Update docstring
- [x] Add unit test
---
 README.md                                     |   1 +
 README_zh-CN.md                               |   1 +
 configs/pidnet/README.md                      |  50 ++
 ...pidnet-l_2xb6-120k_1024x1024-cityscapes.py |  10 +
 ...pidnet-m_2xb6-120k_1024x1024-cityscapes.py |   5 +
 ...pidnet-s_2xb6-120k_1024x1024-cityscapes.py | 113 ++++
 configs/pidnet/pidnet.yml                     |  81 +++
 mmseg/models/backbones/__init__.py            |   3 +-
 mmseg/models/backbones/pidnet.py              | 522 ++++++++++++++++++
 mmseg/models/decode_heads/__init__.py         |   4 +-
 mmseg/models/decode_heads/pid_head.py         | 183 ++++++
 mmseg/models/losses/__init__.py               |   4 +-
 mmseg/models/losses/boundary_loss.py          |  62 +++
 .../models/losses/ohem_cross_entropy_loss.py  |  94 ++++
 mmseg/models/utils/__init__.py                |   4 +-
 mmseg/models/utils/basic_block.py             | 143 +++++
 mmseg/models/utils/ppm.py                     | 193 +++++++
 model-index.yml                               |   1 +
 .../test_models/test_backbones/test_pidnet.py |  87 +++
 .../test_heads/test_pidnet_head.py            |  89 +++
 20 files changed, 1646 insertions(+), 4 deletions(-)
 create mode 100644 configs/pidnet/README.md
 create mode 100644 configs/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes.py
 create mode 100644 configs/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes.py
 create mode 100644 configs/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes.py
 create mode 100644 configs/pidnet/pidnet.yml
 create mode 100644 mmseg/models/backbones/pidnet.py
 create mode 100644 mmseg/models/decode_heads/pid_head.py
 create mode 100644 mmseg/models/losses/boundary_loss.py
 create mode 100644 mmseg/models/losses/ohem_cross_entropy_loss.py
 create mode 100644 mmseg/models/utils/basic_block.py
 create mode 100644 mmseg/models/utils/ppm.py
 create mode 100644 tests/test_models/test_backbones/test_pidnet.py
 create mode 100644 tests/test_models/test_heads/test_pidnet_head.py

diff --git a/README.md b/README.md
index 52eda092c8..69f751b9e5 100644
--- a/README.md
+++ b/README.md
@@ -159,6 +159,7 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
 - [x] [K-Net (NeurIPS'2021)](configs/knet)
 - [x] [MaskFormer (NeurIPS'2021)](configs/maskformer)
 - [x] [Mask2Former (CVPR'2022)](configs/mask2former)
+- [x] [PIDNet (ArXiv'2022)](configs/pidnet)
 
 </details>
 
diff --git a/README_zh-CN.md b/README_zh-CN.md
index 167ecbdc40..709e6ef195 100644
--- a/README_zh-CN.md
+++ b/README_zh-CN.md
@@ -140,6 +140,7 @@ MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 O
 - [x] [K-Net (NeurIPS'2021)](configs/knet)
 - [x] [MaskFormer (NeurIPS'2021)](configs/maskformer)
 - [x] [Mask2Former (CVPR'2022)](configs/mask2former)
+- [x] [PIDNet (ArXiv'2022)](configs/pidnet)
 
 </details>
 
diff --git a/configs/pidnet/README.md b/configs/pidnet/README.md
new file mode 100644
index 0000000000..545b76e8b0
--- /dev/null
+++ b/configs/pidnet/README.md
@@ -0,0 +1,50 @@
+# PIDNet
+
+> [PIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller](https://arxiv.org/pdf/2206.02066.pdf)
+
+## Introduction
+
+<!-- [ALGORITHM] -->
+
+<a href="https://github.com/XuJiacong/PIDNet">Official Repo</a>
+
+<a href="https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/pidnet.py">Code Snippet</a>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Two-branch network architecture has shown its efficiency and effectiveness for real-time semantic segmentation tasks. However, direct fusion of low-level details and high-level semantics will lead to a phenomenon that the detailed features are easily overwhelmed by surrounding contextual information, namely overshoot in this paper, which limits the improvement of the accuracy of existed two-branch models. In this paper, we bridge a connection between Convolutional Neural Network (CNN) and Proportional-IntegralDerivative (PID) controller and reveal that the two-branch network is nothing but a Proportional-Integral (PI) controller, which inherently suffers from the similar overshoot issue. To alleviate this issue, we propose a novel threebranch network architecture: PIDNet, which possesses three branches to parse the detailed, context and boundary information (derivative of semantics), respectively, and employs boundary attention to guide the fusion of detailed and context branches in final stage. The family of PIDNets achieve the best trade-off between inference speed and accuracy and their test accuracy surpasses all the existed models with similar inference speed on Cityscapes, CamVid and COCO-Stuff datasets. Especially, PIDNet-S achieves 78.6% mIOU with inference speed of 93.2 FPS on Cityscapes test set and 80.1% mIOU with speed of 153.7 FPS on CamVid test set.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://raw.githubusercontent.com/XuJiacong/PIDNet/main/figs/pidnet.jpg" width="800"/>
+</div>
+
+## Results and models
+
+### Cityscapes
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------- | -------- | -------------- | ----- | ------------- | ----------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PIDNet | PIDNet-S | 1024x1024 | 120000  | 3.38     | 80.82          | 78.74 | 80.87         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700-bb8e3bcc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700.json) |
+| PIDNet | PIDNet-M | 1024x1024 | 120000  | 5.14     | 71.98          | 80.22 | 82.05         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452-f9bcdbf3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452.json) |
+| PIDNet | PIDNet-L | 1024x1024 | 120000  | 5.83     | 60.06          | 80.89 | 82.37         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514-0783ca6b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514.json) |
+
+## Notes
+
+The pretrained weights in config files are converted from [the official repo](https://github.com/XuJiacong/PIDNet#models).
+
+## Citation
+
+```bibtex
+@misc{xu2022pidnet,
+      title={PIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller},
+      author={Jiacong Xu and Zixiang Xiong and Shankar P. Bhattacharyya},
+      year={2022},
+      eprint={2206.02066},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+```
diff --git a/configs/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes.py b/configs/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes.py
new file mode 100644
index 0000000000..1955c91e05
--- /dev/null
+++ b/configs/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes.py
@@ -0,0 +1,10 @@
+_base_ = './pidnet-s_2xb6-120k_1024x1024-cityscapes.py'
+checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/pidnet/pidnet-l_imagenet1k_20230306-67889109.pth'  # noqa
+model = dict(
+    backbone=dict(
+        channels=64,
+        ppm_channels=112,
+        num_stem_blocks=3,
+        num_branch_blocks=4,
+        init_cfg=dict(checkpoint=checkpoint_file)),
+    decode_head=dict(in_channels=256, channels=256))
diff --git a/configs/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes.py b/configs/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes.py
new file mode 100644
index 0000000000..38a69c1c45
--- /dev/null
+++ b/configs/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes.py
@@ -0,0 +1,5 @@
+_base_ = './pidnet-s_2xb6-120k_1024x1024-cityscapes.py'
+checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/pidnet/pidnet-m_imagenet1k_20230306-39893c52.pth'  # noqa
+model = dict(
+    backbone=dict(channels=64, init_cfg=dict(checkpoint=checkpoint_file)),
+    decode_head=dict(in_channels=256))
diff --git a/configs/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes.py b/configs/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes.py
new file mode 100644
index 0000000000..f70ca4287a
--- /dev/null
+++ b/configs/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes.py
@@ -0,0 +1,113 @@
+_base_ = [
+    '../_base_/datasets/cityscapes_1024x1024.py',
+    '../_base_/default_runtime.py'
+]
+
+# The class_weight is borrowed from https://github.com/openseg-group/OCNet.pytorch/issues/14 # noqa
+# Licensed under the MIT License
+class_weight = [
+    0.8373, 0.918, 0.866, 1.0345, 1.0166, 0.9969, 0.9754, 1.0489, 0.8786,
+    1.0023, 0.9539, 0.9843, 1.1116, 0.9037, 1.0865, 1.0955, 1.0865, 1.1529,
+    1.0507
+]
+checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/pidnet/pidnet-s_imagenet1k_20230306-715e6273.pth'  # noqa
+crop_size = (1024, 1024)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255,
+    size=crop_size)
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    backbone=dict(
+        type='PIDNet',
+        in_channels=3,
+        channels=32,
+        ppm_channels=96,
+        num_stem_blocks=2,
+        num_branch_blocks=3,
+        align_corners=False,
+        norm_cfg=norm_cfg,
+        act_cfg=dict(type='ReLU', inplace=True),
+        init_cfg=dict(type='Pretrained', checkpoint=checkpoint_file)),
+    decode_head=dict(
+        type='PIDHead',
+        in_channels=128,
+        channels=128,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        act_cfg=dict(type='ReLU', inplace=True),
+        align_corners=True,
+        loss_decode=[
+            dict(
+                type='CrossEntropyLoss',
+                use_sigmoid=False,
+                class_weight=class_weight,
+                loss_weight=0.4),
+            dict(
+                type='OhemCrossEntropy',
+                thres=0.9,
+                min_kept=131072,
+                class_weight=class_weight,
+                loss_weight=1.0),
+            dict(type='BoundaryLoss', loss_weight=20.0),
+            dict(
+                type='OhemCrossEntropy',
+                thres=0.9,
+                min_kept=131072,
+                class_weight=class_weight,
+                loss_weight=1.0)
+        ]),
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=(2048, 1024),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='GenerateEdge', edge_width=4),
+    dict(type='PackSegInputs')
+]
+train_dataloader = dict(batch_size=6, dataset=dict(pipeline=train_pipeline))
+
+iters = 120000
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer, clip_grad=None)
+# learning policy
+param_scheduler = [
+    dict(
+        type='PolyLR',
+        eta_min=0,
+        power=0.9,
+        begin=0,
+        end=iters,
+        by_epoch=False)
+]
+# training schedule for 120k
+train_cfg = dict(
+    type='IterBasedTrainLoop', max_iters=iters, val_interval=iters // 10)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+default_hooks = dict(
+    timer=dict(type='IterTimerHook'),
+    logger=dict(type='LoggerHook', interval=50, log_metric_by_epoch=False),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    checkpoint=dict(
+        type='CheckpointHook', by_epoch=False, interval=iters // 10),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    visualization=dict(type='SegVisualizationHook'))
+
+randomness = dict(seed=304)
diff --git a/configs/pidnet/pidnet.yml b/configs/pidnet/pidnet.yml
new file mode 100644
index 0000000000..7fe818ca7c
--- /dev/null
+++ b/configs/pidnet/pidnet.yml
@@ -0,0 +1,81 @@
+Collections:
+- Name: PIDNet
+  Metadata:
+    Training Data:
+    - Cityscapes
+  Paper:
+    URL: https://arxiv.org/pdf/2206.02066.pdf
+    Title: 'PIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller'
+  README: configs/pidnet/README.md
+  Code:
+    URL: https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/pidnet.py
+    Version: dev-1.x
+  Converted From:
+    Code: https://github.com/XuJiacong/PIDNet
+Models:
+- Name: pidnet-s_2xb6-120k_1024x1024-cityscapes
+  In Collection: PIDNet
+  Metadata:
+    backbone: PIDNet-S
+    crop size: (1024,1024)
+    lr schd: 120000
+    inference time (ms/im):
+    - value: 12.37
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (1024,1024)
+    Training Memory (GB): 3.38
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.74
+      mIoU(ms+flip): 80.87
+  Config: configs/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700-bb8e3bcc.pth
+- Name: pidnet-m_2xb6-120k_1024x1024-cityscapes
+  In Collection: PIDNet
+  Metadata:
+    backbone: PIDNet-M
+    crop size: (1024,1024)
+    lr schd: 120000
+    inference time (ms/im):
+    - value: 13.89
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (1024,1024)
+    Training Memory (GB): 5.14
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.22
+      mIoU(ms+flip): 82.05
+  Config: configs/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452-f9bcdbf3.pth
+- Name: pidnet-l_2xb6-120k_1024x1024-cityscapes
+  In Collection: PIDNet
+  Metadata:
+    backbone: PIDNet-L
+    crop size: (1024,1024)
+    lr schd: 120000
+    inference time (ms/im):
+    - value: 16.65
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (1024,1024)
+    Training Memory (GB): 5.83
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.89
+      mIoU(ms+flip): 82.37
+  Config: configs/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514-0783ca6b.pth
diff --git a/mmseg/models/backbones/__init__.py b/mmseg/models/backbones/__init__.py
index bda42bb692..909b54f3ec 100644
--- a/mmseg/models/backbones/__init__.py
+++ b/mmseg/models/backbones/__init__.py
@@ -11,6 +11,7 @@
 from .mit import MixVisionTransformer
 from .mobilenet_v2 import MobileNetV2
 from .mobilenet_v3 import MobileNetV3
+from .pidnet import PIDNet
 from .resnest import ResNeSt
 from .resnet import ResNet, ResNetV1c, ResNetV1d
 from .resnext import ResNeXt
@@ -26,5 +27,5 @@
     'ResNeSt', 'MobileNetV2', 'UNet', 'CGNet', 'MobileNetV3',
     'VisionTransformer', 'SwinTransformer', 'MixVisionTransformer',
     'BiSeNetV1', 'BiSeNetV2', 'ICNet', 'TIMMBackbone', 'ERFNet', 'PCPVT',
-    'SVT', 'STDCNet', 'STDCContextPathNet', 'BEiT', 'MAE'
+    'SVT', 'STDCNet', 'STDCContextPathNet', 'BEiT', 'MAE', 'PIDNet'
 ]
diff --git a/mmseg/models/backbones/pidnet.py b/mmseg/models/backbones/pidnet.py
new file mode 100644
index 0000000000..0b711a3737
--- /dev/null
+++ b/mmseg/models/backbones/pidnet.py
@@ -0,0 +1,522 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from typing import Tuple, Union
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from mmcv.cnn import ConvModule
+from mmengine.model import BaseModule
+from mmengine.runner import CheckpointLoader
+from torch import Tensor
+
+from mmseg.registry import MODELS
+from mmseg.utils import OptConfigType
+from ..utils import DAPPM, PAPPM, BasicBlock, Bottleneck
+
+
+class PagFM(BaseModule):
+    """Pixel-attention-guided fusion module.
+
+    Args:
+        in_channels (int): The number of input channels.
+        channels (int): The number of channels.
+        after_relu (bool): Whether to use ReLU before attention.
+            Default: False.
+        with_channel (bool): Whether to use channel attention.
+            Default: False.
+        upsample_mode (str): The mode of upsample. Default: 'bilinear'.
+        norm_cfg (dict): Config dict for normalization layer.
+            Default: dict(type='BN').
+        act_cfg (dict): Config dict for activation layer.
+            Default: dict(typ='ReLU', inplace=True).
+        init_cfg (dict): Config dict for initialization. Default: None.
+    """
+
+    def __init__(self,
+                 in_channels: int,
+                 channels: int,
+                 after_relu: bool = False,
+                 with_channel: bool = False,
+                 upsample_mode: str = 'bilinear',
+                 norm_cfg: OptConfigType = dict(type='BN'),
+                 act_cfg: OptConfigType = dict(typ='ReLU', inplace=True),
+                 init_cfg: OptConfigType = None):
+        super().__init__(init_cfg)
+        self.after_relu = after_relu
+        self.with_channel = with_channel
+        self.upsample_mode = upsample_mode
+        self.f_i = ConvModule(
+            in_channels, channels, 1, norm_cfg=norm_cfg, act_cfg=None)
+        self.f_p = ConvModule(
+            in_channels, channels, 1, norm_cfg=norm_cfg, act_cfg=None)
+        if with_channel:
+            self.up = ConvModule(
+                channels, in_channels, 1, norm_cfg=norm_cfg, act_cfg=None)
+        if after_relu:
+            self.relu = MODELS.build(act_cfg)
+
+    def forward(self, x_p: Tensor, x_i: Tensor) -> Tensor:
+        """Forward function.
+
+        Args:
+            x_p (Tensor): The featrue map from P branch.
+            x_i (Tensor): The featrue map from I branch.
+
+        Returns:
+            Tensor: The feature map with pixel-attention-guided fusion.
+        """
+        if self.after_relu:
+            x_p = self.relu(x_p)
+            x_i = self.relu(x_i)
+
+        f_i = self.f_i(x_i)
+        f_i = F.interpolate(
+            f_i,
+            size=x_p.shape[2:],
+            mode=self.upsample_mode,
+            align_corners=False)
+
+        f_p = self.f_p(x_p)
+
+        if self.with_channel:
+            sigma = torch.sigmoid(self.up(f_p * f_i))
+        else:
+            sigma = torch.sigmoid(torch.sum(f_p * f_i, dim=1).unsqueeze(1))
+
+        x_i = F.interpolate(
+            x_i,
+            size=x_p.shape[2:],
+            mode=self.upsample_mode,
+            align_corners=False)
+
+        out = sigma * x_i + (1 - sigma) * x_p
+        return out
+
+
+class Bag(BaseModule):
+    """Boundary-attention-guided fusion module.
+
+    Args:
+        in_channels (int): The number of input channels.
+        out_channels (int): The number of output channels.
+        kernel_size (int): The kernel size of the convolution. Default: 3.
+        padding (int): The padding of the convolution. Default: 1.
+        norm_cfg (dict): Config dict for normalization layer.
+            Default: dict(type='BN').
+        act_cfg (dict): Config dict for activation layer.
+            Default: dict(type='ReLU', inplace=True).
+        conv_cfg (dict): Config dict for convolution layer.
+            Default: dict(order=('norm', 'act', 'conv')).
+        init_cfg (dict): Config dict for initialization. Default: None.
+    """
+
+    def __init__(self,
+                 in_channels: int,
+                 out_channels: int,
+                 kernel_size: int = 3,
+                 padding: int = 1,
+                 norm_cfg: OptConfigType = dict(type='BN'),
+                 act_cfg: OptConfigType = dict(type='ReLU', inplace=True),
+                 conv_cfg: OptConfigType = dict(order=('norm', 'act', 'conv')),
+                 init_cfg: OptConfigType = None):
+        super().__init__(init_cfg)
+
+        self.conv = ConvModule(
+            in_channels,
+            out_channels,
+            kernel_size,
+            padding=padding,
+            norm_cfg=norm_cfg,
+            act_cfg=act_cfg,
+            **conv_cfg)
+
+    def forward(self, x_p: Tensor, x_i: Tensor, x_d: Tensor) -> Tensor:
+        """Forward function.
+
+        Args:
+            x_p (Tensor): The featrue map from P branch.
+            x_i (Tensor): The featrue map from I branch.
+            x_d (Tensor): The featrue map from D branch.
+
+        Returns:
+            Tensor: The feature map with boundary-attention-guided fusion.
+        """
+        sigma = torch.sigmoid(x_d)
+        return self.conv(sigma * x_p + (1 - sigma) * x_i)
+
+
+class LightBag(BaseModule):
+    """Light Boundary-attention-guided fusion module.
+
+    Args:
+        in_channels (int): The number of input channels.
+        out_channels (int): The number of output channels.
+        norm_cfg (dict): Config dict for normalization layer.
+            Default: dict(type='BN').
+        act_cfg (dict): Config dict for activation layer. Default: None.
+        init_cfg (dict): Config dict for initialization. Default: None.
+    """
+
+    def __init__(self,
+                 in_channels: int,
+                 out_channels: int,
+                 norm_cfg: OptConfigType = dict(type='BN'),
+                 act_cfg: OptConfigType = None,
+                 init_cfg: OptConfigType = None):
+        super().__init__(init_cfg)
+        self.f_p = ConvModule(
+            in_channels,
+            out_channels,
+            kernel_size=1,
+            norm_cfg=norm_cfg,
+            act_cfg=act_cfg)
+        self.f_i = ConvModule(
+            in_channels,
+            out_channels,
+            kernel_size=1,
+            norm_cfg=norm_cfg,
+            act_cfg=act_cfg)
+
+    def forward(self, x_p: Tensor, x_i: Tensor, x_d: Tensor) -> Tensor:
+        """Forward function.
+        Args:
+            x_p (Tensor): The featrue map from P branch.
+            x_i (Tensor): The featrue map from I branch.
+            x_d (Tensor): The featrue map from D branch.
+
+        Returns:
+            Tensor: The feature map with light boundary-attention-guided
+                fusion.
+        """
+        sigma = torch.sigmoid(x_d)
+
+        f_p = self.f_p((1 - sigma) * x_i + x_p)
+        f_i = self.f_i(x_i + sigma * x_p)
+
+        return f_p + f_i
+
+
+@MODELS.register_module()
+class PIDNet(BaseModule):
+    """PIDNet backbone.
+
+    This backbone is the implementation of `PIDNet: A Real-time Semantic
+    Segmentation Network Inspired from PID Controller
+    <https://arxiv.org/abs/2206.02066>`_.
+    Modified from https://github.com/XuJiacong/PIDNet.
+
+    Licensed under the MIT License.
+
+    Args:
+        in_channels (int): The number of input channels. Default: 3.
+        channels (int): The number of channels in the stem layer. Default: 64.
+        ppm_channels (int): The number of channels in the PPM layer.
+            Default: 96.
+        num_stem_blocks (int): The number of blocks in the stem layer.
+            Default: 2.
+        num_branch_blocks (int): The number of blocks in the branch layer.
+            Default: 3.
+        align_corners (bool): The align_corners argument of F.interpolate.
+            Default: False.
+        norm_cfg (dict): Config dict for normalization layer.
+            Default: dict(type='BN').
+        act_cfg (dict): Config dict for activation layer.
+            Default: dict(type='ReLU', inplace=True).
+        init_cfg (dict): Config dict for initialization. Default: None.
+    """
+
+    def __init__(self,
+                 in_channels: int = 3,
+                 channels: int = 64,
+                 ppm_channels: int = 96,
+                 num_stem_blocks: int = 2,
+                 num_branch_blocks: int = 3,
+                 align_corners: bool = False,
+                 norm_cfg: OptConfigType = dict(type='BN'),
+                 act_cfg: OptConfigType = dict(type='ReLU', inplace=True),
+                 init_cfg: OptConfigType = None,
+                 **kwargs):
+        super().__init__(init_cfg)
+        self.norm_cfg = norm_cfg
+        self.act_cfg = act_cfg
+        self.align_corners = align_corners
+
+        # stem layer
+        self.stem = self._make_stem_layer(in_channels, channels,
+                                          num_stem_blocks)
+        self.relu = nn.ReLU()
+
+        # I Branch
+        self.i_branch_layers = nn.ModuleList()
+        for i in range(3):
+            self.i_branch_layers.append(
+                self._make_layer(
+                    block=BasicBlock if i < 2 else Bottleneck,
+                    in_channels=channels * 2**(i + 1),
+                    channels=channels * 8 if i > 0 else channels * 4,
+                    num_blocks=num_branch_blocks if i < 2 else 2,
+                    stride=2))
+
+        # P Branch
+        self.p_branch_layers = nn.ModuleList()
+        for i in range(3):
+            self.p_branch_layers.append(
+                self._make_layer(
+                    block=BasicBlock if i < 2 else Bottleneck,
+                    in_channels=channels * 2,
+                    channels=channels * 2,
+                    num_blocks=num_stem_blocks if i < 2 else 1))
+        self.compression_1 = ConvModule(
+            channels * 4,
+            channels * 2,
+            kernel_size=1,
+            bias=False,
+            norm_cfg=norm_cfg,
+            act_cfg=None)
+        self.compression_2 = ConvModule(
+            channels * 8,
+            channels * 2,
+            kernel_size=1,
+            bias=False,
+            norm_cfg=norm_cfg,
+            act_cfg=None)
+        self.pag_1 = PagFM(channels * 2, channels)
+        self.pag_2 = PagFM(channels * 2, channels)
+
+        # D Branch
+        if num_stem_blocks == 2:
+            self.d_branch_layers = nn.ModuleList([
+                self._make_single_layer(BasicBlock, channels * 2, channels),
+                self._make_layer(Bottleneck, channels, channels, 1)
+            ])
+            channel_expand = 1
+            spp_module = PAPPM
+            dfm_module = LightBag
+            act_cfg_dfm = None
+        else:
+            self.d_branch_layers = nn.ModuleList([
+                self._make_single_layer(BasicBlock, channels * 2,
+                                        channels * 2),
+                self._make_single_layer(BasicBlock, channels * 2, channels * 2)
+            ])
+            channel_expand = 2
+            spp_module = DAPPM
+            dfm_module = Bag
+            act_cfg_dfm = act_cfg
+
+        self.diff_1 = ConvModule(
+            channels * 4,
+            channels * channel_expand,
+            kernel_size=3,
+            padding=1,
+            bias=False,
+            norm_cfg=norm_cfg,
+            act_cfg=None)
+        self.diff_2 = ConvModule(
+            channels * 8,
+            channels * 2,
+            kernel_size=3,
+            padding=1,
+            bias=False,
+            norm_cfg=norm_cfg,
+            act_cfg=None)
+
+        self.spp = spp_module(
+            channels * 16, ppm_channels, channels * 4, num_scales=5)
+        self.dfm = dfm_module(
+            channels * 4, channels * 4, norm_cfg=norm_cfg, act_cfg=act_cfg_dfm)
+
+        self.d_branch_layers.append(
+            self._make_layer(Bottleneck, channels * 2, channels * 2, 1))
+
+    def _make_stem_layer(self, in_channels: int, channels: int,
+                         num_blocks: int) -> nn.Sequential:
+        """Make stem layer.
+
+        Args:
+            in_channels (int): Number of input channels.
+            channels (int): Number of output channels.
+            num_blocks (int): Number of blocks.
+
+        Returns:
+            nn.Sequential: The stem layer.
+        """
+
+        layers = [
+            ConvModule(
+                in_channels,
+                channels,
+                kernel_size=3,
+                stride=2,
+                padding=1,
+                norm_cfg=self.norm_cfg,
+                act_cfg=self.act_cfg),
+            ConvModule(
+                channels,
+                channels,
+                kernel_size=3,
+                stride=2,
+                padding=1,
+                norm_cfg=self.norm_cfg,
+                act_cfg=self.act_cfg)
+        ]
+
+        layers.append(
+            self._make_layer(BasicBlock, channels, channels, num_blocks))
+        layers.append(nn.ReLU())
+        layers.append(
+            self._make_layer(
+                BasicBlock, channels, channels * 2, num_blocks, stride=2))
+        layers.append(nn.ReLU())
+
+        return nn.Sequential(*layers)
+
+    def _make_layer(self,
+                    block: BasicBlock,
+                    in_channels: int,
+                    channels: int,
+                    num_blocks: int,
+                    stride: int = 1) -> nn.Sequential:
+        """Make layer for PIDNet backbone.
+        Args:
+            block (BasicBlock): Basic block.
+            in_channels (int): Number of input channels.
+            channels (int): Number of output channels.
+            num_blocks (int): Number of blocks.
+            stride (int): Stride of the first block. Default: 1.
+
+        Returns:
+            nn.Sequential: The Branch Layer.
+        """
+        downsample = None
+        if stride != 1 or in_channels != channels * block.expansion:
+            downsample = ConvModule(
+                in_channels,
+                channels * block.expansion,
+                kernel_size=1,
+                stride=stride,
+                norm_cfg=self.norm_cfg,
+                act_cfg=None)
+
+        layers = [block(in_channels, channels, stride, downsample)]
+        in_channels = channels * block.expansion
+        for i in range(1, num_blocks):
+            layers.append(
+                block(
+                    in_channels,
+                    channels,
+                    stride=1,
+                    act_cfg_out=None if i == num_blocks - 1 else self.act_cfg))
+        return nn.Sequential(*layers)
+
+    def _make_single_layer(self,
+                           block: Union[BasicBlock, Bottleneck],
+                           in_channels: int,
+                           channels: int,
+                           stride: int = 1) -> nn.Module:
+        """Make single layer for PIDNet backbone.
+        Args:
+            block (BasicBlock or Bottleneck): Basic block or Bottleneck.
+            in_channels (int): Number of input channels.
+            channels (int): Number of output channels.
+            stride (int): Stride of the first block. Default: 1.
+
+        Returns:
+            nn.Module
+        """
+
+        downsample = None
+        if stride != 1 or in_channels != channels * block.expansion:
+            downsample = ConvModule(
+                in_channels,
+                channels * block.expansion,
+                kernel_size=1,
+                stride=stride,
+                norm_cfg=self.norm_cfg,
+                act_cfg=None)
+        return block(
+            in_channels, channels, stride, downsample, act_cfg_out=None)
+
+    def init_weights(self):
+        """Initialize the weights in backbone.
+
+        Since the D branch is not initialized by the pre-trained model, we
+        initialize it with the same method as the ResNet.
+        """
+        for m in self.modules():
+            if isinstance(m, nn.Conv2d):
+                nn.init.kaiming_normal_(
+                    m.weight, mode='fan_out', nonlinearity='relu')
+            elif isinstance(m, nn.BatchNorm2d):
+                nn.init.constant_(m.weight, 1)
+                nn.init.constant_(m.bias, 0)
+        if self.init_cfg is not None:
+            assert 'checkpoint' in self.init_cfg, f'Only support ' \
+                                                  f'specify `Pretrained` in ' \
+                                                  f'`init_cfg` in ' \
+                                                  f'{self.__class__.__name__} '
+            ckpt = CheckpointLoader.load_checkpoint(
+                self.init_cfg['checkpoint'], map_location='cpu')
+            self.load_state_dict(ckpt, strict=False)
+
+    def forward(self, x: Tensor) -> Union[Tensor, Tuple[Tensor]]:
+        """Forward function.
+
+        Args:
+            x (Tensor): Input tensor with shape (B, C, H, W).
+
+        Returns:
+            Tensor or tuple[Tensor]: If self.training is True, return
+                tuple[Tensor], else return Tensor.
+        """
+        w_out = x.shape[-1] // 8
+        h_out = x.shape[-2] // 8
+
+        # stage 0-2
+        x = self.stem(x)
+
+        # stage 3
+        x_i = self.relu(self.i_branch_layers[0](x))
+        x_p = self.p_branch_layers[0](x)
+        x_d = self.d_branch_layers[0](x)
+
+        comp_i = self.compression_1(x_i)
+        x_p = self.pag_1(x_p, comp_i)
+        diff_i = self.diff_1(x_i)
+        x_d += F.interpolate(
+            diff_i,
+            size=[h_out, w_out],
+            mode='bilinear',
+            align_corners=self.align_corners)
+        if self.training:
+            temp_p = x_p.clone()
+
+        # stage 4
+        x_i = self.relu(self.i_branch_layers[1](x_i))
+        x_p = self.p_branch_layers[1](self.relu(x_p))
+        x_d = self.d_branch_layers[1](self.relu(x_d))
+
+        comp_i = self.compression_2(x_i)
+        x_p = self.pag_2(x_p, comp_i)
+        diff_i = self.diff_2(x_i)
+        x_d += F.interpolate(
+            diff_i,
+            size=[h_out, w_out],
+            mode='bilinear',
+            align_corners=self.align_corners)
+        if self.training:
+            temp_d = x_d.clone()
+
+        # stage 5
+        x_i = self.i_branch_layers[2](x_i)
+        x_p = self.p_branch_layers[2](self.relu(x_p))
+        x_d = self.d_branch_layers[2](self.relu(x_d))
+
+        x_i = self.spp(x_i)
+        x_i = F.interpolate(
+            x_i,
+            size=[h_out, w_out],
+            mode='bilinear',
+            align_corners=self.align_corners)
+        out = self.dfm(x_p, x_i, x_d)
+        return (temp_p, out, temp_d) if self.training else out
diff --git a/mmseg/models/decode_heads/__init__.py b/mmseg/models/decode_heads/__init__.py
index b18152d7d9..e6eeafc248 100644
--- a/mmseg/models/decode_heads/__init__.py
+++ b/mmseg/models/decode_heads/__init__.py
@@ -19,6 +19,7 @@
 from .maskformer_head import MaskFormerHead
 from .nl_head import NLHead
 from .ocr_head import OCRHead
+from .pid_head import PIDHead
 from .point_head import PointHead
 from .psa_head import PSAHead
 from .psp_head import PSPHead
@@ -38,5 +39,6 @@
     'PointHead', 'APCHead', 'DMHead', 'LRASPPHead', 'SETRUPHead',
     'SETRMLAHead', 'DPTHead', 'SETRMLAHead', 'SegmenterMaskTransformerHead',
     'SegformerHead', 'ISAHead', 'STDCHead', 'IterativeDecodeHead',
-    'KernelUpdateHead', 'KernelUpdator', 'MaskFormerHead', 'Mask2FormerHead'
+    'KernelUpdateHead', 'KernelUpdator', 'MaskFormerHead', 'Mask2FormerHead',
+    'PIDHead'
 ]
diff --git a/mmseg/models/decode_heads/pid_head.py b/mmseg/models/decode_heads/pid_head.py
new file mode 100644
index 0000000000..c092cb32d0
--- /dev/null
+++ b/mmseg/models/decode_heads/pid_head.py
@@ -0,0 +1,183 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from typing import Optional, Tuple, Union
+
+import torch
+import torch.nn as nn
+from mmcv.cnn import ConvModule, build_activation_layer, build_norm_layer
+from mmengine.model import BaseModule
+from torch import Tensor
+
+from mmseg.models.decode_heads.decode_head import BaseDecodeHead
+from mmseg.models.losses import accuracy
+from mmseg.models.utils import resize
+from mmseg.registry import MODELS
+from mmseg.utils import OptConfigType, SampleList
+
+
+class BasePIDHead(BaseModule):
+    """Base class for PID head.
+
+    Args:
+        in_channels (int): Number of input channels.
+        channels (int): Number of output channels.
+        norm_cfg (dict): Config dict for normalization layer.
+            Default: dict(type='BN').
+        act_cfg (dict): Config dict for activation layer.
+            Default: dict(type='ReLU', inplace=True).
+        init_cfg (dict or list[dict], optional): Init config dict.
+            Default: None.
+    """
+
+    def __init__(self,
+                 in_channels: int,
+                 channels: int,
+                 norm_cfg: OptConfigType = dict(type='BN'),
+                 act_cfg: OptConfigType = dict(type='ReLU', inplace=True),
+                 init_cfg: OptConfigType = None):
+        super().__init__(init_cfg)
+        self.conv = ConvModule(
+            in_channels,
+            channels,
+            kernel_size=3,
+            padding=1,
+            norm_cfg=norm_cfg,
+            act_cfg=act_cfg,
+            order=('norm', 'act', 'conv'))
+        _, self.norm = build_norm_layer(norm_cfg, num_features=channels)
+        self.act = build_activation_layer(act_cfg)
+
+    def forward(self, x: Tensor, cls_seg: Optional[nn.Module]) -> Tensor:
+        """Forward function.
+        Args:
+            x (Tensor): Input tensor.
+            cls_seg (nn.Module, optional): The classification head.
+
+        Returns:
+            Tensor: Output tensor.
+        """
+        x = self.conv(x)
+        x = self.norm(x)
+        x = self.act(x)
+        if cls_seg is not None:
+            x = cls_seg(x)
+        return x
+
+
+@MODELS.register_module()
+class PIDHead(BaseDecodeHead):
+    """Decode head for PIDNet.
+
+    Args:
+        in_channels (int): Number of input channels.
+        channels (int): Number of output channels.
+        num_classes (int): Number of classes.
+        norm_cfg (dict): Config dict for normalization layer.
+            Default: dict(type='BN').
+        act_cfg (dict): Config dict for activation layer.
+            Default: dict(type='ReLU', inplace=True).
+    """
+
+    def __init__(self,
+                 in_channels: int,
+                 channels: int,
+                 num_classes: int,
+                 norm_cfg: OptConfigType = dict(type='BN'),
+                 act_cfg: OptConfigType = dict(type='ReLU', inplace=True),
+                 **kwargs):
+        super().__init__(
+            in_channels,
+            channels,
+            num_classes=num_classes,
+            norm_cfg=norm_cfg,
+            act_cfg=act_cfg,
+            **kwargs)
+        self.i_head = BasePIDHead(in_channels, channels, norm_cfg, act_cfg)
+        self.p_head = BasePIDHead(in_channels // 2, channels, norm_cfg,
+                                  act_cfg)
+        self.d_head = BasePIDHead(
+            in_channels // 2,
+            in_channels // 4,
+            norm_cfg,
+        )
+        self.p_cls_seg = nn.Conv2d(channels, self.out_channels, kernel_size=1)
+        self.d_cls_seg = nn.Conv2d(in_channels // 4, 1, kernel_size=1)
+
+    def init_weights(self):
+        for m in self.modules():
+            if isinstance(m, nn.Conv2d):
+                nn.init.kaiming_normal_(
+                    m.weight, mode='fan_out', nonlinearity='relu')
+            elif isinstance(m, nn.BatchNorm2d):
+                nn.init.constant_(m.weight, 1)
+                nn.init.constant_(m.bias, 0)
+
+    def forward(
+            self,
+            inputs: Union[Tensor,
+                          Tuple[Tensor]]) -> Union[Tensor, Tuple[Tensor]]:
+        """Forward function.
+        Args:
+            inputs (Tensor | tuple[Tensor]): Input tensor or tuple of
+                Tensor. When training, the input is a tuple of three tensors,
+                (p_feat, i_feat, d_feat), and the output is a tuple of three
+                tensors, (p_seg_logit, i_seg_logit, d_seg_logit).
+                When inference, only the head of integral branch is used, and
+                input is a tensor of integral feature map, and the output is
+                the segmentation logit.
+
+        Returns:
+            Tensor | tuple[Tensor]: Output tensor or tuple of tensors.
+        """
+        if self.training:
+            x_p, x_i, x_d = inputs
+            x_p = self.p_head(x_p, self.p_cls_seg)
+            x_i = self.i_head(x_i, self.cls_seg)
+            x_d = self.d_head(x_d, self.d_cls_seg)
+            return x_p, x_i, x_d
+        else:
+            return self.i_head(inputs, self.cls_seg)
+
+    def _stack_batch_gt(self, batch_data_samples: SampleList) -> Tuple[Tensor]:
+        gt_semantic_segs = [
+            data_sample.gt_sem_seg.data for data_sample in batch_data_samples
+        ]
+        gt_edge_segs = [
+            data_sample.gt_edge_map.data for data_sample in batch_data_samples
+        ]
+        gt_sem_segs = torch.stack(gt_semantic_segs, dim=0)
+        gt_edge_segs = torch.stack(gt_edge_segs, dim=0)
+        return gt_sem_segs, gt_edge_segs
+
+    def loss_by_feat(self, seg_logits: Tuple[Tensor],
+                     batch_data_samples: SampleList) -> dict:
+        loss = dict()
+        p_logit, i_logit, d_logit = seg_logits
+        sem_label, bd_label = self._stack_batch_gt(batch_data_samples)
+        p_logit = resize(
+            input=p_logit,
+            size=sem_label.shape[2:],
+            mode='bilinear',
+            align_corners=self.align_corners)
+        i_logit = resize(
+            input=i_logit,
+            size=sem_label.shape[2:],
+            mode='bilinear',
+            align_corners=self.align_corners)
+        d_logit = resize(
+            input=d_logit,
+            size=bd_label.shape[2:],
+            mode='bilinear',
+            align_corners=self.align_corners)
+        sem_label = sem_label.squeeze(1)
+        bd_label = bd_label.squeeze(1)
+        loss['loss_sem_p'] = self.loss_decode[0](
+            p_logit, sem_label, ignore_index=self.ignore_index)
+        loss['loss_sem_i'] = self.loss_decode[1](i_logit, sem_label)
+        loss['loss_bd'] = self.loss_decode[2](d_logit, bd_label)
+        filler = torch.ones_like(sem_label) * self.ignore_index
+        sem_bd_label = torch.where(
+            torch.sigmoid(d_logit[:, 0, :, :]) > 0.8, sem_label, filler)
+        loss['loss_sem_bd'] = self.loss_decode[3](i_logit, sem_bd_label)
+        loss['acc_seg'] = accuracy(
+            i_logit, sem_label, ignore_index=self.ignore_index)
+        return loss
diff --git a/mmseg/models/losses/__init__.py b/mmseg/models/losses/__init__.py
index d7e019747d..2f7e39cb28 100644
--- a/mmseg/models/losses/__init__.py
+++ b/mmseg/models/losses/__init__.py
@@ -1,10 +1,12 @@
 # Copyright (c) OpenMMLab. All rights reserved.
 from .accuracy import Accuracy, accuracy
+from .boundary_loss import BoundaryLoss
 from .cross_entropy_loss import (CrossEntropyLoss, binary_cross_entropy,
                                  cross_entropy, mask_cross_entropy)
 from .dice_loss import DiceLoss
 from .focal_loss import FocalLoss
 from .lovasz_loss import LovaszLoss
+from .ohem_cross_entropy_loss import OhemCrossEntropy
 from .tversky_loss import TverskyLoss
 from .utils import reduce_loss, weight_reduce_loss, weighted_loss
 
@@ -12,5 +14,5 @@
     'accuracy', 'Accuracy', 'cross_entropy', 'binary_cross_entropy',
     'mask_cross_entropy', 'CrossEntropyLoss', 'reduce_loss',
     'weight_reduce_loss', 'weighted_loss', 'LovaszLoss', 'DiceLoss',
-    'FocalLoss', 'TverskyLoss'
+    'FocalLoss', 'TverskyLoss', 'OhemCrossEntropy', 'BoundaryLoss'
 ]
diff --git a/mmseg/models/losses/boundary_loss.py b/mmseg/models/losses/boundary_loss.py
new file mode 100644
index 0000000000..e86b850d87
--- /dev/null
+++ b/mmseg/models/losses/boundary_loss.py
@@ -0,0 +1,62 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from torch import Tensor
+
+from mmseg.registry import MODELS
+
+
+@MODELS.register_module()
+class BoundaryLoss(nn.Module):
+    """Boundary loss.
+
+    This function is modified from
+    `PIDNet <https://github.com/XuJiacong/PIDNet/blob/main/utils/criterion.py#L122>`_.  # noqa
+    Licensed under the MIT License.
+
+
+    Args:
+        loss_weight (float): Weight of the loss. Defaults to 1.0.
+        loss_name (str): Name of the loss item. If you want this loss
+            item to be included into the backward graph, `loss_` must be the
+            prefix of the name. Defaults to 'loss_boundary'.
+    """
+
+    def __init__(self,
+                 loss_weight: float = 1.0,
+                 loss_name: str = 'loss_boundary'):
+        super().__init__()
+        self.loss_weight = loss_weight
+        self.loss_name_ = loss_name
+
+    def forward(self, bd_pre: Tensor, bd_gt: Tensor) -> Tensor:
+        """Forward function.
+        Args:
+            bd_pre (Tensor): Predictions of the boundary head.
+            bd_gt (Tensor): Ground truth of the boundary.
+
+        Returns:
+            Tensor: Loss tensor.
+        """
+        log_p = bd_pre.permute(0, 2, 3, 1).contiguous().view(1, -1)
+        target_t = bd_gt.view(1, -1).float()
+
+        pos_index = (target_t == 1)
+        neg_index = (target_t == 0)
+
+        weight = torch.zeros_like(log_p)
+        pos_num = pos_index.sum()
+        neg_num = neg_index.sum()
+        sum_num = pos_num + neg_num
+        weight[pos_index] = neg_num * 1.0 / sum_num
+        weight[neg_index] = pos_num * 1.0 / sum_num
+
+        loss = F.binary_cross_entropy_with_logits(
+            log_p, target_t, weight, reduction='mean')
+
+        return self.loss_weight * loss
+
+    @property
+    def loss_name(self):
+        return self.loss_name_
diff --git a/mmseg/models/losses/ohem_cross_entropy_loss.py b/mmseg/models/losses/ohem_cross_entropy_loss.py
new file mode 100644
index 0000000000..a519b4d84e
--- /dev/null
+++ b/mmseg/models/losses/ohem_cross_entropy_loss.py
@@ -0,0 +1,94 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from typing import List, Optional, Union
+
+import torch.nn as nn
+import torch.nn.functional as F
+from torch import Tensor
+
+from mmseg.registry import MODELS
+
+
+@MODELS.register_module()
+class OhemCrossEntropy(nn.Module):
+    """OhemCrossEntropy loss.
+
+    This func is modified from
+    `PIDNet <https://github.com/XuJiacong/PIDNet/blob/main/utils/criterion.py#L43>`_.  # noqa
+
+    Licensed under the MIT License.
+
+    Args:
+        ignore_label (int): Labels to ignore when computing the loss.
+            Default: 255
+        thresh (float, optional): The threshold for hard example selection.
+            Below which, are prediction with low confidence. If not
+            specified, the hard examples will be pixels of top ``min_kept``
+            loss. Default: 0.7.
+        min_kept (int, optional): The minimum number of predictions to keep.
+            Default: 100000.
+        loss_weight (float): Weight of the loss. Defaults to 1.0.
+        class_weight (list[float] | str, optional): Weight of each class. If in
+            str format, read them from a file. Defaults to None.
+        loss_name (str): Name of the loss item. If you want this loss
+            item to be included into the backward graph, `loss_` must be the
+            prefix of the name. Defaults to 'loss_boundary'.
+    """
+
+    def __init__(self,
+                 ignore_label: int = 255,
+                 thres: float = 0.7,
+                 min_kept: int = 100000,
+                 loss_weight: float = 1.0,
+                 class_weight: Optional[Union[List[float], str]] = None,
+                 loss_name: str = 'loss_ohem'):
+        super().__init__()
+        self.thresh = thres
+        self.min_kept = max(1, min_kept)
+        self.ignore_label = ignore_label
+        self.loss_weight = loss_weight
+        self.loss_name_ = loss_name
+        self.class_weight = class_weight
+
+    def forward(self, score: Tensor, target: Tensor) -> Tensor:
+        """Forward function.
+        Args:
+            score (Tensor): Predictions of the segmentation head.
+            target (Tensor): Ground truth of the image.
+
+        Returns:
+            Tensor: Loss tensor.
+        """
+        # score: (N, C, H, W)
+        pred = F.softmax(score, dim=1)
+        if self.class_weight is not None:
+            class_weight = score.new_tensor(self.class_weight)
+        else:
+            class_weight = None
+
+        pixel_losses = F.cross_entropy(
+            score,
+            target,
+            weight=class_weight,
+            ignore_index=self.ignore_label,
+            reduction='none').contiguous().view(-1)  # (N*H*W)
+        mask = target.contiguous().view(-1) != self.ignore_label  # (N*H*W)
+
+        tmp_target = target.clone()  # (N, H, W)
+        tmp_target[tmp_target == self.ignore_label] = 0
+        # pred: (N, C, H, W) -> (N*H*W, C)
+        pred = pred.gather(1, tmp_target.unsqueeze(1))
+        # pred: (N*H*W, C) -> (N*H*W), ind: (N*H*W)
+        pred, ind = pred.contiguous().view(-1, )[mask].contiguous().sort()
+        if pred.numel() > 0:
+            min_value = pred[min(self.min_kept, pred.numel() - 1)]
+        else:
+            return score.new_tensor(0.0)
+        threshold = max(min_value, self.thresh)
+
+        pixel_losses = pixel_losses[mask][ind]
+        pixel_losses = pixel_losses[pred < threshold]
+        return self.loss_weight * pixel_losses.mean()
+
+    @property
+    def loss_name(self):
+        return self.loss_name_
diff --git a/mmseg/models/utils/__init__.py b/mmseg/models/utils/__init__.py
index 7aaa600c2d..fc142f16fc 100644
--- a/mmseg/models/utils/__init__.py
+++ b/mmseg/models/utils/__init__.py
@@ -1,8 +1,10 @@
 # Copyright (c) OpenMMLab. All rights reserved.
+from .basic_block import BasicBlock, Bottleneck
 from .embed import PatchEmbed
 from .encoding import Encoding
 from .inverted_residual import InvertedResidual, InvertedResidualV3
 from .make_divisible import make_divisible
+from .ppm import DAPPM, PAPPM
 from .res_layer import ResLayer
 from .se_layer import SELayer
 from .self_attention_block import SelfAttentionBlock
@@ -15,5 +17,5 @@
     'ResLayer', 'SelfAttentionBlock', 'make_divisible', 'InvertedResidual',
     'UpConvBlock', 'InvertedResidualV3', 'SELayer', 'PatchEmbed',
     'nchw_to_nlc', 'nlc_to_nchw', 'nchw2nlc2nchw', 'nlc2nchw2nlc', 'Encoding',
-    'Upsample', 'resize'
+    'Upsample', 'resize', 'DAPPM', 'PAPPM', 'BasicBlock', 'Bottleneck'
 ]
diff --git a/mmseg/models/utils/basic_block.py b/mmseg/models/utils/basic_block.py
new file mode 100644
index 0000000000..4e1ad8146d
--- /dev/null
+++ b/mmseg/models/utils/basic_block.py
@@ -0,0 +1,143 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from typing import Optional
+
+import torch.nn as nn
+from mmcv.cnn import ConvModule
+from mmengine.model import BaseModule
+from torch import Tensor
+
+from mmseg.registry import MODELS
+from mmseg.utils import OptConfigType
+
+
+class BasicBlock(BaseModule):
+    """Basic block from `ResNet <https://arxiv.org/abs/1512.03385>`_.
+
+    Args:
+        in_channels (int): Input channels.
+        channels (int): Output channels.
+        stride (int): Stride of the first block. Default: 1.
+        downsample (nn.Module, optional): Downsample operation on identity.
+            Default: None.
+        norm_cfg (dict, optional): Config dict for normalization layer.
+            Default: dict(type='BN').
+        act_cfg (dict, optional): Config dict for activation layer in
+            ConvModule. Default: dict(type='ReLU', inplace=True).
+        act_cfg_out (dict, optional): Config dict for activation layer at the
+            last of the block. Default: None.
+        init_cfg (dict, optional): Initialization config dict. Default: None.
+    """
+
+    expansion = 1
+
+    def __init__(self,
+                 in_channels: int,
+                 channels: int,
+                 stride: int = 1,
+                 downsample: nn.Module = None,
+                 norm_cfg: OptConfigType = dict(type='BN'),
+                 act_cfg: OptConfigType = dict(type='ReLU', inplace=True),
+                 act_cfg_out: OptConfigType = dict(type='ReLU', inplace=True),
+                 init_cfg: OptConfigType = None):
+        super().__init__(init_cfg)
+        self.conv1 = ConvModule(
+            in_channels,
+            channels,
+            kernel_size=3,
+            stride=stride,
+            padding=1,
+            norm_cfg=norm_cfg,
+            act_cfg=act_cfg)
+        self.conv2 = ConvModule(
+            channels,
+            channels,
+            kernel_size=3,
+            padding=1,
+            norm_cfg=norm_cfg,
+            act_cfg=None)
+        self.downsample = downsample
+        if act_cfg_out:
+            self.act = MODELS.build(act_cfg_out)
+
+    def forward(self, x: Tensor) -> Tensor:
+        residual = x
+        out = self.conv1(x)
+        out = self.conv2(out)
+
+        if self.downsample:
+            residual = self.downsample(x)
+
+        out += residual
+
+        if hasattr(self, 'act'):
+            out = self.act(out)
+
+        return out
+
+
+class Bottleneck(BaseModule):
+    """Bottleneck block from `ResNet <https://arxiv.org/abs/1512.03385>`_.
+
+    Args:
+        in_channels (int): Input channels.
+        channels (int): Output channels.
+        stride (int): Stride of the first block. Default: 1.
+        downsample (nn.Module, optional): Downsample operation on identity.
+            Default: None.
+        norm_cfg (dict, optional): Config dict for normalization layer.
+            Default: dict(type='BN').
+        act_cfg (dict, optional): Config dict for activation layer in
+            ConvModule. Default: dict(type='ReLU', inplace=True).
+        act_cfg_out (dict, optional): Config dict for activation layer at
+            the last of the block. Default: None.
+        init_cfg (dict, optional): Initialization config dict. Default: None.
+    """
+
+    expansion = 2
+
+    def __init__(self,
+                 in_channels: int,
+                 channels: int,
+                 stride: int = 1,
+                 downsample: Optional[nn.Module] = None,
+                 norm_cfg: OptConfigType = dict(type='BN'),
+                 act_cfg: OptConfigType = dict(type='ReLU', inplace=True),
+                 act_cfg_out: OptConfigType = None,
+                 init_cfg: OptConfigType = None):
+        super().__init__(init_cfg)
+        self.conv1 = ConvModule(
+            in_channels, channels, 1, norm_cfg=norm_cfg, act_cfg=act_cfg)
+        self.conv2 = ConvModule(
+            channels,
+            channels,
+            3,
+            stride,
+            1,
+            norm_cfg=norm_cfg,
+            act_cfg=act_cfg)
+        self.conv3 = ConvModule(
+            channels,
+            channels * self.expansion,
+            1,
+            norm_cfg=norm_cfg,
+            act_cfg=None)
+        if act_cfg_out:
+            self.act = MODELS.build(act_cfg_out)
+        self.downsample = downsample
+
+    def forward(self, x: Tensor) -> Tensor:
+        residual = x
+
+        out = self.conv1(x)
+        out = self.conv2(out)
+        out = self.conv3(out)
+
+        if self.downsample:
+            residual = self.downsample(x)
+
+        out += residual
+
+        if hasattr(self, 'act'):
+            out = self.act(out)
+
+        return out
diff --git a/mmseg/models/utils/ppm.py b/mmseg/models/utils/ppm.py
new file mode 100644
index 0000000000..5fe6ff26fa
--- /dev/null
+++ b/mmseg/models/utils/ppm.py
@@ -0,0 +1,193 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from typing import Dict, List
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from mmcv.cnn import ConvModule
+from mmengine.model import BaseModule, ModuleList, Sequential
+from torch import Tensor
+
+
+class DAPPM(BaseModule):
+    """DAPPM module in `DDRNet <https://arxiv.org/abs/2101.06085>`_.
+
+    Args:
+        in_channels (int): Input channels.
+        branch_channels (int): Branch channels.
+        out_channels (int): Output channels.
+        num_scales (int): Number of scales.
+        kernel_sizes (list[int]): Kernel sizes of each scale.
+        strides (list[int]): Strides of each scale.
+        paddings (list[int]): Paddings of each scale.
+        norm_cfg (dict): Config dict for normalization layer.
+            Default: dict(type='BN').
+        act_cfg (dict): Config dict for activation layer in ConvModule.
+            Default: dict(type='ReLU', inplace=True).
+        conv_cfg (dict): Config dict for convolution layer in ConvModule.
+            Default: dict(order=('norm', 'act', 'conv'), bias=False).
+        upsample_mode (str): Upsample mode. Default: 'bilinear'.
+    """
+
+    def __init__(self,
+                 in_channels: int,
+                 branch_channels: int,
+                 out_channels: int,
+                 num_scales: int,
+                 kernel_sizes: List[int] = [5, 9, 17],
+                 strides: List[int] = [2, 4, 8],
+                 paddings: List[int] = [2, 4, 8],
+                 norm_cfg: Dict = dict(type='BN', momentum=0.1),
+                 act_cfg: Dict = dict(type='ReLU', inplace=True),
+                 conv_cfg: Dict = dict(
+                     order=('norm', 'act', 'conv'), bias=False),
+                 upsample_mode: str = 'bilinear'):
+        super().__init__()
+
+        self.num_scales = num_scales
+        self.unsample_mode = upsample_mode
+        self.in_channels = in_channels
+        self.branch_channels = branch_channels
+        self.out_channels = out_channels
+        self.norm_cfg = norm_cfg
+        self.act_cfg = act_cfg
+        self.conv_cfg = conv_cfg
+
+        self.scales = ModuleList([
+            ConvModule(
+                in_channels,
+                branch_channels,
+                kernel_size=1,
+                norm_cfg=norm_cfg,
+                act_cfg=act_cfg,
+                **conv_cfg)
+        ])
+        for i in range(1, num_scales - 1):
+            self.scales.append(
+                Sequential(*[
+                    nn.AvgPool2d(
+                        kernel_size=kernel_sizes[i - 1],
+                        stride=strides[i - 1],
+                        padding=paddings[i - 1]),
+                    ConvModule(
+                        in_channels,
+                        branch_channels,
+                        kernel_size=1,
+                        norm_cfg=norm_cfg,
+                        act_cfg=act_cfg,
+                        **conv_cfg)
+                ]))
+        self.scales.append(
+            Sequential(*[
+                nn.AdaptiveAvgPool2d((1, 1)),
+                ConvModule(
+                    in_channels,
+                    branch_channels,
+                    kernel_size=1,
+                    norm_cfg=norm_cfg,
+                    act_cfg=act_cfg,
+                    **conv_cfg)
+            ]))
+        self.processes = ModuleList()
+        for i in range(num_scales - 1):
+            self.processes.append(
+                ConvModule(
+                    branch_channels,
+                    branch_channels,
+                    kernel_size=3,
+                    padding=1,
+                    norm_cfg=norm_cfg,
+                    act_cfg=act_cfg,
+                    **conv_cfg))
+
+        self.compression = ConvModule(
+            branch_channels * num_scales,
+            out_channels,
+            kernel_size=1,
+            norm_cfg=norm_cfg,
+            act_cfg=act_cfg,
+            **conv_cfg)
+
+        self.shortcut = ConvModule(
+            in_channels,
+            out_channels,
+            kernel_size=1,
+            norm_cfg=norm_cfg,
+            act_cfg=act_cfg,
+            **conv_cfg)
+
+    def forward(self, inputs: Tensor):
+        feats = []
+        feats.append(self.scales[0](inputs))
+
+        for i in range(1, self.num_scales):
+            feat_up = F.interpolate(
+                self.scales[i](inputs),
+                size=inputs.shape[2:],
+                mode=self.unsample_mode)
+            feats.append(self.processes[i - 1](feat_up + feats[i - 1]))
+
+        return self.compression(torch.cat(feats,
+                                          dim=1)) + self.shortcut(inputs)
+
+
+class PAPPM(DAPPM):
+    """PAPPM module in `PIDNet <https://arxiv.org/abs/2206.02066>`_.
+
+    Args:
+        in_channels (int): Input channels.
+        branch_channels (int): Branch channels.
+        out_channels (int): Output channels.
+        num_scales (int): Number of scales.
+        kernel_sizes (list[int]): Kernel sizes of each scale.
+        strides (list[int]): Strides of each scale.
+        paddings (list[int]): Paddings of each scale.
+        norm_cfg (dict): Config dict for normalization layer.
+            Default: dict(type='BN', momentum=0.1).
+        act_cfg (dict): Config dict for activation layer in ConvModule.
+            Default: dict(type='ReLU', inplace=True).
+        conv_cfg (dict): Config dict for convolution layer in ConvModule.
+            Default: dict(order=('norm', 'act', 'conv'), bias=False).
+        upsample_mode (str): Upsample mode. Default: 'bilinear'.
+    """
+
+    def __init__(self,
+                 in_channels: int,
+                 branch_channels: int,
+                 out_channels: int,
+                 num_scales: int,
+                 kernel_sizes: List[int] = [5, 9, 17],
+                 strides: List[int] = [2, 4, 8],
+                 paddings: List[int] = [2, 4, 8],
+                 norm_cfg: Dict = dict(type='BN', momentum=0.1),
+                 act_cfg: Dict = dict(type='ReLU', inplace=True),
+                 conv_cfg: Dict = dict(
+                     order=('norm', 'act', 'conv'), bias=False),
+                 upsample_mode: str = 'bilinear'):
+        super().__init__(in_channels, branch_channels, out_channels,
+                         num_scales, kernel_sizes, strides, paddings, norm_cfg,
+                         act_cfg, conv_cfg, upsample_mode)
+
+        self.processes = ConvModule(
+            self.branch_channels * (self.num_scales - 1),
+            self.branch_channels * (self.num_scales - 1),
+            kernel_size=3,
+            padding=1,
+            groups=self.num_scales - 1,
+            norm_cfg=self.norm_cfg,
+            act_cfg=self.act_cfg,
+            **self.conv_cfg)
+
+    def forward(self, inputs: Tensor):
+        x_ = self.scales[0](inputs)
+        feats = []
+        for i in range(1, self.num_scales):
+            feat_up = F.interpolate(
+                self.scales[i](inputs),
+                size=inputs.shape[2:],
+                mode=self.unsample_mode,
+                align_corners=False)
+            feats.append(feat_up + x_)
+        scale_out = self.processes(torch.cat(feats, dim=1))
+        return self.compression(torch.cat([x_, scale_out],
+                                          dim=1)) + self.shortcut(inputs)
diff --git a/model-index.yml b/model-index.yml
index ae96bd30f7..be7210e120 100644
--- a/model-index.yml
+++ b/model-index.yml
@@ -31,6 +31,7 @@ Import:
 - configs/mobilenet_v3/mobilenet_v3.yml
 - configs/nonlocal_net/nonlocal_net.yml
 - configs/ocrnet/ocrnet.yml
+- configs/pidnet/pidnet.yml
 - configs/point_rend/point_rend.yml
 - configs/poolformer/poolformer.yml
 - configs/psanet/psanet.yml
diff --git a/tests/test_models/test_backbones/test_pidnet.py b/tests/test_models/test_backbones/test_pidnet.py
new file mode 100644
index 0000000000..208dfc7814
--- /dev/null
+++ b/tests/test_models/test_backbones/test_pidnet.py
@@ -0,0 +1,87 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+import os
+import tempfile
+
+import torch
+from mmengine.registry import init_default_scope
+
+from mmseg.registry import MODELS
+
+init_default_scope('mmseg')
+
+
+def test_pidnet_backbone():
+    # Test PIDNet Standard Forward
+    norm_cfg = dict(type='BN', requires_grad=True)
+    backbone_cfg = dict(
+        type='PIDNet',
+        in_channels=3,
+        channels=32,
+        ppm_channels=96,
+        num_stem_blocks=2,
+        num_branch_blocks=3,
+        align_corners=False,
+        norm_cfg=norm_cfg,
+        act_cfg=dict(type='ReLU', inplace=True))
+    model = MODELS.build(backbone_cfg)
+    model.init_weights()
+
+    # Test init weights
+    temp_file = tempfile.NamedTemporaryFile()
+    temp_file.close()
+    torch.save(model.state_dict(), temp_file.name)
+    backbone_cfg.update(
+        init_cfg=dict(type='Pretrained', checkpoint=temp_file.name))
+    model = MODELS.build(backbone_cfg)
+    model.init_weights()
+    os.remove(temp_file.name)
+
+    # Test eval mode
+    model.eval()
+    batch_size = 1
+    imgs = torch.randn(batch_size, 3, 64, 128)
+    feats = model(imgs)
+
+    assert type(feats) == torch.Tensor
+    assert feats.shape == torch.Size([batch_size, 128, 8, 16])
+
+    # Test train mode
+    model.train()
+    batch_size = 2
+    imgs = torch.randn(batch_size, 3, 64, 128)
+    feats = model(imgs)
+
+    assert len(feats) == 3
+    # test output for P branch
+    assert feats[0].shape == torch.Size([batch_size, 64, 8, 16])
+    # test output for I branch
+    assert feats[1].shape == torch.Size([batch_size, 128, 8, 16])
+    # test output for D branch
+    assert feats[2].shape == torch.Size([batch_size, 64, 8, 16])
+
+    # Test pidnet-m
+    backbone_cfg.update(channels=64)
+    model = MODELS.build(backbone_cfg)
+    feats = model(imgs)
+
+    assert len(feats) == 3
+    # test output for P branch
+    assert feats[0].shape == torch.Size([batch_size, 128, 8, 16])
+    # test output for I branch
+    assert feats[1].shape == torch.Size([batch_size, 256, 8, 16])
+    # test output for D branch
+    assert feats[2].shape == torch.Size([batch_size, 128, 8, 16])
+
+    # Test pidnet-l
+    backbone_cfg.update(
+        channels=64, ppm_channesl=112, num_stem_blocks=3, num_branch_blocks=4)
+    model = MODELS.build(backbone_cfg)
+    feats = model(imgs)
+
+    assert len(feats) == 3
+    # test output for P branch
+    assert feats[0].shape == torch.Size([batch_size, 128, 8, 16])
+    # test output for I branch
+    assert feats[1].shape == torch.Size([batch_size, 256, 8, 16])
+    # test output for D branch
+    assert feats[2].shape == torch.Size([batch_size, 128, 8, 16])
diff --git a/tests/test_models/test_heads/test_pidnet_head.py b/tests/test_models/test_heads/test_pidnet_head.py
new file mode 100644
index 0000000000..a6247371c5
--- /dev/null
+++ b/tests/test_models/test_heads/test_pidnet_head.py
@@ -0,0 +1,89 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+import torch
+from mmengine.registry import init_default_scope
+
+from mmseg.registry import MODELS
+
+
+def test_pidnet_head():
+    init_default_scope('mmseg')
+
+    # Test PIDNet decode head Standard Forward
+    norm_cfg = dict(type='BN', requires_grad=True)
+    backbone_cfg = dict(
+        type='PIDNet',
+        in_channels=3,
+        channels=32,
+        ppm_channels=96,
+        num_stem_blocks=2,
+        num_branch_blocks=3,
+        align_corners=False,
+        norm_cfg=norm_cfg,
+        act_cfg=dict(type='ReLU', inplace=True))
+    decode_head_cfg = dict(
+        type='PIDHead',
+        in_channels=128,
+        channels=128,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        act_cfg=dict(type='ReLU', inplace=True),
+        align_corners=True,
+        loss_decode=[
+            dict(
+                type='CrossEntropyLoss',
+                use_sigmoid=False,
+                class_weight=[
+                    0.8373, 0.918, 0.866, 1.0345, 1.0166, 0.9969, 0.9754,
+                    1.0489, 0.8786, 1.0023, 0.9539, 0.9843, 1.1116, 0.9037,
+                    1.0865, 1.0955, 1.0865, 1.1529, 1.0507
+                ],
+                loss_weight=0.4),
+            dict(
+                type='OhemCrossEntropy',
+                thres=0.9,
+                min_kept=131072,
+                class_weight=[
+                    0.8373, 0.918, 0.866, 1.0345, 1.0166, 0.9969, 0.9754,
+                    1.0489, 0.8786, 1.0023, 0.9539, 0.9843, 1.1116, 0.9037,
+                    1.0865, 1.0955, 1.0865, 1.1529, 1.0507
+                ],
+                loss_weight=1.0),
+            dict(type='BoundaryLoss', loss_weight=20.0),
+            dict(
+                type='OhemCrossEntropy',
+                thres=0.9,
+                min_kept=131072,
+                class_weight=[
+                    0.8373, 0.918, 0.866, 1.0345, 1.0166, 0.9969, 0.9754,
+                    1.0489, 0.8786, 1.0023, 0.9539, 0.9843, 1.1116, 0.9037,
+                    1.0865, 1.0955, 1.0865, 1.1529, 1.0507
+                ],
+                loss_weight=1.0)
+        ])
+    backbone = MODELS.build(backbone_cfg)
+    head = MODELS.build(decode_head_cfg)
+
+    # Test train mode
+    backbone.train()
+    head.train()
+    batch_size = 2
+    imgs = torch.randn(batch_size, 3, 64, 128)
+    feats = backbone(imgs)
+    seg_logit = head(feats)
+
+    assert isinstance(seg_logit, tuple)
+    assert len(seg_logit) == 3
+
+    p_logits, i_logits, d_logits = seg_logit
+    assert p_logits.shape == (batch_size, 19, 8, 16)
+    assert i_logits.shape == (batch_size, 19, 8, 16)
+    assert d_logits.shape == (batch_size, 1, 8, 16)
+
+    # Test eval mode
+    backbone.eval()
+    head.eval()
+    feats = backbone(imgs)
+    seg_logit = head(feats)
+
+    assert isinstance(seg_logit, torch.Tensor)
+    assert seg_logit.shape == (batch_size, 19, 8, 16)

From 3cc7ae2167a48df6234c7d5c68efc5020030ed0a Mon Sep 17 00:00:00 2001
From: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
Date: Wed, 15 Mar 2023 17:49:59 +0800
Subject: [PATCH 15/32] [Fix] Format shape check (#2753)

as title
---
 mmseg/datasets/transforms/formatting.py | 4 ++--
 tests/test_datasets/test_formatting.py  | 6 +++++-
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/mmseg/datasets/transforms/formatting.py b/mmseg/datasets/transforms/formatting.py
index 57cda9b10e..46171d64f5 100644
--- a/mmseg/datasets/transforms/formatting.py
+++ b/mmseg/datasets/transforms/formatting.py
@@ -74,12 +74,12 @@ def transform(self, results: dict) -> dict:
 
         data_sample = SegDataSample()
         if 'gt_seg_map' in results:
-            if results['gt_seg_map'].shape == 2:
+            if len(results['gt_seg_map'].shape) == 2:
                 data = to_tensor(results['gt_seg_map'][None,
                                                        ...].astype(np.int64))
             else:
                 warnings.warn('Please pay attention your ground truth '
-                              'segmentation map, usually the segentation '
+                              'segmentation map, usually the segmentation '
                               'map is 2D, but got '
                               f'{results["gt_seg_map"].shape}')
                 data = to_tensor(results['gt_seg_map'].astype(np.int64))
diff --git a/tests/test_datasets/test_formatting.py b/tests/test_datasets/test_formatting.py
index 51fd90d048..d0e5820ec7 100644
--- a/tests/test_datasets/test_formatting.py
+++ b/tests/test_datasets/test_formatting.py
@@ -4,6 +4,7 @@
 import unittest
 
 import numpy as np
+import pytest
 from mmengine.structures import BaseDataElement
 
 from mmseg.datasets.transforms import PackSegInputs
@@ -46,8 +47,11 @@ def test_transform(self):
         self.assertEqual(results['data_samples'].ori_shape,
                          results['data_samples'].gt_sem_seg.shape)
         results = copy.deepcopy(self.results)
+        # test dataset shape is not 2D
         results['gt_seg_map'] = np.random.rand(3, 300, 400)
-        results = transform(results)
+        msg = 'the segmentation map is 2D'
+        with pytest.warns(UserWarning, match=msg):
+            results = transform(results)
         self.assertEqual(results['data_samples'].ori_shape,
                          results['data_samples'].gt_sem_seg.shape)
 

From 1f1f2666b52ce080240bb8e9ebae695465f30121 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E8=B0=A2=E6=98=95=E8=BE=B0?= <xiexinch@outlook.com>
Date: Wed, 15 Mar 2023 18:29:16 +0800
Subject: [PATCH 16/32] [Dev] Replace the test images (#2754)

## Motivation

The original images are too large.

## Modification

Crop to small images.
---
 .../images/__CRyFzoDOXn6unQ6a3DnQ.jpg         | Bin 1227776 -> 2201 bytes
 .../v1.2/__CRyFzoDOXn6unQ6a3DnQ.png           | Bin 75488 -> 1002 bytes
 .../v2.0/__CRyFzoDOXn6unQ6a3DnQ.png           | Bin 75316 -> 1002 bytes
 3 files changed, 0 insertions(+), 0 deletions(-)

diff --git a/tests/data/pseudo_mapillary_dataset/images/__CRyFzoDOXn6unQ6a3DnQ.jpg b/tests/data/pseudo_mapillary_dataset/images/__CRyFzoDOXn6unQ6a3DnQ.jpg
index deed3177806e443cee9b00e0fb0e80315488742e..c3cf31a170788f257869ec57c760ddb7f931396d 100644
GIT binary patch
delta 1612
zcmV-S2DABq_)3`(kX``@kzYgv0Av7Uv8TuZf8{OX7fcs!(n#xC2g1v7mTAZYcgU>g
z)J2@Eu7njMwOqFGBI6kO6z~8%RT)^cd^vG$n?=U-1BGM#Ycl4`$@v*}k--MEzu_a^
zRI{${OmR?6crT;CLJw`dN%g03nWD`J!mdp*tat}MhH60t@{hO*`i?0JT}D6E=7HFO
zf2^HTa7+%=!vh5%ty&kZ7^}ceI&q2`;u1zw55}k&npY2loz$%ow`#gl*_bv6KDnt;
zV(1RxKp7?_{C<>qARWM-m9!v@fjJ}arb}oxWG`w3b0DB6G*t3i66b0XD5YXgUGaZ~
z>{$z#l$>$Dn&H3U7>Ss$`A@SN^=}o*f25+e&`BJc<qSl&K>$}R*`h}){{RTO1H-mR
z>Ae2{jcsZE3}Av%2{_;_Y1>3v?kMq`<n!spc1fw(=~jp*0Ta770;x%k#|bBfW{ENt
z{{R70<<KV1N|yR@UX-37(XIvz>5?;sIjaEab8?bI57w`k4<l_S01bt{oYhHmf0)-G
z#@u^Xv>htaT$PPVk<@YgtCI0XnH`iQq+xPE2Q_L!XPiEjA0y`c>ITyGk%p7;IjyEp
zSezVIrj?`%_QvM~^YYbPlZ|aQSov8Tk?Tlfy8sSA9<}K*ct%Wufr$5FKc!Qf!xJH3
z5x*0WQ_MRY60GV7Fuz(WvTX)se{5h1Df1$1&cnuED<K4o5!6>F_OiW!HP`slJ2E{7
zU&6RnJoWr*E?b%!+GWR^sKgIJpXvS;spFSe^cKpNA57L3lm7rAC|G^$;<}#~Kqt`1
z!5=PjO{9f$#$;0~31OB<+o#CbtNI)|i(O%E=G&eIdex7zMw!6D6}REre{k0go|)s+
zP}PFxr1)uMiqmA0JCZrctgjh3^8CJmm~r^l?vR0FJaPv(?_B=?jQ|HMq+z(B12~6Y
zn5e~ceh`^rz95miJbf#j9D|zJ@Y;sek^6yzim@H0rQ&-nGId+6${29O@${<kc)vlo
zWnZ*K&usBr=Z~#?=%WV&f9E*$uQ-!S%N>9KeLGfTJ>7L}9mYhF5%^JFCvB!qVH;jT
zGuL(~rU$L~&<`XMa0sppui@=o?~IVOryqN^exLnn;JIZ5y3>dkG{2VqAWs>|uFJ#(
ze`2sCW2fm{Zj;8L9~oZ!^sc|f1O6nAPhq?8p@HV6H4V79JoK&ae-ADt+&{h6xiZbr
zu|JJ;z85Seea=WHy$ljPGfFw%+PVJ#8z=77k2pE4?I-T$vV3Z}fkCMmz!8Ir*zn){
zgx8=M8O3C`-mO0lk~JmIsI58@ZTPu&LWF^zPfFre-Aiyd^{(5+v!Yu9{{VM2$BT%R
z;2+MQW`(Vy`2*(ff9XY8vXKq2IbO6=5!QIb17r#8Kc#v0PZj81F5=T5_BH2)2<t>Z
zwWoZy(Q$#Cb*{t2`TqcfenXu6y}dD9cAh`tVGCgJe=6+!MYsMD)^2wBWd4+-Gsz?B
z4;&0vP2r$C=IfonS30Y<L6OJ3bY34|FOOVcP{w**liXHce~gd%CP=M4Fl3%<KgK8x
zpWPiP0q3Ww$i-=BCmNh!dVgBaf0XlDIv*N}eLt;f&_=h7qd#Pfj_0LuD;D#}=DXh-
zA^y%+9-_GGc>Y|2#XuMI=)zg5?Zyv!DQ(#KXRqF(n2zVgNT$hh4lr|Ga!<8-SBjLj
zoAULqH*=Cmf9Pn4$!z}s<KiQZLyT8(uYCFxzwTr3BDia8o0$3jAb76tRb?6hW7BUm
zn2#dI@7R)a?_CFnNBVY0Tvi*&7oO*E827E84$6k`7H|RJA9@NsJ4@pNsrbA8Jc#Z^
zThjR;<Y3ib7Yx~MpbtGNcU9dRKiVtbrBi1(I0RMAe;nsfh!c;Pb5<jx@rff!3`pY)
zYmkI+F<qaF5I&B?a!TWx<89B&k4l6Eh%>O`J!qmPAx;l^De5E8JW6w?gI;L;828Dd
ziV!kOPHq#oJ*&9ZPVWp$pZVoQ6fvF=A!e7BJf3-}ttOH=w<EA+<Q(^+ibFlG!Iu(C
zVx`XGHlFo=#lP|lqKW|X$p=&3tZ8Q#@nhDCD#<#}6Y-@SdRGx|BQ|qI6p#}6tb~D#
KW{N1L2mje7PaJXp

literal 1227776
zcmcG#Wl&sE7bV)z1Sf>x!QBGE-3hLZdlKA(Yan<?)4?Io5WMlm8;2l)#<g(?uEE`s
z;hULyuV!j~%)ENDZ|(c%p4xTSxu^EId#`o=&HY;iyiik8RRW-)0RU)E7vSF_KmmY_
ziHU{z3>ymz3kL@q7oUUx9}f?o@+C1L3C$}yTAEkX)bz|eZ1jw;nW(ARML1sb@(BtG
z(y@t2iSkSG2nh23CkPr24h}vZJ_P{*1wR8d1ONZA{p$n}VdGU0CIHbG0q8_%Kq9n%
zzW{Vk@A(YvzZ&4b8yY$g;~6FvHV!V{(*VQ^06H2Fh>ih#_6!5#X>{<@a{va>vzH8f
za+t)R4_J&IB>Z8CdDu+yHC?2-6DQ09R-WNFxMbuMl&@G=+1NQa1%-q~M8(7v-YP07
ztEj5!=^Gdt8Jn0|+t}LKJ2*OddHeYK`3D3>L`Fq_iTMgnN=`{l`<|Ww%`Yf~6&071
zmetnPBN`f;np?Vie)aYt`v(Rmr%=-~vvczcYwH`ETiZLkd;6zn=NFe(*EhF!|G|X@
z0RA^vPxt=@?0>>V^n?o?0|SVG^&ebl=zdQQB*J*cz=!!#4uti=gP4&&44XtgF|Vcz
zhe<&9gw)D&0+)<gaE;~kKhXXwvj06`;s2kI{Xf9|Ut9|Sd?4D>#{&`pWB}LCFVLVK
zwDnd9F{Slzf7qUqXf9?VRN+{=vych;UVxHBuV&v-JeXt2khq;@PZ=`~1<2Wfvr~`D
z_OkFkZ!g(~gb3=;7a&M<&_X#lv^8{f(7^(#Ss+<F<t;_JZvZwY&E{geWCVbf-;qPx
zR6`GtALppNBa3sONE1Z@(AE8`pHW1AtRBbCL}C~E5)6Rt%JhZ4j6=O*2R!WNg8}UM
z@jJ4ZQl%a$fuL-5G-WsgEO#6ru7gG5BP8g4bfCKoR@<bJ0NqZH)p^V$!u?mz)qfDq
z*OnZpBHL9y*hqpuxu;1^ZOd=k2wI<(YdU9N5_k3od#xlTQAIG0uyTID+bD7{PH({O
zmA2tgdMhTKLIiGTSoPUXS>&Mh&>IC`xfBr!7DJO%z_fw-7W>J~+{TuuP@e+k>=e87
zsII~S+GTb+7=WTcYA-O`VP_`v#bp7t?!`p`96(QU67_|8vQRM|9j;6S8hHz|+Q3VI
zHGgcMgmXqwknD4@9=R2~&j)jmkbo2c|9?Aa#Ja`H4Rb^sw%c3I;%!5^pi}rhJCI!I
zWG1Izkx}_0@hJIDdhu{y)6cJ(?`f(057$H}duoe^(dhn`T}&O$G{a76$0{3&OIox#
zw*^6=gf5d#`<?FMbUm>{V?0-nWTK5&#_~JvbStC_L+dnbvZ@SZ>y%TJDky^KS$k^l
zN-CtI+oU}0kXPzIfH~jP?RDu5Q!Y&^Y}ly5eW_>Iv&42Rui{WiLfvAD@>y##BqG%5
zOE|&cjT>RTily|Y_MyS54<^~dWD7ltMWzKqC48%S^z8otPKZc&sld01UjM3J9DZ!c
z)Zqs=3f;oz=7(*3i^~E|4d*f1%6;-zJEVuwv?qo?@)x;OamT!sN0{Qb_H>=IpI6W1
z5!oz$n|B5Cqb$U{_@%PHd}BXZE~=qOLTP?v#elSx?X>&cMMo5v>~ROfEQ7PjE%O?G
zea1bikbL7<Y!d5($H{p}YjqCp?|6#uX}-`l!}9ketoqwO0NS2KVkue02T_48o2VJz
zxP^7GiIB|*$V|!tPyS3P=V-ChKR|hi$A!=?@dLl{8a<NW+JiBNRql~+&z!c|zWl~l
z0Y6sKUEmX(i*VN&T0~=lC|N(wi(>W^Tmdl!Y@EU}KEgK`)$MG7$Mj{M>aQU-J@!Rg
z+pRKq{_%=YHKojn>euRIuM1}c9eVe;aeqv<aQfTL8r1nC%Goteyi=L_)^2At%RlLW
z)rm;>?DTpHo*Nx3WR%@Za&xXxX$sew4qZp{`UN|q(=hx020_*N(`pIZGX1SDNf(-}
zkMzWTx7`*xR(z;G_u00kaAT2)G@|nR%(>G4+tL1F1LphfWcJt9%*#S@mCpFf_p{l*
z=PmZWYdiaA>(^wx=&OcnBJu@`j`KW(f?|FLE)7=x^uuBjYAyQocBcN8fzFv<sR9`A
z1G`edB}s)L-m5>5(bL(G4%^uehpL`Y&=+vj&vgve&jU&17bTl!FME`k`xh&Gu(BGe
z#F32X4e%{p8_`oA_=%W*^*F1SXmK5V!R@CuIc_G@){%#bpOtcsJ2e9P%pK8o9}%Om
zMcNYH&1x|cxi^0kM#UKhm#O^&cuzYrCl>g`$%^39aw6v!R=+0@Ev*+o`EaSdEY-zh
z{;aWNW(65s8boZ5dd$t(BK|mgRM(V#tW31JeaCzabB_8lR{F=PEH}rr%x%XbE1|gE
zAY3>DDR!*8bQs6Wk7J3tRZ1jYW^j@4f_nCMG#{H(7B+u0^~`er{6jA;LWmZ-NFF3F
z`tVK1F`Hsuey!t(@YEnSpn8ztop_){BE90RR)Et;P;1z{L!f<>&<}J0?`}Mpc1nM5
zz}?BKX0uooxZ4V8D(g2KbU9Np^6%n|&l<mDt1c5i3{Gd3Ex|Xl{Ss<aC&Imjrc5iG
zxQSBUPxl6_sSGi3(WcYQ<V}3!{<+3nPtHX*pHcm1>3MXW8+HCB{=HqM<7>^&xLVz!
zLug5&W9^y*tQoqN2U4wOC&Ceat{;Q#H|4}hJ(ZP!jR%$=*OAe9{yGZ*dSv(g{>Llz
zK8H-EQx_~yybM@Pr=7l6J-5eqTAPW=tpw5?{3WB{z^obsgacWMlgadv+WXd#ViV$#
zqjgCk?_sn$RRn$c5RB6s;5xU@j+VS<L^||bQ<3=%ezXXkh`BG!{LXqI<wxfa?O}=O
zq*v_M=mC^vWk3BW;bsya5pQ2~1W|*#-8!9j?@H#t^9)V&sJm~ObzfiD3G4<`IMySl
zmMttAveTtFA71q>dXbb7-kThld&V`!3|^bQt>sKuOnDwTZ7``rGvbCrTJGxG$b2Z)
z)wNx307?l5zV|NEOClN?dd=IIRvpPSZqUy8*CF-=enO)GjbZuz`@*HLsRTvch7Pji
zugP?WUKT{j)x^%iF+9>!`0ts2e4(CkS0W7Ss;qQw<y!o})E!sB>n=w6<xN^;pYW0t
zp;Oc7eOQJ-{m1j?Qi{CHp2!X{Y$?>_a+;&)mJ_KG7PD0g@wmc9a~g5IE4@d5(U2FD
z=MA#DmrAT(@R-B6@-&i-+V{HD7cDVDgcFZw&hT3jmKCI;LOj}BkH<Tx{AF?vtJTL1
zV4~?Og9QsTf~nBk?tXHra`E`(aT{`8KF`xQ!V_>M5n#)`yZ$&~Ax-c6IZ`NTisvW@
zC9ky*dd$l})iRZ>pZ@-@4>Nm`2#b5L6JAVSL-Muf<zGUz$v2=m5VnpeDWiPzfM$0d
zculSc#4^u@lVzBcIZtHmiFbNs?aY#sNkvdtiX?rzfW%=S2@TlvGI-y?7reP7HDdfl
zN7V**Z!6rxd<v3)jg3XGf7(pP+owz)gz_x3PmW^tDdMz=UtzJ$9o>+dE@*2Yn_MKU
zXWS{KofbM%C{cRfg7}siSh_=}w&8MARF}c5#N_yJP^js~m7(WZRu_Vpz#S;(S36vd
z#cLH24q8vXQFZY$uc>dEs*)b~WJG^x(Sg{%BEaXh-R^!oavp25_99++D9up#1Q8oC
zQ)J@OuOpI=D>J&O6&vA(4@c97_0aES6R6E5soH_QiuDPY42Ty6Ja9<}R|q={g+Jw&
zdlXL-jgyK6TdXIaV8*$$c6W81wys(wuh_$WeWh<g4&0<!>1#vUi13(3J1S$N7NW8r
zNVcE?-|O4p$M#s1oasm=+e?TurcRaOT%B;^wwVtG%5D?|O}7SltJb!?njU$VlIE;X
z;MfTIA{>(x7**D28qi3k<0)0{yEt?&>U--8F`$t@5;%)EN1OR#+Z5*!!SOeMgoI$g
zG|l<PMk=-6WeLVFgh$gsp2|~3ep;dJCiTg<y@C4LL1<rwpajVKL2*M+i^C=h$s>WI
zrm<c95zY>E;7pLqOZQFce*gl#w6((fUw^$j{o+%y9-TdC5hn+I367kCBXV@k!2^AK
z@qrgq@#OwC(cm*@yOp13<G{pQqp=3^X!gZG9IR{g_kS@n{X&vQ&XCNKgsB}aAwrAz
zx;p3l-bY7n{(}S<&Idk4o!GxyRP>ITt`1GUTPrj*5*8KCG;)SG{7&euThA23V$c?o
zTt~QEn7moMCa+FK7K>GIS(zVuIlI{R0!J6gsbYi<XfaMhe!%u}tU5AQz4wnN;t`(0
z9b_%l3EIr#;&BBZP2X@^8=Vskif-P$>W*fbm-?C|miP|o*;{_lx4&>{uYw%p>mR$Q
zAOX*Bpc{7&Hc|a-H~J{tN~W~)v)vFctPhVCGuUZ=_9||Tbg+WCL5GLZUq~h;$t;xs
zf^R*Ec+)1GI3HWs!s)x&x4|THY>1!S!tt&pnCn%dM<egCm#`1}FcpyY5;LHD61n}*
zQw5Vxn-q8t@t7%lzA6_dTe=Z%wRx^)b#~rEXUUPZdEzYh+#ND!v#eivILWe<74)j3
z?bCd*pp|0RK+%urjF`ClhUd`@hpxXsZc^H!W#I-5z6Oe~rJP3E?^kLJ`SRZYvx^W^
zIO%C?9+ySEly;+HLcV5pprmJ<?D|Vissh{3lf1H}IJcru;Apbop<~tRf!Q3mq~fat
z^wsQ(Xt6>N{WHv9N1ioD#)T@#1V6U*$}~`mE%syD#ODTW)9?O}N~o6`R)}n|IA<jl
zByc+N6VHr~=rJ^UtDDy2VLu=p=hdG+0+TpP;cP|w`pWXK`0h;7!QPzq<S~+BytuyP
zC^!F-UnVl9xgWE3l5fTvE18FCx=Qpnv48ro%};pkEh6mNdn9ZOTJxDBeC&(VJ!UG2
zILP$8J~UBZ!_!}JVER9BrVwF93S(+JHBuNpQ$hoRM+>WR$;a8L(Tof|um0+TE5D$;
zE4_mYh8NIx4vgSOM{pA6Nb#Ccs%&Y*aDl684GhCljkp;kHOj?#cZ*+9D@G?WQ*Ms*
z@Sr?X5tH$rah_i)87|QemV@uXSjvf9j|vQKDTsHS$}NOLj!Cg0J2V7JS}TZ_qJ%%D
zuFCJxd6mS0`bW0>HP)SCB{mXXI`xIn8No?P`$In#-}>RfAX=v&RrP`TvmirvJ8Q_f
znYck7_9TC}YNwzob7-{7>sGb(AG9M)k~1kazYJ>IpkuajPnkl^NZv&rJl{?0q{4tM
z>wAI)dqGbOj4y%j!VT9*ipJ+Qg*28ENGGy|0IRvw5HGEaf+QgummCG%p^w!mGC?zS
zojr%F&Ete0TcaMGBBOm%!lm_gxiq<#ZGa#4vcScDl2>&p3y^mGsBJ{_I&)*#M2Neb
z<TT2vNlF@#;G?SWLZ8mX;6S~fnZ9)+PIia1J<=zTX-u4-()W!OXHj{sN^eo)XFepA
zlv7M|OXEA?!8PsN1C8&!Mm8TNtUu~FHZ5U?bh*Q;dl?(^OarTu*4T#atCPbWPi~TR
zlWBEK9_8Mhz)4!0f1<fn=<-c*o7^)a-s?0)o(vA^<|TsJ`vi=H)LHzm6nG7Hjb`es
z!*VrLJAvgOZs8Y0H(SmYrwK}8i*trbw_xjG&!+ogn0K|H0J4#@LTVp2-Db^lm5d@%
z<EQ*?E0fHiM91YdS-<>?_xN2aWTV|4ds1of+G_;?_om8>@gf}*za#E1T+M8vI8&RF
zHp_vlx=i%_Qjx`KSGjW?_N=W9Yp60?TtFrZ_E*ZZgG+^+0YdeZD`I#0#Mq$=m|li4
z=M)v6#qYqMI6gKy4<Oq4z<tAZo=P~tk85C)4^SZhgX9U9B3!NE#&%RZOwUo9vc=1L
zTWij#(oUDtWbc^LC?$$39Ic#O*g@;O{=JWowNXbL(>;V|0+KyFrX4I<K<kLiEdhU*
z5gM>94Q2O$!0l_Z+d2LL+!X0}SxVz&prSz9>Dl2(c_ro2a^VUFHc5STs;rJla@1tF
z07PGN$(LIKGo;;r%=BC8_a>%=1e#p^$fN>l9mM!s{4GVs6+!!taMi8NhaScxXMLZ?
zIi_8HN7EkK@1E2jNWhKH`co2=2w}QWwD<)_1V^09HH}M#$_rAOf}LspiR4}?ISTp~
z3Eo1ULB=Y-NxDL>M-0d&B9cwb-#VWsL#TuFCph@a=yw*rTPd}tLF?q>@I)TZJoK2;
z$#<6Vl}lXwDmYk|=0#a6E#BdLw<7D4n8v3wP48kTu-1ak*cfjm<Q<6{oTVkwE#-<H
zC!2S;`-|Ppe5=2KY}I;%a;T+`P*(X8z(|fR%fh`~AoxKB96GJGXWDQfe<??H0{kpO
zv6``Jn7_pf>E|3?h%=`PuiKhux>O%s43lgx*gOAPp(Q7esMePrzfFFvRo;lz@Qkm@
ziXb8(*qJp`z-BF;VvLk!`tf3BoAL)GAq5^7Ou6AZxIr_bE!1V)z`03;x+;r=k$#{&
zHS61X=}j9BJ$<e5sRIix+PtLn85gB0`0>v_0H?ZH1ZU~v`p?g!_0d&2&5^U7)@Ze8
z>v{advKmQB?y7yk9G}`=HSp=Am8NjL`5eMQ^qfC8%eORFmf|)P;#*=3D14z(Dxk_n
zjr(ns1o~rujUSz`3Skrk5n1Uk!ADM!{JKrQ6l9+xz%EqkL|U%upQ&RT5M<q1l_;l%
zAee;T0ju`(-m|>USd%NxNaQ;M9)grHS|hN`{YY)|<HcOIV`F|6DZ2*d@>ghQdx}Hr
zKHD)i4sQ501|soe_{m>OId%v9kX<4T=5XONF^7ajnEHZshu!*|W+K)IynZS8WEsa-
zUP;oyBrHy5U~6Aryen|==;`wmP}GoI@{w;JgwsKr*nin0_}2$EA_A30kRhB5{{1;z
z_B7`j7M8)i7Gd(dN?v+e)DbnwoLezIU3(EA`)pA-*FV5-)*EBtz*Vcdk%}!p&X-co
zu6@|xM=j2gACEJs-fXqst^F`;g!E(GMctJ+mAK*pSfQD*;{=-8zeJ$x#fvfamP(k<
z><eMq+Av-cTsc#_jaKaDlAQK(qGFQ!pI@+6ibf5~%}lh`)CRf^4d3c9%nglcaV5fn
z0dea3$(4!@dpWiZI<5YrAqczQvaQV#qmW7|@oCJ4rp9EOel*K<gkG@h9Ms*KfQp~X
z2dmw7xyRMJ@D>~XxHbd5ei>jxi^*9}uIyB~&wN}mI7XNDxi7s|9GyR)oWJ8J*DiOp
zrtn#S#c#2_12tGETV5%RiKp_iRLNW4cTIuzf}P`aM%=XBew#of>C}k5;8iAZ8qImH
zCs||m+t_U7n(fB-DBZOr?0*0srYsIGBQ5S-72})0TiDw(RpUjjG1Fc9lPN@YXXaD;
zfm=VDTV1~H-upVC?GrVtDrE`$!Ii6DjsJxN(Lh<2z6f4M(q1Dd0ghi0v}*WiMz=tC
zYcX!v8P;^l(S$D<Nq~|*N==%~EPhcloRk&f4RUOK`--yAL1bb1kD=j26VE?@AS}dy
z=3u`5A0Q%xCSFUw=^Lzx>s-u=->E9RgLaGt(Z1YQbnpVyAmIgxzb;38h<g9kT4PO#
zUrW<(UeT;%Qu_032jM$M0jcR)*hrc1YHNop;=mI4T|2WUZGDtt;|#?`zh7viKS-nU
z9$Ts$mjIWFz@V~%`3#bCz%VwbT~el}^_<ChrMY!WDS)piBxOsd02e@uDiEbSP_%I%
z(SPHG;Te<dFr%~!tJc(%#aU_F=nKI?J!n=czIOZSl1uRG;<8Gma7;+e5c7k-bB}Nb
z)l}L7x<yNC*4YZ8U5OpWAtq6+!k!OSz-7-5{h$54GvxGjW@RE@mXXymfyb-UH|3->
z3Dn#0m&0`fMcY|DP<c#kIKQm)G@Dd8Wai|$t1jm|VAet+@@uR+-%L|$GjOS9LCXKw
zMBkP%Za6py%@kxdfPw!9Fk%pepUnAuyG3H|%5h>NZ-=o6Pu5<Nfms0G#=ES0-*}6j
zUP#Yy20FM@2ow<Od}ESkTKeA7_O)5WE`haSFbIDoMrveJ+J^5L_iS}#pO|&ZpQY@a
zz_x#Yds)wcZyk}-GKZNFo~1Yjexj>amt{Su-Ck~Otr?!<zuhPEqGDJMeTwd-KJKQ9
zE#JAvpQ^vvy=y+>UF#r9Y7Q~C;?pXL<{9dxkuB4{m`UoFo|=aAD$rp0c^=T0W8Z9F
z@QlgE%*9zv?^fd3R<CC_TSD3={5!)RVZwiE1Mc0u;-*tL&6eL^H-GmlGM`f$;CvDL
z5d4k#WxZ}e9&<!C*Tm~17X*d8#>7PzW-Wr7@wa-4xfybsoszvka7*r8#`E<Br{sDk
zTG<-wB3{nQ8j;L;=Gb~aQmu2d^9dr?Px(ujfqi}{4OjQe=O$Xd*C5rX;W+AYzRptm
z&-L;;o2jcd`dHhm=en|#%-wh1@LiOqv0t;&+j#~W>_Vok1EV)qw=;?WbZHj@hN+nb
z3c`?!KlUpSk1oNS^js`pHmZ;~D}E3v9+t$RO~b*=%ZxUeEM|^BF-u|teb07Q9K0Sp
z>L?Ib-{vl`>z^yvNU|mAT{tGTLsGsM=Lk9YM9j*=yu)I4bmuL!#}1(31E2i^VD(4n
zx_cz$Ui{%g>2FZ>IV*5ENo0+S(q3ddl<fQG=FLBF2;7VZPQJ&*pn1-rZP{G(qw`eB
ze@_-SkO+*xo(J+B8YKFu6kL>(e`aPt+q~0xrkLz~-vXJ5{6wdqpC@0Mb!Sk&nN#Hi
zXvd+pCN;fh-dWO5q{}2(>_W<^pf9=Z6gl<ppqF(AATP@&Sg&YN_@$q*$zYG=sS4+h
zRG6)17j(8vQ|%ruz8&JOlF&Z0l(+(I2{<ZT_-+>GRN~z|S@yW>?>73dI1h_&@CCEI
zKO+;$=xxME=!TQ{qLS!aQHhZHm4di0ysDfs-SsXLktQ3^vB-d=viM2FgfM;A&J;;!
zvYYs1STE~F*54HS^NT_<YN`Ih{=((t0huV)wTNU*er2L~Ck4p4EdBEW7;7+}YIXI-
zb<4Suzoh*FG>~pjP1`aj3P??1mq0y9bOzaxQPUjCf&zSld|_i78cR3_p%S13fS4d)
zeU7q_O%e@hu7?+*lpJ`pFQD;S#f+wejV;@Wm~-dYy9m+!{#?cPHRev0U{r0eQ%#HB
z2=DTnV!=u>ZhM)(EwYbg8Es<#po&}n;jJD~kl%>PJLVkIf~y8(pmu$Y%w&Rb8>Rn6
zfj<`9{&sZv9{^XIZ{Q$IZ9`@JO<Ym(@IQbvcntscSWV%TBDqGHI25B_Y*}Bvn#Qrq
zYbERz(NbwDdA7FGWfgA2p;*8M>4rPKfPFTWoaNA(B3@A?6*EArGUkExqgRlm*VIC4
zfZ&hTSEhh>YpjXx9NM%g5plnxc*$v+)}vN8fRhnZ2tnR{%3PeT_3urOj<MtV5%GZ-
zSiiyX&838x`5}D25kOiobDbyhtI&|zOFe-QOAt_as+xUE61kca=t#Y(gT9LSghAJT
zqoinuTW&-2Ko<C;e4w*e4><b0ij=!2>ko}1k#FVHO2Pohvxiiemw=y9cs0)PkAD$R
zb>wXzDr2m<i1%qS0dJ%){@8dIg&p5cX4eDSC3IwP(F$3^upgkZVs{fcnQRDl`a2z9
zXlJ4I2<x9$O7vj|DmE{3lE-Jr>ME42@d)N5g1O9en&M`b3lk23iOH6V>ry5=EvaX{
z<XaSbmqLWPiJ4{lA0>BASHVbzOw^=c>s$igB|KJ2WH^kng=i6B5LQQuLfHnrnrI3u
zurnMY{mU~AUE({C{eqUG#*4EJC2XhKm36!E2;XOGrl+2*2ykXeu<gH9lB%<m$m=Hu
z#ng1l`0r2~)z0-Z*C?}<>^hgW6GgRe+r-*LeGTCi2b!4nRqXiGn~PoirGp!vl9gWR
zo+5LEH9Rpt_g6CT*f>6asQW0!e5PGm0W0;D9x7M?3qX^33r-3Ib<h?dpd2TOaWt@_
zsbz$qJ!3k7VER=t)bT);U|>wJ=)0SQt~JRKgZPAcypx8<fd+bfpbRJb3thd|NgXt~
zO;DE3Q?B4ekC=jhz@`9)J-LhRw1~+tY%LDy{O<?`>Wd<@8&Gz1e0Q=~F7ULV{f!G)
z4IrTGb`e6Y;~1lbYPy?%YUrRtwc&4^)BxrlN>YwkYU1azxS9;GLqz~9J5tMmF+~S0
z?gFF^fub=;-03wW>-Iih6_~83P?IopvrCK`Ok_2!EL+ui0qhm8^K7pF@I<F^s=p`^
z1U%y=0q7_>Jng7_iX`UfVD{YCLMZXoY04J`R`nc7O3c*LN`{Oc%|E~r`n5_rDEnM^
za`WhPWG_jGw_g!`!GUt14gr9@lrjEubxHRI!ZOM|<FX{>8xs{chQzygLea`CHT)^+
z2gN7$^Z%lw(>5Pkx^7q~tz4Z>l5uY;4@L9^mzSNY9S|1R?j@E3ue)<{PO3zv9@wg!
z{6>?yxLbC10vg}PZ-E3CYJsRW5sKKJ1_1Ro>BnLHt2=MdyRpED;!HL`SU)N24+j_T
z#UT0nVZJiAJ^^r}em$U<^=alhHE?rVY&@3gPlxCUrf~*mqDZD3G|k7-mXKqhL*s?M
zBq3*|a5*Zj&tq>#e590xOw9~J^jGf;tIH-Jd%mLOpV1st-D=E@6&XN~s7kE9e*i*;
zNhXmyy?S@D+YQOE9JQ<BDAbu~NpXWozCTR1zb6qq`$P49A;T0Tt#A8%KzAaG_NMap
znpySqwv2<yeEeO}e(=G&URvz7sY`3AALZ)BgM$`&`B(IYeK{wKDtz$nuWO0b^UCz4
z#cD~A=1R__7Abs8EMFNSW9V#jeX!5$y*x^yN{RXvcu^MhC;D}pobc#?7hT33)OO0h
zjLgtXU1C_+@7E%~bmTPmg<W8lTg}>#HrfhL=?9{;6~mtH9hn%mc7s_-k0K{=%OT^<
zI3p@Gh}*kgMnOES#qVSnLJ*GJvHh)T<~$^iuiAe0(c&a4`=SJUc8mwcj&2uZq#XzK
zHmBT8hxA}K_Uo!U=iawFMrWfh=-T6}0$WcR`^+*0KUdecY8~@Se)>7n7BYCZqt$HI
zDpnY7KrJl#P+paZY)L(WGBx)JKR%`#J~)#aXgW7*5vc8MM@WAT2oKuSceJN@yfCaa
zhc!aoD>s;gFlN6oe$=~e7Oj}CT(Rg6@~*^IUTGB(w{TudX)v_gC(vbk=2c%x`RL5n
zV`>mx$5->S>8!GAA-7rQx7rYNd*3+njgQ1zakg|19S$2VL>B4hivZGvElr8Dq!f6$
zc<{S!@@!fH-o_*q0CPVzwGp3Sx8df-xKY4r`-jV+%ZW?f>lXmw2H(U>r0J2Q!byQj
z+Z0q&SU7qUKfJh#HoDB)8pNSo$_e{X=+6=FaWDxJ7Ga!QD&!v^_bd>t%<G``FBl4L
z@nBFANWgh?OfxO~OAFash|XcG9>c2IGHH{D|MgCM*K;81{nDxF%<M!z@uustdvmWL
zbW>weysOU3#u^^@B^*JA*^qoCQKXU{ZYq(Td)-x$rzFIai8GdJe%@S#ry>h<*mbI?
zYoeUPzOIbudnKG|TY@!NnX)*@4~DnqIBi?dSoernW>h$VbbL7lG)W7a`Q4QnGZ~rt
zl{K;=)QJ3iwzI6~FtG)>aV6q$Z!Wz@sP5l@8j}3=Qwgt|u1SaY$qi>kUOuK`NBCj)
z01Q1Fo^gEk$TC2|Id+Fpx^royMokbR)T|k7F)w!Tb(vY7)Iq}6>fHwjt#ffh@M$TX
zZ?h9yvo%5#!q=ir;^KSfdp9e(3#<lKsqMSLYSP(T(+fl02?O(3;8BAl4NVH1*9W@k
z!zHUw#bIlvDWL*u=Cm`OO;Jf|U!foOLyjt<OT~=}dclp}pZy5-^n^U9`~rK+yR99}
z{9Fu~Yv2C%%PA>4<~a&a#|y+w)nrJ^Z3zkx$zz%`xIi@uU)n*ka}8xhB`1$XWrX=u
z`&KR6e%KjG3=uDZN6vJ$qP+GrtbW~1&;i-#XTBQafg~0ydwmyYNoEtlN!lBlsuAu;
zibF%jZ`2PPp0s?~?CKy&&p~yM$w;0Jr%%YKc1<t4a)x_>qjw7G&$9Lx`xmeRXZGk{
zE>jksZR$b--Kbx+Tpg2-v|^zQN^JBfp7RHJ=t>XxAA`43jXd&t%sx18X}<hPoxqv$
zm52(7>x2VJjFH+O#t<({AP~F@9pE2m4ES(tqWeV_4eP)x-eoVM2D~BZrTYhwv|NzQ
z(B2{~^FyD4x?5#6+K4k)kxQV}&8s=yYb7nni?|w;n9XP8Ju_vZW-(kn@Sx70MR%>T
zXTkSvkn8P17HtuX-6MgQv#nbBD(#-{Rv_-V?A@!`y2iMzxBROwMFj=b1!ApFNRZD%
z+_Wd_-MpLOUzZf<|1xNTDbcsdbsnGU^sfSuF9*NX8l7WF81J0H8rq-}gImUahU*ne
zl;F*>!iaJ-?PM)-_rd{oLnIUBh&^k^_`spt$oM&ta8~frG|H>%VuuM~Z({bCapoRm
zRnISwor=_5TG{=k-x~La(PH>C!JQ`1@W*s&!Q9DL@$5eW=B0sC_0#x<+sl1c$RWJ|
z0tzDrSDQqp(QYK|3Tm10#@K03nzYNJNO)HnZkb{AW6{%A_2Iz2`yhAWcZSd#ju!-F
zU-C$IKWvRKN3rE;{R4pN+tXED9jSSYw&#>(%nbuMUhcU1T5`pAlN<jXbSP+%l5FOc
z;Yl65^;(F2$#!2{>F{eR#ddfgvJwn(^t+oWajgJ2hLh1>tj8`h>5cP%gt$z&VUiWO
zPq9@$3iOn*pgafgzfQh&q3df6${`yoHF=EJBU<WKlI)@wF=tWKyZ({B=qGyW=fPQ(
z>BS5SIZmI4XHqgGk)FR0hy$YOEjmIqPE*6ZKlx%MY6z>k443@^1Uo;YwIA`olP=ig
zP&jAPpiNDd`sIg@?P5PuWwF?8&8kFI(^XL(q!8pkbE1~*U|yDe@t6YRqHpS>WZD4)
zO}>67>=&W^cL>k>^|7V1`p?znb1sxf8Z;HMqTWk8@nF(-+&LX=3A*{>t$Ah4Ec){0
z$`_c;K2iFX^t9uP<J(5A_&~F{hh8HoMIJMLh%HO#m{@7*r@BNv7d^FXIrmx>IX0jl
z$?+UIhj~AFmO*)p8wTz+ztNu2KS1?SZm2d(O84)|lV&=YYJk_3v&;L3CG=%Zm%BU)
zkea|4P1ys#6s%j5i2i7YRGn%rO_8n10De!yb*RIYcfIhio@_)jnl=RrI3yijvHJXC
z&w!_UxKbw$)7_bK=g>3|W3g+4OMm1dvmIM<z1pdhf48>Pbxd--^cJGsZr0?*LD-Kp
zDAULhnGECCt{>X^!(XFuv|z?0Si_gvAOXBA`y(c}M$Fsae_iIbE||7V0*vE0N~o}Q
zepq(r5*)OW&x;2(SIk=~B|J;*9Mf?q#(C$FDb}^AGtNO(&2i@z8&K-ly}fV?gdBl2
zd@d?(-W)MB3t#gc+On8oF*aW5#kVn@DKsTNHGh|dB?PBk$y}>Qk|N!Md-b#5;!@ZX
z?CJBc4xVO<VNEtfRaQz{JfA{lKby**TJM;=#-R+gA^0(0;^Qh!Bhz!+K5_LT&+u&*
zvcs9FTVTKCs@c_U_9OEP-h^YSX3{?`zr!nq4mr3-Hr=~J?5R9e4lOG_kW*drxv9dK
zcGf;qA+P5kmrSG<#}rvi(ET?1Rqt{AA-l<;x@}K*LcvN?l<pj`>Z}qsWr-%E3^ggB
z5kq5sD0M%T*OZ$6;|A$Vv+uC+!42q@9XV@ovLo9tix`kbb+{0Po!N&w>V6Tdc<E~-
zPC(ub)n8yVcfx+<qr2FcAj7%CQz^+zdWgVNrB5~flO}LBo9jQ-3H8k^K#XR*P8*K!
zVo1y|+ZV9pF2`YsEqP6q1M@aav6@mD{jr5wsm<yB-gS6fk-zf%rSbM+;t^LC3eL^#
zHs^R=->?h_DL0u=9AG}*Gh!N2j+S}jGze2<smcG=l1dpPI2pWm9uD8<M0a<7i9AAj
z2JeY@N|k2TXc3I5S#v+un2?I=A_>zEo+`tN$mi3I#l5cLtg@>c^fN*%gOz*}9AW4(
z3QJd|MjA_>dfb~qSzPa@7t8gbQkjFPyF;KpHN{$6qlJ(g>h&fR3L)Q2td!I#Txa7w
z!ibOmQuUo4h)iYd<x7EEgC;oa?4fH=#6yq0J~ZMGgiK{ho}1As{>&U#nnV)l2fwaS
z4;$x-`$DR8ppLDunK*t(!&x#)l$NiE&25{;KZqHOQ+nu9^X5)=0gYfxtlWbW`vsT1
zD_?rru4=gt^A&npv7<wJqJGI=AC-m0`k;c<J7Tk$1Dd;Z8;F~wQZN_$qN&;7hi3jB
z#^h*f_(vtpa=wgw?#kw!?CFWcRWnx#AhmBr%<D?K%xi7xTv{raOS%U-#P8Su^ff`1
zF`Da8e{oAP1mRNT=>e|jSI~c}fQ7|Gd09TbubaE}6$v*m{%h``i7U6MGu`J5+gUKf
zm$jaI>bjC0Q=VgK?0|D;wiP>9r>yHy8y}NapIvY#-s*Gu&8&LA`jqYDskGLGG3{!~
z(C8<M1+5~>3Ff>_G;7U1Cf3I^tNp9l-CyyuhrU$ZtOz*a8a?ZOa?meC^Q)W(w>w4|
zql&V4v$Ttn_96;Mi;0E!NXDvZ4b$X%PLud~e$RrSA^H85U(b&E)N8I+1bTxK;?{X=
zl;sU8Owpt7E@J%v{{XKZIt{<Z?6Nk3SLnEz-hP<F%{7^CNa8!t8CZ9fiighPG3Kmc
zktTj#k1<*NlSoF{Iiz!h8MPI*+|(hrH)0U|hWFMBy{CpW$)|MdHWL@?y_4}Jn_H!#
zx)EB-w*phmc6Do+AR5kAOI6N4NfvWgy_V2BlMf3wwo=-GWB$!c5;H2+;i0W{y(aZ2
z>CxN$WnPKtApginbg>bq#d$?HeE7>c->&WSSF|p~3uM6?k82~=RBvRqje2ZW6FW;6
z)|OAJIrVFJ$IK0dSU0MP%oc}Sq%Coz5lnsXb7_93g*4k9{CgCC-+f)2lr#3UE2PXW
z$c~#5xG$hi(($P`vuZLgWBf%$1tFYYYJX6V{)l?!%6Htl>cs3#g2(U4lB7s#{70@3
z^_l?k?;aTbV}r||#Y<*D<u<Oim!y0-?)+&3MYo}yLcS8rojL{52oGZFI8Lteyq78F
z_M}c)@-@0Qu8S1+?P6tvt?x=owo<e12x0QKwhw{e33@>j-25FH@olJ-NQjVXp`B$j
zdST@2ranc3&`G%_4=wdC4es)BoNaEP@FW>pPP53@>AOKzRo)DZv*<S*oJ3#pO6wzV
z>`mfkcBu_NId9hR$PmvID$Cwt#0L)B9+W#6Ds%XoAj@X-;Y|JWY*lb+6A=;fN5?q-
zfdd1g2-T?T64mW*^E8f8D1(=3<nFg#IdXCsHdg7$t{;x|)@(4oJg_6872-!L`glW6
z!I8g|>Fsj1MdR&;ttX>9v$W8&MFQ;#c#8AT(<r9gj3-rcOOYh`f<{o;@-T252h0SG
z5{S}c9;(J0D8D*+2o;v%7?^WSP-R^bIP1$(JZHWvzb5)h)Z&ID84{(jd%RGyx|`e{
zm)nd<p|;*rPiEZk<x*Q0H3e?wpQ3;!-6D_+#v-20)J@q6xqS}Gl=n6h{6Ev@$D{;Q
zxR-d=C>IY5f#`qrF)n(gY9K^lcMZ>=DHkk7_xE}+{DJmDf}pn5)`Bq2#j}h4<1jr1
zw&YG4PB#fi(EI0dZa)a#j@RfClKSlEif}dr+2tjfNAyXjq=Q-KYo0V;PAVI?Iqr0U
zH5862y1&8}s#KlPWu-i_?m+JR5Nk=jbu=x$8x-tC68R)7db$?gwNq2#g6Yb%O-j{D
zJgVeu=<tEpO<uu|76CatCrZ=;h}j@l{u+o^bL8ylPy03LEX^9NJqj;~F(yupc#S7^
z!ZG^m-@QCoaH<IO`BhHqb?q*lomwXn@1sYlzQ>dilol@vZ`WjuLwdU(x;0mcwl>|r
z9YX~XtyC?H>@p|PT&xF`vM59_EXnTat9AUjD5scP%p@6#4dWO^Q5<mz$C9yf`q{?^
zq7XO?U3g=q6)cHihk896zFnSD?T&&>me=b0SBqvq31?}p2*UnT$Tfxm?5DpqZj<zO
zX<LVPWGk);)-nYoKo%H?3!@HW#t04O{1wjMr2E{d4GfAPN)X$C8^+6JlASds1uPyK
zdfx}Zm39UrOZ3G&pY$#bAeKMxm@YQ5Ig-uHfBlk2j;DO0gV~ibU*gdu@4FT$HK;ZY
zgPwY*#^g{ilVH+TY@lDoy>Gh+?pY68o@jrsjLsK6H!SGDlxuuS75D4{kn=sqL4<~}
znrH6gGX*jr{&WLMvLplKfpjYOmS^(ef}8}Gk{r3_+CaxA>oX9VV+>3b{YOq$dAUey
z+D$u030zG`4`0(75)*32>+NznS%K(R^;OG}aaZKuX68dLQ<gO7#V&Ql|L*5VqJ}3@
z+F7~S)j=M#Y^tt~KmgIgQpltvJh{O2Ey2>qqXvX=!rQH`T)%`xG^rbfCrK<Ro)b!6
zPRT6<CUbxL{8gGT=k3JE#mlcRc;-p@^OQ>{?~D?a1zNalLz&uxh06V3+!QOwLSfwn
zY)jnDW(UyIy$*8ch821X7Er*mNqL-S&Sl=WKgMT}eD(pa-;&=}iyPH_5<3z6ZZ~Do
z^g}$2C~{PZZ>E{+II5*6lA-zMqEIf=sLg8b<#m<wNk?9u;{pK!(U6Cg5(8jC3X$w_
zI%l{MdKG{5RU&?`BMQ)O=SrUa<Og#k>+sb2j#UlWfo@iIa4n1Dy#DhSbe)=#^qEt$
zvf|SKZQV-U+kolVBT=N<`J=@8rWttOFrH$c+QSIm!8ETOyj|!iRL5hG#vgE920kZ-
z+UL{3-`d3p<AbTj5dkt^J6PW_Z%YZYssOqYzf=De>RR$I)@{x>qTSayp2fN~^em-l
z<vZ{AGH%+7h}tT>S7+U#<BIOW%*<QH5!}66fp=F?Ew+C;@LA`&-5`3*2O*kzHe^iU
zj#cmGpETZW{<D&yPN~NAteZjq05K27f)u~L3KBo8nGj+C^)GV1ira2(Q}vOJJh0qg
z7)5KAN**0eN~B5dBsns6%!RmiJ<&d#)$Qq(V`cPB;BC@09MX*s2}62DiT-rGci(DR
zQqqh>42Qb;mHcoog96%a42HESKm4fVRWvWKHf~J@DUz~0BLT_&kDg)|`szu7IEz<)
zUMAtUfXUUI9JA15@%9LHL|E{Q)MG9hB=cpRqaaM%O}ajPXEK=-GGb_vhD=O6Fc0Gi
zxeh^$JD+diqIJ3PI%C9tpK0Dc8lrLOwOwJdBDpHN`v-`%36mb7X+SQX)lqLZ)SCsL
zNsx|x$acz!mE^qUxQfZpnlzCuX8xltxv+ibTuQkk5nm*(M+TY?9V;mwa@{=H?f3L-
zKiA>kx%o_FT=Lsfb>%`SN5D3?yzb;GN?<;A7yf{B1Lag#3QwYLCq@stv;H_8!`qxm
z(|&9QXWC7K^~3XqFjQmVzn5d<88_=4dOoJXd+m@yZ2^Ca%ALfUezrT>`rsnB45+89
z#*ep@nz6eXMexsiwR=m3Uas^kQWVRH%RCF!Lv7cFdOZ*zL3)ebBaBC)l$$`~MIDLX
z1bYo<Di%kd#@<@;a@D<{mo4H|ZW;*~`Ei4YxK>P!&)qJUiTRk{#7%$#qirz{RNiO_
z6U`q~F9v6PjpBbQT?qrvxsoP^J3Yo=F3UIJe{azxipC6tV*Qfjq!B+9DZM!eR3DW%
z7c`1qibUPb*g1>_8LEM`cFSKK);jym&A;Y-qH~#DC9unVbpea~N{(+B7g<k4KdQ~y
zg5tYVsBPj>UKCJ6HN115i82WiL8V$is51wOADTQKO8$lGVYpZ!jsg*X1?|2|=ch+u
zB#FT&>Aef7eRpQE34p?FJjTupesRQM@g9~<v1eTN5-DDma%;0^m;Leb2cg=i&)<SD
zUcZ`Q3>Gb?$5PYbW#3qcIM4u=9>^Vx0HM14q64{@8wkJ)j$huLg-F3ra_rUYY3kz+
zot~^fy*YQMCOSSr{8nPjcpzn|l?>mGknYmv3#TP12lPpI)b~$)BV)^jdi|ZSrXhtJ
z9SjgPZx=k)|7l^tKXi(;#DgqIa2i;0v8(ij>g<}#a>>@t<J!wRngN|X3r!NMialtM
z?V1dS-c!uh$DE=R&Bd#%^){`21uxI3pT9%2xMn^nyCun`ncqQIc`iJS!%5zhl<Kng
zB0i902)V3WEhAxyk13DK@l7N-^NT8@+vP2!u~w_X0S8*dq3xedBL)_DMTN+Evg<3K
z^@u(?e!92>3h50YPwl=BA)kmP4>HBUo$QE(1Pk^(XvE+Wp_4W{Q8qg|asdVGD#{!c
z*JtDv=j|0O3(M)(;oIK(La%3fB+u8l*UL65lZw^6YQK>BOJpoH?$0^I<3M$LI51m^
z<8}`cs7rQ*ago2u2bCAduFv5UeEj7@ab3tCCF8Hd*GgC=7!dpnU6J|Q(zwlDl$|un
z*pKiH0u4Yn89Msw5UgEV?3#T4WhEBdK~@<?L9qkl0PD>=cCT28aoymeZ(!4uY}x~b
z-ptcAGo2LUNuDQbWTuXy4Ls2{fkX@N;IB9Xo4T<Sj~vE+oB<Kk)+Cu-dpUzuc>3>7
zies?YsDs&QhEIM~qKj;(0e6o6D%F3=YsBz|5tY!U81oo5#Obj=&K;njSMLZoUIp&N
ze@6u9du&$nOMmFEGCBDNcnIL=+%%k+8)?^c=Tj4tzF7HuhdN!F1{8(z2W5dq1Ye=A
zCnB97iQphwLO3sgN(Kge&6p&$_si$6Nul1^MOQKYa|hB0F_KADCXzpBnlA4H$ALyL
zj@2psi@)AKzmovG)B>-^0u=_v)HGJTWbvPrA8_U*487ze$KEeu>$x9xRI9xUdB6IJ
zq;E+29&1zDkMc_G-2ic=cPU`2Z<ceh7zVFlV>>GCr(MN9B){0S;e7o}agLj4y+Yrm
zYQO-eI1ZH&`qev7;zB6RMIn=5?&<irk^?%whe{!?*K?fpe87%W3EJlSDI3=>U~FW&
z*9yywZXe<67nEV!u#`BjKGVs8mfsSclBb<?YUdI|Inq`houZ_9WtJI5o=6_$j|axf
z91IQWWVGIv8BWLELoy;-F4ozyNE)ut$aNdHuBgDc(0nsS(Zw(`mZJ>SeXm!r5+io>
zh&^*yC)XRsc08lVfZ@d;T4mGK<0*2jL0+nDI<*lfV~!T8JW=^`pbmc^@kJh2wcv%Z
z<%aH8V*0GZ&qq0?SFTdjj;BeyD!Wo#VJE&{5gqfq@5!-f|EBKNXvGu7@pW19?OD8W
zrVu%%?kFd-NJZ6N4y;~QlI!wy2`{as6N4`_HJ@*HVYqB&BeoYtPkomNUxzA}2*nC1
z&#yfl56oN%n~Wer)h~?`Istqr3J;Y6VDHIE(hI~21dY)X)+1CLL+eAg!CDVG3?3?u
zUP@v`=r7m{s6iUQc2?;WP#im;08a9}K2(=KAQv*BdYOwJcj0@TpN=C7J64?uLtBT6
z(l{=k%8_*UsKCSunP_&U#7||>HgXHvvEb;T_}g(Q^(g>dB6Yd#^vFXcc9MEP3J5Ye
zjvhjiAMx~8&BsQ$p6vVTtt_!2V`O6qDZg3%xgJ`WiJIL+5o3u#CoCU4JolvEc{;85
zzjm<g5<(-wX!Ab0q;UmKKg`LH^1Qw{6=pE7Uf&E=D1fwjEEJRdz1U@1KnU4vjufDy
z5ekV?kbrdO^9`Q_K?&VYJmY^D%>Sz%=dfMp)4VdPk>s5S+UP+a0n0jq%<U341QQG5
zF2nE_--cS#W>oeX^I}j(^fN{t0Za11?@9E%WK!|^F?~y20#Rh*Q5^+XnI9P&ufI!{
zUI?POf!$6h-cT~p>u!gVK&I5f#q~;Z4Fy&lT<!JK-YR;9QcM*!=%s1kUy%-dQkb~p
z)}36u7Z>rYI**jRH{6c0_Hr&X>-GL)r%!b@ze8FU=w&{tGwyHud+UhS{#x5qmx4CZ
zP$u?|O{S)EYyd4)x{~f&W+F>_*Hanux<^zu#})Ob9<1{b*Wx!qqb3exM$;zGAlZS+
z%>G+8=ChQJ`6DIFwGM&Zy?Aucg|{oA*A!A*Sh_dRmbC1NHbVUNR`5>!80oSj6ujKU
zl=_#Mjp55ho*~4$SrWeQ;QWqI^6l*NiFr9D5yPkx!d0iyXn5Y7bY|tErh~_s`fIa<
zdmAIz-m9&SRv2u$HH^bNm0%o2<X_ag6C`o*LJMABm~}*(Uk|QpF^$M{8ovDp_$8cn
zC7w0e6-08<zsx9#cVkz*VE$5nGuU~h?Hys{NJRZiTA|3P5_;BO($$4X-^AsXdHaDS
zj~unWdeWnBjuHjsCm$o@!LBg(`w-Xixco|)Zn%w;?&8te1|a?SvD-xj;j^2foo;Ap
z8jGXr=KX2>p5<b}gT}<=KtVXgCUNR$PZw$72OLF5Pu49;YUN02I_Fm+F;OEI_+?EC
z`*H-9v$O`X%ad6YwZL$G4i6}GYKkuL^b*)CrBQcEROP;A&r<u;OtvMP;j>HmYbnZ9
zX<Ite%Z$9Z^%WHs^FpxxEW|(i*yyAP_F7m3;`)wRk!_T3FG97cq@hd7Te4H$D?t^2
zN^Dj#w8Y*!H1ffl?Pzk$7L*U@{!HGkvpf=@m)1gKmhAeQk#{w3FmY~r-tJ!hHF-%%
z@zE%zQt*MW@~!`RdR+%#MQx{Dh?NJ_68+uFme<xp(zV~?FR6*Obr&0W++?C}`Qf6M
zVLsaf>bn076A~8wnMkMRL;rfcy(J%tPA!akC_9)V3_Bym3pv>+7?gxY&~8vI7xE9F
z_A6~UymoaHd`bAsDVyx)II$**hQ3LE@qX>m*?7{xAgq<Tp*qogQM~n!C>{TkTz5Os
zCS1olBg`_=NDnSY8g<^8q%8TY7DDK><HmTa-u?HcLMn$RLTfuUG1`Sdetzk5fD;v>
z5xmwh_-;@NIIFl8jLvPO^<2n*X4R%mm;3#`p{JSUfLpJOU!TsYp13C%r84#;{&WxS
z%+=@-Jf{&X(HpTFA25{Nv~_m^xz%zoR6A9_r!a_A6+SW@+2xCYeEVBtwx?VB6%&)6
ztK-D7eC@02voGM+4E)779*vZ=o8HAYnQ|v7M@mudr!u;vv2V7W3sODLS(!#HC;Y-6
zgB6V}PE@H}UPo@ktHtUdIL^2P#IxJK>8Q76`f%3rBJE1!V6OsGYrZ&l4;N5_Z5v8#
zEt0|stq)AmwGY2NyMm|`<loKMKy`vZUe6vhbUsbcQWy*-WyyX2^0cdVO<-|H7}MJ9
zYO%V@v}*EePXGAkB`HDFF@)dr3>D}FlEh>Y^~ix+cX`w_bQl}#v5pEiV3olBWGPuj
zfU^1O#QMa+Nn6*=>EMw#O(fh@gs<L8SoC^PTSuUZMf3L?+G&l4X}ci9H;MebQoXMY
z`AL>kkO*&B?hCVl&4KJ(U%1M#p&{+N6`FP~@%81r4-v?A)2WYEhG$2@t`xU}s}tOj
z-hm<cMFIqO2^FFV8>AVZUv_!4%-zQL4^D5rNdE`$V|MxBFQlP#;87<=yL=$Tm0)yc
zlcBXLd#qiD5N`gJ+qbmQZmCQVQwZRtO~oj7Y45+xFZ@UYh<?lN$sspTN@3&EU(#^6
z-DKRElL;5`#WE#S<AZER0#m;p-|Bavz01t|<J9nnP}}Qm+?Gey%*B)y&MTocUcNo8
zIM4pFUnv(C6_1Oy3^6qOf3PKY8#_=-{LV&xxl=sq))@bVwzmjt^9|p$gA`hd6fN%V
z?p7%70fJK?xCbXlkwPK37J?Rcw_wHH-6?Lxt;K%B|M<4^9kZEPyo+R$-IM3Nulqc&
zDUSa7k9Wl@;UsuygENh1P8EMD=TFbUKXMSUa+)xof+Xj!tRsy=RGuN0_`Z-Kig$Vx
z$2#+tD|qr)hx0ilq5B_-_a(4wmu>fQc}J?_#bO%{H)zZs!YWS957456c;)Tyd!=xe
zj~8?7=Y%5jlfnD6h_=TFpk6&s3x#*+Q@@<ewqFO{0Sm7GZ%ZDHg$`B$yhJa8+?A<&
zDl)EbVTp1j5psS0ecn!H4rz1Zx`i5B2<r6Q)}<EAG_>|+)5SB-<-Y3u(=JSk=0M%p
z7OEcKa}({VO3Tl7oy9T&QPyf<pHT9>=^E*H)hIPzNGfPrvi}kWE+{@kN;?0(s}{^_
zDp}~;2DDGzo$y-=k)U6fV~jxK1~PxTuOJBJ(_&1>`bksc%-BC&n|F6hbmrBca}~7f
zDdk_&xhLXi-4yLWex{(a`kt{VSuja-vk~-}8es)Rdl0r2nGnYPSZ(gGQdY_TAX4%(
zVOjZgmjBsWFvi44%fMJZCLVoHf6`+(CLh8?OfYCsmszEBZgSAeg=2W~k;B(73}flD
z1Q~kuznjX#8C@G|)q*^j5GBSu_V?#<2RaqX@qIqZw}hi;!;)pLpQ?*Ivw*$54}1v?
zwABE;$=3O8(=RF>L$yCddTve(w_PuyU65(m($3@Emw*ahpP0X2mo0vbYBQUpV67WL
z4NluqfEbVDxXbElk2}i;*h9?F$Sf$`Lsc9Y>bZs?WcZ7jx_`5|f2u}JKwxe3Z@~6p
z-qcr{^TK5_EBrB22Mdi#JGSwXA`ifUO~D1Rz(xlx^5->gP<%OkERuNeN-4u?LX*u9
z#c);L9mQQ8+75F0UyD)YIBg!E@E%zwzQ8l{c))$7-He-;ta}}T>ASxZWUJvSuOZyF
zHAL9{)I%z=`C(^Ge~mEC?d9BNqzCaI0RJyCYL?B#?&|Nrgn;Ay!7zUX%bt@*NlzX(
z3Uq<BEM=&K>dLoUxpf=OU$c#E5qQVaIODCdZLSq!8Tp>ViE^6HB*|b;J5zgj%5I?C
z4Y#uP-*i`<1zA}^AB_`Z-D7tZx7>;tYIo;ibb*a0#(Bq^b(w9p^i)2&Js}8u%W2j#
z7evK<uJJAcx`USTuB5Fd**7K5^6yW9_7$0N2M_T+Di5Iz%Cu_!*_&z%2U0MJfK7ep
zAoF-Ie1GF%t5^QaL}Iw2l$=PSc95{3T;3=T{El{fFT=oe+?f$SPiT}juAL={j(I?&
zMApnzu@GAYqaPldt%`{|*{Cf(k4SPwN7c0kvS7MEk-GEAr_iBb@^^!V9?sJ>mKMb;
za2^GSQhCJ2tN_Wb7$Z$fS0xG6D6r20QNm;!XeAzM#09l#LM;J8VO!-Y8?8u^o6dvx
z3EYDaJ&$qub*fPVvQevvMGA);ah_9cqZWgYOfbZ(x*!PxBDw6{clJ>PpuMs;=8Ka(
zF9VvG;rpu-KV<2`MG@eDttLqCP|J~|TUCYk=0AY#0b!}9ZGutxRfW%Og%W`js^zY`
z9`W+=+qsMRdVB3!ti<x+8;UX)ycGo-Tmudn1j)4oD+j*HT!pnmOE!1xr+;KMRZ$?&
zT!peSL9J=W@!EEQ*6?45Q{f!OI-$OF58_thYl`D>jjWTX96_fAH@&;oC$N(X5#<L8
z9}w0!J-5Qa8RwvrUL&vt<{ZI`?XD@%maSI|Z7d%rNdN#+&S%PV!Bl9)IVFT6f57l?
zhmyQ_7V~phHaK|Fa59<3F%txvbmgaRZSu!uMn5tnx;E-s9l~CZ6c~R!hRaj;-t~ob
z-4f!39HO26iZq=u4v3*-|LwFD_VFRBv-*Qov+bT~SnC3NbX!e9rZ@kI_tF>?BU>lP
zV{(sEak5dyxtrLu5$ihffE>G#q63lcU2Yl6W5f}Zm2W4)1P{|qPSJDr)9KEXobA_e
z97=pz)mX^t88A+*=hTlWzdccJZoIbAoN>A@Z^q-R9gwC<;eBru6)tH=DV7AA*%sn>
z;%02tKDgV-zD@8gHnyvG^w{V~XOo{*P1iWDHszHH=K~qeqx=UL>`N5-k~!Ce_Sr%S
zpM@+?*Fwz8=OXuD3WlI8rHC2);TqJR-O=v>Fj7HJ$C(I6tgRfPGdKq`kpGS|toL>^
zxC|aNSDT~dQH3PHCpo>{Y&*JUn-Cz(LT(LNP=DP>TPtZ_q{;5Tcj)967301T>omQS
z=PmezN6s>-bq`k5+AOJN?sZ(Hg<Pqru_}Qix<5qEP>E3+*SKD1AS`PaNWq^l#?!D%
zIWKC+E0_6`c+ymkIfQsX=V|@eA1xyG`$B`;pO1WnG}vp;%&|H;|1vI13Y^{4rAR+v
zjJf*UR}8ltRn6_vMI-5Z^VTLs^5qOPeNj}<Nc6_`+b&Vb8%7~=2xCR_C9XUY_C^sO
z*$D;8@&N61W{cA^%-5T1%C6|Tl!wWFQbhE7=!3`dnUJdt`c%$_0e59Q1O4?&x`zg#
zSkZcf?C479E0$KVa%%1F1~a$>V~HXo_vHzr1bWz3Yh*<V%Hyp`V+e2K)B9oqB6f~B
zv#>S$fiqqa!gSKT!A4uQJy&^Vh_n)_g<VKP20^w`xn8UHvN^tQ*wn3LikbrPgv7Xu
zK}zDPu+o6!2|WA{+FMNps<eVct{)O*&tnVMN>`r~5|)L_fI|i5(1p@9IVGgEfHz9c
zJQM0_H01Zi)V&Z{<fpe4EEGL21WSdse}C`iB?7M!pY4&}Gjx%I1>R3A-4%-2Wq*Mq
z4hWTqM3G6F$uXMh%7uPbY|uGc&MsJx(N(JEsqpJN?<U15J20aC9)!WjVs@}`wm{ND
zllCJ|c_dEIVQNfX*7eZ}#p<~BudJhOa(Jm&nVy7&=G=)WWKQ7hH%8O$NHTW4<hzhT
z{s`m2tNn)E5Eg=_>4YO){Bx(}sc90X8raD9a!oX&qa!^-ZaoSto6$}|6m)oHS5rO;
zNxw+YkfcSN{RI11n*Ha9wm0<25_WD#HNoJ=T~hy6KYqVOwuClRZ3dzf<WpyRs?+oZ
zDfU`Ra*w<&Sv=9<%;-nZH}f_BX9@e1h8_cNr>8f@t{Jh@(RbsrB&I&fD(#e5%wFdA
z5t4bS*31a3oJwt>*9jByz%UNk<`Fzvw&5DYL9ZYj(BDxu9roS^jN`5(7^EiIv$BH{
zNRR%rs{T`B$XvOx6x)>ZHX=>37q!P4b9~C|rYfYHe_Xogh>_&?hxsyZd<AV!_c!C6
zy$y8OohdyhL<<Y!9b{v-gCteWFSuz>SyP)6pZ=)1JuJkzzh&~;BYz=ORop2`*%i-8
zO`o^7i_fpi3|<uY@cW)WoZC&LIJn_#edfmqQwnM&l2=X|ki^{LT7LU?fURwc#>O~L
z)Z3RY6S+1?&TbkDi837h?oKYe4XZgWju7DHrjfDiW8sp{D>PJ_Ddr~6G7^?-1MAe`
zbr3_)v|vO_yNAfxjTWvIKj^2V_=QPTTJ>TxYG;3%aPZj_X}anb77rxkOZo05=8#eF
z*eo)LF1{#d1$HTsYqe35{tu7}hV6kJRfZ-s2n#VpM<|8Z+Dg!B?^4$|h4gBgnv>rv
zdT}4~!3&?W+%6jOh*mm=D)n@}W?dMO&yNdAHEgb~l02m;^=AG?G6b4VAF5bFzedv4
z)-O#3J=boOt5nz5+I^^T_B~{q-T5n9a16CrTiqDxf3etVMyqDKr2nx3s`kwP7p@a=
zidpu?{vy(ze}q@PSx+v5YR9mY@^FBgElnjgR<=WNHKyyXDs@B`zQ!-z{Hqb72aIY(
ziYw~sOFdv}^vEW-c==JLdbbGwu@p!40g_-qqhy*Trt4QJri-Ba(===Lv>G3<WoUN1
z5qOs;8Fx{YE*Mr^8QgBvW+l}cpOdaP`)_)C^MmZxBT9)mgKZ54$}s9;texS<KK%;W
zzGmD$bfip=2Wtd}gZ@HcTk5Dz`WTE`Yf>r(ieEC@vM~61-%`Q(c*wgFM3<@<;WPY*
zs3z!8siXxv(d{K?6_SNhobZZ8MHs8R-}-)u0s7^e;o0lrc_4A}ZZuOt7CWVS(&g^k
z>=~+rcMBNaQM9SxLdG$O-679bJp00A*q_Ug3_+w@tPV{|-u5b5B3gYVb?vCcFW#8z
zUJWxxgx>=bw~vP69Bs}*4O<z)YXeL84+}jV&8lTz2;j}(MGdp#%WW_jG_Tm(FFl<c
z?H7NBbPcvhEDBqw!km<qdGCX>&JY)Or~C$7R&7ZWI-4~&LlkUdTa0E=p{c+1a*sEO
zq#8Y%n_uazx_BiDw)Cm}`V=WY=T3_o$@y%il##=dW64n&xn@4&T<gJ+;!G-N&s+)}
zg0)R1M?K|`h{tf9kA8+A`hn8^;V<pR*?jR#C04gZpf43{f;(fWjZ!l@!advGXHVW)
zm<}FTp1*!Xnw+`_Ny~xs;69ZRTTt4tzv>!x$W*iiD_&!}UcV*I8{OqlTK|HusuS_;
zcB!rVNIkhWqPor#0}V{6u<}*&6s8!<m{2zCx79Mx<=E`LWG%T*C0YtlW<Vb7e;!%s
z_wsg#{7PgLnCaY#@l=rI;JwpL72e;o&dj8o%uAD3O6S;!qCBka%gt)iA}{3|!=*%&
zaam3f?YxL-K)H}!>lFu#%`)deo5_;jU9_Ob;ebw9J8qz~)J1F1Fd-pwFY;c%dSXDy
zN{>27q{?Y&e4G-AoTRH)*M)TGj#NC+=(i%8!rp&?lS(THDr@Al--2m9vgwM_LCnc)
zlHqWk2F0~y3z$8f{h$K}wcGn2JAM_!XiA?Q{_U~P&V{50<zd0JVaNv8NO=#x3R}*~
ztk#6{sp2|Rr!b|!+34I`fd9i_CTha2WKnUB{9NL4l_^CnQl=+=KUhPpZJK|Utd9M<
zc{FK=aBlr%+`AxwAT_>9G<@7Q!hLAhqS8=lU$F-4d|b>TU~br(^&cQ`kBkm-uu$CG
z>JzzI(_BhmVxZ#K31%98-NIqWYFPa7j)3*Oko!#Cw=djLclT}|F%?no%R|IW6ns{M
zVhc#u>n_;i@P;LN&|KQlAbJN=jvnQF--k*5Ww&-@)Ks|69=RDNPS=ax(KYILJ4d_6
z87?ImC>kUT4rR?*m)K*WF2gZzCY7TI60+5p4CD6w<Av{w-+VpSCB;M5#!8BZf-;W|
zj6yOm;Uj?GZVn3S!dSTAFtV_ZC{n_cbTHFKi7{G{wk-r9(R8dR9JyD>U8UWogR?uw
zIr%3<8k1yF_5@~pJxlNh1*WP=gAEB*x;DEj#*J+$elv8&64a$n*}<~q)-q0fu5xvq
z$b#MfOd(?*-?TqTCm9O66O&)JkA`MD4Dn|el~!+ggf*4Y=h)x25m?s87?nlq7O8N8
zj}+w<pn$?MdUQjvgq4uMh6X_9%nn=(7^_ATp~rRt`#!q+pqpu(UQa)Ts`Y`M(3$Q!
zZci6|l(}5XlIld7XwLGsUlfwoRki^}D^>kHxR8cDOKp%v&#un<_S9(Prw(>c{mrU5
zfyjL&<vbm2nl&S3UW=1~;D(gp*)ECpxv^yX@ee=u!~iU?W`WyEt2IitoZAl`=Tnow
zTza43)7X@8MbU=^209{rv<-CSQhIcf!G$JEnMU1Ny31n7(umJRyDpLNIcx>aUMi4%
z_j4)L_z{#amyvv5tkx@1z*}}};Rk{l%K!2NI3xO%sWsi3_iy`6!rYn0C?GWd0fI=~
zBFPGz6=s@<aNADQuh9Ia&5Z~2_ocizHSS|sHa_p(Xc@kI(MX1<>_M+=YpN^*QY`{6
zsKSKxM>HNbdkHJ(20Q2!VC-V)U=5Oeg(nud5R|EdjfVF2>3WKPxq5sH10NJd;oi$S
znBNFJ7^Mb&nDf6G30ar9K$A@FG}U+yf?Wlainl*%zfXDkWp5IMQS$+MlkdEd9J1#Y
z^nig3*(}s(z_x3-IgyUIv%Jl>RxnKdNnyK^Ux-4BA)W8yzhAVPqb$=>fGQ?$w{)s8
zAPPJknMLMqzs(2eWVk|SYX|ABa*@})6@xrM6m0Vi^s5#Hx7A!tBg$1s6Oe@t4Y|oB
zf|r!Mr6ffgi8rj-P#}sr<;{R_tUdKx{%togxSSMEE=u!45^*8@-7e0no{_{{@_>Rx
zK{9zxipfxG4kC?V)Wj+%asu~KmpCde%|+YJ3Wdu}C`bg@xhF}70X%=kFd0(RNLA9L
zRMCsMiq39pk)p%~unG_SQ%zxgI+e!ON@(#Y#!WaqQO6)Ko1sMiRmlB;QcW@q{p(ED
z$&vIo@fn^IWi-3D+d;JCjY`oNF^X6krfL8#L!i6bPP4sntmqVqMxjDXrH1n@YW>?q
zcaPgr7FsO%OAa$%iXh?N;7VWgh{hy8*E8c}@*uHAh3&}?0)0iylf$#wY!k)FBTvuM
zT?M=!Eq-5a{G>x!D4-*sCDx=?4WHaGE!~pG0ncJW_uE?;-qiVaRV!R1m%gcxw;-s)
z*pPacIqX@`%P4#hH`0P-%C6RiUbT7sZ?Vw6OIcD~fllDyVOP#-A`m<Wa_;Zzd2bX*
zF}<mU;0Q8DNB5RJW8+;}ew90h5oA3<Op_d3h(ZhYA}~MZmYJUAB^`#%oo~%l%q;LU
zNAIjOwhQr@7#5_9n5R%cUd3sCKKIRu>XY4%p<aREZ8>jMI#J(txfnnG2guxSjA~ac
zYT~kwkQEXcT2ZPNy`)#dKU)t81a?4<OjF7SbUU4YD!rt1{Y_ji0yppt$?G5uIyYvl
z%~Ki0HZ*jU;uvBATv_~Pz}XGfQJ7x71rv766wFBOu{Tuqsx$jR*bV80^uR!Zx9End
zmnzW@Gn8rof_#3jydY#dEKU|tP2?FZ7)y|M;VXOGPXNd-WFVky09c27WmOi{q^6&l
zhA|`IIL`$Er(<urWEbL2l>J^|!OR&yt!Nym7zTiu9L78jAV@3B@8Efh4mD&xwrxRU
z9whj?=#B&et$CNaDK?U&0B%k|9KGlR!lmusPzY`{^P@q)lySQE*spLOR>=P$2t#XG
zYgAjr=_-%z!uZCO&gh3x@aJ>NKw*=s{tKaKU-^{wVZr*q|2yyI|IXt{_-1T>WxYT@
z+ob(ey-|XsAK<&twtZ5R=yQ7Chx_&0{lODk*t~#W`QK>XaW*DT8+y`HN$R6bONj5A
z`aenMt=Q-i{{alIS*oObTz#vQVM@nuq8yfUe?Xi@)Lp-RKQe86jnNG=v>M<G(#q0E
z3KOq$b5l0<zhT#lcDs5VK12&*U*GAs4wPLDP{95J5ZNCdqpON)DT)Gb1*TAeqO5{f
zE!{(m?ZHpdD^d|w?XxDRzO2(qnYbp_h#j=qMmuUjM~nBPiK2_i4y153KmL+n+*Ma9
z!-G=og3rrqrcWBy*%P*>f@wzgxstNT+|t$3GybwR<#zEKMVg9;m32A)wZ*c^?x6|$
z`C=I7&2PEJ(LC}!QJ7XK=TG;Io4Akq$MDLD?02#HX@AzAWLk;D2;+<~w>x#zEPM{|
zD<<kg+r~iRq<3G#IynQN1KSICCu8lAS7n1)+4BuHkc@27ONxQo68jG-*wgR#kalcu
ziXApMUwWL9j%InJJd;Bz_0BnOCb4rGhB3ODxxS}-{M&I7e|c7$zj=7X&{>L`5_nwt
z%6}UdB=A}X7GE+ep++)<hS8C8_xm=k7OvHeMb^99pw1he^cbCsvHXT&j5_2b*MNgJ
z>Qk)eqeVPhPJYnJQxF6;8Y{bJCTNX{4METDk>Pdt^NJOmT8;TWA=jVNI@$~5H=$A&
zrJgx>Dqop$5c9C-skIl+a4ZG3@&ReWb{_m@j-lO1(;dxJ8xn7}!*O^i`!B<Uq$yqR
z-D}-Rx2dv!B&Muq8Gi0X$GD~jox^kz-_chI<?y{_wNF`n2q78jhop!<f>gxS;CjWq
zT9D_CkMQJ{Ayls)zg*dA7ZE$KBSqt}Rv{s}_<i7thZqdx|L!V=py+oXm&-00o-x63
z>-?MHTQI!)<!G35t8YqZ<Uc@|?_lJUqQGjkB%3ewB=Gc^EzO~AdHV{aWTp7xh}k6d
znx||CJH>Qp1oWgBRw++|-fB1PjZdr(GA(4Z*>-Q2zW&C3<+6fcp;r^+8=mkEWV>Zu
zaQsYuJSoT74&a6)Z6G0C4vqa@c3AbxrO7OAddd=X5YjG76zN%a{MNa`(j`q8DQTl2
zhQo<Q(8iXMob)O2b91DN`>$OE;&qTq1AdW-K-LU*IskBs3SG=I-uR2X{j%}$4&3y^
zdji1r?;*fpDpd;e80w}$U5|+1lqDDNQo%tdm>*l4%<%taDjJ)fE03T2CCy8MZG-Cx
zX)DWXe5LzMdrVfHT&B&DsY&HuDZMGqF?VUTTBmZ!wQAGGZzcS&=qh*RyL;b_Y@-{A
z;~rU5yg>+NzbRkJEn%(S#d+U_5yR``)7PmPVyn0tAk|YN(*nltrByC=pfUYaWtfmD
zz&t(IXf;Qp<7b84jz(2!-q9`>g?b>_XugCQ+5%aJXeG5^e-%COq+efVlldd0-N3-8
zUjP&y@$bDP)X6K|q5EY#7wLwJQFrjzKF1}D&X^-!*fM17iY+=18kW*fuBR{SO_FPY
z8DQW~I?mQB?|q=>VxrzT(ff%FLwi;ENPomAz=1jsnDXTmnzI<AXDeX}OOz{1=*v0m
z)lqaqvghHhde!4MMM_=!Kb3w0687T{uyU01OHhHrC=z8WKd2yg@X5K)b-ZnHZHH_{
zud*!8gn&D;wX=Wp{}jvN;~^YfhzLOSBH?!uCMiaD6Tu&z6npsw>;9*)Z-2uM5eg#N
z`TPYTJaco4Q}4x^qv(UD;KlnWQy3Pw-$lx~oAz}Bc{XxUJk^|HHMD06f5LI|SRdws
zYmZ=giH=U0!AG#<PSI?(oYXONaTfNVkWVCs4$2c#3RD|ROV<Wk!{L=t2BAfIm*odF
zX+IWfRh+IVqLD-l_xpHVR`kg!TPjWDsw@#S1|hiJ5<I%#;GM7O&7jN`V@29#9hzQL
z=bgv-VjItNJQiaAzBi2ZcYH0MN$4+F=<y8{vu%d@&d}=Ze@}GosHB@+lMsg3KqymE
zc+hz20kP?oWKwu&HCILccWY?!Y_txCRr)2=<U1z@2%Zlp)FM08g;Ks28ZP!B@-z{X
z$}yIcTL!`=YnJ=l!kg&F_Mhn0-75dVCR>4H?@$Pa@IdB!F2Xklgn5NTbY3KQ0#+%6
za}P5C*(CZ6%+km9Z_Qi%EiJJTmBa*}^J@pC9rAeU=q<fU2uij7!a{s7{W(QWVN=*`
z&^h(v<u_kRt8~x|2g;Pp)!5%j2@{{g6Sv6g!9fnZzX|D^)l+ywz;e$UX8&TJyvGeR
z@JyGu5@GbwcjmK~6;aYX)^uVD#=51a(WR|SsIh&Z_iHI>LyWCL+7hExJ%h!Cp9Ec;
zhN8}^uL|M?l`l2R(=7iPp|7;k>W<i(kWGcgrdW&lTGA0yzj(42S~@+-YZMAtv)n@;
zL9w48b^Y{Mjrq<{+;I)U=(A26fM@r1W>Oos_36@FoyjmWvk`K=+aVh)(Mj0x6#>;z
zR7mb6OpE6sMxAd-w3RtMIyX>ev8TCKo(eKH!;hX7|E)kC+pgQ#nsJsDoz;s`N#C@a
zX)Y0F$%D6*Y*r=rHaAhapX}3P!7C&1mbSn$x;!&!+}2=2BAjx?j@IRl3}vA%#Tzm;
zOQ|P!wM+~#noWxB8#bPAS*R{HR&!@>KX9m}ew@qiy*h^asoh1~iQZ~Y&eU#W??^~C
z+#3t(u?|*|kyQRP+PJ^{$k9YsbCF$Hx}o9XM2to=-+A<)LmD1gVtfD9rZcE~hq{`M
z@UW9=p@I0u9X}&V?4ms(DfQ*P!yOs{zuJphYcE3|F{%=?*=Ri;z>u^6I%O7h<+@6r
zXc(+hc`5a)dE@uexe(t8s5Te6>*vcz$oe8Jr&b2EGXHq?k}@3B&sr^1ktoGQF8%T6
z4HGU|xgTNAKgdLd1}bIa%prVyKf`fKzILNafxGUibAIFytT;PgFxNhxK0sm>9sCz!
zgzHnUF?~jpqt;}gE$k`sThD}9coj%?=&_;@)!;<yecdn^uD1GvJmu-c{$Tqh;%?H#
z9n6CYexo3uZTO=%kpJQze8mS}D^|Q(%s|cO@ww<-_WS5m?WqUQeAx)4r3`NB*y3E(
z&B?lqQp2ALjcZ3HG5h4wSbJhxlgIB^usYDEmMiU<cKf>h9G+GX-ilfs;jskkO>I5X
zNP(_Cs_kmfegj>LOpYJr?X>bKQtZMEN@zB8!D`IZ2>aiO3IAbLTT0L4g4}rM8V?Wm
zn$)-1lz2L7S9@DMU$o+v;f`(&?5PfYIBk>F>s4GOoj`E}^DFaRSw(J68*E15v$3Vk
zk=7^%&)T;T=u{dBXNv?&qq9!eQM9fFw%Z%s0f3*T6sab0XzhD&6*}SE(N~<tEIn1D
zznHXwyKJN_J-}tW-PC>cv;^mW^IyC*dx{V+Lhvq2oRqI$Ai;O_9F3Ml5`~GF=sW&G
zH?~x$au<lLC4l)guoj)$f($}Eq}j80S)JeH#n#%05TstwPEcG2PZHYcm~m<P^n(yh
zwx65|aAxvIYZwse``?1x5Ql0uQNC+ibWBS+cVpt?uaXhSD&f4LT~nv&txMYD)b=dy
zq}}v}-59A31nC&*$WUwT%<)|$)w+Q76&KyPRq{P@iFoP^BS4p_g>X_2q&s-au3-os
zuIKdAF-n)8S*C2nACifeuGpcFE<;~EOB1CCx)ZMCs+C0!CTqj|N~qPGpcPk${{_#r
zGT5lC;{)ELLyHY6<$Q{}nL#LBykDqZep|NmAw9<*KOHqu=T*i%y1(BAJpSe9MsPGN
zdQPUL9eyfITs9LQA<gunmQ*{&KkS8<%{cpKYgF2wp``u3-Oi55yi8EVtXwFF(bCD<
z3}eHrhJ^o~{ZkcIt;;UK`tH4N=1rk-r!YAv3klAv`s1xWAeRd|A^&`_yHlv20F!I9
zf4gWmj?9nBTFhzRGgeA9q(A`ooIFPsb)NLs`y}|oNfaISfjoBoIAy8IT;VGQ%kLkh
z6$SXI3E{*Zl=Hx|E;%lm_}IK6m{~%YF)~XH9irJNa;c3_^45Ct8SNvbxz)41exAc<
zzz7d*_AN-)1Ed`dwXV-$Lw<Kgs@E%dUa8BJps0j3E<wu|ohx!*QE3rbnE}QVW{kSw
z%ZnY=%(|=r0kLeK^2nvWD$irliJ~g%XS*8_CH9q=WN^j4{^RIwDIBOh%5aTt7P6El
z+oEgp`S(`a*OT;q_(FYGQEtVnc6D2<&KUDzw(hsU`$y?@Q*t;HufwNMr~5ZVC-G>?
zEu*6}aihHe85Y_}`cvCcK58N%@jXu0yx%wY{#x?4ltHXTSW)RaD!x<~Lqz^&VP#Lj
zw}`H8`b9ZWdv?sYhP9<}1bI11w9~kL+hXF&nu5Dy`76@C(#oN{(X&k@DctRK0JyDS
zgdt_c2O9;aMe9+M`UAzCLVWHDvgVW_Gx>VJE+CkMb!eu^Xzx_35y4bx<RR7yQ4`iW
zIh6t9F((l-79?m%9<6H;^(&So(hQC&9nuiEI3ZSV%j3uIfJ5H_54wEsAK(r)cI0zs
zw0(Dfh{x8@4nj4}!2Fv$6Zl>V=0F9~gm9*da%o1san@3TYRWZ2GlfD7gK$2j8iLOL
z`y%|dq<+=A8QfnYJK{Q@%`CBPBc^72?#neJ@VHOJd|UP~E_D@eP@kENXIqQ|hLq}Q
zp9;KgOXzkg701Iw2tQszlz0Rc{{wK16~GhO5<jBHRes*Z-N+wgs${G}jrFb-IsZ4e
z;Pwo6dTgC{d=(Vkh~ulTApPRD4iZ-oArICGQGeP&h3e{a?tKHaSG(FD{-X9z2tLtF
z2}-aWDI1OsUC7{8A}Af)(gi26KdvUau`(s<#8-bh(h2EN&QLm619_5r7bhCeluVM0
z8zDuLOz2;)!e#6OUMEU-k}2<HH<<{9ko&VgryI{t8Dw%*yMr1=jUedfifc=UP;KkF
zR1u+k=jfYB!$`JZ^(`-Eu~3^v?ZMjeJ=E%YDejV&p$+GW>|5ry7RkNg(Ob`~-g9Ro
zye%Mf1UU@hkoR16#PPCB?)Z$&rl3DnabrY1YZ7VFy(Im+xzN6JxIAn^_m|IV2GeEL
zk6vB{)EI(qZ=`q+8r?q)p!o<?7YrjeeM$6#>D8nks(Ew7F0P%wr9j#)8?X4}$pUPL
zQl=z$mdou$EU0s%E9cgK{-az&|3I3q3uEkq4`gz#1*DlZ1K+s+X!UR6ePgqp%@=z+
z*X>`6Fi@YrJvBb7EzLLiZSnb}A81#JCW~51EHX$@Cg_n8IUt#0az>kMrR~zlE=!%D
z-pkRK2hyRyA+$d3lEe0SVx!3Tr93@bHD|>{A9|wPrLEKbuQZX{^l9Pm6y-j?KpR$p
zYks4<9(RLwgL9yjF#ptWUOGtCX-MGf*c)CP;);kgx~FxC<7>;}k=Fwn(uT`BhWWkF
zR@P0`PbMMzHk?<TTTMUQ=KFV4%mwYRDbmQreI~%%?|8Rwub6trCui@foo<OT5PMYo
zt1?Hc{}4UTM`N2~BBQV>i(S%A?)}FxDb|x46S`iv=X$MQg8Nr?LMk2gwY8Zz6YcbB
zNmutbrQ6vL`?f!o)_w^0HhsLTTH4N7llu=qZg&UnYmRi({V8UG@s;&<63fuXMdzZ4
zh*+h;T%Q0?JR*E#DqCuMzd+>RDL$oK)vXBHQ<$mv`_=Gev}J5(tO-2kS3AK<sItx*
zhNyRv(n8c*V_Nv5-IngmbLPG+bv@b3>6#OL<u@8KmZyvi>9M62xOd?Lq_<_<8w`+_
zepmS{eT{XL8NKbMLZ@P4)prQ(5Vm2@EEy*iP)lcevv^k5iALMp%fjCv#Sc%LLSG7P
zqM~atMenK(M}U97@v9#TM(?c6p6<Wrwl?0G^PANl@O^7{Sy%VGA;FwfLxC|=m987@
zJ%Rz}X)(J#H6U74qST7R^x1BtNf!$4MsIY}acZk!iuF@`FDLfFh~iP#p<D&RChpXz
zA-<@aH@qdqG`dhpf9<D)i2cgibt!Xr=N%~+$)DIW#zzqJJJ55M*u>o!vqjfbx=1Yo
z+UOz3hSg4IcTKiXIleQ*#h+RmCm$}v60?WKhN2!~^ObQkQKY*NNd8FBAj*%hu^<$*
ziC%2*A!PW1BX1@1T^R777bY238qHS|6+3?th<0h3K?zG0(nBMuOlBkTd)#kjmQAG@
zv-8>MuJQSyZXKh`MYl&q_}eLOqqpQaM8_jz>}r@UcsxL~wKKby_6{W>r;`mIRCm!-
z>`UBsMY*k!B8WhJ(QT%;Jf~?&PuThuz9LtYfp3D|k{mO(3JVELS=P6!Ihu;7Oz)G;
zt9R}f)2R8b(WGz2>uWEJ`B<xmj+~hz4I_dv7wEhHf99)iQ^+?(xB2{@<eJp{$-pTj
zc|H}Tb7|c1m#P+{pf|5B!~0k{Z@yP5PM~-6KLC~XWnAV$l!c=4DR2<J@5$tVNY@E&
z{#EE=(%Rq{wBt=u;p?Plw>&t5IOd5rTB60>r|5bBMce+AMmf8wXtcwvA-g^`3=RtQ
zJ)o_l7!=)t9v~y6h)y=m>h<&D(frGzy~|s}Yj=sl*GcUzqdiEfB^N8s;9n$<JrZ5E
zbSFnoWmAHBuj#Eg=(75o_gmFalmlco$C7>y1E6{mgzZ1@>8agzu`~6`Y)O^vR(!+)
zozf&jqSlheZY|-1z*P2A)x7|S$>cZjPj(VN628`|er3Vg+(2-BOeQTO6i;<r6epD)
zd=oBlyd(H+;$*-Zj{7_g|7=4S9*r&8*n`BHwv7G7RVx-cS5laaGHx)t-T(Y+NckgK
z%c-I4MgsfI=|}0<d)cwk)YTBB?UrTsj8B&s3h}tH65$RDuU2v;RptRH(Q-(h{^rP}
z`&&1^*!kI^Y7g3h%ni>F+~H3RI~@?J4=!-FFZE}r2r8B%lT1T@sK4XXIJG8E!(!s!
zkxS>sugqu9o5mjFEOpzjkgZWBn9N;oTZ4D(Ynu+3{jTgQMu+8UMQx^M1qO@b{nO!U
z?9CN`AG{G9(a4YI3oQ32>FTHQaeITp&jrRaJXbf6kYE$85{m{EM*WK?UM;(vg#P50
zXHn*+qijI>upRALI5=mWB=P{Aq7f;4H55w^9aI`N&AM<de-^wVl<M;#sCuIol%2dQ
z@BJ1wHU<e|D`~h$RnAC{-6&x25Nx$-EVB^4+x6_1O`G7H?QL%6cpQ2v7~GU7FQ~uh
z$Yg7EREA8&vbo9wC~8mC>5*D)Zc7f#1UFD4IQv)7&4epQEigsI&9-Z`<})z-7CLI5
z#~qZ`QVk|VCJ7J(p@m%bOYuzn*3p;pz7Mk>fT5vEaLoV~%y{xRLoA_xz#A8PK-D0=
zMJ1DcsnEl8?7Xv7tLU^V+R^Z-MpM*;Q$EVipHoeOu(rb0z-!+@^<<=K0#l&VxD-J<
zRBJKLFd;?YU4KV%9o5;ra5WF?&zJR4R}H2;twTPOk9}&!`gYinjLXDkdN^AM|5YnD
z_kJr0n1IU<?j}(%ah0hht^A#ERoT&}h(#XJr#})WL_p@`37@ia67<+xkMKd|u)z}k
zaP35%+E9!7k*$CGjafpa#3wqgLKkfMczvHIo40`f0(aqVLDILSJ^wQ&h+d_6mt(KN
zS@G>)Z6<k`pbvz54L1q$d}bY(5CgvbcTkAT=CretWIn(;F$UFEo<VL=mZfr!D>Pv1
z=O1vF{@_RuCTjDFZl|C$3fb?>y)M(ohjs7HoDS{)agzp^S10+qzB_|{IO7<`SC0fB
z<#JU+rR9QS(T^0h8H?D0W77)gC~uI6CJ?zLrONwBwv)=}ZX6w0j2j}QO|xDv1R=Xt
zkXg!`magqAnBcQ5Qb%VpV#2OpeIq&7Y^RW$p`NUYj>2~w>Kv`HgdfdQE!ZUHOxHzy
zc50ec$jLqnZ>)(5J<&klND`)C=_M}WmI~vigu=AfbOOi<QRoMtaP@yD@_`NMx$ksh
zT254E8|6EAo=SV+X2L<}1mBBn*Z*q2*F@f-tA@Igh#wI2OLjI=OZe^wA-e`Pnyl_K
zzgwT%E=U;q0=3`*2~hI{zi%!*wAXh7{GOFb$~gcscb$y$qoz;NhDh%xp)bT$@)%nO
zIyd~myf2DJvCe!=QeM}m0%l>Z{g_g$fa*AS_S<n9Vy2BB!aL240FrZcYA{LB0YO;p
zv>G)gnoHVmJ&x@TT@DUP;lk(Nhv;AJSLR$22R6qn0Cbs)F@NKXh1~1PV{#8%L<kup
zM&?{Lws&h!ZpU>)_#o8MI1A;eqm;K(f4!DepM}5zAV$@3_>AK7U`xN2t5)qw8-?kx
zmOO#`(F($0=}ziMQL!qq-9O(+vT@l*l`Q?^M0`A1^x{YO$rJIT$=sC+Y$3Y@2B&M7
zJ58iNl-adzQFHs4Fhs?z`I<c)t|Zn*)=oH(c(m+$c%xjtu(H2P3nZGs8$s`EA-3N0
z_9E2l6V2^tx1}}TD|_AWKIwOI__(3N;$jOp4W7anp1HAg=KM9o3#RJL^gdT!B=r*6
zk7IkR(T_Kfsf1F6I#&ITM4d|3Mak(ED0FZtvP<};m=8oJDfenE;Np&?6kJ(L5r@r)
z(psJ|mZhr)HAx@LR+?$>6K%m|T1?dg*z)Hz&Z16FCfHz$)bU+Ce9?o=kU~hm@k0`S
zj<T|$yfk!L!Co1a)6O0443T&5N1+&i&S=4v0iKKynCf<Pw3gY&wQ0Eejg}cXP9w@n
z#%<v^fO&T+@RorAz(IghhzgNLx5q+G64#`0@2BC{S_#6Q^Ul>;i2?v;FsB!SkY5uo
zMD7%_)*SG@V1OA3QJ5PCWeKu~fBks+Kfw0pYdK!%YaL%PDr5W%1^Pqxsor<xYD@+r
z#)<`AZ=r9FuOX9Cu9h4D;Q#c@<jw>Ewp0K2VA}s5u=aoJ`*8go_(zzfUQ9TNz9p_H
z#r7(NpoHm{T1En!gs#Uy*xl$qQ?hs2!r2NKUS*g`raBu~uY#k!lsqF(XPwc0Fo@F#
z>EN9B&5!D>*MKX>z@ZXbjn@|`alV$ADKTeP@1x&uE?ff>cKPWdc?&$n7qh_5ltal6
z7am@n<RKiu*^v&Q`i-OT?oNVovK0}!<DZ0|-qg&yNu~kYR1~8Wlgs>fG2TsGk8KM~
zG5hlkQTg^O4KrQ6d#KlOmla<COM{g@wZJ3sA&yyy-mWwM+UgHhWQ`ApflLil4jo}<
zU~sC>i&N)qpQ$24-2M>yN@qzTK_Xh%_n}_mYO2fP-crZ*arquuez{0Xm*150y!rDO
zgNX=DzDy(#!*t{4dZWgAxC+RmM{&`$u(gS~iUK3&?7rIXuNh6-1w(}!YLfFV^>wV;
zhnRlw0pZ$7Ch5XdBhw65>KRL6$mhe$xNG?4->`fmyFkV)Com72(E1;x16c3HMvhbI
z-`I^_&9q+BO=efW2VJ+eL%M>6PP$`wRsqquK>IKWwlPjeY@ZIEJt<d2ek7f&Rp6kl
zvAJQ@-})`E50t7|-{f88>UsHvoGX_zIG)e>&FhdbnSWt7J0{oG&^gIpyYFr_&+B=<
zYhUW;P1Ro?vhLOpqWUYrY()iB(u-k%XP}BzQ{ur`q;K!Fmf;D$;Yhz_yz^PKeMg=N
zs#l=!1!qPsqO}&WQt%(3>=+Beh1Di|1t9h;7g`+m$=KM|o4ja)kNDLmBEJYEH+su3
z*8BN5_pZyI0#2GLkAE%m=K4{rPTqrRSI)79DgPCb%-3|qZyMU^zg?GRs$y-Q4n7Cb
zXZTrWKF+2%6$I7u(PwvjDwEcZ3P*u8;}v*owvSA{{hG;TtbJO!l@3b}`DL!=s+r7*
zz41*qSID!3->Y7wQuKm{oH(Mp!bx%lOBM*5*gkRsswZ;q@Xr}=8i3zYJTQ^J+EZN6
zk3W*;NxVdQN@PaGCAcbdI_NVn)#%^4yzv)op4xeoZjC)<K#H&({8Gs`xPd%%&OgjK
z!{5*vqv9Ox=2Lm1CIp&pxQS8<D~jO4Redzjm|INwyQz68+?pr>WO16hK#m1Gz&7FQ
z9{8%)Mr}$?2R=*TY*)M9{RT7bQl-b!4R^RUqr&V)=#uk%xpWecW9Zz9SI5`fiE(q`
z7^BpfAFOKbM*;G>b6n!mVHMTI@fH5&UE%=_Tw^@V7{XQS0xmc{sd%1Yenv0Z7B(bR
zf@g1?&P;_1uIaSHT(q==s&-TzKh_(q@lSOQIFs<i&s#Vd+8HzvMY-+VJL)PvfPAB`
z<d|b3S7DG+hB=UgOZQj8{aMF1S?f^~G@2+s4=CzQ<QDr^jiS819X4yUo3UuR8-MHx
zP?4RzW%&V0F;6v+lutTKSm_K_31HG~82`1rr?KU8;p$L0Y{y97DEU=V;u0<FwcUq<
zvAI5_nW23+<w=6o0f*SO-o96Jf!_{{0Ak;WQ*~`u`#kC{@cSJ#lwy9w6<#NgAtFY}
z*#r4=YzLqi)tLzO6S=;_KT{tK`bs%>R>fD`F&9Yrw^)sPT%sL#+SBGAofG5B715x0
zQ$F70onT_b{f`1ixT?HglIkK1PBhEJ!tyVK?hLKO$EMrxO9ZvlrGVg~czi~yo`kLY
zW9i!ik1yDhWhMo6^hIOjQmH~zL++-p-G<^9Ewy^D4g+sts;}aK0c>NpPGo(7NOPYW
zIyPO}+>~Pmx7naL(S~77nNFTDA`EM7{#}A+1V^*cgxNc_MuWewKFTP}d6b9wsag(f
z_TC7L9c2@={AzGm_U?9xOVlMfe7y+8^==aSxR}mnsLU-eB)L1qy7wZx8+I~W^d6Er
z{^%q@d>BCDvLA#B&Azrbz4es#aXQUkTJx2+N(QqkKw|}6G$tzT4J#Y>ul>wwHdwax
zTQCDtGCAE4yN`Mqris5=wZIb->Z}bv=rfUYNxiPUuXEJrtq5&MOvzd*B(lD-Dyr-k
zBoB&if6^jO^V1Bvr=Mz`k|}IO>MEuYtgjdamX18mC3Ic!00OO>)m0!xhI0)Cb2~7f
z!nc2SA9X)pgpK@6aHdID5I&T%T_P_xsu2tNr>52F5MgD7*8+G&hgS3*dk{g(YmDa`
zv@PtN`7Ko~N7*FpwMH?5&%aw<m@{qQ{SeF{Lo2cGkd5NzFfH$VXR48;^4xETx~m^_
z4u13RKAd(NgA$a|D8>$!=2e2j=$Jwcio}vHq`S)Fd#<ud=kCk8-TqD*&NSMAMWp#=
z2{Le<_lLI{uhGa~-%7uOmmo&kc;M$t>g;)C-3E+)E0FmdicZkMnWdNTFknvd)w#iW
zmY)lTH;M)I;dY<HDntU&p&Oz!iM^bAlBU1?VCm%b0QZHo(!KbT)kc#@+60~8@MF2p
z71SK9JlEQKfZI~~NDxn`?o+V@@q)Agt|ZDX@1u6*={hG+vB>svlH&Nir|o2w{S&V5
z_t;#IpJGTgi_X(;m|qW4AB^ff4Vn>biL&`Rd@|odnH>@VWsfW?#)*KF=iU<|xjGV7
zqq@xc?DT$#-ALirO;-mZzqX6l!VU$)a;6m<+5JR?4*d$-$#PjT$0ag>49@_9<#)KK
z_hogjueV1k3<W`G#+i>m$8u}~jLeWvw}f6R^5Cq#{rYc?`TN_IM)h~+`Z{w~ubWjO
z!f2%u@HXdheNVHlwoD+mw1k|h<u<QCgG|es`zeqCM)fQ4RSb9$s0~}1S{S)HTwNc!
zNQx=&u;0kq{lk<yDk0dNFSfSlr}v2}bbKP~fH5^LY-EUmRb$IEa;yKs368VAN@78l
zmaSM7s(Z;9zQSH@<L$g-hhj(JfH0p~8(pD0Fp62IYXJ5)eRkwNkr`t!hHBqp-3z%Z
zpC(SID+Jmzn+rQ)ryQuW-XZGd3D1ascAe|Gr%q_>0N2{y;V_new^%=7j;=-FRr)q4
z5vM$p4gt7{(20XA?Pv+Dzr1wlJ2df}0<H%o${4Ve-#ZKunKbk8P(+-{^<Apa@YuLG
z!m1amKHZkAQfJ?Ot{WL|2v$qI5^zZmw+9GetFsx&&Vgr(Qt`nQe}GTpWUqV#t39xu
zCjOI`ft1&O0H%_1JIRIJv-^r?)9o>P%m;s<QTRVNy78N`1$c=(8#9PxE44Y<*Cb?M
zZ>1OFOnhp6f6PXzqQi9mm8-VWNae&}wuC<M-5GOh<LY%-m&CEWWyw{Bi^$*!P&_Tp
z3kn4eUkM4Ij)m|lQF9e?D^^O@`m(E`zBXfCUUO0F>LRQr$OyhW;5TR6O|Q0ReS}R<
zB0z+UZ(3_C+~XZS8LU~Y)l(ic3X;)KiMgMHh{R*ls(dGYt5zj2vyVtN@~#cCo@$R<
zt{JxSxbouIXZLVrQufrlf?7zm`oly@Fe$Z@_W4kj?#eYrc7EQL?4dGZI|zty=Go@E
zGMZlv$;9?9q}xH*_1M}VScB>*Y&_`Xuxyf+f6vf)kr4Uhdh5CH$uZFdnfxH-Sm?qC
zK{kM-_FU)eG;o{}v_lgo!yTByzgH@!zmEMGCPm7i^GYE&d<OM^L^90DVGC;5+wZ9w
zjaQW<er@1MuT^iE=q!p&C7~VD0|IWXk5YE7%Z@O=T+OH9Xo2>BrTTwnz+1IprtsC$
zIe#0AbZvHDo_Z%&_;dCzSSL=lZJR%P;Y+9TF6_`#3a_Jm!z+dUt96R&boB-NYSl^I
z2(&`Z`_*HizhhS$P__h~=v7)QR~IiC@HiX2_olTldAu4ZLym2WPsCCL&|&goDG>1F
zr^M8e)mD*h0;e%2=zsxl<Qz)qy^-P|(WDug5k<ZOY!V@SHXU~F`O(!VR!o12Nt-Vc
zf=<`vXLjSDNwUqpk)Kx-&~i#w#IXq<C_^F?G<ilcck%d)R^*<h<x7^#a5NkjSXhgH
z%~W*<{hW^2flrr59Kj!uNZb^OrC2I-eVjQzDMnz;E7*q^G;?}em#iM&-8GBthRa!v
zoXO_Q)I-cXNV9)XG=^$mMw3VjS6F+(0lhRql@W~@6w3INmq|;}*7e2pv2?8>Le%&B
z^$=OUv@q@HIlB;6UyM6K;+UmGJ(Pt~Bo}4Nk1=G?XXH9UZ8X0;J&C2bNlw)w6Uox{
zECRJxDo^%j?ud&U5)3W3YDD^l*%UE-ao_!W^;T-3eS|z{6E<09cP96;@l<}}9K)T{
z?)?px%Hp#O!k+^YueWK6!OGqr&_C)-(~hhmOB~aa3ELwuzKJEz)zBqM{Cb8)zGx+Z
z80dewD}q-LR{XSz9L^-1+k@}3)y4E2-t=)HHwck^nQ2){<`343UR1D^9LwL;Gxn(b
z@WI~H&S~OT47g#*nFoHnZ)B7K>gvUvL9h*pM}=!8GRKcPK#xPwsbqBv5;7B^*^L;;
z3O7H8O&zjw8T5yb^vqFQex4h+s&9CSLFe~5QU)Ot%zG@j6AZjWu`=xkgxsxcMD)1|
zDV*zmx)L$`-)w>n^FK!vB}DNI8h%H8t=VL4bSKTba)ky87<?z!UQ<OlxS5f4?H471
z9Kw1n$_J2FUCe`F`TPEV6#F&mRWnGBSby2mH(!5*5I=y7y*aa_l-sa#UktEwV(ooN
zKjc_5yCTr1;9nRnP=a%eXEOS{%tLd4_T{Eqal@I=`GP*v*qz}wLU_fSg*xyZJ24Gy
zwSQLs?!Xdd?`9NhNZ$cY+FS_j0EPFYa@y@es@nL)Z2z?HJ4Li%UM%?M3E!nWbev{i
z*EBT#>LeJo_gyCw=sT8u+3z|KuwHf@gmfRl^ujcs5JN?$Bopqi$k%N+Oqqr7bj#){
z@6LYH&f8QZ6tpTsHCjyeRmiC(?f6S9EqJ%+$qTJsa-3I)Rn9JIAySFgg)ukvX)<Wd
zPqSc(pde;Gcw9er`R;tR#ZM<gWk7kmAbdAsMEHQh){XecS_``?m-26!HTPPR+-s}j
z4-5ojRI*R_uuc(_a-i%E*+`$S4fCypJJ9%W##i3<9erGz0S@E9hzR;hgOjJo=fE%N
zla(qOt~`63RF<I*v3c>7tf%MaqhdS0=dfyuiW&KFQfIA=Mk6GmfNPlAIy3OQ2)%nW
zFcX{kJ<g|JOS8rwpx27nqS{Jpw#Zf}RM5;n1Ux$e7|-^)VTG@F?YVlFJn`9yx?Not
zDJ6-;<4M9XE84`)a9)?GRthQ#Oh!=v)!Xl*%iifH#5$9@gsrVyZ6Z3s%z7P59<W>$
z(|z2U_F=g8qn!vrb&2ZqsSVBR?v4Nxid3QEN9udZWNHC^E^G(G=dPEbrbHcdJAX61
zV!L0cw<>=m%b^^<mZPo9pM)=OpkTwJ#n+NIg*{$8o|%sN$FC}n!kL?0bOY|Kt^ep8
z3SHGGZP2?T`P*8~9dC)x7$WvS9>Oo4-Tvycp5?+|(v(cC)qx$n&w-cKwu^yuhbvCy
z&+t9Q96MHY<%@H|zboeh#IQ5!c(&L6K>VzHYrbzhsp91GQ98EjZqhfURi9-kmH*rl
zVz9LgXw2!+c_ZIICf!pbQMmk@mA_+F5A|{x#;*7}6}WIr;B1uA+Y$Q~P*gzS=`s(W
zz4*6V<RjjRRQOeMtVL{LARWF@B5U$J-^d0h1bWB>rep~V^Y9B|NsSo~VLaO<_R+Yo
z;84z!C#tF|IX=#R6%UQRHY$hp^{j~n*qvHMQ%X-7dS)$7;9gFW6m-J$i?A~y1U`Xl
zrid7uaoZn_a=R;j;T<;BHm~RogP%7~^cTD}2!6&&-x8LVZ}xJee@=40@R~|vbnhXM
z4V_?J!~4+k+DgdNu}Yg=JE7RaJ?XF61^;a2UpD(QtO`dw-W}HJxF9S(7$5T5#LJqe
zTAqpt(VzRZi~<z)Dxpj<%RAUVIx=7h{9m-aRa9GD*tQ$2NRd+9DelD`iWGN;;7;)1
zQYca^#hu_1+}$a~-Cc@naksvIzCFesW1sye`#Z>4#!3#7x#nE=b6*$wpsKxRw`Lch
zTHK(R<~2d$h#!2R&e69NFXkYu^e^z<_iVM&ki>R`isc!)I13!MUa?770=el;FIvAQ
z$`B2&?B)VD=WcUbHt1VcEq?lpBs{bG#fDz)_D)OoXwF-9r9Xi9gAHek{&Z^G{I$EG
zO8#hAc2}ijXcguw#0WQ7UmZkkzwu~Cc^K5kWM454Q|{E}*9Vcmj*G#+!Cf*%dUUG^
z@wo-aa=lzt0{_f>w=Ec@I%gzxD!pzV8jUMSX^zY}sc=wkXiqfro0i8pI<8%hxS~X`
zbsaO=so#CG5?S!2IQM!0ZiZtc&$>~AK5h6&i0GUn5pwpSF7dg|WLOPoX?oq2o#}^<
z;Xx){r{&aOreY~Os;S3d28<uz`0p6EZ+gAnl%FoI$G`-g+`i@u7C%won9FMs*8QlN
zX^O4;f1W4*2(NC#3c{bwuAJ6>-`rJkR=Hgdf3_Urm<<s5hG*F5m_0n;Ve&qbyE2-4
zzlE^IW>GE7^G#f)9rAAXLSXcFr`K7f$A;G5Rpn|6)TFGq$)+?mFVwPy_4WoQlk5Oc
z%d<<iZI_(Reo!w#wnG2_jZTvGj*fI$VDJPnlZ1B2nW@J@RojLJxkZyh@a4{&kJbf@
zIlW$&h!;OKAy>A%MjI|C(y_NFeXbQ|#$_<6^+N5}9D0R#qLjYV**ECJ_KwRW4YN$t
zfzBz#S+WLNnd*BWk2{)r^7PVu_ZQ0FU<o^NU7PSeP$D&tE2}EgJ_tL|Oo^T56hq@Z
zxk~TUDD5ksV$be1r|Y4P2ZuN;+zz!Sjxux5;m~4caj?oa(fgzpnHD6bW>`=rC!a_U
z02uKtSJO&idGBVF7UQv*K4|1B3TrF|b2I-3Sb%QT7$@$0!xq3Z{@cgJc~?!QgYG;_
zbs_M@Xh9$^8vTw~bNBDd6jV<{zFa{x&Z9R|NQ`T?^f5&lEVealEr#mn9Ot^Eh`!N>
z>3?Ok%NN#>lm*tl_*@*q7a5HzNKgTG$Es>jVg;0oEYU4#ni`W0xvWQr8TV8vO`{si
zA!{@?e7?XTVTbHjZvZvrXjdywo)fyVWYN*71Ru(k5_w)v6JbjA1}Ie>UBf=!wzC}*
z;*&=!RQw78PRDC}rhTLRSD5A!<h#(5px;4Q#=IA93Hz%pVR!G>ZrC)aSV8;k2W=f=
zLTtr$#j@+dTYBx~-xhRT-me-fTMv!P88<Dd3Ru`8ZR4PG!2RrQe?IMfR%I>jxTL5s
z9-?oIp`1nAX|GV>CPV3$2tKmEJS12lhSi}cIcPZ8#GkY2b@6jGL8}!0K!W8igeq`#
z-x8cm{ZW9IZ{KWzNtOrPJde*y<vtDC4y?8^g9p0=do3?TDb`>5vCK7P>*(r*8g*V-
z-hNV1R|7<1H0A~^zpF3!jeoGxTH=fUAlO%XTO<liG><ZTntR6_l$_^2B`wQ!tcco0
zNaC;bA0V#MlKO31x9O+#lZ`Cpo#Kf8xDL0%5J4GL#Kq_8HSqPe7{Zx^Q7?MWzH);f
z#!}to#QxR>t1t8ILHmS&RCAqa>ZcCTq>(DOJWPy<VeG)6K7M{krR9wk(#03P+5{Gs
zJdL}O;a>clzAj0uSv8J<k%!8)R=n(Tu3v?K;7R+cOA%C)#%4#X*4?aGV&1<tYgslW
zZa{9~Xpi!Syc;pWT>`L><WduL8#1v$J&H4sUmYC6`U%e={0!LabRFxjJ0F$cc%ypc
zz6li$VD?{<q)Af9f{LgM=An?gD|RQZUqRd;0Qkchnw-MLbm5x;c_GT=pfbU?ePBfL
zy9!nArwUFm#`8`PgYMf-=w|cZe0_5izl6=YDszL9!$*0Vc6@aRKE^v?=vh6#*HJ;X
z{wBjbp6V=p!Wt5Y&by3MG-8LN-uZ5-fst#lGuN+Tn>CJ;+m?<?Q^xH%<+!~kXV)9s
zO+dFLgpuC&ME^g4a7GnE_TBK?3c>gWrm{mxhIECW9-mKZ@;{x)F&VtzIX<$_ludAH
zun$B0hg~!`-*Rq_Mas4+iY8U-w?hh6d1nS(Mv=M!)x0d6V+Ep(`wBEpHG=7A{a=k8
zl4Z^6L`cV~zuRz9u3x5U0S{%rc6oo8ZK)GcGlynrDPp>>mYAoWLL}NwB|h+4;?Jg-
zRjYl6@#e9|-iGV3Ce4O~Lb768i_dne0MboDyVu2yR+M)_$W$<f_2*eciZ;f$$s}^^
z4nNHg@&kmpxTb^g)mZX!i)l`u;*%fpI8YQ?;($_xEr$}rmngi!11iz*Q05HI`TVMB
zNnD0@KfoYV#8u=+$?WxfTY~ZiT7C*BMKq)iT)-7?ItH2zMEleTHJIKeALc6F#)y2e
zLO#q%DeyyU#NoYCM&iBX984ehg_tq@3<XnX%?B9P>`UP2Fdj=|sM`&2h0N7uX=%Hw
zO$pxSA;#Arrkya8m8j06*?{M&M6)m=@1`8pFRslfRX)YgjW7sf_`A9?>qt?fmK7cU
z;|+2*7nu#;n{}0|LSHOJ&9OU^WV|jC&1poF9s^H^kcWU;9|q*{EqMWR5<>Sdy1ODq
z2q0Yg#wH7GfN!XZC3J`vQ<FP@IfnWteK=T^aVbmh^G=M*-_&banA})&s6q_+Qp`8W
z!z6UU2jGoiS?95m`{P2F;@x4Z+eKUYKdA;a#$(L{d3D*qro~4&x@xZYe*YyJ!Rm(J
zIRBEuetqg#oWE0^v{kBHLqZ?@huCUt&OZzw7IQbrs2KPc4PI!Q@V##${J<nMAdL^-
z78-y4VM;Xn`K4(*bQ-d8*=MQE8olox4Ak(4luzHSBv>_%k$=njr!(fzUcX{k=|7s?
zHcSpZj@q#4yi+z?!m3^&ixMb(O8eygHH0)H;e>NP<7c93p!MF|e}Lvy&cN|tinvYD
zEByv4`sR^&KkY9LYnui8%ku$J*XQ5wCQSp?Enyx&bbkedbK>&4$zG#xq$Tm_Cf%)7
zF*v#oKhNr|qQOsBdZ=!6aZ;_F0-Pu-v7JkN6*OZG)E06iyHy@Xk&DYF-9>r=WjDxK
z?o;?&eU`_5SR_Tf#HjYD>P)af<{(Y%@Zcf1o-NB0#*jolEdyXalgIHh(vU|czfoku
z*8(si27!bMlO&9QOyue+)EK6dP*j>!cv@!(5uTX<AV$wT&U%P32f+c85m04|ApG6=
z**iF)lG6@BjTcEFhuM9Anh>HWqK+^dJjJWI6I7dy9}x!xVsYXjzi0+S0Pv0+w!hA>
z<?p=(pE-9N#r8tP`b@qOTst^3a{d3WnC*Y-I?O__f*?G0$w{<Hp3T(I;Q@fpMcgZ2
znPll(TQ$}=-bXiC{_hP&I@uG8Dc@T78#*=J(4`^INc}+lMP7q5_lUtgN85Lus5;F)
z&LnhC`krF%97rLn!6zozkHK#+7X6c4wn?u6CUUM@zD1wZomH%N`_;jmDZOhZjN6~z
zpFlTWlx$fIhp5IGX=D0oYZNIl7it>s8W#A563JgjLxo=L7gmwRc&V^zAfk%*wd;+p
zg9z(=^bvmdhEy2G-IUFV4zj7s<>v_nZU{pyiY-NUq~F8YR-7bOh5o1GRS6$OBK2`Q
zS#?mV$e`67ce&0zU`bSxB;V`Co)dK`UElofsKkVtXGE~m7UR9mP*qghK6{QbZ|9Bh
zV65U-65g2oZiO^}W_RMFCo9Ky#g+N3)Pvvp+ivwva1xdZYw*@;T<o2YhXHSuo|+{M
zR!8^o)NCtin}7I9ZH*Wz@c329<r`l{_j=+0vnXv1RhU~+nNlpmuvj@ML;tj-8^`v4
z0681YmDT?MOy3<B7wbxn%N&y=UED!#eaT2}&`A~NeWxFGnc(Hu-vvp!T~HkMKi(w-
z?6SQUggTNTkIy+xVySWdWn6}aLM3PEOEg^~+qvN$pYe|-AMP`&X#%Rf11|jTHh8|y
zH9A;_jIIhM_#@~L(>1-PV%|I=dUl!cwFG})B=H%h%GL>5lL2E!I8d8+;^v5_+@nmu
zn)cYS`kCn*Id#(b4px_bvlBY}%&h;)CBRY!KOV#R&NPdSWav(Te~OKy;HPAs0k`s2
z5yKYyV^O&x$s!Xn2a&zDDE;f6KBLop1wp=?@o*Wo@BG`V=^e=k6AEnUrtQmj1N<u{
zCp*NSdJ`?1xLtYfDsa8kVhzVm{q^xPisGGmduysi1wizvVGj6x4?l^KbDH+4umg#t
z-_zfhU;peE>9>V@h$-*R><R=IP$dT(-xe&titx#4HP^M*C$dWk7KJ76$)o7E^7wwf
z56H2jVha56KdbOnP7QGY_l?>$+M!zu)-8-+o}~Y=TkPYQQ3mhr+q95bOqL#=#}&_c
z)N<LsJA=-YJ&S!}9ygy|z8nbU2`+bSoX?-&SFuyEk=n9PsG)<*@Z!8fLFX)QT0Ie|
z&Y0qEcm!zUNte3i2K$%S7qv~WQko$GzNRHLBtw$U>%ycE_Dc5Cc-p+DzTJn>W1ZGA
z;c4;xH})$dqAxc5Y@=k(ceDwo&{^J%zanJ0?>pa{?>LZr_Qc_d;>`CUrrL!*IPu8V
z&zvp37yN3+%G29Tu7+jDf3Ns%->6xn#qXF)kI}``QG}eazl%s|o>w*p{>~q$qiN)a
zvz@Gpv%nYqmfGkB*>l`1jOS{2?rOoM_ECZ4q`HkDIfrzX{ZrcCX0CxAwoTw2ugt*e
z4p`7hY1=bvmE(mva53TES*WM|p6T{M<>JwUULA0KFSyC~KR|bIjmqU_b{W}AM;l`+
z1Z&?SxRoq0yutIZJ$K-K)g#b0QM+-ghC&$9_1Rqi%E?9k3TMr7?wkW?rl9{I0Gyxy
zygDTNZ(^yD8Mm|cqdGV7n?wF%8jL^J5;@+8P>r*B=meXUW_O75q#frzu*?FeBN>52
z4ITB861_AOb?W{&vv*D`#xm!V+0QApI2Pb)K}&|t#`4!o0M9VP=`4Gj0<H81ZhOsz
z3A5N-er4PKJZAF}y$!1<bI(F@SsC>_drROoV&2`dPr>y+(9Vl!WfF?uQ_{OKIs3ov
zDZ^)qMpc;88SE4-lC)Iz+COdR5SpKZbubO(hQSl|AmERC9;7xP&qHBg$^_Fo+CdiM
z^JGMR`9E9FV_?gKbt$6eXXfWEj|rRf#m@<IxiF?CTwXf+zr87Os7-cG3TciR@B{8w
zqahqjwA%__I%f6pji5t50{VbpG=slI3WZK<IF_q5rV}V<_3JYIzrKyB8v{3iGTjG*
z`=7oHTK=jWvRjm7uNq<96d<mm$<$3`(tRk~vIue?;65P4Wt+~o8Z;z8=^B)s%krAA
z6|B?mGzgl!xt-9{IB2z43-`rev08V<Mkw8i+6kEHp%_57L$xkECJorHp-yEifhl?C
zA1{JC2FZNLYKz;_`TR50F+L5Sh8hRPlr0-G-4ykY3yaz3MG5`H5`Ho0PG$8Ozsm39
zI0rp+6A~JH8~{7-HY_$57WqO;R&P5-*o)4!XrHv9(d`=p>9NnR<Av3hBm<x^N_8P2
z>JJr68q@>UjsAur4&ZGNw?_Sf>0g1^u<jvd_&A-0KlXv6Jr#>j{zAbQc7yAXiKg(S
zp$##RbtFM=srx+Qrlbgq(64`2WmdtK@k{}~9teyrm)Fu-fY}OzelMhHd&p5vDVvF`
zmUX3=*D{<|f<s^x_qKYRJ$rsSQUwGH70qku8%2pD0R9o*`}BXd?`aMbrWZa9X-Ewd
zLF)96oSMiSmb+bP<G;Vxb-Ft-8=@o$(+c~PDBZEY8>&9qZM3`<eWROBV3n|_rnLl}
z3%T3>f#~O1#D8fr6eK0j0$rPO5Yi%H!P&%zfxcRI1h?AWl$s}ztPQAixE`M8EU2oK
z?nOg>)Z}6N?z@MJVlU7+Ru|c#ZkDIo9;@OGe+h+@d|*revl<hNv*8%KwKZ2YMnK?W
zgos#wa|%%cla$fTsPv4dxgIBdUBZ)h@4S0;P?)Eb(QZZX*L|>{Z_JT3qdyco`CAk#
zx#g$()tgeUeG#JCAk+6jjhOF8Vbz$7NJ8tyfX>Do(z~jTi_u(@CZpfOTbD9M9>h-R
zmaP?Bgse@aAF*FC{Mzw)c?Y@DLWH4J%q));t;la`epT)y0Dd0Gh_k}Skw&~B#oJtz
zM?AG9-lL0i=W6zIY;C8Vwi@I|4mJFZH0XB@d`Em#=zaKQcUj(1Y%0;!6ghaCCYw_)
z?gHbEb6#`NSeZqsNDco=H}hRw^^<~#sT>*BXdf!Es7;5l$ToK7j@U=m4h56J?P-40
z@ixB0v{~in=zs2bj2Sl{SDwEM|Lr8W!oK-^#aA`%;%Oty^vn8m?zVs@PPCwZJ+W={
zG3l2H_2rLnhfH_+T9;J2rzv3UQa@qh+LL$rObdcxDc^a^CeQS%T)qlH)5(CyCra%e
zA9DYt$@Z?qpEoX!*FuTX*W9;4XEO3KCoLR2nzA`COV`?fa#oPZO54ZM;Yxiz683ZC
z=`)K?C-6W3<JKP>;MyaQOgAQ03oBvJA3h86A7Fc;Igai*4E88-uHP^B?Y2Axg&<D~
z)WH+p+4)n4l~$JBS~)~7enFSDEZ>!<O^%o^pUjSCzNmIxM(`q0k}sE{=*D(fCn>4d
zk@Nt{%a<RoLJWS=i7Z@qS3hnRNIg+5Ew5Tom@u`%#Z3KmVU$8U$}2k^rRSpNXGVDc
zAAs2!JAftSzPz;Ch>`tIlXjz)z~mvDP?>rf`!ZQMe)L@tThYscPWoUvU>4Q(G(p3R
zEz%-+w+zNVS}{djyjJc!<*u=z($u_%aIDEaj~$Bs>wynDAAO@IaQm-MxuQ3vs$>-!
ze9i{(b(uE@8a=h{=XIe(SOPYu9Cj}L>avBE@T8l4o?bvMll{_8c^6Z91l><WFP^ix
zj+1+zyKlJt1gn&veU1T8N}g_(|GDY~ypYye-$c6!?cqW~wbYYJ$!*&GGCkOas_B};
zXLpsu`oIV8dI_@bCkwr)v3E<0q6GN;bqdJe<{q`OGP$k1o}({6)Z7fMlXl!k+NxW)
z6?skp%bOwV&64mgMU#AHvHPk1D6R!vD@dh|(&qJ$AXz!@mZtF>HMJ8AEjeVV9ksHF
ztU#E1RJ5`Py3`99T5RH5cI$nx+O4ua{<tdrGV#OvS4GQnG|`MxBzLQ5f<gyEs5?>G
z$g^fqkrcl6Tv-;mo1CT2SL_l8%>#sE{OY0~U&6GZ{0go_qFZ}jRcKJV<Z|Wh05Rr7
zeueeF_Cg_jv@wb?31+*qP@4?DG9;LMgVndT4P{Ta<u?{KB#k%?U1`y2$F=Y?XpAMA
zJJe4l;sg|Iu#=@6X=!HIWAD@05xHxIG*8;VHz+|eDMA|N3}cVuje}{%69AVRBgV~G
z?5eic0jp}&_7^LK?aKA<_;f01qgqE_bkpc+>k8aszYAN{5Sx6kDP+@8W5`Pw^m()Q
z4NpK$N*yI2z8m7L>t4ReX{-!x%eS<7i5wRTBkyCEP;XWO$W_USb}Ywi&cFDBq)`)G
zbMC-tstU+qZl}w0%DPm=ASDJmmc4%kO{%&4Xp!Ig8WwyyB{7+BHA4I#9fUn4&1$*f
z{{f0a2?{LglDt7>y{Y;{loJNmhDJs>n=(yr4$iyk{w;5Fvb*!7R<*<NdlXZ#A;r$4
zyF$$^P=;P)+*1`#TNGe(>P$A8&GX)((?Vx_4|(XZK1)^~b@<9m{Z`lmfz>d9uPCH^
z@+vlK!P}cXd$3XQIfiJ}*GlufC52#l$Ui&c(8g!5<|kWao1ACA(G1(wz!ZgQm^*&X
z(G-Ifh3`(pH*##5Pt8p0Svx_YjAASU;QIACm7YFjsme}BqMdeh9v!Yu2xqy3QE&ng
z36gl@Yq$v~OE4X2ij|j<O&Ze=_Zv-w*5_%-!!9LK@Le%x$9pCn)#B=@?}9Cy4F@z`
z7?82JhzX$OLAB6M@x29e#w;IzgCDXkj(vp$awwB?Of+=b^disFwc;PPA=|ydr^;}T
zhMYRR8m$_qt*|5i{_tg?XS^r4LRCyr@Tj@{SpclMe#JkHjRTw$0Eu33w!|pC_T$bb
zQzs>c)FlTu2(C@AoEru5i8Vz@0A(2A6D>#<Zzyz24y0xryK~U7jIpn*32K<K9~HMF
z6!RkY=MkdkXO%A$Na%-%pBJ;Ls9TqslNib0Ks~mu?k!&w7c5EhhK25mhzLie(x?v#
zH<2M4{afF?m*?okfeUN7j4?Is1ud~chuZN$-FM)aCToH-#&~54OYQ*HJSSO_vwH<c
z1f-w^`mU;I=5`W%@FcL|ys&v4$Qln`U}YA!p{eR^`Qhx-ZE9couo#RnL|W*VpuV9(
z_lKrXM<949jS9GlJB=k@eRdBgk#!=w4}c8*fUdt@ap31}J7c-ie)1`ubi*m}tFhsp
zc$Fn<esZmvtq9wJDTTAv{WC-L!w3;1kobyoU1DXs8J|x9((%2^lS)KY)DlOvx6BE!
zA44NWL5g_Dvw#g{6V7tlS44A709%@6*MaIRWRc2FZ(IJe-FZ5+bXRH+S~^G}t=O?t
zqWxbqycRKcm3jkiP}<MNTFjihyV6a<pJ_v4T)^qE1H*4c7045os)iG0LxPoatv@gk
z{w4G7s}kLmeOw-+Bxr8wlIH8IYn~PVp@lHQLnt&=?4T*8YaKeKK=*zwl`k>D$`(c?
ze3!qDCEE!ibI(fT(%@}9gcj4&S#~Mb6Ak+8l&CZQ>ABGAPbj~en%0&EfOA-c(u3nn
z=37YEJCEAKIuPGkllMs8-Pc&nH@RRMJ*w<>7)sL0G!^|obU$J33qsxw*W0XK`x-k&
zxl^%j3t3P~(YGoici<VqBaAWJW1Ow|nPDcQV}t|q6i2_LFNwT>;gmP3kf5l427d3S
zLfi0B+4gKTsIq#}nc93;P-NXsdH9)aM(x9my6wEKW2)ERy<#~y>9;i{*G}+Rdz$C(
z%gXcoN<rIKe;w&Q+he^dMPu2;zk%PE2#^W&{KBT2>%$dnEn~{tYSgC1(d^Uw+>HL1
z{1gcny8bnS*ceSWU^!|t(OC8Vvah6z>x#CT40<MNyd|b3%T2#}z&kh=JS?8lJ6wgF
zW4QIDu6*AvLv~1^_&8Dr$<6SBYp0zgadLENkI8hc3Y;pO)f^RJeAum`(=pGGBPCsr
zBLOn`3T-b-{mZ#W>!&BaX=MvyB%t$48TUna!10UP<IdVCo+|CXA=WN6?#>q0_V<~B
zDMnELoxqfZ6-PeU7qyZcBDT}d<u}wXlc-|*iY}<oT(R$xL~}=fTqrD6Ls?~&nh8Hg
zKWMYxs7Q{7de&sp@(Y8f{1PvLm8!Z@i8(<@$}J06DQ!=Zv<zicw{CUVtwN^;Qk98J
zQ>|U*BIV_;tp_#74GP>8r*Zr0T@|B$uVjh+Ff=H3z<aw#paqRG3Uup^4$lP6^#GRO
zI_dua?1Im_O$D&s0wu;&HH$9$g{6qS=IGW8I>o~uFoIFqoWxlnnw39`4Vx3xBA9v2
z!izC$y+}?d<J}?kRxzu(qR|i4t4_;ov?z>#7w!A20n&@sB>Q{BhP`y@gd91|`BU$f
zB%1F$;J?D83l+h|e5`g+xUA&Qi^aJ<#1*XOU0g=V36bfJlOhOujW@LNB-}#B8p6UR
zG`9JmoymWDa;57d_#$oAw+}T^?K7e{*pTrU1a~T|4t5g}2Um%wp*;s#b}vIa$nQ4P
zQhW8PvGWnM+3DL>297fi2~8<PaPS3CfM{{?dwb#ucL0hj-o~cbcth%S-+utKQj}ke
z9$78!kj9Om6X$dDR2!~wGCuX?ra{9AjIPs9jDYH?&JEVuIg4vY%=+KNIfpR%@n4Wd
z2Pbhh)^}bcyU=iBO}&&1olwfdE^hzQMO|@ybzw8GuE&viH<*-=yY5LUwzxLgUfZh{
zyRo}9R^<gLUJh%v3rF#)IUimz0IvA9U}Yh_@|h|;g6Mx&F146wa{dR<BQl*VTFk4v
zB#ymChoxFxKRE{8d6}2Z7rniO9r(S=AQ)Y%*c3lrwyvAj*){=NUukX{7Z?f&yGar(
z9|cl3Eje|bek&y>a4u+XOs(UMP91FeL_XILEb}hJgW?#3Fu@K$N>G_1E=0x00N^Mx
zoys!N$FIlN*42nDz+PnfgQ5Yw;jHcR^!+lD2d#!%6|Q>;Q&j@B(d<(5#$S&%u-r{u
z(xj|8GUAH;5FKh-pY(kHV!7MQy?E`ROLEd4Qe;8~q9-!dbNh*KWyy!I-E^Bg`9g-2
z>{`lSvsFx0_(zusW9d~&YO289H0`O^N2_bUjTnt$#VSa;gDg=ImZ>riM4=s)<a&BE
z{BC9QyIt%h;hu&qznbl)<GKgiRd{-%Kr{+q*K?`2nQ7AByq*Lx6a2r)lsuU_cW)|Q
zasD;&)4!)=-mP|kvEs8Vrj)T056X4fatKwCX{GRW(dZw`qELVNEOb}K@Y3|*3kPe}
z2fnt0{OG`&Y0nDO{BpO3B1b*Cgh3{MEOMeK=hRb8`A2#;uu*ZoeYXuN<-)u%D6wiU
zO%r!y3wt5cANvk@m!|dLj+gT+A8ijotM8?4Z#OA)LJeOq`I!pXMgeUc_>;pahJqeB
z+zMxYfd~EP$ph^7U(Gp&O*>*)Y6&E$i7Wg9)4-*Q1s~Sj!yUmu;FpMl9?wK;R-8OB
zhmQKWPj$`OQHVi80}Sst61I<=w0R-MQ*0{EG<5b-(Hgv0h8#xQ0p&bQ(2W&r!OG>4
zA5qh|(D9z0MD!HERxFps@rq%%a-zb8<_TxTa7WvKJR#44VInx3Kxz)%J7FnBu%da3
z7_WzXK|Rx1&Dn>5mffg~E6d|urd?}H#EbUB7gp@HqG0fC9-FZCrsOM&HnF6fxx^$h
zV4t?jxKWUJLIX+kAA#HSH7n3C3QB!78y!0zwCCyrqwv#HK$xDE6Do*JMgt50;@zP}
zmR(3tKzsm5@>kIy3e({$2s74tL`zFbGUBpWu~p}Gf<0|gol@4-4#`2KMWq9-VqDDq
zHqW2H<{GU%AI_+I2=kR2!15U)Zi*T4#r}eEdnUEd?nJ3eX9hMEdTh}ZSRJ37#Hjgx
zEZ^uZpvkK8C#OhHWoz0ZAvwCnes5Qe+tmJ4RPbA7H%`gEqT$CWX_r>;9KqxX(!=9F
z&lya#A-~>vy~C+0_vGj$suWI0a`Znw65`<^^>Hgp!SWVbO!+h2x+HZY4r0#|iV@2^
zB>T9*%7V}#zYuJ^wlm!sSBGi_W%Zsa!A~^Vu{^3nd|wl|5q)>zHM(PHnk_GkXG&}U
zku~}BjfpwzpC`vUW%qn0&-!fb2g}-`wat=M0WFLx`GSvMfFRQ<RW06)lFcCMH3-Hb
zBq2F#7lxt+l=`%c3IsiC@A=JnO(WBRRj3bPY7Ow*UWIvTHi(v0p<%U%6$0Q5myY%<
zP8q?P&|gV9)*2|8;xta+y1gyh2v<jknzHR(8FJZKVJ+dI^{kkv7{tD3{pR>{!u(ZJ
z*V(QyTF|lDRuJ;BZwY26mxn0XmQ73X``Z3xL&&&Xs-^%EoDoToSt>$!=G6FNfSN{?
zKJ=IgJz+QGWI95%-#f#(m?u3s3%-`zX(>LBw2o7AS1m@^Oum}@jxmkuEOz`Odafsh
zH=5K;6cckcX{nmI?P7xEZh#YE$Q`0fH%r;L)i%_chk`r}0^b&$2u~w(fB5;v93Qgc
zzWe}7a~BSt<K<$>M|ic@9}0g86GT|b(zfTiC7^z31a$dN2ieZXheGjR7bN7}WYzG~
zM^4q?XWB#2onTBhB#WF9nnIiVl6-ice43=fNEIW}%pzdH%_V^usKS!N932RJUkOgL
z0G!I(Rg~MmHwV!Yu5NjXu?~KdtO%(0CGWnoG{%V*l|EEnEd7fLHo~0sjX9GqsBq7n
zg4+5eL^ScBlH>ub;1o7EeR|Xc_jDMZS{!Phof$&K<}2K2;{f${RiFg1IOTbOzllCT
z{l<v02K&g=1=U%5$r`IO#))jb`<{6T4pUwzVE9PH3&qE#-c6dzRXqDfQZT`G>H&|w
z%?OY^E5)efGBrBmqQBOpGS2IHdY1JSNyRf$w*XKoLhAVVrjPd|*lSzGO{I;(E63k^
zVXVj5A6L?W{^BswIag9>2>AYp)$w_NaRwjg{Z$#u%25zqPzG<-*k>7Mg-#KCy{n9o
zLxL<_-bCK{T*VYw=9(<TVxv_&E9aP$y!RlhP&7;ui?eEYyMy?V_AcnebhZ)GX2mYF
z6@PwJ(nAft&|ih7#JU(!b}q=LQ_11%D{Q9mdKXzxi_d!xa4_W|UqFD0Jf{-xgJt37
zI9q%`vgVd1B@+TjcxDv>;F4vQD5Q`<Fc+Co8ldJy35olih7YG;0<uf<Fue=A0H`n|
zD3?SrLhNn!mD2R=cM1UWT@krW8o9bp9>B8zzQDMjNuW9>Q-T#{)5xb0Af5tG)69Sp
zxT<*sR+NWQNU{@rS5_FEl%&vsAOHAHcmZP1!MyO(TbQO2-qxe}zhNu?SKV&^7i8xD
z_p^~HRD5jXQquI>Olh5s!UWHP-yAkXmXdvXq`SMWv>naNo!Cy^hbBzUys=nSquOo-
zuz^en8>7n%D7;(6OQ1)WpwbY*1XLM-)=AK=Xuvm%#@I#vr?mrX)Y2NRmRZ|{8kDB&
z_Rgw@bT`z+F8lugzco%)3r$Ro8W_oFR0VG*9FCu5!jmY+Sgn4F$)9{DjUelYypG|K
zzCsP{lm_{W3f0@9(|!#!qS7##X#Ie8<RGHc*&M#y#~VqPw*U3q9f-z78oG?pp>O+n
z*A$zfsaP~2h=W!ugoqCQP%bu?uWJoGd{+E^JJ#V;JXi5%3ipwF^tAu}VJWkyuGNKo
z8ob})G8t62FO1qZVc72{VzNSf)mlBY%Qpl1j(kVfYS2WM@A&kj{cYi_Jun+ov;u=A
zv*NSPXzNs~uu|6z`QY>>`iRf&Y#Nwnx}Ph2_yE2zj%7kjO-GX>7=K(c2vwTiR}i;N
z@Crk0_lvc&$ncsVmG6#j%fm_F6M!g1*&x&#3hD?}4hk79ExP##^j(i%{|B%!tPt#T
zk_>&+L$7*eoU>h;^;c)Fs>?vczT*)1R5<!gz}*Fe9B=RE;oUsj>=t<a#*$NJS<JrT
z#78IZ?X2Tm>afuCJ^a}zCfHxa?CaR%2!Dc!R$zTEZ+d?R_IpO^MK@<U{o5({V-#GM
z#D7aN3kKHVYKcPW+i7#+-6>~n$hIxO$LBG1=pXf#HvM!_Zq(!Gr8!E%tFYWi-rD<Z
z=nh}sKtcy!rS-&#&ctc9=IG+8QWOU*T2P{rM-3l;;;Zc9qIZx?vBaP6ohdO_csi*U
z>hJlJ#EJ!Pi~=r>9O^F-6+jjVz26<g@~J#!F-S{CCwtw2H@)pl^%l(^NGwegAlOaY
zoAe8`si4ODS?Z4!DF#|Ks3bK-&d48S>b;F)hS;MQsV^hKAJ{_GS~wzH-Q3*o_!Ku}
zed0no@%{s#W7?e1vJr79gu7_m)_iThG){p<DXj@IsB|cK@U{6@0FU&7o!EEXd;@+U
z#hn_EE<q~cjl?L8oxlum%Ozim!N4c<{I`x?vI4@{^&>ZmVfFpIS25P<s?XHjO-h*{
z<OIRd+R84<Y4M-rAGtj3o;K7U4druX!VhLO(#K(i0W0vuo2JqEWLHi`20w#<{=E!I
z>0Yv2kYCO`$_PtVyHjKP5AVu|sTi-&oCWu$Pb4L-LN!E>x<ma?Ls-9QmxQ8xkB{CY
zG(5!xb^>4@GnR^r2urgJ&OJ1he@q+T4<v88aTa&H3KRXObK?@tx6IdNeZHkeoiz2L
zt>mO&v!3>>?f3mv@eW`h_v){l{u<-(jkhWM0@(HWqfx#_8`>1#fyk=<THBD{GtRb2
zjBUvg?s|HNkz!uQp-^e@`G}B9R1RT%bKIFOA((cH(1ggz_2yA~r0D0V$PtzOxz7}F
zjoa1wv-w=ltO@$Nz|*A|JHO4JB|cEFzdf015|RVfFH(9Hj6>pnRswM2TwlLBYwb{%
zA7jkLH#~QHGL<mG?X>;tG|2U_d5pUGi=XbtlIkrJ1L~-T9@Y~U1$~v9{_UXGQ{;}&
zK5|mpjQk|Gx(TJCm*5@}g)}S3ca|0>R^Yk}uN)4Uv(X~A$?z|Vbnyjevh1;k9;C&#
zeG&%L^06ynvKXv0m)ojwJ?F=NW`Z@Jy5d#5{z8VM-4F-@IL4h~^A<pRazdh{t9&;9
zsA=lk5+`c)(=*GTwW?{a|M<lv)XTEG14mQl-1fOs8)uCA={6s*?DltLQdQ|2L>{Zu
zH$xv>n}UnY))Y&CUS*aQ$I=0d8DM<r#}(Bt!m26vi257r<gs@a3}l0<Xczhk_Vp;l
zU(Evi7FzEJ(yv?3CCap+eo2<iGoCKB=Sp!<@o``3B_+y|VpCaN154`Iw~8_IF09`?
z0a(V(^NR~{qh#Kwylb_wznv%-6`)GAWcL74m|GgDKYPC#T>wFTpp1p#Nrj6SLv%gY
zUg;#O?2C!gGN}-8^fUGs;mjL$b^Im+M^8R%b-EL73c=n=U))*hSwwD;d2a5#WV$#l
z)t9dgGWD`-s8yDuzhZ^b<=aR|Do|2dB}aA&zp8Y<G0)V>ZK(Fuv89>-LuA*V7j#1;
zN@7!d=><^9mc(yY%o9HFz-8ent4Mq)DP>_^IreK?<XiJH+BrPhMaYc%Ca-f0HhV~V
zJ1v{OR56mCXtK1IRUaT4sjAxB<^ArR8JqSCO<{$--6Bz<GY=`{SOeIj#hioMnEyQL
z4B7j8N#Ioo$uXUj5azi9Z#9p<_Kpf{&EU1q<G=hcDwk^4$elJtwzLHZ>(ic`DJ8yi
zgTfcQ_D70&M^g70E%%vCtK<bdFD^6;CE7$(;q28sFy*B;V`-V0s6uR~W}}7Oi`g8-
z!cOlHfqDb8hyr32C%V(Op7yO54LmDL7;m>+DJ(|vKLC<6GlK4!lt_acNI6q=vminI
z9)9+rw*d5g;8BZZ`b}tiI)@)axkXmR<M(b5bz28qAYUZQmLG@Or8?H7=G-LbSJ_ta
zqt&RI$Dpa~qZrY4N?2D`Txq@P9(h`fk{QyGc*==D`@qCzO84kUbsqJFm53qnE#L4f
zQAcx{LgIQd5!#{adBEx1<|q7tpuxaPiqqwvMrHcHmuyGc>jtYlDEVW?a#JG2>`PNp
z8ltlvYOEeBw&c<&+*RTZ-e+jYX`Gtymy?}`5W7mA84(;`j~>i0Pq=e8FFpl5RAC|M
zg^U?Awzq{9U1z2+h7;ualIUv6p$6+jpvX^x=2Dta$#PYJ-;^)+ycB<mkLY|^NTKQM
z*+GR+Uny3qFF$F%J5YaxY@bzs`wtMG&<gL9D7y-lm;JOqrXdg!8&xQ&-Sy%EevsL#
z8GWbb$|50^zp+|oVz1y_nXs2@s<?BQycr%IYE;j02tMM`UwRHze8D@f@ta6JFbv;d
zeL=`!hR^mktADq%a#R~%pl>>r=-YSddaNGWJ}ds|?PIY(N#AOqBzNFVTw`X6<D+`d
z+XUSl6(WAklz*yd7qn(Fiqh8b5+$+vL-`+IHomQTcgO@?oJ_m5{zp^U7m?6-)}Jw7
zqtU8K8?yy$G`*K+W|OVyQUsWUti=ZGeL~c*<?I@U94!-knYzeMwezKDk&v#+1q_Xn
z9r2DFSah_Vp>0MjTxl8x3{RhyOA4TWc~=t7)UooLuUWCzq_LP%XjcQ!w{(K&>UD2K
zD7mzBq`sruO)Yw&hyAV{b#x38c6BiQN9fh)F;&|x_lY%V%Pj79JwvL{&^Wi`sir=e
zgVIs8$)EABC-BjtzQuco6ygb)j(UQ5x(*k9vu+o+cPz~8u!ZXG2^U=MAbs8YCf~vn
zM54MNInMomD#b-Joys|sDOUc(wk8>jm=5`}9DWU|E^f!<$*W%Z#p`U|uK4VeEOuRk
z=zksRuD(Qm6WGz$)CVdl?H_gcOt^7>B+CjU;42(s$4t&#udOaGi5pB`Z{oBHj-Ctt
zH3aO94so08gUWBMh11e`lzpp7|EMB1AB!S^XxwSafnciG1|JdqNJJnXUlE@h1Drko
zp+`^7gf*QDRKZODSgpbq_X8VeLj45q$s4Jl!egjP4zF``4Z-c5D=V{1EpBoAAq)xg
z-R?+{U6Evj6s!xBcgDDyWE_;B%L{IURD*%s1~h9?yBXPHrx*s_;yekud94|=*QqMQ
zavNghRb~tjszyxK+%!?rkgq;g7{4H?vp%~iiL%S+zj#ld46Memp7sdJYw-`#?7@rq
zaQ#OMZz69c&ag!JXzahC=>?|hLSA-0kXh>_cct&UM#c^Zxa}SKfMu`!S$rSrVig;=
zOsphgv6BZu)SfdcarqQYwE{c=np7rB_Bb<ecX=sJwge{)1pv$skm3SUre(YxQ_Tyk
zrj*&;#HBy*3|Cwt)&;Tbqc{N;5?>~i@j{Qaml56U3BgG@C;-}kCFD52pNP`Yl6Bz&
zbhT%uT~KXZ=TMlcQ*pdCt)+@l1%7@)p3@b7pP_DAk{adpe)==UIKLj7s+lWjhJK>Z
z`lCc(mS#>t9gM9bZXC^C0yjyBq<m+`*VS4rbBTa1p;4)m!F`E<E2vT<*;!DOpd7xH
z23i;$B9mJD{_EiMgT3uKn0-=CF;S^#rO~t0DsJp_GoLlb4nYA^fo@hNJTZMO;_~WL
zHLTf_K$<?i;sa5%4x=pAY9&=hH&8P(n7F)^0K>8rrhhF*U?rIp5*VI~iOFz(s?xz4
zY$WsPDB@HL`FC(AboP2`wCkNvu>!VM*x_vbeUQ2ii?G&Co0TKl^_Ogh5mX(aTLNLw
z4IECSx&^%P%ClC-(n{6Kx)cwo66P*73Shn@PEHYA_n&XmN2`jDHK`gA)u>hqzAJa<
zUtF!yv5sR;niL`sjXC+1<IwE<;kC&W%y@9Pna(M8Wcz-=uFxC@l|n_#cKKulb+sZx
z4$iMATvt;~(W8htu3<lH)-0EH5@Y33KSynnL`%q4RsChZ)<aB{f<hy|!!wL0XmXHv
z&Xn(xa`V?;M~E(kjOlO5YCcE*{>W4pdoQ$^ZMNYv8Cb`9plSX`!btf~F6rw;F?)Wt
zv&0qgTQ{`%*nPE)0coy36Pm~+bXnRv>V2V8U97ywZWIxGlz(ptc-BVftQXKV<`<lE
zIUL~jJZBL1s1F~Fl+oMOEzC;eRT}b+lZUc6EAOCi;*0n#8oAXRe=CK(j?sUB4@Ks&
zScC{6QaGsZvTWEl(_Q^EBV)Hu;Xg1X5_LJ`h4pu;;_CLePIUH_!)t1ODYCMXm3zY+
z12oc<@>9Uc9M4o)vrKR87+U8+!MkGO!S67pAlXMzoytAy4!;Gva5`e?y9&+M!la~S
z3=R|n^e>+98Xw^yG9}BF)GLxkR|n@P1onxb7i%e04Ha~uMMi`~A4CPL^eQ2XDwO5k
zGv&T3qn^9qV@-wpM$P$3V%Ak&K3bms)Not<vp456C1Gc)cLN?<-vwo3AsNEd=Bn|E
z(Oc>{9{!fCd6{G7`Jp47Q%kXf=>T-}@uy*&ro3o0!$f##pX*gzN+jh%*1pZVWU5uD
z^bpwjTGsMtCI{q6MQD2J^_y%hlm%(fU#rqHT<6->b!;WFGC)Fh$v5JhQuUos0pI7m
z8JQX7!-L@pjV%JeE;P)^o9olti8bdTDp{AvV)0P(H-eWhs}}{Fj2S_vpU4wTrXBXb
zqdw+pUH&WOa7yFiCkXv)f4_b8SuJ+z+Z913+#pKO2n3<S*~*(4lofXOH-<%Z_3<k;
zITvY4v&HRm&fi43wrw<+m9xC~ZbeKKpJ_J@N>g<sI~|r7$#vi5mV;W_y<b&ejYJ%1
zp5K@$hxokk=AXWSS{@Mg8|SL&gOWl@U0FYc680i<=R{QbAJpySZ=2t<ivrj66<R+@
zjt35Qs;S$wE^s)@1IC|zRqk6!X4DtU|Mb@y&0fc-!_-I4Ny)^euWG#!|K=#_4wQOt
zT=>B%mb(OhO-V2JAP$qLw5m0`$|?OVogdZt?kDgBZT#&p(KS=fz6xW1^1EVV+L<>Q
z5;5_YKK0*~R;;1=+RFuB(;KY;BgYdqMRDv?sXA~A9M3x%+v9Z|G9|;vYD}2w%=#_t
zJySEPjHNeLdvwu{hbM)dT>hH(&5N5Q)fg6e|E42|*DKzbAW9&k)a8wC=er3fFGRWy
zhyg-O)ECA1pia03i-GcK!fJDv#+s{~X1BJCw<66jxaT4AUm?scubRP5EG5J_(IH5l
ze9N=i?L{3Tq^uk2A^kXfVd%FXqCCdU!%UqDxPt#*?k&T6J;^GXIlrbkIZX^i<kTDX
zjAe)URt|)}zoVm~dpHX<o(jJu^JrW<1ejvoV5cY<UWVv5Yz(;)bB??#W;YqO?!i88
zcLzqE<I=@5jo~gfe)e#nuADC5@Y~YkDlsMV(Zf_lmDyW3TrknZqgQxoBd)UM(56Y*
z=vh8kU3ovFaAeQf@h_sw<#+}*p3&K>+S>(!_G=jC>*G7}^=aHFUQxvAo(l=sCZdAX
zS7i=1Wd*65vCmUHV|^w;Gb>NK_FJ|!1YJU#!eKGJwhm-8>DwayWfMB{cT4cmh&|>$
zr&HBg^Vl`qCrVo}{l#(<gVm9=MtuoK=e5no65iXd4Iej^GAx-cl_ih7J~Gd|H7{zg
zz2{ZNL3QRbZWIXoW?mrk{!FuRcqW16^Db~m&Q11FZ(x(HC+_d!Ol29#>NV%F!6v_O
zO5gVq-b6+0gEbP2!X`VrK$cLcE`Qyx@>XNcGE)=AQL`7K%45PN1qSkkZoa<jB1=Yj
zB>=gfD-oc}GTPx?`@a{rH9nX8xeU1lGGzKqZM1AgG5re@RK4x|(PMOkrPdVW(a<Bn
zZY+u|TDe0CDbpQcYV?fqJktbzHWq+_867rKlqV^#iojc3v8k{R?C{uu;%2kuSWV=l
zSF0J;5n=r1x7)X(b*)b2e{x@k4lI?#j?PpwIF+{@Bq2>)+>wpxh5Qcuni-rVn!~C&
z>2ECF7lB3Vfs|wr51OjnR0wc0pwVUE^ov!y9gy)C1-jRrRGb;eV~x2zw0*{73-GO|
zGnA$@Fqh1=-~F`2XSfc_qW8D@jM)Ar%$gE~H9vmQl6A@QfpBQ!*A}U)WUOErV3&8%
zj3}oO(<06ft@k#M{6!re@V;ZByz`pNf)oy@xVXmK`j^LP0kzgsO;giR$+ZZdH}@=<
z3DP}RK`UojOIFJLjM2IQ`@h0?=Hr0fL$%fZ{XCHfMxIDiK>FI5Tp!Wljfg;rYOg&?
z6%VtBdfhjNcYChOQ^2i+0-h8umK>I25gPbi5P)R$#&TPm(sEc@9z?8XNz0hypx3vG
zWC~B?(W3mEDL|`%sn6NhvUvMgi4L<na~5+>v=Zq<z<C)m|F6wqmNMiz?5b~-gNV)}
z2w<%f9{IutRRDqP)3-JKeP=&y&X1SA_X_;Nu{p`@t`luoYhB`We~P#Mg9nam;j^d9
z^O$9bPu>|*-`sVp=a`4KHHLG${sRQ-R0LsKY1dLW5&yt6i^bww`gllr`=}lEWfb;{
zeYlMH&+jxB-YyVaPkA>>JoDOC@>%uPlk(O!I&?D#-?M^$Twu$y{72S8rq<1y$YSyX
zJv1~3o7tzhikWXd5<A&8OC5{D4lu#A-JxlVpLZB4@ewIuNYTh$o=Z*<Kra}L(Nyr8
zLCAB9t9-I@*el?Cp#vtfFQFZ)#z$?35Qa1xo7_{yt$-|V^sLEDuGi0QWdKqm%_1U`
zxU0!^vG&CockSO>`hG>E@Be1DR?(80!FXx{X11|F*hrF;$s}&Ikd?DMHH1p8`2C1w
z<wsdVBk&tkNlVD}%WzZ@W5IzExY&=(FFC~7&()bNf=;#hWLAsrZuvr)iTAL(Sh$7C
z<X?{?#8cSv3rR{Djo{tbv_v&~$6e-D%mq0x7klv9&}<FOjdqp%E<xa@c-AUMi=pyT
zxSlLW=uA;Iu%wF{4dMY`jwh5tALkU~19O@rWc65Qp?XL#mB!G;__)C!YSv&C7KJhh
z)EVw<qv0&10Hs@M?an4SQGcS1_1D7LD1&?iRkr4#L2OsURa*~=Fch}jHR+44FB5Wy
zAepfPsu9)9ig>qt<xn61tN*016_|pR(kia}Y3gAWHZKpuV<1zgCc~ATIQJp&^w6Nh
z8t>&<cGsmmmm3YO^<&oq8D%A^Se(=+E9??_6-8QZE>rQ$nOqz2gs=Q<LfD)AP9%yE
z!7y4|ENeN!5PzfaXEmApey4aB58q<|CERWh7(d1zfp__Z^pw44z6J)@l)uqZE-XsM
zG5PE1(C24GMbIQuDN6X+B;Qs=Aq{ZF@$M=Q+990$x?0WhL8_81Bw%*DD@IaPAfU-Y
zP~I2>D+(Ro=Aq(cX^~vE@@}cfVjoQUlo9_PKppqpN#s;x$fn-(v(kin&k$n`iA$od
zAVf=dut^-nJTp~y6_d6L)xXSz@bEKJ{5BhlL3OiJW3EOK06LycaX*Ggfe`XgQ-^wH
z(^Wxg6kimjT-B<Oh#x8BDes0JD@<P4DCNy>Tmh$stBWwKn4cm!U95wA8|Kv)bjjFi
zQvPt-=~Q>e&4J^`ez;{_N0CN1;rC~@g<6k|=HC0-;Zu1I^KN@lXbYGswI|N6Bx{<h
zH}V4LC$g&^nG{<H9h;Ofs59dzAU@h@gtg%<--}ptALqrU|6-`Eu0n38-xYNE-NGBr
zeZ0*0Wm~7jr%H4vskD4K^0W@Py1FFa;QNu9c>hvl=`)yTW8L@M$L4=Fi^Ad69Mz~I
zIzEW`T4bDPl0!lRe66c>n|4E<rJBp1WNc5An$|>LyI2l_8IAyx`?Nx(cbp}6h*^<8
zMSBdJzc;zaSd>hASI#*x9ko?AXcGsLEyxqZ_sV_47$|h-`CE@^ZNHHHGc&Tw8ypAB
z47*5}&8c@<_I4+GHyLnpd`x3-0%ZCR5M_>Zem9`i6E~hHoyA2=Isb<3xO}FEihliq
zc_nkzyRM2o{^lV2)k8d(aWfUdqi#j<tZ`eA8bo#~r}zbf32>_T9RprFyk<gRLgn>@
zol2m~HGNhC@=O5WLliu+0i}Rr87d$afO>Z}`$-EVxf4W~xtT4m0${w!^MIWyKma1M
z-v1hlL%@$(fI+5X1*p+9!lSy~#RSPA4De|ucu))^I0<r}4Z?Sq+m{#i%)@~O5kg$0
zhw$^iC}zfdA_~=`rD7@{Az`R0I5X09v#E_dVJgU5{@*H({cl{C8G~80lyO~i=6@KO
z|IdqngZEUVMJ{Jkz=OI1clgzQ177ztdWhD1YDC8hDf2Kp%gMv`sSYnprGqj;B-_Z%
zLM2GVi59V2@})f)ko)%HaV{`ctM&SXl~)NX0&I}T6mT*~&Wv>c|F6c4frT|HtgB(P
z?~^Q8OV^|e#@|q+V$;B@$@yfYjvDH7qf@`Y2g+Gpl=sRK{K6!DHv$~nQ*7N9V=cZy
z{n50+ec8)bndodrD5I&<Lu%E7`Aw5OaF(qfBD5Me$%>JXM4z7;=d610)#h1eA;(Z8
zxxL;U`N)k#uriWRi3DE9RUogpu5aH81>&yzj-@>7VYcO+NAdA}p>!a+ce3>*=*%Gg
z)7<tFpsR$}jcDn<$pi76H|TQ}PsuvH!JW-*&T65X@46DNC<UT%e1@%-cr%n1xA;0A
zj<#m|oG}k*I7S~rqB3YnEWDl*fc^^N`4)RX*t$2!)iz;6-|cKobP0qt4vY*@Amb8Y
zj>m4T5l)oQ3pKV0F6$F(3rn+_xfA?Fy9m2+=JoH1;CnCfCZ>`-oXj}d*ZRD8A!%ZK
zxw-0IvAM|-xP95>7q7;5A~;ebqXcD6jqdVRcVbob-$(dilsw7(f2cdFt+?7QN<*;V
z?i$?PU4pwi1c$=iEqLJ$g}WB+7J|E5u;5-eAxQYT{<9u^2Ys-wV2^h!oAa5>;N<u=
z<ulQdfyB>m6Q>T^hPx7hhP=oY{+Tvf^?3QX6O9OI``f{X5%UZ+H8q-2IKLnvOn+k>
zszz{CdVt1>gV_1NiCgnnZwV~FXyf?v&z+j>c)?4K6E^Je-=!um^}Uj@exGxP9E9$K
z&hwuZ0p<jwf)%@;IJ)Zl0rMJtZ8pn|v-KN-Q;3LtYQqQYy)K8&)7(#+hg9q3e+fs7
z#$$`KPHxAKA|f|)W*ybs)1T#M+z3D5?p(n2FGh8((jy=5;&Nh9o&yYj14M<0@*s3A
zA(u(*kK>wQj*)jo;jTd{AJ)QY#pb=Z<Ad*jlZ=#K4^_V^)70q&jr1i33mhF)@61|D
zOInR{A%`?X8Nu@bPn5_(yaP+^-7ek|^ePQlCG(H<^H2y@esFI66@}DyWom*_UXXE`
ze`TF_jUvP5@eka(P?C;NrP08|2cGMfJTTzrzN*K?l@vh{t4GtEHG-^6ji0gMVjkfi
zwc5}`A^iO1o!D6yZol)*It69j=eD85DhZ?Sj=r++-|^n`m}M9<=GEs?zRC;MDHX58
z6Impd1DE#nHSpzUfo-Wbn`b*>jQoKyQ<8sbz<c(2tb=cQJZZ2qElxxxD~JRP7%Y;L
z<J6_LY&V8A;flpnugOZD#tqxBK&bEmn79oazE-1Re-VTZJ`?8aiqKu&nD6y1ER#^$
zy(1ji;6r6{W^*RB5b>lw!fzCmWA^>TbFO~{0rTPCKeuT=je{K^<<Z|}YFI1&M6pex
zE)}4@aNm|Kr|LI&b+n|^HCe4w*S0hWXhPVjCv)(%!!VnwbN@nASp6&0M)q_*|7zx+
zchapulv$x@C;zD{qD>3CRQn4ijmZ*bT-!)oM>dA}2LyN2hN=9DhQRmV{slT8t&NK!
zzOQyC6Qd2|L;zL*3J}$>B6((fx)2lWNFE*iQjz0KpM5epk8gwL%+dy@!O1*M6TX%*
z?X!3dO-8z_yE7TaVxcM7*;wQ1mQ`UwztJ_@kGE@Fs~zG{6{Xh0PMhwH(2~W>>CL`g
z3z+N<8zg=NGfvA8$vg+22l7&jjS9jiSIF=y(0WQ)buH66Pq(>)_+hF0unVe=UB-%N
z%1;^K-}D0OB4&+SO-DEY#bh<%YvD8up;O@Y{PD<yj$i~i-mL}!>A@l+Ru=q(T(JlF
z9G!@SH<FePZRqV+lRhNV%|L|VhKA9;3D3&LeF##=Wh#$m%ST%zEm)nYD}eT(WB7a4
zB1}PW)HZWt8snFX$O@XGXo#+sZ$8%$x27v?G9zX_rO|*XO!N9$g=$3goP%}eMsMZ=
z1Q@9>tx&FT*5{0LSAAEAE;#=HqYq3OyNWtI!kp2v_ho1kdHyOVf4f4cr)@m{@NZ0%
zk5;=ye1Apfe%9R|mHrw@)TfwTiq(Qp@Nli7y>IJYp&KbVpqA|@1-marge1V|2_s-F
zzb2h#>4V(l+{mn!u8%bVa<AO=J}~~&7{pE6aduASMH7vGpH<-YM<v&l8+SNjtsiqJ
z6pL!nn!t1R#Ni(I!8hUU6$mL4w=R7p>c@1&rd=Bog7I=`-}`|b1jnCT!(URh)oZAv
zEIz+)l@^Nf1Ys~)-kqQM{whQj)bjpooKGw!_OSrq7%zBaXe3UXm<_Da?rGJRWhy&S
z-XYX%Z+&oOwM}Bh{ox{OiO%i6l1FsXy|q$`!*bz@ZSRu}rTsWCkCRpFJDd_XSPh2|
z<_&R9E!68XLb{Hd+cecbcdDpWBo`2=I<x<>$RgC9dm44vGG`xsfIaQ^-KDx?@ryAk
z9NT5_L-U85F&_vZdHAQbsVWTF&mvlu;Jn|WZXU6?GRhn``JHWA^8%VoadFC;rI}0%
zSi)RtPS8;jQAZ9E7H3)l?d{6r<%&o`3^zN&+f51lY0?a6bwqKtQw=%-GLIvpm6dC#
ztdcbLbi2I+^BxBNoEXx6K!aVFgL(n-KRh|dqeWt9cH6wRDw7~sFNqIm<o{U2USHpq
zwzmHjdZ*jo_SaGPb3|o377h%sc6Tp*j0gO%mm?BsUg{RA|7IMW#<xLs>T02Bcu9~A
z&B<<7OzxSTRa$0A&eCyxR&$)IGixiTWE^FSOqKAFq!p;HXXq$6-TLtXuj<rFQ8ZV(
z!;%vh=Mh|M#iraHVpljd&sedw*?iPB(ATlM)&iNAj0Aaiw0eBOR){&?I|b_m2Wobt
zW+6{8JiCJ~D-;E8FkZ2beLe3xOAg9Sn)mJ?dS0RUq?mjhPG9<gGHGP6!0*==n+N}n
z+aj*+1QcQ<0jIKbUNh;wtLS6&Ch3p0J$W{%vPRNl-jfrh=h97pO!~w>ayneiLWiF!
zxyKSXe@7|OR_Fu5nAp;GAtc1>))CiTm-_R;hPk|ioRi~Fx~g^{ZvH>!S_iNz)%H0<
z3BEs}<*naijk6bB+OXw4`+*-tJ6ZEpkT*p;-ZMsB*bKr~_6lZhfD={5cdn%xWtO_c
z?(ufxje9P(`4Hx|^qeAl$(2QgrB*J0&lqad79)|KSgoK%o?6#1r{Lo?bGbH-fb-9~
z%F9{R7H>1D`eU!Fuugx5O$*#FJ4vOjEs}fQRdMbqJhS5brW;-~h3K>dOl=~0$3(O0
zU5qG5d;tQI9`*HNvNE)+O9Y>NUV$8LOf%ijyeYjAF`|0Vm?@Rsj|Gialq%X!zy9P3
zJXaPB%E`HC19RnxZH(&aH@7jJP=Z=!NROon(p3|hkTw4?3wR9YM`(bDV}8<?ryb{L
zX?)^-;H1Kls?MKGF2E2280hq(bSN;j_h@?_FR*I@=~KH(?Kde8-fM$DjLE;}viL9D
z3)QJMmwydY$TN?))D`{S>hg2zg4wU~v!q4pjh4Dko;wM|Wdn?3)dUW*FyCnukIv+C
zET7bTT?_eDE`-mk@{@n23(7zxzcN?VJMTuioeyZnXgL0EGPY~(BQt9=MZwi0fDp{g
zSZGK)c>1a{X-_upj8U<__}LDVM&LG6sJ_7L&)8nLWkX&!4H3R%3xooY#-%!AZ9~Hv
zc(le9-HDqyZkYJ8tv-FJXZAHwow~LGQ<gcHM`4j*m~2%^z&gQq7r=UuIe|o6*?dS-
zf&5uM2-7HjW*q#*s&@@^NHptUkv`nsLy|h61|YQ=Ri&C*X`+vep%K;HSmQf-!cPKI
zccPE?8!Aqi1uTkbkRW~wT(-%9XGK&v#ZQ?#EyI4SDo#l<7Oa0^MUt{!^X0rT&yrf_
zBb_V!W(tK5?CA-%XU=IeOFfM$%n&kl;a=)?5kR@%L?|KOgmo2+L(ST8Wupb1PGTqI
zU*8s|iwUKzwJC7?Yb=q7e~z*=!zWNM>n<crDu1CN;=_1<)BPpxLj`nO4%#M55jkjA
zK_QLt)S@PUTUg6&PJ(~&XXvgyC%|w+;7(!OC{j`v=M}P<Wvz$V0)-WOu6Rm)o%MoF
zGF*?<JL2YG&hcY@&vXTw7YCfL+G2<fi({VYN;ZO<FqJ%A2leP|;-~7JnQI?}sS2b@
zNeJ5gj;<X-t)@-hn!9DlUDhDcKJX`wP1BKEXWwCrRW(hD6Po*4C{yW0D{-sIQ*siu
zfwNBs-V@Y(Oddf7N=(h(UdXwYFKjDD)3VAx$TW7SMGf0qIt7JjB>V@1FOKRdE@@*9
zrlLWE`W*fH|9A+MJL>CQe6G+DQwQivniGy0z<>Q_MWzEyh8>~ocA7kM6vQe6wpa16
zO}g&0EVZQ4*vQ9C_3SNYxKCW_d)uK?+zN9L)navT;76;mh^>yOz>uMQhDN!{Bo#2?
zSo9<-@u9+K@gy<pIt4Bg<9wGobC+>8du$jQw*H!f@6X>LqO0F7E2IdQl)sX8O$9jv
zlvq}!gfcI}TG;52Du7iH9u2)mOkG2N0pCkJC*N7<5fhW=zcbHo=t*@WO<#fldf&W5
z*gJ3kRkU&2+ne#ji>tYtNERed2}1Np3<dD)SO*Gfc{{g<;rfN>x-g;-6pk<u-7mG(
zMN9;cp?CwGOQ%u!`#K;2-B2-91pTH^$!l#95hWz4fDn6bcDI)tEl$w8NK<%V5$Mji
zJ<|xhv;Djj@`xiQZ*=oPL|;T1t9i}G5N`3ZB=F)J`c&7E&7#LA%z+mql0E$M=CRx{
zPvRh^PX6&v1KZxi&%Ct6P3Y#&bp7!So#15un%a#<Q1_eXXwbCH!MC)T7WSiELq*=A
zo=19>YhLp>P<9O4Xu2G`bBcw)lcuS7{NXI6PMTw)(GX+B1mmcHb%^evQDGzb<iAbl
zC+ZSaJx`3E-O_g{l@+V@d3isuT)_?RvNXTAV~OCRh-TdzUQA24Zj5kyW*;PWpK6_{
zlRl64OXpw>yVB0z-y&%N9{-Gy1{GrPC<ET|5k9rGvuJe~=Oj=Jfkk2`mc2D?M-7!-
z4*3=~FWuT0jwdMk9f8bWBM*trK}+!gvPF#fN$or`P|OT5JGrH5Spxz_6fIebI-tgW
zqrlwilmEFsyFr$mczfg?!rM0r3LWw?-nZ-#1fQo%;H+^n<Lw@%jFxf;ipBSbbAvGg
zE3SQqLc2r@TV`PlRfQIH{QD9_`rQ&;==`Qi);!MW?W?Ex92J-yCQ7&8A1ME^P^9W$
zW7S@0siyGQu&Szx_7KyO1f2<I(V_yPM1fUw2ZXAzgiVKFD7qL|l$0QX8X#=1;7kPX
zm%T3L7!!rPKZ&%~bab4}nEN9by=~J)<9(>x9@44UT*Wx@MBPYZs_sr+(DL0{5aAUi
zTX(_r@vl{22AZ|tzh4ZmdVhQt;t9QWcr?7t=^|q>P#?=zytZ;uBP$JgR%}}zXFcB3
zKk+{BpTc>pYdX}3*AU*MdI*gNjE-rpCJf&GOjcYk?M_2)Qt%<j?r>agZ$viu+cG5*
zFVZzFn=+t5G{4q8+18{XYEK@p->Yr4#=%>T^^+-yYZ14?e66(1fr`7Gg}5y+y3MUo
z6d**-LT*=hB8Mx*3d9iq%Gd1f@u2n~l5HzA?ExtF-2Ul)GW1tWEr8@8%DQ39wla^l
zQzWsisaRsHYt~dD4L5f1Q{y&(P{6%$(@^p99!=K?&S0*6gwl%uE_GJO1=3g=7#O=1
zYL<aWbkfWxreHKNV6JYog)R{I1=Z6xxKcrn*nEo8cNt&DF(5s^e;9#sr%K+7kJkDD
z`X~8VJsC~1kiY?=Q=92lOCN;iKAZg`o#{igX*BK17%b~50-BiHeSt6sVqO0n=R{%a
zHqX|e4j8Pt@e};B+1kyq;@<GW{B^AwVh&G>QCd|;ciQQ<4HXv=U63VrPqfx&vGW}S
zv{hI<%XBciU%5s<6Ea@zV;S#fM&8^qUX=Z%R=!-Ht*eh`{0h+M>fBpSc87muDqWD1
ztl17r(%*QWFHLc%!Kb<?f|EC|`c@tvS~pj9JzdImdUuGO<ijazO<3}Oml((6-|RG6
z)muhVWXF`fd7JIQtUx~86MV>}si$0RiKcXE0t}1rEhNMG9$*k<pd~moPD1^Lk}biG
ze5tx~4|MS~Y)+mdC<UZ9;*Igqp(7UT<}D>Gbzw+AVY6$WD-U$gkSv)SwV?`#;9foG
zZa*ukkBM@Ugz7&SYs=Cx5^!?wWbJU4g=uv(R~-Jx-yR>u0}Vg&x{eU8S^rbu*363Z
zcTORpnmiI-HVg=te#HHQ!7~l3qp@1h`Cqb6?YU53+d3|5X_Z8QL2tqCGA1aNac9;j
zpJU?=R1GH_8bcuM?VwaJwSCgVfxS&VMzs^|nwPY418?{*LQc+m^T-oa1x|N&`xpnV
zrdfnpciQ}OpwrJ9w?A~KDIsRhfvlDP$}!~*1`ti@X|)>n2?~;*uU%LLh2Yb*KytGw
zs(>DeEnd~cWQ!*zg-Av@l}E&nRSG370h(b5%Adqa)XC4p{3@(w1sK-KzhU?nTZ2^g
zw9-ev#5gT^Fzx)P;4Lgtf<aJsLUw<umS3s}kA)VEE*E7!sY9R%Na0p58-Go*Uly*>
zNcgaw936)7y+(4BYVt<z+WwQ&>(b*X2=I8Ryz&hM({F>Ek`3AHaPBhksulM5fZh_e
z_f`^`mzsk#s~ZZ+r@wsrY?5v)Q{m4rs_K=MG>Q4!iC_3mq1@l42C83N7eIUA783QT
ze=~R%zoNjzGwI@JmxH+itme~cyWc?93!V738wV#6wqz?*Fm3>Yzb^SGD$xP_AZ4S7
zF-~SSMUOtrxpdj!wYv8UXGs^8<bC`ICb9=Kugb!Hrt1ndrUY?7S~T{&q$+L1v)}ow
zL_c55RDiZ5Hv-Jvn5w-Tr+kG*#LW|!C|WI$<T7cDn@%cqw~)|%@E~8X0uHe{ybCW!
zEO4b)4u)Yjg-s)NVh_cI3mUW>zQtP*UTiHJe4Ym|LODpma(=u~?1U4nLxr18ECQ>r
zrLhv52$18HYAMv=5ir;ao}TOBs#`s%9Prg4YL#I#k1-?CB^k!eS~2&>Ymmn)hhQ7Y
zJ-K8k26Aa3;sv0D_jstU<#-wh@tcO1v-+1m&QdDLOpelXl0PUG+S6)aNQ{LediX&x
zbY@*8VdHpcA|x<_qf~p^tzCA!VX+B(3K#*}3gf(cq0BIymOO&vMwis^)WBm_#Peub
zZ}&T#2h)r{JXQ}%m}FW$qZ}+RdXeFmAcuW-<=?!^X@bQi+9fwy;SYf;3jQ^)hj+y?
zIqo-?s@mg5^1M46<^hPbi4&hP$eXY5B49fUJ(#RWi$X0nQ*b`tcU4-YYP%e6<|v#4
zi?KaQ3lz{9;qwC)U>vH>m1n<9irHh+`;niQ=RYXrH!xC%kr-2hgqLes-&bHcD3yS|
z3T1Xy2^f`yp2<o_q85!61<gtH#I7L@cpe|z>(;q5OjMgyjaFvCtd(+eT<7|HsLA45
zgU!VA5=*Tc)(Z&z5|mEKm!rOw%ibWN)8msaHo>SLk%xbK^s6QF+91PW`oKDSneB&v
za+ujP>+Ke)n?197Fx3~O-Eu^pV`8<a(kN+gad?F@=<=_+JKR&smu*Qr30R8b{SN8}
zcpYMP!&NiO@!?|udggI7{yC+J&5~y<B}>j9leSoP6*i7s(N52zwheL`3lDK$_^*A_
z{3pfRn$6l&_?szqSLu7MpomyPzLcD8Zh-d6(z=-P&u80%9VF==hf8fwT#4JBpu-@x
zI(hp#G|g6ikBx=_$Z;moJ=P;dy9XCgP&GsbE4cq<)>GZ%qa1W0s?<#`+<^ReX%a4k
zA1_QWQt2!9QsqA*bts5$4oZbql2Q&0yJ|l<n?U;wsITb5oDFb+Jg2}n|Cir%?W}jj
zis7*#PfLsXdDe@F;?^FDtqYsL^F7EOa6o#1LKL6=M~LIq0&z0J3Ik0-cwtA$4#Kb!
zNQ}&wgh4Q789wE+3;-C7KuyK<exhO+&!r5@@U<jH7zUtvfQgn*G0b9uhEOpOMtCt{
z5y&Npyy9B{kwYLy;KYbd&`iqEfR#6rdDRL}dW6B2yp$C}RCp{Oi^pb{=VQoVvVvi(
zT4T!_qtSI&D+Q)YmI4`J{y+ZU_?-cB<YsJKIWPAKVZta&^+NA_&f<NbW{_^?XAya&
z?c)F2r}HU777teI^?q&%G3{PqmGEtK1nQ;1fn0qke?}jqIkp=04*9aMzwUL?8C*wo
zA|RIN?*2}%2t#O;hfg_75}GKh<``HisA{KAa=g4fQ>arRxhZT{=m=X<h{T?p6pHdk
z@B`O@QHFG@(&Dm{a;iyGc~1nw{;R>6j?m}uh6TO8eN>oFz<Oi<Fhiw;Si#A+)^oVM
zt8&tlt$sYnPw1_(5_ln!LHi!*jo5T-uZl;T%<Lz+F14qQvE`R+(ADxoqD#jlXhWpG
zHqRk_8sOqwnr5G|-+{KbYRvQ=7nxcgN1czD_@{|)Rnc$<IPPEbj+I6|Uw&a|awN|<
zzMrb=rH<+sKP=~)t(tTq(Q`qXk8x0cE`j}&XTQcn{hPy;OZ=Mz%9AOjc8u0C!Bx+-
zd$!8I;d4_U$~xn{Gv!#B{2lHTTVj7bIPO3+bv@sw(XOqx6Kdm#chFPFx8}}YkMz5^
zn0@*aXl<Uef6G<aB~hWdAZl9e=K~>G@~}8t6nas3hQ66eJ;nPbvGj4_uSVH1Cn;OV
zwvjGsZlS_2Cl|Qz2@%OTcV~_pHy?~=*&y0Q1vBEK*nKF6n&ggL?rm=OV#hQGW6ur<
zgebD$Y@{j3FXhxDlda0;_q-29X4nZm&w6^asKv-E+phEZv9kUAHvXI-5#@MJjw#o<
z*mefqOQ6!+><isTTjPHnohUru18MZ)cg+T}*916uox4~uE3r#5M3_b4W#ES;J_QB_
z>xm#2IZh#~Jo43<i}=Nl>Vqm<|A41)jXNjXTTMG72k3%pR}3${%NKYAJ*vD9{H;Ar
zC`eT-tO&#W^c@Zj>+^GMkMoeJA?@8XbW{d|0(K-_NGQ3!7F(C>9TZj&gTSMas7C<C
zFF-RKi^2KzcE9Z8#N&$nNPx4q{V+2IPjbK?bsRu|{Dxig3K9BQh@SRKgt^Eihb#Hj
z5E2`<pvkLkD_A>=|4U}umcn(VO$cdcKigB<m}uvbH@+HbGr}MhL@c(hQ$KYcr)9tZ
z&8vZaL?c;!a_2axtgB|UbV9VLO#CF(n<<SmPdBEf)^ocpu{%i&rtWmXCNRgkEjQv8
zcFbY$2;-@n`)|Or(r+3Q<6Y(_;xCCdL%7M=P#<?dIHJ2|ZrFt6oV-REU-^RFhXGEx
zC)BxE6wB7fA^PD1>eN)&Yj&yAC2@Eno|f{5O<`?rdP1xhFE}{~6nHokZGpbTb(@3W
z&>`V>y1k`Y@QFtQp{w}c2E;GEHr^-l{GU%*-p$79(wGvww5S+pPRwcnemlyp$&5n{
zVzXK0`0OiN+lBBzK?$P@uSCmZTa)Uu!>$^8r0w0d%l4jRqe|h&7l(7A0s)zaVBrPL
z^e^FBVh#o>p}$hIJ)WwUSQVrwH5F{XaSH2XF)l0pBK|qc;7%Y5y`fP%CV$zA+U90H
zo=fP+I)&iWPd|6z8(D9C5xmi7!+&D2iz1H*4^yWKmv&d$^Gr%*>CEC3W6_$r(}P1*
zh#>cMS4mg5Ki*;u#IzJyHJ-NSI%Ev|wo0EfJ=dF?@RcG^cZZ7ZZ=hqQF73X$2TT5U
z{jm4)S1UeS(rD$#T(Y_^ND_(20E8WFnVzQHjN!M|XVU;Zkus*A_`i29sBaWb5rC)E
zUEK#m-@K5(#@O1od@f8bHZici+;@|;XB8$cM|u_A*eT~@enK@K#PX*c4_3)an)j~<
z_39*(LeAx<P1U<Rl;*vfGw`xfeBcUooNCip0}2lo-fF}Q^eSez;F?OB(k$iTUWg8k
z2+3?H*6x=0WQp|j3g@VKbANZPv{=X8e=uTrk2QR#xV&}&E?Odue6_Tef0H)t4Mc6o
z<*6R)FAD<w?iY1xC<>U1o4=+MK&3|2rv}tE2&6?aDp;e^r*1CjD$c0`mK*Ndnxun+
z2otZX$*oNZ1N+Hf1+1QI4a$7qYI1(GtMd)*nGITP;w=}bfS;SbPy0UeCwXmKHgRZ=
zj?PS>9m99%ZKbaW&=zgj76W0*66ABi<H|~=iAY!j^hOPCBUOW)c@PX*2~Ypl+BHpS
zr{X2lbA}eM^^dI&J=b-1IMTR3$JPHmxVN6y5(DU!a`3WlWJ)15;#cioqH<t4raJhl
z)2cG>(<V2c^3Ea(wg*nKv0M9T&}**v&iZ)#g+E)QZ*=fm+}Yv)kzr6m^L@6(FdUVP
ziKk3a1F{D%&z$=pEZT-@JT02Q2je%=9R`iGsSgfzFPBKS-%8KUa0d<Pf$#+D7z<|k
z^h4#}S0{pWdy_8g(K?vBHKu)#&W&`->^tHTmVE@pxE<gVYFI|x#4iKa)hl-|+||_5
zo-w^PkSwqF?7;34_GvpRi)7q3;rNiE&xI>zLk{Ih%BRzug4;s%_MVE@I;9EIj;5h+
zMr_LF9qE$^FrOu60&RPDM3j>L#%UeXwOKPyB~OZHF3@#%(@u0thg@Qy+X2KWJFpbl
z5}P}_QG6y{-afwzlU(bvcDu-gk2*>qdD(LBZ0>9uPp4hT1TUN69|$%;_!OPlD;2YF
zbgi%D`vWM-4sNiF|7LmxD}5ZG`g%n6R0~3u>P_B-7dY5R?p5tPf6R8ZEY%><Id81g
zKZ#l=ohB?FUU4#?v|55(D(HGt=;A^yR~gqFXdG~ejrczJq-EW@T5YP+f(C}ya>ytW
zB;cTzaCwAn?OB&>PNtXrkOY>V{^dScu!D3k|Gg^rKYelK<P1=|YS*@NMfcC<iE;WI
zzZ%*k1%vVeokNdD*MP*BwN}{A+ACT$*d50c;>F9J$|?2^Xlre&N3zJA4|rZ;qfWGE
zYbW;G6f9{t%upRT(!y%ILm~Zkzp%dO?Oi}I+a&vo$=j-;6<zC68vz#!A-NdSxH@+V
z4HCmrQi$n@4Qr^t?8|EG;qbrzZFhO)v3Xwhjo&I;jt!m5b%UbC&`oTsTH)ld#&l1C
z#!!4^inAM1Nj2D-ZWzZyjCpoDcMx^nQxPN)IiJR#fZ&-H%-GQx{Pu#kX3GWvwY9wX
zjbAFMmfKEK3c&G37M|W$#>Z|IdaCUv4)P_Hhkug#E?AuafF)bmvjS@ItmAp|!r{HR
z^K&bb*9qYUjdXdDVdm&n6OFMLORtnJHJT|G@RR<vzQpS%JU5aK+Jv2RCXI#v765(G
zi0T0lzJ8J6o+;FS)Pcd`Zn=S4TwVWIVsX?HM2$%W#~AaCz8NM_$q5Goz|*rXzxL$h
zIEPYZxlcXaf&umSN>{!j+^-ZF(iqPqSSBfhdng0R?j*><<LhASg9c+0?uId^<bdw+
zrfF^!b*jBLlCWObtdmO1#APrm6>BZA4BW<=JvN!*$@_E>Sg9gf>J;BYhf9`JDvaoT
zN*>@iR&LjQ39LjwG{K$adM?ZvZ#VEB$`56(Kg9cL6YoNO4$A5J2A$Et4m>rwOsSXW
zrsx$>eW`I|6afzg(~1ZQv{5HT)A6LqR?1@SqrF#I+(^|&`f4EO1W#mrzi(my$GcO*
z0bCz31d7FyeDuMedwV+WHsy7ln$Ac`(X~{=cc$*Xu>_e4WY7``!*DXIWGzTM&ZlOu
z(Gl>E*@|!_&Gap1ig~ntK<21w&moH)c%;A`Xj|R`!^!9;RwF*B%-b}x{fW7k(=6g#
zp)T_yQ&bPaD56iRwefkF>j(|xhB0yk(u=m4_%$x0@Mjsa4Gt60?7~urQuEATq1!B6
zrqKPkJt)<F_(swe&HP<qj(Kg>2E`wuiJ5v2m{vuVjieH&5P`+T#v&qTChQVA2U=`n
zGVqB8I6Z_-t}iT3QNz+ecO?kI1fHBk6F2&KirsChbHz0fl{lY!?IM7RRpEwzVBBUf
z0zVNd#k<ZFg~G=<nQxU`OXKt$*Mg1<709Ee$qmUw&ntGkP}YT2O40){FhYmJ)J&!g
z7FdDRU08pZkgvTg67LL6K8Lyv1#5h5Jli01!n&O7TM9<lv&t)v)esF)k+3mlY0b~m
zCoOc%m2?b(CzbG2^A$WZ+Pm3Pwq$PYdbB{}WUkmTq<+acJUc=BGG|9(OKZ<_-A1R(
zBuhba8Qtd6R0UO72?>`c&Q_o<CNdPnRMQFfy%>~+l!n<o-dy44lypF7#`9f-q;_f;
zY?jeiZ`iZSBu9&?#)|c~3?ZD)B~XVmf|BE0(b<A`@mj0w0x&2aHN?Xt#?4Hp-88Je
z47naq-1m01QeW}Psb9!3NDv5EZSzTpx!D4y{oOJ%&hXhh91vMETYW$~eBTq-H*=7w
zq0UlP)RXQt2p_vKiXCllP6wSSibWb|Z>A|chv4G`RW$&HPRSOVfQh8hV@&*HUUi1^
zX6{mqi0EX)%%3MNnAbpQ>H*DPQ0EjYY_<MJxX&VZZYZXedds>{wbN^4HD+STeK;dz
zf!g#^lPev`GrmLHopZCgdcS}xqnkEqB5(ACb#!N!MPlmSnCIFp50P~-VQ^h@SI!qV
zS%Z!tPB864!wu2D0-lIT7X;(@pPQ+~4kd|U=LxGyeFTZ6PS)GoAve=RwGKaAd`{Y2
zc+s^)!f~YS4n?wogla!prcE{{at~o_+q9y<?gq1TCKNtJGOFZqss>$KEbc#_Yj34a
z=4d7+pTNBB<Cf;)jCf5G^CqitPz6_P{Zwcy28+`8(5+SQ197~^r$UyR*3MQSCS4hY
z0U63+9k8;^C~3T?ns^V`m&M<yRPpTkhi_vbu6+9%dzi@T-|KAG?LdWtK!G!w*7ypu
z1a)m8J@<x56^FMKe(R^GreMHmn7(SEWeFsGtz^|YXFD?Q*`+Ge0_cTo`-Ow{vd;r5
z0KJZ~fH;$R{>b^I<wspXA>H(=SNtjCd2|~xxBMLJp!G*`V{%K$JtH%Ye+5DY4DOY8
zr=M|RsB~m!Ibn<Tw)y8M&1l<aLol6vh(9jq0hX^R5znYbrh2>rwAVW$R=9G@pZGg*
zm){QcAS4dVQ0LM0kgYjE5c)>oQRJmDjX*>(mg&K&Kk&?cZJ$|hj(sTzaX~WIG;=&g
zR@mTHw=mURJ=~Exrv3)mgSt$ts`%P!4G<3_w)mDV-#QWHZT9EIbfIWyo`0+O%k+gE
z{KL;fDrg5K1l$NXvwpP&8M-W&adhhR#Hsp}0ZobeT1G8OzS5+5>Cv0JT?aMh=a(pT
zw0UzOXLVIF1NNzV1$G`GI<i81=i-Ea1JR74GF~gLXHq7jBt`xSHN3i=tl}k$EC;bQ
z;=f6scd}r;v@GUpu)DAy@y}e;_K_vEKgG7nw%rTh<hd{CPnof|C{vPLXh<7d{vdlW
zQX{LA+VJX8W(^e#f0)~2VZY?RcV?he@@{+Pn(I!@6(g+xOxMXDU%gS^eEivEDKg&B
z=lar@bBc3FUSno!BNFF%V>WJeTRU&IkamU*{~(94#}#3s9y>s3`qxLmf#X~DG)?#l
zuzN^J04~zbd82L(m|lWIhH<)-?{)9-3+}eg&Dfu1y_0Y5f(oId!y?k#_9qb%=n<-(
zf7gwXUMy(_jWlM|hA}^hw~uT%^f09L?iDI`T!q~S3)bGB2h8}r$z=+E4>6sP^9az_
z5lUM?S0@UR%^P_}ra*I}my}w*aO8m!6yi$T=4ex*%(H(0%Bt<P&zo60`2{p+LUBEy
zEk%SYxW3QW@*xVl&e=93j6woTF%JS9^<#d$P5vGvYf(L3t&E0_HPs??l&m=#(B9qA
zuOA2b-WJ5&1NC<I6PvRs9l8jPe!DDWSn^_tHtv3}OU#RwgQYaOG-AQG;u!^Xr0#7A
zR;En}Jd_Vg!o02%*7|i0lZ<9W&#M`55V_MY)MKu7bHs{MXOFf@TXiK{qe)V<&zy%?
zs+cL{If#l2HmIoD7GI%Vu)4O3SXu?9v)XlEFm~m%<(iL`>FXy5KjY(4h}DgI`=`VO
z4gZEGk%V?Gtamrcy}$AEuBa{jo~q;RD(rSIntt|qj9`R$)jRM_(mFXg7q0e;idJ;d
zlz~1N3Ddh?VL_*ju9jKS2A=1}0j^1>P3^`OR%nZd#4ap+cXb!)-n7!30mWyI-5ODh
zJDkKQ(`4dK%%3elzZTzraW922kua7;SxH4vWY(3LoMVkm`cTO444PjW_Rbm|u*!3(
zaCdxutm3b8+n|?&p*R#>Ma`>DTq)GzmU(9$2C+Til0^V0FcG^M1&}Wui6J4VMcR4t
z3BP4KX{gd?y@?xn7e2mxJ}__r|GC=B|7id1@LJJO<wD<)!d<v}Q#0lW`a<Z8+C5qE
zUc)53%=-ztU<R3k>Cw4K(Oywh0+#7Q+3BsqfirDuB%z$57<okZ!_~E#PT4fZ=LWu^
zVz*F|N$V2_rGpPTEi-MF*C8N@=Nx28{r0A`(`Zc!_vxp41-c=IaK^i`@A3JKOXN!n
zdM%Pks^+;-pppH=Y{7L|gu%_}r8uK$;#=$n50>Anz6F$XC;M51L+SerKT$0Yl~o$^
z1C(Mi__J0Ew-8`W4L45A8^L?>e5o>P&9!HlGyGVEIR)BI0H!9+K>>Dp-9OsfOqXYX
z?NR;*D=Oo5xI*M6i?;uZ=EOntYzww;UU9C-Oe2<QDJmkbo3|Sn=t~9pZ#kS1wmbQm
z`0LNf1YcRN%L*Dq2MDJox$E-0ja4afWFsExIJ=C_%%(3q@-4*C_1h}jg-n|{SN|vq
z7VV9LJEmCO`3tm(QFH1L*K(Zi+q=8_y;f>N<0vmu|L09tWX_t;Rp#3Q<ifw&H3K>J
zESM$B7>W)%Y1oi__Dz*8b3^0N{Y)+lMUnNIi|FjMLCD}X^I;34;HlSDWnpSQv!H6L
z8F+Aeg3hkDgR0Ap&kcHNZ9-92^2i>8R3yjHm3rl_UNu{v2mjotGj)ea6v)79Mb>0|
zdm^ea#CTth>KWRK@l+RG;YvNEPK{<#!{kl;Eyk=w^NmM^h9(JJs9BXQX{a3TyYOPZ
z?*Yh9%zmCcR9I3()cd`<{9Jhjgh)IN2x9$OcMh_9nHA@WAv)JbpGXB$C?&XSVQ-ek
zTEJd0{d;L>L9$B*2$QHRepiR?iQSj7g~T(4M;S$v+R*$&UzdA;vSiD#FZOWSO5d#D
zB!<`8zR}D;!7S=iqXDOnVEZIW@(Y7;03nN=4Q<1qySad0oldZ_exaRHX*23?N~J#%
zv6~yqUadGqxqk<V8;csPX*0GJ8Pc`PrTe6g^QtJSz>Xt1304)_O)(N&?=12iVvJb3
z4wosMn7j-AV@xk1p(yZkzlZPZw%B(uwz1ER1j?Qn*74)_J9m(YAja8-oRmsqf!~EX
z=T7F$0ST*dp4~}OLe&9J)Wyv?;`vM1nN{ht#4ir9-)TB5l5)U|9{OaKt%ol*Cv9aK
zT<d3!wWP!fO=ZV5pH2}$@%PDq43vfNu0gyC524F*wK03AQ&H_tV!4%&Q6)r!gF-AA
z)Q2l(8`|j9PviYf%o?%zKg5SJD})AN<%_EoZ$>@m>Y$?|@7xY&-ML2kjTCfRvTSm0
zmFlgDDL%-^=c-I2?MF8Gym92YqAgt5c8WI?VkF7##~aa3JVB;8CwQ*2@L8Qc!$a(x
zC)vpC-`Uxx!}c#kc-I+uo|jsjaOaN|?@U~?M0n9(C=>Z4=i5b-9Ewq3`m6qf86R5L
zBt#LU?heF!x`ddTgkG#S;{Q^&V#3hkTKn#Pqkt*8bP8NakpS~1IjAYVYT41JjH-|w
zlxu31eCbaV%|ewN@qAgKISKIO8b8!LolgE&Sq@+CvE`oF=dKNVAFlbe&-w|FL8eQE
zN12tQMp6jipSza*M25~td$$Y1kZ)()uZI0q>4sc&nv^kSlEm1Bp&dTT?pGOp|BsOz
zBS3>o;RW!?<M+Py^+BzPTGN=d&k#^jZ?$o0Xf`3{H`s5Wv$p?fWo86Fo$8a&sH<P+
zh^w!Mm6k5I6#fW~VQW$W6Ix;tfLf@Ij+2?*%pQM|%_CcrlXy5{Hef8v$eA|{X?g+W
zzRuoAv257N5pFiXEHMyX4@>}=85RT+jEK#M*`gtB3bCa*#&w%^V)mwk9!)iaPHb7)
z@F(yG&DlA~(!;gv_2bZ%J}=lLOPNLO@38UqesSkV&D>Um7z_|B!bARa|J-^Px`r0i
zSUz2btCWF-e3C^LdzqCB-eA?nlXQzc>tHv4s;;E8$b-pqWJ9JwwNuB3R70M=%9!7g
zZ*4BB=S-gzF~)cjm%-O>6z$7@fnv3PHJ|uq(xXoKvbA-a*Zy)Qw{?FL46?iDJM%48
zB)|(?&-tsSmA%B=0c(O0kp3UcMWcEbDOe{7ahFA#y$bn2;n@hM?m7ELA8SKQXfyz$
z3;aiJ-c47%-wo$WLWY<=UqWKaj8(f}pf}!cBe%UbE#t&1pAS?^rKI96D`*=+-&=S6
zjiIPFU%$YQ-va-#j$rcVVbhsJW`OG8Z`WSYN5me(`ISGfjAa$Jl0Id4o=S|c5-8$r
z8ul<{yx+5Hpm!0m8q9VWHlmZ{H6V-<lcy{UarrD8yv8S3Wf0P*Y%mNRQ3XU%5|K$n
zs}O+$0OP_a#uNaQW`rSoT^z46;(}g|E}?k1>SFjYPvxx&BEd4^N=_u+BP6%VB0v_k
zfE7NgeJdp&9d!bV(P#nJ|4cJ7D2%0H|6hL<Hnm0<nB2yS-6hTq%;&^JV(7N#J!}n`
ztoOz@Gvl;ebBu6G{|`A14ouHvUkpDUv_=^33f-GdCY-2e19xjl8gdEhswN#7FT}M(
zNVN1NgPsH7owkZ@xMo%N&mIGVE$CNhz07;tDvvCT^$T%VRi0s_QKc0Qe=Iebt93=a
zcWY0%g;-IIZ9c5-vuW~+Ez2)@IVx+@7vQk+1VP%4C~q6Z?g(RekwxtQsa>dU<FnBc
zCX_k)t`+t@HoJ*fohc>ugB;FG=Er9K2eY3phd}L>rLDYwny1Kw-liYC#M^fmoSkTv
zd0ju-Z_-mNtp?3@?QVliL&orzZM%U>{JD7fjZ-@!ByM*IwP(Lw5|?yzc80BJE=@X0
z?$p2Dqe)nIWhmaaU~whS)oSUj@QTVCbv<zWI^3>R<|l5Egv@FuU0rRC7ik*_U#;o;
z-p|{(+|tJQX8o(f9v6R_fGm8SrzeD~l4PdteFY^1%_k1~nzb`dB~T2k<}JvSbnpnI
z6Yf4&b)*KhL~-V)CnR}(b?3pR?l$opb^g~q+tZvwK<OQ$sXg<B{&udWax1>H81mAI
zc;v3g0OX5l=Pz>Y!m>gzd{FJb<1h2H`eS%xs4Xf;WMPQIGD=O_8yIWB3hSfBW!$+$
zP2obEmo=y636*vZ5z%+uAuLCtBSM2qKRgX6Zxig-dwe%}XZ=Z>`$om_if$WiZwX`e
zZ%@Ke>B%=-e9WRd%2Y>p!mENEL(5dwdvqK{(If%^#;ynLC%c??kpaVBEjqf|dty_&
z-plo^4%8_e?lyS!TAK=T8u*{d9Y@<me)HRTezEmAFU%wYz7JgaGIDsoy~QAV`_f+Y
z3kWDpc^ht#rG*MBvXy)9c0X0?$tNaPUn6*${wqP|tCQO%JE-3rC7<e%m>51rtea$;
zwxTl($>ELny682O5-*ETyllcDWy?$Hp7?W6-4ixqThF(0r7llt2Ec;zkVC#e=h{eA
z+?Q8t2MFov!^5ZtBu{8`?}W=hG<YWe;9V22{@NDGDe<}ADhwoPtW#L%NnLpLt?RMA
zog{5Uxtv26(6I-8KVR{Es;sy{NU+Z6ItMm2c8dW<lX6^Xi5R{er7-VS6suQJD;4#}
z=978j-H>jeMcarv&l-MzXEjru3EUHP5!1_UgDot4+$fK-o|!yh@IoT4ZI70-G-ZAW
zQd7a)5)-Qi-CdhIShS%f0BuX?^SHL`$VXH#XIdyQmr5h#2m0cJo6!1&oJbZcdJ!45
zJPQGVBJJ&&7=l*qag~Ofs^nAk6EfGw=+3)mYsoG%amV5wZi4g`V@HYIU0jxaWl6f1
zO^?)_k2|(Q2kXy1)9|&3lB4bb>o!E{U2B8G%_1_FrJA@~$|ROTuePSye`Y5_MgAI`
z9$Y5v%fv*^<U~hn4Hb^GdT)zAlZ7mPSF(H-Nru{3GK3_X$(*L6#zKv(v+lopLW%dv
zc3X_BnEQI~GYwot=Q>-`UpjgVcll%QW5SRC`rj_2v}a|YA;>5r$Li$FM4JW^Q!U9d
zGV2-)R7`aQKgp9!z|te!r~Rx>o=X)?Y|Wbi3CqNp*^Uot+uz0WSB%5w0W+VCxC?ls
zXPTR~bLRosVBVTB_fZprcuvQ$nFB^Cq*|zca<pR!J)0|M;$7C$)wS!|B$%0AI^skF
z3G7rJcKNYb1?BZ}kDpjox~YBxaML;;^XrC>Q@8FXttpNdamD(0nWUOU6`zBGA=&A^
zHBu}^JuXy-ullmWL1)<|KkIFxbxtbKseNfS!G7O=IyG*5iI}2v+Y;AVQ}O5_bJ-R{
zw-OZW#WOsN*p1r$MMN5SlH2=3O2KxUQxKx~Wy7h3=r_RYxq>~?x(5DL+YQ>9@ning
zMbo68fz({Zal5cfib>X<;|dMdh|jZ9@>p|JmtPHnl)FdDUH1ZYI5>ppGxqYIEAdR8
zW>v$QI5aJhaYdaZXiOsu#Rmo!%|?rzkA0A2ASOmXU8&!1jtfV0|FMz=hRGlkuD?6V
znrY~L6|5vMitOlg+aBZM>qQ(+dfIT5z*6fkZI7DEkEa@=6rwab^|pXdppAw3`?Ee>
zqnTT2=t#e7=o<VSVp5pV@x1(N{$xw#cJker2<YQC4oH&2t~@CI=OA6CE?rn<RTcF0
zjx7h4Ptg$1y%+ucb=|QdNNN4L?SaQQzDt-`lT#k-2i!$`@wwX~doWFo{-EZF;hn$w
z^$5A>erauQedPOvl9v9Qi}6{V$n4jJR{UGAmZHld6jMAUezR|=t>_81cjWcCtuLcX
zaBkbvqb~`{?#Wo!9Bxt=ZBiF~P+#KXxT?GJJj%t-cBB$K<lVm3`npTevGhc4#$sw|
zXwjK|gp<7Q8t^>JG8~{E)hBi&FY1fcYzby0KF!w;yCe+oep=t;{afBi%ERg;xO2hM
z)w<|i;QI3*nEU$GdGWXejm+Ac=u(M$X|&ueU@_`xdL2lYs1ga$PF-);RQB!8rRt2F
zW@#eD^9C#bM*AC~mLPVW?Tu3OVt<!{5a>D-ih8!mUqt?IyW@UW$=AgxXkaC)zK(1@
z2AWPl(vafvgc`?s8e)~)fYj9}c*hZQ-N)B3U%4#-!g_CkO<3Q^-aN^xGHjn6T~Wk&
zW-}KIl3E#0d{?WfFnn32Ohv&^MaLM=N$spIN8jv?`@sFXCPL%omBozc^GN`6m~V92
z*&kuqNZF2io9SmVG@eceI9?XSeQOf~^xBHE?bI(ItFfa>c45iAOOA0B<p8(${h5Sk
z5A|(sLDyL13)UWfP1`nVTX6nT9?NAq)X!pmM;ZQZQRe!CP!CkO_<&XznyH&^gz{(m
zfmAtL&W48S5B`b+C&A`?=AZgR_A%Zb8@-2;Ian7A5q(wCa*PT>6ik}6zCIa~?P_#G
zR<IVK4~i82>1)2*bim@bD48*q=2eab11|M!U*dVCy(7y95m$y~-fFqc*j#FC&P_G3
zi#3mlJmQ>N7}K#@x!=C|{{R=$bbU3VIJ_Pl%ojYS@xiLTaRtF}QjC~nsRU;&UyS15
zCZ@Xa>%f0&|AW!#An0@-d=pk8gx4bq;Z`*{=;7he@);74$f+9TuKVUyJ8}etGBf96
zWWs0D<;(fHz-=sK=lzK1GnFjxNu39Pskrz#^^z2tc+30j6$ZB}bLk#>PCjY8^4Y!2
z45z6v4M`8;6HzBAlqP~vHJa&dR=z9J2#~I)KGqy}1C?X$#rGMUEhcGk7)5-PA-j?6
zcvxy;wH39v9J^9pxItweff$*x8Tc0xC`)at?<Gg`GuC&h`B0}^h0}J^_rMIJ3`jAN
zEvqLmji_u_AO%TfW$7yAz57$%abmyw*K&Tfwc4_qnrFNZSd*uDBcNao8XPb)2}!(w
zg(aMIIcJ{?_py|8B-4iiLy%UN`-+fsz~qsSLg8GGds;!p8Q{p=G(mH&>0&zu`28!Y
zy|Hj&3C-@fboh(>J+V45bmw7cQhpn)o}E-smzt)@wUZyQ)L?&ow=KRjDkpCCtENu1
z-3v*FIOhmET;a8iA0=o~@Uec<=-yBvQM&p{ReJ4O{Z$fe_g@{+&wnK*(SJTj4`yh%
zI{Pitb1?zS-3rUgpt)3Wr$0{(wLWK`LHOKB>Pi_y@@5&+mb#wDtsE-hTIJCvnk3y?
zf!M0OpR<0eK?SyR-+~d00u?Mwn&2NNFBS33t&i_LFLl{n(PC~O@Q0w$2Yv+Gl&qmo
zIwT$<l_<?fE7}oMf($@i#(+l%us7^ZbmVA2zNFf=o6hH+qzbq(v9AeDY&I?sJGAJJ
z5sN}D=8oMSU&}9ZK&mh%FoeTke50ZF*gI%DkzvX9kW&k3yDhFcC^&vtSnZWU$|-f>
zdC_!7EOLf#`FIm?AFp&Y^%;2+gcHTq?oaE1L!6iWRFXAyAiMb~^tbNUB;}#B7hJM3
zuL&qJ>J$H89d5hgN>tKZov{zI(8$77pS2}-%1qw6`8%eXv@Uu(1*?0VMvOob1wC8h
zI8;hN=40;)8*P0efgj6St95UIqQUf7t$Y3<A4sM2u|=f}hkkgA59!yM`j1&VvC-)c
z!`$wRvGVW!WiFn{GOCp{A#0nzG_XI}tpIaDSn8w-kLQM)L1Pa5{Mzm>P)_f!a;$9s
zA232S?UPK?>>&pc$wrMQGD6IY5UM}t+Fx}$@s9#m<znMd;eJ9??Gf5qB|~J!`-L(F
zQ67?wq8R)Zyd;bYh0;8~4^q6;s_0SujyPlfhGTF${=;Yi+lbYF(n`01p|dmDW6XF#
zE5%?Egvl(2RApo#>8@wj_Yn7Q$!cA6HTd1D24?fq!)}?v!sG-|4bcr`sgxDpUE5=s
zUfe`AV{+U=kIl}o0_8S|MZ|sQQo+`*z!Z6VAd_8y`BaW3CAAYK5ZLJZ)}`EXlyuNa
zYTTd3!E&r6$d&}a=AD1uNeVcr`nBQ9K-stNIS-iV$2Fb_8e!?W)33<fBh7e#=(4jP
z_iD6Y6wDi)m)6tDlWqGTRw*93&`SI5*A}8Pfl1(GuC5Qg>^xq937Zp3r7pu<HyWF}
zVy!kIHWEXCt=;lLA=Uc6Lq3c%>DjUi{+j+02i!F-P`b*SQ$U9HX5$Tw(57SeB0Dr!
z_1_FW@#Kv%emV8ctOtJh<4L!po_l-`0!>5P+Hu#?8cUu}l62ogp<@vVdG;1<zTy|V
zIgLW*M{QW5OU)@6%na!L`PS5bXG{8J%!18oE3sBs$C=kTjoZ!tAXjWK&XcD$VjDEo
zb%&nVirpI`r(jgARU_ua0{Xofhx35TE^>&U+~}99HPhZY21$z4)A?Y1u-<0#L=DI%
zndr%4sdAu>|MpE>+OJU=Gor1#62Z_Vaimh7#{IF1UZ%Y6Clb{PqG+Mu<m=juFrYn0
z^!iF&#`Hc7*wg?xCrJ=s|6;j6cqn%1FxV*p_1{i5urCpVZ%Wd{4ag{~0+!ai2|RJw
z{pQpG54HOl71tTL11=VmR0+?cfb;cfiX~+0=aa5p(v2PIY5L)XbW?a1T*iAB*grca
zOO@v$#VXAQU{uvL=aHrf9Nm`)Sd*;yQhEH#ab{%xLL%U$>WG{4+m0Hc;Ji_ztFLR~
zS#xXV9FHk)-AV?lR`aCe8inqLeewOulX%-dnqk$N6zhyJiC<)Eg=N)>zHi-M5(UVM
zpTGr_D!pwnvkvlE{zHEnK<#uSMq&z?4XhOSZJizWkmeuVA%H)rWqJ71^t9JHy5+QF
zxjZ*|TES%{e0%eRy4TYxjecLEltppG#p=>l(uk{A@roZC))a$AnJ>1~iR;OgWgjYV
zj5`hjN}x)_bxeJb(KV(v+;JRdze8P3q-ipNdb_=1$u9GaCElyM;e&CQQrAliIm<#~
z_K58-=@U=h(SftaSzZ-gz?QM>JlR3(NqEFw3W8I<*$~?~Xy-b&dfeBs(<2o1k#A%E
zV5=Zx3D=V$la;~k{_n8<r{=3~$V6aeLuxr98?->sFWuusv?o*!3diZn7uy2?8&Vn0
zlfGdiTvJEf?Me3Y?f0v|m1p7h*>V7Nst={o{F`FhVNg}{r777uYJqyBD6;#(SXXFU
z8#U*r_x|9Es(4Wb?|qTuj;{0|mu^L_^|f9J1iwSs+no%(t2FFZ*1tD81GIlz)$eTD
z>wRR<ab29p^8+-+Wox%Fe*b(0AODDOHaplSiWR^Kcx<Fz^NwD<IqmiNwv?Ya4~M^U
zUdXbzf4gbW6LN<;O||}ixI2r0HomZ5L!rgpy-0D2J3&fucL-8kf)k)fDb@l_L$Kmj
zN^k<jo#O6<;8L`B@uL5mZ+ka)eZR#lW;SOvXWlvQ`+FWNO8wuxW0ZSxsM_SLT8@%e
zhh6Ge(OSemoO3vFO}GBS+dpXoDV_HI_3Km5EXhbEit=7k#r}lQ9Wmq12QauQF9(Ia
z-Y^}^ASTk=(u>mycY4gH`nBj)mrP){)m;_(d-qq>M9RL5hrW~!oX(O#RRP$0HXnQC
zDQXdVf67hJxbkG_;_1m(x=6ee54Oy<nEg2JvvXFz_r3`HQ<*2zn&KtdWT(4YPgY=R
z>7o0JhL5&Q7`B3H5AO5ZfAwPNyO{Wl)MHL8a)j={Mz}g?l9xL=)-E=BEKlG*;BE=G
zE^<6g2-*55ejwvjShU;#9~BtWOGvy{*ftaNj~O&>sU!C~w|ul^Qrb3Suk4p+98%{v
z*_vNNAX}{Z0<}}rv(x|ZHGE>7oxfpighjRA>m{Wf@l4?T;hXVKHTx_Y-Rxh<QC-Nn
z%e%@c8dV7R6Pl4qFtmZGdq$ld)Aw3U>ad?P-=+AmmgLw%Z*c%C(y9WFhL2L^`j67B
z#)fmPIFa1~)#onxhW)jde<!0AegZdpwg=gY|2m|k+|I`~y?!7S@wM#5q4&Cvy9&eU
z|HzoH4C~p_yQr4y_-rDgN7ego|9p9k2{nmrD14q8`*$uM^PL;e^yf_o?DxPz7ai49
z(5P{OaYtkF#FFdr*8RjjtYO+_MDmRq6Qv;I7SH*-64`SjTE@UqQb*&nE%qt16hqIS
z{M`&I+BKY*06aM}osxep`d_|U4to^cbxJbMi^O+7HLSTZ^VZLbH6JfgyO<1Yt+oD4
zWepFGOb^)53AuK7DXf(!@3dhiTj~ac#e=usaixVa7hY8BM{hFvC^|qEMPxqAC6sCf
zY-URG2E#f?efTVTK6MhAPY?YG(Jex(@>(npv%#u*32x_`gB+ARsryv7(-egFIt>0o
z-T@T_syqxaBA$Ef1qA$Pv(qt({~=!5QrLl2q#~C<>6FZwnDCnk1fe!Gm9SOpn$QXM
z>eyNZuHCs?zI*l7OLc2P#UF@#VnuCa^^9~M&BYK-{Ci3rU;OZ@#b+|ST%;{0iAJHU
zybdxo0?cUq$UY|y@Ed>a&4I@sX~iB`ZD%ep({EA}B|Lm+^*NzuoOfbZdg=T?O}W_*
zM;tsrZ*p_Z@yos?Wt$-aXLrN&%jzpX!<ssW-;bQ*SwRQ~as^X|tckN%m-JrQJ_lzN
zN3x1r@^f1Xf0GYgD~s>61=p<RPD#}7cH60+%rYr<2%ylc;kGQrOFg{hqnW<imlm|!
zXX9RE9X`B#jxg>tsTia_4ysZWz6-BoJ_lsd?pwg5b{iXBbptA>ZoNl}mH8wvi<vPw
zHY-3`xmB51awn8`=-EP<e2Ac+Gau+f>DdC<z*gq)IB-ypMXoy=z?a^B2H3ej{uE5+
zf|l6!n)~?Ox|~>MrH|nkW}#t}ucZsu`itHtrld5_Mqm|`&ef8f7vbdbsn~L2n|4NW
ziobfOAdx;byZj>8p~^B+|AqgGC`vsLR;j?-Tle|6frccRp#?ES?76l5xP*8gaj?*h
zFd~cGyrrv**iVAqo3YUL2!<p4p9EU*oQrDBZp|1<*42EzJHDvgHk4r^-8g0hXIZNR
zPOJl+Q_olY2XuhQ9~`kO&+g~t(u&yG3nrCpVmAmx(msZkF{H~qx<@QI+D5p5F??;>
zzV}}1kc;ywVL^Nphl_1*o}<r@@`^JP6k>RT^fG0W4z)@-?e9!K<@9pW(lgA@z<nb^
z&K72AqdItLar>Ctk*~vu<dSuH(JAJ`tQcYQjeufVJMdb@9_8+R-j5<ERM^WcSpu(n
zs6_BAuymV6=n^ixS0qd#R#+lti=W7GM^Blj0CWY2@PHNjk9BQmKN`=tDSO)Lv5On5
zWHJc*eS69=*56>gDf>5x2xJ$|B@$HR=_3sPOiMc`*5$-|b*j5~!2L=;ccO45OHokQ
zZR5;%8(GOF6*`3TKwKdicbW0U$lpBSgjGy9`_7Uovjt({OufAA&~tfH6{><{Yisq)
zvo(6qZ3B@og2qeSbcYoENH{J_o!G~p*xgm{fn;CQVM0C_C+?q3E-YQ2{2$+3YpjnY
zEoOFlY$kV$NH(4M!$sd<FH%oQKSN{jQq@N1X-hC%F`w;~7N|*;I55{&C^8Agl1y~e
zSTk<ja4>?cnqn<I5P8S_0bp{6N|)xOi4{U!)u21$=isb5e_@_Mz(GwnAXxl49!&K)
zEshuqg7@;~yCa7EJ1f&1oi-NDaXF2DD5yd}(Du9u09tIRG$3qv%*ZlR_{n!tGgIVa
zOoJ#5qwi8q*{|iSkil-TGcwSZiDk+ks+vD?qdBfh8TV2yD_#p>Jn+_SC*`FMODvX8
zIXn~9UR^Gd0&6FFQfAF;5zf*ki$X+HWNXSHtz-nDMwol-l!$Kl9eswEFbCk^#UBw+
zFsADTEHzcE5|NV(Ad-Hm^0;_6YxT2O@g51z6E%`tW&Q?;u-_{v!_o9QN*UbJ#oj8}
zH;f2W;pFkn!i5iTVKrdSY+W8|43G0gFntf5PL;dR%2VMonu&P5zi_X?TqtK|7z@Hg
zwS-CSdTmi5Uuz1USB-?y4FyUMf7h2Uj?w|C)4OPX1V6fwD2=nmlSE<c!iVuvw6R^X
zOg#r_4^_HcIcl7bz}f_z+Ie~3_M~NL&PoO%&CtBeZ(!JSDPN5&8^s5=IGk#bgX3)1
z9&`OXW9SqX4xb*5IPFuzOR4WT;hOFg5Sw85u_A7XT*y>!gR0)R9v7CFgwW(jSc`a1
z&}<(Yt~Sp;6gD^YFV-wU>*sqHOvvLp@GQ(-Kl#LOV%tTUu8dCgV1Fl_0XBVzDxS5w
z*BK%d>EM&{2}SM2OaTr`j8Ij)n`tqhkD~@LdOqZegv?8WS<*R0A(uM3NCqz>#%L>v
z3cN41(sYN0-E@o6Xm8E*0~euy$15+bQt4_*M#lMqAU5qK2f5=xad@CJcx4L3#+n_u
z581Y#X3<ApiwsfFIl%bZel=YbjZ$v}P#Idr`TrvxOP6!bntIOzYT|+Ke|*dGfvDY#
zS(NAX@>fZYtff|gV9wi?rxV_$MH4-oYJ~bY389cy@$;XHrpwj?a7pFmBrDY~#G||2
z-Ry|>H021-M89WO;)S9I!KZN!48*$|_RSaP+b-hk2iJejNdN8CRGCz!NKbyeN)fjt
z5Ay5_`SF5Ln6?^-Ar3i9fr;AK6}?S*r*@-Cc`iF&V#$QUNZSykYEqVL89l_+DbpuD
ziH2O1ZG{6S6@sp-^^j(`A=~5{Rpht$E7BZ9>q1n}cnaY@oqf%hzWJKXZe}q=`-Twl
zc1eof5GOC84w*BX@7oPOB(+N)h=TJ{OCQsW$<*kiU)B12Y*<|)Xv_8%abB>D`i{C0
z2K<MCkcl1?%YCkqVE{F}g0m-_!G*4VKxB<bJ6v%fLT=ocO5dUMy7h&qL>!xXl9A+e
z=~KlX$O|4l1O}&keJ+oBAu|%gKm%&HnSuAuAj^gX!Gz}i?Q5yKVm!J5_E%;?^)ZzS
z5w!4U4wM@$W$a(2#<kf9W>S(gIi3sg!0ju4c6FDsWLb5OsD_}An51#WHA{h&954M`
zJxcqM<d0<{RUAE{(5*Q;6*TVdf9ds{VVR}jwf(nl!G}u|90lNo0#lHsex#+oR$ppp
z#p{*%?*~t;4O4&Tr^jl@&WFCX=ry6*fAz1Evd?|BR3f832y$4ft#Ai%`syFPzte`I
z<|z~(9%^c^AZ3+7gO+mz=7NIopt|X^EUglXM!)Bt4>Er@57&4({mCsAGkroB(b{wQ
z)X%b`O0;QN@naGL+*LcqAJuW9k0GC{l%GLy*_*GbZO+nr<K@?NlK;cde1XSC=X!B2
z^pv_SD)Qnsv4U7ghXR^{e4*wY97Mactl`^qiknyi{PV!FK`=?NqIKP$HNl+;&KO#g
zy|CWv@gxtrj6wERhP&EpdowFBRUplH<qr~W+=Gm?Ol6tFB)fkRj5|)<8ganG5f;Qp
zck|Gox}Ndh*7jQFdl#Mq_-WGOC;6n}ZO81|7Xs8OE4Y3*dOq%Zp6?7=kO6p{EomBz
ziGF(=21e=j7Vg?juqT0>$_|_&v$p!yI*|f&@aC*|e@4SIq>l9^R<bavmB{{X<N)&m
zyM@IccGb7_N&wrBQ2lvb^gQCdJpJ712c;jQ@Q(7;cHf*b?=`CHt7CJZPEKoSCWCtD
z&kPa{jjTVHk6gfM=dZ?%Q!Yj%D@js5fWh#Q*0SP6nC9tQq*xhL5=Fku^4rCVWTKTx
zw7>N_!M<_oK%14Ii<cJvSM|Tmy*|?)Bj<g~L$So`j}BI!nh0=tqBe+mUHB9NBK>a6
z+FQKk|7g5)$d^-#0FgBHK(y0_ePR=p{rGG~2X9Q5+<xY3H8p?rn)AvDMd2BQRGMPq
zdTC<L6wK;eyfd`0(K=2h!?0ua!<1(Gaj(P$cqB4^8U^>H+!|NF%OiJfcfTl_@v4Pb
zG~UWK4~y-;@#3eU+oP(BvyTN0e7{He*W4DhI^G#`o5M#&^aZuUcqOvk*y$d4NJiO-
zdpnrz^E8umRCkDB0fF6HOL@#p|AzOLApx!EY&6F;<#NVb(dRo#SA{ONyrZ5Ret2yB
z#*8PbRVBTu02`FL*U(zK?K~e_D^|_WWKqBx6>=jn*i1c1_t(IS)j9ExOwV=^F)5EJ
z?2&B4n8O&vsd7yQpSgcqFw{_HeeNlw#-_TWN|DVpyTjkssX<Tj(K8eaMbtEDo7zUk
zvFgb;pmeBnP#%JXz2Ss$A*O_*o&*%wosPj9C&N`seyvncvxby0uizthuxe*0_Xx$b
znpbhD_U(N+sJX*+IRn@LI_UDR9d!wgUELW$bEmqL8ROfgP^@jHO#M29kR#~_SKXc(
zfgz)|msE!-CWux0OwB#~5d7NlUpoUJGGfMLVU4y(z~!!aRH+Ax(M%naL`qieg?gd$
zlo`S#<y9-amLk<Ve$WazMsT@S_akpmHW$9US4LT4JRT>j>ip!^47^^gHH9VU9`zyZ
zV5K(qsbfEJ*w;m*=~S+6H3V7YTj*{yo4h8TiD^2xa#e{y@1{>w#dYHWt`>Vlf8ZON
z<v@bql5;0ktH-Gj;}a}4pMTg!aQu$)vBc%&(Vejb@<8wu^1V=SFb9cX-E}FM+DCKa
z7Q%LzTX}h~nkh3<MnYz@9$NWwjJ<{A&JfQGknmeu*y~V}^$_CO_qL`Lk8I4f+wv7d
zVW?S|@@B3K3lVLVoV;D1i(3SaRk-H41b=K4*ywdp$WL0+UB$eJc^l>uHVQMIwPDJ6
zBQ4xz3i3Dkzso%8<2C;cpsr^`hCUh&DS8+5n=~65Oa@XNuM?qpo2P^Vd82VfUnFkZ
z<gM=MmvT(hO4s7ft+iC=#NsYW7l!fw!<f{qxJB8&mbY7Ln`Cwec2riwS65ZQ1b&sq
zF9v^Gy>u~oMdM3F<yP9pmbjaw=8<I%zo31+;#{3i>@ET%C_PI3F`&gCF{fp)J=*F~
z#$@`_m55JD;(Wt*sQ{^tH=xc`eq?stk3aYeAa4g`rklPLBwe+#I7mNr@on>eP0Q_6
z3h`1_W8-`y<rRhtS0#7B%KEkWi%{!#yanQOkJWOM@JLDNO=YOxs1W0wX*^-xo1w*H
zEpIS~Kqp1?sTuy!^6pF9wZdrKX2_}o2`)k29A2`{b?J$jtc4@M7^$)~Aqh5~9ymHD
zY0$<^426ss{3MUj4%;%&B!K$D+?v_*zHKPbQ~ZRS_3yO)<dE^hJ#tqwoU3YZSKvHn
zaHA!x9LcsaabTgNa-ME{K^Pg!<nD^JbwX4mrEM`cPzx<ghAbp&g$;((yaS<yMDgcu
zViyO2CHiDv*=U@;D6JgfP+gPs9#a#s^hn?_;xQt~GjSPHAh%u%-gA{t!|0CaH@2L!
z;hXBh*Ox4`i+?QZ5gs~hgGmH^<$6po85DAL`iJC)_YA*236A*|{)GPRm3v>Eb!oY%
z45(|*#$<O@c>lLrnT1;1t@5>4yp|@3U#WwirGrb!%lWKjB@W31*=KDT$t4Xg){CwZ
zuGaDI4BDG!1*%<=ycpRA*>lWVKgj)i@BLd=uYQ#>-!SpRIcCp2{@GW{xf-OvX?ua_
z^3Q-bzFC)i2~hI!qHhg#!q%RHle2$I3rzg($6kjx|0-`xEz<ENw6~zrr4iqvW)}E6
z*H{7$t#T{!E>;j*7AcvfiUe;m=^ln>21_hT`wJ%J+gYJ%IE`AEOR{u-bvW`RoOM<g
zA1tNk7T<oMceESi5+7lsb2i4=<-+1j+jXK{@d5A-q@i{<G(_sSx2cYSo=n&iwLL??
z<;qIc&6ex(bL*3Id>>KufFLN*Gw<$gN7LXW2iC9RKHQRgLvQasFXN7Q(aQPpQ7ayh
zTvmiY`?pLJepQ2tD8vv=$!H}~lm;eSlo_nSP75At5s%^7^(<d5SZP8&)p^wZQ(Qc!
zo^%<C&ohEl<Fb^qhtavvLU@So=KI9k+8@#9PpUtb^MStMLeOV!=3;2&PN;L#3qD#a
znWy^E%!gaa+K8~SD6`aSSm$LjA5Sl#uW^i!i?|p;$L$7*racS{X~I@h0D3|zz_jFc
z;C{<li~vXe_re=2nxW>lCtM*-(q-iH!_rXtSaEmUYJT#fZo>9}7nN|30}f--1otuz
zi<CHMRUi}NeUhcOd}gU1nR@BCdc|aTk^1!?#CeO@{3{#};}hY^1zMaW13Ke9@K%;b
z?J@S8@BQE;a|4K-|HSl<#xp44Uyu-#7Q^@0kaimwh<Q&?H8(8Z(|Sz4q$O*>G-j_p
zbfD{=7P&-yfhm272-OMUdK{aUbD1Mnd7EvCmvoTF)DWB($|dZ$Js@K&qmr=r$|app
z0|D*lMYE<CkEiBzK3jjeDg&piWT(AaqWpPP?$I_pZsq#5JM|^XJQto?h_M4=Tvw#3
zA970ZhtBCf&Bz*($<CE%<pVH@ezMr43jBw$X!A-dCwkULZuV2Q6Q^NKM~s}>%Y{(p
zxym+699L;Z`rX%t9B8#U=hY<kRhg$ap63_q<wUgJaqqmu@M}n)^UnD9X1%1wpW7zx
zZua%5n@In4dHI4=QKRKGj&fYP%d*`RJ}7w!!j5i4FinXGUosHrc#c<zQqcxe&=*Li
z5Js}U!6_+neVe4ZH)?c?^56fG+vf5Mco4tnZ8%=ZY0$#p4A4=NOL>9bTSbYlEClfh
zO+ICe$+j^IJ(s9-HgU_5n1UPKG|uo2HDwNLF|XgmD~SZF(d~W`p|;oMNpY-Z;$ezA
zHK;p7X3cP`ls0_54<KMHH})swbI@sN?s((alW?skKKew}V8<rVIhVNCVM!s8XBiZ<
zHuf=<e3h@0ohWi%T+vwr!;EWIJbXyYT<uJliX$y;KO<P7CuGh|Y>3{}_TRNQB{m)y
zrcqWUAHd%c#!bh#6i`vZ!XFX#+rrRN%uAVP&;h8qAUz0j>hDSh)WajHy;^K_Ro6g$
zwd$3fZu}X?`zFT=Y2Dq&rmues;vRM#>x)>pe0F$T$H(!yQfZ*wawedVZ1aVPeNt`h
zZCQpr?gxBTf$ZaxD!-?6Lv|Xrw1_r_;4=iS2nxJWrD1Mht5sbW?k;bJ)adYwz;s22
zI2)qBu(NZNm5aXK#bFHNHRr-_29&AC#9$5&xZ&CjNS6^#ry#M^a%n63?W$9)@_6%D
z-Yegll<mD~W`7xC+(^PWduz`{ccMmlWMH60(d2dqnTD|Mly-64^jox;G-7e913oJ;
zZ4fGexll!MnPNqW)Mi#!1AM&Kben$Io_X!2Q?2;uvJRp8A4a>!MZaclq-d6RW2$W8
z5mTs%&xn;5?G06R`Gi4W!N%ET<r~0ZE%Be)E)%8;y>sO#Fr*?12k2K9jfB|hZF}x#
z5qd_~`|*%1Y&e2VsU%WAT#6H_1^i|hLaQS`ntbr=2Hc|>t3lU&Lkv3rVJlQ*n8!BX
zt<RXAHaIVJZkT5IrR>Vt3fSt@)Y*?F-LLM9&ll+efxl+j#;Ci`?KACoN;?y!w2Iuf
z=%MW%`wsOl^)H;JjJvXMzUTHxes;;((%=H1YdN*1dZ^&gge)?zWtQ=K^4ou^!2;9)
zXA=0eq<cFhZufs2Z+U+s=hHJ_20ujDUa@yL)$^BNo0g9ec}nbXeG{dEx)d<E7dha4
z@^E5}1^qT@FB~)gwt9Uxx^enKR|UMx?~7Q62o=hH^fs`d@fkbc@B`nP)*I5;WQ-f5
z`DKFCW_lvjavoPVl{}jB&j#{K${OB@t7T6pRo-XQM5zkN^6^X(S#t!|tg7w4!ReGi
z1&mj8vl0i1@$UZw(l22vc$iqiZD`7<oNs#44aYnCNvq%eYOF1&YiW!dXBuRVs<r^t
zB3k0B91Zf@8F0i-nWoF#PV8)!-T^1jVVTs}vp{j=etMUA9Da?gJFmrdOK$t1%ix<8
z<n>ZwV*rF3J2`N;(#c@*t^JK4FV+4ps*o2wA0EO$%U^>kANGYf<WnbBL8$V+QJ?0g
zO=fqxsaVf9JNsUE8J_$3z%=(i$F?Ld(fuYYE2o>dg82V1rVEp@=dvmk;+*rC>acx6
zlV<9RqJ2LMQ~5nrZ1Tl^P+|YXR3Snzka@1Lm!ENAk)k=XGtAtR@AQ&9plW#b#%ov-
zoI?uAz03U+0XF?qUb7Q9>0wM#W^ueNy9c%ZS)3J$zpIZXdo5LV6$ev=9dz{e&3Jvr
zk6y^~aJu>1_fdRl#`V2S>ARz8&$I<~67*u%>c#0o{dGjM;>OmRM((myH{!V2tPyfk
zFQOl&_TKA-R8?a6tcD$Ar#Z1E;56WIN>A$gDw|<>p(bwhW%&_KEgly;1)zP;4-{1d
z4uG{UoB;Jb7R`pgSx-R^8jPkV@)HL@6}$eB*n|gPnwa{e?W5#fuV*PsjU^gyB*`}J
zvWs(DI>$0hmm^U%)q<#f%=5-$It1V2+rxAU-Cl>G<(hqC)vToI*Sf)UyM;>?&`a-F
z1)^%NV>{IGRW+MEE_X$K*M+g%$5tpXVy1z|(8A$4N^yls&Zv|5-})07b>7mJC~)*5
zM({?Lw<)1r$7$2re(eMWXfrB(;#~skxZ>sTEsi<re@$%1d~^?0n!nN`ZXYE{Gc{qT
zZP~5cpwMDfu?O6nw0J^^TawHv4lPDA1+d4Fb4%Bc)tm&o>fgzh%G@iM`gBC1gn}uD
z?7B#xE;-0^MNY%&A$CSnNe?x~q~TY6_Hyhom`bNMzl;9iKdo!sd!$Qy3;M*HMGhhy
z(6v{XTcr))cx|sqt<QCErUNavwIlt^fU%qaI@V8kUDz<0muK8;lndXZ1yrOVqt*PG
zB3yf;YhaT09cBZ046|ag|GW@X29Ds};!_V4prbP*KsLDQxG+dG7TXI8aLBC`s_5kY
zmB3o9SLOGV*NZ<lILZ$#)k5iSf5iY!J%zDKP8NLM8C#DQFa8U9Ok!6@DWn=ZK+V$k
zZDi`w=n9(a@Qsg+=6w(c+(o7AgU13cS^L;d4gu0*u~dHq!Ua&-*V1Et!U;rmi9}!<
zZoE==3aj4Faa+#3Rhi-7674mu9dkcn^HBBXdOmtP!tgfs)D7fx-YPH8$;WBQ95g0e
zS7s_c>l~zJjnT@0VT(NLoWbRod-cex@-gVp>X@)&FA0f)rBsYN2sy1ZORv$_kUB=`
z0KXu8vu3EA^vvU~)}J5NfeiJS#=AW$@x8E;tViZQyOIKSYp{hz>-YF^xL9U7T2aE-
z_z@|Q$oV!^uOe|y(vXyCjr<TkW!2X~<?pYPSC`ribnOCZ(S%Yn9=zi0H?G^q>3uSy
zEcKK~0i2tUcM0!87NZRskOB+b9+!>*FCjDg#)7uyTcUjtBIk;yK$S9p_EOCRh#CLy
zUAOrBBDUuZY)0{+0;l_q(UeGh^Ti^2nh7BCSgSlJZL1Ge>y~9@I52XL9(ImgYV=1+
zG$vUxmqxR%rRorTsd%vH*Ygs=D<6?JF!M~`o(vhQ6E(7)2--vVd}Kev23oO+u@>7!
zV4hlg#|N0#d-7_m#%$zsb0LE8S9QwQwcab7Nsa)XzrB8Tj64U4+|KKzO(+7Mivv02
z!v4c3GD|i!f<+j~O&zyklUa%MX%z^hGaEF$w6ADil`i=?7R+>jN%wNw7(C*b41d@x
zF&ozpSX$Q%8S;(R6yJFvo2~(BDjwchS6n~dFa-{opb?>gi@(AcUTjO!R=<fi5%Rcd
z;~f9N{K(y6Rk~R)%Ob(kh3#wV#L~8HrVo*%7Fq|^Q(ze1o3Vy%V8`f5>Lz}lTmkSk
zez|dUNHUa?4dbB<?*H6b=;A*NsLv2UGV|^hGn*1_x#2*~Y^S4Wo48u4z{b!Is~RtA
zGSy4qK!$kJS2(ij;)jNUNw!I>gQNXEAMtA}0;p4CSLGi0THC{pC<%=;yHr5GBs+QL
zw}kR!jqEq|WsTFdIvELP$;O7{otcQtxRQBS{=?vh0`BIF&RfcCjol+sJUDiLyq5=U
zfU{Dkf^VH3Kplf4xBKhj+1wurDGLQyC~LX0GOh|<Oz<kkJ~zLgT9n#^d-22@3d{KL
zi01ifK}bAiFbc8go{as`I+g?w2JYTG#Q0WMjcX=yo~cZcaw?PKu5IZ*jI!E1@Sj{>
zaa2IC0`kv2&ZAh!Y~x6EgRU9!DPWPD4#suHKlZGsQu=a_GG^2={V}l0Xwm*zqvD{Z
zjqmWdK2&9DH}T_t7)EX3`W#&))iIa9FXa3*Lr)X47RFhn;Lkax{gLmIClvaetCZcb
zd7mlMM@~I2an5TQ7b52}x6XIF4Hn;fN7~>J<}c9AYL=39az%4~4EO1ikTruHLeJd|
zlaCZ>`;~bZcSh@U{-Nf+v9jAp_d8CKiTa36g4Up(+P+=eGs+xGn0p*XjXB$f+`Bp7
znOiQ4u{5OaW<E<@qT7y4-0wOxyWCy-1eW3#s`?W553NkUy;-fU^6d{y%AF2VaWL``
zI;A1sE&sW{R{bu%_H4GnfM1O&Q{C<IJ0UpBsB1#zOp)o|_ZN~Q3#W%>0x>)94ox_i
zh(k@<l+R&7;?r98oUYHi4tQ5cg_jmKF30ITvsW~QXQ%E^%}uy3LQUfnlT>UmoRf8l
zfEm11yMJU%IP)YuOYfIwslJN6<qxN?de}-aY92nEDM&{ekH`>yQ4>qXH$bH+TBy+#
z9Fp?o)$iPQxaG>yn@{NS+7dzxE<%ig2I=mM&!IU1rD`6VMSljcQu|Gt8#IX3(0bSE
z4&n3A&1_qfC>E}lw#Wh49_9OiaQy6u*lM}m2oZGLNcIk2nNgY+4sd&qxt6$<u&;PT
z`@kauQR<%X)l>uD&e*atO;Y|&04gXTBz-1C-;fm+^H4zdsAgc4;F*>VfnQ;R)q24F
z$dP+9PXKhA?)Yv>)eUfVRkRPpRiM|tEIfnD?UgdQVSI{T*!`CKb<$`i@!2~71{{0z
zwJdRQBDpfN?yj8Ch~w;is3CKMqSX7#LOFjp9b1&>i7TekGVF2@mtb73N+^sc*-yS6
zlXlSS@+`-`P`^<A@@(j-9-~8cD(F;o>N&fga6g7x4&zm^)kLCY-4MFFyPJ1JWu6jI
znDzUE(<W(6yW0h!BNSOvn04mWaJ?MUE2Zc=?(6qq!n_6z*xF4T*{)IeQkvng7MYZT
z8jQ`RkGhBD$2(jAvlz(AR8pk?>Ij|_?Q6j6e>C;{7}Dt2?bT53o4~E25Q%BdoOtAM
z6_-uyw*5xVIZlx@oBgFUp)I4C_r{k%AwtWP!3LkL2tCk=9Ep=yzBD$`BIW*3kBeRD
z$}2>hD7S3zc<@?DsfPH%POAEU7@ZZ<0U5~NmUQ{vnPvemN(g6IAy>hqrZ$@?>`d`C
zCmMEn-4<6Wd)p62_-IK;-xR^@+V*xrk;NvkQI%HZ;PbML_f*Rb2Ra}!%+*<`YM~mG
zrXC~dKmqMu-fjntF0)e<x!-z_FN{xT3{m#Ey!s@elw+Rh)e?^M<QA&U+S)Jq>=He~
zVr4U=pcw;-XV5xY`M#Qv!JO+pTi*h`W^{>MUu*XhF;%?XCbMb!UAMbfUai}LFlyJ{
zX?X!Jad#;=ws~J6Z8<MJ`u@6F3&}3;z{4o05Fgywp6#7+j`I>SqS7}mN|BNi#)CaR
zIc^XjRx#V)Y*A1=vhJz-xrvZsKkI5$EcU0VG;7d!&}s<{S)v}H%%l5)7@c+_hXQuq
zstnqYSMfupuO~!w-L?O<kj#{d5}Sb*M0pVPH6r#|H0s;b3s+KnnQ5h~@3yYTs^A$2
z_A{uV17&e!tdR<3y%qKVpiB?QJ@6cZiP-f}ZBG>s{*2xxDus@+5LVx%ZFoPeg7J#d
zfs(kMFv(#>#t22x>}Z_i_oJwCSseP7px$s3!b`-@s=w;i3Cu&@aW|VQ7KET5aufWI
z399G+N~t~j-*JxvkVZ!vwKu;pPW?}l@40|(4?s&VYsSQsoCnKi=tbv;vv;wAmjX&#
zZ4vzZV1|-a(4AcVM9qUnaeujMO7E+3D<MMzmia>??hDNGhpxC`>=W;Ag!5Ahgby-V
zTrq{Yvow;5>f5le&%vf&f42mXPyrWdFG$nJl6-S8f?srgfr!UY#s`_uQi=T@VW$}&
z&uAA8T-d^3DGsjA5+ogGW&Z~!h(2;ZU?H<a|Kr{d72Ow$xbOa{9G{G<JSI&i@qw&c
zugsKIO|iTU3fBvhRBDV_shXzk^PW`z4x-uvml#LA-^0flE0;|&&tumE`F=*qwYkpT
zmp`}v*W%we_4-A5+?l7W@#E(D(LJh?gyxJTzJY|iu3s){X@R_$0}xKXRdwvyq%fi3
zfQF;bX#Hjiyq-Swe|)XlxaZ9x0qAhYzv%tQ8nZHSr?LoT)=TqKz~4>>T)!%0T*+YY
z2#vcMS9>*|8NVJ{?3P>+rCeB8wqxO=q7tEI<7$*{V1DWSnMT7C%(1>y(?j?fxNwFR
z-|c^J+LHG40tzS?e$z_Ge8&22qTNtzCsT+4)o^*cmGnuJ6ZMDD<lec^j=Ea#RYz(`
z?&xTqF7KD6zG$GN=`MFhFT?OrJBn}kOJh>~4WW>Gz6I#TYISU$Z@Xsm-CXt0hO+Zv
z9Hv9wQT>)0>Bzr`Im;x|Z8XXyCcvb7l4<`3osU}gQ!2yv0U|MX>fhnPJ5eeo*@lh0
zA6k^|APszR)nIwlax?@gs^0d^*T6~>+HRs(FJxVob5B1l{6qGOyz`*d?8{Z2!6K71
zH>M#U@TnHX5Uq!77+4bpqz3T|GMt*egf#w{$Au@4TTE5X43#@dU5j@(JnMV$*yn<9
zo;T&otYDsQh}8qS=`%<n7#8L-j<)1bzA)_#$cXL+EN1Di)k3AqDR*}T=?c(txlXS+
zQ3kSmyyPAneJhxtSr_2rXx;Oc?jWObizKN2bxD|8I0J{}T<lFOs7Imoj|iW#(2Aq#
zzZ5B6(C0pWKY&c6WxqLYA3Tbej`HW0IESt3RyfBcm1`BHFihp0bwl|JXH{dCcSRQD
z8148ok@f$&)-nOg#xxR*M&xXXuzxrm^tdpBVwi65pk@PL+enpIs1Iy0ZhNq(Cc=6W
zYRLA`uiniBR*kR-{4x(?Xco7=1K-YGV_>e)-uoJe8KR>VsKl5nagKL<yBS~e8bp5l
zhe7i!h0J}NoFwPM@U1%I<BAEj6Pm8cz81;8728#LtJu;)dIzZx=^IZxQ796l26W$)
zI-0H<C(@H!w{`v0;L0eM;zD@3%8WztJ*$RH6xQjeMj~s#NaG~EoksPc5?dLB;b89#
zdGNHg8e?vIV^<|XMt=oq?QL{T5wqp%e`klMsvDy*{mu)JH8+8!JjOetS1LHmGv90@
z6GpybB7Uz@>yaM{yOq94W61pKK#+CG1l|BI?H_|nKt)9+lPSU*PvW~Wo<}J997&;Z
zvFCasZ$8>8&|ifKO>UWQYJAY~@g#-DLfKsotruKX4eGFlyu}XD^tQ%Us2cAXbRPWu
zK^;xp(!%rq*+%1<Op%mtWme$6hA~b2nGOEaO1ISKLW*Ax)fw6x;~ttRuo@V*5P>=F
zx^<K<_GX^n-R!vH-ROJKSQlv{SX3Q`^sUAVxE(q*VEk!I{8NeF7sN@`Z&P(I=Xi$l
ziZf099BS{03@P-N$S{2ZO$xwGBE|t~kc=k30I^8xKa4$RMe36X+IrmBLCEQq-)pcg
zbHKV7OSz=V3hR~FT0A4@t1RV?2S8mgWjz1q=?nS`<84h%p`?)Eq*=GhzzK=83Epxt
z1~2p(q-hq{yY`WF&2OIolrMI_r5Wmi_2K!F#6;%HsasT{q?Z99*3Fz1e#IpuZCoX~
z4HBe(WdaMqf>^Y0Y{Hxfj6-!sipb&XVk~?KP<wSl%}k|+;J0ooDz7dG>hEr@0|L~m
zi+sbY^HlD+tjVH{N>Wyzn8Nc6nWA-UR`DFCblJ5#e)pDZfQWhkx1hbDJ<3+d(EK{d
z#xC^l?nMth6xdO8K8pPs!N9k3c57z6MHJrq#Q8U;j4)B-L(RiiUb{#%Wu+0CJXM%?
zmj0zapF)FiN||8{{xjFi9Tq~r{V)-HcxZ7g0k*_==Pe)GVCjZ2NLR&M*B)7m^iaB@
zT;yQ;0a0qBL#wh4S9nakqG~YNvjfB8&5#_b(9;QDEn4nRXzRSQjRspXG42&3D$&eV
z*)IGsJB(?lA!Zvh24<H8nQEW&5a%o1i`KS$fkjvohN}FelG>BDoE5s%t}SnCRw`9h
zrllzHG)a$fplj}eAa@G~G22_wqA}DY2<NvGWpfEzW(A$xZ7d}>6_k~Ikd)<bvXay{
z6={L)l(GwUt@u%fSTsh>q53oJ876_u$n9)pax>FJ%tJ#BW)nT&=cz)%fFBk>(n>3`
zwR-i=&%p&2j<<d)B2rm$P70b+QM-7$JGPdy1tnJ28L`99k{);Ai`l#{x1<IU+$}JP
z;eO-h%;LmUov(j*U&3b^Zpf+v7~I&G8{Yd5GtRMkd2>8_wHBtdZ!#mkB5H<!Ykhct
zyEK<;{T%8~e%mWe^atdX`IO3-5}eQ$>~RCXFe?cMr7ciX)f__f(XmD9pvzLfcRNN2
zA-Mv%v0!xOi}c4^CdSCTn0$T(Zim}Bp2DD_rIC$5ajzK@SEykQW^RKfH*Vd4Z`THr
zh%JV#QhQoe^AzU~D69X~<QNo!d7wjP%G=99mU??5G&H2!JSo1cM$_B&__9n=LekcO
zBj+)6o<O|rM@q7fZ<2{plAb+@b+33imYHFF)TBYOtZYf%GRD9$s^Ift9Gyb0F}bKM
z^E0TgDWdSU+k(J%#r|8p;%HKTPFnFTi1y5I$lT%k15dK(4`#eOQ+yprpG_z$w#1AK
z*%AWy?&nBbUD|%0JL|gdHrWwqyr@mRt13*XJXyo~Gc0dH)ybJZtZahDmlZ?4KCL@#
zfrk;|k<1UWh@-u#!U?=2z&&Dz)?npHS8DBJ$Nyr4@rLFqdC8wDS<DPKqkW74yn%CZ
z#oIKy-{{qF#IhsgQ)di0A$r^~IDae7Kw~V9mDCbjKF1dF$nxyg%bU_~>;eP+d<?I;
zGC9oRu9#CT&Ces_Q_7g)MY<!NF>PQj%(-v$Y`Hhh&Qg(?1`?#Q#TO+Re-xhrR+^fY
z?tJv&6Ila9hg?;Vh$ggayeravJjRv})5sIS1_2J`HAeH?IKI_*5zihQ1PAX!ng@DF
zb61{H>F(wtiRI5q;c<d$tK+T_Uz@2Ao*v6Dc4YNJM&6}PUG?H09&t3L&4suB3c~l$
z7F*^pUNa+<y$>-c8<OizXglDY8TmX?tT-7mIw!J?=3tQk-%!($N=PP5AmDK#j60!Z
zR><!u5$YI7RR6NqE89>*0(w!s9pSE5p!mMXUKvM1qwUo9w_do%S!Hs9xd&U`#lb&r
zXcwyCUzrw63K8nl-+~IaO|S@9vR~vsFC1FSI8}!55J&kX$C|#p>344!vFa0^;1e7*
zwy(^&n^n%Rstuc6nDK2M9Wx;r?{}Hl)KGrSt5GFC&HOAC&5lgOW~A3JPyW-I#KxCp
z%s-vJjkWZhU=SGeEzt}@OSB%XvFn1wm++FWM<q;aP@1cZ;`ZGrik4U3TOT$yYPqsn
zHw!{tJbg$>UaL3^kc1pn3VL#?sHBO6VeZzHF4^0IK2)iB&E>Ib(Cl!8LKa$}8gwHM
zF+brJ2>2^Xv<oSF<xRH3uUB7<-y0z+)$))D6*7;b0hhbAg0F2h-&jV3;x~5>ABd^=
z3V%D{k}fZ5+1Jzq*>Q;@Q{(Z-YD0`WwQ6ofK$Pe}(&uCiu~D)Xb2f(y*-J`csz#3k
z-7p@VzGkeM#(-+#&J=H|9#GnRQcL&w9b{mMNDFh6UG!OS_mF&Qn?n`)MHjAd9iE(=
zq>3tJr`^smMP-8=Kb7ZuHGG>Ja#14r^3cZzCK+2vmZ6U}G4~c=cI6;=$>M)zo~-JS
z;{I0!P3kW{y$PXcYH%*JRly_tLgBcz^M{Axm_dsw)tJ$*xoUS=ar#O<QQ{)6n0*2i
z_D%!F;9Uz(;NX<|cyVg7YF;?8oz%tT7U!7T_~XRGzk(*McukdX{q+ei6(@hIJh99i
zEBWi}kOcwEe)C4CTGIy+9;1Jz@vtAWs%6r6NxftdpshDMe|^9(vkn*O{Zgx`S%G8c
z&(^CKe{?Le2xyV97a@C?ZFBBU=j`1WXWdK((nYWR)WiqU4M$Crl|5gQC6|V`FILR^
zD$8NFT`W_@w`)MzqKK?its|LRiuBf}l#k3Ut0ZqD&SEOa7gc;OddYbJij<>aGF(mM
zYQC^`lYpdeDSHt(McM`2LwFy@rt<S$OYMx^a}S#N@^nmEe!XWT#_<c83-TV}lU8mH
zp<l|C#vg!H`yYBK1=3#bTXi?Nk>+K0?56`i%^ON)y;#?*c!e7C6kpZN=N=fPfM;+?
z6;lBYg5Dh~@R22<6LAu47`;?29NO|mky@BMFJ*nlg&L)|XH$`pYbj<}hFXoTBez_S
zXu}Qd!($9+TW6P(@|@=oR4Wm<_qS9-1yh}o@l20U#rhswDMmXqd<`Abgnk&DUHe>0
zDyJujmvmXeVQA?PBJ>VO?xHl0!&I&;DkbgLJ2mU!SaXC%Z<Ppq3GAWTnsZCc=ze}K
zpZc@Y<Wfl>Hf^iZ%}TBCLArg~A3!y8@SC-5_2M?i@jlcn|KH5*RRY=S$ZT+8VQPZg
z7V{kTi)+64l%9Fv|1g5KcB-OgmX&kg>(R!yZa`213oc9^_6?p3(nmO8;B#tMX44hY
zk2rs;)@F2`@vxb=o5owYNKJ^22j;!X?w)6+Xt#7}aD#GuhsH0r8IPns?&AKXdzQA5
z6E0KZ?(I6gYvK5&BqADN{3XerZvEk48<i54FhSOo8ovktc{^iqAq!%Km6Oe&Nfzg8
zbh;KR`8HQTwRP6hNuaAXjL(;$)wHdSbTm0Se#{*n^ZOOU4>d=Ew!mJ<wpc!o7tKWD
zh0o$%!FBbIcJ|UgDgW#_S{oZ0StV+zsXmo~J&xE}e#783AS26BDO{s%-QE)M{hKCI
zL}7kIoURCy`cQRVKrrj<2NnM;tHnr5KhlpUp+@r-?P&rDehUgcBvb?pBM1&L+5Xl;
z9fTgi#0@^;d?<Lge806&{kPR#<2rB*8TrjKUg-AFm_1nF@1iu*{y>SyE`?;kqopZz
zzwr>;fDqa)?L2Bg{Kk(2v_RjhN0Z#=_#Z}ShYPv_)8W_}e(UUz^X!G|x7){QJbpv<
z4K}&F>8hhJkkjn-he~{nc|u{c-!iboa?8>942SzUu-ad=Z2W^sz^gv>PQ!<`?OUZg
z({F`A%cT>6=N2Aag3KGT(fu-`1{bh(K^B{<y3KHsm3_mnmR)jVA1Y<&_l_=G49}eJ
zmGD*sffN24mkzG0SO5jhBzs!ytomuU^Ti5F4e3m^GyeyW6n|BfnUESsp_D9*lz6WU
zMMq+!{_}0*9|NE8+_(056pgNq&^sA=eYKAb>2>a^I2OOHL*_M*SnY3P4@N|7dYyu)
zjtKZI8*5{3)2TM-!)_K_)YRvqe!5@>RtL-k;J&W^vlDN{!$gOFeNzp_y)8}7g@cHn
zQ%x#B>s?RsmNdrvRMkDIsX#1b`;z!{g6!Q_8}n*>e7Q8I-sB^5CH~GP+nc%We(C!B
zLqdoNB9pepuV!_wX}|jfx`mU*WhUm2Na19{u1E&~RQX8vn9Tui!=XogQrsWBt$p3*
zmY9jvl4hTzYL2W6LFy0M=j=iJq#=%pe!NELM#^qU^ksch%)ud@TZ!{_;JAeaflUB=
zGGFH3_X)PhH;Y<y7BCI=Vt2U1Q`#rO*C8|Csz$$574k|WXlcmKP;~{ejgV=hS`j@(
zX)%bL%NBE~V`szc)D6G;mswA;-wT%BSY`dL4@&L#-cV=l<Qf+obfNDUY|KdZhnH!^
zACI91=ypBwww66*3dLOH%_tJwxGh34JM$w)u3SFwMQMhYrblpYBIEhopkemfTMEkq
zvavV*%UNk!Ibm}HvRT9UHN#0sKw;hFt@l{PI$#Yc*}gY)H%&#DF`_C<%gcQhibHf<
zXk87L+d4i0II^)^XwRxwz$NFp?0D#63-IQr*l+iS@SsY>A2$d5`1~Q$OSErV$pPgr
zxn2wnrJqWXB`KL{-_kwv9RK8ws|3BFYGH{VgZ(VZYHRXa3FkeAu@MqS30@UfCY_^f
z^1;6Ta>KvPGx9J175ZVbSqu1E-vEbs$gbxdAs3d@@*1@4)xZ&?zU)!=s03P0KBA_y
zvHXrp?;<C+FJM5_l5ly?8)Pl>s&QtD`-yB^gmwOQ3hiNFL(U{RaF_&2r7TrSk8wsw
z-)G#&O4^3tPr9y;4c)g)@EJPX4_+~W3Ypq(#Q6z_NAb>}2?kmmynCF8A(^f7(gfzz
zY&vS;eopW#OD-R?+ppeyJ<Z5?FSUQhj<z3D+5JnG0X&4RfPJY!g<KpMvcnC7xIK%6
z&`s^~vXE}_;yVURdYl`(se$h5Ak;8Y2eZ)Yqb_gQ+MMoO_pK5RbIzF==I~Y3(2;Ym
zte!3pI4Mhe6MD99{E{on>g-f|T#zk-<|V8r4~~`BKq|K56~_IHZ~MYN=;G#c&|X}D
zyQj(I_ysXh$noQ33RcUlB2Lyh38@vqef*yZiEW2psDf|M4QkcB1kh~UjuLZ5)kkRy
zGzQ7RkG3{{XDt~^NeyY#S^s5H`KoAeOB;)+?shin;!x2l=}_0?W?$V2A-B2VrzSV=
z?(yDoaNkO$X;kFSxy_RO3EGY_A*H)HZ20QX;nFDUdkk!ix{|tcu3b(Jb7za21RC5L
z=J7O70x>+I`TqHu@l%Z1MwfZbS;USIi}1PknpTS~pA8&;r~gw@LoO30G3r65oe=V2
zom;vK;fotXPGX&}ZN{)!QIQ>l`Kh)HVD_`Pn>DMKx;Byh9Fx(E@Aq=7+lW*zrv_m-
z{(4PP$*f-Hu=u26{EH@7UdxSmHr;HVD$SvRraUl|5j|ap7`ZoSeby;e!ZQMKzyPSo
zh^Dd?3w~cD$RT!vd~|rC;)o@I#O0+j2qz1zq~di+U6v`0Am2iL)cYy0>56~Jw}%+!
zU9z;HO1_gZhv#Cw+)a(VDo%sT;^i3bar_ll4>`M=-sRbhV4B}ob;BD3kyuUpLexTZ
zOJ=??Kl0%1Nr_>!JnYLnx^=kuCap!%hgkG=04j=bq)x3+i3%Zbw5vJM=U0$@o7)4Y
zhmXCe#y^7`UnQKZ8qDIxaG5}#Il5EGvrSD6TC11}(o*$*+c%|!3Ay99#=T|e*2>Wy
zOtCl(y~ycA1{h)suoU~%2jKZSTqYVNx)kwjk>xXc6vYxW%S=H4ix1WzI|IXnA1qFW
zm{4NAWcLO-NZN$czjqiAH4&^LpIL<`re02lC_4R%Hih*Js5;ZJCp>iop~}htJH6`W
zxvLcp{q%=xYf>t#>>P||S=*Uk$wO!8Kx-5}_eM>2Mk|Z$j54;Ugcw^3X8;3}B0|Sz
zh_?!dt2nq{qLTfqT?_)iJpcI0>y-}#vu7{G*ef;J*}8cUA;QV_KNcwhth+g7UoD3@
zPj9EJX#;ycT7!!_6mc`m-q)Hr;fq*z%&l*pyR3fwz4AAFKUwGckj%afe*bx-cN!%Z
zX6@cm2e8}IKh&uy!8S1=0~1x|mSs%ORMz~>=`6>`o#y!b9jG8?Cyrcc5?Bh;J`!AX
zY#<sUl%2<{h7N#{m&|i(qZbxLgSmxtRif4y%WceoIfNmmez<kfSG%w|cGWQr{E$0C
zTr2d%V5t~qgKZNY4A0l5<A+cvb@y#33+P-n=#@zEl-kP_o08us&OWTiH9qqr7lDyG
zcsNH+o=R}%k2bGSQooh?63|GX%t<!@a5&ju`NqovP1k|i7prhOl4QU9`#j{=r)>eZ
zS&mEQT)wfiMOEqX5R&M|O7*XEU$*CZf3p?uqKeMzB&`QoG%pg!3ob79A8xC4kZKIA
zSXL}?i1~DZsXeS;)t9BouW^|E8Aa?z8l_t0I7hP}Q7TCVJh61L>K<lQ|J+dShBQ?x
zXUh+}?cY^#*^y@OAo({As+gUg-H**w(<Gk;iuYy~Hd8vV&(wA-l3yf7D{V~YgRo!G
zc3qeFZzj%S%6|(e0`SP{V?rUq{geUUu_!yZv9hGUW6|v<TtK*Y6A7T<pD8;oR4^nd
z4KItjzrUD<8s2=r{BCcciNi9JPKmL;qdO>OpHs-;s}aQ&X9v;*K{0hJ7iXE!F(tUr
zkN>~bT>nq4*tid~5HcVP|FO#RJ)$zgv218^rgin5N#l%%V^-*=FHsL|ZTUsPW^r=C
zVc}Ry!GY&oH*@NPd#E3NwN&HBESqveA397|TB&<RGKTITM`A2wOF^GqLRCBy8)qy#
zKKzGqojiU4Irzw^<I^dqj#!DyCD5cPV7{U}kT~kPA)HnZ5>G&YlH4?FhdC<pgi1BD
z7Mv{F-Qmltqu!!2axU1%n?J?#Y2E1C38>;9`#VlHN-0H7C;w($Oj6m%f>MU8fs$b(
zk5V^Po+nQKVE}1&<egs5i&o82O&0TuA>@bIlh<Y_Q@roGqTlZUnN+}eFOWrZa$GKQ
zr=8Yq79H+CCUE3PfPZwigg+>i9E23*FM4?WXjHpD>E%e!?D|_BS@3tunn}|#G)eUJ
z0D1*_B=W%<?ncA8cDBYN3NvHBpxVt7`j;S4e7<C!=*jX~4qZkAGc^SI!AqtmNbSZ$
zIcMt@Tm~*GblBLq2AxfQr(L(7ETqAP9{jCX@uB;ezoqjp;P<WADwB6L@nKt1o4}me
zPee71TN8ar%!wyL{o*ejrqqP2Nn|xUqWyWA1n<|}nku~wJ{a<e{h!x}YGaFAG+_k^
z-*dg0vY^mSBB)Hr{@u#BXSkPysJfJgzw}i#(^+S`xK3cO;jXladASTBqoLo=j6D8O
zPc@^~*6AhpW{akp^Ul+GSn5b&#DXxPLvpBD;RF9!T519OI;+PH4sJ9oq`l-U|Db_v
z7cB$HfBcs81@dt6C1MWxBM+V<;%PckU<Vt3r_ow#4YCu<1~AX*-PqlDC6Y?@Th%p%
zRzb0tPc4pc;17IZ#609DdnT^cfvG{x0|S=_3J9Bji1$BM&@}y~&pVT%1BHD1<H4<e
z4)H&nH=d#spc4C398!tsbEJ+O)4XZmkQv9lw$?e?Yn->U8u+~naKH-NJF9rJxhD1G
zdShS2YE}F)O=abKj&ThoM(p7U&*X<l%h9fKPvIn(<?fyS6o-XQBqXx?`(P}``_f}%
z`lNzp<6)P$pd#CdG-k~>cirotCli9g*cJFyMcRdscLwpdPs0C)yR%$tqiwq|1zOyp
zSg=B&Skd6_?!lpGad)?3DFnCR?(Xic#S6jRix=zjWdpt~cz?|QOma+)x$bM7=dv%3
z4MXgM+<Rg?#=;}7vNDx;FlmU~*txY=W3uTl)w(OKC;dh|cty+L)j#3#(rJ$=i@N_1
zOb%;hO&vH96S7NxRlJqNI+0(>n8>PqJE+>A<I3)d(`bUztqq-8qu9S*ORvjV^aI2a
z&_6Oirsco+uH@_fou8G%Dn9))O^5Ys9LDp8V_O?gV~sv1Uvg5fjLUC6kV0gOC)ecC
zP=q@n^2<>}&6|JCO=CmIwZHwB*yTVs{<_j%w_U}6`BNR=fXT4*1OMQ_DxBLIS*`ht
zJB&iC)MBjrjvG|NP+=?va$EJ%KTu(;E=?BShGClY_pO}4V+Qj*AzgnCV}o!~+)DJv
z()*?)X^-uWm<9bP9H%BN9c(Pi3WF;39xf^K?J5=mzuJ)jYgcQ{BQE6vRkL1S{UBKG
z!=q_p?KA#Tf0}C}o5#%?lnhd5=3TYOcK2H7_9+9-imqkBrPo+5hOnBA>6<+MXYGF}
z+Y~Z;sxQ(o-j74ElP{rXaT?Ml3%*0L*!3xfyhMcHu50K@XMHNaB?xb#@>PA`<qnum
z>)OpR>pN?3O3PQ|11qg9&oeA|jgkMRFJC=T=}Q?5@(AM}3CgzqVPJuEOQU(Bqy^i?
z%X%mkCxyQvss*hBt@X!AVe9Nc(aQ9nevURr4Ws`6cbuZA%LAMfm1^(;REaW8bfl54
zJWAP(-<Yf-eiyJ}4U7o}`z`xNmW>2d6l9X9D1GBNQ2mfTgx79Rt>Zzvh}~^1v%W&-
zr`=V+0P&QW71^!%SvKH=(MeH}7fu%?PjGh%-zvT%eJ2xO3m`!Jl|moq{Gn1Pgj0MU
z<dGxAV25|g7=8m+M{1qFA8ylr@=Y?%hL74K(2ofwEFNz_3+WxJ-<`Ka``1_tObCj+
z2yArA6Z-f<?OFW{h2<#sl`$K<c@(t}k6bk4$xaCfD5ZUil&SEPc{alnV&E6#*R9`P
z2cgN{iT+2UW#o*a|5-B~b)WXS_@{epYcsi|XMg!8M3FG47^k6(-~P*@OKS$T^19oZ
zYMXXKKT@$2b+Us)IucaOs8#Ro?60G_?o>inZF;-rUmfWRZ>X^2==qAkhit%LT+=|O
zd>N}5__<%hSP>`rS=;d0zm8pPI_0qt+V7eWZMGAqs^46?F;r!`5x*hK<kT2Y07Hq2
zpc=ulQbvvYtBdOkSz;}>7ECn$-K3-^a;3(lH*`B~*Dsollfr;0a>Bh;SM_tzs+KVM
zqL36CnH8c<+s52KyCXICq})0YGzj(g<m8OTYrCU`mVQ^Hb2sBf2vC;sVi)zM5|{Kj
zV^jh_?#<BBM<!Ve3|6R8l!M*L3>ybK(8T!;44Ucmh4;OvNivfj!_l}WLz75WvjXgD
z=4(@#h0_v#mR*N$4gPa)me$R|5+VQj8GHj1oeaxq7PEfPcS}NZsOfdj+HID8tKedy
z`Ta`k>7u(9J5Ot=Iyu9fbEAY2TZU(E2D{9KvAFz2A8E6+AszBFps2uU?)l@ry;wt9
zi1`60zfj%K)OAqk%_e3V(wogim#bPV7$|sjCKfgIgR-PXmMs$(c^_Qa!|5u+ctU3_
zqTwbfrpzQqyifY94H|NdIKWaBUThy|N4N(fxS~v{HruIC%X|WjGl!jGi3Z9F&0l(n
zEV4MvNE;xi=N9Yg%2O_V^CSm={nN1PFZ9q~-a+H>&CE!|p#}zJ3DF7UkQAv61++n{
zKSjJO{~-jSP+S{Gd$E2jY1gwd&ikHGMlF|w61D;~#69QV*LqCo)Q>dbfHYfv!r-vC
z5X?vwUzo2U(&$8Te1?ulsHeaq`aRyM?Cb2Cp#?6dl6ZyVd%`w|7P|$U>~OA~K!c^7
zf(cm<GE7H0NpPWUvd}6zO-~F!(n^($E8I=LZRg*V5ysLm<35@<lR)P+?piYV>Cq}q
zvngA`WS}Q0J!T)L-?9FcRnOo<E^FV2Vq5>f(M=`ZCg)B<J!Faecb!9JTnQ6>^xnX0
zDfc<2&pmNGGV^*l+@@$FHu$pn#^}Evc96K>{O_M_dn&IG<7kO>-8k8e(tFe}%EfyN
zS|*Oo3IKuT@T_k%63ggq-Py2qZ}d=~i8<eiHoiK6WdxS>=Yq|WI}eu}F`;GuS7<%p
z1X09*dKr@DK$}Fr%ul+;Y$+t@xW{6^y6AYKQ+-Z0y_EmE-p{N=Hyvofg_md;IyaW@
z$GHcTfV=xU{s@wtv&H2$A<t60H=E6y7CK{*=5aSsRu-5$MICLU^hLqA^<D1C`em>d
z;raVq#<u8T%RHSK8?A)fG~EF?XP~((d2TwxgIP*r(`y@d`Tb?lijqXcYJknHL3|sN
zSVaNuw`wM>d<wB23ZOF1{rmFi8l0_fGer?Iq`%E4qT`gOgY7&_b;~TMgYGNveXjHy
zZMa7MS}*z%ISgcV&?du@WK;wwnQA`hLw(5G4ogze3LWCe9Vx-KANTmRsX)WTh<;i@
zyumJa<&L|ioPS1<$}2nEaSqCmYF%^=o8HzkLNNId>pXx+pV$%v@l^1Oioy}dQg>0}
z$hE>9|4wT`Ve1IzfREht>FElYBoCA+l-tDN{Ij-pJeTcM`g3)SKA&7ZnNW2o8(p-4
z_2>d@yMmD(<KRS@)^FxdS=&oqF(Em2Qk-~ewQEM1)-67kab<iJVnpT1AJzI?KqhQ8
zWv4^$1p|}Qh-W#^Vg0Ur6wF_3im}2S8O@S=an?%u&8z}d__%wNdW_#noy4T2WU!g0
zn|5&}V`_`vWBNqEsJgE}l5SatMQv&`dNS|s$~exH(TD3@a`-FpcoE_{-<X8}nyqyt
z$a8a(DznZmBxfVGorp1@5iC0!7unD=c5{e~fF@ghbR<9Jo1I92JuTP4eK}3Y#zP)`
zAx8l;l|1gNm>2sak&^U+X_NmR3X#5|M@-U;?dfT}+^{7}DGBmjX_F!Y?R(X3D^FV5
zss0_D<)YX}|2CkbqK6~Gn=NOi3g0v_B7;(^Ka~RJ7iaPQH(St?0iA`02x+6jBjsUD
zlDCPVRj%s;@?CW~EqIsn<WuY13MJt^MSHcJV@5uR76(#VY<0fiML)3lTe1@~&uVTN
z`4<zv+EC6@CGUvyP&>6%{h3zCQ4;h-pYYSV&(KaV<zb#TSOj*I(`@mFsS{9tSdE1k
z<5j*Q$g%jMg>rfL!xanDvTR(v>Bz|*+DOsBEe(qoW-8dfjo?3iuP9u7(Gdw<KBW`h
zVDHVA{_(Z1Xb%Op)M-!>5*8N9$u79;0xN~OPD6g@=W~0!zi38nH)#OJ-kqrHrkDxq
zKo5JC`ybgR0;KJ9|AH^^32QT{3Nfil>~hqgtJ=I>%-#=a(`frWx=4%A%VuCxXZ=Qu
zDUwyU&yS860%fA9FV`~=v<o9pN#R4LyQlqL*?qC+C&6jNnVm4$r!le9fd)vnC1%m6
zJqGq$rS_FhC=i3IA^)l29Z-Wj-BF(BCi0%*ET>uCebt&+r8!Y}fu4NHdl<-y|KW)=
zJ*ZhTDJw+X(1;GtQkVFSXquQIZ(M0C^3X7@nnx!%-#nfvxPzBGBLd-`NZ&z%fOF`x
z;Zf<|<++&kx@nTDb5xF^Ez$h)U#&bi;%bHi(CmsT7yY5_upYWWvkGOiYk8_?#bnCr
zm|sjT8Vx2+Fdt^~sNz$0F<=ZkagMT1TXHxCUUBrn?;d;eRkNmK1V8+(ube&i5)YT3
z5rIr75;m=^FN8&6^}@qC;S_}%ECGHA2AZV~x*v{Xf|!{>vOkd%U4<)NKjJXs6WcyN
zFBi9@;8%X=pY{E$&tdkR0xAI^)1;;hcF}=Ovyq(Bu6r1D%*n-c7Zu07-qOa+G%EMx
zBRTNQkk8?%01H1~*5fG`Pm@xg|A!C^ty$(|M6tv7MPN3g>s)_X&2Z(K*1Lg~k({0A
zDRll^#Pk#N(NOBRP+u-d+%bBfZAgH5Rca3DggtA#LE-jK3u{GD!yMZbMaYQKt|_(i
z{$6_}2c8Qh+938~5_^1VT-F1;+RinJ(R8d@lPJmxEVqB4`;YM0gcCr}D(q&kP7M`~
z(c&$uI*YofmY3MKD&|32o=ZW`1Nf3T&6+ZCkce!Y7EF9pKB2|QFMr)V<~;8U@?MPT
zX5CMV=`k?*2l`wgPy3GHx&Ku*1mu4B0~XO1T_;$nBT48h49kCgh+RpnPO11=hfxX}
zH+2pDH_w03yS5*uT}uZ(E?VZ0wf)(yKscgWE$?Dy=k{UJrw}GUvED0i^mVVZ(IHVz
z#Sc6KV(@#Xts6MY2s`fg*=w6NFw&5TRi}_L!9)}U$*s0qdW_$5k0%rW@)2^rC`VPh
z*il}b@{RJHLG$*I|3he8Zq~35&4LR^KbAE_;*7XW+n{%o;H|<i{K__UCmBkZ^U@4A
zGfe|B;E!&$7Y$T6szTN<1f;P9T9jK4xYlGe#IiGp8h7e&_4TS$Ic|sd&AQjE4)0{8
zFl0T{<VqWOr~8am$?^xLgvA&%l4f#}?6Tc{9I@lk*pBF5lU2C;c-_^auw1XZHU{Pi
zgD|Hr(j{s2*d>vb{Hq`80?qvTt2?#s0k)3X7A*(P9UEixE@Mm*!SLSi$aqoJHd{=V
ztQ!QcCa45nRonjc(^kgTGnD4GA0>r3OB)emyzFz!mj4aXo4XX9H{p^ckC1oEih*nW
zYv=uSyzK1#yS_R*GbgP0t5$zA;{Cl(k8~3Zb5XaMrPDq;;@CL1Ee1($o0>iTbUIkN
z`gp3%@+;;GFvQ-_k)>F?vT-AE9qD?NEL;u7t}Upus3Y3cE;&yhPsLgnVCOdA#S8u3
zjL3FX2o>uDY-_ul(!5h|rPAO0Q^a%g7cyt)$l!UrLi$u$i+sh&P=D&X@`Kf1((ETK
zD!??1x<=t~$8yTsPVq-31O$Qe9|HGM2r_vtqlD)=N+$!VTA(<(1rf?Ko)vYNJW>12
zDjxZGKUInsfgNKpxAw{l>rfV=0j)?zO=6eVZpw833M&oMN9uO+cI1UP)-T6DcCG&w
zO3XFqC9R#Rtt&(xGRcs2-RREG99rYc1XSsG|6`h11j>eLYiEG1Qb1#(;o=`FViZ$Y
z;o^XC?MBx_Fj3sMKRPk2v@Lc9Coz6FnE(Dmh+u9H!aeyCK7B5QBU78D{OT~}Lh_ez
z!P$bu)o1&#C4xEET|!&1H%dfESpxRk=F-2;`I{5UT35raDzF{-HV22O>X!j3HnGSL
zvay@Ktm~9-%h4?xzYBQogr!c>)F$ejFmjWF^zQ<2hS^W&M;h1?$6h0Z?Pi<oNJ3d|
zW<zn%I-eGtNOO+mahWQ&;1#QDtd##Dz?pO}X!=Q_Evxyr1@0G8q%Fx_8$KA<H&H{|
zj<v62U*Si<UJO~jAbKP1OR@QAx}z&WXU3W47K(ufokfrJ$`vY~S;_wKa@{?^t@^m*
z!+7`e3rNxvgA#2Ty?W1u$CwTpGe}DiHU3Q<q<r=TPI^B<TTLrR63zp|gqA_Jn*!*E
z+6CwwH0Tc%GKWT)VziLKYI|G9G|XADkQ}~$9+{*{4-aKOA3g9sL&rH|PgjLAyPfnt
z7Z*51qxbq2+Nwc<I1C<sNlb>T4Y@y-B{^7gi>l&&>tvZgf4BHp?#Rk=ak!Stft2O?
z9+XOpfv*Bj_Q*Qd%L(j1dsX=qtuRV8%75_8<A>iTQTt9?6}~Euh1(Yrm@Hz$rrfen
z@(b*)OyilmPy4k}fzz2ln3c!;V4pIg3iEuo4MP-f7CBF_v(R0m^sZ(_wfn`REMAh%
z(A_1>xSIdAGRj{*!amWqqmRB@d=>?0%h{jle0HVi6yCkDMG6nOaXWFWqYnvaP!G$H
zPsMv)X;9+$N`A7>VEXPaAzLl==67F|(o&4XnRWPmRH14Q-0{c!=mKPUc2{nZlI0rE
zeM+D?_Fin`cCFD8FZUK~N|jJr_Z&#L5cXOj!=7|sLbY7P0O|5uw7~y>(k(Ya)gdq^
zhw!3lnaCG$WJ0`L&*rag`u#lrb>$R6bN(mlCO>ryd>4i_z0uup=(86qtXFSnv;qcV
z%+L%e_y%L!aU|NMvO0Sut=?+qjd-*Mvb2QDHHROW=lE)~j<lB>)q^(hb1#7!a`+sN
zfhm^cShKXiDpNB9K^zR`BE`dY&r!M@HzQun#TC|_$hS2}uD6Z~ww)%&Z>l$6C9nWk
zayfl?wx0V(unpSmxB2*7HEY}t!|yw`=kXca`_IJ2zSh&RM5ffJz$@ZH<s0h+THJD&
ztJ89%)l#XaWH_<tLjYg%cgCy^a7!J#nUgyj(^Rv<a&X+nYrolfAm#723u`P%|A7V9
z!hLPZtBom5OXvuYtY^r5E%LSD*L}wTEY2fIi06C6a)yOstJy+Z9@ZW}!+jr-ojSP~
zb{JuvHu~v;Sie<-q1R_S4OW#k@y9>H@<k)xqF&G5>>BFETS@O~m`DqQ+PwZl=rn>P
zx;YA?UfR;XD`OkKuL?z=II~kTED`44t%pZ)3Are9vq}0#Toi)^7V1+=LZa%^o(Q+$
z_Vz1(-qN3T7ABd_Jm7;nJE~^G%6sYU7wDa$cWl>tt$-!I>g^_)l>2B42#ll+?o5}}
zhzv|UJ)d&9#rLTJA6jME+s79)d?h6JA<l`&#7JM$WQ+fma8sLK6`;cP{^4PaA)NFI
zK7?4de^LE*3$CsiZVy9{A0>HSwzoV!z?X{6`op+=NmAj-i4r14dvI5&peih06dWPh
zTwbwi9;TY^|8#$*euPxQUv|o2Y0T>Zd}pR2tB^g$v51lsW0pj6;FSE@G{W5uPo|^2
zG4gPro++`;=Vm?dmEg&l5#;cfynp0A6?jG$BO#aOvIc+y`DTle7?y+IBOpC%P$mZv
z3m=~bOj9FrjfgT~p_HmI;;7gJx6^H#B|Ez<YT$|Soh)oZ;WcuiJxFwJ&=cZfH+{9K
zc4J?Unt0cOPR3Vy7GuVB75-^zp~EzOKwz^8cgX$2G?$~HOR&vRwXhBfH^QM><t7w|
z`$WL2q}I?JY9d%xQnv^8*>)eM84;L6q!|^TmLILLWtU@!@hY{V1tWNwE88Q_230fE
z3TfO^HoenrAuHA#rO#)+eI0}*V{<HUM=(0)r^j5tyNz0-^ggjm3}>`Wx>MdSc*p7f
zRH^r8$ILs*@zsew<*oJL&&c>WR_JMiS?a<VzkNF+|5z4DpHxkyZ;f5s4^Qg;al7SJ
zRX5_Px6RR8O~3lP@_C1pXR9F*fsguSC7?n&9sT~v4Z18hEv(AE_$yWNEGD;FO*K`T
z;c0oKCDY)LghC_*><hRawN3Yz?vB&_GwIXeZT#Z9G+7MU;^L=sA0tZJ9!G0HcZ)3y
z<v-E<n*f)Z$G4^yc?{dIVis7~uC;ZV;y0FQ?<e(FJjief9Mzu+=!gP4*W}i7U30uX
z&e$qCh!<L_O$C~c_^K0^?Z>HU7!Ns6Ew{%?AoA|T=*Snhrzw-C^R^jk^VDQYRkhP0
z^<8OFM~_TIk@gsBA)Cjr8MjwFrYWUi<{JhmYuSaW&NqHpIE&50gx}##$#9iIVQ`+C
zu^|KB-hpteR}OAhqBTMv%H>71+1orFButysOl;tO*csY8N$WAmOSj@vF8k65$+%i>
zW5X+b9^fZM5uGWKmYT$_TmZP&%=RbItkuh5FAH`z8v7&RBfP%%62WQp(_y0lk+;Gz
z#WG<;>kALmF%2A5O+$t#*@^kPSv5Z$uK)pgr^iRDW|u&ks44~_M+!fU_=1@)lS#SD
zNmC*z#3;1!C?t92^9{gyksFw6-eb*6ztRAaw%K5v5I`rl4B-!R(;xd)co5L*9xkC<
zYNCt);oUoYX7d#l2;&eX6EI6FC(PLE-4Vmsj8P9}93;dv1<Yfo(3Iebp>2XS7#X7!
zJgD>35afpeNn*tmaNQu(@PRwqnt?D_%}r7H<V0oTN^I~?A>sG5yrOpy>q4rOFI4&n
zO5bxyCKvn`f7LMQsY}6^c4Y$pBPbP|qx$myUlq2z5)<QxU!%mfdlg!Ib#h<jn|l1T
za!4tvA9ms~!$miX?!=ro8LxrU8)ua>jTMjLt$&C{Cj-44@#69dE~0G^TU30P-Rgy`
zu4@>1eq+v){cyy-qh2X{r3qdB*1S>JIQgg|yYWy<EQWLqy<__U4WBLruWj;e?6j+H
z1~oz=nhLM6C|@?aT6aITSN=8vR*sT1zWk1H)!FP;>~^IToTpuE^78D|B@+?1M4??c
zF~VQ90>e&29o9$gOc#ifwdA?g3&ZjG40{nYznWQ>dZ(&?(d^f+q>Je*1VFY|SgOX`
z@8Ncaw!0u4eZ3J^ybrowB2E7x;M#K7_zJDyj~>#qPv(qv`{4ZOVVEvF`DtF34@Hew
zOfWbEUF7&w)#7`vT^YGIwe}`ll*ChOj|TZ}tw~e2ht$|^IV_TaJQ0#^xHIcl-8P$h
zD33Y3(}rBg(=^}L!;XV~uAdkuZ=rYb1{I7Rj?(E+>P}tv@;_5DkKQxO{3&Vw^xJsM
zGP+0J%VG9FZ6T&T((P1B8UmCe0g)iKT@ia%><#j|Bu5#FGi4vEpuaH>YwoH>(<X~P
zBso%un8_Y!HRqC^k-f;Q+|<H5cuoV{KujIhKYrsx-@7k1%h#CW%O)D;i_Wy$&<$?y
zA0;J0e`W7^&ycgWI;!4Rpv&yE%P^TTUot1I(R4UOwU3=aQcj+!LSKQ^-XP;$CuX%+
za%b?jtd#!{EUu0HO50lbrLdCbRwSJmB5PPZPgVV_TyCj&KB529lJ5>Z67|ayE-3~U
zX;v2S5XDW|naCFFulk?Sag`k;#gCro7M!pgrLe5R`a2nELw|rH{7xA70!0Cf-NP=A
zym8bHHLJp>@gzcl?z?;?DWm@(7(=7!>W31sEzviBc$7Wj@@xm#d{E_|oloB{1xgZ_
zQ|<JXu-}z`+=&{Ugp;hid}Z&JZwXDikaU)%668>F#r3e|XCH0Cy!WZDODA1cd#-K)
zVBLM)(Wx!AZn3GV&IT{PMOAJM*)YUP>|@)+x}OdKxQ>!kc|`&#Z95r}d<bkn=!_2n
zKu3KWBO7sR$aCJ#(@g<wt&n^{xJO?Y8bAL<&n`jV5Rp<nXV|;?_*J^JEB8zxr<<=<
z`}*j|E9uwphjQ+6`_-C*oJ~YT_~J1H{HJstq0QRiJHcR<%p1<0RC!t6fk4KEy+@gP
zMk{9yopG~_k+8!j>$#(?5<7GGIs<Fe5%QQ2>5GEK3aMHaNTBZAM{`5X?2QPB{J3HM
zjNtc@)>Htu3aZW}lihJ)O9zLMB)4Plz+}@riCT>ok1+ZzXbQ6un4}NmiZ_4&Jd4u^
z4D8Kkyd19#Fr2F$8XQVbnVEDOw&>@%vas(<fh}~3qI9zuDpkAuNDdSR6qP4NNTZwN
zi*Tf@2eR}_qDcpthH7qQrbXp}m}kZF0QtJbd64-p_!Q_wq-&=wAsCCkEZ9?W`s*R<
z1tO}cqtc+$E}zW{xx5=$-cKFA$eluHkLzt8_L-Wyz-mLNp0DixLO|y@YR69cy}DWj
z75^7{egEA*4{ZOLT`NXzI*vY+oSYQU+-PJ!QZ12Xjn<d3r^dPaiW@`VkYhp~N<GlU
zjF~*)s654J8|4t~u@`+w{_dK@`fEv&kbQ#lKs|{i#MxF3z>+~rQrS>9Nlcu-Wp9C(
z(<ICDVMTeuPfJ7K<3#Y6nGb%8-09)g1)&mSRcKV<V!lV+dQV0!Pzf+L)7(U<9a7fO
ze0u%s>OT*`q2g}gVHVH*ti#NAQA$Q9=l{&Iuye9B<YGv!m$OL*5ebjxi{F9L4u!~+
zw6lI5*5dt>DC8LgT;Er;5!q)+SLpTJgnXwGEfuyq!E#fcyPtg@@_C4JBKl?m{SpiO
z^y^|tbrTb%nQudZ_T~qqp0cdQIS8FU-Y`*~l02H)i;mXBVvhY}B#5jETW0A@A8#G+
z<2j|YBt}Yx%gJ5Ep+o6q?m%fq-MX?4M_6`EJ5qiHo+G@`GEbEG1bTKi&85^Cc^JDF
z?*f08IjnY`t_t)%rD#a=4?>s&$;msp(HG>x-m>tX!AeS<^f{>u4(bDU!!i#xJpMyt
z&x>_N4LhHo{zF&;a@XXUuwk7j3=z^bM9FAyBfQyt^#djym^R&s+&3qZ+=9NQaehF8
z+^6VHtVAtvnEyITJ^aFoA<rE{L_iDOXq#i>{=4K<_0_@RC9lK3DroaW?-oS{Ut%gT
z9|kE!rm{Vk1t;mw>8SSPs^c>`&rBQ}yq!C~*=WKOA$a-Y6#T)$qIl2@d-zX_PTo2>
zY!nvw;dcFSR%t1LtmEy{&Z0&<!=X6V_)-ux6*=R!)n^s$j`IFz&9T5$_@$J7c550r
zfUa$Vch6uY^}us1Mm;4Av0DqWTY0w0uyn7?@FH@vZ7AU!<VQ8tE2+XGEuHR}_N%Fr
zl5p#k*?Q{mGYlNo!px?)pn(bdh|Lj00A190)GTgpvYinhxI`E5Th^5C#)6Awk;`BE
zs?O4UsDwLWv^rwE$b3WG?0}6{Oh(Qe_f`AdT(7^6<`YY;TsT2$u8MefrKATEh=S~Q
z!b}<QD*KFMAM)cTkvqBi4>M!OfVznSW|;?EybPtbl~{W*h_1qCiWds;KB2&)<-*@%
z(mISdTYKHQ5x?2;r@MZ(1)*&(V?JsaD$T$U1CJ}o?7Da<&G^6R_gdyny4kE0;nua$
zw%9&ontgBOFdRAi0sxq`nB-2!$_d-bN(`Qy>D_h*?|Wd_Rg$WX>4|m~HcL8)c>70O
z7_shsY^7=c<~z{L6R|DxjXGyTyD6qU{#?3UanE_0Zh(Vymd;aCr>03hIV~hi$_G>R
zQ+e@EG*NFDb|HneHVkuK=JE^kU+wUXih<4t0Jax)Xk}mLK4zq-!jhtRO5`R<b$Ik;
zmBLqE^I)6#by^94IgltX<NMqCHf4LMUuq10K`I)$JUJuEeC-cYM^aUiBXFm`^a#<D
z<6$a>e9q!|Ov;IZhEl3!j&G7S9tW=f8)M>-xjp-uAK0Gw3uj3G#_BIqY@0c@37^tW
zlhm7MKkmyc#7HhmBA8*@3+foesqW&f&3X||^6Us#^9{*~ocJZ7I<kU2Cl3{P6^0Hh
za#Z@$?E#l^!Y|q(>O!nJDuUXE;Olq_RQL=JSi$=^FnZ`3P>yU)!T9@#`{3?EdPE{G
zbsPX1OK2QbS0w6P<6Iwb$+6Xn981pL2S>A0cSKJ(BJmZB98}Z8sw5tXzH10Ij`b6z
z_eBU@OM#ZsDU2Ycgx9YPv6F*{KGhn-=CF6b{&l6fnNlR1?WDCPm2w}eulKIM*r}KS
z;DgFAhfUi0MW<2L{(GRzqvnl{y<AN|tTc8l)}6EpzVWHD_KQHL|4@RSW}($p2*5MZ
zSn)`(XZf{KpU+_zq!r@=yDu}Rr(1ueoiDVD_)hK2R6I>hS}x=&8#d^^H{V{q$`bii
z=eh>6)6zFQ;<iPE5^?ye%3ty!)_1z5=}5T<8LRGj#gS6v_*ZBHqbRc#MSo?7XZrK>
ztEY=$KSmuL_eHSW1$5(jkrLnM;<AgGD?IS?k0Ycl=%K0dhQy2ZtQc=i)s;I&a$T?P
zD*MDZ!6mY0>>c}P0*Tw%X8nHr4=vabo0zIXjfK+{o?a8J<-PTRrJf1HTdhJpfrQS%
z+QyT*F8dhh=_#_?=tZ$a&(u{Amy?OE^Ib`z1HTl~0um9?#;+7lLC5>5*;ctBA{59-
z4Jy>mNtoSbQHy(d+uFL-$jmfh!9%%RDoIMm`guthW0IpQvtjhEGAY%QDa_4JTU8!)
z0`iM6?wf7T;AHDlKk{AWatnGCeVaYiWdi7HHa$kXM6IeXttM20{WF!IS%SHCY#1MA
zfQ_S`hK5%lk%nY@gE!H!l!@8k9zSWN42vwB=Tj#?Jmol3WZeNFiq4doTgArT9nBZS
z97LQ7t;D|$?IwT4p*Uf$x6kt+7g#`jk_k*68<&|?NHy*91^6z)i@If)2=2<Y9L~nd
z)>A7<(sxtDkLF`cG`(>B<`FM`rX<vP6P}I#zMa*NSl*VsiRbj&&2`_Y3o4dwrmG=~
zcxo?t)?5LbNNEb+F!}i$1n*GY?rV}@tKO6lgh7#Q-kN)3iG{~@%O?dt&RqHaoHA>p
z<vze@N_s8Vd&kZD4nhuC9MFy1bZKdf+K0QrIfWTrF_%1FIHS$qCwuTsOY@YFzZuIm
zYlU8H&xlw$R@iFVrzu!O9=I*pCgWoeu%5d~X{!L9mw109waZd25zvkdQ^<+j<#ISC
z4-C{ZkLrKNcD0qrjvD4A5iW<B#lcNkVF?<+2Eir8(%LT@fystCRMumvv$QgU`9xl7
z%WRhpWb<|lF7HOMn>8oIdfnkC;5C|*t0(e;;Ul=y%UNA6V2K^oYP%DtP-_F?pL!+0
zQSW?2-z4~Rs<gzg+ZM2B%`oAMyLN)u_-;m-ZZ?k$l~oEZRhJI9xAZTBWcTLlr-Yx*
zdMHl%X`Zz7CT8(>_rp%sI<>$~=9KrY{6v{vm^z$I@qEl9?=BhF3`joHj9H3wSMoFG
z>mNe$%OnAvbWw5w0FN@(>I*XI)GdyzJFF0`uLt<BR1Hyd10D93y%9TpnO}3Bf&nyl
zyy+#abmw`91;Fh9xw88VZZtZNUl&HW@1l+37_MtP4HCFb4RSTUgtC3&YX1|-8fquV
zfT3$~BY8NY87O?_)u;b4#jb|5`L7vtakSkF^G49kaC;HK2{ux*S;JSUCTN(*_BrU$
z+#Y>C>A@g;R_pp=G@N?w!MgXmVp3=ULKpbPr>3|qT1#wwF~>_|vSjq|67rp*?|Yds
zso9YW^C^~<hFbDdydiW}ZkdgiQ__w(PxNNW>b~k{`GG++O+bGFxXv+e`5?8o;-tRG
z)2k}Vha({&*S1z9+lt%GSoo!RF~d_W%dvWeP38kP$EAiQo!?TW8R-MQw@9<CV0vEj
zS_1t&h1g-Ec^YQ~h5WNd&XlYwvTc2+C{ukn->j-ap&dsma3BG~G~W~+K?uFEfSR$4
zekG@fRr;1&t=$)Q<xz>-WzTEcOE$9>Tmd($C)zQC76T`Q+R{Hd3ZH53?$Ab^)3w+5
zunN5_aNRaH@CGTI7OGyzS+`o1z*IsGps2T-8a}T~8xKESQ>%M)C(J9@Y%RNToq9gT
z693t^>ZY$|J<Mk6Zxa|3(c<5`uQoZDv6-9s=nG6q0uCi8^Qs?AHbEzvyBZVE#*;WI
z0Uy4f+*fM<13;hm{1aI?j)X9q-N}L?s@%6#um+Q6p@px^CDpbrhC_}PMyumiExI*k
zi9-IXj<&toPE0AO_=a9*M)c*yPc8o;96#_3lJ38@)hPHGqyt!@z?&hB;0g~~4c@3K
zN#T4O&a7gE_~cknCe?iPnnCyMn5A@(Oo`#|E>0${$`7IgUzU#Fv#(pchp&U(=4<-B
z+z1ZV5BRphbM^C!B;&Esj@|%Jw}DbP_kRc+#95AjM<Nv#8T+`;3s<s<JpUn>gQ>x%
zyD~rhxUf6nf0?3s26`}Mhi(j08K25W-`J*YMQdYz#M{=gDi|G@yJ>ZKz>`<d?RQ0L
zeVN2<;CWc;Hf2gK>)m;;ARt#iuY@u8@@5olEfW)o$LxT>J|oS3xyGp#XWQwRr~h7q
zik4(lA)hsGQ)SB(46zPz9J#+J8WZbp`&6?b?;yymnBtpnhbALr8JHqGB|T6_nA3?`
zZw27uS9I0;>F}=Yu%oSuXqVQWUXkKh=bv7i=+p|S6+uz%r`zRD3f|Ek>V-nc?@Kf9
zwAf;wve+;3FT=D%RR<BW-~%!S%?ND9<zn-U)*j+|qVft`*R%9QDcwJAqvVy@9YKsO
zB|&7LG1wi4pYG)@4q<&`#5uD1mMdVPNlh|+WQOai?<|wIfLu+`I{(?iTG`Z6W2YB`
zpR2MFXM7RTw5dV8HVV+c-nuTb+HHa-e(baVl=Ft2#K$3Ohw-xnt-{v9&^|YP4#_O{
z=bRLm*auQN%T{czoTc`>&EZn`sHznFsh1V<u|jM)VOt1H0#B?duF_<qg-=?z3p3Yb
zb*FVHE<R&3uiLO{dt~r9%(!XYZQ<MaR!_A&EF9|2kjf4FKYpwZvO$Ue`WcOCg2*Pp
zHtpkWRh``NUa!(pm%TuKNdR+@cMFfJA%`I~U8svO@io#25A?J@$|82xEd-`5{0P1`
z_-T|z?5O5}l3!zNkbbH6n9_f&lcZHy@pFUXQj?d>&2_8O@`zOUbbt{+`BvWYi*^fD
z!$Pyw#Ri+%5zn0BPTtGqAfJ>KW%jR@AJ4dbKCX%L2eJDLZL{dyBxtvvNb-vIiK(DG
zWnhrdd#XvGfmSx_cGNnCv*LdUlb<hCxG&0DzpmTxrY-ka;00$;6Yn-Ced}`HZb(W}
zZCSpTH?ptFQK}mUjjE1h3U@8bK9<+#W+6d4W;f=VqA*LSQ8MCeF>h56M>%s=r?qm}
z_@j<al$u&z0R4;gPBKE;c!@2=WF_*TKxa;z5Aj>vV&!z6Gq#MiWc&8c1b{#3Z*HK5
zDHWfqB;639#|SB*BU%bOPL7x1P1JuW4oOHgOic}+60;nK?Ub2O^?r*#DRX{8J36@J
zFVhzr6>?GQddal)@2+_Admk%K&KXZGjII1#krblw-dbYa6v^3f2|1Yd(lK(mQAZy&
zaa?6rk)4lZ*inyblse@=(53ILitjSP!f?mW*-jpa0SKOLJ1W6BwU#e=Us)}NCgOaQ
z<)RX)*~;KJAa`l2IMlkx68!_2?@TvdM*XJ0?a4+S`w+GO>_em|boux7z4h<Es#@J}
zpp?41kAK)?-HCT@6cA`N#aC-KPs6@ikp7X~cdy%hKA*S@tp6>tx@ppxl<0sq?XlWA
z4R2cuB8YAw8@AkuFXu)3?LPgnte6eZ<@>x;hCAs=U~|+hs^9wYIMbDDxkOSr^TXCH
zm8yQrAS;ObHLAbTp3{{{fs~qbh7klB;ebXMl+mV`eH9wuY64A4ZzMq&LsTxQ6U^(Y
zqO~v|sxQR3;zbJT4$1v)HHNhP&B0ZJ*OfTgLuUEHa&Wc^Beuvz**qi*0J3{iSyz#`
zog@pnde$K*_ntXD(PJsRNj^Gq48qg23t8Pf^=!erY>TI6Af0x7j*QWZRwRk;A9)ZR
zLq8<_-Vr}3$l-aa_`O6<oqtrMph@cmvODYMS0<-)JJxr^oWoeRUg62VO`vHG5mf+f
z%z0F*%Sn`B+?Apn7H))$7qP8y_a%#}IyU{?%5j^m*2d{9t>)uDIeUdWx6{INBaAn=
zu8gb!35K%amh_%yG20<$XGVPtJven0bOQI>Kiszd6we}{tCXbEU~%UzXZKU!H1oo}
z?Z`8X@5ZhaHf*vv#AvGCeLDfAn_O$hDgB4Q^rJ>UekAIq?dSx00F08@yyV|FwyRe^
zGaQXl8}%lq@_Blwve4inj-Uu)YCR}__9A*mGOUk;l5=0gLod@4S)#ioe*jw_y7)JL
zSalkN)#L~3LN!UsA%vH<hVx7wp!D$798<;fuw!XTC|!46MRatB+_IDqApAz+12*rR
z2~HY_rTyaU$a1@{m0`RBPcANoj~hPrRUI~cIbwUqkrZb;9Ef4Q-0C=Pt!g_EZziK@
zIMqZAa8V51@(T5ve|K*CkZrp{Y|AmaP+k$*Ng%L=`J2TPygELszuuE0*Drn9wXgBJ
z|H02S-v@2j5(a}egFp}+gqiaaB){VtkOEUDNQ=Z@jVe|D>D}{JouC;cK?F3+`1_+g
zDCM6ZAB1g<w1t;r_EOb{>5IbI6u&&B{A4?bJJY6n+9A;#JGs!~Oo%IPL;r>S`=3XC
zTf~g-vSt0vmGFmiTxPL50K`^?CBqVkVI{g;O6MS|5YhnGdJlRz+H%F@^y+J-yxLTW
zb4SnuuGN$7OOJB=G&t@M<45+Oc9bah#e5<qP!(xvf=|hm98fV?V;g~Z-#|EeH;fz~
z@CCsND$JLM#Es9DdnAss{-@|z`0cpv-KpO%sM7u%-__qa8d=(6UOrpHdFOy20bFu2
zzNb<9Ya>F_mXJi|%=scImP;{^@T@{7ydCZ@s@$ex<iB${`I=RGi|K^rh*?S9Z|efF
zqaS?@n5cHs_bB((>^*+gIC|ir?lC$F2Ka&AH3EmbFfvNzMmygrw|0ddrGN8%hNNWU
zL{`OLr2{9Qr@Y9PT0{9h-Rwz&C=f_0#1z;+_$JA<eaO-&;ZXXPe4mH1w^B@@!#B+b
z|9~<FLD>lGxCVEn?=O^44$rQph1~A*-j8x;j5d?LmJ7O_EeC%}cA$H#c=WQfw4LXh
zMS)LO__)L@Vw8tnS0iNqR{f)3{@acg<0R#bfU9Va!XO`dj33%GvbEi=j#C#&n#zo+
z62lE#!%|{^=LJN3{$e%3Bd~@~9uJPvn>CWxAidlb@-X>?As{E^m}_&`%~7X(J?lj$
z^Mn_F(hr@BL(CT`#5e<h@jxvRa&rM}Tp|^o!7+xfwL(>e%!^Id^cDR)Q?K#b+xYKl
zI(3^<oz-zK8AyprcQ(jandUY&5Xs9oKUl{&l)+**aFqT{E&QTr@7wke)l^<waKnrb
zY*rZ6x4V!}5J#<UU2F1y>wEV;Wq#(G2EI*xMVlEBbUD$z9;Rzxs<I!tU2gSP>9nBe
zaqZGZ?_~Cm0d<R4Eg#lu`Obtmf2v30011km2rU_@9%-YEJG$D&h2yFsc4e41{_VC?
z)QpuCR8?|O&R``y^ewx&N(WpHtMkt=e>0AI<D)Ef#Im?x$SVWB8$ay)_8t~^HzW=#
z4Goxf0mtTcNP7h03OZVl&|Qwd+Ufg|F0NkP14X`>jyg6U{renc|4xvDHmCWxHJF4v
z#>C^HhWuNYyT#sSa{RVSaH~p6XPzo>`gDDgtAf1`ZN!dHYV~EcI^aFeX;eSt+*!6n
z`U|#IiKIz_!H4mu1)-djX*&ZbF?u@!WjEJ}Q7F~}x|UU|aAn3)TXb6=DScKH<S0|X
z-mIHL2?cTwTuW|Gkdfg#g8l?1@ltjRuBh*z@of31rfSaRPPAJhXE`9R$nS&_sA+Zr
zoO|x8xtJnXMypYvhKEUK8sBM1D4PoT@_xM@BTz7k7v*`LiJ{x{W-}fpQQjd~t%b?j
zq9`4v{}`qCGX2&2u}}nVax5MNsNWaH%poEKSc@zcgw6j94t@r6jWBX3E(a3}pY$#8
z6Xwmod)iw|)_hlrv;~#~pa4w;K<?urOQs(_=0p2D2-P)g3Du<${+BP5V$dRMLD#}z
zsA;l0^-_|dQ`~*)0{20vC_iRc8t6&2#YQ;zIv02Cb4@AdNZ)n}pUC}eT|WR{m4d&T
zd0dif>`4&fMRj1r5c-M|u#0i*^wpewb!5Fk2JKmg&SZbQep+_t!giN~$%fZ~z!^0*
z@~+n7ug^|Mo;9BEbVKo7p?i#vlc|wEE*&17dKr2lVgv9SZjc2U=7Z~41t%s88tt)*
z5qn92dZj>GD}1VFa!HC??(w{iT`s41eR$N-^r4x(?7G?e4`IoOA-d<w)<)l-RhiUZ
zM^2lQE2*2OoEu!E7T?WbInvUybEy-FMv8x*(Z!v0{hywf&`1~m^woANA`t`b@2a45
z&0WOEA-S5`+ld5BPZOR<Sz&rgf9->q)EV~}Zp-W9Byx9wZ!K{TUmU;3^G>#pP8FU(
zf|z!`TBVxYv{@x|8vr$|Xb%Cq8GuW1k`GNfe!*kwqU^Je<y$t)n|Wq<?eP3)OuTF{
zD8i5cMJRV7m-KxIAXj1LeLuOE$6e)I{u&7wzb?abQ@Q%D)*~0`CsGoO*=7y=^yd(;
zp5wcpiK@m-**V*ihc(_p9%Yk=s<x3+C^affAhpSyh{Du<GwY%#fI`OXHM5&a#NPR>
zBVN^bj<)!s7KyWrnSIW?S;B|bb}7LN7|zv$Xe=-<5(YDv*wtm#NBsRYvjN^+lW2%2
zlAI)elM}=N!r9zE%&tK`OBJPeJAu}dDNNpuXje$nL=R%yzSvrf=vdSJQ5I28-WNn8
z*$p0ong)zQUE^ipIOI=+H+Vk*55LoOUMswoayvnSB+q?X85jK&7GVsERD+{W7T2oL
z8>><IJ_`41Tp-h&5X)<vVV*T}z0WYO)FOwsXGhxWs<>7mu(56`gIS=~2ooFX30AG`
zq^XNP)J}ARivcr$YpuIf@~>pcpu^{ycHA5pe()iho>zcuwbd8pV?j!TQrlBfa~JCG
z1GS__3*e2$u4|O=W}e0W5b9S4oH1ZhtLx_*l}?&}Nxjpmo_T5;-VaJKn72`t{fB_Q
z90qU93u9eg8S=GWyjvt!o-zTjQONE6dnS~`Ogc0_;M*d8l?xm4{Iurqaf42CFcmqj
z*d+n>!<i)H9(bm|bTp`ndy?33QQwIckI#jNvhY&U<$H}sI!`JzMCH-4y$s5GYW^JU
z;fe8@%T~udwCMSoC?mR6H2_Gu5%Ei!eor^coU5vDJgqzRTW^qU41SuTVpl*O?kXIs
z9is#(owP)@O3*0dlz&tVU<!arw(W6F4GN|q1KyYpHj9N)Gchw}*j?s-W;5=!-0sO*
zBDmzp))GOhN&(l>!8SjLVM95uixYt=t{V|HieD(Kk*y$2S0>cnDNn{+YgzGFMP3)$
zsGt#XWJuHUXg%ekTRp7U1t(>e;Y^+!MaelZ`*d3<2W3xHw=l3SezU^1J-DbsFGM|+
z@bKi;apTHh8On2@hsr!V-I3SZ2r|w(it#GGz$FFu=hM>i(Pt2?s`eDkU#!QAm7q#h
z-tdY<H0cM|GVyL)ttD6t>}wJ^uj^i)X|iCoVl+pVara4eTSvc(D)yPok^fX4FTYLZ
zMeSLHd?>z_?}f6cf#{OMSj8y-M#x$EMdg<}NaWH?gmMs5N5TB1wpn0P3?f-cbSajf
zS1**r+~Rqo!l6^$G)}@YFQX@{nFWgF*1N)d)|!QDUCZPyio+h|CPX`AIOOH+>8HF8
z>_F?J+m95sQ~GeaQ^)xS<2GC}tPfQdpeUt#-Ugx3G=$Nsvg14+yUHav#U#WDtRG2^
zm*p*Ii0G+p2lZ9lr#EM#j|@6>9&snxcuF3A84EztY^R3Cc8_?rsj3ZrDEi{k9yMBP
zTQK)~V2}N3v=a0ZL~jtpW>FvG-*p(lSrwJYXgTNyhLDt~zqE~Mj#%?(_OqoYJ|!fL
z36Z6grlc_@gv~9w7X0`jckVpIey*%~sOtFJa^mQ0Se+MM@Hm3gYzVog6mo4l_gkX*
z_&t^1p+^i`c9$9b9zAh~t2GAF>_0=8SP?XmsQOjcXwl>mr9Kba*{Fj%`p5cK{XY+a
z${8LswJeu5xS{UKv-`X>=CNR9QuezE{Df~(Q_GJb9Jqx&yF=nW?P=imGioV~mr1pT
z{Y^k8bzQQ=;BOvr)OcxCm4CC~Bj&$??%eHjyGk3)ljoeDn9Cfo%eRwu@jm;GK!&&;
zioZ^>A@^<WFTp<&=+yWJC_95^sgA%)Lp71Pe<PLtq%0K}S+kh7GhpF;H@y2tU^qPu
zb}-{K^n0i#?rKbk`%UJ=_R{Do{=7uq8T=$DgYdGHBsZQx<C$~soHZD`;d@wl`P6uJ
zAr*G;@KE%rehmkOVXd^~y@50Bu`PQAUn%}+FB_fvW6|n#rs6nmnX%6ic(b|9AQ>Tx
z%CY&IN`pbB=w^Ow6iMGOu<4|_2s<xDbG_STx`bP=t!3Q8k`8aH+U1eQ^eZY$X7t!8
z&Ysa<khPBQ5x9Tp9BCp+hTZMfe7+<_Q4ljQ*}}k5C&7@aQyn(=FCjZP3<lZ&R>$^y
zqA?1*5xpxA!<HwZTs(5`i@?yz<RC<5?<dOi**U7mVQm>TE=EzmtJbX%ism#3QR-Qy
zZ+EE2t=xh%?H*950m?h6<8^E8$?6^Ge}menABaj=KY4toWr6MA>OJzz_a`QNP*oGq
z{!^9{{^|S-kvd`T`>-tQzVi?&OPQ}Z^jwJI&+hF=i>6VmxC1^{^M?&M+(WwC371g3
zQqDJxrJtQqY^=%m@W_)pZn<nW$1-1X4cd2!R-N^B)h&E2)n<6iF>nxta40XCcGi7b
z2hGi+sZKPEe_Z$`WhaV%$A-bbaB)F8^o{9B4Ea?gWlx0nTKFoKP3V^cp)<{nOA>fq
z{orHd2LqumNGA%!w7_znOsd~KY9E!{PqdOh#HJ`B_I~A1D|U61LR(+StwyM$g#?@m
zZ}a-Lv~rL<qz~c>fXVSbH}^|8d+ya&<{5mWU!hhIFxiHV=@k+%3mKcS3CfaIvH=@O
z*48!^y^M7~j#XuOw1uZBLPayaF<)tA&_xflTq!Sg!!yC0o#Vn0HjWNT(e3|CdSi9i
zN!gWf_xK(v#Y60KXNnDolHQCLY5&TfDO>Ny?R)<ggC7UM!#pi=4Xa-Tu<vt1i4BRK
zx@~P7enBpV68#`{GV24aT)|hK2{L{c(;7Cc;-v9<-0(h33yiEJ=o$T-N!LP*!7{&R
zC<Ttfj01K6r?iW68mc!nCRtYlku<C`uz6bF@hl}7)bQtJ4YTXd*xS4EqUIZf?;b+8
zV7;%N&qvFZq{Tj77Us*1{x@DG3Oc?!db0IrDy{REhv79e&23PipqDHGfXsUBFTTU5
z|B7j;_t^`V{0k-z-iX9C3+qUL!qNiRFY1ux6<FyFUEa6(glOVW4Tx*Ly#tPHu5F(1
z-spalnuAF>Px!5f2YETOS@ed=v(|k6oRR0+^^Yix#f$eQpyWn7N4f2mv>{0Uyl7q;
z-`hzdZKz|>*CFSlj>h@FuoHdbFMr@|L_aP+McfxTaa&SNu8Cw+kt=p~Gpj>hRD5Wl
zT!Z=5v3A29v(ek&Ev=02x{w1n9I7y{{b4EqzR&)SR+^MMl1oOAg?Ut0HO6$iE(%8l
zji0|<NoTKPCGwL0hmfM)8a}k++@IOPbeBW5Xe{l0k;P^-ah7|euAy#IGLq3-Z7twX
zNt(Dy#qR2BR);@<mz{=Hciozx-}{>^d%8`wd%g9a-UQe4LfRl#D)w!->51XyF9SWo
zjfs{yIwlZ`G1H<VK(Hv`k5~yz(%d0xKL?c10a(N#8;i8>F{!#wKym`ApgOF(K|a`K
zt<)D-j%eK-5!s*A4TTq*=U$Gz1`@@(VFp=?D9KU{?WNQ}oudf9mO$irk!jD=D;-OX
z#KvAjQOo8`{B+E|*s;U>G-cH#F@a1eS6K^)Vtfy!?-6d7gZXBxg?-8qZWSmQB~wc%
zt+nWOe1P(p3E0M|<`KuD=pQ+Md@oLXN4*=&cu5~y3<os*WTnPvl6|!RkUNAO;vG3Y
z_%|!yo2U)-0e+%{Pibm_rt2qi{1l86{KGV;eTPYoj7Owr3aHz7!-zyO@A=M6oNeTl
z%n9ejDLC$mI2-F>Hr=*9`I@)yX1k@tiR6%x=oZ3oC7DeiyHFb>U$gYd&|UJF&r|R~
z$gCI#*mX@vaylwnrv`q&98*!4$fW{4AO2T8CIXv7zVsTuts}iJ$DdaH{I~c;w?nO=
zZ#Ys$8fZpHx^{dTw5GvC8Cp+J<w8%8wWL1jx0IPI2iuF$62o-aEZJo-z!#@LJ(Xs!
zcuEH>dNz(&^*du3SQ9D$QmBR%Gm|lVc`Dy>nORbQCEqhA>8FuhWxa#EkAdu#85yom
zJ4Qjuwk~hAGJ^N20go7Dy=xzi8^)uFFXMv->aS>8@B=SD!;j{?n&o2aju=Yy?H8nJ
z5nPVn<;&OWmT-;mT@CBkGlg#|{|iRfq)HWCiowgViCI@2V}#Nf8CYL_<A~-7nY)%+
zt}F1r!4{+`F}Ud@UHx#@Qp2r=dL67^+!S1sbRkaBMfV><lZs8j`mA7)d3V6cIB^oq
zsz9#(|8aL#U2Qeo8ifJ{iff^`J1y?+?ykk%f=h8}iaWtwgS!-W2^u807A;QE_wfCV
zbCIizk&&^Jy|c5{^UPUq)rSBa(R8&iVqLTUL%DH?DIoAyo32BCpX%*z1wpA}J%OxC
z06@zz$w;l7BOdWRKX~0eAIG~{lBLA0%5TN+dS$TuCA(jU650Ijh$pi~FEmZG7|gM6
zdjc?$3^R(Ids|Sz+F%A8>lS8+0b-%Zl=omEQMhsIaz@58^x0(CbVThLdBKuQOR6H*
zb;4hNo#kv7p}L0hNiV#?13xQXj?NO9F2@p_GtC*j4x(v;&l=wblOw!O_3tYzC*Qxm
z=GrCcPB+F21#JitR_p8JEE2?olziXl8@7Wpy<Qw;NNC=t0X8*#EiRWdP3!b`=fiaS
ziK7TaiJ@_Q0ZRh3)YgwN2w=`5jh57yl&P^dPJZwX{p=ijlK=e^5F-5jU7?<$E38m0
z<4G0VgdH3iXC<1CBN}`kqP65R9&gWn$01S}8NzRhLUyWV13Q%25|29jyB-?-@~IhY
zo$jaoj*B+`DeazT=FNYCp)Hux(CSma23US!^dw#SDZ;#`^gD>VTN%xgmdB0FU07=x
z|Bp`;Wtd~ZoUo<H5dE45IKOKIwT4XpNE4(S2o4ik(kMP#N+h7g)Ndp!A!pvqb@ihC
zV}+CixZ$X}H~Y=N0GIQFpvKA4E@8&|cBd0Mq2i*@z7`jY&5#krGIsQy{%`GZ{~?^4
zZD}s+9<Dpw($Xw7p+}*Wvt&Rmxr)+#2TqavhUjD@#<xshBM{hr|4r=MxuNDjCF=Lv
zVe3Xz_JVhm(yLvvigAgtk!_xEp=IcUZ<PXmqI}gJQV@oBn<+tSh7y*&XT_`hrr%3-
zLjEhJZsZn#U9XP5WBV~JaXS0^b0jlr-w}SPheyDDO*Mv0K|7)-!uy&CEcDZdg2P1L
z@*@8C9Ym8&almrUO_l$}f8k{+mPb=*v43o=5`1CVK9N&bCZmlfDTqN$WEI<-?{f;Q
z3vjh@=~v(PIU@K*y*ZS&(|T7`&uqeb=ya6cf0&wK&W0K`LV$@^hGhr_I5kFEj|7BI
zn?BRJGnuSDfoukIt4i`E^p*0yqy%I($<F11mGvjX#0jdInVjQ^)d~rWWs?Mk!YLHz
zd0fJV@wG@ihfPBbipTnSlr(+=VWF5euiFmbw8d%<aChijRXMrcx~+<{C6&<F7<s{>
zo}p<m_xlf%=&)X?v%SwB=+48-<nnvu-q~Y9&#qQi=co!S$k`f|Q_i&Claih;pyb6b
ztUYoU!dgG}4q)5u^!N!#a%J>9?*eJhnOgqzjZN4-)jctjRtlYXZJHiWl9el{K>vfa
zIqa3}D>*~Abu@<k^kMXcx!BiM^^ETO)|A+M$0==#)yk2fzLiR?tO#TLz=RA-@5IK!
z$4;7p)jmGffS&eYiB|Dmx@u=KtW*wz0dRgN7pt!+txhicfky-{CewrW6f_go<*JtY
z>G#Zu>a~v8FNz)Io<(qE>o8IbWID&WPLazazNle@D{P8?SOGmd`^ds?hD+yy7d59)
zNMR$H={`xgkqI*K(GQG0x8nQb8lr~VMSssP6m!_rLfG+p>99kG1!rW5Ezwa>!H~L;
zPE{;gq)K}U7IO7o6mmCMzRzi8tasMOnExnssxwYiKa>xU8HP<{#t6FXU+|#BOO|H!
zQ*1zZrb%Gxq#J@sx216gGYFOh=n<ib0@JiESM{SOOwIj-d3?VP+!KRjwA&-TJus9S
zI`;jMx;fTaMcMZxz0py9m6dMII_aY@ti7Lz4$lwN3EOWsMG_uuC#`$}t}fQs%Ag_b
zf1L`l%Y!>1wH0kH66qb$TPwQJ(7&5jxwueJl(S|KK-B&L@Mh&O#H=6VV_|a1(f-Jv
zQHJ5r0$&*{7^y*%<2hdKt=To+@e6kotb=Gb8sDqfWo>uXN8N;eEyGlTY`cS!ZlV^j
z?}UK(P^YJg9VED%=Bu9Rh120S9gFQ(rycv_*u#UvBsHxlBp_%(XBWYJ?B%4-R7m?f
ziiLZAsU7D?Hu>q)-o-7?=byCGQz)wMdZ?DT-qqdBt-yqdj&rAr&adGQJzNH3CHD3&
z!{?eCV^^>SX^YVUf{!2{qdfkKJKsB{U%F9!qvZZwd^DHC(i=q|Rl>$xOOmd}M~Dt0
zy$R)|1?rfCWN)N@14%}1a@$|$_ft%>id9`aXBEdu_Wq?N9BC-3fW^H|u2oq+d`}2=
z*EszWRq9xg36(g2zrhtt`@ZRjCtE6f$d*^!qTGOE2w&;W>iq}8<*d#Uw=AsYraf9_
zI88$?eBS*DT)}fUhjG961z`g74qcDy>)3@`&x1`v9+f9r4s6)Z&zJT$u8Ym{6tdzU
zxoGMD$#=`pBHj(TVYLIb@qyar8znOun`D5&4_#V5GIu3dTNPT8lC`_j8QsqXSK+<#
z9d+A$#Z!w;rDt_mhTHZY!KA4q^qNzwZX(FBD%aGFn)Vg}h)NoJ6Tdi*;<DGqJupOw
zm_O0Nn6h%qy}l1fI@d@)u}Aa2I~K=v=_^IN30Du}g62?wImpB!V0_B45`!O5?&>5M
z4v%7QOr3WO#1`@|DUT}p-&&5D71U9lbg&1Zspvpuz=i)@+j|NtBz_CbMJzC4KlJ2g
z2jPZ;5)<{6&>)a8jb0aoisR&1ZfzERzX{MjpO%*6hG%u)c-PAu1<FP<^TtMf?Bs`#
zouUod@m|1%E<!okh~hcIm?z8&_=WGQ&Zisz{RF~N`^YWYy!0~9$g7^wTP}{X&M}VC
z#N!ZmQ-Bl9Mw0W}d#jp^=V3K`i=dEpUk5`$A+lbce~+MG5L#)*#NmIXAp(^9%0DG-
z{$x{cJqq%x4YMXu^B>6kae4dVm<GZ@XiLPJ^{H(dOedusmWNFLTNbi(zRw<#SR~ye
zIPMJUO>y{4z99fM|7pp7U`MH*yLd!)N=QdLG#y{+d#-y?YVTScmq5}Qs)2}d3{k+a
zqt<k5zvanr<DCrMY~J7I<H_}Qd+s<w0K$zfS>9kV*wG-e@zSq{lSS$;(%ew5W1>`j
zYvn9zOp>4KRAWA#`G)2~zT}Jj2TOdQs5`+E))P`1+4LpWvt~pQ^K<xZg?`?<Ku{na
z(_MKTtMH-1@(Unuabe-*FlXh6fZQ$UMjUy{-<JF~TFg)rmf$Zt`rD3ZWYlaTg?pD{
znu{3nzRsJKBRZDF65CPAV~Y77QJUQsV#ujRpF*8zjCFjj=qC41OHIUXBwzuX@d^Fu
zN&@09R!WL6ObOqAS2E6Ro5!TEZ#9cFNy1-C^b`Nv1xcwV;XUsqb<D2zJwa0O-qeVi
zh;MBI5&y7vznxA0#~FO2CwEl@#3SK3pz%XBc8*r!9_fO-Ksl8_8Nx(3G&^VEef($x
ze=d$idLzFfPC6fktZ83jTMmZfrcmBq2puD{kL8%v>gyvlSAS3D2$bbDU%(CPb#?)v
zxEF5i!m}fmzS(-ws*UdLt`q}?-Da9S0pq`fdRg7d>(5whhe0qi6P$WyxiNtm{~P0K
z4iEinHGsTz7r*En4LZlDvQF0q{~*zTWxQJ85(K^WfpLO&A1CP%T3cr$T*FAGWGhf*
zm+Cf;&OvtEtD(zYe7z5gkE*_zR*=~cG-JM}7Ke2qKIws1DpOR9u>qz+E|N3R2!DM<
zs#myC37Q+OLpq2E8doNal1d{OpG*7EW=KGzODze_2~8414sMHo@l4lc>(Ck1Drfj>
z1(`OC4j~M}^X;@=orsQP<Bu?;#+F4h_CKn=!)|MIx4}+2w*118cRZWMKd#pS4;ehl
zCaPFN=@#0g=C<L+mkUX9GY7xR380SU6OrpFEq=QlHa${#VqEI>fTqh#c}g70fxSYo
zvxFN8EFWzCPxg-*{oJ@F{Krle8INe!@*VA|yrcY6b*c=Hb7bMrS*YwVS+(mBW>qxY
zfxOtaW8<Cn+nUuz*0^59mCM_T44A0(*!ZaNrz6CDQgRk0>2|w2{Y)z>Y<({R&n!Gc
z@)mZwCQLo}jO$uC1GQU=;Gd4*&{$Alu&9x%u~)5`p2h($C%*vqx6lCrEgCQ3rD<Lb
zvRg}UK2mlhTa~mtnNiA{aLu)EMv)$FV^Zk;K=t*?vjCpLujcS4el;RG2&2?kr4DxS
z6l$Xky{g46nv3ccA_g&IqXe3qp@&~Uh`nCMmxA$k+To{$hEv~NH;`Q%LSmC{Yic~v
zz8rL389kx<_JpZsx^S%H7-&dFN+$Z>0AUO8VY|YyOip;f`K&al)0(+>CVx$zN-p#x
z5aX$$95>v$MMe)|fV$w5I{eD}Gq<JG@1V_fi}>Ho?JpJFa3L1)_TsxK_;8lJhD`3~
z3b9`h8OaxOE6x@Dhzk%;6}Hw=U+oG$Bseg+&oIKbmt*<^RM9~Gg$(>9s|uJug%)pt
z-<TYET?x#KfK2%RpLcQi7Qmt9X4vVZp0ntiFTKV9)1zSs+sT)f^bGRn%CMsXGRL3G
zqSSWFDCzX8W$}7w44M3B>$~0Wn$5gj0c)d-q<uN&{TwLS<YQmL5QYCynt|zn(_P6W
zVPvscS@(@1^w$lM0Ur`W`8G>?!(ub69e-uL?>L@-$m+*C))Mnyv<*n`Sn$$K=M$=8
zhOU|aVW4cMN!(-mJP&~{tx)t7s+z-+!l$FAf8m-9jq|q20mGqT$+2}&7%-w5yKXV-
zJuFNENQJQqZ5+iUrzi^KrVf3PhuDRNs?5(Ie$(i$zh|A(Ka<iEL$fGvv$$%Oj5su_
ziYnE;jw4a#f6kS5YKKNyU!72ei(V$*F5g;)jE@IUbXF!0{)1bPPq;ZY(>~EOm9aUu
zbtIdN6zlSV<<I~2y>hAi(V03s`TZVl=<QGKMR2Jt|J_G7ADjvc{J^|B6FTfM?Y(&B
z(>>;SxkE|;s~ObVk%`Hjnd&kGp5e`WUu5PZH^_m81?DFOi_|c9#JfrbDGCwyQ3ASK
zZ|?`(($xRp>>^ch#X0f^sv3^N<)y7d_C%NvyVO*FG~<s`T5cxR9i3}O$#MO)2)L^l
ziY*~)DJ}ogX4p7=Z^qgzjS;0%v+iAWbDVK$ER1E#keQQM?n7YzK{`D{qj${mdh2x9
zOy*Ji%#o0PJd*_v4<WpJ8(QK)%Mv%#u>We$QxVagU^jzOHRB@-lM|`(qvJ%lA-@Yy
zowHnG4V(;8WxU9U3e%yvE@bI}Cqi=DK<+W%3@NCwEjXUfaz{^Z`-;A@Sx#&keXK-M
zXxcrie&qp^|0K5zvTx7&u^)^7AKXXZm&(#8Kk7`iXYHR<N%5)x<&gmGVF~;q!4gFG
z3R(0qGCA$H%iC%nmXe9kbLx(k#GrjZnwa8uWlU8Jy^JIXeI|x59?&gbPu6bayhr?0
zo!ozEgKbkNY%kH5IyE<~uOfoa)czUe9$bBjVr`R*UCpqMVbe^fpzu+|UE>Q-ifS_?
z=;BA(ZFIjHx`Cmux&tc>$T59g!K~}t*tP!^P5O#G->=l66_tB7canFVtbDTviR=ey
z`N}e24ap`NVE*mB$JDGS=ju~*>~q}uSFJVG6RDV(LTXW$=P25>W{z(5j(G1n=DV$M
z_MW*|q{4IWQK>}bChT8tf3oqhmKf->KQk|}aWHD#=eDbSVB`?U!I5*Yr9SXc)O8sY
zfO#}WDA>|+7JN!5u>6zCn<S|Vc=Y18i`Mg1R%{j6IJM>1P9@`OQ;*RQP`)g+QNKPQ
zb;I#;n(K;Vs`!C>K17bW@tfI@O_^rvfYTh5hof5IX#IF@kjpBI`cdlLGE4oFE@sLa
zxUoMtQKdE^xVM?lGeC5GQS9S%*mheNqYKiBZJo2%h<0-O_-E^+TTf8W$LcAY^Pi<k
z5UuGk=)82D1}Ux206REeorT+;_r#--CF+E~#*asZPrWOk0*pJGr>v2Xstb-Uw<jW^
ztRT&~QS^u(YGi>)KMPSJ)+5%k;0_r1y8H;5&~}sG<5}1=mX-Gu3I~7=yo|hbZ$5tl
zB-&GvES!3y5)Se%oX8POnLyB#GQB(Vvi-Hum1>FJyo~5P6v~P?XU45!g*lpmqL-$<
zX)1_E9*59(q~0X7Y`%u@%3yFJo`1@wby=xPhFoW@;f$UFnhKI?$Raz_EYyrtb(44}
z8lcxV*6t7eT8?Kvy9c;T54Xo95R*o|IFyWCv46@T&r8e1Kd`7U&~}HB&Ko%-S5olb
z(>Y9;oeDs9wEq_BB;|1=h&#%|Y(A#`pllDR%PjJIqx^^|QnkA1>^htIE1()3$9P~$
z>U$K6A(HklkG;zx?PR?VOq7qAO#5#<Xp&ceE*?)(V5LwVU|BRx{X<FJ%{z;-xyVN1
zIz?w+l9rY<MPi1z9}hL^>;@X0DCUyu(5q&sj^;Bg1W!eJTf~#Br!5a-cdOZAezO4y
z5AR#|M0y({{-$hdu$QSR8je<~wz#4gCDp8-L!>}|vGzms7%XW^e<kJo4=&C>VQ?#)
z(;mVD`B~JOKZRgrp3b7MWA>}H(<E`BrOWDC>p;P&L;d%Os^jOO-@M;F=Y3s=GUj3O
zVtbpit|>RwjY=kp9k#n_k+)wl@w4SR<gJ8zs+GEY7U;VVMLY<Ih4x%^2-GweYh5o8
zmvOt3<1ai^Y#K;O_l}L5N>PQ1NIK?PyJy<bN!H&%Pghi&PW>W}H6o)8VsT2{X-6VV
z*LW6F%XMVqpmkZS0<vmdh=x%CJc;ogQgx2i_;d43AL;fJG=|mtn_)3yQX9wZ43p^v
zn(^Nhd$N#eK&#;yv_OW}>Q`a^Ay`2)&D&7?)5HpGz9C6{jib>P-E^OLL4un&n4+N!
zK{&{d6pB<bCy$bl<9@7b)t*f7F1>?a&F4u@IYX-crLXid*54yhfzge^snh$nD(+5w
z?wdI*+Fkzvlr~Vi1b4A*0dhVQ`f_c&!Z_Gj8w}%40JubiG!ntu-^VNZMd@!x4jp<7
z)#OOd!{x>XBQ-O{uEL%?YBCiQdTUa}Szxm%*^`Ku!50S%X2|)|G&o`gdh9MZN*mkj
zBf{b({n-K2ZF0j1|9HDi2YxAQ@rsgPpfb+LZc_Qlvj2^u^Ah@tAQjXGb6)y5@Ex@|
z06RF>qZi-Hs&_%G>5M_aN_Q%$roe^hkBpy8UF?g5y$kEIRtN8B7<$CjvA*F<IqjJa
z*CEIA<HHeXWAS&t`!#b+{GA4;+sa+dBMIPqO;v>xKY-r{d%jX6Qn_&u3zCpsPry3W
zMAoc;eZ$dJNuHMB*(cxc@wr7*sWtcKpojlg|Hz%J1ROEZq7bT?%~uB*!0WDPY7}b7
zV`}JM6<93kVl!9KT(|foXTPVCtSZ9!u}L!L#IJf6sdqrLKUufe6ErV3$j52hXl6pJ
zT~!94Q@)6K;uy?m?T36@1M6?ycvE*^5m7rwc!)ma231>p;4~7BbvI6LV&Xzk43kRy
z$fC$J*`K=|zS*Q>nIwk}-U3Pn_IAepNLwJ7>N7ZG6ENP^u15)Z4<Y;q_o0Hwub7E6
z7TKg21Tx{BKlx^fg$MtT<p-uC4>53~*-sQXDQS}rIcNg@^c-g+VPUks5UFBW!JC|7
z2E@yOv7?IRY6BUryc3F7)?sETi1Xw5+*Ia+>%e2L|KMT}&b1`0(Y1^kzcc6^c7K(~
z)6XfpX{#T0Rq~(_(#A2GsiT!NB=`#^R62Gc8)sD`KGt9al6%iXJS1Hhu4`CwWfg3(
z3*i+`LA!^!x)K1*?l$R_IqRpmvihlpZ!RdV#yY>Ut#u~khkruoo2<}Di1zPm+ojU<
zEzXfTc56@&f8`(OEb<E%R%3t7W@ZtRyI}5%+g|aQ*v7o$X=dR}LbXYmYZn8%z>X7N
zbFGyYn2_l^b6Je$i{qSY3uDQ%m=f)I+>LKq3}}M-iRFb<9S!Htg_9do+A;Z0O;qbj
z{`ntFg=x7`?F(YEWOZG>4rG94d}}Sv2;Q8u4PvI-^S_4hQ&d(HUgt#mX1xAYtT^VT
z>-D-x$iV0)_|!7<!!p6ao+?+Qr5P7vpQipy#*VHZr%Ld<T<P~?&H`D)G|}iMonzbe
z68ax4{W=O==;<fsRZ~C=i`Sl#q_hJ#ta-2!OAS_{8UchhPI&6W)hmmk_C*Vc%~eON
z+>LW${Pt4No9l*i$r6(MREW>rv;vKv(lXegAkstO{NQ?g{3%@Lyq2!TwWlXI22aIr
z6~Z>3f!Zb@a1Z{{S<kEA)nkyzYMubr^V`)QNVNp%$XL@_g9@Kn8|%&3LLYXM6$m`^
zT`k%IYn&fls*_K6n?_rTnez8;tJExJWk(V79m=d|S~P+F1-#DNZ4}ox_#sa%_D15s
zA1dW{wGMo==2t*+<6t~=|1VjZDJM!oJU=r%qEC<vfqpx0SLAnnzdAmbEL7YBbS;<I
z6C>j<EYu#dc_6|pj&4F3i<TfhOhX2QsB_~JQwYzj0t%ov`a`8mtqB#i4Q`#PZkYn^
zPTO$el!sg?|NKE52tiIqI-T*~<EU1=LrW*C`1_tLk`~hNO@Xe*0Vu_hW)-&{`ocEf
z9M<^JOWm+^O04H}1qYO>uRn^0n)F$0!|Yi5+|>lU3^*J8u2m3!V*W*4oa9};EuHmu
z2d`SFnT=aW`<#tpBIq=0@kK1Sbe$mIQ7)bgncxIRiLR$oyX$pR&}-QJshLkOZjd!Y
zVs|4y1L)xLb*y<tYK+x`>9=NOzW})7_Fs+pxPXh_w51UG)kDCi4WU%#kP^*itQku;
zI0%{o`Z#IVYD0WlL1$NfI$eSt*%K&zZ3Vq1e9WQCYAht>ApxJe|Iyb%ESg&u=j|9}
zw4r1LJt=qN7e@Cj{uZw^1=9->Z5Bq<_QHn?Lvs-q7x;bjfEF2Q<Z+#0%AZYILpcB`
zZ#+xt*gcHC!ovRdo5sL_<N?LNQdviV)x`5@+93q$vR{Wn*;f?=znyZl2Dfi_v&nv;
z|BM%0vj1TWnAVTEfZGLG5I@FD(-N{o_l+v%QIi}?Mo3LLY#BDU5%vYXCwE4EA;r-4
zN$I#5U4;Dz=PAE$4?f7PhxBrfbmr{K;@cKg6a<!V*!$oz+L9aQ@6wkmIWlIVYR||8
zLd&9{4|?kKRZ`L<N0RQN(3U`pJd)-npfd)64J!gcP+x)~a>LB8Y+qH&);Kw{4mA@!
z^8q5{)_wymWoxI<P>m85?y3;4!h$27Exqq4hgGjg(k^SpT=McyhXvV6$(xjC9grR=
zQqDXY$<^Buc7O|;=EAskM^l(NmV1g4>zZV(<wDWM1%J)re0gUAOPZ@n3t~E-?s=oi
z=sZYb%IvduCH?z{sC%c*Y~W>McOL{|^+aT|bfOUfoa=$*J>fe;HH6so0fkW)U%5Qz
zlJeRs$6GSq$2iY?hUqp*NtTSnSS?zhKI*8|*gS#CZhZi~GHtWgTYFnQzQX?47GwW8
z2#6M(ec1n`6aMAs;?1*TH?n|4V8gAJVny9^GL>W%b4%S$E}i~$F%rw6{zl}CTxp%T
zRWPqCpJ#$)6s_TrR`)5--ViPFxoZDaqN1eD5zsQa8vyj^7)8$cq&i?-F$5;U%FHKo
zSO1pI>7&p~hEmQNy_f)2wswvn{Xt#yC&QvLYm6lW(&DftW6f6P>QWp29^TS5UXlQC
zyC<_{tWI05Zz{2tX8D~1=b4{z9mv=TGhT5Fb%b9wRAhLQ(~msI51PosLF1qC3O7g-
zi0^bOvvoSMbl8oiG)B&D<mhA;t(O+&)JUH}AV$l$DE0r~`h1IMVxp(>1Q*AM+MUbo
z?`y1?M2Mn{Ik^HWV}E$=*flY_a@oJHj=7ID{CA@Fl;ei{h#@V?9m%s+SA&%1;RW~Q
z3aAvGcxu3Hqyu-gn<DFRbn)8?trT4gnxB|{L|_zP1$+jNCe*I<{c0orxmLzO*4au(
zx`D-qq&mIWXXVp!zi{k`!0>m`ZPoQ<6@V+c-4I7${3viBn~iVm*JvBhf|NNY?fRL)
zgYB}2LxUgMOY|WbDo<%J>BO(+9RC(|X<|s7|6kquaoXQ`GB}eH@sHDzIBIY|nhQ0u
z!$fl#Q9_P-p_#_%n`TX-7n}kwjt=v7>^jriYk+>3{tqpjzEefIG_6SnwDm9I(?|97
zP9mk_6E_L}!I=m$d~3(_VfWW1MXafkfRA*RbD5V!U7wCus5xLk>2*g_bL=1|T8Pcr
z2SPH&KdGy}myx^Fq9`q|SGJETcx<4X(}kiQ)RVD<WT#?wAC)6%o@<6EG=N6(ZCFB<
ziC9FWK@NNN^(B!n|G_2RN)y<~#SXWUcwjl*;w#pse__P1KOa2Xw1B&W8*#+l^=@z9
z++#?|ODhzq0b=SUIFxe-(DV~%=lH|5+TbU09mTt^b<!=avMI`-3&0*4jH5IAo7P%t
zlI^|m`c9{r6T8~O{OEm<G7eoYVs*NR3`%v~Mls$=&Sk)b0dQM+kGQi+?__hVH+4hm
zyLf8WzQJT5a5ZT}Y$<$N>zSjz-St)hNAM#jA>>GVUN2td<N)P@zglzMSb+lKc8zYE
z|JFh~G(OcZ{-A^_a*TKpa);<MZIv!QoHq7-;jsG8DJw&wzSl6Wq|_ATtGYo?q(&Ou
zjgp|!Y5S)-_W$5`Qu!zh8_ErhO_ep*)|A3}B$=Evh}s%tQWrFzaETRM3T#2;gjsCe
zXWi$wq|3&M5bNhk@RVA}u;O--b{&qCAMjJk%A$@(d^o$ECSBWC@=Li5n!?gWy3cwT
z&uJ)JqX2`sX=<#VP)(MPfk`PRjv$`1$&S+Z#t>tP58xogt;&p|)Qd1lWPNvY^`?DK
zs2=&)_-nFNCN@m|k7H%CMT2<`c~&L(SENAsEFbsX2Jf>>Bi<BEGPT=O#J<0Gjqj#F
zitmw^E2Ls$bFG<E*_(5><8Z;YRoU-Et5&?o7pP<Hi!(9%XXjCY;i`&H&q9D0y-V``
zD{w9hIcvyf&)kJm#Z#2*ax-)JFWoxy!7`TSd)Trp1%_Z_=ZYM>$Yq>Vlx9$azF=hJ
z@Z@U=!{jn?oj<hjQZyU;bE5vpMi}MBlO9&!Z)D%q1@#^aKm)RPP<x%x$u)4D_#oxD
z7W#ZI8ssQ6kw^7@CQ86syHKYx^pc025l@}4CTYt_A~hY&8cpQf=@xMwo%8&Pa#MSD
zGR{QN|7B}6f6jC6rW%pt+I|b`U~`rIeF-grey$Q;gl~+dtW&(b{a5Pl>d-nK@Yd(P
z@JMlF{8r7I9e90$RoSux6_^rvD{HGN+Vf;=YZ4IRN&jK+g?j`*Ic)D#A4S$^qCgYu
z{s9^=&b5;@^VcN}E%8^%GPM26Ppj(<*>F#duz=45W>bFpdCX0LLx8&y&HmqMx}Q0O
z8`GSNucj5yKGXQ;7gU9~Sb~z}?9$|2{RLzI3cDc#kQ?NxnCXr-7O%esMYfi?qoM_i
zRcGaN<D#jIJ|ESDXY}LR|7s*`VZ1j{m}oPC`HwdXe@;w}s`)R;4#lfGTe&7;2bhyC
zI#bft!%-+U@v-DXt1R;k)x=qgEU*Xbptbf*<A*s`*#0=fa#rF9G@--xHNGzSrRFCr
zYf`drkz5#x>#YJ1)umGoz6*7Pq<9R!kMW8p*m<jUCQU*$yO!&ob+Xy2g6OH{S{mpn
zMFCfuUQd`yBC&KwTVWh)m7)H}-PsyZgYQ+Xfu-W<+Jon5!?yW!E9KiNpVQ9auE36I
zTY623vP5X{^GbDzxhI5-B{pB5u(gJ=-JSX>RNE=gxdMU6Gg*6d${Q-W$+UvGOU4d0
zYM?P3m@232#Kf@MoT+D~PRj8<H?;%@O0YOx8H6S0@!9q``l_jRr@Zn$*_Zg?(KgwD
z)w0cLt^yRvzy7`$^_hfr1pM@-KVt9})P*F}icZa8aZD0!BM-YPx%Vcj2635M`}{>s
z5k8yp-GdcYamf?^zTCdAuBNUfTWrO2V{RGhwTE2ja-1(N%AnA6M5Y|2<j)i&ec!ll
zbrjTIWtdD-m4)Ry%rUfo@pdM~CC2~W)4B93&SCwfXqAEtFl|knDZD`Ym;f;0&e5MM
zdumq0lXaeDBBJ~>>QUOhah_g`+^}2BAgpJ|sx^u%7D?~cO`4(t*-^-ob1)aH{0qV-
zgT344D$p*4v?pC@kOuMscFWgj=^g)BXSI-J5h2{2o8~9txF@@h*ReF&v{?JjtRgFa
zTK;l=xvf0-hGg*Sg2?rot@-_SH<$gTj$qjSGasMNrqx2j_&`+cEF6LR0>K>W4NHus
z-)?ehEc#n>uwg@tzq@=ev$sH5k~nIz$XgoDv~Yel0x&LG#2%j8%nd3Q^N|vwxbkbW
zv0Geh79ycRodiiI*R)IkD|~+Hb+E`8z$!Rb4ZrX@mPVqUl0zhqZt?MF?XOwHOIhaW
zFIb;^bp+3rBQU+lwb&`l;b{N;{GiOGhf?+M3Ek?UGJQ~viSzXmm7l-HU;(e~y}q&0
zVXSzx*<`rBZc1y*&o)i~nFL5V4uIUQhiX4wsNS9aTQ(Bv*1+fnEYDZlxBhf=sp$3x
zhP|%7A1NU@b4P6&&ZQE^-I+6(wQ!<ffDWt_#v~&8qvb>G<cx?EsSd1#UeY}_(LN?j
z*&G@)J4P01H$Dpu-1GE30f@&wrg8`P9X49h%FFs48%}wk-tIP*4f!BGzj>tsB~?3O
z<73^&Drkf}Fq9$r{@;&EttP&#$76hJxO-(f%DbZw_p2l#q)?2#8Y4~c_dW5Qriu6e
z0_PHRj48CQ0rWxiI?Tj*IG*Nn6=}LFrNt_x+@3RU$BBOrSJHDO2d4?VH+pm5QZqjx
zt707}YGbB`*!Bqg+xIF%w5895f$Yg|x9#B;`u?iSFda0g2!q6l`GtYX@0rDKB20Zb
zPqU$Cj>mB65O<SLw|7s_kFmYomK$BV|F)MsdATfJk-05zi&Lh*F5gwtVqypg?q;iM
z`gquV(7G$b6}b*rNI1Bw$gfkL<y2V}0m!NeUn!fF3db{k;B~^8W_DY5pXP{S(heyh
zo#mL?mY&i-Cq3-G8QG*753t)pzS#D@t4$etTJ$%~SwDE(<Jrx4$al^y6&l%lG3jxT
z)y|q~Bou(lgBK{nv|~F~6yPrlIToheI-V&{#OHk0(*X|z7Ir^OyT1_xI*2okxRD&2
zT+~$4Rl97%-wr!+@pK#tRyno*2N&vD^LM6=XDloc)<NHZGK!EKplcIxulv`_51;Y9
zwsBo&J9m!pJF{>g8W!dVylhQpa|T`OjEWfb60F$!ocsPAyMF6ov2KXXD^snH8Tu(s
zdCkcJX+dpO9V^dSE^%c3kXK$`$Gb!`eERmG$yz#Fw$pksDfi!T7z_0K+L}L~xd3_E
z{*z3FQ3LB4jm&dFez)U7%>`M_62Z4BjvIjCMZ|*u1Y0gf-#`8>?dYH>=jr`b-5XjG
zabWFr0x2IPITm7VnyiaUFP)-<+SC=+B|h{ZXcDyvP|1P)@}sO#E6n#vZBI>8cx{@G
zE)r38E3=dU(O1+Iv=O5JTy{GULXhuj_l7u9Tvle>q3s@+Dpn6X;+QCht<6HHhh0D~
z<_hqO3besLK>Pms9ZPFnum3@$s`3I?B!2#$sAh<bxhwu#H<Z4{M}qxZSJxeZk3<_#
ziE~Hw-FCQHu$YGD`wlSxcHk!Pb|4y$1wCugP%4%}CQw9}gTx7Xy#7~k-78n#YmpYE
zE^RpdO_Hi$A@ox4gWG||2{;rugwwTI=_@II&k<jm!Eg;0k&q>!p?r&KNy<^<Ti$VP
zOGci|Lpe4${=9sBZ1S<i;#{yXXn1Dlu4XYD_hl#)+Q{9WID*I4C9uCVhSoD5lOQl?
zTTo#tUTlY-wBButmdFJvQ4$>~84=P-;Lfbz!b29ZcUJ&vh@&b2Ib<2(u~btv=Vba+
zZ!OZ}i$ZW?)fo#AL`PD%n=LX?b3Q2pRQn2M5#%8b#_9lZd=$Z1CU=l}#5~czf5J<l
zu{ze882XA)j);Ol#!8+~j71^;uOArr>d07o!6*`yYdx=x1Rbgd+Lv3=U|;Z}Q;Hx?
z!{T<hnOY}Hp`7}}AR_tQ;J@BM)6dbWj=!?C!^ANMDG=WXQjc#O=zW!wos>zJ)V}fZ
zBgRME5fu8NE6~LFIAL5LHkrIMy<grGj~b9QE+3x1sC}+-L^da~<I7KM>j|R6k-~kH
zQM8QfVc9!omySj4V_8Sn3*L66Ft+2Hlks6qF#ivZg~}PG_7LgWU#(vfgl1e9-`qq0
zADlQyMFF3aT~i`tBB<Kud^d>SWQDQ|vn!D%G=HR<Z<hh+6#y%1?rKS%q2uS^^?UkK
zDMZ!k_9cQtiUlR)`iW}V1}7;60<AGt$gr{5f6^hgv39cMfpj23b#crb((e;I(kmGZ
zh_?0Ab}6DigV+*#T6&|dx5&7r-FF_~^M152b+!{8QnXCaFr=-ESJe~r2_RM?lP(OL
zn{3TDdj=8Sm|&4b4tE)k<_wIY53Y5QiR~QZ6_$(zx7?e_y)_d5Fe#q}>#+pDA9)Bd
zVb)GaY*&toR3EEFY!Zfz4stlO(ad!Jmhth!yb${Icy){RuxO?lh1`)&%}M?E>#P6$
zU-TEHg<BOuHo>=<!`1UtN}$YsK=9K^u~&zD&z0I>9&r%m#yV^e=~9elh&TOd4;=XD
z?nILmMs^IDeyN`84&M9oqTv2T!tr3>7gV(z4ETZbj#c<|H`M&o%1GzXUVM){)rGg#
z1C}QEMx9MlmHVb|8LKzXw}mA9)yJXoixT2V`(|AKQ@AP5o*CTq4w=-%jq=>L_0s-V
z4AP<l{(+&|Pl?5Ch8}WV6_xWC(@|rhX)GfRBPhh{z8^{(6=NgZWSO$v9LBx&$%|Wb
z(ly3OEkZHAMvXAr!B`eRtj#@2I$vM&zq@;Uu8c#)2V*Sd#35}oC%%gmMwmkYxXiR_
z9QS!#r)pnQ7Vavh!hNkjCSs38l2&7;{TPQgzAf)oH?7LFLZc+Z@=spd*rp}Tf$A_^
zgqo8BQh)(NDQ^Dphl%U~^Nr_^)!CU?;{U#akDmy^L5{(KgGbvVfBXJ!_I%yNxQO=K
z`KjsHUXu8|=z7fNmF0*_un)iEeLetYeJW9Fn*oH*#_o0&>#RW$XX*y>M1qmkgz4ek
z(G!w&VyGL1jdqpPa8J|#NWi{WK(7ng@0Mu=x`tdsgOvfb8O!~p!m?qvIk~c_<!P4h
zmY;kQD!?vlEFK`3vB}1x_neAwDd1p)&t0S2Lxu|Y{$H*su9m~}<}zXD^*+Ie7hJU#
z^Q!`fCFt)Dmf+ol$OXOmJzhic_AZ;zEPMlNibx*Z4z=vtk`^^=gJ65tXOu)@@3{2<
z;1i$Lzn~oo+<&f+1?ThJ0T%`EnDKkq(+n<<rET7v546#(Wuhpy#J`U3|7CM25U-T%
zZ;5GZoUa}nY_dgdDR`igeaG@h9*mj9-Ri?D=h1+aW4^>hY$$6Uf_`O^5!WqLXYV6>
zs-0+D?0z`ZmoU+ujx7A9GpV)9X+0^BW<%~d52woM_o216W;=Q7p^8Fev=l%SpL*Nd
z)fQ9Yfvh_A%B&8&k)=*rl32rp7a7(S`UpsLuxBUUh@bsESgOmCl7C=GRd~6f=FFH5
z)s-WQmL<Pi(*FlqJH*b2p3JA%;IGw}CjOzdmND`D?VO1gT5K!lRVk@m#KH2=QL|Uk
zNtUgv582dof7CUXLx@dM)fr_dwV_d=X=`V7&MnS(^HUB^s`4q*H=6`8AQNvaQjAoM
zGieN~*w?7RuL}N(A-b*=ppY_@F}A`$kY7dkSSs_ac6RiSqq5PkCzviLO9M(RKp?5V
z+SqRGx~K`Cz?IPH4ho&DKXIU;VW}6XTErW%r24JtFpr~=S~*RxCk$%x2z3k4!R>3<
z1*0eJnRLjG-&QOF6cU3f`(m}~$1ReIlgQ9$3MZ0QmV-+Jjjsr^%7c=2n{we!sl8t~
zOaoCqqz1mA=YJPJGwE5(*Z7@xuoKUlHQ7kHjd!d;<z@Uq{Ap3Kr1s47uH<F|xm39Y
zkIwSFx@v{DnQ<;MfgYe0UQ_-M@H^67!x5K5i(yu~3MN4@Q-Z^9s&`pw-el`GlcSC#
zD||$BU$*CixLa!?9<wSD!i*6SkBpCEoBC0pRMOIXumvNr`!eW+mqBbtd^$Tw`T#&3
zMC@0s)wqrx0)Jma6oukC-)z~=L~h_qfGaOue(*eWBV~Wz=Id>*{U2PTyN-3Y=BjYY
zx$@_EMj_G)(Ir#`j4x3n0VKg2$%^laYoLj|(#Pp+{xe683#+6bwrqE0m6LF8%#W_^
zpFL1-@b-fZ+ddZe1h&CC0LwkL$gqSu|29(Q$u8k1C_ooOiRtFT1Ma9rH<>nB`JKHE
zOr2<`N8kGT9aJYW%Ne06Kk861-LTSy-Y^h~I&s%umIX%dqqQT+v35wkP*(gLd!-@e
zU>x2RDL~+;Y0x@6=feyq_)=87)o$%qfwW*WLU28vKT*bI)EzJ{k*`?7lEm$F6f<^T
zbvO=4kBd}w$%@BwFUz8JA@2Rej-*#F{zL9)v%IBMKmU;S)j>d200NEdjClcWKYto2
zU7Ib|aGvsD{TY(CWO1U!N<&KU;t-b!pppgP?(w^%nh1^T3g4Wt<Y{N=k|)I%-|z@I
zHNj}k($o%_LCP>yfeNdiw&qqFqdoSjgiEnOhdoH$E1~eN;v8y?P@2V(YnZ3Ue{h};
zHIJTSR$08tvU_1zJRFy2iDQk#aIo3ReuCyB#2SojTmxmi;Oq#IhWVyi=QX;`l)q0`
zy72{b;^t}LR?e)Bg2$RW9z^J#)Qxenbo9If=jp+@F%ZT1j_zl{+IwWT<5PX5=PY>3
zSe;+LP7P*dSY>Yh8qR#OUfW~n&D-^ojsvEQ%uO4_6PT)Pia4M-M(T=6IX~qr&HJwV
z&o{;o*i%O&Td0)3a|yK94;}#Ly6ggJ*&Tn?<-N;=p_Loh0=85Q{ZGJ5709~D%DKVG
z5RU;vf+7*8hUdwnr1rCBP?2Nnko!27<>4BOqa<$zwmdoF&1|0hsnI=GjJb7dYnYt!
zUsWWPae-+Lo_&j-c7NdonE2mxs@XIAT5Q^)0_=rGC|ESjve?CfoR)d#u>mA_t&L(W
zJOq8u($zB@GP6HzfJ)0a#)a`#NYZ&_??;KYHL=({VTa~lwdv-bdbT}ic}Cfa>!tir
z>&}FCn?k@k6x$1P%eyICsZv(@Ga9zQ*dD1C^iL(m;RW#p)2ZD8MY^Mplc(&dh6-ZC
z3mBnNq;+4LHgnvy6yWrQo7Q<8HsdIy9J|j&WqkDaQ=$^La#aUHnMf5(@SK=L#;#|{
zoLQurIBQSXwy>gH6R1^r4`%!GvmZ{!R*P!AeI{UuO<G-_-a^zE%P><`ydU|h`e*$9
z5BkKhj(yu>?Y{Wgm@=d{;|Chxiot{2HLdOXr?K_u4*aSeu7;;&;k3T4uMlG5!;X%A
z1yX<VmRYs|zAfR!&zwf&pD;$3L7pYMXIun<M?3iW-*ug9zU;I%;RBwu8WD2PgP6~g
zqcdG8zgB`_AEnm-Yv1Vx@#doa<G}Eb(a5v9;MbT4RGP=c_=3aAj~XK<(L%VkW054t
zVsU~{n=q%H5C*W>w_!fbk4%@xe<o8Oe>c--&e@2uAJPle!+d$9O{dW#`99!35aZX>
zA;y-|(6q?yH}Sf8hmPZyq(yle$}F#8a}87so%fUCoa)gv`cX^)+2Y=&ZD5>!W?lOT
z^J!jXk*z=V&95>1ZoEhykiIWxXo?GW#a*F$iC|c(c_s~z(W9fBly!25#8+Es>e(Y$
zk##2-WRT;}??p^BPPs1t+*pdz>6ttrvfS~yj#)PR7H&c|1>ZYVxj>$SpEavUt6Gr+
z#7EU;ddPk;pVQuQ-#JHU*F+P2DEijH@Sy@Z3-$O>D{zDX4j>LRzOU4Uiw<bzm_btd
zU{&AVk>K{|z6fd~%=q;BXvOvii-1-2;G=$$`eY^kN0I6-VbI7;0E)u7b*!~GlMX!X
zC5HT3YDmLQ=s6I4pYvM{xsE_LL!F%|8K<NFQ;<V*Z0tdMX+Y6cge_eVh8`=|d?lrP
z>NheZq>Qy9hWX+(fbM5Dzd?$C>%x-5YPi+%5chFN51dHJVfa__#dXY=g-<u~>|#Hd
z^~*Twt%<+S7kol}D6be5C=tp|e_-*>8A0rkWsW@Q5-cvzS|+X_lryOz4f~x|N;chE
z62?-p_KFzZQ99`?d1xSsrHIXMF40fMyfGbdAA&oe50OPEsDRfLOsKWzRq%2>_?CG{
zZvO6N@|Ybn#MOTCE@RX)#RRNtj=BsO-<c^!Q>!?VIiW=u#qvEX^^eZCvQM|H=!HJg
z(5V?7eYR32qI_>-{$UMc{a~M_Xn9pm95d9}h|_v^MCQQR3gg6FMK<%F&AXV<b*0y=
z{_|Q*ew@m2J^p<i`16D_Sd0cf<N<%)!+-y2i5p#Q15&1<M!e>S0Gh6bXP`V#Q?$=V
z*W)3bsp3D?(eq3;&r@sBjG4@{@gv?%ikBBYTB}xW?DHcfzim)nd5nTTtb!sKqD>7S
znABbh^0lz0JA9sr925skYsH0QqrRM~_A9$6SkQbQJ3&$gv3LL*0qF?u?>NH^E}hkl
zrMjtg-i7$*^|)Ejh(Kj7_h5&G-E90maAaq~gAYwuJ#b>v$RA46s#bAV3(;ywIXk<8
zkXCJkZhzW8iV+yNN{}$&HVyN~PtbZ-4FUxi$Q?t%bI8kb?>z*MPL-{UV}Yw@GzA}^
z`jQfi3=8d*dx>kI?YPMPmA1|}YP{GQA>#;z6&EhFTm;_7Ywc~`(jd-p%#utUmIN(>
zqD>7(I6kuD`_Ex(d!FDJh^AxFB2qJSlH17OYPr2iu^)h;WO+nTS}sHEWa;h{gk&XD
zZy7bM<XX3}RzFZ_`fq#jI?loW3k>#)vZm@FnkoQF+p6oql}{%{p4SW_Z_bGCe;F3&
zABP<1{XLuO4MO8}L{%xb;leet{E*v$wt}Y|eKs{XJ#kpZL|a1B1z2Bt<x_367Ypnv
zGmU7)pF1ZAWl6KeUR(R?8#wl=xGdnzvblBk(}T~})s&^RyWN-0$R|Pp4HM<)vVv~D
zIZgoS+J<=RpO3qdq{HwkvEfJ(B4G!JlPiqqtCTT#x-N;~0!DLJyAf!@oSb0aBlzJx
zMJzbBv|^@6zm6lqd!zR$*`HgfVWxOIsgI}7)g?J$6HfljZ`$#n+<^MOswcbu;998~
zePO61*G5~!)#TqUbxXG!+c=Gf{p_Yb-tJLo7%Aq=cQA<YQ{4|$_MbH$vzN=jj}sF;
zsxqgpg;+i}qhR?vVbBc*hH$)8X;Z8b+l9AHd3fKQYRdVcTYY~#V<xVxrHL82$jf1~
z8Fx<~FF9V9eaV<h8*_Shw!sJUWsRFhBa@wSox}Sh<oio`?|Wk06{^eI%8(Z%vk&5U
z458bWe%2MrK8joPLUy)YH7+pYDig%gGSQ8z8>Aw9(4CE<@XWb+ga&qlV*0+=ogP$@
zw}S(ML?SSfmfX0E=7-V9{=^jA8#+)hTFa5|@gzWL*pMv1Y5T1c8WX+dSPsbtmU%0a
z_qmOn1ZyG=;LWlB;QT_kmgDad=w|dUoW8c0{y~Me__zb{?=2rlY1gBL{|l{<{j=>P
zaJvicqkyPKW8_>J6xDbp+4+A@2t0v5;rmkO{@q;E$g;W3&0pJxuu08DQK30>R2XUw
z+$9$C*QZeQ_;C@|fHV^4Lwa%ADi2G8L3<o`Bvn3Ux181Nk^Hp1`F3=|Vd{!>%78Kc
z%A%*Tw7YO%|6%aZ3$a$kK5EFrM4R|eFt!VKmW6)S-e=oLYhmDx!P(2OsMceIPLS%g
z(kZmVt>cZHS;%MsKg(y-#WAmYNuk5@1NJ!SZ{skP%@Ba@4WjR4V|<6ZZuhAT)rLX#
z^P~>@Jh2hw`Rz2|?Ys-U3qO78^kBTB2Y%S|2U%l+dbj)?1BcNCiKN2#e{lZo9M+6p
z*9KXD93ZR#?~$U1wX4$~n!2Zy%UjE)X4Eq;{I%SWJN8Oi{CVe*=itGVRw-B3QOQWw
zS7%J2=^^^SgrF|!MR3hw-PlZlyUWM<Yr>0n!}(YI*vwT~c?6=p7RT5~!sV_?_r=3I
zthRp2I6Ti}zOf$1@_Au|s+pvXtrHDH$w79UnKOTXUEX@7&so;y<2URJQ510o3p`|m
z&&seGN4|r_8#IN8Iw=GqMgZ~RT(;pxMkMzsM+5HRUfJ&RPqB%1SeyoROlew;JKlOM
zXkgJrlT3Aob)2{Vx5~@aT}fL~EeY9c5Yu9%j~g+-FTkCvdv(OEr=Eq}ZgbZe7LP1(
zY(o14=nhC4QPXs!V?D%+nfoGV8IlwW%Cr3%;X@Taj^m-_eww0LKM+@r=&$?Q8`5p!
zhYDijl}TuQVS06B4?;7HKQRhEgGKqm9M2`~?s-gi8G~+?U7_#HmWQ#jbtSr*bM);|
z>dT4Ogu;q7-+k3A$b$;IZ01-jjDpPfrOG<!L=hN|qCCU@w6xz8DSJrEqZ2lSBi8|e
zG(UqH=yPoPZK#5x9JtDRbH4B*BD}6Gx1m#$wDZ&uM(Pjct8k!)=u<e<Vp~RzLOVUK
zkev7P{rh{YZrsWJA1agR1Ta02k5uCLlzZGk0aiEtMKsaqzD2ui>#~!Ccd|6c+MyIf
zDCdTAW(ATFmB<yYh7Dh&r-&%;*91ZFwu`dHm;_4_e`j@Hc$cw=zN1H9R*&x-*I5jC
z!{kW?OdSj6Us&$FUT@>&5%$Mx4pc7=XaP@w0JdAEgYn$e<N2OoRm7DMl3q)F?|XNn
z8&Y%24pQiAwGGb7^RhEp4QHRJziwKiQ$)U*V&Rtys(^gOUbi=GI0R_3xn>3%ljSt;
zvG63X*6X@9c)&L0w#Kmz#}GC&r{e1NJ8~h+ftK6K(AUr??JL<DJJtr1;r*Jw!O-lK
z&g-}CPcEU=2F8RMg4MR6T`B)`o5QC8Z5Xg{^@1qB14yI`&sW?*>LJlFO#RU7E0bo>
zYgB?u>v?<oHvBqtA>pfv%LmR_&pHxl-r<o}dwV)l1WtZZ7K)kwNb`Y8Kn1!Q`N@q#
z=emcV2P-pYh))IU7U8aP5PWICq*3~#t)yI?VaP-bCS(d=4A82`=%oLJYnt|k9aIr^
zV2$h_B4_T9El+g$&AtKF4Qb?|eb%YcRMM2(4yF145)i3eCUnNnHj9E>J(OJM%DI+m
zZ>Ebg3Xn05&ulcuaH^sVi}L7_@^Tq4m=n``#}DavxXB+8S91;@#xj*YBZeo-icI@x
zf$A@GUO1U1@p|DbYJX8z=No!@Yl%%a@9~RNDpvm?9RzcatTzfF{RK9-@nRJJv$tp`
zd>@=9u55pDx^9^h)z>!7(WBj8$)?srNPy;8?TMyt(M1Ya_CIgsS{2chUk=A!%$(sf
z_9Ijdd%Z1<`~J8crHbHB49|f#vG5!_;yKg!C+?%Ma8pw5z6RP51Q^D0fUs1X^P`yj
zeM%4vd@J;|N6AwMdXMno{<$H;feP!`oti@Xcz#e!R5>E>+KS~$eG%{#XrZWs=A!I}
zF}1FItN$ZnZz;ydUBs&|74>jm8!bauM&ibYeq($a%xC!9C9X)WLG>c%Q|q|U?oP-s
zr$(k4{v__S1)9ew0qw6&E@%`Ns7sxlf@TZUP-6dPy_GX)hfpS@tvB&5qdOi6fab+M
z_5(r<*d};fa^zgL_{3%!b|)2|e+qmkU9vTSX<RGbRydEnZV62IRAV298Vq_qcP~wb
zCbi#ES8uTMl6wDDP5UVgDg8i96Id?nZgBm3c71<obc8u#UEru<8vPSzZpYY%CYR6N
zfE?Y}|KNO|mzd!CM?W?tPQ;3zKhC0v{2zH|xzJV@Ze66srBK|p6ao|r#kIJ*QyhW^
zcbDRB!CiwC*W$sUxVux_rF~D%-|rI6_ahgulf8G=TF;zgpz1U2p^8RT6gp)j2c*S(
zPK{UTmL5Nk_7Z-2A)^#SxO-9MVh?leyDJS)cAaac9eKeB_*$;&x*3KQN&S`YFil$X
zW%gs<XLasSF}#lbIl-5OND8plZ9*x{Cu*)2NbMdf$zgeT@b(-d0+1J33<x(!4wzGq
z<xtyRk5;w~C&3J71Y9AgOi9wBERslG|C%P(XSeahDQ1vWP}@uSi$yYFrO1D``XTFz
z8^2{4NorMuv=8}fl!$XnOw6O#Mo{AcE##z}E9bK4lN3I)@Qb`Z9eihAPH=Fh#K#2X
z!||~SqR!9AAA<}MokaWMc%91<m^|=ci3K#3*Qrz%xG2K~odk#!xqMYio@TSCY4sTK
z+}fpr1UY+D&4)c)*EqVX{YRoh@wv9r@veg%Yp29D=%Stc3A61j>niheC9d?uuE{o>
zANY@LNR2umh%{7PFB&<f@N@RyPzmI~frm-L*-1f~iwd8=cAa@n0`s}WWp)#H!{+|v
zUm1Aq=IMU$=EZtLAElL6a@bpOu6nX6ganJb|86IRqN(1<UK+hWOnZ2U=Z1;$qViRH
zs!)ZO)^J#67obAvYSpe$%J2dkp>4g-KZF4?{oI1E`uk~msEZOs9QR1CWxO(=;;Q9c
zzHjWmX0_!ga)F=wchA0uU2}%&8MbgU*JOUFPhJ^EP#zozImjWJQ;YZG`*3Mdk$L~b
zCq-+TYvcAJzI>IjTv)A=H<=VbbR;gvN2l^hm%6^{gV-wWY^5Jv`o7Pg1&paoa4Ac<
z)6r6UI|6vx@zY5U;qKhnp+fKHCg+svC@`B1y{HAqz$bKV+(?33J}gV#V60Ilxxe*o
z^6v#;0gC3pCFD*i1)3Q%$m!`QgytY{3B!fI<cw=HNA5mWRWT2suZhA+&fNM%%Ip4n
zIXDZcacW}78j?3-wO$xL^F6Yt(ORm40dA7J<ier@SjI3X4`XiS1;Q9Up-Sa6gMM|Z
z#V^@lz`WL9B}B#q<cq~dE*Xd&bFN%|C$9YTDD_wi@OZ^BD+_#nqWgRynr7C@BaGbV
z$rr+dO0HYE7i&#8w^fVsyH_M__=(p;PhTjmGtx2lthHPHDrG%ktb@U<l|MViBirkk
zd;M1L_9PmYE65jFe@?j}(#jJ4=XP}2{Nr0GA!R1T^&DX~8`6n$wUd<@ICxT)jfQdr
z4nk^K6tP;(@r~6CT#c8(V8(&1cwg91=TaU|%4MpF6(yo@uBQ6_UJSk~Kqf7|DoS-f
z5kmtByv{X<!@HNNDA*(q#myX8YHI{$85HIO2&v}66~i|4NI_V>YSDsjrN}%8pBbWa
zHKOB)yOo=<AriDr>cRgzK&)4jBEb4w6piqI{R5cjp*P+fb!IDQO4g+_Yz$+-xLcLH
z8!1`neGWVENjpwfFcLVlG_HvT>t%Fkm)ho8PGy5Bte;l7M05QOE246%s`JIwHrP51
zMjz57i9{UsVzuR?8H@Mo*dP)fc=wevO}66uI^XxG|196fgqqPacT#_@74a5BNwG6i
zI{z~C(vv_nPAM;o_z%HLG+b@5ORoBi8*s|4z&uSV1}J}$D+1|HRl15)(Wi`?Gz=cy
z5BbXc;4#AYCv*2=BPg*prSU7vj`5fFt8{*5%WGC36<S<u#~%pfQ3xsg0beev3W6AD
zgPncmaKs*f^G{!US2N-qEr}W#J`6frnC3$|g0CVRi0(_T(e>`mGxbbG-5ZDfS(1^b
zyMR0`FDo6b^QH~$F@Fsddj0MXyNPw17rT^9l0_dB)(3y_B<2X}knh%EpXjr_e9HE6
z#B0A9L3P@D*2eE#Yqv4lwWm`1QSK}_9nrB+9?@kpdxmihC{Hzf>oW+QJ}@5Nb0Al|
zR*9ILtVy3$BH6;K7)UySJll8Xq<fezvAVeG5bJbC=`zep<67_$T&P>OKLL6JaIaC)
z9@4pu48M$W@q~MPoe31Ui^CmQwT@)NuFZ0!lW=iyk$YJR^<y%UJ{!avCtfWIJHQ@l
z8$qq5uA^A`-TR^7W6Ju1{t$|H?blr)efv$a#P83+Go*AD2|~eh@Q%Lsg%@&r9otj+
zZUxQU>e%KBzU=efTH9Y&N#wzrE<x`)+Z4SMr`ut@`tx~f!gFK9Cq0m9Sr=p<Y`Ctl
z_8K||+#!PG9_ChLkMmFH2p!DtiH5t$UE>a>8281Ds(bV!e>C}8svMiWd>8oRKLjij
zJ5K*1J<epI#;UgM0O0mg%a@NN``Q}6gHHj+&vQc`z2qi0n~J0pSp6D$U#`CkpNiQ0
z%2fOZS`P>`wyDn+yo?CMgZgosEb6DFw7nK-l5YEIdk%gf*MBN=CxY1S7(BX|ABu*9
zSx5sewmFv<TcVu&Dev<t-&eLpY${C@>?dtS>(uM^B^g=Zb*W3kp7g+KTzHTNT#~1{
zeto#xeJq<dQdRO1E07Pke?f5Mv~hk{AY}rMzz)F?C-f1PKhQ&1_T*551fju8AF*v3
z$?e0Z_g~)o@%|P9TYPaKIvxDB&F7S5u!NF9m%b;<Lml2jv&5*A1I=w@_v@9kJ~2wq
zzG5FkkFgcVY31At7jNknl%Fg5-85o9YvmRt5s`SSbDG9i8&2i9`z5j^Zs)nE>BHCw
z5ux?>D>y0PdK&dfN2c>vcZ^X(hu80x=k!zAgtO=u?!lK-GOHxkR=hEDOBQ3`)E3l>
zDY8q(q425b{NDl#oXO>qg?h?-95&&E@1--K?UOuEWUH=}p=EQp$A8CH2fp$Q?qas4
z?7q*fYTmcS*<)r5#9E5>`_`c(qpy$+V%wKP5Zr}FyTDhSFzs0-oP?UeY8RAccG$ZF
zX<<+`XYslXDGWIMl=t$g^t<F&eS1__Lt9NW3Em&jKm5h-##aZ;cQrk(`ywd(D4CP%
zRt0&Rm_NqW#VLAm;)AQ)Y3^wL0=U($QBsN%?$(xzMK?C455%Y__a>>;TIZSCT7Em8
z|9Qk$#+fj`spCz|lZzKWgAv}p`-LaOYWab;poaQjYF5)<MZUxIs&QG4cM=Hwe%bQT
zPFuZn;zB`Ybl~uPB#p;iNs?|}+Vay1kHr!@xt#7d>|Q*#S_#Q!?oKE1l-2gt#s(t5
zA8*`?-DE}g&s^`_G~W2G?FGDk2`JW~8x5F@B5(LCwY>?<`3V<1+42%={~TqSxM`r~
ztj&8l)9l7}C^aaNm&P9a<%Vl&gpn6sl92QE<*IYgn5FsE0-F-r@D3oi9xvctCBkrJ
zRlOsa7Nf4a^8G@N6h1KbS1CC;D>(tLMQomu<^~NPGBMo)Z@&*xs_$tn)$Zr%a8|br
zZuJNE_P(7cL+W|rzXaeglRlm0+d@7Mj85}Bvn3{P;6g3O&AC}5yQBEa8LT}#_O-I;
z5IfY7@Q|vut*TA%fh>KyNl7qC$Xxs`c|Vb#lxqUqq8eV!uOs}~8JBWMsW(ME?!$YF
z!JHdZl%LC<!*<$&gLr@QPCSQ|xlm-wHbKNmQV%~&x!0&W8LWl;0h(jnk;tf}GIZE0
zl&|Wq8fmVY@5Dt})Z6%wA!}Ec;rHJOzmJ2;=!oMyIbD?(guYfk*{R98+i8cjeqP?5
z=^s{Wf&j68=a99V+GUZ(ya$}kEQ}hJYKbT1>&w<yX|xHMw~tn+x678gJhg#aMK7+H
zX<O#l>1mAC`@ky}N@Ia6vqoe$n#4#`dgk}y5GdmvZ?cft+_?Ln4ckNlnufFy7>TIY
z6+oGsBM6;I3|63)@~p|4;VN@P@<@Bu+AN3M+*wmG#7GfADfKPNK6@fsD16;0u&b>M
zbICPw7+0CaAXoqJuexB1j7{I_85KHQt=|6bGmxPLglU;^$goGrjNQc<#F=tm!B!_5
zOAn6!*VMRKSEj^?x6b<QEhbh=99Ky5=+FpGZV>@KcLWdw#nG9FVW>2VIv(_mkR02-
zv521}l*(Tfv-^-u*<&$9rOd<+7cw0lwklO2-nv4@+L~>a(?-8LE~usr>o7G78(?w0
z|2mqQM{uhy<Mdf5xo1$j1<7k9EfrZGo2!rHS<cYnuWfS|iNj=wzby#(`FteGo2g}e
zkz1*r(y405t^*LqwR*@sVm=rh(5z-o<tl)L7ca*2sf;W~usxbfV7pYl)noR<H$mTP
z<;(ivpUk~Nnm<mcDTPnF7v_bL_Hk`v3ERlMkmnab1Pa&^+nh*WQK?cp^bM454822?
zm&@2Q3y>Z$V;>0O9Fz9&ttrteT@|I9I{bPAi<QVj-%t-swN^KG>9bM`?$5N$AiG@B
zZ*{f&P&?91%jG%n91dUE`xwNsO!1Be?w_96(Z05;LgHa$YH^V+Ar%{l4m8IyF3lL>
z?eBv}DZ@Xhn;EW`{>kr(3km!QR;!m4(?oS@pTw?@tCDl_iNd_-o8Hsg+&ct1%mRa2
zb~;J>YECXNJFO2$&vlxfsHEKCFYEYR=0|<P{@UXu7J+?tg8oAb?lAk>UGdr?J#zuG
zN4R-Om@o!C&?{aTx740ojtn6@6xVPGsGSouIPZ{TKIIHYoHr(sw(t#jh%~dUIR7(f
z0dE%1ZBK3@1F&3hZBL?`5YhdqrB7X>%L%KMovZw>^##Jj(MVy<+714Vc=|(|jKva*
z6dZcQSc1DbN2sJF>5}np(LrO}r*@wt&6!j(Je_>X#=G`JbM+vB8H5_FM+eh8Iz+TZ
z!cC>YLPw?e+~%ke4;AfGs6Z2=#umFMPRf2M+HK2*j*bmf`B&hKw}D@Ib>v7bMIrbW
zYhfG^#ro46@{Q!AlP)djzVe(Qo|=nj>`|Mts^+WhhbU7iKM&*k{-HfK<M(LB{Ka?9
z;?Ow3ArDXJ&qJnYbz#0YX5Dl+vu5gSLHy6>WRgps#}LhNu6siL)4k~)2Im~ayUIGo
zY^7xWAY3A6&6#H8c*yvlN1S4&!ztT0pOoQ3p<((qM=5(dJSlfarr0o(Za~fr*WeLd
z5lDEvy_n$Pw*8i*+I@<zOo1-MgTVAGx{4lih~`qgh#2kSfL+~YW>^^!nUHc_W7v~+
zgNpm+p_&#?OWY6=u!}e><ydTLIQV`m7Sf2n9WTctU(mn@oBa`ltwBpfg1mHFMxg4W
z3d5F%rpy+Yy+sO94=#ACi;s}1o#^P0OpB)B)1M29!|!MraF*>`>|r@K2Q_;jqS}wJ
z_^+Y|+It~Dn4gdK;zv>pMS@gs-uxZ5A;YE!29_JiwjgoTQtnA3xU^3fi1==7mVJMU
zobnfj5}Lzvb58k65t@v8mzKs6jC6oQ#dfyym1jtQL&RDn^_6e)b5z<7rdHcTuJgCK
zwq%ut>dzPB5j2`h+$QH3xIHXY_!EdEgscU(7IAViEdEle$#M)XLzy{?*?r**NVZ`!
z&kn=R{-FNP*idW+7g9!K3UkV{5{I&tw11aS@QV^GiG6Xb81GhlVPHJAbWBKPj__!y
z_zMWGZJTGMlPj@vba5HjTK%a&XwT7i2W<DGoI>iOx>>o5E(8`v2+#g~I3lf+h`pO{
z8jEd2>)QGxN&VP=tyXe8q51V_$lVxefwd`tK>8&%z@a3nz8bri;zdX1+M!DnY-%Tx
zU}vA~#F&RbOs!^=H+gf5u6zN@%8FEk_#saw;;dAyJa=e~$fUNv#aYs>xAR2s$$mF|
z(pC(PaR&-LN=t?g3r7F=O0~eLjYrJ?SVCWTsX?Hj1PIl9r}rORJ)_CQb6$W2A)Kd5
z9i}y3S4Z+^ejX`9gdljCu2al94uc_%oAaHncLkEc(*&K${3RGNrOIu9=yYVdRkTUr
zmilK~UNpW>*}o{U5oA9`r_()5w<Cxe+tw%bjR1>Ut4uM>RsBK13}huqvI@1Tf44VS
z{zS^#gu|9S9|e^GgeB5W9V|m}rv~kE2sc}`@Ro9V&qm2F(UqTd9U?4h>{%?-%;mw;
zZ+HBJ@-HLIc0ar&M=@6`P^S3bP7OaIEAL|dm~R-YJk8%xg`Uq=N?4-jh1)i1D3Fp<
zX8c{PZ(ZVt6WCSeHT7t1#OZrnaQOG=nxr<mCo5vcm-h-Et9~lZZug*5L!}2W6U81%
z+hQ8l+Fq;Ms3nz?XDt{Ufa<H;{e9PMI1BFXn&x97KH84>iddt{h|=oil-PRpVc<{v
z!rbcJ6E0sTNjEOF3oLG;7-b4BwI2|F8hA%zVjVT}==E2RUC$=%f;iN&ymyP@LFOjt
z4}FKls%&gs@?FR|8vmv+9VJ}6`FN5PD4=n%*hZ?T8z*|aGX!Pf>z?Y}LpmSjaJP(L
zWl}a1CqcgE&8F+)bQ2^4w3H*HP}57BvGz{v^Uf6>%dwtKal)XZ#|f`t+rJ&zPZI%Z
zGL+oIw&+lObPqoMdnhfHnrtmh$eiaXZzd!K_Q_vU{n^9?6n~1V>|fdJf(fedPuP#3
z9P_vR$lR9gt;p@8wZ_b<=V^%7*(~Skjqq&xg8~ehPGW1tQ`MJUKcAF)K>y}<sU<AS
zS246+@Pd(Xo)QlDMZZ~C_O9hYN<PD5<!;gjRs@2f$m#WTEs%TXz`_H3Tn##0R37YG
z)5q5+?J(l)DxFCkO4*v1(-&fxu918eH#Qm>8`3DM^NI@R>eTsTU4~IE!WMJ?d}N?a
zIfU0b4_s1wQm3R9vb3#7hXo;ZC^f%Ukw_U#(DsC}zjs9$QBKYL3+;AcAnY=80UNoU
z46ES_lCSJaZIS1|Rbnk^<xZP|qK~et1qte7B@Sfyiu09RM6d9(LQPsT2AH?uQ7L1;
zccQm-qRMyqpExRXg<11=gboH~iqiF+Kii3U)kheoH>KBFQs67@#!B%ABl%N3bJUB@
zl;_0)KdSQC#(T`q*GGuc`m4DhQ4cA4-gWP|Sfuyg<I>-66IQUL(VGpIdZYZgjlGUu
z_GDH**!N4B7FzJ6=Z8@>o9)c%2!6OeWy$v6QzCd5!hBuTiBNE>wvfpb!Ffx|bfzf1
znPh2;B!8?otin`kJ8F$RPA{D;{|F2QRZ8PdV}6{L-)QQJmr>0kr3A!RgHGus7UgIY
z%w^>+<I}v^KRQh;zbr~l-hySRef-9gE{**vT{(ao>Ru~+CO+1suD77+cY}q`=-ZHA
z@8ZaI0xnAhb^|$B_OCegHPqw7Njd1h?FT2tngavqQxZ{uT1z&2&-2yJiNolkX-;F>
z!*N}~Ryb4QRB0}Jmq2eUA|e+>joSH9YW<_3Kgsp+o1eHo!U*q(2aHI0wy=f-v#?qb
zWOvo#N}@OOh_hUIWi((Vv!CkI=;!ga6JyUUs}=3HW9aV)XWlgP_}$L}8IH^n2i@v~
zk`G|xqeHGr4C~?$b*`~NBs6#cjRW_-q&a2cA6agM0m+by{U5ZrPc|LwcJgcEZ3%Xt
z_53GwqSpfXNviFf>O*H6D+y_n89ouMN=tJ?e0xw_q-fNu*C8Ms55~^lgeIf}H`R&Z
z_1;5<x50`ZBVHEVqcX@r@K_3d8L{(TEZJngvZ<@YxLS-#TK=C=k)5fX93AFe>llrB
zZBqvdMdJ77$968*LTeJndKA}FxBm#I3=M^ra2q%Z_EL=FSW?2g<r=i?2b`afI=*0f
zc>|$ptmFV{b&Z!rK6|9WE5MQnWj@yODrTYkN8^sSNqVg4i+-8hR$5_fl7D!|J*xPI
z8{Fn~<NpX-3%sc1ukPX)JJ5~dJ;w^_-|V!<^&5U!5#0jbZ>J1>*U@>cfhI^AwH&Mv
z)xf~99#vmGu4U{142U_QL8ux!x0>#5?J4qY3Nq+|wD6jJIdR1wugUxY<hrwr)$}GL
zhFXuoxRIl7m+v3^P(eE<?}vWKZi~MTvC2KrZ`La8PUCx-tEaD?99qGHgt_E-%~885
zr0Y*1AF+;+K72(02xR{_a#;8f6xJ|gEAEs&5%p;^Qb-eGIh97E^}$TaxM!hJ$hYWJ
z#5gTjwuE&X?*eoFh#o4@`-M`hT6-3kZ9a$u2eE20_df(l{Xq<3d=L6~J9b$yGci7)
zC9&(`5K>o_P?_}SSdS}<gk8swpQ%O{O7S2(*Z6<;<TMQX(F+Sr3b{O$sk~^<KM1oa
zFjQKh3T6P3USuJROF!<NYT_1!^t3fFcF@8EB^_vQ%P~B`9&&OgtoMhGqs!N02b?gK
z;)A#bXu@-7jYEWMK+_iBrpiTaoIlY%1jvM@_ZrU6I3Do`Cn^blTJx`Osjl<5M{53-
zwNQ?@8R_4uQZroAQf_!@Jn0mGbfQ@7Jx~-~6Z8k>ptK=u_5DBK1v7&V|EfZ^;C%f*
zMR5K+C=0RtyIhZIW^cLvTZ3cO<?WapR2SFuwI_|N?0A`rnfe^V*CjOxslPOi<Y7^}
z&Sj@Cfz?}(!}ecx*^oJX7ys&HCsZ2&`nngSvS*O2Ko}R5=b?!?J-L}IN#ETOf~Hm4
zr!5Sa_(x~=na4W%^8<>Y&o*SGb6!ZHnkU6TPn<G3KXG(jC-bRM_3Ki^oT^zJu}!>q
z$ryh%-(&r5b3K8k_O*fZuTGB_Jnfwyt;~(rJiMR8@_E583!UVHO{u&xe5jOFlM8pe
zSMP2H<l-f;7KJkK#?~Uorxo35^^+a4Mozyt(shJ6{&)!iz#B}M;T};CM*gEx<5@)w
z2{Oq}%F~U5jV8N>Y^u#>h|y?!hPOLjESkfD!HMRhg(G|k-Kryd<0vK(zhG3WQ}|As
zD{eECunYsXn#L|Y%ME{}e;9szACG`MKNlV5*rg>{z)Bt^r&^^K;Z^Od5O8(w5zhmY
z@UH3O#kCKXpLL>X;D<qhf&jz-L7hBshByhON??CY3U(WYA?{*Bj6gzaZu^Nu@*p@x
zy?6Q5!opM&-xlb^rP@yV2vpxBHMab_<{%6M9{U(amiy=G6>6s-^Fs?GQ+pEzI>cI0
z4zkeA+x7!lj(d^er2HS1{Rq`3$}pk3I(fVUZG<zqc)s!vpZA1WBDksMyKdi3eAS(8
zNCuK^dH105QXGGo5soALt0)z%MiUAu&G~E-R7o36V;?ILe~;>0kK6AF2N&|WE<p^;
z=gpT0G6%;vr)*VMJl-Qd;^k<KqiJ8fChF1$G%H)(n5u1cJ03qoph@=3PEHfb8KyW2
zORxS$lIv>Wlbvs<*nCy*)K*X+jDRC`*w}H<-&iIy46o!a;PV~?k6mc+*hcA~OM32O
z`yT<^QWaBI3P6hvhU|$#Rou@2U}jL(o>PAV{7gFPLNYc{90}UbG5Qo;jbX;u@OMwA
zm;`|;xN1;fkI{UuoIn;eIqpOezSNrHFZDp#S_}fTkHO93i9T-CdK2!-_PY`9ndR(X
zAk|FDX;#YIFIswtG(OQ&l2V|E<LNR^tq<Y$=7iwhH`}mwx#?Eh!J<(<q!P;sJ$@h&
z7vlc)Vu^(O`8mV}<ISuzrVS=<A9f)!FTG}vcSl3Y^5G~xqL_mBqO8V{_FOCaR-s}v
z$1#TVOe=bOK0+FyoI38CvdV0tuBKTek024kmH$a(jyj@TklP!xPiU~*JXW-@Ff*1a
z7{*iM!rXr0UCIaRM#jmNLcPfOEz4IRafB4)kHd@(69(a+GDX{v&e$C78^+`Mtc*^R
z*7(zcN$#NF-v9M8!a`y4ino`SVnSv?$^u$H_$OKNymu37-=jY^<_T9IImRS{Wp&d^
zr%8pGYo6&ck@CDtoxY1JqS95{5*PI^>~Gv6&dfKIn0uA$C#W=d?U~(R`9*tAKLdA{
zT2T(2IB(nHT~?q@_-FXGIui<S1<3_eT)4m>7Zu~CXttAM%WkPVVboH$uRdNkynkTM
zy4plZ{~^%w-8c&z&329-!}AQtZSTQa4(L7QIh(M9j`-rm>LXws6xNVovj??sT`jR#
zEP>8{Ln5D`PWP@eoz0v!BfvslUy2)EV~owe#JIo2&G<K=J|b>>*pkry?GgV$*KK)K
zroVmLs_oe+`NGP>%zF<NYV%Y?+%-nbr;(#WVety!N=U6N;fcHX7$Wdu)qKZ<={!P=
z><k>nmezR0<@*CDm^t#Y{wTk~DzXDqvzVk@Eb4@|#KReoXLwfz2poG1OGb<XlTP_x
zY|i10OImXZYh=OTVUR4H#eqxvvHw~7)!?t=imw()YtKvRHFd!$M$;h|k789DT0eR(
zmA{BV1lSY``Ob#C|J60HXHx9@E(Q7xE&Sw8f!t2x(aVT<s~SXS;V^uVj{%ck-_+Ns
z&X(S?DvMkQK&}@YVo4tQ>a?yVA`A#AevR=170fJ}>E_KgD8dpEjv%)i5)!Sb2Q=2P
zOC_haBwzhPA-Dck!WomtGKBa%QldQ8-7F*MFd+74(!Emob?YK8E_a(53KYXy8A@z7
zvgC9`l^(nJE5AX`i?3FlapDSvr||gM2(0q(AAO8{I1D+yIU*`2#}{lQ`h#{;5-~rc
zd`~xNAavbh($ZY3;nz+=vdc0P$=>>5=gMP@TI`X7vk$#}2Rb!oPM%#ClYiCi8?cz`
z)Md4k)nnpmqsbbn%`Q8XC(;IaiE!ieI$c^cs1`|6GwA_~-Hz7|51px-?w?n&$Og06
zq@2v!Q}Hi()n+;<F^6mnN-Fbz2xppWAc<S~1D9CLU`4tz$M+KJWbYQj&SY%Gd}j}{
z=zh;@xCT$MgT*kw(w`?Oj}c0S_)Ju#eP)mlpCFvk9$U7Gs>onvwMmllqV2;JW_*^p
z3Ia{?5;)lv`Tulv@&Bo2et4**-c@|W1AR`KQvWI{fV)e$PF2)3up2gY3nP*h%RxK^
z$*rKnAv<xiUrDA*&6G$tmVm!1sIwxxYAR9oa&#y!M#)Q6z~-KZ2FcX??<idL$;#@g
z)~kVot=Oc-;;s=;CloJSwd-K-?OZl^->_zKT1Eb}c`M9kC_HA;+N-q?MV}+nsn-+A
zZ`mDm9qH*he?+lAZ$fboJ<G-4MbBcCJp8g{=n9#FP_y+4`&a#Dvb=%~fws?;O@+87
zoxmY}Ew627u;&wFXq}(t)!++j1N|uXSf^ii&eF8Jo~CR3UHo%wqAXkQ%Yv<7!aTb<
z<oYm<*GZUr(mEx5q;~jh=c3N8jP1|jZN)12Bxbk4S$x{qI8LvMqpw@#vV9FmOjJK$
zR%T-oD83OvQkEINv@`q*`edyYuYd_+YU&VL+fMo<P=8lfynRhr(?SP&*Yfix5xmkM
z{T~AIlg^|u{x$R{5^Da_*QS=nXj4zr>+51i`V-WbH-#<tph*YqSj(4sxH?z2WNMR|
zOl9|6S{R9zv2iqoaS->7{>`?h`O0|pVqtYltBn{rXM_tI{0nV!_iUK%;!~?pVLF^a
z_;iod-8dKk_<1#%ylyN5aO6WPPElT3w;uE9N#jlO=fNLKZgSM1uNAL3X8+XE-P#sg
z!8ry^KkQ7PwDq83=&?HoC??|%W>~?#8zL)TE%ieUhI|zD!*uYzg+ImhQGbCVxQWm&
z_(}UQOgi~m0}FdWrVJGR0y_Cm2K{9Dv0pIsycH{Y$0#3CzRR9`$GtP4#23Vj(LE4E
z8UY8v=9hBLUew>XuiXUl;=vRZlHcInnfTpI-T8%o?@w-*vv|%TBd(Y*CT~)V#jB1X
zbrE0kRxR6F+EB@puE=`Q;X}5V{UtZe`H%ALeGGWy%qRDBU7ow1QRnyFQbj~_22J1D
zKN&&Qgg;Q3I#1m2%!bTTp$nxL@NS}9Gp>WUKvQP!>+voq0Cx3S4)Ny>vOhdqQU7RW
zd4?Oc<GmI*%EZU!%Uy7|)#jXP7+={Aiif!U3aIYynffQcyaIaD)tc<%&$>ggC?L06
zNKfD{?{{Q*wHfr|DLy?q=B{&u7fI5IgGn^~6}^PbHTtM=jB&+DlJr;~?8ff%32a5M
z7x!C2G~4Q}#)jw}S%kX*b3io9d=&_vHHW<Bd7=mK_A%N|WSVhk-RF*2Lt6Riz@Y}$
zC#oeq$l&_>kO9={cTM_l6X}bDPT=9V0Q8P~6fFy{mB+GU&JrPzg#WH;YWd`ONt7oG
zJNE&)TZd~aATL9dS?!^N@H4pex|Yk8+|1?^#^{^KeFi-|9?at6f7bAG?(J(}d5!1$
z^Dn$d6Hcig-{SOVJOS%Z37QVnf3}?3Z{%<B0z^VryFGV)4Jy(3<IKrrdK3SqQ7tjy
zryTMg-2BkgHb-X1W`zpj884<nujTd9U-RX>IY{UroBenpm@f%(^~x2}@W2j>7&|qL
z#NYn>@9{vN_&)?pw_N!{gP6|oMfSBHIDCHraaUCN*GP}j5jWV{j4c6b?8=9*10(6?
zonI7ND-JQ=gZL?ivs8L{0TQ*|t#NO}WlsU;AC(v0h3{+Ll$z%G9(G&HK6w|)?40=;
zWQzk*-|w%BGZFTB1@0(A1EEbl401#p-dK$98g+h7f-Q?cRaQx6t-%~$se)94^SQl_
z<U$904mNVzoIZaYZ@WWj8~wz^d{jr_R%iH>n9;)(`Klm48`ctCf(~OBgUjL`(Z*^x
z`i2ovL$Iy3Qy5;5x9{^KORom0+&pehaa_ikCg7YNqd0tq<!C|~Q$v;h4fv$@$|&Vq
zh4D9>>EN8at|j{#Qcq?qT(CZta7U=I)SgpVLX|Dj<+qy|*#NKH`VTJ&PEI$%GMb$N
z0U54tmF>k6V)wwIWk0>&#_O1Wuat`qdq>RA<>KUFNoUm9LJB*_d560*h6V-Wa>z&o
zJ}*mOi4v;5w~Q-^fV}%wOW?ox!@0p8PUb@#c3N@g=#AC)&PgBXTr9AzWCNi~=tZn1
zpP})Yi0p#Ums*foR2@%eW-(0L7<EsNTw=S~U*?)guXEOoi|%K%m(_dH+@6ycoe6H0
zqmilY&!YXP@=+3lO=0S2!z^io!4|8{mIqqu^r+WWT*X9e64Bpsbq2ETw64D-)p8nu
zhUZg+XyLKN{}6@)h?{00fDO7+{u-;DJrZ*Nr`;|+F0^S!yMO_8kC?IB9G3i!30aY+
zQms{b%t?$X8Lr+X^eH_pPmC#lDk(EMzq)GeQ^TJ<`!3MaX8zR4bVq~5c9F)<)w=A~
zHe9E9R0~9}Ds8%@$P~PuxRUyLEY|_0yHerqz*scz_oxgD{MTd@U|r(azJFG*QU~dp
zqc*zbp7l1o5E-zM=K!DEr1?+?TuVFJx{v!P{#c8#W)ZL1gAI~G!>K#8w>;inT#`%m
zC*AuDr`+1?*Cylh6I4K^5h@=EZ-IL<Y;UuGk>e?4-P`D2m39IXNetXZ>+2GNP2oXr
zEG?16MqU}Z3Cb;4*$J17Yl*+~e|P?2Q}WfLvm?~K2~4V~jLZNyqm}_`7XMM(1>m;G
zl_v{kYx7M64m{~_@@os$%MCjNNNvQ8xo;hXS<sESHvV^U*xEN&_vB?u+<NXLRP1Jx
zOXz<VJ>Rs_^`*)Xq)|d#Urbpe!=sC1PmjZ2mMBiCWZ?0x6@lH0Dx|>t791_6A7P>i
zpm}52$B0ZW@VEOcKRUMX<6>;PBTtycBFr{vn&1xgmwYh$uFaC!KX()C(L-q&$~dcG
zhON_ab^t%U!wNf}@Q^-akMoAZwuxP@v1u_?l~{dwWQ)VtpE(2XS$61Q$7?rlN#vV1
z>fu98mUXf<KjV+R=wl?U%;%MDWGyG@6CbRX`QLp2q-7en!;<6$OKPvsytaxCWMNu-
z99)sKLXgcY(*((virvztxsV>uBRDKWf>8A{AIw%UJCm45`R4((3l0p*%V<Fp;9kyP
z(Li6SZ8Lhx!a$4?OeTD~|Fy6p5nsTpCKL<vbz@m1P3PR>bRUJ$*BWYRJ%ipaK)5XF
zSY~WwWH9)vgG6+&8QApW6K=A2bxPUO6X|z(c}G?_^{1nA>va@O@>%N~pwjcJ8?!9D
zBdzgf7)MGkj#b-mQ@`ozZaMOu?^44XU{Q#=u#c6*S0M_=Z><@j{yzlYQun^fq9!3H
z)%vcvi*&(PJt!PCXRr18dABQJJSn<|1F#stZ2O{J>DaJ_NnTHU;3f*+0=P_5v%DJF
zktG@-F0VCs^Q?@?u{8N}2rMSeC(_=m^Lp*JXFBb5TFMa&|K*-1Yf?#f#(~FY9c%_c
zrTbQj3hASF<;L=bvc}4MNL5np^zY}9WuZN$Q&MJo6TJ~^M5lL0R&(*t*{bnEqm$(4
z+G~?Mk7l=VpDXcp?^R&{q&=(l!Vfm(&plhkl`=!B|HACTVByeqDxf9%kr)%^x7gE5
zFDm#~P!rQJ?1uL>`Z)Ga4Uo1qt^s*3N83&*sSipiLFcdp8ojW?TS)b1DJGAXt!Mc6
zcqHG*a>I8AR5>hW)A!|4a1n*L=7I3J(<qJ>3$$r8D}~k~C!bUoLJqRjXjIgF7u26c
zXQ579pWj)`l51KXyPm1PclNc)B{5|o0HmFKTTJ;BV3=U*rp@)sFrl2_4(}Iyaf*AN
z4|nEb+sQfK_Ky5PA978Utp7VDqfJ<R#42`~3SOQs#M=m^Rz^S9T>U0~%Rz8<uD>dW
zv7adL0f2FMG$r~)o`ReVnC@jXRtyg%bHQ#up6GharKTK;vbo_2D15M_d5yN^MGWEP
zFG0A$*42p3LxpN|ILoc%ETGjnXY0n>lC&q{gd{emjEcsg@*`6mrlt++Cw~GYP0CQC
zqLk#h-RPK8Zk!e-cH)55Ouk(7R#KfE42;5)AU;1!64TaF67(C(K>z&4{t#RH&8d-;
z+3A?jvrcLt2FIFTL8ExGZHV3YUdSdg!zjV=&4mn72#*!3BCdLm#IxQd^hvGJtstQk
z34JlX%QLw$K_XMuFnf1((JpRnhBgm%j9PywYZ;FiT0sS0j4XC_D|&Jzi#5tfyv}GT
zZS8lrN(gySNlx(#7Omc{TD0ecBTc7049PDvbLKr_Yh+yhlLl<>u6J@+UKXVEVy9Z#
zdFQIbvA9QoZLMI#;rJgPd@u&{R_F)lqfnbg`2UTSY~LP(G!56#mTp_V{3^BH8lm(Q
z6@OB5@Jb2J3BA;w_%OoB;2T+3Q`F8_@yYd^CE25a;vSU%%9%wVRO>8qBBXWJ>1#7n
zLX<3+7mNs01$hSOC9buta)&N<(hF9nYqE?5LS<`Juw{3WqT5XGNy_kDwVW9^zHV+}
z1HB##6#JZ+vs=F^s?vdBDq|3Fo*&BG%IvP8>PW#iAH*sMo&9a!OsP=zFNRqPV&Oo!
zGESr%b%%$_kXUoLDTgk%Hx^Oc(4#z^+*wTIZbqdW;Va*{L<=@E)qIf23{w5ZSTsnv
z=?bjSnY5S~@qUPpA{qyAKcFdqpx0Ry6)D1!zLbX-m%pr`uZ&xJ%-!oPDi9eG;`^mh
zuIcaG$fpXFzIWEqzav!@eoPQ|6&~MniP3!`_UM<Htyw#1&F~v=JU}~xQHRS=WOQgA
z>Nc`cMJ5>$md7}RghSSc!Sk-s`?aT1#u&TIOyLRXWO~^F+|5eXpOSb|1PE5h@_YV6
z7&5YW$t|61_p(3;&I3R?y3;Z*?DNt{eA1Y%u?oK?foNls*o9dbe_;%Ks8IKr6;c!N
z>VxBvL1mcfeTlv}_p6_5dZV~5OoKMl0H7@OnI7C~vSy5Nv=!0>r*76b_tBfZwbM8~
z9=Qa!M-Ev1KH|D()s+&S*_0fxRCsY8K2>aZUf`We_G>P45e>s&g_<Vw9Di_N1pWU0
z=d#N>6u#YCJVn5&7ZLXPjTqNs+DBQ*NAsm=!T>Bp*7<I2@0nWA=cw5#GHyO}l9PBe
z#fRvfk2<)`a2|3rF62(Jul1zV(tr>WxG}*$!pF2(FKIdMX|AG2YQUT*1J+Cn%}l<O
z>zF&RWSM1B-J7lGXz_lhy-x<+79)uwrl^ix$mdq*SvwNDmYegUz^D$7*R`M$oIl2-
zy6@Vgj@~uY-}<)hKet$^Qm$kTJ`i}@=q4*t)CRCB5`~i|$hXbNHKqdOC<|H9li(bX
z@k~j&sIX{yCRZJ`@-?fiqf{B)FNmvz{36w>W$np3G=mATb!v-+Llez~g#xLGe^Mss
z+o1m3gI~y4zg7%Vebr$DxpujJl7E?>HR_Bt1)siGC@+ol%`G-Kd2DF03afms#|2K<
z8WY45bL*99#b0*oK|7>2gHS1l+y&Tf4EtKNpED|itJ7U_i6A~`JMW~}N%b(!_fTs4
z(e_Adryj*4ZX|hBNCkax^#?lYU-_AvnAN6m-~uz7`Q<3mbJ`P$;aT$*TV}^FnS<Dr
zQ_%a@yxx!J`f@#C8S1}v@|xDF^~jKf>JlHTCjG_}GOg-FiVp|sbD$u!l3G9}ObWA;
zJHc{D@<9#rI{g9aGT<TD%=O~l)H<CMAv!d#WmsaeK840o*$T{}i(A*q(rx5?mvft<
z#&Yp2@dk@stW4MDxsPop5weD=Jm{&$ouU%5st*40Zn&>%8z*Y1Lb*7K_tn^xmTMhW
zzMezLVmOYe=k;-W(QLU{MZ2+J*&38R(Y@&@YJehlT}Aehp6A)h25U^qPep)HUn<jJ
z#xi`>)qEy6J`aSG0v<j%L;oRgYIFTXIEPFnUkT;P-VG^UVrfqq9{kvLudz;SF-STY
zG6d;1#SvI~yUr)*`}bd{%8bMB*|~Ff!Af;mR!3tYYiA7u2dt!Xy%f9PTjsLu-HUHo
z5{rilpaJ?1r(VFNzH55JkdO9t4YGTc=US``O|hSC=tb4E9c%yS)03?QsgNL(K%bx0
zP%MWVeQVwxSv!Nz^=_Rs8mZ$z12##1Bl&DnJp3XH{aanC9eS1|!b*mTJH6+6NwPER
z%*p}H-~+~BAx&lGWxR$mDT=|%EOX>M-}w|J0`APN?f($Y5#e@~mTSFgILYXBU)%SL
z*G743%j8OmNwV$2aad@|HN0$H<$V#S)zoIQ@qk+TCFe6Zc%CfeWpR5%e1Q3gq^y2y
zx9zwY2vKSXD5^uX>br~w>$O~q+ZN_3P>&`1%frRi2Z@0{?O0Ov(}Q#t>h@X9<LZkV
zCYCjBZWWt1JiU6;HO-vmMu$|qZP}tt1X0c=?MMv70O)x-w7wKzZK!0g!al%*#;qcS
zJ`I@^`U?l-e5N1k(fSn$P1%#fbka?NJ2llzfwKHNQTxi#A8nGPN0TJu4BWwSN`c?3
z=TKvBde!#n``SqPE73^%yMuT%+HC5tnNRQopg^K;Zq#_229mfJjooOEb<!6(>g(Fp
zUB~*jb{-+$*9VVkY+s`ntMqpsd49G(3hBf>S$~VB<ag%>w(q9RdFwJ@Ae==n&I+lR
z`b<(4?~?!O(jp|Mu#UYpuz7ed=m_#txjOGDEbcl%0L@rCQzVr7t&eoR72zBYFH*wb
z&$e%1QJjEE!ztsFknC&qk&=IL%HY=o{BZSwG?I6Zz;GEWqYJyIz=8BU^^L6D(br-j
zf0q08{<VD<Lb=}2S||AhN1nIg_)hM0wzU(Zci_K`ZgaAAdD*_&=Iut(qF(&dCyE;p
zqc55%?^``kFQO}erA=)jhM%7t<;o{bc<ou~yOVS#m^u+pjE2HfJ<{9MVjpYim9B%6
zchq*`87Zv09pk($f}FDCzm6xZmX26#(kLiodtkNu=Sq3U3?|9$NFt!08K;>CT7nOq
zvdEvD?c%P5Fuufyadr7`4L2laWniz@`;U_9yfzEhWPDsl+kKyvAR1>~!CxCXpxvtC
zlOjpNd7Cbz>ByjK^i?aK=0>j*!Iz_a&3F>?!k6?02h9;s-@V9I1MN-fGviY;?0kw?
z1nJ8e(uF>H{2m48N~dvmc{^()bZk^t)H`M5ETw#jrrOhrCb#}ONA+ga{Y7!U;8jQg
z03SxU|DF>QP~jertYxlF=GM&Hu~us=ywphzII(j^p7zmgNM`2nc;s1Xi(lkTm%OPn
zKa-0i_0;iL{F>)JzN2#p-%W6O?+PAxHm3`Vh-fwp@7>ible)ucg+jjzBUsNL`Rl|<
zZqhWuU`UA*aUS1({$8g+Bg8?d%XY_9k~q`M`?ETxwidCr+MU14TXQ|g_N`B7pq27$
z`e2^n^-FS}9ym61Qo)09491c4hg?Ms#<N=^^Dd#(Ey*izsu7f?eA%r#yS!d9Ec!_@
zK9)F|J<D)3tB!DZFEr-`V!iSy<Dv{+dWaTVyIP@GEYg+4sQI}bf-v%Kp09|(Y7La(
z%q(J`^p~pfAlfoJJX!K$=$F8jzdR8mW)+i}lHQzoLx&?Jt}q-y(DZ{}59?}}w9q_X
z@me{7oB0lAyl_ly`cwBmgn+8vK=g`QA*OPpa!3U|@?k%P=CY>@>ANzf0fgRI^>x|U
zzL2yBAk@EPb>+*2M(~#K*(d)_XFfPP3Hh7+m<+)#D#>mE<u4)iD9+$cU_K4ePUa_R
zZrM{z3kofhv)FxVC~an|J+5uDyrRb!ad+WP_E7_yQ-N#a(4B58%xwQ42WMv&?>ZjI
zv?;ritAA<0ja4~{GYl*z%GK7Qb)(D#1>?~9*`(E?)|innnYI?b(IX(&{h3h#lf2~g
zjspDX3qyi?H8}D+6wappej@kSUVv~{kwD1&X3M*qh)zQO6JZ)kd>Syk|C<^m-|eeG
z>uWO?8Q+;b`quJ%pLiSg-?<!3=eid;68=g3HYC2rgv<xREJ<j=S5H$<%IYQ5Zg=Mj
z-33%~X#n6`6X%+D!kdiH;#lxf>|#Z_itTcuc2V2_{7VsG&|hmcghA}FC|%f!J@=j#
z>6}mf&kC2Et5D0&46hKtm%8_)HKC8XFzGYx-r>ty+a_~PQQIt8hR59+i7~FS?EDS0
z64%!r?@6t#wzLA2hG!N1s(sG;YV15IEvwa|QY?&*pLO<v7pq&)UKX+on_uqFwe&iC
z7ws)v%&)76&C}@W+Ip)zkvSn_QdmDORNH|9RMNJo*zk@1qW84Ctoebe_oNQnt!6Us
zu0P8s(xP38TOw6X)mENeW%RqUWFPlRbMky!T>gSt3mhAgxM^`EdZZj>!CChb#MSuJ
z?#gziGcgPfRG#+T>?d`2y%qj=savJ`s&Y(IXf!|+_h$rfq?rr33xC5d63q337PS*5
zOcr}onmu6VOl@sv3iGqp5YaSM_)FGD!!_?HT2<HvNn#^T+TY(+JfvJ`Uhil&w-@9d
zdtrW~1M!+0WMdo9|F+d>Ttas8rcnb8uhay${oTCZd(8Oa>OAG|&6J|9rU&;)`pyYZ
z!4*fk9|UE(urQ+bR=taQb?1~fBq)**ow0p<3zGY}1Z(Xk+}6AgyJCkvn#wZ5-NeQj
z@3xmqBpG{$>>d=i2Ek-+$QhKbo9zn}ICk~d@94*^&BX8i*kv>~`F56sa3;f;PBu%W
z|CIazdAZ8?tEfxB@MK1X?H0~w$$h0l*gfLQ+Dq&LaY4GO+1E4Ikn91SI*;%YhDOJe
zIbfX<*8a$Sv)8IMg-M7=+Tr7r{;A@X>&RoB`l2*J2p>JDj$?j?aqj~MuFsg%U==#d
zP&+=3`%^IqtMdTKW6iXFtI4ZVq41+ddD}t5S<>6X=e58v9p<`XV5bF^+l!7?d3%bA
z2HX)2K>aTDDwONGMAhs<hnkDrSKHVZ=KZHD4hjQ~aXe?b@YlxlC#Q9r;0US*Yw-%>
z|Kl(tsS~+Y6uPAF+W`Eo(^9Haq|ia#^_osylW}Y+`ApH>gg4D0$ADJ;6z3xy>S<~1
zL{_sifL)Br0J+6-_OEWevXLkbz@;$D@gSIrf9@J$D)m14K}Yup-gY=KP75TfF-<kW
zIqZ5J1RpBxfK%Y(&`&7LnmZlpZhU{4bxOsp)pmFXU&Z@|_wx1c6l%yVMXKWg6GD7L
zPU5I_By}o)e?Ln0EoE+?FZ4|9W2eqCT>I{8>pFrAriPzMFO3}b?HGb(d#3;*2D%?m
zZ59%grR6HwxY_%i*iVHs1+yKcd>A{<8^6!I>fjOlmSTD4Kp1l=i8bp0=rJU7-At^3
zJ3+@y7n1sE_m1YPp@P})%l9;QeJESOBw0)J2Q+mqI-q^7A^E!#pB5~<A9y?Ok65z;
z=8VX8-#~b?wVW*@8AV;zYUvX1^IOQ}qm;NdiF7@P*cFX{=&&3u(`bey$v{O36B!6{
zD++F9&2{G$xop+>3b5vAi;&s~GKUm(gfvLBK3UC7%zQ4&44>jF<|`?l4Wf*7l~>tO
zLP>R<L}0%Ff!=@KO&lsz`UD!6OT$;2O;1#x&kiS06MO&v(FfIM$4_ZHS8~uZPVkgd
zqWD6ZAP>+{LeJxf8g)vI=3e-*i#YwJo`0A_$@!<3xvGQ4D{$|_`Vna3QRlj@GC~R*
zKz~J`Ke^u#rsIU&N8v!Bt(?4pp7Mk&o-oiu84u%Z+VYW6j#X0H%_q#ql@4YtP1~Xt
z*-8um9z?wA{&p9tEoO!=u^>35CX@;e8uQHG#}G89N*Cbf2A!!u26<iKEwqw_duDbj
zl3lh(4;^Ob>?2m6#XT056xufc-HT1;zw@6yZWW3lVZHD~M~Xt6<>DWFdlI30cJear
z%|a8s_DLVq{y?+@ywjiG*BuS)Jl|pY?~4A_0;PRCwv&Y(%ofE-2(f)2p$OspF6i|i
z!T>(VXMXlii>w8cQ!3oN3OGi0186t#UXePWtfREJWWEXLM0rj3We_dl8|s~!t7|cE
z5sz2g6_pJ&PLff^on0!Llu(JX<n1yi+NY86YDB1WYQ_+%s+{Q3iPcLcvPh-Lo=unP
zSW%v|V{|5%>X^u=ZCmxk40~{&%se-K(k<|BCxMCP`X0rYEi~uj%9%lEAbP}?#75N@
z!e`_ENW4(>+Ikw77H#%gcOqZSXO?Ep`h(96pfR$~ItFvUe$v}G{c&Wi^+?2^PJ(o7
zMgGE%2rZ4{R%=eyrDtHM;0`{vYkn%<k*v`xePa*a(Z-4e=Yube-^Br|@k@&1vA>m$
zee&JRzm62k+a98uCZmcU&!Lvz5pvoc|Ng-%c_PSq4qj_s>!XJQX|^fltP~yh6PbG(
zDUd_FCnYPFr!!w#<;Wbfiv}pm(+I1W5P;tItzm`NPSN*(wKbDPnrBdFY`&WDH=vO`
zIoNSE>^}qx21l`t>f<^zyH&=m$n*56dlKm&4v&EZs0}1ZUMBacb9;R7m+g$^SoI@x
zrJY*-#<!crKn}8c%1@i-W#NccS9!NZbmIAVy9^ye-?c}AA^uAndsDwU%=Rvi6Hmk6
z2e&!vmpPwC!w1p5|3rJPa(^uc5fg3oCR3r#Jk&0~S)_k^W_4KTJk&526%Or(OHHht
z4%B{J$k7tyms(CU&QFfqvq|o5Rtk5*D0qKIP%bYa^UN7KCgr3j#qj!Q(<_f{b-$~-
z2FGgu4RLHGS5}Kuk<VZjDV&(HI^A?jOUot|*3Rs(xFovFid^jEX>9cvAIh(@9bbrB
zNP}HyDSF-Q#*Dt7GW*@t9^EFyizaO6HHt4yoGfFmDgbkh%5+G?hyZcm-qsul*0<9e
zJ&XMeZo3ESHX4Qeg3+#W`Oc%VZg`cSlgplK5u1oaJvr_Ee6g&Jsa(sp3o~kv71_^m
zn}+%*`GuNSZ|c?131$(G!2{h>Bs#WR#K0_`0T7tNMPwaaoJGo=r4p*3F5JJT+uELY
zrqtMpw>6wafxOf<t$&3}Z5zPYJU^M&=uR)Ke6aF}Z7#lR_iCi_DzSN}2A-Ze67tau
zV7YcUiV{j_hEYQbDlINPyX%M@k`{Xn7|iT4n|j80OqpgJ8V9B+Z6BLlGYtY{?{!<D
zeXJv)$TU{%gMyr0_@Sh0OO)5f-B+D`WDbjkIKRqmzp(Trnz{AiCVU?*<L<=F8^;Ib
zQT$$@$6M1gC`T4TG?sL|CUXD`E^&igpC8y?A*8sdOH^r<*XFtg1_u888!?H7!NY;m
zz@1I6#7hc)CCwv;NY~B#?=kv3FO-7{6fths=QnFf`A{$S^Bdv0CP`!=pJ2_wULVyD
z=^LtLoBJ&ajyvo-X(^wRtMSez{k3-fLm;$SoeX0Gd6PI4knB6uh$4SyK0<;r?l+Wu
zOGru>Yw8X;n(g8IAM(!XA&S3k;|nMqlG3$wN_R^v-3`*+NP_~BD=b|LEZr>Kp&;G8
zG}1^*3n;&L-@oHInA17>&dfdc6`$X|_26?uV2x0t+;y~--WBP#CI269@0~m~^a^)B
zva>vDx^Z~UN6sm(DOb3bXJC9Lc-xNHJgWII@p(+z)1k^^&xiee)wCG~B9}`+4CA`;
zK*IP*J3&znNP+KS<}0WR$rVtiPa6qt_w05yq}E|AoQ|O)v8uHv_q<r396ymL;90}E
zz!!*H_8!uPI6xHp_ZC|Hf|cXS=RBkr+-z7q_~=LLlwa)wbDZ-=tutBTV+~Tg76*1F
z;0_e_P0BfYGW_fS#8LcTQ=!MbR9A_>O>~iwpI3F>Law=-1>)1Y#-P*Yiak?#>ZDCd
ze#G=H!U(kMWPwk?M7>nR07R2q?26u8x-D>q$^mIx<#?psE8y--TO~FZur2jcc+0&M
zr>`91QZRSG&+1p|e}Fff0|rR8X<$GMb+7>uE~}@!luOWsnxk{=pAqwAMjXi#!r(!S
zao3#9hL{8FCj+_4CZ2hehf;yZaaE*c!9~lPO6Sj|Wqa(|tP7Dc(bY9kDS~<EZfOH9
zG<b>3YaJn~9)o=Q(aV8YrhE{vNEXGuBQ(<(@va1er7+SVx_^c?!^K2b<q_F|gIPy~
zH>L7U$%Scc3f!QFjlr0Pa(|WS9#?v_&}y0L*|;8l;R}oH)oI6vU&lOwf4RFez-H{n
zJ)iE%3c+1;u}FJ^oZypvb`C>Wg2?t^8^OS5iuJWI38!mP>KzKui(k=>hL0x(h;PBx
z5N!B*H~BvR(4v%%f(O@!=?Mg=!q$1PdPbyxaY_ctZV)>=nLz3|uhG4XD(hHZNE8Cr
zD7NJ1T#tPg^dS$SKMP8T2mZx-zks@)Q!Hz%bJ<ne3gs+m(x~j)zOQ~Ku%6W0<2Rr$
zKy%(pQY5AL-fC-4oO<1?ZjaFusi9O0oi~c&rMkX`?`Jd-h*qJJpyd&23=giXNPwm<
z@Dw-)t5vK_t8%LV0KyRkS<iR&UGq2u8?2&U-p6{173;(6Q9&~2z6N~*b&6&p%=&Kh
zVXk5~+%fT%^nGq9{<nQqgsVyd2B}xgH_1O$(=A3iE|CqP5JNsP-mQbaHJ1t18rq=)
zDLkES7%?HCw1xpVNTA(cDP)Pm$3}=D+vB;kN^-ZkRdimhgo!!a1G9XL`h1$4z$L0X
zsV4|-Q_B~RVu(>EVWem8SHaxKkTr!?B)Kd}niF6Pc9LbH*3AowaUJ{UkcRS2=V@N@
z9P3eh>D@7EL^9~MJg7TYtQKy~fAVwmI93#+p;C>_y^m5wHmhTbY5Ss&;ylHGL?vkQ
zd~t6+HAu1)?+KeR$%<ls-XdY>)Mydd5&1!Q<Bp<Q17Mwm$j60z*{2w-5+*Z;yJaLg
zC_zK~h>DPbS&>HHV`w9JMiU0wR`NFl{ddM#&Nl{RL`R3)_$~LXm;;{Dt*)Q`1ME#P
z1TK1n4Tczccx)R6ZW?*vJ?a&u|3m2A!P!{aG6fDmcX<8PS#9lV@$}lK8v!NIi%ATe
z$Zxwj_XDZb;!lgrrN%EGac+e^ByK>(Jop#0^lY7&eK#nlvn71ajGv$_Q-?P?{Jg63
z96va%zAVd_`p<2Za?YS;8+0RUJ>LOSeIw3I$#&KJUt>DW*y=Ojn)o1l$11FG?I4@Y
zx)PKE)8%{-;He-0`PdUQd<&Q$ti)cHsu_Dznh`m$pME6PS5B4iQ0nE~M=~S_bBP?x
z&Hp3B$x$1cN39FQeO}BZ)B3K<2sz>&c2ym|zF2(-t;?T_R$|cpq@zpJM_|fBCiH!W
zsfE4COe`aASedc$vOd$%lb4>(6k->+%P(n%UBZt0>BBhub&P<o8C$UgU{heN(I5J=
zeVw`ZN>AItP5?Oi*80_xVWcel%ipR~a+>fbZF41onH`f}e-v!D(J46w>UpUjX?ZVx
zmY@g<n(B1fAf4_@>>Nfbbj-glso%_`{<+vCXPo|-T?%gnl8|#kIHiLq3M$%3fi-EJ
z*-cNdCA87nZQQ)8WcDHYhG(Dm-JN^jjW404Y|mS*iL^Et2aIqt^9kHYm6b>iR$8mZ
zPUch7^_@1zM9P%iMD;YpU+oS($2aVLSx2(e{p@Y85;r^-kInzXy=V=%sbPVudd=nJ
zRpP;P$rs}X;p;Vx1JD=^`A2Iby9Hp{Ls#f?+kb!wkyG7?x9f0#J>PV`(UV~&MM@qt
z1?A;j=`9`v=^|)4+YM)?r}Hcm+!N%g{%Puxmp9)Kk4AckgsNkdNwY|VpM%10lRg$v
zfNQ87=iypKAKsHLKcqA~kK!4@MBZHX<1A8M2-d8JsmWh2_;gs52JANGmC@*^?DKHD
zoxvadQ+36O7ZEz5r>4ZISvC^UGt8PUgHU2gI;TjBtCZwIUn7cjZ}RnK*&0G;XnNG6
zzn+M6dg>5!vwKJUo~M%Of-E^>a^1hgwj90qa7%u<+sbS@^}`5UE&<K)h!;`{UAzwq
zeJNm3@+a-h@N%tS>-{SukJ>f#K3$_W4l~YI>6a<y_}RtV4pFxAu(qbrz`iHMx-k&c
zMk<Nls%z}nmUa|%en-RRX0x_2;Y>U7Z}%2iisjg5Wi|!`7FG5jeCLbPd=^jo(l?8#
zId-HtTG9^2bTt@~L|G;04tA>)8O#$JSrKsK*q}b6HD5#_pZ@)cO;#X<6yN(6VsTp!
zIN{HCiM_5o4p5f0w1c4SfSQ4SjP%%!kd|L(y22C4n!WM;oVNQJul0SKx66q7b<wsg
z%<l|T&S%*k1f&%4Up**>)U3U_;t@K6j%>=4C5WavJ41Rw+=@;d)064%yfPVr-^h=O
z&YU#pJEPl}DRft>w2_gh^_sw+zDW71I=>~ve&nXQgZTB2Ctpp=j!P{!Ueh;K(k;1!
zlJ;^m(dw5T;*(<M1}jw-odDR9xtWI;h0J`#r!pW27(f2#*}8aPs29mu9O>#VPZD`a
z>*?Y38O>Z?$tKr}MjX+(L?5~NdG4V>X3$$l_;Orl_QRh~yQ1U+#9jVC=s^Y8$&Q^z
zZ<g{jRA%p0SG({76RwxQv7uuK*7|;;NfLbuRKw>2G~t{WE%vxU`&yw=!|Oa=yBPM)
zwIWTa-H(U7hT!7LI7@hb(1cQUKxPP$Zr6o-M3KPV58NtM+g73(douXi%MmmXWPHcE
z)jW?d-iS<a_4F(3tSQ^_>~?zOga}yR3cwp=cqhX+bJ{-u4~MbtYR)CPa2vOcNLARi
zWIJmg6ia{78uZH5G>UHw2Za6g6N-10)KT(L>(%;K)F#)+cLy)h;EuNofQHl#g+IEA
ztB~<n%+zsQ)O%gO_m|+6O7tBzFnY|%eumDmfJEC<cR!?wPFbj#Me7PTjFf4Ew_{%G
zT_eSGmX9Yg#HLJ)rHwskz8+{a8oE%&yw@8;!P~8_qqu*C$@Te7lqv1Apz%(+e1A(I
z=^ZMIM6b2Hxj-2SL}4x^oFZGt$7bALi9%B5^q}>rX9PkLO5{=TI5LH#TwWkgjvOGJ
zf>Fb;d>miT`3ziR|8eTMm08(~pR?jO_?Jelf^@4VdmFYFu3bH%TkEaqA07=R=_DWS
z!!`f7KNzQ~+NtKtI51ns7HPzz*;XqgS1^u7d0ffYSVJr#y@Bc~?a~N-SJM!Ifi1;}
zL3YPY_BTB~30fGjAf&&wPC+Td{D(SizO*CLIlWteSRd6#tWtG<ET8#%9FLouA(d;4
zfuuW4B}A#i5$e{Gh}4<qRP)lN%pp%|eiTYx;tp-!V(cFhYEpX)x(yxfft?i9!JjIe
zMIG|h-T#VSaO(bW7dIiF@#SKAxAK;H(dPz_A|N>Nprznsqdd^66g%u&aTe$ETx&0<
ztp&oat37r7UADk=GWsrOila8N`K~fU^eom_V^*2vx18SlWta10z7+#BVAFp9G7e)M
zQ6A%fW8;o>ZK2!eZ0^0!5?bw@TpI#+s8#09iQWO+gTRT+2Ys*CqL!<QWSeIri`=>$
zi)}I2W?tt|@ARWW8lDu~Ob*<hv=L2ClS>~=b>EF;fnpaUJ{8H4jl}c5x>?KP>yaDG
zE<bX3W^UZ!9l6?%5sKYTM<krPS;R7@?rDd+4rr$yVuko{uUL!gkkW3OM>+0Ck0Ip*
zGxJo)Tev8@!LDi4HfHy{SnA$XA-ygNXAFKaK%)|Gr+!}21$%B`G@jDZ{86j0SRV)p
z_$*ktV)Zowx^ne4{8oxr3$lyYP;N8ez3~~41o!>+gj~Qa7`pjz3^Y0@rd?(rl6qu~
zp09g*4)leO0DkpKz7-%}!nYp-?mtn^OOMcHpvW6tG9_UCa~*j>YG8PjFI$0!9VvD;
zI4aLc^DQkiZ(V}TRq^)5XwN6f_oHt~Jx2lzgO6fq?K?mYiJ>dQ7rx*ESISuru98Xa
z16Nlc(iL~Txh}M|2K#K}ZI6Wf5xcv;$q`a#pSw-EqKM44-t5E#qlz2835E>kmp2O)
zr$ZE4VCg@`Lh>T9_S5vawxKrI!>W#zHOExtBvs^+ySV}WR{E(MC80k95N$0JOJGTf
z(2D$)g;z#z8UwI{0j`oiPO$g!OTK`bQl#sviFq%6L`%(hme~fK18-TW9l8>EmX-OC
zqqWCgw+LhPN!va4B;s00T3eP>a@n6E%bmY!-}h8A^(unl!<R*Uj%>HvDLJWb2|L1(
z8k_oL#b3-oR}6cpK&jLBAfUnx8L+<B-eg!uIa}X1B4*mPun|hd)e}eVSS5sql6b_g
ziaw0?udFUt4lzH!u|AG@8p+YqW^0zLh9$$}MdDXm^EK$><6r=${yqI+YFuJ&Ys~fj
zWN9-kZ0T#|s`=p0ZbPS;Enuq}-hY7f4!Mj|(-iX(CG7Ck6Fk=jYD57bq=l$ck$Zp^
zvtDEV(=ejyb<2ccL<hwf>CjI>U*Tbm3L4qEv_9eQj{o+nNk!5+dpT9T%{B<+7PbSe
z5@aL;YL?d$DBY{oyta9L0@uyk<9bY-OMh&=|FvLyVA)YG(0gSFuMx=-e4d-Z0e4O`
zDp$)4(r_C`P52Ls)rMS>(l|U(NjTWWLyT?HEJL+c7cgSrS{O+(gPCV^&gN-ph$g-6
zh9tw5W(z5J-;wuW*8;to4lrzqG~!ctXr?(e;e5d^jgkZ}!RST*Cw0VF#Qqll6<+T$
z7*|BLwMWt}c<Dp)iX~%jd?@WuM;(h<R_|gRk6maE^&V+&d3*BsxEFzriM~I{-2BFg
zud(qXn_fUga3Qp$^s~f1tjC}TKkuq`**nuyZ?p!>xqOOT7*2@MAXZxkn$%*;SXp8x
zPe6V<Xf9H9D2gcR{CE6?C6)&CR8F*0<oDA+c88pU_Q{F0*e|3^@jV}_hZ!y25m-7o
z>Bj%cd<PN_N@TgC8FDt;tTl<wrM60P8J+*DR&o5~1@fV)z=8HH`~4L6y4MUd1Hv^D
z&OVwhS|wh!ZHI9}@+VX#11CaTR_-{L%|YxV6)v_a)2pJQH9CS|>H@w~!(_9d&w^jP
zX{zHy50mM1l$#f8aMq>R0CUSy$IA09NEi($B~09=7dWsc3+7{EYWIcl9b0;Il5;-9
z*29CBV^!Rxu=8RcBdQY&_d!%_Mfz+^5t_$P<ZP`Hj3|vbo}$ZVBZ-Bhy@7?yqoipb
zLI8#6l(q?Iy2MjTBVJFsD8TK-W>jmB9GtD<q)VIf3^n<GFQ)M%5OLtwBN~8M6{Atl
zqM@X8U(mXa1w*8xTN-Ssd*|7v;c*hv|GqM&?m)nXEt5%~rlZO?LSsbmWF^x0lk;2J
z-qT=)rZ-ps{PHHZ;w|4_F8}tynS;bP!MbR<OJ$B->)(BFw-KIVQZAc|EM%`cC#Vgy
zKe>!u2-t`akcFhcIE*1iCmgL+EJCmD&kaj<lu2zcL=}E<)Y^H7-PQ2>MCr3rV28}U
za`VzMcc`*>LrweA>ausBr+=|d$VmyP_YsJZ!qa2r93k~E#G|8&))C4Zj*@c0GU6C$
ztSYGEV3CBCH>D`rg>#~cRgwD%?gGji9~*V~qWo^l-yQeOw2EG7u)^5QZ9b*XOy@7x
zAFIgD1OuE$Jkl42*wGMa5h}LGS^!=Oj8<;e&?jwFN7|QLv@bIx9VCR%R~QtB$#*5|
zcZEsNY;37$dJH(=MgJoSpwJ3(TX-{{Or57Y8<CHm)G@LUfoL6>Z~j=)M%Z2-JUcB~
zw{m7D6RzCL>S>Bn$~s?(1?Vq?X$S~z`vfnb?C+t$TxE0?fsO54E7Js)Oa34-CP&{0
z$hVAxPeRM42hde2%<sbz_oafqPcPLEH_fT?ME;f1cX6>F<0^_6W5Y%&v{c`_r*hhM
z6nO~1+nV*PTi?*7-_=sJ5Ei5rp>)<ws3m^TASY+=PpZ&5Hb1N)Ow7mjA*)u2OV=~%
zN#H2b*F@<<n$?vbTlSCqLzc72Bn-MCuJeC+erN~*sFaxq>SY#}26k9Na-LdikiVRX
zBMT(|FcgzOZ6bOJ67<OTrju<V40P3s;&OCnp>4_69v@kpGFm9)KwA^~l)pTgz^Hd!
z_2SS)hb5{HNU(x&;`UXP1i&`|=Xq5ltTL))4LSAI3G6fiTRj67D4t*KVt^S!CjsN?
zj<8KUueH`D$+8@U&w;R3B1I&m667)D0kmEeg)6wfk@2#HOW7#Wp99dK`nR@jw_zlY
znRrREL8Mvma_)U#;r*$Rq?C8pBz{De=xya4BPF|(ESw^bK%g@^dg9zX0Z|c?sdC4V
z_j->W)-uuGcA+q&Ri;YxBmm7O6)8HNf4TlC<<mOq+BU(R^K)_e12GntJ{!HQ(4=eU
zHADc+#72#=`e*;{+`=)6)J7tJ?6D>*z`%wxVBoE2R|?-)KYAP_gy!HWwOb2tH{|sV
zm~@#EsefhhZ$63H4DM|SOoWQ8h>lW}G05&Uu7lqm3Klw)K_rpttz1!2N!!HeRsK-;
z_Hwmsz)CsDy~MemZy{|0CXkftk5aGNWaFm)g5Lhi?t!1z%vEIZu1-sTk=4Zi^3i+c
z26`%_=-oYgTQB`RWxp$IGk(aC#a#Jco7<PePQVeV_ucW@&+&fT0o?wsFi!G>g&1E%
z@m|BB)nGCoRC9IaNErdEob+eB@DU|p_F`&-fa=KD`W;0dWygksk0L{PpmvrYD<y|d
zv`kC3J#hw5xu>QP{u0e+L3J1RP9L8QlmB*5qb!%XHcG%6T225%q?0bmwop$*z6MJ;
zF`OjKi6zpQGGQU2@J2l|PNlS>p*#iLowK42mQMfF(orbOMm+~%Lrc&`i`a$4M1WvU
zD89PNI*yF6JYD<u*}C&+L)>z+$S5P=f8$aX1n7Xq>ePlm0lVkOgj!a!=!BJ2s?uxg
z(5GwaOpkTtNOFS8z2d$iS_KxizIiYDt*_VI_Bj8XPPkNu?e-4*_(mT)NGT{#`}ICr
zyQxr$s#j6G+M~~NDdZbhg%}WX1013ncS@yFw0=<~2}PQ6+vbPyaoAB?32$CnejYb{
z(+uzvN*xw{o{2DByVV^C5hT8%_aD7KH*k}bghm&2MBcsnLO(b{y)0OuAZ)eyK4D$$
z;)9O<R1em}8@`8Q!+N0bb&H3OGBsu4bzI{Oig`e8F!m5t@)R3{FY*E~QWhq&U4Vz=
z4M=#B7QGrR+WgQtQt$FOyrz+rxeWfw5UCjYIfSO><TL(>w<{%S{+Wu7U83f~I{2)J
z^Ow1%<6yy?y;;UovD@|R3v}6O;eVfCcRRt~<LWN&;x83iJkC4FUo4T$AY4@4@kqxN
zcjnF}*4o$3{{a6CcHg!cW%@iC`KSHZ2^P;dtgD5xr=2Xnb9wi#<eUg=`I0Hz5G@Z-
z(dwdR&7k!?VSBeq%jJspliLGoW5R`;wq3!g?r^zT+_u4g0ONiimoWbRJ1LJDEs75<
zDpehR)VsZvp$uO%x>{h$sUgD2T#b+_Sb_}Yns{cC`fo@UOX5xl6-B8Dt!N)t2>?;H
zQOs#V-pt<LZ`sl|%MGv9Rx&PiAyuQ!)8mChFQ!#=?p2h>w_@5TcD`|3MQ@cJu3m_&
z7xi!CY6SgTyehHAlpgNVqWI%!Jm)cCVcIRPMN~OXcz0LFFKZHS8K&s7c=)Z{hwE!6
zn0!f2VFhfXOh1hDN!HF0cQN{&&$nQECPkzet7=eWU;vMfk2N9Nib=da{I_i0nt@jf
z*VPHNOqEAgu5$k4hO*NXnn>!#r6l(*Cp>r>X=!Q2G>Lg-<2MF8wR9NY=X5Ni&vo?7
z{wSTHe<C>E*;y~glU6z9$*#2KQzlMmtaCzZ-hC}w>e^XnKhUkB6(A;f>^AVG$s5+%
zI>t>kL6r$8+=Qulo4%VOQEQV)4>2UTXS%L(4SMr0cp=3T-jwxDdghXC3RUD~_MC;H
z<IK6;M_H&*iB6=dHt;f1t=UV6dH=-@C5?NCz=~~*_`R?P6M<@xk5@<G_|Ug2l5Jq}
z&QIruGV%aQ_R=P%PU?tLT{WK%$=%LrteJnN<=`~LaxbeJ*Qz?=00N;Bm6kYqYsT#~
zC`hOONYZfXC4w}{&di+5kIw6%`bw6`T&#aa&xCJf+=z2nQ%XySMU;YRvAr<}U*4+T
zd@1lki=&VFSx@I%r9uRgZGB^1(vK~nrBI;nx2XZMX8S@Z%FY0P!|jiy#CbK2xMIip
zby5D`_^!qS2Y<|)3ch8}+i5Db={QIjMonATs#mKO8tSUeoW+tu9=do4M@q7aZ#bZQ
z1*csqh&IDsWp$)X&k;yd^=myzs=7El(`Xg8J^O&&cqF80Vg|4SFaQ1=^I=%L2O4l6
z-pbY;VLyFR9+ME;VdPeDpxtKDF;=hL^G5(Zg*vh3w3vS6LAUTxX4_!E<%#uP@l*lt
zOeA@aQU6$V$jMgNcZP)5JfO^B?4i60hf#pDi4$+UBDMDzvxza|lb^hDWeuOqIM&~q
z4h^*auHmoui9jP)&hzg=y#uza3#7vv##1gU!y#55|8g*gg`*oMg0<$qeobw3qkmzn
zVM;5_&7xmS>z<-DD^q3zuihAh(^H1Wiji*{RBq2q<>|4eRg#m#Qz=yPW6=cvr0lyf
zUX&T4U0N;u5+b)jVM>UW^w2uh@6Y0L416=fcx7-2gaqO9Q%MRLvj|(vb#<IWTHh+Y
zsuG%B%3)EzKgY5Eb_o|>&yjdG%+(^3K04CQ{b~d1!<DM;TsLgMO>?Po*j{4I;?{zC
z@;#tL9Bb(7Eti?wmKS0N+@7ju@wHLJ33(vBoTL;&g%K=?2Jk&A=?i5+RYNqMHPjWR
z7X!bngU9OGXy6Vp?UJd9uJHPkp~el0P~P0&p4TY6CQP0*l)AdWGGn^55mrIU<&nsi
zly<JrMJ%qCik+3{Lp9&5Cdn}pf}21LO&2#En8=jQ$nf(!6u|!?)FP3}9};<)mq+W;
z!Q6PP?x?*or9nj06Up9~Mo%S2zZCZ8a;rk&dQV7K6KfBOuENxhEOnjkqzk#JEP4IQ
z?HL-+8Q$%+`I#eCx>rM~+B9yR$o5gU;cY6Z)7Xsk9cmH3EzsQ(OqMDwvBXZemy%hE
z!!+<_%zTM6H#+%m3C@as5*5;D*;&n$w~(L>_!O*P)Hn`~f&?!tiddQb;*{kn>*qU?
zoTDBChOTU08d#@@xKC@9nSs|sOCr&O7hBNt4AuNRdogi)Y)K1z-L8a1X-kAU-8oFw
z-LXyLesR9l7TDkmgzt}?gQuLv1vYJULCKD%I)Y^pe4cKf1EAfmE(#vd!I+s(cm8T2
zk;=)%gvV{U>3R(mYjz7*KYIAjJa;+Gh!~YbBFUGcoQd9bj*XPbPgCy<BkoAn)noLT
z8fhxMDETX(p%YAw<@)%=HMOylSK9r!&1>x}Qa$f}g)H5m)?wEP7`*pjGE%2(dcdx^
zc~gs_x}<v0{?VXQ$wP$n9Jy@UAGPt_ioXaQK26as|GgnHaaSG%qP0c(N*gkpHi$^@
zT7J=+MURcL_Btt($D=~RPO;OPXR-N?YpIW%Wim{R_Y+l)!Fgg1Xc&Tz0}6yh$UXLr
ziEn$ynZpcoXJT65mV}`;XUA^pFHZBf3jO5M&M8T`z5e}9WK5e8L&k|I%SD^>MI%h!
zI<;GRzJGQr6)O@yV_PTX@gC_+g!H(}L54G#efU8|iH!Q%;TIUBx+Vx^`Xf@VX(bZ6
zOr!?oEl-XJ^{-G`6{4VCNc*DMr%AO?5F9_@M^d`bj@DOZMaHhBbgr-g_{rm~E<K#B
ze;ECy(FLc6n)*dZV&iNd7ZF^ip+eDku9bqq)!wYy;rJ--Uj1joi8>EE&69?Gt?wN@
zY4EhNUbCc4_4b!3(Qf+PvYNR0Ab&{klJf<SFquGli6DE5E)@LLnRP2Q?oA#n%w?%P
z73C)A_OPY_2)X@1VD8Y;Ft*PZ`)|wtiBgeOj1(IZv<n}gu<^gq;|`x)xMXan`yK_N
z^WN$u04*Rx*@S{*S41l>w65bH4w83!sdoM?60Xsw+T#u+Yl+pVwwzbSg=*{w8fy$S
z1^M9q78ml?$;38@)kON|KW379azh!%`@UG3?dHF}eg4AbG*13^g~r8M>#Q+{3}zx`
zhtV!1nEAUCRr1TM-Ia;=2M`vJE`pSPaeS1@5eZg?Gw`$DPMiw!pM^Re*hxl!Tr0<@
zBlcNjMf*?9ICnoj^C?Gv&8Yk2NUS~&cpLB=vSiy?CY(=JnCNRuj~~R>9y|)Au*oRN
zz!p7oz5+23#WN<?puspzw~YOm_%`Y<yS}JdXM?kaIKZ$F$4EmZ44Oofuc{p|(p2)v
z@H-qtTB`g?Y2}6Vd!`V*VqFiQvXS-(1!Mb}wb>iB#8U6pQ~#N<&SZ4smA#0FA;)vG
zl~~3Ee@w3BNqK|VPZ^|zX=)C}z}HlDt`(_kd~}<A$Kb;IqA>tMcL_BE;t=A^+?Q#2
zlw$hE<*PlpTA&;n#57Gm(Y?_2pb@zznQZ@<A3nV$Fj|tKrsVAFGh+l(izZ6q*7BZ3
zObtHy9b`_xqcVOOK@Uo^*LIR2Vq=Fj6LmA<K@OO6nsUHih2q8DIrGu(NODiRH=u7s
zKBWcorIFJi(UYzjcP!A~sGSN0E(wyq`Bs4=u)by8Zj>4KgK^vB?Pr5r3E2b_GsYT$
z9J7zH+^4$h7D0G7w-054XXqsW49-;c+2IEaYj1K=I#@zf)vIR%qaN>!6+B0r2rfkZ
ztEe#e{XK_Ee!u&7p+QK<g`k>vwAh&FFFc)p6CxX7t0$&yrs2Q)wS=gfn~9t!QJ!0g
zt4vz}EMDT?p!*o^(IJsmw#Q1;eYd(E>czMnCJbcUiqdz4lubgbvN9P08%jyu%fmLg
zAd<}TDhv>sQVtNr4Xqe<zLD6VcgA;>)-mput|bL4jfeen>4Djebxb~Y1D3R0Q0B|G
zBzy4LwAHLv=ofk2H&FQOk(S+h7Px@$5twDhhR?(pa3sW~Ofw`V_pY(X*O#O!T_f>0
z4?JUH!Ah{=Uvb$lM)712^ppGgFx}Rw(Z>X4NKQ`5q)bk8DlC?-6`W_0EJgw%wlx)9
zdNGo9IrA<BC3uAx8nhm&^#A1;Z2v-j*qMh+SR3c)#J{%^IM(L@^2j3xW5eiPB>j^H
z&#Zm+Wx*@k|4~a$ziiyZ_WkUcL#qxuL)YD~tG*JwdtwWZH*~3Oz7V{mqw{6&PqkPJ
z5|77fV!hFtUKTdiN!_TL`5lOgxeYzEPqpRbN_is(|IT%Mb#cA+en$Rw)h|(6#kiFF
zu--;unOlg%{ThyvT~3jkt`KpoQ0vXkns%y{rMvMTpesK7A4mRVjEDCZGvBe^_lBW8
zrS}z;qkTtfxzqv@fDV~xVXOO}pChF>&b>4H_2~l0EBAZa5{Lh0oxOID8oX{>nr6RR
zYqXdweco+L2#M?EnNq3Msi_HbmEKc^ZRC%yN{Q|-eFc4+s$3uabn;zjbA4Sg#H&u$
zy~i-#*hq4Q8wW5hCtY0E#}d|C)4UWaTC6))Ztxwib!Njki)`v4Vy~i1I|tPs!!qAR
zY~Mj)h9rkGe*nG20ax}^@12sts9##pKJ9J+mdRU;N_Y)_dy`OmM#>3C|L?^4NmWTz
z_=1>_<-C*zu1ZPZPai&AaY8*tsi7b7D|<j+0`(iyEK7>T^L37tuKxfH8fw<%8n3v8
zmcCE-8nvp`xW{Bn7jxSVtSMy!Z`5Pau-YY!IICUxKD2Se_f&j4n>sc%pu596suLbM
z8I8;HjTcNtDJ4ntc3xp@M!DU*={#E$%Ln8mdK&FJaWr9UZ>+rntAHwdG9t&OYCEV4
z6LI&Die6c;+;hdL%JQ3Ly8JAR`AmtZ_y?@)`UjQD1TF<7NJa(s-EtP=RBPZkKBt<+
zTw+G06EI-JeBRWxd|v9igEg|;gd?z(;%@BI%zbHs?JHa8Y%X=OSv1gw^l54EE9djT
z4BT_;*MK@lz~eyu45FdcBtJv`Toyl&lvnAUzGo-lXw}X_+i2Yh=(hG$L;38+J&089
z!c{fQlD@hobtDhsLTO_^=W#hNQ_jKu@wwQ)l=tMdM&X~7S`QXy?o{`mAKP6D^sW@g
zzBy-Z8ghA&x>(SQJ+Fs!$WC&VY#6$t<K6IZ7Jnux`$bjc5fZUht>uc>&*W)%eryOe
zMaiPOlvegflWuLbb*Vw8S<RY*1l1O~NiHRB%CWTTfnaQZ_q@vZ#*<XRDYO3Uy*G6_
zXecL?b<QcR>jhiy{7xvQbn-@+fAnJxhyV&sbu3LRR|+$7Aq5PTiA;zeLgh*^`@=h+
z)BdRt-UuE^v4GMMcP`-?u~X_&BCR&pzO%a0RL}fyoDGO;+wb9$vSSUd_WSQnK0etL
zL!PnFs7^cey5J8<3o7%W5<t^6)7qr#N=3B#vcSIrg5cV5xrbA|z?#8$xQi-7>_lsV
z74B{`u~BO@W-4-lcQ`aP?H{kQ)&`y2P|Esd6_Jap2mf&Oik1e_uL)fU8r+kJuf>xY
z5)bR07j2mq{db^$#Tu_vsdpBa9EW^5#g`Q^ujku!1k^OsROh9GY<)n}a<!j{$K0z#
zJDT0jx9dU-1r?97nNr)t51^@D?)%qEO}#!6i<PFK1FQ=c#c7wxz0of5)*Gv~chap1
zSu$)Ga4qsIpGLf<c#DLvKCb@sy|tnrM~4(NCqbq1qB7=-ipjXvkPsBT$w7e$SsxOI
z)T@*??)IYneQ=yW+l+?aDjg>()oYMk$_%GsBx|__83V1;3Hh~;Sr;92!s)0wce|<B
z$d}zsU1iUy^XpzX@<bry6$gf4%IVx5wEqmjNlf(}@anL=cXnDl3`cWz%s<*e??GUi
zQ(2=e#@{)TAwG6Ps=7UXH_#w|S?Zm@d;@nYRuPrl`gEXBnvIAj&)J#CqqH3n?K^SG
ziS|yB<=l&_h*_xf;sxqoa8lA`!V=X8>_khzre5ZUxB&}`v&$UjCN5^jh)b?&>mnrz
zeT0ElRjn&Xo=*h-&z%rc*TIAU7ty!=aFkQ9o{@sm(!qXaxFBMqzE#T;KEeG><T0e{
zb+MGq*8R-5tE0`^*K7GrtK9z8Y#!mu;vNI;nD@UmD7b)*z`CGnPRCcc7TS(~!m8g&
z8+tuH>9Rb&xnn)m6oML}k6r-r*K=aRriAAe+`XDcfI#-`GJ~-7>D>VsEd5U*RO$7b
zhWkn%I~t4juR?@=gsJjZHTZD7KQlwII`c2%)jk6l&UNN%k)3|lkl~sx_3O}HDNHzn
z!HQFvJEhrZ6L~+*3V1=Sh!4d;-=9=x>3dufoI_I&!uP&>MWCW3h7jMw?iJyKf&tY!
zj*tx^i<cz(OvAD4hj@4_DgVVb@_Z0gBSusIwVWkC>Pd9mP1&6YcQgIONhJ^!a%DZ%
z8DB|ay+mR%YufbHGnJAKfE4A9cU9y9jogUjk&)mtl|_%=1fPeY23U83{{eVul#kRJ
z2o<Ak_(l{)%4q(KRbgAvnF=Rtdu!k(`2zsNvSNMf;7=Q0lBS_bA$sIFq7P+s!Rhnc
zX<%87gWTW9POlwBta3*DT=8I|^o$=!G}uU#k$+w`1%sk9F+0^nUm2B>^I5mI22GgD
z7(p2e*69@6j#BV$nj|(lRbVObs-zVyLKf4o*gFML4uq7Kcn{G76$h|k@~_?(Ac_IR
z`a<158Rx=JA)6;my8JjSMKyvd6RnzCoQ;t(Jg?-ENsM@RT*>@hbCkJn!d&54BNeUs
z2FZN+Pr4CVL+sSvh*B`)WxwE{i*cdBrnZH+hSxY>gdrM^tIgC5d2Mb`&nnu3lrtv0
zs&00(kFhE4@zhmcofnw*#dzxB`LH?jfKvE~kGH<nI3W$mnRfD~l_D^0$HyUJk29iC
zZWTkhUb)KCvlH_n@H<w+xs3kYGqzQU{Z=Df>$;j)_?dfCrKVkGC@lfI`0ZqS;N!Fp
z9t$JDCyKJVkA2@DJfZW|B0nzex4VQ@mG~sNr$u#dXi99I3;(CcCVN6y`ap7+^U+_Z
zho&!75zjg$$<!g}NpIx{!XCRU2>20rsiGytZtQ!m&MMskpnWZvd0Rp2dwi)Og`{TC
z<G(BxChR7sfMCuE<}ZSN=b$NGz1zZ9QqI9T%NS6JFsC>8Em5{;=wId&uC|h2i)o?e
z=IMR0I{L;@(vdUoZ2Mr_IpnklOfh+Kd}=)b+`?%iyKNh@a|CyloO>17_Cpo`QdP>#
zLAz;r!TNgNGjPO2A2k5JFWd;c{I87sS)sTgMoF6+lJlWQ$*vVw?q}_9C%3FtN~i<s
z<gznaQWRA7;4CV-vio|Ch<wWO{{Z=M=6)o59XY?YXjfUFQpyy6UEi8&@yHhh5)H8a
zeMV%()RU~nStn+@Pw(lt3`{!Oh=-Pj+{w(h<PiFc#{Bx%;B6VPJ@$32I9X*q50Wv!
zjbw^&x47PnuDn7HW_NfPS{fo+i3D3X2@e%`k!5wdSJYW}I3t7r@txd`I!q83xiY!b
zP_S?{KfkgV6ZTD*rNgrxUbnJo4j$QC9X3Aj`tQ4o=UVs2Bt3J(%i#IB1BXQ&oDRKT
zAq!uKm8*V|B8!09&6f#wDKt8!H9>XbqNHw1>DJ)Gj-NzD#^lLZ>jv~+#hOF^95JSy
zd-TCv3dg7q^LkyG?znCXFu&(Gi7|!qnTqEH;=L?c2QsP`SLmgsL67ga`1h!f5)3ED
zC14h{9vX6u!x{qWCTsUHYyrc2YqhSGw%^3W#DtV^s;p%gfGL0Um3_8G8jNMK%3lS%
zz7OXQs^xZ87(NT)G!#^`%Ull`1LmRfJ1v!<QoOB1Bh_VO&6zB7@Sf2dat;hlsbYC2
zL06{zjf$6U<F4v9tywqfnn19q(|6_0_r|mYmVInq-d6DI9EMC&l0~W6M73Kdhq)FY
zZ1CLnFp7#&h@)0h0}m@AX+|V>ORt+oJk|GvB)!kKZ%LUmxtDEGSGNzm*Lu;Elc($k
znjjf{itfw{kIpHOiiWxc)wHve+7E#cQ8<qRv0ehH<Q}Z`C>ZM2h4zZ}PrcGNdye{)
z8JBH8zjYrJa!=K1rMQV{<z6wPHn#QY*P;Zuh%(LuZDfGO<s?+5l!IeqLrLKR_w5?|
zk6!=6hvD|rf0MtZYHW3*Kd#=>uNAt#g0&XUrhOW|=2Y`Cj)-^&JB41c##!2B9nw?V
z=IyOD@!Z*xxM9fzU=#!&*=O!vSPZ5V>{QvRJiCC|YBf-^6{W#|B&cwz^PjRI)P|{V
zw{8`4vc?WSUF5?T)Ac&?RL`=dj>8?{#(uYz<Gz}Q9!z#0%Sg(cQ1eF{zDK{iE0fd>
z*v$r<>hd^e_g6sJ`HHQ4r?~l?@6dlC$$IGj3+fPQV%^V^wl|M$WSl;QJ^?;5*sJ9#
z{fq%jR;WRR1oWL(hwV3fDa8_TYb6&iexoPBn}=n-N0u9-myn#@mQa&m55M>vQXK{A
z=wGfGDNR~JN1D1}Acq7~`=Q;Sh8}gkR2-`XuDcL8$LCvT%eQ!Adc&?_AZ`EA(J+HX
zRqip1p~r_R6=mz9z-s#|gN(a>6OyX_oi>3pq!+VO$ZQ6eIt{tqyZTIn94hC!p9A0C
zeQS#|;~q=ww!4G>T59k5aTq)3j_2kHJ4AnUq=J|g)eEE=#Xq2Yfdtj94;p2e4o*Ml
zy_F*QNM6Tt!Wy?-LIAfl30Y=N-%kq~6BAr_EphZd!Ys*9SsQ&xPb4Pm)6+mkKKtoR
z^)F|QSh_pfGj*@bFtzU#C5bJ&x2Nca{eziwS1f+CU38j-z-lbDob6J7nwB0t@N&dU
zBbDfuUwdCQ+f_a<MNzp{r}JL&@A{fzH7%57x?3VaEnbp)Uh;dZA-2b+!G}o|fmuq>
zw}fiF_+xsns_uopUg2n(eEfAer$6>~)c4=Q3+W+nP^2r=zP4^ZDX%G}k9EUfx`HPW
zFYmCqB40!siVrgxmf{pf|8oAOZ0oMwVKAXr-=J4n8}@Vvs-qq~pCHz!Xs6SHd$m_#
z*ki<e?8Pu_yduk~90+kHS%=Z>?SE>$fWD36@_W`o4qTmp8=!TJ!sQ398h4LBG;bx1
z+<%`AikLcr3*#g}q{|ok@?IEHp9xMa1Z!L!bRB1ZB-qU@r)(8>rn12|%e|0RpgbcJ
zM~OW=U(JQv_~Op@d0pq%Ps<UOLmn1oU<L|S3C_YR>e=!N--Ahe`H?@(Tb&YBW&mEa
z3ZWU@OIr$l-j*NrG2~KLAm%~mH0s>OMatsI+I0|W+Qcam-D<Z!n{vI8HZzG)Ct6OS
zX18wum%cw78h0~c@bGUq)`GGfWRx191u&r`%zHJA+xXv3iDr0@mf6c<qT&5=>BbV6
zPYsXdu4BTbPFZwpHAx1w*!`AR)Q$yQ?$Jz1TFA>8hSD8rQ~`!^c04H3VcScki*|B1
zDwD2^CK<UXNqcHE!vmL>hIQfJg|5|~?OXAs^sN?W2UCA+S=v$s;`@RpUE|R_w)fUb
zMUb=I22g6q;K#7vXeRrLv<!CLP!b%uoApt9698Ad#^*DdvQF<=wjZ8fVr~%`<Ct=p
zAADKue_Cq6#F&&%GVOI@iO2UK-SY^?&)}&~0i|)h)%($;A^!NK04|!=fU@LVwyGs1
z4z{S<lj^N`%Q8-%$v{6muT^GbMy>#%6_$$MZ6Vqm6Ft}I(6^aN#WQD`<C^JdBjgEA
zaw+vsu%q0P&Enn%V1DA)aQJB=Rno+N*s9w>8eC6PRo39@GSJ^u2e(>=nzt=PJQNe$
zaNCZ#3$@haO>*N_dW|m`5>lmtX3*du>TGJ*=X@n4Gg9Kb;C%yn)^yHyYc5k!?ZN^~
z_ctKiFMpD^5jO9(_ygf8<Jlu(Wg=EWo}mg=rzprie5lIuACo6U*aS_rSUHdKqW)Cl
zwwQGX_C&U#bw$~@0PxdI*OF0N3X{r<0nd)lX7w$9@w-QmRWRZ(ho*OP@a<RT_5$3T
zYZlQ>{Zav?qwN_mW24%-7RNF61+7~6(wNv{Evu{AL8e$*3`l%=R+{`zPT9t49502N
z2TA&h*@5UoJ;R@`)n+FzEY9#{4t^X+B6zOUWD+C*TjH2H9BBqe+a-LiJwDb*Jy#~I
z98zYhHMV=-?mpAnZRpD13=6!gapj+)04Zx`fMz{Jr#Zr#1RpZ#PfiR=T;FQ?I3u!%
zka0o==FeThhG`usJ|T;p#<=r!z#pmKRWqsLZC_IiRGov<>st*!GC(j6)Vz(E8JZ)&
z^;{uYUq-9&f3NhHL(FKf?y6M>8qHBFk`*aV0C1M(RJG9JNJX9NJX^0JCy>pw!RGTo
zf<Zz1kNVc`U;|QZ^uXO{4&^CC(eSoKXE#6Z#b@#Qql*Nt#tYz|?pcV4wUKBgY&*s?
zjm}h+3`G|`=bm1A5b^h&qP6>>`uNQ9R_B0($D^in`Y$lqzhfWYQ>cdsp~vo_$!3!#
z2TfftxIq|(j1r9PfnDX^D3Be0x>TLh2e_k&mdlZe&8RYG?78t^gwFQGMe>Vd*X?l$
z41o@PBZJD=KCI7Y3^U2v3Q91x&leE!^NmNA7enc?4+vPr%Dm{P3B>dBF@j;7!cmEP
ztccq62CM{Isc56`-GQTW%QV#<=;;B5v$F5AaX(Yme2nM4v}H(#EX7<mLwXSTQHk7j
z1WaDe#{Trq=6K&S0<;#ktPi_hE<1;`J3p{k_wXga{O{_T2a<5D)djL3TH9Hb)hdc=
zfh|A076u8_9a_$B|1ssSFPy;jPP$%~?NShlBIL!`hkR0<wLFCfLq#krz=h%=9X+D&
z(v)y$qtWqnLR>jN!|)C;fRpDM4GZetwP^)>|4!ut63_2dzBq1H*@~TR+H8k5vc(bX
zqQUhj|2^?Y_9=IP5xw(PkkK)ZZ(eBSK8g;eQV|l4arm1Y7Vt{*$oa#k7hPH<99RkX
z7to?Hdc%y`zM9atLY^P;1&x~99K=maziTBDy!g{1&aLi5dA=CBxhgqmzPDB%Bv-^s
z<w$)C=a#;Zs8o{A^CPcr?K{}>SMI+&)iHlBf{KoHTUVez8#-`gYFq9P?MuZ1var8(
zt+!Q(BiUo7tU6JjMxQRPoq89273o5L05MtA_~FM=#A9g6j}RmHopxJ8*w3q(^K$2+
z4*mE+s-<o+4A0TLCt;P99sxG*b6NXgtxmjED*)jSyc3E_OYUIqxP%7f(pw|DMTYh3
zhW!vV*0>z!9G;@04#%eTlpuTx(xq5L&*jv<Jw!lH18x~L=p#xaT6Sil^bNk#aiqtb
zG)8~q^lNECQbgF7v?IFYQ{O|?&QksPMd*IU%7fvtk;k1v<@-c_mYsg`y11%-lM{5?
znci66`Mjz_>Xa!hjuNYCz}8|)jOBN@v$rv0`xuuJ->I6HmvGTxF4N>dq--^uPwX%P
zVs8`V;`|{vG4~YoeSxJ?K7*pPj|8b&B!B@{GQw=bR1o&(;Cc7L*L0>{^!G(?iw;Zo
zkiXI7=C<UO8`Qs%t?MF8z8XeePH+0k!~}1cRSdEnDM&_=Xct*fJvOAANp^ZGE%Dgh
zuwSWsVFhRGTn~pl>+2LfFFvq@Ggx5=VTo2{?~!7ex0_nAoaxVQNU|PO-X}ZPO8v5B
z2{KjQlBH86GE$F9S(aK{RGSI*f2}}R;adIE?A)oIMZQ<s*YtAt_zuUgZIPI@C48Cx
z9T^O%D&$tYokdqYJ5#&fYMFkl@X`?6_BI3fmr3dcpuUy>1Jr}{E7#3weZ*}_(0EG9
zHJr)|u%me{Q(O5{&C*rv&7Q+z<Bd8mb$^L?mRoX6pH=(j|J0dsG=J}IE}qun!+v<~
z5krj&IV@JoG1f4@<*W&j(p|w&++5^emPGihs!w5l!vEBoV!Mkacx=d``}=C4)ql<X
zU+b;)o}Hca27+6ZqSdA~vv5J_*P{^{F8i-PpDN%MVZxlTH^4qm#XTX_5dXNNiR1!B
z^Eq$hnrch#)^C4-1sBi*4<V)e0dfPekqJ}iX2$cm)2>8F%x;rXzE__e{n7K1TIL#*
z@l<}wgSx}MT7xoW$Rrlj!?w~v{U3m!Oo6$!ZQvink0f*LGTJ?ktd&7_A>z(Y6<0O<
zrSBaCy0_qF&Wui>!(Lx6&59`EDgsQq?cJDjFY)s+OQB1)VR6qj3YzWLX};8r=f?^-
z85hh>rPna}l0^fMgH;q8I{YMj55~_)Pfgn@Swb`RJOUT7I-e3vNHVo@qijKi<t;kq
z>BAE{Nr`bk3HEsiB+T|uV*YiqWJ9$M?;H}P`B5@5fym@1t)@ir{_@W`fIq<z45A6}
z5-r6q4sW=_pg;;|Hec90_>|^@?g}wqI!~d&+q5mq<^-x%f@iN|y)Z^Kj2xI|wSq+@
z7aCC8g*eJ@rsNVFTg@WUd8ZJ?@<42Z;f0o^AxEwXXSaJ21ek@YD+C<Y!12j&+o3r*
z@tpqz(~J5Y2DRT|y$hN581}~MrnpMpj%kyd-TMjgBgkSFFOm6U<&ge=08F8;vLD3*
zz~?Yh@Vye`qeRf9(Xs_Ukc&0&7<z~pM;r@aF*i<g>S@jI#lAlLD4l35T2YPKdoXqO
z@JjVf<uAjk^uMkyu44P%`#o9|l2EV){_*hp6jT?$gyIIls4^mbaOKIc$tg><<{E>w
z3U7%2a9#x{F<bB9yjny8FH;c-N`m}d;*1u#k)UVroi9xRd2opG>aJvDV2$;!1sk@^
z4#VRU8_<of%zhuwkQT?IZu=;TXn?7j4;jRe(X!Ty5-j2xYAbKE%3q-V6aQU_q!i&w
zG1RW_*gs!U*~^5uTW!fM^IQA;KLb-U*VmmqS@h9NLRql4*z|Rhe7e#!mX%!XKSvet
z?$60+*)+O*d&SP8pP30&N6-)F^}G+3uBysb0?Mu6jO;V-tdvI&od}GD`Dzjxh-)E2
zr$X8*Ztr=ewnmNJ!*2CQSWsVee&ldwqW3GlzjO9ikpply=FN%Jt3vW)XgL>Gtraix
zGzcx6lfbAK%ARhfIgpfoTW3$}Smbp4)38(B6Y%u6qq^Buae>wl^CZkQyS1Y$a0_%{
z5hL(L#WQ{fJxs1fKgYJ7+4;b+?-lGvj=SB^&9c<kv6eOy#W3Gk6+@TGPqafESVm2c
zt(~y5@Yh#!?kVd(?Hxb-@%qty&SaZ#V0;L#t0$tn^P#>+FJSpjG_1Uu3q*A4S697R
z9c?1@SJtf+|02tTF9w%*oPP<MlO2rs%Q;`kPqGt%F}wWHVoro5_1gB$Ch!f0Y9!+7
zyzc#1An>TNkWmDG5F5ljhiM;%MEpubl=0N~1~Fdb=L^gwkuuL2MG?u3^g71bT|b;L
zd{#}GVk0L`Iac$g85ux&;wj;OE6h7_7~9Cm+)GX^coPMaFrC{b{^fWRby9N(pD*nb
zPTF)34W)n9G34<q>m0sWD1tjIB&Oo2HTHO$XHh397<rVL#bJN>V~DHEXWfxzWZNP8
zZiLCdmUICf96Ob`Sn*oJb>&1}k#CaZO$b8&%MsH@WLi}V&Gi#!{#2pLHZ>Mq0-~{O
zrkaox*_<$Kr!*=R&0Wfi^BQU**|<my<6Lc-i8h2PWuAYg?@UpWvwVl-K~=Q1_Ab>G
zwtnDY%dW(ADWkO@&t+IGjbb5!d0Lu5Yl4_k8God-M8U%C7I@v^Esr@4aWuV{a0{G4
zN{>X5bzm#e=v(qMs5aPBN5nQqxSedFJ_knu=FOO5iZy;Dc0T0vr($SiaF`@SbVp_S
ztRB75{h}oP#Y#SHt)ZSY3`a5kyuI!~UU|M+!`jUX9pr%Tn=Fnj<Fq`!Va+t>2}x0W
zN%8<XMm)sqe=#2qP11pR(NXB-eE}Q#P)T^38D)Y~1>DeRs=vGszey_dXJ@I4GWr@K
zYV!_dnqzV5h|R!H57ufhEq!^ULRapqfI4V+LC4eoEyF|1Ke>A3*Z^L(vWX#hwEi6k
z&PA!Afh^%MUd%`?EOMyQ7_(FCR`pH}p=OOoXk*2B^g!d4wm*8i>Ipi?FwitcV+%m5
z0whzc^Mb59`bqIKf@sP{3RsyEdu~ZCiOe=nq%B6pVx-4L$WKAK-}d-<J#R8(v84X7
ze>^um{GsuCd}0NTJWgxxI?;Niw^l9Xn?0z#!M{|;`}~Y3j~C&z5;5|Fwg5vMvJEeO
z0Yr@;4smF1+?|linsNduUbqW6u7FBmQtqivPt*CR=wFwh5*y!cu`0KZUlZl6sqLaq
zyP^a{reM0nud}bf$)@T>#yck6l*egG;(|q+CL7eLr=~_m{sC<vcJT&J$f&SUG5REq
zm}KcHWMg6T#kM`kv|ehEQ+kjUBL!KYz-OSB2OXa@qBWyag<>_xnlDXg@N*|JFLZu*
zax~yo_Zod&DXnb@N0j%C9lj@Q=0E6KgxW92tGd%}_}4Z{(52@U1h>1%!v2rCw~mSH
zjiWvXcP&u7Sg`?G+`V{lch|uNmqKwFU~n5K?l8DZTZ%(ra41&X-6^!coj2KJ-%WNm
zoBiWW_K$CJGnt#rP42y!=Q-zd4)+{Oa2|T0YE`wF;@+$Z7nM<rrYDead*cXaFX9jE
zbY(}awULx2IyV~)rDf9l^}~^G&}bw!$PhioyMwpWRUCYz4a9gDay36frW<MsCNOmi
z&6a6f37#=F2KXx%rBCr|aDB11y%kJ%|7wdeX?bnJ1&&;W34ARQndJP&CT$X!GC@zs
z$&d>+&^L4!E%Az?k7TFUWQOs-)Xc3q?i(D;*0#FSoYQB{;5KCqRq!*VGkaJ#F+@U~
z$*TrwT85o@M;5;*@<T9%>3CsIm8peCiXy{KD4nd?bm|iLxEKuNib|8;k1Q%TE7mJ2
zJ+jI72G}<G*!ubR2MOU*7|yRmzqm#bBJYo=X$?&QZ&<U8mza)iLB`ixA{T(X8gesG
zRnZynGlU~KU-z+U?MeoJjbBfYK>X|{jt$^1=kkdGv!$-GZR?3|YnyV4CzfEq-#M)+
z30rdB-37ov`f|F7pC>_4Q{7{__dmhrK_v%7iqM@PgZ=Tt$HFd)pBM(smKi*}vBR8S
zc3QK&l?U$##^5yeD4kgKPOn~TTduVS?v#69dx1*7Y0Z2yv*~&Y2%0j@NH9p0+ip;J
z_}W(J+M8VN^Z^{kQH-A7J;&%#z*z8Dsj+IzUtmgZ)V^SOZ`r0rGG4x8cToM$*MyQK
zeie+OX>B;m_KxihX9sH@`^icSvyc{mja*Jk_<%fUbI&NmC9%&7SYXfeS^^T4t|NM|
zQOcG+R+qpm5v;3nF<UV50<-?-6C-fVQMnQE8AW9{wDr53GqQ|pBz!S1aTW!qzv3WW
zLwa{kWD=FI)z;|`E?;07?R^FB_k4%&Ny?|7Ikg(75fL1XZUtJ<I`5a+K19=XhX(1R
zNcZM+(A^_)SLY>@eW>IykD0f9G}skW@BN4~(Rl81{Goc9sDcCgV0(_I0&u$gwW2|(
zn1QjtX7DpMt-&`BIOWUnHmleQdbDR4iY{2W$gLcS&a^e5Ua358CnoBIAHl2`T_zUo
zecE@Tne!JLzPSutVcS;b<3}5?_zQ&7%hrfb@VC6`@&9;N_c-(AK0IIldGjBLVk>@%
z(~V+vDocZ}znQ&pwJDqBV?K#Cl0Pv(OyqR{446MPzrU>rJME?FDyBN7Jdnf^fzuhR
zeoFfs2t9pM^k%mC6UD$oD%$MF!okmXwe?-?$&=1@yU?~4{@@&HMQHn+<jeAUWQQc@
z--41Q6X>AXJDVWt;_4HU@iTm-z2{2IY^5w-k&(-MU0Lp=iMw&szeH$HhIydsy|wBQ
z1BRta7f$>T6e@CL>3w70fbwB+vIHbP^Hn1A{*j?i^H|l;b%BPMPwiJ7Lb>_&PL(-8
z(g;jz%}bI3lixWqqVf&gtAH`~6Dc66hjPdl1|~hKg{nv_@-#xUZwd(c4Vgs>yzd>6
zz0xJWnnlUI<Pw<c!L9cf7wR|2?gXidY%ve4fBQOE4^Q<|Pu_(GX426-x@YCmaW|3X
z>j<H}rr9=!5KXZwg6_bru&0(u>pD<s<YKo6DbM2i#S|!)l-P@RL^ZlAgh=DEYu!N%
zlC2}tKmQ-#b<otM&+{qSXA*SS!aOnU8w-&d2axwqU*+DOxs&u17aIQdW9GwkkdlSg
zyJRY<wwzKf-uy&*4kd4;rsHl?k2yrW7%mbBOv9cE*6YT5%958jr>gdNMKrpp&o7dn
zw4V3$3wxsQ9Lia$@P239`<8rhTt{R=3U#NtF0i3Ap|+&@0v2(u1))i)M9I{|!fY29
zTbU&fPE$nI`(*sd5S8w=kmTgA{-KC7dS4D+{^kug)AanY!J@Y(U(l9y|IVkYz>z!u
z9JN&VGPzUazCx&sT%{jTR0>W<W?l`y7Dp_0YvKo}ax41yDcWJh2r3Pj=>LxMNJV#T
zKmO%+8Up-vdU|%ds*t3uFLTQIkJMd(?EO)Ye>O30oOEWOKcr3O{4Ae7-%w$@fyA4O
zS8C{EwTA|9>@GyvYz=MQkj{li=fn2i{stn9NL*btIY0WuDB{zfWRn8maGaHGzD_5i
z8>w-OHkLrx0sr$LU#w~h07fn6uSNoY*vVrkuQ_6PTwFNT%;Fk4+}O#5IQcq7OLo1W
zCLxMt4h3R5+;|FPT3Xr)WPtzYq5B`WjS384!hup=gbHCt4*&o7XafR3{*eFQ3~02e
z*x#x~lx4w~bWXp?siSUMq@VrwmaZ9-WG`fsk6aY9SM|oIcgEKlTIhGha~h>P^x<F}
z13~<VXV~$T_vn8Acs*}V@;j2&|M)1+wG&$F$7FCY5u5%56VQx*NIh1guOmNuv&U1K
zA=P$#i4;MATpIMkR0de^57sy?VO!RZ3R|Q9p1M+kUJoh%#`(l2`$I$WWk7BF;`K&=
zJM!)d)l22u1-@gL4<)^l`nE0pA3zY!oUEyR(`1HrE7kgB9c+ZJZn$|I?JV#`Hu4_&
z`Kq4T;4-VP7=PVJb*4eZc9$p=czB~P$N}G++Yc@&Fqr$Y&LQ^R#&I$W?(0?9(<OaA
zw$j1P?eps_N-XVTI@<Ll)p*C2vDm8Hf?cqkR^n>sCZTiI!<6n@2>s^#FDkywwRr0)
z0eiI{m8f#OuvI+g&lT}oD>4?5Z8F&@KP9?e+AZaPWtYh@t$#r}93DK&%>MyQNjuEu
zw9V0-Uj#0_);Sghf$qYgTbB9BW`^|ua?etL4{A|UbAo0wWETGk%(H+sTWLe0#t*>q
zHg$DPP2ZMek_0Ki7A9hbcb9{gro{4vh5XZHE}I41lJl*$zn0VYd0PZ-{|AV<4uJkW
zhhJpT{nbt{{sWmR6HTFi#cZF9CV2$u`I>ohUx>k7+L817cgv`TcFB|9(ihMl78AnK
zw{?aVLGNh(o<M!}=!^-dXvhjxJId7QD!y5Rr9Q>&VT?-r`46C4{Ee%$hps4i{+04k
z7mHjOt#zj$@5Z)NktNL`v)XG=2$j}1e`(=83*&7>+(S^c(EVxZ>dke7?uCUt-5gi2
zthn+a0T+nn;32^O_QIU6u79-mL3hnTb4NPK(AXiJv4pvxvJcRTufH%rIH;fF3*e>w
z?JwyRRWHx)ZUY<>d|OHy>v?8)ewI=wB(zr9W=Nc=K3+BlmIEHRM%T>#MBUvX$Br5e
z)Zvt;Tw!KN{DaGd0m?;5;e*9aiR>5p+s*Loap~RG%`x*RdP6H(8mVoz?9>ybJj@n-
zp4OEAa`JlVX7)?nF@9k&i?Vm$T!0ggj-fk3Gx2Ka6-0BO%N3ZML364*wAmUEt@@Bj
z6><b(?otqk>ctt~h>Fhnnt>;`lr2?pQxk5WXGQ3(T1o3z?y!wflq9w#%G@R;(2Lj1
z`$&KLm(yu>$1dv2M&|4gZX#XjRcQvksie^H$G=5n9u9DkQ;DXV_KR|-;o44AURc_(
zX|U7qKZ1|NR$bBTK<1h>-j(V`aEkWVimc<1r2?CYD1_>4gwX~A{3hsqwX#1SQ?gyy
z7+$wO8r<zw>H13C?w8DY&o>uvHR>Pl>yIV>=;MuT>C7~jHaO6^Jo(^d!hRfR<|C{F
znSf9ep;f&*4huO817uDS5;m1yq5O9$I#SMezKrmQi7Q2m2LE+R-1v#Fmr{FBRqZ}6
zM9&y~&T&@pvEWP4>~IAWsqY$*wF!zU<%E>bX3!!mdYI#*c6v8&e?|1urAXcGIpba?
z7D5{-0(k3~FZZTiC{BsNKZId7DpJS6F;(7-iyUe2)j(ws7A`g8a)o(?L3Qp%yjYmE
zX*)u07ZU9RZOXR-6T{FG8rtE3>$=f$p3XO!>^wA70#B~*eR%K0TTaxaG9EfIUIz1n
zb#Y<EnBdu1!x0>vlF0eQ#iU-()NVyBNp;p!3?RE@mW2M!T)C+e{1-~h2ai&H4wjXX
z*=F}0f}$(^eW<>btv%Y>Y;O@-I;8A|LfWLN=q;w}%ix=G4oYie$)H)}q#AA92!3d0
zk=d{C++s8j@;v{{bVqU;)$#XrV6E1uyGa4YEhQa}P1ev0K}xH6W{l9*LDj0~4)jrS
z+L@<H$-l>cHdvHPY5&Y?VDxh(7Tw*Jd-4y}<%MrIaOWw#$qiF#Gjy%$7pUc+q(RIH
z6cm}s;oG8S=xM!|2yJ7hJP??9+bO#~7rs$rS#79;sR)L#blc0t&)?NNPZZ|gl`W6b
z>vKw(!#Ci@U-$3_#5IHJj#>+|1-%xPqr~Yn`16xZve2k~Z@_aB3)!;l==3fbsT?+B
z1#LF#xiWG%Qbl^ob`T+OIt+4ToGxx0c5!6j7X)>FT3uaf)@h`4>RENMPkvBvI{JAz
zuHSDl!qgzsG{SSIfLYcJl<1#%AG{5p?;Q1jFKTrTbBa)%#g64WmYZ^9oM>kNC%E;D
zavf&s>&+uZ4<qLnOIfr`DcHbt2-fDaGCL|dPSN^@uKw@0@Dyl*+N!UU;<?@deWuB2
zRNnZMl8HGhX3Wt3Ap(I}60?4gWo+Daa;A*`i>a@XTQD-PNq8e3ssZ9W)`NY1uQ<c|
zjNCoaP)ns7sQ28+tub_cE8Z00{GJo%s}<_*pM}wv?QwYcA!mw~ov!Kq^t-HP(#j5#
zu%^%rMd;7cOcrQcUgetLmwz|u^ydm1tMRvQOe#GMxbpvz8<MOIgt!UF3~%m+tX*>w
z$g6eCGjliMU~evcQQ?YFKjKO))N|FJFb~#hbB*ssX#LALM-w!c0vV6@dbIirW<jW8
zzquS&ToJUr(C~1NrmuN|2zuLdnv=SY&Xn7#wM(wQ82LO@v+8FWdTetB=RB-7S@yQ6
z3fXH`s>-)TKa0OJ+fOsPy1^$hp*Dr`wkE>`T5Mrl=vLbWX`H(SF2Vp(bzZ2Lei>T1
z*V*@NSf#rpyYl)JfVGYb2v}!Bg7|h<wiAdTILl8YFGSAbo%V9OUz9l^$P#ATWeu^?
z87UXX#}X)RhdRe4#mvnmn>dMX>ZOrB0%oxxNS+TcjdP?ifHE5<N1yqgaR?xzBB9eT
zSE!m(Q#hQX<tG5Z8Ug5rA1&*+j>yBDKIS`w(NFP@sPg6`n-WB1NW=J7FRKCEnRGH$
z_uh*IYxFr~qjyDIiUYL!nN*+S9P$VKs>V=4j>Cf2&Ynvlvc3hi`pMji{4x{|rNZl*
zv(i`$HpOvgf<P}0=zzNLD%p9);kJX+JWh$=^F}7??_t<D8hx+sd?Ic<wpaC(bHnvN
zK_Hl3L7&UGnt?T1nB&|zjS>C6OvQx%dWL0amBm)jN+Ep?rhXbyJ;{2CZ+oPS`I#E?
z-P@r2KaiECF14yece&B8Z4feK%Tkk_E>jwj88rlQXb+d!^81XlpRPGOITy=^@zIgK
z%{eLKl7zNQSvtB#UD}0bkl8DLyV=V{=)+hR&uta;>cm?<ECT3VjN664!#i|n*na?0
zdZ5Lz|BAd-utDIw38^f4L#2t&Do7jdFD6X{dhMRumHm^!svd0eA7FK^bXV?6;6XWf
z%pL@eN1D<%M#xOpLefrbMrYYHbM{;Exoh5*mM^@U+!epX6vrJ?xS?5{*L&!~ZccRb
zP=&7Oonu)2dRvt;ELrolJYey@><P$v{@!J*fVfa#CfRk-y&CK$fhmw{^aocj-5cGi
z_4rgZEbN{RXt41TlI$pdWK2M2ds)pKAoG0+G_%}8K`J+E-xq9<uQ@to>%J0D>$eoJ
z6(cz$z~rWXL-_(EJ3oQUeodd$g@Q!Vq%r_8O2cco*0ee)&MMmxu?-xP?;F_qRB+Rr
z>{r$xRv*a1oUtn%_bcl(g1CWUh^-M54|$zl*IYJ8)PqQo6<CL<nii5kdn?G<jwKCe
zMX!m6fhnbv6f4;xb>3;}s$fH9N2;sTKR!v;yfQ#jK4hnJl6022FG8at=cK**sHIFU
z_CYGAD(@B7;OoTO^3}-eyDAH%XvGCYpJE4(X$43i%G5FU^=?QTF8>50U%T={Rl()$
z>f;<!ev5UWhiWBB)=p2_hWhl!!-3zB6CX?B5nsxVul=qeS7wT#t{o=1c3LvJkt<Er
zNI{7!Nbj;lM!j7bjUnsA%=Schdi1L96d;JbaEIRU{^^$vZ<=UL<7!|T1^3-ubtR$x
z1@4IE)^F0EY1r<T%%Wo#=B&ld$FCS&AGSNiLH6w-<K=xPYR^_t*DDnCPn9B-ofPKG
zn(r_E7$`S(e(h$${!)535;Ps*v`TnrMATc+9n7sWrtP=QCl<jes%H@9E!1HcL>A7H
zi0K~cGA;Z-o#ycg|383V-Ep#G2qVw<tH|yz1RL45#7X*vP?!1@a!BJCzBiY9Pah}<
z8A2E7<uN7Z&^6I@MwOV7R0L_W4oH_BdooPiFHI$jzi=G<NK7(hd$fOkpnbiizDw&^
z0hD{tjuGHRAG<rzKD5Egt!GTrdfMY%thCN*Q*PjP>(Zj?p;wSEbM|s+ZuN7~IST^%
zAfCv*brzU-NaYU2=<dS7z5=g7U`LkJPR5Q3mn|KR=VzSKn$FA2p*k<MZS1!YE}j7_
z2KuM^*QV-H+~!#;j%jbTlh%`b(jIG#=G_$P9zGt;v~1MMm;D-{w~N>8q3+JK`bvg<
zkh<gZ1KAbzks~sblC@hFR9<X@gs0~X?8lX8(mL^ujy`Z&7ME$Os>NAFM|R>XsZQ{B
z3t6W`-@}un_J1s%TedrYbK?t{{XKA|FDPP@^-l$EMREC+m-w)vtyx(obNq62FfcKY
z?6ES&aFs_xv!3J9gu>w6m)yImvR38a9BF+Diczog@$A<<Nc1I@Mai?dVzlgRpNEe*
z=hmk#<7SjKz5sdT4s$pE0`-X-|50^SH$w(!+upV%-5#@;s^AhPrCMZeO2>AyL2kEL
zI=ucidG9m0x=Ll%Ig8>Rpu#f7+!>e4Y%i$Gn$D%A0S^rZ3;(d!kEUDOAI3OQl?_I>
zJ9^(<`m6WO>0B6YAlUJVh4J*N1nPkW%mnb3SFz%K$D&qFc?-dYGh&tfNkpf!Diu#D
zYbcoq{)eEkJ87H~DgR$~&6#fve%QaKxvIYZ=s=OWHR){_UOso*Ri+jCw5j*H+xI*>
zz^&m7h7&@KbZstvGTh92$EikaeOR=a`eZ1+O`xWA<=z2$`x8hD^;0afZGgY3eABG{
zE84@>`?F`(V&fPKBA*lT@GkZ@QJXpI5Aj@I@dRVa^Y>7ty%RI67v}EYk@k^>D^TKV
znb9|vE_ca<FKSKm+(PS>zxK4Dnpj8X#Ac~;o?YozM8k&N+@(fk(Alx;SYYB({Oah1
zm%~k5O8d6=MxWy#wGX}6)hD4NFO2Syp5z9>Lu%o$7s(P+b~VZ`-}hB8HBXFHCC;}c
zNCkzRK3&(BJ|=nlf9vW=cf?u7y+y={i7rT}VHAX8hm;<?|GOZ10on0I+6G)qXmQ?N
z#bLUA<2VpZQuWdtbvmH1{f${*eE(9)TEbKo_wpzSB+dQpRDcrktY-S0^kLB0pEzk4
zh#BI2y7bEULyYz-a#G*XyRzm^D5Z{Q0}nOr%XH~2-4N*aFQ*+%VKMuRCNuK&ZbSI7
zZq$yKZ3t9#d#j!*F_)?)nY2L3q+m0hnOEW<UypJJcA&cY+NP(1BQFq5&=!!IZot*r
z>46v6@)Y`gF-}2QxA3Z(B`LGZLed3vf>zmxZ9dlnv-5U0?{lG>CW0y>NbUS;G1plD
zL!(35BrT-UUz}y;jQaOgo0@l)iYh@#_@F>$`P8HV@~*9kPSzXlhI3n^rYJ=b=>xb|
zn#(J*b(Y|J=5Z{vCc)p9hX%v}HfmAvpXP|U2I|44ieJL^dlhWm-24h{7=EnL(xZ^)
zIip(yfYP4zc3m$_=n29v5|20oqcuDS`gE5{(pHU9(H#UNC9#J%6#J{W4^{O4{VXT;
zmskL)(bU$4rLK-@(w;HZ1$g$jSQ}p_^2Rh+wYA4k+A<OgZFmC3QI+yP|DdY2mK*H>
zk6Dk_C(BI}X4Tw$j1D_n=?-pH;r@*;Y+EF_-(8oTvaW*nbDQ_UNQgt65f=JxaTCHC
zgGIz_?I~_Z+dRgML1jHhwlDLROV;5CMzkS<0b<j}ZUU3}T~#|}q`oNDzMaBePUs(Y
z3V<o}+l00@8OMFKEp&I%QFmdw6;9sE6usLis_~xaOwWf<Th%CnSE|%ly(5Q+V@jC|
zEDM2?>iAv0<B`cG^{D9xU4x?5RK%zVB52mHF~P!51^~b+=lqHt>cz<#zr#X5zm&mr
z4I&mQ>Wkk&S*}L=7WDHQz5fL!?-8ub5rGoJLH=;5@&H%l;=^9H+paHtD*e1sF@jIy
zo%q+qhqDy7Smw4W!=v$3?)2D8bgX*EYa)?a(H@}@Qa#4xa|q;^OFyJw)13tNl<fLe
z)MA*Wr)rOh;H5t4lxvuMM=EK&6L(ep|ID3Fe~xf#3si})7*-?^pUyc;%ztOt5!jSH
zLPk;zQJ!dw4HM7>Bkcp4KQi!bvYEnHH_}nYhWx+c*xm=+^lP_w3O*0i6ZlKvGLLEG
zpxwclK0udsqtT$)Wo*+6DU>_qSdmH|C(49D)G|C+qDA;VMXxpzuVk=)l%#-lQqv#(
zE2M$>T72!E>zn}{q!@Cdp>6Jrt+S{;wDSdbZz`ORU7}1{<z_Ka%N7cKq|EGg>j?>@
zrlaDrp4()1N!Q*VoapfL?2@HMf-`mv;Kl2th5F?3`aeda!Xq->$Ku<P|E{1<yk>i!
zYWA{2ihn2gjd3mZ$jDHhl#mc4n)K=yv0jiPxtro5eRxfI*h&$RN&7BP^kH{_fyO6P
zPR#md(!kfP8Dn>sRxkVGN4|fU)kbR)D`hihESx;1S2bvUWcE?%^GFBD!3F&<cnrGy
z=%E<yNVhca9~~P-eS{gB@%3h+LDa6@BB<c&9fD~FFI4{(K0T-50c)|;a@{z!CfN_?
zv(zK)YjtIUQL-pcjv(KPgM6DDEQ=srf4@qS!iNx-r2T3~r*FMqa1d*{V<q2>nW^?O
zpf7(G+3wfoYPrAUCnGjoVBEs`^ORKe)Rc(JcjN}Br`ZNqZ(#ZuJr2ds&Kcq8+>Dag
zwE8ES_$wbU4+o>@)viJAG$Pw(oESy;l&zDBTVCg>s6lLO<h7vU)xp(us^4_xEha9I
zz8Fai5wv_Q-bR@wqD&e3$Z}OaO%sjzuG=Enr4v;}%phvp@l>88I;~*X@V6_AJO}Iz
z7T;sC87pCbk|PLSom#h&KK*|0znc+5zFO`&DGd$se213k#p)Uj;U?>XCnTo3L&CpM
zlFNc+jkV@q9kghW@JikRB8z+x&SPPAr}2}4{|RW%9Vy9g<N*HZf2md2|JA&ChXt8t
zLoLm~)TzvrRA4ONt}_v{)QAEU4nSJAMk&=9SM-7kUJTW@lNeYE0vOy}4qD^((?TMY
zlAWpO+q9Qi#7*OHa##t;sQ1csSUf@%{DRu@<mv_~xKGRyw@46eK$MOxoDYW0>|<Wz
zs(*paODutI$WSf*37aMfx)KZ`Z?R7!ssBE6{$5P~DcgF}6CnvwRMMR~cO&S9^8`AG
zAWYiIHpGrONISHUYju(#g?e71Lj}j9W|A6Y2upG~b~Uhcp&s)@ZX=RYDsw0xLawQ)
ze<yX)&*|88jxM{;i=HJ`=o}oQFN$?jViP|mxKj|qZaRi?5GFclXp4B9{hY5S`zr%s
zbh-P@sS&}vhnTGa0dsc0Z|X`gbC?1u>yc4^cLCF-e(Osst-1L`?>jNvE&a{zs#>5i
zb;rQ=KQiJrwE&bO*x>x?<$Rv+dotclyYPa$qnkuiH<78eC75$ishkd8z)rG1P16);
z+KutIQ?q!NjVSt!DR*MQ!Q1V)8~4eG&<pa>&4S1JgTXkd;Q@5mHfkdh1bOGRIO4py
znpDL24Dl>7)czDZ@$gX3|AQ1oAihloD;e(px@M9h=%E%V-H2bI{(G?%sms|xd8$ts
zBu;r8<_j|T;JFtj0m<wNA-oyj&eMN$x(~N}$GzkZ6d!P%AY9v_{YPG1MTkxJSd&U3
zk`yw=O@GfG?9g@n$o6M(B#wEoJkl`*NQVE$Wei3*#=Mb%U+^vZt;jn#Bjk0P<*Y!L
zpqm`f{!Nc-wp4=tW_#B5N4cmp@QBOZXI!VnKd$U{ANbr()(lb%79bx_dIga+pMLCd
zMZB65ke^o?9rr%h+cuQoR7LnUqce(f4u|!;Z^K(8Sz_0jJ7bh9Ml7!5%9Qvw*eE#H
zTtClA(tELyDw1@hy4*%(LP(t{%nY?(sk(|wc1)o4;RCKjv(cY9)UJQ8l$ADawH0Ko
zk!lCZ|J^7naFYSPb8M$1t6H@FU+5udi($CzCCE9FMamzl*pmPbkuuhFI2qt{PQ%%I
zh^h#XKck{#f=<Wb4O7)}0?@*6?n|r6C(-a{X49EcU;sa-7Y-~{69D^#0-FiIguQGM
zz)hy5@qgBE{%1Ys|2P)?-&L3Yp}hRBA51Ziq>MCSe1}fp@8~T5^j>(i8K!so_Xe4=
zk>YBwrl&;r=g3CBe>(;l@Baf7#HVU62Y3&|Fh-kN=1Yud&iSSEo&idjeTL+z+iD)I
zhv}Jb?c)Md8zo}M>8F5JA`Op*f2P`MXc~xr504jNka)vxP1TgS+-y5Kl5_+pQ53-4
zSjlH>vd*>2)?JBbe5u#p9;r_cI-xYWo~FpYJ<r=(h?*5!-J4g3k*2c+f;P=n<2U{A
zU{KXNYtq&6X2$c1t_$MF-yf$*Kje4i2H;|uc*r=$K0=U<7klk)=)#kKK^dL%Z1|`J
zFH2=0{}qSocPqs<IyT1PbU5{5_Y;~nL;0R!)%AXMKYM~Zc=#843S(i*%~$r#6KvV&
zT{`P1?!Ou&g58=OMEwbi<`=VdhM3}I7<{bN3VulSc4phxr7^QJdf^;d2yR=_xbT~)
zP@4s+(4bZ&6)1qO9={oZUb(=M2IM<H)$ZU^5Z#z-`}WV!D@hkei$9Dv^o7n>5%)lS
zmAaiYEpYx0Q_nZNfR%|sExEiM=-IFd!#ePQCB96zEt$?`KR3j?^w{9xe%8jxi0^7?
zc`n-FE91=@?G01-LVlyDRec$0CA#6y4fYNYw?P2$Q@L4U`ULG=!-u}dZ?t~|s_AM6
z{KJGD8G@I9o4KcV->Cmq>cY72zd%E8(gKIf_NZ3a{RKj40??0_2&ztm65GdXri(@J
zLqO9K)|(-0`ZKJ*JZN=`*3wWSM_gL!PVSM-y&L*I!Afooqy>i4aPJMS$H)>F6ZEWm
zVba!9MKaVf{p(@gMtUk=yTuj(1#nC9aA`-%sz&{{U`dzzqA6w~E<688+xYNLv`gar
zVuSOHUG0N4b<58Ki%s>VNrlLcxCQpg04UjfL9kSC2<UB5{AQYyW|r5C5B&l|H~Ruc
z@AxmnCr#IfDwZ$)shvdDhEvP0)&JCbacI=#MbxpKXqg<H_>2gngf!`>RH(T=t6^G9
z%B4`uUT*|6{te9}YtK5TJVnY)MFDbE%ol{MTt7tOL?;E#naU^2T=;q+RZX^n5*;Zq
zj2(_EMQKjPL|KEu)J>Tcv<1UOwA88nF0xdToYP}g`o7}b_myt_yFL|z(Byna$yyb+
z!KU=qT6Tn>j6-jn$htPI_t;C#;LO=4zQjNCS@+{F^NDa*<!<wupWeg3=C+IxY7a>z
zv_7rYW}_JJ4Sh^qpq<K%kfN9tv&M$asooA<l1)JTL5GjHap~9u;lek3gOVA`NnCIN
z2=&3>x{~B6LMEtIZxmmiHx&o%rnX&o^He+XOh>}tfj8I9&#_jKC}{YG&Q5eZ|5_5r
ze#~zX95KRmr?RI#bE73W@@0gj;1<E`j!jk57@v8$=6zzo*q!z+qXpy7Y`;y5!dJA`
z2VGUJocC+raVZjUhR%8u+I4i_Tu&2Xuq@h68IWQn`g}i9S0QN4Rj*`D*<paN&I>h(
z=wmgOT}%@IL8iJCyfJ?<6#U&&zix#?7j#yR?4=4itIJjBz-fkXfF5Yikfi(N>jK#k
zb+z4J7w=L8+Xcx0#R0j2vN=&E-<c?a>_bUnLq0U3mc{iHfWC0!OeM*;;IhcRJw6`R
zVLRKdql}N>F1;6Yppvnw@1k!tFIF6NjfB;)+PRIRNT2DuW1J)`r$2-cS!7zejO81K
zTz3CJ42rF_w>ULT(6C)t$fs1U^jwg<;5T>v_AN1|Q9(TzW9D@BYFfS&h)@FWMU2c=
z=CVf1z$h#mR9Es8dgeUJ+j~$PqTBQJ+go2_W939ad3D*`z7Nf~Mm;|y6~uf&x)Snx
z!$#L)G2vsNw=K39vWH5lM*@9sG?#AoWo%6|DYt50i$h1Scrk?pvuLJ6^_N^M-ehZL
zZU>^-bU9}z@w18<+}@*9r=RGM3>hPX=l<=~Jd^0Emm@sr@2M;vD+YCGAh(l>zsOz4
z2BWCmevk%%k2%b62lh<(Vc3&2gkoSl^n|pEoL^XbEL!kZYJ>f<4_unMnr5lWw>=QJ
z7KIf|BzAK2wlbuJt%5*{yPzW5PZV*WYxOR$scFwsvs~zd_s`ErGtG(#!e__n$Ae(e
zG`#r?5Fxhcwwx{|o(QOqqV8lehaA7JT&xlOd&ni$E&^Xw-tLNGE|$C&w~6P?eMW5@
zeQ_D;`<>3z!k(&kK+ZkO!kaog3w%dOr_TNTq$~}g8?Ndg8g^uqW;#KZSXX9KJpg2O
zH|D*C=Tz{$yI2cRx7(>22M_Qkr%+U<?W^esE2`1+CN9ESJ*zlnv7TF#L&&>vLVwnu
zf>Y&W44tWL*9A+7gXuXNvlch`hD4Qglj@zbgUW~I2!-A~xa5tXC*p^>-=V^t@H_Xe
zn)LGLnA$MaXGO54=OeX(oeV_ml`QXLMQS2;r~U)<q6r$hD(>QLp)&K#9NxL$Wwb@l
zAh2c|lj@mCZJA0zT~yTXiJB_Ot$WDN_lSHZJ3ORXCkL+z`f6};>eYM&aW(qG(IX9T
zUMI?eS5l`&|2-4FP)FDM6DkQ{_{qt20UXOQmZjFNZoMj3B7^Ln5j`teI9z#qFs5Js
zIJ+C2#Z`z&LnaBoZ)-cOiO&(IECg;h0i*bo{y?g%eMJ>FB%K<&6d1B9co~}&Iqh{j
zSV%sm$%#m1FsKeCILEHL-;u9(CKFISsq3q}-&v^)#CwN@S~Ik==P6p*gdxL}2UQ2+
zhrdKqFbxvDO4gCAzU(is3^&kn(?)2T$lnmTSSkJ_vk?^3{<YrhZ77HC_Nzjbq}wWJ
zdYL>!>-&8*uXZ{@Ae}hJT3wP~hZOs+Vn<LJ`x@o8GO!F6oB-4&=M2(C*_sH_?XW4;
z);vPm0mmOtbTBPd!@M=D=Vnuk3WK0v?Urg<u(}pl`Ds{O3-u|fpo?sP84V_zf2F(z
z<3fEZZ%WtTjy}<T<Knri#jEB3Q)gyFBSS$5e8(<ZRuEyY1j`U4T6b0>m~t@1v|*SW
zw14JyxQgb437@KGgunmf9dR*y#l+p!ttBc*<&jrZje@RYmwedg!ky3~QXRxCz%a=`
zsp}ztNXcKwqOAJJ(k?qBFf2*RrjaXI9rM1jO}R?Tdoe0{&l8n`?n*wzEb7|%s^cdB
zJ$;0{gCfCc1}Lr!KV8#PI;G%_%jbu79SGvq1hKs4%U4ds8$MK$Q&1x-H&Tu|$7+)@
zS5?8;L^*VMn;XB2_NW_b!`j`$S09K~EGU&{eIWhC3zz98awE?nRg?4F?4kcivD#k>
z39P+udLaAY1iOFH_|)TtF8>W~kc3B!Wm1e+qAD@;R($bql%KbCsi^DU-$AhCOq^zW
zB~B^t@a0+6!=~#2|2@O62pUFuhq=2djl@I)O^I<y?0N<Ejnh1;rtd=?zJmCR)_E*p
zSc20EZum+E1h+%V)^i>1?=NhZZ{dA4hgeMaF0#C$Y>hSXT{Qa!h}j;sDz|;JIDO^k
zGB9MkK!UC=jL1x1vF#QwXYV^|PP1@sMs0(Q9nC`QY>fg5bkE-heo?G2?~o=T=B>XU
z^I>-+e0i}jtDG!6an3H`CvEzPu~?O&&=PZnbF`(jZ}OIDJg%ZwU&ztvc$~`jV*OJA
zo02hV`+mS|6OD^$?xMkp7;eM-cH2i=f7^0#ZxopKNGlqICUXdlxQUr;Bl1W|U{C$m
z1CqlCd)qU=jgel>EXV>5^VSJ(p#ng%hP*1XW-eU@Wx~@93~d`YISdei;--}@X5V#F
zcwJ%P=>;+Mqj@y$-r8{wpNYv;<v87j09Ja*ud1i`IEp;I4Z&%g?q~hA)2mOt{x!T`
zr#S!CmHvG4!afI5#iw(}N4;#9Ls!-chz+9ZSUSu{4sHdt4GUFwGjd|S@C+-`%p_0G
z@wi&G$K@~%_=(mw0f<!9a_l>kU8RA3tQCUgleN=?)@gDFelDPZdyxy1gmSZ{zgt?8
zNko-gqMy<sNB1*9jET=8pZGV?R?0!OMyU08g|c!nPF-|Bp)DDA3~}s@*3NK5j@^fk
zx3$8gD?MnG2lKeQ+wwi(cW|Rm2#!z4q^^|~7*$2OJf1sSgZ^E0#7JoIwlNd)Y-2@7
zXBQj8$SKHR=%78`*4JPE&8K(d{7I!nM!Chl==?%Ta9Jkhnda+-PinNM0Eq%ldAGeU
zi0^cuw>ncl{X~v<EJSey+;i>(srr1kJ`EInzpD+Jc<L~FCp}&x@4-)Z92S0JUd<Y|
z(DE(*yNYl`@RE8-p1%)}KQRsYzquECYhO2Y8h2^#?wN*M-^l2jY^qtCvv4Eb+^W%J
zTV<m1#5Alif|2q=2MS=AcgTyo!QK3ML9&n2N$_O7MrT_%;p<+#@zzC;t-zf+&jQ)n
z$m^_;G}(HG>pgq7@LzFfD-A9%#LBc>+_<LhO3l%IRzqKXy=}A@Pq3jmwJLj=!#*~)
z?U!92+J!(KdS~yc8RXW0GS_K`VB4`7;ebT4$xl$UQ*LJ9sk$#agKKL`9X?g6ad5$%
z+=&)}^yoLXa#@yKHnuhct6x-=V_xc};=kW#utXN1)Gnh3J#06+t=gVTmzz8*Q9|V^
znlssgON?g}Bvb%$2}pnAq|Zr+G3&Qjp_eqk=%ikIUyQ<F&YHAImUEf{=W9r(o~J)!
z`eU+gBMjtmsx|YSymvvq)$vI8QFoX+JElCd_3<a<EbE6O?7-sP_ON7a<>e=nx2tVm
z*0M>~doD@tBh7uv_HW6d7iw3Z<6d;qfo21)BoU|JNb{t^c)>|LRi+0u(<*DryJ?Z#
z&pl?)*vkt4c^>zReWua$J&cSC=6Trol|?U%>p*F?fff8_bo`<dccWC5$rQGdJskYY
z@-HS!yxujXL(ezt<E#Rn8T|_jj`LWaBCG0#{I?x}72>$Xwh!?Q;K$%iyd<VYNjW+j
z1!q0dnl4@Axy+raKe_axm+<@aD){beQkBXc{3odC_{*~a_kVy`kBSKKQB<MX_usE2
zhk~IEWjsw~>b71_H_X6J!q~-5I<)?v`(&?sFBg^jx2_d|EJ5D0)e36WA17c$lxBw&
zczM|SZM<h(ly-@}CuZoXSx_tQq)L3T&80bBlWx;MLhW?QO}_@b$K1_lH`1+(y7Rce
z-Lbe1oe&`I$$B@bqVJdOqYmd_H~+S!<_GeXcSCr1dCHreP@A7ZEkK_J){c&zu2jZ^
z37z#_SKQOv&(W}$+NSbvZSi9N4$lP(==JGWag}Nw-7f~RvXr^)ljv>J?4<dr4?<ZV
z!M=Zmr<y%ym2TV!hRj+X4c(j|8s*;1RR?U4*_paJF8ALbVZt}w-}t<{y9>X<tZSq|
z>Qeil*a#8n0C;OX=<~n^#<zt#r!)5}H=Ny+Uu;JfxjXC3>eGJazf7YGw$13iwg$ZZ
z2t6?tZc#PfqQvV7H}ff4a5qM#&Xc~pA@EVhL}OnCo*jvdVl6hE_X>g}_w69BXcD94
zJb`l!HvFVbnXca9lU^oe9TaITfjB^vq{>J|VPz+0CGUwB>#aC0+Z(vn?zP`-J+@b=
z^uO-A-z4S&e}dz=d)qlRkc;FGL*XPP;$6=*rEKJrDk@4F0<fNG2Y~3LQAbC2m)t#=
zik7aI`mog!XT9sSaK!r}&&a~z_Nhz{o7HXHFfUKB#g5l4BEUFbr*yYd_rk}AH_=KU
zG%6YW`hU;*EfH%^mEhGm^0BWCPD^j+ZP^-2VY{l5kOzu1GJMQMNdirK+O&V?cKE!*
z!E+nBU{-Cyjb4N3wuJg6SLhBoVF=FqHff@bz|<$La|7GCj`ARlO#4bxXOe+xGpr0A
z)YoGkt_J$~{G!~6!=>NM7NPMVit+}l(pR{bG8eNw&OOCK=FQVvt;jxgQ{OP&@07bs
zSpivl=WSzDsbL=*qz_iUCZzphZYOEnQdGnWx@w5?`<R_d*0B<Ot$Z=bk&*Zr%gA)Y
zqAp$ZH;uK7;0dEOlsM`o%tvrvig?bvp)A$Bgc(;0iY*D8-T1X3sL1%mkV>+a3V*LH
z-XX#vSYOoP<jCyH+0QhMA6h%khrzIuJDR1Yl)5~XDKeYRNsYVnb2V^d$eJO)p^Y68
z!!TG|(ZX1$UTmJFMF_)X#W-#YJ-_KqrkV4ag6PbaFGfG2T#aRHFAP2@b}lGe;2)$P
z0Lgk<V#<q-krlw<_vVqTq7EYY*K#T7XD$}p_swC5D@gFHJ1h6Qro7hf><nZ-NFJZ4
zGci?{d%OB58LS4zl(JDG&t=|f<SeDP64?C~9mb_`T*-EkcfMZ=ar~Hxm;Rfoa&Sp^
z99MA)OQ(9sBsvVEb%0<mMbbrifjlgfvp+<pN+x!H2gBvmBpCbCL<&``d8-jFv>&h%
zP+i2Nw>~0aU_YCQT!H$LONNiXARe_!1e~5!mCSSrT5dHyQ{(3;(ZZOr_n%<3umL7}
zUrJH4pn0C}c6an`4X##cdla^rlEBg|0tz)>N-Sndaub}Eu$z|YzsE50=xp!e^%HYL
zq&llULNXB%B0A*YVnH9wKJek^*l`F)1+Jn%%5EYdhM=y~kY*yjFIm1#t74p$1;_Gz
zX@>@u?g!NyFsVS&VM)#)GZjKrdqlEUXLaDAxriSl>WziEtI4C+_*=tle(6sIL|Zz$
zQC`!E*X_%xWulwh{skm0ogIn2Gf#n|xXzbDWYWhw%Fmxl+I*V*Q&%OAkY3>U)ULz=
zB!Cmdue4>Fh6Pdee;Q(ZsUo(8n0&laDa<ZsOc;~ofQIU7BFIKYHRi)=Nq$Dz!YvZ5
zA|cfj!ubpH41d|F7)Q}&GXN+fCe93rIuYUrmo+T8=e>D;GQ9;c)uv<dc)Z8nw`HB)
z$frYgY6hBH_C3!K`*MWUJ6e)`cK4k_uB0TVc=@`OX{SiV5kU^_`4k}sN}W_@(x=Y!
z>HT)yFd);5jSYCC#P+p@bif;vg1xVSl4AR{MuoXo(|SwNLNA~FV5k-4>_+8d46ay^
zj-sOq@z}1EPi06~SV?2s*`|S&EjuQ#wmnV(cUWXdEB0fkJQPHFX`LsP*&)0pbr<XV
zfY?)s;A4|GSgaZc*e(hB?J(Tc@X>lNcI}%0n@+UT6X&6xQkfK(L7N7)l=Eu^KxwTd
zt~x!gwDU}_)z{Vaq2|H53#RrNtOC-pC+ZAh2?-M*J4cumq)#bmID4?>8ofDcvLHH!
zU(5K>COG@%!j7#SE9j{8jG9J4J$~9p;FLcvSkhKs%64o|CSV1gXpos4&AnyTc|!>`
zTGFIzW<YcK%V|vs0EZv4capi?9&YL{LjaW9^-8EEVPbm4p8T3<l+3d!*srjlF&PlM
z4&v`!xwE{-CQTPF#+AkdU3^`K6bUHpM2opBS8{l&$3_0Eo#GeNmS&_`RZSe{3icQa
zZ93Gtj5=bsl~&>j$S&^ok1`oO4OYOs-m8Vb!*?wmB-J8ofr1vRKmJ*<DvjP=nEJt3
zh?DP3^Jb#oi;5C9)d=UZ%!){J&|&Qv!X>zYRX2}+=t0epNi6{8N@M%-bE_FX(2}U1
zVtv#se4*9^k8<a8rqZ6_q6Aon<<o*feAd}(S39d`{V)-7GKSNUay4`Ip9J)`BoL0U
z3fS6A{><Eo44KDi+WC4)6`~J(c|>Y-9Gg@nmcG)1fXlNe&r&eBNzG5wYIMB9STVgI
zB=EZLHnlufYnQBn_r=pX^tf59?_0OwFel>HStTep`islox#q*#it72c{{g8OTa-lY
z*^=GCh7KNlQ>@I7poGD6v$FG3OaIUE<`51cv@}mFsmBUt$fBO&L|1dpuyU2#J2=-%
z6GkJ?;HN3^zaS;^uwIQSPb8QF$}@EqCKx$?`Bi;vC_j5jl;_lppQa>_G%9Pk{fax8
z1Rb%o7Zly$>G|e-^V*?{o79Vs-$y*;wJ{8tWsP!0p*lw_h^IdqNU9V5?)S<HM>*+%
zyB{l~@onP6y}uIKDWS0e^6_uXg^GlEG&kV;Hm#0X$5&7O=b|Ik7kZcKZlIJJvtqXW
zy6;#)-<LxRa5of3id^n$0d|et^N!Ndff7ofb4vRCK10P66{}K8skYY8R~+uPpw#nr
z@78?7f;4@o(w0SbU4^x4$PDbpdC6_C^lwe>>sKBFIwXFWfos_0hv}ad2j(F++!%@e
z<7fGX<s5t_#Z!taEz+&tCVk!GVx&PnM@C85Nnej%YU_P}mg&CjAncFRK2~Rfgwp!k
z=+y#<z~-1mo#qEnkQm3A+ZdEeUVTWD-z|Y(Eo|g588hY_hqk`M?g9S?8Jmb?kb%ss
zJ548|+(#_>Z|^4@vPQbsurW6ssZ}VDZ+u7PQ^+NOYPVe1^V1HkuBDDvFC)Tw4R-oT
za_gzS)HHVv?;-52MmaC_5cW}sGWBMk{$P&0O{gp@wZLn6OTlpdmm8HQj_%0x5?%E%
zpMXaUC;teXAi|LQgnDPnk2TO0ywa$H{ZgEoez7E|y_;J0E{))QYwpy}(|nex6Zg&N
zn<O<4x)QbS4|08-H8g7e0)UCNE7eUG3-eX6s2CP~spU!Cn^HQ!OOL*1KFl*&@(}IZ
zguSGN>;DrvQz}3hh!lauW<%IfoW*d(wP65WMQ45)G5{`nsQ@-d&<qmFQ8fdrEFqOC
zo2)!F8NfqHR{9O{9Fg)O^itMHnO!Z^$c+d|4kW_!&Q*IholJ{&UdIteqzW(*)AiOk
zlffXv{eL4${jd6tU38SImi_lp%&_;q9wY>8`Y|}F&8m8~w29A4vYo_4wicq><{F^C
z3Z?T}vSJansfmV`TfeDR`l38tnps{It@b64KVBF=D+KeJojKKHtwd)YyacZ+G2R;N
z=Paeym$m=4`^*vh=k&_No$pR-!53ssKfPuyqEETgRa@Ur)^vyo8j)f+sjfCVg|OjK
zUq1cI$ZMqUbN0u$EAtmRr)Q(m0lpi|@^4uV{Npo8HxFpu-0{4v*+A#}{DaPVKR+%1
zjq8>98w+tQtmKYCxcjsKUmgC*%&+$@G38gLI(h18YXdlrlpDQZtxsxmCJ2Mf)b~jU
z^1UTe+8ya=@2~D4v#iN@-@etv@t;E-6qtSKTMtl{MY{y$PQ5%5J7p2^kfBevc6ap&
z-@hW^n<$SVza@C2`y<rS+K}Ap;{#mj`}I@0W~ocMu?i#0NMZJE1NXuU<F;|zV*59@
zS#qwlrg7mNi~j(~EBcGPqFJt#(VonV{jS0|ifgGD9>$yj7VebI9XGQQh(yDW4#XCn
z@$ChP@$ljt&u`us@Y0)D)?^y_t>p`Ny(?QZ!<UhqDpBo%g{c6@jZR-0$2&IT68#^U
zBU1Za3Ev%uDI@y$jn=ub9pQzMDaQs^7Dpz_yrW$-F<XBO>9#+|{^^LxpO8qMaQij)
z!qHAI93WuX%s=7gi8(#pWxjl02Ui+`ec2yOJ69=@4Qr-7IFa9D-KCfiEc@y{dpMAJ
zUz-d@PXl5A(<2D96SU*Qryf@;#3Bvg6>XilI<8e7+i0}&zASxUQ2QG(RGGT=ynXQ`
zx1V42>_3F3#-QBSCFEHrR+sDQTXCwqm#~|kDVyQcBy-oJTU~k#Iqp{Iy7WGp^f<b~
zQ*%q~nI_E4*D^a6K*Yih;sq#uUxgaT;V75CZ5H=7bFU_tO7MRRpLgKc5!dttmCk-;
z1c|-vikSTX^6XUJJ@A<AydXY#-CbX@l-=_&jeY>Nz13Ab!(9-^VbqJJO=tb)jR`2f
zV=-ssvZnDhQ-%*0b}iLv43;2dGIB_x1KwC#AnEc}voXo{`uugwK!Z!U2=5qzsWgIP
z*MpCo%X^CR<tniDh6lT<1Bi+jJRBc0aEsYqGJk`)6qj{3X)T~e`kG<Wu=4TUR$C>+
zC)iEdOpSPoB{Bbi+$?_;e~Yz?#tQ{e?x^YclW1Hqc&X&^VC#jRy6st^Z4FunZu;kP
z6Zl3_FWFWusg=ai;R60H^Tth}IPR#ws@xA@Qbccyr}E`XHK~o^J_E!qjYmXKp5<A$
z`bn1DkBTK=_;k^SknS=l*<>L$8en@_!6ej?3cYjv576v#mq<d=xhss!eoT1!l)Ttb
zuROK(rksHX!|Y97xPCnkbGUb5-t=O~`fkE?trg)yHVd3_A}zEHS3NE*_$eW+zF(8Z
zdq^uy(RNa^QP~g5`BSLzKL91mf|)&~apnMrbhJ?>8b`|K?^Qh{EA`;;m6DdO{{YG>
zzrmdci|Ok1)>(38+L+f5K_uF3gYq>}lCtoC8U6QwmB9Y8;9%P~f69^dsQ2Udww%W6
zOa$XkmZ1a+JS8P^Qde}*&WG;<+}*5;mJ*vx`I5PJ4l6n&ls4gH!)cG7P1_0t%?Fit
zy#DFWQ2U$p+a|!y+1{`sOAd6I!L$dnZGuGj7S1y`y@#xki5cz+b}7f97GF5Kbnr-H
zcyDbu$1T+g%#-OR9nYCBu5=hjOsGj_Sxc(jsfB3Tp?$SXpx7(}M~Q`y9jW=e?B(D^
z7a`OiQpg}1a9Q*;g@}i>F+`Z0VIgk7ES2_6ulKUnaNNZ&egAiyZ3VIphoI&;A6Bto
z$?=r6{P)P-f!CQ$^Q626l{R&*0lG%L)914wwXCqhZ3O!BQth`Pf*>Gwv+2rY7kHm>
zH96?YPIfw!slMM=fOnG@cx2q&Y)UF@@U6Fd!D9cixfPMc)LuM$dcjSxzj4*{n_M}g
zFE)kda#!22%JRs%__`$P)ig?LxY2lRVb!_D%%qDdj&Q@bppMetlJE)lSSRV>zFIL*
zn;%yx`hAtoR;2H)fvQ{dq$Y{_t5S`$^BwYm3A8n}ZpK2_C2by_EvFpJHD046kGEw#
z;Apf&Lv`G2<SrX`N<b;fG$wspF~!mNU~xy&hy_rTRq=_{s<LU)<rh|bHh%rrl6D7w
zroPLU_RGNVIX~|qYk??XtQ1h~e8a+7Z}wInD2t+#(gD$@B-jDW2{kYpmZ|z_8oD*4
zno@&*F)5KTA`i*tHJgI1$4;S?EMsMSSpVyCzXg>xam>P5dyO@(&jH;FPWap+MSHdU
zXLfZpK7M_+Auv4GwkzI@FqU@yge*Wx$8C~Lr{9~g&ivqd%Y0y7f7OlQ9YV^V5E7)f
z|HG+XVp?Mgi`;Xf@0I6MHiXXNyMf|06ca#>N3aU@-YCzN>!3UCt|Cg;?u?>1we(iH
zUYP%~ll-9i+C$Z<%a-CtsHLhrt1V}r^Erli?XL>+G-B|Ye+`ngsZ?Gq6k%Q|1QEl`
z`@{{Z@k3gPI8GvuOtoVe<rDR^Ov`8!7mE734Ro@tBLu*IH|{LXy<6FL9aBFX*fgP~
z8ecGiZwNUUDSkUAsluWXafx^jX1~zbQ)wQkhg%qqnA97`eqPM-$c&qmEpXWkn}r-j
zF_Qgr$XaK~QqML288BoJh1z*>VaUBaB-TWW>jgo@d#1@Tqbm7vFX>Xsmesai+`7m`
z{qD&HOCySU$73s4Z8&-w`oHn^RzYpP;k#~dC{A&A2~u2&6ligGr#K|IdkdvdnnKVZ
z!CiwprKL!4cXudWyh!=&{Abq8I@mLNucLMF&gA6HQD*Xd-~HUzwIc@;%v090ruJah
zpJJ_hewBsY>{s=#SOxgOKaCwD&i+te`SCsT4MG4rekr<`!;ttbWGq=L=LiH<SwA*%
z@Y8!7wO{{CMR(ge(X5*O?vWP3#{8K70=0TlU3k&q)pcdGm$`W0u7<zo1)_lwy*Lm>
zGYFOqLWI8_wNjYidjoS8RDOi0%(sdvoBlGU-a+ul652RPUak&64e#>BCB^v9CYoO^
z1j-oV$B=VsCVJj?=nMTCl$oZ^O0%BB-o`6+GQGl&LX`*QQnSW+RvMp0qiv&@XG{t9
zb5C%<2>~I#@}_c85M3|S0%NFMHulzUa70j&{80H~mA)WQ7EGTq&W-MdrmC!?4o+Fm
z)y6@g$b<~oZQ>feb;*cB@O}+)#zZ77Iz*FCE}iS$=gv+aG&6JXj$t|&Dk>5;OG|&D
zpA=+`AOd-7qh}DTMGo%AJsQ+&M8W|sY@*J&sl~*Wy4bIEg%t9qozhDPFn@n&n(m{2
z0n=?YHy{eafoH|mC=<SxV2R)?g)fZAv`JO&33|irID(;PLJ;uiV^>9ik{Y${>XZ#9
zf$9MYUtJ8;@E((_m=I$IuHqJtaNb;xnZJg!Tj-;|p)DRPre}n`6p+^6)5H^a#hFpz
zWP>A5OkrsY#lpa}%dSiFAQlT@rm{yn0uEb9bKCx%O|)=lZe^QBAY;@hR5YJ9)W`Kn
z{s9M(4zNWVsB9&Er>)pZ%O!TuK#BW?MV5uUByLc*STdu?Y{GcK(1twEh>cNT?U>##
z-epyD8T63-Cc+~E!uBU%XgsUN$j4@jZZBbN;_ITk;_lI|4$%0vX*i*lW0lMc(xsN`
zLD8h&cY#S!q?-Qs6^Xx1d`9X{8FxzLzyXbprfZ-6S^TqIl~t(fBrUok*)<VuNv92q
z;rW!b7`2@13@2RIjBCFZOK(_Eq?OQCJ2X7!kE?GuUk>#(^?koC^>4Rtr;WPYcx&m|
ziJh@;4ygS)`b&lfo86Z{#(0Cb_?<N>BkQG~_`*)^8Dnx6KIq;nZX<@eV$2oxO7XfG
zo2V2;zT0=%k4Uw#)9=iPStZu4O)y?}CEI|t%GtSaI}_#`54zw1Csn_JKd5iYfID5T
z)Z7tykrld*?FF_Y&SKmNCF0%2TpmEVzx4aXi{8iD(L&6gXR|HB3Z;Wo!H&OZ20~KJ
zN!l5}#(B*AvhVlU#PURFG!;KCKLI`K>*e(tQHf_2YlT!9jqg-jshZkc;qD(`<La>K
z<{$85T~f<M)4X4-(cemW?##Sn10tfJ%A?E*Sit7Xx9Hl%2T6Jz=%A%jEh+L8v_cuu
zjpb_PYDBxjv2F~ee^uHa4ffC-tC7j+tVupIP;3J8Zi4wIezU|#c4lX&RF&?EXxC2+
zZFl_O!MA^Dha_dGzw)0KX78N+1OE<trTGXc_y=Xy)jnMdF2OqerH^bs(l@!2|IR*O
z{pN+^ATbSolp%=@+m>Zrm0i!)AI$PEZKBGsoJsP}9s@4cO~;+05VC&cmhsliD-`vS
zbu+NM#_eNpiwVcTo)vF~lX+NW01Nvy0-s4-^!|tD?U;!$M|KH?u#WHYS7xXed(z4R
zTE$RF+nBRyoO2*xejQf15}vveQGI-D37;U*Dn^ZWs7`^#=d1uD9myKAwKLuviqRwy
z=Mh7X{5k1E8h#CD3`SU|`z>9T5{yI|`uV2%aaD*VJ#v=RtT$X;a)~lD(}ImpsyO*p
z!|*bfC0PjmTm9{niWq&G>VJS>i3CO04lxp_)VdlwpO5cyEeN$8U{)kh*vdX_&s^=2
z|Ibx?9~r79Y|j#|1RA5NW6Uci#yRYe@@%+Ab%y^vINvX@1p5=TPK%OO>q%_^ki3-B
zw|Z2mRv90gLiD~@dGe=Bn8VX@ca&j$NtHO~=a&CgpMC%2-wqu@AZNi0_x4SUFjJ{#
zzU|nzso1>PHCxlwG`i(4z>U#I2)N7Ud?Ej4`OrU5PLSxkQA3YYh4)#^H~Ba~=g2Yb
zdi%;}zZKP`V$6TM=5#s|5h4(WhA&G@w*K0=Fpes>4s^?tF;7rSO+#uJxrdOk^Q3LM
zUy|g6t-7ujZq-NUVjb5XG(}LO1GLV0TuTa}q;_ou?5?*x9|_!=gMZ8g1~gi{da74w
zN;z}o+7?JC`1@g-&Pr}xBRI-uG|1LsruYzf$9czlxbf2e7@w(5=*nK9bySLr@dnwv
z+bSVEex{i$uI)PcOb2e6s2~)+mbdZ#%%L1;^z-WvyvAuOF_Z&iB`?kYz3+Te1r^8W
zV&Ob8y%!~9F>Wp`Ehv|16gPESi;$|dnGwyn{^sA(9QgS9-)sP%Qt+$Z1bR@2avC3J
zfTTTC`lI=^luYOrYHDu!7WO&v&UZ|r^qWmw(q!X(Ut!DZs3_~u3v9`gq8JU=OuO$d
z6w^|ldb@mIGxZfWUWnc02+@XJQtEf-ly<x)`AucbbLnp(WgOJw$i`L^&eJsgT_yCl
z7vauFvR!tc!MN{~uVAGro|S(~4?j%#El6nG*%@tyg9-I{$M`c}RhP6L&}9Za@lJkt
zX|9|mysjCGB6?ScY!@gD$=QU6K)U`A{d8{uA?)LcY1VrFx#s_I{_<VTxkAa;ogJI7
z%zFc7duTntr?>iUYOr7`hA=p{1i|#B;|>-jkmI9)JL~gh86x;uU{cNUdU1q$Aqee{
zFb=}zZ_E-aoKT);lxrU-wW2d6V_;j`ooqIU!DvQ*$?HWjGEQv(>OazNN&sHic#>Ew
zf0I8+8cO4eLs?s~gG|kp?{fVL)#Q}vei&HQloc(51yhq{NXK=zb8t!D)%5|E1trhl
zu{rH>)$Kuec~#P7DwEY}>F1ujc8qc;d?J6&6RAvh64U>!{12emN_mRu$Z3fu0(I>b
z;0$(1T0HRexDPSm1j^igEs-T!(VgF(y+*zi=4LxbjSy*5qV1yz65~MxJ#{el-2FFc
ziUl$9H4V4p7)2>!ZGb?r&$h$Wu0FEP$QCB2%j%)P-$LDEK7y`yU=0n?_>`FdZ^If&
zv7{s%w0hl$T$nj2kL67J&qwo<qqcK1CG?4z0t(jC_uxFz==G%uYV>c(@eD#ewOo<e
z2VEY7?uA<Av5RMGRj?Ri+a@od)ZEjwZau?&O(1^#km=DvAC*#1e%vb`-u6EUvF;ox
zglMsmIj7cIb|QD<GZU<>QziALBQ0o$ki+6V!qEip_MqZ8H-Ba#L09YtBz`Hn%Upsc
zYM0^qC-qzKSGr+IrcfHzYF9?7rq=om_s7GmJ%*|et}s#$zEi(%DPE)XNU1mKgR@Uw
z;wLlP#JLi!6hqcviI5STHfOfS_7W(Twzo!N{c=o!e=z6$`#;s0??W-^^AyZeC`jq&
zq=S0ZEg$a6Z_T5>x}Riuj^c?iOk2JirC2hk#jeE$_A&r-4nf4`TBgP#=G&V8_T2(G
za|NuGx>=NzfU4~r;<Z=hsWn@<IsLMje(O{TMrxV!*lEPy@etwa7tS3Tprk@iMc}I!
zL0`0Inzk9YS|3R7!2cRnj$6lsI=}v~Zz5`|$dPLy{Ssc-SS6W-2fZ0yGn4J4-$jHt
zA@Wz>68&~uebeEZ4j-hj7eNn=GN37`S9xO#UJ$_~a~nb)ou}(iK4_E4kK$NkyGD1y
zc>|VSY$j}vDG}BB;@t~4Ff)GMHI7G{+CC&g&kddRS^sQH4>8L6q_+KyFhCl%#M0|r
zSAJ9ev@1|XLvL5CXth{0&`vMS*wYx69^IHwVp{hdpO*KB1@)L|VkVZZ=<6ZOI0>Tc
z`M3v*@NBtjoVv;fzjvDeADy=rm9|jfMgb+>7YF>wlI+gQ*^LdYf9InQ8<=AgaTtgZ
zPN^ekLk~umJgj$O)wQ`?SVXe%o;hk<t@z$?q;d8LUt@Fk)ri+h(Xxv>koh1?!3YJr
zHpXVS_G@8xd&b*|Q>wQo<)bCBk_^E9+UQpTFT+L?3+NrLOx(lv((k;PvTDJL1it_@
zhvtv(ASNRDf5x+1??%%JpBHq7o9v;I180-W^Z+c$4~7HYOxFLZB&5@ARr%B=M0YN?
zGiqwu(F>9?RHeGb0OpuPbH3`C4p}3BsN7~XqFtQ&Dsw0M_Q9Q2F$8}<TOk8&1VGdt
zJN3%S$xYGa{S_SdP&w#S9&o6xu%ecI$$fmN3h?=k;!}t-&g$*}Lno0&nv~m!d_#Jt
z%CZf%Wdz0;OR_<_EU0Rxgd0apk)>nky|->TmWZ)4UCMkF67TJRx+2-meq)m4u^vbT
z?J;C#Z(qXFzx1%XIwAK<GqV`1t>5WLEh_gJ7EUZPC#!Kr#S~I%K}b=Za1OC=(R%%$
zSWV8<MKh-4@^M;ZGD-hmj({iIdb?ylDf)W6LlUd{fUoc+p?kr0RX^=p>UUOEhsO3&
zGzh%56pX!Wg50_2z@~P@(AUe0Y-7U3)dBcdLK-SQY#sB$r@V_QlPeWWPd+FqiH}aR
z7wy0|_B7+>nG}BL`!=y}N=1SC^X{VEVfP9ikvNtMT!FPmuRFgRe~V4HBi<WRD+~H?
z^t?0ioy(UrXEo*A$|J8}#k^d#h|Z)GOFK#`T)JnBwaQ9_EZ8n|zoS!@5#P;S;e^+S
zMQLF8LuttiVIrw~T)P%SOS>{$z@g5{giI)WY}WtujYfRjOa)s${WNJl)gA^t#I2zh
zFglH?H^jbx|8b}4Yq8Lx{77dJqp%z-fiI+{)@w{OnG{-5hqI*=6R_|sI8*)A&<Qs1
zr@Y4JYJjR${n(W>ArSuvi2oixhW9}3Y`^7Hl+MK{pj1_Ah@4>0%wJ>Yu~%vbC-@kZ
zUJ3V4j<R>t4Au<OVOlE!!jHBU>T-$@0N<7lOj1dE+8^OcuKji-Sj&L_08UNsOl1tK
zC}n@6CtGlHLBal?ff2@K_)*&Z%&epd>Oq=91LP+T2K8syJb<yLJ^DEdg!1s@OTOQ@
zchxZ$(U~yHwLlL^thO;r%0g$uB7i~1oCR-`Kl-qV=QIK(!k%~H*_=kx_y>A@mv0Lt
zlxUW&)frBNV6rh3vCsRpnn!7UZpN1Dqx})gIGfOYIHpe;Rj!@LmC0kYEG730L-D+~
z+Pi|jN*Z)NEI4kHUy*jx$VU6j=Q3F-{$^g!VEEXjRSzp{H={7krjP0mFiys)JNO$T
zPmvzDrGbxo7hKJb^f@=KE`~~ba*b}ZKK_J>4mlZD=dqE-!Tz~si?G!W28Q#tJhF>e
z0#)<NPr`wt>ohYCU-qI6<g)dT^ehx%><t8Ek(UVuYL%}>SUiLU!KWqJlo|~z-FM}l
z-FDps2VDk>u!4hDXuaiY39H4*bsuMhv<aPOG1IA^*gFE>>3Y%E{{iqUkpe_hgC5N*
z;1}<h(<YjO2cq+wN@fAx35XD-;r-QQ1?oYH&N&(sxo(1_fb3H*CaGySmR~N1d|<Xs
z8a?VgH0imih@Rq~kbk^0VIthgi`bF?f3f{oG*1O9)a&xS4Kj>7vmivp6Q}PhaQTZL
z;jZJa>{iOvj&$~{v&zf##=YU2uku;%pWnlv3I$L$(Gom=#xvNV_}Gsj;y+1{s}br<
zkC)JY$CG~le%c{@RKVf5p_#3t2EMP>WlSi_H%71AuPpX93D<ZV=h6kYbjHoUKijrA
zZw68jrjvzA|7=|4TYc)1st_YI4_9cZU!lFm=yLWb<DseG_NH;$g&XN)#U+ClH{nZ@
zey!hU?b(TW@8^^yu-*Q?>hUbs7C10K?Q1};Lt~<Jnz)NuF?%5OCEr{bWaXD51iUT3
z#ER|O^($t3<v$ptur3JsudGtC70}yvdHas+x2X1;|LlTa>Yw2<NFExAi{lKg$pQ)a
zRFV$mnZ$u_F_L<OZp!$Z79T&`C6fB4oU27bZyZ+IXr7zqqek|gb3kZBB6)lI_7Gct
zy@(HG(=Y{(;KD8YGaz?i{{M?m_rDuW|2sT7M>VnlF8wrx5idpc{U7uX;ON_vuMI+O
z$%{(Ryl@~q-1!*I<fVy|%>7K`5g=|f-$-Q;cfNuWd0_-uTFP>|C?HjTYCVE1T~tpV
z2Q00JBGaY%7e-LY==Gy438+v@SMpR|D&KB91;NiEGl{0L0MVR+qi-pZ2jmMd#WP^>
z6hG*qPeDO%Xf3xRzbSEog2n*ky2R7}L$-su01BbAx@gyh5Fu1BruTpMu>1poP)yV9
z@6K}Zp{2uImp_)M(B8+GU)<#GZ=Vc+Fvhp)DvRLPwGc{MTDrc=UyBMjRUdO*2iBim
z@#or`GPjc~8HQ1ErsCidTLuL5+xCjaZ-M+7=lHoO^!LpFT$lLHYxH|~#JFWL129;u
z4QZ{2?)?eLrcbFQlR4a=PX;w&yd0n23p>y$5LA1)ntSP*zt}hVD)ZLWwOC_UGg&&0
z5P^C~Fl>9-+2}yILs5p<SnfJOE-T|w=RG$&9o{niNd)Ve{t_6nJn*LXRvVMBwY-}k
z>}gr2um7ry-cxj4E|x$E3K5n}^Sa{x4`AHos@=1O5Pb}y|1_1auY&NhmYx4DC7!$P
zSGiD6M&)upP+t|onjn7B3MrefrFAlT#{|TBJ`KLE%^Pp>ta&=jVhWUDGB2H^I-p2?
zC!FQ}YXz>VO2)ebI|EL(44A*?&<!iBh&_IKwX<f@E0lpKb^e@pqjSY?eZka+u&`==
z6s=C|eNukC*?wKVD!6-aQN1B}_Imp?(9!Dl;IWK6IBpHc{Al~4<omMDVvVQ^N4nD-
zQphrVte0>6oGBS^l{`1KUEV%@h<zHMb_8_rbD)cqi^+oVLyYUiNj#A2F#fho(^p1Z
z?T4C9rbyqEL-kg*PPE{PK#F)HsLm_8XG>>>!@4~FXAs`|w}$;^hCV*v&JDDbraWD+
zzl~?VCpol1h3iMJ?h$b_avmuQjBno6NLTX;8Y~2TpStq9DV_V&n`>lbeR`@FUY;>5
zNtAnoE6D{<rq)D6CX^xYBGu(F#NWL529iXG#|W!a^uGAIY4l(`g(2D3$D|&a8Y5#|
zmR!7N`b>^&)g%j<E5%&Ke12DR7RXiB<+?iJ%KIh0?%x2y$xKE!0J$^9K3O?vW(fli
z7s<bO*5TU~Ky~eJ!g2bjmQ7;j-G$v>ACV{c4ltdq>C8yhvNkb4Atnl{wqEoM*BG{_
zP~^PMPNyl_CME&XKGpKC7T0_*y}ENvPSaLp!&xp(R6}FSzd1H6oyZ6}HY^EXK`T{{
zTiS+xHcV2dsO(16?c@R_B*j8h%+wAcHIuJofial`4riN&>uwNv&2$-nEC|!$<HPKd
z_M}%Z{l$DdGUTq83GHzC;rnuvZ&NH9_W{PAn&ZCr_)Xl`Lk@Ktp06u_rP|cbV*49}
zVP+hNisn4SwnqOqe6=LWZw9)oFY=)NNaeZ|{ie1S?<D><8n!1_4Q7?>W6Cj5xf<z#
z=SXtM9AP&UBvAT_MLHw5I9KcK{`I+;Pi$kNEDzb9%;?M3)j2&cw8#8s(IqA?8M}05
z24WaipJ|f5ku0&j-hjKO$8Iss0_Lu<du*HXurr9BXs)LA2TR-L9c#N&wp9)0r+2=Q
zmwDQA)<<uf3ghzLtK(Y(pHDyM{82LA5N$|dW-S$ch;z_o7#Ky1HY4pvFTb39q&4AX
z8eIcsFW5PAx6^sKx~ywruWMjl#KbT|ais&p5DDPl9N+(pH<nfo*tj)|cHajPs7$x3
z`Or~!pF+}*Z2ZHdNlgc=t-m=fa{I!AH{oCTEh89s3!uX^wwmH6ft>JVAL7n^fj7&8
z`B~Y!^IFuyJVV#T8oZh0kuRg3C;R>9Z@aTQq`4I3_rRCsdf$Ae?aO&nl=s*Y|2$`j
zKD1kut3m}Tjt{MFR?U^ONq1)Kh5a^|FpXR=$9-6PcWTvZWjsZ*@X!r5WWf$6paL0q
zK>#rgi>#1YV9dBO2tI}HKS)3KWyaZbNnv>{!QPZiO;kAJU^750HA66wjZ9DcpqW(X
zHgJ5h`^G@MqRm^=pQWd6+*O!H?E6_d$Cf-*M~cZF`sPcLhk1|=e_()U(z>Wf4AP`a
zLP=JQ@?Fp_7wAqD5*R-R^8Ah*UyagJohtfN6`>;<D$q-6mI~F`Qj>A#^;lM)|FqZ}
zOnH;h*L#7T-wv@L{R%S|mV3BT7ivVW{N+YP%oy%#>^_g1iaX-YP$fx5x3_7u5<KHH
z(9L`xRt39eul2opBkOBKy%`SN9d1xHa!|Va0F#kpYR`O|X}hwp=Qgip;Z>h9NJIZf
z1UCHQ7n*IuI9J9|X<9=xJ<wL%`e{X1zgAj#ILOwB@)J@J!y9m2u@z4j@ZR;sPv7E_
z>W>$H*x#%pf!We}Ux)LMS+n-L?{LvJAEq6M{sX``rbSp`Yz+71<Xheo+B~L&+_kyX
zx97tT`s$NPXz9tagwE1oZCr;sWcP`<8@WPi?{JH=hc_c3*uG=RNt;*qv!i&--0a&;
zbwu$JuM<K9UJg3~eZ19Z2dhJw)O{^G8EPs)`7F_`S}~eY%e5yl*wVTfheqFERx7^H
zo^l<ptGdULgb;VjDh7IKj&J<X*Dq8JvR{2P-!~Z*pjO|xKxk+*(w+vg>wC*v=dSI>
zo!Au5hpqsbZkFUSs>*Z|hWp&8|AAuzoj4V7$3f;j{K4Qq5!l2CW3CbQ8ZFb%&!pT0
z+TlQQ2LbWD@;dT04KnZSX%$L~BuJNx4Ph_aq5-q}B?WV~ksBZhNH8;6UMc>vb3Mna
z(|)JKS#><f9MRL?{1cA%xx9}_um5d1n9RB%laAf5T-C{{_E));Am|b?OwMGWy{w|0
z+LJ-o>Yz&qc!L9?mYI*v0!>;KpSv}>Gs(PUg8hgoFGe!^lF5aNNpV4yA3J3mlQfkO
z9`3-ysq0gzQ@X#iKQ=$WlD{4Io92*9Q1{EPuK`oIVcIiE)7imN$3{`~cU7cMt4@&+
zDmGc3i`5|vN4#=}^kHht53I>jeR(`_&a=9PR$o#6^7>uW-+(}z>X^mn$XpT4cC9wa
z?%QI+n9Lz<Ecx!FF&5E1BS)Fd8D)F<!R>5eEcw0|$$Sx_{hWx5xJiZm0%4NZ2jszD
zWPOz)0#3YDQ6NTVnMnX^&SxD`q7Sxkc3t9O00mjg44hW;E*~vHbmrMx)e@el{8%>v
z<wob<FgMWl@BPCK&}C&U4j`ZDH(i3EIx^y)Uh8=$+GV%jl{HYv`f74UF#Ht7=@+S0
z*KHRy#d6}z{jM)eL4RF}2S5pT<;k+05iX$l2mfC8cH#3I%uQn#$Cd1ZLkn81CK2?#
ziHx5;A%;VX4uNn#$_6`{z=DI^!f*WI8l{Ahd$SX6&fk$U1K2H_N--q)w(>|UTk|UQ
zDQvxP^r^bQ!7mJOn4h$%vL<u{S`At-Zz2hU1h&>6ng)h^PUq|O#{C#mNLs}|#8mzZ
zME+Tct#M}oGJdX(GoM2)yxOv88;rNJ_x{)lWCj+h8mhq5q>6T8EI=6qx4MjGg;xle
zOpv_l>tjuH!R&4R?u#6%hx!K;btk?ojgxS=$dRwP1g%~>RO4?X?tcLBNmn3WaD)R%
zP~jm0tq>`+oE~KT0{da6W;<<8Z+Ktg+(@(YerSv|(1bnsQX(9QqG^`Tqi8Dj^OckY
zzf|~i00c8|8a<y$)ymLRW+Oo-h$fK_(S~`-=|xXK?613urf&`%t=zqPvUoRDBU{Hx
zn8MORzfs>-rO02(OS53oaAf?$c#_<YwQ9wzp7%C>h~~(o?gmknaniIRSe>=8Qc=Dg
zf5yU3GALWQ$II+k#ZRZB&q%YbsB+<JMOfhSK^}WU)8rK>l%v9BS+;j0&S>`s%=F%)
zI{>>4tmwX0&mi$2FwP$=3&z08wP5PJ*{|O)%qgPb^4grk^KeRaUstKXZiwf+bA&D!
zXmUXBK!*OxH5OyseXn@WEkr;^_35st-?p(s-Mh?R6I~&x$$Aaw*>Uu{-a0Yp2h(Lx
zy70}Wk?Se~JrxS~Sgjt>MP)D^%Jg@xY7r<YS_WfHmVZl8Je{&<lNaJ^v8ueO89}VK
zj#%<gahxD{ZP?g1DkybbrAcrcds&cZzi6ae#ujBx^aYb?xZs5eLcH5_yC>#A@=)iO
zKG4(_?qO#+*FWt+A8~?;OsH6Bme?<JzADypsHo@eXm@@NE2j^MGU6~Z!LQrT-QjTk
z%%Auj9)Ct8XFW$6f00~vs0|fib7PK!1SohTL~=_r_kULOTjb7DZ?B@Q8Hs0az9_Nb
zW6viXI1ebd*p~&V^7LXHYsrSrpj{-Emgv3oO_pnZu~YH}e9%S75Y0}xoftoWT`aU~
z@FI?BxEL#j#M0ONfsI|HN&6??7ij35hT%KRr1?zV=!}fNfIncyd=Jb20EKHzDR(MK
z6Cv#svp$ja0r0*A-L{|rOL@n*-2Av%1V@KT&K0-prvnODH7}i}-Ol*>hBi$9Rx(2b
zi!OZ3k*|(rctU8Ryi6y2f1r*`MF9>~8S^%U&tvC)T-DBdRZ+HPHlE@ctizbl@BGVF
zgp{p7FYdwU_m+OQYH@9;tD|Gx0B4~sqgm3QpzXwu#iS7@K$Ds6oXA+=hq(PFT3iI;
z8T3i;0KK6?Vp3UbEf(YB(!TNgZRX8+-ycDiI~$Nwgp3Nv<A+sWkKXe+Ykk;Tv7D)w
z=C7TlfUlF(iFDKm4on;3ZcCM<ixN#wW#!8TM~PR*Opq42F&$Dy&Fn|lp#zao@BW?{
zUe_wLwA9b?8JpQ)bu45ou9+7S7PCCIiOn5aGefXQy9SxPe0bw~^-2vF3etF+A30jX
zY+j7CQF*=HAH#$c)$q1|dQ@#oKY&wu29zC#IF^=_y;fikM-hQ@ax$j&lh=pYh+mQ#
ztQ<4?1WSBPUd6Tsm+W;eORqFMjjS4(vLxm0-@8^VA^S}y+nY$=WTLmsj2Rg@qd?PE
zSYOi8A~_wosD~=`m%ilfdbgHne*bJcLSqrx{R=U8{Wo_`<6S~77|$=_idS}1w+N<Z
zveVTV!x1%ZXA*aMY#`o)4C@eUDpzDxR<SiraF}Yr*>tTZS&=xGs2@BLGBwZYX?WhG
ze?=|VWKh9*!Y0MqO`dCp6PXB9+v+fVTDu@WzRU$J`=^yvj9x7LVvm%&$ImuVjLWEb
zmn<xJugau8+wy}{;N)PrS=0>S7rNt!SpI(De8vql-1&K+vEBKTAXrbWV0nnVd&gC1
z;D@idq?w1-@I(bmY=?&lLp0?=An~1mIL0_y^^^~XRW0QVG#t2}SvKS^-0LRT=ge6b
zHi7bFJ*iavP7$$K6JKzv!+{Je+>9VR4jnrZ+X*{!=X@Sj=JH|8p(@UaTQnx0!h!2W
ze|GxPLTqO}$N;ff!w2wnf#RZb^!oUswSO^}baQs*JQTOkzqJZ;VOmu|J4$Ii6IviD
zHowR(!z%XHCa!$Seq;_Tww<2l*G$Ag@iNlRtf0pd758z+f%o8YEuXf*FHE6t(=7NE
zS9D$RY*s`~35fs9b#@8w&oc~HTTB|SN_bX)O-xR_uIP8%t%<tBmY!VutG;D}U7Exs
zANf%-RF|JVgIQmM=}qPsY2y?M%m=#Y+`z&`7$sr<0c87x{@sg5ZHUb;1?4GC`z6*}
zu8s&tUS_Ht99koZem0eWTpalsCiE|GzMMQM*!<BU6R`)XjuQr9H)8+X%$ko_ZLkp8
zdLi+?rwill-=<bD-$ARYGhT0}ty-<rMgPs(b2I&d1TRod9ryWYzPWVP&t6NzxB5?Q
zKki9Fdc~?v>tD59W1YTN)Qf*Vg??;E-17Z0L48-F<^H*jK&4Zzix;?!fnO)S_u>w{
zeJ|F>7>hhXYf_Fm96pS1i`7w!dy;JvvQP(NWSKrk*paLw$Cbs?_kS2S1%CAcu(t5s
zNFkWQd^=taV8fB`)e3x?|Kuqj|KM(!v@@$A8NwHz9#k1IGv|sIUDLnRzpMr#F269-
zUP!O`g#NwNkV!6oCJUlSo$wNn8QgR9==Q6G@=G{C_MGdU%xABU<1vxZjv1s)wSN}A
zs<6POU-HC>V?W<4f(`}Bs4Xh2o^y_#UUOz*W{@ar`?e#!O=qiutq7&*_d5EWsh52B
z0l^dIs5V^M(HpK0x*sThe{}^B)*C_4vp#+%;{Dt;>0T>F!zkgu>fJ0!Qxj;?ZaKgv
zx5Un(B2`xMEvYj?8h$7c#y461Z#i04O-fAW!A(3(+H7J>G3Od1(M8_PS#*eMuf#ub
z_%WciwS?Pv<;rG$zW(hNH9Lx^E4hdm!daZQP;Ow#rnnPB{QDvbp?#AVwSmxzX`Y1e
z`q*#0;NcyY1)r`h<hWGuxg`hi0pVKyCH0Gt+ULoMEvvo|@{aMebO}k-INLl=hW36C
z`EJ~*xnvewgTiGDAY{(ngr8MVldB#PZlclJ5H0tMJ(=L?5$eUu!ta4QkfwSgnq4hg
ztw1sSu6k^tuAgO&mABP)NLCFATyc2@KR*ZQI+vcn!;IldDfB7Q_63j4>h7s}%J7Sy
z0a+2}#`7$0I2j{(3VQ2DSZtT>Nw)6|&Bw^nJu@%0ta|o`IO<!YD=)Jp01gjx4w=1x
zvIK;Jx6jeW>~u)<5EoiH!A3-7*~xEt_GcqwHQKjVl5ezuWRJ9EiOQ)?V;*E?8sydi
z+>di}OG_)@$&Y=NJwfaWN#X%lmUv+c_FEq*Ef-bTiR;SfsG;G<s#RoE5*?*q1Y<4@
zL|U2eqkrb;cFb{nx2gf$Qi!*U9JOwMoO_5OUX&4*66rO7Y2(lIG6M>Nk<@bv3n-(S
zKb7Q|{v{r}KSBVr<qFGM+C&8)kya*`!P=g|X4t0tbP&PY&{VHlWR(fH?456L)ho)4
z($W)Oz(A{dXHgs`;3ey-?JBzZo<c8yp5K+ii=#QCmsxVV`OG6f)OJ#en%P)J^-}Pi
z;^_c-hZR?EXQpF2jpSojG?6$3G-O7ly@RK9FZPcHfsOIMny>DztuNTwI-xg{VjYTE
zM#{34)oluCZYWVLIm9i487&UQca34F3}ou$E4!#n9G(#Gk@gqM;$}3AdpclJPpu%W
z$H_1EwA*zq(V!AK_^B>$3^Ad?GQC(X&GtyhZN`XC$N85wFpm%vz+>YgCs*?LV6dL%
zmd#kyMR{C59u9PRpN>GMWP%GFF4rsy2)qH7(VkS@T8?D@!vbk+b7Yy_cR~V!OK-4q
z;3pykdBafyB^X_tf>OuwSOOwy%0lu)^wUYOV#c2A4_gd`%)orqy!Jwp0{vrk75b;I
zhGF^i`W3yQ2Ey_H{iq4@KHh}1$^zsWp}B`jvmuVaDx>r?DP4B5h=$Y8?`z9NVK{Hh
zb7x8V9<PhBZm22r|1$B^-&BFs7((VWrXJJezNuRflJmD`1dRC!c1NI7UDSk3?)xA2
z`%PYukQdZt6h9g!{Q*+41^zWGS73zYM`vNZzNyhMpGBEm0^!aW4Dp^v3rUNMY9c>}
ziwd6ocNWINw@=Mt1}I$yfIs`kG-Kk%-s=6lu)2sLWnJ-I!MG6XEc|OtXDDF6@#9aw
zUx;-yQM$)B5*&>EJFy@nw$7V)hY_A%PD$>Ig5h94#qZnM{cQT9Tk;3+eSc3H^QFNl
z^C+3)?g4yVk&-}&=qujOFQnKP-c<ZWB8PHpu+2=Ops+!$;A&TW+u|gW%@aVxhvtH^
zAX{Pc%`ag$Y+aP-i1XMREwk0PKe)Z)xXd*?30EzFSzjbQblCI8JMrB)sbeOyLm`tI
zy6tSALZ(T_m;Qdh|9IoQ`H+G#dC1CAc-Ij<8E3?z4L*Uk0QrvW%@~IUu|S(l(LWgs
zmC8c)-4x8)Ao&B7FCa;=bJySK9|(X&zKQK?+Pcm&!&g`8e*SN+Cgf_s_j@Pbrjq3*
z6$5CIXm7YOd6Yaf+t_`-t90oTN1J|#E$^qaW3xFXVm9|9a;5{FFTIU}5rd2N<2W(~
zb#&=Jq~kRZh(?C*9^l@#3!=vImN_!!J8FchC!u1VG@FQh7kK5c9(W?;@GyfB_f2)S
zW^YY2|CKRc$TLN4*<VMtOmh@rqCsf6Bjc3hBRT{wiQd*-1>J2_9)2aTWKeeq&yy5g
ztgD9#U6=WZO=dDn4Tu&y%jivp=uPa&;~gs;9%@W|y(!I3(!?nH4`7|q3&@_iFKyq>
zfVx`hDgbuaD3V;O2TGHze358ktq1|b1IU(`>M!n(9jJ}8KHAxi>iFGcTi)#3TSP4Z
zvdWF_lX&EWjQ@WC+I?d|A{@q^js!x9GxaS6sqTl54~GS+lN`oZ9$N!U>I=fis+cq}
z>N8h-1FJ?UYst;1>9)tt3az1iMU{erxU=MasTvx)BukG0?6fo4Z`t<8mJ2bC&e>IR
zUK=of^UuL3ZK<cN?1aSpCVq%|ob&y>XR5D7$Tc`UE7fPII@_3Uinc@a5ObLIE2YVO
zph+OPCr88J>8wc(sHQ5M#x@Cl{isNk$MmL0g`vu^KDAZyKL9z4g|mAm{(Rd7XQ+w$
zwkXOudKr%8E$t;$ZC1(9NwM-*(bC;|rB3S9Ql6>AUydZ*y?b!@?5RpUlx9}ibq`B}
zc(`5TQHm?eN7<BUn76ibAho;JeDI2r^OsGOn4OB?d}Aq2>e7Vfl~r0|1ApteGM?;f
zcz@{NyW|h|s>X-#pJngwr|Q4PV)~!Ui>j3)$NL1(xPF4S_owziW+R_OP<f__0VcH*
zKhj6bC%q#ZBtRONw|ziOk;OxfOn}n5{lilGmriVT5<XP^AE4=%6S_>ejyinYB1ieu
zJzt^iKL7~>xB8yAS<}>JTcQBb=+o-Ldt36?VN6_@fwC3z%ThB43{}BBuW()}z1cpW
zCb0aQ9%<UH==R$1nk0OJyjRo*UEZxG{N6nF*T+VlHGAHz!F;~i^PsgE@9M=dPa%^}
z#+kRDxz1n7-DHrYEF`Gw@O^lr{#NwEBqZ2IE_I?=nd)5V37DyHuCD7`3kGDKU3DMo
zcAhi6RojCEOn}o)L}P%_a?RWsJJi(Ir6hoB^1OJbr2x5uLJ06P`Tt~K|9^)T1rki@
z;^%4xaG7(L<SPaimCzKy0k}o^{g~Uy5tIqYlrC~y+47=hasa9&CaTL4qBkFh3fhRS
z(Z(2lV@I_47bZ?$ivnoP)wuy<{4B@HE`TxWn<7zXa;%=T6jA?tTaD$!DS3Q2@pLlu
z8W6CZmJ9({&pN}kXZ`YVoRU*kAgDA?LrvL*+OMdYp~402wXPO9EdWcvTP+TC4`Qxe
z2)!mS=V{+hFCzyO#_h*VJ1<92T^2$V<o`!q^*=C2bVe)`MG^HW@PF8d*#8UC`2PWV
z{9pI}=kEXUQ3bh5n9e%Q@R@J(Dz`05z38@!0RAo0Xr1#jE6k{@)7M+6ug&$hz@6UP
zrc=f7P&l??g2-4@gHHm7-M7bOnrp~h52IjSZKsf7i_8}P5D7^0IicBoKuTH*;Hh@-
zeF^^rq{d&e7{0YImKfHrW4@2@pO3opRqCQGb!ur-akW!;W@n=yBc)$ZTC2|{N_`~M
zKh~JF?P|$PekZwI@j7Sq6LFW{I@+Jj3&s}4Z9~dQi7}d^xdi^b0@b^4x_(-Zva;Sc
z%SBLSd2=bEd8X(flRh<+h+9dj(LV`4XY`BALdoCSo(?Q%ssnWAq^4+((Fv`VF6hTx
zIAKox`juKEv<&_`b@@)&*&^tp`H$vDtI|ww*`Ieimd`LUh1U}4?4B?0OsH$C!eonk
z3xB80dvl|apohCk_sdaCi)Cru>9T6#;tR)-8W$2W2{nmuuhq9CY~v^Cje6mfgp9ZU
z`KdqUUiy9de00j+#Z06>*r{kAdAdK)%H`6%U#gl#GbUsiY2*mYc$gVn>lYa*Z;Nh8
z?Pa!&yWVeUa+ej`AT=}7%$hbB#Gxr~TH~C)TvT;@FOpqxtjjSCO0Qd6A#CX0LT=a_
zW-#tmhOtaLPOY7|!SS0De4^81+yW`KI!g06v%GE_S40hzRb>`B)GlPKgXA<~5wA}7
zFQ3gYrBm||L2?D*;$@+HGn!*O?gPPR;M^h+wSdRoi<+vQXPm75mJj|dMVMq2%XS~T
z;QJc(<rB?XC^An9U(2{{lJ?tzUt<D>YK_~(xZodj%8#~C)vKo0v<JDG<%9QKt{?sb
z^uyCi%J3~t)3Jid7@L#m6?Qp%=gZ!);&LQl3MVcd@f-&k-8Ov6h1u<Bk=Cx?^&35s
zHC%A+oa>(;HBYEL6a_=|@ytT}Z_7Vx*1}NIKglhjGvkpvoMxqn1mF5`;@R0`Y?s)9
z9epMLy`iQElS6~i-&39dUvnPZ38+-#WqFw@RAm(R!Klj27=?u<+Aay!O-dNNE%O3$
z$G`j$x}W=Opwv!89Z<S<;zaO9-A$eeRiOc+udLqt*g%_$uP`W8z+)LI8!6_rmYh3m
z(up4l?b(Iv69<F6qmFeg%{}g;B7gIGU;i}>pDwMi`n9WU_ThI`8Ma!??ImZ>1VYgV
z%MC#9U=w9j!)Nx@ult5#%7zC+IcPk%#LrJA&T!JAxi@wuT_#c=`8HX4;q4X^i7ANc
zn6ciLVn44l;05|%cok5K^M)D&?O;7wOKy9PV48E5VT=?8kv-CR879)zU}lY5loTPQ
zdOP?NvXJq&*J!G?H0T<UTqW_)%ZSuFKelvYSR=P-BthXvCTk<Y%w*G7n5Rc4cLMBf
zmY$o#7BJv#-#~*lOV{P-$>HG8*s>;A(f8<We>V!-$!RP_N!zGHP28P#Tz6mFLX4wp
zm)PF00H9;bRl&S_XRE-f(zE;WY!8A%!+g3nz%<S2HgYF|7h5`0&x=s3EC7R@cK@OC
z$M$QE`I8+?fm?<@?Uk2ZUA^~pLcb2Ek-UKViTA^$&7Fcmt0k$q%3v6sn~39%FjDmw
z<65QIH@lX_UV^~NPbZYaj^ULfRumC!*9YX;4lNjRJLm?NJM?y?GtebvV$E6o)@4%?
zuY=_bR`_ZR@FUSptAa><Bi)YiDa3v3KR|jaZV^+Cv&FG-%dNEV%I%#s?2GL2n24aP
zjyaze6jeG3b&clkj`0$7t$@;$DYZeB5@soC@HL@yJ^E&5rV=5C?#*;#Z~Q)jV;tyl
zH_A&G0E=+PWPZe}^N>9y-`AfPlG>JNV1@@FUJ4HeH8Q5j!&CP-ALWnZoXQzY4B(oq
zpStAstYYH3xGXKIJR7YlppG{TE}f|kEoe;YWtmU;&Uim-6t|PuH(;`%w7V76kaje#
z;4)!ev?Mjw&7@TW2PdULNzvq4YRxwRSWfLMv0_111@{(*@G4+jvJ}O%+Dr8dfc%)K
z<=~UBjlL@JpDVqHKEM5B8|&saUgrBHlS!0(Gr+_qsU>$VW%!mt)WBhLipPaD*kI&X
z3+fpEi=7~3dbF?RgpzSi(eBa@6T?)QzfP1Lj>lli%~)6*^Ls^=mN;G3+YFDOd~*lA
zw%4C5zBcY*J~`?w|9eeGL;D1T5s`gtL(3Zk`&HFbG3lY<nFBA?VDMc<oP4h97q}o@
ztGAJ{xbv#WfTeNBgmCs3V0h(Nbu!Itqcc~t`^gDrN~Z_SplF>HOj<+Vn&;}rPlSPt
z1UYwU45;bocty0H#B_H~wZRKKYs1JZUX4}CU9~u;b|5cjdC(;jGcKq)0Cw%^RPf*_
zpk(nBm%Rr-2N3cc_?)UpLS?fbzbDAoR<vKwvFjC(PbCM`jq|?V#macfCssE~dW$X9
z&))CgzBCR#5oXT6t|(0KwRwgS>wpbYhy)k=IX_$C)wfZLvAsK{Niwx>6TQvQ!sSqK
z^QTZ$^FRY84VuWnb1kC3*_}CJ>{CA&O$8xbbH3eFd!-Y!3$~TS@Fs|$nSE%Ij0BZ|
zh$yK40cT0b<I*s=vJK~Nx5akz5bC>V3lwoB;UuH@?eE8JXj(#?A#SgruKM9}Y#0-a
zC2rGbDR|Uk(Bw0jNQ-_K%<6$~DTwd^{atxx3=cj9J;7W=r;dk`2qtZsxbfpK*r7f*
z7$>c`_AWtPYw<<Vztw*{gjE!)Q3>kxeAWufyXZXimde_b-BVt?_ntGLig(PM76?=4
z7r^S|G*M<=$-Xa;kWOCjw?2#gvW7b)X77HHX}1-8QaXfx)j<C3{XpKp;@gfIbvl2s
zQGhJQ5^$y~V5q%4IZn1csoN5}&ndWz-K=TBtlZ+v2J6WNDM>~@n$^gVDJgKpppxTd
zXj32a;dDBt?{b7()4AX&lAC00Ro|muGP}GqnlplMsq7V7iBLNEpI!(+7gyHX_{Zcq
zi3$x{mkIrKg~@tJYy?|ME_m)c;FFophbHKbCrz1(6#kuRKKAg6@~Rh*u@p8U&B$Xk
zxRnlhL2bgCGCa6n?1bq+Z-CE;%!s-72hU5wHAkb<3jnv3N6At>KH*qe<i0set%>eO
zs{I5+xeTu~+gl0AU#K353|4vlHZBz&qE}gp_Ab2K#(Ue(qHHkT;)j~7-%t3lCiXWy
z2=K!FcAMJ?g+s^WD2;U*3zLw#c8zxNi2dIx)MI|>05!&wt;!}hwEG{n8~%<oT^Tiw
z!<R~|gGGO%Ex(glfwU)cs(TZG4?}LfXn<QbNUKLu#XW`kgOP;0dV7C=shU`$x^Qs-
z8^X}g=fk1ovDLpmv?8akipf&w?e(++C}4+<n0jN~sLjvsdW`|Ztepr3q0-V7ZyZKg
zf^8XIt+D>^`dW6zo91fGi^Y9{M4WYPA$9!&1z*%sVxI)9FD7?`!wy%o5mjPPG8;jA
zYhC~Vhk16LVRFU-6hAb$HhEJDwx(^L^j9ryY8wq6T$MZj4`2>2p+<;?4~+UzhG>;7
znlGl1w;@g1s{aH0HJN{;7VGtp`9yq;7*W%ARn;2n0|`f_X@8!N-@RR+Jl?Z>zR|H=
zZ?jUb+O+Q)w;So*UY|NWPalo-PBA=xdQ~z&`RHI58o%FRXyOw1!(w5*f-WeoN2>v2
zf@V8*zJkW8o<bBM(6i2wauUl_s^zj_f#^?p_m%O)i&)dp*;hgrr_1ixyzkZq35oj>
z7d1u_SE+p%d%)G2)^qx46^+Z2x9-6>KBiUBn_~Km=J7Aml?-IHD-Z%VU7KKcAO>Go
z8pOehaV%sJ#RsFQ&TslGD45%to8vHD{@|c#yXGY5cP|gM%Mx<W3jYV_Y<<Vj<(j@I
zSFIes6I}6w1MA;7&wRiFCZ&z!;kc`~?t%lA0I_>%7TM~eL?*tf^2gX2zjHdSa=L9!
z`j-$_g$Q*B!Wpr$_68<#=5QlR2xfMaZcJK)?1Oa!TwY4?9=A|&O7IocjtXhLkqJw&
z3cIbdQfYCqPwJ$k7(Wsp^H{`1w`ardET4;mC8=ecP*~J_fW01SW8~@dStS1w;p$Cf
z%$a(j_f;J338#Y?qxbooxRqBB&ZNv>tXE-k1m#nrz|ERxqrSR7ZuVku+RB*HQy?)W
z>%n#^CG@T6dp}BVM?ULrm~+kTwoxxdZD2S48c_GzPj8ghx&2DV^!<ahM+p^K1(SH_
zm2RcS8}-DVU1w(f26Wr7kb4cd_Z$}+J~>zpW@R&k{DWmm*=drJSHjCe^8HeM$^P)V
z*dXn2Or16EsjRl3h`S8%!Uk-n+VHkMg{?wv&OpEA(;GMyLx_E|xYTXbljLt-BLP}7
zI&Uck7yQKVshf%-AC$)}_GKKY;*a_La>rS|v#K^?Ujq%QG(h*kbmagu0p4#ymrWf!
zn-Ab&?FrrX7j>5C!ayG6dms^zl~YapDj}pJsiWNK;867~KS2iFmyr$Dnw3FF-#Jni
z9OMiQ3d<~_>lEB>e8qp}zAODwi197_3w}d#yVDV7ifcdX+4Jx1qE8bdTp21jY`Hh;
zG^?r-JAbMU*>zHKRlpyKKGoM)ZGOhqW3`VHbC~#0-;U|dnz$;=ChD{K;9O$hu4eT!
z)D3D9mwR1=jg>Z+h1tC;p*dqadyuu4aW;59rpO>rv|3mFp<DkK;3}ZqhWLWt08&?N
zPWii+IiNC{T-8K!pu{3~X)9qbv4im$rZ$|{HgHiwC_yT0t0KQ)4lyEFX>l*Uazeh2
zTu<XJ&UjiS4spZg1CBwGU2r9hCGW&O%p)bAo#+~mHT*rJelqb?&z_yc=(R*tu<Eph
zI@L5^Pwu(zI!qK9*-33@vv8MuJ=_p0sckQek1YXN8}Lnw2%YP%w2o>RY+qgma-N04
zLza~-0<%d!cJN4DV-I~r5jlLJ2PHzu`ohx=jNNk<#fCPOdyW03pLi(cu+#{X?i=3;
z(W0Fjm>n4m2t8UVrNq%YmBiw3nEGCqWvDk?!1Wsy+uaAVh@$quF)p^@r49zr%(4Nw
zZV5l~B{DT#SZeh1Aw{Y|8?{NRS5>fhU4>lnJTj_sq?moibj>YT?kQ9l-^h$?NYx@%
zS;g2II4ksyg_F7$siGT9u|x~yRamT&D+>HrJ`w2iSdzl@rCBI8@Ue)i+3M3W9y`vk
z``GyWsb<?(doSx{)sHZ{BWp#Pe|f@X+4J{GCCy#mo4TN(V#^l?sIrH#`Cb!{H48TI
zKExst>~Ll4vvdLiHbk`{e7mM)!i5^4vdYp1lQ=7%c#Tfej+RxPmm~tFeOUP0?5}Fs
z-V1{St>$E1bu^O0f#LfHep0`EFXu1&D+XX^0&fwou@gMj?JV-;x=n;?LCJU$y|k>a
zB*(E_HMX_Hy<4PKMm_qxTp6DqoS42F)VFQk)&x}zP6HoPMZ1)jr+p6uH+L|)Jp2A^
zG-w>~=>_6+`I=Bs{&Zf>AP6^jm=8-S*ZtuEIE>QvOA?pHUs3hwRRIroGitjgbbQj#
zQYZ>M9OsV9>D)=0&D|>Jr_cVO5t1?{sZ{XNd^BlIf#=ua{Q$!Cn5CI}GbrFZzOm`z
zugRN(UeaxbzQCFkC0C8XFF9UGLcj6KB*Yl-n&bZFcYcmZ0^9&lvG~TR-enuR&3^NS
zjuI35C#4BJJ!(q1Y}$dGddmY3H@OK$`627>`M27bC|>R>M1XH!EnUo!3Ple%UnwNu
zYCsGjYhA*ozOLr{eysroQ~gO4Up4-?9RyR@;UCkR^eAZ6b&9s&l9H{eok3Ltcl&_t
z6Ot9#C6s0rwr;oJTqg;p@02x`$oLot^%b=1NXRen2|+CzDQ3KF@gG1ad%Y*=fyfn$
zlaNh)jaGGuLAZ-o{F2Us=kw@M+v8H$i~Z)0WMJ`2rpERUiwV>1T5t6`XTLmXCSzZV
z6@!Kq>wl94rH#hN*!-2jI=HEEwVp3-kIy8D#$n<f5*tD8(N&<Bv6CBo$$VUZe<AaA
zCBtXGc&WEdlJy6qGj`BhPvSm0zvKPsLJub_$!Yqe9|`qc5UVIVorSJgI2dcwWY%H1
zo$^E4-@j_~z$R9JSU9)0WSqiHXTztKJHp@el2|HQhaz9{JY!Qo8!7LocbL(#gwekm
z255uBv(tL^c?o@N#MQ_RHc=|e?PjX}bZ?7b9_M--N#Z2ahZq<I?B}w8%vyJVBooY8
z?PJEDSjlsESOby0x;uE^coEY(@LoBnaze_F(=}OSd;>ffy6`42!3!t~Duo%GQ%d%~
zYeK&;<l>plo|A5N{||7I+ta%B=eDqAWt2TR+dkJthuB*EgWn6B4>xhn&gG`vaUB&z
z?e9ZE%)TP`n5H}M{Hk~*XV-|=Kl+IoaRfZ?k#ptOz<u^fqh4#EZF)~v4r@4zHOh94
z{kk_YbgnYOj~Cl94$LwA=x3aTme~p#eD;6o8~}Eb))vu1;i304NTWW<9?gA^q^Ea2
zHiE!pX11kl;ncMIzoU^KU(~yQ$iHl>zG(E6fq&zwuZHi_)cUiI8&;wrv3csv(6ujB
z>MD)n)&ta@!h!z*(j0A@q0-w3mugnSsoh5hp9rtAvYVP5z5j=`w+w3Q3*UBw6qf>_
zCAd2+?ocSjCAdRzclTn2lHyKqmk>NS6xU+GiWhe%UZCyo&Hv1tIbY5knR!2~FPYgh
zJCn(tz1IC)_oXL#uDLQK87&nsqHe^rn#PS1^8Vc#saABF-{5xOUxO*qy_L>D1}G{)
zY@K7Z4O`EAcUmi0hvxoBk(Y(pR1qYM_YJ!O@q{BHe&`)SSMk%84FQMY5=-wO<(dt-
zMnp7^tHFB8xa9S9ORsPv?rKjFH<kocy`DOoVfPdpK^8hB1ex_mFDxcM=tude=g}3{
z{0uZ8clzP#7C@UpJ@;o9S!QKgceL_lPgi*GAz)O_03=8MK#m?+8+uF-<Io$jFdq5!
z6r%W|OS^ueGEW;Vf_H;clh>hdO;PSr22b6zNz}`!%1s(!H+!IF4R-|Zuqyn(2H<%B
zhu^VRqOv9_u7>ZXvl@YA(;9rL1)@dR9^w#wu~YRChoTqEyAg#W`FT<2>KMRnWb(_m
zlWao#X}@&=#QYW1n*4gy+9>BORQrb@AeH*9hPuAa4T*Nl=Ejszh8(H)dlGXutk9F;
z>Yq;suxS9HzQy*(AMu*}lS-3!$9gu8J7VJ#$g#b&yQ+-1B&lj%u2pZ(s09K8b-I^z
z&biIn|MQeH;{;gKF7lBvc*j%@dEQp7U0Mr~Po94cKUvq06a&8kOE>xnp87EGWAI90
zIo;=$nH(>{Na@EYSnCWO#}b!`zIC%@GNs+YkepTA3a^*S<EMS;GAx{-e+!ZmdSz}%
z+7$?8cZf+RdungT9wwv>!Uj5?!NlsGOzWFtQ%oT%Og;9DDLMXCr?d>oU-}c*3m`vG
z6)QR0Hi}!K<81NQ0%kmQ`2=Vm0x;@Tx>EpvQF07{bD!TowHg7V6r;u+G@W(4e4Di|
z2Jy5KmG_Wn<N%6u4U9CEcBw`=UOfp^Rh=Us`@YnXt@6-_G8W>qA+pCG$9zk@ED*SB
zGC8_tNt`Ke@8(EwVOzj%;FDM-HD&cNpi8Yq|Hq~ywPnyj2bwj^$-Q^S5wF>cs@!2M
zzzlexK9d-*3l*fuGUxx+X{Rb0FC*eR?JQ)u<jdi&a!t<myO4ZYwzQw(kt7rxviQ4J
z3rw$xP2;|;*3_L4PUN@qKipaX@H|0r!Ct7l^#prkSR)0%-VU1mG1C5sjnPoOi_nzN
z+oq`Gj7Vf}CyxeD?-cIi<)#d?pN=1HhBIErILT{-rJs4uYEp1n{M1R@VM{`jm!QUT
zN)8x%r{ceVS6700yamB#%|h{pd^kZj%7sokqfT<e0M@{#`-;M@nL`apsI$$U_k0hp
z9Z>@sHe}CseoM2RucX@Y$Fg-zF}q1A(W0CZLe8@z4%0i_DLcMh^5wqVWPoPDSa%qr
zy7IS^6yHbJK`|GSLgS;xBTnIm^C{-O1B7Ts*$>_P2?aufuY;W~CpMWhQ>V~xHQtP=
zem}jF;Jgz|&HmHU+UjBi!-nuP1eg<ZpqJuY3Rax2td)!_UD19jMsY$lz84?Lg~&Q+
zr8wOGmtlqzoQEA(ipxbC&_}yCP5r!VvJ>#DY>#C9pU`+K?j7?I_Z*o~7t42f@OKJ>
zn&Wup#<lp*yMLU=OZzNGxaMy;{0+~j^X!Fc{TPFDp7tbuN+!!5aYeXXy2N`q&j}em
z4E+s7tC!BUGQhMx7`A8D{*ffwH|+C|^2;cjWfw}gvig?)Jy_NZE497*V>Yo<r&YnI
zzmGSzH?l*@P4{yk{j%<P?+d1i&6xH}(gAa(M85HRn9YX+=KPJMnNf*Qn98WpGfRg&
z0rS6KmxkT(!9nw%?Y-X*J?N}Y%y1`q&nX{qzN`@^Mp@BNtsSH%=r#oanj@867F4nD
z_!9eUGv7}G*l&};m&dKu+|{wvdrKnGK0<9;-u&$Ld-hdzU0Ms;tAsgXbUAS059SAM
zT>&X0R+uS?y?2L{wMT4^flQIkI%Z3G7l!3DflR4f>Hh00c5Lf+wQD?hV5z_gvQrf$
zNxJDY)NDD$_IUX)W8TwzEcjFj>mW*lUMpVP#j=2%=lZ9A#dQG1o?jVT0iThS%KNKA
zCkk|q*n)JzA^&pA_2&WzI~?=>HLChQqpVn{F`o>MqXe=*o=ydmqT=uW2)T$=*g-%X
zW3?N3AdbLo*@%N6tz&pcSxHp<EPY8b6qPW^v(QwbIUFk^qvp#2ZyZYNfgMFw_Kcay
zP(lE0i(e@!sd_&LmGNK)4P(3(D~;E-M_{ie<0B&-JIbd~*DD68yrTpdbFfQlqR$et
zdZJ*mH#{Iz&}H|Pz;tdIm5uopy_iBrg<HnNDk|(~@-#=s@)*SBZ`6e&WK2E9&XpAc
zie_IEr5D|oZV6@=VQZ-$E2?0L`jn0K08k{_PuwZYo#ek94uJ7eu`)q>2*8iMj2czR
z2=JwzQw%~;X#Yc^{qI|H$OcL4u+>ko_C6px3iP%am7D(naS!|n((Lq!MtnEY!($km
zX&9sRb(98=(}o4kZ=7BK6e8=<4th<`nX244^*`gCzwkUa0<~CkYmKf61(6ciW^z+g
zduj;Jaruef*0l|6Qh(L#h(SI1H(zeYdl7bx?ke&OjDGxCh#v4sbFO5;9_w!3l+XJC
z><K|GNK+g`ww&f@)upcjwd?%SOn#aF4jx>hH8ptE`YTZdMx^dd`E58sc<JL?jiht)
z!~KK$RCZW_|BeH~Ik=i}3G}rRqky<a_m|+(%K#(@flDenC&J*}?<5J{`3euax^S~p
zO8fn~$MQHRbg8WhUxK}D!b6#jD)clrbAFb%-1igN@v27NGV6}8YsUv{7T9a$G@~n>
z!BF2;<cJ6{wNv-_-Hg-l?7!DwoJdzy&6~*N5p-Ogr{!{b$SQNZYXZ=MD6(^QR0%gB
zGF(FxySTov+ZL3hpF7=bsC$ReSg*4v8ERc}a&5Q)<0l}`z>=A<HdowrCndBtO4-J<
z!bp8#ZDM$&Ds~#@6Uel})4I}lJ=XJ1<&agq?B^YfzcYtu>2g+^pI-gP;byaPvX<4a
z{0Yz7nkGIU%T#_oV~t71pSzHm92^(oE`yg6mxO=xzRmd*o;~L(y(vl%t{#~;)rVC}
zR|m4pmw9Gct!Y~5IqWzRamw0vUFsL<lfK+s<YdeHP0rgK?@Lo-gZN-}#2aKU#1lcB
zt`&Cg<ZzHdL=rRjhuN;gV!yHNsv5u$h)Fr#NSx~D*^q}9>jn_~iFU4mL#&|@>hy+R
z(C%Y4!84^}j;alTNV$rVmbS^7yhQ$m@-1t%6F=~yxNOAyC9zY7r0_9`O{Zz1-#hGI
zRTsOjYTzJL+*2^$;qr|Umaa}3*etWZo0X)ddDD%wu~p~oB*&y1fW~6O0d6Y};;5Ng
zsx=8)D9Z)&;dKp~X-K(WK{VysFXka9q!Fq+cZ&UmTq9aig_AqUQPz_})s|};z3L73
z7k`dFjzZ;q2OFNt^*zSO3X|aOtX1L=q&lrZx$XCVCMly!72;pc%edZtkFTw47aXT2
z9k6DKxvf(e)l6Nr3K_u*mC#=gLiERrE5%biPpWs3S;2?%mR_@DfJ)d7q|<M_ASa+0
zDF;_O11yn5ez8O7c&6D*28Grt)Wu$*LB?_@^OTeKd7w!l*OTzpmdQ8Hgo{3G^R_i8
zHa%OivfOFdAGlt;TSsg>p~v#NT2a-4aJcG**U+B{s=8)&+6<^Zlh<xq=q~%Q=X$2@
zz%%DoMslwA+LK~;;NBIZDy5A!{Qi$)Cu`SE68;7vp|y&q=pUU_Q*@Y6?RAszEmg$1
zVdstFCtT%l1+8n|GpAjhl+QCVOTI8Ooq>y|3^;s$ChMUTFU(!boP_h-k24pT_xTov
zDokjJbtzYQFiqqndp`fp8|rD|&8np<K^uDwr{MnHdg#u)aBu7jKeOQ{_q`CO>>wZ+
z=2euio|#Gn?{7BcVp(M4wXp#QN=4yQA5~*;hL%?2{rMV?m{uo$>(iTN>;ZzI#RQy+
zPOsepr<B$_6MoJs?ZWwzloqq1W)Nzr=@YauH866QgpFXl*+gIln$^UXincYA0-q9v
zHTF`WP@f+C-_`hdnjQ~Nt+B3UiqW8%Y8E?72GOzma(TQp2o}a~@A&ylvd)4=l5=CU
z#!BH_dNi}*w4x1Tco`p~;$Zb*kcjaC<99_bf|OMR!}8_){<T(C#oP#|3s$Mo>Kfrc
zL#BmABX?_2RofMYUD2K9dSB&3i+X_ihPr7()I;!whDm{=Mo7)Jm5bW%E&5L(Rwb@;
zZAds1#a3}Yj0@8M8<Ur<y-rc0t1&$)FfQ-5=HbnbB)RAvI)X|gz{FD&dtrf8=4f;h
zy7@uM+P)IIiXxhn7kl^p<6L|dbEtrcd%5a9sMNGhU_S;#r&7|?x>KMF!L}!#&7Whz
z%IN_-;l($y^*Y@yS&kev7Rn9lry_MR8+I2o8R<lruv1Rex0EJyy*MSI+*lbsvzS<;
zLPb^a#c2e@o`$0K<Zeq^Zn5zHIk;TVX#96>z}k>cD?CZ$U4ZZlm2b1oL)C@Y+_c22
zyOi4S@2EBX$|F&l>`)TYrr6`@QP>LV#R)+VB<C?C*u`BB<-Ge`mZtIfH3L`>PCJY5
zb62TwU9-cX7H~mGBqt~o%s`yFOM}x_Yeb?vEv}#5b~A|<V?c_r4w><eq2DFvL#xi9
zCVFAmn)c9cnRi=dfSsaK28l}UD2By%lH*d0NFCc7F1_2dI4sw?`R4*7IfvGBiSV@l
z^C<<lBiRCz+c0|g_EtOa#O|sr{RQ6arWmkt2nKt$t?Qk=;&|N7qH+XcoNF~v{D?oK
z8D{*o;S`=Dt1yVyjEQp{wZ4EQ%oj7_t>5zZpB-P~<GYCpV>C+;2F|Y+4ss0fzXTwC
zU3RLO5=lZV`MYal^?Yw%H<VjarK&NjS=iMehAb>l3LZ1_2nyl<0Q_y5gXHp+j?`%_
zp`4~4e1u)nK2!8diB(-pbqfS~b%4$|>rxX0bCo63-*j1Bt;c!c9HEsJ)$wJ0wX-IC
zy>-Xftl~w)sa|&)&X>58SKY|}=Xvpr?<=jMQ`*^SQg+mB87apu=0dKr>CNvsk46Q3
zoHc_;4#uALSOykRskog&AL49WZGm-N4$Ah!cL~Oe1UW2T|LlH#tY;DmJJl)pM?yZ_
z)3_>aL@wM=`?pK+wn&1m{FRL4d!-ZhRoKEovA^fmI~Duv$~wm%_%G&L-{Hx!idNy%
z_tQAyx^;WYTo~TONr@F3!fgKX={?XHYYx3Nod<aqk^UJ|LLFTv7fZJs?bB_dN(`ym
z1Y<q~f`e*C38M_q^A6EVGD)dCFlbwbCjNNJx={LUnQAplsq-sfW9q~Z(wehlpnnbD
z;hQlQK@ZXv!M{|2P@O7aTQio}96}21(8kNIy9#2GNnqzkoU-&x5lVCW4G1zUohd%j
z4vT;(!HLo8D%AaGsWZk3?9`6hdZNA(q~SFFMo&+~u7&&Za|wUbp3l03c3Q)P{6|lH
z3d<3W0mgu7PSpy#?1^ulv6#9HahEc2@P$#2gaglYyw&bZW$wh8izU2P3Q`p0l%724
zq$|p{*<A2IGSy7|XB1j6;?8<4%oK?d;+Z13wRa7iO{(PRMMvJjjhAm#UHNTZJ;saZ
zajT1I@LZEy`|&q1c6!0J%OPqMF?gW@rWx?_*<?28$eZ|*w%u=$_#U}5GjK1J{J1@C
zb!VW~f!6g?q9adPE5?Js+u19l)Gaq_$_Ble4LAi4eS0)aLHH_9PazZ9<Z3N{QIv?$
zzW;5d&L~s)694_@EXjj9b0d~seHJSORxUH2SrG^=kx+D?&so-*cEOf_xC3rt;_#=L
ztT2rl-O>JKKhVn^)fht=QIQa%)fk0@8-dp6=Kp+^_$>b@J9gMnYLqnPYw&(-5JM=*
zlZjj(kg1dG>>(+hm<p#3SHa$MNDs`2Jg{w{v$6I2Krie;=#t}tV8x|aVf3ZpO3BrE
zspfC{MZ#~VQrXVlq>4rNPG?=8A2lwocJyZcEH%*OkWg=2Utx{?I8P_nur+m2dzX-P
zvlL;|_1b;IrXpa<LxYGLmL~L_g)ZzW@sWJ!#0?(GI?6&Udu;Y%Pn9!!J;RP-?1VF&
z_BGT(;~*u89v#cMjc6BV<4d2Oy{|lhDz*Nq1F{S)p9oy8_9WKQY1lfJl=o*;2w4SY
zQ2jFma8^N>=asnZGta)YPWsLp8Eqe>_i7_5q!g7eoxHu{$O%c;YVn`4QW^>w6}xbJ
z?-dN$XOdjnBW`YvTF2{g_U1WzLrVgp28gE^&6}%9?}i}km3kxWt}n`L#U4G4Ro-SE
zI~jADMkm_E|6I)FF?Lq$_qwuY0Xxlg&hfa*sp6lf-*Rj=G9wZA_Cv|k_Lq>by~S)n
zzgG`_{&78QI2()Y<(;i<1skabT1Ss{s?YqVjwyx$L_ca20^71z-&1%P2u1TgZStd^
zZ<MTk*JD-23Ru(pLU8ERJFkUh6;ue9lBK>lT<v=KId$0bU5`J{87DQpB#Y^%ma$S%
zPHb<z6>uffQvRri5k*KTMVbGo;AaiKM2FF;DKsy}p?M0s+8Ty`v<}Z)WY>22eHCbe
zMTN$lOJtmpil>?_VIR#~OfeHS_@eYNi<71~tIIK=>S!=b2OY1Jq@`4C)1Q>3m@%(G
z;~Kk5waWWR(AUyCW%A)EV0`Q(o|T9i`0LCcYf0tKN7sF(gQ9eN6Nfzp3ogB*5|}JI
zY>{BbaDj+F979)8!!INbaucQGd6_)hgwWh`E6F8<<>i`@)qvYHu1L=B+Ud4~zK4*?
zmV?^0&e28LCuq*d5vb_M{+P|}j{6OhS-cl`S5I;ngXyNK)GIY+I`Bx{a%{+99TU(L
z0zZY?h)1VHrsj_;A246DTetY5=LDn6)3b-&i&97Erf6k+CE{TNdBF;HAs^<fa<hGz
zXfI@JXHJd$O%<fQ2z3=b6voZejgxZP`0WszaluZtr{2IK?`tAw_KB<BWeRtVjB4lV
zY+l0{>CZI_S+7K_1xzACo$A-~392p(E&cSyF52E~WJ|Xk$E4xgTnGKM`*LwcC1GuU
zKddTisU@2bHPu2J?pymPa>3co)W`}S_jhNaW9AID%eH3mzj~arG>o7%474-*X52&F
zYZaL{@7mpd_)%QQXNCc0d~L=qBRz>%`*kHqS9CoW2tUYBMGpWTGY3)u!lh2)V(eXi
z7WN?}`*A_siz*~0uQI;o0!i}d%K5hao-3suYggWs5ss3VR+<S7W@Lb=ZPnG%jMG>d
zsXn{70K$9{m`2&AW;~7S@ko-o?wnxUeBs`#JH!;^P=EST$xUaB*{A|8tAPUnhlGWj
zLgNWOF0%e%<0iA(3F)Ki>ISNll!>BqV}-9l)I`BLJT_*vUF|epPT*FPflo{JM_dKC
z6$B+ZF40P#L*-2jq6ZOrZIm%5JDb~RFCu7HYU0;`4Pmd_;pZM5I$CYH0Ui;%w^B~a
zv4S*m29AYl2-mS69?Z6XIVtX9iOBVoB==!0zutX0YYG0E<F^0mY?^|ens?ZDc0cSa
zdfz(hTl=EqyAZ2|T65NEjCbI^Mdt)Js{SZuh%RcNVW;zBoVh^kPy-^N+lh&Y7}_oY
zo57}T{Bx`u?_PA_#!RBJqFK<r7`;ZTV>x4vQtZYAlE`Q%BJ&AvYI7IE-JSaT`SO9U
zuBQY&<XcqE$mNLcR#ks3o0^b$OP4xQOZbZde!b(|m3#+NbN{LAR{Hhu1+&A0_p#Z`
z7fCtT-!C#*b6|`;UJ`5C4QIpmz~h@qFDkqG=yOS61HL0ttS)Zkv5zGQVe$KB!2QMQ
zy2DYENgEc<a>hfQEn7b1b0<l|zmw&P-*m&7OZt<JpE8r_?utH%ZzeM4o3S{@ZL+@p
z{O_e4%<*c&DJvD1!i}Vo%2`qKw{qpNpVvfYllkXEbTjxr@+1Gm<$J43h0X+9u5=48
zxar<MiH<pI;Z24XEQRNKG)xjR^C_SA+R~xj=v&(DG3<ZZ<w79Ac(oITdj@j53eRp`
zti{eYS8F7xQ^Vd9>&rAsE19yA6>qcR=N#?*!?s<Mg~962ffeQo!%Z(JeU^nEICx+r
zlJ*{G$|WS)epYq|g%!VZm8_Xt4Y=G3vt5}D^z5rv&Ht1~eitvLCQ;AY$!v$37^^$J
zy3P|*|5jWtRB&*j+TmvWzG-Z&36=MY{|@Ld=T<ho!#^5WYef@1k`LTpuv2}+czfjw
zd)3R?^KnCC*O6i!JE-|k@Wd9cPU5G&*4NJ$TFQzW2?nSLliAQDC#2hL(uUTl)HXLj
zf%f*ej`=0fdKsA>>)~qUsC%JL)nlG-mzC92)6e8G?Exk)kmVZ4!&{oolgsq->Y#G6
z*~u7pnd@u}R?3QKzhi8w15R`q+O=H1EeIjXzJ&6;p-%v>dT0cg-=$U!<$NEnG{c_w
zFkM+7p*>nju{Zg48a2p%;{Jy5W!N^~8r;rgq-pF!LOgBG374{72E;hsrm?q2CNpzJ
z#69z?MCeD2u>#y}j1F_Iw)wX$r|i5mt}Ebr<Bt1w#Eayz62mF)$yeK@#{R<lv-`I&
zgh-#6+BVJ+v5xjhXT1LF$$Mez>-`9!+<Ft%EP5MmSvP*EM0G2~<hxCsVLzQbXeYnJ
ziPaL15XGM!eGqg1K)44dKAazy(Z2b8%6|a78|dNBZo{(4&>;Q%*7|+aX2RiWd`4wO
zWZ?s!W3vkJuS6^=$lPqpqwC$58$<_)4OuG}NIsDvJEMW6;izTP@co}n0-L!^EvEzw
zm?Up+=$cW%P6iqm9rpJB$Aq+g3w(37cm6#TmeR9W=iYqKopS_iqs!1zY8vVoKkcin
zo--MH^Y!LM>h^&Vi^u3cW524=NpO4?7>ulpoMLtv8^vf^wr`1k`Ms;s7Mz}!B&SQe
zor9OE5$ar;InqCFfP&P;YLE{4!~SdQ%EyQi=XcIncVuFb+19B2PB!ySotf;Ol4dg4
zi?i47j=Y{X+QGjt-9i^a$_{B_BHPS8e8~$y&!(U?+)1-w-@93@H(4nw4D53osA6*S
zK<{Ato2G9SGFB+upJ#(~yv5KU6cah~U+XF+@3GwOvX3*9JT{Tc`^8oLYhcY3rGY2u
z`$wj_!=tjM9$sF<mbY#}tpnXp_%Y8rgf$ze9x>ys5_C0+Y&3q_QI;G`*t~P2sxG%6
zn!6>Bb~Z~qfWVac$^8ZVu*r`*39Fjs$XiQ#rvs<CqGxLhuJ1hOmr?)lxyM)IIHqpu
zl~`TJa9n;+X?M6_KX|eu6oz-Mx*B^y<!-zL?dLhq-?e|6cy5#{vN{%(keBF?OUd~8
zLna1YfbXb^AsIs&f+zgr8=Dc&X%0Q+7;v^_u*DL0i);&bL3$d;E+ixzmly4>%%uTT
zWzA&zXuVWo8B?8vUMhJ{PA?)xx2+)0W|?@~^LGjZ?R<(IB%S`Y97A+Z6C?b|s@C|1
ze+TAUeg2qiU#=_7Xw)9dB)B`z23MpCDHURWZm*l?rD4aQVF%#(q4;@rrgG|kf;sg6
z0TKYBlmUBq7SA0!dBni*I<y;3-$VEZ?*qST&7ZeL#V6f=gBHB<LY>~PDR}GkZ}Bh~
zrV93LsGPRnR;OF&7<wYBajHG9VfM%jX}za#N4M9U6MUIET8Rcp7Z4fIn3RRLZ2l^<
z0eal`8H4tzPBhXRW!W9i#Z6Mf4x77Y-^H~t(1)-(Tzm-4DA+8X^s(}aOnHxIoHnNw
zUN@A5f1ch%6tFz&O%H*zmBea#=@*yP+iVs7KHIx-ej@H?Z+iZabHgmraR@160^?GD
z;=`aZ?g+KI*wwUlx8oxsp6LR?pC9qx46zaR*WMuv8CSxI#35<~TqrhrK11eXhm_My
zCNPZLOH+yy9S77`TV~94eqRk3MNO=wiL$Mhws%BMfev%X75#(&YPtnLyOM$n{101_
zag<LT!(RUXcr)!C1gi*QMYsL~EY)roZ=N7=>kqS}RLGDKP-s%3)%!Wa4@eO(Uo2or
zu+nUq`S0miL#uGah}7@8%t6^!M8DFn$yq+QA?hfL;!icf9*-pR*YDqv-%OvE&g;?$
z@M;?CX<C;C2Ey$ziGu<(i2>T^sYW$<5s*e|dSbUlUJ8(wh76}0A1OWYMmb4%kj}9|
z9p4myo*FqHj_FUXf2rBjloUEVz$$@Kv>E<k2c$su-6ef3iL{ZdInQLsj^}T$P9D}u
z+x{Z&SEeM;j?&CbRukscDTxXNtQzi!DUbDCw2byFM`;m5Gy;YT8g6VU-%cw$jfHzj
z<RZ`fY0Et!e(1xaNp%PR0g{5>$NhL1)^Gl{=>B$BV*QO*-wk9XYViJw<hgkC)VNij
z16U>NQqPu%&|J@SHLOlt#FmnHS}dN2Lg+I2mda*?kV@^RQw-;d#=JqhP@A~rtD=G^
zAjxPChuEbI;h*ZdAr3K=g2*H_w1<=Gi@w7zFzrY<KSDu=f?*`cLQkEcS;9V^sO9ur
ziX>+_u>Z)o2wBQ{AP>S@lR1DD(SXFTAu;-EeW>D)%7}T<OEu55R1SJxgjTZX2(fX0
zci>e0(*UeMAqaAe5TpwH$xcrfw0DQ=Nfj~6QPB^&zi;FJ$i(QGXG0s=mCo79j?dw1
zE+cf1YNo`TK(eCRS#2v?_n_ALp;1AM`H;2Rg@Z@!E$N$Qe>#r!ZyBEPydH`|8>d%x
z>#YLeE2su8k|v6)v0dnd{HTQ{dLC+zI43E%b}kT(qlxv-_+|*RP~|d&@wpiAr<){x
zspTJ;7*xE(%>dQ3=$3JKW74*|N6kC)@z^}2nx5$ZyHd+E{|qO(^S!_CBbgAtynK#l
zvEJIekl*5;uBv4w=7;jOsPD;GL}Zf5?Qp@E)de(H{7g0;rdH1nK4juwY!Y13>fWCZ
zdq16-6sP-+4VyqNB%HzG+rPj}tf(VD9QWihro_EpggTZ$PyAGI>r;(exIU6nL97s4
zY8fHwh$nsfGyci1s?kmpK$o2~(iw{Jfgo&!Ke_bc5bhZ8sedxyz%jiEBLf8hZY{X>
z4iy7kDgLON)ykoay_%}*aY+)5ZGhW4d;MiQKZk(^_e%`uSIw?5Tf!%Oi@`tNJ07ZC
z91V*Fli0Szq%&xjW=LAG5l%TIs9L;{Qpfp)Fy9wIOgGPH_lZ1)^lMT$)#uY>sp<r;
z@`j3VCRIm@TiPB^xndb$V$fYh4>B!2v&uMhD$iT{#~l4TzM{l#h<#3EKpFqlspbUm
z5FuC)q%GJn3JB#uo7uc8w@k!L6@?|s_#J|V<uS#~{#b9unTBgxBssN2hYrfK29^rO
z@ce(TN!$#7c{|J^p1X<Sw#tg$BekFcGSQ{Lmh>SW7NGT2k!+$P&M?gs^(>l#r#ukg
zSALL&c<TgEF;<aI2ZW`QZAP6dZ-xUk3F$>oRSRwbK1E1-L7fKt<^KTnvSlS-0hJMo
z#^4Ev%v%+4ZF`8ow5JUAw(4q{AejvQqjr?~46w%m&C7v?gOL5c2ov)kuy-N<2ne{i
z&9B0W7%#Fc2zB&^%E=bJphh8Z<uu1HhH2POHzT0z6#hGj3tFq;cmjznS_KP$o}){7
z7F0@?3c(Uj)|#D@!3N@iCo;oPhPJVT#1?>;qwGOy{FMxzSh*Aj&J;=zf&ug?EvKgt
zYyoI(LjJEh%>TQJ%>O^1RW#N6VoL>7YROQvZN8op;s{xTOTYePYSn!3J9K+RcFk^%
zkH$LXv#%)7LX(Sv(m%?Fh9_#!l1holfAWTIsWtv(i!CMl1T9_$MRoWv185lFVJ`HG
zJf_@|XAz1Y91UWSKK{cs;LcqRQ816s^F942|9f!gI>2wyhzI$Rmn1X9^$%CyUB2yI
z!h7Yt2&S#S{Yxbk19teeiO(N}KB;~yRPKKLY6!OLzBvlS9N($>Udz0DD>OOf1vWtZ
z9t@>M=Qx`s31=pRt~LEeV74Bf>#H&yQdxiMdAu?QVupwALSQ`o`j1^f&^g`Y>E}^%
zhI!xIip=R%r7{c5@P@uRER!sP3F66Pl?OsLiD^E){N}s6a@cx`v6^u3V#6sn{lf(p
zU!kNo)G=exgHZc@qhuW#)6LX-QF2hS+v8W#P&A=N%k5Ba-FXxo%FRu1|1;SmP+Lk~
zf@s7`WpZ>^hdClvY^K5qR+geRHw8+RXXY2tlJ!}+p{D&&Syk)A$SUHBshhMPXg$g1
z@8QgLUe)OGywLA)DDlyiH5YxYQD+S}lAcjhVU!bduk%}z&e_W;5Rjd<c8$=N<12Jg
zWlj`Zg{A3Z{-C}xE}&etp8fMa%e#*ik&KzaH!US^91eOm)|wD+IH~287n$&}%(R#Y
zUjAkh@OrRU07IM0o0@+_vMCA>{2$=y6mpd`&=Dd@87$H4?GpGR5ic~<$&`{NQAf6A
z?oLjs7anwfVHoIAiC%R=sfWlvYcSaeEfJCwBX?TUh)-xHpuSj#&o20L>`%xE2R@IK
zkI8e~22hf*AjY_{IX9;4wv$5!G4=CKfEU=Cr7Uz={en9e7~EwsVvBj<pL)gXk)1S(
zBO(t__xsS{o%PX_mWF;n@G_gIeA<JJ^{E;acoPI`pt3tBFrv>}a@~WRC%@ol#c4m{
zu;I%PJJp)Bpa*~JgR2@0>{itdr(k@#t1&!W^<r;`bLZJt#xH%@n_(_BS}#;&o47;G
z1^7|pAS_{XP$)y!;?pO%e?#`y<YkaunXbZ-=UpXEpE-rTi+yc~$ebkC&Ib3&)`!y?
z#y?Ztk)fkbr8`MDPSURzkT_pe9T|qSzkw^4ItnoYY6B!pMUq_azu2M~V#Itb4}R4H
zH~xJ&5VQNC@S!1pimW1VbVI1tad^~168dlFpwFcv%4s)FLZ53QOQKb&?r;m*{Zxzc
zeH;wa=s_g4Md(avGtz=zB#gk_rm%nT<c9|`N`yb`l<2zMVkUkY@RufP3ZyfNk?+z<
zK-T>Xi);)relojgfN!sPU9~?BRD<f0w0{R49D8mWI;EWWjdqgsyfb%N%HOUhJ?ga7
zoliaaPEcEgLGs%dPTG3Z9Mhm|?V2icCGuc`Z1JUG<(mA&|B^AA2=~-jV9m7U%#Pb+
zo?>)cOW8Sk^ZR7PTDd)|?4)eDy1R$DV;e?4cDX9dNbcV1s^qmEN;&0sVj9u`s_p6^
zPBo-;(lZD~`x-7`@kE)*OKoujiAD2{>c4{tleDCgO{1L}H$tH<W0{xK4UuDEI*E(s
zGDvBFh0?J>j+zvp|59^o2%{xr1NQ0;Ln;~eGFbbw6qY)7f|y-k5yy<_0hG#5{PPU6
zU!@(xePeeUm7azoa}Zv^(_94UTZ|qb%FyD1aWj?#$n9>A95azu>gagw`o?(2^Z*3)
z$}zi;8!N;2d;ak2SWfaCwZ($V509VrGzlMhCttBTcSXm$`haKz%mn?8fif@fZ)=^U
zbU!G#E@RY<3_FGPf~<K!?xh5jht=O#lu{~USg6uGpBC{GbccS&kp!Nu>%M-?^7~lt
zJ-YXJ@dw<`lVf`mXDj~!9Oh}qnHe%=N1bH&`YNmO$A9W4H(7Pit(fJZF^3Z?2zd-$
z4Pbm9A{tth$bI<C=f*o)T_dNN(gcc=zH5!nqCK}}JE#cl;n$0>aF*KJNcC`H<qWM-
z!fys+7W!Dh&b4La9_M%B;sg2irR3F#S9D|8*J9s;RRGaLeja$xq=z1Ub@Noit<Ncj
z59mdyOp6*XFgX9_+x!PG;U5Vmo8mhQ-?t@A(yjip{N>`&C={n+#^*+4{2EoDtL<X7
z8Xm9J^o}x97f<w{y4IaJVtgDMZZ>Z5f)CdrRoR0KZT4=;#mwkKYjBB7ofy5Y-^&-8
zgY|HpaT~Sjz0ec=c8Zg_=}~MU^MLaAs>A~=%qc*3xyWE$9^alY_v|pA5iPR~j+4ao
zpU~u*W}i`nd0Tr6y*xjEueAOQ(A3Ti$Hl+=`s-Uw>|!{`rLCQ>fU_*T)a571`&4Vr
zXue)BT+K{_DCkLZjE?YFePm7zGo)i$gQJ8O%v$~)Faun+(2yAhn6$3SyjNVRtz&Y-
zB66lznG>}L(vSBZWR|%c^e4~%&<Cp`nCJ;jkkEKTB)l(ssefOVy^cXFr_Z2d4Jg8p
z>e9VAwj>>QNE<}N;9hW%!&gBnqW!czrvajDOwbqy>vU2t^$+%z<SupQ!del>(4%d>
zlUMT0bRuqdlS&oBYly}*a#+d4@cp?(Wyc-d8b*S#Vk*b6f@58fUCC4CZ%8J`D0-wA
zw3W(YRmtRWTdoYC`gm{)$M*i3Pl@#UY^JE82u%6j)gQ8S-^`HXS6cE+n_cH_b$E%P
z>XlL{_{kxP9r$clEnA`L`(`LWs}U&|zc4%9ST~@Om;*Fjk!O5GhAkZnEcM~f-)Olf
z!?9bX`Wv%OC`@m2<oFe9FzHlg12hJ+VoA}-`{!#^icwrmYj!)R4w!APBsoSVblet2
zN~ib9Chn9m?M-t;LA-rVWkwEv=+>-dmg1*C)iMr}FH|$Jqf+$AGnP?Bp*MQzk(>@D
z?vm7=QEDY18NyMyQ!P(uM<~%uPS}A{CUT=0`k^tD*HM_%d#TJYQA%CR%H33lahF^K
z4VtVNajAfWh@GMiL#Qo~G{gNmdG@E^n?6&tsrR<lr|Qh8DX3&M+^2cw^q&bOIT<r@
zDh2^R=Vd-<IG$jK=zQ?CqvC>PuBK$rti-$^EN>rMY`r};_Jbl2EhhTkmDylERfX@{
zb-7ve-FB(NeDjWGduco`bsWCGah$9f_FA)Vh-Ugk>PxN=pvKHAQR?0~P`uGaad@on
zTGEAK5#C~7^9^`znQ^0Ed+|X-tB-Tz7<rtEkqwpp6y2us<;QxxGzwkAqsgYJ{OqeP
z#3KBFQ!Np?w3fe6Al&kP+;g^?F2V8$CTN_|orK|PE?`C%Z>-puu(N8A$n`ZVvo%Wb
zZTZTSAP@f#C~%K*G2Y}$(=}(ZIGO$}{b{j8^rMH;Zn+n!so>ZBj7ic!^j1%=WC6_<
ztld~Fp+jGHqpdXt-AsA0e?O-@m+o%_u<&Fqq4RBs0t1}aI0}Z1!yM8&!U-F8!J>19
zA-l7bV{tB)*39;k$%)?j2{lIY-zGN)n{EuV1VH(D72j{szes$U58fu;u#hPh%1?OU
z=X#koWA32K|F>_r<_ye%9NwX_WeRaCT{QXQtg@xqkmjG_-I)6uXV|Ot$tSgeKx1jw
zfqGfTal5T8!Zs9AT9|ErSHx|<ZX~fO*cUG%ijqNXF4@IbKUY3?FJ$p6=-_Sn!G<MC
z$M?s*X5U%ILq=TFzj_>}?8O<SBq``jy^L_?qEDBWDBxhBReE866Cow9t;gz{OtTRu
zG%0$+DqzpS%kcP6wPF|7jGyrUTnn`J5^k6&t}e@Uc*lX7pNi%8Lr<6l3%KX>T7KYF
z=a%oc(^~VD_2x_Yf^oAGy`ZK=F-q0WOnJ*O?`oF(Ln(DEFrH0R?9}L~7_uY<XWvSU
zY2|je3{(nO$-XLBv^Ho!bVbwgfR+=*m*zfaGev6?e?%s?j!gXBUPt9OX{&8BBzVCK
zpu1D!3kQ=}op$9^83QjLiawzQ<KHC%S1)?b6gZ^7^#6p0Yl9P%_lhtmrtHNvGmk*a
zW+vI6g7H)HyRM8Lh|-2u5^zUNy_{&+jGsAPJ<tiNkA!js?MUb&Hb~jm1=38r>++&K
z%RQ52cGATo0mi92!bT>K^RKWl!uFpG9QgJ9*5Y+7Y{O60Q(Z>^)K5|BNgghD6^tjc
z3@0_x6{P`@jfaI!b`NgS?gLTXhx<%G92xYyodSDK-aM4B$$u0BE+|5C)F^Wk?UL#h
zyufP7v@k4EIrXUL`BF!nA&C>L;h-rn#o4-8AvU%PDPp#u01&;Sv@{}14yaP5pN}3^
zz%3bIOVWh05foATz$xkzOA1VDyS`j_BAfLXGjKLyA8M{Y%!x?SX{n6aC9Da3n@m>z
z<5cS(D4K?%>#W(>n4h4gXscgw7GHrqDFOm_**2?kKs4!zu~@Y~oapTTu0^#xkXv0-
z1)5BM?xVR<=+h#q4-c3EH<E)t1=VjsQk3c6!c{E{+cNM2-H4?K)s{}WV|QvW`=^~`
zRxHHtsh8Y#fC=>()e6Uke#7{fup3F&_$S?QT0_^%r81m4MlH%eMQz2Gs`pC6y$=c4
zG}Uh|2)G;1A7kO~=QXaf`1U;wsM2+kt0o>Qxrr&=jkL0!I}Wmk-iZzdFPMPJ@JgAV
zmp(IkFs0RxZ6fMR1%)s4Z82#R3@<ST^ZO1;Z<Odl3Y{RyhY2x$X@-U~wA-W@3opef
zVYG419pzAadg4xagmM|r@YJ`7Z@lNLU-Lz@UB8b`etld90_XR=I2iGtzk0+_SrB*B
z;1*OqE*#@2XoOi`%CZM|$lj5!Q1M`HKpsTOiW6RAELG!D-_P_I2K)yI&<hHJLO0iG
zYY4@JfXez5@zW)(3;`~h90@sJ#<{ct8DILbik++JOMJ-`LuJH}{$Bq*WtQQA@v(`&
z8cr<Cx4<oqybDdgzZ_$^i5u;sJ$lhf{GvjrEE99s24rf1SGDyPPSU#c!uwc<#fS0y
z*N1kOkWzQ2k@oiN@fK=gEn`w#Hp@m;5p>wNEt4qeze}m$6b)R4q^95~H@!A;+f%3)
zz2+cxp^gC~WSYuu2<bP*hF&$!f5D)%i_EwqA<l>sA()?Ro$H7j1sluAy4*lgc@jMf
z%{f{zKe+E5LQ|J0HeJThG!@O$$MMnqEUe1g>_51k5Xo~mzqG6Wp>bZ_f^n>+T5LR~
zie>A))c~Um8PN3d0KnYVI?>KeX_v}uo#PK_2X+Sb1U1lO#yA6EqxwCDDuG>1UaH<x
z(t8&?x;X*k_3!ikmbub1tNSj!cPp|7-v=8gmTXkiKf~lXb;Cn;A^S-7GBIxKrIaQ1
zz4howEHrFj0cEbgLrhS@->pAPnMIRz7NLD9sa*NpSBM?CJ?1&nAqA21y)fSau(#km
zsoBJBzY8P;HAdtxfP2q}5(&o&O1~~*HtAZdtH2V;DU1IP@M)=7HmFY|?b=@q)lFq%
z#?C|k2sj_FnpMUfNP~FgKd>8p<p*fOg6H7|M)NGMg<Iim9T<L!+u-EX@CnG^iMPon
z?IKDw&6dM#mfj#*D^*)sMSXt$ccj$&z;sMsM);hG9DAkBo=s@$R79M%IGUH&a^yUF
z*gFeqvew7k#;{A1WL&jqCNqYZlU`UKo2$B|aW0?dfuHHJgGT*oo)j8gEUxX<n}|e#
z$Jvtc26=NFA3aG=JQO(ylH!Aw1W+Up3B^p%YRq_Dm`ulgC2MMe=l-OPpFeY+K7U5v
zs8X2PD3wS%xf>3Prt+irZ~eVY?6DOG$#T$0sB?Z-%pLXPisuob%^itE6N;h{oWq}t
ziBkscK}yOO7N1Qj5|Sn;o`^X8FjblZ1LKkf=(M!(<qLx!iz)IfZp$*?yAcdoEbyBu
zx4%mR>D^7alZUD>Ab#CVSBKp<i~$)Q3+tquVPL$?BgbB<sXgM($zeStf&t$xPA~80
z)vz0(@yR142L%(+Zr+0aqS2W|GjyRGdM_Na&4e8pIOX*qe2JOO$6sG9Hsw#580#IN
zx;7Ch`*(Y(d2O)GA1(FSOL2sf^-?2!_k~5rP*YlgD9y1|qLGOetMYjwSFIW4^x_1)
zBe{Y<YFnGfv-72pLoM(Y_O$M9Bawh?nat*y9DsFneFL`frEnx3cwK<Mqis9&EZ!|v
zEJAdSXN1($rG_e$Ck|I(p8}}fP-qi{1Ei|229^ar$6HICV83WhNd=Qv+d8+dOYrKu
zfhFfyirH<4-nxTK6E+u(KoMe2c9ri|(gU>vn`k>~TNcXQyTh&9$)RPF9kX&S%OtN9
z#>Z<z-#fbQ<8~2={#<xl{XP5~;C6&oqpi$5)u~}p?n>#18zs^4_(Mp89{iT4O~?$5
zt%7eeqX`_;NWc{%3P(A9J|xwUqiDGX0AoXn=YoFgS7)K&CvJX0`z|7NQxTHWhgYxg
zEB{<6lAfQMtHOS)$yJH9ViPV49c7W49Y1NXG^KvbqT0y9zN_ai*sthJHIn1-MpfsX
zYt$lU@s0KFmU4Vj<+9A<qnEXO-Uv;y1TsO;5+i!ur`vzjMT$(UKVO->%Jr^XU;7VG
zHthGY@?!j7Mqa(>N`%ST4%v;HC<+PO&0q6U{7hR3cN%K7|Es3Mj$PX^W!BPcbfE<p
zNSm@HkZ{*dtn3%os9{Zi>4_>ZnCZz{O`X7Oo=?&8OBL4^UGKPXMk10^G(3CP>+7+}
zqnwDduV{Bcb&)cDx3x0m?m?c=Y5A8Xtdp_-0i2`s*+3sHk+}(}G1$~Q`CK9Gqe0{G
zRWkijQy+ediBVJ=?h4^LO{IVM>qTsw#N>}GA6;0mj~Eq<5#03$55!ydFfd8+%{b}I
z00HS`1alA+PQ;F;C?tr@kA~tjN&4@ri~a+c{vY`R+qzsqDO`zHQEmS91)7FAwv;mh
zlsF^U)#HeESX5fhOVpxWke*ZY0=rz2x?UrF`p-gCg{KT7Q~2#w@{eKO_;0{kKS)YE
z)LiB-r%AwXY`O%!FYfJ<1VKxX+ns1Yj~E6-amFc(?^3-_jQl;P`uM{Lr)bR1mv?cV
z5!%wYQtC$YJZ&%cEUb|cl=>cDEC>r)vMdA%6P-N!@K;Oo>|Q--TUZ*_tyN%vW{elQ
zJ5)^qnXO74PJ;CHa!}|(R79b1)NslaPi1OTIEDQcFnL-ZX%wQmlf>J~@KtmMtigq3
z`pCF~e)w*pv0I>A&f1zPqE%t<pp{u7`>m{Q3U{3K&&HaYI$oJmV-~*=Y)f4?EGp3M
zYD@&E*&?MNL;pRxKqDStZ((^^%V@wZzqN=i-}52MIHp4+16``8QS=QFZmo?m9V{SQ
zj>*K3E&p9LHF3~*l2X?qn=%5VK*akRg}8TFmk!!s0aGPV2bZhf=c5Rl6?uFq&P}uk
z(rqw$3rcD~CK){6cTk4G2CPHJ?3<Egr=AtRLFT=VM_bAsVod*2<O38Y12KdlQbKoJ
z*}&6}Lv^A*@}T+{Ce?ROTFFJ142s{#2h9RDFZNd@@TDSpPrn&YJNTaKMVgs*7E?#5
z3`)T2Umj<EeV&ZA&a;$u-#7hxnUqeGnT*m<`PBFokbQZ<pJn&Fo@b*!RS@Bf9-i`6
z^0v~FdhO&N!=h2EyRO?wx#uHta2p1zer2>J5u@zZQMbw?^)htsQ7^(ZS#$>R8Z>G0
zTYv6lU`ia3_sxy*?6D`a(<{kPE?Wz&KTN>?0QC0duSuY-7T%5C$B=v;U4rv|SS0s+
z<SqiB_ww`curjrxKWk-QxmMJat_T@z6!7Y{A}V6W$%Cn2aY4p9G2NO=bu&%6Wr#xb
z%rRczT!Z<a&t^J-Mznno-%aEvPVd&uN=V65ek+dskD!o+A-N!2oxc}|tnxAG+2Mde
z*Ks(0wZ82ecyeh~Z5LV7X@S_OE>pQ>!44EW!O<VnzmTT`233J_Y5>;jd=E)j?Hg)`
zK?OwL_lQ>NHt+D)3S}ggX#zohRIyXDkXCFKi7ykcFheGPdz+_~^M<}l73lxVHG@#K
zXjYIJIp&LBE;{0T4W>S%5m4r}^K0sYfAq)3v@s}X*YyhDOA5L@e~;-pw&fGQ%p%zt
z3j203Pk&Dhop#qQZH%H;<5hVnrS7{)8j=bdSssx(&FknE(csOMxr5i^si5islG%TX
zXc^D{$jSG;{}A?<Gbck!%oYPBxDUM^*^4Y)YX9rCBWgYK5Ky8q0O^oy`-Mv-K!1O#
zNn^b5mehXBoqQZu!%O)fkNMbWy^HE0C<8ulmZ}W$?9<yRGSgV$YZy;bM<i1f8vDM+
zrySMOm*k-7fSaLj?izNhr$mu{n`!qnToq1}hKDr{MOhW*^l&Zv^zai>_FHR>QKy`m
zu(&Fx37&1of)T4&qLU=1AHN_po80(=&gG1uy*<=Qis-y$w9b>ha68rNoHkP2M+I?R
z6}fn&x_a8cFikJc##HP706aKPl(owV%kGD2BK$#k)B8W#_2QVJvbbZzI?uY_z~u}D
za?`u=!&bkd3wLIARhZN)zhE`TCk7!Htb(C(Ld;58C_wbxdc8saeeI6&g`?Q8((6^F
zi08*A9kn_3U1<4uDf|`sT#n}!kY}L&*FnvFso=;*@i>k)2im_U3;~KxFxAZnx?p>(
zbXpFaio?|i(=bmBtkO$l9+5mlg)~GBIjgCK%BTLH7ex`^wgOpbjJ+#^3l*P(s9@4K
zpvn?y<<U_t5TNfc&2cKlPHGnDAgu>LQTnU&t|S})R*{&Cr(_2_2<Ef16)f0=6U?#~
z=>ST5Kt;0vb&66Z>bV6?v}p$^cAB6$87%f=#jy0S7Jz2Jv4Vpn9zd)l?Oi?(fGx<F
z{aoe+U>72;h3aGE5WiAX;YPnLx|#yEguf5`AGaC43`Hp%E1Y;FYAJ0s{YnNau)HEo
zg&2VWq?D2erUNR{M9a%Am0ldHpyX@l5CK%#<6#dv>cZi&k}L!Om~((CbCjo^ML}|W
z4i6=1Kmx5{%xCQ|!Hyz~&CE17Mmd0o=6`s-|D7vQAD19e1Auu@R);;h$u6w#WoWX7
zdXaft(SZQ2XQ)m{KRS88>Im#}0Zip1MzcItK(IE_Zlr)xD%Old3@4Tz27Uc3<rFM=
zNHv~!lTg-U(|SLE+*@PbZpk;;Rd~zqF%NyPiWYG!LWl8&^vAe6>@pWbGM4?<+bCGN
z-+KH{+fD@p^PNDI(7JI5)0O1IrrJre$zhHv2gN=4CR;z4C^S;EEI6qJ?M5x(A!&9`
zvwECpbmoC~@PG_3S~V>%yt)daF8}TxHCyUauXklIkn2ut+_T?XB3Urbc@19bzS<>`
zMg!d+8%!+iG^Th~4x_nqDzlicwZomkIBVd_xcZB?+-z)7g7%Y4r^u@B*Ms8X<O~{T
zLOzbW!8x^*L$HeNBrViXMn!G-w_o1x=kJIq%y`BVw=L8d8^+u}-JF{D?6`6V7!Tit
zqOXcV3U9x9NGls0pI(|9{c0OrTCHgF=k|Zl_xE@?H;!*Db`~0zu@-PM1bv8Y8FzUz
z+*(Xs{W;fd<Uc^fTku4+;J{(dNz-rt;itYpvlf#M;y07M!tanRWIw}uW$t@fBh}&~
z$&zN5^EcF%`6b4RB=}s2wp0v-@L?jv&c1@$Zxs{;FT&@q=m!7V4>Z#uC@Nw>q#wKp
zt&AM~J1fcwKc_ph46XdY9dTNmM%0|}cdnbRZxGl<OzLp^swTYEZtF!@lYi&Qus4@Z
zkN&vWO}67sR5M<E{2j%u6_25YzaVoa1ZJTTb%SQV>uUp|<S1QcO*r0#UgZz8XU`?0
z3qWygGh3sBh(i_#F-_}DpJzjMx9C1gv(qG+{vt$|_=NTQ!QfXdmpiZ|*b4p8>!yWZ
z*S*r%|4WE-?di3O+eh0j+mJHzA9r<}fqvoDtJ%!Cs2_%SsY2TUAGz)(#*o$Ot-EP}
zahVqk{TyApB@mWDgd@r=QyT-GM9pyA={vNh$^e2OVR!#nEpLk>$tN1$nR6zS`&$HS
zf-4BQ-e@SQd`JrZnJRTMBBnv%wjaFsHJYTPQ`mc1a0KBa*}$}vHXcIGT^@QwLM6Nl
z^|6T>5m2*XcXVhNkDI}?Kqhw21C<%CqV9mjDjq|2W%56g51F9MoC1C0RSYRv7-GQ3
zD2|O}dG%=1&)jS+_R4Nn?a^KdulCt~)eZKUi-QT|h03R5bAa&fCR)X9Q<_Bhr%JJB
zL5NloU*|z=cY9}kS(e+5_rNZ>s(SePm2e|b8(iJfl{gESbY1+9(Xmr8>aA}zEnTa;
zt?(!R7b6DWX^S3ev(HoAsOmKhARBF|`|uat%cPT}c@b>y;1cU)XC%MDL(s5}S7}sf
z0yGo)ACpn8%X9Eh!7JqG>X}V^I8gn?nxOqZz$oPA{LGI$RsHJk$fnmfuu2!tXxty=
z|Hax{M77nw;o1QTv^W&^;$Gaf6xZPH8r)q{JV0=F*WgZRk>Vb-SaFx)McVh|Kl)~8
zoxwLv_DUwnUcdd^&wX7khzZVC2_enx6fx~f;ho5;aRKUO((YNE?y^mXVX4iQFMhJb
zuop>STZ?h*{#(9vcpv?MQD^*JyiWV_opD^-X0NOZvfT3*r@TLDjyu^U#+$5IUSmJn
ztZD5}KA&{7Q6-6V^+A#THHHR7=+Xd{@al}pQ2x!=w&KlpQS+^3E(=#Ck8)1*t0NQi
zg72$!QkSA)+B7!~V9Sc@l=Pn1CJQM2m(aI+36MBu=sQD9hCB@{966IO&s+N!9}g4}
z+S+Y+uPlX^cS<wX)2yXo+SW9^`#!EKTZl56A=*v%=me_P4Z{FC1&sw;y52b|F2_ZC
zK_2C;+EhyZ`@3nE;~rzFt8z18Qc!!HBW;-mIhwB7r~B7BAv3n%QeI~P$F`G*(FrKV
z5zKq;)c3iF?58{WrZ|d;>r}*I(sEmUhIK6BaDJ3qMR?CxrlFPOZJduv-)D=u_hx&!
zXpMT86Z%q%)~@hSe;KJ|Fdpo>hLGCp>Epj~>89$hmWy@XiAAnZ#87y=VM%4NQ=wcK
z4DX_H{FL$wv41iJ#P7|#t6$|2+|A*K)Fk{PlvrzidQW3yNe#-kpa~?v*Y<EN)@A_U
zrt4N;0L0t%GX%%M!>)8hart}QcQ7Y*(#%hGvMFN>x<M>W>)G1~IC94$imwo&l#qJy
zFnq%zem`u}(oB0#RGgc;J|SC0U9R)g`Sqzp8n;s!FlN>Vnz9g@08KsH^eP!VQSlg_
z+kiV1>tX-k_q9zwGB=J=z-uWk@**{K={zICHN$NTnOehrtU?waRFrII)6uD72=6;Q
z3XZqI`5D4>nT`A7H`lX3Q<RC8wU)6zCVuq=YVww=8V4OCDCpl<dXsz=j}Z>9tpOJi
zbl<H|OW9M88DILHkUy|py7wcxF?*00kh~Dev<7>mIOWTd2q~&q(uwpaL4}GvS~1r2
zFn`BR!nL{_+4MWCPL~jYRtvo2AnNu;H-U;1snbcHA*=2j;ZXDgZ3S|nnN$~#^{t9w
zSFEkBmM<ph@lHvyh9r1T%%qYz_jQh89tX}DR_;;>*p+#_{PTNaU_@n7A3wj$jp#k4
zy;OmU2UZhJ!CURQrO=2zBhsjlW-VhE!;zhv!mi5qf99$VEBP!vDbL5L@05RjlIYPj
z7j;Z_-dGR3Rl{c1tM4l;Z}BO#O|p>URCDt@I<TGwI*NMo-Pc$?=@7U(xa;9pmgA41
zOPo%BeL$c#^fbc~^o&egr1)&o^tGI;0sDdE<MLCOXMS1Og!vD9v<qBE&crrsLAzym
zso<CsU^dgQsYvDumnk%X&0R4(w2<B<#uOEowVxN^YQCAG$e@Jl0<E=msQ6gG>#Z4h
zC;r#lKW-X$rw_TGSDLwk|Abro2gp7%8Wb`j=hE?S6V?5@i01G?2_T*%AdCCwUG34n
zdG^J*jKE1?^!M%WglE^Xf(1A!j=g!=;i!M1=tO>|zpEnd#8CU-SDYVrGnxi>hLG-T
zPxN*euz%c=UJ%$kxn(ksZurkiCCV?qm#>HeVD$POl%Lb%GuRw__H?5u;JXk`vIm|R
zbkH-#z1g>bBdiWFKdq8O;A|wFZzZ*GBtYHa_0!Pwxz#FOt8D$;Vumq^VW!K)!BxV+
zABEZXmAqpt@=C=nQkw!g)c16h7<$N~=~agsKeSW6G}7nBkwy$lrO5zoTIAuh`}-Kx
zy6GtkRJCxPosb}H+fT;A(;vo7=t4%ZpBB6J1PEGcZyZwnAO7yhWJIR)-_=fS6tY-n
z&N!BXS0L7ky4Ho!1+!KBOB;d6AP+Zw2*$@l54jjCDVP$L8sCMq(gR@#^oX*8&3H@x
zDQU{w$650=d_HCfF1#sT!Z)_cXVkIg-LcQMDIT|qhiZS4n>hTP#ABMR5M35BPabI-
zrzW|LlLtk=6_}KA*v!G%pGHG72;pUoClncg@P-T%NZYN`wI&DI<u_*|GNt-tvfSd%
z4vL*Gj9H5qqxw#9$cTrbpl)HJ);bx=39|4F1XXzkBiSp$)ZI_cq*pRN#1&=SVT2m~
zk*+*mt}hdxGvCb9Z_PLNM4S<ZT)Mn#HA+fG1fO*BLOtCyxXAIC3f2iy2;%NOF#q=D
zQ)*uJPmQUs2?&c%r+#K4&O^vo+b+qaQ!Dr{ofvF4N^R?g%ljCnWX^qd?`&JQOqntM
z3ikB!glTqSQRXZU=G3zhGXDnK*&-hN>r}6(VLt>rY>n8(-sdgt-xVNa|KCW5kOq>J
z;3X>4bA)xh^A16ALEhn>2Nio@kX|cTQij9EgAQgD&9*8bnNfpN6@U>SmZ_*XGI}n>
zc9iFm=&V)vDTN2SjYfGW<1^GfJPEYYmzdo;QvC5z=0x}W{ICmQy43J6mRI^boN>Wl
z?Mm~$Ew=2XFavJ%himKby+C1AJFc*0@BOsii$t3>2?<8mKfKl1BV%&2s<LuyHv&Zs
z&y2i0XSss+a_z182v5b`nAzPdu~|7Dsg;<)9sq|AI9@Gh%eC&oWSrRR#CERWBf@c8
zM}ug`kXJ7oV~yjB7l<&Yod5%jNo{cY&Ro}KDCF&fI(^vu*$vkUrg&5K8-!n0M;u?J
z%@*2T9HoD84JvMj5jjd`*+pDkiR^&?vggg+t7PBfw$@BBS4s;@?U>5Jr<)WL@wI0b
zh6U7U*=NgFO_;{^@uv%sYD(tqJ2iJ5#s;4F^8aEhxOg!b^2(73ZyyQQxodp<xc~3?
zk%+f4Z_b{zZZLI&HQHbSv8+RT*ql3Z|4tGZ`ji;u_goo=)@<{m^eKCml5(X;<zbU<
zr_|npsHvhy@3+yrB;<d5!(Xe2N<eO8x^FxQ!oGPx7Uu5bo$m2Ainw;<dCso%?E7+u
z*CdYj!`^!jYcovbDde8ec;^}1Ann_ApPW;_!^lLCMt?G17hTbTPuaOn2bC)AQPuYz
zo8eX2<ufks@2J$UxOw?<7kl7#V61F?6CWx$o8Fpj$_1lLp8QUr9!`a))y+5~DCbPM
zuDf>4RJxm@HL2h`oA%&ql>lXc8G<PJMda#4iw+BWRiNx0INA9i#@cY^-G6{HZP-5d
zcyGS;dx8E)q?-%LcC)=g;z9%EZY>_oPO~z?x79j_33!g@(r!kM9t%$kq&w3*1LAvh
z$(<(TLis^+{GUgWvvC3!^7r=$H>_Y-Z;!x=n)vXdgaj@8StEd};5Iyqql>@XE}glG
zDH-cm#t4rZ;iD?$!(%xn1mIb-o*%R@7Y?$f=8T8>*B-B)vV9ureGs7YS}vXC|5L8(
zEWi#JwPHZ=cs+ShVG*IdALBpK;X{*AQ?R{AxsoR5KE0L0hZ=M?aF_d3eA(k=w}?c^
z&vo`~-jJSY<vMp=2O6PK?4_vh%nAs05nnd)pJhMv?)0FcNJVM;FDks$JffWP=r(BE
zY~V<+rifr65ni}_8B%0Z_Zl`?kQPD@c=Ax=zT=vz(__edyN5~6>UO0|9DgY0X#QAk
zsX!*6=i5ocfu~S-p#$)hEIZSd8?vq`zhgOWQ~QL;5;09t7cnnFIPLXA#S2rxg?>b=
z*(8*55wD^vN_Im?YLK|jbd~NFUr&2A_W+nA#D~s_^`qNcWD5b?j@lKT>Bnu?6C^Q|
z>JfhAUyR!G$~f!@Zq#O)R)p=QG9^z&9J75$4=&9#2RU;i;O;KyFym;1zYf_wC^vc}
zZb!l3QBwMjt{mcEGnRz@1`_Sp*%uLC+WctZ19K5&r)ef_?xzfHk6e>wr7PWkb2eUC
zkKa6z)W7uet}JnWYV{m&p+p3h`+G!`UeLi<Dq=zK318DD!5-c^lO=AE@gY5wsFgf`
zGx^;EqE+E~V`fg29+`9*MYN)^6~{!FP^%%nh|V=3zCd~zxZ)T<1nXj}&dcyR^)gwH
z6+cv(YYZ8LeTbtlSTo)?324v|YhG?D+@BO#4G-RI)!&~p9nW0hWztafP;z^dSvz)3
zXg#8))ihq#ngLr8$LX4u+kfJv6g?_=sQcY)eK6LWyj0`N5sCC5xZT}<bW`7uxouZI
zHgpK!zN=Zv7;(oX(pz3u=}jXq(LMD`u&OsXf%nUDPJE!^O98U5U#i%|@#|gOJf5=~
zaft4FpYoZ6jAez2k2q8Mo$0%LbiKG3d^&<oecf%Xi|OeJ1os7gP>fI&`A5x8tjC9P
zz{Rs5;9_qdn{(hOJVp_y=M6u&sX|#0s35(mBb2ww!JWzT`X$i2^B({e6iU~Pl)t`?
z|6?+G_RK)u(FAFTroqYl^OArH8FqVQJxalV(vDL@ereG+yM^PA5OKCGf*vsSZ&Qx1
zAsa4#outldJcy4sRiGXxdIFOna+M?`0|l!`w3jF+hC58MX<tK7KUX#u&po+ah2O*{
zlO*+kgv&iQaV6UYZ}hqLX#yK=>aE4zQ5Wl&w!{fd_%qYPD?7gi$-i`KDA!O<(xL|H
zoXk?{jGKb!OXJ|zJT%&?UJ%_b7lEIyrM`(h+($%NPCOl<gnQqGVJg|vOGT3f{eBYc
ziCes_tN2DvI>~=aCv@Bc);Dy++NR#ALnRzD%h!5Qpu*EC9EbqZqITwcCcAf@h4(+2
z%r!xRO+k#CGJ%q6^Z0RH&g<rYy*{r@%_r_?4w}VWcnr`WE4Fmo*C>wlj-iRsgRTM2
zrjjU%nJvWiCemkGC#W*R*ljXpPLE+yr0bThXoB<zGc}A{`C~PmSe=N=k&lh=ELsjx
z8zLX|>7w$z)?ePdGPQg$iR%00Dgc*rK}{@{?P^KdC455jtaG?gM4Q4zV2F}rw#vtd
z^vQO*Uu%!1X1i=&I2{cK+^?^=xknoV;}#F*386}vm||sEZ#BGbb{onY%8AYjm+Jg%
zTE1<AZOr;w*cq?RFB-6TC*#m0ujrxzU})1w)uIX$w{v)bi>$kX`nGKKGW!VbWYv)(
z)Us;=OAtM9_;aDiJ3DlVP@@@s=T7`Nvr{GSAKA!4CNLfSU;VS~x*SxYas&GpDB`*S
zt_N|xPc|Vs5l`AWd6*=&aZDCe0aVy}nNtnQKa88MbU*aD?6i(QK~FcM4fZ2@h?9%5
zK(|H}!o6=Bt(^jSZQ{5QC*$^;Erto$J6g|*0Mfb=rWYGG))eiRhy=Zx*h5Wv9gkBv
z?;%a$A7VuWjnl`VsB@0gXn6|7lVhjW@4sJfN-~Ah?VAwc_7$gHR0b1;aTAPqmv8AE
znYi|Yh4!Fj=uNJskRUH&U^zjLc_nj}o08!bKB3WEEZ3U=$7gI=C;l<9@z{_hBN~!%
zI!%%J@7PR9G9${ZLW3<eO<n?tsH_}zndZ-!`SvGz=#u;VhC-vE>RMvgt@EbUI$Zbc
zk52T+a7@;NLGuO@WQS%%6j~-~u#Ot<r-duraHiUM!?6%Vu<z9i^I^)KNb@(B%@eEt
zFn;=J7ba7+_S5*uUAj7=xGuaw;kI(}Ut_{w2S)=O6`cf*yygW+-%g15hIu_SRA$k-
zLZ*(DLtfHX99dXk>5u2ad5>QX9o1ABEd=60!DX(NLxe8Ts(AKNs3Bm`op}_hj;q`!
zgm={E@WWn_`|VwQeAK$2{z~pr4s;KCU*Jv#RYO1vi3ay0G}Ru___Qxk-4UCTs^I=v
zc#~~u9Tv2m?Af~}?>kMwr#&JRdS}+^Jju2Piy#b$Y|)vb)xB`B2ZH!Ks;zAiU@=F>
z?byGMXl6MA9w=&10pb=#Myc;#=I^UpN6iPzV_!FMc-Cqu;_~MI4$qo{LS*r$EFkG#
zV^RgaWjsm<pP$w}^<wrYJR65F(z>J=fU9hR(CQE(fwgdz6W(8GP(r)zrvdW&mlv8Q
zN{`ZHlHD~-?%_o{_X1k)k2I1!%kFE)d}lZmGPlzf1iZa~Na0cyis(d2fNlm|D*4-U
z--dmpl*QccU+7iKUFIaGlMG*$`ELEN*TS2di%mPK+%LL29v&NJNQ2YYPt5$b4I_G4
zj<Ech`aUSgLfghjBr8+pwi3`yw2tyUa%Ja^Dgc(oBbJLQ9&HhS$g{NLr{fHEI<7TU
zxLq_q^+M4+(TM_YB${ykwbk?VgiYGjiUHX69gA`jH5dN*4F2YWw}(@B=)}>x1CH8l
zPlb5aDis;W7<GJLVlntX3{niV`d9SP^sO{Nq?G5G??Kvs8*an09<?ObLrzE2o2x%-
z5_*%u9O*IY39YIpN0pCqO4(gTwV&aBRW!Y-5&>ja1}!l-*uw7@?P|<Gf|>YFY2&wH
z?$jDP27G6^&|=j<pR!Mgl+u{?FkCb~@ze5z#ESMvBs8iCvAu9z9f0~R&tXAncFG^Q
zPIl*KL$*?Y*u-eVt+8+JXX0ag9jrhMYZ1pR(<K|b?k@j5sR0V_*V?73$Q=wAubcI_
z6~Y$n)S%*RR#eC)gX7MpylrE2d~MvYx;H8^?J(*9aVNyphP1a77GucL8T;%lSKudD
zS4bs1FMPQkMkc2xED6}--&xL(9>0Ko)kN_<f-aU-ZH_LN<@#Hg!j)scHEie!T*Z6G
zGa|xb2Ks*i$&Lvd+rWsG;`;`Ivt8651OEY9>%+<V{ivKc?`a4?&SwnkL|K=}I@(Rt
zi9Xe9hKUO%BN3Z*qEdt>@QrNCkV`4Hot@vC(=#Kz-6^vsHp`c3JI63CJ>92*K;k18
z9pX}Z7p$l~?1))VSm@pAr*g%w`8p9P8!NzM9EFl%oWL804fN{g`H`@ZaGcf3{ksb0
z*IZQ^5E^~84SPbw`f{BTG9kUiXrIw+&Fmg<ywkEW(sDx{QeWNcVYuAb@f+pux$aA{
zUrNzPEBb3FtA#qQ?0p^nlDrowvsgE2r4kzpGXhzdcA^6KJ8`>~{hR*Ye6W=)FQ8hM
z)kg84pL9b%!eBw(3<xe7>=BDyvUUdWvKLy%bu=zwG<*@^^bXKZZgzenj3MXyjL(Ev
zalcK8SnJXtz*}L>&lGX?zA#OSVVurJafRc`4zpZpbAVWsiM5|r3eDMI1Df(WD`mfG
zR#*RB$(j(CfyVuRVt0q{QEKIq^UeEln;rI;zIUnb_hC-Zlc=ZT=M~*fGWuR=LMHHL
zhzFgXee7Ags)Sc8zO{#l5do=aKpDnoO>a<iws-Ms7}${}{oUtfVh_<IRgEb1tJ1ar
zkKyF-Z*#Mjhl~DeL#OU@q8nE*Nm$BLadhJ%U=ZUCOwlciJIJt3G%e@>uz&mgF9o}x
zXPV{j4ynjJ%mP-&*jo8}B*m%9D6yO2@2<Q^)!Eut_s%rD$$MsTB*VwR^#QaW^p)?9
zoghp1S!uyCvHu=KUXRlwlc(Jb0&HwZ_vld&B?~`4yGd%$j|M|^CCPgOaPD~SyDhK+
z!YNi>!Ec2qP|Zt|l_UEUzbtgXU5=K+39^vW*=cr|3ieeAi&&c^YF5##5_EQFwv+BZ
zK53JqYmb%oD@YSwqvV=1M977|Og6&v^0k`Ehv_~QmS$s%+ks1h=2)dG%8mY?qA0gO
zA12}AH)Vw6EO_Z{z$9hBCx>GPaZSfm{(t;khgp48&vPHD65tQ_<+O;_7r$Q_CHzjf
z5*d$GRO@9ojjR}@5e~icJ&^-^K!+#T!1r=l007{9S<whI9Z-M^V%30sAl=qPj!@{M
z-A&K`i)ezS{Vs+8%wg1v>9{4uC>0+;JPI%XjS<Vgbf03B69_t?Jp>!@27bgJoy8Bp
z5QW2i5np0t0{1IT22@;~$+Hab1Ax+J3Lt<ehGbjB?}||v3f8rX(pJ)7I2Ih5p7VO*
z02oH(h51?!<;cKXBV_>ML$v0&%LvoE55ZAf0p%CccZiS=@rIGIkqlykL<`zxm4GBY
z{K`^UC|rSp98L@o14^U*zZd=f@7D@6$-f<YtkMkB#HwSA${%{nY?6AJk1%QI{=Ghw
zTkb~NMhv&EXSS#-{BVs^Qt^40lUMeHMQr7!QE(;Lwh;t;8#=$w?)6gA`MlW8pyDg~
zF?tKD6@GQ)gF2b+MQGcD<ue@UA-<9m%zurd;KG#^CLYF49NQXvkv6;BhwsK|lQm(S
zoe=TI4{M$R=b+GGw2xG>UCqasWU)xyIPyiSVUIdsSQ8)gECB7ce^5CN9=q)hphsVU
z{6>s8f<+g-MHqV8FeNfQCEaoq;NQTb0terT?y=Q4hii?~+oVP)uAcw0s#u6K?H|O7
zb8j!Q5XpO~cWW{9qo3&f{OwyP**@EiHj=T+sq*<7iKx$L`o3k41*CabisE#OE+ur$
zda&Ww=Jm9f&6mw)HF~sMJ-o<5jljgYmV7^|T4`=Iu5%2(H$k2K-_J1<=?qf01eVH3
z^SQ?@XK-&DzK{4y;xu(QCE6>8zw^J<qgHx`{C11>GwS&>{$c*`reKBlz>k%B@1|jP
zclZcGu(fJFOp@%$hbL@(Wh}qUaqHsaowZaU%8yI*?LR<<$x#we7kwg}yz=JKeKIL4
ze<?kCBK{_7)MRlZGp@|^sC!nx)m9NE?|<&0+QCY*WtqyCu$ZNqgo{q=M~G(=y|tYX
zD!>rx+>*T$twd3Yd{;T{g^}^YHl3TJDj^9Lg1;R`?$2b3!_wceP@#*gc&I7zAaTO7
z;VVvjq>+ny`!25R9z7XR*_uspcXvk(WFE$LQ~tU%6=>2lPD(aqO)v4(D3J5`x?XF-
zfnv5r7kbTk-(OB`1SsjQ9-j@A7P*iMFPhxVt&3P-ip(!{5r5GZ-^-sv&19RLHA>7u
zfG^*r7<j48AR=<!9}%u7`^5V?*k2^hyySickac<uK3eMfU^5-U^~8i~L~tZnRIvsI
z?yK-{=^?rRsE0aR5anM7Ktg_)QI?mrI9x7+nVza<C&L)v4pOpK*;@`r$VDDM$p>n!
z?we3uAB48OZFj+{1&oAdl#%3?zec`5fZ`6{Sy2}9wbc+&h|)B!G^f0uPs3<GHCy}d
zii@Gm4?ODn43vAnhz1zv^!Becx(bQa<rTDKz3ZRuyA|*M1CR!rwLsqP%}=PM<@kMh
zYku8eto<jW6x73RY<9d}#Tu22%0PZIUfE%Nt3dBn^j$rAnarGf2CwMJ?mxhuDfPmq
zIO>U+eevZ^5_HNZUM49Zu-IVFVqSsvlBV4>{*l)Uyn2f$RH(#00(gbTsy(})ArH-B
znjf30eG4{g7w5ieM9lqWBcP&au9ampC^Wbxw}GOuJE_5$MxJbK_DUgDWvytwSd+IH
z8$p9dR>bCE%KJam{SIPDN@Hc;YN{Y@EDT+^^`;$T+i@h)U<!K8V5@hMjd-P;m^s%>
zJX(>3RIQo5XO)L&kL--qzq>}CFu)UooD7YiUr}I$sOdl^)xRz3VNaxT19<3*ob`3d
zQ<bM2O|vu4Ja@_!8F`@fBoO180{V@56kM~VV=v=T7pHx?5#jBa!){0ZJVh--uK5c6
z*(nX=_Q>vnb6sT+$3F4HiTs;${a?B5j@8OGLk%*QZ0xHp!waw$BJ~Y-kduKai62sr
zzDc@^r?X+EFO5$v)w#Oy_rL;L?Z<uTkdqc;Q7AcIVK!)Fko4>I`c^ugFc}dUL|TI;
zL!h(H;#ws=RqI@Me=%qisx;dtLNzehO@xnQobtR>%sI+VI<w{t%wk|6dlarNNdjE*
zKRAahO!K5pg03r{2&sd-fbXWT)AyFae!O91^k=|v-m$OMZvrtK<RX_2<kpTgDk+G3
z#q!jYsnYNo*Ck}?=@LRu`9fHXSr6P&e~!N*RM_#JtFw;6n_03GU6k5fG_Dxn-W37g
zWh!L`Ovb_5_m4E#!-7|834%L5P0vJozst{oMq8I!L+&S6`UhW=i!nE>suLxjG?lPh
zXK5biD7DSD&bjvEJ0EL|XtlmFe8W+?(p5)it}qi!RUQq{b@S5vO8q(8$7HFJ*Wl-8
ziwI5S_3XzgzUBwQkLm%HC_*e|I>5tX8W!Yo&xEfE(f88|P5Aj%;6y9Z!wkXbe{IX!
z>vxq=h#i!V90%xXTO$!(A5bg?5F4+QzywboElX`u%EdO+KMipI*ZA~RToegxU~jXN
zr(vkg{j^#}A#DT1zXsn1z!p3{S4YirS7U^f@@3I7#@a~3n#`mYRWhPND?5PKg=MH~
z59UywjgM~YeyT{<D3_HW1k+axzI2xt5vZ`YNche<bUgwuBg}hG7rmi4P~?D;ubUZ-
z<+((;eEWG6zZtlx4(duj!cGn$)#;!c%_60(%|D9BE%J2v(TsnYp*=N9HVRLk7{Hd5
zPO-cv-P39sQ}O;#TkqFWo`=}GuAbKQ+xU?(O;>cowg^<B5~$elDo!O+R_qHHAgbV7
zJ57#l?BKIT>R($LVwlD%w8G8nkaJrF*&T}Kv*X}WoiV@DUKT^j3oECR{G?o;Vt?SV
zeg-Tro6~!3u~lxl(%Xg%erpQSVo2B}mH<CF8O)q%c0s+MQfvmAy?ZV)gu|Y=Q*8d1
z7vn=iEQpOWhQmD4m%im{T<baVXtC^aQm^(tR5?FSX2iWJPvI4zyG565Ta?Z~a9^vI
z%dEi~=za39h3yvH`Ec*5aMAb6(I(Wa;qw}AtlRnegb^fofP0NB<)SS0NLEQXzj5c&
zp$=tWZm&<(STi`E`e*$y<LW?<5X{smj*(W(MklvSLf#;TN_1h;n9GCI`Z7?bWdzR+
zC1R`ke}2EuyrXMC<G)5JcNH%l=G_?9TXogb!eAMO-KW{#w9ncM-6=1N-V5NQ16A}m
zo0G1+GYtZ6vaMeQ(i()WW5t-6Ei<kpnU+SW^%K3n+|5mvN%H6#$9@Ds5~f*69c}36
zI*IaYZpC7MMd)SNDW-gr-MEKUKPr)D4hRg!F#lSsU*FnTSEOd1ec>EKOxg9k%0l9r
z;lD=e-le30|Ex$nd=yw8%M>~)CaOS>CHTy<In-1rM7vwu)&afJGqCRVzQqCV9p-C)
z@gwKIOC&x;Gt9HvLqO<Pj6qG<%_<BY6T&n?Mq_D%S^FhHkEuKx?v9PyXYsLd?cWIg
z12nVUH-sGc{+Q{@sfe<bQzG?t=LIGH_!q3o=yh{HaM;x5g!}&F5lM?yliJ#zbo9v7
zbTe(!Xy+n9h(q#NTvw0|lj23&?SLPaL1m&B+RB-DNMuPcBmAjAVNcJyfMCaP>p#Gw
z$}ykzjQ1JK<2n-k`@|pi0#3mEa*ydZMf?<DTa;R}K7^{`zw+Pz2jG~~$%R(aO!cqN
zpox)Bc3^wBd-i70_*M*~3nZ?q5H2d(wQ=J3r-{Qs#4|i@E+TQ#qZ55{ZVt;+oTj=D
zfUhVff6v7A<#0Jf0sgONB(9O&CgY;Q`kd^U_Z#fWBmA*o*BOd=LN8-Mqo{)6UdF*F
zgwNepX_r$Jvz2JLJ`P_j7%?R|1Nz=6;zX!*7GCmBx(>gTRhf?z_()X1dSN3)9DFRo
zdXx4iMr%yn&Y9gEU64}_ThDELldObbSJzx8#twg*(aUu)@MDQ~nk{|8;=O*?H+HOq
z<j=~e=#9&@?enhRXKE>1gQpBT3DiZHvV=(+hB2MRi0M)?Z7mc<259#n7ckTER;^3Q
z=fkego?<?i?Ai(`yS<vwv)-l?pthU`RaASvU-2iJam!z>p6s@;OiY)&PU{5dQcQq&
zhdXS-)e6l}rg}8)qLFhpHC6uaTY8w9RG<)kDCWu+D|{j7>k_9Hri&3laB%}VErkEU
z2{9h&3}O3vGwKvPmweq!8T>?(1zLK$e|dM}+@S9^f%kg^Ca|&a8LOT&X;+}rS9P+`
zoH`@ky?^w^;}<%N{R?f-lM6iunDk**87wXvii=Dc=u+DvPZhvaN90hHtgze$RQ;xH
z76Lj|jNz&C8(cQ--B48F<_N+7L)Dea2^XDt$2x)&f3e)vqzdSgQs!pPTiZ}u3ZoQ)
zSY6AMFb1=!?+ezEd@rc)DWMvG-GZ-O`?vSCNzBs&<F$&ujBg6R&bI~XfDj|D=5REl
za2moGUy-VDUPM)dt=<N3ATKd3uf8|S|K4(V=>2l8x?`kIY4#{GI{yv}%9{{uK1#oG
zdcuBR8RkAN)?zIih=urE7`cO+k=E*cF$(3vjdZo2SFTX=i8MKJGehmfSy!&@aPInc
z!fsI&{iVo=Xl~(MRAjQqZs{{vS!kj#<XU}=Lb6@gxKIKF7iL#Fe&gJ$;H8FD{&$Ye
z?-`=OsciqJ50pkuzg4R+X)K7hZu+xe0_ApYnVqiDNRbg=wabf~_zB7a+MYh6a3I(V
zYK_qzkl%)bc*|5WD50>e+_d%2d8yu^k{O?jiv(3KCyr2v^0l3na5Ah4#RX-|B6UsV
z@Sj4h#FonJ1K1*ndV7T22TNTf4{)zIE0dV7M0Xob=wcJ5nK9}^GkDu96=;Mi%-cJm
zZwCNb^lAFL!M}ea<6aZ(wq%%kGiMJF@X&aN3eY9irSj;z(rya-FJj%3_E)Jm5vGLO
zu!QJn9d((^D!6afx*s*jsdCc3LGkPl>ov;kVc-LZUxk8fS-@#W1=*V`TO~M1%w(|f
zVBv9A&676hTPn7?V}cPWKb|ZqeNutk{Gix6d?c_qf-9vWm&<cg7nD2WZ<E*|+R|Ba
zp?6Mf6Sg@uS)`q!cGiTvKI-5pqbvTqo2bGu3{=D#QqtR!q8FP=`b8OX^f%X~y`JEp
zkn+W+KG)4Netz~%G4Hv!w_fEYhv#TFQA$jiU4|7z;DZI`s3u#)EWZ{(q=?xM9f6Iv
zRf}@9b_PGYN8FvbH%*j2=1{QtT*2GrE7x<Fqds|`t=yFp2bvDK`X>v8dKi5IQN&i$
z^%XfE`tSD-pnPGA8Xiy8)rrlTWq5#L#=5xtj`LvA@+4t?TA+n<?xmZee}o>vTyrz)
z(@NmpIzbG#3~P$JIew+$PPf^IQQ$Gm&$)v#Z&~_dpHcdWlplxT;_|{)(jI?L3AI--
z;wbUQj094UE;=cf%ELGkJUW{GZQUq+P5CbJP>1~BXF4cA=}i>_v(`$_rn1YS^h?<%
z+K_10+*nsajN>q<q(|<}P@PXYG%E`4vN!^0KN>BxcQUjNk;;o_vde1y#Fq0BUYR2f
z=v16Y{CDZ}`FMpyaF-DO{A83;Un77b0Q<Y;-WPO%iOr$f&53b)FG5<6#9=jCQgyAx
z@7`mJ;sQQZiC0YxA|L((R9H_|mEkB%A3NFoIW_Vu?n|khMVj2_wCgCZszsZv68MS9
zAZyDQ{#lW}Lgft?v!S*p!tsb#H)+8{@q?Mcry5R?Nrxv(Bh91YLCpAl%8K<$w@H-J
zX3-(Sk=k+nMCZ!lh4%06p{$P9Nm5g_yR-bAsB4;+uv6ba2sBLj4A>TriG*D`qSH7*
z=3zoyP$LW4S91CK;9<=EF~8K3k4S=W55lpWm@vFlkG@u3h*z9;%Z4#!ah)%O*2DVE
zej|)+=6k|~u=zxr`ZjsUamS(DhQx@6e)%`v4>vljuHE%K6pctpM_TJ7(Ppwz)zhrQ
z{JiTi7V7<>(M1Gw`5k@>Hj6~>#Q2ho;O$;Pr1Yf1hgFum4A~Z3S3~^wJ)H_eBCjl8
zn-zh1<5)rYOL7jz5rh$)Ott%&9|fd%@u|K~o~mi;rhxr2bc3*$+{R*RukUJ8*In79
zNzwaMQprFQPQC84j;!dlm-~7XPD0^!=k(xt!04H7Jwr1D|2=Z!8MK{ogIkF0h`QLj
zo>_}?)n@)rT#427+NT6j+g6~;?zH^DXwJ<?_sUkatZYSs>tFORhCokZih{g#%1~Wi
zApWA^DSNF#i?m@L_@MJmkgnK&0Blp?0M0LOqy{=ELcTxWQ|Ixt+is;0zVv>%VE?n+
zH++9kA9TSS7xSrwJX?8Y%wf-(Sz{A>x{Q*#H)%&3*45>kp&8{G3i9o)H!)47q-$x~
z!rNcMml%*H4bR!*j4<U*oI7_llz`R8OuF_dkrBDNxGv+3jWzsv83@bp`tp}RqQZSN
z0@_|6e&oSAa5t^$=!Lb~L%gCDS1y}!)p=LBwyEIw;YHMC(kpiaa%k&T#D!|!DJ$vw
z>BhPVt?_4Hobz&~;??NP6jWrQ9p53;IN*9~JlW3z=Wg`?Lb&<?|C{f2qk!GonV0ic
zpj{=r@?3G;hf`~8+vJ@#6)Dm`H5+rp&SQ>@m}pDdoI7Zw0WObbK<Ksuoc6k0PXskg
zeAecbAI2XC{vs8w9?fAQk}axmaC~+$S8pE0w|+GZhfOA;9jSHPQg5(GZHArb9Y$No
zR8ABNW!DaM8o@hT*|@g_gP`s5LEU90iPcr$^urwL3Vsd-oO6W(r5Z)~b3Lw9jubvt
z^h!@`P@CuMJ6vjGA_dhYwaMT=>cXRB&&%-7sSSH9WEZ(xtOi($40-B3eCvY<Wvuss
zlk38WQ0YIG@>Kpe7MYZGt@pS*#&3B6`_K#s)2E}*%RV^`u~_O&N6`)AdT@k&4HX+=
zefHV}JxW~0$&o<8_r@mQ&1={%WtQ^yRpKLipie`rj<yj}u8Z1oaWx+}B41yd4hAcZ
z^5mHn$g&{0NL=57ZO$I5>Qd19)j|8mI2Yfc@#xz#Pd;4fT8)8ny<Un&@{l8Am<5bv
zx&TYI-PM#<Ey?rp+U>E`o1rFHc9|E0<M$_O*u6#YX1iEeQugzrI?sQAl^UBJ1pCvb
zt}sS`o+T|BaeGt3om?p1En?o<yDv#6LLB6D5+G99)aYnc*inZix@#JLv|CU4?ke0V
zH6%{ZUB4GF@gXj%@>u99MkSqAB6%LBN|a4m&rSXKt^1X&q${V}S;`$8^FdB69QQ=C
zKg{nJTIE@Sz9%nn^6OWv-+>UB+2wGO#tJTpVcK#2J_o=EF5&eFqJ^aV6@Qd4+76^f
z*HW6yr|10PW{w(_<2sIkY~OoWjap$+nphP2J%jD;L}`X)M&_;<L$u=6S5Qmw4+9S2
zO6ulTNXxTRG)?gR{qu_Uo*J<8t@WD0-)(FUgpWvVLUa~Yy%`ilh}63P?{hJxZ#*+2
zDK_o<)=GdZ?RvJ{*D*bn$<yJvIsn6u-)N$M9@d=d7umP5CEj+OvQ2V-=Gb64GkGn!
z$JSw|lrIuQ_fW+QG;JWNO8)ozLHrQ5RdnZfM3blv!AE`$)Dfb8{J4$+!?HD{XYYP@
z5CC&UH;aH-oj|c>^d+-l6yrZMw-esaX)@{bdU<e5yQ7Mfu7)G2IN~7cr?>qzN2U{j
zFPa0SHwh?)@T8*VVTY-%S*@U;6_FYzy!B?tYFs5VDC)3#KM|jE@!I&uEC-~FY$QMc
z>``k5;yhR#nV0zwAVC&T_pV|(KqU8RO>LBp*Pp12@*O#g&Ip=t{ZDy;#+do?+s3!K
z@=}63#+pX;CZ7ett2k`Z2<y0iKP4oYLGfV`jQqR^Qj~0G@>&e_#xngLUR(i)wm!R1
z>IL22{B<BL%Qa)CLs*&veG6`;-7)_Ic!(~eu0U;5AghM07QYcx%Oyqp4FF(PMyH{@
zPqd$=%}k!>r@ETE=l9rqCEOg(>yJLisA?pUYw}a@URUvaB=vr0bN}a=4;?eaIWGj#
zM2SKWpTDXu?MY*(J*B>|UJcxJ>5@<O-^J66+)u7)`(xQ2F^9Q@lg`!jUN67)aAA64
zrWp}`!|O=+a%}#$bmOm6Gj#C-MVL{x>=is73`UD_#Mx|OaqT`!Gs3h9Pf7`6gX1Uo
z@^42FBFVV`D3P8P=lhG1k}3>-j?!A?7rPMw15?N4{ilWP7mwiJ1fQ}h(8&h~ufqt=
zyH^&pWbgt!8+}Kqkkun|MwmbR{p^8s`1YcwXV(m>6iW5%E{JS^hkFeB6AIb^xZs;}
zVP)&#2V4C$A(YM{FZ~8W&L5GF5^RZZ)EpYhv|r0@_zT8V%P*bwYlWi`xkKi7t83Dq
zi-O%hJ=Vy#-469|3hwk_TIld(aoOnVQA8^^uSj`^n{b`uNItM3qI{KvN!*O2-ptwM
z(mv9ZEJynFK7AQV`M#v~5m}V>CXF!VlVBk)yiU^@A@B7QljS-Jf!*dYDn-j_vpJlP
zI@Z*cks<|&Yftg3_6zOS8dV`>&fw&a*Eadf=X?8;))h8prhlP$|BRZ@d#xdrs;WQv
z=Oc0marzfKev3OJWz#*^?l#-6G+-ql%XErk5y(mVOoq!y$NvXFIxNefSK({Teb}1$
zNtTaBFBalNjev;1CeE=V{k?R`DSS5E_?nt|Bs@wu5I~odu^NIcn~S6E{&St4(rEY(
zqhg(Fv6XOEhwqA@tGNh=*QMi|oKfdM&0I`Acrc%fi-)(6eEqhKbrVb?KyoJhQ=Z3G
zHw~(}M6a^o?Mh)bOzQm^%}^IW0fnf}h8_jj%l<gFzb61$As)SAWnSdubtDfE@=6MA
z>o2PzO0$d9zOa8nLfKek;`JYq%<yuc8Pa%LmRhz}j^XiB@rao=aJTZ`w6lHK3X!uS
z`ZYkZZ9hkdaxCIZnlQBg`xbvRoZBPqX{p;jfznm)k?38a_}^_Fr39<>5vdp{ZDk9!
z@9^lZ!~oo)3TaoF@;6{Yn%=^@<DHFPekYokh#D*}2$|=Hwd7s@+?P%3r&)&347zGN
zT6u+<Q+DoCsKVRQ^fMtD_dJq~kNo`$y}9f*_+_{}-~K$*cchei4l$(ZQU@@Km0Mk$
zI?Da1?Ug|aO@Eu8jA^qCaSbgpsyEH6Df77J$9maAPHyBsWmB-sbM#%PF6JNv$~%z$
z->Y^1U-d2mf=k$@iQ)m#;!)Xx-T`LPsS8*~Qo-+_4#S*O)p*(eE4$S*iOo4WR3amt
zDLMw-$|I6JBzY+e6T5JVg!u^dXDuIoKv5LcNf^f4Dt7`1j~swT8Jo1M0syd>N3{Hq
zAUq03@+^Q?mQjA-RyfunMAWAkG4sEYXE{?)2C$s63=;zS6!`OTVJHZpVmL`BLJ$YH
zi$`E3G1PhFXuG@#`<fNiKAM97EdQ&-VIktcwFFH>AJ0o^psWvo0u|LdOw9zxfOw=!
zlhJ`H5SC&qtry@{!vEq>;BvxI1qw0ZHH2}F1qt!1JdyXWK>WXlst>`^CkjUYzq;c7
z=bh`nR#sfo&MwJSK%wa|-Ox|k8X1u{<UByES9L@={d&<C+KqSMf=#`%cqCDk{1mrv
z3Sy>6o!`ZMKP>F;ish`JxjO7%q)-bIvcgnJ;yuX<%->5nUdq{}dan(4Ef?z0mVHlo
zboKGbs0gPqSj4RseTi#JEW>T1l}Cpr!>07gO1;#L)W37c*HXZgWvtho0sSc@_crf4
zf!PK~0cdCoJt*>Q>EJON-V1RROTtm?aUhTWC*><M9Q+@^eU`F5b;R1^m8n48;U2T_
zU^^^MZ)Lg2difGA)+TId9*&SczTb`RtvZEa_Z3z$u8BY;<wM&Ki0e46ItY0E2ZYgj
ziZIqs9&$&-<ztsqnU;iiG<JX&#&cX=xEAwcTdo__3TV|^>-66aws8X=`;2#1q6JL3
zH%>^Xb-=vP)Jyc+Mv_JExcbUeL5nS8Yxb>-&)ZBEf3xvdXpG`^22-o5j5?VJlZ|S{
z_JnaXno2pF@$sSm0SXj~lnu@QUJYXla?=P)gwz>h-AR2(T^-sBkXtMj*_4i9M(UFb
z!Q6#WuN%#|a$eFIN@{6KBnHPgi`T$y?exui`uB*gq_Bd0yc)}MiR-vibu~7}HVvH=
zm5984_yjSwEHXuDTWEQrH+X2C%p0pz8?SAdU^)fhEQpv6X!Hd!$4O#>^!2?=96NtE
zWyCxCtS61;-hRaQXE*sh_p@friZ@g#{Y!W0vZeI~=Rd+ffsaF(r$kKI(t@V)9*D7d
zz_-NTL;5|}Rws`gt(8R-MS|+mv|;VP#KQ^;i+%?_JX{Sl$Ja&X06Tu5>i|cv{Z@oD
z4f_{Nlv75^7_+w#Y;dT#_V1Wz+TYh-4o7}kL`!AlBXuSjJ;m!AxCn^F7Hig09DG3B
zy+6{tY9+++|K(8NkTVeLl)o7E_udM*7{DLAnHVl|wq_=qR!wDWAv>^p`H}fp8-oH#
zm0?h~&SZwjymE0n=3K0QbHMv>4$|(gtceS~MVbvvL2k{UQqTl3&~e<(DqAzL{RES`
zyKjBT@AxBv*g?DfkS<+QVyh&?jU~aRq+hd&st<sc5&3mdg{HeyV5|q68AZ#I0I>TO
zq3z?x?`t=br`A2u6qL`DtMBQTTY^$2^aIs%0u3XPg<R{qDObci$~V_l=gZaT><`@8
z>)*BIdzXMsl0B67Hzqsb)VCTykM|1PH2%0p211#9hBMba)|6iY$uD3H`+(w^U&?j0
z(w&-8V`O8y8Rug8<@7<Q&R9!njt6O9Py!EYo(KXWdGRL4-{`=VU!?n=Ax$4rS;2@7
zVG_dOIg)PMbyuNzBc$9-`RT*#R!v?L0WTT~Z5mL+8P19{i1Soq`tTt*A5uqkLlHYY
zG0uTBnhS9^3_+C>@CD+o3WZI2zquo;sz^vloH#`c2o^5dX`(uNXn#2|_RXofc>bK-
z_AsHWv%5T;^~>lwM~8O?qE5kX-@RqO`3w4+{|{&rs`>m-{rWX?M&@3Ct^ZVVj|TA!
z>nWZ66PD@o6xvn4^2I+p0<$GzQD4Kwk?IFh<;VBl8*IJ{nhMzsD9@LK8PXyzBHNKJ
z1K4vBxl8yYrq@0r(gLlPRnlFleo8zu%Tx#}<%KUgkW6+}M_I@ZvoK7cef0IlZLndW
z^4BnK{=_$PbdiP={<9Ca*~xW2BD>WfzO@0@vDA_I&WXChj10xeEa~o1<x3j$sQTVc
zT($<W-wLEKu`HQx75fHko6PCK*RRB97jg{1UV9IgPR;cVaOcrJ#E_DY$Ikiv;F4z}
zA&3x-u(_-^I;;5D$%&54=u+75o2{*xsGjZc54LqWuke6rN3$4vO&kSPU8YX0@287F
z3rX3Ryacv80n_T1Hmb#k742Z_*ln*ftw_r>BSVY>?ur=nloO?BW+$4#dVa1JH}xu*
ztcM2yH_qFzBh|Op(IZmi1(rUh>;BaXz*u*n|36wD4HqR+7fr;-A<2S4vGe2f(~^B6
zSoq{jTOqjIvWFanzL3hd@E+rF@onm|QjDb$agVAAnSR)E6?hx?WBwmnrPCN)La%DX
zKUBTAHyseH*ksy=swSkcWq^cIZCx!r*7*eD5w1vLLG_#{oAqwDV2*@TdBJ%*33#H{
zfkHh(MtTM`9EzMdPtzBq^d&^Xj_eFHZffi6f-wCD$OQdjdBr8l^G{U^UZChE%e%Vl
zM?BN%p2baJrVZTH8(ylyNyI}~UA5>7ITO1O1vw=z`Wv>HcjiWd?*6Y1WN+WFqWAHo
zpR>t}Txh5Yv;D+ki}A$SlroYXJA2YDFf>jE5hzuXFz{TGQB_k~I}jch?T?<R`B;S-
z`64^4&=<CGKgI45QL3K?9G2hGZ>aNVkuXSmfPq=rJSX{!!|B)?R>i3vh!rDYQ*l-9
z{@d42ZHz@Tok=`j6pHJa#r}q2Y_{|^2g%^(w0uG%miY^^gVo|SpZl!u*W!HVH0sci
z{seJM;H>dRkxXAVP7jkg7t>)2SL(Fh*EU?5VbJwBmab!rP#9&ZR?H6ezJpmUrZ5JS
zsM?aCtd*eTllP#zeAT9A#Lmt6kduYqrseZwTvEO0Wh{h`*1o0Va$gS~AfrhX?#+xQ
zDkZ~uA5e|9(?2Z|L!<0Ss|)^aSsg#T`o>Z8VU1f&iK~VmspR`Y-lVu&Qi{pBR(3f~
zJAY5&dP>KxbkQcWKzwOqQ_KdecVgPrJ*Hj9q68XH?x=M1ti$0Mc-WEP%&(|;22ou=
znpTXz(BWnl*A~tF^!2fd4RH`!Usy{{puYR}^Pf&cnsoFYp;ZAyR0~is&Hu0My&^i=
zK+XKKuJgWjR&;T7tDG@Cw(emE?WLLiR#X-k+HR}pLpH078JHeikF^_Z)JjJrZcT)V
z1@sb>Rya`9r@BQ{OztZ2XVqC_tv$akh)gRh5KeihqSH=eQwM40Yd>nfA*Ef2(5XsM
z{fX$J5OweC#v9jMaJ^Yhee(S1j#PUPHdY~%<fg2OlPX1c*1689dW`SSsDlDIb|zNg
zIgHCG=oVkWxAc6txq@z1&RVb+cPw*F;!2JjAc#8DVHKWw35~_w>KzicN~;ey?ABK(
z!}>)Ai^RG*X^*B|<F$3Z%|>m<-OeFDNr(!noKj8A+l07l!E?pCO=_1S@@oZo<{A=T
z#tESfJa?~kbRqH=@BQ(bFOjYJ_c-bXMb?4N8@yBT_rhgs?>*}{6aRc<EaiYbcGaJF
z|AAE!^e1JAW#NPw&G!-vc7NWIAcQQ>anLU*6eJ{v9tP?)XY8sF59v5^5ScB0)*zb(
zE?LXs<`oq+HAFwJj<P0NJdsdBe)PEsQu2dp-=VcEDu}p+WIZVX3jdx?zcx?X9Kg!b
z!6TsbhuBmeb-uOib3JtY-ySP-bDiYexx!1Ur7hM?*28+4N>nZ922frN0g(1B)ob^u
z$8wzzL+)jqHC}Rvn)qD_U~{~}*`<z@eUGNX+l;c+u=3VMMD+_=h}eoSH!R<-LdirB
zxQTJcwmNL9B|b4ILHF+?@Aw?Ddtm{4>_P?pRu8YeQ*vl~W2HYV(#bx6ST_q<dQ;8H
zWQ=y1(fdDu-Z`nBj@8~}Gha7cxek5wyFk&d%`Nl$kCU`}^b7EYRZ%4en`r4jX6-rE
zMLY%s8X~Y9CU2p%5pD#~l3n!qzRX#Uph+T8@sZON)_F*sk^Tt1$y{#>ae#CKKf8(e
zj&B!krNamQSWl~n1I5Kwkn-BKkDYW3>Z8;};kYB^=$_kPRYXa`LcBvBsS=7y#Nkdx
zinZ-mhkw#we3jT1W5w^TPbyM-^8s6*A<@!GG`Hc2ABmg`G@FtAk{d;MB-zfc)E;UE
z`Yf+cM1kSqdzJ>gV#>xq+AV<aMNNN5lc>f!_fqsoQ{@P89O%>p;9!4rGg1bwzyK^J
z5o#Wg45h=owRkYjyK~3mNXpz~90brqdE2O?fateBTK!g(lXU`KKz%bfNx8u0*9|fA
zbq#W{#LHr=LMVdrYaGVuS295kc6Yo)-H*#b;d)!Cgh@MY0(A3CNo?$;9_rKJduR1T
z8NvrIG0*MS8KvAU<4!nAScrEXW9A3n&UqN6iwcKJA?o4vbY1<ozMbER@(#Cy`$8Pg
z#F)33mrH{;-~9Y}((y=)f}ielCr}Z@udnIi?=NoE<juNYkbX&l9(dxK%d%s_n|5K+
zpiz@DzA4>t!yTt&@_g86_$!HJRI~}D1gK{uC8*lNC7F>^D;$Zc!zK~MaH+*=q8x1p
z-E8XZ;#75D&^_p+0e-f{MGYhOG(NQOM3g~WR$*{iwt!yqH{|opi_BkCM_JkbE}zIO
z&=%StnRLGVghl`U`VN#t#xoTb&s3@|hBGwN?a4j;hQYc)q>iUt2wW8l{;-{}!pB;;
zrcK$s_Z_C;7&^~$j_oy3@PJ}<r23*|IsX~L^VO$bu)Vh}xh5`+#wW%@zw&E$C~$la
z691wLM&1j;iL{Glm0LvsaBI&$UQsM$!1&uT*HCyBm8eVWjmMEX^gc}}?)%lB)xBif
zU_htJAIXM&96C{OUVz_)L`c-XKA@0R{XDhJvmMyK1NC|!n{hp&QhZw*`PK~OyAhd1
zcdY)(7F2DUcaBV@uCQF3FwJ(z*Y&ZuYMrJ{dY<=naznR|Q&$Q48U64W#1Bot3hT&B
zqy4hmXspBuCo=0gmT;0+G1&9eT0^BS0c9-hFRL;@-t7J9(Ss-(F?`@!c4Ajm&*mKQ
zvuj1etqcK8<qr4#TL^MK_ez}Dz-Y-7)k&rM+oCAzbqfG}qv~(81w9hn4IVYZd;@*+
zFsgC5F&2H<t(|MAdWTpk`NR--rg@X@Nvyrf<qMOA8b2!)_vW_9^PkNM*Sf%6l~}vC
zDJ7JzJ2kBXeoUWUV-*;3XUSFSa~zXe8tFPJ8?e@?8F_=D*0|8Y?hsksMfz{J<SsJ5
zni`VS7Z&m}<xlc;0;9tzb0p!HNK)*mL?#^sJVj>zhqbc`YU_=|bZ{v}S||?1o#GC~
zU4sW{OK=Y^r9}#q6!)gM69^t03M~-aoj@sC+zS+FH~+obncbP4o!N^o7nvlJ%$zwV
z=X-ze^O&`)_!1971_$)O^f#$y=N_t-TW99wEpC=p+k-~4^PENFg&#KqAzEq@pcfjI
ztitqLau;I?j6f-NbVp1`Zd=Ve+7x#5(wjYy{>QV}r1CP?TX)V^UF|c+OL@k^*{Adc
z_f?F2F1ZDpYfXr1;O{4u8QDzfEg(`v*|!-R%lyX8hu0`7EiCA($NkP0tJW;&g!9B=
zaivwO6obg^pLcMw`Lu*@D9x;TnIsuGrke^+g)w%^mJ}V*(cp4t54_p<#$eCg1jL@X
z=e;z&^+TaVUlhCmN4%f6{=-qd7L8)X-Ox&{YqnK`+KwRM@0z$K>h1_->O^toQ0%rN
zb=;W?Twl$x$;c41(+W71UCiQ|L9YEhU6V)F;Z$aPL%8n{JlQI|$TA0V|9o~wiHDH-
zv=sO&#*MSAMboIzu*V;sWw}iJCamAgVD+Vn*@sBYTkQHB7ib@OFpKxnh0HT?+;y+@
zGc&Vk$G1iPCouo<EdOnuc<j|)*M-bYT2Dz%bK2|5>aBqE0rXDejLy7jlzXVg-9|~M
zTQ<Owl;PSKHeO0kJWv9EW1J^?Vp$vJ{o#|}?H`=^9GpHJnUe{xe*jZ$2i0h;6foBf
zrLU=e##J(ONTPVhvo#&gygnh$E1F5t!b8ur1DC6l3s3$TcQt0Es;>KxoBO^S!xR}1
zUM#YASsieQTV$#Z<F!#SijgALA@PxtA|VJVWUp73s9@WRfL8ka`eg-iJb<RhC|=Nh
z;g?8T^eg*lCI6Bxc88#l>B?0$Euzc!kWcSJ-?`=;D)DOmCeXOKnTI6q`s>F(3p@e?
z$K)PIx-I#GS)o<U^hgs;S%m8V-{)sR-um7Fu#qgymktv-Dyd<W{Nk!GkwFDB=^ccg
zKRv4DrW*;wNrLgvHtTR6L;7{x%1csz4kvkmCMAZ)mA5>%*8SiM&t@$37$y=5wiqxe
zI9T$??~9Z`=iCKQvGWbQ>$q4h8tgMpjS=o<F8^wcePfR%I6ZX}`Mu+ieaw%w*W3W<
z-c((nZVoie_B0;$7PjO%{HWZY$q0WfQ2GyGYmv7o&s#Pt$`}zoj*qFx4Obh5teqTw
z^~MfapPhEQChjaE!=Tjp8<H2zq^XGP#wNsz%&8Kt&M5v$T{D0a@l+U>ZS>ALiMAs4
zERAYMCH=<yB>u#?z2X&91^7Q&jwKgdQQL{CZ)2>gIqh!tSgJn31b-1J{lUL-zhkp|
zD~+3MG{NrPx{h`v5u}Z~Ne%V>Vp{+n;bg{r4~4dQ4p>S`(w^9Y%YwQx4R~L(830A|
z=Q{)>``dNTQ8aDDW8aSD=nl(`#Mnv)7B))0C>X&ft^0j5<Dx2$d4nM{Navn1b58j9
zw!zm@X9)t=k=clI+8C3>pz1Op@7mYnlvCeSBwpv2WHb4iD*m$(*Y$dp-s`IQb4ugR
z*NNHH(x3Q8%W<fTj>&VsG$yvf|746-x$llHS1avV%Y~q4Y&*g>zqZNq@#yO1{sW{R
z7970<#l_4&1i>Zf;{1s+S=v($%(b}kd|bF7{qZOS0gg0&7JG|4Pl5mLX}M4T5O%t;
z0cZMF6h;<<lgg|5Gg_2sc1zYW)Yp`;Z)`C*Aq@UHEI|otRA&a38*){%Wsh=Vqm07%
zZ<6M7@TL2OsB@<O0dj!;_b$D%bO5EB85BkV;9Nu-Or>~?qOv&1B$VJ^13QI7LCGU&
z<jjmN#%U)e)P~d|KLw7d-gh4~ncm#8hVwH;iL01&=*UVsdY8m+N>z=n^F4cxHSRY4
z_7z<0T6xvV+c+%>IFRUbzIl}8qkF%Fp{P<B<?!x)E!EZ+H7OI3z6~)+x11?os#M}$
zZF?03yAFHyMlhGgHV7S7)wBNaWAq(RdYo@rjw2}5d4Fs7(PX^Y)Z%~@42GP@B1rFe
z=e|XuKjVSdMBMK)W~jluBKUTIy~Ifz-XD2>4{M5Rorg>prDZRM`T}`(Vea7`3QgHl
zS#~Re%LuK%8IV*1M)@kC!I7{g5~oT;E8F=dL8U7z$y-;zX1oz^YP=2}ic9QlhAItV
zoBYX*I5TAhw_;B(jz$Lg(BJnD0B$sdE3I+{Q<=?Z$4rVInPtR|?xtBu{H6f)|6TFv
zyBJgBwQJjQhN?*j0xE`jcgnn_51`Rq2ly7BX^(&b2S%6MA92>|PwutexSX@cSibLI
z77Jem%Dk6B1XfvC@JLDuSN`4cam!4-vz}Y({Ca6YG_cyaQQCA`?fKV#L~H{6lJ>d)
zTyyUP5v932pynzFq^aI*S@5_1G}OFXu!s6-V<KY$sW_kHW^A8BB2A^4gZ^9>IB~iC
zlp=Uio~?DP=V|3a{;hyrySNnvnz#6UMR^)^UbMl7DB7h#xd&9H;@Jutd!SfzsOOUh
z2z#v8X9oik@$m!|nqn`;0GvFFTZYu~qS^uQ$i5fz;aFNIh>0NbNMeRnr{XVkNjxfe
z^MK~n2vUXbPg=h)qciRJ`wVUrBf;!O=i2T7sC4O(7gPU9IOKM2j95?q{I;ayCC?@;
zyJJ)2tnMXV@1DNYxR6VVJ!{&0?vF&if*4MEB==qC^d`Gw<bOmSmtN_D@W%uxP@<Fh
za5{AjBi-ybTKl}FltW+Va!%!43K@`>e{H6m2pEOuE3Nf*$x<}`%snX8`wxvUztWC`
zG&xoFTYMB~T3WfDymkNHfibkjRo-eJ_~NiIqA=*u=lL&ISWD(Me>`$mvz3;r42>VK
zO3%A3QC0*e6YX7=?@Mu`TDlx96IvF1L`XI25LTmNjD(wA7VSB<#m_t~TQ`vg#cB;_
zL0s`^#<u;0VWTpq1_;p1v0by#z1xxTte0_lwjI?UQY7jo(Z!U|kPt0@W)s<{<<{XT
z4BfiddNdei?*Pq{xGD;)Ge&P&<%P~@^;Us(ySBnGCytXseLB+>QsozS18u?f?nYuW
zd(de*@c|+i*53mz-_^OIyo-M|&C=M=GP?AvZy*!n!(XE%!lI@9TA%KqchB}f9Cn)g
z{sfI0Z=x9ok9l)fZ($m5;)RE}y0qSJ_h~;LkePSGQL(ERwXT<555to@dJ+Qt)J0Pw
zVxXX`a8~x2CaD{JHv{RXDZt}L-BgmzL&-4Zqg)Q|10_r&NElNp(w3dxhz~WyT22OT
zB)PukplotFFTl<S7K==WsP)`oIDnPh|HTH}V#eOSilqN9@+!=0u?R5*swu_Czqkj2
z%MI0?u>i&RnNWZ((68Js-jF35BL_3&BZ>zaSH2|1d&4d7q6aX>lDR6z&Z0DADKVPC
z=)r^)iL`mR#Rz4L)EFzn^P_3@bdIzz-{;=>S8zW~KY-Fm1Cy4NG8oNc@*zWRN(?`d
zyIAa<A0VKZVM+~vGoKEGT$b)(oMf`V>yrNG)CC7>oG!jl><vG$?t%EtwfGA~YhyJI
zN<d&KXIeq2+@#P>Vr2Xz4*;SA<q=ivFM?_V{5d$JE);u=G>{nnE+*I+kSgs5;LsK?
zN6i{K(=-{WVZO%y=j8<BA$pV=gdM>YwwXk=H&nK2*{O6)euz~E$-CNWe;JJ=dt%eR
zSBHn891G-n6KvXWCF)Ys^-pA?j}JxDY+i+TdXzn6h^@>)hktrgwDbJ~M8A0#yqE?<
z-uQ3IGc;u)ytq9p8m{iotbcc5s7NTbwf$$fg<I(kJ+*}|uDIQ++1o_am21?kqHJ}l
z@2xVO9g$WR00+KSiJ!2Ar7EJvvGrz)B!ZL`v07PDvga7S)rsZK3tFt~-AR*?cWM0>
z1!PCoraX7cg!QDQfzB%hZJBZb#(HjFUvfl=w(y6!#z<_1ziX|M@a}8~n@Rj!ji!0#
z_aLj+Hi!6O3RQ7MfrH;toV-%pQ@}Yz=B5VI>2<<Ka%VWt-^-lNAv3u?F@*2y6DYk>
zba}@zT{6v*{zI_>PMPVA@74@8tD9oJfBu*D$!(Ns<Ky`ERW$ciLw^N=+?1y_&1XEo
zEgi`WytzeP%aU4P(s)`6Z?(4%XAZ1%2ifSM{LY%K2#|Qe(sn1=xALaWwz`g(<9SDD
zkpA}TVE8%nKoJ3dahnuv^$QOz`GfDwbVsF)78nNC6O&tz#Vzy4icYUH9i`bzOa3E)
z<vp~w#cQ6cS{`KGXT)`eZf)UC!?A#wbT8Krb~AYCw_TleFM5OZ2T1Aiz<?)vbnqW$
zL<n`<-{&_v7L7LZGq<B9apY9zD?jEtJ*~`ygFo%fS02+ITKI|GE-w<*da8{6RB;Dq
z{20P6M7HM*9|<0n3G3z(?i8gz5p6F(`vM76Fi~9|do<HekNaO;_|r-?VL#88GEQl{
z)m=s)>^6Th6ml!9tVXBSTu!Y~Ja^*(8TYO|6(q^p4Fi-7=Y=t9ue#<ox(G+gRJ^3_
z&WpoNzO`_jJ}V7&zh1VUFI&7HBFu;296+}mpgO@Io|%yheOj%e1?*{S?C*RxbJ45M
z2ldHl#~fm)M0BTWs1mp+pYdDs72ZY*AQsXWgHmSDzNR2E_h&m_c9P0N%qW&!E<ifW
z<R4dR$na|`+4ihWn@jm|u?uHf<=^92HUG)a?nucF7;t+AV}acsy7EZVyK>hot?U>Q
zofx6_y;mT}_^2E()ST**Fb_t)^BXON4u((Zg>n?3C*DAC^#;@4EF~d?Y*bMSb}g+T
z{Lg4BhS|c)>A%EpmiopAiqg$}#qcaBUx#c|hC$V&?FfHY0yPWgr`{+@@06rK<})SE
z_pG<<fjKja#P?}Kn`@QUfYgSFtEvX=k0QHNpXCO$w1)ak<+YWgCiIa$%gWUTuRv9v
ztXaJ4k+M<d;E1PqzE|)s*h93mm@HE7Il3#4@Nwd2`Ko90ZW?bMqcJ<IqqYU}N7WwX
zEO+t)zchb>+U!?*ACtMa=r9g9S#Ku#g6du9{D#_j*yHQ&_Ji)LV6&bd5_NpOw;q|Y
z%$2vGD}A3E-*YxaP14Tl6|O3GAdaVBS>Ko6&I!FhunU^3`xC%+nSrfZotJrLuLIrD
zkXy5ino9Z0cdpV2v-dsmj!m;^n)}-3+$8Qn&tb#4nHxrISSdQb+!=oZaPvyTTr#J4
zV;0wItwT%<UMq!y<$gz6IpEeBnI1J=s*=6uR+On#F=x6PiYPMcWus-RVs$CC)2a7D
z=qb2aOfC=PfK6LEV`<mDXyMdZ*sI+@`d>kCGLEMDBVjyuZ#5%3xHlZnJq52AjxBUX
z9-8dKd(@O-&EQG((Gk-|xhduDNlZuM`{g^CnmueJN^wEM+iMQ%Q1gwYUuAuVxaKRX
zM&v&Kh}cu6s9qqiksJoV8?6Kmyr72WR~5Nb>LR?{Xcf*Yc8Wc<+?sHmPqc`b&5MB$
ziU(JUR4J;ubE2PE`acshU}v|w>cXnLk|oe5V(gdY$r}1R&w|<Hp59J3#&FGE!O_ZK
zHYrq>aQB;oe2|%UC*5mV7-s7xSivKT%E6ek@%OC{{wk`Xit`U8+X<cClPLtl0KZe|
zD@lrA`XQRDF<%WMr=OZD$4DHsG+rQMcjTw1VD*0hBTHsGfcaO1k!2dAu%YMUBLgTa
z3bF;P*Lp_nVqH1LBGu2r5_IUYRW{Kn<5!kU-Vk*&`H?z*SC8}&1lWRx*Y%bx<Etx`
zWvDazg}IQ87K_bocH;rKGMdi%<+!b%uBE*r70sEeu)%e(AVVR9SWV4r72y}EPg4mv
zYwC?wpyl3Ett&ZoCs4qLXE@uOFf1|8o=UK6cT=?pCn$6IrHIl!+y+V@?l{aa)cS&{
zwN%m`KQ(?yB#-RCVyf*^lKw5CO?^=lhqI2I!{Q7&0Bg0FLgsXD5a9*)?ipFTiqyTP
zdS|?6di2+0ae^rWsPTpmCl3k#c<9y}V0D7c!{OwfEOk{qc*6dPncF=;JU~EwX_7yp
z*sDxUwV2giwdK6;FhAG;Y&f`oY-8>$->Bt7sj2JL6>3-bgzBXb;t3tcgzeX8q3L6w
zR0%F!VVt@UPY;Q)6>)bu;2Tb0*%3|`i)YY@KCkBZOJ0C5?EUGV832kkk2K`63`Zib
z2~Mamdv2B%H62bmJKaMEVK5dR#LRt2GZ+U?X#3-xO^4HAD%|f(zO;?=1Ol1>>zMzT
zVypN5B^TVZyxRuajg(#TaCl?JCU%|(fmk)j;ncJjcNbdAuBOHN-KF9?fY(7b)-~Ay
zd|hv(5EyDY^k#K9-qai|CGS#%Yn><0li0)H*)Od>V}2;^SWlAR<l+0&U(2jQ4UeEg
zx_lSP;Sjv0xk15}^KtgHdlsE1Bx0Z_JBfV;Q&wbv*f8a<hq)O?b0ip1wa3Uo_YS-1
zKvra;#u+*P0D%E`dVRqK{^JBM_1%CYnlR%X^h)aoKjyVs?NE=GdY?ux`*+}*ZyOD3
zS{zx@9^H|pgVyuXZl<ZBO_AT2c{#jtzkWm3oQN|@E4E}rF#e9ZKhP>MO#$n5G>(Dt
z#GQW+M`6w_>2_<yzvFkw;{5Tyxjr*A@C-@mckL%lO%7`qCa{jL(~|s~!MAAHsVc_I
z!<gV}4uUk~kI$^B@nP~@ioJr{W0xO6-{$f9ylLt0%DL4XUw#zucO*xzd=&lG`gZP!
zhu-irU8u#HenR@zU;nPaA{PUX1|2C6bUaQY!(2tLKy=~YV+pHZD%fkbm;O<(<4!7{
z=6ZMcj9t#+nI?K?1c|X$#^K1~JMpU0#l@BX?i0U^zds)IcK&4FsJ`=HyCuWZ%jhO*
z*eKZsp=%i#=gq5xcQxf%#ty$*`sJEY^YtAK;TolF+kh*qO+xy?%u>MqVK#K}ABMeB
zB&ZTu`&1((-*xZm(?@X*rT~&~e<kRS*KSaOeY8lQU7?!ocXj)^4t?eJlnE|qqD8#5
zFmnX_+fnZb&qQHaaPJD2+=BKewW1!`kP5L6TTYa#_fAMISi-kmaTQ8n<rYMfK<pQ5
zaH&Z`;L9#fmi`u@qr}SwHqC+~kFKD~W3hv(0DOBKh07U|50K|Z4>Lx7xXbG051-li
z<npWn2GrcFZLHAur^B?GS2b_)8J>vhM_*)I?U_tggIe2^`wgAYrs~ft4-AAoJT)l2
zzy5`jPhna6$%UBk%O_a6P%^g}J?*%09Z<;$s5HIy4iY0o>C(MoPrS6YukRk1aP4fV
zFN$P%nwX)8%D}LS&re+>jKmsfty^3jC7HDW{gN~XYJE~_iIV=6&*Vs$T-(G>gf_ca
za8ou@W~K{IjEP94OFT-p;*GK56+sTtv2sAXG2zGZu4=zzV9!Jhw3EHF`Lx%C8)431
z7>#j?;%yQLU#Ew1edwy<yS*`KD6sBn9a^LbZA7vofmJt@r-5{q$ey6i^<q8TSE}?J
zA5{;;4=3gE9_|zBWmJ<4WPscl(~4+^yfknHKPT80XF8lLNeice1<?G(434<4Z{*cG
z1P}e0`*>)-$j%ZF7F=G0ok<q*=nrv=_~%#czNWvaFh7V;J-EEl)1&yR;v$l_kA-2g
zQod5evbGRC;>9%eq#@52Hm|cST9J-t`$OD(W-9_r2wqxDmN7j@;9TDJNfXIijd4qK
zX?tonn??BimYQpJPP%|vDC7Cl6Ch}D#Pfq*tkP5?>~nF1#bL62fOwW9A5K;tkH?o?
zWr7-)PonDYZ25{?TP#`Gp5K|vL!Op&D4$sk1oCd**{IFU7WtikzFVafV{PKziTes4
zD{A&A>}0o~Mp<r3=6*AdM;>#ZfY%VnSUK33#i=HaINj<o&Jzr(ro}-%r)S`9TK9?#
z`UGn#(;)rq&z#kSfJG|~RZ;Uz7A=2XQC!oYO~knL1edrhmSE1|JlDI;h~5g?Tb8df
z?ZhiR1ZzD<mP@P2Zqj;#L{y2grlEtteTGOJQW;=y1kLVwC3#6yd>Aj)`f)g_rBlL~
zf>TI;b?vH_(6ZzS0Xxoo{gv!{K_ebBseJ;Blxj|?zhgjMcB9?3#`!{(wj9E)38%AZ
zyJB=@t++u;a&?){{tbN_%_svyl-p>s^6+lv>(2?<9`y-~LA9j0E1()u@GMYJe3jRl
zj4#M><HvDl?>nTvBQ$_skURuu4H+x`?VHQUZ!NjSrH?PaFSlFCgPs?R27o6Qq={+9
zEfQNdKJ%kIC*K``xur*pEDqi`xxXmEOghAi;IGRt%*_<C;;<W!Q@3f6s(G6&oLi!a
z0B9MH{s0;L&NNx|8fIJ^dghM5;!SoNI${W8ZkCJf7fI>)AcSxEP2{}c)X<J{@EU+?
zZ_M4=McHfZyTa%N)Gv@aIU{L2Q8SiaUy17VYqX7luV*EM#6D+RdmXmz<-tKhReavd
z6~EK<2>7)zk%2J1^*Fdj#q``ueXgA%W1sR}dWzrNIQZ}w@hzUr*qA7wZZj{(v=#9@
zI?+DW%TCz*HHN#?)1t;y;H$U)ipB05b?j5kDR{&MpJ|thnbn=K2fHVmQH%8YyzZFT
zQF>0!Z+Sdc(8q3<nlB2_rdkKP^e4h6&!3$%vkK<`G+Yy&sWbb3#pCQ?|70NXo<Fn%
z=lNjUPCdrHENF5>PyH}U$%8i2orsYgT;+%%YI)zPafw*0J?V38u?4^OlQU&LqMu4y
z+dM7ndKfL)zTQMS0bzN+%p{KGR6?4&)!?``t-A={CrZIPUO_N*PaP+iueH9_Zop1E
zf>_fjE+gg9d!(iQyKgeAmg80`Y!dV4Y9}b|?m7#rn%{S-wJUYZ8CGYw4a*eUeG<Z`
zk>y4YuRbVSt6{?8%&t$8h@yTi<M*G21M*}bL_ni*5^Gt&rF2yh(S6S;o)^N=4HP|<
zG#I4p)LN9)^}IgQpFYb@Hz`SXu9Zs!JO)!r45u4Q(AvD6{pqbPvtUI5ci)9%mwLVG
zcJ>YUHPsPMx`|L?+(LXX%0xJ{EIE$<c$@gJZ$%MZKX1@AcrZrNA3?Gz?_w{_uLCeJ
z(lg~>)x%~8kC!+n^-URb>#wGaIy`x1lGK&+E+aeTXZ^%<s{O6HNg8k?Z=Jp2IQfrL
z1dP>zpJ?yI5MYX;0d+7|X|DrHLeiiCnpN@4-99PUs3jM(VN-&T^*eJNhq4uTMv`kA
zBe1Ze$r%S*={{us?ee0A96X{U%?!Innz@u?^aa@otx$CcG*Ob{;}OVqQ0<eG(8xL1
z%bWMMZ+gA^2V}W{xPfsbZ6D9lI)l_eoV0+h8we^$;rMZ^XZK_Oh2Nq;2IWEA4gfC9
z_e&3G<-+Cp)LGtQ4rLU_JiJ6TYiVia`V9AWY$sw+V8AUem9Q}BB-6`!mSTh*_s|EU
z2%)0`9~-$J>-zec-DaDuPp7(3wKWo>JuwQ{VO<9w%kLS-nuCZjGPAt3r$l}!)Zqme
zP!AW#hmB>;cN;MSBFNNJcQ9&(>fKo~T2zDnF*=X8J$^G}{kK#(K5H{^d_a{<Nbof)
zndAt+HyH?AW`&a!GTk_HlpH+4^J11X5-~)G3@kEmAP*bxm)FKz*|d;QNdxU)EVG9t
zF{&b(C8QB?RO9*;Gu=yAy4$`BRG(B-8$en<N^yZ?2HMk;BYO+nf&y<Bv+p-wPB#>0
zS~;2}3{us4AxayGtjU%3@m+rwd_DvTjG8|iv_m?ZdntFg9*(opXa5Xy8}l1;{0A^p
z{GBDz08Z$FA6IRB>7al5Xtc~u2tMo!+w&KAqF>?G?l}F`J;BCD2yKRs+~lKS6;gk@
zFc7qd0a1zfHFgYfjZQP<%yr;K9|NV|9R!T|$ef2zit5czx&kLeqR~rtb6?-rt{gEt
zfZ6j_`FvIsXY^{WT9P1F3=5)Fd)~c}HX^0L*RD=}rlVuVuQE4g`&!M8EHVqX(&*#7
zjE!wqhIX8sxiJT9V*}WCXIQ%^F_bv7>8Xqkt>6*c#^RuXY^)L}b74UwM~`%78g4b=
z&{UqS$&{;S1=Z|3+Gft0oYEJF9{HY<rY$WGkNWZMf?na3r|a?{0_AR&SzlzIy*nQ%
zV@L{t5{=<u?PL(5C7F1dwrSqvm}>Y~Hj>n%2t{Q6`pwT(8*WYj!vL%IaGFDbUHa_^
zOBAhm2wzaKH9sWckguM$q1d%F_K$qd#nZ`*<(DAS*4Z*<fgDI^XWIks@2TZHO04M$
zV%8r<X$lU@{rR`MOfM0SO7Z^zUIqKUctG|bNVeW5;NXT_C{k`tyH7@XOeIw%{1~r6
zkr>s?sWD|U@`V1TJex2WNM<GKAzOq@=Q08IZjA-iX@kWIBUP<vmqj&;5<4mp2~nFT
zM~A_+yqRFxEZ?>-Z3k9se6wrkzZCHU^4xMbA_j5JDrqUFadEF-X2=@Eqn{0+O|?GB
z#ZDvrg0k6m>v2P;X)Py9s=L$!HagxvMvpu$F^t)|xCt?rewMcY%Is6_ZIe2(IZi8n
zfLUnW?aSCTN2E{9@140Lt-~eX4wQ0*;xRxWOg8NyFipzSF%WIiGN6Z%CsC?0`@!|u
zKLBf)iaN<Z0LP!qzgM2>KZ`L)RHnjq+17k!!4p`sz_`c7%6z&~suovzbiK*zrXQkc
zsqbkS;(U_%g8gjHjJ%V$f--aUtkJ_fN0!E0!t(9DpleGUscJptV?Irg))!|+43R{|
z#PqF0i#Gx2`>gmus2qyyWM}uo);n>kvDLLIK7Qvn;R;g6yl#3TYYPRyrGv!3$SD3H
zXK|Z1U&CIcJ$jG1>6vMoL{u+XsK#sf&eBZ*oaz*iyl2{*gg;f8c>(l!c)FCNt(bWp
zq+GyGGU*>6^R~9k@6yMMWaHsa8JIynSG#3AC7TR$d<Z9l`iXphnwP7_Y1-e#u+{^|
zG$nB&rKnIgH#>L%I<hY8Z|)r%%jf(b^qL2{P4vcn|LVzNt&P2RbM2_%N)*T7H0mu{
z@<gW*k8oE-D}UkhWg3v$SXYF0G>l92N^c+q-ikWW;|phjf4m&d4X^UuOwix6;TIrz
zouAP@Z~tk7(LllP0#9C1R(ZjJH0ue88aWfvl}{)(n%DsJ8bThVuVq31StnwDYaY=O
zUA?ia>%8U1=mvkbFWlt!yZob)+=~N6nz}tL!sQfhqbUv7>4s+VZsjAU42-h`sY7>h
zVop%W-&8zle3p+8fA?!l&UdYyko1FL*ab}Y^5o_}8k)+9-X0WUoTTk#G{8;%;h1^8
z@p!%M-J3Q@%MIb6_}k0Bk+A#9A+c$SLEDl8DN%CE*7DJ%7BjXod{++#>^5ns14H2#
z&a#(-R0Y&xW~SqtO?BUWe;{pUJq@j-E-33ap*yL+H5E1@Q0(y+max3KZCr<RY36T8
zfycxzMr`Xo0t{BI--CW}-Xe^p*=sR43wF)psS%RKa19Kj5X}>+YHKiJ!qt}jv3hr#
zfZ;+nbBD%Z8Jl`SQL$eoxJw7?d@~6FL{7fWi4D#TemsFt-72o4OBgR3KXxgQHhe18
z1DC0~^_HcG?v-YMRRvvVo{D!x!U3^6TsKwe9hv_CES?<Ri<nD`U;~eFO2MCM4lST2
z&J04?U+OG3KCFtb{IRBD^+RPjOUZJDJS*Ro*mt;sK5IM~&^5x=c|~WLfW>*AG{i1W
z9A_(?mjAtWnIh%d{e=N+Yq`(oNnhH~v7V|1<9^temDVcqMfLSeu0=z9Z`vcMFh~zf
zE=^ki8qiQu#t|*$bTdCZOZqv1lv1M;R0W@xEKa2j9cfeM&6Sx_O94WO6SBA>{!Bp@
zi<{F`cMI;}8>o&0^CN`myMR|;ZjC8YGmYzh234Btw5K&h9Kg`LI;2v+DXmvIU|1KT
zEe<sOhVeX2x6heHE4ii%g>vR9Ib5t$g~*ijesN=eO(qC2!k)d^q$$}`9K6pc9yS;*
zIXY1~>IaC9;MDz@q{PA;MF%jOwj;%)4op0h8u?#?<$qhcQ_0Q%+A#r6NIy$~N<~>@
zn9D55|4ftqOO*aEOIRyPM-3nmZ?u-^O#Z<L3X-1C#^n&8j0wk?kDt=?)lF$F2Rey?
z#Q=fDT{OjFgpWCWFqNHmJRc3Eic-TNijR^&JfcTBFnpRZ#>celQ;I}TYoqBzZY%<j
ztS{!HIc0p6{s1p2F_9R}22}P;4M4j~=>+30!BP(@iZ>KOAt~(=X92AR7wSC01%N3H
zTOMvKXB;S2QSxNhnTFWsF+qsp_lV`p)F>E0=D+Ak*o7N~6aaA0;-~wS6xc=d3t-}?
zA22-3quT%HrK$K@iT1xN?X31A26r7$x~rD5%eX3&j|hI4P3u$mO>mtR$+xEm){Zit
zSz9wPV}Dy3t76Nx!TeYuMYejq;-#NIRkS8YCCRoR5<>{-EboA6YWA9W&PB+5mU|a=
z0KD|zmmwZZ2h2$}_ff8{ybOA99jjimkDz%||J{Tn_kF338^5=%++s`R2^!e?NhFT#
zuJ+a}CWWv4<%#y7eCW(PUuZ>C@r$4OG2%!&-#j$2nQowD!5mF_mJpDDmeEaSUzFaF
z+OBOiJY-HIqs7UEQtXf#ul2H;VL60!w|?)(Q?XV*1A+KB2xSoAgTbaP7@@w#o~g6o
zt(*AD(Hmls=YpFk;(DCT2|HtL`Jg9yTA?or3Jum#<Sva2j$t8}Z`-Nqjw1{wYxv;5
zcYaw@cJVzVp+c*C>R90BAHX8p|4)uzmA6$%^Bt#dl94e_>oHqOovvCVAVZ$_Cn4z!
z@%>scbgs27)}WP|;%q5-R+4l0<W2LAZ}d3|Xh2oM%PC9q)v+P*e3dKd*%)hecmOb1
zd@krqPaa9q_lZhNn_&JZX)Q_YFusP<q;R^mVN0Y<gM1Hj$AB`K_Rn{0H*CgrpT9O7
z?WFc6Wj_&@HD6$DFQ%I1pI~nFZWx5?_k*JhHN8nm$q-hp5u1*dSOl$XRHj)lML(e%
z84nEuNto%qIlG{)4UL&;RxC0>`L7jynEZC@hj(X~InTySO~yRhl8AqRE_%D#y*17`
zzc71O;nl%WZw{0hHVhlNnpjvO4c%GW7&pCQC;Qg0$cSR&Y8&%k<2%#2foVD=noHwZ
z60g6|-d^UHoDY8#)VYKma$Rn{GUUdsML>`OTuQo(#;Mpc8>l26a)ocE42s9^FKc1N
zVzW<|yiGtcn6#J;;liQpw13ZM|M<s$b=A@|rufx!VZ#I9jiaz2GcuC7uT{zkEsVvB
z5uN_BD<b7LTzAY@@wF*tA6;Qs{Z**n_mg|s_8XW<oFv`_jW^FsMR{wSvH54I=aQSy
z=-Q<%+B-zQ^Zpu5*Yr9yr!!ZRXKLS%Q8UhQ4S8vVw4ueX^)vO35=$fkdH2YiK0s3v
zya(I0)#At~apK56=8_shP`6ngD$BW@U!PcRd&~Uw*SdW4L`{B$u}bc1?yH!6Q>nn!
z8#6z_sa8JFsg)NX$JdCPlT){bF_6L>QP7-Ata*=N=9*?sL7MEzz($X#6BW<USc!dR
zp6Ob=uH+h&2paE)UN{plAK_-Jn)dUF$y0DN7XqAnHdH@bl{io%4`rJ2h)yaP3vv8>
zIz0k9{pKoT+aUK3@B$LO!WJMCYM#@xf)e*3a%jFq>^Og!BciOSb!3@Q;;25s-LGP0
zL`1FCF53>CeZ01>1^h94ZDyy_79ekNjmRfk?mN#N?{)%;TFx3_XN-FNXd5#<Pt;;N
ztBEo+N%%}?9F@q&vby1ZM8i0ys!fO>smkc>Ie=M=&U-=zk3U?O{6!}UNm{WG#3ypk
zGN~zm)y^f=soIt4u8pYC{pl%_zr`OJG%NoctRN<O#jV7CDb8@#eqYXP=xaPo^i(S_
z=i+A8?l67vMxhK2CLp+~EJUVy2M8WQOp20^`8=L)rs&#q^;;$BwgG4<pI^fRy@zmi
zc}=b<rzu#!1U#2smUo%{?pZ-B^!ysXB9<-ZY|o6%-k(+%jG<i{hJ&S12+a<qO@#7k
z3<ju2Xj7-OQ5c?jERgbNCh$A&hT7uas%gX!KuUVcI6%FAJ60?WTk4TjCW_ZNZ*%N@
zyN|rfnGo5v64U3R4e{~QR;F};V_dep*%A-h5+K%pvn^ibrOqPcrAgur&((A{)0F!M
z_LIr7Fb!|Z!U>#G#k1GfRqlP_YJ4P4P(i|KiY}L*QrG1b6WG;i?tRCe>DKt5Woq{p
zY=rK{%M5jSJTkv}&PlRelf3oL&qs=}a$n$2gqO?lXs&k3D7g1UO&*i?Q!`vuG72Gi
zzFk%v+rQ$En9ru*xvi5feRIJ;_N_2B4f?s{(d?Ze?vv()BV!`N%keN?0<1)r5K?EF
z2K_^CdT1;=P!vmBWOn)ypu7?XAxRkvRS{5@Obiz9C|e%k4~7!B2O9k`mt^RdF;^+D
zLGu@n<VM=xN6i=2e#1*pUOVP9^J>s1g?ux^Ezu@5C+Sk6+M`(Arxqd<SQF`cKcZsY
zj4WLpIP_#o;P`va5K|N4tF_p{@Q}=^(XZx>l`-^Zem<qhMt35^3@wbY5sc4Xe#w>D
zs=gx@zSVAaE7X^)6E7XT2<PbxQ`0_M_Y)^wa~&klIn%KHks&B!+*5#STK+n)Am_65
z;6RZSCuz@U(5E|n1ESS?qDao0b7n@>ZP;4ULs{Uf_}CLqvew$9#M>oWvuItYwiPo3
z5)Yj6#tynJyV^;={F^>aMA>8g$5`K48UXa<45x%7Ubaopl<l&H_XHLIQu5MYfXK87
zr3&8U>+|@mHEk&mWXx6;;Nm8gYNwiT!lc9~UukSgkC8@9$c4EUy+r8OMx~9hP>4`@
z{s2jd?cTzlq3N=poaMRBeE}&2G9cJL8}}^r8)-=QQu#do#G2}Af60=UTYOVK7=gW=
z9x%XXioAJ|bv;FhYCEuItb16_cb%Dellbr%{8{N$Co-~P?E_3QFi!T?aP#rro+%ff
z7d4F&TbJu6?jwN_Z!4;aR~@(2m;<QK>`7+!?n$Uw2}_Amn#Bvrv{}yyuvs;-WMz9W
zKIiJlvYC%QRfAV0V*u@69cQVNZ=~Nb@96wCJ2LtTuH~CH@g6kb!0x=L@8S6&BG4?a
zI80!Z_3%0A2QwUlrl{$-6Hd+h#ZunyWg1kFt{4xLFYjxwHzwj*p4BB*2NG;ve@6Y`
zkbPL`bPBGpENN>^;`q1Y6K&RG_Jk!(Sv_DoRs4Y$?eZ#1lyOpxRE7_qNsyD~JeBSE
z`id+mF+<diIaOe3Oh!tbcKsMf>MNHPY#pnF0*OP@B~Lat^V9LF5>dtjF}CB@&5IgO
z^AsY|5`~ZjUzd%_(oci4Kh5J>F9=?izCQRP=Uvx@%y9U)%N8h>x}cQfKi5&X+LUnx
zZ>>71kUjm%eF^u7@dEuaZ!Y~9OBh_P+5v;rx7kvQ!4s>c#E$WjiR9*11vlv37T4Up
z(WWFB2V*a!hhcGo4tDyxCK4@~9h?5in?--j`9x8ye-Eipt})AjaY>_!^6D-ff5Axz
zCmIXF&q{3mVn@ck*!hqi`7YPE-J2@=7&j$;FCq<T*K#TQ&#_WRrdbi!UwI$Z%jG<{
zEC#TThwV)z&(Z8wme=Bkb1akcU@E4!(+ni!JkcY5w3Y5e0g!%G1F^z<nvHk{n95VJ
z=`cK5T1q?uN-SFZ<jd<yiQP4rx_o5>EyGmKOk9DlE-sEZD@kC<%7LEaF7&mwH<_z4
zPKzO)Dp^QKvW7fd6(4i2Yt!Lsh;|aEN8-?EFr`mcyiZI{IniqK_HOD)8~)_=qY4(b
z*OcbMZzt!?`vKCFfK=D2Iw)B^`mw!5redsM1yTaLgL-9er;Z%hXsg5YCkERTKyS2m
z&#NQ?pIDKxd5^!_s}!tZ9C_AzS>x>c%}#f`u_e(`V%)}ex@lwPCo-ENGS^4nO}so)
z!&D9%<5;>i`_YDSoi52m`E0uUZgKCn;^R64V?woD;^#{&0(;QG`uXm0I_5?arx*f+
z+cJ7c#=FFKt#JnyVCP=$Tb5k-`~K^2{fR()5O0pT5wH8JuAIAh_qz~Dm1SgnwC`u(
zI<GI~UHm?HknoV-Rar*Gnwm6lTMJrTKSUty>>i!*c%UBN2gVjV#J&;Ai#EYQJ{YSi
zJ=Ul#Q8CYjI1GND`q>UG^XJd3n3m6qY3dY|wsUah#tI1vTw9rW&J<K*wBw_>XGLc-
zXusGOl@HpjeJqGy0@Q6F%h_Bj?1%|od22L)Y7>YuD^^_9(7$5g&YoZf?M6{R`@zOL
zZ!{~O1X*vW4*or@g5`F4!~%WyEV+Bc{na>YfG^}fKS$QkKcvl9iHdoR|Jt@4D76GJ
zh{U%b6lB{tli3Gr$lhzaG#S?IFEH=-Vsr@B_3bdNY`q*ms@$;G&%vycBrkctmcOkR
zyhw{Tnbls#`_w|JLNx^MNe(s6Kk-$rAq@#N7d2ydEAxgJksCEU2BAh^2@}kLVjF}N
z{)$NrHs9;yUDC)cWZ=xoyvXwtyFnRKi_{|vp}22!hb9}zW2jE8qYol|A_N3T<Ch)A
zNOQ4*+$g?rUdiO_!IkOa)D=R5##rF1NA1O#?8+L0ikIR{M}7D{uCy&I6H<HTlp~sr
zPkhgv&cs>2^_>#AX6YyF7(P>wtw&I|kdrzl2%n7U*7|@%^2Ra(>na5{GKKV7WgpaB
zA1l*PW6?PgoK}ooPDgDiK7DyOyBf<g^9xk6|Ac46gYBftbzhm~kxV^M18f`O^`f9P
zVMW^b+9IGP(XHdts=V#e!YtN3Jnx(L^H~K=eFp~8wi^AN4UDW#Vb^-@0HHQ~>ywl%
zbTDfS)6vN$F=_+neK5>L(oLdbHhykx9se=Ka4$aRsrBnO3-{bzr-sRzPRSSZJW;vW
zgucCAd^-xikWckm9xt9W-Re&KyZDrj@0#(#NR2<7N*&L@u>?Xa>?0w)Z(hp7S9GlB
z!4enl`0Z|{rdc~1%E2{js`odLsIC5C3Z}BFE_66tUUtkUA6-w9dENr-4TEbI5_Tw#
zDab~WPU4Vu&d+Bt<@>D&Qa@g(#g8>AvK$@3?H|~hkcXqKjyBBbvzTH_JrC-Zm%k-A
zJSEp;@S_?Z^Nqj%kzgQN*~Yg0)h)Z8Emb(_3&Pw&OLsFshOXeE%4tDtCQyi8CAm8T
zURs(=S8s~}g0g>zUXP!v+-{krWCNsv3wPRXtZ&1GH=5!N1(}1cpU?c}(NUfPSroVU
ze8vqyh#Lo@%brBvxX)EYsb@2Snw|O8DNz?rDQMtGp!A0*_UN#o($<Lk+`GF=D%>Zd
zzXs92Z!0T4Lb>nvgml8N5R~yKCfPZ+px@|3NL21zF?&U{Pfx^hk#39%ebKPwsl2OO
z{tM5*7^XRWGrZQTBSTT){h-RaYW<q{pOE>Q?B4?x5|oJp4QVI#zMy##t5_nIZ}kT!
zDp;qV!b=8@tI&U@8?-N8%QpH;yUul-vwp}eIm2X?hN}hA4v+Fm=#pQ^$EBjHaxSLp
zcA8VybSZAleVtj)>C~~pkL7vka}|b<@wvU1_Vz&RFdV3*Jub;c4O?SHm5)nYTPqc1
z3jO;O6N-lu(0B<|6E>}#zivd{m5~?w@*9fHJU1ZM==<r$TE}xoVnfoUisF|IBGKQ5
z^0QLVW-&>xxsv5a*Q{Mb=xQ|I1^R^Xq&D5Gbnq?d`N^vXo=y~vku624|5PV6hg$d@
z@&2OHasF$&Zr93PnkvRFF&%ON?5(iv`#zEraiaZQ=CO_z>``(vB(ilvAl}rVv4bb^
zjGW@vQk9I}_Ub5!gxI+gm5Px@V@7HBD}nr*K%f>5Ynq<oKL8syL7AR)lzNON%}7{k
zC?A+A{RL~rZw*1wG3TXUpwjbVOLfaI9lJ{Ptqc#prN@UxxBDL_nsR>Ed^bF`Q!DxO
zN$jHLWxKvxT4!C?bPd=lDH9lK?o<?1Qd$vX`eHy7wkB+&=KCp3;#7Z#pUHM6snk}F
zbtvs^R%p-`jt%2wzFP+Dafu|Tf0i7i(XARU{p(rbz&Cyu$;@TWEo2~XXeJyKe^9ad
z0N2v#mWT{Bm0}m!lpj!6Q<J9H^@U8gm2C~gk)r)6=UQWEsTOk_8|_;sR);pF;nnE0
zRNn(t7x~5U{Sk{*vg6VWbGh7|)B~H~r+Cl6iIQgTqU^7q73u9$wDlh7enmcFVHuEF
zH%mPf12qNhs)weg@W}DzWsnr1MF~IuV8p(zPIGPZSUrO+Phl(GrkLP)K4L;XCW+%e
zF&Iy7Cpk--1=4@1Sjk8RSH5;@NOUgM8{A*}_C@H!fbJK-zK+RxcYJ`<W`&J?_&WD*
zgbk~u;C1JxuP(PfGEk3)<B!ml4?u>?q_m^y%G|I`dj6xjE}t;hpF~%WEcQPgNe|4S
zbm!c1_2-x6#$*I#N!>C+bJh2iXRN7kw|LL`SwYY3ti9N`(yVw@+8QO}iUFUT=``53
zIja(kfo=XY<h5t7fB%{DTaMbs3fp(Kdct$x??UH-;}lqmEkG&TxK3)o*+dD@$1|KB
z@CZLhEHS+Y&o_%Q8FX<=%h7qU)ru8E0sh<@+4|CZ`Ui?A{9ULwW?TfEnBFE9L4o#7
z+Ov4~e71Y2oSgmyVnyA+tJJ!S-8o~~oq2wiQJl=1Cqkxh#oy%E=*6+PRnPC^Yg*&5
zSY8uqf?y%a7x>CsbnN&Rj9^K%QgxJl;47Rwg1MDN<EtxxEi=s~Si?WF{{xWneVuIT
zYiTi#*9_yW)(SM3VL^IKsY*(k%e&cOHJFM&i8nlEi*Ggnz$#M5`V_nYCU=ks%Rj1X
zewGusA@dQhrH2r@F~cj0;@G*E<`k{to!&sdG>XAAHQSI!xR}hsxDB%4y(umhsN^w6
z)$kDG0{b!a>@@5^R6XOkd=$F4|JaFf;J1vMW^>ujeh-uD;K1^0DFA6WP*18QcFc3N
z3aE>4GyG(LbV|$Ghsx&74G828AcR`G?{a?n_}V;LmM9G5nCs<ug#FQg!LNLThFD#A
zK!`7|utYZ|j*SMVR5j$Xw+fh8oD%`7{{H;JdRk2Ju_nT37i|nPfr?BEnKF)P4yDh=
zr9vjnU;1yjX)<UyD$EG~BG4}6Zy%`cr;Tp1>;;^=L`<)_&YLlxoyp+D9}&QM+s{Hr
z&Rv>4F;h?sxjX`$lGqsmz@vSXcsW(%fRrIYU4hd}?geo!0kIu1&#7iS9gm;c84+RQ
zp{bz@T8wbMz{+_Jh6t!2zP*gK5LN>o&Al6tQZ?2qgXzTDBmz(#Pw|)1nh*#eTV=}N
z?ZfeIEw4aHl~?uyG`2~0N+`ndcz;ib9b-g4*^eJBrwhJBaBrO%jX_A551bNSuDRlB
zMQVKQ;;kWL6OZ-X7~@6%biAOSG#2~%^f7R&M5v~Bt`Vf<%IP<V$1~x{Qz0=^-|uG;
z;iE^}`+O>G1?Dmac+n+RD^<$AS>qy{<IfDTqths5ix-faVYqK%VHj^J=nfumtv1NU
znlMzeUQox93#V%=xIGG=kXLt8#aFv%=OKK_`<*?Lzh^5aXa4H!(bt_nW-{tC!YCa1
zJ>lpaGJzgdhI(2yWZ)-vjH&6k#PmIx%Or~F9BRdtHjjM4*+OhS21F$k&nGj)RArbS
zETkArHH>sr60{YY*xa(wPEawWzHJ`CrVN=EU+5_G7AwQOq8f5D$`{39%Yhw~_+fQJ
zBIVt3=U7sIHZsv14TxITed-=qklqkQPsIm_`?&<lf2*BOcQK~O^y6AIL&uwQGej+C
zD7jAAJZJ92)X^l;Xc?`^bZ36M>#NJAT3l|x-aoZsUOY|ONa+eLrSl^ipMJk4Ud}@;
z0#+UsUarAHs%f5S(0gFKcTJ-dd9&fx7c&UXpgpKFs)l<!blTkot1J^`J)L%9Bx*lP
znH+DCmp&Q&C7Ls@s)NyWnmgV{)Fhb*mtM3Ldo8;vJaZG*)ILp6Lp#svLrZ*GI0Q2*
zUC*|g>rp%$|MHE+wCos9%EaiZtA-0l#wP-<`hG3OrfH_<DczqGp^N=uiSiJu%r(0C
z6N5j3S)xwe-`so_etLa6UU^j7KxVf2XHpcp_+1X7O&N8qMYS)HkKJkD-7_IZ@#5|u
z;K6mR@gbjsMiSJ+G~D*L3F~KXQ0X$6w*vCgCcnpvthZ^^c0`yd8@u`FFU5__!ikmK
z*#5XP&UPJj4bdNB7@tm@=J}BWWG4FLm8H^p645evWNO_jkp63~i%R)kKo#cdwJaoy
zi@`mrQJTd6pArq1V!7!QEhsLF*yo){c^7Vu7?++u#)Q44_~C5=lu#cYXa4`w+y1xb
zFkyrtwq53bm6|agOmgC-t?VrJxgWRQ7p9-?nE9DC%o#;f+W$gZg+@JeQk`cu7HU^F
zGehZwBtWnnD6vjyP3PeOSoX9G`Z2gP*~embIgh!z09;BMAnVX+W55_AQ87*Nd<1^*
ziB3NUW9TGy9`}S;K7!F1%lT+6GjWzgSS!iZdMZT|_ZN5R5mXzWQBQz_Te<){k$YT?
z(HVf93)6+D;gF`|C{jW+u@lpQXHa}b?js#7#qX`9VmXt+7;zDnwsbKrFyj9f{zO9l
z7sJp~sLbU5Q+%Q)SQwcJ$cxN1tvTH2iXBO3Hg%BV4O0W?u*Z=&Y`uodq}d9bG55^}
zE(qYYXZqa+?n3wO^$LTUofAqk&f1#Z;V|GE9lK$ZMP-?*jLnM6$A8~3p?z>pogN%E
zmn+(Vurc{srVdMjr@J2YeI<LP{Q8-tCt~rwpKY5OJ>%(@gje=yN9_Djw5<;+;9W*m
zojsGczQsm02qfQEz;JZ@t*CvGQ^D-$^R3naR8#lY_n`o@e*nk&5R$dTS(lN!>XehU
z!Yts@1Timr=8kILc^1=UVm%Y_Ru~_VfgwNYUE=@|ig6Di1YU;!RJ=7LRsgRx((wy3
z1YT27wmf#<6MK?frjqV2#ajH@GT>x6l)<=rL|U(bS35R*Z`Q17z6EFgUi2(xT#v>5
zs`H_c+9kP`%%Uy`N{>)~#VNJf%pVZ$dkaPehpi&UDj&8~2Nd=g<|kq?VpIkZvTSgd
z7sz@NXG)whac3w|L!UJ4AhB+4YsR0wgMvNbsl8J-SqMxgHbHZ3-ESq2kJH|PqcO$W
zFzw?+i5N4zbNg7Tm?We+0?T=*m+JGzkB>5rpPcwTX?GlkxoIEUVlkZe<+IhHlu3DB
zcrx8_ZYYnnICIt2{Msm<BR(8j@Rz<y0ET|{7Wu(#iemT&xT<;{&j5z~DmvXNdm$oQ
z;*WEjGI3Guc4vlcvwufs{b#a@N7LCOmG)5qpjnCl`cd@=vaMO2^vlKLl>^%S{e<|8
zj(w_T7DY-P4n*5unubyU(OGJ}UK0u(>x%wxv@ICOfMwMpa%r>5E0(N`8wI|j8#2kb
z{h;PhC}$_V3~oJFqHKqzFinkls8xLTcUP{>G{4~!IhtjNTB|osFAc^U*i%&VY6)LL
z6CnuFMqjmyTG$2?OlQjO8KHQU4$a_(9%w<A@m|b+w)lkHlT{tAEOJO*Of%t~`Hx?r
z#Gj#-J!X{O!7xKuRKug3M*bA)q|l1L?5q8vQdJk<9Fhmo%-SFO;4<cZHYiAP&tXX-
zL1o2+b%@#8XY$lVQBE@HiUnOx_2Jh6{f`$(vU7?f0bby>W^gvmTt+|(#FUQDnR)kT
ztgAtDUu>eQ^_NB6Y0M`1s<hY-u`B5c0dY-`fk5H1fy#1e2ir^Dzv>M>Sw>V_7Hb|i
zx2O<KKEDVXC5K;gPlX12$3y`a6O%?2Q*XeUth=@EWK6UK=cRwSDRXGCjby@&+co$e
z=O+NM`;6>8383|DW{ST6ZziFm(Cv(vagEYf8jq7ix33ShK4O4*hA*C*jBC6Pfvz0~
z5s7kVkQut_d^{Q?$)Xr0E8KcV1+u2R)f1~0nfU?A=!s=oJTaY{Hl9p!t<0<<ua$<A
zUpp`dwqV25*V}f!$OgNMPG{K1Cv}QyMevIh`TQzBts1JRe&sDFx@Q@SkvTo{bm9BB
zkhxvD^)99YUFj~(G&{%`t7JADT$hWcYw8(2kLAqnowO%zAV+bHO8pPM-ZH4Iuz%ML
zQlL0AP~6?!o#Jl6DaC`kLy-a{4eqW1f<p;TOR?bYUbH}QYoYDC^X~KE?AiZ0=R;<a
zNhZmx_2F6T_uTh&0oBWpTYE(#rjX+anbIdn580$46q;hkRXa>EdK@4T4^7Ezs^VhF
zptLiOJ|q$u_T33~%In*q{wkHupAnl3wis-N2t=Axcls6y>ps8XSam|WrnM8M<g4Sa
z*-IXMoUiZU_V)Q@%)8P=R*K}NT^)l<8!Iy$H^|F)dxLRe)G%slHiO7`AVPiyOrJYV
zWL?YA)i@G61ZEKG0b<O!JrT8dAM?eLqFBpy&0`L^T{VL=*NV!?xo~C!=wr1lJzhAf
z4u0hSh9={#ert0fHt^Ji_S1|HCB>=h=k&opuEfY7Q74>(ycQ~Q**L90vUsK}$rHUi
zVLG*KvUg?KTYtLt96b9UYc6nb)oRKg$slO|Tv3&<Dxuv4!Cxl$K93@$_W63+COsZP
zM?Z*oZ0RozJ$OeHJ0EHE6&fK(<!nk*A#8j}!@l=a*~bG%8nIm64iA!KxM0XJpYbcC
z#m<6uV49bF2+AcaY<RUaQi8szK<Dx#faEr=zs%>1`bkJZW%QWZ=rYrkAz<ml;#q`)
zf}cEv+~aX<7N&;W*JKZH&g7E#M!KUdSN3Q$WQJ%(sf8Z-nu0imj`HAI1R2W2lr}<P
zru=Z0$Jatu)59tD=N1pCqLV!vzI2tzS;Bp-BeR+xV!{YrFUK#8B!BU4yP#Yk5w1Cz
zHg9=-H9RUHXFuD{3Tj3XsyAwso?KI3;@n(=7=zyLVOP0k83~i_4Aw9Z2^W@lww0{n
z6Yc?3rSnfIc>BIM3{-`!aMztFfdmv#>Pn!hVRpa0jeGKWx(twZWx0%C7{AnCWYC(N
zHg0Q5!k)(X4Q^Vf5t`pL4*YfXzV-;0igX_wUoNwA^tgdfP>u2%oCJ?mxQc5UTa-k>
zGT#NO_Md;HT}dautG#$TSN}UokvQ=7UGDE1w9aYHHvwGLw35}ipVe`nQBfr|x3pWo
zGc9~ZOLoe0qxb{dX+yLs){QoRT$ZMZqdT4JtyJwnK1?J!1*?z`(|iikZ&)nnD_NOR
z+!2hHi%S0&5KZnql^Z<ZL>C(WtqwrYIjlbUPsO|qqS45V8_b^XHk>DTW<jp}vp-Yc
z>}hdojdV(SEqi-SKjLV=0sKqXO<IyA|FEAY)Rfsz<VGj2`zf&cC8aT)@Omp$(tuo+
z@7Q`_tA#S~ZS}8Zl^<I0$vKh^TJD0D%t>tJWNNH#78S_qpT0WIv7aJP>3(gPnrplW
zXR=FYfjiQ>e~QPQ{^C~i+q=V$42G4fwm8!|@?L%*p55DOYBfCzS8=os{P4oZJ2;E&
z0|m1vAB;No1|YbeG>6E+a9f6mkz_dgKXhn`=r!NjhEiR6@UL4s2A&R<Hpv9t97<<+
zH^!<hlB=ha;TzMIp~8=)Y|C~oo<p@l^f6Mn)8c5R#~(8OjWvF?jFD`!Dn%PWRm*)z
zQmc=@yS^0W=Wn!-d2>$jlf2a--<Lw9ap<0PMl|r>vwOTmv*`+%a<IMSH*;VbF8UOt
zi?%ztQ)G07hig5l2K!7`y9}oAP?Z*YY4|E`#<k|A+1&?{iE;2;h`+$(8)=idW=Rrj
zFwB*Rx;^hfa~MUd(%{={rE`_EBt^j%gq%fwk^{$Y_^9(0s#1$lG6>wYVF4O=zE8?_
zVJ^)=0$VChUG%Uza6wO3dY0bJDV5MZ3j9^zP=}|U!qLY7``w93RFUF^pE9v5f!dMt
ztiiWS&3?WM@Wd^ZLY^#mJXglRE_JW>{tp+M$cag+^Gaup_$wWTW^obz<$}(+5zdc3
z?h6`6Q9kM+vNdQEvAX@(?VPn=+V=8fU7FE&b(ktm=-RHmI1M*YAV38*ppD!4^xP@<
z(&MmQY8G<F;4Xl%-p<g~Y>f8Uv){O$sN3&2Ov&=wr$zGIVtHkLwR#$s;VBksTn%b7
z!R0-WD>QQGX-&QD)9XHJ$?)C6X{Og(T<~{?vq|k^Mv7`i$lYbM7%Y5#rJc+4?z;)Y
zjrx5JN#j-rvwG*9D=GK~lX~0lHxLKx6wR;LskMeDf<OGsy=0dKJXtVAo*m6;F0(qQ
zsKQ#PCmh{Fk~;6nxSEqRN7N}V&9kp3fF;bd)it6Xu$zCLI*#vyRnEd()+RG1JK3Xk
zJLk_EXD*H%n5!<bk{v@5w^u3m5X?CNAIDf*9^))L&@uwPKi8oQ;To^k%XB35=|y!f
z_S!uzn|mmq0%4tKzo!*zkKXwKMoRZxFxFE`w!UNUx}Gm`jvxn3m~h+;e5_#JkXVVM
z@_0Y|38s6SB~OQ)VH3eDi3TGb^UMGXj|0;*z}FBJb1r2M|3BPmG0t%vs>3?|+4-&7
zW$gX#0gcXjX+JP;k<@%j(Bzn|I>b$tR}O}(TOG+uqj2|ngyAXmJNhTh-O#;SA<Ri>
z>BKA?|M6pZ9m&>^rwNGorK~G#=ohBaRFuz@i6y+kc668I6s<urBu)L!T3WaLOZ1o3
zkIICC%eAL+G~_rAZT5%z^3wiKptlKsG`u~@sXxwEZ{f?&kbT`_$-292Qx+z}$fOlC
zdloa9R?s~B{WGKva?qr`{C=I``P=VH0|GtF%xP>pjx4sxsnV}}>chr8T_o{}k1fLr
z`CoQ{S=igTx5~_aZrDx@Vw3lo43+7Y1dA0q&(#&qw811{`5XDWdatJm6=&|s4%Cz9
zpvQf3<0g`*6soHu=uTkW$8;7;yCtb!0juDZ>eQpJ8X4_o?JW9hOsXc2&?~K?+WqYh
zZ6aOO#}fU|pUzFwN41D^r6qr;!R&NuWGYK|)k@L32}r}hymNf4H<gYD{zv6O7KttH
zKXWBL>W%5*+&t%j<`};<-{a24a2V2I9WdoF*GMF@0qk0wJaY4=2C!B?R&OrrAf_f?
zd8%h+-dhiWmMcFAU)*&2WRVr8d3c)2#~GU&ID#t|8jrU8JebCQ>fP0zdsMY;%uasr
zxmixyS$o&<_l~87KG@q0`<$bvUCHOd&A~i4cO@>!E3hgL?P*E<LcCqf4n`<BI;=cv
z$^s6IO@3K}RV_sdV}7r5W`tzIi0A&bC^U#a6_<wn2QTf7^`jDd!rRUc`JNbnEMUZS
zu{)`;60N(#-#y|$G}FJ!FO7kDmMR>yz}Ua8@L08%-S1{;agxO7a!E<?9uK#hdA=b-
zE+~)R3JMt%&_rVu=WmcB-?{l$e4k-TvIbt!X0kmyil^rg9d_fQHqIDVq%r%hFhUf1
zE+XuK`R<bTox$2P=RYQEBBQqd0Mxo;XKX%*hvwSwWQM?F36^sWKKV?!{(ff$#ZRsT
zHRe?f`-=DG(m}Y(g()XQ6oHq_KU_b{5x%02^UoiNWz6jBIed?bL(lvhE~e;3LX)}u
z=S+o7gD^pHy`5H?f|sBbg<gTge#6{pA~N&y%5eV8f0+e@wi%@7Hy6N~pWy0npIwjR
z*&~>gvBB_>jwCY;ptDwSk0lu*QOfW0eM1J4D(D_m#ZBs6&6KIpL31oh{!01Z)lqTw
zB~v<Ximxk)<jmFx=b87*ewghGon%!tGCnjK5(6YjzCMZGA!tW4&(`#$>*Ke|+4wO(
znOL`WV^nihR^iNmw{N|R8t5VWvTAb-5y&4|6-V5Hs5&EMB>y>Ri^OO!E56uU`!Yu~
zl@XJ7Zq-IAq}3b9)KO6|*|B@EE?JXV$fEP9y`v#Sj#8{-z9_PR)N>=18|@(YaQEC%
zhDw9)Vmy`2?n`_d$X>lWr-qPD2&c+Q!_9{h1Uf0sD(E_}@9KUsIl!rreqI*(V0V#V
z2gj{Qjwy3XRGa8bGaY9RUp<QUz=xXezl9mQTKZ(Au@(8oQar#J7Ml221#5pY*NNJE
za<|3Q$40zG^tplYymu@b!=k!be@X$jttVoT6~`DS=G%gcc3(U7IK_!Bjq@93Huy-b
zdo<~`&bT5T4e{H<?BF5@bXhKmFLPg<^`$&SPw7Z{4G-T@ChEPtYLcXqJ0R%gIJ4f4
z771)-Xm<dO2!t(Xo+`FFxCCDe%->8-(UhEUiE||*j@yN@!aW?1`@*>Xrtbkf?LI;S
zP)^^|j!+q~ix=e%{tWh_^>?OtG;xS;$%?TnT@4L%)4Y1drX_@FcVuImHYzli2y45o
zRBWqI)6!qurVGxX<n^`kOriqc8&|M&VuhB;+}-Lqj@i6yg*?|@ZxhIcE$_?B=#L$X
zN4y%|qqls4dc1wQ+>mSjXx=^OHh7*P^~SgZ(<ndt2gy;lelo4vcxO_j#_N=Z0QmPh
zSxr4DOs}5t4#2WY3=Yor{^T9DsIRO?Jup)`e#Z(VvqH)A?SVTJ(X~NijtY~J)nr?Q
z?T_dAB_~b0B`pTby%(^jcBT)L0fla9^gxsS9#hEp4GOydC~+pQ>9<hqLs47?wcK}y
zPIP&Dx!(?ahu2kQ$EM7p&BUiGotLxfF(2N0wtsT0PbWt0gu+Rm4!<t2`o8bh<qlK$
z9Bpr|H$LP{KVMS2(NYqWE#{1tVA1F@Y@K|B8EDWbB;{YnXiNvh{gS2xP*ssTM#xzP
z8;En={@_%5t!sFw+*PQ6mt3AI0a&nZ9tt%MnF_!!crS9`*Xg%u;<0`At3(Kiq>d95
zo^Oj7ne*#s7Of~*{w$(gK*rt_I*(0pZmfP0lS5er4V#Z2t3uyJ)0+0v!9b4*E`1>%
z8ZSY2mw6cqX!41N!Y{3s&hypJZz4_Rr-dq)t!jxR;4UtQUOdD~Q&9T_m|qN_wOIPT
z@!{wNN2F2y!91!|Ex<1s$)zdUD_)&fMe1+8+IUJaqzQOC4nHB6w~toyTLmTlwxkes
z_+&8NlR-JGk^fHeu?+3K(#K%{!9qqfNK~uovvTxOH^-U5st%1nOQiHaQGCIIvxlq^
zX6(ZmHiY(Ac0Hq@a$i5;U^UFl{=_f~&w%_mdKg^@5wL@S?_k$*XGnHE8ydEJR4ME^
zgum<G7^KHdut4uO?C^zYXCM$K`25$BbQdO+X+~Bq^MvmW`SYVg+IsoIt7$eT>|#^V
z7J^qY+(6AzKeNXYZhDxPuJ7xT@#e;FTm6*vuCHJ5xkF&gA3#CgsHxd}hRIUH-PJ~(
z`7^)8w;O)Z9A2O2I?vIUn5b00=$jRb(+XfqQgtfS>mP{;^TH*9d?$o)9qFSW(eTMy
zj)R!#O)0-F*B&|+HhO6g$Jz<`^6w2gjUR40c4($6Wk3eX8BvD)Djf_U02{_8IpgYm
zqGnXA!tmk(JXpLq5cqslETo2d^N+1R47)?or20!+yDIpCMDX9zyRBa<I_>yO{KCoO
zQVY$r0um>hGl$R?gL~2An_q(_y*%yh<$@cBERaf(zhTC|8=W(~&U+w%7=69hSOs<;
zrhH3Oj+!t2gb@p=IlE4)DJ|uIzhlyDW(U3<UEXSp29t{obX}-d+X}$0343ai=Gb#c
zWYO<x{{vX<PC7f<Q&PVO5#3aKM@901UV&@2<6&C11_RoDRVi4rNx3l>=l{f(Ly#jl
z@`{}Sx0iu(TAu1Nt}T>mzF;xilCG`vC@VCelxj1IVZWxTq)(Tb?k@JXKDs^jnW8*L
zh0Lvb$gm(z@KNqyO6YrKMM?`>KdK+oKGB^ZozisBYQ?D@%-t=j6^@Nf6X7PV#oFOB
zqX#oY$19SPSmnfwK6U-NT5gn;f-TAhC-0D%v^8vD_cJ@9H9uH&a8DJ`GPHG<FIIdj
zreX*fDD*K*+-++IvxbYwRg>xN3|JH$NEiP$EiSLh=+7Zcm|9H4Xny;zk8u^%j4&lg
zH82jUu{hm&ixvFqPBaH@u3T*s!gCn&r!EchCVq9W^FUnNkZYvitwqXj_i9l**T7GI
zBCh8@YvW86drKSZLShg5f$^?I7KGzFNlNPj?=dBfF3n>-LwxiAwzt1=UpQEKSZH74
zMuj>YRd^U4cC!Re32|5_OyDQ{!!T{|r?t2r-#F<&*-|?{%t`~N?k9Y*=msi5SuK4n
zXV$7ER};fIo$p{mu_#Xw)@EeD+}a<~Ymr~V6JFTuek#NEQv*?4Y&yLeHcQ|ulF_&A
zuBX`7Tx{<xHrsyDeqS|xd=wrZ>_o9I)PGMa$tO@e&Er@ntKQDMduy~2&UF<5$6WoL
z@VA3qw8`r`KmOW(0PuNU#YgS=7E?L31g+jKuk`5<3Y4zM&!Ro@#Wm{*z4P1=LrL$b
z+nGc1z?uSN9Y_Z$HEb`#x5sdiZP6X&3txM8l`_0w9|0MmejdV)M09yvQCns!csA{R
zw6C#S{lmRkV8nir_RHAmpHaUE?s2wxIH2`YL7(y0#zmxjV#9`BOfeAQeJeZk>*plk
z?~A~Aa0$HX`vzR(V#sklm}r2UndHQ~UH<Fsd#R;Z-MM<?lU#vk?n%3#=Bw?Z_Ehp0
zli(rm@|1UqeV&^UTwf$hc>!7vaGX<cys1b5SfLb?2YI3qo2(;ExtG)im=$nAid?mk
zl@eHRlvkFbfM0<B>w)%i7$YC0Vi8opQ4#i(GS2*<&rL$tX1g#t`ZSBh!8Xt!m5NVg
zfs4yg9vufX_&>(}|NqYknDQ5I=krxvSd-3&`M`o&$%{iAlGS#p{353+jDqSaQmC4S
zY@5e^emWHQ#kerQaIZ)OLtWc0UlokpPKBTksvpG&YC)uo*ajn}=#w}rfVcxe6@d9P
zbq-<@_29jtOLg!^?Pr6M2JHWqU<$~g|A57d`rMy%u|>wM_F@{PG8))IU?TCrAlSoy
zyB^V6I<zOK&63I);Fmi<z_|*LFf*Q)Vb|~oIxEQOlmCJeNi!?JoTmAL5>{%5>Yx0-
zmYe@+!(kM8*#fSd%lACRT<wBk1E-d<0vZ(^;osb(&u?#l3z`SF1(HvOP6Z|Jhd>?=
zaPp!6bnQSSx5s9vQwi^2;bLjnf-*W9Hp3&Z8pe2wSL`w+&Xy4vcJv8bkj-UESi~6^
zo0}nGB&>@S)5wcD?gRg$yYt^Z4+?)~g*vlQsIwDAj8c`oo&zs8_({ka{@tsPs6%A!
zvGA8!1B7p=d^Qu^)v!KSZEsw*b;cMD#<8cnjfeYux3)Cvc{ZjZ%AzWo9z7jS_-^Gm
zwKXJsnYhi#>@n!(lYdu25U$p>c$W~J{wjia1Q`MAJ8jHw$#Bko`^$;jaho-bWo8Ok
zL6ARXDVk7R8M<Pyhqtluj7<McLL<ni=6ZaXf%z!<&D_o5g|oZ=2$ztWg{ctv291y=
zvb=Px_VZZ4OC~qUil+t#xCS&=z4S)mY0+03l4p*k14=hw3CC@GT^t%_^33gtc`1GV
zykt3<>P!1gF3Iq_`bg-)G8xTM10ajviRAm*rhSDkSD22jmg)<SMYTT)R59!Hh;0@3
z<X4j(RmyX2TGm%f(@Aa*CGE;0yuX)x;k*fck<xAr%G#EryF78i-)ddQ=coe}@Pb6A
zPx7bBs>8E8Cet3FP)HYBg-B;wKOwRfB+AL!{8C8I{m{yu=9tEir=WX*Kfv6fZFOAZ
zo-QlxxYgg8-fFSdlyXj)TWQ01Kj1Y9>!On+nHGrDRh9La$1jyzbN#R?#oMs+(p)#Q
zqGs~i@d5mC0}6_<O3jrGTZCcO-TJB+7Rhu@6RMM0O<Sg`@bu)SOc#)5dwqolPQCf{
z2#jUMq*`Nq-HsE*6}l+w<$?T)5Iv&CBGfSzXSIT+8I50{r~Zxp1D+GAzzWZI$xXY5
zIpPa({Z&|fP4e-ZV%mNES|k0GgeOsh8cp)2=>9u0>)eEc#esB-=rFE{{A4ZXOiw5}
zwn2Uz3(DPQ)39dsuHBp4q?8KOk90S_nlP}omLb2;ckB~3(qp*kiEv{xC)|5EI-{&>
zh#^whnw=K^@=RY~3>mt}k{Th)1+8$)uhBdtc_H&&>Z=#uk1M}nkYzi-!I{P%_N*)&
z9);^`ie*VYKe^NOvCmq|i-lm{4Q+O*fWz7&NOiYel1%AnPb1h<wodkgoW>$iYT=?^
zn{d-)v;*z1il<^KR>YU1rWxK3+|OIk2o-L$5)Z5qmOEOm?Vo;6CX)QS?2nc$mxjtx
z>Ue||2<<Yq{&Y2^q%6Raf#<VdjN*M|HpuCBC~i7+{7r9%Oz6^jzaW#{Ux_I>^WKa&
znowiNSq$1yIcHb$r3I$yO<Ub9KL$+cb)Suj(g!}m1(V8wi+z|rNe+W8l}k9yQQqS7
z?E5T?mI^N)y1BHrzg)Aq^jGz{B@{LY!OgIF7nLz9ahTF1k>b=F>G@+YJ3=SQp1vS@
z%G`O<R?Ib*a9Z;LPUqAQx;xXh6UM*RSXqF0>I#8}>_z4&?i}QKMse;hjjB`iYgnQe
zM6)k~jIYx7WjUc)OIq)IbW9{+h6&QGIB=%uk_$1lKK4?aS|SUd_K5x_&98)6(v9cW
z&_LHBqRc?8sEE*IzK9Qw)RJuS{`SkY8n0Im=mmIWxl7acc07SG5h`}pBTbCqX+K?0
z#&u4G3P!D4!KZUsKl}{ry<DYM)L*rzQHL$^phNV%yZ&-kUX<c|I~EOHAKLU~QF&m4
zL!I-#+Ft*L*$C|ZcczSA@)IZF$i4YYZ%eLt&n1Rrg|dOeqYST8$@njL{!L0!zbSK_
z(+lyud!1Imo5Vj7d$pV9R^uBM?7E>VigcspXjrm8LNwg(>;LvPp>}Aup|b-l8lRI(
zArmqyYV|fF?IS|fVcvj7X9|kOang*W1FYiWY;kP&mJdaG6EoY7jn$e%W=2Hg@}F87
znZ$9FF=C`w>|t&XW1cNm?<h?hC59y%57d89eJ3W$d?6Q86@NJi;P(6BCL2IaUG}lP
z3u!Ehx6zW}|B7Pt=RmcRr$5(onQcGKE#&+C23|1xtrF&Dkf7pn_XMYNwruM;U!VG=
zxy6AJC&mS!xHeROMEK1!?^daxMz%p)>~g~?IS+4MM^pqi)jXJ|Y6st-*%98vzr9Bn
zFQg`Kagg~|bX+?}^EdP4K9AgEOC7cnV)2NGu%h{xO(vO}lshlHg#_*6<(a;fg*D?V
zWETrYOaj7sAvDLYAz3SlrJm!2i;z%7?AAcN99;26^)lMZ*Yzp&jPKHpYkUVUYiJVf
zf=JU7Q_N}StRpBxsu#+PuexI~&V{WE;`h)t>fyr`9Q{@c4Kuak^}u4=BNF)<e66wg
zSn6{L!Yl@<Nb1ASbX51!Dn;UT1?QvWJeSNQu^VIrMa9r}3^dZx402dQ|A~_9&Nq`&
z<8leDmCDolg5#PwE71>*Qd6>1H5E^Ei8^h4K<M_e95{Yyikq^W<CXU(XBy3H21aVs
zT@O#j-lL`8yM~1<R|wiThMg{kbmxGlDvI3aRuFr=E*(Kg=QoL}a!l<*c;_f^uU77i
z3N?HY>_o~K?&ljp=L(HbxqKjvL+FAW!fDxY=WybY8k+Ah+!g&xI`!{72fD-txXxv;
z4+KSb4M2(2&DB$znHijl$Tr_2v*Z?MOQFX%wXFnAMsA7aV3?4)w{Kr9d8A-5C*@UJ
ze?1ark|ri1lHk=|v+YxOZ4H}@_K0)>oL{)bf9`yy8Bi!~rafJJ`q0tJk&#7*m@zC7
zX=Kxp4w=tL=1kLI5eokr)W@Y3x24VUL}Ox3YE4?1&anB~XM`Z&$tjC!q*5%1-@qoE
zA@RV}$rkObIO`-7u;Eb4{sOR{4`vX!*HD4YnqwJ1Ug}$g=wSUQp*%P3H7D&2Tda$a
zHWkL4Jc#*&Ypdohb`NiRP9r!786}uq3}VNInV65aV@Z?}{`+$@fwMNF>z2AqJ<;JV
zMp2w)dHz}Td$t<gMrZxT^HFbxA3<f<e3E?VZkl$whU^rBByj(qkB+PyYQz3oZfGVn
zbbN9!A6}e!wE;F$g`yDau4ytRusp{OhI<T1T}DQJZYfFPMlu4hyA&_~H`EEO4qa%C
zMjus;=16iG;h-o8gy;<v3t%(FLNHNZe&-o7thRUu!^WPke3>}5hmy-@HUkIz&Q#(#
zJO#BDjW`DjjR3=#B)TJDHQ)y(PkK#I8hl)E3X|VRVTe?0lO)Y#lWx-(#fpvU>CqP%
zMPo*du`NK*Su~o+wjpsADsPZTPngk?rKgX=Fdigw^U27>GC&iUF&`}?lj`bnn8}HI
zz~9G^;tf3PNc{?oa+{I=bI*LDtx;rln_-0b?9UP@N|N&KC)iA-{K#aiUv6<aLH38S
zbWo@fb<n=P(4vxwe9ybKCrHWUyV+agh6@@wq>VJm8EEB2>mOcw5heyIHO5)c2T%(-
zy~`*piIEGpS@Iy?Kj$HP5I2cA2)#KYV~%vfRj5m1HvmpnLGgR>8N;lDs`r*}v|mMT
zNk`dXv>IP>inwyQUQID@xL>Cey{grE*^vkngnI_4VjboFh7|n_vmW-tTCy+kvAk)+
z3NQPfd8vdW>pImp-@N)KlqzCSjVFnwqIl%<QHQ^MN7g;iOy#6h4Ya-$!7aMyPcbHU
z1oJRB-}}AGqee+X)%aBJTllx=k*<Gkd|-fBl{1}#I}N#<RT=b;>|<Cl7-Mk67kO8!
zQMQ_7ANXAr{4<^;M?#dd+a($YP|XJO;NT3Q+kOAZL)<4zZi|aO2QO2%8mm102>jY@
zbXd*aV&0{Fz9Y}`fb%CxK^5fgQMvl9S=Dd7(D8LMftu6XEI<9R$1XTy#)Oxv$Kc4!
zjWfOG98;QD@oM*~C0asL=ueRd4U7GshMkT9&(+JFjEtrrs{<O;QpWW&H`%l>c}eJ_
z&|_j-P+RZqyQJ`{pNJWUrk2OXT(|cwiR8A!NQKR1;Bolz!3HGXH%x%Z)MzOLX8V%C
z@KcCjk24*DweRzcKoSKv&3)~x!|c?DbzL9B5gM{IBj4D0*uN361?~y&rhnrNZyDdU
z|DCl8sCQ;*Q!p()VgKZA;QkH?Y+3z%;I*4y>gZxs_`Q1>7WX~VgR?U^3%Z%!&9tAP
z-C=d1vrkLls8>C}!Uiy1E#`K5n6w&F(j485{Z{J(&Pgj8c;hMc%0##Ia0!Yeo}fAF
z@<yfZ`xZWxPmvHxiNnM$q(63{%JctN59~f`sjx-bxRr|)!<f5Tme|?=nYX+tK7T~#
zEnLNN1SxF?1CM$KHuSq&b>Qhy_E-(;r_slxBO{b(&qYbv@P}8?8?LXxulYXaQZ`0j
z4v{c8v=0j1_;OMAMV>HXS*oPH927V=Gs3x`8ACIceExzc1V6qYT^gxffrO97bTl|O
zuR*MY1ZO<&1=~W5BEKgi8i$Fiu|>K9BrzKJwh~SZSs<$PK%A(uwAO=#r0(xzB@?Q)
zc*RTJmK$7oRB!uDI9ZZf1vH-*J}sKEM-Wudd1SV3ziaPIk~>!z5lO2^qjfM!z!y*f
zyL@5$G8=x-ZtRd5Kgh3a?A2Jgcu#rhWJ0Q`$mkXdA+TW?o~UWrk)c1$OP2po%yl4D
zsmE~J@X(=iviw;IzgSRnZZ{ke%XMtz<w00l$<jqDhG4yj2IGgVFe3Z>0#{l$#OxxP
z&Mb`1h-#FY$3Dw-4XZIEes9iJe9pWTJOPzuYrWla7wnWJFkWcn7daAA6<1rZCF`Kw
zYOmlbSVh_K&J5^3X1ji}45{y!91lJv<oYmY$r3gQr{B6X++0-#zW*^ie!s5c*xg-{
z7l?|2YBm;-G|<7E+@ZWP?jX#o4VDzXLls%H%6xY2=Th;oW#0a*18&p>duTT*T}8?I
zQ0}OV|Mv9B78mZGh6<v)(4YImBPR=d>xD1%MLdU+2N0bLVitJ5WkxhXWJ-Hm%<SB8
z_adX(@F>eZYa!+;7VY^iQz7S1F4%z)wU{{*w*8AM(SzR=(QD%*rwPoGw&eWH^}F_&
zx`kQGKD;i#OWud<W}lR~Lx}|~mowO4SOfK?wzhN#AtmlpUj;Vwb&t)1v=bBDHfU(t
zshhcfgrHe0cLkldMILXjH+suB{c0fGPgxjXvhPB7?@8T)J)T$?z*H48MN@PEBwS1%
zXw>$>G?>jF`{IPb*U0O+x2_S_@~w8xocjxT#HcJ)Wsc69@374+U#_9R?5j87UsE4_
zLqvPs<3XL#W&IGIk_Hwn&eOPvB+V<!9-3{jOIP*n@z=;A5vZ&LaMOq)#4mdU$RAon
zk^{$lf`oTGq>kVz=!SV6)fHI)zIL_${<`5hHQ)J(D;ar+>UbGaINF$db4wz$5+$tD
zQdH`)w;fs%vh7g$h-YHfFz0Of`xfNCt0^^b^+2QfMeK1JLeRp8AT^D}HdcR(#*Om5
zFx^t1mSQ&ZLSfRi<%9rxsV9f&vq(Yqi+BShbDGh~HtRDDI>#)jR9F33k;(--Ki{&G
z{NSvyw8|FRmkum-<(U9Z_S9F=X0Hvu{JBU)xnD`9)E*M`aHzdXOTD~<u*#O)(?xov
zn@xz8R5-r$AyWI=dW2Vf^5HTn^r<RRoH?FIud-^&2aLw6^Qo-6{{XIKdebK8(0pG6
zr44`YVKp!7j3Uep5qG|AqPSU7cmGUe5AuKTI_EG~C9|S;{SoK<ndHaQd1Fewh2W=g
z<qqncC)12G@|$(5kT-QNF0wX*6U^f7E;;QChxVH^_YO_-Xh*I7x^Zf4Qwfp5zd;_W
zDI(n={(*+t3N+5ka5O*NVnMO_Ja=cddh1QaWHX}h$68X$0#&q>sU2W{OUsyu7;~7;
z67_`H=bl;IKA+mjN|u&FIyBK4r4+gm#eOol=+7JycY(P70Nf<&H$#@9=2W&JyY{lR
zdV<XI()dK7Fvp;FF>^v9*QNl8tPK}{sVI#|;U!b59#dNaEf?*ts#jBt$oW2{gm_V=
zl04zHI8#i!Vl$|Hg9uw_<VQa{ZUc=GRc>Zw`XAh9^N0k>qc(>3-}B`%OGfoM(6;YL
ze$TBZ_r2!=D9-$v4S~tz<CHoGN32h$g@{&j429p-KhV(KMO8~V2_t3e_*LhFT&JXK
zkl3_S{^+8CBkLWQFG<FsuT<i7KSe9ji@Tyww)^wBFO$K9Y9c>r7R+|T=F#FdQxlW6
z+#;7n;@6A=WHQVQINhS5H{9jeBpjE~7DLlY9b0yxxZ{wkO=}UCNE4ZS9h>I~s3IL+
zNuS<=2LYm)f1-nBfhFLWxMRLceN)+A%NK20C!j+sceIh(bhEXaooq&y#TB8t)izVJ
z<!(db9emeV%xbJqx89{kz^LWd8+j{}e`<V;(dV9r?>>0wSz=@*{_*}Rmveio{zB)v
z7z&}<)$ktx@#%~QWqUhXRYsJs8HkE&gR`p;t25`w9d+rh4lB#CFC+I6-KS*x#}G=j
zaFd0F9=A_HR(dM#GvZp<yCU;R#W%C(JuZkg)JRpw!6YFzHb2!NALdtMvG&Gh&oM<-
z*eu9~pVH;$c`=Cg<=%(*fDl|cuS~ilxV0NOxlUrEQP87eqoHzx8(ue9TYa_PX31`4
z;JUs5=A1PHvR5G8{5AX*@16UFp5Z=4Z3<r>ynUr$OnDS<*dO$yEf9_HNpby3TU&Fk
zO(;i%n@1r#nZ*ArDL;)k|04-Tk7`aq7Q2-uv(gV5{&pn*IH^>t=Ar?Z`}9x}O90ok
z0teoPNPlB911(|1sR@*0giAYYAqwL}9V-rL5o{AtV<R75h^@<kR-o!?)=!{g3t(xc
zw{SNaSn$wDOKEA~ywKvs)%RNfhWbI?y8d9nnPT%fnWEUAHHxBqIMc>T4l@k=7aw!o
zbd9E2P$dD8q+ip|#}o+yqL@f^b0<{wXU`2{UcZQktx^Uo7E5E@KN8j5m4CPYu&lJ3
zJ%a6L{-o_P)uovnOj|d55&7Dc3R=+URi32&&4kQL=a-3xZKX!7;Bh$v{fwxoqCHgF
zPz;3JI$Q6m8nkf-S>;$f2wtry?sV^+o_d+^N4Y7je2XOe{5As>BX(e|wMwv`YJeq-
zV}v>c&S<86$Z&iYZ*E4k3(da|b{BEeyQlJKeg19Nh&QCm90v@;HKkIU%1;>l3Oo}Z
zF!MhVJ7#E&`*Umh^9ycp)px}_y9D+MiQn(Jp73`xX8j+ksJm9@J7;JSzg~v!Qul!*
zX1w!6TfDAbsh|pws$jWXvL8p_k7wF!N|C?IcYWJSu>a7z2wjZ{-a9w+yvO{dIeREl
zV5cVOh}8u2Tg;dFBH)6q&eP^5_$fkeOYrX^nPhLgd>1KEX>IXa1b@!CIv)KxPvi+8
zf-|W`JP23zl%9p^xK~GX7*P;Wlu7E7p@VZm_sf~imVLe80seB7?C2lW*RNsM`18Ga
zGd8PDYVksIoLs6AE@%xh$TIYT=SLK4^g{&K`bLe+!T`rEu7Uyi(BEVGdr^jVo8Y=&
zp#6FjgPFp)E=h`JE;n6FF=ODrR|>?Kl(3B{GxC|jE6yDU`=vO537#5l?QWaFm@B?M
z=kLNufBb4KkcFiLQi%Q7gl+k*z&m{6V-8(|0^uJHT;wku$Ial&!H2b-5S(wwZL*Y*
zYrnzeYIHAQR7I5!+lnD8;iVpV>$7RzR=C$fM$p>%K`P;|dab6UN3Y?A#N#r1m8gd_
zr(cKtFtL`DJ_h=v@c#e;uKk9@DT$FZk;we9uIm+umoL?S0235HGR=r;YW_coQXD4=
zFBoNOroqy)3{07J1uOH#QvVySB=CQ2JpA7q5&z?LB@+ssq`-kfGy(qS{2d6$tz;@X
z*NAdK6WmVE0S1(Uh>!9)^+fXa^6;ey!NSEZ(_mrkD0Z2-OB6%Oh&ZqUXrFI^3B=IQ
zQl@BY+ni5sgD8JiI7-jNRl!qpeevHPVJzk2rG=xxu%hGm5v+V*e5tu712xK0yW>K`
zyQ=xvVZi@0iT~dp{y+Z}RunGSJ%Ay?t?-(!q2@>Pr%zs7W@CqMYZ|$3_cCubMBdvQ
zhwrBTi3Gw}X(u;R6jwyW=53!XQiLh6WbSMHOUS{YgCF;DS$1xxQbhNIzOeT!GCH`m
zb8ViVK_<lKnd?}fjYX7%3ue7<j9xj<TSm(&R!#+9#{FZmTDQUxH5FDx;{F=J?h7Tp
zu1Y+78MzpzSJtptzO=w}bkK^k&!ZE9orI|FT*_3=a<k9+c4=LO*e9UV5qryaXg&U?
zl+JC$(@W+oC&NcNw=lzexwed&9WJZqbM-aR<6f4IE!+4t?pLYU*%jLT5}-=te*m@}
zw&M-A60$grgxgpB8p-Cw#p6B(y#*UhqB+YK?TdlVwZZfwOqOq(PYt7atgvMXT!Isj
z`e0|rGL1?kvkcKlZ@O$bpQ>JiaY^{)S+QiplBtJ2LOS|d+@$Ag{5r=TItcFu`VVp1
zj`nXFdY;WC<aWFzHZ)jcse2)34m>{@ar;3aw<qad&ZWkEW}&2OfPP5(g9h@lv_-KR
zLmT;B7ckFDipz<uX`veZKha)sG0<W_DQ-|c4EDkCf)%H3yQKh$T3PL%?JgVN?h$=t
zj(_Lou9sieHNKKD6<GRNK#~_V&xRmmi?aof-0#ng_T<+BaLAX^EhB#Atk5lOf!DLz
z;VwC1^H?Ct-Mgk7n`>P)`SJEUJ>cfajotd5`oYL-#Fs3RAx_U|u?U8JUy@GveUog@
z^@o4-*GiVIL2jZIDZQ^>L?Wh$5~=c$hdm)lNj)toBVDpi50=&Gdx5tssn_}2!YPW9
zViAlUegucDR*DSi?9^EaJ|+PXk_c`}2Cew$Ra*(lzg#)7a~Xr=j0uxW`oRwkn-QFS
zbn%~zgNtET71m*Ji<jpI%8wcnQ+}^e)l3;vr#)r+uYYSS)84AJjke;fMLGR=d1hz`
z7Wbvm%Us`n;-upqJv2A1$w1jv8MIqu2;CO{acg+;m8&Pd0+`3}A6oGz{E-gYD^mVB
zi$S9`F={HB`J;pPWy^Xv$5m&cT!SA4*D(%-KiS!9DU-NG0^qWDcN$a(x2|mUOG>pG
zSf~s~@Q9&bKEd@f+!e3dTy|k(h7{WJ_B$P-8`P#hQz*yivfS<2#}oKqw=KrbLWe;9
z<~&2f0_EhE8bm!@!KFbcMvDM<LXhN{nW@cH8h>h^;;{5sw(1(bq2}MfnkmIsRys0)
z52rTf6kH8qkApJ_D^#Kh8%_>xT~R!(_>g@65QOav&Ae!yza^-3QKWEWDE)?yTS#lP
z2?HAqz*2rOEtmD9gskdo`k@EwLiQ5ck%HnD>Z)4yY=RD*kQ=PF_JgH=<V_*f>b!@_
z{e3SsD~q%`K^tVcBkq$upm<5-suiC;N9G`~F>t|=Eg&={D!`0Y(b3*Vs`WU)_pv)*
zDkJxz+{FP<D7Bw5(oIXWN8VR%r4WB#jW9iAIZkN^ef-o*@4UZ-jyK`<v7(Uge7|Ur
zmfLLZ1L70yOtHtd%)3n5ZG@9##fM$up4#Dmx$7*K&e9cH^y8X^%SO$<*pXRN9M*9Y
zNpjST-{=-c3Ok1l$3SOB*!u{z&&{)%L5xVOQk~Ok2{=n?pk}BP{)G*q{1vxw;j^)>
zP)HrAZAP<?zEFBdtrCeEO*>ccmTAR5GV;xU3R@nD6Wu{pAwf^6*?(={nQH&+V>~bJ
z^Jw=HM`lJv+w%x<8N9MDdxB&Oz<ev|?M=zwxLi%NL2~?GsHCe{7j)o4<0VJySTh<_
z&2>ZP(Xlp}S@_gzeOvruhg~i<W<lXYZIiO6Cl^A1-o>lNBiffW*GO5gp$1c`j5``#
zg=n3!nEMEBLTXbafgTU>_}7qV+B2F{p={7<><UJM=6Y<m2ZyQbuuftN!R*ayjpQSl
zF(BgPB1AgHB76HqRv#zSK|hgD3b%PzwLrgcaf2yNcPIC0$tf-C^PeBKYTf$YXmb4^
zL{agN!Ksl@<G@$U?F$t6SiW4tlRv2&Un7)RW;zl1LP&<jV2LVjIf1PR*Q>nTfYF+D
z5&Lvkz8ALIYMhU?fd(>R9|w)B_maGk#fvI3o;cWaQA>=OYu+On6xCg(8Od$Cc^0-}
zf|o}8?h6Ju62mg2l9g!rR_KJ_Qe3aR_Eb_9X!XTjgKG1nSm*CLnekuyx0T{TO@NdJ
zLSE=nhIX;a-|;fJqnb?%>kV|L4{`U{B4;|9!DEEaNZT-zo%5uMW0_E@l29qM^z8Xf
z=ZO)uCg6RHTOc<R+0$cPf^poz7&IlI4om%#>4g<JZDK{Swf^KiR5*MMiEvq$ZLMM?
z$oP92V>ao6hjCw9t{{&~b@WPnKT{mj#Ii0`&KiPhcAG|HD}g&+af@A#gc;XH3@MM=
zz1K|M{rxF9VLj$|#fx~Kj33-4)My6Z9S_nVP|hh-X1zL>1@OMrwIx?fVSl|{h4CWz
zOlRiIAmfJ%<rF{~TLu*ONdq{3h9@C=Jzs;x)K(t={%%`uYD=qTk+;==<xl+$@MkAW
zg@I)^5<&lve7#5oam&WofO-20zQW3&oY8b&m^%FTlUd@YMU7SjgI-R}iMj9R@r@Em
z(Rz+Ybho%-u($>#h_-tXecfoz&ro5$zEFMtx^D6U$?{KhwkWEyU8ogKAN<f5Gct1R
z5r}B>BGT@xpBnNzu?EHZ`Ovni-AKJaPA(R7@r)_+@ZRuEhvN3pHHP;JOrVmfS%+OY
z1bt**vhtVNR3(wJCuZqph!D!JK{x~(;4_Q4DcVIveiE~i>DGCP^A)_9?Y7y=ql%1C
zS+D@FW`5|TeUiE6?Q-4b`XJ9+mQwh6vYXT1Hg%6kM46+(a#vSnK!F#f#kfAF5Jy@1
z%OGd&6I1)lb7l&;%zl}nX+cf(B)?(Xzkjh*0$kYQVpK7TgZH}D_JUXI;MlV(4mR?v
zW}VFIHCq;zTO&grJF81ZnWg89G=&SpG?tpQ+e-?C%S-2JpHKzsN3yJ&6@T0}ly;#;
z!}1~@ZkO8>*uXC-4h(dda*=?SaHS}&&ND-9KZt@x@jzPVAF%Kghx;8c$`efSypX%Q
zpuWk0R_doIQBhi1g*l+juW7(fM)(r8ak*TH$A#b9WRY0mv3Y-~YY+|H%S=^!3u9np
zMlWcuW@bx$BMaWdQ9uFThSg1N$C%GFNLe<b@<_gJNMPlDoWWkteQ%L%2G!Niat{K|
z0?xJVaWmFon;Yl{yMd+Rv{+m!i3e736l6SnZ-n#H9GJJGfMOK?jQ1&+4@4kuAR54<
zPm{a$a#>VrT+k2f9q5f~-}v(zm;~rP7<ZYuPX@1wZH5mbG)Oyb#g>z+T})p!MGn9>
zCif5Ji)dCXh|SW6txbNT$dWIOC^w##qJ#TiIL`D59uc~U957AQg`lF}2>j;W2wm0C
z`HfNdZNNjdNO714`(cFvF$;unGE&sm^|jA%t2l1wh>F0;7QUJf{IyOhT3=M15~ogp
z?>+&yc%zQk?ALWwOB87GGxDkT)tQNjLr0#C%B~TH>W`<Z2(C}0vZp~s?27SYHJTS?
zfH4?~HdVhjRG5$O`8I4K1NvBrU0gViBA)UQ0Y_N*yg4ZMMdG9Al2zriWGiPpT^Tq>
zQWKm-(0Z1$OfgvYMP98s=%WiFfd%mKxJ`7089yx%qL+hY439<%FMFaPNr~(*+P`1{
z^)m&)H2C0qsF8xq4X08*mH?@a#(Zj%h&~E>x9g`)C^ffuzZb<qaSxjoG&rWH#(*fX
zfR15|+7H7b?VR!2`G8;(cFe_%rPtK&rRoXH36qHNd!J@8nU5r4jvG@9{qCTV4BH$x
zZppV^u6bHnR+aV{v3d&UZNJ?y!a#9Hh3}kP4%Gm6jp+kqQesZ4D9ux%aWl=g&y3>S
ze$XXdEn;8lZA3>6h8G5KjD&SUeES|)VQ|lO6o?}m3>Qza2+tO(**Quo`fQRXcxkcu
za%3RHvuy;o0VzsMQAffw?tKCDS<XOTYQ><Ch0iOQc?;gvk?%?9j-*k9h8Z2_Q&<Kb
zILgI$6=dC!=yJ=n@I;)BZw|Ww6PfBTqADM1=WVdPQqdsErne!?JHSPUM|2^qhnquN
zA$7Ve>#aoAM0tz%*}~Afn$0Mm!u&Y~ntIpCcfGA)RAt4x%SG7^9is;jBM=#MjhV?P
zI@L{0#U6P2vVSYTLW-i2y+!tiMwPC8IK4%6Ep2ku6Kl3uCaM`$n1gC7+og=&v6WHn
znkfM{!%)uix=+<bpNIkHklckY-|a2HOkHENT$zm|0wv?H)^{xIK4@^89e$*;aT}Eo
zw5RLr9!_$rAtGlC)1y5>zpJARWEGA<qa0R!XB(JyKE*=Rc7IgOLZ`<(UzR#`F2-i&
z^G9yU&W)ujZgICnSv7};A7^z<Vnp_I<Bjowf1}eqUZKfS#y9V?*tVdW*SOyO^sZ<8
z4d@k<Fm>c4x6q14`yxfmIdyWRk+t!$zoC=G1XZ%J$(hFYtne!LR|^pTCrXIlEA7KD
zL9(KN>R!^H=HkxV_2moyMT}xE`e;2YPOp8ZRtq=-@no&9ZfvEFtBr4+Hf&XAh+*sI
ziIQuRvZg;Uldq~_FZ!8?1HMJCM}VV+Hn6v4Pro5<GL9Mk5@4{u8l9MMDxq{d)tJ$D
zli5}w?q`>~m+f2E4NUhlpQcrJOl&Cr9yC&!rqA0p7c)filaRp0LX#oae|^i(^3g)2
z{-MMTqNen^^uV~fjMal}cFb#qFGAN%?&jfU`+K<{2gNkkNDlmO+RBtYqI=hw>}v#B
zG0blJZRREPf;ZL-L4L0+`D~h%N!dIe%;hTS{|W54b;}_`i%{S0tKR@7=(`?RRBFHG
zF-d7~+6NJBQIST_i~Z!?;Jt7w$mV2p*NkIn?B<ST7TBx|jkP+0Qx|D;kSfyt2Qbs;
z|E?OPN>lzBkl29C-k(ZA9lW(u?CGcwJ_%+DGLwcf$j(ytwaMPrYr%Fo#Qf5TTVAnn
zv(&+RV!-0jiOr6^(C51ovpJCwN0563jkgpC8fuZ&$1)L#h>e1@B2z=gP~F;Mw7U9}
zSFP%row6qrvRyWB<@yZ`T~z(}7N&GRX7EX18qfH64pOjXbClb@^#%mah$;zhi-R_x
zf4R);QVZ$l>x-akicq68&9oD>Hew{g7Mq2t@p^(n<^Tjq4|A%>UOrO&O&0p-3M{~o
z#wc9Oeo)=huj!Jv==9fWKWs@+1T`>Fg?Wv#JTHk2$uYjKuFm13VqTC1&rUu+{>u`{
zhgk8at6DaTy6Ij0oi6{aK_&7ZKwwsPx^>4=e_YW1EM!h_<21XZN5W_4i)+i3bNbib
zMa>eO^6VA00zEtX#l^<3MlNUIQZ6&q-u%(J>h=fwva?}>LY9`u>(O_sd~Q8qVQ#RO
z+zt=6ZhU822t*deZUx<!EMkbd^9zpm0_PaCUGR6eYWjq3enxF^M@HxeM18}~A0JXO
zU!9xG_+)L*JG~Wr?TuB4;m!{HeZd+ppXV)Gn?A+^jg0&f3$s9XPOP>~NDdL1c$WCC
z&0!mHW;e17{^#?GBs#;uRZO{#t|-M`Yuz6s%O#iIVtI~gQKQ{sd|v`^<znf;Tj-$w
zgLhS^dZKWt%Np%#0JwUPBAblwm_6`xsLMHCry@>fsb=k<-LNrtL{K**d@}x{Geu(<
zf{}7$&&rlyq)FLcGGRLRC;e6xCdrpW1qy$-r<a9UVCT2HDYpktq0Hy6QS>!cmX>2a
z0x7|Cuq5-i&;2OsC!(7s^76<_7a<7uK>ETCoQCHpm&Ps-XsS7XEz%=iScM5A+6Nga
z@AlxFU5EmIPlMFQOUvO+2VZmRDk{qm1HEej7|9E(fV!1X#NnniODaj>F37iQ>(;*(
zeMpcSV;WFRh6z1R3GJd?>di(C_78$E`b+@c>Sx=nnNh7d!XlBD(n7^Ui)rhX)qj0!
zXg`~f{DyxLYIIdd-gh@VS95->iB%u+u+MLPJOW@SHOk_Yy1tYKG&9j#G$`$pht(v^
z^oA|fcx~mR>&l+l?WlVgj+trq$^E!AzbxDO#{7~5B>2as&9|{sKRqyQ?BMvW_NVT}
z*DT8(4JN%UwnJGn|5}4)UqzAnZk!G`ulL@i8w&F^GJjU#e^xpI6TfM^uBpAUnR40b
z&dUmGYLGfQZ``D5)R@sW^3i@{YN#PNvR`7g^qy~*SX^+*1y92f`obpkU{Rc;fORt6
zu{O1TJp}ZdXCuL)?0EA{@Tgo>wbWqTMhnq$g}9#2$;>-ra@u1p-^fU_VjVf@5Egef
zIYh;~cL<Y8tBf&=R@<)37h2x2v~kKLy6ej>dY621x}ETR+iJWi9iQq6T=ch+H4XD?
zrV$ea+n<&*GN|YhCf{bK6=3qpHZpL33cmiKKCH;>*f;E<^TUw%3wEEfOk>)ie#;%4
zP%qRo_^|=YStQ5#@F%v-9o#EG7+_UHJ66|!yC4a#keCie(JqA-{>b698Z5?Pv$em+
z9lm-L<6e+JZy%93Y7@qf9p>2GOC^+=--{xTddZer90Aq?0($M|Gp;K)UvP|;I{4w2
z)xNR4h0JDL<d>TsKa{>KP3hCsmE~llXA4{S2*lTq&=I-4D@~U814m<d)_+a&UegU~
z6n&KMf^MnY?)VP@^YLwem=Z30=Zi?A_DJ>95|o0TQOVg)<B<6<IapZN?d%{9PE8aB
zQ1|BoothAe59-XiB*E|$JYz-BE@@>@Bfp{Y!}3-PL11faJlW`}TkG+CW9UdTuL}|o
z<7a7_V>dok^mUmej%*t2i<!e-Z8RnHbdQkLly;F!3`Q+9`k|zAep;>K>3u)XP62Xx
zdri7u`DD3%68{$4z^3@=3Y(>tA4o(OE=aqt^;*21GA}l3nC+d%)C=7UkSCpaFW9~i
z#PJMkzpHnImy0$b!enK{ix_SNQ)9ZidKGJ3dF)%EY9zFJ+tq772)Gj)9Yg57q>(Jk
zf290fdX&&cB<dUNl3jNci~Wvlq}6|_VP0E4bh8i_emHIsh0!Sb44a#MdmD;=Kw`l~
zD6iRE1Nb4Ad2fYpG_V`3K!B%bki6JSNPzW5FE<T>B@3$Dh^u10U^QR~Jo}*JdLZRl
z;g`a$+vVk3;BsgS8VSu;k{oStxN7>yDxo9oT71a_$qmLH%D8fFZO8ti^}kqqtDv^t
z@NGAETdcIWy99Ul;_mJm+#L!<3c($M7k6k01Z#13f)p$6?$-Xk{P)?m+4IfpgPg3%
z(Mr}k?|Sd&zAild>L#u)2l<;pkVf&pnKkEy`}~wqOIrT{-em=6p}!1hfB)=7zxvl{
zudNqxZMEq3D-0%iHu?{LfyVTPwUHDwle|WsUZlxwBuL4<;FeRL7^ihCuh<yedMO!s
zigA8h>o@#AoFHd8%2ZHv+m8r^7iQq!e3^qu*7AUUgY0<c{?5N&(EKFuFNxyV{c=wY
z-RZOZ$qk_Y0UT))=#?eDKvojImK%Sk-zmAYZ|KLp_jzEf@81;uj`jQ{+1B_laknmb
z9_#zBE9-)u@#LNrC%2o1{m^xJIrT#P%U4-+jP&1Sk~;<f>p$FlsFMH@R(9YYO0@*)
zq^NphBE`tvIHE(SuDs~{mxv1~LhRG8<=hQ+?%Ts#s)HQ!iflA#GC}j|JMj7YxwGOo
z_xGg^P^H#%$`(LRt@;YfBfd{D`dO(P=yj)?nCVdsz{if}t^H<K{QZ1%OPSB`VmR#z
z^9r!1CFPD<=jRB<h9?+M8*!wpYh9O9KNB*?Ol6#S;qxf*dX-%LZBynWQ@KDW&&oAV
z8{rllVVFxMb|kcU$iCm1KOji;yi({-vBhk$IrWwzdk%}N1l3J~9IGb0G>m7s2!)T#
zodd5L<sxaR&qK4C8vY4&{s$N?k1u+F72`S*_LD=zVzVy<_ni-3iV`5FJx>DQ+(V@!
z!v`w75FP&%H$tvZQ7ub}ED+lc6<@4GMXgdDDCO_b4kDxIl#K0?_4yoJtrGcnaZo2q
zWxVLF?MK_fBq7StNfDW&esL}*E%C|CyW!5q+N~4I&vRPMhu#(<p@}(ZDs2nZ+r7A#
zVLqoA(2Wq6xsvI0veBam!?w?474DDs-&2x3&26*jI*=xnTch&PDO*l4Oc1fk01?Uq
zH@$DB=g!5)wV1&fRmA4u2jTSInqP8bP{5ZrqidUj6^?tDiFqbV4LL244A?!t(&Dj~
zu~AuS-o*!}i(IF&eck8%oae+SI&b0Orb^3pMI#52jj%c=xn}LK&1rLmpb*G<)xWD@
zlq4s{C42{4;hpvh)+~KELJvwJR9Rl3Ag1qdzurRy1il>bV;;99RDNKl4EHa_-g5dX
zO#VF6ECYDznXYc|SYPAW9a$G1{A3Oy!a6${q$zTll_N;C`oEut{~rkrN|06|2!W+S
zrQR=4D;3%fr$Bu1e>=AM|B87^>uEM;ApjYnGQRdnzPsWWzPWeWfn^lHgk^+L-LXP(
z!x2Hx(wYkgF&Cp<s2nL`lMK=%m!YS4o~SIQN~hnJHU{xNYht6ox}Imjs{08EGpzAS
zGc!1jgD4bph*r2@Jw>zBxhS8ueR$|0X1t2pG@k=R7Iqnyq2mo^rWl@8yHF{zL1^RC
z`RpU&<@g{na6<#Cq97iiIJ~5aVEChA;O1@FB$LjW8p5D1L08uFezx<;i-UxBFi>rF
z<t!=lwy@I1F4RT)nm$#5&g00OWrxg+bYoj@e#q9Gm}XPox5RhCE>xXhH(+|iL!9MG
zeQMdSLh+3a;_V)=E|2E%JrOZF4b6UNeoCb*_9gJ!zMstVEmW4Ir(8&3f1Tbzw6u)_
z^u~oGm4#cH**~=OnZG{kx^yKg2d&^#y*}%dD5O~-Cv=hn)P?I#SCN?vdVYrwM?lV8
zev%w#`;B^K*VK*S^mR*;{<*9Sx6)0z{}1r+-E|9B+DyHq5wt>D_i?PbY6k-vq{~&q
z{m{nnWAdVlsv4xfJ5B6sv17cy9`&JB-E)4W8)cyAJzdO4R3HPJNK!x}SJzJ>19Vfg
zX;Ei3)lzIa7@dtq#9bb|IpT71RAS+bl57SYah{K&XqvR&MWwK?s`%3c7S7h?Z9cw*
zOK$ua9a2HdlATy~SKFuCWqd4A=`f=m5uudCvRpr=sD68;h|bcZ3!z7ZY|{VN|0psy
zjrwf*k?DE)b|*V`A?smz-0+Jq#zu!oN%hfUP+}*;uG4r@C6rG!8E3JP{m#{CdwW?Z
zws5CjJITFi=&&j+vMBYWY3Y?AK3yQ$BmKR{tgTN2@E>cAouflU>Qa)NjrND`3FT~D
z)MM4fktoDtU0t6qufZL}sqVzO1<cP+5?S!;a%TnX?m#VfQwaBcEw+2fmp*TDz8kIs
zt{-c~L~(I9I$g)v+9&M&eQGT00<eGVYyF1)^bTd(cq67^`*(p^7x(G_U4oUI0X%Fj
zYm%Y1DidAGvp?8C7~wfmN8q}Cz_2zGvSlB_zEwRY4?jB{HnK-=cebIBFR4NN?Skc;
z$&<lipkQBrV%-<MtVURccNW1>A^sJX1nsPKy8^l<H*M0Sh0un@xTnYU#O8>Ju<`Qc
z*95m$&d}KV?v@6WTEB<7Ogk2@@A_Y7wU>=12FqI$m+#oxD~v&YB4Inu&iH`*lz4Dx
z;!O9Cq&>fs<2SvNMnZI`_AQ;pgw&SfDPFkc-jrOB`&EU^I@gKl2rNM?o5k;9TH8-z
ztX0gd@lz4Q(|DUK_xw}NMflcmA0_>nI`2&3#2BaTc4L>xk!v$mHU5c2YLbHp!*k(-
zdYA6rRMjL2KN9zP*GKn0W6rqK++WZY%v<t-HS4DPkZV7RQz+e|$yR@TK!LltRI~9f
z0Ad!ZvCQ39MVv~5XBzlTKKI0eeT?bSzGmDmXk3IFZ5|Oe<Y`@HtSrC~)=3z#9?cZ)
zmho^FaPCmWy`=35Wsq~*`Cd_%y-VTU`lKf|iUSi#qiOP%Uj0y1_K`QO=~Hm5_}fO&
z!X8=PPk}&B$kcatO?e-@oNWh`N}VHhBnNs)8Q{W7AmJmqeesXz4Y5?yJ(8Q1Of(JF
zGZRwA=2|24)*nC9i1&8vy?|X;-#?H@Q%KjitzvTc6}ID>4O_SIakSLtGB~&wteta0
zrt(x^@>|~er%;w18oQJZ+zvI6N)?Or^@rg~3SeLZ9Yi3T?w`>=`uW7V6UuGapbN*-
z@(-$h0=_(mcn+#IsRJJs#f`R=)H;l`In<?uq;D&`L3H7L4)uJ~DhFqlwOGQlo&!rK
zwN5tEWyM*)&0G{s53-1-IyB<E!qBypXW|tQ$#1)w9ezrlYQB2efcs{&td}$04U&L@
zV{s8_A|uula1HVoNIUCn3AkDLG^pTVm4Ht;8+l^hc;##|ALY4f{AM?Yyx?c%jz5t(
zXk`0GH3kV__)TpAjNjsntr9`iG8m@>Ap?Z*!R?mHQZKm`7Yyyh_&u*X_&Xf4lZu1_
zbPaez!7<yltp#55?t1bTnoj7UXJ_i#M>llei);)Ctl~Ke0xb3-B@-3?76p;9yDZ<K
z>i!EICB7+p-p{W%z2=~QChZJQHB|b+{&xLPR7Ze?!SKC;aR&d8_W_sN?RV7%#X`wP
z(!28D@MW;c&-;Fd=4yt{4M~4ujSxLy<clZrjJxU#?9x;OgN^LHywa5Cnc`6v1<Pqq
z5E$9b6wat(Esy2$E(Pd^%|xHvR~rM^;VZN!23OGbHOvT=4=HrNEy$lSZbp8aLDdZ|
zr+ycvldso4!V0O8Hz|yPhW80RJ=GSo)Ev1(GQAQL4j?XX-wZFNUwDYXBU4isi#a|O
z00Hs}(|nU(nda&Pj}o?X=3|7Zv4V6+fj@Oa#&4^<3-9>S+!#v%h$fckT$;Re`7j?B
zLikl~6eEQ(_f3y2ObgP~s$D3Peg;-60ne+BN2i?KmMNO64=h9_mPqp0EQ166-QJ^7
ze);w{YN!sKi>J)K*o};>pFsHLtAUVsP0N+-2Vmv^rC0S1{vk)2u-6Xj+PiOS9>JQV
zHA^VaACL{lp(WWOb13#krd@D*nAE}Je7%>jbpV4x8~$#ZVbX3c{Q11DJKcmQmH$4E
zA+OcLph8abrJ_;kGuv#Sw<JXTc|jZLzJ4dzi93839zO@c*XcpvHj$24<-Oiis`%1>
zoj=mrA=kBQKT*lVN}pgXe;J>v$(mHbx*#6bx{!-9ic>Qrp$^vNUMp=C*h+S4sv0U!
z8{N_MAeiFuglv3OyLKHS=bF}B1NXNj38a5i)C)y(3a!~ddqcm8Q&Aja*4n)MmO~@N
zz9O|LhJRDf@s3O_@-NNX+X^+GL`*S`y3p!aZzb~2f#DS`<7~mD=Hkw@4h-?TS^Sj&
zQxHY!Gn%01MQ^{RQzv6}v`+8TBcqSdu54B5exE^m6LV8O6WMJUbWcUH56vmj4>iG9
zi-iXx;en#`_l!T>INaP8q*kdq?yA`LqB*$EV3eSx>o>8>IJmMWhRj~y8|YO+-5Kvv
zO@nxS>sJjFr0>J=u2$Ol+x_T@`s&?z7#Hndu|KLR$T7s+vE%1b^c&FB_GCTS>2B@_
z(GfTblsf+NAyVD^j6(S<+J|sSAdL3Az=LL>KfufH;hw+Dw50z0%K>&LpMJrguZ?GJ
zSk~f4zlX~;vryhXT@@)GYsW8t<B<n(g9Wy;PjtDt3o~GRr|irqP-?o-5&WxEjo}b&
z?n!DQ(XZW1(sOwUUM#&oz*00M6$I|*@J`TJJ%V3qpgk6(7kg;{$)X3muEDjvh8+i4
z!+9N`TwabV2jre78gi?tfA9hAJLO2t7m5LV8E?{9tW<K01IGKlqfleiJR4M<{G@yQ
z?7h{<IISLc?uUvh2hHB-%I#fO%E!s97cOgM82T$MkB*q^aAmG$)(#jniDV}P7L#9l
z>hv;Y4ZlD?NO8m2qSXu&OWt08kbq(((2IW6IZ?x$;!c>+D!22Y&4|b+UEt;5aTZuv
zW($s;o~y7LCVw&DyR&vl+gtcXqaIpIv*{5)O=a8>rcn?2eb{s?VE@S<M+98Xp;xU$
z90&4<@6ILBD5=U1S+j20z-Y6NQ?mS7TJDgV3rufkGc<^VxRj(<(pG9ksCgCw<EX($
zTW+|N3m&E_)Tr&NM&~&tMkx-G^;~>->n0bTI?5$G^bN=3FHYfJmHc5-o630+D;t>{
zCt4&)b!i`XfcHggJQK9-u4UJ_^@bf04Mf0W@n$2Q(m`qiVylfBjy*ztmCv-Bm6vy@
z{se`ZNts?IqxN5IBQ#1b^!oK<ZA}!vmGjMk!dJK<X8m&oFbCvtV*GpLf`oTLpRS8C
zy_g-xtW)r^=&e&o^|g6V6on72i{HwIz^qciAnJ!=O5Ab=WKtp~{Blou<|zzifF>Hb
zA3urET_tBX3RUk3M5dc%nfSg;9AWOm??hnTli+T}7!m1<`EuOqpxp>XSu(m4)oS8>
zL=FOQJg66IUDN)DzqF|Xz`<}zQ3HA<jTd%05llI`wo|a+Yq)z-r|@!1wAb5ZLdaR)
zSGGE%S=cNbp3^6Zm1u{akf!|Xvm3(rWt@=qmY<yHi}t5@=rL<;QcaX@m1v4StUXPE
zc}h76KF>5JqKm~lDM-1{{%P>3dNw&*4~g2LTeb0e2MQ1y>4_+sO8FopHm_?7pL2c3
zJz9-K7XoRbb1=n$nlp@J`AmwJT`#|PL?U)|3wT}#j9Jr95cH7vV2et*AKxuR9My!~
z<9A!$G*PT5=CG{4pXll}->_<LH?m$RRA==ueaMSdyYG+Y*N0i<P2WB!uw$steyV+I
zH73Fy8mGd!p&10;=dux{P?mf!w1&!e2jd^xr7qyVj^P@gM91WAyGjUCAgA#bM(N|_
zm8BK-DdcseD3$1bob>7V71_w9J8ez6{a#pW6uG@=(3bgdtiOtmVD{~h)0JI%nFmr<
zel>Z7aqHCxEf&FV$!<Nqcy528)FrP*IdRtNn60iNnmTjlrNpa*$R~aNitSr8%>3?C
z6_Imtp4+-X*LGAJf<K&JCkNYe<!6EmS+n3i7r@WisMWnSm3rbxwItxqJaAL$FDdUL
zV|i&(Fxu40k{8L$VbjwG)=og#HET(Z3>`ap%|_1>Ho@+Bsq@uby~)&-P|8?8{M|t{
z&On~`>nzlIkh`e^gpWM18)<y0L2=e@6*26zcWxR#e6m=8Q&m;q(zfW|`inOzBy?rB
z5#w1}b1TEgN-Os*)s`Av)1;5#EDbN?dgtmTzaMKhOzw*uj=^KHaiTUZecJ@pM#+l4
zoNZ{G2&uH!`J?7pmVnNQVh#9ZJA>*--_12~Fy?w+rc?-}+m<!j#p}%}h>y`X#kB7p
zbsCiez(1)*+dZVspQu1gU_Ez(^lgR2(1#y2l{+(zTsKA7@EpTasQyggpI-Dg6qcle
z+d3Kq)e=nuZG3=4bF)Z!^68E51Q`eY!3FtUg&b8TwJn<@sk5wT5wDHS;+Itni2^6M
zydg|&d|#o(bJCuWAyEP}V(K>K)Sm9%try;g|3k*VOxsN?G6`tcnx~n;2h%^qtrt{Z
zvJH>5l?K`Z6c4T%5bLG~IrHcttFW@>ENy~HB0)WkJr4%Jp^-n~)ZgdGOuibYn#~Zr
zOnm9FTASl&A&e-fA&4e^4_`e?auul;VmbEP3T%~<5eZ8@bg6;+OqJnlQ#~7RC6RGh
zGtTHQU#`PYU<*WbrfDE{ba}tYz*Fe%w)RSi&yqet_4C+|3>Vbv6?_*ropT`FOT>+L
zk@8{78ExPGj1pGDbW(KZ0@<X<{sO7eHl>9|HYCDu3hX0>2X1Kqi&B+4Ow?$cU!zI=
z7)ksRP;s=DN7Tq^^q%b#y7&oyB`h=M$s##KH%&RM5fD=qzEf{%V@t@-4i&aW%zINv
z^=doI*+F4n_cZP98a(B3p(a1_r8y^Z@ym*2j76|{&d0{AAGprxN`{<EEr^zDXjclN
zt`ea`qhdU5k{lpX`cESPf8}Ic^hH^qm|uR{aQt0=&<!%RKR=l6kfhCL=ARt&n|zZ*
zs~#|2?wjRt+GMta+1A*NOj2vSJ_uY}uH{K0Mwztg-fhE<i==BrQ*-aF`kQNHZjq9N
zX~0{pYTpU6vK&2TeU~EpDf)px=GWl#90G_qKR52&|D$TsduC)`?wvoc2b#rV%XoD2
zdJ6B6oRGNyiLtB$v~{;yj8J&H^vj!a>Oo>)Ft~T)%2j`wKWJ=gHh>;whP0AI8fy^-
zZ*(OZi>(<FO{ypX`*)-S!dwdF6zE-j+R1e_SJqaQDX31AIcP;#>v?+XWNBRwgehtX
zPOa8fbHUH>2O=-=CYc%>FRlfSLYMtD4%@!l6B9#u)x)N%cSMv6!kNX9K|3B)KJbT8
zXOMs^!ym**VP)151`379{ts8C>Q7p0Vo8%UFKd@TNA^0VOtrxyIf`VG5|`ytm#1W9
zXUA+DL1M*weox4<{Mw3n_Pt#&NI8=#z}xV;V^xvD%))BF3cA_s7d`trl_L%$;90ke
zTltx(4q3wnbxED!W|h1TTEw0>V_VHhU*%g`BO@WHQl!7zT^Ka9zUZmd*B|v~!DW^z
zy(ynN)&BQn=?}!wpl}*$FK0}rmk~(Kd?_+6$tp=&oCS-<Py|$(|B>bkGu0YC>S+j!
zci3l=$n+XpIX+>0gBh_#uJ83#lS%r<QzJ7$D@LfdYS%sjEID=p_n*`W#B4MD3zDa$
zPt&2p+Rh>989C80ruIYXSge~FMr-eDkUH*b!6VG9T?3u8FdB&eWi5@ly4c34EgVLN
zr3<skvs%a}1MO}qwaHQnSViJsok(4-1j*BpXDi>`Z&U0x^0b1kObD}QN6dwh$kcg)
z7EW~AI$(Hv#LuKREb!X5zY{k1lO30vMN{Dsx_KUwT)<H5V6$Ie>p!q>|HgQc?G8Ku
zyI|bMjOd1*ub<3B>pq|qw038aL~!_h{s3P6V6r~&HreAO=ER6e4nDo!!iF2#*HY($
zSv6eX*ZYymAJORb@`TPKos^qsOs{E8D}PZ5pviLqia7Y!TL|WnSgIvp1cC3#w46*C
zhfWo2lsRGX&jdf#c!F*gJM@2W*>!d8qz%EaIn9gIVQf-9>~kFoSH93)WMRCNB3X6!
z^6(<<>j@6Lm{XtI1}PSQ)H_7^p+D<7+i}?RMpsXfkNJDbR^PKWH~o3JTQ{$o7|wG2
zcAcgVUu2~*hB1bgE;nFMHQZ+y1NsSfN4s&x=R!AXTJ`de0Lv{3Ka4BL6FhKvAiz3v
zwbJ@*-NI{$&Lv4|{!3YP{>KnAV$cEId!=B;Q;PfwAr|(Kxc#GyV2z`g+J!pN$J*NJ
zPI#*8_04F`4pU|<@|{|z{B;DF`cHv~ZB{Z!i8WEA%9xNdD4E?dkjUJCo}>Jq725R7
zPD}j|o4^F{a<i%Ia0T$&r*WatLA&FX;_pDPKR1<+-uP-X6dH)DN1`bT>792igEuCg
zo}{#6c9uKJCBotyQH1tl)LC;E(HXH5@>9)}%t}ef4FntU<xmsyZwaRL%t(9oIWMvn
zKa@00cnF^uhmnMDPW`sGXMzlc3OK)%*|ip$RZ^oecDhn2!`~IF32f;m`7?@Wse18$
zWm$ssFW!-ba;)#=4iPn<J6DOI|DYEwY18u(x*;Q9;t#&eGhRHGJvPpGKO}L?XacTy
zO9|rNI{<UOc^ZTXQHSL=WKAo58RPOpYOB6&RGRxqcqC#fZG88qD6f*g88<RS)IIU4
z3-<4((23lQchokZcdPfdx0+5NC+wJo{C*{BzdMbBNeU5>=v7Lmt`*nD`#Qh-cf5`t
z%&zc5R?KfzZlOWryrnZul+g5l_(r|vG&w0Qi`2ngk<SJd1xm^9qI6w9^I`#{Do<y~
zO{s8vi8OBG4@>C1o7`$oF1J?!rcU0$rvL*PHx9C&XuKakPGl;xAjxo|Jca>CHF)gL
zjb*178{|q437H-Qxc(|mvV^CPx6P%W=A0u`@SdFPR;F^OPU2bFFIv-YNnUFu0$!`)
zi?$j#{sRp8`>jMuWB(x5Az|};(y|msx_hfZ4rdSaT4R3JqX1r7nAAmks5v1;^c265
zoHKpB0E<=ryW+QH;_GBaZcHJ*nO-c|4R@NFRcX<rg~h%L0GDrPh125cbakY#;ytK|
z$<q8ok$Qhx{*HUn@P+Mb154P5=Zz4)DVu%|zNdaytigq%q)6O3-(%S8p+vphkb-iJ
zhEuI%Tnj6|ecCkvN`s-k-t@pP>{Z_`nb7t!4B6e0AO;~5Wd$kLFCCB5C2~b<ygM+0
zINz%=j;uxX&`EB}7PjTPpwGYYLk}9?bUu#PPhR)Br0(8HWF~uG@eUH1gu@hjcYq>V
z_87B+>^c`hRQgr6zveAT(gJ!Y>n*s|wu|uAY{#o6V>Zu1^nI2DA3l8KKkFxda1u70
zuCl)}k9L1(v_cTH9QDPQ263^COWdKg!JPazscrU>yzLU59W$+<CCBM*2`$qH(O-!o
ze5SJGX`a0(-PUHWUP6*~P2T4Vd$o2wWcW4}EJM@&uv`2m8H5|^D%&)ND`u7`iN~3C
zXWIeXppH69HP@s+Ls{dkvMXPsvPo4>Ug8z_s<Um<q;Dp#Rv8&ncf<r|be-EURaBq~
zs<-})PsNWRJ+95aP-Z0IlooopC+(H|TQK2=@N;uH;oG84NYgX4F2pO8TT7{)>GfuW
zuWvWbR^t-^&``hwIZ~I(I3%%|6As7FYnK#h(m9eMleDH7sf@QZFPCU<@V&!qf6MS6
z!jfE`rSXd{lvgS#&$q)jP2wl?qlHm5E6nqdHIF+zEqE?=xzJk?dvTGSKz$*lZ~@b~
zI)M#!Cn=z=k(C1DK$&*hGz@>p+|^4)C{Frz@{_Mgg&P^=0w7*8QA{5Bl2<A!c)S`N
zD{;77VPElcZ2mKR5Z`yD`_Lg4H+Si>_}!K%*2h6)-V<&9^^S=A)Z410(sz+i-n(Lq
zCnE|TP#=fVpn*tQc$jIL6Cph3@4_HAy~Xw8uD3c~qX#Ps^leg@TWAfhFRP9Bj8=1$
zsrSm4+3KepTu;M9-ZrnWmO{`pMJO}M1p+YD{Qu%XNw`5Ye#B<f7(JyTyD4vd?@ER6
z0b6ohq<)T=@&7+2NJzqy2wOWMq=M)yrp!=Rq^c;Y@ffaoE6ru|+2`iHQ@{23mP@1b
zm&IF23UkV_Y?2*-QcsnMp8<fCqim#i10ocy?@Rf7zeU6_AIWhB0W=Pz#O5f~D43Cc
zPohRB$$M{v6Y;?+uB4Bo&N(FCaVug|R5f9Okp>w-p+`8|2N1+&pc|W{*q`EmXk9`V
z%GgMrph~cIK*fH90LdU=&X-SzaeF^q9OQT=m1Hx}!O<N0kwOH~mH~Q`ank>F9=cn{
zG@K{?`+ZKT^C#$I!N%RKg>r51d&qjE%=ZMZGT%!2ih3H}y>|TC%>!{y-Ew=ae#@7o
zx`4|56|6~`w!|~Hu>&_8;YN`>Iaq8*=0@#CyOZXwWtqdO69f8hfi@30GnKsR-yc>4
zQj5OfKn)F1cq#z)H1f{yF4oJ9XQ9oXM70Ecul?^xJdZvxvvfu}K+L4;4SychIVAY5
zjT@ZJLYWETiT8Cn>8ct-l8%|vPlG1QJSDgq<aa+0wI{z1_$-^G<L&T4fzx6=A9t)k
zRm{3QonZ3UTZ@jzFdA<UhE$^TnWch&RbA4C5<2-(m(RfT4M_Hpoy0(H2KU|OV(9O<
zoH*RE^+D5GVc7}x>hV!Jti<0EcR1S!{ipwZJbw7Vu`a^#U1s?2WxMN1u2l;ddLE>o
z89i>&(WN>oBC+Rl0vS<&*bflStNh!BoQUymhFT0rfUMY4%!wvsC!N(3<<G;<_;6#F
zE^AiJSK}+`QLq19QJl=RoT)m!e=9M`CwxZT$ky`sdHXZ2>EDVz73c4gQI{GA|M)i!
zvngqFn?HlFTP!`0MjIX(cP_9+DY#CgDp-V`s(+8{K(KZ2AyT07AEv)z#auyKPx`_(
zAd*fTIP+SzD1|x5nM!eqW}#)|qBJp;s@TR@OFf-&R~TQYg<mvX3z1}&8MbIaco7i2
z+=@W3IttdaeT1OZ_cb}9=V8n{{=Gupt5CRsw&99tBnf%y^OE!xy71>8+Io3-r7@O5
zlEzng)epi?4_J3~%><ztK3wVhe)RGBT`gTi0&SdR2MykX=3Q5+OC@0&u@jPe->yt2
z(xXEh2vEjTAHIvT#;>S>hYBmb-Nl5XBW&QLJ?u9g+&Xxj0363_*nY-G8)`aF6oQRM
z=b?1a3RhD*)&Prcs+uQ=Uhxgxp{FXuItqn6LZb%HEaR!9h9R31ih($5F)H$IJ`X$7
z1C5#!Z~9fyi*_HC(j_^QAfQovigv;e{2!Zup=xvvb9rq)fgeeZ3yB`9p6!#eyjQ5!
ziuEi5s14jVFUZy&V@NjkiL<zNY4m%C=ejU8n!A2kvb&b0PzoYlhxs-U{s;JEc@@~2
zUeu-c9or9~yZXCVl4tHv{J1(mxF|?OEi#SZx1O16Fy{GwCh7iaO~*|uDQ!GEk`4Ky
zRy}d?)@uJ{NoPCw0$XA0dJ&f@e;gX}6FT$vQXzfJju`D1&{o?ubTw&fNUs@OU~N=j
zcGEU5UPG31_MRnT`QV3NgULM~{(u8Rmi77PpF#8Anml>9SFc;oHH<6d1JU!-l}jnD
zSd~vn#qA_$otWgDDdNe?1-@cHy#$l!(KUDv#L_~Y-z}c?V8Rx%Q(*hxOfr4js?>ka
z+dKA3D2uI@v2yQqX5fU#ym*#8{ZQk~;go?|ite5x9SUW-_5i8z<P;x7U2BPF;6W5G
zZrF<((#dc@rq%lWbxgxX`_D;o)ha!wgB!h05r0sGTFaYpofx#Bg;kJQ+3)mKa8+rc
z(-|y5sol^v2r@xZyO){ZJsqUMy2qG#ZmEaMnwgk9p_7K@!&Zp-Z}LNbO_x7XnB}_C
zGwBNcT3mbopV~M94opEn@Ir0~_BJuQ#NyS^?2aG)4fwc=Ds)STKaR>Uh1;f8l3S3G
zcd?sO`>HX@ojp&Dw{L67DWt3+4BEn631cZepe|P@ejkdB9nBwX8pCR4zAa=d5Fg0e
z`~zI?4)P6V0WYo?8DhPDYp*0z9_j9ND?<Tn>e_FWW>3i5x$C*;ltW={UfG1#GJn=n
zJ)G(yyWbsxK1_PkAA}@LEe|PG1-f`5lslE~J(aLgnN6L(1K6umyPs9UoV%sOJvJ*^
z+;6}$oCoCsjFQ6Jkv@UZ$QTcZn`He^3D)cvXQ}f(clxr)Vd}eICnw~Bm>owqEsQDC
z8^Td4sf`HC!Bw`R-}NhNOP<2W$2$h4)y)c{1>BX7(UM5$3z6$5L9P_*(g1JI<s1mt
z!kp50MqV<u^WZoUw^a%BjT^Uhpz>>@lm;$md2D&XC{`Gbs9tbRDa<-Zuz{5k@#9q6
zN%jtbVteB@7VOUaP|}Elz%>XXT4oI>A)q5uentre+>Bp0euG7&Tt>|5`wHAn(IxlP
z-bPmHZXPB+(>7Vn*7QsRU5%1i5pTtA=etqDUtz)}NOS|%7CGL93uXf6`(-!AK1}pU
zn|cmN76%Nx8&w!_rHLbaPx=C8S3-0Rz`Enw**1snPjv=#`Pxl{i(LH>8-=!1C3oQ0
zrytW!g=(;!ZthGOHwsW68xBhkxlWAKvnEYVo(8{|Q^HzOCKX@t<{V~HuAks&PX$Yk
z;76|eN%8N?6h~!fD2ypH4QH>e>37uxD!AFSH7O(=Nx)q%YE8t+@ojVt`3EOLb47kD
z3zYg#C)tyz8D(GhN2=cK)I0GRk(_CX$x;AgazC+iXYAA)rF^^Hg^ND#=PJg#<9~%{
zZ>(v85~LT)um?W{J!@A#RG<#8<mjhxVQdr<<4KJqsR`2S)(KbON#R7_uhB4}h^3pT
zFzynQ5T6-dDpF@C&d`tl9c9(kATQ<WqtO)7bh7=F^7r6K`J!Dx_!<5ojirguO$7el
zkPSe^JUv(5miLgSwE0kloTV+2`bkTv^Ze#akxj!3M&Z<_)G_hN#4BQEL3lZ{S1fh0
z<mO!!TJn|-^IDk(L#I3nO~sS9sU;Uuw{+#8&z=DH`d#hJC@IH1V7}=+W5J$pzknnV
zd`ZPta?GmCk|i^loZZHs=i|T5ZJzOE-v}VV4K5Va4B9VZ_<04xacWpkP@o383F4K#
zS1!kNWrEd{ePrm8!vg>1>d_bDB}bbA?v)DWwTV#~_nJ9k$YJlg{pt!4{1sGQ^=K__
zz$;B1*ZincY#W=*7XsxUYQpoAP5cS<Oe~lox4TbU2`SW>X!s9sx_}I;FHpmj%vawR
z_ck2tZHWCokMDb=@pc&f+xn#P+d<8Ndp@+$io$M?!HFUUkXLYh(o9A1%S}F9pib6z
zq!#@4Xz`n>oI@1L<~)}!e2y}ZxB_i$8NYAG%k!=RAiD4$fI-;{YTDOxfa0pbHIieg
zgY?w?dOZJW;%mZobt<%d8)8j<jIGe=Zk!@W3H`VL;9ggCl0Q=0T_{=B4BRh(-&Fw9
zwNW36+32ud7UF}o1m1UkWeTtE<j3)ABwzR|sZE$vcf35!5Cm3L^*Yj_v(}<Lc$rPr
zpI3{e>QbzC4EeP5k=AVJ!Oum)QWyD`a(#XIFYMA$#`)>2@dsyM+^uc(do;t3piSQz
zZ__jhDG%TWHz^4pFLGSvI>yx1Jyet>a88f))6{VO;$lQFd*;-UAaNdeTpM;PR8PU7
zV!>5DzDXH1tFy(fJOn)g8$mwFpm;f>n}kd#SMo13<aYn^<!MnUXFdD|u<%$GzH118
zxAqA;-oCWUTgOZ4fI}d1*EA0Ai&09&-Bi3StD$Z=nc{@aoNmTju~^FYlOPhcW)g37
zgB8TUGuWwNXQZ0ZY|JCfsWMysSh{`&Ck;6<O{m%?WvGi3Z9b<}2wQKQwAK_;<ul)B
z-=!;j@z?avb$IP}wAJ}K(zHcDWP6vZxg3_x??E#-pa=%WfU@bJH`9nJJgMl7G8#LQ
z)e-NfFk`IfB$IU2Ns=dTxo`#gIiLM6Yjc~0jz~!RMJYr_N?>ztMH$=ul!TpnrIa8r
zXoz<b!0ReReIXxMi82TfwlT2i@)CCvBjC4^=C-wj%XtM9+hEY9G}f!8<iBWlRDIk0
zRMTa<UDQGf8e)+~=|;wnM(O5C5&h?LGs#E$FbN=QKT@+F<WIsDB&k4c9;pc=xvx&?
zs(ceu+R~DCY*sx(spiuPanbJ~G@CprWF=iFRpqc7Ea!{lq4?PsUmKi<O02j-w}#_f
z^1iWhOZQHxM8z*Qg*+j`6n--1-Nb0sSIw69^CT!}PCZJ(b5gGB7NeXwrDOBbxy=gi
zY#pv+#HA)W!Mtpx1`_nEK(6@`SRV4u%?~1@f~S-a;(%VL#0V+Hyii|}T9dA_X8S$h
zkUb{lowOjf!dQXH1!V|>@%?37+%%^@?8V3W;0)`4S<uMK2f39`TDt}QZOFPA(e{O4
z9P<>^*r$b3y0h<c;vIE#*tcs4MN*GER70>O_QkV3V)QQ-OLPC2eVy?BA&p*wTi~{3
zFWD!$pkk8i!tq7OvToT<9L?u!t5!w-rXJJPtw>PWbt5Yzoh3oyjijKK+&rheAt9ki
zbgm8ZTZv4<f<Q`0^1C4kbHKDRc<2rm?M1w6`>s;FZj?6;@RV$Rha*m0=i8x>xY=w$
zd%SLBxanfL=pSdks;7_eD-)OqyTWK;!D;sos<PxUJB%$v79FiEtNotIkP6*;`fV-!
zz<=Y!Ngw<lsJEeF;@f12{7H|ma3*Sg??yj222L8O;VR>qxl_pTCMz%SZX24f2mP3t
z)cP_gXq?z7OOEip4j=&f6Q+a*@WrM35S0%*$w8LQQK6fG4gR(Y+~XT2PmY5y^dHJq
zl$G6ng8EGa%WIY0mgYxs??~tlMS~XM$CbtNyrte$$`(Qmm>-|uvitlq0rvA6!Sze2
zlXMO*?Z$I;8MM1Im=&OoqO>J$f+VKXe#l6N^%6TQ<Vg(49Lio_u#h$G@b-|f>Fd{X
zm)w8T6rF_hd(Zo@>K%U9Ofqu2n6IB}kS*Uu{_VQa=$bwE`7N;a6nLup(5N!ELs;E$
zjV61XzbFXapShrZau_HrHpg+=0(%#+RD5M|55;$+h5R;YvQqu^exi7oSf8LUjldUs
z1f#k>TG5SeO3}(pJDUZo-15exc|8sH^1j;r!^-Z5Sk%(FB0l?d1DAHnOnG^>fa6eR
z?RHuPH?0R8Y{lzln{<d_Lf7u=&ltp8K(u1+@;!14O|^tPPgurgWI8x=p;Xka6|ZoZ
z;3N6RX##+nt2ed1yd<3mQcYVp%To}QGL#gj+vG^^A_hQ?{!ptb?<{DVexVU9*tA2N
zYJ&-f|FqKTMLdXmrLmR(+`00WUtDH%X?_T0khd^XA(ZXSoFMCPb%`j_!XKx9u2qVE
zn2uK3<Fr;ZQqCvYvN7?PyS8id+Lfp&es1UV8Q%Xr=hYO{&{9uRu)6V1y2CjwggSmR
zlrkdXuTTcQzE;<T_SdU67zNlo!pDe^kJtaES@66iQScC5th}FGZlV8o_vX+UVpI64
z*Dc{eK1jo$Aq{b&qfNUBNiaatu+nUaXx6b<iM1c|_}bR3(_7P&%cU(2>Q9|31^eqH
zc<QULR_#EfxD;ywx69ed8pl41#70f?(>nr2E|g-mIM)0Jjljph4S0Hpi`1Rk(&|Ei
z6NJb%4@p3ZD6^P-YT0kEkx=Jf@wxSj>oi01f*%dlJ`84#R=Z+hGMb`4gB3{$ASU5h
z^B+ndJ;90oEGvoE2&K{eHj(cqA<6|EoAh3xX=8FX^vu?~Tw85f&aj0;Qp;rR7G0QB
z&&`=B=L$RZkN000u9gjyHcu|EYKSmU|DlMpNE^zn{(5UTc6wNx^lHHE`Ayc{vsHi^
z{m}Wx(#71==(_E@0iVgh7D#FC+SAv4$xH$|A9Q%uIO*m{>5RVb8Qibw!{q2o>0(Xb
z_fgK=uJmINCtG=koR<oLsVhPY;(d$`>P~65cXQTIgC)t{IFQ`dXdTV5A|J{ml`UL(
z(It;c;U{f(>}IwgadIeS)bwcu9#A+DgzoHRyN3b&SFfAf?S+Tt=hB{3@z@$knT1G<
z$33%K#><jI=i0`E`DaK@?Gw;DNW?CK4Uq0<_1POzM{)lVNQ}1m(Y5~TpLg$B8{6tQ
zztA)b5Fv<V&(Fgs5w7l{ad7weY1h}}yGyZV-N9OdrQo6+$9-gG+JQFB)ji`@S1}Nw
z{Gvw$)$|^1c+gE-+2^S_X0Xti^fEx&PHleUdp9Xx9ia{%br%^W9#6`t{|yD)@3~Wt
zFeUL$+8Xhw2-CkAw$eGqVNi?nZNY&T?&1C$Y+k_17HDHoI?frw7L;j$Yu~FF<|@05
z3mxg!749z-(0Dg@Tp8=5I~sP39S`hoxBNgc(7Md9qg3L|r1)vS1KH(p{jhP^kM++h
z0=}erMY7N~HZj~uTJ2hCILLTpN=Vh`*hD-VxOh&ERM@jv4UZlWb<^iQ2dZfsl8UD?
z(ho@w6NJ0Ek)H!KU}CzlE#O2}R}^;}<E-qVK|`0d`q4q#UX(`Jn_zfnnSMVV-boVB
z*jixTpfyc3H2-y&elB;*C}f#<;OWeWoz0b)80fiDBbHQ*7_sCC(iQsSA)YPWsZ)s}
z_IpQ?y8&fj2~VvW#hs^J-sSA>%<w?x7cAU_epS;ZdJ_^6H7jr+o4)Z~_jE|{X5*V1
zkrzPxn7hubMUK+J_n~CPsFX&#Dg*dPN6>{(17NlaT5$~L4}+$~xed-6<__#ys6<A4
z`J)Ul3Y~(TBS0dfUwS@co5aR7@Qr>O?d>_>e^<(k2z@r_z{mUvGCOn)D^u-RZw(Ra
z-1(bQO;k5DRUUjVH9fEm3}vp)s~_xfYK+s;J}Br+u{QI*a32cnOP}N_%DAsQL$#da
z@gK$qOet-`Q%9jOire4bw%nBi6;P@vSW0*oLipQVbh*wF77wRbG5ezm#D(aA5hgH%
zfWE&3AJ<7lCq@mxPJA>{Hd1NB2f$NGR`%FW%_F%lwze+AOaXGUS%#b1-VXCy3%S`1
zjjP1y9FY{;qT0?Y-q+L5K;!Zrf`WGzmf20?dskY1gUsJ3SQWrytf)7^&UmdIBOwSw
zi6cDeLKmP{)y48nc4F#AfXiRd7}W!O%!OI?>d5m&9>Mc1N>yt76sa`hO3WvKM@TU;
zS{v_)YV&^e8?IfYhu8+Tq*goK==?b`<(^;iVuv`d^g>tafmE}@qY8?d@J}xZt>oeg
zvN)4!dd-4}+I;ArFZ|f*7PqyB#ZgqSNc!ZUrPj;x%oZgw(`LPYhl3V>XwDsbnW{^3
zqf<W|28ocjh)#PA^8<f_v_i*;y^r-1i;Oi(`5Jhn`8*R8{wHBcZ78RsKy+jXvt0pv
zqpbdtaTV_ms;gUP+rS*ClosR=tv9zPI+pKD-$_Z)U_hB;ZOYXWNHuw--p4j8(;Yyv
zGFZgpo;6X!%*c2*Dhy5k10Yq#2jW^i&7iq+q*RD5%sQ?wYr1Z0-Hb3JN2LVLX8Z|v
z&TYSZ-~RLFSIe8&R%PNFvvgC#J_+Y2D*YPo$7FdZ)z7ZjP~-UU)*xE}fo);~p?`E6
zb(sFA&<M{f)_(on<hCKjTmG;9SEbUC68cZve-V>A{=e)p?(w%kOn%5+StmOg3bczu
z^5Ss_cviy7+DnwcC{_D@MB&A~CdS03Ha;{V<eK>z^7Qj$TLaATYwyU0>J*HiXA%Ai
zSgnBXNsJBX{6IN6;%5i0E2V8yV|Y3991K&Ee`heif3ILE7c$D$_TxW5LsxG5G`m*3
z+CbXWz%wMIPGKhdGtsNCJB+?=H;CQJEX4D>S>MW>!A>Oj3jPBnmG~K6>-;6mG<c?%
zNc`Q-j(sKb1R*u<LoMaWc2V3p@!4<E!v1tq7?k)(`we=K?ff2QcI8!aoLlUlst%Oj
z!TK&s&jsUQ&;Pb=4)@EiGeWN=KdJ@RTfNLH{09itvRbRK%#t4;XQjGNq_X}G;J~y|
z=_)^p`w>|j^wpphkP7>Ue@d;QN(IB%(#CZ2@PyPnAB;y(QPgxg>)>58Ylb?a7#iOR
zNwi$KM3UT2TK%l{*+J`}TtHbf71^CwzUS*Xy!!BWU;3^hFa8rfk*30d=@wgmHdEp4
zdj0|ILMkZ&Dk>DiHGJ5mi(S`;Ll;%(IcfXm@jt-Hd{-SrhL6m|rl1*ZxL)RYaGu=i
zGq85gHezWbpAK`WoQu*Ivz<%jpL{8(!sdn>k*WZbHnr2h5)N8-#dd!BVYp$SPpaxW
zqt)1x9S0BbkMpGe)}=+`p5Fny`U^oJ>EQ6=RNO6o68PxU0+s0u?M3PzlJaW=$|>hL
zp)wyyi~qFFJ54;AHDMWX-%hcfAyPK~u9NGn`N!Kfyw!Mwd-lTx3b%=$M}9@iyO)rN
z%h_%{NAtbebBou=(kM2acU7hye&fUlkCg;A0E=5Q{sW+i8MR9WU)ShXJY(j55Gdg$
ze~;@FwW0bs0sd_mJ|7)B^jR7DHIHfKQ_Xz)KcM}C_%#2wR#^h-78G**__sWvEvj9j
zxW=g3A0NC;kO7r|cOFqTg_+J6Yv#X6FkM-3`U=_pwAWjP2We++;s_lX*U_tPP){J_
zqoaIRl?^<ffiuY2_G*qzS2Fi!8CgSIp>nFN&5f4gLbU)-l@@Y`a?q(Yr{i=BqNsC;
zE5(ec>-?WT|6_-zDHT3abbOy%oUi>6tUAxo{JV?^tU5>K^cMCjlbLVgzF3op;h`LV
zCZG~Uc_=PkjuGTY{Qtyx``^9>QJwoJ)j;FM(q39!b_hyYZr@LVu&|^pYe}ET@t_uy
z%1+|HG5zO*0znjv@U`Z^=#0$eWyJuW@+ol;Qu!p32e}r6`CG3CzP5k)BuzvqU+zBG
zn&|3VT6Q;0IA41i`3xM(m|Gqsj1TB$E)_0L-3Z4WO1Ud0*OJ2c9K<|Hp$6b^6lWG^
z0Zam@5;>J+dj|2}7_;!oJ0gKFT}f_BTOFwhsBbG6y~3E<<`4996yrQF!g$Tyy|jLs
zbtZYInh7S>r&uJkZU=vy>$=f0s*iVd&@;Ve6`5pIT$i6E&adkCLqIs+K0e>{&y^S4
z7KX<7eHHs|@R70VnsL$PD&e7KF=g%8pxVJPM#*-ka-9;IDe_~#MUzUielM%BJn%9D
z_C;>w!kl*-Gad%brGskIU?FIcRhJE^oYBR;aQjsDd@M!cGb*i>A6;6NM!#FK7oWjm
zs{RD@<OX(%!L2gwgBuo4PT%&aO8wElmoF^paX;l!Al0*mFPWapRQ@s^ZEtIp(UvN8
z_if;b4<g7nK5ru|;<h3=9!Io_{t=vKZ=Jy0+%#6|&AzndpzDaUMqK_KnQsjHZ9hR)
zIl+T%dZmy6WjEho^@Qq(orw>+D{Gp>RL%t1$Cs~|$g{iB=nj+Vx6I;UjMV&+wh%s~
zB7oL2GP^Wz1JU0#{Pl!9<7#x7oDetQC+8qL6?Rl;+jZ@9lO=jlGF=%zy8WAzCp+6^
zutRB6|6HKqzT--{fBa^rOa9~E84c=r51Ru8O>fA}ACkw41G%5kr*TH;A%pH63IvPJ
zq>cBk@uu=4%Ll0Ujc>0$gLfC*{KrX$#spGuq^t9G6Gy$;*QBr9xvaN`U2>-MVEjD+
z$pbtmZPTI&bY5|VnbV;q<<#iIP()q4sVBMKbF5{}g_SaQOCy%h&sYTXz&(;ox+O1h
z7sT`h$_Q_H;}D3NAg@HB(A=0m=hzRF5T+BmZ}h*U7ctK(QQ)uJ>=&TODg2+6&_JHD
ztO9|nnL4CoW{*&lH;@|X&A6q7*vW;q@3;K0?;2pzYyQxp=1r>Dt(WwsmU|+tIAGmK
zLk8Q!;(eDW`>mG6Dgn9#{i$N3*j$%R&0&@6-0qWTk_{7eD2v(<eMiy(^!Ojmd`s*P
zUyqvM;%Ua}wIj_Fzmz}5X5$|-|B%sa9u&$2ls|RAM`4h|Q9AO5{Y~$=Zts5M3GM(V
z0%CT2DFTc_G+p|_fp&>X>>YOVW5yTqQ~x1>AAU?n2rb!|X~q!uN{2hKQ>FHTZKf_G
zm+*yYS?u6<0Do_6$W2o^u}qt>fNY`eJ9(wxN^>ZiUwTf|5aIRo6=kO8ms8P**4V@`
zVFJ`K55Q|p4_UyjuK(L62jOYHxh8`9Go;Qhk_DjzrH+K8jnTzQ_20a%a7ur&9#~I`
zv41CYjk2vmbhhw9T|Kw*bjU|~sHeq+8fw^oFKc-BcWG_DoMGza{Uw+~{zJ#ipu8k7
zZ1Y~{Cztc#H2&jP6&1305ItB4?=8^zAg*C<-#>l)ZI%#Vu3jxfMx*&{^5=3P<NeBI
zLoA$c8Lwa3yCEcvTNe0ckEVP)CiRnfZR_F&{1|bsvX#f*`C7;MJ{+7=W@fp)4?SJ<
zU0=g~C854{)?;D5j{Z8t;kF6-AS1JDU7c&XODJ^9Z#}N{B8K%1)veOQ%~?#bf1fVR
z%P~!#R4$dZcQp2UD*RnFH%`xH^l(tl`gbfrPrVhd0FvG_E$i`1lR<jwA4qx(@#EGg
zZdH*yw|w+<^{{J}W$VV=E;J!PLXp!E=@g0^<Ci<C=ESf3vC1OV(lN)LnnZ`{JS_a4
z0&XVb_ksS%=t0{Z$ryiD)M}yiyQzb2!`?)a!AY41)gEJ>u!R%nD0zLaN~+wd#LaUR
z@wtcIpBOJZy<W3%l`is^e@_eZ-|coOT<)tNF@K-?U8<FHju+#3&dSugK{wBLrl|J$
zZR+S+lDZ#~d7ItN8PPyT=;U|dxb!`;skzWWKe;{?E7PZ`?YUrufXc))y_Yd3W@IRw
zR)&x<1%rMEbEA#_aLw7Ddy+H9|L=c*`B&Btk8GwKbL|KG<Ma($Cut!PGthMwH=i?Q
zW;YV)ZPn@q^@pv{<AHNuOoLqSm+!#_*c1cJ*v(^Oys0fa1a6`)6&cFz3?Ol%S~sWA
zIDh%YxJ_|)vzt8i<&c<_)jSe@1)VwHY3z+}=G8HVtH6nN^lp>Q^IES~^xu5jI>GJ*
zrZ)Wk+iQQW7;hLA1$SMsgdghl_!edw0t)V{1xi04*eqtB6Ae(|`a!Lwl@6y%WZVw{
zFHoZ*e>(F203tS|2c7LD)f`>?9+CPWh|kOSO4+-*QAO+3AcsgzN-{cdDvv@ri|FwX
zS0sdcP*DnnYAhw>TguSD7S;Z)?%5vfNveX+ar6DML<|I@n+6BZcJ2wYNJmkcd_ViA
zKPd-I1MC$@!$FpUt;F)=d7{_42`NL{{gkOhJZS*o<ZK`0N)p<9(dlzDH{8!5CFK)n
zlZrFFpy(hCD|cnXcwm4?^mghS56rgidDV%6XIzaphnsigDceu9m+?#EcExciTei7Z
z8s$VxL&oxOJy=NjnJRaTIv{a8sQ~N+o_3aTOYKqQ?`e7d!SHvJL|ETyl}@#+q=hf;
zYNlOA8I3YnBw8vQJcp6LdA2Kb>)Ke-Q>r@9e|@Od>gTjX(^qi_3kqI{bhwVpr-TcH
z+eA-OwhW_X6Npe>EEdoQP;nk8Zz|YcU{VGk;KdD_fvE0pP+o@0S|iF_k_>&2%i%2p
zZx1&26ehtRF$vJ3+IZh=(=nB}q3O4`LdHG=T^vZr)a8^XrV0P>_Y8^5YY~`!Q1N_K
z;FppmHljk|_h`VuP}Tubf=iS7vV{Fw&pK<|XtdF%)RAA{$&@V9UbcW}1Sq;eHRJ{?
zLrsS|XM;F{-03Y#B@vnmWm!WBAcx~@*z8<SDkZboB^m@uyJv&(WG6dqDdCsgkGjsn
zly}sw{To$p^|edujT19tymcK7R)Xg6{I+#}H~H4Moc?~QKBIOEm^ARG>GW20{31>J
zOI#cTn|_49TnkrZPI)+`eqso~FBlY0jXQy$s^ijKSD*;o^_H!8PpZ<6+?KxuTS_O~
zR|2U_bq9d+B#$G-fJ>2iH7>z!F#_=;EZ(GrpoIl^c$iZKKAzHE!kuIRBkgIK+b*~b
zxz5ual@f}0PLA|xi(JTX;ktZk@hV<eQMSlHBL|PN(hyi(ah<xzegmyga{41F8)K}o
zA0x!H@D<)jJmsmG+HzZgdb!bp5~UqFXc({ST_nJV@)t6FvQj{LUN%Fz`0&37JBz3`
z+pcZnE~Nx_DGo(~OL5oW?(XhI3nj&!6eqa5x3~v)cZ#-nk@9?b$N%6TWR%IhR@S<5
zUwfbDar_8Gd>0;Y+{!p_%l#W$2lyeO&X0T0m->FqRE?;|Op9!5zUY_I7>1&2d6Zh3
z+AZ1<1AjFTF}JIJa;03kh^yM(&QJ9Hp*@1mtzg3#{rq7dk=6=_XVkD$d(7`zdctm|
zO)s4#3URBE<1=ou5|2&z*sPZix^6b_<p~z1Sc(`TVe|MabXQTTIY<kay_(9-Dfa~}
zx$|dqsxA=Vq*RC02_mmIUA5%s<j@X&d{pW$-!WIFEZ+N^=PWcalW-&aA3}s)quh{F
zNe&XK)#zWzN-{<e(LuoYX|H01Kfq&b3hRbKY^kzUw7X)7Ico}gHpK`a|Drz+F&1YH
zzbZXd<S=P6Qz0C+)FVH#7V~oEcN1F2Kq^ZVwqbB0%)jTv8fuy_IZnkSvjse~`@}a_
z_Eo(!&X;=#2wo{C>JA(R>5`tL=Z5a-r?eO9p*6RLCwa1->Ov9jtGW6F$48e7GyE;T
z7$H?!h-e!&@F@XpyhL@B5nTu&b99LueCjCFc~yd-G6)`9cyca8I@EDuY?B&SbVB?q
zeK-R;>2H|(=>vCD;J64J@Je7H>x#bK?!$9K&`f&8F7lm_$pOliM{-k&?kG%JZ4s8H
zIW-*0V{&Z6?2Op@bw<;{*a1pmiuep-x2s_osZQ>6H(BUZ%JEmScbcFUrkJn3TG%)a
zu#q~$HSO(I+L*{ENE{AYb{$(47)^~`u65$w3^uWvK2xiHrRXd^e!f9jJ5j7&$UHY(
zzR8AemZLA~j=Q(ZGeGFr!h*#XZ`RWFRkFNeot&GY(NXEcxbG2vFl`r1Kvk_%hV}Zi
z10`Jh=DRShw}m9q+Xb%6r^?AH_LGYSaVl%y(eriyqjly{M`Un<bY!uL64r+KJ1T{M
z@r7Qv+;H|{xMo0+1LDDLshD=))_nT4B!)4-{#?x#hAez4i3cdOE)~dPd|p8Ggnc9}
z#KCjygd%7#<+75X_`_Idl=a`)MckL8K-s}u$jNA8*LwTy(MT#W4^=9;*BWF}{goDK
zthz$T)JvFd0i~N7o%dygQEE6jj04F|Orl*7&47w;?*q#%aDUwO;B`Q!S^MlFusaCV
zH8GEK+H%oY5I@k)xg+LlQD6SJi>AD*79dCyc8ds3Q&y|^CEz0<;${3rS9r$Th@KYL
zW~OFiqeyo9iUb)MTo@wdWz9ZIqkQ}Ci&A%!dJ0(nvprn)*12W2tKxx<zNx2^Cic5?
zHTM~!-SJU%zl+s!Nze}@L)JO%v`IY48^hrx&X&U2O<Id9zC?lNmt?dZjQm01SIJ77
z1MwNfRlGkD)LMpG+Yx?bM<I)|=Zq)Y%vdRHkw`3=3~Am3-qjYp6m_J5M?14Zro17`
zxQ*Zr8l!G!w@0pSH2q#%w5R50eJSX<fZkuj+BJD$%dv9C=l8H+pTso)rOzn8?UB56
zl{~srtF=Hu*gFSl#UStH0-#49F9TMPRbg6AFDTJaUdn9=MNkl<8z4-bUDq_ds77n`
zEwPnju1e|Vi_m$5B;{p(k-wW1_t?Z%TRyw#74A|RX;HGUd6!P2L*^N&!pF1)hic8h
z+l?&MI&mlY7Ga0FknZrNI9kuy4){p$fvgTNh8co$g{u-=p@EZ4tB9^^3sWgSU&fH0
zt|nk06=(4ZhB|vA)|eS*Y+@kiLRQT&VHID8{CS|(sTjvK=D=<D0*6S4usEIgC78&=
z+M?|?I%Pw;EA&jTB5#uCueHiT3fX?#k=8hUad&51Jd27|_OCvjtcVXuhd;jFrV8q4
z!BfRefhBk65EyLIi-OAC8*t)0T_uhyCsvd8b>+nTH(oj}pL|C9w||Mjtd+~lEFW-D
zUq6Wc7OpwGiZ+d$7S!sMvGE<Yb=szZu=_!#Py4QtOesn9KwL}R3Aw(=M0!^@Yl}nE
zc)=fyj>=g_f`|j1$9`D9pG*!M_M^rVEkr;tX1qPuCy|ZeHe;!sJ}Afu(j{89n5#1g
zEeMH<BrFYbD;H^!^i4Zs5_-7MO8i^F>6@N!5iKBSv8x9ZSt_fLFd6y}VbfE)fENu1
zDdo~6wH)nYw$87pwkKimF|zUFow%U3f(H9UN^=aAx6XS<sM>%d33Z0o_R+LpTPVzH
zny;J_E$1X?J3-(Zw;{5aiwDhowc%!<y7lMmUC5nl*chZQuB}b@e~9jwwM7a)#+6#-
zaxs3kJ;wN?cpEL8YvT3sn0vJ9)W2AR*A>k%2ko`y%oadfjjSW_ZY|tPST`~SLhzvu
zri8v5?#Jv>e;cgy9Hv}I$>!kE7*Td&2Q-?|+6Rn5RV^Wm@YE}!(=d^?>5>7iZ&wZ}
zbQ~=G*E;_GNohs6pI^o>M$~45;x_{_fBi$YwRFWU93bT+h_t_(!GINrT<T~^^mm#M
z(uy0`5tl>iM*SZ`sf=6Ujl5nB=4;Hq)mJuyiQ=u4KL->+D>7xP>pSb2V(|R2a1CqS
zj*tg3XniMJE4>l^Zi!2bO$eiE0X3nB>RgWhR<&(rBXJvCu2S);QxyJW6#nBtz0a^C
zl2L7vJ~_y$dDR<)L$CnYeD4Wv(aaM81NPu)E6p4#Rve3l@m0P_YoRLA)C%lQH3iBt
zLEObeXZ8K*Wp>j!^SISEq{~sF^aE?FY>LKgUu<16cINV4%~aUInB{y?Q}(FH?M<2y
zIk-vogC45rVhdVWdfy3H_bf;!-^2D&t6_ZiT2VR^F~;ea&MG(CSCbnx<Mx~w!a64#
zq-69~htvNMxF4!qc!el~wcPz01cH*3Cq0Spkr;@iutlD+T(@@Cp(q~cE(>xKBPINP
zh)rmlfz0UhU#(MR9ye%=Agp^ijq(4S1{71qNNM}-irVPJn&bVd_2!kV_6@!}+w+Ik
ztQ+(Uo2Liqh0IPgS=5D|i_5M;5*zu~3xwO>2@xf|<76Qtvo;d+c>6_FC?K-zqBVAl
zkiCiP5dO>cf-#YRF&Zz7&CqQbfZ(l9*Xe$-2bfKrg1Ql9abcyrR_84|hI{nfdXUA4
z<0>xmkUpZDPgH#On(Xhd#a5~KJOv7I+cK&!44+gH`hb-x#3eb}YYrKjs>Ng@_~(=#
zi&CO_yOb%ZghJzTS2t`EW6+oXu6DcCX+VhLC+@Z}b2gkhV=d-O^!@0I`}aupSvTKr
z><R);%;H@u;+2jM?YtCU5#`;-78LD(`pp|9UyoAc`38OJ_5YOR*bAgKF-9EOQl1Du
z)_-saDYMvIZi}skl?lP=3z8yr0cGK*Ju-VwyNft5MoWxAo&y@?<FbE)T@2O150$N<
zcBZBSGlEzB(|pU73_~Sp86}y|>HIERha3XY^m$@_vqJiy=_SAEEBbTdt*3*;r8$Af
zG{c%9mcD6$Tf<xE1EFxhkwM83ujhQVg5Qn<b|ZWjZ}ibVE?Yn#@u^mvetVweePD3T
z&#w=qY!IwtLq`V7^mTmI`G)sxd*If3g}C<N1#!e0Egx&Qe}Odzf*zfAyYjWSvNUT|
z0Y<_kc0-y0`<1Xjx78EeUk)ufHeG7bL^D#xoRT3AmxS(;2s2W;wwd}*BFkH6P>*UG
zJ-W2C_9Smz%Xd7ktG2@m^zNs6eYzBRi|wVd(}}AfR2dl>XEYDl2#n*p=GY|XwzI;v
ztIKG{!-rZ?S0NWPX%#;xxKWiA<oW2-@~!jQ*xd>1a#-rYVD`iUrb91ERty`bBv5{k
ztiuq#ua)faf$BbWoa#?7fg!eWguDOHg7s>*!N2kT6{d3Is+0}c=6R3J(5`4k0uV%R
zM9Im}A>*!x?V=sko^|?n|FiZOt(R>@yFJzjNy#LvtqY9?d2(X516_p<YBebNR9963
zv8luHT1%Yw^89X@aOp1+hej0cYB@}&LcG_r9E6b}7p|Yl0_u)B7kV03xOTDDTmN#_
zt0YNWtt0-z`+cgwLTzLH)G$a|jxo?cYcDQ-zFPZ+F74sYAE^-<mvnASyn`Y3(Zydw
z?3U)?JIw?{+MZ^wOm3lx;z%4*OmBUxkjIV`nVE9M-F`0#*RisVg5PrG#A;`{zHt6>
z^s1)F+#|!EX*8dKENp3zAxT%-Y06LVCSlytW3X`}>BRK<ht^viKk}Mmf-l1(!|5<>
z<M_s3cfC%U>x)LbpFQq>svG_aoYR~NHkMG2bq>2~gjmG4q(y6OB}m~_;`R@D$4V>?
z3~2>?(xBWlg|WUORBQhAmTY(3vBMkf&RzUM)jw&K?K<<AK-=g=S7wAG<BSq;r={+y
z$GGQthg8K`D3<@ZmCdLskpzs!?vyI@L{u5Gf2Q&9xm73{Z*h+rUK7e<4}D}RIK(-;
zucl!2i=Rb7qGjDSFI9_JPAe+J7zhGg&=<(h2a_YXZO*loz8edRUKnmJkW$3pku!K<
zp$QzO;4GmLE4c<DnqZmTsZ}`o_2qC`n*_DmZUt-%wkf<f8^A9+Ls-NzE-ZiIrCzNQ
zIN$#r>pK13Vn@orzkuR`K&h?GUo1bMcsD4#EjdxL9NSF74nhB`X^89M2Mf-c2K>iF
zcH)!$STI+U);w*f2$&!FR~k`Q=##>U*0_JU)Z}#3|EfVI0qsLsw(VzLEDR`Eu*_Rf
z!N1V^p{Rwx;wk*{D>37}7rr?6%cWlI_+|c`VGW#h9PCziTeA9G2wHN;vHWu@+iIa3
zBD@)-hu&fK3g@q(U;I&G_d6hp^S>UkN59C#FL<b)T%N5sjeo2pp6R75@~-dt+q*BC
zDyx`+Jm2Wn<Guf_KX#Fv=WUcIyKPN)SZv_iV~*5g`9$QQ_gPTy0ddD7lULY!RRSRO
zKZKf0J$KV3pK(`G3Mj}iDa-*ZO#1L!F4?5^fgb^>v=>f!`}WFGtt!&nWRJ1-?5QQu
zya=@kPE*zA;;atx{jKrBMUmf{`P@4gI#B&rhqGd<^H}u_fC}4bE}Vfqfm|XGHh-Zn
zcOH21;gFG+d|1sJ?kwXga-QUe3xU9B!8-P!HX5Ik?S>&2g&?s^@gNXE!}<iyg_%?L
zIVksw+<wIqL;WWiWxA~mh=uxk>4uL-=W&s9ciY(QM*dwS!QX{w3+fUuiuAk^vp(}G
z{N~}UO%fN>Q1<<+WWURP_&YAvkRGt*k7&v-aN_>gGbx3M+>>6qOg%A5?E%lUq*D7l
zd6`+Z=lv4rCxd%htMJC^qxg6PhkvW)IqAWA>?UJ7BaSh8VpoNBa}c7l!9QjEM;&L*
zw6?t(tt<*+F8n4nM&xQ0^3Z$W$l^E+8=_A1`}RNAAkJK<ACYqUj%1ILdI<|D4*DK^
zAvPtPoKz}iz%ybDI9eDD`roc9pQX-?GT)q^%+GzFQ7^nnYCXSgF6vRLmiWDfm#Izs
zwBIgkDb`6bWZBr4i~%XX5plWJV(j5qu|1;;F)1jZ(L26@sH!q?vE#0m7>}{*0``JA
z!<nm7U0!(4RPV~%%Ej$07n5W~<)>}TNQFQ|+pe`<V~w5*_W{pog6WoQJ+XqcqgAwB
zVJt|s+OjXw+~G7vS~SAt*0{@Al)7GYxA81OC6jl@1xZ>ex!OlWV-s-lq~ElsI_2|R
z(sW)NlH@_FAi^8qAWa!92#bR~o)%fbjrAn$4M22v(92DT0HW^k0oI6E#cNp*#{0lQ
z_vl6l)aeHHYj;|5A^qoH09ul$WPs=eL2t?Lj4(Rj=Dgc+go)po$pYr3Bn;8>2|%cJ
z36>5l<YE;&PA*V(b2!wd-@h+|_&d4sV6gzwKLas9EL5zbb6^BNN2xO3LJ)Zh)0w7|
z*z>JATI6CJA`GxO*G+Xw<hf{<ZIrNxIy$Gi1*52FFbM^0LIgEQsN|R&V93N^UY0^6
z@c-|_idl#(rUkJU1mqNcPl7-1&PX!E>X=fE$q_z*BlKK@LSbZ&Woo0^p$_K?PAGs}
zt!=OsF<2eGvtZ>>QJN12Xbr<Dl$K!8Ifya>E9>Gq3fVAK#hXvZFaqhRQc|rbpriPp
zVeYPUm~@!x8AKHce<oyLZ^fm&LJ%5lF_>>V0*zI&1ZWRL0D&H%Km@BqIVzSB2h!dk
z2p^ayVwi~qQEIFZgfstGh@3muS5k^#pF4}VoPFLaa6&`}unHFz*X~>HDqS!U-yD#?
z9ATg7F)nONEH!+jJCJC-RNr{l8mOOe*BfTsb92d|VqA_*C+^f4xX_7nBie147V<Th
zI$Xc{mG{q4Mqc3}a|U@Jn(=z|UzNS(QtGO9NQ?EPdDr)j*Xmi{PZ+1|ZM<^t1K$%&
zrG%8_vB*<gG404uj8cDCxB%u@8y5T7j%EgKnIVUMesmfAz+jyher^25IZL6`<!t|b
z%H=xqaG5%<M59WHe#8$N8u<HE+vxH}RxySmjv%;w9%}5!MatLtSk=C~B4WGuW!0Xn
znA3D0M9t0fD&6U_z_J}HFhL~3DR7LMOH9h#Nc8nUr|aLHUzUW_DLvf?n_|lgRO8cS
zbjFD@4uQH-ZC|2JprHJ0s{Y?tr}J0NYZ`+;5A+$Ztp-Go(G-*3d?;t>t&n%V)NiAR
zyGv=?z+wp*kC(96?XS~Xelh}L*85{(a*Xe#5Y<X@^D`#Db%G>+P1NB@jVk{PD|bwm
z`YxKr%RQ0UQA4KHNqPNS8G3lsQRCyE&%O8?xZKpy$;2&ml4gJ}m{;)qSllV<-__lV
z9Ve4$kdD%Lt%9{YATXQW*E%A9Y3r|hpZAV&+`Z#9fq4c&H8|b{;efREn|PRJbGw6O
zr>|PKUw+i7a-QPw%b4nA>=!Y9%J0N-cJZ%$`5l$e&Of~|sUriIvqYchJL!HRn;A-!
zi{W-s4N}(^3^c3uxE{p>z<fAlKTjzgxqHw0?0gkTOraQdW$#goB$`oY|M}OxW~N@j
zH_-o64r_Wi<}MD_9|C4dzuMn;&W~@DJu21m6V@j(_hfH6+O_O0BgLVt`@Hh8-d{NU
zs8K_<Jbs@DVNDdCKpx#O|2FLmi&)om6Kmac5nh^k?*B$NH+JUY;DqLr@s5$?{b(&U
zQrB$4KKD*|F-~c}E{)ay*~qcn&Xo}Fx;4yuJaIK5Z#?Np%g|g&Mg$*oPQaU|yIDZ8
zAYPSP1CuG66s7b7&$5jzXhQqdQdl#Y0f$u145Fqze|O1W68$Clzf&HC=f_B-pV8_v
z1etxl6tnKO%M=vVHTSoj2Rr-Pd-4{Iui|@}Ts7`(sSK8?&R|zly2%)NY?{_oh0OD8
zQtGQ3NB178AHnQZJLi2XIoB;21IC8!wv1J1aVX>cV5WYVfjCW~qU{_*^F16^+rmiA
znRUNx@~M|8q<9%K2OMmKnLGIP+=<LL&iGWyMc0QeryMrP8_VQyxB8VD8-wC^7x)YC
zR%tn{Lti$p95!!_hG(+maZP4il~vLh(|A%2k0z;G{WX?-I;?q2P92%Tl4>ohfPqw>
zGsr%L*YrZuu*v<qYH*ZV(SXcfVLGOYm;HUOPAO6xU*q?XDM`eM+v<97c^xN%U8^=s
zxCD7w5hBzDv*%e2>CcVQ1?Y8T=#Jp2$6mL;N&SA$oK+_Mp2unbA#iNP@(%%}XpYBh
zuh@bU)b|b2Rm4(J_J}rwYIpZDE7T-nmHghQ-^M?pnCVW`KR5BDnN$l=UH@GP+xrjU
z%gTC-URO*B?>9ly8)kW=_PSSsKhM)NT*v<*SQqT$r?TZSb4n?*T<^b?17|0UY4zHA
zOV=DBQ8MM*p;enVwZGUI-(l7mwZ&9}d{W37#yfPjO?%=7quph6aVA8t)ZpjF!FKXE
z_~K1MJb}9|I7-ooRzeRZZ4&bo@T^J9$Y6O=UMm{*6Zp-u(@*4z^taLx!@uSJJ0Jv`
z*tJA2-LADH&UNR}MQVf>*Gl%omzDUa?e>0c^5<o~*-UV|+!61@6pY>1?S454@2|DV
z+}cH5Dy|ed)~n4M|D@tr^hv93N))TDSWuLlu(6L?j@i}H#Z_s<Do^}@$1g_&M1OmT
zODc&S$8ax9!{s{^XOq)d&fqMBtj5_0<&vp@$G{vu&wVLt5i<_--H#)7?tEYiC*~JJ
z-tN5rxkfz~amALN)%1R+XY8*0(k`Qp-IsN9L%f=Z*@N=9iZE?dx%<OVT0QKJ2r-I5
z{FF%xgY;4xF<wVb@lyS%aXE&B@)aw3F`jR}<N=tBg-{-e*bfAw@xgc^c2d@}<Bs~1
zgevADgvwH-cOeE@!iDIHokrgr;g%0RxR)lr7KkjppNlJ@q}2ehd09a7l*B>@tW0l{
zFs$dw_z_ucGmABl6213(H>nz_grf7C8$HqS2%elg*RkU!ZwP9{;WBvE(dLr8uQZNQ
z45VT^D4aEtui4<cwJufpP&KmpDMQnaUY%FeQ%?(Av3Z#E+1Zd-wTeVyahx(GLN(C4
zAn2VNLfWt$trpmWE$9x)1Tl6eh4GLJ%#V_ukWoprWQlaHYER1K|HzP1H_DVV7?HN;
zSG4BIo{X;O*L~U4IrmCcXq8{4v{({G&cP?GLcFAp5e?Et9jw<GD~r@jWN{R}d)Bhx
z8ph1f$+D$h3PoWj#p%;y>B-Zf4T(5oeecK^La08_=oK0#@b1d2vn(ghTwALtLx|1M
z8eT*X(lI~-Cdy;%7g^rw_T$~I&=@(ds%}P+QI9}uiDp@;*fe`QSZj*Vc=^<o1n{Nw
zkS=L&c(lfpli9rCfh0&R^OUG2@jFEskf__JlPW0Gfi&lN4))1m1eYHirHWt&m7!Uu
zSAk>9axtkysvavshSAehQ!NIms*-0k7sasmQ2y*ZWERwq*<k02;{C`t*5FcFUqkMd
zri#48>kqn|0ety~s@*R2o|w6pNll&txTlB;V{vz~Je&uSalJYAkBgB<rKp1(4X{=E
zj<aZWT}M~Ins)|z93@{|@|Q%-j|48ND8AkocH9^DTTPn1N1tF7{7rVM>kVndo97k=
zLWp9mA?@$$X4x8${eqU#ElNBu&p}F7WJdG8kPlBQWkI@YVluuQ1!7w1G<lXv6+$j_
z6N_#0*hzL&2~2hD#P$5&+WHcvRPrMmp()2+Hv-4vXG_<J4cuy)49wfPRw<5nGa4tR
zZeMC9Ie%s_<QASeCnJON*N;^UqZ_%meg%Uo*`pNf*>fmz$rWqoW|+^|c}I0sMpmuY
z|Mk_<daQk7y{~b#!U^?P2@Y*`eF~MVVW6ST*f2kD9JYN3EHn-ubn`Zeirz{GRj=BY
zI=|o7V@*@Y`f>~vBc~9m?v$oIh|q6&;gq<ia%&}YWXmT?J7PFD+{;l{01$tCOjOe`
zjmW#t_zxk<V&0}Xe}Ih3nnHHE=jRXSZz}Ume9YrypV&S+mB)Lq>I5z6KnkQ8D11Lk
zlrX$@9xM<M-zD3;)?VtiBhKgYZZ#Vi4U=4I)22nT>38awQ83Ty1$6kBMn<c>LNcS(
znI;L-l7ez<w#yM{g6f+AFBUQYaa<$@KZ>@;sts=M5!QtmLq&daNQ)Lj1sjj%ZLUu3
z#Qkv&*g}wuh|vb@2q<zu(vv<wuB`i}go%S{6!1u}xx#Hwd9G))Ehoj8{60GL8m3w@
z#Z>2KaUxdv?5%rfnU<^1WB<9$MOmgN>?gRHsbhNQES&7pP{busTennmd+`V*e%U0e
zVvbcFUEJwk-UaUfL5}XIRnVeWqXAR=C!=znIK;`QOOW|^^RfI1Rid12Zkq<kS#ikP
z_CEx}mj;9T{ZfLdYy2&tS9TTk)=a|Vi<w2g+QW`M)Y>L-an?57Y323pedaMUd@UnR
zTb`sT*|CS(94<~JhKtkgQ{D13HeIy7P&TvT&M4j^k5|25F49|LZGn}4`|t6C;%Y6^
zZ9VvOTCj7RJXgt`X$ES?9VQ<Gt1ijppQ`G#sILMGaR&-UOBG4jbG_9M*a7$DRoXd@
zh<(Mo=n>~?q8<Ct$HMzU3=gI9Cu=H4c}%D`xR6v{sF2cPKT5fz9nhb+TL}{+gTG3r
zskGNBBGs{Ocq)s6GDc;F)rJI9d6bUQU`mwkbWefRWn0CuSHG<jQQ0F3S~yuy6Ga!+
z3^k@O?qI++Tm)cbc`2RNs$DJ&;-<z;Lb+fhb_=S2v9lso9kB2E(B}%3^8*vbD>|ab
zUmd*@9eJXpgkZ=3A+%E5{`-dtbR)kj)_Bj9ta{+)74)zjcn?=`Bjw&#bF&fVATm%@
z(IS+hQ?c?y_hZ`zP*qk8QG(tnl@EpIJMtRxDqmM1c0AUG3OI1-Pvn6KH_1m*6y~d2
zN-2(Z^Y1AuQ+@P<a8Q78pAQldosJLV<%it168E8kUQI4`W5d!K=emITMJub^!Uy1h
zr@F$SU1h41feFl-C3P#E(&D73E^|jeRGPOPqgd`p@wdq$qIALp58TUA@^SoQW@yj~
zFfZ<i%XsW&`|@KuWi(UW)`tyyo3F^e2usF7Rxy?g9VyM3^j(SvZC!{xP?Y;3(J%4F
zRQxCIA{KZ&5$o-Ru2q^AwaWWK*6SSzp2Jc&VCK;SND-+~Tc+u{oJ{87e#bxgF&T!;
z)8A%Up+1?Hu?SanqC?FalVohyF;sE{K@i!2rru7lZz35ON$9Q)tgA(mLl@%D068vR
zV~FVEpL>69h3E$GudKNkS)<fEeN<J<YsV`ob&zqieD{>ah~L}Q84F76v%z<2Nc}N)
zD|n)7g_m&wd@1b<`#!tOKV86?8(;h>?Pc=xw=SaV+NRW9rIB$C8udl=9Wz*+1VzQ>
zSGywBb;mu-_uU|#%xi37>j+KbZeSY2yHHPKV!a9Lorf5kJH1P75xpgVqmzEtyWwoB
zP0W6V`A+tx`LU}(yqye})~PoK;x(SA7<{D<-!~-;J<k&}*wjTMrYdcO7~}oX+JUv2
zMK_FIYcDm6lm7%S{!VW@3)dEiQHxj09{?FT+YFV^6Uu*_`5s+;N4n_jl2m-Da)vD6
z6ml?GA$vxxLl?!w-S~h_jdq96dQJps%_#AC(gttyBkRZd;SZd{va#$L=dziz>~Q+-
z=##d9ix5@!iZobx7|O0D;293b@#vPOIcTN9rGZcb_$)Z#W~$e7l;7Oo&qz_}1ZoeH
zFM7f^m~=J8O=gLAekyCRn|{<7G=W;L?_|BpXWs3o<-OSk5KDCNA;?E>7#d!a-+9KC
zzOb4j+5bWd53pq1Y=u`LNt3pVI~(iTrpok@o?bW;MMz>&1(7$wmB1Pk{@z+&HiPa<
z>~tDuh!_b+J2<}G(T6u$&1<k^Kh{x{IZeF_TwxE#)8PO9p?TtHA1@`bwHvAsiTx)4
zO8=wQIq9R<0~}rUnms2qs$q1>FZ7M;N+9t*{1;inCYPg$4PG3By&HZj-xxt2>=xgt
zozZVD+%jd7;L)g9_=;!P$eQloDoS8j0#G3;Wvo&#7-zoPwTy&5Rk}A82v+CQE-lZ0
z(vHwKSI8;kbi;w-ccF^LkKF<UJTQqkk{PevWp0DCsVB}p-Z${ld|v!Z=lj$wW6f5l
zvwL6bDx%vFSCo#N&jwu{dOeR)jp)hAloU4NLcVe_+FA?7i>XFzxiwxPz<vRy3JiX9
znjnZ&gdbA+p8q!IH@X@7?l1MG5QA|*^ulfcM5RedfttfO{gXbL>1KBZLY3Zk*0~W1
z)79;eIK!-7yJ(>CLE-bF`@0J^d;8P)f2`Ma+8nXJoMtDgqN&l3^h)&6k577m6M#!y
zz+IN-x(6zfy`?4h3l}!)7(A7zH+J5O=ghY3O(_vm8moP?8GB?5mL=FSVrNph7zH^4
zI>06)N4<S@iBCkAgA9=xQYM2YEg)`Ccau~RAi=>mjvCl*G5wDZoOUryfs<WDOcICv
zluP{E6!%BDJFnet6&9>p#d5XmA-X>*JXEQgm<HchO&JjgUn08%*|(~BBXlHFpx=^t
zC`XwR7wj9fVEe}0XxfZ!5iO{VRu~-m;!?eS!YRWZH?v&*h@eMdzD;d(tS8Rb)%A(s
zZ}hn!sX+=I`pR!Tj0VT#rgZED;Zn|FD^5|3&SicAcPEYPK>IDT6xTnaM#L%%=1c(l
z^pjJQtk`>JeEe;)XkH*JQA2g5bT!1VIsYS<qI4a%y0ePZP};=3E7$(|mEsm+#%J@a
zqMF0jJR8yE3aaz=Ypznu>YZ8`<o4Aj9t#Hc0+i6FtS&46vK8gm{0Vf}(SnKG5arV&
z!MXk3U=7yfLux)1jtB;hgCnF?R?@N5ewKhEtTS)O=C`58x$yYwba*{ydQ-KYb!}J)
zzR_C@4_$h@_g?(6n$yZuOEoUKA5Y_Uuf@+=bI2qHph_@{8CZu4BX^iYAWLlmBzo`)
zL<UK~0aj<F7UOXpzhDoU@4A9h1)!0Vx^=ld(%z3(_Jv;T72ZZuK`a~76y-4^1)G#I
zxGM)^><u;0Sx+m%<b0X3n*vj$89V~%8#v(#wvP)9<sv2%hYIe%9C4%t&5Thi<CU1B
z7^XDjm$FLnF7ACp^fu>``4F0lt*SVntLhIAtfBre^5vvGjc<0jEkSOJV)#6Zo=?kF
zyx7!%j5y_yqi2rbM9f{t1G`2<*X4|0mfkGu#ZP{BgICO^Sf+D*zZos^h&O(99FBm@
zyza26`h{G5HGr{xE`Dt=XTbms)>?z3>O%XAM*N#@uj}rA2-t>o4D<V+pOW3)eArAU
zBtlpy^Wqo|Ds^FO4kEn^$2%%r$<zg1LiME<Z40hp2iqeUZ(rHMS}tEwivOXSSR~Vk
zY`ltHo32d-S;|?z29W-9w%gc!jI$g4{-H(kesdE()_Az}Wxao8jZq@K8L8_FEX(*4
z<V<fCs>efjCT;(`{4IoY0h-<OoO_s-ON*fI8FOFA$&NMp0evtGXFvxAcvLNqVt_10
z4Q!LQjb@b?Q&L8bVb<oQcPp4^BVnX2uSxgYqBw~lWPDt=qw&=F4ER@^<;qRxc$NKU
z6)-}AzjQXeE-;I#(LCYVrLFY9FGkFKUELj6ihV9gM7%^&e4I;%y<Tg9WuC4{%=T|*
z4~7u=`Si7FhdLeg<Z2!neC_+)Ou9n%wdY1UpIvakjHUy8rc`)~qdMqlAqoEr&P2`^
zc(cl92(d1FDBcArQnG9ZmVaH6Gvo;uwxvk`{)2q_$@}Jm_>Qy$xW+HeyBTsjB2m_S
z6=GYs7C#>NJ_)p`<pJ!o5(4Z2VvFGg!XNAbUK<|9P#2tQn8nts`@*{vcgob4syWa6
ze9lAWWK_|Mj<fw9>E8#whw%f;uzzti#s%OXA3COII03WhbEurNAvY0!mjd1ICVi)}
z2qLbQZaLn#uQ^vm@6ix@*?Eog<WK&&-u?a$0l9ceVZq;w@6W%l|Bf~p-cZ=zKkl!@
z*76ejdcV!^-_EQ}hQ7AH3@t3fKAq%A=<%)omJl>#=Uq4Mi4O8K5G)|~Rl>jG6!=)J
zpI=)>a<!{d?Sl1h?+(a<@vH6!^WXgQtErU8uxOtexI7{t@hJO8IoHApE;#Dq7fDsr
zm1E7rT%wJ-$m`;hrb&$Rx0lSRm3BOZYP%w1S6C+3=8e*{)A)}jsmG^^#Cq3)6vOb-
z2(X_dy<xcqhi~PVGIix^UA#7b0s1`!ltuUIO@f;*XyHIur6%8UE~mowKYXL1G_9`W
zuo~JItS_a>@qq~iwFo{qv>H9XK9S3KyCf=Pchvb$a`ePMo+>k-+z8QUC$uebYK9cH
zH&hfDB>lA-Jur;qz`rgv@Ls8JMKE<WQw^yoE)G>bdUUnGl{-B2RKIBhBUqbkazACi
zp=GPqKIRrw!VIvYXm}UQ6bWk@-_VlZU2rafo)~xcb65P%AE7i~q}QX_0#x6CeOVK<
z@C2|Hp11CIZLPe<lQSoh#Zs|dEPZ5|iKi~m*HKGD&I%Lmk$s5_vd;8-@25ErfjC{0
zR5k`NHg%)MsV`lJ3tmI7g>O1eeJjo{zG7|+r&<C<G`8^cDtj2Nu&b?g-!Q0La8_Tg
zZP6e%{C~Tg*P2j?^rgn+dw%-UwKFw`3bk+lTjfB<pQiDREHjd>b?+9k&e(Jt;=SW_
zYdCVaYP3=fuFf3&y72&M#`H@F&)U(*3kAw^mNXzLA8U*crwzyXoJ?-H<m(2pZY@6y
zpRwjF={4GUQKMrkU#nynl0Jtv8+|tKMX|W=t0g98?3ya<3Ng!hh9n!x{~TajGh_9`
zYpp6Gnk{ge*x&wO;zBlK6c{HZ=CfahJ%&zNXx|CbZ<g(f|H`Czs*v@xxZxEvr;$Q9
zE!UhBgcZpK>MTo{X*FlVv+NcjH;t;N)c$$^5jX*JeDTCe=on_=`MWUo6bvF5HA^32
z;#rUCE1{hGYZZ<-%q8>yEk`a;_Inpa3jM8;itc2D0{pk*sVp)p3?m&zKzZ}gboi}`
zkgGLvrQn2dQp;j~B-sa#)v)o+C~NjSYr@+<y{v(76DOOW<S-dhax~eiBL)L$xjkIN
zOVQruDA|9m96C14Bn;#E79M=9j1=z+6}yKX<S!yV_yV-dxq=blFg+xK6g4sJ(;A^d
zRa-7py8U!Y2qs11U1#|L(E3!BgE#qE`vHF0eLpl_0*uyDO$owlNw){){d!k851Lbz
zlB2#$N9crq6(M;XPEyJu(UJ}#w{BK~sOI_>&RO2#!I%PJAE<scn0SbvE>7*IQ?mlH
zdlTp+TFCK@koF2{xz6mh6%HgjV`IvZwT^RzfW%NmJO?N`pc88F|1`Cf;HWcfIbbW3
z1JURq$PS{$6s*Y(=LQ3F9-+*@q1EVFR89n|9K>0WPdUivu6P%@ln&4V`{;yV3m{O~
zlcJM%KnCuzkjr=ula{Bb6{_Ku2o=uz?B_64vXH@lkwQx)6*+_tfR>mDEJs}Uq6)Pf
zQL#9`mz4y-0<cOaH<Hh!0IRi}v0&q{gH>@BAdsM08EK!=!g*~*R)=ShZy_p-Nsa}1
z9gLuCmL4=8AvutS@K6e0EFl0u2UM(ll88Voi5CAt1mAKCZHIHoQBB8AxY;;7pfIEa
z0a2bu34%!?@v3Lm>G`4VJ4a(KZ{=^j-~RtH*7<G`N7#q%^TKok%MzW(k*+NCNlB~J
z<h*$qr|nG_?H2i!>^cV}Jn&0xLyL_~V94o~ldiw-YyD!j?Hv8D?9Sk?u?-z`n6L8e
z-yt_03|PlUSBG{Pan>vR@{0X9y@=KA?^IB}r@!wNDnnJuVxahu!5M!Z^6{EDlu(^K
z^fKO`AflC$l2ZR;?Ky6h6Yo^=w}9*u2eBn<S3Z$Z0Iw=+mj1X@jn|N7JcBWA^f6Xr
zx+OzNXf2|k`(G7=tn}-VX>5bI<E?=j@`VMSDA?fATv#mBnS_z|0(6zc9+BUtYtBd4
z48I=i{k_Y|yYy9H?|8dhiPz=yS8raZ2OG^CS9`HpV^>EcFd%tv7bk#~F|M5a5Wh!g
z8?TiPf#cuIjuC{(u<xrR)!St$g+6_)#-{b~G&YKj^`%f_p5ikyl`JGmQKuk+H#h1K
zNST@|)e4z9zQK|Z!}(?DX80>y?QT>aC?VlS-T$_KEGo!VOq_lZ=4abNwJ1pqLe{69
z8=A~YJ7cq*FKRRA$6yRv@NT%!YwiBg*hxZM&%s+yTQuxPjy|lWpwY#k3!C?I<1;y%
zIcAmIO&P&;`O7{iV%J$Sw*F;G_T%IsHQc0ys|Vd`qgNu&XTNSuimN4}Yo?b;%E^i_
zQDKqRX``qYcU}xp`!lK9((K$zFIn@GC%#RpUOY=P#dV$jYct)z<Q>0mWv7z&`<$Iu
zp+Cx|82puPm}4_p5lN*%p>MIyq0UD!4j+)QITW0+ZfG!GRrA-4gK_1B4pc8+Bu@)G
z&3<|ZyE0`il+K{?GRCiflGseTF<Te^)YJU(fBsw?CsF7|?<cBa%|9vLJE#ybjqbE^
zP4u|YI{y8V*M!Z3>Yo#P2(NXi*Gj6lADbxUPM(+-!Ew_;V>##H7~k=mZ?|vx##UtC
zWmch!o@^J@dQ=PhOO$~(Kwr?fAWUY30gQ6{-h?T1G^|$PL&g+i%$KD3Y7!qI+FH>~
z4xdb=k~0xQrITRiAyV64d<G!4O16X!<Zz8rJ^Wi6-^#Sl3vIl?cjcUt2t+^@B1M#l
zO|%Nx@LVF~_1q?Fa702!6IYl|;3!#jKFuGu_I;Js#OXz-am=ZP<r%As#dqx=F#~JZ
z8tfLqSkM0bpQ*k{&hAFj;*q2!dYb}?bLWx2hEj}*D8$;dtvLsPquE&p4^HFt!DqxP
znp-{oV|o_qy2GJKki#DBU2%q?22rK=gPw^WBoXUkxk9O<Z=fLs!q~Hj`K?+%+%gvb
zwhyKS1Z!umgYwM|TB1zaRhRL&xTfZCh7m(qhnDg_ss3E5Gulyab&f+A$6n8<(?S}K
zfXI{9K^FS9KXi5o#A@)UR(D|H@v<d0?uq+LTmLJv`W0@|aH=~t>`mt(JaejOey-2Z
z;<d#cimS?@8jIT!yx)9`opDJu1aE=Ow-c!B(&zfY^jcfmnouT%-2xH(sz)BSS#l2g
zH&#w%VtF{z>#~l7A8U$@__AN_0jF0-`FlHz2%|_jCoG>ttT(mBCmY5Itn=PHteF=|
z&Ad`%1-kC0<+L`T9{VXjY}e(OVy(Q+6t-b}3=((0iib>&vk=H(UsWxGKsNW~zJQ%c
zK;!|X052PAS}wm)|EGy+B~m;!kfrCD&Ld2SX-~88DMmy$GlxN)TaBC0ZBC6RZN5+t
z?*wJPJRu3$--rX5?6WqE$22{c{O6&C4Wt@qW_;3Eh>@tlT+2tw&p>^*1%1{nif4=h
z$<bOzsq*C70|%g#a~2%a7)i9dx;FOcbeo~LViQLKg39(m-w{7!jw86Cyg-^lvp*9h
zN-@-`020f8+Y@m?h`tSfc5|%h_uys2bX!Xg=MJ)~$`Kx~)I|9Picoqt2B(mI^Rfx+
zakT0i+s$1P2UAa|1cNF@|7zk-$vf`CWeM3)k)h(O7$cwH1I(C;qZGtGv4wYNSiPUv
zaOd*{UaYE#z4Ozj6`ba1KZKTc$Z7pzVF;k&WfM#Lg-X#7SZ)cHVqCznd8o{GJ0!PT
zF)Adr>MPaQ+TC5OWKt)GT7{FVTG-saOZEso<L`7RI2q&$2BD3WJ-LkL>OfKEO}X~9
z0%n5Z&0XD;9-+Rb5r(mQYQ%rq|IQXi4y6&$zW=CURLAS#2*aZNw~=xViHky9q0b)e
zw)J5B-T<#FBSQ+QAiUyosF+6aMRx#12JVZ%isuDP@n3*GPcuiPXRy|MF8+}!*<66}
z0QcYM%+5vPIn05EL5twTrH$<nyg1-;Pt)~>o<X<0T#Gm1dM0!`WnxgkM6O-k>2u2i
zM_*w_LJXGTrrx)dD`wbi<V}C=$K&QL$|MTcEead{|D6Uh9|;l9wN19<JiTla*M-m@
zb>3PDHP~^;46|kzyM4$IRegc;(K@kA@$ZF?q1FmOM2P3^ye9WARFwET=s1jZKRNtx
zL4fd7{iD2NIAZ&s@*zbRZKcX0<SE@NH6|wW_E-;;_~0eu`3dP;@B&0Gl2!)!f}LFd
zmV)sXl){K|n9q9Ms6;d(gRh)a7V7A&Zxv@cRhy=^@f$`f^jHp-M9@}_TF*;lVFpX8
zSRGTe_V<aOS0z36%iPg-98=-{bn3OQR&$c>+@V>3WKn>Jd)+oJn&`GN#O#{<?b_}G
z^{&R5)FT`4O_pRG0w1C9MpfZ{mamp{%BdOy73&}b7m1>q0T7-$e@S*6L9KYkf)wEL
zdflN|ec?1P&`=4#Bes&u>fqSr%cH|lS&UVaIcydkNJZAScIEPT;^LJJB!9iZ)}2Ym
zXl0{CRVyIx2qh;v<{U1(3(H<M1lE%6TzsM;>*irH==rHS=;yGaG@b_FA~6O^hcMPx
zL3R^*iuf@z{%0@|^*)JJx69oOAV<8iw81fa-w~fuTd4%tm&OltQ(p3AeAc<f69z!g
z;4H^fjaJ&-`x2@OB<OeYF4x!Jyc^2;j=wx%uHOS0H(q85mpf6qoC9?S&_=C?eMLT(
zQ<u6C$&X%@FP9b@G3IbukbXPyew970YBTiK>#10LEy=%IAer*u0Wk=#cwL_B!djw_
z*iKDaWjqOoCI&?{N|EU}kFM#kHz4v~Khdyriaq)BBmoH%V~O&3^2a9`B4hI%6s@@~
zj^diW4vSZj7BHhh-xj-P-Xn?g3`^bulX@ZwEWz``#8{C*3ubF;{)Jn2733fXB|}mo
zq2fX6@TjO^_V|1@DX+wzV)hb+i*9oVM>rB?;S8sW+pi1RL0aS|^~x6flFTRz52)ha
zcjbXjBA^2}ki_O$J3VbVixjZ6Dg;F-ycBm74Az#hul?xODnMYhZ2L8>J-?N)tL4pZ
z@uu%?L&yJ}<CmMYB3W!glS#oHi_ek8==9mft;kWjmWib!66uB3sSa*JK#U-tO2LGV
z5hoy0{v>=&hJ_}*Igh1JO63@FEiK7<ke@!_I2>0Nk)p#*sU2R<MhL30d4SQaI@N`;
zDj@_fm<WoIXK-$~osa@B<7eg*?;^N^7o*%ZtsyD62fa#U=U}_3yGm=UpJB8?i(hTN
z&yejG1^h7WJ6SHx(GgzVh^;khrzl!i*k|btpF&EHUplV_M1=G+@di<6$Tl2;p;yR@
zAFpv1_P!XIsiXJGL(@QY0b@W!Ph&ToiqZN~xQeMs)s1vU#;^#?jb5q<Xc)8BJn#_s
zG4F+yQlMqzw|>_k%ZEjH#-8%2%d|h+TaV*oX<(b@jFjPv==<sE4b#Lw*`+cRi8;TV
zdPl1Ht4U<_HQDLfPK5iRkU$bqo+M?5?<8TZ<~q`e#lr7waF*qUoOyh+T_s|Yg#EAf
zj2VQgZ#G85+`Ii&C~b5<Sj~lV4ybc0QB{{j+&VY@I5mrD?8!`YAs&~B(hhS_FQ8>3
zSs)@}n3~N_vz`)F2>R+q#To(|m1w!|hre7Pc3KFHmnpBAz?D$Kn!=+8st$wR;kfJ(
zxV3q`L#1|B-_ClSp4wGxG3`aiN|uX>gDv<NuGaa6Wo^1PZrp`_%U#77gO42yJn$>T
z*$zoAJ{)1awI*|IA#4NMm!WFPyY(2~5)U8~I^U7Yot=Zn8rd=*&>G4X7$cIhIx1fZ
zm-5)&SU<2`$>e()JrYccyd8xLy|Eo9oK9v$j43fNcpWJ}>#T^RnHiFryp!CEsKx$=
z8gZ*S8dgYYRUwe%gG`!(aoz$xk1j@&X3h*4<EOPl$UU4_#8R9%Z<7<EeJEZ=@5*xE
zco(|QZg)p65{5c9cNQZpEw6A*iF{YD(rZY{k)r%9Kl+A!wBDER{Ws^ZUTVaU{q8WF
zfUfPcA!9S%IHEw56{-NGm*d%t#4o9au7^rUpUC!tRtnB|whYfc-dunXpF~%bYW{w|
zm`!gT(b)2w??hc@?&?H4%E<L+Xk{Zv$IJ!aB%I*q-XCfUVvJy*hT=Lpan;&=kfw}y
zl(S{b4?&C-vnN`D6+u`x>oeD+vGR-It%Ol0fd!Dz%iuz*9wy5q!XVYP5hvJT?n`MD
zWhQbYuA{Ni7aYaA8lm6dc*RfT?e08YA-&}cz3LU;DUvGIG4fgC*uvKKbBGdhJN#{K
zjDI-uyT%uY?#Saml6k_EPB=U-#l^eqiW-jI@9(JPeZQDPQlLmrflTLrVx3@C^{<xF
zLgrP}NrTkPqj_)FBEFY36|^V9)Z<LN4-$*VTLj7$bQi!=9j)e!d^}H~)t?9TBS{S<
zKRn~;y&o`bBLrs@zX+{EDHoMY>|%<7(MrgkB&_?N^*DZZ4MZQT=h_f7UdmF~egFO0
zC$(W@^eET1>!B0^(CVS?tr}|kRlmY;I-jZ-GWJ7$M3lUNp*baGqMc>2SsDbA$7-jI
z(Cx{QdfD(aGCz0qXGKU{<Vk8#QCeC)G81^a(G{(*YDtbx$)(OIAEdk_e!xJJI2BtY
z%#GL~!bmCBW&W+nJ9<RMRD`{i1<tV%^`xQHJ|eT^yb`eaLLJqs15rxPVAP&>On!y^
zT{M%;dQWUpFbIam$Tpo+9Os+6Gt?WoWX@1nz$t%LSBjq!bfcX%)TumkLmiK3ZJ%-z
zgLPSK)+NXGYv0`z{z9*)aQIHF15{oO9i-F~pD)ig3=lry4`{Af$3M`qPxFZtD#E2l
zP;T=y>hjSO3{dIJGjCe}PwUa*d1?d<h4aFZxc0Wz&W^U2ncK%o@ElU<LJMYyOf|dk
zaMM8;?6GTwHs*-XDiyuVQ{VOeTQ_inXeg!P?OeB-*4}x)0LjSlIpDj-IvLtA%88gh
zp~G5^RS423q@4upo(?cBOAC9<^3^xEa;uk^1AxX1Bc8OuASBqs_Xkia9kaK0SEUTj
zm&Y$;_jQH8B<PpmY%TKZQC%k9;#Q6~(!V2qs6Iz=iZj1Wbf6c+LW`+z!&q4z<6P6f
zUHp)hLb*TMLnJc)n2wjJwv>gLpY#&y`?zUBw_85PQGcqHkS7)!Lkh)ssDNTjAX^h%
z`Td80_9}{q=KMXULA2p5vbFXz&0qPkkS?#Wpx49p+gcZN*fGHRM$)hwH_usmbny9d
zRmQ$#OSyLT>ljUe^0U)|+MLU$g9X*L`2P?ZNr{3l9m!uSs_y`~gxE9^Mj`yyz7q-S
z1_>IEN0gsi7k_=iy5C^va;(`OA3q!EH95oie0p%I)qCy_WMO2d>@mm3jIQ0TIn4iI
zgs2|7=O1HjmwNP}%gakO>5a4w9%K-HDM!n#xsY&^$k0>t<GXw%+Y@ETZV3j3t;dru
zC9-2%pb%>oQh#NQaP0S94`+U{Fz*2Wlu{D}<=<0pYPDr!*`;)+sZCPf?XtklrS8CP
zxlhRR;Vg*X9X-`wS(vFR5Rqn4h1jXN)r2imVzDK0M(5*o29{-3X!1U;c`j8VqM?2;
z;E^l{(xpj|`Ed0eeJ4-o97aN#^H6%2AJcp#W>{#%b;`9*dhayW`L}eh+U2rKk2VYg
zXrcfj*eHg0L`sW%_C3)zr|>aIq)$}Be_?;){}OmTEv>x1+9&~icx6FeldFlXMpSlP
zQh<F3K%E)k4DuV|X0+aJtdpP%DErlR-rIS1DPI`M_S>FjCr9Bx*LL~tyJc*?*gxl^
zryi+#Q%|naPt0Yv;8J$eO`0837&E1tmjj&p6+A=p_w!gra7U9U3DFn->nN%4kW};s
z%9U_z@hN0tcU4G=OH;`qrPjp2N!`|~XZtp2dtLjNr$PHCa$nZiXa17-g8e#FPIT>M
zC~-;mM}QaVH27rSKh8}^L3XCqW@dlqy{Xr86sve<6=|{5R0aAnWWi`eIKy+hfR><l
zxm0*+C9PB3V~J!<1;1eGlO8|oqAMVzC~2Wr_PGi5i58CQH>p51=8`z}K4bH3LzKi$
zaw=Z$fz1(VR8$y)IzvMKK5I9S53EU^DYS}CNcJ?ms#z*|du-Y86Y?n~OpSz#Aam9P
z?9jj5YPFTvl_S1|>%B{2zFO#M3f4qxTsr8-$`e;pU}~q^Bk~Y;7LtjY0sdxY3TF=0
zJMBPWsYp1Qj3hUKGsOW!n!%reSVLwu9U~7CL-VNOXWER;uQFg~Q|Vqx5F(1~jnesi
z5_`d0D^LAC?ucWo=BO;XM9UTGmv2}Ky`mFT!MenYlu_}YiLgy4G>i~dZvNnt(kEYP
z@=iW2^W@8)!JZbd4`1fVnid8MEpJr?Ju1(F{D@MCR{xOa(&u!sj`o7$3#1$zeiU{-
z5gt*uQaHILrQ?_C8M972&?G1VADJ_UL8XGTCUeqx^44Q6p=`{(dH*3CRqvOZ3R!ck
zl_!Wxo<1$rh^<M?e?aCd*cU3x5<6TjUPA=c7T1fxvpANFDpm0wlz$LkEB7%q{_MA*
zU;u6*<{WyB{dLf;5#@Eoplc9U{*<u$Kr50p*l%LVl2)c>>S!VBe;|-_gW(kixKWga
z(!U&aY}#3IulTF4jjpkdS)P*=#{W@tmSIi4eHb3yr32}f28q!%M7l>xiJ-vfMnGCn
zM>mWbF**gLL=j=5V<RM`JESG_|L*;?ec16F$Fm*V?)$p0-+3}_)ayU`98wvPRa*Wb
zkclRngt5|t-~fVmu#ibP69y6slJZh8X`jT7lU<af-qdXI=Ngn3q(?FXc+d4Tp=WXZ
zXjN<bFcVFwWa!WQconZ!Jd`-q6O!KuxCKQLx~hylx02lJFlf`XsrQLIE~BPP!{m@C
z1(e}pa1@`UzuuSt<4z*E`ZNZx$_|w<+*?V$uu}J3$T`p=0QU4$(H8#QlVhu1-V^uL
zck<0fL>m$SJ+BdjCPl3d*qB>PRO~|Phu%RXTln4$0Rrg4)>-k0@e${#8X@-FU;+dn
z0(Ic078r+IA&5AA$Cv;Y<pk3hx)U(9C|dXFQmDz|LMnCmUevy>JQ~S}aHRgSin#>I
zZY{uZa#QsW>ly49e#F!QoGJAHu06dX1C|g34UQR4Y`}E6r)957ZY(iIpfXkp6W&U3
z_&?fAkQ7-O#b^;FUkMkW%>$TPZEzRsb4N=^8Zedf<xijL$D?s~2{Y6Ju|rdV5Dfd9
z3NC>$QH~^h+Nn$ARcX{iAY=+m){8`3lp}}+aHAl7>De#<5q^~GfwtpzMvs^)kWx)g
z%MEw+F##ov$zna8?|db3)wwPe_w+}#GL;$jLzAuq`cWk~fmv9~N)E_M{-cx*JW-Yj
z!7Res-&xL=S5V*#BglpL>lBCTPhnzg<AyGQ&iOdhwqr;fKU_*j2bbEru#GWo=fedk
zlE;|J%MoIVatOHEZ1PW>(*~|!3a+GvQcCEgxCP0Vv1d~E;Ta-)akCga%+4W5&=Qtg
zO;4u?3QfmPZgostkB(QaLXyC3A$T3-m5zy_#taXEjyXVtu_7svfRYI&5k@Sw?;}4T
z1$qeAu#LozH6Q_cl`AGBVjQEUAD-yzL(5ML<w1pGl8l)Uj47?jgs!eFhPD&I4pk)=
zU_-ksB%T_S)f05ALZNx+P;3144dV2~DL6n7io0=usg^DtVm%693S6c%Z91IxZ1gCK
z2-LvWr{kplSrfovpSAIVF5ph?$@A4T%h8)A8YAnr_5T3$`L&%Q^_8P0X&vw_?``)3
zf3aXW_RgwmIrK7*f5FJ{-ID3!F4xCf!B0wRu!?p4UVvCk`isKw0Y5h>9Xl7EYdJ!T
zhLqL4z#VSJL?MMCOs7rQ{3@fx{Y^vd4-Pu7xAM8iCFk||*qYharI4Q0*CRdnJH6K*
z!zkBH{sSm&GA$qIpFV=M{`LD#+C*#jge!%k-sMdtifmoDEuH@L$1vvY^4w2nWJrtd
z1mE~Rjhw*3Fai^Cp|ADkYA5hiUETAG2FdUL9JH$HZnjf#i{YsNe-_$u2j8wwn|RTW
zyDToiMJq1p8cEz#JcXr=+)Il?|I)m-Vo{;7R{Q<p3))_Y<hJ(8ePLcrHq(G97eBfE
zuS=HCAYmV79%O$$%lnYP5y0F?j;2IZQP=*&Vz$Z5XZeO3)iGsyiY<a?j?N_86K=x}
zwqNo`+PHu(JJ+kA5oQ=kgD06ACCXH8x#<CC<t!|iPYrdYFjI<l)jr?ZmNe})e@V40
zOA)Di=`8<H?!>jui_7wlqmqo9T+^X520E!tf+)Z(B$0l&)7*>q!3o4{M~S%;%G*5X
z{BfRF`FqWz`gVoABz@Pbz<PmF?Npa^<%3col%MpsHSX!hNlxkOV8CJ&nlNnEY>w(A
z@w(RJ#_$VWv9IBslIV53R-4=Ayr5Od!@9)U#8?~LM9@|uF=OLnt8bk}!pbG>AKL|v
zRvI*@TAS~8mT28&1x2|T^y>~O7#398c!OhpdcRE59%A({8~m08=}aSCV0&|9b!ZYO
z-R+VY6DM(RSM4SJfy@6aTlJ9nN3g9!v<c(P`MHH(MNyeFN57iXXLcNhn&Ir^$dv4<
z&?`T@N<9FYwZM!|c7v|C-rZ1QSE5<_fd=m@YSd@Wq7|#FGyj9<TpV}tb&IGWPA?7U
zOA634nII?lhis}b_s>>Bho;?8I=%PqHpag-28#0kBHDev$WfXl7pp&mc6tcsMLe9%
z`LV+D-uTUE+J<}bYUtdwHO+^BzrjYy>*KE+EFb$1Hl}YRYlSy|=jl)lG?i<#`lC+S
z6+T)WiCorvrOJCm;KZJXrk~QVSE_%=?`h;m{oJoZ$&zFJ+as9-uPMEXiO%SS)z^^<
zD?M|dBLzO_j@g1#?DSvZ;V<r|lH>nSVJu;?9-AZ%S{pV`WrEWu4K0736$6(d-S#=$
zWcj@6fW_TMwo|s`Qyqo2TRy-Gw*3V7cERzOqvli-6Pn&%d#3S1_%y82&@t1ArzPC2
zONt|haHq}oy-^6>le6Ucs;h#o%<+8FKgEr1@eGuoG5z1a430~|Y<_)!U$uLDwshua
z+)4SOd{ATu@?s2BnQ>N@vmRx-ANc?HOvP!a)%Xy#D}{W}ei-)k;)9KhqS)E`S}yxe
z`sUScDw#V}_DH0ph${hi^IE=ip=yK$@nPtrAKvfNzNUL!zM&sOu?z=}PyICi_2`}*
z>wUQ0fzfI2L_KqQC%xNuHjEl|w3-Fk{&r8EdmC0UQDOL*IVVeoyxKKoFU@W$_G^Ng
zKhO5v81shyG_tKH<yDRUY+2ev78#e7&(dMlV&3dJ+mgEIboa+YqC*WrpRPwbb=J9h
zYRp#sVG)YhpkoheDzdmCCtj2SMEqDD`H|!9i|KsOtY_5t{5o8VAMWlKhQ+=6J3zp_
z@0j`%rC3<T_=m=o@7FbBVsi94luxzU{EeF?W(&r;k)-tnv#~tnI=gN@jjc|xCl;Kd
zg<qU76*3iSY3SJuSF$4~xb}NE01(JJqc}FiC)Hc6(VxBHz-taYR=OT3fM>ShMR#1{
za5K22$^(fLePL^W;Nu##g3EPyEXhKV)f4#vfTHWm*!vnmV9lxa9GD}M9NMwctviYD
zwO$S;znccEb(y})y(~fS^WvNuh;}!Mz=}=BbagSCHHYoer9Snh6jaGlcxX_$qZ(Uv
zbQz2Opeza*2KP;uSlVvM8TD`|2zR}~rp?VFze{9qWd`jTGf{^ymD|LqoC)5-D62N&
zzL#b9D#+L${4u@ZucQZXm_Uj%gAo?^zDEZC6ihR;4RJ>EEV<2Tq&nrfN#FPQr4+ZO
zN35s%8k&Pj)A~0!nV>CYqoG^AAi`DSt*mu!Is-f{ZVM&I>$yY@cpqeBEh~NtVFv8f
z1FYiCzi$_qg+kOB@Ls}0*2{@Qoc6%RLT}PI;{OU_`_l><w6785KUc9<v<lluRxGn<
zKNcTfN+(Llpv0yalXqF8{t!d}S5KTW6IZU5^wmo{&<w}pEsBYvbS@y)>Jj-UB1Sl=
z#~%3=={iKx#z!fU(xV~Bi(v+XU^3V^!q8v@F`Yh-5<H`xPii5Wa#2?fS*B#lh&S#Q
zpu@E&^<AiBcZ*u6bLb=`bWilHZ`~sF$cg8BpvOq72rdtq#C~#gW*b8n{owE+kFCVS
z2fH}Sjf7H?zZ_B)BzjMGqOB?Ly^MrAir!7_$Ycjtg02T>Q-@cf+xRrNd=xQwHuUU%
zf}`^lE|@5O*zvP>0|h0QN5&4t$R}#rMxb6}<=uY)xgd4{#-kq<&|v2>1p6BVnQt0I
zy**Ni{KLaNy;N8H->=z7x${J#EgPlHWCWa-O@_HxG9XWVLI$2fL&<CLpqps*8*^tS
zl~xyJK|hJ77HsiO!1XV_TGqCvc<&srMwp`Ty^b*eC#b|%=W~IokOkmKTho<4xs_u_
zpGbRoeA>3SUYHAFj>7J`@xaM=&%qA_zHe71W<;A$p9z8Q3^geAKWT<dwMH2+vR}j)
zA9Q;Wsq+qW(DVLudSGN-Y!sx|_9JTuMG{&kIP9aI_$r{Jq&3*$H2Z_By#m(W^}FNv
zBle1_z1zQEtRsdbdbEtJzfZUEg!9mrsO>G3JS#FqsBfzdtFgVQCGzW#9<h2c<oqAt
zP3|3R@8!3)js!oQKkRLyRw6uo-`{|>bSwRx(|gUT?}c@lro|V}Y4oS(DC-&4CA8_j
zH!buB;y#ZKdg*C<^Tp_E{{ao0nzmyA_-!@{H_jw<s_pmnB7liRRo7tt08GOQ&!nWz
zVs&6On`fVn(iJDM7c^2b^N<t|#o+bF2zF~8!W_7CwsU-xsl+*wBYO78dMks7-#Mg=
z)67Pb{t8YNdLU(#*WSs4d`2yp7}@~+?h{f`8#bM{9#0U*;{b6{mPedlmXkV;6Zpwh
zQ}(7lx~y6dM`QB0=s|}PXGLxb!EDgsRutzBrrc}{FJ#jUwiroHtld;_Q4M?hg*v=C
zL4eb-u5naSh}bkaQtah+g;vRtwUh|tDLYqGNZkQ~u&<DEU81!}SwQL)1h@EIPt!Ew
zCC~PYYl$5^F)vJE&wOXlmKmFNS-ozg{P~HhZs{Bez@j2c#Q4W{CsB{$^pGN+z|>5{
z-9w0m8;^skP`2VgVFy2ZM>U1hw>2xBCLw$4k2ypi(3}>gKMi_fqNDG%kY3u0`TR)B
zoVY7Ay-z;asSd(*lNkZL8dP>0N+I#}YO{yPzJ7CEkL^H7DAzc!jL_ThX{0{dB(Ny&
z)G;S?Z!>cscj8G6seMmK8yaiE{YCP<=AJ3RzQD_jNeJ;r`@cVFGJRJXcq`U_i3FXF
zE6zGL*y6XnUN7QZsT5Ge)9tr%8pK-=ylVIMmN99fF<Gd-$y036wrVjZzG!3}*}m|f
z!>^I_^0*iS)JYJho*tQ!MoiJ<d+qOV1ox=pf9@09)gG$Uj9a9+`^=U<Th`(46&Z3J
zu7T_9_PV8u@o8|<^B2r8HgfS(E^1ZpSzydWNF7{VsqW(1X$6w#)!1tDdr~zAoV>!K
zZD?}}wU$wG@^#(y3OZtx-^rBasuOf#oIO4}k`j*Icz=O9^u$G2zROlVx3nG|F5#7@
zx3^(jeR<a#W?s$TsnOx`(Mb~TJP5xvpvPLLc=&BRS{=P*dqDExVn9T)sWUO2>)J;{
zL)XoOVDe?on|W@R1ARDlByoi7KR^_7rTbf0G<dYE8wV-*s<-Hz<n(i=vr*b#Gn8~q
z4ESqbv>VruWB8@p><hAx2oZOXjR>i)tygik(s#WYk>8>IBRy^hZJ(r(eAC_-oOs-5
z_z<#Gnx>dv$zLx4dk^>>uHn8Ls<+?HGjd}Rntfn5YX1;ZSARdhW|48%@0_K38oznY
z?oU6$%H?P|C+&22e3}i&x~eaH@xztvxZc{}TYpqQO*Z)vqfu^w!>KtLO81n>#M?Pq
zCaF%Dw5oi%fi8J)BPl$)erXSj&YAC376NKlMAd%A?uO3HQ!$+c47B?&-a=U3zdV;v
znJ-TlO^ob@h<?6Y>0GaSmA#vkevq~s1{pNg>3Wj!6C#KQ9s`|^>2PjszUb_#h&7hb
zG$~t=+QZ~~@(8bmT-8GCQ8rFs;2m|Vmt<Ybqa7B16Onuy`61TJ+UT+@A0QxHQ@}Er
zr+Jky@=aiwqxMFg-6yia%X*5y=Om-Pd+?fwv6$0D*$8ND!0s;*#m;*n@9?Nj-$$9t
zT5HeGZOLr5JR0?9r?qpM&!QulN5dsbyZ6r6wdjTHP_R-ay`<{y8}sYW?X)Lp<n5)i
zg<nW{*qE!_EG+r2tJDRKbj-S$z(DkKU=SPBv541)Vly=D`6t~&U0SnbbgY3%hK&_n
zqfB3f#hB!Zw-~rQ=6!P&kHe~12r@%xSzJpW(lqku(-$xCrzM9%r9&AL(h&@Lwaz-=
zC54A(<gNN@wobDNq*>Y?1iDTWLPB^#MY$9D)4vr5sRuVB^{HDA3H@T*3rrDdWhB%x
zw-)6J)NP@NMc27>f@Mdi`#AUK_c$5n@6k{elwwHvlXLFsXD*K=&TTj^4~%&=!se>1
z@5xS|9XEomviCz{ZqR#n^u>oa>}u1}qqyI4&D?*^wV7J)x6D{mB`h9nY4`H}#cM1T
zi6Hs&bgW(f`VnD}OYdI^JNn8WxCr=Xbc<Hp;O;BCU*pN(=CgZYuEbCM$1B6`jvUm#
z_8GqI-qMezH=%PmRVU~#fefMM@VGW?{RTl3SZHD)C}kOyaADo>jAS$@l3d9yxZOF|
zk>pRggTx<8t=GSKUS!4whIrFX{4V$ppnL7_FZho~U$S%G-zW=jE2tPymp1akT~a2r
zMu1~Ny3^(Ni#~=gV>?S6SHCz$=ocT%pXk6uh?Og&?%67%w_ImOwSo<Pjekb8V?~_E
z+?~81BuCTY=_F3In&UaF#Bm74-I6CYIxFJ}2V_T@;{y2nUphC<4E%kIF8v*@${a2b
z<iz`4?~L<*ozN=R;Ls@V|3E92DPH+N@nRc(4Ivl4eCYIe+i~pv@JEDDzC~eKk!Z(>
zoilRn&!wCU%lnT#K2(+%B`(j3VQ09vilanfw1#4IdDF>@%+mwi&u{kUYhy&e1wd||
zBxgo7a8VeN3PrZ`2($z4$B6)Ht>i*ZS62V-N6<YM`4*V^_a|OXrpMEO{{Vea<yX>4
z{y5v~!UN`i)N*n!t#Tq6zu<%mTJnC1LU1t>uV(GY_b{K&sb{|SrXi=ONqkYy$Nr1a
zR>6_XfzLmQ)?NJv`0CohzH?<8z5|@Kd2<tz86kaM_^bcd!)2Om*R=^HYIla6{uRz1
z)t>2Xbc<tQE{Bm`4b);o(oU14+ro1qSxNqNvE&tP<Vs^6FMK~}wB27je4+GC=GdxP
z<w$pwrsVjm*c-o}GDE>>^BOpTwl@}wzp|nwicPdk5Ut5bjr|1+wLZTF-wSMcSFxuA
zpLQFk(s{pZEy_=!$4M<r`>!MSSLD>L8eV#)uttFX1GIP^V2U|yyHyjF^nzF-kevK?
zZF!<A)d5DuRkm`<?L}@+J#*yKv?5w(zqF(<`bESPbK|$D@xI@2c1jH2Fw}cSF4=jd
zg#8cD=9#%E%n_Q@7DpgansF@nlMFYg6+UoZz2{ye0YlvO?;Mv-YngO8->rrd0X$ed
z-xs*7#55sBv||^gqp-T#BQ24=)g{!&{{fQlWyWUUw3G=GNYH*z?X_9+t;N%URKd4p
zd-_xivjA0IMwQElZY^?azzBLXb+jr{?kU+Gn8tmvlH)+}g8t!{Z~+rp^}FZ5(Y_u#
zC>|cf&jv&~VH;ST_*?KlfYmqMq(%fAV{u=?2f`3Jl;GP2A%^J;RRO|jgK7y?5eH+*
z)kKG>twu!M_P5jv4>N;6o<JvkD(8hV-UevVD^3@mTMM<kmTP!ow-Y&fPqW1T`SF^4
ze3|Sn%~B0MQ|^C&+LxEW%jOR6wcbly7dd11kw*Nq)de8T%phD$Q=CXXpfka5GqTt1
z6-L{(rM<ETQYK@hWTL+`xNP?|i>bq_e`lf1Qa_Q_K##qcb~9PIW|r9_$6BC&slTWq
znzepV|8DN-=PG%W1cV}h<Yu;(RIefVt+lP(8j<$rhje>KHho<4{wKOXf&xm51mX{G
zVu8?C$uAlWg`Q!}F1OpFfG!mw^$g4cIrf@9*iw$~$(I6c8cKK;e{h9ljwIKrXYb9k
z2D%d8)(G}-DwuWb4Y2jp%z!>#y^F9q!6d~>Kjs*&O(T&Tb%K$u7ior|L6qUpvxHpd
zrBlscy1wN~Ggg+g01{isYADQ50!~8$va)=1Rz@O!q$y|yz?lN|!ys2kl%g?_aePsa
zE2u|tlI8{k=s-t6JMIPN7eWU3Bc=g)+nK(LpiF<bW5>oH2;G<f+wNik22T!Gpw?B*
z66A;jI818CRx(~83fikG@k!=ZGI;hhaAL9|0g5O|Fs_}$rygd?*fDgVi8scl=_-e!
z0a4nLOOh~-L#Y-0FUv(!^l_`+oyH9v)QScZ&^gL+^VKOPW}X$|57Q-7^t~vbXaok8
z-C}7YGc*OIV#frwqnA|21?28s2`*05{<TJ_AFX7lWR~q|Svx*dnXX90unPik!Xe-q
zCdL(ynuuwDag2*`PoIe7KfsKp#3Y2HTMym12JQ{m({fWV=~fnC43t-PReELGvqz%*
zHIsn0NWu8mcqT5sO{wQ1VZ044CrMT?)_g<)dtu}Rci=bC)nKJoWhU8EcL*=k5SNx?
zzH$25(Q2aU%J>il1wEX=1#+ae7?^9BTxnm&zf9Dg=AkLsgtemwjkT`2h7`j<nOyl8
zes04PYyGJL*#EoPGRYD!Kp=kpLUt5&X?BKu83@oCj05}N9v}g@wmHT`gMcBYUUp9p
z_hQa6rAY}W?pgx0tr0-y<O_hw7=NfWK-c>Jwv5tr7+938Sw{~%Fadg~qveLbzMXnI
z>AHurT|>wn$>mC6gg|NmoFoH)1VSbyB$6-uTuW1bC_ymJnZ_Ww03-m<0EEDZN@$nM
zALtrzA&84wF@oqeKq!_IEa-cQM1$T(gRMvhWOC#WGzDl2tLG=&B*w(32p(qWVPbpt
zv_rO|lNkq?(7L+HyLdFV#zsh{`#l;Usnj2AG#WUif!|TSIt4c*;&a8t%X?}djOzr5
zBG+~s=7oE5D4fif`dfKVDoxXs_TiWSXwp{?Og&g$fjc<>w6?CahMj|{#~$<H>Sf@8
z@-eZHBONdiU`h`TkkW(-AP6%eerz2r|CH6;eEZyeU9Z+ck0@aTt!R^B7bh`N^Pr43
zs3xH)@BH;8a;9KBNBoOd|KCd<zU<!Wn-`p+mX&|@!zIs%W5OK8v@`|4xIdHHp#>d}
za;Q?HL^z-!baE^Bv4pfIwI;E9WbxO9K8RVXpP&|7QsC)+&{>5ORrjBG39|;r`19>-
zy6zV0wk()@$!MWm?IVl*sTz7f=<Q6WXbD6nwi`4=ZR*WLKOygCEeTmdt*o^9ipVxH
z4OM(;*8J&1S{>PHhW-#QGZnT^B*^uKci|xU29aLdDbW!Md+x<<L9{O^TY!(J(&{D5
za4h}M-wTK$NZu%^+rn-aNR<%&2MB64)q!h|lu)&&)6lbuIQWq_-6mS3xp6utSZHn+
zwznIFcJrM0Ppp}3-H>hPXZ2c<!AzRx{g*73v+I>>g&6ocH(z#dJJuHWELj@8uHd~|
zOW&6#F=?F|;p2MZy_0hdTa|5WGcDQ~<I3IY8Iv{s<t>}t?>j*v4HpaMaDuG=oC2ks
zvwgwZofWI@XyuajvaXi~ru`w{gC{UmES%)O5{0jT1XL{Sb8DvTBphYD{$*)6q{`@S
z?6-NovdVd~H~aZ<$$D@Q0i$#%Cq%4+e|py44pj&cU8IlHOE5lVTmNa*SD`*`1Qr~S
zcjY`Q^377stD^q1$kKV)sDn|Va_4~RJZUIBGZLXoj?8j*FD5Y;EeaR19ZPof!n?0o
zCZ5Y}c(bAO{?EDj7NubbVL*M7lg9J~^!XE!1*PDlKNdV+H+s?EkS`B63(Fx+fCxVg
zWnc&6dOOH>?GLR?B``yKB+=<xn_l(qw*0KSsLZi21Jly!#yxEJ_G=Ec6KSnu7U`ZP
zC1-SUQI_T&+Y7<7btLKspZsOjs{(#arWym#{N}$l3I^P6jd}ppm2PY%hmwd9uEZ*N
zN4g**otJ(PjdBH5tPRo+)Ox-gv(d5uY{$t`y_=eQ6N#EzU_IoCUvYh&@DfEjG!|%Z
zntW{I{HzHkyIV&U;v?`=%d<Oq8P(JBLzViiRO6c<{sca|j&lMW&txTYdo~fJV|)Hr
z9e14K&(vtQ?c)cqXDDsSYYY3~{hCE8YspVjc%fA_zDwn!i;y0(;Zfn}D!a1q;M*60
z{{cvU!CwDES(WKiR<TB8F7u1N=A2Sw!a<uvM7QkbLyV>a<QtsVhmI<~>kIC>>lvTQ
z)K)Erv_FhS$xvrO6tC@(R-w#Wg{6P7uZEjz$%t2!4_=mYi#N`(2_@!l5_pK^?GDOS
zpGp|5_$P0FDk^(49uSZP81-OusiZ%OplijxeTitiYV{!=VlnSztL@L<hA2ALTk8Zm
z&bM~H`FQY2-?<@9gK7|d82nHEw`N)?c#he*lpyeog|N6ncw{pn;KNY&C@&FU_1tnh
z`#JS1#r)}WGw0=2$>KaKS`FKpfp39U#)b=pz$+EWwzjyFk}h{wlv!~u-t*cJ-dJ~P
z<&H*=wlA|Azg<HNkPCGzANbwF{3qvN%ijuvdAi;?_(p|V8oUUS?LZt~2`y<e#j~WD
z#|kK|m**1kds|1L4*iqe;|;gp9e&WFr?sokz+|%G3rb~}_&m{)lyq`<fi%x=fFkH7
zyxm|fyl*SgtrHVMCUjqYITM79E7a>S=oS1k@A@!EqYN!4u69P9M-NC#6lvH+xuJBb
zqtLeGcz{zQH0wE}m#(j4h$G3+3v5pX2~zBGEEDmC*_QFb4bYucnapN(M~T=1Cs=E|
zYzmTdCrxcL%ygO@;H|FCifvAweidp=sHtQM=C1S6;1NLW2jf$>mJ#%j5S|+F|E?g2
zCOlUI_}^Fe`06Dlw*q!=JY4V_MAC#d9X1*?AOwutMTkJl0d=rVvZ`v<s`E$Dey!}C
z$?5Fti3dlolHNC}>u0MAw_H$ZlOLC1@|q3wXBg#h^5D|Hf*c&nWr`$7iIr615ahmc
z_&)a%_B&y41%4HN9XeU%?KXm7r9e|l*AibZj!Ub$rgOV!wAZ0vI#3%*6TH`3l>+LH
zW5SPWilQX<t7*YI0B`3Y@f@A|I038EPH>kzxcS>D2mTK)(el+U_66tW&uZ$V=2j{t
zMLrf?%Fy8{8ps(U-u9I_lO$J^@beW$WoudN8E3?fiK%2dk+d13GT`DyNKrX|eKAh3
zh7nbLe_cHuUiA3U&+k=xo#gZK9La)9Vu6iyZ}LssJh|#2e-3Y+b5r&P3=X`scMV;R
zIqAV1mvXGU8T^-}8h@`AyjG}pbS2F4pyO3Ue7lm-DUI1Fcb%8Y7%j>|W_*82V8~v7
z_$=X*HLDXojS_?=)P7l~yv_i?;U=lUR)rwmoEj56I8wU?Q9hN@S%`r`qY5<`k*aFi
zQ~*(~ThnSPfRtPrsIpjB{SpX>c#%Yqp*O(AI!W-I(AQw2O*=-0L+X?4r%hAso!KZx
ze>9R0y6Fhl05IOWA}LUkf?)h8N+&jf0Y)U7E5Pj5cwcHjiB$}zq5w!C_B4+bAX)1f
zYyyCBC<P?=L@N~VhCAj>g%kXZX(Akd!_Rd*46;+SUYLT4jyF^=DH75EJmF5^_gRJD
zt6VsNkfdd-SUl1)CJ;?%ur8Rd7fQZfVC1G&;G9b-tkb>+i73rbGA1yGYEQV?u3}t@
zrU5luPQ7DNp!31<0bI6xw33<mp3Rl<9e$X<+A5}c2nAi#IgDr}H9tt6dFfYs#u_d}
zM95)XXoJ)~l(RP??T0A*lSV?<Wv%WLy1gYrADK>UJx@dwy{Q^@Dk;mf5Z(9m6e-n%
zO6~Uyxa`0)oaHNCQR{#J*eF4=a_6B9q!8=x5X93B{2Zooo}zoxES+5{PWJZ{nB>+a
zTIJp4Ibc+lQPV9%2aSP$qSHR<a8WG;XpZc`{Q`H+5NDwnF=e+X2&odQu^QSsl@hDH
ziNSmK8v0&UH{bP8aKGlqHmiw`aJ_b8v9<rxcdupfmBXef$uEJ|OagM1Vp7ICjFlvO
z33$SkrcCE6xmIaoV)EO$y?$;Qdteio=^6DjpyRTVAa)^_j4xBn$XcH)^E_qCvOYuP
zk!q5OCB;wX7I(h{fkEZa=_Cnwrbse#H9_owO=ulwFPkB_j)}}<_MP6dBnciyR<p2=
zRlyl6QD`~7hCW^tkshOGkFP%1h_BL+h@d$L<*dHdbOYXZ+sr5xlqbBku=1V6S|zf#
zWmYeV*rmS|+OlChGIQ>D%@W}enxQX7i<>ikBJg(8G)a-PjULl=<V>!mKP@%Z(?vPs
z2rME}WIC|OilPB^E@Be#W)mHAhtlnq*oDCUD<!(YhEVFw?|JeUwRA7OE@!;VnXMfV
zu@PTAuFM_B3=NhuOJHosY~G5<2HQ>>xJ#yV^_#(hF4rrc6a4lQ^0MT9O~CT${zs+1
zVa)UTa(0_l7rELUCz>=|f9GX;1VZrE#Mkd(L+RrC!UrARYO(O5b-WOE6HVO>!Wqsp
z8QMB0_BKyXd+pzyJ6+R?d@804b_!?Q{@z)artr>6v><DvVQ2MMbTw-0!QS&Q;dW`i
z$JwOkk4uO6?`UQVb^=QZ5@w&c)|I4jMQqB_JD#qd1()F*j&7|_u_Mbe1$RBaK)SQ(
zG0h7&k|+JBn)Z@^a+bwj#!C<UAE|Er*{{A)r8v5J%ESI$1!|}i%n0(54nfOv-wojo
zR7K^>(jMo{aGMr~{%mT&ZX|Z8=5AC=$A$-->pFRN(Eu!JY{v&%B1D~0vf5KjOObT-
z-R?U{c!^vSN^?Zs0!iP!z$Z2qI1wyoBEFWNmTq4?i~9q^Y_reP>VJD^lMyMW4bIya
z(40k)yhI+3ZvT#lyTX1p34!mj3xQdKYzHy}0ejNYVF~5N#9${FOt!^CEbz)iOEd~j
z+x+=gKEZi4Py0ihO0&bE?6bROuT3tU=Y6|=pkaJjSJcyi#1OVOOaqQHL$8H9-uW<z
zW^FCVlgsmUD$aI6S}5cl&F@A>V8>-)IVqkkd<wK$pd_g1rn796LX(j1xEpl(%8$^8
zZr{|7ukVBW{eHnM)ek8h)^~!6ojdfCZYmF_MYo`b4#Nch>Q0}xKe9A&W;*JZOeR}~
z@0-6`UcUfo$tzJ2Ml(u1+=HmGWG)Z$hoe3pUTlPj2WR13NNe>oRJ#W<a45!OcZHEg
zxs=yJDd~O+zJ}TJ>8j%5f=6m*0jtqy-M3IVP1`M-rrM`m?Vc_FUjf%XZVgV2VHBpm
z%()6F%ZUE2#5|2%bWr>~e>9s5T##w^Oo@&i6RPuDv+J$5>6R{%++m4A8R-sd(^(z+
zriP%UW$>7ZGzlWeD%%RDgZ??P4a)bH9bydk9dsT$M3|fLOLtfP2_BHWduj0CWcX#w
z+tP2<z|I%o=2*`VUhg=E6-1G{+U1B2&(GgYZ^PFP?2tKqFMvzhY$9uICdrReBlTyO
zUJyv@EqyMlUieYG1{3`cP(5Jzse@g|yEX)J|3d&>iKyo|3JV_mIAb%_W!W@;kN<n7
z)1telEAPEIC6EKtMd2OykMt8R*n1Zj*4@mJ4ZWjC#Eoo+yw2YyKl%@#pHnY`)tPQI
z6b(4YOSz*f-g{xc_$I8cE6l4M<5Bi<=~-uO-)-MdM}c*d-CFA^E1E116_!84r?KD5
zmb8k_s5)?)uVy=g#_u!?_6X>|F%Kh`oU|K)7hpD**iTY7rqm??J5fMffqK(A^6;;c
z7yG%L`Nna1$X}g?beb3yhL5p!OG``ace#}Ro_2el56v`RAfD~iJ~Yat6jpt2Plj#Y
z+M^r(@ukyy$0leYBE_+z1yk?Hafl+)=f*E!D14_a7F0#X>V9EOHH!Z8O~_eU5R4!c
zI~sC?N`@OKdWtOs;pOu8u)NuWIG98c0mP|Y7sph2kbJ8Gc->GRXs=X&DMaJ}dn^!-
zT5&2_Xt2d;CaN+VE`2wyssJ`e18I;}P?1umkj!ucvyQn|cj?h~<Em>9V?u-rqEf`m
zh|Eg%1>G0<S1f^>uNq%({>zFEJFR?*Gve+kM<HmyHc%r6oXOQ~`A;Kz*Pl%tRp+ME
zSgdq(@M(g5=U@z>{>9+V%_PYrF|VQBG>yML^l;s_bx@W0ru1N)1}4_|2$shhCGlM9
zAar?;Z^tAx_B&n`!9LUFk<j8_&uORAy0GF8MXYTi%vXFoRaEes>g;v(^QF;W7Uc{H
z1q`B>phJ?cc5h!#at<bq`~}WZouK7n>D*m-qJJSnm=_RtRdQF=3_qQYr-n(w0#D1V
zbJM)tXd~OL+Fv|)YvM<G2hsX><o_SQnZHfRhWdT%iBTq5<thJ%CwS+9@=b=?)NZju
zfr`#Hd9PGY%ww7bwy@_F(#v1odXelsh0zbM&jsm-^k4IX)|{ii?(FFXDh4XXY|`i^
zwIvoWSMJ~x84O=uQHD*&EH&zmdRni2C$Cb8DGj^(tTZ&yR6#s3KeV|@<FAwO>h7%c
z`oKz5WCAzWgp=%=0$&wi2?AEEH6^LTYxrjnCTFOz6x~6x>FdkN5UoYHn%~W=_7YEA
zc)OWF&G=X<$(s2yCG0z0)kY9tyQd=}UA(GD=M|&aX1JRgBh%g(QJG2l$jv07mGge+
z71C;46)9}{jD%Y1#H8)QZRMLTSeN@I1k?>UGEXj*I73X-Kbt$5#?z-*SAi}9g9uLR
z%7S?U{Z!iMIvgWT5mbePaw0^sN3@Nn0n#bkQUz4~*e`jD<(^t1QJA{`2dBo43Yqe<
zIDK>J<_`YjjeR$Btc%kGy>7v;ry;2uRZY7R@WfxEzXsa(Op^o(oK1_bp$8S3l4Nc;
zI{2ejm_Xa~*v!wAP?v(0inbiXca%r>I+Y0^jy@{uzQJOTL}RuT(s`8`?nPViHK{+d
z3yV&yjz!!|>#bHQn|Dt10e9IPeP8>hYmuF(9g;m8F5)o9;?^*WS_+_g!)PWZgW{W9
zb&h^J8_)fLmV@%158efRozJNq>D6d8TY>u&;9f`#pJt6-Red)0;Ql~Ehucn5{2Ab1
z=4y$i49s>?0mpK+uK2j~GD;Pd8GU51D~H^duN;gUW$Pj*o4};PsaQ)p%8E}B0p+U!
zWf_Kj9nQ(6i3M<}ROnAaG*7e|N)aZNade_>2p+@l5I;E3(OWEPedkhDfzM&BhF;T4
zRfdN87_DhU(GavTvO+FU)B*&F<RbX~#k$_|Tg`^3ka8vG1WLnj4KCK}N@}_F0xgx+
zzRg#-mI8JNaDn)&EP&U65ah31GZfLjLM|_YNTKR*<0Lf@1E)V2&#-@z7B9Iqs^Eez
zu}GjPZb7k)QB6lXB9nUKBLEW5cr;NjwFq=dRWzkN+H^`4q;SqCIk+(nIT-_xzzxfQ
z6{+NeglWa~Ou#SOsnp82Rd*P~PjNfvTN|em^*q9H6XWt9U{0@KQtqlkoCMetRjzX3
z!s&ovroM+1_hod*<Dx@+I5?yXR}pRq7r@adoO9Ypl>cRts_V+%8q1yhG5O;d{T}Gx
zoEUpiegMY1T2E!gD}el;(E#>`+lN<^e8T(=^9Pe@kW>Q8sr_)xU&8N;m}Ds|D3=L|
zR{3`U!1)f7FTR9f0uV$5jlhmuY$!RzmC@n+z6$-~6cL%BjjjX&yigI=5U`2PG>4I!
z&jC1o2WB#~Pb_eta~}|8GDw`b(Zi>y7>Fdv7~Ft6gr{{CP)WjWVy7XzV?@<?S0Lxq
zoA=JCxP%tt9PLlN{AbbtWU^8i=QH+L%-}KMXVJ&NnB3SoxL_zGT<`-C2~3q->d+NX
z*29TBnT?{nn<}_2LlV>jaJwg*E7;AR=rM8Bqdl!q!;7*xxH?1XlpdH22G~xqmVyDS
zbp>4kIMN7?q|T7hBg%h<z)!rL($dBCUwd{DM92!<A`;iOf-0D3L|F?eOfB{RL?1KZ
z>cwTCOk;v-K`FgrU4Shl!Yrtq9}WoK(BK5M0w6dhJEgUK>w+zYaW&LLTL4jl%BU^_
zU@(k%KuF+$t^^hikTl>r(mT*8Fr{Ud(z2%M!Kb_<HxBnTm;iQOB8ZN3W?@okU~<<Z
zO<cB%DiT0ml_Ro&CVz~fuyqIoW6X)`GYcN9M9=kz(_SLST}z|MQrzrYsS5=LxZ>~=
zofE?aD9AKb{|1zYO)UcZ*#w4gci+Yc0_1MzwCk$0#x{lmaNjtSB3A?vaSXH^g8@tc
zaXB>gbZcH2Qe3=kg5tS*$(J41`FO@E)_;y2BPa2X7<^k7A`lpQ+>xSRbjqY<6*V-S
zwwd(;c?#v_*%37z|I|%8_~8@fdvsMzbv2=fLJ7%vBY5U5S$Ly6Hg}oxvuNsf9o3!F
z+R3+USfY*xOR5Vb_id)X_MT7wXcJ}R3$gjJ-Qh^>hMcMUAWJm7G27h;d}DF`BlSIX
zJ8kTbbOQ2KF=-v%$6Arr8?~AyuPgl(*654j^=Ie;M`U5)*(ixhmcfwx;D8yO`uzFi
z^wrsirAMlwra#fZcb<34`-krWP26U`n|efZC@Z@|v_0Ac%qz%k{#dbReP_}=orYtv
z4U)wNxeiXm8Bf`&=i3VI%-f$d*Ujrp$a9$3cmvZvKW{lP_vSh4i^{XVxh#1`ne;15
zMUYOOBe-J^@`XZR6%Z~&@KD$xx%H6v<jP?Big;&)iiK+N+U2~?_hHM?0%@(xZPHAg
zD4`VH!$AFMiP2M;)p_|HC2Y_xaa>z$*H(&QN3BGS^*6hp#~P4uZI_g^lxg#jK#KIT
z2sB%YE?_xZ+y0kuEXt2WcL4qy952X~tUWX#{a~M}sc|G@q0UARx!gMxLV*@%IuBz;
zNM*ivv@F@~PKm$G+RmvD36g1Ex*6;IE+_nF?vdz+kKckNJ5Xx$PP#K~95nk9_6r6{
ziDaht<~|r`tTo3A>!Cntcnc~`ul;z3yYtC|KixLJPaf>)aMSfSO9<b0)Uq?4_B6Dw
z?KU!%J@0dVMpanJI#=xe9{`v%Gc%U>+1ci8*07)Nft{O7x4SySEzhI=e@}YmjwTAy
z`oHzz4c%H6*$#6pja`0U@6ron!P#?O=rCk>jF#~-$<-({#$Sp`KJ7}%uf8PUp`S3#
z>;BoX8}y4Rg0&F(a;8m_2JeRk!y9yUqi4_LkrycElQEsHCn0s#Mltc_{Nbe_D9?*=
zQG682&nSJ!eBA9_W~JPZw8Bd&tFABIdi_!+#O32#lCs@dPd|RHtk7<1gAjvL^=u;T
zqt9Lc0ay<nS@(Z+voQct$~_hy-zuDmdKu5wBjo=4(2OvXV0y-{SeCf(Td?&@)>}*Y
zs#2v>c=qE!FZrr$4fUj@TPNwMH->$4Hgl#%9V@lmYgR!Zflfv4=b6+I_J)z~EF141
zIT5z-&d$;0sPg8scqvO+cX9Ncmag=yE(SBb$SF_=$6K8(y$567s#a0xB?zv4NPaQI
zS$&db2XgIL&K=f1zD$q^sW75-tTSGFk3$#zNylhQKQGC<9%hXRo9j4G1-3E<d``#s
zOUdGaIk&&CJfA5xn|A5)K@83_R@DX?j?$MOC%$k0zUs1Ps_y=vaDv^aM~|T9mCoQ1
zEb}n+cW;C=Dv2yBi-$<XHi(`AHxD=c(WTX!+V{lx3k!>K^-p|hmai`dlzya>ZzIkV
zy;L-nJAixML4u0~S7Qe8B7>UYLY)Tv6~qQQR0|^%B6akC4ZN(Ec6G`!U9Tq?74<4d
zZD!*r;!!=7Nv~qn72akqYGpO)Fdf;(4W^6-#SK|{E@71Z14xj6qMO@fs!7+Db>T1S
zcbFOWhqpY?p_WLR2VUuOqUoQzaK(c+W|1M{h)ufZt%{T=?1Wp^(|60UW-F@?O<L;@
z^s-l<r>_B5FWKVMMG~$vi^AP_28T!v^rh=wzD#F&uM`0iiN%zn!c6_Gt(<-p<CY8f
ziK|W*6~~K<Fk(S|IeJIA+{RI;L&D|*@%3WfC?9I5l?GJK!?}cq-fdyn^XWepZ6=22
z$@B%Q=12a0aP<2i<$L*${|?j6q%06CB@yvY)8H9GBZ>Yd1V)347u5pln5dtt)31|V
z`FR$yqEb6R%e_;SeCykC&ptBwM~(XktDF5kMwapVEurckCi8wcelcFJ))VKiB%^>m
z?Rg`ARV8(zTi^QI%|k+$7D~PW&j<=*y~Q#z1E71_@}NV1Lye)*RTjo%BB2t~m7;IL
zVWxTGD`4&n2aw=|$4oAI$o%>oQ<-?*Qv-H?KyrapFY34@f4uOBH>IzHS_7cNuYXmg
zyNyI?LM5WXbRN9ZAIi;OfCEFPWT>r}7R+{oJHIFtW*ZBp3=|!#VtK<${<*T!J5>Fc
z$e310;=qtpO?hwgOn^YS89X>dE{Kfvh4X5Orjk|pX?YLl((tneBmaMBYd{4L!cDM<
zv-(bBv%%CXH)b{{!Co%}aSL$<U}smbpSkmInZPHRMnbXNh4N$#h<z)miQ4yy9KeQ8
zi4}V$rL~U|#yQIXAK$gtO_NOk2PMwtV$SFxs8DcDyZ^E-?V!2<%Bx7%>H%=EPF<Ey
zoR^C(<Wdh#=ugeU4WVX}kMJcH;6{8%9v)a?HG=SDj0rix236dFzw{+z+MJX~Zd0xw
zUetbm^s>W(BS`JOIzvHe{PY=*=8m)f=UfzwY&{Y4a3z%tTTh%{6oNbg6VtSb0;a$c
zZ+MV;p6-tqKWXs_j4a@G7qHy#;R1MPny1=RUu6Zqqjg>PH2qwajPW;qm!>8w@A-l$
z;69ANC>+L&cCGakrpYK@jv}$v-%iDIDz=vDUdUj@MhyVOD_noh2<$AxPEYx8FY4r&
zK+?2bJLtT&3+e~Q1j$wVa(!X1AJ*bo)b~riQp~&<aB%^;tR#@55~uoV?>>!(yH&_v
z3~07=Rg<HMGe(thZGi~+N(U##s^9|5`xCebVF%~MdR9CQaHhMEw)ES`uAA~auuk&n
zoATuWDW&T&)lDqkVv8oUb3@5w+LZBpfQhZT;{<NYu85(1cM2v-8JVp#OY!o#>)F>J
zt-X$L`Xwz2+teYTWDTrsCe8BsBW*U(x=QXoPJa3wSxb@Ztl>vYT3O3OT_}|6G^U*t
zYi8mIhZ1ZT(2NWKG?#_s@o@O;&~r6h@zfHqUCg|?3QNTWqphMPG3KLRXxt1f=+w%N
z1xt0ni{D_)K3rOh6cR5iYU&I_C%Mh!c|y~bYc#D`ju}k<P1YRnln^qvY~Q32b4K82
z;B!17;Ka(fl$7NA?qL#r4Je_6%s#B=aD}4j@>N{%7QY((AHY6-r>TO0FOwC6H<V^5
z8Y74Zbu4(Kx(24`R_;IwF!^`5V9NN}e<jIjce^s87$<Zc0GRA0=rDmfrK_!JR><Ya
zfT|Y>s1i4MOV(R8|FN31cSxFrnNUbZ{=gJP(1^4!jWv8ADK0$5#Q>u;dv<s+xLuGz
za*OF;+=CE*C?0RRROvZjQ15PtWbSbt<rV4_3dMj3hc$;?%aooOsr`YcIdUe#ru5zh
za>OZ@Zd3t}83aW_E|BvRh8hM*6<PVAcawyaf^lbp<8P{T5X7BBWsfZ~u{KDM_DW^j
z6I~79p)uY<c@jk^o=NmV`QFlBSG+%L)hd~IFvU~wJ03Pg^AVer)Dl)-^CT7e5vQ+0
zR?MH1+*~vS{ESxIc2x#g&>t;ijPwH=>}}*7+t1Yz?5O&AcdQL6ZHzP%@49<VX?>+C
z7$kO~7j&~`_wI@cz4iRen!@Fnruo2Pd(Pq+yIpr}=qdWZjIw2XJ}vK4*cFofb%*~a
z3vY4HpWi-IwxP32B-;1%IW=j{agqW_Tt%hctc^&<POZW)xBF@1{7m(k>y+TRC^Bzu
zvUA|&@^Xk&#EH9E>i+qru#0z_ijIxCmustD(3}j$gND;|H`ELoB2IAKe<v#)SSZG|
z8BfyV($gaB<41yIt)QHOt-WF#T(+>D-9@Cm?ddt2iOo?jif=pIN#9;>{vl9T$@1XE
zr(}i<Mf`7mmG#Cm0Z6gehAcnLZr`F<>eK1Y*{Qt02#PVXe{GA+uau|=SrpXdil_E9
z{BY#+=3urf$^BVYiPY0hfWPg~Uo257(EGUE`uN@S%#_8Go}FA+c}6r0_U!!8ak3lZ
zvU#-J&Pv_Khv`hdD^>Yy-Z6oEqE|Y0>dB8(vUVQ~r<KNU!cN`8ay}Qym#%OqQ3f^|
zVFKj?DL{hI5T#*xGBWQiTj>(H?ta^fW+^*#Ggl(PQej0)_F1@)#huo0S<x3?n^3R9
zhF{u*p&FPc^?ipFHb$$$%eu5V%{DdHd{1p|EZp90pE#H(jo6<iZ4KW9McDU=zv%Ik
z3b8zE8RI|cshy+gMM6Jj*twSe+k_6@`~MZz#IB~q9hE<@U0$(my3Am@j|*0(#E79k
z{Gg4FDen)HKt(D9G*OIdnk@g@?Olf7s?7DO(0np}qyvK}FlnCu2S~A)>B-J;1mJp@
zrRcy!9K`aMFNe_gwIs)l1kVSzuMeN`6NbB&H2tyJ5S}52JG84$4zD^yD%=_!<!cQw
zH%^*bA6uNHAl<5ey2Q`Fr8uRmQ<<+?1Q#Esqi@J}>r{vq)Wp*dY_ggpKBPW59}9h1
zq<IXDE4ZEU<7^&P`(4{N>0oe`km8bwOFS*g*(rV}A&lXowe-8M!02;nWLpx8)QM3R
zCkHun7FO-~n$Y!I05={itMTgZG{J7$i`QaP$<Qe2i+ADM_d;Y(meq!OuicuOc`WHS
z;yUyKlNIBWY_^7d!EDAwI43e;7%L`sxoeJXm2g@$wBc-o(Tg$Nk{#6p&_a(2MuTm<
z_NlZ#!{i6-NJ-p+u*pC;prHwG0S9ERq#cfoFAyzPiHQ<EMAX|bRCbe7(l(0nA83>3
zZYK*p7X#h-=J6+nTUU>*8&EHvEcZ$Ln?#VE7DZv-c`XCy6a!Bcf5^a$7L7MPom<I9
zvVi2G&v@VvMO@c}8E_%tE%=W$9NLF5or!AX`0{6az~->)ZQj2J%fi$r8#Es(oi=~4
zs<Z9wlYIS~O7l&iLcHZe#983I!P~jOQ<4GMcg5`?Zef&^78<DLx@DJ%>204dFTMnE
zm6BqcDNniVea>(S3*}$^k(AE`RXsn#uIwYT-p>B>sL$ieoA4XczY|yOGn#{oJW}4i
z-Y|TR|8Eskzf1CGmi`y|kwe5tWw*<5`kO`phCjQ+q1bGmqFC5lM6fKbTdF3fV&3Z8
zh@%RKMf{&CP<+wMqztD2Ali~KgbwwIa^l5V=b{2po%PEZS4o=Ari;P!8t<^L%R924
zhHlktgqXzkOw;{rdo~wTeO->9K)y-gCY7FdJDuPK^eGf<tg()JtP|-Y#5enpQQPXT
zYm;qjQ?wzS3)AXsnA;ggN9`Zj$2Q??UXlfsOe-;u5cRJ03_7u3g~YH~Iyf%O$sYIr
zHzWRDZipY)yDS^z_Uj<E>AFIv)&`|*Y_r>z+<g1*P34DO{5!Y57_L9?q_*eHXWX#|
zvo#++3679&M1!f_4=Pk6Q|z-?^n^L`ex~@F5*ml}-eRAxn`ChR^#{{t@y5cHT7JQN
zyFROp?Cc83e2b#V@kNLz4qu|6&s64X#;T&PA!VK#gKJ;}#Ts#_NfQB<!+O+xFSj_q
z*e$NX4vhm2$mnR?jmPdo<KJkVHn_8liWa>3OQghGf9>Rd34GoYg>fHz4>ou<xA7?=
z(9Wa5)+Yh?j|8e-x?i+B9s57*)^>=%?EzhMtC?pA*Wi=rBa1mL-Y5*maHRpaxB@Y{
zx}JgEBL^ZdDD@Sm<f)ep@w&MeMx^LR%e#JO^EDN%5$H|w-6gW_)6RL$x`5{SJI$|r
z3aL-}5eeW(3UH()66<BeF}c(FXitd&*vHB^%spR9T6XGRB2SMC{DOzVSjLNb3kHD{
zuhA^b%NJkD6EFGdkcp&z&74=Yi^Rv7o=lAO^rWSB78W)E<~L>$W~b!05rMBQlU0SD
zmYd)48nwRS7MIH6*wE$KL28pQ4#<g-AZo5$i-I(1Lmf<mD2uXW<SN(|Ot&6MFib7v
z!!oMMdEpJl9g{RKbV>M;a`>U9Iar_-%fmEGMpfkzu2W~&$C7weKJWzCIRUh?WI2J^
z>->d=o@$3)Zy=3{r7jWF5_$_!egd@bRs(RDYPytA{7ru_v8I9vHbXCp^gn=Hx!jR9
zArC?HpQ#(nCf-8g`9dzK+Rn{XObBuU$+hz}BC~HT`aqW+H>^IK>aR@@BL{k)2q`LB
zxp=pUZF)CusCWz6Ijz{)uB7oW#zX5G{FEPfG7Gm+3cfYP^Vd?J*a446qB3!fOxJPc
z>Se{LVmGoK7(g8Z$L)Uf$n{tM16TuS*nGi!F|MqkllZHYx04FSazK~pF-~$LM41wf
zFdj0&RKX>ulGz%23ZgUysKg}FE#$z#OAeF&qwCGXp?duA?_q4&Wn|yQj4jKM-B9*@
zCQC@7FeJ;^vy5bEvWC(mhM6&TDne4qGE@`BR!Fui$-X9hp7VYFd#>mA`{P`fKMdzO
zW1RQ7-}n8xr9tp$@{IRjTo{5&98e#B#1dsP|D8sFczSbp_s9y<SU`x(p%=%6P2`h>
zPhgpByQ>yL#1?DKWvCFC#`F()Q=(Oj{)k(jE=2ixjP6LNie)VcShi^J90vW4!z0yK
z%n=*I&El~nDH<r$5ZWW=O9o02fi)~q_TR^QVVwj}7(F>R0exnPEWC6a0NOBT`yE3X
zAgjhOVtIOj@X@{Oiez?s7-<+gKp@FNK*ia;$)$0q6na7NW*8!E{wD-T!sS?BqJhq<
zV%AK=?hXeCZLFGy0V-|9Lh(*9D$T;3Mf?qYDf{j4UDO-NhBzh#g$@vdH3G2nayN0_
znNIpx5E@q!z$9ssy~_eNJQ`&E4tc&z6K;5F$V+S%UoP*IB1@)<FB44gFikUtP%?>3
zF!jOd4NYUY(SR&D44gENyC=@Ri48;&Ur8E(i-7E#h}kfJxCRID9}aRUByEu)pok-&
zIFbv*^7s+(Gz)K<fHI5}5#hxLaBOrSAhQ<WL0&LTtHYs@LB_@Gk<wIgz{p|kZa)%D
zK%ik^G)Sj4EUu*K`3po>2hcCMd<<p4{6#v^bI2f8<5UPAkXYocNH&o}MgiL8k<*8A
zz%t|*=QQYq2kD8hLL%Y*+Xn=nApk+VW*$pm9td;~350=WZSw5MtCls{;sM7iZDbm=
z=k<@7Ge~~CKJZKiNUnIO{2X#I7tgE@7;d9U8;CiqxY>CXkZOQ@KD@v!T2KaO8a53$
zNTf#!QpS?|2&VZx=fwcaY^T?5G?@b*{lxkgbn2D>G#iUWwt3zUB>h8mCpMpl)VpH`
zlu@?8Zg0qp`YA)r!rgvUSGXe9=Xu}$%?O_gc4ko%h^OIGE_vOmeRgdgYt;*WCOG3d
zTNM1K>cfZM^YYfr45}ai?XJz>H763eOJqz29{(V%@B&Z-=@w_J0WK2KnZ@TL7PjHJ
z|9)On<xH6L1?d^ZdqHuFL#jl@YlC@NeX#;dMskPV2h!`c7k;4;v$vM^s<TS|<;$&=
zbsu*1wz#ise=PF$a`V^K>guij5*_9tc%(92s-C?r=<3Drw-JpuPS@h$^%Sb(t(DcM
zC{bsx+7~bW`D7>OJ0(vKH4(UM(Y9&M94SIgJHL5&2@~3|n9$X(tK~P|wJ#WFJ+1UO
z&lSTprCytGfB2WA`sZg!Dj4dl^N;Pxn4>EPE&9Slsf9Q(_OI8r^=gw0vO{Z1tg04n
zoo$l0Pm$Q|NppK}Q+ET^&-{zfGa})>#PF&|^UEy*W7!vFy_Q@Fs<S_=jhT{1hAJOB
zP3mZ6wvatSS8Y_whqn(|-$6%|FYmm3%{vq4ldSoY&YIO54c@KTkSL(~bX&hvL&?Zq
z1c|(bk2_Dvfg+Fa-375J!UBoCi#K1p9W1~AmXciO3(OPQxcb>CXCKYHug2DZiA%a@
zCa-ve<?=Mkv80K4?d4k_Lu0*A(0nE?s@I?xd7(_eRoI7Z&i7O0L66O^G#~ZC>aFLL
zy;Ya9A<B1js8!{20gu7^+Va9TGh41T;2sH|oi>4Mt`&(b%$GJa``bmf-r_c?MrvAh
zVg3ZpYCFJo)3I=&df$gGkKH)GXqeT+*R3bmMT(542Jh9hqg6oxv$y|9@&5G0{Y^62
zI#)M4u7N%n{zy4AVe;Psn%*~hAHEW?sQxCL4yNVYOJZL`EsZJDYVO3rHdS$NGF=-z
z<d765MOD$=>S_4B399);^C7=&dvo)v2|Xcby>5{nLR*WKBVVy)>q*e_t@j!5_5>pj
zj)f;0Fz`We$}ZgGGyaQ+ivcbP=W6VaA4@P2o{_sB+$w$7@9o@gUrhK8<V@>QfH-r+
z!Kq+-p5NP4lZ;10m4@#M&3VoQxw<3;ru`5X+=%Zo{#sF!uc~d%Ynxs0gF<hqjlWp)
zJJ)t>-+q+=`oTfBcI8h+^YhuK?3R>5DO}G-8xMgmQP<hVZQqRh(f4ei3Oj<(^)}=6
z@#e{6t<7JL8zhJ!x6he;qV^6Z1TFD!U(34CJtp|lQr2=o^qF|gZ|#xb<}9Xu-?&t~
zapC-p+%ON+p>sz5E4UZDnW1pVk^7_uyVa4N*6g86LeFF$NGfAzUNq>8#k<yc*oBb;
zbIx}=y;!`olS8Qs4-aHClWp0&r%2Iqu&6l?Gt3AHCgCjX{*6T3QULl%A1?jtT6MLX
zXJjODIu3tKM9W^IzK@$Jc&2^%#uGo2ABfvK^t}4u9A_z>c+?IUrj%D22Xy&xw1K|a
zThuAHWW4<|o!IQ6AM5brtD&8Vva8}hOV(xd4twwY=!`Rewf~g_zNM2t?~7UptvZXn
zxgf<}UpK(YI`+I?(<Jw-=1APIv-NB6W=xNq*@QuhgZm9rdyOzh%@EVA;DNLY?v`~k
zZ(8zCZffivb4kdLt{IppN4w}bd>h&RQ`MXB;&2Q+agT>q@*}8rv-IJApvE;1z@B@!
z5v&pV1+0<N`$lRwM@hOS5ToAdtFS01(OWnq;1R%q@2H-hocev17R=tm&+}Nzt9UG^
z&qE-yMHsALfD#?NQYZ?}>ou$@d-xZ1@AxOZ(D(eAxhIA>?oH|juf_!+4;!7ap`n4o
zS8aUj9A(5Fg~DddH3HaKbO2}CS4)zUVoMP*fZABq4GxiIDaYM1NfwrWrZS(IRU}@O
zk@>eu?=yeVLe|Sneb?HRQ`MaAQ?7i6QMy$<@mhuD?9bh`vA5|oKcmw<t-8@sQm>6o
zOH0(h9uLq-P@r=xTt0NsBn%i~W$s5ZWM8ZwKEz=&M<0HE_Vm||s^8Ad_336*nEb29
zwIuz34ZBHP)LoPnH7+kJ-~hJ2a;@WW8>#e+sPI|YFfs4o(5|r4=AMv=7|58eu1wSY
zsVE2$LwI62M9Z0wX>Gr%p2ts3K6Ejtto$Z+W$dW1+p)-f4ke-9lIa}#O?OHo&|fKw
zlV+Xq(&BX7y`jBi&p@$riBS8EHNQk?u7uB3qG`@V7RP?mUqFy|IBf-|eKQP6l`Km1
zT>24a&ug9D(xH^>S)sXN%?7T!8ainifm${*AN#u6>V4M_&-emth(<^>)$v_Q`9N}H
zs1|B(?UVsN5v&tL4a}Muwm_T9l9sou`1<s;Ak97;*kLQ5Q}*7YDDITNRCW~TwFOii
z(jcENB(rrbr%or?Cb{K^&M1`#xLo06O{WKpTXt$PPoKJRkMb(KcW;)vF)mZ%%gTx)
zsr5ifOi`5R3Wg@W;XR@dgb+#C3}B!{*9R~iVQg&7I+x=$s{{6<d$j8GU@D}UKK}Db
z?EbjAUCTYDXP2MfY$><{HNMxFfH5CsO_fY_)f#>9YwUngcdjrFsitUt_XwDo@-o~+
z9J@NyaHg8O1lGs)BWJnHSpsBBU~bAf#q4)tDVwfB0uqKW?2M+pqXPxrBbjQz8^AD?
zheO_Ps1prWUqyykZqxeyFoR5Q+}?3&o6ynH_hb<RACCH5l(1uC;+$^!vw%{!=5plz
z3jJyUe_?t)xZ+CAj{(R^-Nd)l=&UZzw5%4eS(-&D8RB=3qPu3vy!HW-RsddgfaMLI
z1Td-}`aB8PB~K>Pq`jdGYE3sqxS?JS5YVhW6~d5Wp+hiPGgD<F9UJR`ppbNmJF}FS
z*?CoCcJ*m22o|?blC2Zx0ttOsu?w|mHiqZ)?Go5D0@kciko28usJ>&sGK@QHtcWcX
z+II}?)gNk_!*X)ci|6aaPM{0Gm~ApXR+@=JsIMYc=!Ko?|KnM)qO6VXl{_dpta6{0
zmY9Y5u2|2Q8dkeisP)x4dB$m(+XLhGI#l2@#<TVd$*l3<15HyZyR|a@gPle)z2c*?
z5QO@kmSg<G??d(doouK|JKny~MZ`4Q!8*DbbY}$@W6K>NRB2U(*{$rP?26Ha`0O@L
z;S?t1JPY=mj(hM2qs=7&e$6VWb)^24%}+N9)cR_6EYNYpo0alw*_6$yJ0E-{!+a6_
zIx8rL;PbC;q|Y&5!ubS*irTMhZn*SJShsu0nd;-pW2q3LQi@d>|EC*Lw^vsu%8c3|
zzi!=<+9N66#n^$Sa85M1>Y_|>KcIqxJpJD<nX4I|R1xw9hf~7Lu%QOS>0aE1D{X{U
za3xKOMQC-PLp@b~+fD~_CAZtDuS&p-ohYCOHH2wvXy`j-UhqZo4bY3GkbJ@lkdKCe
z4t4NNP20<teX={yOZhl6F(B^dZNq-+P<F+>)!dXjNiQSknG!y)0?qGROmF<`j?(bF
zAdEVwafvYVIb8kb;_~SJ)OI(I^+cOPftC&QYb*k2Clb8<Kixqou~|S(TJ8v^YxF)<
zCp)Z1+oU<Mpfk;7B5azVB_BSuV>vZ^{>AeZ%;X+X%qb_1NhTZp4>+R>afJyl5S&6>
z*%W%+Ll|CK>QavVT&>%bsoEp9t|*;4(ller$K<QlL|g6~h4~w@7yf-R(+s6WYEE9l
zoD)?H%T_w;5p#Q8*!m8*P;NMLof%<bu;BcUO*V@AU$*`g4L#i{_LMc$_a7GE#DfB|
zexvr7(9O(xx?_%ecL$E?+0Dy2K7rj6UlLs=6CD75p2!#OZObpAR)&U(vMenE>6Os$
zKMvX313$F((U1%+7@Exc{7{apu0d3QGWxTO)Za<Tw7}Gb+)u5U`jXd3$ZNJQliN%s
z6Zgb4?bCg3j1QyX^P++06f>sHrJZx$(GgW=&m5$>J%5J_Y91uMebe&&Tp>m_;$*}u
zeZ@WWP_jpG`^D?Qb!Ug`TJdjBBmR<p)H;16Jd&HqO@Q?q#oowq-}MN&=cV#ibTLT(
z_I|8J5+W#^x*zA=FHdX`%X!;K%^4Z}r`_ZG$@^tcr<=KBQge?5q|~<~;Cn%XZ3_NK
z_4BMlTCMM77$z+8&$jPhpQhkr;hASFQ+UIg_q8=|Pus|UJf@W6H}0g?Ke8;3jl1Ct
z{O7&aQSqQEkdNop@<Hm0ULU0+{C=gVeN(1||E;so<thng+mH%b_A(24*({{R=f#3{
z63<(dI`!LJGEeMH$&<J@?^*XaGM{~()VUaW6G=UCr97qF0d)O4Vx@0`+-}S=lmxMM
z()d6Z@f}~XO8?$u%vtq_l4Oq;rWDG54SI}vPVb97W?_z!xVnxu9eZ2J?t&LguXQtg
z{lG7~L-Lbn4!!x@vPE~8OwPVbSuZTizU%x&j0Av`<g9m?u2_RJ6HL$fPUmLg6Nk(}
z6=3Zh`jcQ|z(WJN^RpM*TE*D5oK_-LP}&M$3h$p+of=JTDk!l|cK9bH8E1=RBrs;P
zlHHZiyeA7a)Eeijd(S1l@T+{04XGk9_r@_M7W~4Qi%Hkoyw5lle#IJ9#wVKz>#t8d
zm^V)b2j924a69#XisA-+bY}o^@Dg`L3GUQKc~$>=YxRBhtq12GbN}3M;riJt$!AaP
zzo%2MI{;_c6|oRg|AWX#IlKabJ-X&@_W83A_@w&pqYdgQ?2YclUkrbm^TTRa1=IO|
zN2~n4D7i)PHX^oespbTbKF6M&A5Hb~ig(x?Eq@e3^w#-n6!Po3RufY9FDdWU@7~nc
zCZE!OtiE~3upa$Ww8<@8W&RQBHw*KPAIIT^1son{J@@?@RCvQWg$~Humg1@U3===%
zy|(0f?mKn9D`GtkIyX;!2Yd7N-(qG-Cp(ol7xt0Y5c-QjVKnk?-oF#;*$-kV(z?}I
z{C)5B+xBUmioCZPLF<7R+g{t-=AD>OyruqW@XRjk$rrz#msA8u6c+o1FH4^Qda-P+
zl$XqrU(rJ)ZarMmcPu#ND%CZ&bT9Dj7Cv=P^sz!vC4f;4K(KJY2-QlM%rUU1?T>43
z_6@H1Ul>_G8q`dvzhQfCl}f%Gsej9WMQ8B^Q*7Uw17EHol#ev=Y3U%;f3@fGQ4=*a
z%k^C#<w<t988oNV9aPvX+QJmVv0KUU<!7A#K!>Hw{Lx}=fn)fmunh!X@cCzluS~m5
z=HdG#ObRN8xEt?U#5LD?z~aC1CJKEFeCrUA0$d;cC$;zkk>~nw>boRagjvq)K!=2T
z_KzUtY1^MYRI+-#c+QvZ6FWf;kzaY{R!)b*T-}I-%`mrr{f1ns;%_*IUwH?LF0)ou
z{zRD^@Phx23f%KQ<>bL2AHsNC%#H&`bzf+wzavT;0E$x4IK8nmyloYii|$T-OsU87
zpsrNfJs82kn!a{DJ+miVA!rzT%p4?NDkO#t{N!F<(j`$?{;_}E;`M`j)$2xA!VSZa
z5B1Yd8F||3hS;-#ah5rt@#dRF8FVz)v9&QDN;TL1q9tO#F4d7)e}lWcIs2S^2=A9~
zyG5)DcYQYnl;a}UfBr5wF%LW)vImQ~eC81teBy3ftCHtRSehtlloHDstLT(@j%Agp
z`A)KVc9YRaKY`0qP-u^`J8;QDqB%aJ<VJh!0nr;W`*%21pFdoqIDc}iSiNPUn48BM
znUJKYte?e^hq!JJ!|W0^F#sMmZLRY-pm*3oHXBW$#3@V3W;25`7dQtQSnFUwvlJVv
zaXn0L_|1`1@rj*UD|aj?@k){+t5_7Uo@Vt5R1jOZa{nISyd0aEuLD_3;_d)<(|P05
zH`)upf|}J~lj4nsnKOeyMdDCuGgQ~<cv+WlDe8zF)JdiZ9RUSdhe!$i-8GwRJ-YvE
zbcW8+u*rUp&cfY9$Wz85W>%Sec*iR`mNy@W3zNnF9#?4?Rx*GVAK#0e%UoKu1ye5B
z{3MY2kD&xp36_`@6CFu<O7?E?DFk%Z0uU8*izCRsINNxt4gtg%yJ9ohEHn_PdB_gZ
zJw~hNuUfO-F%~gZf5Z%u?pw7s1kr?65Cm54ru0n+JCE02f{*V{3YoRUm@M2`u{2%>
zf>A5bn&x46V`~tK>dB7)lG?UMPP+g!O;^%AB+=|b{0!39_#_bINl%1Oj2GyUr^=2}
z1|=i+OP-_SxbM>aCvhOB;bzu4@hgt8QjUz#^JJJX>8nxGS-_+T77w8Qg)|k>7zN9y
z5DDXlaPKX=8t9Li8t*<y=h#rwUMe$5-RkE=o=M5u#q9F@WFXc|0E@@K+m5%a9@&ZO
z4KrY}8ID&pGrb+r4iGFj%&K^gxJ`s(&j2J->L3y*$h+_h`06i&KNHDqo>ZtNrWXOZ
zKXinYC}8u<vl@va0vD`b_@IK3SKkM#`yYtkl1FUIX1D_+zGdMBL#xxIIFrr8ELl51
zz|vtHk+Lb7CA3dI+O!jIM+spuc@x>Yd^^aQZFNMKE})NA>>3&?h8Yx}Mqqh#dkt6E
zsPMK<nm8MQ$soI6t(9;#jGj**@VuzHJ7gB$zswRqgg7$%9WsM}oXpNMa?*#aMjQcN
ziHN5YAP|ZtRH4<)82M!$=aa=(un`Bq)U#m@1<7uczQO`@Xdoe>@|<}h@Y=~7dUk;$
z!*nLbVimAp>fu<MSu4;13{WzV0`JOh^2>?S8<g6xu;!A?4gdk~AR!K~53H>VL~Ku+
z92qPi{%}VII!+TvxAmwfGy@?)&bvsu6A+DWDggQ9e0=-}%NaI?(?b>mB58q$I^YAP
z<6r>{`h&)WDw6J(&SuU%&P0J|DpD(EQs;2?1%Aot@K%yIU=c0HUFu<Ew`PHY<%^gh
z9eP7Kfr#@LoXnwXW>jw)Xo0?_yJD_B@h~;5q$x3CvyJ>M%zFOUP2b@<#u7)|9d-M;
zUp|g{^gOHVfU}qT`zRw$#aEh@r}dd3PL_@3I4JN7{{KgXhF__fAit|L)S^y)cm*|N
zzpyPMo=(T6(<{m!rpw6k&EZ`IwB(_!;WEn3HtlKm<Zq@~>6|hv{B=HQc0Za`UXv>^
zHI?d@slI?b5ANUduygHk|9rLM;l!lB(apT#`7MEEcl*>^<=<-6F5@6kLY24U?Z|=r
zaQo9M{Ues`Nza2ida6t%-1hUP#=b@m30;+7-Et#MJR;rEHdp_ZeXs4Aow*x)hu1b(
zG)AYMGG~`n9n>=`*18lNCdjo=&wL}J>a)Hy)mP^C%n$os%Wu44`0txq<ol<pErRsw
z>iGV*n|3!XtA$D!3>M2Tvt04by|O1z?Eh&U9n2Ga_=K|J6krwlkb`L<d8A}?_E8P1
z9F`|;_{~UtMe2>mvp)oLDP>1v7;Tmq8X8&sRLy0oA!P$^*TJltZMb|P4+|2=tDM3I
zg$8it+jG3f>H_TJA1SWhF>l{8Lgp!C<aRM88!8KUJ(aE9{sRe3Iu_m@CdLDjU|n6v
zg|nA#=QU=|)M)e6$zf~6>O}p;uFTmj85*<KDTjy(c!Tevh)gh}CY@ye#HnFhqJcz0
z^^1hMgZFwv^oVvtdls~odPpegbgdD3Wu4g~zl!mZ+Ky$Fh`#P}Mw>kGxj|Kl;p~3t
zTU|)5Ck-8%|3S$@&R_9k!=uUMpNF!YHC2J~c8Rc=7N@pzmY>p&gT}O;m7WREyZHUr
z>(`IqlFBz2sE4klKvsM!@W|#{Q1r)(;E<vRP4gr8g~-0zxwo`>LW@lag|Qu#DZ5^z
z1+zib3>nGLW@$(i8q!dqnN*nzG%I>NypZu$cAf?|!zep>3UuxuTu^`PVpIxiqsQ}1
z570~s8~rO@?+Nkho8(b^%RZ5&bYa@+3ZK)Nw!35BFjfKHze`v~;H`ez6C+8tbUzBK
zv7I`1cE#Q$+HOq*YFMQG-8V7;M!wzmLdQC7!+&h?QB}(OpDxB~yt9i{DF&k3gePjX
zceY+kWqoSa!(S!bzgu#$`L3sSS68*+7S6m4qq;R->OS)hrutOA{h20f(NwD!X-s82
ztN!i%Y#LWX5rvkm{Wo^Qv-p7J>eB(0k|z7GUuW;v>)lFH!Gfdo$J>sfTk@%@X^%_W
z?rpJ%y9FyJ1bt-6PAn87&l&~BzhC3#@@2>AiC7C7rq4;HRg4*!rdzk5<Q{xUZEPO6
zwE3iaPUX*j_ue;;{3BPDpx8N~vaIiWOqm$b<DaR)SL4mMR0_Xv9;Af{|B^gRFQWx4
z**i?jPMdRAk*_Zw@Nn%l<yn>J=on}De){r-ZROg=!&4cB2es#>R#v(C{?R3VUYc%I
zo4H^Z#GZ#sTp>kDZBH7X#I@hf6jjJub36l4n<hbbt6Eew`CWn`*MBx~s?VT^N=iQV
zCC!gtw%)Nia_+n1n4O5as^ezrH8~TXdNm<O%bg?AT$H-xa@^hjH&s<OvVYZqz!~+i
z*qd_{Depg@Jg((k`mEXTCI8@vbb-f0yfI7RO^#D|y=%12S2U!Wr@gosq_^0_aB1O@
z&YGRVR=HWstBz}$gL-r28vd<IW7$q_d1@Z`Vww47<g|r7EcIuYewL9FUICm!owbrv
zYKgljUqyNudhwCrZ|8!P{3FyW#N|shl1rAB#_lg<S!|bfs!13-&QQfL`!gkb=fX_F
zc_6(Ws8?l`3R6_sy~-~Xql%)h9>S*)onFt;2-Q#6<koowvbj;y?C^$nHU@F-PHjaq
zsK2pn*`&JDdt~R@=P+KYt5&EFy<8@xWKLFJ`4q_xDY<z_J9aLY)7v5tP3<svcNY~S
zQ^Wz$n6mlR{cORwtN2QVXhzPH^KZ+jn|}-yrOGm-a=Xe{^IXi<=zT8}s;~W46Dk?u
zOj8p&;+vqbGCtM+9H~&MnSR?hREWmc=s%hH5BFHcd117*__EQB6c?2`8TItwDg2{r
z+UIn$eME=8jWk&?6gBQue&6{iAk`G}VJ25UJ5WI&H(8*6_SKq`rMQOLCo_FH-{LFu
z3Y8Wc+5B%3fw^DyF*!v$cCPa!P(Ow@bpDciP0-9oG`m|&5y!s~dU=0`MJam~ShS;V
zg}QjMJlVJCq?$X+mSdm0Eb%r&e~;4Cose9HD^9qaCls=w+%02zKH|Dl?wR@N<l(V$
zfbGHLJ6*w*?+Cu0TDurhJeJzU3;+VJ&fKcbJu64HFc|zJv;;!2QO75ebKJ|Ys}78K
zW`o2gkY8?29E$#|eUktdf=7_{$Y2~3On2@X{>%rW&MM;EY_XhjEz->R;}5ede*G&5
znY;{^B6e={x7`ZA0w6N73|+N6L$j>v#aLmVVF3C)=WVt=3d1n2u&;B&s!@m-zB88R
zgTk?TF<WO6MGpzgmYu8y34y|)aS;M?)KGmZ&<H5{^a?gJI|d@QgnKO~t)0o^rPvNK
z56tCTlPk5hYo%Z<;?!+#-nCk#K|P}=+yT8nC#;?I(_51Cr!6w2!p>di!~n_hekT*o
z*D9xrUgGEJEjA(t=(Cr2UuX#*kfl=0HR(lXO6#nP7>mx82tqtBwI2=Td@K-iba+3H
zxZlg#A+1C4O}3Mz=W>jo?3o##h&eJUdDGi{$!eKmgRwx8euoF(c78Y-RtMJj=*)b$
z`aoPTlqSt)A0V_2H9*BBWvQ26e@rweL7yQ=#<8fv!VZx*JxA&Oyk*Qd{4AIuGk=f)
zA7H5DYq}*ckY0Z}6vS2Az4KsL=LqHg;FYpc2uEY)uAI+vt@d69earpZ;}&x~;?swZ
zzPL|)bGvN3L~_badX717KiyVV6Up?Qn@b+HmfT<FTln1BH@7{4Ar_tnnn5mz#5dAd
z3=YpfG`v{meoLM+bi(8hx{YeBM^Da1vt=cd<^_}rCp#<Oi;&boG&}CmLNCk9l{_?I
zpNokyMZ|4NGByqcMmasZ-1>m~xqn!Y+OHOE*S}*?zi-^I<VJ($sNd*mLLVx`_{Z?!
zFwWOQg@_*+U(xN=_4DgVBF=XLgni*N-Fzv1m7~d3po21k#Lkz`&67aU){RRTdI68S
zxzK;0JvxJkf#j-bJ;vnD$hitBrDVIs=WRK{^YkK<xm+$WG2C7C{EgtgbrzWVS1tv{
zBEHf%r{bi&Wg+>35*YSb#)?&b2~;ZInz(}Kamq(Q`zk7{1hrJKTcTL*VSA*7xTXWU
zHJCc@cy38yw@NOr2*eU7uX_}Sl8nB-WXJOt#n64+)^piPLB61kCS5I5)4yiE9%iQ?
zu{(7F`*xFz!#jRA81Y`3F2?$$Vc+}A-efJ?tD`1qGc%<mySaFWEVxwlJ><CBcT1Pp
zUF<Iap5^g$e(+6klm*CwF<jfk<T>fDL*_aY0+sLFiK&nhb4=>1V$X3$JcV~(wjhhM
z*4Z_?K0+J~ho+02UV?)jAaCo?jD*fVF}k9myUXD|_KtT;WgX~J@M<*tV#~UOLtL~8
z*5+FjWEg$Zy5Q1f1^FbQ?IJc)cWw9`PYiwQeXMsQ%PGv0GtvCb52YEuw^a|<tS7YQ
z*MH^g*81CZIM&7<XJt$_GPX_jciEf&0vlqkn|K^^4|nz~wuDX(-AF140^EHA_v%C=
z`op5W0Y;{m|AEpJSB8VaO4a`2>>>Go-i{2KMCwj*HPtU{3WNu(+FWNk)N}xu%>FaA
zh|W+4I_ddt1eU4PN<DDJ@_~AS`eYZ{9heR)j*~;mrXSsHQYP+b4Wa*6-4hnx6`AQW
zbMP3!x`IFQ{CzfC0Ft1n-S!64wN||V?zw#mUZv-TL@Mb=Qf1UUj+NXe_mk*@>+i=F
zF)QrMr?Cx=H{hjlmkzJk`B6{Z`=-0;SLRq1Zfxd!5Q(dNG#&KVE7}IOwA~Z&+MOr0
z>7x;q_?^go|8g6JCY)xtq#(YUmn7yvt!d7Dy$#`dl@wBk#IZzoIkqH+L7;><6$|;M
znfMIqvLZ*oT#3LV?LNaSdzC9<Gbl!I)$|wE$L$vXOz~&8egE}aN_=dn_KqU=sKFkd
zH;#WLi9y!Axo}ys(2WWyBCy29EW@Hu154JjQOoz~jD`j6fnmY0HC*Vc+wlNe(FNp}
zf_piLD1J-ak|8|)4`lP2^-F7}?`S1Q2F&!u@_X_v&zRLNmsph~R<Y2z7Z={C9fl8O
zT+JjUMfhR$wOR__r|(c6UNnxyHo)2sSAtUZ_0M<$SV8JG&F5Nt&{&1e>z7%q|NOB2
zZ6{e4({YysYLgPpj#rmB-amM!-2UTX<s8=_bj9t!NN&90%ue&wzklk@^qB`Ji=*&|
zKyOxtt3=(^XfMOf(Ol_`8M!DIrtvQ!DqlW7xKnXswRI%PkBR>g^`t(aQPN~O-e>by
zr4h<XTj#IfaS-FqJc$AKePu(TY~au}N99dsR?RA%#Fw8r+$fO}yG6WKJU8)G=ZV<5
zu2y>NmO{@H@0{1lQoG;Y=6rG0Ydm7Vt{eySntC2Sy#CgBMWlG`Ps8h1&%PEcS}i0{
zi<{k*L?k>f{2LW6nc~^&|2y1>1Cq&?ekV-_=BbSEw6fCEMuK@IFcal^O^D+c{2TTk
z!aLJt4XZvXZ{f-(n(oKHsFY}}e0HT(Hf{1}vKe;NEevRa(nD6VDigPAE!s*<(hA=-
zO9)RY$o(5+nJxLD`4logU8a}%QmjFN{?gWe7*Z})lCp{e4F_Li>wIXO<r?gDXUJlY
z=FGcg{X%TU5nPIF&jsBCpM1b&{_uPkZMz`RIegsM5wlPF$Q=$O$`Q`bHqM3g-pk5X
zM8TClgu>F+#lWp6P=<FNJg3e2pM8&YEAf9V*jeYDo*k?uBhGavR&&7+9oX9acTbv%
z_60;e`?{F>E6%|`OPxwFOXGR<#$2||gnV?E0Id!EtS_HJ+nXa^oZ;q`j31R|$|}AP
z7x&%z2lhCyP}k_*;^l$Lc5cR;kL5w%pAnfMd&57nZMKjV#iVfiz_I_=yI0|#yN5X(
z=Ez@9sBuIu1Kt$H@4b|DkYSD4{Ziz$fTB+IQ<1n2nn^q?ukW*~Z>tzwChRUX2Q()1
zM}E2Ws%Sn}6RGmBvEMkOE=d{i*Yomcm!<|bhF;bKEG;@og2tPQg|~Slz!H1pM*n7^
zzcD~8IY#xq-b+|r^#$ielG_#Tl<lfdN8yHO(}OwzIiQh;H_J}va$B#WXJQ0%kI`kI
zkLNR(Kw&bBp{yM<t4_nVIf}eJd6KLhbtv9W&Nn<AVc&%2A<0RKQJO0~`s{NIRQR7;
zXbNCC!zrtWT98$tLIyiFhr_(U>G51&wHiFiiF2Moa-@%wRn<=++<GDiGZ3);zuT}!
z-k>Qs?d}r5!pnB-YHD##C7LUUK3xLyZ!18x?SSb*0Eqmch8fEfiCs|XC3=B~hOvky
zjv?*ta1x*W%1<1tAx)i)RXmo!-=j~lhbm;3=W;FPwJoEm&C)6*lvP_*P4PqWaX=4~
zcX$8;&-5-~YvR$9Fe-%8Y1K?>Y1L-3*bgfb&PI668W=`wa9K>|`q3i|_ZRbrL;^Zd
zVriW`Ph5<G#K_b>fn`3s*l8FSl~@3zH||qkCscxgMTO^F4iy3_8n7<_sha>{>f)##
zkWS<tVRzLkFT07q7h?<B28vG|yQZIw134Z9M<x#W@#$JGIuYv#e$cr`GQ><j0W&3A
zh^K<2jdsW8vtiV!VJrD$cFn(zFjko-&0vONI$qBSh|t>J+&`j6K*Rv*5l50c$TYV6
zNrSavfKc(K1>|P-u0P%}b`^1EBGdOcpq~<sp@HB$b*h@Vu&@<NGe+K>Jz|9}v5bfV
z*@_MQB&!0xND~?eDoi>KFr-3K9>oAspWJYGLN?k?JOK()$bNg*DSxs~9NGuzmR2d<
zB!PhpguCa~35-*HK!;=yN#WHoMC<Ppd^r6}nk1}FuXI2Gzhwo(U=&F#(WrpL-A1^{
z2Y?9|j)sbN%%r$a&@n*fSnO;Z&XgZsM6FZZ2s5`@wY_mTgg-+}L2x9$em3!Bi%=Q|
zlqC6KKjt5AS#(GV8tp#aBOLKt+M_d&3DDI+x^EqH1}TJ%T(M5lQ(v|ESqJ6^l+l8l
z3#DV3TlvS8^Z&cdETM)0{o<g3v22rh<1Deg3Xp@4VL~PAi&gU&8WZOc9wDqNhRolI
zr{ED*RENMQjW~ADKaotp<%hYh5eEc1hUm!%R{EnSIBO69l}u&}7^nwyERZmnG|&v}
zd2>bFO%N$9@FuKN36w$8#>&FoTZl*&{%}x^1%Df|h=YRq;1NUuahm`pY#<aM={bP_
zZ?ZfEK>)uCD9;Ao1|X4*(_@E%458v-mS~ejEO$VUcm^br0NR<r!C2uSe~5@)NkJq*
z6%yxE3jDwg8%u!r$Sh3Kg}fU9`DG4`<(CndS>fgRQouKOK^YvZZ82s-1ZENeNoRm1
zEcXC~Q_<@%G+G_O62Ovdh2WUTOhEv_Y<Pjw1Qz0CHC-^sU_w9wSjlNLf~KR2{-8cq
z_}Qs-5ca{L*?`^M749f|26wGw<Os%7$aXHPsmW3Q49*=&xPdcmBbO(;Wl-Q#SGrNw
zi%(VMyywWMJiAGJj1WY<#|^k>c_wBMM~45y!L0woeA40D9nao|&Tt)aj?>E`Km9(p
zyE@g0=iNL^TX!<pSy5gphFfWVF+T$ahPP`2M?=BWD)odnE<v$KGZ$!&eQ01$3^n-}
zrTwgqT#)l_Z0qk-;;O{nAEd%F{))Masv7#vsLG0ZrY2X(vY5xS%@3OH_GrLwn|@_I
zO}&;DTL*#?jdmSDaW2LW6mVQ;XRJS6R8<Rdo($CV)i)3G(w|S_9jLtaHt}k<&{v2A
zWvm?I<SK6=9jPeV=K1<SHJo~k-aLGCG|2nvZRwx(n*c22=@N6c&VKcsAF;I9Q@Yg;
zP5CU9>&R1jfhEwe$dv4PG8Q(xRj0(Edw~+*6TvMg8@B4)eD~^~_mMgr3Y0)Pe}3V&
zN9s30`6q#lPjBS1t;2eNTX0rDz-oooq-s^GtS?$%oH@!c`(KwNCp-rd;OIq-l=1Wy
z1TFZze0zQ7E)RE4tA*N=GN;E}8~EKEumfRYW!Qq~rFP?U?+GTydeWmks0Q{7nf#Ph
z>W#m^bXAQz)!2wK5M{(Pu66C=+P;rqj_@}Jnw!RVn_&G9q3t&>;daGQF3(Ixm#)eD
zd1%ETZDF!2Kn;vmiH+QU`b_iUwC<|sUaTwy<!1Ft-ZHdldH%1-2I~3Cu)&ebw+%$P
z2lLXFH|?DB17B+nH1lY-K)&1zj|B?S{76<zwh|h^UG}^Vd@|za&$60fkB@n*XO(#D
zchmeo{h{7HsQi-ECw67~WnYI{LUnn~XDALjVRfd{S-4K79{iA>o>%Cx0W~`LJ^X#j
z1HAt*)>mhF**sAGdSEbIZryCS?3hc3bFX3vpJ#6-o$oQQ@cs+Jb8iyAzX3kh99rL9
zcs~kyPP*0;eZzITfrDN0g-i$LBUf#pm&A6HRf&2_K=xG=uhOEr%D_LqD7$Q8_e2PG
zH{h|t>r8lhfcnDxF-&>)C&MKQ>77s3&j?ao`*wrzr~!D+M0F)kRs4Obr2Lx!(4odZ
zyJFAZ?wt8z$F*N6A;(PP$S4nC_l2XSbjm|J^ln|^Z16t7X~uhLkLTGjy|mpT#9mJv
z%C^$lT_+N`eERFMv&62e@-0kgpE^G%k2h=|CjEpp3a!7mSz2e?cE0^ZXt1R5yR4+(
z9Z!$XLewpyYLa!ur}l8ranQ>9vxhdw(TE2s^u@u~!&n)`Bm?~4;j2RpaE}$03$l@s
z#xc8EnJYD3%B}r-8fR{A^|;-e|IFaQ<lkCpHSrDJyAU_7WS(BR{GJcK5|Q+$!>^lH
zFwpX0uTshgtrma3g0^!;;f^cIi)&xQfLPq=jg~rHTC-2AvUUGG=l6Qa<C(ZOAFhf<
zdpavnZAavhmv|WQLdkj4_=Plhb(g^?XRbP+Im=xP=`A8oRDc-h`Mje#T8T6Ps$t+`
z2+)w`aAq6(trP#%6rR{?<fA>x@%nqN9`d>AEa<N<>v)|@-ozb;>wyJD0!2W{(CG7_
z(ZRLIUk+te?(z!1g!e1hN)4*!nlCB;_&qMTC5O8INo-x*4k@m9RhIp|%4K`SPBxkX
zz!{!e*sXAq(%GXBv%0hx$ig&f!E1%CAY29go&!+YXOO1kj(2I_=eTq$%r^vc$Er)?
zcolyZtk7T>0De&=7oryxihGvB*1>%FJIa<RY#H_(J?#$}rb**;4hUFu8>Jou3=f8|
zo|sjd{Ol^uNs1MZxL_T`4}jFI1#Bds45g_ToE+FN_LF#3L80^@zv7KnWbNgh9!oxi
zxKTkpgP*|DyneB$8b;{ozq~aYum`iOZ^(Y-)xLd_y#4BqpYAj9WG!W00QYZ@lPaEE
z6|559!~Gv9uO`}F=Dv&+7w(LVi(U6Qh3Q9sDp;n?%!DSurv-M<+ngd_J(Arv<K}8;
z@P_Ske@)g<Z3BDNbX7Y(VM*CW0wdaTsR0ho-YdIwMs}iTfM$qYEJ7&I@eJheX*?^Y
z6()1VHAsg1VZ67xkIsN~)YO#<ZN43+5-t$<*NP3K-D3i8CoM&1{L-zlSN#tmUUlhL
zm=zuYZ!m<JmYM)DGD->N3S%y!7tKK88i1!Z!my;pe8|&13PU~}%P+iU|CI~AAi}VS
z6@>WaxO>u55FpgV6R{nHuFeWDy)cKO*#<fcF?*DGiQRhUun#N9D%K8|?H*)U@HG^q
zg0ox56fw`C7n+Eh^hgQZR7`+gDA^sm_O_&8pttDk(h5p(-HW>7JXZV)=zKhL)uPVy
zyBO-2wnXO6YQZBevqBQ##O$W~m20-(tz%de9)a#W!XQANdDCwa6l_N1hn}x3(iiVD
z+S&u7&wrrRak%0|j(+ikY{mR_h0r`<zsOtcpSsn=Va|8y_1ekyq6uhD#(T`tCipO@
zF|I%)SG19PRJ2|(T%)3<AUx4Cf5nu+3`E!ae2yvarGJH)JOE0ZLizy&6LA;_lmLsK
zq0iwR;Go*hd0eoxvGth~bfz8v$D!wEI^jUk?v6SY-0uqfa@|nl%~HpevT)`K#=Jap
zH5dQ@6`RBIaw4}AoBSb+3=5|bY<8qwIOI;#TqpO)m&N1<Db`%#u|%U0&_a~eS+m)~
zWZ@P33VG`tS&ok?ckaGaXUsU)-|-6;m+)lm*ZfxaHx(VxHEV*bzq}rf<3A4=!t`>i
zt?j0wBt!~YW)#&N;?Bq+K?-4IuJZY10(#z@^LS7IlGU1ZjHE(?zrKrP)E3^b$wak>
z*#VR4YZxGTvc%Cf9GL>o+-AV%R(Z9Nz>wN041!ZRAu#4UZZs5aBHLD>@ilhUGPd$^
z5v3Mq(V@hd2<>HUXjYA-FgAg3h6wnKW+&wSk)se!8T5G?|JlZT3U|YY@hzRNWKSCM
zEP#QyRmB&Lgi;MgQc?glRYFz@W6u}24QmhAqo4Ec2t1?w=aOJqH97Q~IFu7m&fXis
zzFn>{2+OLF`U|*ikr%}obACCU{B{n0%kC=^F|qiJW*LeWf`a9Es;bR+^DSAM^~3)I
zaeJ&FdxFD4KX|v`%?%mr)H4}Nhzj_r7n>G1EynW6OYOSL?(&Rpt{KlXWNv6bd5s%M
z8nyuc^~+}pd)!^05M<9{kt595q1ZLULdiXN)6M%&O662w@OwP_;M%xgT=NK})t2En
z%R<RJ{v`Cv&0AAO*Js5>Om+2YZ>6_r?Qu1He9!cK`!=cQs9(Bn(t+m?;~+H=@Hzw0
zY2-$8RlXlzh$aU{Z@m2J&{}XLb2f<3co;UfX7Ymj0X%j?G59p5p^APbBRGwXDEX%z
z);s67ZZV9jcQjz6&N$!{oG<c!pUkoQE4y2tJ+L3&)E8{yt}<0?m9rQ$_F4CL_bEKZ
zkS3O4!QsE@@ZoWhW<vQ)&c-|AT!F!>hddu13vEZ}`^mOf%pZ+SYa~=oIuwE??_SgH
zH=RK54_5xkOGcg4QKv3nCsb~&nNJWP0CTO^f?jlWvPL9vLYo1Rfy*CREKnfZH93N)
z)}ZuT&>TFzfH4L%$mDgE%r`Oz)0d`jpxG99da+8e{$p8nC%@bFFa5xh0@mjL?eKID
zYLEbJC?J)ng8i}Oc{kqR?sLb_ktz+}A3iymzJ&i%F$%9S`S-bUykzaFU@33BmT#+7
zl7#EaVmvd(Z~8-UnH#a6T|FOp^87?8<?Z3X>|~@7%7Ai`cdC^fyEP`8hxV0~bP*!(
zTszm0O+dZ-QgcwuzNs{jrMLF6^wlJlcTc`?Jy9m6dPDc!_Re?oHy-ly+Sz|Q(4%I@
z)-CQ-|I;`7KP<(kTt5#7x&In84j5S%k|5}dkUn0uzlFbQJPmi_A*-G$9Qx24j@*rm
z+h~~aQn84bhbnK+T3THCHl9}ZGUemW??4m5xcKt6mGSptA;o-XO6q_q4T!D^96N=R
zWX;YcFo!epx|GNW_2@H{Mb2%U^=jE@wt8~XJ9%8AYE{4FGkncX+Aw?+n#non4w2NX
zJSgvUanlIz&flOJN`Z4h2aFFc1n2HZ4Uo+vJ;I(7O6d<dOFu1^{=(246Wo%w%~{9F
z66`T0YS2cJaxn=r{m-7e$E$qx>(^^DjS3n3<9|&pjSR|`p{1QZR~ow~H>|lTlS&CR
z-`hUA#?Mv1?Bv^W8LzpS=sT8ToQ&$fSh<}RT3WOo91TAfEA<*-P#>Y(N%yCh2h}|G
z@>4KsVtX=ikIz1u9hCV%^wGkJeE=W7gT`gz2BV>(=3U06d|;;$Yge-SA4s7hrh3WI
z<ayO!ATTOuD3I9X$?;K=tlCLol|%+<HB=aPv(n3g9=L5U46+QdvDkoEJ1&p&$|uDr
zi5KBPQOj)<zs`}1n>m<2irOPjvMNE<j4-!^sVfiB(yLdhtacTi%J_}QQ5noGhn)94
z7?^eNV2pdG=seuHy5sVYOIyL^ymo8U@3p_f7hlZl)|tJ`^!-(3^jQQziyteFaRV(I
z@`&jlS-QRjIqe=wjHR=b41l)M?54V4V1iRQ59D(d-E{wTp9(bcS=>fpJ^z)ukLl=?
zOGrPpsmP2rcE=kUGW=^UOSTs}UUg2#E!#B6Jo-+Mj3S-u>v*sDQh(5>**epSn<&Fu
zc`6e9_<fea*2ac;Vsm*##*%MT#0+u`(nb)&#g~1N2Q76lK9NYv2b@@+l+xXuiX9Qa
zqthQj?h)^(xdQJ<vN(|GJwp>xsJpO3F7K2#Dt~eZDt07->N&^jeRs&h-Kzj=?bQKY
z`ME{m^udbaod(JXnW!h3!@QiusC#=PFLW0@x3{q8;^Y{aD)F=;7c)!-Np1A#3$Iz_
zY{L>N0qPb37`Q=m1>9kHkWs<=EU7*?F^571U2rlJ^LEq)97Y4PRyp?2)m3Z#IAAG+
z=!_=n5``I)A7;*F@&g7a7N|jzH9{H^wFJ38bAom|fONxmR}P2M4UUGnO;+e7Y+O^0
zj7!-tpvnMH4R%4#1LWqnh+<nfwjR*Mcj)wHouw7KP6$Y%h_p6w53@_GT0yY$1bQw3
zd=%r}%%usec;1S6%rct6I29^uG{W4uWA`T^z&JyA#i~^@(3>^IPNBruJuzHwnC%0>
zBs)gtiIi`hlvhFP3Ib?nkuoj>C$E};n3nL?D9e}wf@yM!%`hE%7pWN!Gzh|rhxUxK
zSjTdUvx`w6aXUa_B7xz592q6lOWqam4Or_(EKy`~aiEYrB5QpNQFk8r^n_94Kx&!@
z9ikYXM|_!Aq669^3<2P0LSlDT%r(vbWOE4*ga!y@vgpF^Cq`h*0kTRm;Cv#)?H-Um
zfZ-rRSO(yDUCM?E?*cw6FO12-VlMKZU+$SwYaMYIW*m>EVi4?cbcyEyzo*~3>sB!Q
zBtwe&$uy7{Pn;TbAkL@>M5%*|9jw~m?-;W)>DTKL>tU=W$pd7G=NJUlKhqZ<a{FlL
z8#46npn6;sVW=1n!vdWoCU~zDnVhj)c6+0O0_=P<BUZem>1N69^Mn;mY9K;I<zg$b
zPEBwV2xp31YlC#!4(b4}&D<j~jAf_PDJVdECz3g=xi0D)4YF`C3hEFI093YkoYPO8
zV|1qH0U;c%h7d!}<#rGFB#D^V_nImABG^1+vkS`7lfLE-m0)n*(3$<E5*Rq_=h%}d
z9#8fF1qe0~gXgvq?+63zEig-IELe&T{)2;-zYEx9#6bzb(ZhHar{{#=uo_FY8FXay
z!9wRAWBHrKtI$veyYs5(Gjqwzko#K}&1&q>axA;Lg*y}^gM|`-eCX=`R1%9jyWajf
z|1)`+seq(c&EtkT;haF1r#w2qzzMJ<S{oJc=Kwj?lBon3f<#`UV>z7wr<Nnbh7}#y
zt}=tfnI)|?fj=VoP;_E}PbOvz3%0Vs+lo1YU||*#O+YX@;A_BKP9R8qmrS^l9BAXz
z+No*tn#5s)1C$<_UKks-&JJfvgoBg0&RaX8EZ1yly<K;aQDjoJoSq2uf5j(k>SmBu
zlDc8lCtdOxBy*2dtq<rf5D`_vrvl*%z^e8CJubq3t0UN0;Y~g`(Es|&|8EB_MyBmS
zd5P8|?ccQ;Trq&|u^St#rF|~Wmn69}C@obQxNoWi?w&ZwesZ%PW+fMvda3U?P|?gP
zkoEpazH>`Jz01en#wuOu0ogylc7$9y%%c2Q32e!f>c}#R84xxa9r&=Nq3OLpk$Ug(
z2ggrFC@;+2g#D`LUo4X!eB>Vef~RcamKx%XBSs?a-2VfC((?mYOXGfy$J+^}-yzr(
z;ca4*9>i7EE6o~+Hnr8O+yR#84`husN^M6Z&uXFlTWzd-F2lZJx?I+SP3H_5yLv^m
z387CIwW(H#?%&hqI0}9;^~)U9_`UOa^lRj`Xq1Jtd0>!A5^8u-yCs~Ow*&PZn7vxP
zQR#W4<T8FcA_%4Rg$O>pvM@eyDz_ze@u;KU><svQe@XeP2CeowvsakVjjy5h7<Vth
z;dsM3gU#P95_X+BITu>C$*`Sen_Fj^>~76o9kzWwYbX|7vvq8|rTm&Bdf)Ly<Bu2b
z_Lb<zy7MZMmi~hwAuPe0FYHgm6O5WKWF*3t<06n<;HN*C&4+r?ioCCDE$&ZI!ze!l
zynPEr#nc6mN55^p3;fD`RY_IQ3fx}|PV!)I_I<qWQ1D_Fb1h-xqfOmKyMLkYtPq|r
zOPKj6{)8OuZA*jQgDPL?1kDXszpUsRYF#=ss~hFhzsDJ;d(Uo{_9uz7MIkJFt3Fe_
zdN3i)SB2D<FS?Suw(fii*8Fo2rP7u*J}>18u89%#7@Xt3mhqj(K<kEF>~BqX)3+-%
zn!2dA#M562dE_fsm=+WxY9Dyq4UHAJHIf-6a5W!&8Yy<X{->$-vL-$VT)ebXW!X93
zY@wj#D$K%-p7ANXdUx1CR~(iMzms7U@~K8Y&F>G)l4*~z$U>NMBj1c?f_F`4zJVOq
z^0ECt5Jz|3MBv!#&7a+gS8tl^++A;gwLJG`ovu&6>ZpgcJnliC+1BtEB`*I55<SFN
zkL@Z1FqsTR%Svxt*Yx@*-Ku_%4TT#^?~W^cEC2n@qFYj{DB~+t($47}N|hmC&?9*w
z-SgP`4Xy3E97$mN4H{Pycj1E<ih8^CIUg^+39j32IyiWZ0n@?Q(a%*Zb?#Ho?zXD(
z@%HnlGqlfD7q{ICm#@#MHBh-#(OeMi_;Evy82jj!T>jpjAmZbQ7CSm`hF;4J&nI02
z=R9H_nq+J|Q02WbkD|Z%D|6L1;KwCdPF{19x@!H;C}<sA8h7+{CUNmM%=m|QU}qOM
zoAD(t@%aSCjZ34XxAz<rzds9)_0MyAoTxqyKll++{Uzyp?z&_htdi<?9u{da)G0}h
zJ?Op;&WalX;sK%sk{ZdM*%u==G6na4vk*fdtE&>1oI7mh?eaZ@{;VzV=N-63l%Jv8
zU3S%olTfN$+5Tp~H6UuCfUH%&n)$A<p<z`}@7KR;Q;iC`opUdh*dM=tgBEX=jj<9I
z4+M$3?ex`b@fFi8GbUeW@?D)OlS<N!((OXs!b-2^Ie&mDbXdzPbU2<_V2m5ta=+Yt
z&K}ca&K*N@;B2?oF?P4T{2$2o;T?qRR^_jkzTLNZUd&PW9~o^(j2Hlg?$%#t{F-jr
z3*BhPT@vaS%`yBP>!!cp?DMUY22wibb@3)D+W#GlM~)s(SQvFX!?)i!pmpnq@53Z<
zL&g00YKgGvXL96TL&aL~bm;2G`H6DhQtJR6vScChQX^fbB9CT(L+@6oxy+G}LNnf1
z059ttjKN6Ve&%Gzxutl=`n=KvR{6qox!VCJu5R(giuJW;DF`lEyltMz*MK#I8@E2t
zIt(+ZVD!oKZ`L<JdOI?5+bixBHau?+U!qs})VqJNi07kM{6D0<Wl)s=1NOVHG)TzO
z9Rf=u3(}!dOM}uPA+dBwH%PeBA-GZkOQ(c%w^B<<N~cJ7{LcM<UY|L0W}X+kVTR=%
zc89(9`hKp@rC>r`dQj~aR4Q4{73s5*cHRfC^*_JZH)L%iL9={YM}121#LBp}jrk-p
zz*Sf2tXnD5JIJ)xWg1dj_0o%Jr}5VYgVa_*Bv`GfT1ghgb$B&N@`=IC6NNKETe&J!
z%kAUB^M!a&Z3rK&8!ODN;l?|;+@C*nW0lp*|BEA9VpM9HE3w6zd&fSYA+6>|f+8mG
zsZEKPdvdkJs6$<r?^;@+i^AGBnUtC27ffSJJO7}<3MCZEi#2P-?>tB@#ej-h`N1+-
zad8%)G7?jESk$#}amAGNgPgL{M76}-prO~a%(x0YTU(*G@lcF~H6w<CmhmFDh{^K+
zE;X4hcZNmzepiE&tis4kVk_5%4miIe^5mkCnf&%~E5*s)=mzVB=(n!t6+1mBi|0`P
zasN~GY}wt=P}^)-Tv!gATC?cR9;?^t>o|&TZWk~-ApJc6puY<)*O*KA95@vzSV9u(
zVO@8kA6-o;mMZoCYaPcy2H``#gF0;^*&_xI6k@~=Af(zR01rFiy)AL)pb!(A?O1V?
z-ZQ!OQ#o0{Wt2|Ei1x0#No6&`LAAh_^Ks_^Lqy`Bn_>mD@y{}4#|!OVW~Qd2(LyJ|
zLZl%FYrm#-+D3d@;M>Jf?Ri1Y%yqide*>7(YR%zaw7C{$(2YvJJhMvko#~qtM6=Cu
zk;jB_fBbP=uc%e|p17w8C1k?S1rMG*{R1z8aX#cCC-R?A!DrFi-wlijE}7FEq*ok<
z$9?BrpZ}WvBpcpR+Lp^GP2>9LS<{`if${U}sx0bjCu}|n8t(D(fh^oOi;a-u!=q3W
zsagFv1OEDoE<B4O@IJ!EwUk3<X<Y?*6C5sgMQ+H-Q&ClwdXR87!q6KyYR+}@-Boz}
zvR9lw*|O#b-o9#v9au~z>5#z#>k<|kv%HuQm?K>GcF7X;35R42-Bg=BBRm>yxwBN}
zF{?7Mg^`;Q%N11EqG1hA^LDb6@{rht`+JqVwUifHst_Xa4c30VKfZh1-s|!vY=cNm
z{4d|{eiB?Z3r&Cg_+WaKRR)QFc^yy7ybSvtL+6PiCgtk2#1|<wY*^4xK>s`y3so3%
z0HOP#U`o1tM*SMKSbZ#>yIQS&#0RTT$g>LRHeoma$u9iad0@N_<p){6nFv#evbaaM
zC&5)9-nmv-NDV#U@DoIfoeuLV7}W&PUF6HPLEDbila>=n2k^c|XhGT#q2rAuuO_9C
zH1na%Dv*dAlPu1JpFQ2gA-?o6Nvb%!nq0$geix9a0dc4cl;8p_b5>A*&4PyA*k-HL
zGk9tcbP&DJ;y{USHx+{YFN#Pa)Z=;jAAw}VmDoH{O1p4_#J<M?`aO2viW@L1Li#t8
zbYhS`%S=0N3_8wSnSnj&<6r8qa42`qOlm)13vT!uC{X!kbrmDTIk-;2NWWBnWw_2T
zPK3}T=Pr-MRkv_kkd%a!VsWsynM|%c`)EhJy=<x=Iwtv$*5-ICXBzb=sN(a$QGeq@
zUHR_>3X#wz8KDZ1Y0;Bv`4?}MO#;b}B8!;=XGPa%H0(|)zPd)W<9)XnLKCX~2g;89
zC9kiY{9MlX<UdezdGIGx&7-)@pE%*&YX-8|D#;<dH=}=E98D+bJLb-D2t8*58huqk
zr4rR_HF2`tM3n~k!_?W}WAogr9}|M9%>N=oviV9UgK@7K&cSA4ZN;)#{Xh|NM>Ih4
zpe~5FqQ6Y6`sZ+Id!<8@!YQ%*+#Y|)RDE|yYYmrt&i~o2RqyhKKN^@9GztmU2;n!h
zr0Pw#fAdb|?JKdT3)nB7aWBW4;{FQI#=hd#)?u4)&a8UD?kZp5w9r>*Tx=>UwahBt
zL|a5Kp#stmpR9fy)U3Vo8VI-M_k14Mq22NhZv`_bs1wf}uv4Z`Uu^`(d9ayMzk#U4
z@y&Gb8HsR|sbgPtKXXAMx@Qay0Fl15FS^gzR2jTw!6W=ULWqY&U%{*b`4;~E2g;`U
zSGq{NbiJ+F)mYDG)-OW2EJth#Bm9)VQEpKNJ81(;cjiaah0hmVIlhx@RSP{x&M7q-
z&#6HVlERce_#@|sRU{zCwtsq845OCr+@{fhV9pd*`!e2<^mMK2lc2|A`?WDI$X^<{
z1mW(8tyHp-V)IkYAGenj4+3w6%&t0me|$OhQlsI>L;XT+J#3`N{vFl!Se&qs%WFPP
zkLDNM`ePa{?Lt?sKK3b_t`6V1)AM0W>@=p~d@;B%>*D>x+QX~A`1MP7UNw3K^Zj<R
z-}&$k*P|++>@&kKx(D9V*D<8n>$`gV#us_rO;gK(`p0jU4{BA&&rEuoj<sVBLuMUn
zEzXG+Lelh4^cm}Mt@MAA0s68iH5V670oh*|%EfjE5qtFaE}-`s;ptSwY|lOaO)9S1
z3U56D&QHU%VO`BtKq10BZCtMeI*7^X&v(|dz0G$93lRuQPxgXHj{B_Z&wJck*T-Ku
z^H=sBI^Aq##EmT#Z&cl%>((7Xhup8|du#-QUBB)t|GLP11YlEB?w^5dtKP+}I#{xl
znA#JN?i|GGVfQ$AQg&nMw4MFc9!qdn+jLj%)AQ88qk9reJm~okAx=3WGeqyj`pR~X
zZ8?#MqjQIc;+|K$U2&XJ<JtC=!kv91^-GHzt85N%B?usxQZLu%^BupKmgT@L94sM0
zKus=iF!f{~H3W<-PleWIT0Fcm4l8!a18_DPOvdbS*vYpMos-2ATnW=*_Y-8jmTT@C
zYOUOj4U$*RL2TfyLV>S8aFX=UF?(uq(~e}iiF-=q^}i}IhyP?Lzq4LMwKhQG{YsPy
ztglp7P53#NH<~A&o@hJWVq%t}mt<zDe`vMsF2m!e9dQ@a-_SjuSAL*Ra%Q{~E2M;c
zQ}Lg(So`Sp>)2*r%T(#C>=ydmwmzPoXJp1k#3>@Kp1r$i*Wmg3GT_#n&_h0%ddDtu
zUgY#2h{%tL2apM)*nTOQkxJa?#X~#6aC|B_dt;dQsrpPRfV7&FQM#cSPs22K)s-UM
zJ+<~VIWjThG&BIpGQt#~Urhu|fi0eoK;=@Sm{aqaN_cihqzT?y@a!(YScYS*OY%DL
zs|xKUySCyNbr2w?Ids1YnoDxKO`g@_ybr|6n5nlGJAnd$(DU|V%x9F@XP_4M<yh-B
zFzPu_Sp!4<;c^8`Oaj>R0PsY=*wusp!_IbiiNP=+td^P_fQ-9iau$66&Kt@g_Z!W8
z)@F|tk+QEgSub%$Taasceh*cFD<BlvR5WxzT0Htm2P!18_SlI;QfIlsCfM8AXN@;H
z;1>ZFn61<sBxnFQCqv+m-(uE*CKzZdEXKYc7}>yaAK{?|`Rjn)`y~dyMTx{up`$^-
z)GToQOk^iTvDU?q@m3+Uj5VWA?sMI2UqDwiRuAI7?qkHn>M>fg#0k@S?yC)=Wu^29
z2VkN4le@axTsb)}RDD@dpyvdKaA0^(isks57OAujxbqH|c1-e{QG5>EY%7!;yszq>
zJ=G{V273n{*THJE&FF!x&n~01{PoGRa0NZHLwL2(OqyVldmvEA)xov^;N{|hHl}D3
z(SP>jp1(0(xtU%C`$!A?utSA?B*DfdnmBTU2&CJ&abB>WiJ>R#%*D66+sfF=%0a`<
zS9Gvl&hG6GXMv925iS%A;5eR(X9X;2IG7dBKQIDmJ6OT?BqY=-MKaear-JqnkV$X#
z0jw2?Rt}srWC$>@v4^|o_=Cu}Wp^&}D`*Q@$5z#+Jg+gNskWgs-*S;!XJ90N)hceK
zb7QA8$pL95+<kXfEi=;#)`^c_Xpa;2&wt|TbS7~edp&a^r$6@HdYCGZeYM&GW(pNo
z6Oef{P!2xFhxx47rUOQdPDqZH{TS_miqp98#y!Gw2f+ho)DckxCh6V-fD}+5HUFJ^
zv6dp^2~4`0Ph|zy`Q!sbfRaN6V{K9?KVY45bziyw-w2sMNCzPg$Dah|6qdjAaRp}-
z>Bjox;`FPn#k#pG?v60E=&<=)<E7NoLA);tvF~{fl!JB&hxQdZ8A&%LrY`bxN1%{U
zf~7yO4?&{)iV`E>nb5{BXLma?8(ZmlNhxYM*5`o#O-na3_<crxsIWZ{c)@iK)c`^Y
z`+r5oECd2-Po8}S6bOSMAg_ER&sr#vi3adV1Z1M9gkuZz(4<f%&e%k_%&CPLgev|f
zQa~&gzo>`Q7{^k<#Al}ljAH>q>?S-|z?Sg=@QCF05AWT8FfAT%ljY)!0PDQi0c#Qe
z>mN!HNfC*TKtM#Y#Sj1cu@M#x;9-E@Cw;36^dNci+aMro6p*QTLrFCBtg?_IN&}V>
zkh*}$(5*xaIdnudA3M=qiwR2KN2~<V<A>5>Ch0$LvBA1M;l8lNt>S*g<>V}7Xo_X)
zTB;XNzeHkpBRwiuso0Szs=aQ&>;s3+|6Bj?|L6CxiOam2fA|`Ic|l_1I3)A>+tTh2
z5+hNi7M_jI>r{VVtGu2RI1iwyYr=OVYn4KN8Tf*A8Z?7-#xm3V_R*c#l#BxP*6ID@
z@e{IRF@L7?o*?mA-CGUJmwd*UFTNw*4q@c%Jg*r+d=eAtZo+r6t4w@7I)7_E99o{X
zh&(A>Mz0?58S=V1ttX}DTcai!XP6E@)oIFI{!M>|OtzLBV99dKqp*>Y%^v_ozTdaV
z=$EN6H$JB9a+~9OGncXc;Xe@8%Es+%k(qCiN<+-xWz4G(AJmB}^Ht%3VaJKU(5*0w
zr0n3X@u;rqXE&Ck*nNiSCE<+Q;c0J8SZ|9Bkr`?3`wCw#(|2_zk;^(Egf5Qa`}%6M
ztAw<Bnx1e&PJRK{mx=t2%svm%sHJN|c~5$QpZub={7wpT_5O|@(s_RlG?ve;Q`E4<
zFE@S@$E&EU0vw*tK2r=zt45$weFsb&m1_cu9N(@!nj+JfAzEa8Q(nZ~_VV=I3b@a(
zwX>C~05{chrpjIpIwd3GdjNrQJ{C7-C@yc|OJUreh>|?efBW6f+@go_w}*pXa-z}X
z?43<W)v%s2AHIA`Ie8=FD_v(h&}PW88Bq-vC0ORXvn*|)g_ykhf%5f+W~ukoKo!31
z2^6hn=3P)nh15>Le695|5m`AaOhRH-UZ3oiH}31VlqO64K)-LNJ>qIw>oyr>;l=t7
zB=By>VZC@%sa;1j?7aB6rBI&ek_o&L!PEG#^s~k_DXFo~b6McZr_i35zrp9){-*yg
zA@g)|!Tk8=zkZG!q`3(d{FE{(5nW}^R6HsEITSNaL5#TlMwOxE-Yd2RNJ-iNBB!Ao
z4_V&ly*SB!xv`Vs2QtW4Jio7_Wh3>l`6)UpYdeFPF@T76#_-bB)hpS0UJAJdXIhe{
z-@U_MJ$P$4v;Gwx!u`{|S@%v1E#~I{b$b86eq{3>DC|l6zwQT{$d1hdJAARdkVjrw
zb|w=Bj<+$kngx8;+hZLL+B8?e52xJ%Oux!t6UwyJZ(9|%s@os!3D7SgJVMLkniTgV
z-jEsXSfn(K`%ZSFmfOpi+7|g-Bqce;LwHX{LVCznH}U+|6EC*`8Hra~o+Y8qhI@9}
zx;gI=4N^=NZaSlC!xY}`CeJ&jCZIgsATw&L&nW~S%X)npQQuZ(zOOVTP{lm&C>b~{
z?`4qthW^A@T+v#z>2Fzzk%W4UT82kH$&tgOCfds3KV9=nKY2rJ%?j7!Mkp;_2YGfi
zM|~)C{6-gZX)amve#1~o((4-Egs$D3j0^o)?2b48QPZB1E%F82MG~@UFtAki+2r;8
z8QvNOFZqc~b@3D1c$Mb_UJ|U+u^jb2PGOiLQ#BvArw&Cq?6Khv)+KOq=%95c@p6i0
zOv5wQ>waEBV`T;Q+>9lxX8R{fE}NuKBv#30HK}!cz?Act?4GhL@EI{Q_Ph|4?xG3R
zMdq>|^s&;x?%Xvb$MA|Re_s^9EKtvZGaYMKq;LMnfUfFWZrL^-tO7uxV}^SER73*@
zvU*k+pSmeC4vvW2`%;v{`y%6e(QRQq)|^LD3(rcLxv1#_<&g_|ZQ<fa!z1jxjln_p
zoC-1O3*yXE>>@mr$eWy)JL2Lik5^H5_=|GJ95}P$7o@rWfv9DvzkV`BZa&6Cxc7OR
zGhewDJ2oSxm^YoR9>{;rSD&+xEgAi3YjtMoe0z;xaM$cYyKN~e^H^bT*BgHx4)D6)
z!#XSd{#X&*_I%3vMM9weRO#P>r&}#wS?G4gR@aLh=%om!y$fO@Sk}$>s`=d~xhmb%
z2&F&gw{CAMo>Mvgii=)0n=xT?2;dfrh>81<p+vD1>s{(8vh>#>PkeE`$X&mn<kBp#
zeX3kI0m0#eUD@-fHfZPt<$TFg+}o-~|0xYK#uAQ2Jxb->1d3EyKDk$~gLz>sO(&sF
z6#GbPIH^%4y&C8!<EOqB8Attd7g=6a!Efp@^J^6R($N_rcVY-L0<#h)KJ1_puyt|O
z^VXEr^_?hFMc!qsZi{U%zX_|mvk^z$z;86}TN+52#c$W9Oi!uv!IBkBPc^lcY#nJ0
zj80EE1phfW=|MR>vs2NhGZhjV(o(p#P6z$sx3BfS$k2Zc#fa>~AHiZT3pZjt6)2$~
zThsv82i6J_V9P50oQG9V=_Q^aY-<!F8j1kL30ua#(&)S_v`R$g3e2_i@HECDo8Ple
zR-H@7z5JGCwcP5Wh%7BQSXt3`A7jtxk(<g#bBQPn%G!gt$Ms0`Q1bMk5Uilx)Rq=K
zyZ<4{b^wb$6H4Pn=fVSNT(1W`<0?=YFtL>=+|a>!u*65EC4iakd2?m-r@upCxRC?J
zMMB(}R%Ov$Ob*&2s-5y#s?pygP_ZSDBhMl9WiB4D1x7UpyKs4=lBpwFbd>Y)oQ3qw
z_j#oZL87QflVUp$k1*#WDkkYh$p_^XoUWojwc^fM(tKMMH947$QxEpY{D0R1UPu1F
znke&*v{0&O97AW`p+Jr9_X{)JHpjLX)0HzbPt+=(|3ftAp#3ay#Cd<s>Md%WYO?uQ
zXQCp%dRZD2$yCNc`}!PSLi8AkJSlXu1E%PS81T|1VT+z{Jn3<^t{S)+B$N^J01Nec
zW@-0&xh(tX01_WBy2}I<us};o$>~D&Ua}<kB=fXS56lQoKx@Rm){@tMfo(HYW%<L=
zRm6n(>pLCQQVE>xZx<y%L#Md=2Knt%CVe*M-`4P|i?iU9D4U&~-|XM8(`mm+JK<H9
zt;w32Az@QhChjatT;D%(#Rk`X&`-_G`kkz9**LbU0BPJH@};FKq0LxJCG$tX@VCQ&
zj)0G1A2*Z3ubF3`2P@p2IaUAk_8`N;*1{f*lF3YJJ;GTDiF*bk@o~Tgum(-ld}3e>
zj2<7x4DHpUhz0JoCe@1cwSl|0=K&KlfGsvu5?ufu$E<}iB=pDX*C>lj>9Cs56<I?T
z^?+t%CYcF8R@zcHV)&_tuu8qxGR<sV#nVwG6lUJo=&sv6_I9i3Kx>QP=XIs?imC6{
ze|cwRsged8eSf}bCu#6ImSS3|z22}K9Pd@<hpK%lq536b^Ct0ojecx=n&2ZB*yL|p
z&zW#xWgZT2rd9aQOgni+lmTzg<W`ZNh94S9xZ$Kk60dDh-%)g>(rdU=;au=Ws%GU{
zg(XYf($=$!KxVRm(mc}UD59Sx?$n5%C}6lJVWye*ZKzahD6n1l<3q@ILU~NufOS8d
z5o7ZzXhn8^N17$n1V$9RR64}Ra=j(;Al8I93h6Qkb#2IAjrQ@p7cr>h*aG>G(`=39
zmVIv4LI>VD^Sf|!7xr?sf3H1?j{GZf;Y>Qq(UQx3UQztgV1=K$T3LP$?rjlRVR<yx
zPaj3%&p#;pjsXay(6v{@YhSY}WG-e_&VPEyv%P)!^<%>EN&tzz`rseGp&MW~GS2v6
zbO)_@(UPM}Z+$a!U(`89FrT?N;_1;dU2_-dFG%LE*<N?8^Uu@!EomT4(fZE`%ya3X
z(-5h}ACvC`C_ZU&&9FWEdR`v3tKN{6Xy(>rvnG+R__r=<%bO+SB;T1wSF4-NHm$j-
z@UNBJaT%5`nurIxDkbw>io%Zp*4Lf507O9*Si}SsS0&?d*cm#|nqzyQ2Ni%^TR#L-
z_4;mW`MrMerT2{wZ?Zi6%o5C;S3q%K_PFDP!kFX{S3(fNnX}R+o{Kfo|DfS`XymP3
z82%w=Y_OP#^IP=>oS&XVw;MWr9>T5fi()d*UKl?MmOt7|l(YRtFyP!>Efg&3>+(B^
zafFR29L10CAyB~aZ+%~j+Qq+`YU5c4Gb`vmzTZ%`why46=)Lyy9}-*{`5tC8rLoS)
z=92snB3F~l>a^{5!*UgGMV10z9>3Z5^koO~58QWSm5zolznrT_oO$q6v*<1QetKDp
zThJWoeSQt7u<o>gexB=D<6L^NKI%GaM$N+}+it8(AGg%*-}e59G|_hJpFp>XRoWl%
zYNm6JIjvWl-rM)|T?4n%o1XyqRY5L1XVW@VGOx?Cy5*{VEg*OKZ8}lTFM}tuv3HsQ
zIijzURBov<YM6@>{N3YdSfnPaNk0F3SlM!1_(*W>AKKOW&*N{%yu){MDw*a7F9vf{
z@I$@YMP8SOh)YBsQIho;6@!CLzm(lkaY((98;7~{WHn7-X3E$moNd84S}!Xju`4({
zKj3HjzGyH6>-!+`>4++3L1jjXR$|}CX4CRibzomXBUDxr2&meB=qI$DiBU|gvv_k{
z&DbX-g+sdq-4&?6zRFlpE^d-_5N~e|YO)|a+to0NlFN#dc1VCLh!keEpVr(V8a-nv
z&r6>5cKC*AJ`*mv?GB~<d2v_r()hek?9MThDDGTH34&!ebO^WV+N%Adlhllho#$9W
zb{zZ)tE>jJCokm)bL_I<WBoP2h{5NcngqYDWP7`IR}yu>Dq(gzV{a(mjp)XgEluUT
zA=+t}-Dcqhd|KYck(nRB*}RI@{lxF4ODTg0z1U;oe#HhK7t$GJ8%<Bw=>8F7pI0vW
zH}i>5T)l!))Sc54<rcSa6(TilYQq$%T3x(iP=+_?`{5n2pXz}&wH^z6nnDOIp)5K`
zRoc~?9`m&C;{!(@yg_ZiWPDy?Ewxg~zIx(i^GNFFQ5mvyF`gd^tsve`$QpjVBfZE=
zsn~K>Ff9|}!BFOX2_ON(uA0m9o1=XW^}abh)LTbtMI$Tq{GxC>^X+B*Cy!Mni!99)
z+FQqQg@RLq>;BTv8=?ir2}cBYHpoUl5v|cnpQBfp&)(@;JWg<sILr0a>Lxw&VouEs
z1|kBskK=mbz#RR0O(B~+uUs3h1Zlu~G%Z-xo_u12R<`6CLOl@D9ZF6LfG*k<f`0od
zlDQxuKz+O`iX<EX;RH<99BKl_9@@H`nRGfJNl+Z{=aKBA11d<L6ak1SpA$fVvg?4=
zOZ~8ZToAVc!d+o^vQ3Z&#2giIps=gRWRDfF9*a41sY|s=>>FV&I91tH0V;60K1IQ>
zi3d-uTpUg!$nCf<no)-pvZ@JLO;Q*DDr(*r`QMm!RZJAvHiBfKSU`Xii~x-F3LqIw
zJTx;FIBK)UnuBD5cNG8ulDjJIQuf0cNe}`gqn}D<rX#FB=C7|w%MP^OK%yf|^ofke
zidIS>=?-}`>x%9lq(+KDA4k!*f|YT?0W;m%1|BQ~K)r-+w<7}18OK?{V95d|L;#S@
z0W$Rb6h$zssh}SSLP;LpXN3?MaIj+RIAA2t{SFmnVkbS+)>29?ft+a%A=(Gd3Gvr(
zS0Kg9B<vIRE{c7J0dXhntHma1Sq`+p#<3~;SaAe|@DjISy=?0hY%-X$5pe)nl1KCG
zL7QX)bfmU2NH_HC7QW@n)nzGxK(;CIQ%xW*pooQ+m`R!nMw%Tf5GqIlbPXni2t;g^
z0<+GZ^1sz#l@F-kx!6ja$kY*0U6<L49d{o%DHvdC2aHzh^Ix;;8qd(3qdZu3))4Rg
zne;ypk{6ix%yA`fNv>ti3D2lRS3W+BGJA0xI|L3~3VsDPWI`2)p>pxP_tiDQ*>xRp
zAf_E)J##ITl9u@__`Q$p2yLG*B^}ISyF!2)V7~IvtdO=6DImDi^Fr?`D+f%1Ai<LP
zx%(=d^a`|>ecWbNsh$HYCeQJKLKUZV5!`&KL}Vr*c&Z;np{gm!vm-SQ;L-{=7<#E2
zJ@O8HwFG}@uYAeBfI|x{1j{(fWpr1-T6v#~lF}PzYbv-y^rPGX8-aB^R0YP&GXM$I
z*W_kT-yf^zzTV0pk|>~M^7qGVr6hDG5>Ix(3H!J-nVPpzAW>y|nE;e|DWDT0m72KY
zM(O#ELJ64f?P=R+J+H@uFMMIyjcAE~0eV1!^+?EpZ%g|n9Jp2}4|!dx9uOjFrPjIq
zPhiDEo~k#YKnN7=?6I&4U~Ra-D(Fr@J_@8~UoZxUv(%M<)q{#Bbh&`1BQH619Hhhs
zc(;}laRs<%A@mjy-36315E=qnEbly^BsifypGc^#hU8%i4^v-`4Tj-<=;Df>YP>5h
zWP>8)iA+F}`SslE>PVm(u_p>VBj>#FQ2Ks$=fd@D2NU2h88NIZr5B$$*?=Ke%rzjH
zXj%RWygb)J8}FCTnu>QjG4w1+8XT~?#@u%{ep_E-U)5RYbEjHBR_b!ywfexi40RN$
zhNvJ&v}LGOHn7hM{y*f||LC*-i!Tx#`vO@WaK^D~j9^`yoKi#0mkrA>Ru-Nr@YFvS
z7s1WX&k3zFf0$g#GdryP)S@mesLN+)<Lf!}7#&C+C@D!I8KbFXk6ivG`+Ms1d~kkQ
zd6l)prJQNtLI8ak>%3o;(G?pgfcW}rqRra(4b7O7!kVV=H$SK`z3X+KkkyID!&_}W
zYsz0~o5Q_`o`DmoTSwQ#GzY@s9qAJ{y%lU}ds7CS$$w#lU%&PL({iP~)&aFqT}^!^
zt=rMx!V(osTHmfbQ_tZ1i}M%Oeamd+*@_#V!~5w<J(XYd2|d~nL<4|^qb7`{|87(D
zFDePNqRlMg``e3-$6{z+j&Ck7$Y3g`fP?9(Ou^~OEd=*}AftieGKX$k8T(3)-mvpB
zf0ta8d5Lpy&8Nti&HRuxNXg>`Gex#oIJM$!?cM8r6W1Odnb){&OC#wQ{&xKGA7^*x
z3wi$%3-7g49rvePI66vjwExyl-2sF5_`)aI8je0!iM2PO>3XtCyF3T#y|dYl+P@s_
zDwm)aoikT81btlTwyB1*^!5kjI42L@JZ5K+&|heC-s7-!jhcOUlJRDjI%)T_^WbUw
zX-H>)0a=V3lfwh!r(ew?KWTi-GpgQGEM3{D80#6d)<<F`amq`WZ_uyad94R=n;cEV
z4}BVbqZrpua5FVZVP$_zXFacNt@F%(xox~^CDd#%hmYiZhYx2oG%H6~EP;n1n4#rp
zk0!#bE@*CeQ3!rRyxLzuiq0Qy_*_O+E@&N>YVF3fzlF7-v4_5^`1MpX2!FMT#-5qs
zD4df<<Y{MyMN#sfd;fWQh<7mbSfD8Ctcg3TD+Td8Yb3C*(l^T4^;Pzk8JWnZH2Elb
zc*mM6#h#qVjIvLy>MeU@fT0gdcN^Z%?zOE4t8_l*?et*0Lx<@${tpvtqU0wj@#plF
zv<6xCc`tl;pO>?fD${yiP0Mqh_Psls2rJ4rRthOLRTBH<{(S6oW1R!jM%mjz_TJH%
z?BFJ7IOT`WA0V|i4_R$2AB%COzNgFOmt>NP=i6~SjBaO{dhdL3ltEkgI;rO7eFd~%
zz`;g3n`V^-kBoZ1!^U~vmE~qYv8&21XJs}zq_*J&mfEzhTfnU73SrfIP4kQH$-l`e
zkRlKG!rLRU9s2b6zjZ%tpG|!A^S)o|YPu-f_+H(Vw2>4jP}6a%LFjw@r`JeEvvcX-
zz&z!srN_X8I&qgFy6Mr!wyzlUk=76EwH+5huJ0erl&>D+Y_piuRP0_hQ*B?&q-sQj
z!Du)8%yWovMu%ULG4S!&$SNKh@vUm|FALmf%3C*^SC9>p)lj)UpFQwe5P?am8GdAU
zZ7sT!-G3EVk;uo_xMQDeQTja8kE2ZjtTjUQOn~#1v(&`)>HG|(xX2cSq2|1(BI|p@
zX1H*WH*$39PRRzn)a5D@3LB-Y(ynkQFW#e-;0@UNx}|Eq^E9v0EjNg7=z+uclO|FP
zw!cr6lwtEE0kwZ;x3<6phNt{;J85Kl<@r{0&!qOx((sA2T3hYnT17xj%hS(Q&*_rr
z4d+46=X96L)E#1<GT<*4ND`;qOexMS(B3&Rn?53)tmnIbtRlXd%`Fdea>H*d{UIta
zy;#c&S@sMMm_fHiE`Mv5mPWW3kp|WYAdO|7tbxk^%+autdRWV^8rn`6if9CNa__$J
ziKyGLo~G1Is&EO+eku5y*YQO+GajZ@<Bv`Dg{iEf7ClsA>8wmn_)6DnwanVjIjEWK
zr}btLt?|+~QT@J$XP7G3u9I~&5;}oLHE!p#I^S9xSF*s3$sB%RliBoeyfLNsSi9a%
zFYp(6zvYhoa;d0>i?)faJW*K6b<^(5*T$Ny4_Z<rm}*vc4TAYE@d2+sc&d7%@S;d1
z3nlTge+j$mqyX>UObGW8kY4dNgyebaxW9geyCz^LNDU3O=RiG|EX4OZy6vZb8*O6x
z#%gS=KJ9yDDWU!!vDv*28YfsM$I(H74Q*gWtqU2Z)xuqSM|!5Ze67Oj3C_|#e_(n3
zfq$fUKgq;5YI(-gI9_H5Pu#FdDE#h8adq<>xw%iVchL#M?eO|n$rg<7ci(76)tCIn
zp>B?xaxb|pf%ZKv&q@(>Zy3DHp;01>4itNesK93bMof8eV>l+V*p2Q{KXn;eYp8!q
z`F5`~>Yul_;`Dyf*K{k1tvvL*=|m;zJ;%0Y2lotX-@Bek_tNNYL+YdJbVGuSZMx#K
zF9LbfY>u<<e(d~eEA#22kF03bePJoJ+{4oYWj!c@FIId{@u?XSuJ?N^`A$Sxi*Cw}
z%Ia35y8dMTkB(^)w~b6f#p~N=8LfOgXY7f_Fm7K<olT}VevQOPEodBz7*DgpS7YTv
zT@AbK;$jM#xut|*QSDoqrv61eze*|k+Q;onqgn{uK@wAZfe~U>^G11-%(?q~fvuJ8
z+|o<&3fJkbn{mSA=#S&!3)=NM!6s<cPo$&{+O;jvd3;E}!R~G!?+;qE*Sp*9{0(5D
z_ArqVI4(pcv`MpCWsvR~{5=%p-#lggGCQrf+Cfx8%Rg<Is$2)sesA|>X_jQ9DNcza
zHZThs>j|&|3b^s}4rMv3BU)brkl*9Of_0$6&;l1z+7c%3;*!{}?js7Oo*tg6`0Ssl
z7(Z0~)Z<*%51L2Xp1$=KNl}QoLBfNVp&6xEd!1eomMRD?WCkz^Y-dk>tp)Bn0aZZ;
z5wIGn+7Bv_WUd1%fVM&<ceQfqLEg&%$*7Q)%E&UDs5Vx?3L!GHgg&#)93a+s7X&4n
zK}tY6wa#+aVo&?<kqQ!eV5A0SobBh(##*@~LB6YhS>~%wJn&YD1vK!LhNq!iZ?^f$
zM!n&C9lru>j=;JmyhI|M)=6x~AawP9Qha~1&Fhd9`8ZAwKW7Z;;PV*#1+9LYNVG#b
zhb*EZ+_$um0!s@Ir3i76$Tj4Aw69f+H6o)HKZV6cSD2IptX6R$dUjR$U%tAx2h)`>
z#HZ15PSSqx)QV+u&5^h$OzGp1D8z}>)gJ6k@PCh>WNb;h<7Hi!LFw%w2n>iSPJppo
zWi3rUiul4recEpbQ{wm#DUG#eA%X-l_2TCJ6V;@oNY;1sjfz8aL|VgJIO3;fYMTrF
zCquJN)?CQ}#s@h+o5EE;K3w(rGyMuC8~561te$$3{8UP5B7{PBKiT-I(vm9;!P!q)
zpD|STpj?;6Y;>Ji`X&?F)cTo>SFPwX|2Byl6&)RRoo!Oxg`*Kl$8ghk1H37gZOCZw
zlz&G?+Gcfs0jmGHnS8NC+DCjMe(|!>e~VzX$#*qXot)b-{><r7Y}k1bZXYRp0sAFu
zFeIM?a%c5*rr_IRQv6guH|+G%Q)7OhUYIVsy$-C+>p1|+;c{=X2Qhk&JW(w*3T$%C
zEfYrkNY|j|lblPiXtQs|&d@^umi@xoBm7T7s^mMfVA(l>2d@dEyT`{ttM_Lj3lU4d
zL*Rna%<i@G>2}y{sL2bzDKl_DSr6^mYwkO~;IWI~@o%il4tm2ul-Qv)r#-ml<)Y`6
zwcRyW{wIqAB@2F@1D7@eJ;79m1|0-4WOi{g3DV#@Ek`Rdf-B`-EYfHP)qlqkhSal)
zurH@k)t_%Z#5ot)?_fAAZGY&Wk`?lNzw%pKQk)%}_$Pkk$$r365u`@;yL_G4*~a;C
z{9x#-ijquAH@WbruRgf%e3f##$*7hUz$SCMza;pRsrcnrBrAM7?D~Au52W&5-gj57
znm4*W@$BN>*LZ5yp>ogT6HvqXc>veuh^4zB<C!7lsQ>-n5Z;~gb|znL4ao#}{EPoU
znxu!@rhGUD58uu1B}xpYRhrPl$QC+RME-987!#indH7}Vy2kga*FHuzQn|YH404qE
zm#sqPaC&T2a~`;f_MZ5GvUo{O<UOI?2hAloM!GTTo%j>E#SPsShSD{pJ8KD`U49o4
zD?e~!hw`oHhUsVIYIi(+;QF5w3*JDNyd{iZrfWfh3Ds5-OY&N;BKe&udq>9<VO#z0
zLFCE-NZn#L{Dn-st(q42^@LXuYx6I5<mpd7b;LKoRqJb$T095DB7BZJjK7%voq;m@
zKb`}^uBE<j58M#iiuK!*gwb}VmaF`=pRHkTiT{CGj83oed()jXnp@ZJXIOPDn$9_!
zqtcz^13bwGE>YhrTY)!Cpr-zuB)%&$u#NwR&!gtG6F<{w)VEs+Zh_A?nUmECc~x>E
zzP975T!JCL&1N3`83@4TG&LSxuj%tGu8*}iprc~%`Hj^_O`IJET$y1y`*N4zBC4n5
zs%WjOV)*+2a{zJ+I03_sFVM%H9z))#1oX}q<oc8Hi6agx{jyK|WIs)9TA7#Q@rpM#
zya-=$pZ|n~KNsedHIj2Eju^84bcdZ*mHYOhRJ5e{w&vkImc%Fd_g0zg17_2B(_Hdi
z<N!G3(Zet}hNcF;Qv4^^lp8Y@I4V(Ym#iYw^6-99<bgwhfopA%45f7Q%DKdpdl)S8
zAISUr1?89tw&xTQ)as>p$LoHmo23_=%X7!u7^8P>!5pBEHR2;}cNvxcRCVtKV-DPx
zsPQ_q@H(kvvkxSSupUGc<~-E1HOIV{nWVo~QOrhQ@q9`dD!P8H^QXg7S8O9X4k$A>
z(zA;IF*=9xZD*LVraOn1zh%<L+x}3o*y<wbNRi4_vvt(3Yg8s%;+c89!{Y$9H#C|z
zWGyUPh^YIn;n*MtECff8gLX|ys9NbO+Z)1B4wDP-2l>HQwm$N}NNrsM^zJ1p(Rd&h
zP)@0Re`EBeFXI>vwvLoIt6+1<&ztOJz36kOb}f-xq6_B+v|-a@?k3?+AnitnCj5-5
zUcXlD2Dnd3l#&zP_E&yjDp~M7FjXOjyeJ?3WS_sUC(s-}Z9z7gN-Awo8ms%YcrXw>
z2KPx78Gxrl^6FkqkUAy&?1w%lO7wt=%;)elMSbW(^TkiCjzO5U%^k}5J|aPVLJV!Y
z{<;>8U+w#~O?Y<CiY)Q){eelpKBk)qi^irA=BUJX^+FDK5MTxnq_tc}0o1TqcSo?(
zmlFUw2=1z{)z!z~J_#cL-R%ri+V?>~AN)O)MfcTXt>ULTHT-q(*R_EH)&PV+{1_7s
z=zUaRp&|niZ!~Oqs#91pcN^F$l=0UADcc{aIEVtqqkbM4cg59^?!;{WNpf%WUxc(5
z8hGpM0X$3EXd$=){=Rw+T-#rI9Q!|zsDj*7DtJVgrV<xBk;TO9Ru8m4lZqh{(ZB_U
zdzxqqSp3r=p=RS+zWK4XvDP!85ce??DI}<~pa6hkaJdkQeZowg`7*lm;c_O=De2H)
zK;}-yJoP@;I@-inLgupgRExzt6^m`peh+~UHvvi9OdO){G4bw51uoBJl>cPRTC5IO
zg$ddh23bzk!H&Jv0rEt}F(CMXtpx2hT^1}U4EXf%9E>9Bz@uc_s`yxAPMDM-FdDYu
zGr}VSaB|?WlY%kX_BuwOpEn=MNXo;AR3Mc{Ll62u(0hdF0*X{c3$T!To!v|<r;;KF
z2HZ7XFjPSn!=a`rsytXyl!`Lrz|!Qnh^L}tu0^cQQ+p7Tzy5d6F}S@0)|iQc+}DU@
zq`pE_SoWgcds+L@N8p)aTrl?6@zZO)Y=nFkwuSE<RPCaG8zps~Yq_r|_Z!G@fYlyy
zcewKZ(#Qn}2vGO!t1oAm0xtUjm{->Tgz^OAp<;HbKzg8-JpchRJFsktBw#vyp{@|I
z9HA^Sjs*V5FUEDVr}Sd&0Fk@Yse+7-wk!e{OuA&>hhM>Hhr(m|m<JGp7Whe;MWm@-
z1#CqTC@k!(*c*&Bp#Kkkwc>e?z~$KrCDDOmjhP)QYl3KRw!(##a8Qbw+mc0YG>j7i
zn0Vm7_KRyBEI@LFN#Q(2i6TLIqKa$r;j!baFdYdde?5vnuqd8wMkH3(t}4FF1)3WI
zvV*y+!6kDo2QOfxb)+gLWdDbeI#khBd7%Ny9M@!AuV=&%gZ7cQbe9DZz_W0u>^=t6
z46_iSF8_hpfh^G%;srpLIE(<KCnXY&%hXu7fx(*V@z?R)i~~Ku!o%=?oT6piRS9u!
zCZ;B78}VXEbb@#DCAShmjPDBuWD$x(Xc?bAFgXcx6aGv}?&Sus-c$t($wq{V^xM<n
zcfcBfI;E6_9bEzb9Fu)NLiM8H&T)$j-YFZ$bb~o7kYNPsye4oSa%&XS^H52cK?QC;
zrNc+4uEezSzrYTQXXOTn>^}4{Pr0iDcq94%1-y8*hr?#l0b6`N@H*!zAcC6J6DL{2
z(&V7nSn$n&r~K|}$c*AXWkY<V&y(&RcO@aMI(@FL`9!@5%%>O)Pc@_u%o=9q&F}}6
zWPM&#x}sm|f}kaU5Q!sAp!CL%enSg^l%FTptT?n1Dx#l+vP@Vm-EzS(LNh_vM70TU
zX~=9}lB0B@3i}|HdW9nTkYgptCwLdo@)XVm%A$A&1#|N`O4!xob-BRB8v(6IJXX9^
zxBrV!?*A*$6RtlbnY;Q>w7{9j3&qk|mpk8F7CCx$fuk;47sv11eJC#?mv+!=TlVJn
zf_Y5eFDpd`7o8x4n7h%n!@hRg;}5=Xn66&)jXM4bX1ub$^6Am#%>DGS-4E-pqxY%8
zq-$%fz;~Cpo)Y45<m9RX$btwiPRy)wtZqoY=hj{Hgl3Dbv(%jWi09b$v(P^wdY-vP
zC91i*mzehh<AOq54KF0j_|`Ko%Knf!xBp!E`9xw<Z6yHXre#RXfU?aYO)2cL!G{vz
z;#`(J9Zr0X8D7;@R)ZZ+qE_2kyGny1Mv*%Lc{yJc9=t3(JIDi#9RsN`zxnb`TV`5I
zU!k^+R2;$TeD}Y{-%YpdikH1hsPOOTt|By@+x;^?izoTdZqvxKJ_zcf_S08;H40r!
z)iL$@?<P`Vf`eoW$baNm-%u)jVQY>jZhRH^U1+&-uv#}+f%$yx53S(Alh#nBr>&(0
z5Oep#8{KNrvAY**YUj5_sMRky@@y{14tPk|*{6GJJ;x=k6P_ymKRgL{uSc}q!e!@N
z+WHK>PrICzowt0?0*FH%pel07d09mssM0=pR`PyHUDMvxn8@$bu(*n@Ih8<HvK=S0
zsYHdWVZR~jjQPzR=@mF_!+_Sx6jg|Cx*EVj?u*&dWF{U@RL+(DVeV+Ed&N<O=ohR1
z;^O1)j@&qVWP7VH75t}g*gAvc=|xCIz-(kYtMR^+nU6`_l>0J!)()x2)vMUko+BY6
zP032zw&+nJ?etleI5!%4uU?uetI~I=;^Q^{fhelpP05M!{aG}5fz6=fjsMTldbK0U
zS@6RHdsF=j&PkCUi=y?OfDEU!Ms?#3Yem3Ld1`I?T!8;4r65Q@J>idY04t`hLK$R^
zlP$AteS&r4KhxmeS?WXWgz=mCel2<_G2C(69hU90-Vr74bMbw7*S$bA)Hs!_)v?><
zuL(w<xR|t6n2B#MPFn{x^SdXAFzyM1+ywbz{+_g9)}B0Jxu8?_!@_ICTZV{tR;g)2
zcE|zpK{r*&#R6}!og406XPdg7!mqX{8_nY5?D|17#Fli`_wG3U+(c|o)LuKyPT^%=
z<s}7`DkZH8fz$E517a9%z*d%7w_nm1d}&Crr0Dk7tet3zra7)}vGmfTt{`Y+`t0II
z;qLcc4}lE|Dgv#w`jhRLN8k5miJeb+%ZKrT_SJ^+7&V2+d@FBzeE4T5dGj+{od>Hl
zk61pQCs1BxE$=kd8x79OZH4r=Mt9$g#3z;UIT%nZnbcZj+SI;PxN_~wex&~9;<2fT
z%Vuh5ROMH1>S)Dcd;5`#Hi?RgJ#e&Q=);K4PBte^in>j3O;-T1Gha*8CDn*;%D^)k
zd*@aW@Um)wUvhubYpM-Y*1wwj(pjIMVy)ME9tE#qsX?nHj^ED7Sx*Q`YgIf(1Dlfc
zm;9=-&Z=TemQ$XJG$-#-+&vcarpckD4uaihW2fU-W7Up4uRpVqZ11;=D;LB^P6)Y7
zee|rKoosL<)0wUh61t}ruwCgk3~NE_&j@+FQFd)`AlE4GVNK&maM<3?+LrXA3qN}5
zX*5%QT_?Kv%=!Jru|OyC*2sCTn~v0Rs#R=Nh+tRBILf%9lFPLnL#`&a0pLKu_<*)E
zqiOg{A4#f(JIx8_x_c?Qi3_;IdPxOTbNHEM&33y){7|5h2g-ZwiKz>94RA>D#_$z#
zn3*J+WIGR8<5<}6Er6*`o#Q%|{&~a`!#02C^Y)0<CH&Ev-#>W2>O9kPNN+3Uy^wv@
zl}$5wC!60#)y$!)GR7sz)oji9&LVGplIpZF;`rH{?`h7TpJa4U6tx9(L~l=3)@2k<
zvm>RW>3aQk4-a3q6e93F6OVuNOiigx!<<a_2z&ygU4k<X&4t!9?Ro`6zSjpdHT1h-
z$p`H3ztvx?MYpv2F5>xBr3VIi+<fkk`G+j8iX~kto%$M6kT$BDXZLm~Hca>a%b;}1
zaWMvQ@Qx&!WBd|wEo7pjEWXt=PfWEHmLf~mSWJ{OQ-EObW<bB}*&1O>X6xKaLW5oz
zOB7PZ*BRm0rYwKeSVBJ2ukMpYFi4XECUbQpXiCca^SnDs_T`tUz(MU0v|TF8a$zYp
zAqemMo3G5V0zs$su4WPCPyygzc*ck!t><=`nlT4HoruIcc*UV)f3MGc<DNmQF@`Z(
zW+f1nO^vgU&F7tn-=`8PtcF!AQLk&ZzO8*)N5ko6bTlwu2MdWbXPd5g^eeVujv>v=
ztJ2eWyy`vQRzs_qYGzr<{;PH83Bmq?i&?TjC(Pp$mX_MYo|$3?6Q>K6dv=<*F>CYM
zqpv+C-es$&ekCHGy}2FJuTul)H`+PpO^h8Ml-eeTk*yr!2X#_%2ZJ6n13CYOcJ-kB
za<A`jIlf18$cLfhA{fC&D0by+1LvZD{;v!bhwuLi<(BkMBs=hZN!A0cQ}N{GM&r+9
zE2-j5GwnV_hyHWum0IR+bh52X!_sCdNn#(^)k5h|I!tmRp&#Cc{F`*OiFblHMd+)L
z`wm)OmX=rZYk(vHeeD%HF@a0dfq{h=iy!Zoi~<{FUffpqPQC+mk0k#SRmDvYZEc4!
zSqa(#{!t$Q_2)boGbxCYk_haVo05T-3tyLw756-;j-6A1tb~-CrzvD^jN>G6O*XE5
zkwJfrIGJPsh99)F0pyO8ITbqaAILn5QHam^l~qurwm_{Zk6;m3D90lFtT6OmiD6Vk
z54%s&1q$k9%+{vjclZ{@fpiEubQo7%7omvFF?kOCNl$r_xn2LFcBUwm-zf+Y7C{fP
zH=BfCmXva6;H?0ajoorNC;g_vnnIE22)HalbVP=k2U}Z+h(MBxl7tyoLK;vmYZKkI
zph9^A^eE0t-gTv}xNEYxFJ}zaAo2a(A=y))P1wb4YL}kyb<hqruQ|}Y*h;{Jl1A49
z-d}(LAbmZ8gEgNjKA~Zqq7XWjIPiIY7OkRXU}K5YcqEZD8^wWAOJfoV%Q5-riua4^
zx+O_5HG4XPD%M6DF7-^z##9!;`Fg+wu}D;~T|qY@QGyp*gvl_2yqh}i7CF`D0LF=p
z`U!G1o+GhVUOhJXH)L=}PzGAd$`)0KorzrMOp`b-T%WI7R#F_g<Bk1(9XAe=Eh*IF
zz=s@)9u<NJ`VpN1Is>2e+Wd+W@UmaKW3q7TW(^5(DAJRfNmH@N(O{YPH`6UyQYXE6
zOAB?TS7xWEj~rZzVZihTG4+LmVF1Z3eVNC%cPkbF2C?aS3*D4MyaW04qi!eSYkU&R
zH(^+#(4RvUnhZV7pF7++4Jh*cLVRob1dCP=)L*99+_8x+X=B${({)6Wd|~l~t>}c%
z%EPngO=I3YHSHb^qLV0)rkV!r6a>(FxPH7FL??@%E6+PxF%g?jbN-=Dk(NH2qw911
z9SA*+JZ3o-5P?2Gg+<h}dp7MLYW&6-wIW0O9-7>oH?!q)fjGw`3z~gPt$d4iUM};&
zV{UkO|ACD8r9YVImJu`4)=*pIm#o;eQNG|5q*(WI)vP~5Cv?3fG_f8<{3AGb`d|Ka
zN4UxWlBwW=5*!MR-0jYVotPP<Kf@t#w(&lQtSDmvU!ku519|2xGM+7dAe(8g3t!Nz
z*J-#QSH{mHs=3I+qo4{7k2k>o)$kTC(9#zaV017$qYOxxcliGU*;N>rF^m|{M!SXP
z998)|d-~&;;;a~Ok$Gw=kO|b@=bRaZ-nx{)+K0m4Jj&^2!8LYXvOlf<_t&wy3uZkN
z|B~iug$&cGrc45d@{h$fVpgvDHFZ8OYz7H((hNn-Ih0PlSqbh?`|tICxVnF#aqfI}
zTk=`Y>>RLfCaa^UJ^Ux(HQQW;#OL|gp==8W>YHWWC7}?%cW3$vbj?T^>ZijQ!&P)u
zGLv2h{zBxOPoI6EtYJ0=w4dcc8LF|#g&UUPj|^&$X1>^npopzFWtTpMNC{$h=c!I3
z54ej<URu2Ffmj6o!hLya{Nm?m#GXAiqi)2GL)$>inY5CCz+WQBrKM4N2P9C)W?&)T
zLz)}*x6czz(X>;T*>J-AyGpX{YBjIhNRcr)Q3`O;{uxmJqDF1vH&8~;k6-smdC!Qf
z0vi5g6AeDD%BpM^xXRv_dz(T~E}cVnm3=5@TfCqB4RI27c9(AA)%Yu&K;&WCX7Q@0
zr$OO5y&7A7f$HS$$9(F_^?YRSmxI=|vY;Fv!GCk-4*VQDKgT`=)73ihca4>j%*y*6
zV}`T@_zS$wWeh(Fe8-kE3#Q`valsP#ztGO_xWgcorPc`NY|)W)e=QyPZz?ibqITD;
zBPl|gT%XQiyN{W@&1tN36l;&7#`r|tM}jM0sDS&Mpo2Aim6<+C!}_5Fj?M=|>fHM^
z)BAO8>cPhOP^-+@nNmE4;2>VEX|}Q9sEo%ksxqf=R=G4?zypE>Vm>E+yC}cp+<t~t
z%m%PlrKBqc(q>wVbdOZhZTB=mPIcAX%SlSY%L|q6r~VYiY)^gBCmm!CpmArouy5?W
z1J~5z{S@=`Yil$GDFO@H-e`RpI#&M@GrVMma#NfQLp~oQ_=yDBGG+qy#Yn>aYrU^A
zukMep^dFr$-f>Q1b;}_F+uf0&e@KVM+LUKUJ;(j^EZ&^-L%p&7P-V{Qh4|--QZ7z{
zb-qU=_aH5sJ_c;nJ`;V94{0~8UZHn*8ic)h>JOB;M5;2tk-D!VTgwsq)@&DLKuq^|
zn_?sYDmlmkkE;Z@M=Gsmzp;@KIP82tyLY-AHYZrFn{DHLsFptP;%cUJj`d88wL#<7
z;1j`3@;(Qn3Wv4*ou;fa+7<qr0_zU8N(;`d$d7m_qnO&jzobgVS}lg&TzQY4+Xecc
z8cW_frVys+sj2V@h1<M}v>Uy(`Z$8THwMFNxGde!Ze|BFy<_BrzG}AjOY+#shRn5`
z`Q)-hvmWo2fQed^Pd)b!yd0iNuEltS_gefJY29DGP{va=t&NG;8{1E~y%5UzR3Z_r
zPHqR?u?n7ko<pr}5Kr!eLIfa%-G+Dp;-u&#^@!{#KykIN0eYxw{9pc{Fqo^TtRSNs
zfh0Ik0Iemb>UQOV^eziH?SR0B3=QIv<&i+I!*Yr+p%AP1dni<K2sr8**R#W~2S+IW
zKg_*XP?LWEt{DiuiUtLw3IY*9O3=`QNbjKsM4CWAP&$Mn2%^T&K`>GxNhl&9N^cgV
z8%ltHG!c+0Qlz*4`P`jzE_U}~FV5`jMJ^a;Li~~#^ZwrFc_AQ=U1GkH0XlpgK{uOG
zBNt$Zc$E1NAmg^YcL|K0Fw0y4U|lbl8sAAv4F=3te54gsB<>sn=(LeEl#EQp2n<&J
z)XY?^j*QoZv5*Wr6D!acN-m6J(@-$tg0`5-X`NVeIB!>H7R6rJARGo0V$=tsfw?_P
z<MDU{cWwAG-jWvgi9}K05<$V24FD2OpP&4B)qqR&6y}-AJ^*ODXt=1>Z4Mxjv*6Md
z!h{fE9I9;0FiXHvrv_|Nr;3<R^EpL1LWm+LAk_4ddQD)C!!x6FfMAH3t^gCTIF0Al
z%={CNMer?Ro!sJZVMKT*3Z#J5$>-$nkX}v!r1GPXT<&r;{y8{FNSY2bS1t;u|M_9=
z1^0bGW|IQusDM?&VL&0;T^vVE^-|d;GsQxJ7g9Y67WJ)0$wHj;9G0E0`%y~c$@&2X
z?r}XwgZWBWX8P3pOc04`Ik2~k;0Kl@o?4)l`nQR2h<ma${dE%AAKE<E0uqzV*qqJG
z#TzjRe<y5BXSOs_&jumrI=q=7R5)31k0f>gDEkXgbnWtxXsCvoW&W4s;{l+%h)e@)
zVneyX1Y}yf7<f7kw5<QHn>Qfe&al`bD+x?7F+~))FPj6Y9t<=%I{qSauLw9q1UUhi
z>H24)C~}*?&{@t5E|&|`hX4dz1|lbqQ%-e&8ImUrT0@ZgfajE96Tx`xr#?n!r-)7;
z0|&hSB>8@ra2`~Z$B3Ce=d1dFDm7Vp9T<sB0CpNz^-(6#-XL*^3t(n|vh)F)1OXjT
z&TCNv0TVFL%kH9+helyq+J+g)%@!c(e)^2^YkUN7J&AwCyH80ke7%6I0PGQMcz2>$
zNFW3ONah4sD3Xc+fQSwje@M;Gj88FQV(<_E^j@8U7^FJ{#HCMt<lV;z6&(_A^TJxT
z3#OPLfwtoLZ1tm|Ami!SbHx}7IPouW6F@E*`6*Js)7~|kiD!1M4p}wPHqaFm;L^<B
zPGnYDHGC8ac;dMi5%Gco@<9j{LheEiQzSAbxPB5r6hzV~0p>U|2!L!CAzswj3+i5@
zRm75Y?e0Zj+g581(Z&h<tGBpG5=1VF%$ab%Us|0`&sN^*ERpho69)9qPj5=MLuUdE
zyaAU!URpAa6|aT_Vqipq2+Ak`k_ieULfD{BjZjR|?Q|}MxBy)`mvvpp>mY-xqGV8p
z8SAP!7;u>37;GRb(j*^%)&xNk0*rM*x7rx20+3l0$#D-j2OA)@*MojS4zP)<R~cP^
ztU!5PfC!P#5+G0ie{!Rv>=&E)-J4i;yP5XEKZ<Ll&i(HB0(V{#nCEMg?OPXcF2^BY
zmE#wG>+LXhC7DF?f4_Tn`P|7HgK?pTU-jjB{79CrZRPg;A38%?RZ@)}XWn!F^dp=?
zSo7&-p}aeWx=m^44L+U7n16|ZjW#Prl{qBTE}l9Vgo_w`85WcsN>JfnHK}py?{2?K
zapU@7zd2o3_D$k1<^9@36=%TSXtr!%ov{D%@VruxB_-;TT7=}A7HUs}kdGjVDQgis
z*IadeJn<!e>b1kMPrMm^KU;K=HIBVDxG$4)VKO$CRrtrl7hcyiH@x#aQvOy|_Q3iE
z@7vp7uP;y|p`j)a_;yLcdRp>!dapzRzl4`&ISsECTr_arttq(cis5eQ<KMXN2Mw$1
z*4g<Zfj!V-?q50!iaVC0TLgA|RO;pNiwUyle`gAw!ydYSin%selXqQ>U3Q=s@EzBG
zZjYi>CDp&U@a)r48-E4y=e*^|=WdB;f1VtF{l~in9eAkH^2w*jXml9(UwB1(vCe@|
z{`LX);0}M8FlzBnO3zE($lfO7V4J3NWkYz|wsPNo@~Dw1*X#mQviQ5>-Sujbo<{VV
zO9PIyLBd8VE;J;W|2$1Ad2vu7YAd3s_a6v)yiD+l_nsD2z3}W~wE#o@NQ|D@QM7LG
z^wrJ${B^H4`=PeA%~OeN3QZ>~OEq^A4$WTOhs}lt;F8w%d^>7b&dMB!*WI5i{gN^L
zp_y3vN<+tdxY=*+gq0>$V{kEPKDCo~u~lrNh)np_T{5Gx_+Vb(<4o|TOB4PYm+7T9
z$KNjg@vIE*6XB)&%8QwdEq;QMSihJaF-Po}=h<%e-pAbX!}Lwhxg_e;ysR%NNSwD4
zfJF(qBy01gmoU?uFH(coWc0CW@HuPot8EQCl_L9f0rx_x4IB(7s^i8+d5gn`zM@Ru
z)jhEYeR5P0gzahhSU+6hyb$3)@^4TcSdn}w>tubW+ECE4R%pUo=)>*k(YB=fCUtcm
z_0P%exV>rJ`4WH0brAbLw^S%8a`DSY-tJkobM7V8rdL5AZmV@Oyt%DqQ_0eez0<Sy
zvx(;(3~~^YF`<>0%%5mpezDr+cupW=FUN(uqcsae7dL=hc!qK;Y%sg{Nt4N(eT-l3
zddqxn6ZZA2hNjTNPTNMmFZb(`#l^4fj}n|NJmyF%_5bDjCCX~n_~?$n_1B&Y{Nidi
zKW@^EVX3N;hdknA<?7JaW1O_{C?2@e1#1v~YaOz$y4S9GB|Nx(&fv9$uq~j>R#(~-
zp7^>H+&kiH+)d|H`m^;3ttn5$DBh@M%avh%zG}sL-@Rmn)F=K0h$@@4!i084+MFgU
z5&AtcRM5CQ99+Y<@Zy92LbrW!iIZ$i0=3q_S_%|W$<nwXTs7<1+q=o}VzX<$g9UIR
zx5l}=mH#AC4g$$DF(T8Az8c-o)T9NgRF@UkHrR3$^NaJBz$#f+Rgc~cT^-kTeme!k
zrdFTv!c`@g*VYQVui#v^wJcGgs<)G0a%bH|Ls&<7N+3U^-wtjrl>VHu)6dm^=p`YM
zt|Dk_Rl(g7Ewp)eu9eE~;(eq2+e<C@Y-?!l*>5usln#)kT-Gn4lW)uh%w26W^hYj#
zxR5qxLi?sDA-HM7=WzyOOUs^}x?}jk7w%<OE0ZE;nHznD=QVEd-pr|9VJZ0)C2bzw
zdv?<LYG4rJF*AS%TEv^1w-~Uq^gg<B9V84@^NcfKJcb5FqY?1A9g?`zbSi7^&O&^@
znRJKh5KYoOR=WP_H;)Qk%`=<zFQgP21rvpmyisVXS_;h1+-K02WyU-!9=bODdiWis
zT%@z{(Eb&4=Zv^a?5_y=+Uj*MWp>r(WBrIG^?C1`T2wt}SwW^-#aMW}<Hq5;s!R!~
zcf94QlYK*q0kxfW0VHm&yhf>~DCVUNg9(S2GN;9f3GET$uqV&Tx$9v}YITt`F5;Uh
zpV2$s%^6YO<nQoNtXVF6MA2-JRMFSb4%G0BuZJ-;66R>K?1z+{mlle?ycL$GzkRq%
zc<l+|HMe?Z7MX=d5`HK(pe5|R_zogUsFFc#ZdtOETY=D@7YlQ(A$na)n0cg2e0@l<
zLI5rA%;W=IMeT*GOtyRXer{oGUepPpNuYq-0fv-No(IhWge~=y(IrN6xdCXEqL)OF
zbt-fAQ96}tWCDFEJXCoskfA(9$koqCY1U}1>1=-f>$p6B?2Y}n8MSu>GGkNpVn%XO
zVf;J)9Aw4}S`RL!&jk7K-^`uaCh(ZqFvh|cDjjRG8vg^4v_EQ?qq0Sz6BEWEqV}V>
zxqxLnHN_yAUchVe$CQwa+4$l3(n09bnF@G2%Gl;PH}uDv#lok)#P9A_Vz--ZRK9zK
znnbn4t=ZME3cY{!CEnUS>2GfEIx>eJi9p^i%C+;c&NefdSC|PVvAwP5B_!&}kAy0M
z)@>eK;8nP5|9RbnrGm+auM1pm@}ni`4WVmhAoXlh?q>T9^`M)EHBWl+hK@mAytaH`
zyu{7wPYV5H1BuJ>=r|s$n`!Gti`cs$6?0`*(q+)HP2A_=KM;FHaq)89AC<gN(d1!D
zHHVRonJ8w+o6hP*Dc_8hyC7cgGobr;N$vxNb|4@E8#BtHFjJZ$dQNbc%(IX;oedn2
zGOdAEb;SVn%%|I*O{Ftn1MqpPS}!~TuE~r-jIAgcmF|!(r9PHxdwmSuEUQ{IVgDQG
z6Z}wne}JKBbF{KTS_+0GHwKw&cS^XWCa(3Xp^pOL#lQQf0t$@M)zIXlw1!TXqS&gu
zAi=mgcbQe24SoOU)naqb)v)K!Z_6!cuZSxb`);&#+z40`utY@GP68*o=of@Oq4%9|
zi)cor`!$&If=_qOPG;S>aOMlQQ@(G^=x*4(_^`JeVQd8_n6j*%aC<%tU1N^-+N#|g
z6v*?z$I&8Q8|T{O6>HkR{^gknWnOlq{a{t+zo&iL_m}1LZ`En_&hPX3-|&yuXoRX)
z&+vi7dA1g4@Y8kV((fVX`5Qp^f5%~bU#so9{gGyp56k*59PO<w?fUA|dp}Ju(#2(x
zT?eksVzZ{62wEd#v-qxuXiR;%@3nYMxkhkw^Yyt?{EdCj)~q87XI|@QM&*i}WJPEo
z{lKQig&F@kw+@|(^0FJU^YQ<IXyx1cGDUsUp5<?yowb?*PJ9Q)z5KVoe2X0UK0eB=
z^rC9tW`?4k=*X?|<apa{<fHHFB>~Lrs8Ov6Mzl;UNbd*AsU%F&;dRQ>pGh&#4Mxo{
zg3(v5x(s4n;61-1-1n)05fT8*HD~taVzPHT6b|^X2?U0AHAo@!;=ZXtZF+uvJLo2(
z9H@-GS0ticEO}h(qw3~5;!MD*o~}gWiwu9I%inZXMzTZZ3OK)eMgIn>SZr5i@KZo|
z*ReLp88G_rLbI}OYQ_`sqr!&O{^Z>&e2yric?>qxHE2Y)niSj)M_t$SqHmV_JC|H8
zr&|;2w0+f=ZGE;9`{y$&?7<1+dGPXiEK7&;U6CZaY$Vms`lUY+6w+(go9!&Kd3pVC
z4RyEQ1OB%Aa#O)c^xD^#Dk_*z@bYS<NVsQLmhadNE`oeT%-)>&6TdnZV*~xW&NYA6
zzmJyoMw_8~?>!$x!0hcb9<9$cx;`#XNLt2!Zr&fPG*h_mownE{I10LS3_Z1jP{Ek>
zSrP0y-Bgq~=XV)_XkS#bRR4$^SG3>|17eRf_Ix;Qr|?Ua6S4ke{=L>Pl|6VOi7>pT
z&ZZIoY*Rk;Z!I@*PiM6J61Q*l^_Fn1jpy({bk}JX>+r(w^Rcj7&Ml?0@|+$T+v~^S
zht|#>N!?*8dj!t+gC*U7NbAq{2RdHM_WPcKfRM}b!lD7^^<g6OFDJkOuk&3?l~naN
z9-Gkv#=97Vuui0&Cq}-?R+0Ph7=Gyp`6mhU4noH&7qgxGP{3TeR)u2VFA83dw`|!q
zP9mfkFm9P)kWbCjtYu5xGcEUrO-s6_<Cjg?^DUV10ZE7z8QDs}1OMiF-k56+P#mk=
zf*!3}zRIy_-9KdOncwavv-}RXE%yAfG~hcHHzVNsv2)6Df5g>SMx^NgA6}KZ^XZLs
z(c#%&Jd|kYa-8MGQv1LiSJ*73s?^TZO!YLRu+21m<!ir^!s%7&S%Y;{VLRY|R~#p-
z0qv?rAj>%;o{xQa<-sF8A(?wOiFI@4Jlw7*edft*r*=mbZVO$5T80h7a#y}%^pT#7
z_ss0mknfp|4=a@wzl+X^knc>y>Fc20s$0H#+w*8pVGn(JGj31UVF{{gi_Nsu987(R
zSTo~^Lwfz2+bi9=1b~i2kN^Pp&6Z`c=V)(39!Pg+ENMvpVt@7n($YYz06Ix%HsEta
zHI)1r7F;Bzv8l^XR3A`~hJdjaF*yXe%M3BWJjvU_nV%R%S1EGRK>o5@h(pG88Zq!u
z#EN68qcIi=_1g;ojCVMg?0qH=pv6`!hiEw*o&MVZ>8StnpU=Dwma~A%4F$}L*Y0CX
zuy9zO^qGcTGP8)0H;@E?%psP?rTXG{7bzbF?N7_PAilyBBQ<~r1O7iVSI*Z(00ooQ
zSB+CJ3d;s=VPwIh!A=MlP()&rUjFAC+U`d|%>kj4E?`4nZwE=0ORpNz9x0+@!w4JF
zgk*0J`BG|-86*};0zRJmpxiLfKsd1yV@1PR&|B(BA1?uuZu#{jEi!}!Wl6aKU&C5>
z^PN_Qk*0vY6re;8&~{cbk_Hx8zPW6Z=E3Ib73kana1}NAB}up_yO@6=l}*pPL&-=(
z+D%u1bKP7BUX&j#O`poO3OK8H@Cw}o*Xdj(Q}v<8AZc}KJRTt4(4f2}p>P7#0{l1s
zn3@t`Dma^~Isonzhdf}ugylvduA$(o`UkVX_?;7S2lyUD1?fZ10dbHy4Hsafpsi8A
zOQ3&MfI+cz(qhl4yTuzmiU1T=s|aSH561e=`pX8~@KbBh?+wgfy`XjmfDFV0Az1U7
z&~wZ+@*KGW4+ID3H?)MS^Sq@b@RpyJ4d`PdARde3$=e({`^XHeD$)xeGNp2@0)wyt
z!ozKN2L8_b9r43K+N%b@^-G`ztr|rLT17)+&qg8_v1*<;AOuU-1!WilfH4b!kpMiH
zPV<fotvrzMHb5EzpSRp7^zyQ?;dHD(IJsYtx&w%5fn=wTk$-U%%i51(mKdNLPr)dS
z($bPZ{6)YhB@P+fSpyRC29#7oSf>GS$`mZAU!8hRznq@C6AJ|t@60HT((vPDwE=k{
z1!J6m{6hhzFaeOs5s)h`N%tuMSL2r<9;NvN%LI;_#sN<{kSc@8%rx8~(u)?yju77V
zTGf*V%~*H?<t4XRdN@gZt5^^jC`~7?fo56A1>#?~*fYY?T6thtGjPZ5<G4k@>2@>C
zgi&)iAq!X-0Mbu9f?0|WsCtQ7sLsLu03(ETWXW*IZ1ghs9TW%wr!XvJ#{zf6l?!x^
zIC7D58)U&CTHI4bX^Kc6ki4-t2T=sUhD};V&dtD}rBr_A!z)0uO8zuBbB-cO$G5z0
z!oZYW2cwJE2431apJoQ&g#f3xziOZtQ(f(jb>pzi<v@l}pz1&)OcgMFSz;9q2I!M9
zNMUdCzv~xM9iO;tbU}7HR^`x2K(iNuq{FLJzR&=YGvFGI=dc^r;ZdCQ=g49Z5(dv~
z1TtR*Ud_@3AX`fI?oc7Z2@IE#hl}w_2s+41vV?^$JpiWG6CP9(EacfK>TJ5p<|H%(
zh<Yx4`9J;p{~Y}PAKaj<0Q(8-KLRfMM*zJF2f)w->N)IH8LX)^>|1(7F&ksRFcOSM
zvHh=378C$f>AZ{n93uY^?9O9V2NC~I51BzjH)6D1tEM6!C)r*X{^_W5x`oTZ{TX}L
zPwNoL=8Rdh=Elq_dxx`K#S6eeSi*<SicvXJYeP0+nZfNJj}JTEhh+$!`41GH{PFSK
z{gj_Ae_}VwD2uS9TKV|&n5+VE$<DJ|G6pKW!dJp)zx>K5_SsEgKNcAxQIUS0*L_Qw
z!r>G4&T<>dbx)+|C!21~iHE^UG6n3wz5YaY{>}gg4o#n>ox5Yra`FKb7lRx(X5kv^
zPqDZ?vUdEMac=nyiF2r@8KQQ+8%3-7@$GuDjy^BpSX*_llhNHSUQhVDpgn_mp7EkN
z{h=6{{Se>E<(V;~)Gnr9VljK<@E5O1E6#$$$F++3>deo?yN+dOF&z8&J$owoL(415
z(e?9+`tZZOO2ek1d-n&(BX5!MCp%0fWr9+1$9Bw5tLLjD4`y1ELf?M~jBXEu7Qg4l
z@BTWibdH!^r$gIb?=M*nipDO8f27;cIL*4*KYQU>up>kuKS%Dhg@S56aS}Mj>$kpc
z60<h-<%I9yWBpy$s+6^h1;=5>S3W+e8B^CLX-Bh+c{o*jY!$coDE>hzYK!v=m4Mq@
zrSf!)8j**Y)Gz;mzL=?vrrdUVksY|9<XpUIXEJ>C&w1ll{na<W9z+~{ssF*ekKqj5
zU6x8eFaGE2B2yuz=}hl5c=K0hg6*xyko>6$iIiroj_N3{O|fHBZ@<D?c|Cnw5#=Dw
z%hcrOr57!7a1WS*>^-Uu5?KyuW`WMjIo*7KuO{-tBsIVJ)F#rHIya&|Mxkn7IT?t=
zCRF@ZeDrqj9O?Y#L57wt#SnHO^lDic_X`TOIC0jG+a_JM>RXq7A6zT0Xaz&2RVh~Y
zfXwUF=BDd@8FI~^sUAJo=Eud6Ua!kM-PFs?7~b^dgMPUqqgsq7Pd;&Al<{oyS$*{&
zhO~>)ZB><e1IG_%Z`;DRVLawnpVv4g=Py(f-5fQHKi@gC7KQkDw-tInrWqnd*P1m2
zPD>51WP12mVC3CV#IU%->3<-8!4q_F<<s%?$A9|rN>XY&^1`m$$0!q%b_BBOG!~l6
zX6+LED?C&mXG#yoH6oZ*DxT==zasdwyGP(@R>w*l+<lF|(l6$`$EEAF)m=(AQ!A%8
zQ&hk4v-0ul;T`^K{_llZncA5d1Dx0R*a%z?6!2|{vWlG+(EDe#)oKkalRE0GH*bxk
z8$1xvl~PC2Jpc7I86#h!ScGk!k;av3Fa_iQf#P;q5wrWU#DZ^qG+Ps1<!LoWhWtm(
zGP7T8nQa}!I&<_XaXSmuMH!~mt~NDQZTmmIdO6cP8j^axv|VJr_&DI}e15pHM%UNJ
zIv$u2lf9DM$(&nZFNzAo>HNxi-Qn~k#b_p(_xtv{ogETWS541};v({ksYMEYV}4^Z
z25Pmb)`!B?2@hnx$0&NMMw4tuY4ZB~zZ~6;?2?6xakd#xq;J~sBlQ$JVe#X+BJLa<
zb*`%p)t2(NCfYBu^fB`;|KM)DAOb-ro*qMz_Hn_T>a=9yhU%frOVspTN1KBuS_<VF
zug-a;qfo}tCE93K#9z$;N3!4k^R^2p&gwuXM~18W(@$_Ve!e;l10hm1_?wbXI4Yhn
zMnkh>M2BnGVb!foN^Sg%VH|jWRvCrso+aJwCOo6H8q3Q}zoy@^6hHm`%6n0nBFh*U
z>04}7lQL)ZGEDHCMRW%GSLaU?x6Nb`<-FAAdg`3L6kYL5+#lsL4LNN0bB&`mm6B)J
zu7g#+hY1yL6-(g6$1DW*%5d*YMGeY#Ge(uqec8Ou7P4Ko096!aQVp_o$zV+<Aaz-7
zdt<DZ9d24*SGb&ScVI^s{n)14YZaTPhvsnSFN*c)>~|X8Oh`%fDUGgf^%b1kpjbTn
zm3vQAkPf8~e#hy>SLgDSLp8bI85HNC7@^g}_D4U)qw}qgCV1cbB>j0kdt1!W6d$pc
zanb08ay4`(6~}K=ccxQ9Fu;T%c}KECE3%ZdWj~zxbkF0&TS{3KF}0k+F1i$e;OIby
zxx>B$7#M0mIUc_1Cd=7}beD_-VumLWYZOssb#>B|$ZmbbvrYs?*f)3RKCR=@w>Ni=
zX9)#%&3P}I+xVnnHDsjDk6pZAdZtTJ+VwO4n}J>~8r`Tk&Q@H_=xakaAvdguK;QSh
z{^4GgL9#x${3a#irlyE8IW}MaAY#?zuh~EgVyCDV8aA5>e26g=`c-A^lxRzpi>bgV
zYH)hI4t;=unXZ(NSr$T_O-Bzw@}!7yO5qg@r}M^RK`P6}2$*mt$crAg*aE|wCB{Oi
zkyNUMqCqli5zh<QekUx!1rI`06NHCjkE}XP21MBcj17bywrZ)u!IxX_pmaF!PF@g#
zKO8~Xwz9ideH(S~sd}j5^8H<l0mXvsGz7LuM&yaGY_rYQ_Oml0>zl``q<8ybv&IEG
zTiT%hAc|<!uQDKI`GuQ#cWBpa9|f+~<9zr=DgP&v%$s-nhBHTk=WCU29Nj|$g_C_;
z-K5@qm!eAT*FUB?Yilnk*1h*^t*YLrOT5Q&{qXiX*B>qvAHCWKDN~MmA9aaYk5jU)
zwhHXO-}9$jLa_V?dXf83b@{g@b9nksh?7P$dv0zn{!nU-A$kP71m*Y>jXsiB5AB^1
zD5Xrld4NeUd5BuN+RD1`HWsgDsv`8<{lJdEFNin&7CE%*%@x!Cb2Q<1zz36OUF%Ym
z<JCY;8KW8}9d~-VrAGz0J(4)&z``jPW*}chIAr7O7Zix+gXJ-*F?O4_VKPjW6iPZ9
zAOUzFfS4+68lwtE4n6of1J;c#FZE$9Mk#+Sp0`Ywxo~qc??prKZa4eawp7O!A7547
zKc#MijyWSAmkG1)gSqMZ?}qG_bq~X5B)qU;;No#^OlaSgyVYYLIS}N=cjD2I^dbJH
z%p4y2VMWy%tms4#UUSG6zP|A*O>EtDQq3R0zN|TRDR8}iDMfa{h2tCO`m0S{r%M!<
z>8Ox*2;G{u=_0OX-{dfa+RR;%Jhk6X_<@+>3ZV5alXkuDUN=zVI(3ZPwCNV}F!;O;
zXuY@Nbpcwwd-U&{trb<>cap{>og-zxdMhFOiAT>u96-CXA3X4fKR+nXQy+dR9rGH#
z;SArHdJ#6=mUcSuR^}tl`C^Tyb;dWDlab22q<YyGlRvER59(~R9>iEX(5>Al5c-{c
zX`H6F-PP`TJL<tmF(5hj6(yb!o$pnJexlD6@Ba^k%1f;XvAY9lwhZNy=su5ev6UUg
zs_RF71AwtTwg*>Ivdp$V@e^1s<F|f((3sy62`d>N6Sl89#J@N3QE`DLh1_fA*VFd_
zJ@ZQq);_R)Bz&Z+P{Z!pGe0c*hHeiTEBo{zTUZvp&(F+uhLJw!+MgT#cH`0B;5$9+
zNt4m&Bng>45~}OP%IpmIYQmvAHU-c-`_}wwlne7L^fMCcqx#+emOgqGV&$%ve2Pjt
z4Pp1W!MPV+()=1Xgk=;=1E`b$wdmz%MM9Ke;88_D^9_ost134+2Eb9xC+MgT`I$pu
zd_^ZU0bl-_Ts0Ecs4wQ*{84W0+u4b@q7*#8^(EDQfGsu%NA*uK3*(@<W~JB?xsI=7
zm{H;i{oS15K;0zG9IR~VSM2|+-Ka76Ta8if5A7fcmC6FGYmknXoXwBeca07!6lBp$
zfxqd%wp<$pP>Ayvg}LrgU>|rUX`enkd-(X_70$-wSev(38=p_y>S6(2MADCL#w=5O
zpB}kyk+%-Y-Q)l0RNR#<tK;XDuR8rJFvx@3CbK7JRX<4mty9s%?v@u(YD-mKX|`#`
zPyzTXTrNTNZAI;pRzi%;l@1^mQ@3jOF1_URU4YPO6grK@U{N)uJm0=f7%@qcyZT$~
zq$|Lcu+V=@mhPh&G+K2)`kj;2bnF8(G{{;M*ki}j9a@O#-hjir1d(Ay^c%V&&xplF
ztcMo#LHfnzkbe**@`&oSYyhr<G-yyRU&DaZEc+rL?$a3`C3Bd#Q3`3f$YdrU!eEKq
zBUaXGK($GIK?r8&VIJe$9nu;iL8~tl1aN5AjNIvVAnpYy&CJ4BuI=iVb1=_XE}&Wo
zRe>St)CK{<1^aK4O$|86X9Fq48RDh;TUZzuvLOR8)%8Vm#wk6ihl9%qb{t;8fKv|m
z6=vH4CX4(8K<os(qE(T?)eY@{zz3Fx_69NImGBCP6)1=Y&oVb1>n+GJAYYhG0EX$c
zsoDHO-h!b-U{+6@pG4MBDFpU+>9k?-<@6WmljpEX#(+nZh&9<<LI+VmV9AVCv!VgI
zlpd^fCoPT%%2FIg`m}1`<_>$Z+73qsi~^=;Q|Sd<aJwiVD+<c@W?nXoH%4$FF;*Ye
zO#lfL@IWPmbB7FyLqy79bCR(fA;n(!`wu%ZLxi_Eoc4&N-9-4BzR^t%5LBOGFn61%
zIR*idHVrVFX6tK)xj=Tn2@fz`L1Td8%<!Xl<K^j8mT)3jE;^jF47e(5q58}KjNSkN
z9d8<O_ZlbyVj{Z8WM)|5s~_cz?-3;MvpK9bh2MFb2yXR8fCQ0T=%5S(#{~kIuMf=}
z#fCH|>o=_;xPL2XFQncOTGsA#t_EELLLZ8t7c5~>GLF5QDHX5hx<90Iz8x%*AA}Ij
zjNOV9pzGcxFuP?nhL8j?)O0gA0VE73;1No+WZ+%Jw~lhIp4=tPfs1Le0w?Iq@_rrs
zeT>_Mx)vA~#mzsP!vf_(8vwvr3*cx1;wGp*(1l=%hJp?il@N>Xh=7EPG`OmLjE2TG
zEMz2C2NQr;V@)s8!W<@iK=@Z%!B`^J5N(21W-5eq`0~2;I$$;$n@w&3UWo}(AOKm5
zhCWmUfk^Fg582Fr{^Pv(h?Qi9Abn~q7^tnxX0(9dAtYFIkUmi0_y{|P+au&6xvD`8
zQZO$7Kr>maGhz~oE@2)|=}107KLvu31*{w>$cXtq4NFH61tV6C^L544E$Bw6@$Hg<
zK#2vxnvtKG7i4xAvQw1O5lfe!w;X`gdW4HN0d1i{JAg|G!45RPVlpkbI6)#=%;GIl
zK1z6yrGcSjTsMW`;bAGLd9fIlo1qU2o{fv^^H#?@6D6@sLK@3zF|Zczbwn)2azDU$
zqD4r<n~qx>t65)|dc?*c2l%0=UU*J5oO4kIa9Vn59T0B-O7{LNWGY4$@&@s*aG_15
zwumJ#mYdLkRRcwHlqG@%E}5B(W?je(YX|WO;!V!!W1PGIc{*}?4r_via4c>V!J=R4
zLLqLg);n)+@RK^3avAvuwil;UI&yUZ%YY24K1xAPV~O`MvDLd1_;U#3;}xg^R+>WR
zLaYISjRD8F3)O?VfU~N9D<zr9f!BDfqI)TwS63Aa75Kkx>HS}~_5OGNtXw+Gg9oLA
za!SK^@Fqdp;vd!xyooh*4`Aa~;~9`{ZcKoBXwg3k^e+&cXO|Mfgp6~CA{QZSI`zLd
z4NPyqEH0dnM-cf53@6Z_<0aBM;t3X|ZLF>Rk9z}(Hvf3N|9PY1*Wr+7zzCED6xmOK
zq&_4fw3;844<a~|&P%XhdG&pI>xTr6Y!YV|q;VEOA}T87KGJ9MRD&yYI`NkmKA`XO
z;vz}cYEt&}%R?a+=hexr5J!Dt-GszhGf4Vu^9}nUD(%qQ^8K4mhMmfa8g1xMk-fX3
zQP0hiol3rf8Cqp@>#T9TduaC<lc_b*;6?Z=NhsN1{kGlH=F5>kj}o!J{asimFO*b-
zx33vKeWPhBNXyj0EN)jc{d|%z@m1jW`zeQm+RH}%{&9&i)SCN`YORzEizXvD>`ol`
z`AY)o`3vY@9Gu<odpdq!^gmF9qexH72ldh1DCL35V;R}$>}dZU{yGxzPaPOHN=z;)
z^>$di!_#~%=ppmOTmHR*7uHjsMHUZ6FZ?t=FPZ;Dds9%Y{NlWWU|@dd#B|HloWmI+
zuJpGrMY-~^#Y&i6w&%};_ewzflI)#FD^yM4Tt3uj$vLHb{9Cy4`Y!YRU#P~~Vy>*>
z-T?6uX;Q2?YPR|EjE3M+iD#m9{hhR~)JJ?)>W)7XYK9!f9sXRhf&aa%B`cZL?MLiA
zzCC*}DJJa2&r{1s;{8(<$i9Q>6Qhe=+1L2{g;xCZZ2tC$%Iv(Q@!j{C&um#u3#w?{
z6n^%$raJpYpg!DkfoFiGSKFxhHCiT7O4k1C+KLt%R{y}<)wDO~rW(MNqLQWt{Pjc+
zvF-}$L&ThGKTIkEZrbv-=gr^Gs}r%JksX|`z2xFF3vTL{aFWezwOkBsv+-~#=HoT{
zeNpwf=|f|`tDl349+IzYUZRUP-<WRB7Z}a3vcFYzZ@jH>^pZ#}82i9Wh@02vo-Kg#
z+&N#qqjB!{A*SoSL6bx4pC6dTDE4SKxuVwLYcG5gFQQbq!jFCX63TzH*gsM;?EYJ{
zHQ&MPGc=(Pm^b=N`L>K*Q|OSJLDYNeRE35XUnP^x<Qn3;^EbAxl>P^@rKCA!_Z0h_
zi<`856I$A>o?M;h75O?apG-RTXmnh<WAi@Q;>k;K!8qrJ*ZY4Fqi$A=EBa!qkYZoY
z=DMHis&}4V<;>bmPOnzy?~&8$Xo}YVDfcXp{X6VMdgzrv8OPGg-{4dCF!YU$iM9-w
zcr&JEpLOlc;>Qx4#kVJKPe@JKTu#)QDlKo741aEZ5OP~6hig{x$qs4xj;CEs?c%!_
zh-Wj68;4gB^Y`<=bf2I_t8v*U{(RYa9G!JvPsfm&zGPSPY|KnTq2O|+mS5YYX7ky^
zvZ%K-yT)M0lu5ii#?G%a%4*<h;S^*cblcL|anAf%{8xG9>hn)aFiJRlNo46?elsI;
z9m?GhG+(8T=@BF4tDe2fbi7tD)r4zO4*vU!n(=DWjr$)o=~l|A?__xmyOvWdZ!;%0
z-?{e0EgWb(1ze1#$@I_J2dSx7%FG35JiaC9PAyftXH$U@PO112{$gtlIj;69SoEo+
ze?rR73jMDER|Q_(l+~n2ANBY=PTHZp#MId;<&amRFRonaC@XXF8KsXbN%QRB&x~Ga
zuwF=RN+)`~#xu!S-E2xR9(}uBlwizZdh}JJ-RsX3HMbbfT<($g^4^ht+tzm{Z`#n<
z8x{#foA+!@Kzr2kM%}DOjBv`4xV_hrm{wyp|HP<DWz;)b@EVd%IqUa1J-xtWPPD|{
zt@iSl&)ytsY@Akw$&QSaqRE1_D}B^sx}Q<z-iID08?{s4n$uQq4~XI(vFyH8P-mS@
zxh$b`HSN3ybH1uTKp=YZvPZ<?^V74-*AJsc8-r?EKiR(qTJxWM&Y~|!#D4W`Z5h5Q
zHvIN(P3~O@WHIlov-rManZ1*Gqfhxavv3O)Fbu!w>`~+1E9V}*rA@IqdpDXhbhH(;
zsUEtf+>v|B{hhe@PKDy^IdEo3TYS%<t=ubwX3t=y4sU&ugZZR}57l#0SR+~GZ5L55
z)Bk9?CPvLuW~)Jb08d#`xQmBgh_!iw(GD(Ur;mG8r3`uZ2$;)#x$D<Eyf|Joqx_P@
z&yyuQ!ckQ*xd=&rn=0rrOH8Yi(?@x`WF)|0zp`#8t72@FGLZUvK{l?>l{kht#+>{}
zqDoe%QVuG$S+{g4{rpg6ah=wb-GTW}%T-~~Vdd4V{8O7S%eZQH<rkAwI#f{4Bx$Q`
zGEcJ2HOa)|^Qxsj*RQ^ZY!4nkMs%MJlxTV`QWNX#n9-9m12MeID4QWC!?HHW(?xH^
zYka(SW~CnAyBeY$P?(txWj?Hr<dU&5t^do@mr=F&7HmQAEJ|j7X8Fx_3$Bw0998w$
zt#gPNbx&OgctccYi%cqfp^&ZuGt-+4YS;b4;QC1jO@4pnwBYBOyG_ERy?r-~edN=p
zH$&ge(Nfs~tXPw+qKZ#9nIcai9fCZ_9EyAel;e3hT@bCvz+qI>Gb<GoT^h&ggycCK
z&glY9V2Z$W;8GRBI|*ba1V|oK-T89^bhTW_Y>c2A_j}__!T1b~QuuEuh;bJGX^+g^
zNuQR32l+q14B`Qv59=a@a>5L*nX#ucigEUng?uJMapgzt$EHSpMCTp#&w+)UMYy~5
z#f=fcl&_W#B<!EfbBw%V7{Vj34UTcenMv1WgfH?7X9<0IlN(1%cM0Yxe$oTIEjz`{
z|D#W4SpDKgiuQ2%1!R*U4jI*ZF4vFuC#^2!{-ugQ(i~H3#YWyn#+Thcxl!>cUuxdF
zo8)(XZsn!!9tc>gW$(Y#E-xX!uRU<Bd&c~prk;KEcMwIt<=Lur;RV(6%~F3-HM7o5
zc7<Q{<>kP(`THDmN<8mTKF|K*MwR9;7y6c&T1*IPZQ&7<w|Z?Rch>Eu0mWH;^9gL{
zK#1>Z8%#Cnz1~WU75@x&QcT|#yn-IHyJ(2l$B%36WV2`q6bDo+?SB7zUz`unJOUn?
z;2`7pWv7w;uh%$H;Kp60ZJ*Bi{kEU`IZx{h0*+<ySCuQCu0LuDwlX`@6=|1o``8nI
zXMf{eTGtB8+sJiX<9xtbd?*!jF2i^M{kwQ<Ped&4AcwnLEK&Jak>&m<CF~>Q*fA={
z);<uET$7>o{MaT`;d<#MVAn3d#$9~HtNz`Sle<0K`@EL*o04&!T9J`w#79<tJ(H{P
zeSMl%>I4T)bcUHm3f8;DPf*Y4wrhTT?dNcqzgRMs{AuA`Me7Z33y+)pt<Rk~u8NC%
zF4$`*MGjslq}#W2b=rAVnY{G<JPj$LgY9V8AF41Z?*1^b6y(GgyA6i?2a=-Ci(Qh7
zxx8PobZ$2jhhgig-_(D4Uuj__Fy-!S8A~jL!E#BOp7nA|{ePg_5o#x>LSNI)?7-;p
z@)t>F#&M>;uR=stnW?d&j<@d2Fp=yvn4sk)2+d_#OU)vJP{~7qtBh%U#Sz-iBtIk<
zD=dLZ=0E1^9gT??foNO9!KBNOlNm-g*wBs3V?%)k|4^HkGghbXto<JPUnsp#_V_(F
z1Y5s`2epRC$E<h>QErao-ooj8-lb5py$P%WyFdG{9k4wkXLZW`h$D{^b7xb#1@;zV
zFaAB3Zb<Z3>0H!qz*z~b>1!j-CP)!hjl`85Dp}R(ENh1Hx9K8#`)R3<g;rIH@2?~8
zd+xv(Dd!}NyI~#mPlMlFyq%(B?igXeQIPY-GGj^3!{NvUj77IbZJIbj9jWBo%1s45
z<(3&2)D4m*>M*#z#fGv~a%I$TcM(A=ECn;@O6m%6b6*GUwov6_VL|zQ@*}QK0P0k0
z19A}<aXCs|CFVP#U+tS+v3Zx79A3W3!b~V;un0f#wV#>Q`O25Jd@rEkgH_QBVm!sy
z4_w3Gj{olJ)_7+1y2WkH%cp02KGo_9F`6f<3YgEfdzZBHH>UH6S*Ri(gOGSv<roTk
zUc4~+2~%c1y12;u7niHRE38%gcpNtBbpXNYodV)mTG@~d(Bs5dBj@s=*tviMY6|ci
zLp%mRs>!-)LZu%c%SoRRR--P&(~_$>RJUP~gMjJ;m`T&)lrmD%jdjk<TMkN9p~oUb
z;X6ba00(>(1nR+hD!?>5oAYoc8?ea)@xtEZ2%3(k$VE$c6WjxU9)~0_j|rO7Lo0RG
zFyk4nIqd+Lj2={;u84jQAV2a-R1T?pqzyEesTi!K1k_(6XGl`#8YTo$a}vPQxj=!V
z6mw`nrz<4A<PG}t&(y;NUC2<!3<A~_Iz4IP1_7a`D`n)InX?dk4i@Q#!&m|q6A%}t
z^o)i6PsAqzSP)6&HnK7S^B2Yj<qvz|LDD1&KMDM#Mal>uAqd(7z(w>-F+;}+Gs<2T
zL4hp0$fv@Y1)aKLiI@SsNb1g^g$6SWl+(^P6N${|_c1xLPzYMriy-v_JN1xU%Y1!E
zo;UDUq-9iI0%SA^6j?Ds5TK9IQ!>m&0+<Le^`7T_#tUl(jAwxaoB`ztH;PGC3S)*g
zTt&oY;B~sm8W^fbM=V5y437>k3MLD(F{xXb>lm3qm2wB@cF3d|<Sqpy2ZwM~zuW`t
z-OQmRiV!CsKZ$-Jj+RkeMHB=c(kBb(`Mmr9z%m4Qe^V6<KNF~DT6961hB(ZC>VSei
zY*wWm#v$B1^z5K%031hwE}J-4|4EGH!dT`<kR(&n^_??8GvRy1Y|o`&zW{<cHbZ6k
zkji}z$)yX-oeJ0wdkjCx(B^}&JP(*Fhu?tUK(K)a7y*Q7!G9ndhWS9~o1h<fry)9n
zZW3s20wSCnOc8UXh^2G{EE~q*5v=R&YH=NaWqF4TY{$i}PG|7JIGj&D7)9LMG}S<V
z8u-Mrh)1hir2rwxLTX}0KC~zki=Jzdzpz8F)c)6}fYJD2bEfU`pa;<<!kHwbXDsAl
znqGJjpveY*{!G-|p4>F+(-jp6^USV+_Gv)t3E(O+ATCxHaAELF-6m{mFSdxD6OS_!
zv@%?!rfzui{oV@H7o-YsV^}HjTuSXyI@-hv^iyt>Q&c?#%uiZ1VC*mj#~ZHd50UA?
z+90fEX7I5zAAs8c>>bE62eiCREZ!fa#!ts`6&RVBGR2Kz5nwXJ6E_=6w~zG7r53mw
z(qieB%}%WcX}G@#=1bW%u%RZd>QBzwnZ@NoiPCgxJ46WA^l(gdtXVEKY&LWA6q1l@
z1v+l$Tb)i;IJAI6Vl9W#3}SYr*J$yhK+!}8v7=?gD0EUnr!VrP7^5&TU^!asqmTi#
zb3j4H6Vy~LG`G`$g15L9N_9gTJRJ*M@YU^Il4f;$aV?;6r!J;ZUl}9V`+dyKyhR@K
zFOosBLTKRa&ShRhe*u#7dEt@w>NKzfatLV5Q)8tmplhp!`QGjP?I8FWbDx`$n}(l>
zA7Mb7WE9IHP6a43I04L*$;SN+&E*a1Q#l5P)rgmH0ILLeh(<Ta9fSCrT1FNM<2fQ;
zJZUr>2Xz*EVD<eX)(H^daKfxg2(|)fg?7!<SZ{Vtadk@^Tc~t9{X43ncL#JhZ;721
z%QE`{XL0@_R)GS%3fLH3>4#$5<rH)oC4ef({}#XX|Eg{LztQpBM59@{2uvARgeer*
znl?$~-ysM?TR7DOEo9<8uN!WYJ2-EoAsz!3z90h?^0EnttJ*Eu8)gp%Xf?GU;7tv3
z%Z5$j?*JaH`30b@g$iFbs1^gVH|VM^7=om-p#UKnfHVEi8`7T$163nEfw`7JpkxHJ
zP_X~U4XOgEwqR!76#ueTz8n+Xto=(nai=|MJ=$Y;C^IdTr}I+l=PN=E_8!7AU4F-6
zcT1v-8x5^t@}8!}O&%hv*1+Uu6uX0!S&J<$;jf{sc;&%t%aaz1q3SYIC`t`}R>IAp
z7Uw~W<s<dHi}nVpK#&9rU)6;_f5x3<IW`Ms_2y$B)OylymsK6)fSkwh_J~7y!OQZo
z?LFT9JI6N%cPM8g9V}<E1|F5K{`TqrYHDu%M9;JCb}GDWKB_GZyIEGI;lL~B+!y?;
z)ibc3mo$NGsZp6|$chRxTZ@lH@ao>h3ER8aF1#wf<2zdF=XLS=T)dc|EM`1Psk&ic
z_R%aneXn<7f${WeNQL)c&~TXg<xl>)w!z(!E!^z|oc_&PZ03-KTT%;ZzVZ1Nl6r#D
zl37SgJzx_OGByD`mWCU7lyLG3vdLxl;4`^|a&n_Rd(gYm<<#-#gO@^ODX%bnM+a^}
zokrsy>Qp@8bF@+)nX^^UUM^15Jp)1>W|#o(3owylCX3#yP$Bh5EF;Dv#9@6!WP{Ut
zR5yt(Hcb@Y8gsrzY3L#~Q!MNj!eQ!5iD2&Vv;6f9H8Xi{s#C*l>UD!ZGNbK*nmiwv
z+g`l->FZeYGzb@T;_F)T^!HeMl(3|;I)zjgxp_M<X_uv^qmGFf8BXR4AB@{U75kN=
zM<cebxkiQ1CF*KldsdwzhZ^@COTWuM{!Imvd3g}B2>uo$wXABJeZ`4g_hgSj^mBiC
z1Z3-V#ysC0)HXLZ|4Qx1H5%=EZ^Z5BvR?d6GiD>1+PAp5QlH4ecePY~-nE$X)Mk;e
zpSL31YtS~DL8%5>sExq=Rf;)BIor95@4env(HCa^-nnSfP+{nMz5zbO<vKYg5n#>t
zlFI=oXu~<bYrQOjy@`#tkqQfjUAMQEa`sg(nZnk3{54#}p8X!wT>|BO@qLRgn4&R~
zJCoA$wt=lUmC@Eg32Avz_XF)QNM5DX;~vghA42ziU;MM*EM>?rwDexGb;py%O81Q)
zZEClLXKqjU{5=DC^m1;qGWYGZYq0MowRS;{8Kdqz_(AjYtEqn`-b~T2bvdvsG>XAV
zcP0K{MpK#{%lEA;u<XY3-ar1N+;KVu>hAiTL*x4k8alT1Q-U)czk{~0GZi)LdD;WF
zCz~3gUl+OG)=g>SKDT1~EQ0>?RsB?+GIMm8$7O~ZuMyii3+IW;?agHp{)+r&+GT=v
zy{dLtb<2(2&9_tEZQxr{-DW2;P1IKPiGmE9cOL#sOVJMnC_}${c3(^hQ(%^qbNZJO
zZTUn;<Blyh*v5LU!DbT0N0k1`-dp_-bg^8s|APTiLj8W~0~tz40k5;~`zH;pY43xo
z6~J4h@uHTWDna+2DRZ-+mdE8=Z*VSN!BzbJbKhu@_RChD>|p*{NM@j!y)4|}m$7V=
zr>+DkBlmTA|I^V{zG^DZ)vGfv=YI-=<g4>8D+k}quT}T^QRYRqJ2GAb4W~1W1r6`K
z>A8O5o8Ix2A|wCx$t9vo%9jV|gp76-x1cerch}{==sWwkJc9M9l)63}U5}~GX8YEp
zE4jnam5|2x6{}fe>%uJ4b4XS98&61fnUvICk-23_cgH793^*O#Le-ngL+M|hdw-q#
z8@Epw9nTjpQT$8$8~4~UFGbH(C)e-3olG!AKaBABQC}adcho&Law2laPwv<866aUN
zfbL(u5<D3hW)~H?G4+%}0kwX{<?{lkWf7O|)aG%;7}UjQ{1Byi;i6>y2tK!TqUtpL
z?dNC>UDw6exhzk#+wF%#UjBJ~rpxWY$IfJ5J9z!~KbM2O8rXMA68s(<@dg@{t`!<5
zvUOr>c4fTd)LxCo+ZPVWdOORF9xGiO|8A0RxY&~w$mr!GfNOmGJ3FY=Bdv}n#nr;h
zqN`Km4J#L_lv3kj>6qe0fz?9k)B_MEROt_NlMTQeu&;nm*V(IF3k1C@-<e`1vgo}8
zN01$F4JD5~%ieVt#oh=Swk{j6=A&q!N|-<1F-qYT>p&AQNV<kOrdQLsdQhP5;hMjF
zF3pH35@;m4T$YnwwH2#78^{N=f<a1S!?ev0-<pG!uYG?6EKRswx;RwhC20)9x?R12
zdi`J`yi8%b?FxuXWMITGZnVf3#;AC(YSIxY5CHq7)<laJV*f4q!fuk0fpOiK|8kQ&
zNvz;*x^}Akh1^l9Fnu%6zL{d+7-~cCm>|rES#P_o_q|%L_JvD*ANYn*i2<kUY{&)j
ze7(0T^Pd^P6in->=AgJs8Y?+tSQ1gGHJX@>E~{@ICT=}DdOpg(Y$kFBm?LfbHRb@@
zN`7*Ge-t6~R#R+KuS~&M%_C80%uc~?ZnGkBdekm5<U&|+*ycUI`pOFp`&AW`G~fHY
zjiDN5GM836FeghVyT!m)=nB8O11tXZ40hjJ*CNW^fK;X~2MUXhG)qayIohNf>Z>F@
zw@Yqb50msvk6``t2feBNF7Kt&PIuv_;NDHm|3D^bGefRkNinNk5z45CPfuk(GT)o!
zS+igDX{vMa*ehc_BUAz^aM--Ob$Vo#8O>=O>DVx#bi40h@p2Oln}P|oIvS?Sggw@9
z=-!caY!#`gt*yVkq-ncu(<=&>B-Mns4!?|UC@E<fs-si0wbQuHdHuVr<*rzl3cSMc
zPTk|Nw>n_KSQ%q8>iV^{_jTXi$$v(Lk_%4~Cjuw=<rNYa8vaBxpoeg|PL)CZ<AMrZ
z8t6jx5XjMDaJ>sB5-sVzS5_gnbb#HMfAuWLdlzyZ7vdtLb}wN*!@&KjJUS=a^c!2u
zJ}}vIC311uM*VfZg7$NDo_3JQc%tU)0@3#X<46DMm*5dH!hLlO!Eqyu^B-Vw@9!DK
z4)R@H^)$=sK{>@40g&r7CLLWaA|&nGm5CV=K2h2#2N}3Y30nSgr<Exm{4Ol?{m%Nc
z%7A^^9x_F6S@<x%qH`SFk=4KHnIoV(=lmAF0!>`tS@BiBe;)(j3L4xrd_sY?x1(>h
z(1pK67r$-O7djeVY%zc>N_d>w_~3xb!7bOOjG_R`ny(2bD~*lb41uNwjZrSa<>v+N
zWh14(DXNGsNa9rH@ZTLJz<;ct`@{w+p{|Or=v3geA;tTg8nTzw=Xe|DOV-SJK&rOS
znVyBmpRsRP;WTQz&#(NxD$?pJLika&y?vojs7Dc=_)c>~)n1SI2S<CFA|ws%RDSdN
z+zne@1y8KL$WP>3`nQikk<`s)RHVeSU0j@tr8x^|8To*bUj#*FFi!nM6oP(6Xh`?N
z&M$wW|L41q7PKtrNL99Z95B^Tv~x&3FI@eq1v<tYEIjOA(u)MIn=oGh^b#Lwcyx=d
zD5Oqvn2HWERR>H0-5O{p5ce_N5M*PN(=g>*Gmw*1eQ0DMuR^3|FPkv5^A!WaP`5Zv
zajXJ07f#4MfyPd{*9f68fUAPOo(f;pg)Rd_^6arNIzvDY0Oqj#L1q{PoCf|-Mj>Fk
zXEu`!JwuJ7fP@YO2lJy9^xX|{ZaK_8CbQX_Bn@xgc;W4OQnzF*nuA*%FV9TN-hm_p
zA(#MJ0THhPOq>H}$Z3dEYZfJKq6SoL(}X_xcyL|ci0SgR`#wer09Jrv#xNT>&0zsj
zz)Byb1pK0U(vtUzx4H%W;QnB4j8LgYX>2HA3)ln7jCBq$#+#Q*^AkXan})O(@xT|o
z2$DG7s?*4<+8zu{HY;@+N%Il$mhCr$x1-Uq4TZS*LBu26Z1S<izk^3k5Cn_|^|yco
z7h)kXnYlb2-hu;MOh6|As|W>VpDpOAShHiSq5^_l?;)EJ;8J*axUBD7Ex<ZQi#?ku
zD4;5!2n98eR`q@8+UYMaWs^n8T}5=`*^tcoJ>cx!2(4;a8^@kY73q5<eOwB%&<84*
znZUNw@iOZ|o*ol4Hul6@Wv)i8WZ6{fF-Y_nQ0Zrs3w;#OfkaX>R!#fMp(^~#2qw%S
zbul?J?|{4tXnc{2z|@rSXAx>DBSfTJ3Innl!gDj@&4#@ojGfoa(7G^@4xot#VN)H<
z#p+2!Qt76Wq|COxlEX<|nwcCH5oDnV(i~ZO6~T4KIdikST^?8lqUZRl2VcdqP_F49
zI&$4%;B_Oth$281@;``s@2Do*u-o&YBT_6uilGTY0#X7&=>(7#dJ{!N1Ox(t^b!Oq
zf*NB00g*_FB%w&NfPjLclz<vaKv0@UFVX}A5q;17p8396-^@9GoLMvL%wJhcT}YlM
z<=)q|_iqdGl<I*gMHboK7G-Umjy0%_Knrq*lc7Mi0cRgi!oxbVuQ`x(X$r~E%@=9L
z(+sJE;ljyAgQ@e}{$dDNffh9@eaT$5S(-f_F-E|I#Nz}wM6@Jp`FQkE7&)OO44<7C
zJK5G8>%N|dm?m?o{odZB{joucG6Hb2fS<c?-OVK3ZQm;68vw3kklp!vLEwhAVae25
zx4<Qi^Ps8eSZ#VsJA}|euMG5RFWL6gNgsUaDDK3{DhINC!0%W_eiSGpFj*kzzi|`&
z-D_92WWgau+1jM-`A>jVz66M}tg}cr(bsi6#pd)uu+p1F+H7&}6_7>?Hoy{f9rj>R
zt40d2@6zbV6@(ni!4o!Dh%?BR{F@y?@k&N?$86H*utXD964nkjx&iLd5B~+Dy#*9Q
zt{1XFP(@*RS`@BT%O%kM<OJ#EJ8oDKL(Omyg*E%IFq<7@SH90?X-Q$-LCw8B1C*g@
z$!Cdy;?)fbNe4`=MA6Cls4N?WQaO8$#5wXl^o^f15Loh5iNB6z>jJ;Ss=1Q|hqlx=
zOR_tDGNp@R%;%`VN+LS?>91qjJ2cGV{o&iQBn`56LxBxPjR%5GV;h(x)e3I%hhz8v
zbA~DQma4tm%bqgeW3Tg*Duw02a!Ty9bM__e^c8|c!|c6W$=U~EluLVMo$|@y3=<0@
z&dEfPW|eqt8V4)_G`;s!iLEjvo|_4V4kz*1aQ=3T?%60#<k+^Leyx+RV`WJCv*EYU
zf-y^5l(}OW@rL5u@l;co>j%ls{{gcx4iLU5BQbh$;$fIK_x=Av%l@aP{onn_%Ty!8
zqkH86-LM~&<XI<`R*BL<Z3+U?bL3|gA{JN=DrJ_i+B8P9C<709l)~5ux_$js(nm5J
z23Vv9iWeaS-DhP%Lr$|CSyBPqTKo<cI{z01ZxKG6cqj{93o6|D$Vdn<gsNZ>6iI)G
zyTE1<8BTz}A7565L7=Y9&BI@`Kx63~KKQOc&KUEHdynq@6Zk1sU2O4#WP;++TjOWN
zyfQkbuT|=bW30$E5~GLQ_4X@@IjzbkT-tGcc+oxPAINH8IwoVR<>v3kGg948H7|-R
zWiHwW@Yvk%o>aYWT|T^2m{yY+sU9g5P_58Wc<fWe`Bw-~j3j>zULD>!*|=b!#`t;Z
zj>5T^u0;)JmA@x`^%*IAcF2>s)-s;ASo`gRNR(Ah_iy(X4WH0j)sIs7%Wt375PZ!T
zZ@3URsgiXvT|fK2jWDa+M9kyvg_-eU&Gh~IU+w$IeYQ2(+=!I35nRoBQLc-fnHe=P
ztkSmWI3=?ZxO2Tjq)_UYcRk_kFKM>!!0Kl^A2gbqTu)-<R32Lxs%S7{Ei*_vKWQ#s
zNo?(x#DBb|&KQ(845F8+4vaP4?e|?S72YT%L@Mb!ImcE8?KSL%pqLKg1s~4caf&=f
z(H?2oSaxyg(;8(TT%pBYxsjz~$m5TftczJ+5|KQg#&_$Yf57I89o2734=f4ia%Gdn
zn;ic72<`utyYg&HxUTe?)w)5J_z3N9n5vyxI006ilQgR5{jFrJdG|}JOvs0VkvLZ|
zy(?@AgD)j6wz&@f`Sr57C7zDqA$(}4|9WI^eNjn~q&F;l7@oD{Xj+?bG}GE=j*fr}
ze&V{XSI0q)ny6@ZJ;8vJGiAN#BwX02$q&oT@@2n3rKLF91?K)0=#wG3!n?m2`C#(S
zdC#X?*Hf;Yr|;acND5jx;9e}SemIS1;R2!|^;72i^;RWU2KmTymD`U^;tv~mUuke6
z61H^H@2CfgU;R>5yD<DME1>CGMqqi^hx2)_iVbhCyWw_kHTA1xa!6EXo*E0-(7kIr
z>#MS%@n-vWm$2quu7E~?k)NwC@IvSDXlBV#p0f?-xRJjIqE@i|wf8hoCm8o^%ttru
zS7zyK4?^8PvfgPk(eFPG3-Cm#nemoMp?l8`9sY8>v~%vG)VugV?T6i2k|h=V=~Xsd
zZT86u#3%Z1-wGQ)4bye8);3Jl@8%upd~6pv%kd=Nk0@@0vgqviMmW=O#3y<2Eb&et
z^2TP?Rc`9}>#EXQ9>uRSccN)H)rpboW72*^5i{K<7IRgxJfzy4E7$D8g`YTxe5ezl
zNKK2goR^PgG0WR^ByBX0#cDfW5!{(9eK-?z^Zs`p{BUjkx?oYsy<P8z=5VpYaQuLo
zKyEnKTbB+s|GG>{(Z_x8qVLT%s$6%%o%74(?<Urjj~^dVI@#tjCArnV<2RZ1=GzCS
zz^ihOBPHy&T`7+XdDr&vC5^c7h@Z;=_axSzho`%3ON4*hPP^PY-I#nd=AFvV%aiql
ztB#kw-|jg~DXkv4AU9ObmpUEmEqvoRr)23`g&VW<X96`AVyxsR?G!3~c`Y@sbHZc)
zIn8~_D<&oXKm}&@ct>3Knf<i%1EPw2Q#`}j`O!;mg))J%)nfvhq5h@&QW)RP@vFxQ
z6F(Ix@xDq4QkVskIG2|p1p4Qxl7M43qB={|%B^1=A^vjDVw&F1eC?36>~QNtbSWpo
zh-oFJck=m>6I1>YkLUjkhq`z+hCLF^+NzM&t$(joS+HWlzUM`j*|7UMaz-{0G5U%B
z`SLZcmaWqFEg}6k3gq8zwF~$TW}ZB}tcVx>mU{4l%ILK7QWPbA&*3Ae*t#(5T^}fK
zXL6?axyb>X;Kc#wA;qj~^I!BAk4N6}mM_w5F{Vf=B4ZY;lvzQ#uF8u6LTWjS0&vQy
z=w=IUL7gcUwNru8RVtROYC?V_kX3W>U9ldX^*q?ytV7PnTOXNv=f(c}D;jROX97={
z1m<WxjvDDR8}JNWa4k-A`d9$kNbjC3k~4{&vBOt()o!$3wWhof8hflU(!myje3T7A
zApsgg!Y6KvN6Z=I2%{49`qQA2gG?DY!DfGUch6Ak5dDBdjDfy}ENdP%3<GP_S(;=G
z!6j=~nir^r0}YcI2VWSK%n`DQ{c0NhWKZeo{-43KRqZqnrpSXbdi;K`ieJa&KASW1
zog1N+8{v-BpesLw>du~JFB?_IO-~g|(?c51Gv~@npRagml{6*UqHK)ar#;z*(7ZN}
zfPs|*e=@M|ucW`E$Uv2EQ1I;WoQE@KGHQf-c519xC+cqA!8RUhdDC_@WY@R$r(N!Y
zRLwYePgY~J6Luohm8AyTShly4(hCVxUpb?#so&6H33m=KE-Eb5XcO7KBD#AJ+hQvv
z3wzq#cj%Cx^_p?MOU%rudQ91uXl<omPQ>$gUb5#scu`)nWshcKWc=kw+Aj=;+C|&I
zBd~WH{ezXpZ$*b(sv3IBea*P1h%TwmjMZ)RAD@0Gn=0ot@CqElMJxDf@EKR!BT7yL
zn`<f>Q`bv4qDjX6`wes^OWDln>Xu%2ZiXO}4!T|{XtRHszv0kTKHLG6`GU*zU@=@V
zc$dY#W9^ij8X4Ll<i-fP8ZxQp5*rzJpP1+z-K|agi7r(+Cyx&<%&iaMdU4M-^hZTd
zb(*rl?1&|5++c3l*2=e`hi@@g{hZRf>v8o-i-C`=1gxBI)P4Hf&J*>nq1x)a$&!RQ
z!YqhJl0AF-(8Li%Ej{vkjq}CC9;rWD7o=`q(~pn$U-diq@PoFeK<x91irO$4SCeF+
zstCvC${6kJV~^`a8ei|GmPsuc?K&$zJ}>yu#_K?wGW#jRcY(p@qVz_nE?bdZUnCVp
zK3#adm>9p9k=j$I`sM3j#TVwLLf)a*k5KcUcb&}^z5juf#dE)x5;GEV&}Zb&bO`DP
z<m`K@lWA&}k-yiG8U1FAbMSlA$u*S=VXe*TIAPL3_TNcvm9lXeOR}O28GQjnn%Q!@
z|MyWvpTwzIw?5B4m8azUq}F^w<`pwrOHKL{Av&9OmG=#T%+Te7zCbWLDnG*uDo$97
zUwHkgxD~9MfyI7NmoMWq4@MDFyJk>VOv^Or%X}Q?^unu91h5rd$_`C;q_%6Rg!VeJ
zQZ^z>-zz2B;(o`M8|v7{PJ9X@OePHgWL;5##4hM$nFwXFH7;59#yLtNp4<$cV%;4W
z<x>a6x%(Tkut&)_^uw|P%Zx!{e>mCL6f#8LB>UntFhYB{M%tK#4Wz5LVPT8poh5pY
zKj8LXHCnRlZ-&J5k-U?+Rh;%5q2>WmNFjM}wx)`refaFEK!Y+K_@o~&5pYLQ$_Ccp
z0h+B{MF7qAwMwF_OOz54=XAg!9dCHpXt!4;Zt`IZy{B1X;g)fz<v<jjp^p^uFy#;o
zwZNJ21b~{BQWzgpoRp?vwZn=4RV=_}y<jz-m15OjkA)l&+q7jC5%k4&m>yRFUhM(|
zl>-e}Ao4&G;2ko_kZnpCnok2OAj6A~b99`|dQ!qRp3)6!hm|3j1+1<AlDWrb2P|}}
zIK3ky70#MMM=zP71|RHu3u{K|*duw}Oxjg{&;U$;8wlNOzu}~t0Xh!(`4Kc8?nDu~
zN^H*$5NhWkc&dc?)0haLf67rkZXVe__Us^_P^TJP3#w8?^SA*tF&5qA4NK&4(*-N=
zpG@`xVTfgnR`CO9n<{~r7T4`%Gcw4dqU|B1PL|bhQac0|j6;P;o+0k^0LWu3RRW3V
zVo&6QjuAYv`EApZn5r8zAn5&J2hEVY4(7+Q;8FB$1k|;J6+#a?4AsC|uK#O+UlYW&
z{P8~!YVPJ9%E}^bLJw%AQiI6|HXz@9903WM*vm`nu)}&ln_%-_hzun|K+cNk3qW8S
z9|8NpHk+(LFfopVMS@Kj^1UFgwh;|YsN=vDl>AI%F9e%<fR<Rp+nbA_p`yF6k}Na?
z@*9z-^jN##xnL$Uz(vhsCEXcL)W-?ciMG(#2%s8RW7!HA&-=v~gM~uP=HwW7FGs4X
zVd^P5G~LTSN2<L!j|<bs?Q56j7$R{YrXxyHvW5um8;SmGZ3N)7U%*-bHTnSdE_}Q&
z48>F<CDcMGMeB4P^yp+Zyb4kc;8JjlfqNywZE>X}zyrX5->Tl471aYsmWU+_@YRv+
zgLjN5$x6w$=cxAt1Kq4aV!DH6CWhA%G{<a|9`0df>}~>XBn<8uYFP+Kr@+Avp_mfQ
z3&7ydcO8pke6#wBF5GO<qSot|Ei*x33cNpiqTfh{1SC7B7HA!^QRR%JDHPEm?uW^^
zQC9R4hSznCl5S#-*C37Bv*X3Vog~|C@;j}LKP<v}m;*Y&+;}3)4`@Lg&p6!PqK6JZ
zi{6i@kB()FL+YV}q|H30GP~gBgE@epQGl(WFtbUPg-sC@dv;)&XJuIu?b*metc-Oa
zA!QdVxM;_6;SM83tVBpH+#+V#+{vno!r2Al4*MpPIy+Y}JPu}Bv)OBG;4O`56PrT&
zfxZ~B5ksrwh={BxwF+=Mm@<6a=8q^W!DgI(BZb4z%{tubEiAf)!YK=*go9jqD8Y6-
z8%n(Pxd&D%9oK7KC)yK=;SNKBdTtuy4UAXUD?1Da-YcLrQw66r58#u91*sf@1KvZ;
zAe54(ju0)_WqE>;jP}&Ae_x%GIkw1s?Z_>-JzFM0V;QTjj?jywaMHAxDzQ|35b~H4
zgB5{MmKcQtEX`x|?O0jW@#Wz5drR#8q-oRt#LsK3Vz_nt$Qom13i*>s++n!5{_8py
zI}!!Irowzkrt(@2AVb2(4Z+EvUx}mq4>ELtsb<j2gpCh0*5v3v@~3g%|9@5C{Qqdh
z{lBsX|IdGelfZqMe27V#+9=M2ImsbWrpoNVVWYsEAr84a5ZHiI2=Xr6^p?!_lK>$k
z23-}81qJJT?ktd`nQ+`sqH2}Qp}mqu!AZ{=HUTQ?|Lam81wfsn4k@<9iAT+l12?>q
z_6=vzwFHs86i%kHJPL#6b!Yv+ArYdB)+`51wXP<dbVtn36Bem?XOipFw>pgl5WBC8
z>Dp7e@#^By@wD-KytjVmaiE8vH6D6s9v3)iV}P5vb;0bdpa!|TGA7H2@P&n&$jq}9
zNg=O~0UTX_(WzT&4N^ZoPJ|CX@oPdr9=!AWeV^W!DP7AOdp7vw=Mecu?vdLwr$=uw
zF#3VVCgiY|`uKyN2Z9np-%k(+<J$*by}sBm)>)l^C%Jk*?KhdK@)+!}lF{;y3KD}8
zW<2}~#y<Fkc2)igJ}#8wC7|sWC8eHdM~@h{3D|eIHZk&w%ZG@Mmy)FJdSiux2j+t>
z-wG1Q(VHaS`hKOS#G|>fG5N?nLx;0JDo&61j_#Y|t~9C+IASO#a{N;GhEf=J+|Z@y
zZ&rU?P0xMzO<RpJh-fj`dR9VTyW@SQ{?!lBy)PF{9NkB$sR*MUcc+>r?Z*p5t{JKs
zs^HyoqD|M<vg737#Mx7Fs&DAVKAGuXrSVS2LGTT%cG;8fdIyczGZ0(U88jMY?CDn}
z6!D(!yiQ6ZuXbqI7uu*D&;-sKw<sGC(WYlPJq{i<-&7_1#m&;EKa`3FAJo=m;}3if
z%ikTCXQ7seF7M9BJ2dw1l(uuU<z9M}>Yb*Mnb}nxI(hth)rq*I=>+twZ?~?4!pD`P
z!at?31;-K1?OJ@^M2?rmt=1&VuyFe)qv5ufQnpIAX{ZP7?yP^H=l#xi>yBT4E-V{z
z;qCdSvdzZa*WcwIh+d3gR5>0Tiy<-IW}S^4mirit{RgTr)hj9upn{@<o5MwSE@v)}
z1wFd^<YVmY%dg2%yUs%*_oGA1hP1h&H-7B8HsXf$OR|6bxhHp5PM1)|(Ci%zif-ha
z%PvY4@6IaCsU4a*>UyhR=}+JtR+CV9Ozy?PzLJOod(UhqUaSCMME`jsZCN?|04|8%
zQS8uh*I=4pok8Dud*`jj+1;z}Bs8#1^{+Q*_bs@i8aurSa|ZG|FL*uUk1(A+%3dMy
zaHO<s*96@|9TWBniC232TGjujPS8ikk@gqoj)vE}lfqqXUF{k*&iMZjJ0(dgayt>R
zUKVh0MC@c*mwf5{K`*NZG>&R)W~NJr^R{E@)Aq3Ervn2{UM=a&cqNN+Up1;v$NIR9
z(>ag927*tYW!#t3dK{$tk<vtL3poWJ1O?suza9*D$NI=tKZ_HMAFiDqE0)h1{k%5R
zI%d~#ChQ_3tZW}+RdDjFTial5kkh;EFx-ZnV)^31Tb!<x0FiOIwPUn{a**0DpVKV{
zjlypOciaEIx~6h<hJPYNIMDJq*Q{~0@1cA(qYrrJq<w~q%piY}pZ5ELw)US6VuWE)
z<QjaJa9g1Rx88c~&+2o_A1{2IyZbJ~RoK27UdCBZ5vH&z_@2@Nf6Sk<Qyeh~hZV)j
zd0gjk67ZnAe>nT2ITY(UUivBW?AHFF#`;<-m+QZL>xyPyhYwaeJnvQUKhN0kt@W~2
z4S3|IN;bcO|J2+T-Hv(iWjef(+gy{sPwIJLZ29Lj-RC`YQ*`64iDbq0a7DGh{`>PK
zi|eN9I4}PmbYxC<N>wWbi&1kpIC|)p9bo2)imD}wR2|PxchWw1mAyawd!U#LN1B}^
z=fOAZj>h9!AwRt{DTfsZm(a5T5k}`)g0rEPeZr-lH~g;KPTtB9JXvbzR$D<r$WQs=
zJg-z-MltHp7rVB#v@2u=_K51pn#)h?j|EHCCQ>!jpQwli&(Sq+$E=lVdd=D_q;*Nw
znd3XYBK2IPl{y7i@B{GyxT5R9@sHsfM#hka#k`pgD=Ud?BrAy!JGf2T3ovekjWxMI
zGjOLQ8b1W8{th9g$d|6>BlL0R(u3o7N=IJNo>`E-j+JFsR*N8paU!m^r#N7KJGZ*3
z&NitYxE!nEUSu75e$?z_*#y6*^Wi`A{_WH3I<6WO@=6&^PtVGargR7@NlseK<`o?F
z+@v=i`gOxD|Mvh_@*I2J4g9^&wB#^TQ=K%MmT=pzn2f`$+9w2KWkz8R9ZZ&YKV_fD
z)X{tJMW*Gdw@t)o0hi0!X_9j!N7zZT0BYc(Zeic#1*zXhTNAE%NYy!-Ma!n`XZ$X1
z3b2%DlwE~SiB^}MUElgyQ!HO_A~+vnM2l9NPCK+zExtdAl@GBi*OQ(&JWlg(MRqRO
zn<7wC`iiGtrP^1ZW*hUW2s6&V@dGDrA#kU(M_3QegWTa_<Alo{qdUX|y-yLIIxY{R
zKQ4wYpYM$#A3ou3)Nr?PmybOBG4<%;HI--$h({AXOhoZ3e7v3$F|>12;!eQhW@OKa
zP@#f%RhO*FK2D{zpZR)XI`xoM;S}9Z^o3K@DY;LNJPywqG(LW|<oFNtK?{6_pT*^-
z8Ugg>-z_cNTQd*$BGW3W@zqBU%VEab+d|tk$(_e(XD%gwPbk$a4w5lyQCP&K$vJGB
z;<nC3di^ZxnL|HpemqK`grHo0`V2Z!y&5~W;VhroD&<!v4cwkfq-@E~z~YV=;=D`N
zZ0>IUWHC#y_qy}s$I_4GRqoV#B!8=tGr7`v@`br}WuWe>D#>4}5x<D8yx|Np$+Tvv
zWt~%P1#0GMqz@jqLpb2EMN@x}f6l4KeDMwl`%(WW<=d+d^R?xxrFpGg_rmamscC~N
zKd?(17VUSVb;c^@#igHTr{)H?fMM{h4#SR@<xb|p*k@U<yrYsZ4tD!{tQ}LU=`gQp
zHRYoyLWZ)ILY=Fkh+605xEbDMxr-fA6ELnkh$EdF(Vu@(eaON`uK&o%j5Wo!lihQ(
z6E2iX=~Q|1^3qH0$-4F_%7pM7u)U^Tef4Uclkdh;?{3A6g4RStM?&p{LH1s#v&_R#
zAjxdBHg+7wlLSUs1?g@c1CrToqHn2E%CH7TJ?uLhQQRR30~R`5OqCeg^k3lAg(!Wm
zhN_NBb>D$#$p|^JZMNU|9o~J^Ix!ma$bnMesYHrrty6e>BsXu8ZaDgpt$W#5KvTA5
zQGoRZhT*4=D47FpKa?rlaq3ti=<n=^zbmoRNhN!-C+mXvHy@{Dc7Gz$R>MZ2P9{mO
zKiW4r+%gkX7hEDcFr}vnG4mRO87-duWeWriV>VQ~1Xw`loPKJ`8Ab5~%h6d<oa0|~
z-WG*}QZkuqn4^%e*@8u&oBx42z+#3^!xU0Rv;F|KTr1ksm-v%n&xX}nBAb}1@skk%
zb_ebDnL7cZS@HcO3^%HsGZAGun6aL3FEh4K%ASk9F`LNIxnO?9m)HmL=g|Pmrq>VA
zIXJW_4nycfF2p7*fjh;T{T`9X0ywwycNvjXxn6&^82D`VX33NST`QjeS+k<4QglwQ
zM8N`_sXRiggq>9Dn?7en!rQYIVG*=;NEsAia>=CObT_Q>B@sOm^9T4)zZ@eeQ2=gV
z3}nXe16~1y<mN;FRm^^Kxn6{!doSd_YFUKW=mP6H3qgILpB!=E{p-&FgtTyg>;gdr
zAvdE{qq%Ybh+nlNI5DN!5fhtKIBSyvg%kS*GY&79#WLt>{PuXF<6ND*HjN$71<AgK
ziW;k!!#-a5DEqX{(v+4G&IgkjNrhTlbO{8LT{NLKtuWs76byRDE8#zzZ!|{^7J$Th
z@NPN|Ah~0MPQ=gVhv2lB5Slb_kf7VEz3T|c=J$Q2!|X+1@xzhQ^d1<$Mh}__C{0)-
zpyIJ2Clf<4sj|I&>26>N4jknO__WhYabLXS^g8Bd6nb>SRu<jAjM+Dw?KhZ_kX@X?
z5G>BuandLpp!9O=<`Yns;BSB~N&OpfbDgdyZa0VFj-mCy-pr9rc6vqNLI5CW15WS!
zA=*?};<r#MFknGf<4*3bW9`^UJAiG#1v2<OFkl%6m$xvX_Q8_5wWD7lg3YqW5gA|3
z1%tfOC#YJq>3c{hsB75>*4Tcktb|=08x_9OZ|4RfV;3xk36Rb<EZh<h7kb$XMaDD0
z+=SRSo_HXCiz)FZp;ofF+>VC~@%GRW3pPB_0U@0f<H?M_&XGVhjSoOK!Ywc`zakdt
z&ELnKP&h$IKD`z6MyMM7@n1x6uxHGPih);~XitDXE|#r~4V40lP>swT1`{Dv5#HKo
zbNk=Rx`E-1fjj2g`vY^eWOg2q)5v|3fNJAoj|>4_9W7d-+sj51j!|@lbh@<QK(-IS
z5PC|ybh2zmcA~urkVd;$cf5ZKO)r{;@@Js)TDB>m=K(XD&Y-iWvmWeQA{%xiy0&14
z0G=}ailZOLV0s65-5+Sy?JLwrbnrCG$7+Kuut76;m4_1@N!bwpY_fT?m^M|+4HA%7
zi(iQI9!&WPF3MjRb#IdBU6`D4Zy&{YiVVhIlNpj4m{yL$l5DA9|F;Y`@F9}IzzfwW
zELr~Qf3l*hZ8(^+MPo?J)7by$usC|EfE5H331j}~<6_$7!@-q^Mc=rdX+<z%Jvhsw
zzYxP1%&Ncmp1}TgJlT8>Gn)bKXT1Mp#v0BJ3kiua?C7FQ9=aH#3X)!8WrO!aB*nNe
znK(^0c)$cV%J5GFwZ_f%4=x7Q5uaye31sm_Mf~=WBun5pCtFW|Ia9A1QyCq}L{8B;
zju3dT|7Sk@KXc;$e?795Rvp(OA%(D<3IT|AW%dI^2P4qJ!W{!jGK8!hXOs4&gNqk#
z3Mt^-`z(hO1rc2fpj9Obg!9l|*?hc!nTS=7FAoJkXmBT`i!)80TamA#*_d2{|0M<g
zAJ5K&1;Q$M6xLxTCrO@gHKEoIL}T0p6b4v;+>xE#<bdI}k-6$7Wb1$IL0(5pPwNY}
zRASbzG;NVtSp}XV?AojOPrjGoH4fjE#+xF`_DhH+NzO*?E3yrI=X+toz|OX$q`A>)
z(W_qF$AzIFm1+iU2>XO&qFPa6?QYp-k8Up!idQokcKA8d`&$<UjQpRDw#GcG92IC9
zgg@0&@cr6Rh3*mE-%KDy%~n!=TOY#^MTUYy&yW8D@w&f_O!yOUNHn_2>ed|}5@vJR
z`2`1K0ps4^8zC|Te&504wlK*O&<wWjmlhEyhF<#2c`9lOm#L%8aPT;L&oUsoRjK3p
z7c`?mAYHqYKfza4t82;aU8zdjdp(9pO$<36yLdX;@3(wd63Nz}uDj8f`^9Azx}Pq#
ztQqp7>;tmhlZVUPqX1{qsQVNwnHa46N*=dMVg}iHEoF$f_fVG>NUs=-jXT|tl_5-s
ze_l&S$JNB7o>+~pH9B?ayl{Wal5P5FlG1rgvS~s$H>OH<f5q)u5>FZZ53-%FFuQ@F
znRnVR#WFui6D7?$fDnD!`3fIycjiRQB;^a!2DIWVU~W63c7?E?d-pUdVlwk_gWu<i
zI$V?Em1t{zt@}am()s;g6wdn}&AtH6RW+0*T}t~ST&7!P=vC9VC?dzsna6xe<Hw6s
z0}@0(MQH0a8~63SX{u=VJsS3*kOwrOt@EUPzh>$=IE3qQxilcYUUT@G%0R@sjp3Za
zQNLiGF+f#9szyAlYn)LZo|}b>-#9(;^!z<HUA5az+r$wybNr_74&sOZn?S<)_>%9$
z%|u(BGY%=it+RUlr`HPWC*iO2uK3(NkGn>6#a&&CYg?H4xc2U?Z4`3)Z{&9awzUCC
z$zCraFkgygkY-<gC->2LJV!U0g}$ZUFO+FYv#e6>FL?XB=S^AlO7G~c_hX8|PKli{
zmzK`pi|`>Z`pNeW2lB;F@m;8O&b>sL9uivL|4u|wzV6ofmog^z<-&<lf9s<4xqO$R
zi(9S8R}LAk@r1kD)G6~XDr*{e56(6Bxy4IP`BYXU$?KfCnp*20*#kTG**zC!S+FQn
zcWzKJ$j;?{teHf?gSmRmc|-1Ns<R%W0ozKQy55`Z&i7_zu3Y?Nz+-Yu78h-BRyI3}
zytpU4wm9-G#8M{vLnMOj_HU|W&RF3a>{Ww?a;NVn)6wfUQ}@gt_voJ2Y^dXyA=%n}
z^ALM{*8S|bRZ!?*Zj-uOaE^<n9y@nj9$x(0o;;}DI*W5@7;#^1YnI=tbzBHM^64lo
zlt>=5pY`}T8*m0M$#&xMc@BAUdR^23O!<tL+?DlZ`@>m1RUzmAT`_lZ1&VVmrb5Lq
zs?CM{yurXE!8nn&O&?}kHHJIZo&69M^ukuq)J`v@%zNjITjz(bV)R3EjZB+VZ_3)I
zTAk`Q0tLM}-x5j;zPc?o1x}m~;_meLJX+i5$(>$aW7xkHSS7z6{5_aoLscp|M3eqF
z=7YoFW%JiwV%%(Z5)+DFly*{A4@|B;x~VE?Zs(==DZlH$ua_>C^g|XsW2A5!Q<YZM
zQ*z@Y>WQ~ZhpgEv1HWUm%JwP?W6B9n&ffgxbo1hZt>=-v{7;FMLRH$L?CPQB#{*7E
zl%ExNrB2cz1$_LNS$%d*Tl2QJR+@3Opb);UY*dbNA}DijLH&wt?$6380b(T6-D>BM
z+IW~$M`N0!o&G!rPn|B;-4A(`obZD@vUM(JT}H(A0xDI?MmIGh<!s(4rMrt$l<fB1
zZZ>s+{A#d`8q>eyT+A+wG#|?tywYzYD~Y!kolQzNTEe<mEE(7T>z%vg?#P#0R&oWn
z;Go8NQ{*j4TFN4V&qT0xO|0OU>6mPWaQs5BY<b@g<s_WMI^$!YWx>s{B?sJV@gek*
zgXS{TbU**fC~w74BZm!7Jb9*^JMR=q6Z1QoWM><Q3~QNvu{v`HXI*Ykms?x(iohzo
z#W(HT+h)g1B7`O}9Gnz09tNJjbt~m1H9^3-r4X0G89_0P=IxA*dhExczx1eoQ}>TA
z@@~$XyqSEpZly!BgMpUg`}(hxg>>S+WD`bi&ErbB^IN7udcHZV$lrl!n>TX?KRT~4
zPPa$pvqYb^So8#t(Mrd9O9R$fG=lZZ^--7pDDpAWhtI6fKf|AKzBkk0{(G?Pz4!@d
z<6(7;TD~ns$JtL}9Z~AV^@URp7#=w++>3YJBi?G>g$<9_%*y-I>1S1-MWq0k^M%gx
zlb=!>A1V_!AFG4~So-*S*Jm!de9pXJ^Wdymz@=5AE9-Xl`-FuY2UEk3{Ok$dQvLjS
zgQR4(ADwW<IR2><&4}k?I3pm{I@s53WC|c^ozincnI1Acmt26K#D}liIQIQLA@TzX
zE$LI9gdKk=xjyLX&sW(gq3N+5-y^CgKYaU{-&=Wa^kaLP1=G(lG;O9`8xHI5(N%IE
z?UM0GGh>?hIP4iWpN`=<Z84(uD&OxoQzf0UaDT(1cu<4X7JjbM8h@-gbLQ=Kd<)<W
zI+^nSXgIrE8Ww+GsP6dPd=q4l_#ZCE0dInKapY<ER=aA|FQL!Wk1}gN>rSC?tf?0(
zio-ir9>eD<-=*73HV2>Nf~B@F0^*YU)ZTXJI5+v+{O%PSe=})o|I8?>^5XYpX7IT^
z^>?#z9p1}H7d&#BKB(WNn_Him4sDP~_0u!8opPS~yfL$;-%Q_hu#&r1{&y=PB*w}z
z#s6gJJ>4AU`GE<$7pH%`2<;st-+G_^P+Ry=`Keb(Q(48S)6Y(ZNvCNrE)mxM*nW|I
zopUhc5lLyx=SR~EGak7R)0q0(BJT%FtV0K1KDm0v`=a;JL=fQ>vK8PUZ;~*KUohWv
zI@HTHQiYgeB`uj<*YWaxlOxj(`8Y0v^XGVWet&YNg*l9?ZJLaF3+U7wJ%Ho25V~qL
z2v$A59}8<=Y1pyn!tIagH_Rp*DrOM-E#59z^Y%2O*T14StdAw#ilHrI6KYu@NT|uj
zmsC*JGh^=I5A8Z8#?9u!uVdY#DV%SqKj>1{08GZaZ?`YgB9;oYRFV;zUE>du2HcGD
zRD~Bhj#-xXko>`+!`b|jHZY1KTZ>n|j-$}^_xV~hR4CB9x>`%%1STGjSRN-vwaZLw
zSR41UwM+P~T4QuV2XkS0lS!;Z{sc5I2#;u&$f!Y}I1TtuJJC*}1p=JwrV=>FmzeIR
zrbP(}x9|jQ$YD4e>FIT#C?!Gx-4dDTM>f``ubO*&E@78!1|+Ay5l!9%dwo+Gfw!Ou
z*Krygn1$RUDcpbjm#l~m1jx2lax;Po){QA!^hE?9S##9j-GtD<Ic<x?&^nheVDn{I
zbzId1NJ-CLcCReh)WCJOtK<3zHuHbemEEE3$ln7{-WC(N%i?335~Xl)0Fr&Kp&PIg
zCl>qz(N*32^#D32L>mn?+xi;}6mTJB(NK0HQ-;PsLyeOeTU0u5aAFLa`i91nG7!)z
zW_pse$+01h(aEAiv)R2$``VA|f?Zf0bjq+m!c=q>BLUVK2xW#F2)sH0+FX)ZLTxhw
zq7dVLv%~?coZ!CKuwV&%tc?s{0*xaZ`|rP#zuVWZ?+*hr1R(>Er8Y*H&wv`f-CjWu
zjcx&<W%-Q##CV*cxDcptYv$6n8_X-jwag}|y8z$DU0v<6XQukL0_^Zuno<{iV!d6}
z4GKoyi0&%qEy-&6H&m%%Ziv;{qImV&;p1gm3|WasySC7yVaP8_DVF`(b88e%9yC}g
zTTp<Qva%4w*>Qm5cG>E1mgqJemIjjwH6KVo+q0*45U}p|!0MT)g7?Y-arGKED3m+v
z4PAj#(7zk_=-Ux`z2>EE)^WWuBWXBuSRcUyICg}3BsUwkCLb<X?ew#SSfZntqMfuJ
z&>N@^xMPMK7%5F@zKeDNLT=VTuFma&?Ju$4R3)~H32|=G<_xhsz$VTCV*{u(la{Up
zOaLV0;SZ><-G(`0JzxX8V4-EmN&={?;lu-54D7{RIykfTlOYh0CKwjT12jHIIv#7N
zWBUi->R3W_KJM7Rpl9k|U0U1UU#I(I!Qx%w;d=R8o(38n6gTq5pc}fnuZvr6Q}urM
zi#BZU;mo+?LlDdT8x-R?SR&{(JeF1B&lcVj;2t_m)<;Z<mayj+(K(W~mMwqv#?L=#
z6`QIPT`<Rk1ueIRx#%{fw~Y_dT{nwIpn<$@o@eru(s@!l|J|}`w@b|L&9mVIRO|xm
zK>S%=$8j<voD4$aMOba>k~zq;DqM84R|DQ&P_+TnPyh<6bN#Nubzo$UT?YLGegGxs
z3Y^&zxDX3CF`5G3hK+LU^rFV}%X*e9%$a6pq1K@93AM|bO2?|l&>$U0$E;-w2>5PM
z-ToX<xS3Fmd@cu?*Die5UO-Gt&(Uwa1PZZ{N}}r7$Lay!06c=eO0W($|HYJsNxAKN
zziydcrRpx&S_ixrMrc|D!_8P%9Q@dSAd#|?Y0}rbs#r*aY`xAZDC9y*1$ZJSiE+JJ
z+tj2XG{3H3Ej|>yz`mdpA<5eO6sDMbHc;CTKq*E|{6QM_pdmjJf+^vTZqc=Gi*v99
z0$oJEUBb@IIs+FzQU~$82{1PBXvSSn&O-B|zy_3+tEGRP&tx!>KXhctXfb}CQAVGZ
z3V<|HGPF0*pr6U|ABc_KGq!-~d9LgD*EwHspzg<9rLqFdmw-VO-y`;-T7aRP43?e9
zMtaW_roA`|VEG_71b{~JA$hR>5e=p`gV~jt|NjOs{{IBNp9QNG2XAQsB>dlwj!_3f
zl!hh2=d%e56pd!|N>i)g;<m|&92lk;8jK;?|3(~Sg3y|%BSFW(;*yzvJ75CnIFgVC
zwNwJP^8cN8rvO?gm{5mTa`UfJFQRYKSt8LMxigzV*!QGYJ=_-LOpvL`q)jg(XrQoQ
z)*jiUAIr?n=?FDGtXDKCv3Jkogde`+vC}23(ev;j^0-y)Gg9KZ2V=^R_q>PMZp!FK
zU%Pzvud0&CO&%+flvh3>En8CrrT*F4%<fuWpO2P$YXK6px$>=wr{_OJs<&R<52hHr
zip=rU@`b+G-1~=(3!5vr_8Fv(meXSJt8L``s54KqHWIdeBWj8_i#Ty-@N!37k38)>
zq;@lGP~@G2q|#LZ<!=|qZLI(-b^h1v%iM;_n}LPe>xbX!1ZR0}4~AYj(W<B;zAk^E
zDdV$2llbnPN#%!QF>cpY#oP}UVSg3=ICk%p(5v4KU60AL1fO;{>kki7df?8Sa7nGL
ziY39Vd9%2K1j1QVenL*tW#z<PN{ZtY4_O_An!S(KhxCLy95B+<>W=F_2fA$7?r-!2
zMr4g(*RjoFwn}bO&Myb1&(-*BNVo=&JKvt^R&??0HlMLw8RWk08~NS*n~NoATKf?W
zk}Yy+ijuMAIYwG#uuxZ7qjWqJFrxcDv*!4S|6KFMEUSk4`&#tdHy^Zc5V9<v-UHaQ
z7fH&~MS(Yc(yNu`nF{al%FA{6>3(t=Ehd#=6-e$EH=JC3PF~qjwYX`vHdfVSl=xX)
zboQlcmF5At0D>B{Y+Ii73MmtsX+LVLP=D{3g&@rb)NglEVOcMzbv^2=zvA_K$L}o;
zRTj%-)H+P9M!wZtz!szVnt4RaQSCBfj|<FY!fq$(MuIu9y}2;Q6Mnvs5;k%O40e-s
z5Mx-t$r25EJajT-%&bc>&FS+eVjmeda!E71ZSTTb$IRAM9oFT`FLRHAIm8?jpPqKj
z@ai|F<WU6o$r`!Bk`mJUb9M5Kjlau_P6#H~c1>10y_AvBaS?E}fBvL4`c<~#6h)8R
z3wIVd(|4hzmnr`8$^5(Q2t46Dyygb_!`Z2#Gkhb}5`^b3&Z-0^?$k}4y?kRK>J;Dd
zz2h$W6*cRwccj;<lAisBCw)0<CgOi_uKn72*_h_c$07AKmi84t&3<H<$JK<igRZ^Z
zID@Nh#CmOdaDe<?MH+T?zBcs&uV05^Q<?B9sZi^#6&$qcm_rbc+onr<<#XG);j}~_
ziyegbX4F1=Y@YZrL<7u`A2)=wmd&Br!ltnI-ydMToZf8rdm{TfU~eegy_nWrEm9%^
zO6-<RJb?*TDW?=B24WS^buy!|+$5vvWWY<}&+?oY8mG^ZEBWN8_c2Z_Z%eN*@cRx2
z$udZ$wyrZ<k6wa7zAZeIY2c97vtSKRvhbR4k}#f_TUf;X19exOd;B5(N?}AuaEM+P
z&;G5F#H33(689|%ETDo#Q>D}9CWM7+*7bwE?{Y<=whsi0qH46OFVng<OOIcYA)WQh
zvY*a!e7-(NRRFa<K?a|Wl_050c03$pZW$-WCXGt$HPQoL=;?R|>vjt&SO~PFte&Y<
zo$kLX`-&iX`JP6`vuac4;o=9(&-S&^hh6n$9d`2M8|lgqKP#8J2VcID;%@r4N`K+U
zl%GY;%j&Q|l#eVO_gT@R?RHerN`HQ1!536A>Fp(Y0GXz$O!NOBCcS$7;g9mFZ!yzK
zO4H@7-cQS4zbCZcHy8Um<^9X)K9{Mk<<{);>|CQ~mJrWO&_G85_n%fR9%25cI{C?;
zf0kDcb-#R(X8!qEXPG-G`~LLvVRTQbn|#f;vTBNkIXaVDEG)J?R^%4?c7)BDK<x%a
z3-?g+HgeDHFaO$rV4ul#K8X50KGl4QylyDIQ)mbaEDBEkG+}-1?UV2e;idk0<rhzT
znny=p4xRlnW)=MBJxZ)XJR$ROOs-=FhI3nB!(!$0Ul)(@eOFZ;y+{;Ncjcx09_lS*
z+wqpXS$gzNW3&fWqcNssv+^70gGn7{BnAu%&)z+iiBHx>71Z6W51$B&PsNwEJr%CM
z<&*yX{m}mO@v9Rxtf#7)6%ytaN3MSfyc(WZp*}@W5Ef||=$6BnE718}jM%H)gG?t1
zzIH!85%)T$;C&<e$Ei~6eQnYNqfV~3n4dV{Z(J|2Sj=;}NV9?A?$j67G;p%&W&co}
zjTCm9QUeQXehbOx>6x8I9L4D`OkDfw=EycDd`9?Vta5en@iW#_4Vw0&)<mNai>b`>
zA4`SPV}p;l3t128o1&}lK9bv(JwGU6e|S;JjOp8${*k2as)^N=i|mnIuek3syy_C=
zKHykjw!QDih>6*7d{y1cT^D9+@b{?7w%ovAS?MiJMAMY0)~+k<g|?X7O|d1HQMe>-
zc1bVD@GhqR(C2n``Ded0b)%*s@T`8`F+JqgHnIMq39EfNyj>}n4UTH5vG2cjp7s#Y
z=R-E{V6U_(nsL`^s1KBYkups4iG_hGt^Tib!i&OfE*?PN+!ntu_4{S&U*E<%|3I*D
z963e1KkCu<6{UOV>CKa2PrrV{$Zl0GyVv9#J$A^%t0C4vHsGGZO4TFcKTxe@<<eKt
zfbBlmeShkif1pCoWTms;O5-geh1}|W@4<A{LWfJC#4pmJqeHi(4hB?++AUlDOvk5g
z-6@r7YJM5MGF!7)==0n4^G^Xo`zLj8vM+ocX^R(o>ZY+%(R%-jdcdvE%Tk&Xvwtj=
z_bz-MP>x_c(yB_R60A(eX$)=^NzDgW{M4Fmi2R=5;QVm1Rgq1QbZ6zq^{t8zdn`LC
zI)}p0MwKvMAf=H$x_Z?Bu@rsuzE;pTr{$N8N@LhL`v%+!9DR2niBJsNX6ngIk?QKS
z%yeb7byxH(nR+N`r_(;53JW&awx8_I3Obex;|*D|-JkD-*)DeuwYIi)`Z>2?yC0m^
zE%ZY-DJG$$>>FVMT7_ffv<cq_0!jpXYL!^ej$@)7;JApE5<Pv%B7+4j;JiA;%BX)z
z5yVxo9tij`QAOGkNYQ_*5+EeaA^*3-*JcjE%^QxrIEc-bJ;R6K26>o@!MK=U(RtXQ
zcJv3n|26|w0J6SJ8Q3CD3w$YEn#{Mw-QDTsMWPts?2cI&&S;4$6%^z`!?#NTen-%d
zt_6={3F7cSX)UN9ASwDL^<+kyELnGpQkb2$UBW(>V!1`Fk{oDLi34?8q-4<L)T=cM
zI<SCXM(p+tCjnI}4jC~_OeF+VG+HSB2H9z(@WR^W9U4kVmM#i%nIO0Z^OHd08hPlD
znEd@LZOUIwW0CwwdP%P?i|sQ_HvgV~%O>bugWaq`%%K5Ss%XjxNK(*~nGlhf04qsP
z7=XYfo6BO6QuJ-W>gmD$f5A~mi3Q3uFl*^xkZ}8$Eo!sOk~K7&!OH3o!rN`I64}EL
zi(rbOhJ(Dxz;nnkNYEu96F~$u$&!RHq(eGc@MtO;c$*7>-xsvJ&5<1eCydq(s<dQ8
zyC`0y*PAItZqQyC1Bm{EU4WY<u^<G4igVGum=&Cn7=^2+P65v*F~5LG?dFmPX;yPU
z5P$8zU^$-q+Mf*o)tk-n0@5IuE3}b`*$X#AnX2(=Q|$4e`Kng(%{Pl!j>2roW}x^b
zn{jr7Necw61#ptpU@9v-r9d16jZ9O{aBI%xo+a~HWcV`K_GXndTZTUnR&Lf4fW!3<
zB%fm;R^mrO0uOPewJ676!7EL^!f=v}_Ss&}#_f`<!cD>KID46!RUks`sK0<BbBj%;
zVE*`bm_jErX0r*#YWQ_)&JLtG7O^nEVhhENPG48N8e9v;DUjAK3!s~ItN6Wqk{C;1
zb>16;F1jl%lJ78_m8@@2d$^}gO#-wBoHE2l2Vf+)RE;eAht{buUICbQ;eb8+I#%FR
zmEv!(Fn)o=ft$O5`8SE2oyQo=PKe;Q1@Np*T93ia;oQWrUo;v0c^;1OWIM@h4gxn~
z$!bU3wsn}mDcZtL^a1K$9v?~o-dgICCHQo4bDtxEHSRKS?`wnUh#79*)*r-^{X^`;
zLvbt)2F&j(U7BAKv1&CcZVl!#>_op|QvNP0ngZp=^;^*8vMekCn2J41?{BuFq>equ
zb0S$|ML+>mkby7qsWsS}yV5-RI7<q5(fe$_HTptfOvwfYqW5^<bnQWN{UU`U%N%yl
zs>qE~Mgdfs<bxJ7?{&%shK-vDUR#zVL*UKLei(+d_3y?zi9VR4^N<YFNNjXbApGNF
z=-sBGzrt|)C=fvaCb<XX2EoHd!F?TI)A@Mn#M(Johrx!Fr$o^I56%`vs(k?80`BC&
zY{58jREiY=qrjfj$xig#{&$MO%9w&RF7LAZBoJ&+cL)-+?{!X-*(e<2NoGh?(s<Gx
zVDlEo@~|fjfspYs!FpnnbdxSRZO_IcX2j30GPx7kSlRL4w||ywu41XcJP#&W#J*nA
zSSk-`An$D_Am@X;_QH~p-uf>VsTL|K@n0P$N_}7@6;37!)<#m{v!v3}84NdA-g1z_
z|9eg0(yCQfKf$g$x4c9~*CC65TD2Si)VnPvEKEQ$8>$!@Pu5=AafG-;mn<GxbZ*h!
z{-k69)_1!E&lY`xZ{OTgim^9$N-KQbh{td+u^B{ulPo)fH}~MZ7>+6kU5L~n;holj
zp_7CnL%4Zus<yU1&SHwJ104E13L9_fiWU?>;G8(jBRSyBP3*&PV-(02YtX6}19;#+
zDSlr(Hk-=<sh#gv_$U5E#F7!r9>VvAg<F|{Y(oQ$`UbB}Q(G`cM*{mX$hsrB!2ha(
zGok@MLnLhUk3WTLY5}87qx7N%hV6mFp$y>VeDB>);$BooB7loW`BbUfze2lteh*X(
zIE62PY=9e5W0NYMc!XdaKhI<f^)H#t1z;|R%>Tmb`cG!p|3{D9S?nMnZSCkyh=f5O
z9S8|r@?7js#%dpwPNm~*-e9>dp-hpYbjpcSQh#6CBQbPJ)L~ey!~e8wj{U!M<#EcQ
zy}%E~!5aRJVT)4hlwlx*ajd{bK|bkh$Ix>1D!Q>M$n%`IsnWd`Z~dj7s)WPi?iNSw
zn~CyfGk0SR@8SUmF>a6$bw)kJRc-U)z6Bk)k#bOO$RdNBd%m}-?$zNy#Z<@l42c%)
z_Q1((e#bf7=(SXRUE37v=cK_eC(Z68YOt!N26O4c$}d(J?~Ou(BnFgWR75K$e(0c3
z;+3g&>s$}xhrW0GotE08J2Db&+yk`ct&(P5BX-V7mL^n{z8vYWzsJ7*vZ=N0FZ;kX
zZRDZ1vyAlDRqgRc`L3!{uXwLEX&XN5b1rNsDbjsz7UuqV?tNJ6hSapF(UWAn>!s2d
zbH{b%?->j0LMrOfR-Xdy*8rom;M%#-wpERSGFbd#F4m&jCp>1Z?r7k%f1uRRNz~<^
zUCP48I-<6#gRRVN=N)}qKy%irYv^yZde8Hj#c3aM&b-bIftiS?@!Bz;XjX9P^=TYX
zKIE6#^Hr?<pzHoZg&Chc$`gqJ-|B^3uD_M6qesu=c`v1})s$8KmDow>@+Ijy`_JgU
zXz2b*H~Ln?bAIQld-IPhHM^U3xv4*^9Pic(f7u8s0*9<ujJlh)zJ;jV^hDDr9iew0
z{&@6X3*%Kekg;wxAijI}w|HM9TRcoLYbsD}zIEZu-E1kG2w##f$I)COA^PT}Ve56n
z{X4p@Ykq`@`#;!@S2ma&n-bd#9Cc1}kq$A{D=`z~r9*5<tYSx-a{}fK-s~A0wjhXP
ze<3Xi%L7I;-$kjg=CY1>fbF9*RkUfxlFkCK2|)*7Il+fW2N>!Aab1Ptl3B6>tvFZl
z71!ehivqR}-#ch7$N%Z0vr|6i9|#$&!<OGqn(p$ywlKAN=tXn+vzn6&Iq5SU@!{?#
zGBqU4Z9mNy%CF7Vmo1%gJ+N>}(h4<_10O_73Jk8OQlB3=WcDNaQZIfm$7{5b=v}N8
zTihCE48C8Irod)vvpZ>xYSLdjQ9rm89@46^ytKUFVKg;%Y{+IEzV=1>Y_6F5iniv%
zw7b=*rBx)}8euW5tty@uo^76?Ho3M97JL2sV}1Oh13vb4>yh!BE4U7L81j9?R5KSp
z{10yNVI%!Z`qG7~H<~ye$2@ZklKt_>Axkbl!I_I>t#BnFJ56t>EZ`!aX7eefAm42c
zsaV@UK|A)qE~$qqIbkqK+g2;jr)>|Ir(2XJ3hl6qwQmI61KkGP-0h}qWMm^!HfucA
zqTfCYIypPN)Y}@_Y<|BrL;t$?CGWY~JK;gyc9e3mata;q*LIZ$6cHL$7=Bj%5_HZ)
z6`sJ|G#E6~Z5v;%eonMSo358mkCHsF6B<9cELJlyAY)UNuGFwQbgCS8O8iW@a%zu;
zX+~QF?bw4W?E4I{fl_$OBwNK3h59&mV>SI>boP9z!gxW(>j8e>uh_eZ(&Z8XzM(0d
zWv84>IN8j4ZFMFJHz&haErj5Xq{&2aCp6cUNjl`0X_aX12Hgn3g)-p1MhYD0ymmDa
z>2>o5JRGpc2JQnv7@-XwIwFh5kZ$_f`H613UYIPGk7w(#f*a==pS-Sj4!q-fS8C<S
zw0P<zfxp6^+T$MYe352(K0oAM!R}$WbfM`DmueNdsLl$Xeyn6lEPds#X7Iy#tRIQ@
zNjM3~?NBctzI5JI=Srr<;`JL-26e2Ri{Ik^fo^YhG@rA+j^d-o9LtrJ=+-&9eY%Zm
zh<zj6k{Q-i(@-J4dZSKCXiPM?>V2@BeB5tBU&>pzHgUuN&FKm8J0jdc(Pm$sO~~Un
z(V9o?nkG6>TP3GtkMlCzw}d6*JkOlYdcXhln<WYT{fAwK(cwe5&31hwcT&odjl$ei
zm4WZOj+z^npFUep&3>8s-Zc1T)a*hLe)p)``s+;ZM@>KRIR$SIuH9Cj{v#MT_m%&3
zrsT7mZuihHE>FB%5v%%>z<9^JmSQtdMK!z77Uu9q^3#y{w-K-7ujfuh*Vx5Xj9t*f
zod|mos`@c>tMW^*2}+u)YhL$EciC>7B2BHs$Ckfuld)A9U7t#t>AH&Vpgp`#mph|)
z@8tJ{h`Wa}f2^Noyq8c5K#<Q}^n$-}7ynp%@(yPT*}IJv`gW^4;rgk-WT8jp%ik<l
zWN&neeAJCD`nHW;^}79CeK5t)eX_DWE7NVL@MxA<?Kxr}^YEthc4h5_X9qq0N@64W
zwS6l){(&U5=Z0zfhpAdZP8=7IVoy`e^p$k&iHE-{*>5nNnlJPn!cXRZi_o%iY<~Go
zAJ?8ERW|$IxO?+xs2lk2`#S~`St?T@gD7U|N@SGX$YmSrj7muoUCdC*&PYaDr^(VN
zOqR*aSSl@7T&XCfu~cIjTd5QZlO&85(e-@#o#+1Jety6EpZmU_=RW5-C#Q~6qxsHv
z`7H1E>s=IKT6EiQ#fhECEt-0gyZps&63-hW<yA)WGK*VkS)q)(tgYq?y;5Hvpg82_
z2bwNKUXi$Lafy!lUS=LE5nhyhR5Wng-!RECT<3~kG%F0#Hqf)`$uL1-tSmm>!)BQj
ztrD#;b+{jN_@61a+NSj{>y*kGqf0A~EOa)1_ct<8zc|vp|3=7z@O6xl+C!^$d0i+<
zfA=NwRhQd8i=T#nd~tnm^NNcOFTL(OQ^R<@ylzdH;nVLMHoROD#pFzSP4C~p-hA{z
zZ%sAXisFT5*>B(bwEob(*fV{%o}Q&&D!tV#B>!Qe)YLQ|DGV-DQL`g#&FH`SajYaN
zwzVu!x7P1hkLSHVn<o#74yLDz6(TNZUQXHZmr+i}%$*NZBkq;t1HGpyBt)$y@c7K%
z+<twBSfip33OI$`QTY}74eM7de;QRA#b2(mfjnCBrEEAWAYpONiFV<t2+z=panjyP
zI2x|$#85GBmVZdAeCaGt!4@@;n{{K5M5Tk|`lPOv5K-P?=c-2~m`!-1vplJ+z~Byh
zSo2^rG9juOmZFt{DOqWQVd|t0BUDFnYd%$a3JSe<`>DayJ3?ZiFUq|)L&mQ{tFWhF
zDQu9rK)b1iqq~wxsTDkhH!M$1FURUDzdV41MY;Mgpmmj>Pbw>}r@M<*m!Z5Is&Hdi
zWN9<Q6PVIgLdEox3RcegT3^f6*8ORztct4;G_5YpE~M&utv(Gkd&;kEMaZPfXF9W7
zhzw=5afnawwy+^Jwh|JbV3i?$O;LT=m0>+R*D1+Yzyj0uZM{Br6gok?LAD~Er)J4Z
z=|F(UvS^eT`lXDi^p&4Jz%pkAqi>L{JG(*msEl_AaM0cgCApxDrpc2@Nf=_jaGn6e
z!&JPEGQ?3saUCtm{7&QxHF;>v9b&lDV^(XHU+60r$1AClmuLs;WzzUnSVY-D+mdgE
zMPR9A$%jL(fOE#(?`)zYxerfZDu1VxuLc+CQW+!&;hPBRI$`Wtp?pFaqF`d~Y~&2~
zUdA+CRW4hJO#wpiJk2QmoYbQ@7qYO+z=9d%E@*%F!SUT(hdxpFLA8ch?-5A>AmByL
ztIxJs@-6v9bURrdi#|s1Av;O(7r&h+;Nd4?Lo(|+#{u4?U_9vJplm)1i}x8y2bDSt
z)H}HhktV!yQ6=;EPf8}NY|kOSkQ(0ETCU=oM1*89>Q9O!69XI18$J=fZj(Q{9N`mN
zhW03S(3SOw@o>;^3lO#@B2JMMqrG9B)jlI6E+R(}noFF#<nkM5d2s?ren#tbcEkyd
z(crx;24gQPz?=6|@<oY<#+GwH0Kh(qRe`8A_wT<U#5ie;9pNq<#wP?GLmT3kHOtdU
z2TEXVX}pG!0-&#qYO0*85Sen@I?4(<1@!6i{fStlphak<li?EGvD6Eq%7%^djJS&U
z`B>+Z1S{e}{ue>%V{DulnE|Y?0JBi?oQirw$K&j!y!iKin!Np)z~qY45^I4td}$Wh
zY0lTjQxXkUTzYg%S*EK@*cR=kfJUegM=uYpB~ZlU__}4>Mwn_?^5v&otVS}UK_FZV
z`@*W#!&0)BJ~mEPR!oon4y_jx#r1o{LuHm@b@50u@e~WMBU`{DPcvgMV7e9jixg5d
zpqrz(q>(q-(N6<Mx{^l?XCX@MWV3d=3Zgm#QP^NygPRhgSL!4JoU9p}AZUV2L7N+x
zboXPbnmQ~q62>o+U=49_^8_Cvk}||G)ExJaLStl!MdTD#gZs8huNb!I82DQ$TuK`q
zVkr!m*kXJe9ho58f5Vi+&;Z}$yfMJLT<0hjiGw_^@01=!2g1<y@fr6JYw|*(LGmy=
zlAE5H8)_Rj*M(X%4m7UJSl6k}EHa5OJnl7_DXX{fwYx<^G>JNJBdIXNB@vg7law+`
z+SsGFhH}+j4p-?5;Mj~em(j-i^8gj69_+11XH-~P+F1(bErp9S+EBA)W_HXG7F8Xi
zHA`fzx~_`I2j|R-FgF-`?uKUKU%jo8({|92e0v{~r-cpA<O5&c5L1kw@J8b*E#c|`
zP&OpS?PqX9m$2i1Z41du@Cp1W$;bhvZkU6%TxLq=eIRqsQ8mjlZD1zRn+MwYMx6w~
z=+qpQ1Ghlm)lT78wMohC0p{&NG+Pz$MR+qLpVy?O((g{X-v=^VLQL%l$4X$VM^@rt
z!n4Sp(OC?~4uF-*p_{!Q4CTT{Dv1xOC&-O{r=fPIw==9I3RqMLG_FbCWPB@P;Xyv`
z-W193QwROUXk}S(bu0_I-<1_Y!KB9zUpd_*5uSMRV*1Hg_uf36P7-Dm!pNKvc}hP(
z@!;L{vVTX$Q4uX71%P}eGy#PC5yNYYey7F-CeTD%Y$?U~#VkgrdtoOS;hpvMJK<Ho
z2?Z0t(QoAX2(2L=4haDVwChnkBGxL+q#*)6NI^{SAbQA!l(-=_2%2G{26+A7uU*{+
zsfIXbBRWm<KT*KI*ZaTxJuwz?0sbey9JMq79zX|eH!P^x+VTk1@0L59>U^C}XSrqB
zT<Eu7Z{M&(WT9%m+h1#!qPpb9(777Qg`(EzyBz-5KU|CRj}9uA>utvP1?`<uDEXyv
zaAQkg%in7D0{`1fMX`S;g{;q7nilzHdDx#XwTH{==}I48v&%6ZBlF=y*sePBJ5g)0
z51^SxYX*l&-JcJt&L_0>&VM**im6ID#Hw4JI8+s~$UttDCZ>ILv+*nLc=cP=T~fv-
zdZ#}A>K&siM{c-yhO~2KhZM$x49^s|seZY7Ff`|vh3rs<3@=kxe?-erxjK`Y(zCGA
z<)6+2584lEZf{GfvP~Si&0$H5o^Cj;h;I;zG(};1GT>fct*mH*p8%2mPHScR>Qh`i
zijLRe28J+IsG->EY86jv+)$A_5XeKZ6tJ8`$Yb+|^04_l5^d7M8MO}+5P-+3n7Now
zdawfI9_y9SP4BjKmIV4$ln(BDNZGl?UcF;-?M3>v?PZ)vw<j0>MaKOdT@-9iWNplN
z*PCPT`cmN}eP@$z&WVYjw4sfvxXtUIY3{2%q(7ngBSU%4RxL97;hj7GBFD=jt@teu
zod2?kZ8J@~pnq$6^u^13m(#o2l{2b5OgM=L{3lklFR@#ES+6S9yz~gMBQA3CpZxxj
zcetm2HDP}$*AM-RC^ZgkSktK7y!>$?e`0~4)-1Ny?M$nl_b7i+yK2paM8z>z;4!wf
zEnd8HVq(Z`_}tbL6xNS#USGn5hlV}89P&RKUP>!qPoN9?I+Yh~r^b-p&q>@u|4t=b
zziP0_^6AY-*tvDblfC)x6n$_zpOxDfeE#WlKW&j>y+02vVXKVl%t<6@jHrLh*U3}Y
zH{_tb*v%yYKQe+OYq~b-_S1T|I2{vAuODw4sY4IRc61~aJlXB^l=-kX_e^;1%RLd=
z&YdM*_1vEOKcYwurx>X{6K`ab(TO%*=J8=Ty3Uc&+Oj38e<g%%&p~f<R_?jDzA(Im
z9I9aap`~oo+PN-cEp)%|hoRq0Z2wi8^T}3a*-a%3Z&gFRsx3y>l+Yo?Mz6ZJ8P?!E
zOL{qS4cVKf=DM`<i)HW9{WFi|Hd*36`XUDfBiv-6ZI{^&^o3jQg~h6tDiY-W&0Vpx
z<-w@h8IBLie^MtkBB`q2p4`!*@z6$Y%$_9HQ>}v+2erK(>^gYAQrO{Dob|<E=2=~B
zwb|C64-P+pG|IW52kD0T87+2K^E>MdOJ6n~vb7F>8P5L8&1R?GmEy>93e&uG_UeTT
z=dpg_Mc>~xByfcvYPxrwuDkNLd=TH_HBe5qgGy8(l*xsK$XzE!yo*8>=x-|T{&UUV
zkNy3O;MLot1dmhwoLBQxt(lI?KlC3GB~QruZuZEk>$6rRHoaP<=RGS;TUO(dvR74n
zAk2}-N13<TUzj=3(0D$Y(?);FKfd(h^sVrq?oT(O>crNq6Z}JiIWwXVrCsN|j5L?#
z_?n{YW2|B$_MAB~U^Q}SL`PPU7(B{4Y&DX<LTLx3-f8K$&*{paSC}cvOq~V0i0#3A
zE1u^~7<osW!y3lTOVNa*Zeshub-o5gV~Rlnjs8n)UK=LbD|jaGfN$IA=L#*OYj%R1
zjqN(8N$mz_vF?%K_QFK$iq;YDQQZ2MwuC|4D&O0g&D*=Y%J@ruXzFNW4dJqegZ2zY
z9<P~Fz3{x!z@@6@G;qsi*ZwW&J>06>r&71Xd^^_sxozTLO;>f$TL0}1>vNUgmM?#A
z<CZ;>!JS(_gk5iZV&vEKWkdU#nfp`g54(7~q^^JQ=m^GQPs<Bj<DK3z$La1rOufi;
z8yHJXLpV8otQ#?R&)%ro*@p36r*+b|=a$j-JHrNoBKN><UuK;OqkFm-v%Iahtcrc7
zHif=rwPm}(y~SR8{vw^yb9!|Ba8_=7*-3m%x#B&;4HlbnqY{D+#9T%fy*an_E5*Ua
zC9?1om1`^K{z_6aG5cpW-co+9XDqBc=fF;b=_?8hb*2m~spev@9V42pmgme)EUZ7y
z8nMELrw`PJ4%RWHCh31~KYcwgw8l=A7HQ}4FY<-;vc*ACR(H=q)*HI8UgODwC6d9e
zHQZI3u3zz<_>@+axZp!tZ?pIG=Ch{pAJvzC@T)Y5OL)4jxxH%Dwa8YBrBrhf&CSVN
zFK^A)3gvSHJu<Tw(}Eqgk`tr7<%?y)m+id;Yh$dyinV-ybMfmg&m>EMylo=DbGf-?
z)?I3@_2^Z-r8%fk+wQv~rCe`i*&GYG(wfniMV5<BceJT|YBOAAaPs(Yj>m0Gjhmut
z#NoY%+On5kp$?~Wb4?Tp%I}t$eWz-+b>|zDWPWd=8TT^{42{^~#4pK^d;<KG)%TOe
z9RuH?eRNpri+h=dg#P@-FO}}YlFKnZWJO};5O<(j(7k^S9)cStyo@qHi5QAqAgJ$U
zc#jGp&KAMeK7!z!$&xlE7B%jz@8@Wg$3+6EaYDhoNMEg}Qb{Hx4#*m|+DT36PrBTB
z^38Vzfc)Ue6=iVgLLNr_aiL`yGo`EH>-<NOHKpsaaMG<QyNSCGJN$`mo%Kav+FY;C
zH_i$`l`-*}GO)rz=y8bp2S=XzlTJ^Ce-YbGSF9g0!m=}SHdA6L4IPXAg=I#Ql$}*y
zK@jl~YOwyet9Py%9Uz#qRFqO_F6v*TmybmX<&uSy1KCrK_Ob@0Z>20sVHawpt>hQ5
zWuo2W?P7pxTce``=p8YF4a*>vp<Z!Bm>-?ujeaaAR7dBdaTmHHKyWl_aAP>|6`~*r
zn$h`o9?x@hCF&N9jrKFu$EA*FTS}V`Q5&(sE(LcgsPD{*b7TLb)e6t-MkwDq9eIdv
z+6BF51L+)31wHa2euZGP9zk15!IJ3b>Jy>3vG;s#D&1OwD$BE#%nHN^UJ6Fyf|2Za
znQ-zI7xC+7N4v$2yD|_felbW7>CDh$;2DHGUM{k?nVA1bgk+4nSiOrTWe`&+b3k<_
zU<==An?oe9C4by43Co8F+yz1kRgKolL)*(@#T%n!!OFqL5UZjdvA2zlA}O%}t}Mw$
zl>}gZ3}s^iJVVF5Khn*>B@Ay~AePfBWJogDUG};B`H}SViE|V$OmD7*oJy>#)HSvj
z6o0iXWjUO;+-O5A+v+PXG}aZCj<A|O4l&v}?PYiXrb!8mVIEMLKvsP~5`0q1`b~un
z>JIKu#}+&ip>bSq{*4cAK9KE;K$zx3Z#ppUmy*=5s8?8Yj%!)~NiV>%i8hZne1%0G
zbTgxSvl#d#^$V3Tu7M*Q`)=TFVLp8O-C)0`p410?&+#0QiMe}&)Fn+l29H<@(TW_f
zZyDN|0Ux<-(eR95PT7iollRBQL6K2(A2E@q77Y<ovQ~cA!`^INOaP^Uhrq&eR%(+<
z19@=0Pd#FMMBCR{-_l-o7nW=J?P-tmbWd^;btDoL26B9&8|DcwCyx=#GT0hG2AdTU
zyPCgKzk=5|7*xXTcDKnu@J7(S?voH+)GBCq66xz~^4Aj*Gn0w+KHn)M)n@2@DX$cn
za(DrzPsT3^qM=;(O37+2<`S-z@LL(=UVVeCT}2R@<7kGnJfw3VSEWz}>&r#z_P=uX
zqa+z!*J&SVD4)PkuIDg!tEH6e3ZNpiZJM<=xH<E_@X$!s7hb$b-*U3O21i4A<C}jF
zix?DkNd(ErimwaX4x1V+Kq~#d>biaLfIe#AWfFX9G!>cJmX@$!t(9S`j}nnL)x6-a
zi@@%}+^E76qqFMZ)aXq=(*b-c>#kevhBt&pb`>b0Po+Wb{;7eyTB0vH;Udq(KBES8
zcT54^qPc{lm}eK=pEW20G_E8sy+b`Bq<DeWZs#nA%Vfmyty+naRJv1i9}C%=7O=@(
zD!EjcFi&gmBR1LCnTd=hgXvbr^91!lXzUf)Gj0xKn-S(pEn*nwJkX1ap)DEhztrYX
zWnw99fn{L05YC@w{Z4lA!y>fGRBw8NaB&GaQ12J?HgWdVu~3@wX8Ku*CU$hQ&k!B&
zSX_i(B4GTgzLfk;XqO6YDq3fTq?GP1TcD>wt4(@hR{?9Rard{NbkLP)a7Z7$@%kZ5
z#A>`msA-hWfqRe;0Q$$9tV5@S?<L{r3ej3*<57AvBv5)6QWt3GPxmNYz}&jqj$8ks
zeVaP5R#5J1W|k!cI5G*VO;AO2wDCe-2*q0fB<9i#xc(h3tQMB0o7Ik7JP%kX2kod7
z<-~e341;WH?m>Edo`qimCs1!@_sNY!wOo{k<k)c@q==z`wJb7$%?t_|y2yc54MK<(
z=}Sp4PYK1UrT8kKf+yX*MQc&}%t`zjJPxv#B)QZf4os#ju_!VqQnbDaAfpJ^%ZiEy
zvwSzWy>r80A4&qS(|`83{(tZ6<rTu-b+y#Z*>c7W;VH`a*iW(USqufp-o^rV%{tl{
zhv)5smQgMgXE{gx`hN#0{f16^hH$|B42lP}T-cxfmr306VZX`M9<WCJ1A52*{@q=B
zRkY5gD5%djS<~WPc7+XB0((^*m~aH(<@9bpHaXh)zP#klp@QnD=CX*0-%kf1iUDEa
zVt)d%`ya352M>o+gBk<G_57-9uBsY0-s(Q+>7x%2x-2%V+1qS=<@oEd<`KU!`X1Et
z@idJtr@O_y<DUC3I^>$>FY);h82_sTz(vcXGZCDmbHxj%3Je}}I8IK-1L2w5_qF-7
z$>&?sc{ZzTLuyC+pUm^8D>$qFUKl%ORk-`^dD9pEh7}dEv1`}kQ<7>3^OrU|*mVEp
zlXv$Fx?_8?#`;X<ZUgTU5yR+2*&?Cj&`_;=Qh&as?tA|=qgvm}v+jaC{_)kj2fIHR
zY>6!i2;Fxw)+yt@W?7DC*Vd3+wu~o78%r)jtR>fDEcrTJJ$iO@(>0Ed?BA?2wz4o)
zS$W4oV^+W<nR_r*l{ZD~sf!cuTw*YJVddei&sRq4D1V#899b?Y?;5J_i3*SwIc|5X
ziF{l&NWWfs#@{Mh@}TvL_<q3mgf=6qzs|Ty12!1O?Cxz|9{Xi?<Ai?7_I35$+{T+<
zY?5|2C&Uun*9smQ+@eeu_e|(-i{0IPnCEu)QH!0(vaNla+DcvCK}{(uUVjxyH}~$f
zm!%y6PL4$OVI{kYtvQWJ&;HDK(h|Z=IQ8j0@NE0qwZ*mn^q6emr?zSwl=n{_o`{(~
zv?QoGJg!x{WW!CL;h+=)E6dRHHa#IaREpKmEJ1UoB!ERi4Oi_hP<DC3@Q*E@w>X)m
zdi`p2<)*t?M<3T}US}MRd2zp(_Uab-8mV&Rgv#@!tw@ff;O1eQ;>X2}Ml~lRD|g^S
z!V^AKk9wT-5O`b)^W1b%^-b#4Lyzxm|K~E}nNiu-yogu(w(BvfXD5{+58r<sbk#N@
zL2xcTC!ndQr!`FYE#2sn=P8P$N;~A;p+yCj*ZqAvHy$iFe$&=fvwt`$Qo2{}<*JR!
zyIfw~zL`3hv3pDZ_RLaV;49bFeznW26sym(5_CfPZ5KB<EVkG^L4CWeJ9Nd@&Z0+w
zF|egI`%XV}^<~o>!zFJ?;U~jY3%7$#SKQ)l*Q7{2FD4Cc{rnNZf!bfx-(0d=I*0ih
zA)R||x~B5mdFt}?IhMz(?vA)KYG<m}yDFRQT=UAvE`2=k&J&RGZR0%ScthA_=s&TY
zCmj~HkKCin%^F9BMea|_|7>3e!CYPL1y;rUw2Hv-qsvn+{mi@Y^*q+7vqYGTYcO~>
zZ23CbsQ%K<sg<WT)af6|8`za_MeY9S8=A#lT~R@(k$Rmq0cY<XfAgZ*_Uk-B`t+BD
zhR#fu&|OdNeks)IbzN)LxH#MVi}ZO#ovc}l<tTq2DoeZXyZ?-tU-<f+c4Ea)VpG6{
z!%8B<>#jAlGy8D__ebw$$S#ViSX9XRR=&gfk^47LN#(n0F77<Ip|oIesLIcTzG4-B
zzjt&`#xp{clFkl`qIaLStth{NOA%?{sb5Vs-YhRTH7cU?2>QZq=6vY=wlQwS$C`sa
z&qPi~7r(GpuS!0AiE3RKm9-&7sP-sx1cMoOGg(q>CcAc3(z&;-WTLR!z(prE=+oM`
z<iF3{yQABvD|>LbDe2l?iwt0HwjYT%xc>gdYxD4%%e8XDb(C9XO0x2)T5o?o&fnQX
z-<G&sBhX-uE2i)KR`ywp3i*_mtP_7lZ1nkVSy&!$F>}wSdhPTpOuRCt81bI+E^#DV
ztr=%V(!@?RG!bCi>$_4bGg|7XBP$<f(Z}5sgJb)%(+h`kN2`oznuWeA$63Bs6JEy3
zHXU-eQInn<9!)xq5l*D@<c;+f7-zD^9iwED*k9NN^<MtI406+@;%Lxq>sIH&uSaSQ
z0p4$D;}Rxbd!?P32bYvIl(o-IVH8_`PjVRFK1fpbGBS7PMjJ7gu+`{-nSsJ2Y!?ah
zL%gLPu!N9bf$mLrw8ZAOM=0WjI7rX%MjKbDIGwP`cr8&omX|}7lTCOLhdtL&HBa4O
z914t~@6ME+${{r@yq3fk%g|(oHe&a)gAtD{X!t5D(|^RHyoDhoH^8wwIKDJr*&#0i
zgPQ{K1;tAVI;BZ>F2z&68M~D1Q@>UpB{DuT3V|zb3W}T>Jb+b@A{yV8!V1<qhkq9@
zXs*#}2jik-D4TkI5l?>n7m+$_C9nm^=kMrAuu7_v_X^jdg{#jtd1<u*+!d^8mI9%z
zWQ!k30WHLNVV~%XuysN*yJOu#bcXU~_?IVK%t$C6#q|MxNx~!-FYSktcq!L9)-?i9
zA;VMr-`OSUfWr}K@s1LgHqn`3S&dVIHalrDa2vUJem#06uaqMz%~oPz0>SZh%o))=
zmK!WNT9!A!M6+d3OcHZ_QEX^%CS9UQiZmX@Q=wI~dbAg;K#TCwaaXd<3=m4DK$2w+
zrHc~@R8<U$oBTu*-4WX1db||KAPPpb_79#4(A!ui@VSUne`d9|ISB)0E4E0%#8Mzf
z$%^oMG?bnBg9ltt#bXeLnJ>cD+tKSJvQ`25wny(JZXkPqSo-3O3Ag0t2qnJlFc-0g
zsw!=rQy=F$$V2lX=EO=cN6Ex5Sr+TqMz?CR@jE>NTNd>yY^b3Sy>fo!JR1ZI5Wz6^
zrkxx#uj2b#nuzd?GEe56rz7!vp}u${6_4mWWzq!A*hLA5-91V>iH_;QK0JZo@Dr{?
zD2N51fi=QJm;p4kkkaIE!H5y-N=5>IrH<(ZcqWW{bd8flVq-0tKqiz<l8|@QZ@SfQ
zVF~zYreP$zQ^rr&!Bhd-t)*@^U}HP<RVO^4(5&|%`&zZn2+Ul)PZ8_AjJ>NfwB~*%
zjSQtXC5^C$AA-4+g*dvCNsmS{k1<t7vZpPDZR%vtDL15;hD5(k>HO|%lL0i{EXN<d
z-qs@-Vw?h^sW~o^53M(5*Z@gL$M-O}uk3Rh%pIk!RhS!4DdQfAF<QhW0Emfh4p2nC
zj-<EI+U-jMe9bu|M1~t{f>P2@4t7~(bF<}oGa_Ov31x{DjHFBQbh{CW>%Yhqrlp}}
zc^przeheAm=xt7|^wIq>>7JA6C_wx(Y5g|wd?;mY=Q_}}?P)^2Q})$wUJ7)wz)EOi
z97RwPv^xyCM6*CFI+P*a0xnnHtbq6KD=!4NH=KGSAE>zRHuJETZ}(p+q`ay}2v&S!
zoYcX3PrW$_H9o+pw?w<c86(dZ>b?|eY3jh{6&g7|x0boCXX<1-%jRK{sv&2-Vtt8_
zpotYEU>6<QK9Yxa7<4ukqOmHzrnJdP7n_dNHjJN;Rca{}BWpF~yRv#YmP1Sp+>EQH
zaLjy;@`{MO{<W=6xAbE66iKd(5hWt%#0_P~3qRpCLBm`=Ep#B`ag7xsJnm+!dq?M_
zn}SY?wqsX4ra~;2u2fu0RN;^u0?fw6rs|L{k||?w17TYzXmS_Yel;G*kO|B%RwKE^
zDYCN9#5#>Wow%~qZkD!RT!osGUE}VrsxUbuM9YwfV!GZT`+)-ZSS(2|ES(i3qx3!q
zoF!36eC$a~x--yo5r}%4hY<$SPOK+@*H^QCOzNhJH-x@Ihe~CU5dw@CK)a20jj$|D
zhlMg(LG$+{1Fl=^&Vk=XXL1m@f1^n|&Bz1-iMP+AP}!5>=v0AacDV5rN;#HTZDcDR
z!&MTavjUJrM`t5i>sMHji?sOmxri>^wH{kk%lpIRKiUOBbJc(74o8Zdk+rMGz4>y?
zRj+zk(OMHO0M!}DTSHw66?d#ltUC)XC)g*wm9P*{Z;lGB|If2<&Hl^nlh(xlCNXHi
z2<S7X_iDY3=wo!fqW?4fkGEWMV9t2piW~g#{{2+1*vM$*oRe0A>2v;)150-aUTi^i
zn|K}GyW|L^%u(PIez*TqW&b%16}=}rVop)aM|TVU_<{LyWx(n7m4ya~V|lmZR+dV;
zv7gvKUgM<ZuyE_2x;caD$2a#EmGsw~+vPnt4N$kNrrJsE?=g*y_r_oBeEp+hWrBPA
zVBp<ikA&%=+VeW`D6z?r#t|a>bK2>`E^@<*m!bXnxQI&x49DO2!q#OA_tXRaCfa<h
zS$Sw*%*_j`^_&kPo6~L6+sb?bPVj7pg|rht{yDg>opGkY<(1gziK|e$vcI=nw`8BL
z^mTNxWtCmzqkxB}1dA)Sc3urt8%E2nXAMRP`BHnr7VT@LN}IE8x4ezhJtf_v*W{pi
zy)2u4acJdn(`@fdwMhz#{&$uh?V{16;J4%)zYkK@=`W@+5h1T~4@ZBbg&2mo3b#J>
z*j^ZqeUp(Gfn<EX&IsOq)>l%Jqt)<nN5+!#Zlyock_NpaKejJQa@hL!m)V<{O-h@X
zlk3l?Y4<9B96B)VaC~#Z-`~r2MxEcJwM7ucoAd9y#dB8XD_bHv<cn21&%I8(*!wo@
zF8jm&(>ZgA*H1VppfcSi{f(;jFF9NP;vH(jQHS9RG6=_;UCxT|TsnFAZfdrT9=U|u
z*1LcDlg?buz!l|BZ7I6Ap|^`8E`IB?zEo;gC()RWA=%e7J}qcnF1vA>IC}5P^PDFi
z&&#)j>G-#OqgY*N*z+NOy7WT4c+znB<ukEbgjs$6+i8#2|51!mupm6G*22FFEx%*I
zKB~FEZ|wYdkz@Wacg^&R_{pFGp|o$Mz0%1Jw%6KP&zob>{$#aP8UFT+FOw&uY#pza
z6&<?pXyH@-*!qEk_A8PS`aG7bT1$WYFLJH5Ez<R|z4GlZ)oLwAURA0EZFO+m<BjLI
zkI_n#9U9+a)@GfySYNrJ?-|Qadw<;MzX(Jg+~JwrPp197<ev`vZ+q?zxJC?Qt~r~~
z(=^P1=dAC?$T%wV#qdu4Hp&Sd6xA1hO}ruaiezX1GwbJHR%geBtP@+jq<EMiYVLLw
zq|U}8lyjFJpO>f1m{KD%yXH4W4^FChCC6;<uDp=Vo|uokGIfJ3yPD#D;7IzBCrdu6
zFYbFd7_?XY$@&YOWs?1w#wR*2n%%#E;e8XuO9BLKg!(<15#N08)}3uFc;<55O|#ia
z6e`wV7INJxtkw7rZ!h0kJxh!6pBBq6vl4Zi4N6x1l^P*;ltOjx=y~E<a)aU2SEUa-
z_2__XY7Qy?UH9E#sb_A;p(@LmV>fe36*Q%O$DhuPTs`Kr{Y4ADoK>4+aP`lWZ7${m
z)vOHPIwy-AYd4+0t{VA0C~0Ee3EeV?jy@le@i=;dy3<+XV?w7`_xsD6jzhOASBdhJ
zB2xB#eNeDW-TK$^mbS&Q+oO(n2v_Y|v66d${g*-L0^w_bOOe7gFC0X?<3tL(_ugyS
zp72w7s@ij+x0xLgBe+*6F}TN;#Xq`o`EFI(O6T{H2eXEB(sz<_Ag(0I@MI*lLswQ_
zF5$bjSuH16+{%9rn>^Y4e#wbPSC;D95l9v$on%G)lIJOs6C)*eGIM8jI#!3AwK%A#
z;F2LH1T<qvq3Z$3VFsw6+Gv2IBxYi;pSyc4jSD-_>bkN5-CXUhG;MV<d&*~x?(6OY
zZ|GQyd)=O|wf)l==~=`@J8b>bA<8}0>({pC;PC<0R@%7RA9^6c@}~P>RXo3f^5hlq
zH>DB<R-Ggn|E&y`)5Zg!5y}V7K5v|C?W>3pZa}t_OE|zH2iO~W#ihayFD+h3C=ucg
zq~0*&WKqUhn1OON`l9W_c9qd0BU3_5DqY31%N>Tet>bPX+E$90byQz7f@2#bv9;H%
zw&I~7$K9$lvxsool<q<jv<Ijgr7zCOVqiXyhFHNMwduXc5t=FB0ijVuL($!^u^C+N
zXc8uXoapBT<^&K-K;@;cR+?EI%eCnuX|>9*0tv7=k&{rygGNUgKf;ET47&=1-^(5q
zYQg-sKkG5ePqg|>Z?4MJ!1+8@FvP+ty&D!1_;()G=qr0hdkkb2Ntx=?c=R;C61XJC
zan5?Z>0&)-E__|^;??6Mlsp8P6;l0BKA7Hg*Q2yCYbwfZ2y)7pA<Px&y(}kBWQI(z
zp+aqmn0*fer4tu~SL3b$J~NP0A(z4S#kbo^G$ByqJw?WcfpWz+z9pD(epMr{B{F^&
z3uQ+`zVajqLQr}@BxTl&SWc~)BH>sOn>J|i>)~kkvMI#`8{gG#ZI(QB&kj5Yr(A3#
zG8~~AT`WU<y|B9VW118$d>><99r_QAnDQ%^2^4*Y06!UTYf5JZ%M4;E@|6m839;_v
zIx5o62t3cA9tF@U6Znv_2LrN#Ar@jo`CamMk}|kvT=Qlv-Z47cA;3D3Umk&x%U&$W
zXbyGn2740vBW(%qC#9ItVQGId6R#OwW0Fe18>_m7Kt*qCOoXxaZ*@p!(HMB9)XFk*
z69q=uYVBC{D!Jbn*RbqmAQwz9gP#|YRYuc$-^uPk4X{-xF3yM!T9Q6rK`g33ky?d1
zYOfOn=mFRXp(e>{DU!5eJTF*5zJo#G%3~9GDO1h}epHAvb7#+`(qm_VL<yp??xK3a
z<McDt%E(ae`%IWu9+J8~Abcl=f=nga&Cwv2YyHy~eOQUFDI9-GESQ%fYPsQ=&a3WI
zN}QnktTB15BdKgYiZ|wn^_Q^qs*w1ve7kyls|Yb6kea`D#rAQ{MW(p#VXzzVdedBf
zOMv0Z+rZ6>;pfgP^fh}`@h0=NpLuf--q_$QbJ|@u_tex-zIxDIVOuO|adQ<$YmPw;
zpZTquR4~N!o_k|SJlGs4*-S$@&ePRW38a=`Y(5rblmg>dusYzw&A~>-KX2W|{Dv)>
zlkq|siNfYP#QKzwjJXa}E98K4uyx_xorM54#i<i1U;u*j48L}=Bb>Ogt`DNgj2Tz&
zw`X|r`VzleTqhtE@wwimMQwC7N1pufb%JBdxVzNj7!;l1U0g>Gu4i<A5z{i5fB^;Q
zM{o+_DwbpzJ`A7&;8VBgL2f(`U9UNRH1{Y`&D;$+{8C_aG5ae>GVjAapjXgjCek$g
z-aJHz79*O1c>-oHBN5H^)d$@b=Q}lRk(AUp!<!v<Y>IVkA*y()(H$T0ZAZ&e=?uL9
z#JU4EeEO15h}tx^?;fbG)ocUBkss2Gt7u9Vwh`39u=XprP><m`_l3alMUuwdVjP<C
zxSojB1jJYxWABcRyEAPh8Dd2KXSxTM&VT45l+#HX|KUs6L`eBLl&=>y40)szZj8QX
zy0yR6rW6TNO%~6C^A>@V2ih_v=ZzE(IHz+<vxESdaUJw7O+V*AHuE;LuZFN3H)jXk
z?tI=KM)>AYxQYM%1FrJT7}$#b!yvSZW%k?nK~l<a2OpA3l$B8QA9Z_kl{NT6z3Vz?
z?L^?{FsLwn-+;}4(RjH!nTD-aF>4SCq#iI$&xdyEKk2>v+<q7STd?J<0Q_QA9ag+%
zDO2TtSrqoaLs<4-yhcjL|E$vN|M~CSxvn|X%?Xy<wTx<UX+x>P^rSe*G0(^{tEG@|
zqMq&*n<t`U*EMUiFIo&1+fErIo!Y+exa79e^woqzjJBS6k1LVq3pRfCF#htSswPq~
z<?^w*qs!IY3bgzsOIJH)+eIcmdZ5y68xVE0<uUej@NJpV&9$m)3X4;(zWJp>7t;sb
zP4-qj5o85|Z`k{j`%-C|a-7#jQrZNK`tgI4?fGHZ@<HzN&7Bb|-46&?@2~;g<zDjq
z)}Bl5U#@*Vdok}@a=T~W^E=mdJ$2pMe5$P0D;0R|PVigReeCWi_w%Zu9d}}RX@7Y{
z9>}2WweY_qshvIN*0zp%$scSUEvw8A+M>7>-n%QUD%a#~7^mFSr)oB@^Lb8SRlKy+
z^CN$J<)h*gq!6#CM)cYeIK|$~Ey?d(ZXbXjyoCD~Sw|DZu3qjV?iU{3EC-3I-+oSJ
z1Zcl52tDt%PwAWcJML6!!qfi7-S=))AN=|ScWGgFy$#y5Wln<f3E9G6LweAnNPVl8
zR-9_eokwq%zYQ{!`o}i^LCJda*`W?S*LU*3nz+&B(!I)c`u#oK-#XrU&|{-MQkd-{
z4$A$Uf7p4eN?g-fe%oYIiMYQ-Nki_OEHfAM&!Ou&9b(_RL(EtgOP-3a@9!NevFi~J
zz5GJe@TZDvnCHXGtNK`?Uj9#KaiNxe0XllZU-kKw1G|7sK>7Qpt;D*iA!^ZKufGDm
z$9jMHlKjVn|I?`bZ(8-v#qokeyI9J{Op_H)Y)*ef43V1e+H-9@!pSIxG`2p3xG3G9
zY2$AvkWLE56MbD8KXHCdVYBW5h*Yj{ptO8Rb3KGM4X~cS@MKUV7qi*$n85W~{P78y
zwK$hDbZ*_#ZLamq^Dp+*{gpbN|2-r8$~lXXJ*1i&PP%Vu=N)gXNXeek%jbW?^q#4G
zEdCgK?|f9tT&dMEw?@9)wM~mA$<J?H4%5ef^h!R}xL0SFSEz1Q@*jr-FTc`-3V)YO
z9Ps^g|J$#Ar=Ql}vI~yM>i88OU3O_&uexLK=(>;AJ9`qO=_}s7f9lUqE9@(NRJrN#
z!Ow>3za&$v5=vLis(owvHgoi&5?j_UUGsz)FWzSSQxs}Li!gh=uIO>pz87;nLMxwu
ztA`VA&h>R1(#VOjymGwNmUZAy4Yq88DyM5|2A~t;WjR}4|8=WHuqNz0tNU1e^MGQG
z&oiI9KY6l>j;VGF_OsJ>e=K}_dgod3h24Bc_Z2tYp2J3eKG=sYrXP9A<cQ6U$9Fi!
zZPF0CD~j%=e+yl<A$-!p;JIVVfu$|>vzvNUbtm?pwK(omd)+m{@btAhxt@`WdzaRv
z*qBAFKIT=2v5Tm0&$9TLA$t0!`ZtaF$Y)8`=ZYfg4pwf-(tmkX>2S=^y%Fz~MsHqC
zym#Ww{4tNKCv!6kt|Z^sTBu_f7Tfyf^<hg3+e5`QyNSGB0Wk<;RA>cbtRA-y`tg+)
zJu~YGuP<rD6K6fU*CkhGu;WEGoDjg^c~g4%D(XjmcC%g*pO9<x7uKyco)*5zYD-@R
zYg^_pw%y!VC+u8<FZ%4kk<#!ocVpXa3O~k4t&MXsp?JsJOoC^=j<5W+Mx6WCianKD
zGqV*h>&Ni)5LYrFV)(Wa4H(JWP~+{!Y`IEbiHM$1O90akBzhoEi%*0SOanXU?t))Z
z7e2t2B!KTWFsllYXpm-kPPg0`P<U(d6pIPwVuBW|+^Gy-QyzGAeNn$+y|JBQ8zvCY
z-up4X3b1^DU-7GOc-!CecrsmR+{@7tnA)8nPI*Y+@q>}N#1O1eFrlKjyLu+@raaNb
zFL;@FY~ru#MS);+@s`E$LHI*)qdgK~pJ<6TLb!G@ff<J_5RPJtq{z~)Y?z3(V=v#2
zB`v}~66#38iwOv&pXF-?dFqHn0^R{#1)S7}*x-!^#9(h`2^q1^EqMw98UURY0=yi9
zRZ$OcxUj(}6_3bx9Sp8{x|{qYnITF12oriBty~^TCza`s(VDN*_&6z|=P3!xv+Ydh
zB90#5mrTMocvpv{_h$TtzH?DSc{Rpl#BY|*HJ@}#3kXIS5;jG0ESV=SY+_J~a}#7d
zv>aQdQ}UZ}sBM<xN({?x<ngC|bH8+^X>DmutgY%1!5g&{*%CDcoR|KR7&DLl3<)y^
zk4h34Wy+Khq<z>K4S7rG8nnJ{E`@~B;(rlqj+{?dv=Z_w__iZ3U&9!&5QP6Q!0bGp
zhn^8*k7DC^`&eck9l8Vz7D*INxCZ6M5t*JUl99~n1i)i=bS#p~vlAP40Y5>98V+&o
zo}j)=1tkcB3Id{v(yTy9bbt0@Xm})`HUJ(uC9~RB4g50ZB1KM>UI7o96|K^|DIRPx
z%$(&rgEh`ui8osQ{zPziWL}!mS<C?KF`}vov3F_f5Nm)jxR`^!r~}0zLvsiai*X8z
zq(3e~%S(o<6qy?3Ra(sqK$efgN&->{baP=8?u+WG*?6ca7vC_Fxk=rUCqLm@W0TP`
zlHMK7mY@V7Omz%)$c2!o4rs!z;#>v$+@a);gvGGhczzUnusz!4BNadv>0r5EXSY!C
zhBHZO-GW&Axyvf1eF7zl^J8+p-*M6tAP2s5+oPYk(u$|Ua&$R-*cq|0<lCnBB{h=+
z)xg_Q$+sQKMM=dN&I`yhi0~ZA)0%X3a+5cfy0?mL<k%rht#(_=ucY!RuG2uiYLge5
zwfBfGzIKtBi=8w@#;+Ix$ImyOiTNv{p5H(&90c}K_qJ3zNv!#9xC&W4E7UtD&+tt$
z%3tJ)gSc|7F)Ln-HKejlf92~?Tz>2GU_hVV?&wj-4eDkd3Mvrj=n@h-T<nfkBSn=Y
zUMju?G~Fx(TuMkbd`jT0cYieiX>J1<5-=3>rYlYK=7wvbSw4)QZWSd1cG_G8L}rA;
zO6wL}lCfg_@?e$yC}$je)(*-DxItVQW=uPLEk=G;Wc<JxKfZvsv(`qu%W^{pvZMR+
zERC(^Bug?l9<R#mq~^0i*jDsIJL2KS7-FJ0l04g=e!v@T6^@w!u)m!VG*De9@kL^2
zI%=|%G;1aO=s91r1Wtz}Hhq4q*%p>BAb8SI-rK~6U^(7C5jGS|VhE$NWzw-d!g8)_
ziL&=Y^4<t!f`pRe=t$DJp6`dt;nd{`90<G_N7*FlNt1%Sh6{ee&C%Pi%2>jFSJ<%v
z^_J^<IB6WzZc@jx74~iKB%wq~Q{;!NK&#R`7>p}<NI;UKUbPmmeMt51fI@Q*cQRfR
z?a}Q=!{BJJ{6dL0Ac{clE2P4OEL6;_PJ|IVD1kaqF0|7Bez2{Ig`BxZ0+DsL3hV$~
zKm{ZZ+A!?@K%nv;-wy+kk3bP_j0v=|@cumFq6BB`KvBi~@1JZ=wt^q^TYd8X&oAX~
zcYi804LsPLw(iHX9dDL5POdr=`pr3Y^`@1_{tR64mp(dBE$_=~*K1{$D+1TBszw%N
zr>(62v!`LicFUK0lRIy(<Q6^aZ^l2}dUYmrpz?dk;E93k(v;1S6+VF`i{|?7p_p=P
zREKY4%!S}Zc8>fU)XdQn?{NM>wdeSEa{ibX|4lv`sP=vK#@3!FlcQQ=H(kpE&*ty?
z`a^?B{<damP=OA8nf$rs+Y%`0fh(VsEOxG>Pgef;J2`tJe)lo_hkr`Lv%d42xerhG
z4A<6D6k}GCOdYh}Z;7&tNU2d;9b`APtzeVOx>a`zERP(vDsL%&syQz8#qVGLDC`q2
z*8kwO$=Th4+qZ6?cYj+N%H6RXPS|NH-bRC($$7ggQqLW~dM*dQ@}5dBi4g0v0Tvxz
zaYUzM!XmDY_0#*<PRDlc{6DE?vg_08rx^YxXMd(LBr!RUpG#c+Mc(Kyyk_{f&xPHn
z80#YTr@rrf{${JL`rwX@NBpiu?Amhg!jnrUO(i-<_pB?G5Zw8%9_WAnw)N0rk3*4h
zc^cjh@i!MFHdA};-0>G)Ho1IG9w$#jnj_{iF`(Zkw!~n-UGAH+c+ckzEn8OzX+fsA
zz7JoocJ4AQ+TPi7Yu<w;ts|5LMCh*TI=InrX2YAd55K<Qq&r>BL-+UjIVm4$H#~tZ
zPYamKdmN+z&YJz&ZAO{yIY*w~vh7|OB-dg4%=OMqw_?Kf2hKlV%wE5VAn2OF?dO)M
zFeIJMzMrtrwPKmSaTuPlyELplZn&x)jq`d@b+qRA*INPK&qO&rkoHAMlCGo|Ie{F|
zgZd0VU_AHdvb6XsWABx#jyQCl4M!b4(0$YG@5h;^)-~$)*qsU36o4-k+*)5a<z2t|
zEUm0}DRCNCQJ*~L?@l2uwK+xWzB%Srz9MIn{|?*Gz&_hu71Fl6gg^e7=sryzsvE5O
z{1+$q1ecmbs_X0d#ClefyWGxkIr*T5XW{4bPmSzi?{KN)-32K|Sr?6NcE?rjdqCS^
zbfz&T`9^qm_@yUDSN^lhq_jHgL->WvXx6juw?YShrdq|~J!*bX(40Acy}`*d+B-Od
zjlv-Mr#;(-9X8b*TI{&9_2a?s<4;y(Cq>6iPH38hPygCQalE0+irK6}_$GXC&*RnI
z@}2X7oNtTL-)-}))!2yU7XL-KioK9?^Z1X@%pQfuE77zztI8N3##Y7@_uEi?7pJ0O
z5t1m{;dG`&S{%{WSF_#W581#)`G5(LQJOWXofwacq$&ocT@i0B%pw<iCdcp6<UalD
zNdjVF8$8U-sPb89$U1Bk%2HJ1|J5*i6&bp4(#4DB=r-lv(fz5g+moO|qP4+uC9^u0
z>E|_18wNYtzV97ss-SLk(owbAnORogUh*{mTEMP#qz0Bi-NK+HC8S`piDE<f)oF!o
z%QE_ltHe++Pq#LillNxU?Aog(q#q41Sz$C|?dRFE_j$V=L0I{E$J*pg5q7V;7RN3S
z?pLPkM=?f@MSH4B-2&3Hj0zx2W`vzC6QH<GC1e{(Ncvf+`vRV*3sX$yl!v<nFfqP9
zHS#~HAWm*mHG!E@UztqM=8RZ=9d~Cza1c*H=L>C&ZvB(`u0yWFO4tna<XpegWy5e%
zQXGllwldxy*!l1>g2G1PBFIpYgt87p5sW?lb%N|{EXjVdHrmU+`eA_Q(KzJPWf6v}
zYLsT?wy%Y#3<B8{WhB9hmzi2=UJMaXNGQu3bQ)!=qs7K#B@m#*fufWgtU1CSVNbcl
zZqr9|tve;`;kW(S3fPcbpn}2ll#pZqt6vy@8No9(!!<zt1`!N$)Qsi;vN=f^GGav=
z2i>{BSn3ql2Y6_}>v7~M7-h%7xEQag0{>g{fh-0|lLtBiyk<KHmUXBQoE*&!S&;!)
zB9^(E{5*aV;$%GKjk!TX=UGUQD!2w=tY1hC#q?gx_LX}V#!Q9+cab@1v>tdhh!Oqm
z38Q4t^Ty3dvI0n6csl};0LNS-UBbB&=%@Jra*?w~@`Q-q3EggZOC5-7fT@DMmav_H
zY_%H$z%%&LQ8Z)Rm>3Mrg3{atP{oQdRam)2ysZ)qfQXHO04AT0t0VzDy2exmsvAT5
zZuK^1GMJa~4cLs5h(HOdRyfxI*~=X$md%VawrQi27{Zpb7=h94Sf-!Y$iA8~=d0h0
z)wZE_$WbN=VNzaYszxG4|HGz$OL)-&{{3&mG!+G>0dxuqCT4D`8%$L?-C2jB>R@+f
zTKigeSn-0ros9?yosgBpReB_BXeWj+m&D414I&eQIST<v>ed%R)f~`I8|3=Mx(0P4
z^Xh&iO7X1b8tO^ASU1c&v?O<CVzz9>Eb-DqZ6r;Rt+GHb7{*D>Ju&mOyrple%qwJ<
z&)5cYNjCOyw8DnG57RN;L;1_1hS;OaH8HlcLfGe%Y!a+}y^K&3@JTAP;f>jycfJVM
zixAV1W3eI|1XdMFZApB^Jlz*SA`dll=|9Z3#3FA5+(6|(m}plZB3uO@&;laFmjTQ+
zM8}t|^aykTi>#@|rJOqf_}axke61<H>AmUcT0`tGPB~)}9<^w$leISjlw!VK8&>N`
zkao>d4lY?JHeD&>6(;fxi|J~BoaxQTqyg?c5RvE<%RW&=D^UVp%m;F^?nAKIN|;#o
zH!KzKqUa1aI4^Z_UQ=a)i3R);l<U!IK>8iFuWo`3$!|>D1PAIqdNemMMM6cIB@pJW
zqYPDZG>2@X^D8cqp92|ZuHK90sJhXPqk4m+c}reMaCo6)7OPDnoc23!*3Z!rT8=}=
zbVEF(Y1L~E6AK_S88-)2sOF@L6)%esf&z8ENVhPUl9|iIz_aI=9ij0u01t@ycIQm+
zJVZT$(#&v7cQ5?eA@_c`3IICklI$<A7to<DO$RqR3pFf6Fj1*v{O@DUSQR`5mZ=^R
zj_nK>SZcotM(rSFn5tQCqfIbxt}=;%)&mKh5<uM>MTi}9mQyRsXc5cLxVPaokCYv=
zVL1Vrdcsq|0Yb^F49n|ru9h(F*3HdVH228zdCK9C6=_S917S6QsVBglNd0!L5Jcgj
zx)-KLZv~gKf=)7T=6@^A{4RtGrj?HcJeml#k4GKK(-P=+tWd^_w7$Z4-6Tn@FSJ!w
zMDv6Kkv!bz0HOd_MVwfx8KJ!Tt?*EP%9g}ORfifu(<E#nR44E-2_xC5bTb!cIV^{T
zY7xxSen&RPdi_?Vfq`e+KsDS^L9V0)g|UvLQv{#jZ!!1(=!>Al`;{9CoHhKUOHygN
zBEC7ohQdW4J}wgv2MVv5&x;2j*8gi+$^R`g`Tz9qbYn~uw2dDdrd-eL`!Z12bzxWe
zFU`bvT;xfQy<ubNKr211%=7Q&zWwQc+d0P+Z~R`e@9J3Wu3gtUZ5H0WXkGp|sXVA;
zch8#pT)WISr)(mZwS67vqp%{MQDPAX>ypu3<kY3;0}@HfzliJ+;q=Dmo!1Yie%#<p
z9Q*uLI$f7D^{w{N4VNsJuJW2+J(ADP*ESgim|`=2Eg$t+THjN!v?KX^sMt{1PP#Vu
z*2leyadw-2t$+2bVj2Cy*Bb?GitDQ%^c}GoEWtL*CpbJTkh5thSl^CbzJ+<jxNJ<@
zfEXkAwrqZyysGks)%T1cEm;<BZBy}S-KDLzXY67Fc178pn>?GdCt}CuY0+QnUOCU$
ziqnI%{@@?85;Gi5+y4=il+h@mx0nB+@(ykAAdNg@9E6#*SawVG^z{2^U(*m$C3zTw
z{bT<fMvh?3I<Y>g;j{U`gVOJjya4F{=GGgP12Y@*pWLWQDrxlEym(Ukm1BI^oh8{$
zihCNO`{s^X$YiFXgUU`S5jniaSJ=q9q3g7q4|>=-tG^DZto)~QO^j{fV48|QdeFdM
zbT3Hu;?G9z>?Dh(mX3~|e!9M;I&W#xS#Qp-V!wZptyd#j+AC#kN!V(U)j6M=<z2-8
zcJ@MYBsPq>q<2HNYVx(M)G+q$`6uf}?RzR?t#`kwyM7oOb~_ILtZ~DuTN`YmVECAM
z<~HHurvofPb-B>-va5eytK{=ex#nk43j4o%eKwE`XAZt;jJcGz%2jyat@*munoWa+
zy$-CJinwzt=w1>hE58qVJDQhYTi&-ZR*T#=>OzRT_@zu}(NtXabK9{Iy6H9(l<vT6
zH(K=P(9kFGYWsb(Qr7v$l@VJy>Af0zJReal{)qMWA-D7qJ?vsyd37rO73-daT-p3U
z&>lLHr5!nWV?6eC{^N3I<X26LU3`#9SFoh!{@F<SmZnUX$h>`b?pRptf6X?$h0b1Q
zkr#ThDZ<sWdrffhx{yzwDK+v}iTkogdj*e-`)^YH&)i<MB*NwX-Ry(QmVR3Qf`86y
z*XNM2Ri3Bp{7V9aW{XXKJZct(FE3~}Y3}0|FCw=n%}4&Vr)~EVX$9ZQM=!ukj4a^C
z*5B3nwBv(zCE?N4a(V4C`vvE%rMAWEXc2eY%>7)FH7l8Jf5S~w%60T^US65q>)GvD
zC!3Er6799mnR#so*Lmk(6|5PSlOeH-y0pD&^?W6kIOAnd1gUv$Ar!#UhCaZfXzf+{
zBDBy<4Rfpfl;t?<Y=scg$L1ToHofn5(pM*M@msv?$0=LNeLMGx8JAS+jumU(i1lqp
z3Vv^NZyC{y_^M))*mmsa_3CYm&O$$@Xb;%>CQZ6aSe9~34NGi1R>Li&LyqGpa45oX
zNtU`aDTplvQzQ%-HBaLc8#d8n#cManfrMGn3yJRHQo071%UFrzLxUv6<T8%8(RrrE
z7hw~P$QuQ{tjN;O)u<4^gkQA*oMc}FW<K78vSYN*c$5ILO&{kOaDGTM!-=O#Zd75_
za!&$$0E$fW{`9vJPUXl&&?nHO#WKc7eg?5#3ZiEi-NN8QS9X#qN7G?p>}YND(|aS#
z;b}0=LSYeJhWkJ!>^c!j76V1R3&W=hq0xCj`kVqMBu{}~gHyndWGj(?fWZpZ8kM?4
zI~#$jS6N*M`pp3Fa*pIx@V=y0NJ$8=k7_WI>_xPXgy>!lkBCqPSnA|pEl`%Yz*2Y?
zmj7a$H5b8;un5dVevOGK-Y9#K7p?-Jynr?8!2jA72H6g-hFFRx$&wgK6i|H;1^hgI
z!Uby6COV$S_BF-DdcbR!<}Y@f5bJhBg#pi5(Z*3XP<KdOr-f~<5l}_3C7oRo4lqOI
za@k;uRE9aTw@e_3A4y;A+RJ99R_H-!PA7nu;Mg%qgxF%5j0b-?YZMljDV-oKINo9A
zjhAEMhw?$8N4Mz&QYWS!SLygJ8vId^_%SN9so+0|B^?K$ww12z6E&_3)%Smq_wHdy
z=l#0>7f?|%t)xQpn5B@TNz&vAg-TI8f;E+yIoT-KOl6)Dvp_qNp$4Uq2NKYn#txH~
zPFZ$9Yi3kL#~LdubyOl#6V1w+{dV@=Ydz0e&sxvE_I2&+TI=`wqpN8;hzfk(pZk5^
zuN#-z2a+LPit!xm%HQ5`q}D>J*VG+ls0j>%4#@MvL8V#e!RU`M5SH_@LYE>)GQ+Ti
zTx<;aQqz{@i8}-SI-EH-dj$x<UDcMRR3+h|H34rmxAd@ROiAp^3F_354Wq}QG{b5_
zW*bGtduRj9s%=jb_kg&)m`6-*g=ZS#NK6{04uIaR-;DdN8MpoOx-$bsMnZAjJ1L8=
z3DmQViXm8;ij(2s)|HFj9<U4}0W!%9moP5#QK5uv2s$z!L1s-K3q&cn@ATwmK`mz-
z8A<CE16D{H;WixVfO~BYxi<>YOFb#a8t@HPZ~|p-p}#klj(Z-JzKg+mMVKSqR;aL(
z)nYLD1PmyWKx+2DkI<vmbnziVmox(}w(ql;P_#Kz+xb=78Pgsrfc?^fSo?j@MR<<~
zaCoMNh42xb6n56#`65v8<+~D*7~PTEQOt*OpZFqd6an(o-Fz%Li_qpFa{@V^%Y3A;
zfNKb5;W@dcbAbOqR^c8P8%Ag{!*K@{_N~ysQ`%{}ubm2?X_ru3Vuq`iV$PA{XRdBw
zfVR_&(5VzQM1zmUOlbolfosK-P%)J|*)3o#`I-)XT{CTvYShb8&yi*U`fp632bndu
z8H~Yw7yXwbAJlOQ>@8r!dyMoHY67`x9S+GUR`dDvNTpK@qzWyx@7teyYJyHC(bs%p
z<851WB!0#Os8>pOuRci%DuV)8vPn!%Pa!TxV%C7TI8rpBPE4i!ad12L2*qLq76k&s
zhvj?(#Ba+rUBa7@_yc|nGX<EC+M-o<xFjKw^ghDRL;xkO0d#Ii+<P^@d26*j(qz~g
z>SE_fmX;DQuRnOR+PAu9+7U?-cnu?sGAHuQ0Rgh61>XYmGdhO`L)>b2_&vm$=qs*?
zK(lO0YaqE@*Fx0L$Z1j}DLBv<(j-XDnO>gffXF8T1>uD*J_BAJK=B%ewG{*(LF-mA
zJ6SBCETt>RB}6uKB*6+5)>y9aF60hZT!TUh7;(r55UhMVw*yNS08H-GS^kb0ihn4w
zV*V1FW(24IAN+8b{WEPS%Q<^&`Msiv4VlNiD}`~>E57tk?<{Mk<`qqczHC{ux>)ga
zug-38aXkn7t3P){d2E+sXP=P0cK5RBBG2V9>z8c$c6XN6$aw|h+N*--wLi9zzxv_%
zt;fx8J~{uE+OV~8bg$FHj)S43++})O%X}yPXtJ7Tn5^Z8>_|Cr?Dw2EMCsC;$cC$b
zB6&NW6wyB8@&$q&N9yu_A)gF(K45PBYoc1SYT(JRqk5O~qMZ2@=gU*+FOD~)e|5cc
z$@<N+GFHvwUZYgqxEv7>eq>s|TKg`k>DtMAJNp-$dW5*J_qM%kAFaI^nbAvg819dK
zq@LSUV7E5ndjn*C(?0s>Yi<{BywG`R-Ov4_6wX^*`?xzb;`98Tz3DH%x^!{qLKQvP
zc*)K34a-+v{(>={&3$xZ+CGPQee|4g%=pR3vz?nSnr*$SaLx`maJS9q>CjK7rXMA}
z-dp&<^Rr`X`u>fVSRm%C*oYXxqVcP$jS2I|JZYoq?b|bci6O>6S-Im&%Dk7Jeo^mi
zj~U&*+e&SHWN_0~aew=Pwut?wp!Oq+j(WBWR<GOF)kZzMzLDB<ep!pdT6kV!{^tOB
z{*NT9Z<}*XR0p5sW-%8<+&ug+*znGCN9Pzq*AhdSu>tbKu>F$!;AGcTfzOGP7t)XK
z?s|Rt;xQuL<k^C10K1<2{B?Z8wd)p=l#l}%ydRv~tf%(e=YLsc8ua9?_0!Mu8~1iJ
zdX*KpDqO$cX`KD5d~ROXO)mYLpD$dF&78Q9RB`H^`(Tw*+^dg;*E*}WWqtnU#>*co
zEiMtKswbT`x_r@BP#JS0=x%lR==J*xC3hcI_H1d=3!EQ0b*uJO0q6ACPBY7(8z(nq
zTwvuc$iDjR`?3Jl&DB@$W$pMbZ7zPUV+Vg^YpBLCxnlF#GkPaqFDi0{hm`1XawTeR
z1Q#U`*_<kVmF#SJcR{+f|0?pE-wG~&mG<LRU(p`Btdkkv)%4wR4k#~4-~6Dil~!qO
zv0?-LVbrfXQ;ptTNpRg0o-AsKS60NtT%8rXDc<>)?<}6gTskm%J^FTMW&PR{4jC4w
zw%jn^(#+du&|^^}?pfiZE?v(xu2Oo&49pE{Zb{~-?>W=m-aZT1Xqn4NU!fdWv&&hk
z_oh2(E92F3lW$k<n&+r+IG>X}I{dNeCySbDzd*IkqEOP7^<fS|A5rA%uG8Nn<_TjK
z26V6MPZn(c=GP*Jo*Q`!rjplN${(pYdp1*t-(K_``r+(>S+9mIpU(Drp?vf!QMn_`
zr}m5B(}x*Nn73Z)Q}+^d7n1LeG1lMt%K8Mgx1lJY*+)(Z+dzIZAd%$+cXa*K8+)%@
zwBGQZ<QjJVSG139)uEwB=H8#at(ND$=!_n&RCZrI{6}D2B|oe}xXv=>w<|}t_d<Dh
z?+SPINgh7bZJcGf6L9tcPfa=uD{IMbIVSOhW-g297HWUY-<1^91d;Qlu5ft6`>$NN
z6k}{gwp<N-40em%NN}eLGI!JrOs&(`VJ}=cbj2$5>ElOtlk0oW7OMw}4lQAUU1(>h
zD~AVU221xg2JvW2lORM5nfe3EwlczM5EPIhJf)V*Hb$&1EtskeZvKOMko*G7!{6bM
z1S^*9TTbS95Y?zloZ8F)rvidkpoPzf1k~L^1unu4D~N^^osk@!DjyDj#XA2eH^M7k
zsBiCg$o>d7Y?>u;gRvVyi2^g3#Vm;dUhZS*E&?Ais&fywy;DL&wbi1nh!jq8L69I8
zmqV@qwKs`|i!%^q6L~U)wZ>aLA*JQ5VQ~9dupRWrSwiq1-wRblh#5sggb{2xm!KV{
zSFjN+?Q;sCOAOeWfZc=^1lVkyB}1sp)E0|@9GW%+^BxKp8_vJhhjhGzk<<r8bRfyV
z#u6)F7+8QxHDm?7X%ambdmN}P7<`M}3so5Cni1#%NeCQOi=fq-wI6rbl|4f9l=&S(
za5Xv5eXZxp#>)rQkSL6Y%BKekC1PhGqj;;5BwjPN+gvrsL?$G_h@H%#&e8<#F~gM$
zVwdU_1Vb*5=a-#3si1H?`)U!37JM_=l->L?1hI^c&)>}fH=*G`;dC#LLJZV_v?G{J
z=!0Wh4+sVd3>@h-ND}l~n&EmmF#c5IDoe!&)u`QWME8JXn2boF2+Ldo!n6V5PsCI1
zK{jZFmIrQhUyo!nIl}&caY%oAajN`P7Ku7b6o$=X?4nU$ypv)v&18O^oDxcaXx%h>
zIDjoj+nfPk1y~;t(-QVTZhT>76cQ2-DZvSFH5U!H5M(^~Y6D~fGtSh~{TK$`=Z1*h
z#)uXs{+beEU|+YW7H!tV^E39XfbR~4LshzRytrTtF0ACTeLCRL-^SJTo}I4pcf;ki
z=Caad9&!{_nj$p^VBe#L<?sYo5<H_23SmTPp##m-Hj36IJjfaZXJ;mKIFON=ZF!CD
zFgYeGaS1*7`^hFO5BU>8OmFUX@LXu=J8Q~H?0h?s*YSLsbgYYK>>iMn*$#rWBxHPq
zt_jNN;?H7`I&f!(=?54F)<YoC0%mn22>yvIqL&Ia9bGC;V$ip0Lw)8_XH7+9*n%lM
z0+YuDJjO`yCpOARW~DA@Q_Nfk06SP21vC?r2rlzvDDp8mglZ)7&E|ov7NU295>jgr
z*?4sp4EB9EmFMC@bhc+N|Co>yuFf40Hsu@al?ptYqo{1u?mg`02EF!H0`dy_E}l=o
z-BL+90^cOl3|XDr24*(XyM<K)d>*$W6d`C~5Qg!MgP5|L0{i(?nUz%p$ve4CUCiyE
z|3L#ggJGmdLKtGB`H%v(_wcQ0@VEX67!Xj^=^?AEh47oThD03>ZgHDeh!*X_y;^M!
z2+5KYt{elfflJInjNRM7y>9~C&5B%>jduj9)eKkHXj5b3p=c%_J~-_u9c91b7Biop
zgXfvTaW|Xdsqsg}0)8o(-hh~gAQ(nw5<P|kiPkGpq1Ri2(hdPvkrnE>kZqN_O;`+^
zz3FG1M*c`BBq>Iyw(NHQ`EQ#q|I;b)AWIFFBMd-b9N~5Xwtu()s$dBM0FX>3J<%%y
z@ppCOP=<gNL(EjC0<v!gMp^)IyX8@4z%GF~G=PoB8i?RWK$!GMhCar;N-+~X`#T9$
zKBCU;<t-2iyi9=&h(u?q_JXvX2J`Rfvm=0M@n2O*evu5V1GE3V%lE&kq4)phaj|TH
zbBN(hoj4c0W6wrff>Flfva>%51|wfQ>&)N(F5(#AOO2i8zs3*x#OG$Jlj^Ll9eH7G
zPVYGVtlFVYG}WKKU9@iLR9t!RMTK^4=q>mD$!DMEKiyV{+k{%Z#pdn~gCD;fJIZ+7
zjZJJDZ9e?<XiM$=ISloZA9q>2c0Pa>iW@^~&-BiU%y{|nvG2Dx*Y1-^I?H)JvU|41
z=i&t)qx1#`=9v18d_UoFPH4y?h?gX~eeb;v(%FGrmfA*)`gz~lEj{y!_qhGM$2&Pj
zKdJfG<dPSHcYh*Bmu<egkQNZs?Z@2e7yViKTM9|^F0Z0ylh3mS?c-fbKd+a18Q&j0
zzH9Vi@c~WtfuY6Mv5bI%#{~Hc7WS);KbWc1gwz@P$u~O|t|kkfg^xIXiyDqP*kzl4
z{j=Tp#&28-F|QJ(we`i%*Tfhej93zPLN?!(fRRKj+r(if+pPL=N1I7>`OjmASk1Am
zbj7}x1}8Gk_xLO*@Hz2|m1)w}_0OLy`i1Cnr?G$`8gljy8=X8WeOxsBUH+AiztX?h
zv9{yH8PVbEJ_#?Iv*Ujn(-Up|Vl3-a4iUSnC1%2M*!b+RZjy+(vAg=_w;$0rk2uX|
zJDPGBQ5zGj>3~$`u+IbXLEQ_+^>PTDdcqnZGWzq)TlRJ(j+@u5x44&kWwPSb?<>**
z4h>wX)V%m~@eO|WiuAhq4-@?s>{}Jvnw@^8@Z<42(>t1OCR|7??7n~O!grgG?hhC7
zxQ~`Dxfs;8q%^Vr<?K~%dy20msJ#5{UoxE%PE;@Nq;7n<VAoH-J^!}m<gfDJxkoQ8
zN)k*B6&H_BeRWIJTe54-o-bA!IUKvCOBle8S6VcEm$J0Vf5G%7!|P)%(}~F+yBa5-
zhEM!p!7X0@%g3rqZ{#<M2R4NbICNFrZpbWnJYZERn7z`h)@Q8er?@MSXHH%pZ+r8C
zaRypi*BhcPy)*YnWz<P`X6pPUS<d)3(Z{9xWVIft754Ax+^n7306a{FCS}7t#1q5e
zN_*+{wUMC=&cO)1tdHusg8jszel`9eD|K;6AY_K^wf?voq^LKi)jI-&pruZgQAygM
z_bdWQ5+D_F+_-8~GhROAkAagjm0S-zVnqc)A=06$;jBpFF4<-+iMiGJ^aU$N6tWuZ
zn`I>~BrGFZ%@QCGUFdw8qzTql*wdq84vT7C5Q0MK=!t7ECCu5Dn=mF*EaxH|sU#9c
z5kp!aB)3|?FgP6CBeJNBYe4Y0ZKp->w)Nr#OhIuHiUv8NSV|laU5YYr3ey!S+7cOS
z=8OXjO}tG62h}95?1VLYn5yg*CIwP^#j&tm6yf#|{Yi+XOPFIJQ(!6?2<5zt3~fXo
zA~O^k02)KchEl~f#$Li@g1nH)QUTV$faGs6kUt42j%wGvI{6!7kdmaYm*j6T2=fGi
z-0)s%(}@%f2>edrkhoeL6MzNn0?K)afj0^KX5N@FXaTBahT0?_(E`xAhPPea4`;op
zI6fyR7a&&>BbiiYJ%sX$B1~(z5abBcX#E{c2`G;Tiso9JF%>@vArP4E=9HWt0+a)y
z*DLTSFVZK<aH(<(By+f?L<onQgp37G$kBzhZst`GAhIS55s@>}{yw0Pap9PR3`iS=
z-8Tj~dRzEFMBX;BAOxagsHC7CUe-|SjMS^wL4(PUfPXE3Qaz~UNunZvTaaVPXDTo^
z+6933d2)-5U>(oq1oxcIKiJA%(pz}D0qD?HER-M#;7sOv(AH3hn+d3KRr-3F>OPDk
zxLdy*59-cN241!sTiUK2q2^eC*1FW%ONIGqLJJBu0Yx35$w#1fX;vU%ga#;yZecc`
zz6%aRCQN7GR)8;@59DERCMqm9L=E`nIyuHhXUc^&vnd!wDMSMTDBMW_ZiE3L_%-5s
z#I`?+Ea1&jfEX(Ew&kjG0@1n5V%YJcg`tjNFz!uC^(pSqc&+dB$nTJ~hL?)F^||Iq
zHj(Bj2Qb^`l;lz|Qq;T?G(%zrTnxaXFd%{_0N}Z2AbQpS$~AC@hYGF_6^tzXER%v@
zDoXR91%!AosHV#8j1kB&0`McPpOr4R{~a$^I=!4~2iI|=hKk!hAR;%puJCT}=+5b=
zc5>+AVcPn73U%@(e<G090M5J*#I8EUQ22GYHuWi%Gs48OfoTv}Vfm~DGvyv4GS7`e
zDlOrJ?<Dx%j6@kW`lwS{Jb?aP4eo7;;R9_zaudOBP(lT1n_SoUx#lpa@*8lr3TyTp
zb9k9Y;!~^%O2@1!=!^wNN0>Nm03=~!f(9(cUa--%4b$xhwjw6v>%74L0$QB>2*Pe+
zvxY}xSV^y#Z8v8g0gD5|dmq^ZtLC{sm$=gpRHKc(<8uNtKp+0tp8KJLZlkNa16pc>
z<^Y3Gfp{n_CZsyKj~W#yZ+4O}hXb=_Bd(qm1rla{5(D&UWKuys1Gw?ny(0|Ift)*<
zpi&N!;M-{m#oeT*DzZhhk6LZ&#TqPS<BwEMslhEFq-Z>bsk}aN9LCd%RZtMx#6|_-
z=4u#jW*TZE2%kB@`JqnOQN?f<IEniLGbR<S0m(p^L`?mRnV&=LJV(Io(pqH8Vg3ix
znhuxV`#0NU2-2b8CBp&bI*dKUCTH_-mSLf|2>axbpe`ZhJQ<E320T}d!@2GOd%^U2
zrxMVK&_-oVtb?c&#vHhtkd*?T3Vvop^ORFO6*3DD8WH8cpSvQ!OKNU4DZlfs5{QDs
z;2G{b7!PZk2vRWhaC?{%UV8}!r@^c64~5GAuR28k<@3tdDdZFa=Iq!b8}pkEKjsZ?
z^?ds4p-sWF@98~K?{^FRys*Jm*Lo}I=HV5sTUK~=m2Dp^Ys#AYBH`IfYrpQL*tZvR
zcRROzUKDkDR6dV(V7C!w+0-{NUP$IwJ++s%?A`y{MOXhH+6isX-#-3qrB1q`Qg}Pa
z?cD5yv-g(e9Rj@KP3m=S%DBJDL9g?>#B;lU8XI#o-|pH{96$TqvCTZjXZ-iKNLR|5
zY^;N-<F9SJyafO4N#9zz1EIjP%3)Vy=`vqJ``Ql2UyceN`gMC~w~!0dM$3A_EejrB
zZpmoo-L&1Yqk^7ca5eeJ`w|C{arl1c8`*c8o?Ty)XcKnh@%GR0<w+ZstvDs%Rtj9m
zAJbw*frAI{Z%6O1O<oh^+j#ZYvrEqoI&0PqoP0aDQP3JF6F%Md9=r6)<`=Qs#6O%W
zVBSdI26q$#*`{lgZE7iNoU!&;?S{&gv64hMzt;?v3)cMaJ@j8c1F!1zwa9P>{dKIM
zmGKw0Jn>IY_`=*S<r}-IitFZ&-^VFeB`_boc@x;A3EppgLBIS9DsqyG+7f;&W#sDK
z!*5;AtzWXtuTmp;eQV)f$IUlJhBJrgzl-Oeh)(sbVfd)yNl`XIlPi!1ySaOu!vjZ8
zU%1$EP3`p9)Ag4o=b_<Ujb6S#9@Sg@O#HU}d_VWA$r8mTO<GcS_uVSX*)sG|#ln=I
zlj`4Iyef+x>R7bnhm7OG;)x#)TVT2xcJvvP%)j;hbwhr7v*=9*4ES%4;3K;lx>*B)
z1l;Lsi-8mt65}4;CcRkqdi(v)UvzHp86IJYgthY<-zSG{M%#~sg-unMb(Pr8-stkn
zH$xvH-zG&g?Y_CLzPkPB>;5!3`OHJbE6!0;PGA5h6kBa)Nl*NG{!%i;HSgAw@2*(J
zA|B448;2_zP&nZ367a1(I+o-+N3v@&q-&t3UghWIXY3t;Hh;smEm>ZTmwO)*V55M`
zTYe`Ac4NI_8*#Cj0#+7-_42j`BEE&Bk0dl;6}bB@1e{np9-@zvCefpq&DDB`iO|<1
zg=Wh*Y_)e)ugHSjz>PFVDP7sN46GD}6p2}k*v1n$GER!+wSadDVX@RIbYzvg(xL@p
z7R?lZN`^N1$n4}sWZ+6pU`&!}VA4twa!9Qllht7v<++1XoG>=Z9d@&+EjZq6>#OiS
zJ(K-mnFsd(w+K=ydu5CHM!~RVYQQymw+HissQOmz(?b9~)wlkseM$wpDSr!~RblWD
zzol6~eaf2PVmQqW*nra1`Xd%v+Pm_cwnPLAhmVX;HN@g-i~+W2eV%MulLlH?S1wee
zfQ1lPbS~EC!3#8@fPXI5T>@J~09o2actx1u;JBXv<6ji*0l1oCnLy2vBFRdERdT=z
zqQCuY2Xav*%Y2Ht8x47BTZLCP8|B8K_KJLU@q9jZRHmiLt~a<X5HQ?3K%#*JR0kV%
zf3p1SZ&h6A5e%7-zhXDT5Shjv3AIjQP=-)@IPNXh4MTbos*4@j)ZYbhiV>G&j)gVX
zIzf&F?@5l6Bw0YT5IuKTLJIbWO&>ix3fzNe8&Jf$1u>lv_?}D0*5V&lpy-LT;`TcA
zoQhn400TFe0LiLx>DQ8QEh9rJK@4VF^jV*`hEFI}c8MGZT7j_}d!koZ0Y}wvzzPme
z<^e87eHR2%)+FpqFVDw*%L27cmx^lyu2pF#5Q>U)WM1@u0E8Q8&4znvsth)0RB3Wg
z?ikG3WAp|q%P<fM(vp?Pw)`X&EAMBXX~__IyE+YOav0J56H05U4(tX9Q4`=P!{X{&
z>`ZS)Pzds7M;>l2eOzwsD{eTCz-!CVv+u3Kg4~F-HMm&xik#r%j!WD-Bq2JfF|zfK
z0QLjmB)h_PI$$rPo$*p*qdrN<hlqs>1Q4jX#5KT~x7g_5p~Q5SfPD~3T5GlmXjEga
z`W+O^^g-v$Y_!-`ay)mnyTC6y=RGR|Juwp0T?n8dh8K7QLCi|%DfF!=W5m>JL-by;
zUnFURRhi7j#WTy@aCN@!1!Uyah?7-&DPfxJcdRnjl;fQl;nfb_J=DpC9hv}cZ|)fF
z#aIvMC!TV=lLowIm$6z2GXN@kP&(;uaAE|jiwwg(o5?6)30n%Cw+nA^DkTwYtGsGE
z(<A4gTZkTINP&Ql0ILmvrXUI@*GpI=^ZCT~0Z|rd_|VI9gWYRWZoh!)y249E{{_4c
zA5<{AABc)n=O*=ttW+p9UkQU~Zd@&5hp#mC(#gS<qAoh*+sS36VkjKAo{^MTK}?Q-
z247ET0xf2JRHwj2rG5ZV8=#R=En0~I9B;4z)tIdCcUe`1tE|K|*;}-c>jr(=gJ3#!
zSBsMa!)7n{lz!cnKd2yRM*>ijayusjVWk2ucfblE!$mxx&>QQ@x0*4R7_2c7kR*l!
zJaZpG#Gc>ZaQvc~52TpsG3tjD*|`=%1-6^a^xt>o_21H14Q7O?*?1*bn@~`AD@EtF
zLx$Y;lq-<~H$FP>RuN68gL)=dp34$MHo_AV4Y#_Edigu49#+U!I0&Hah#5>Z0(;Fi
zxLX2U3Z^IX0tNtC3BCN|-TWyvM&b^F^}h{n|MhEI1{Ht@{!ZMO|3}E%yrzF6zQO1F
zcVgUs#b3iKmogjKzW21>s(aTj@IU|XsO5U>NUVnk@~Fe>aqICkKaB`7IX}I1AJ~`U
zfWPq3iQ+$EQ}|-Geyy2tGug6w;wlhGoqqN+zMXWAecGh?e)pM%654k2p92<ZB!w?S
zq*EaQrctZDap;h|-6b%87Swy8z}wq!(`wA8j?bYx7Rq+TeOa)kX<^io?kijLjh_gk
zv#Hb0iyv+J?F;GNZzn8z58dXinlIRNDsR!Aphm?!H@v}R@!9kM0pVR<_NuYqZ!!`b
zs?Kb8$<gp*?mPFlq4ys1S=H;YD?TXZ%l8}Y2X4taY7JMOSn2xRuT@sZ3+fq{r(czH
zhwM&MeRpM3ZP3#_aqm~`2)nHFUVb?|-SCV;|J|GYwbx5)D(iPYjut?BeD%~Xbk)+g
zyLKA?a^lJQpp|W!GTax-YumTCpUVDfmPyIOcjs1zVrx#k=3-J57(wjrjdA((`A&)c
z)vE;rxf|$Ge<9OmewH`6_rUnydu}STqV0$1M6MvCWr;%V(4H}(-Exq*gmko*dh{l;
zEQ)yT@ehvOq--L`EOCvGsL%h}kjpoNr&9e2F3l6~yI*=r=cGKpYG}8Ig>QV%t)^R<
z;;)P2c=tD41zLNa@AoyoZ%o!Q418<0LpRudh$An;2d?QLi}sv>YG+B1NA7QwgMyj~
zkHlC?747|z`E8vY=k~assq%_*Ja_a(Y88LldHZ%{Wfrj>SG!gKFBxF4%z||igR8;>
zKIoNf7^`d-a!_;EggR>@-9|zk$`lyq0%7Mi#WxQ$A>YVXteB1KB^pY%rQle6i5q+V
zeQUN)<dv@6?PJvFZ(K=2;*?y8N~-hh6`iXr;0NWhtnZ^mwcfiNaC2uiY4q@FU|2W#
zyP3adeTclGbnVbp*x}0yZKI+i?9d_`opd_{1kiI#jAOD3uMs8(iVR4@45C-NPD<+$
ztRQlD9n^jnMEZ#)VPZ=|1zfe~SbDY79eJ3*3<a3__3UJLX+(Gzl;mv7<Azu3!~BpG
zNJPLx^F9JKbH79m^VNVZF{aR@GkQ)7;DU5AsT8qfO2VEIvot*DW>VX5qzlR7IvGe$
zsS0bzCIos7O2EBI^Z^_X(%|pJgo`_aJ?9{+BdF38_^Du7qR`0+PThQCQ?4q^tikTw
zVOXlPVxi7}&^jBj9&!|2uZ4SK>%t!4bo&#5H!KgWkAV_|94^F3SrI50oA#6E!R7$R
zEY+O>K|=}MU{2t<*~dx{)-XH%L@tFOwacS+0<iHK2dP&&zFMP1^Q<T2PLLr1AOzKb
zW29ju%`^hNc_44IhQSr6ozzK%l`&0MfqEb#1FD9hPt?-jkGc`P)ev65#t^Kz5G{#7
zJs}%|lLjE|{mkw>S`QC&1TVF&TtqfxhBi|;bVu<x_5NTNFi@DV#JaQ-8pdV>ITRUE
z1CgNX`P($*WB-6!cD<w!>Ryn45{+6Aq_<F7Az%@anmO!Yf6}oYac-(y3Q_L*37G(k
zh6N>o0%#y|Dj6{c!6-N=gnA%~pn(U7QeY+CEU4mci^48Zc}19JagenB_HHrICSjlB
z6lEy0$%f-5%6lAQ=BQ?F6e9{!7okHOwx0EDi^V(=^xH-ks{te`-JS}xLv0tlOu^Tl
z80D46KvrkKd^vso6=W|9{TMT>bcli4{+vxTpuT3KlBu$b#BdxB5=6`n2?6mD1(4Kv
z8u%AIHA?&>IbG3;jiefSj4;9#OKo%r2$<9i1%P{2S#=zVVqj}A3r-g1ws(NISIlDd
z;ou;qocB~Za-apG+PZ-~tbuP537|$ADtt4PFdhR3sZ?hSyS*HNx3O6dJS)Vh3Li)n
zp@?QZN)Pq^nnotLy=tVHYD>g4iKYz>AfOu9t?t34HKlb@%ynxvwzNhj)QNd9<syhj
zL`R~$fDj)i@xoByTYo(YMpriCBv_Fgtbzd)$J=R$t5af1iQGsOiOw)}7Z^#msgng^
zI`cMo(!Z1Hq^Z5YRYKaV*-m5|f|Zbi6!lR!;K&lX-)WS$dZkER^*-+x+a$xcnxxZ0
zZ5_M|uwWF)DOQ;P@P9&TQ(7d2VHj{-T(xOk6DR9D%Bz<@A*)niBzhLZRB{@)W<hPz
zw^LXNs7swZ`_+TO&Xfvtae9kwS8j5PW1uJWWC)8@S?pmt)=EWkF9o>Kn-an@lA7n|
zg~IL>+h89x0A9DR0nDBm)<Zt;riVUQt~P5D^R@JG8TJwEWQ!nFbAZ8y`DPYG3KC7}
z3_lw-;`fQWrZ|}qICxp^^DzSQ{6g%0&Y}jZQqTdAEQLRA!!M<cf47kOhj2-t4AT=q
zfW(0@6~c-EM1Ys+jReh*z(B+y(J;X36q~4RYNVj2;^M`ubR~jo(0I3Jv*)Ch3nA2E
zV85gtym@oMAz)2pqhWFXzdvfc0M@!FAy<`k-U*7H0Za=MGFVpy$SS79Qzp<Ocq&@R
z?LB;9c|LS&z~|?`%0po=1OHE+A^e#0CGhwE;m8CJ`=9^+G%0$9SzFGVld5R3fZG}P
z6=9!*E2)AxOIULLzrIS9qlO?2&ux11?(g=wXAs(E<>akV?i)+>bP*Qy&DVt=U*~sd
zgl~a%SMD3kxZftsxUkje;Ae;WsZHmfXWe?M?k1;xOZp{l{`Fq7L&<xOu<ANpYxM*2
z`_~><nHE2yjPkEdmHy%WuDtD)^V2K&{#JMJPv6hFFL7XhxH)P1M6#gim2%_8>p!ou
zrNzj`-0u}$^Xe}YZS${--@eRazHD^-rM$4?iPkcI{q@L(#m!sS03YP#q6wdi>h6K=
zy*qu*#Mz(Xf72)U&~Yz4IP>L4=R-qd#81TKKC9$gqt0f$E+^*hcJsINJxR8vRL2!P
zL|Zl2?UAVqZ|tx?U-M?;l{+`<?M!PVEhCfrPf;E$vzSv**C*LuGH2G3#{&T^-%MS<
zH++ec?QwKG|Bv-Qt-2x$`;Kw-58r)VshdlpJ_kSSckQ2OW?X++He1VWRp?zK{enwu
zeBU4Il77o-D$#YqDB-skq~=AjtIhO2JUajTMnIxI+{H0&o@as(4$S}E_)9yr%bVfv
zzH<I0&)47fz)t6|`YpSfzWm9tT0f`p?L&`6jN;_tue7fgjCRjDer6tSR{il+3|8)S
z*A;;`{MVSYKMhzSpbp)$%ZXg~_{LKhxDEc@^8N7Xe4W(Pxi|G{^j@YQSG?PQ-*b;A
z&TkD}3Irc=nv*Q{+3%;X&%HeDJmCEsarc7_>==D+-NH8;UtVk&_vyEck*WsGg0(Tl
zrWv!H3=V%hB8e#(dL>U&ZX#6noC?*8m0&}9>w5+i=j(T#^38g6GXejwsyUq7?YIJG
z!)@;p)h-()o?O05LFg4JEGl;|fFLIvR3P3kz>eG_!ky_8tN@3Pd~t~+1kB@xlam$0
zpf`{t=zecEPFiP?yc<kR0a)^A&5a~=u>rl>Tfgbsfx=z$?W{c%$^~fa(#}I3RoVT?
z!O)dDyG|3hZlY>3R{b4?efhzcy@mLdZp;}R+LIjW+(QbbAGBvWbo1~F#LLNVbP@K_
z<X{1d!dAM?F@*ydXZTmlQUFdM#*E1t$}(}85uPK#uQ|M)&MZ!nV6~?lofA|n0Yg<%
zPzxTU8iNe!xW7{(Lh8;<4q!V-s8~rzW;<05bQgDlx1|AA8%oI__Y&nIs<EkuqQ!}e
z4cAg<2|y5+!rN?%LEg`KcZ*OKIQR>I@9^_7f{-nt0wthS?S|76Z31<y-cZ4d<{yKb
zy8_;2>@>k2n4R%JMMB4_XU_2mI5u%dEMy)dFt5oSB+-*(o(lB@oI3*|nB9OU*Fb>M
z$kl#c2Hr_`zy)z62bNE!Fae=@bGef;2$%t)SPVlJ0v=&*igb)>m?8Z{3?GMx8mz9C
z57K&zi~>9qaybf$i$JksAmNEI{#cE`3tS-MO8gx;+-(<D+n!ju{H;`PAQ#vtP6nro
z3<zzB`uG_Q4%I6Z$Mcci9B`D&fQ!6Xs4I>YP?D+l1kq#Kzzkf96tjf+&>%lkJ@HP8
zq{uFTOtV+I8U&Z96&x=sH6DT(O`J^DI}Oz+=)HPS0HFp`!Z1x5ff&GI<|AwS0Eh(^
z(zk>*1p!RbMN)8r5s!MQ4B+BzF*9gZ+gUM#TL~y{wXkN6uQ<X@W+5As536|#azToN
zjTwLD08{7YMkE!`qhgmk!PkvG#oC|Jz%hiCZbG$nxMs$lrI{)J0c2nkz1ERVPSeRL
z93DIcF#O<xYx#ym2zKYpjLp_lQe%BM5#Z|UE+Mrn59j)|vQhd3gKT0F2nkpQt<+1!
zMp2b`d0SWEb(|pq{QeSxrD<_$d2T#tie?HIdordBI)0X80Yzs9D9i<@zyT31p5H;{
z>0|h`53F}mOg6ju1;<_K3dsOr5<Mh>;6O%7=-lXd0c8j(c#ELlR44tqJ6}DBgSmy(
z{saQaVLE8Y0Y8<%TMZTq6ZZfToeTpu=!N|EDl|sIq%({_Me0u-3G_1d<}!PV4CsH*
z{|Ml~{%WtnCtg%mNw(S(9)-BWK2sb=0R$i>vpuh=5O9%@`$!{&LWmXy5V!F2<+&eK
z$R79vN_917fa`^aHtg8;V)GvH9=NN7^{3$yunMPW7|DUQ4SQ`p_zJ)1&DY7Y2@VZ*
zCNEN3i2z3}Jg1XFkuZGk)F$du01k4;0?j-o6q+a1js#R#hI~ZgRa#^EGy*N8zYJ21
z2a5z@a4cI*D#~;2NcCO?4TuMEIp-BP{ewfK;6PLECk_o_0yg2vG!57wwIJiZQ$Q;?
zXsy&keXtsb9-<>xa7c|=lc>S=1VU_Lk94x;1xg{JI`^R*YpY`QOUxY9{Nu$i4%w4;
z4&u@#D%@I=B`n~<pp@33_Om*=M9&??X>xej$zYlkc`VKybgD(Li$&EI-dTrGm$P6I
zEVHfF>lJx8^3YK8%X6nDQlF+s&1%k<Lrd=CzuQLqqx>b70jL|qF{$e`09jyeIx~o?
zE9Y5eK+wIe1->v;CAKmuv>rT;;2DU^W%U)qm4?C81`w>^IY@(bl9O84z=pUM_+YSH
zf*f|y{!W84v(d~P^FMzWvSDL)n~Q{)2ZhOjoSzh=QqdJ)Le-O6rbmS&bo0y`a8ho2
zH{S?eSs35~$luLiowgNv$gPP~B?isGY9O*42N9cbxLJZsiE_*x4^qMNQvVg9Vz8qc
z6zxuyDG{co8D{3+eC+@1zm0M&X9Lo4W*CG){$C&OfA)9&OZ=Yw5Qk&7hH6o2Pjfml
z5_xgk%JFX=>%U8nHTv+V!}6y$?Qf2Ja!-6;F}>|;;aR#t%~qqf$X>78hvt1ZcHEVF
zm;TDRCtR`b)9Azd`&S+{>pl7>;`KpqV!p{wSs~Bj0&2QmD{H$AsCTaBt=SNJUC{N+
zjz8alR=dtLyQ2K~jg9KNvFmrdKfUOycn_?gc2oCFbmqE;O}}Fzt{X&O+j6=+Z!$3|
z@xX<xz^k8EKQd?PcF3q^<47*QBq*Y)_|a<aqoRF`(Ki>Wx7?pxuxnYs!37Vr!(otj
z486h5s1*9FH?93a@!LUBz_ABTc2$!<INx5N-7wkPt!14IjQG?M-ld}iGxA-Ae<)b+
z*)hi1aBZ?mHR#~Gc9$lG&`CaXO4_;eTwYq>u_;?-&n@xj#Tz>=4yoGoAJ^@cdZ&0c
zCv7FrF$*IKu3mX<u;cM9vmLW4+8jmci`K?}+w_{$cCIqBnjyHVn!KVuEj%p9fu#4p
zYEU!(E!CChP%Uhh9t?kZW9q>Y{ARxH(&<#n^KT22ES#=)3O@W25$+yVLWvN(U$cRF
zUHD~j!lhn+?#6{Ox{ZBi)0!7wW^ux~K_m(4J@?TC%<0wUEz4|f!r`!NqI%xa`HK$w
zcAk0IdwT0cg~V+B!Rssii}Gx0<9yb$k2cSbO_``(9B1FC&IuVpS_muGo-`(&fsV;^
z4OJ6r1&u4vK`q@Tpjv4BapqxnjY<AinJP>gI8|}wqM4|@65m*vN+E!LRPz#2LlBm;
z4g$rWAEGC-iX#^(T|?~_3EZ+c&&+C9feJ4^xV_`bpU5luD|bm6er^zhyDk5-U(^=}
zN7gMKpD5=?hr}|$CoU%=XCN8K0p0{xohJPRyDfA?1~j}-?}Hx(ccx`2X;wZ#s|o!u
z4jtUYes%gtuq3=SAC52v2QE;8aD|83e3)uP>uZ2rL0GeP4XQ!kLIFJ;UHL{TX2-Y;
zQ*AwjPnd~KCXjhyK`jKFDG;3z9Dt<dgT9@O(Z-}e_kciHJF!f~_06D6<S{%d5^5Kn
zK>X~0Go?=G%8x{KMh1aMgS_q)`KS}h5|LisLdp<a>r05?gH(iU9sr$?NmSm42rN0S
zD~AfVUzC>W0S^`l>%0lqP%4qPAD5<~X=rUg5zD`4#mtLZo#nsWdI)(yX2tS2K~l5`
zmN=9#x&d#VI6ik<4m=bT^q)^Eq{WjJ=yWZE!tS@6ZD-!#nl$2X)mvnc6mY;eoUyeD
zLX?u(R-g27JQCQGdvaL`z?<k5HUP}5nG6m0?rpVt>MUZix(LfadZD~#l#N(1yLoIW
z?GyWf614eF$ogf&$jF4m<p6(#;jUHMX`v&CTm;u*5T;1}F6cSn*(Lg8;i!2hgPdpB
zK^BTz%!=nzJ)sXTVH(OX;Isjcwb+;n{g>!M$cxp>s!2wVS?$0^NtdH~^6v6T-7`=Q
zrV`B$LFd9=kqiwmOab(w;3IsClvstu01wxv7EzMu`*q+8E8`Mi9SU2AuDpBX1R)#5
zI{Oi&i^WKAvC1B#lLi-9aLu+3h2<)+M{IOCIbo2&#FFbFra8jUhkn5Xt72B4qsWhe
zfI%L_o`{ToFecSx3!4hTJY*_PkrgKeQ4vkB>Jta+gaf(8svQbl06=kq;1@;R1FE2p
zn$<4c3(7$koL92<su|pba(N<1yT~>kIGTYyQ`acF-CzJ7ewOJTVrDW`j^3^wguUrI
zX*`gH)8r0<2!9Ml4Q4gSAqoi)i#3L=ZYF?${|GAR=7S#v<}RK|yhsq8a82JH3&td5
z@HS4~KafMe<_#kUET{GYF_~&aPmJk2sK#5x3J7h{>e8$#UXe`N%Wv)jbl#i^sR?k<
zQ>1z?(#f}DIx|^uqf)&OtiGPy<lJrf#paOmOr;z!_GTqWU~Y${p0W2fVRpVjrVRl?
zpjO5t5t!vbV7om-Le@*xz}Rie2<a`F)svq)*d;LRSGoDjrC(z=PDpLxMXpQLQm4;1
z5fG%kfaVuP)IZponKDBCz=Y1EM(kT@W<s^AZ}f}>9x-Etx8|wZfmspFY$F$&9Ebu_
zG&;^nU1&G{02c?PEo7uvJ@{Uo6#QhGfHI?;Z+3Dlv|`2c5Z`)PCGPgmc};vHYM+3q
z=0kB$004{<6s{y~AX->C)6{C}rE>G2usyAZu(f*d^wy5h(IQF)bTvw`f;3JYJf*2v
z50JN_j9Qjc;MCG{B&qX-H+zdIe#Rm5KxWiSm?qdl990jjiJIoETqA9%Zo9zjXWxS=
zVAz3TrZW5!S<El{%e*vr@n3JdAaN4ljUA46SUiEh5TqDLfc)JLmT?rsJN)foa>vai
zQ-Wac_ScdM)^Gn*sQDMk3GkSZ5l6`Cor4MwQzD6a=%E7opj;q;2I7xiU-fdvF2@oz
z&yuZZ!{xx0&mfDf1x4Nx+@IJnsQ?LY&4n-wTtk9%(ggC%!WiBHf!)#^g+xKOCcz0-
z?L;WV{F_Oo^Z!JP`fu@P^n)j!RXjCYw{kqJJlp$7$lPnUB=uXmPUfv&IsVm^CWT+6
z<hi<fpA%*4G0Ov{Pb*Ih(<nzTm76iQdhDHlZK|iS??RmJlB_LJ!~iD`?gaY#M7>$N
z-Lp4ttNzXCyRHv|?+(6a+8~rrvSSSMkS!x1R<KcrAvd_`$G>X&G#usP`EpZHT*{Hk
zm#a6Jr}=cmOr1Kvaj*P~xj+8C_KuBXOmu>%g?r-AbkvE1t9FZiTxa5E`SwKQ%j-v1
zLfiJ2uQJo(Jvq4Xyq~XczJKh6cW~CSSB|Bt>v9kG32tnS^S-*H*#`e7a<DM;a5v?G
zz4)6yk>5w6<p=a#jKOEWPsnrO#+=>rj=OKwyk!@DI=rmXWAegYC&}R``U%^Eh26fg
z*~5o^ZoN|Xg_m{1)TMQn0VPQ$0l|UA=k>nqp?&De$B(Q&&*Zrg>Rub4TSpk8aM<Mq
zw11#d>ai{kS!dBMoxZtw*W{MO0o$L-<C)XiSH;`sZe6i&&9U+^{}-QMfBX|c*Ij%)
z>o?iix$VX49zT@NR(`=7ROh4hGjXk+C?Cmso!p6B*1UNR&EuX(%j{Lu`3Q~{8{f^8
z+`lr{JF)Tm%hxi7zv8#73#nLsk%J}M>{VQ_BZBr(ftqTcC>N(n*YL<pjX$!yFMvpD
zA&`+GrR@pVjB;@F!O9yivjXW~j95mInq$CuJgXFD4!Dk<t(Rh%6ElJWylaC?7vQ+H
zKocq!tZ6}<xPF#isWR|3UJ9$R(RbZnbFeqx*efY8+@oCd7UbB`EW#`JK+GVBQW@ww
zddgkEQ^C*sM67SCwyu}=zmtAJ)C2_uL(f6L0S2j!49!lMYFkDmSdYO-3Pu@EpNLSz
zpzwB=h(h#(T=WxQ5O_h;3ddwC^w5<MXX9aR$>}Pz5<-nf83SavZlU-HC_19xK+2GI
z0=6&vJ6XmMG{aAGlKibYP$amhmu6|OfcqC1!rqCvn}D=J#>KDNX+p8M$Vfm^y816g
z^Z+AOY-t7#;_)CMXEz*rBcV;4a9`-tKp<cShf2B>LuSPp2*rkG49{tTkBSaSHL8|Q
zqs`#>$>MAn6Ab0OVjVE)2LxDL$$l{+ZSTqf%_-KE(1w>e;gU+(C|@y(L1>woVLZSY
zhIMYiKte30v*&Q3o-h;-#9sK$0F?|$z?l@#@k)%4R)OADc)nbCcm|n4jxd0&3&)*L
zhYIUd1$>{1P&gY?7z=PbeWx|S!GNL)wPt@{na)NCc*QHiVqs?^78lnAs4ac+M5PS}
z*b7D)<#M#hCsPfET`<@0Cj+Bwp--wbj}a25@kcL&8{r6@8@m*|)u&++OOX!;LrxF`
zI-VIB6BurA8jz=&0Iy^^5a|f`bTB57;UcX<fg|Xtx*w&^hZElK6f9D)@YLg_E1Epy
zIJnvyz*#y-KI73hrf7mZUb+l!!qD)s8?0o}?PXC^@+jw-7qdrHi@4Y_NG-M{V9v>l
z0wx1YcU|I7e#YU0@NACk;y-FYUNGB#QlWL^2sqJdk;YMWE7+(pU?FesP+$P1#lyjk
z+%`sR>fPRgU_|tNYSWq;B#Yyh&F@s_C=u|pq4{uGhEm5a@mK)l>pmy@BXM2XZbZba
z2`XR`{GwJLcrdf(#6YYMkgrfXXB7#D8qMcVgt5kWH3!%t2*W#>zM23Ft_BN>7EsYv
zk7ka;^DV*RMLVpVcGg(NTu|!ut1xtOB|Oc+a+fN*UJXgHdbnz&Kzfsa@=_fzCJ6~6
z0zK=!GLips+OWU?Tuakz@TDP>o^mbigL<q{s`qYCL+fXW0>k%3AO}d)zFLGe3ByoF
zwM}Q7Cb$&Hz7n&oQOqe;LIKqP97n<oh?l}^#WWNg=~j_-cXL%M5b2-Dhblu7>}<?@
zb+Pa_%MuN+)k}%EBgGMjJJsrAgh!(1OxOZ)rbLTLumj^|7a{`NCgj7^S-=XxdT2|<
zaS{YVczN(%fbERWM`6dMtl`G~{WWDUG5R}2cI7-$7g}{7Sf6%(Jb3CLd@G1~7LF@=
z2YRB6%-Tah$Z>qyV4W-p#0eVEA)e#}WfPXf=No4@;7UGe=vaIUq!6~L_IPRoIR{EG
z=A*LO<%#Zrs}oA=e8p$<!^{{ll?v-m&`IYhEn_g4pEx{o;d{9?1R4xHtcfPHuHqGx
zDnIjP1->=I69gSL2s$~B{;8nzm&gNMlHM%n?lT&p@8m#f{J)qe{_SP<?|v<0|24&c
z4JZg+Gsf;9i_AzPEX!ynz*$V$6d;FE4FlK%;3a@>x-m%-34S9Fg`Omm4&sRuyitR!
z3(|FuSO-t&rPdmMdn>rytzlpx!^>c#*V^Nd177aHZ1W@|@nQj!<{>qhz?t1(%uq(K
z3<CPE*$d(q{|BqH|2BU{kCofl_er$%%PGEbVxhz3Q{!!Q$}B?PyIs1K<As9AU%E!H
zaqb5gb<>XX_b>5(@!sb)p7Z<2@|C)xewTg9mjlkdC&+_ko(FVGFI6u56!l3zXkBx=
z|H=|(uqTSn;#eO0vTxR~$9I(mvf8b#U8JYN(1d4Oo^84K3uaz(nIy<NFY%{$X_KQn
zGa~=6UbTmFv~jHL*dL><rB~_b2iv{ZEcjTdiSbPDYgqj!5?yoicJb<KBfo5}Y!M9a
zx9f?~rkx&W3%tqh-S%tS+~)Aaw-0}C-RZjTJXy=%eeaE)XT?+5&Pb=K*TZ88_cXDW
za95+-uA>&LF!DQ*u`qYyLfgE=&;u?%Tv==ITkCG;>!a9v4U9({a+safeSxdrJieE|
z|CDxvB=pc97w%AM0=~q1GD8DBH~ZwhG&{bS|A#tt(eIcmHq=wM!lk-PiMEQ}X$MTE
z-Bc$9>W89ZtgsDlduyvxKJB8H6288*x!Pw=UGcsla7O=n{%U2pVA*W+e?WZJd$VJ3
zm*Cp4t>DeIu^T(~<NdmB9lK;Sr9?jW1W;^j>iVWGT+;g!*_+(^rH>?FLK_-=swp|x
zt|@V)lP0Efl}FL%XH}@dYFt_MPU<fOxt5ny6N`U%y8MBu_xhcsza8?glBX>>atXWg
zyZytF2VZ{Qy9cR6JG!{wr`aP>7RMO|occ=B;toVfkT((OP?4jdelT7QZecn@4<m_Y
zu?BIC2mqL-piK$Q^M@)RODfb*L1sRWN#EaTs*gBz39y%Z)V(}pwpD583t|RE!}~Qk
z0D67o$(q1$m|x1?5_}?)six#35GEFQv5@I1_rNfEwWAp*$X&VMIX=m|+`w_CCsKy+
zX~ThVe(VKP>2h>Vhpoc#%}fef$O-eZWPq+)>(nLe5l13@u>NPN+9gz+xaJ_d4-cVs
zbKC{)N+%k1R#*NQ)dQCRf&Vs~4U80h{s^{$19;Z1{C*ZP0*2>sH7Mx-mOo<qDbcVk
zkw(1-V0-W*#+vu!>o1QKn8oN)he2qr#5EA6XFGaU*rCPHb|CRbT$AWbe^+<d+vHlN
zxd%}Vvd*`%6(ANUz)_5A3`tdJ3VL#aI;!E+J>f{uD3Rq5TF&1Nm$aM!0=$JT0r+aJ
z#2un><onoa=v`~8Cdx@jD<^Y8I^GRmWSdZehYT=TR0D!^fR|j_i5%%Jgi+ks9XMM^
zk(GK<X${WMi3&82-hgj$+{1=dOjsZU>mI?`VR~Dgk9Clwg)7J(K&A#aZz>#9q5#4x
zxGOf}N}E8im+F(Vp=gbY8kW!i<E~4X?k&RhQGE{!jbsp^qQM=I_~A2v69gfw!BKey
zdU8@ea9Z@d+RkKv=PNdjPKMo)CyqBRz;5M&TBF}aP60YksGBLIeQcgG;ge8r%i9lE
zJpl>qPY)EJ1?V+F%~fQm6)PXc(4b&dL>3o<(^!eV1=)sZ2<K<fJ97OeqNfy5dCG1x
zydzP`d`$qyluhP&4)*Z7#4K|GVrJE@F7(x<_3{rP?UJx2-a@Fsh?rUTw8c>^wB3aQ
z_c92cCHoV}+xvQWb3SpBML``6%ek?*nqr{qs`*%M^aq%U$UL*KniO&Z4pR!p9xjEP
zI?V8dRo(0gVJD^qy7Ce%KvH3)=_=E;)ce-EiBM{mQa9qyGa77g&6<)mK&t_q@Wb7O
z4UQB7@}a#Hk&|DxAofZt=2TKJ^`Hij!#Prg60=%(ORNew&{T}QMZ{Ly3%r<}ObJSg
zL?A$BYaz|*$$3<bS6Z`C0UR?5`&DLpAjU@(ic1+H@=V3X?h+5+16zRxn9!B`k)>x1
zo?fbk9z(#}xHqc>SY0_E_0Z?D81S701V-@v^$Kfm7Az<H0OVB=1WzX@3xJKWtV>wV
z=Uc%t$JMjN-b#gj0sBZM^`J~)d&m_!k1*!faoYz4D~x21dU(j*K?$>2EgF?V39jEM
z1CfI0cM1XMnCOFg5adM%fJ=nwK#jz%2>|88*qix5f>5qXP<^-*g@cb8=`SVT91qU>
zx$t%^#ym$$wVLS7$4s$a^g(UgGj`v_y>cr+gP29FUMLELv1fe5A7gemcS4%rByk73
z7NT_YV?-xdspo!Bkpf#V9b*HcN(1p8NFk!Mfh$O@BnI81jhq8B9=EuRYf8Xnu~Bra
zD9~eMN)q8lX{d7l>~CkzA0lRcQ1>}es@wrp>yv^5vk$0G@La^e!qn_C<n<6&f&+{g
zWknI_zMMyru-#C8X8?f(vszr5%r6?O=sU$n8t@OLq6ZHrXAEDEjctR)CP}bn;q9sR
z7OWPQfDtHBqa2#}bUq--nKuB0F2w<=i|q~H*Z1ab6Tc`3gpeDmZ?RbSB3=G)AXi{O
zgz}i){4t3c4c<^SsL4|}=2kcE%YShD{ZEIFmjAUU!jdijx#;sBg0HNH{?^Yt^1mjn
zzg$T{pxo%i^Z!<R0^bv1=Fcl}|80hz|MY7JUvrF^{e{5;mUdg`Jez<l^u0^!TgNEc
z!4aDP?9q#NqW8b^{9f3!GM(-%e|Yu2W%A&g*2+H-oB0!ZE<YKzouB_!dG<Z`l<ZF=
zEy6!5h@HOa{(;|d*^5puJ5Hbcy>-0E!Q;vAl1pDL5bgRtYRl6lEqbR<IInnlD^=Rr
z^>GR6w}Y|sHG+a(;p$mUKhRePaC9sXAoqUp#jh0$3QNxUf7PKYvKRLR>8<Xim7U^#
zB`;V~b>-2X50=*10WH7#lkc}%y_?g0|C`cv!j-Rn-R<0ZbL*IQ*pGr8E`FaD$FE+M
z_meYktnJvPOA|YamfVcLzQKDN-p=@?W6{IM2*snK|J<wiXD!1En=C7j)cReI3N(!S
z_#pZ1<x9-=&nq8qY0ZDGdHdvabK9bwn9)nKA~)#j`;IWLWpwQ0EW2X!`+%(b+NYP!
zWt)EQxs#PxxZq8U(<1&dy6uTg-*dOCo^npVy^}}GpRbIzUUue3xGv=1{Rcyk-U!qx
zR9I2O_ohyrY9KxOu;FrP?H^^9U(c3BJ>ZUfgMC_cvDl$@-Pc=R_?R+t$J!d!-YyBY
zf4K8$r}LeOOFO-bLo)i+HYLO`;_MWQD@!eo3ofWqF0e}4w<oO+cf3+nzuR{1z2ELT
z;J-KCpLoNf4=vbs#x=R8P=MPWIf{)rRh8dJ;iPrEEzhq5O$ON4@U!E{PQskmc~M*L
z)mLmUZOWc)XFDV4bPymDZDXV``LZMFJ!`tI0^J{1ZGn6Qw(A%am-t1+luJypQ4zlb
z9cDSuGv&GJ1p_=AQ*iFBU4%PZ-{Q6;UTz?J#xNzIe%DjOTikwf5gC!@Zp%IC#o}_A
zjW{0BOUNd}7R{)P5#=6`@fQzqhCP`AadvDJjrI^GBiOPx%s}kBq(U~*s!#CgpecYb
zk|CpLGGsF>lTREHco{_0Mj<x|oF;px*^7DRPd}$HTOf#1+R3EOT(A0sl{mx{rIWu<
zCDDAwA$(P*4ag!;ILHBgJ6wVTE*1JfJ>-fe3as+JexlCh5n#7dnW$$$t|z0K8D0=r
zTBxue;1|%>fL)p<<uYLjUM{K(tEsQB^WmyfJrvrYGKc`xlyJNf8W3!?i<1Ym?DPUW
zT@(BqSK3)WJ%reF?oTldUA~5j@{}vB)FP<XOpK9{i`9L=GS&8Evo&x9Tr{l-57!3e
z2%-VInEQcQ3hoWUKpxC8b4RE~Q0S8vWu}I8kO@=>rN}f4;C~yHaU-W9%+&c%<jU;K
zY?qJ<-~u1lool7?TZTXcAGVvoV5*&I!vseF!_VB`b+6LR{8ED}xJ}FR5pAGXilWtv
zSsIGqN7N!*jkqyFe<?-~JqW-g_}KV~@_dxs!O0fr*Ui=7DIS0amiMg+or;r=sq>k|
zHXL5V5R@kY(8(ZgFj$o)helRM;WN;F?2Jit8!;Tz`pcu-l~%@xdue9^XmcObDwKex
z17@gEAAG@b0zE4u*mDl^N5F0_h{Fw>Ec8+B1+@a1C>Ne7&o>CQJ!K6^`XU3!*gy1P
z7N;-fEiC`U24bkctG9YiQJ+t{kVx;5DM&{~S+T6L8&pVeQ{@)TQII%NIXdm<GAGD2
z@jOd9*)k?MI0VUJPsm@S;_4^mXaUi;tQuo`!VMOi&Ec(uzMUl+q+ankrKb-kjYM%L
za1Ea*8kE!~LyiK%XPd$`DF}Qxe1Dv=o)csDi&W`EGl)3)Z&vJ;3Bo$dvw6D_>pIyK
zEE|!2*nw0=5p<txtUxRp4hqvs{s(*S9u0Nl{(FBI3=$niA>$A+I*5#N8b)$H52YlD
ziqV}+<J35(QqwdDsmWn#j6*^PilTHFbif#*qjCsil7vX;xqSCtd;OmE`~CKQ)_$J7
z_S$Pbf86W7Q#WGFT-W=0zh7^&1iZ904@499Zv4X<fKH8&X@5LFZ~?#IG7hOY$38}4
zhQoFh+~U=RI^(4jJxT;4R{d{aAc0q3)f4KB#LPSwsLmaq-!sIZ|I5w_Ox7m=2I2WF
zWK?A520mc-rz!BjRWYNoq`;uv77FW(gbuDhccpW_yn&t}yilW|o$RynT&bCCkbG7#
z-4s9pJPk2$#9D$mMu$q2awAj59GOOd5fcx>^46Sa6FEUC7)-b$?)7?K1S>-D2w2j5
z_m?X{uxh+z$?ru-|6ha<B8K*ILPMVxjSMs_f;r0ta%tec(?{JVwu00Wq6#4qxhVW8
zR5#tjNC>M13^q7`K1soOknXbR;%P7ovf^T6NwmW$uOf$p4k#3ev`#TEfXpV=O$WwV
z6ad<nJuU&O`d0@x&=HaP61H4KU&?2lq?NOR2%bp+SJ&MMAxe*g5De*_Qy6)3IGPpH
ze9^Vnvm0Did>S@Eu}C=KlOk~tK@{-y?)XT!)oT$>EB6DeI2mYYxg=CG*D71L93|G3
z6^+jd>cGp%j5@OXRAo&SHE=IfA+>pbZDzgMd4{{tu^SYwI<b6;1Hp_Xp;jNmmKz}T
zYjM%_22ulZ0&t&;Su3^CjED`Y`2~4u&kD+QzQIoyq!#0g|7FUq`PU%wZ-<iq_TOl(
zv^f2Xg?nFoki+9;O<^wogkQ)ndhlt*&%tR|=H8l9$1^6x+@98gyPKr+pTC>`qAdNd
z_<eB8{Xdku{?GbzV&<$Lo6kC?t@x~m8q-sE@p&|D+-tSM+rID0%#%aAnnga?E7`8?
z4OgUDE2NYh<l{{%Z{Qmz@MVXm7%IP=g6?@f={+6q&bGR8ZO<*!*UodL2F$^NP`YYZ
zI&;)5>U|ArBTd#JaJf$VixJ1d5XZ&u-%f(Vt&T9+GNXS?yhlR6YKpe=U49?i+i~o|
zB#`fS9p}X^>}0TZ4vhG2*i&dd-)Z4fJ!kWS`{~#1qsGksUzxW~PgT5nx}cg$<X^iJ
z(@#cTpOQNn+m8G6@x1yb<J%X`YN2~_Z^spDGk+_Ns;{V9rk!oP$+Gia!tC=arj>dR
zZr9vDdhuycI5m}IQj)vrhE7vmoT19i1m!d4U+wNU9!R%z>v^X5k(u2Zqxfb{Gr)V`
zM1YT-*-n=IB4l0m-)W^r&DYcCdx>g^{fTP+F~KDI`}YF9oWs-dZVqk#_^@Ky`cxm`
zI{K5pt&(KAeol-wF@6(wAo=uE)=LH4%Y^KH!M$x_1&#H&o0LqT9cSoG=3w>f!7vA`
zxom(**yTd24fg>tjT-aub~u>Im5Acb!G+qrXal=>&DrK5ddWw%YU+%8IVr#<`sT>$
z<^1dw0|WF&%%r$7dh4!dRG;OK{HF|LE-kr@HP9>0ANo-=Abx^d&Pajy3phL3BnT%!
zN{P6{9*Tw8yX3*Y+nz)NU&yGPD<&A<V3gvV*Lj5t_Cpkgt$wUr!?NxVDeW2?^(X`k
zIecOfijvu)iJ6P*1oiu{)p|o_J$a_h%OON8Z?>HgSqyU#)M^7B9AYrOL`_0TD+S62
z1s(=1m>@1>No2ax6TCh1b5#&H+k3cbg7r>MdTw~V^+=+bArWcjupmnzPB*d_(50{t
zIKgKjveKMt7(8U5<Yle|8D$ZM=Y}EK<ZDRZo~Yv47$1Us!xg^31ks67Sxi@58i0#K
zn&C(#_iHfud>V~BE1(+y&CQez)ET!<NNN-AI>4bDFHIy<9eWr7U_Qu?;aua0>@f|d
zc$Brtb+8bF8I)$kLM*G;G}3aG8RS;sbr4E6AmA_SUta=a73vmGsRfgVhJ(2oA7bHn
zM8y!+dnjuTs>do+E5Qnm_OcIkJCma}n6%<jdM;_+5MB>S1A`Est3o2JfB?R3v--k=
z0IZ~HM)waklLoy$NoFKKQ$xZWD2n(<cEBRXe1dKWeI_aa`U+IX1_Hq75_1K}H|m_w
zZYkCj%-dpSU>ePvCG{oA2?F3177PXE@CrUuk2MDZIsyX$8eNVJ!9pJl*UG&$*+CM(
ze|FN}U9q?(6qtAr6ZV9?Ckv8p9T`MXiz;+dBEeE=6}aJe+@d9QmM`6g34&H{7<c((
z_^NmqI?f0dvU>8Xkm3}3C5TuX*dj_moD@>v-}uN`zB_?j)!@f6i)ORHXQa^CZY=_b
zn3$D{iG^TlRsbA8@$mvDvq^YyhG-Xaei$#Gp9O~k<sxyhj&glMi4dIO2n=8eco^-$
zw*o9~14@V5q_p{TTm9x44>N(<6}F^E1R<gI3ZXEARUK3>*EfhMTokO}lBE`+3Tyr1
zH!x*x!tO*rSD#8m|AhW=YD!nykOPvB8+k_egTpV96zfU+a$FMYz8xo)Xh9mn7vza2
ztrj`Ra4pobQi^Gad0*Po90J)&1@Yu5bL!WLuUgc!U|Epb?A48zCpK^hMlC=r8dgf0
z93%D@;kdv;6&rwsRAy3S4fZBv8dH@-by|w(n6!pisQ7nsO4w2n+yS*L&PP5Jj5kV&
zafj|tu%URUUy!tNqR>K?1pU%_{qR`2!o$)?86!}H4t1dl`^$Ch`qM(A-8xeMDb<4d
zP`#P3#a36V8k$|Cu@pLqLU$|l05TFLstpPVfUi{8)Y8lykkv!fVwyyb-S4ybK=M`+
z%?R=xhKfVM%)Q`>k~eEl2LqXD(<GZ7fE7yWn@n=X*+g1<KAB+T>=59N)q_ghR!RIt
zptB?O=ANzSpPWUT$vmzNCh@sp?Jq;(Nf_03#(cc6R(py&z(TCn?*|mr;7LnR_54()
z3SZ!(3c(_m<X;ucH23^WUy73di_Fu^J<P&!vmW9J;#rY{naZPZ$OytTC}0jA9Zccr
zgosgCXc&$AlHu}s@CzvjI*Up<*CuBH11m^wB#W6e(f0dyCW$qgsH#l{u>f08qF#<j
z);2kXh#IZTJi_(N{($yP9EFj;Db($g2?(kgV0N0vNhKxhcOp6v7OIds6+=4(_aR4y
z8X2j7*uD_M{=;&slH^$p;ZxvNh#Qs)0fy)#Hslk_vR*GKlBe1K7b$mU4sq9Mpx!eE
zrWPko4@V2yWRU?_(CId_0=Uwnu{BeLT5=R8DM>g5W+!=^Sg2Y)#*z|a|7j0Es2y7O
z46UtB>zJ5Y@WW*q;MyKnE1Kaat~W3peV_6<EfgUcHTU<ViyJkM@fT%yg4Bs=Od|x|
zf=8x*lDk~P&pkf&gHGS%S%K$0uzk<lh9qQ9tRi^rN_$#6y4vrmS5-!#$3?ACJo){{
zoNd!lg1JYYPcMF^<((X|u~%&V6xtm=LpMK^etDma#Sg1;>l3lZAG}G+G`bn~+2mKt
zswH{ln4~$jpp)@0(dgd@O@kJD|Eajwu|7|zu`X$JpJc%t?Ky=(e=%-$rYhBHf*(~L
zYxAIM3t@f!^YRxZP*Za9KadV!hy5R#o&Ntn^Y6b#aC3UTfNSJDXHR6V3YRzUzL%&N
zGsH7k{e0PN|6Bc9mHVMt!O!f9_wb3GBYoQ)7dA3{I(n7|E?_#&i3aq6BarG5SKD7x
z$*o(ene*iRk(HSPl~$)6?5UB~Mzy*cV#z|UmEO6I$080Zhxi?6inOdQ=-U)Ne2MaD
zec=s1z3m^U1vYNo`oFeq327@bsl<+}^Uiaw9yLQ(ADHF_D5VKWGl_kT*@p_xjvcIF
zeVco|=lJV4X3@IuwYt@8FD$8*<&+vL*8N37&cBv^SzPpe>I>9eW|xFcZ_wVj_TK4d
zH_<b<MgEyz#?Ja4J9~}Z<@GCeF5tO6dN`#0+Y?u#s*Bn=VdHtl8h<)3Lri9OYVyd2
z)qX!(^D6h^qnAsjr(LpDrGL1d_q5R`wW>*gkNM_T`ty#Me_wUTf2?7Nr%z$3QrWY7
z^yRn%NqJja5BX)MCr>?T68S6YOZQJyUVF6BdN5|sp;n99osWyBD)YZfz0t}@3;p#&
ze=^PT&h)#2uj1eKlrrh3j+2`Q9G<ClX6AmGd?MP1Yxam8OqtS2SI=R2?Y(YGG-?ws
zeKFm#*MCh{nd|iY1y@)4+1I@{I$fKbiW$^h*EN#g-#OENMSm`eyF$fKXpKD*wCp3T
zJrk1LU<g%}CzRS8C)W-#_^4+=@C0NRU%KdG5Ym9Ye3&uBHDc|12aUDl;|W!*b%41}
zfTF@7ot)oZVh#P*@U>%tD{dG+bP6jfp>EbYsHAxDPUMGP-nsZ(ui`gOJk<o8;=_6Q
zdZ*w%b#S~Z)5_Nf5=3I=@|_-JBZmXO+o7uQ58nZ9QRO;PdghS*g8XqIq^-Ay$FL>m
zN(}|cLQoOJe?jLTs$6q=4yROa7Ey@G^%O9(kjG9oe8?`%m%f|jqo_Qf=TAY=A!=<>
z$Si!aX#c9qT!1VBBOKUkFzPWwfY2XNIIKr~LNK%o*F*9iKV?=yVS01h3||ZgbgJ!R
zb|w%gVvIwsSIlsxec?p0tj&{OKsDi8skn?YWF<Cxb^`g&kcR>liS9;r2kj*vimGMd
zauA?n5W^)9p!pE3RgP@ts!hsDw;-ysp566Oke$Lp^bEUl2&VWXpx+=sM4}mvL9CY~
zh!pX32q&O&(ladqHw^tW$SmJPl`ka;gX{~Qa-&(MV=lvU#zTB^K(IU+n9lW!SIzF8
zlN15ni~%9*0zuBTLQ^Pihte1z1voZy`<U}WBv?GN6jM9RfpNnsTf+oX40~l8{_-^E
zk)d-N7s2GYi)VS}#}6Yy;uL=Q7#OV}`DWJM2_+?baXCT%M|iC^g7`Y5$K!=|IN|%t
z$l|oDo{jLuRrWVB^Q(fS($Rj2W@tfLBQqAxdse;*7&&P1OYn|_>Ti$ZI81|C`z#--
zz?(v)kXh1TCfMZ#>7appDA#o%r4XfEaY9=(003AaCL*^vJrGfb=tT0Cr6@*+SW~7W
zc%}xX@V)$50ip%h$7#;{Br$kAsL1f(C|BE}3pU?ik-cS=oZCVtI|!_{Zj*H$NDLmu
zoK(xhHDR7(B1WwTrVGbf;NbBA4yM6B*hoCZ8hRMafN@<9asM_yQcylPpy1~U#?mA+
zK|)s0I7hh<N(Haet=ncu{rCo4KY@q+p=YmEiBGZ~b#m31ZJ+TFb4pZy$`FW?lfI1$
z9dM)0X%HKLn4^1R)`GXRL5McXE#7?y;D^a{7%5D(%9SLdTX0rR0TK#MR<a6fPwF9{
zUoNOS`MQTfy?t^={>gNCa4FFP#euhOWbX$EAbZ3Er`9BuIl+#`=Bj2kvsGLQX#Vx&
zq`cTkZvXwSPUtR36(Y*B@i?slnja}Mg}78JzbXKlR+go_2Z794XlFPI;@L0g+hKbG
z!t5k?u<X0w!H2jA`k3(3wmjX8w9IJKiRvVy3eIkn?%IqqOZ6#0iZpFOwq-aM{KL1S
zbo}7J-vO*UD`8nNpN619V0w_!)HHX&41r{#6k{Ne5d?#?|0MY2wx7U5vjv!u1MI<9
zzuy<U*6J@Wr({?Q=T7Sh9jw|QCXrS9;urg*7zfA;r>OReNCUW=HmMa{&_RUOvnXo}
zqW)9Qj0Mv^UwpjDm(1JT@BFzGh(SL%n3ZFW#H4%&_Usn{bU8K=6J@2K$<)s31&1L}
z;^dNoEcjc@`+JyRvO|EjMi_2I>p(Bl_IOv#X>KDhqJn!ai!G)kl3SGfMRx9$y`XDj
z=P3?ul%~h9Q6dLP2w36q?3B*-8JNCh-cl#og2^HHxw9dn)oS5Rd^~1Yk2uYi8dB!K
z@{@PcTo43_I*<j~@>b<YMy_F@cyO}4lb-_3hA8D;j{<Z-n-T;&7Lx{<YL82S@C}lF
z+5}6UC~Tsci0qGrBCb810SciCzAh6mOnP>J+fp^$E`&hPV_38Hy*2G)1PL7rp1sdh
zs%?vF=P#;{ri5YW&qN1nakrtcQt`rA&rWq;32c1GCVQHB2VxNo#jNY}wCOftqq82?
zsB5O2qJ%sljq)JLvTWS$?jfl(gDqnlxlz{!x@8LIcHBMhwv}qobG~ZZblK(cLv^=B
zJ~-^XF^%L&#in}tMN~ilW&f5>Y5oRBvEK{EW$>aay+^qR({F#smzlm<_E`xZ-4Y%0
zO?CWXw6>4_QMAkW2YTAKs|uf5Y%*>X2hk>)R^R=!v8B$5^Oay#?zCXu$&D%g`PNm<
zz<v9Xyxl&g@Cd#w9@ilGWt#gsgdMy2jO9k(ktNvb`MUJhaItSk1Oa*a0eb=icBU#$
z?BizHUff>%b%46>-i5xS&MxO)(mmQ~+dLiLI3Is>W1w>7+q<K7_T}N1td=FG9sT-9
zHQKA|-p#s0Tz?&xN1j+4Mj$J9zn8K{ZnV9vt<U|3_iJ5$I8{7icT^OH96gv}u*c5U
zf6#R|i~d3o8QgiZt}j`}vfAm{p4zM4byewzro}R<TSG*Ij|q$WGUn7?a|O*zE!~Sp
zu4@ry*mm}3J+>C)21`}G{fjhZ?RP4!WC)MTUHEjP>vHt&9q}c@8&(Zpr`u}$pQ#Ai
zMOsf7K(nXsdM%2y$(G_Fhp^Fx!JTu%iZ4oT49>n)n0n=6cA;iL$I6zizxR6SUxaMK
z-<bNND9;t`kjr1a*>lfd<o%AxQ)y)+tep#Gnbid`svZ5c*{PxH?80sLwZpv=Fi!`$
zis{|ax(mKylbC1JaEJK`kJVdCZg~2=#2gcw8ST2c?zMaSt$3l_rT<N1zr^<q&6XQ4
zu*$1ai!VWNvHK7G=dtq{VKsM-7Jl8W8uisJ^jhc3qNWR<Uve)i)S-Q6SNGnlB<r61
zmfp53reEyL_w0%9T&0cSmeX8oNq+U&jmNZiM82JAaVg4J9j{P48h7aWrx5`;k?j4z
zE2+GFA@y3tw!X>AVD5*@+L0GN4-&W3C9WU88gJXn((4NveBRqlX>%H>vl(A?Y<WnK
zTTS(j>^;`u@8&`-I9#|lZ8BJMxVIp>iz9b)F0dZ$IAb4QLViK(9)Di(FiA^y96zuA
zB*?M5-B>B8z8Xi2@MHYxN@yjaT3=|UdIB3=A@oS$k*@BJ6K705Y+PNwZ@kJkLgn{)
z*YmH=Zf-@pbXyjF@2}rrV(@YHm37yqsTQ3zqWC9RYO0cPiM$<{+K`x(=Uq86L7bFG
z8LN>(m+K3Jvd>k&9v#_v)H+~K^Vb8dR=(Zwt{ShhJZ&XU|5q==ze$Sxm(++>#J@1H
znKS3aYJQx4U-Cl91WU;%=rEqx*So=Jz+jBw!!J;@7@M)<{49)+3Q#9&X`##GrXvz#
z+)c1X{*7X>sY?^jzTW*#`{Og^!kq6v*FR&fmqEXz?(4c^P}BK^lwU=U0T&B}aKz!_
z6St*4xp7k_f8JpF<z%>C2cB2h?m0CeU$>Jg^xB(mV$6uv-@B@$F-Ax<wP+Xag@#@S
zdjk1w(|!T;jI1oC*|4IkbxyDk<m)*W5@KK$)wB51p8Wn|N-}XtYeLq_6!2qXAFz;U
zCzn4Ylyg2PYv1^^sUj4!v-Wzwwp7+u%W8R7{W;HY9R+$+FFhr?o8|G*W5bF|FN!i#
zJjcK?v^y#Ut)1V=@06Mw#-^@pkr?Q^%5v>QMvTUIcrc{Xkp!|#i%y6x2qh${V|OhF
zpNdE70_jFAnihbKvA1?O0Z@b`Ea{<HfQSbZN|S<FzGyIXz^fmhKwgrVNnFyC7V3l(
zvu^5Q&O_Q^GaiWqIMnqd1?Uqulb=+>i7myVL0KdrB3pF1>VykQ1l=Q*_~=3ed~`r*
z!T_<0Q{Zbh50-SyxC6u-EZQOHaNobGcGTY25T;SAJ*J>Fr*g&<-aNr=;9vq-VzC1C
za`n@THfKV~g7>L-GE92N<!MO7E!NveqN>p>@Y{<G2vngF52P?%p|!+>gX?Cn^t@+&
zD*20;aIV4OmrsJa8YKuY;nlJtRRssZz79ZCPe37oFB`WOkjoHRG9&e?b>_JlIl~yQ
z7eC7)Qh1wbL|uGwK{>`l9MT*t1q_ITN-#|m2|{Wn5si;xtJ0;x#4dEC`%MmJR)E&I
zh~<p+P*7S-`HeX{IIvM#THq~Q$bw32c^uMciirf(1MMWK_7{1X$$&8GFV17k;|uG=
z<#B|Nwy-SK!6XzN{hNoq>-_$*i~xufqd-AYo@C3d6ePEWiWQ3gDmn={6edp0$lf<n
z1C|8<0RW~+iV3r^eCOr9Br0(*N!Aw!^Mg2aUPN(6i6_&+`Ibx+0<bH0FvseG@{0iv
zv3#-_sT~HPA(jhe0ng#8dLSn_6(Pb8conJ5_no#|HM65eTl7uADFAlxac}~F%g=1U
zLq?ab7fTZRmw@?x(Jn2Y@Muzv7OqGA%+<s^R~m%Q8E9;{pdsg(=4A~)HlVvF-~o7A
zB*vKakmlT%%DEp(L;{A=acyB$k?aVdyZt_#6dwZnQlpORCVkVz90QVP!U3YxA6P+<
zf(t05oiCtEpwR*bm1UFxTWV4QK4KE0zH$P@*FS~b$B5uI;pM`5@@QUnj2x##cCO;9
zP2nqI${m6E$zEcT%frF`C}U^TmGc;dhY-WkwT#1gV=O1}UVdOEhV2QNLj;O)1{qOo
zxHepwZFf!!b)ohoC#_BCq7xLH5IsGIHX7Je5twb2xTDsn&roiP6VYY*7nd{W@1cGt
zlVxC2Q3a;?h<m6QnkCJaAShU6OT=|P7Mz4d3$K>HkhP4;G6b#wzHR|?YNE3p@}5+d
znXG?bdYUg{=J`S`Yo#qpzQ9+S4OA|OKIn!T2~t3=UhoE!T&_T^mW?dnAD=6ng8Tqb
zB3k8fg;L3~u9}TBy3sHsr-X7Oqb6UQg37L}h`|dVBVnXxnUPZRt4{F^pf^A$vnV24
zr6z?SBO(2Og{bqe|4KxrFg0`10GbG*+qA+GmVA#{zZCh?&RmM1tCw`;SkU;c$hLB5
zI``wlXH~B(5;}eyWEQxWYpk9s>c<ow2654F>^CF`bqOWYMW|A%rwq9tu$|;nfGan?
zHq&&}$=yP5P=HwQrSWQ~Cg8@+7ju2mz-<j#yy#~_t|Du^QO^+6QN#GVj!q`R_bCgD
znO3GL$FdPTzDe@#lu7(SmXWp67!mE+B(moZy-&&S6p!^<7NOkKOZ@W;{Ec?*PEzai
zW`X0H`wMEZawBxo)gJesjVn($R$v-t|CQdi&W|$NZCgG<8d=?9G_<asy8AB9_~(}F
zwri(0()SEi*y{Eu9^6|NQFJyd>IwJwH=>u)q_MWf>JjTvk|HVp=~XosPKYYi_NCpV
zVeiiS5oICsX^NySFO{VYij!qtIs+5z-#MkeZJC#Q6fw~{yZUloKT-0}BivxM%5Mwr
z$=;GX-FN2=cKz$S@|>-?zRu*hJ7DK#g7~s`|Jj`7HriW0p2INy(LT7#<$S$ESoZ7C
zt!0C`K`3@P`EJ2-$)n5<E;Dr2o(MU$t$_|`?oRi!`wzeQT6fmrh34;^wAPwqx@c9e
z=Rw#zN6Icw)XKky3G^|!^Wt}GZ+3zgGrR2Q`1+re+x{*kBZe*EtHQsByKM;UQoQg)
z==4Q694YFX-|PJs*>MT=^+nTV6AhmmWSg+7%YId^Z$Eq}&qfzbpS-%}%o)u0!s8ok
zR$XANFX=pb?wMuBm{(aDqYRdjcE=Qvrz>^ogTXxz+Y;MKmT7qLCAQltzVFo%+o!h!
zV<c$ZYszA#KAP#iWUJYd&g)*DoXXc}eTV7qDQN4eb0fsR_gw2{{pI4)fA+-OTlloF
zw<z1NeSDU(^BeCqtth^f>StV;=HT_~>OWr+Um0cY-TKHtP_dVsas8ORQYj@Q)ZW_G
z=j3cxFUr>9AB8_V15_tXOL6}aoH@q324~H8$$rV5_1JK!<mQQ~K(A>V38s;EYgvTC
zY{UB6Jr+%lwgF8yTG6kqi(bWUOc~2yneL`yB^6&)kG<=TV}7KvE_FY@cQ<M6!wY|r
z9!^$Vlf7;5hmo~56Gye)xb8=XH*3&$DOEuj_cUggU2TbT@$-v~*fS@jaVY;J>tU*&
z%ff~S%n0iv;p2}bz6tkQs?@MzPq0D;TxuIA#5GkO@*)5GMC{TLS(WAajTPS19e3?K
zo1|DP4Y#KVojj2R6)yD{_TgQlTYi5L8tb<9x%z#VV^t33B%f9N8e;U+im@y3go5VT
z<MBo=b@@v+hS{X>HzA?(H$Eo5+F4{gdP_ZSr%Um>x~Y9HrNSk*JpCFrt*%{URfiKF
z`fv?|+XYN~t@Q7p#FwS@uQPf!`g<u79Q@a}v`)D+LSiz$D(!dRbJCi33ZIe|@VAe}
zCSH-P_PD$4b6BEjVq`wLpNH(-=A)gi*;I>fm=@eqw2L1ZM=9~lHp-we;>t@0ns-pQ
zziaA2(Q{wl{1{m#s=@^t(a#(?@3>kX!U7Fsx#V@(Yrdw>FSQhT$KvD!ya&e0=4M^-
zukSp6`Kz=J^)hqk_i7oPyD{7(PHcNX?cJdAw<EF^SCS4dpuco66IFglPc3z8^0+L0
zFhb#Ht;vB&%j}QC{u>|cwtp}4vomq|n#U?}*K3C-cWo``+kmxStL&NQCOeejdv1%B
zP0E-fk2z39I(+FrOuYV&{Hp&mzb~$Ky{@CLF6h<mtS@mq`+omRH2Opv{r2~ca;3>V
zR=y=+!Cpbn!a5V`4&Qar7aX;ftlzNf$DvfT&^xQn4QrxRf57XwoUk{4+p{p}KsowM
zp?R`wwU4{eq1HjwU`5w9-{kz%FPqP8?tT3(^yJ>FI>YZi-HPAPUh!z{%=&(pi?}ew
zCHmXX(tX-!@fUiEPhh#ZhXymv?T%1MKZ>e3Pb*7zgOmSQZ&^so+e?RgUT5~SZ9MV5
zHLAcfU+?zlMzNvy_vXxdmwaA<{~Q#P7(J&wv2XwBgw>xy??-!vN|p;gerr~bnVoRH
zMCuGF{!)2%Q?K1m{f!roke&^?DIfV1XVtgCYWdsq54Ep&U0b1J=&#xLSZrSm`N?+O
z>H|L?Nt>2|9X)O*rT4>M<c@#N)|G0<jlSNm6qM`UcDCuU$9q$pGIv~j{)9uR-5ssC
zPU_l!X4SR^+KE_7U(539dGT1>+l_^Xj9^pAzkmIsu$yEZxx|h?e!p0^>(Pyy@q3>=
z*maM4Y;?tTyCo4OvkQ^kXP!UsB`|J~hAcf;*n0Q+U6%~BTBqhj)id1Qn!0T_lLKWN
z#=lFuTV@ZfICt)MZiYYo`KJ)3kKHF{%H$Z&WWw`9d@HS!v-TlbwC1w29d<;op$~vw
zIjFD2R;RRTcNL}9&WCRN(wUx_zd^E=^R`N%+#IWindA!J-#2|5T&)baH6Up~gSwM{
z=St#pD2n$4r8i0balb8E3c@FloUpn8DTZXr$;i17oy>c{=kS0MA~5ZvCpdWMlfG3e
zB!(VUtMc1u9!1_3fj`xEG4JWKi4375=$4BmHMhR;6-tXz@+TjkD-sucpY5P|0t9_j
zkU|_}W}SQj*-Jem$l^(Une}uq`^9a;OM@>{{WSJAWPPpj^dtiKF(N0}nn)|BxFTy+
z7>nzL6j6)1uU-<WMQO|#JfP4nFVmA#!cqN0@(f=M`65WBiYG%T8E|fJoR$GU8=f}B
z_Iv^JA1RWnMJO2(PnWhb+n-P+3+NGi9yF2Tk=R*Mf_H5*2WnopV-RCXT4cfjkp$ul
z6r#+>VAg(cRKRCI>p(_KIi*5t4&Y7y5d^QzQDy^Z-69ARgptQV+7^i~HJlMJ6+##3
zGH53oCsV+*$w~wLzA26`X5VkUn9+uau;W}QFxjN2#5r689*9<+4z#H`J({3jCut2Z
z;uxOHsw^OJ&heo-3C4J<g$LlXoeL>M+$*45Jd%w-e#lyVfNuo!m>`yU;H9LMlUz&^
zDa}_x>T2gCmtY1(6;jIJUI-^bX$>;TMnXn`DZJ7I{0b8swa!S`EntNLPch_1abj>%
z;i>O`c^Mg^i!~22e>dtG0Mj+rL*5k=#M&;_vbm#LnWu|K3i4DVp`qvEWgbr%jkyBQ
z6r>m*n5CisUV|?lVj??92rr3X{{R?`twvumc!YUK5)L{nPy$9Qv|em7fLyFHKHgOy
zx9qZnCo`mvPLvP?<yTcvUBpkuT!%-ETzgt58lNbMC|g!7QfDDQkLo6bsC6nhS)REp
zHqAv1gWE9(T@4Ho(xk|N#@FEK0~G~W^ka_v_JXI-fApBE+&`x$%>`E`JWd!<*V9^)
z<WFXa+3DH$x@?c=OU`AqKUupdlv`G*gKbhZFsB~TO{9UOoM|5_wV4LThTmM+%p{dj
zTr6&M3_6oEP{c1Z4|jZkiUgF#&#^p3ElTU4>1l0phsX_UWM^XG1(uc^w6f6gLpSz<
zi3(ApMXA4jlRkJ_q(IG1^9}bWgN=NuZHl8B#Zkf(muu9(azO-?uKaTkFc_JzQ|JM@
zp;jt}O!A2qjb$n}JQI1Gh6l=4VtEfkko-PLg`C(L0tjAyl7jeE=9OYnY+&*klR|=-
zieF^ma0rwYVQ;g%PMXXK4SBG2w*5o3#^O+>{lGjEHaUTJ+N(PW67UWIU}zu^N(i%p
zU(g;0`KJc<Pa~q32_};JLgFXcOg2Cl>K@<`GPOuOv*B%0Z_RcGlrMguok7Y~v64mX
z;H%=s)16=kMz*L@tf#mHSX$|ZX$$r6<PPa7QgVlSD+BD%5>MJ@1SxGU9`;HcSRBR4
za7Xg&%3+JZfbVPAqV!%$QXkaTbxN?Hc%}eBx?T@yG-*Mp=V52*Qu5Dp^Qm@ldP8AS
zsu4}mduBs`AmzhiD~f(kftw!EFp1}YjenMp#8T~!6GDWGk8+KPSpoEk(B#RxB}9Lb
zZg%W1uEjjK*&4#Wn{Zpr+tYrM;dvziPs+E|k<?f=HN}-^PlMGIdZ@U{U_W;uK>-B#
zhluky4bb(?Vm&`|mGG$=9){Na%G#b|b^z|BBU{`BN#S~qLr`UwCzM0`shCQ5C=6MH
z6>D@}QX&DPX3CSiE4Z8j_ITJypG<MlOsn-aOFw$lc}{Yag*?r?Pfza}TF!M!Y?gey
zK2ESg{Sje(nKQFixL>2K&?W26LBzDk`M#;5SjKr(xquF}?F#stTMo&(nR%bRaZxU?
zv@o@&a3d{DWPAC0#4`KAhN$Ij#+QxlJ1Q8qRAno({5Qv69dG(+WqiJL)warqQ^oGb
zLkUaM+doz2{nJoJ?J8vYoc~H2JX%qBFDGIj!F(6D<<-YVS-I(kvOM$C8*P|p+B4(g
z)EjSAUY+J8nw>NkUVHf}L%8GOIi>sM!Lm`btDPmqSm|&D->8rMn1_zVr<(-TrZ-(f
z3m%#33VnqurR>qgp)b!hU0yR&7T7ZF0_7UcB?M-UeRGD9sD);Ht>pogHSucsJ%`((
zu6pt3->YqYcQt7lSop4aLE_F1eKo1@#qK91M{W8@x2*1*xv73P_#Va2`Mxf_zg(w?
zwtKgo_mr9WF_n?qjX{@e<01l2SoxMwD?ffp>*@bte9B$-EB>H*U?`#L!a}+GZL&a*
zT7Oxb+EsNl!gZBUyzb$BT6N&T{7I>!k7K$rp1%kSwop}T^0Po+-x9Vl(To<OYtM+g
zFJJZ+{Uv@w_C7nIPv}dckRdSs+90v%d4qafR~d%tjLc$l6IKc`(+KCjMRyK8Q`tjO
z>78Go_3}R6G#Yvt)3}ZF;>7WnaSuy<2zH^5ZXNt_-2Qkzw&Os+_`VlwqHt3jiNwQy
z5ucLgA;$O6pXc<Al?nzPrWgCIaGVp_Jexh;AL?2De84W|$@losZ0C&iE6#}wKEFKw
zYD}%DT%W5jPVw$dj^lo4UR$_IB-|C~t8%*b`{!)Wx(wa;`5XJ!C1fcrW1c8VXB=TP
zT`buhyEDj4mBN^%zq|CQbI?NFBeXDM!$C)MKfUlp$jv)?*ihGxopy~{ufuk+kL;~U
z5dBX1_{Q(*O8<mkt;BdEf8`r4zaC^aWsRyS{YX`+Jj5Dt=#3dXouWAEzwPF8K`8Z*
zQrPb^-U5{+R*Isn>n+azc48*~uK4h*VCC3QJ+o^>HC6Mtg42Z2(e=6C%4iyq-J4|W
z)vbCR?h0S+t<`?};m(>8i!N>ex%|9&oV?-Q-_4~#Ysu|^=<R?R>o|e8V=O1M(qh4B
z^?EnchQW0Chjk|fC~f*RAHEMn6lFeLzbA@$zjJuc3B?P2dH%DrtM1*YihA*(x$o8-
zp?HLK@LRV^P|K3YcPVL4lk-!GXZqH>$nbyH?{oA9rL%kYO{|UlnHt*|m53O&;jKpN
zeMJvrkIno_6B1Xn+hR`k{%7Oh|H`++s410fB=u7)e2@C~&Zu9d$JCzxsSXXgx2s6p
zop#;nY2)(EmpMyCBv-Or!!aUdWPR9Vm6%Ecy{1VmYa^~8l2{t+ffEzgr@;ZgflwOK
zB6h$)uQ0$X4c~=NB40B}_u5;&wxDMdawPH9=BKwRkFAo@ykbufQQU?TWqTvjD{q(?
zSP59--&hYcejoCq7wg=qFwI@Llb7|6DQdiMtHEC+B3S5iKxy{Wcop03IF;dJ9xM0R
zT>FmP)RT%g-};wKV-^(M_ByzGt9mUT`h4VJhtA3-iguW3D{cPB_4Y@4BfFBd>Mw+8
zVGp8n<2S6?ck7~K;gX*vyyJJ(*S##2pzEXgG~MU%Ydk(E*X%xI^>j$F`$K5dG)`H2
zm)eaZ10~ZAAI@no`>Ox3uq`ED{EKk*w=^joZss0*<{iJQ;-(4yTlXoU)v9CV;hTFW
zwEVYK?tfX2ww*c82|Zg=v%I$dpHxMC!kNOT&YioD9mqp%5LckIxClx}(Q@;l|M(dE
zpgQllHA4QCDOYD`u`9>Z#%3|CkQxq0z9s+BJ>w+Ytq%OZcu0t=e0ikTsJ<il;W_&m
zpr(wuTTfMN?hBOq@zzABaf3M+X}R)A#jS%9l#g%BQ(Z4N|3y@)Ph9w{AMXBjpU<<;
zON6w!ZC?A$SCm)jQ{Gbdc%N>zzq$q6L=WP~Q}#`@C4Zm722SCfcd@!wy;q%VyIqmE
zlfOCQ-Rsr61X}V-j+)&3t({6;@$%<{Tiu!OtzN3_TfZ8AZW|Bse%xWnD<$8XUUFYD
z8BWW;{xJ|0lsjB%nke%MvA;35>CNP}u563qyN@VI+v3tj{XZ&tU)qV}7e-g+CaBFE
z#>V;^x>B@tw0nvy6?|uPT2V)js&2w(Vw67X_E`D0n_ursbw9eaGhyFzz4gH+krF$}
z5l6Sg%++oTI7pz&@~@xI2`tZMsKkjc3D~7M?U9?jtK@p}fAlT*Z|5c5aexIwbF+K@
z>FdT{bB9g_9%_Tqjc)(V>jSo_c0Z0I-}gEIcK@HX`x}^v*)e$f6Ndv6u|Ab&e2T6-
z^L+1eQZsp&JYQOJqS%My9+ba*CF>uKUjC!W{>FGc?WU~Io~O2U#XCN4D>p9nQVW=@
zNGPgbQW8_Vvc)j5RqxFmg8+G3B@X8CX{gwBY5#pV3;g5I7Y_4Q6V1kY0N^I%kQXhw
zLk<VvjrKGtO-!`Njx5HO)DmY=oMD*~<3KCc6=2fJncx-5u|ml4q}ZE4BW@80{hgmd
zx9wO~3x1E_pM@hhF*2E8=p-*Gz9Mgi<O#Hg796Yr6rxxmkZnTxlF`MOXifzVEtRwy
zk0NsJa}iBUF$17;%D(^zz=gI~=v8gC_l4C0N^*^O2v%q%>kA4wps+HmF%5n{aFb9q
z3-eJIg92ruzC_i&6d3Gv0ZNBgt4e`1q?1|u`<!w_LkO&N`2RyNK_WZD7DV0G6yo*^
zYCy|n;#9p52|)q;WpGFfCYT8{a|EtrgX#Gv*nIKKQODeI`+wk#L?u9DQJrDMNm^MB
z4VvW!7%z8Bl`0fc&6S$}&^rO#M3YHwn{uIrid!dAAHt@a^EE64@?`g~j=5e+^}|p}
zD-@(7O5g`Kv<DvwAO$$sVL}XB0%*2|qt1N3IG8!ap#4SK%e7gT3*E8F#Ans29>?{}
zfM4bLk;IQ#yjZaL3cfar?KAzl<+>Ig;W)9k(}nDDd$7*K0_22)&^*;1NB~G)iE8_2
zY>BFeMl*-258(uZVM*-pVzaPE2o^BqMq@;vmqWRUFXC2JGuz$+ja>$^aIjPB<Y)lL
z8#s@EyUfa!b@|2p!q<c)Xq;}-42^v8B_ewe;(3@zn0}$P0ro)2wvt8M=@$T?PC`K+
zbCSk4&=qH}2(j(_aR(G${Uw9KQvwqYO!9(xJ@a;#?F#^{I?Q0!6e6%m0wr_8e#qX}
zlu&xsoYc<n%p{5_V}bH3awa0Ge0VQ{FLJ=FRO`Ib%*CXZBhW}}FLg0%84j6(db9fV
z$z4$6CT2tg0*A*5;o_Hv+0z+`S15*K-ttU)KT<L?D~J_<wa1d5{TR%kMa_{v=^>Y;
z7!)`+PA=|`5m>UVj)5K#d`u`+6<-K+h=|h1V-ql_WH*#lj;aR=sPn}Exg-cu0HC2i
z*@+6&o?|o{ksC@p6QU!YZdx#VabbPquG_pn6y|yrn^9*twV;SH4rB)&e2mMZb_ROD
zz~2I=KtYgpU>@8ei0A|yq-UgZO$$*D?BskIu4)2iIkQvFCEyQ<>b5D@3-)sB78v6d
zZ0xoufKN<ljYnk=(Y^LGnWla~RU!Q>YdR?e*0uu-mJOdYM7IV9(PYhJVGGt3K~F*N
zA*PT9ttU~1a10A#*~|!*U1!dRsLhcwiBB`R5>x<xAR?%7<Zadtsz+1-TgPAshVXey
zHCE?OQlX)Mf7})&PGK5~?ERwH40sZQiy+G-f`Ai!z^D;I5Ilt?uOP*I2ZuOV`OQ2F
zoJ>V&G@>#>I=E03oS(%}cM3qAo-WkYRVr2w>-^jY4+Rm+#<?q9ez9$?zlZLYwbDT!
z>&P9h%DV#|cT}5Bx;&6HY!S_d!hu<@R4b?LQdB|m8AG`JYC?w~w7MbUWCc81)x$uQ
zlqs~;1swxol002NlIvQ&S-bjn;czh^K7HjWE+~sBeBlB{U?S|w%N_7AH0zhjqFDEf
z98apGWB<7``ui5qvTo<DT=C;Z`x1X?n`PG>UkNJTXXE5@vX*<B_MiOh3AYPrM|W-U
z7oop4DX#I$4Q6<onrd`Nzfh&_`I%aEh!Z9KG_5h+5Bn+R#<L{7FI0Qn?{^OmMZ{<c
z&OiTSH|TOq?Tu8vrGM_ucjAnIK-O8)tyJnU=3x)%($Vh&r|nw=<$ljA9I@`c>}J|>
z`t`8Tb)$JNB`DSNO;bh3&g~vG#g?tz9@NBLVzdozYnc~bdfl$MxWi{G0dqQ2m9j_k
zt+;iuj4VT{#s2Pw_pBdgzv;?%>7T0J?vt(5Wx5{UC0NmrUth+(b#)8d%FAB=+NeHL
z&@pB!VtudbU7%m7Q28Jk#EVur(Q;>;7ZUh7ZB@}fcck2mSQFDtp_9ij3X`h+C6%U8
zrhgtMRjmJuEFTGYBv$*vf-fU}wWAyAhA6Ct?`qOkPG&)1v&8h-b2Y>X!fmJpOp3&x
zj&R2>9ZM9n3Y-kc>{+_UGXjxISyIz4#gIE`qLm)6XEf_|$8c8>KX>J}$<M1sR!NiW
zjC5kOe@Y(x5c5;(XWPn^B8JZr$jpa3v`v)l9AvCJRn+ELJq|cX_V3GtCN5c@LtcAG
zce{Cant0T>Apb5tZUfkd1SUD1Pj@Twf9=T7R^I@8R)aNe-?Ik{L+{`FQ}?h)`A;oj
z12Lx3^X-j&j-H~f>fNUTe{3Nv?P<Rn_Vts{x=P}ZQnJ7A?4@gz@XYPoU*y|;SLk}^
zs=lXY)%f{B<=MgNVy}Xr{BpEAb?4||^g6{R!JW#8HA@<Gjs#v{UVotUeV6ygdc6<X
zGl!(AYfq<{KK`+B#fqa`Rag%y5{91L5q2+sv973p&A~1C1-`#@?wqlHIy$>^$*1MT
z!(S>no|L!E{JBHLN<nA7{N9)sP1*O{H!t^xOi&G@R9VTm$+7og6r=1ZhY{x467;I~
z?jhU}@^?krx229F=!lEQq7U#{>9>rpa=-80(drzO`{rqrv4(o^`9CRLH$T{wrQfKT
z<k{6FdlADw3Y4#wJxxkoG9fkEQx!4qrp)$!LgH|}-<%CuNUgReYa2e@+QGbj_+$5v
z?OUGr3q9_YFVhOmWbyJ74R3dnjI%mE+_r!Jj4ky2gAZ<v*gAbU=;TAHpxg)D>+0^6
zNvgS97cN@fkTCUWh}G)EE83)(pHpP2eDJIF+>M_P9(?!8a4eJWhs=e|ze_Fti|DrK
ztp5M}pJb(Jt(Et?E>|0Ougvh26femjavSv^2(}KB8i`{g?T~BhrxT&t4I?megS_+F
z15-t5b(Ymea-9c{<4{hPfpZ%e-K$l~5^K92nw&UOtFR0)Uixmt%xn94t+}e3&niMC
zG=hG6-6_uSIlg_nbc=VKTK)RZIS-Rv{^)HQbL$OC>t3<ru&jyJR0aO+Sk!NsNuBz`
z)3$&7Esr%RTE{7!{wY}4&b^(#e_iIO){na)M%oQ@Cn^tF%G^8jMA!2A^<$|j{|pV0
zKIduX8xNTb55#)k`=WN-&V17N+wD11f!D&m&No#*^e?8&yPDIRE|U{Bcj0}kkH-Am
zp#V3=?~{r23!2uYdrd~`#WcFU`O9}`DX(f)s42^cIsU@xE4{x1<L6g&=1RHH>}Khv
zx|au0CSlc`yvQ|4M)dx`_Du)k$G6j;&7Azwb#f#9@`UuY5&X?a%@lcf7LY;JR0N!O
zJn^Qfy)>%U;)U*zXJAFdnH|`DiDm~LB%j#Ao;#BNbAC@-XZu$j2%`UfT#XHOZ{?VA
z*;c?y+@*1W%1`hfJ<m*`Z<KoctG+1au$8sT(ZG-Lifz4nPFv$o6P1et@XTt^c`vO{
zVTe+!HZBFn-^<G%<vVxlhhRg)x<oT9#>ljNA*Hg{J36WGw)zDd<Efjb6FQ!={0*$&
zo%L29)lb{ao*uVw;{2#MF5>O-*sxZ?xakM8Iyt)U>We44f95ZAO13%Osj173o@bk4
zz3J_H`SLp3^XJPNHO8g5<jr}CO|6F0slLL=zsOm}q20&6wLWX_VA<3PWk>pP4QZi~
z)Y*h;?nqE1m#;AYak~7_rGt&(q7gm0YTF$-(oM?m<Ci*j{rC5V|HP&yO;aeRz!Pz2
z!4gxHw!<lf=RN^6AI<SqG5tS2*v;L2Fsgp`#+k(ht)Zf0(@3<>fgcZ_iOT&yIdy05
z$cVd{ksBrvG^;Yiy?-w4lkl_gyEwhhwH;HU^E&=v-T`SIiL;Yeq<<}0vgGL2H=D|X
zmN!1ibFaOrux94SpJ<0;nyW{b=RITYrulf=frwsPsW;JfI*t(5v-!-kJyijPac4yg
z)}+<4IsJ}G&I+OR(XiF`EO%9udHt9#x)ysh{?@uqc_jz5HcjQ7md>S<0~XW0ZD;iH
zGMjnd_6Bc0y^faVafEO0<%DAw-UJLa>c9W<kA=Wd`Y(36lw-q`aq5Y_dYxBZ%%?{f
z&bs3Y4-~H9Wge>D=ZO-xJu?IjvBe<zcbaIw`D=sGR(L(>J2IR`H>+plV=m!_E_{7?
zr-;VrZtYO~7}GFWxmPAJIOt5}^OvIOv&FwGs~Qq$3GqA{{+B_Zy07%>gY9(Bm(?NK
zUKT308pe9+hJ~uzLWg3nM(FDe=9AAc4(G>=`aXZU_cWTmoou^D6MR2Fe2bUVkhj(K
z^`Js<7rD~F(N2TZE(SS#F$XmJ9$2&L#Tmhnu^>L@U`Tz*=hD1fi#?z}lfuK6Qh+k0
zN^4L44WU`n>(79p1>hA5GplAWX_@R&{cynH|8BS4WGLfgeVrbKh<MN&msC?T2cmN@
zzQ(djdOHQ2WE5ahB1wlCa)K|3vn5S<M63(A`EWvl$qyQoVe3H5+UYVp<$u9SP%Quy
zg(!0i8YE~HBRlvY5+Y!cvlad#`w;P~ZljJJ)#gc_bHf}{*s~-tRVW9E7G<E2+fe`!
zW5O{3=vx=us1P*>9Am+K9^ip`5Q#r13yfGqVwzJTbbt*N2n<l{Yp?ys3(-k-W<Vcz
zl364hiVA$qAl+#zL9sI;Lbm1#fWg`0ExLgA2U1I-tP|8*DbKdIC=CLv!Vi$(94;R4
zE5%(&;C5?OC<nFPIk!F6lZb}*W7GtncM?R6@xd0JEGZ;0(;n(3IjWI>|5tF50S0|2
zkUvDuEGHv4-xOm~dU6OMy0_Sf?3R#)h-fyFP$gdk)z>^kC!{e11GSR%C2gwhx$;?X
z42$5H;Gv-bsizI5%gGvLK=HN&Y>+^IwFCYv0k`&2dVUN>+Dyf|yC*BS9_xxywAI0_
z&GOL1!2t~BcU1j4v-C74sm=Wk);i489x&{j1`dq#;*u^YG0ww)3DPKE&zfT~S!mHA
z24~FV4oEvnbGYbCTX9S-d}XQjHuilX2oIeB6%$V{OA&_q=!P(^qcF9Fgr<7f{`@DS
z*+0z%@{fC=1G7=jaWJif9Vq{(GXj4&eTt2i@4O=7DMA1FK@}IO^9%snnlSY++kYyB
z!YKbokD)Qg)4DI|K>AW0L+9Tfb|K4Ttz@mAOmeM&fn5KagUN-C3JlWQ%qiE25jyE1
zG&(pkMc@}yc$%X+&6(hs;u|2NR0e!w^J+wC_Hc4jy@W?GBM=IkaBL4S`_(j>a4LtK
zJ3WAnBBdAZfKN$w!%pxtR!S^Hu!Cw_z;VT8>u<yK3ev)W*lhS)kj#>b^~#Q6OEGbc
zW?s!>?=#svL`khmjKQb1f5V9(O$lV_dA)Z4luKH}Qot8dA%Z0Z-Ccry#t>#Xcwr5b
z$E;1b-^g~Z2%Z66y?P-6K;E=+%m}RW9cfP)vc5KOylrQh0gRC-9fQd;!Spj=`J_TQ
zMmUZ;Clmw3&|sF{5MI^_kjl9U-nqYuS3Vha?#^rxS8lU>%0Q&KO>rKH>upvl5r!?~
zai*<$v9L_8WLc>|cM)GafF@8OQLG6iN_oR$PT^#+BC!m*7vpdy0JM=a3@{Dn=RzRJ
z9iQs~XWbdTE!GVB6i~{%%}(xu#e=0>BpXU86U_NEIuTXC)t4E<p9%<<T)Tjm^N3NK
ztTj;{WSPSC=Z9q$62-w^nbQjqQ`kSwA(Yw|huRQjoG+p=lBPxQ5Xm}xQXv6KsWcUI
zPLioVp}+%@%iZ;wllaIHV9ki}Bq&a>rO8npoj+iJ&{OzDkl_8$&2<fY3#Or&g9o8y
zDcvxr)iPnmdfrPumlV=e+n4o=qmjZx$x%hlbeUg;qEUEqFa-o?qKb<Ed167zaBwIN
zE7WvA)SZX~nOQGqN>8plPAQz)qU*A7nG=1jFVpI@0U^=7cKeMIH?&`8&I4~>R-gZd
ze5TL6?1LB1HhGHnt;#F4iMX~zY%`_jQPh^<HaCa9sd*`a(GVlOEJ=#SYS8__n!5T)
zr<>$@cg0f5gTF{>;4MbWl2sm7Dx@Skd&8Pw{1j!TbH~7>@+3z>?$^z4p;syoY<sET
zCG^Ql`6+hus>?ut>aLTmoUc#XswJ1-`5qYC>AoT(g|}N*BR_Pj@>G#y4n?Jc(&CNI
zO!oP%rLQn?L;v*daiY8ekff)0$ia@e$2r%EH2Ei$<i=UUH<!;196ElYg0}J8>iUQW
zPIn(jnx9kV+2~<gbKm})=z2Jc4}6!9-SF<(X|M1nil2nX_3rw|k6gau%-ir6Suxn3
z>%*!YVjB5p_C=|``))rSQ)v{`@i?^id7ORm$r+p631=6flR|w!H1kUozIG_Z6|X>X
z2+VXaBdIqssa?skv42R*lbw#ko^StZjJQ-z(qfzClrrYAZvc=4zQmL~;o-ESo2oU_
zBq%K=od^5rVk1UG1)e5PQ`nV~3$e&EUmD5+@8esJCavn$US|LD3w5_?ldqjJc0|~j
zg>BDs@+>LW;%`#xTP;^u<=T4WuwZ<hru)+2BW)4o2}jmy<}uP&GV;sznMq{Zw%okd
zT`5(s5~;W&=FJZvA26#aZdz+^e>2{Zc+so+?i1q@?PgKNE-Lc_oxYP%+N`KE=35?J
zpr0;%+Iv}*;9Y3h^2ljLt4(w%KYwqpl%o=z<mvUhyD3kEBq{l8Wgph0$dA`WDyGDi
zI|i>+w2Ntt4!TvIXS4mo4ae|hcvAeBZ>3JQ+*z;h!PWS0a@UUa9ohHt@XOL6*5}N<
z=gJe?2P85Y#^_%Mf7DJaS%1dng>s2@yEfgm{ow|+#;U>Ef=w6Hm-u}fmwcVM;*3{g
zzd!4ysuW4uGP{4}o=*dDJg0o=zMJp&&766zaCbz?7WLgxkZB#OmKyH#@%AMCwx8q5
z)bkm0jw1gki=E|rU3`Cj+GBKS!~BNp9Tr~2`*6pM4#ylyF!bHC`-0p1_ao-n>lCzZ
z<X^w(V{*{*+~^>x=78^|Xpw=8?knBlH@Tdn7qr&SV}dc>tNw3g9-y=SPySk57T1Em
z!z`2)?=LA*4*IVHJ?-V=JcC+e#oeDjDEto9yKuv|^v}@G>rak<RV0r5n!iI%-JNP-
z*LYsCW&H*mK+bk_J}b{Zsor&7c95rdHnQ|=^Evx|PwZjQ9o#H<-}s(>AC9bs8;-Z@
zjh=#j)G+z2ek5KnQY@KdIasUPc}!uh&g#DL(etlDDs~SrYp*|{ZXYOfbC?^k=qn@c
zeYJ+^UcUPYPki+RR|#~X992FdiPfX<pj0hMFX3__PxFkC>jrn;I>gS_AT7vix#xXM
z!^2~*BU_F{ohS6&jrc$p9%TmIblpEs<7+8zB;718bWY2`PYr?%eu>;(2yZ-e-|cg!
zFTdX0>+yQ=XFHskC-b%ZO}MK4<t70h;?j+V^nEGSX6Zn2_(v)W$Cb*7M7ABXfQ6D2
zQ#cC%ES6_0t`*l-kC@1@^o%CiH9$F)5d1P;<G`sYx_S!hdtOXWNm*!TZS41n_lf8E
zu<Pi}<P&R>yD_`<j~F)UrD^yp^^5#23|&}m_cl;>p5r&)eYR4cIh2k9{nPy2RIK^2
zsm!IH!p*w~pU)p~xoJ42m4D=H?7hQsKUW>|a@htE+hhA?=s$%~sXv?U`@TNWW4BRY
zxT%{}bf^t~><dXeDh`S5aHi1D$FHejqd{2xq<8hMBa7&8QRzcm*zo5byC)SXuH%==
zi%z>62A`umKlOc1baj@LLYJZyUF~n#IwMiH|L)6}SBYlA(IMs`g(GIokFJ(IaZ~zf
zM!z3i;!pmj*7Y;w*W|vB3EpC3YvUC19E{gKxNpOn*reOH?z!{Vk?^w0>CCwel^t_7
zg(K%5^avH_w|StgZFl-)6SY=su6DXF-K3f_Mtl*%DaXkD%YXZCfDixKuWdSguEcrg
zdtYi%yp_D?_85;w9@+2;hy%u%M|CyNgtEby_~Ltos=T~jk9uAH=jZPuN(R(TkAME5
zxiieca;8wg{B-y=6P;T-C)~1p>iE{-jC!K+I-4-->a%~5TkAvZn&CtL`!3o4<cH2U
z%PjjqIxWRNwl6W2?`Kar5gZ;E7xw-W+EnC!&cpo}_UX5*u<Zt3w`chew;ZfUyApZT
z{LQ_OGXaGa&cP_%xeaL<&Rb)B1doh<9KIUO0aE{VnH5_P+&$e^v0-RKr%d$Pp9XK6
zxU?Gc<9k#icV4kq->TQoHJJa_v5-C7VGtNDxjwhF(6Z_Vt?PN##{<npOo!rE)6GR{
z(iP;efBrAV-ZQGnunX5r=pscWC?Hi32r3c@NGFK2(7VzUP$3{S)Sy&FjSzYZEtrH}
zM7n~aNYzk6Q<?|}1_Y!FqTf7zv*xThXPqfO{G$s4;Z5>Bd*AnUHOlM1qpVnT^o@*G
znn;P1!3{;ecUnpu41FQ01%Z0blFka?qge%YBiq!lKpGB=it;?N&)P2w?2(1BW(>WP
z0@+|@yiLLyvWoLf(cK5FLG$LvDZwNM1idi9x)HqI1z|pmRHnpM;`wtaK8p!AiCKOy
zA5!R<PI)=hvozQ>`_oOZTrZOdYs0r-KHn*DCNmC*tFp<0)Gpuw0g&F)jRf%W7Un}8
z8L@y*GkAdzQ85++v?gDTQ9ueL2|I3-jCrg!WT1l%hs9qeI=K->09Q{F&W4HDCMWEG
zdzu&>fKti>2La*V^x$nkkxU_iE^>jV*h4V6k0rcI4<&_=*kTMC)Tz=4pi~j&l<fvp
zZ8f*Fwu?wNK!G$cO9wZOTsP1>Q9^2Y01?fhxT3E%G+assC5~swN&T^&z@P!g@S<5E
z7adG2xJ5v=4PiV8?nNoZP-CM6I_P3k&q@c-(*fI<!Er!O^0KC99~lJuoVe~b>HDQ9
zc~41X!FD9rY2d8~sBCeo|G-m4pxt8ueM`cdfQGpRbX8w=9kp%<+4yCdN94iM6F?UU
zT3E#{;t5Pt*+)U)WPzSw_3z{oP9lU+G$O42)<Z%_xGjAwKz~BEDce*TST+r4ps3Q^
z7e@x6Z>fMP{*P+Vya=pp1#qY;iT$P(bblz1Xf_SbHL6s0*qyY}xo8oBR(f0w*5Ixs
zxKGuYwcr8Q1+<fyDvyyp#tBrL#tFj^a+SmiP*^4(#mkCS!62caV=oF=kes||MV)0?
z0e3(f2z?gK1i<P#43w}n)bk8sgp&nCxPbHtaMDHC!J#J(z_^kCz5xKcjVNM$cuSOm
zWPxmV6`)3i1EK5wpg|L|5F8W59M}W^cG&=lJFsA)3-LNQEyl24@mvQWF7S)MjseW)
z1mFsbcy_bzgUBNE2_7sgJ-^F>V`u<9ON0?&A)&ra1qxtt8$@=g0q_;_;q21UBJGTs
zXiY^Fc`TXT%aV4MDOwmDD?uxLzJWQ-1Yp6AyrnJysu%EP?9OX}NY=Y(zJv&?d66>I
zPLaNzIFFiDL4dyO4G>^eIj|yxQ6V>@<dg@QB9SDB3XD852<lL$USk3Zy-eIi%07de
z<V$d-IHEtyr#sRU+Dz@@Ru>%+g4_hJlVHJ;dA!NZL1qLIVJ6uIu6hcW70}7P_aK_&
zf%7yHOcn%6+zTD9@Z5(-zukMCE)=kI2-o_)7=3yGtvgnTHwg?tadparlOWcpXVs8d
z@L3vIx-b_+(1pQ+V^<B(5OW9fsBgyIIFKJ?LGrX9NdZPg$dRrvptx%)X^;oadZ5MN
zEu}~@fqfP)5S(g$-vLAkPno1Di6?P7+hmnJvc@1Z$pNM1bqQ;>Iu?^SAbe{mVTcIc
zEYge(*Z^JvipC9MI2NN%iRFW*dE0_1l==r;$3U=A81;@&!T{Ppu=Ei?hL9`(UxFUf
zDYAuHDnrK0Al>nyXqEMu=+lE1pqr<!hz8_q_9X*4LEUNzJRik)mA9n7>5!W#EB`bz
zi+C1@g@1&FnE_SC8g(=p^wa2^sEatX?t$gYXxQ<IEN%21!-GLn1rZ{YrU=^fgpqg+
zB6KmE7xV!42TzK;`bkk`1NK$a(S+ZCe(CX?#^PRe2803w3{{ao01)JcuFiK1R29Ts
zS%D7n7AF`^Sb>7sqp_GmYf$$xLktcJq&F|YTK-_5Y%!wo8w&0-sR})vfMR?_?#GiP
z+{3KrH94BtQ1cO%@)NpS?r|%2Yn4T>A9N#nTnXngtUe?J^VgJkJ-lVOrf>6;+v)aD
zPM=7EreDX&v5<nh&bXi6Ns<@d&b6gR7+!S!EF)(hdoFM6o}ve9PO8*`M~PRN?sI*+
zsRiUW*4Mjwe)5IFDe)4ap`GpyU3hd^Pd~zLex#t!IZfL2&N4fiCS+{m*;sfg6SZ<Z
z>tvTQ!*Q@DO@3QL$Y}Nbhri=qcQAFSL}}{*$X<z7V!&<yyaUM9SDjg8Q$Boi(pOga
zmgF^E_dMP+War^{>2|qgi)n#NpUobu;7-_1^|<rTIo(q^KBD(4QZoCm0qbMQlpD3{
zZJ?4*b@9u5>Eq|!Z{<pfh4O>s%}#ZkVPLkT)~Ct^3}4gmj*@fcc&DBI*IPflNp+)A
z!(D^a<S4nV$ug4-pJa%Eu7ktnCk_LDM8AjEMuqK^^uJ8{{KdU|EV#7#hcis%TNo`M
zse{kie6qgnic|_`O|9^lJQ=9MO?;9g?3IEFO4r|A77He8t1`@1P0yqUI6WfCYAj}{
zB4cA>)vN@_D*cMa!=;O9c{^myI#lO?h@OB7Xqg_F9gJ4rKE!Yq)VC~6q<awEj(KPj
z;A*?1q%k~r`~F)$1@Q1~%%VJI2vdRGgP}=DywffPIx=Vj#x?oT+MH|(rMDLX?CxHq
z4u4U2b>4Yigj**ePG{CSA<uc}QY^7f?NxYDt0nRhRCaaB?r&D<;fzV;Iob*Rc#Dm1
z*X(tRy?&zmUZ@a!vo%*<7f6^JiJD1re60-86h79+QCcGC@UC%;E085E;m;S`$Zs!W
zF;~YtyXQM7J=PH7h0o6BswF)ED88aTe5P2NMfaYUXR}wb*qOx&V?W`-a6N~#F)|XG
zw=2N@!F^lF_E|p9=QCWd8*1@rH`V<MH&Y1uV{3A+7`KGqV|S_(XA}Q!GFvp@{{vy>
zFK@049RB=LSOb_8ivlQ<{YHrL+BMb?bIheBmD@YzFC4n2)Z8kvok}G5Gj^W*2cp~R
z&ugm@XGh*RS>Y8j;7OPLE9J*<48(N!t$mRh96jQ`dBb~N$zHmvI&J><so>bXkB?L)
z`YG-!&i6vcQoCN9eSiCO5x2|j3k~(;r6&%l>MF5wn!SX+0E;1`f^q?czUPt?`7Rhg
z`7%EMSFb}x^DyUa*;gGpmO3<El=!Z?T~=!lK|ELRV&iuHjE<Z@u+!!_D-kog>t+vh
z8ysy`VV#-EzpG0&O6bp>WGP^PxsG}VjFte}qksSV|9inI=X?d%?WwPNS~=(4uJv8k
zWuW*^+chyqzyBjAJ@!m+l26#mn9^uOK;2KY%AD|wJoHHdGWN#cLPNuYVY51k-_Mh}
zN(C)~Z<fpyD5tz-v3~y4w8AWMS@r<$v77%{P@R3yhBcfFyLLqA?~ekhPUN(+!lJc_
zB-ncofNZ`|Ze`*xA=jB{=QnCmB{&3%>r+G;>S@iJvJ!$Pv&eU7fyD}5d9IM4LKYrm
zR*uu32q@k%VUZ-7lJEgY;8qu~hdto3E)y6$qs*{;elYT2Yf_1CW6GN8l!jfa@MnBi
z2y<CggdMjV9IDj(=hIGwB#W)Lb;fQ5D!}k2T(KXHqRGobIt893fVe*R*yYt28li)J
zv{1kwI5)F^d4vAcFbx5OrAITn;nya5nQRsteFzrzBJ;UT^$`}WCkK#&Ij+tDd-1rD
z0x#yh3fjecdRUBh=J79*s%+&^@2*E3as;f6I#IR?p36MdzGwY<SZpt*=JIgxWCi7H
z7suR7P35nPEQs%NZ8`E(LWb`gtaw*k&CbANsQzHIT-vv#YIi|!9yVMmV{+#OVC0Q_
z`gpzMhu-Rks>lc^>doDt%2{rWiz4vfQWt$c6#8I?@tC%NWK(<F4xakdgeKUZR9>Gm
z*l-DLT=JB56{<XdrtOD}P)S?8rGf5OOtZ|%)igB{3el!Yn1u2>rLbFFjdV{Ni(bPO
zU>3D;7I^lVlD;QP$&DRB9hwJYp-)#^+YrT1B5!(|9b^89H66K7JnG{zBC%knguGl5
zk|ZsZ`XV#P%ksQ+AVIb2g7G`Gcw!|XQCxL@;~G=fGUQ$l5%G!GGt#JAx>ShsOvY2W
zKlXeq>fqYmEn{7{J9*2hb(eB!AeZQ$rn!8qwkIlNUb2>QD|o3|6MpSB=}#REelN7#
zbz_Hm9XP$@ou<3RGE|felx&O&`ziKsw<)aAQ4SW7#bo>G!Qna-Z$IYqs%5<B$n0li
zd$O`R9scQS+JZl}IhZowr3h|4{=4U&@J?)E^W0?XRp<PH{PI}n{$#lQP;Mxr<)v6x
zYq!c`esXu4xF(&xJHybOa3aS|Dh1zh?I=3H|1@^|@bvN*AB~jDwbg~@8-L3@YURm<
zMa8$0@x|<w=ke15))lG4tr)V`)pNZI#>3p5K`Ce{)X%;baMEp}oP;uu2zn$YE=ZO1
z&x83t?4<uYB=e)vn#;eQM_-?K9p1~-CceYJ^oHL$B**(Nh++J<!}i|yRJ1xip4R&6
z`{@v^U?sQjfnOZT#6AQ*nu=00iCa0X`0^d|-}VY6V|0|FQN8QT*}t~_L9oPRP~iOk
z*lYdIJ8$^%v9tZT8kgk1h4m$SFH8rDowLg4ov}_DNn+e^R{3bAnRu^iULZkK{I%uq
z!0kT{ZCppEg_|Fidz_yq`hQoUB)byeI_)(MIX&++l5n=OgHaCb4xdu%=l9~DY05>!
z#IINcSL1St-EQv<m@1jL?H+6}?6f(X@7})9NddQMtk;?F+MKc^R^}B$paSdyKzxz!
z-AGWMf$WlD&ArrrZygB32%!)JI0&-CNLDcg|BTW{@Q^M{I~JUK#GR}&bf`zuCi2+5
z+>S|*J$K6h1_^kLSQKv~sm7BGofXuv`H2LZ2iAsj$zASvlaLaN2x}+>Xn-g34Z|0s
zg>XXz3|2<~$z@hB^59Nh01-oC1~YAnj3iYSK;i!)d2x!s=LGg4+k2E%bT|Mxy-NrL
z@c~}I9Xl)q@5_jPC7n(YPZAK>QTC{Sj0TSe%q}cAg7MTtcmSuC2k@Nq#9;^45!)a>
z34SQZ9>|E{0Naehj<-OdRFI&w;XXqs214H$K??OdZcq(CYy)Tlq@7)|3JHZ#-@v<k
zCIcwy4i$C>U}=Hl01$TT+jWWT#j+F%)6aj)o42F_a0CPja4d=jfq0aWI4$YPn;@?Q
z;JWM}MFwJc0B+0sPk$||ogvr@l3#%T#6(yG%aW66Rcr}^;_Wa#8Vn1#C0P88Dv8G+
z7l#X>NCKp<rlO%%dTYUyHDnn)aPz;2+XJE^jn$LHTD+BJ4E8a6$P&B?i12}%Vr%du
zaT*|x>&f6C5K{1B0+3sLhX(9h8e&jqOCi9289)IIw*>bp_*^<(r<cSGpd2o-coy;5
z-$NsoUtm1x?SQ^IOAn@YigUR|dxA|Br1R{>Gf7nD6Pb7*6ta+|$$LU%fS7>X2ID~J
zs~ilWK}ZcEWbVa_R^RA^uy6)Y)(u$|c&04Tk?G((y+H@zL@%@aQi!B<mH@IoA8fTQ
zh?L0+gphwy#WDl|eRqlgOut}96zC}<1E^S@XJWvP59qKDh5+5lf?YHnI=OEFcC3J>
z!7&fZ_Y_`Ch5)-31DtbFvYjHb>n4yOD(LtJpuyTlhAkbar!Dj#OaR)-rUv9<(7fR?
zwR>%421u|jDFRCiU=ig|ql2Gmo7%++5n$kL|Hv|H2szvo0K&y)Qlw4uTrvk+6sMB~
za54hAp7`WLun~ndBO$yvrwB{DKM1Q$>MPQ-CL3e{QkwfMthwYkN^~R|1Dsl#n1u)n
zHdcs17a-b}aSj_I-zy3h@04*+Iw6W80jAyT_~e9LvLCWNNjQko%`dG&ImZ}F?mCXg
zsL(X<7y*U}%fN>}aBXw|rArnHNGR+MQND0Q8cqCkg79{63e6Cpv){rX?W)u+(5C}S
zpyu}e08<sJ2Hjn?n2ARXYsgL`hRmp0;!)DzgWtVMU~eu<fW$^bDHfO-;W19Tz*opX
z2f|VNZKd;{1`#Dy5bIi+z>-#aG<YDI#<1a18dzG3lzFb2T;T^aW-?LHkZmrVQ<f>_
z5&FntoY6i&R_g(4b;2wiEUXLEEFuO?A#})kClFI4;S}TOF%QMHse%IzyzC<ukW(64
zzXkyxB}m)~2jaT(qHi4hHSXk&19>bIs7ELRKsmsURvwfvl>vtNUBCgksb~sRP3()F
z-GEEY(o2I_KVAph%42~5OSxd>k1<*T*Q_wk3TjMG_-g|uNS;*j`8ELC0PQt#%LFV<
zZ~>%QJEg(l5pOp0x1LMk5(cnn#$g5Zh<G*}kaH3^K)n@$`vb@7h;9o(6qBQ<klCSO
zw$x-OprQC{)$_#^(qsBnikSea@BV}u*0|6Y!_!@EB*t&M$)@el_@aU*&&EpJwe#NR
zm1J;<J?hgT$@3`FAO16XLp}`$UzFnbwx7JM+3AygrsV;fp!K>_p7#$0Z+o*>$_tbS
z`?u!*Of>iOTOj9uj-`LyEwu{Y537!H8m#)teIk!dfW;o`ek%J?;iUuoyA7qv@>dzB
zF`5CyKqLHxg5cfLEB5cL){^M?yB~i07Y)7u^&8HO#?$!ZXU2I+@9N~bgozc1Nu<XL
zeuy5NQ?+0b{$N+T!z%Y$L>F%h>9csk{!I`1(@!C4vel`p8t*51B80j&c!=^opE`Jd
z9=^9V#(aAoI8-)yXymNaT03=B@U&J-ReJT~)W(wZ58fBv9DM4VPr!}6PWYtGuDa?>
zAb+hNz41{uZr>L1)qp;XYh1&Qy~x+<N=eBt>uo$c%Z%@>YdNC)InaKb-Vhv+?&SV(
zvE_w7qOhx0*@Q8y&QhyoKT+%$JCCUbWvwd5Jr8jZuB(!5fQpMi*UqU9w+y4(>Qi2*
z4H3(@`{%c8pJNByol+B%^iRAz8MCauO9C~|)K0tJ#aKndQ~$Q)5Up1F(sxV=@Q?BA
zlK`;vk;V?g`0$$WTs9B4iZJmeiwEqOq8@XNXd4Fdb{zI2|8>3SYd{cw$OMb5C&gmg
z%pEM(4cVFTmOZq~NG3H4L`RI#uUY!i7G<CTBF(EoSGX{dpErLdZr_6KA)(%9)b*9=
zP}I?+HsW{Jws&!Sw|UWXeG9?!^pd(aEzkXru_yerP4ZeMKW<D_2@ue`h?5ERj{JVO
zx9$KBIoqu&+R#~CwV1e(fJ;J;)Q!Z5^Zl~-UH-oL?bN9|AquJ1N^Te5*i_#57~@c5
zuvgB4KHM#(p}izcbQKLTfMd_XFa{rWkmllayJgZJ%&%wBs!@DzFXZREs!JIfUx$EQ
zho*O;cg2TpzHn00o*vGZdRM;k_LG<VH3D}cjxuI-2gg#*677i%)2XX>xi<1Vh%1M3
zPs$m+iachQw4Sw29DG}olz8FD&k$ux6B2U&CJw#Y$P%35AZ6SxJbdd#y#AjB*O3I_
zak0`v!$(&~X8PAYKQCD){N1T?onK|Qn04x^nmXBe$C8aqx?d2u%gCPGVygT5ad$O)
zA;pkE3&|YM4Bc3q3Cb`ps=nCSM59hg*r;D`X=m7;lzxg>9&e=eT#{E8dgC`2Z`+ZT
z_-3N|$_3mh;phK>ye@AaJ-=YPA0snU8CMR}<8#K>Q#_uyobbOTQV}A?cfD62gay9t
z<m8||VS|1gqJ+_VmQ<J0l0M&N>{%cD)2q>5JUu6Dc4_QsqQkq<%SLLEY|S@*ysEGb
zeNbzzv*OfMIewzxG81pq81;3Brlp20xn)8=Efn0vk8Pf7?&!`F+FvyMHW4mP*ctw1
z+|}f8-O>2jt;De2O0u;hqF_MJuC~>9<!Zqtp07Rpw}kN{I{#Cdhh4Kw!4v8UOo{(f
zKvJC8KQZfe&GHQ=t@-C_Ye^8FF?6+|xrzvX{7oL|e1|#r`fNH*OQ&4Xd3jgn&qdRe
z@!uO<<5)wKBzp>~(%&+y;C-!8)BE|lYPlb3Rp~36W(7I?L(>?C`?H;$l#6Q?cHB$R
z$fubXk7u%JDqm)b7R@^LV(mKY54U!IQuWtsKYvO8HgCJ`_8N2Z@7X)5Wosk_VXo2A
zsmvdq;Tr(%k+zB;>?8;jEFrs-^(n7z@><*f=-G{b+X`aDm^Ph3&d!L*z)yVAkqyFG
zyMwZq3|oH>{TRg7VOJ~0vd3qhI{g}5%|0aX(yKev`iiphMkA2s^><=k`=MRiqNvus
z_1{=_OMVQ=SDbJ7P_QFdU?P@Hch|76Pp}QV>N1poncCB^zE&rkiV4{oCnC&K_*SJ1
znp9Wpi`q7;TA#O$`XW}X44RY_V{83${j5Dqd*TX?Eb)_g^empMKE*d5;r|$P!qSip
z;|WD|3ha`RJOJ_qG>=%oXEG+Dz{d%!S;|hnsPd>Y`l!u*QyyX)2`zs|b~W!eaI!wK
z7=6JZPj;~xL<U3Fk#@e#?^-UTtvcT?W3EBZy_TFVdJ&71dY)G3+lDEIi-wn8*LYFE
zZka;B&6UY#No!%!g_KgnQ-sx_O$}~!hLPI|Q9_>u>gwp{S&YQD;zXv#EsM`cHroyC
zR3Ghluu$d}>4qEkrXUnW-(zi_+?`+rOZ-dFJe!*yE5=PRj*@KfTl})>WJagGE51(b
zpd6AEHh|`O^nwoR+S??y$`Tc7N{=R^jdABYI4*_9C-;T-mNp&3S=}PKo!60Y3ojPV
z(ipz^d)n)Y*4;q~dn6@@6jUNcg{VQFJZkfuke9NnREd}7e}l=ZK`&JX4Ssrs4Cs67
z%>Sr}Key}`?%n>CdQPp_27zx6&$qF<Vo6_vZ#-(`_F2>s9TQFna7x_k`0(&C&0EDy
z`@wj<`A7AzGj-pFpDElvV!f)@>Av(KU;d!qd}gvo!Tcln4C&ORtG}jGrtF8<(G8g+
z<f{~SdW$!B7Y{i#WWo?IGMCe{NRs~TWb#F2a@~C5AGb?rs`aO6g>XWxlrKmjC_1e!
z7Gm8c2-otR%~6V|6UpDr?!z^{w2#`pBuZpD5t@}QO;0xOKQGRRU0}$|*=CFGa6A;b
z-1W8XAy?|va5K%)TBFRX(Mb-;3N&kbnV7;ps@1npmOw?q$&BdwsxJ83a#^~ahOW$?
zEo%;WUM=H!2KsFPZuk)zH{n#k!o8y;_sN;3%;4P7WKMsrom-f3!Eca(HVsT&%4on2
zIpbm9113$Z{SPJYKZrUE_RPh-BR!>E`QjQctzW;h!OBGj?Mt0fzo0lLRo=@(^?NmD
z!*KS^ug2hrY>h9SXL4#JPJT!|spqEJu2gXFz`_Z3=>uQQ>GZj@r@AfM0(Y1-6n0?e
zOQ(O{=MERmndi28Ykzm<-i_(Bnk8qKocUF)z2jf5`cO3o%=;-G-g?%JFJl>@j!xv7
zVyxZejNkL3+wG}%6zId(^Zf5hs{d^i7O$S1%G*#7w#P->_kR4VfbuI?P(P%vxLWLZ
z{*4DebJJ32Rx*oMH1(Wcex3X@dP+r=xrix+edMoLlp?Cm?^@QrU5V?pNS>R2PYjzG
z{du?b%WjroIHrCSczga&4AcLQHSoXnu(`v2?wpON!PA;e6%14?rKULQ@%TX0$<_Cf
z@MhOTOE#JPC`spRnf1EDWAz5veX6?@fK6oRED}r3v=Jln?!wjayl7r2yZ6VZ+|N`5
zSA>dTsWxCJa~Vl^|8vVu-_+*8>|7OmekPA2yEp;dP1G28owHV$%S_t`Ei;G!XiFKi
zK`yEQrEm@?#dO2Sgpqs<2$iYRK^3f}y;A|kX=$`>fJUj~Eqei$uYI`r5wuf#yO<e$
znhH^GV8I%_O!ynb;j$f1bYzB2e@1czASaH{6o`-z&jA=cjMN00d+R!sc`*mYeG7#i
znslUtqEWIe)Ko^-C~q!(3w4Bu(Enixth8@C<uU3*AQrf81R7rIAkev@4;a7CVst1_
zJ%MN7#2DInLB<6n96iC|4%Uu#U=`f^7n6HOc!mc=x4Gnib=n09B!rp9gjXDkh7qqQ
z8XEz61*IFwvu&ZUJd)i@RsH7!#B;10r5U%cq8<vcB`46qe<B39;4b;4f7L*pNP`HH
ze*#nz3mNqEw6=xQP!JkZG@z-gSwNG31t=ebvxfA5DCbN<Wc@KV@D-g*NqtErz+SRq
zV2xM5101vlI5mPSNVdko=75zpTD24W-XLulwSPdx8(q;SfbM;eiI7eCE;}Gh52i5f
z99T}^wW$iQ2+&~6p}_%r)?^6@%6cH7`o|N1|7H#W9395o3FCxV_bet`;k6&(0c{;^
zfYzZw1fJn}LM@nv@ah)eU?@PQij*QDd5aIp;zI-Uf0KtDV2AgDnB~I_(CQ$H+6H2|
zG3;jBQEDK$oYa@#k!Jze=6}N|XEH(SkIG)dM2ID%x65{3^fIvkmAkSqN;eoom=6=#
zK$avq`aWC**;ZB@%_Zb?)5>E5jAEks@CY5)aUhNXOmeX6wFEJ~M|iZ0?7&zIbccex
zlLfklZtg@5>M9`K8Mqtx;S@|kN0J@Mi9khffkhu2=N1i7z#!uEE`klS51B*?Fu+}b
z!1V-aGH8gC6|gT2$C)sfz=GEGJ;9GWmp(*KD+9trl@i1N+GK~E3N8Tx#=r#wr2>}A
z=QUZF1ssf1P`!)EQF+7h3JRW(5-uxdaGY){(~+_YW~QoZ%K{Cwmjz;nbbsB;iI1NA
z(2^z#8Dtk7aR(o%(2|%K6#I(tC(!aFjF8;&*v!2`6b;?MCfT~324|m$79_xx=U1#^
zCMVKF)1&Y7Ph+SED}XprzBPOt>NFQiaaX#WX>JDBXw=k$T$x7TO+17HtoH9laB4i$
zRNXEKNO?%28rKQXRLbYaqR+tq930u5)K_(^O+BPoS-@YGsn&uAVJfMFuu?RIK(~uo
zt{zjf@{wtjb16)e@G@cZnQxGFQM(gsepB(kaC?->AtrkrZ7OYE;s8-zj8z+S1ljMY
zP!e-dH_i_SUV&l2C56}S_mqx9u>oLe7==3x;CLV?8t~GoAhQ{(s7{RpIxkrM0{b3>
zvSq3furia0hnTg_rB%U&H!(*#A+X|PF|<|K4h2e2-ligBqj{o3fm@kj=*E{|d0+_`
zEkp>L&Wetpm;?JhNN@8xa6ALom4G0*N*J*3!<X=o8zqtHL;C?{B5)3nYXvm=nKam&
zw}vd;4FWWI1<zTx>?8UJJz;ksGk}R60WX>>0W_vl(s48iF{hy(VGE`xImoj#DZ0Q9
zuu(9Z*$!O+fd}?)dSXS}z(g7I=?HRo>JCAD5C{-6L`OvH>z&+q()qq)crf7Q!h-vo
z-iG0w*N1bd|MC1ItASTfL$S(yGX^i&8xAP;f&haWfC)7Wgpfi`#mWwNnQVX+K@7@i
z=PU~^E>zc0;4;p#e!O3_R#0#mMg6Y0j@Cadf>8$7A(U&&F;?3lUEPD2^g*KB_C{90
zcKnU!WAc?}X9(!|wStUS;DE@vtX!;0ws`MO$mr!47aoEYUxx9yjV_3_oqrQj*YnAr
z+l%c)kl(waf{~{Fyg!~yDQOx)sh20W_exmXJGt=YW*9Ch&iTP%pK7VP+`zy#I>qp<
ztCi-9=L5Q{dR@K_Gf$F@{o?vLwkxtu2>J*&75jUqHDx*q?sX3qW(zG>uHUU$4Ou@b
zE*#hCRdQc2H?dL0$L&JG)KBl6;C)&sakbJoPk3RmMexE<UO{|q>d07LwFeVvvC2U|
zt%uz_3SFUg>BOnA;^C)N-NH6Pxi7AVTV`3O94@Q){``H(`_3n}rqj=LV5y%RO;6us
zy%)^S7n?$rTjQ!upxm-4f6vp9w?Xr?x%tAjRQkI6T=UXVQHmV=$F&QD=Hdk*lck>|
z=H7XHoX!_BjJ6yqV23Keop<Y2fXR`swJpt1^5YcU&rV&RJhO%88iQzN{HA4_%^Gnt
z^<S_(FXYFW%k6J#Xn2SSzO@#VMbm^M&Yim%E0hu=S;9Z9oaKF=&-LWxRi~~Js%ddg
z`$CCJVPA3aNsAGB<|QTMr2)ThXnn&yiYiw)NjRl5u))22kLUA>kq%q>f{-pJVgQ-5
zdk9wqWUyI(*#V|x;l&tw3_*}#T<GQZ^QQ`xnYoN|ib)SyB_B>jLIqL{bAvp7?v%N`
zChB){><9{5!Vt*W+P6E^ME-DR!d*R9r3f!v(xd9J2>uV>Ht0=mzo*7elli=bkXAq0
z!q%NlGq$k=j)4H@gbiY2!t3dB#WAXH245(}NRWaICT$o03q*nrE0PoKG{|&m&FXcl
zeQH>RN#^i%4CJ(w)I1fpsOXeMIB(L(rnij1mp&=DecmyPF!!qP5e?oDHWl~XJ5lTs
ze)S%kE}O_m-u#M#v8$wZ*UV|cvNblLS-@d4x9UPsPRu;Gr4<@|lf#_kn(E!xs&l9O
zhna#Jbf<E#r4n-}lWG@YpOG!o*SamJJ?GuDAu^);;|(T3Bce8KqWMd_`|S}to7Uag
z-{VH}XTF@-5%xf?uES>H)%Bj4OI*?wIv{qB|F}CJcRw%g+Y)mF5Q`z`WzHvA<`c$R
zDWb2wVxWUXGgCi=)5aR#1kHa7($;nAepszF{<SAbU-ptg^|_BbtH#blJB~>&rqQ*E
z-*ltomb|UjBC?Vpt8r6y(j{Mi$s41!T+}!>&xzp=Rx6%Ool%R6mu~a!n0Py0U*DYK
zpp6K<N&iGndo|=wdrnXn`rxDaEE}Pdp-KzRnz)-f-81MC@M^8$POo>FZZiyTyFwgJ
zxg_uMbGJ@8ebUbU)}3!+C10JZN}g0zcZlm>hpf|EJM>#pSDd`Bf8{`=5O%)*yw=TB
zJt7=R*%lHhUODG?esJcMT-I5Um-o-P2CK^mIzEsb5$f~y{IV`9IrE}syN;zGn8;jE
zVWgl|v#M^gp`eY%jQX%2*4L=N9{UfZZeepN&fDV+u6RZ^sb0?jYkTWlL7C5eztBQy
zi%wj^NWUOiT={fu4ZMED*CCiVW-eRMyzW@LOsp^Qm^`%ss~0?3HOCz|_SZ3t@<6WO
zbl%*HFE_@g08MpvrH83z>XTDn*L59vT#AhY{p#|A<14mB%C~cUbl)SAl>GJxuSCMC
z1P(pQCb?V~4Dr8*SN{W%E5QWT%4B{z^!k!39LJW(Z2f$==1u)w`s~$>c#+dpj^()P
z)~=!*DfaA2tpCUqYyXV_TiwD9UgOz@)LY+sFZLd;u^{$d_SgZ!GG~5=YGiw04gC^y
ztKeMjs4LXiE`Mnvas0#I5)sW6<{NKb##o(gJYSN!V;OR**Qxhav#~l>GWf?i!kbY_
z&g8v34^pu=ab>FCIugArQjt^eEr~O-I3L}1j4`zQA?vd2+4B!$G&^jM=3kjJyZnmh
zv!-0LPdDLjgSBNw>V=B8mEnm~C-@tlzA`%HUc0o|yW*@|xB(S!v<>@v69;v{v848e
zyAu|(ywB&G^LzOSzQh!?_{^`IOW7(j5FKrEuW@iG-7M}9`zqb4A^(kg0Nvmh9N;@=
zNR`v`EKmNqr@7RBlidaL^$GvtOR>a-2bF5^B1dm(;<%|FLlH;L`1geODAjxE8z`Zz
z;$*~^#23^21WUFC(CESUzEfNywRj&b1Tp7_vnDN<`C+FEDE1yysGF%e(5v->iwt1(
zRv>tGf_>gNVO(ZTP|5M~mUzm&Rsu&^dSx}cgPB~zcADPZb<Wu3bF|Z44tVA9fXxkj
z%c=M5u}mVDvDfb3Iivh-ROv%F*FbI6K#Aq`kiOs>$2$V0+7q_A9lF{!?td&3xBW8=
z9P%r6Qn)`0><d<!gS(X_&YID?b5~fo+5^VQ2O?M`jMcWjC@op6oSH~1PdlH(yaXBZ
z>7*V0xbktiqD$^?-DlPT)0UBS^3#vCO<Qpx442Tkkx_qnKNQEuR~hD2J`-WY#d9pE
zp0izAzFlR%@@KZt*KcJT{^D-Hc~tR~<7yR?M%*GEKeH7Ns(j)zBfbC7$7J^1qlw(?
zZ%^*^lUpjn-Z!4<(9pVKEW5`)fys07sdhIpzD999HM33&dKuxi)!aUyG^$^ob3*?h
z!9t(gK<dM3*KDgN$$?JxZXW8o*&b}gk0X~WkQ-6=?!z~xufS@uTPPDkCh0_1RsN$c
zlV#eiVll<{UkdvQYU>zWI(6<m&$CQlM9TGXhbM+xT;`GyHoO%x8rM&rILQucd!|?J
z+m+>#p1oL3o$ipG^nm-_E`yHTpg#R8U0DA(LiMDCU@|_vM#(|8!F2y5DN^a;ryYB#
zeH5?L$jir?=}+3V(wjT={^V3B-ro^>s2OBx`FdyU$TqC4ocH#bYt8AR87-Jz3m$J)
z4ec<*%l*1#NQI^6o>9^^10tG{VT2Wd&G!W*D10CWQGA5|1`jCb27ZbBYYn8I^rNw&
zYoP-bcKS_fM;5NeVb!A5@<y2}uL&ssDZ;K_Ph~Kv+}L~3Y&lq4BfN2zMyoD6Z)q-W
zl9UyNo=Ft*`f+tRumEgIO3v#!1P>H1C*CtJ*5^=!Oa3X}pPF%6%2|*UZ8+YN^LjgJ
zfBeRX#>ckW_0_r6v&N~jX$NEcYj2)?2%=w3pMGhdD43V3`+T5HA+OQgDO4$-UB1#~
zWLrf42KUs*e&<symNu;eTn}Zhb8J^DY$7I-xd<60BjhQ~q6z7uug#}}yxI^c=6)x>
z_q@7#`ah6arT4Ju4hYuFGGQL}w*(rYAHqGCh%i|D(Q%(uV&mZp-qhiroq?yZIxcF~
z2UJ9ak%;53!L)~Uhhe2jiSkEpI+lv=eB_tFD0pR_EOZ6`%>3)+pC`<2_=ktqWd(%T
zTE&0uzBd)aKjcHanjQ!1{|Ay4vu|Tsd80RJJCk|PE=sb%lcw#;I;i^jc1?Bf2d57M
zMaB24v18%9wO(;jgR14bmOq3)PW?RWpCE|z3asIVs#9OS`OuAv(~<mb3Hd#}Jn%Sv
z+T`+YrA4>7^hCxhvP)-&Bh_hkhd;jrd-qYo=+1zyi)+iBvBe1Z<q4XU=3o7}m-jDs
z6BEm>t<5_=aH&@D>uVAJk|E15^r*zVmZvL8AAh2eWB#*=zvc8vi=mf21*2cd+#><@
zKZ5fOOd!{%GAs|}jX7_E;K+E~x;f2X$nQP-Y4?%UmhMY>J=N76j>9|r);@u+vOO?J
zXqld(6i<%mvjQGH#Qz;d!~v!(NxzbFTjjfBp1_tis@u1#t>=Wo3y!}O`6*Y_lCQT`
zs5PzZ{C1_F;fmRV-?3f`^YR@UJQ)Q`{u=Xmc>`U>8|dr*K-d`Iv+2Xx>hz#$>#ra7
z3pi`<MzIFFQzft6y#TW`BmoK)<p1$cnxsn409E-qIVKdnT(Rs4-L^hMR3-DCX0x8M
z{{DY`9aJ0NdU;;sbZ~ms7$oZac#8*dlQ&U0`VV1V-K^W`ukFyokW%*>Up3TRqSO-A
zZ0c|^V@2j|F4Kw+32Sg(WJ!&e?oM^Az~}u0tgZTJZ#bb`sIPc2S>zNi0b$R6ZrvvN
zaOZ9yVkZ4a_S!SRMn$PsnLK365~Or%Z8H-*1=`>`-Oa@X80;533mha@wbJv!%A6*<
zl42@4avvOP7c;X}$N>AU5p-Y?4x6F_^%fkvQ@lo*)_bq5L0{rO?pFl`y$;itX;J(q
z4@?)MYvDHy94-efKKs%QW22oq%6ow(ZK`-CVGH#`TV)L>>UaexH1X%J%CJOVPlgG*
z2lCdPT;o*W4Wmh`(qQq?&r84<LXajM=m|BaXH|)VZ0QyH9nhu(i(W|24wZ6Ps(}Rv
z);5gnA6dve4D8B90DwvMyB-{bVFlOqWq~Xm!pnwt85!y&u~NZp^G>&enl&^4NZ}X=
z<8i$1DP+FqcTgUlBpxAup(kTeoZ(=yO<53yV^JIkG!9rhz+!X}&#_J71Xi!10>JGA
zD}FH-Plg^ub}l)>YKH>&_)ui9CPvY~Wu)CoQK!ojc^r=dm?u@T@Ln;5_p8Cbv`8q0
zX`9k*VkL?JgPx%k;{>bF0c5*VfFa2LX60EyBj%F&atkoH;9_XfJqvR$lOZrja<5{+
zjz#0>fXJ&xl${L#`+D%5cjwWWQ6QJzDXsyOEr8hHCasS#+@k{YCW(Ya<1EyyAr#QS
z#KXY?-UKM0M8Moaf{dhCfyHgy0NUjf1>i%85Ji9s1$E^#1Koe2ZGX&&J8&Ua39cHd
zf*!1uJB;+t5C+v(Wdi|!z?FjGERBX4sE5KsGjVSznx0Stwj?jvRTE}m%LGfJRT!vj
zgH148PXbhwnc{#xShOBepRckQLlaO1MAF~Z5%f*?W2Y@c1DEtbkXaeD0O|V3Ac$!F
zO}vX9%Um`Gb~r{)cn%MNv{Oldj?A--HB_8zyZ9B=Q3B)jP3OxC&|?N~rNsrNf|{jJ
zpmy+&LYw`8>yWO@rQub{c!;)|(_)$m^-K(#Ds>G`u5qw5WL?+CDC%QPSOKXCNa`SO
z5@GJhAYjgj&0+~6@%Dqia)$*o(Ci;jAVwo(ITqc5{Mw~j3>_nY%sD({kck=GW{~c~
zQ4B&s`Yd={$Xpg=hdN;@Yh92IiRSIkV@F%0&ptvzM!}?{ghwAUr=^XKN-s$pOFkal
zsqSOQk2OCX@XLxxykr>p^T86q%T_XpVLqeD4Y`s6HZJ?@swGD_4y+G53i7O&5J#EK
zuN`5R&VQrH2*nan;xPs|7DL`Pc_R^7sX?ZPwi-P3iAlg3s*o2-ks;K#2i#_uURX6U
zm2!(d*2t<<*aW<OAfx5G*4>~WY~HkFnfU`gxxegn>h6XK`^g15d+8^lZ#V<RH?P`T
z+9Nz1ikM4C1FDxUwL94crE`S|JmwA<OTgy!xvVuZ$6j?=*xwV%b02Gz5Q?1Nr}F`G
zU2$Z(*e1ph^xLn1e^ayUVHi*0ul&14IhPnZOGGx*E{SEbuu2*+C=?P{|FDi8%>?bG
zOs35wRSBxD8@dh-vP!Ivfc|(r7w9&a42^)EJw(Q3q<(6Pp0!Pa03{?E4MlP|-ATY%
zd2EqW0gdEL!YvCm%VDZ|f_i{{m<r4-P1p*G+93-p0+8^P0MyY!m-?VC99<YJrnms*
z3wCn|m~2!bmXliPIo&u!TstV5i?qSbC1D_3(>)fe3c@@(J>X*1WR+HkphpIQiv+Yi
zmy$qdA0~uic}@YoPBm7A<E4Lt-k^01Sv80{BZG(n&sEe>BO3F6-Ozv+urH)DfXs_S
z9UV)G%(G(F(cskO+R_Jp_AqiOlFO2TVsr|!#m&UT!_};|T}JYMTS3iDh$eG!d7${B
zc3@eEQx!NY)5P(Nw7ZnRO5y-S8Fg*vluiM!(zTwRPk+2?#_D;`*k_(?7wc=ueas)n
zxj%kdl$d(kwxuKRb49?%>sb7|R|N0y%N}t1`rU#Z?cjLz=Xy$~3A@OIKD*d}U!xee
z)~10RuXg5fWY2n<n1bXoT%~!96O)y(`MMsM*n=-!zRqT|LrDu%Ha*9E$xs?`Sp)z2
z1)Fn6%9Pz{Gy57q&T)oBhRh|On&4Gj+c3%e)J3XYp;sC_IfnFUF<0dm-W`yA>-GlC
zW_=ziJd*MuZJcOb-1p>F>2B$jba5*|PZ9w6Ru4U%loYeH?&>?_Lk}$kw^PnkzA8?L
zcQZrKT+I>^W6uQ)7VVbGJTNN(&2|Fr+8ZIC7cV|GFPl1Lo{Bd)#<5e}>6a7gk)&hg
zNeK$+|Kef!DF_y?ZzsClBgR4YV+pR%fkm5p*-6xPO-m)LcOkCXhiqOK`Tj*RGNW-%
z0P1xz(KjV!->xj(7h^__d#Sj3F*SJN3$BWZqcWoHlDEv3q&iuvu*2&5GGq>(yEwqs
z;$>C4Y*k(C6$<-tSl_O%2}G5IhLj<Hjf8DY>`Y@&+imf4{JoMdTK+a9#tm90$rN~_
zgM~%ogW>wm>NGhgzKc*UWk|{y;M$}traNEU;^H{e3m+wvD8<F3{$x&ll!u#pIqB?t
zuOUUi=ycSv8gzcJQrWy+hgsUoOFMo%N8RX-ycsP545uyqAyL4i|Kj*7w#%tgvD9gH
zZPw1EhB|>Ro}126`Qa_}D|q87qr>e>hhlnfr$EnugD~qX-%jx+yTjJ!Wto78jfv#n
zmU)Y*F?b-_+3NS~Vr8y^24MBg0}Q?y;(mJR!zGcebdM>U+N)a%Hcm_U6L(ENC6OrI
zO=H!Kxq;E~iI1N1ABnYLfw?AG+I*Elmz}CR|H;e8<I;W(V*7w|rRri)*x2%f^ZpW3
z^CiSvVcVzbpU>Z(Ddh~k;V_fo>nz%>EXh?KF*LQ4>*F#Lalf;%$=~aCfohiQY?9Zv
z?TQsmGqGu5mDvj0?(089oCDprSDaJo><!XXnqL`C4j_HY8~0MCcm#a6D+Ea?STooV
z$Pa1@s**R0*Qo4BNJDOQyF9X&?TDldez>%n?_*QYfCc99hS9NZ^`gHgHP03Ow4Hrq
zl_~AoBX)6#c5Auzv63p-O~qJJoK8Di!FiZY@DI#)Vp^}_G7cUk#7&8M(^{>M+<(s%
zT7wSdbBu2X`GQtULBt8@eDiMQ5LemH9lX~GS?1D1oW1e9>}G92^kD<-7sryVd($xg
zc-XrOW4YskI_-yYU*6m6M&A`HU9nv>A>;5brc_~Ff(tuUPt<FeNzUBIJib+a;bYWJ
zg;#%w8><OB`Aw^RFl~#cp{V@rs}Kkc+txL3tZjInaL4pbL@ck@t{7AG0B`r-xvKE~
z28eN)&W*X98l#^I(?z9c@*4H@@^&k*QVw~qty8u<s;t#^7C8KWw>_y4npho`0i&(+
zPdCS&x?RV1gwFY$^b4MpbZ-mQlG@Oi5lOsr&7?Ni&(+0`a>aFnzrM%cXz`Vwh{59b
zPnw3aW7ZCtjYq|v3Y~q+G{0y1MQN1rTAbcMIKO7wuNaNJq3C>FBCv?<6#Z4<gZ-yA
zIY$)$N?hjn)T)Nhb0@t`u5smA!{&B|<BWE4W#$jX-fsT>E0a0e4v$E^tLySVKKVQf
zJfKf|H*qPnDlAFj85dS9SJPM7S8Uemo4@%=-l#f9=yEPe@FOMh{Qen;9c#RB7;yJz
z{L4q40~*-tY2OVy<QfW<A9t(?;|?tSYbSNeJ;!Gif(0wC(2v+FIMrzFEWTibA`Z)6
zWr@JcG<UK$$>GO>cVPPu-AC^(j3NhTjL9W8M??RfP^bI{a@{v<t#v$W;#Y-LooVg|
zvEAQeBU&o&&#sYrwnZ>ooZS&(Pb9IAT*a#OoRh2xmYW~n#8jWTc<lSQEY}0QmWb_&
zfTu?7-VsG{Q^MBG*M2<cY~d}Wp3VmFqQjN+O+WI@Au~tO?Y)s;7Sp6=+%fo+omzes
zk#h^cQLA~@eqX=Yb*`<|oz<IXZm-ia?@uZE2!o#AzJrbFx8EwxdJN5hMJml*CU!sh
z%HAK&A(Hx{c)a2AY0=GF+SC2A%wG!DMzwa{yDxh=My$Af;*(&XdF`Kj{pG!LPU<``
zP+VXfYs&eW@oBB94jLznH+`67b*ZbY_2nwFDlNR5aOli}XsBwL!kuJm!D#4~UYod|
zvo3lgt4yiGE3_uqzcV{8ufWR}BXHtFpmWaF2Vr7#-?dRo1;6wS!vxcJ#kdh-X6U9I
z+#s7bVBOSiKUb!x%z}v<Vv(x(=o~#8h7i6}Z7TY8b2RFF1+&@0r+Y@xHiR8<6ptpx
z*8lG!WrFkfNM`(*T}h=kMc!EsHuHjEykF3roIKnPW(bC<aw9wc1prfwEMg<ytwZgz
zRo6(jHtCLv8Nar(f6wF3m}rB`pYXONo?^MIG;a1XqTs%h`qRPMI70f)teyQt%~79E
z*p-Q-`Y(CW59a?6TWn1Fk9jU5JEFZ!ZsHf}f9EzA2K98T&|jX5$jG=HmsEwV3;elD
zWmq`UgkSiakiV~J&t*_bxg_ZX@+>~S^0S*U@9zhm^WD7F(Bu(188b4TyBvvVd6jAC
zW4W;TAIKAS7cUuPa?Xe4Msx3oM*FGuf(#21Vm74^{m8zpz>$3ZVH1ynH$3==;M;|0
zoIMM<Iu?oUsbn*>UboXSbf3DRx!m0P8(p5kdB6Nr(0NOOVX5aGYG&z1-&+CsNEf+x
zGgG9yS~g=LNld2LZzqqec`a55F}}Zb3^+=Rrw(5A^WRhy`Q>ga^{SQNWGwC0{b9R2
zcI9J#*a47Id2W$p`w%NuH4zF@zr#W%R76MRE*UYdHyh5+-W&OK_FUo=Gd;bm`C(#i
zX#7bQ$hi{wF_%C4A;0lon=;*}INz{Q2EQ_|iUc?eSIBxvw)tp%-s5dJ8Svf9m|Jda
zwjOIFZL_fz=sl2SpDGx$C9pKpa3MJV%0}xe`#*a>i421LCV$G93&XB<`fRJ!Ysb{f
zb{}!9m3EV@Zwh_G%hgUk^7m!k`CVt6z~fyi%bBt2T$_d?bPF^c*j9CP_%o$zzxUFe
z<7QJ;Zu}^Q^DUw}I(ns=YOvCEHbF4&Tf>8<)P2c#>4k^w4t;?{?j(a+<;%~{k9~j0
zYo<09+abUZS{nCp`@F2|5R!XxNe_axRl0ck`t@wut8i+PoTl8LXU3LOjQ8G!FSR)X
z1VqjaD2YA3bke*|{>VJ>WpJC7@wMu!wdws!H@q?&F5U!TH+Gb^oHfm(yW;x&M49k(
zrb~L)nnvn>Kj0SW%iHCDmg*X47o-n)F1Tu4enN3_qU8pk*KtRucgyA<W}bfo5RE;~
zlrOD@>?Rf^r$5&^Z3iO8a%0AtX?)jOu>rn&F1Q-GUyF5Ly7+X@XR>5w<a)Zc^S64o
z+&i<V$t&krDqX&OY7jG4rO_JGFUNgmWb)dRTj@RPy@8&u2r~!LT(*t7mAA>4i_=0g
zJ1!_ab+#IsIDr#wm={Gjc~>QwWgm>!Iy!!ym|T6#K?^^Xn4(|PEE?!t2l=z5VTF%e
z>z3<=_2*Cl<L~rvRfLhSWHVdbIE)@nwNA4U@0FBHa~N|G9cf@a;V`-Xgiz9U`=nd~
zY9a94WTdd%oA|GhZ!QKneZp6#ho|@_eqOQ+lXOf@m{=9v!Dxwi`vyE7v2Svp6nl7a
z&U+w?ksBe|IseO}@-o*(^nJO3L%C@KUz3$rqIvc;03=pgcJK|gYq)W4;1RL2`Fyj#
zI_IKq(C=I$PA8o+3OoGUnJV2|m2EdVc7@trNo~l_57jzab*oQYed(N(-*<B)vVs09
ztpn?sbw|2ach8}v(R{2;rPs(=;D>|^G9OrK;Ey%mIJl(efHs66wJ6VPqwrn5hKceQ
zeKUW(+l=#UCD87Bc1`%#*TrSp!o$8ip2_U2y6_*!P&d_+`Int^uJk8}Hq}cir$*W_
zpS6gH!{Zg3c~mtYdQN;E@Sl{3HR1_K&LQ2t`CzB)<QX$a?{+ou!&|lVg>ZarncxR8
zhO<ak%-u8R&JNeV;9bk(3}GH{eX?-=j9oIJN6}%|<<zKrPuR0C<-@+!&Af4{BWBF*
zCdUP`Q|M8<uE_Lj9-3s&mkp^U6Af2pgHehH<5yMw7ea#s!|4lQIO>5P@1A|=H(Jmm
zs%u!6;>CwG77$};)pEl3Cx_?vN9V0YXH}IRsT`HqUBG{T`L>xSW56Y<I+^e+h2uc|
z>#cZm7Kanqg#SPkok=yCztpvJXGcwrzqq1$2;6(PW8Wj|6D6O6-p_w`FaLuK{=X3Z
z1WSw>>{6W&DJ{KTrdpq_N*O`?X(_LWFCDSLb2$>%9%~iHX1N91+Cou~Af|j%-3+#T
z9SJ=csL{iz>A|l1!&1!zi7mcgT!Sp2y>#JMU-YNXs^3N4Z1er)XSjX4#$6^E)ouvB
zzvfhPQv1DBNET}w8@Jyh`ZL9fO7j9S^(gdX|51%-=C}PSH2b&HE>k>g8k=y0vEj5g
zRq*jVf>^5Oq#ZP>*kKoZG#cK)+1z?ytF$s!RpRIHn5BD<{04nvizcB|mJ!Xf%}mrq
zYo)g<(&RCeK?F@4mWEcPfRiYR-Jcz8R)YU02PNK=_oST#1DEr%$UHv7BUHea8X}^3
z9oR(56lYR1liPR5(u5Jv&S_ILWdYy;3y@F=f>;4YvF9N-(@DH604NyZfWDJ0rV~~V
z>?zDdCo9gI0zKqyV0n!`)du-{1@Gh*eHsk*27vFC<xUK!B$>*fopztiALHU=H%sS>
zp(oHGz`GR4gV7dpV+Q;&MSVpSTNr7Z+#nnbPz!*Xt!|kxggP>OVD-mySx+R26LJM%
zJVr=Q=elv%lA&)Z0FKr~lgRq|9MTmc+5s@kM|Q{)fZ5XK359e@NT-W>f~nau&T`$r
z&r2ONhL)((7_7clJ;Vbq+bO6*Vj&g2O9v4mam}&-)QT}Z`q)p|WiTBA#;08>44mVw
z!6P7r2>>GD@&^Nf8mLkkK&{JM)G1Qh{l)<pM0vOYOVC~OJCqmZmIZ^31K1jPW~`2<
zfWkV^@rnQvIt0&)<kT5U<^*$0G_MRjnG+J~rJW%zK%N0U+@YCh41x%8Ks)H5*f5$H
z+)xUNRYX>6n+!;2pGgS^gQwWi0pMYT9tpcesBZz>nq}-vS{qw5H$*<bXd*g7$P7e$
zehjKoNZ?sJibo-g4bUurj1H1pJn0b21TbRUBr!LL$S%Qx0OJhM*}Gv79y8fa=4x4F
zyn2HK%yJL_$m77zMABKu>(DNMz81MkfXpyq!gIr-UFsj)vNY<YDR3QZQz<KG@HFcz
zg5;G1&I&xgs#E~2;${mlpi1A@hezgnLLh(O?DQ-!;{!v{0HetwP;F7AO5#yqeg||*
z7ED%oOR#2e%pQhnbAs4iG%zj4320c3xMe2%b4jTW5!fB90r3xk`U7uYij|$U0P{69
zqJxFLx&@OvodBWEZ&1bhqahf5cyYQAB>Cp{VqCXqeY-hTwS~mWmT^tUb7>}PEL!Xh
z0shWxT234YCQ&EiyH%+?VZEigCj!jak<sbG4f1oi1e^Q3f+eg{+epY-8{=);0i8wl
zcl}PnE-V`L#lhm&nwRav$Dp$Lau#dI5d(x={;DDoBkzv2T92I-DT8u0np>JPi`#s&
zSDAqKWi#k88Sk1*ge>_EY}@hzjGK<4zq*yAE`*SOfYI1a`79?cXpekzVEfrTe4m9Y
zn4)0&t{|3tZX*A^?Pm0L@eBDGm~FfZ$6WS@6nZwEP>^4KDW}u%wjlDIa*PRQmlmd2
z8=XghH;d+3A7`85NvF4kmF4DHb0boo7ta-hGfeu`t)MDEb$um_`aSFqhWdZ7^<L3%
zJr3CJFnWz-M2Sw+2x3GXC8GB(T69M5HF^*eMh`{}qZ=)HNl0|jMvWj^j3J0#BKe*D
zKkJ;EZ+#bXVOeX~v$JjQe&6S*j?Q|mKMc^kfifDqE-~xhDmk{6gcx&KEZgl2;7>9n
z(1pQ!Nd&@~wQpDXDM22-T8sNSK*7QQ;PdqX?7)P$a^5EbVG_Jj`<aS^>%JNQ7bF>I
zy|v_?@8pzotW$shcY!=mr#nZ3q#?}8SJQexyNYx}lN2_{0XtR%D2sB;0<z&)6rk67
zB0H-DU?a&4zGE1rCpe^F{8JdAWPNcBl=ks?8OO9JH*Yf5rKrUbtVmhpdWN1<paAxF
z;0X>Q3Zp@8AP{GThp<~HhM@VdZ<DQnY0zXi!q86u*hR^<vZ}dx`KryHmk{qCsp~ME
zvB#4(xDk<}Xz^;1Sv|kuAONo}--5<rI2oZ<#6w{e%4em?TgN4Y(F6cPsi-9pV8Dy3
zL9%*%6+a_k01E?5A;ZiMfL*9&77)*5{edfKbi}bv`7j?sYzoq6=)=!~5F2DA21RH+
zoamX!%Dn1gG2_PIeVb^#Q*b9$pEg9ALr&0M+$?7kfab>?n*4&7SZ}<o2hP9rtMY4J
zj=%Ri0j>p$x*My_a6h$IL0sJg-mGVus$hp;i;<4DlW%32sLvA*P%_RRJTd(3*@`*Q
zBkrZCpBIcueo#65U}_LYEo;4qpQy{{F<O-P9uhqC8~W_KemW8UM-zq{`j1<nA7k&P
z@Y>GgKad(flN!iJsPN;g*Q0I6>?h(&W~OTbz{V<piI?bH_gqc?m>%=F&g_2kkmcc_
zP0I>hmK*e3>iQtA8b?Z>a#4}6<#5IqXL)I;%FE-VB<Eah^+GM66VGQa^ng{<?9n$X
zE2Y!ndmY28!}Jw_uA|=tJ*0Ns!P*Ol0b1)h21&x?x5j4WOT5{&%a0n-ezjqyO_k)_
z0&`h5!;+pg-*FBHm8;*BWv(03r#u$bL=swX-siG<e_%B&H)0=jrZ;k=F3Sa<E*UgL
zOfm<e)~qDiUK^*a9&M!JtcfRH2Ma0_?7C;qKl1Wm_Z!j<os6ixkBk>WQFC=A8`C_^
zOg4qeAQ^<e(9B&+*xz!3VN%tNR^0+gTe8Rpjdj%z)zJ_AA`{A=Yv}HHPUs=9YcHNQ
zZY^Xd`g)#cC$;s6AoEBi-qU>W6!QETF;W*^OZ!0#$K9#|Cbp%xXUJU^TAJl#4lvX1
zE8R^uzvf9vHlvqZwx;13hV3>UT1ygIRfJ#Gjju{*z>R>y0<~p|S<vr!p{WPd73H<4
zXPzETFJ3|)ai)JbmuSogeLKuOXBx1qxzhNKbL`^0#&`0<DAX^90;b|`T<Mvri{#W(
z4PZwKC|=eyTA{!Ew2iE!mzs3Hk3<jKZvEUTkKMHN&;0@Jx~OV~`RWeosz8^QSc{S~
zEE}YD)N}Z-6)m5T4^O_0;W)t98aiaSu}60*SE~uSU3!g~)_$=6r8sv-)rZV!BRvmn
z+zUzn5FuB7$k7l&+xVS`)CI7`0~Y&$vm-gM{6ORTAxhsDP|#Z?<H{{QbXf+k#+=tg
zMBo*t7%`lWt=|-cW+T^T4YYt2Srnk$l4x!HOdpac-&-4lfD3QmRn=pyt($E%?ou)R
zvsAwq$ZcSLQfpAi7ucj`JoD<)+Gh=e<;GPeOW=u`^-Xb3h4F%JWtrNOJUbn9V1J$4
z^j^yEt4|-e-zC5?j;9=HLu;k&p10P4S;#%8YwFlQV4bwR>$c$jNYyu8_iSB#7f1Z(
z(s|ael7fG{gmt5GG2<{5UVWC0VSV?nb*&HHl7pZB$t>dz;Og2J+C8$nr+m`L{sfmT
zv8r2B)w*)BzfrEU>Jh}mSjoTHbRdF|LfW*}A(@m|g_LuBZTMLXcQRWEsaLRK56I=S
zu<~v`CA6%ITmG8@=?3Eg|A7<=Ro|J}&Ch^va*GvvVLF&E&>^0?BC-><n75j~9aL=d
z@c6eDUiH*DnZEIXTk@rix61$W!8{K&ya-5IcxILrb=8M`^)0X5G!DgCriMMR3<7HX
z7yip`@kMfKX#^92MO?h@K5tL&EkbtBWUJ^wit2|g8pLC<JSmM40_PohxDNsvnol-z
zTA!`3m<0=Ge`ufbJe4$bBZq2{E0KXP#z|s50ztwOyk=6TqM%>y&D~$hY_||N``^EO
zR(NJQR}x|F@4;fx>Nvz$c+8Fs-&=;1p(pM=zxgLKugpX?Bc5(enW_iJ`jFvJ_*ZwF
z-s*^H$FoL+PyeGE=s#xmnCBT$u;`C;uR1o23*;_vn7gQVis_T6S<29nFbT8_Wxvv+
zUk>Tj+O>?H!gd&NCM_tU*KvsbK+5y(X?4EB=<_;Ur!_5q5sT)n!_GwDC+c}Kb02Zk
z4$c}Y%FQUX*_E33#kt;$l<2(Tf-L_N9d|?%-L!+mq<PzB!6p6Dt<oD<>?iBiFZiiH
zKXq2s2b~_iFNJaIlKrmYBdyeIx%ke&jjDBE$h+HU6KxvDO@vcOaWpU%WbY|0dpbQj
zM+g%$rEpC4SGTtfWibRl)#9iRIy<ZRfUo9`n7LXw9IR+@vxt@s4dCz#N;ZA9Oiq+V
zeT5Y26r|W<VmoJwdBA}P22bT{6!4PJhQ+Gamsx*$vi06{Fn9`{(6<{=Lpp2H?we}E
z-@%g1#x;*=d;RKQi`w$e)m{KNj7dp~k5zC5#dUuQ*kS|@#l|Uc3$P9{fc@C%@tFiW
z!*g3PW?P+DFH3U2k_)2Eju%iS<vYj$`)Un`KuQvVx0OC_o$(H{%%7zd#YQq*%AIXO
z`~(t@gdMzJnbEVoullah>zI>jGzho2`eK~meCqgu8(gu%{OWUK`x-^7?I2y51Ktef
zTd|u$sURp;Y>_SJl{xf$;g7ip^&)Ch;;(i61B&kv0@79;rSS**Bh0EpzXC{_l2*uJ
z{)RnyFUz0x`h{aV-`@v-Vd`sPjdECmB=teF^d_O?Gicwm+`S_`)oVBUsHfj}SreFZ
zn|*XZ=6piMVN8Cexs`rMIPT{l2b%_2$AJ;?*k3nd*%;QEuPy<K(_$v!%wa676=jnw
z5%9^N0tBe3ovD8?$cB2}D5R;=`%){op3`{**Q!T_Y_4l+TeMMOXp{(aSo8EO{eDSs
zgsmrYAbR!oisGjn_a@Jr?H$dn12QpWUVR7iH%%N*nKSRaLZ8@KO?z7L!?suGKZa}8
zm=?#w>t4a^wyq3KyH0IczYZ8&+B`Gs<E#XGTkBV|Cj%36e44N1xsIu0$bNiM6xE_)
z{&k_mcg*I-6tML0WtX@jOA0Q@%X<v7Vy-j?wg^)#+t{}Z{<i&oZ?*d7Q{qOr+V#^6
zslm{ci{#(d;&dl8w<qq*$mKVgL(B2#o8lXOqC0x5LYW%xp7J26E#~Y`e%hn&xQmi-
zSGX5`bny{Ud1bz?`op5o@2gC#TgxL8!t6=G;k@K~2Ar8gLjvy<bxkYg9;ZwjQ%@e*
zwCZbgMrK>T8s+1U<1zf{K^pIr*|1@GKdAe?Lwe?*V{>y_1Hjw=;4Xl4qPjBrA;E%?
zeY2LT9WTtRQRqkPJTU!Epv6f|+3;cS#Mf~M^$z#njqcW`H$ytG9G~k{-WHUfC76zl
z>!;8C(zM67^IY{WW%FV1Z%!Mj5@Q3F=6CJJZRZc9@+ot7l0G_l{B`FS{eGFcVPv^N
z?48dCaVzY*5at^Y@@Z1-b9v9(^=wyqt>b1fUI`=df%tV-Y#3@L)oRX*`_9|UxIV9h
z?&{4hF@O=O`1`}%WKe@t(Vo<K>~_QWkdW?==O0sbpQNaonZ4|q|Lisa%kLUX$yizo
z1KymKrtW9Z*1tv!`2@=3U~Y_mFcP`_eylhwhN}J2or3M<`&#jkaQ)V_2XCgb^wunX
z7WY=&>F4_jJ}Fr=;%VEQ=F$!tk=B`i`Q-*;mZNC<gyw-nYi-DVXL5;pZsWb$Nfm2W
zBFCvfSI^G_!@)WwSa?{>hYp%tp<7LA)BAOZ=Rs4v52!#pU6fPgT=3&HOEF!r=<r#!
zo98b0ajR38)srKst))fisg-a)?-PjW#Ec~o)y$zsV4Y>}i+c3mrDe0_Qj1$f4|vXp
z?^-(*#-ja3*7ws(`)gDlweu6@H`9h~cpNrxdVKw!BloIx7S4>Gc$LQaxnrHyVz=_G
z?+h_=SUKZF=*6RYGp;AkfWnoL-t3XEL^V~j`o-`=0&l!Eth{Cz^dn{4-&C%J{fp)3
zsat?i&3b`ulvxXWAW~P6R2X^wvq<`x1pj!%QDtj*(a3RZ8S41co0{4xAF@NC2I5;~
zit`5uHNqdE%>q3DczZ|#T6kmDg%lH;b3vI@0HEqhj4WA{w}Z|6?=hW!50b+OLv9uk
zfkp)`t>Jv1@k-O*SBezwSxFsjps-iSKflYF&_vU;Bt1sx(avM}RJe44dkGIIG5o@Y
z6WdDus@5GH{O{0x<dt7Z2+}@uWW`UYpuIa|a!2+JV_6v$UEi(y43b)tL3@1JEkYpK
zK5qX-B>N{%HMIm6ZeN?yR>jQ@o=)o&-KfDXxv=_l-rfEHCQ|zKMSZBD%u}!c*T;9+
zlHbP?%LE#VUzvc~7Y^w|uDi@Cqw|B4rcBKH`lsBaCj?lcQXYn>O5VxfX9Bu8B%zEY
zDj4X&94C)|SNkhdFb{RK`gwiW^yURk=c+Yd(vYXEtvFCl9l{_Hj$NK;fy$)YnF1FQ
zRM+b#I!(H?<t{3G*_H2UlLPDb`{l`7j@gPYzPH;3vv^8LtQ#l)6napKi^Uu?oP(TS
z%PD*wZfY=3Sf&i5q*DK+WPalk4_y^pwTpjA;rC>|i)0=Ygek47v!ID^9pslT%>`Im
zC9eM`!xb2to4wf(zY04iHM-}(t~u{aAuTmUuWaFolK3`t+wA>Q$4k3S-oCrY@llm3
zLnXEe?Wc8@fUniv<|#g(byCOSD?!>{S59`N+XvFWT}N2dRl+!SBU^W(i0fak(Z9PR
z_H)elY%t6g?HXSSWIdk|;u;;{z_Lqc1*XE8ZdU!5pWw_`$L9@!^iJl1pb}R!kL`eu
zA{3D2ApeBZ3$>(L_)Yk7%F>guj+Rgw8;4spJR<lH<fzZ>eZ7Y}DIphEg%_E_{Gyl*
zm~Q}mae%?8D7(>%uy+j?vZ1_41u=-@%|hk7&dK@PYQX>gY<C1rHw&SDA)cskx8>^K
zQp1z$Q-%11Ugg!+AFq&uUjd7u>Z_*({OlH+fI~)SbupieNOS2Dhgklt>v_JN#Bk|E
zHdU@&k1S`@6h;SE>i23@t!I4Yhy=%_TR4i@bjX)Bw=z|v8a5h}jyrq)2g0`QAx+;H
z-Zy&pPVGXfnpwgwfr%}lP=%1o(pCQ_mx}y*H*E?Fegay;PQ5olwZ7~7!-7m3hWMgk
zq9`Nlmk#D@0*O<<KbA2afujU#yk?*4*gU#^h7bC>KYb);Urm>YVO6xp5BY_7EcpA)
z9}TQK#Pj;<R-Cg+)n|&@_?xg-<9aP^#7!I-{Sk<GMZ0~|>3MO}EonyjJ1hQ6nQ^KB
zhB6Y;TK%RlUIbbk&%b|O0r<m#lrMOKgXSARlUGLrWS9cOO8{6y02tCs%7<JD1O(K0
zV-*BRctu^yhe82P2+2BNKCbi}0jgq5ahd?r6_Q)>7+As~=l-H21OUrlM{KflaXTwe
z_5m6^!wbp&x<?v_pgXUF%ZC9Kxt0A}P<}`W!a{5zhI|&o=P}zfND>nRd5zE)1wcOp
z#KMGtb72bN$Oh1Bdv`%xC{pOBLJ`2U2iTum1t76$pmh|frh#gdAQ7O2+=3V~+cItf
z!itD$(gt8_XP_}R0~iR2kCe)ep}7z$gDDF!fLaPn3Ge3Y1G4tpUC@!@K8jzyN1sy$
z_0o-4L`e~tYbiqX2?I(32L<qhj1wSUVCpx)r}V$BS7&Le8_X4SGaUtt6$Jo{XIb%3
zrgWt~A%LBobp1yG5`c@vXvCpFR{m;k0@NUZLH^CmR^a<p^yBXb90zI`Q9^O0Z37K}
z$Hh?22&J&F<<nF~0bdQ!Hpu}L;@l1bICda?0X1DX5XT{`Hq!toZW^!$Bbu220Yx(h
zu9!g(KVu0>`9QIP@KoIuNFssanw||mx`eo_1i--nuMYp88gdZi!w))A^Hn4PI6Q>n
z*jNG%>?N>0#V}3?Fs<tY^@d#ZF!1EnPCcZAcvl8%NMSSq5>dh;v%spL5+xOOO)D3?
zBKbK9@)Iz%1o*Wm*_kUK)FjY~h7)kbhL+ePEs_oGvsm;&B(xS{8Vd!aEYpM(HlH-9
z8B3l4P^W|(NERqE;8Q$%%0m!Iv=1$y!~@opdYkL|QjiX*GSc4_gaPHiH&c%01of37
z0nZ?nI07VxE!cwQ-5hI!S>fL!y0C#4B}GzbF}Rp&=uVE@G^Z;LT8xx$q0s>WaV9&4
z0|*A=hRZpC6)GTSf0|k@%0_;J4KoV1ohf!Bk}Ci}Nzh_o;2X$vfo2s~(*^cUsw$5U
z1+r*9o`Fu*&Z19sSSWn95Fj6*h`D;8*uQR=M$G}zk=B@k&ZJscts4=H$$RV+kS?HT
zHN#p#{8q;|vvdC1q%nF_Vn^!a^r3r#DlC!ojM8!e)pw?e-uS3!ck8t((x_RaNj6~A
z?-6K9$<KYoRgkvw%K-y8%^)!yBBN<AHjPH97%*Fz*ho!q@l6bBlfj}im6c7@A-_8z
zj<gn%K#&D0D$zG8B9@XY=l2|n=3EM&eG&1Aq9DC!{y}jVsDAvwfNoOI#dlKh!wA7<
zHJQV4F<!r^JXAEIrhAOk;ytZ%1;a4T;5rXF%hxK}#L3+N{p@RyN6wb@83!TYREQT#
zWtxDti5=+(7tMiAr)SMibygII-QXS$a?@hpuhG2u9S+mj`=ceK;6YBgbd9tpVMhLO
zinOB@f3VJ}<qVXR1(%x$-Pl+-h?xvzP=E~_WB~E?vVFoL*Uo$h(11pGy6Om<j8M=F
z1|4V>%&JP4P#F>|-3oLLl9m%4BY^g(Y6u!|y97W%n{eqN0UA&l6!fu$SsS4br;^d9
zf%8vBRDtlSK1*eC1R9e%VAdmzA{akQAeuLtK?(;+WW)g%AT$(Iwg`<Xg7cqkMl&4W
zR`d7&%L3?%3>aRe1Ev2!ywPw_Q27MZ|9iQJM^FiIe_1)WQa9`MdcaODxu#4208a+!
z_Hc4sFROalwLYgmLOVvy2(M<-k|1IsW9Wd*VhNw-fWBs%%c=zCpHdK)<FW!5NZ#jZ
zQT#~x{tuMyT-hhQA}O#j4&?@@%rWuc2CghWIBgqH%|%#Y!whb)1bUjv0Dk(XMl3)$
zW8l7ZEh8nOuuu#$$8s={z~W{?Dm2i<vRhdIydrFu-cbLWtsX}8qQi!4w4tzb&%6&o
z`N#WQ();SNYVG1DkC4=gZ-(N&g;@+{OL)RweRj$RH||#>-Vp#D5E?se1lgBFNGLuI
z%AiqkRl3(q5Hl4P{z6k7w3Egh$#l%xT8pVDiKe@BwClg9#~$wMp`iSu?JJu-U7jMo
z<Moz5FrrHSjIs|icg+`OY8G}3%Og^)WSsNEJxE4IgyziX8eC`LemSjQzNDWZTa(-)
zYAr>^1ESWSRb-maZEtGJ{Btg-QMF8~9($zrEg;{KG*GGX$Bz)N>xc1$C49K#B3f+j
zX-`V$Ty41V?~xpJyPOQ^(K_P-n}myx$>+lCmTe2drsj?W$ESSdaJo!n>t@<$M5#5?
zuWdo`OEqQdp!}^Fzv)4r{d@m`?(eNh+>_ojYOC5i3K;OSk^2wSB}8$^Sj5e;f4ykr
z9qJu?C;g#vhok?X{~FKWfb)ZAL~AWL-OWnF??t|~=DCkqzN>179xRu%s+XJGrOlr<
zv#adqdF0TYOt?BlpI#5=T~LNKR|6JBe+kb?%vdx0qgD9yf1o}$*^mnMlaaq}o`S!6
zYFW1&NK?b`>347-w(CJc>57=2wyZj;7q#HH%b1J$40j3N&M3MUC(n%pznoS#sZY_V
zJ=q|6u&>`+p+S9fUQ5gVZAr#4+Fv&#Fr7w`TD=tI%$~*4fGtY;sB%`dl)NQ3Tbe)a
zS%Ib=_jyYIqB^fJTYeRsE)Vg#nd3d52^pytt{n5zm=J>GTQW_DIPbWuLMnf*-wiWe
z$lS12wJg_IS*N19XY@^vYm88gslI5L@@mE<>0hM3-n)l?fIm0%*1u&aWH}ZUoYmpw
zBm#<0M$%x+-Hfe5XKiLD%EuYB26{Rno?jOZl7pDgc$KUs69%K`9JLOmOePbSQ<I`G
z^C8W}iWDR5jt4dzuP>YiWq;l1tV9W^hMZT0gq%qrpIRII6o$O<8K01d24j0=UQ)jp
z5q|)Rm@p{rHy8;XI!-v}`VbO4y)3nRu2!6UNBR~&z;a&S6-8`?1o5o|)a@5jt_>`y
zC>V;r=(?*q&Y*KH+BwLcNFREZ-*M$A+Y72<!){7EERB>|cYZ(Xx-4OP;mA}OSPqK0
zRA<}F^!A=JUi#?Bfj%nw*RuIPm|b59(K@yaYDoG_nZi3VtFymG_d8glR{VX_BEvY@
z=m<;0mC2`rrON~U0h+6NHNJ%+zHA!fe}S_sY8ou`qG4;if6vlZlWTsaO2iA&XENdq
zhpR^tNyJj!950{w(U1)ryfFP4R_37~7xC>*8tv6wnhp$Is?O`gUG?vBA(s@m1;XhL
zTLQ0G{b4?;g@bI^W2*+S3q8;ulB?Dm-?#C2f@Eb)&nc+JycN1Sq|Nc=9hP(aE!37B
z=^dn&_vW+ZS`2<>B%|JVr$EQA&Fsh-<Z^9no8ev-dnlXxg>y1O=zT2<RW8bEGhcBh
zd%$ilqiYPpMoa%y4>r-e|32%rS2lJJ^Dhe$V|Dnc0yf8gEKO4>XULfP>X^`GJ$}zG
z+_1mq3HuYF;@qGqk`9dF@&%N$!uvAjuTVkyIhiiep^wbWS6Q}h&#m#9h>PG9Cf`MA
z4ENT4h_iY<CQs|EZz3dsxu}wETg>~2&dlgVkr`W1u!!oBn$)#kQ0hRJ+%B6f7in>U
zeI2)Ju!C5SZF|I016`(-r0ARNXXAgj23=pc-x+jnV*L-q|9P}KT}}EiY14lohwqx*
zr5(6$AGAHWoQQa0YR3Y4oz-o$e`qUocaAb*EcF=NDMOktbKYby_3hamzN`bUNA>Bt
zyTMfcF~%DxYx!pu;w=|ImE&}4KOatHw45__EW*{0$_%eBJJ8R)3>Fy1>2BD!UN?Pw
zA$bh6p_$Iect#Vp(?UUu`XW$aB`t2X3DquY^tHQXM#;@nx6Y)WQk`ev9e$Cf1}i4E
zUUzvD?ZAw9>z;qCJ;{-WN`ili+-0nv+<<f1uOn1s<5ML&lgiTH3a}ek{v(oFq==hy
zZu5HNP;h`+s{RiYR9tTUV#$pVPeR5x1b+(k3K<i5+9yK4v#{TG@ubJ@lja%5X=~0d
z#Xj42tpld4-qVuXBiKxZ-KF%$LdEi*dzCG;R;swxX8cB$30b}ke=TU%bYT6u>{5+B
zC51-Pys=01k4nqe_i9R0IODVL6UH{gg<rmm@Hx|-)(>u;3g>h0x{C=vi&ozbE}>>D
zJG~<cX;y0S6AU-Gb{p8wouYrpIJiM&JoY}(9{z`1&h{_0(>}ApGF^rCbu^3ZSsg}Z
z`QI{LuV{!}^_OcSvRs!|dwR4;MUTbCWfiZBx}W0T4yCG&OTHtJO#jiaO#V#xAipq0
z)a<O<cu05K$#*eMkqP@v%-&2222ZIF0v9;9PH|`7);v+5Ao8EZlZ}5E-&*^Co8IC$
zQk2@aekb+It#Ir<(-Fcpw5WxvkxjkNrC#$SC^V;FYpqL<vGzZZ2k)<JoB468W5LFC
z9E5?6DnIR_vSGr*JkV$XpffEsr$6E&l60dKOw!aQ*b^l0J7u{!)q0X;k3OknD$l<}
zB+G1}T%X@O??!34Flmr%6b+T_NVAFe)0^^zl$$=IkHN^c(v14WC6P}2awTZ&;Gk&Y
zTcy{aS*ZQ8lVS;QGq~7vblkQ-@Ks8HuJxel(#T!^FZ#rzx+}&W*R1eG!2vHE0@E#|
zc$X*NiZG=5^_nGBWUG=BLDP!A(L1V6b_`e&BjVJa{aCmFJwA;%JEFOov-vK#IwV=u
zAK37qtwS&fM_*aFs^t{Kq`O;O1+^KNlpDFAwshLolK7CZ8ZBog6yfjh?hDDeBj=X#
z<pxm;uUbu5^~{5D3l9bc$zX~~O1~S%8(f?qpYVI<?)WyjD9&xn8*|uNN9@0MS8n{}
zN9#7!IC~aOt*GNXGc+mIs`v797XwO4(IujG&n>Oa@1~+Wv@(G~j58&Cr)T!%G5fNM
z0K{P&k2s&Y_pQHbw>eex?<5ng#QJh_q;AQs@5$wPosiW#;|{j)dsmyK3EzSpA|qQH
zy!~zMPqry&G5Y$i3oDb4&0%*S{ULlmgBx032sR|x9qG~Cm+rTP$r>B##g-8fELZw)
zXE-JK#7Q3*3<u1#ol8OSfVc6X3=%!h@apNBkSkS-SG%MYmPzAUm#jvqtpNAC8qDIG
zI#iH7;A!q=WTBm~dNHCZjkgH)vszWV$SWsBCbrs|D_!JBUk9B@Jh~*|n2FW<=*|!k
zoe@5<1TI-O=2{o`^w_CNl6?B0T)kXr3-efu!0CsBL)H0v9-kHGf;1-MJN`y09%HZD
z*QzoJpJyH(4Z>eoJu<8wS(cu3FUpa3UMVn1?$IniA;3S2vkki_-Xwb*fQgUosux3T
zo$p_@(wl3CQur5J?09@#j2|$Q^$}I{61e#DtKsR`H_Gp=f#EA{cJ?O&@9K~>_f@WA
z&M*%e?pj+dU(=))_@=KlwYm@FmAQ6s#}Ye1+aD&(A|_S?NdkhpdMA>8c-4u9#Y^4p
zSNy(A@p|lSI{E7-qfdl;?yN*A?;xh4)pTS?@3gwEG~QwD>2)%^avU=d5ca9CVo!Bv
z(Jp3K;Ar21jrsU_Sn@r~AJkQ!0*cOut#yJgd2`dk{Fh7G9camsdc3LLn7&^k4bX~r
z=5HU%x|I6_n>{^wIpR4Cp7u3*$t~`fGQ3dH(yHZTnW(?NNN-qEQAaEm)E5<MQHPg_
z<E>`M2$Elqv@^09_x8c_h<OUl*;k0ef4zO$*E~E$*qrPT!8qkIyA%3r<_GA2J;j2z
zqk;CS>)WF|KB~K7(E}!LZlfwS#E0yhC~qBo+_4E&j{`kNB(@dkrZK=>hGoO`&BDRu
zfFYLAw$-P*?HxB_=as+g%A<R2VsrmgyG6Y(6C~IYDb`8kjAV?8mveQ6*3_hE0OSfO
zB!K=I3usHK!RpHR8+Q9;!}Y(wZ3hm-`ODXse{oNW%2Rx{KE3wT+JuSv0`-=PtU&rr
zZuGGNyQ;zlM`nXS+|44FS;(^dsSk<FV*OQ4-=)k#)no2_GSW>QW%MhkmR3tgSFx|n
zvvh24SV*pF(GCj|r@TJmnE2&)T^y0fd3`c-0+}J%0+i8&kr3S==#A3Jf6wEgiu;>s
zL$F2qBJlc$oc9oQcu?=FcQVG4x2&zFJMaB3^7DB6ALJIW^}1un*U!_ZUSut;v*lK7
zhxuzpR7>HI?sK9bI02dz(n36n$!8E_iJ}i=<FvvzNqUJ}6?i7ylOEc@c1`$rO_v?@
zO@wx=C8~&*{bo=66(}q(eds`4<g;2kdnObiKW5s}Lis>sqLKNx4&^|5n95t_2ODaX
zmNxXqDQEIL_rA*Yb5g7}er#QzEPeYyQf(Uc0A(>|9oCO|=bQ(jE4XLWUt_Uic|G<Y
zNZ1vf7c3G`H}TTy!;IYvueTn~L&h%jQ~O;jIX(%q=w;5RT;#v`$>Gi2TP^kr<2IM@
z#w4^<-vR3JV~4hxTN8M_8!d6hhv!L|oQybZ`+n|k93Ut^OO<FHZ_1(`TS4H5!e{@-
zJ0pP@Iux}4@Fy#*7a&fmg2jV)*Tb0gB*c?Xb%AmluvRaj$a&-PTCkQy)JsTq;9keH
zms+|2C#|>JO3mflk3+Vqeif*DOV_6Bk=NH#d?ypm>YsY>%U#rlqV0yqm%3xaQ9Vjr
z33XqMVE*f9zqeYw8N~WOf?3S!t1{VT1>`^X#I3)64fLl~{fE{*rCyme(Nv_@sU9f&
zaI@}YtTa$kmTSV_U=P@03spe8%T|C3OXZQ!BPaF!wHlT3IuCNxGnmjb1gKUxzGZ2Z
zjkZckLe95N?6p#~z?nY5{|~)X{}I@6prx)$AfH9BEzgtl%c7vj@0aPeq{EA4@1%Qr
za~mCr9x;B50bBbvg*E2pdrx^SYXgH4cdWl)RM=7~p1yndRx^g&dTEK@w{u>%&c1HO
zf|db~N=oV(G6NrG!Q875djfRo4p)dVtq@OP&XBrI^2Ky)TMjV+$bo4y!}Lk**gv{6
z0~K+O{|%jCg6}HX3(Hs476Y^uG`sb`c4M|*nm|>)z1MQs_B0?|lj0`*7+KN$@~4NH
z%4Wz{i{7suAR(bGe8<+!qO8ao@5fkL<q7+(R5w}+6$N1d7BfT6=(C#U-#c}2Cb*3~
zm&UD5Iy|;+z^}CS-k=`&NZtER!=>V?GT?b-jP9U^JrjEUvg~+57{tL6T$T<jUL&(W
z`cV|J22&e~WUf=KBB$jQgn=VvFd*PlCmv+n0)Qc|L+~Y{@2W8T(gfoK;T<Xf7G)Iy
z@6!iAJJlqXWie{op5}b-uk$TER?txDvV;H?M49f{UqTaRoQT&MywA8|7+iT#0r0~a
zCpekPr~U)k<N%Rp3BaVri0Fj@OIe3<V8^FX24IqNq4vO0g18{W)%Bpj;*=2zSYN^5
zD+;UW2!Tq4e>I?BB@M+(AaCouF?0m$qJjD(e_1;eRFPkxuOqMr)czP*1*8X=Hlrbc
zKn(dgvl60DFv+i=34{~&(GXu%sj|!o)~Y)+EeTowOLjo`|KZs90WH@KG8TY+-3qJ_
zL&LGbQ&0*JwJ@a6l^|?pwv_{z^%kx2mk+Y0fFAPiYb;@ZO9AU)HyH%~Il#j`FYDab
zDlTV9S0o1*<b7pVfT0wm+p8nY2r$tIkzyLjhFh?BQ38}0ur4cOghq=Eg4fb~;Qn#I
z@HU$;ncadKButWtSF9iy1l<?{+NeQJvM``*cv68Pk=+%L)t5Cufn;s~a{6K~q)!|{
z3*gjoT8d;eDkNFh{~_r4FUv?z%YlSc1{;G#{;dLNYs0{lH4YGgse=lFOHm|haz<T%
zC8>nn!ltE=T9iQwuTkW$raKp~2edHZfVXT2$XodcvjWN>4z~b4eqU8g&4LJwVQo@V
z_!~w82xJ#BE8xC^j{yugRt>{14RwI%i<UtQuJj4c%1U<LWkf>=cHw$**Z?#R3hF$s
zjDVMHCjaIqSnVi5w&dY%`KN6B7323cQZ2+|G=Nyo=B(tlWo0`6xB<xmm25Slp^2%-
zK)B0-uz`1OVFYgd70r!?!xa7CVpCBTKwxTgH8UG4rlt>&?Mv*Ik$Ib$$7L0OMc79!
zU?&F(2<m0@!HIn3O#f@o0m>&zlsKT7ehkEF<wq014P}%YC<ySF%7hsP07ht#!wSkm
z_pi(hAhE_lfi?4A{s}P};2$VE22hxE8vvc`n<`S)-O13u`~+c!amAl=X#|u;(PGy-
z1-fpJa32M}H_J=|3pRi4Nxco#JtD1Q@3Aa^zS<sjg9qQ7YEu#<YM<)<I5N3J=r5H}
z3Vvgnq=s1rN4mX_BxVcNor|8nYdaTfa_BBO#f_rw$3dg#?)t#sd+Vn!C<FXQ6*OPA
zr6>EImpt;Uy_|TV9l*Mu|8K_bR&6cwkEx1+0F-9f_`%O@!^3NT)b?a+KnQJWRmD?G
zn2+41d@MRhW?chve$GcfDDihTut@ulg!sYTcHu{fdvnCd<7`dbSI}QKlI%NM9Ge{j
zdBe{_&!NC%_nG`313OmBwV~(}!P-5cJ)xpgM%o^K)zigZS%L=P-#qg!-6DA7V5csu
zSAT`j{fT~Q)>JpUtl~<|xIj*i*^bek&v3cVQv3RcKom)wr1cN7dUc=;n6Okne`(KD
zw`A9}<3a+^`{8XmKycn!8qEL=gyxlTy^Y>e1{^p5qVch4Ib=2lI5COi<-mB2f(!JX
zd||cp@XN_)Hh+}zY=ea|76GzaM^J_v`6Fbol$1p+_cApKX0W*=5xb<ouG$Y!1#~Z`
zQ7XZz#WPjm(SXM~1h1+HMD2zhG^^Lx$gH>`0MV624D9hy+SqB)DV#>S5;x-@U)W>9
z8w#sgH86$=SaAm%X-wm=`6#RD`wW46URhCOzW`BQ-%eJBK$&z202WXhgv0?QVWKS*
z$mkcq!NjH=t1EX0?yEpEsQLLIphE%R*&T`0lqQH=PG7nN8vyAuP}9`?p=tFGl270Z
z>_}BO<y%}JRv@r?gqRkJmL&Slmefc&;L(ec0Z}sz68!~+>!Msay_}3Ne!u~m0mB0(
zw+Pprw810b4qgqK5DiA2Q8_S`Rk*US$znmUUHmzkCjt)m9ax#uE?Ep?l}cRZupvRb
z|3HzY)e{?4#@_wJ;ea{P<=F4{0Tn>7UgJ(SZM>>`sFOmzvYPVhbKYLdqb{PHb_|6#
zr)8^a!)t9p28RgWg%4+`Zx+N>WUV-qibC+#Che&$LZzh32Id!hkn2%tyquV5RQEL^
zzJ+NHH@n>Z=9OBR)t1woi`+TAuk-97>FA^9%&+=F>$;$Qj`ieq__I7aoE=XX#rYRI
zIB$q5`;jqi>9a3CS>~-=QhKB!&|;T_B~B;Be3c%H4LTdSFFCUxz-ncp$oj@(DExm3
zSgGYsJn3M4x{0z|E>)@T`qN+Q?em@h4Ab&)E&gI-(#aQ-+Wq~s(wAkC7WC+SV!6GQ
za8p|S3OmM4qkQ$@))&f7nCjlx$3_(SlKN|yP!j6?BE!P(!`5ymaGSp#b5T7u@stSJ
z+w1;R)>-`vb-(4uu=xXdMf2gwz4{<M!N)rFHdca1t;_#9F_aJ9b@X=-U2uJHA(E8!
zH$7ks<tD2=6p)OVxchLf#W>HxJ?IO~7RG4yoUb+iSG!{B;YT5Z$1fOIBePPdBoY0Y
zRH3BU*VGISsHcj`;G%PuWAf%GL?_-uf>D>FgGWSBMYSDO*lo9zc~+9o{G`t~%X^{9
z%0l#d9_c%BUeVSbpmro2E%mc|KKJq9qzqW&U9uss>Gqunc>O>l4^qf}Q{qwN%duuJ
zd%-K#u({+;Hb;Fm3EnN{)9ZzZy5?tMg<sZMV)Ga<oTWp>!4Iqi#rpTik8CjI(Kl|6
zR53Oh#HDih^deOf_xUq=%JNdSlE4b8h4%QTclW5(JxlDB$Y9mNACDwPuL>O{|Je1Q
z*g&7z1Tq4e;rA!WmtLdFB@^xVwjWh4cks@g=RX~gNzFC>`&psTV>eQGey3N<y@Nip
zn}P_iYB{b9UOsl*pGN6)4Srhn<v8P(m{tw0@)}+!Y>SpYt#dO4kP?r^t6-2*!v+Kw
zQRqbm*V#D5Qb00QhrxMG1939$Xkb8}*mwb|^^Oz8v3eq?+KjEA8rh9ZF&KaULi3X#
zzx=%FOUl7+{u6<7(-L@#o=E(!ZR*Aoy^R+iuAua?kbA$}Uj9mXw)(+4T=JIc5N$a{
zXX)D|pc;<IA?uwf#YoHz6@Qi#b3|)L_=K{@J57|@JlD04^1uWs51OSVTj8-JM<3D+
z)iw*|?eFh=+mLU5s9bj66EGO!nqN#juuG4@k5ny_=hTIOI~(*6M@j%+()4%cFF`Xb
zbUfw+Lb_bGx8K=39ITcZ$YL1ne{^J%?!UfU;Zat(Da5<gchayTJ$$L7{AK)ooo{1!
z0o)1+&({qzQ<04KdOtOC8&r4Q65c^0SK&QNpI`ZKdQA%9U0ob28);l}b6&lM4T%<E
zKd;g(>~oOFe5*PJf1@-gk?F%RJ7pCN3>~iLFceVeU$fD`g!N3O^?Q>-m93rXCVa8_
zyCLhxR?;>RZi9vU-y~OmF#Q?*N5A+#S;F9(&(+~GFj>91jC0k6?c>z2Y10OUwrti{
ze<WqQniKv7PQ!05cH6W&(t;)CKUV#}rU6+~0`EI9dxAYPIf=;L6q%C)r$Tej{fQ?p
z(j8vrg3qgMkuR-heumtR46ibAxBBKkRP`9pnBwitUblQ}mtcBh`oQ(~qtuV|a+#U>
z<7!3E)3w<7BeMmUzHknKE(U{z(J$Ts2R4`QPb)Yi?Cz69((f3Z1Yhrp0T?ysOhLT~
z&B7K}*S8jkx7A<xG5$m`|K3B_ds0cz@sWQfL?9VD1HrZD<BLLg>pvDvAP7;wgcI3=
zN&cA)|6xeqPs5Azs6~c8DSCTrQ#hA7`g*v!J{LbNX^?y)ta!sCeCc~$`BjLCZeMJe
z>`fg)?U*JzN^^m@x&6iwFd0(KL)KWIfD?HB`o6&Kn$exfB8ta~MLTu7^^OxtFGZLN
zpEf9dDV}V_^!V&-_e*q3vkr;bI6W+1Q6|Vu$1lVe?eUHuj<D8r#*c-Q9Y4)}dOxIb
zxQU)$hvN1pD}Czw{stzQf(b6U&aooeu=c0Tk0C;}s%n99^ZuD*VdEjrSk+bH@wi{-
zENiUY6hU18kL0xc7?N&Ly1Y7ZuL^wR-1bY(x?0I)r**n;_;-5p%-8#p{|3XIc#pmO
zR}d`{ql!Y09>e^NTc+50zjA54)vx_QDp5xI7D}y5_VxXgL2_h^YhSB3#^OyVP=e$O
zNb}YusAkumt@r#o&0({}x+jrH=fO(q_6}<GVN}s=uGnYpe)XH-s#+S+*TxW&5GKrb
zu$-xd<(uehU%VxW8j>UsM_&w0aJ>w!;5ulyX);_%T{RAhyL>hGq22*4p0;>qT)^|5
zq6ucaS+gtSzqCTtlOI9pXl5M<zj$jEcu_+rA`pAfUqUTaVrn%f=}X2C@}L86dN4J5
zq~Qk!(Q1<TrEcc)FV*et8n18LW6IB42jo4xvwpeNx1+y2#1@wAux$IebDKC+xE}r7
z&=oE55mU^R`f+~^eUl^*TNCQ`^HBGMG5ElOIYxwYd;LW4ZE_VKhT9P_@M<mVPiRkm
z_G2{3kr7%ckMy$3sNRli<)c{3_GWo=ol4D@*7lMSuU6fqB;$tngRVM%zWYe`v)00%
z^~-DQ>ps%CGZwA><u~SmpH5Tq*`6TNmZ|Oj56mM!Mp56jn(Y*hg#PM-QM-1Sz^P|M
z^Wdd<P|b|A#zlI61@ULm$W|L%@Cbg0Rsy~Vldh?uJW^hWhGxJ1{fEAWeD21%yvdJT
zxri2GHP{x!Ed{l5(umZM45}_mqaWVa?ubXR{wv&L<Pm1HqTwf;{M%f8j(Ouu%e){&
zeOzo{>fy4~C&tHz(PEm1OHR>$Zf;x?>#xr^%bO|~{eD)@#dm@}W#DM1pVkPKZc73G
z3_4M-3;p$cBhX(@wL4+f^hG6c*`#scvU}rvD-2NGSVD8F{eiaT$xe@`0JQ<NDv`XK
z*WF4%HH@*FI7$tpQpuZB-W5?^u6-9=w3fZS+~cEGrO`_lC(foPHSy@<ldg_;Qaqur
z+Bo%KZmT~M>yGGMBn_*;94^VTnL8ZY&fg%FE~}G*w@(cp`1;T-izDBnl3KFEKadxX
zoBZRIZZP=Wb3X`0$<wSRs;{dj!IA@>5UzY4<eFU|)(;AhunVXXDGg09Rhl-<zP(s5
zyO-}eL-#$U47_jdUDI;+lTty!T)XF;<mwGqN1=D?^GuM#N1^m}rxK?uTR~FXzw7Y1
zLlkM^D+VNenBHKDP#<G|M8Y#r)fbmuH-jL`VO9B#&HRT0NdI&bGlGP}LcwRoA|#dB
zWMQ(RqeE`4qa)O*m?w;m<UO3<_rF8EN6&7su9W+Mk9dgn)iBR*;wS%Z6+0LReeliH
zeJ(uxFEA5v=a_pU^H#OZ-nGFqV=aJ*hyXQ#Sh;W1)#B--?#$Q^`|vC~dVltdjAuQP
zFI7OWQh%r;e?0eV-2>U)THSrCPO|9)V)dP-p+etKFE5gL>B+T<F6pc^dhN=fP5-O;
zad^+Xy%hJ_hd0YlyVAk}s#qCC`|Zvo3Njod%Q}MjcJM2+*xP}~bNgB?!rRH=;NBPQ
zoe3&p9sTFk+lp{jN7>gwtg>^Z+u0)?h$(VXTN+r{T#Z&5#PqJIt<9h3$c|CG9uh}p
z6g7@F7;WML_v+^%s8=K6HO-c&RSK09sw$d!w&T~CN00~qfjWkN*G{j{Ur#}L3(Bg*
zTU+KH<*48P8iSPDtiT?5+@IKZw{(BoQN&`?@ItOQD|Hz0Z6;9a{X3Q16wEXVU;YLa
zl=jw0xcm7nzx@w>?pCv7SL$-*6#{*$uNf<nM<63!GtxG<ABe<TjWW3mn9zKmF|O8M
zrkMP58v|i}H&?*`@V8%O+)HhwEldXM0PT)vn$V9Y^$OYSRoD=szBIsHP0|0{I&ILr
zGT`_V@tMj+wxeF#?e8qK@)#gqw?sQYD|vhFH7aYouxLnv9<WCD_?6c(d%wBi(dZ84
zhV^5(RsFu*!9fE5hMR<se-CFwX%v7+wHFKa6d?0k3U(^jNuacl+uFqWTb-y{X>mP{
z)IWKfUDdXgB5x*5%#_`SA|L<z)+ySD8+oa`&{659G0K~s&&}AkufrX)NWVW@@t)1t
zzui{`C4Pp+7hA}h#@_3wbVkWw{~1U76&LD?kJNuLF}xuR^JE|ESXmGIE7a6;-2?4_
zF<?Rgi$*VZ<}<y8)<*;hCRy?e7ZN$FJ=ozcs7Q-rj9DGGwCvm;T<fbg0r&S!?SZ~N
zd#sK=okZ)4b-SlZp%u@Lhj)ZTxO&_kls)k9$YQMx);-o4%3-vWuoWLGQmk_|-hNjK
zll>$A&3f*$0ecNHyL{t_8h)cqyFKvWtLI=oYTe-q*=*tYikz0nz7DQH$204>WK(8E
z;!!dAxjQ?A(50p>{cx$Slf^;eVQ73R(zbU#IfMHV^~e-s{jByeeNojEYhA1|`x?ht
ztqC`u;{;@)OHe@^jPkMl5@%-LnP{N>gkztBJw?i8UnSAk_5WLh(?hnNVregQv<ybX
z@1;8Ec=0uz@^%!NRtKQBuTyR(g(#FVCjyEd>WNtPSOuhiV$<>WOO~{nEyBq?g=wu9
zboS2O*^)J@Y;#|Z0$_&gAL1A4%eHn>gZFKI-kR`E18e1y#{Z><|F@5-9iq=0k;g`e
zj5HMJG{1qt?S7I({7)o{lc}~XojK(e%<6@PBlf)^MQuz1VOJFU_avtl<JTHI$@IQ+
zf%ReR1nvxULK0}P%*F5%1;IRjHVnIMNx?)owYS;a*+5e=xzz?$&8IImiG<CTrS1A1
z5}!jPb-QK)UwC+P8QXWKH9QlyiP7QCVceK-6(%l42o%KpFMZYF=1j!Mqy?7HzPpX^
z;5=5jY$#g!!{(lrg9+ms<d-YHznURho}IX<Ff4)db8H$6Zz<eNl{n<Wv1RF3BE(R?
zkV77_bCRq|)m;<_-<X0(h?Z@V)m&qN@$)}(>4A0Jo#-}U-_+mbatPN0-7`#j+?|V3
zWR?*KhL3D<f##JE-vDyNztjS^@Mx;b5(?T%3?TMHh-usc9jN#rfGW@HiU*2-KpvI{
zNDXBR0tWfF5MCi=fgp9-Ye>nQ?e<J}x!64yV0-EY`vzecDIvXoQGr7}TY^cW`Jlv!
z_jKfnvhr^6;_CKiWqb(Tq86}9pOLD+hDO0O;r~<zgRFqnQe!6*3RqZx_F!mv1u`<L
zV|0HI+!z353)83F&^S`0nN)$~UZQsaEfZH}vab@b?Jhej@sl;Ax-poZCcM~5MuubA
zvH(n5QI<jS8JYw5++|6?t}6>l48Z8+O%P@wbQ7XMvNL!Tfa_Bv@e%MJE@#!V&~^lB
z$gvvx8pCenCCBPusRJ#PZVN!+Ck3PwtW`Jqfbv2h+&=m)!fHm5R6$dkFI^FRr2PzV
zKXl?C?Dc?b9burc76*tPSzTH2)Q?p_j62EGVTKNb(F}MEEhKP-1CA)lV2~H6ECM-a
zme>9uQ6vPA!SlnE1{nt*1LguUF(73VSL4wqEO3BC|1-9an*cEZd`Add7O3zqUayzs
zuWJQJ4;XNV0c&3J36U_e|GD4ym)~XH0$z7e#{@VIiy#)I;D?|M2}psFEQ>)~Ch!_l
zVL*;4Yq%LrGndCSNXqJ~_6i71EcAx53V@#`j345%7EPrug&u{8EB>z-$MC;ZK5uAA
zz)oSGEEb`S5XYvOzr>JYGh2bmMY$M(bV<NApr!|mnWYFgAEdLy9snYuC*dj}rjY|x
zU!_6TUZ8-g>N~*;_+NXgC8@B^$;>3O9EM<Z8Q?^tEcU?SpldBI*xbZJG!U*5ld=Lp
zPLvhO8`h-iO5i)JNsfaWsgp#rs`^m#S-dO<v45ROM$yWzwY&z3athgxMI&2^aS$3H
zk7Tznz{bJ>e;&XQg%kkUuY!dQH7}f+fncd@AydwfjTpp_*TQB(!I_FQfFzDjQyf8T
z_l-5GkT+ycT%$<V@UAQ4uhV^1cxV5<sv_edKYe1VuIpq3KE8_NZS*f}oc1J)pE@<{
zG5EB=aQlyaUa_Y3PTF0t>MtY8qO<%a#o@z2-dmQ73UMPX=Unrg2o4WA#9L^02m1a)
z8Z{RClv`uV5B&hablBd2R|>);wOKZ`rE^~H(<BguP3z=?d@aUs$^}4(6Yoo-M=Q2Y
zORyck9{Vn&wdwFm@n({|MSjLrLN@lbS@CPYNqoM2rjWuH73Sryy9bNRBJ)Fq@X60J
zO5GSW3%v35FiaTT*FjG~iIc?lHGY75p)3g5z!Fjyl)eBUyx~0pqCpz|iu*v~Z4)~e
z`{jdHk)Y^Y=g2OQ{ox>;Tg$n6<-EEuJm@4mMpt^vEfeKd<Zh<HG2%y};$&LM)#)4m
z^+@<cA>j6M2|n)W_eIE)^FL7ZX4lpwXqos~I14+*FCy?l@`7wfe%Lp;<#F*#&6pV0
z6B#oD->)J_N}BVp+P>W2xVYu6syUq5lLBc~U@U*LyMHz7r)HxA+H4bNEtn~ojml<1
zgOdh91%VYfsf#k0>@0!5(t6+~ike9puShc`jXnULdfZzB-k{A)Y2a;T0#4jCN)!Pk
zuS|{^WVDv4kisE%ilDUhRiq)^SC<JcgYol0scb5HSpgF^DF-0g*hwoApmj4)1P=BD
z=Xpu$yG)j|eU$<J9pqoUc!4iMJX#>SWDCJhiU)e1ilmCvypb)zTNqZD0B~*8du8ZS
za#?;hvJ=fv;ICAH>wWA$1h)c91OH(a8d{mQZh#Y2&hVb9E4!xcW4H{nZq~=b-40R%
z1UX4s(JJuxh=Jfs<vDtihJP}OS=)EEmjl8q>#t5DW4Luv!7<2K5+P$SU6hL^ymz2=
z3rUDMQXCweAT74gv^k^FJ?nLa6a%6Wo2<kJH?r-`)IQ*nd4s*D)y)K4*^2zH3_+0C
ztbfkPvTBxTF%r0*gA$9wLd+QiRBI<b`l+DkT<$)0xS$aXBZiZW*v!+#tfV0ZQ+Z-u
zN&-eNO(hwe2k=W|u(ybdL{#aQm{}2N>QOB0O_c>`KW+hO%)rXlvFFpD6;5Tc`%2HB
ziLo=6VB|qZoxiKbX4z9TO=0*>&Ic8L)|5}F66OU@)|$X2n0$q#n-)dz6Tr;o9d~1v
z2c?q12qYy+17G=zwAJF3buN{T`=`Il%WYSf$}xto?OwW4Lc{wn<&(T1ubTe_{OryH
ztpVqXg)~p}%~Nky*Bsw?pn-&QR+R8lpxbR<P=7vC#r<C5)MC%O=RT`!x~XTYDo>48
zJIfa4ep+hKr?=YTD!x>EwDlnpV<8{;=}O-{CB0cJrnYxBRZYJrTKg1Jt5q}Q&y3Fe
zP;<7r@DBX}`>W;64z|q4xWFZ5p>--=A71-}V>S8DVy^ksyPF|)F3GW=(R$>UO{brj
z#@NF<ICcT$Tl@+g*7C}r0m8)L1Y}6GuV1t9+bYN;YF|}WUc0pmHU3EkTV52&P1pZ3
zkV$}5?Wi!`3vs%*#l(F_l?1%4Rc^P7^0kR$YeHK^jBb(Cz4_(EAb4E-YPMra{3#X`
zT>T(|SXnqJ&8d^^9N$nj@E<5ZWZf<6Bl|Or2k@93!*9_`bde;rErjA}C1#~l8zuYE
zDd+T=!5c0FxsCt_^-7<*zzjw8+JR4M(74zXx#o<pRP~`HHf{A1zKi{hE)EUBA-btd
z?=~E9r}QqlKq+v-{!-~gX+vi7zR4zqPhAh`N}UIy*C}=%b2eu1nvjt*4!IY1U_XD{
zWq(x3fgH+C$SY$j=F-i}&Qmt4xQe*MBUYaXjd0A1Jj%a!yGJ9verl7wv8ti_?xmE}
zb<8;g;bQIKqkdNJ^0GB({?$ZuH7V{4`tIN3_LO}13(z4(i>*UKw%quQlott2NJ(bw
z+*Yo8679q`GLf&Lx_(Nh#YD8zif)wqQ?I)fT;A63H&yx~y}6~8lAygp8Ve43$X)%~
zUKB?B|Il@oVNL#z+a4W~3QBhk6iKBSD&5_PfH0adKtf7HWRC8hj3G5bS|p{Lk<yI=
z0g(>*KKJkc{&~US8xI-m-tBgMuIoIt=SwXY@4xqE^44l#G9Y<m`Nl$~bKs;(Zc3`S
z{+(v}uEp_m)SD{JcGmqxbMZ>6thyMB)CU0d!T0_*Kz+cIqmBEe(Ip2=g@e5k;EL19
zie1t0S$2{4;}uRHh|W?CxlT?h&oy<^%f~|~LG6umCcde0+R96e(yG2K*u@Y7QmO3T
zcw4mVgl#Yqm@5=gi(ab4p#%DCj&0(riaHb)VpLMjV=F{Ln1_e>^QNjd3Q~_QjfloK
z|Fow3Elu#3DeL=Tqz0!R{&dAMJI>-Vx$!_EC^>TIYNlaAhvo&4oe#e)?}hyg*u3@I
zDBJtPrf^4y?7C^=xDs<~D$u+)#^{=!Qg=76$bUV8H=&nALbSpb*2x7kTRozQ3qVy<
z6dYnyys^K|cO3NZZ%pVBl;4G>zkyW0P<l@(N|ZhJyxnu~=-%zAY11F<cSM%}h$C+o
z{8ofuEY+6joD_ZgV+!lY={&^;;vjNb2R5r^njV8098`{R?*XZ-)<{8D1}q^h{AhB-
zn_1zxM^Mshl}Rw5W1`zl5*3x&-<Z}vDe*&%IL4NI%T1l<Uktn?7p$@R@(79N){Wt<
zbRWOhJ!2$h{YhPo7cJoC)G{He_MGRR8ujxZmB?io{G&11*h&w+V>$`PDmIqo>b4Kp
zAg=fgcG{y*kupzSy*&NoiJRpQwO((9FpV91tTZN9rq6QMs>{s3n7Y*q^CYjxts(-d
zidoC0|2m7O%MLaO_g7ExLXr!c*}M&B3hV2dB_;Hpa4U-jVfo^<GwH3|&5&5ewb$&%
z(48a9?bJ*PkGAJ^_&jLV#;;oaE*x*zkh-R6M5E{~U?ux_e_-81-@85`xSi~yM-IWQ
zQD|W4V<!#11>q9I&i<0mb&YM1J+H5&2P7Ip_&4rgR%e}%>H0`^U-1hw`iV758eIPf
zUh`l65$%$VM9N|#L&Rc;cgDfdzNy^^Q!WxQCh2A%M&4z(oUVQSYfAFj%U|F~kDsD)
zVg5uvUA{0f1n<Zs-zS@*TE`ZbdkS%Og_5Hvb)7dE7u~XIvIY76D$6ZtzDhaJ=G-wN
zXPo6F4o29+-z{mg<7Y~jeo)@D87O@>H|1|KJ{Hh-i~e1hai|6$BFOj!Qm8KM%gBm_
zi`qDewkhFr&MnU|m15<Q`vxQSj&{IV^xEr*ya$_03Beft)c!C7lYcPVqXz%|?9V}7
zf9V_O!oR~2MIBq%ww1Gw>#S$uoy@D|7(544WBf?5-%t}t>)t)RTK&520NU13b*;lk
z8Lz*_&lPUgS=J!cU24oJ<!H6+uZuDD>0(IaoD>i5eaa14;KRCS+rB>crLfEcPfhMi
z@*)ZTZ89s=(BJFnU$NqiUW#s|L}XIkmJQ4*#yUz`Rc?X3!a)fKznJxo@;u)Nl1UqW
z?O{4CpG-b;DJd%<o#u&<vNxjRsMC=!ua^Top|p(AdJbM*D2mj4)q-m(c+i-F(QNWT
zW&if)bL7+cLiV}Ryw~79?zLi=U3;{cddi}hN66czvI^ub85!B<LQTryU*X>azd*G0
z9<ZetjJ}8dTzHM%*)q^qsvA0wg9CnqoqBDUuV*S)MrLo{0^aZBqd7KHtIA@i#?l>)
z&yBKtb5`_>IqclfmOZX*f#G?Cb(M5h+2g~HMA1y^*$xt`&Vi)Asasu#JKnYabDOTO
zxqcYq#gx1Hrpy=3#mqKcXmx*n#}!&|knP_|Ie0PFR2H@E5LnuHfE1xxFG(@A2+d-n
z(KUJ15PGqCR!%qg$)kK_CR0TgMLK_bu*0_2T>eIg-Ir|m`?P?wnL05Qn?wCQ_sB6r
z$b?~vpQxg{uz15Wf)3I~@ed1gN7;kPVi{h|%zGCGnY60?J4jr#&?1|2QQVuymBP<*
z(DJHcQoo(<b$*cLt#_Yq`}Kr&ZM`|?Df!PaUaa2}-&fVLX4}nfB9a!n72fl|#+NNF
zqsQsw5o`X;arHwbtPO1R*5<SDg{KDsugB~~a<jpFk9n!mWo64^JEfhqJ-;lwJsDA;
z_xU0#nBB@aeTL?-^nUH{!FGiB^t`3*gHbFGxt=e1Wz6&RCGUb@wMCz$W2+*Sl#tKi
z&M5a{8jJItY}~jgA%%U~A}>u|oawALNpGd`umHb-PY9>hNOQA84lf^Y?3+`=zi%R#
z#r-@H8zGXPbB+w$gqg8y6~4^fEU=1xZO)g*Hmg*+NZHS#BpD$L79ZHv6CNtz%H3qC
z#N2(}{u%qg2mD=6&(vZ&$@6s>qQfj#;%|UMarC*eASmF=J`2%ZZTI)PaS6uSgth$-
zE@y7$prepic$<F%3zBq{$K$4IZ-2<S^OSqnL<q^7+{OPHI##n#wlO~W1b-BfRKWj1
z&($eqFg)Y9;@>8(tb<tdqB!0RP3SxywS7~XA?fsP0C|2|ys*eKaEMpK+T5YeRKxkY
z35wDfthKuGaX2*#X6N%gqs-S6hE$x>FzhfhR(+|P`STFl|0=mYiD#edDHn(COZQrD
zH$){fty_IHbz7dG<KI=6cE&Ujl2;?zkNR@q$Pg16$!vSg?{X0%xI9)aFS+T5X<uUH
z{k}NFfg}dI{|IY7ej!{YdtR2f7;WPeCe7bHQ)}&MLa1W2<|Cl1VoMr$HL3eU_LSo^
z_p8u)RpIR~89<`QN}lD#PDZIJ5mF&&=i0wJXwF<Fv9Oqv_u+}DSG+o-&#aG>r>Nun
zo719e&BQIG12^Q1QOAmGzhaN3>pg7&`gS>fT`sA(A3dCz-#7A#zlC~s=d-K-21)mS
zrI3hGS~WK>;ZkBURTLwW{+Z!wGFsfn^dD$2Cjl!$l(Ha|c3LB=dH~meO)_v0-25u$
z{((5WWmJ-my(W}Q=;OpS(QLOQME?!%zFiG2n|<>5LI+pS9b&PkJyENnKO9y^Kl1i+
zCMc#y<6P4N*5swQH|zv&u1!fAklqbv*jTJiE;{Z!k&)h#2t8iG+a1taX>64I+m>oj
zSHRs3OO4@4%$<EjkU#Y$e`>idRDPUb+%VUGR25K5l8A=(2uK7QzM}>SDID1%ZjXOZ
z()v|O2hYBOY6k*X*_P!dSoxwfra2lje2=>Z`B%hBb1ekE1)_oVz>}U#cWquxU%Q_D
zsOdkeO72x({w7B{!1G}(URT%C?~xO0|7%56RVn($krshc8(uVFM3T*sIXxy+!JONQ
zzpvG{*1_}s)367q3hSVN2+k<0C#6ABUGjmSLJ-9{69h%C($^SyJzP+gdmRld>FLay
zunz~aH+zvyll9ht=V{QI-cXT-KQ^<4b2&NK&Op$WS*qi}<3Jb3kn+~#x|E^!r#-%Q
zTt}X}R_R|`K>5BRM(ff?<nFIG9DN}tMYkh$HEBHA{RvmD^DSO;9H9?lrL*$VH95C8
zYXT~Bo*j{ljNIHee{fC)Cy3DB(w&uV6~?W3;)d@l2fgzl!+Hiv>^*PEGNNZ{8eMDl
zv8tW7PES_kSt1Vj6`2)bSK;gC<^|%S^!K|Dn7)W89ev|2Ch@IsNY-)8r%CUR-uKuZ
z4#O|Q<9y+v2O?jOx=4U%@8xOxFy)3zzlW(loZKUrwzH9_$M~`S;>M+U>wh4|x7U9{
z&n^aH&I=X8Y5!EA+7TF*ZY!a}cU?fTN%;TyqA|A<;f$?o=3@rP#*)_RhT&2?^BNo1
zgKEOX^@O^iPA`%7qRck}M9at6oHG}`iTlepbH1ERvQHK;^Jp*W<N4+`(i$%w;@17P
z=Rz8znf55rP?dr1|MX>1heo(?c2FQ^uQrUPO`wmKN!iBb#(l83*GFW&?Fr<5h~?R7
zY^1W*k*gZh4q5hD_2|jO&WM!`LcBLTPiFESR(`n!UGs?wp6#>&)*n-#^!OpZUHbcu
zFGh)XL|qSg^P?VqD((Jkj?MU+5zSQnSFu;wLZh^9;0TW3iG;2QMJNgc<a8G}zrx5n
zv-Rv(IM|*#*A<{cP0fXC7r-@F0LSl|x|S9I3<M-?R(b$O6(o-#-uY9!{lDhYXb@0g
z8y*k7Hn`7O5d3WUWY9+du)gG{x<vK}Ku5{k-rS+2P^>Aik}SBb2LvV&Hn5o##b1Z&
zYY<?{if$EvZY)PsH(&jOjtB_-1ENR3*h<S2L39h#zBFQy)BzO$I#JXYBF#O(k-{X?
zD}?@oB1EoE0ANl~=9LjZ;5^y~+?!2gc2mG~wFg9&w8BuA#SR7lmwI*ZeCR5Wg@JMn
zN5ujQkwBP$5ePO^4+aU{`n8>KkOe~o1!q!EQ71szj~y&C!nq^mkV*20pS=a>Bg53h
zzyzllsR((T;}K?WCWUz)LP^HJ(N;&G7S>cupi;CQ1$6t6Ax4f2A-JnIDB^X5VvRcR
zxB~F1?4eMgmZ_qh?@ECI(hcPdtbh<ZSRE+)$)2Dw+?ag`2`LhoX3J$OvnaLd0s)<*
zmM$@F0}HSkv&n+V2ha>4BNwSwp$)*h452u|a0bK|SW)zdQ9hr^5I}Ak5Fm}NCgFWr
zcCD911Sde;+$skHJUY%PfZ35`Oo}59Uzk@g8gY*Yx$0L0gm(FLpor~^b}4^gtxn1i
zg8_;OV1;omMWMa;se-{&e-tr$$hh(VT9%;|;0)Gt0h>-a$@nQsQf7guPRu|rScuLL
zAS(5cMmzxWmp(UrEYS_n1T{LwrA#8^fLt&S1iUxSq|jbYNl}yC*8nWaBkUtYRLAP!
zN9fZc;8)LPbZtbV%W(p7jt3B=iX|JZgb#qMO(5fP0w}ZXFaSQ8)k(VV=X=>&GQf4B
z2(ZsCjNw|!qX7DH`JJoWKj<0olX0B5OlCjt5!6ei0(=TGKzs|dMpYjNdr>G*3f-Y0
z6U2bFb0z`PCW`E?xCZpr#Bcpmg#V#-|5?$VMz8@<^9jnYcsuIC(1(4pm7jQZ(pSF~
z@EVN}Pr@~mG#<)Jy+57@(k%f^AXZ1{;JgS^WY19#<&~q^fhs75cmftrCJ?2=4px0|
zhhPtf+)m-tbCn1z+^GJ2jSGb;y3&NzRo;If(?g7N$xZ4JkUhh|<^p_!CvNa9U*(PN
z-Kv6=6~VN@kRY@VmjU4pPr{zsA?B$}5n!mHbY(Mgj!=C-pzj9S(-mZ+v|R=s`+uOd
zKF+wuIP|ij&`OVdbgasHhH~CBj?`u;8#DgV!0n6xH?|Zlg1#9b9ewi_=bT9<^&M%z
z{d1$9wO!a#NcNn8BzlB-3?mR&G#X6f3i^#ZQ^dbNMN8Q@#%`x5x>BH(>MDskd9!ho
zFYiU45+7OSdg0Aaw!7Ouh!ouWlZ{)%k6l%(s^s2FF{&D&<w&Dh{_$6Oi~Tw0w%X~w
zP50$Jna*8(>1hw5Dh0nvfX~SDYjeAmjjv92x3CSaUd1rcL%iOiL!y9tbBg}FuSWa7
z+&6zct}h>$HmP*rHT2}i30EEB|6QPOwi62mKSg{=z!G7ld;<Z%K!IH<8Y9@q8OMB6
z0@}l6C`~P1BWyM*|L5jqK1H7t5oLp53NX!-Y)QNd9=LymO!Na+pS}#r-hWRc;DHP<
zme0hiA59X31_DVx!5Ef{+3Wq01_^tqVhIsO(A!RkAjD`V9{tM|EyG4>5LyBNSyN<t
zh|l-cXhKWwP$~;cW_ufJ=@K#|!Zm^vsfkegr$vXqTtUqpC#Y9G&`}`;zhbd}&>N^i
zh!KYj>iIV~WDl2e%m7%CIA3YWo)+~|69EJJ7>2CNIA+WuV7&s$o|5ws@OglUfjpYU
zYpxWNkVQgBh(pGq8_H`CQe`Xh0l-szI)JiQ<_H1qUlE}&6=tB03|yItFbz%K?3Zs1
z2mlDj|H{`u7Rmbug$$(@YzMfy;gqDnKSQPmmWzj}?A*8#OxD-1D_f<DG-GL|>LenR
zvdYa2`HZNVxad185z8SCC<lpuOl)lCqxq4;Bfc5sQABE+zVFTa(qH(Rli^yL^SdAn
z<cOr%`d4oEk5EhZDNiY7JHEhj&wnn)8#th$@*WB^$u`dxQwr=|*VbP55k_Wi6D4Fi
zr2JkLb$9>$r@u+({sG*ewNi$ts#VNcCDK}f6Bya&qoq-2Ut^Wl7WA#1UmfBRpx!6;
zq2NEAn<Kd{30l)n685f)?S4)Np{S1Uc=5q6OwxA;w~JnJc?j*y<Pt|#FTsr_s4VY8
z78>%}>KP~eRh<S-Ps?f8!@QbLOX=^gPrVbnElm4>6lhL;I^3NQoakm$NvZ*m0kI5h
z;;#-3S~L0fc}WX|AErNY(}=YF4PQ~1NvryFxWBSF_1g4=uzDnEp@XR;dp!PWn29g<
z;^FUGez$5m>X}pag(&N@@cUIJ1P`IN6)%Y{%@aPEEhYMdMw2de4vhURISX@aK1^S^
zU$Mz$vmm$gxuX+n(Z=;_R->PZxBAzj`N*x`Q5BiOIV0EiJO;3VS}?)Y#Nar4<0olw
zl|NcKaoDAl?WCfq>Tq^DaP#%~deNVK{CE3gw6~oY3>iG@NrHrYV7vA#^@To!O)M_8
zjq~s)IEaaS`_uTry9yLiK|Ur_ej`mX@|8Su;}2t=>qhw!<r?-psPu+=AzKU6=h*h`
zkAlQ!R$-(aUH))WL%u!s2hsQ~quSW|_9lmaO5-;=_ke|Uy98Md-|yl35{bgiNl#=g
z74DT-*D|@tP)}rJr#v4&717lc2ugoy9DUBIb%;885*yfp+ve^IV03<2ZPRVZr*k$B
z(;?P8Oy~OIPQSvy{tOZxL<5_R7m1ve#+vI)4O$Ia(RWfOlbFWz1y{VF*q`o|``=lG
z2d$>{p4YFz@TGDQxF^@T0mX0ku}5v(9UY;C3$DLZK;c&Hv~f~k3(~>-O&Vo6Q8Kqb
z6=g848)}nK(Pxwu5ml|PRm$;_35zz71qYK`)7%XS!AmtauF=s=6P3MI(l5Vg)fOv`
zlzC)JUIbKzg>!^v4W=$j4uIIg>ZKdItts?oV<WG^qq*mP-}mXtf{BUK_xPp+ZZ9bF
zfu^4v_0;aX<#HSkkEVzLha1(oms_F@o<4<JvgqYK%0Cig9;?!ts+p}T|JPJ7=qy99
zz${%Zka|v$S@irco5W!>K|+eaxZW))duLy2Z|KoTqtDqo_S3-R;R_gq#h0yj<+)ub
z7QZu^y~@S^?P&hnm+7P^ZlfZ90iZK`eD3*n6Fx#HLw>T;QZO9lcQ<|`%I@=8i5<J5
z;ZiKy+dk=GtDn;8Z`xM%)PfPae)6fWh1dbZpQN`pBgs%EcMynEXvBg{0rBpH$W<T&
zX}}v_&}Y~wuK9Z|l*D@S`^&;zB+oK$;!({kY4b?%bm98}ipAmEtg9&&yZEpA)ZGZ8
zawoWk3%a4eQ;w*{Cuq}D_N}~&$bIp@YBDlddHw}=ro)B``h3@q+b_E&XdIF?jwWef
zmnPIjd-n&!#)9?8j^O{?ycz9Y&VNiFw12;oENK&Ylwa@28#KVM!MuSqAk*<z^c{IO
z=9S|3*;E17xqh*gsp9`-gsr6^m%6L!BHa3uO)bqm_y0h5uQ;{RL&(z)hskpi-oiC&
z3Jr!N$PyylqNn#34o#W4{IEQPj`ga1VDT;AP?$ykG@I$7ps8r3<xAywclRHA)bB}W
zY$W61h}v)$hCrZG$xQaS<Y9$wcfLJv#+V#ej38qcF=&mhJ?Wb6j(rxb*i-~HZ7uyc
zBKNG8I$j-@eWlZ?LR$Ad-7Zc$*5pj&6h-5;-Lppa){^k+W__Kg3Cc_nX8Qyk#$zLH
z`lv&o`KPDd`l_6)0qrpG7PLw<J-!)XZV<|n&i>>dQ;@lQ`*JwmR_A_zueE@Q%WNyJ
zt53nV?qKH#*=BRoNZ+y6U{8kW>79>h=_7MAtL8d>c-UW{?^GB9PHHw7!mGa9eqps#
zF2EvayuwrQXg{y(H6JKsa(l9IEB~hkdjO)hd2*Hb)sufRDC)EivgSg+!dV=DzS8z2
zt-;nEx12wq<pc;DaaJ#;xmk_i07nK2^z5L66jQ%D87F(&o9(E5!9jlKq_VG!mJ90y
znr0sEt8{(ah(sFGPpEj*l5S*I&fs4B4yMIAS_h`zE)t05;=&u!P;ElBIfNQcp#MOV
z65x;14FL-ydi#IR%br{nXLoq!iXI-)3GXp&>JA9YoJkQd_(q#ipX);YzEG#Wm@X+a
zw^KDK(0}pphd^d5R<_)z(y=VP;4$YYw%@0Yz)p3frVJtW>7QHBP9Q4aP7?vH<k8gt
z%NF^K5Ru#B)&quGC&ze6L(7yc<aDf_i4m*NOWJg$;^ub7zHQgL$hW;pBE@ane2S43
zd1eb^k%{Neqjcz3-wYc4PS^dS0CaXPKVOHK#W#B#*?4)-StI?~-Ie&{HTDn#dE~Zs
z2FoUSGJVo|wE57#6h=YiGz!;d2?-fVCaazaW0cg~c?MZ(_W;-QlXXMIANxD(usxIF
zW&w$yva?wpG0nb8AtH1w#hFhG^ULh7hiQEIrgmtonlyEJ8rwBX`L^W9_epv^jhhBC
zfh1N~uiMffTU75%nKhwil9~2n%vgE}?WD9Pyd^&-ySv4K$F6zIZ7%YAzu`X<xLy~l
z0FmeIsT)bRc%m3=zBccUm{N=^R$Smwp<vCS(GcV(?E<lX#X`SEs)h_!B!iGKrCKUu
zoV4M=owy>ZNG;&w714)2d0lI9PlKSc*uip|=}^wm1TUaE;2;U#T%!K5<!$w=BHodh
zv&BMERFkZveBO450-}({+zaS25WkvofD8LGLp&?nJ&Q@Q_jE&%D}>*2EN=Rr!D2~O
z$|e_jgfm~;h;8ibTd1k|<M-eNU!%r6QHj`&*TptgOVIOvGu!btHTjv%XRO+9mR06`
zshvjnM=|m*n3d;7JSpbZ-FkIzhP~3J7t(f=>iV~nQV$g3W9Ey$H-rQ==!gLoJ-*K-
z$OI2u3SX&YZR1NXH;oTlT>ixa#|`RXuKhh0gtV)|AhooPg$U{w&-<GV_j~NbDk9i_
zD61HwpCx)M#qhRU$yP{G$(Q?YSE!1V$MqHmN(}!(OPgNWv&OsCIY?#ozsx9bG?4zf
z{6ZVVHmUHt#BjEmVatULTw>)$Y*=xI^H?^O2f1yvl=l<0Z5(RNRLOZMhPrZpHNC#c
zU!Gc=B)q}(mJyY_##=gT2k~8+2<=<Zm&tuqVhWiuw)}|{Q(aUfdExTf9-QW!vi13U
zzXhq;)$|-AeVfX1#pt$0K(15p#4zdG*BB2*!8zkE)k%dCG*8Z?6~8aPc>h&MF-{Zq
z_HXH>4|yL$^Y4x>XZi*v`|HW|EY>Y)KKkx+c^Be?19{V*b={5c`)iu*`bw}~9~?CW
z*!G!7Go6HGnM+yan~C2r5+~p1sn;NuNS?ZpW%DbPCZ62%kuhN^mQdiBR(LG<%-S2H
zOJp5wd$BZ=Cu{pNA+5w-ld8=Iv3ToW1Fv`<<W<9@c6tzEF5AxNJatGSK7coNC$Hff
z9;i8r!kazBcG%;OC1Dpc3ZH}rO_R#@(bCOSU&Rh}Kkj<pJc5xVED-D$oQI_a`&f6m
zJkAxk!_oVdvwL>dOxe*DB#4|@`8gQ)BJO&?NaeipH)}$jnSeE$BxmMH(b$^a+p80X
zvEZwc-@cSVBTPkjEm@f|IyB;U7>j0O_i)xNO+gy0c`wpdKSDs`yH3tW)A>HZS;UXK
zRhk+4@D*h(ihZ4Xyk!li_&xO;I<|iFQB_{8+<}iW&>tFB!yi8iy#BN4+#0^FJ4O3N
zxG1T{jEpS%=u9wZ%<9}n`&^x0|DzXNmx1H^ZE8#ku7&);U(6Us-TVJh073rynpczG
z5Z;CwL<)v0K#2(e<Mm0;;Ze#l?BPETZD7oH)B!9aq~n-T@u-{f1m-_1lZ#u9o>*Lk
zQs2CJ)N)xrO2Y>Lkr9r5A*dGF7N={GqlOwh9cnB5Mtz68Q!xA8V$j?4k(VF--tBbK
znWe7izCS}h%FwSqGB+E#7Du|=EB!6r4EAqyx>MUHx>trh+7lnf^~B7XeK@cy$;vn&
z82R(a3?rDI_~X9e?PbND{8n_p17)qxN@%#0$6qZ{IimUI%k5;#;g1XPurbD>`Z-#|
zKVu)0<r^Zrhd4e5R{lIlKO<m^P4((FCt8~`>RJ{_A*wX-G9DGt?q24%RT^=s^KrT!
zlru{VutJU<JxQ!?<BnSff}wp&E6;|iFC+Kr>`Vs313KWw_!T<UrA6_j`Dl-S>u_7W
z#tM<2pX>fEjV-B3<rWSq5~+QEI&UK>{%?CxnSD=N!Tb|m>FJc8Ekq@d4zd|Kkti~Q
z^_SOPaLNZKmQ($857d=1dc7-L{k=|6)Zsr+TaVyEMNL8d^Mvyriy@P!Dqw!lmi>h~
zgj^|SS8(<u^V`ZZJ;?}PXcGtj(OrRr?sLmNz`1bNQAxA2>2Wpdcy!04aq7GN!-f@~
z__lVf^#kjzf8bUfqni1*{5dXhpEqL67*AdvQC@0y$yIz)j;%P@U~Q<OdVf~+`QeR|
z==<<rcd3{3)--T}rmCvm5{r<pCA>brLQI-a)kV&f(FqU<=tFcl!KpOE<a0JrJ5$p>
zBPfyhjkZI(pT>%cYSqVmuLIn&RHD4!LvfqBeJKB%dtO5vp!KZRr9Um)=!bZ#4Z@@0
z8nmi~wfp{Yawm}_i#j7W^37N(W1wV40{Xu!5*W7s?@#*+1hZgz4-cIASh6WpMB}*>
zta1-MSv+CjHnR=)tVeupQ&UQN%U<$1Mh34#12<_7tY@Wb<nVgUY&_+{^9_dk>dz{3
zz!z`nXxraW+Slq9|1Qb*!l2GjmH7X>LEO7wS87m@cdt84Ak9@^aV-ltw7z9rH3m`i
zgz_GFvESZ17Sm6^+-PJxe!o}$6NbFk6MXUXy7og=?_hbS($qoSxZZA9xZDYMO%&aB
ztSoX|SA?o}MXQD<7Gr!&N#4UH<F>QwKK@PKxVA@J&bZvkVH^!uYS_Uat+eD$(0dS4
zXkjGKy#&~B30S5x6bp#VN)8Z1k1<3@_AsNd{2(x16M~2A>AX^R1N<M`i4@tAd)kK@
zLQKHGdHWqLFs_DxHUO=U5V}3QH#2%H7%aXkv<F0*_q6lDKn%$=!gK{-?4>~Ts(>+F
z?rNMH1}RJi%1j}KE0L-|i1r1;FRBNY8PkJ;&<ylyvc({<8d%;B4M>{x09W%7x&%dp
zurcgg(~NJQiJ<up6wQE+)WiedB3pkHXbBZZ5DN9NgJJ)Hb^#XOo8M5t3H{Gi2-N3@
zFcRt!B=*}*1l@q)2#HYOn_xhIEE)%xAJCtR2@P?8lVb<)(hx?@WMBlK)dWmv!1BXe
zU<DD}(w+ij+2L~bWLV}6EGZHO0qR+9Kosg53TS}(3o~S;a-GJx;rUbkMI&tEfVs#A
zNKbgPpVNdG78t6z%Ef~tTA@Xwl6&fSh=tvf(2i8D0hF!@&1S@L;)ilL$|l&KNu1~f
z%BVLbBLYF_IRr8LmEkM`ga$~Kr$uN!+&IB<f|g#YBZBmCSZYBYJ9KY8;z7HX&h@xb
zssTZ~5V`@n9YFxW|8ot#!uj=p*uObP1Rknv2qXZ%rhm}BU=q$~;5v>3<ldZCz!Ww`
z;RHppD^x^Q41;V(P+HOA5@~}$R+5@XO4$*DSDL`aT~;dZ7hoF~NDY+*oY;qus4rM{
zyvmrBUY-yWAO~mgLJ?*lwB(N=chsP~*$^K&Ah^p`EG6SO2|zg<tHCr>nYI(}026Pa
zy#y`s9{G<}D!9aPYS3d0*NxDqq`DNy5NJp?qljjZ<1}D`8^C)VrBbvj=ZC^EHTTVA
z@XBoG<cEw~XM^7CXlCmbrYLKHV0Z|x)M9?CQeE=^1E~1~EmM4?A_F9mGMqEW>&ajP
zeJ?11W{&_IubHA2E=MZAoS2Jq$^PGi%$A?@4S%d9xzfs2{Tt_;QqNqt`WT12@+%rE
zDU6`S0xZYks6AXN&=Vz4BM|`5i`NDkC#Z*_P<E(dtp=?k5JifLcP9XFSfc<GA(__m
z>VlbEQrEgS{lH%eB2B5@*OJ-SM1TMV)rg=mL{aDtC6L~SQxc#+xdt@K|4ba2PSBiI
z&uO4UKrRg^nIHoHyH@8I9G5fS_d<KYkTc9YOs^Bxw1ZI)4Q4ZFW{*}dX6%gys=6|M
z+sKeGlWsvPp)slGZ#z*C3!5W#srN^^g0g*9Npo+SQTcG-N!`G3qsS(%rtH`A^1(D+
zr<lW;Y&|&~=c^Hrg8w@9=UoAtH|wRQImWT(Z1&qVRTbJFkiTCsH?Yf=So-`>#%Q`1
z@cvr{TjZ|pNN+UwCpJ7w8HFu3=N#q4EgnxwPt#H0`&!}O2BWiN?o7d!TYQpddZi6B
z0|$x}D8-{x@P~E?*$$8^`Np1hS3+2wQ~nQ*I-7@Fs2#S6c(Ax?w~W6co*Xl9Bg8B4
zDf&Gdr<RfUd<t<WSfg+i6oR1U8m0Zq-~yP)yU%V@ji_#=;3p^|ft1N?it`@kfz_Qo
z9Wt8Ktc}tU(Af!EDGzvWfR*vTtsCB{=Nyduv<TBq(twSC{{gVe_|*5X$@%y%7&3M|
zNfgumrGaF}o`yPUDhvR#R{LStV9SYrWNw6h1+$oghye3AT__#~9QSap>5$w&N5!uu
z;@{(FT0v6pA2CF1hGn9eQA7-WeZh({!0RZ%yElRX1pg&;Qq&9kC&b2LF9h&Q64kZz
z#}IZ)1OT&^TTl`FBOCNg6Lp5JGE@P|)Q-zQcYHvR`hP8D$-d{>1zm{=S}(gI2s%!I
z`Y788W{jx^M0~WTCKk-{jI5psIQn5~;>-0fj66YK01SkyiB1Mb(s*CsbcWc;AW$l+
zQ!xm`0Lnc_MFBTEG%{QKVxyiL@pIs`h=}OmmNY{A5I{uC9YZ*xsxI`6CySh8M<;(a
z0iZd)1jE>m!aGYayRG%PjG>M@Q4yMzBEM_Eohp~+!|>WkjkOtD2wRY^eZWS+Oy$o`
zfARSVS+aDlS(|j&;BL+XvUlW_L%M$!X`PEoj6w)>bpjMJe;v`MM?~!zXcm2zF%`ty
z4Jk)|cH;I0-WWZ8ud<8gD6Gn)<&}HB<KwbZQ!Jf^JGrT`LkmW26JLk>IbO~PV9=UQ
z6{F<ra?@anT(EZ9Eh%4!5k)cCP8=YWMf~CrZ(()4-#-|pvA8kroF#B~#qnLdWUsEq
zWLG~yzaU~EMI)(6tRH?m>Q?@%Q*+pZ_WD^`pF@6*t2Zn_VO2xHEWHtJZPlIJ_2ep1
z!ZkhE=N;aXh9)EzF*!>VniR5wEB{QjWwlg<jQGBRRUs)#%D=$wD>9yoJoch~w4Dct
zivIkVY~_oTWLWT4h}Tt{3Cjyh3$r-%%zT*sQ?UM-=)1rD5d2B8q0YR_7-!nEKa8Bd
z^(2Fi38To~e}AAvY+d>uMojYX1dKb=bIw$RYn}JOU014pG11^-!}^Bs4|T5_6P1TJ
z?M?~_6;)0OI|QO{<AU44KkYKyCcZmPvc^_Dy+2%GO(fVPgT13`bg=Z|Ed%pTbH&b`
zG<aQmzRdm*S$`FH`i=J6(L9OZS(T8oMSZ5O$j0VFi?7_&O~`9pw7eHvuS0C%!@(YF
z*?uhcK653Xzu#icSF)GApDheyzy)?9m_KppdtW>ChiPC_4s~De<h_jX%bZOtQ}P0M
z2DU8tXA;ahS*KL$3`49g2#BL${kQdR7M|xXijZdZ@CR~`EU}^7Hwx20{B@5im5DuY
zy(PScP=<(Ox}Z!e+w*-R6~$ch!c;af%=f~cOkR&vZickn#nmZ1aIpKzzdYkV5Z(Ag
z1kW6UuRd`Y<M#a6$JbNaz7-nYZj>6h=2?0oY#W4(h|QF@%I!`^vxi@&?0WOD$jN}r
zft!1f#9}hoqE=_uT%vJIax;X=q<TfCQk<6)YeM<eF+SKi4ZHcgSw$)fx*TKDY>IE9
z=|fD`Poc74;8%Ny?fv4+7oUg3M_!tJFx`CBw<_#qi6d#q^i*3^q`-Pg+D=P}DSRrB
z0MPFbH!o{Wq<4z9H7u*UAJ>}9WPktD@7t61?E?lTm35Hq5_=#mG+k(s)e>dpVwx#-
z{D^F=CorwDp1&?ux~__OG|afOGFl-htb{h5ug~U*+Z6Kk9gc#37#HsDL<S{{>x*wD
zKMo`Gs~C6aZl3+1t+R5RA{lv^(3`E$9aLI#bpxERSL((OdfpwxhiO(zCaN$RaZ<OY
zE?^I|sZu_8oyK~uvvXL6X-8BB+auQ-xZB@p{7?-COuem;IHncDMou}e9wqB6fsa+`
z9aCV1i{UrIL-^dOPw)V_!l%{6_a$6#%Np?)bB}GVr=>pq_Fx3w?nK&3EDzF-c&Jyp
zvYbss9&>e`TY<tdf*8)qo>F)CjX<3ov9Eij2H5tybwWvnyE>V!lW*lqh$QVk_RBn*
zV_t6pd)(QLkh&}JALyPVL3nSg3iju%XJ>1VifGmjRVwo-ifV<*ivR1kGU50Rv)2B9
z>t=rUXJ?+O-qZ)Sf@I5m7o{c%wj|<Pg)O>ZNHdPs(nZ(wcTkg*Ifq7P;$9J=ZtWcI
zP8rg#4VcAa?J<sBT2X-*=m4eU_^oOCS~zD{GP$=zOU!cLY2_Q6N#16p1`k0?(p1Q_
zH|?*r%9$r58N7UNq<z2G8#Nz_jWJG%Jbct_;eT2v-gInI=lAz_*9NQFqH`S&+Z2^C
zr)<f}byGQ?bNN7bDmnJidwA(`vveBFojvEK`7&PI@FJ(D9L1&oaI1;UoC>&ssSYnX
zMjgMM1OAsnPyF`GBE8vS#n?a@;+rY}OkDDiX}uw9wD-Zx_b<hA2I2}CL{YkTgcRW?
z<@8{%Mn@k6vF#1kJ0)9S9N9fQD}3>gF0zlgGF>BV90Q+iswl_O+Y7u_Y=ttbt4#g?
zKXp0J?``1JK_(>Y1hahhsvM<yj`38Xe?8Ezlv+V*K1cP2nTvkU>Z=;dBJ9ef_64!!
zNfBF5ybwJxU18~9RQ_C<v1Kogy}zlv^9;;rXX$8qIjYP8O1LKN+GXFn-`6J}_HxVe
z?*(i>Ee^X_^Whd0_|M&UQ0K`g>ZJUus99#b)x4tf6m^OhD0J5A)ZT5rLgpBYhAlU8
z6TQ(3b<L1mAgFDxF4tO@Kp#ohdB$RG$v1y9V}(w&<xAeYxa2rhv*f+y8$^5#5A`Mv
zQuWC1Do>?(C(9Lh)Ee~L?fZ-{`utf_)&54)r6Y)AhqOXv-5tXkkZyPbkdVyS<F}_R
z8Aw;BMrpCWXJLZoI${+0ZLbz?_DrSy@`wa^=RXm+9SDjGkoqjA5%slf?Iks4Lyt%j
zF9nZzl=msCzgp`pB-@kOu;{4AUDWFRtva~(ieJ`vrL<D(Aw|%Q`(zu}{Ktdjqo)$z
zQbXHEzvBX@MW3QN98)Yc+3A8ACs@GFHd_{(ri5FzZLPvL*an@H+4<5zC5J&bEk-7B
zqFG$|Hz}_nWH7ycY&^A&xTO6l`!R&BTQc{AVY^oblSBo*arj7(l7P#M^$Pf8qNuo=
zYF`W9rH0z}#7X7)DI}SkR99kNMk4>fO=3lCN(T-Rlarg&t{lKLg0(4&Jyw<~@XBbe
zt^drWow<z2V^z%>kqnmf%A=jB70ArY(r0E=tlJnc<qHK%Bvn;wI;iZlGweYG>!6o-
zgmwVw&loGO{9BvR?=-^9s*J46<1X>r6;?8<zz#yY=T1-yyBge3Z9x>&tLFMqn)q+!
zSIPPqh_J{TF<aihz^lP*Wwg#&uLO>_6nuQQO_sqc%JFM;i|}qvb<DPL!Z)|u&u-^Q
zvFjkc?`%N#$amhhGk;>Lak#w%`|ru+!a0@iZu1plE4lWGdlvI!Ua-HtRzX^i!7^9q
zQE3N0pW55aY*j2<eD(w5CobE$&3m{~H=n6!<j_z|OXy#=HW_K1Ql?vf-|gul7jfE5
ze-#rAe|b*s7()a)uiICgy`6=xiN0E14Jfe{eP*x+R);Ebm!qs~R|ee4cH*$w=rJy1
zogLw!K3o!ZrOs)mRWDsXGMA;ih<Ij%FClK_&810(@OzhceGS6IwDb;Ns)CUZ(*FDu
zoI#hwpv!9dM=a`_USv9vo{X5K<6g&Q?u-0(P3lFb^BI4Ix~O5afFlf@M<%N6C(@r7
zCnbVHg5Q)nwgzTU`HDOsC5a`qI6|5}eZ3TEe5duO#;x*4(3lke;&auppDSE6!Ba*r
zHE{R7uNQ~->_z2GtN%V=b;a*l@kOLAWyp-JnW35<=CJ*7BY7ufm||3<8bdb!A#uQ_
z;x5I#Q!Hz!{y8hNui~Ci%qQ;74P5D%pEe^o<dmVcK<rNV@b9M}R$Q$H`C{(W?t$ju
zYN#-&+QaZXzdn0Twz#GURn6mk3lp~{_Gq12wpZT_B%US`Ax#noDF_C(vl%UN$4%@v
z7&1St15PVhraeun;`{QleF{@_{lHQrU${dTEq$NvXXVhnCb-VMn(K(o>7bnRFZset
zh1~Y6O?$fKT%z;y+F(nC@g~Kl%9(!gKivqXbW^v@S#dR!S;NoG-qig?J0RptrofUD
z*aL=qQUjcv&=)ZSJ(3t7njm1w6<nZoE%X~!1MAbrrL>ZS7)2kN5v1rN%wvHc*Q+?E
z?g(-{$2`C;6dYOeABaM!`UiD5PgUWRcjYep=~(cty#29dRxiBMu6Z9KY=PXtTVBfq
z5C&Db<Q6<p^EiFz>((s0xwHI^{2W!aW0uxHm*)yr3)*0?zXH0D9a>}pxhDHd3o|*n
zFb$&QU?Vuv?~DCiS_9|;gu3tT1mb_6b4q}+!mRn)xV3tg<^VI}KvW9uTl<}Acjms(
zKIx%Px6ByDQD>XWzeN8wOc%vu@y1K?szJ(kBIf$boV}muxG)|E#*L<0Hzrxf%Jz6#
zJxM=`4xD^b$}IhX%b;C^BXn0P!6|E0@!0My+ULpPqYY#NFKg(CvDhecKm-%#AUb|O
zl3knTwD2lbfX`l>dslv{1;v+jGpF{4z|g?j=A+Z1p{3k<=IpN<xgEU8mXq%@zY}Sb
zgO2@^0{S7J;<=v8)X@Fup^F%!q^ew5{s(->^O1+feXm|`cli7hxxc+u$@IM-@Yq^_
zuurZor-5$u9gQq@&ppelTg%HSb}pJMOt#YPsfny0P=fyTU75`)x(glsntBnS5lrVt
z$?dgLhCbE1_TQS<Yf;-kbY++Ynea(!d~6llVVqoCfTVN0!0jVxBAY5H|Mr@GbE)%(
z%91^r#G6bH%H=6rQ!r^qHRXzGD$J@dE({WAoAO?FpH)4ri<^0w#a!JAw`EWG=v<dD
z6!?|QV3Ez_xXwyWRvP-s^PS94ysR{<+Z)NAtsb_p@8+yQzS1HYeyo-`@&+l{d*77{
zmpY+1-6y|KY)sXRynS?z|Ji2l!YK&uh8}tZn>j7XVyo^7W>hFE%JewsiG5jaG3)h)
z&08#$ThkQCY?^<w#JiqZWa{(ep>FC|uR@qkwbk&kCg$U2cg3sUKb5tUK^4i#hkTrM
z*nRp+UuIFctKckP$A4=w^tH6Wt`+Gsk9F_w$KvN{?Y-H4*A8LOA;(0^fpT`*dS=B-
z6uBz42~SD1r$?_QS2&5MRk|#a==n}x=dx)SpX>MKxzcA3n5&NlJ8#Ce)k7zwtlA;2
zZc>-#soK(&5tzJ<7Yef8d-^OKp_~~W=We;O@UpLM8S-QNkNTR0`AjkovJ_bANRcP;
zCv}ws?5YR5Mz*Umn34mCQqcdt250inh@~_{q!4j}7S4eAK|8x!d}Yy3uqjpNENJ>8
z`tE{YriRRwfka!eorrm&ePp~cOAGz5R`^fGoN)Uw=RLL@6)Y1emrCxMDp5GaBL+i2
zd@k*z#wSwBTSA%#A>sAIpiWRU`s-30Z{8iY|FoSxrk-Cnm)UHtD*tXtHvd+nqz_rZ
zUvp_b_-5tk?;IOJLTQyY;lIh`Z|BJ0Tdifrxqh6+h8%o*M$WBTE>iCWGRnlptf=pF
zU^T%Ub-AQpnto&>Pp`}+7pEWa${J>eDVE8M4H><2H+ju<18gYmB91P{)umrVVq~w3
z3;+qxhUz0Ol!}@V>Il-^3&o6ZodE`KLm;H#q7+xxl9B4ruhhpO9U0mOqww<)_bLIk
zcYxAMEijc{D?pTcY^C3o3D}DXl=a;pGXHBqx(VF?4k5y(Fux|i7{oCJ3PAH2UQEo+
zL=Zvn>N^1Cku#0hAeaTv@Tf_^RE2;b!s#3hpf5oq%!mKLAx6ecr1I<WK-n>@4%Ck2
zX9uX4peyGL=Kt~a)b(#$xhN$O$}F<yQXPsR27wHY1y-_viD*PXUF+ox(g&!S-BZ_+
zO9&S4g@Tv>`wcq3H<3cS<Gc`Xb%4YZ1JMl5?_49AMt~K$s}KS7Q1fD3_W=QP7c7HD
zK&Z6~u!1<`>Ldtd<btpnC)iit(uBws0j*dot7p*S`&4HmY=*NKey-~8E?8#HXeJ;d
z{6!!+k1&Sp{9lPPAE*by60nbr0XMoInhnrG7Za#^j0YPoN6-NM<5L+RrZb!iV@Rb0
zgPajc06?HuZbDrj@S79fkJ8-@#0bWxQpruIiL0PM0O;}*&F~@Oe!P$}h7${7D(ZO*
z_-&vB`h);>^EUMzU}9l!g`$s94u1Pux&lByjm{s<;EysOytk(%q+sN?2kGJ5#7+7t
z;zPzkfefvxQui)`4djgIn$Zd{Re_-G%sc8@Iyj&=YN&ZSBBWGj17cCc%bpb`_5jCW
zz!n_908BNn!bYA}wKDH~Mv>eAzWex-_Z!G@!V`wpD<fy*I6=1LsH6(&1ZYr_Atz>%
zfl00IQ>o^{$Vjdvb*~eS)Hf)IVu)d~kYIw=Gboesw<wKJd~pP)=2XF!2CWpQ7Ras@
zFBg7Qsu&EYZXBzdMxlye`8TM0K)4J8X4o!@x@0%mqFkgA6pE4>;XtuY6cmJR)Y3!Y
z2!)t_pYb3O&)`#Gb$P!C`WC~a-a8o)Aq>YFacLbAp{1d&P3P<JFbF{pxCjmGg*DMK
z_)DAva$`A>%venptzbkW#8ikh0Mo!Bcg87&1OaxaLU=US1Er~mBTZoZ9&jTh6rlbe
zs4_k(`*|Njc&;JL!YIUWlHuJu_<x{T6v+mFAXO|S7;~c#+ye-rmxlS`*<L<Ef@B!(
zxuCva$$f-#&<;X((a@)c%M0AGjapWBQ|P_jXTy_$?Wu^y*0f}<ro*K_{vun`u#FFr
z3VFeXsW{HIfi0Tqj_g8z+?&lVfU-r8lJ8|B>tB>;4r~`RGT&Na_MiVmSjSIgjp1^T
zC;y<l3?Yy$cHq*zGV){YK!bKLY-@v{aR8ypG$xoW`y*BI1VeO+61oYMn`}r7wl^GA
zGR!;xhf2=m{(zE^0i?_h{CNw3b{=h_k4?acF2TRmz1*{Pl(`w-+m-Wy($%517hd73
zq&4M6!txoEp0%|#m!G}u<cxFg?oftP>I(4kx!38eEUOx4x6S(>KOK7IcljTv_|Yxn
z+Elmkr|CS{7XgDgJz4yo1<NL@DHC|!`m`sY=9gSWJ6t#SF}l?FrmV7b)idCRr^lVe
z@pH0iN7;{U8R*z@_H|caP<^4oo<g=A+_v!M(Gd;l<;f-o_9^h9{F1O{R-%6>El>Q?
zG%@8r5Ng)uc$nd7R>4$RTMSv<&W$SAu5~0>_$^qqGsh0{<14qcoAL)12xt3DrEP+3
z62Z-0-Vq0Zr$qWo^O|h}eFNb6qD;I)f05J^Ty-OoK&2KQ6jai$yvn&|{A1Od;+fv7
zZyEFEhBwjhF+_FJ&nM8Y^T@wE5Rbc(Q|pP}(pIDFM%y_4<dVe+&|a_=0go`x<NH&(
zF6exK@_d57qv*rW-T_qgX+zEHtRM8Aa-uLaMSsbG`G3KmD(}B_{LHq3`Y&N#LatH<
zplilT`7pfd>)VFD+fZ?UR@k-^BUK{99|^n*ova<DQJ*reum2DQ|KWO;drt3Aed<ks
z&w$mXzv$RVtXVY=xEEVJ{d$Oh@U`*7-1{+^F4?4RXPBa8S6_xEP>F(u9KA{GNGQ8p
zQucQ2jvfsSj<vwe=BP*T%U@JJYy_%-mN_|>idfATI^0*IkODQGW7rTXxs*zWc2l6D
zomN3FGCX8Gr4+dLA}Q@)z)^t>6>w7GvNfjfCLuqua%G?d+@IKi3-GBx#^;UGBCcD?
zXYl3JjVP5~Ib#AE2!@SADRo@kPMH#bt+KCF0chms30gWK30;u{#0VRQlzLGbIivwd
z?#<N%(jQQ-$pa$-#nK3xw$!M<SB6mt`EwM}mzTJA;u<m-GAtoc{!i3#E-+t^H%dv#
z#WCehAmrk+Fz3ZwoxE2DumT;N3+54sXyF(Lv6;71m=$GDdx##i15Z(W?gm4vA{aQa
zr;>x=wULpB>N^OXD<cB^XX00ek@N5L*R%mPial@)MvvE0b5;B{PSEEjp_GNnN4M7t
zXou72a<QrN(IX(T{V3dD$#^KyFF>Hw@0hF<;pERa67zg)=(IASH;PHV2FVdlxo$Zc
zeDqR$F!;krrur0jpJL$odc#}Q5Pyto0kk2}+inckjOFg1S|5A9-1r@SX8@HeNek0Y
z?}Vpu-jkMBzr)8r$r+^N<*u)PQFT_T&{$``ydmBBr~;#&DS2qkLYl{Fd#{m?GiT<L
z1+5cKnqk`W<`A4#)2nXPag+;vG|E7_C?U6#{d0Wd?;7Ya(*|SAhGItv5%O4<B9~Vk
zc|79R#?Yw!DK4Rd&1Jdy`1mfY591l=VE)O(#NbJzEJwYAe3lfeEbVaQ$Adw+Y0bCd
zL_2QrAv9^D7h}fllXhUN0C&Pr)c7o40iFNeo6By`#*)*D-e8j1_Y)6-=+oF$Y-ZWl
z<pU54Zl}-3sZ3iqKgvb_z4UZb@;2^K!RqhK=lur?YA%nJ5R+=Xj&P8)t`Uz*Ye~@R
zoxDiNo;1IVILE%KA=Bm<`sDMqmqy*Nv(m+6qHFkV=BVO_z{>0&v~&aP!7RV9C)e_s
zorCv~zQIN*H5z}(CVXhGB&x1U5mf?-6umPqU)c=_e%R046fS@v&`+c3YvaBww7QJi
zCh&yvcbzJjsNvQn|0-*pENTBxc8>VAx`V1TgF-w%!xOBE4tTS8)~u6~PEd<tgQ?09
zl`(@hp%aJdKaKPVkvqlUMK!{u$eAZ(O&-SC&=rLfY;BR3;JHmcz+Hyg*C=U_{mT}W
zl#+U=N3Lw;(a?{N98mh_wwNsh%2yoILgH~kgG%adpu%*csPWT1Tkk0B;7UBxn~q<~
zqwcxx+KCV&cbBe-l?E)?p+cQPH9K=NaH7XFW>K3y&s=?BbFy8J{G(1EF74AAS(b!P
z9P%oF>ZBX!w;E1AB<4N$fW@C?G66-0s-N1JVx}nMht4X+X$8xYkvmxegZIY-<J!}-
z*JJ41;<IGE+5iQG9?t9e0RE)NO4U~DaQ^}8M%U@1zU7LgIgV4<XBQbVWh<qQ%PkqH
z2ZJu@?7J3dDm9#{m8Ue~KDnN}X+YfSs|BE`Fa3ytOBP`N;3CRzGMOq`?xcE%w8>uA
zqb9zVCMlic4TkvA`J-=D2cKeIyf%!B8~6=&{C51b_kx%bBQWiqQB}_+7{rv+wEa$n
zxoq8oN=9n(2~PjGh@|NtUzFhpZ*{-X@^!#vY9cv%IX^qQ8u_T4QBf~50oieJ<ZiHS
zdaP%-m%#fES2V7#|I|kH=|hAIBBZ@V{{#L0D)HO9W#6uF=5vhJ1e3N}P{@UYzjuaL
z2peU|75{H_-eLByw5L@T?)<L?A8#2x$zvwlycv<_@d|qPq}JJle=3T-qaVm=9@7UR
zmf9|13y6c)IBo|e2rb4;PReHOL4g}+XX9wQhW74)Nbu&ym1)y0kEFe>lm2HW>B6hK
zPoDLXhPRHGW&9`svC^I6A$0BW9z`~a&1On{2{=?jPebOqYsA^e-3xaGHkY|+=C@*(
z@|rvKAU`v!-wy=O<x=>fN(4z8Do)*d9B-53+hQ2EaTmdU4$qQ9eBG3*-R>7LVUlQV
zqLMDgA1K->)7fNwZx?ua&IonONjSu60dhC@KI&d9)yEa6=WeLDwcHzo|CcN-|7UZ(
z+qaK_3E9Jy`RYxLcGHqdr62xozsP0TS!e5A<`st<2BiAYKK(tG*>v`fle}0F<eI-W
zziR4Z5L=?#mzd8K!5tu)-Q_6<XM|0z6U*R4;+<y3Krfk-FOOoQrcT)93E8MN7{hpv
zvqvY}r%it)j9Idzx22h>#FAK!F&b?ICTZXy9HB=Kow(*`d|-&b3waOaX*0avIwH>W
zSs`Eh2*QH!HteT0sw8TvHii#sA6<xO(~mKr5{*G@CyaaA!@}-kHxJ+Qq_fSUxc~KU
zWRDy`ts>s$31z-5PUmdVe!3{tZJdsO^l0Avmh=B{be3UF{%;>1IYq*t*=T8zmJX5b
zh7lsoK%|i&NC@a0-IExM(F21HX(mXH6p(I2q>=FV-2dkVFFAG}+dcT+pX+m-Cw%$j
z>APSyG`+0%(t&+MaZBy@n193K4ou;t_}-qTr_DXov>vzevzFVLtR3{nw9j2%eAT1~
zF=>{iVKMz$^!3$fZE5NjPfIT15$tsDhE%XXRS(J;Eh1_9C-#ef04lhO`QfuWz@viW
zLR_<@@z~OF)n$UjtoFOZ4)0CwG%^{sUbI2J<CPICb7y2Yri^FXL=UT3Y;bdSwE#wJ
zaID{X6a8~Xb!a?3c~1MXt<u+C)ojDt5<1z|698^-B#~2`c=Sbi@DWYoq_5RIwz6F(
zrXRFABWmXO6Q-0V^2-#PIs3(^M8s4qzEFbzKET(LhVJ`+&|RIkR9s&V$h@L>E}gjk
zJtD(24Dx6|$j4OkmE|X~ztaV<r(7WkF$M6(`p@i4C*^oNiz|y=nzpMNJn3xwurm1f
zgBgm;90IX6bF}>l{kBM?ek^@8BmG==aOCIs)$$7G?t1_JSThzdC!RM=x^%eJxr_iC
zt8Lbcz1z2FqV@nX{r2h+_x1zEZC(u(Q6nRK=<}hLu6?#mf4|HfudNs=2U|r6>Nuzu
zq1C?Fz`6WxaP|n>+snmG<U0mRKmR8%PQ)FHJj3~^_ViABIw1|WVX7tepS!$1mTGA_
z(W(BS3_?rV63R{G{P9>?;DJZw;)%jIThy8vBjmPOA{+!`sc%rXyo0=6$dArWcv)zJ
zXH{M|B-!#RxWi`6yA(&+AmYY6j9}F}=gF`x<vB0Yrw(Cv0j<hyO6v>i$aTWD_5#<Q
zKSDI^=AsAk7r$qhXqdb3nPgg$kMC92H-e`yt(1@0<0^zB=Pfh2H{IQ3`$iF`(*8fq
zzgY)yH!0W>#V}XhP54T-Ls5|I_K0+DN|EdJ6DNiU<x^qVhW+FVs+QLhiX>{A)xumG
zJ#X7z1{FtdYLS11FC~h9t7@>vjgxWcruLmY8E9W%zA*Di<aoJ@R_z&gJA62%68q1r
z*SoUyZg`Pcg!*VmHG=;?kna0j*FJ;5cZV^#Df=cStZL{!>$N9&zRs^(m1x`-JxBKz
zn8?lzJ-rvbAKa0%l-sC!cTZVA7khSG9faAWb<S)|SWQ;p%ED4<Sxh7+L@VG{fAo4g
zSnqke-|&)NI=u1x2l*c@_{>VKh$}vg^xN*yLu1bbMk14s__pomZ=Y2Ul^>PuC`?Hu
zeqNp~#q;D<QbF&keE3s#)t3>ef5B?Pk`iHe?^^KrVNz|0q|Rr(yS#o{J6>{nIRUJY
z8tKqA^MQ|l%b(ZZ4Cnw)z4=99vo0ZegK#NrJdA<lhYOt+*114vH<3Nbj2m^)jf|;V
zl;zx6gW+{*w^yY-we3_6ENUgL;4B|yrNtL=SCJL`rkK)!6Tt}%H-d3^N0psVkG^O?
zua>ZDbI@^x+qzyZii%?3-b4W$&Pe*W38Cr9)7KHYZz^bI&~aSaEBXuTFW^BDw`0;B
z9e!X@BHK7$IWe(*_0jNU32#*P8rfsgwt=g^oB1a!s{Jw3Qzbb)smm`3a1`p!Y^|zh
zf9!F|Lq)1rQIUUdZd7CjMUY%fa?J<EjvXLP1YuU+ITv%sWym_|JCgM!`_#%Am$Swi
z_bqa$95<1#UMg*UjLP2UZ^F|kJ67EyOEGUv?Uvi9wt;<HJASH$&YA6&P8ek-$gRp&
zSE{qSy?f|rzC=6Oo%g3+<{t9bmEfa-;_vxAD6_6@i@U>?uR;_0l$~g_Mgz?3X&NMI
zpm0bC*`J!vCC9QeWw>ks7QPldPe<_4EbsJDGTR1$p}TNq%hw;DtPyz1G+W)?V33eF
z*%1Pcl)TyzKAQU(3^8%<VZX_0&@lIa*FBQfUlZIGz&Kjmko;sRJ!H0fw(U{RnV4rj
ztF0ghZ^@ulj*Z--shp*K7L^3|$Ns+0)6bL)TE&-#<okVIaG_jWzC6%Ud2<YP*O%NL
zKt8^zilJ=2H6$})IqDR*_ruKNdB@6Ujnjl>yo8>YO-A-1{Z~EK<piDf*p|$dQ2(ul
zFAI8}<PSws@`{&8{!YG6x&=S=3;kl#WOPdF=a8`6qcK)GVJXI&f;Ix~MDZ2Dx|R=>
zwvE$H*F@kcdHZD!-gG8keYo~N5FMPg*maNRh%}dhA0LQ#7+I5M{BFOskSS>2J~PIP
zwjk^^wQwv=<H4@o*z~?pg6WS^<;Os7(WdkBiJU3N%7366%tS$vC%PSnr3sTco=dkX
zKLn<(tf>x-Q3_WcD0Nqtm;8S5Q!&O@Noez}!JC^NXUZ>3zI-2n^;?w{rE&-<PMvj5
z*CV2Bp~Ig!GCKd&)kbh^54?R?15pShU$UHPs${Yas*Aen<-|7bS*4jppY_L^6M5%f
z(tYty>Z`EWu>o@{5*$X;G(WhQz2n}SpW@p74>VPyelQi|`JBq$mQEz-N51fg5noH$
zNIsKz*t>rSE2Cw}%Xe|05nKSXH1VbJicX)Qm!j35A2_8!;hEDN$vBQa_?PWb#e64s
zCG8=HiO>l*-rW6)1i^%_+nxJQA0f4LxqXo{U~s#%h<G%~19Zub-Xrg`N<R_^=cj7E
zIJ<YxzXL59VGc9>_B!jnKZ|i*O2xrGDpYkeRnu$^T5Mo7)5$mDKI6YXUI|7S{+4AZ
z%B=4>n)*`REiwb4ozR%Sxw@ci_s8=9_Qa;O3xl94y5)UIP=N&sOMQL=4pADih^%jR
zZR?4B)n_s;SN!s+q4OG(@J{=15l}tWt2dwhiaCJQyV^(i(<*t&Nl{F-er_bbA=(d!
zlA<aRQx^EOU$IUKR?K+0Ks}vrDX!0UB+cs5Z`&k&>AMLD(95G&QT-anhHtppG~zFh
z{PnO^$-T<DDn}b&UED?aIfUP1_908D4YR}zH-%A?aAi!|Hf=Jn69;iT6~rqZ_fp-o
z%GB?RQ_aOswEwh<N;){Rw~74u6&42yfk38m7sL~9aX}=0M-)ig!TAO@v?N!?zSzAc
z-~z_)nki{l&f?}Ae&!S?N0;d;+f4^L#2KW_<~qzJF2Mgm0N&NJhb5~2fx1k;zCtlH
zN9Kdkb^8|zam43;w`%DV?hvGWE{J3)y)1+X4*|Qe{P1!Tpkj{$DW|<qG$ljd>|cqL
zlB$#p5T<t>H~|;p1L*&7pgGb*)X})*!-#P{e_8xotea8FM^8qiu*`DI_$aYs8``(h
zNQpO~cY_Ww^HNpUdw*jW6r=m|5##oj6P1{5Aq(@cbtw!!?JS>NxzDmdM=VQ)2{kV~
zUX8mJ1QwKx0)RE{`z2Cu-%tjbB3vf!DW)cTtRFE$c244-Z$$l@q)(7Y%6u}chRva#
zo?1VYnof2WQe(lj<UJ$KhIY=rYuxi@T|R*#R>H-raBlvU!_IQ$Z?ahX(x^?p-jz`7
zpj*IZ2aj$qO)j?*XH8iZ$<97miJY*>;qN|aep4-;yo&dSVLel~X*0WAlAi_BbSqE3
ze-R*Zr&i3<Y+ikf37PNoH@thCXTrNA?K|=}(`yZ1cs~odJNwDtxr2bitj*o;zYZxo
zX<LkRD}(Smo_>m^IuKh(S=Xf95Kl>5A6qD^v2{xj?_~1;v6^BCt$jr4#v#t%<`HiJ
z`PO(cB*qJ%3x+i{oL*L1W@-Fc|9Q;G;;dgC#sTBb%}aSO(^gTMQ~Z-Z_+9+=Q{Ek1
zmT``eL;N4UHog}q`4$_c){nL=9BHrB&!;mM=R+He_=XCHed$<gY;S1>?hpD~q^6Bl
zY|`Xjj(4o?nkcx>=F^%7*F4U76MruW4+1cc{KPuW8iBtF8i{aE!XW(KNp+}?7xcY2
z<RR=s0|Pm43d($GvS%1TiopO%W`Lz?Z5$8*!&F$oFoD}nF}Xk>ZA=2R1vSWx#RWY<
zxREvxpM<=zmQ>?aIlynwr_yzph&1NhR%OA^!Hfa>Rxkgu9twb}`lJU*QQ5iE-!QDr
zUdf_w+=y(<25eq1q{DH1qQ|Xxn3%ysBV8I0Spi%g4MZ{kj}@#dKpu>3m&1@176VY)
zvMmpgRJ*R>1eq$yY8}fj0YWK4MF^y#3p4y$8;BumV+O8<EDG>JWwYRTO@saeu}Z3f
z4JU%=gP=e|n36(NxwZfXNWPTH*lPhVoWfT@I(<`Gd1AhS0!sf#*GMYQgMj0@)ysaI
z?gqGp-04UCG-=3~_@_{-Up>WjCDG)fFQJ~a1}sI9)ME>YrBZ&gkyMg<T2BEoN3HW$
zK?y&#5x6S&50>5p*nG!sYdiq)DFk8JC%)FY1FkMA$zFb4d1I2<tiL7zwGsr=rGtU%
zKmxK-IVV7M95GH3QIvQM5Nu6DmPSd5?s%xjjwk5rvB_+7fGSB*^h*qYiP#_Fr%aP-
z+X8I~0P~+QRodPE6)Y7^-A7H%M@iIFvawQmU|mW;Yvv%ZNpH+anbwY@4>|*sS4f3b
zsW-<fd0kz^KsnsD&UhjKX&3@8Bokwhs{BwRBV7}<(~YzS97wSE+Jk+<ovaQ7ZN%;Z
zs83A~V61VZ1=!XkXGTdbMg^`shCl)<s7;Q6H1HIFj<y>$s(U0$Ukhs5KwX%c00JQ;
zPfwK*U63SF;XoDQmVAP7I>n|cZ9y)b((s^%fPhYYoW2c^#Eo#LwQ;dvWqW}R{R9V|
zb5|3*tkH3ESYQYOz(+VX(ICn5v0PJH4UPnms6WsRM+!Ldg>I`#v3~_Hrx?(+z_7=+
z;~{1M21=P6v}M5DxvRRZ4T1ozYP5pM|Ddi>?@=bX*Pb*G09V$uL=40%<)^3rCOzHO
z`8zgD0WE8!6!;IM1dO@psb!(tVW#)?(1xC%_E>1S3YEh`Iw*oZ5CHiC7bv(7XrOTY
z>~YB?OD3~1{ku8~k@Wwh@&twe%1H0-EP(Mi1|X~=g34E>#)bf;mlB|yu0+i#j-iMk
zMU*L78bPWy7fl(7hP|N7+6IJao7#d#cs@aDbu^uW1{e+6*LETUKpXp0xdH@fPEJUW
z6edE-SPtjNMBgYy5~WL0+~Ip#E*>f28&T(OI9?qj*dsIM<L@`{M|fQ7Dakh4T+grk
zdDDmL>Aq1f!k{FAS&8@eC3M1<SQZ-Fmaw;Z6=q{+@E^!-mDdv29@DBGa3)or{(Af|
z)8FYz8dG5@aho{;x%0o!k}-=p>t_CUH?Aa~Dww_VyZaAv_e5beQ>#)|K$-1j=F^iD
z*khIL;_eGKd}-HDzc}{)K!&I=y@Kn^=JB$h{)!uAL+jn)+ps2Ffiv!l_N41XN)%n!
zhsc0{syWQwmj~ArFr(O6|0Cr#9*!q(EpyP1LsODg_3yu3@4rBIZnC^-C_iWXNZ-QH
zz6^Wm`g#hUwfCz~rL6p3M?Ot#d#GOs*Kx`!2QjaKr+rhe0eFgVv+jRklKC+(>v2y6
z+aGh`|3K^x9vlnF1?!fKBVD&4K;3T9g6~TsVBsQuy6EHDH#OSuJVAIBR^0z{{CcNW
zm}L83f@yVSX@_}diEUqZp*FprbyI)w_8iVt)U&0(y%mmPQh#-h4q{HwW}kt@w(110
zD!U-V^FJl(T$tWT8`2WmdCF^`IlXUtezc`0t;SdBPiSb8lh!J2z>7+RmiDuEuWQuo
z-75IIopfeJKOXA)V=(6eSq)~{*Q6CZBz*k!E_UK-#oaiJHa*Tpd&BBQrMdZ1xX0&P
zwB)J&)^3p`ic6PhH3EWCgDa5?1PthaIbIum<ZHe}8h#%^KkaAJ#L~EfWhDbE{(6Be
z)uQS9m6<{I%20=%Xry&w-8ySY0bkC`KMjHf>1S77la4u9*%5~Rms3Aq)fTvED^>oI
z4S*`UKla&7$X;Icaq)Ws@@x46pv6bNYlIgrMQ(+c^=XD(j7=*E&TRLR-S(B7rpM&^
zHuXM|1GGw}n-c&%JR<#Gt`jOCMr&K2qR)Wbxd!$^RWM*g3iL?12}6fYKEXjY>p1CY
zL$RQcV)o-Uu%S}<Tgn@~Yyh)J!DCo^wGAWy^_Ytpmc=%}#bf@*4}!j?q6OxG=E23J
zNjPW|mSv6FDfwto>V_#Do>Pt)6M#C<ls%#Ec-oC)DIP%pazZ@FZx?{5gMk-9%byg!
z?Ii=Iw4(CC#e_Og*yaN2&O+3!e3IgAwLTJh!0HHzppTHs=5#;75p*dz@caQI%IT$b
z_r;hB^wA1yL=rs|kr_c`2fygbnnK<C-(G|wM=9cl6g7Y|E|tpr5=D#|;vxr1^q93k
zr~m-`h)SkYi4~<akOC8xr8rv7dVLdeFQ>y+A8UMk)+e84$Hl|(kozl~zr>bkbn)ux
ze&9)UcTdVYDYM<$Bx2*W@Pjg~#2Xteba%y*G`$^<)X4_vM9pbS+kDRbMGSSebKO1~
zY*@u!3uFFF^ot}!`WHh|)X9^yiG2*Q0biw=L1ikEh-vlWg0}r#>wFpg4!Q^-O<zYx
z%aORoiRtNjVXpWg*aDlQ^!;t1U|z^qn!t6pCk7S5(8;E{xuJXfl#y>YkSsU2T8`)M
zXT$_`fyPHw=G6_QttsOw>X-)UFU8f*d{nE30=ORuFO=Wm$@?tlmtR*bVI45!`r|f#
z=juXjTnHU(itTpbh2Nr2g&|#l-9|$hJd-I5?-N`SHm%{f*mzo{6ig?haVjl+>)i*s
zMCo%5^1k^$+SUJox>^4fmg_5z->q=pr`)xpXv=hS=m}xi%4e^?y~nZ?m9lM(W<xKG
zm-aW3Y7?Z_8)QA_+7J<~Dx)kP<*l*?>9P&g1NwxD_#WR5yRdjKMY$~*{Rp*5EF7uR
zVR07v)fYlr=cFV$r&XUisYh-<!-q}lo~pXZ<{u8$Ees~+k)8Q}PA*K3aR}#suc+p7
z`Km`&w!gnBN2|za*_zM3kuE0R*h27%_r`r^W`dvHzqHkGx8Ff;JE{n%wMgM{5g*o_
zA=ikOfDs%M*?{ydad)}L#g81c)T~-XFz~If)}1~9$I>cqU$0)Fd?k$9OHWG9JxD6Z
zrXg!n@3wd*;*D^olZBoldE;zZpDKH9W2GIO@@>IEpo1YjvaVNFK8Fr<T}M|6TGd`q
zsfSsEP2YZwWc`!gx~MO>3-@m(pYhcu%Uh_63Z;X^4Q=ye$@DYbKw_wUh4_$lxOj9_
zVbz>G_TGIg56&Y0r>i|aQaR%jue70cS)*)j&!^hw6W0if?@DT`Ty}ZbMZ8V~QbKpN
z&ZSXk-e1^YI6Ma*B&7JB*M_X^iK~cYbA^_m_%D9?(H`H|x|X*xQI}uMI!_3&IQJk~
zVDjFVFidr%y<%wuh*e6Re1!Ds8mO8N-`y6ItqP`=KR7AnMU}FY4v0Eq$E2-3x5v49
zOEmT?XB=0@2ci>`C<d0_3-BWUO7L?{Bt~9LH@*^`ej$3iS@-y6{5rs;@5(H#VD8*A
zIMl)!U)o<ijhHVmF|;=?8_e84H<P@dKa<PAT=-z7W=I!}uYI2i4fhwaXsvftK~Ru#
z%d{fKY09?it3^IG-ghxOAOFJ~jG^wU11AdA)-QdPiL#ATfk*49+J@+YzIibSN7s>g
zzSR=1HV9PKhL)Gy4kJ;8bbC}7{e+A$Cb8-km&yJMB7X2Q{~0|0i*r;;S@x>M7jsO%
z(t`gsr0aaWAjCpBXC=EOiHvTBoE%0cDhc1xS@}DW7!ri%5lnBUUgdRO`235xx<c*O
zW!5bImpjeye;^~1&()f*Um_-<QdilhmD^_rHXrUGqgVH-J__C3B1=4I5_Z4$kXMC)
zFwcJ>c1(cpwYs%bF(v7)m7;Fh|Gd#_r|){erp(IGgvu|Du$bi>eB8KC8_8{ln0Dt7
zryBae_-sX4kSJ<Qe4-3XiPHcLzMtUh^3{SLzFa+WX<R*@OLOQBB(v35c&;S;-7)@}
zdq1jSkk<(<nM3=|$MQV7anB*AgzjhJ%$^-%a`puC8B}<*_TcUHR_1!|7X0;h`DYw0
zQXTu_9)xPo%dhIDeXidn35|Zp5>aM3+0~B>>b)=gpr67*b>);)hy46@(etL{mRkKw
z5Mo`|Chk_TN55ldytDP$G&j%|$6LghXNGBbn#XTxSa`+ci+L4^f975tO%v$#>SUk!
zceZTpJGfz&pC_zpf0g%|<Ox#qt$&+slCJ%L+&AUPj7@FAx=NlN?O}v-63)%Tu5V+t
z6lX*?;IE-UD?u56ZhRX+OukozEfEY^4lRiVT}<55nJ{hAx$~1(BNRAB!pc=m1w({y
z-`x1X!)TT{Ld4KwjyiCDjd@Q(gg&h!?%0JSifF83GR&7Ea;Hvmd$D&`AIvS_=VADT
z4^sXD>)`?^=&^h*ZfMI#N(F?a^bd+=f8omZdJi85rp{;6yLP+W1Dm|=#HR6y9T-+J
zx`(|^h*3O4j;B;AP5m@1CFL;xd>5v}Ec0Qy;GjtVRSC^X_G!bqM(wp)NBQp~LH!!2
zgwUH$AKX~LUj8(mP;Gc$T}!B6>Wx_=`prg1@q9Y?a9vJ5)6?IRZ*?-1Yj2FzH46GT
zk*z6CDh$ezL&T(|$mkmCtOVSe#m!XJLg0K2{Y!}f)*>t%;3RyoExo20=(Nh~r{c%g
zBGB&NNhTJI>hBV(w4M%E&)SFbULcS~JH`N?>CLcgrOSt+1DvHBKk>`#TKoc?uE-*&
zGEge(PWtPtWVo(qcR;-=!mUOxpm~uO6=OZRHgVXZ8Kt^X93r9>tUQ{~4oRGx?DkJB
z8{wa7yvGIRfgq;Z;xOO3AEfM?-S=M^Cf+7ZQ&o0!9T^mUWcc;Sn%@rHcJpVT6^Afw
z$;Vu8c#d1&x@+>>NKC#&xX`UVh3^BuyB;~u=F}3zU48Os^c(uc4&BzG7Ta|Bip^1J
zm*uZY9j-5@9IzhGA<fiJ7KfX?=3E*Z7MTYR5@mOUS+yiJPt!of*TjXoB3bz3zPs8^
z&clMA=abb175!rL{Co}+MA~1nW7|wq3`rP@Vh6qLnUuX<R2JCNqnD$Y6)hN?*f<7q
z_l`&+1rNEb8x)I-Z~AB*mW@fKJ)RQ=g@jG4h~4wBOVJ?SA+N0U>pU&Fk*}X|4G*~U
z>{}`K^QDlYRUsbcIdraGON|jueq(I)sU!$lRpl3>xx&X4uxldzH~tXwLh<<!DZf(F
zaj6UWfnBjWt@ysqX$H;Vu{7J0^@!yw&v(r3WEh-Fp99i(q%MkQDvvkJ?yoZsF;)6W
zNzPTtu#h*`b9~A=S3e7T>$t;UXz5u(5<;_;;<FfCoqkmU<5IWsMr4!8sPJtXt&h=4
zLW1jV>DQj$1<9b5Pa<<7UDkYsK*bH}dM%u}8@1kCR`Ht-VWw#x2Rv`2)PLj+spL0^
z)fP@UfsZ2vipVprgmSY(c!R6*^nP&zP!jjQ_o%V>$GA?~3O^*8>2EOmi7$mm>&MEI
z@(of-)Nl?o+^ghIv=l77>(QT2)sNlsnYuo)oL0AVp*94&A(vA#?(nxP!wz)E{f#PN
zkV!;cnV`Myy7ua8%8I?s@!hBHM$1}kkax{b9CBng+OoP}26>r@El@^Hj<B|u!;(o)
zVeRadWg52=9`aiJ2XaQDGz85p^*v{Pzp`4cL(A2$nFc>grC*9Vx60?CXiRwbE%9jy
zd=MRbJoZ^Hl&6yVj)iXKQX+-C`Mk5IxC|okQ`MZove-NSO3`5wZ>y~RU}Fa>x!p`0
z3)SsU1Y=2kPQlLAnK4~-NmW!!9`G<`^}KX055Q?%>n!U)y~3s2={)`zD804tq}66v
zm;HIT#^LBWP$t{Kyoz&GRAg%-3=c2r9Ms<a`P0t+Ri(nK;{3_s`JHb-?6D`H`Ab=q
zJtO;eN(S2(z0*+J3>~^L8W`?I8(B`?(0`yrk%zw+W!_8H2x)J@g;n0RJji65Q{!7~
z?r^bUgW?7YgyswvpOkCnL~P!2_B;MzbIGb>Z8tbGd1dQYHjqU6SGQD_AKgIL!`4`M
zr|okSN00E$K&ZuAjvozRm0x~lHL)k9m(8zYb`AOxstCba`19x^n}7`;Z2+#D>;*Xt
zKyIaVqK{+VD}DWin0#~ox<*@NqOTp+IEiC$>Hp#`KuL#t@zVZNkc9I&Vha6AZdzxv
z|LJhecEqiT;}7xqtKVm|cr7h<x{N&~wfO^(leixh!-Zi}78AIR?WhsTdPQ{>1DHOo
z3f}2&w4CO0%Dh#~TlqW8aqh+@H(@FF1DBgE-!D9#v!E9ZTS5QnTUF5XiW=x{GV?Li
zP}a*!@um*gHTw=<Fx)y#RdD+Py~*sC1P_aXFD&1>Z5?+e?Q`EYSv?3U49va3x@`=E
zO!e^beO=?7H?Y($kF-Ia^%KBWYiWvcF=t{e9{h0UpQ+rC%<Qdxo_kL~>?H}R4X+hi
z3);y2l4-Q4vmLO?C(z!WG*P}=DV@EVDNUPT`gtG9^hfKGt&Z+fc-(pwhT?Vh^^#XX
zc9TQXl|YhFQ|3J>TN^F8AziHBhr_3{8i%PmS34#zQ!%8{KkQnAf7u2k#*m@M>W{dS
zsF$9|K83$C)4r8O`m-U_I$;E}Z_>MbZTjz?h;iKU2!jas<PTm^9ZN82v%tyrvIn;A
z@Iwf*5`6my4J2r&_O#Ts$0t#K1CzWWP9SY~Wx|^}a_<|GrHRu@*^XkDfD6`g(r!Fr
zN<`7=o+Z&X<Y2oKE3hgVFL@xz<^kxlr&RszYEf<G5!NN9k5oj6Xb+`!SP;c~^kV?@
z8D>mk2tlhVr?-JHZuOC`$06+5)rpTu@A`_*PfHfwefW*QjL&nC8~Yu77t-gKSa+X$
zLtQIbjogG*@grEx`YS{$UJdolu3qxUG9z}v$~Y6XMi%qfnd7Aic7{MRi*2ZXlR%(o
znS6)Q$)c9~1<x7O0_7sTH4a!GYLNZGbyQ7Hyvq2#QS!N6@AKnL6<tw^L8`(E#o#~J
zMP_wO`(jYx$C#G7#M2*`57~2N^c^dEzoq1SHoOv4efT361<I;Fe47t+-pt*UTd6;J
zdTX}7L^1dy&5p9ku1zz0jPxhh{Fx^={@t4@Ob}PxUg*^S)CWn*MX-*2)QY1|(Vm^R
zg5qCF+P6;O!op&pIh-~7@(~P^_|_>_*yH<_DO#psM4=1oE$<w=Z<>;Q@chC;^-%gb
zXi>g;%ivkbmZx7GE@v#}A&JIw*2c7OLyA_K$`+U1Fv%+cW~wjXsOn@oN&6=L8IFVM
zarR@9eM`u%o=<;{e#p8_KD>YHO61DoDVq(R@J5<}H}~<-5r>++;I>WkFAk5<hlM-}
z%g>U!Dn8Vvar+#EC>u6%ij$SB2uo~cLjDNb8k6g9USoS*hsi#UFxM0{G>5*+$UZRR
z7m_q^G5%WnsXoAv$9aUkDDA6<@&r3wo%dU=MrO_lO1xbn$q=w1EB)q7DzWEJ2y};F
zV&SMF4YM<QcX$3NT%f3yQ{Y-aswnE_LZT4|j;xL}lG;y$Y+LON=;lgg112;ufWg2O
z1K|%6B>r~{WehL}fQ+sU+y-(4ke*v096>7P05<{$$@~!@&|{^@&`$T5>7D7DR?>j7
zxxVS?cJKZFw{nSVh6~DJoc?j6Ox>qYNRXgkicUTdY>HA+fRBoqIsP>R3AkgZqRF|j
zhZHEVDDjF4cxBmrEm9P~S`J*v0+PVsV!kNaJuQd7#Q=qZ#19R^vH+Jza&Dp-S`-y8
zm5nO~P#DxE(`W$<uoEONKp&H9Op2lc!vQb`=P8!n84WbtopGW9+p0iD`#<#^@WZ*g
zef+=8dMS{zimsh0$8cgaASyHUHFyX#8j%VnTC1utbzmSOp%0V-(TZz&VB0`Y1A4&p
zrC@?O!=wNW`;k>G{ZWBo8W3e-bYd;L2WamY^S|E%OL5>RQNT_>8+`<T=0FO_Q393k
z@p=G%0<cs-+iEP>Tw}=;)$USV0D3GHMg(nZy?}}La%}@9H;>{yP3?Uk+3_IglAK_x
z<%&sSv<1k=&c{hS6^uP40)P;A832lmB>}#<|H-H>Od~=u;NaroYtH~}G9>}<5oQb!
ztBs8w7x#(^04lcz7#;mReX_3tOK5$UvFR8cl*trQ9I1{bC->{~)ZPc!Aj?{i5R6lV
zN~{332Bv>RjAW{VZqw-p166W63LYLQx99*J0P;*X6)A@?J;jh;Z9x^r(sZ;bwl)0)
z09;8w2IM@2q#z&jB@Oq~q!er<P51R6p@Gs(<r(b%lM;Ummcyy&8%xMx^24`C6iipg
z3$d~)x`xLf620mFX~<S$h{<53tzqrsVtybgq7IIL8(wRG#(>H>TowxiMbr`LtdeLt
z7)Wwoiw|j7OWTz;hn6=<d|AA$dTSf#%=_s8qc>1#X&YbYt{UdrgT%8GZFgzvP7ey~
zg>FGZv3O1@HG;0)f1otAt1@QyI{NGlq$(L&pf5m;c~6xDD@B5)0r7eCQIOH!4bXPF
zlWXiNsbxo{RK^Se&@b$sMm2a4KU{ndtwJ{(Lx8J7%Lp8+YB*--7j0my4J^0--S#OA
z<iaVL3S4JIt$!#a@OLhj0mM*)>E3`-4Qozb)_s3p`Kw%xm6#+&R1)q&+sRwzr-@y!
zKIENj`Cgy-_|a{p^3GFOEHrYZj9o{r=KHRpMa4jIQdyzFV|lQd&O-W;j<Js*Rx#*G
zuy_m&3ikL`vSu2f5g7r{waE-d067>^gsg>1Obh1YhXmwh9<qQTPm0}07bGFMkVU@`
zha?x=2Fz^5d})}Ks6<L2+z-M6->H|os!Q(lIlBblRsmfh#&XRh&&{H~NdcpVEal^_
z*Q~~#*5DXbMIzZWQgRQiDzFXEiD_6$PNaU3Wqd^p9f&-(7d0&2Q=B~5HQuRg*MDv2
z)Mi)Y!(2AA+NXJ(v);|7xj1No3~-bLiIH%c>2z$g>%DJQhUs>^)|F2@$FS#`m}|Qu
z<qHmQibp#CfLj}tpAHEJ?jYcH)Th`l&{Zga8OGOp?Con)>|d3GA#UmH;@U5j04Ddv
zc+(JPFBGUV)8D0Y5R@Fjg8&oR>7MG%mi+YMyrvaY(9k11NH$Fs3yfnx7o#KqiQ7+G
zGi+?sm?RgnWE$-WI>nKnY-Gn`+c>uYK+mnwQKMC0&!YHf0RS8s1K^h6ZN2GF81i4T
z8%c)8j|`6;Ssg_YM7Nj=V@;*4Ta*E_s3ioNWR;kBE#YyCR*}|I7Qk=J0edJwI=VJ0
zu0ck&|931GVA@iT#l#R`Ao&8gS`vcRh@LEMWE0?_A7iKy#FWmx*_d;H&n~GQkfyg|
z01em$Sl=azPVHMUsF;Ze%0>{#7_58zkSX_vv+OE9bRoQQqX=<-Nb>#pyQd!->Vnz%
zIkzP4TrW;D^Z~7e!`p937I`nMTvv>rcJC7u!T`#OdumKmyjlu+yH!FvCsE;~8ZNEy
zsSh~xZ+;Ip%P%Z*Rua~^Y^-W$LCr-gSmtN?8X*P`QVTw<COOnbF5TFuy;3>c(V0`6
z@&vg<sK!R)uk=SRU&F>R2`^Y$2;PmdPKaqn_YWaJx%KxeIQEzLnj@K=op{XNo-tSh
zqkU+5wImv5@xZ%)Ypx#tFD_DxyE+0EZ-ruBOd-IFpCrmpqzDed9ajrC%B+jnl5(%T
zu$MyKPe0&2Noi;llfIA)nNB+Q_bt(Qzy!2a)vPa8WY#w~id=hKKay$?%BuIZOb$U}
zI&0JDIg$5@-nO#OdJ)Q~A2);<J>a|Thty8;R@vGTgmF9~vsPur^6IqaLHcvq(z`b7
za+p_DY$<Ug^z*r4#1q*LB?@cy_w<jSGgE@8bEiqFJdq9H=+M1B;n4^8t!rHt$9=p~
zCyJ4tI*{aWFJMV3_&fE}XC!RM<M;P(Ichn|9N4)b@9{(5Ruc&upJo38!IMW6rza9j
z9l`;wJv(&O68wpQ|Lyt2`~@;z^~L!IO-Vr4{RUA891iNx4mPcZ!E3(VWzxlRY8F0O
z;^O6wzSEg1P9{v*#Jer;#W$KRdm+>IRn;y}UH+9cDXjN-@dcU9^yEewShzDtPm@oD
zeX9B~%_y(QU}(o0rVQuXi29r`!L6bA>SraTxoaA@v@P&gPDR=bZ*l&cvr1IeGx-p)
zRLK@;`7V|(L$;UXDfvu1v-#XY%eqUG^WQUy1Tb8U5X;GQ-?`-RuC#||!ABNLZ+xI_
zyP5;HTs{njMs;3RdCBQ7<cU^gZW@i(dCc2t^5j|l&Hzo*gm|1z(?H(WMM>`*dNLkq
zW@XxGQ{K>BY1Q-S+G;XpV}5}^`-eQdqvLN6Y4(lC*nUm<dsgL+!A<YD-q0rfpk4c{
zu738#-muZg(tR>}{`_#+j^8RU&jcf56`?4f?~$5x#QX*pZ)eJA<^)f&6I6u7&G85C
z_@8Z#PId(7<+6K_Nguy73{Gt-8_tkG-S4NYivqVnfWMsIE=3EOyR_MMJQm9}m0cFJ
za9%5E?CI9jh2g>N5#xs&xzZLt<6}E7oN5O)&`#=;OotdMb+dYvuyyv5Vw=4ZZ(&ln
zWo_(;c+HYvr7P9fb$wP4<W;MMLL^OX&argSZbq*eTCr<&7F%vl%N20?PE|2x$o#XV
zz15_lztW|};f<CLNv$Wk)4r4bvis*#NzPPZdDXcnrbTHCW`Ey2aAP27&#JTAl3zzm
z(Wx-k{JV((F;cF8v1IQNl=-Y$SECmhE#Ws5?C^kmn>T6G&i`skv-Tb8OuAKJ(BY?_
zeXhDV)vBUAVL;U{KVw$oUm0RT(%dHgH!^v`&$o_iTicbbFx!=#fD6TAhJJ3c{2d`}
z6MdGRrt(usc=$Q}e;`jg4CHSdTCz+5m}(|RJsoFQ^t>wDL@x)P&s`cX6+Bkj{rXY;
zBV^;lyx&Y)!&(W+;Y7!)I%WuKCQ>ZOn$dbjY^2UVu1mIB=jLCl07bQaFhf-3k5F-`
z$eQ!Xj(3pjlcfeWvgc<*7KsNIA;6A|jn#-qQfuyJLR+Pj0e2J0$D4bw1gLf^Me~8x
zo)6E<KU&iL>H;pE{K_XaUNV!+Ji9ji=&}zV{`fatm{<Jna7Gr=%r3d0E-iX8bYoI%
z=35wxQdS&ozM8<w15vGh$U(D>9`Fkj3-;g!YL-T*r;PO7g14`p24RQWTdrqR#CsVX
zB<d!gTVzBAOgMw3ld7r^t^a!~98?r7Y=v*p@G2}zXg&Q?mL_c?A2e|$qotb%<)CS#
zMp)ew{lXG_$0Z8TKw?y;8laT&quEl4nc>zjgF_i{7~@xwWd1Y}k)6dpg>bL<#+C-O
zlSPMV7<#%EDSk`h8y%Da=4Sd%&s_D)3@BjBvS;*Y)3h!34@?IHE_nM;$^%=fWwT{Q
zvVOyKQ%w&m<?oJ02PN+GXZZF;xK^Flpoywb!};Y*EOL3Nx${4eB_YKO?xC0@rwxhJ
zF8WC&YT!&W!Ds8%=@ZN@EVI$015V%EFf_lM$V~fIzv`T~BY!c04{Q*R=W)qiL!fbi
zPZAN6`E2cipC85adfCKk3C*xo)b-r=QCv7)RLKyYo~@rBoN`M37Fw|i|2C{JX~TD9
z&Z=!)`x4_?sZg`n{ApOh{7}?zeMd<sUF`Gs77S^Ptu~(LNsr3~@fJ%~vtN$QxMFZs
z_TE7K4TAJU)mQyRG4eoZb>pZ<l7ut(_<gL>v$=7()AA{CkqA9@+usdsVlqrq`3XmK
z#{L4ldLAsUF0S2zos?Azvmb)2T=`^{IMfaEeZOe<Hu9f$;*+`CKMBnUEEbme^x^^%
zQ@M*1nxJY$k7kYV9zTERyx`B`&V5bhyl-h9mGN0_HneiymUZ^|oVwU%J8Vnj_d#G4
zB4Efr`PCp@S>-MdPh|`N=YHRRT)x&%_+(c{By5-|9!ldj`;#F}ZYdDYn~_I=<i|_D
zw-j2t8NlnT#1ak<)%aS-dR4(3{%eevWNpNGs%+$*Iw#57dBpg8iAwe&I3u6-S>K~O
zozPF#B|UN9K@^?@#OP1voZ%b$Iy@T6VF44t`06pjeP@cj;-ecDBRK0M!%(IWh($kg
zj{PNnBwV(-Gu;uLC3suY+wL|t7h$$K^ikRAw{o3pb+U`ExW!rquXKKmA6?37KKFu+
z*)L(iC@q2<bl32vNqWh$ZXfaC*Y9cj7BrL^Ylf%GHvjBGDk`ZSiv$0A4fY)~NO>-)
zDtZ0(_@$=BstjKEB(Mi3y_(E^{*1RE-Ov2)?#)j|?8lW{PHMiAHUko*HtEs6trm<k
z5cfoQN8_dBisr!Oq}=bjHWF>ZFpnpnC7joJFDLzbM~1Yiq6{hgW-B`6?mlQ&ek~OB
zL;ZF<vW}sBHo{`0O)J##xtYih_F6s)n&n0EvvOy90^qD`e!lgZ>Wj1Qr+Lvo6t*)S
zO)rXv#6<8>z)t&W!rscAP{-WxWkaTS>=R^h$EA2;d^dHtS7t!kJk=vNS5)k((zOuE
z^jkuTy|9%3H(E-;FEE&j#Z`rcd98=0Yt_K_RAqR&UgNr<&}e-$r$yMsL<+&XmA!FK
z54~h%al{6kn?x`}Qo8;GvN`F&79kn>yt=j};(wr7e~_{zVH37|T$Vj_D~WVx`YcWF
zt|pJ$YLFgB_k(AIhj$Bbh@qtKw>w7|yyYwXm%SFP2j1DR$a@@W|6_oYC!7g^FNH0w
zmK8sX^0vsGFzhJ55>lBiUGm)K)@9b*=?Maj9%QKhcyi?N6-c=5+UuONHgI&c&?YIO
zz?D|O`4MRsFjcs+^A&sQC+m7{k9B;puxKgmrV@9-`+Ptl+<Mx1U&rJGnMe4w5+Htl
zOI<DL3m1DVocK~fJqeetHIMf(i`BzFns}8WVb+a);x6pYbbTn~I##>B?a8qwbRw{A
zw#R#sl)+$SRO^s=kkpm`;Q4g1;9v8<Wj;Q4r|$9Q%*x@0_!u9*bp~I<BFqcvUxThH
zguTjs?@f7po9X7p*lVyJ&oOvM0nKrxrO_4?g02hcnJL1tfH@ta<JOe;g+ZXDZ@vAY
zT&HDXeEOShW3{l7`}fb`yB;(7ofT|j+04M&aOK-SMhqoGo*hd|#|%SyUW!SFj>sKg
zEEj~`1JYT7U)@JvtvdI&ZMCHI?}|9u$XPSo|FIhi<eSK&Am#%9%wF_q@7Y=YrWgyz
z_$z;DuA=z)Re#!al!4v^lhE&ihb6L=bQRt7@!#Jr9hfKIR!r%;!jx54Yji)m^SDNR
zA=MML7_69k(rf9vur!IPqxszY`vFWjV&+xjI}H=_U!<7%(9_DqPeudvL<P5xX%m_*
ziI<62x$JeNt}g;YU8rRRgrpm8gghEl+F5&K;M2m*r5;S651>xcZGNvm@o0hb!I>(2
zesV!L+w%9s+p#PPEru-KF;3^88~(CjmZ~w~{>-GI!+<fhjtax>`-uZ9+qV67mmy`M
z`cp&eLu@?230_Zg!nE7;spQ-FrOgr}-CrlRvO&UhsnQ}=aRhbP_#5{|>!U_>>@#Nx
z#@#)8hUzpwXe%OBjLTd$5l4LWAmq8sZYoZ8gxGwkjjczOkUSQT+1C2xacAS=dUN)t
zM58OTlI@x6jz$ps!*Ogwn+^9X;ZFnkKmG%qSSgOZd6$SlSXQcj%97M!TzL(keBpnp
zzqmeMo(YiuWWmC)D)~_*Om?>yL5RXXua=ViQDon%>?7pz%Z@v+e+ADe(-%sjG{E|~
z`813Bw^l}ct-(L~IeXS&9T`OdwQV%oOWQHMsIM|nwk*J7I^A>HJN?zCd70PSY33?_
zQfz&=M1IdCor;_N<#F4~MU0Dqp8<ERvbmI3ll}K+a;LH-c|PmyliTg6RHx!iVs-~w
zZViG>>j^o%d(*N{f~m|#A;O}KE-~<XWsqL|?UtnGn<~VQt<l>fx-pkB54r^;&9kld
z9ou8^GODpD@ic~?xCbOk7^&vhsMg=4&8epJxv1@#*`CM!n}&<u)4I}BAF`2A5cuts
z{0e{0iu4FMer2f$8;b21EE{boTeCPvek)vR)?|M(KCkZjrAZ)|{DnT+wRyg0#-ppi
z#Hy%8HCWfgs7zWepH#xdXt+RtA=shduV>V*R?17n@N25v1=vHIRgMJrg&j+eM-Tpu
z6ygSY{ilCa8_~$|j1t*c=xn^QKlF(6$OL&u9al)47xk-2zz4g>eX*%VnBR&0wO2{#
zXXoh6pch|kesV5uh;uqCpG2vkj$KS?{(2wu#C>u<Fp4+$mNi1dozKh;&tUl)HJIcy
zej1)lZbxGIWzXT6=Rts0Ly}9>hwDl1;<Qzn<kGeJjIXU0ed(8X*IM$k(zdmv*N9hM
zbs|q>B%F7I-W0I$yKxKOXaA4{%zSID;Yo#}MM~IQb0+7Y;)<}snmeyivtN9;XT`#(
zzPFx#sabeD_Kd;W@$*zl*TmNz-HK0ryB^#Vzl|Y#De0HDfx$7}+Dz_<QrxQACA2iv
zO)gb)z9+w=>|6224(Yw{v?y9P<)?;|knru*-z!+uvtf91y5203u8oiKC0?7&?@YF$
z6y5Mpd{UkGsl2IJhx3~^VzRE{BLnRtvcHp~-4IcMD9L$MfhA(*2>iuVtt9P6l#ZTi
z3<?M>Y3Sn}hYdLJ_aBJS9)}cfg_)qqAFgY#6#o(cQbrOTRRV4LJ#9H?83yc5`~W!S
zP0$q20yINQ(zHwgE!T+hafH;U2S)-KB(%7A*aIj)UU~cr%mV<$AcZk)T8}dfn6{mW
z4qYN{B#)BDAXSDv1%a4PaTJJM-RnT~;T|JXQA1)>H;Vvg9T|{;0ZDC;6sRbTBaiu1
z3d<dNJLnWAMNJF>m?0)wFrXl-U;>1?0)QFq97CpfjAiD*gUhgB0L81*j|1~1gQsG8
z=|e8YK?Er(k_{lYL<&f;16UD1)n0&P3$$5PmrUI$v!p;&k{SRJl`^q52oqrr$~8S5
zA|KNRQrl5Opyml$9UapE<Had}ifdvz36c_IGBJuUWd%8011T)j^TtLbJ<(aJ<bO?A
z5RphFaJwWq2uG-6#yp!R`e^}(j%|uq_T!u(dOsvNWg@`C0LralX6;m}ep*wJWc@gT
zk^zLSD{aRY$Wt|-TT;{lK+FrCilh$M*HrkQVyz6o-R^1m)S4_rf$P|h^FAS;4oAI3
zj3UB4q>M>owsjV=8nMSkOQdNvl$mKYaB|A5sWe$q)IW3Tr@PvcTIxiU-*2Fzn!sPj
zB3mrgVRzeup7v%jkb=IHqOEm8szMDOaPF!NfuLZxuDt1}xWI^yr=e^w7cY=6X(1&0
zkBcH{=K;(z<P6JCjG|T1RU3kSmiwRZ4F?V1ru78Fz|RQf#Y#gQnI1a=BsYgdmC6Of
z!aW+nMtBw#7#(*qkt7U3bcz~+0s-Bgjuz}DhBQX2jvt}#1iTs13S+7iEJXnC`u4#z
zQv4VL%z7Ljwoyi@4ROT-P3j@~;&Bq$;{B=g<J00H;KPsfV9&t-?d1E+LoB`Y)Z#;A
zrETDRLGh@mNTxQ>5%6A7(1Y^I!%U44L=c!fXai*$pr;C=Pj8gPG6N~<mB&gHF*TAJ
zsG$R3mV2at{%<u!gN#*nPcKpqE7!|hEPi9Njs3Xk49mh^YYk+?og1j5ZCwo#U(&1^
zJS0k$KGHu4U3bh)@rPwc-V*3VVvC^-1FzrDwqErqPVl}^*TGKwIO{5Q#%y2|S*;D9
zTjl1OYmDe#4a^o;7%f9=XMlXuClsq>z$g-Iz%s<uDHVeR1^W?E<Ng79Gh>cSavO>N
zCUQtor$e9zpnvqaqw*&huxT(>5wN;NDww2<{xb(0XF6A&Ghp`;PdZri%8szd_knZh
zZbsXI%c10hTrT>+;2p1tPFH3WY$JMf1CK1#TXA<1PnFbZ;hiQ|)GDVO$!nRzd3pX5
zkdz?!k}~ctH2bko3ZX*r0YWb?%!1`n8&REQ&vN*UExr`!rdz!eXl#+JQ+S^^fmuO&
zN*)CbaV7Bs`FQwtF$%c!1Kkb<6&QFK?V)&K8q>=O0V^LH3lO9t4Y6p^EE&-oBRE+<
zVy4=Mkbf3)Q3ayh)ZMphC_^neegsH`XMAH|6j~@{d2iZClh5{dQh$0!>gP&QYW@<9
z055=tk<>KwdQ6&loM#{^27t4vLKQ=bmrRgA&l<Y56K1SnlK&EzQb7OJvZn`aMBWZr
z$(tCrc0sV30)QSJ&ZADu(Ya{|_U|ZZe(12k&O|mA4-y2vAV=2#(A-EDtV=E`816}j
zP>GI&AdsqI_f-2=fgAp{Jo&?FT2FuRYftgs2TUa5yLyXL$Q!`eh&|_m2tdrS7o&0~
z7&0(>0Ss(-4ERTJ0_3N?Oe7^)2Uy5O5?pf?z``id=^Bd}YSBBB(Z7lPEv^ryrbU>#
zrM;A058a}ms9!@{LF0p<f~q6*lWr=9{Rg|X6W=Mi9r0Cb>?@KQqkpyE?rAC|SR;ow
zg69}o2N8~%h{>`mm8x$M1~M;t?&#%-V%Ob#WLJ`@H|k$6GfoZbd2Wa)v`oH#NV#j(
zM7kjBx1hOuTpr}q9M2=SBAKF>R8R`v<2rv4(S0^O+7}KQ(tFfh8~tD}oac43xXra&
zf&Zi+gp1RW)u6jUc5mMy5BHKo$HQhLTBjHc4qd5V{_{1B#2)R<a>i1%AR!RZpI7?c
z0zC-vSL+SkCD}$Ezh<DerreBj@ckaGiLgqzSDR0G|IL=A+qp(}@70sy^U&!KZiz=>
zD~<0>8CS%oHyM8J>~46x_(w$QYo)k^&VUZ)r`48M49-fSUNl%?1=`7`<rU?*-D3=P
zT<S|o+CtfRE18p#qtNfn2zcqr{`v7KhE6fUHc?nzL*+o+@Wdbzf^H~w-rGW~MOpF`
z9i&!zdX4xE`TY@PDj05g$Sf$Y#z_*pQ~+D!TvwC6L6dL`^nGHICg}9ukz>I5<n?Vb
zo<tq#k@GGV#w}gRUQ?GZd<#!>-ph6HOXHzepx1b_lyT`{4fb`Vkv4Pm4^xBQnX?g`
z`3)rnqqJ8~660~kQ&yWMxf@yCO^muSz^-3^=}wu0u?nn-9yJ#@$Lo@KO%c+pGEhEV
z=ew@>kvTE0C7dmr>l=q|$LQP?_)3p$nqfVQ=Pt*Z*JK?)f4MuYq;hSs-oSGg0-)jF
zA{$5Ka2CJBjNoG8<2a$aHMxPC(%xFW2^%lNO06%ZZ;H6ShYmG;P@E3+dE{Y>0JU1N
z(u)rZi=!9V7uS=-);~>9?MwZBE^a3pNjIp(Ru_VJc}*ZD4}*K&0Zd!Nu+4%}j;RU{
zRT?Mm#qNKv%PSZ7*@75P!R(Xjnq517GKh@T*;?BhC$a0`ahz4t24AmX!H(6oiCqB8
zX_>R!kRgZ6ygVv>*jK>{8j<JKD)K)0DrV-a>bag)UFy`vGITP<<`m^T4HcG2C=_N7
z3U2cfGO@LaNwc{}ZRx%HUNFCw1elQ_CeWNe(27+P15M?Yio_;6oC#f>!mp*2j3ImL
z@_z<Q99&*TA3vs2r>~ui7*7tvS-tQ_f5kV!EWIx@SAOb=-49!Gs}?Q1`HH}(2Gs_R
zM9xl$F%Ks5zNquuTcj*|S#*#4Z=S-m+6KPcg_E*uH@HOabyKdtpP}d=y5i5L&3lja
z+!-ccsf_pjuIkO0sA21@(%GBQ)&gL($8>R)Y;K{*J25fa_K!x7+}WVNESdfsF|6iq
z`VM(|>_ud;+mHW!KOrtH;tpnTo2RQSt&?Q*jzVfKvHC&<Su57ELs;i!rYTwOYVgdW
zzjA$q<eW}^nBmD(Z&MG4fAE~DxdMgD7E`w22Id7`&damEv1mQ8L2ES63G;@|3hU8#
zc*&U%KWx_c89(jitsh!fCJ@N26o3yf`@46FHR6sc)G9Z=u(Xm?LO7?kbwYWP%3iaO
z&XT>3*rRNs?RX_vAqjcBbivxruRGGT^7GqTnN;=##5?Cvb$Fjpx>19b$^05R`Uu8&
zmKxuc_fx4N<7*{#GrB2g))sF&(?>OUoF}_RSE}2}c9xM<{0-tm?mSyNLMwa^Q!8&C
zK#f;~I2ARqpwOVs1J&WgHTKAVLA@Q1JpV#AnX3ssm;{EAY4j>S_d(`-E^S>gwR=<L
z@@IDOM7b@m`Zp0<0e1ZHHndi9Ylk!;w`Ii=;rE*=9&~q<8|g-qb(X&y;>x&x`Pscu
zaXL@+^-4g<$bnViz-9pLOpUy;m3{NpBN<PueC!AQ!xL4NxRy3~Q?q*cX%ZG5OB3Yp
zz}57UGf1!uSXiGxzkXTUffzN(li1KCYYSjqBVy_M9TBwW)g6x=R(H)3WPW5T^i=&T
ztuwu!|F}7P@Oy7<el8Lx6C1j5_W>`!ho66N=OtBSxM0^r2$g37JAL48HngFelV`$D
zuika_cm7J-+^=N$<z>w)p^U}Y<CY$k|D)(E!<zcvFg~ONDP<_5OBg9FHA1ANOBw-b
zkdDzJAahI_86BesA}t|EgCj;al2Rhl<^O+vuXx8faK6`duJb(i{rR-~UAZ2fFDUVV
z6!rZ~R-YvqWR|Mj3EYfoX~rJj4>I;kdwR!e00u`N?=7k5&r<dS2inoCNapDg>D<Sm
zp6FQ<kFB<IIreVq?=3Een@O<~QTni+Eco%taw0>Ds}C|~<!QBR)z@e($T7WL?N+kR
zXq48b#^a8EKCa1+8~Lr0``ri+4X}f&zeo5X>kG}%f1AJ;CAL+i=#qDt<4PfrH_MdE
z4NaxXH_ZwE3?~`Z-JPuZB<YDvuxT?HG9`*Ou0!Sz8)WYmKVX7inS_^mnml~rKWzV}
z+%B;gp_fbL+E=*j9!AQE^<G(i`pXNMHL+-1e0!F=8_bbZxWHc`1-=fNdtfBhO+NL$
z)a{4%h<uv0$?Kgib9`f@z>}yOW7RFfmfDGSBkRH>@bR0bd0iZ$ME*HbvWwTqHjI?c
zXfUfm|C~PvOJO0%FDyUhGyj}F#=Sw*G~RRw^q{+?syL}Ak8L%2J}pWNgHYl);M}4!
z-wbVy-0PptauH&-k*b_YB(pWORxgLX)7oanE&3Wij%fRa(ExR_otAusI7n?wym(PG
zv=Lb1P#m4x;O~L5K|QRn>ffvnqEmmXp>wT0JkzdKyi5H?AuVr7>Tq^SeM8=;LKhZX
zQ7gT)fCz0O=4W1i|Hgx1X+Wq5`tS6Imb+XZMYBThX<5PKrfj$mM0eX%xhf@i!zp69
z*D*sV=C`9NmZB=IcAc(>z?6XA9<70m)@lzwbWI>z7U^PIOR-mNbBQ^@y1fh^zdzT5
z5N$|ulA%#PCB(R!E6mNRBSp?*UUTcq@!+0`K7FEZuxN(GmD!5!_3Dc27w^fb#cd#>
zJf|TLDk@i+a}#N;vTxx%1;jd}ShmOZ^RsgPSZ!;(y3OXc*HV&Mgl&7K^7H(om3DtM
z!`Q+)P9dizXN%+_zL04P)uX2?3g-36gT$RwSuZ8&8PX37)Ni^jCK`~4_f`vA@|WfD
zB$egeAl^-2Is<52x!zYsH?Mv9UA)8(m2fnZH;^&re$nW<)7Sa9&GWaUkhl4kb|SI#
z&T_e#WmwwTK6UGK^$Uv1j`-ii5z-&v#+8c9|9lg*jmQ;8cn7^3z8ckYoF0^{$(3-~
zw>!1B7HlKFy$QS?(das@tbQe@nIEl}Wlk`X(Y1h+wxP$~%Yku+O<!!!SA?Ndq+B~3
z`YgYs_GvK7UgLM4YdtvF$xd{Y0{3}M`8}&)S(Ae8$<8gNP(&l`#qp7=>&w-{_XJ{0
z3jOE0_RLE}jx=|>zUatI*T1T{JFjTJXV!Rrzv?w4g0IdcAaU??2R-85j8lFzr!yUj
zPNL3yXcT>DW~g(>!!=nu{J8CLQitK}v6;{N9A<*c1$yxmOI5}VYna>P4Ii!hhiIS0
z&{oZG3Cs76*)OVl+Wq9|JkZT^H&zO1KEjFHSU+n>is$Fbnax|*ol0$jLm6MYIUP~A
zcSnuoArG;1#esrM?(L>E_|_be_$X1hJ;uvg5~XmV{z{aXt$Y<leYw`|sx#v-T#$8}
z6>wAsEOK?Ugj6l=G=$y@40FTkI(d8jWg|!xb2z7?9VmCbW(HJ4MmMzL$$<Pim?%w3
zdi0q>U-M^)y{YZ9EQYCf_HN8$Qzaj4LV~G(Kl^>BN^5Q5Zc{>X<3xR8Db{}X{xHBM
zmNXIj+@tCuz94vJ8uioT8bwI;P4h&WbFy!9DWqrg4RL+CM!TbX7~f<E59*#Dx7?7a
ztXp1leU6`0F29pc!cY`WOs}r_tK>|Q`QYa#KR#_3ZbVw{c-$CL_GZ_)-{WJ=<SS<3
zX>YD`YpB;J-$3TN$#=g%TbRAHNEMu`)Lb5NmJ<`8B|fIp@$SS76FqvZv=(OD&AdIg
zb}jbwM_US_q1-J)(2c24n|@$~74d!I)zo2qL!%1vyRIn9u(@e2<eR+Kg621#Ws?m<
zS2D!@>yL;ho`OQkX%C*m5w4P@5yiu>-Y&l`_OJ>oh3-dVjIlZEx7&P=5OcM77D~2R
z*{g(gEU)H0+d8QgYPXE186WJ0?CwS!7Ff`Zipxyor)=E63aniDgIIWPKf7PoH)lq$
zRTW`d@b!3Uv2l^b*`GZmzjnCSUgDsAvTw`QIG*0OAD_IgpKc{I&lqnp#Ko`RYvteg
z;f?#33KD+yL89}jTP+oJ@se2j=kH~O7hNin+y!j!3c8;zh`I0xb}25oHMMj<50Y=_
zcKOPM-%UTx;$?q%oy*_+$s-cgUg0{w+pYHgVkuzv!vfb<OHG}MaJT&QX?0D1q~ISI
zm0N6P-VaM!<Vm&p?hzzlZJOU`G@CvT{?46KdbGg=t$nSA5fwu*v<Qd>SfbJz3WDI;
zW~tc~44tC?PM}hBcr&+}SD=@(etl}LI+pp)ZXHYv#)WOv$0%tC&IjMc<&c?r>jt->
zkvL)G@-frJ>bFfjAKds#oeEH^Qxu&tITS%_NjxtXCHJXL%|jtRA|GA#>DibZ3%|?U
zlYGkmx5RY1N|M3@q8Qe1j+>~_E)4x7pMPGKWq5lehXhV!)du!6PS#QV%>%80AL;95
zgi=_kP^E%yv4!q89i*&_>w)mz*bAMwTp7D$S>truZY0y>v1n=)Y~OZDf<#>etUcjf
zJq*-o>nmTYwU`xgLU@ua4;m2hUCe5(Q|KYHxd6)nYDF;%yup&_I`mY{wA36nA@1Jm
zC0dddNN6@>d}QXmy!#OD9lLZaV87|K{imAH>`1<229-kb<&R{pTe+`4I2+E$BIX|u
z)BLmUV<#YO_4x>YD@h=ID&cyvYiL&7^q5}sY!5vo-6x_%9GDsDPL;O*jmpe%Ouunm
zV*LSS&rH>gbenKcsHbJrKZ!JDb+L(jq`*LTyIKeXc2MfTOsz+laHxq{#H4r4n(fs}
zV{p~nm#6!Mv0Giyg^sn46O0j2V^asRYGxjDKfYAMU+vb{26L72urzS;9c<5k@eh0H
zaz7Z)y>W7<@oukghnU`#2Fp~#-EwX2=Syin0xv$2*S=g0h3BRbhH4Ug%y9SJv!n_r
zV~wNR0RWj)Nf9OezE3}CQH8_LUdI(_TdVPx^VFuU(7s^~w+K(O)_rgOVdFN3B!uCB
zy88|FK#cv!zCX2f#M(Eq!F=r&i%`-6SouV0T-KN8UsF`d<UA@CMM&+UW{u6{+^YIH
ziM-yi2v5b>1^no)R#Ect_FDDB`3pRj-Pf&m+~^RS#>nRWeYT=+ywGzsnUFr|aKry7
zKnDMCt>LAsTY=pEWR}(B=3a>Km2?HJ%t~E7B=aRpKDsoQS5ysN^NM&(I+I^B(C2q}
zNmd$9c3ydj6Y~z)D7?n$zOP6RuYzB=k(8y60)h6SIh>+Vc(?2dC6_3}qUziGK$Gw6
zUg|WjWL2J1Dvx$=5ayWbN3?Y-W)B`-8*nCh<~`_MyD`|*9=!6wef7)q)=Tn=u)n0P
zTcxJCmRPW1<9I{Jub%X2(E((TXX+k~_GRt+Vc%DxYJ13;(jXs;zCW6<<Y?c`(Com<
z08v*%XW9gR8hOT)Nbf^L|DLG9tUyqaB-v#%Ns(Yw;#`et?Vt2`<|=f0N$H@S8AzHS
zBs`6(X0=`DQ0vh==Ya`hBu}(OnB${bK^DIrw4<*%LwZ64hVD@k@zQt(#wqQxx%%CN
zsjA>zxLtvM{N3{JzoixlPAcXWBt^*z+EtUJ&x>JVS_^<RXj`J-j?BN`6|8^xezLNY
z;>%gv&5VRN3x6J)8f`=*=ou&@n&YZnZKWR=gp5&(`(ZupfCR4JdC`s{G4IZFGE$E~
zl~+Lqkg}Z|sLS9_#qCKVsh~H%4pl%*<GIeG;`Z{X0BKr2RsZlmazvbX5n6%4mLA8W
zj88`>f_xR_0(!x=0FBxap+gdc83lvvP$A<=Qq2Ex5%L*$BYo8{z$6i5u$7EZ6yyPN
z#red&%r3I{Z6M@YBvlM3`-sLr!U28)xy)(tC>H1elgpeHA`L-1I7t36J~}xJO5oee
zMqe1M4jR)YEXxlu1d&8*Os6t{q&rUwkpQZ?nBed~*zz`Tr+(XD$K;GsK-u?eM+3(U
zq=Wx~88l_a?yN7PQX@|R6Bg~EVt)3K#zZ49FFh}ezW6VzYrx_HAfAC?wjJ`Hcq$06
z3j()6Rj&v4FS^ttxcLQx_G4IcK+Mip<6~papnpIG8k0}B0AL~d0L-==LP17>oD#&N
ztky21AVUcP!^cr!0OvxuxG%(DEI6O2k5U#Rnf@WNV+nwKD@{j+=!t~j3DEkd#redr
zU~o>YqICZC7(w<G!g4Dal>->=05u&Rb)rY`Uj~sk%$b0!tFttq_)tAe8^r7azc#QJ
z2ZD{nz*Er3w#R>jg94S+)!Fo<^8@lhtV5{M9j)G{P39o$!YmYT@F)PT4j_jzLq|6i
z-$wUBx6na_t5U3*FR}s3^tAzfM{24QcZM8=7jI-f5LU$d0Z*IiI}MPbbvH=5#KZO2
zz16_;zzI2BrO=N)Q1#Zh2!l3LF^#|V)fTts5eJo`U)W_76w~8CBpD4n<}!E?%$cVh
zYyeWgLW=NjrR5Ci!~OKf4D5l(a0!6m)_%-Jh-1bv|H`*pk5VUX0hrTb02GAqPV@>8
zyGFc7(F`sbyR!u_uipZpRAP3>Nf8Dr9?QKLh`DhQ`$f!ZP9zjuyoEekM)@lC+>`@Y
zYid^zG~Y)?KNk-C0<m7ElOh-t@EB^6m`6T9747{8qz=p{Y#>ZgQjmDeMo!7QqqvO#
zDV-Dn+ZQy+6P^0{Y+4mInj}>(DS$1G)VmX<7NJS)dUq?4Snx6P-IHPwHOrG;%ZZWU
zf!p0r8%AfP?n6s%S>PH?b$nKR(ypYMKbmQqUw!If>gK*_?%NXI*qR@%)#eGT#wyE%
zYMNv~#5SMFF@Mtf#0epSqhH@qf0Zk<l`UgPYHpeGg4BLGqv0u&es*qsWZ=5S<Y_T!
z6hbEz^lwE|CX5$YYp`aKL^7Z5y+~?g_k>B8+GaDnef9MrGrzg;7Wzf}FO))$OceTX
zf3=ZTnz^p`RdlcQR5zu@sGddzq-N@m-?|Rco_14&)+ejEMd7KAtii|jq)A`xQSm3s
zYfZ^tMRfYLf8HuJ$BZs<CF^npRAVhRNt&4<wGn;6eQs?ZxVhw~F8hL2#cQ8rl%LE(
zTJV!8UgyOFMW@Aw){sRghRI2M5iRzD)Uy=$o@4dYCf8BK*ghsjd(qLrc2=WK%bm$U
zgQd3no}UUuk_`Bw(fD^Qt|d;!);yVe<M%7IZYM6MwLLFN1ksgVGX7O^$2&F^uP`_r
zflG#=30vv^aP2FnMfugyY)s?GJWWa<eQyvBZYk#Y6azM}OGPL`ifX|3QGn-@zTbfO
z5m7X!xIwmuIAt5t$G#7!?>^8zmq6YP2jqIxa&|o6L5Wp6yXzv&wn;Cwqg9ViHDA0b
zUU(s@IQYW&LQWdHNWHZ4m+xw@SGOLqD?#!)X*8lQmD+XXV;6e=6D0*7%nTqsp*yIj
z9=;KrCpc^dF8joTYJJ0zhKRvBZoZYigIPO9Y*#b?^ls*@>u#uQ9qD#Q&c_C)(@)fM
zby5AAFB1Cm&vAjgtJ*N3w-6`(T-DzVt&iS{tN+nXQaF?@4=O9T<_^|)O_*-eIsR3Y
z8u*0YkN;^UNV7kI?JszZGx(rVhdLK@A!QYkB)2hFK2uApP`_B9z~+9^%<<bhgILM`
z`e*~4X~LvJ+xVz2DESvkCZ=L#{K~Gj6Q{sI*)lp9@$V87TZ?KsX&BaM{~cY)a{7bz
zUbuF>`qwy8RPJfrW}h0@NqJDYAN6b6LDI;EY|mi9F{(DSf6dz`j;WkWeUYc$|LAsq
zzvp;`jQ#D#Em#>!Ldrv@U{*GC<}Iz>!Q2P1LLM|-mrs`}P*rgNsX&(&o?V6StxI!+
zNJHikyktsJRIl1JUm$-n58<m-D|xp9Cal=?1BDz<rB#myj|M&u{)WU?PJ50oA^(V7
zO*gy965x1^vv!%1gdP4grY5#%%YeL>RFp8kWPBEH8ufnnQy5BBBa8!(Z{g8q0bG~?
z<5h;-U<>cLN8jq$lwweH{{#7}h_2xtKDuu60~s$>srn*NFV9tt&cQ98%)lpQuO85O
zN{!yBpBEN8{+E_w*XlWF2l^#q-Y2p1jR&9F1Tnv)nXlc*Mk1%er1G7XqIb|uavGab
z0%E@?9bamG@YC-&f{aL&j!_0UkYbG6SsbYH0|qL&HoV?luVqSxrVn&>jkxOlc6#}v
ztN3p70P}^!>*9<+dP2yaneeWOh|YJd0sGyy&vg8I^MD>|ve33YpwXqd^{wn7ZRETc
zX_B?`?ePfN7Qpp$Wqh&MwbnMG6nm#7$vt`Uf1qNXnT9}yZn{4cpQZU(RJ=al)Ulse
z9~y3VBYpeRZlU&a=Gw;ZYTk|L(iIg2MVedje;N@xW;(kvRS>~VTsfRxO?{w$(WIXb
z+HBcM91Zw$upc;9RUWl~mNQpavqDFIPon>MZx3gFq_<T12SzPUuuUbbYlF4KGddRC
zKd-=3h!EzwhDk(DvRnF?SEXQ&l$MHVmeYC_O|vE4s*XZct;iblvIvu`L+C?7>l$?p
zHP~cu3`VG*O~NE~p=!a@=;6fGqfys>)MeYoTz1MNLroRekBTKFn9J;o%6o5oU{{l)
z4+v5QVHL>7X%~mO$&BT~0eM)O#puQ{GRd~{B8#*_TT>?g;xP+%zS7SC^|c2|T>GX}
zqBs^IVwo9`4EMEKey`MoYQvKydW}Y*Pr^tXf*w(bMS20rZ&ZptLH#)?O1d}LW9Z+N
zA{i&wO!@L#zwPactu~;F1?&F?=OBL54YpmUA9a1^<*k_zXArziSHR=%9OxYJhhc;L
zQpwWK-YOjZ)Y+E$_geG7r%cQ`q4%9HuNmPiL_Hxh-la@kmMrgQTfF$&CXP4ogfT~U
zN#S?<sFz3A&CE@HmMhAD{ws*wy4m*vU-+~H{oxHCOODEw_rBIE!Y4UtN~H%#it;{<
z;)~<{!6p=z%1T*VJ-vIM$NHKgwP^UNj>X}x2NKhX>8ah1Ze0(4umtkWzJcQ=r|`3!
z_tW<fgJ@;n_%`K~mrZwl+)7%JzArOGP_AZkgv=ReA3@Dsf?`V}F$XPR0AU_;xALwl
zq>$UVToMs)p3{+}e7331+{YJ5z4b@rv~rM}KFrl1vN2=~@jM-IXRW588U0ZCM!DTM
z{;mYZ`6-o)By7BA<(KH??0wqkY{c(23Bi(-Qumy;&mm1%Yt$4IWv6j;@xo%6T7o75
zPy5Tq1cMo_-FqmCtlH~ucXl~X!b#m#_ML>Al2tf+5U<@O*o#I@O<Y81CXe`qCew#5
z&KN|?O$QQUIN@X8{Pc9e``SM$r+dC>Rxz#9O90Dy(=&J^&2wNDW%4{+uvufC*W-)#
zqyb^u1PU0*Jo|hD^FM12OzYbmq4Ycv@2pX{`r;;748bz)5C!b_wbYh(zKrIJ{>3YT
ze$^y%zSUTC{o$nA_1-{nl4LW0rL2vpv<}fD<ndD(PV6|<G`o*2mTe6v*$asMy+Xce
z2DdAlox`zwvh^{07vg)Mf&7aNOV?J_&LO;y?nj87HP_w#MDI$35gN+8t2r}){?Ope
zm+rg;RY3$K=$9<^4S7xe9oRfGfZ250-h0jns0@##Ob0uwBff8B(GN#Fl0(dNL^&!Y
z`<_;r6%<z$dnuJ|UpI{0mJVkPnE@}t7gN{1k}JzC?pOFb)HL}r;?cE-*0x`Zy;R33
z(spq0^wyD>C%UcEZAxjyNrQvk_su)w1$A1xGivKmG?721eoYr&($lT~gJ^$koJeRH
zUAG=~6nO(U3k8RtpKZhVW-Ig-pH(TnGHIJV>Mk!9t^d%nfH;nqx4CZ_9Vto-*Y8%q
z2HU*%#O1b&LDyjwg-)V>Yi_g)J$Kz&CZzRLg0&l)DgTQ7=DD0Hb54mbSSBIGND~D-
zO_6maO_z#a?ov^&E4-<i6`yH%`?E>zRYyG@k`!3oO@!p+%Cj_vGz@S54`fVH+BDQK
z+55^pdh@Nwg>l1MHhCkJEAoK*T@t^)P?^lHqL!cxC3O#uJ-oBe%@2P-e!F1rp*|_-
zt3gL3pFCLVisJjmoWpM{r%$9GoC0@juzt+C$7aI%8*$9~{;A2?n7ZJ|G+ROuBBMZk
z_^32t!6>3`A(5S=ZENcwyXl8IcR@?bsPx8Z#S>n^U4F6G1x21OP+q>vIRg1KMP(HM
z=g*`Dm_!cs>VN!w5X3e9YVqp^jTEHPbtrv(j67d=9g)fU!zvCYGjU&aH6D!mUKt&Y
zbC%PLlUg;7fQpRpBD&c!9J*n<Hw%dZNvAAn+CT5WR(<&2XyUiq-ia64`Qn~82r@Fj
zX6EfIPy1aLlPQnRa1Qee%C-f18>o^7wwB{NwO0)5l`N(OV-0Fg#JOe52`OmcdgTok
zoQ?buX7#9N8TTVg6-1c#?yM<d8vi=$tSU0IBTFMTjkaWMMV~77iYzrf<Vl&YbTtIW
zaI&;*)gvb3_Z>&M7bB-E(rlN01w8&DT~f=r{54s6nCfzV=~r_?6aVSba{fvx)AT!y
z?amJfU8O=?;kUW*b~sQC$$i~yGFmF3if2*<qoOgEb*yc#4|ZNkdZxeg>3d-5!E|2c
z{^&<Xws&MZrPWu0$E;}%U7TwE+>0sM6CLkn@#%Cg&EgNu7~b-KXDk^B!pf#>nH_$d
zK@Ya4$tC3fbuCX46Jhn1`sKpT=)ks)4rNs8I#lNF1L!(vPW{Fg0oVhnJ28yEzhs+e
z*ONF6T(|Ezic6j?^absh89By36tM3}R^1L*4z4JXvua*{b!cF2mB~%r|Kn4oNZ*$S
zQaFcmXyo_7<TfTRH!a<kWn=1a`7}bISA<`W&{i<-;HC?2bS6hqdoX(}Ui9uRKg*hp
z=!@eNbA}IP4NTjJ;h3nA-?7Q}(CBQ@6}5ZMcE9j;@qC@m%`12m6*|}%amLTG8~Ans
zetKZcaYVUq36eySw)+`0pfu-e<<x%8Rc%~9w`n(dlQsQ$O;)ce4;tR^jpw~5PeM_W
z=sUZX*1Aj(Db|HMb41b^At}oeTaaUQ-=@LhfqN5+ldOt<y0TcJblEe$f$Iw4ISKa#
z8qv#&s(hw9#LkgvI&iyEgef5?5ynTaHavk<ul<Z+f9NyPMu9Htie@SzH0%|LZ@EdZ
zR^I-+E|C&&Csi`=L4P}~7bY+Vq&C3u^`44|>UxPQncopVghj`9f(~7gHAyin+rmMt
zqh8r(oa!TDsOv!?xmrmv1-`^l+UO^P_25UQ@*^fRU6auRU1bk(B|7jBqv1!%cN`-5
zr9~jeJwJ~xjmZoGQhqzZ_IzHmZTOWj$l0#9yFfq-9tya3>&|Sx=$QQHa`p(nl)-xk
zhE3wV3B}Uf<&jvnMS^mz7OQ+umed_~^|h5Q`P5+-BT2ED2Em~R5~i}2-kQ^Fc}Y#=
zh#*H7DGHJhqk+fKhbb3$TB4}@>lLi~1>8txpPbqrJrqbAHNtlm{cy>VENZ8V&I?#z
zUQw&M&)58|VB!3e)AU}hF&M&3CQVZH3(qq*BOpxd7Cea34yZVaZtoxVjrsU9=8Hqt
zVBP*{OTmRqw{o*ffdC$!l49}A`5na}IL|Fk>X>xfP{1FSop_tI56h3w3t@YLD#@<p
zNQs)xzxMd@KhUtEHv6Pt|4ltzbpM!*2lbp*?Q8u<3T)e0s4*dkAkP(ZTj_E8Cp@*g
z$|5?_*Q{-nyknlVHp5<-utch4-~$KPmK;4Q^Me!lz$F3Orw}=9Fe3cnAni2x?1}lj
ziqoSE@&jGXY(&4z=((YIchxuNN?xZ=#%FP-E?M@ulTL^(naLj3G}Ar(#s(qzzl5h%
zxnZ$8J{^^ug#)9So^EIlPo-(+PC7!j_Jj=^W#AjB3j9?m?No!=GkEWX0Dq!K`2F)5
z`_Vch(ICX6lRqFDUNQRCRP$%z)v1lx7Z-3;vQ!zjA5`_o(kK^N3jy9?qvI8I7nQn>
zcZD=~8eI!=Oj47LK6O;JX3z9I#;q|0ZZ%5>xo@?8glKG4>9oA|^l^)B7O0Y1Yu^@f
z<{q(l`3f>f$XzJPbihWalQ26#GLKIux?9zqZ7Oy@o$w8l@zgBGhzM%3HYVXO>9+dD
zfLC<Njz$#2K-K?1Pv{ipl%WE?r)9(i?>DouPs-EvvYkMaBD5o)VI5sGCWK`b6p*`J
z1I!hFUPHFU<4JQQ!K(&3ouW{yPT2_ZBoBL+N4Npd37zNCgQxQjhNePQO7X7~Vr3ZO
zxP@EuwEvAbug>#y(itpmB#1IfZ-e9A-+z;(>~Db1=0U}Co)edyK0-a;-WsLHK4}_#
zLyb0T+2_L)Eogj}f%5ri6nCV`?CTDF6<+$j#!9Erknw=Z%SX)2U{^ytfs<VzBuQ5!
z*6wcpv;16QzZ9RgnV&!Zt^^s5xV9u%%k}NLUdGUet$Z&G@v2a#FA-y&kgies!*iB2
zZm}OwxJq%<O4s$`uKmqk$oGHzU;kWbFmVyXJ}MiGYs@xPTy$J@>$wG2ne*y*9JtK6
z&7A8A6pJ&D@Mlf>zngqh+}6w)VzLq&s!_5qdgh^ZYa(yT-wPv0ehmAQnj4PD$`(1T
zI#Bm$jli<d#c8+Hi|&{{?+YP0T+Yyo?DjHB)-A7garWbgVw>hcJPJ?Vj*fKmeFd6U
z?P#qZj59RXyBL>{r|r#)oLy`0?lR!N2v9ipwq^&qljbtaJ-*icf6lDt?-J&(wJ&O(
z(@L4FpI~_m8;?|a2NxSZ4nS6?Y~l^R`{l&Bc#j#s0SEm(R%>&U!me}OPN0tyOwHP-
zg(#Xlb!0$6m}f}LV@Y1o_DZ{-VczqF9rRx#ly&Mj4>%VMtk(}HysZ%z$e~4h40kXv
zGKw|_`CsWpkV_RI^+cNYRHaJo<;FkSD^eb08&}@rm0%n=-~iRf5dn^3qq7+?vyrBU
z2aPJfTzLZO3FkcOc~7*d2l4r8nHh(&_N?pH7L~KhDixX%;M<ezWGYn{pW*rw8d2Mo
z>@a>Ak7vLC{bboS6sVAP{Taji{UAL7dShDU+!(Hsx?B74>)jn=?xT{Hvc5s@z`wae
zGRH;@?4KI1sQ88EVzpnXrHw8_PqCc(pO1KAOm&hEY@3ZhzxR?1tZa7vF^&-@FL7<K
zteF4Jz2`|(&IuvOY1)(?z9V~VrC_RC{jTooQEd6EGUw0lw@_*ZK!hx2iZXIy{J?B_
zos;dnBoeevC_(xCjn3lKSIL+Z?yF3dV*6o++(qFOv`;CI_y*Bax@_JC{zaeUT4%p}
zWJCh%cPNa%ZHpkMq~fW0bLm@IW3`_n{4z0}wwEs%nxi)>-q}tykC+q^ruW3nBlV;X
zwH6SQJ(>VaI1s=ZgJkdqW4w{}+^9+WJtgr-F;!>4t_RW+bsp>llC|~vDj+abZmN?w
zK>Z~vLarf16baT)srE^VTzUj!22}M$z(iOtJT(j|X9xn5OCPGi6~VLzYSTdYxv2dK
zK9UxY7s~1@g0A#}ivAWxg4aIc0m=a&W7JWRx{Bb_`Om^gU!;%&S&O84`>_=K?w@!&
ze2icoHAx6ungAhkIi?G=&*gw<wZ0;0sQv<mcMZ9Y6{gX@Ld!6ilkjL-`se!)gN|=@
z?t(zq`2TJ=9Be<20LhR`_hTWeenrwi7`Pprc?BeS!Q}Gwks=3buF#S@|BQ0Vc7Q28
zWb{Aw0gpMz+`9f#FAp4KIKwptmD*Di2l<GoN)?|2?nr_g=N&~k{cHfu49OoyiybPG
z;WIF#DZP&gDGbhvN5bnnPTmpW129E-{{vZp9zStangBD{3bLQ(hiQW&ErIWs<&1VF
z29Q$klb<S&2?=meCVV&;fG-<(YiTIn)0mFJBX6P2BqFL2=Df}XqzXUPUEp@n$+8p8
zcV+y0pIG~<>70Zc#j>vhXy`s|X26j_#9qW)r`ApcsCHP|#(~`NMKL7*m71%$E->AN
zju3MP=QE8F^zn*mmhz+OqY)$!B0Sy)x+|>^1ETMr{#di4Da}(}1df!!vT8nq0sIi+
z5lS9#QIaN<J`?;chMU(5N}vGjFWO15kbD7VO44@rwT!YI#YkWrt8`^>gmMP;K6wN8
zbS8=VkSmjI;8#>$7)fq@TdSeMP5^K`0Lrp0Nwm_f3+#GKI3Ji4+X0vfN_Gf_O-~s2
z<fk^Prp>lGVFT$$I52N!09GI@yfRM9fWHxcUoE`e@3fczbz+AC<fnH*cvelzH6Vn|
zh&;hyZg`>e_VcJ_3@~ZWR|K?~sd^yq9kuWrmym0`o^U@G9@SDz52gbCpaE`Fw0Ly1
z77%71x}NYwP3|9QoEC$qr4AK~{v(di;vNeH!JL7mOKKp7R6MW%`NH-DbD*)OR7^0_
z07S(>m|Y<HzJP|30J|D*HFKHq3%o643xhoHmpd(M-OA02z<;TzA^CvX#yC@FJ;}(X
zI`vdO_TuOHj?bvG&g7kM*rd0&$+TM^wpPDFinY=F2rMe=6pzEQON{u%2>EKLI@9mt
zf%|~&DOM9+8ho@g)W}DZ$YPkw32>l4P|%1BgPs>m`!PG4pZH^MDlV2ZFp^H^FQ}hu
zN?Xk^TK8Q>qUXt>rDti?;w}}*8A3kXSYf0iPH@o8jv>2!Hk-c6otNLAxoVgq<1)U<
z!}5U)!;ew%F<}r!x@OE};>=554W|=|Z~i$7UTyE^!55J-y9FxYAN)2+cUq--*dlV#
z{L@8xV1Zg=DvwX#B2YJNUSrdegx<z=Pb88QCZZk76?3Pr)hGabv*F`*Ea%Ag5?u|z
zG>S9~<M<vmO-G|#sI8$pma*UUytJWm0Pt3^(+^XOgY4}As1xw&6hxeGpzymuF;YIw
z^C6M%a$TTLnCn#CL)&_+W2Pva$p&e+5KyyHP;LM1O<#MU{-57@Wd|Xt!IEbq#P-%f
zrW)^RGTcF@JQ7#(_rUF``o~g;z$~Ynbd}C0(b~(UF@rb!Q+_MdJ9-P1k5k?Ivzu`)
z{UzqA@>=ST<m0VuEUb{Qq;*9xig!M+0CX-R|8NY8cJ^Uw;xli=DeT!YogRgLWZ1)c
z_ax#kV1l6aJ1M=b*4<}n$t6*h-?SxPonlhD=i7o;?DVLDUC-DDt{11n^AXkWvNsG~
zmJ6RbAGbyj?*-nis#Qb;U(Q#n{W&-Gy&nExWOL?g{lQ_^gC=Dxu#$12^iEw+{KvVX
zA0>YT7X|Jg+DjkSVO$qN<?4dcN}5}IQ5CBEC6gOn2Kj_2sXg<DU&Q816juWZjki7e
z2T-r%2nzEdZ%yT^Pt6a%%RGOi{&s><M{(5rK(xo+x%ai}2lh;Q8c`X$0;3do?cYKz
z52_((Dkkmgc6JP%hr69p6xgl*b?E}XM3qzEDxY4?2mi8G``U!SJCEmof=~KXTq`(L
zsde~J1rNBAzVSd<bDTTNrjK$j@<~3ecdaMwm^EoIEK8CenT+cJAY?Z&{r8szopS4F
z4$;5D&RugzK+}7$B6P=Fx5?n_*RzQsy1ma~=85zfMA(Tm>v#Ti1zdHa$ow5Nrow7L
zN%S&9Sm^gc`Cz3BhsZaBs4%5)msue*Ly_wRwRN)tM$Ft|=VnW(?wSI%d9}kg<sFn8
z`EeimN#1p7QXjlxsxLcFNt(0a<uKpIHjKAVp?@COFkF~1JlCsu@05rVLmCHn@XSSq
zW|0a=UnY>hyS|sn`1gD5a%lgiU~WTw0f@8-6YSsL!@m%Ze2b^kRi4B*_2f8t&aO2n
zl0xVrOv(ng<997+P&6#ECeO<_+m}9XJf+*F4OKiM%3oWPIuE>u|FU^Rg%vmu$oQK9
z_%T<F)yU)v&&tl9i4rjCGW+V+aS*nzEA4%46KrTVtIJVcCvCinI;?RtsIwa7$n`R>
z+<nvB{sjitT6lT*{@RF$<lm`H*c&Zt3;js%v4$Y?Cei@vX|%Bp6{zwm?^B5VeCd&A
zJV<(SO^W#uy7Ob7xy*=qy0I~A1`7btTeDfer&eshsiw5ZSk}(^D{)8EO3z0##lmQB
zT(iH?iX&eMdcL$Di%1C0RD?%qp?Isfh<59mKlG13?uz)_q8F~mc;Py6qiIQlwzscc
znr=InV%C-oB1|zpb-p)0a3B=UVKdYmr<(vHlSuCnnx0nm`x{N0ecwz^#aBvRyDd2+
zrd%5{D;4yeDeypRZXAUSJ$8K8A$SDN-#WLuCiq8}=Z$r(6NC8Qi>2&)dUR<tT)Z+Q
z(gEw3BA(9lc1PhwX)3d+PFBlGf5*3^-j(92wF}<HiswslQ2-)Mp7~UVBz)5su`Q=b
z7LI1*4p3VkX&a$bom;W*n6_>yaqSQcnf*@0_if2ja)vROLt9LEU@0ZiZQB4wJFYLd
z;m<Fct4i#j@qj<bM^SeP`4QhHIsdDRgD$hna1VXrLE4iZC|T(iC_}UIga<2$kX!ca
z-J_sxGqRmpg1$d25^9S^qE9m0U<H<9_O^qAU59$5(I*2NW*o2jb$ks-O@F%3VQC7M
ze)Da|&jjSE>1H%Ixe)l_-jiLb(b>Oje$?3a*f3cJpffRX_9*RTPuM$ZDD$iUI0noJ
z%^`%dxuS5YFje-+k{rXB@@dx6GnhbdWg4LX&eFg-`1;H8>8~bJ-UtVeWnm4bZH!a(
zhdZC&aKM(E%b8K8+Ks{0UGo7HtXMyDOyjk7hs`i@oi6_aW$R{=Az_UsUTZiwh5Er~
znDds>u<sA{_gu4tzjIF;?)B8(+1@(eu}YnPm=eLd1YJ_38`+a5Z+-T<{*x#uNPKN-
zz`Is3iek=i0jpgms^Mv$LToWz{wqD>;W#+e0rk!};=v;XogWv|G*b2PKlGSLQ1-s3
zx0S+M%FfJl&3!2;&&6rgywHrZ1E#!CFJk|2NWD7uC2cGldPJqDy{-G@a8%#8wN+53
zmBz<IrkS!4jfs`9nNKSOXD!~h{{xMbaJ=T6b&O$#ibF@lP9*YC3mSIfs&-F7RQz!k
z7Z1+16n=lJ2|r!<RT>_%lXkd(_`COo1X#xfld;a6Rt?D<u<A8E3R)EHFQ|DwVJXL$
zc!d5lEX)OLU-H`btjB+1UQg&rFRDR`WtnC^1h<VyG5wQ>vJ2QX+5YlP;e4?ALm!{X
zk<A61wXbF2g;2pg+P~Y!70+Nkvs=?bc>$R+TVh(y5o2rT`qRnwe;Z!J+RB6;yp50<
zoc`HL6FmJV{(T=%PH18dcLXC!Sz{b6Uwi0(U$*#Ky@n+Ctzx^RHr=kE_vI<vVW2z%
z!pD!>bjZ0^ttQ0>FFz4SKP{F0<SWG2;pKWeWG|7!LsC#wpq^=6V#fC#p5##G+`w^>
zobjVV-s4Hmp=K}dqiIb)Q;Q8C+E6agK3MkCw@rH68^?qxXBMo{<F^|Jv6;eN%Wsg~
z7=N?Vvgg4#j@Kyr5S>;c+Frx2rtZ=s<{CcWth!^YHN=0CY0Ps=a1}O4YkN|9TI5U*
zQD{#q%{R44yM$Kcx#Y>Jjcj4taDksz*TC2KfHKE+$9qnte@L$e?;hBwsOA(nHpmCk
znIE6)AQ)$hTO^NaecH7xr0#qc-&W`TYp>mV8Ngf_dON?>qonf77;>y;nAhHDCbST)
zUajvz=vK`j0NsVT)wlXTr6B9$&uEO0?Rh|Pl-q!_w=Wt0`Io6o?-9N+j-*aN?Jx+d
zsSMqXl*o#<Hm&@HBjOHm;_K(4(Z#|WF@RJ-7w2Vu4aRp^BB?0vKz`!njnR;06Cat4
zvwqE!PeJjdUi?X8cN+6(PnYVqXAyhsb{sYs!WT6Wa$bFbDHEJ@6i>bByQHh~9_>bJ
z$2d4#dcWn*Z9LjcuE`L89CoBP=X`*>5oA*(%=Ja2Vzb-rk+&+|M;D_i+0=P&W)Stc
z?0AQ+M~Y6RI79E*o#eZQspPO2sUFmls@q*x$rs@kwbB2kULrQ>U-KA#ge!BmPO#Hr
zJJ)pHO|Cd3trN4-5hQKW9~0cTIu~cs5)y?ugW5j3;iM0`K|S`|ZENeD=EXw)tS4A)
z;WL<9Y@9L1;%M={Q6^8C3k$<kmBcHqG0MDUl6LuCZ});Y38w?+lS(cdO<n!WjM_ra
z4AOhQ_+<#sN|sUGx%~yzdG11hPf$meemdZeSVJoSKohjwPRTaS4C=dc)xvpPV;TM8
z<qEWvF0K4Vp?<15^b(MI=1X`#uj`cz_U#Ek#^T`Tu}$)MEa02&28+fE`-0~`Hxf4G
z_ua}HCj_w^FIN-v!L|e@Q#}TVVV;0RbYptWNoChF0Kit&*!<gN_#vO2_j0Np(W|=$
z8mHwu7$qhIC~9Vd=W|V7IOi^C<wrhc!TUYy<EkHx<|@5?inH&w|J0=4X!)FHd}*Yb
zIJUi>RBz6{7I9n`N91vPKdXEYw6kYO0VRAZV>FB3G#MzTITt@>*_zK!$+iuY7;}-o
zH`x$iBS_&K@qx~j3#jKPmb_^lf$=Rm+pnTZ+O;$;+$du@=8BgWe8L-EwNbk>6({CO
zGw-&4N;3);NP5WVr30rhnm36H3;!+Gp0v$~gCi~+N5=jKDj%ILXf^bpzn^bOYo@#O
zG@;nHk%i^$cN%W?#p6*4JCnOvdZ40w@MTRv-m-sHYr77ZixAyAFs0i4+6R(gjVH}w
z+P(D#j(_WvW#eqhN8jnHiwKK{Geaqofq%kcUh6-7kn(ghz$lsJ8*l%nWt%}*!R$6q
zbM@B){WlL)fV~foG#zePg)SEhwI;lot;!#AgmvAMB&a%2IfuTPE^hP5cr(iWo>jAw
zGc)zcPn=(uzepAvLiDyg1xg($W=i+&u14Q(RbGeFDbsXW4@x%pvEBU;#|97mHDhKA
zjH5se?ORGqi=`x_KMcp~YNT!Glb#sOKHQ|pucn3k#Nf2<y)F?`syJgx;!;<u<5ob+
zziAj_qq&_M`>V8UK-u$DA`cuTl&*S>?K-PGcj+KRsaFjfA8-8qD)t0YX<lf(xt+)*
z^xlUN-QC9Zs#0q(2+R6ow<AqsRm`HfPko!NSX?Yqhw$qvh5vztsU({!3cOmw@kRXP
z!D0>1p<O%SK70KR$zq!IWQFDrcE+N_26;uEH#$=o$#G}tOB;+~`eKZee!m2kf>#pt
z?!@{uHM1~2%gNO^E}i6IlivUbD&ho5vm~}>e8BeCw@+27+@FNkwOW>?L2kz0*}EYD
z=oZZn3q87=j*TxG^kdkP8irm59hy!5h3s=@5Iy8nNP|C$JECk0ks8=$7BQdGm>n|M
zR3oi4#}SRxFvchZ!uXK-b($aE`dZhm-IJ9)5Q1ichyH>@POHt2yG3W0ohk_XTt;%z
zW4+76Mof)78VB01{~2rBJ!_GWZ<UH{mJ-MlqI}ixtJ88Vn*%SJU9BDLy}_g^J;E>T
z@WiXbmM3>PHCg?yyaw)NV-oFQ4ND33mxIhD$s;Fzl!{}OXEHxB5?K8IeQxpgZfTi@
zor6@>WEDrjr=gbqJL$6Ojs&-E=6F1~-pP^iqa7Sk+-)Czn5g4zI69l`TtD{cJhY}=
zb%)7QiRq(x?)bJ~t-M{(0s^fq=~65^Msmwrrm3hetfrtyiZ6*}g%V_=8>mu5v;9cX
zb6+M5#9u)dHBULp@t>HETAfEo0dTqU{-HmEsI>mda)pfrG;>^?=mZNB2RD#qucgUo
zULi5usQrb|??%%xd9g+JquZk@iG0n^xavt^{FO;mefBOKOHcWKuYZGYS39owU3>R4
z1Md*!&1^WWbyyJc4cENp>e->0NfBKI*H~jB8EJNlX71`U`d}wSDMj%!(U#5<@n4&*
zcFou_>L7Nf6(KRb`Xn-WYZ6y7r+}fevZ0&ILvv_Hk;D@dTIU)@9}-G?RU{XMEPPVu
zu=UVe7iCwvB~ciY_^9}6nq<;^am$;Ag>uVSYu75DxHqmji)`}>d?V9$?giyILZl45
z(JT11ml9Isf046Q9&J8zSPyRfvt}h}+0K%@w#bvd84te;JnzOrv-b#Z!aB2r+EcDu
zhGqrERcs54Y@M$EJ|GXEFwxa%yIjniAit>?WEuJ=H9;Gj+9*q_r|_|UF*|g2pTGYW
z==X->6^H(%jowDZ?atYlW!O(ST*TSt0kQ7$!7|1*mCx6;OhDC3Drs3UNp<Al+*pmf
zdfDaCRcJ+1I+hkp(IPz{9$|00cKNy`wRSo~@KiQlo-1EY`4Vdy5pNhl1i6~I_r}fJ
z-!J`7kF}Z{`E<*l#!8n!=Ay#-<VbzP>?tk5&WV6z(aKMK*)6XHwRhw>ty6k9S*=}L
zZ<HoKz1FjzXm?t=P&TM<kDa<H=gQd9YmdXa<i*XnCd*nCroH$GSiv52+p-tM_si`f
z-51aKG}hbA`b*%UQxqLyQx+ek%KCXE3NS$|7T1Qp0&8q)gSoz^74jT^zBm^u2<>2w
z!MSQn62;KfmP@cdM{b~|e^_!lM)JtIYMs@^Hq2M=>HE{COv|+rspI#x|9+8~@%gT2
zp~8~Ukh1F{*%ZF<ur(aU$20YY>u0qM>Qvu;0DPL@i?280ee#9rZ<v~7fj9fsnlAp6
zW71Wv_{Rq|I(%{j=6qiJx?)_%mZy&LbLDKIma6cZZbZ#Ojrc`#rgWcKM2-zt2>G^u
zP2+(O>6IyuFjv^(j4_sZp6Gdqsc<QG{LTZ-n0GJTeR%O!t?R*9xdjaxs>r4?I=a3b
ziqDyLUU&E1K4dk6ALyyBOjj52^-)8rzLVE7ADh^3$vyCa+6f*!2s`dIoM(8}9wYR!
znvmgrtaA2b)Ejy8L}E&Kmv{XWe7>nWxm)OMu=qZ4D;Zh9(nNzr`d<sD!OKLXU4`l$
zi;Zka6-gJ0@>(5T&43r6UD<`-1cqt?m~M_c&4*^s4<fP<4aBSJXB2rD9&JBJ;rTyZ
zc^mn(M`sJI%#9Ay!Jme?MMm9cT=HGg&(Y2SgaIUO<|2)ezRISli4O;ymQ#1@&gu@V
zI`V#AyZp|9sH#2Vn+P&ka_Hn_maazWv-tT}#_Tx~tA?sPJg77O%vn8d<@Da~rMm}<
z%Jv&;{`7x1-N%bHob80_<*?p{!6)~Ua=l#Af13U2mmouOeg<DSX_*KOy@Zp$5O5ZN
z$`BazlRsokeOg;#Z;BLBsS6j6@TA-EELub>*Y4!rnc2kGm=DquN3@)t)Tkw|U2Q3z
z)7%slF<c(&97W7|a=5tn>30pG&+@2(&X}Eahs~Oe2vf$UCGL+CzW#JZmr^atNJc;}
zh4YsQoo-4xRKLKz4yu@c`i_V|ONf+tXB__u_VG@u<&usRFurg5qlWOieX1=v^MKA@
zYOC^TcY?vLY1YBrf)O=3fe3O>8<v3l<`XjOlU;*sX$z^U9}4uYCiCg#TMLqZ6h2&;
ziUx1B%RG5EL__vu0kT%b8UuIW{~9u=$a+BDY*+qFvPCXAj9RFHbq5M(nw)>n>O7+A
zZC&H?XGTfZ$}w3{nlQ{J0u&UQ{P#N!wOKCbFS`g!{Yddx4bn^MDc1Z?wH+&`@Du7l
zc4oAP{IX%PD9<o9PJsAM!i?(D*t-7<aVDxZ8Uhmy|6m|kUqwKpsrH58d^pQPa%{hG
z!Y&wg2N9Nfw)Tp0I*+-vY4Mj*S#a{cK{u{4mjdmvAL;(3CG?!kpeF7#SpIjW_eXz@
zj=0SHruR)L^svwT64ecle^h#S+U+54X3K(8_9f!nkECuM*9?f=X0VN7&2<Sb5K6u1
za@b&vZ)58t8iDu1A;`e0y~>5k4|&|vTTsp0Gd9{wBe_1Ss8<VPf1Up^1tFCFRTEb>
zu27zaJU#yXLI)wO=Z4>J(6Ik{&5Y|Y6oF7>JN>DgN&a+Dd=*$0G&f*aG}yBCsFC4$
z6A5o=5YpjoORuk3uZs(O&_ft4vUoM!6dxY;?C1OLM=*ua2EB1{H;-q1!JocpF^X=m
zNR=CeB;4<2Zo>`HF$+^#H#Lkmtp#r~!b^Slg_a@goZh3%Di-s}*<X(*BueYib8)=W
zE;3J|4+ndDV&eX!bAoT(zRy#3q=={M#(@$81FN6zuSpXn)v2y5t9F$RN0i+&jrsi|
z>2p7Bu-AxBd(hPh`l*dJFMKlR)&+MSiDPG#fJ1vzP`M}V5mzU@I9a-{qIO6^V+U60
zH7t3J)Q{Mbl3q0*+C7uPUs4stYgNx?>9RG`dy(U+&RG5T`hZX7ngJxD0_Y<Nl-8np
zf%-yV(T=)^)&xeFU;?a1jioOp$iqT#KpY(h=`3mhK<5x~{S^%G6UNKy%<K%h8b?N{
z!u2BfKu{PItOt@RjK*<06L_oKL4d^2fE^JP2L{=L4V=)Vz-k6s7)iLJ3f-FqI4acN
zk$0f|?EtSuIK*HZAp>jy{sVK5iaSk5g8lMyMbvD}MQ|YcVvrwZ=d`HQ93%y>sSh*&
zui_{;cd4uo25cD*6$uVhcmap(f1QUNRjK@AMJ8%ZkO*29f32s$K=hayN>~D11q8N3
z#iAxH0e;7?{}y8PnQI6|u>NxNXvFtV-3_d1;Eoeewq1&N5jOy<f$l=rP$wXkR6iV;
zR*`Hz{p0ty)IdSQS5<*r6TqXdt|e#uDc%Nf-v@y5fCsXb!HNOVpB5Kp08p46pww}a
zPgpaJymbLe9&!%j7v36xgYv8xzzu{$d%0yNK%+n``?R<p3~C3M=e!|6tX_6p>#g*T
zx~O+l_Laf5x+`V;l|IU)*UKB_LgG^DwdwpqUll4hL6es!-Y%UFAO8sK`~vdv_6Pz_
zd?ba_juL=kR+6s=F|qzBf)uZ%0$){k*U_N0tXvlj03a{jONctjTnGN|i6l@C)Fc%p
z2xK3v_EXgdN(zv=x$Gi^VLL%Z<@tnr8k1WY(!ff~L0?t6m=g^0-$NRpl}7QXoL}_y
zEZGM3W8>KjAXz^Em>yIlr+4RgKGDDdP5NKq#TyN*cPK%R0j9gTg1I970MKYKkRFjL
z?tA!&Y;0U>Y+R8H#p^xV4(W&8LJu`p!8yE2#fK`L&?4Z9RFkC$-A#2}eAEYo%z05e
z1jqIu0|PQZ+lpu7@9Ufv@2L|J!dybe5inhIkgOi15UH!OBAKSIBGZ_vHi&KOt&18y
z@ko(uOn*7!^IBvuj*t*2_KfGbDnh~cb0=9+eGzs5`A=*V1CYyQfkD<O0Au>p$E)52
zY$hEO{cwVh*{GnTNd2+#D8SCDQ3P&2FP0l4Kso3CSIQwkE&W<&IcdK6#g8E2rep?=
z6}>p<ZAJqW+<dbGn&(}JAiuk?oY>Q+!dC+~kQ(e{IU!ZLQC!CthJcgiFM#N`S9!K~
zC*8P?ysfuo>ATkk-UIWC8>VK${bQzEbJ@Y(2J#ss{{scQ2XYO4ygdM%(mTnL$C<(M
z2<Rk@qnv4}oVU_bfI}aH>1Dgp#}Sjhf$NlFp1|Ft^hY(zdI#so&q&zF`==TPs=%tv
zE*AOB71gaZ*k-p7cX6b5(yS@RK3-O=amzkg7k*7q#QxRTttM%GUF4=?gG|Wtacj<2
z+U#%XK3~L#rs>2K#kGz;VSN*|I9_SlS|4IIz&8l#WhV-#q-l54RiEUl`veMCUcrC4
zb@9&o-XandWXIe5Vj5VchYp;yYGImVEG|Cc4F6C`SF@^3p_h7mHmHBP9tdt7uP;h-
zIXHfM`ooL%yHVZjRj4F~guS1Zl0ps$rHf&%{2}vvv<93LK~4|XKX^gZr@|T|%Nm&v
zJX+v%j%hPff*@U$k~P<zAybBvlZnYy!cezo)_q4l_Cz3Wqc?$VTAhRv;bLSBO9F!o
zsExHRhYeN?%Zt$wj7bCJb2SaaOFR55R6H7Araze-#L9Y`1^|M((b=G)=dlkQ+KdNB
zh~;gVf8CdSXvU?mj}83lv+wK6`Rt#lJ(E-Jso+~$H<SiROUTN52Ft`RU2bA5b9Cm^
z?`h`y^vqgw+tA-$OEx|dmHi@X5?+$mymUB&Z{fa35#ez}N8fG%VoDSL6_kWUr(Q3S
z%RX;Ewd_8RI9v$*Yx+XZ_4j^WE50pB&Z_Ert6jRps5D1mUN6JRde%XHgr9%KRa@`D
z{ay3y0uEI+P-%*R%Zz@OC4|N{(DkS_>-rkQv2|r?xy@M7Iw)3#`%z4Q^sKz9bNxR6
zV?mt0*B7)$xXq~9!^_@Vuhr`pRq+;*il6DI<Q#mQ^Ik^Fxw6d7^)!GYo&Y%Y=BZ(=
z)Lzi_i*Fogv0I`^JD2DHT4cWwv}lU~4D45o^v!u*N4MZ96~0~+eiZ(%5cY?8fAJA6
z2>UgL(d#2raePX>iaoLE@pQl>^sXa5w3#F8RqQE~&d$b9i8|XZ1a|AkVcxQ?d|j>H
zF!OH++D<lcn!?@r(e<lT;JOLUM!E4Ou*w(vN^rUCaaG?{)F#gR`-jg@oYfCnT=e#<
z<d0%*$&Aj#Z*AScG}6U~I3Bna9!5<W^rxV%$pZj510T+mNyafz^&iTU9MA-Xk8UXo
zk|~FetuA?>Lxa+mCZinprK$n@v-P8SrXFcUF<4xj^`kVHr5z}^tQ)Xtb43K?QE;&A
zk=Gwe0nZeJgT*d6=8KNNIG~zPF^psJqZC{O?Mx>e@lPNDQAkHY&1WWBM_Hq5LK|qq
z0N4R=qL%ks6a1SaiB#w7T!b?`JC#n=W0D0DDI~MEC%$XXbgu7nqAeq({@;-kV00<z
znkUqL)n<5%1{+VUa;2hQ;uSn|0~i~)UX(^E61~D&qHvfijzFmb=BYj6D-Z!Cdy0?y
zLAwqsyW2$=`zFs;lEOA-B}PwLf%NE)-ib|h$3)2+UXbWBHzNkTQ?TPslLKJv3O%SA
zG)O^21Kd|rE{{B4JM0VTRg5gBq5LU<h?;cc0z0V}-zK*-ogY$_)!OOAK=aR9)YG)@
zFszcs3g)_7c<pUt8<-DVQqW}>ZDo!<tO@rt=WCEc#|dwG)H;oXSR~YK;#)GMZPRfa
z4k}!cY9>>)%8|M@T=zAdd3&*Zu%9-0ty%SFynHI{2hyuHoA!{+x8^>TJjJM)*0_0c
zc+VNF`%7|%5A&mU9jl+6O_QDmM@2pBV@T8n-MLpC)Y5D@N$<4y?;wy!iJW!yu108O
z(yq!Q?u(3bUF*pksmCDpu0zBSG!23?5cz{vZGuFR-WzsVIcS{x**|u+1^)oq(PjsH
zUBz+s7s}B!yvI5Fr1dqmVRWJvw|2-QidQR?++zj$2TiEW>E5~RYeJU(0~SJ&z@$lJ
zf_H;B<0^An+I;D#4UXYuUbU<$bY^m=)Zstj5!9iOG!rIApv86C99Nc`eC5Mqr@c$9
z8@(ppOPD})3!1`T7|k1g_S@=fMrL|*UPN^FCyqX0UTdk{MwgBW@0zh~;<0>>7*iW`
z#@@Be>*d%pfO+UgtqBO&Mvg!*>(9L_Mh7_+=ig|a9Bq`YIulmyHEV^Gd6Mp4l|XwI
zjKOr4Q|X%Wy-9a#S1t)0o)5XM&%?UxPJ$MZeqn+;)9<_`Yj<|{5zGTOEtA%vqK-FA
z%Ia}B#uquSY|ww>#YK74J`nOJ5(z;d@$FsKhj1+*Xykn3j%q;3@rvf*Na>s(psr>S
z{*ag$?^}K`)D@q6e=rO>S1Dzy!!+9+g1@F}q6f5CxN9i+<S$BFfI>D0AXf`%uU<g{
zc_6xvO1T$}Zd88$#zpPG&T3@9v~S}QvN}4j=aEt_p=zIf_Tb|cp583e-cqt#m2Tj!
zF-P{!jdU>FW~Rfr(CO2|aUt@UFzD5Z;-3mc)~|VC5Ld}(QQoJp)wKIYW{uZq>`hp^
z@m;Y~40z|RXs{<|bI5L>VV)}{XxMhH()K%fuO^NnG7jy&-rm)Zb7PG0Qqj>FoXHFg
zCgv5VHLedzsPSX9E>ii(Ji|ben;_Z=JPNGyaftaozLdF2Q!GhzcZ6JHxvdLF47k9o
zMU3PYtqV879>$AY))O}%1sihp_O0DM;E~jWSo(Few=Au-m3s_zuFp!+qP36hH$N)%
z$?sh>uv4k4(Gg!83VL-kEUnnYCzlBiT$-@AhWGbzk1o+qE#0cCNiL>CG4gDb;C9_r
z<-JA*-Yg_b`q!sR2?%VD7QQlbW`y^Vv|`%W?0|5@54}@q*8Xw<7s(Ojq&@2<+$Gq=
zTtpAd*!?SB5LOV2^2EIWt>qglBa5B4sib5`HpK#}f`0k$S_yO&Kz<ElTimPS)^C}Q
z-E35lU8tDaTrj{mSFUN(QdVfvHC%QJ$X-j9myoB@xl1N{KM+Wgqy6lLJrA{ZyNqqJ
zPr3c-Nnna%H=sU@I#zCkS+cJBl4<fRt+{v`YfiFkqK?td-W9p6MUfZ|YnF7JS<woL
zMSJnO&QXrl!fUwx$84`4jw`*q=GIS4SC(s9fqPk@3DLOc(zE4doo|N-I#fNz(On}f
zk8C`m16K#(tz<o%FqP)L0@!BV4{|C>IqhQ0?a&DB5Hg;|x!aEp+o(UeP{-Q4O<s5{
zV^^KTX`E!%VV=@ZyKWJMWiv>el%5ubPLZ$URb=pzs+C-TeJi|8nBqmx*R3{4@z@`w
zNk^Wa3{Q`iX*lDqDmiqGO42>?T*?CTk6QE}Ba`xGn{xt~PE!X598&|xrSU$qX+M-F
zU`KyiwHL%KV%wI(f$vqkLu5vv@4&%09@S&Qo(;M2CEza}+eQ1#e~al`MlooHZCLz7
z)h}6A-o@o_MCbZfU8df6pHf6`>|q)=c^jX~x{Vvd8g7GVkz2r^sOoE>w>eG#{3zsz
zu5$L8KB&Nbr^-X<hdHe^(FOo>$F*%|nrk)%7C~}^I!sWG3H(i4OL&v`d8e14xB`m^
zZ~=M@P)MknPSn!brUb>YP2K5Hhd84-6vRoMDGL!y--<%nG=@D}-lPpssi)?EB?gS-
zRC)T)8h|rAPam7%>$KzU9M{X*p#AgvwS7^lpr1>*i1WHLUI_<-W!5g-7G#Tg8T@-u
zVW(q*x3!k(ia{B7&N1qJtEtfb8tS^3NiM%}5j>}SSEy+I6VmipSIdkvgSqCnKGCso
zssJ5@J0vGI&TB{beWhuNrezYi?rWuvC~cQyF{%%0W6zWAO=(D6)47{01Cz~0Ne4MU
zg)}n}`qev&wTnFDdQoyo8c4H;Kyz67jifS@gN*j5?sX<P*f4!7Jl#9zCyGs6xXw}7
z$JDf*OCx8sa$1I$c6V%y6&+1?a<On!p0%4i1h2PDR!)>nm3ba>cWrcx6fXmg1yu6q
zg|`H4)!kj$gY)u9thwynSg-(!Ud<xaR$jHgdGx4*x9<i&3dz5?6W+%mA2R%;=dD;z
zk}a6v9MyRtStQ+zbDUQzrDK0-a+Ulro2~fHMP=OFqBh8o4|>{~G-mnNrDI%MAYwqr
zwQEgiM5Iw?X6x3G8*3j*S4>kjo;y~yGr0HWKczkZm>c?gQoy{N@}{G~40+?V12je3
z`DqLp1EKY;M3ro8ksX0{Jma-uTF4WT%X`$ii!nrFn#NJPv8-fm!6x{hzj~)MeoU)4
z7{x=T-HfPw;EYzpvE~wvqmhwQYdaOVi5a`IW(YT9psf2Cyt|g&>494MKGtbqJRERp
zq{t(j;9#l6B=<nkjdy5t{Xn`Ok((-eS8=9YhKe+h1uUC-^{!)7fZRkjjo2Bd+FeN{
zl7je}CgA%~Qtl{l(9ycI@~)&@4TX*|QrJPV-b-fXS-8zfZ#;U8TU&|K?+VnhwIzy?
z&NwErdZSH>)|z?Ux01g7srr_f;?<*N``n7_bjt;BrH5YCZ&A`x;@gf07|m-6cSk(x
zS)P5P*l$I)<d8wft$Gc$t3r!`#@^LKN7E4|^D)m#>mY!6L}RU8IP0mESzlun16*qs
zNJq-8mK}|B7ci~G+HO&_sok2RZELdo&I|W=&$VqtnfZ@e-59gZd~M)Qm9MOZR|m{N
zUNdoLCA@`tVDJxISJs3qiM7T->MO~7ci`lL>|I-++aWuKIQrJwG-S^tQ<V+cq}{o3
zo@&kgr`gzmIO)Yyf)|yDUrNGS0K@HCHc_LlcjJ-Cs()jYpSsxkR)wXscJ8J6cNL7<
zwu3A*V}ZLOty|gKNgEb#nMGEfSV2BkaC;hn$a^+3=~(K-YgrUGyAY3*)}a_~m4T$3
zY5}-870|fmyRhof9f1HXnwegpUNcCtb6qhdnA)sl-f#dlZ%<vY1|($CUZHtL)6aT!
ziZUq-1#&n0+YJ`mo^e{5cQG7RWBYMe>{}7G1#VL<PS}9@*Bz)NUuluBHxt^rsU;1S
z_O2^dFBR*zYReF=h#_}m;GPXvbB5q%p=nv0CA-zzS3!cqIIc@rWqqt0B`ID)h;qDE
zgww36wNwG^Q5hpt+aMn|sHMyXL#HK$L%*C>l#nmp9FEmmNMpgk=C)D+kw+`8W9Jom
z))^QdFm&%!5`QJ|D%?7ck`6h~V^cfy0@JFe)~B#wF5+zR8mo(_=V9^y-lC-3uv|oX
zfa+>e19!%Qb)~uN$NE<rfx5e277f}=2m7Q~6nG}R2e2ajx<ZN_j^pW0BrxDrF)&a@
zGCNX>t-r&Xn-pz$e)cUpTerBKNsOI@D9PjzT0S7uZgq*ov02Ws3?L<b@Bk0!D-TAx
z&an_=UV43N)#TbV#VZ>9z<O6Ks6o}|dz_NN!d1P$+C0Zb)J~JE!+2vZsgUS8)~oos
zX*I}inh)JZcwF<0Rvx`G4N`5PSDpYBl5QBDzm+<;I(22uBxhFxMy*e2C8^g-;>(Hk
zh_9L@DG@tk&VMsgU3l8=dq#y}5wjDP4V*1;9(#_ak)?cf6`%HfChpOT%COIu-Pr5w
zykC1^Ya9t2OcjaU&mi`!&0ko#)hF|3ae>iCL0DdE=bBCJ_*SsN(uBE^)Y_h3LKF6p
zj-{eUwKR}DKMJl~icFLAuA3dDfXX}cr4oQ@w{Dbkjw#q>r*w7atyb?zk_n?3%{u_S
zJJPFdV0{fB!4!-Smc(&P4)akPyfYurS2Bm1=_he7g_MlrV8E_iF^#w4qJIe^_MP7_
z+s!qm3dKuQv)@ND1t<X>#aHs-nNC}g(zt+*O{A0S%}WvUlW6Nz3gf@yQo`Xo)38{u
zmdva?!-H0m6nIKH1Mg79Iyc`qBfVLQ?lkF!tmSbOCLtSdN`M@<9qUqP<G9Y{+It$H
z_HxF=AlyAgG{D)gu(qDnjPhWPF`CSp#M+iI$-XdnH4?SNL>67YT6B_|nHC`?3H>V4
z0+i^?+uJ<)(QZUChsJ$s?ajBAyG!rKHAgsNyk@S$FDph)R99o*yM}1xjk(%L1KPMm
zeS?5absiJD#-t)0`8@s=P}~mpO-yQy#y(oymOe9#)<uXTRzuqut@d1#?_D8diScS;
z(HHy8isbI%@~oS;YU})DapbRk;9|KQW?w4E92|6{2P#(t=C=GRqo%W{JWu=tRv3Kr
zuCw9Xfi?1nxZPQ@k<?4zNMLl^7IJEP?*mvan(_!o13ZqE=tew_MN!p;-7<bKF-Wt>
zY_tn@NgrS(dy&bnPVjw|ygn2-x7tFUqpfll{{Xwwvw#RcoqDdBZmHow00ZPaipHZg
zi9^B~t*Ew^DPIg6jAQQApAkATLg4YfuzVo?O3Rd29%}=U?_CzWqwI*md-SCT?~Y4C
z7M#OkthveJv8L0WX@ti1;TW8N8v?dc5piMV1Nhcd@oQ->mlQVdA3)^xuC_!xjV(55
zN;Fco_D+m@)l0)Hva$Qydm7NOvv?CSHe8NzOuDd^NjKZb7e9CrQ*hGeZLpFll4Kh>
z`IpwUbrxf1^7TEcJ6$^AWZiQj5IF!=gGU?2QO0w{E@TgMU^8B{SW8%%5;-h+tNJi=
zY*67;9t9xLBSVC`nPdLu?25k%LvDc)z#pwcs|C9po|+gsk-AI9hB=l3{{VJI6&<qP
z8RLfH;yafIA(e1NbQArK<pNF>!ur&49X{9nPQ^Z=vz981cakZ34Ah{KOE2B7S$eHx
z8;fZmBwP<P5A|8+HNE!xbv#H7K=+m<!+B}D*KK0+3@ZC*QG~6k8>Gb~R)jwr`RCHP
z+wBt4-&T8@#JDLhAjgt3_*Y7GC|4gL$EIngRF4PbW17xct`U8*lqcB0(exWQwLi64
zq^P|=d7tZDE!0L>U45#nYOBuJO)%=OwZKlJrAPMG5q+X(N^|IVr;4Fybt{p#`2PS*
zfA#5}4Nz^bqx;`Ge=4)$_wzMtqs}?!^37*>K737jndHA8m3r#3bkxp%TNWa-Qmd31
z#Y$`y2MhRBsCbhH`_+5O4w=Podx3=|mIvI&(x}|pvc}teE2J@T$f#$x9!rJe139XL
z_lc6w;N%!{O{wnJZ0tSzR0Q!}yiP_+gXO1=l*rE%@=q1KOxR-`>KVY@Q*v=pTy+#n
zV2<Ps(x!%>H8dpWHHzHQTNX!8dOheIQs)(_F%0ICfz1>MP%%NHG<7rpohe5&oO;ob
zKnss*Oj3$F&;UJX#TgW4fCI-tMmgz5aYkqW_N1kw9GU<+(MD+EfDZIgo+u}io|FI%
zD4<dAKm`VhGe8OjAk7rL=m8BaCr){ztpFIHjL|_f0Cu8|^k)<RQQm-iQJMe%qrETV
zNuJaIVvvecMkoNsG<Kt*qJR+6j=d<w0Ahd+)MkoK!=(T(ezbNJbn8ZQKn5}?KN?fT
zCu#;9@y#9mX+g-Klbp~3eQ4y-+lo7SPys;pqmn2+X#jfBMIAY&06NfU&L{$qh4!Nq
zW7n-2paT??w4Bf|>r2i@6qv!IGyrubgUv2zpacSrpW#Pdl(?V-#Tep@(V8v+^`eYX
zKnE0K6j7Q0Q`VEc0*v}|Km{QH`%&JMjtu}HrR&y#^b}GUP-rLCf!3G@dNJ=u<3SXJ
zA^a$%%_kY+m<x`*DCt3?AkaGjql!ugy&(!XJW+}W>+45aV*}_Y$3IG5)KUQeCxANB
zw&Zo8K_>&fb)FsYHTJWKpD<hZE!5WrGaE|}3(cLFY&5D%Z3#3#4{6OBOMY4N$WVB$
zjN9n8sf&F%TesX5E9p__aV${zv*WvSQyb_EV{9Nf9IIF7_^iUcTCP!>vG!2G(TrCl
zPH$7v?JrLCfW&=3u1itVq|@B*AG_@0y)E-H{m?#ws>!CqJZ3rL3=ewsvi$!5*{)i<
z9N4U~m3Vuq(mcbhC3Tv|gqjl4+GMUXjMptBZxa=DD#Nj_uEOIfVk6B>-1$sK7Ia;t
zM}b8yI(MY&U3WP{`BD%`rRmsFPT(dzXyhKWxS(|7tpGNXosK)w4rl=nTv3eXl!`;g
zYCr%|k6!enudOFPod5@|0+X5r04^~{Ui5VSbZ|RR0%sJtG=q;ybpSMdDQL+wlmPCg
znop%JDG0_+DGXlp5s}3MnlnrU_M@6J>qdB>10)`3#(1N(08j#Vqa607?Lp`$0Q%An
zywdVLX*$pX=Z+}{JW+$3(u3a=fK1RveW=DwDH#;NLq;+vqqP7SqrDV+(g7%=G*ALj
zoYIa380LY2%_ch1jztHdGyon+=8l}wcj-&gfEJGQV~QvN597@zdR$Ox0C%RIw7mr`
zIQO6g`q9>ptr_RqfETSL1o6_7JWv9PI*ybK(0byK35;~3)|B%{dSE6f#~BniT3mBL
z4IfHeeiUMski_dr?deJf7^5S*0r=5y3}fDmW`OISSW<!*WqBUdt~)V0el%jHTWiSx
zDQ7#W?hw@9+1i4p_OO^Qaz-h0F5zZV$Mc|y+P3hvt#*OZ6^&2#+ONmpJxz!2ZsJd%
z%|opP)TI`3+ezz66E)M^cq-!E2l{YkKkWCd8!rRc$r3%x^2kr2z!fhM5Kw0fKp4pa
zlPU*Le;V}E@Lr7=`Ji_9E^4*^0EYD2W<wpcY8YpcQT3RQ*`9VCNdR(vs%5vhbBOI`
zV~_3{^_xo@IPKHQwv2JtZCg|dKH`tUvv{t^uV#4hvAzTYXD&}-xUDF>DXq+)i*!)m
z-fHi)6vU!I*RZW9#^{&*(NOUc8iG9KJPWJ0FD<%#2{fPZh+aoHjqaoC$qQbT7rkX(
zCflVw4Nte5A0jX#_<w8nrM#8%*j1$PCXk>L=dt%{>LVW_`_stJN{3c`$I6a1JSn9^
zs4RO6C_Ndgpoc=!AzUSd1L~Qm?#|6g2Hw2pwemKKiOx@{aYZw03?mW48jitN6%5BC
zHF{(6bmpl~%y>2Nxw8KNXu0j+{sOT$_oOYFF~ueT?Otiz9r&fkG?=5DP$9s3^rSs#
z6laPG4%AW_GsQH7BQ_0ly8gBHc-|NsZ*HVj?O#z#J7(_9z#g^2Nh?huk;l%*wS9g=
zl_`Gys`NaJ!xrQ2L}4t>U60Mwnhs4%6f#XB#*322u&ej_T3AFHN6Vgo8v5^VO-)n2
zr;F_5*D;ljDcBgKJemz|W-0cdesrB^#sI}J03w&ADj_H3&1gZPUe6Djp%rnRr>%2U
z#L}ky_hU#?l>QV@>Fr$xiL5d@$1@h&z$d+6%?z+eQdHV|8fZAdQ-%kFT)5mFJY_Cc
zZ9=rDO!WAqSx_>OgHOeA`c}Q=m5y)+Z1%3I-sT&K_alRz-Rtw*ZeLdmHyJGtq@jq7
zSlu#gPzR+P9)^M1yyKuuVvuriPUM_Zaf${6W4$3C{;GE*QG=Q;Aqd4e1_(c;0ASMN
zBQ#u16}6$}>C&kg%4eGMBB)0z&U@FX-o_rulykXAuQHT=`P2@LUvrU8_<J4>J~o*V
zP{SO4R4B(m(u`xh2cG7=+n#V^y(TeBjPXZYQOp({lbUk;&Ch=H!%4dx_!M)6jXN6$
zzF?4mSam0$tux`9n1M1pAPT^;zk5lUgEH>!4MC{u8ieyYz1x_G`=iph>tZIIk*q1F
zxvw>znG=M#)uU6~Al+7$$HE><88yqD{csZ%!xtO589g#-Rgkb72Pe|8Sc;AAU$TkN
zUBzOOm9x2$Xvadrs*#hAN{$?X{VBwd-7C<9u8bswKD>I;XVB112j%K2?oEX`2hxmv
zX$u3~Qf^V+j$|tfKs?iY#T;i8hGZ1Iq(hXG7^AI3XHY%qrstlNdsv4nEPfQ74OaU}
z&m0;<aL1hDm$gIoY_+#Ipj9(Fo;Ol?&x7++`+p((GVwfPr`C|4aa0S)dy_}beN7(U
z$bQVdyPl$u$fK)OJU5~I=m^K4%_mwx$cvtO;L?4eIp^`J!roT@0G4g_#YnbuH~h0W
z^`-4*K2%6<Q~^ylOPWJu;~7vsw7+5FJJ;}|o}&vyX}lw+G=}Z7+Mo7h2bTP)MZ9_8
zNi=@(hq^`f$vMX~({nF9YS-D1Q66zpN2kv(+=P+qia9E<=7K1FreCE7;$zhDT7yNs
zlOMT1%BCJ2x?{=#k9uCpr*P+ihv&=LjWEk0>c=(Ff5J9EJLEuqw8=DUcvQ2_zd=dS
zmsT}WCN->6+)K3qV^%I~8rgu90$6A7W~3%NX`9H9;P(|A@)vFFa&gwU>L(U&9ZLHb
z9RRB~uq3AqAXEpD-k>CUidgO=hCuw1I|`U;$0S&NCQ~M1Rw>R2>rzLd-MAmQIQ6S>
z>$9?tEfz7;J!((wtG>lR$6;QbI&ik9EUHZFt$b6h7TNOc10>+_T@|N_F9dm<5IsB7
zf3WTm8I~`)GsvuKs3b`YZPOfAkz{q6m)<Z8%NqXx3HgOx(DgLbA>QkS2ZDVolNLeF
zBp)f@*1WfI+1jjeC{8*GiAuwaZgm%W+%~FKGnW1nSdXhss7<uL$^2OFTz;jhu>lN+
zB=SdE*U}<px63)$-0nS1V&rtjnYI0-vbeX55=q8=YpjYpcx?hM41{H}YnQW%2r;n+
z;rvIF`PRHL(&jIay=s|u!i?3}F1(ilMEQDgR3enA3=RmZ>K5`A^3K_mWRHJQO-Pp#
zO;1OMQnoTcM((O>i;Udqm-u0~Z&b$yx=T$`OG%kk@H?YY>SEJZw{}GfHa{v(MA&2+
zoL39E4j6S(d8NEDUs@GCK(0FJ=dzdOA9txe>h+$r<{;imzj2y@*u~YYC9#`5R35nL
zQrqebVM$Ptv~ybbvcq>7S1NZNzLm_#ve?~p9$S7Qi-FS1ap&8l;}`;+rQdm4yk~$J
zc_y=MCPQf=W43Cl&g*d#4lu%<$79fSSz7l`WB?3~4RJEr_1wQVdh4t%1=K@v$Uc;k
z=@3lZJ~^(KPUk$MV~k5_BXwmR4Qa*};S6rQdm7yyA6DrmDUadDjklzkHKoWn>-`cX
zJH&f|{{UvQPL&`0^BsG3uSRVuQoC4uzV)9jfiPlY0IdQzrPB%!=<FQyE7VoU=G0<9
z7V1ttYol!z=|RL?ezgpmT*^uEh#>T&#$*2gX==a>PFvX2>8|Su{A%9SZLFV+p$8f1
zO#3k$0oTw{uw2Ny)bH*ci>S->@5N;Kav6T<UO6CgeXFZ$U8A7<X^~oiBDT;9oaBmO
zbI?35r8IhIYlK$MJbH0m0$AHNN060YO1id(P6*N{V7&!E+Kt5XvRg)W^e%s;O9I8!
zhMJMLoQa=$=dSeVZ&{YkAcsHQt?2Z3n3lS1?(JG}Tcj!iC|XtnmACM8EW71yYQuO=
z40ILKk@?bNngHRoPXx~{C)4f>Gos@-2S0(})?;{oRAnnQkIp)@Yzm)#dVM+i*QR3~
z>2iH(SfwV9BA>#VoAk6li4}vXXjisHM6m_Wa&wCJk~3UCkBoNKPc*6mdeud0CsCdo
zs4S7qvEOw<jkmo;s$Y56C4n3ohAV*Uj)YZIrn(x_o%b~(lsEX+g@SHxHGl}c{Y_%V
za>xfcBE1UJK#b_3dxqJyaugcd3x`v8kgMW7lufS>U)fyg?Q-M>Q-Ynrtrna6LP0dy
zTUhy39A><`O}+art2`>?q3EO5wHsKxxY=xlvfUI{u?QYTM%%g2>i#2nTkP<Bu&C`(
zX<A+N+>uW_#Vu5Go~=;nx=LGYxx8Rs8B{&1f6ks}ML~g_V06V++9NBP_WKqA7{Wss
z@7|?bm1xNv0n;@Sz|9&*&=0*+rMM@N!q#Mv4dJ)s?>>~R3p)g7E1VL0)Un(_6EuW|
z3USX$tu^}X-kB}vD6oyVWq2d<q|2e~dWunU&^OAVqCHggteCIbPFp7(YeL+#k*tmU
zU5#ZZSftGqWR*9@ayyRVq#r08@#|U1BBaHj`KD9z0n_oV24G@YlpG!%Ju3+-8m1C_
z=un;r>s&vGbVrT}<c2-NJds_wAY;64K31j>9a=U}LEwYjQsj#%RFY?$_-+|h5Rrlh
zPkQxhZeT&|E0ldDBe?$nMsSEbb^2FRWWd{nKY2$YxT?dEo%H9<u4njy%`WWrKSRN;
zE&MwW3aHFB_Xn+d9qeLAN|FJ^VNYzR39eb2#N}U0ySGPp?xfG5ImKs*wKygJ0FTKI
z4|?6WlIBeLP{_%+u4;>0y0%?T<Jz+<Bh+<VD@Ne2y;%O$)b{@JA@vmN0L9AeDmWuG
zu^p2;1p_&zgw9nwJwJ%GD4%IqddPA5SF33{UAC2GkXy#8sykI{3na6MU;xLHinJzl
zm)g1(#%#4W3r(|^B#LCt8ajr-$CyTXP$O8j22Dg-mE2>kLRx?nlSpL6M$d|mJB<KM
zyENrB9yp~9iU5-|W|_a5UE+Wgkxd7hYd9j19F8agU~x)KF--?F0V2N??BrEqaB5I~
zS_D?UkO){GOjj^`s1&4V5kcfFTh?^|j$sF(tW!CB=9wk4b&@gOfpU$ID><d~p&T*f
zQUgbLJocu2rD8unKE|uP*2uPuaap$)McClvnqn?p>Li`Yeo@8+XH9eFbk1rSPI`2x
zvN$vfz|Kz%{HPI*ov3F6jPhzRxHzCJGDSO&pzl?r7zA-v<!p{BjHL1nB9T_%0ZjE3
zl{yk~I3AU)BAfy1Rc4KNIHb)HkYMN9nI*Yid)ARvR=^b56g^=zb7->>(Ek7xW!=NL
z@G)H@+vMQ%HJ@{805wroA-kO0Kzj0OArUQ{VzuSAz$7kexQCu`RKXRNG8Z*jly9v$
zBJ$xR3ePLK$*4@y#P*S8LG`C<NA92<s%S`63NcK%P4Z<=9+WM?=uo$2iN-6YvAX+Q
zEgxAIrE{V@^NO0vc`fBKCu5vc)Q!rgBcMWUuHusfeB6q&ty_6)mr4Gu$IVeYt>v1{
zAKx8CU$%6<(q7g<`@p<cE0a#<=6rZ~0PaRHSmd-f4i}BJpf|ztx85B`y;izhmSR6D
z-9CnIK#8Pg6Cv9oo*KI?4_1y=L2-nWJ4x(oh>A_CjMlE1JW@)L%Z|7??ODzyk(JM6
zv`Cp%;~=T&iqekU7|QT-TwaMC?wc|ZC!KD@U=z?+acbf4!|s~al&*5tR%K{3!4t7g
z=QW`edlzmg>N%$<JFB9`4T8d<xWK7OU~$rg2R-<wu*a~bNW}yk)ooJEZ}j<4^57D=
z`c<%L%65^)bK06EpF8-UO=zWLWGKs$2Tm&oPum2ACF$#4yYUx9^Cejq0cFk(JNj3a
zHG{`1E3ZR?iq5jok(25%!ZxC2s7ZO|u<eSsHl3fkFgpQMB#X*s1admpJW?IYg@K17
zsi(tk@<v;pJJl4IXvbkv$9!Xrk#Yg5<pTba_|*b+71c20Vz|v2!)j>9t#)tsJu9Z3
zh@^&R6&S&6d(_ILsUb^o&~j?9g6){>wV8%{DXkS)E!c84RK7b~Bdt2Xv0k~UFSLzT
zc+<+$?hbmLl>IYC)+3R;?K*#KEpSf}OWOQMxY3tlQhDaIbmhvwur!is8lFB&36J4d
zbiFT84&qBG)qU2r`rR+)MLJUKRY;i0{uRk;`%UzUMhUM&8eRInO_aFy70PN}8q}Xq
zX_mrrJwWSO)y7h{#EAA%>~W6?4aGh=iVdBsr9K|j3vs4SeKIN;yeq7qnRLl(53SPv
zZ^(YiU5sE%pLV2sKQ%Wg<aOq>lf#<g@%@<~9<^!>4^=^lG|PkZTFzLCeI&mC_A~5a
zn1VtS@s5;5XB?}NeqT!0ywG)NcKLd2{0x2Cd^!fIkq`6<{+nriW|~*#{6pBwvCG|9
z5c^b)c@+q;n<t^JnoTECjFUZ#$_F{cR+kW<ApJ%;6}&MDS|@QjazzU(31#2_q<Z?)
zvRlfmfw0(R{&h0lY#Hf_of)1lGz^bQr6+wzv9aQDyF^Cqz|W;{=Yf-5;Ga&_G_;21
zU<YxWRd4LC4<Y&FM)oaUl9Ff+B%X1RN?BBAHQN|GF$w7z$318lo*RfAv7tVIQFI3<
zrpOmjw<D0PxsRZ)V=`~jMmiK2t}-2OLl+2<K&9J{yIoqbeLS+Cm6s|jDwet}9%rsc
zB$|_zhC)3+&1Q=$wkKt@g#Q4$U3K2L)-y>D*}UDS?}65{o5izkEA~yN-mOUx%unpQ
z_9OicN_f%r1HiOz#MRk+X>zT!+hMy^XYq~u{n(W~`qR1#0MIoy#votCs#WmTq{Hr@
z`kICOORNOk5dih7ui|}F<QY{>FtMzj5!4-j*2bslQ>TLO8}Ho2KMLo6;UU$}{Jnlc
zrd?xHk$-u3`0NEID*@3bf@jaodY_d{JQ9HX`iI~Ja^q9f8L{@sHq!m7=lHH=IrpXQ
zEF-D^0E9BdN6&xy)4$;r(v<x7-2VW*T-VJY8Ja`u^HeiH@nrd~N1<w7*bcY;5v>J&
z{nmfrbjHy9Hizbz9Dlc5Ul}{O`kDg9=L8?lk7@^Ps9))px?96<HsAml&TE?cL{|}<
za8GKekU%-wGg57hc>@&^sc;=7yDWS7!KhYMUJYo$Zza?uCphg*O%yy#UR{k?b46|=
zJ*EV4O%0LhM3H$?G9TeM$fZSI^<zUfH?2(*_vmRFG{$L!W8RAh(Ob{mfZUN$eW}Cd
zpn-Wb=@jSbQDGLRo>`#6fr`o@m9w~m>MBQ_kl-8-YJsHP_|?T&XtQfEl5MiF$7*bm
z5h*=ISBZ+qIjtzfZo}pVo6uw_B8t(`ZxYj1idSL~aB7tHgeyrNFge9T2`7#+IOc@L
zdo_jaxx0=}IWXAdwRF<n*!|&g9tTmH`P=O`NOvsF?dU4N)vmm-3%*YWn$<`wdLN5*
z8)@%iM3o2(JNK?f#1{piMMIOix%qA$R|LCf`BY3;H_an9eN9!wJaJtYgC+93K?`od
zZa)g=0n1jmho?(@VksShuTE(&N71oJB!yerscXDw*By%tW~yoW=A3NP%)Eto?!u|~
zhr}9N=`zI~>`crL-E5wfH#J8s3i;NM$Gk4~<eK(<G8F#BNLOiHovXz3Sfkcww$tO6
z=4a%NxW#&mUL4e{Es-sCIR?>yuhO~dZfg>zfv3H!*NW?f6B4|0iqqD{bj~`DTF#0+
zZ%??9ytTPj^x~q{b=g-+kk4rGkPbymcPWuu-^&zb7pJvIx{UqGk4`JhU*a3v%ILPv
zaL1a7z9ni0i0sckwZUHljHy3%t&l2|*F)7s^zG5VN(I%+3<v!y$sgh_w8!MNQTWsk
z<IfPkK^oRS*!Y=zRhWBte<|!uEcxY$rWcTpng0Os>hXCzW#SpQ^U-+iRb=rFzWkj*
zhtO4jVBg}YAo{}Sk8d&@oVfo0zNw~Y*Q|&>ro1t=U20#ysLO-tQJM88``5Fd_z|c6
zuhRQcVfBaD_cp(_Q}bL#Kj2jv)wJ{necWU5uMXLA;BKB{{{RA}n@1;?kgvN{tb+`<
z53ES`r|}+=oEzwe;wroNyF_34eT@D!<EKwkj;HaX><CZ#y4pD=5q*+<yw6#e$66F%
z=5-`?s?z*K(GfupyXXyhf7n!XMWy>54t4|ErEIdSD*FhZZ9eCsOYt*FQg%ln{{Vp1
zR`{W2KINpjBdJ>9MYvz!0-NOEj+Lx(>@wO2msVZPomTceLFBkZW#7&XVd;8=mRf-F
z)D&}rSEXFq9A|-8=tADb^8vNNHRwhuM#g)cy|ej>ul??8Q4h`lteYRYm8?EfnxPU+
z2Ia{7>Z_>o>qR8qryrG3nF=xPrkWEt4NZ35%AjCw%~I+sOIKW9N_~09rDmR$>_g#4
z9JeKp+MEff(D6?ltD+`sUO=WyK3>%NY{M~+YI4{kxmKiytw!Bx(BwB2&bKvt7Z;@|
zrm4WE4%M-P3S1mfj%e*bgS{c?N@&Lv0AheJDLc}hv;e)SF-Lj_9cTccangzb_2z&M
z^Z`W~$@HKDnlVRuGe89Z=88H{FwSVeqK@<k0sN@N0*U}TQH;?+98dsg?dd?`j0ylK
z&S_~V0HD!EO#mGz%^fJ~Km{FgD5DerW{%W%%^A%hhgvAb2c-ZVs2ym}tsPH#U=(7G
zDKkI|oKR0Rb?r&dGytNL(v(tQj+6ku#hNijd7~Mi12mqT^G6w@sGtSLX$Kvs#!Udw
z0n@!NT28c50HdcgV*-!EtpEq59`sV@iU3T}OOJX_!hjTYqm0o(=b8WwCt43mJ5T{Y
zpwgdu08W&-qym&0006}x$F(WuldoC;D58wg02B&8ogF9u>FGvsM|wFl02&G6mppn=
z)9FA6e;NtJ9XnA##2nGz6ui-j05On#DSwqFG5An=Pyk209XO(nv;ci+DSGvz88iS6
z0qsER(vH-1>qrAMaYt%9QvpXxUV11j-G{9pu7kpwNz`=(k(4xXw;x*K$717#r0PiO
z!q9bQqI5nE@Nl>(d3rJr%&FSF7Up>EVf#J46+pqoM1^cE1Zjo9#w#_XGD(t6eov0Z
z)y7tHlhFFg6eCVHL=!VSnd?*k0Ac;IFj@?Zed@6kD7beS?^?}s=fUNvDUQp<aZ0qJ
z{nMpMt&ULW;x{WD+^7e*G>Kxcu_k#X{{Vip<%~v1^!2I}$%1+5T~Vtk#?6n~NscI`
zNFyS-jeo<@+{9iL#Dl$b3qIa@`&7(QXo&T$+zvXf3aXS|hc$XJs~%Y%J8=_1DUHDl
z4mqfMkSnk8PLQ!NyG7`@BDoWQ)%u1H6C6b)IG-bm!@4tZ8;-PcJ*en^`t)@;?_Fmw
zo%>Pg%_;Px&pG`l0dtB<2TC(Q00f#knlt!O^q>RjM|xj+LOGxViV63m&vD+4L7)ZC
zKJ*$)^GlDV046a?I(pJBIT)qmGyr0gKGeD5l<;T)G1iXsxxu8(APP={kxSl_p7aa{
zIHMf(qnbK3Fca{l#%RZH)_^Dg$27R410DFICXfq?ZU?<DdNbO953foIp!DxXJ*j{i
zN?x>wkH&xu@j*OM#%V~+03rHNe<}#Y9QC9D*BsIHqn@<Ar~x|C5Gltr)5)UX7^TNv
zGe#*0>qW*cGun_+;{zvvI+IP`9zOTvDRUsR9iG&mg(~H_RCXWk)X`ep+-J$RmO;>A
zX>*{nAvBrAUri5JkbJs)xb2gQe4ZZFqK|x*s-yk-mr^~-QD$i4ie9zQ+ITNgxrjSS
z66AEnT!+9H2br%|=#>t<7gD(y$m5Drz^<z6!Aonm{VrC`Yg>39OAxN}Gm<$wy41W(
zP<u9c@gRTt=*p0Kes$@wcr!&o{{SAOpH?}lmmVI|ZSR!@vIWmVDn7Ll`!;#vvXRD5
zuoWW5D~zqY#Cs)r{Cah=1=(#7Tz___TUhb_tw8!zeQU^m%<;Ibu4ZLOtz~8>0Bx(Q
z;q7Kj5n#hTGQzzKL*?pfp#UYi0b5>K1E=dsSeYUFBzaQ!OIcx-hBf+})9rjEsNGIu
zGDjF4$j)ojj77bxCIs22k)Kd%KC?DIW{z4vhqE8`m*XGorB2=ff;gFt+@-qpuH(zY
zb)rO8je$L?ez88|<VOvrcrwOUkX$pq-odMKKL_ZMpZN9-kMC64eire^@e!KVC30y>
zq`QYIGAGb<c&%G)lzCr8qeZc>h87XqN9=air1&tf1FD+M(Vym-ah0XdE?vsyMxY2d
zR8jO5PgGL&L<Iwp&0NXt#Y1$A_R;{k`Fd2Q7Axte7R<aT2NhwYQrOK>(-KLQl}F8<
z^`e#%mMxrQ_o7>YM*jdFK-e;OXYi@C=G|nY9SNx}?8;idn<DY*Y7H{t&N$=`a~S7<
zTAJ7kxZ^cLR7EhRMsa`zT$5GOA>vEufgORYeOJX=3ft{Vk1?~x&T~X!@30z{ExOe>
z=B!|v<t;pSrP<ry!z&)WD3jt%kRQ3Rk-oHhIrbMaHuWg}P)PZDRl6|HYK#X2R|Tke
z_Tu$IMQD+ysWnM_X{^T>SmcNgaat-9YhiPv)O@GU0M=Hi5R8U?53YJwp2_0PZd~rW
zE1&L+RSESQ+lKx1<j?hLrG}7uM0*Sm3qq&PLC1EcNqJ!b%$Kkz_iFK}C6-0`t|cST
zwMJ8L!6f}nKdSkQ+8&pxYnoJd3jY9USNBfUFZ?E2Br$;V5=Wq~FaUpaQ-Y9By*G!C
zQ0F}@d|{^EN#wyCtle{pzU&?y;9wrcywgfMbr{bio-5KLJMB~b+W5@&l7(es+Q3fn
zASa4U{b(bTK;ZSS5cMu0_od*PN>0=WcLUap;+sk{iUu#WM>M`nWyt^zwBypSyg@Uq
zp+q>{>s|SN8|xM024P;OvxAY%>X*-Tc_C)`7p5wSQTp_t4mwq>I@zx;L|`0aC53*G
zQgFjizeIe>Qma#5rv8Ouuv?ksQV(8zYad*=Hy7bqh9k}ZIj)aVnQV075c}J4&2dbj
ziGFt;r`EjeqMWKXh@VrZ7}O%EApIzyXEdD;wR^{$2kA?Iezcuwc<N0lJ0MEthLLOb
zi?wdcp0(dc3al!HMgXpR!**q25^cfjlU*nWIrXp2v#evSiD^9%^!O?~l+4{nN`~$>
z!g59{kJL2TtYyJcQ?ai@12qN3ymO%q7-B{Sdsg{wc~cK)RMsS7un?=PcRbYcIn7+O
z)MvDP=_$weeJe{<&>j~LY^Acitzj}U5*QUehqZl-Dq-=ouev;E3b=V4mYd=fxlNL(
zR~#G)-d7F*uQjwJT*effmhE1FW6U9raz=TtiO#Szu+=|z)b}to<yJoNZ1L|w`cdAD
zXT5kwaD$3b$)v`5QuLq$6ul_T08#<c0Bv8s2NmX5sj~WU#y9a^o=5H)yt`ff-m@}i
zpGx}9AFF6d9yVbcyOqme(iRm|vBwnB&5HU(QJ!BZZ*b^Hqk0DW)k`c#S}?@W>M_{2
z=P0H$=~YUSd(&BQQ0B@=nWhYS)NTPBnvGX1Dq|i1<Qn6s?#*IEB37vq6haQ%;+~1e
zL5g{gj=d@n#cB480a2OX9cfC6Q5I{mo!OL-&o#)+H+y>il{&!3qLMwS>uVwCy{lyj
z5p-3{6G%fI)qGjXc~uoMY4Q>kimrQ_e$A84jH4U+8h4b~>02qL3=Gbqr(H7HzV*r7
z=qkOCokU=HTnzU-P$4C;@6cCBmU?7FZgRzV%~)2`VI-<4J;|r+MePn@ZCtiCHhz^d
zX}2zTfzR@;l;2o|$|>W~X&Y3v94a{a)ha~$Lk)CGo-+_1jZT^qobPoQtzYd#{us%o
z{{U-$b|r3cRqRRjjG_I97#};cf4jvm_Do7}mhRrUtN#GnvYwE~kEJK}rOD`n+lsYK
z3Djjp(;Sde(FeUqG`pPb5yqMJsm<;2BZ2q|Pqg0=)w=WotJ$J?*wLb0G3I3-K~7%}
zx&HuLaz6@o-9d*t_V>jeMe8@p9FJ0I@*w75z8;4h+%d-;Y3ZVA>PTkEJRBN{tZzss
zX>9r$Y18i5<6#5+>aJ3GnQ3fvn2*lG)00m#X^<%k7$ewbsDEYLoPicG)0z&MdH(=B
zN%~W;u3T+O(m%NXBl4)<T-)-b01AWqCiS=wWOt_x4*kf@w;x)ThBdXx$>Box994OB
zTbDTxgYCs!{{Vz<Qf%TS&$*`m0Kze;_e9Uuq_kv9b0oy?Vslm9o2E}5^}7BUzEvT-
zvG~<_bRwDGCg%SDXQgK(%Z-d9_qjC7kM(?atqJUeV?DFn)hVM_=QZYH6HM%;P(0J4
z8IgFPkU8y7hlgBb^U!)$5Zux1XvB;c09A;sXPNe-ZTVH3T}IyCFZlH=dSviw@_3Ro
zQ?>x0dYblW@^bsk^XJcf5%jy;!7YyDMcTuRSCQ-9WO|gSi<Dnl^}R3;>`P=kA1QJV
zt}D*<<X`P6eo!)VUJ5(TP)OzZQ;N^jCuWgHQU)udD2>2T`Byus$Fl2bI5_D_rpAyn
zE$z+Lrl?5Rqk99~dRJEzfdBvi2LKAj(&7PTlbo~T@*n+r(#|Uubi~z$Zfiyv>z|H7
z4PJ&*>rmOUM?oCor;6#Im1RtBUtX1q9H-W&SxKq5IGVbGM|lXjg>fL|fc36rwMVy<
z<-lz8HLn!y8)P021bWs^vu3w}q>WW%1M{Y(VtFnk_ps_v?PXo!u%u&eDI)_19V;H<
zYt24jr{r$l^x>?e-|NO3)KzX}Ya7dOuNh!>e@coCLK!3$cLO2$NAxv^_SK1rSIU}(
z?&TyK(aNyo5!#UKb<ii1GeS>M!Kmehyvz~JWoa6x+pYYkAY4Vzp7qp-)_ZXK^4RC=
zKv>k#pUH(r;JE2jd`j0bB1>yKBX!{LX|{KmA~(RrTbM1{?B^$nxHCDUkWUh8R>ZD%
z5ynZzYGLDzWd|s~_tkXo;MpXPb_v~F=A)whj!!JEIL9KoQ#sg0@dHp!WrQ|88oE6z
z#?N~ee2^S{<?mci*vB9!#XblmhF#IN*6aAyi0<zEYAo9iZ0w$(R15J3OD7T_9C}qK
zE&knZRz&T|tSkQj4LoidB|BMu_q`^Bc1hzM65|<o#(hpI%4=FB!jO_if8avA-F!Q_
zl)1*<MP7?ax3ogVH+Rc(O3Y`Ws%bK*Kf4|Itn0V4c|t^2r{`RRw|6Qw#^pg=3|3pk
zb1cZ_W>?$>?EBLL*YrCO2>t1G?ho*q?4W`ulmt*Xu4}>eZ5EiXAq-ds&%Jd^fGSu9
zIi<xeb44H<jL=0dN-;nU#V1OA1W*GAu0zL`Cs5K_-FmR&BD(@Yt22-lc_z5e5bKFP
zB7_aU-W9zHZgMlJK2&%ny`asdv01RpPI3ic2%Qf8as2DpwMgx?B_dP|bGxl`bLf`0
z4#8LF$I5eFjIgTO7()=#IXFIbQl`62D^O#ld3O?@lzQ=8{Q7*BHyC8X`kHHM1{-&b
zHbLVRo*ta3Pg82rjYw!tu8*z33@9-nB)RNsy@OAR$`Ipg%>3@hO7n|NChA$CxETZ<
zJw<m~eZ#C+n3rW3&TF+sP2A#}Nm$vmvlGp}cgp+Lx=9Rdq+q{qrE|$~Ghll9RLLXx
zuKD|;6>R4^2Gme95I#ldbJnOnr!zwG4y=A%zLi=vD`JhDnK|aBFohAP_eafBU>W4i
zG-`yB9D;M{RwdaCN2U{sY_}~9yGh&bii%8#5nK4Vr(qX#<W`G(j1*^~J!<s2kz?gT
zG5kCpg0Q^iRp8?k>q%P;kM)jmNy6nObapZ<Q7jhYB=YWh)}6G;8yFQ!lby${U?s@2
zkIIbx@=SBw3ebl65+{ZxUq8z{p60ow64Ne4a*EGr?a$sr*n3hf$}v-s!NIJHSrYQn
z8>RmMSqtIDd-OGY#1=pokmHPc(aT|6ve1a-enBO3SgLQ@=%URaaB{r%`c%=+aUJ#>
zK2R9Rs4n#qo8H+8o)`T4)J~T=v8^hu4ArrHKo%EZ9sm_{$`ZFc({$ZV9bUn1V!&W9
z>Uyd4s|r7P^{*bR9A##Duy<DnwTTcDg*o6?F{;lLcUas7W%%=5)O7dq?T=mo9gTT|
z_>)+Y;Sy23*x&)pWy;xiJ=)6N8KFrOFC(>VTU!W#C#`b+1k<nM)0X1#%QNyr9-h_K
z$l*>q){%vYlP3*GIcl#Qgtay)(Jyv80lTJZ$u2ngYMrquaKp7-or1<|KH0ZjH*r83
zxy>Osq|OC5GypSHd+^kx=9n;fpb3L!jMG7-{OADOXx&MQQfL9C>B!W~@k*zhb3hZT
zQ-f4s)4I?DU9f5^i;pVV-y<M#PL{HD$^5N6?Kopi63$Zg>&%^`Eu53drlry}Wl!F!
zGRe5}O99;2%><U!w;T?>l|E7>!#3AF0jkQzKbZCHP){eFkl7-TgnN+k?IdTdFtFWG
zW4>}}tmH0wP%^>!`4tR<XyTGNG55Ms%E04qr6HBfyIY^mnA05Mm5*XN)K0nSObK`A
z6&1`)w7T}{DZ_(?9EwtMI?x3s8P8gRMdR32sXktuia@)DN{m#plQVV_!-|=0HzD_{
zpJwmHPaGdFT9WQ%2!=M5>E5$%Asg5Mftu)Ng@7as)=k8DCpn-DIU)fLD>2ZCa8G*Q
zxQA?i(y?V<-viiEXsEIsM`}ZbJmRs?l0X%we0Q(QoK|#dLu8IB60xPpfhPbSb5=|&
zI*-Ppw_M4`Pg>FlNzGCwMK3Rol~OWexM7Ue!^f4#{Hma}&Bpw79Vsw|<*hbT6Ecsu
z-HmHN%N)mH#(wT=D%KJt105>Zj#g}RBaxcslGN%?L2uOgh4GEYl4>|$6Re2blD%r&
zku<jMjgPyW)_s)zRnSL0_VHA-S0eW+2zIsz=|K$~;HRjqIqh02#=-)m?ii)LwJR8u
zE(d-p+PV^zndn{-z8CgBT!l=L<PULOrL=otK&R!e7Vy@kC8g>*90enClhjwS>Gxvp
z!6%H3r=cAwQPV;zuBGmcjQ6SH<nvY4^Vbz(Gq)b~(vDJkbb|m7T8+73QU>{X=BPtR
z@7k44X{7N<6o5&#fFaei^wjJc2URVCRO6wq7T2`dEH2qfkgRLnw{096^Zx)H+WAap
z#$#@CQ#kWP&7;dj*i^$OPIHREyCO@LWh8^mZC|0471w|{$7;@k2t#Gh70Vp}pcDa;
zMIc}^#Y=VN`K*JYo+`XR8FrJ3+n~$3SzqlGBjqQ7?_Q_jy#@8lwcWiSOmA#;uQt=6
zj9jkVGY`(bfbg6V*l3W9{Oq~Sd6||u;pn#=&dfDFXLf8_X}WciDo1M>z{cV^s+ae0
zBN*a_FnyM+&2SPXBDwh_F8i4BYvKO2UaNfaJxX+<N%pq~f<Gz+>-$x6&O6d|9MU>@
z5o_(zbpDi|ZkyCqeg|qy&>V=f_StjP(i{0n?NzgyQ9yD;vG&<LzbZp}DH!AOs^dAJ
z=NwQzL|FS|xb68+FC_l}BCGbLqQS_C&D_4<l_%Qd_WY^?MFQnSuW`9>$gTAi&UlZ*
z7P_UgO9BY47oV4m*6u05;kmAgHK#^OP-M=OWUSHQR|;T~NTpmnXAPQ&T{<SjY%iq%
zUqPV0b>2JDg|4mkl#B?ZTrnQJS1K&k+bj52+hMClwIx32@Uay6C1Mc)nZ8~L>xxM&
zN-*9k><~Osf)07Bw~!l{!z$$aS4XsWIgBwH0ni$e7n}(A^~Fo}H&r{bq;{*(O#)e%
z<Q%R}X}JLvoFT3wVmU_*UYl)??63hi365*Yqq$*o2}S@ki__~~v!|(TDGywyC*GWQ
zG>XvSwI#*TEIv|t)?Btxmh%wy=~`ORBK4DucB(5dhYDRzX;ivoG-X}G9If-<GVm&`
zrMk7q?}q8?SM>xE+yIO+MtGvi##FjTJTJX%N?HM-HJW{t@Hp*?=5DRba-5Hp^P26X
z09s=mv0UByZ#^(8r3j~EVdu;9Hr2;kvv*=G)NF0T6#G&mQJTIax0vl@<I^?CQc_YA
zIpLKY)T+Ub4NG|%M{rdE3cj^pAP)6gfnc4Bl{DwQSGU+l&FfV+5VYu_l5FivpREZ2
z7UD<Nr9v2B(<X*UTM{7#k$Uy216svEA>9Kh^{W!ti-#=;$FT2NFx*Ihs6186O+r{F
zSI^2jR#Hqv*78kY8a~AKsS@Gk<3F7?{@`3m<^|jItoNM8+mXI%j!s}Tr?p9;Vh7AS
z)*B6sS2@RemR&+=hSec+>BT?*2j;CI9#yEvw3%E}0VE%#HG#!T6i!Y+s{s;LM)s=)
zLhJ2KXn4*kF!A!rK&cS}MVIx>T#CXns>G6N7i8Oz)QfWJK2uLnEj6H#KXw3NRnZ+J
z+D9YOrnkPsVE6A=VqdgLlwNa;)V4AxB*bMIdi=OG8AOelisL7xZOd<`tN|sD%bboI
zy=9w8ZbNK8C?}KYNdZBKJb~Vsyf182i3F#j6OO{8c#9r*2d!wB3}L*S3<`~aQ}?r4
z5<(-kToIGk6`JGbBQ>HKAb(1;Yx7)00Lf<x1yV!JS&BxAMU^_C&U^k8Fh|gS5by?*
zaiYZ6_Q9vdNepXSTkubZ-%s)(wT?N6`AF+r)|2CF-6zBF+}&8o<rH6;I#$1jJWDT(
z?<GrkL?SE_<aHI#c620Z=zbp2{4omO7!*hV4I%AaAlEdRVlDQ#!1rpBO9*Du+TLIo
zW1QC|H-ggQ=(@7(UVzj{q;CtzFBph!BM48gTFUV@jT`8<4wI6_4^zcf9uc~>Kj`ih
zdscR(Z>iha&XP#(gb|8MakInjVa3$hKQMEjN?;)uoC>pcyKW|5_RU%F{j3+hA%Yv6
z6vl9RX1y5fa!Abc5dQ!b0hISA{sL>=VDRRQkpN<ck5DSW({zZsMIYA{rHHxUf;VIG
zK`VU_)W2l9*c<F~<J~LXJe?_V`?&M;qVm?&tX-ps0tXlsGDAm{>HY%oE~5g?29)MD
z`=qd6=UbNF2>eeXg7I4?`_Eq0;d!2Y3If0a7aR)NT#lx>`L1hY!(#X~uAjekXoJ|3
zS0eZ;e}TVLflq(kX1$({{Y5*4k0VclZU@b+0rZ3a0IyH~0EH%m^Q}4hMUU%Vv5$HS
z1RI#~Lu0YxF#INsd{mlc&HSd>;W7ta8-h5k``?1vKbN}N?&({&W);)lT*RI`($3-g
z$Yf0Bx3v^^vvrK&@(46@1&<+rgVs?T%RR#ntv~)1K7`5g85RB7y#!5v2;szoxM4`z
zfGhr!Xa;)isa0AIRCp(fGzjz?kF!P&#l{6<_&-Ls)_hU+Tbu;)%W^vNUDw37isMj5
ziCGvcXLsR`=Uh*Ot{&6IR_>b#C|Bk<&27(k+?yRXsi#Mz>d$8$;;NyAJ2?WS@h#Dt
zT@1(-yrG;N=Bq_KZ5SKIMQIm!+)STwL6K54LRj(YGf-qQ16E;f0L@U22VaE8df5PE
z9zPnzVb;2D7N*;<eS6n3PHWbqtP#mSh!d?%>rltmrUQ!Uj>b|Kw`xfSV?0sThW`Lp
z#Z%anQ(@Yj9}P%&IiypDu70N73#-zd+L*m5-78dJ$7dZV>N`*k9<;<5qcnaL9<%@s
zw05M&AJUGWS^!*PlZ?{!r2cdOcB7>(Jt#B)cjl6cJK#_;O%!9>G-vam1GOFKG=hK@
zj{MSfpb7*n6n$vV27!la3B?`yicFtM014@uT+(AScBBH(Fa;;+Mh<8I{AlS%^P+$Z
zA4*=7b)>}t3}%-&qaM^6V-7Px=|H3LqyfzzT0a^?k<9=Aa44nv&}o33`cm`w(o&8E
z02EQ28cg#@12n#rgNisb?g5TH#V=|~4>SOG%^h>vfr>iw{OJH5e;PV-Mlv%-C;-kV
zJv!0ejQh|5(wC(t(vE_F3IU_NEdVBS?MGT#Owa<F0i@?NV-x^TM-&P&Xc!Yk1DY{F
zgEVJ~2h%in#UKu&tu83-M?pXcXrno!sGtM28K9b6b)aHr6m=94N(}%9-jh7i_B50L
zW|N9u^cp}E4sk|v#TfLa0q;lBgT*d+9Vh`i(b|DQ>SzHo#T_$86r-g81FuRwX><5e
zA8siCl<GUu4miyWV}^P!EO-^_J`=JQI(&J?;sH3XHn5A%zJwEzyc+dOIaVkTbO3a(
zh~lh7tr|%B9HN$vY}LA)vB5PALoMx9n&3+(8RD&{%7VTkQL?e_mORdJR-tc7%vmzr
z)u<&H6^!GdB$syW<(UOwTscyE`&UlK&V`h8#d25d5<)AZ3ho7SAq~l?t?qWn0mjo*
znW>xcUWB5gftU4#N$q4pGshL?H!zqkWQg#f<$jgv(SbAra3;7f5W(c?B=laD^_($X
zxXO#@c-g%a;--vo!K3h{$ju?Iu|9A@XvY+B?Mw8aLJ>*QgGat70H7ag4JpoO0XU+J
zXT2HbkO0Oy(jK(Eb4iK-PW;mM=}X>@w7_rjr!P*F4&3oT1El~2<I;eAX>pIO7|Emp
z6N*l8nht#_*q~wxG0iC-g%kjt4F?97w;a%T>x@tU1sJ2J)7F!Euki{^j>3_F??D{U
z9CRH0Daxis+KSA50`o^Q6^4Ek0g=sIO)pV?QpR!*a+Nsn{<22@0POh!`j(~bBiwdo
zZ)!q5xvh&o4QjXKszK$I?)~dZF92%}!+ek^?nY`|XfC5rY~?y0w4_&GFT?BDW8QA#
zZ*8@2Oz<7O#2fDBeZzya;8Z+B7PlX>X9!tva(Yp{K+Z-h)8g<Rj}ZBzXFlZ9bsr1q
zw$UTSZ5}-;KDQo)dnS3H`Hs~DpJ7t1rQC<)w4H(Ic2}=i*jpu<6oE&}&lPA|qJIb<
zg=F!Mu+<aBMxB0U5&e!(?fv13(~rVB%)pZpMlr_Y&3C$-UR~-Oef~4)TMHI&%iMa@
z%N0I_swneF{0FJ99%Rucy3;MZ89bN98E%(q^&xB1{IR&?);q=JYkP5zm{cr8*!_|)
zQ@|EV0?TzX9P`agd<mr@7X9fX)w<VX<thFiedz>WnW%NA+<b`Rbe{}qLU#rN<mZRx
zx06V*i-fd<4`ijYi)N<YpEnh)jC&7CQ>iBR8c7*9RuG$K#0kLcwGNSPf(B3k+TE*W
zSWJ*h#tz!d)8qZ*fDhNbE4vJ_pPLm1p%VR@f(Zt$3wI|wKs1*&j`ofU<LOeH0v$3f
z_F(!kt70r>q0$f-U2~DTv`iT4Req+JBNtVG2$9M4$g5UkHmFJG6uPt9MP_`-W8<E+
zTE|(^MX$|$2tV&rv#@Ai2m$F?I-p-U8LHFxn?i_XucJRhSbEQkw4JHsktxq(PB4?`
zE@X7^g3%$yatAc+tWOKga>?-vO^Ovpf<`0L6$AWBw_NP8a=nSC>}qxwJWZ>}oizn~
zaxq%sIR-P{yxRW&$9GqA`LM$rc>eg#X|3@KSpckS2px{v)7VXiIz2bZa!IUNB51W$
z$;RgOt_E)$YtsTg(HeaPW=XB;GTa%O?n3_nUIjSerPN;09@1h1ac4oF_Npl)w2gmx
za~Sp}yjArp`9AgR&Hn%cs2*uqgEZ0-JzAQ=zN}u*^yJkv*fk8j<b3g*)#-dkqC!sV
z=>Gr%UO+mW;OD6{;1~O=`BnW{cNerhI_t(7Jbx^5w2ka54%@~ywzpD9*76i@myW+$
z=OVI{MfQnM#{e107~-H^V%j1aJ0T}*$bVYSUd9?WQs-x4-w|PtJ1ofqrdq4d@fPxU
zWDwb+XN4r@vF&_Ir!gsWqe4eOdYYkqHLS9iwuD8ys)NNkUdnG^mohXX@oupTvqx}?
zyZxGuZxm~D62|$5`=g4;&S?Rzk7o|XcV)YcQvT!>n(|jx`@?bOs+S~lyYXs6$E6i^
zNLLdIPxYn1AHp+AI#JMe%>n>;rRXU!k?BP+4CCoa4Imw<Xb@(Uaw!W19J1z<dXvKn
z0>i-OfyF9D@*my9B%kgfHDxsILP7Fr_aBPlmogefU@&RGRrS#IMnCcAv)$YZo<9w0
z3^OC!$NuwXvz179DJE9a&fB<%JsYX7N4G!diS({I*Tanr%Otvt0|%n6f30>_@rdpA
zqwZf?`0gO(ZAl)+UfR%r@W+a87^gTpjWpNJ9>8ZE=|37w(dkSD2PT$~QPBF*7!S^>
z-&v*F6=eq_6=;t1xhI<1m041foF1gk3QEl5W$?Y<n0%*FI~Fyqr09oFR(Y8Whn%lU
z+~{g4Mk8^Yan`*mxvnD>YIPomG;oyZ`_V@u;!Ca52v8IA79jSl0CGBFwDq+Mf7c+6
zwVRy%EA%WJ6evYR`OHk5sy4v%q@eYn^sb`;M@-bV(RueV#8*3yH3;kNTG|92W$|Ny
zux(uX{{Z@{gE6n{aPpDSg{RL^BeBz=SgpVVZcjs3I-g2nU?2c?sX7Y$wsLZllRmC0
z%E3hgnmX2H4Rj7LaBC*_!_Zy6{o5NoK&^p+?MGg`S5*vUY&*R<Sk9#=R92EO?EEur
zYao@RXCtL<Duozc1t|i60I08ssa{;w9oXs9jWuYX=|Mi7X!>`cb<JQ{ndXE1>1Z5|
zXc%Vz8Vv`f9lhxYl>jl3+Pv$;u!Ytgwvt(LO?oUml09pR@oI$BU@AB&b6-otwsj>I
zd0CE;xyyND(v!;rwOB5FDGQwPE9^a-PZyYr%l`monqnumDnlU@(#=P+LCi*DA$wp{
zE&&~CVoo{YqHgsL1*s5~!Q!Kpn0LiWz~hQ+sf8Z(!(CaMMU945SLB{+K}dDu9M)(|
z8og{z!JKBWLu7?{KU#W`{n|n|W7e$OTY2nPaL(oHUHDlm*vh7eXmf$ZJA1JHg0-X3
z(BpIC+*Op)t)m6p=hK?>R8B`T1Uuk$r{Z2muNBaxm74I%xau=gFWBN=l~nryntY`5
z9N2<MI)dKSVRYN61{NYc>vd&_=VV-uMX5)eRBeTaAH`M5$>uP|k1^!!AB{}9D}T>G
zJ@H!@orXM+zgkfY#9^Hi-i}c@8Ed02KfL`q)Qh7+4ofjLqvb4re(fqZn#3G6=*a91
z9H>`h3#33gf`1x%>2}Nf3JLV3I*yeaW6v+@38h_cN>D=XCq3xUc5HI#_Wb;nDp(-<
zpng?Y_>RFwV?mmU{8EZOSabOEMuBE($EPki9DOQv)0LM4ZapiRlf}0n9g+TLimd)6
zzJ7NoG_Hrr&d6D!oN>o&)4Zq`lIxGHa1!e`l4s4hJoW;sKA|H38fS0E6)vPvUd~6N
zwDu8j^B`)C^=&l)-86o+=H}_j{o~iUsLjKk!ll+orAeNK{wC7n+!429t_47RUt$5<
z6JU1&xF(s-M((s_+ch5F$bQJ}+s0PoqzrxP2l2b9`7PA@*CVu=XhYJMw3Fypvx(F{
zjju>MZQ~xFHCBHZYGmYjc=W|#2#GzZ;vPCuyxB=b7v}LEqdz`w-1Ws$n^C-x$@5MR
zP&!fMl4(pIFIp`&K4_wuX&ij#ajW`DE6BmnHA3-G71LSGyeMVIO60^-cDb!NT<A@N
z9ivhS^rSYiA>1QXBhXe_c#N;e@G(7d4KiJRcllw9X!U+;hB4IW4Mr79gO10bs*4s*
zHr1HgNx^9_N#vT9W60*cs&ti(8BL~rRi%vS5EGr=SSRwYJn;bk0Evs_W4(GNl6=h;
z*#7`}A)4SkMnB?bCtPES@KM@gD*WJj(s++Too(T|i32GaClsN8anCvLUF2~r-Wws*
z5wM!6Yzf%%izu-Z5HXhif~RQebW}^(VO83n!ZZGV$f;zD0<e-g;O<gIIjeC4QL1xR
zBU;IwF)X302x_wNQ=zD3*s!LN#(PtfnsHo;R}NB@-j!>qLf^Yk<EnxB*9EHhdRs|L
zM8jb``&Xh6$l=i8he9bYtYW=~%|U{Cspt(gD-h}2^9XEbD~u8=PRl`sftu~c!O=x@
z%i+t380=i<oC+@Cg3PV0$q47StvO61PRB7ZwXm6f%@9Q%g10Pn0Acx02bzZSPlj7_
zvw}GURwB&St~Q)t_n|wEaXLny68Ve4^{rcbh7Jg9HY=NsaUy)AVE+I*(6)Szxve5|
zNglVNTnozx*~Ty{i1C%It9iKy+)3iPp9Z@fFJlk7IIO=GATxK!?OVj;p68u3Q;*=y
zDhY#dhwEDc5uR6yQLzULTiAoF&_2X8-P07_qX#sy$!l?O<ROoCGx%12_F5ej%#E?}
zmajFNP`<OhW=WX3y8v_2r(qt)ZQ-jq7k*PGxan3u;TE+c04_a+dH$2)OPjk~2Vo$<
zY&QVb){UrY?W!=6UGcUymhH_aaid#S@Wr*gq>^prS0s^K3waU9!;h5XKKZX^)R)cD
z<lF)II({72lU!->{jGxW`_d2RNeuOG4NV-{QapT(qxn{|90GHS$nexYR*?@UkUISZ
zYqI4?#(1HDPwmkL+vg}Fu{7~|y#%U#vtCi+txE4s*BUtU^ABHo&WpuYfs{!cm?v&U
zNY86at?i7Dz}2K;de@(LPV#HJy!ou-JGtyVE6@~orUQw<sHC|_ht0sLNXV{xUb_$>
z1pXDRDtz*>6PGHvOT>O4D+iNqcy7M+!OL{+a8EU6{%IziiQz|1YKTncy{c4H5$9B^
z%*v8Gp(nLx+`9=kDdZg1grJupfi*_rCUb@S>r!IVGj&}<?NJC^Wr6BC)+BanXD=Y!
z2^?2V9*gJ3^7(+U{u+|gLU)lo#M(OXP_<^a<wd(zS7_2D;YKS;3u3WlfXg10J)MHW
zGq4Bgk~&r7w)ye5g%z&HJf(81aUI<;w~DZkk1bdDq|I1ZGmm<nIPk^s_c)|T7;^E0
z_fQTglF5X3$0v%kVq*vcA>=p|!DQy*IJ5GvFPc{ZvzC$-fq=$ynvPB%`BnEs5=kNC
zDEVrXYv*1?5C<gW{V9lw<w8J!ADOu{wkKqAOy}<KqNmgqVs_&k;0lJ{$ttDK?$qas
zt<V=y9c_Nv#Ce^8rGnxks6i&)7;QB|`K~6uhC68hg9MO!)NgRH>?8eTZ_X+?ZdJ~X
z#TE;jm{;ydHz=!*Cfg*Cb%lm&D(37*e`9c*BPmw>D_AP-xPu>gcUL^oNR^Js(BKti
z2C&hL8l>~8ZiZjHJ?ly-S?r^H=WA^=<O#BMU@*%>bQz1Kyqa#Xv%@BBE?oJM`}2cc
zsDGFeFms$&03(vd+DW8P%M+JSJ1-U1>G$yJcCp-BzCr7X<Hu6JzK+}-O*vW5_|D00
zq(aM+js<0SSHY=1qSse2{_TF~HP~tzc+@W9LJk+6D{2@cv$j-4#~k9k_?=~_6(WUV
zL4czbQt0iMH7&c6$2D5?{M_;BQ~?`)^EFFWK3&8zuO~dyR%cfkYE4h)u`D`)nnN!c
z*{z08ZnU~!K4Tua?^)Kem$o0ywKU)n3lsU%5u{tvo7%H(?~HC0KT5p}o@6TBDKHhd
zqz4rYvVhp34rl_%G`q1;_T*Da6VQ=B6K>{)HC<tG&zNblEP#FL0GoKHtBln(Qd_C3
z3cOGR;l)a|Ul<iEeJBBwS2^NI{JT{L8Rr$!$_;UzDRTb+CU8{a=~RhlHd$GZC-JFc
zO^1#_J*u*yJm)5?LfAhrpn_Y5D+nX8=~WD&scvO1!~=nhVygqwH7pTrI2i6}t&WYs
zs8E%Etw_t}5$i~zAaH%NPdk}^!js7(4ci=#dXVP;U~%a{5EUnkaqCQBv~{awjB{1p
zOE&-!KoJ3z>zWf8r1_P)V0uu#{Y3yw(4kzO^$3p`1F@?JM&3D~AO}9Q0N9f%LwBiF
zLg4lGsTXKmZKMn7-lVd;<M(7^tzz6nNcZ(MyD#0W`J){4=771+-m5C~C+S$z#z`a&
zE2Fst{JlV|$*qei9E|!?3z!n7Mi^5T*aO9CHM3;rtxFA`9WzqVT*X^^P^+AN6=`j<
zc@?4dP^vJrzD7Bs!E-W5hI&$4zzblC(0DV~r4ZYNY@E_)E<i2BQtw^`SY^uw0;Y8D
ziWPRBdWQtcRT?8;cDK;h0JWL*1z@-bx4m?&^DaHQRJQi3jH>+9C=Z;iBtl3~IKvEb
zD^A5BxKAcv4t`#JDL%?rXB4qS(aXCXF;9}h=Lq~M_I*oyeA~VP{{XUU&~$rGuv-0`
zAD1~E)k91sNKk)wn%jf|Gm0Y}ZYfl4SeXF_)~rVP7{ym7VClt683z@qkz>p`?NS5s
z9`#=}G$3vKDTrdf7&OK>Y}9PwS+m&FQb1hiy#aFcZMkz<y4{N3>C(ryB}V0~7>M%D
zDK`NB05RjeG)p`yThqi6NQ=hb;Wf(LLo{k~xb!`ZdQXmQWVh8zqLR4i7uL87fi=Ri
z1Yk#UE1qz)t|OafZQSRBNMD-KpH7t<e#gP>ifkHlyqS?mUuv#(VUSo(%c<JoxG#b;
zUqRU3m9m6n{oa+~OKSvoP`ZLy8;)z&Y$bDL7pPkK%<(D4Ha#pB%<0zW&9^@FRGMX@
z7PmR|r<(a!8#C2_XEc<QP-rb3X){appkef)ke+B1#2qN&iYW{!X(;?@h+0EHG<7rp
zb)t^_D4-61#&E2<F?Q;>=DfMw#C~1?73+Q|i_Gx-z#VpzUN<2pjMvoUuJoGoJbb}>
z*CvYWnJ_WUXhk^;Hk@X#b~fTiZ%V&!D-DW%_IUTNZN(mGZsJywUYO4uR-T`s`H}gz
zKX<OvS2VpO=j|6D1?#u@RZVML1RHyDRC<c2#T_(o@~G^M7_@B-8CZl2IR`b+TIzN-
zw%$mTZN@R0@{@5sIhDER?^8_k70;OC@v6E#6_@#*k8x|G+)id@Qs=&Ew7O1>E;kkY
z>w)`3*yd;a==((3{{UM50G%AjU)kPga=skWA09{t9PrhbduMTBI>zW)Eb!x{U|Z@}
zc9X2BDLZ=}_1)=ujkdLIvQPtm5I(h0<!3G<2P#^e{lFp~O<>&QFFk9s)vUhH8Omi%
za(A!=83g**Ts21n(60(9i2Bs9!l8*L1P{`p`;hKa#YS#-AsN8}xoXEzG8>=uhrK|n
zxPj|He7W!Spg36tFf1*ZY+z*jRhZ#xa;jHoH6@(u8v@<=tv0;1nn1o+Znd1G#AjSU
zCyy8e_BB~FnAsc5eWY`mxi(f$kx5TcR4%2Fl&X>x`_UVLOrb^~9OI#@5Rlv+wOD49
z93GXX;Aw3RzFAz<PiBe1QUz6t<>Qbz&P8fXe3uZf$^l<Wjey1|RgY>@owa6kLU#j<
z`qfq>bgM%X_=QMi+uozWG`k7nfGoo<NG;RSuQ^MI#!myaXNB51?^m?zNv>{@RN-^Y
zOA$_cM=$aMN3}z@VZ(7=pJCzKRERU6IOC^NR*r#SN!<#cV^*U+!_e~BqK(+$`CfRd
zc2k&GfE<Ez!k%l>BhoBT{I>A|f7z*pm9p|7kMg70$${oGTuUo%@}y(xRMMM=NXR)%
za6zvB09Kmb!pWu)N4bB8*15~rW7Kr$r;;^|n1&S-rsKHna|+g7vgHWLq`E{bcK{0-
z=`=qI4Pxudw%{+`Iq6Q<{4;T&UR!y=ULxb>D?}O#9Msl~mix94Nbgx~7U7lvH>G+n
zh_u<4OO8ahI6ZJH&*h2IQ=av-b^^M`u++-lURyj4l!Rc?4u`)TDX>S<-WayE);=7>
zvLd-KZ9IEbpM_QsTKIZGh&TDH82&Yt@TT<KcpN6*xw&gs;f#(gH5erMSuR`U^sZI8
z&~}oi?#**jc%w?NylY#FfMh2hFK?}M8m+{(dUVsl5t-F;5Op=<*B1|{-+7biaz^bZ
z%u4j4LrnFRnVkfQlB_ZfL4D=Rr_H}^aaQa$wS)s7z$=9DJeL-l<i1n3#*gl9;-wUL
z&a49Jw__b8Z|7BX_h_|?Srik7&IM1Zw*5-v_h;!*X{T<pYDw;E(1yn>k7~2>XS9vB
z0&&i2-qZjL3d+(OFmdTxfxFe*iv|=Qx+#})ve`+Fn5XfYhU5l?hBzadO^qX_@Kx5$
z0SxXHI<9*Py(X&#(UujsP{TVwJeub;T{vof4i?VLq^3AHtj!}zwea?+mvda?E<smr
z^~ZC25?)+u(cP4aTZ126!E;?-grvEaz&+bJoac7#y=r&yW{{R<<LxSTkGQ>Rt%r&e
zQ=fH)n{eyUvjC#2VI4CJip|w;{>K8NA!8xh4O&?)hy>f9_VYRZRaW-)1yqje1_h4+
zhDYaAz~g*hnDuQ2;2aS+Q;%{#!o30~42n9Ocdi@9q9|a}?%5BQ9m?bmxc>kmyNDTH
z-Z>MaC^R4*(MJCOc@+K?UTr=ZdH|-a<C;U-s=_=|;)ap-TZOpWg*n^)(c}Cp%5<wY
zyzwQJ2pCArPFB8v_^|@EhYYyOE8u%(yi>yG$??va>Kh00s*Z?E-q$p_^zA_weg6P7
zU@0|E$wH%!Yq9u_ci(B;W94J~tCCZnt!)?XiH%rFFUrQ8vrQS!bBdX0bjA;AWSq~6
zKY8V`>Nz#bdg8k;6UCclZ}W=dSRLlQOgp>|TAvUg=B3XS2>ZZvsmC?f6DbRdTzsaI
zlnxDOLMk^T(?`m~(w`^ZH6MJ}Gu+v1UQSnvbuv8Q8h(E&)flkPJt*%>-i&)wBu@0X
z$)JyFN&sBqldT=-paZ9+FHuR&9jF**B963D_MijSiZe-?0ABPQA9_slK|hrMFIqrz
zM_MQlQi@CutrP&gX+7z4j?|vmpkk5uQQne@09sD;xXJobcBBG|DLp71dQbuQQjWBl
z^rNuN04@a>$)Ft3$e;tgCu&~3MHB#Iib`LtA4&iXAT(#S8Rmcr2LhM9B>)8Dr5K=4
zO#mMFrRZp&@+bh!6rCwg;Xnu|rRncR0PR2sI(yMdN9Re~)_@L%j?___01X{IDD6Nr
z3<VSuM|uP(G@X8wXNo8Q;}m1oj<mc`0r=6LX$L*1&L{xL$66_JDGdMvr30lc8Kf}j
z+KhIittWosfeYG$NCr<dW`Gx{^`xa7P-qx+pwUUx&;g%XTv8m;^q>IqpL$L+OP(nS
z%^`sM*`pn4Paf2npaOx{G<T)x-hczrljt!=eoY-{5N95lqk<^wN=5;oV|#N;jP#?u
zFVcYsDNO>Cr2qnf$fW1-qa1al#*G~rcj{<2V-@HY@_f5V=Dhnz;`w>!71_ro)*PDn
z9wCkK2i4^*dlOzPhRs|1Slf=mslh2RdewOk-sc9sWy6{3dWFBXD!1OL7X4SF3c_bO
z;L~?Dahlia@njurdXfnCm&YBep1+hl#H#~Nv$kuN3L65XxzfxmK5fMMRMU(p%GWBz
z79oW&oEo;)QYz;hR0iF<gIlR0O&bOVE^ChQY<QM87{+U_vp|uZ#<@QhoS4WN0gZc{
zHtmX$=Voj72QGM|G`OU%zemb2=}DXlcX~#^JkfCoI*L8<P6ItV({cgEK<!1q2NY)q
zr5n@^xjiXWS@~Gp{{X;gIU(3X^rXdDhSKKZO^{m4BX<FMRp`7otV@hpFv#xJE~Hmc
z@-rtKQsA1}lfv4pQSW%sS07rxW#DVem;{nsq<QpOhh7V))j2bk12nsT{Z-sW@b!P?
zt>d5fYAe46Tfsa_=1H)hnC|4%eP$Q3E7>!P$Q?-hXap0%2E9%X1?dr@pCdea)yTXv
zr6&T;A@8(QJY;(h*t5tN=3=9gDpa<*kPj}_X9v+M(=D`%TWwULLl|7}0@p&ev93Uk
zN6=Ku7jA_rCyfmwQen7Q%m=ustb9MI-|q75@T2?2y?T3K*6cQ~O3u+#31(0S%Te{I
zHK6^HI5_+bt4et>B|d)yU)vyQE>oVtdRM6I8-A5nQI9rGanq$o)@m}nlujDQz+!kK
zlH%cp;mWTSqZfd5z;Z;S`j+cmK9~bpf!A*w)xf+|%DqnDsl?%LydS4p%MjYeGI|!`
zx9$8hrNt8B)*>;~jMa^4M%Z72jt*+XY+Bkgp4Bd-n%u5LM;?`8oh@R=vegB#f<0g4
zg*xLn?OKsBEseyHRPKR>`ZnX16qK9lI~u|?RpA%%rx?Q{1JfMwQkCcHKwq1=1Jbj&
z%uO+vUPzsY&MR2*I@VR9G+MKJ<Y3mZQU^715nAy#+qm|sS~H&_SlH!*bv1rwPc4J6
z0FPS3((mlyo@F-?g$I&N31}mHRV`ElWw?y(IQ;1!UD4tsHS}PPyw+x=;_VtcR#ltK
zEx-btAtv?<qgzdF_9y@+Z_8GS@mxKp#0yJkN{eQ0bJrBvekG_lip2ZpoK^b?_7^-(
zpIL>9q<{=#gIX5Rmx4Fzk<z@&Qt{rSewz{{gpXcxRTIWq)Nz#;DZ%-ETEDB!p?gGn
z@PW9<{7qwOs~lIzOn@J)d6b?h)}_g7`96ZPX1uw%Wj8lc%11(4syJD7V)lslAGFzp
z4)-yxM{`x=*0hBC*YM}i8u2%goMEJpfzvE$rTFhx^-nQ-L)2vPPLpk^?-OoQ&lLH-
zAZVy~NnH8?URCn)LZ~C!lsN-}YW}MMdq#Rx-x2Hrvcqd3Byde)L*u)crjkhQRd;8G
zHOOVXX*XxJTEoE;?HSm~@efyTxfBY%n5uUkHrDPVDAOPZ`=YtN^k%Er!?3y8qPpIu
zfb6}IH+98E`o5(mcj^}h+j**AogGD2vyWk2lC{+G{{XC-NB;nMvr&`oe>!OE(vQNQ
zDiD024nG4yz{$tyNHOV4f<BZ0pwbhLooPCX2;zVfB%D!<bj2y)P-y_%XEb)8oOL)J
zw42lW%6}SHDO@v0Q;I<9dImp1nvo%%U-ee=KhbGj4#P)!Y=rrE93ItnEhAK&a~*`d
ze|zQrbu##4Ta<zJb&uVo6_n~L6&RCWYHM?$n76QEpy2neRJk6t*GJ(EOn|dp+oJm%
z)s*l}x`XFxNLSHUy?Jtur$Tl(m6WN;HK3^8UgrF(u#dtT3Jl3{ERBxbRg<Cke6Csv
zr6c>!MQcK83{uqLyu}&$*B@Fu#VxcQ-$7mUT6T*Te62AX(|OPHsnA=(GX|e*pGB^p
ztwnS)<UH+3bA*mZJvdWVqp-f1?T*IbkGc_E__>`}U__(+m83J=ANgu|>?&R_vLCZJ
zxcoh=NssgwQR>Vpc>F7>vYpEWe(wJO;ayuvBcGl|Z*0>~BfUe#PoR4=bFuhB=%3!|
z7U}d{)T`k*SN(3HSbwmXt-LCez@)%A!KiqejIKmwFNXBBQeJ7~B<CRFr5YBHha%oa
zKJIHkj4d#nHy^D}x1Vt2L~z<^@eC%N7aiN0on}bB<+Ka*N{?~JG}8Qx{#6d7pHcFp
zS!>z)F2(vSMAO_Jvz~n_GdLf@Gw(=cEW82u(&j3{J2^i)ll3(b`Hl}yb4_sV*wj0l
z+JTm%!Z10mj=_uDoYy8L3)Pf;TDpBMM0kEi2abT(gPm(l9oRi2Ng%^DM~-S)hwmyp
z4A;)1*c;SR4h<>mNmK#af_<n2QO0NidVA0@NHb2wAQF+s$bH2r=zVDpO<WzMn4ZTE
z;t0sR+!WyEvCVWoBtind56a!EpC=~2Q@~H34;Fl;DO#%=(EC!J1v|cJ4R)O3aw}Uz
zyN=%EtehA7r{1#h!RM_ik`Ce2bmqA+n01Jx>At4aDtkGp9+wn?KnNr7sX6XzkJ0s}
zjI2_T>62Y#GAyaM8vNfKfvJR_EVe$M4_-B6bV?~l9MS**qdBiQ=oFmM)X~z6&;sYB
z6mmrwqygWGI(DP4)6$G_%`g!Aic!r3W|K4k;Y+}#=kueW`ufrWSg;?8<$PUg(oGYf
zB>PuU5!&?4W(IpyDxffK3GH7)!>j$Fo?d0}9&9w*qtYfdBIx%ojHW)Ox@V1*zG)PD
zmZ%+}0PeYreGPr*A@jV<!T!dVyC~<qNV+m(nLy&S<himzgLS_hK&t-$+8Sbx7Dpr4
z)U<&%RytjpefK2Qc`a;{?q#q#W~?@;XU5w?eaWh`YUiDhM!ucuA1SPEQ@M^k#H!-6
zrW^{pad#}IlYoDORT)Qo*9~;6Zvhl$p3misiezp8=dWsPubkHrsQ&=9F!igtWx#8k
zNc#cC2=&f?rDXs~;AX7Cj<{g8(L(W+$f>Ha+5Nh~Rd-DO=7Ff`YTUey#(MUyOcu$f
z0D5<?O;>#mS4AC3*Q`<@vfQ^A0Mi@9#Rd}52jg7U81b4swg)tOX$P`LK;9?0I4c}!
zgPN}XA-!edY;)HYljWZDr8`mWCd1jpy(X=9A<4LZa4HjhG@V`X?$uv!G~fX2XuQ~3
zC~=v;gt+`^rOE1`{uH2Qj2vW9X$8>GNEq9kQ^zN@CJCc7a<N=odwx`a6OPomC%qYL
zQOd&NZ8U{A9Mgb1sX+BOqmVg<`FZb2<%3Va=bAe4kH()Ma}n$VlTIipcJV*}cB7Oz
zgxlY>E&$^cy@qJTQi=<JOqzP9y#s;ToEUmlXe)}UGoCtA$OI2+h_@7Ek>BY<X$r)r
z0CuLcrySHLdkoU-YR%0Llvj}es&^7A9060huwG9dl}=ts99K1Y-X`>;VF1r0b*F)W
zQK`uz^r-;PLCtyS>A7Yrml1>>y((X{&5j#CTCEYoXQnx;01V`jk7HhiDw46z;*YKL
z(YH@UAaUBb9}}<oa}QD0yZZn>$fK=rJ}3Eg0uF1)M@fL2Re|^GUG;}L0Uzv~*904D
z0(uT`E56f19TAjuDtW46JeySv*Aglg4j7Sxf(>j;K3b_gzWruE-8W$8y=Y9oEoCF7
zhQ@YIYGfvxvznO_v60;o;F_8~w9ta2Km}&aELw`J0g+XsIH}e6sAI5<f|f6omCpy7
z8L1;Vl|@Kck#AlG+JqMLHB$FZk6D|2#7vEkm9vVge;v=5CAVGdy+?YzW2j2Yn}pep
zxfCIpacIk8vLSNoj_sP@^?6k_IZy%@upI?=y5743pR?JOGIV3<UU#WRQsLeDlg?{s
zBPy=QyQSSJjhCZt{3~wVh@C+Dr><+4)0+}w^UZX2=l6-naaXa+x#|8F)T6P8#`z(*
zs-7d%Qs#E@)1kqwFALZ~aSr(tECA;|)l0=zX#}}J+-DWhPgHT#_>NGW%z5USw{v5)
zPS8phagDL+1xBP0+er65mAhmeotmrYJojFe<l3Ac=~FNm8{0Yh*RAP`oefHnoxjq&
z+fk4GGEK)k)F3jfx4_%t<35$$_*+vKZl#xN2Ez*FAVJR@0C=s>41Bk1k+gDYf$Eno
zB+`i=#6Mn@<=3PAB3u%@kWG3_sKU>mO5rsdS6hiNF`s_)k{RfpA0+8f9<`*$0<%0m
zLDH0tovTUd0q5Q)(<8am3zZ))aw`%Y9zQr`So6j!xzw#vOO9A)y-@zo2`b1Rf!dH0
z=yq#uDzbn$>?^MwE1$9>&rk@h_2p<7k~m12+oFt`^PO{8-F+zG!t}1=TDTVaa~;^-
z#}(vqNMw>mCncPk^srR#?;Mzi&~&r3z>>d}HF|WXMu!>T)SgZ~tJOFeU8CUo(;$f(
z&T^RwzMbmU&HmLiaENs2pQ$|LQexPprCS%1o)<j(*1S+5F354(saUB*+!ybDb*mI*
z3XF8-i4Nkb1UzDw8RNO73!lcMzyzFQ6(SLSOq2Af;8nm=#(6akF@fK$HKhylW4<#$
z8nG`XXB;TP(^weo-GKR|=uJgyb>}cn%h>m=7~>Zp&iD~W(z9;cfs1#QjU!R+^xYX3
z?GjA?0Khn@u9%y7ZVGVO3z1nVKa*!KUPoN>S|!YYFXb1PY!j6Xaf)mxe#<SXP#dVM
zNUmjuM09dQeL=08%e83WzC{^e75i3}wulV-OPSTmNTqzY+nn^Pg4oS>A<y1i=7=V@
znn|N8w8`@W?@(zPi!Q6=J~oe+CX@0Rr+tB=q{DGBH*Z?$A(wQP(h^CMFty6x&#^A;
z+>MX-KA5fRIY_Xxa5{dKjYXx(Cb#AtLLtfDk@^aFeaR6x%O=xH7Z>*^NZQG|q1;89
z;PD)o&$VQRCB$M~I#^jVo<6l(MsMuRX>4PU5lp+6KDp#o@q(@~)0)4h*vEG@wdh}%
zCPy7JQC3TlrfWj#YR2L~iSr7AcikohTa~b+)@W?W&3PxJPaAAJ(=VbE#gzNQr6anh
zCyILPag{YAIje@1SnfMm9@RQbWwDSs$*HekEUtPtUTdDVyJ+QgZ&C=LW`&i}iCQvp
z1#3ffl;GDbZ27t=lhZub>_03yrURyx-eHs8x+`;wRjyqa$#ROmwbG%*xE_L#5i!h%
zik>>C7@0ctt4MJ`iMgfPX%z8G$sK3`r*NnxXRA0k>s4h3o@fAwob{>H`_*{;YEazM
z0%B?LNruHn2qK!`FFeu$>wwGBxK9)Ds4^44?Omi3hw5`&2Z^OEt4o9Of&EQVA(*+^
za641MA$dQYF@Jd7c@*hJ;nso%2HeL#Tu{;N9@NEOoHrt+!Dbv}RI-r}KQ4VL#BwVp
zbA}zNJbc}8$4X+Z*2wAFkjcEw%s}r=B!N;v7GD@N`D4QKOhtA)@zS2Cfk_;bNC(Y~
zQ-BKCJWvE?H7q+)yeK*jYF+{6n$3(3^oB-(LjXoIR(!Q}#}xyN;87f<4>_O<1~9#8
zzFi`@mj^WUA1ORi85<})xvG=G3E*O{>^-@~MnawsQ9#T|?UbSRs#04oOmkfmTdB_(
z`cx*%E%#^xpB8BB6t7=uyB&fe0k@Az)fOtaAm*en;G7N(CI&gTBY-%n#sVC!E1))@
z{c60H*fb2lcyZH_>rz8+oYm<dBPVWY@I#d#@Msx9pl+Drnr*#vTPbK;{0%kjNL&&4
z(y)wmhX>ZREp2lU-~&=eYJrCA)##!DaJ{GzS*^iQ(3+Y%4az!aIjPZ9HC%;3;}ijF
zPmjx1IPF@9z&8hvN~0V53{>IB&mC!ja23zYX}f|-yHCn`)qgM!Y55*kT4b`|kni@Z
z5i#l0(x}GUv7BbDMsfi(#6x(cZWs~6RBIMnJG#{O>cvs}V;QP3N<sOKC<9JBig6ji
zra;*Wz~mZxWFKk(=lox%$#rIvz&>RdIUHA#>QcvTJ0WEb4j5OyIxM!&6ZBz<`S-`#
zP1cpH6>v(sWH{(XF;}_~QcXb#`K4c_NByH72i(PScL?a*yJzcFn4Y_v^Qmz~on6iB
zMGO3y2d}+)Zj~pQr^HF;9la~TnVT8hdgi^m!;B7%Z_aQ#*MpuxdpNXr;P+=!U~_K%
z)h>U@sC42CatfQhd~E(Eders<>q$X5=|HJ87Lzo+=%52MP(NB)1SWgZJE||vcKvBZ
zah@sGo)+>UX2~4j<MppkE6Zn?S5%;5h_4zD=aJYX(Mo@JDzWYX=AJpPD6!TqtZszC
z-T459a@<#^SzWE=oKvqG*EsaALptI5nQBwL;><93*kV_^xoVJfqnaz{4$*%)JBm7r
zDFH)W8?;N1f4YB_c#_8DLFvXT+;v0`rCcfKR=j;8VyCAE7&Y|S9KFdeGs?^ssG}9D
z$tr~BHP-1mB100-bOAWvdQ-G}2(47zPmlI<+Nf)~<4nyAEwwrmn)(%~%R>(8NOrle
zZzkH=wyt?K%&{%h<n^GOp1I98JkZ(iQl%Pd$WEQ;JQ@MbCj`>5uxHwgnp!|V{Zv>5
z9QstYmvdQMB+#}Bo=2#tNI9hheJCbTQdVc7>3X%cvuEVYL1V!Otzv8XV_E#bW;4;N
zn}T_5Ci5Y3r`o%{Ggi0Otj)aR5_BNfMLC`(F9_l9M`MYS9oFo;bgYL{y_E?fyB$+W
z`xCat${tp-A=6S;f0TyzJ?TzqJx?*K7>YLgQW5BC_3oPRu`9{%S;bvW8zbvYNj-p+
zNcbF(MO(M?56tbF&d4~cwz7oCV@gO3m~L5AuH1v`P`k!Y%!8VS8M6CS^{dGoYs;u7
z(AEz@88<OU9vKH(rpG6WyQz>Q!tg49$UgP7b{S$Ai?3Q!6o`89?MNpjani0@L+8hi
z=7u7HQq6{LDdsg8!Kr0{MC3Uc6<xAVT4)J&g*?*bMln!jf#)<5b3hhDZa5;fv^lY=
zM;_91SV71&tD?+XREY2nIi$)*szJhhwH$?vo$2=9>QmQkCB*9jZX+kK^{&`#OCsAL
z{wiVKi@5&)4<?wpi@Et=IIL}JUwdn3LY`dB_kAjaQPgIWS=OPpi2m(Q%xh0uvrBy;
z5jY8g52h&azM5f&?J_7WC(X@V@f1h<G@JqtT>5vcYb(UKvp2x^jccx^ZalSP^AB3-
zz9j1Qa%u7TZmm3Q99J1_Z3VJ@syXv2^ikHXTljnXb|#VTwy&qHaK}bjzo2-U(_PY5
z3E3897%N;yiFD+&za}B_H$zEjrOl&jhjv15+N=-Wt?v?AiL{Y$2h10}bw#3Cz{rEp
z(_)FFnIliW=K`mYa>A$4#@%wyC}jEm=<h^{Tb=&^!`))%M}qH9kZtY;Yq9ugseP9J
z08&|mgh@8+<083_9B7l<*xKLPTFDUy4C}@PdKbfs6pzC(N*^;g-21DZ$4!pB>NfWX
zQ9fp2(z$EvCSNgRwj-W0de>JKsw9EN(tSl!*CX>G?V6bsi8Q>M7>WMxYUTVxYP0Jb
za57V^bvju806~vEmaw&W-0P4q7+s_s)RcHXiY(2py*yp9n#r~dH4A;9le@64tKtk>
zJVwM0Hgv8<CR=-`Cw3~aza&?6H+UTKUh(UiJ@ioN`>sEAfs$Bst0%<TMnbLPF+G%K
zxmd67ue9<l5ofn5Lr5#6_*J6W++5vU%K|j9$%QU6wwF0JFUNOvD=(L(U9vIZ%y<=}
zbK&0*-CLg~D|nH=zQ=WU_bRJub|@I>iXuDg{{RY?GL%kN!~PDq)9i#-TCD7?%SRJ!
zP=2+w7lt%=_h!vxW<0c{u|J(&f=!VQ^v2YHVmz`j+|=k(D;+w@I|(66SkwS;0*Zq`
zQ5w3cgizfDa(*lLooApdmdmzVhRy=^uNRx*X1^ruG#8B!Vt!G@EqVd<iFH%UDEgYu
z){s7%BV|J-8A<xr%98v*@fF|t>-mqcd{d?PhvH|o`#b6qJVav*f2~)%7CrOFtR?WA
zPmz_88}+W!PCK;AazD5$<plB8t9=YsI)%Y_S%=|@`j^9#EzgJS=2i@^5|BsIniDl?
z4FjbIrC5$H;(R`5g<ZP`P=6DT>s||@v5Ur<TlY5#KLXgVq5OSs_KykO0iTqsaqPg?
z&QU+vd{1F8UBxbA01p2EHbo1lk68Gh78gx*>GK2nR}2ORO6|TOT|LH^Vq}GotcU1F
z{{X7Efz#5phr%XEP8OsibRwh4BOPh#eq3g(Mn{O3ewN3$^sXNVI5pmDOTSH&XAS=V
z>#i10zt39qu&>-XYVI?mRKU~(^HV9v=DT2G#U~x9!kRg!Eog`<NyLVtH7xu&sE<x-
znp>M9++TE5*!t8Ef>dDUrxm13rMOYrmlU6+Q3243Oy-t?4FDJvccZlw0DDo6)O4dD
zP%y`(9jP~VrJw_~B`zrZr~v6j8O<dC6m_FHG_(Mi=8SVjDEw&v8an+bqJRu@OPqD2
zqJS5z7~|HChJ(`-0G!d9I*!zJ`p^J*qa0DswIQGd$Ec<H(ov6U04YZll)uV=4^Akf
zG#);*02(NuPyvo<I#Q0bcAx{&j?@Y}Pyvcg^rP<5e@Xyf=SONzX=nh)){J2BMFep`
z2zjHLS~13G0Vw3sla9Tqy$u5vgVQun2jxJ69G>2kAFUY89S6N27LZ`l(j3zO>qp~C
zIi#Qiy)6Qa&;f%;eW`m=QUK$QX>o%<8R}^dN(XU4qJS_cKGX;gG-KY5ooL9QVh#-l
z*EGK3f%TvRJt#lqQPz(10A`9h&_{7V26;4gqa0DTkid=w0+$qej8Fq|Xd@kI#Ak{^
zD7aWoIRsLXN)*zS!S|pnHi`(KkPkdk0e+N(W~7ZCRy!h){T8l8q-s|K_cjx`J+>NL
z$pwu14Q+qIDXy$uYw5D854>|#wEZ6MQ@#5ox+stwF@B3no*`yu4wM0!?+?P=S~yIz
zTt&4;c7a?~&9hqENelhx+^IgesZ}E_nOv<7uwfnaXWF|Mn<%F_;<$uwE=6vbHP=|m
zUKL_PE;z+}mk`mk)kEm=iTjQw^{W#eDjS2fh^4cWj8pEDBO|SRmeW11g(7*U#+jfm
ztyqP5=xa$z$Shm4lgK-O&2B{;cepIL#bU;Tjw^Fc`9*p4-`ZQ1VoQr;PzC_{R#dRB
zKQ9%rJ7=$2%eml@S<-Bq6&X=b?eAP)iD9^!=y_K1Nf;T*3hhGgkx&k%wuQ7`V=3jS
zA$sDz!-t~jw^g1_XFJD`@q1kpQoa8GQE0?>C#7h`;GJ$vW;oD#lbZC6A89jyplv@X
zQN?QYJooQkSu9+-9s;6|CAjcTqi%toRQZlG=~~u*4&!)MN$%bA>BV;1q7!G^0QaS{
zlQt>GBaSK_CZj|4Q8{?N9_fmHc9n<w{8SI&9Xj7sRocvhA1ORnVy}{Oip|u6E!1-7
zra2WVtlv_(BDxaApy{wT%V{6iXsQ1Ivn{YyU_ta1c~0eDpftVkI@WyB?mHu%(jbm2
z`Jz~Yp1mt<L<d2idd;_AD_eEw8~N72=N|OutGFVK{2Q%YvEh08RC-cwwE3~PF&!%X
z#0BkTRvZ=UR5YetvaguGd%IHTGWOm&epQ>R#GxW^2sNc7_R$~ST*RaO>d4l$ohmC|
zn(8-X<N#^HEwN~7Tj1M9Mo1#11E*@hwDDez9jYvsLvoIl48A<kV<%~nOdsK@_H*n{
zGA`amV%B4lwsDc|UVo{0=GuFtlG+kgc;=q}01{*zC6EWUNUQb}cF<nZCwYp<)0fNC
zW<$p8@my@*5w$nZl>}-&oYq5luU0n(VJfL^qZM((PRw4`C$V{Cj+G7Kuh}FF$^jio
zuO64g`qaec@rSaSrzWeY%aJYQtPlG}sbMADpK6a<(k`tchD2+W&hG72<khsuv%dNf
zj=`(Myw(}Rzddlqm`>x#CywT;>X+&s)b)L9#9BCmV%)2;_7z^&#`-jN;T*YT_OCGD
ze@aZ|uj;X|y`w!cPl#GdjHD7ZWNKbJH&ev+_TMV<LykppVYsG)@5MOb;DzlO+_%Jw
z<z2Dbp~rJor1*!eI{d2&{{X;yS0Wn}Zsw^`rn(c)BWb)xs>yNopR@&&o&e&TCcmsq
zcRr&ck3{0B=~l7o8i(2Co6C$Q?EW><{{X@zV&v_)C2`Yvshvttc4(y;vz&cG@=w2e
zaNk!oQOc9MB$MBDbz{QzMEvtQC;R+WOWhk!f&$4aNK_mU)T4-|-I5PyKBqX%l5)iV
z0Kln)<B^QhSmBO3P-~**b`_3I8SBkAno~>!&U?|CFi&h!gMrNe1o|2}^`MW)ngPho
z1F(NOJxw&abu2#)w4u=OGIQ-k&{%dbIiL@wY4OE0yhU#-{{XtRWi*XeLxr%DKIas<
zkaCp|CX*PgWbo#*CO27x9m_bW*TPzf`|{f+JxMgZtQSz_W*=_!6YpIT_(oE3CZ!4w
zK(#b}5VYwotPlICil3}g?mkD@<_9PG(h{nE@ciqu9u?9NF(lK;gX>me(KI+YOBR3k
zoREJC&ElYn_H5vbpyW3mqnb_IjubIJO7wMG3xD-mb-Ew-ML6mXIF2ZQ_7$7PE{J}~
zo_?Br{M<)lI}csB6>dKc>r#$1_5;+g71;j(Xk703WB__?sEy6bbLNrk4QKTL96{s0
zxpp72M>w7j)!Q4^2)&+9@T)1{smUI0r*9v8D(1Azk~dii&ur5Q?a9qc#Z8S<MMdzH
zihr)vT2Ew5Q;&yq2!IavbDynPGhkpIYCXld+-o;pqv}$ELqD@TJr*`;@;UziY0XU<
z>5u?o(_tRuW~(?Plg%)K2O^==lj=THUTe*~M+6Ezm!&nY=Lh9*K8sZ_Lebxzl)0N9
zDPZ5+lg!QdQX7d_a_^s9)pERar^GUTl!s!(a<gD^X&H`s8dP*c&ILy;)v^uGG;8&G
zL$L2PhjBoZ=aW^RSkj|b-FFxK1m>x?h;*p>Ow2u$(zsaLSuh6`IyWD!a_{2XDE|P}
zMJxOCs_o+-RE4uS_j)cCJ1;Rn!6WHGnJa~p#y4jnZQ@@{oYhD1KBoK$5q^nE<#L{b
zypz;sl*koGBz4DH^Jz8hPC?Dn5BEkYv)|rJ{<7+0{{RCtTr7H#nk8SE!1|i0KB;2?
z!(GA;f114R2X=G5M{lcUrMQK5WDMiIbSe$Qn4YI=Cy4a4AMy03{n47KCyKPiIS(VB
zWUdnwW7@gh%d$Hs@r|fICA_Ecs*?D@&V0L2Ki)OW;*4UXERE*zW$R~TP_Mo!2Jtqg
z-}2QL*ezqy(;0eAYf+TtuAF^1s2cL={`JI%{smBUpo#!_X&<Yx`kM5=1Ik*~A;I}c
zCp_1gFHS4aybAkvbH#aiv~NJ_!#haq=jEy#a50LrH#n#{74oT`${0m8g-)rS!xYCt
zItpowhdAPl`ePKNdeBBm%}|9Nv>GTp6U`xpIUG__=hK=G*P3WYJ>n<}+DJ!SWE$jn
z_04zsls;vn0zRU+7mv$!T%H)>zeLDudrT@_kDSb5%TnV`FiHI@qS7>rTgW`d$!uc)
z^saXwFK%n1@but*=PWSBwa#i)r9+;ZwT!S)jH+5jcBP~>jHIUGp7ovw0=*vM1h|Bw
zC_HsF#_IZ6vu2TbQhQc8PH!Aa<e$WCjKR8o^ma1A!N{%c8(C=NSY>SX1lK+oHyQ6v
zR>23*<YK$=*eZCcPBJ-g_2oud9+wP@D9W`;2PU~~3sWuxPQ!5db6r9(a2q-Iug)=;
zN#UwENcwseRao;Oew3$yM{cxYxQ&CQFC2<Hb3x?L0n(713JK$i2R~W>P<o1A(wmNG
z_U%9l4>Y)@k&mS)>C%7|a2#Xutj`xaE|ggx8+bT1ratigbxXu?`MNZtxn9-kWc3_z
zQL)91jp?(_Opf33(VOaNrbZnP6s2%+NP2o#->znS?t@Dlb3q5!^`s}7Flq9N;t@??
zIT_-dah{yh8k30ABl&U1H4MEtsrK?sM#F<xRECC;Wil{vKm?y^bBr9)1+EUJ<)}x?
z_3u-tDu1n4w>ck5x)&p+E7YZKQ<{5?P=5nQIH@-A%>)sF#cO0m#*EXlK%~dh@HC?s
z<C=CA!}us4%A6Gc0QIRh=j%?wxR~cOpn6ag;PFlaBOv{0h(JFYObT28Gx^iT2*_cd
zN_P;<QGw}C3fSmR&{Nh4q+zxhe+11JL1G{VX?Bd&=(Jr{U<`V7%MRF#^H*T-pNMV;
z$)r#J00IPmF-x5a#v$v^Y5?N8sJ<R}qEIoWF#52o@O&%rOv{r5F`xFDrPYG!S1UM;
zydEhCUrO|7{ts)-k2dPvPoOn+FN3#3iM4oB*mF?p$GG_!<-2!uADt$`E7z0Y)t?PM
zv60*={{Z#s<Ua{KI~n=4JBIdO{{U4ltkVx>&lcD*o|I)W4tTG4hv9#Op<kR_OnpsX
zhrm7&h<uuCkM+r=^{5Zov*&!M>ykZ%Jy$#c{CX*`q~q|nhoCr31sH#{D&%@bmjKK<
zEuv%83WtkbiuO$TiC~^az_*zDZL4r;I+Xa?r`$UGC4DZd6ldkMvX9@2b6+fdF09ac
z3|4Z*U!h8yK6FnBYtw(K(e8g0BCSR6`^6LTx@)TAqj6sH+Po{1CaZ1-qT;GQh;+0+
zKCzto8jq|##d|Zy;`mGAn}q)WQxXIH_Nmw4j=d-P>$_<G0N`K!YV`@cQ=%^qeDC<x
zfA~wZ6bu8%`1y@Ptl3I7I0$|RN`QT%T!uFEU;hAIU5ntxl%MhUuQQ(8MRgMR<3w2p
zmuT)t&QAmLs2|6+Ymxn&-rqKBK4F<Ld?oO-OS(-$?m#;2PyV%N#qj6Caj+&UsYvc~
zM4u2`FYa{M^XN@P-w-tne3q8$^fgMPmdsqIrr7Zc{{TwhyjC{q9lCVy*1PK=`<!}L
z3F6Rx+6eWoQ&XE9u&)0AMm}bWI`XHl(!BT*4stl=y$3-50FW?ToP_K6RRO?WM(e7+
zasISmk4l<R^3kcM{7mKcG?JXAYdIsLi_*nI)|5Uw)J||}BK3rk-3DF~d(*?#ddX8P
zm6J9_^^&C$RTX-bUbAB@87WdiBwl-pueyhDi@5fr45_N?ZKcePv3a>}MP>Mt#Rlrd
z4X`m~eq<egI=gddx6Ov<K9!xV=>p$R`;E9(k+)Mh7`_@uxVd>>JdWo$HG5aI1zCXk
z!RzZ<z82GrRxL9pEy*;u_TlnD_UTrhr!=)W2qI{t2cB!8wchGB@Wa-#?jZ8y+CLi6
zu~spA=QV6e9<||%sO{{LTkkOIRy98+?m$S%KDC9UI{lU%yz$N}S=*fRT{ISl9dC$z
zqd^00k|i<cIjfg?9+jy@zsXI<__0|;=dEh#S82P-m!aai8o7<eMW&^-n?$ej<ALd3
zRjXNDE}=7+$yQ=UIu1@N+2^)l%5pnaJ>7&eD+yv5J@H9FFuCNvV4U|O>0NJzEjA;&
zugtyw0Htn?2GtM9xc9|R4X4?@RTva|Fy=Pe>NmDjIL0t*5=|fN8<{>~o|R;h6P%A~
zE$?0lP7eo+QOX>~rilTyu@JW#PXN}7f>yE;?3UcTRe^Tcsc{|7a`Bz@Nz-}s1JG7I
zz3j(SFuQS{2YTo(Eg7#GWy#NK#QP-CYNk^d!EEGpz^LS7<~n;=gmVH7Z>s>H@CUtf
zf@azoP7keFTc>rwG}IXGQSp`FOFfAH05M*k_2-*#i;qlJ_lqu>=8ho4hQ<wJ#HE`I
z1_gUqSaQJgtIq7P3}F*J>9RKe0F-p4-H}QckLz7WF&t44q@T{DW?^CFft}n`>&1(<
zGtXM8+(rg)1t2cz>KVra3tBJo!p9u96_sHw4#Cx%oO)KQ?UpOqX*L81*!%@a&;j_>
zXo+S3^vzCKmUrwI6o7W_8M^kUSaOI5J!z&)s;c8XO$hC|q|eHuAB_XCOy0G;(vy%s
zhaQ!$W3NSU_SSQ_K>nHes}klRu}kCTVN~^-VJ*}$+Y-A5c;lKHOla-3R2N}mw=3nK
z=N;>hy=|*3Kf|8YXGQS{TRALdVfLJmGga?Ejevf4diSSISy)XOA7uvSG)HfkeB9Qm
z1$#NI-M)3{io(f@QdwhSP#ohqt&6@UNxCeU=B#!QN3z)_M&dpXH6^q=<oj%75x>*g
zpo(K|(!%-KCqC6{L}nKER?;uZ2`EQ;O^jVh7~Mwy0N)&p*F~nT-3<_P<&l&0u6dYU
zYy@SO(APz!Wwhzg4t**o@QbN=PIWtW;E5w69{&L3Q!%;=xQ9?!fID}n{LQo2zTx-q
ze<M@6;{JG#S6<&r!>MD@vMu+2%WN+mrn+r5+*;VAeMlJ3wPfj5K4r8<KzBymeJh|G
z3gE<4zq*df6z%Ua8JmJLR2bq)mf_EsaZoot#}&qP4`x?P6P(jw+LB-%wF3r5IDGq6
zIc`i&GDS&7t=vF@M?GtWzHcv5amUThF<nU13n1=24RX5L6MC|#Ja9!YA+($RCQI`S
z8tJ!UA9~~L9h*?W>FZr=m<iXlFeb1<({4E8w^{KGW@*vkGm6lZ{FJN&QT)cNmny#X
z1WS%;W*k!y8M$D8r3X>iIRyPEHtOe^U$CJZ8bB&)u({fPQ%#a(enI2fqLR%}@HbEs
zZ*C|8c$gk4ZYn6i#XYh3(*kJu6!{|#q#A}2Y0}NHaz_*aR!z}9Mr(uC9LcIk`ObYS
zwYj+sn&L0;*HRxtOo<gzO{WH;cNsfR;Y%u#q>TO*Sw40fPbAVHoHlAjE)N|kvBnhR
zsHcSI<vl4BFtZb$ho&k>m}dv`sH8tRrbfqb>GYuitfy}ul|59-Ivk3I6lcccj&oKN
z6>JW_&VVblCO63(R8pZW`qjBfVow<zMOJplxD){1rx_IOicU{aQSS%6OrY%@X$+0f
zV}a75D0gwlHEEOO9kER-wtyNUD#3@{J*q`=k4@cxf4fQuJt+Yr5!7@&sxk)PY3QYh
z8RDMM?Kz-gFU>(r0y*csNReZ|6)%=Jq%xMyIj6-Qc=oFvS2(2DRN|P5?HLW}QMv=g
zTXf?+ssqU2b)+*oNL+*c+8~c<`G*ytV>^CoK)%9&A^<QuP7NVaLC$KzC{kE-`ckrP
z9Vh~m!-2&{fs$tDuWGdF%6ZNz7s&e11o2=GYPkvyp{qJK?ZsP!<NfLa<>fm%9MzO0
zrbz4BsYNJWqcvzaC>V60M3~C)N*I6?_oR)3WQuD^gOVwTu^GrGrCqmRR~1DhPTgvF
zq}<qE!kCNqF?p756#d_rRvdDMk(IxM^IOqA==PrCuo*U8P3gM=fHf`KBztrfJ1{2%
z^X*ja`2Lk;$X8R(J?H{Wq{e&kn&AE<>8DW9Qt1>lkseQMcg=V4VTESg+edY6b8PF8
zARuO`2>FKc*nRwPYdT2BrFLE*(i>0ICW+LiILB|oxx0vV9N^-aNtu!iCr*{@-W6@y
zEIF?qVU@*t&x2ofhaWuvuNOLBxJPym;%8^3o*t|ozO`FSKQoVNwA^!F5mVwldSZT*
zV-#oJii1$iEhQ}g9q7drW`Gg62evEAJVNF5R|Sq2wR)Qk%4^HKNgtQ2&76GL>0fcd
zDSc*shl`y*+@l=Vp?E6gr_sW;PQ$k*y!4y{UH<@rVJoGV846Bo>bR{(`#N05my<X3
zgQ}-=6w%U_za3}Ri$Li~OWUO&AiWu}n>{w-yglZTZ-|YXK42I>g?p6aeXOhg&3I+-
zXmz90<d}XUzLz5VNb|AFW3tsii$+tPcH*-%O${$&6I>8;&IsvRI-&mni5kCspw+Dr
zh31K}G6R9P-oBoiMsaeDE5u};9MZ1g*%|`t+;D52i%GV()SA}!?tck1$*#2x6H<Nb
zST;bam)e}Svn#(0Dx~7N9W-H6`LsIdd^Mxa!ICv|j@>E?pATs9#=~kO4tN+f2ZLsn
zqmfz3!w?Dl>odeMx@wM!>;^J$YVRIP*v2ub?RhzgwEqAPt>w$^Ai{?NwwJ>?K~E$E
z5`p)-)S4GMADTY%E`J*4ZLa4U+7kZ&dH!LX(pF02a;Z5=(%6q!(N33f@-Sp>nXSz~
z!#aHSD=f$e#&X82_?<zpSL1L4pIWhQG2zj)5rN33$hnA>dCHp9rT+j3u9YxvA(S}j
zwAKOBrP6hHl(ETvG2B&+25XV5GM12q2O!qYycFMBk+<(;ni^IPc}4O!dzLlVSgcja
z1o76nh;EQSrEd7Bh0vEha5=6TDGM;mRuv)4d6hRc?_M`u%hc5ei7pfeUzm5Rainv{
zwVwv77~Tmsk_Z)=Rx>G2rtJB{ap_e`6>spZ-J)2?>GiDR3wfIYZenqP-n5NQ;I%79
za_GXep}HAXZ_1(m$i9)Xma-CiVx>ABs;ju#HV0ptrc;CJZR}?H6W>HGaU>~`jz^_t
z$rn&~BD5`@;?1z|FhV)cN`igU&AC@OqAtdAgrm8gwS#fZXa<@qa51z~0_<=*`&H1d
zBqe%r-l@ogCSNhm;?%&~dew`FUfHoA>(Gj%&6mwu0>_zxC?uZ13Uo1vG1`d}W0n1B
zjE^5TwQ1>*Lml)IZacG#R#x&46{DuO`$R#y?p%I!q%+oS8+EF4+L?X+s2t}VsVrM`
z3G3dSea*ikHPuhyM6#rX(jD;}eQS=Ech)uN<8>ZVw_jX;`s-g`)J3+Pu^ex6fGan{
z)}|IoB<0xSBvpv+t<XnqimQMI1yt7t{WZbojw<wAsQqfTsm+U=6Ybu!sql>+e-)&v
z72{?tkJh%d%gOA^Mlpuuiibeabq!AWBUoheca<)u(z{Eqhi`3Y^9kLZM&KH}=9@G}
zJrwRf`gxfo^rKYsrqfz9AP&1&cC7fdIPGs0WcffmlThoo-h8Og$+<Dww5NO7gJ(GZ
z0Cb<ypJ6lG>bA2W%SRw?l#+64vywU7M?I@|u`6@y4L;fr5qMcratg^F4&K$Lq{SQ-
zg4PsK97AZpuRZv8HT9Q=7H>Oz44Z<tBvt<a4r`i(n%(rMh3wq&3Hz))D+F}d?w4nr
zah=~<sjTP901j)Ki^T5!D|=Lov@V!pKZMkp-198T4admc05vixBUaZ{`!pLQP(bt*
znLe)_#<-FB5&%cu?NqGojl`ep2^jUN#(Ck@e$Ry`s33DtQNesnjIO&ADB+aX12^3`
z8SP#7#I|<Spkf&~BcEE}WX|5WZlb%W{0BV#Bh!2hXL%NY=_DB4_cL4m2)DoR?xj0j
zD)}=V#|Ncyo*(f<!%Rq{8yInu(z=@qok^neB#~r8>Nz5`RMSA>)~BJ~_?Jk698GqL
zNZ@CaRw2KDS$U!V0CdA4jd+KOB=hBo&&tZ(2c>uRn#j8F$c)B$O}ValMW<tVQ%ahV
z*+X$0(2|T8dm8g^h~6?9G(TpxlWfd7inFKd2T#(ZN4U$V`EqN)yicgy>KfG2O(~Hx
z@|@Ai*^x_7)F!;SX{LSbPI7BKn3MJNt1*b1mONEySS#UrR+bQ(&OIpJYBJOV#W52h
z4Bc=IeJSu;#i^@!fBPbN7wtBjAkQqd^E$9!t#rNx@f&z^#TK`!%p%?vKtH-_C8ncV
zpJR@+r=?Z0yoXS-hVBOs6sQ?UJwdA^@l>73W*>|Zr0}KsuU{^{V!DvqYWC8V8A*}<
z01;nIc-PMV0EAxi%3uc0YvwIgztY2W+UnS+9mLON@$|lLhb)+(P-Go{-8I1}&NE&A
z0F5UT_#z*W?#hrruRrNp!{HF}eqVZcsKMf&ocq-Xt*J&D!c*<my#8VHx3zjL*bQeO
z#(3#od33vFZ}*6=LkRR|Jz@jROrLh5JvpfsyWn%N;~-M5LsNUxhX<u<K?LLGs9U8^
zIQg?s9+l5M&111*1IN;=WOb^rb*o*fqC|r{QQnF_DzXI!no!(RaZCA7A$J-x#U?nT
z6u>(5q{p=#4>SruAfvxZUjEdb=oq~PCt3jFj{g9KAOJa|8TF+ccBJPNz&)uuQqh_K
zKh9|>f0ZEoDFD6cdKyE`6acu*AnQkCOF#iMnWdz~03VGl7^5@*nf9RaF-K2qQP-sa
z8SE)(DRYWoCr;G8sWD4H26^p87{^KoqyT;B#UENZpa5`aA6h9f+JG0IN;$|hgc>{0
z0o$b+r5z}s0*vH}PW>qDKnin6KU!ST(tr~mg)i6gqd7jbP%$!19VtgX^nhe~&;inp
z)OY5W6bLcJCO)*i2YO0CFSQuviVXl1AH78Yb4&xL6dEy~dME%CoCEzSaf&DaqK-W&
zdQbvTdeM(+Dn<Zejx*kr4rn8aU?wr|MmgzD0OFIWq`)zPc%{aA3fRy*GkfAWN?JN1
zf<b0H*7mLN+V@A(-s(%SF2T5<Tvl$Z6Xk5B2|bP{2S0X`jAZfkuBXEu4Y~0x*UV&w
z&3^I6CcC@e0QhG@)0*PtKI;AFex{;$h{f{t9BIj(MQdeueC2H|rJS!&tJ0*KPrI~`
zLvw8;a<JiXn(n+Ot%!9gEHvvq;p979o{CL+U50^g3yYhSNv{}u&clWF6_rd&gVh%b
zS3C|c59;!b(doAgzPmA2^xp~U7y5$R+=FDe&SYLswR^qRxua?G7$>=fB=q#D+8Yg0
z+a)8K7aTIyFBdMw`wuh3yh-4b;p-o?eW*%0oYy<2X?L2%;I^@ZyOV;zaGzTAj~{q$
z;?~qnZ9I){k@7nh0=ka_Xb@=nDmYBfCK-tx@GDQO^3%TTUd!IG%W0noQIQ`~x^n$W
z$Hi*D!hIXdAq<Mmz+&C&OUC{ylf(9^mfX(#0&A7<--|p|e{s4iRl0{b<+0CxYc6`T
zT-Pg-3v(Y{_;GusA)eX%_*bYsg=F|X(h0mv92Za{fu0|?HS3el;#<fJe_*wNTd8;5
z{Hx4kwx3Ax#4R?#z1tf&6|Fk5lv-rY32KjMgG;crh<SFgF4Y|tvTpoeplS28EZLEI
zgp8Wsjg_H{_GJXtJ>AEKwELF(OIjr7mdF{dB<}S#wU&oJseDG#&8&$Pti*KO%Yj@c
zgzrOm;7QRgGI9Bu?0i|`EdqTeXssGKCE7sPwdWojltbb>33?6qBD(2CdpQ|Y>2v6*
z2b*l;oD}I_I{2y|E5w&;w`c_ZJlD}S>|WkH{{RwKka)AgTE?TVO*NIHvN7%e1M#TB
z$wp4))Q#4Mo#T&M+|ce1F!dl+%Z~u-*4Ey9(4wdrARcO`hJiZ4g_oX$H*RV(3Nge{
zX&T_`x)m;TR`LXJN#eB#S6;czL#gSnX5v&_q2&8i5L^`){&o58B8;IcJ<qMBQZtV-
zALWq8inR)0RAc5DsS&^(YnDy4YFUg7<GpKHoF;RM#9Opc?^a;EZq?6HoTPx(nY)u&
z6U;ZBMMrmeAw$kSm4`ItGVaZ{zD;!DFjA`}6h%p>M(pXd=)Bpto>W%AKmMxV<MF&!
zaQRW%7Qp-4g+VvOE5;wYwnZNOf1Q2q69GC@loCE;6N!xG-OjU2%4!luye~Nwv#{g6
zc>e(WC3=!wNpiB`nElFRzAx4#&Tg4c`!(o1B-zF7qK{bAV+T)^I{-1BO=s!T+Y3bx
za~gr$HRV(5nvB^JUP{1>6)bU74Dt>Gwmb9Iw2l$mR!gne_K9^(9y9abLO<YDjji~j
zNJWfAH<^R9?5{0$3_fF?I#X4)k=Rwo2^G5~)n}-$#62oF!ic4EtLch@Ux_x#NQ%Zo
z?oD~HY>#R)oOP@Ev<dc-I?JCM-M#s^iZG#i0>AxwAL0hG`PySq>9)BddS^6e2i~jL
zL$JBzZ_ncGV&F18+W^D(c&wp)dCo58T>3p$$^5Afa%$B$t&q8!EH&lJa@R9A`_4^7
zWF#HLwoZAbd(n=yR!EV>w{{epfcu~ir5VK;&N!w4+ccvhkaI>eNChP0r6W;}X>p#t
zXaT+Hazz-RoSgQe;}aw6Ml;%%8KgW8PAC8?#U==$r9gRM_)r~4`EqmU4J(C&rR)t$
z9i8mUm~CZY^u<|^Le?ZdEs-DZ98|f*6p=$T5;2O|kHY%1ef5Gd{?pX!;R}};lTn2}
zi<-(+q1>ewVB5{*T&tEKV2&!&YfEg|#LiD(^|HPWwG4dyMcdRM#XtTLO$iV0JoyRr
zYT&IUDP0{A(8OOCs+>KR>~swEGkCh%;@rdb0U17=irbGs&>~>VU|f&yxgxH`2A=^2
z4LSrPzR_91+E*KQH~>SRlrhhs=BHabxBHfJk^b#^2)n_+hBO|_PB${J;Qp1_^}i!8
zXLE&3A61ZimJ*Zbc&iZjYgwG_`zppgUF)$E&E1dTQ%3INpXXBXa_EEE9J2T-`I{47
z!k<B!n0PiI51XlyKiOL8Svbz(N$piiV~&*%6H$-Zqb)oyq#^y}v&cuiPMQXWhl^Hn
zIr*5?!a&KU768<HX}+W6LZzOW5dk#Ve-Trpi5dOfqzjIpEmsaf@5MP?h~!lJNp~MA
zCpU9r?xOnvQ8mQ)B)uHSNgXMUjMy0KQslzK5?#xjdC!kPYO^+2oz8Rq)k`E;%Vcp?
zp8-x-52>YctUMg`%{>m!{{U4~YrAzk%!BG_jjUKieruS)`qH@UY)3PEym9YV0}{Cc
zx#sacl^UGRTi7Y6+s3+lV+j<`_*1x8=v(INOlZmaS1TutVkh@@kL|ePt4-r;rd&m9
z8lP4<rEsy>05QoF<N@0m{HuYJ#d@Rg3~BTgR!x6YldaKT_dpa}IZsEL-6L$IibvL}
z&e5pmR2}&>=P#&U&G+u5KHH5z%<g_?WA!u#Dc`=KXBorYLOr)sEv{*i4sKNc0J<|=
zCfYU=(u**%J16ljoV=?@{{Te)02-|?itWk5TDyHtE125Z>BTO?igshr-+vZJa3i!p
z2dStZ#TU#li4uMptbK-pF;A6-hM?DVDVzg1QQv9`ON*=aO~&$EdmL35K34{`!g-N?
z9V@yNBPxDmN>*k&%Pa8mx%#z6ee;@@RArEYF--`4D}lt)<1xodTzgcZ38$<*sN`XC
zwm7B7wraqS1E(~*2YRn&#d5CFPBBkdnDnb+Bk4{ELj#T}`yq1_+6Gb0Gij|>Qc|hN
znCrzJ&7s_m4jQlHba+0MMMl=EsB%4xcVYF1DV(0Bbcwa`Nw%%bfIn)8uQka!dX}U^
zx0*KbQtack8#$@=W4R8~nq8))+A%<0am60YE=9JKElLxLa8Ios%vT}`b6tmmoUFxj
zz-r}!*GJ(e5#M7yTcvrqoj>+=bYbQ1qtfQ&Zp}lE^)!busmI=^M_xKt#UtI0#H-Sp
z;2KPyN@?f?1q@~8nng%yrmEmG7!(1K(w&U^=93uhRd5p+6qx)e+2gGzUTL8fZ*lf#
zIIlmuVs7Q^0sfWU>XNKBY+F2z1#mLInK5jA<6n2fP-=sdJRH%kbcP<?Yga;YZkc-H
zn#vWm;q)zdSZ8WC%zrBH&ZL$WS2=Jh^-<a($^-3H?=4c|7E-J0{OZUAAQ_;7Ml18m
z6{SX^oKK~k6r*N&=A&TNcMZteagR!-N&G9a*X&Yza>@@GYU7H4#Ai6K(z4uN)@Ui8
zGmE3_sx&?+3~~k^op*Xg$DIiW&~&Z@42*X4uBXFy8Gs=tcR$aH@wk%?oh4Bnd2Lpw
z%5>w3UetYPuZ2DE;Pj=)A6f+%pakNVIi${MK=z;jiZhP1cck_mC;>+uXdT5F;)Bpo
z0DF2;YH=BK*92q~BNU^8D$85F#k)p`&&NgPyK?z*;$U-PmFcs|PwFzfQ%@Drw}N~^
z^01FheWi)!tw-?Z#PWQ`&Na_s!oNgSBV*>J6OY+Pm&Y~UNARb_4ncWslkw?Sqxe6l
zI*&V3iG6Uidsz1-$C?xwq-5`p&b?wEgK(S~wP_o+BTByy!M!0y9`@<JgB32c29rEg
z;d<bGYBy-e`^%rLd)z+>JUEIsB<+snv6{CZ!;cEWGHe4LpFE%addgKI%U3>bVheo_
zZfO+>KP+zF@E*1F<bDzGt+51Y_G^ypYV<aK8MPlQdU~?=IId^PYNUL@1QQeT!72JB
zYD1-Ja_7s_t{WXbLtjT7Tf<hrD3-~6FryUK@qU2{lC#7}AHbEoEAp#Y&QWae2>dOt
z%14)^+@DOLtq8s!_@Zn9rIGcoX#W6&{{Tl$l1SM&;XnG-1fLQ#;ljl`H=!7+`pfK3
zvpl{Zg?=fSLHjgO{{XzzqX)sy5J<U_<_NuqHQP7D*g*MgCO*Z_HC|7NdzHMq6-FHG
zbJml@%zn)r<bMTk0R8r<3L3i~!Fw_P03RC3WB$O!T9e`}^Bk?6xE_o-s_pRuT6}~^
z6VnS*^@)$!qTGK6^aa3^P`Z$M4xh@d$MCDd@niQl5BQ#I3H)uXxBRz{KkSOG{wLOC
z<*y%_pKU(j$d1M@hkh4`bEPvM_Rs$SUarUCFAhL3G;3^sv_*OA>za&@lXoZQRo?#j
z%VzFE4{g-Fq~B5UBh{Bo(ILT(!o@M`ik)sW*tm>Xuh3VG8E47N(t6-EFtf4w-H+o_
zcE@CULDg)Nt?jCN1r=UT5b3cN&Z{3CLZ~(5DxtcJ_NDUF<N<;8q!vf1w~KUj&UGmy
z_FAa^Gtt!izi5!3ezoTt6>)_edr(z@pms-m{yWpvzDp?|+`U(Sh&ISrE|$mYbDH8A
za=Z#cqcp(l<oJa-Bg)g_RreJi{45<yY1?lAIqWf9rol_F=9PfyPmi^7IM_Y*)Cb0T
z<b;uOsqL^<09=}OI|@U&t1pSQsSbYH$?6Ast0u9i&G+vmIq$gDOlPk&iZhx*Bx|du
zQXb+%yV0r~K1uUjo|(-_w;bY-4s(iPA#~n;e4lc2OS1>9Oh+9vKvSHNPQ@Z6k7*}w
zB;?b?SV6UFMMoTfaZgoa&M-abu*&{lsH7@K6=<j={K`KXfU5VAKBcNTkXUN2e!i5b
zxuqKbB+DQD^-1R2j<-mrj(D!2W_x5(vY^;bF<83JlOCc}@)=0zd)4@6$I5DF8;(XX
zTJokv&KB!HxrR&y;f@GCmDc!uS}i3~Z;|nWKMJ%}f$PAgg~vgPPMTxpIeX0?exmZb
z<y(!RYQCqZh;7zbf!H{1IvVPxgts7b?^Wis^Wc&v18WQuo|L5pYZnQ$?s?q6f@-6Z
z4QbuN(8}?*-cmuV$%ZS2X!NPbV331SthG$G4JeYZk~&i~R%)3ftksgNM<r&;xuUO6
zF|^=Dx#aR{v{`Icm8$JfO-RY@tb&1o#a7pCzS9E2hXkIrqLKriM?I=|Y|?21KS9XN
z1W3;ositX)z4r5(%$7Aa`;R8Jb!Oimm-3OC!@p&Y6^#yDjGECL%;&C^Wxd!vdREMK
zo=V0C8+(IM*x2ovu4Y_%3|6<6JiX*&Ju2==t7Ul&oMqVjn?_A^dM)*iwIA+WZUd!x
z_3OyGY^6E*a4QGHnyt>0u0=9%ukyYYx~RPd@cz;_J(g`XqmZfN9+cIv!3TFv)Y&{m
zZ1AL#5HdT}fA~o(@x~iH)vK*Lo@ArS>}^GTJ-h)V%Z2DgNgUDLAZ%i}*YPE;Fccnr
zYPj(dK>Lw)gN{1Wu_sdYp@|^kpf-$aHa`=@%kxHk*k=`CJV$KfJ9GL_1%|U?G0i~w
zbe&e6{{RUMp&0(PDr<I4kDD2w1cDhO`CJkYdXif=+rAgU^rc-=&Bk}}{_RM*g`w#$
zPijC>23(&pNXJZ5j9bqulUI%05B~ryBQy!2JsC&7c%}stZdCNeGE!iP*o*)xQ_P2q
zu;<dM>S8vqmz-pEs*1ZMyCcpuS(@)s3U;tKB#Hna9+d^d?YoexV1wSIjmsz`4t*=x
zg0yUT^&Q>GqEbiA#&goFGJ=B?sDT&X6e-&uYNIfff8t)prcNrnmXiIO%{azAYHO((
zbjbcuhB(K1r#1B6L5+@3j8<=(p`s?z2y2re&J=X5M3;Vge8;t8Y0vUW>6{9@k_frL
z9`!^r%i%t5!@Wl%{^w_QsU#SI2|T|_VFS*<>@rOuqLry=q?dk5fyQdXzS|W&8Q=7%
z$Wv)C`B|N~#Wq33yg5C3&}mY9^0_7M$qZ2-_sOa%0KbtK@T0v*(-hTOB~9BGJk?m`
zGF)7{j1Xy(bGNaWwF$0cW)Hg{=bToynR)%Ia)|6oh3o5C*CkE7@|NJ|9CWBO8HK(4
zY}{@K6kMxa8$V})Elz7xY#qClnq;#(K-SD~(eeqZ_p<EO{?Z2UP6$1POM1Xaml6HR
z2n5v%#L|_#)6tX_nF!8LL02sippiyN+@NRHu`Z;0Nw>y9N9P8&n&Bj{hGbwE5u8#B
z6|J1bt}I6(SoE&DPTdr<CO%det~eEKa?0UJWnvWbz^>T<O+z5#aK=5VCJh0=wT%A&
zc1&irEp0r_P+bwjCMy`m@>|ImAh>*~_O8CoK(U3p?XEmT`BA+Hb3IEDBBu&4Dn>Y7
zwHg{7uq(@M?DP>vVhn`SbI<gmW&zKwMo2vkNX29=(z5UEa(8~UsIqOS?ipP_r6HWp
znqp(xs@%vWT%3M&V)$YG0IaKtFh(kXmrI2{(9&Z(n%V`PWlZNMpsG4}5yQM-6WX-2
z^X6WI)G442j?OZ$u2&pWra7xYvZH}jB_nrA1T=$=4KNo6?_^Vn`F-jV+|UD=<XT9s
z-A)^=H01vPg)pugIHU!kaLm+i$*2N@>MBJXQv!836!LN^5J426;(#n$pPQPr@rPUy
zRV~3J;;l6B+o5^n3Zj59Z{RT&$4cX7UGg*fn%~!aO#@yFXgTAku4d|1A())gB4S(>
zSaJCp&5a0ShU$2vX<5|##E(NvjP7bg8gY^3fN~g8@wbYv6Kw-`LsH4|D9=MkqA3nf
zJ*pI7lP@_Lrq1kgR{^~$7#zq{W7>o>q>JZ_I*y=c6=hR^bInz;ltiHV40F=0Je!v*
z^`=P#r!L!m?`opi^El~OUk@M4)~Pt#k(~FWF@$YAkHW0OF5aM;&JJ1e-mk$PaqB=9
zqd6EOuS!RczA8jPw;q(~SB1~zND3&eovbOvNEyMY@DE(mNY5Rq0Eluo4x_bPO|nPS
z2FFUQunoD*IR-n7^q^$1KE~MndsL2d7{>%uF9SO%&V7YVvtYwe0~8W{X-cl*4Li%|
zM@n&DUbGB?MB}AHx8>wwt%11osNFa;fQeUf^`?~@sZji)mHP2aV}>!dqh)scoPkQ6
zd8xwuyk?bzR6H-uiqD;hkZt8nX|x#(-D<4R7hI?q6j%y~aKny0O<hJ%-FT{kHUM$Y
zT9z!3OH%^;OdRp+R-+838RD~{1UI!^iOBCjizxdsOqIh>8*t8PvMQ9yoYN4#VvshP
zxn|%1d)9ntyM|3%wr!FF_)rG5yvw*L^~F)Yi^{re4jg0}o;F>;(W)=*5^lrg{LKOq
z)Qo~oMO&09P(@R-!*Dv9mgQRrfa5*r0YvV+Aly$MN`_$QRfk;Ek>)kpc|N9+KwUCA
z&<6qW8%UB^W4(=Yk@E!{lU_}Jj3Zt!r{)5_iq!3fqoU0V47#Z+^{)liqfv1x5EYS#
z+gH#L%ec<(>t3DUc?b3?^Im5z#UySA9+l|60&ymngMvq;c{#jqK<>gneDn<^zj*w1
ztBgKliqF#cm##-j(P8r*YvF4AXR%CWE--r0j1Fk5&46)5Egek)0m-C13UK7rJwo<7
zD`%CQ4WqqpLX7KFRN%E@l$2H3LtNJ5)1fK|GI|R0d%KsqnVv@6%yLaw)inpdx{_wx
z19Zu({8#LG7EezBMSnBg`25Ej>(7;JShBK~{^>2^<9AlCRMRX*pJf%go)t%0^KAn3
zSnAQca*T0|bgxrZ3<D|1Jm$W0jjL8%l>Wi#WRQm|mr_oYnavcn`O7`=MH!?flc#z>
z56n^y+iS)3`v#9!xS2j>GJ16BUeI%~{{Y=J<T{o5uDy3|>@pvY)$}<J@g$BMYWGpE
zsO0!{cH{15xy>_Gn@qb|GJLk-!L8fd_-=H=4$;tXYN~i<DYX9pv>|Q#az%YoPoWrj
z!Be#QoA;KMn*N-!CJW=`$E|QzHj-LS@X6IqGwWOa7dMud{{Uwp#9oDX9MqmMjy1Sf
zLGzpfNBQ@yCb^@jR3+@{@^lXc<9xUW0l54}HJ#!@KeZc<Ok??)((qx-lX?clW_Xm7
zs=j*dss8|%WyAgDokoEF0P!IlU<LkyxfoP`ZUfHmFy^|y50fs0yE$#Ru3iXc8sSz$
zo&NycBvbn+%AdzGrtv7wlD?fXYVMahN1`Lh2G(4krYet#c+!+~$FFLZ+>iK2bK4l=
zuJ)15%X(`4$WMs0=t~&m!>I4px!Lu3H62<PVTIrF;<6+kG5YnV*nh}E-_vzvDvjuR
z5W_|h<~q+8ll_Yy)1`1|7&bGHrFT9oZQ3#~(zr6%Zbl6=!m05V!_8{qMQr+mQ=M1O
zIB5D-drOtZYW<d-_K*>B%+-}g7^|^H4Z9Xi%B(^94|=hqtoIjz;j?EQe8NA*x(zeJ
zkU|8vzq~vUotC-;RgHE=fGFqyuPYIlQ;p*dPgf0sY4gaZ6JG5A#utv8MrrD|a)PD6
z_bXGpW=vxs`%{!j5a1K(UPG&QbJbcIcUm3v(H*{1?j1m`W%MiC88bDkiZl1PKgzq<
z@7YcrK_0%9e%AU48*Hi>dUUSZIfS6CBy!@g?zXo)s!t{<OE~0vP|S_WoR2|Xf#N>}
zMXDp-Y0f<0GqbL1%_dpw?%E54G03MFVT$!=)s1C%v&655l|9LBY+mef)C}_2thKXs
zeWiYE^sPvyXK=fK%}gyOFO^-{_pXS^tqxNo%90lf%Z&6jE5-8f>r&q|izr9q9R)`j
zF1W`vsYN#m8=$K;t`=ys#vF4^k_7~o<+|}z*o9;#qPm_ww8nb|l_vWrn?J%ol~}xW
zTUKc}Us}r2x4xd6Umn=3zY*SC1xq-kQ1YF)#dOm6MI%1a%ll(kc4FUVjPc(!*TbdT
zz~3ks?axZ3qG=+}Pe9DxV-8MhP(&B_{{ULllFF4uz;2Ztz!Jh$c_*-@7|?$oN_<d^
zU>xJ#vZ?Tu6TI+Nl@_0($NQz-oae1?$88nF%#x<%VS+0=!;$$qL~)iRuUyu>xgTm3
z!yS$6V%>Z)@Wt36tUzPjG5-J>@-H5EBmNPKk@ja}Zr^Y*{VV9uFl)<xGbVKVM*je&
zm_L<jh>|=SUi?*Q1{ba><m>Y>>7Ht_Qp7GsP6b;tN6_C6H21pjbVy$tkcze8JvQRQ
zRMe~;!z!>~aqCt-7XJXqs}2r${<W{C#pL*w`OopH;;^yQna$Y4abx1U_+Aphlrp&V
z^#1@pm5Xz&GHY_%U%?_|<q18jyP7aOSS39?t){cQRcCE*Baoto2dNb@DHyie<aUw=
ziXzB3Di^hD!{U7sNdcBElX{iKXK8lU>2?f?2(FfG8%>=<m{;?tMK*aq#OwQ8+3nf@
z7;eVkYt9-ck+vYqo&|UR01_<Xw$z|V5s1k+12xCnTHU?c6t$Irae@}R>8X1=q;tux
zVe(pD>3VkTkb30ws@C2p)-BU&-5tJ%rFUBAhqYVH97k`bO7b3d;<;G<9eAp5yQHws
z_oN@=U3q;^X;1g6#x=Bl>oM*%o2!P*_eYO>Rm(pUYBuqhQtgab#tF%<OVK_Suh>zq
z^w@;tati}iZ@v=SUBpCI@ms%U2mC9k)uVfIne$H8JeKELxSBQwc{AzSxtZi=bCP&9
z>$Ch6yox7(?R3sMZ2ti3*OhA;blN_lEtJkAWMVgt^~;D+Zt*mPx)g+%<24H%&(@m6
z{{Z!=y=#=#<eR81ii~yZPR3{fH)VxNj?2@nFbZ;vbf6EVJ`DKM-upz0N4vREc@N5p
zc*yOF^~`(M#F`GZHi4?!Uqiu)K-_;{YWlB4@zu7grNeL+EX(s_nux10$*s-b5T}`-
z-KpekIj@v;jvSnFTX8>)eH-F06~q0DaIvWjRE)CM&6?z;%auPb8%J^Vtzfkwv)uLN
z^Zp#gD)alaZadeW1C<9oYFIp3c|U_8(~QZ&Dsa5uRS2#bVpVkH4x+9q$VI<#Psqhr
z^N_DoP7W|T(*jpt-5zVtZ;&n2oag2yyXil99^CaEYlYOJ@@}0nGFY{C;P++~ibP~n
z(D6+pBAlIT(TU8-I#PqkpkN9PJ65C-+zvBUjai$N_o}_?8k?HOVpw|BvD2+nhpFvX
z6p|=`6Wm@XqrDZO0*Y`MrH(h2REjT|*x^Qc*Joq!!^9VM{&9PFm4-kkH4>=^d`xOB
z>~VxsPaIaJucS|--WzGyIUmNOipyioQj%)uO*OdF){Id_F$O6p??+BEK*i_UfzEJg
zI(v#<^ngzEVw8ItI`*JKXC{ugqL0Ry3y#^N9+Y?Vp!M%S2z%0=DCU9G(ioVd@TH>|
z6bKJa)OMrsp#F3WFnwqT)`~(X0de@zj2@H@xTQU45Qd5~%?5#qk6K<R8K7sq00dBZ
z6jI`V6R4t$Q9uP8W{M~PqZu?~J!tPh1sUd!DR}iXfK1|!f`iDTuQb3jMn^Ps$9g&J
zDF6ZVqXK|EDClW`5znOnVvJ^w#+AT3(My9$Mg<oEw0FfJWf;p0`cj4f<2?FOxa=6C
zlTt+!&T$eux1x%-9*?NXe|M+d9RC1$a4LDy3ls-hTvn54dZMzUSjep10j(>418Z}T
zSz?RobDB=97g6#vn*#=vsU5RjlKeQ-cJ6D`80r;ibpHSWi;10XZyyWB5MrU?DXydT
zayY^;DLU7vMey%POc!}y>eQFM4AJc&4HdtB>`iC&$aF8*Nb>xEd*|s>Bo`0&ZRbDm
z176Kzqu4`hAC+$(Pwv&#wuJx!CC{!aIb(YwmLJUVIJB)o=0hAdk~8(g4Yj8SgLS!f
z?tvl)yFPJVjU0YPuv8$$Y$~5#DkY4ULcM}KvR?vfFv4V(blN|<D$SR}`7R<4ae78a
zMHsI|yM?5-eW0DboYY!k?X~%a2=%PqDt0T_#N-p<#i8Y{rawc9#qlSGAkh&XGb1S=
zWb=ykU_d#pN5{$k021Bc94Q&9qh4-lHWQ~66F=cpf-PF+EaNN=E7o;gJvB>5ww17r
z!Nqv5!`c4N;*~;w)+i_SuXcA4#?roafxC*FR+R#W!dBC4E%eJox3-G`2LN}kDEN=4
zYO-F4E)k-(-IXJ~b&&i-fcSy*`Qs7B7^<=A)xWH0_MRcr$~aay$~{CMvzIi{Z&hS@
zx5BlF?`JQDkT+5}_ODjHcN%=n7zMG?yj#e<@IQ#W#u79P*d%&py=O`B9-FILquboa
zyr|rS^Z8X`7roEWntEt>MzC%Ur*O9|CiQH4{{Z#t)qWT?`{*a_A-uof&*xn=#*d`l
zPLs`RZt??=#}zHsr>1E3z{xyOqW=I0qNQaxsKpecXL5&(o;C2)`}*u8RDKQB?e!fN
zAsoA;kA@!g=Ds)ao9nJEtzT`jwj18LjUQaU(60p6GVRaaMm!qQI9WPmN}^Idlg7Rh
zo5WBDw{Rsx^5(Mq8{wZ3Xp-!bNK)H7h{ob-g^$I}h!*P0EsvR%u~S@pUAJh@*{!~1
z>z>s-l~j2wK4`sedSGT%8}ZF~2aeQR_@d5a0Q}$q?oDCe{6W`l?-q2JM5FjY<MOOc
zQ(C;$<ykJ|%P(~}ttjE=2X<#tq*}5*iqhosH24@W$WRY8n|<L;3ijphFCh-?)R_<X
z*M`O7oni}rCOhdd*zO>Y$kll@y;4@pm(oAE&T3W`Y2M@ZsP_Y+_)5ky40dUb?!f;5
zI`Z!pPo`S<k_(MFlWI2SF;_76_bz$4pC{4HL}hkjS;@~+ThhbIF7jkbY3z@0vG|Lj
z#izn0nYV@M(Ehbv<KoVd5oL-AT&c!M7_SxtZteIALfem0O)siK;q7F4cC+zKbqhHy
z?X3##<8yScI*RsNd%v|n+a<|4#~(_nPJ7Z4O=}uZin0@&p65p|jWubIM(+_!07lxe
zWvs_=K#=S{r0`90l;kX}@}J7Q%x+amymVG)eityEC$7h!#_f;2#aM_tzSYJ}b2?PB
z3w+Ft$MIJ6mDFnBy9{^drF>Q^2`Vyb*FL6|Sk#9yHSP3ko0m{N@2IWYe+{&0hm<$y
zYbx7Zh6Nuw<Ji`k_?09ZM&thKlU_YYVw<#LHta=rqsA8le(ZGyxE*fOP`J5xVJeWX
z8=H*RqQ^bu`j4{NO(Abo$Lm?1Ch*1Hn_}98%olGZMSV6$3beiIi&M|X%}SptXPZ8O
zeH=b)xC!higTvQ13SC$P9m%3^5lU5~l2&x=1ynlpsK2_A)k*1JQmfWyg6Y6DEj_F-
zT2T2oKGmL0Ues>|-Lz!&&R81E2cEUxPHs`VIcFO^2{(4n;Yrx@O`{^UBEz~5Uur|s
zG;XBcG1r=R3krRx92#$!gdCB@Cz`!OenO699HgJhl=Y^r_h71ybI0B5^s5o+_wt{T
z&QtHV9Mton*^pp;X?tMR__PgHL;nCCg#qr&D$@8~`LVu8qWYZFy0BeCk(k_OlRTQ<
z{{VzvY0SEuYCqXdX~RL&)o}NcNuTbD&EjCXmF%V1=kh&hBoAuoS4+|mV8tu_TNNT%
z=}1E^o`m+x6H@Vz8l@wY5+FF;QYy(I#Bn?Q1$JWLVo%-MM!!X)?Xos_+m66iPZ`-4
z>`qm5y+&WTXDG+0s}cBnRFwY!sPg{++I9d}L~f)!?{Ch5aV{`fu~6}n>>kM&(fCsJ
z#$>s-kJud4<HAYOO-z5lW37~6!zP?mW2R~zDrG8hGZ(`;VycOznqoM};-_5?MvRTN
zW&PRBTrG-Faw|7peaiN6B3pYXR0wP#3-8T6W!kukD5D?jpr@WkYH!`_KD8dwPpJ72
z8SY0${VG2)b~tBZKD99*j=zmY&5_3<moQjD4&J2GNWi5sCOYHmQ8dtk36XK^YI)G?
zNEaXBP3U@6Ni`T1vAk4mtH6MK#QI=V`$#UOa!Hy>ayn7bYaHuI{3y+zPAU_wOP`hi
zKD93q1X86Vc|jwnr>kLq!nwBAu9?17jdSWMyqcBc{{YKUpYGKCW&!MGc9E1MX9w$3
z31e2|p!{pjZm;irvIWbJp~Ydn#l(zvT+H8BHLNGku$?y@&tI1Q#x!8}F@yf_tm$=~
zE<U%hZaue(^6aq~XJQXxYep+HlGyD4p5Ru|rzf#4$7MH)w3zt&M(_7VYJ|Qr)6@N0
zNdExv8slzbSk3~0PytgYwCu;B*URH%P<*RG-t2KzB=M!wXUn#YPpLVsaQ>8-rC`w8
ze-`SFIB1jHFEw5KNvlcL@xKKh;aQt$Leo(V3s0)*51rR?<onfjo^}{%q$AypAVO)|
zDCA*s9kd1dRQoA}VAACs$*p2X$z{kDHN+c}C^3%J6{*H*+k(kngegW;^fPj^Ge8-o
zBdttR=b)u>`#nmz2H$F3fb<nGN_NgF<49K_5&Kg4e$_gsYH&)`Q74$M<@N%cu^jZN
z_TbaP@zSkP7cl^fjL>4oO0pLRwFPPW5pxwnQ&|A3TQT&eFr?{~%s_yH+O%L`Qx!u4
zHDcW1hHH8~iIEM`W>fuY5S4P}a@nRu9^=zBjH#t2H7y3JW7jn-XuN_mQmiK&kH(x6
z4??CFDwO%Tpe0V}&IJJtXsMxd4OPIU#v9(G3&k~tR)<Vi8e1!lG3`~Q<ozmUs9YZP
zl%QH=d~zz>Ju0!yPYJ-Pp`!^8nLGZq2HtAp45e2CBAnr<lNpKv=e0bFTvT!lk8J^Y
zr-6!Hze+g*;{sEF0B1Dd271zgfzqEKTxKw9Tf?psQQBLcF<F@BioK;bm8ihn72Shg
zem)%3B#o%MNgl9=HtUm6=LVf`^VxzuDTC`@pEYKE4LxEzc5z5rke*H{xus)4#{^P#
z{*(ep#V1+-Q^4Yo(sZTIBbs7pX%yBtUMc5{^VYL<d+)K@IT$QQ$}6u4hn6C$rxQAr
z6*%)V8^pKcKW9f9_TvM!b0Y(%YJ8G3vplZZEOKf-57xg=!QtbFq@fe#Yt?lo<i+P<
z$6tEu{5xf~6DGz5@LP9oE0d1`L@aQ*8?j!4rmC&5L>qRDVD+z^;#%@hRM%6{%IT)u
zi@4^3I2`7VJ5pzYE8<UZqo}BBW?cR?=gvQP;}`*muSUHYwjgyi=eGbQ)W8qo?_YPr
zQ@sX{2Q-bOnIBK3ZuoLdueY3Lu!kqLYUl)uq5&L_<z3m_6tJ>6urAe6-S#}v=9s*y
z`}0m8m40f^rxejeC*eq9_Micd=7EgRMkoPKJt)ox6rA+M6acgn&orEhQ$PnD>uW{6
zOEzg5HgnhmSiJ>Wv?F23<F#!<Zk<IWV_G+jjk)}L3>OU&SV+WmCAiI0o8kq|KX+ya
z*13z++jSt%dVp8jQ<HH#DMco9a(L%dZ0wFP-=$TP#yZRLlZEyQKf<xd7^ay200CMM
zYPXAZ;sE<*2e85ZRSEG9vnN~my?8Z1CJs8#5wpO>F&7(C)F%YVeQ??T0BaQ!++4F0
z_K7ff!8xeLM--uR-}+Oqh@|ry0L=JagVLIrRwUq@^&_Q9V>#XY=<?gtP$7ptxb~xH
zAH$z~RH8QaKT2_ojO1t9otZ=!`HncC0tPcv00}|%zHGt94F)`QAbn`Ch=QMd(Xitb
z=4jXNIsiRdqHC*U`}a`~_!SmlDNZx%M$c-6^=&mi_4EV&1yH|;w3Hiu*oWx3r^>?R
z;FR#at1S4VNX7-hKSiN@QKvA>aL*^W0;)9R_9e>3s7~M-a2$II$$t{YSLCpipH^@x
z2k{Gmxpe;k{E1tAR;OZptb3cJDLq9VTJ8JFE0mkXvqZoxif8?%s;%PvOZZ~9kLWW|
z?4*jh+iX?FKMHA9Uc?VvR}kJT))}~XP<Fy*qi+%G3{GxA`YtH;Y%X`9T=Yi846Tfn
zHRms^>aF*$rRSawDh9p1a6{f)9RC2*Lr1e=bb3H%9P#;zagYvPNZ0DZyv%uya?;4d
z-OXLKwnEupex#b-o)%LwomCUOYs*N1^DiJC+p|b@jU^YG=+DsCB(O#>c8YO9i~uoR
zKiT?jW%ZMxm&Cd}V;+9udTkX={8goa!FE4N=WZ?I9T$$+6-lFHJl8bvyr$5qnbg0F
z?38?#^Evurpgu8O-z|e+^gHXCDoOs7g->0z9>EsobZz4qv+~)1JqgW1-Z8&?g@Pcy
zgjNwwM-?KjSaK?(L0nwspz$WHCU(3@?x|KG)wM~!_2C?U3X02(FgWX1VZxjq1$R=z
zN2)pMR%>F}xxHcYUrc_SRAf&e!(7bG*qIG4YMvrDu0X&&>Z{@4pxun=)|-~B(YMpt
z?fk$u<Z?|y*85oIKAyGH>9C{PZUpm><w<d78QHPPug<IDTB#&`1vvYt<&C~i3VHXb
z;IT3=82m9?e`Dkf0BU$Gc5#ZrShH0V);7YQ#-lxjD3TF?Wl{LokGGE^X8!<R^MAil
z{{X^i1CT!0LH2bO_DV;Rdmq}ZNBp;5PkLit*{|N1eQU_m#MaUtE|~YmMNFE^GPlV)
zbnevd!pEsTt6%}d!H?xt=G7rFmQAGe_O1des9f%M41GQQD?#peL^d!39jaSpBuA~!
z3ow~IFxVA?B#9#KMhvH+2O_p!BQueM=~XUt=t7nsCOUv?o^k4R!lGIjjz(%WkyDmn
zqukRqI~n5NED|_D>T3a-P2@N^HOnM+LRU9Vp$fLuV(sX>)r)CvXO(cci#+4{)(yD=
zQC&8jDl!Ac7lV$~gtRt`H!b4;4^dhQxKDbcZ!(MzZ(6X|8%Ju)vEp5hHxMf6z7gA#
zy#VQxSXVa+0X<Ksta;w<=OAPQ(FHU_mCftDPCuDchB?MXRVFBZdpmv=i50!%Y=3q}
zJ7S-0qiPzJ)+BSV`W}^cGI2DL{{YUoBREAo0aM;zdCsbiR1U_h#o;-jfkHEXym{iH
zJ{P%JGLN5QM>zeN70t^30A~~{)q0+l$H2^&N%P|jJCj{*p`~hq+^^YO?f&TMD+<#{
zxJ%VD!ypRVi6*zh&wHIwii}Rh+d4?jH*6hhhU^Xr<W%#v*cCbh*wsP#;=AB@Rb%fq
zSkE~Jr9B%2VAXKg&s<`qLzCNz)W*it2lqqyRN3d=s@osjkLgwi*NTx60lV|2gabT&
zTvCn(DSCYc05nFSz5cYI9C1+GUO@zVo$zyt<u#8Oh*hJvBRTc$R~R{LBdmLv;r{?x
zHqXYW&*CdM3Ey*_xF-g@&ih=wy;cRbk48D>vm{5AetBKJiO8;q;U>v)Nc9ur+f{6&
z?YE#Mk2Ni?jG@%#Yh;|{jN_$wA+<(3nE^GWqQ&HD3h|s1$KhK;2`Ia=B_z?_$oant
zPT<EKYewEM3W0zHU|F{L!C{i7x+vG?;P&Rb7Ka4ONV|z6ie<`$g_z(9nOq`ckF7;@
zwo5$ohCM|BMN6p*!vbv>Q{JmenB9|+Q{A7M0q8o_E1RSNqd$Avgjr(Afs`izbtbeV
z1Clyc1*D|i{I$MU5vED`sR@=Mkh=ve2tmeaIT6hvAa3c3sk;U6dT~f4Cfxz*Pc#a}
zmWRuN1<o0dK}hkZ_K-#=<y_*4<Y%~rK^!kN3c+!6cQm_~0Aui^1Z{T@+NRh>dRAmI
zgjtWSd8-j=?8!XMfsabAum#g*W*E<<1*0D3B|2+4Jof^#BbA|Kd|<CNwRsja@B<OM
zipIS{s}?c_X&NI+2TO%g-^4#!XnnqAu{i+bW}(tHwWZ1&h8&JL%|f>;AoBxZ*Vd^q
zG-_FuypUT>_mFNwS~iDlGr`8;$QY~$?lwsk(mqHdIP|TnxxUYIvkc&Y`BM=VpFZoz
z<8E1BBX=KK^eGCh<-0M?;fnKt7yL{FiOTT6F|SmzvKNusP6l?5l>63Iq@u1k$C=o%
zrfKBdO49UZ%KHl2W3n|>=}iC(0o%PcN6E!_^=dh@(5DVmN{xl6rI2En9FFwaIUI_>
z)Ph*U9QUM-E@{j_JQ_my??_^peRELD3ERQVI!mC7oYqzLv>;aOqtmS*DC#jXmT%$4
zKN`T0d6O!yAR51MtNo{N*l>GdqOpX$n}|Jo)d6=NTp$DQ#cAkpvq;6eox-Tej`*#;
z8aze2)4#niHu3`TRhZ<SwJV+~6U`wFXZd>6B=b*diLr`6Oq|l54OI@su~yKiUU{Yh
z6US;%p45kFrBVQ<1C(*kTBoUN7TQ!`&da#}012y7%(n16u0T~4<NhbtP5!QVO{j37
zP*hdUhf(p(<H+A;!YJbhxc07k_r&+};a=r}_Zh4?W!^da)mCQt4KrR-t<o+H#n^Xc
zDtd9=wk}h8<TlY*9u|qDR+KP3tEp>!u(5XS!89|Lr^H||#DsnoBx|(fkF8U<m7}_F
zPI2C>#O7VO>fNeIFQCfq7%NCfXz<x7(<8Mt5=clZ_ekUlF^6VSMtH>{idPC@lahT$
zy*AOeK7I2=>t!*Tj?X*rdeDKLGy~=At=6oL6ocNNi9k&I3XzLr9Fa_snZf6Zp)(aE
zG0u7#y8J0DGwdrm<-;#RIHWQo!)Nua8#z3|gMihPu36Mpg}EiO)9|1TXvWm!^`+{Z
zifll-;+0R#P>yH;tTF)=R#ZE`*{iJ%Lvz>OqLL%zoOSo41$ddj;P8EF!9lx|!K#Q|
zatOz_rBAf52Q*j<NWiW$f;}okaC4q&oPR5SjaVP+0TcmcSP_l1?VFd1YILg$iUvd@
zE7qcvVD!yhC`$U&E-~7W%05^*IH;a7tLs+WcNGJ+(SywZLd}v5T!Dul)~S|Wn8jI)
zVRJx*BL#rR(y2`w<kj840!>3B0uM9+l*Pl~^rmonF{=}l368wgBETLxde9=&PQc?i
z&0B_E_~NpnkgJa1)x?u;x}KB)pc}3!cM+aAs>vY)XFSx{3_bnnfa4|&Sb|k!%T{!p
z9<?M4Ffwpx5xo!v_&+UMbl+&`4t*;k37R&+IUcpGZ7?8%+)xE;R@%cAYWW0^D~{cH
zs`%MEf!Vr>w;;{4DLfhgtB_WtPDV#+fg5Ma-73Uj1mb`qUy^S{ZVh<nj_j9D*QH6K
z{oLO&oN@I1E7+tsdglCbq+9BmKc6aP;pZZ%AaQyxgtT2s(l?N-Zbo|6t)7c-qe}5x
zV5WM5T#d||Y!t&Wi>KW+tKpfRMSasWtbX?9&MVK%*ZVxKb>V(9veUog;<TUdR#u+d
zZc{xgQbU<5;A<~<_UVXe1s(d(csQ($MWv>L%^Bi=25^d4_OCqgF0j{ECK%3DdXClA
zc!vDiS+c7IX9Nt_o-}IiOFEZ5YxF)4%GJKLQF<N*ag1?Z$^}OJ=`rt8$bnlO>OL#<
zWY3qq!FXkGc~g;Inc<y8U+GDc`@|SE=3rLug|!o7sjMWC6uo)=D)2aqFZ$*VNp6o<
zD#Uv#ysu_@P~_xNifH6!m$iN|D7d>b?1iK!Ii;ZRDgZ;k{0(?-j4ZBO#B<9XyOE#0
z+P%z;!_vH$#gN_&b^NdOWwXhze<78tKSPfiy~7Jkp6$<*aHk8<p7qq}+Sm4Kn55<`
z_w8Ji{{Y(2f>X;sk2P^(x}Q(|;(qh^tLu&mc5jwj9gLnJ)1gLq#v7(<j@7j{)UG#j
z5l;a3ssv*`-KnJDb5Sado~;}_DZXTHcyCmO!buWtH=mT%O=|KxtwEkLHj((&QNs?@
zx#JZa+F0Az$Df?r(6#2%7{xYPCOmsrQ~kH478eVG{Wn*g56*$X$N(Cs)M&=85)~!P
zZ)=*<Y7e$DL}31vqXxTbG=mFgJ8^+rhEH=q>+MIhcezgu2NfQ}<ZaB@>6((r6Mq0z
z$=^}O8_eMmcQLNVN6}-jgY7o}2F7xGQ5AAA6=O~oBJnzx(+~yEt#C3D8oF;0>Za;O
zjwTyBW74^o<+EDscn?+ymyuC<Vt4|*E5lkiv$R>{=11qA)yjBNP5VvoxPCVD&3Zz7
zqiDw!;%1nq{5YPj3lFC}hkbfe_acvahDX5Q)Fw>#uLqXrre70rfCVR+yRIsdNP1O-
zetGXw<6#y;Lm<PiUrMiWV$p*nWR&&vspA<nW;qHSjmnyycM*|k8nf8k#_V^;k&*3I
zynCZ*o+Z(R{gNzqk*;?t@_nl^`rFHYHa>=>({Gs@%W_Jd)!T=~N|v$M!o3L8N0E6_
zM=LM!Ms}Qz^?eM{!M)!D)K^X7pANLwhUUoOU+*Xtk6{|yxr*Zs2N*T<v?i;;O&$g!
zi>E6b<;<@0Htv1uF)=|}I?5v5Fhn6mWQEUK>M#}LEx<IuaC7PFPx(~P8|Y{m==ycn
zk)te(;aCp!lcd@{uc#Zzo8(vd2s~DDTu*&z4XSbp!LG|o(w5TI6moDgTGMujG-$^H
zssX>{UIr<CLVooMfd<pSq}qV+LHY{UoeIMK>pyy@jO`ncfZ5`q3ZKG+oM(Ygg&yYO
zD`=v8$<FP#3MwZg)rS>h&~(e&`+GQp+besD(~ACOl_WNDW7mpypJZ*c=+;?7ZBR3c
zdtckd8#~OK7qPB8SlHHz`^-?r7aq0d{{R;5Be=4*iWPY!54#F8fr_WDd`<f#?**_#
zhXe=oH9vwbUt5Lm?$Km!ipRLkbW?@(WKHOJ;nHuWZ<9~DVto+ety}mj#5ZM3I#h}?
zoUsG>*U^g}Izof~15+etsUUqTepr~Rnf?LO=F$8$1-;@dGJ(o&&MRItNcASTFP!nk
zL`Yuwq%T=}G;7XFG;p=|+H!hgsp}Tnex+`)Pm-at^0p~m!0%O^qxPy);wLs$hfmS%
z7_@P@Z}yIAQ7xoxxfO@EYK})ja4Hg49Mz~tu^jBPCBzKdj1jT*D@_-{IF1w_MXKAE
z@T4*U(yw7$w%V=6-U6@Tny)smENWUyh|qm;Q8R(kyz9rhmEE=2R7rfX$!Ps4JqxEE
zd06e{@mvw`btKPRDXLO<w%a-Td*{>xULkd_NbCZk&#2A?R{KTe*~Ae@?A=14tohEr
zs;;d14%YFn;`3p;c~OV0d8dwa3v;U%kd}8$jB$b3{)W0Q0NUQz>3``e!HD~Ztyb~M
zyIe(dbF{CPc*YMTetiB_rSBb1M;l8+#cplnww<GpVTa^>>I21enyf-~JvR=9x%NT{
z7{L{Zq9YvCfC1i-S2ZY6Kn+yQIQ+e-Nx-O?vp@<?;er7buc!E@Sko;&&24kGG539|
z7%LoLQ~a(y>7)mLr2Ig8oi<BNRnM8u9G<n!U*5woWk~@()rMnlV@Lxi?TVyLj;}yt
z<Z{I0oYzqf3|~s&G)wVsD26~ratEb%HpelH5Ob0-Rd6NPHgGB+g+~VfRN#%hL8#e)
z<o2Ne24TljT#mN5yd>~QIj)tpD>&b5lBhpg=XJ><o_{ha118?0yRfm6md8C;bY%9W
zjQ*6>IR>1E2iCm^oa~q$IHHc;w7AcD*vw>^DOE_~t~kPVs%_S>s%a6?95q~1kyMc3
zs_OEhlm#)=6F{UVty>_mr?6dC$%q7rM+Ux#({&lmnr;i_Y~a_;fy8sd{gy!0?^-qY
zpQ6I+{mfUDj_7sJJoCqFe%{Uq!EV*Y5;4Vh9x;!4$lQ&mwQ$5_@m&}xUY&@qA9y;N
z1t)rTIj+;3F^mcaPSl<0aZExJjs-4g{AdG;00&Av=%b;aL5c?+lu?c;g@xdXPSgrh
z*S!EC7^C@8id<)<05lFd($auv?e9Ph9cg+RF-JI{0*q#ideMpiN;^{WXvPg8iPn#5
zT+!Bm6X`}il<xF|g*>0Y(zplEQPP{{M~=UMrQW9iZprP6T)}236qRBtE6ackHgn0I
zge_TJ16pD7>9T$-DSJq+qvd9QQ|U+seXCN}!@9NOluKns9e1}%)rY`(v*XR46!jrV
zsCD4Fl%UzmQkv>6ybpJ24)?tbzJV)J&*AmE#IHTf>`2ZxU{t(JJCE5&;PHw$2a*MP
zT6{gyKn1+R@8%k*ZQ)HSEkUD^6_I!W-y*Yk$QSHndGDDXf7UPIKy@SlN%XH?hfUDo
zB~)7Fdkkb$m%44F)(p_Y85qj(QT535AFyYULj}a(811K#Pjo_R(rCK8tGRUfKt8-z
zu4#7B9X=wFDC4Fo_<>h|pneq(82b;{o-ZDSs>^V&{gA7l?;e$@7lAc*8EIi(!1b>~
zxP(Qk#zq33yjGx$=RN9Wi=RRJ6nS*M0@NXd%GWXcy@J&Ge}KN#51TdIfaeEl;=Lkx
zvui2q>MD+kxVM!K30L~{sQS#>E7?Tm<M?-`g#qN5y-x161l|kNEiYi<%9D+x@m=-+
zTFlk<q_Ink;BYEEyx&p#IF&8@Eu}!1TUfyK+g8SlU?Y8&aE?0d6{Nd%j4xqM#&{k0
zsP>ZXK2&4rc92CIg@t}nFfm$-8iT?Q%Ba|>Td6?xHK-Af9e$LYnOYed!fjYw0l}-n
zRq}%d>^f9B#7?%MznwbT0`{?f@o}^RL)if$%ahYNtjifc;%O=qjxqtQBN|7`OrQ_;
zs|;W1_WIL#x6r2_#Y9!p26SI8eQK_xq3mDUt54!R8U+O3BQN^{HJPY*&q!N$NSMgP
zbR1KSIbUJ(ByZ{O=2@ZdR=+yoEq){0Tib}no^m^rP*3qL=$7(rqEAEA)qP&0=ufnX
z*4;+yt0M$F;<moeAvne}UOlLI-&MSk9VQXTz0hD9sXvQ#snDz5K7EcWU#iWM?NRUX
z!)K@1Nj2@vK<($6<gGPp2a;#|TuT{qw{s4a<C5x^*9(iAxn&2lImJLFApERX=xUY?
z+g3}gdy8wDQgCmfKEb)JU&Y$?n|Y=*5nL>;dkXVLk;vuCcjVAyEIH{~)57vgn&ir@
z)s2k<RZS;dhVoS=FgBca=DkMa;+~8wom9Dfy$I`GExR-m^H#MeMsDoRGjZ6_)vrbF
zp)~571GeFYt?eV?Cb6X32r!bWt`(T`T!!wX^FcVPl{iURpyy{puXwie#28DG3J!iy
z2Q`Tl@>;QIBzTGb>tdh>(w8Edgi_^8K{+;Qe{br$HhsQqV~n}~02-}veLc<$)5z`W
zTfJ7!JJM$zC{*IMLgr()k_{naNlBAh2vA#hQYamIpISdm(cg*&C_da8D9FcJKu6Y)
zgS{A~q|Q%T05Ez|fxzaII42Yn&%FZ<2|Uq^4k<E0rj`bf4j|EwrAA~?)Z_7^%~Q~l
zeT62_>`BLZ8;H&`y!1ZwvBNy4Y;a2<_ET1)(e+7o?X!Nl=Au$b4k^8lX7Cq<^sP@t
zicLx%F|o)s+OLDWFA(ESkMXW+z^x=YVn;gdU<VoRU3|9*82R)0SAkJQw%O^^l#;R_
zUkrG1K2uDH{Y722v(s#c`ZbI(`-K^%EQ-sKN15+gC_uhx7nbusbrfUTvOH04ny!I!
z4BU;Ur&^p$OJf{VxmUN9TLckQ_Rv>%K1kI!!>LaQhD@t%01B$HUdVn+DVzQPYt%K3
zK*g+GLbmay*$Cx&^Hfd!$vIywN3z#iuc4HwyPSktPOWopg)Cd1yS`IXN8ycW*a2u0
zJ<NlO>P_v*;L1nRn$yg~23E(`sbX5#&C<Duo(|NQ4>DLI_ReZ$@NV3Bx|Cq&oF!>_
zu6nsN!g4)mc&UrnqL=(4`fNmbnuLwt0;f$IKtKsuWFU58Dts>7kPRY$qdX6#Pu3>-
zhqH*~w$b7sN2dZuLQZPHxrKk#*}@09)kDGJmZjC7a=8&}?UNDm2+(^draj#5Mr0s=
zvr(wyxTftSoPKp2?T?fh<YCLRd+w;5l5vxdtxC$+rW_vXG3!Ob%xKF2?MNd$oKR+o
zPcklPrt$?KZ^<VZ3!0ZWuA}8+m{NqrR+~_U79oSE^(b*rzP5+%L|Yy6ikDgosQsLo
zqqA_JCJuAbvOl(D$O@m<qitI8o8&5^=}_?zE7-}K*dDaufz^g9oBMU^^_b)7NYczs
zT4(3pvv{P6`nx)TA}ASUAB_#DTSlZbpkldSE6fKh>`$qw1*;L98qMPhSaW^#i#6PL
zla9(WRoh#HbV7eh%oeZx(@r){2MN!uX7Q}k*dpV2fQ*3y4}8;3uX8RoqMY`sjb$c7
z6*Yd!(+&ygSk%SIE8L|<CWLx!rFjRN4510_iow)VQ?zg<m4;7IUXP*xA=)_$+uE|c
zZKeZj=U^)iK^4bOA2(ByMf)h8eq@!t^se7pXiW7`exj|%Y|?hX_03MUIXNn8t<^&0
zGlW2l0r^veeFiIGblt=FcKg)P>Av6&)tj!6a+vE0JwT;4<o^H-bP1;@^e5L8@nMtO
z@~qw=50vK3v;P2hkEJ2Ca7KIAPHb`fG|{J_2ZQ)fu_!rCKI+~4u0>)pV4iExFD!tK
zush=w#$MW(nU7Ej&3jpV)kMx}@v%i$J!;jwj~FVCw0cwkQ{y<0dRMarW08f}Etcme
zty9HlO_HY-OK&_>)u-=V6BB77oT-pFr-6!cgP&TM(;djdb503T;8KCdTGdk~;{pm$
zoOY*yPF1S*Xf8xk6%>n#wnrRdp_F2>oiV0G4-P%*`VKfXK`<l+wJn04z4})8eTbP+
zhs{GT%~qwi0o$Im#*1hlH4}xHCRWBj`qbbv?Mi9b$?Z)cv8pNIc<VqM^rwN)R;dug
z0A`d7Q?bn$tFVDb<3R&G=~wT1Q?Z|VEFvrljIISvR+v`+iq1%+R@={dbZxb|(m27U
zu0i6IG-E8vcP4!)_J=QuU^!fInq+OU{{R|uT7jg<0*Zx{hvylmB)gYA>01Pzdh$&q
zfQ~_y%`{ZZK3{rf2jyBMK-_fqrm!Q5lmG^O=^SN6Hh`+iY8Mq@hcycTJu3+#L|0*+
zYDms0t=5$fHJo&1GTOG}$4Y^RJXFw;oN!GNs1kNLt);01IO+VUaYj9<arxBPp#Y`Z
z?@v%^#dDu(s|bt(PQeuA7^Nd3iwJJsIjL<9+sN4T2AD?_=zdw#zdh@Z6&urN)|=Gz
zT{(%dPIL0pn~Y|wXwAC7WAm#m_p9@2iq#rEj*q|~Ui6sc^rgiiJk%Qi6rCwYJZFkS
z!KMP|G?ZgJ&;~^SCO=xu)im>Y11Dy!KE%*L#xq?wY(((&6-aJpQktB3S?4#JZOxhe
z<Y#ZF6;qN<J6ELKTSqz+krlE#isrR141(M33xoaKWLMke`SmKvLavfLEJj@@`_MV8
zau4NQK8dXlk}3ZH)&Y#3ojI;{SS7cSl2qG{hdpT(@OLi_>s|Q#6+CS%PJBISP?o2q
zB!SdAjw#)1pYZ+Ml0p@q%)sT3b6o%#?m@54aTHw|jt`;ql;_VCA{&$YgX%f2KEGX;
za&k8l)6@Loy$)bJw#dlGHRsxxKiU#EW&;>C^?Wfuc1ZGbMX^)))td{SvfKyb(<ioS
zvFpI3=RIrct5S_vI7?&5rzZ(>BfqlNEar_zoPhM?_pJ!!iTX$nxI9;wjNss~`Y{z|
z+V<k!MP-&pQT#0D{A=X#Tr{<nDIUcf&!my*Bp=F*=i0I~eMH=*8>dcdU3yo^)}<;_
zaF*!x;UzfpAkGgIr=B>Z=hBMAprfT7MJGMZXaRH00QI1rD9;oCy(-PA<gPL*p{ec3
z-RMnJSG<Uy!cf&+W4O!g86SACsxNtM66Nk;U-zD~{9S7s-bXV7({JON!CQFo!jHzk
zMZ#cZQj(R=nXg?&Z5=~v8gR%radGL*K`)3j$ijxaUVRre$<1XLf4C3Ut3A1lk+cAP
z>ser&cOo@YI|lJCn4Ed?G4@)3_`1M-#JGRM70DQe>|kb>%f(OC>|ZiEi9BCzleW%x
zKkYCT2mB^XzjsX;_mlqstz7QYoYR&v!k4iZF}!?dcZ@BhYwMnBNc=^q+zhI~fb{uu
z#bL(>=T~h2T!YR%E4GFjFXB1s)oFXCulBa8!~Q<iN3>$0d)-BsKW>*N*i#QZ=|?M!
z4Eoo1)hTv4eZ2a!D(3G|^A2wA0LBI+HBj7Klk;54PI~UGiQvfTmG`PL+ki;M52bQc
z!*ab2s8+fuHs|}!&Gn|NU=Aw5haKn<pTe;AY`${2MZh~j{3%rjOab(%{G9fwBZOx)
zN|nQ$i6G#9m7{MNN{JJ{HEI!#{d?DC3Th`cT8)!{cGH6H9{#j13(2RU1-Q+29G9`3
zcWeu10Q=T^!L-)>#CcKPv*e2)`d1}dDe84os?5(Uj-r&It7bf&DLlMaFS0iFg-<Wo
z(~>`$td#mtr~#)MLUja=I=L54d8pI@Qzs2wl;dNba=AFA13hUvuVYJ&dy44X!LgE|
zWjO1O1yPbB8=BH!7;{iE^UpPnN_RG=GdZIK_6C$k$7-0WhCL6~lNHVE&H2boV?8Oz
zgdV?zOhBXnb?Hq)!sZ^IfvJ}VrA7y#sSse}Ij)E!IkL(QKf;_a2`7aV#XMAlAQHT{
zVMT3V$cMyt`XYIjNw{|83b!;TlZ@3r3y}5$=E~sXJx()P@-98A@*ID;h>||0j<8J2
z^1$m)NY~P(b;-%41B2T&$$Off9%2EB1D{YR5#aay>QW9kpbjhb-(w!fg>oM+2ZnL$
zgGxNnf#*sw+j*%m{uH<w?kRf+b{dfQwF~$iO5DkT>x#c`;+;z0h6yV7-PBfS9+aDZ
z{Z*W>@MS3-wv*$fd6F6P7;jOLT@&lpS0D)HN6(=j%Dj-r&#g^nWm}at`F37PgT->x
z!r0a_JyKa#TUN*$4{GBtqYE<>UJo_UTQ$YaqIt?t<Dtc5U8Y@zN8?^ib!K<b(HTL?
zx2L^nSl*O8u^{@@6AOdR54fo!QW$m>&d#WvBv)(z*g(&%X+?I$K5l*MH&1~CVT11^
zbv>%vkc4&ot0s*}c9~zF%Qdy9SRo4ARkP4~R!zSncWUcAHy7IPptdpjk&}kN{&XdG
zVr1-&tHVAUvzpuOR~D;=`>Ml(?^ZSK7S7f*n%*UiiN^xEnB!QHQ2+{~01C(P1AgW)
z)a0C3O<Hk`4>}bkDwjEk;K}*ARi%M(+zMily(!{eM|$P4+k21l@H-!4&1Y*3X>V#|
zk`)d7BNd?6QNtN|2mlP=*8{HV=TN&ibF&{VI2f&I?sj1C&b0N|tM=q}A(2S+4M>dy
z{{VC4&#h&7xNb<>Pg#^#TAhz}rdvj8%^FPx2Na4nzqj(L@ZRnDcl^D<t7~wMdBFDq
zwvA5biHXSVtusd1hm<{PeER-%hdun(%epiyqx-d1KN3DjD9w(;HGIjQ4Qwq+QnZoQ
zV=2kw+OxG?VjVU&CB{I>9-ob5KZ%{uks=|s<B&yjH_LN-DR*Oo)pMHCnoa6*w8(WW
zdglGvce1CZYaeN5JB~^3T1QKp7+=?#L#8_5u_}G5)}tyhTbNBq&A`c}$Q+8XCAXKx
zcYETa+k>2E+PalWeayLJFpfG^izf2!k-HO$j6~$%E^5WSrOV8X9AJexC7Tsq(iYrK
zGCK=IRb$U5j0)I}O@L%p9iH;aNa!+gT7PH?*lNYInWkSaxRaWF$pcJ{@N>S1!i#5@
zh8W|Tj{65ljBe^jIjICzo&NxN4{&{ZRV#!NJFwvQt4`lKaz0Vty;PT#U^Ca63o5}f
zM|67}RrS`?+#;|WcJ&?W7D5+MNVk3Aftr4^Y4%y+l`^ESLD100V^{5;Bb@i87lB$G
z&xI$ru67Hekw~YEoY2~aHXeBOskr%0x*Non_405)>MGusaFN4vB#)ihz|C?tT8bH@
z4%=9+b5pdpt6??7E=uF>`U);CL#B#&hMg$~EZeb~%y|N7U;+Vd=D9!kNGAImMIexK
z#?ekX)P~M91QzT^1X8(thSl0;&K&c&_N=X9+y{uM&mAe!>ggwttVRbM_Ngysj(MV0
zWEjRs=8KNTWwfT=;nX%VxjpKt$dTMJ3O2raRJw@8^OOLt1_-L8W-Z+aqV@|Lx_l8l
z6RMo;=O9(~m+g9P);V~`-cGozjUlA9mNtL&QejWGHKi(jlIy0_et=cnRxfCUZta;i
zmUP^p_pe&fHpQhRXYj5Q!Ma2Fle~$AW0k<;>0RU_%1wiT+PwT-RQ=PcjXP>vGJM9E
z$2`<qy3ks@)^!i$^HDs8GuE2&x}E?uz}{yEnnN1WlH6vYV<Yq=4{Ed(K<1U5LjM4T
zNXiD;q~YAwR;Q$a8x>+3A9#){YFXkyNp6+SYMR=|n8TC1jlJjs9X8r1V<|F>_iE5o
zjZ~Pzipq{pF>{}-Urel7su0#C-9SC-sMCN*O5?9QS1oR=_lh&r*I#W8$i{i%n2DXZ
zsIoCjApqi|Cmrbl8@>*DR3-Nk2Q;&(Vlhlen{Ymq0W@pKJ?h2{ByJM`^{2Cw{50$Y
zWb;qpkMW=(H8#ZxNdV%2IG-PCa@gtOC|O4C3C<0972U=sS8NX0^{%VOx}V#17lef>
zgyTNmmBdWqMf&v=%_3_nWd>=I91l_4R2H%qfOo}Pg*?ds11Hc^H0XC;9kmwvbZk*n
z5I7y_y0nr+##Cdoy7m>NWfzyGMY{l=ezlpXoQV^$9Vs)4TC)Y6-S-j>O>A3&$PZqd
zPHPthB*soNTNZ56AjjPvl^|#<Gp>4(L$31MNCkfI^`(h+x7LfIBae1=`_dVadO>Uh
zf;%4d9-epHsvbMiUodGi@79^7HgyEYIP7RcI>^t;MsVG+LOWyT!S|@Q7REY`^(Nw=
zvvLnwWQ}<;JN+v*>;QMEKH{!PC<(Zc)4gX(>$QL<j?{pTGxLwFY(VS5$2EelnHSc!
ztxBAC_n-}H8GO%`k&~a|?^hWD93J&j-Gbw{6>qBJtqf#k260v7W{zFBIIB!BIn75Z
zs3L$VNQ5^uESSd?JfLmPYO^=Zf;gZFckbgH)Parx%~lLlj2zT~sR4c$^B3me`&FpD
z4{D<p02uytawpuvfGh?h{3#hju5n5LJ@ZNj9Zo12N<|CTtyE<nHfsFIlblsY!8pOB
zBR!jI^yAj8LoV!&NUE0yWS@9r(9$F4p~V1PDhC<-DTf0is6A<l<gZ-*H05kCJ&gcT
zxrbvh2O!lqAy?3f)sZ(4N#dy7+o23qhXQ~q2?0GS&g_ALMN%<=&hNsdNqEKp^q>oB
z<wve6$CyuZRD+CvO0cb-e;Qy+;1$g}GxK!s-l8qX9D_hPAdK-qjToJOz4gs$+b{>~
z+OPv{!*;D3S#yF<N(5~*LvqNOIqOL~w%mJCTg&pFZ(5K?zbtvp08my8I@P#Xb6La@
zbjj1bT!liOC>ZGwm*Szgw-+{ZTame4af-Oy9QEx{ZrdWVo@u5Bfq0utxUjpBB%4$*
z1qWeAfQu#E@iVdHb*`i0WuMt@9%N0TQ=P-Pu1~=Z!&bQkNIYOy9%8SDk=2Fx&rY%j
z?FxC%Y*wKJIn89+lD7yu`qtEgBx1e-zLGt<WMpTIQMCHgy{R!+T-ZRkrEir_9jS56
zQ`G1CJ)5^qJJ$GmPOVtMbrhYI&KJcO=IZ@avD+6TKg4O#X<;-|b#gNy8SA$dl@|NW
zOKBr>NPmltwbJ;KPa{l@6z0EQiu$xD;i;c0(yHoKk;ggQ#+iXmCp_YtpHsl*zKLj$
z5v@zwewA^ld7ow(+1E7$kxOTBvHn>R!Su~`-VL|%wEgGrKPNQr6zINk8>?)WURVw*
z<tlL$A(%WJPlWelmVV(?j^>AlwRm+cJybaJkbKFUk@c;WuO_m;n@zk+i+(xz$6Sxj
zy(dc5A=NDsXpS8H<vm4wmlEW!4>yUW@JRLY{9>yfNqk7r#U(GcX)EK;NOJYB8u8S#
z$KoF?9IBC#&3ho^;Qm$SzAw|GeQ?a+H_L@n^{;Crm9ZZqlNs<Fg_W(zK6H~d(asvT
z^nG5{F22Wc#{NTgtb5Dgjpawr_n3C}tZ@mKlw!=MAdbeq#`ipqYaN!m;r)#FR*UkU
zSbtjP2+I-Bk6P*cJFiS*TU+?aU%R=f`u2b%Pqf+p0KK;zX*F}v!s4y&%;e5RCQfQr
zhD0a#QVey<nv4v#HnBc|O-Cu}b0NK`r)*>V5)R*R{{V#;`LVV0*8xo{2QnMmr9KEH
zxR4}DSo>4qwVLL2jyR;;-44<R>s^kSrbDH|W|@~NKJ`+G&tDN5Ys`~I(Ic^hPcn_i
zpPIAv-C3?w#~Irg{c6?5v@Z~>WEAKRt#kLI3R|mp;<_M@3av*sc4FK!4aJU5YNuYt
zu1vd!HC{AtIyDQNu>7c=h|W5*&^#{?gH1p{4bwi=w<Lsjti3KX6cG-qx3yZDLapsz
zC12mD+4QvI%LI`jke=e3za8oUC%p|Q12vx^MWlQ-GgqPHgIIChW<UjOS~w$?109WL
zRt+FDm2jYnV@kR8#Z{j4D(y~ci(HUv2-0kKHH_;dOr+<~RW(<Mw*@47cB-p##k$nO
z>O=z!K&=!UbQv}Lul6F*97qQlt_f0k?q!%p#IeZ&yU3kok~Nc+b_zvkYF-arEX8+d
z50NL|PwQURP~NdTtjaqx$h8-CobL>bI*e9p5L>NuzAOuGen<=R4wcHY7AL3SUh7so
za%=*$)l3>{h7}@~IOFlD0?o9t#Nfpy%pBIq@eZo05kNe5?^tS8FbTmYsIAy-V{36D
z&i-ol1FcI7jE`H?Ct{NBQ_lf^#*$Nfspbi!80V8!<hQ<_;7bfLNQ3*MKc#dL!~Xyh
z^3IHh(S|8CV&kcM!agIO&hRDDtcuuC#{#`h1Z%Ccqy!9PVAquB7B-5z-ND-3GtGMT
zk8~SKQjy_f9=&NNsYRuNXF#Zo-o>k!@r<vf=`40UJ$G}~yDbw?7m+-|CL0*8KO9#D
z@oQNRVz44IHsh1{8rlgG&l$PBXK7vB6Owv$uWI;fbny6gFc*+I8t{i=sh&^CkIuc*
z;mZF2#W@=h$v|s#LpyJ_&)S1`IXK)u3Wp%)psruUUMc>~f3w?^^YPU7rb*Trt`Ao=
z8@r#qApZcqtIDMDHmNx!?l4baPCqKH+Lhd+=DCo4I#Rh-Jz?iX`|_ywEmhl4vO)7)
z$IrcaTTdX5CTGa^tZhbnocy;E5Z~>QnrVxa_D9yV)F=HVNgkZlckv#UpYreyI|}gT
zx|xPN*T=hNp=RFMW0UmFQ75)Pj5L%y%t`dB&*SYaKI;Cz{d)1TN&XW}2Z}5+)+P9l
zr!PfPJp)!%{{W8k+tk}7y09PK99Nz*vHmKCK*Qz+iviWi;>|5w1+z|jZT|r4Q@`OZ
zjR`T@ryqrI<buQ;Q~ba%Gmm<buFlp^h?j8y5kl1q{{R?IsX?~k!yzE^+uT<vAzu9Z
z)N1Rr@yD$u2-mrjc55nV!?(RYJB`Q`=O9us=QRx370i22BAf;XYO;2S{$csmcW`MS
zXklEAX#yzs%`QbWwknAoyB|t7W4$wWXw5LN;(l68{duI%6o8rlapZgY*GHmwhwSVi
zx@;-oUb(E%!KMeOM<Ps{<8bQTF-aiIY!4h)1E=cO77j4v#=T?5TI_7KOKnCC=-BL3
zo|RF0lF`pz23x5z02!+8KXz)>`2PS(Y?4oUtPc!38u#hz6mU;+nD?ir-lSC}jz<}%
zgdzFsQh}1v{uBX`{V9K)Zf3+kaPd_SU!`0<4O4Cjtm+jJsly7ohow^fA&R*f&1V73
zc{ntNjN*{;D%l8Q{nMUBdhdg7e9amzNo)=Uc^(cu>(Ra+PrFZKCmVR;y!>Q+%bgTn
zr5_nyh~#@<m}l#g)84p&fnD#8?Z9N0Z&t=@g<*r%uLhE*pjW-b2Ojjf6b@<F&32sP
zQT*w^dm0H<>QsGAF$tfRl9aNJth{^D7ffSzPoU<DptB5irN>GG7S1DM^ixv#7dyf=
zw4vLeD~ep`RwBoxC>&Mv(6xDSvre4-Mk;^!MYZ68&Ya2zT)3s}BD#;2nK<Y_N&xl6
zZrON4S-u5?NfLvOc{QaU!@X3K=3T(J@3$tU*QUCU*~#=d3}AJo1CBFYRQ>|LhT=Gl
z<amGL5##i&h<+JGg)`sG+<ySYOT<%MMyX4&=cG_b&)ya3ZSdPnjwdE*n1P%#{{Z!=
zbe{$2vP4YQ;n;t8nvbqPuVW+3iz=R2eQCSU4!rc>SF}UnT@DZe*hToJX_}6eWe|np
zw~a!#_eDq7W6>0-KBtgHYj-eTF4p1xh<U3~=$gEVk*7{RtBUrBZQ~IG<*CT-Dp72N
z9kHm$>59qYUt+z1<2Jq<)o$FZa3o}P^9^c6;2lyy^ISr|?x8i_>5wdU^TsxD*mkXR
z4NS3f=ru(iRde7=%V4b6frA_zMk`w1;mxB)8e5r|kU0zo^sd8LiAAC@2jxAx)$3p$
z-ZO#sMMK2YYjVAmPCY&z=@GBZ6pY@!VW{-43Ta7sEKh0}j&mT+KRWK03fZiiUCXOZ
zol9~JN41+<mB|&*WO@#tAKkQ!f51gn)ik?kt^CEdkL5qzu7m@RZ%V1EBQ=8+?axYu
zIXAghL{_%3n^Yn-0FIcc#kV;KF-D#p?4$Zs-?GX`+A;MMuE6K5qeyi*RFFP`v`+_&
z)G}Ghy2;60F&yWb(KaJ*%`gY+Lm8Q<fNY4`KBlZ#0M>AxxmsJ{Wd)4Bb>u2>-KvJ2
zuIP5wL0?gi<;XPDTUrI|bKWnK=HBTV8DvE1u@4o?nO;$X?0w0upT)YSov9QyQ;9Z^
z#{;OYPs<^W8nSBJjJ>D3$8g7cbm^M!?E_1rN(WuPDeqo&Zc0i4=Xbqya(JfWNwE>6
zLH7(~tz9^|J0VG(W{k2ulP<%RayhLvx0Ha}7}u3S@ds74QmE<p$Div-FT_oDPq{Lv
z^a=%Zye&q|y`)b=)UBOwt>11wwWc88Hs#0Gyh{7T+ODAJWx91M(5oE(0H4CEHnph{
z{{SEJ414CU>XR3?N4ZRGqJ^4Eh*V>{)()MkX!g=fl4=mHPxrgml0Eg*gqFCGiT?m-
ziipbRC7ri-JG#{@A9gQo<a=bkD9|7nZALc#0CSqg)_h%~GRO9LJmy}?NBGy3`HTU<
zKU~vG6Yo^8kwW&&^%eM!rmSkeWR#KW!~AL~ekMYn>U8t<XBFmK&NwE3*d2MzQo_KW
zX(O`#0EK~n71K)uaO`8yuS#U!5cRnS%Oog&*aH>Ej;D$<SL`YF7d(yYzZUB^vH5e|
zhEwP<{HmbVwJo7O-6r2bpYg2C-n5&5&$T~i1<)?psxB^FOV4>O+;r!k)~kKC$e-UN
z?gw(!pDoLIdr9J`w8uHkdDSb;O33L{;?}2C_Iq2%18MTM@9vXX^P|BbjsE!SRCJq%
zO+hvu4tG`ULT@(cw;eD|bm8ktdPvHpG`1itPk+{sx#>&?@uk2by9{hNeQ3w|%^3VB
z{Ar58kIsTKMsO($4A27Oj(MfP9VxqoCjNR+aIqx^lT6*8r5o|>MZkV@N(eOxke-Bo
zeJKpe2PAdJ28*HDla?N|nH?%6F6Ro4f8AWv>0^5*-L##v)8ymxrObt9Gc*%g5qN)A
zmjx_b5B8V}ojfb3o@DZ)!S2;Av=>qGHe=-aQM(n;CxqJ@rPLKqqH|Nn;d>NZ&3QDK
zJr!|K@l@ARy_CBg#&bb+9F`T=E`_A1{{U4ypYO31Y8^XFhn3TpKCIcS-ZBWKMn?_2
zb={T!0B4$d$1DBFBy;E&HRvlWDfca6PxuWy-a4-v6#ELv<5xsiusC@1jZROwV<6A2
z1z3;6I=l6@L>{d5*0t=c2;cIbN@1Epf7US`o2xgCmqb^vM?9Vo)Hn}u0(}l@Rq&c1
z{qCf^c0{dbaz`Z9XCO60##AX$iB)_#rLQvF%>MvRDZ@<BAs_MYEBlu@{&Yzx=ri@j
zL`yYgEJa7urA{lMWq-3_Q{`#VpH0U!{{Zb0fQYQ%j;eq_#(Gmv2C{V~_hzaQ>{<TO
zydQC*9@{D@FRvUQ^p;cp&lMN)sM<gqXgL)e&6Q+&Z-8f#OFuG3W^UwHcOxsNNyT}G
zfbQ^2YU}cyxhB0GnO-nR$UUlRY+XNyjcy#vv`RwyRPQ?~{H>p@Qb@5QKb8drrXa2`
zE0*>;noXCYxI_1yi+w8WE?;tv11(`HxFg!NEhO6N#eQDqwv4Y68LKnL{9S5od{1&u
z9%0?cte|qeb6Y<XZno?3JbO-8kz709&OYfIeJeQDiZzsOZjuXo(y0cy-?!YK<Hyuy
zwDhZKwFwHmtPh}~c&No)nfn`;S<z2gjix|3<G)&$Q}Ddjwyijs{c)P+mLR=4jz1dC
zIM~TvBl@|xFQFgCwAR$%9nZcNvIHa8(yRwPIi&Gye^*8J)leLwllXH;b!h{9h@jPU
zwqi0s{3=-OS-NzrrHheDj8K1S-8c6tHoUub`}q1|ttE?+0A0=KDsiUwWx@RGCyJMH
zy_)Q1G}E}|R{ZKRtizH|<67fQ&tv#g{{XW#^+HFkD>sQNkr=5PF~-r&Yw1?%w+SOI
zcJ`@$zyQcn53OFZhhu||wS`*k$3m15(n+G*T<PWfq%KsCdh;DZ#M)m;2*@3Q73{i6
z^DUJQI{McQ;!Qhds9dj6f&k{Z@R*q?H6geoj$3EWdi^TIcC6<FVAjlbJ?hjpSaJRp
z)htRQkj9R|k5wbs)tL0*pPTXmx)iYEJ9+f05m{rPAB|%yLmw&6$EGh`zk#c9X@R<+
zBi6T)(Fd(b6}SzaMRUs#$72;V{xOf%oOI>sw<foZztWmv9+)+swqvo+Nniq;t|_+m
z+hiXtZpjW87#Tj*N6Omd)%#na*wWJ*Y^&5(p0#K$^xv5`9ldKF*|tcn)3tPHJljrA
zK^-d=?WoT+j>rN=&U^7zQpjWO55l#kwFz|~8P0zSkzpHqepR!s#Ntto&yFw+SW7Xt
zIQsEdpokHHR#p&rtldT{8H;EKN_W`+?OJ|LDW(ygf}`32o^6!zj%kf(F~~KjBFg^&
zT4P1u`cqW}V*>Kk3`dYYwdZ=$I!wq$2U2U*uHYs!w;zbFHSruiTj7RWw{NX|7D-a`
zvpKOV-8t-a6sy7X#Ru<npmndUN1VwC$mXjN^BT2+M^DP2afhNx;0nA`)N@FngT+X_
zX~h7$KN<q&oJT&iqO`FhZR52lTzx3TIB`{B368Z4ql&Obdx23n$UW;hL};c47*>=S
zU^bjqc^GW)D%1=>;Ps_PMibP!{V|`;qL^hp>Oq3J<1{+vCg^=@da=<mB2vZ;EhaxI
zQO{b<6vZEV(xe>I2Pd!PPROkhBe(~(E;#h08K9mj#5fQ0nsr5-8kZo9)3AicbImol
zCx9v4y5Lh=r)r5Jky=56QPi@Gd(>U?Srk}@80V+8B#X7_VQr_M&Yf}rDn(NPVsqb`
zv@*-msYY>DLvi=N3J{qw89;gFqv|?-wDQAer8B>!YLNg>JabBV9<<PYzl}SnBc%-i
zS;l+R57+5dWM9IoFz2YOW{o1qjwu(f6s=7h8pZBeY7>X&nv!9XDzYD#Rgz05YT0Ut
zAp`uHcplV%eQDx=90orccF;TZr9qsUckp(qu&yuxL0;6P^Th@IsIXjM2OVhng9aT%
zF6_|Xcb?VHS~r6(8=jHj#}8t7Kb>euKX_{!!jkW_0CyP&*0!bl{?+-WE<Cm5kE6po
z!4c<*O!G={N#EA6Iz<N}ko2YfXe1NXfD<Nx(~h)#e@adVN&sK!NJt00E^$aY@j!#E
zG>&@;cOJMD6W=+eorF@m(_p$xI({J6Id|ci)ycL2)b_(?ADwm>BaudV=Dj>NZHdFK
zSj$76t`e19WQ?5`NP8Q7(txg4?tzRR`R28_>yBvtbYmUQ<6Kp0%B<YwyEcRr6_CdO
zt9s(N{a;DCmg%I983_Z03&(2g&$k%#qrW+>+y-S+2HS!%#9`xIT1T9XD^TP80)NPV
zjXY@jiymwyz&Jb)@vlVaFbyC*K5F#8)_h0uqmTP8mvew!3sPV|(4-%V{{W3kABMFz
z!Sd2S_qqPH-4Vx9C<ENqQ{pUCyB4y_D9O?^iR@D|%Nrl=rE89~oOGic@OiHmwOLi0
zoVRCmAfUNWxX*e_VAA4`#;`0qe_A;n=86wA08##Uqa8bDgVf@H6R%A1Q(K?jf$LFV
zcBe$eWnA&iR9&6Pp2jzeVZuV#&&|*p=3yB)=bG!hRUeySyNs_n705!^Bfr+aRmvyN
zhl@TtFjlI^N}iQcScx5SewCphs_eT?bDyBEN~A7v!ge#7F7$#wZk2J6VB}}knin6#
z`qwL@bSi~I9y?O10(j@ztTObbfI#=C_Ij1hAVKd^#q!c|)2Gsv0Vfr;HD+f$i(`;7
zahiIJw_ZJJCFh{0sOPRguEcV&@+m8jII42Q4{T=@pu;1rSC9a3I-bU+aJf*GjPoBu
z(=>uS4l2VaED59o1KPQrI~((mG7R*gM?HY4h|fKJ>7yT7T!G9vc^EY+@sCPkjxuTM
z!Q!=oB1G%YdU`Pp{uLN+N^q@=8DdeoK04#lsLL1w>sOm_P){{k`qGjd8A*`triH19
z$)pNT9A>d_Hs&E=NC&?)Gmd-H20L+6$~%gqij@aFF;Nd;Qm-9<ooNzePw$gTykk7m
zMgaDw4x<&SGGw804l(u3K_c_dKJ{P>tw$j2f1M_W7E^T{O(rqVA6k*H38sB{^sJgT
zxW*aHHAYWrmBSwRri0H=aZ_Q6ymiGqA5Qe#_NRe^pVp}o%LoQXKdnfZEPLXkP`i56
zirFA_6jWD>C1}p)!iW70Mt5z<$oiV-B~V!B*15k3HtTcHVaVYB0H0dwCIn|aM_T-k
zH;u7!KA#QzG-tTxnm8V#9V$sd-NiE%=G^H#WLV7k!jp=SSWbE`=4+<%P(MW<LsA%!
zuHE>@PAm0ijc10VbD4`unU6erVW@pBWL{W(Yo_}&WA2<|nm)pW=bZkPKU|TbrE`{B
z2WH0Xnzasy^B=xJ^aJ&-fY`>Io;%c*(EY06ZQ%ngS<4$UvW@~$_obpSt$aAr&asTX
zdgNmQx|<yq&rgJGLBGCzD*ct0*aIOMVtFLf<rzO(<Ex6Cw7IXcg7{HVP$OKS#(Gyd
ze575KKU|+m=wytR=xU|aubvbRB<Kz+j!xw*4t1koPToaA3n@9`x{;%?BX$FN;-+l@
zBm)Yd^~qYzo5dM=S-53Fr9!_s+nVSS&Ex=`+4iSt`cbi591eH_w_%df)-26|k>0ar
zrb1cFm<X(WE7Cq6Xr|KD?=Ao{xY`Ik1$mCE;+th68&HQo#f;YPgFIEO+Y*yQzR~&1
z3>ErTwEf?Cob_)d%M;kH?vmEsrE)kG$6o3WbvcoV$6;C5SN9jP?`aq(WF0>mh&ILN
zAX2MSm?+TY)t8oBj<qAp4ZL1$!-Zdd^@n$=!(_X>#Vy!pJl8F$YnK;~uuAyONXHd1
zS3NvF2322?rLXI+buo$u0wv*>p1)e=Cz}uQu_X2OG|6PfK_Hs0TPHu3D^#p~CLa$P
zQL-G;XWQ_k4n{NEnrLE1Is7TCaB9uVOEY5t;A5`AQl!kIt_4s=EA;wQn~C(Jn3G8^
znE?Y0pIVWjj_UzO&yH|7tj{n610S6NckTZG>Z(&YaTrQ<qiG?tK{NpRKn1@|wXw&&
zWl1g6as><rsjiwEl)8bVn*vOAJ?j?iKqhVFayy#ZGP&`X><qB;@+mBmvE_*-o}xz_
zXY#3%OGW#{5-ND^Ee8sJ0a{%1B#O&yTZ5mbXcl9#)`WL<N4PtB;-`-8$6z6TU#2Rq
zNt7))&z4B3<BDj(#!h`}P+Z$LK)LkID^CkxFH_grt}}Nfp|<StDK5C<rDo55TsG63
z)w|1t5wOlZ5502o%Z6gaj(S(7rD&s%mhGM9ji`B=Gb5b*#ANmBS8kZLmk&aF78TFv
zfHsoM2UDEZ)#v<!?bL!twQP*!tj9#5rb6Aj6IL!FvQ0hOJ-dm?!Rl(P8%&G8I0CAa
zLj;b1p<~c-nwJ}h$+{(VTVhT=VS&234Sw8D9kX-5^sEc0_FO>hGC{~Vt>w8}s9;0X
zaaJRcyo|+g>OSwiQGMG9J*%eI?RH+P5CXX1g{(w`1(qTSAZMDHMA9szla!TMo(RQu
z9vHladn=1+4qGQA_xe{L@G-Y%0DOnmlGf%+TZNJ=52>gv>U7$lhlA<wG#+Ps4@%~5
zEhM*&BK!h7_pbNDx}sm{GuzLVkYsXyl~&aBw4TKrC^&9&{VLpUXUyZHI4?1k({acZ
zI@}e!Oz=LLt6G+v(A=u=f-(TC=Uta4e+~WG&tqN7Qoo%uW4~-v3`;`mlh&PXP`muz
z^$WU?{NvLUnCxunGX1AXR%Q9uJu6ZOj;PQm-0v9y$m@*OCx<2TF5|RDT+4;$iuTVA
z_*&aZu`=vdX$DxH^r}@*h~W#e_LUmj>F}=`w)Lwl`1Pv6l}-l&lg-cgSC2Veov9W#
z(ib6fP#4Fw22wgUY6=M?Af8XstC{9g!4!`9Y?@~A^u-~L7f#p=4t}((uP7uoKN_Vx
z!4q~rDqB54CT)!PU^*H=GU6sAhGyJ5S1EaJvR`8#FgeY2dY_!Iv!E<~mC0DiCC09(
z;BenJdT0&EY@~!Dl>mBG;sPexnnvly4l1;{BMK^nPo;p@gFQ3Wx^o~{#w(fAkcY|Z
zn%UmLaB)Brv*iB(g*Z1AQ*rmHQHu^UNI=cG>S)s#Jt{sBXRp$nk{3AJKo&)^xXEBC
zSycuBrA^fw-3c_nRbWLysa~a~n>393epB_PqhRzVu>5Iqv1m^iBY7PgxS$Um*DluQ
zP?kWs-N+`enXpJbed|i>`KTLq4_x}zJgjq$rl{2#8ho3hAYgNjYi~wf`hqTUcViXH
z*~{h4fNQq!g^$|rjPKDo0MHV4iQ3HNU|7N7Mg}V)>9VXy<cigqJrChnm+n=_!2If2
z$YV}-Gkey~lz(!nc=fD_NLH(MvK2$Mh~kjWm&sr{XVBAT`B38x#~_N&vekkTvvlrH
z0~Muks`mSp!0(*qkkQUxu0H9&9jdmIBY$ZiImh#>I)N%q;hb|+w3q(?iL#!f3}{0-
z_~cFF(yWFZ4?)5As)|&o<DR*tF6!G`p6cGT#4XuXJOyPV?)p|N%mZ!biqV{wY!1Af
zdsbZM5)s@|5SGJqp1!<R<)ZBv9gcpLiEi6S$6DXFIg6(xew4t_jRc4?dG@Q;;ZOnT
zS@5$r%DkGn5Ml4_NG@Ao81Ya^6A^|LC`_+fRwbdJ49u3#7^r1U!=+s*ht5aRqjeZO
z^q^%#EBsi^N&u)>;kf3MJN6WSvAB+%D$S|f-D;ADJ$hA`q}hy628y;Sc*tNd4O2$l
zgPaPr2?*Fd4FD@4^53Oo%buVRYjm#Qaa68i+Z#6A&;|s(c^Neb+>M^qqa-A$II5Dx
z#zDgl^nhYLJh2}&Mu_Y4@8{6;sR_;q1Kdyp9%4t$$*S@`;nTG`WOCmj<a114nBexH
z3T^V{mNE$EtupPHF{mSNo9Ai((hHRT02+F+1HNjqNwibhhBMUtX@PBWdk@B?8%Amc
zRw@p0o+?ea_Ml9gi58`{^!zHgU<L&`ISg&qfg9FyD=7f|Dsg;~NL8DW!4;VUfr1TT
zc&g@WZB1S`AtaBH+v`9bT<Q#))rJV-og4A}YZFDiH+D$H_bI^y^{u$qdX2xSpk>7y
zlXp{9<QN}XwHWy-2@V>7IX@j~>wV$Zm62JZ^<42@RpB;u)^OQhW5s*b%t>)+EF_Pa
zNUs#MhD$#c$!`4?M#FmZT=>m!@;Ae~OzxmKnLTq`vK-)y9xI=Lu<A#zdf##auhPFh
z#4S&Hn94KHy&WlQoZJVcW^2(jx@4O&K2yl;T73sJ)=<Ey83wv=)!iDgs=5(4bH&8-
zpAK6I^)V?Ri1VEK)4W?VJ>+rc<xax8&$C4UW<UmO%{AE!nyl_yCxPu>rDVC1%<-Pm
z*5yae<ESh)ACYx3$?evV^Ry16f%?)Dp60A+@p;;nx*zX`{HyHhOOg&pflfTrQ9VCI
zfI+6hpmVpH(q#+?JrAu#Zyv}{dJ3Aq3CCA;F;l62r{7Y7j1*5l@g|Jc7cFrg`j+?U
zR{Rvsl3WAI{{RWjdkX8XEh4?P@@C!j2CM11OgdT=izJhrl5zUi&`XHbT(#k<tH|Sy
z1CtT$W3iz{80L!j^U@A0&%Ao(8>HGZyNr(9*PxC?dH0XgH<094r<F?Blyc(N?%Bdh
zp_K3sH25L_lFSyaC8M-}uHB=PlUlbH>n5A$AsHQqO8Zzlo)L4y+IO2YXxP~8$s)Y~
z_-5WqfAnjYS#i*uit@cbQMs``Vxu%{cLV8KFXGGLDtR)P-_-XNdY5xwR)!rKL-xXq
z2OEGDkTvZbup1Yj_iLK*E~R&SGWqic-PjJ*out~uJ<tr81CA>7?pL&Dbh_q>{ADrt
zQogIEsNpz0!tq#Fx(qhTvZ9VV)hSBJ7R6=B?Mr^7x{^lxn%$IPjA#Q7TnfR|wfV19
zAj%*;D=64ZK4BOK+N;VP8H0B8r(zvO&WlZUcnQyb^&P`8W(Jv~WZM&r_U5O!Pzffq
zM43|e;-H20+{ga#t2Y=^RYP(+5Nc|CB}3vzrCFR=#(k+J49!q!l6jUf`l^b)i@C5d
zUn5i9n?9Nv#T3>iCje90&PG#_$E|8ZZW=%<W(!pc4%M!C;yFvP#ah`kl8&K)#%oeb
zSBXNNJ?honym4F>P60gu?^WfSb~DMX9alRvN>&r>jpgS*twLkkIW=Kt;}k#4GI=!#
zwYbXo#V=p~09`z-Ar)5wcsZIJe|%S`Ux0izs`<%GSD9IDH;^lI-U&6+c(cTETG>Se
zFz=5aIa6M~Q%+KovF7FtSsqQ}D^nHTR2`i-u19HJ)!yoceO6e?DDsHp9&udur>C`{
z92QW#wlQAx;?vad`HYB;_QpBw&0SO|zjPmZjZAp=^{X(lODd*%upCw_3z|De4Z$}k
zN-)MpYV=<Z_-9JLU$r9dZ0;Cr);^u#OI=e<Un*^v1B~N8rCZYPrtoyHZ76vF<#@#w
z5$XD7iD7MT`?w=g$L0ZXTpx=ejvY!^&~5onIO+a)uD3_=WLk}?n`pt551CI<T%U>_
z=Hlyoh$DPqzMiy8V`v(F74W@;+G||8mT4DuazVv*x^=3<Wh5~Hg%|_d6^G#RAH(s1
zjucl<rwo};^y!*}Szp1>E5mT5juuzx^{y}DHkAxEP+f03T(Dv9{z0zWK!W1R=IA~Y
zw569FF<xEqhgiG0zDqYN<;C*=4`1`mZvq+Q6a2x5=y}Jrd#A(K{{V_|CI^C|yef7C
zG3XB%uX6Z*$A@9(KPdkIKdo$tXJE$=yMG8$YskDqalciQEDs$qUa>L7te;Bp-F=DG
zCBYQgD{`VpLvdE3JF$+Hm!5gWPZZ3*cA(I|F9Q``RYy&vXWE)(BxH(=&H$k?nU^qm
zZO0?&RrWDG59M0!!M}$i+*DhAu~p1Xibf|}cOePlv!I#Z?=C$nfA0)-tgGlmB(eec
zccS944n|LEhGrr@DmAzbjof=vr)Ki^V*;+?C>K3{T4{2Al!rObttVQ|vWFa=`KLyu
zqi*#O8;(2Hg2b`foD6rM3LCbZ)TrgVR5|NYM7$G7XmRP(nvITW%+(P&rce_}oY9_o
z(i55h4Fuwo9<+q>%@+Z4gPv(~?M&%FIG_i5(Vxbe58+Fnr2srNO9bz3`{He<zr8@J
zS?~r;SzS8$hyoMOOq!^Y%^`C4L(Fms$68WAQcpSer`c&&SUdJ1?l)GWcyi;(G8y9o
z8R2tY%_{IvNwbP@Zbl?TIXO6{$O=DP(FiK+q;xo?m~`v-*2`6L9^`=JQsXp{oTo~6
zewC>JM|}PjPEWpS;pA004jUCUHYy}!;l*2w{G%XML)NUqMlo4HsccMnqt=rKmb5Yq
zA8PD=A5XUGNV0e}#^b$o{sfpqt~wqAD6U*oZ%vxge)2nS5$KmXwYsISj6bVaC;tEn
z<5gwe_fW5}Qft%-0Kl9Yvb<vnpFv)297LfWSe<nsrMcvG9s{|&nWB5pHlN^5YibXM
zmg;jY%+H?NfFGrGx?3OZOOcH6(-pCY=oLr3Z7f9lnR_UnZFlhg#@1NCGGUK7Zq>I3
zfV5b!#?ThW@i8K|HMEq$8!6gUo_gl5My~Op&lnXhwC%Y4oJ<4Y-6TZ8boeul4$)BP
zdNrJWaxJ_;k-B3zuB1o7%O0JpA4-g+-P#k*c_+BdN3@gbK2(dTV+xEcXff?sdcCv}
zO>ZCxoxpVOTj2*4m#*6ef+k%3?EX2W7TXzdA&FFA55Q8qQF$^AoDu2XrinboRtm%r
zI#c|<5AOc}J}L%b=<Kn1=ubxJ=~u<T&j64;s)n5#3#*0Ps!7i+`BnCaCoMV;t5r3q
z%>80h=i9c-XB_@Dt-O#r^salvSJsfl2z#hYhQ=}pAB9~0-LMd>k9N4)It<d5h!&=k
zoyh+H?wZNb9}&!?l6Q5dKZrEp8FZh_z~}{X*1kEgu)VlhV3!2oV2m25Ma?@3PTQU6
zIqYhdtQ+h=uVdc1qwzORRVFJL7?1BaAEs)R{{Y0bxwSFd+K8C?^Ze^b;p%oF)Q@w$
zv<2;B@AB29fzB{1$|Lxbtw#!?tZR-qQPQEC;vT%`<(f4I)N}e(EF{>ytWQU_vz0Zu
zi7FMBrhm_^Ym0n+_eCD1g?K&AyQtktWs>E*!gIJWs2^0mbpfvC<I#`!)}K?8>QA;u
zw`%fOMP$YABKb~w=BwH3`V!k9d-dF-pk8am4c)|mhq;lDp=yM%CkLNg)vOxo#qIo$
za+AgW9)NCZz29CxopZBz?@G4S8hEYVMPb;A^5PJj1O)m4ntLP0Ky+l!KvxxU!ohCE
z?WB5?pA@XsPnD+}`<l+a_?<n~yG0GCh@OWT$Ln5sllW2-R~#)gPqmrY$MF+ci8dpm
zr>@Rw2|gfe(q(?qP#@w70sO0!?aAhs998=YeTnvx?rGg?x`o_^Np9q3&Oy#FY8TaS
zpYL4A-&0hD1pM89I=)Eu7c(a}*Ck5*rc8S=sJHyZiOU}J!^rJG>+Md-2Qx0&w&T>`
zcC9r*jOXyIiy}m))YiOM3DlbMF-p@q>ARt0{{UJKOd7SWjoNBS({4Gcc^m%##;<Av
z&C*-g3}Dj3zkLp-$0o#vC(?t~g4yfo(vu(#YuGr&Ii&tnZWyH9+odrJk506dZsL%)
z9A=QmepsTKSdYSxK20lyhZ9GxX@QSS(r)7=x^<<@I}alwkepOyurgZ%)|%5Ilk;Tz
zRCA%IlN0Uu)NbDO7?8ILuE)?WYGt&&n;un_%Y)oTYdKU!#wA&X`0?CTaR)igY{%if
za(-7&WgqRZ1l5TAAFVbw#{^&RxA<3?QQlWNqoOgRZz4r2fK6STsXcRA%iyb$%4XDJ
zTpmCbY5X5xz!`N{&$97XMyDgWGgmpV>z<;6Ai>8$T|9ml(PM19w^Du}RfW>DIK~#q
z-`SkkPuAjP?3u?IKtFg2H|L-&k4|g2NOb7e5$Uk6yDn-}oug1Ah8V#9;!=3T9>ttI
za9mHHCfa8suv)bqjjBj8EL?xQz*k^yu33NAV0s0nIg$SRxBc}{@t#Gh2R9#vbvX`P
zLlXZ0wA|H{@SKhQw^M~b-CX|wTHHvLeKYM(3IOR@JZ!oYsG}J8V#X!RnuL$+sZu71
zqyj&8JD*+Et`Ky^D2!&I;_5!7dl-}xP155(Er~zxxiw}awv1*Q7}MQ_PGdfwjWj1U
zo3A(2J(PP76G)_NL|>xPJ;ll7%lIuS=bn_O9Xk6|`$osgkq~EgJKdY=c%xtkAfL{q
z$WhSLQb>xqE~DzyUg2Qr%?i7@2CL0`Z4!<55iWgS6;-wEJ|aV2AjfRe3mW(*t7exO
ztO-0>rlBEj3lZq1qF)q2C?z72PH~WG9Fp9n8=WTAE0B5grWH^*BiF5S&#yZSBp`iS
zqB_;nbX8IHtllChwMnz1EP&%6QU?0hF#3(`gXW!ZeG~&xwD&GPX{5*d#}%8!M6Y1Z
zmPrr~zPbMZdZ3cx1zfa>KN{y)JfD4urujJNrlI1B_6ED^5H5aTY6jHMV;JYsv&=;D
zdHgB9R&&Kq)>%r5E}c|ogeH|PrMNp$KRVA4uwVuSZfREFvgg0OWm6R>tCp#vq_*0M
zlFJ?tcLK7_<mluxb6%U|EycFpq>ORJdCsY5ZS^OQ93FF7VexLOcPrT>Z+J&qO*Qw=
zm)*-_t$MD9;_EG37@&=n)3b{3yKTtZM@s8F6DUnuWDkRYde?ks%vZ2p&CK=#s3z<c
zVffaKrM<n>CRe$Q0PVO}pWoT)4Kqr*kr5yHW(O6=T;H2LZYy(e(KLsb5|N*+R);>l
z4_&#rSlPD89>9L~b6i)7yiI**$hNa=K-eWZVu#c8>DD=>xZXz~891yD6lyjsBDRKj
z+CYBlb6M5WIvsd8bJVnvkEr?g()qJFk-F!pswTvN(z+XaaWpE&9VyLbGq~s4yoZRh
zv9(AgCUYNU!TW}~Eev^AF&>#=QCwP;JpOe(pz_L**o;;+s&mAYj@IS{xYJx8;`J5f
z^4UChQmM!x&tI*2m4u>8bq5EIYm?NhJiS6rpf?~BT)0}iiK47?>14!n$JVUHWVq!1
zRjD1Z$4vXxsI5RFJl4{##bZ4zK_egq6>2LCjEo;~T8VFl1g<{{ogv3g^^B{E#!Pk?
z&&$WHPL?X^j4`ccgkqeLC~C>pkXXqUC<x>7rwc>}rfXEh0qMms#qCn6u(6RXs0;T1
z_Z40^_L1JUC5tM0^He;n9`#)J8MUIzuw%ESL*i>ib`tI65KShTAc|_$)S(kvo;k;@
zW6jGep`3(P;kt^o916G?=z7(N<L0MW)Ybb@SVV*68L5^XqoApxT%|lNDjh))EPs_a
zNAvcng5$LzTrj9?1Iq)_n(^Rtt08iL<E=G@D7aXn$OmfAkuf0#wcRuRHJ>_u^!2NZ
zfP@?Y#co*5`>;K+Se*J*>p3=_PZdvLjnpB<&f$zyNf-mAU%XE_Lt{Pa1XGTcnve@`
z7~DbU-lq}rX^=1PD#>4)oP7ljRuK?Gibh{Snx7f=q}#`T!l#^8D}*@4DH%Id>IQi@
zrm_+{esxMfXU`EJ;{))oJ@Hfr4tC=?9M`7GnN$8X!g#9NF*wM{&*%O{dwD%eRz@||
z;LkbgIQ?h`2ik$k`%+ikBgtgS-!By$pE1u$6dYrvE(u<0gfT~RQm#XBQ4S4ADxwUV
zuca8pIaevtn~rN#NTaPN#%Vfr{U`>VggEriN?|?oQXZ6nNj~*00%a)|4N^pYTAq7+
zL%SKMAn)F>T1cY8$a|7%Qrp+R)~gS5Q$!iEstaeeb>8tHfw*ER2jNps3&7!B2;4F$
zn5>Y*6($BfO*0rY<*P)F1M;BsqdA}ou?dd-Dn<LbsPbv+(wGhcj8cw8I3YQt&=jTn
z$3Lw{oK=aV!6O2ylf_{pL`sd?q-HFYT}}@}RwKg<cJ`)#XeOpZo;v2D+lI&Ur>_n4
zrY2iMnD9r<nu|Cz_<rUojlr!GAW+{mF6{k1MMem~<39B!K@`}A)n{BBb5^iV6$GnL
z(MYP?W13;$)Q&16_*XpDjZpPGRhXMO7#~`yoYjbdG6BX7X#!ZJeB2s(si(YUTkA>(
z%T;1-Dx4g5_NVdRG=L0xQ?bS~nxPC}F-<r%AYSwlfzRthKtWD9+d&vO$j5$Zz;57m
ztf#SYXJz3DfkX_%al+S4Faf*QAK@tgn2cu)U3}v|HGXfJLzfpL=x}cI(Fr-DBifLF
zI#Q3It^=@D;*&X}9MhKsb)W{|ib{}<DUJYcpy#~^1fw+N2o7AIz)}+#&eDGxViSyY
z7^65e<tP;H&V4C=c27AUg##n%X-i;WQ=BgEmo%L@pazD|KxjSqr)NC-Q9uX>f6|w=
z9=^199MTvLD9(7z0Dd$cXaFM}X(*+}C;>a4T3m5SM;?>_zl9%#9XnEklhT0*dQte&
zfk}+!fESF8w0|l<Flm0A&;lGDoKT#&$27En@+cG7t>PiSNtY{@+uFF8&&&wNHRu|;
z`I<{(vXfqa7zKd_zf0ljm%~K)JkmCqZ1u)!HeNV9`&5ClxXvl8GvAu}MtI4UnQ%EZ
zA5Of~?x1$4k6x9Gk+fMGU<}lKa0h<%GY&od>L4<4o@*&1WW^%`tqMkI53i*IuQ>c@
zh)A@&u5b-GI`zgqDY2ZbJ!`5bGbaP(7(Hq?1Dx|xrz!7EewgFmil&H9Qllu%G!ODB
zSMQ388T71Vjgt|Vf^mvq81GUX<Fzo3M?BONAJUu+H`1KFeX&ggCR}aJJ#)n|27mhW
z{{XFOjAU8H7oZhghi;WBg(`c~TygDGLMt+^bCa5nXdd+|ijS|QX3?@^SaDJQ8L5~Z
zyb6f+^{8c_9^Gl`N3Aq;rvs0r2uzq@(}xG4rX@TQ0phhrY?(;Up`;*_?@mmQ#)tkc
z!`i8mnN~rA#tlc0OjNS-+M;2TSu|}HBXsC0KAdKy$II8A)fpHk{AvqBm#;siJRa1+
zl5tMXKC~e+bUakResx_B2dOn+0D5=zr!9zEoqvPn&h+RJ{{W?SGj%<=;MWh~2i<WX
z3IWbo`{Ro49}SWGBy|<}PJFp>Z2D{)y);mmfA#T91M#V47(Hqsk&rW9Db{ey2R|=L
zmMdmqkSY(}?>rFRo$Asz*yG&flZ@j%YxH?L9)24R>ra&qHo_tM*2i)wl3d3c{EL!$
z8mTqQ&c%l1%|cj{oaV4~52wTB^y#H_sVtK;nadt~R`-Lg1<t1?;ghq2T-iB3)z|n6
zbX`s2BxJA3$MK>L^3=R!Ek*K|Z!O*_-CKqP@G1bjbCF$L=7D)UvRpF<Kf<a8F<4XE
zGza&9C)Ts68#BU$)R9BW8OLg=b#7I|qhUeLYgk*7aj@ijQvH>if`G4j$C%TRGo8Ni
z47O;XMjVc~?@-0#C)@t3@yAN&8$^O}kU_^`&ML${6t-Ylp(T1}ZYegIJd%#g<R$TB
z_aLHYEyvu&S+;{x)Zy8glppVUS7~eEXv=N4vt~UxAN^|6Zx3EuqT<_*nLJ{IpF|pc
zrg9o@h9H5r&zT=N=e2Z@F5DvE3}69WC5MFGXw~PKsXxL6SH01uvbYF<K3nA{(zH~k
zEx}fT(1JTD{?5{(Zc$u*r>owO@derx;}z&vx`*~oj8^A{W%&jx%5QZz=Um36S&z=H
zITT8oiRfkSQ<eE{QEB9vw>y>{vrR4TYBuAgG_g_bNcy-%C7|aj#Bognx2;9goO)A%
z>5>IALD)Itr6J(;6cf*_Ga3H?^-~ZMa(idBH_RaM&{CeFn8%uuMczkxdO0GY1bb7|
z{M=D-7wz9`0^Ko>$BK_pwTOW2&N|a0eWRcvth)&<T(>2AR?uggnqk#iFS(Fni+A@$
zF4)xY1xGF2vbo57`z~s^)NS*D8y~H7CVV8|)3YvyKy$EDgo~a4tl_CZIwYID0@H@3
ztWWNlPI0#!)43Kjgs7{zsx{OQ$cTrW)@-_%Acaz_I}uP>2Ya+_t+%doz^kXMk|pSk
zjY?Ky*X7T8#ke?jZb<5De)c@t0l~@dT;zu`I1Tw4_2iC7orZ#Oq2ruqgIm|k1)M&D
zurwwMqOUpUBDXIv&_UnUw2#7!r@1Y>WVt!ORn11qMZ08mHEs;7GUF!;)Kps=>_`}3
zvFIt8vlj7x(qkCL271(%Q~5Uwmi{5qoqnKS?f&e2O;Anopf8N)nqYNW)v7hj53~~N
zTz&Pig8ET{H+ollF-wg$(nTPED+5upEvX%VZ7cVWtpmM|ZDJ2=ENxkh1|koho|Un&
zpq5yeu^^B^<WvIRb)1U5yW*jvNV1-tc=mH<G88vbYq-!aqtq;Bibn;PkSl_g-xkd4
zpO@06(=Vsf?t`NZthi<ANoZ7+&aYIn{p2o#q34R_uWZq;=FUdkkH)(VHu61E)xzg;
z^XyNhWZl5as4;LbdsVe_D7PIM#+cb<d>s7^R$P@iJm$A0wq5e=JqhjiYa&R>E4DZu
zm4ua!r0!nu{lnW|th;$e4ZE)bzL3#18+}hkh@`nYbM>#7EUrzo=*ykC`GEAVOVD+B
zEu&SARzP}JCLvxoHl}(7%${7#ySx5X0l3IK)-vh_X3H_$JD&9OcelCCdF<%1w6fy>
z^V*pt*l$lt&w}+sVU(YG(H0Y2$Cy&2b{Y1Ju5-;)n&<#Sa68d0rR*+4!2EH?CaX_n
zcPaw05J=A>IHUwK-YHg4+0PiRe&bM*+UcGbz|T|7Ya1(t7?B8S#MEpy?kKn;o_%N;
zXHoHG&)A4iS$5$1)E*DIeM3-bn0Fi=)y~T+M20pBbJ$lw;CUm8?YB3}oR7wu5#CC<
z?Zq+5qScF#n-rr4thrdpCf=f`My;XRp!cha?Cpb9Y@#AH9V+rFr%X@-)p_SNAdoL=
zi+8;^b)*CGTed3HBWmWWq4~J00PYy3B2xSu8m%jwa%y5QIjCI~fuINzB;`osn)5Fl
z>aTrvZ9>XCv)iGsM&4ta+PN)m$`9=aVS~S|Or^@MT{v?}$Cb(%8|GfUs)fvI$1B5E
zq}*s0*AZZRr`oxVN5gj(s?W5`804H(D#@KPqS3|)3^V1rbj^ClgTlq7d8A`^e_Hcd
zwBI&mOr4v)Y*(x4aIL111S_AqD^&D3D<>TpYDs=#eJdjT<+JP7v>XDh>sZ&0Rh!e+
zq`?$rIFO9wRQAUR!=+bZ4`WkX<$E4!lv`L5b;EO!iW=T)Z<;9>{{XyrH7&Wv9qPoH
z8Rn3TE1So0`@w_WjUcOPs#iG(O&9Qt7UGk`*c!BioR2RU6am$5F~zx09dS+GdLK;E
zCSCE)4;ZO7ZCsv5aYF$ah#4c0D;oAw=46k($*pNVxgOo?A5eTd58)jR09S@$Wb2P}
zT}GQIAOq64<bAFQuB%L7&><bV&?9M3D}uSL1puz#e;T5=$5B&TN_Ul^jJSl38}p|>
z1Bw{#P*<%vl;fHJsOZDys2xr>RjE+ta3>y>T5xb^0<$L=9cdO%&Y2_aUcCJ&sM%m~
z%^{Nc{Nt&oE2}U8s<zReN+Wzpx1pd7c+T!PtB7-hn#qnrPE_=(_V)uAZV$BpX~h2k
zC>Z={@<tg66-j60cdM#Pr`CWoCXZ`#ftsmxZLzllkZVfrGq)gQilZ*#0V5co4C5IJ
zX^|YZ3CSI5#J@4fsF^UqhX#-hb!B1cRi<5xNI52~G5ji|#IpR|yU+%G!xNucrZc*<
zB?R=W>4_3#8UVE$ZX_O`TDAZRJ#(7RibW_n8?ntyvTt4+6v3KHAO|CwnLc83_*Ezl
zKyJRdtBMN@iU|-7LmmxIqbr=|qAJWVNX<zf`o6RQG%iuF4}8<LyMMOWq>YByeL9MP
z3vT(l)|@J`*~*8UsoS5W0A}fD%a3S0R_r4r9OAi~X<iwQR|h_|y=^A=`J^*p7!|0d
zJ83PC$?f!~OgB>k7{*_op7rNGCDPKz#c|H7fj2qrUXB-@I@dkpJ5BcXS0N5#ep}FV
ztgEZjk}i|9(UB1<%aL6Ja~cvmRtlUj$>dh{b8eaIiv0H!tt04Zjq6E82a4r71GOKW
z8Ka=>Kn;@yHsiH<UbUa?D~>bsSE{!t!@euayh58bd9ryRabI)6QvU#GoP3WHI$ya=
z$2?Y_hS4O~ViI702>{k%$Tc;U%URyVa)%7375YXlo1F<pJyG*mX(-i;ea~T!g#`YT
z`lqMfM}1`#!eb0N3b|i|VyQ}%SwdT*?_kqcLW4ynd8O@KrH6Vu&<`{k08V>X72~T{
zo?CMtBp>ju+PQxhN#qD-Jptrbep@SIB6H$@hR!nEOuL#Ue5!@&D>DA(YfE=ctU*6E
zJ6BM;!lWA`TxYqeX8sr%jPM3S{?2ReDC&3*b00_5p%87j8C~3NIQ%N+yQo7op!+f^
zZBlRzbNYqFyq8XGQ)FkA1Nqe_o<>p&R@N2B9!F-&wn+7@Zw;$9sn;Jb_*O|g@+)t{
zu8XKf0RaC17dbTE!$)VSMy+bVf%kGN&Tb@RxNxL=yjQ1cDVsJt@xZS%zKPoMMT~MA
zkZD9xBNtO`!9SHk%v(JV)`AFZHUShWZakWz4b2h1(a7t~T(}FrkIJ+3f08D^?^fn~
zob;<hDoq~lImfkUv_)j;--^@Vw|~l#L@LMkZhzo3q^>i2K${lZ9l6H>x)=x!4?$dZ
zlRuR(SIUFj^sc5Uh6x=j=Q9j5gt?bf-oe&VjhWHgz>HOwp{vulj^6{VW9hnrDhQvC
zMm28cc4fwLwct(?=hW{rt{Ab;N~Ha2^rPh_sxp(DS5zK?WJ{20VA&NOF-g0xTDPer
zjMx;ybI(d?Cp{^J{{RZ8#^P?pt0yaRkBoqMt&M$@=+3}oGSwY6$jSqT$n>lF&&#B`
z@%L-%a>^dcD(8WYtL-JB%;^zE_MpBF>~%Dn?Tj*M%ufff6^{km!oflOJt?=kgt815
zJ4YB5+lf}2JoJuOAS^*A-yBzUplN!2{kjBI4x^u~apK+PmCBB%rEO@Y=FZ?WJU2tl
zax#xq(DbnaZvX;2n!Tv#)|!}8aT2j!joz?yT}JX_g!`;Hu7)qP;1-ccJ+acM2-nlB
zZQzYOxPp}x%6QH!ULnEfjQ(}mSw3MIu2aVV2aWp!`Q%cT#?UNy8co_rL+DBUE3mNn
zq;(u-xUT|88pX#<1IOk60N1Y4#Ny$rBv}rPGrp&Ejr=+5UP<v%%JSo01`B7DZS7vA
zr#3a4;2R7`tPN&IlIhE~aqC?)%;tCmnr5K9HI2afrF&<?^drOZj{AF$rBt21Q^!9_
z)$p{ttlK#D$EW!fv6;|ZgZ5cImE)S*=Tw`q2N<tmxncH6bDz6jH>wXiRGV-2sAF51
z{2qp$h)Lq6dq;*pF!DXB6_|SFvNR_#0=XumF(@SUr+MEfs9nC40IYC0?N#1=y>Uv<
zfI;NdSvfsvp%G80#)SObj<rhS{5Ts<>XLg{q;5uPfhhwpY<2BSLM(_$+%fo5XS>Sm
z#Wn6!slp1VShG+T9?lr_6w-O^NtzEdfRX|PgFPziNUa+vIpY<aG7lAI+vm*ySLoq+
zB=+xCNGh1CR@a8lD5|ZVq}6%k-t5PW(;6XeDl<-I2APpS#3F;~K{=%BNOuFxCw^%3
zq&;X5r;e1IfBLA;wH+t`Jv}HiXP%T(0!SDv@srBty9nDcFF75Jak23#@!q=IW-n}}
zfinDD;DPO1(XX3kz;_0)Eyn;>{hJRb8S7OSshc>9sDxLN1zdB<s?&14t4C5zm(qLI
zbfgjMUi5whaleRI&&nzP09@2?<j2<)Aw4?Q$cBLNRVLx8-x;dY{r=Rau;aN2;-`o1
ziiC`gDoCpsZfQM>KJ)-6RnJlR)4;&3jBYdzaa%qYQkv{<g5NJn$puH@TmB7HxbY-$
z^!YRT*ES>IWz+bP>Gt}>Ge{!YwTDtoZlu=Ap^e0A-|ur#U1;!sXSqa7?aoJ9@f}L`
z;@<jr(rE&#9t)cCu=Ks7wa(g;<ySpQEmumk)}}Jw#Dt7>;<R7H+7xS(sYQ=tUK1tE
zk`JBPyX2l~GbVq$e;V%kn(lM^ZzI?>uNdf!Y`#>cY&Li`1YZ&~Sm9OjWhHv{uO;3-
zv=-@A^;i?_WO}UM6SVX{y0UEhwPHu{8Q{E@XzZgZ-Hvly5n^d~XPTvkriJY!dJMl5
zug(NEv7-8w>H5}Qq2v8mQC+*%EOa1OBwHh;AvqM)3TvRfq`RFk@z;nJFox-H1~LXe
zr9nT7wVBV&eB&b+T;uuH2R~X}#;H<=VCI){+0-tCts>7NvF;f2QMKjE{rj0%d$m^1
zXa^r!t0Wg@rk!}HAx2Hdv!1o0(um~9MJLx4ho)?j_^Y-RS2b#T_@j}dA2!y;<HdP+
z&1a$4OJhgQV5F!y#w!+fkV*T%K_vC>Q^Tn*nw!VTpO}u-XI#0rmMFw34l(mlgQ?3a
z3bbyFjpsd2G@H*n(+gzLoL8-Lj>ETcNKFEhITXNlayaQrk}0InSPp0dqwwC7W2&(i
zk-0g>Rk2=+XYi**)NRAt%`^@@^Ze`2JRfpmzEm9;=LWskLbyR~oZyZt%B@mrPR!mA
zPjk-?f`8#3)fau*+;NS*SW{f@jgeAhP>X<lE6{bTmzP;$c~RQD`^Nclq#gksX;7%$
zO-q~-j)xddDKZ<qF`S<C-N)0K^*PbZ(Jd)84s+>98z!GR6^TisKT3=mGtU%r4#UGz
zmgA_X$i*Rb7##irmoQkhY=3?QZA7_FD+b&#m=#G5JMFFLK>&R@HRfXeE1fizkT4^Y
zT0{wS*HAgyYKa`yt%M?bVvPH8I@dip^2+7OT^vDN9C}j;#(gWLe-B!j95wS3yY8ys
z)X``fQjeKtlj>{H`rS3u=k`+Ua%8S~IHVFGI0TdE1$PkXT1+G4umpd!<kf^|AwRja
zg$Mh!4;v1JDiSy-(d0OeCvW%-TaQN6=l=j#VJYXM3}U-qwcG>2jX&L5KGQkm%HPVe
zmOHX7Vf@ZjJSnWO1)z>G-+PQzl<;NKW6iy{kJ(0RdEJ<TT>f;!v=Vxn$>Szkpp3Qf
zd<bzisLlT5c&Qh|8ZtIsYl)Bh*sTEIb{~}?ZhO{m6H)aav55>?E`<{h^agx)XC|!(
z^yq)pX|RL-?MJ(hdQ8@Cte;Z7oKazKT}~o~1pfelQ`=CwBOYJ_*i~RYxTl8z5ssbe
zd7B-OG}jN$oWh}ZX8X=f4K^F5KD84%pW`1)(g4V$E~BkN*APa2X;6Q>YP`C(n;+l1
zk3P&OuowK!Dl**GOZbmWQU1K2V5X}-i!9eWBc1;M04dlGgCrknkaVt1yj(MsvpN3&
zX{rbDb>RdgF{iy28QUlr<0R6t00Y{%HSrdyD+T*PqW=K0l$TnC`=`rwAoan;YwRTB
z%r0ZS5~yBS4_um#OXwr}^F{~z!o0#undNM}^0(FMB1t^t{Y_=aQR$DbX|T2$@;*Cm
z2CF}dbhJ4VvGx_`gC2wOr)~OC?84`9FO96g{oE3`s*-rzF*_|7dy`z2+)x&)*^1{w
zCycMjK2jnNdaWmlHD^ET(S3r}K|_;_Qf)N(0_Ev7twut3UA7Nlz^bO|<;mYXr$6l)
zk7rsj%~F7_U$s)}xSX8llbU7RSs;#0I?1pxR&En=WOlCiO*k3fQy{Jh=qpQ31<pT}
zQ)KU2`W$=9t}}yPJ}GiS=S4TEdK+hDtC4B!#D6N#wY2O;D^d$}+&KKJ!l_=zWMX2C
zFpfwyBI%>kis*%^oUt7JX$`UTu5YY1Y07i|0NLyG{3+jI1GR4bo|<j`UV|c^wqvn?
z)|*d2MMCz!?AJih1I<;E5$Re+psZs3pDZ}Q`c}rD5EwNPho(AJ>vakTr7E+!5wU5|
z4&K$uc&gL=H5>!S8LpZJ+lry$cucm4;DPf3YYa4;YS`24oSZNWd(?AFJ*=K>yoDrQ
z;<X`!ao;|bpM0BSV8e>_=*isZ!&*tirv4+=Wl|pYL7u|1rY$>fm6_lB#Pd@au*7u~
zZ1%3Jm+Vp^-!pybWFUXFQro^C=3;&O(YKma`CJ}xQuQ^b9!GQ0bYLa1UNA*oczDfI
z@T5<1WsI&cG0ktjpCIFUXX{=iOg&zAWO3D+=4J)tUm&WnuG7-DZmkB!4LnQ7cB%<z
zi}$Y}{{X(~zOPlUgwNVU*V3l~HRO8cq0~fE&K(#t4&tJ<lGfQaz1(Bmo+{MZhL~5I
zut@&ulUTe3U$TSRM5>W-QY>IN$nQ$G+G+cfNci+aN_9IWP9eEt=oD4QFT_5Cy6{~~
zYaSOqwJ?jnYNWc%c*1G7PwqgaI>f~Mnp<)G=Ic-UD!V1(AYWADntG-i0<+GoepBSr
zqK&`WIUl7T+8VZUu-Sv2K2!cRYbUDull7RIO&RV#N{N%yei*8MY}Q<I_Q~oNEdKyn
zV+~$LB;RcwixP^s<g@D{ezOwHu`nE|ABAQz;p)s0UZb(Nx-)aY+l*5#1{~yKy!!Ze
zLVS$g66RMM1B8`NYTb>@uyyQfoeVNL&1+iDa0Yu<EaGTa5$%xr`c$DXxWzt2#JSFQ
zdQ-yIBOd_Vy!NRA3T?M>(xuzY1c|ngt|{V>{n~dCB7kBZw2Y+m6zIpv)}4+iTnet7
zR(;yw=QXV0<BFkm4)o%#3=FoD9`!w}o1Yb0NXicNExE&1$PG-EO}&7{H5b!7)Rx3E
zls#%mV)Eqn^{#1YB8Eru$T$^jkCv+ef(aF9a)XgWVi}4y@zR~QiZOvmM1RNHk;Xs$
zRQ4EQK^YuVxQeq3sRSD2d`}3H8Cx72u^*jwj=3DyH?Kq*-a-Dub6%cXK3dTtqP$NW
zejNIqX$L;lHR5f$lK>6JbwC(qzek40j>{1sC~1ed^fZyaIsGUsOA%IyBgf2X!>_$4
z88q@ZszM|}e7<Q2q+ayB`c{aL&S)o|Iix>@8PBCKAD%g-2NfO$I6Tlv#~Auh1;m*Q
zO&jumhO^iNn1Rxtxcbyj_l034W-;S~Q`^bq%#EIhwLlNOJxB+Wk9=0qdI^{BRLCQ5
zz4+B{B<<<=R{h1Tta@LY8fEYf<5}B=JxwTTgl6sF@rp(3SLBUcW~rF=u@z`Td-eP%
zJkp*GH#qv!5M!Eh@zR=2DmD*lU_DPFtwK4$Kb=(!b5g6ak;xv^z-`)<Wx&pAl!NBR
zD*V8>3^SivqU(;iHI$K2A><mKHrhb_Y9rUCDn-W8!Kp<Ou*(zHoENTX(elB1Rk3fC
z%~gnOh8}~dC)ScqxfMF8MhAgWOTgo$XoNyI116LlA9@MF{<MJPb)kVOa!zR;GI;`)
zGlR}6M%p1fB!3nvSQrv6-+F<oLh=tKy5}bXs4zLKDkD_IN|&Gi098V`2en#Mc8@y_
zJ!wIMC5}z%H+?E_gB4CMl#0-ZZeF#%=451h(srv476)PPP~!)$Gyxt!6vFxMPGg?c
z8;o}%m<JtkPafH*f%m7O;<J(|9S4S`+k3Q(Wa7KYcue&6uR75f$9lgnQ(lhz#tG|=
zmHGC24qR3Hp6&uyfnR8(00WXJ{3!)^$D~S|bMpa;NlFqnj2dX^NsRhXA-!lLr8o}s
z5zl%q789tX?ZrEqLx6ZZ8ekkzfuBkRFBE`GWKn_ippLX=m;s|a(&rs|Q*l5BF-Ct1
zaL1uEho?b62o6mGotiq(19?95r>8s$rFW>Mu5vgW98qhi!*~9zf$m3o>H4i+Pif1c
zKGHYkxpS{-0l~?m9*6R!BX1SVSb%<Xqw}B+PZVH-%>V<XDC<j#P$>Z3hJ((1DcI(M
zIqQl6j3%3sIvSU1{uG5r)`Y~z+>QEcfsB<k=Vg4U*)h<Z=Di)cvth<CYtHVF$9pjU
z0BqOj95GV#E!g>-+BRvHk-l6Wo`RUm&rUt)jDWP`*S&p-^W8`!7#TGNJLas(_i$J7
zs>J$Maz>F5i~~^o+4T3T2at16FaZ13Gd75X@N-GrdQy@wDGoEnDp5?aA5JP!_i6~S
zikJEK#dO5NMVQV<Uft<ilTC+}#Vc?)>slFgAYp^oCZonpNZo2P#%n1fR3RA^8NjJ~
zR7^2Y(P&I_*R42X)|<vDz)~4Be)S;h>rlop1xucJtx=4N5&ha@cj-=ug1F?+>yE;x
z&#7JhwGqjwnxa2URJ3go3h|nVj2e*S3Ss-zn=J^VCp79#ly{*4G85@f9Mn;qcc}*r
zS|d3VMhWBj)0?F-Gsgy=!;BiEG6ozGP?67CnohlH9yfnF&PLG?uN>55cBzlOL`e0?
zs5Ah3Q-w4hdV@+hpb4Yx)}|ciy+EF$ik*2p8gF7cohO9cuA<4;AangIzi*l~_1pbx
z&U`g4-9#b&CCSg$y%=Z7PhGY7e-cL6qv)^>^pQ?c$>e=15!S3sJMryRfgF>H`P01S
zR_ew=OeAG_1Q2T)dBmq6=N-*Tbeml{3q*F7>Ivehwi_H*=o6LCLo1+^d4$aw`AHO|
zK<U%oml+kA?j$0TPATyli)q$-cVv-1=@gNu&1z}Z65d@$3SbsJd;S#B6(YG^&s6X>
zr+=wfsktK?M#4uuIn8e!0y*_lb#U2@mm3F9twX0mx+adO=Oiy&cB>j5rzWB$EEp(1
zAtQn-qjjnARiwS6aoBC=hhdeJ+x&z0fvcAO9I%Qp=0qL4mNg00W=&jM3uZAN<MgW<
zo!pRFJErbE25NaD*vp<>$)K>Z3`B6oG3!<)vbUBUj*E{`#dF>tX{44*nO(?k2H}d;
z)otgzvoYJsV{G*taZi;8Gkr^Tc92>}wj@xezj`jO?XA~q5uW3{L1-j~(m3RD>;?%n
zi>m3DcUQ_&9$SAFe(eG}YkA|I6_OSO7-u4xaXq>+`LZIOpqhrp53}1Wf87|YpAzYo
z(psCT8*Gt-wC0m`E}VI!qH<plby((+ZP4&L*PE3<*uVt)RlP#x=D1@cvoIuNoYf-0
z;O4oTx%XHK9?Fu4?Co54s2PhMc%^pF8PC#?06P*X9*P%k-~PQhNXS2>H$3#EU&ffn
zbQGONJ5uyLDTL<~2uA6Oix~jttv$E^ij2}FfEeJ@gAC(1rhX!n9-Th4fS4V_4b#%C
z+Q^K^jJc{Y<brtOtw7sY90OMtOykWP8M=ktwVl~nBI}Z)6<It(V7q^GGB_=^toV}L
zOKz7NFc&IF>+M{rO}%)*t<$;j8HOL(RcPv?@g<y!e7IUcoNznWaii%ed1Lm8Q9_<T
z#c=)@@OGiAx11zMqdbGRIUfF%=~CHVXgW!bNlT5JK`V}F-16DN-Pl0)(=ZqThyxud
z(b=qIU;&D@4(z)gSm&iVK<m=FaO(3$6*P%TR5C~vdapcJBPxjQCCSgsd;8a7ud~gS
zx#Jwy9eahibMIcnj#xcTv%?G|(!%m^*yg$!({o!VJo|L6U&3;2xAM*pIU~1P>}Fl>
zZb8NeAR4u?l>Q>X`7NA*obgSPPxVWT3}Y2)*2nE}>~|5X9`z=#VwRV1B4n=KwLHr9
zBF}T3kZ-@ZVgXeZLh3v~di>lP(IgbOesPiwQ@+oY7CZV?fvu%oqiOI!&9$RA0M@Rh
zZT^vN;df<v*B+Dk2Xm4XbHJ|lNfLc3)^uecV3K-bmBE}<<*{4&d*`vN=n!nUPI&KK
zzM-YY+JtfepD{S%xk+ryS98XIge3K&ai(P$huEfE`_^Q!GTVs;4>h$H&m7_UvBoN!
zMn1zJQH*q{v8rTRPNw!3OUd%tPDf!~3^JwMW<~0~E0C2j4p;lau4x*BT3+Du6OWi0
zr0gjxmgI?r&Bk~q(y*E$ZJd=Wj@8o^7gEb20fWfTTEUfglw%}y9`sH(6eVL3&ehL6
zS4rWUr;&sOi(qaU<mS2gm*mL7tsf8Ev^O4RGlN{*sopH;jIF8P3zD1`D#C+%w4a>*
zHI*&jnA~vHS?6V791)(G?_OP6P7Lj*H6(7uti8OM!mt&$W$_^_(Gl&5Q<0AU09y0u
zE*Xzr1uzZWPJXq{%@0-|6tvkt)<WR+`D!_SB<VcuQ~6hzeU~8RjYljhs(wJ<T0%Vr
z^T+yZpzT#GN3Ls>zwumGJG_)-z~>{aU`rS$p!!vLW1s}R)R~EIKu!SWx^Ducmj`o>
zS+kC~7_Kg0N|EY1*J0pmpD92DlD)H3gnA^h7@`BAsBKS~ILAtYdAE%5Ry54{neCdP
z9UKZ(2VqYqnuQp#7|uFXg&YrB07YEXs<;@Yf%w#bQUUANj%vy-(UVZbr#z3&rD90p
zn1p#bJk@t*Cypt`HzznEqLqwifPS=qjzSR$VV*0F)Mqbv+;Lr0u6DNL+PIs?-*n{q
z`qovpI&j|+GB--JgLfFn^fjLo9s%iE5HQbd4_f3sA{&nm*xk68qKOxiO_$|gm$z!x
z$Pk}Qb*x#Kf^sXam%@2i&xnbe3Ul7E?>KIpR-~*eF7cF{;<QH@K#(}*r;GwPHBF8i
zv8ynigY}@JRvn>3a4L2q$t3fWS<%U~fP3~8E67+J905QX_v8d`T3-zO_qPs7;BC)p
ziuCc<In7`2+!?f%Q=GS2VmDSjr;L7d;=~SdpGsjHbI;0s=|J6_o_%ph2w8w!epswa
z(ppwhFc;UoZb=ht&))aNVcuZA{^Vki8I2|ny>z-vxs5sN+PP^7Ry<bLgE=v6VmB{J
zVmnB1$PZex9A|K4;<Kz|z!^L@6{fF_4;Y{ek%Dp0TAYKQUe#XTZvEZ6)uInL#Q-ss
z6~-!r@$-^!1zyWCk(~W%v+z1lG*Bpv+~S~h2*h>gtzD8Z$0LJK6)ZjJ0bRnLeJUbG
z?9}gtI4AR}uG?GGP%_*-GoC8qoUav@v$oK+Y8THUfHfgyCkKyu)Q1e4LCs;t#ens#
zSV2#pBNPE?kTB-6ZV+xO&1sC4%~qP-2;GmyfH9<q4C9)CqYd7!%v1t8nygn~_V=I)
za;aW1#%dXGP#o3QIT^)Mb)*+4OMnOhv#ug+lZw-ser*1AO5ip<vBdyV1Y?d(PYYpl
z+M&i<k}6o60|1U`h|+=70ml`28GT1JksO;P2yudIRwY(lt&Gqjb>tk=)j7uonGnWQ
zaz4E(#ACB&fFNaclOL^US~D|YKp^qWR+W8u_ou+&Wyd`;NM$+VcyE|V_etOm)vIl{
zpy}SByo5@@$m1TBHL~yqdQb+e3<8XF^{HQI?NCL+fDS6b!Qj&w05~+;m_^mA!pErN
zJo8e?7~91{7?0&i>V&jsB|W=9O129Q^{W{_V~q6Tpw;8@r($wRIjLbev`ludh0Uod
zb!?A&3qELuXwNhO??-C#PT)N#>p`QX046dk&HPfEHHOI;Ve;3cV~XJXXBOM2+dcY$
zUt7WzIWgS5(dFjQ=Ad)-I&Aunm>?r`eR!&JMDa>vejRvW>0K9t<O!-unc=y?@5Ns6
zevlBG*w?qsU!YXYeU>?4YHcl#0bqIX{?;3zo(t8PW|GEdP){mJ?Oo=5YsTQ8?3Yp8
zE<ufkaoks|Y1fh7*uyk!m1WLr<G9ByP@2U-Z@KK`_?~)x&Re4AYF^ZxdQqDAGujGV
z(M13!L0q4XRldO)Tz%o!>s?{#T-S{hoh?~LcCaV&uG|B)c$nfphR-^e&WVQbSK5|f
z?`lbWw`>}Isd6SLN7FSDf5*8v$sMci=<IkCMgv4u_5sH@#U$|+$sN0jl3CD9dJk%`
zJaL;gl^^B6;QQ9(8ClB@Q^jm(FiN_Rd|-58x0=kez|<|vbPt1Gy9Sx1-&)5kJ5u3!
z$m8>+CNzle#%#_r&3WbQD;}dM3=V73ZzKNzL%|~>gI;;5>DQ56Ji7}<-3~fY0Z7c6
z5x;oArmSBnH8{7PR@#W{-9GLq%^TZpNdd_99V*ByX(hjUIT)*KnE(+%?!F}Es%dTv
zl7pY6USW)!P=<xDZzoZO@tie!eY?WYF8Gm)5AKTd2nZKZf4n+ZquP}=@$z|4X|dS5
z<yfD+Z5jUnfLAqs5iaBruGP;$(zm24tHv^G2T;RY?)I$eLNz1HBU*EG-Qqxmlg@uS
zw3nt7*jqU4Y4%oeUV@Im6Tm)|759d(EnG6o=0e@iTJY=Ttv1%ju}2vhSu$0-6JQ()
zu#j$E)XNPql~lGj4%M?3og*$l<Lh26R~l}|YcS`wbQuI=(-oTcB^!>%n(kLlh#^@}
zu_LbIT-K|jtWV~`Fg-ffxOqmSu{W`vw_-uGb*m6Sq!*I_d(-rLRr3o;jQV!PY0qO5
zx$F<Udw6^jisxqqd{(@u&yq!oBCuST$?laxbkwes$rG7Fc4Lgzi)irf>fiU(AK2&z
z61e&r^r_X9HazLWn8p79gi~289W6_P&kicQ{u$OprN6V?f$g{o?X72)-FBHW2S9sP
zjCYSY>NkCBe{0Y289H`6!E`NNIWRP-fc2~PdKRnZ1#3A~N$ZZ4=;nE%8;XKE{M4fU
zU^gQQZp3n#`ZbN+tY$ZWlhZ$iZbY{Sk06i6p-o=pK;(W^BJ1}-he7`U0jUmCYRnXj
zZWtq|u4~5Yn4%!@#b_^xCOu>Pa4QeR8mHS~SiHPvztW~#6o`BmsKIY@EHf}s^K<zh
z>s{@o-K$N$JB5)*&lSRaKAIoxDWQ`LS&syC$N3fLvfEpsE>ovGR!E|y<k4D3CEPF)
z`*Lu4*OBYKJ4o)%ZSq4M!?^q_)h~5xKe5W6DFu5P`RB!8%dAS#U@lKV)1LLbB#<g@
zZpgnck6uM!uyfdY*P!?+@vij0KW^R1IIj>E@;M{FY*(~=KmP!b3ZG$HMpq`KDO23*
zr)*lxIUuiU@+r{&0Bp<;3Rv@AwKIRC$<sS)%kBXF(3!LRSgK|ywsijhI?SKF?dx2t
zk1AJ8V`)9>zP4Oi;B&ZhTsEe@UZEnK20Y@kv3DU85!li^#I7+>9%+Z3l<XH3r8p$j
zOPL%*%!itM(yUAKWY%rf=JB<0^`-=0Yn&W;gYv4=9nF?GV@=HlkP#eajMS<Sk5f^R
z&!r$6){Nt=Eg>V;fEOaIS)NGG6;Cy4(YBVL2Qk{`xv0rz>)xK-a%wg|T4fEzG}DQu
zW{?PI^`j<`oSFbLnlr^GQAkcG0mS-J9=y{tPXp3`04aL^0QIQ-C>R2O91h=`)1E7<
z(}-&{!2N5J=qsqvTXmZA)`2rlBa9qY=A7Jo-K!NVUruhls*#&HZFY2m^zZ&Iaaj^x
z#={DqoojfmAN0h2F_YS`gnU<}PNhc_k&}#fE<oGR=Zcp+`_wkzg*oP?>DIj}e+kb$
z!!-=xRQ>wY6ZWEe3M2$on`zoLBiGui9-V4PYX!Nawk|ZT!x<u&Tdf^?;(|TRY+@$t
z*G1qjpT)6^<M)5mS2}uitv?Ig3ttmk%FI=9jMp|J;AWKfK8BjvZS5s}<mGxA`SZjf
zMz=mci=J!RCf5GZX3HNXmb_!cxf;t8pO|#7HwOOzcy-tK44N~|G`I)elX%T~*Eq=l
z<E<DKADE($%sS$Wph%a$G?@C-W_~HAd>`pYG7B<sK=rELd89Kr?~0c+QiClMNsoG~
z=DGea%A38q<o#-Wq8}qImIJ*ZIBKZO-lmvK_hV4%c@&^pSqjQ9*fn#89M&^4kDGDG
z^rj2x*Nx`5F%J5j5LPx^4TO%|(^^n$m7AXUtb=_sp;G5*>sl~J9M(*)C{h97ipHF+
zBBZn;^Vi!HeWsu``($Mt^VC$U0}-93y*SEj=4vDS{L*>E)5WtK61b<WqqjsgcAF>N
zA@f-K&>gYTtcw>Pz(q*5Qg&LdNfXZ!T@vA-)RInvxvy`~wMbsee((q!?ynQJvXVKM
zBOUWyBv%th9wT-D^#J0$>|9(WsnJQPY<D+z5?$U%(2eV!iPpJa8d=D;DJ+4($3V4S
z(^|T<l$f6$$E9eEcTu^I_m3IR`xVVje6zW%mC@%B+g#2+b89n`+$~&>L)GK}t%QR=
z-e4=W`%LU`Wd8uZc%^1?GFiVm>v+z{$Jm^Lcwbd>mq=nC?LKP4cv5U;OXySRnf|rX
z6$EllJ<T{E+r>l0&!E*5bLruGWh2bLk;kH@Dpm0InHc+%$^P?J$z7(HaC=sNS*ZG#
z?4o9_m#0Q@ESDqu%uPIOg@1PpY4lpM+*Mgu9Oj|bo9aJj70`xjsR72}k6}^8mOO(^
zmLN_^$JVB{Kt~^yP3{BT0**RW-7&GfaDA!<P*=TAr?$y<deQ;yfg^E>Qb(;+ztwCk
zt{Eq|RBpR#HT+klu5lwb&{8cMxy3Y+53O@A<12h+Ev0X-{{XJ5KaA!->g{pr8K|)C
zb>NXe>s%}NyHa9y`AeTcRiDIKq=)`K6o0z3a)Ib<06%zCZ!AfY&ZFOTd91pP^rI48
z$U*cts2H)%UC;aqj!?PjGHP}(g3?@|{A#S8BhupQa0&LWJuAm1fydIHC>^|>F0c)?
zQb+d-O`FA`6f}0M%j#OV#Lh))MixkLM@s3Xhm7NL9IRcJ##bZ}6})Ic?rMylDb*jO
zh`IC?mpW~bfl&dP!NSEC<<|8nzWvi+{{VLat2Ncj^|+Y*T-12ytvn|^X{ZY033mI=
z=jzl19+fbU9`xXxbTy)+7b}Fp;+=!mrw9S`r7FG1`c?ZOT&fh(?KL?I>qtU@$;Cfp
z7aI`T)uD~hpXpQ)*LNJ_&{l*#V;}-4Fh^uH*+$&1EY4TCl_KIpO$*Imp3dc@`E4gB
z{<)f1w4FvkHdxGltBT>|)Y9b;ze<%-w3Ea7yAh2&$JK>eUkqymb8LzAkX5L~17<GH
zw4p0`d@ZS;yw>T@cd1vxcbVqq-F>>^tK9A@vz+qjJi6*v!Ys#|%xC+tnxFm<v>+3G
zFVsg%njON@eGWLFG{TrYE4W_<T87Kda{mDE5Gq07?KqxNbM<UgI*{%)8Fo0kU^k58
z8TGAMVqYh(LC?~<czi3R#K8TO@%`zITU{ecLNjX+{{VVJT77B>SUrrJJmJEIAh5u#
zZw_s1rr2}Zy91|bK;Xk^pF_#5D_ajOSM1^l*RT<DTsWRu(B+AwZwYEaX%DKL{VPf<
zcOUZ2zbbOUcn1@*p4dT77WbdUJg4i$c@HhV@;W}TVs*A=A990g;B&=5Z0=YL$uas$
z!}`*HW=PHRGdKIrSk(UjWUj0}v*b$F$En%}u4*=g0On}d{s%zQGs$1pkL<8N)vD*$
z6{5<Zx`);o1AUwxZlV7GzUsWoZT|p0!3Vkx)pPqgOyJ0%f4NUxJyiV8Pw866FQ$q1
z@-j?z-@@$QRjCBgM7av@?TXbF3F_4gX>b#hxSy?Q^%`A?_VP2ow052?q&WWoXjFGP
zl-Ch?e`NrFwArmDv4ww!81$w|1WKI%G~<J%7tD}*X)~UACI<rp9RRGW;zI)YIqGYx
zbxwXv{VJWt;xLfp`kK|#M$~aGo4Lp`ox~m~1bdGav2g=46SMQ}RK#*G-j5jfsP<=9
z*JSo93uiu`ol72>Eba2PJ(i?0mFPLGO(sbm<y4`-?^POT%6Q3|+E$Y+P^!Glp!L|;
zt!2?-d}dh>u{o)2P>9D)D*AEhTJj^3Rb00zE{Sgt^&aPndg-t)Awc@o@H53bW(cRs
zjNF+?EMN!j55lZ1q+oE1QmTr708_B8LLiKP59vxHj1hzs@_JA?Jt>k*tA+mn3Tv+8
z^K(ud4o+zsp7^E%HUq{e1E1+n+y2!i4rma75$jJKX{6FI_n>G=q+Eb9Pp)e|_BJ^q
z>sRDLN}N+>P0P=qua?bpt8>xAzjVU~2ftd<gp#0+Dy*?>a6M{kb}QeC^DcB35bi#>
zt4f1yL2jj&bz4>Ap{_~kCQ#THY|YI~!<uFYlvJ<BG=w)FT+$IsN!RO4L*Y0CbHzWW
z6%;u02&rm7Mj0ln%DEM97$4H3kutfam>F_LrB5Rws3_V&#cD{Qvw_pSP;rLEZ%$pr
zS+|#LsKj-xi4aK`ZVh7~$^r#xS=_rtw4)4hob{zvI`aj=;UHvmsnCAxP;kpa9HFcR
zAso^XnhEFn(r)L{fe1!<psxayoUJH4QvxSYM?LEoSBrhDfb;;L(zjR)R&Jo6+qf9X
z9qY3TD^yIDj}g`oN2oeup8o(}^NOHrZ^TGOrpE&ZCqCyDibf6vew#twnrDqQX)zS?
zKD8!!sD(&ID`EpRAUPEo;8KPotyRQIt>|$<>DHqRGfEFM?kf(#Jt#TB%^BmZ2CCo#
znleXDw3(zQ+NeNkC+kln`t|KmzD-2NhxVlhu1z(1Q@J9gFgGF9W0JvPl)D|c`B#dl
z9Xl~UT7HoOJWY%qbBd!NWST`inBx@by;>!r+e!lGBB~e3B-04>%^mYv+*TaMke+|W
zlpZOEtrs1I&(fT{nqc724rzsl<c6oCeB6;ycjlBFd(#z*fbUALDga39OB}m#M6LW;
zr6HoDE)FV4+m0$c<kXS2IQ6WCO&Q&fOxBE2ZcKFJ6_$=i7^yze#A6krWVBtDMNoOi
zy;YI-9t}j!#9*GCb4?6L$A4OP3kuCiyl0wgXFl|q$l{BR#PPSy&1hR*`EADnvO%e%
zgt*S|2d-*GV(sKY<$T@1F!!vfBib?PSD}~!704&C^{MBz7ZH|BXRS<?#*8d}2DL0M
zC1epa%BmNP_o@#Iq@^4TgW8-EX~7)UDOr|SmN=thiFYyQJ*w@H-g!9!v53P}yGfaN
z&lRj$4I5Gv10TieYJ|iS$6s1xvy#A$l?zN;f@<y|NhD|5m`^;=Ty_3c5p0?+G2=Py
zPg79?ns6W=YMBhx(&X8ApPhP4N6oZX{{UyLd3}l5bdSY)WrO*a3H0K=ABgGNtYmu`
zd*~)Oq!`a!QP|Rx*jLUTumh3nP0uv65tH?x0FVb1pqdHW-kZCcX*aMoJT6ZlQWfT#
zpL#Ruz<xD;%6)~*g{9-TH5qjSmr?lAeWnq|oS&UnvZ>jNnmx&SP<i&M=K9eN8s;qe
z7p69&W~-LFgedM_sbQ->vc&2`xoiyQo+#)!HAnkrOkRH720z~w8*6%4{{WZRe+CAv
zV6hKqKe%4nn)^nTBXW4_SzqvxX(J%s#!t00_>V~+^7fUg%W-f1UB9@GtWsZS*FRsv
zfOzXz&ElOTf6ID}yjiAag2(7ZQp&N9{#~&=RTcJ!>*yNL<luKT#>I0iEtQ$ZKic5d
z?x*5QTck0=6o)((z`zyGZuGCZ$}n@Mg;eWA@UfNDs&he`_8upi0Fhi|u5ejJbk>@+
zt>D5<89ngT=Un5~pB%3d`5cAr0j_L!4^XY|QukSSe9CardY+&$jOVQ{Q=HckW8!J8
z*sROBF@?wf0Is@gEn3p=?n*a$X1+%ml;UvT6m&hBIJ$LqW{@0uQh+hdBCuu3ur%(U
z<6cY9>I`CnG17uPDSC5A2At9`1oKYC1XDoCV_d?+BN*>qeW|G$t-v61+0A+!94&B~
z=-aD5^Y7Na--T*>vWfHAyhv^NK~G`dwK4!U0h5tZ5t3`}*2l~}$XH^aBc9b^@BqoG
z%uecw7Z4*IY6r+Brp`q|{e3f7$l4=%=aWg(6utTDNuJ{s2^LKe7~`c(f6gihk3OQN
z&MSBr$et70p2MH;rb2xHsfheDTcZcLU5BZtNvjSrJ!-i*HJpuN0OveZZPys)pN#!Q
zF|ayjvn*~uN>FH|=eB7Kl{u+u6>d8Il_=y@q9jWhAk)dg_og8v`_!&7D?=7Q!z6-g
z6UXCIIK@KMGBt?P$o(mXpPzb-xF<D}Edc38eQ5<KJkT;k>r!T+T-3mPwP?;n(F}@{
z2iKa0GlNqQ-&(UaS8zIW_|z@erB5eXfbdVHM2%u0&mx%I)Q6glx#`lgW~fXId(w_6
zqMQu^B~oxIWhS6OQ=sOVEY#4Y5$chb<8qOT^%P<DbU4QtuP4(Pmr=K4lA-h0@~=~}
zeA+1F<BXH_ug*B87ObRuxof-#=H%e@{#8?^D%{xQb^6t2<n$ihtK~W#p~Buw?I1#U
z?kbu4+~b;(>5E;ma6s-VJP>Q|E`1gr3K6mqh6nSf1q5-$HL7(VFTEqSC~B`2-h4mO
zzSXIjnBil?01kQPxJ5f#xi#tE4CHJ+M;lHE6;Rcjd5oMWO2?sI*rnaSlv$S@4L;J=
zD@YbJP@#P*KT^2V7Ul@7*W_dKxf#ICUb`}jCn^504A(*NOl)_Sv)vd`!Iei$RPs7U
z6EuVb@0#YcdkLh}KGgfvE^)iPZt50eP_t`xa;o3m??8zlF-W`NU{~6+^<87^1yL6*
z=xWxPV47{9fg2!mlT`Ix5AD}WH_fo{z#eD=M^C#;>m-~FtbXvS_j=Sem(kiZax=Nc
zLe;BFXzcCQD8|)M(vgzU?to=RnR(}^pbJdfP?6UeuQc(NzcH7|$=T0J^oeFzVv<)p
zD9w0}iSH8cRglI`6z6HIsx#Kgu>R7oGuappz_;G(P{`X?AEhjhfO}LKEZyq^?O?2j
z#sR56l_HJ2QsRR^9@PALbDC#E+MLbafCgjvcBsi9^q|vE)M9`UpCXuBJYtlCnoQ!A
z$pC3GG7TN+3HiS50wq&{)9|U$#_oI7Vb}7hROHh`E_o?=6T<k|%Y&M&ZQ(d&*jcc8
zX02M17=E?Z=(cglq1&9D!!@i~^Lgbhri~8>=<?}A114h%I3x3`zBQd1$7p5Ujzw5&
z%Uc9ND}+6Xt~16O)Hgv=7hjdR_w}ns%gD}1qa*Ku#S=y%w=M`L6`GFh-y{3tt~bvb
zN5(~Z7)ah{EoY%v$GRj;@=qqYomvpLG6e&JitG$(s?Cv}g0Qt)EvnD=i5=_KYeSAM
z(ig&{Jevn3H+t@Ff7ikkR|(-GzVNOv#kyCbNf~RLXB$Q+TM;+!G0kr>TSer_vG)V`
zQ|9w-FH1<-*u3QQt8Nre3U0>L$*4&K&tO5~mAaF5bIpNoE<3rZmxy*i2Xl;7=Z%G<
zvwHTZE_pBjFe-*-T_G*A(z=}r`+kk&zBeX5Q(XPx;$oyQBi54Ic7dB|>N-+o9)ltC
zE$!|Vat0Tg&$!crYI)i*AkP%-KHywvB{veta!zYPSp!+y-6jEC3Z02(5;WXi+(ZZ6
z&JV3+M`~SVQ~-4ZSD?>ir&1GeJk`J$tYy>o&2bn)2+t;{YDW&%o2(=Qjih~RGFbe$
z_h9^|71u43q!&DH<knQSfwb1bgYyHQdMs#}mt}Ts?twpbxT_2!nt3su%neYvw=r7@
zmz4wq?@fZ|$eCE5mX+)cT&ZypP(TM6t2$}(ZG5QFx8$BGXJxpVusWK(p%u50nd1aE
zN}g4Fj`|lYH2LL79!Dw_x{pfQpG}T?j5i!rbk*UFb_lm^Z=k87)gYGqd8DGaz|XBz
z;TbD5N|ckjW*x<&hGQ7q6Rs+z=SJ&_?zG4(BwM71A(xJN)K^{{j(b5m6-Ukp9M_*$
z2DgdXPZYM1#|xR1=XEKPNxu2y`qj(bCgRbGy6$1<D?R=~Mt!T#ohe5~b*U$?_C$zf
znQEQP$%Bqa^rev*xMn!TM9CWU7_7!oky=97;Ct6m;OKm!#2x|UpW?24ok8tgFNK?Y
zVb_{yM_k|Ct!*wZlXYdN%MX8A-?LD$V>LoFVXFWERpL26txuXjNC@fPq>rv@CF33H
zRUWhmvJOT7sZ~O$EY)3GYVk<_05Cr`C;=L5xdM}PPs7m|8^+_GtxqkQN}n$VfGAx;
zpJ#Hd&{v#XoZUJ1?Ou~TzRPKOCjz|A;db0h+vh!ND%%}cUx<+$U<}rb4acr4G7-<x
zwCup(n&z?SbT3ZWw@^j{cdW<S4_wu~LO@v*e+cPWl0P}kb){r@)#uG7M=ImKYcB5!
zed|%5aP+Ku#tg)Esxc`sUo+mN9V)SGI5lPv7$0w10J6U_k7|G2UbR`Ajz5(=Hdm9y
zFe+ZLE5PQu9T9x1P@EDDO=1X^S=Y?L3+Y-S_*+VnMBp-v5soPVw>(P{`G9<<t~*oU
zNUk7bzYY!xilu9*#d8q=s|Pq?o>rueV`X{@;HGxBxW^QLvnsH++CVt&E1JJS<`*1x
z=e=|@+@z%JIL%>Sa;!V`rUn$p0Q%;w=(B~q+FJvyK{{us!KzWr(A=Z1P<i@L2clTB
zGL5Z|YTCE?un#qXrOJ|RVfRYz2Dj~-3`b1#phcu#DY!fy)p{J1sw6%tdvfdapbHA2
z8z&VU(SyjT56lS8Xc+>5nUX7IyHz~rC%EleR~)eeilES))B#dZax>DICnyFwRk;R6
z397|-!Q@f`AV6xF8)+S>g#qnHu?B&fk-jlkqMLF7xM0>aG7vp6SK@4e>p&Y2$aa8v
z6=8z1V--dTeqoOFbqVj%fHS7I!xN4woU!F`j<vTedFlC83zYKIHqP_`n9+Qh=~bnV
zBDCaOrbSYd?wryCE?9c!ip-gEHucSGOs6fJ;<IO6qon|5I&5xwW|08jydEk^jylvx
zdw!I}T}D<1*0imh7{*R<Sy7yv3~^dk$^cxDLw`C1Uq;%&{{WR*OuPGIBCEteToL)z
z*jJJLC;{znk=O93l@&>=B=;Gpq+e=4PNy*pbB-y|fF$&)=_<n>U!_W}l4qPyGW<?A
zZR%=t`HoFdft8qJClzQM98fYx9Zf_4!Ks1yao(b00j36iw+EeQBpk5$O;Wc10FN*+
z&27$tTX&4`7*;|jmk|VeSIY4P4~C*WOa)J}Mt!)Via4*BJ#gx1?MdIQFKS>XIj%Ft
z;1d&L__9rQW0PDzjbuCGT;K!EeIE<Oyuvm-{LR}A%x?}p-FhtW3Lcf|H_#=`tD^za
z(!AfpOTS)59F<eedSZ;B2fcedVN=;+>CQW&mnn}m2Xo19ts2tp;cOgsuBX7)#KkR}
zWQhLn(yI8z%twBcC>;8FRc{BoCa}x=EIn)JaWal!lexaf1sJ?OH<ccc4n{>UT59yC
zXWG9bk@X=(6cf!z3(!^{iqn3M#PkNX{c9J+MZd7*AQDGv>B9d28a}2~wSzpuO|z>e
zHsJiVOM5D^7a)!g6?tQldC_6PW;ESW)^(60rX<_J9qaDsK8Mb+H2nw7ohF!uLVob=
zTV5;CEbR1SG9Xio<#^3u>9Fd^QZxjv;7(6YYe&X9l;=){)&Bt2J1G3Rn(FEY83`gl
z>M(Pf?YuvJ^G2v#fTV$%<Sn6TSnWS|l52lRa~!=s;rW1~MI*bEhO-&q9<{Ti_%cmW
z)6Dxu26_eUSS8q54aWg$#+mUTX$S1mDFF{cDqtpcmcI_S?o&P)c-$A7&%gLJ_P3GV
z@UU)x3{=)17VO@9IubpU*1CLE(%gU%fj{i@t!_^#<J!lCCGf_f_Iae<tbSJM_*Dr|
zC_Lu6KNt9x9e-X89yXxieQOb8dx>@+<oBZCV>Z?~CA@_r&UfcE=nCx>q<&!9cJqT+
z7P?DYI?i}u+O=MGG3`AuQz;gZ^|}4;C*}00ZuYd99Mu+|%5Hj7mgCH91JAW6?lx-a
zM69D7Gt#@a(RB-}1qh4NBPWXB^uzv{2pQ#uYtn|HHM}v##A6-mYfq7CX-1zr(BrOr
zGvY}8REivTWqMnG4)}$i4|5zN+nVnn)ON>$yR+|ET8#LRyexM8YsjsJr$2hftxlxd
z<z_s77u87$`jI=h+#}6xN8l(VwjXKKW{{DNFa=w&GRdW)!#FHYIW@l$ZGjY=kUG~+
z8wpA}q;leG&1jByPw-}$Vpwf56Z}qjtQ}_34L0}5bLEEnr1Y;tL?x?|_>S;LrKw=1
zLHXCDqMy2X&ArZHmKPb0L~hvzp(&50ai48`kC~94PSv?#E!?)nmSD;|Q1IdHY-zE_
zK}-^mc;d5vwWNq*c!oM0broSXD>q-hRG!A6(vmGyOuTO9*|nc4dsM5b+grnl<l1{0
zrn@HPB}N}w$kt+lL=iNuuipc$3z=>wV|45KYLZ0x`czHgZ8USetA+mngl|=u$Jni&
z<w(l1o<&)Mz<w&ZY^IjO{pKIzR%YyW*82UO&-$m&){|Fl(5oCARUHH2--$lm3f)<(
zPy_QgagqAhdEyTSC7zJe$1@)+ZYp`=lS4-v;W*gq&R1{&JAHcBtH!p|z*1?5?bn*~
z&xeW^U$|KaEKnNs3H41P(*FSLx27Opk+^YLq*2c5UJ0;Nl50!Z#GJP+kZZ&|L2fN?
zrG&Y1jkhPgeL!^0BJ$owg%E-{Dr@I29$Q0Yugwf+<?{%lTOF7m;vB3fW!}9Fde?wX
zbY;gX6pyd@=DeQKg2?>hy;r~l9S?)YY<+6*@7^}d;<+Nuwr}+k{{Xsc%dRBbsLs9j
z^{-Hr<{5w8HRTtKf43%#V+7{9nc^KLp3GuZ#%q@G8U?;2kEL|lIotsBtS=g`ku*}1
zfu4BlP&1q)8g6iE1-MuHtU0MSWqm1>QoWWxEtQT9WHXMvt4{tP;5S3l>sc(E<E|+T
zP}FkWO#(a~Xxaq;DuNFfq+~eGDtKNbUzh@YYC~}tJRm<>1W-B7DLM@Isb`bSZ16sn
z2|UsPMoAT7+y%*Mg#l*3sroGg7DG^zO3j*KpkPffoSF&sr0YNdG?~vzQZqro6aa+c
zo1B^rB>*@Knt1l6k6Lj3XaM6hcA|_>0`wmB(dZBUjkk}MxxD>rcf-%S%u+ZM37ryF
zww6Xpw>j=>DmB5)X;@^;7<N4=qc&uCvMg<2J@f5c(HUCoyh??w2JggI9ywa|aN5Mi
zW1=`G-lgNyiiR_W^{KO7gf=jcbQKiiijbUkrbq!od()P}MPPGJi2UZ6pURd$^_9%G
zHG39;$A7|}8Gnd=R1Qxxr9tgm7zzX})rg^ESY}CLm*!U8Q4|}pDFS5msFW|EN!aTl
z@x{zhEGufKX#2&h8&IBYQs?atg>IOv<U><{!yMK$@UVogi=AfGgf?yuRs89{V`6&&
zPTKhEMjO_;c~Oru7;Oh~DL%@hxTliD@tQJmM=B0xH|(RXX!{`SMK}^O%{&@85c!!G
z*>mYYvtMIYRN&LqfLsbWA{@-8_An^>AGKT#qJt{qwI>*dG>U&?C$PmMT6<NNoMVcH
zNw_@Y=}_X4NwTxq0=$~anl_F`U)HrAR?ah3ZgQ!*xG_sZu9GML*&J4lf@C&MYdE|5
z)$KK2Nyy!fD~2Btv)I#!Mvaf>R}rDxjs<7B?BJZAYE9iM+Jja&B(*ifkgs*8eWDx_
zky!ibH-2@mG9#4O`&2`{C)*<(xvY)n9cV01b4NJ25v(u3=M}9RZ;T&NT&FqbkzFl=
z7q(XGUUoZMGpi1*aCIVa=~}Rmsn)Wt7H0XP#~o`vO-k+n!zBpmfnI!I-p5JQM#RaU
z)hw={b<g8ob9b(4p^y4WRr(6glTo{u{bk!9p~Vg@ZU?CupupcM0q$wD>bhO3eD`sV
zIs;x#&$#8JC+gXz7GLjD8R+u(r$|wea8IWOs88b?AU|}HInO{bTs~K@&*4%mGB+X_
zPJI%cfazuNkzho2hyDa=q`oM-l>D*AgY&GEv$}A0+RQ-z0A$xmq4*C`)?xFW;yYwN
z!v6qzpC}m8Yj^SzT24I_S5x8VlIqoDcFO=N%ls@crexL7A5E31rTBPg@d!=Sav(o@
zr5YkwuNTS`Qb8Uj$2?Y?k-#JQri?e%pjNj=3}wmBWvK&&@w^^g@-W(Z@m!`*bT#g>
z4-Q_&rs~7Yd~$rIs#9rx7j@YVleN1O5ul`a((=4y(0Lg(=%>LtYs}B(+<eWP1Ar+<
zgS4@e_7@;}%4*es^PVyHhv!NPkKz^SU+|7-@qDdg5F@VVplRAHUv|>af4nnKo(Q#0
zZ)AC<V;$-00mcI#pf%~pnqm)^?1)E9D4^ZgM!)g(68#WV`)X*lhpP68=7Qd4KP(cT
zq8d?UcIOFcIr^cmN*cDFfadEzME?NmRBf&4z@Oeoeu9(4Q!QZYKeBL9=$fOSmcmcQ
zwe0jAP^KQxuN~Z1MBX8>2MZj{?@=ES+bPQ0NPe{8j!@XY?Ap@%Cp&ZDJyqq(#}Hpu
zdTMwxQzs84x_j=;bWP%P3-Va0`n5)UQ$O(AM8Az^EL?AMRh8FfN_ZyZ^}dVnTCko9
zOaS_W6YUwRE#h0wcBCu#R4uOG9AZGfN{_DCwUkzSlP`lUJKf4p`zuq$;SD?wovtMO
zaaql+Y7PGYFAP3_Qx2ti#~*2v^P}ssEBhLKS++bWrDy&<oc{p5B}hCmrK<k`$DDtR
zmCqZSllQJ9IrTKxc^rK5F{A5q5A3UH%yg@vX;BbOtONb#%}e%8Dlg%)Q}4}k9Zqwa
z7y?iAsd$;O{{UvwPR*T&xYHr~v)icu0A&R<>pFZrE_3d&@mziv&~ZQuo^et2iJcM4
zDK4j2{vojb{GWo<P2wvx8-mWm+PRPxl!5J1>q(j{zJbs;h^<aG+PU{8qW=JdmNIy=
z<J7fbZ4?p56&})k%@zX>*xWuRkbTQY$JEmgiLXC~7+2|7v~=c|JfBl#gTt<dt9XX}
z`ZBN4YBtvOCLinepJ7?qJw-1jmo$r5dJCa#wLL+xo4F6<Dl>g{-EOA;0KTdWH8?5t
zrmo4U3Q*`g&v480O(7obQJEMoF4*<WJdhf!*xXv$7J01%?0RnLOi|@=x`}hcF?pJa
zR*3BwY>|xhuT72x3b_Cb3iHbiap%<*F#^R18N%0nZFT0tHvwI=-QaxwJvCbFur@Co
zQj_xV0j7eaeb6YzSB|x32@^hhepJy;an_MXY?@#w&MA*3)6+jnSsP+iZN!|=1Dbaq
z^2pN!(h`4kN4cp3A4*fwfCOUQMlnrt0r#PqvGV4tP3E^jKnWw@;Nq)HL0r-_Qx@r(
z8s1{05sE`8w1GJ9Q9R?OY44}XPY!+ZGfg^tndV}D3PUN}uHlucrVY`Nj!%46r`Sm9
z?0vCL`xXe~oK#q(&S2PFiAEJqx%94|O0a0rS=4X#s}WiSVaMWYLKMYP6J+qN#j8p8
zd8lJfc&i{2R3XX8r~4i$n+Z9k*~eO99#iGcaZTs(r7e}mYEHBY<0fsOY+U_mU}xKx
z<Jz6ZIi~`lc%TI*JY?}oIS2aFGm2=Cf#2ysiOA1-TmW-Wq}g6U{Hb?j&;+<#{pww+
zKZ>IRJmgWHMrau$w?HXbH%HAfPE$2H4bb}6%x6l{Ozy*MW!*q=yV9#$u@YnX)}_eZ
z6DjXmfpIQHc<|KgH7tNESM;lc<YQTu(s_3ZbJwkDN=TDG!;aO3MQMy|k`2J~Qb=;E
zj%u@<jyb7`-54W^OhQuAcTgMBkP3$qROF4_>aK9$)a2v}8UjJql=JCPhWb+O^`r%P
z7Y;xMv+h&(hZUi5G9<e*&#hFPfZKrUTShHzA+VAYX{%67Baax%RcLu{YChv*Ij+S{
zGxu2~rIm^A^r>NTNflWRK*xHLCjIBNan33-aTz-?%^*GLAMaCh{{ZW(+8FZL9@OM)
zk6MrV(3uW-qQV||Ju0>0X5Fwmb*m&`(_C@WJXW-wqz8+5x-TzROk@V#{W1Cq=h)=e
zYvX%QF6keq&B;H@^R6k7_OH|Ma^|5Hc@>qW#%=)9_x!)skV5R-4z)T!$AiUmnGj@^
z_oWAle35M&FsMg*1V6PMJJUeTDdX{~5b)g6^!KQNH1KFZE`6vXkTz-AtrHN;cBCNt
z(}|{@l$aqDaZbS^gy+3H3RVMKLJrL;sA6-*1y$5yFy6Rtyn2eipk0`5yolpJFv((S
z4R|;9j^q4F4QCA|(2U>5G=$K26ol5p9nY?54FK?cXeWwd5`oKcNKGi~){B7V;0k7G
z&T=u*qcv9oMPr&*U}_+7N=YJ<U`cGK@)eWtspo^sbBtr!sH+t@9cozJnfYwzv8Vyq
z=93hy_lHVpCp6OlZrPw5nrS>{oDMmv0Z%mAQN<xNTm|n=Q^iM|9x2Lm^`hVvJXbE9
zZsMR}_)-IdNDDGd803Iz2@c=@>E4=KBQ+a0ILXatA&x7GP;t_eJC`}8=Lf9_WT2l~
zGtDBYW7tr~9C!7qxU4(yrtbHo1mc><nl2U|8=6qVH5by992`<?W!rf|Oq}&S>(jJp
zJk2^Y$UAGwqHV4T=sB-U@Z75|pTXpc`936%xfvdoUhN|DaM+|BX<XsYw|Z`W3i&hI
zBq_9VK&H}lq#t^KxG-Mz%Xo?Ai2;sQQg{RsE2txbT(^m1F9tzBD`vgyfkomiBZnN?
zrJ>K6u2_Grlpg2IKjTrnvmEAWdH(=x(;1Y19w`ebAAEjw_tB?GbVts)&$y(yZN^DH
zyN?uyap%pD=hck`hp7DNyVv{Gf4f4w#lS7N^NyUFUWXu@{b@I-95?ApkC@~f{V8+O
zLigAX_&=2)>(EoSu^c00bu{q=tiuq=`BL`umsCDUzJy?4amS?%$mEi0(6hN5h#dVX
z!%n|)HrdKYt}1@FL4Bk@V^Q=eW|t!sbZGjC0~T_94h21QEl~6JHva&=g-6%0%k824
zUa#_*_~MVln!ef=sG~1v!F_iR@v1DP9g)<lslf)iDPk$rSA)3|r#O5_G0h;QG#_kM
zj!AB2E(zxp^kW+-Oy@iwdb4Gw-0BU8up`b3j&WUvnV{QPC?ts_>ymr@E5OXNoIM2M
zz3Cp769ZChOJr5h(^Y&t#g;z7xzFoe7|uC4G=V_vflHqC@ED5T+M}JUeHA!zM#6)N
z2PTZs-nokueQ4t}qnvTllLIsemL37FGsN(O)fKQ$%h$Dbkp1ir(z#C-04`!9xUa3@
zYL=-eo;GU>z{j>cnwY5~t6H9LYT)<h>tCWnW8|l#h@50`Rb&`qJJrYMnyDzm(ITQV
z7#aRm1f6k{Qxj0ic?Pj&$ZmP0KgyJKr0>?CqDX%ASjWnGRdgRWUMj%(m(w+@HZz{&
z(2=_pGYo(#v}X<0tz&5wx-gdHE)N2$w_a+@pU$ekTA3FS2PT-q2ac5RFe$Cpvu1;P
z`_YOqOY}827^rbmgY~EvIH{D1sF5OA@w?WhZ@cuUQ2g1ck18u<V#r&jYP)bcb*l_B
z=~dWfrbdwv{do4M+m7_`G18jjwPei@+~$n)?MN^>QP9#EA`F~Vz|<?)_7x~6gNmd?
zi4b$vrXcZ9A?B=O3UOK^CPMsrRdxe4Wyci(;-#8IZaJnmYI*5QV_CCQGrccLLB%@*
zG=@EX{Z5!}arxDCKQ&IR$I_V$vu?$1p~eUA7x~wz>HOI!<A5{nYszCI&Q9Ml^Z3`Q
zX$SoQ26L6Kg5t<)7JFG^(V|&LALCUI2iR5FhE}OC!LN!(u6em_^E+hay?aux-v0m^
zjy5Em)Qi+t-JelUU}~_3<s4KG?Ng`R6de%|uWl>WJ{`uZV$4$nam{&A$OW<QUajCr
zB$q&ME0W#8tEai==D)yaUNviDcrA-A=IM`GyDZV$M$*jT5qgtc_K%@5-kZyW+T(+o
z=q~J{ynw?uD0^1t#>h))p}2%g3kF8+D=S*nUe6K654i%iZ0usQfI|xHMXL8&G&ffZ
zEAj_b^`JvEtBEeGQRa_p_xGqL)t)U?EY{jbR>oWo1#6^93}65iRCcK2mKmigjHTD8
z??4ToazN~zK;pSOWWBuAyv@V}Z0}x`+P2hOwgC628LjQ@-en*v^O{A&S7Vy-UZo;g
zn@Dlyu=$AXUP-Ay_VXVx)Vp)Lxvjqt_?GSUsUA0tqx+>jKN{ulF5coz%t5YcyR+*u
z%r#0@(?YbZxwej!s--|Qs+eum<Ifc*zJwh1r3WWG&=mCSY1jaDpkgrt=}jl*z@WB8
zF^(}n0c@ISAoZkUO=F&E64(=t^n>Q?e+oiDq$l2xhjySIdQ&%ZO0D@(a3vjmsmgic
zqYaGH)bUJZkjH4+aqcU*@T9_cOl-lM9DWtRspr2H()d>E$<zQ};~@V4O1PeOXG_{p
zW~Yp8-gsh(I<sT^{&na2mWz9BBCEfer=dQT-T3<ASTyl0EJH2|5$l@aqVW`$>XFPB
za*XHJw}J4oRtW4bl}6Ff*0d2wa?imWAFW9R?o@4Iij*<NJ$bKN1iG9!htQ4CmIZmo
zT-7_6jIqg{n|Q0OIE^qtC5=~^)@9g-<yAR7>(Dt2{{RJBvDRc<eb&u-EWhi9Fbg+&
z^REp{HJ6AOqO&XKApZa{UW0OTc?b?qaw!un$=WUYfh6FncB-Hv!!bPxJk*PM7`&T)
zckRYKYMi$beU00vJxwA@Hx_}k$kZ<F&b*GjYQ6Q6Ez|*53>UAhBsbfh&NO_kMo+bA
zvU$3W;mWATJt>U9xP(2^j^KV3ks=jUah_|gSP+Yuwu6oZXI*Kl_Be-f^upocxv_6_
zj85Ql&2HLUq?$vaIoRA*1(YVn@>u@>yqyhP({CdX+(dK6agk8UHusq<A-ErT8)>29
z3wW*o*&@{qHsH;qO&MSc9%|}I_Kh+rMgytG9+ZhPKE<-`>Lwjjk($9<Y}s7Kppd5n
zHP~FPCWhe-Rn+AB)-ysD^6E3Y56G)ph0aQAB|3YB7~9^k?=2oXaW2qDQ;yZxBuZ_k
zN6s->az*B8@^-~H6G+JAOSDoc85OaoEY}0~c=>rFHD312Nox~~1`WxnbpHT0&5K2h
zH(b<g%X*`F4Lb$A!NxjPtU67xXtJA!9cwni{^!dkNSA3JF+b9-zP6j9ju^@32Q_9l
zHZ857x1QiegK-!puG?hUIp>EJm!(TR%-23(RQ@GCwWVey7B>Xo;j%H<R7eXV-Z^f9
z%z?pP39KDc!`9Ns?uZrhl^q3dqa47@FmZ$VR5!Q}k6aqgQBvH}H6<O7JG#;?Vw9jv
zx#R^Mt1jlw?k2;)M()|KM!8S)lHc7Nn##Q%bn%h^!Qj^|Oe8GYI_Y91C(3#IK=~W6
zE35FFeq0AVPtE$)oz9PCe7xaU3<FD~>0?g}o55a-$3b3FlIF4K&Yvnapi=W~J$>t=
zw;N&r^{gue-7af>5K4k-%uA4r^{H5M=}|^;#Y#CefRZuIPPGymloBz`F$#WKjo;<q
z(vW1}aZt>nF-QebmK@dOW3XV>Kbk{~3|5pf29B5sIVK0=BL_9+7hwIWPX7QguS&dj
zOKBK&0=(j41;n20de${gtS;jr>&<G~4bAlLS<#W6m7{I)BRKS|V6M)}va}l@x|B7;
zRY?y#b53>z*yIyc-MQ;sM~e3uGms5sT)Q#PPpxT8PTc;Ln>ifktpY_R`_(i|M;)rG
zwq)(~spD~q0GXQywG70L4k|7A&T1BzsTnxU04q*bTBj}PSxzuVxu#u8QNv_l)f<Tc
zk8m^rsSVLt2hD{%;Ck0Z75E^0z@GT75*wo#+Ik+9trgeGIUIAELpry++;Vu&rB{|f
z%10HK9oxEqUp=!^d7FUwsfdc`7Wus^In?u7ZbNi6N>RxjO#(Vi0_6RX4_00cby3^~
zM1F+VpXe71vP~OwCxcy{p3caFu5u^?qlmPej@3L_2W~2rqm%$=2CqjpIPX9f6)<`0
zK^t>}`O=5T$m>o~xb>iAX$ln}<Ji`G$Z_)4tkExSJ?f09wX>7?PzG$ONy(^NrCXow
z`c-BFX~rl5EasCO(=qd$98`b?7#KApCWN5sYSc~xjPaV!3dtZns@!22IWz&U8QN;}
zGUa|{{HrP^Ayg06uR>Y9sez(Y6v*#Yrd`Q`Gwo7AC-9R`kpW&gGy#nyOb!65%@IAZ
zj@7Qwl6@*ER1t~*z_?uexa-AaUB>IqG6!5&O*|^CpI=(exVQNmjwu1lT#OuJ6;P`w
z&TCffHxfNMR$=)L59dG=ME?Lb52am#O`{p+vqJ#GH9T_Qa55>9Zo@X<H-2@aZ7YTV
zoU2wHyrH(0IUU7pTOL5paoT~J_VM7bW7nlJPzPQGIyVOjMI`%7WqZ;CBKF}BsLpqG
zr&(QwQO<a*T}t6(zF?;T2HLY}BNS4-k2J0aPiTL6^{ZrH<W_x)=LA*I`%lflG{#LE
zWMK56*P2+_e9U&KT|3hPAiIF77fH2Sj`gArI@No{-)_epJJ*++Qudf>Bz0jW%TXBT
zr6J~y=99gA8T1GbT3pf8QVu8>IRIpyE6n^)bM~D`W1{eDz16OM&1CQTSC?GOZY~}|
z-D~f-F9&(c5d9AiI;&_X8{P`G-+eUr<#;B&0c()(InA5lfo;biS711=D~l?*<J@0E
zuPlcy9w#H?P9Tkd8-d1gT<3?RDX&6CK*6q~#)CF$%jzqW(VPA!miRpLUssX7e3_@&
zo>ntVbbd#wFC#SIeQAh(P%%%h%jzphpG+@m0mTB0RzN3FS$-m2`W)c@0Cd)=sv68j
zeIj_rIa9@SVcn|7)QX=AJhIkN6lhfZ!#yiz4KiIwpF4DHys14+T=0&L_crb3LmTWp
zN#?dLt?_WktF@D`HTMwS=g&=QU_omoq|YAgfO^**;+w{})KyqyBVc=1RVBoN_0`D2
z=O^B{eOb3^lOL^iz=8U6ganWX?oD)hUA&7n{fo7a<}04FT(21GT`rk)cdR%W1Fckw
zM^30so9CRZakti?@0rL49Adjjj%<iH{41BeoI`#|P*n3%5F(1$ss;)H_Nx)wy9U}S
z)w>Ikkfa{<qAhktTNoIt5yrzCjaWu7OCCL|xYKmcD2K+=*Cw*GeH=ckCBuSITjeBI
zTa{D&D><^#D{2viw>w8Qmk~!BPB|5?cER8~jdJZdie?$W&&oY2QA4k7+BVNs_NtcP
zi-XwXzol)%c@4yS9ED~5Y6+46cd6#CJBgPp8*R*A?+Ww?74-$$7y<?`YtHoM&CEkT
z#a)y$n|AqRAl6u>m9BMQ<9pcYbj>?tF0(ND3Q4RZk@n+(=~T4+Nu%az8U5;MuAOA_
zKz+X4=As_W$3o`nDH2;)LuE4gIRUsT4;9hJ_f%IKcXcC5vRk_;1RNhq>mZ$DvstEa
z09=z-2}L_2DzTHZWS6&*X|_*sFBlmW;+`t;18Va~?ej((0A{v)W8$aO?i$+GO|Y*F
zf2DEWK$&&{fKN)AmAN%XeH;a-xyy4kLr%m-g^yeTnx5BFlGAi)BC7+86J4)|bSUA8
z%Pv`$xUVenrKj0^MKcA!CxcjEvtMsj(mcx8bro}Rd+8_Y!|Ey(cVAlMEw1j+kR@zl
zrcV*w#Qy*~BdFl#t$W<9M(rFuPTDKHCtat~klr(}SLe{zH*4YuX3pra2UAyK)+`-?
z6R0P#?NZ<uXLq3Lw-%D_i($`W#dHtjElL94A_2}j*PBCsumcRChg^eNcDms5$hiTs
zde&~5A2U6V!@8V$t&~qDqqcS&g*^>u>$*+N#*aF#p&`ni7z`ddSBHJB85}*m!@%p)
zX{(d?yI!<~t^WYDJmkmmFCw#a-$Im)&jXf=#g867@*JG~Kl;_J<2w^`u0%m0cJgb1
z(tKFjUaFUm8oTlttE1FBZ)d8m{$p%?{-9QTl0|bGc6!J5D0D)^FvAVi<sL7+YyDnn
zx~V<uuWN{IRQY!bN%yW7Tt|-JyCV?9pOtf2xU;_k<Ik%xf!bJ~O7*XYjt+pmGhR`;
zHdBH#iuA7ml6*h3A6}nYx(d=dGd1oj9mKONaW?l=1bWw(>NYnCtx0td4+D1wwJu&q
zmC(63W5=Z`AuzRcv%@TD4T%Bm)~Wd76_ZQff^a)j)+}SVz~en?--uvajUAh*Rip=w
zsoHw-Ju6nqWoAP*N@tqHX*N3sY@G3dT6%4Ut91E>)P(-@zbL3|(lNQ!%W0-w#sENv
z*QH@k;TgBH+gt}7m4#@-px;Eh=D9_{<yV@0yz{L7Slr&e)sve?bZN#*W0t(qbt^&p
z+fvKiq0MHu2ONSs8uZ4wDxW%nJq>bN&DFf~{IMdi<2~x(K4Th`6g9ceka6ok1oRbc
zodElzH5dhsdsc@z4#Le(7Uwx`l{$bqJ*gf{&;n&qZ~zq>Hh=omjNX*e+)@D;^`;Y=
zQgigCb)W;i1W+jnz@z|36w-L3y*C`t0pFT%q^0dZ4hEN@`qO^2;CQAN3Oe_qiU3;J
z@Z)W~DtQN-RxmZAqA^`fap{T#&ek~cYW=Uu!mA)4)w^V3;8P)u@eB(3a~yCvIP|Uz
z4mbk6D_4c2(j0I`-gD_*ZdYp+;Nyz*Fpu3ZnAG9D>S66rkG)e41$q!>3^F_Qrm)Or
zpUyK#+$qVbdkGZ4{{SYHavF~O&;}a0x|?(@sXIp}@TUV!QHA!U9`&+j3|_PjX$c+a
zGCQyzQ%>S0QHq&QwN?@@_lM_B^8*op$LO?NR%NV;LI4#Cmu^-$4u9A+Foxle7SkW1
z8hpr3A{<m~Fe=*V_ws$)Nk8CRQ~v<5^*00k4<A<)ok;fu7G|7-OVn1c_8y{o!5aSn
zy(K611@?I`FZ>HNo2v!X(lC?gWR@e0(iU!im1`Xab^FpG{{VDRABT*MgK)$C0Ba|S
zhw~aLQhf|^=NS}*y>s|iM7|YMo!3%l&?YE87mGOaCS&W2R&NzebuCbzW12a~6&WOT
zIIg*TD{Y*4Q%HT}snf!igZ^RVkG!U{mMRQ>$@NDF?mxUSQA;Y6<$<qDkHYq<ylHWa
z_br-`_+9~xmKLCA_>(n-O3{+Bq+-$KAg8bCQ$}#Ws>z>FroCD}5BW`%h7s$wDzz4q
zAmbSK*ejhhnWgS|TrtftKe?Fy0Kg4fi%h<hWi2H>#c}-W)CQM081oN4fK;POa(Q<A
z>!o6?(8bcfQ_W-W_NON+YJP=)tBK)FMY(9u4&OC;9C|9a%Qzm!oOFn>g3F43T$f>c
z4>N;L2~5B1C5>~`W~N^Zz&U$}$I`ojrNTdpihtN`lyX2mpi%Y7_77mYoMLDe2thM}
zk3=<PY%LXVw-R7~auZ!*+uDJi57v>|(lNB{B>Pr1E6$>{jUi4j*yZEXZIqHt!{_~g
zwN~fD)^`$@cy4*@Ulr7bgti&D&q}zq@iL4KJu4LCwq=|!@P3-$7O`@F+LY7N!Mb7`
z{{Uwv{0c&AybvxrQkYXX+e4FMIG^}MwAIEm_!N%ib5<8av_Zr$FSw4n)`BuV=%~%K
zP5dIJz;lVBsb7=JQ`-@WfA(F;k83_ucM1Wng=19U0g9I++Y|xJ$EBulRzgR8)T2+B
zF;up8Ush`Am6Na^l`co7D6p<_k7F_%3ot(#jcp1O=0=D;xvsIow^bjFMdYA7AU|3x
z7dg>sY(_+{^u<jDjk59?*!?qGq9p^BAC)~+1Hyq$z)^zAJY<GHQHrv*k>eez!h^ds
zr;d711RrFKe+@@*0{xxU7pSX6fu=DGq#8|VRX>RyORBq#LUFmUAEED52+7F+{uQsU
zM6v3#Z5ST4lvf<rpDoX?rx<c3M~riT4FL1dXV_EQ891h3d(<;%@_{GXl%6RF_oAfJ
zK}f*s#U(o<6vN4&69Y-!m!%~I06bFC9+Y&X1A_rh55-1LG-jBYF8T{(R9W_=%{!2(
zM)wyd(vvx(G?ZK&7~bONJ*cFkwJVR=raL&|jnv%IQ|2MjB+sFs9Mp8ZsJMF}`J<_(
z206_cr*d5~Y_B4KDlOo4r+KvQjJYMz5(UBHl$;K=7npNRENSxz(ww&yn>3q<q|G1F
zp|hei(nY;Jh}2;|rxogUVEvXe{>^zsi*3KQ?emKDt3m#YAN#f4ht?<0X0f$YP673&
zq04>hW;ykw+6Sd?W63Rx27EgZs(a?5nIVa`A>EFqkjo)Wo6bEdyM`I#ngCY{=N&1Y
zPy@9hm*XH*z?^YF$hP1CNrEa<Olky2jME%rp{Y)4CdutU#sUE5hG9y|L8cYR<j?~c
zWYY{-sltvhDIGxoKS990;8Gb_AOkoVr};`(r40*~;j#3leU?&kXE^i}fRQ4=^{Xit
zZ1GXY7>}zH^{J9&27oN8qNo6KOOAahsVWhUGfv(!#ZZOM6a({93yM%l?LZFQK<A18
z?MgWOXb^;RPf_#~%o9#kEszH^0OGWpGwDVc0iH;w4t*%N3A6*#G#q+TnoYShTm%dc
z)|?m-nnJkuq{R$locyM&MBv-G1E*T0CgKUsK9yq8w?fL@5Av^{&LMRcc40<0&Wv%4
zR&x-nezhms{Hy1Tw&gvlDG2j_-ZkSo5~nYC>rUgt@~1oln%0_SXwwbavy#|_-BT4I
zdscN}&8itOY^HIVmNS?|LJm@-gz!ddnT&9wwI+F^IqgUUbKey)IZ;qQ-9D8f9LG!t
z15VFsj2?Q@=dC590~1_#7g3n=l{w<AGj6t752rOf^~yqvy?FJ-E3!*$9eeh#Mx^<n
z8>2p?HqZFflMkEHtHN<G8S7SMUEaTiXBk<Ii3?zn`qbdzv&B|k4^Ap<@C{*C<G9gf
z&osi^Q;EnF+RO(Go_MCKVa91kN@>WDdQt**z^I;31_eFA$4rb=4I8#_r|DH4z~Fpx
zq@XzHcVf5)KQSN9y&uLf5pGV>PY3x|n-V(u*XcP#`S7tkyh^mkBNZporVM2*>s7Ok
z^*y=ykFe=psmwNCySKem#t&M%FF%j1RAGjwu!J<Hr2uh544Pme>rSTkpmE-S90pB0
zX&uchWCA<Wor6^&5%eCk)7F&nO(zvVIR;HkMg>BI@9R^y+@u8d7cyGjM$3X3utBXK
z5FjE64<s>Ce+tEj{`x+c+$*EkS2|)j#zD_DoV1byoW~r~Nau=C&(ed^v;nlZ<20DX
zDdvE%hw`LT?MvF5k4gZL{KA;S2R*67g{G69)WA%8;)c#WMFO5wu<6o(A{6Mz-afR`
z`HE0*b5aEEF@sUK^))n$`=RUBtGVN@X#jES&%HTvO)wriQm!hK0p$DBN!)tSNzZCd
zw7@%xa*<3p#%T2BfF&mxsLOYxEPd&@rEnZiG{!im9G|5$@leJ}gDX*$!y1wj2{e*@
z<3J4FeR-pIsiu%<rE!l2l>I5Aic_CjcK{>~lmo}5Aw1)X2TDu_p&PmB?Ou=JM$MSP
z=Ny1*&DR*N<H3{ejAyPZ=X3bq4|BH$?K7y8{b8mP%|2Xtr`DO)zA*Pi&J8ATXeTt<
zU?@EERc>r8?*9PRuJP%bwUe3w8R=R=q@eE?VK}FwGsc6asN&!9V^112hIqD5#;){U
zn56{vt$w#(`QP40v8Vi{QKeXe{{SA*{#7s7EYyFfj{~MfPmp_2Qt>sO@_%_=&K-zF
zrLgG)fA`3zED<UBV?qA_0jWka)Ot{AU22c*G4e;S!5R)WFa7gQ3ZwW}@}QHRw4icp
zH#t6|vJ8RQe=0NWOMyv_eJXjFSU(C53mmODdS-w*JkiV+D_nwLZKH3!dG-3@{!TJa
zTJ%|lV>^8-n3qA4`uMY~k;VT2Jv%jhMn{;^!qb<vXPb`0O0Bt0ZYW-P5g|?P-*rK*
zmrL-@aV_W`$T+R*9WK(w6-d{12UE{AcRjIzSY{dhYWIaNb|b^(@TaV`WN|?p5s2bY
zsyb8fI#TnFd8E!dSI;>)YR^e4Y&$#(Pr{6fKMIkGDROwG=M=f(fEPJE=*iC%nWJ?p
z2(bY9tDEtBT*Tgo70|@zHI3rmp3omhucP6qTNKgd=8N}7CkG8zNi{+bm8$Pm$*<F?
z>l5Q@d_!b76;@6ftvSv)s<L(UrotmVYAFUsYL`4yB>Gk|Hbf((9jQ9fk9vba$-x|R
z>sHh54u1-!xZDL<Q^tQv(gt%SLJI*_x!Y9}s5NLDuThHK7)XigyAHXl5>yZAQzD`>
zjEZY;bL&qW(_5uv%}~lr(o?aYts#mCClxY``cx~%DpeWv#W;~7LDsB~yMa}ZWQwu}
z%UdHE5k4?RGHSb=995|}9Mx$Lekn+(k%3HZ^!^IcF|66DBmF6O%^Bi>Qc&THk6M{W
z9<>O?OuZ_R3~~$_vd03e1Nv2kY_2%15tA6_k9w@#b5>;My+FeUz9~q!k)E{H7!>o?
znBKy(HA6a|N`HKsZ+}`)aC=f1<*C!AI@NG{ikS{Y1hQrO>5>54E7Wu;1L^S|`v!CE
zn)1e0+Su!ifNRq{Hv8-&Ozthsd}kHM_i9J2mOWZD=j0zsqT}cK)#<ubMj3No0*`F-
zIDi4Ur>Myl6df^+I`dPmJj_?zpHoj^9Zus@LVAj0FJ9u20aNWkzQv|eRDefJjMuDq
zLsWvpMO=bOJrriVmNU76=K;IdwD=U*K9dw6MrBd@)|B@=+}-}*>!NQm5hmPZXBCHW
zd3AHBtS}>mR^*P=(Ey5^oDX_rQNy^rU~}A7=f|;BIEU_y;C{7A$#0F^jdOt?@G8{T
znv7O)lE$57c(+gq0L20#)e>`Uh;x#9ii1be-qnn=HtAcBpsO<KkR{UFa$UOtR%V;Z
zh_D%;2=6Q-y^Kcf@{Vu~aNaf4zq9Px&IvMDbO)Ndt$2oeM0Zb>m+te{yt7r-Wz=pw
z`2h}l7OZMZq3z{(DNcOy*r9bc=?`<?6<=uUNxv=6G~>t>iS`jzRzOWO4AS?f0tb2v
z5PQ>D^PgH$`KZ~6??AwjO((4(JbTkfIp&a<XFcf;CW3k5j`^fW)9H?t8EmgwbcX{V
z)n<?{6dB5PB?lza!*f-U^WLUYnh8_6IvvLqD)#rN6yl`^f!FIy)iPL*O4ZTi*{H{!
za>M!7Ong<#88%(VjAwAFMmUAdO{1vzfzFH@wg(mC@Ue-P{hSUf*8FEG&7or;{Jks4
zv5b;ycy4?JRcSPJdS&UI#9%J`{n6=N405qJWFrE(4-KhpL!JiQ=hnLRlVHge?qJoS
zbIHU%c#3pc9C3iXYd&ZlV|G@??f|K-u9_$_vvFh4Rev$1l~vSjUU6M!1^XyI#UI)q
z13mlJ=8-7WbwqH)l^j<ksp?NU`3MdhxUP@k{j{xdAz}A=RJIm1uC%+0jY4@M4fk=t
ztQkD<X*4erjjTpZcluS}X1a}|A>(d+>nh+a-kWmE4tF_Rky51jtWAz$36?jE^Tlge
zUx6g~;IQeQwU={i<i`^LF`b|T)|mj=B&RsY&oy9lA8J^%r*hl3HgV`Gt@f=1OK*dp
zVO-74)XieZvNq7!z%`X|bs@L;xW`&UNa(J0M3+}r3>Pbm`&F$rbdu^+BofQlHOI+u
zosLf)wJ5rHuGN-854A~rr)yy&M%OX!+&SW}>635MCqs}yt|r%6xV5}>avfT)>AoS^
zEy_z63VH>gPA6X!k0yqU!0wH^dR2SDhKA&1h5<;;W@-BMxw4)Ybq&-h?N^p)uC!3d
z*(llI)uv|RXH6PIc=3^)>UQJOvKk^5;xo%u{ro5ez1p`dHWBSvw<;sP-_c|oR)CIn
zR1IiT1B!~!VNd{YIIRN?$>xVW25P0A@EHdrcB!#xn(@OVqhjPHJJr~%;I>#p47Ned
zQ?#DuB^!dU_pLR)f#!jvQNbW)f(te`AMr7jeN#BCEiO+s*77yy2B=v)CsdH_0a<#V
zUMlXJGOX8tV+0e&<5|eGS$vClB>o)KH|>drJAqCP=E^On<lT@nP)<L6&NGTaC|^6g
zGGm5rGgT$p(64>Ctrt~j$Uj=knl=&2z~EL@z6NiH_|Y6~gPieKBa|@f(y#>PB??cq
zUbK;)C0nh0{Wb3%<yY>VR+O9uJ<V?>I)0Urrbn_7k?)$;Kuv6Nlc~t$RfQe-s3QkH
z)nx$+4IvLvfGR*Y3S#x7mf;X}=9m(*>>O1qle{08=AI=7q0LsEj_xr?2p@8q(zPVT
zS?)4A8oOrr810H+Pj&&Zmp|RFGP!I_bB^`tw^{ofr~QLoUw4sk{{Zh3SXMf)+mDJv
zky>jnmu7nw6_;#sM^RU9n-GN+6qcsAsah5)oHlAQFby=Z#xqH{=LFY5<q%HXbKbMA
z2sL_Q6|hfg&YPT`)D0C64^u^g4tiBbd^JxKg1m7+$s2=;tv4(?)UP2v_^2drl#V|d
z0Hb&FL~&FR@}(H?eQQcg5JAOb%Dz;DjN>`xfEHy0a56pWdnRIs(Rio>h60ur@}vcN
zPzI9SD!<?4cB@wRJoWhxtz*c!B<BQE7HK2kAL~FJ5R@?B(;3MXj<=+dyCWTH%HAt?
zq$5JkZz|**e5CVTm7UQZSO?r1^YJ(z#a(8Rbe9&f$-B2&E*3irdE{(1bM&paO0wa)
z`qw#OIAzBbxe45&fU&Oz6?o=?aNG{H1OSX+@mDqyv;h>0zA#5xr0iEa#}%OEm2rxz
zI)+n`ObppTe2i66fMgL@9SJ=uCPVE&8S+P;m{dv%)#m{_XX#anFF2_f#CACZ^r;k_
z^Tjnz)~7ob_M`>qCVVfoYC|sUb*^z9MRnv6>01y;HV$xUfu|c}<Go&t@H?8!jkw%;
z)%e?i+JF{SAe?kHQdo}Mj%!7LWXF20$$|YTftM<hF^Z=u;Yym*nSNY?DvZgxCOzl_
znY@Fq999(Rwfga0ZPa;;{VSZhh#?^TMF3C$78PO<xBMy+R5d7@BhrwIvCXxCQH*}I
zt7~}M#yc9oNqXnjw5=Zw8$4owI(uu6K0N2YIH+|CkpdTHBWUUCQQ1BeW4>!I#aC?#
zEGzfh3;0k5NteyIW?_uCPfFLb^d6OiZZdFB=UcYPuw<UKBRWku1st6Btp`<ncC76%
zZaa@cIISK7XRS~UMe@(JScvZ6ny#mJ8O2VEwR+G5aviUaT8;A2vU=3At8U#)_wQ3U
z^F^jq9i?*?McVAXl^Lsd!)*D-TB>^2=Xk1K%Cw+;B`I@3F+0-HNNbqXr>WWfw#niL
zYY~d`4MNUaD}xiS<BIjZn5>O+MUPW~nLrZ`gjdw?=5_TNp3bMiBhJh)e%=>bqmJ;F
zryYi(&`R4@Zd9LI^kpE|k=)x)XLhJl_mQ|^kF9!!mm^Q7#LdsjIj>8Lu+*lZi>Ce~
z463A*T`BZ2yks+{8sV*H`z`Df?atQ0uJgs?I$8O#gI;>zj=g)=xx$fC%eh~f=jPII
z#3>`z>@V%_t)r3|RktYMRkOjxc=fgQ&4jBYGLRRIy{pvptD|{i6vXn#2?D-Ph;kQz
ze%cQ4Z1yl1)rgI{qWvAH9VqQzCVBykiiYTJwUGyLQ+oPSB*=}wt!Yi#Ns~W>;B0PY
zv6^2ZZH!p_zO|vHJ>|}#?RJHC^gWF?N3^$Z5XhHmJgkkR*I%r`Yi%qK4%H;%j`jCc
zY|-FNYI&}&0kqUEQAfy5@6Nb8gPVtO*LU@=Lh);Pcd{|`;=J|7`9VD8hHKD<#%$cT
zfGAu5eQQ%jP;S_JW~j)m3`#n2$f>k>gjcN3ox4UVp1^idoI=WLlhjjv_#9((boS4_
zGQ*{FxA`|p-S=@(0A~G#uplrP&1$>=K*hRrsI=IyiNB@=Sk;_c+jqgO7?GW5<z{tW
zF;~lDENdFhaArGBYTVNo!h?ZWOLIgQ6Ewtx=CZD=TWKP;B8)2YP+d%@Hh>KXXDKwT
z6O<%^DXV=jZK3yP)~{+d!e!lz9+?$^_IZ|26}bn$dZZ?HI%UYWo;jRkFKX(bzqY&$
zBuC~PFs?Gp?tljCSM)ux+}tMMo4QouVa*e#2<>)uv0W||KJV7G<C=ST@=7wFdh@I6
zYxv=i$#=Ohan33Y2UM2!IW6S9`D6KZ?)$aRPM;#VrAhN0#;bS`d9jcjb_X@hTzJP(
zxwCj2h0hrj$t8x;C-W}1j9_jx&NTbUD!}{FZ&T91QH@WCnPl9=oaFT;u4$4gU8!zB
zH9#EG{NE-va(Gdkik7*()_V2gy^~1v-5&17;ryuF2{HE#d4I%hH_O!ImB7bpg4@Iw
zhV=|SVZ)3Ny{lWrqT>5Y^XEbv9mPf(g$fnZj_1hNa&c#x#-tyuXUe#hzO}5W?^LIY
z6OmtOI%-fz@)Wfa-7tsgRUJrn7|15HA{aFZi}#1$nwpev1d&QaYSTdwDCKZ!Xmy*|
zo0&JS_eiCce{@HBs*&XLT-9h<q>4=2i(hnAGbVj;TNXYd)8^c=xej>4cdkx!%p7$U
zUKGoN>CH__4NH{;&cw?Ugfd8^dzyI4k80!YLo9=7AOXc((=IMd!CF=*4@2Iwl_@E5
zlyuQZ=)-Gm^sO6BL`N>$fUJj%);tq#Y-2p)wB*w+qqi4QAy~SDToT1njJag&YwYH=
zMfvPBtCb`{8#lLF((vuwwwZ3$;x-A`*E1O-gltv&X<Y`_>H5}@oF1u)PHkF7%;jF`
z*?A0dD#}_;V`8yoan`Z7u{j2tcdA_5TAwaL0PR%Sk$qFkZQ0sA>uN-f>qwF~&i32X
z*DqrvnvJk_Qb%*|TNWuIBb5bW?NM=@jjoGnrq3nB(QlV00~y6=rQOZcN9^zwLEjjy
znV|jWn4FS%s9I^Ww;B2h&Be2}m1ssbF;16zG@re=D4lUrF^1ATk(JML-mFR)vKShv
z<VTae8$Pu>jMwWBGc{YSmafCDIIcCxXJhJXv()tDxKH)6D*Fn-eFcXrdH58qDaOY=
zYKl)o9FCOmdR57Edx-h-V{!V`Ng|Rgd7FN<sn2jN#wsQ`6or5vcxUTOGB0-@g&~eP
zrkX=4dY{UZcJI0v{uF>i%_rkht+m5_+j)rf2x;r5-oM?mxIgyH(P3Q`$;CGu)`IAo
zoAk1ipI$0d@XoN`^5#d?$N14;xs{4cR_O4SuH9mdey>sw2I?e@(m=oPDl8W{?v$Z(
zT`KrC;G8|=L+H7y3E-W_okQ!0{{Z^*0m)<Wr2~$&+7ATUC>!r*C)fc}$Kb6zwmj>W
zK7@(}aNy^?10;nXF+BjULSF}Iaq!VIdhU?bt6vXkR?;lVYZm3?7JSm?k8+eG&p%Bg
zQ;=me`<4fx^37;z+CHfT{4z^nG;96mQ;PKj*340b65B4{#-W?U2+8x_L61->eWXhE
z6(2&9S-+O2Yi9$sU$eI9l_IIOy=}<*cR%ckjkWlfrPQzN1s>KVeNwCYCsO)X+pO9l
zAVA;6Ty4+8o6$S@cku;cPb*J<5!&aOE<f+AR1<iP*}vtS&FFWUsAD~!!pi>6t1q%-
zUU*wlvbixYmoUb6hQ%~!I*tZoh=0KAMYa2Kf8)@x1G%O*h)Dakk&ni@Bbr!0v8z6X
zH1PfD`_BUXTQw?pYHobXqyYZ_b#qQWB)B=nykqdHvg<eUK78PV(N>3>NVw#cdXs;`
zB1t6QH@+gN2ZP}qZzm(!DyY`A4j0dEeW}M+)DZsh<z9b`5m^5KX-wby9(FXN@WrHR
zH?_n4PAWz4?SVYR=l$s`3QbD#MnCBi4Ae&E;PPg2ea$DB)b1sczNb*SE}EZu+CRoh
zU$E&3!G_d*PHU7hJ9T1n?@eG2UVgQdvGre5su>(Qv#lT5aF3O(Q|Kr<j-I_Pkbk<B
z$Y6U=00y&o%8#k4$tfeQ{@SoykF>GJ`!v(y3l;u3o9SGi28x%8sQQ|$qJlbh@g=u7
zhF13`qHhvHNBnu@d$n`4cc}LB?r5^SKVx+GjDdx;Kt8n_c#`Y*V1#}Zjh|`-ORYE5
z(Pj8`(AGX8zRy^|^b1kGy{ItaP^Z{dZfMW7E_rt}SV}AGms?lV7-Q`(O*)nHf6L6D
zom8L#NTtro`n@IgPeAZohJ8PCw&nzbn(EYT`9R{h-vT}@q>S|3de>*4di1Ef!1-)^
zd22L<7zFW3ImQJv6X+>Htqu{udH^XH5HU^%(t<@WAv^bWpsODEr}yhhezXihAE7i9
zJ?ZLkPdz>80udNA!v`j(1JaO_ngm9%0BMq1tb`J^I5`yKNDT34p|iAA)Lo*K#tkmg
zxS(UU@koBO1I;J^jz?MmX&)%4%A8c>eiVdK0uq@3fkxgcbpoTBFx(ve6o6{3Jt=5a
zRa{fZ^q>fi6q;w+3bx&usY?B60swLcCV&|vrB@(SD|I1bfydIV?8xSVgFPq$ub%$&
zG>&^3v|||QK~P5mfG9DPbW(pBe#RoM2>Hz^7$9S>6b?I{SK<_8)LVDnVVcM+K(3F*
zF@)5?2L+39T-P|}yxH!3ZXO)e(-WYj#UTWCrR`93+S>*_si&<eITV<rXpmAGTv8E0
z>?TbuB_B#d3NuDBC^P_Kl9xCXou~n5qKW`0qKXC-Qc}<XMIq};KwLY}D5E%}0YRfQ
zQxKF2J?Nl8_|Rye^q?*Tel$_mjOUsJ$sjnnfxRRKy>h_j#wPU@<OJ>7eHe3IucS(3
z)1j{XH^O)sy45pFpzTI8PC%#cQ;AG*T^BquEa7PzpRG9K9qEjH=oq_mnnRI5<ME^3
zi-4Vb(@rT%DDP3cv9Iw0X<Y!l1vHLo7QBQXyid?mPN4v7eB}QCxkb<xfKt5FU{JC~
z!|xh5E`N*bid@Kc6saScXiOg1r!#^$q#5@7O)g|R2GK{9r<{T9O=%ZAZTjvN15XP5
z>7xhz>N${EmP)DP`BXblG0j0HqiU&>a}fUkfmKJ<boKl9$xEFFDYFA1YPbMBF^cBm
z)U0#FvJsx44Om@9Ct$Iei9V=BL&Q^Cv8rvGfMoWk1p}!coo5GP235Zra2Yw+YZs29
zzR_OBMfWH(^N-G=^I>1TCM!I@%ExU~I))np1uLHQKiU*~mFy&K3#)Pbd8HTdrg5Hq
zt1fAoW84Cdpr#2QXkm(%n9>ic$k!KfzeRj|ibHdgg+~0VIc{Yu%Z&Xh!b;B=%bLnr
ztt4O7WLXnAKkAx;B&P&LkF8e>LB`|x)T0d8=O0?edCfJlAJthPYmfQo7#{6Onf(xc
zG~8j9r#LDrC!Ma5E9$;wb{8%&<{-}*6=n!Z!?l|^>S$b4z~EP(ip-sRd#2Rr@)#l{
zi&9WVLleoXmk6r)6kpk~x{hf3cJ-&+M#`z4J5t0{RTO1%qOEepzs(5dowqAdS`x^6
z)qp-zT-xkV#XYI;f2<?cqFx@K8N{{CC1H<l38h|rsB?y<=A;K4kwix-MmZE?ifmth
zZ@n-aPu83X08<-=$4UXD436ytma+rS6_uvl?ni~WBDP#*2<~eN3n{IyT%J_)VP38q
zl6ZMWOwL=P>YPcMwoc^EDx)haXBBET4Hy;3nL=RW=}%r$G}1m(NQdRAtEeL2JEIhs
z;}np#V<Xa(b66BF1k+{X29zFXbGbR7MW`-NC=8=M^=L?vdJ4-`20UVwO8_yNKv3~z
zfVtCOW)A}+@vjh?5}Ss3Qdb@8-L*aKV;~%#TJZf!HiuBSL&;a`>tB1rwRxyG_B{Mz
z)iR#k8k#ICbKauQ6!m|Ye>(akaI#n0TcuQ&@70+B0-%&(g$zh$Xzf7$bu362k>Apg
z$bXKCbFK;ODY&2o1c6J|leHB<1QEqI88qrbGwn<S9dboYf>xq6AkIZ04Ll!UYo@x8
zU1((RTW;=anPct6bb4}`^n!;c<RIpvr$z@pI#HhVF9eTHD60Vv;YNMv???s*Y5)x&
z89tQaG1`#y=|Bp<c97BzJJY&T0fbfiEVMf|<mZ!*YNUF4R`!Uj(K3Y_zokV<a;t%W
z>9Lq&6x^KggI2W|9t(~}6rK%J2L_H{E#$O#HD0HImjiGnp(6y3PV~k!bf+o93TWes
zQ9ur3P5N<8Ve-^@!RDwydFx8N5t>fDMFWw+pao$}@0ybtUX;vIU^j84Cy`FT=9<Hb
zmNCi6>rQdaHZ$!{ZboTb2+vAfccVOYrsuabhCAs<)SYNJ#Q|Y5aYtG@QjWBk3a1_G
zuJClkO|<pr0=XWwx#7!&g6wYNHRR^h-0<$lP8r%~qR)`yJXB=kp0up{kT!A;dT2H9
zmOg<yp+V+@(=>IY=|IH>jP|6Z$20)Brk2Go@}Q2CfH#)yQUmQw0|erop0qKGOPuDD
zIW%WEsR1_RigDtK4_XETj<n&^-kL=K^FW2hMJeP`cBP~O4E-rjJ!tDoj?@6sIHkv5
zT2L`d-hdlNQ%XQ0jC)WqxaO2mON<HtK}vek?WD$dpa70KQ*qXxNsQ1TV>oatp7B(t
z_i4N4Cy|=yK@r5#NOq_lO>r8%=i2WXgKkCPO?`(9VVj()wV~qXwO1!8LNE1$By;In
zBd2Q4jO}1+L358v`}%tyDOYi=!0T1qb5<B;tGU6eWW<Z0sNW=1ne9!Iv5~w=_~Y@T
z9MRLQ9V;_I-3Y5o$jwz=y?WKCxk}QR5+0`*CaoyQs=vopqu~c$ohx)<F^sttU8>7{
z(VDF%Et*UsN7ub0bI0pSI#LnX)=bqA^riQt$318r{pv~-b*Yf?=}`C0N~8Y()M=t*
zN~b2Qpao89s_|B181KQYk%WYC%~f$$m}i`tuO>%sD3IbrX{}B_Tv8FoTFILtEDX|t
z(vXg6dXIXNg&Z|byo!T0G9Gy~NQOKCRtF-h@tU1a;aVd(2yu>T2dUfc@+t@Rp^hw!
zo_MC3b}_&-)Ag*GvLnYQ)YA8*^`sf(^`tRIaw>Eg#X>zlTA2^a)1O)iWQQdmX(5W?
zO?nrD-CIwEhDH+yJ$)<Bi6f_4?tB|A>ktky7^yk;uax4deAsKAmRkMusFYw4)~G)W
zMPHXCjZ>9y)%na%c=FqJ&T-nOTxW`>17<_$MO;zRzUs%+QkI2)GAc90Iam(8#Wm02
zNa);>Bl9RdE7-gPr8n4x+>&JHfW0fmqjIbYk+^iPYWRD6B+*I|Nm{ylo^EY-htTV9
z?V9e*;Sw@#?mZ~6wib5cAmzTbfvk9+?6V{>0$XqdR?VIA-C3;LSxM|`p!pdliu#6^
z_RE!allMpOEoi|SK@y^H6jm4fBuv`TuuEnkd1v;kdbR7@*t@4)w8^ocrWcut?Jm7Y
zsaix4lO{F}xvmRDyS!~k$;yC!Y;p}~_?qT*(cR;dYvZS_OteM9H<Cv!<E=&qxbiLA
z<zC>|p362{o_l7cyttN0*vjWQ<DQjCoH5U8<&(Mg*cwWeH4;@h6#dlzY*X_{^iw1U
zG=SjqQRgE$r3ab|xZ>PXPa~x!;Ydi$Ah;7odFe<<$u$eP9129a5|>f!Q9S6U?{ie=
zc>v*0*0LwMkywIyP;uAAdoy-v!Bc~ude3P_><Y{mhZxDJW00}UI~-ERDw`US5muCp
z)hLfcR#5UyD;;#@p=Db=DpfeDpy$0zt<F2pbwQR<fIRf85jhe9qmX*lH0Kp^0rQVs
z;+hJd3odwuX$FwMwtie!p6>Gi@0#>Ycqr0Y*b+8&t_Ilwl|lMfRWsnRKg4GL0ETU3
zX(e)Sp+Q`BJl9O}h5;C1y=omk-Z(A(Q;dqSDUF*M#?Ios>@xk@JWBrn8B*tIkOkx*
z^s2VV_ZKJor-AQFB;is<4aq;HK@6`B%n`pi2DdUbpwm_f31AqJo@=e}d}S8uZ@Qpu
zT-G(Du}G^Vn|Cn9Shv<v)J+PJvAa<ABUW}6-?`JInT8pTDocfoX-N*;w4<8lV(~05
zrL1n_a6IFot7l(<=e7BUI0v4UlZy)$b*&|S&u<#Xm(Fkna<^8mZKym9gdLs5cJ}(+
zwbrN*xeK(Bky3d!H<wb+Ax8Ag3T<e@$C_H{(@wLaj2?SZL!rF7T+OrYoB(UkEo`h-
zJBbTN^Lo=FwzH2(l|0}~hpu_6=0myXb9i;1O-XQ7!(*O?nRVgW);Jv_0H0d)d2Q@s
z(qoO8TR6^In|_vpJ9Q4e<WQuCc6sF99i1-WDUw}!9+dC+N3LSk3}Ja;+n}!Y`de7_
zD^efj1DsS+>NcZU-Mv7?0eKuvr-!B&_Xx)vXL##VY3Xxo4blKY1Iabi!FOymN!xfE
zmZ?QOynksd$}`73>Ff)cltj-qj7cLP<Y(5aUPy+@8BPITTB@3i5!g!~ni~Y>sL89s
z+G#>^bKG~Q&XD;TZ%}yB<~exz)NVDKpDz3=;|wYbtxXNOah<($+OO%+$9UpoC4%vh
zO-V3uX<XApk=UXxNgR4rl($HPB4rHyNCTm(w(|KXaD%2gRPs)+*@<UBtmoy;HfCkp
ziR9Frd2E4(7mgd6*U_!!X>Ox*Wo~i1ze=+{p|?y+%V>ki9u6_<RIfG1mf9=(Xq(ML
zwp2s+PkM$?qaC#E2iezd^=fIcnp>cmRc@Iz&0qMkXM|nAj*JTAA4(g=kzXQCleBXo
z<PHr@$L!hBHkd`nl+po{j2gt(pnV?M)V}PThCS)}j=cr;nl7T3Z1Jh(dgi(N-Es9h
zHi~Bq-BpcaRi_4x=tag?F)lBRvS4yOb6q})H>6y3#c_!cX;6N3=o$nYgj^h8aqnIv
zRgYSvu66dwwl(@zgd--Y#;0QYRhaoTW+k*4IIAeVGf+gh`qi9(w17z;V65rRShZPp
z%V5(P6~FrQfTSIP<MpQ&&pgzwp+#0{0B%Mo88CbUnwH(i9P?Gi8G6&ATsA3ze&%2-
zCgf*jd7aB<;qjak-n-2~%vyBK+^z+A?1Y&KtScQja^;MEY@iHrQr)ogFbzki2T;xr
z0CQ2vCg}-1b55GFGsVj8!yQ|<Lro(Cnhb}xN{&b3v^fYa32v30G>0ax%O`%-pKw9s
zaY$t+8FF*i)}@a>{d%lU8yr;j?g=YE4kVQ#p^zG#$?f^nG8~UjT3}U?vIwd-Nxd_Q
zxgpD7)KXxn9cTk6DOSf!)QU-N)cI59qA2p?9WzX0i<2XNcY#V%CxOjDEW4bZoc67o
zC>D4`hq%oE%)=97IH->v*{*_H50q^mg=XAYx}0tA-j#_n)!Z;3n&`Ygd*w;w5OBxk
z#bWs^hwkR4wv))XN9W}^;+2MaW}h%=0B(Z1OM9T0?xMJBJApE!x#~C~x9sO;$IZa?
zphshEI=b;%aIi68^{!UdR#^cbcDF2UOE%8F^Z|XrBav0704{M?<Xoo}PD7PB%>ZXg
zF`c6oPj@&yYek~Uu>7i<Ap?=kF_q;5Zb0U$Dc(qB!L24;(ScN?LauS%kQwuqj!;44
zH1%LW%}(i&^RG1t!RR_t0pN^fdWydUp`r>#4P~PI-D=Vuz4}rEdI<w41XZQp21R4q
z&Zi1kR;*99FbT<~1^AzGQ(1G<y+s2B9CS5jf-)(AP2mGQ>XgxyZMfm9Ro4|t;xco#
zfH5v%J6K~lu5$9+s+^4ToY!MKEX%oT68Z)p<$BNuBPwlX^r%4{Yf|#xA2vExW3JaD
zr63&}43KK{65x(|)@V63W(UUxkR3gQy#{(7l|#kW?k*yka#BSZ2eGEvT$FG-9CKUO
z7Q<E3OhAJ)e6DB_#K3Ue*7cj_AdQ2x@M|VJc8$s~Ia9RpT9ztORrmcU8Pe&+w&8mW
zR)B1eLMk0LJ%iUhYH6Y<{BS5hAz~k`T82TKRU(-noa9uB#Et=`1<5&6imGzGMNEfs
z{{TvkL7q0y27U76EA;JDzZ%rMjGJo9>IHm8bxV^Ie&@e~mFa*y(V8*M7{SeW$7RIr
zMlf@lQPfdP3~ggVi&A8ie2%T2D@M`*ZEmrSfM8XD(vGIOr;M#SN|c|vh*aXAGDc5`
zG}*NcJft`>dRHa?00?fOCNfn)_OC<dttKnb%k%732A{K}^f{~GsaKaY&ILRVcFZ?i
zE<Fn7yB#je>=tPT{o7OmK<aAnUrIVs$LE-=bU7<M3ZaChLs%dK6jIVxiggLvn<&gO
zeJS*Zqi3glRY!44W6!3Q;nbgL%PT4W0D8L1twc?2Y#V8H<LO*ih^B(eS@U6$i7nIo
z{VJpQiM;5gB;gOHc(1&}(`pHyKT+CD)A60Z?~IOcHva%h^VA<ae(a+kh_0Vn@gzE|
zYKA~K=e1?n=`&r(j}rqPa-emuN)gb>$mw;f5;SP#jWThZfz5I@_vRMf$BbaFabCM+
z<j1E7F3^&ogO&ELCh<qv#<4Hh)R@orSGlb{n_G!V9lnz&lFL50;<GPC+oi@ZUak0a
z=T1zI;m<v*KUj`dk-WI1fA?0fhT~^lX{g&<!5L>#-~o)(T9xWwMf;=1E1s~?r;-Jd
zWMF+UQp=lVIN*xXYQ)9diq-s^#s@hkp{=M`H$AJDhIVVh<mW9~Q|dt>*&kEEBC%%X
zmCmBEuEgZ~RVV}8NK0}mrIoG4+Xp$p^{ugQ_IQGhz3Bl)bt*C1u<othNp&47p_Br7
zs*@_Pri50qcJhY)J*tMMEbvL@!0aE_Ju68REoW+qNc#1wsjN<%61@3Yk2blgP72F(
zNX9dYpps7$vqvi-W0Q{NtTb6_Jgin1JH3e?+AbNg^GL@&wbN;`d65o#S3DyFoL0V+
z#{qNRvzj~bE0R_=*NVNTglm*m83g`yQaIU<0<Kv^;_VN<Pd%$CEe}eoT&(nKD+_4g
zM@VA_9ff9i!qiKpIaM4hagS=;vH;n{cMrSkQ0s6sx>SHJa->(u(Uod=#e432%~+=v
zkDldSlCT_L)jNUn?(S=5{=)GuCjS6Lkg0Qm7O2UmUqAf0$zQP1oLwaDeC(B^Q;Bgy
z51y{YrD_C{ElB?Wd4Q>ohp9g+ZiD^@RqY|%c72SuT*hiB(-pb@00{N_41VMv_o-9D
z*QYs}A^2vpok~}|#-lFAD~-|AF(wZc(<g<dWAk0(=^aX*4G;IPB;a#|#YFKGuX~iC
zC(!0D6MoZ<wKbybkt?Sj5Vj}*xS!?YImJy6hOBMm+;_Rp@xMyWc&a?txoVY8#-4?w
zEb^%<@}HaWuGd-9mApOWfCdIQ^{hQRQ;x+|VYgNzoP%1DYuC3>7#7SRKBB%S8G)}`
z5$z+f=|Zd{8#52Xx(eJ(l1ib6rada3h%8>$S7_kKLaWEUbTD6PcBc_T5&{0rL3DL1
zxqQi1FvFt-t!ZF!3a2w<O1w5OE-kekKGkj+H^-lucI4uyUEa0Lx&Ht|nNOfY&2^3a
zt14_SxqgD2x@FNHGh^6Sr%shs@iU%sgV@LLPNOA}Xznb?k9YA5S9f)H4EBX$g(Fk+
zu6cB4J!CoS)}Q^4o~}>)3c6HUF)_6%H8q&6x0AQ2$*Lk<XyZR-$DwNKmqmpA<DacN
z`w|aRnyUfLBi;;o%@O|qcAl~CIe9Vdw>8s^D%}ow{Hfzkw*>sOa)r)S?O>1{(zyfC
zDmT(CdKQ%a71=GE0z7OO^rRNBgZBj%3!F=6c9J#(GN1SrHM})q=Ph8&eOZlnLJ0c~
zY5NgC;+T#ZJS$<5{{RxW{-&m13t8vo({0DqYp#}9;Tdi!6}pN0(7?c74WjV2uqpM~
zQm%tC4h%nn*53AP{MZJVWXBt+SPY?~-Hy@Xo-}EQ`J4*BB=5Is6II>r&p_sj0SERe
z&&@EYQ$&CamLFPhj_mX0x73=NJA0<V+4;2=0=nrIpq<WmroNqInJniOZLMw(R9t_(
zP5TUoy64iE6p!{&54*fm(oH-zQVf0-Yx_H%LZ78bmOKJ+_)%afJ;kUw7JJY8l-Z|^
z?b|lqUI(RUHKUwuYynJ?(6lZcv&U*pXjC7(d4=543yDE@IAg(Tre$*3+<!W^sm5c!
zoq5Ld)~OyV&7SAkP>gvKu)bpx$>h=!PkywV=9B|jogAn-(}6T8B9xraK2!vZ=NYLa
zk|xH)+B?)tDYOSFCs|cvU}FTH^%43~XNoiHK<tohBy^ym&q|&WzP!|hGTk`!r(-zO
zQY%Fx!z#$Q+^3Ay+x=R5=+z_&0{RMqP>Q^Ds>ISOmM>7v1k*(rprP5M%^AfdAQqB}
zC;+3q6i@=u+LDR@T29nb&;n6K6vPzpdQ&k<I?xAU;AsGsbpHTs;C>a|FWs*^@JyRE
zDRcZp3iL(bb+1bg@E<9fD_3Efa5(Ki9MX>2t<N-0^b=0oO(Tzb1SW83&op4ufZ~gQ
z1MN=-G>b}j6bw*t%??g@6q~(2DskuEG=w1FbmoFFN_ggs&@f)K;uMV2bBa#=XaHgF
zMtP>^C*GBv6>`mwtpGTaicAtIzG`~X@7>VSU^!0H+Z3eJ6oP7Po4WL=3lZmzl$*X<
z90d2MgXD3FU`QY4{{R|RZa5VQ51uH)`ry%U9lf`8sRYVLII5u;kKU&nem-X;(Qquh
z>fJF+GO7L{P>5GP)P~&&%>Ya$PMd`SMPtFuF=2^E+#a+9Rr{a{296iT(c<zp&sR0c
zH&b1wj#C~~q#hV_?Zt5>yxN*cpIw4?qJ_xrDG8)Gq&cWN1?xw8Zbmx(w7CIE$o%P8
zcS7fiLr54C)KQ$A08V`c7GcbV^`!4kRboI?a($H3(%#|z<+R8C0BGcwVqHisq;yr4
z({%^V+Zq1=@0yTknzNsl!e7R#l3j>(=`N)n^mCfkUkz(5($D_@9;p+;ddr{n5wF$h
z`ziJz;^?omV;_1#YoK2T>Zk8Du=>3{d>MXoy5i7(!0D<p6UNYAXy-FUbpyeU05a-O
zC$0?#!qzB1d8{DETw<TFnVZZgE~hU>Yo`9h@cIwl>sk6RrpaO9NH8B#k%{e1VdO*1
z=%bs@6l8je=!^I^5Hmcke;Nj-;ONK63qCs)t5{hXJl2{y+^Ft9I&YYR_=R+T@R0ak
zG|YNteTWpp;>`^{=8n1dQC6^WGkLr_7$D~y6ZECQCxmi+l-BzA&dZXTOl#?yiTrR>
ze3mf}ZM9!gWIW<MjByO-rM$=3A*mL|@z2X=a7X)wub&;?<K(u5SKWX5^$U38RcwsL
zzeT6@CQHsdhAxq*xcO{l{6$K>9@X6QX2bpBD!cgCSs(#$zxT~SCyI4>0WEsNj(}Bt
zNX_Q+=#4SqomIc(lxy{Rc<`>KPd{fLSFU~a-BLh9UQ3^2P&TE0+(~sS5BH5fsgUz(
zjOtH?Z@-G-+<OMD*G!rlJ0y;2;to6RuOBy84nAq+C%4RMH)lMVB+vWCv{ZQ(hb4Sm
ztNcf}uB&6n7jYAg$26x>wgWzA9=NYE@VvQ;spqbJtE)!HuO_}abmZcYp+!kt-~QBq
z{{YKIKkyoB>X7Z=Is7XRJm=D$53O>%#;Y~<5H(J$ouYrl(_2#nf2u!=R#`k!XNsS%
z)gQ2lqHl{6`?aPUxij}reicm{2A)`RSxXyP^&hc^Vt=(u{=okLfYVLH$DQ2=YJ+za
z;Bqlg@pZeE?Bm#Ex0B=jYYJevmD4_B^ZwN~QJjj2I8&OXh^Y5r$q`ydKl0K40Pm`W
zp+`SCX8O6Q32c4ZRr|TcbSjc?dXnIU7I5S4anr4Gdd0t!s4^olQoVE1yAW`quyweU
z+^dn=w82hJc4SpaMCW$o@<}7!r?UiK!VgW=Wg%RgE@{aEtmxS2z~;S4$J}Q!mZyKE
zZCF(mKse7eb2x8G&C?%t)6;OPvM~}duac~qn^!#;Y*<&#O0AG;lF7|jf%i7r=V+o7
zJi7gBE=JoU1M6BuZM=2<_BgD&&-nO%&b6nw8U*jP9P?2|3$D;{MXPVO#(APFF73S6
zO*gAdmI1bt>N{1dcg$a2)kk;E+lV=<Hjnq0^sah{q*+$We}zhfkyU}`6*O&J@)<KX
zLQPr(7=fy7%KO!bj%~T9U_B2tAZ!Y*rwvjA&{VDU09p6QIQz8w@16zij+FpbLSGzI
z_Y5A-IOJ8!;?R<uCDvXK6?irq>r`#dWvirOMdrFWn-IcrAr#@mie$(4f`i(*>Mcf#
z56KkO=d~$0Kt(hjYcY=meiVtsoKQcVAo*klfFArvX}PCLK458stq1|6R8q`vDIk$#
zkg||{>b3fofbFJfvTfL;b6v8b%R|~CIlb!^E*JNwH6_0bf+^PsOH(2xTiUr}sY9e)
zq|`B<G2W+}kyTU><ae%z1?=u3+zp)dr{|i65<}Fj!&f8RV}Z_irEXT5I+}Jkq%e)L
zzSQ7x_|$QXF&(M@07?LD!uhuBJNnm(_?822s+GsyVl((xwt<u*sK-I{uPO1}u!`zA
zdCAE9{{a0}^?Wr~-;@qaTz%V|c{x3(R>KNzFgc|IBNg_Cmdi3rkPg~{Rtz&!1qM2a
zxn6)!A}~OwBVobmOzF~`I_8kcCHb>Z_3cugR-?u!0Xxy2X?s#<il7eEhwoDU6rCsl
z$2Br8<j?b{v*}Yt-zF(B3@cp@g))mLM{YssSO=d<(9$wykw-YiO;3ahQ!dMi6lWWa
zMomws9h!uT>&;dyD#ir+8V9{6LCq+jL%UN5?N1rSH?0E!LmYe2-j#-WQvsWfYpd|R
z!m4akQrzI0<%iO=G-;k2;1G}vV_Gf5Mb8pQ(p-dP0B$GotUo6m>vLZYT_s`<V_0SK
z#~{<DmnafMxRb92nJB}MIRb>`fu)dV7~-vrh;Y>4a48Obs6N#oJaVJ?(-?E_PD4oD
zYLfxE%^CEh?beJ_xDQ-l(=&rk2P;fHdeLzKZ(33^Ii%y#m$fD_tHnK=IK?y`X-`Ul
zjA|)J?M(uZ3J)~l_i4ORj+Cx3O*iR59MRU02N|mt(-<xiU~pI3pdD%5y3|yHoLpH^
zm7UK>(zPVIwO)Sctpt;B<YVhzX{TzkY163#_hjJvS97Q8cK6W+iH3f)@i_dxbSBzb
z9@ZNWrmW3cP~6mEv5eC0=Denk#K-o<9`xLtQkJD*i;!psC(@HRGy{W*ECZ=?#V{P4
zQj>$yiv`Dye+oKNJj_yg!#q*S!<iD3icoSYEy0ITkF7Z#GJn=6&%GRvu$-bl=|DdG
z(^>7%b8#Q%O&2y`7JH=6r9WpU&|cCcx#UneZnaJID<E<9gyN!oYfg{vT_E<VSbC43
zdq{UQx=;u;j{YXnRN&pNeJT^;-5r1B=kgVz!Pk35i`!FOPJs2zAR{%;f5Ky=_LaD%
zH;r_$(8zmmDwbb~e_@jGG?!DP$26dO*DL=33ALu|ExgT+;-)?>h~xbk@s72;GJItA
zft$wAUufxZOW&n(=f&r5{Cl6zH3N9gRzEBOf8G^qBF4Y6NA`sd=V5`?mmTqn;v2>{
zWbq2ra(Ke{2EhyI^5&^zIKIOE(V}-Gsc(O3it6st#v>)n%Nq6s@@vm0@m{4VA!Ndl
z*0Ls^TejVB?IUM7HQj~b**AKu#;#)<d#6dQc$!U3%oeB1wj4L9tmHXS{cAZ7&A`Q8
zgc6><_4b$?JSbD-g3$0WH62NFGF8AMCpDuP{oQ8)hVPothdVJ|r8CZ~DI<eWIN<a6
znwh;gsHFS7s@V}M=k%sOLxWGob4_d&1e(R0#IKHhXvS$<if9DZMuOG2xj;vHrUhDr
z-~rBYT2m%Oqxn^oKPcv__BA|5<^GkrIpjHpR;x%qDzy2<R*-Q`>=7ZLj8H}m2cfK)
zsv|u`Cwf!XlNBWZ`qatOH4RH2K|&>x^!nA9+bAl&JJj&>=bF_R$Q+#Ys3bY>RtV((
z04jz509vLfvbh5^huW0#X%Dqx&CwMt2hdU4q@*uel?HvPEPK?k_2coXM6yD0%}*cQ
z^{5EXYMLyC#b}JAIl5JOI`kD~#(iqD^Fs)c91%$0Oj4YBP)`}GnYto9XzkPTpp2R-
zMmTlrQ^q~<RqABqejHOJlY$2$rFI?;KP0L#fO>oN{<X$~#&L@3JRK+RWK8sJ#CrFy
zo#IGyVOiamyHq>5NXhHXQIPz{zdb7SoT6j<y=s)B2mCAZ3t0Li$gQ1BryWIU<dL7!
zu;Y{@<D6vTwaXvIzU=qt&!H~rW4{#{lLwPg$oP!ots}8dLSrUW^In1Q<61~A#iWmd
z++?>}^DXQ<)r%{stge#g7Aqohq;{e%%*LwruyAM4m)aCJcfNn{6Tj%ys}{)OR89aD
z=5`)Exgy#If=1jzmd0zcxW9L^ca65O917`+x$=0NJn72PFMX=bu31sz5{{$2O(dvM
zk@-`{HRa~!?X_G-pEGzF&o$gRnoClnA@=vGIb^I`fo<)<NJ{h19V?gduBg%2h|}iH
zSJH-|XK^>$*tho^JYu<z7;6ZZ!_C~tr#K$9okyY7g@^AGIl1M*IXT_yRs6s^({C@5
z>BFLI80M<^gR!n->Zw({ORD^JrwMW1sEKjjo#y=AXgVWQyd)%h(s`9sOOEur`R0+L
zs*796??E~5Rea0}1fMq)iuQ$q#8Z6SpO{o-%Ti}F3C`rCtFNVJ-C3iKoYkxva9?^Z
zXE-UVGnt;;#NOVt`+rK;zJN42$4bhLKs85`Iv&cVhKw!pfmYD)I#nn}d8>$WMI*kG
zCIdaHM5uxK)TzZIx(uE(gIBHB=T7-O>Vh19TG6u^b;f>LXez&PnmX!(q!c`Sq<)p>
zakj}7{{Xsq#d;pKy|n2*Qa)3I+PwP0#^X@A@?npFPWL?*uNB)u4szv3z+zv%+1=@d
zrqiQ#?NUz4v7B{!b-D{%MYiMp>Pc;x<wcJS625|*d18^`&E9R9_b~=kjdt_NrG_Ol
z<o(5>O~OWZ;160zot_p^-<qK^8MP*gL*?=XW*tsZBQR~i`u3|g7VMyw=y}CtI|X*_
z?OgR_(XBL#OLW_I?>NqJQvU#IOo*$$C41I1w>w(^jQUco*E!i-uCs~1vrOpX@jTY8
z<{|m9j%pcvSE|D^`Er7i4hDKxGc&s7vyS+vTK@nbbI9WrKU%)*e#IRVc$Zm>e3v*z
z>J2dXqgYtge$oQxy>o4N@5Xqk>}_Vhk$`R#fNEYV%zniiQh1|QXo5A)Q`@aFZx?D#
zgZHEr?oDKBHd9$jtMdgTsj4_6a%(q=pGH!n6QY;J_w08GNj~)izAC($P3%}7_p1+R
zqh}Ql5kBRrQS56U6KVod=_$=Z+V-O%+|#i36+|w1q&yCX6+Yg5$LyonnY9a+7&AUS
zGfDRQox6O-D?~OIH#qX(b6S@E7P*w>R|=hg>S*?|?mk3hNqI92Zamkh_)5}SeIhXY
z?gOW4<sk5)EXd8duzF^@%Q+Il!9W<=I0W(OUXBIc?VNbM5=hZ$;nU#rCc$_6tM6IU
z+)u0ADSU`j5)@OTwx3YFhD(3~{o=lrdN|YV5|qGD4R^DMpGlC(X*?~19tJ9ni8eP<
zl0k{Nlpp8%R2mGVUc4pn3lK+Y(ULJ1rz9i|t~2;l$fQ@i(_xBD@r5wSj=edqH&)Q(
z)2<69(+rJ~fzhj^wz+hk<3^Rq+Dk-FVd+@clioq*K|jtE@M|V&jB8OOQ#u@kVZ~UE
zJjt~1Ds0DdZX`?=L-S&^G}{3zi!_H3jz_(6){=$Js%q?^7M#y<kc5HOyWIu`NLP1J
zSutH%MLcnd6LU7+E3daijuqLAFwYg{M^mm%bS}oMcmp+dC>d}{)k|BHR_Co>Nw?Jy
zN}K>GU4Rt1!r;|;T#`Vf0yC*@)SPYhsP>%y09u(7DTCIK$Q*&t)d`N)IjfgT<sMHS
z^_eu8&olu%6M@0$S0Rx};<?tGqm8DtY%Vw8;Dhf>3);!sq|5ZpdFvdtcKYnN(+JPr
z;8zF-&yJkpu&KG#Lq&5|G9$D&&&)ZhPTbYm*h6lLdg8O5Odso7M`Mz-uOQE*K{IyE
zIh)h9RcGYWGDI><v$lS<PFX{BIH{!0K5C}<`GMk)$fN+V?@Mk-eAGp|Q{sP`fGrov
zs9z-UO3j@5RAhj(z^y)Nxqn)o<L?uSs>dRbz>UC;^yXhKGtLb<B*`RmRc>AP1B}%o
zkzL2maBHB_oBb6xa0xgb)y|$pY*@*+Pswgq^r{?|hg%$IQy^xkT-t`n$4bAaIGWWQ
z9Pa5>Uf*&aDHxob_SigCUnm1z1;x7U;C^+PEMO7{q!%w}v;4kEJr4r9XeU%E4@%<T
zV+?@j1KPSMCM_DCxgBW?>uqj8UJh5<wyfnWs_WEst~Sm>tT{ODE2^-V1;<c&Vvrp@
zjNW2x?mcQrq8*1`)k4xzju=*`B1OvcK+LHlDr&RGkVkshnjyC}p7G$4J5v##<s4&m
zR+b_LbIoaN4U^ufN{+l9hL9AUnYds+wOT;{8$sm0wSo1k>=f`tSDGa&!K5;_a%svw
zZ04BYuM~<->O(F<cD@a1!8YIlHI)(hhEElGCQt@w3mVa}Dn4vhglsnTtaxNyzk49n
z*k&W;?Mw@fy*{-BiPwsqeqm9PGFF(15{-tl?*Vn?dUvg9qTJ!T8m)B(BRC@zfa5P=
z3|No4dsZdPTVEjL8tiXvQ*KwkQC#iiyBBUSG4h&VV&iG4V|=iuNeLf#)EL^}_w}h@
zYe3srd)G~+%v5gRkz9?uyVuZ)*RY+VkP+698hY-Q1fOn%l85go^{o3j6<BAXuA<KI
zWm1v=QHB^1SlXtZY_0@|%3))bpbnQyUD1*SSdu1V?OFN^`AjooJ&$_ckpUSQrhv}!
z6?)Q`)bmp~%KOwn5!R>$Mcd6XYIkaD9m+wZ1a14+opZ>nR{%L3g=}uY!0TBvp-I>u
zTKTRZr|!mQtC!Dsk<pH5qZRUpsvYRXE-2^Lki^Cf1CdKcF-$@lF-zKvdQbvUid=GN
z&!qq+C_O29(w->{ZYdaL7=L(ToJJ@;57MeTiJoJvX)(T`B)>W5Bxj0CO$OFTgFTA3
zY_npvb!0znoUZ^>V^X$@P1;Bj?de~o;dP@I<b2(4jg-%aEkk^|ZLvOut4_mCTR7Ci
zYi^7WK-JFM>kN#|CQeW3R!+VL2^;cy;<|2PcQIZIn7pfmhamIKWM1iZW>6q7DEel(
zc|1coQmYyEJ8Hh1F79<fG?xsKug!tS;Z)?>1df$$MYA%7&piOD=z*u^W{hV)D62+Q
zFY`FfQ{KsN<rP>C=CDf4({n=N;6-n-WpXjzxotw_S;{-$`c>KWm?Lej%Z{BYqiU8?
zx6Ii80D#h*;%y8)OK6PPO8J;fpTe(26SRZnKb10D`)G(LLH88J*A;mQlm7KZ;%>0j
zU)eV8yx5pzkO!??W-PprKN{tm#0}at=eBAl*WCXA%QY1|(J$(CdmS972dJvgu#dh!
z3g_EenD<YnDi+mdz`@7iM=~GOs`fX_BDdbEx{&h`e7u(Q0<m9GxPEuz=~2D)%M5vk
z6x`ERE}j~tIddXYYd2Dq#)Xg_*dFx@T+B!M#;Bw+GLl^5)~7?FQmBbbDE=W&hUh~e
zkz1!~%xsg?({t}fDr7446Wr+k0JoTZ*&9Bhtyyc1vln@Z`ikY_Q&yuG6%NSjkF~13
z=^e^=wd0HdaKqDRsoTc$81@^P2*+_;9(d|$;OC*NoMQS8I2iRhXYmS2obO}mY6GrE
z&+fkh)qqLGC<eCn^R=#0%jtDC&bql6g?}1DuP`|fr{!4zc%TZ0R(;JD0)qP{nb#-J
z%BlhFiec9;2>aL`)j)td_oOG%lc_G{tQ{ZaFCAX+@#i=4sGn23ZnHLhb5%+D&^pv}
zvsH$szR5FQ+&2bi$JUx|W+VM;{&gAkqzj%X<}2AjbUhQn(JZ=ZGpK0-f=TcGb6rS`
zXN9g$z^q$Oe`Al-*JKp*uS$!&Pm;#Nma{}=EaNnuSk5uUPqdD-nD?ztG9efP7{xd)
z1w0MZy9oBC1bb<_D#FG+b4bXdkPrd3f-~t-ouZmb_ND_ioKj;3r0qy~pazkVNJc#=
z-4y=-N@jWVphLFO913Y-0iu{0I?6ne{GGcB$+5S&67|CR*HX}l7Y&S5Yig0PAw?mT
zlHBK>O-?OxGHS>e?M?%V0D&My9<?`?xZ;#_qopPT0^*bmQ-`nVN=F&*Kn*7+9cg@=
zj+Gga1b`FPt|-L-R&?6GT8|`(mgZ2ZPimkp$zm}@z_bbcDXcdmFHEVZ*5`5Oij=Uy
zJRT@xj^~u?%ePpZ4ukwnWuJQ6@hSnUN<ig+&0-OX^D2By`#dYXBqv%?MIfj;1<pRS
zXP#&SrfER-re^Ql3F9=Fr)L72jMA}j^%M>{q|PZ%N@+BUXi!gTQzK)oHiMH)l?bhY
zn4Ywmqa0C+MFj(zITU7)3rRtufDF+|jM9!Nh$zh%qXf_aMK0O^pajJf>~YqRj%ct6
zM;N2=qm0l2MrnAX7^VjAgdDE7j+tEkM1PHXauB1Zt$9y}r1G`Mn16TriuFYMi|Pgq
zcj5j6<}-Es(rj@?a%rIDXy-jEpz=vc`DvSY;Lr&xNrFW%6B#t4p5lNp+)<D^kw`-0
z9Zdx1y*Da<h*ODQT2~l~aC!{VhB>6%o!X8MOrOGwh+Wi#<n<zt_zQki1C#ep<4WkO
z2sv)_5_@FQk_R6yKi(9caxYeleOyv<L18w6Ia5K5KTr)s`h}t~-E#;1_fbB-rALtW
zumU~lbD`LuX5NYgJ$GZEteHGjqbK~tBjTya<6RvO7vuf{v~vZHkx{;s_DL`{xvnx#
zA89Io<MLPb0-<k-T2d(DXB1ub3mv$(cNu5r>qxO|;IKc9a1wk?vJLXvI}fcvFU0tm
zVm&yY_!cPFuvqkr4E^9frjd+&3y;9pmY<1|4F3S20qIqr;!dNJ<y%CejY7w*Ge!>v
znkA1o8;{{$RG$$wnTFBjrhTe5@s_tMVQ%sCQA?SHk?T9ue+zz8XO4#+_2g;dZDY+-
zE#tC-$Q)E!w!Nt<ppNcPt<T=3uHJ!Udiyv78<c%mQ%tC%nIj+YI`ElwO+rW9Z)V4)
z>WA&OWlnBoIqq7u_Hq@^VAri}wRPC{u*3(Wb6oN8-i;nN>Z3pJ*PZ#2lgzKv){&Wr
z`|f-4)h`a2)eLP|N0u)`(Ek9k{5FK|)C=R$sh(GaA^Z0($KJg3qL%10*EygnjC`V+
z!$fZ#S^cBXe%0XkfB{SWL8Kb*gk$@*Dt(Gq1V_uz3TeO{D*mk#H;bzJo#F9^hhpL#
zEf4$zQ%{dH=<*}dBLmkJ!XL_-N$O1}LMWfCP4zpY@eLD%(xL<Nrk{v+NA6j|qv>2Y
z>rWgS6)2MG$m^x}g{mGBDA(|+t>c|-zvZxBpcT$B0*v;pJ(LOdk~dF`HP;w7UzI}s
zB-P}|H?j)JT3q6<k}IIO<X(MSQhv9yAI6|Jw@mw*;zE7epw4J)Q%XIB%*h&gn3B^-
zevM7u<mY>n?$p`|=C49-1d=&pQLq{5pRGQcdizwd+-?9hDjZ^=J$h8Cyk|8baBjch
zK&3vSldVt>jrQ^U>f6SVrhC;TI6q3Tk{KOP;~um&A~JF@OvPE4B91=wRVIs!QUEm4
zDNQDGO5h;tO)PUy1P`r7!w0QHU`o8Gp#9#oARBq7Fzrc<=sYyrK?8seKRW9Xu)K=o
zJT!1yCxFNKS6HXzua(9x-m}r8@RAnhpSvqilY`crKJ9TDk1dJ=debvWlR(J>VX6DG
zPz>%BCwf3jnmoX?#XM8ChBP2!KKoQmyBLo3XvPviI(t+XBlnzhO$cAT89nKX!gEqW
zH!d?wakLuVo9HGA*&S;?RgXIwt|Re|^#-7Y?S6+f(}Q-ZWmj04O1R)sG<ZBxq0Kyw
zM>Xv|QN(mwW94Ew;8vvEx29_sOgKou=M}Rt$REnSR~Z{sXQfHr2yH$YF(9aO#VYXN
z*CR%R*G;zaHWi<IKYXXuRqOnN3-shwE7AV1*Ve9>gtKfCy~sS&@vdb9*R55x{{UIV
zT3?o6b6UL^h$Q(Y#ZPM3kl^;HuSVI_`id>GCR&;7G+tsub*U8bQ8x|ENP~*P!zTyj
zs}{V*!mEm&(BQcAtfZ_1v5eD)9MD(h;*OOlWm#@>CzcIeLAuYcZYrPIRqry-g~v~N
z&`quiFJWCcu3b3^Mq)D~1I=FFx-iugw&hy{cdH&)7XJWy6qM7Aghwgh9+a8N(#y;}
zb4^?o?^)DZjIkNa9;8!2#%W<cBMNO|GDSR6wlX>IOa_(t6ahPrlpfU)7^kl>b4(wN
zAR6FoIpkFvQU%iX#a?byj8;gK?Dwa*CcP?GmL5qNzlhqHl2)PW;+8p*W%m@uU5B}@
z80gC;kbJ+^s^=0KuruXzRoGyIT`O8`2$nO60Tp4nAk{#6b5>6%D~+v66c8#vfBkh3
z=qbv1>rw!x_q}QEed;5`fYh(hb3h8G2Dm>S+V8gxgDsuIKb3bt*E!<omVG^e_B?%S
z*~qGLVv&t?cr(WV>CS26pyGyAQ?zgwjCxWN#eRsH<Fa&MVj`Nu0~}LgJmRD{swAv)
zxYM!EY7Yd_nnN9oif-DKakSGI`%?j=U{h(#d8Xqgm<L)9J?Ti}>q*{#0JQWtrUQeT
zdYq}G0_Lyi=+a*lUh7%sk&3fnA&%``TL+~n{30jTpfKtgY<$bwvvbc%+1HSR8<Xvm
zSj6*6FWnetIi*vMDW;sJs0VhS^riaJW|#>}if=imsLxtpH>ExaJgbC!;AfLfd@1Wq
z>%|XMVH?_`M{{5Zb>6rluyN`tPOH~6g>#=ui&+ehIH_3)T<1L0Smvx`c|A=4Rz9?&
zr5s|8*r^x;=|g>ap?GRm?betP&_|^JQTWpf0PDpeJky6-YXj>*gx&O~1Mf^CkW{c8
z{B*skwCv)L#62mrr<3?odQuqd^GZ5XX~2<40Q%B;&_yKxC^Vp&Owv*SJo-|{B#=J%
zBxu{!O)%#;qM~q8R*_MYTO9?DiSOe(BxR6#nzH^jk|_$cm~VAz<|6}m&S;rHY>M-0
z<=A;U@|_D4Q@Pf!jGkEXwqxjDrAB;Vat;NekA2n5+cJ&WJkyJO+3QpNmxi~(Kdn^m
zbqnH)>4yk_k6N4iYf@zg0e5x_(y(n^0UUc)vN$Wp99I<ZbYm-WkLxubQfc*VNJsL@
z0qRaWRy_LlvK)aw$UE(=Ev+l;>zY~gOQR5zY1!xnZBGkJ`9<yL+~(!i^+t1>ryuUr
zU)uVUFE?`jbta*wG&8wX;QCb<=TwNU#U%HweT)~`UvRywpHkd<uAt7luO;iywRF)l
zy_)7m{Q0gm8+3r+XEoQ@znNylf4V64QS2^xcPO|azWaaQRU58xmSgzUiI;4IQ$#?4
z>S?NR>@Id!*~dMqGNDxbpnKJ!AE$api0yBBwE|p>cR(a388qelzLfcf*)dHXmEQ>H
zV<tG#&<1!Woz!NvQ8Tz9!*uUjaqzX8qvowBNZ2c?j7(}VPpw4bbxcMHIH=rUcCF<T
zG|Je)p}y@shhDUVe3g?%ibYe6)T0Bv3^02dP%9*jE<F!F)~~|ACfcC9V~V|Qc;>q3
zm{cYmb64T!FmqHk^H*)yDq#1nx@Q$#i5OH;jIISve(9)W<kpPNC0>S*jH#tzmg`7+
zn#G%<y9^p=IH$?fnr<>{BT;jTu@S+l-D<=<pHo*2$&oPN;-`zHLP5tTCZ&rY<E?It
zBt6eRUX>Hz_NkkvH3JNNDw#1LVa_Q23Nw>OTFsjwjZ7Im>BpxugQaFt6miz1jQq6_
zJmRE}k8@24lL5ya>S#^{MT7ZNk@^bOCK4rK#~7$(92&60j8qTE#ZweY$BIM3)0?d{
z)=b$EccsTPj5(lkYDyFj%B7E!)}pB+2iBSfO^TKgfNCt$;^5VzDH582_{~n(s3i2J
zD3BBN#Ri5yF`)IV*|H-%8cv6rRv$4mfbrI#q1n$Kl_H*)6&R@#fI3qXB^;0|q41*>
z)FcNZcisFeo(CM7+3@Uzb%lK3Y%BQx0FhokcN^hkbl}~pqthJZanh-{!yYQm34s`A
zrB{?-lloWW`!ng0;qy3I26_t9S<H}!1a#|J6O27rw48ZtmG>v98QGT_UO*<0$&u?-
zoya((564;#g;kTYW2FL9gHdnK(wfBbM-+$cEOy=))UD!`Bb5$&SE5?p$2t!!!4=`w
zS8s1Juxu`KUV-7co@te%JCTpw>5A48IPtVStUaVo$zruz#h(hYXB?X9*hXxb&t>cF
zUU{k7Tu&Gg$OEf}9@W~w4aSlXoH0yi-nO~mP8K-bOT-Bk<HpN~$3y8}Yp&gWvr=}>
zR2~g=I{l3H^G)UhkZ=#RaS!u3&tiD2YBSf%sV|6xfIHF?ig_GyQL*Wo!so59jA^YW
zG}dFEN@?e<1oIE`4LnGFY6^Pw#RF0%RypfZD|*xb8j(k(BY3i9I5i@HnyxzcsTIh@
z2C0*daZ1?W^r(cNOo|Md7zd>zM9A*WV_}NMM$1->+u}CC#bqO5^Hh&F6)$}n5MYYG
z9snM-nG~F4XX{sDB(TSN4d}AaZ$nR9{c1E&M_QQ&L5fFoN3L=`YgbLfPZE$w6_|jY
zgB7Evu!?xy+>NX@fI8DfR9AyK?P|~dDfvEKxL!Xh;yg4JWw;DL8;Xo{JpTat>(X^!
z^q&s?=oc*?MH%g0Qw5~ZyBW8{yN}9vCz|x|O{$5Xp5qt9nbb=hg|ImTrYbKz?ctD)
zrjtya<c+2;@-F~V%v9TMU~?mJUh(4WQG3-`0y^ZktxpZjtXB9!3->ir_SGDw*1^Y0
zpt@Z1+=UVj4{FMDv8si~>e`Yh+A*APYnHmbEc_|J?rWpH@Z{{@D9A06Ph(g*m65ib
zE<vv=5nZ>T*G7^^g5F@$Wz=!fn>5ZGfsh3d#v_qSgSWjp^+1y=(AOiIXGbYr-J7YX
zN(|HRL7=ZSH!8yd;<o%ZaF+MvKk*JL8HNWuRF?7>u3?dKFx`)8E*3g(6(UUxbE2FB
z)K@IY$*$t!6}!@3Bpu6~S0@gUsNBotLumQW860AzF_Z|%;-!Wbn+St*dRI$f@c#f;
zzL+DC41T!gy1P$@BTrc65*B6q#P<~L2;%I#F+7Ac&9M&{9Zhr=UK+NKC&@Cf{vs>0
zgGGe^FVuHhxv~gXjQ&+O8O_C{1q*}&(~6tyK}XHbD*fK4Z)&HN&pcKX+QZJ<VNM&c
z^rv!KA0jMoxbOu^*Y=V_=DdKR>?=Cp$nfFE)C$Rt$=*yC3OZM(gQ;c8a@VKKb@tlD
zq_>H-R0AE2XxOYWJnkECt}@!n#xw-njIIY-w+^{&r`$}dKgz=Z6W+ZKXqM+EvV9FC
zwl?y-sgO$&D@N+$%#zx0{2VFArE+n2hS&#L9G-u@Q@@IAq_$Y1T)JZ(^)jyx;HXT{
z)~(oTu-rqP>&{1NOV@&El6N2#!nSG)Yx%Xyh}IlNssJSW^r&@j4QdhH4fhAhBX$Q&
z_pB$1hRE79B)%e+o~d=IOp$-8U%iThQNNX+$be!s;MTQ*{{Un{(W3c`+4+xpd>U+W
zznd;F-qpcUZgSM>icwk^{vES>&15r-2(WYb*Q_ZC5-0ap99J!+T1OSeQ2^()b;)TY
zg-c{FZYwr1AVTlQBDXE!*&a<Loq|H3;8gO+0HgyL<l`VziD<4z&PFPsmum{W1o5^x
z!TQn}D%nH)QWN-8hS~%ld!I@O7|0^4&oEI^GCSdF(K7WWuq6=0+%0Iz44~q&t|D<E
z&nB1<$jab>82Zv%osx`Ig@A<lg;$k?Ah)M#U{lua%c{q_fz($zjvip6sbDGEo$sA+
z{{S|5s`_%7Zxz3Veqw8xyU6X2y8}k{LP#Bl9MuNNJm#mplQI%}ny6(U9CfYFHR?3B
zIqg-XeshYMiDAuGnUr;)3e&JHnyTcmKcz`C<&PW+gtix+w19=NnnXB1N=LvxqM}pt
z&@$t5ieUTQGeK|{>q+Kd`_mB1frYApc|EG!tXNbkpEi49ganYT5SnC`>frQ0N}+Rf
z;$g9{qwf!Tq}rshN_og$-nB-NG}^-l<r)69X3pPYN~fa=%8Oq4zI1QGwQTQTx;s(2
z`p{F@*U|2TEbu#Ebz15pkxJt|x{me27TYHsL9P8B`CT@#<Z+4)c57T)tD(n3ShrTd
zWa7G1RdfR&{VKK1u2(#MGzl}4F^{GzR?1w(wDF3HdvJvI#Wn}n!jVSprOv_>{&mn;
z&zu!*-7Aufg9_8Kx!B!mMt7Fe6Br`3tY=`@ZicyyKKB88sIBNF$=tmt16|az8qSn$
zY#+|FE#(p>4+qkrxQBUaVl#>i@m1#FbgO<#u6W{@@owPekQs8u4<o6nuNwo8TGW~y
zr__4Yc8N&c*m}?gbH*Dr0UJ*vn$eQqC`jN{X<#IJ40WW&K(CXEvlBRdr=jAjG$C+9
z^HOi<Gg3120}_E+@RA76O29`d!zZO`!#?x?w@PC+VSKer(e4~o2&LKwImKO$P|KQR
zm0vm9YBpWSRQ0Pesb<^<H46p@IO3QYcQ)IydR9fvrt$BNmDEWVNItbv;?YkaV-x|x
zUD+MS^Q@_3A<lTkcQ;lcvz7csVqR(d940`d&=@c_*(**7%x7@sv!{ikZ@5K1DRRD*
zAayo(Acb^n*5ZV{vwLSyPBNcb<7{qxxkh?psji;NaNAvdXacR2lUhm<&RI`W+Ph0x
zgz$m<Lb*L@f|%~(KO+um#*3>JkyXzb>U&cIq?#?YR#Fu7&0X_SX!F-S>ZF~`Fd;2X
zA26uQyNO=nmNprn1UX!uywyAP8~5X!Rk>J_d8*fOmWMu-=4SN0rW#&HUJiDuQ0YMF
zKs09+@JGHK=%b|>6aaRhQQm<_0*q1k(vzIxm<it$0a#M&OJk`uy~~puebedEw&P`F
z-h?t9j4QUj0<{Q6q?U|`)Qp=*dj6EBr64q-xJw(-kKm_u7^FV`0If75lhqe><izyd
zkzDP}L(JrMu8&x6^w(aStBKb2DXrgZTwrofdi^Ia_ptEvK6eqNMowcueW^AKaa`2e
z?b@%)gZ!$y_=@=O89?@~+Zdg2UO3G?8Pt5d3gZ)8y^+7x{uE8BUIIUS-uUlT%E0YB
z$r$9HYKnWAE$!Tg?Z>@v$5Oq|`r}jCUe6?rzCz2`8qRA&qYjg(lQd<O<U5(Oo@tpq
z%^@I>=}1q#dD1?z2_!FmlxH-Vqd!WUngQaF^rZxfLPaqNoKj~TP);eN&}SegnnOXP
z=QU}Z@<QgDo-s><NJd3f%w(=Y>&HrHT-4=Bp<~5W&R0rKdJaUusnlRnD)hxTa4RNy
zl%r%B=9~>C4mwealY61yWQurEQGzMq`Ji_kagMay^Gsu!Ku#)IaU>>_AewGzb5dBj
z<1}X!(?C4XG5PkOXFO9gP7Q-VncMghPu$9bsAG{`$T%7GuRib_VtIWsYtbVgD6dNo
z@E;|aD_3G<@F@4CJRAyeYy-t^dBkPN>%gamEIH{>pP18$`6vP8;CH4I+nQ!iy&0ed
z&j*@J=e;2~8KXVLFde%K%{QY^4rm-T0u{RZQz=-}XaPqekHUaGDpgFbb3hCLP<qmy
zDW@6spkiQ(QgAayMK9KX8W{c*jUfVtUO%lcjGnZBiRO?V7L(4Df(}Ja7b2usl%9G}
z1{KZYM|8h752aoEbcF#fY8^t_5jU8~ay<oDjtI<S<=}eK11{?JXF1-)_o^RnyAop=
z80%ZoTOlWC0-;+Gx|#xoz1-3tpNw~{J9c(c$vNVtj?Dqi1zAXyMg;>$oA{|V>RW-y
zBNfk_3hKON7)#}Bfsw$jP?3&EuR5ytkE_8y+@>x)=+88Tmp^z?7eo9*HJQ}p$BGY1
zXPBV<;m^G|N`kJ&Qf-U3G;QXT7i028BY(Pt)BKBrz_p+7jL_GSDYf>9@M)xE)sbU-
zK*gQG`lVQpL)GR{vdzYSym3dfljv;m5KCDZ_@u>buZ8uN=j`aeSE(1m8nX|*Y`<4O
z;Z^LV*vsp5mh(my(@Bcx2ZMDH_pa?%{so$lcs^AhyuXBf4IaWmc<L*u&EpiO71PJy
z=%j7G+Dco|YDVyumjE7qsN?jb*htOhlslZ6>qj27)eQ^7ai5=2osZO0#-HJ3<IH!*
zsWqy>)O`%zZ9yD{<<C(|y+?6faUK_p5H0uPtu*Q$9)x8y^={mzYSsd$V>g`9M<!%n
zT20*aBz-Hb9w5=vgwf;rY@|LevyHHtRAbWutNT8uV<(-{=#E)dMmR{MbN<ScQZ1$9
zpOVht{{Y)FT^aGK;CXg2Ekt~4dCu4neJa*nHbc(WL}MnGsY&;2Xa4}cDpb%lc~8q>
zDEi=4@Ayo0Qcm5gQNN1yRyq4l)9H%8?AaMS@%9*=7S<n+vnU_!HA=n@)!6;m7wXkq
z_>)y}^IZNosD`zu6Z2iUs##+)mUljen)oMDKYrrbe;m}G@P$q}Yxq{NzqIb0^KmEV
zNY_(2B+V!1TE{G1Or@PxI(sh)MP+ce2UJXgF~@4_7g4c|2K)HI1GRZjnTX}wel#`4
zJMrjiWq?uYaaPApv%HT}ZD&kh`F}rx(H6I+OEN;YPSQV2E-T7S<_-o0Skf+)b?ZYU
zim9GSqF899xss^gL)n_j>tJZ@-SRR9>{1IIO!4+8!T$hiZ~nDuT6mL3j?F~Ug5d^8
zr~d%LU7{>F$s~St#^nTRl$o3TpK_M(H1I+Sc1JCm<0tW&M(jSwgKkGBy>~i~jkJTM
z&atl3gU&kF&$oJ_%X2G+#^yX$l$|GjV0`HBAIDOE1+01Ys85cszk(!OR{(Vt&s@}P
zsddI{Z}xT2k9_Xr@xG?Zjp`4sDx>(vR$-5{kHWaKsW)LvH||bAAB`_*L39pT_d6Hy
zR;J^dqxscoHT^-){Cz*ub#jLGL+MR7G7;3&y0p4PYBK81#OhZv+k^Ip&(^3(bve#t
zC)TRzleCtM2*x|p+c`P?D~3%sb5v8BSr$h9;}3eLBNjh9vwyu-u2*XcsK?g2AhZy|
z7t(@8c@&LE4N!-S4#V=L;1BSo53M^C0KZC6O~okSQey@jQx8shQ_Uw@Rszj{-zL*q
zt8NZBti3dkwAV_Je4RR0Yz*d$9V!h+?x`cCYP@*%tnEl*-H$=*P8)%e=O;AG(vDX&
znXa-x8gV?+d-bI~sSI4=lRu>>qt=>Y96C}SC>=V|nz0Nco|N2nr<JCWkF89AN^msV
zRq0uwj$@E10pgr_T+?&KSPBo}OWu%EvBdx=_n`Ajib5%X3PLkVDSJ~w89}FGni+j*
zg~-iFy(x?-!luAD;}n^rwG;rE=M><?9D_~4%^2dC602@MG3J=d&uUKe5@-M-nngIA
z(@3RYxYO2}Y1D*fm4J~x?MS0E$c7i`QmX-uDq0!4;pG8}`tw~<u0}<38UWofD}jT}
zb!wff<+BYcv(cgOk?iEt)DpcZ{#`jEz%}RG+>2!<+L);{Y^87^0Oq74<s8%eymL<p
z^3iZ2QBtYLJ*WxAJSP~TJwUEYJll;r>O3lu-lbUbjKK0JoNkO$llO#Gh+yKRBjh92
zk|p`6%%?4ixIcJBCHuruTrTTkI{hidaU*7)erTJXaa~j;YKV#aCK~<jDn?!fC-HtX
z_UJ3$TBFZ2^wv88_r-6wFy}cn&S}ISm!=JLko@-fubRvis-A`&-Xu7s7|+(9v%N0b
z^Y3$FOQD-(ZlrgrcX1YsGV{e+X_264o1QvUHuDGhWFDfgmQdV9I2X&59@TPX9%7u+
z9^Y$adR2*rVpCOnffV+#NryqZj8aEuIFL5NG3#2eoz{pu)v<0ov4Yj>Vem1lPnolx
zrDqpoG}}nn!ql<ZOv{i44;<F)Hb`O($peE^C6W#{l6@<G?7BvOSdosJWY|A<ik8<+
zluUkP!R=dXZh>$qV1hAn2OQJ>%b*`vk)GOAiddN=KA5U<!eVd<&wA=7jTEj&Ue$r9
zrY1v=QC?<agQr3X!5dMk=JhhJQ#*Z6dWt4{X?Q;)brots(yPuepq@FeHcd(i8y7y*
zWgLM|iaqGZdFQof!ziov<g&IaJ!7!Qwq`aQap_USeqOaY^6s@-HQLM%tqt4>?T^gB
z(vyQth~iOBkbK$gSuu}Olg%j^9`wL!Oz}tu$MZ#xPfCo88g;vT>?!*JV?Yp=+CG(?
zBxK!u%ktxcTFnp3k<zNP?*jphgT`yS2{|}QF(PCr{#$WYgsSVos`qF%`N_`iwG2}N
zaC+7}s^c^mA15@>s?dUZ;)ow|l_U{QxB0iB?Nd_lLn|IutuHY1Rpec)!lZ$>N7k}q
z9x1@n0p^?z4ti1nAA_HIl%2{dC*)_Sr>`qOTv1ut)FN966pZ8_<yZ4jTn*5$&l^p4
zU}wo*ESamto)vngJNegv^V9@qwQ6{VFDq7+K;V;;`G1XN=D$v+?-b7xTaJ(KaZ)n#
z=};-d=BzTFJ?laW@(yV`aZZ<tZhh$tnm&g-R7CSm6vN+~(*X&{=87}vMrgPaG2FhD
z9(kt@5}BT8xC%)fsaK^pH03yIKrV6Glrtj+2bDRb&%HId8KZF<T8jy+Mi0ygZ(b`P
zn$TABEFTS@ma}u#rW*`X(t*^{3Q#%gRd5^)2bz$l%g0)cv-F^0{OLjOnqj8{R3Uox
zq`(6-gy5Xh82jdd69O~GK~7#f)BurE#0xO(N<a*_ITRtnkxJyNVA4jrjx$m+CKQ6K
zNfs2G)qS8ELl->Ku=#Rny=m_Iln+5b5grXEOj7hThx4Wbm#q#kXkMb6;(-xTfykw!
zIPXb}MjJ@yG<6+K2dx-5%|HMg^Gzd~P;hAvN(LRNK<A1<PR=N}0T>k8d8Qmv0Hn_}
z9-V0c=71MCq|erroYH5Gl$ggU!J=XEW{`W+oRYgmM3Bg$Y&SJC5zup0fx)R1<aMb6
z^_c^c)Ee4`LRY0>TYRnf*44S(gVPn~Vl<IRok>;=+;pz0!sB!yK_r3RxlOqkt^F{T
zfM?Sg6;zlOuC&{0(81IOJ;3i=hNIzg2hOpA2V4%-+bIJWp~A|WUy+W6wXhy(CZ4F}
zLIonV>{DzTI#$M|qwgX}fF1FU)tzk{ARzV0sFKiSOM&~-o-!&(6MT3dtu5FhLfGKq
zrn4KP&N!kV$c%Kxgzi16{E>i1ziN!foSLFecKHHLimU}*)gvJ1-xWk>xvt848OV@+
zw79^a3Q#$&gpAlPTG6-rf~Y7Y)%$QUT~v{ULRMOh)~74S^r+ZzTeM=CRl4Gn8C+A?
zbKZ~*pw=xK#g!NkaYFM>kYVsCtJboysPWpaTOO5A4DnX2_&FUbdOMj^*t5{pyK}&*
zm?ZjDt7D4nfyYx~!RLyJzy_rvqkf!ptyz>xu0U?4m^oT>zk809+R8^nNLzuAN^X18
zpXtYXXMe3=%@E*oQpLkm6*OEQTBr&|ug8j#FTI@9K;&T5k@di?gmcK9hAJ5crA&RQ
z7d#55u_&(JdpI<d9%*sKX3bF>3TfnY#W|GIM^95(vd{{0j2<a7%_^K8xjwWYWq@;1
zL^5hIz^BKZ-u1FDkz|2^nubA))ZAjCd}G$B>_RG%GsPkLQn%jbo8Gc!=#7s)l$gyc
zt~sR5NkP<9k(`=mPU4({4L~w*KD8ozq*OrT>rX&)R*cy@bf{k^Cp9r1^$Ya>01BZZ
z0&-~q>zY%^?@8SIR&3P_VUG0NW9v?Sl*|xCK}dgp>rX>bV~pmWyk>zG0O0*AOGN}~
z$&<!ET-Iug4h>w>n69G<&sM<|!I{UK4J2!Z(xN?DCI;R-j#nVm5{_z1RtC{PIqTM$
zAo;8E2`f$9`jxTaQ}Rti9L6aD?cSuA^VX`l&3(c<>N`CRCOf$uDlC!Sp|zhQV;Y%;
zC>&>WIb`*xZm4M8ibeAho|vuw01j)?X}4&s*<R%Ku5WcXIR_$xNL03r_ZQTln#5hH
z9FLd^-_Wm;=SW$DfAy=z^bK*q@+Bh-F@w^*FT-z*G2=$a&g|CkmCrvLh2&h(*uwFa
zs|3o>0897nn)A2jy1y5NI)Nh@2Dv$Uk;P*-c6vA(T(qu2#|NG&Hf|};$?Z{-gHUua
zq?&GNNT!kaP-ZV`dY`2?9QsnI=b8qQD)Y@ugFi}y9Mp<&QglF@Za}0fjMI^WRO=Wb
zgQ_sOQ{I#id)1R{4KTyAk|-(CXwSSO%VSw7%YHSrcAqK7VOeOL`cq8uu~gr*CXDbZ
z<S&Y*i;sG;jkcMsEeq&L9kJG@UJqKNlM*-;IuhSXM{F5w91begyt$S!j)XVmR26&o
z6=E}t9)xpD-*sc(JUT2b{5J#2V<1KeC+S{i;`>PTEp*EUKF*^U9COe3)+Nu0?``yx
zYL3en1CGL^TiIucP7Y5dy_~+y-2C@8p(<5cW7-vl0Sf;B7dRb_L2%if6S9t#U=n2B
zdMK)Lx{dQTa(Y*)+2eBDtogXTz+eHu<F$3#R*tdT`MmBuYn0QOR_z`5G8_*|^c!}>
z0FPt(SDT8c)`;$-1!F$yz%sW09C43Y<24@+d9$?6N!of>pffW$Tpntq(IXr%=Dg-~
zEe;T9(6a3+8HaK!F7w0kyx$=TgVa}|Nn{AlMn09BabjGR<w5I;l8-)Z4bbJB0qs@f
z)AnR3&(ggZXpl5#C5>e#hjVh>PEV~NoI%sr^Mm!PHrgcDP35d@&rEl(NVf32Y{M(~
zu<2b6pQl+^mCA3E7|EaxcSG>Sz=9+(0ze#^?rd}mOE~h#rcY{?8B9yRX4M@RrB=Gs
zrQXCc^v~X@Y-YMc3a2{}ewCGfs9V5{k0Nbh)K@2}_=a*gln<?P_qwynaU_i1z|^)D
zJs8UXi+akNah&G4`~7Cv600sq>yFjNMR$2Sh%GnraqI<kx<7^;w#|6k{{V|=rZX{E
z-bh*)S^4UF)#&Za02WLiOjlNxHumvsMF4gKr9n58s(2kcifByb=aHCw!-4Hs7tu4j
zY}}yZrF56K$>ot8JfFg_+D5pX;18u*n~uR4b2FK_)8;@}Nc(ft9%_TbA(JO8$GJ7w
z&ux|I#Zi4c6Og2uk8LJ&dl;PJLg#_QA6nA3w)ukhCy#SihMSiAg#9Y?b`Gkfj`{jh
z_KlRO*xT^kjFG_C5U$`(SL!RMxM!N&2O0YM(&-R=n$k4KUNKd*-9<FOs#iOogGD)B
zM?Fo9E5=p33%5DsRkXm3df*OgnYz|X%p@OpA4+HT-N6A)2==a?W1h!(p-P|H3OFnd
z2(L@FwL=oNIXE@qUKF~SZ(4Z|0l3d<^{X9zC$?Ut@sDa(xXo!}^4F*1S<(_oqFr6z
z<=e$q7h9X|;+Tj1nccI4ij{55cq5OcD%_|Q6KV)sZ%RyL&pV>xsD_q#Na!lSlg;Qj
z^{JUmQ8TLN6(b^dSR>_gS#wFb^Nbpv>gRClilyhF2j<D91(kj4&oz&&$ZhQ#jAx;%
zB61||N3~)2qU?l3Q=E0?l--eZ)#P%Q6Bd+_jDK3!(g90WnZ_98Ry<LOWaQT2Q5K%N
zMhkk@6xHN(R+XSsm5Z?_^{7beNY9Z>X54z#?DN5!sLnA}W;}YDbeYekSCsA;&OPY?
z5pLaT2@MbOu))v0MEkSN10iNP>qxDZ6i9Gss&YZ}pbG@#3T`>;nnH541JC0?iCATO
z)Kcf{@?!%cr^Z*_p_NYFyj3F7F(qs}Zq9viRb`D_?#*m6BXGltfZD+0IVx(4v5?TP
zr(4e@t;BL;AzS7i)uh^bgT%DPwNdwoKD38pd@9PTA|4x&NgT3TOT8PO;8N*3Wq?E*
zJ9s&%Zel1sFf*DAB&^P_PQ6LtM$aTxu>qqU550NbmwwP(Y|k0!Yq-;{mQ_{Vo;r#|
zm9K3wHwF5N%XoI2^!zKWFc(9U$?sXW7DI9Q4t+&288Kv@wQdu&){w!lb4wltNmn+k
zuD);y#dTIvH$`GVt{&a6**|u=T{7ju4t`Te4#L^W;GVU6i6g8CC*v$@TGnmr!vmUN
z5)6CQMmXS(YeCm0s<;8LaA*RXDRKTaPI$=ck?mSiE;&=jrB;vzQ=YT|pRvb$ie$0n
zd8zV7Mkyu9N<%W`kAuxXTMhK9%^Mu?QAq-o$?M*ghE{2vMs|}{Vv(2v4hX1SN{kQ)
zq|ON2#UY&qyo_<4^```jw}J_-W(oQN_%*3-Atg?EphohjBQ(SE?o-l|2|iJtz3NAd
zH#I^lk+@^hpq4xWYRFxzGg6qt$B$Y7#dx>%s?BBzZNqn`wQIaw^u{VCU9F#50Ohar
zVEHOP4@%~)ZC=)FV}fyBmn2H+K^2dwXv=YI?4NjZKpbo`eEjiS+I`PVbnjTQL}6ki
z7$erEx41Dk2a1~k*ofl2vy$2HcXGM)u4P%RW@z6zQ;gO7OYOK}OX3(7OK9)o$j9FF
z#Q<K@^_B=#j~zPJkK0T2JReHo?Wfx)!(%^{Z(3Y$OlKH4>p&W;;7O2r)Uo3ms=P<c
zAo^9X09+bi487_(7cmj*PcmYo-;<7&m1y(9#JW<n(=y1xG=4O$Hp;@Wb$w*%j548t
zIIn`Ef~knF>}jn}qIDw}b4b|-nhD~#$vkBz8(|-XR+GjTWl0zr?Ox?R5y#7WBaT_7
z9d$dxaZ7`amFJD(-9fX40-$daYElE2{8qZ-!FZ?fO&H5Kpte0MgWn&WG~f<de>(F9
z*EI$?X=)eMZy%8{0Q*->J_(!nreyP~eG#|f!lzJ1L;NIhQD|NweKtjcX3eqbpW&<t
zCz4Z_V#n0eGus)jvZs|&`l`cKS4i>RK5DzG1J~f5DdAZneaOQg)SzO#!$j7uG^w_(
z=Zy7C*Q429CGE6xMhI6>*gdQBJo_S^Up{#227NXU85~4(+_B#@8Z(MRn)#%5oR+e2
zsxTgzt`Ee+GA0LKO78XG6II+gusN<H#EXEhp5S7?NXhlX!1?T6m08Kmrx+rt6~V0;
zS0L3k0=>Uxb6jjZKfO;X<ug#A=xWQ1rZLB*UnYXNNUd41;(tL=u<iV*_NNnKv8fMr
zofv6aq)ju|G?~pEsRnx2hb_;sj>CljWYP`|CP=9$QZQ*hr5VYhn1rM~X~feF1Ti{&
zXw5D&#UT{Tq^=pGuX+f@CQUMVMFa7t0g6HNr-7PRG*BNK?Hqt<#kuKB0~ERAts_+w
zDQY)lQe)nVL*+rAN)%FcrS%kwNM5<6rvCs+GlNK><C;73Kon9aGesszpdV@i;`-*7
zJkoMa9S=0@CeEwCvVX+NVBB%j*1ato<@K*E@MM8?qPw|e$of~O4lr^#_pd__q)(U4
z7w?IOBbsA56spQcBz|<8ke|E<<6Cnh%djsats@#nbR7t$85DItr5wmCFH^-XFfmOG
zr=Vj;m^&*`&V^tjno-3CuusT-w42E1V*VzYcMAdF(}yOQWN-Rs{{VdoVVr_~=hmnR
z8?Q=C^U|R=A%66W_zGdYfOVT6@EUe~g>um+6ri>$tamZYNRDS?{_Q#3pyzdGDvBCN
zq^?*BO(6%RXG?sM47#~r_o}OFkj5|}V~<v>{k%%#X4Y}sQI+TBU(UJL@e1~~U#@Db
z{wVShm|I41Ladm3Hg$xkQcJEqGf|g9de@#m#2H9CE!9Z&s!!wHL!F2}8rR+xk?I@Q
z)Y6H-7{mTm<j>=sRmtaXr_E8H7wYUexyE||MWihcS$l}e;G-YHnf9pH_&+m>@<j0t
zr!(w(ql4bGbp1b7)!$@SZLnwNCp2=%O{985UB`}*kE>HY*8n`r2>$?qSDflvHlwAm
zTZ@TZG53{-ts5^19Y)zEOWANnahk7XA#+6Rn^v=o9rtj8I|G`9{7I%pr#I1LdRLP8
zk4c+LzA5KOz>*0k+ORW$f>@8OM58$FTv}(UYgc|A)TR>L>JODU!kh}rXYhP0%+Dd~
z%Nq0IGo17FrNFG(xz!v@;<-~h#?^czhXUVsr7`?L;gmoVPgcR|R96fzDMwx@av?lT
zN7U|M@g|7F<kI5Kc*=^Hc)ryK?)1o%j@v7p@co<@G0Q8j&V-EnQ1<MyFh01Wke6Oh
zbD|zLlW+@WiV5_s8TGmU0JGlWB7lX?HrE=k5Xy7jwp8OzWjQU33Th-ejD>t%sYw_<
zU<cSzr;9aLEDgp7(z*D!3_9VBOA*8L&3iOx({N75ElShwY&VECM?dlMz*H}*U&t``
zE^47YJ!uKWb*eP~0F=Sho9b9=>!O8?#EtEm$$duWaor;k=uKZEF|e$c7;{`$%R=0y
z)Lr*FUkTroxMiA50)AYY(eZTtb)ai^EZ^*NT&A1ln}Dow-!;&nwN=Ef?f&VnH<{k%
z=QnFD>`quh<w?l|Vz!o0>zrVopw`{JjkUylBV+xlhVMj$erR_g^c^d%jw_Q!V^W_v
znYn$btlV)^e`DPrxOX3VgxKB1ozd57#z5zEBt}6r(;IqJD}IS_<gzh*;}xl~%I9Za
zYOk$Q>dE#~GfE#yZZLXQiG|o_<x%fZn{)@6qx|bRV<~hkQJGH!@kxSl#TNlkAK%Bv
zp{#lC<numB4n2)#@vtpWk+N_HI3HR<=)GNkI_J#NG3DFyrk8B;#EQ-1S7N@e=5!5n
z0&rzh^r&Ujp;3e+o|TD{j<kg4qFC8Iic}(vC)F5?53NGlgr=#|V!7pro9bw(#THH6
zr>h!ixN^YmJa?!mb5QC@^(&Plri;arM;fV%aRag9kodlQVPOmS*EL3KI}~&>c&g?^
zE9I{v9M%+)86BAMo@tq*prL3W%^CKiw*r%#(+dkl9Qx7TkOeIz6u{Tgd5MK+74)p#
z6y=#~VV6IJK#a@OA%~?<f9G2lvF1FQ%XP(eQdfx#tiv4BdYX~P<4gmZZXkdR(}3+t
z7M+Y!<pG%XrvXY9osKBw7{V!pb5aqCX%w75p1|$ATI(Qh-QXPNxeH^q=?JdA)MYuW
zW&%hu-77y(P0%(vW17^Fd8#*Sm`Ur>ly?i9((<%-qobVC;8$AMLJ`F-C_h?JPQh_I
z(SeFl*Qlc%>DWS3fW;?TaNy#dfH6&F$f*DVkcxH!5;>(&N>_>ydem}&pb`x-ro~1^
z54Ao~4IQcDy(THborVIJ9AbgZDd16H5DHvzMoxI?N-C@&q*9T^DFT%6wMhtzwF)_>
zb)XCyml20zC>&F<lg%@|D-2WkQH-7`4rxUe0Ncd`WOS!>rN>$<B0PFfY2b54IHzDC
zJ!sq3q-Exl6j%u@pn0+r@y$#2Ntco`J*qod8a8DIt!PIxDjq?p<+!d~&{>lCV{S61
zrFQC_@r+jqrbxq6Ni+2o=y4!q-PbkpnY?)_o{kybBwkn|gpUUUy;<4CBCpNGc>Kpv
z50}paG;HUkSitwB02-cPE0w3J<$6@x1vwXrIe>&9qh}o|#?U<}3gU$zAb}eWw1xsu
zo|R(M6C;f0o|NJ+jK1|wdV!j%cknr<vJl%%F5Ru~>qzCdsmDsvEJZ7n+T-4upoKW*
zu3n7nJZHUEMI`gmx+zQEOqnAVQL^F3=}*8Si=YL|dYTmFYv}3xCz~x9Z%!l3Wv-UQ
zW)=sna=LqMzFha>x~l`bAbl&q&7<$!?ZZ7RJ88ib;Jnm?VDmsmJ--_9?sYUl9h*rr
zvhuj~s&a;kZdU|#6}@7Oy@CBIhNEqlX5%%t)*VM_6JnxHU#|kMNUGMJwUh(x_pK{m
zp3R4FGgV}jz_V-%TY{sSiRQfzfpn3jKGCrmT#z~Du&;a)+Kt0a{i4VS#?fB>T`ST#
zE3Hn3-tyzg+V}B}JGCR<OS>Q1@gX1WS2+*Ecvyb(Q<sjoH2D4<Y358mp*UYwHR+tE
zM!Kv~t9iP-C+gJz)wI!attPfMgOH*4sw?p0MaTSp+&9sO_*0kR?uL>sW|_a>RGUkv
zj+Vz((x<r*!>Ebm>$Du!mY{)<AJ(xn?+Ix7RLgN}k~E{#)|R0=q-BR0?OtALl&Cio
zrw{QN^RCrrBjp1)sO}=&ZMy>lwM``LBxPIzJt-|NR(KjG94{EJn~MF{G1_8pD%k0Y
zyJ>L#X5QGVjcW)zAji_9OLUG<z;o$Q8mnszkw^ML1ojnPKo)X6d8gkNSrSpf1GQB$
zyT8xRy+3C8dBC)|4h>5sK+X3^soR*r&1Aqu9`x+f0Y2Yaa5<?O9SOvZQWhbq5Zh!G
zB#q4gNGIFxRjvZa%69klr-700Lnc7L&22)jvz^g0R|mEdCNsySLTo~usH++KI*rYo
z(i?!;#Ya4wxX9s*M#mzb4pw#pr8FG1D*Us3Yf6sl><H%n09e$p9(k!Q(+!{2p@d=j
z)+<y5o$2avOmXuX6|+bOw<(GuY>G_r(wh@}#C7dV2>>-5fIMsurAT|`nBzYv6{RO>
zrZdSrX$X&41b-Io-j&Z_*I(nv2ijwhWaqf9H+DU1^voprsYRYOXxeOXt1jOlBdt^o
zlg(HIbU%f57&18qMMOGOrG8A4QR0D$2?m;TOVrR;iY@|Db>^3)A^d0o-KnOYw2U#w
z7@!8@ng?1AXcT~O{{T6ljB!U{M^j8juALZrR>|izl-x+e-mYn>ERs4SkUc6JwDRtq
zY9qTD2<uCcNsfBaRs^a^1HA-{(^auf0|%OsjBNB2ihghCX<G-SH=Os)JAgL?(`n2O
zIi?P@?jc87ky~K(%}1ZkgY7^LW-ZC5#&D*h9Wli?cQqhdmAej@s;z*=r45y+++dD?
z`cN^s;LuML-^PMy0M9g;%^9Q}DFEPpYIC<0A5tlMb49|!W|SUjgitanZUmiq=~GC^
z$O`ak6&r_MDM<AFDGX%?nj18f0D_&zdT1210OL$O>BO8<d(a@r$26Q#){gWHT25(k
zN%&G2QiI1or6+0$#{!TM9vYsciff*IDNyGXnM}0~HwxRdZ{7YltQgK46|ZH+d-I%E
z4k>C>OW^d+7~-~cmddct0M<WGrC-w~M3W47<knQ)qh{`U_M>nEG{Y(;cQ;zFnyhgu
ztT6)JG3#9<kt~~sLyUK<yU2ij;A0iA*Rk9yZ%i=stgF_~dQ1#U&N}xsC4mR8IpUjn
z^L=|!r<@bkltGtdT=x7bCR4YLm1WfMIuX=U3h_)v4y-bTyH-FTn%>o;%s3tE2v=<_
zQIv;@kw?w+rl>x(C>gG}BNo66dR6On<E2y!`qj%|4RupS6&{4=ij9VIj0%{q6vCWV
z?HHz1a5IW;81|_o9Mf@;Sjig2l_VcA%`^d0%(x_)jBrmKYbK4ZJPcKc1`qVA{rRg9
zaC6$Op5}AdwZY=2w?996hqX-sIj*>Fa!+E{d}Q-XWzTw$3@t|aCjz!+D61gr?NJV%
z^)$R@q0c;4QaU5B$p%2EhdpX(IW-VCJk~7L3I|$zd^j~2=A=XO3UL&ReW}Uvwnu7W
zoYR!^TcZgUNg4bq7aUaI!Rt{!Emq9YU57N^N^^DQo6@sp$ZHNNJXDX<>rCDA8qJo1
zo~P+d6a$Vqpc!Ngj<qVBeQE?ee~n7LMQalY7J<m9n~ITo3XV_mYRu7ILC$HMQ=Dd*
z?^&~SG3m7C=}o9*iU;RTLP4gEl%uXq2pM1u0sSe<_o<^KW}LlnYSEh~{vT?IjsXL`
zN(SMIiNVcKkz9{@X&E`~Phr-R6`M3fZA{M`)Q!b688rolLE@xN4;0L2-khBCKohUs
zJ!*Sq#oR5&5-I&^x^(8IP&~-L-(TlkxX9j&k#s&ZdcBF=Y01dQ0-YcOKEAbIN03XW
zqyGSTL)Di!75M%mO0q}PLs+B1B;@Bc18`5JPa(!lKzo||M0ZpoM%v+rV_FJ##t5wQ
z$@Z(3Y*`t71u|*9Y(EByb8(ysXc?(D6B!g>iheOp+D}>vQ5zJm3#%c)2O!s>cu&O!
zD9lneGB_Uf=j#zQp>H6GS7^fy^czK8a!Y1z>zAV9`bWVVs|rWYYEv(o+1<rB!;wjy
zk%zm>5}`Tfm_~Zytu$EeOevpgl3g}Ij{PYy(x)lM_|r^y6v*Tl23S+V`ciPd^zn*C
zMkA4Od8heU9qD5r<aDcO6_9rnj;eI-Q&G32S&nR|&svb%gVTzQt=I}IbSiRzWgSSy
zb5ANCJXU^QJ}Sc8=K%5VL86uPWET-_je-2@9Htoc&2)}c*9>?yjXXYFhq$2Q#L~Ow
zD*$oRtxAYSJJNtEMIlWzV4#sCYC?=vlnqtHwK7OSpxy<vO!HHsDCe#!qPaW_p7ko0
z&w37|Tb3A}*pk@69cx<HBg4Kj8B}AfH$c$g)$WXU6K#lm#1Bg8^`8vd=@t$4Uy)DV
zHR)k%`!sw26hZ60c6m)swT@z9BY{^VEu7-BuU~4cKy>R;%M{U`x%$?1#INQvIOe;f
zji)oicsh|C4*QKl+8C9KD+WJG^qYBvNU^(Q<DAz!;GI1s6JAS#TaTr5x7JNEgA-wa
zu3SY$C!uuW*5u)1kZwW=sM^rG4l)H$g=V&p9mmk*)}mdjC<pI)S0gncdq0<fflz;D
zyYxS$YQ}er)!3n3oYb&6xit3*Ry7CfQd(&3ynKf~q*p|+#H9M3^h<D%MpiCZ_oPvt
z)-YQkdzqAR(3+!j;(aE;F%S;^!zQch8dUePmurF)uPAF0eHJ)>i*YorG=^$^GPt?Q
zLl7xg6Ka}_uah9!dt$WZvx+`|XV$BjRFU%Iw*sJ}9z!(w`^43o9S&RRf}CtUPHUjB
z(VkWhw3R)Lb-H$rmWT$>r1SNrBQr+u^}U2D+dq0oHM9}%0xer<A%GI#41N_~`%zi3
z3S{P(h$Oag_x}K$XI>&8>MHI2q>&-setckK*10W1RousM!1ksCFCHZy!cVPHiZzl#
z%Ai$gZiKA9rn;XF_+sYz(dW67WLe0^dM$HGZAVsOn>>Iq%{eSi@4JfXVv9<KLmRMV
z1F3A+K@WrNwOc>6Y10G8O!4%kDl(3&+uOmOe-(;``O}`YI@k#=6<J2#de*wOYfFcQ
zW!oz7!xa<(O~Rb?IjoJI*EEs#$h-^=g0MVcZf<sbz%Jj`wXS6eAS%F&)<1~mTct?D
zgi+7EX;0!fY8)fmZIP6K3LJ6Lp9CA+AHt_(EhgNPjtTXvP@sx7Ju%H`HfE8hrR{_m
zgATnhT~41a!Z#D?Tuz&EWWCy;;0{f8R*@Gc=HOL88aD;dAY+=5ZW|Z?^HrdU5rG4m
zx_~MBr|VWhBuK>k%xXz3A}f%7YDkVwaaMe$W#oZUGCOh+b}=A&)q9J}h)W=oayMhz
ztu?c;$si9}&bUlxb8|q<_6+Tpb4sfcj5Ri2m%T$8?_={CU|3a9+*c*yDb?;s2Z7qU
z^KM16zH&gXJ=JFOFJG=#iq59Sv{s{S8-2>D@9A4ttTrTSe(0>76+Fw_o_4Nk?c3%;
zefv>OXig@2*r>!*Y;o3=oC=J-b5?SUkdi8_goQa3Vchf;N@gnEc%(ABzCM)3e2h}a
z-OfJ>iO;125za+7oKSO~w9$}HGyySTv``x+qZsc_P&W?z(*k*&mL2Jg)p+lcUzS`c
z_03HzqCdPc4{E73vP`7JFlvoriwzWVa;yk716q^FBB&I(fr!D!txXm5n}WYI%?lr9
zlpb-4U$T}w(h1$Z?kNTQk^SiD1&exoX42~+PS(J#k?mGgKP__0se!k*u0?fPRpMVm
z!3@KLiVSK;sm$NP(96c*+ut>%qUv%*AdTCp#!YGJnqZO^bzHEnP!>r#5WwdYSj6?4
z8J1|n0zQ>uNESeNt|vm)SSq0;6&S&;+Q#uFjAT*~LTe@-=Bs^_uQ;xhz$Hw9Ri(1$
zrah^Fh$A3p7^_yYv_L34dR2)nh#2coh*=JCO2BVf&RAfRpGw=Zl!o*IxqCTEvXU@s
ze%esSaQmmVA)OX?N0C*e;ZAzfZD;IyRfknzNuXsio0qLd@DRDH7#ww>fx)0f5QqaQ
zL6hFA%^y4i#a`MN`_ycNaX=JVNKd*Cwkm^=TW&e6oDIYrRcT=algHsjfXrw{+JZ=i
z!RwmPmL|bv{Hlbg_}n^rQDNL_9lRgTuiD%MP&3cHWtJlas#IVU9@MNCI%{j7$}o5}
zrxe?lo-32Hm@gZ?m8%uQjAJwbu_^`t=77Wwyi^cN=C3VMvjygu4Up%xRDAXHtIVO-
zBCEI?IqOA$sL}z(Xi2u8YK~>Yarx2|Vugkc77>%K>9NiG$dm<P&OK|HTS-vhjw`(u
zk32;Q>)NWF6;u*eIi%1W<)y2-@NrwqZRY7yLj3%_4|=(2r>gO{j=2?et<_;+)8#zS
z2bZLqS(m2Mw-u#nb^yWap0z^pRvkuR*_$<H+i5(0RV5uQwaXR*x2UZYV<6_RV4G)O
z&b4i4&uU;=W3-&qK%Lch$r7(TRe2*ZH($npMGL{UU~$&CzZa0PN9bRzcK1NY10Uh6
z9a~3_RSG41BIg4Y^3<!t1DbnUp9$>pI{0o_o@m7G{(_KXo|WDwgEa64^(;kCAB41}
zKQ+F7we|Aj3<Oq}XOsPpS-sCa$2cSMpfJY@=jf)rE<X=xk>eK8kN6E)T{6v2%L=c!
z70W&~!>@)6wUSS)k1YuA(m6lxgHo-n!*qgQ#SMCr+QhvPe=3n;j2-~|tD0PHzRfcK
z0I>VW@@Zg_6ShdopK(mbe@g3oVvD&5PzgP&BSg|4P@P%Oh=)HndisnuaZaWUVybA5
zHl|-SU)e`e$A@$`zL{s00>q>+&wlma!4g3jL|iD~3X0a<E#g?vVOOPC&INvDo#zwG
zD!=7hA5VkAM-L8FxZ}+L({o5k#ds%S$@r5CtEV5s{uRggkvChZUQKo0C~dl=C)oc0
zO62w6O`-mE`W{Cs;i7mL<@?5Rj6Pq&skr&Rm34?JaaCj-*V3bah!PK_S?atDnyrp%
z!i=vJz=67)Q6CZtR;H=MfRo;$YU!HNcA7N-$fWPqoDul_+=q8hmYyxH801^ZbLh46
z^MmF-#ua1AwIj#lMk>PT_pCl!Nr?JXgGba{{{Y9FfK>8G9eQi2NcE(xCD1iC96$%u
z)SvK<YD9g=^X_Q&av|brcQSiXTT%F4`Nz*JDeO6^m%>*BjNM20EmyOV4;e?f&m2+s
z*GfDmgNM66fTbQ8v_|>vq&~xnYLtxLHj3(VILV+cJ6BmBhIIKG9%Rf%`&FrL;EOkK
z3~tPQT8UF>U6K8vNZ^3SQZr5kagD=1)#?fG{TCnTQGHAQ0QIU#ycPCaSCi~;e4{uG
zTwhwl-rVS~uP%{imJqnkMJ~*Y_WD;xHnC%GB$54!Fj0!_s_o)f6Yf~YpJCFwRW$W7
zd7@iH$5>s*%NvpGhNN2yw;5YmNdEwKx;;Btn^2k<<F-Xv4&CFmdL^fYa<R)L?3lnM
z0w@*9ip0>ve-Vy3gyrzW@x{_L83)N{E<H_1x(=wv{yhl#wR=vfqg%tL$s{4es_@n1
z*LwZ*Q_C2BkBaEaT|9bjmqRMqol1WaDzAq1LVwjD_AOH<g>@$CU{mhKsZFn6^%Jl@
zm0h*HMZWdR5$r43SwxOUom4jy!Z&1m_g3m^LE#ornQ!7BO6OZryJqHN_|l8X*$!km
zHKNJ<$a&3EqaGKsOnI7<aC5-|lz4kaULO8K{{RCO$r)umWNKqOHc4aG)~#gm?q>69
z&#Bn1nc>LC&2a7YY6LzQfsZcP^<#?STavj0ij*Iabil16l|gkfmS<V@JN-6Y1l`1z
ziHUb%3ZC`f!J@g1OE>|Bdh#p8G<i%q)tmab2mJmu^gX+8wTZn)TKSG6sZ%eEWl8RB
zho9Ci=24GCjE-1i=~DjyV#AO1pN`tlUTMO<GFj#={iCbcL$RCvkq=Vu`BFBS5_D$z
zR*A(nUX_#0v2X2<*u$}de*w3F-ZmkC;}y<X-_3B$Bz7k}XSH?r>RR3XF<d3KVZLS0
z1;4F(S$;CDT2Go<qdJt-UWU{x&nCtsimN*na=AFqdVDNI;|)>Yf+h#lSJ`EA=C#i&
z7j<&1j8E|q^f;yoWnM$IDFuy59DADry{AnkdFpP(NiJp?*_`{;c`mNc8x+=yMTcS9
zpp{Bhav`aV)30vgy8{Y0b;WL7O?t>m;1BkNWLmPV+-KjdbyBLbbIwOK;pTMGl9A|P
zYF$|4ZrbRv-pBCoS$76wljblr(_Y3loMVpFhdg*0KZSXRQIP&%C+8-sTt_P@8OoZ|
zb@s`qWB`twRmIp$<K|tmGWt|RaaV7n5zhU~9Mv<$deGK4Ihcd+r;fDIN~bk;5iBjX
zWk02QFM+Qi*(7IbusN?bErwImo~F7>KMv}z7`d{zK+Vr}qQtYX@ul1?ZjtX&$F*PZ
zbWa|TrbQs1TIMW#E2!MvBkFf5QBLeGN&RcQx7lqH#xb|joSI6)JoCl2-)Pm|9ByNS
z)2AJ4g1@qs#^l2)<M@>OSFmbY5x&(v)Gl@oI0CW!W8vuTtOT);W{hx0Q&Ul=6pD_A
zmL9a3%_|HN2;>}60h;DC6m<8e55kg{r2{$-3^)?HXYY2a^FxW7(y(-E<g>jD;FUaa
z+PWr{C2i}_&`Tp&Lsiv}bY%uJ?@*{6s@NG^la48&9L&0P&6~(&*|nP^YjaT`#GNVg
zysvvIyOMLjG@BhyIj>(2FL506Ldm?0Cw}!JTDXsJXFj{BysjHK#anG}%!tK=UNM?g
zr6o0HD91t&zabToF#X}JUpgVyRQhJJt{qIosm*1Kl5tv>MKs6R?lbKJCbyC%iKBLW
zZRCSo+*c+S+_fy4tkO14KM`JG(01vqA`lse`~+2$)@_O%>f`<cUU)T2mHV%cr8Tu1
zx9c<G>p&gcy62SNx`}q4tlU*O^^qzRA~Bw%8sd$_%yQBb^)$mHk@vWyGje@K+6QNX
z1!+(5pIXnGR=kks&MWM-NbWsannf@sd)eIl(>eTVGb^9sG~V=30%nYwF-wX7P&lN|
zGy%mJB+vnxN_xiUqLcVjmI;`QA^fNUDk^hnI0Ts4K=l<Lmcy+e8%a*sXxMQ;4W*!r
zQ9uCiMHFIy7pU~3G=yWl6acyAj{PYpJkSD;xamQp08-EfmW}@aA19tj>087c^y0bw
z8Hm16KDE<hxbH|zsdEu%5A&>f2V7S4%b1U9#FapEk6P`+>WtY{*N!SYb5pYM$6AXS
z^sU@=5UMFfDvVO&nmIrKqwuF<leI2Uh<FsjKPq_`r2Hv3jA{%_hul|RVt;l!=D8v<
z`PWmXK5b)e{p*^duomT9cB+>se4+(ietH^$ZX;q3%m?RLt-$1`8)tAj6H$;V#nNn@
zhv`tB)!Q9_Z)$K9VwGyrBur9)#V8r2$0O36g5qL~VwB|KmmTTY1Fb2bFW2cxMLtj>
z>N?Oc4h=sX@zR@)X>y2h>M4YCQV=-LT5FDIuv~5^9Vn*(kwt(hdiJ1kN->_a>;Z~C
zl%R9gml!npLgH~j9Cf9}O)27<LL)TM)}M@;0KuZcad!8p$g3NEQJRhV(r9-h1BwM0
z#W)I903NxgcEunRb>@o<2P6toK5Wni9-KxW(u)WJdt#W;;P<J<0`5KN+`G2=&?2h*
zt?62J`0{q(6It$=m?*|uwOxmF921tuYLH~{Zieb7^kJXQy(Yx@mZ-pSit|%3BX%>k
zy$eKdGSNPrtLAgqZ6mh_E{2}micNquOc$*t-cL32H$4jsC=D}aO-w+|E-^*MMX-Jp
zsG}TIyJ;10X<SwqSDI@MDs7^Wuhx~og4<}h!Q(XBr`aJ){#46|B*BpwsrKttEQ`%>
z#n`qNsjo&Db?n_!H#<8I11u^@R|pMA>w`gD#%rD>6(?NA53N8r$4Ydvws!CZGdu%b
z2{_u~xtV>BJ9aoV3K4-;wG{c3`ubHRI5@APpzj2E^;f)Ew;^s+*Hx!5^FJEo5wR+h
z(>SiG#q!bg!LKVfgR*AWXQ`$@4r$?lT4bCxIaf9Fr*P<JNT&?>*mxjRm+>Tu9XSWq
zp^yb!<EMHA>d|%iYPniUNJU0~V>qcSlW1h;xv5JoIH_&8CaF(L2!hFTJ0l;I@(njt
z@g9?+%&|_6%)>t@sUbTrdUCwgi=86M?bb_+DCS|tSaz>#Dw}h0W*CL;+{90anktff
znLqEEr$3MM$v)+z=ie36!Jug4pX|6v^eIy=nP7+I(xFrT09@<dQAZ8VMh}Qqmg$Ie
z`Mvn555%1P%^`{RuDvYKIN7JijP==8+RXxtTE;zoT70n%W^&qpj_&W}iWu~k8_o-D
z;cKY921{UYazHq%HnF&UvA~Ku@lU;6LUYTGrnqwmudB+&)IKu<YZX1Ikj5cKamnW-
z)Y<&IRZE9;ZN01I==<=LPWDQ-d)KB73Q2HDs<Cq1)tuw}E1uTaWVgw>1@BZ+Ga7u&
zn$er)x5($(tFnU*c_y`uR-wqmH>y<VcSY@0RAnl7IgImIv5F2&JQ|OU)bMjsFn$O$
z=gClMjCiNxbYRc`l464^a6!d0Z9i`qrXov_8WnF!tC9sy{{ZTC)qG_~dJqU1gN#(=
zwz8Ac(xE_iRI?q(D`xJj28_uIS_U6`6_}tboKvG|RWQ9h>MW4egjImCCsEH7(ZJ@E
z{lz_f>45(LIvB@hn2oki=T73A(Z{6#NLvlf1+$z|NzXpC!I7G{=)mH9dkZzWbQn3v
z{Oit%<kziu#t%D9cE(Dsc<)|Ij0}2L=vhqp@Ugk&VwI*D?^8v{BRQygRPZ($y<~EO
z5)h82pw3NLJd^dR$A%)94xsg<9VyK~4I+-zyq@%*jQ}cSu%&)6-i7<Zhy7>)nWHoj
z>qmM(K9G!5{#q<xhRYtK6&Vx=lFn};<w+-Nam7iffYOKVc&hNW%Y=T)YWAfhGDeE8
zmd<z;FG&o~>N7}4sqHP==1q&~){DDIEo2JnasBFiz(6_aPR=Q`dQuo?Jw+MrXa<bX
z0^{YV$;C(y%S<bZU?+NZ2^4@)f;}h@qL;M_dsB$x8597ja5Kjg$L5}+1Fbdx06GRo
z-hgw8Z$VB`#UKz0N>jxlJkSA-X+iHzr3dRs0Gb5^dQxYK20R*3QDoAqbBd4@@M#Wd
zSaU@HHkUu0H=kNw)UE=WZ8&tMnqm_;>q-u3G4IU)VwJ`?diSI!ng`N@(t(CWA>dKa
zP-!qDbJmqQiXW{tPAe{@7Gpm!J*!sDu;V>Qtd%$;iqf`hWBFG$C1^Bk1C=!dvOFW{
z*i_N{$_V12odHKDo-2wEQo<c%${img(=~DpTkO(qDqB3`Ju8wVtcJF9)fa#vVh(*f
z*HU*AIwsbB(7{AOeT6LKnEwD;EOf<%gEu5`lU6Q}2+7A3$uTYfBRS%d$o}yCYFXDQ
zP}!2Q<JN=>*kW6g=}{Bu%}m2`9lo^_f)|`|R7shsreWjLn&%W_jP$Oe^+UqhIPYA~
z@g8$sxP6SKJx4VvjQiAU&u%JY7|nM<9P(qp;;h>aYPbhAW&!h8RWxBYp=g?8RHSFt
zn!_fyXu&d^fD_k>j{`M4hzQL_6n-^>M$u(?SBiviYQ)2eg9KJBYHXO`IH{rF;-Ox1
z{OV}<VcxDAihCBuc7Q5Kxo`=<rUUYdbVujKbwuTnd#LHfF!jf3esH}wrns$)I+Z2r
zYA`S=X;(hA4lr|A$lfC)<$kpR=j&D<p4DHe^sJe(6dZ9+UK*MXJJW#zk_K8sgr|<Y
z@$F2Hm8Yn~aa|EGkz@?7wMO9e=qc;Mel*q@HEhXlR&z`Q4)pmBX@h}^&6^<`rAPQ?
zq&XneXRSji2r1o9tv58F;+4i&LxEDM=An%Kew85Rw26$1N<La+50{E`dB>opwsY-T
z8Feek!)BuIQph=|@ma{)BV1s0sQXloIjFOP^{6yL^XX0;nobWiX9j>}l;Cqu=s~FC
zCuygV)6%UF$(NPpn0corG2W4fzAA`CcNod0XM<8Xrh%SwP|Z;r4n66eJ!(cdsOkzr
z=O0>flbT@UQ<PEybUEgw40DWUIR14Cb5F_Txd*jnU0$0VH)$T7pf>9W&U3jsj)t^d
zc<GAB@T-N>kp_A7JwMMivnu19*W>uu^5SNXsiUkB;4U*zFzZt>!No$}we{zrGA0<S
zwk!Ncil$CEtCoKvGo0fb3Z_jzh>}B=IHggNF;O$_W7@1i7$-eyS<@AEIZ&Q3F;WQm
z#wultAmgn{v5!uDYEH;gB1k@An$yxW#?)`t1Q{p4rBz&G(!B@arJQqWGP(JgM<*RB
zqOQXcHA<6_!)qEu+GYHakT5y{P(t}!SEPJIw}4%vqK(45?{3qIQdVNXRrZkP5U$}-
zGUw}70QJQ+hI>>Vmo3V;?MPE1r(`)ergWgq!o+4Q^HG?vaz3?bNIfb3TD1dI(=+~H
zc&X!`Y5sL9L6g#>FzwAC_Hv8Rw-w5j<chSCAsmXuF|r)?^{1u7E;-IAn^UjSMzM(`
z2aHu`v?Hf#NUr(M6>(-(Ty`{$k9I`_+=m#z6&29khZy?Sqr{~%#Z$P0_hgP}BBeic
z$}8_k5SlmO@=krJM1%oB=jqg$VdLpmp^bWzRTZSq9qLrxe>!H6vNR)AQJ%FqbPLCN
zq?y13)as+T%`>GlV@A8Ug6*2!@K+f=wYPt(-Ce`7<aX^`=9wzRFdZ^~I@!DcH%xJw
z(LZ$g?9!d<CTGmp>(Ev;+k#k*$F*r(5>=1#teGM*Fi?4B$26jOvONdFffq_$q-Qze
zx)N|bYd1)@x3kh=Kn_Cn??`nhgKRna*6j1;xh%|wA0{zXRfhb7gH|^s$}vXyy(>Cz
zGABEDq$6h5=#P-#R)Dzqa7nIe-sHOs@M}y+T>|El8EWF~5pbt*`qeolk%m_Q&|~e_
zG|BGbv5d5hjPNQMNRCU1QBL+IvM#T|ZMa<HsHMErWxG3LI3Bf5J1Jy;T9S(6ebk#H
z8?jruUVwK7n>jUSPqK>EFzhnjYQ^5Hk+1H?9CqzY3;zJ<)-gBT1byx~tjmpNNt<LV
z$MEr4f$nt+j22=u(z;zcMUDu>(~Nr>1ZUe=U0%Lrm6b<xRxc$McI=jx?DBg0)w{i7
z%GG?4Bx|?O*FSOMi&2n}nGg5JK|mR|Hrj>bZg}=*nxig>A>v0|j&Lg6-X)f7h@k<8
zezlt}p{UHqujNkQDACa+3|tHzGJ02BHAT15n$8`pSuw$`Qrg<$T$y_I#YHu><+RHz
zEtO76o`h44M46+bCa!GQM6%0?*CcxS*H_`)VqFGF*fDE)IoMA_-xcSr;%_76lGK?o
zoPot>&El)MSgP9`V~kertXyni>|~kR_>*0SQPkRa^10(4wNFdDihGiw_a4>B#dS5%
zR%>|`y~k?T@cdE@NS9ra?EoKI=4l-X$w!pi)JTp+QT^)V^~ssFB?!l0UX{}7Og`MG
z56Y;#d*s$d*ON8Dd;^X#Qk{(CW5e9{r_7U00a*Ig#<fOYlZu8H+ix$kVy+(ah<YN%
zho`-}Zjg=aa%;2Glgur~26)ADwsMArPw@_>x*aZDhQR656-oQ%u0OlE&|AWRfIN>{
zzrue2IjppEjt@?idMQ9%uUj*muvve)2hxu@SDKCGLcI-Dc@Sp<fl>sw7rAYV$I`Rr
zMw8|&ed^*%8vW?==~eC}Rr|lKA(@k|TLzgP)il|zP)U-*pL&Si!Te5&-&$Z=ySiws
zq$~Gv&3UcVjQ3JA4oi16+3GrsUuASjRF)ON83Rh$`F9%5rl$0CIvpAxF49RbL2mSu
zw?4IIGGWtEI0pi#NclCY(HxZ>=Gg?C9zQCFJmQ|`ImxKl{V5QE$icv>Q#M!dt4w}c
zr8hK&R%bb;WFKmC_3N5u;%FFT(hU9-xH;z(cc2FXK&Qlicn@A`65L}PRQBnSyPzFu
zp`mUPIS*f&t0-uX9Ey>%yqxqjgmG4GknqUs&tBBWf+rlWKBA47=|<8`A(04tvNoEK
zg>i;neP|)Rv}Ex>4G|`Kbgdm4;M?B$VBkAv^r{5=QmbttvxfDc8oB5o8DqwIYUQ<k
zHKUlyxIA-#Te>yp+O1WOQH9T~Uc0hcp(<A+9OjwFC1!B2$YWr`BD!58R3Vfrjorbn
za{AfquDrJUzNVJl+6+E$eJL<Ut!etIG6d?r^`{cWa0zY)wRxVOsc!>ofWxt_rqfdS
z1MknZNF4;0h!>7(q|pF6WALN<NJ$caz#MbMS2qQefz(qF<#dg}tEo6pHk=yAaQpXl
zt1-!yQJ!f5(pcX9@i!6IrEh?*7+`wW6>k1qfSTy+E=g6-Oi)p2*Yl{sbz(bIvM<e^
z)M0wi1yHy-rP>cC^Q#O2UwUa!R+x&f0A}6zRBa9hI+0fKj)RH_<0gP8HNVPDR+iIf
zJq~><RhQ+*YJl=~b)ZHC#kZHybDv785QQJsx;bD6u&n9rK4LM?wE$;E2w-v2wBebK
z1DqbURHn~*K+dcf55j?)(8vf3xUB?~O1LAXb8yP)Ps~TsufcLu4b9GJ0j(T>Hq+}%
zC_=ljRhC3zD#|*Q=72NgQc3xE%|ZbSfGbhgoPZ5iU<uvO&;r{o8}-dvWI3v9aw4gg
z>_~V&l>j^)y#N%+n0ahZOd3*nENZpPq+7|3a-?xU9(8`3^$8!bJW@crPX??=1k<_A
zIygc$O+y)K2-x9GY+4<-?rT0Z`>o!t!N4t?P=;(I_&+s1LFOiVRy?;mNDJS+Ubd9&
z#(K~MR|*72n$N{+O&;ZMrDYM0JBs-n{tZ=9J*>W0g@mQ=MrjH3ub({t>L{c?Ps)@~
zFd~is;(^5(1oxm0e_hks{^A(IHqhB-ABPpKXJs9gvc!M@2TGi;Ii<~a)W_DH2++T}
zjMXS9Idv9}b4N6l!e}iaJkoPXo|Gg9DdNlxLe!qUE11>(dsZCqGhGjiq}zFG)A9cR
zKU(MS_PwiQ^R(CBWLja-;A8&)h|WVN9+g^7Pg=5m^LlPI1b~BIQxnf2J!)k8wGU2e
zSo#`ZM#Gay9ELej#tze*9+c<fG|u!`4z}OK>l6w8iU|X^N^$XV?Fb)A<|5CR{VA=-
zTIQ)nHa3k(9i^X$WxHX<(dk-=dnq3=BzspOq4JE(dCvm6bOB-9Ys;35=;pa<E2nur
zew67X-O;})tcq|*8O>_h>4lE@FitayhQ?Khv8!;$l0{r=MGMN}mLie1-_n)B<#7Q&
zDHV}_8HRjgf;jiCmF9^PB~KkqbNaN)ET1PBtET<pXRzHp@h2ym?R56rJT4pN<C@^?
z&+i8~HQL!e5*F{cRn}L7Mlkr1*-6V}Rcn<GYbeJXPZc>kkqGXhn8PUFO8mmFxn266
z%yvF})~!r>#m}bmf&A+!<0Cz5tnodv#o`Nr+~u)YZx|W$uhKA&nv7ZIRnlzO@XCai
zHvZ|aZL~YAVL9zyC8DuR;PkI((;P{rLix^CzI%xw?nXyO74A!U9{VX&kKyTF1+By)
z)b3LUJNlaX3Q?F`9^$+&#n70w*@5GB@8`$$uC5EKYO;ZzJ$siqryO%p4z)C&bLmiL
zKDGLB<B}fSQ=>lA(TopTbbol7V!0c0pIT`(BM+LGdeQ-%>OuE@wHta<)9z3*#jJ)q
zh~!g(j2oKzCrW=eNVZ}9-|(-TP~hjDmGlpVrt`c%1N#B=uZiO-Y2j3lOD}%&M%whJ
z^`<GOfnSxg)*8c_YYeU_?M**)(14?IKXSv`xG5LO)SMh+b$SfLDtnsXwO~_Jaf}g)
z_wspPnkH3tEDj__%}ag(3TnA<=#@3e-4dKv+vPLS9#$=0<u;{^?K$Ft26I5**VNCs
z<3JelNvI{}r)(V53@MCcL@dfrW18zwtd_{$)yI>yy{oCRlYOFd+PsX?H-eGff_k)O
zUoTq1xEUustE0YLv8)S~A(;BtgpWkbam`nkg{x9?Ri3E{obIa_S(M}2vlw~`+SQ`V
zD|&UTX0KX<yb;Yk#%7dsr2HrYHK`+?mE>_<mWQfbt(v4~<p2N&rE$lnd{<xL1s5<d
zf4!au=TRgEu+(px_}G1EP37C1mvdSdOBJGzkjTfiR5$7Zl($}b=9PlvK6TR$UH<?Y
zV+rI;9FRvtQ?{njsm-!ywhb-5sT|U(GAiyPBRwdvu6ee-Vl6cm*f6Yf(}HU(bK1K9
z02;;x@&I^k$Bxy=kU^~Ei%d=^>p&nLquYv|Qrr*TJLk{}Rx0F5Hnv+8)>#nt%EP#>
zejl-h{{W9^rf<a8MPO9gDOgM^pSr^oSWLAaw|ci4G=wfHqMmB~s|@qfgh|J1t0lIi
zP8bvXU8^mwr8)V@{A;w;ZCc`Tep08g6`0yUBZObdv`vjz=M3^6<1~evv8^d|SrN&|
z$81#zU@*Bx?Na2%L|C5m(!`#%AWy=lj@4X_1}ZOcl=DVwU;8>RGmO(#(Fy1&0hQaK
zrv+osAIi4U+A)ldYQTXukCamboe@ag5Sn<kow`PAcgR!+j<qrZ695t^0f4%7%l`ll
zDn-(68w6sy1q==d$JV3|l^m`<qJTN|(WE>V{Hk%G41Cfs`U=+)M!)jW2mA_=t}WA-
zokaj=E{6(_nV9?M6r)OoPu<Vftu_6a{{WYOaoAK%s@V>V=jbQ`oz;|ZjG~MhmeSQ5
zlh^4{-0DzDpdvO!MGmTM&j=2B=8(<E?I8eV1xjLxR~Q_7RtxL0G2$cwqHSt_;Q&wu
z?bg$3<8Et}k^W=FS$$gOPOVhhOwa+7&oqSlQM-yv=70iew7E2bfs6S5lxH0&4K8Q^
z$uv=(Xvm-fjAy+r0i^HgKn5@mG_-=3wrB$GlyQE9aBHqb`D=~S$XnFTMo((&qx-r2
zX%fiYN0xEcu<lcAtUW8CZZqDn?-vr2U6@y?oQfu)+k;b{w8AT~qDH6y)3HhT8gL(l
zRe&*(O~pEa>q@{k6w)}S_VlD96%7n-0Tt2dF3oP7j#M01I@|+Wnmc~wMsfA7YRIdb
zO_HLaVU_0<F&G2Vq1%=<%m+8ACN6W2ygJoFGC8dsO#;e2YdaVRHQ!HEOArG}C<7*(
z7v?>yR4afVT2OIDC<7g;tO49o<3CzaMmY7SVE`1l#USfNFdO_>q{lSkDG1Fg1;xk8
z4K$33ct0*EBP&Y4MmVPd^`HuH98<6j@69a)8dFZea04ctjC<2ZYIr!s77&=l6s*~#
z6zl^}T4~KZ{pwISpjQ=nN<+$2k$@K;jVq7co+?1Cjwwe&Mm_03%>@m|y(<1Rq;pCJ
zN3|9KJC4-(R~Y9$^v*NwQZW7AXt0QKaDOTRA+t^^?MaLg{b;bp=WNQ|NcF2eXfh6X
z#X%}y4r%D40QaoY)C+5pymhYI!n27i(SM0R6~scscFlC26S;J{l^pStkIKAU@|QIZ
zZpTIvR+--~N($~hDIz&gc&FmNCFpv>6#!9+aU60uqaFKH+y>%>2RNtTW|Qeo;t_@k
z=98%FPhpyjoC;SM%Y+SXz#JOHu{$ox=ZseI0!7>FSu)$3d)%s%yP>aV4N@--;Ufvh
z-b}FP4aGbFV>HH%_J(|qYIJ!3`d0^`p`AQLzG^%iel?<5S38H&s!G2$dsj!aa<#={
zJ5XH48=w`KKN{J-Oxm1vtaTqZJlD`*<$6fruD#$R7(HvK)1Pvoz~Z@<9C~}!{*q6Y
zJ$)+-$~UAuJNJ$G4sq#Hp&0b0Z4DCVt|?>aJJ-ue9*H9W<7*zh>Kl;|P$TCZ_S5B4
zw~8)e*>4#K-!-#Vrimd@@{VfFsml;*uv`pOkZwtV1B%3Bqy%0v^O6D0ZCXejM;|Fr
zezlK2M4`Q^cr^nS)G-1FeB!-4x~yqU%1p|%d6kj5oHzp<)a*xGcC0g~@(7ReJt}!M
zOrq_8XX{?e%<${&9KTnQsvT6)`Kni_tY7UCar=Sw%?D6?aT*GTnqm8g)#Pm3x{3b&
zGfcl9BYV~)dZpBJ?nH<Y*o@S-8m;X7N>HzCE-RZ8n9!+8QAU*L$vc%tE8djCCO<Yt
zDY?k0V+62KUpA^ZUdLHNNQ74fLEuuB{HgN;_J#+oAy5T1ASQ{POK+G`0L=*t)|(lX
zkg5)zrk`k~a*lb;T||<)U_yZH!RDU{!D?4Hkb#Ot;qWUqz+OQ#qK5n3XdE83AP1#O
z8U5ZWK7*w?E(yg005E;16oio2p-xROB$u0Wim4ggD(GF&zZFtG9D+><L7Y^r%sJ0A
z$rk|AkZz2OR*8V1<{mkydaq7>>SzEdvmb>-!wlW3I)OTpVa+qBJ*n{JqQ|8rNWgWb
zziLo<z@>hl)_@f9qM7Ya$I0}jA9`pEzYs;{>9P!SjAU1gy6ljzBiPruUm%jr!5sDD
z+Pq&^gu|>|FZ*5V?YMre=(zSg{9JWRsZWdV)L{Iy<ZLiC^oZePhlf1%sGQ-dL(5Yn
z7(F?rApy-P>7KOF^rh-LPytA2KaCwtFcfi0+>W%+b5B2|05FVu(Ta8{G5-MSqyy0L
ziWqU8^oVe2`N-`+h>7(ShpjlN>sRe87F$Cz5Lkjh^r@S$$TZ1}S84`+V~Xi@8+4Y}
z<{4qqxoA(9GPXK3b;&22r*0#hW17NuQ%q+bS7{*i98)oYQp|T;IqjNZ70?8D^`e}5
z(jEw@00*};q~OpvKUzlVOaL630`NN1L8k`ir2sb=qa6Fw^O|o$DFGx|JQ4@in*GHh
znqOW!Py-GDqy~e*{U{iq0lHEgeiY-yG>i{w09;U~2c{{sqJf8gDGfOCDY&Eoij44h
zseg`|!v~Of^{HSxxA@X^rzql#98zE~($ILMrEnIL8Ko4U5-EWh;L+c$DWepIDB_Tc
zQJOKH^Z?W8){joPr94t&){_D^88iV(!<s?BtooElyo%AZY=Aq~a_1Ft$-ZIy>l{M&
zK^yTLCfX%ZRN!+>wjh8<>r;?RZU;5xr)Fw%*Y<Nl=1qjADcWVz+uW|vob~?z>sIEe
zsM<qj@MQVLP7X8ArE+TICVG7<vJU7>^y?`Eu@6(tKIu0`Ff-WJR)cls!H4UPezmzI
z4<tt&eQQDva^R91f)Bk@fb5q!z#LYE&jj>5^{N9Z<&PjzTZ1;o%?LQ_QJy%dVjG|g
zYBpS))uKw5i-=A+z^-Cd+i<{v_*YYKprZ^N<E?X3t|xZ>@%*c^3}sMi)T_^K^&0+0
zq)=<nfy*LLF^ZlJqqRf;sbb;9bwI*p!NB&Ww>cdRNrUP5Qy6pBw`V#lNHPx<7C5Qo
zTn@DX>-}pPBWSWYSBkBUYSe(^wO7H(tYo!1A|M#4P<+F%rgzOqoE~}_aS0a}?t#rY
zIAKjw^3#;yj+N6BmPOS$UTGiNmNAtyjrrEcIRu?51JAWslQ<{!s^`8dDI36Ri~&%0
z>G;)y$*Sju_N<wz4z#Lrd87iIIHZbYh<Qqse63K#cs=TG<E^4$BE)Cq`qNvAA{4F2
ztqi)A++zl!{3=&CsHz#PL_g%zY;)SB>a`KzR&2B<PSjwJ#*6{hgTbj8JbBs(!Knvq
z^zTtddJjsNeci^iiIj^G{n}RonIBF%Q_nqXRAbbyAjL(VK&hXlLDW=8+9O}}sIiQ3
znwfybLTff?g&(ahezXCRLF<l`4U@)u^c4K$=bB`Ejw$tM&624FM`~8U&%doCV-&4a
zK?`^9QJ(mz9AuwrjfOsz4ABf>-l8=zIX_B>^)&^c{3%w70VCRw$&;sEYD4{MH1*=9
z0DwoWO;3f2JDu-@&g(!2Vo&p~j&65ngXvtCgQaGR2con7K9$$VGCgbZOxirSxgSx7
zcczb@TdDV`PZ`Zj`0PzW-Og+34^CqU%M5p`hvbV3RWpOdT|i`2&w2$*ayZbp9<`|i
zdn2YnZP3-ie59#op-P>#Vtvpl17)fMA!FX8OoPd!bYA4ZWMJ`Lq42saMLYihe<X2U
zVHn>a^!Be~_-+v`7^vr*gVwdCwLI+3r!6j1FUER(&BfVZGC8gS>fPaOvH}mGub_1=
z?D>94WQ<Ra21ZSJXN+{w4CYi0bNN+Njn&RfuM*=vMsYY4fZ)^EVZEu1#d9B35env^
zk|rY}rVKu`^Yae070b+Jw2X(IzLh*zKD9iy`?7Y`86aeCGCq_TN)m&*G*VSy0pm3$
z7tmHZ%F27ynC@~0Xf&r;JsEZ3St_&Iah!8grNGC0)rE9!XgB4AjFyP2d(e`!Y&xH<
zYBWgQ_^4#F1&LmUf<26uu^Aoq20K*3WN-mECaRk@Q}T*$ks|Ytr6Reem6|Hf7AenQ
zPDKeSgTNGCBW@e|_B9$O%grN(S5jqxF#iDS)7DeF8-E&r06D2p=dDoGiP6~fCZ}BE
zuUdfxPKSyO;$5-|vjW|ZYS+1UnR}m6SP^F`-j&f?{Ll>c?^V#?%xT^#Mti9$%Zz*0
zct`tWDx)Qux1J^c0PEFzD=pfre2zOFm2lko`kEuMw=ON$cVSfTA`&nw!K=3us>Y~3
z=;#GfQq26C*`9Hh)6Z<-vcz{C>dNYoNV{Jk_a?1L402~H&uYuMu>^dihW4Z~+;XD6
z<sgr0oL(^Ke_H3+q=(j;Zy0l&d(@2T<Gsv$o<&+sId7ue?|^v#_pUGdS)&*j&#$d(
z=>8zs!Cp-LdepLw_0S_+Y*0s_6q8t+RNNQw0<Oob#HgnqHabxHl3Xqv06k4e&U$;f
z5bRD%aZ=f6w^!^P)zLjobh=KFr!%zc``7nuf%qD?cOCu=cF~|7y@fFqAhWX5A{i^Y
zp*X5@>vmiGxu)aO6s_T#`?lRZ$zNqWRFQZp!FipGpH`uW%bNE=BP1&^?}~+PG@?RV
z+Gn0HyjMgtEgsVZLY#W2s&{&gg_tEE%LDu)G=^u7ErwRvSB|@SRd+-uXhDi?&aH89
z`yz*8{SP%}1>S*(!x7CXI~!7`%*KmUNcUq0+M4#sB9OouxOq@JR0Qokt24INGbht+
zrC?bG;nJ%ugfTu<7xJwM&c+Q;yKWw*r56T<q;aqC3YA$D@Qa*qY9KS5R3V$r$GuWB
zoK=b%t;-~g=Nt^;xu3POJ2F2c=V`4iYJKu!C()}A#z_a?HC8xVFFvaA!r38QbUw6c
z^T|DgvPg2<yACs07g5b~B85WVHZnacr?IqaeJ{(wB#>}=*7V_Tc!tZCavvmQ*GZ(^
zBuLxYSAcSBn72Za0D6k6t6k3plle|pjCAXo$v=GQYxiesf8!lHP9<cJZUd2;z`6LX
zX%<XLyms4OQ9RR5?9)3r&+$|}{VQ{f^vQlL+%|Svy;Yauo%@W4aqJCw@Hq9S6M>pR
zbG3ho`k@~zAbm|ypW+U$IBbwJ+jVkm*)-hIV7a+Bi#3Uumbn=81B$68xv9$EHPaA%
zt2;Din67Q;_tVLA-fYa<x>rx8!S>7LO!7{7u1i8f*W0o8d9L$7jJ3l_w;OxZHFj*J
zXk6C5#A>J*U=G!lDapvIm#$i7?xLtUC+7Z@qd3UPrV>G=FP<q0%I1*B&(^9<_3Kke
zcO3r!Dy<`abOIo6z4WHzno``-6W7|2LJ~*TkYt})Q_nPQ4Bqs>a;E0?r^_fs*eW-W
zLmoP2t22l1O(NonOu6q$B<)Zhhng^YgH&o*SM{fd3_8_N821E<cr8H7A@j%SNsxO~
zDsp`)P)VQ%Vt@r8C;tG~QYK01KpPrG&yw3S@*HvLitKG?7b-#M-7#D}f|(@>oRPs5
z)7wb!ZR3g#YP*&-O(8B~F6uXW*Bf<j<U1+OduF{J8MnqkJ$-8@R?*g5a_G5iP-U^g
zM=6Ft>Uqs{7CL~JXbpz$D-LK{IS6GceJUk(jl(G*ik6Bym@kewI2C#uyth-$arRn)
zejlxG+FYxEr>!72<33^nGoMPc1U_fBDy5exyE*mEYQqp#AEg2ws8_G&SG4K;sW!3s
zeGNtBw>(sWFbc3<lnmZ19x%h9rT|8HsI8?kMlg8mPi7PhlrhE)AzYrd986e|gZR|U
zIL!hfWFU2=9+{xF53#7^Y!FvGb*2QE4f51SYMw<(4oG1`1wS#M3aq5J6xkxm4a8N3
zC`rMnIo-_wQI_8ab~vp0%SPQkQ(Nu^+<sL~YhN^Q2jf7D#h(ko=A}u)DC3_&QcG>L
zec!D>B4N7&y&yCom~9#2twDGD)s4EILw`!mjj{l4qrFIE3$*%orUv@BVZ|h{i6hGJ
z{c4;Of(AR)<dAWk8bdQCiPRn{1(#vsx23jOl;f>tUD$<-0ZN(xuJ<g<@}4Rft|WDq
zH(sLynqtQwKQ9#IEgY&y&#eG*QX@e;ibgQ!`PA_rGpIaPzQ3m+adwE<Yy*y!oe@M|
ztw_m%+6Of%u{}HX6&kK_v!Sb&sB@Ayq%u{7SwU{J<vV`q;8fCZ1wpq5+JG#HvN2Sq
z0cCG`cPjm9vkbVepU>fXDqd%&m&;a&=`-s`ew1{tkv)Js=M)dE1o27RtpEe9JL^oP
z>xuw7&_x9L{*(n~Jq<7rp46GCJeNHMA7zz>P6y*gg1HuH0p}yNP4<1fyr>7MHIJ+6
z@YzPuLffRyGhH+&&a{+Zh^bLUT;n`lekau90A(Z3^u<(|`Ig{zD^O}|U4)H-dSukd
zGijeyIIqyK6n%{t$FcL+ne$HPCQr=3@y|-HFAP7GSexazll|jR%sYzrBeBX>J!)9F
zQ|(a^QbcfSfJf_5ky1;Y)e)ow@btwboMx69Y{wbqvaRr!1ETQkD)5Kvl5<@S-P~j4
ztbYuJTMlqNYisRM<IvZUQ*)&kt)V4GdJ4FcHNUA}O3kypLfZ@D@vUF87G1&f?kgry
zek-_Tj03<TqLK)_&FK95)_J#;e(zCAqE3&TQUgXbSrci;=UJM~iY31E;~teT0XbPY
z^s3sE$tAuSfF9LQ_=PQuyJW<htFE&pZH9C5*BKm)vT<Ezn{ry;2cA1uM3#p+-NM_f
z;W<BWQ^($_+H{^~of-Tp$9nwBFpnlGOU(9Z>lAqRjae=A#&=Q!4Y~a5m20SpJm$SW
z#M))G-lX1iN<#G9c&<-T&@BA2P^2f-R=&S4#;;`<oOP+bX3YII?i68`3!hr`9S_AC
zQrSgsCCFJv7_TU8Gzi#7bG-H&a4S>8z7kDJeY49Xa&;R>#wznVbgNPQ>#__!l0BLW
z>sz$UGKmLp1$hUL;bhjco(~|3^luO7!$gswb}yb)*!B9?74atBS5b;g@z4t7;iVc_
z-dH=PRyAIk=Wcf?s{XZRKtMSaT#EflJ02MDc%?&wO#_3)3J!Rx0c9UHX@~WxCHuqE
z)}tqy0SrB9$lodNieq)B#(zpf9uFL1z0bfm9(RVL=PW)_evMujqoDP#V)$n^{UM?!
zkj#Ja>iKRfrO$zFbUUyP)eh}VKB8046)3OAne7N^xX7m(LCqj5zZ{-%Tt|pdCZq_@
z&C<J<9M>D-uw!JC10?mYXDF4cSkAA&QD2(eani2+`)qm&p=lv|d^cXaR*k6!7E{;K
zzSAt7n~OZ$LeQcI^Q1WZsn67oywq%PYwY)eXN0tqLKDZWM8n#jNJqU0Y_99YZ|RS^
z+W_>eHWja=wqx6z8sN-hdPi0f+C<l?NIZ6~e(VhWYoohgmp;|c-Y(vp*Uh8UG9(zP
z@(it7kaJa>627%aY{}G<FrBr4MhUK#@i#)tj-Bh9lY)Or^zg3nIqDHL9q41tCUadT
zV~0xWJP|(Irj5xQ;Z1VteKS||Sz0YXZD-nXfSt`ufb~n=J#S(Q=CTpdf##u$Mv6H0
zJe!CePkO>@i}M~*IoUITmCZ~BputPSC-TK4BU()!)@H*w&!BpU_;SG)aX=4dFU?iA
zgHaa>!acA506iGwR)y81_YomtrGd^nPzML&coGTi!Z08o>0GQathX@6%1CAd71wy$
z7e<H7UAXQ&Ym5)JMPb2K2R@aYi$|zw`c9Vxsu5=!9DU-v)`V92YPMF&9Qy1P&e`j*
z%V>(Av#+H#<69Aqen3tECZ9Hh*y%1UVO7jf#F*sZRu$@uuS&_6#LSJfZa(C3Qb&LG
zv7D(m=N^?VS1QDq_p6W$gH;!io+{J_C!f-!0&Sz*)mM=fYCUFuvfG(P;sL?I!LDvi
zT=q<ldM-0|Ntpitchd&2btv}BkW~AMgz9p)Wdqn$4|4M`1msZI>>`XcT#k5?o%K-t
z-n9dDsRM9oHsNqw{sODL{kC#}vsp%yngYhR_Nu7)W2G9?j*+M3StG4EcoYGB^?Qfu
zw0#9abt|6IwN}L?08H1{FZZQm^)(ruQ`OJsO~oOkFx-2ZLP?{w6aZ$7^GQqIfDH3S
zNurW~7c^&@N+=k)%>eLd{Ad`U13r`yM@mWnS~JZQPy$lXNk9cJy%dxHx#Z%Kic$K|
z0h}5E;*yuO08MIfbs6`r;@ED48sQ>4Wkcw|*Lh~e;70WnnG9D#7b3BB1luE5L`NL}
ztW8clo;a?IJNL+DJ1!}Nb5l1J8OK`m>_C|3p0r~W;3&laG>^)Tl&9K~fD^C1A*D2j
z9qL*rZxyGbzc|fhky;u{e*C9SYnrOiXHU-FPg;+;ry;_Qd8YK{xdvnE%0b+I=;Jk#
zM>wsmSu-Ae#}$l0;PkHQKM5>g7&PO-q$FppEo_81b*0-)9G_~Cb5ux}%_(1%PDLDJ
ztuB62DS*sS1}M%=F9X(?2u3M(gT*<3D@+`E(-p@A>)wIK9+c?G?MS#U^L})!7b85i
z9XO?7^Bhn*(ioV<7|kjC=?Kj`0F>;Kw4S}Gz;RB%H#8D)M^2q+!9Mg@LDrR96a^!b
zO(z|x0W@v%cBe@A1a_$6IgkUzPa<Kubsm(2Q#b~kDP4Iq-u*us3IZqwl=0S+kbbnl
zUwWH4j~LDcL-<qB;aF1vH+xc&xZ@QWJeo|>80m&odeLq31B{<)L-Qq1VJLu;jo!7B
z+zBH%Z%<m%(dB5hh`BplVzO1YImS;lrDEYO;m$LW{Ogk)9%>Ryx=zzaszAY%U{u-1
z;Z-b->vTS%t=H#OJ|o(W!??#eqywHPPzd6ey=E~0&!r#7OYKK`0C--1!j!~>V2TG!
z(ic6r_oM`JKoLs^{3^Ue%;ld97o|%qgrTao?7?&TS6Xk_lFL#@y-yt~lYFg;x+lj`
zRpwQaOsz#X+zP}gf1042DSQJ~T`+KJq>G04#cLKKwaVre2C-L${A+SW`CsW+jxixq
zo-62b`Cb+{u^Wom$GvQ64g^(@2NkEJI4sHA6}CDzq|E5QeClF5t=5$|rrVv+p7iA$
z*T~5$>Uv|QQehw*Q>1<NNsw{}r9F8V#ZJ-x0HQGloa){RBC(#MDk?=BgNkHFBOP|r
z@rLikV|y`@U5qL?=AvaAb5q=c)})R~_7sYtpakcwCp(OY4un+4lo_Z;PPnO*<}*ov
zz$xO9NB;n>o!gpM0x`s+H8j0PVe3(_!w&T$50D>PR{^7?Pi}JKIj9u#Q^s(@rdt74
z<ZZe?r77qtOYyc<JoTu+%JEdS5X*NfGbpJ+D{yKE@+TEx#@PY&ttGG#%DZOIT278Q
zrIdX6??^`gnvf)ZqMJ(~`9TJn4h12O9Ssq2Ary2p(f+U+U_M3po0>t-H2HdiO;eLY
z0?Z?VDv29rZ>?RoY&T5%)mw$zK6_F?4BSx<3_<TrCnJg>Y(HLWNQjaXwo^pME$>Mo
z#F?mp48(&}>AQ0Z<o4%=9MOytF-(Zzxv3lPb6Bx}8Ryr%HToP5Y27G1k55VfBjrz8
zL&^1}L&^1|INWKBV-3+T_OBuFTml_gvBp=Cj=uHmN;&Jrd4G=KDSDD)*c0`yrs3+I
z`+>`fjpA|Rr8!T%G<E!XQi}U1o?9k81u{XCPYt;_6vsa=ADvi+Vx5es^c5KUwD35^
z0}k|1ew2PR#0RAvF-J5SKrJcfwKI1#xu6A4z5f8#sniqOAbL~);kx&$B4-J;PZS7&
zo1WFJq_Z`nCf?_o%WiYUOK*84s<MDcYKn^JWOH#l40LL-E%nT>`DR~}9jcs?G_n^b
ztv9bzPS+Ua<BD-=j-9ulssX3)qi$#;2ilI5m<f(Lnh#v&m*4qO{(4k^%3g<>TysF{
zieM=Fy(ze-bQ~IC=71azH0)y?DS-E<h6Ho@&;uL*b4@1(pCaT8VErmQVvr6!DYU$m
zq#}S5wJ7WFM;_vV{zV`i*R40DI~-F@A&R6aq>@d|oMMpD5mLaB7~>rNG@Feg@k(((
z4P!_##wcn9ND2?NNC(PIGo?LbDx?aaB4bJPr!geb02)E%z78k=9<*?1pwa*%KmB?!
z$E_4|j8bDFZoO#%=A6L#Qvm0sWz?ifzjm!!oHyfD7OdN!-VD^%SBQ=KLP~?uu8e0L
z54};eJdutn@{ga4@!q^znlof!YcQyA!|x8Yk^#xjYUuSi3no@KX9oiVu7CYihR5b*
zC{>4JU6h}?ft!9Gx$@-OoRB&7BD#ju<nls=3tV25KX~JuXQ-_ijIkcA?agdvY0HLF
z(x^Gan8#i-RxO#{5xjHjP)-6!Fni*FHZ7QWD!Ir5ihohkqO!q@o}!+>_Nyh3%D@7=
z99J`VxSu1Xbn-6;AlEslDf9El?d)r>4Y`d%veb*zRBCELg4O82=8-y#)Tl7rnqu-j
zDeL!#wRObjnRPiGsR-lL)02VI@uUNa+~**WWE!k`^H!w%D!X8PYbhGUjfWj7zwy<k
z<W*)kYQ{%IL?3pZ52YtebD97@{<=tPxf#mS`}H*(dE3oP->r1S=9cBS`5Em>!*w<h
zmFFLwIE?dJqX)SIj02jkMon6A^70K=VT0D9M$j03?sHH#E$AxA9lKR#Ijotg40B2;
zxHzW)_!^P2cuo#GRNQv_>IgdHH8Jha6|78TPYK8!b4uI}X|ZtLwB{c-f5x;%T}U6T
zL{Bw4<2-e!4n1mFq(lcJG{QOcsRnvy6%p@QvqUuWON`Oi{3sk$jFK^mo42(<y=rmE
z;<SmJiQ(vZr?x%KG9!V{H6g7`9^?<xHC&prFWvO2$KN#)HHeIOs9UcUIT+7cg@-kp
zH9?X`T2Oh%T1<1^mz>fWG-QG6QUZNAsFOXo`qbFqRiYUpo;eh)`BEUy{{UK~b*nQg
zy+lu1nm}>Es1F}ni5f&kUPm<>b>gNOD~`jOg}GzUR2GJUNv95Zr0vq3)Y2IA`?%(&
z&piEVDEJ*JRRbK*_7_vE@O*(}ar|Q^+Xw#u)m_A(ZX>OE_k|=P`b0c%xcBQ`fO(7>
z{Hs5YE-jx)gLkBlpPh1gf@%^PrFX%_M$KON>`aY;9cxQXUEt*8=L6caPdUYGY04vo
zTe;3@+$bx|zHt(Aaa3fTq~IE5%;skc#?`07nE8%B8kTqS-$XtoJ<l~UI26&1)b%+%
zX&R!<jAmPeJ$diay@SA(zhw`HZ=2NSysJi!ec()RF<!ahON3ecvfT$H`quQ%7c-sT
zDSKY<)c2Qh-9>pMajyg?TE+1lpV~C$Q=Q7Z9M=B7u06gIBfp)jxW;QBU9PETm0SV$
zgLM_7S3I~>aFUVa_Y1Z{Jv!8Eqzn;^`qs9ovfET-lOZ#>kULa*wbh%XV$i7`sw<L8
z$JXKTeD+BgkCdcKkf)vnPRbc-gz;=VXPT3~PEpkwDIjGSrxXNMLR^@R4@$ia;;{h!
zbQeyvXQYVkEq5IB@0zG>-9~pB+DTE<4b!zUOI_bX-hiD1_A*tNU~^Nf><1iE-q?fF
z@urwa9@LD~B@$TfyK`0+<wzN<@}wU0pp+x629c>HxvC|Ny*;QUPi$hdl0X~S)ax|{
z@u-;F)ZG!sQhjSF3H(KC$slAQyZ050*-1$Js5tRDO6ZwMK9w|Mk<WUrq~fecl1FS)
zFplMv11IZK0qIbvJ9%!s>SYIL=7Xvv$a(b@vuh#pfbHp6sM~8&%1z7k?@bwE<9bZG
zUn+UVYF#07sPb|%(yGXRDz&1Jmrm?6#sz5&&y}sSIySU3Fg+<6#IFJW02+t;Wf7HL
zJ(XfDV#-s4GOcLOIIQ+ks3aWKH;!EV!|Pkib!#a*W<%^LC5kCW1RgzU4CQCG-g!9s
zR(;i>jA!_LtE#!N+6hs}=LWFvkcB_ppl2;`3YGzlUeaV#a?Wr)del?HxzDeqK09#~
zIVTNLQQ6r<E};z*h6kw?nc@rPu|WbkCqFZEBDvcgdhbeiSn|O7nx&{}GHO%1$Ugbt
zb){fCUj|*?i-(makjC9ZHfzyh)S1u|_q&iQ&b$_gmWqtqf8OG|)o4{XBR=%R%Z+sV
zdeu9Nx53N)RLKc{x_=t1*6iO??@|O)Kbm=JtoG2c`G!xeToz7vE7qn>FE}S4dr@JS
zS4@#aLUBy8oG{1ptxZPSD6OT>Jq2;Cc-GJI{{RnqmX4|iOw+`N=XC`1sGZVIRM#ta
zt&*9^By~QN+dX|jK5Nw2={h@(P;;NHLZBMO)I3EDP^pcJ9QN&0<MApqEI*66=mjeQ
z)Ud)52jf+Dsb+6ZYnG41QkhESS#yFtJ?mQ3+}&yBSdf-(r*}%NiI%9szJ1pc43ePn
zil*FvqwhBrYFk^xSCVUDoc9=}TSMkuE_w>u8ne%+xlKD;2w;N@ftcX)>sO;7L%_#1
zMdsMSLk~`S)woV=#dPdqF@VodD>qjmtqPB=US`2+g6i3B;Ar2KBi9we-KKg8UI(7s
zMiq$|IjW7vy>uFfhNgg%6x)#U0qdH?p3Zm<B~k~ybg3qA&JH9Ssilvt81<ybtx=e!
zkn=#IkN~CYMkzX+Qv;yz+)UE80Xw+OdS0DqmU?dDa>Q2`;oCnZ2zkk4>0Q>M-)FLl
zJPt=RmvX8*M#eqUf=)k5pkF!WpEF}8J$a~E@+dJBpL$~+4F&qtWZ+T)HzbS?(yKN{
zU(ThGzq?Q|#WA6TWc}c2pmXm|CmE#2%Sd+v&uUV_72ns|oTKF|+$gGda`}t$XY!^r
zh@_Ca6Pj;OY9d&6$)^WzdZScIt%{Lb(~5;y6VGaP?4F#{D40D+t)AdiBLmWu53k`s
z%K(lu%_uqN7^pxw9lhz`@zaVxN(lAEN`oXS_wP^!6?;tq?+_lD=9n|2(`{1P5X5A#
z&P`l#p5mF1ybgnkXp^-EB)2tf8wvNb^{obprGNp>M@r`6yV)>O2_MR}qq}9uSK^h(
zGPO-4Ou0nEdSja9CboE8k;WN%gI=7QB?EA*O<zS@gl0jt{YP2^aN7tUDXZ3(@<ht4
zNglNMEaitW$;tk8RjrtF+tQVaxzt%|jNBIo+}BB`>d7D*oqn0GHi6nE&q~y?yZ~dr
zrAW_Lw!MkS+Tp!LXrsjIfVJm3Zm7stlZ^MSzfaWCbW^wn92#J2W#eFD#yf*n0c`H<
zeX1Brzs;PjU4$+T03>)X=~C_leJNTXS0nSNSTgz%Km!5|F@|aR=8S?fOa=jg?M-8x
z3VkNr`_KadWc2)LS{&r#@Tqp-b4ocK#Q;??dj6CwVP36yc@zkF9P>ylQ=SIfxj3pu
z7h{f<wdLgdQ%nloxu8ZdgJ|QLf%(YBF<ZvgJ=n%MsNTUJk&M$BlM}k_&p6;#v@)xw
zC#6<vLXvU~2jv6%-6;X0mm6>cW~a)!^Nwp6KHT6{nC8OdpQQjvJ(ve_3=c}DEwLmV
z^sC=%1YlGTGB6{*pr8lrN$naLc}!y%t`hbyvERG_vZIk*gI*=HFC(~81$o}7s+*lg
zN68uPDGeL;(x_jpUWthOYnigTakY;i@m&pxFOk>1NX-M5$MdNKV6UxDwO$}QR6#)E
zm=xVelO3tEp~%3^OF3k5#|E-Bt$uwfB?%t#dRL#B;bn-R;~mbdB~?yWWziF{#?w*@
zS--jm)Yk=d<IO<s3WYfS_x}J|vMxMft4bSW`*J&+*UZNw#XZkW;~;vWwhPP3gYl@^
zOGv@ra-->9F*diUPoFaJi2mpTpJjV+@}DwdN$4}hbi;@0KZ-;=bb21VZ?xs<Be&30
zt#xdX`JGqXb6$O5l3Z9ipk{SB&Unpq8g=7c>46`KQ-)kubuJ&GzBx8wJZ!ob@4QJJ
zjABKCGQPa#ooTPheH?CxBgp70p46ZwEU@`UIK@Y$>M_MCMqAhn*7Y)6Ej6Mv!{Q}V
z;yXbjvVG!yrmINK2?eo=b)>5zoxiO%<#zX}SSk_PCsod4#B$Ds8acZ4827BDidhEY
zGRLVs>t|R^(XMff@lA$3(XRslSEYxe1s`=Db}CIs<@Jk6BY_=;2XRe+6J?B!7Poci
zcj=D9jC3`DYT>QA<QnuKtdBlU=Qnt}Z=@do0MDAOC*7->m&<(Krxiuc7pSj78xTOl
zp7iMWG{)>{$@i+nE1qgIQc2dLV@L_0Jkw`CHapP?!KTQ-$yiqGX#=G2{l?orEOj4v
zn$`fwa0t)6bJ_!b@uM8%^sbQExxrTCSDjs2M)4fFZO%8N<LE0}PoCldwqv|idugPF
zaM(1m-R^vLu69|q_N8I+oO@GRPc&^Nvmv+)0L5PsqX5+)G}@+eWj}$aZezqOH)K_v
zs(_DLt#cv>$m>o!gV@6-5@X)FEh22L-nGrjesV|UTbe8M&l#?hot}xJIek5WBZlc$
zzgo%g?3<yPJr8=;JXhy=)jmvHJ!%f{M+@V`cpe!elVNOSMR0R7vCBIXn)H7jqWyw5
zVV;0jo6K^)_4OGaEb!^r<;2}ceXC`OZVh*y9ze3f=!5U$CcOUG;j6vy+@azL-A+KQ
zGl+iSvT)DdJFhG_3~+1Dz9iczw~kB@R~W^56h!$;^sYbR9k`cB3<t~)74v*QQPao8
zGpi7<O`bU*>+4ldTvf?P-gfk=t;1r!W`n#>o?ti>9;4or912X<f@9p|3XJD8_WQY}
z6N5kq+~+u?Ps){#PSh#M=}2S2!+M<8r~E3L{yt*PNN)c1<--K@uKxhxgvLE)RV)tW
zR<9R5r|mFPUPo39+NwQxb*U+UZER;W@zTE#lCwSFJt+k)Kb0qXkRx&FT(65`-DjPo
z``1|f*FWM^-=@Ak@abNbTPtEBO-*9XV#p6HkKxBkxop_YP_jFhKb>8G5hwJov%pH#
zT0Hv7@gtBAF}u`kGC372tFmK~aC=lloY&o9-!&wB{aq>%?I3leB-EdcF^9DX2-}~n
zUea87<$GY&GCvxzr=7P$-nsEny*7=gJ4n{J8Be8QU7_4-pqu81)*ay8oDasnRQ60s
zMjMK$CvjINUUF)q_n`q!<#$F$Y*#UGHpoX@dskH`AxP_7&F~95bA#z#h7w&2Y9gT=
zQ%x&Vb6v((6gSOQw7ERJQYOey#{{0$Ode`T+ia+K;N+i5i3s*9TiZXgC-0Q-I#j=J
zvi=D{Ca^TE8VkKXH+PkZ_r+g24W8uYPnV`x)QEN7uJKF+5yZ>ie_Db~V)>*3HHB33
zf-_d+(yb+6%%rmSr#+>*u6FV%=m_(l7i!Yp-82rWJg?TdVsI;8#B!v%#Kjn6Xa^tO
z=QWZ1t0v76(D-f*(MtUCdYWBY-KUQM)mb^@)|ZAY@uhEW=e=U<<(A-$-!HeVK7#63
zm17aAd4Qhy=~gs?t8nO!PaP`^vCmUl{vU|E?Bkpoft?UI<0Ca<+~x7@Re;8GR$xE8
z6wr#A{C;JN3gM4j^sf6@UDgudXXLI4#u$P6QW_XZpdZeXmXSj4Zk?$zX(*%y<XS))
zIl5t&BXBj3k8190WJ{d@oulsYTwqb=kjMDD(*hu;y(m+TD@|=-AU1eC4Ndk1Zk+uo
zh{q^E=}jwxS~EhaoCEmP88eyyi?uY<kJgf;V`!!5X*<vXMHEm1(M1#hQg@=3fr;Li
zBQ#P_0-8?LxuY}yVv>x}KnqAHqJS5@6qHaQNIsNy85F;zAw1DxiAzQ(qQVq#N40la
zWAC$wk50A1_pZZ2a{7E@(A3CG*mH#$ti3@uM1AW~hDW7RyFy@YYg!N9L^GRlie@Tl
z7X<xk5<e>T48R^JCo~FE%>W_iG~U$gQe)|w1R?s<Pkt%K6ogV`3^iv>A#W6pgRNFI
zEvpf7rvt5XR9Xz{q9m^r)7F;XnCO1B#8FF8UDoaHF<kNKT{Y5{w{9z&7{DF+S8gBS
zC6SSWDcz|UdJ0f$ppihwYH%17fYOSjAq^-zVvJ&i=~N*H<3~ye$>xGcrUS#_Hi~9(
z)|{jt{<RD{;)VmF`I{8GF#B;)p(`LGwM`>rgVQvGGC_u@{W59ncYD(h6p9zGy(V!>
z`OpqedY}XAk<BRj(j1y{iUb&?10Py5gGf$KTvHJ$sBYq-E6pm921O`(mN5chg;|ts
zM8_u`YOr<P)~9|{Hh(HYE66$L6&V>lYIzPvdW4>F)`EbFOdRu4<BCE8&;)q*H00+w
zq$dN?g>S-`gg&&Gr!dD}X}HY;9%KE<eDP7mkbNppsL_%~H3+~yhO=mQEF)mm*jRb7
zzxPgRg7ea?z{MF`(9~9sH8z1eJD#JZ${yJ}agHlddUIUghpvUqoNT;hLF27-NOA^i
z^K4B%N{t@fH+ZH>oUH`<(74aFDIE1bTIMVOq{qwjrvX9Zr63!Uex8)Z&MH;LDMI^F
z0--|6Mk$LImbk0uYN=!TRWopt94;$(!fqGnCPsOoe)R;ON<e;UkP>0@3ZXicezl<}
z<JPL&s1b+nTR=>xM&)mDSaYu1hWgg=<a^dN_ZL4=UhY{f(aDHf5UI^y(wk-A1Du+m
zzjvisu{gV4+pE&VM)cY_pzS1e_DAI_Q)8O1YTrNBtezV+@zrB#v(=8oiO8!-{-MXU
zRYTscKv&Bln{TaiO+J8St8I23l<oKenBx}>O2dj^T?9#L*g4{eFk@nR{{UKLk<3MN
zjQ6T@T(lB-SRfO@tD{BLlZpoHPEX8zDoD9pR7!L7sbR@{de&21x(rc|%A5z*lN6v-
z0NFm^IO)wzkKGE5hF2c7A{@kM0yP-#`BaJb#YQ-%uU@pJunxW-D!1oQj1(1O?RVRZ
zaaB|OU-hQ85d@h@LG`P0a;j>yqY@8lvg0uW>057P1amMOM|wgsyi_t|u;!#w^5d;t
zT0YE4+>l_!NIKJ_!H*u4)1PX<p=l2U8U}OMtqeHDP!c{$gHeOf)B43x4m(l;%tsC?
zE5*wprHuUC(%%fkjh;uPE}%j_?ILAl>yM=(l2(|f6Ap3otzoMZB)SD-;Pt2>Y_G0;
zYQ^9!A5X@q+X4aI*1a2F4$R)=v~8{`!~N|3wNzwnt1fZ}9M_dC%>>6jl<xG<d(*Q>
z1|t026O2=wWd8t-E>7>QER+mpGmO^><NIcNWq(G={{X(Ly2-9*#&E3KW8@M7*Rzq-
z<iw*Y>hNci?$0z2tr)=C4IK@A{7)T{pc{G`2pdmYMLcJUQ_%LSM3D};rS_yfXrT;T
z8cwu((M&>$UZ3Gj2adGt(Qq5h1A=KyB^Ll4MN9=jQUjHs2cK$|2wr&vQS#@ps0qbs
z=yGE5xf$C^a<o9tyM)@@d2PY#P?J~n@A(PtILT2|IHgVAHy8$|1Db9JtvP)v#0RZ3
z_3KU}6wLbdqQD*c=A1sXfZ$V<<Lgsk5Sl^PtuKDUlRVNG8g439LKm8gy#N@cAC(}d
zFKPe|aZSxUj1TKfJ!(J)G>3{a#UVWPp@4RxgUuMEF>^?02ilC}bmou=Nz`*ooYGW`
z2U?XEa}0iU7k<?BEIzadNmpcq9DWponqz;gIn6i@X(5j3nmSSn2&xc<ic?8I1uiK%
zic)9*?deU%Y1yD2X)q&kfu7XPhNN+v)P1WLxkHw$N0lIog*w!zd8Z|KgEwqR+sVk!
zdel>n^^<1X$nC{xclNIqveeck`$<wT=1CP(__JK5t9Ng4eC7d_UzD*OYhLVbwPnB|
ztD6x7eWN%H+v{6l-QqTFXiyiBafNE=O_oOie=4h>+HHq;IrQ`bw!#3zxURD{WqCeV
z1L;(56ttK;VzsV84t~FtW?YOPdXOz?=Ly#xO<N~9sx}SOb`^Y(2;!)cynylrVQNUD
zC%tdTNcz?$s;jru?yjse_l)XnWdKD=qncm_q+WmhRq90JlO>L%U%gCDI5hFrx}sqs
z>|`=?N@*ecy{YY-`+HXFW1p!5s0-^=n<Kv!ZI2aMhc%pyVn*L~tFYQ?&wpyKBIUj7
zDH}vUPC5MP!kdnrso?!hN-2}Xc=V}pQA3h*f%w$j^UZG)2^MY6a5GXd;;X`NM>RP-
zkZWXfy~x>d-0@XiwzXMokaJK-GTEq+tO)mFp^yM@F;bqD6ZIdZX3da*^Glp{=9)RD
zXNrN6#f*=_tm7SOs&ae#Rgr+8bDw(FCUYc+;NqUc@iiJ8p0z0+`K=5Y6Y@Lb+N(El
zRvZ8-7VA>YA~vF7&O7y~f6q#5b>g#Th-V;wjRU12%_!tlls!2$IN*9!bm0AJ!nSJS
zXChegxXnyOK!fHLIXqUV!bC1VF0}(ynLh4uimbz)^)fVwhowT@dQ`+_qH%`g)@;=Y
zo@suRgRLh@LnVyk+>X^a=brUmKk{n8#yZuaBuN<}r9Z=iQ7a7QpN=z})gv+)2M798
zM}z$;cLVQ!m0X+}mRv&_^{7~5f^aHcqpd{T9(nrI8X><fahhDwjGszgxabe9A&*Z^
zqNm98BCE!Esq@o06f#ZE3@}|xobb#S^d#4$lbDpA{{S`xd47a;YDjl~3lKd|PwQTs
zr}rZrzFPdxiDS!(x%5~E`>P*5x|5$uh>TRFi0pGrEPX51x$VeeBQs*OnnM&j6yl(P
z0xtIasTqs6dM;fx%1ds$pFWj;7(8$)I3d{|r9AP^r6aDIvJ@JXP8*71t}0|9PDtrN
zsya^%S&5uV4nXWHzR==WuebCqjMqKkSmOHvJS&jHpsTj}nTK2QPu<QiYo-fB=JAu~
zsLsb((9WR{k|FZ9QhN%g9+tK!SNOY}*0XET*lFTdjFcG26xlCh)GfurV`FkKD$Xrz
zdGCv~t5%PB`CqRbR|LUO?HmEvS8w8vwM}rr`w{>g<X06e1svoM4*->{Do3gA<yHB8
z*$r38=9HCjw2TUATsJ*w8z(s6*E#gjozV@&fN)wq^_=m%ZO3lETGmO59&z~8jFDV&
zR|me{^bsl%o~v^nJIN8g^BU2%)bMay1Ja<m(~p^yBOjG#yblu)GsOo#Jz7lZ65=^m
zC%rtzg+a*Xxs;YwIo@j0U&(+8%@#Uo;}iIiv~ANK)QxHfr#_t3Nc9C}0Fm_-I$kLl
z$fCzesZK)ujW-T+NNtsP$K_Iq)QtMk=PAx;E8HPyfLsd8)FLsR{MN%r3COA!*m%xI
zG>&XcQ-*~I+dXR3OaaGwp#x#U^%=k<)~rxx2l-PtsJ>zGxGU173;-15hYAKNUnpac
zKC~UGEfDWeIq6rer$roh7^>zmjwuTHagsR4G|`=V`!;JW%t10w>04eMF-<#?GCiw}
ziOlf>#?xIlg&!9ZMsc~h1P-;V50k`vEbJt)vzPCvKT%nCx;?bK#sas}wN~0wzz6cF
zR?vfn?dw+0IO3+!FKx&AEX))PW3^IioodK!;#?l$yXhf>5B0bn^+si~8U6B&-t{9n
zA>y0FDkryY4?;hcP5r%Va~{{sWcD?ua++{pUC{H4S3jv+>2hvtqV3{=kladwPm^me
zu4=T>xs2zE&7B(1pDJzZ*Cv+VRaseLnSckOpa=OaaW2p@d-tnIww4XKz;{u}JknfU
zq$m>D24ly$H1yFt$A#{lvRiRe{HcM_=ocSoi_S(OA<z+u=tcA@*_KS>(AG?lJ6fz(
zXfOsa4l6yhJwZWf2M5raOb*u5SF&@B#MZ=jRz-Ig0DIS)rL?f%KJEvoCbYEeGVcBM
zEK)3767RsN1G-I4%2_<PU0H`X9jZIcLMRo0KQQ;=u<qov(Cxga^3yQJPjg&-_N{d@
zKOnAgfz1O(=BcWgq+!1SdK%^KS)@NN0G`y=x?u?~kjAQ|$sFXLr6zV#Rz-X0WR3#s
zlD++_1I&;y0g0}*X}-~B=sK0>wQ`8LkP+9?q^U8JOy#x~CZBGeVL0cuJJL%FM%i)i
zfGei(wvRN|0(M=otA7&pre@?Oi{V+WE(G@~5;6P@*1A(?e`hAx9TpzyYf|cVv$K*!
zK+LLkfx-5!CgWVyeB1_8pW-}zl`N`K*5^ZiJipm;`OyM8Zvwe3J{FAuEt6BOzj-{r
zWRxqcgS}jq*U1XQkUjcWO&Hr#pA|IB%l2fGJBLhGt*gfNsEH^gMo1Nlsw<o}e(BE8
zeX2bwNesn^aqLGGvpG?^!{+EsG>i^vMQnqfzSP$^;~ZB6{v*?;@RV*Cjx+Om*D<XS
z@SmHUo;_=#ynG&+=DD3sx8#9WPjedE7)-c0=}p1*sT_0OnO!Fc-jrgNj<g6)hNrWK
z&%A~))U`r*uAjsHA2TA}&Tui50+TKgyE?rVEZ#<|{3j%y)vv5h8eM~eqtct9Sb0#%
zaOypcP}C<rd*Bu))`U%0c^UE?9A`M=tw2f7)}(TMFlxItX%Ii3{{U4n_ykZJo_|_n
zo(VnafeW718O=DJdeR&o)BzY7^`|QOu6-%Wndm#!d&`xEJSiFby=WR6dp^|&q<ZmL
z{{U!V)05JX-#>U9`_x$-f&8hOqJOk!wE|#A+|5D=&$qolcp1pWJB*iddyl0&C?sN_
zSqD+iYH$*j+#-<rVGRIU1HMH+p2T939X|GQHo*M<0C-}qL*d<CRS)HC&tuIO9m=4b
zb*J_3#cDy}eL%0zARkEc{c7|+7G1cWW53gOGx${V4(C09yq{XRXEG#;!H2P~uHVC!
zFsK`Ip1E>!S_`Mx!c>b?V7-q@If0oG&Ln_3KLk=FxR3&QHKD5rQrYB&AsT_44wcUf
z$mC)b*K+pHHCMUMBxpQ@NGf<Ib_eDFip!GY3Jy+t)I#va#PSUyY<4zUiUk4BJv!Ff
zG;*Nsr`Ejo8}xPOBQ>#Us7$Bja8tOTn;iw_haKuOMmD$Bxl64kOJ`+qlkeKP`z=^1
zfZ#CotpJv~gnJ}TeQA<;T#ymU^Pftp-ehb>KVECoZu}z@+n(L|J*%6(@V(4T-zi`_
zgy;FvXm>fd^(i1AlblxNhPbZd5@7Ig=~;8=(;RL`8TI0-eTG=u06LNCw2D0z-^7v)
zqDg^IKx=l}#8J8g1c?W4TJmdqiK4*CIO4P;zhQzIhB@m%9?fH`LplIS-Q7=W&?QLq
z&3NUOvpiD<5)irFk=DD*9ehg?F@4CxsqIC;=`b027^W+QI3t5plKoup#f46!O1rWM
zqTo#?%<yqd45PgsT9wEmml>c1X3t6&Aa$k{_oOU}GFVVDb08ekeB6qzE~5u&{&dE5
zAng4p5qded4x@?;$Q!L@3!tn=G{?L^r@5dFZ!u4PwAFpBft*%2y<nxW)7F8iL{RUP
zF5ag!hhth}mG`RbR1L@JSr6h16hpdY<F@QpUH<@$wDeJiUI%&vbl@osj!i<$Nav4p
zUUhZxHrCz$0CwDZlaIo=txw`@&BK#yxz7g+&-0)UUbwu9+%b7Oaf4j`q2o(i1>5Gv
zWISVbYsjuVORZ`xhIa}_VT^vYUMOxQm0spnBpl#$t55^6)%<O7c-sKPPr)FO_*ED#
zS+M)L^sN0&hm#Nqv~kE3S;*KK=}J+s(bsAB4Y(=$tbZ!&>?RTI{{TE!0cml#1^cJ@
z*GZ?|x&=nTQQor|+`}@u^{1XI8p7wyN7_b5Kzr4bct^_I3SuO_b=n4Njqz0A#=PXH
z?Oj#Nd6A|+8uPCeY69N(%MFlwRU|ZX(=c`=h7YwscC%ugB%W_P)L8k4TB{dv<^rvP
zIjQYo#KWKmjMb%#Is!#SbDL-x#|O1L3gw7(JDoL|5anAqtKJvX<ZG*hmjttCAmbH{
zX$;qJ85xE;<aDa~OxV?(H)GqSQm3WEnCvx6hMGW`%5);I^(#p&Rb@u`Phr$l`h?FI
z2cN^OKkW;9YKTT_8r!3@39-AOYbYXLIfp!QYeM%}wNyX68TA##T-&TlyABBHky%pQ
zN?5BoC(^k+lWgvFV-uy-HI$L|NArB$t4_{M_UPF8NXYlBog+r`EZOc;_n69(D@M^w
zaRfiZ#dguB%8xG*SDlU3hW$2Cp1fBrVt;l=80lS2@hxX4&o#<faCU>#*2v{Cbz!#a
z(~h;DBXL@~(8bJcoSsh=l_1D!?Wd{{2iBEN4I$^&m3ePU)CWn|gHalqLB~QW6Ol*<
zN6UAl19Km0R8q$Sy<4-i-#FfX0xOoZz2jIRuso1BWj>hZySod`@%xd@a{|-}m2s2p
zTaZG^s>9Q*dG%f0&C;=<Jc`arl0B-XNn&bM9&2p}HF`T_P&0#AjIRN8$H+&$Xh$v=
z9D_(s7XzgV0OW!7qyx!k#(4TwX^MhIYIl<Z?_#M)>w-be2xfHr$i#Q8O(Do-8NsZ%
z{`VDkOMS8o*Gkyuk?6i0lNSu6oR#TYq;p)}fhZTL$1JtdH&fcaABdr9>7I@i`-eH>
zILw+OoMf*cSCu))&3gxlV)JxaI`<XiGK>}&@7ldy9hK;`WsF*(kpBR!UqfBLgxCEw
zlykUr&wAou0L&|~@U**i6y);4y==l4!^pyew9(e-x{btoq?QufIgc3<bC2avc+%g^
z&}AniZRuO)H8ZT3`L>R0Kg5xF+BC>V@Se5t7%I{F>?D=7JsOJeXMoB!HaZNPVyd{q
z6IZTc@}`kG1Y#6bDKWb}jeglh-U#{GXvPjGJPHL2NHwto@JwQ(JXE8Y`qW){paAry
zj=iZ^@z#(YdFkm$WP`A-x8eNWSBR8u#_R$;fUZb(HMikee7_M{wttV4_*V{L4tzZ0
z<ZVIPqG!-K`KjZIiB9B4^-)s_{35)0X45{1F-`AJ=}oLaYmC-ju@3z{Y<=yutU#(a
z>$=ia_O7fXxoV~-vFFwt1>pL1tr*VPv6{<@MT%#SpOwhYJ?l$=%EO%3+hN}=bB3b#
z2i-1Y4eBbhRm-LMRe|RfO}h85y1>fx?0o(zHki@%ppXZ>M%)j)Y8NlhQhh~R(TQq_
zn1DGTdr@mD$8@=6!KzOjvJO~d(-e{0GO#S&4@!!cacI&SGpLsK9hfiMoK_9p{3NhI
z<R4L5(OQRxcc&j(&Aqe=Nd6((zEY%ZHjiFA7&jLOKPoOg>Wj}V<A9^}tviSUu>(G}
zMdJawRFqPc-J88(Y6`+(xYtNy!t>Ix^+>q{bt1a(&eAifv5MTET5c)icg-eoUXg$R
zC}ECAS^=daD@lRr8V;{&nsj1on9$>m&x+Fi+tYym0FUTD@3CHC3&PQlG-q!?igA+E
z=j0u8z^qtU^oQ{Vn4NE9&$Cu`r{cQ=vXjZU+}Q2ZR}gM3*OgA6N~wD~N~3D+BiE^^
zxk(i#m(7{vY;JS8fb41(=Zxbg6cQ=XVXh(vp>h1^8R(ikA}t{lt_vs`70CF3!MtuU
zitjCu$EHRI0k-7Vo$GRM)FmE`jMHST%+tkm-WyC?J8{co8s;(0b-F5uwB`5psT(v%
z$4ZhPyecf^YDk+0=~N<H<lSh??Ot~xY<66OgI<p?EeFg#Tw{@5dwm&>?nOB3&{Pc-
zk2I90sidS(Qh}3!Nl%RJkQxSd8dRd!Nf63L<`tUyOfM@DG@Sh^TO;<UfCG>^RH{m`
z3~)tY>)KX2V}^2%F;3@8cpwiB;yul3>6&zqX{|iRbHAr*EhL`u8Da=Fj`g}@jWjXF
zIL&m$-5ioub~xL}`u??<Dj!PdZXw?0s~aH4lR%Drh7C8rO5A-lSe$W>#;QrC$h{O}
z){6}@G}2Y4v~}zJsuql`CWmr5DM-a7A&W^zQ%gXEqLe9P$2B6t<m06<Bcl~;T7&#e
zpGq3kXSkxkQ~YUa*V&iU)4tBWlvplPrN`E;2mm~&r--=hJ?YpA0a*V42{hpop2Su0
zAERVYR~=0j70MzP$mve|JAu?yy|ip3^rFC37W{QIzi0Z@u^WGM(d5W^2uIe70a#m)
zttf>-`?Y9W%6hH^NR~2@p1(mwfT$r%ecI^sBZziqky+8{<goKH2e(?((_l+^ST76c
z)iYWM*FSeX>YUgr!!>g`U+GmQ877q`4CiJTk-Om4axqsfmu!u|s(owOrtXYbgM-aD
zel*{uDLFkWK@Jqw6syG{?kE9<lljxlG}N(-KKZ4L;zd66H(F>oBkNd9qph@%7!Z@3
zfOAv1=Bd~b_IS=adR4a>AcI^Fa)_iG(U;n}h8U5@q2{`>xnI(`sm9xhIPPn&4#djG
zniT#bl#cY(IIf}x_vt|3(5F06)~G_`G^^=HYE-~(^+-doq|>$!PAR+gjs|Hw=IKmC
zsF80QiO01zRb9l#_kHR$lP%6E#Lxspbf@;9nqC47W`G)aG>5NBairUxX$)_@E_gI!
z6qx6wFbw`w;l(tcYH;F!40GvAv<{+!#U^u11p^%^gnQG+T1KP;G3!>5cSH^<wkmkJ
zUU~sY0zvZB2ZM~%?nc}$c&IbhfsW2cT0(QzkxHZyO*t9nfDF(xM;?@8nm`2Rj?|>|
z#WeFw2QS<w)}bGG;-wr8l@J{N0EI&tDjXiam067B^x~>1#aWHMP$@Apv+#|_?#ci#
zyjN(4A4>C&4NlQtY|7!jZ>4%HXL5qwabE+Q(&Vor*TXx(6NcxlE^>L|n4ob=aqC`5
z&`F$8yNX~v=-tP)07#~nb~90_=9hL4tt$Y_hCWMUipaHB5|=x+lUrEac><bHY&hb&
z;fYbC>DZfURmN!#^PrF^4>g5`Ik}Fq?j&O%8R2VC451k9SyRS*)6%;z@w#b}*oC+i
zn|z<W9Q3UmXOHJpuaxCaYV@-GDp=>NuM(n+cB!ESW>P7!At$9wBV}+$T=%bTYVkOc
z(pr#M8oc~BQCXI(N};V5KPaz^#l^;}N2^a*il>TP68`{s`Qw3_YMPz{wqe}nu!Tnk
zRf^LgN%`(NQZN|BOQ?oPgB;XE<YJ=t0&51t6wlJD>QJ*>FU^c`Pqb~fIK@qNyW2I>
zgr6l*NnH$8#@>5#PKe?2nnlYlJ5Vwl9M)KvT5NG9ZX22b$)>sazX~^Fj%%93B^*-3
zdv!GsaC%dra^&q(`Bf-M^Z+9aPfvPso^U8JIVWl{_oplplbwWBdm5k0E0Q@cY<+5s
zCo7M7yoYpb52aIxeC@}2$6z9zurpTBd6w86YQ4hce!XgIHfDi_KPuKe0M3SHd$)~;
z0<Hnpppq?@0~KQdN2Pjr#mxxF&OZ|!7D1-4!+%Ox&LyHiH`kVG9{8b$%4q@56sNy5
z0Qk9x`+8FjLB&2JpO>0z3>~!W0xM#tm3LcJex9``Y`|A1r63@QgDpn+Su>g=f0&Lj
z?M#urY>`(H7no)adG)IJQPkq6gA!Y3ImoPOUE;Ypa@pt)YVO0q&N3yMN2YxZO`qM0
ztLCdlxXAXYk+&sq$~Gu?Z)$Kk#X=4mpPUNLz&VaOaZ)kdyi^3|H7fFy42+YS%Gcua
zbjRa46{y@*OZDAm!>}FruIvo?D@Btvba<V>+i@b1f)6>Ux>fC36Aq;}To&k0Juy^!
z{{UM39-F*VJZY^*p)~&h*Xc}CgHHV`WI-E!>}Q%OTpaeM=l=lLNCiKI8Kl9Zy*q%k
zpi@Dm9=uQjw>YF6QuU<H1p*L`DdX<b4LvAK1wUG~q&qI8fk?sYRk4xMr_&qD)KL12
zR8;sziM8@g>YR4wvw_D!S~~k?;y%20tgvxYN$569)KagfT4z)JY0LMx>06RJ10M9l
z)}=ppoPHG#N(3K>%^drRPtKREA&NLXXwFFV%_rqYZ1?u0GTieah$1dMYNtw3$j7B8
zeDtIN?fj|AX`T3`UPS;sc^KxR#t&MU90S)i3xW?cm;fK8C-k5mDG8~#>@IOhnoM#2
z6rCvrhv$k7Go>jwH8&WYXgxis;*&i4RDcG-9Ac~{0`B8ARFVx$rz$f}8i5>#=Iu(S
zG?MUWLUEcFj0q^D2A4VSR)hwS()G<D`cnZjONvkPnqP0{QUO5E{{XIz)MkJ~U!kU8
zQ=ih9I@U7Wq3iXj0mVe8nv@>+%~wD*>?GO-dgSq1sgk+qYYx!l5T^$|mAx4GRCC36
z_?2lIM03Vo61{k=m~A}E;E0@_{{YgqRZGXWceZNG5G9fsbBQueaqC7KVx(=^Y5rZh
zDJX-|tjVTItGYQA$EU4f#d#$1h=Y)ES{vlGKn%>w?_HNODP5xiK^Q&#t1{(BsP?T{
z<?{jWp7on@2^>%YSqvN=r?qIe09JLQVs1y_T5PyQJ&gh(a7|<Ck^HCJWLDV#_pH59
ze{lW&T>4i=9olAfHZTFsIjI+|Fb<slboCtbUd&Dz5}?Sb02`@^QgADHn8>#VHgu^D
zGsjwr+yV_udiAb_vCl2YopNfcjGmQg{{YW5UGtiW8bpk*rB{9%nzAYh6laRcM)4y9
znsEGa?MNv{H7KHJxIVRG6<#hXa56joRkARVG+nr<+nRzgkHfW24nW0fj3v1lADvfm
zhUr#cimxEgZoTP9xRJ1^+<rLpsd=d6{HrEvi1L1veLpHOOVo2xS{)hr!9SH+Q^o~U
zLxK%iUQlydM9yTZ!y1<d1D<LG>&|L^g9H=!)`-SLPtu`mV?AnjIUk35uEXZ!RLHoE
z9eBkx`uo$cah!2YbJwq}W?Ca4cLtaFQUjBbOVm`9Ie0ZVIqQK{*Y8z?;YU2xM41vr
z%XO<DaqU&32Y0`<SO8<3*2w3U<ZeG4)pq;bRfz|&{A#mx>r*1)1DcJ%$)|%+$Od};
z2D3IpdI~#G2c<7lnnNC$`U;!^7OSDbsqs{Zks@d7Qjy24M1XqK#N=kI&5^%Om05|&
zso3YOM8o`wmRv>>a6#)(zZuO++|wL;ii1Q(I@5szwKo~1?Lf&CfzqY|tD)!GryPt>
zBL0@;HCP83Z<J=ePTc0$Hc3C%HRRTABfg2c0NMBGYt^hyY{O?f59?o^aZD{%GCj<>
z`-g%zT0w%sk@M^a)|eTU>$1ntxfdlP017RlXOnU1Oi*P59qUrwAc#2IkwLs8cX3GC
zNTeW~Q`;b(X)}RA(uGhlQ$iJ`jUSNA0jlf8O`Iqo<LN-#v{~xf1&mhKNRg({%iDk{
z*BVNj^tcWH9aN0-RD2_UEcSj>xXABTHJxI6TlKe8%y=0gbDze#mdDCfZOxrll5M3!
z4aib6(T#1JNF#%67zx`I=J%IZ5yQSP*&T34O6dGCsa)Mf<rQT>nEAU?G99Yu*0;nN
zB2vTn_SY+~=&`Mt5ezUK6iVv6M-}YW47O)$`U=I<EU!MmQu}F;`|hb~<<pyk=0}-K
zn<ivG!|PFzn&`YsryCiJ+fFbt0O{{s!^{=7@=t6G*DRxEeTEYi8kE$9c!B5!DlM#s
zh9Z^bWl_{;)}k^q9>0x2*X?7_yA*)%aD8*l4-`@iRW;mu{xvjt1Yxn74HZl1#yym0
z?&I*NUc&~jsLwggI}`(@2^ni^x4A!Bdd5??<61ib#V*0=_)toumc>O6+N22i=BI2g
zJPiBOm2!oLE9;&pD{iHKEaL@@LvbD<KQ=h6t9>I-xg*Q7nX)sGx&E}-G%Mo%T#4mv
z;D%F8MYEc=CX`c7M;u5=Hx5AO>soN?F6aU%z~i3Pe^>CsT0^+VTo4aT3eK^$@|$a`
zDwDJm)~UkC@s>5IS`2a2E_Yx?Nj(YA<x|_qsZ7CEKY#wUYg*~s*ypM41$0)Laz&1e
zG5DIr%EkR|xAPo+H2^+%4<58!Tr^Pma)wglKGofub@KM`2fcG1B8)6JA#x5q$Gs@d
z?!hc&URyS2SrBdeW3_1L*QsT!#_V}NC>^UV)tl^K^)(z)k#`XwoHzHeis^yp)OS5v
zZBpUl32O&FtWR3Rx|dm*NZq&8VEnau+fhGeU90>!Jn>M=sqGyz&o!ew`)XiMrfM@C
z&2#?%eAO8=i_jR0nL{^F8-w}RMB2TuY)GT&N&T&AbMl^kn5nSNU;7H-{`)^ZoKhVH
zBU~K)J6BUCqYEbsfGalc^__r7$r$=kU@+yeK&$}z@ruB{(^GRW7|(NET+&SZm<Uf%
zS(8RvJHWy0C;@yI;n}XPJog!nHu)49?x(ftHjr1o+U7hbsLg47@x%V84nbb^=uzr%
zPi$oJgF5g=DTwA0Jyt10Tf*!|p%vHYi>R_<_9T7WVLN_xg?p{t!GwkYqdX8ZRDZWM
zzq=j+p4`%7Jq@(IIxI^z#UruBX6jnatRu;WL|)5`S10FcEgtFa3C}oQDj4*uoB0@w
z;QG=7RzqQPAa`|X4;gZ5t<%}t$B>K;GsQ|Y7_|7BSzIwAq3N3D^$X@%b01Eaq%>q}
zSH5I~M0my+3abt47*sJh9COyBx@47!C=?!WYP!M+;~720BcW8WqYcuS*+&Jq%{?@q
zF^@RUJQ}2y(ka}H$mnZI$>xp5=KKXAN~OzCXmdyh$}l}mbXrt$+hJrFB>otx)@<^o
z<*R#&D>LT`Gn`Omb2r4=%G<yrPrcmYy#Du5o<`avU<dK{tGfN&)$XYxs{ZJII>M1~
z`xFw}cQsriaQ2+2*3y!9DRx|!BO}(kNW#r$$oaq+1F1E~X)>E-3RfWVd9IENfWQ@E
zGtU*)m5zBkk<S2mFn;f*DPp#QHp&7!Q{|K*5=Kej3d&oeBqIbI_cWM9+F$`YPCpuk
zT&kS+sUkb0>+eY~3!31c#Cnwe6k*@K(noPz<=+b3b6eM}H#Remdc&SKn|M!~9OAX6
zj(Xb}56L+7rXG~%7-9`Fw>X;+iZO#u#UV6=J_sbanPP@Ek<VovtI_oLXszP5VT@r<
zHHqPCi#vN)<rZ_)oD*FxgrfUWE~GM{%L7R2inMNTUCH)6F%fv&I%c_Br`$=coqppt
zB~<%y+PTRaE!Q;8N2?pZj&n>clirn>nvI(n>p+JC%`!~(Kdm@7J^uh2Y=blb2?Uc$
zvE=vTsi%2l_596K)Gk6>G;6~S^bC(s)I6mr3HiIWYZ304zULvotwz#r<kChw$&oYF
zhcpz9vKZpIw2kDCYi-6UzuB;n!skBqZV`ylNX7+PRbQ#8Y_lloG4OUAdhV&$On`B;
zf#}tJQFGIplVbk>`lz_d(P{SU(l7z$ufrTMoTO@}zr8RF0mVFea19p%>Rmc8tJeCy
z#yij)@seu{x#&r!2lb=}Sek?qbLD_)K_m=5?sHtc7aJe%5n2m&I%lmRn$9hcB$4!}
zwr)Qojic1nAv!STkVz4K8w`DD0h;N?ktjdJ4^O3egWQ<zS<sEO*?6|>q-h5JJCW&J
z69KrNeznm~KIx2^xn-*YHcg*m1z9(7vgKQ!dgc#W0AbOO(uV?0fwcufcQ~n`*3uqC
zocfC8*>TdF)2%L0JqpjnJsBm>`#Z6U-?H&a2Kk83vsaJ_8G11lD89Hu{;{~}%_|DW
zzSww%JB&KaoQ(Qb%vyvO1LoS;>PJ7FeCGzab8gG?5Es+s{#DRf_~Lj0551Sy(vYls
zMAo*G{E8G0TF$xf>{Ai4LB~N{Rgc67<i=S@9e18_T@9y;?5+`6X8`B!=M-ElGJgwo
z^&NJvKhCJPhaNMO1PbWm@g2P66CxgZk_Alq)wxmkNcJ?vW0e|Au^jSGy<f0};BC8{
zFIv=>ShFFOmuNMaE$T-mMp=DFN<%m8@0k>WR<t410-Wya&MS>Nh-~r4y)0UUfp+g3
zea|%@chTw!$Cm?+^nYnbk<UNQxUs0m5`yx8Ki(At+WnQe%$Hd{??BGowME^4#Cuas
z+q(=7y(`Zp@!p#Q6yB}3xIHUA^Wr>go1olB)_^@mM`80jC?8s^+J&qDv&;`-1$e#Z
zkFRFjsT&39*9Nj~{86Y(*p5=8uV3?;c41@NFFaFYXj#@p`F{59YXejGhi4NPM>su`
zy?FGOmlrMj$()bwgNlHrdb4rUC#60>Jqr8cOul4|1G{{@DO1H_&Ep&Esd2b+IOnBu
z{#ovN(~+5E$l%lD8L4rtUdo^A$j4$&<5`567?&l9>z-&X<nu@g2hxvbz)+zZAx3LL
zB+85}QCyzYZYOd_VbZjW87-F)O5*~o2T(aY`c*I_Bys?&5kr;)vE#LBqD{rRn;|pC
z-`1zLD$1j$H3iy_EOF9{X2w0atZJ=Fi#P1%TmX1(*{z7Kc7-|lhkEAiw;V7%@m&m2
z0;#>Q4Pa5dVSWV49N-bfYovlx)bm{RnntpX!>1sc-Hug1baCrIi_>8&UH5<#SBUt6
z@#NIzG7#MSrCSEQXIHvtG}hWl9+l&ozT1nZa5gg@am{HIG|O-u(2Vn%alq!GvSJ_$
z=z7%c^)$-4w`zf{k-fh<OY3hs(`N(Rijz+}tkb<M=0&sfgN%&TM3z&A+}YYV--O5A
zu5nM5tj8$MOID4i+U1f|c4kcV>zb>52a|OWBdO0mmD45elXIiE%SDamtayIY?GlUv
z%Dfz&^-UvrVN8+tM{4bSC#EcD7%0niKK0KirfW{ChQ}e|m3=zn9F6|~m1lT2Ol@CW
zj(G;?qkLC&<J|&XLd7Juf=Q-R(ly*gUhr3i=F_y;WM~Sz5MOw~tz#I*Hwjggw>NHd
zxS%Sl8sl%$xf_^T+Tuj*oc$}*pHE5T8;RRo$BDcyv6D5s9o@k>CbLFo4Rrgh<Q}Wu
zxhq5dkic+vS6@6XvAlauaq|k~VO_Vfbpv*I{VJ>@J6ZuqY;Zc(LxH!c6}hgiQC#5X
zj0(eSV!Ek(A}gQ9f!36YZ!6AgU?p+JI#fpkzAL4F3z6aBs660&q3~;!bGkwS&p50n
zR?9-7u1y@GHp=y_n>i6s$nG<W#EvpZ{<VHJ8#-Xu9Iq|Tm@68#QhlRPTpk5<ldy&m
z0j_UAi*>`lrEOk0Cy&;-=Cvq-JGPC<%YGGl4M?<$lsNBMUS4y}U$%o{hVNMcujYqb
zftmy3wlP&94ZGXDO(cOS0LkR!jOMD3nA2o&l5>+$3%KKASTV=<XaJu*3e?sI3^}UO
z-L1zU6+c>*$+I9G>!Ldt%X7WbBq?`p;QMB~2j#1W(-<>C+0V=?w%l11`lzpx;#hn#
zJ8*ACikhr`W|cm9!kY29#@S?E2v*x(({{V8rXH(aH>fE~>xA2kNKZ6y-2Nz!7_>zZ
z#DI)~4_fMcJ0>sSZsg-WwaR5fa(nl#lShBvM#CI1JlE7>73s+wFm{qXX%10OwN}*A
z%+uu`?3$VqS~X+bQrxL~cU)v`JXhv)-?PO0&t2+|o^?fN^$Ue=&TBSd(zpCc7)@ez
z+5;1kN7k@q1Y^B^=YgL+2(#yFD@~COv>rQBcBMS?U4}!{<w)dvQx6oeb;oK$-;i)=
zfQN<ksQIY~rW}(<WT5<_uIW<wI-RRzfFA_a5x6g3!lt)>E@WVFwX;}Pjo{I6(n$J3
z(f8Rx!x$^nRi)`!nlzqnk8IwloYs<@j@9^1We!YC<K}%Nb{st^4_bHYO+Vz<0K=%L
zC;tFe{{ZfuwLfZ#KuVte)ulISCI_0$9?e2@3yrOjS9-?0(rSsbSDbO$h>rL<HTG1e
z@5V<YmW>ljxuFKCvB0ZjX58~sdi&SjWwN|a0~oa%oV6%GJN`7_IO##;99Lx5ykQ6K
zjAf{g2Lhzd1`RQX8S6tuCU06D_N&hzRXf%F;Um9uQ)!L9-1E|#crr(|e6}t&s?T1N
zybgBdKw^7VbfdWyt#r6=t!2u*lUN!Rp8~SAG~Eg6J*!oT=Zc|zyQ4VfwxaDMO!hgl
z2wIHi)~1kQkF`X4SFUrh2jxmf9WzJ|H1SD*ir9^@)}k$+YLN~y4KU9N=Ogm2c2L53
z?@>y_H8Hw}(A8;JGZH)0jBn>w^vKMboC}Qn*~hI@&MRZXarxTB1RhZ5>(-hEclRz~
zvTk@)?_Ou9FnhN>vTM>cXU3l(#s=PVUSl(dna`=Al8D0PfEmd()>@A$#W*0~b*@?!
z-EkQI0BBcPaD1y}P&y8VkjpW#F{wRGO&=9b)=lvG`_-uVJc^+g@E#s=E6??GE2zny
zr;}a$JVpLB#rTpinvr3^VN$^ur>ztdlSxuoQQnF%K+Qcm?&96Qbft%-Uy|bPa6(#z
zB;?>^)qNe=0VAydFhS40bPI4=J){--9&3udMHy^&(dTis%qwf_jWS7<j!Si1^sc7T
z=j|G9M&{l#k4ogVLH?5GJ!`1adD4bED6YzG@wvlQT2>g4d6MHC)aOrrs)rt?nz9I_
z+-YUj)-E_dL(N&3$FX(lhnj+0QlN$$4tms6>(fZTA=~SUqWAMVeD25Ei;RNxS2+Xn
z6_X&z#c0nsU{6n4&XPcB0bPeYQ)%Sn@F}K{#HXScIHvchp{9YBqJ==|Qi$<O42YoQ
zXX{cMz`X`P3ZV=UvFNATo*{G5DW7d_ql#zSUo>0^#k+e{v1#H)JMIKy&<<*gUC2f^
z@##$$5B=jn8ZueHhaYKT--SfcLIz9p_o^mL(?g8ni-Dn=ao?Y6UpfUpcRx{@q8mI=
zTNGRi#^y49Skz~}DW>a>xTEl@CQNkVnq<#<R|4t1e!x?H+bRAmeGO7F0p6Nr8KU4`
z`&_5^%{X4py(Kk3OP<vAeER+rTnlFIVb7Y?Z%n$8uhcQh`<lycYQ~&M)FZ=Vam7rw
z1Gelq>)NYGxO&k`SCJLQ06nu%O=`)WbM0Bv5zb#B^Eu8>YR_ofcO2H`^kGWmbL&~p
zBSzT(epT$y_zYP@f~|stQiWsMr=C}khHTV3vMXdD1Ds@iX{R2vr2hbsNZo0GhX=lC
zryjK9O(PX7Vh}Oc@urYE^GZf(dXIX_MI8p1b8fgKiqe0()Ye9j!^>6ALCtEj<a1tp
zw<!$-j!j@{Di-jA#dI0SBQ=Gqs9T`;IBq}B=Ud_5ye3fYMKirjR|cbD^H+7q5Ot;K
zC?BmUri3jR^`z#E@#$11IljD8a4}9Nj<lS9bO0}{4b#$r!Rt!>d7uXNr5sapQbso~
zQANN`Dau!2rsIkMA#vJ}0UT3E?@PE+6N6L%ng<4q=hlpMpkn%SKsoJ6+K=Zz4hIw-
zX*>1JDL9}61M#OJ^rlj&!9M<!0WtZqI#dJKtx75;>(Y=4xdwtT*rZc~#Rsoi04T;N
z29WgPfs5O{A>%Z?`qB~j)P;veyW|3yDtU7-BL<v=sn2swbu4;{h66)$R$^{5#Z=gR
zYQzi2U(SJ=npDO;LN-&5Yt$_td}F3-$}I-j)TdBu(=^FL+ol*EGhZjf6#exhzXvTW
zY6kbkIIyU*k=C5Y312tLcHDO1noRyx7DrleY*XZ8xgxh9Q_lz1q6`aD^OiWJ$nGnP
zo+;VNb;U+WJw-Y+c04Jk?4{UODY*HMT4wBb{Azh^<Su?wQJZNGeWto0hp74snF$+=
z9&=SLm;z7qtAZ_n?v)4Cg#c-xzkhiieFImag~C+k)mX|^B4wYumcaU&ie(Z<_p&`j
zZJXT~Hy=Jfx}?<`>zzK~Mg_oML`;7=?xBTr=gea|iN?lwUo3OYN`uTCfCWsmY5RZF
z+!DP5W14^45b%~jf&5Z8_*bNIm#ovxiFSO$rxl`YrYZnKpQU8m>NkM^x3jlZ^vN}3
z-Ro=)-y${bwmxgkt(L;9xsI4(IaQ0M-dM-Zr=HlS#}vhe(7@-Yteu+VyvcjFK8gqQ
zrT)&;AMffiuqUSMS3Aj~-sSyh+rPDvMNTqm5pFT_OoP_528ixIdvPlUJsGo3It{5m
zIVbAIw2n_rZcD`$qg!~V-uJKt0~stj{&bhRhL*$web1sHG?D0*BMKqhed@yL_K^*%
z5|3<GL^8@zcSO8QnNlrZN{D%WY_Fe4&S?&_WE<qQypVeAz^kI(5O5<=j-M||aEd&S
zkbNsxm(p(XMEiLZpIQt*cc#kN;AM!Y{{Xdbe}heof4t0prD^$SI8+~%3cTP9RmTTK
zbS2iCGk)K#$fPB`vUA-|DHdII&-{GF7(R(wrFwf(;{ba4){2ES(4T28=0}sN$^NrY
zll}sre@cYuw_8}rdpr7q=C?}V@l9crZ>1^Gk1mL6q^?I{Dl9}ZbmN*}z?9=SJt>xm
ziy=qn+N7TgZ~*9gSH<FC7*ugbqfOljFx<ZMSf7yp0F4qKlu}w8yART^T12svoK3i6
zIH}%skr(9|0-(DaSn*Y3Y#+UoUY$wvVbPlSi-EBysU_@qs-9s4e_Ea7%s|(e(Wtrk
zY1_T34cR`F@WV8$1kpAm?@Ipwc+?8pTpF3lJf3NQnEa{h-;>QZq4uQ%spB5hm=!uo
zNAjl4z@?OdHV5*gf0=5K7OY=%TYW1pQeCo^0~tID(6AsmQ~A{mRJWQ@bBys_*jZZW
zmWZO5?EBwZy#wcu=ULGyRT=(uZU@6)@N-<U8DP22Gx^hlam7O+1?Ua5^r)~FGsjw*
zCd!(mA0zRp;e7E@&=MSDsphNP?J&3_<?qK@oxb;aidD$NecINOw37$1<lZTVW~6u{
z?`P7mx*F@eWd<e^44(PMF<gjj*XZ~;^U;itBC52Q;nt)B<>+cL)}+rB*o;O<NcN^@
z6zN768K|*P#y>uk-1C|}sOv?*GfoDYC><!chm(<mNz=6e&}yy%b@io;{M62rD`CY=
z^#ay2#X8(#?lK2MOeeo4ndUk;bZ$Y-T}60;+`q2HxW^#lZ)(X?(zIs3d)Nv{27lSC
z{z0y2=urOMDe2Oo%{@r=t>YqDV6Io5zO@m+ILH+6*<WgAd94v6dKv`>gGxTXoeXGB
z{V3zsm+_>=KmAoB6dVs)F+e!#Y28jUNC@%Ay(m1>nLX(TOi%*jr(9HWdeqD^GHNLY
zG^eo8z<<stCqC2wXgrTf%wiKw=z7xQ9q6P0c%!ugpL#vIQUNiFDQOQPkj4|w_|(bw
zd8iw$O&1{3r?@bX9l0GUH9t2wshnj^RvaAX@}gQuNU*fOg)vTh)4}wsLKmO}0r*l<
zj+CA1fJ$CJ8c)ub@~HsrNI5+zXrKt%qXUYaxg7DDi=|^N%0hvPk$I@I$6Aq2DWGPJ
zgAX)%;<w;Az|U&uESZC!QhHZKZoq&$k6QAvYu+vewKzNz_*JJH;l_FIRb%$atC247
zMgSF#75mK>BLU);He#y4=OL8y_*C|0@>xE1l}8!Naa%&s8}BGJIEf=%jAOnly2KTv
zQy2gqeQKoV_ie^bIvSql?G`|t`+{m0<Q#KF#6fSwgdBbqu*c<5obg!k<V&77tznFC
zX^3h1eicIfa|!Ftaasg*{*_kjA1L>3)wL&SA}6uRg&97*IH#{4(wgd4XCCz6YubUs
zB4s9|1Dc65nwLF4t#m}jMVJp5?^B+nRakgE>drZ?g|W{q#xMl)`c-)c&EBjq<3G}%
zkRM8xTuA=_&ou<Sc;==(Mk+ad`qol5i3lLl{&aw2k4kU{>rjhh<KT?dvB>X%RS@C7
z#;pQ&_N`)LG3a>!e=4()fzRnxk+5_5;;e(7GDU3@2@O3z#;dsG^vzf!E9+1{dL&dx
zhB|kqH{I(_!N?TG<F6lD$(o`(QJjHCw-jfmKZQYKlRJSp&v90e9fRrD6;(jU9kbk3
zsKDEv=B^}2c<L&3C8GoSQ~(oGf(n6JqX`k5W3S;*Fz<s_8<KHV+<R2WsEp`)(;Q%$
zcpUNh(_C@Wn$4P`F4UvbG`&6PGlSZsp+V#PYRVCSF;%mkrmQC;j@3w(NSM#PSX^u;
z{{Yujm#NR;RuKH2^{OzK)+5%dxB{#<xd-V`KNLuC8Tx%{C&={0N>3TZM<CDB+Ojr7
z2PT1xa%nTy7!;$ENTKWZyVZs0I@Mvxt1+;^^{PZM%1-Wi`qbR*`-dL25|P@a>@W}E
zR%XU9Iq!;r^WQ&}PX7Ss6$|isQe{Ms@cikFdW?0aoaUJI28fI4Ksi0BPh1L8NgQ?h
zQW&ZZef^DCP8O?zaw=p8uRPEq#0|FU78u6h57V0UJv8pLA2v<{1MOZ?a#V#RbmUj4
zXm7s8GRgtiI(Dyy;;MJ$k?du!Mvn}WlbUE;upYGL>r>gqnSo)zHEAD1BK57l)L)cm
ztz8On=zRr5e|OWIcBE<C<D6rhP<j;Y7?Kt5ij3fOYKBRhZv@nNb~);34`@zLVOMNz
zKHW0M_p|D2J|!gbI(4l*HHu8d22cAvXiHN%vV4u6jiA|$KG|ajEO@KBjP|Ih=aeVZ
zbrsBLI<3@<@m#4~ebyqG;tx5tNDd?ZB5S1is-GFt0SwAEox>H=_)Zutp?J~qdXjpY
z^F0b_Rwoa*C-C;JgGjo%v(_S-DG!pv5(YF}gU~f4SYc^E$X`n3to56FtCqJY$m)2?
z<8^e`sx>V*qCYLjuRVuGxrbOlQIrSV>{$Mk0yaEHq$SpwD}2KXkZZ?U?QAbu9Rb>K
zN3DGhma)%jVs-gsUiIa^Bk+%tsJVycQrSMW6OGQyEoBSFTO3W@#CK8&5jKI-H3Vu%
z;AiPwj2;nZLe6&o0J23wo*qc0!ZMMbaansNdJ8d(J=mk2NM?PZB6cm@4AjqUEC6}2
zNQ2dv73%sNdUcd4jEYGEsOeo?x(1!9S_cuUag2dg?1e1iYvD)FvF2F<ATH;PsmV3d
z+V~$_xQ$(4RYEg^$*)R_!a8Mz+FYb6vad|7b+)bqY67UI?4m=?D|9>-!@=6s<?CBD
zoRN|IZln*+x(mOCH@4Q^WOA2r&pik0UcA%5l7%}_&w8=daC#a&nlYYfh?i5wygT4k
zxYX18M5_fk2%QCb1<!-D=(P8a&e|~|kCjN{HM*A3Loswv38`7Ir<$%*j4ER))OT#j
z(5zYu1&-$4G?jQb85PfXn?Pr{W{M`+Cq_=+{d(zQ*6j`Hw=NZ`?d{Aq*0N12e(h9}
zX_)&-UzqXTb3lKwm{_yz>64y)Yk|he+7hRF9lUd1->ThPUfHy;?I;xU{uSf5Y!gwJ
z%}u4710Iz!E}XSAY?vtE@OxIo7a78wWqm6y#Rlb7Bm8S}2-I!u$9mwI=|$*B*(z~d
zpNNz)I3pm}TOxp`p0&$sOO|C-9WXQNQ%~X)*`ML~W0Kco$~P|rAEi~+V20g+j19eU
z(x^=L7H#s(OCG#cIi;3&V(v*j$7=3JG@0oBAG^1{)6^mRykz&Q_Zm`3^B392BOPmv
z@T0my;kxe4cNXrG#t^nxRWp)Xln#?_2>H3BeLC4sI49{&)NC$Sl#?iW<E?Y@#dRAT
zvjz1zsS&zkf;9kb$DpdWGg`p8Tr;=hSj!{E{{S?OaoC*Is4k&ySZDCX10tT{Nr6R;
zfc3>tdpDCMx_`Zj)Va8S`DVCU%bH1BB)&82Kphu`Y@xG(rPx@L*18nbtkP8vo_$uS
z_-+vTDwgQn)RO5c&ATTV=~N?r2sHc93QB;tLNF?EpaL@#h(Fpj&Rghd8*e0!b?aIY
zwZu6-e7}!1AY48c-zv4u%Ce5YV1GKZGg;}76p48Qpf#S?leYw%cdA!1i9Yc(hGXj2
zvR}$^ke<hi%lkTmoPL$M@JIRfs&mAfaHkXu=Wi`?eo#Gttk#UH9ktNU5pKlQCx8>u
zlL9+TGVN}@rmp>-L|m>9J?f%HV{D9P-n8wfblMv~g-FvU)8#Qpi8FkxdkWFit_`)L
zo#b(heQLalHi-^0r*=<DZlf%7!okjPI*MR%mqk<;Aykri9nDj*w-b4@K5$M2Te(yS
z`Q#&HW}<@W64ewANXv8Hwx*2cS&Gy!&lO@k+b|=aVrh^``?d5uijlCxq0Mv{mN)t8
zNaW+CV9zV1;5)JZ00HY;Hsca!v8Zlz_L}7xdIQjRsg}jZb5;x+bt9=A>6dQGoFA=Q
zhA-WPWyjL0-h#1_*FCGxd!DM&Co_ECe<#0DRgL0XS-Oac-PDm*Z$Mc-ZZlEIWj)=9
zYgi<kCmBJS=%jJik;}`=l6&^3`c;dl9tpNe2q(5NRqz4EYg3c~qX#q+DLG;lK_u`1
zqy*N`%X4y&LOypj>|Pkt2AgEC?hPg~TO8Lf;k_X==zQr^G|kCxPipL}CE6K@zyql@
zDczg3%LAU(n5E>v^(~soV~$2ES6N{_!?-+(#y?tY<rJTMnrZ1q<sQ@m4FEky%S|JJ
z^K(FNS_6F8pk;fhyr^3pYn+<p*_(0eTDq0Ws|5sPdR7F@xw0vgHIFquoB`A!z{$>P
zwrhLCmg&8&WKG3>@3jLuSfkj#G0uBax^$pFoA-uADJSXeP|FlZyQ$mPvF4zVlB894
zC40~!_n10Rul`MEi-r{8bfoi-!ixc+xG~2{UCKc_x$RUw&<-$opiP577lfGa&(f^L
zHht?P%y(lIAe@8O9@GrlS0}&cPg(HTagps=3vdV@HAp2MS^2*jKx24?np>5_t_P)a
z%z;l@($ua2xNtg*4EC(!xvRDdL!It04r$Dtg+3^YJx<An=Z|`{iMc_OCY$Ax)MwtW
z6k2}N9OLw(kU5Ou5%i@opGwhPp|jGF)HZ2*Fy=FSquPy!(yw`A98&~&J!%~>+^Sce
zK&Gzf+j16D>J3?BIX={eBaW3W1Go)B^%#+G^<_LksvsDgjCyyffhaNKy-y(SXs3y_
z6&NyP`qTda;V8f7<yJnXvV>=*Da#KdJ?P{SsC-YU5&pApxD^xlhf-mWKk??O3w&dq
zw2c-!Q{)SZ+Li2#OI*J_vT8p%QZc=UuwzmzLxWNXxT@p}qPEiDWR}ONq}h+d(ybWw
z<I<6ncReZc1;|un(lTL){#7(X58IDXO_Y5906|59<Y6<~oD(9Pi_bLi!Ry|O0D%X3
zMNCLI<J?rEuUbYpk$rQ;G$E}RSr77{0qM<Iah4?VbInA{&00jZG$<a`JW4V2sL%?Y
zJ{Pr7B#Hw4YSd0K=~W9<(GiSLA@@ghxu~uF`1C#MOOgJL!lJQa;YLQ`*wz(IAZ}Wr
z!N=DXy9`evMcT4#REc(uMmtwcrzv>U<L;bSJ1nthYQTWmt=QvDyz@+gAD4yqt0jVc
z;-ej@2+8pbZT2-Pr`o)}`ptgW`&S(F#d?p3ZiCu+Nt1!rxGAABOmMl!bJn_OtBA{v
zEsL}t!j+fws}jUxd@#YNSo6&(t1^+drySX@Yz%Qz&ls6P6Tzz5V}GLHcB?MLE<mLn
z#L4Znm>`cWz+u?eA>vl@uHp&&E;;oT(uwAA^JP?V&wArEsr>1iJBd?Wa`;I{VPXW4
z!k{w|fnJy4*o0_+sOG%Oz;cVLt8|m*T#x>}dvaRE3n@hdy>k>^j@1Y(S2-A|5+qTD
zP(7*9N%Dc|Pb6fIT9(E+aJ8L!o?$KNSIE!!RePV3-QS=c&lDyWIK59tjhah{kcY=X
zUQ>Aw+4XCP$RV?u_KV45SX+FGfR3fHURUB<bdOgOMC!rM&9v5+xh&?jq}^?jxy4`~
zyUr`5)zr147Ck*Hoa(jFN$4WG9<=C2`GSx!){y>mM%x=TwBNckZ`^AaKiNOo%<HfX
zxgMUFte24_fmg{u!?<2)vQ6i6fG9}DI+0vGEN=)1iI(Y#oC0x68UTH2ZJ-R&HZ(MR
z$GD!p)qZTT2fxy)X^Kj*9k{JEws#;NE0(9kA}eS&u--@>!n8teAOnF)BUmHA#X=aD
z_RVG@;R=!90CC=_%;fzlSC?Yrxu~O(J>R|!k6}_Wz78@eo1+bhaBD@L)S(HS`_&tm
zV`RuVZ)yNz+a!NHZSu7(u_8gxRXCg@><0p@MBls|;<tvzGCM6a<|OHnitpn&wu!&l
z9V^as);><&!<zI92H&Q_Yv;I%7op5_;NQH_B!C#$dW=_(Ymxan#mcUJ@glv88B#k}
zm3Xc{D_L`n8;sYN!?LwmMCiq@aOX;$)w!jSy))n1u^*G^TN+`^YuK-P`&sJ~&0C(m
zWJ6lVjCAW$Fv`^(8c#Dzi_~OsSJ&UAeq)P|CMrpHJ&3!b#C&aTA=hNbPw}o&QS#S&
z@e15WsfYQuH(}DaIR-`tPip;_B&qE%kbXyjidLw~<AX|iQVwZz$0EIhoD;5Tag5M9
zkLyDoeJBCEXVROF^ts1MLV2KL*QZ)l<cyqiO;M57o;vz_)^pfvbKg82Ik@oUzJBmf
z4RkBkxbKHkdA=S|yE|C_06Odt;=d8ksq$m0Bj~8R(@c}KAso`uH#Op#iTo7Cr;e1y
z=~W%T;k-hgR<v`RGSy2%`?em2wES3`FJqTD?fO<tl!#<y9Ou%$wuG-v5;>*2FT|Uo
zY*jEYNFx<;(qb8b9DCJyMka3c_jz3IczDR@M@_~JI+}UwUbRDpp2J&_nuxa@DpmmT
zOks+W(V?Y2cPHsqF2@<|RJ5ksa7P0ow62#cUptsa)oyy2cX%A_*vm2eGg(vj?mcT}
z>}5z^D<WZ&Tqi+I#zj-P03q*J81ibo%at{xHx!OqW&PuSym}gihHB;7?3nxZs%M(^
zBdktlH?J9`2a)MWIHR0n0)_}cIcljjyQ3B*arLW*hTv5x$yo?B&mxf*dRi!{7z*jU
z8woe={ZtQ_{{VKmkzKcfA;fY?kCmG_{VBvxV^hRTQ%{jk@eEg-9$4cw-T1O?wxI(N
z>+UOrJRj1A2(hO}=3mA?8s609+ZH;Uaqn3gDsR8f_eN_+Sdb)PKOE8qS<<E7YtJV<
z`&Nu+=Jgeep|<E*dXei}NVLRXx8*C7@l0E8Q1r;nb+&xBpsXJlp$i*hpyY~75yu)z
zQ%O=-QAHF1y`(7ef#aU_vw_YHP|@w2>HD#OeQQ$E&gSfug+5XIXQgr0p()Df?V(yR
zj;02xhs<57NhbkEdh4{iMz_;dTw%8Sz>2eNpxZ?td6-Qg=m_9d=~FS0#@ttBIP%8K
z<f|nqT^!BOBX@E=D;DHozgpkDLNa~x$*c?Da^E-M+Ngr7N~_;K)miRI=qfijs91sN
z_*9H@N?WO@n38EpruU!(rRhPUfDVSFjQwgldUd7@vbiIz3{5o;PAS-?0uxA2)|Asn
z(vSu-)|7GF&_4=X&;j0zA4)q>_|pN)fk_}BW`(E7GPHzKC(z=M=N)*d3iD0JGyubz
zFlqaFqiLW9;--xH(=p9S7y!@&gm5ZLcG-Cge|7UsJdTu$%c(qodKyd*O4HmunjGZ%
z;-s7?9XizwA@gFJPZe@<G0*E*(|U=RnzUaaVV)}nMh73xx_w7uTkXeQwadr}Cm)@A
zIA?g6v63gtkVn#^!Kdx{dghsfT>=}9X;0FTxIJhlfD@<Ekka+0{V6ek9AsjeT9+8$
z({MAM)s%`xrjp>3`qtjuu=nj)8cTlsqMlDm=>XilGh8(^Wg)7+HY+Du2QiYMirCxp
zVzV{0#h;nS6;xfM49GmTdsI)uP!2%A;*t7Spk^<6G0%EI&|;h@0eYNL5ziEJ){`gc
zRdEZ~){u%&MmfzVQ%>L<XT2%KCp=Nk-t>TPr}L>HZKsh;9VvT?0FaT+1veC9k~yU0
ziej*IJ!uIvcgIRG$8W-z!jAn#1bfgjXt)YF?@5Y!j-r@PUPTueccuOwn5G#N9$0>K
zd8j{#QFIm@GuNP_@aNi^g`fRgQa}5vQmw7yFxz8td;b8dBBz-Jg#!ngV~(b;MWt#|
zk&79Ar;4(CH>tY+0IH1-yHvW7T|&k%1R7E^TMOY$MTaxnC*xLA!V{61FOhTo(VCZ9
z9m?d9&V%^UlZxrn!SOc_eKUW$wPidXVaDdVZ+zBo6HRp~Qj_R$!NAQl$fNjx{A;?8
z!rEj_pR>Dm`P!_mkEKPDY~UW`)VyUhQlU4{^T8@-mg(tEZRZ6NQ}j&Np)7h_Uocx0
z1HREuI-P`H^6>~i>@I65V_;~om0v^8658?jOFM=>(VDkyqv~?Yx9n0N^(t$$ZGONL
ziR5GGqZJc)j?D)GcKmBUuP(-m16JD@F?e%VW07tY1KqGqcN!j@b8l#?c`PA-;|<Oz
z)1Xa4HJEN7`kK;R4kB_wx7M)4!D3>R(Ucpc$-mLnerw3Sfaaq&HVeVIk<X$=$NE&s
zq+6~y1L!Jbu!Tl3TuUvb*wgD0D7EFLPwwtp=rKrdkPnj1L)+&#tx;<VkGc4o1QCOr
zR*M5kbQiagkTnZ}aUFzt^)hGrQ-$89NyW4S)2(a>)N}w)P*#fzNpvOEk&b267>}Gs
z?5HX?k5+Cz*&z1X1#7gMKZ7+HxY`cbdU~3_V+GKcQcTGjUE`AS&oh6($Q3GS8@YFK
z#B~gKtIa&G&dht}gn2XkHEIz;=4EBjt+?OMu^Fl3(QLrMA1L(Vt}gPRlS&Q`tx$*#
zn*dR;e_BCjY`iu;gjJo*x6-Q5miMJ$5zA?22tHUe=%csV07Uv#Db`nTs^nC*_U?=c
zeCO7f8YvPe-~sqlrM>y6l>)9ansx>$fM6d=P(c3x8g6(r5^?uUASDV|cf}^!bZ$y|
zQXH{7;+O)Bt)3~^$67Ig%`V*c{HOt+tr*2WF^|4+_2Q{rY8Ehqo5+ScZlDVcbNpmd
z#xdNtzgp+!*5DHmk`_^pSDMnZylbV%M^TLY%ZdQd&pkP$&&}*<a!T~1BO{Kq2u2}C
zUTL5b4m;DtWRaS3f(I%1(qk#d7)zC623Mh{-)&byyq<)SM5K#>$4Xnlx&i%b<1+|y
z;u-1D_y}3DnaviA1;#lU9cmRIrYY9!1ml|F=xR@TnaTcDm_sQ%5C=-uzFpf1B}aTw
zslg0((a3`X+PXcmbkqfHZe?#IdQ{=JMn9!j;CH8?%44l(VuuI8sa5hSwsA_W??)&W
zgJTt8n<z0^;p*By?tmttp%MnhP6bG!s|LZxYOsydik32+(vbamp#9(JQ(dlks>7$f
zS^`^E+c4@WZ!OI1838|DDmZ`>F7H~>JmVZzk&}+7Mk_?hagLOzaMfz|-IM3f4OGVm
zu4rfpTZ2qIRE!B)ZzBSb3a6z_ZrGBdUOyUqY*s}*su&j-dVW<C{nJt!iQ0(h2M^;&
zw?QFLKDEJPIsB{B{7(>jGI5h$U{r?rzVJP3?{bQq*mQZAm1%&dC?53Dk<+C)Mr+td
zD-u9<@;^F=eidQ4Q`_rR&r?$%3Omz)$;VHvD<<FmwIPfhI#4>&<06x><j^5<MJH-p
z((G*ePy;E1;ky1cF2Xxg9eC%8P1t3$IgcWvlyRO#EC(n%igbe`=~}&FA{dSd=8=~z
z{xqt%dI`gIu64M^?LCL(N(MU`c<1n>Cbv<rfqm(Ed(sLs$F)0%cUmxU^rowKrOr+$
zxCztLQPPxjG?WYm4m(qaCYnC=IeqB>6G#Oqz{fPvpIQKRc&51HnvgC=X{<7OQ9Xc&
zbB>g|X~9lCYFNHbYZ8bG;P<BDuCjTUJu^@=TTf5MnpXlGb5BGJaBwqD+e?BwQ{@%L
zyg^R{VxuZ^Q)APLX&iG)lrC0b%}Eael0k|i>x!6ZA(9jFnykx)s|3_C51Z>nP(!0Q
zsR8^d739>Q)kGMp_|bunUuspxYE-v*e(u~3xvCKlT07I32qaP-X$Sz#CNL>L<E0_s
z(7;ZEiiqbt)TW|twTz2G4_bPTX_(2UuldbXL6+^l_{RiSM{L+!j%%5KlH-9}_N}`d
zf%5b9t_)Oc%897BC!oz~THua<EY?(KCndXnb#f`zHqL%uYV+wyMxmoLN!yN|)t9O2
zscRde;K+Ev=BR3V>co;PKR60Yk-_{clb=#!AvoN`?q(-BHRv~TY;8d=nK^lOmnS_d
zbR0$pwt221*7c;gRbk(X>}~#Qb@jmSK$z7h%;T<oYhp3-jNoRm!2(tK*0r(U7bm4s
zB!1ElZ^Elx^BEZJR`Zcm?tmz8dey=E!j{J`FvRXN&#fT9_o*%i`a`ux(!I)i91|s9
zygJm_>-}mK814Af;Bn1##KJ_8WM>AgV4A3$8n~n7_pRfx&n?Cgfz4N!BaYQOaC&4^
zG7O(eOmQKor3V-TBBmmulkNeE&6~u79kEUwsl89VIDT~ogVV9ADa3isDySzoB;u_h
z%8yFYCNmzrf2~?xP#weRRRQOUwH`JPde$Z~1DsS3-!(ZE1fHDG!X!ZCnqzgR@to$G
z-1Et-*{UGO{5|L#;Lt}s%_!;q6$XGf1KO=ZaJ<z}Ni}96!0albM2SGb$u%<aoxduB
zJk-eFE-}`%MlunHLz;nsKU$s0<Ww$4;Y5NYT#uzAe8U_HUbHtNvSz4<jGR)6LU}Z2
zBRwe=0<1)EwE(H3$E`F(i4>lsin4?i;MHNA^s5o)6{<0itb1gNfxtC8bgJ#p3K-x=
zj&LcGWO`G{`HeC0kF8|Qkr`iVQb6>i&NIyz$)r%d#aTg-z^d8ir-<ZWjMX9}N-DtQ
zU{zz+{3>+G8LKm6U-QjC<2?mV-raLhx#~JnVG=J<flXn>DeL|;*64qwL8>Do8K-fA
zKUz#=(vFmh6n*UDBBoDF@lXSbnLh0T9>*x%{!?C+;mJc-E(s-9w_5X88`Xw7*P(bx
z^J5>(OKdqkGhZLYFuf$v>SeOkqsK9mfIkZAd@G?zs@^Io`9?z@O2D&$r=4R&C7kVF
zt$UAyyfHSFrL4gNT{8T~7^hAhS?t%Z%c40wN5OMJI11o`I#qP=HQmH!Lxli!#d<vE
zXd#)dvSn4k30M(o*H38hz9TJ=205nb#K~i-?Q@Es!SX~yd8Fg@t8n;g+884*yDTzE
zHKA@bA#|`v`;pl4I}fc%tXo`&K!}p7)OV%If#Rw@rD=3KSmWFZp5U4+Y~zW(PW<yy
zT17PWepJtfJq<p>!fQ~=DJ&@EM15kTR%{NTZv?v>V*{!6tAbdjkM9OU+*T&7rN~=)
zWx37;UDG0x8*Pr?g)<kZ{{Za^Sm!XLqdC9_)~r3_+b;DSj%uC8pJ*i$GJz-es%Q){
zqePCZI(48&WuR-3+}n({KfI@?tGb4(XC1-^kwdotoN{Z6u#DQdF_H6itG8A#U&$N4
zB|39VM{jR-7TurFaa_IC<g#iz(Rc3S0P$M7T#K+F=Zt*SaA<LTpiGT~>QfXA5nb9D
z^zslDc3uT>cDgp94coQP+&RW`n)H|397M4B61fY#b|HH3x+;R-D^eP4$Go+8r4sJK
zdj9}+y$`}^GHHX&R!~%68t0&v2==thtcSL1v(lx8TQz7%De5VT=2wZVbt{L4O9#f&
zxSaI%tNL@!EYMtI&d1G<TANnXVzIXy@>#k8)~Z-v!FYk<Z1aX5hthyDb#Zqc;5(S9
z`Gz~!O{GaYY4QD_A29RJS{Oqj{`+GA({)%}1si!7?MN<VY7pv;slhe0xPX1-t#XCp
z+ni)#sb1=F+3f@tB=pT%x4MSv1)3MiA6~Qp$KL4EjY}LM&RNHL=)8}%SbdscLJ_o&
zTAFLCf3_vNxbs`?j^?Dg1`9bI6q2jjkQu3?TS0B*L=+$!c&{$;uZQBZX)bN{jAg!t
zyWJ-8{^sPvI6kM?=cRN101#}hS`hK6W!=yYJJMw*W^lHW?I=e8b6d8v2@nu@tQ&ZW
z@M~Jk1U+klrst;zp{C<8lhZ%Wv9C0_uX50^-a3Xj2DB!*0XFriG>0#6%s3s5Itue9
zysZnIh1Y}iNmwCFjPT=vwV@ZoM|i$z*yp+)wdpH@2YQp~#d<!@Cz|WYoED$qTa6))
z3{%`>{xxYNdue?uuDMS#-bKy{7~;7*;jo{VBh=K+HWHQhG?mh5w+=z9>&tbKPDWcC
z98^{pyCm|M;2twt(#5_$x%V}ZXCrlCo<SSEYboP+ob4fpsIIc+)r)+;m1SI6ka@)e
zGgeLCDg5dwtxSWA`(lZscv$dy^#YmZkfdjVDFNtS8;GWh8o1}Mtrmj^HD5rCzLOJo
z_UT$Blngf&LMuCLP7PPyU8-45<Ht{0iynYe0mOW@LT;zltjR9ltwA9322DWGMavKW
z09{s*_cl2C)!8k}3=Cu5tI2P(EKkerNM>}y1E{J_K4G5qZsGDubH{q7!!1Yy89Aw-
zIeuz2ZYpGtIB$9Y(sBeRJPcyF3(Z1!uHPRroc$}J)GmCxH9&KmWLGnE%jJ^X`cMU1
zsnEx?j5Bp3*0V{$<BW5GR-i+2ShE2d_o66##$(iE*7VHePir|yl`wV=F;;}cdh<~&
zzCgzmq9z>Y0~NWMW;yoq&BbZjzuG=%#zK*kOw&9+HPI7XosjlZ)YnF~(WGW55CM+W
zGx$n}#8ilUnZV6a)P@1|>IG{HNkPK>?DVSIj+=4izsr}vBNgYZU5`!Fjkh_yKSrNi
z)QmA9Fsb>UHSAs-(RA%P#cejJ0AnY;a#{;p>2_ywkon6HDr=7y3v84lk80?Sh~cR2
z%x{Xm7`B2Bwpt>oP)-1^9AzHW>mDibQ|kJ2!dDxYk}Jv_<khEhA(*S$JaL^;BOy3b
zk%69SiO3ayNJo2zZg8TUwkn^*cfV~_P!SjNsnb#k3kEpNVp|--38?3r4p)(i=Zmq|
zG@7w`;$b5;4(!%>Y-XTqr&i#f#+ug|Jmc$Ha~!UniT4BTO)u|NWVy-XimvmV)44v(
zywe5#AzAktu}5@N&!MR2n`A71iMXtmI6l=#O;~)>nOKr}J!%4TK{S;@4A%FD9Fr;%
zNbD;Fo-3#D-MLG1D-rYb9@Lo8&;|KclLIF|ohqDC6Pkj?FaR2fhcz)ioYZUwGzhNa
zf-zAvWd8vAs$#hvIHn$)XOZ53E3%)ZAl^SZoPd7{ZU!g;f!$7X^{G;3JQ`*fGy*X|
z7E(?rWs~<u7!B)Hl=^k25=#8prnd%STzvDnJ#)=D7ml1$=NOdWQvvN=u{oJED~-nj
zl41zYN?3+eagoxbnJ~Q75>(ntQ?~O@DNj`ACYXqTBhwz#e8>L)uU8TfS3SKmNL5p>
z6ai31$FByYNK_6^Y0mjLU(TAKvgar1NMbT3dx~k>O#tV)`q7G37!aiN#W9kk3z0}h
zDr`HEZ2alUg_v+D>ws!_ky)vOV+s?+Mq(wnAEjHBN_{FA&T>yCnKvTxuzFL1RNemW
zX{>RIU^f`eLPiMUq}%`;^G#w3p1)c{78MM{{{VKNlx9;?!b<0@R(8vpl8^(BN^oF1
zR9}rQa5~Z%F7t{Q<<o#ZYL9kl3CRN|)`1sYu-z%0Pi~Yu<PQ9Gry#-RsWMs-S2Zdr
z#VU09e>!m|J#&uLM2&2NPDwCEI@3wr_4cKXCXzq~1s4KKiAc6)Ju!}bYc4y7Mg>nI
zuWC%O+3Zux8pT#Bde=Q&S-m86);AYH6vpTL4RrQ1YOKMO44UM8KXM&_Ex_YpuTjv-
zOBf1q$7<r7+C2(%BGt#*M}H(C<d+`Gaaos_Gg?f=%V*Q6uErSlW1-`vbG{<7A2Xt{
zAY@{q6+P`ssX{!u7&khu_|8cu(x}@?kGT8ytmh@2vCSe00}_Lp^ynUB)r&frQ#jjH
z8}X;RxqqKIsLx)1Dk|<IYiVu!mKpC?m}Ghy&(hn6;;&?dCmF?O9mK-%{EIS4!!YAD
z#!qV_7jV31oYuAV!_9DaV1f5@+Nn);$fZxrE3WzyZG1KP^|wrLt<%!Iz|V*4!1b>e
z_->(fDJBXASf8zW%#z@B#bVJ&(o5mVGAixr4OG1Gj+0`*OK_~-fvbVmbxEStq={Uz
zNfto#`d6OaOC*<4B#)2@8!><@DHe}#xcG%;5P1baJ<oct;yqsKe+|!Yj>_9|0N_`U
zX)|wvOH+c#z=Q2xtm-a&5`4@qBj&J_nrPJ{%hy}Iy0zHzF+Gmz&x-2mTcs1W@HhuO
zD!!XPm8wY-@T|mb0<Ygjuv{Sn8=D!eqRixn>SuME^Pi=2Jrv`&t#r4mx(D>fKGn@0
z{+_kjM`IEe<JN@$p8o(!80D$ajGmm<wI8}%71<&$JvgZcEz*Ttaoq4RQ;7C2J!_2X
zNJTqF2U<MVp?xz<eoY~>e?%v0$+xeqbVgz2^}+V64HiJQ>JLm-q00^iYnFSGIp2Aw
zB4K#zOo<MDY*VCuflX#28J$<}8h{@&qhsq=qK*kNCQaXsHLYyMc9Wm2A(X|l1CuB|
z!lX-4C*GZxo`R%wR2W8FQ#_d@A1N97&;@tW%u+OqFPW2*nqm#Jb54<O;gE-A+3igP
z`GApHz{*EWrZ(Z%wRgHBnKZ$i4X34f-jgO@o|xjh-wwX}Ia96<Ys${y&4p&TS81BH
z=KeK=CaJiNzLn_!^P1s2aT!_Se128)85H?(Ry%PD^v)TFHK(O=pmwb3KKB)SN;q~W
zrg6=E_UQ7DQ}FDe^wb02n%Q1h59eI}0EOH&qb7Lt{A+v>U!3OD`7v@mYEJM+nfywF
z_mNBK`q!I3PfGQViBOi)QdP*?)Z^N`o$yb#EA;Lcsn3Fm<YSep6*{-|rw*Uikc>CA
zD)g_WIK=*R=HU9`n@&0HOhY@<SW}Kcp!T3*r%sf;N2N77jOLtr)W{E8_+3AlVKgKA
z=K%d{&{n*+;bhxxWw+`EI{yHlt$LWo?kn;RE2YVea_)QhM|wz*b)-C+1qQxQ=@3&}
zj%i0)54AK0CF2-Fz>ZHtn&zwkj_-~O3hcaBADN}IWA67A#Kv~rA@{GTz|Wr!k<U?k
z#?(h`zyxw=x=ph2-@QbH`Qfvi`qhi22MjCh@|pZMJe*{7Wi$1rRD|SHPeETxQ)9`e
zxYp@W5=~0Nnnh-d>PcpHTmy>OxaBe{4lX8B=zG@do$w<9er2y0G>+0e94pes9oXRd
z)-}T9oL2SN%Ms~Vw=45EHRPRUa||C!uOP@im1af3s_)Mf&@-LX6ZgdSHJ;-JwRJE&
z-PM-on)Rs4@JBqBq<`l$qt=>uIiP)WT3kbzWrtd@Zc$?Z#+mwaRnN6SF~>EGhD~*J
zl13CL81||Mtto8rO#-thU-O#p{3#!mrVMpqpX*!zQdlVNabBUKLLt)Q$M<+2O1Kjv
zobi3gGKk3P0Q_r`>T7?+GVjzjmK<|j`5@9`TN_#c!^p&YW}U3aH|-rwOQNBM)V>BA
zo@$1xCi(Jv0Z0pa1fM&mM_%>5j8(Eadsj1|H~L{8!``|)vh$7&0BPDb82vL@ek&X7
zbF?3NziQm|>M9QrD19;5bRDU&BhQbuHk^GaDhm>pj;9rFD|pJ~hJPAhcG?U{{gi~S
zBms)qhGdO)ZrBHE<E{0Xt*urVzzRF#nyEeY;}&F?ob!V~k3sunApQK(Np}H^{M~EK
z4y|~Nk1~*JS4!K9f=8_v1F^hd%v<<#*0Ao?a6=F?S#PdhNVwdi*NUel<nsOL82&Ve
zVp(<qagIBRtjGTV*Gw!=Q%5uaq?%5ql8OK+MHCLS0KMr{@+qUIG^2_Du$jd?o;mAL
zMsjLWI5fm19VvQ>F+juumyzp7Ph8Q808X^H&w4si&;Y%9bg3A8oj(d->r$#^Kl=2<
zRx8h?I4bw%oN0{M_xe%-MP*)!DSXfNSMU`9lA2^E+JGjJ@;>iA)f$hQnh7Jn6(TA8
z=mJa}Q%aMZ9%@WsdQuKe0Cv6}aQ34kr&`sVF2j!1&iG<-BXlQ?-79_0<UX~{Pva9a
zZxlVb$QbLM_07siTyitiS5rFv?Y^B2b2E%cLF-<|74$NZQ?)lf^!DPTC(^o^B2h<b
zDO>}!H1(%v-kVC}5S}T$DcM?U99D8=7PQ92@cM9l>#ny(XhF_vjj()QM!iWj-P%XG
zCHJm6yOfH|xNd5mtbo`!KXk8e=UVc_s@Xgrde78RL=KJp(m3zMC_P4T=*JYSa=zl2
zjLhVDZ@Zj;Dpa+*lz#5c;fG?Vab5S&hq)N`{VDm#s|%y*t_I5q{{Y}a6>>ieYYu>z
zBahwR6uqQY>{c^(V~TEi^II$7JxPzxacdvd^Hay*+4$e6$NvBTOw#ty?pL#CJ-B9+
zkSnNP2V1ZD%h{O!0J1So9u(8m^7l{v^8r)!nro=lDL#iOy+?o6kjS|E!;aam&3rke
zAOyxwyGc?DJr)o7V``_>h&2xxO%|~AA47!`DE=W&MRt57Qn5aWYq&{tSV#Q1jCv(V
zHJvUtA!Hx$6auq&_#;(;toj^iv%GWiS=^tZaZ;|4s!DJyB_8ZCU1NBL(0$)D{vcE>
z;#31GZzFwPrREEwG+AwD(7;a(YR-9zBp$5wI(SP{WAj{Ep!Ez*Xt#+ZC*`(5?&hO^
z5#6`kNSEj<CzzW@DXhxt;Omd$zleJ6T-A}__(03u&fei_7T0wa2luK6vekFg?^xvA
z$@o+}!bY*l=hd1~cu!9sdG6aDtN^PC;msiiKFnD9yVe6;-7vwpl>Y$0%`nL9Id(tr
zBU!w3*|c(Q?CKXz(V`#m?`ARG@lG>n@Da1@DUU@J$>5x1^!KI5J!?0Mn>LP54y@}=
zv8Eya0FQ+K0Dz@L-XO38D$=)Z1#<m6nod0{H;9`yj#Wi&bf?6yFH3ud`mp~18io8#
z8)t2y&-+HOc%{nYrBAh&b7hxMT@7~e9m5}%2v_PeQ9iwX-*m*EM6Au!s;u1sKS5LN
zB+V8Miu)zT*0mSwagU<ZO{m{K16;^{jB2sS?adiJ^tqX$!_!+LLvcI(>0FOZ#+X!-
zl31Uqq|F&8){B;*70@s+cn8-sfPalHGHGdCc0yu<)3+4tW|Sx*ns#E6x;-DlQg73M
z1RQ@l=)mH*&j!j&Oq;qk03U^Ridm1{!q=w_Vtj5UJhfzn+r>0+dehHLQg^CG1M!ur
z?ASFp;Bs?FVpGrQKoJ>u^`<natIJ}hXx9W)3AFPo5@cY#uxJ>qaR^<;Kt0K-?{^C}
z(Da8!w;#tLA6j~8u*ATC#QV@9SXHDM9MjS{Gsy2#K@m}bfm4L$fFTO~v6=)fPc2h2
z5HXrnT%NRmX2k=kH5({BYQ{01l@y4?=Yc>K+6663<$*|5)w^PVPI)Gn5}_eaS_6`4
z%EPDgrj|M4fFxBt=@@ZHtmNZAjYiiI2HWNWeKSZ42rwziK5<Y9zyswcJ%FZ7bYmNY
zaxoo%rUlkseRDziM{37?W^ln%PPlH_#aK&=_X^E!i|kK9KoVYCwbB&aRaju+vy(u#
z^EWaE^~ud>H{0YtCzL&R0%~-IMH!KXeE_21RfkNsf%ha)sr3uZT*rS-)bSWUUuuc%
zgTC#~HuepQ1Wb%J^Tip*Y8Pscr9U3jfM}B)sNC4jKMGPk1vW=0yaG)jl`cu#81YY=
z4{PgH?<HnYxDirD`>jbF;8)7#@cr^=^f2$;DK8lx%9R@u155)9eza!{J!{Hn=rv{=
z)eSQFGi8iZfz7ZZwLai(vBp0ds!_ba=g-ShLe#Ap9Vv^D{*}Kiz;Wx+fk?r(8hB3l
zp}+*{Drnm)%|*8ZrAr9OBC?PPyB+G?yn&88`c*bwXjUk|kItdS;Aq^gV<Vx(P+Gmb
zO>TXEl~D>+h&^aaKmm}zj@5l1J91AoLltTql)>ct)q!hM0NN{Y^7SIIaf;r#K_!7+
zrySz3%w(?us!u=wGMVc}DrA6|x{*xs*?Q)sY6N)Zf!93`)}FwqG{R`G6PXUdieo)0
z{m%U<g>&yo0hO&MnP%SH{uSjnC}X;jPX~7*y>n1q@W>A%ZFy#>o?YaFzH^%U42pNA
z;&5Wtw<%PyjFId0sE4tqp~)GqqDKoJ%Y#rJ39BSjBvTN8bM>i|29MsO#t5mDkcN&>
zAYt^RBOGF+J$i~UimpH-0|)V|8@$B}=~3VhN_w6s<O_@|$MvWr7!_r>9Pv=fIO$V3
zXf(vPkwRel)a(Y_RXC5%MO=>rb3`@=xd9yH(bA=O#(UEla5$*7m<R|0n$67=-_Epb
zLW4o1@ARhu?@|Cd<AF*z{{ZXI2Wn6;{uNdj5lMn6)b6W_ECgfprwR&?XvHf46Z2Dg
zb5Fta;8Rat^uTa5V<Vi?LFS*ImWCk$)6=gM(B72ba7H<)<sHd}?9?vBjx$m;fR31`
zkJE~!3ku^orO6$QAmbDsyj562=K}y!PHA(INJT3Qif%<lhX>xBCTWZJtDo%@iSeHG
z6oa3oP1Ju%jmI4`RW)=pMx&aPb4&~Mr+{iuF?t$)eJQ_zr5p;PMJFS@F!k?C){IjD
zI*LqUm!%lR05!5YRAl3=N_*2Aipof&Fdk{^)KfX9sihIJ#8?emR!yC?f}<ziwyax@
z_#?e@Vvy0T8T@I}f?;5zo|!$Vv6HkN+zOF~Q;vA)UMtc@$m8_`<ufAWlib#5Q@f>U
z->Lg!ZXLL&6-%5d*QXsxV{HQ^#Ct#_u<KpLo(;b^^{!sh%1yz7<mcA9dsSqIW-7>H
z6#`MuR;^28x<7GQk||f<oceaF_Dz)_=bzG;izk!KL2{s>?~1T^KD7k-DsfdE#Li;y
zAGEjfsD)b8P^5_av6`q4w>9n3e(E?XZb+x`sZ`)%pvTsy1B&a3gC&H5MtarFxD`q>
zk_}u_^7C6n!edxe4m;I`=bn`egE{o3!X;zZp`>zl@lGQ&)*N-LnX)VLDSDa+!Ju*1
zii1JR_pw%xWjLy;G3!=iJCoY3CUPIwgVL-a7#XVg!O!%m<L0%AjE9_#dsI)!;-x)J
zG0*EwlM=b(wK0Z8J%(DE-*-JLHg1aTf@l~N<{VRa$F)I1_svfq-TKrE$f=?{ifEY=
zRPpk>^{6^yJom**5#Uy+%0jmTj<pMd1x)L~&P_zar8Xo(oKhT-(wB-x<EL85nxY~G
z?kJ@rno5$z8L1HSQGwc|PfBQpOb%+qM?TeD4xOrahw15BqbUwy{{ZT!AFoQCi0z-o
zp?}t!6i7(NIHde>PHvquO>71CtXaAuBa=vf3J)LSKsYpt7p^LF;0lAaO%bX@$d{_r
z>B5{XSN$qw=hm$mF<%Ff-lB1zN|}HQ>P0}^dE*o?i4n-irm&|sT5EgMGgL&~XzfZx
zA??LUKn+h3?fohr;r{^ZRH@D|4>SprDfJ%p+xR*|_I<g=*2WK~t#J#;{VS~SWSM3{
zafe}w`K}|U&4*`xUj6f(@ZGqFShg>Nw~@_#0cO!hYZP0#BY|H%=r&SnTCyTJMO8T?
zu4~zBFXpj$(r=kg2Rv41p;6u3)zs`3P13XB8~AIHeGcmG{{Z)C<-`sP6ZeK|y|=!!
zzb=rF{$2xn8fE^WX{W|FoI3-+9GVQy16qswCo#kr$lZ@Q`d24)uip!U2a}#~0P0P8
z;@w(bS{bK{0Q3cUta&t@Hd~Lh2=L@|2a1xeaRTD!$`TaXJAyh>jr^*c&PZOktDYg$
zV2JrK3}EtWGfa?PGb=Ao$kMRQm6$vmz~dRmddY`bGv0Xu0Eyq8MQki98iZbpS-1DL
z_HEHeOq_E_2WpnGT-yMIk~7DxWa&27Fy4hAZC<0jZ`j@?;vKzL?+Qo0iEq{ql}Q-p
zfeoBpMI=oS1wV`$k5ssp7`Gr~9oTiNdWFx}p;LkLa0wM1t;|=@?PHVCsfEoC4Qmf@
zq8TvEyl2pR*GH&o_x8&Q+QYwb$3B(J>6Vb%%)%f!IU~Jw_SewEY&^}a=sVCeLR4$3
zJP(z~>0W<zqFgQWBgVmUNhdhx(!B~Pl32sWL0@Xb)b;B)E|S_-!yW*~Q%DSpjWMn)
zL<QP1K;>(s@P?lzlWOq1&meAj^sJlfrM9(shA;+y3Op;~FE;6|reT(EmyXoH>NWi}
z?`^!;)W}eBqpmAI!@4xKW$qv4-;a~hx<hb~MAAE9RA)6-%T}_~nby)!<$8)hR@OAh
z^&2A;6BwlG2sL9xvY$_|SSOgu!}yI!dw4AE%iv`6&lN{S*HZn=Qe!#!Td|-6UeXQP
zd8iDXGM<%ZMzogJ)CqWV)DCM+<XF_R5C^SRvD7WK2-&UV2Wi7EaX{`iT_)Ol*zX)S
zn;%2Ev``J0Jw5B5@eZRsoI}VMJY@RSod*6}>nAe|GB(~j(h+Uowy~Y=6;w0v^{!9G
z8oW{1GXl5(j(gU|qorM3>ak2F+XC~C%ZlfGb)+x$drK2?Gqp#!q{fdrR`Vm?oil-&
zy9vUa)ms>!%T(*{S0PYj!LAyco~1RQlAHm9pQT;U<s#vS_j%{(QO=0m0rKOTv!h|A
zWkkl&oSJxljL#A900%+%zB8*rLXLT<SDJ}%QE~Xx!1`CFc`R$M%Z|0o>QQZ#xXSus
zx`J}1uysiBF(-`rRLrQH#ljfQ<QP8Hqo(QxMe?OTFz5$*j(CHUkIJ)TMutGi#bC`&
zg5ftNS3gR~o;KWaP7PkMycZFaINgp$X)aSJ#~jp*!<r4<d8~V=N`}BBS3u)&+A6%p
zD3|wyW8Rp~=fdGfhv7rjR1DS2h_@cKPr~vEbcG`rC#7gl^71$|#8X&bcRzNSa_JK7
z1bgD9mUj_1^Q?&_48=lVev|<W(ibPMUX>S|P<5;0W2oYTX%lwm+Mr|$D#*D9JXI^_
z2&4`w<nXP!ouC6*(x;oAa%l|5k&8Banr1WJt~HrfG|>xoQ~6PFE28oMtEmoD4#J{X
ziZJ<m)u|*A!MyeDKpftoJNekb+BnT+-AGJ}4i4sSgM(cfSj5fdKW5xL>a_Ndwb!1A
z0Ub%83@t)$u-PK60etnSG|SlKDx`qfJ?fsbarT?WMJHnL0Uc_LaWZ_-whlX2MI~b?
zGr2^Bg)1N+^vz$fvNsYdBIg|Ru0KGE?@+rjw37KMFzipQdR3&5+C;IcD*NZHI+b~L
zHKRwLRx3~CMk8a&imz{V<xQ43@AanYBY*Eu^z^7KpUhxivFTXKrQu^wVecF9-V$;E
z`~^jKs4^%eIvPdVxb>>{{K0`-v5lS0-56NFzST^Hkz4_vyXtE))Jc7OsNAo9^;1=C
zlgP=`oYz_4IIX6)D{#skn>Et~q03QNuc+y8N2i^!sK`0U>t11cyKbak_KqvwJX7I|
zi8Qy8#IvwdfDL$Fp$yjdZ5_mHlBvT6tx<z1eLB{@j&W~3MmZIbSZ1`e>D6I$&&+6^
z#nar?j^UCrH=KG@K6^Ze-jf-J>s2$g#(AtPbr#*m?*9OdM9-7{6&p7c-Nu0qX6L;(
zJo{2|X|8s_&DyCEBviVWdjJmuim2Ub>~eb4Wb<1inm}nOd(vl`WS~4(Q{n#rFj{Ss
zBb=^%E0<I*!A42+72VlIvd%Tzw*sY>iSv`zkdySLvD=UhMqZ$%OSln^^n`*l%~ok}
zbDC$KI%b%O&#|b_Q|KwCU9IXpsSKIzOavmBPX?5};CoX^$)o^#(U46c&O6g^a(=wf
z1exp4G~#l(H5eSw&4ECS`LbtW+K>Pj(w!&EA*N?F+_pL7PZ$oMXODi=TqfLXeZrq>
zZzSrwSLG+II_5Np>;#fJ=Bsj9PkT37Q8TEg9BuZbr(q29<=yE{-du8jI$gA+4z#Q>
z4>{?9OZ)_Liix`MO=%7=DS;>=kdP_@<aeM+nvvMB9Ao-ZOZKS414)sd;*bvv3I4S#
zas@qVIN^Delo`b^DJKUai-B_D<TN-PeX0avtJbTMcVnQbH*tyr#NtEinrl9L)Fh1c
zrWWJtMZ&~{?mcj6t+{i}L=8L4C2&T63Qd(_LikP%KwBdwhi);7h@8|mQbWP!pPcrn
zK^@IIJY-RDu>AC-WAhH!rh~;Wo=4V;fp$p(qG0tDi6_nT8m#S&qco`bAJ&A)XxD`|
zp1H+H$;L%z!7*H5@;Vb*QO&)2b6p9UvM(>3{*<e|8vuKCt4c!}up?c*rk^Tg+``ns
zFsW}|m7BLCwQuVoWPm8ZAd1BNE0VU1>ZJ50vY6Z42hSb(uS4+euu;?ZgmLL!Y<kwN
zlYG!hqjpAk2DvIm=Y1L5L)~pIOp&XMVE3fd5J?Ds?$!r~^#LLPSZ9tiT|*#}JYyk+
za%^@UXRTP9Z9(041e4~cSxambBN3BbR<oxq&6}t3r`<T|Tx>3|P4h-RUI;bnVCr9U
z%*E5Qx*w{?3gP29&w9ym^Lo~%qbx3quo0Teat&=;bCnu8S?!K%K>gF2%+k-yaqC)t
zg=B=v7j}s%6Pz07FNle-9An<MZl!3|$$SA^g~YN+Bc7i1(|rV%r=fTZBD8!CPf=cx
zbs~tzBPX!0C-A$qzMl-q&N=t4hCNPs?@@frkKzZdan{7DZ70<1qlJ}Nxh{oY60=2p
zZFBzK(tkSS_3`#=^q7y5PW9IKrbIRcfcck^^{z)%U+o<#DU^-Mz57;;-56TMduxMX
ztHj)Fkl=&B?_SpIzwm~*QH-JDyeZG0ro%WJq>K#ay-Lqk`$vScxZ`F94PiaetW!Ls
zOd!_0$8oh}`Irv1&}*{AErPwdAg?01o7D3z?o<Ls^U}2}*{-yPRtIvDK5q4P7b9ip
zrSo+1;0{#RI^b_3t!imo*4jv%=Wa2I&71|9{R0ujc2O{#9A2en7&SBtl_sKoPfD62
z#w$vX-7b>UvmY&!Pm%IZH5#3xG<U93s7=^446*>+)s<c<l(_RV??V$heH>;Uohw~V
zF@adxDgOXQY}TxI8y}3~xo5cywAfYaRm<*d15KK3+|)=5bKbLHi?Jkc^33~BsHuL-
zZrD>JW46&%3vT&vbM00j)900U<f3*Y)ZApI#@t7gXFkTNOKB?u<Twt!jZZ$yafNm#
z=~X4UF`eOAzLWsNBa&mAa<{*FfzbNZpY4bpw%oy=LI)zN+{qs7#hs_1HKj5pYiURK
ziYvVE)8*biM-}J#Yiwa%w};zp@CUlrE@d8UJcmKrXzB<x$9U#4ZPHf285yp@k2THs
z&L1;O<F_^N*<87CQ9UZE@MoAz=gh`4SG2aoz;^Fd9d{kw1y84)w^-wv{T*z0=cRa6
zwwY7ZX1Y=Ju1mt~%XI#LX1dY!>t6@N5Vj`gr-yfe%XsqK&7r?=1$d*4u10tqSH1YI
z4?jYk7w>H+o|WL!3^M>R^PlHmX~ESmhH>n0W((fAO~x6yrBi{5Bp7bgi}$PTk>-Xm
z(wu)kdQ4H;m<{jJhWnJAX-OEM2CrOG{i&mZaZmm)T-33hx5HU{t##8RZown-uVn)U
zyeGid1}_srr2XN6{(n06U^xVO3jDW>>Dv(*_dTowy)sa7N`91zc%?P)=Wx;1gUux=
zpbVXTH|WzS?kmpR?U7g>{cF?p1oJfcm)g9-U_m{(HT0QVZi$Ue&46&I`Ri6LK4=v2
zRPE0Dc>a}n<1K0(YwNPAn;vd0T@<}(y=laOP3YD364ob&9V8*9o<YS))|gM_Ste;>
zFiQFw-hqSLt~(4@J0!6w`JG4OT2`8XYfXwWdV^kOWUm9W3%JY0`_+eZ06w1erFlKe
zvkj^j9YtbXMI&xIo9SK==oKcF0p-SOq?ZFfDEv)K*5n_XtwQnh$f`hOYD~;BYaz#_
zbQjSNCAjyj7F>3(PY(UV3GPMpr30D>r5!7BE-4%uf^{BVefm|A)2~{JQJC7Ys5DW}
zy&qaAtcoSKkIlJ?G5k%6^_xh<T5^HedRLfe(6qX&Ab$znUasTIwJKW~Qa+qku-J)i
za#z+iQ(U~#MZJ%y=~SfhAp4L;G40J-yP6>1JAe<pV^4PzHaFy-N{1qeq|{p<B7lCC
zi+LfD^4_(i&^sVu^%aph{plSDH6tx)4U5r+#zqBofpgxt+XIWl`qyXyDl<$>v2H$f
zKc!8p!@EqAjNo%nLUKo?Y092%pCWcE)|(OKBoKWmpN&|&U6)dh!HB4MsVxW(HGU3I
z9Muvk?Xk*JLS+3-Dv+l+q@y^d11=*Hra<|JrDqYek<%5Z4<f5w!_mN`z@<w{MK-03
zT1r|<04So009rawDSA)=iaJqCKoUpys=(=ru7{CRiee7*8ah#qdQdR@Xf$y~MF0mB
z4@xo3D4;@$nkK;+s6ff7lyg)B@<WBns5^({R3u(_ttf7hMjgNvD?tN|=*#nZ8Z0ZA
zWlm@aO>7$g-*p|ni%v~4W?&N1ch7K?a<I9R97Of0)-pR*x@dZX45pno<Hbt89M&d0
zS?&J-d4Q+N7cm)ddh<-luAlx98{)q`#k6neTQueHMay#flnegiW{U!49}PG9M2b1d
z71ossxIe8@(>yB$gn~&grIo!STvpkN!Fr{`S3k3S_X8qe85nU~z4=iyF5nx|yYXvm
z<dw6XzO7N676}}`_GCrR_xY~sH54ACG<lJlKktf&$_e>$et_4lCW=*lT|U`Q`;|Iq
z)3bfZka`5Io+Wk{Ddcg(aV7+I@}GURYAqXAm=c<8$JC}joqE90B?IQ02mOvJRnnXf
zn&M;hV^HxPLCSeL_-|QbgK4mOvjI~lgta#rd2Nt-m#<U)#kV6T%wz7=D(N<{oUOPm
z+_g`)knDM4cs}PJywoj}f3wM}3E=B-k2g?|pY|6O>I-8Mr~(MU{{VKJAZ5<QjD8g^
zw3zI9&98(kA(dst{JVWHE2oCm7~xR17Yu*fHM+6N4^;!$RI3wY{Km6#Z*VZg6XXQa
z;S1``{{YscHg}A0E$r7P`<boNZ<YQd^fad1Z}6O-T0<}wNV(_cw@mj{8L38&<mBEk
zBm1BX*78ETdja1x?T7~ePzDlctAGv6%zbxOHoC8+0Af(%)%w?Ov;){zE#ml$migdg
zuhO%tqPjY;X-cY6IO%oEqUT^l2e!(tbz9O7E*O0}Re1mnflS90z~;}Wjuw*WSZzY>
zhc_~PYBO;&pPp$O*s-QkWOU6Y%~cv}pro;E?mwL&&M5q84J($R70_L@V~PjmMra*_
z7^LaNI39VVJklM8l6`0#iYY*#EGBV59`yAY=ZbKTE9+LFa|)P<)7*<ZQf90ONgRw&
zW5-UFUd+Smv3nv6^GT9wMj1UQ3H7AoV_4!-Bh4IsCY)CtsW576YwaS$?fogy#?wd<
zag#_v^rN7qVy|)X#A0%+S0m8VRfy<u^rrGoX+;AA$<JC!KROKn80U&mDN%BJQ<!s3
z#(etNW-5DIIWHZSJbb-LsPTbK1(cGk!#r?l4(yU>{E19Om5TQrDVa15c|Cn;!vN4#
z&bPr6fg?qb4&$8v07~>9`D8t7%RDc7wz`lTU4a9I9qZHMkhBOuJv-N>OW{6CFpaCR
zz+m%84ti83Su?_Bq*D0lS{y`!r+QrczVwPtDGHGJ&lCX@?#)ITPDXGl%OH?-#Y5z6
zJ%2g^!_|OXllfCw(6%v7BWm+dxgCuFSWq!a8FN(2ga@3{e%l(iB+>&&Fe8u7nJ36T
zQJk8i{ihH(+Rf}LSnmXbgfsyS(bOFPw-Np|M;fV+26%$!oDz7gks&MTnu+ELF}8ps
zKtlY@lSzPjWKx*`OxAVH?6Ec?LJz6wObrFK+<9mE=BzE6?H_obtz$u|&7HC-W<Hgz
z71NQ=Pf7r?v2EavO-60v-cObR>%ghuniInwY11@q_c~GnB}Gx6(u}7$J!u$i9+b}A
zsJa4B$&=QA@q#(1z~ioJG6?H|MZmNqjei;hh)Cn}s)dF+(s`&lxC7Re!o}v5KpcKm
z8%yj3S8KRcald!dnuy*;212`gZKceD#lb1ZY}16CWYq(B#Ni;5>rOWl5yW4eE_6Op
z<4Geh*^E?f&Oyl;s%<^MJOv+(HQMmDR%ph5*{t1YE!kX*j`lejL40GcTCrkE#8tg2
zgK75?${u@}2+u_wD|#rAVpUMzh{3O&&FaCl;?CSUX=-D-kt1gvbDE8^YURrO`KnSJ
zSC@O82D~l4+m6*@FP_!Z)f)!PMSE4K+zhX3Q22nPZI0td*#fvERrLV2aZYH*29v2~
zGMu)GtDIG4fSTJe2_pv;6F><R)mDXL9KgV5ueBs-M4NgOTOViQoAzZAX9G0-rS}UN
zO$>$4%00QDTgb=m@mp^K@$!NVAWWZX&Q*}i$fIbK<BayGT^U<E*1N_Cs#g*I@Zz00
zCWKKnX5F~!gH^~X)hq{}O0YDO_m<>zBc)deKU$jEvJV|;yKva3sQuIe#DMX(k>e+d
zd|XLV6w7m2Mc8E*gL2h*ExYB3>w#K(M}D;3p0%==ig7~Bx#>>(H(qMoJn>Ft=RK=F
zcX63lP=4=fkF9xEiQzD62LlU^4SNjWZ6~PDHRZlEhh@sJ9Bw%^^!z_k)j3XFRBr>5
z@6w#O;+xGVIOjF?DDv55l~qPaB=)N8dFP6MOlLJ4RT4Wnr>hO0N{oJV_4LhJ5K)40
z%^9T}cB%m}%}53XHjUg+F;AeVoae1b#9-p0BPTU1WD9`&)ucG8?6_)`dscAl47&_z
zA;Im^nQ;(C<B{u8qY=m?A6k^$p;Clo`qPws;T8O%Mn*AA*_xdOds5>grD&;z%Hk4g
z(%XX`>|>7fhyggoO`V7U9CWAb#d4WW4>WDTs~8#nw1f=P<Q2$v)0J{5*v}m*SkU91
zlyZg0O3)+EUe#sS1Y@6iW01XlDOfI6VYZ?m<KCt?Z1MD{j%pe#XzNcLnqcOg-|0vN
z6zp?I0S1m~p$^E$ttL668R<*fs6&4$LOG`&OjCPypaX$TKTK1wDF_sXM8k@Y1T|SI
z2<cI>;MOvZr6wrkcc!q-I1iSBGAL@`3TU7MP5|xqqQP;UGeAF`J%JR@%8&<2PPC-r
zlOR&K3II5x0QUT;0i!01j6>5L(_5cPd8Uz4#zcD4m#qy*wFqRue~oHco;uc2@-hu*
zSs$3MIjpe@-2`u2pO+`SSsa2n1ZSG3ZcAVR`PJ0G<2kPmtZdEVVP0weWx<o4Snw*%
zmW*bZBS2W=7#OarPSYTrT1k&yIIEYso|~e@#=t`3j<x7h_)#pOW8v5>qVsOY&y0l6
zN`m2`GmxBt>DsV0KNa0-1(w_8i#X3r)S6Q}Mhmv)Jl2G=?B^_VpK7;YduFRk>r&Xa
z?+D}TOh$tcO+@D-9nDPK)GTR;!PO(f1CDc9%6+S2RReF`<bIWq2d#TJcX%U;s?=~e
z0OF=o#z$(0KU`F*f5@)r9MT@A2c=w$f`E_KsjnujM0mz4XqZTQbmpRSQl7rm6AX_3
z09tHFuEXY}BAmvU!-~n9M6So?CqJDXO)K!<T0p#d)EWv86=D<qO+cpynw~RMh><Qn
zZ+~i@E&v%72_R(RrG)-fv`l15agO4nVUK!{^rkmH!kZx#h{JkQNc`#SG4Jh)V-5)d
zvu4PJy7&J88bQSler`no=Z^IZv?|oGWF8Gf23NI77Dhd(p-7)UkG)F~`M9Xb$@=qB
zCtP~gsK!H>W3S~<zc{JLIQmpghW?b<F)Og7#}wiQPxPc99_F)V$cXjtNlL?-L4Ya?
z7wb<^Os6R1Q$(_K81|{7ZgEj5%JivF9Q)R&%0#WtJPL*X02-OPVxf=_J?XL{Kz->t
zbfqJjPM_mhGocU=LHg2+(zY^lMtJK|Pz+-gEIgWsocdIe5D#3_LS=wzRLKPQsE2xy
zcsR!uqA`%-Gwy08;F_55-3>(igP+QV2(EbInn~Jtr#A<uG?@4NF;LAB8*pj8>CK;7
zKx#`4)hciWMV{uRL64`kGFdRk^sbA-FaDc1bGc3l=yFYS*&BHot*;CaH9?L$pU8^w
zbGm%kc6H#TYKVV;?dF?QK2mOzc1g#|2c>$`X);{gVqiiqZM|!g_-Y`q(>%u|q>%0g
zy*}FEr+_z5Yk>5Ooj*vj)2?KYzS(5;JW;4YU?(%lhiqq)owZ9;@b%`Ssr{j6WkTSL
zG2nV)v}f@7p4LPxM69F&DniFIed1dU;uzgA(>Vg83}2KjwY!f>h93mYJ=rdpRls5B
zYpst*OM68{1&WLU)B)!@mxr3><Vd*+dV@q7D6+S8kL6|<CpEupnw+}1ifdAk?jt|l
z6@OK<NGxQR%NvJJY5?P{ZRdb8O8d@uKGj!I(PX@DHY1V;3TgKDZzb}eeagpyT?O2$
zV`b;eynA(|GaE$Fp4A-7kt2QVR*}(dWV%_HW<}|mv!`7x?VDVpk^CfQy<{$-GU^M3
zW0uARF&8yWG+tY5$=<w!Svq!^HMGpm!0z-Iu8QvC$cV~N@mYFqs+xq16;1)<5!#Rn
zwo|S0PLg3pcQ36^be9H1*js0Py=n{XNZHF8xA8VGE1<ES*v7KR%jKS#q%%`Nj!3Kl
zes_CfsOp+Mtk<#Jz66WYn%lR!f@lGR40~4_;yq4i?>3Bu4aPgt8L2gz&u(Kq2&(=c
z(2cG8OD1-&+{ISX^(ii4%kBr?y+2R!8l7NS$sCFg8^^6su6h_q=8I$UtT29+Qp-oO
z)24T}1Qz7v)DvB_7IH|LBra>7gI>9c@NUZ}IU}y&?MM#7_R%k`{HN{8{c9si(B9JT
z&66J^9e{KdxfFq;SvlsjBJm}(y1B4rVBq7Y8Kg5_NY-dtCmBW<BC6^7b-tV(ZGlx|
zmIUUdyPcr6cL-R4oOiBYPS);DrGg2Cn+1!1Dgf!V4L&VG*^*3yjAo|O?NZL$$xqDF
z=4MzVWCXt7lzY}+hp%sLgvRnRn_Fneq%!WQe6~>o!D4HM@twub_F%b;?umfu*1GL~
zPm=N&-V>Hq<W@GN5Q9cop9~Wj1XRyrqq)P_+P9W~pdTm(t-XX{$p}3&Q>(;;<BZg$
z)#Kyy6~QypiJLNn7{)VJbkqwrf4$n4TT<<uoKw*}r45gpu%%91vrH;Onl?Anpr;d5
zH0$)cLX4$lUfHYLvMbh3>ge(32M1;@>>pan)R1mceL7Z|9M*oR9_Yv7X);lXBIJ-N
zoUj6?j%v<IoO7C2UDb;<Mla88C~?-cAi5V3`X578?w~9UP*!Vc0R+^PTe&73*cm6K
zbGLh@cHG>0S4PsT$)5F@HN0rsx(Wd8d>Fv!s-WW>R?WdGq>8}sUCK*qDkgTX8TYP|
zbS#IAVt_IpUFT`&YA1vh;B)U*Ufbr+H2Cey95nz?jwjqWIH}ta$CH8WS0`w#qC2?y
z8t1QX4byB=0*`)bSjw7~s+c%zj+K`dsG?8_z^iYjGi2?^&sxs9(wSF(BOHp7jrb*o
z>2j<I1GOt6N6E!<c9&9F%s?luaD8i~id4FTetu!jC<_S2HYYq0QIw8QQNHi3AWiM^
zjM7M=G|4!iMLYE?8IA%o=~;S|#?HZue5~9G(ArGl$@xWb`t{+|Z+3>vQG&P!gH;IK
ziMt}bv`|XGxa9oA=cuiiG|OwH01c$~tJ*G!8Mj$Hy}dSr>03ugh+u^w$8pxZYIO8G
z%9UR+n{1ZaZKszX%DDV<R3p@!$^$VRbL?vVucyqh7fdoQZuQQTF^`;|O7rVcl9B6S
z@ey%I=nknG$MZRFdfL+>MvKe{c{t{{J4mFsyif@$xFlD36vEaJg}V+bno7rHUCZup
z*%e0kv5dBPs_Ut5kcQj&({8V0@|Xe+MM^20j-rL-V42{YX1bpXS+%a2x!9I&0rWYp
zPWIz%_m;WqjN`p}R)Y*_V-RKBdg8jH@Sc5F?-wn#-A36RB~^QTU=!B7hsIY?UTWq<
zO|Oy-drRqGX@&OiHuSF)@r9wY)}1hZZ{qc)w=riofN4S6*#`&Kkn>H)HA1<uYcY60
zKZPL~WA&;Q_XZ=3{HCrf%Eyz<XDFQzsd7gcrVh07RE`d5y)(vYENGa#f$v+^+FD%b
z#r6&ExvU|QdSbUB)+4pk_M9kD)82$V4mwz#IT>5{PkMxkvvV=HndIZ<JqJpzM-{Qg
z#?n%nI#Ut5;XOI;^-x4*(KtBwuKxg8v=;2BgK69NRwsZhFD;bZ2!_|>XT5bEAd#Ix
zb=uhJS+}WZ<lp5r3$_>1r<0S`tH?OdPV@l-<2mCdqG3*dm+4V%1oxl-IR^rjX9KM;
zmHcWp9sAG)k2QNznQ(oonHcRrbL~JEJklRMy(tWb*A-Yb1&;&008i#0!jYuH{Iw8r
z1x94!7{T<QPhlUI<nz{=#0p&G`qLW+{{XFB%VV9E;GO=;p;&;Yw-lc<63lZ|qL*WA
zX2PESl&sGjn@>KJ)3A$M7ik<)c}AmIn2u@RY4XSpYST=S#@)_%rWhP{t7)j)1|L0G
zOUpS+WtSecS_s5+bv%lVw_~BMf#b88_-+SIYPH3@c*=l9CWe`dj1Nj~ea&5#6<+mS
zlbX$znH?w@_01_l2V+t1AY!4hlBDxM-y>jCo^s2R_o}&b>&+(abDEohC~sO)_^5Yh
zy)No^0sHBjvrR3{ChAR$kT*2Dfi({7P+J3<n~ZZlNv6^U$)c6U6uHGTnov2QLgt!%
zXr{F=BzE9nbfyO&(7cRNPz9Lf%T=_SXCRzbP&hR_auP6V)QM=*`)M0aYepNL@NVc7
zbM07b&JJ-_Vv+o|RT-^gA~{A}%x09a&MKd+XbX2MoxJ0vP%3grHHBr=-jIaQk`!Rs
z=|o7<&m16tT;rP3yYS`xoE~!&c)F4}HHxPxE2DmE8@?OW%u^!rPB!HK06O&>4NWD4
zHvU5PuL!ZYHtra72D|M8R}#h)wj>=u?_8B3W6`57bayk}A(Ov7>z39u8LsX;`wmt9
z`j1+@JngYv4t;BPz#>ggQMqR31V91D0M%jJQzsIaBe~~ST5R^C6GtMR`?^&JU8cR$
z#<~OzqCBXpy;rU)#4Z%6KDotuH8s@n$+XY)%sO|iP<rE<$<w%>6|A_)#}%3rIn8S4
z%5aJ@Yn`|u!xr!9TOK1&FBIgK#bJ}jHQP>|<91EX{{X{qfuzQtfFia9myqIMPT}cP
zG&BQ7i;!@gN3Bae?4}aE03743c-e!DWSc#lznR8K5$fya*~ky~b6mZ#-)zxz+DOH9
zKkMxMbCu7va&VT1T9OhNqn-{puDCvGYDnXhA3KO>_5tI&x0&(IR~@T+!`B82Sv32B
z@{hVtN~dLSCAO`ZG7yeOV_R!wZkIk`Q@g126{IQi9_AY_bApwQX7V^b-72De)6NA)
z6d(tS3<D3B9V?~OA&ijW6c1rpyH#5_99FK8-Tj{%YGm12T|${Fw~n5bm2wEVlj~ih
zAKmXA>y*_Y@~;~UfO)Mc#>bPHU{yGC#La#U5xyHVOTnfJitfnqsVg$t&5`d?FC&_y
zzk3;}OzfX@{#DI$p|ab)7t*M|4eE1F`$2BC8Tp!>$+^;LEEeCIypOt0D>q8RA@*LC
zs~TW&T=U$K*&Bc&r&U}4IvT7?9>$d%769-oHU_P_+rq(%{MBYlgCcB%jQ;>S&s$WG
zWH`+W1hBX&dVAE2Y__*Wj^#gqs9k4>?eb(f_N{SwBMdpsF{hUqOk>`V9KF)9VoDX~
z(wz}I25VC4Hjr-ParLSmUOMrL)&$7Wuz$PPgI%_a;A#*a?eg(lC5a$_KPv2Wx7$1o
z&kQPY3!0RX5YkBP&186vJ=#N_PAgydN7AV3=wD5ccERJ{75UyD_jsl1dh*sMkx3pp
z9@N`nQseNcCU2SeAc95>Lj!-MCVgx4ntH_Xp68%=Vqf&dUscU^fbrJ29Rf|aNORX5
z*ME?4k3r3RcM?P2jE_SK{nD1PADO01zwDa%{`-r$R~XvtG5FWf7fZg<Me0h|&-%<p
zEmGxi(cAf&_V_M(PA4{Cv`opDuhy74=B1EeR6t<Y=&15VBPNgzIvP@aC<OGyFdN?{
zjAdy}B>*%K8l)zfif|behHQ9dLm!Ck9Djdq1$_e%4H}<eUpVQ{<?0Yg(`$y!eG_2Y
z>>+Gtj<xyc8q)V+Bi75_jTZ+r;y9)+PHFY|!#yFVtp<k82c;k)nRi>vz4o3f$*<#(
zY7-6Zv^N#&m<J&A>0V*1ua~M!G2b|^pvmR#$r)89vXFh78R@{yYQ)>^@toELh#Z{$
zRkdnCLM!UB*J&IWg>+S6hR3HB88~W{#vJyj9FfI+tX=7&z-rTCNh59Jnt_%{4^k>%
zxEVC%QBaYoL|c5^^PcsyrCY{PfKgN!a%)3LkSzN<w`%3aLiCxw9$xVKyLDXSr%J@S
zj~%(LlJH?`2Jvv+1}o;#>6nuaO;wP0#ax(@#{#NINgnk=DP2dt7Orwt+Qb^^<{!E_
zu5#gjczN$#*j8mwsz*N5l;Sz2itI8S)Y1jq2<matm3kahkuGH%W}--C6KueA$JU`_
zD0!~BI~9=xm;kq}P}Q`epiF}UxB{>&Z-nFDtf|2`{{RDCgR4p8X>v0E0CT-@z6pmn
zFE2O;j8{kEdxH*_AqN11pUSjaM2ETNb4X;F*s*Mr)|S<L%c$1`^U|U|m2*jqzM`FY
z=Zeg;e(gM)UqY$Pa<d=aALm_euG?)`k4ofR<&6MKXCR91HX}bU>s_o|#I2m>xI{RS
zPob{r%}ZKGgW7;)n7J9PxD(8?e`Ph53}<hzy=+>Luo2Ual-VbhYLWSRjl%jrTBYk+
z{vl1ew47r+=CThJB_PdOwLDc(R&7oXr8Eq;)N@W9X$Rv=x2`IHPMxX523@Raqz;*+
zE{pt1KN><P+(YFz9V!ade=bzUa(!`BR@!MBYC$Xi0J@~o<z*0NlC)#dbvaMTV{(3|
zMOj}9Yi=?$`2ha_Xo39A9Fhy87MH26jz0wI?z@>`kNx>7#C`?4KkF~8Q2GK|j!?bM
zR+hUY@F)l7)It9Mu5lWbd=+Ax$#Zi4%AkKbT6Z0vV~C>z*1Z8dC8MYX*5LmDy!fft
zL(t$H+rlyb06iql7msnOb9*Ds)qtteMPdL1=i0pxN1{M}SZq{#CTZhW(;?wr5$v(i
z&jr-AhpP68=c{dXA^9xlVd@aosPt`GQS#~2{ws>@o5WUUg?T>#fl#-Jp;Pk3JN;i3
zKH8b0!PkFe<<rAD+n@OHEAGxJ%J?@`JiNBCXVt51yiQngY<c6C%~;blZ@1p04;I4R
z4;0mCH)K=5R#E0=EItRhAQsf%AMUPdbnrwt{qCgff7nb{qQ#~}sy7VPnDqEb#>Ew}
z!p}O3!J24a-c5BU<5p9_`a+H^rhI>S>(E7%OVJjbAVJX=@}O5ZnEW}XDvg?KfAB6%
zU5`uI!r5A={{XIa)%i<~6jJT!Kpg7W&x|TYpG2vXO}TI5{J5>Xxb05cjz<)%1}M^8
zjI@#g)9+M^q9GZ6e!SMX9nB$`K-v)J)_^nP(IMTO0BXR}VNBpDsf>;X%DmN^W-T6N
z05_&-0Yqu>BX$CwEu&vdQ{_n{Ew%7Hsv%~?WXR(_^bD8FjYT*F2dyz}R1W9rX+#N-
zY1{{8dmPekr4fwgowpRM14HplGN9t0fzptwnk)ouI*;Hq({uj-Oq!)A1~>+rk6Hj~
z%EW!bKD0E14u+qCeJPSDGyw}wDf^@k!jWEbe)#;UN_+E8P8xs%9L>*~!;aM(+qqx$
zulO3crz0HHqBZNlG{B`Dx%<pcea%j>af}~Ilz=)BKp7%{8@C*PI>+%W22C~C4l8Vo
zR(7zyW}7EH6!BTr_zsLCwOF&rTZ6}HZh5KZj3kZJe8kiQV!YGrqp*UI^`$wa_MoeV
zIi)$I9cgI*1M5W{I`KsV0YN9)ieB^p+5peJEhkz4k}@%hdXNt_5)cI`ZgW<hj4D%8
zR%Gue0;4a3!KjJJq^9P~<A;J)BoCT)?kW!SySSs69Rx{`X?CqeyA+|b>%|u#(R~N)
zq`^ID193~djwlXUpxf<Bu$o=|wC^y3j<sIsoT{OoLlw>rDZ&B<aZBbo6xNitb4R*I
z@1Ib?Ri=^Jke{s^s#`aw3vLFIgUO<#-2kJC0H6v0)6gW@tVPt<twO}Wpq$r^>2Kxg
zmh5qY-Rsuv<juMf(-q%A-Y3mwk+oZvh6W8r>hIBr`cj4jb53c{E;y}^EM!XRm@Y~6
zH1_0m=9%UJ-xL=cbNs1X2d@T)8R=1pTR8~F@TC&Ae&c>MJj1aZi6I!yDy*Nngqa)<
zdbaXAaljtts>$W&4?GHe3sUDp<z@xt{kpgfcHMsJwHB9<%P!OsG4(Z}G&*Q)(p+2Q
z_ZZCx`eX--lplpltp&R)l3k0jTBhC1593x;1s`+@%xzl1Iy}$xUMauZHjV!PEa&>1
zVxi)xcOSB!V@S-vV+sWzW@DFSz^rHS6ibzg$=!j+&e#;6+P6}-%LTX%+>=v0WjOB2
z_7XLvbbgLM3aas=cO=$S_xJF|#Caf&auT_D{9UX0j)9eMNXQiF;v-Yx6sb7wdJ3Wp
zA1R6T#Y~vz2;Yr)dw7#qbwBBBGx}An8&JR0FScD>&QM{14UE&NTarA?QH9-)OA_I8
zh5D0G%XcWiNnsrHtou7FSBRI1S-o54H8NX68<LTtljtkQshsO%j+KQji<W$EnQ9s2
zjC{>Jn^*g)X}RaxnJCOmKN`>bUT>jaRz-O=D^v#!J9~jhx}~{osFF5+ym48Q5DR10
zpbv>uf!{T!*XpqL5jr70N`VT3-2pW_1_Wd;BeiEFyS6&>TB{<<0vz_~SW6jQ#k9**
zVc0;YZ>P{y$sXj$b_d#`C*`T_`Gkt|s$+2$_>Dc3I|9T3>S_BIrxbBUa%-L9YQMBs
zBzp{GMPc$UUrM^jn?Y3qsmO2#TCyCN*N&B(s!8=9DjpjPjPXwcJmWQ7K22GO<$dcG
z-r_T_6Am+3)2=IO`FX6{i1Qw6rkfDDYv7g6YH8#!uoX_o;%xd>g~Vc0)Z)5n^2U79
z0?Z#YVD+h(e4g}{skSgVshxgPUVP>6GKWGl2*}MTTu}i92=u2PYL0dT3W7bUj(}j)
zqL||;#R_j=99J>aL}UK|)l-gRsGF@w4B8JhTH-tqNb6S9lhUKPT&_iF2VofZC<A7h
z0U^N0TDLl7Nx-U#Fv7Z2u7J^pf_bMOylM!W=27@nwophuqLojC1}_dOR~V?z3_i6h
zaf-wS5lzQ5{Pm>I6u^Z^Noq%I4wV~l{{W3Ojwyi2pZ8>DxE~nXsf@nReL?MA)Po|q
ze->Mpvt!pa?PT>iF%dDYuLgO0c0B<Zriycsz!cHezWOJQ$w12bnntBY`AGhBj4@gv
z4HWgJ55}CeNr+N%XatH(<k6a|fc*Q=PJO9>)5j;ZCdMW+O~pKlOlE*1b;;>UqMwZR
z6mgoHSU?VG$&PcHN^%iY05T09N^lB#H{nk(vW)hvV<K3^BpQ@3<Pt?gj8lX1Fe-^0
zag)s<`_$6erWQW9pe#rfWK`(GZZpkOE@?xY^`ysQ#IoSy`Bi3Yifg&WGbW&E5{_5i
zqBs<)O)2S8${UU;R+5b4H6TB>X$}oEkSGVO06ZLaqcni#kdQi62oE%$l_={$^rGVd
zNO_`@y&xAnP<iV>IqgM57>B(fJoTfHO)Ve*aoU1u2NZVnpaGbXOv%MK(rv8R#*>pr
z<x7e~QZS%;QA$9d1U%732U=1+DS;CX)X;hQ)83dm)_q1yq;Xelh!3B9@l;l=TKulG
zs;_it-+=IOR|4aK>FZP?ZU;<Oj4E54WLJlX(B33>*H=*4?19PxxKb;aD>cK3E~b)4
z9;b@xE?4(JFz0P^gb+_Pwi(_4#8unE8rag?EHXH(jw??}Y)C$CM{jECGiJ1d<utaZ
z6AE;LImb$5Ew)wq&`GF!9)0RJ8-YD)Lye;p(lMV(qy|2uxPi$$kyxwst^4)NCnKos
zSUALny=*S9IIC_us2-If{obOZ2k@yCtG)*_9tH@<BCW;9%~S{Ut1)98>v)(<k-ce+
z$fvOccfqDMN4;Am5I!?Z=nthih8v|Y^sJe*NMEVVG#|pBAj^Byf9E2zH6PcL(x!)!
z4tS`43YIPyb*e<jobyse#FW#FQpQf<?^?vhMUIA;_&w?4IHorhW@xP7=M>(&)QmI7
ztwu(8tfXraC*ql&^(2E0(xduxs5C;4K~f>+qVG~C280Z>I(Fip80YCxjFHnc^{rxK
zB4dI&R7^qSihE}RwK2yPOo)}wQ%Sq8r8&<|I#Ul^n$4S`jB-a@QgBTxe8-$qK+b9k
z7p*G(wBD5Up$U^ON|rCZjN+nDeQD{#R<SaXXz|vflO;&0daiqVR8P~Iqcm4xOe9m=
zob!rrBo39EIuR3n>N*NmrjOE~v3pdJpPHitA8LGmdmU+#%OGKC>&_{e$sBP`UJY6@
zWQV`4F!jLePjU6A-2PP9kqiCfOz0_FC9_R64ABw4C#@Z+TZ8LO9Y-{a6q=GT&#f>T
zkq!yuQWGTrd*Zb;6Sr7SzcQR3ToGA(AI7wFcG;>#NEkeRHRtAW=AhBhg#IEszXe*8
zqeHxq>UhboMN8<dEI`Hy>6+#|8>b(z10rnWD5t6SuCVFROc7)pDawlR+3F3^u4cP=
zUP$p8oGW7)HDgoNV$&51BfB>MD68m+6k${<s`^w(HNDinQj}+3n+Bi+g~afrfi~_L
z=hm||En?cs<<95y&2E_Z>0F+t;b||grE<W=!-L!pN(NuFx`R-&NuvN~IbP~%m$plF
zZ1GB<h8$+6)3mkIt;A|c_pDuEHOAE=OEty5;CFh^BAu6optNBo((XDE2NinnPq%O(
zn_(@FmbK(rVzYTV$g9%08@caq?}8><=LL55G{VP64wn_YZwe?_uy7W#mqWL;ym^^2
z=cY|+U&%eTlf6-zKtAeqtX&f4QM;07yo{m~@`Kb+BHXY?<*}FU3ZrjnXq%qgbUfmh
z#7!h9fpQd@&CmtQTst}a$ser)CDk;)wW5??-YLk<TZ>8atp3gBl>l|9b&W!8J~U*9
zaAv_HwMj0Z*7k8pf*JT2q%)z?bk)-=L?}ZJrSsmXYT9g9z_T1N^s0I;tu)g-Z<3k&
z+0H6$c6)`fb8Lm5JW@yoTHB-xwO6Ne)~(u$CA|I*I~AFx%W-jLOsTP(u{DKvHOgu@
zMR6*gG1izKp$jar^Nplq6;eG0A%3?3j=*?NN=-I-Ud>s)@LJCP+tlONMX0us;3oyK
z&{70;F{*?M+MpIzM)%ALqHJ~VPV<;R8Ae+jD~q_)ZvNWxDJbbC(4n)<AV+>cU{!`e
z>J4Yx=(hH^W^}>H`@3qztgP0^@At9VvBsyVw!UqQKe#;Z$7%+2EZY#VI0C9!>NeLG
zjc%@@LE4>uuJ&#dIUL|uDWKWSCaf+o@~>7sbDn4eufDrWD@UGR^=sC+t$S65`%m*A
zCu!r4TJG*`qPw?}IhS;74r|VQQ4AInBrp&Vo}Tp+*tl+BZf0JX=klvIQZg`J-_ENm
zf~V4<8j@STJ-Z6vl07(^<YW&@Y{`YkN~)LXDyv4ogU>Z+v5_|pm77JF+Ktqjbdg*_
zaq|F8bh>T)ch<s4*f2ePs~YCrWkVc;Bi^v1x|hScrURCN`l+t0JzHqVt%p@(rstuC
z$7-p6^F!&yI@antyLFN#$Ud}8p`$<6yPl_yD7d>boOQz!+Kh~Kt2Yr9$Reu(Gg(Nq
zMJ^a^#sz0x!}9hdR->*#HBG=E)D&Zh*&7FpQ>Jy5Gn{cwyo;Q!c&Z!O7#`gzf!TOM
zAG1PoPG6sD>|`6GIIdSrA}d&19eU!rn`ZMOUWEEkz|UvP5t>K2jwHt6xYQb@yy^3&
z9M%MvQ==WqanB~C3AIa$nTPI|^Y2(>%(8sIh85H4*YMm&v54c>tz4H*x0yl42el?M
zo3y?ug??*5>~-95Ml(}Qq(FeU#~!s#Pn7H&tw~2es@nj;)p{P)9-DIUx08+=j1yY-
ziX3gMW`oL~a-3~B;(#}x{o3cD^{N+-ynMfpy-d?Fi{<J?XR&?lBc2pzngFS)UW*$8
z&K<%2Rn2JD!ds?hk1Nyyb5d*f#^{)VCl7#YTf?v`ebL(jy0Fo^IqS;NH>_g6l~o}^
z5my=8S|SZi9YIamsdUqJk#8|J)f;vS=`5|IQYB^#*zaDN*z#qoIN2_q+DA*Y*fYjf
zvhQqcC4|h546+bF2e08?jdNvha1QiVBzLY~QSg)`q>wk4gV1)RD>Y)FCl_;@({#kP
zoH=ihkJh#)w-Tm7%T_(iSDJm%h=yhCaauN4Qn)`MC3}0<mx-s!^gY}qUU;1TqF&Zr
z*k;M(iX)KA9_*5*rEk5XOjykk+v`|!Ml5D{+mVt*a-DZ6Pi^K*hbNZ@k6QIDI?ctD
zEf^nn@UJd=v@WD6I3d3yUa6wq`TBG_Saik#uBdz`4PS`Xg{6%MY!i+!E5`mJAR5Nz
z810eoUd*}3uO0Y~!|lKfZuO*$nZU3#+*6M<+}4DKDZt=xX`oYy$E5+WD4pY61DZp3
zCu53$oYR$QSgvMHmr{o7`Ox!8Ao-8sQGhW^iYy$=Z7}`<q$7%H9CW8)5fD320e4j%
zwCsIq=9dqfe!G|DUU{VS8b_gca{2765fKUFjMdFz`L3bevu#$lWLVdp1wQTk$VgvG
z!up!n!I1pb14u`qsU|pLDyx&9Z(6cL%~RL6N@Hy&Ak<EBO+wjRkwA%DU>b<Yj8ja6
z40BCl2=|}|nFS{Yo@z5lO9P4kkaoxCno!3z2$vm2JWMl_KohHEW7eUS%Krcl=}N8v
z>rzRwMdO+TK&Nmt6=T!#G}I+eJ*r=|ZR=gM?9qglq%5YSj$fC{k$N5)o&BK~_bOD>
z?FhrJKDDKyPNQB2RSY>_QB~bT95*$5PipJ?sTEJ5H5o9;{7P}@P~%`oq4sUZ<<HPl
z8q!q<gNnH76#T3zKQM#WH6tmomNUyRAMa9|sldUJvGuEsi4HNy_NK{ZU4L|hnp%NO
z-9C9@X-&%!#XYq7f#nGHrkf{R<l>d2R)Q>~XC|6nm+Z~gbsuJGR$+0u28`01cJ!cI
zw`wfH;sZ;&-jrK8rkGrJqRccM)|f~X6=Ca9wsXxUG%oy_3shp9PZc8`r_l7LQwOCu
z57vMRQ^f#Lk4|Zb0OFJ0m+49d4FEI_X?oMKkxe6>C;<ScE_YB5tvP;_&=wP%Rr^_E
zjO~!)zD-oOOaM<(YEnikSQ1{EWC`+CV<;ygr}ID*f-vCYuWHV-xxE#sRu)+Apm#V_
zaK^UvzYsOux<PIam;70*Qh{c{<kqdmnvz<1h`9N899A)^;H+%v^J-#8jy-E@MYwdj
zUT^{GD;MsZcdNR5#w&zA{0ho?qiQm=ta^w+CZ5|5&9kqicE1YSZj~w#f{eh|3#CjY
zu)seyIVQVrhD5A)vFGl{X<^o-<31F2J|saehwc>T8%=!ec(|2^Ko1r4Ubr{tcR1(e
zJXg;5{7Tsea3mV+dmdvWvN*UEv4dE4pYif5bOXStTawOG#EMPAo@)T`K_k6%o+cRC
zisqXode@^%;2`v^8W1$t`Nl^|y!uy}YR|l==s>Lf8bT}~X3tJ*qLx^Vn*=>YdG+W*
zqxX)wIEm8ICR}!l4Y*Oz3dp#(i6;-RZXD*feAvSB-1=5k*cmJ;;}n-FJ97EnzrECb
z+4CTdML&&66y9tq<Y4Wp@V@(2L)28Z>x*Pl#?gw}p6A)&(!VH|ExIBHQ{J;3NUay=
zJ*u386{OCo(m@x_n|&(_T#p1drENm^kmrsoBU?L^@zVmKGsMi}`<Wd4pLU_nIH{kN
zs7U8E6{6n9$3j*dAHPa#Hbo|VX)Bb`%Hu)7;-rpEr#_V#&#gD9G+djT`W*Y6fc37B
zWDJ0FT&95Q6y=}SwRATcv@kC_j(Ff!b57$-xE0uRsEjUq56-fNyA-5_ETDgStKDmi
zszNwE)t@UF(M7#S4T`%Agz)c!^sWVU>$T(+BvX%w?#as#DCA*tzjXth{`sRL9JsCx
zyiasM8OZmklf)Mcx$_2b(DbFq$8)ch!3XDBry<DdE17+I>-({RSL|<%$R&u#9jc=i
ziIX<0oA<cwU2ThE6n^W@YmT!7N)2`PE4tGivD%8i37XvQ;yHmi>Y(PKzFpQ*^U+D7
z!S~rA=hCE@ZiT?^q*vz^*Cr|Yp2T&D<M)b8(wuR;)c_e~91gXwseu*z@!*e`n#y7G
z_3vM!VcqGbc@;F1I}IU$k`kltk<EG>M|5g^tIYI?HUL4-O7xpkx&$EhubbjXd$Ez%
zgnOcA8H|rw@Q)S2<m<DjKY5Ag(>*KR6l7x+;{H5~%hw4b<!q1VSHaaSiIjVb9~;v+
z`F`$d5P7NP<tn{?rnWpmPf7>S{b^4)rjEUORRD4YAFU~*??4DgG~j+(Y3oj3&XCC=
zZITD)gI_~<eqTF9wsFv<eC(v|1P)Z@z2CtTdEOm>f=DVbO?+P%)4mZ)%=B{i?=*Dj
z%{+9d)byzb75Pg&ai)XPgGXvWB7j^Edh?$XN9F46w~gIv(Uf6@a9%P(w~@)8uf2PD
zJN@H{omHWgVBfsOYuhjmRMr-sIvd1XgS(2_LAK!Miu#NjaI0o<R@NhKa<gNOl~slf
zT(}3!HBM3a*W2Np=^hPrYJv`(C>?1B1JaxZKN`^z#B83GC6jq~h{uj_Y9cY-mNT|h
zKH{^kuLg}NJ4oKTUNhU)urF7su7+?L5Jh3$0l+o#jajqUxq)!GB=iEQ$S`XCz%@=l
zPu74cO1WS0u730ZDLBS!qHsv8O-V5zJpuKuyfgRgXHd#vO~p)CnujBr^cjfd{3+>?
zBA&RYR#?kpaQtdTkT)ro=b%$k#*UuNOF+2E6#JPXF__r!Mmp6iS?>*|$ZYN#+$BWX
zeybt*bouk!HOb3T=E>8swc$%M0!sM8mg1uEtlKP>F3rY&I^WRjE+Di0>Im5Lw3^EC
zE`xcgNESPbWkK1GHL}>pspiL%TK*l2ecQGN1HEb|f#q%_)UDL|0h3!ASB7mg^=~%u
zr6-@2aZ=T{F3p%)+Yta8xF@A@<Y1cgo4o@_xnR@1!vWB40;{iwd_5m5jz{}anoY;K
zYMh?P^X`Vb-3``VJ|+$b@9HYT+IW5+^>+5ekM9k}uE(ufTOde$r311jYM*HoQp41J
z38Rm2`@fZ5hT2Ap9$bg$D=~aTC2}Jy2eRU;$>J#kkgqQti&VPNG>#6d=wSGVLDa4_
z4e(jHUU{t4@Sd#vyh$JX?klE~#1j*cnLq74LfYi-)gvE;Pq&X_b(Yp<GI%=lu-|cN
zzemsXtM=Xuk}?`g^#jooq-|d4{{Rw?qSR+mxngrG{uI8jx+7JURDDZ};VU3PlIH2Z
z-QulB;hhnG)_tI#_N2vPwdBp#M<e~}jiz?$<o!)g)>*7_d39$<G=C1lNfxM2tIL{x
zG$@D*Z(==)<ku)kC$4EewLe*rvdQ7qooj0PWEt4D{{Zj^sjcE0Fg{Sj=%80Clj}x(
z>Ruvj+BsDvxzV?X&>xmLkNgi65%D8q<b{d<0B%gy2*IEXRC`&zri(40x*HAR3x*s;
z68^OdYd6I4BxC56o6?Syy`;OE#{)rqlH{7L^Yyu5>;@_(zPW$BJD>O!SIPCI?^Ddp
zRvwbs4tXST^GNJH3sX7+=}#bItww0Me$ES^xu9{}^GGP5e5hRUNktv=NOl&qbZJC-
ztSsjpc{Q7gniKo@^T6CHqU_A-#_(wM=%$Zi?P1cbM<^e_Ptvlq+jVP1X5^8Y)rCTR
zJ6Ec<J}RQLng(*reo`nKg-HDL9Mef1DUcv1(t>eI+K?RcKmatMyMIanqZ9z7@#&gF
zz@#TMxy~s7y(tgB6bzG2Jb^&O1dfK6ITXM#)|>?ZDKwelf-y*Q=|B!2jVM0<0G&e4
zM@1ymZ8U?AFCSAt7IVchv5e-R^Jnd|@uobNEx;%}IHUyo!1dyj%nW|%#Z@-fvi|_f
zWL)<Gv!>9m<dC23A~V<mC<AcK8WFja6Y6RSZs1UJDreI*fj5P&q&aKnY<4E7$>B@q
zmvFc{e!u;CEC)n&D`Cd<C;jRMp$}0sVz3j!7X?DS)A8AOss8}s58TU(iBlepMVK3d
zQ?(0|az6@*bz2nqe$Yw!)f-<2+eG3?W|Be<c{RHZpJNXZ+pipF6vRgkrDn^8EPX~Q
z!rexGV3KYB0CuHVqfz$<<x;87@K6Ouz5^Rzl>6eKyt#8?__uCX)1_z<K>M`GgBy3i
z87g?Gn!HUZJ54jlbp;D~Fk#N_l~asyTDsf|4x=y~+c~Vit$EVi`wCHRDcoiTdQuQS
zyHCv_H73d<57L9vr7lSwX$j_##L3MB01!d%zS4~5mte<wEIXl?paLnxV9-jAq)}kz
zLUyK_d1c$2=92>)0!Of>qRIA%L7Gn0I$B)0!a*Vb0D#nsrRp+$%Q;WfVyoH9u@1F0
zyD9P3lxDP}@cykK09mm2BvqC0rmV~JMvL#7e#%{p-Y$~+Mj7c#is+NUm+n4mm{O)+
z1-hS~QH&3zKVu^|kD$7o)M|ykeB;`mAYQ4EzV*@n0KzM#!~VZlUw@kvzu6uejemKl
z`JYFs_6*JDRFTUZQ+F?R0=h{X!PdtOBRTZR%|>;<3PFP%tgnyuYLyF_ywaazpWeUT
z6mA4%Lmu1;-+vnD(PTrWGksK4N8$`fF&37f`{J}%R$(mGJrG&=XH&ekHwG~hb`904
znbI{a?x|%X;jxe^+4zyDGL??jAUgsol)gOH82o}1`U=zPjr1`7)tV-c!`j51ESP;*
zRh00auO<P77d`V>&*Keo)aK|9pv6^x5bE#2zm$CqHG?JQ)97_$!Pmh2*HEQActDJq
zbvRS<t}0DN{#+Nloxk8_pfb+q=bA?Pn!l<eIc9ZVQ@sBGglkQWN1d!jPqP6`{>$+6
zAL}(D$NiSB6t3=DpRF#?6M!lGSsA>2SJdt!pTahi34YSgAUu4;*1GunMTJ5km4c2i
zE6YewItp;%cohAL?sL?yDxVSQa(qhDRD71wu=f>OZ;8kU$*1G};a-27ic`oV6x}4z
zpE2qd{w=$@gh?7(s9~O&r?$U-RDmcN{_5hmy$<937h&p$7_GE?o@>LcI+2r2osfiD
zxuGVpsS~&DZI7iybu0GHZsf<-p=@>h>N8k-Nj{~hq$6BhyJ6>Y4}8>tvb^N|YB0Rj
zsNl#M=i0NCLaauQfsWMRyq>jV$xXc~5}SXB)?D{0!-MgGPE(J1gE%><6y*1$1c7&S
z6?)x%QO6>p({R%;VV|vCG3|T`#-&F6(u&uLOiVC29czZWw*LT2m))`jdIiFKzT0b&
zzKDIXk4^_l^)ks_G;`uMGL{jHVz21gituz4<%khZwFNI!f!e(sL~l)_nh)MPtv&e0
zep6F3WSmtUIP8}M^&RTmhYWjjUm;R9lRY)C@N?3XjH?f7iBBAKsgUG>-lt)hQ!Zt2
zJ5@&D){VmA;ehYjv*llygI$nhGfo!*-#vh>J7oRPZ1L+@w(YtcS3{@bT{qclI+YwD
z>IhZo)}^(40uE}b$&pgqzwh?;Jl6!aG%V*71E2oAG@qJ*lg(xVxytcU#@UCjN{F1T
zKHTm@p2rjbpp5Wp&8z1ksgi0~Uu*ZNk`Ze4KXe$@Y>LJftx3OmYH{gQ6mE%!@~VV{
zWW$A+0b2XMW&X92ep$WqT0@0KB#P-`HINXhY2;O9n26B(RLc3TN{Z4bbO#PaJ<dI9
zBw(_idRJ_*tn31VgVvGGSFJaH98(<b;;8{5Kg)qpGv<;mr!*DjivZ*#eQB2yfZ;pQ
zk~&lq5#|i_s)Sn*`O`7yrDtu&(zSm4S?!9>Jm(&@bl!kHGnG9m(>DUDDHzWcDe0co
zqtyW`Hb-8SChW(WgE?Aqwouk-0K2)PJbLD%Cz?=cun7-6d7!REHG!vR<)j2mzb#<+
zf-xnV^f(pJH??N!Q3te;5&Su?LjhBkv{^G(M~X@|%IJTEh~}6&Rjc@Xi|LT?#O|ut
zuhJmyj}l7EdeWYAO#l<^P9qheBw*6|Pyhy$o_f%j37<+k(Lmr;fDTWsJ$R;c#wp5i
zKo1xm)U?plpyQ=57pdl$#AcM5Ve3hN?2k%N-RYoYW{gk-fxeWi<%izQFduq8w8ddT
z=8ebRlOB|S;;P|c%rWcDHzyRN=9=7|^zIfA(~|?#(+^4%;+4Qw7&Mfm=R8tl0~w$N
zQ_gWg#yO`%k0XRZlS@1=1BG#e){|gIN(N3xN(WkeeDT(#1lxg{WlG#|IH+<>ARG_j
zNP5vh=}ZGO5sEX-8K48D1b59HD4+u%3PaO_ONu^}n8e0u4@!19q$38PV^@Z$Rd;=A
zJo8c^=9q*j#WXK9J~Ai^_|V~SxeF-Ar8LB9$xPB?1FcUWT&=ehZKseypmn2^cOxU3
zL+MfwJ!zkyp`as>RAV(OoQzams|UG5#aMx{Agbxfsp8;{nf0Q2#0~p%xly><MQXx7
zck=yfBHM_Ddseh$1>pAWUM3+MMUvb`THN%`ILWS7;B2@m0ULUcdg}AOC(k@)xt&3F
z-4cI`=EtQh8~Y_Prsg=sUeZn{8STlcE7GpmAK#9(=oz!6Wx&RBP!1(uP-@D6(Pd71
z)n-4u@797%QS&Gy(^zD2(v~xrhdHG@Q$ce!@D_=|C#M({fI$zBO6jK?)wAhb<jaYO
z=hnSUAHs518UfGJoSdI(Po+6eHRwd-W5rpA1J@N?atXyx3Hhsd8BCb|AB{BA*x>WY
zrjc41qO<+u+MAs8r?{pbxaSp{HbhbmIjHbDV~UbaooXK9vu22Y6!`vA^`-;OIZr((
zh%(M;@%`-k_oidz&mdEm?+$BZV<Oi<O<(}^r)LANT0_9%sK~DUI({`6IODxbCjz1O
z?NH4S#^$5Q$JV5Nl@Z|Lvu3DXF;5>WVB_$p#&SI=P>@G7kTT+)I#ZM7IPFY~@%0qo
z4(iq>Ot5f4=AwQV@Toz}eR-(d<onf`qPugRb4(pEPkx7rXgD0!ayCS7gG}ft?T~Ry
z>FrsT6!qg2(a9o|aqCP)l*T<N>OOB=)N%4MY3gx~O=%N37Dq~BQ-R9#roK;3YRr*Y
z_|FvIdXdI?rgOz)&WMn|Ii%}PkPOsd;PPrq9s$Q%dJmX%rVNi-a`1g9LS=<G98=Tp
zaZFAWb5bu}YSEJ(bNEzjK3bO^ywq)+9@Ru5yHjb;!KQU@N``2Lu;UcKGn$cy6w^}6
z3}jQ&ftqRLdsCMnPz8lMzLjdg<50K9Uoms^s;PiFd;T>wxhr`K4x7O>$&HUSDH~zk
zrjMbtt9;EFPq`SyXr-;g>K=2;`=$G+JJSusI(?XYU}CLl*Pm>*^LCZ_vGuP3p0$Q*
zkj~bafMt(rt)uA=XhgEU=c{e2Ks6C&GGxVHW>iAQfl@NAr7gr3toG3PvUXh5b`Nnq
zvc1egIXkU1>sH@sSa)^r*j9)G9C1Jym-n&RFFdvjRV^=5T}7l#g-GOj5n39Sn3t*p
zKEe-C>FG&rX$6#fAxwIjE(2#|jx)J}k9x+6%H9`gp@~6eB;uym^r`h|5n-6egYyq+
zn!`;tmT|)DUueN5fHCzO=xr0{VT0SfNvEtg5UkMQk-Lvt%GdPS-uGhVi=3#&YimK%
zB(bvzA;CQC{_QaZ?wxOY0>wDU&m7}5U2I{uk7Q^79jcbOr|R<RP_?`5w+APjR;Y?b
zgbe=kZ*xExw@+;x!DQM_anG$J`gB*31S1LCn&)q0yPo;u*u{hV+~&F>v&Cek0m`pT
z&;*tmWL7b-UAw(ji_4_9jf;*w2YRcazM(2RUmzbh9<>jM;FQ804k8EVIq5*lc9$^S
zD0p$rINCua$C${W{cAJBmb1kJNa#lMkiXWGP_xvIs|(w?Sab6aN&xF1J7ep|wJPd%
zpK3@QfPTb^fjq~yD4d<6uUg}zg5|ILyps7U%6P!_qzLr%IUc#HZKGP7<9D!cZb<A;
ztu2q3mXU{SxKKT-7D+X)_(&BOi%j+Qqz73Vg+MwAfa(_CYZm3ln0iyB-1g)r54WXq
z31M|}t0==OhRJVXK+ffP{{VE;Vix9BNZEHO<O-TNw!*8=O3${^Qp);Ul#$zi@RQPj
zENZtuWYXrBIKZzU)TOz)S!bM_hByc7#d@}?i+5($@(sx$<Yu^ia>XLDlNk9%J-XDf
ztr^0;q+{cg+wrVR?MVsy$IJw+Yh2lGVicSP{cD@oBKt4STlk0TT#agaN!c9+fv9=0
zruNG9&$V{8`i-!)*jR4#uPxJV8|?o8DfvTHld4M*#_}*a)Ji3(9qr}(cIPJ;Bdv4V
z(ob`3=SHkTo~zoqtDR<h+$P+B03+7B%@O0d(abYo5;6Kx<*~gv+1$qP=ZG4{;b57G
zM(dNFYtW&YE+JP|>*-!Us6qBkLRgit&f$*L(D-k}Z3$azhQgEAJ!__wUW{1WAGD9O
zf!oZ1)Yeqclx_uV#OU~CJAoBe?%zC*O3|JztYwpx#%iR?g*?@kIQFX39IvfN8Pju|
z)iZ8okx(93_N!M12BguW6Y7Kgo@tEf?c?(8(KC{xt!miaZEPM1s*ZzZY7qD|*d05n
zTqxYRth>z-Wnyvio+<Ws2XEfZSh&>Vwp_a}(3*fb_Ru7Z<YSLRPLgA%!?s4l4%w+L
zyiaa&k(4LevY7q7-M44!NM&2yW#!7L;Pu5p1@U*o91nW2E|SUy&<~|jpHG@TRA<)}
zBQIT9ypZ{kI3$Y0a6=q}$6DCa?k*x_h2nCjjGDhajjXYj#@5eKK<;5i{$wGP)^@9N
z<yyJ{mfKTbPY#}16>-NvJ6AJ(e)FjX@(y<q=~Sa}He|;X_jhW6vxApr>0X1OS;K9#
zd4TQcD~Hll&8j4MWmC>YdXAgn=vq9?$1FO7UWOh$Pd^hQrm%Y>8O+h(k6NAD*nzTT
zRLRNBW<jD@sQKe1agM!ez|w7|P4OM$I3qm`bsR>VUt^9R^`MZs&T52LHq%^~eAO;`
zdQ#l!i58u;0Wy`^cAjfISlgnj5>$^$1#r~t5>_nWWkJCe&NK~ea;I)1ZvOejbW>^a
zNg}jTxK6`4%~5L`mA*j#05pAgtm;8dHaaL)lqI31aAA)|Z<R!wazL*yy)AV+0NKIo
zUVttZdF~+OWq7U;;W6LNoy%7ruva}5h-EmecT54t(!0G16BVEe-zhc6E9{#%&O29a
zqkQ(ukGtzmQBjSNKGDtUZ9y3%e9esd*OvT4g_8C%53dHjUJjqqyyN0TKoxc5<Q!Hj
zakI?GqZp+=^xW2jh)yWMJ$h1wr-AK22o|0f6mgmf>?i=nDCUl|gnkqZ4L2OqyL!?S
zKn%y}TfQ5KJmz-*p17<sYqRkB#SNB7$;VuEtmgDIf;EF9ebM<)>;UGZY2pC<pOr%-
zs>2w?VrXRCj&s}Ismc86{m}WbR2(11wMI;?%be6_j+HSWH$3}PY%*vO9x^FBzA5J*
z4Dm_3CV&~Rk5VZ-vMJ&7OTnOIB{NJZj`cG}Tct+PoP8(}A0v@Rm`CwqhFlJFQ7|Hy
z5{WlAG}#n>6<oOnr47ABZ3!93LlT-{L<ioSK{T5=t0Wg-?^a@-73!I)>mE%zXSFoM
zUrWnA3qm&vb6(rB{E<}@hn$neTZ$ATpTiYGB^Suc^25{Cg}ReD3xInHPc1>GsZrPp
zq#<9-d}QLHXiI(LRu)f}6x{PvNdULo-!%UKD<|nsCyz>RnYX8U1_l+T`AhhUkVr6c
zMMh=KI|||Df;v=kLDSNt5)(*6H$lY~3zc3RcB<0Caaubwl4>SQ=Zt2eP`OE&Bo#D-
z<n^g1U9MK570&cEL&2vdMh*=<c@%(sDB#j^XvHxKI*L$u>qsfUa7{1(a%l+WkLOAU
zGzEY!N}4q16vP!Wjib<$h5FS2t)y7B+`OmAqa>QrmrRA*<z2r@=`<Z2TIed}KY1t2
z#;Z>b$2@ab(y#3=%4p$j&Td^6Gq?@Mj^?S0V{0zfKPl{Mrg)13RPJqj$o^6DFRf`M
zbX7TWyPVD3L(T<yclQ<5L29=aDyRY6wa-m&GP^s*!B?s6SM;q@$wiIH>%p!{iKC`6
zOv}}D-|YL(yYka5;|($qT6*2eUq}x^y~ldXg^EnL%|3+Fm%et|Y^@!bDsh9&dKbe9
z!_9VHMBdHPyu(kNeVF#i=xez6c*FZba85F6s4Fu}T&|KmS5yJCslj!@Q_{Y9)P^pm
z9eF(~+^_eYK7Fo!?Rb8uyDugg=*GI9$DC8O;^`}V@Nr!91TD;G-<s%Iaw-9w=ZS`5
z4u3l32+G%A;z<7h(O0%>k?&rH9o`0KPo#L2V73t4DEW8<3e*1IhD<1sD*Kw@2&Np5
z;yI-%DYBD0v#LTz5~=)Y7f_C4ut*6t!>gW|{0&*Mn5FD{k9x{fZL!&dtIJj=YYdxY
z{*|o)hl#t^ew(MwsWbhb1g~o7wCyrz$Cq;GjNNhClwGwx&+9blyS8F9G5~Od^Hk?T
zgDuC_y&^9U=-x`S_iRWUk23<R&1K<>bvz?|PH2@#vMOhER>ztwiMV{=?%-7odKO4k
z#tM^Oi+etY<*<S%hqwc+aNZ=A6KDIp9QO99jFV@Njm+a(n~YJ&w@zvk%})L54D($_
z&Ndj$47n5nDc`|SDsf{{A}dL^8O1#FR&>(<)Fb;-VjiZW*hGBCPvK1&Ay2p5aKwC|
z^r~JY)l&B0+M<Zi9;?>2JV~hAL#4(nrc%It)bCs%JKQ^#=c(^lHGPM2Zy+z-a%!Wt
zGm6_UV9<ev$n@)3(#IJ&L5_M<x@<X$=$n+0)Knx9*0e374KCkN(y3e~$(?=cDJwe^
znGmHEnV=k0jF3pcV>O|p%4592ISu?ZnkwF%^4`X11G%;0YV0(lx-S0!O5?5mSpnj@
z?H4BllUP=M=+@_Hr5xBO^d_ww?QC*-)h#ix6EC^quAJBB*@l>=&sLwpd3T6mE2~M4
zH)Q^`gvwRDYpU@~B{gm25D2bnSlF@0KGpZQ33E`3Ji5x$X4aFD2;&@ArfJQ(#xtL4
z^KBUkhyXq7(DZiAk6iO!XAnmCdz)c?BSlUKuPOMC0bNBHovV)B>(!Lug?Y!sxN{QA
zjD>IMUQY{D<i@0Ji&v!2FOb!9jGs!gBI7*rYPsP1*X%La@B^ZNI5cz|P!ANG{c3=7
z9(r+29cj!n^Lo>00i<^{<@>aUr7Db47~#S6_pfO9Yd@Xg@W0(8bM>znTodhHsqm_O
z*0V*DK5YKA^L$NDp93Se1np4th4iThJk(3a6(`_p@y8R}5rqSqQVH!!vAH}Ury5gx
zAh{VF=D3fDaS?3{%e&?4j^ewvh5PLvjdOl5vU|G~NX%vXWw;gXWb|so6B$Z67}kE{
zJhw}lNc9-ls}Y|{?WF$zTBqKzQ%aIH1+J~rY3NODJ6aT1`*e9<yhl9O*;Jy{Sk5O5
zXLvNlxCeOjs<N&s#Mib5<@01>I^b1zytBv4Z*t??74PAz#xS!y%G6xtbVdNpDz55q
zx>7z%IWyZPoNg}m{_f2`;6k-{sG>fvA|gJA6y2qW+Jv8_SXb1XAM|LK+$}wA^*Kfw
zc+=>$62&IAE;Jf@n(?HMXrCuFn{#D5=j6cp(^pK?3jErHfO;(lMt3=u?q@!kuOd_w
zrE|4P$jX~cnTgB9nDuI_CXfNkU)!Mk>!JR|w<qT;!`_3X+QxZ8d(%`9bDY=qOa=MA
z4m}Yny~l^NxySEhxs#sUS6(cw_i&XUwYN|*oK}&CE4n4SoI-e8Lj#*ThyMV1@m5pA
zmMAfAr3VA1=FN4B9lqi`vB!FqSrK-R(zWJqsX838X$Y7JV{0F_%+;0C<s1Zseu-P-
z%Z!tO&w8&l%9qAEQo9+LEo2{g*dIly7SkgJNeKS{dZv<n*y9+aSq^&A0x@T7rzAN(
z?M--Xfxui;j^8#vN`^>_^VHA-lFr$f5<e>Dd_ft4=WH@EsU3}VmbPf?`_~|j)zA2{
z(IP7%WP!zJSK&JFTGg@2yS^}8kJQsR^v~9wMk$0>p4s%&=-5zk(vxwf_suCdG#WZ(
zi+MzH0^JW<j&=_*DmbS`$YbSxZ>>hh(t;yTTZ|(Vl)0qIskyp<xiq<?6sD1-hS8c_
zW|JP20F+YW0+Y1^0m-6(DM;dw2n{VI7@z`*D8(@ctrUKAbfg02ntIapG<T*UD5IJv
z00N9sgT(`y06Suyr)vV=cALcqrxehovFkcJ8Ej*0^Z{#K7vBcC-wRA+(vWAG-&4r1
zQk%R_io{2jtdS{Ep0vyltp)k@qz%nkfcy$DJ*fet&*eZ4IQFAFbfhB`XEXqez;VSP
zIG~Ku1Bw7#nrE2j_)aQ7xu*pKy&;v@&HN#M8Z&Tvr{z;S1s!TLa|q7o0E#XJa~<n9
z`sGpR7M!;CBbK^j_*0GaAmLcI(w>v7qkwRIXacmh(nxY{B>D<L0q9+i<5vo0GAcah
zv7iR5VR)yg1Em-wa4CjRpISgp4mqa=$*Spb6MgAXezhpLwo*TO57LW)AX42qqsc$r
zG#ynTOe$o0?WkK+GXDU}H$O@)1ff4VQI3^c?M}qv2mER`dGVYm{AqIqi}@WWEHRqN
zYpKD>o)jI)s3pIGGnsV=#(&$T&WFm)uQ&>NN{793XI9d~eENzUb_Sw<5$K7P`%^YJ
z;L>#v`A(8ssG{oJ)B{k3!wmC^<)-nLg94oSkGHmKK3|BMTzL>#NPh}<Z=fv-{vnCx
z)C=3j(kbjKC~4Qv!rHmwv|r*n<M(=ZKI4k1Kg28j-@3Jg4|S~muYQNC48~B3NEblW
zAD^=jJ=&~C;Z0gmpCMQ3)tM)cb%*<l5@*nKs<L>)U2(<HQ~u30hVm25DjgztGf?X!
zsGo&9{t*cjo%fM}>s)-EAl4>Q9{yqUYN+@3vVW|*nStzDtznFwV^#G#_3)*VsPpwC
zUtgOUryUc+kg)T0A(j6CrnToA+_vVG$@gkuMJJJ;tv{=oymeR9^mb1OTc4WbG5-L2
ztuggq2-~;%oyXU0dC*i1ouZ^H4^BRUnxp1J#ngRH_55Ao%YXG&On!<gCh_fpkS+AQ
z`;Y~2r2aH#j-QoUqZ2=GH`MLh;uQJBRuL#4-W5(?h#IrD5*QGDIj&PYb>fUwsxTqc
zXGH!t)+AGhL_XC<UlQw5@Yl`<`!$!0@kT0@IIe>Bk}sWGQIqf9%t!mx3tikfCGKT!
zt5t7m4>b8vJj`=5Gi1Ay?$q6*80X)bJ5m~UL2(EGV*?Zb2TneeHwKp+3Xr(8ooFL8
zqpeVd0OyKRK;oAMs6%_wid<2O013?$rB2-Treul$c6-yam8ikVr}MPZV?zn;LXs&l
zidCo>>QT=WgXu~*G+0ILE^j9IE`C-$y=$t8gA9*a;nj?CEB6Mv?LKcd1S6pp;^XPs
zT*qYzX=6|vfGNQ<NUP8qlOHX4Eu8}lXUrQ#TS0}UAm*gtcC6(ql!R`+)f|b1<Gn}*
zd7;-SQkcq)C_{r%NgvCaU_+c@tuQX>&$j1`XB`b_Jd5US$T+Nc0ZFphsoqVp0&6+a
zzq}VO%5uG{n$(jMtB(9)w;DoY<kmi-0RWDf?_JqrwCrPu)+HofX@2aZ9eruh@k;B7
z0me>i+^DY>jwroOlFmWqAm|CL8Ar@bWZ9j@KTa!Q*P*YE#4cI1da!qi7~-r&_k~0k
z@u{QXg>yDhopzYITF<;spQm26wS1VCGmf>Le;xqG0Q9b!QX!GpkCDE$y`wn$BPl%z
z&0*OOoxA&1o}Qabskq^ZG*yQ(unLXWJo8gP+b16N2wXAx)7P04^IWruW%Ku`MHr_K
z^NQyILgZ3gefA#o@Cl~I3eCj;3_fE{UJo?)8(7k9piH$J<^z+?Dy_2ak(bcau?(pl
zsyI&DmK@VbSVl#{`F95&-sd%<xoAczuA;kV9`!U0y56^1pe(aC#OqIvQb5V3l02R{
zBBG6|Dn|N(E${u{sa*WP`qe^yW&U+woQ&2j6ew;e4augCv{ZmAZF+m~$C{5AZ1YZ&
z?`D_=dsSPMFDyhH0i4yGdWx-kxJIQrS4JIPRuLk%$&B$-q-;n=c%)g}5ra|4Pnnb6
zmm^NVT8(~QYE0rfhBm+zAURs03a#?ctTy+isqODbr{>4=tkB2jsHI*hItnv`Ob3z0
z3-?Vos?tW?YHR|N#}!iLH^k$dZ8d1|P{=-0*0!MeW|*1dJ|Kt5)uzek)7t{GYoqa$
z20cU)IBo$Q@m$*;I#=m<S@Tj%@#?Ehk5kPrdSK3J<Y0YksKktt4K8y{f4xdNQUSzd
zQc{8P^GG@MssIPplu}Wg3Sc`tb*BTGjP<1*X@LAw8?Rb-2bxA06o3KB(|UEFcjpvP
z0)i>P5-FXyr;1<(gG=pA&JQG05VY2%<kApm0Wr-3826xzU{E<cVweg*#UMBoq;u^_
zgW7;DY4QZPVt>2VjYYTIj(>+d)p#3h$_e1r>+5w$k;f;cM^H0K!KbHDO~wxt<>)8@
z&yJ(5MbF_<F$G0NaX<%CONu~q(v<MD0G)dALF4H~7~+@+GfPN6N?z2i0os%wY|>_o
z_2z<u1e{dTTFDxDgnYFL{VDG&x`p!?sO?a|jP<80;0j}Ppc)eb%CJ1sj|QtN5Nc5<
zJabxHk;L)Vnt7nI<GnP!00l`H%{7KS#V-8PG3TXA7|!(4X~(TGk2MTq8kj{q@@csD
ztRzwudQ^%=az_;q9Mp%}pFlV5IgDebI-d2VZrhOJv8<%bU>x9d6|HR8IPKoNj7&{p
zT@D8ao-tTDv}Gk?InNcjoS)@b+R5N^&$V;m^qFlLS-|3~S;>o}9`#JIAYfGXU-9)9
zJh3(Ckj}m^&j?~iBeg>yA;+d_dvlvq`gW!`!RbZFF2FMo=j&2q6$P_=n`&(B`c)wi
zOuR52mCoG!vuy&pDOHM{rm$}m3Ap;#r-OYCYWo#w$;qVa>q<DUNgQO^0D4rh9%>Lz
zrAraZd)Bbr&SjkEgG^&j;{urD2dCv)86qhTO+}iK&JS9TtwS|LQgiQ74AjzesC)2h
zHfn|ZDaqEF0H+}%)2#>@WCM)T(>tlFgN|q%9xGUxNVqu^)*N*dh(_8{0Y6H!5-B}#
zlTiJ5sh=3fPkM(n5;Q|tV0~%>%N+Vt@5tt$Bc2Ur%}@?$z>;Z$uO^gm!`6`5YCK||
zIW-)7U{l8pTExahg&!_yt=62JB{B2wR%VD?bJnBB)}(&<rgyC5YKFHf?@<whQ$O9$
zH4ZuAvt^6kmmMjc$69uNY5=f<jw(guijF_K>r$u#6{<6lI**o`*#exWJ-DHde${4c
za<ltWGmK)SmySh6?TXEt#AAb;_oil~b>pTfho?20C_7V>;L}Gd=}M=bdeDT+Dliu`
z@z$7!pw0zIyqeV+vP>PHhe~6NkLgkmyHT;p>560!$a2*cOCaW>zyx<S2B=}drh}83
ze_Ci6J!)A(^yZWwYDN61z#g=Knm$+XsiOI0LOO#{MmX!mNTi1zxvcA}!Iw?iN79pN
zi*+0-&UPnJp0%qKX$)B4DvWViR@WDgsq8Ug*e73BskL^TT7KjbTa1p?^Cz-iiYOja
zDkAS36W*tmFES#PiJ)3tM5b$oY`0@tI+fMMt+xAkeCN;I6ozKO;oz4dXJW*5t;4w^
z!u1_0I~k<7wpk{O#^iFRwL^WWLuN4N1kwXC(rsP!SrX<Dw%p;XM&eb1Gb41VEiNOy
zgh-jsdRx0uaRWuj&w2pBi(21wskd^o?ICM%hvixJnk-hb7yHb5=CmF?=u@U?gDQz_
zr<kHTw29Xg>7+||i@Ct8?K?w<Ot_Y0c^TiiG~Ip)r_<cR4&~<qy#gx5uS0Wq&<~V1
z+&;B^qspF~S2d$}c0+czQ*T0zxkh-dmi7s!vymfgI}8Ir8SMqDNYf&zlc6BhE1Rfo
zRJq&qs#;}*=AY)Q_a0+0{{X&fzO`dC>W%}DI_>9*0MgSn7_|m5f)-FR7Oma9Ht_G9
zfV~M}S-u?5C4s)tG4=cfY3sT-_O*|aB-mG;JJT6nDPl2~Rs}m1th=p#7%xO;kUHbj
z)~?!VzhJcxa#VkK^IYZri#(c`+MgqT%Sr@xcG5>QQOz3-j5h;MQ)c%ecSdFDj^?Y_
zLT&95FHV)42Zt^bTo=aR?ap>~q%?I=kc*SR9Zgjl?Xul@C9nq@s!8CIYd4NI!!Y8w
z=yZF#olHgLH$QpDL4!ae(NF@uqtsN9`2uXIQ7_%&twn5}UAm#k!s4-CN;cZ5z4P4g
zepAwr&W?M8f)<g^6>E}j6iE8Fl$#8DxgGIWui9J7W`q;Zdc?BO-qup=8Qh+&+nNB?
z)~;?}Pj$1&kl?8t)>ZsdHj+)i!<FX)zol(7pJR)3s!8+}Lt4Lqw0T@M)*Y!mhIwSK
zw&mA38;SjEpYcFL1Ymb+>W-b}mX~+TdHUBc;#WfH2;rBUS2~5{cez>ucz!gv)3-nO
zy(rYI<4Flq(z5jX#<Er$oQ!Y>N_4j}T(-qLp2NL4(`rOUdR(((5HcKc)zU>PSlW(B
z?Zt9-nvz&Ck;yDO0bM?uZT-D!vx#<-`~dW*bmYyURx4Iu+}%k$%<qCp>s84o1RM}@
z2(GeU2XB0dis!IBYCrfw+#i-^&$*}Uq>n~8>O8i&cf#7-_X^QT&clzbcH%^lFl&&|
z{5vk4aAav2(2n@6$!2IX?ONK)Q^&<hoa$Zz-dX_rkmo(C66v-Ymg88FNe7RmWy?RD
zcXayFxy(l~-fL6CYNB~~`G-ST?E8;e)$sd-zG1kH;+g}dC*?V+u6p$!N|Sa0s955d
z6324U{njddY74D1?a?c4IUMkM)oEtinzvzf#@*bGGf=?guXMSs<zhE5>w(sywz{~p
zWh=Xb(W|n*ggWml&s>VkXklUVf$vCVs|{uwl|^+So2F}9Y*^iZa4VZ=;DmyQ815<Y
z-g)1-65#sgkjvNljjSkAAg=kwM{4G7Wx1VCmh7grhK~EUbv~oLB-V0UjIt2FN~k2>
zqLZ=0Ut3)yjAlnX=QWKoHctmN=`&j-!)uI#Sr<MXww1#NV0!Ue`##1z#s`I9chsIl
zLgaCbSFhVcGe;Q43XEd7{U+FHY2?6|Y~`5uHMAtuS<uE#*$+=cU6izm#fW!jT@{LM
zUpD0v+cjmIOt4QXDPvO1TN}Fj*DY<OTwPoTySbC@?btZ22{emv6Xs&TZ8<fm%u3p&
zmAP*=V0p<kPf^wMqZZ|nRS4aY{8cE??BHCnW1sIDt#_r^2oBT)g}|Uja%<LbMycj}
zr|$gKYR6HISmu>qDh>-8$Gg+)nUsit3OE&VD4?~{BxFnuP6Z}wO%x#1Et^+X5A#Wp
zS-QQCm8(38enuTV>b$TZyB7#@!MHWEtXsUWM{u1=;;@;~2649&GD<>`$5UOOg{CiK
z$>cUOToX^Wc@U04#diJ^lXafmqdCvxSxx(<(cJ5i!l`20c<WwO<LmJ?;8kpoYV_&9
z<K4${I@gK#rQ|x)%K6AS<I=HPnzIdoKGceo^3>cD(x{Ne4k>q<K!%(K25EqpYB5Wm
z)P8gTVwBPjD9$JVJt?I0r9C+m1Cv0<M!Tf|b*|dV5RfXV>&dQ5O^nHSykus(I5Jdw
zRuvhn2jc@6qi=J~Je&$nm64%J={{_pD?VNiOrEu=a4@{qbb(m%D_EIGro(m(K<NFm
zinPd7@zR^rRT5O(d;YZFGo0h4S$KnEjMOaw8Q{<aVoYM3vj8w?F}Gc$(g?}zKoa@u
zk9rKs!~AM5B=;1B7<Qmw?!4#ps3c*J>rzOky+YW<F%{V6rif%zY`7zeo-vBF$zVol
zn5Q=%ohM#<*2D>%9<<=p!f09qN)I(WZGbAUH1OCw)gnu!`0i*Db5+A`qdZk6BGG<n
zrMu^)M4{h-Q>~=3E_ziGM)L9RP?lrB1lF8(3AZkAeW)VZ0CK~MU{FYAayFxWHDPS#
zJWzFOc+{$?II7ZWbIXw$<N4FN3mO6ijec?#n({(}8^ve&S2KZ@Z^orfKMR(Bo6?%N
zg=x^9F-#{Xf+}GG1^1?y`38nGWnHc&s<n3bVo~&}ee05^#BC4*oYaffm=D&J9%@j@
zLF26l6oaUxBfT*RPE(QTP0c9jienv&`wDOwrhqxASD(h13WJfwZuo0WeM?x0HZg`X
zxrp`jtUz&$edE(L>Rt%a*3V8^*nIMQ**$vnt~`Dt*imvdr4DHwBSaR*%29w6Enr;0
z3!XU@(=g!U(z0$K4#yzkxiX1!L7HL}j8ksJa5Gh&3}=em5MW?rR5Cyb=Dn*N*E##h
z(i>SF{_fuOlc(u1+{5O~2m_kd))&vchQSXXd5ERC{{Tg`@>8pDPkNao7qQOVK&qvY
zPSrRW^s3Os=1IqD+AH$yAe@THw{NrR1~b6VA4<i<r8bRNqiBW+_pal>IXa0zdB;;+
zYk|CTn&0sB?{9pPMsdjLPAbE5a@_UH`wOFKCOI2VO7R_9HcRQlj1b1XhTFv?T0B<>
z#e((4c`m(i9mb_Jk@PNWSFr{xCle|6u9+~=udQ<!`MB$v>ESz|Odiz&W-p0UHIXOM
zxTE>kplcS!;>t{NM@sYZFzh>u?!$ZrVVu-$)}Q&)58^9e0ZLe|)*KK)8T!*fG^deC
ztCbm9-1R*VP_nbMNz&z2n0);8sV;T<C+E&A{(#q&d9o^O4#9l^scqzQFWw~My>rVC
zeQtHn87c011anV#yNu6*f4xinnmndr>{&;4%~a5z_ak;rM@rfa*U;7+sKeSbm_y~x
z$&vubz^Zz=%qN~3jMcZu)MfnYwyHnT!5+0yvShh7bId<lg!MH)Z(4=8V_is*1v|GC
z+ISpO0fb_Zec*j5NT5&y$;iPZifQBUr{j-$X{kfF(NCri#-sw2z>?GtwJuFp)KDek
zW4|>$wpQsqGm1@A19S-f?Qqxl(WFf5VwV))xTmUT(y}Oz8L90UrPOEMlV`0e;bm6N
zFlZUw+Ks^*K9$&LfP?tgC#A0VBjAJ9yL}!OBmksm+Pu6~dn0;u?sT?aE0KUI>Fd&}
z!x@c%U_h%S;|Jy@zEcx~tzM@*B6h)~tZ{xVjEm&YMnPPgF4+k6uFu4v+`5=Y;>V?O
zlIil7JFcQboY&Z8v6LuAGtrzFg?Z>}_;EuC0q8ncYoldhl~1m5?OYa>vc^JZy+;S8
z(Oo6Ci7f3u)s}Cq8IB#-qUoTZ`DJsg>Uvib@fI+2&Ck;~{VPlU6N@Ow-3LEjD-XmT
zEYo#Me<DbeY3-Wua=f~>6BMdTWOdc|;L<#)<O4gIN$6^`Nf=@abo8#prqZG$BzEiV
zwwe8<WQsyZ7JU^f^i`TtNb;5ntLSoZtG;$d>^(x7nQZSL?%B`(0DRX(+T2PG*v<!_
z#YT1Gw1te1t5iJRJrS&O%Fm&aG;K|WMVk-zm<p9VJE=%U<%Tit*{g4@&VK5k_s(i2
z)vk*0_#VqyJl*t0%PFcV_+IIo=e@R1!!<l!69DF2Nm+aBN}~FW(}S5?>(ZiIna*=G
zoc{o|Sj#o2_BD=B-t5?44e4qAvg&z0gbL|AGkas<>7VS8$sl|UrL$ZSk<K#h`PR>c
zn4L(gHdiA6*CkwB>&KFNGiR2281trjdw9O_n-J-W2>$V<ZxicsAC@R19{DubqC$Y4
z81qjE7tq%<a?CpWCj_w*AZ=g76LPl*gU~HT(`yoP_wtYTaf-M;>A<Din%X!zE9{W#
zP4zQ=&3PgH<?QYM00OB00JAr8(z6rSam{M%G;OVw7%h<wq@PnMbZce)5${$b(rtj^
zJc_!hma7<0IIRh}oVHLQ&z34-Zw@*S%BE$_CI%^i8$y6_`BD|`KRS7&??EFlb4sdu
z)6{y>;Ltk=N!x)`?=MB7?qQHS3cZX9&eRoI3K8;}KxLm1311MV0rjg<+_a~0&1EH^
zNq7ex>uTN&$_VHNDGWU0{3A5*C2`)Y$83b)@m4&rtHvpToNZ=2jkO@ObssZT!Nofn
zJc<CJ_Euxd(*1}P<mRpbanqVn-heZXpB^~kkXWEOtpYzvjgBY+r`aONBz31PtN`bO
z^fc)s^P?-0JqW6H`apth{{U#2y_vYC1<xf{qSra%)Xk_n2wZ1A{i~}A2Ts+A;&`{|
ztZ|%kk6O;B!gS#ss-w*q<kL+AU>a_7UTO8}_8r=jsierI&w2-9Xl4<Dr2)^aF}XkN
z(?Rb>c%VWs$7)P*#W=C1(lkH@X~vpQ6jB)AF-eL}^q?`x3V82K1f(LAaY%VIfI;=6
ztt}WdhAlTV>Ple5qL&n6fer0JrJ{ieMJ*WOfD^uG&w5>?^zBGSDcDy4X>*>moO<)=
zLEH!2Z*P{LD-)7ii=I8`2R$lvu)BCf%WWr?MnT6~a%tDn5w_M$`Vmy2F2p*p?spyu
zm>o1BJc{cxisO7EX?JN0t;M^irFFoP1|xG_^z@FW%42NnHxd0$U&@{_nuwMiP>;r#
z((OMpBK=ygnH+X3?j1W*mjv>0S?zso82Rrl*Xq?-^}RAMOX_fO=tVAcK2~oaPMFOy
zQmTGY#d8w)w?sqD`Q!VwPJbL|F&z1mIURwi_K19p>kBO=^&IXM#L4j!NKu4>RzK}k
zNq!|;q5aK)Vd`l1gXBE~T}98%xgE1XxIyZEg1pK8CSD))c2O_BDhK$7tI79PH2Ml&
z(T6GO4Jyh%)w!mW1b?VM@GA0IylJh=_ij~3d@d>oyhp4_a-vJw3Lc`Dw2*S1#k3&e
zDAVz#J;Fu~>xdKT)#j7l-59|)GJ)tCv*elF^6uF6H43Dd+DEE3uV)gGCZ}u%UJX&3
z#F{Kz$*Cb9?3(hc?6Q2vHI!8|)A6m;Tk1*c)A-lJ(T;CqZ)K`a<IM##wmIM2*OiqW
z02HgmKWF9_@;xF?h<a+|LuDbs{wl2}#Ign<)5jjYD}%|!A@`^3&|K{$_>-u=32Per
zkyK>y=C;||@vos3%+dlV_HhfF@_55qkYwER?NuAZ8nmb9zLVSrHIxlM(=?nAT)5X)
za}2f2r2hcDO;vNlv$r|PZnZ76d5CeAse=67DtS;`sv<7jsr>4ruE`3HK=n1S6P^LA
zyQL{|z>HNu2*KpiWcH)df!4Q3knhye^fV~TQ=0(Q2u{>ukPd>3Py)Bz>rDU?OT_?Y
zfq~<SX*^T$Nw$Fzno&+++K_Y7qy;?EahhIfK&n6{X+X^`0pfwvilGiz!98is78f+p
zPAp2|fFi-o7^i{wQMc(uhDVIj5yeVYnneO5$GtcVQjv-j53MTznE7eSJ!x^*6c0*v
z0YK+8Fv+Fq*wUV9*am@`cET4RQh-3GHclu3sq^G^rjWH_Ex0+TNEtNjA)r!$gY8NO
zG~zg+p^y>J^rT$V*br&B=Ay&6qpck&!jOujgdsWNx(y0#{{Xws-RoTb1!(B96uic9
zn&HROy*ryxm85pDE_!F0m?#6KG69&^p0#6cYvrcTK?sSJsRVw#Y0;)fT976yCdwiU
zfIFI9hl-tJ%{76}IqOStmE?;H(xKWjT26z>=Bfn2;+kS25&ZN>KX@}!mBFS;xqSLo
zx4c9IWh#a0W;)R$3Ncjfm*i|#_!(NFBCo<`E`2HO!sopU!S|(Z2Q~CBW6n0LN%CX%
zt;QKeHG`#{&~sf3V>aTxQ!tIHv(ljN5sEpf6R4p_9Ey=fNB~!wY(c38+ZzG%2Jclh
z7`IynUV{~-s3!YOz;Y^~LoJpMVa;n!TM3zVicFdH?^?D=iHPV=HJNL~xc>la6{`>;
zY}W1SA<mm+J-gDL8Gf{~{{XJfdJS_=a*KogTDPq|Dmac|98`<mxtbX$6womsry<Wy
zXl~UYK1KPnOdwRR$R4#GJ*Wamj>iWF@T&5&M|cPW<~3q7ha6RXKzVY+{`IXrUnwPh
zReyM{dgHYvnao>HH7)4#Al=StwVPpxtrD^V{{TqMLWd2Coeosg0AYxyQ{g~~7}V-_
zM^&?tQ%B5r&0xkjH?==G?NNh_`cr|;O@LN4BOU?fp>Mm~)QWQ$%^(5Oo+=xVS`t56
zm><TG*K!eCVdu*=a57>WzM`LSgl)(p+NO#hE=CK|mh5kfkGv~Nx=n~=KyB|*uX=_I
zZ68XUU{qWN4yKu(-ilMihMIBaibE!DSo+gOOBz-^I~oVIND4U5G$FyD^yn$0trh{t
zhN#`J53Neo45J|P&1nEQ4;sU_58Pv#;u!qZ=^iq+GFUeUJbzmAR^WqQq2+T^!=uW?
zt4uwqc_S3ibJCxh^p0VUGuDAh=9&)}pa+hWgi?-_hl5N2(bukM&PPfy%`pdIMrml{
zbx;U8)5?6ArhXNpZ)$EJ%KM5<*bMMJ{{RY5I?^1Yl|5AAjQ5}f9clE^aZ8`2059V~
z0)R#{NznAF0YJ?m9C}mGWK&N+g#sFQpdZ4VN3}GZ8US`Uru$QdaY@d3paL)qk?uHM
z!zQ(_nIyLPc{$G&lb#2?YTDVE?HS9S{d!c$43aU79+aTx+K{dtho=-M&wgkD{S%(m
z8+H6@b-`XuLck84C<Gur^x$|D+;Po0PY1mKAw8+I<~Smdp0og+MLRqiPSl`r%^`{2
zj)t9q`O<Vbpkf|q&mAdGT1t=@b3inwr6QiRfKy61G@U)^X@I9BVwy)ic&CAZ)A6LB
z2KB`$^`*vX2PX!QSVO?39MjJ})Q13cqy$8Crjzuk4mQ+H#bq*(p!-yVps0sxlv7&)
zsi!t^-nHW4&%I*l(g7h2-nG%PSB}-@Viv5@CDO#MFmdZy+L!`7;En}oE9E|8Rd2>^
zPDie5iW*GR<~O&Y=B2hQE)ebkL8uAABi@8^8GddvUFe2)Rwp)*_sFG~5Na(ox7)9%
z994-&b5v$YXmj<e93Hh=*OqS8WcR8O41kfrtX)BN$i1s=&T*Q@)R!e#<a1s4C+`?y
zJ`#cJK<l0<3Fp><&3ee<B<;;hA1o?9l=%2?D@d70wM{(zX@7)LXO6Y0kqfVSi=nC5
z;2MYc>o#hJH#y^)gBT{Pumoh)axi^r8KM*)YE|jQG;``HbCXDAr9Uq`15Wx=5amA(
zl<qU@TExmlq(3e@)0kv)OoU}>LO8`}WJ1H`$>~tHUs{=m8K?;79V%H!Yjmg^8;*Y}
zu-!hD1egcwSu<FS&OtQbKb<!o^x$}@DU-%eN|18Lw>1<;ECz8?0qcs^CUQlD<aVZ<
zVu;&42Q=ovHKCDN_y(DdYDqW-q5e9}njmqNs7dFFnD8lwn$4Co02~T%?M68Dr0YNv
z#!fm^ihh+EW~AtUrD%-gSWml3!y~BrP@K~BTF}jIK`G<k)KodeO(>{w_*QJ*BN*{a
z$f*wly+hu!Weyw~QPz{UT08MTnPNUgNH}3ki-FRg(-;+^Gi2c8d(#+aH1!;F){**S
zp{gXUAiz9wDlFjC&N$<rtw3|gsb+`?<E0_%(wtArif?~vhERQJM}K;69Vx@0%^{P=
z#wt)odj3@s8kqg+Q`HVTpHEobLv_E)IoNj9i7u_<kz#jH@6mJCsA$$rX=c7=42}1Q
zt52rePj;6syQM+Fua;-FUQnvJ915v6rv!4WOyF)ft4y1sE1uQPHjO;mhW*<HdghhD
z>C^%^tj$+S`*B8A+qSeKQyf8k1}i2#QtayOYWA!n9Em$(kQa380c8k4#Gd5UeOlu7
z4=mcm924_<R+CDonKhoey}R6qH;j|F@t_IeXJ}QOaM<K~);_VS{h3)5k&X^J*FYEL
ztozL_8>s_6eZ>G#(r)Cuw%qIU1C08LlKW7$uvIg*Hy#JAX+>&~#u7CFM;H}PP|__m
z2T!yiI}Ug>!o%X(Bw^HW!!?zw->tNJP=I}Fb~qL|)evDv09G!ipd0I@IsMV(iU6gf
zr}mN=Bp-FQ)~&-@Y0#;dqJ!&KY^))%fJYMIs%pADwx-dvz?M$H&;+O=c$K3AW->8c
z=DVw#U{V}#-1?g7qk&?GB7hZm09QAu_;>9W-fr!v+>$!xfd!Sv+w7J`Ql}N2F0E-5
z^4c^0^^Y7^M-7r&M6sautZR=C+CHK7yk=l}dQ$=OTqUF>$>~{|e~A3c{{SJIdUQUb
zwXSRh#k<CM<F#}8Z-?fJ^ht0RD1J~o`_MDKjIO}r0CmkWE1PMiD;ptk!NpWm-)>>t
zKqDCyou_DNrd-J|k)(MJcN#!$-d?4oF79!(b*@U=#E*ZgeV=e-&KP=o*2bl3*VeBJ
z@^~N<R5V=(Suv7TQ#W&p2ce^=-JL$g=8hvH`U<t6Jhzq$J<MfUxxuN2lM?Qm8%M2Z
z+q7*T?vKmuNDOUnPnL2SS9E>A>t1u>dzQB=0DKl4gI=SlY9bHZ#=E5EyqCn*mls#;
zN-!8I6#oDhY|u2!X*@v<jjV-;%8mi97VhxhUcBdaIxg=@(blb6-a!<IK_fUdl^iVY
za5`1fg|#ZBS0!N?im5#@Ry;eteOqI$<q6l{BBEskVAhv~AjRymV*@zPtz6NHn?-LD
z=}m2LmoaC`f4m3trg(Q%n@qkz=3*9XA6o5h?3VV;p^#)Sz^)GN#jS20C&??w%}R)K
zGu4dJG$KT7<aMUoTu$7%Zfl?Lp0<WDWpGC2=xeHycu*F`aZxP>nQqaF?sLfZs<)Df
z7?t1}Zk?$|JglF>Dc8)Kh#hlTvXO~*7;c^GGD1^|-eeEggH$f9)byxjnMPc3ioK*<
z71Sd>p0%AkMG2&|k=E@o$nQcK-TA!wiW#%(S<y^S_*J1GBPOUtYr}!XQ;O-JkT4{3
zS7cE94)tD362Rc(`c#3?TU@R6j^3voYZC1FQXgu9&PlAM2bEsq)~{d3_L#i*c_d_t
zk(lyMK<;X(6K~96v+62lVmT^m#8+`dGE`C-drA9xATvG{amRC8jQ;>=ws1#5#%q^-
zUQM}Eg&nI#&sQ@>suO7G&w3CvMJkZz1k(Wj0PEEEQJCc-t7PQorFKVDb27!OMo0BN
zmC<RgjO!e|vPEIo60At)J!?`TcZMCSs-DLcea-cFS067bI*QLS4>hIaD;`1ZO0swA
z4OF|FM!`=2)`kVUxubhVB!W9}T=X{&9#x4br@y6Wwi?)}<0MvKwt2$~V9&LC4CaBQ
zb2jGX<)8Os<=y#;)YKviYLTxTW|L0Q^$Ux?`0$Xbw^BM*-Oq(JTbq#OHbSa6C#_{U
zBX~ulg1LymHmUi8XBDSx?{T3&nfKHh-Jihj13SoadY#me=_zFcL`h|C=CYKNHm4T1
zJhIbCn*RV+`O$<<YtS@Z9z8BSv9V?MrIHBZEwMoQRQh~{q}W=rY}rJ-*($@(SB?0_
z7mrtGINC}5YuGNOOM7;9ZKt5G9Pvfx+Vv*E;8tk1bL5QiKyPX`^u+)#tx+Q9j<kL>
z(~S3}80pP07XuVvdeR@Q9A<zQ6dG>>y&1&=9ZAxFXzxH8`Z8^8*!iocg@!8+Nr)^V
z{cBxMHO)QE;)@}uY@TW)H6SE|S(Za^GM`GxoczZbt(jLVSyQGP2e_@EXCjf2)aSRo
zBHaG~cnox@9Ah2oyo-^=QJG~fq6&D)sSV6~FjQ7p`D%FBFrW(t@;v8mDmJ@}=W0-6
zQn(rBqG*bfng%%C4E@i>qG?%=Oj7Ls0B5f>Z32KGeAFkcO(P7Nhqr2CB64?+O0<cT
z_o|2Qel@KGd!r4=$fhEzNAgq$fzq$MC2E|g%Gm8%!H~#}AUxBGlR-{u$pAs=no*K?
z$*0DNpP1sNGC>F3aA~0n3^GdG3{~W@UaoUl$59G?Mf|CrebvtkoK>cUW^8?;)(&#H
z9jdIl&KQW0AFpbpmNK(`_3>5~3ushi<oBm`D<ZkOx}P{Cf!GRqSWhWZ#~gE-v~OU9
zC`IY%P@P5Fgi-}CB#%!>-!8$i?N<S}jZQc|)tF_LQ=jEh#|b}Lq$XK6NxOlX1lzJP
zQHa3pPbvl~$rwrYrjwpcNPF>2IR60a&<1Vz%%J;KGtFJU$DM$90;vImTvPasqp)@2
zlyS`<IHd-q6i6@)2d~nbns#$c08);WgQ2Aqz;gAe7pMZ52Q?s8Y$_j^o;a#NbY2nB
zq}6qJ*^o3SaMkSZV+ER`L@~!AxnBj@rk$rGY(IR%aX7B}J5{@|G69JftpEZ+{l0PI
zX!}}jCq)-#Vim&?`c(<W3F5V8jK?8Tb5v(cx3zgWRK1-?PDZ$eb#jmd=AyZEwzqj)
zj3~`oDYvCyc$P<$!KcJNd3hvuucbIl{TdT@H23fPMD5REQQrRc^?>D8x&v;Sc9^J`
z3X6}%uwsjT=~(i|IH_Pzm2iHQji^Vm?m2(G^5(ZE7?Fl6J5Y<vx5ybQ&1S%}Y}?@t
z+;Lq8hNX%PK@G?HuBN%GDFUb?m36JHIn>;aDo`WYB9BSBv?X?vx7NIi#BiiKtjQVq
zGo05^Z#~i`P;F2;isUtRXS{cAq@F8Ru*`x$V0z%!OK<+6I^wy8KQ}ehT4k+M=};m<
zfyo}#=Q^B59Y$sCn)GIEtUFf?;yAYIOyK?M>%%^TGZ*!wJt^HjwAS~okqj86KAot|
z2Z{hg!KcFCy&VNG(#CNA0Hr6e&gVj4eqQ3Yh{_t~v^h4hAME0~C307#aXrR!x2j{*
z+w`j1m<G{^;QH0gNkP?foDTI<P*81q`qJtLG{b2%8+GEPZb=!a&rU0<ATv0pj+EMP
zrUEdgjyqG2G@n`kc2!5rK%@brZ{4G}(M@RSGHkfXL~)Km9V?<b`p1Rx6nllNDp!p+
zskJ&2sqmbXRyWe)%d(xlGMKBe=o-X}#e)y`oC@A=5x;1<d*Y%#A-FllN8?ya8yC>&
zj$d8$GUD*guw_<g;*THRY}Ki}CwDu8CHxEP^5&k}-OKa555l5tPVYQR`3mQrCNk)4
z47RAN;J@$cK#%rg#ZJBx)0c^EW^?Ke1yO6;ht6hyrfM@IvhvJ+rm}dB$mot&KCIRr
z9njEx>oa|1plO;6Es+ZG({U!U1F)ss$E8o!8LG;yyE?mVa@y4bM6qFdVRKfO#*#)b
zj>G-c#c_G!ipo}f3yuaU+nDTR@wME88>Rdk6;f{$-AHq}`R-o1wHf0zCNMEcX|cD|
z=`GDUHS3pS$T{_@((2a__edXwR3f83l=+%2IBGqM2T{2r@0yLSWsr^T$MLAKgGEi*
zy2I052k&A!nn1*7Cp6kj^F_+`aa$r$$)qS3ts=2eNX$(a7bu5{N(M=%5raXZu+S+<
zsao1)i_9@L&rwj5k;MU{*gfbJb4F<eh3{Ja9DgrXj~M5!Ya=ytNqxGsB$JHe>s1}h
z>#Ngf_6X$Msz;?f8n0^Gt)o54ik`hhd~CNAH#DT;lYlx?v5`RoNh9ABnJ0|mgOX?i
zCYTNcuX<9%=bB+Xu|Vd49;BaoaY6@5jAT>%#xwyOfR1SfPo+OO>&+%Opach+Qhy3>
zdI`k<Jhv52>P6X%W~7~*N5HJsl$ODy1LA;8{BSEuI6Sd|)7qi5OepoMgQWu)PAFM>
zcBe4;bJnBVpK1V<6+cRI91lu^rVS%V<YRB+Kn)WO#4*J@%A>t!+`%k^<iI}l3X6aO
zlRz3xIu7*%+{6#w6_+GeEPnC#s7;)Q8D=Jg2EyEq#8j&~kSiV=5(ak=N4;K1+kj0l
zF08wO;<L52EvL3Q>sO;)qn@=EqPy%|XB=XtTBBMn(@gStlMX@bY7#2d+U>cMj*i3i
zs>EZ~yvZ$3v8N>9gdCbsJ*haQ1X3-q0MVLJgVR5iIZ@dBvAOyRu2y9#i3}q&n5zqG
za@g4fjr6ILO4KADEu){U3Y?!n`pq@FC=o#ETG9A_RFnQ)7=2Anz7y2gebid7V=^8-
zg6d(6kMOG|@<xC|fDm>Sww?{WBj>qA{3>7gL-vo}Un2X{_A)Y-V?gDPUX;^acl;w7
zS`p^op*?>6MD`vSxBK@<asJk6`wr}%?Mht^RFFEHQMeKY?tQDIH@*|M<n4Mt;VSUG
zy5c)VY<evUitc9fX!J)oIXJ=3(xnhgdP5@*Wv$cW%@#5Hy*-cBYP`P@q5%0ida3m^
z{faV{YWgENY;M~dZKUVdik);#QbriFZhzXS<@k$!PwwrYU#O~*c=uUz#F4MjYLz9}
z%2};WhRS$PSA2fy7xB$mkHI>NefgtbY*#A&G1jC%HPQSysUp|)E1)-APFud#s#Mow
z7n#+4PONw)RUf>*jC$0g!diS|_u7(w-&M-TdwRrqk3Kql)nzWkP5a4DuOh8eU5ure
zR((#9JUO8z?f09{v(x_ov%EJE<sMVhJet63`%(cjE`6vPjj+KJjw$k)yj@qjHKf)&
zJ7VFJPmq-Fwxg5A`bcc8gFX)@9V;p3hi2{EeJe8dG@de%a@ag=qm<3olii&Qd_`Ua
zHVUiTbyt6gm$=MU(69Uln&p49E)P$`ihAi6Cz6hSf{sQ{wPxg=KGt6(6pz>nttX6i
z+0It%sP?KK*f-?iEuFr#D(D)rkNEWK=xOp2=W){bgISaiZ)F+o4OWu>08o%(OUaMX
zt3n+UR#Ss!2=C2WUkqGIz_Lh(&~&K_ocm2X{pqAR_ofxx+?F`$lUwt6R{J1Az@PSo
zG<ZK)ECCUZ!hu}DF@U+I6@N<Wt$Z1&AU=1NeK@ICz}K$%^MVgy%`|}HHaQ&)J{xJL
z&z1)swc0ns>&G9vxGV15)w?eO-P?WZglzCZp^YPkdnut$opODuu_aC$gYRCOCxq@J
z0JO=EOjJk0v9jfvAL~)fJ05czf(=}=g5u(J7V(!OziRHsg9O+q8Yt^m;qZ5t4&OM(
z>$8d+v<n=a(mYYBKi<b8s1kEq+O?0_CV14A+uYU@ji;K*n-eQtXUjOvWw5~JwdYL4
zdy2_%f=62Jr?HzNYCsMt<Wh9SY9V@3QPP|R03{(AH2hLyp0rp7;+zLGoez3D=9Pfi
zu^+k4+|=2_ZXrPF&0&dMR{@9~l!e^?01>I>19jzza!Vqd<E>-e$g<2zo+<)K??<gQ
z5Er5MrkZf;O*~eD7M+eMpyHltfI&tnz;jE3MT9dHpi{Xtl<XG{w1m`&x1HT-t}-aF
z5fX7iic&F1qnbHDaTEbgAeuqeoq$|(%`XRvP<`mZs<4Fjr2>^jI4Lw(25lVUr7i&!
z{8D2*sO1Zc$25g=+oeCappGf>fe~6o6(a&gHAl@yD6SnlPzFsnFEr&tp7dCE6R#t^
zC<J4*I4>0=sq)5u3M>RbeAO{k*mK7e)g9<81LTb2oq&uUw1>WF`O9>q*hv)mL?8s8
zT9CxsI#YR8z%?qfFrvU#an5<B0nJ#HW}rM8n+#GgDW;wdMkp)I76G+Ao0#sAhf~Ex
zflq|uWvpw%nwv#I*`9%5Opu}W>sl(A8LYh^mbXB9W3_Fhd0P0Y-t3w^Na}{ffD_)O
z36q+1YBwG@skR<QE0xI5h#~1wxWnVpt}63Y<&FH}dsdXSxQflVnn1rdH7tv@sj4@B
z4RuzH;G~JZqV4%}iiY8Fu;Q(Ogy~UTF69RuE0QllhzBFJR=82Ig<4c4bJC%i2+w-x
z!#h+&)c8z5Ij6P?(^wUem;1a^$jJIv)2&hFJ<Tm4vKdE8>8+0FE0xh(7h64eHPu;i
zg?+2$vsl`t&ipg?M<DuA5kHtVh1*jF^{EwW$y2e?EXkV&J?fpZmbY=%wNW=)vi9sN
zCf+G`x(CN&MLo9>o8<(!$4nlTrvif_=canqOPGpW;PP{dxS86uz3#w$(&5(wttQ`-
z0;IX*r!;_YD;WVSJjc&!k$LS=+xMwJ#{gDLW1|?SxZ;{ReJNXzMMDB!v4hr{4G0O3
z29SP~fO7D9({&NL1#j-sf$vVZMr%`^aoVn)l1xQL`Rz|Up4C#{i96KD`&O$$Hcz)b
zPg?7!xmb~=oeyfS(qbxR4pbHIP;wiS&1Wxx0WLBPJ_E)npa8T)-!T<~D3F|SPF#v>
zee+5P_xvdU?BrA9KPNe+deh-N5#FQ#U{dz&Nzh`9=N^>e?Cu6}c7o}$PtDIYY1A0=
z?Ns#=Ov#Sz%}ont9D0iH#zNe(T}g<@y*pIkbKaqd1!6tw#yi(3MR`WqX)}{ca6Wz1
z!P7Lroc-EpI5fRusKGrBDnOSx98-IPKs-`0=}y2($BK!#YI)@aH1*GVNDMC$L?p0c
zYslG3{HHlyGHcoOXv5e(S9S$>_1Xlukxp_O2Q~K@9PdYz^Ra7NmHJYOKN@<0n)i+&
zhov+Mk+2697kpD-NW61F<o#(EJW{dApah_fJ?NsCh3Y9fdsCDSl-zSn11B|R3)vu2
ziN-}${yK8?q`(}OV%X|v=qNZHC>RtV6TJhP8;S=sz$njpF_Zmh#ZVK(X^+DmaZZHb
z;)zBGIG{ra%_ceKmW+E-033r!fIHHtBme~%pa2ZlMWG;;#k0>PNc?M^&l#<q4(P{k
zBtd@b=QR~J10v~mT}&~68kjofro3(UvNkcE)edL@>PhWPehocaAB`iQZfSuYdUvNO
z#WZGsd7uX|=cPCBrxBA)$3I#Cbtg(X(ZwNyaY#5l>CMd`A6fuTO#+>dm!&eHj0obI
z4LtHXQvt^mfLt1SC?}pNxy~s)s(_S?9<<U;AnQ&b4s*=_Hj}+ACVi;@cBY&PQ_TjD
z5s}44!!<Gb)NT3Ja~c{uQ`hyTW14uS5tl5RZN+XYe7POPU|V3$J9<{~4bYCh)x}+V
z#YD1=k(zDJTHVwhHua{VAzO}psqzfK<EItp&00pN<YX9``6uQygCNwGV6DpzeQF)R
z3hRiO+UV`N6glAatMdN<5bO>)tc?ZK+bHT(R;+}O4QPlK*yc*M-A}Dkw;^X-)xyAz
zIi`fj+;LetlAWK8YPmI?se$F6rFCItX_-}5iHsW~(wq-97voP+&-AZmEaH+U>N)F9
zPrXbWj8m7E?OQ~~MX~pB(wf;LgT*THJt!dK6|spEecFhewlPyl)0&08^=BhUjVF&<
zi2d%BE;HJpZV$C)Xn=8^;+Gg6^mpQv4m#39C5-SrY5i%D9y6MG9M*`2Sb*ersgFJC
z2(krED^y~}u>4I_b;BNN+30<$tM%(r#}TKe^{7wY>zq`~J5)?SYR#IWGJ1@DRC7u|
z1Gh>;#Ys$-Bbt~T)DfH-pFCsrtq}~GEQ*kx4M!D7PD$dlF?*0d4Ufj4JRJ6`4r;mU
z?b4z~kr0AcKD5KupMnK2_37TTWrlN_1tH*41JCuK3FGNffK5XgH83RcR)}SY!2Idv
zqKstYo@!R$;<Pg>$}`usM0)yEvMxqy5^5xC5v)!sK8L+ZPI>gGi6@*^Wq_s6){u6k
z>U)|2lf>8^>RxkEM%bwjBR%UxX33-AQ&{Ge53M=4HAEHPr9qr_spaE5=Ab<LRI@}4
zO*{_t;f=K1<Wv+X8O<F|4Kz1OcI=My44OQX?^AJ}bM&ZUA%|L+@ZQv<Bz-+`dG>o2
znO8Vm)^3e^d3C5W;Q1KCXQq2%wweguB9bU5cp%ia*3sL>5+DNl3i(6a3#+*7?b>-V
z5qjWMb{dQtj6QTcu5pqvQ%oT-v~pmpbq0tnqJlk<BBFKzkj0+nJ9OObijLmq8?aeA
zuN9xJ**(R!V+U~bs5C7$;?0@nZ<)Bj^q^+s(TQRxdy40+JUq#J=DTfGY=Av|YhO^m
z`vt2{<+JVVqmxe4uZ8`x&*i*(yD*?dvV=u}*0QZrQWx@lqi2!)09A|aO)OBBCnM66
zP1NJRLPrceeJO!v<&1F_QO$EU_xF?PU@GV4!2_n+>l~?Ho1v<(TEP$cq);=S1t29K
zEMT{%YRR?NKGUc@u(p)|{x%#|w6dgWmN@pR@w8I>>4WYmfLz>&Au=A^*Cu>Hb0(&W
zgDbnHI*RM1g=USB##D?}ZKjKFX*Zeoo1&B0QUc*&<?r^%tQ&t3M|Y~dl0xHY#^chu
z231sIa2Bb@ZE9T25~yR;_of6Ig~+tEX*-Vf$yn<b5^Bt)S@)iK;YY1@w-%{$1IFqI
zKi;gHO%e+h^9BQY&>~CAi0thicT&oukOgFEy8IfR<%Au|bAl^FQJNpKI!S^Xu4@+7
z8+bXlMMcj=rZV28tP3c{0StNfH5QAlo5@-!TRp)QUr@69Y-_juV)UtWjWulx9A(?R
zA(}e2sJeBjlVM}+R`ffk)a=sXk&}00LnXVat-w;g^}A^lDQ=!tHW9`>DFKUrXLl{y
zA}%8XC6BFXL>EuB2u~xg){^5{vWn;Itof6s0LiRR5?{!%?2mUToR3-oBU0YpIpjAP
z4ZEDvbvr8sxASI1R$P@PqVVK%N2if4?W}hu?x1>AUm96?`V7)}g-AodpiJ<e8c33B
zPLU8mB=PCZMWorJwvsttm!4{sz<Z5GL?xZfn{(~yUB->!_f0j|3<{1jTDNG}mU-jH
zwaT_~7>w5c0EX@V0Cw(1GT$%16`88T_FYa`x$BN=d&BMKS!dCWUg(ox0;8cL(y_I@
zC|$-TiE!u-*0!<hQQVY@EV%$0kUa7US_u+V19CUgySpt$JNqS*KQQ~kxV=;$yLlob
zV|K@SsRi7yNwr*sZoJj|JB7}=*7Ihd7B(OQgPNaL)=V=EgE$$_t#al`1Mf#8zZFvE
zdFFO3`N*g2(D{zTN!QZ#+7=^v_U~F!%B-fm?@LFEQb|Jb>JNJD4EbF4Bd4WuRgIaf
zSWE+Esvz?26OJ=eJg9n9TlogEDBO+6BW+I8VR@{WuT)?fl6m*G1_1P?1(v%iep6NC
z)aH)|XlkPKbHS#TElG^AF1PamD&y%^^#1@5!yKDi8&9obNSng~D?V7A0T{@sV?71o
zu+$fPQUK(12C}X+xuEE!)SjZbSZ=1a{{U3%htL|<w(&jWU@V_M)}#xD)=j*|_^mAt
z38$Hz;wub&3GQm5c&^+h&lcnK>ractvH78P6;G!Ift_Ub0_gx=4nHc!p4p(23@cYp
z*KIB=&c_~SrAu-kxsT>-vFD1`6V}FZiAPLSKY0Dq-nL>;>=74}#bri{fbIP2Lc--y
zkTJ>NXT5qb_)ZFo-!);f=PiIJy3*}u;kow)ta*TeQI_WdvUOxyqXN~QgJJeyr8ge=
z=C*9DEiD&pP$G{&Dvg8w<n#E}g6AAoZgOU-oKbi(4pCHn1vW-685yWmyHtenQF6@7
z#Qn+dT%Mpd65T7axlmKyxlLXoGmbG*2O)e&k@3LISJUOi*sE8-1M7~pnQr@U5QBlA
z&Y4EmvkM(QM;u^e8t}W`ZssA0R&qvb*L+p1n+-U{%N7^_SCCven&ID|CxJ~8%Khlc
z^rvE!05kJbu!!@H)ZlYY!1WZJC;%AE1T84(Ntysq7Xadr(@P&pGoI7{r2ABmjq<4P
zOa~&bX|NgR<b0s@q{>F+nzV6&j&WC&vr$C57v>c@s-I(A(l<lL`86OM_oPI@>rWV|
zC~KUKd)8&h0<{heWZyQ@G2HW7K#3IHvejLVSaVYoP`SlfnG<04$F(#awB}rAy)f``
zKo(({ax#A!v@qSltgYDTR-m~f<!S)3(Se-RIotq3)RN9lMN?y*^Z>(5CyICQQyUb-
zLgPISE1}cWNdj#>IK^N$9V=@=olK@T9=N6=-OaI3&DyfAP?8OGw>FGo+%f4`lfku!
zJv-Gw*i9HM<_~&dSr21ZW<E^2K;s-5f$ng46|tERhDPA=Pg`XGmvK?F?&g3Qk37%?
zjqpXnCh9)ez<i1YF)gw)inSaFiYkzb%+pB3u{7njb{Rb?@5#3Sb3kFV)uc&YJ4Gx(
zsfD_xG17wMHfeW~YJ@x}T5xYlkEo?wj8jNNnK{h_{G{?QX$T;7qyvhgKn#j*PH|2j
ztsD$`(;1h2#N<^>X07T2_qp||N7lHid`8jOUI3*O-)eP1LXN#De+of>X~UdV0KJbi
zqLZT2faaJIARyOC;cYJB>i+=kFu~@cjk!HDn!vS#?Kcs@y8=fFPo;Zyi=vGR!Z>Zw
zn|R&38LGX8ku8Roc+QOABB;qwYq8Q*QW;R3hU@jNe%Y=IF>UxKp%v3;7H$mkK5+j4
zcPFJqNnF({85*6pmiw0;^_3!S7{@iau0=9kY(bSBb6BpY9`)ekAm~?(NSnjnR%JH1
zjtJe`7*Uh$T+WnNRn_Oz8Oe-s5Iw0pS$IY);ASr`8%0~uY#P$lLFxxe_vufbH#p|3
z#n&VSW3~f#m^*f=Nd^=zpzBUD8?92|zlJlk5my!*in2~}?MlpQi-O3?IVQFBR10u%
z-m;so6%s&ZTCfqae-v+u=rpMSxrvGrxz81Z(fL=UI(dU|t!*kzvV;ebPzj!qYjI~H
zZD3a-xUGIQi&9{XmF-(`0wY#su76iz*Ez|-tvU?JZ@ts<u9Cx>MD@jUt@pEC4w~7u
zUrbbiJb)ezaegWv>EN$Tyo&7Z8)OXF=Nt<2?Pgge)Ffv;c)&H$hxmzRaml8?9kWjd
z6vhD8V<crdo7R_{QV@oO8Fj}z((NSSRFhIiZ!0(4+vrU$VVypR{{Xx=87H-MAc6p{
zQ%7Bru1_F-wbU;tJ69XrW-hF_y;cJt_p0|uO|IgksT@`PNDnnT4z$U>Yhb<VTN%YN
z?QD1VrZCS=ewDt~5QZ#QCpkRRg}g{U;1!~)U^(TAS6~)5{6$$?8;1T24^vxVLj60_
zl}|tj{3vyVW3H6se9~jsRI8+?@ovx7wj+X8<Rg9}rdugrugRK^X(5?V*`>0+-bwFO
z-|rgePMQR4%y$u3Hw&^>UrOS|UFy$wDQVn?>(+v3Kb<9U9^iDP&M6N9f!2T*J+n$W
zQ%L5Qr6Pr=D5ir-DWH1_Pta3GG~hU(jMl4T%c;#8sBj<}kT)OJqaO79)E%y$GfYxx
zy*(%+G!exkWUMDzHqrhxVvyStZho|dX~V4q)pD6itXAV_Ij3Y&XB1c!Sg=!rO6PIu
zNuPQN%_7rG=`<UrHgZPky_fREVBNR+Q{gs_!nCvoz@I%o`rrL}%eV*5e&jLct^6l7
z6>72}KJ*S-{AkA%0nI_xadGKV+7h>rk;lwAred59##Y8kkkrwYNhX>-drxiFQ4lh?
z#a;`ND=S8mcAFO7Yft9D#d=YCA0Jg(Y<4-tDHs%snszd3jK-g8Ok`7vW4$QBrXn&k
zNxUxyikyHuR4#?60R(`Wcwy3_+EmlW&DV+sKOFsOamTGj4;{rnJa?ucr|FtwXB--n
zAk#}O4ox8y=aJ)xlUP>LJ;l*4k%RhH`@9XqNTQ()Zl7=i^b`!502KfRtOJgjs-J7e
z3WU-2#{-LIE%mA9NUIk;b5S&bPCu1F_Nm!2VhDZOtDAzXcTF0fb4#5EDR<1>&{Kx&
z)>G<mM!z-mE88^#>(&T4)PeR|T<AGX&>Pbg3pxh*m<(4nFNpM*`7_Ah@G7A{j5K)g
zJc(rVJ*egj9jItX$z`bCYgOaTO5#_?R%S#<Z7^8v88xys$7lnrF@k+pG;=Z7*%I4w
zLw-V>Cxmi~BY(halApx4(G~;C$Fg*+tIrearZ18~^$SJVSssWk26(rS`{Yz}Nb<(W
zV+siVCKctUU)5w7Gd4ZV5dQ#b>P&yqrrV$4YMaTFnny`<;hS@E@;&0N<D3TXOd1Z1
zgZG#5^ylWRxO6*?T3<ET_jakyl<}s*sxmS7QS8p2u2tKZz5Sozm{a~fP~-iq)GvGC
zn|?!v`d2lp_*U@|u3<Zu8QLqBW!l7Gs}2Y~sd6+=)@Ju-rZ0%}7>N<vNZfVBM&2#4
zU-edhoq5vERF7(LyMJ6#<z%|8o%;B`UE5%_jQVj^=kfi_EwQbDJ@B=|i^-SnJ1^3r
zc^XE`5>LGxr1PC+*TfA<Rm3OD_ad_-@ou#*{JyaE6^BO@`B6N~(|vzckmawYKHICU
z(sdiAut7TpW*N&@6{f(q8iX;h%9G7{g{7ndB}IoS2i_vBBukSrt|yVAeBp^4aa;}N
z;d1_FcNVW$xUz`G$8H8XSC;CB{XS8gjPXMR%01{b5#ExdcNZttj+A$xW`F`PXdF`W
z&lH$60HUqgU44$>WWi<6%mq`%4LBXX^u&5@oQCERCz1-V&TBz5_jMSyL-<#i!K>d}
z!R1A8%79=GO4+gTuBB=Kd`bYuXy##KxlJgyCJ2Z81XI^YPNpaazS_>xykBj7fie|*
zR=evK$D*<N(sN_5&+L8c(LX9h(Af16h3<RO9c~hKsH8gUlYqEdj&?p$%IJ_MC4o8V
zim){6P`m<bG4-sTqwuDGY&J@UrOwA=Xj?)DBAy|Mdt$KHR+#<Y)KL12?l4;vuENIp
zK@sS=r+I19Vvc<)n-|w3qnb~)Tpl;I0CfT=mz{un)4aq|d9F~)aNO^D1e0WLb~vC8
zoXVxX`hoSM&V%@!b6m%q!1CPGidni6X$<Ji&9eUh%T=Z|^aCI{{3{7mka^~sTLYE?
zfHozb7hjdh_02<=T!LR|^sMDzd*+m%n~rILtS(kG+Om=9Rf+Qn-+3_ys0WIqPCMe7
zWC}j_G@1iDS4CG~yNc(z&2#dmTdj0A+=6QkWx&trQBUF}m0fbARy^spQ(Huwjw>$h
zaW;KxzKNSDFu<nNj5~8t{x#9cO~RCYX?D_#ntY*gamQLi#VF>CQOXw>MHu|)+j;9s
z7n)q5ahqtxKNzGma)8bS6yh_AOj57{`q12(P(7&|tyP2|sWF;h>6(-btx`ZVb5A^q
zW-;3pAO{^O*h4xB2&dzk0OFr0hJi}mDnS{?Ow(9morXfnNa;wR=By|Hobyp`1-PYP
z9gminMMwsFQUEhmVGUkINCs&E7^eaV>CHO;3=XupJ*mo6ADCoN#1p{9I{?q)rN^~6
zf@tr}I|yzl#(inTW11=02+9*o#tlo1Eku6xD*-A2xKxa#Tdg%P7-O|bJAA_(DOd=}
z&otn2ywhpwnHlt=z#^$*@`?z+=~6@)xLQ|Dj&sj?b^^E@;PFmjhU29!cRx&1h!_~B
zVF;;_lR-O2JW_%qZ(3n(?av=dECVDvhEH0L0;MDJrjESQaTvkYl#Xh6!j|bznHTs+
z6uCumt|`HDo_VKj_NN5ROrxPmou7xL4{iYHyjN2ajkU#iY0lEQ_r-S5WtTPZnE3Kl
zX!WSO#Cj$grYoM5D%7EW$*(!HVTz{}9K&f9K0DM`Bkr6U(vGZ5f>?v7&w7Yk?C+Yk
zK-#=h3i?)(sQDB{VlcR0T8?r1v6{IYMbzS<yNHNLK9!nf6xXLphCzlPinObR?NG?S
zH`2DFFL;(<T&^x0`twZym8q}S7aeg?Ai(vntETS+d6QO=XGtY5!k#nEYp=98l#ljn
zi?w2xv7W@&XJ*-9pW?3*H;39fu&lGvq#Y?6?{}vGUpmp)TDKqr&urFwKrQP7(>?0^
z9JyZPb*d78nv#akCaN|O2BMp875nE06)bUYjAN#1O-e76ILFJ)Ewd94UrzO0@0141
z9@JdWgDZ-bWhN7zqoqe5N>{iKh+(QiFvg=^7;{p%<PTbgFjJ9Bnir)tfvEymPE^sJ
z)Rz1bDGL1NfFvALr!8v6p#rCfjf}pu2*=MP3Wt@Pam`#Y{`;qXMMrSEB?lGNQl;#K
zT!)okr9mjfxW!8e`2{lI9qMZfj6i8qiD?wk(ZwJplN-6>kxxoj=M>OLsj$b6Y0+@h
zz(C@FK#*pDCOvURawuX8W{~uxkQDDAEh4^n_o<*&$GuF*k{mZmt`C<wftu^BTiU^2
zppvl^gJk4Yh2(O7DvIP{T;r`t8)Zdv++<fkaZsqp_Nz0DrfRYrin#0qk&Xxz8xk9(
zJ~NE<=}m48062HWDL4ncGMo>}X#pailv7E|QYqljPptq~xn0n(=jmQSt;8eL<>Lju
zY<`vOGI9?*VAqy-sx6wLxgAu3YwB_emTo5=EnYV{{?#Cig;po<sPlu;mvwzwJmJJt
zIKx!A<24g-)YylN55j@~??^I7wJE@+0(YeY-jGs`O#mp(2d_#8wG`6<q;uAsIn5_S
zMmg(1fQ%0OPzc9N(nvy&T10G*dQp0ea|{mjfYX@#w7_ZH2Z~T>w0l*EmNWAKQc5_e
zSMOBpeolMR5eOXjrx?oh6*ix>ZiadJO(pNkbB)~=gakbR=94sl@&;*7CpADOc&nOZ
z!a13LyfIX2YiSk<M2rdR(v+3Z66#5^@V4K+GsRQ~nz4IyE?Ec|!r;|x@lt@1c_Nkh
zriSL82`h?VL(tLIj+7CfN&t88QgrsE2Z}>L#OQr<Mm}misP9Mz(TsGYA9jr5fETSZ
zy*iqBsAClIQ4@yarAkIeOw=#I#Xt}1N-3kJX+brj5TM}F^&Yg|wEo=C07;}GjQh|*
zq{cM$rN%}*XgU7?>r&#74cJRycc|n>Q_e9~;UB&p)S7_9De5a4jHFQ_o}(h0pRGB1
zQ2-~6eq+uuF<bWMbR*N&un^$&=C-U`d?Wj{&xk4|wLdm0O#bci4*;5lMjL}u#u<qK
z9!4w9s*Mg;QeX7Uj-*v>q>oct`jwsJ*FWgia><XpLepUI*1vJgdUT+Fv@u)9U}mR>
zNimVv(zfJWk3sKQx>kX#>G5v7w=tp5UbUt{E6)|F79xm#^i|{jMNv_Q6?6{t2w@o<
zb*eY(m`~HSXm_fYe8#{J#<!uQ(G%F_fccF)4)l%0jI`i6#d~o$BuEYgIdht5=}NzQ
zCbmX0EyjLMv}1}RA14G*Mswb`F&Ny`B!FsiKMH|{53NLvA|rG)198nuoPISMjPY5T
zAt}S2)X~W6P6H$9NMqBlwN2|#r{hx|r=GQFmQ4Zquxi2Ls>AoQ-mMdnTBc(mu5dW2
zvURIX_iD7CtqdYZ*R4eSl6q8`BPOF^$6Cpnp@$ghNkAOZ1Cvr&EPlPJ$4_digo?5E
zR0_02i6TESs|-d4KPs;o%VW~4WaFnbsxV{{R0jgAKOIF^BNZ|<h@CprZTF52YEDmn
zDmUcTWsS~84Fd$wIioa&OC3%Ds_}L9s{*MK$>KPtwsLAH&&|@OZV!6V88W-`P!Y~*
zc`=__fsa0wGBk+NIH=fSq&+GoBi^$t260AlNDVG?iV!krx^q?u&wLuK5y{3X#y~xB
zS|d3UMtK9RNZ98X`qW9yNcBV&<mts%J!-=PwAFGj--RY<fO=C~0Op<By&*X7#X&-L
z=8TX(8d1rl0;CDz>r;{P)p-8;<JPQgAaH16KA6-kZmz^%XSni|AD<mfYQUyA6-mk4
z*15awX{~NNv;c)TW1f|_1;CmmagZ57#eAXf82X>uzS_~FIR_X_cCGzCc(qS6?_<3|
z=RqXfH=&Sr?^coUw1!u?)h(^=65dwY@_pQnwQ)9;$mvw)g4X6$c@bIH?wYf}Ob#dk
zlFtryF$Xl{RSE(QJ*$+|VZ8fuq+yu1KtIO1TP2Y#QDyts=7AOUEjV7P^MVaKPt&8a
zj|tSA)E9b{#l7-Ewyx;R7jUgT-zMq+tEk$|cWz^fc8QPi3VnsU+S>@8Mv#u}S=U;~
zj^$!Qmd~YYTg)biJ~2QUI_I7u{n%rkn?*N5wYj%Ol5NAx=!dmyOK}3oB6d*6pfxA}
zFC8cYJ5{*4x3g!pi_CvYH0drSvsb!Jl6P8`;{F(4YrZqbHDPed7;+DK0Ox#1bv!Zc
zk18?Npzzwx#pQDTQ+74cT-!l#swP0ePFFO6Ry5kU0)R3+L4R{&Vj9{LBbLV%Qo{D;
z_Ru}ldmX!0mF@HqVmB&FQlx0n?o4ew=9nB8iKd;d%qV+hSD>n%9b2-lBvvsFK5n_L
z`uj(;)I76s5N1R2<BZhM=@BA@R0szH6amEQ`jy6=v&n?Edg8imA{nl&R##oD$_^_<
zZ7mi;jEYMfWY)Swkfu5T*iZ*6ai(3}-k7%)MPNbpu9Dpayek+v+f?M%tXgJ?W(Cyk
z!0TB0#=6#UZ&YK>IG|>$Y1YzRHNvX-r=8VdwCj10d5fHS*Eiw4MrrPw%+Ji-52bBu
z7WdaS=$3N%XLd;k98v>OR4VOJz~hSGJ|=7HXJBm<=OYC{``vi{Roz)fBsS5BiDn$J
zuM_y4dM4IdBs~T)I%hP|Co$o>Lw~L=@=5|rW4R|k(!FvAfh}Z)Gy#=xE6@HP+6R(b
z**G6{djsoT<T0lCb{y^;)lKRLk@&5#s}{%JRy8k&r;QZG#E$v(=9%K<3#u^3D_FME
zvNlO0o}#pdu_c|{w~)sc^7uTQo|Vk%T8mvV37wT%d$y3{c_ZGdG^Iz@wTuX5OUcOv
z52svJF(_>NRm+ftMtas{iqXlQcAovHmVk|Dt`tC3xo@pkX@ET{s+^EOsTwjyanhQ1
z8EOlbf>7u)&2%wb31bCYHOj_D>?sDcEN+ZPXKdCrsoh+-NZT$+!0S=GkJ_FX6%0C4
zBq0>@Tt>uVLJohGUW!JQN2siql!L`S3${kbtpI39`6r%gAvjY^BXBtDRoz}T!vZM`
z)QV{2J6HjphNNqBameDb1F*qUQ%89sbvdL3m($gU(xU#(Vtwh$s9^G$%{b}=jwuWy
z)37-|g-!NUkFX}AO-BT07|%7Q1ooSh%2x#SG=@iLuD1&DXLqJ+wbLy(!VJv7u<hEj
zwD!{2hRS600<|AiwzV5WecmxiI|D?mrAD)~jc`^o*qUKWD{F{|k$3Oo>qx3~s3uL@
zK3|lI!;43Id(~%^+^c5|UX2QujgAViw61q5cPKwfF@sHsvl3^L6bgB$W~k7xZ<O>M
zD@j`-vTTSgx1K9e2vbtZCmE>~y=pXIM-=>b%}W9)xd-W7)~=kjbnG+Iur)}xGY-^-
zaCfIJ%ZkQt-OHa!=x<XJAA0AtDOT1OmHJZyobiR|nl*@$+3Wr_#4_cH^{qWh^v^R5
z+rG7&*=$t^i*LOsQR`0Ij?@L_fd~<Mnq7&E?&gA~nqwz4z;+k=)M0T^h>mIAS)d01
zx$8j-){|x_jM$_hS+=PnyA1-#7fkaCfX~fwv8k3+Kr&geiuEfS23;)#V+4-Al<jfe
z##<pDN<n~ltN#FEl@IR})j4C?ApqvNWSZRQgSaUKXE-$d$2h2QgHox$s4Q_LpXXTj
zptOW@#cTpIRIkx@hO3DZGDK_#tw$<t8^21@3Yf=#dZBZ)Hr>^snN;=ZOdt|^Q;8X*
z>OCj{0_X6jEPFsC)QK6u<F9&=)D8szK>ay25gGQWTO`zMaC6##Az_cDMBOS@UCo+}
z*9%PvkT+VM%6Eq0U3(g?PEYvL;y7{Wd({Z^%{A9hu*&e`s2;VCsM@r0vDimqO=f7i
zl$w3QxciNO-u2hqBpS`D$!`AuKX5&2Z)P)wzPAMfE=D?<%rW|k>26^t&l|5j2sMK`
z?2wLe>T75_naL1@0-U6S=|H2Yt0b9Tq(<iz0uDxMRpPA@$+68e9%;jsq+~s_R!H3D
zq(PDEO0g4Cq+thBRD?A~4k+7C;2H@PLI6Ho&_+%>8Ue_s9Akk@LvRHLicY_sA``e~
zfHL(HnW~LwYKj);iqFaKTy;Jpcx)YMMty0%^q})umO7j}3TQc{80}0$hczOOK>k$4
z<ond9Fxfl-R*;V4;jW7YrLIdY%H<;=SJU3T>U&g<$M-3_%Upmf#{3U%mU?#eyHs~M
zIImUF^*3v1#LOSCanlr3i&~pS5JeofQ-+Lf0kGhXYero|`zAF`g}tj%&KM*P@RZzs
z_pMXDw-Ua`h!8pxS#DVk;A_Z4$iTiiKGn`$D1^JWMI6^vZ6A~scmo|Pjq&87($%eD
zSMx3i3yS2%QFUNkB$3MLRw=A&lip0n%8j<ipVqn^Tg%gQsa;6iMi#4SnryZjaw5b@
z#&QK`YE5x{sKaK7BN5Am>?@-OQuO(I9Mx8#V`?L}4oA%Vnzb4ZK;%}4vAFWo3t2jK
z#YrBUaw9A)WY4BL*I@@2u1B`uuccy@;<~MCM%8XEH%DP19r8tGpAGAT@uta-_k~1|
z7<X}ku+5LUcIKaI!aJz_81=1dj|=N^Y4R&+(gMFQ`NdF=Nz|@veE6)SA|uW_5n0$r
zZEYJoN`CU1=QX6;ba=o#^IIBbuM1g5vl5QJqO!HCw7HvdkVmyu$}t=eYkNs=^iXro
zD+$JUt<58wPp1_iTe$#7pVqwJQ~v;u`2%De*QHE1K;zoEIrQ|F;Inr<>snLgcO>Q&
z9l9y{)Pl}wI*eC9wuv9z8KcYW2kBcn?UG_Hl*b#Kf$dhK)1pjgBvzVQO(#UhrfPWf
z*;|<i1KOd~lLIkrqaSnuK~zq)zaEttC*&-9RZUk(F#t*x?SWF*%61Zuw0ytCT{1R6
z<MFP3#>B@e0pHTPgt542{!~0vp_y01aZYLn4dsEF($s9GiXhCrc=}dz97n<S%>YLo
zgH4l@_*Chof%o~Xdkrn-i5N+=5uTNObW`3!e+ptS6HbW+a5L{yh*#KRw+@bsc-$M(
zqZ$)83qA<-6zmr=cCL8EE&;70qOyJI*CX1Ydj?OsLwzY&WfBI~9-_Gm^z!cAbH{4!
zn$^c@<aLO=yTUtq*ES`4r>~XD)3KU!NO`B@nrU8Z&pwEJEQvBSi@7t%6>k1ZRwL}_
z7mn3O7^NdVlqM@(+-ar3pbQ>qXe=;$WYNf{bfoJ*#L4YOO(><sG|XyIjP+uvr)P>_
z9Mh;NX`t@Zg!@&yEjHs&Vz6!8Jxv!@7ZxwF;XppeGzT)jFH)H}G-ov-jgQ@2(+D}~
zK~@-Zjw!ff+*F%>w7BA_O2<7)3QUYI<w^&=II@n0jlkpOVm&~j?UJcRBS811#%e(n
zjg7H6&!DMN%I(j~Z1njg`WG2O9ZR|hcbZtovsF9T%vVyO?A3P4$5Vxi#cacO8O=!A
z2BmQ>^B7$9+-px~Caq&1Z%Q+A<}oreK*!Rz<M5@^5xzj4{8Y=~J*P6?41c;P_7W7a
zv{%|W>~Ts63zLt=x<&BrpBeq-_#k%8Jv8kSKb5XfpZ2Pj8fG%gDD*l{3(6+bQ;+}|
z#dK;HXgj$2*E6AM@mwj2z`IA#oz>8%hi7H`$h?0O6H!+iOAqeUm5&yrJ*?cKJhW;)
z_!S#mz@K_#{OZDZVZr9&EaUs8ryd?qK6`>seWMk{EcXi^v`^KhW*hrl<ITzTqwSIZ
z017)+%4l|&`S-CM^NNsZHh}%t$GcZN_>T;>)U||>g7<85vIz<NDTd}^Gv$T)wKK++
zX3Etjw~|EU^lJ0TFRsZ0?G6XOdiAilwTP$B6DiW=c4wk}rSZ$gKOE2}aDUe?;I)IM
z%4D@hZ05C8f`Hbvs`I-tB^wqE!P;{%CZRK-&V0uDHA3U`rVeY?h8itg;+=N1Cl?W~
z@IT`8t#p{m#y=iv4WpW29Q#(Q4NTA5$e7>C1^|qIz-rZ-wajIhfPIE5G>>Y~(z$6D
zJ^EKRDwJVOxSP?a+^op%Ln$M3eszm+D~yfqG3aZ4@qT0NT>a9J#1GEAPG)x4&zj;z
z;7H>>^-5V>oR=i}=B&@fP>|-SFtJ|ki$vM)$*dWlb6{`>O5B~kR_C8e!I*r+=M~jK
zq9j7ipW-}w)JG&^JW{&_&ltygSRj__K(PkF{yxICY=Xv`GkppHkDIl6AV47L)N(76
z(zL|4xmRFJy)&BYWnh-)o}RRUqOIkeNoHkXhR<JW$h^F^Hr`AmGv^0yKq_n9O6o-N
zObqGhJJkkR#BN2l&N|eLVnhsV&D)yQ@bt<WL}meZde<i|sdWxxETnYlRqe&)+>9cd
zW=>liPzS6m*3NdV!WQ(+0y|_o%!&`GuQs>S=C_y3H*D?otCC&a78sbQ>547~eD^k_
zY%;0reJhCZPLW{2t}Wz6kaYvSP`bI9qhM|@dtlZ)@-bXI?0rQS0*M<>G?e!|oMxHU
zki)GU8Yssc(g87wLrQwlObrbhZzEHQ!h&<&y&gSP_!t2DSD0DOmiK8ZuH{qGy(dl7
z^xLQtU<I-FY1~YG)~735NI2=*yw>r&$>d}G?$znKtdWf}X7YmZ+Pu1E4CIdVHUwSi
z4_aD7nnMBBm!%*h6l78XX+<V@??5yFy(rBk1C#Zp0?-dM^ogGssRg5F?@$H3CS96@
zMcCt~72HQ89$4kGTs^!(Csxlx+O-!_3NeGlOBy<VGT09E8;fDURzCTzVCrq2X$Gf*
zQ_5A&oXc;(+HpX-fm`m^Fm+cs$6s1$)MUm96j)a}v#3Uch0QeTLAeSAa)(fSbu`m{
z{fVN%bFBW-!Os+bYZ1WP_*W(N*$C@RH;x<c9MNF8)xNIT!i*D9Hl-^N8S#qcn(>(O
z>}jU#{{VRNMS$u~qCw^9PN|RiY6WtCYvYzboi*-5e~l{+=Tvo&ITKW8SOnzBk?mZs
zoyKVULB|yA7dlqfxcMb<>zW3)fy<I>nDfmv%+y#8m9@4l*Xc+0%AfBOT+yAV^P3b{
zE_K$|e`-V2)8vc_$IxaiD<M6zn%tF7rDC*^B{qz8?OAv6ZJRmI6|7g9&%YVL;=8E7
zc!?P$a%qKeRtn{~sEFpftY$O}P!}}pWKx08r8@wdd87+ZAdYiM#(AQ^Fp4`<h|M4r
zSOmocbj>>)=8e55unZ!T7{y3O6x>p<36E+<UTMG@59><6HAP6Km?~IR448kr?MwiL
z#wmX4)rl?QNcW_<K8CC0(^`p$4rysY=7tqw9<q^&k2yJ_f!2!vnK-D3!_<UfsfPim
z82)ic2_~E=JLZ7~DZq0`I#T=9SO*+XC>SD?Qvq{F`QnVzy(xgu0HYq%r>`HKAtjGA
z2t)c*OgTQ4D`&2AQ9ex;0(4ahIHhBr-6<E86oll8RuBr256awBT|H^&#5NSsVUk6=
zaRaSL(XyPA%~u457&RlxO*;W2oy(E|#X`&q?H`>)Sf8Z>igpkllnyBRQQx4Vz#XW@
zGfq5?lmo>L0M$5ZusK?;2Q@eVuUu0=L`bCukdA1KWq>>ndQynZ?+vzYHUZwf2HPSq
zab9zwkeA>C#%t0n$T5$ld?s}sTI}^OuJJ4Z$f+^!NIsP&GNQaT&Y_s*l3*G>l_mf*
z#~D-2T`!0p#c)4#aZ#&fij&W!Sx^K-XYs7K<RbNlZ&O{=>GM*P>_c{B_X%+%Wnhq@
zJ;gCZ!T_@8jxu}I_<-;EQd|Jg*C#XBqJpo>QAjWbGgGfhicx{mw5Ih2V`@qJ)%>ce
zjlFSKbtODE<5}Z1^;lV6nmpRd(jKf5baQ|KuEx;dMT5!3acl|4t#!6CW;l;hJJ$|t
z8`HV28R~2tp1zdz&N!xZP-)AbTKPtI6UM9@Y(I@>-%I|UiobYcKaFWbNnus>IME~w
z23+x<!mcxoni(dbf=f(+&swDluuum%tqD*19zgq}jMaM+^0M{EH8A)@1T#iMd(?3Q
zf$LYC0*BYusm4EA7Qin?savf^!vIvR&{AMDd((;LkaNW-OrJqWV#IdI?M{EaO<p8k
zaZ)(R&w4;KRPYc1?ND+mXo%`?KD6SlBA!6K=K*ugGf+{zTOUevrx$~u+<VlQ<1r(E
z4QToR%X9m&id&WBW|G|D2OpI_=lxzq079pVAEs#+njB<QuqI~R2<R!9r$_TdDljl9
z0Vr-d(h>u&^QME(6frr?09b5s(vv^rP(auX6(a-lduE}QJ+h$P-;-7s?^IVSi4@iI
zUqB<fA1az4Ac|X+CLl*@Wx3!FN=slSlx0u!szZZU@suK{GW_kuTtIR+%}V3u?@^8z
zRE|Dx=S&2p&otc9X9J}GJsalsq<oqb;L@?;kP*l}Q|XHH-x=Gem0X-);}z&l$owme
z@svQ@=OcHmdzmcxaS0e=72wVR@EDpyO5ZTu{qAW!tL@R{G2g@1qI1nmr{$=m9+gZ&
zj+DK6(-i!)`al44){drvC<BUO6m&For2e$*Vwea;DygN#DvYolIiN%`iezWz#aX+z
z@{@jZRaYUaB`<igbI7Q>nw0RoR40b57>QMeJ5kp($j_}wj1yLvniLFs)q#^A;Z^%{
zR%1WA`U(UVvaC{WJ*l@c31=_Z)L6kHkn$)(3J!26?M@tuuo;h~E`8|l#RSj;7=uVD
z&B&x2eQE$zr}bWxz;Y?$?wVjmXr*dS)PQ&y2bxfum<np1F`84?G%=D*Zezw+A7N0C
zKPq`*e)eg&#Uua@F~u%8>}V9AW~c-s(wOI(mlVetAK_WZWVY+({Hqyb?NMID(YMUI
zezm>f+Y@;yMUhZ--QKn}&kfl}Xwu1W#e(nybTy2fn9;$Z&ILbhLWc*QamH%E`qr^`
z6GCH}J8?@&qde6B-n5``P9rp6@z$k`VeV;1IOdcL&=ZP4Np3SXD8I%>Ju2>*7FFH3
zD^#@-zH4#^JZHUg)OwVPIKihaCjfT*Drlgc@wOQoaqP54Kp^0sdepII3y|4d;-O6{
z<%cL!9<_4b(d|@+Z@dTftgA^hR7qA)T&-V)@OOH1R6@oNsm)w~dUqHV!!%jzejbJs
zWSE6{8P3|=^1e_)0rVAt;YroB<s|SIXs(aVUAPh_{q<Iu9PfyroY|bB<Gp#@h*0f4
zYt%K#VE)f=^8!kq0k1M_G31hS)Yg#`Dqx4nJ?irPz-pw50}8Vk{oXUhQ2^Kg`qg>B
z@<=^u)-rM4p`8Fm^{r|ANSSPN5-;zV=e+}peaPE8W|%Qv><$Tz2Z2t`TAIBn!x*hm
zi!8=D&T2zZL~&1JTcaj1sut^09x5kZbI(4NGARxI3W<i}QuGxQpL)#E4e8dMk?T#x
zJGCo}dUAQGG6h1tNam5a6kJ8PpXSG{T<z1+vf+Q9t!W3!uN>CUcScnZt}ximR+M3S
z{xxXjkJhV7IOn%&rb-|^F-&X&PaxAAR!r6;SqGXxG4&Ku4srbIOC&@1;;ks$G2W^t
z2iw-Hs2~76Dv=T;QHJkR<AKdqPrrdyKZg~fF=S6w+pSF}*A)pPG?_?2OnQEOsgiL}
z%R>R_(wDfV8eHV_)}*Tvp&`0+Ru-zM=BzFPj@4+EO%_S%Q#S4@6k-NyS8M>?%~~^L
zQu9zAJ5;XSa(SqYCR{}A#X{p9_^GqT1w{V<O#N#%S{X~4Ly`5QB#J{Oi-rcR162@^
z)ofw0&o!bmW8>k!3VRMIktrm8wIg)*t3(jV?rO6P6Plh+daTC>=~E)&IDSHydJ#$q
z0+Ekug2d`6!=R?*XB49Yy&xrz?+kUTK-EM%=B-9ol1BoQ5%dktj@KHnxnujDyM60+
zB-t22&{Ze8Z|#9;v>4TLTR)|0%O96&(kUNzJlD$H_l#kn#5Hg26_NMnJ3Dl(Sqqq7
zXWqvZi*0==)B@$18TRATj<wM=B|$x@4V+wemyus1?`^@b$?si+au$tA;E~N%`z5is
zX_XhvCzIZ+sOEqoOS^d{Xw`#Aokdv^g&gA*lOBa{7OMC0yY6nQo-<dch{+40oG}y$
zk}dVDlLQQ<x(;f{Wgv>;VzIexM={3SK6f{2>Vb8S)QSLxZ6+yhmQqjBw4;q<P@sNQ
z&e&>tl=t$a(5k|$S0}HvYfp60+q;f-iUcz2Nw&GWN!$HmbUCY~eoPAF;PDN>zEyM^
zOL4c7MRelnc5XZh2Fwf1D&pe!4#T5%#c$g}VTDlhimz|1SzX*1VwoC6>Y&xRE)poq
zvA`Y80x|Ebbs4od<&NYm3;Y7KSqnx~9&uU2#4tVglg`#VcXq8Uz>Mw$PzM32+234h
zWmU)-=qs$!V3OX&B9N9V#!XvhwwcE$&N~jYl3Yb@h24MywJ<TSH0@4JW;xP*w#qsR
z-jUeA+Xu`BYY2FfDXtbFwB+OObgMGzX$&Sw8)|yf22!>&OLEe`05&<R_nL?9e4WI6
zxF)h&SAy&}+20@@cGecJsx)|wI6F%dNM-v=2;;kwSl@FoB=@bA)1kSxVKzu%)6%%l
z58m9#co-A0htI`ydW5=+(TMcq%M<f9d0GMPYH3<*Hf%O>7l3`MM*C4q7`<5b6wNB$
z0Odd$ziVq4*6H_4kC@d>Url?d71B&cpO^#90v#r}jit{v(xp`Oub#Y1s2lxWX-t_=
z#klmZWAS^(rucSY8N*1PxUUbjh~MiGM;04%bw9;`ar~;HBdF3Pxw6wBjQ}qp+sE>*
z>d$qaiRVnD&5lp4J4*1(X5I#N`Osvq_l-y5JFl?Y7#L%Wao&`Hv&p<ua`!r$$e$`>
zob{|oSeM3X{--idSobHtrfV%6EA`GRYI-6Wd>ns`GDGtBrz?g|Mm;HkT1MI{dyqiL
zT=YL$5czAh#^8Nw@QY&f?N#JJL1D!WTnbW0wYNvg{{VKaSVk{hmBIM{-lM%l_(7g%
zx75DJGrUo#FV{WmKZK)J?&ic>{hbg;BJ?$k>@wJ^DdgX7?8N6j^-e`(c1IX1$JUy6
z16I>h{oj<wpL(CnEPCd!k+v`(R@JK{k*?poI_9~nQ?{tqG91bnR9;>inv}2y*i(a}
zdRH-_Br=vj8-^X~+%qJhqnDq0q@_1?rE%STXkclbC104|wN;kFc*yw)1HC1^{E;_Y
zVzw=HXePjz1wOs1Sj;AZP@i-k#*jw%#t6-I;?CCWW-}Qb$TZnBKt@+-9@Qf`F$-s<
zOB`U4mFBuH>=y@sO*wQ44o=>kC>f0czTgn!jAVALTWd)d_ma70J;|%-qRg1tA4<0d
zhjS|c&Lc`gCeyE82iYIqZnd#2Q$E+==9zC{VP>B(R(^qr=A`>_GlW$b>5*E|pDQz|
z9%Ns(;w*9s_BA0qRB<>eI3UyVGhHmfD;BJq6OO>vwh8sDC?9Oe*l*^y(m+6|7>l`T
zM3J*k8)<m<sTk#L!m@Qm!k#}G)=s9g^+d`s9qA0<H4(N$&rH`7;;C3#{G<x*budh=
z>0A$rq(g78zuh%R4?cVe8<W<W3H)j9Ib-YVO(v?ujX9%h;9{McGe8J8Q@&wHPqj6U
zO&}DuJJT9mawys;+A}~5G7~@<>rW^s#yijiwn@KGg?ang;=OlIY}zh<_A_2-;mcpN
z>L}-;H|t)N56c+9;<Sn-lH8`~8>UFEBJN29?bLJ7*KEfsew<e&szg?1Kc}T-U1)7V
z>tdSR$SMB-YGv)3tCR0i1M>d>O5$gFiY6M0h6R)gm|R72zb-2+;@UIV`c><A7AP6W
z=kHa)nN*5Mt$8Sm<plaxYY=*pYRt(b&G%1QV%kVR<MXYKQn-saH7s!RoOG#-5-v_L
zj@5D)3aH&e0=lNu$r!4#I3(kWw{;?>cAWZFa}viUfDxM?Q~Faexb&sljyb6kJdy8A
z1_Z!0R^;P7s{D(z4(6y`a@}~QgjEOLm0Jucq~eV6R3mN-JZo32uC6RweY=p}osZV2
zX}`RWn$}nqhC9?Tn#p}(tE#2WA)m26wSlc@vspQlK58C>3YqN+oyu4ocA`t0m$NWR
z`+yuVs)Mr>k%%KCU~x<2=8{J-z6d{!Fx)xEYUsK#CrCzqV~Vg56>5i_A;mj;kTOkL
zVl)-edN*1cRSWW(&*b$q^#pe&uHr0-n9v!IaZtzBq^c1v4%%?WI*LUccB4O?GD!yp
zl&=*M$VdMGUX;1^rU9NfKb0!-!lT{C(wv8Lch6x>2+!3<B^8@mdZ;2mJu5W&*Bx(&
z-Wv(tfz1@PnL>_~pkz`CaL#F<9=r;>r@{8C_#o%^kI&&$*97}lSKy5yb$wuYl6hh;
znQ%MRpi1oZy&uDxJXTS{<q)!C8?bR(mYPI*ZMhcm?~6GA^NP%h!X{rO#!B=j(zdL2
zLcUlSTwr=sN^*KObSPMw(&Z5E`;ud?tzK)hAnK%646L!SJ!?AaP<WX6PmX%i<S}wO
zp>oUf@B;H(OfyO1KNQJ&;}BXBhzCM_YPPfEC$`e0idG(EpDHl-t?vuNXAXvsZzyGx
z=iGSb-leMtF{LD;7#>#I6&IY=H-s1Mnw{RF=n6{PQ;x!$;=M*VbpHUd!rP{t?7%e)
zdeyInbTm!i%Bj#E^t4+E>UEmtyJMo-7rAuYIw-Fq)&4MfS1%o`CDeEIt|!HwE4kOM
zpAs;SJ#*H%Vsp-DxE`l%@s?$oO!j1_d}6%^!@fDvJVJpYnNnl?3~+1ap0zE#%=UAv
z_VToHDad6w#Ua@G$RXXd@~!Jw-WOPHZuN~hz$~&E7eC!<;=Bv-AMMbK4NZW!A9cUI
zRy<X#T<F)ys@Y-MRr1|OaoVXeS}-*wFzT0({n6%@A4<<+dFHXst#f;*OxFaglAM5g
z)~rPA=ab&2s3)a_ah_{;NFTW47_36PdRE?zmO`X~ftsK%%A~|V>+4wWr^xaXxB**i
zK3c4JJ;A1lGuKT(MsuI7PPV9=1Q@Ga=hm&;**wY#$R40phz#Ym+yF((8rQSX*@o+r
zu}^Bh98g(BxP>KsYYzVa#xO@Tv2AuLcHsp*g=2Unou3h>IO+#Afvz&nco-e4GEW#}
zVk>6)nx!_sJ?1>f!hSU_L$M{fDJpu3>#d~Q60;uN>x65b`@br<`nwB#sQ&;sADt_X
z$6I|UlGkehSKhG5v)i$XgWomE%dTIuFfstR>(;0}<FPFAxy>$N*z}7%PTC071;T~)
z=CsoG7d%|ABQ@la%1O$*amGze{h>X%%FO(B%^bmF)*S9aR^@m0=DB<O{bB}q<5YC@
z9cz*vAi4f24M;pmDC0bzS~-PcdyRWkS1U8RzIf|W*?6Av1SujJKiUWUY8bV9d)M-(
zRRI40cfCtKjHW*})?BIRy=iVTXYn=Una0!yu@w#UGThsJszw>cO=4ZaEDpicj8&U>
z?wZp)w0$rdv8t~VzX2{<m$?wl1o!JwEv)W%iT?m9nKY~S<!ze>yAUgnl3kCWRjIAn
zRDQI$tt8Md+<eih{{X<NO4mS+Bf4}9{{ZbjN@|pemNJxjoY!75e;QITU3B_go4`@#
ziZ5|gKe6<r{{UNjTQvQXGg*xzpU)JbtDrW%9fV<~4t?7ulkI*Rhag*med+raCz(^|
zj1@bw7bK3rQ_38D$v^LdTlN~hmo3MWZEO&V=%BY(VYOob^PRPwUP?;xWPfP$d@(pk
z?5<=PNF*!jR~0;ZRs6ql+5Z3@E7YuXn56(bt`GY>R>$@gnCs>o_YI2kr<!45y9bM_
z(kGBxXu7;o86r<Dv5p$7%c1Ib3>s-uIP09(s()bEWS=REdb4J{tH&^2X_}@j-O?_@
zwrcR1l?+7rB6HQm*7%9-^cR2=J<LH*T+%j!W@Ikc$&X6o9`5{}Ze-0mC@<U@H%TH9
z$lcz(S7o`&^}4s*?QQ%wr(EqZywe8%0G?`1Z(8^w8P{^yxL;OmX0(1BD;*dKBLV(m
z+4|RNqXPqlubal_a-&t#gmyPlt2K8c%=Jwk%RoT$S!I1iW1W9Wh@F;X?e!ejbL0DQ
zHkLaKaz%LDjh4wLn)=L*#~VZ1Pjk-2Rh>Cn=R*E2ff)H#p+{`3F!;J>QdT8gdsi&q
zdzx|+>-bmD#|24rIG!SJsktYLZ`iinD)z@(hEEV*I{yHzV108~{EB$xJJyQ}NpvCB
zlP<omc_VW?m>=zTs2=|4^3%wF8m?&@rC+gv=ufnfD4E>h-O2jXa@oNo(-7f@LrTXF
zo=32!$c4<$Pxx0kB3pI`<;Uxq^x^lb$Nm`4w_2Gojldf9_3QpM`9Bv^<i=mQ?cn8l
zWTKI&M<X<hFe~Jav8r)M*q~5(6u`joj6QCL>~Zq?*Odf}5#|DYtJu6l7?VVppWy_W
z^3Uvhlg57&UwOmx=EK<F#Qa8vmne7&rwS`#9%I3*Z93KM2}e05we5jyfJYsx)up9Y
zbI;)(<LOKw=A|ox%`VSs`Wh0vPco|1gbG4Asqu#BX$tXMn3c{=S<=|8+k^K=s7ULI
zb))%LYR94A*ES(un@02<q>I;!$sOyTyBKQdFWnHf;sD1}T!yWz+QlZtV8@{uubxq7
zrc$_UXV*26cX=Ft#m`zzLgnsbEdz{W<^zLV`B@!;;feRH<3e3T<XWEnn>%n99Zgn_
z8Lmd;2Or*Xfm$|p5UUAp7tCzrDd;Ow;&hrJAC>?fmAZn7o$h8^Y1&*VzV>rBJu`qR
z%j=p&s3`<H{e@P!hSDY6@u@!b98%k^c0_~lrXt7o$J#z<U})3S(<Rm~&J#P6(xi-|
zbpbQ@RCB5-{pAO*6aj8ca7AiAc1t!t3e33i9P+CwLI6B-Ri=E56I5h>n}bMWWR^)^
zb1&gfww>+YH5TuBLUBk92Gw8tqdwJL@8_4$3Zlm+j+Aabv;iZtu>`rO&t6)SG-rwc
zN?Iu>7*Z2Unm9CoN+=@+l7JnLtw{{hTgoJfu)?G5?L`1@j}cFCZ{$onb<JcvC7X_F
z9%}8b;~g;-O}w6zo<sUpk&peVLl^_CFf+V|qsU|b0P3sTSJyPF7-}ptKgnPze3q>*
zAXA09QUfo@H06f0Oe(+qdQT*0u4n?P{GIVn4B78i)-(gBH1L2C#Q;()$JUo?k(^cR
z3~&WBu6?Kim{+AS$a)I47YjxJALBsE%LJ{!12tvs3@SH1<~_YB1fdVgd8p*Lcattj
z8S6|!Ix-BfsP>bdMLK(hbB@(teh*v<Ku@sx(@JBE)P89l=?uN|nm|7s@k}e4X_QlZ
z(MV&+0-A6szHVv0XA}V@D8@Qeeq|?_KoZhq4)q@MnoZq}FeN<DDm~nHqjBv(jlU1N
z{{U!#&)w-=RD<O_R}rI1S5%9d?$69Jd)F-0stn7Keq&W{Vg?U!S`w%Xar)FVplA;j
z+e>mJbBv@Kjm8_3RwNr+pUR+Plf`;S$ZZ2Tr2x^2s{rO&Kn5vs+LUm-3M>R=NEBn%
zoy92p=&%jN80MX}jAz=NfNnVBG}@CKa4CdTuoX@z?G{&XrVh0>{4U<LAXfsE4%8?E
zwLI;>1FZ-I>DM@<$@HZnfGW_1>TqerX`h8IPBFz$0Td1fXfy$nK!iPWOmWRh!w0P~
zg5r}HD8Qs6nsW5wf-q@_PvfP?qym?vFdQjOG#n1JA5Ln3co{V#E-{*oTak*Dj(Q3}
zGZ>`fG;=}V)d1!L8O=iD12rpj6p|6J06CzLQIs^&Fe%X-ttnjQfsy8(ze;EwX+Y$P
zL2=*3#wh1FqXZguDS;6f=9~zi;QG_n7Gb+QQvxjG>p|;E%Z5JGn4m(QoKlKa<w(T~
zjL<QpeA%aijw!58<I<k0jJ~Fl0ygVFG_1Hd>qrGQ29B2}mvtG(Ij>IBn{+AMV!W;i
z79xa_K42@;v`61+ho=~?kKzh`@{#D^-j+47QUS#`2OQJKPipyQcL|KsSvMi4fkD6=
z@kAulu7Q=1g;E&sD=@kn;t+Ayn$fvrDt4aTs~*M)8sxUt9M`W$l~9zP<}&z^u^Go&
zS@Gqc%7t8UP~2ynSDSmA5H0|w$}&1r(;#vwvVCgdxQwkuLAP(EWGUwcw=V!_NX=o4
z2Ct{UO7zYQLidNb!h_V;Nu<fX*)h=ZT<!sn>suNmhsi1Z+|tY=%}J9%+GkXwF)lk&
zsis?<_RGykg1$0GrcDt$*V>t>46H<+{Y^;``IOUjRn4Fyw@Q@t0FRqiQgfWuTVsg`
zJ#$tgBgi8?s+=bmP0nhT!Zfz-4OJJ1Z$VcSWOwGPFvFTx0UMF;QUSU#Od}$vhXOi7
zu@b3KPY0Y*lSmKJhQMp^MNHiVLi|+u%wYGSfP$0~4+B3+Me0ADN`nnf6Xeti7cu7X
zcW0WO@dw%00-1g>GPkLzry=b}(vD`@xQJ|`5~nS+nv&)%k&)NwRqSO8CfwEAoS2XD
ztyPxbX6Nvw>(ta^j=!xNvM6W?;UuX5eiWRJ2&Tf{F;PnSQ_VmQr9CrE28`#e09lWi
z@Ms*=cI}lQ=AI9|OBo{5E`ivloWELa(f!x8CAbktOI!Z{DuNTV`qY5p4Wo`Kv~RTg
z)|Su>A<EW#z=PheM%iA*s9ZKB$Gtd!#y9}xrD6!qc&HfEs(*J^U<~7mZgcBKaY>$O
zSO)|1`&5UMQ0AuN0McMF_~yCa62OvLZ`+o^u7#U5k*&w(Sid`a*P)lx<gFHGQC=+a
zcT%K`W7?wpYTeX(ZX9;1xW~PIffsdi$dIad#Wq7zM60`+j&;KyO0r0mszHj0Mh!>~
za5<y`o+$jObLmJ&tuX-P)B92Z$4XI50~k1^PnE%>$I`4>MkTvdVM<QQ;1`S<HQ;}R
zW)eXav8|#-A}V9oBC(0d?_BG0i$LXS7U8ORvdhIqIx;^svycs6&Zh(ws^H+%@r}Z&
zEKG6fQ$je}4Ms*W+N6Zwfs<EqM#;ld0OF;Qes1*{<E=Y@nCFUB1di0W&!tHmY~2SG
z#6o_QV+YoyDs$ef+gX{TXC=5D1r32gl=b7SHB{A!6sh@_Y4kM+89h0rae&DDDd-6&
zwKNXZYTW}9O5$Zk1U5Jx)X~LQx(X!ubBcsgxW!srbj1ogRDn;_Vwe%)j8%x>X<Q=x
z<5S$}lUl~E><K-Aspdl{1<fwpRDlR=4!-o@g}QU}8K=yEhaZJ0UsG2jvYtf+V0Iq3
zsn<!nlm1wgAMI9hsFDj1X{_OyQbtZXgM(U)ZT5&rc_eIf4B4pcw0nzrx4WY8&{m{&
z`xK}>YZ+CENgN|DmvG4A?zSs&EJU{1U7+KN(tixu$tjjqa>t*(de)2<s|0>jYO0;P
z)?U`nL7ZuiVIZjo=~At<uD>iUbLcCtOJTectM$cBu_~S_{<6hmi(NAAM!<{nsaHe1
zZmOVtYq1Ep{zjTY;~hSgFA*Ww<=4Zrw+3Wf`&EVT>LUK~<<393TkJp;6XbD@wGOnx
z#&jA~F$0H_4c4R@Ww3AcO2^cSx}ytCECDz*n{Ab16|#YU<&tsjQh7)hXj}u=0-PT_
zQRW55N<dbTFx*uui2hTK53OiBCsuGPChF-J1r9!LgVvEr5vT#U1JbR-%M9`=lx_p<
zC#_tFje{M#R#GVJGznxxC?#S5>FHbHTkkWI^fk=rb0K|!z0c)cFa-Wo&=v1SZQqO^
z=UkkhE3ovg!gXO81bg#bl<3PV{G?>`HE|S*k{_C_MA?iQuHcTfG#sZ+D##@V6%^+R
z#Qv2b&ovv3+#0w&Ns-Q8BYmKrY7X^s{YaM?HB<w@uX2;TQNcaO4n1jegFqC7*678S
zV&<Gj&79L9_o*AxHL5aW3H)j|>xz($d8RSv+M6097(8-nCmzD4>HZZHj%zk(hK{tL
zQ$fk60qIguqpx~d1_w$(?rH8mT=k>`Y4?XtD*SF)b6KjtHC>E?7t_|Rn<AnujN`3A
zA;`~ql{#aw?@W+j6N=cz#bfj}8v&k!H6b+<HU~=0vsjVmADtmQ(q}va-inKwSdk8D
z(jK1GRYx6a%KgwPlO>NpH&o~D`&D&6FslPQd95PMWw{F+=cPdB2BdcDP!|MJWh6Lq
zX|nOwkUn|cifoPVP|HYXH0<~9QJPJ|9sQ|XyA~6u%~(=M6<Rjj!?CM7d-N1@65>jS
z6*<PiRpUoy`9|-?tT-Wd<EL7_WM<;ZvN6p=&T2^(LP=D1Ip_s6L2&#mG86QvbB}VA
zSY+d^LnlvKvbHzuK3iFM_N6*bq{9nqC*xVVknU)r${94Hp7nWrKdQO^0FPq7?;4#v
zF{;1(vW<V>RUY08seaB(&x--N)v?nZ{c8Lk7t}xHtH!?g&0Sv&&78E$^b1GUsjj5D
zGkpwHBsEOH?H-l3o*Ezw&w>wNYEj|9!woxQ9YsH`(p^b-d7Ql5cdCwguFL)rOH!d)
zX?@P)%`|vZPtQJS`njy7j;75chmpqa8TO=U6rQ!&j|=H&I7j~gzKuM1e@#LE03Q3k
zt(wi_pi;xg;slG&%neAgsa)<;-y*w_q*#H0Zyq{|df3^HkRs>NDqcQ4iu$`acuxNS
zyWaz+dcLr_DfxPHk6P=zhzH$?K=u^yi^vMUOm?aM(DEPE{LPVnsa`Oh=P3CjiqL}Z
zS9pw4-WE?nD;Cmx{Y7hAP5ZxG*U7rFKBL(~u=`cjZD)>1?t`)%;rshnMHi0@R_d4b
zGe*Q<xEqCMK_U<{ntPbaka^FoQp8Ca%8Xe36U5dMYLgi+hnD>n_^z(%_Sjjpkxqw>
zF<xJ*XtuY3ys@$Uan380ySCKqWGe;izE@=2O=}!Y%$^xD+H}oR%(?QNvKaA`Thc&P
zcXb_W=KC)ZYdUPgQ7bkMcDGvVEq*TFEIwV;qk3c-+uKCWczJX^YTDupr;tS9oemgO
zk{>M#HUO_4(tak|X}7XGsNhQ3V#lR)7he_hTgygB*oQn|iltU8&QxTM-rnjvwrzuz
zH8aFzjgYQGaBI(WPZq@Y3oLO+Q+FXncSpo}e9?uCh<08+Tw<@88Ok<fR{AU!^R(Z2
z+o3&&rCu?Dgde+EdQPh>momk6$P+n?j<~HILg59j<YD+zxU5jN(XA}5UgF(;cJ572
zeH@ool178(BZ{r2-)@<ra!&7F)va>rYi{!%LX7c19LAgB?X!880Dv%dk6Pc7+{+V2
zvJ}Y1M`~`Js6(niWQ!|~s>1|QYO+18w&W#q+)yJUPw@NLUA)b3(z|!XSk<g1y0dkR
zWq`;YwPQ!SH;7|){oosc^%ZMSpZh-C%_6o3r7%3+-oob6>E)6U8iVyFuiro0teOTp
zGPvftn5VbZ?fl5lZ8=gvu1CaHEoCq6<SQSbpnBY|qiLyTFr1V3iSJs|X%XM1*HAN&
zp7l?|_qOcG9P)y=`AGh?t>QgG3q3fSd4O@;b)!Mq+=4AVEMXDCoq5Qr7ak$F(k1~Q
zFSzqh(tKT}%WsRDh{U|~Zq?5CtHpX+I~8<b-3p$jmog4UdQO>hHm7U$f=CVgBehf2
zwW&0VxT9#pBlj)e(!842;=}1tyir8YpSlN1$<#c5d9Tbvf~lOQdaW*X&^au3KN7WQ
zXVT#jNTI>b&bi{e+eXx5vDBlT<NL#D#~garW%i{#!Bm!3V5g@~&Y58On>g#hQY%X}
z5)Vw5$J56;Gzdb2#(Gvqi9AyJx-QjaW*>VMg|&hW!?#L-qGxZA6YW<@o3-RAGKA_w
zF~egy>siYG0KMm@rEA>6{##^WvC^>S`DDP!t(vh0j`wT?<kpR{gid+KdZT2yjb!Vd
zD#?1JBE#T=&sw23%1G@~nGYQIs`7?zII0l?5J#<5Vb4s}mm6?1oYXEc+v`%sheq33
zN*rMHt8+#!A@h?v$KDm4yX#jir}C!<_*<=J^eC&GeJV(0DJL8Q-le>Q$$v3UV{@OS
zRb%N@x($sI?&Bb_rtTxwqp`YFkgSWxu4_}viebPx_UT+zA<E5TB8Qsep{q9c9EE;!
z)C!UG<^wCY^Qiv9>T{9}VrWd@B)=~!+N2DuKJPUWt8D=1G~hVRASQz5YjcEh7p-gA
z>obNbT%E(ItV{-8X|c%BH&Kc#2WJ+oF;TZ^sYbPOons$`VCnbD*bUFUZ$;(EnBe^>
zG*BIW>!3l;Oi<db^q>roJq=Cvanxgqo;U{$w~pqd3h0weLrCrF05z`)>{M+0!;@72
z2uEyot2WXpa;Nd6Gj<6Cw(9=fDomW5)f+q`JY9Lnt3du0(@s}L5>_We^AE0TVir3F
zc+Fx1>sr>$x)6HtS`b?j<GnadgUv(RjMC)ir6HH1e4JHl;0#TVLrDu^hpjsIn2kuz
z3t0Jg<F<NNkNBcylJj9FjGFc>Xar|$`u<hoz9Mk?gKg>8HBkc)_3uU~G*uEEdeUb!
zrvy>>Py$i39<*~!A&H;|5C?i;U^~(j=8&MI0vQH4rWQCf@VuHrpa4d5Kpp=8glznq
z66G*k2j04s999>Gw;eq>=ZuQz6>(cFiDORye=6s-$hOJ98QuC<Mn+Fc&DG#CTA%L@
z)fE-uT_<TAg8&J|IY{e{O)HFNBau-D!S?j8Ii8$J3g?{CO)I2hgS1nFWMpHC*tWKY
zcmnSmxXydkQ{2kF#sXbzJrA!+1>3(0y=$O-5-`~=G3qKM)8R(@=rDTbw>b>R(noKY
zU{YPp<)#M(dE%|!-CJ5N#9&(=cvm}ddFC^7&(?q>bCOSP)WXrJ#&hdckjXOQFvpKd
zxelEpefBu+4FE=?%sgiv)nF)wJhnLXsTf5H0-RMDWHL5SPpvTxl2YyMRIVH6>DH}d
z2B}=1-XBV6L^;haX))559MuTa(wLu@(APx@laE^E^tn8{j1$4)y4Yc6z)b!%45V9z
z1%AD0WYWCDz~I%}OAUZLkF?d9^&3bFBRZUQ1GOQX2CZP$cT5VNPhPb|FML;1u3W=?
zAMSa_d{-_;JM&#IdKj=AQ-K(!espIwq9k41ntHJn4m(qq8LB`|2`%YTj+v;GRDh3K
zv_l*TqXg2a;+%Li#4s9n@bjF|M?Qj`kXIs@h`{EgQ^!t~7Cvf~0X%g2Q$SSJ)PC&x
zipV`HZ&Hu<3y^Xv6plSBnzHweY3v|0pyrZ+#bQ|R)|@)iY04>qBH$@z>5BCq0O=Ag
zly4m!T1LwKJ6D<8L+9MX3Z13gE=7Gep=q(NhN6l!<}?@s=}o;0hW99?rNmK&jFX>V
zTF@&ra3jcf9{3d2xmY6!Ayw=Fr>3uOC9#VDw>UZGr6XxQ4Eu?W(tSN^4&q;&mhD<M
zvhscT#bRB_gl?Sl&2DlWX1goi>jK-Xar0ZY7n0jVA@f|r{mkOAVYFtyp5|_)@)oT~
z`y(f(6)a_~UjA#A7d9waEx2)>SKhd-b5^;#A3W?sb;lf6bK!eMy@K-DoG02dwfzlO
zy7)tRG^OLz)1Jj@Ic^D_Sb3&my(#_=YUA$SM1SBF7yK#T5g)rPx%_EzG4mtNuz$&=
z#d<gVDbEs-_pSc`KmN5U{21{oAH8q?0DXV;sN`YJk2{J<AeknKipYl`iu9XJNp)=+
z-r{gsp*ibHzXbe9Pt7&B9-yD_tvg?Z-XXKKYiQ?yq4mu*1}8L8yInr|-+j4{&c;_G
zrB;hiylC<*$?fuyTM&F5*GS#=m_r|}be10rHM?{LwPaI{$xoC?oCJ_b8N`vgA8}eb
zI4Vd7t$JKP548e{lWNg8@0bNyUxs#w!T#SOzwr<UG_1Rh=LG6}vs~_{s~Z-}V0~-S
zb?*xQ0Aj|wE@YWlWMxMc<6bX)x2U<}Cz?P@{{RVuxXO=iR<Fb2%fO?1;c;AbtR`7A
zgMnJfX)LR}M%z1aO$^wR#4}DwdGZM9RGN6EVt0JUsjBH@NgKleeQB4BkSSIF03v`Y
zT;1keMfXR1(nBn-^AnX7NmR)u2U^ip+Mof_q%1g2;AAiBOXkSkuzFGeeJLe#8fR%F
z^a6pE?j_sDbK0u|mK|_SGDmk}%@l(@_L{Y6Z1Xaa9Gv>DC<~TjDv;&9DwNU|bKC1z
z?rkq)jdN)zTB6Y~Bo!y<DS-(YqaM`qy?XIR4tvr84o9_Hwbkw|2Eygz^gXJiqvg)h
zDv>!IaYzonEmG4^U5~dXf(=@Mq_KqgAy{?BGh8}+t(EIq_8PO=fRd0?>q+WT(Abm2
zS4!B}x%L#WYWkJ!!p9ciJD$R=M{8-R#Ipq)j;D$q6}DZL)U1l<X0O^~v4vjdK+m@)
zCb=z7Sekj6p>hD|D#X@THvpHJxvG-bq-u9QO*;#jnNNFi#etqqdf?Q4V{?~t^=ey)
zS{ESlGt^W=-j#=O`Q&<z^q9|6pRFfqN<njD!)d!#$?LYgKGcQT*8;q&M993|xQ;l*
zdM2NA#x=`i_sx0vj5(<tIB8l(Z>G37`c~SUuc)qTOPz6w=wl?PuZ6@xsUDMLgRObb
z#CTWDM`6hzX1x>|<2-#5ya>*@Is7_ix-yw^;-X<&;b)ag4?QYt8K<@-Qw#~t7*z76
zO)@0eI-DN0_tJu#EYB~R%<TL#<0R8uLw9en82rq&>6TZv+JpjIX%*GE$ZXe@S?M3z
zQ87gulzhUUVW?dAcI{=0c#JpiBRxL~`E17lPNd%_#CjBF+;uyz7sRt@t_e87>0Ti?
zWsrg}a(MKwYrfSjb*~RRmh2AXZaa$cd!T;PFJJYBzLSKM>C%-sbU1PS8Ae0Ttu=WD
zpD*6_rYNtrN0=GQd(?^dYBScKA4*~xcw<2yEh})|^qJ$<h67iEJJgH^aZz`v3F4C(
z)%XH-hs1FX0=9P&eXHC$F!aTI{oz@5c#6b~gSem2*S|)<pgzLCHRDQuy^N1%0R6^^
z$4XQ8b4^fBKuM`K;1bLcM|R@A78Ip9S}5+h4@T`nRcUn#ICGh|u<VtcapD&v7S{Mb
z?TYm1WcZrDX2eRY7VOZ}(Vt6@5ymUe&HORtSe^axTH21Sc`7hwU<l_8{VR=}m6M#3
zeQWG;yuMgUe6nW+da;|((vwg}lwnSN>h+WFdgeE6aC2L_T)A)uCl%>(T3p60=xq`=
z)QC8y1o_7mIpAj%=}?kUIO;@&m%T>Zb*Y#VeJPBgl=IDNEJR{w8ZDJs!t!y0RHwW0
zpK$9*dpM2HQhfzs-pz5ezQ$49n&hcoQrPH)E>ZfXt3ArFc|C?Y3gk5lkR0zl4teid
z6Wr}qk;&RK-npBrlQe{!;B>B48yno2E}Td<Zq0NM#4aLNWci4!Ju27Ekj%jC9R+j<
zLaKpU$3j?!10H(Q7%GCyeo@w?X>z$FW7e_tTh2VF{`Y)P#8cER{Q0mx>hLN{6$M$_
zpzdm%5WU69#DkN`C$Oy}50*?ycoicgjZ#L-jHvae`Ej8eR8k_Uum1pAl34@^xaa+v
z24~+gAt*Z5c;x!jvpJGRe_C`gAH7Q8G$twu8$AtLnC%^En;f1g0MkGey{PLz35r@V
z#UY>tq@y%v2c-Z9wI*_C$G$0hQW%+~#T`d_KMG&~cBz)#o38?!2>Je%Y)BMS5X83w
zuQfWT6&arthH^Sla4h!gO(b;1Rx>g0NM&q_0JbqpxB*o6lir$Hz33UBB~Upu(K_a-
zb?-@>(gN|BGe_DGa%z@oxikTI-KeIUzTj0rGfR(Z0I~L`J%u5;erf<RX+Rn2Ko2)h
z>rFE|4oTvhjG98Y^`Hgb$Gt{a`kHn>8ca|FNj~(MIHw++DKX6eCP?SK8OWu<=7OiS
zAq>qF;F;}9<(dFz9`p_={#VkJMrat$^kfQnkBV?iiU5l=rli;@LJvv+hl&97sf1@V
zqCaW?b&Q59*q9DOS9=Vb;Y00QBtVIfjy9gP+E_7rW$T*fs=e!g=|)<ajmq41=~7Av
zW14JyaqC?)*(~R-Q*4Z<J!+e#-|(%gq*HMGbnjXB3&$e8SnOg`#s_gmDc{42ZYscV
z7#(N_B9|1M`_Kb<29yqINam0X8g>hgso{jb@RB>!0<6G}>BEIumIN#Tf0me2lTQQb
z%{90+AUAFWAslf*Y@RbmClstPwB-BaBZ1a|>p=&K0I_i}l!a9Q0gA1RQ_nytp=!{C
zr2zU-j8l}=0Ma|=oCh6E9VsZVhsc{$b5SznW}hL-jC82mJ81x@IHh5OO^vYF^{2Yz
zieNW`)|84*=T;#Rlso?bIsk*O(u2=hRv0)2o7${H!Nxn&!wQXk>B5)~$2}=Z{uH3+
z)`Q6FK!)rlJ>RWD!-}wZOjA6pscplK)BwnramO_zfPiVS5*zWUoyOvN=71~oT2Y+P
zI@0vTAQX%PKyO+PBRS@q`O^W%lZ@2SG0rLvUTSDbEs6k+L5U9(+Ll!)%nw?NtuPcE
zQ+j98o(6IJsR-tP8MmIbBAik+3BjZ>?l`7_nvsDcr%H@<rXp4J{&ndd8JBgM@(3L(
z%@-#luhP5E2gpn%N$J|YXNVzsS37Wz-a8Np9V$io(hs{%0Qy(OHhN=CF~BHu(-kW%
zAsOpLCCe+YGlGCm8TP9&#kB$3jMH8`Hb)gFJ8NpSF7y?M&NEcyzP1vyZtAW&3cOe5
zroFr*?r8FAV<psO9r-*{9D~}N*bYGLQ8RVzTEs<Zhwk6$SVl6eeQSDCpUSaj{{UKh
z*U)9M_iS<E5ak$J(b8LMk&mTjhREsCtZA-A*!j3T5nZ^L-kUI{?IX0ZAi#0WOgj5j
zOBcu>W~}3!SH#s;lRZVTG-vmVo|&r`i@MFnwO5UB)oy>9(ZT2zu-S~yfxmP5)gt>Y
zeQM3KWEJ|=TaZMBg=qzFHezh5)H5g&9=J67R}B}ird$)hr(X1|14;RKr^0e79Pla8
zADysGD*+)mqz4|fgmP#c(g9dyYFN%;@A%Y5o+?OkK?j`B0*((gEN7l-Fn(_T0F6kM
z6W9vciN?Y^(}Neb!KBo%A>2m-p@vQHp7o+$>H@v7Rl3>-IjxD8b-TB<VuQBfSa3n<
zTS#}?bk0R+w-Jh44#4*9NB|WCt+wg&!Ou#NHCsSfgyLG3UbRj(#KWE{<b*H>HJd<3
z-j^p7W|MKpN)Qi$&hj~_!NXNpjwQuUAvxo{CWcOjBhsS0;t`DImJ&@R&^|~w=}Ie5
zD#Y2gRd4Q$)pBtB)8jb>O)^Ent&$Ob2L&^bJ?e$zzc|Mraro7XQVL+zd*G_T<Gnb=
z42T@BJ-DgkB(EF_s0~RI6OrDk!nrR|_4S~0%^=C?&M8U4idGAXNIX=Ea=GhK5zl&Z
z9x!Qg+yxv}EkJIxla8SAR<~ugj`d#Te(AoI(Lr)e3F?n4)K_KXgB=?cpO0GH*CQ!<
zeq07QtVS4PUwuMXf@hCCBnYIp9cl8xFhb0PFR!IO+X*VRJM^s?UF3@ebL(33G7JEu
zH#Hy_&w7?vz?AbzvmNQF0Krb@6(Nsm{b&iAtAQ6jl;KhY#&g!5k$`z0g$anRYVMWA
z(LGAkES!!FU(#*KZQyt2l}US`Q`Wv~p8Qs3&`oRVqZd4nrDqi5p{$W)kPZMHYFo&k
z%MRUryHhRDh7H?2>qb}%)})_G8xevk!~&Ypgg7O0^{FCUxC0qJ^y51NB@5}zJ`;%s
zMOuc?yj#uy=~2fR&PO=oIjwoqB(V$u*!y;(D@f+J+H#_&jBQ`9dX1OoIQ+#&H<(zh
zb!@QA%7-9RBVwayTG5M6lI08JW2Y@qn;DUcg>OPYt5pzKqRMmF3ed5cBZ0$kNWi5U
zWz5{9Pxy+nZ=z3)&%pF1l&Z(La+wzcd*t;sOsU*GYo|H`yB25T&>R{U!_WhlcgJ45
z)VlE>Da|78{{ZV&g_J4geBk1`2=tpsh{6+(TDF#uCkqT<`h~3CAURG__RZQ>@?&${
zVymW|blCp@MvxCvUB8x~{Hg^ZM#oc8^@dj|%0;2xFbq{d&weW6=n`WL!ncp7N<gf7
zW|!6^7BVByVPC&Afc7Bc6>)U9TZfRa>6Rqbzc1=dJV(uD>Pdx)gHE)M8)1y&`@*JJ
zqd+i-K8sU`{<QBXupCtLG1#u$p47~d*zs39fDbg&8i08et`;i%#B|L!=L4lnB+;P8
zaz~{kY-S(2idH=^7K@I<Rovq=rJo};b}b`SnZI?W+-Loz!2Ig`eiGMbW&Z$0SjT<L
zD7aY0UD@KCqt?2ce}}rPqZ8gm5cV0XYw+qQ$M3Z%T>k*DyJ=i3aZI@6nqwHyjL0$d
zuSAEydRSb^CB%c!zAHxC!kQhkf5(EhIu|+qbX;~koXsB~Fh7Mi_tGET+e;$$Dl6L~
z(=@gDQo<GbD5-^&tZD#)G3*5^j>n3_r)pO$$rX&G<G96Z!{8lu;xO*<L%Xr$iuF$>
z1s^0Rze+%XUwPz@Q$@#P&7$~gbDUmkSQy3?aBA9oJksLgTgl`;nXc+Uu6|?IlkCv-
zDk!*E<CDRf3=B6y@*noia(+G0>}_<}64C(~19&REE7uLQEOJy<4~s10n@W5_t%W@Y
zY=8CXTxWqpXN6X8nBaT!S`dtFQPQ5V1wuUu9D5QefbBT%O2Bnq8!9E)j!z_4c9yRD
zNR5d0t`EYpV^)b6XXPY*73@$b@)3gIkZ22>+_qB~TlX$Kh^{MBg`&J=b;0znT`QDe
zdy4Y^0240FRQKEtYLJ<OB7!?n3GLdH@-do7@rtHNF+SAO%KCk2*e8*mXxaY&>!L2g
zW)`RkVn-Mw@v1;^n%C6rZY5mB8DpN+Np#ERZ}|0-9lBSyLacce*~M0yzJ+0v(Btb#
z&U#j)S~cn9$ARc-R?)8*@ep67Y3<?M%h|}xha{ZT$C01sS5rd03^JjQa5$+Bhkobe
z3cp@!MTw`}k7F*zS>)!Jz#7*+8PrPT%MkoCPX7RePWgxYd_+Is6uz}jxc!9t7+`u-
zO@Un({316*^LUHLWu;#ROn&wF_rg@XRX*jaQtWdh>rWZ)T{8GM<D0;L3{=bD=tnJd
z_&nBc7fp35*vRE^N<j!uBv)EIC1OX-JcpjmQ-8uOr<K~$Kj7HSOU6Kc#zzVp4bYsL
zxez5m3O3hXo)gi*-Q_XIt5wv}boAk23bdn*f(M6_IJIHa?H@x-oyG{<IPG20)2whm
za=klKMYWooExcg*;;;KgJ&9OWdC_)1by)rs)>#|wqa5@V=>$WcmL<k9QL-l8qBS6P
z#bWXPMyn2y=O*6dx61^F@TaY<?&1E4FFiQTdJ?YCK~>}0gTUYpY92ZEAFxLXnsxIq
z#jKb$eKeb*G3B^!yw_8L2dygm()#qf2i4Kc$D>`A&cWBe6=VAz=%CsZWaFCO+6P{=
z;Bb8?`u#zDT0Ks1_-f`u%Y^z2(+7oTJ#LrqO6kKe`=_lO<Gn-1)qP7;AdYoBDy{df
zoA4Dc{32H1{MRy{p{>qA;*^pH)~D-rdym+}!yXc_&RL~zt5t}+Go~QNl*in$tv-XA
z2PZhFc#4mx{gg^^=o)&qQalmRnzEX8vUXp@RH3=+%?jA-QSGPPe$FB$pK1wzEq8k2
zo^9=v{{X9BtpY>Paqmc9JYtu$o9aG9JcI*<2OiX+hCbjP!l5mLPFV&h=3}t&!98g~
z0N_(Y0y^fb+rb;7G?MKdIir|4NVnkh{b^Qg9#`rrDddhhN`stqsEpXDxN?@vpn>T~
zW>9LOm=V+usiqlMJg^j8e5K(&J5lzII2A#zp-=&p2h`II>?{8OEmQNQaoEu}1OrSm
z<kn;Ac4%<-3LDa)I_91+{+AwoGfS8`O>NmHnmV4j{3{grmrVmdX-rg7c&AN9$J##%
zT*KvN_bk{4k4jy;N4;||<4rau$b6B|3a;KcvB}yT5BE(R=zND=z*=c_-&|~-I=9$%
zBe5UDx2;!i9b-7PW5>z?qn!sS=(fNI1lGm6-~}GFhZ^S_kGLS#rM#sudXH0HBR%6%
zHrd7wDeoZ)YPw1tG6z1?*;uOOPagFlVH#1If>;t%IRieTnq)h(?b4--=3M547BMcg
zh~!hT0MA@^u4hrxnhb^K2cYj>iegs!R!*g2lEU98C$Q;?)-old%%@$fLBT&t)9{{{
znx43eGJ=ux1ED_k7NrN5aNF>G#dRMJZSCQndzpUuZb>!M4NiKmmM5ay>Gsj6M1@yx
zbrm<*0VJ*$C$&6Z*{c5ltsg<wqL*5+iGS8*tD{4JnQgXr>E5g=lDO^Gxtq@s!xQdD
z+$xLs-Qrv<Y<<UH>qWxHXd>rwa7TKX?i{H}B>)l5PZj3(J}$qw;dsYGy0PchbxGgl
zxbppR%`S1+^@wjRtVuE4qVD93);EfLPq$2CZcDJ}1$nHuH}ZVaTsg;Kz%`#g+F4(D
zljzOXlb9&#Y*~Cxztg4;Exg0r2F5E!_v0j&_N{LvgQ+8ePHW9B!QM^?HCJ~v4pQ!P
za>eR*cE1v@tW>47x60o(Gm53Dd_dH-C_s`nQ=jhxT#r5JTY;SOM>Fm>817zeYWaR>
z?qpv06&%{`r7CTj>6m+t)lBrytw#7K6kJUVX&AQUmPJ0zij2tnkIqhgPH1D#Ow?t+
z*)-7%QrWGa4%<f|mPuG=ra#Z)SVa3`x(yJlI%Lu|IX~pqutZ4DyI^l*+N2%Za0g21
zbS)okv)oI$v(5<Visx+Od36;k33BDYJeKQTpRHM@m*MD!8FwZ?JRiH#x*M{wi#a)2
z-J5J=0C*IU{h<a#L=4o)eGyPVCqA9(M!Zhok80>!88%S86Uh?(=zV*Nqb`Dm*UgS*
zX6~mL6|Hl96DuO*w@hNNrj?_Y<Zjp_G@hV{Eu?r8$z}Ve7^@87mvHY@-Td}B`{VVi
zwib^nyEa0g??RP_VgzjC3=TaiR$+rlGsJe3Bc8&ccfjJV_Y*`?5sHDaQ#*F3nB$Mu
zkP$J*wK*ig+H*{9wA}krXlA9eiK9019QqO}q>vcoAoLv#GC3O=1cEz?zTfFK`-TLI
z)Ko11&%q5>tuI+d!ao|PDd!!<MYw_p?L?!@hMkUzEkr5hexTLZuWj8<RH^z`I~1Ff
zH8|j8isGDXZx?fW%(i^|)eMoxoW$F`#bgP+v-s4|Z!!l)KTPpilvtPL+e!DAoKxpJ
zfWXHcDiC=Xpa-M0Es$|rntl5fUVdfvtU|dSw6NSXErFBIN(OfjUnwIw1JH9?ak{w3
z<Qn7bZv5YramTH6787xUxQ|-RjMXTNImIy$D}pe2sZub?A0Xy{Fx@E(&_=|H{{V$r
z$T%XXLUS7PgXvZxmp>=*3b;EmB#SC=e;U%VebMop)>!^ke@|>~Q^Bs26GT(M$fQ9}
z7@!4Q?gOPh>zHaVMHdbGgY-2cI1dv@(ZwT%#s^yP{Yp<V@y|Fs*R%M|{JR+rPfnlC
zygqj?CgO9Rl;Q+^=*|Tud8G$E^H*|1JW-QJQ`(Glpg?m;%`QFZ4@`4I0ld-3r6)X7
zNGGKsh)oEFNn?z4W&;9~2DJP+Z|CdQ>zo8Tsl{E1yDOf9qFb~UQLKnnvEH?~z~Z!i
z#lFQP3AB#>wLzC1de-e&%}V1>Cz@>W`H`?BbHzI!l{J{;aZ<}p#}$18MR4eUgw}H$
z9zR;?wVOeMF3z1zbCRas*gn<4QZ|w3QmJ@}12aewN6c$h2;_lxyJOommv0o!DG>q>
ztvcXe{HV-8?@kDcv%ZF;*H3h&KR0R|ay_d(^ogC0+sOz&H#JaN+_xq8r<-esIP+xx
z02;Faf3RbB%-4=hT7yNfje!KY?t0Zk(xz;YkHx#ynDohFK<_pVdIq2i&u0uV?@ggk
zpsdTJa-$4!p47K@ep@OGvG0naZe?ur!K4Eo-Ond9!xjf4^r=foS2_GCg^ow9Fe6|Q
z3B_f|a>Vtm8Q*M8pQbA*y82ZjLV$2R=_zx^N}&^4xl5G#^In0cTqJNH3%T){^V@t2
zh|i&}s?JHFWSIeM4uYYL9U-&SwFw!1Wsk7NGgct*p(p(zh#r7<rPI7k8f{sW?q2oL
z#jL|J<s)IwQ&L%qd@XJxV2QZn(-r5Mt&7=TOB1f#HvsjoWm~+jEEP!ZYtOuI6b(Au
zBdc+eKf<-8Eo^5voMSF2pk!0Y%_lX`jD$QIL7dW_v;&L`)d4D;)QWLYFItgKM_RN?
z9x{8>n=?_2b*a_D`_&R4h1=8dsg~FPH(+tzqG`$K4rzg2LP^a~iCLqMr!;}V?Lxo>
zKWC*e47y$Rjt3ldu6erVx`3OIspMeSH9TfFDn>c!SXV}r*%m>ggGfyn?OevAsq4Vz
zqXV@{2g{SswKNAw;N3b){c#-;*<#1cqaZi`0II#R!usP)xJ!NckD~&46@&0|Pli1h
z%EK<?x6Rwz^sc+a8X{g?!6Y*n<s1xpQ_;OmV=EyVJ6%p<94_S?S2j`$eO^mtfrN|E
z{Y74jPt+`>%<sEt&&oK(TAFlt&g9FF;v%a^yBEA$GVY|n<EgA`nL&_>)w*B-JsYsB
z8-bT3Rovw($+UE;Q=__IbCc4ikeq|soP%{p&7TXv5<$}=)3tXI<S)H)ejSfwjNQ*H
zYphIuRDhXD9nD>Zm?k$KYJ_I5LOxnUEg^63995{8gPhe=9Mzc56(CFtf_dvuZ9Dp!
zu~8qr=}2U;jw*05P{wLu(vS`edr%si-i*)&2aMYmFr3$h>bgC?tE;3lxmP*cgI?d`
zMPsJIM?HA26V}_v*DYopcY%@CsR*9mz=kQ8Wy9>q&lS=~;eD}e5AycFtte(9C1mag
zH8R}FeL(lBxE!Xd;hVIN_X@ILe5W`y$6R<@TbfeNsDsdq*RB1fxAMN#BTp2ulyn5q
zaUMTw;ftt=X=OrB`y^Gr_(zB%eEfGCYrVg+kg0oc53#OtMAW?E4U(=uh`$vqqcJpl
zX!$#j9Oj(TS=tTisq*yCQ&(S2xt&hyp%^2gul1-C!@HX$_mlnVKrDVEu;G5n%rn_~
zR*GxZN}naWZS}_#S@>;9P)JeiD%AcOv{=|QgrCZo8Pn@F*E!m&x2Gbg$rZe(gaJ=s
z(xjKes95ZkfTkvtV#X(KI~oAapGvcQ?NSfcqFpY{ALa+AV_LFVKm7E__NtF=kvGgw
z<56%cy@iPze60Tfz^a7WPM$beNYDFKsH~<yFm}^!?KeysDHNgWO5-wO(rp>If!Gek
z&1l78XKq9Nn*?+jsg)ivwNBIPOP4s_<&V8Z<T2}hhzcm$zJizSuw#*v?@<Lq)p(|u
zqYc8<Y5^_du=y2KRZlDJ2lu}*>sJIz)F`KIz~O0#!_{p(xPz+Tde$#W>+fR^Y{c{H
zT$F=sgkbSZVgpM^I#SXZqofbs=LWjVNtqXtGhD`sGFiPit@IsgYC%di9A##9+7-_1
z1HrD&-2UsD^IZ<$q>4GoJq>y#oZF$_*p8l+@)?#6N`C4+Ds?X%OQ7*w=ZxYKX-;vH
zqda{pp^djKWq6t|H%FCw;MbXkUdtAfE_%hDM=D_S=e<S%45uTlT9FQM*j07}w@=2u
zLXNRKc6WXZb^BP1oa6(F-0>%eKGzYR(*=hmaa_lQWb(BL#!t)#HR+)A=Q$Pe`PEra
z#Kv(w3_h?t&Rsa^)^csR*yr!Zo-_2W2J$&$nVMXD-Rs-6?+wAIz|+B)=TYi$`B$0h
z5||!HFCj&ldJj=wL6GKr@7-FQ*qS$5vyqigrADLPuU@*b!VREys$;Ev+#71_^4hRB
z288>=y(_64lhTNeWmO7Uk6<%Z%#eYG81X<-R<sjIzq)^t-)iIUlZw3$hUFjYu5djO
zYdP11cVp!_;xKvR>r*UEEML1vbLfkj>n-#hF+OLv-sh=yIjzfYBH03}paZZK$x|N{
z@S&(PkkPb_PAx{-<?Wg%<891at$Q3EAhugr#==+*q}M2KP^k!*sG8xQw@*s(a|%?k
zw)U~u>!VUs)`wGb;#sy8w?tg`&JATxeRXui$up2gVtB0Bq;2>)t0wL^KK}sa-npq@
zs8aZ1Tdg;{CK44DGERz_X2A7hRO4eY$WjMv)+W6ZZW(4=bBxzVEw&=}HgEO4G%Clx
z%#id{?^)65*0;lZM$PnWRSg!wr4J*F0nlgp*42>_GbZ7I#}v}Au2s0w;))NF4Y=-2
zL1KKV$2~e$j;Wuq<rvl?N4+;T;ysNf2VWT_1Lp(QnD+r&EO@FKagnWu-rMSGW(dP4
zB#zWwg^?k<EIv+s>b=8ASA)5aVL@lz#{!&RXeF3a89+wkEh6n6=CO5~(C1=ug0wYl
zO%XP$Dvwjvxhwmf>d716w^L5wW9l~zG^GJM1yzRGrju&%>T5x45<{1`+w28iw}#T$
za3uu$ieeoKh@l9Jg#xAAPtu$xwF8#H`cq8y<L<fqr~<v^$CDO2w`#$ew-U##YTQJZ
zGVXWdrxcM|TSX@Qg_v|C^q>gspm<{p6z^fz(yd2sK*{BgKJ_ZyD!1I?oNkx<pOqjO
z(W)k21M67#mnLQ^0Rc^F%`lZQjw-L08vMdE40`|!LG!-S8J!#~=kD?CQ$8bJdsUev
zTpX3fXU{UR`ADD$rESL}y+%bpYq|MWow3n!$VDI^*+CwZ=X_HM&#eF<>q$yZXvm-h
zpztX(M{f9_V&{)aI?_^)VL%6ZF;5Xle}TU$Um{RBMjuf?ghPsuHcv`?c2hXc(iiDd
zuA2Sxigp5?Y2Njqx@qI({OVQGfjtk_ivg94`%>eMm9zbqfq}=?q)jjb(u)Cx6^X_v
z!Z-fut>I}J{o|i(Ql+9X0Z`Flm_ipLk&0g;PwpD%zQlu|#V^>v{u%<uJT0W@u!?`!
z<gM=|6Rs(xW6l8>qy{jubDx_Sr8Y!&HLPM!y}3p^QyGylmLHV>W{WKKZ_=0SKx31d
zywk)x)DJrU0Q#r`vA0kM2l1pa0otT8hbKAwshjcGngEEVJ8?}hgZNa%usIwGK5l+P
z`A`HNR(num$?a2Zke(3!RK84sv5tKx0>6}K^3Qs-wz9B1Q<lzV>~laBJflhFd)A6+
zvc5BsQVk*f2^0a8BBc=z?+n(;=+1hp6W5B6Xr%B^^X)(wdlYvR-Jn-QG&UpsNF&~-
zO#qhv08*vB#wY`r5tG=|i*C))YpWUqE;50AIK@nw7ft~u(t(_R*`GKIQVVAEuF*6G
zKfulJwAGlrI9vW$$@JK01BP2k0R(pJE2Ob3mgoq^d9I2-49r*Mv|@cRP~T|R7DygT
zW{rJKWmN%}D(9MmqYQMb67VV!*ELl3A(>awEK@c|UTZp8jEY7o{;Gv!#(3{pm?phi
zZt*f?V9|<P{xq9_t&oKjVvrhe86K3xAsh-!RG80tFbBN=G!B&_w$$L_nd^!;J!r5C
zxE|R)w1iN^dI9vLX3woF3}!hMC;+FuMBPEBuic`+As9U<A5OHd!wN8RDnL%u)6$%N
zw8O<T0**V=hgxTPc;=`<){qV<#*mKK6vQKrDm>&=&-ZdTs7GEY403RPtw_g@TvR|{
z)V)`w05&kL;5ScNno}BKN9R??UMWvX1Q{5lpkVf+y;=dnoTr|ZA6k0#rXpGZ&#eQF
zDM|UL0PW9Ogr1_LVsa`!<D>x>GAf<{HGXKLiEzI$1FdHCaC#cK8s<FYoYM;s9vIT+
z@%E%64bK$6jVp{!ooO*jGH3%h;+O*Rd8Y=!_om|n(&wM)Knm<h^`!5bT!K4NdsDE7
z1H~hB=|@gzZbz*EAv7Vwds24(lrP=`){qjh$n~hm=B+eXgppN<rUI$wIj+mW&Osx0
zQ~6gKoE+Cv;VD1ToPQR23h=YY-ww{aEBDVwLzU*GQ&7eCM>Q&(HGY22RB^#Hn4~-$
zQu2CI85FC9H4>gG#G?!ARac>=fN|<7KmkslokVyX)Kbr}c8uq>XqCXFaCY1^S7W#y
zl^pKNIShHE-;PanMG`f!&m7iG;^J!6+zWA8x5O*t`q!<OO4G5;h+gRmZYPSG*W|lj
zOw=*9M-?iKml5^my_$;gXB>Ar?J`WU9@U}IjbvE99dXjN*yQIG@i>}xsLxUk@h6X#
z9jfyHZP<HN2uNZ-8qr=?9gT6l%P`aBnbW2{Y8#&TsV;$z>5pcp=Q#qp6l@~ypC)0)
zOw_l82>3kX(x}+J+>Z4%<fqByaZ_Q94aZt^c@hIqM!@u`6|o|kmIb%!DWRxr6$d=i
zI`dKlooVoW^W4-*IHy8!C%qPI366JtDd-9I_Nd<>xu-0NAKqXy>s9Qe_Cax%svaG@
z8qKwkY{hKKiuUb;o+|*1Ov*UswWkku!X=dAO4hWL7yxR<U~|^2!z6`3QTWv;0Z&zM
zw~7>FlT1koT+}-5=;n-`x$98d&$&ixM+a+xdwvMxHF21jf$3S`)yUj=Bi6Iz3xGK1
zH0<ZGrkBMalP!ul0B~)R0!>_F#ZoVp9+h*fW7?CAg5V}ZY%>52O(rCW{{VE3^-5UY
zQo9{M&pcJkgpXqK6k@fN7}+?A=1z7#D3QN9Y`cZa`h6&TR<4*_6`0{ww))f;@|cRo
zLw!$rlXlad;;8E~?u-@5?oMl>jvt*8=VDZoaQ3O9d^a_nX*iZ4j^F1MYBp~(0yz)V
zQT1nih0a?tbB@&YZaY+RLoU+ZTd@BCWeKUEw7ro7t+Q=CvCSV;sQ$=%NcRz>RmOYK
z8>#iF&W))!$h2?9q_@yDBPTZdN4pB8f~fw;y{vnci3)Ryt2y4RIuBatKj9d>k$!n&
zPu7vV7V?qiU+wh^Tf;A%?#OkbwmhR<g{Qe<1~&Ard9BL!ZaUYvzr&q6SKo1R@)~@9
z4YUP0D#z+`UqwQvBotZ0Q{HzxJ}8@a3dh_E(2fZ<<e|s4ds_G>MuIJfjknlQ2Z1y;
zV&>iQduMO*t96LvXM|kYvq(y*W1L}oQ)954jEiahrEBRcO$SY|La<pvzW5n6WWj2@
zc~Fn7FK#|V=Ch{Uo_^19{{VjIk4V2`@>txTq;>Rjn+S8i?92L9d39|X)Mf7Nm+=(-
zupZ3t%MTB_hL-ly<0I~<Ls8vmH|Ao{>GO#F3Rkn-_`}1o^}3Az0Jx>UkgVB!eWasp
zhT3WU!hk<opKj3k4=RVky4=_crpfg^D}PMzj=dCrJ)b_A0=kKQB1_WSOThJc0R1Y2
z-Z|GM&cwHbeKKjvyrs}whD-c6)~~1D{#+_gB%JYAQ{ghKKu>oYIPZ*9QtSHc;}Ys_
zqyCww2B^sQQyk5GbpHTZDm|pfWLUWPY_{$|)ZzoMC#5uaLfsT4#<2`)JC5~KTEpLS
zA5!L}NTNgXpa<HYJcVRii^4t=jX!;V=C^aZ{3w&c-V!(~D|=v?gyU{Dicog)Fg}#I
zrQ9ru+ey%&j4WPbuV4jIeJ@SODQ-X<;F`0)I49D8MkwZe!o^p%gZN_r4uYBXSbL!Q
zVy!v(a0NxR$0Sj4Sdnex*@YM$f|Vgy^R-5O=@W43aZb(#I%1W_VnLtpQ%eDipTd~O
zj<o|x7k3_n(Q(+Bolkm&-9e#BNy00$9)VV@!(n+p`n@{gj(QX{TvjWF2arD+H!<g>
zZCm(jTbF^S>>jS*RgvJ$RFUUTZw`GjXt-GCfP7$J8g>s%*INgH->ll3bJ{c=D?%Rv
zX)FG=N#;K7j8Spe;EE!Xxv@&JLI~vkRq3&KS3-yG*ef6Q{%_}3pwsMa$ntF>PomPe
z?0FzrWhcpkSuxjY)wncmV&n#gPm>?*V1F}Su<*u46%~GhqmCDihs<`;xLEVJd?BvN
zK6HjL=vuEu;9K_}z0_h)P>GuFOoylFDZcbvEOJoz2GkY%Mf|Qmy1WBd6Tuo1bx9oi
zv95&m^`?>sN-jGYwz?*jW=E4_AJnfkq`pjJ2^4GFfl9aonivDz8dn{KGhqJ!g*VM(
z-k>h%_&q(UP{D_4E*2Mm)`Dor6lXs41%=Huq;)@cBh=FVloAQ*4HpXz4yV5~Zeo9>
zHB@Gi<WxN7fF2m0IHfO+)Wu|A2w{UxEUUoh(t(X5f7j4b1t8M1jwv#I=m8mujz>z*
z)fdjOb=}h^>MKidDt8LcytR?7-z-2Qx7Lsz8+jj*bu@U#e0pZ6mie=a+wlxOR<h`O
zuI&E+I>V6qcIqmLX7-74Ak=M~ZX~!|j@9ip4$|2pXFPT8YryQTJeh+6c=YdH-J#3o
zY3sU9a5(9j1ZldsQp&{Rt$E*yl%?|S$5Who*Pt}&NgLFCPAi4+QBya{Rfs*lrkWYc
z98(m4#0=D=8i_~G-|?y>v<U!Hhti?OM^B|ngmXv>FrB?KQi(lJN~|OU+v`tP4g6K2
zVzD@rIl<zbB;aw<p$@;^Tn~CTCtUut?kf`p&w7zhH43ty;{)nyMRg-Plw;nGV6kNz
zoYR@H-m0a{O86`eI-KH_?qJ9I<@#ohVc2<MdVaL=Ar)8cP!IWP2jfZh>rwvzEs!5`
zMai=*7b2Qm)kf4U6lJ9Wf4q1U!>ib@D{~q4%^b)%OQ4b|Rgc!F4OY;Rwb{SjT6xqX
zTo96D{li7d<u8&?erW+=%}_d-ImB<)qisS{(j4QtrEujmcjEw>2^`i@y_}!*YCXLv
zzihh4-A~4gi<HyPG?+d5de&gMyCd(Q{3r(LxoMCo?YBJAxLDIC2e0C3JvkMc#j=0W
z7msRY;to9K>BcEsb~TAX$v;|QkuY#YWsq2W(@1|xiMFrac@N`7$75W|pWg%OX{~V{
z2h0GhZ!jLe&YR|B=AFf3bL|QJ_4*S{7m;#z1B$|Va1R+Bjw-v&AqN@amB(YCeNNp@
zH-40#+P1N;&oCca<tCO=4kg-0wPZ|^E>7}E>%8WdFzk9XchOD$q%@yFPHUIW1-ysp
zTppjVU)VCCmNtlX+k;)DhQDif2;U-uj-+Cx)M&0$$-dEWau(UY6H?~zV{NhbB#N{O
zvVuAu{c2P@PapoO&DD`gnka~`T=0>vyEQ9Aa*7O+L^IF|)C?Q~L8yyEDLC859`zpH
zMf*6FW7DqZUBc!x9fsZ1gGae$DsK)wldWr8rr7w%s}V0bsrIsA?9r1RfJh~-<Q}6K
zs4n!QYXi8NN7|<f=Zx1)!5#kq8moAL?Pdoc?d?_0!;u~_f8t$E8>fwBPyyg`#b>vO
z^+zW+BzpnHPvVGtopyheZEtGEY=8ReRLN+%b<ITeyKMU6qis_5LGxV7evOK$fk#f%
z5=?I{SYz!IelBUI;$k_PQ~v-1G|UPIwF9ub+?<vt>c*3E0l*x3($aJ4e;Ps)Jbl&t
zr~vW6r*lbzlR(1<G#%cwV?8N)&;lIittclQXu%wu(&HUX0DTo{1Z6(x$9^$a4U#&N
zx%RAUJJn(adHxgYTUPf$_$IuQ+B2pyS~1^{0qfe3UaYHvaz2%>a}S!hZoZYx-&oB9
zG|`-|U!@_Ii;zuA9Hdrk5}6oh8TG9g)bWu*0@^Xa$*8VAb>o_qTjl1fTt3*_(y208
z#Q1_C=j9ZhI#ilPjpT4EhjhsKlys>zHS=a2`Sq)j-ZG+qxFBPS?4YiWEJUrKrrJVx
ze8s(LH?z2Ixj*nDQnkakuM~ZvTy+?&{h7(kS8FLxDxEsh6&ZUPv}TZf(MWeTGAa8o
z<}0)=pd9dhDS<LG&0kR1<#R}21p0j__G0ELsR6ef@$F8X#HdEx@!VB|2T;8!e$7wW
z0-3>Tv3YZlr#;9Oo1SZ?@g<{2DzbsJ@DHtXC-khOtj>r#fElOl&L|7dT6o}-=~8G!
zSB%swPDmAH-yh*nF;o6DT$Wd027je6jB~|KN2lRTAatrkG(t!fb{pR=)I_J{9mjft
zJ%UBt0Uq@|_=C<30Kj3+I#$p!k*DD{7hWc|SLCh_>(A&b()@LFlB^KNf>Q*a(!A@y
z=)+!$MaI-8cjd?PuAg1FH(JARKu?#0*N^_aZ5ZB0QY+a*2_q?<%g0L6TN`FAl~BI@
z>Yca|uJ3O2>8}3(c5#u4=`tg~wzG~V8$clS9qWp_Tuk56x+|;CF%CZHJ^R-=a@*Ok
z4k#KR+*Id3FzHi8s7{PIVgcwX2IGoo`C6t*<r{_sySMvAxxxM*MP*3XJ;&Chx4V|r
z*K3`J?+!Xui`bQ+^W*4vAW<C&W^rux%{AK;Q(KYRtVC?y^qqUtjW-67LWU^SW(oYM
zLuUZ>s>E}}IT#FsP{6Zw5LWXSqjbepJXNSqn;({P4{EI_+U0qsm<t@cTCbz4ugY>O
zD?Yqci)qTR1m#U<Qas3{%aU=|r?p11x;8;PRg#;>AEiL?{eG3k(W+&LZp?>k@$Xha
z@7L>DB<(pJs{Op;NWktrX$-U*BifahkLyvZVx?1>Lmy{5+gt`ecRc+ot<&dOR6Kdx
zTx%~pbgd04?AuOJi7}I$W~HKz{?<&#gUwD)PSurVI5<AMn$QingHSTsHWsGdBXGl^
z>s6vZDfO!gH^+|j(3xo)BPSJV+D(#U)~Leyk82KAtVG|u2c{2d>4Um4k~d<LE1H{d
z#b!eLK=i9o$y7;abv8l_WKh30F-)5&86?tUJm1H!<=D(K{09}{Z`T<7F<!^<5`XkE
zrF!=V72{6ZiS0rV%;KB~G~Aj{c&ZTY1t{W>bn8pgiU32`7^CpwkF6m%6aXLRO`w`-
zGyt`;;Z)zQrW+U>RxW<Ez2PPi>d7Y^cGW|2XYiiYrcPvxMBr?!{YuHLZi<}kKQ?ii
zx2H;qg@FNuJ5ZIbBl(6{bw1U*Iil>$Onx-b38@Ie^rIXMaZq#=br^TRe>&skLaad?
z=DUl9{n6xb4RN<Awr2x@lZ^JRTIlMaL2o~kHb6Z3R^nVhS9H;H>rv_UksE#G2|lK-
z7@@{7ikR#b9;H{CP6XyW`r?>ou#k}+6OT%;)^L^N52&UcGR;($BxBUmAk4Y9x?oMT
z`2_F)=~>Tds<At_ZO=d}peto=2#<Nkxu}k+;Z!6?8N~o|!%w+p`Oxxt^{0(J$76x%
zT5{jW2KE6-<L=c-ukv=BW{}F}*_7ZBpL%1!5d7UU!KkIYXKp`QgUohsz4%iRQu<8D
zRB$s?3H@q&l3G^JZj}e)R*7Li%`SMP6vQf%ymqeFNMyOTL(`@>t|z5*T2<r4Y`-=!
z=~Bjyxh(DB`P>G_Bhrtw-4-bXM1kwZD?Z=E(L)##N4SporoO*<e=f^tSTFanflyhs
zZ@<kFT}`n^@X~9Irrg*V<HM3ZwUn09v0t@aZ1oGttvfkvqe79w&nXxTdCdz(C$Z=3
zxMDhc9@N9dX=@O)dV_9_khjf)S;TYFyHSG>(|FD?Po|NIp$}H+&sv#!;-FKCm^L}8
zM6zC@q*0!g7$A-*>B+|xq9l+g+nNE|0HEZ1(@$z*B?r=!bL&hE$GtpenIqM*YZq0F
zCEiCyt)*R~(~6_2!@dCB*S~t2k-SQS)Wjzg13?(09M=)hD)l|8#7X8bUVdY@k9vhh
zD@RH(MXFlOGXCi#%L=%lJ+tAIaa-Bp717jk7}rOryzh0s8HXK+sPw4qj-M3vK|W;2
zBfk`B5nV93Yskuy$7%Ne03x!U=T$33YFf0N@9o+<nDHPRRfj|GSkkk{8zhmHDtq^>
zy*=WNM%vi{iq$_71dU^57|72Qp{pit%R`mCmm;y{Y?F^#yL927iqDbqNfpv_5V*?`
zQp7gniein%twxwQ6)X;iKujz8=Yd@!6O2|Cikl-R80R&+A5VHfOuQPqZ^^1^colL3
z(vZt)GDTR7a4H3<ke-zwPQ59Z=9~z{ChYrAGD!OKikMU=G4-i|<Gn}@3z|)|pwj0e
zfI06N=le1*t$3ckF{!{oAw%Sm>0Zs_Spw<y;PfqCJ>pAaJctwTvkrZz1Esfl1Th%o
z1$f|&m2BO-X_nc6+?wR!f>@&3)5`o~JE{Iakxt@B^k&U2Vytakc%sG!DJ{f#9e~Yd
z-FVv38!<-mf4a3oOFMAHg$2L7YOmSQ9!5vfmoQkc-aGR{2;r4~0aeF|p5>43CH!zI
z$CYXa`mve_g;e1bQFc2Jja|t5kN64(tuJWbKA5LDOnue-u~7!Wzyt80MW5|!fZsHG
zfbUYSxiO2C8@($%n|IUFnVu<#B)qwK3m4m-!lP;K5Al*I#FPFs5C`E!g5wrhm4gRi
zO=d025=}ghttQ->IYQ)nX>xrj;9`I<aYcZP?gUa5?del(0CoH+q+s-?V7S1%=8k<T
zObk+Rdr%h`ez>H`_os!)q%q^GQDG6d424L@u2T9xF6EaTX1eu{bKrCIte+BC#{)*_
zF}tk;Inns$gH9{WBMu0~A)6W|4toz;-i^aH6|-1+D#IeMd3H8&f-9xB)8bK)bGZ6q
zfF-kbON1k_uS3%&GFx@$>0W-2d2%TS^RClGlsqMSsOwl%rlq+`Ryr$3+!%GisP%;3
zrb<1D{V6o_^Ek&^v3R+$lmVZYrF>>%Pub&BJsMA%2ailJ&ZKdZimFCBR-OI6+203%
z#;CIM^slz0?*z{-TbuqKl%@5!0CS$T>WV=MM?wX7{*y3<M39~lvtEk_iLFFwglyn)
zNX2~qb(ht|wCSU>4^lB+@w`E3UmRh0`qz#4!YK~0QDSKr{{VD-YtSw{Nhsar?NmL0
z70+B<J;Rrm1)HxG(U9OO;Hq=X&l6QnJh3<tqhH)8#2Y`~spIgx*v!`$_D<i8b<B7;
z{DoI=Ngkfn^|Hpz>~JU<cKQX1V7vvKcP@FYSS_vLU){u@<I;sfc&TGRt(I`O?OgJ&
zId0135GNmVpRGK`fjg7*sNU|{7Ws}y9jXbnXm%A5oSufW=40g-%W42rU!Cz;^4`B=
zihxTbxb5vyQbwy?#SzX6Q&(4nF#XH7=~>}OCnlY+8U}7htlI@A$Y6f7HnDC<V{gr2
z6Xo^K<xMiGjJDuDlvoY_0PWDL#3Sl!KKk@s{{Z#tG~L<%02Gb+QVYvj*epedxu8c!
zqvUQrqM)AZ?6;0~XWFIGfeL?>P}Z7LZ~|lBGyy%vs${oh@`%XqQ)n8jFf&DS0<sgq
zu6jAP=gx3XP6ldwcSev9bNE!To#fL;J-Zl`BKivFr@N9VT|;y{R;7cimftrA6_2Sw
zI?Q$^@J}RC0y!_Gey#a&QH!?+<rp;Rbi3PtNO+?igK}z9q2DOn(!fCPnl3Y$)ve~Z
zkh&>zoZwb#SzV9$cRBis>zc|!#Z;?$?L1N)Hh=CY_uWhmHSMn#AL#i10D)6Yo%vjg
zaDBs9W|~xta-d}QCZ<giXE<h!PobtGh!$FlFZ#4!Vrg2!@B#Newc9p{D)7=PdxfT*
z84m^9@}>tEEH1msgWGOuMX<OdnKSfS>{CO4a7!@y^HZjk7fqjuqR3Y`Z|u2==4a>H
zoVq-?`|tVJe41<v(ltL*N7>_F^>Lv33VH#;e`0O`Ge~}>p1K5I#IhdzlU<>Rlk%t)
z34!uUk&mq_p`4)5?Z;bv#B{|2NJTrA*%#|wIS{W|V+ZR|v)bpG)|JrCZ0RmY`B8q9
z*3pZC2_Jy2f$pu8931<KtZ!i%&QH>n#bcY7!$iNyE9cW~G<al?OH4<#Z?>SJc!{y^
zQMRBzhAw`zTr6a-hb`0%<%sp&igM^S$bRAcYQ&PuBktsTRD$AV>4C?mG+cHo4IU6U
zjX?CpJNqIGa|mK8Z$4%tG{W}>r56hbH0V@g$pBJ|Xw-0uKMH9}hW<18(hGT=xnf7w
zfUw~TXD4W-D;VUmnoqDxj!8b0_0t@Wx@Zd#mVk9(_)~n?ha#=6lPN!N=dd*4q&Dmr
z`p_#BlHma-8>xQMr12g-t4L_XkGoD9IUe6y2V*Q;vo;bU#;5XiHyK+4x7T>BDD;^S
zs|N~4d{x-(ZoIr1i6509Ikz_m+hm9-6wxHacg=Jyr57cecO6OTN;I^{T!K$cywE!w
z;~CFJVN78;9ZhwMpqA*2Pp~ySei*rOHbB_-2ACXChC`4tKD3`^lh(V@;TxyMEu{Yd
zdacFa%f}-&q+`_51I^8xj7J>$;)AC<9*thBAAv4eeq_P+H9UR;m#L9g@CJZ9k#xCR
zjk)@BPhB0)SoyDEi@>N4&vsAz092#Fw&=iltbMjoaUMRp9E`j~--S+|9+ZRfk?g{~
zia!WhD&j?XH*?A9R^sr+of?nyWo&<WvqjL)8IQxRcq%^%o<9#c&&qiJ0ASa&CW~br
zHrqro=qk$DLaW44@z^aFLOfzW43-1sWB&jFIIEF(Mphpsv#{;*^{-k`rLd?5I-FFv
z^c1c$$`ip?k^#2JaoL)$#o&9=qkJ)e>6-MM5$b7nZX}UP;bYI2z|x)xjZd{sJQl0+
z`KSr$^7CE8?T><aJ*WT%<wrf}<^zz6z{$9Iw;zX>R};aOSoxi?T{k_2C{j*wnmK^L
zkHR``?3j<#nz0{-bhQ5fmtaSst)QnpDG9;Gd83#tWgR0;w#M5y^VnjgOB+$j+Qbji
zulY;6KdmvXk=vip(zwVL-3BonW9TY%P`wd<DwQD!I28T39@Jb4<Y4pz@UDNxR*OEC
zUmKZu!0lZlDBa2YDweHovgxt_q_!$0s2(pW?Lk$6+7CllFBfF8DHz)1VyV-ou?)=B
z6zx|$)>j03n%mU*fqL;+pma6r;q{4>h#QJ;y*bWg!Nw`42a4GeIe*BdC)$u4A4+#x
zu?g3`7&LVBr6=*G0;nxWexj6qRG9ZP0N%e!8zh=BNPAGgX*DcgFvq1tI(pRbZC*`H
zz-x>g_oV1EQpz*P9D16JcByP*cY9J)$qPukf$7?!U{$C<CNoMYGfEFbR3T5}LBODL
zD8(=aAV*LGQ#VeB6$WtBm=6SIrVWsBP=n9CN(f<|MKBmoJ?PIA!oztK?zCJ0ahhC>
z)Pw6m_Nusr$j>z3am_QmDEujbGM*^TSW^c|aP>7p9NZd&=QT47j+Gk&k6}rSVHvAY
zGZ^qV6;--ak+JETKoapF%`|^1bjo&ysMWZsxXA}zv~;F|DaMO{9!(#|MswKFR3IGE
zjwx4~cY1dQHyJdfanhfFdeRZ@X^3Vq(wpBsDNo}@2JW<gxE!=#bQr44FywPqp^TLT
zezg;+1d=gAU_=PUYohS0V*K(CHP7RU*6{S(H6;VDTJke^Ibqq+hjyAhQUZ344NSSu
zYOic}MyJ11R)EV_=aY?(VGaYF8V~7C`ce^DjERTJYM}eoZHES{sQHh4dez5Z40jb8
zTf1fW-S1MI)KbpzE^(h>TERE4j2%ZQcZ1hGsu28jrPgLXa<N^c_NsBsk<E8TB4wTU
zHCp$ODs9=QF23Nd>>ia2D{B(8f0atd-|?uF;j(j2C-kp*>~NhWlY${TvCb=Pn|C?I
zb5>25<9rf*E22^iVB}ZG<Kb$|^k}=pwQO?2wAb$r{{ULdwE(vV6{tSw_OCKfce*vX
zi>M8^Ad(JS7^=_8`_;WcNtYw=s$^kvj@8ta&<?fx_@~^L^1fs$zNVXO!Dhie*sE7$
z8)na1T!4(&B_DRJgV6r~D#MO_j8{B^&1gq9<OejRNsQLOE1GBkR8h(rA&PgHxatK*
zv0zFDIvPNJanhT-5lnei21&*bdbm=O=px*QCp{{y+bD@f+?tw60Eu6>TFkt>LPGDy
zPC(6im>M$XZpJkwWNyTN(N#KQy<<q2nAVlN;97H*Be+_o*0)p0T03bzrn35_UT2{F
zq9APIty#7g6h4)IkM#uoDX{5!%FdxJmtpEl)x!Z&T?Or8jK34%Vcy5?;MOgz%48kG
zA6oPl@T%$&;{0$wg-s-W1ku%ld2f;LT~zYvC|XRHh({o^qc7e9uE8eg_&KhvJQt;Q
zh57fZaQIVAiEtqQ0KSfD{{XXm$@<5U#F<BOe=4(WHk}kjrkDx64^dr^&@|Yve$5eK
z+~Sd~G|N-IM73OZBc*E$1Y)&hy6yBhlKX*l%P8j}v?6C{6bR()$raHZTSJAg*H)^3
z-dahuJvLpY8<<Gz*Mm|0n@#l(Y|d4q)gDceTQF1HiqeZtzjO=bfZnWn*GF%EZ1Lmm
z5u8xhwyD<UAV1!&pQ+L8L#;EOe+^wq`;Ed!&m*l3;kFC|Pm$j%&1}i9X;$R<nuGwK
z_NuJDFYx?X&FZ)Nyw;yrqx_`%N%tr}h2vp?JcrmVT(a=apBL{ZgUxf#&&VG^+Nn+P
z7ek0*F*LvKty7ocZJ^=}K6dvjT0#(pkwS8BbFE!I&N1>@#s_RIO0mM23lgtBn63f-
zBi=I~FHclX#J4|{RFlWL#H@CCG5QQ<s7I%m#DHcbBmLS?g;Z_YpnetP(s;*Pm>k@q
zf4a3!U2|5L{MwAXcT<Wr1KC57_nk++>W1d_*4+y{@q_;Lc%#dED(!pQhWf~AxwI^P
zc_eSEQE3SFC-EMS9(UhcsU3`hsNDGL!}iPbUMqjO&3Qvxsxb<@5rgv@Xtz*tv41LR
zGU^vS3U7(}TDST&wDNm}s#E+;x^e!Erm^&AZMDXTlo9?FG7JDH<PKwgPl#S2mnxR<
z#yw9z)~UCOyiD0|w?>)l7ykgQS+5`isUJ#M*f)B7qPcQSYh9cDW~(MWhAOF^@&5qU
zUtF>8i46zqNKP|O!EwG)6Ov?O?#7%FKjDpY>U&ZL=8rR)p#v!X==?<@_26QZoyLIs
ze~T0V;4n{rdT_w)Q5%Sce|Qc$^G)-!ov6$QqUMl`3Pvz#cZy_o_cE?h)=d2>%sM8k
zF&Km(J;~`#;6hkrREl`58-EJjGiGf<BnQ!RS`hd`&mX?k9lzaOv|KE6!PI@`z@{6h
zNBpz{2Nl`d_+!J-9LUB-?~__FX&xGb8*NdTdZ{#<9gjITQDgvE=h13djl}JU?WKHr
zEqY`vqucP7(XY{Jf9)$&k0}`+MWu1r^QiP)YErv2=jZ#xRmglHu1}9JM+ZI5Yq@P^
zB?sjrk4kH6aOD2!=(t$rqVN^r1J2YV$9ymU0A8(s!U1lGJp0+04!Zyqwso}_#4bN7
zc-F@%&^rU}D7fro!{J>IaNh)vw~eK%N*x<TgABTKSqC7M29dAT<lZ7GI{q|$w48DD
zqTypkKeI=H6|w>Jsl~#M1bcp!l((dFfsb=e{?Q6Ev~%f7;bT+nE<I_ouyy4|ed{H)
ze2gM?>ro9>Kz?M;<3+;8q-B+`d8y2sdsZ3M=FiH64@w5Ba$n_)4EHnzjg_A#8wozt
z?d)6b)+y9(daD8WRA&0~IrD=3JJ2(AnoRM>)KgEIN8bEEtRtvhV+M9%>z-+!Yn=6&
z%>Zt&ojEO$^r<187;JNg9+l30qF$TWk8@GUBewzD9@GKVGoTqVr{_?#@c#hMb^Pm=
zC5ijZ`O`=zx8i66r)lBa{=5&ZNA`<<`T1UbE1hn7^NLX*QG~}Hlnm&N%st$n!kTYw
z27Y$q&{hF2jNtxsfSiuB0nje1Y&iLc)Kku_0O&rMu57U#Xb+B^edr4t?W`dG0G4du
zQ&7IOh2k-h=~%_H-klt=q0Er8{S6?osM_R<_aa6<{8B!*Jd3x;h-c8&V@eq16CQ$^
zW+V7FQv&3Al*r|Q9>9uw>vtu-{A1{~nD-l-Z<NE_Q-o#z0EiE*0AFoh==5dBVpLOG
zRlF;YH)zLWREXMo=9350Gy!k>M&uFu=OfaZZ!Su<C1yURs{nZUX;}LaPQi1}{6-vJ
z`I3Cj+2nsp!EOOK&pEEE#ZaFzHzS<qfzz#Wk`Q>td8R`ofPllVx3zi?hwmAz)COao
zNZnp+jfTPCp7q&yT6btwK?JS?{c%8!!JM+-la9ce!qo<G{qI3rTVH7`+~c)i>N2BA
z<(%=(dQ(GYS#Okj`&3GPY}S>WHV-I!sY<W+dewbP>|)?0plz$pcV{%&BR33Z6xKh>
zr64C1;7)lIfMbwX=5nLdRjXSYJGBfZkdcCL-D;Ho0CT-x(25U{n;rU78YVhC3Vv6V
z=hf+_Oo4bMkGAU8Z!8YKl|tlaj+9)h8UFy;w%dQ@q57IZrdt01&m0eK^>`3X1(bSX
zmBPg%rrQPkhv}My?cy2RY#ZFxnVups$jwAuN$Hd9X@!jCwv^=g5k@^!=9JkP1{)uT
z6>zsX8RnYOFyeqI4L08=D9nA>)S?K`U?Pvgq%xcnQI;lv3<Vt&eiVh9G=%51H2Y-G
z0<#}_VUf1-P6ujUfYNY97ZB1(rsoGV^0^%b4MulliU3W-deRrj$74Xr9<+r|rbPfF
zHgI|#;F@TDaslR@wU5h=Y9?2}9FOs!0QSkvH-Y?A?T2U_pTji1LlgH%_B6nVgX@Z8
z5~i#Rc^Lh}k=l^iTr&aWzdoXn6-#dRrZGEe;jp+Me(#?29XfCB;LrwBpk~cimLNy1
zZJjPsdSLs~HjyaKS#UcF0Oh5F4YX#ftIuyP_+~M<>IHQYXs!qP!}yA!HjOcD+weUI
zsc3g5(|k)T4h73$d$(g<y_Tm9+)Bt)40k-&n@OeMm2;m_nz0St-JAa9@Qczh{cAZy
zw9if_Aw#hX*8{yxz5y6jj1PQQBcto7Bx;uvZIJ!)#=5IG?Vd2^<hql=HO$tgshW1`
z8UgxJp~GUH9wm$gWyhv!6?HOT9G_}PWw0~<0N1Fl6c}7&aw<^i&&)oR8%YZ`$9$IP
zqN?Jt;+``=n$c!myO*_dm<0Fd*1hs?1r16;G?A(gR_pmw)8VDK`L{+?_1#vgq)SJD
z?ZN2B@TCw+Px`4p@0$7<J|5aexDvvj@EW+D1k$sHxLjkAflu0@a-TV^h0An;P2EC~
zPa0+O{o7YQ-7D#Md=sGsJDo`Pp}aYvMTGzydI~+La-TM)g{jH^04|QdQ&T5~b!h;_
zu|Mwfiuye?-3}JYMi~0yoCc1c^6&ouj?(s_%6#fPC90CZM%f)k!&1lK%~{l+DMk)3
zL9e1#T__GMhaS}Sy|D}eTJHL;F-zKyl=<mA2dgmzsrDgi+<y*rX%1VC{{SlVuX`8p
zqWreW`BRRg!Nh33;8OOiIZq5vhFXdH+mAf}Ju2K^3U1%;Jfl8?rF$^dCG4sBQZA!8
z{vZ$gwEd$WDdcwgu}Lt^hREq#R=Tf3TyfM_DKrX~9d|cub*oU>P32}bAa%g+`PVd{
zmdB+TT<)RN!=@dx^zTb0#_`wX^sai$OB#ITx(tKsS5V2jZ#W{cXweUo3i(6DShl)w
zyIACU)GKa4`MM638EuV<0Ms)P+N#{kxlf?{s<X~^fz#<#CAh-(=9r3(zHQDb+CZbX
zy;rkgH16MpY6S<UZ%Xv=@w5*!6EAqKVFh@=r558njw*0{dQuLR&~n^7g!)h-1DaBL
zbfr*vpa3eKG1t8&(N7zPZYaUYqQWBE#~G&(eX00A{d!O`r;o;%7`pAJ+AN8{%JZ7w
zrHHJD+}EjGKqZK$_qa9ZTC4&ar$RA<gM*H1o~r6}QjtV2r8u_@>xyo1-}9#KC(^mj
zk_k8G1Fcsf)Pj0d=3X;{%_GC|{b}5mildX<QgMzrsU9PqKU!%Udgng1NRqQ0o}>z4
zc2SJyo&`-H2cgYLV;aeO2brCMMJ<Zxq+uhe(CuzCEj=&g*cxIuVT1m9)up}{7q2v&
zGxJvNFLd^@OJ<ljRrzv8Mk|w+?d;vdKKSrHVbZ!Gxs;C2bWa#`ZNQGksNKp6k+*3a
zb6A%8gmVv-@O$9Y@;fs1CqDfvV=^n2F2v*<_pIr8ZNsHmownyM_-?9h<gR^b0UHbo
zgyfUOJoOaPaoidP3fsO~w`Xu-Zz+f<{c}`0Hbp#u$((aZg^BMW@*ml`6<lDgUX1;w
z*I~(Z92%q*fx}ZkF!j!VN(WA9><3_KHyG<o1Sg)qg&=GmqJmGQH1(-qPLdU6aqCiC
z4ay`?aop8qJk-%Xa)j`E8j_0S^GF+M%@Pf+R-2QGR|8hoV<O=CW~F|oHB(O9bJuTt
zR*S|tBN+FtS?*dWNHBT)D7T!#{{YZaq(XC*JX8jtvsokzpy#h*DnuZ*I{VgS65_5z
z_~)E@PzBuX#zrV?t8N0Aua)D9c=^7xhID#8_ETrgyRoj88AGq$$j4k)pIBTyyt_sY
zPu9CDDb$6=a7HU8ibmXd;MK^6f5xf7hm11wnz<K2`cfGt2yTZN=Zcv}BOFtcf%T-p
z2Lq*VO_|LXB4e~-rw_OMDx7>O<FBPWHZl(awKFfJ!y|mXeJWWW%wK+MI5sisQ!Kp&
zAUx0FSw**H4pfe&yoHWQ$3tGB@hafCXtT>5xgVW*dmM4d#WbuYGxMhp@@Y8w(u3bM
zLLJhK^GyeyKROBZ%>W&L#*UPk_u`Zs^rQfOwA0r#;(e*6fD`qtzYFb6LwoWwo+}cy
zv=+tE{c5ARGuZWuOP}Hd4xKAu8Dv9|g2K4VX~W8gco`TV8tN@JzSUF3ZgUl#NMb$l
z#YKbv0PC)`JUef77XC8b_Yi3t!ef%MW8Sl7@i`e6bY)1cGW-#6<DbI4UgN_T3mIe~
zv*<XlG}kO-v(y<STtD65aadJ4D7{DNQnV4}hU7dBYh0`o46g_4RP5tJ8mj@)tcb=v
z38);kV@;_i<!Vo|xax%d6#a~PHa+NNomYm<ArXipQU3rQ<LiowL_wTJxE|FhY1AKI
zaZoh(O4%`?6oyxp1(Sx3vnSHx11;3m`DeRv_dq>zPfE_3E5hZAkHmE}&@!afkf0-s
z)?MYyR^t&5nDLX+v?jBWj$TZ57_2=;C5~P`_BrOM36!Kenwv*cNmf9;xinEh6aZGn
zhGUStQZ_U9b6Dn_j#b7B522(qb#EPwyq`JTN3~4_<d<@J7BClV;|e$xPRh~-K=;gB
zu!^_sd_e}C8pma52w#+Z)dd>bPlRr62c3LQ;@|4j@CA0ZdR?`YK~gmUcRg#7u+(+y
z@(4tM4@~-3Lu;lpVXkIr8G90Wsbe``h#G8dvUpS-z5OfC9RTTrUe)3qIVaKGRWpk5
zi=F8+hEND3W74{5OG7E54B&cGNf@KQN>d*0d994b1D{%%Hxb+Lrmedk)oKeV8HVfu
zR-(ybMnE+6Cw2u|j?OgYm}mQ@mRGm7P)X}rrD6uGQZdFj^{EZE0OvIuYL?2sy9A$1
zVynriJc9sWeJHvWi|Gmjf<Qj>>_(#*6_m1EO5VfU6*^kGa_)2KnrVo+xjF{HsHa7i
z-IuTU(#HS`^L6#7>>qa^des6shFmr}Q$<gA3nk2oK^Qd;mes{5>U1V3#an|Qax;;@
zs8SL+Zhfm?L$!TFShu!`O9f!ZA6lfWGu`|jwhs?mERu4n4o}j$i)o>mcy(?ta4U$u
zg|w|2BxR7s6e%O9towahc-t^a(r2V+<;7*}+_gFvFLS%pY>m4qw@im@w%#k9@f6Oo
zA~pup$6ochqw1e+(^hGdYmTbN(z#C%Uwxwdx(p~7>r(}3Seg7MKRfLux%$?5a>uWF
zvvk>94o_YxvI2Uk{{RZzn3Kj1YVErG)mk712d_%dw@^Fe`U;RbJsLmsP~H72T^IDM
z%_L&YbH~=TP-cK020iN39YCm53{>!BN#7M9U5}+qqnc!RJt}RyV>Kf~vBe<k=|DIb
z%{UKA0C=far9`8TN{~`x9y(IfM@m{ia~?YRbeIl5kF9xjrg3v0ve&8j=nw38$>(d1
zmF2pq0H?1!Pz83m3b-{~+-^DPP_t*6YaEYSl8Ks7ed&!L6#?Vgkx8P!N?w>xdQ1{P
z;+jD{DcA*Lo++ELOR)FdiUJW#LT<?C^rOE@QZRnByKz8-#twL-BfqUXW(U@cQvy73
zPEnrUjX!4wnpd>|CI&u~fpdy?G!ijD3@ge0l!SBMqyznuXb4E_K**aEfRDzcXmd!g
zqMVR3Knou)hTzi8Zn^m+4VqU9>N32J^u>s7`9%Og(A+D2>6K5dWNPwVHq^La*zJy$
z(UY}tT*j>+lJEk0X99pS*?zSV;;k`7T%3&iRYz>Gz@#&0L6J;`Bj1r-TqA3*&5>Mx
zhGSW^U5~qNIs;ygG`nFRm@}T(Y5>k=ApF9*Uk}Z@k8btPPJv$)siI6{kYlAt9gG(#
z1iXfBItpdxumlo$Q1TS=aa9$t`?}Q`@KQiCT$L~sYR{f)Qq^fiSsb<L4Kp}DeT!8F
z9`&Ph7%ahtFlwBT?H^wC+M{J;V%^IYDo>^>NJvM}RT~fpK9yfl){{?vFYK~N;PQUx
zq%>@q449-Lw(>x(GWW!~v%W2@#6bFxO<~;K>ldt6N0FVm+7A@&!pEaasMy<v^KKM&
zAXN6?U9XuN4TrvK&-Bj^-peYz(=tT7;ZO6f#b>v&x7r^#{t?!i3mV==1`CDvs`6RJ
z!2HCH_%+W@u4->4AhabtSFUQe+dM-r@VfEsOh;67yJugWwvS^~r?j)S%P#pyA9k?g
zI@UKCj(e^uPqk`81>7IQGz`8kH1VC*>^SFxM7Q>FugPrfp4i1v{?nEm`Kca#>7&G(
z8;ApX;){W%s@E%+;V4gIPX5liX8!<>g^wM!aaqgar2vm3IQ8PDPZmN~=7rbT3U>od
zY@}7e`S3dX)NgBaLBK)(00GTa9x9I?Eu@F*iW9{O@&t~~V%~y_fgrTGPOu}NU@4$n
zJMA{`sL%KEMQU5!+)kvmh>ZIAnKc~RWt{F>WE+oPnDbKD>`AA^G%|eVJRkO{_mP*G
zT_lfa>&;UB%CJrrCg-@3s?D{nlq-P={9M#I50s6gX$BT8`07+u31XPZh^=KLdM$L(
zPO&0|i3TW=b|jvkN?gIpRMT2ihzU@t<Gopz_qiG1j&atQSh34>rW^ysD~`ou;mcY6
zV?67gxNOtcM1}=bN14F>`&IjQ4A?zt_>D;UN8)I>Sj77SM7T`j=}NY&-+oZPtzVza
zRy9gfA;%z41X97}5w-UUsd0660L(v3nzj}~I^@(&gaf%hI$&Yk>zAT3%-F}Mt6EQq
zV!g~$4X(Y|;-l2G-?Ur5m%%D}R~2y#*7qbxpfa8apbu1<?V$i9DB0u@RbN$~q9U#<
znb5pU(f<IW-W;#@$m?B1A{)e6E#yX4?Np>qh#L0g#!nxGR(Fw?nKv5O{?A}X-XwJh
zxu<_)%y3c(8|b+-?kgPoiE)kZf!j3+M+d6|^{%Er58gi2TS<<4u*Fzk3g2=JA4)?w
zvmA#!8c(yi<fzYT?ni~MnYM_=?);2ZxcnV)xA%_{pJGh|x#uR)&+w5zv2uP@&3b6?
zTqUw+Z2MHn;EQfIw50VE0p-i3vFC$IG{Q~-W8S@Cydhy1GA=%i{sNXS3~7pYeVn(Z
z=QIV+C>m%7=4z2N<bDSBKFCda+IW9WLxE=)#ZJ0Snt#i>QFIqPk#tSor@jK3nmrMp
zgtd|X0N@y}TT5$YJVKfJRG()Ba1lWC0+qt&lqQJf!mYa(^xAm+D#Cbb{m&Ln`HJ-w
zfGX_@0QTaKBp%J5trrU(aUX>5xc$<vvk_L4!S~IL%>w)KYrb1_>#z)WsYGZ-Hi1RJ
z;Zwo#DEY2qR`m;-vmb+(7;DD-5LaR3u0N$eVu~&YD!vZ3&(CtiW2QK%)53ac{{Re)
z_}4}w1GO&CK}z9c0C-nRQ=cUMJk^i*NA&eylGQWWm}a#6l3Q~UeX32Zx2NSr$73=L
z2EsPo<RNq1ing{euSnxj=mlB|MK01sD}h*BL_dUn0-mv;?NYcS)O*qeAau$1G+Zn|
zP_uK8Jt^f>3<bxvIgUQ@Rr;E1NeYvhkWp~3fMeR7w>dki7Q3}iy>Kccs9GHV0Hgp1
zpeBH^FV527fT%n7H73#j0P3o3s#y=aHh%+A{{U=S6M?<GIK=^DLtxKZP@eUab^B#I
zMZC^)j4n?<l{o8&I$1wX=M<RiY3xN(#GXB=o68&pHJml|$NYPL<Mh+w2f;DhqMv#K
z#;A`6rYXWMYY^-AIcy>-_TrH1*LVl_dG*BsV|U5pJ!&~5j@~fRvkdSsxvVzVFIZqW
zUv*KMuO_E;Bjx08m!$z?rj8#lZwPtzr}+*KAY!>gsa_F}Il%hVPjxd9x#T|Ok2Hs4
zvDiD~^Q12lw=Sdct}UgI^=fExrv;nyH0%dv*EXYYH&Kjr=Arv`oftW~Pr|uVFEtxV
zr2746u#Tm*s|Dmp&Og}|5!bCb*&L1d*ED7Cj8jCJ?U72rbT8s4!8>i+{`#n&#AJ__
z(5d%&!Y+4ky(#<m4w$E5nx|i%s>ZAO)HfR4<ghxiUVDLA#QV}0z&QMAGzS@~D}AO`
zZdsc-HJ8uQw{^wD=Z^lBg`Baa0vS^Mb8g2O_N;Q1xjJShCb3C7k58emOA9WBGBfTt
zl93KgE#hs#{VE9C2d#8pQfyiy9@P9X=}{@jsh6Hl=UQAtN-~aU$;CMHj%mHBgdGhb
z9Q38gqZGhQb4EF(Kb<HY=`bQA2Bd)g^BsMu7*nD<TpUyY`N<268mz2w>sIG|(2<T$
zLsV0i_o-t<;n)u1kdSGhkSRy5O$cF%2+b6^st~F$I%b1P4{8rJLK;Y@SYYw_ROXmR
zttK)sPtvDOMMgNMCPC}P3t%fuaWTa{H^`=3f?qwVG<~M9Q?n|?ywFa2(-pEQ;O4hZ
z<gle5r6xr#a%)5)MO>Ov2;fkFu>zjU&-AJ!2P4v$>zwmb?ZWn`*nFpq(qLD|e)RPF
z!=)xUr$#=1YLbHG@Vj_5U0SW&uIR}F6`nDZSk6|FNftrK_owGQ4L}ZR#C<vnYC&LJ
z=9dIhf^|IwNE7ABs!|n*fXh^yc%Te+#XJwjuH=mX=hl}Uc&Dn2e6-*(-zKW!E3o(d
zDFTf8)a<`EwIE-cIH_!Ag{p3d5%j2T6XqZaxnMB8Kp5asO&27dGg)(_$I4|D+t-S-
zra6aFiHYHkDeo5?;M8%9T*r^R4@&37$}^=TX-euxtk^#2RDr=9)y(wjGgx{};9E$Q
z*lyd<brqs+<J<r}eQV%qVdc!vWit6ZQJnt(iK?dQ2OEL+r8iLp&zQB3)#N*pvE#25
zS0iz#X4Iex-@INu#Zwxssd7Bz{7q>LG}72EYM!3e425=k)hE`p=+p+fKzj1Rt4ptG
z`*Zflg8u-$n$|dZ_9e*~z9VcXY~zk=1{;ttcLF}OKZ!MKJJ|e~XDyM{dR73FXa#b8
zv0kk#BjiR>s*a*NoPZSM`%~p$>DQl1<>R|}+l2@4tFdYlz7xyf_9nKahLmS>Db!6G
zsxo+~7-V&*p(WSerD8T<XEo{Wa$M1}kcb9J<JPyKxXr4!rx+E>+Ov62vjwrhKDCi1
zrK=;D!hku!+rY0U6@ztWbFP(W#yXyh75A2f(=119R=hXL@di9+)Yp-<{;>UL+3uqs
z)|zM49AMo{eSdg=#<O{1aZ1JgVke~PdaNlX!6ae7QYx?7qua}%9_GB=tuESK^4z~a
z?V1+R@Hbo*!QcXE{{UubxW2HDL0wY9DYrf3OSh6YignM3H2GDdOO;~7w>TBS$7{$f
zBOh+HWi6Fh9nH;a48Aekmx%0a2`x)A{jlJkfogB<D`>{iG@pXjKve{seiXSMO5f^~
z`w{J=Z$qzG!w^<!*}Zo4saM2yEB^p4_hkP7x<AIb(A@nhMJK-kpVcY$7q*eo4;0yh
zfnjidxTl{L+2cRibCcWVu52*&qjwzis#tg~g!@Sy8S$(j6>TBN_mlqstxNv^3Bc{6
zDE|O~3g-#Qq#$P%s-~92^RuR3h*u~!#id|>zyAQ%r;ms_i8x&~6#AFX^sZx^`%{3(
z;-4UM8|~x0ZHLQk05s3|PCP(I%MGyn>kujRr5VSs)}JC5Gc}vWo+Ll>@A*_s;=d5T
zTZota)vUrfrBV3(C~!f{%|-E7h*?MaQVf5yO>YwTf=|7u6d&xUtne}KOOE`}$b*@Z
z$*5`*ljmRDwtw3oepL@F+nJoP?pr2;GwV-S^Hs`)b}+<^)kb}3$!dU>UBmIIf_*92
z>+4R!xnIa$c_%$`XfQ{E!+v!+;B}`)2|alAqQF*bc>e(BnxCkrt)k;A5|44kPVR_u
zppSgi5;1<}ki=-z9)s|x*%z(}%_n}e5^;>s1Tsg1o-^rH9xRNL`qb0OmOnTc>6)g}
zam!M$$(4B==B>mRZzr#<WcisqGn1SSD#UTzvwXJlo;Wz7!!(IirWr@~sjH{nxB)HM
ziS?-mhjm75rMjl><+@W51d{@ADh8Ye>6+G03hE3&mf|GO_g1Y%;LYk<OXHtFC<C51
zOCKc(A6j3wqMo1**)`Nh;R^&`-aL{K-==EZULMk*#>iXixaNSd#T%%|7|Rpb8kHsm
zen{kg*i<CfcOIQ$hbwHE^<kQ_sS17AlkgN=c0B!JzL%7+l#aylRw2@LxdHzGL<$f0
zjw`z@gZF<*Kz*qNjyXIzs=wZ7qx$nxFNCfcvo@jlEOplgJ*m5iJm>SG;<3*FPeHK0
z$KfkvQRZAu^=3Z}>GAXBGkr~L4yK#AvrKj?N2XdL{I;pbPAYYQ5PYzp`U-aA^faKc
zA9{h<LaYx(9@wCv;|KDmXCHf-Mj507LgW7cuR%QUDaWR1o3e51Knf4xK`a5mG@C&7
z`ctqt8OZNI0FVy9ttdJ4q}sIQ017}i9Dh1qpGtnvPf7^w%>Xb08}O%Piu1)dI)V3d
zO$<rJ05rRk-|0XA{c22(o&71GP%%Ir{{UZF3H6|H_|oHy=b8i{>?sdFDB_ghV?UiB
zY#ip83PA_nj6MehQnM00kEJu9pa<-KYGG*wF79)hUCYy@0~m4-si2Z58*}eYECArr
z5S)=owTPwMeF-#WyVC&*lg2SjDA?;q%ntz5gOSv8KnNo{c|1~W=YvxDjO)qI<4wmN
zlnh>ria-JFnm|eGP6TH?s1So@e(z6uLaNy`{HYu+J<VimT9le?nRxJf^FSJV0UNgQ
z>zXsSwRu#&Ik`KxJmt4>jkQ_)ae4j82|deWG*}N_GA};AN{ysJ=rPv3jCkho51k(e
zxqQ+$j;^@ck^$`46j&~L_-)IPfCV(ltJSN=WbwW8kQ5$z?rMzqw*B{Hs{_v8GK&Sz
zV{51hz?DmVYP|Y{Ht1i?M#pT|nA_{kJY}87sRy+_;`ZuwDHeUP-m1d6);EkB%zr6R
zuSFra%|zZPyk^Kq*Bw4;^YiwIiQDEMnDrRv)}w2?<v7fTw;kxPu65d`r!DfG?Y}*R
zV@SCf&*fAtB)MsEB1ix|NUcx-Qb5ir*iDoH*(c1|$8TEcJUe`r(uR?MPu8%VF~W@d
z3Vpu~@~&InlR$bw@eP69^OiW^V-<@%z`B!o1xG+Dm1wmVVnxEJJOHa(HftnN1(ri0
z$0YjGNE<9N<EA<3P`*Pi9qPe+j@1n7y+#Qb?kR|wP8Y9kf}NcD(nrbz)|V87Bd%jV
zO2U&?O)}++@5m#k0jqeAl=rS<SkvC>Q0c;tyb93DMwP#eMZ}vUPznC^T{`Qk?vrr?
zu&!DS5@b8ybAPjpR<DyHj!@7tS^Q@VLqBJeAoMH!YP)#hdBwAz!~X!UO?^Hocs8e=
zP8ypYlW4p(o^i%l=76}3<CD7|V?27cDi-mz$!x`Fx%J&z31wv(@ogF7zcnI7YZyBq
zjedfFxt2U<shkC}2j~rSx=q#IqX?2n$zn5|xT?{VRrwJI(Q3>(i^2CBoPJaRul5;8
z&z9Mz4LaoGY6JB(C5E#M<yL1!Vmj8c?3q4C$UO+;QUevVyM-KuG~evGer&Re+(@>c
zx_=W>tP#1%IHKTl%cU{SWFMAkMvzW_dNcm*ZnSZ(X}>4}i-C##l9=X3^yx@+rR^d2
z;<gx##{pF5ieqxch*LlrDW^t<=Vm`nDp6r-7`K=6de(`->Y|uHrZSJ%t+*=~%`e%b
zQ}UpzEg~aw#F|4Yvf*-j^yxql2vHaxB}01Ro3wv%bL)zG7Gs^K6o+?Bln7x8TOmOA
zq$}S!rOS2LO*v0LaM5roISRjbJkn>5m3B-tWNjq+nyDhNJg*dhgn|Zfk?l=jdefd(
zLEKbkM`k<|Knb;nKgyz(EyJ82txvW?(0+7{8)KSaWlv|7Ju5a_OgB-H>MNm^5_+~i
zl}cMZ#|8fYIxGi0BpzFm56#$vT`!0AD`%L)ag~w1dRAoiV|EK1`U;}<?58WZ5ONrH
ztY=L#M9*Hcv9g*mBxt=kAXbbP@k8>euNCH=AMrfaZ5%g`oOCC+_pd^-)vT`K4zs5{
zfz5Nc*wHfaRVO7!<v<FjAOLAMBYoFX_|uNi0WO&O)D$!};(0v#)R`mKk9^cc;|Kj>
z5&rcJaSEK7kPmjE!X*cs=k=%VCj+%mZC1fY&3PF7YBtui)yX$%eSn}1G0%RTC?kQ-
z*0P_(I%;*fCp|Wd)DrlsONRu>AqT!WrZZ)L3USlkt4ODIMn|<|j~3WT_aeA+=o2)j
z#A-2(I_UBJ$~jmzYbxhGaqUl7@PEd!hlpp9eoZRq{{X;vqx(-)l;Je8eLs1FM<WZH
zqJVx=Sifx7j{`~_dU=aYGI)|kIJUQo{rAm2Mk|}Uwv6r=GzmsIZncDA@iVXAwoLmI
zRb{pDGZMaZBi%Eae5`jk$>t3yKK+GVw7WoX_zT<GsNKiqOxua!v5!iEH`;NUi6g3<
zu8y`j(Xd7_jtyN)gxWb6UUDmsisO=Vmc}zyQszfET;j24-se(p5&lt+!l}tHB<&p5
zK=b5ac|O9eBDh?U&$-P_g5{Gi+k;eYor<<HO;3VP-OWPKob=+VC``YmT0fE<i1~*j
z-n14issa4P7K-0yL66R+!7H~MSFKGY6UeEonGsAJQu%!Jr|svaKD1+xTC*X7A<ZE{
z*kYyI*V2ug(iqKv^c0vFsj<d0Oe@U*FbtXk^&AR#UMWDy`?SPFS3iYvekidEFPsP0
zj+NMAv$cCcb7uR4F#{V%dd{M}O)0xG%iRL8^!2GCRNaj8R_-mwn#ANBk@WVezEcJm
zJbTw0JCSZEH~M>3hPO-%ATQG=tyPKkoS(|3X^&jgjHxBMAvw+}r0diHpQjaSNpeW(
z&#gv&U{B#xiD=C!hva@#qV6~!<WdbuF;IEq@TPyDV3Mae=xe5%vCB|w&u?=c{{Sm%
z=brhf{KXNnhGU+_nKZDn;w8t@tAoI;l#E*>2Wt|i8@(%54MCG`PDVTW);4*o5u6Wd
z)-0Bd2Aq~8lY>#S0zIlRgVvX?de8;x-7`%*^PZil*!Sk6JwWT4E&?93M))}X8fnS&
zG>7y0P|y|;{F#-(IUbcY%xi_6SZ!{ms)pQ{$2DrsP3qR?spMvm70BnUM#CIblEzWk
zR7XChoxoufgq-tAee+BwnwBx!so}X&c&M{a2Ru|Uj+kYE^`@kI+XJmi5Xb--&uY`N
zvH=4c#!@LDvbPZr;y&1`#W*d`y&DEbMNWvjNFz0qcPz}Ec7kzKWE_qwTH-Ks#y=X(
zWyeFsNX4^_C6i-5+|<Qh8H{H+9lb?C1MQs;L7w%ssap$+SZ?Dda2$cx@umfIY>agF
zs}T>B)d(MwbDVnB=nhZTkP_o-2IB+Pw{-dTsA4h+>+e`H;0lt~;GxETUwVdGJqu5q
z9g0p1bgf9oLEk;Aj?*tT^&=J3+uW>?2M4Gbs3_16fsf}?#>*sm!N{sXw=W!2w(eDc
zJqh)ygR>??#4@keg^_`&f&w|gs3t=h;<`*ni9pA_D%>iZ9{ggdFk*Ah;Y=tMU5`v;
z(-G!B5w45hh{g!t$@J%n;Fx`Ds`0GbwMI;nx1ZLzMmQ#!B4?k*oC&D&PhLKh#4mb7
zoSJdzOgxS$0Ahj1dQ8zwVuPAOJ@ZFeP&?8A57xGHA&E1Llj~U7;<YrUWn{+#JesJJ
zEsm-XNe4C8=z*lz3z7jG*D-0bW#C}vxUQQ-n8hcQql3Zbw?{KO`)lZJV8ik|9+hG}
zUe-gyp!yuwIJ#)mm?q=T=~BOiBmj>*;Qkeq&8eLlY8J%vC<D^G+s2W_CaW7GWERQ%
ztDrs@yHWB?Mm<=!^{icMMw-$AH1Y>vbJPC-uUSh|Xy{-dz^Ru7Y9qk+rwmqRgrMWS
zE?c%UQSy3Iz$Epl7!u%a&q`|+Z%%4Kob~74n#t?>Pz6~43PT#FFhTdYHF{LQ^&_=s
z+z*!@tuQh535r1=LCUWL_O3qSLnND+<esEgTYQ+ck&5I2(zy8!Td6-<v_l(4MJH-n
zqC$?8QPzMA(y7|O_Y{CpKpN28y~#ul10Dr-dNz-501m+KJo8?6YV8%oY&wJArFuq<
zGtP@4ASvdhmX5;BHm=m+eKT6H-~m{+jLNDHUcD<`7T{KFqST19TgZo_EqIo_VfI~G
zWZQ)-d9QCn!0TRP<LiI3>Vi-{L(c-WqV=(y(Z&lyoa6yggA^<C8mTqgoxpMQs-(#$
zcKTOeH)95i?|z8KW__wQ)h1vSPT!?fSQwsj`BkW6L_IV0s!mK!!YR9-_?s0vY0i0e
z=B8ObUKbxqnPhf7N%pHzC9)Xop;8NEpL(5QKrjX|PmVWp(A3LrN&f&EzET?@U7@pz
zofmNFfkCyyb<Io@3)oXgL?J15;Pj~oUs@k%1E0e*#A9lxi6-NWky&PC>?><kh)WPX
z2&``-Jm$ITD>Hg;LB4Cg1#})0)Ei3H1=p5X5ERxlaU!rMt!UZE1E3zgO+~acTC>^g
zJ|I|J!pm_93cN94Rc}s*s>}9^X}p<7-tyYH{VvTWu|_<D$<1cm>Apm-EATV#n!!#{
z*y;9Zo|j{CmYQFd(+Myz3F>Q<x}VII$mgE5gi>i0b3A|!n@JUY7_2yAPaNi|4(+y0
zO(V)haQmAW_NK(YFTcG&(upQG9r2S^;ZdHIce#N&4o82jXhZ<Ucoj-D%Z`5vzPQNs
z6u{}U(f)>qy=cekDvgqnWgbBpT>Wb7Cp4HAm)5LCI$%|GJap&Mr;De*wMzo@WO~%#
z@l~QVWqVQ>y#+aXQ%wufkP{EBJabG0Q^ypBJWweCrKATn<6)f$`iB+f_f~6l@|P=)
zgmte=@u9|sao2dSIh~|c-4`@~qy37R`{(IP{fM~x=kXMcd3?vF-=#*^cYyul&#f&=
zBpMul-s|g1G$iB)W1qsPKBsUvE=N77r&pZu<{mw0)D0!jEzdcSANS}Q6e>9^IsW!*
zDYbioyhwj4Xw|L<@tplJMxbkr8XSx}pQSalX!FMGbjhs0?Ms3_`wDAnbKvBYOh%vf
zIuZV{iKF`&bDZPU=CTf_Gk+Hp!+A3dZe!m$rUtv|aG}SWlTbCBO4u^-^yyiRbt&(U
z#}v~mk;@;>ftDsHhYH(=uS$e7x%Q~UfOpTi6uy2v{b&&(k0YFPr4fP6KyC>*#V4G{
zzfRNvWPyy(PZdzi!jR5$Ol6|LbBY7|RYNO~deF1&Zk$je;)Y|w=B-6)?0#+qQ5uA+
z_f7|F3UBs}&p$EG<v<#*X#{Z@ACkVc#oq*$@tYU`oB>+5clS+h>g>!9LtMPq#JjF>
zp8e=xi*nt@mgXdlcY2;{Erw1{6vmlP@fuWM?Zb{~4A=1O%vN{h<tjZ1?rYE&QMU5I
z^RbcKb6#YN&<;&>mPqXu<|I%C-RyywFg$wI-5OA5P+N>vGabr5!mjDE6u48n7$Sik
zv6Ui#yoVfDKXb3g6S~J9PI~6HE`NEZI8ZufxM^*%Ase>f(?Tx2<6OC8%`x9`=y6fo
z01i6TvTRdKM7nv)6+Mkm@eSlw&Whj?#NeKSv^4Mx#-rD)(q&gFKPo_uGE4T5^vLVQ
zO=ER-@@$0w1CqwCe`lvx0Y_|#HzXjc{*;O?o6{Y+1&bcMaw>tmexoG%nu<@Kr|C@E
z0+Zh~&=!BSZdC0IDrmKvjogv!PB^T>pk}6m0U<lPPzCFqa^yxrV7IBoWy>b5c3bBx
zt?n1{r?3jgj-9E|%oC^SKokvzrIYe~2yE1eWqG)7jB)<eX$#OtdUD>3@-aY)u*DQZ
z7ck_W#PqAlJ%TUG0)8T>$o^|?BlDz4^FSKusoO97u^)yiN7i5pyCWca<E3MHe0?dn
zq%*$L^*AJjQ_aI;ocE?`CRaoDX+UngS0iH}jzPGRE2*@e5}Sz_q%#KQ^6EVKj?3>-
zX<GIi#X0Z6=~{Y*mY1=)PnGe*R}Xb-HlK1*Wngo|4u+FMx#_T6dB7YKp7lSO$XejE
zy>>_$QbzfID(WD)S(H9=p7kTSu1F(1QwYKKs3Vhb>w{7Z?&masvV{j2=h)Sl?n(?0
z#cGIr4wU}@Gy%w<3)4v)$W=)UYLmer$EU3#%jt?d_Z&A*r2r!%s^kieLhiU`$@Hs9
zEN(WFwwm#%JabG62@<>E#}!Lh(QPl|z(B2z4mquYsyXjSBSzr152>ed9$%<wv+2_n
zWn!b1ezk8))+V%d1fMI|S95u19I9e}om;m`=dOGnWSF(R!l=*64ow3){{Relp4L@F
znSckO?Ooa=4xVIUHdD}!wc!??8@|)oKhon04snBBzKyP2>CGBE-eM2ElS^S(^bo`y
zsDmHgse={+a2!=DeNxVQb(enJ_3ujht)l+`%U{S*aIt8r=Y;}*oc$_^)olL&=c^Ow
z1tHe$fcZBu9`syxFSBjn55kjiBbv@S%xrkKZ2FcI*4B2mKF**H`?E#D#+Cz7f$3Q1
zU2qQA;~x0UNBy~UPYW0y?$WrdZtOkQqB0=J#%m4ri<t%;&(I2C)Gh$w$R5Ih*yvSp
z(LX9s82<nbb1i*x$M3i2O*d1MmUcgl0b{A@)Tlm$((h1kWRL#(6~?^M5^(Ia2axbz
zGy&I1G$4TYDfA6d8~a560G8^0oYynB_G9_d_xt!h)B(|*Qpj`X5`6$UsE)U2r--LD
zfDS*1pRF&L2XjCha%-b*Beh_A9r>#1tU8>SGJSKJ%{MWq`<XO`<Q|DdfYv(n;NT*F
zdL6wgIW_yd<0BrR3e6V-AL{W<XWTl`VVB0Wc*h=WpI#}is@;%4nZGksH*Kc0ta^-4
zBGYOYJd*6*xngQ2x|y3l)}sta;+j~WT3|?Bi2Lk5hMHG*Q=g?U<aDI@y5x!nam=s%
z;wTHpCqGk6$=%kICp`@Ta&G--#z)Q4qU3a?P{)vj{*(cwZL8hdCdkZtJ=USRy?dz(
z$P;nvx204J!Ff!5O(RK;sNY?tfCAfo?=){FkOJ7kpT~-N#O%Zf+@E1U4BS}zdWuq5
zFR!&swpS;Vw~*tosYai8-EE{E!j*#MRgshtj8J4Fl0Pc8G@HUR<jM3nr>=>1%yNN#
zuS{1nx02bV+;i5oSHrWOS(E8bPY${J_Xr2DG*~WVahjBHyaDyCrSR-%yH?|G{05{N
z1S9@iKj0_}ocU5aQk2N&rF2o~mcfB9A@|)={{UrK#<^7`k3*i62<5~MdMQ5i{{XWx
zuIJ!aLNus<jJs#w6(G}X00YZBdbVkS%9yd+k6Lcru~GTgUbfcD(iI<tN#&pz2$=r>
zbWl5-aEZwW%VG^Fwz+?~Y~+10U5Hg)in;a}rwCIVib6ck#5!%rfK2g_GtPTg7VC)*
zr_#N{#1KU`l;ddKjtCXwccT(E;4&E0uZT>gFZ!}De;UDWmB`?F*8HOgbNSX3!xJzg
z@vh7}_l%@cyj}6`9YL(lLFTqxW+on$j^hq%dXCZ(CXMnjR*>XYcsU}i+sTz7kLOxK
zcN0YI!uF>6)QHfG??0|7A8M1x1Ju@>!W*8s%>#kbnn)P=g&UXq%6^8cm_vZi;Yu=1
zC<-{|@}`GS0OtqVhQL-h<D60syiiVg3diUvS8!koF=N|lsOBAlL%K3MRV8dOtyddj
zBg?@fjxkwn45m^RCnWy>vx<q!P)K-eif}pYnn7)KfIiP5snW{yul#yH(C}%gplFLU
zy{b{CYB<QVe0uRxrjw|*{JOCGML%f~ScMdx)cw7{=BHgNQC<bBeqyXeqG~MM#jtwr
z8K><d+$>Y_8*WQ4&{au64P70!nLI&+skq~{QJX}(c^H793F4*IhjG}*2R-V<5v!gE
z&%Ik79lawyYLB3+Fz8n(aL%9aQueX7<K;3h;0hGro;#Y&=xeRI(5@~JBF=y)>PBjT
z@U-OQ-ADfbeAhgrx)h95e_F7Oky=0SjJl7S=w$T5)4#A9B+uG+A5FDztzk50fyFos
z)a_+B2Wk=rr+P(!!TFSrt#m5UBElk&!yPJSOf@<<K45Bghrd%+s>DqYZQ%2oR9uX7
z?^B46@fwymSDdqR*iw~fuArjK*%Rh8*wF9AT$0tvKA)XAAu+IGH&$;E1Xn8}Yjfo=
zJQ~Dvv5)t2U6KWy5Fr418gyD*Sqxx{p7qO8wdHcsIOLT`<o*?Y-(eYW;2xP=b6s3|
zd<n{1#H95*M>O+l0Qpb>=|{E;9Kxm;0x&y!)SEZ)gT-$cQZc~K)KrkdHt~Qxg$}o1
zvCRnb-7*Jyd5u(e{{X&oT}P0Z<Zyb@tVj+OK&ADG3zX$^wDBB={s3vkpQ77IT|+>M
ze&{~<s@DjS;F6$vQ~Jb%kiaQ&PyBl@{As2;&Vtzg0N+)(84BbIayCyq3eDA%>ONBq
zQ&lGjrANLEJv8lBZ@($Y>A<b<%Zy+OnE-5JrsFx|qu!hYa069{berfHvfM;}-a%Vs
zKyF7gF<fAZhp9-;7Mh%3pSP;#o)?;hj;0$wZ<G2}`EHap%rT&d*lm*|Bc^$*ohWuS
zRV2EZZ!OzC-|Y!lk4HRywK7`IbA@}mh6AZG8jbXnNqo$<+~=Cnfst2gt_2E|I|<a6
za<S4OKPycujC9;_Od1`i=jS>1tvuv$$Gssgys0DDRr0RHbF(~X_J~f@Z^Y)5X!iN(
z?~2jGGUt+g>L#2*e|T|D$S%mE)9sV^KOu^dtu3+(AkWg8FRh)MWPytI2CJL9r;xCT
z0R9}cAhBhv;n+6Dzl~LRwzmirQ`%dj9_i&(PeD~Ay@-+f#U_LW=)UeM(vOqYv+br?
zBi;^2wOv^-pRHLW_S~}%Zi1_o*(+fFbtR;jnD$}~QoE6&yedusT;shaBHl5cM>HaV
z(Bi52pb&8(`YEXrP4Bg1nB%X=X%tzKIQcD%k7}w_44)|HuL7iWxOL*%Zrp6-(^Asx
zV>Yt$*eNEM34n*MTA2zEY5xG(SMm~4&BJ;gKb=YaiK?~$vTyhktuP@NJt?Jvo@(rR
z2Cx4BKHEpLgHk7jwKi|Kqw3UL4A8)uc$EiQ(>@f`lwqWVQ<K71&-bpPPi?vVX#tjG
zUwS;jj)t|*gl0c}^ZxlmQ!j(xIcvO+K)?NZL$QP#o}!#v1F!2_!@=lJ&3OBLHq^=B
z`!UvOTk*&8pe%D@P)$8$TIm<UI%qu|zuq~iKj9bB<LMUT*Mdbf!pAUVQg}G`p=LmS
z@aDSY@cx<){Ch5aPEAg_MS?dLvGLy=(R3C#x1J^H$MQ7av>-i5K7<<Xg_WwV1-gDB
zo|f>Z+=&N0mVmLsB&CQ86pT-$JxuMw+e+E=T-SO42Z+=1qmXz{(vVo;#kQi~cEU`a
znc}5O4OP0?I{yH`g?6Qw;Pmwr9mRU{^`~&L$F85MlYwl0rK&~IwN@OWjQX1DvPtHn
zWoZvCcKT6pvCWMGQe(8dOYUl4_(pGd4}OR}mo?E1tI<HIlHnJUfwSI=g^pwX5l3P-
z>I`$&<)C;%4tHJ1eQ})ENYiBHln&I;>ccdLV+43c!2Rc)kGq<1@U4QM`D%WyYizIr
zjEqrn*vVfH>4Wb<$g2?O+G-z`414CTfuEX@y}Hl@BF5Suxg30YEkDYL1B74u<W!g=
z=qb79=}2T|K1Dxn(a-@-98e0MN@5$g@}(SiH10N<OyF{G2fY9$-Z&qvH*X#4LQhVk
z*A$rNfzP!7G$*YaNdC0sVC{t<<IvKTB>c31VFZp36rDTfq*Q)DRzHP1?9w0M%>YI-
ziVx*di+N8-+MX<@Jz_tV09V`q#VE!(t0zvnKXxy|oVs<-If#sRrUhKDT0%!$)#cJ|
zU!O1PcM3nUE(yRwe;NSK3<<}~KMGULXpJ7^;~`d*Xwrk#bKK^OftF*>Q%SUXR;y^v
zI!Y=Nrbr|Uz|REckQ9f~f=J{j&1{VkKJcEDXs~DIn4hHpV=HbLJxv)MGtaecu8(Y|
z{bZj^)6Sb`pX1NgfH4;vedy`arEL9z#Yo}F{{VWO_Dey6sDBfh0LMlLwG2SxAbVEQ
z*;<mhT;TSpQrg*0RwT|SxE%PCJa!&}m`*t=arCZ~#RwpID?mup=VJa;0nCs=$MUCz
zkx$${y$y7uAKe2zz^85@r~{W}W>Via-%zB}0`4Cu-CbmukbKI&h^lQ1s|}d^Xafmg
zn2dRDc+X0aZDnEpsDt#a)kj~w*V>hd9q~*IFYNjA#4Kq}pFTe01L<3tY>v4UZuOuH
zRMW0mfDryX3R9*|PA~`KTOjkCkxmLT){q#ZOS>cPr~|%f{{Y!{2d>b5wW%t|ha)6<
ziegE-1n_+*12}0jk&`TA@TUzfOrM+|!nAk&Y2olXQE)Pjj;HU-*V>-CRAUFsW9^F5
z-cL{sA?LUh0iOD7Svvt=dRVmUF_P%sXZM9)1P&>f8?p!EKo!oNZUMsQ+?wD%CCDvw
z^9*qC#{}n!^qk<}_UD@NABi`sEXe{(ziWbV&`_8hO^1<$62=?THMt#@p5PI089nkV
z0w492qPJ2*AMWv!>MKG`i1hnzqTK=Z6*1FOZhVCmfS0#&NPp5DbJG~Dbh=fKYuvFo
z<eFk7dl=MU!x{eofYeWE8xQpe7tjDJI_>Vsd2Qw+YVbX45w9=zH<@uV^TtmUHU`bc
zlnWL`+n&sMsV$%E>=IlNyOZ9z<8wF|Yncu|+Nol?EyKy}lSmHc2;sOu$^&-!jw)ZW
z#yMpN+PM2m=`Ec+x5{Uf82PKFvesajVq_tQQfY{?EZ{%##ZPWVX^p1YxFw+@KkZfT
zI^3p5)L`+7p?i9sN%DwhUN}AJfa9asx6S45_uWV|n>Yp*90AWPO=d&lDXmu$LbBxX
zgHsO{F=LxB2l@A;1=de0Gvr%ue#!+^4{{IBYbpYM?$Uo+c=23?vMtp?>BuIhPZF7l
zS&>ue$v;W}t_;C*<jL3jrkyg*5EBb8)~=0N@sVvV-}b7V?xgae5ZlSMhYkTW0I<3B
zBOPkS;8#6A3eL4@81jx7bMvk%MIe}=VH=U2tSACK-!?ka+R^13#swn5K6B*A-$knt
z85C_O<LW5^RM@ybFgW(6+RJAw{z>_dbt50GT(}n{2u3P>yVo~$qTiVsL=5DgTp9*;
zKiSrSepNs}-lSU_Zrcg^=D45i{b+okTz)d~{Oa0inz&#2Z_i^fqfj@mbXaGNnI<aU
zig>OkRk79VN%F3mNQVF~Tz^{KO*d5BH$yXhXXEj$NbRnI1aw2}ImhEb9&rub<kE$E
zhXbc8$gQ{_Mu;OwdUY?!u7cykR@VeKD*ejmCWw43Z4OGx!#&HI0OoGA>xi651<Zhc
zCcP)Z5wmHD^W~X-VtUp@T1Bi}d8Z?>JXXD>@7Q4xB=IV*spQbcbPa4vVTlLnOj|IG
z!NIJT*SQ<D1<#-&p9Z@ejCR~^9-@_i)oWI7uhOG?R#Tt-3aK4x-@LdUw6JP$Tu!m1
z`EI=CiwL$Yeq8g9T0?8t=O0?ww+kd=at^|*eVQ&fAC)VVbN>Kl9AtiUeVf~#rE~(>
zGyWo!!4UouPrVlz%{7+hJCK~x3kLuML-^N9AwkC9&XdRl=V%nJ2RHqla5||O>E4g*
z`9UC|71D^tdJn>sN1gzp;bWN^Y@UFMQKZT_>-DaXqXWnCrv%S#Pqi*!vCSPWPIL2n
zV~S7gi5Pv)%vVw&a6iJE_Iwge7YiJ?(HkFd{YunrqRq$8gI!Zw_v0SsgB~%)Dcme^
z(rGs!<oxH?Jq0>F7HLWS$<8{SmDdu9pPD?=9iwr?+kYB4g=3dK8I^zxIrZ&PH-+}_
z(?Y)3u9?=~Aid9SfYe)b?EUvA{pO>Xb~%Ue#ByNy$&YoQcrqD4{{Ty2?5ZoN2EZN{
z-zS=Iy|zR9xXX6plVdqk@b=070M^dUj@YNi@bbYMBI@9KXCwJnPWqB4$cf4H?@9fr
zdHumY*{OPr!~Xz;G8hzprd}`|7k&jkKMdF_gCpGW$1)R|**c?uHpB<lH5=baA;5w#
zeRIt#1=(FZF{Kb2W4EzlY5xH5jOjxM?AiYSfiV8GsdFk5hQ=x1Z@I_%+<Vbs+>vxW
zIY<0?#kaT1QjIdnPJYV>Z&H;^-AZ4HoRdrEN!QF`ed*XPXp2Y}<XB=KK~4V8vkklK
z@Nf0N6`Ea}_}lZQ5XXjnz<ScK8iq7O(NuN-3PNH+H_n6c6_?0fy+>nBF(Kz*<Gnip
zt>?l?-8cu@o9D)Qzv)?sfM*NVqz7rmAT$lcW2+K+bfz1q$ruht(yEMO6q|r1orGEw
z9#|>-O)0r&AL_<E0jj{{P!Ic9rDQXO@dcP$!y;$r7{zmBu<M%bb=ZT*U%9SMNbvlO
z)-_e6bkX=o;@->xZqI7o)9p_z;BG#(pJs@!@~=)gu8!J73cH4Q;<=`EBIGb2jBNuR
z;+}2tcmouRD%9%vA1_}@i<Ckvk9<^8!WZQq%C9rB{{RoxtG~|K=QPu>65D^O>G&F(
z1o~7^0=WjJ=hXfc>QR;8k1D)vApit)_Mn5B4o4JZ6VG3I)WBSTJJM&Kv@xJI1poj6
z)Y4=hr5m%KT4`Vn06LUoG|j;K(ig%0lmO-+aZGda`ySL2%{7?+0QKktjo0kFo2HU5
z6;C+tn&*p=*1L^*J@%~FEW@D&xQm3^*zH_(V`g^ImC(a4Iq8~;NnE!Ekb*P$QLvDD
z@mU)YF=qFv7_u*>DtMp@azJ2vRCfa_j-N_ovohiLWPY_pxg6E$#?@{(`c)HMRQ5RM
zxXwtUG!dTEm7$Q~%}WyiaL27g4_aEZz`VTU+N2+bYNRjgR+WP<y=<5V=xMF=#VZ_p
z(@D?&0A8KMHyqGu!yj4?Uus}6Nmk(VQij;U*YA4fqsgUQx69I{fp%~7n1sl3N8YL=
z9(q-qNdnE~H%1u6MR6NPD+B9D3hZ%A&S}T5T5b&{F$m;S*NQ+Y{f&c9FlSt#=CYiu
zQbnCQ*K&zpf!ei-4%i<`d~hlzF-~an&o$27%@Gifo|R-K)W98SB1|@V)qx&Q)7Fs8
z+0!45Wy>GTf0b?BCf53Otf|wf!9KJBNUj?>Bk-=DMca7;+ewr1?FZJm)?C)Fhi<%!
z(4ck6VN`*XCxPrQ-rhjKh9@VXtJdeZ9`&i>y*nlw#6zFD*!T6U>r^3f+<MU@D6wt;
zUOCD2s_NZ3j%sU-r01uos>6={^_wjlHZzrF{(X3^n#%WUFU(Fjz^*pc$YIanTegzm
zfuFnIH4L-0w3tbb*{hL-SvLyiY_6E&=f|<Gg3?hd09a&@DFLe($m!ObAj+K8ff9LN
zA<jEhX>-nNrVi-BO2uMVw_1i@k{J&i15*LHskbSMNeBdmT-A_xSBj<&tjb1l$jx9A
zn%eO*1Fc+OW9G@ndd1Ha#1!G!nrJledQ$+-N3Y{S`cmXl9+ZSMib_+~n~DHldr)#{
z>N?PI??AxvJJ#Ngv3X;6Tviz4>svZ{6o@eDX~daqbvE}25CK;w+}4Cw#d$_ypFvm_
zvxZgR`V)?oyAGQyh!|ylwYoW^b-o_drjrbWh69mWl6a!!S(Kv;5;8hgCW8w>I-pP(
z@mBR%nmNzQ?oAU{Dx8UA@g4Iw47e4Is_NG_C{g4jXD1_yc>`@_>I?%9dcmDYtLEh3
z=A>61wNH1hMM|yyO=8UpV{0G3QmDszsE>?e@~M=MQ&KX>P)}M?00W*Wi-AhV3TXiZ
zpa4N9ip;piKRVEyhB-a6#b?}(KBAb+Z9#|G*b&rY>0DXsj+|Fvs(iNPbJx9b?f0tD
zoQBf#MI~7x(bkGkC=gN_QaR?69<%_XsKKv5@Z6iU*iQ!_R{@SY{VTNa<6_l7@69G!
zJF7`@Id8(XpmU#0Rt2LB_5AB<*zQmV<5@DzG#iu}<US!-dG-r390At4_)is2#1`V?
zM43wGXzkvd9i&XQJTOETgVc2gwE&KB#Y=Rb=?|5|XKAJ?W18-X&c@)HnkZS1@}yQ(
zZ)%h6YM<)YCbdK|<ThlVo2^?|qd);7vm=t~R^xC7rYiIrb;P{9gbK15C!G{ejnvk>
z1mZRNd)0-~(MQbL`qil7h7dRd9@Rt{n7fzmrqSpPK07JdzIQz<MoYwvO5_Ig^{R&P
z-vB8i)KCI7p48_wh5!^}ifoNL9yt7I0FbT^^Qr<1xVKv{9Y=cSOimPTu9i*95jplX
z%}7f~a&yV7YMRpkK&$#((Zh7I%rcAjhBH)AGI|=j3Mw7h#yWG-vfS5W)U?ZWmLJ_t
z!?@d3^?7zkAUP+3TQ!a0-A$o|mn``i+w1REF7M&Hk+YNU{VSfPnjKJW>PBvY$Riw#
z)tThm3lr#ib*w0@@o=miun$0MM(#kC*w4&*RYlnuRC<(Rxpb9&P*e|_J?nbW)_Y`;
zKI>O3(*r)=%-2t1n=O;+oK(|p=4IGd=IPS35M_8BO;dzq)zst;wXhvz3;v9rfpJqt
zxNk~ju+6%C1z17#sRCsg0;i9)K%D{RtR)~U#yK99WqNy6X!#!XW-3D-ewn3SdQu*=
zql!R0b*HJwri>bL^rSK1W|yrXrR_)#W5<jW!*VyH4wdHe-I%S|gWJ-*AIIZ96}Ug$
z=Dfx-Cb3@ZRB=EU^J-5fdF#`Tl~~OqcdbUVQrotJP5T;ubPsw%Ge+Xv(v;3?Pwbw<
z@}OJer{zV^8Gciq+)yIMc&%TvG3`oi0O~2+43dOkj<h^Qmx0Y|{hvHwWKw;TJ&)l<
z!p1tlRCN4JI7G|qTHj$f`=|4#ErWk_ieoX%XO6Un2J2g6P3_k-t*1%Q4E-rw3^8uZ
zd**{|!MO(pwiivgXE=sJGt>&Qx-Huu^$vd?Y1~IY_HRK!wtkqdlluby02%u+RrhLY
z=$eC)sRC#H>Mk>#Hk^IlX$_lmg%#IF;hWY_SyUR8JS8zFbn3r_7ZJvNnfM!XN-cd>
zyJ6uK3=3VcKHOA;!WMf*`5n*Ji-E&^l|au*X^sWty?3L+dU}ubIrlX2;fnx2)bal9
z7YiPBB3sD2Nyz$Ejjo&FsO>z-ppHpDh__np4~J~Z?GX%pD<=N{!8W&&D{f^~>Z6U-
zFHq3Kiu=QM@A6qdJ7g%T8tZA7)}UBhB#wJ3;<|M3E|neuh!g5btvhW7!q@#&D!3eC
zm7j6x*z#*#3sROvWw$C1WBxVK+h~`<KlMjF!8PBDSXAQ~`igr-p+bdFK9xc^3!6Eu
zllRC6(B_iJ;%syk(0Gafum`~DgIv@sQb0#0iwNyfK`pQV^%a_QAnm!PIVYt{WivEN
z3F%s~@}ScZ%irnZ#z0k=?&B3j_&xGHYkOZI)j>Q~3ydWINn+o>#z6HZwC|Y`-*y9W
z`qo9GV&k53SG7XFWe0!<Q%Gp%uBI+<G5A$Kz0Wly*ASN>SZ6rvQ0@(kV-yT_0sjCR
zVUHwpflnDdIs9qG$pL5)075#FYUQ*<sUxB9Rfww*KbA75pRE8_yH72SR{_0hra)f5
zty|P&GD0#39`(+&?yN^zE;D6VdkUHiZwhch>0JK++FTyLtvzofTw#b5g2ziNY1Ct%
zN@}JLBB0X@*U^O-XC1n6T2E^63_9&KKvreQq%rZ&H1fFXOP#|Rqy$PZ-3?9liBsha
za65LTSol1FQM6}wQAiEFJ63)a;E`HVS;MMFvDfD81#)UyBa}Rf+|zY;kDn~>1G(!+
zW+tbi-0AY2%EdZ^jMP>-gw`?uA1Zqq?$+%u;@c!@<c^h*ap5RtlXA>q2lznE09vrr
zVx2?%?`-p0CS-QRc>~<m6~Bho$@eAuaB@c8wW_TIKz{cp+*FiVP2KbO)S*Lh(y9Hf
z1p_VlQTEiqDarJt1+tqPf+`83Nia*C`evz{*K^PUJxxa?=G7(SRUWyZ4QN)~R0j%w
z-ZV7U;PE01dK%<zHE0>RxkKrL%}IA@aTSl+$~=g1fSmC~$77+A`r16<@&#9YW)ve}
zWA1B`ON~z8?Y7e<U^*7!r%fNkmn=5hM*{l03Su{(Sa}O<L61^uzxJG}`7EpGcXX;L
z;C*7{Gjo6C?(Cwj+k88SgZ7)*r2271g5_(SW*F3&E=Esb&+@3@)@@~wMvh&NbCF#f
zUI@{m0Go2;cV;!KXQFAgpm{cNsrAJJAEgEs>4Ur9+O-56?!XLbk)p3m4@z^p5(zw1
zfhxcl{NJ5P_H<vH<>S3n+*_gIlN+1g-heF~gV36d<@va%im>Rd^}(kI<z@L|e0t)T
z2b_H<6CT<6Ql+KK^ohyzBA&W#qr2s`KUQ!B07bp2e8Y;j{h4^j41j$NO1dPhxoxU*
z*|SB2Pz}#Noi6_XUcQy4x+I5#I)VP}JN^;q&I!AJz)%J|5uaL6;8w!ua3IH=?e0`_
zQYMdVzw0u}duD(z%(&@HGq!nL*Gje)ig<v2bm3=gt;M=f2QJd*qLWAqH{DWxmDh+N
zTw*m}!!)1;BWPdy<WmEZSfxDqZhbhZzRhrYM8>+zu^nj+Pjg5PX*Ao%$L?5u6y?!x
ziTkUM_p75Fb4!2+N?>#2L%w0Pf`Oj9s$rn88Ijhu%$WZG3Jy*<Gy#nkgS$JJ0oNz|
zDr2A{WBnwr{06k}bM5a&C<8roD0tmGg!?EIzwnOQ5;wE9J%wmz2As0vf!2$GL9|^y
zHTlqy?r8>@r4fN|pRHVE^Bl8t^`!~NtrrnlbnQKQTCP5{{{XUC_O(n@<PS;!$2gz{
zEHMG{+r&TMG~lQR#A-4A$ft^p)t`**9-@JZC(OG*3!gzmVNhXI3TKi74!@l|AkSJ?
z0p4d(%>jVvND+9*rxgHZi-m)BN3}*t&mBE!uJ||#aqCJB;ogggkTU^GxRc4nAU~BT
z>qWp*$j4etP%=AH1dPq{sUnMx!=DN}=7`j=%YIZH$Ba{eWB&lwqTylTK%i{*rUG-1
z;-uR7<E;T=LJ(AMG--|rC!iD*!1>4n+|x=%8*zBXJ?IM)s6x5hic%DH6;<vcRmqu0
z<4hN}x&Hu<l{n&yfi2<(w3K5!SBvXV`5KJKG4h=8Uc&l~ipI)i$s^LdtHmy@s7UdQ
zDHRWJvC2(0Sgv#Hij3L`eto$<^;S%ag2z2`n$om#RAqSet)SW>NUHj9W%-r1pH3<z
z(5+pv$o~HTHEzi#n7uzLVz0_ZD{pBgMU3R|=AW=1DVx_VR$}npn5r{u4t-dfyBpzg
zR-<sesdLM?Sfdw*^wXT%0rX>14FgSIyKFf1HLDw-kCpst6DCg_QudPWD-;foV!w9T
zSKgQVHqClL812GUve*?FlP85gg&xvf!<43M;ZBh!{qxq3Dll`i{{S5oVnkvyo<6l-
zIc$3NrR^B`Mx-gffIljkZKKZY4Et0C-5Y`JQYFD|Gs&gS9Hhn-7{ac8l&cUuRdN39
zGt6A_<AY8UAiyt6m^n$7J-iLSl?6%fO!MQ$6~zrSL#%`FqnJ5I`FwTF8#u=psJ_{3
zKjo+fnfA+a-|L6xOPD!J8%_l`Xy&V%=tE=71bT{TzqSFtc%%<{Ifu$v+5qWE<%9I9
zPpaD|8}aX&i0by>f306`XyzXwspY8PQyD^v%R0@lKkJwCsNY<*B>wl2>CGI$%4!py
zX`8db6_fqBZJ+hI{3(sD+vo2eLGsh)4pUUB1NU=L$Pf;dmUa7O7$vjpwAR;cbB(Tl
z3OR$2zRHY#=rvks6obbVSnH61!Z+nnHoAxYSs%`qFmf`)acn0dpOOx0h}M*jA$n=n
z2|wySoYBrcQ&C*G`MQr<oDc`SVhvo5iTcwHviRaZ{CbXY@*AbMbQH~lf>yCVwkG}+
z8TaOctXy>9deY_&L!^cA+O2toln>=xdDd?+jIKVE)2m+N?}7BAm^lu}&Bt1aq++0F
z70De|@SK@3^c2&m-5#=>QOrI=tztIio0?c<1ECejo9W2^09e>Pd86&O2dvMJN?hai
zXKG~yKK>0fP8EpUNgjhW#WmF1N%LQ)UDfHn3yLd^G(VOL70WT_Jk=&kiIUTX9B!y5
zMwLg%=l%j~(bm>D&O}N0El435{{U8_{sUEUSn~yjYyhxIbN<PxVYIs3Khfkl_ODFx
zlpJke%9KayxTSO!JnQUNt@mu@KS5R_vD6g*0LP4kSAG<ZohkYJsa$-g0&MkH2WFl?
z{{ViTG<{W5FJ^Lj0OGr{`0q$u73=v?aoF?M@b<dxnBYjyt2i|f@OHN$%gVVu>(O(8
z#U?UnxLDv5!Me|TxX-bxk@!mec{fr0HrHlA&q@iR;bWCg3thH1UIicQtw`P$mw;~o
z{{Vnyx?SA#Ij40}!j55B<`0DaY@6vn1)=;IWgz+Ha(!#39eJa6Sn--J7CE%=R+_7U
zB#JulYDDmkn5(e)jri9@q-UiunL+8zD~`q|{304Y2{!p8(f<GleuxMBd4rCXxCn04
z5#K#%xLDw|Z9Xe0l_CnG&>Er#ALCsQiKE)+!x#gRis#qn;}uEVi6Uz-qUj0en(b_@
zt)zf6K#p<FMR3uUR#Ti~*1Me{!&>lq^FtCY2xC?GEzl1@v~0l7mZRvkWmu>naZMzK
z;2&z6nh=293IX_2yte)jJ$h5g2k&rcLlE0>nl1!*eDZVcM%N<@20bcWuH@kl6bR(!
z<ut;?VSb{V7ai(Uf_M9nxu=Uel1J`{C$Xh)u>+=7qX3GyEUsAXDS_)j({6Hh#gIGX
zPz7AKttjWMT3ssS@<{fljV6A%LHN)G5=LnSXpJUw{7PtD9$u{~3INUr-=!uF?AE&I
zg^xD?eHNg)(+#|#e9k+PD7YEm;B!s{X0N7>7-gmd{sU8u8U<b)k5P&M$T%Gh0D;if
zx@i`>u-mceQvU#D+6BhO9{HdQ0$5UlNyh5v6HT)Nn92IKY2w1s21I=KG=Sz=_P-|?
z=~4r@b?ef)L2qmi`lK}B6}dSv55Q0dGB;zn`cM^*Pu9AeMgaZN{!|7EKH~mV0nGUh
zf907!g($XR{{Sq`f8DN_N;?6%lsG+cKpdOw3{it_>42ov>1itf5(zo<7_Iw|Ukre5
z9WW{I%>GdikZ1!J`zq)t{m2LX>QkiLcK{rBHMzehj?~@RJtzYmba{_bxIXms(H}W3
zpH8)@oPcqPK*Rz~12fk}UNY<T6z}YKf4`5`t~*Ev$Z=J~_X^)QO}XTX1T}Q10Oi=9
zr8wz!pY3s0l0{_%3Pw2?z@Q4_PP6{uC*0GP!of~Ox*x4ckUeR5&!sRGZLO4XZ5a9r
zbK6@yMSQeV>IFA`af(8~_329BRgT#seX4+g?N-(Z@&2uTxTyZo9Bqt%dvi__k~kCr
zDu96Emka&SJ@HY8;+G)M1IsROarshj+HeLbgemV$$X<<_0GrG!l4=FIC5Yq?b59My
z%W+lZK<||_0dIaN-bGelm-zXohWF3bfFv#SrjkeTQ%TSN09um@X@K(W)2F>fBqC3~
z<kP~b^~F0Yo;jch$H*|R#U=|My`QBez-1r16$ElII60&Q{WvC!FRdV4`p{RNlmMWh
z_NKImr>!o`_Q|9%q2R3mGC&=70)GQbZ*o<(IX{S}s0u#l$Gs*2Z@ZcRvF0!EnnLP1
z&*@d(b&PYKeW^U<BP-L~Pz8Y?UX+GkLHN`=v-G6|W`G=ADb7s>OrDvhj8cHB-!#C6
zThNjOA-%mSb$sB|az`7c-u|@|arrsHIQO6nMY!ZrZaC|Tgv-xSnrV~k^q>nFKi>Rl
zzG3N_j5wrb0)QqH0mettnYl^tQSR+d3{)Ia0o%?;T6THwimf9P&p(|yDRSFfPz8<T
z_WWrJ9-Tgvgo;lyY2y^YT(@=4;Z6=mQ9zjXV@c+U0IjIRCAM}{`GEV`uLbcGuKMM`
zcipt&y|=^{!rMoiYZc0#Yv=i-X|83FpK*6%%?JlZ$9HfITqot@CbQQ&g<b^tXZls#
zk~rkVpL(?Ik`UREh;GKRQ2ze_>&<8l#OHQs5z-~4oROmgxld!>r;ozAZThnalnnFo
z*D|xptFSrS>08<@+{{XO#AN<M(yHJ}-VD+ck0nX>6*Bm1N=M?_B6?=Ee$MPpBsir@
zS5x=;(gU2hvCwVbWU;~<up+BV4vY&0xbnx{+P$fsD6wcABs`|!yFRtffVlN1-iv|N
z+uUi;kXG=vIPPjz)U>H&R5J%Ga0bI%fglWY`WlE_GR%QT8TpU37X!Th$J1v(<}By%
zr>=>m#JM)fyS7f_RV;4a;@C3)Ffs2^$#)C@8D$B$@tR^M8g`l+FKrno`@*e76^uFZ
z;se-LQPk{mOI|{LjY>7GJy-rdqsOjk4Bw6Izvq(YtuL8u8~suq{{VKd2Dzt(`L37p
zq<;}<%ExWm@!FNZ+>-t~Sd6I(lh6Pw27engcMln{-M7%ym@gu`P4T|qdjVXowQnRh
zgJP1clabrnfHx10+<(kC{{Y`r6rMDmMatVox%K9`Qb`_$n&$v!ft_WaiKn@g#^@r)
zr#ppjEbhyd$35%KEoCv@BZIfp`qzJDaAmbZ1_%@gz309##8ZCKM*x66l~k*qdr(!g
z&q`oUW+$yG%Oaeq{3@wCO+8wGCz|3}BMNXUD^rd~w#j@Bn@1U~EEC`GsAh~5AoTuJ
z0mI7du2G&sM{UNVFN3*D0z2oLx2eEknBh(d>Uvckl&(;Y#Qo#D{qAd5LcAzS90gOK
zm$<A+8$Q0Y>p4t!N=F^26Fm`TR$PPEwNDFTP{VM?rDfPiWQTq-K<6E*;xQx-=|GOp
zO4V(|D-4o3+wzQZO=&i#Y?;pd4{X;HZ6iWUXYY2cXs7cO6;>ek#X~6@jjh_NZOfl?
zz@-}09O5=D+tRW&sp`L-C{<pA6pA&@uzqYrqz`&w)!l|fNPixcow|jQM+YSJ#RIXR
z+Qi#ISde=2?@_j`a>pPj^%&_?*_Y|*MnU$V3!mCoj6c^NeE_CC-0pJIH|K#>!2bXy
zmji-N;3xt^bvRrJoDcV@ziXVZ%+K=nG{!4{1}ZP0pb3nU6T8e~^)#7r{BQpNeN<ug
z`_k_Obj<)ba6Nvef;~FYWM_&pXaPU~5Lff0AwcdaH!uT=0VlNpI06q``(~sZ4hJ;M
zw%%z&oKOSP+*AHgYO!OUqwu8MPkKOEIPZ#0{@;~XE7&ooEJX9q;%EYW_%z?WoYZ9)
z3Sr2`X@$uOfZux_)S^wSc>=4FGI>9ZARuR-&VVin0bXf_VYdRS`HRQR#V4AdS^%8B
zNZ{ub;LI_`DzUg8*rV+L4A2DrV}(18O&(@VR%?{UsT9+7j+9tM!zL8}04i(D!MI*3
zn_U6P9MXNTs2If-0_WOs_p%A&ns=N}A*(&ELua@2sQ%T1+MR%hTV6ru=HOQ`IQ`}i
zrF9z6{mPI}UZ?3?+~dFTcdlyR5z|5Yq%o3=2>h#F-h8O%AJ(zS!N+XW_R<o;2OibW
zBy~lb$ukl-81<{L%0hElkQ20jD$s>+zvEe&CR;}j_rD6Vkf{T%Dy(ak{(`Q@!1;|K
zkvjQinqT#)CT-oml>)9-yKs`|aN?uXcK$u-p|i~^413dY?_I|T?D5>>&_x(H;*YHY
z5R8freL7K`Qf7b-ov6qk{d!T!^rR{eN&pIiGl~Gmu%Ic&tpFcN0Hvy;J&cM1jx$^Z
z#}Z?YQC^R9fvw$7Od8-d2)wynIa8iSYo59~u<Xn{p48<T^raE=!2IdKagVKY9V3VV
ze_YjPIc|E@h9oKJRb&~@JkW`epLTY}NUZkHy<WTNfzv#LR9IwJT|JIEn~W!#OmR*)
z&r?n9S{VmXOU(j`U@m#%wOEcoc&gp0z~Q?76={KUIi=5`sFAk{m3aRE^;W5fa04AE
zBNVE+&-JGgF^ZreJaI|W>q^|yPZWTDa6_+AR;MO=WsycokD952k&2qt@wztQSX3}7
zW12rYl10OwGf#peESnHzy((KN6Iocj<-*2?uO~It+gJ;D!i57J=+d<R0I}Puk@Ghv
zBDD%*sjg`|nj(RVC%$Qd9%}QZdB#4KAD72Uf{5dfk%7fbR||p9)|4l|6y^hOdH~M4
zLZ?0JE_4{l&#i1up!(*src90p=Rg^xZ8^tUlFDx)_A)sHfrCjRV1bMeN{4pY6^Y?a
zO*A9XFA&`5$DPCh*101xgux5XO6s(dX41zcvIuO~8K_3qw-U#KHa0LiR+HFK5#M`%
zjV3`oDyVkuahj23V!pMDG%s7W*W);?%VD$tOhL20DF?PV?_API+qzb?7or$bC#OJa
z8AkAtV;-DRe{VD|wHuuNCb{!<H12kE`gE-eYeE1c=994XsbfcFpzG4zd1)&h*&%qq
zHPOt#wn6J$eTAplQDv0vWBfjqp=aV1j^x|iVU+#Cf0a}xXJC{ru8rto$<IMjU9zQw
zxlz;a8m0ZFp+?=<Jq9X{qp3>vl3?T>#A3RU%F*IpC2#niT#!1k81xm7k9yJ8pUl*!
zZu_~c&uU^rg*&x3JkpMxX@KF<j-rzkhp(+60rxbWeQ9&}QfDH8hH!h*QHm%419Jc?
zptFl@x}1-vrC~sut|MM~YV4xZOWP`_#(UPZ<8vyG#8&q{OK%IDcExEA5KewnOlP<?
zS}hiLkyjuN=C7`o1%$q7A*3S&R<<y@IxP<VW_1z_w%^vbZs2+C49)yKYl^bHm2QGW
znaLH~MR6i&?u?k+I5ah&uV!Pg&(g8=LIj0!Gm6%5cW`l^O2*YTiFUIMz;Xq1%<X}k
z4t;7=%|@X1sUuQ)*E>d~ggq*CIUH0Gg1O?SO!`nVWjqgRar?B;TR(P{iQ9}+fnHDI
zsuOUvdO~tDR3<piPJWaO!PfA$ua8U*t#VF&Z))lMLh5by1{;A5kMs4eS&m6Hsxy$3
zQA<=vQjAhj)`1Qqjwt}=6l0*l{OS0h04{5@&|sD*6u-)?&{rNZF^=A~*=Sm%Q^K~+
zFvvR4QaY<J#QS>I)w3!dx%R9pc^F|q;<YWv3=bx=Wut!Gi*yw=%q=yPso1SWXhzZ7
zHFyEFhJQ+xpfka>q)UB9SVucp<29GLf#^<avhk*u4Zf<<ZO53|+&`6a(oGC4@~(ch
z-v@MaGB~W|oaMen?rTOHYfDxP$gS>0WyyTZa5MM{YDF}sjO{+Av`?`N=#HTbW93i}
zU<F2XX9sHXy{eV2lO(%xKvUF~=C$I}QY0B)%CsSre%W&=KYQy_#SGG~B$9n<*4t=D
z-^~fA+eMt5fyFXNe#Iu=x@qZaAp;z9=~A6t8$Mc+Dlw`|#BGRuDcn{O?B!FE?esMg
z!6tdB<h!|$XUZUbDg$$HIl=cBpa`YPt0^680&@z=_+Ohm<E3<RN*plhkzDMMZ<)wb
z_m4FdHAavaE<RotwK@{=ILSWsBvwGSPZecijx2N@^@*j;TVM=81t5BgkZr*o>Yb&*
zUOKO!t7Vc?kQftOwLT-VpTa)TF>uE@_NnDQY=91#?@?REBP@Lf6*a0fjKv0e{#0Jk
zB5LfT3Msuj6S;s~`qx<sZH)r;1DfWo<8SRakPP7N>s?Z=&;T`5%n6}VN4;Kze9OiU
ztyGJi1zUuE`3HT~upMM45ih1H#Ak}EgasYAt0~f?Wa-wXQ-e^(xxuNzh7^FaA0nqi
zwAFZq2TGlK(itIaj@0!zsPWL#*P1{}#%Wj7(|-zh81G19$0C<MjWkobia>LoHBJ5(
zycp+c#d&U&1KCGjt>Wd+hi*Xr>EgVfL_4iiasrYldk0fP?C8g^slT&g#^X2PvZY9e
z2BzpS)K+ZKBRtrEO(3yQf5xwp2R(;sKsOF39g1IKOm(1IDDPJ`9p6e^XNoQsC^fPk
zPgCtr5TcHmt6orJKta1`Q=ZhtVz7-d!qSoyecsin4w-Q-Fp8>1a(dR4u9A^2&Uc^o
zg%=AP{1&EW!B!dcT-Lpngb_Y|&dyKqHEZD^UzJHCpd3_TrIGhA3+N~d4hiyr5PlS<
zJPt4oJ}|&z2kTE@-2(GKilPF?El=_|#^d=^xn*o)2Aa-C-*487fYEF_(lj7&1uI=f
zycq!c)DNiJFIkjPa2(d?dVqekqBI|LoP9A=Cf04x?cex;RbO0zPf|(kObuxtVc`aS
zO;=*X<knkj@Pqd=$6eK4O?(6LMn5Vn2H8AysF;8`HGum3$D)P&D!c1fEJzKGds7k6
z$oOBBXX{Y_-^4~MoPAR1*B)yRVTyt8=Kdz2EOkuE8<Y7|QcV(!ysD$z*D7wMJs8tW
z(h^HQQR_fh)7S1HlGucO#cPv@;z5zlYeMCi#&T;hPw#Wo^`<6t`g@-*`c{KqM*@)9
z2hi4LkV%iHxu$AzE6jH1K9tD~TK?YRFsq%_kX#i$w6_Q3sL%r+S^<Pd_p95Q*O5e)
z_;lQaat&ml+bBN$YiW75$7(}4yNxE+XZwgb&)ux~d_08wlgNktmcXuofDGIow9=!s
z139M9XJ5N`;QOv=pV>NsoGso*uFC1c=Z>_v&N@&BEOh;0F^!Hr_@<kEU<?=#{x#H)
zbL&nq6OWfX&=xrfQ&QN<_Q#(_6+yJ?=4}0)g?Gj*o)emQvm|n#od9{@((g0#M8cdj
ztDt`4SE36o_!v{{YUEl<GU83Yg3+KHMuyL&%p{&C+v|+hwf?tY=Wq}1N}B6NiD*=O
zoO=ofhV=INo&+b{b4Gz<&RbW3pKeNzbu}QqwLkLNKRWbJ_(rtW{{WY8$JZ1ugmk7E
z`y6NJohZ-_0dHY%lt`r0#L*w)=DW}MLG-sAS%Lom0nIhO9%+q%_FR1drJx)sWn-P=
z2i~W)UBs1^HOH%0W<D3#$a1#QW7wLQd?&RSI~_mZbZ7@0nw!Hh3nBnN+N%?5i?{c;
zKp*bz<X2%A!i_mjNYB;k{67vft8t$qCU5qMYMncd?DJVQs88H?fA?3KjddHTm<Tlc
ziF3wJ73^025wf?yMO4RROjX3tt)l=8pL|l#dY(BQuD@^rhfFb#_MWc6;lB{vljhyW
zZU^^9Yu6J<fM+S!)}$Iuuox-3-!xqYr<5mwu3YBhR+Y2a1`qSAaQGKWOc@N*eMzrT
zOABb%9#F@j=A3Qg=oM9cHqp#8&uzRbqr?Z3U>J^aMr%$x1%@FMR>x@Qp=+@6<B#q{
z0reE|xraFV0ZFhqNc8EmkpUltPBg2w81nEv>!b1sJw`n!F}MUT=St%__0jI1?-c{<
zQVkAM)^%KV0=AYX{w^v0Szh^~;xU&&O#JsOK<pNz{>X?PU9s(2zDV__2viKv258eQ
z6kwM>T5{>uN<ZV>Pr0jSX>1@l^`SxPdr@(e+RoIs7U;P2sS?uOKbSz7>}t+4)1@Ip
z*E9f#+dk@n_*2$KIqoVV>Z}JOo-it8Os+`BwE!`TwtjPpXyJP2>r<G*^O|T11}G4V
z$4)32ZuH?8JkoDK+eUIdr~$xn-kL^!?KsH2a7`hQc3NO4L5^v`GI;4x`J@c(r+J6c
zkP-wq;7~@v^DYG<$ikwKNYCaMC)o6&;7AB>T5v!!P>(Z=k&1Vkp?P8X(QqXEDBx9d
zEJeAL55|LYYZ~OtnflNLphhVRuX@Xp^43F{CO95~m2d4;cx;LQ&|fSz?lbFBhZT|i
zrEU)#(|@*OUWn8Iuw>?eAR~@zANynx%sBr5fmBVbxj!UW9;SdcnaSXBLa<TOKJ|tD
zv2b6aW9dlxwBdmax$S{K>~sciVMmw^b4OLUWB#)qyi-2ga^wADeN8a2)a-WTRBY|I
zpm0d8WZlks$j9EHGP&+^^`I<uyTJR>rhc@Bc);dl{OgkQBm=qjCW2UwgA@qsKGkd+
z=DCiT*Y=sfm=Zk&a-d)eP{mYr;(?tzYF4Y(U&9p7?OR@%bNE*>caxB42*>_f5k-Q>
zMs<5-JRv`gC-%%M(gr{9D(8ye43kGe&VLg?8?CQKIzj>TEm1d!9G{i|0Pam?Dk$nW
zrFD(I=s%4BUu|}G7{ag8qit&F02P!D_!UH;^rR7hXs{QCv3TVE^8oq^YwDMo{{URr
z?^OU?_53OMTw@fh0=}VgdGlQRQY`NO05i=XAKl$Z(VTKHC@`tV6j%nCT%YxlAFEI#
z{`T*tYFOfderXk({gF+PRh#8qqtciHw0m-~VEU7qM+{FR0-TGprau}|aydDm2#Ps8
z6USj(pNOF=CR?v+><<GO=DF_>#yp(kG?<S)x<MXaprnUW354?V*mGJefr(zVpL=AW
zZ%zm~;;e(DveES`n1rG@)lWQ{vOGJf5zED#_N~1JaW0sI<n{p8z~Opzr*N^zuZC|K
zj%P*uDa+xTz{CA9Kktg_q$KnldenH6uLtQ*n0%)`JT-H)@4f&ZMW&Ao&5&C7^z4<<
zsgMtw0-RSgt`<i+z8Dz!uH5_Wr;iLpx8}Nk!nd|@%>pJp4n-@6DTaJA2F507N&f(P
zy!TkVmcvkz7>)w;uU#lceQ{nz;}{t=l6IY~Qp-rneO~d2!+}w@r+xnbKLmXRRV#+Z
zX}GB!i$_qsX54OA{sNkB?oS?jRdY$V(w)M^gL`m)<+IZb)XmmbsDQ;O1L;6mQ!}t2
z$i;rN7A&|dO8Qb_m#rWWaC4KMnau^hr}3oe+Kkcw$?y8olSoORW}U!ZohZwC@kS36
zVt^MJ>q(4JiU7#%Kn4KqM{bm(fky_I3EqtHOP|h@@T3+KKdm^9D5U3_0>O@HMm;E_
z6bwv&D9tWC_@&$U&;vJQ&<-i(ayn84pkiW_^rhRyD8^_3nD;cjPZaV8r8g7+U^0+<
z*Qb0rm>Ul%a8Et`E6jkvHR^u|VuE;ONmp@KJk=r@+b7C$a7`i0fAy<g?#dG|2)l9H
zH8gg1_#e9;T6YnJwEaG`n@)R?T?n*<^^6~_JX*pB5w2*sT;|5=HnG720=i!zK;akg
z6v1w%ISM}t0Ot&BTWA?H<+YUm00GC+x-Tvy2Y^0<nsTnu?LZvqw7BXcIQmnCoc+*`
z!n!ip9ePs<2kY-Z7$(YaGE~y8pKx3KTN7Js6F)KLoC=S-Kp2asT$cX;Q~;>{$2^a*
zP**{}ZzHWjBLT|}GfLoQu8}zIr{6Uo(j5KfABAay)|9q7;+Pp{M$QSF9>7!AMBE1H
z(0&=K<%j1+@0NfmE{hN&GZXZue`Q7oGILiDHhKK1w?(3WvUR0#9Dj@Sh|^7HizUZ@
zdf*gdy-Qw6E;Ly~WaJTEUW!HmJv-*A1jtjt72fzfLv?OUi;<p{!a8xB*I(edu_;p7
z&Kr)y{EDU|cOt^f40&hsrE5!b`~&D|`@U@Urul$%{cAgxR9I3wki{~-;<Om1Kh>sw
zm0e^Kz7q|OIHwX-h{&SgN;cyG6OU>@ew<VxvN)w2dJ14pA3Zpuc4{rlNM+*`fP1#Z
z&tXiCZNs%A$_nkrT8To((;1)(Me#vw4!l$f-;FPr0X!Vj0!{w_g*Y}k8i2@8K}`%s
zM_K@|Sm%mIVIutFp4AeQny+-vjliBd3IMhg0fA4>0jMF6n8ruvN@dB$IiLwLN%W=8
zO*e5P{{XE@Hqrt>*y5Vb2*pP71@%9LBC&iB7!RcYH*2f&$f>txk=tT?+59Rsm1G%C
zXc;Iz^rI%2K|N{XkwAdszv)I)cczdi;0geK&;~~}3r+-qJNBoSIq6Jz)tojyZ(0UD
zUnGpu?&;4I)j^7I9MBd5dFenP_M{*Iic)X}M;}@O!fqazrZ^0}IHz?y_4J_dF+hma
z1srjje^F4%q^ahgZpc^X;E!4WaSe)Z&G=M>&>Uxq14o{si-5qH<n*QT$UV(Jdirrk
znu39l%Wu7YZVfipDI;PZk=u%&%|q1FOv*iI0!_WS`qCKpXFruzYvd1rgnN@xdBlw1
z0YDOYAW{VbwMNr0JbpBWSI0^OSPB?piUev0N`+(~bBY#Ro=pHG!Q<p8#X2lXyl~y<
zcir;j5loICr~9L+#Q;oKjAQYp;}p{2G4p1d<|#A*A>eoXDWUrFQ4@}&kEx|nfc@n;
z?V13Wc>edbG%~LoR7}dJ=5-&9Ms6Y*`Nl;9EHtsN-jPSt)J=T=$Pz0bYNv8wkOw;(
z>NAQ+r-UxTRYd??`)qyq_Mxv6JY@bAQ|%VvzWyoy0BpAdXvz8t1X=r1cSE10J!jAG
zpRH%fc^Et)BA9gmazbF!14dZ{i_)M)kT!9}R~O(Y+=7x#R3h(Kv+QUB=q`B2<w^^2
z-m_O+$iR>F#XI{|vM~@D????5$){~|+<{p?+HMYZW}W@9D}266uj4=(dw<$AV?0(f
z>XY^>$81x7w5K^6lyT`y4OyabouqzM6l%xib6Mk2xf#Ttr9^J#`^C;p1F^Z~F&zn`
z$-wJaPkAd2WRpIdsz0?kZ0>G-4FWn9OnTFTs|x3S(*2}w`|6t0J04xJ{`CNKEKoNr
zKAE9jKD(Fmu5iEmWSWmE7~xl*xD)}@`LGlIv2#o^LO<oI<J!5R*~K?@*7Y>N>3-1w
zAL~?9PkU~wkun^170>S@zvD(vu73(ZP2y{qWzx#|fUmc$c#MmQ<mtnnmFw5BJ=8k^
z$6kFa&9$u>;>Jdo=5)?YFfvD4xgK_8)kOews}Yg3)e=;ePcC9J&T93g;FAh@>}xvU
zW>QThvD-cdPG}LgxT|woT4mcsI^(JBippd1)b`T(QY(5MJ?Vkn9YB>EPJKzCuN{a!
zo|Q(>Z-^C9f;*a(*_30Ur*J6ijxMcRe}3NmD~)51y<ObsWrWAHWc1B&+Js(B+>7^4
zbB|wILm+7nW74WgAuM?Ir^s=T4M0iF0y^&wT<?r;`{j1y`qqv1lO5CUVYnV^l+kW{
zn~|3Jw|uqUTeqDWob!rcV=snm_U<Zhc_TGeT^`CQ8#dtMu{F_>LF1)Yo+LSUJ$<PR
z%7;d=eD1bSps8ljEaP9@TPVoqy<CpvKvY#Y#aMh3)`1yzN9^)!7*IIC6#Zfi_U23<
z!ku#wibCN@%~@ggi$>#~;LryS&9t6+dekob;8ndw4<hDHxMSY4i8%J4VYv3ib{ZA#
z=#>lSw>8FaF<Tlf&L&jON2Yq31a|^Vjx$IbJRIZJg(~U}2;;pw8TFtD*>cpOLXm^T
zJgF4WFlm7GY%VBeC#j%g(w(?sfH3u&64vGNK2UL7lbyVBaqC`%aJ%4j>&F0!;B^R^
zJI7ElNTQ?3gVLB7=PG#}DIX!Zq|c@)37x)!eVCOBu6B+^Za2!_mBQ%PEpIaHI6Z}T
z7Vc(^T%Fk+YJ^yXFko?-*R_;|18VW#HIdHT57MTB;KF`xN2NnUM#zwnM&>!J&+Ux-
zq8<lE%?qq$$ijif4|<oT<*iK?GIk^Ks2Sx448sStR+CeWSeLkk7ryL+Q%R`laoZM>
z`CYpxq@<q3IJ8c)XQK*}c<Y+x*HTBzuI0)5rlws(Jsk1xS7I)721Uj{N=?H&Rs(7|
z^`tt11Nf=(h0cR_`&6E82PV1Ud|Ui!4ff&7np~mGbOuDvTv6vn7!NRWT;aONJ9!?Y
z(*?_dIOEozD6Vw>0BVbOUMU*(9N;z&VO;RLU=Dv;VYw$AO+HcF=#HTn$19&oY19=@
z01D^6&_K!D0jSOP*9x21pG78@DizL%>N}4h&~J0w6@;?P-1%?MQ%~C~o{vwIE^Ga;
z{{VOotth<CMpm*!GBEFtdO>X|?0EGwxkH%OH@N;U!h?J6aqU@aZ73h(Px~ajhy%Ey
z!?}Fl1N=?Ly)fQ;ll3)I?9H_0vGkx@7Gd+_6znUO4c<NewAQ>Qp0yX)$m((_MUnpc
zj(sSwTzA^WK;4hVkluiJIQp7Vr|0G_w1&k=`^sprTx(y9pO_z7iS-!s!}C*rXTSj8
zjDwyH2Tz0M!Q=T-uw1TnCG5@lP;~|eIjN0|M}ol9MT9xP&*wl9i^(6LIQ6CT<YAmt
z=T1iZxd*3Oc+%s?%;XR~X^g03m)LveorwwMg;;Gq6+3qv0i1(MkU<&wl(u^kNTdb5
zSqZUs10{M2<X%nr$Ln3S+82UV9d@28jA*vW^KfuDu6#n&+Yb5_8M&*Lp-+0Q$%i~~
zQb)86yz)C5<Y!_w?b{tjeJfH0E`II>V_Qf_03X7(ZLU;jAcOU&W~kALLUhO0q{atc
zYNA}{1J<lF?q6DlGAYh+#W4<72bx(<2U?C2F^+TfuB;=pj%-)LOH0<59PvOHuSoMo
zkPQT5wK!urq&;y!hGQa}R~=~S*R447??4O-N(Vzu>x|Gi=}ZK{?Mc(?PRBT-6ady-
zuO_%%ZZ9t64E6P{^BfcWtCI07AhBYZ8><@2LuxM4Iifk_W`Z%=k$?x&6cf|dxY^n=
zL!L2I<Q)4|$LW(*rW_h^CPrQ7OmojQM;vsk*Jpq`ilp4;x}mYhQ*np#6rS{^lf7tU
z6tsel^uS)e*ry6;{&Z%k0V=)^)~rTD992QhNgM3z-mNe%D8M-b@T6`(Diwhggy%J)
z5W~~8M8leuh6O}L048v1XqX99)IPNE*iq|QO^lvp{oyL5vUmfnb-o?&>xj(rC(dv{
z_NsaYk@oA<nnXJnoch<H!5YIDMHu&}8Zjh~V;l;Fx#?H#(`=nO)h7TobF)-NNgnjg
zy!5B`&L}E#NMb1Bk&g$1PAb{!NEbb58B#^hYNImk>6+A*KDD1Zfx*u{lz_~caxsh%
zRNX=1v}KGAl}bp)eQBUN{{Rb4B(!AedlOlnDYRtNmPS?D<G-y-;bsXxm!3BDu7g<9
zhM{Pw)<pT29qVgeBt03z!Dd~D9971O8*H`#_o;(4LvF@K?g;5nF%CxI(y?f?%8wvs
z`9~Ekv=4CGPVKqpinRs0$oqEW`c}oAvZD0K9V!_`?Keh`$y1dc!nYyQt?g8i%P)GN
z3Hu~_%P0VKHJg9pRA=(-dG+T8vypLEHMI+rM)J|Oe@el+Vy%$bWx)j0QQSP8ai3~g
z-{m>&T&{1J?2K%Vmq@y6i&gVD>Z2X1#-NW4w3+ASBZ|ebQx2aRXZMW7_^rsVmg>St
zq*6++HRw>Ob!Kqar)^Q<TEWh%a61Oa<5VkCUymBi&tPAHS(vVba*O=w!`hqHlpJ=T
z1s_}*ZxrfGbD988!jhDe=}j~Myig4w=9Yn$Eb;cJ+tBo`wmn8c2-}`3nA0G6?*K(P
z9^6+>_U0&zZlEv~tvw7XqBE-9F+V;%g+AVS?rszlzO#Zl^cky~e6qoEvY-KnuS&B!
z9j=av1e=;PjsF0=-j%s`sar|}C{*#*xk#>>_>VA*`gWwdmJK@DoSeBF0oJLqIbF*M
zs)W4qS(h8}^s4%^B#a#hB=yB|GhMsfZ{c(A&1*$>B=G>)EBq$8rgp&($?ck+Hexal
zHC;{{lU5@<b<JYUNzloW^Yc@nkbe=V;^c!?0_0K{29O`Wni-!RY1?o<l-E2|jDkYl
z$sdhTxMBlizjIezgLNjU-F&I*ni2z%*QDPvj9~Z2dc!?yOIDN2yI?^DdVM&o%GDV$
zXrhXuLV?8;Py>PHo(SntjOLs<pk%9BS~~>4LDN0!GzyvtHeE*Ej3{G0D#85Df1PXF
zxX&jYD+5ZDJSsuYY}Wm_RU>~Uvt^^Bv*i@lg8kf9ZILXawkrP9?@}{?_=%^?VOy9E
zR2-ajuQWE(NXH5I*Sq+F$}5c_)qy7j*Nk24wUv=FPI{W@qpC2dtU(2$Cohkos}FZ=
z3XA|;R&<Xf&4mV}k4<*}09ldv*HZE^Egfoh07VuDwMifLjoNb~4)`>&Brt%g0mrRd
zj^TdjI2A~SM7noFG{-$~D$I6vs(BebjUkhAnj=S&Kotr1HAI(U@)w1Pc=Qz`Tx}!-
z0D1vLHg4X7*P5`}a%2Z`J%vz;l3X#1YWJ!n%6g@1u(W}3v>bjlM&|Jq{z#5H8UUpt
zupcn|Ydx-EU#(xB=#WOr$&xVAZVT3;WufhO2q6$uCCePsj95J}K?(u&tXZNrv~3~p
z>_pM?AS7a~zLR+ZWv$8jR+oT|?KWP&>o5<uO6@QkIq6*07N<=)*&b$)-9s4@M~vqc
zcHAwsiIMUSGt#zvR)_-ZAx;K8`L1T}^A@EG06h<S&Fi4s>OV(+KUkEJ{3ow!>63u9
z$oOJWE$z&MJOI4cVw@0qn%<hSFf2s4HG0uET}7W<RXE2?iqNtfuA|4OHJ}|TMSv>I
zV*{l`hj1KXr5x0Zl{)pS3&(1#pGvU3DFHfq)rIYffe$q>=~6O7_i4%NP3=xx&;-3t
z6yegEDb$$9ie7@64;1Y2NDLnqWcYsMV?Qb4yrW59F5GqG*Q@xi{zdze4<s7%J5>?E
z7{)L;p@K9}<v^z%y=js32A{vK1!m1qn8E&(ql%2NCX_JEARmHH0GhJ}gwr<w0qSbF
zxnvwr*RnSSjW9JM(rw}&y>P&soV8tvY+wX0ls&7PX$u_Xv-PGk7XxwW%`qKIYF3ex
z%H(zSs2^8>NWtA)*_3CkM$-~cGy%{{uBbmGUiAxjg|osS`qm+Hjw&{AD6kt3uU-?w
z?HTAQ7S}G_f7dWIl4S!p>rp(c4;)coG+$G=kaH;?O06a2r12wtH&s&k9`wTa?@qyT
zV?2Oiq<s4^rupo8vmdFb8T(UrhW`NTQDG7^ywqk~j-QPt+^<IK=}l$YdSKH5cX3T;
zr+HGa;xa`aXP*c6W`PXfO%0lq*<2I%KRN}K$^H?KtpRcpaw&{6+zPb1eZg<KKRRFR
z$&V$Hm|Uhn&ot6%+0$mv-V~qNQsXSdPz4zq<v-H0=9N*&11B}pog)a}yd#d7>s-y$
zTPALY27wxSedETtLEpVeDJ<K)Y7IF7WnT5TY*s}FZ#eBiCJn$Pc;=x-0eP;1Z6p{R
z?c{nI=bkeYvhk2<p^3le<ae#OH$Asp<W?E$(zkTi1|gBbqy;$<iyk}FVka&4TNTl)
z5x*fuDeG>a{n`d|ixW59Q^&PDTFA|fr$0*R79`FH`qYBnIU51H<l=xiw6d9-h*`e1
zX*9{({#oFAn&{)Ri~+|^^=d0k#A1tq%*CYKJ7a1n^{en`7ZQP&LG@bdAhuOKGn%*}
zAO%s1R~gO0;h5BBNl9b;BD7-g{k}7nZ>?-aZH#fxa%$S39C}i?Si?;U*+=@U{SGS9
zX!eW$04!C0m8-A-aYjEnR|153ZKQmxDUVE5l(&IL`k4O!1*eo^eLbn_wKpAxv`9g~
z+CSOikyJ)-x%}znNjw^E0OZoR>^mlc!lHL(8&d<`oT_oj&%GB51Le3F9`zciLH;!<
z9Mg8>^`sU6M}BEZ2iBNKR@#2`NQiOLknASq1E&<uSm!tt`3By&6%lkDarw{$%2a#O
zmjv|Ysx{1D@<k`w;qLgyr8EWJDkqc!h2^RPeQp;aoARhmqY50VGkb~x#o))kS~<^J
z&uv|Q=Zk0SNhZ0pe3schrMRFhX)2uh(vh`t+zQA(AeaC|5%KR(ORP@p9PP-W!DDer
zeBg0T!5-rk&YfcL@w|Ri*3~Xw8Go%XIxwIgttLS0ispXZGj(I1T5DWL{aF46kR3U6
z2k)r-YBM|`4qbkL*D_g)XL0tysMziRGZWvf0CZ;J(OfZ<Eg#wz*#7`s`d2h~?r}<s
zyPi+horZKLRJK$1*q@~*_PiUuSjqaDz-@{3rum?9D6kt>8sj$66kAvIsDHIte}gCM
zSzcg0sSKIzPQo?Ltmp2k{&gAEZgPI;`gN?ea>s#EmSA}XfG>?o;lGRnLB6;@^4Y$%
zo=BrDj<f-H?UR$ttZ4gGr2X^ss(_KjIJVQ?fGqu?*kg7+hL;jB$ax6$%~TTO`qhJ}
zPSJ$V$U6Z=fMX#&OCQFNt9qJLna{NzWQVS3urLZo@S0t(*KZV?pFMwCa&KnA=}bZ-
zPa|PtW<H8DLq^EkSx7#Wq%MWD9#ytcoA0^mYN-W|OJpBf0IlV_45}PcmeN*SkX3zZ
zedR_F;*q70^<qT;NA@)xUYcOsHiP)op!)MtBnr#D<k-HQ=mM~{ISferDOms*=qb!`
z#z3g>zO(?sIpF?uV>#xXj%f;vbf9B*E_frFF_G7;E)X7>KD6wpJtzSRfG{aAKD4{~
zam_b>Gzda@;1f>H2TDOFH2mZm0F8+~2540$wK%yA{uHYyafQkE6byb5M<`jow89DJ
zpr@d05scCh<ZzA8wIK}(eQBf`ltn2R5lCnjw<m>!ngERu2B{T5<PlQGr(L&LPCJ@=
zX}2tJu@gWQnnDH-=S|=3R>qff$B4i_gwp>2WnK~n*vI?|ft3Rq7`A<C@zQ4p0IfZA
zTaq$nQIGa$12mT%0pgH4fs$)c^r_@vqGSj<lC;0rQ3K4(ev}Bw-|1Nz<VIUl#dY7<
zkz?<-wO7>iNEc6b+~*u)){_IrnTkp~Q8r{l$7*%pSnk~i7&zvIY_EFJ5Ow|)l(wF#
z-9>b4q$oTJ#rSh?4a72uMoP%tO?UqQV6s>L09Cu{X)=+_76jvPq~(vwYpVM#s341U
zr55pI{^>FP?JJDsL~KCo$@Hf*L>`P!pcU4LqYI6SJ;0?vigUF=`cZH>Aqy4Vv4Hm!
zs~nihBN6Habkir=Crq#I*Y&A<pcE>AK9sHpE-fTHge2FO{6N#Cx4cP=Y`pZZc@gaB
zFl)>{EL(22NpYR6z@*AYjuj-4icO^UrQTV09CJ;{$fPjaN<apaar|j00KoL46o)i(
zK!w^pXvQhHCyI95nm{fFD9!~Y!$v3o$fcy)-j@TPN&rlsN-}68(vpA|wG@<Qm<x`5
zD5jS7%_io}06!ejie^n5`cMRvnFHRLgY=*&^`K~eedq>|id;|uxKLXisK!ny3iY4`
z-f>B~fG9KoZl%s?xTWhr4hIxwo1bo!v;d*G;8&o0EWeJ{`ekxg<|eol9<|i?4{!V=
zjEm0-*rq8S_2=(9)prBj)TsGfbfFUpfPvE#GW+pNkxSrlL356{q*Xm=$9h)*ck{tC
zyO^F&<w!7l;8Lu6&sqR$jlz_+)y54+JjoP+I+I8o6Vo&SF5-JqZ6x;kQv)1kmwq}>
z0{KAwY05U7W|`(SF6v+;rI8EcC(?*n<c}vAJ*rKi*O~--F^WJV9lrknN@6i?ybpSu
zu0=*y9`pc&<KCPH9VsvX=Q*Hqb3hVf0OK^$p!MhLKsh`fDU*Y<>*+uhbwY<tmjOuw
zrFi=R9GgMTGn)13U=MEVf_Uj(ReukYsLY4^)leoxM3R{mz2Rv#Ut>7rRvR*`cwV)8
zM3~2@F90s?wQQ7nsU)Z*_7sc*##4%HLv$+S=Ockl+ra1X6`5o<P<@(K*f1Hgd8<s>
zCAq~!>?2*&*yTqVC-R_VxW^-kO!hq~jQQYD2pzeg2NuNx29qF~Fa;M7?0l!`RpXVJ
z_OTs$RHi}vRKU@L@+R5_PIys@KtLp#h_|gb%wFs$0?Cmn3#dIR0P1}y42ljnb4Uw2
z{$EOCKU@sdK57N!z^Nk}#&-@V0Ys~}=HS!8!Odq~&WUl9Y~rk~%wjR-HX9u%xE4zT
z&uURJsH&1*LmKX8+P<VzU)nZp{{Ssd{qse@(EC92r8fXo0e@&Si8J_8HTAl#1C~CN
z0d`A`%eRhrs39I%&PFp?^Iq8%{o=lJ=~b5Y*f+?MekPb3`^$F}yPF2G7gX~4M!5RZ
zj<3M^GyNz7OvptjmmbxO+OzKAK@{KZM?HY{%@zY(&x7kr=I`|tirTEp_e!36)JIjA
z^<XJjE^f@zM<DsIzVyCp75mlCNvKOA;pQjwsM`8W03{>Roq*|sA6~TL;2dt_>s+VW
z<SopN_!>{NklEhcda<Amp{@Wp3>)ZaQsiyrmycGiQ|$%#-S13!bH+|RjR1ANbVrXd
z4t?pLXp1{{pg&sWM8Kco&w4{B;{!dYupM98U;{hFH0l<>=gd$&O>+KjM|@Hly(xj!
z4MN%f0Og_l1x9b}iNcm|!nva>V1G&k&M`%R=>Gt;AW@tWeJPEoz*}()1z;@fPfSyq
zP**+Zuo|}-luV<_jlUC$i8WVM!Ck}CHIFRqkCbMSA0wJ9Gi>Uw(_sAR4zVccsgJE?
z7wOI^GNAqM){6+#8pXqL@&Qe4QsZ~Z!|7SO*Cz&=9Y^tIivgr{E0NEbN7AB_{^YPe
zdyi_V<^#^*NM%xb)3A$UP?+#!Z^YAH_Hr@ix93$^lrOivG&&FB6j&}<Y2C4xf6k)w
zoNyhn^`;5qQ<B)EYnVqy&(Kj}+?RO#Pf`szcLUU)a%!txLOQq<3;36$fYD$s?`+`n
zN@pw7aa9)jJZ{Lqs3p`RZ<&q(J!r68zSj(T3{tJb;<M8J9G{zydK*xK95>-llvgyq
z(&0$Y7^aJt7{_|g8l)@63ws_Z4yP6~gGVS_(evD%lnGt14Q4)~qbxFNGpe4RS)-MO
z%~H5LADinymB-7UrDT6;H}`OHNV<vsCCAc^Ru?vet`zf4E>AhEvwZA$7@@Cj2>~Jv
zp1je>#dA|U3PJf+ak`Q=0mdnfs5m%YMLtG5nxVGwo@qB^eQP0g7tTuXDpk38xyp~m
zjz%k&jz?ae^z|#6%zK@g1;cxag|Fp3G5FEQ!<gGR^`zswU{)x<m(&lSsUy@%GVfjD
zpCb#SQ-$}ZWGMBli;YQ}<w)_5;>}iT+mGRF52YNTbAKzIxuh%r=Nwl&*Ox4Fyz}TP
z87{8C{{UG30EZNE1<shvfR1rTo0EZ><6h$MgNa!4`P2<@bWi%}KRSNRhcVl;`&E0W
zA-IQQ?djIIc_+LsN7`irwhdR6?>3FM5}#AMnp})7Nv!A|O~X$Mpj_pFtaMUN1}bUR
z=3oQOD=(pQP%KXq4CjvKorG1n1zZjZG}~ZI;PNWP#@F=CLlFw=?NSED+{QX{KwLLH
zs6+d;=xIp+5-Et@(QetkR&r0*wQcNY<kugjOjhA>*n$AA+T3}VJJmt;6afK3Mml8o
zu0zDI>}~7Rb6wogz^Hafxq$6l*1u?y*_^2@oMe0PNM{7cBQ(v_gcbP-$y~4H#Ru`G
zGR>ofog18n73dl)>piFooS$Dz^{+XL=3!lrhHg_EOC8I`f29ICIR+2bpq3#ZT=nf&
zq}m46=Oa0)uDwM7W%(?#cEJAtYP2JW7{TDxSs;H;Zj~etB9R#x6vQpuWz#;D9fO7?
zJ^EF*Uokm2tk}y%a5@SA$?+wiLFOv40M{~Go|vxlSx>au79azT)xk<OGb#1QG?>O3
zvt=ihC~r=~y;UuPQbG5<y=e&aO*-Sxi-DXDD?|n>ou8d^dL_ZwaKo_cT`q8+TA>Uv
zkU8d=ftsJqAY&X<WwY9Wj4SDy0-sJQRT=aY9iaF8C;|skRIfG3c#71bnRCeOJJ({z
zIO4N4TYo;?_9Jk(q%+T0=bAuysV0xfnb3j=Jq<)puX;l+Te*#tf!tSZq}~Z33aS)z
z89nQUw>cHiX%l&D0XQmhqM8xesld<jrpY3(=x}N<;gswL9+ep+cBfz<niC^+>rlR$
zWy>?R2W-`n&cytu1EnX=o&o&otQRZCqQHRg0LDIQuq+^7xQL{5AX4U5;~yyXr;MI6
zMUb0pjM()3@b;zq0`&8ZNK~3a8AozGy3ip$!hwGIG{4!&pS`;twBVCB-A2KwlHO)s
zWLW;Z&=)KHjwKxDpF>X;(1VWHsfD`k{{UED-=#<)MLUY-kj6!3vJ5KzRcL9%4rA#=
za<UJQ1^QB%=6~X0OHdrPNW8lA>;+Z3mfqZF%4R(_ftr}CtVU&WJt;h%a(nio%w~Gt
zM(jUwSJ<siE)iFRAbJJGSr*7vp0>e{-Otv6Hdpi2v9U-L<1*r{eVh*6J!#8szLdmN
z6AS`HI9%h6xf$(KwZ9(J3x9qo41?_}oOGk@DozJlur1Vf1bflssO{E)ka_FRN=1_(
z;E%$kHtN~=MJL$eUPec#6ae9YkDY%CLC@W4jM)}%k!1G8IBC}aa>WN?!jKZ|E!D6o
ztslKf6_8wck{10c(yVE~9Xpy$jHBf<dg7e6+lSuz;;qT^p3C&8yq72CBm8Ir0}?L;
z=iZTy)AEig!G*EwNNw0R1E}px3g$^L!GBs~2W;e?eJanE;kjB2G9TeTT3}Yg<b5e{
z*y>31shTEG2?m0MXDgZzGUSo&Ql#fTwaQ;aVY-ku2?rw;*yI+;{HvMPqW=I$&vVb=
zSl3sHr5EoQr?<T<c+X0Zi~~&zgNop1dM-fZ91cnCTGshIXNts){Iii-mafdW%}Yjz
z*N5c;J$<UyIO8=|0(NB8oP51{)@-sVNCTc}urMscxTxjanLTMNatj{3*G?DXIk6uB
zd+ABHid9~Dr((TB%wuu&=7FB{;l&-P5+>hzYY<PVr;JjNG18dG)KjoCN&uzXk=#%N
zagN+jMtTa9jkw3+X@dfQ5G8ZoBZG7y*mtgr8RD}wl+BZL^~FU`gt~6hJn7CDie~H@
zp5z}i@H5<suaZtUt_FGlTRHw!T1LwrD$9&jNkPxOIFii!&%8LQWO8_`mxr8H5_4T}
z*yEn!5lQ$^O&?0LFr&R7Cp5GG4rm`r4HU#JKd7kr_N5K#Dw6`la&5q?N%IPz8x>{=
z_V9mN(kuyF08K>QDeiMo9(&a`Av^n4mW!uJsoyMNPn4&Y_o{aGvR+6djBaK);=Mn^
znlkCuYrq8ZO=QMs>GpBiTE`kEE8JDwWE0+nj{wqz>}df)^>U`NoP5>2br@vnSkfc;
zgmYL;8pMDuDcf=Q`&F3j$;N5M5xc%>3MsGy@uVjM7^_Vl8{VR2`cMT%49(B2Qk$vA
zYS(1}Jw2;7bs?D4vW&TxAeyG*2d;5iQ%9616+%Vl{AfU4&|D^<MtZLzyYx_Tft-#j
z&2;%Zo78X#&lTy~b=|B{q_-d4&#*PsOH&Gt+MM5sbnmgqmjwR+tj2R(+q#3#9`(?C
zLDg-qY~qgIKp9Bq)0*=axSTio!gJWv)rwC*r6(nJc5q$W+c0@t01vN9B=JNR>fT5a
z9=ul+9%o^eC-JLR*5%3Ilh<hPT=GXubv14^%e(n8AYceQ2IC&$u4(rB*%^-~r})xZ
zX!*wR*N`*Q>sm0|ktPNetDdCR$myp7+-MaA2o25DP>lZowU0`aryVNQlxT}AtiN<%
z8t0Cz=$44G&NqC&aeh_$Rh>HGI95e${KM0V%z0H*fJfKTx9qJ}J2lApi0CV}gl{XH
zHRWiYL*hpdtjx*>-of^)ir(=}uam6L=wCmetP@>_5OYBEqcl(hg(f+rpil!y?@ToF
zjP<4w%>Wdll9qrwPXSph_f0ddM<8apFA>C+$j<x>b*!(4pm|Lza5KQC_`6q2xSj-Z
zrA{kIyAdUGn43{RPalV+FlyioWd1dj>R9k|ijQv7NzH<R(%SfeEuT300%|**PFvYo
z+vNw04wZ)%1z8ej8);pY%8M>R>MM53KV?&laaa(mODZCOS-YNsyBQ!B_OWhIIO-}U
z%SBPwkyFRlIjBHG&ioTnpk9pinPu3{JC179Y&)8%7nTZw<m0tnMu;DprGR7~{=G!!
ztywP~5A~|@$Q$?q`-)d6sLW4pDm91g5`@PmidSqmDr)wQo^|SsXKyB|B9X&*s>AGe
zXxm69<@N)pu5k6QRPnZwZuIdYt|U{}KVR{$Eq}d^`K?)q&eTwP(MSS{DJg)Xk&0C`
zlnMuOVAKQ1Jc12I4;1A%pbq;(xy`yZISM#6(b_SQ)V*=O9DUYc$WB4Pu9_>R+@4tD
zJu5bgM|Whng+7&VboZ(@C4?wQ?N>u&RI-BRF*Tgg`l;r;KUdTK&#6k2K5%|o_cY~z
zHRnDy(x81vNSF=Z-nF6eSjwu<;Wr{2C=~BC*zH`OrDzR4IKbRG_cb9A#s<&;?_PpO
zD>Bm7;z#?0XSp?{Wu%9E%^?HYgLM>Rl4<FGAS58#J!*+;(~D2Dwo=TXp2fP-{iX=P
z+6UBC4>CzQvoY;Xj@oAEm=wt^eYLtR4>XLYE`JIm)7hAAU<cN%$7LG-02XuWOh!pv
z$BdkNR4p5`U?(2+y3xZQAOZELCYA*UC2}c&hVU>4gH&EX8J8F$wP(47QHcD-V@&&;
zpI()nLr9Hx%|gruNx`IYbHz7l2cByd%~9z-2#iOeqafs-YpY(ku1~=(289?IJ?p34
z!S$|b?rR;6cf~t!Hw@yu{{U8z)?fiR_O9#1O}n1sisJ6jNccaEO5AcU_%{SyXFuyR
z`d4Wfu3N&8s>eRu09%|_Sq~MuGc3luX0F)tbfT%J=4(Sw8?Kc4RRPjMyRlNAm#s1p
zoK>xZ9CK1Jh(%db+M);zN{j2wASaCERO`~AjBpJ~IjI>arw^qxeiZfVKo9Ls98*O<
zuQY}@Que0M4+fAJekv#X0^@CYnjA*FcCSqFDBYt<2=DpVnW-QQ{!}n6Td~N<;;fyc
zps8(i`DTe3Fahpr$kJRl&m}`G6bR2sZZTSa*(r<}82i)LON4s2)Y2Wyc0RPmY<C=1
z_|xrFf2zs#CY&v8kmNw0l`y%_Wr)twN79$eb_3)iJu_VqSi$>>0qiQgi@P{Dphh9L
zlhTvymkp2Io@;4iP<L@i?~atf#}*T|GPw3M@9eiH?~2q8eR@+Jn4ANFObqYru6}1Z
z&uVzmBR_reD%r?6?@AlqkcxlVR_p%&)}(DN*k=o$_o~xK26I)O@rh-QFR5w(L1k>C
zA|X-;VPCrn55k~EkhWQm)3s0LQvs5LpO7m46<pg!$L1T4y-w0|QJDrh{sMp$U=6(~
za4DJGcoa|}uO<&ded!eX(94re`9Y^}CHZ)xDoryyXSFvt>CFH+nHTSIO!E|<mzrw@
zVhtc)d{6_~fkH9#u18b_E}OM=p_N7t>s+?6{{SCFfWXB94K?!X>J4<!I8_{V?_8dq
z-@gOCYp96kF}j$G6G^%w$vGI}xf$0NEsW#dy4=N#d5UY6yCH7m!N@0y20-JvtzA9A
zh#yMJlcyNXU(*TlhIurA=&gq6^Hw~z$KJ+$Dx^0_2*VzgIMgA@=Q*S@bb(kE>J3R{
zrbPoEEl3T?9jYkrq22cw)ws1dQ>0&sG_E@r;<p_=D$+%QIO4Luws1}m1@)u*Y4UKJ
zf2~ODbTQ!<Z+e*+hTvB-{jGA~?Ie5RllxBapY^Blq&pp8a(fzSl#_)YopNn^bmy5{
z9+bg6q;gN!G=_FUWK;7xgY~G|?htvIKRV-#(v>+s{d!H(6ONPxj=1VJsxsFLk5NpM
zRkmF1m5=-exm>z;>qtp%q|gUS+T04c!_yAAZcoUkK7`jgPI{cvaZ1BF2G+`xu`~G8
zM_ik30w6xUYaMU^>r!r2UX)l1=UKQsj0$q=7cL5tI(8MAy-CInDM=WoU@X1l{E;pX
zprBq{GUeTg{{VWc1NqY99cfqx{ic8K5`MITc^LC6eKSd)YHmO@>>^`3?dwVAxBT=!
zK~askq$7?f89$tHg7llle)+{i&fb&)%Z@0pjVP_*kO!9IU>%1!sAgD0pDsXDcdCj>
zV0U7NQU?Z@77=a#0F8(g=Zf46pvfKTpCD3XiU6N0&w6RVAJU@-wKoJ%1h^;AP(c_T
zW>2+6l6z7DM?iR>2@ZRjG7nm2NIdaUBdA^gVm&AUyHtA8fB?oQ1ha4$`)xGkic)?^
z<RkslOaMi=@R&5dUOx3oE$&Z9Tk@xi8@9$EbDvs4a=DBSGAX7%TD&ydv%rU+cEvbp
z7l#=N2f3g{05DEC`cb<)R+?y+0R8y>rk*ru0U42c_7q$Ut)o3@2**L1+f5L+EjB)a
zn)+HRY>rY-cH2e3#~BTeTAXcBoMf8Sk4A|`US=fr0-TyuN!KUw=|C8ay!50B-`%c&
zX;$P6gZb2>O0^wTkK;wa=T%#6E*l*yp!)@)9#fC4N|v^RAG#D=4s{`S8;Qb-es+#C
z^{$KT_Sxbkr+HBS0M8}Qt|{COVc)UO(-eWbVZNBIrBN4<i}_Q*P&iOC?M1-lm1R8@
zvHtBLLQgw~;ayhXbH)uuV?z6xRO8x}z~`0;Ke*WXQ^kzOkT8ACZ|_jpz|Yc~kWWEH
zz{473&ySRTbidhiXXaHN`>Ss_IL#<-G3!OZ#TrwV=ZsVT0I|vE%-Snan;Zkrr92FE
z>qWrLO)y5ke?H_?qf3jf@=wyPpS_+bK_-iVKxpuKo;|7KNwytSpP|KF4aZ6yf+prT
z1J;XyTxr%|U_*{QYB?+{^R*zs_03ycvgVPqNw6!$r@<f1<*9Fao5+ZcQAzq!hfcJZ
zz|8<Bl7k;8AB8v~sQOSj0+bGW&;YT6+L`AkndPr6J*m#+mum6rOh}SGgPH)7X*9Uv
zn~}vEvD$zPVuQ)zlOd_<6m@J02Vpm3uqKem%rHp;s!MRMC&<_o;Q2h9(hC-N9A=EI
zK|tX1Oe|R3D!tkBEhQe*xyb8}rABs@WXE3g2=QHRJ({GdeRG<v8Oq|cd{+sFS!{jN
z-m<OOH+t42Gp_I~#yw5q94KMMdW3iayobXV0^eFraprgWfBNgzK`ev4M23qy$8XA*
zWfZ~CaY_*fH6;!*`clU)n5S>&P_nadP8ZNrfbCo=;0gejc>@FSrSljrGuEKVG?~Gm
z3E9p$HNkvKht1J)eMje-?F$@w*D>SB%=!zB*f<@!b4iqs0dS)W=rK*;Q`#U-bJx8y
z%K*@d8^>xX+dZjD`%oc-iVFivv}S;Ufep_c4H@E}uzFH$qyu+ilYS}tK<!DlngDL>
zng&fj9CW4Qt|$wPA+gqtwC=g2JP%3$O`?o(#V%+x!sBtpFIo?3O!G_y#T!7N9yz7&
zNCS#J=*=9_VT(lpN&3<ej;4zMx&Ht-riyU`r6vUy3yaPvF`RKu3&G-(BcP(eaRxeZ
zNz_yRP$>>QIi?pG)|>`uG6^`Nb~?}lv0L5_oLcyjDM`RFk)KmoAQm{qU(#F3)gWS|
z;N)>dgwLYwuME*6A`&)(nz82|<2BCN>gyG%0~p8yBRy(w?Z8ROs)5s<wCqW?Cvn>b
zo#*b(Kox@8;l@}lI~t5@zJX8UO2BkJXSF>gDl$6yS2_K-?B6Iu?0V8Zvo_zC3TOjz
zNJNu)hnDrH09UPZKil%{Al#@v)E#r=;^Yr;KpjT&j<g2{rE(`+%YVn%KU#6|0s*w#
zDD}lVFuB(Uq-h6k^~Se|AP1X+_)`yvq3t_2;YFAos4UzLDUeLUQVZuDiLNvL5(u-q
z&6Dz|Pl#g#uxWC81*giw==3i<cgATv<vk8-&d-R{pZRT?L$88x1fIDjj!6a2Lo+6M
zYHLh@{o(o7p0|khuOZGmW|{v02^b^&RGd-CAzdDdF5^-6*YPyhyM&+hsgHKAIX)sn
zK4@}B_o^k=4l)#H(9`6QT^^42*5Ww<lxJ@kuPfJNR@LQoZ<V?Z{c7`gjh8Fs56-bJ
z?#<1?bAz7r)NCfj5`4HgHD^qeE#N0S9M)?#8<R_Ea3Q!y{sY#k#Gbirslt}vHthE_
z^QuG-LPjfwI+e>tzFQr*;7~8G@CV%orBAbET<zu6qG<N29FbKbzcC!5@!y){e$#sU
zNtlmdDSYeg!}sh*;YYIzou~G)b!B34)|z!?^vBk?!!64U8HuKoGq~L|Q}$uZc86Cd
zkgNFAZL7$782zh|*(UGxu74U)45yDVkG(%+9LG`psVN8MT%P!-#pTO4`s(M6yrYum
z{`#c*G?>Qr1M5rKhcVDS+@$=|5`MK2yE*>=T7U1V#9J12$3LAYvD$yuW7{<SpO|wS
zLgzWm*#7{5QvIeb@?`qvu+6wu>P-d=oE~ZWHQYIkroFZp%-B8hX+N}WfXAMGfYva!
zTw}F4ZDL=WI6l;SG%jORuaI-UJm;-Mbr@bv<=D5rYKVawx%$v;zyk)4W`mf~I)q=u
z=a0sl{i6pYHx)p_2j0avM40VIvxsvR&ZQ9d^rQPx2Sp;OnA1G~qiU`w<cM<@4y3FP
zdaiFuH_MY%%7fn&p;ULL$q{oBwxIt2-2#{UMY?S#@u(OmreSmSqmm=$WwEJatY<%3
zY1DFfTpz7faG-L33SbCm<%nIEj-UbzCq2$;xxSF+p{8sZ^rSJV;~A&R5nPa6x$HkW
zLw3M)sQi(UL5*|kMWQRRPqxXopv?mIY#+Oyerb$=eJQ5^WQul(?#WI3>zr*K_@*1_
z{{XyA0BJ#%zBC^(TL^HYu%;1?u{YNgz0vAF?YAQXa36&)+ULjK=hmZBxsS--_su)X
zk&g(&(;|;_H5A>>e~i<9(>M3dY2Hk`f7Oy`@+QyvhCfO@(9};pVn5b44{8L`=kK*A
zk#I@<!+tdHB6VD}cs_%gFBA&n8Rb95e>yQKAAFj5hHMX(h~c@A;6+QCA!aOc$gPq|
z_NxxfGJu4FeJD!_&m;luQb%WSjx)C(T9;w!QDZW;(#MK#?+-~E^R0Wx1hI{{-|bls
z1>%FYHT(@Uz)-J`zQ^&TA-k6R=oXibKKRdiw;r0|b0qxw3Vg^cRRw?pI25_hR;f%8
zF$!kq*R4Eh;GCO|J(iASD>6Op{qu@r0uMPNtS+1Lf374`+f8Ttl9BIEm@HGnV09k!
z1skgG_Can9!*l6K+Da+nc@NXQE?}`qqUWwfG{uZ(rCT;i3C`p0X`g0*edmz-152EC
zAy_gA3`ID?SO8n_tBDL{f4fZbVJGG+ew5UOVyj#29YOk1d1D<wtB#iHI80O_AtxQ^
z<_i#c1GyB25!uFS=}1&y##sAPGZ;BBap^}ea+Os(2J1nEfCQdBYTEf~awGgI!Jao8
zRS4paaq^j|87Bjpc(juk?^BTQw()^PH<C`kBv~EF;+M1zQXy+1{{R^j;S8t#TOX!r
zWH)8;<o-FPG<TTdFT|RB;bbYaels8+T2<4_oCyK?P`1}4es)zk?MSfPqw_w|+zMRm
zIY}2smAW|3v7z*NQ<CQ%#-;u050TD&X@%z;H01qg=MGV;rswYreQD=RXZxJf*6Lum
z>+Wi^UfiUmk=XObXy*=6Z|qr!$x%wWJnNmS^{2<HUJhNmbnR0eV(MfFa6#aTIfBM}
z+6df-ZbxBJv`0Anja<miSaV1kB{*zn+|syMs<y1&l&xk*92&N=LU!%P=TXZtsmNjV
z%`RZEPD@FFB%&xDhcyq`gYZBE)_~MdE*oLvy)aD_&GIP8^rM_sD9NUxrcAj0wN6VU
z18(ekn%;drMos)<9Su}#D4*tL!S<@=3m7kH5@+|B`qVFLZrRJ^dWzP#)8l48K1bH5
z$!v-D4oIp4HLR^z{Ks`tpHH?8@)9}8_pOJwz{u&|qw-S+Bvdijq^q?+9Vw5_MtBuF
zvMBmgWT^y>l!P`iQb6mTIj+x5o6UfzZOyb3isMm&pRIHn70y^G&mD2;)_^yN$6k1-
zZsHQ!y6wrwO1F%^%gUZ<3NtPS0W`q!tzy-!H3tj|`G;@^^{NEp@vlkL^oXt`GP>?>
zU+GwP8Z0UoI0Mk9dP6x_zMX4lNt{D=H!=CXUOH5-VY6`Z+m7O(Fc{?FxirLg&_3&Q
z3&zokQjF(t>GY~vMag?`k|^A{{A*Y`s`J;drUfSs4|<L$T2@>fR*S_f>yWt~wH$Dm
z4-1c_05sb<Ty5#=Rc@>uBvu$dO1?~><L03e*>_2vXc0l})$R5;IqGv<KCPrmF5S=u
z1-b2Blp#_%6+-h(Ghl&(>yEW7XPbXzT%6%QT5s9jE(iguyO&3lFUq9;6;6Ey;BsN(
z+K|j`Hh(H~d;oe^Z*4D~5IFa)P4uZzjuDiPV_goE?6C!9?den^`BR!qRQnl^-J~!-
zJP*!+5EF&XHyQ0x7@RgTKRQff_|$$h0Uq2O<ce&I<|$LiH7Sx6`_iENX{O@MMqXw7
z=o!o3=n%_r&yq<w80}R*u%c6)#~y~eCZ51`m2i3MO)}|t+Qm=dNM{iyo?}v1g`(WN
z4j=V3*q74EkOG19s#3$JGm;qNumXTB>F?&iall%)<&1w?%Cwr&(a8ovJA9`VZMB#|
z{{T|wj>4V9TM=$-08Kfqrvr${6`%dOirGjT*!otTo~)CMu;scRN_P;`X)}ZSzA8xc
z$(^`d4mqn)-o)JPEzcPBsYT$=`lHWkF2JVtNfc~eLUGwwB-5fqPE`-o)z!URaUL^G
z7brO?k(yUvK=N<Sax>^DzEni~+|}i|vuy8QsKrRXVUX~@hAG?(;ECBrJ!#uh@vHv;
zXVcrCFR#5YX_|348<*(VqTp0exZq-wjomq`tzl*c5?3EqrmmlCr#^fBG+bmOr)p9%
zc<1R;n<#>kvYh%<M#fTbE&%*GQFH?WbIGTL!Kucc_#eF#{{XPctCKK4N;!~Nt`vP~
zNKid0U$Zv@BAhJv$;anK!o_f*y=mJ<D$3gAV4PEmBtt73JuYCeRU^svsg~5Z>4EBK
zdzm^dyJye=Oljl;8(M&{rrI?)XJS36R6`&7wCB{+B0@;WG^XQcVfCa0re{44J%vVD
znYpF=Lb=a>K}}W#v+Gm=o@q$wN^#nblz;)_rxdgW%`Ok86u?k2c&C*ha%r6Q;*hr1
z27n!~{xso{k@!<LlZtR`b>lRKJ7FW<o&zu8NF9Ff1p3p9XPkaiz=V#2sV1@Y=v&J&
zsNsA1*3dZm)m=spHqiFl^BS6p@f|m5BavVYMIzyj4h2}_c017PoN>~;*()B5NFvT_
zR?vbmR0M0cJx{e?w!j(hQq2*w3H7Uha1UysZu#~#bx+DMS+dBd#?on)BN62Hr%c%g
zH0v}TSpMyF;XWgq6Yv(W4Je}kdQxZduT1k8H%>XGoa3kEN_eEtIp%;AQQDiktpJcQ
z??^+ljwyM`#W3^F^Q8y3tpgp<b3<btDKVc~L&wsX3R?q;r>LlVIWhs@j%vv{^!inM
zpjsCT*V3k24m+NCc)z`2?^R0V)$7E?!{@H*rofgp=gV`^TM;k~Rpc1WSbT%^sGV>z
z=|U4R?@lC8YKi;RqkOm{9qT=-t{WV6HyV8@DRW8RHKCZagQXO-2nRG!1s>D@W{N1q
zFcc3;e|lgPqMBnTN8|d^oSX$*u{Z!!DslK%PvI>b>Ni5=!7+n{TyyoSxU6q@Q$Y}-
z+|LeVJoEfD+AMolifmTv5(QPp2jx>J+eie@=}SwDjzu9H(gBPEaB7iN4UBRtM6c&n
zCyQv@DkO@FBj5^!{d2`vxV;cBCy`mLteoI&tX_tutMl8Mh1VyFpf#0dIU^&|ri%F`
z2PYLHu=hN4s#1*P{*`T|TwzXgP;DnTsbe$dRtiQxD$JQVCl$EyA9GY@k0gUa12zy$
z@neI#@vlU+wp*P#G>~)Kir`P~rB?pwuSD?u%y)L<EC63x>7%)gO^-kEhL|j8k8U=z
zXKIS%h{@^Cdh~CI%L$bXaxQWP2e0`R!K4o<9$M}+s=G;!io6EFZqqQ^!1eU5hfK8C
z>br2o_|0TMvRk$=MRXcd?PDW>n&hb?vYbweEiHsO<dfE!<ODp5w*}Vt#9;2lB#6T~
zt~t9MQAH;CdUIAvmD7{4W~#H53P$Wz%z2YrLcKorDbS7Bs=FdBH%PlTMd$wjSGYK?
zwkVh`F`V<oIx&R<k9<_P+s%5=f{M`cs!hqBS>xLg75@O7Q<mc*xMt)7(!Gnunp<A!
z?I7fe@%cu{8GpKJjL^bprqY8*V$eyWJaI{k(*P%mX*o3FIHW(V04LIroKohIhE&i8
zr+hz)HUWx^5Nkum8f~)auQEnAmE_Yr5f;rYdShs<4-|shVF&Kws7H**86O=zDVZj$
zT(9rj>rkqkjwuX$XC12C2&^(s;Z?xE=~f~PJ5V!UOo3#+i3d~q*JG+%AhcC)y^alY
zei*iCwIya>x<LlIooPu3G6pL-l#Bxa>rPZs!y_~WU}?$088syqqK$H=Z#^pfY6|_{
zeGOE%X2oAYk)KMIG$Bwi#X#yg;-_r!ii%u{KxfKuz<So6fa)#_w^PMt%8i}}(AB*l
zvRvTg0gQuH9mLLyQh_e)%w%M9{Hw(^Ya?ZT@Z$rne-bO)Rd+{&UU}oa5z=#c8WOy4
zKN{G`;7?jgk%t2y(+J1bqy~{kN>lh!QvqnCrOf~+;+&*YF-}$Hft??Q-^_BE<2|de
zwLoNysp!?f=`u7|Kra>D=_>wwZ0(<FmQp<e&9=h4aqU)j^H5oxu>C5)0QIcPBt~2w
zYs<W3(nG2<Gn{7~Yt&XWC$X+u$C^ABI)9#14i0NdPSPT#$CS%=GqJ-Rw2HSAk(cA9
zNv6CKsrgfnN_<hy+zu<yiOS1SSn@L<`qquLya9k_EEcokw3WGMVeM99v%uPCZhHGw
zqb6=ETgQUCbL~gkV?8reqD55LIX<-YfcMQY4tuoD6|+FNnT`iak~kDM2nng;h@Rk6
z5uWKYjI*3~6<SC^z&UTNY_cF9dYHmJpwk1KyNQ-Fg~0R`n(U!}m30$^Z16bfeJhl?
zz?txP2D7TPHGvDsxcgH#AEhDAN2LUs=QTYq!DnuZ8xT44>0LOL1~Xi@g=J6dI7c`g
z>vPUcr=0e#dG2ckp^2@xnGEC}Lv5}&oy4E#T_&SB7I%F7*>1JQCEk8P^0z~uS|SrV
z{{RaQ^j1(gFSwfOBOL{Eo*6>6IVa|7>7oY%irE>HAoQ&*HFI_NRRte~Xz3$2MB|{U
z1avTD4Ap>1s38MtvsB<<)QpjOij_~bM473VnoJ3h)QW$}sMDoLDn?6;)7Pl$QI0A_
z=|B<;flmUMIH!tCV$vVFY531-7;#7rf5gN7B(ihfyxIHY;=L!uWBw$q$MIL3Fa)-G
zPzLUsevbk~vH(<Ifm%Lfc=?+?`L1(MwuL`<gXivZT3eJ3-;HKbpk|G6lT0^pXA0cb
zT+JEI_86*&_M%PeH$J(bX7f#-yHPx(^P0^%j4Q{SKNCtW<B)uk6YMAg;g>vSlYY>D
zomPoAHb#FMv?4os98qu~GqKJT_3ua+u;(>n$j7xIgbH^8xnsxcO(BS)N7#PnKGj{W
zr0j&BdM*RrK^phXQ5waWkjLhzV0Pe|l*w}<AKitjGx&be@!n}qmm_s#qTp#8s7T7p
zgnzwFE{*dCOnqwr_+H&x<-e2h#YmnSh5BDeap-AW4Y0~`M5+1IQcR1CK21@J!w|&&
zV_eAC9onzOXKesos928dXt)XG%O^NE_n=#{o|R}!N#J6b%uiFAcLEU}I+|$;I9#8t
zJ+nvwr*T+fk6MOY#=C|O)}L~cZTWvHz`wh>wL<4O2dz!VV?s?u(Qr`I4XH}Khc%sT
zu3OxVmkL)s@m9<cN;ks$m(r;_h*PP{&|;c(3C|m`^s3B^t$?J`ZrjvV2)Fjxh{<zV
zchX4iOSXOLz}!z2Qt*+AVjW^}a6L1QYo$(YdUJ~9tt7;w(z-~bA7&knI#LyiauN%6
ztoLk7T27^jKDC>6r6izWNHup$Y?3(caapB~->qEJBncthGnxR|5t(1EDrB|Cr7Rd`
zEmqY>9E^I@mWt^Fo4Lo<t;GWE`Hv>6$*I`FO1$bZ)|%SYf&+=r{xq&K@P#?xRG|Rt
zSg+zcFx!0P7^qvtR*FFLhA9EkDB_#|2c~P5J}I|vyEvp@5v-UI$XhfF>qLmXR8pA`
zuRtr8{?e8Dll09Xyyu?Y^o4VxX9c*$0CAe<E;Sceo9zDpf3;?x65rX#QfN1*8O~@O
z&e!Wn&#hwVz9q1~Dz4%uIQdxDQ*EX#&<vLf2Yd|D8AFN*1J<>Z!|EHGgY*KV8UlX}
z!=G$W1};Z&P9$xuwa{PyW!pZ+pZ$q!4hS#xGzh@R+DH@?VcNP>(rn{iA?g0rJNq)!
z5PXFscc2bv98hG!^u={4VQj0!2tJiKf&s~e5BvszIMF8Jah^S?H*M;|yJH={mPe2|
z_Noo0KxXq=H9mripgE8ohsqfJ1xm5Zf8~qUR3SjTAQd7;7mw15fy%9|%W>p59<?gz
z*Nwo7@h273d11QrsNBSd7$v=^xE$~HRq;RS)DK<Mzu6aOJDCULTkE;H5(PVNuQXf?
zMA4iMX9Mu18ZRH~vyRxUkbwOu!asU020G}f2+XX13XybsZg+2Qt!b6*nn1f-r56IK
zX%-Q#b`pIv#YS|?c43Id&^>EGhH5>&oY8P1OKW(>78Mm?VL-ofG5-JosL1KZ9<?Cj
zlbS9eLV=&<PA87Ez}cgN-j%>|f=?L()}6N)!QzlM1t#p!1BuNiYH4B(1;#z-0sjDv
z0OO@sZ!z5b*k4MKM$^)OBxAT^nqXC4f|od?Co}-y5DxjJ;0kCSw0?k70l~cmILY$x
zGHR;ad5l6Y1G%Y#;(!^mEteTJARKW`X+IihleHiwQN}4q^r)4xIHztSy)Ybj9+elF
zBQ`Pe(vzA{+~aAW1S^qF$j7||;8bI2JPH7FHVq(eZYau%YdFpaIG_g>pgvC(9vRyQ
zg{e5(fk0e%Ip+eAq}r#NZ#c;&oA-?XNF?3((;3}Q6y;3x2AWfIWbi#r04JFsIov-g
zVP81zmjn)!&Fbxd!*8x>7$b4J^PmeJdV#la7^BXIJjqo=P@YRC(3*bRbOZO1k6g6?
zSQ5m3>w{7U2C4b>;{(o*{`#aha0bA*LHN)HfEhp5pq_7-q;Jo2P<^@uTz#f9{{RB0
z4dsfl-Ekk`Ko&t|{yfwC!|$4=bxkz~{Cz0;(tm8}pk!R`9-vSK<&lr5#Wl0fHB0+%
zO;P^<A0z(xrvCtM>BFR_kM?M=7s8X;nnDA}$*jpdQDT6Fc4qB`%~T#Ivq6&_jK|uJ
zRu?xsm|K$?)3&0Xg0V-5?fYB4KC~YbTc7!NKb<~C7dE$kR0EJJ1^ibK7#7*6+r;=8
zTT%Z2eN*LObE7J8N#(u?Q~A~c_<_QQc#(6^2F*h!h~{E32>fW}V!6k7?$q1r2`fHw
zNHxpF@?-0Y?KOmbYG2=hk3m_<qQwyCNcT0YV`3RgOmPmWZ6O)Mcduc!yE0oNDt<NP
z>0umFD}}=;$ThVdyQx7Mq;58-;{v8pY-sNM*FCB^?);d{lKiSW*AU(z)v`~T2d5PT
z+P0&2g_dO?f3s8U*;hL|TkDI!T>(@lk9xYkU_Ab{=i^e;V_mS^>|a1BKeaV7+}<%C
zN<Etko{}2}*WQq}M>zcJ%?_b{Pt9{CeQBod^?=RHzWmYb<Q&NKtbyG}<5-?7@}ESO
zGRkr~R~Yl%u?NnWpRGdT;$i#Nk-nynWW$*A$zpeq?Tvse$EUqR<xX1$C$9eh>>YkV
z`BbT3fP=IOrAZ6g9&zN(dO;!jEjU`;6OXgWpK)H4Ef90%f@oV(IotYE_Hh?GJlt5_
zxBReheF&$2X5N3#yM7huk7gM1pQQrBxZ~JS?BX2k^TDOxk&m<fW}Gy8{&NTGUWN81
z9Dh1;*)Zf{j!1_&=bzZxf&T!OANchs(C^zgjB)DK=s#p^<kE{KAaE$;h;uW~*Fe;t
zvVl+k0EBk%@w{fe09frkX-&98z#m#UVlHNIW5X9@aO3JlN&f%{rNJD|GwEHyjhc@n
znmJJUju?1W;hP?HIQUNGPCVuOtG4p-+L5El$uwC7*~G7e=0ARJo`7>tUk5vKW<Q;F
zs}c@>oi5RgcB05G&NKcI1yS?dF+PHncuF#J=14o^HQ1Q9a0fJ=N#ngcAi2q}g<&7w
z{OU#UwYl#3`qxllV0fnpFgnqoT;+e^7quMilRxiMm%~=M$Ch*TuB*vY)czELB^>hK
zN;C_zoL>#v9vTr(J{`4H$Ur?YT{>CIAv+<E`{JXK6$uWXFrz@Z&3|E94v^<PO-Py@
zuu=Pg`BvE@KX#<a9F9#F3z$Phw(Sbjzp*W`{-s&H>v2eKqX*ueCPY1mr*JVBM}!Vw
zOrH4WoVrX){{Sph{Z_U<)PSFt@uge1m;gZri-DB7WFs4*P(GBR#TOeQQI7S|+G+FN
zsC0<zZiLcZX~xt7$^g&jOPEF?!o+Q7e0o#X*#l&wAEjOSMtKy3=dq+RyIUb2E=RU%
zCbV<(tLi;-P6`R8GNqgnMK4^{yS8Hn&Twi-n8lr=A6gj<@*pPw@lkC?WPO)7#{!-9
zChB>vrX3C^kL76#9;Xyt=&)JYypGPrdE%`|lb8D|XWE>Wxb&+*8IRo{9+{>QwYcV=
zFpB2QPdF5-Xtik<2j<OK5al-o$fKAH{{SHurxXixCakn1w+ly--%4D-KrLe@1b$SF
zY@LS{ucukVB+6zv_O6CaD$*E(JW3P~;S`-q1&$cmCVpk+nrxvbIIZj3i&u%EvxF!-
zGuCp&fk(8sSf%}+0-jJ4O*(bC{tS~^0wbPjL?Zy?)8}DhJZV;^@1|+TOR_=29%}Ii
z83LEeElZdzXa4|ZSdp~EPt?$Ky*zW|dv&b?Zr+t77KV9NA;&#^DRU0RL@+4|sCf3`
zoWZ0UVM0&6b`fZ%-rs60Y)`dj-&jj+ndERl=!2lC=N~E0wT0R)WKF)9rU<0q6U}NH
z=D3V*Y^kP5V?ep!nyz56L_>keB+wxT7&TxrH9b)nXPP;Qu}{e(sp&z5{YcGU5vF=(
zmtytrPT^vlP_QF81KzHAUnfISz{s*Ga0v7@x+025L$YvsVxh>SjzVOSTbz$!QGn;E
zVOMYe0Cji^A==)w23@~*ilremR>AE}+T*ob#_zhc;cYV!ur7Vg9Km9sSM)zhToO7~
zhxT-U0`e&D!JybNZ<a*&C8=`-jPn$XI2CHz#N04LBQLP2n$}o`10#JZc!ZH1$+RBl
zG@O{yDc@+*LN{fZSE;Pk-GhVeU281Y5N+k_o4JB$CL_ruO-yIpb|6Tdj&~ZFZ5@Vp
zVy1{4xjY|AlokTC<|f1|VHixjq_?Ih`yIb`eElk8y^qb(n969lSc#y3asv`+o>X7m
z=Bx<tY5xFcR*&Tebt{a|mf0m3L>a101=KCdDEe07*-m*-52(#wTR$@2%WwuqYKJQh
z$1fa=!<+&SYIgER%UW{jl6|LSVM@^^oFN%<276Vh649L-F(V_2e$vOGskUI@Mt$k!
z7_S2cox;Ns9mD4!RAp2?!Ox{l<ggs%3Sois^5=>MUbc-yY_0cCVf3Z)RbL&dqNT!+
z1N}u^wUzwLNw;X~eJdxSLK3Rj0O!{f^58E@wjsBe9L}nJb5BbPPIGvN`cdr=>`*eR
zU~K2snutR&Ju6YHEI{4;po6*TRIe_qtjHdCW%i*|xL9FjI2b1tT3JIlU4$ByHG3xw
zwN5>0<5IL-W;Q<HW}U=mOCUpltWUK|ZF4vn^6)zoSB9ylsQ&;``StSZ1F1k{%G<fm
zeY{WvnVFY8y{W!T(sl#uR^z$f9ySF7)~n5S5lKP0howGX5ZO#{HvvwIPmst9V*|IX
zQf*&QEyN?!k}1Peyw25)Gmr06xEeFr73{0@q>jNEetEI%1yC2)<ow=H{AxD7zt8%}
z0L?3bJoXT*+m$+Z#Y9m-#!W!imo6~VD9@m%OtO=oI1g>KfYVh}T$+^}ZQxcpmGRBd
z`lzH6GOzr7JA2}t!p5u27MilFaan?IS)Grm6l5Om)b1lxg(L5PDnBON{pMQCF+#`g
z$aDVPLe|#BhSWSB???@KQWad60DBsVXSRstV?ujm);mK3H{BnLQtY)=#v?p>(*ssZ
zt7D%rk$r_%H<oHnCI+bngN!VA6c&gt%253U7XtcfHn_-d(x#5)DY3L?-m*lB4`crT
z0jUJpQUPJdWyUB2RNIrzK3`g`GskW+Lm#C>Z+_vnknO<1G)^Uu3?nelIHWO6+(nP>
z<YIpcY<Gbh<$>@$YO_ah2g?MF_|plQK>gMap=tooYv*JBt+0LRR{8UT7a#9c0%jN{
zBnSQaZf7TjjA#9-cM+lX*^WR+$EI4NGs;eWKy&L<$dq+t2iuxAJ^(Tx{3y5<n(A%X
z-T?HdnpvM8zfu1H0j3iBave{&T4CS+06koN7Jw{olW#MV^c1ZjBbGR-*v|&yWB&jF
z6sVk@UB0vdDQ-Hkrsw^p{OPTM!z&Z$4InB95I5&Vz?TV+<3CrZ-4LEseQ5zLkKF<F
zG?@PYrfK=na2ml0{t@`oa=+}<fr_8I81&CHh0Aw9eT5Bx)3oOfqa6hzxlWQ1^c1AN
z327G}?$dJE`}z7UA(o@LcK~^^H?ga+TQuO33Xgin4(f6wdXn1aNM!`PkKC;QU6#ee
z9iZ*1a$6`QcO7eH-%*xdkU|tU_q$Tu+Q#JU#`>;cvCPYDoaCRvt2MKQ^{$PqNPpgb
zl*yt+Tq=GfQ|1dCrNxH)uw$RfsCf+*;hqI__ZCk+;)5J?sxoP_1t38qV1IY50<n~w
zx2H9J!sG1MD*Tl_YLxb~K+TvWP(4<X3HF{rA5lmwb+PN{xWp}rm;Mqo118v(>0IK;
z9^Ch%&Cg0eZ%M4J!j14?cITRa>ai|Z+k?kaYaB>24m;CM*)fuNqTyp;YZi=8`Zz3V
zC%m;`fo6bbkZUa?MC<v}n5I2*MZ(6ET7pBCiX|P?8kB2N_JwonSfrj?BN*>MxZB@7
z>D)&6*RB<KRR_@1B-ic;;TJvfI@TxJ2YzYaXbtH~;A?+w-jk4tidNUI$5_E0)s!v*
z_Q<EL(gTtPDclVt*Y1&t*tqwlJ|ej%kU6YrE|G!gK9vBJGht3>1EBu^gpTb;M9nbx
zj_HZ{Qn8vGs3m|uT8PgYIaZND9kWOczwL{c1hG@}6(9D5;4uxipU$#c{uE!9L_du}
z+M*BnXupjY17)=vmgmlIY*P*Fueda>N$;A%ZC(&C9Z2?|YZl$uFXL1rXU~*>%SS&}
zrWOY!j&oTb+cv=c^G$tb+;SN6_|OK&AKo|~^nj&djbbd}L$^JJNOh$PkFrWWqpcPL
zZDvL3PxH|72(ERtXCvjbln-6B-|b6)Hm#HA{nJI5&Xal&azGRZUs~qY{{8w{%6)>G
zUq4o6J8Y%F{{UdoW(P_eCjii0M;n2zc^h3L3uh=En`su`UUS8qr|_b}IuAKl(-pO&
zFp?By9DOU9()8_Le*2q8K7+k?c6P56X}JQN0fAH^Q?V2l9Q7MTBoaG}n05}^k0z!T
z=OdogGDDT?ns)*ar1s*NRD+GD)~^d^BP4#b^KX&UC)$gkGeYE^DnK#Nb5@PB4B-s|
z*n`{irUU?X#XWeZnD*z2W&rC*Vr|I(02*Eg9Mp)r#~C=Gqubcf0E$WZe<4akDdhfC
z4o(I@q#*9bc%&B}8?<ee;QG|fJIF@zc&h584o+!tgGG>Bd$0R{g(9&EIiLzqI1~lN
z+~<(QQ^UCLnuxctH03k}$BAE#cocbu9S7x1$Q>xoJ!t@}`5!Rinl>E%?M^+Z*#z`7
z;5{);z&Fc`@DvZFGwj25?BM!T*ubPD`cMQ*67J_BoMA)8PHDvY(+hw)nm{3iyGzo9
zf%jw0$Gs}BW5#M=qw%CM1Oxl|sG2ek268IH3~~n|jhyp95G)QyE(g6lTk-QZ<5O+T
zD*U{3rWY%f+DRPK3rIhNW7@41P~9m2+&WML2*xrg9WuQ#DM==fw`_Iyt03er?f%bw
zBztj#P%<73Yip5hxJkgyMhNek&0&?uuR5}{k4B8Hh}Y#6G%OmSQJw`!7{hvd*E>25
zdp9A6b6To$D<0Lbb6RmqG4-frA<`y!9cgVc5QFPT&%va%d=?n3@UP!6#A^cQZoic@
z^Gyw!kTC6Dq2>(51aaD(nojh@$oAw>j+G`j#WaEi050Ep4+fe^0P&xCX<~S!1e>|*
zOf8yd&v8pY4JYRA4Khw*ZoJgHX|IJ8n9;!MX|nQBjNs<8h$Q3Iwza5sUb}k#0F7ia
z`kuAHQ$}~g;UP5>0na9;agKtaenISMBAJzbgsyvv&0*`!ZOnnyl=IrNCbeWa0FnHw
zqMVLek<_Ya;-1KJ(C5$&wP7^fLB>|fVn5xjlQC$gid<HLXu6z(KVxz1c&UenHD^EZ
z;=p>A;+Tw#A52mHHMqVM)(QUrk97mrIjL8{+QSq3w4%Z}?!QV>E2)dXnxn4i3V?cH
zPHOZY4yTdV&Y8BJz+#<(=Mj!`&{7No!OzmYE+2<hs#Lix>~mWdz7Eo@j^he5kM?QU
zE_rsDqh0E^3Xvl$f5hZ|b?bUAkh*26Bz!8aD)qLXZ)!0NDvQ$stq#4ZgA*K5fleo$
zlwkT$A*50T=AVqx>?4Cf4f4t76paXF#Y#A(C*`1LKYyZm(+Ll5)sr@n0uqGt=qs|3
zwkGblu2)l<XOx7Evz!Bu*07p2i!!Fs3V>0`$mlAhmXk($zCArFN*QlbPDjhoiql91
z+UI~s=xZiubFoh8joJKbPTF5I@+ofg$5Wk{BC5g~-bG`;JmAt9qbvY(*0U$KJg^u7
zw_(N9InN@i&uyH6){q>n%zW@L)uo}%%QGjKV^hv^QC{1a*q&=D;4-TyBxH6qwK;OT
zktp9n$B0qp)i!yXqTq%nH5IXj0-*-qdZ!d`BYgh=g<XQcNO8Mp?rWa4PG;HDLZ2*2
z*)6Vm;GWp0!)(cs8xi!W?eys4!Qakm>=BLNAm_QRUS@SzOFK#9JNM*+n!5Kc>O=mO
zYACT0FY=sLZOh_f6ymdyNf5G`rd7{Y9qVS(YwFRD?y0QpIy{qcC){2IYv|E5lNp#}
z9SN?iG<7+#4@00vBkxq3!Ctip>GM!J;=MD?F}zuK_I)|KWpQ3Jam=N?de@_P{_v%`
zz&Xx4*P5}(K9wv6=8}_kD9(G*0pgbw#cWi7`qL28$I_Z=Ok`6?_Ml@kNW+e}ryjJ@
z2?BsUf5Hk=NnSCKD?i4%!$A+((B+$qR-c7%nmlBXK3;2?@p~lK-zno5C25G_nTs**
zd(xr9b5;$seTfu?)<0SXJUmCONUXWys|XMpy=w|?Tnw?`Vu781gW<$3>@vgFwl$>r
z1Fw3I!}g7DYNeNM?rP4uLAM2P2<Wv8q|R+wiR4qVI5?=(v3^J8PxLhmX_qaeJFr*r
ztrU?0@|B-#L0~b{rD~$(eX3Z<&BC9%5hkIU=#D(E#MQPO@Vr%9gM~jR!S6_;GI^wb
zU@C1CyJ~w+JOiJ`qL}1!R<tz#08b5$n5u~^>zB8+Q`Kxz{>|flPBH~uL%})eO(Q)<
zYhyFRbxRp6FQkRT4oLw0YdNu9pN?Tj@0S2>J^S~rG5Y3{5YNJj4@xNvS}4sZ>p*~1
zh%jjsWb~;4;)XI<rSe@^=Y!h4Bg3<OsHA{o0ouILP`Tp0C&9pdm@Y>ZETng^HX;Cb
z=A;3$)YWL@2_H=2o-SCQyNZ&_@PbI@xPKe!mvGz&T;dbJ9<|y-Hc!&1c%wy+R?;1?
z7DXR=st(d7dmcXbv4<^;=h~t-p~uR&s<T^56wIAUoE%V*6(E}QBPPy9i}6h(pS{gn
zgXVvj=M_p419YpAob;^`n>6j!dCwxO{h=2jSM#j++~XOkmAL6tNk7^dvIi7KTR1fq
z?l`A_Kovxiutfk9lkZgIxdU+nJm6K9UCIeOj`bVFgPc$XJ>2sM9e~DLwP8rxoyqyR
z>T9le(*%z7&T4kT-eZA{-!*4eIvUevdmMJAgV)$nzw@Rs`CHeea@gG-f#F4!v=lMn
zvQHhWv9N+T6`oKS?L2x{HQ-W%L5CRb4RntnSY$nZTvs%e*|ON;wTH==AQ;a8R~I@d
zRw#OAy6eezGo8n4F~`!l>yffq6dZDRHE4!+z7{*Qn2vhmAC+}c;9|L73j#D~dmIYt
z;TZt;tx*J{u5(&?O5xqUg0l+oiq+B=mcZ{+2K--iRN!z9Y6KV^>T%OGBP10n8ig}b
zry`RAVa-ap%`tgeco^x;NXZ2~b4(nHa{EvOs%k+|tw;?fG2(;LlfGytD@Y746@vOm
zMgAtP6j-1nb^6zD;>p(EN)tXdsjoSI5m|$s<DS(rDH@3u!L<%JroFt5r)-$|)>8PA
z$Pd5Iy&v$C*a9--R(C4Jne=IHP@~+i9@UmS63%yhzESN~hl*_T_lYN`6yxHHVA#m#
zp0r#nKGVU_L^sKB@}A+32DTy7;I&LeA0G9H{wRty$>~rJ7{j#iaZ2E7-s|@IWV;#`
zVtqSRGvj+=c(#z|+NjIoJ4=lDkg59jsE)N~kUq|t^q~!!U+|k-;Qr;5j=wE8{u2vx
z{{Sqc1JnwF8>r<6%C=GXR)Rwa0K7@`#W58RifvuLi$CtvtE$g)v`21mPhU!y!)&AF
ziAFoptK)>=dJ14zSly$`yA1XfUF=ZxmGSOr%`1`Diaf$_twI91)1c^AaQ8K4DAF;t
zR4DWm<vWM;pztVQDPDTe5HO)m?$qpUG=N}_X{V8ja-H8wQWSmTieN-z&m)RM83&qH
zxQzxglTp3d+khyz6KqmCb5(BbBAz|6CRfuGvE0bdk1UbvR*nkx`WgYFhtzy53mI)m
zQhK30Rwn&JN}WURP(KiB(~iTy!S@EK-Rai%Xi`)Rr?x7Da+ZD|hFlAftIjj)S`u1C
zdHcvD4eSk7zwoPVceGsd_bUw_P|~KuD<ZFKaZgbl5w>X84S+>ey0U514>bqAX|~$z
zH!=BlDg!qetBI!D+=X<Nw)-_Zh|h+_ZRFn9D$D)cRqwZ3MHme(J?R@uvx&J!I6ciO
z+1Q5N_F#MDngYWk)GgTIS)1r8wdKrmON8y|TJWp~g@rcv0;Co;_}%27qTyqnJg*t6
zT67ahDKV!52PERP&9qD~h(48>HI}Engbt{Or!-tf$w{Lit~2SHWBsN@+FT6#))~{a
zrXTV2ppLnwe`4y)K6}i4DOjR;{4}>RZkFl(fvO?lJ7wq3WAvnL6Hv#^e$)*L>5t8*
z98qR5@_1U#Fbhm^(;25Phb+JY1;5}`V%taAw99hx73Y)IuFW!AE<)r1NJe1r^^WoT
zo(E!T<W^9?K12$AF;T~@+DLZp+TFpcf<%**IpehhE51f}s7n$~?zMMjM-;}lJRP*`
zBC?!&Q?|t?$m1(aot7`W*!*gvT}a$Sxc4*ww|Xt4g!yM<<AN$XTitI(Ikuij0PJ}b
zBi_d3{H`0Hr8RXXj$BQJrD5Fc^k0dP5+T&$cw46Yab3NxuW6_#dub4c864M*Ngbu?
z<oRbc4ZJtnQ<-%8w#WBPLx*A9_f_EMy*qY(mF5~x#7moHSoI5Xalv)2$4>D^m8xwC
zau!4UEy1a2t;TN#Blv$>44Zwah<AO{kVhQQW8B{}E<Mc`7#Z7k7o{kX@xdQjQX&KI
zp#K1Y3OwkQe)@mkR0u%NpP2p>?Ee6@QN7F~pE^Izqc_%}ap%YQPz0{z4zz*E?rN)Q
z7R9)o2jfTfg_@paQSX`nx;O2ndeu{^+4KA1_$?>)wVr<af8R9h#9Pig;*>u)&1bf&
zXO3BjrvCtI*?=&z7Wz?U2A*+DGBF?q#bg~_3v#YN>?wb?QF=g6)v5BZxvL&ijOX5@
z-bbxre{Y_@X4{_IsYbZi{{T{%_cU@axwg_DUTLC6&0-yG@t-LHK8Bce*}C~-@u$eb
z=KlN+MKH-Uhh%CLcWS~q)xpLU7x18KSG}2W^rMl5&F!UE<tCS74CnH$akX34AL~f=
z#W3nuc;<Gak&5R`10IH)GBKVjil11%Pm%{>!@XRw)~}7e+k{fxpS>KRbFFn)*K@k4
z_oxNTI6pA_>y(m7rhU@L&7V_ImD_`pPuYdeyj<I<=2ZUxzNroEuo*KT9l5SJjl-U4
zKt&h_^{4E^nClLuW)527F+tUA{{ZLVF<h3!&q@ef<Wu%yxz#qcV55tmeu9|V-kjqG
z;GbZ%%U}*VQ-X>;nhTvO>soT-Y>a(^(+7wwH*zKV?XGo~9Xixx7RMBOG#tlCFNrkq
z(PTeCP@fXnf-wY@fUtqi05lkRr|jY!$3lEagQc0l=y!^*{{RUlNoKWX1F&kxSnxe)
z*@Mtxj!1>gv*Nd5l(HLr+Z2DoRWTe|u6-*M3{wd7qmm(WW&BNYNX5DejQE!K_+vmt
zWo_e=O(WipSc>M8c#~4k9$5S-t*>ewrUUS-!g$VUH-I_dQ{{+VnnPE;Zd&F3fKyJZ
zf4~#4thc&`Gt8<F)}I{0U$`BIs9G%$yEI0vd<Qd=PHkHEw9Eji1nuofzuKLm7cRD`
zdU8b1pIVAr+o@FUna+LjPzNWq89mc9Sp~@z<i>o-KBbK*nZlJ0{{T|e5oW;X2c<Q#
zGe&~D0?s<f=kcUv+;CWtk6LQOcW@8c?OE_~lfbJ{>6(dLn^Fk>0BVcGH7fZ?4td?5
zT2UD3laH-SEw$CT{qib(4r;lS=YyZ67eT2e!~;F^NI5kbb_2a3b^zcLk7{}a$%K9J
z_|vwGV-*>jYJJ!L0KQE=B$|F!89?`3QFH?NOOAk2c|f*6s}SjzmsyPgQ|fC`JSs$A
zzPo(moKka0EMlsUQJO|XBw&ozjn0U+>6oQv?a8W1VRGl?jgP$?;bOT?X$pZ?8&9}V
z^MJooQ41$M#(uQ<fPiB?sa)WXTDH1v#xfK2r5a`1WVB&^txK3JQZ2<fetwm7X>&2*
zqxxp8>AG1<g7P}IU<D^2v6k2?@}VC1>rgituIf7|6mp1j*NV;5w8oqMJzyJv?a<Ww
zLb*;)atcL}82qBN*TZ^~$(bXC2m94K_-0^(ZNe$VS1~p+K|{$}8MDx1=qmhv9-O(|
zcNgJOwuiTdy<GbWIfBMMJye=FAH!Pz0NGKf=IjqnDUGEgV;4*K(abv;(IZMfcM)Pc
z3X|-&4bt8IxUHQw$~#tNSqrf>tn8>NT|x4kirZX~pR=|p8aYrB$^~s-o0g2bxJbdk
z1Gua|DVY7@MI6@)4gKdJfmT+~GzFeTR_rN@3*#Yq_oZkgJ$U*WVzE@aCO}Yq>4oOq
z_eEV6`Q*|Ia85H$;wf&QvU5{gr1DB5+m}5m!9alg+*ZDg1af7zWwFI6O2s5o{=~U#
zZ@5MLGgR*_MUw;*`H$7O#w)UGZ<p@zj@8R*w#yyCeu2GeREJ|2@6Rnw-5@+M6?4m6
zX9x190Hl4xk6cyUf~v_P_svKFKYPDwm0di*p)!2{%~%n?Un&0p@0tcv2w3sboFkV!
zFXL8~TcM6YkM<2;)9fxKxDHk0MdvKPdX>V(J3S_Axfgns2iC4j;n!ZWfIS6tp>P2`
zt3Ob=lt;1^=lGhVnU2RdK9=!x8DH-cQ43CaBQ<7C&nGXF?rFjy{7!@Ms{*iq0fOKk
zQBM}ASDC*dPH+c8DPi)7K5V-Ou%JS%oEv}R<Np91rVDFqoXmc>r^uGX9h15IDiN?a
z##<h=t_AB|5iW54c2N6sTM+5C*3pDW@<$mpTTaz2A&nw@gVTXqcve71dWkZOtLeVa
z18hRgw}2~+n9T0XW7=5fp0(NPu|D0YD2<Qt9@Ug|n_!ui`*WVPQ4>ct8)^BfWS%wZ
zo4vDIhefk3{{SB(pHWJ>9-a<lxhFMu5l%a+MaE$y)a!YsXAcH{3cVJOq=Aj(dzPsN
zjim+RV@l((1b3P-1xzRMt9I~dnt~R!fHpgk#%h_<bmJ!zH$AIkNqcKYF)QakbW}Dn
zTO_-L6_zm?kGQC78(O&EF3&F{4wcq37G2%3n&t1W;x`g1+XBnRb3y|Y%Y*)_@)aVx
zu+NkLt3pF7f2rG^!lghIe9@d$+>(hcj+p!?S#k8OKQaVQp4<^gC$=3eWA`SN$6}J)
zCVDBWQCzcp$!s_^6t{N#fU%5zl^S0LJ5k2m^c0%|sjy=#YS;se@lL;ViUxT?V0LPu
zr{6@%A&YQv>rK`ze8|L-46x`kP&1yqyL*{gq8}kVcBo?v4&n`43;a8AN*FH~tGKKY
zAnM#zp)5+c3%l6WStSaYE1V9(tBdqgffFBXv|Ls$yU8Kr3O%YZ87G#g{O4o^V>vyl
zCZ6*nY$yk=Xt?ZaSRh-J%K$Uf*ILCM6%2Bsy!m9hR}F>S2+mD)wt9`4TB1F`57he9
zF`0V3v;siQFO&huRUdk?@o%0P&0f`nH<JdAP1}2#q2yqF;Y|S`TX1;X-&%2KHvPu`
z0KTdb7~lrtl&UD<vT584X>n{iz{l!ot#JuFLO}L4M|Mp;8C3kl(Qq^t=F|_K65o$n
zu?_8<GHy$Kq>9NdgWS@s!lBMN6qp^XQb@=eOpifTuI-xUG8#O^gV()bMXpO39S_vg
z=J6b|s7Klcdm53GNq&~+%7WE6;IZ#jB)#5AF(*FNPD{Zn5^#SSiLMjael<yfaL$9W
z=jlo%-I0(7YR)pmU+?Ch_K1*jSo#38Tt(u!?^YnPl0@H(4%w`qv={rK{{Sj;Tuh{V
z@(gqU(aaV%7e;nn%-H%>+iOROLV2L$)Ymipqi}zUR>!?C-aC)F-}lu`?lYy-EnpVq
z<Yjq(gc`t6#y0*H0lAfr3y*Tt)|O8}pZBOvz{_Q53yP!W$<N&X0KTaVubx?dI(HGI
zFi$3eyl_Y7S>I^D&gGy?PgnewfG_1i<^KRGLh3rbXSDwS?SJF6)}J^V-~Rcg37hts
zs#~tsV#D5<cd12j9v3Pr3w!79Ii=ml3nP0}fjn%9#!2-xD4jvTQfi{Bu+Nh((6tBU
z<H~XMYM?B=-=Y#}KGU8`<LYXt2Y1|G#i@2={mAqF^#U$OHsgcG<4<daL;kP^tnP!N
zkH)5p%0GM{Zqy8!wHHu)x98kcM^?JpLd+EV3W{iX&zKZ?VxbC(c#xlPDn?uv(}9yW
zKT3_RrIRJ4=l$A>MZ%0bAEMM*3cq>J)Kw%R!pk#p=M$d1Q}@0{&iNHpWFY*aL+?@o
zf4cegCYTa=j!Db8<E1c$W6tdN=A)2&r{y36{pyP+jt}QZ3jh#1{w+ZxkC*=d9;h;U
zlpmchUdlbG43skGJ6Ati8IuHIKMIQ(>R0fj>7Ji}qQP<CrcO2k^r55~#^LnEC~Wi~
zf52&_@$3HpeA5e#N!Pg<_F8jZ<X{&35~B+vV*#=17ME;;vl;|D?F@eCZ><e?F9Qr|
z6i7zht@+Sx<s+E$^?XraA06bZ%B+OvxoWUOD)6K5HAulK{{YK0ANJCn8qJ=ukE_xc
zt{)u$s85;*+qdy*y78{i46zgSs?Tmg{{WAemp;@Cg^kWm){h?ap(ZLndmitlN+2J_
zatG0BGXerX(iy$N&>=$12R9M@HqtP5%9;NF@0FpVk3Z|A&-=825OjGCJyxBBD1~v4
zIgjB;){%~U**>(4nd9fC8*;=CpZ@x$1I40e@5tZqEKqIYUN^t}_GzNn<nT!zuZm+?
zu;ip?>hu9IhTJYj;(y<!GFzz`g-QPadZ7@V+{Bn4?No~zbuh$F){qV@YtQab3UDxI
zgpcy7=kMSJA4+yyaq{~dQv$)7KFFgTfTsDQ8Qb|SLK<Gg`gEz#NJj0=`A{LgY2yR`
z03D_CTm#E~6!EzK02|VIZa~iS_)`KB&KQud^`}QP%0|>KPhxROZRBo3NrCH3Yj-R6
z8z1jd8Eu;3lZf%2+qzX|f@N%&fjREg9BJf`0v<hHtt`?o%LEwrq%yR-l>F+8^lZ}u
zbNnBTOwhgyl?2pfSOb$9{Y5YjGjDVhEX&SWKPrq6=OKaj0-vyB{{XE(4)c`oBqQjw
z;z3jMx%?@M!TZPZr{JIBV@w7R5BJFS6driQpUS1r`%ZC47d?#vD-hW~D}E-N6^f6O
z^{XCU;rDU%H5(xZ8$kLR0ANP$qw}L~?h3AcwEScELHEr^B&`~pM5pOU1Pc4Hh{ikh
zsTCU?SMU`acM_lAR2}jv)OkO}kHVM`u-*JXeiXqQe|-J|tPpo{$Dc)|026}pAEMF%
zt4817Z>1n!ah5f2Vv+v<Ef48PBOSv~GN3~3jgEgBy>8_Q9#|ga(|ok<r|Ft$jR+%P
zBd;caH4<cg;;pT;b41150qKgtR`Q!G9Bb|kU5`>wxRsQ915;s>`F=}oOpqz<c;R-k
zW8W01Jaa{um@qx*CS+*Ju;(3U)fKr`Ye?@AzG5@i6_0!2SCw}{Uyj)3w_%DwAlsd!
z`c~SeP!>NnDwM7(9$znowWR+5QrQEbJ^r;>v_BF@{{Sq|kEMFrug!tLsdi_bywwS#
z$6rnH3ZZASW9f#)LYjYwrI0GwpQ$zN3vImR>OpD)eZ|El2adOgd`79g-X#E5JkPGj
zBgN!4SE*F5dV54+$_lLZ5VlUm$?uAgJT@zRdgOw(vp1n56>W5n6F2<3W7y)og>Awd
zc}N9Fv8y)GjQdl#Sn-)WKjJLzDnA25cx%KWJ?(%$ySlxg*`dx*9QC9Ya1KlW{b&*5
z2SeACatQwbfm5OI?}#pVNZ*6~?kn58n_xfGMt=%$k~JJEt`ABFW5v&d{6q)bWBApZ
ze*|k%oZL!dUqIZ~uYIWlADm?R)K7N_;N`pUDcn{(%{&Ic6D8#2cNIK;4{g|guA86l
z8t$HWorns0^TjfGNsR1P1aZ=x(79R1ufuCR=3AHl0KTfkUk~(X*9_7~-lW$-8oS|{
zo0_(WfOo1$gP0x#(YJ9CKaD(iKSzxGwy1yJ71afZ4?|8^EuDU6=BmJRE8#688T%|>
zg4C<woh1%Z(h={9=nODp0o(GX`3gtM)Wl;Zg<yp3hB7*R+LUQlV}S&Jh^+>XW`Csv
z2Z{iux_zoPL=l7ZsYRu^{{WUr`BeDlv8S)z#Q}1+*rNj~7xJfw5eF)y{VLYLIHWNl
zAeGGkR|<o$rv&r>eiZW>6Zby~f0lUuRE9;hbI@njm3I0AflrZAEEg(1rlV;iJsEwm
zK!+W<^rr*I0A`~Or_z-lBdMTc^3>o!UQQ{QVtuK2&ou0SagYVTB>S3bjFZTuJ3VMn
z0OE@QI0K>Pkc1r+QwbRKrQS0|gvnM=tHO#=At&zVH5PNyq*nE!z(3_b!;?*Dl%ABm
zaoZFU2Q;iPg4#1k*2|y1SK6JpXWE^SjOKtK`z|_4e;PcO9UCI72~Zw$nmp7w!2Brz
zSz(a3QA0&KjEKuslPZcqDvag7S_V@MHtcx~N@rogh>Ex7BXp+i3_31p0Sd@i=V_!f
z>_2lqK~fPX@PK`)ctK8fjo!4b##d=y8Ccl<6$jhx<88A_s>k?8TGEnMafc%vFe-yt
z+p}e%LVao3upl><&G#nH)}0mAs}q+Wok}d=RmYOQT5D;x@75Lk1r`x9Ttm2k!`B(9
z1EJ+uAEBy?rP~e!U#(b%(g+FL0L=p?LAc{0rPw$In5huwXIfSugYutB1Uw?+uUb|`
z7|uFXXNPkGmt1xRfoh<A_v8JlU`@0G+Ks9^{VE?Q1C8Y3l)_kit<5fEfR8lM$26J2
z6r(5G>sCTD^+?2)tU%>?tSG@~@!Z!>I&X=={_hpd#DGle&eh-(*0}L2soRHR0)y>N
zROAnOl0^#KQVzbqO5!_FcHa!UYeFctaw?Uw0>Ju;(u|%3LntInFM5jGhBabA@*1xP
z5*pVJ@tIfn8D^AyX)tk4=quJolrC^+$mvPfnnTur6t*d)zdA-kpK1c)n1gjM`Qm~(
z=}rS2(gD1C&_-#)J$RswC;_;pmEFJ;@;Ks;yFeVLh+)HS<CBt4aa_?j9@W}-iUB3L
z^dq%$4hG^qD~h&~J7~Mag!LKk(yO>XHCT1VDh33vzoll4Sy{)gdW?<3{AyQH4L1Py
zHKHMxG+Si2)DcQAu1$JXwX7);e&l3V58+!+Ht)>AC%X=vfBMzvDl)1uz^<x$9JPKS
zo>X~1ApEJp5HH*u)A2^$!n86IXy9xZ>48eP90kYHo%nM}iU4pY^Q9?~&jx_Kc%=gr
z0Ma{Vmv0!S0fRswPy%foDB3ur&U=1zXBngdfzLD&2<b+1OSj&D5H@MTfV@&<1I+<p
zX*-^jd(&lj;!W;A6ab|+Q%$-PlB-<Cv9H`27AtHj{{RuH5o(u%m6s%X))gj^(N3FZ
zRV+|Nl2v|{pEcA#{Hm*p$~u+q-`=8(b6J-f$w?2IhaR}%vFA1RZ5?zvjjV(TPC*@M
zXVR^1z>+sn^sWMJawl$1G20a!ULx{yvUdRRd8R8Jr;sdM;eq-ZmO0~P`G-BLjQ;?H
zo+!fkk{9--$>TIb`>07iy{NMhv8u5Jaf}R{n&z3A=3qOXDy{E`E-%<Aiz7S$YhO&$
z%CfYB=RBNxQ6~T?LDs&?wJH(jW8kzb0mWO2*}=#-_04EO1{5l-Y*=Z3Xn#;TlU#0B
zXJS?{V6c`|`HvavT?K}Z_GrsLe#W$x8%-`C(h$xLK&(wuU)}OTq@P1Wb{Q4q#Tc$Y
z9jiVFzSBPc0N_w^PkLyAS-*R5?222Fo=r$urTxq~2s;k6LY>(%sbWcHYl#vFR|$@l
z)7e4fTOzMvj8#oPPg`G|{%KEEBD6~cQp|7#dK9Vhqk^qYeFqcJ=8&*ZSoNq4)L{ML
zQC!?0wRQ}r13Vs;wahGepNy{l(Wy8LaIKyzlw+U9w6&QGy0qkzw|4;59iaXcghY8X
z-KM75icOTjj|5VN=bC=bdUHm@KmxEm>D{qSC`BPWPy(L6g&4^L+*3)XNAt>y$5B8Y
zmuqnL`WOgy{JHB~t<Y&*iE>!=HFo-GBh!u_x8YpixgeI`*WQ>G&9->lL8I)!c_y1|
z=H<9^?rUPtOG}0xYrfDq#}v7c%y}a~JpirW4ruaAa4v2ODlgnZF;}9nwzoNo43Ydz
z&1hLH`;Oqi9)hLH<sA$mRdJjTN~No8by1P>)6?#Onx(2E2*VCee@XzzkpjQUX{aft
zMl5*9?M_An)G?Or&JRl1jFTGntgCUHVzi)Q6P2XOLyO>h)oGoG>E5ld+%N#<s>vHK
z-l!RyE&~#4LqS3Ir*`R#;<KeWCbaZk0X~Nnq)BH;KJEv9N<v6H98^K@anyCCX#nI_
zre~e_^4-P4%Y(FaC#7)D$@*8Q_|hRYfhBq5gZNjMu;6;*nnEMR7^TK(4Im6s=O6uQ
zGm%Nu@HwCdDd)e^uE7Ce%`)EGBXd>nF=9=l8TFuKOq*4Qr=@pZ3|!j=9erzodA_)>
zL->5r&0~k*sWOq+Kz6PVJk-XtBeS*(pEXCeX&xIiUB&)icBm|^2^sViF09i30AtFq
z47M{-eWusU3klpkYg*M7Sc<*~B7rl&Z{4H2nOI?g$rVAaPI^~U<E<$zHHLV|!)JDT
z*CbR|bRE&nBwB)IY*o}|^{Oy97^{iSD|F1Hi?Hy(p1$>cPDV~EE+#o1)p|C{^{Yl~
zoHh?imvJk=sB`ku(oQjovPo2A9MD%Q#Wh>no=!m@tpY1bpko8QbK2kf<n+O=j#MRc
zn#R@byx2qIk;P2a(RBAY#wRq~;O3RbwKt)z7ImZ0d=dWuAW_K#Gjaa_0{;N(*HbjA
zw(_3AbBf}8BR`j>HV^!?Z|7YN&DQH#0q1bVWcM^V{{Ss!m<bPGO6K*8SGT>8lsiG{
zdSbdubD1)F=hn9kj2HI4UBd1Jb*o5*QSh4QNRP4Wk8ai1Kr*}!#<29u6|jIrhmG0#
zdsg%#<*Gs?BO|79TDmC8zib-K+v!^RI)Mv!+{FGBKx`<$`qYDw>?$$9AIh9R8jvMk
zxvA3?0`cop#&Jjs3UN{n4Mw=)r4=I-8gQoL@TUp@l~1imwF;V<4-}Zk;*q*jg(Lmi
zKyqF^aGo7~{Rbwz4o$m@3irPrM$>34iUB96HR4j}m%EtkUBAQ4OG8BqYguj|Y%%BD
z^sQ@e4qi&j=E#V?tI4dky13KZZz{vEJW{T^cvp!TO-+hBn{5KYQ|E{l9sO#;=z4L+
zZQ~=}y!31L{TgOI^uO?sUj^nyKJ=^yqm3fLcoxu)!jx$mct7ePCcN1Aiuj%-G>61D
z_|KSVu+L2zPMrA65S&$8+g&!&5=0S#M_hETJpSLl{u!7PNcz3q!s1B}J$>k~9ejG7
zy6~78?^dF`R$zAmD}Wbnr?2Z*tu->389z#)9q64HW7eqNUCj#siN-lKlWnUg0C0V4
zPAkZ+6Vw_k27I0&Xe0tacAogHJ55e2=)*@MmhL?(GgH!1@j;2UxaPU3t#7p18MZQm
z(62eAU_A{aa56cm(p>UuiPOAIBy1L7SuyvGbk_Q<tnsTWFU&dvNM@ooA9i@D9k(yN
zQxl;X2Z~=f9y34<cXc^T(yyN=$MdBv^3&mRM=gp#BHEHN&CNYfD&Q_#r!^;-6SjV|
zzGy$f2hxBV7D9UM9@O&+I^q6mP)XyhE+5nAC>au4M;F{pze-XLdQ<YlsKq!QI%b%N
zafZ$fR=c)>?KVvqf3035H(^X@!90q05yt917i_cIH+=0qF<9GgwAns=$TN}YUX)ZJ
z`FN_gcF@lj$x&E!=|#kH*1GMysj}%XPkM^`N&8G@TN%jR$X(nTn(xEt@)2zN4s-KW
zi%kbnwfU0bGM<gvoxtYTPuJD9q-1-OTN-tx>M8qv_9vWYit3b@q5boqZ)#h2hIcEt
zW~o?C=1_8j_i-_&iEbG43C?SG$X%puAC)vjM@6c#4NNlEMX(_znX>)ch<`I(5R0c6
zrwH-%qd+;Pw!dyRCVsT^)33tekvR9Rhz#Ijq*%**sxron26M|}cCCh7A8N3cPFLqZ
zezm^3ebaJb<JUCSw73KPL;XPMOF%gb-wHu?%*uSS{{VP_-lMnhwbi?2FY)X}b=wHx
zh6tc2EzKGQnU4;aDlQseeuAZKF`Y`Rq-VWqgvT_~!whz!=qzHN3)^nq?(D~m=A=&#
z*{?)w`j)Mr8NQU^7VdGurEsy7noY3B$PeQ~Xx5MSp;Ml<u(q-l$Y0K#_DML)C_a>~
z7BJJp`h0J^TPEt5X?Ds!SW`8x_A(FOA4+RN6mowmE;|{gPqt&0iBGmDT{hk~+>t6C
z#0tE@RDdbL0qaLFScG|sFdgyrrvo9+?_cw&yrG^AI6|ammVstLw1b_@ex{L-p6Bzc
zLO7T26ZlizZNT|AF{gAEGsGF|$)yme>MGc1z`+KYut?k-QE^$2`A80MY1;)^4GIhp
zN%o|YdvqV_WOL{iozPj8!VGn$oO;#B;`2s)vl{!JY3pwmdSv_4<_j{06}W61Q?_xy
zC+S*35C;mi6w<7DRRedeCm^vw{!z{WreR3rijc--eB&h3#+f{-Sz#C**wM~A5ReGt
zpQS3qPb72iQpS^6WM(0sPHBc$c?sRtj$p8!Nj(N=HqX23PbYE>tO2GexL3)Tk)D{P
z%sx;sH~`{<Z6I9ZG&^0E&hS+B#Z3j+jyyjtOPz|veU77*#V~9vOCFT#%cF3|ZWr8D
zb!_m<ntHJgl0^d>g+kNq2aqakASd@CoEi`YZGrlVcCd&ed8Ntc0QyyhSr}j|F+SBP
zzjcpfaUzO~`$FkCUA%SzmDmn8w_o$gzLgr=$|S>~1bWqreOFPPwk4T&C)X8nSCvjC
z3a{*QQ0B_zGA^+e2J9b7rq>Rqh8U?QuzQKi%PI8Z(we$7Tff&y^vzmqO$fI#vA}L=
z=1GAEdBsZ|gfSk6KDA^;)8xpfaTE)=Y!XgrCDdn}R*|<+_wWTO#<D)uPCk@eb~532
zo<Na;&z_Y%%olJ-h|!;$ueEgcI!&~AlgrrWsjAwY+C&UW1AEl-Ty`-U&PBq+jLl2-
zE5JVDkE>L|>j#IXo3cl9^`<5<Y-cU=Ix70+tc^A$Q~sIHsTEnIW83hknrt^el{<*K
zH0X?cUgZA(yHw4L!S?y_{Y^2h6c4-yy)@jSj&j8G0A_%(E7}-7XK>%{^sP-Q*4Fwp
zK60q&%0(uXroGdNC)}yo4|?8hF46^Jkf=~O09G|G(V9f7absm{jpaiLIQ!=r&2y8>
zJd+sGV2kv|D@Nk#6_KG9%tz@|XSXvPEG>iDh(Z0JlOg*YE5w(jo7htXc8ez8wK4VL
zoHY3tEFo-q)0W)r`O^cXZDTQ1*rM|8!@0#wC(}kS8y>Y?(kRB&i}I+1A&z$9ivgm|
zrArweVTh07sciI%TZc&!X&yZFHJB|-tf(9&Pg7lvon>!rZWcCTG2GP8LXh~NNTUjf
z5Ds{%H~N$o_)YuU&~&SpvYmuR4&&HYD?PA;7L@Goj;6Cp<rd|=ww<>%w)}MFlwLvr
z0@(ro0CusYxhwL*%su^Rg68r!3}p?D#VYM3vKF1qsP7YT&8XwKTvWqQMN^wq&1S9b
z#NX=(E9eF(((ib;eb77Rk9)9LcP|Y`=E^_^;ZqGww)1Y^m0+#J(LPbywk#6z?5jM#
zCUJpENJzhJs62|^U7H3Sa%$`n`QV3*ko(qpiJ@YsIPZ!sT3I970SZSrtn5)!RlR~a
zOmL`?$KE}KX8p3@5wb#~+MOaPcEbKN!4b`Fm5~gJNghrlc5kgSa2zQDtociyyPB~a
zaG(XO)xR19XNj19%U{-!rY<qOpI~ccX0iis*rOiUsZwn>?=`3c=}O};0=$idRwUO$
zqG{7Wg_*Js=~F>>r^?ul*@5?5R-9~`2Hb(^QrSS!l^Nb@ocDf6I|k+*vsUE=m+x&J
zwTp3m1P`$zGBDtiNe<-;tI6kV$XuW9rB-KfM&*BQwRihfh`_g1KD71J*aQBKtbNT{
zCU`QqAyKjJDGXB;#>PK|Y7Jr4axLRrcFiyL>*tGg>FY(n$?_)ve&$c06sF!|jnKE{
zTPxxnr<;7AQBSw=6G?Qa)_{Z1^`zJrG}|<a09ih7e$_kMhUh;NR?D=YH_EGut9tJo
zEFfUgk-;6RIgv>idZ*b3?&rAyKe{T2I&&Y9+aA7^WBUqun8`fR2gW^3C-x@Ko9!{L
zq4la$k8tIEh)h<y5AUS>s%S0kRX8rk)QX7N%!mDKZSPVm-o&5@qQL$fb)%UJm5%!z
zp=_6seFaLfX|O0SHc36jSN_u~N1Y5~+!})OP>w|T0)Tj?BV1c)vmnL~YPn|wP#{?P
zb|$#nX&Bt8lH+V&#07MTt!eQ>xtRJ=V@TV^;5qA9ceCm7-0YAvl7XF}b4{DX_Asd-
zhAR#HNogd<YAy+(0jC}9xo_QR@-e5i)Zf9TjC<C2@e-ih9>Mge+r%;-<21=M{?~Y`
z`>RM%z3L;YU&q0Q4}9jbA6IAOmdWo>olKK}3H)h=jlb<{^WHJ|Rf}C$P?m8X11bLK
zu6SOP{{SrW^=h>iy)Cc$sA2?n-${(_Jf~2*x}Qqt{6Qq@o?HO@$Ed8P@rC;wZH-5>
zRA*e8SqzNoT>5iJWLsrK`PAp$l~s>wWSWD>a?BY20J~9(mhF-M00FDHC9xYGF-Y<3
zA2$_PUAQM~jt{QdMv_S|Op+hMmB5#FKgN_2Y8|qH(oB2Pc1%Y`{OGtER&bZQkB|m=
zCc7Bk%_9NsQ#kdnJ26Z-D&TtW#UQrb^OREFrb?Hn&X--DIi(A3>cDs1Rqdg*@<UBH
z1dc$gF$n|iNBFe{CU(I{!S*z42S7f;zi=}jV@#6f)*tnV7wT&wD?=a5CoA-*r?p8+
zmzkTK<%V-bz}^1U(^PPZed#~7?J#p0J*x#_RXoT?{05)7BOFf0-)#VC&#6Z#ArK<x
zjylwKx2bD!=K#!oF<Io2IFdv7QjCS_=N-*3I#=;f@(K%A85>PvnT)Q_u$FF3QYVaI
z&-@Cae=x7h_zn1=4RySlA@atc`_xZ;a`|Rd8SD*bM(nr-G-K}c_Lw*Pv5)@xGy!1F
z>@$TY{rX|J-ND<A<24eM2PI>r&IjIK!D#?yHtMKp=*XjhtMnBZY@fgREiOm*-2GO7
zEk|_dPRU(=-CA>9%{B{7A;+kyd&ub|pMan_&o0J`0d1#Y)tH}LQg33TA&=IoyvR5^
zkK;}f#Jq@DpHlR!1%+Z;?q;kg8-C)9b6Ng=8~sqn`}J-Mq-DVhr=|rVgGvbJZ|6uP
z8+qD48f!9!IE6m76J6s05->e+KoYde>Xg$ucad}Ss2X=;{5byra-j__ct4KXb`f>1
z5D&h`=(NSS$@}tS(`7;=n2uetKiS0qTpznEzksJ;ED3UWFZofI^po+ZgjWZtk-oHf
zZ=Q|$(y$T`*f>Z0=?rd0JfrxvHLaUz<Np96RDWh3qw$iM4rs{ei}<}E4S)*ApZBRn
zx`EG@N4sW_+rk$m;R1jGv<=701bfp<jE%(rrBt@<EMxGeW&l?b=l%mlfQ-tY^U*Wx
zDol>@=jbRhTaGuMrpg460g})E0DRB_g1wo~`~rm}j0t7OrrK4xj3477oG#)Y!v6rB
zCNgLw7zn}n^{HOcFE4X5bH+DSL3a_s@?4Mis!@EBDIaIa9R})F0fk~l$CmBe@6wMb
zbhq2j_o@jmRx^WP&->K~)LokkYY-mnXaehbK!2)UeN9Cp1NUNHzO@j$an=MTgMBs#
z5TGN`Y1l%x_Bd2bQe=**qwu9mtD(;1A4H||u3Y@j`7IU!RoeiAkN6EJX^$RZKkyoH
zd4lro`BY`+JS({RQvt<gZ2a%|3PBXd_~bOrvk}X`=SU-y9I^cA0U(NDo@68IN+5pf
ze;24e%OE`G{`;jC{EXxN`=%mhwI`M%KGIW7r}vpXzj;wLyeFz5{AmTeA->|!GGS{N
z>d}Gj)TJ%cq|m9T4ZIot5$%e2iWMAS{T7&k<+TgM@ssUP{jwG1rWp1asft1~*!v|h
zk``S2_&@B@89aK8oQ@+hxnus#K6Zr$L%I4cYJo`AzEo~I;;q|D82L&u$?9ngRJx2V
z2b$kSro5`hh-CN4sU~Ql`L>_<0jiI35AZkQXb~@-yMN=^&-@CVyc`i|8~z1VmR|l?
z{OL{6P8J3K0KTb#VWnZnwM_e(YRKoGv&22~Q45wN{_RF;K_*uuqKaS)@6X7Bs=dX?
zZL1u74!EmgMA}=<jN{Nz=B5~z#ytf9QZwEhVORe7pi6z*ANR#t^T|9p+v&EHPWb!M
zasJIA74v?_A&U9{wJJk)$L5wz-om75oc{n6pOrVvn4D%xEHQ=)!}ny6eQGAOyl=fL
zeRov*rahSZW|Rq(WWq@L(-~0dvt<78l6&u|BeQfrK3nSbDV9)vTV*_SFHI6mf8~T@
z>huydtl5ru$GcLkqN3#O{OQ=aVUn>gr#YzFIiDGL$KgQ9P^xrf6>=$}JQ)`?o8%C`
z>lZ%4o{*I}^NOFPD-6+SUP1Cn_ywxFNyzggA4R9y%F)U5Pa~gAyjHP+WrvTIk9^RO
z7*EGp9R3v;mI1+ePt%IIai%im-c}&?2CA*BDA_3^pLV7p>m);<kdJdgF}5;|{{Vec
z{>lzE#gAgt@3M@4s$Z#UVzC;-5&r;|L-A@-v8F$9AL7)$Mg|OV`(>#fAiV95^PmMT
zhpaG+`_Lp%1{NXo6$aotClnuD%07aCCNuosdNKb10i-kSz%sAkl@0(o-}qviyc3Pb
z{`sH_2I+8reBbxQI9viacgY@=0B{C3KmGGdkbmc;ARJuee9md0yBy*}@0w8KBlm89
z8c^WyVk4hgU^!KX1xWguaX<$n^J;3U1^JL3d$lfO3;wDwf8L;DAIkvzk>}jgLneRa
zn*KE6P;>jg&Vg`>yu3^4#VZBHS(pwPLi^Q-l_Vo0Aol{Po4EH9vqo{(3ra5}QS!_{
zK8Z*R(_3y)v3BFoRThQ$`CQ}un!jmyWKfLKK6{m-?mK`orNH)}W@$oyf%EPu;ZELF
zzZ#B7C2kpJC*GPGW6~K9)|iRJeQ<`HBPaL<J=&@>$QS)fmh|07e9{N*SEqNT1<xh1
zkg<>W6(NHdKf51Rs^MlMh@%{LYCx0j=g1$8ASWnCR*#QLFoUd!KMIR$?Higg^yZfb
z9Lj^}DcA{qLV1}-(P=k;*jY*X3SdNRZn`7rwDgA5WBnp#_uEKU9AwBKNaN@!qz-v{
zR!e0cDY!pH%{R&pak67fU`qc0w0{~-Gts~As&|qXk0w%2eACw4XCG#NscHmAlu&X%
zGfE^tGv&vRtw>-Q{{W9j{-x*<0(iH8H@naT4>AS+097C3P4kdv2@v-caH=OeZPfi~
z9gwL$b+{i&k&q?+!G@3p{{Urb^|j=4j7C_U+jF+5v!FcOLOroj{ip`{Z$S1zK+cK_
z$n9lOFnI|au;?o1?rvAij!mkgBzo612B!=pndXvTLRPeG=8F9bLP!eODtPT#xINP?
zGTYt=pJNTf)~v&IkPZ(%wN+6fUztN6daoiDCAkCCRP)X|j>h^sFvwrRrSn-3794w4
zO_lR*^7gUyHK1lv*k%LkTPa-$pnXml@wz8sc;HYkZ6B6KRXus9t3{ruLHDN!VqwM&
zGDa#`OuLzj6WDhYik7e+-NlUhntNHGY^s29*A%U44_XE}Ha8-kVpcsVikm>%I(DfH
zn?_ogh<?p(r{*7(IKgfPL|`0I=Al1#6mD#tt3bw!c(KBP_*2EQY$IqR=}<~$$6@rU
z<`+MHX9L=cfpf}$5rxfGnWJX;wx6v)Z3zQw%G~<W8!1Q3!voyX0y$$3%xVDks!}UP
z+~<nX5J<mufcjLPM)C9VYLl@oT+C7!WSW0L)|+!|Vr|L!RB=d8-WyG5q?wyU;Db)>
zOi}n|oq{`lCY{A#<c^$DgyNi_9{f_VOpd*184*S=*A&)<Kys|a`_-0{`=XiVwgyHj
zYy$$$qvs(<dX_f|dXtY@iHUB#DZt{Lg5;uOoM3)brQGx0kPtb=J0ov2>;-qXNn3M_
zx4lLz;$PwCwkq!7oQgr$BAtXlE#WJIG5FSX)}M1DX4*_+oEEL2u}I(=Ldlv|8O|-1
ztq?i5$QZ^NteCYl<y5h)uuyiPoE&5FpbQXoZhvx&y{dTMQWyr<ZZ)v0mh1RafJM#;
z=|TfF9_@e=M7z7<rC&26DT=WpXMj3XK$F&i4+jbf>rFCk9Pv&OGYsSLsSUfca-4da
z0>x&zMgA^n=_qC3=A>;s8;8L9Q+~v;sVK+kNMXr6sS6&I@e2>UMJqz*2c-ZtVsfDH
z0qK)WU;*UPm>pZGBhr{{*~sLN#()e0y-g?qM{LrqpZzu?+Z5w$%luiO1_P7Up1E#)
zDWWC@oV%B{MKKbnBa(kAc+Ey79Q=*NFWOgt0q5F~$KxZKFgkVm)M8=Pmj;mBqV+hU
zz*rkV#wa^^9V)9`0m}1AE~5T713jp)7Bi02naTQ8YjYb9yfaG8>O})34eLq{1}eXr
zhxn=J>fJNekQ3)7ml^k@RVVA*(vqq<Ka~I>8SRRQtlPhK*v}m)T5M8@TNpeKtt(s#
z!9WI)x{v8d>{OLGq}|@EfMp!|S3h>1RqGsm?)AFdp0$^%N43@cu~=7);B;Z-X%%IR
z6$jR#RXHEZuA=UQ0n(unlE%El(nX7Q+PLjnQH+6)N~Hp08RoCXFtnLNm|=GH_oyP`
zPL(-eLH4L2$D7Xrw8Q*p%D2GFL4e|d-;G8{2fYKQ73&^Q{=Cu6CUC-+cjG_`0i+|E
z1A6tP$e;tS9+c90(&y<&PAP~@z*C9*sW`<QsQ}=3pz=Lw4o6BxZU-GZQxTo4E^Ns3
zt}bEobj5c1m@-(t1{)Q{&Yv>^Fa|iTI{TfNeTs|;2B2}8vivWtK<krOqjpw)gSAJ3
zNC4yOQ!?>QjxzG10DfbN(IOex_(s=lqdz!1jz>?un(Gu`dm7BqZT`z)3`m<s-u0#q
zJJ)1Yk;gq)yG{l_DqXzL8`IK|pI-Gui;n!!NDV)3O(6{p#V-dKq$!rjrv=3@4s-2I
zE0!Ip=Yj1>zXpI5MmlGjO_(^KFsEc=tt*U9!kxedn9jJzKUzZ|#TNoXeJQL4a%lvB
zjDyWY@{oG*K<quFR6^MtS39a-?qY*1aaT17-IoY(0Oqk73FVG`&0$umNZy?m^=4oP
zdmec`>fAAW!Lf>DspY;$Jkcf6gafVyD~3|LJ5sRgyR0cl$KzQu5JxyC-kou9Gr{~T
zI$Nw{(5?hm5JudQjP<Omh&I0;cCN{C81hY5l0ZS`wvEhZVv&r{u;+@fSu@g)F-J<$
z?9RolF4KL_m{@#+7&X!@)E3c!yB||rid-@`$&h`jMv`e?nu$fS;WUoc4Q|~N1mM-N
z;*yd6<n7~(R}l@nI|9$Od*-!ZYiJdAAU@`@bj>}XuPx=~r6yg<sNgZF(V(_LxbKj4
zYQmdWjv<G94?$Sh8tjh5LU6r<4r-%D?1|Pp2fA7Agkkc`+yT%E==AGIt(WBc+0O3f
zyvIYjd39tbasDIk&3aPYe(4Tzk4o&PO(T|d8#FF&Qpz&UMt#k5SH2_j8)^^+dS|6$
z_={C>Ka-MMocdQb*DlOYbL&l#j>G##Svd^Hw-s9NRFXS){oq=_wbbRckiIu59D`Eo
zx{bBmV_?|*2=x^OHeg&zWw>`Fl21}<9n1|qfFzo3D$$!9vXU|DQmba57!>XJrXqat
zO)dpTzapb2BA609wGnL65P9N`)PP;pcS((A)T379b*eR|ps)N*BR-rOXb(gF$G4u`
zBM+Ay4Obo;)8jev$FRj{MC2w9(uQN4lTCpHdQFlp79cU{Q!S;mKy4gS7C5GoNcz&S
z$<<>YbX1~6szW)aXC3IUT)XFhI&)B8N#;h~IUOn>`85>Jxo{|GW?@pS*&I`qK^$kA
znn+72H3}#VS+a{TqsGIqt-Ds<r+1}e#kdR}Yg*e2)Ks=oCUq*jRSTAKO6IhgcPSN4
zSR9kbT7j8TCtAOzxQ}q?3FezUx`o3UY<N(1*0jixujk|I>r88q4Nwl}y)?7d#$;OT
zsU?{Q1mM?}%9uSd?de{JtwiS4q(vtK2OhP-&e?VhxH-luSQLmf4wWHQCV&MX8j%?f
z9V+BdDx93t5=2fhLrh(;xhK#H0I<`9A16NbS>G+4+}5p*i!ACMU{p6n6>3io$B&nG
zeP{!mEKPO34%8kbWLMj_jw?01JO}ZxtNJdQ);A2?m0^RLOr&;;dvN$3b9z>ty}R6i
zS;^16W5N(1CAw9pZ)FaPA3@%ryPI%XD3j)VdwSO8ii89LdH1e<*`3=MJCAzkY|!~&
z=QS*Qo^$aU0GB(6;F|N6Tzg`@kH`9On$2!8xT^9!YsV#gxxhHCx-z;koNUKNaNX+k
zZ-I`rnx_XfdK2Ed6EKl&A0T6jy9pq2Ydr|vS7Klkb6O)NT0@b@sbV-aSx-GpNRPFJ
zUCFU+dF@jGHdS<+AbhnbeBf{@i6VABoj9r&OXgd;{{R<izQU_Wg8+L_IOuV=Dr1?D
z_Bg0{>?-D_g)bz}LUIq~RI|l!%~_q0cSm30%ST-?WG*(b+@sjmoc9QjmEDtr-nr`w
zvkijA813{usC%!QHG?!S+MLOrc_8AtizAr5v&C}OJig*<sj>e6R5MnIWw^#2PbReE
z;9|3*>OQrj5cxr?LMP)Ng>3067StNW=sH&ZnlWa+{Llr=(}PnD8O<OpA>;W~sQT3;
zJu2L1fGSuPkZ>wxsAC_MOuSM6rw+83=ZaB4#{<nwhnj#Il~4Zws*?h7O@2iv=8^dn
zhH{=bpX~ZVw{Df>((0hbSAT4MYtnuuHZ&DJoY#hKU{2zGnW>P_>)AZ%$?7VwLMlRX
zO*^h?N-OQoX?E1X1qM7&1%8L81BwgNnQ(ciSYw)E6u&$QaBL3UdQ^1tfDJGW$`5iV
zSvljVrVnaE!Td2m7FO+}&unvA7Mjpj19(z;8pSGGuS$%r8h|@XZAi#+SaII865=_K
zEPywrYlDL7M10n*zNm0MZU?OcHSc^q9l<j~>l=D@tQ(6v-6l=S93G&rJXY<trX*jz
z_z_x>PZh*i;EseE1anqCCXx`b%*Ep!PkQLBHJfXpkidR5Ls9U(o#=LlF~3}nE1bE|
z^$k8<%A~Jil&m|Ri5<XY$Rh@<172^Z_=4izKqlPD_edl4uDeavZSIg^z;2sOCI<S9
zijh{Jie)R1LG8s&=8iE)WXf4SWjLw+*vA`&Ppwch;*?I546`(){%VhXMANQ4swcQo
zK2t~u{K6<{@HroyX3cc5uiwe4XHdyFZ_a==UURpB%~zIlj=!B`J@YZBTH;sFGzh%c
zimZ7Q#?+bA1tzm3B%WxD9QsqZ7ALupnx)dFaeM}P^{T}ghf14H+%MI(lg=m^)&BU8
zmP~#WBojB^xNQ3hmNd%chcxmObGQ#`cO8g~E;;iF`qTF97|lC+0gTf{%qYM+WALSL
z8e-fy&V8zA<S=85d(%zbx}W)JpJX)jx`IRZSp8Jf0qc7%PF#hl8&jQ=%MM53P0A7S
zM~}jpfu1Q0g^6RyIVY1&5V1|%jyuzc<nvD^M_dwkpiLEz%f?BkMy1$cO-#1Z72vLZ
zwD{w?kBrBI*AxLF#)_Q@r;oext|_4<BL%k8{HMn*PtZ^TZ*p;*((Gb-&~4ZZ`K?g8
z%7b^9PvJm`in5H8P_YcyCjzBac@Q&a@u{PYMhQ@80yr(8L7Z-5+?uek#8)0z&#frO
z7+O)!V?YtK3Fs+O6z`ADm65T~esvgw%=_qZ)2#ql5kLX^hd%XE>gv`7`Pl#+DUw;F
z3RnTp9Ga#qt)wc`G8}(+^rdhjI;Dp1`1l$26=pl@JY-0C^jdj_#S{RsV0IK{%{wUi
z&;!!$(2Td3eLh-y-@<r_7y-t1)P8la&&(;J_RqA)Po*#>Nm@ga593esSx!<VKT}Yf
z+f3j}quQ%Ye;6lYsm(5E_Zd9bEdKx|(4S6fHG!WT;;Jpc-JBjN<5K4w{{Y`KxsV!h
zK@>kWOE;;h9(l|@TvCN!VOZl)e={CTgnH~WzuFGY7C0m)-AJRI2()b&jI`Zp4xGhv
z_KtlqQX!D8NTxO8MV!XPSK6xML}JF}e~B8CdADKak;kPAt0bptq>9J;%4%P;85b@S
z4cDG(B*uiA@+7r0Wq9paZK>I-9n*8)6>4n;9n8jgFn`+OtFDV^jvVGsty~p|kTvXW
zg9;ZOq*a)unUmy=2m945Nfaaig9Fy2X5XKe@)dU^tt`{R1LZT=b*DhrdV+)UAYWQ>
zPIytrtv}{b{n{=7G|RKzGEbqaFzDAoftgWP*yfVeoJcVFu8!4ORRsQKvy`k-L_*mk
ziAsEo7n5A|^UTs8Di&^f_N@(DP$@G*9K+@GHImb_obJ!#L{;?$Dq7t*2VxIQwKn1@
zt;h%?eDxu^QkjqpGk|`zUTer>8F%8eCgUV~_u&Gs`(0|Jqg5-iIkuluQXP8EKC0OF
z2ArC@T=N7{KYzJE46?Soj$-r9Txafz>@?`oR8kk~Sh{trm(n4SJW=PKIU>6Rwuag@
z5Oy8wImsfCUT}8#Y6!^dT;2AcZxrlaX<g4g)wQVVA{1Z-N#i29dz-gAq-1V?yUh>=
zJz=*87&!XVw!*z32kL7%uOvac%5&^im2Rgz`3?Bigqo=;h54ddJj-nV0LQw1HJbMq
z9$(8DZ}vr3lH&6N7Qml&qTyq2&a_P8)-#^uRJQlY6E4eSW+wm&$G4H(e(@C#`_-?f
zixikiJ=|-7(=?kJM?nftA|$O4O~bV_QI=S3S%Z$9DXZcQDlxI{hp`optm^hRaRh>2
zFgH_JYjXB8&C|4jjDWX#f7;INqD{X;S?acXu=(5UD(rV!L`)y-Vn$wtl;<_8b|-S#
zG9)5q&erLgfu{_|Ah)(D)9dYUc|Z_!8#+~X)pLeIK^}`qN?n4({?Q(G`AnzTO*e3E
zHn7jNM*6Ih5A}?r>55qOQwwfw(qp!2xtOe8v$YdWGZP#z<c<Y(n>?uYs^h;E$Db3*
zs5aX#{q;niD!G{%OiPS*YKdKxjVsM|7%mzZvE~lvwPMXPPa{bzn~CpL#mc)M^kf9}
z#!X0OiX{2t>*%?vim;gsvqu|Xe8<>kgq;XDiSz#LIj-QwVh#`cl#PD)`AHu8YWbNY
z$t=g^jtLLdaZgBZ82<pN$JEtRsa@mbcKjBFy}damQaf{jO6&`U)_yY)=hC_z9tk40
z0&T1K*Bve8_W(?P2NZ_t^B+9NKAvY4ElG_YiaeFi?~osJSsJr9mF3$?yN^?xVz}dR
zanXtq?;)jG7=y}#{_!-F818FFrp$Kvx2qqp>r)#zqv?7NsV1;XG3wx-U}-nMKfEL8
zhObgiiBiCD_oN?c8Y?$oe%m5}+PUD;9(>n7@Cs4pu+Nz{(`5j3-gcQ7`|fe=O>507
zE0EsVu5WCM!IEFboGsmsUw`7@Qn#4SqCINCSLKfYdJ2F1B$ko%LO&Yh{>Qn#=^o}<
zPqJ<2VjrxPHXY8QPZOhp1R#%dR4z4WB?OpupIp`mMBW$6kB<4xO(_b!fS?No`8RP$
zbphx<I-*Q$aNAGeNc$9RL&y8ILM|Ol9)4VVQx2xN;r{?irU*Rczwg<njeumdpM-P)
zWBXAzeB1v31SXYrO^jMEH$9J*MOR!F`AmcU1B!W8J!En3O`t3tX6)zpmksq8rhjVP
zfN+wMf7+_dK5kw{{AqwF;|_kUQ_6>Ochs+#oa7Jp>OZz!9(DuulB0BpeeuWp^(sfF
z7|D}3$3HpZosh1`{?&Bn9$a7#St;IS$?9Ss@H&A10A%j|B0aKmOSZtc^6kdo_LR^B
ztY%@Bni1>{Y7%A-#L13;1*uixi2Shy{{V6_X<FbDln<Z!<V6Cx7!T2<`Ms8t%Q@oW
zU;E~!4>KS6Xn6kZFZy0SSmZxk3I<h@$tF0GX-NM7cBZq^?G{g)%x*u5o}%!cVtjwS
zR;?}OX8Di-?)=gi$#lzBQ}Vb2p$$~Uq(I;+kUd_s?k(Mr?J9k@R%=?ae*|OeB^MCB
zL~Hk=1bekNYy%r@<NpA@sa6oJ&yb_nbtpFA<joFf0l?dn^TiM2Pf-E;vBo}vqw_74
zAM}X9{{VJ_JR=|JE06anfj;<94WR+=^3W%ZRPJW_2<orftyyvQhx+++hVI*^n<+o;
z&;`MAzryZ6;1r)|&sUKC6--^*D9`WP@WnIj7WpNF-<>fRjHd+daw!boFYzC#s-pJP
zt`^c(_bpMi(&r0dxkpU376RhP$0Yv%=v1u4{{RaA0N+(d&p=1|1Yn;-%`e)Y7#4sZ
zYAgk|m;IIe={(<;7*Hy&+HOzXwjYX8t<CTs>XdyFiv`O|D|RW5_i9y@)b{@XzG{%T
zzG5(g@LG47sUB44+Zd%`n-LOMCBI6FcPiUP?`$nWY4+vjM;_qQB$EBqpxC|lZsw50
zkW0_{!}S!!M<;}1Q27_c9rNedwIGUq(*f_gorKFuvlH`1--}WoG~@(d#p=6S76*OK
zG1*>_Sugzd2i%<12${q18BibhsWz_M0TBANMz#?jzc4<+m-{-`Co=Q?<rV@=DEYU>
z1s-I5=8RK*#Q?z)NuT#A!q(Vz^AFW&0Mk4pkF=@w3rqHt<2M8kWT^$6w_h#W=}Y87
zukyzK0G$9u=dbX|C;jtIS-nf2(xed~IS6y^)TS=`5RZ4DE<*P)ul%!+{xrin72*~@
zQ&xPmAM(l{`|gdg{{V6TeVa6Zq$L^op#*(tOwp6YvY*DS?vEdO5$T#z7yf!gKj1V0
zOw8oqLMnJKCyn@tSN;Q<vaX0eS(lGRq-j)q-h7{eQYe~hshSaphJW3v4%dg~*c5v0
zt-E=lczE**da%V;oI7U)$I_4)MBcE#b_3IGFO_~<@4ZS{_jPm4JO^Cm9OvGch<vM@
z4b1-liK#?Wh41*aFe{Uh9)7J)5y{>p1J{2v#2!?exySwYO>1cn@hBhf(}ZPD5yzkR
zsoQWfvOJmqu56s=biYxWQDuR|sgI>u%M9>>k-Xdwo-ysVfFS!Sj*<_;fn^_gSp62K
z266uYEmQDHa1tE;`IqP@0tL2(Kjox^{{Xp8@}lPrAwKC-gmK53{PWU{jh<zafFl<1
zt7mKHxuh`fZ0vG9YGDHvCwqQ$G)j2Of8SJqgv7WzVSM|wFOa21U<CgFv}xug<2nBT
zzNjdkpREHSXk-Nb<|QBR(#FjL9jh4k%}Npy4r5=fISslJ%@`-w6o+xk7?C$NK59md
zar?6vAMVnPLfo-kq~nejrCm<Y5A`Jf0Kg3bD`9`<qJ!+T0=?xK_FA2_7$uMdMjqZ>
zA(2SP{!{^3rNRFITOl6HQhCZp5=u|HRGGm0q#ADiIaBzWU_s_9H~h9E=}+9JpDJ&u
zsZ56-bYuPMQ7<2LGCKU!fQKWz5`HaBU~z@EBj0sQZqyukQU3tnblEPz{s@P@>I7AI
zosTj8W|{VO&U~2v06LkkR33@>(hIcy@(O4KSQ$t9n8)K%?I34z4{TEf>L21Cg3}t|
zbJf4^gG>pEmLKa-dt#V3f%3>cp=vKVN&f(roPV%s!f+4Wm)L|f0PwRM=5`-JLq_M1
zG0(j*r)|6}zm+siGk?n&54{0$PqUox(onY9VV02ol$)gkm|rK<(?d-E0P@Fgv1&s#
zEd)ytLWmT9c+;*dESu+N!jD5(%>=CZ5urVCyS-nG&op?MVq6ShHgia16US*Aff|PT
znu`ceD73O#$c|6$)q7;rKuMqVk&pNdFtIX-&pQ-*)0Q~@0KC6URctu_0G5mY0DRNc
zn;G*n^b`o3d264TepG~moP9p+L<^J5t)F2_wTJ`lGLNFu0%0Ry4crewO)|<CA3xHV
zV|;UQG5P^a5a$^)Hyw>35-F8{`^JDIEzW;BXW7@L*?;e&O*Y`1glv1g10}%(0zX<t
z&!Xe~>Wsjnq-uVzK!zaS>f_JWm<IL#0A!!70_GvcVh7yRqTbkY(Lwps7~3ZSU;=?y
zVZ4ZP&lnWdy@`k4TzY{{GQo`bkmK5;Gu!j~)cgf79xkKY2bgjG<v868e3CI9%TT@5
zxXvdh*J@HN-MK$2P5%IXjUj=$ZP{NpKkm`?nVT6i5l;JbK>h26{{Xf|gLN6{6y#_7
zw3rqV-G|(e{Y^Gl-)?-iC)ueYy~gZW+%O%_6*t;sm+sl^{{VTppk;ICAi=j^uKI+d
zmgW@t7OSq8Qa8(KkOy7$QdPZ1EA})v?q%yu2xtyZFv2nD)gp;`Ke}JTG{GI|T!<l7
z_mYzufEd|r{{Vee3dG8?<340#{sBl9Z~5;T_7T%JUHZe*)1@<I_ul(VL+G5)1NP0k
zKWGE~0ZFm)F>^QIf{_yJf#zNUJ(8Ybx-F4-RDX0W0u)=xoc*G6LqVJk(v#fgm|(g*
zeX>k@3Td*H{`KVjJ5U7QW?nduf&SGs?NomQ5$^QG(^RGm_e6E;O&UZ%{{YK(`n3Q%
z$x+Bf&%4r<PI9qv*tIkJE)0NC{{R-GT{_uLe4yX&H2_XlA<-@W06Id*z2O+7TN`Yj
z+(pm0rE6PU1=|7+`7|+&`&3KTXhHf@(((|$HPnAaT0sqrXC_Nw=rcz91!X>TG=Otz
zaUy(|5)Yypo;_Y1bLYr?c6F-XYtxlW8<?^^Dg&u$`S~swpJX(wGhBwb!y-N!t4xn<
zFk@!=8m|_y5}%Su*m?vtdM#QR{#CS;<GD_0458+d2HQ#BJ@ZIpl>Y$BjDQbQS8jaW
zyVeP@{ne^+O)CEY%bmgYr*RKaI}et@LH_`0=^88UqSoC<yVPrOF<<!em>+T|Y3_gL
z$0PlxrUaP1T#}Zf@t~#Ce;u$s>rt%tWc;>q0q*qVlJsYER?GhY0?h(sqC2Hr8Lh!S
ziB1t*1M^&f2lrN>^RNE^gj$2`N@dia?@t2z1kC~@5zK$(`N#XILc;9-06p~Ndo4A5
z@IGtE`SgyM!f?bb^Ks~u0XepfpZ#sg2e&mLvy1zeCy(zDRg}yD&D`vN-N*E%?0FcU
zKIy*<Pz8^$LR%&oPqA}SeU{x92E+4egj*5;DRfW!*r%*asy}l#;?xX2&uR%_Wf%Mj
zseGu9TU%^<oYZb`f7BK}=9nWaaxI}A<*5TLW+WV>BRvH~-cu%b#-q>*jG-9BaIev+
zrSYC&28#g4+TA5kr`nMONhkb#zfQ|f-k8Cj5%^S2$%D2`{RI{pW~>^F3c+2ZWzQck
zTGkRo_$MKAT$FC$<j*DtqV%f~T`EXR$vgXPBB8{qo95wFu^KTRwBNK6apg8oa%!cm
z>=MhcMJPQo-78)zc#M8y$$~v<IbT8Z6X}g?t^4b5Gqr9c)*CREzF6!>70o2BBs*J!
z(yXn+HaAFcJu2eb+-(|ncM%0XOB|1Cq$QUi?<ea`1AaD=X~_e*z$Ua1{{XZ$dCdmr
zI0b(yW7$d9&OG`GMS!nY27n}46t+tK6>29(`|c1`28GD^TQvb&g~7lkm4e382pzDJ
z{*?@nMt~71W9f>c9mL7^q8Rn5(sj?znm{?7k$M5|P&s)QjE{3uyCDOQ&Y@=GYJ>Pw
zxDlU~al0m(p`7(4sM#SODih6540kA)7U6T<+pRRjS9LqGdB<vuEL*oS6IVXXcKzdD
z_i0wavJA&@^c2KH43LKTqrjz_*52g&lWZfkT5B{T?tm(*St^z*!S$lzv70mx3lJwB
z+*1QE=-K+!*-*#9UBvgQ#RDI6+Nnq^F4s6YA4*PhOk{L9^`sB<t3+6vBpwADuzl%(
z=e;=W&U4LBhY3!39qB~8^yZO54yTHjFt6QiXaRw<%_)2yyiyXK6pDzhdQc)=$DyD}
zgW9Wz+_5=0rSgjOG=^H<00ND}s5Jt4YNvMQBhsWZCuq)n=>aI`jQi6;Dmfyn$vY8^
zxD?bok2F{dLPQ--eQ89=kM(0dwOcAjemyBNae>FZ76RX$CO%va)a}w1#{U4o)f1oZ
z9x12HApGYP>=!hF3)R7?6oXj_<^!D7q-SBz0+7qAfsi?+IrKG1PVqKZ29@sSf4%tu
zNDFz*2N|sKan1-MKGg5D5yIy*0iYC6!-}LX%8#3hkX?ekvp|VT{xlGA(xEev)}#`G
zD7X#-+Ksu-6yH1!dsABJ0Lc7lTw|MP7$TZBGv^(uBXpawf^$eGCzW2F)LaV&D2U{9
zP_?b7z`}xhXRR!2$Ifcf+{GGVD>MzzyYoO4yr>YIADB?s+rpBxxFr42%}StWy)YtB
zLCyfH5jNU3j<}`#DOh9LY_<k{=>`eG2c<V5dvi;_JW*f(tBmK4!j!200QJ%XgW8?B
zPoVnH7b#=r%?BfjLF=B>xyM?fL{>Zx)}X#$GS!LfcV?$-9MfeRpk?IzrlxA~WkX3L
zF4?yr8P63Uk1y916{q^#5#REy4=;0$I@gf&XRfv%Zyp6&*@2pLapYjr*?wP2hBC7O
z=}@ow?0%JHh8C+1W*)Vr7w@AwzY8TJng&HU40NP5>>gX(G3$z2K)D?a8*%GEfDF>@
zz|U$k&lFK%2sspotu8-0Qn{c+W3DsBJ#(B=1m~?k1J;3tayjCdS0~b>$7*gdKoxHP
z0OQ(EOji|jxsmcZ*J*l3lKK2Aj<^|a*&J6MBXh40u|<<B(x4z_tv?v|s`7F%=~yG7
zm89%5S9FVEKA?e@D!kPfBX(<d!qEdeOO4I<MRZeFW)&Td;sLfaAMEt0K-}GhK#rwX
zoO@FFxas=WQOR;}IL>iMNzc-&85o|lp@|&R6D)7qI`p7UIvTFr{VBM{dr%_Lm<kNS
zs^s&NNs>BIVU|qU`cq2|xu^*wd(>^mQ$>KZWCx6zVV4*=<KDCHuKvw#ThMb{?4BV&
z_}!nzv#C>%+Lb<YuQw<UFHaXSw?`Gm4Qe?#G^bQf&yU8r-XZonKCct7l4L=<ct4G2
zO?*K-)*M&p?Zk)itBT6&^AK}b&k-hR8ZkrWyWRXp6;-FnIW*~nA%0fL9`%`az-OMG
zmCogJV(UnZc_6K3OrT_g^3@q`oq7@lQI_@hbDaBCD7Gf-PdwPqwPsB*>6{9YoZJwq
zF-kP>NADZ{0xNjN#uAyH%t`e$(2m^!ty2UjJ-z7^#xT4Z)XMiW*4jcwMI%JRjFVc*
z6CCyQHCkp>I0Kp!xS2@-R>>KwDKd_uiiMt=yl1Ulh-{IsHs|?NGHMdH3566G#GM5@
z><&(LHagQ$Cz+I<SCO*pSo+d~>sS8(vL<ee)Mq)V6GNPkNx<X1T0&*t3&FbSrYdl}
zeKB3?XYBs~g>(8Xx>>>#Z}AdyTJkY5kP8o`Ykdef&1OcIP;l5Rxg2z??)~d(`$)W+
zc9Iyu+)EtxH46B8{gje}KGlmY8Hxsel@#bPpGw<b4quFXqaR93j}KkL36Zgne_BZm
zvz<IsO-{p%Z6NwoSgi;nAev32)T7>?#wiNrU<mf7j(b$34@zkO&=(nwDKS!Gj8YNL
zN&t+3is-y6WMsH&h94*#6IgJ-_g4vT7|XfG73x|xik6mWgef>5g)kg3fzLE|#cHjT
zbn$5r?VS44xES~+wIL7KXWF*JF^}OC?=CQY;LS1E!7BT(7e7iFBnOl=y|q;E02DGQ
z8QVxlILjdD398cxRSRI?cdneqnfr@W^#B^#x*uu=j7v-9SJ^7%eNSq?HG!1`mfKrA
z;<9Cj4V+ZAmsd8&Xm69SHIp<hM{RbDKXSo+O>5i4M0t~H;8Zc)Pcnv52&qytI*}ka
z@0x}(8=L5D-(YN?L0OXOw-fOiZ3Or9tvib-hboz@`-svg_*^wB46JS>3^x!>Y+Km}
zg&TGWtQ1nx0(s`QW4=hC8;@_wwWf%XY+9ht6rv<vPw7;Ss~!#sC)$!b$DMvqzz)nS
zQ!?a{LdroI6~gOY7L})IZ4?D#n(SP-PEIr0tC<^sO+5hfx%3O@W8brQ{{UyLR9!yt
zjsz?Yam{*T9MyNX4BbUfx;q>+8XeS`4mOcnx_*rXlZKE7VcxfX%!-6$;B!cA(2RE!
zT?K{-S7=;d4@wB#%JiwCw_oC^NRBo3rF1(LgdmW1=9zIHmN#~*sU%JJYAd1UM}^Hx
zW3gHZS-wt9Y}qc<-2VV5@0!DitPQ=+)$f|6f2~V<D%je6(r`vP)H0H}=$Z>1UgXCC
z+Y)iSkG=G+>eEh!6btvU$0oS{01Lu2`#7Q<hJLlz+ud~Mn#r@a6w*XKBGKTv(dNQ@
z%BL0ceyMCNuH=Y<3b7eI>*^_F^R3z<IAB4qocv*C*80`J?Z1M4wY>>yV~B^ka^T?A
zxDI*gRSD#b^r>QQ)!P%#k~CF@ed^3iK)^qpP>u1|rA!|Ukbf%G88m2y81>CRcn7Uj
zjq);0NuNXbRS{y`a^!rt#ZIJ=ilGzYPC8Y@Y#wTnEehEOlTk~OeQLoWu~4}EYK3E-
z*5U}t$GFX7eQT%H<1cDR0E|~M6b4oG^{z_l%;}}Ep%5&J4Nb7_9+Z~L)32pkMfCk^
zjkBV~%VJljEPGc~V0S3`S1kwtk6&8pG^sE)9y7&UNoJboa`DY+Mm|tF)^Hec*0e#w
ziq#TITjk=qojwirQ84I5az0?_E4T2x(cJ0F8D%dR#U=!AZpeBXk8UfcHnFnct!3R<
zY$T|p1q9)}s?<lCt+1<Lf-zG<er{+2@^C6()e3Z_EmAT~)CT7@5Ndco{<;8^A9|Hf
z6<tp}RLFVFASYADr7IkPO;TxFrfCe|eksYfL_x?WxUUUqls6xAde^pmSjp02QOQ5y
zUq6{R1a$SOV@8;hCY+|K+cxO`0Hs*~15!}_f}9RO^rmhEQWJrW4Im^TU#Q1wh2zIT
z#Ylj=3Yf={j?@93%jr$paat`3j@hV8IXI_qDBy;r01tY!@p7OFZ<UeKs6}#f_|%ZD
z;gT~-ur_%aKDA;bD;@~ND~zt{qyGS{OxwDwI*@6K05n_&#?Km#wRYc7FqQd_6<o3f
z!5Kca5gFuXGy&6E>ifV~HKiTwGM%{kn&N>e(DPOyzAE2&v(lIyJ?4pFe!L=v>+<nj
z)#r!rY$Ybxv!`6=n$Wh^3b!q{+}A`dVV=!fAiwgUM?0omYcRIfg^Xj=*8F!<5r_Ft
zrDi?p-c%ESaZeJq-1^k9nm=kFoz3}Ee%1;3Uy98x?A+5zu|4SwyDjS%BPZ~vp7F}m
z8w!l~pp11ChB01AGq~_-LWgZCg&l=SzBC^^h^O4r0uvi4=~Biy`?Z&O;vG8B98Ko1
z{uHVw#9EE-%VA+52Y}&w(?E1ns;Jz|h&}kK6Kb}0?i0>ekoFZ$)5Ch^uKB-tB41AR
zxoPm~6kUZwQ*9R?Al;oZ5Tpd8n+;G>LKqDy-Q6K2Aw9Zb<VH%DC?$<_NOwp}H}7}9
z|6q5|z2`aS{AvYjmE{LK9-~nbO^)!raS;CDp{C#mk<6F%hq%w8S64iDg$wM9N{Shc
z-<Rr8nsG?gC&&N9WMUjLHsPm;L0eAhd9>>c6?0hg*RG%*&TF8MXV8r3TeCBF#&h#Z
zvXv@m&M(t6KfA?Km&kgiBVZWOckywaE#afSLJxh)z-Bb#?9AdWX>$`7r-R4i54qso
z8l-@$zumD^>l^aPs2!!Kv6Tx-O`fBa;7IItuAvv`q9%D4!4^&o$pdARma^A^3O9-}
z*ptQbWFn-v4;*NPhZs-QXDIGl+Wr^062F{Dy@`nHW}UBogO1+$dSk@vRZ)}XPl-c4
zrX2%>d_HmVA7~?tc{-ce4-~ILGC1_*5La<Ptj>xC`w$6niBe6Qh!Iq!jAA~Z@2$oS
z71!8;`Iso_?&Cf$W@C8tzfNrd!zFMl1o9>O`31(4;TP%FlBc<*ujvGelQ9LP+4iUZ
zfnJLnY8)P9ik~l@3Y}L*A#m}IE=L4DI1eShS18`h@hWkRb)@rT&CEbpl~3t^R9H+q
zN`IWKaQuc%YgTqqs!-w7bDSj*AgGE%HM*l2(dxDW#3_g^r<P=n{h=vUFC$W)*ABpZ
z!*g}|)Gh;^H{@oqBNSDOs*$;iZudCiG#il2UTNw3Y3YC;HP$rbW=D+y7chp^eDhQ;
zR(y?1VI+M&qwL}Dv%_T`r%_rd>(3%O!iwrx=~Wfh8>BbdH_ZLAJ-kdngR9tIa8Y@$
zMoOk*i{z%BEpgN}DRz{T#-A}SZOd~kV*le?c4hCnw1A7wp@V}Zp*`?I-K|3fNVaZx
z?)Qu4&SEO40qL;L{~rh>Y+Sswx8>pFhJLS2@UL2LqxDyihvE>Cv==OJ%0rLa;?6|V
zL?T2;ztc6^dx2-hy@lL3^utGpwjjrUActt3tbh)wB1m@cE23RZ)_*F>+(is%+OK!g
z_+z}D&8oVI-~UF0?i8yj7djBLR=4h?a~!`a`CazMKES73!#seN*Qw>ouIVnv4ZI>`
zzNblFp(XgE`My+5i<OBiISR>o)rG368U(gOj?DfbyEfzQk+Xi+evKtM^X2aWb52Hi
zU${)&PNP3`oSyY|<Vumn-1qb7m}hRiSNk~*J>JM0;a%bR23=F-#A$Ud>m>+@RiC@0
zbkZOd?4Bt6&bb+)U%XV)*#PWRom62ToN)jawh#3I4?D$BOT9e9q?1=V>v$A{%3I6M
zYhk*@kF|pU%ll-fm}DunOQdLTgde2;p>Bd2Qc~_2K_==;n&UV9;#GqC?jmuqhp#u2
z`B4TCoyI{bi8D6jSlIiHa#6m=RROdYVsP(-<!wi9{+L36<OGs5!Oa#y-=W>X!bBxr
z(t3Y6I~Mfbnk-R5h7AhmjjDR5f;wwe?caGh-#WQI?zyTA#_tsTNRvHZYV&7+$<M+1
zcUyF9Dvy5D74pd*j$}DBr6r<0!5we1ylRZI-i7k2uR+&5F;pVkvXuH~_Q|+AJDVHx
z=`BH}!9m{}aG(wOwDd(Re>{a&<%Z8f68Dld1el)wGPZFdHyK!3#;(nf&)D__h;#=3
z1AViK$m0#C$DU+Sw`C1{R{w;nwsN!mE&Fdu50j-8je!P|rHtAI%%udyi&c35fa?D7
zQ<)^i0TLDW{*`=Q1I$Q()Xoe!#FV0bTEkx6udCcTw?iH9U@chRU+K<Yr-h`2O2D(k
zI!?CH&fEAp1)r96s9@j@M;qV?m}`TM4T)!iS<gxMhZbW!Z_5gmI`1cT=U_>bmh|3>
zaMhP!OT-Nd4n6FZF@}%ICQULRt^`%>!<K&yj}<FaN;kB2wYm2H%SV>{D2Z^g=nn*q
zFtxH04T%Essfy?b`&PX)qc8qwhM4B~=dA|^Iu`NR$xns>-s1wHD@q!q>X4S=^9)Wj
zhDUuJRC5zUJAgTbY~-JD1BUgCod|D~DbDlLL^^O~3fAXy%#O!LRMpP}@aZliRKmvy
zShDfDtOeD}2S+OXbz^SEST40kEd}cHAIz5MHe22Dm;+z}4$5gaQgN*Tr|hbE`Fi7l
zte9FL^?nPi1E(|@xc3R~f54!?&rAra`20kH25QOJB_HW8_MqjB`VaKUL-9WJfy=Yy
zyVR`@<B`hLGGjLOtO}^|%iqxZ#n4L%<g2tJm!LKMGO2s`2^-)HcsqsoDI^p0Q-)B9
z*UcTn{IQku$lT=!!N%=BtVTv~?#>v%B`#9``42uIFTsjIvp!7bIwfqm8=MWnk3Ckx
z9^a|xXLy&R!F;vYtLjyAYY9MdB?U`K_@9So`2^>5BBFHKy>B%d^@3kGy+oSt>n1La
zY+5Y3PiG~@ym(dHJIryR-^&-70>8+H->+$9^xJGf7Rv>Sa@cn+#>vsK(Kp<0(3Ap4
ziwLH`H<WVTg}Y`!s~%rRO%ZIX&OaJ;Nve7B|JL(MH=E^DI}IZ0>Vtk<k|yf7Oe}tp
zrWeW!l%N6JnSyf`hh#0L%<*Hlv+@()TAb9!c;9oYslG;?MFSASJQs#%a*OKj+)FC7
z#P6cRR~DZ>>&z9zWl+T#07#d;n=3-XENH2Kmu**+n&z^X3P1g|c?&2Yi==2lYRaT;
z#!~Jb_a~jQD&f|uq6O0=82rcd?kVOkQ7VU^H5pA)GNZo|q2G3=l^6#&Ehk=6)3hZ#
z@<*57UEX3?Fk=@aWq9VQg)AiQP7kW`LN@xYc;ChaOQcm^MI6Qo{mNV1|F!gKX>*js
z@ybt@arJh0tb|Q~xL#d>&ZIJct~h>Hd-UK3#vZJ6;m3FKLoS`DZR0ZRe`T}?R)X74
z4Xu=P^M!dI`X8``%N>w9OP|29Iypl`qDmV1`SParxcigf8$zX~+9RnZNlQDmI{w`t
z3Y4_?!(Q-&J&~Wd5OS6TI>Ue0NKcG<l2+rwc7E{7Fm{Q?96NTu^plB!C*ib*?;%;A
zwygK3^Na%~NjT8u<3Pi**lY8}FBpO<;<E@;im;e3ig|OF1!bZznAULm*Hw(;-C7|r
z@4w2qw|<@A5CDl;0~`ezRkmHs+M_zePOS-k^ID_6N>B%YcD@m$x<4a5kr~GFdZJEv
zqVOH{eO#xcF>gLrvh8&LEfB~fgLNhCO<ab;INJr}x#&m|@1Qauv#<P`PeHNmJ!Xu1
z+TP%$u#-{|3r_>0%DQ+o36#(+=`wwv=Ce7BIaun=?NCA*PX?9M6fE0M3_av(Q}VXn
z0*8w!hhF#pp^%3ZTC{cb<6oes`(m7!|81mKmmM(U|J(4zdh<HzF5s80(z&3E)F2;p
zzGUTS(%|d3S-PuvGIuNEbh!Y;D&u~f>2XK#<fTw>!u;d9(BW%IGOd-8Jrqkh`K1tn
zMkf5t?Nl@ru<LIxE3W?69r}c+MDZVJj7IT+C>XrGd7?-kV3-A?9eNA-Dzwf>Ey)c2
z$EA@9`VXWF&?wPbWdE4tQ;ZRUw>6aAXEyuq8zN*@&t^1g3_<UQ;Xfp<DAr#jUn8Dw
zipdlz;KG1U7N?RkY2aZp_y&`Sm3V*hQDiEVfZ<hE=+V$45~>+3>p}cBJvuR6OOb}2
z6&y$Q;d`vF;=W;7)h{P-t4sS%l$EbGg4=aeQ1)%NwVTHLpHn}3H9(sKXUwkG4po9~
zXCVMpn}8L@wPtKkqiWKIamy1<xR^1O)UEly^2jsBG7`viHETYD?;FT6M-A0AfH-vo
z0}wOXd0?t0of-d*;th|I!I#)k05KtbokR0@^+5IIP?6{{fQusamxb!GA0~=B_s5=_
z<WW8@{crc{;$9{)Z(Bk><@mbaJwf&A?_*sEfC5j-ucdcf3)xB4?3a}A`zbejxJ(A%
zh(FaxNP#ju$$!bC9OA%#!eIO#s9ELAT+%G;@nd;aJ}a2%_2+u6Y!A(Id9d_f^v+}!
zdS)P^87Z`nvdJRpZ{ot#(HnXL#747&eN7qe#xWz(ZGqBDbJ;!7;c|-{x|Xyfk=aIu
z*si#7EM8@t{|S*HWaC--AS(3`rK_T_UmhXjxAl#ydErOpf1u*9ev^iZGH2(s<2U>0
zTC|*DA;W`-YKtA=288<FR#9G=;s?Dt34CHaY|`=|Ole(>(S*YIM5UlL9jcL@btfX}
zzh^jGZv=xnOVN6P>m?2232S<sWf{&Ub!Q!|7&WlL4u+|o$sFJSuws;wOrU<@rxGEG
zG4$7;v+RwOxgKidq=%=lGF@Dhf`dBu!lSMgsu0V>v+#y^S5_Inqw*t@{a-xbHCxQ0
zB!~yt5LDyTg?&AsSU07$7qtPq;bE#@5U_^-qu7qI-7pF0%*UorkYTe`gf10}x)MnZ
z0*UiE|4zWC|NaBXG*Zu-OIsuW3vL@U!#fakyCO)%`YP6PUQW4J@^Jjx7UxbY+eVVL
z!w@9v7iK-|+%rXYM38ybak`(e*d6#G$^Ar$Ir#O1zbNt@5G?1`^EsjPt`V4$J1a@a
zpQg0iUi1$;V1rkR`MJzV`ZU_KXkRGv^nG5-{z=`a$km|VWt`Vn9JeAM@&<?HvAkh~
zB5_BP*6G(|YM*sw68P4hF4mj|MdjA^dHcQOQ5mkKb1Mm?JL8;T4R~?$u?ROqeK!9V
z!ugm7f3%2SsBU~Y4m{|GU)w@lg8l@i^q?ylv5&TjUm9yguA4vAZRMCx2Ghn%?c5!e
zQAw9WgGBh}ZP2JVzW)0SB#E=nk0UMxte5xNpnDCE?%k)V{LJflYYbQU*cp^9RH&zC
z(=iSx@rKAvq#FDD2DH}&ph!@;1oPEfFUNtHn{=S3C+K&dr~9JNM&~F3Y&ZI-phBt&
zK~ZHL^G$X=k7*ET!;EKEe0&7>m&l(z96^7K04qlkuYf9`jV71*GNT}s{TW#OVtA55
z56t?%aUS?OU=hv+Eg2?sIZ!+CoX)2IZjN*LxXc-Xw>+O5B2|3<Qb`zJro(RyI6gJz
zwn(>n`AdA|tBj85bu4MB7!aY{3mnoVgd-};q>X#d=w0k1m#KtTO9otC#ivCMI%^!@
zrG=loFeo0&(P#-i(i(Pt&C3%5R-IOMDQE_Z*UrW2rcmQ@+?ugG?!V!udso$~kcT>8
z<FNdJ{Un{Qx&N{0V=o(PO6NiFjJgq&J5|ZxYnxSWXEEU#3;!b8)8i}p#JCYBs39F^
z=99fx1Qx`WQwn8C6Ty(TxEJYUWuEL!wmD(zt)%e~h7LDX;a+<9J&v)L^~Py$7SKrH
zMxuev%lR+RFojB4z>Y2K(&^yI5*?fVhtG@mpHtT6#qU)T_sKFS76{y&c^4AR!qp9p
zif+&KaGsreGD8N{&_$pJ)~rEO5}@iWxsmRr)-kUa3G+q-q>gNg6*IkImwLb$&}mCx
z2i?y71^$?VrfvH#ysK_^xlBIg?YT9PMum1S47zXq@G;pAeCsK`mpcvWvMQpfZv<>T
z-4@m?-Z*r;Q8%S)!fXh-p5ed?ydVKItsv%Dc6MNqoGvupN%}SBpJ7UaIa5FAPFsUF
za4!ZfD?=oJHfegpL%RIT`Q|3sJD}|SW68#vlrQvf%J3LyHhE<3cwWSDTrzEff0`e+
zlr7W#0T}H1WFJ4E%c;y?sd!L(+p}4wDSndU)VI7fn_H?7oy>rVEn@tit3{i8Of(a(
z@r|<&mjvs@o4oma88eq3oeKU``EoblRyd%C-*7@$rN9kwGhHBqId_fxWRY9ovr&ei
z4w-ZQ>q1J>cv!@}1jh07GeqLnum8)UNi9Ej<qU)RT^e>0<AWy0%_r=><96OB01qpk
z2D{E<zMue|ZGunl0K!<C>MFZ^CX~ym8*(uba)Cl0>fq^T41O;lpG17?$TKWDnH}S8
zUdx-4JYGxD$KB89(eXv=$VDvA{pLOMs`bbAxAPaP@0$1o9B{_2vl6%~{Zv<ON*6fs
zgDSFFP(s0oA=S@Kr1AfO_)(aji7$*?0u~DOBN-M4mb~rkE0W=LY(Wclpo~nhdBXDO
zxRPAO0W;bQL+eqZxBR=0Pn@oT?)Tx0;bp;vMqgTOH))URv#Oa}yv*1(k^EY1Q1L7f
zcHt!V7C3E(NjjW45oZUOK$R0U?pdlnHh(`;0FQWGmX8Q}+*>n7b5;o;ZhaDg%UcMo
z&5=J#KvU`3iBl&}bS*;q0PQ9G2G!biNHWtRjANo!=IF{SeL7o`?*4wnC5iAi=vdH@
zWS^P(M8uv#<vfJNNQvUgF7H)@1B;Bd$6)26O|fIl<3W5wq2tQtLR|@AgOD|YcX6~q
zYP*-JU#JdUOsW2qC|7Z;=#-=U%U{F6Xd6kKGaWJFWzkz#73v#IWMUMjyx2l*SjUab
zq(_%_pz_!6uf_Is9go``tm6S_eef@o%Z~|mZBs)%GyTnd1WT!{Ls*A(RQA&-N=IS$
zqMVe;^AJD)oi9s>YGWN3u1m9AP$f)s=Q(H9H+aEI;^2My(_VEp?!ZQ_xADGDKE+rT
zNn4hwy5%gtSZdUj#5QZI_L%C$iAjR0tV_PLw#t;|Ul{TV<opu~Ad=VPKN;vBF;bY%
z-m#^m{v)g_7d=wH(@$HJq04VcOfA&YdRudQH=ErF-Vxtz)Iq4OCVhQ&ryE^B#mb%U
zF>p~#`}z6L06Qp`f6$MxSkD3{G_VK;(Ts}T%fdrfUaZ~zM)6dN&zX>&3hrpv_(m4;
z_(nO3oQu+{<S!bKl#Qddyp)i7RT<C#c66HXN8iEXg@V>c+x5+lUSt7rR5Vj$wHL_9
z+6z?L=8J@!Y6|@~pGywaIYlsmaPIKZ=)5KWag10y;*T6?n2HT|dD6DSj2c3nZ<;Cc
zK?1mUT0;ItU-;Gf%Zf3&n0AFZJV6%I&oEC$n6}2LU%x8Y+}_AKXIewM)p`FdKfyIi
zHt#=BW-<S9`F|k8U^&6*=p52L6+9q?3yaH~AsHsf)gSh(`KKsLZGIwbKxkmV{Xms}
zGsmhDtKScD3AOsNg$|?U&bc!e+L{&vx0nQk8){)sri3~DTFDL5747_2YP<0_Bn_LA
z1*eUTOQ7|+?cB3_3zk;4ob(B=(gn;53ZC!HViahii_E488Z9XN6pRNh$}fEG@f;kL
z(C^aa3I+ldlwBZLSTxa+cdr&-@K5CjI~M%XTMMY_go%(r@UAfZk|ND;^R_k}ZEfx?
z(xGJxuacuCrib_=<}(w3g9BTY<|GQ>jC}*BcBxV5!M01TZ=P9%FM22zjM&MDI+l|&
z85PQI&E}TU=semFmRGUNB2UO3G&vbBl8}&8Gm2ZkKw-n}tJ<r|cU*&=8)f8C?WsIH
z59Y!;V2_v)o!4>XuyxDP_J%cAMHTE9KT~|UagP+-<DV{2C>6CZ#*{%kBAm-2+c7_p
zwFwvMV6hVH7uk()6&SsF7B7<&jAkQ`B3dgG@No)jCuV(5L!OmB{Ji&d8rppWA#GMz
zuzallA9gYNx#+#iBr-ng6K~4l0cG~+_3Bpx$N81fZsZ4xC3*=>(ssX#sf4v)@sheq
z^QlXlcY5~g*_2<^wXnqxj5W7h#D(|#=oGF<YFrB1^ge>!liI`M+WgJpiZ?@buM~_P
zIOX!!^z=A~wC4gidjrbd^q}hs+Wr$mo!_tx@$P{i<uWjWnTB|UpFopw9<53HaYi(Y
zVoJ40YHAxl_6*qH9KaZ*0QYldM0_g#NTMPK4c$oJ_=L#RV%9b)ij_U2*Yi6v!Fk<`
zmFxDtyVc-=P(_40zOv&e;80ImMeWcYcdmH$Z{Qv@SHUszuhDr)8jsv`?tXSaIpV5T
zcUwT(K6ldUwER=N_zQ7m8h@)Q{IXO<fJ8Sy*KM96enH88l_T%o*g<OWT_JCJ!aoWj
zCN`qL=-_rcqGPn>)H98+u>y0eO{Uio+eyf?pD<{%aeQ^XnVK_J5_^-ZO6NKKYlmL3
zwIWWEWFH&BAai7TgI6KF2j&82&o(lT8{8%&UkE$#5RyFpCWejJ6~^X#b94FwvmjAM
z87+M94Nh?lnQePJwGn%Uy{Sd7!$LFgJX{*IwL%|~x**&8))6T!3k~;rhhh!gF{}|v
z!4SjPQy);vVXj4BbGRyAeeOJ`g>>rq2sJQxpxE+A>lA5^RFe~$YBGq-00Jo2cyzZ{
z|8aEL$p^#E-~<>YQ?xL>tNNOI&7NQyeF|p9#Ga%vdFU!-U7HNxGTSF$)1r@}%A+vh
zpfoZ1#y_G0riifAa+B$$#>c63+`EI#i0`r`AK_pR-)IFCC9cH8_p}MfmS2x^HysnJ
zT4R-v$NliUDF4$;(`+V5AWTgO=V_1a_hfxHW4yIf@r-pQd*0yWCAavP*k0Zx$iaO?
z=p94NZUL&K$*&1YXZJ2tLy-7m!ywJ60FdXXXqQ=hSvnW0WZ~b50{teMHp6z|<fFOx
z*7nQmG()L7IZrm<%t!H^MaHsvw(`201m206Yct41*Mh^m6BI0|6Z#4duhvIxgfj!P
za?&CxcUx>doAx@N+gMatjl5oz5+{m+z=YV)*ul7B{281DC1qCNKb3=aH%0dzu)v(Q
zh+uaXI%Xd8=?|T(7-3OulhoeeQ)G!&X2JW40c3?o)4Y!r*j%X;E=gu0d|`b_ndsug
zDoJ`39q}A<*R<V?GIBY-F`IiK>}A{MWH!Nt22-!(@6C*jhEu<0YmwL)t>UA$ydKg;
zBG<fMCzENB=KAAlEZ&Xo*98^<YgZ@lFzj?I$*hSP{d1D#yT8zW4RqBCE}|oUJ=A)q
z-8bo5^4<j`EvQ>LMM@shGE;-{bR<*Z+gr7k5p21e2@dm%t{G6t^P&9sep%GTw&@iv
zKP!>Hj!24i66ci6NvC;qxX|Wue89ewB-tyhlV~42|0&%+*18*rZKe|?^G-PqNkJL;
zGPAd%{Hj<5u)YOdZS2$%D|wpdoCP6AS<j$$M{6)+i_ejE?-fg=)hVv>y~IYej0TTC
zM~>(DQZ}#u#H`v<w!&lGcVAp+WND0i*Jd*4uv7hxOOfhy&g~W3NCCO_${TAEvrVxz
zyzn3IYMxFmzd^2Ux05lm@fU?ZymXu&e6Yt=I#3KCj<#eaykSh;{V1G1)^RSo9<N-5
zgIbuc9PxZRaq`?%PcHB_*VBg~CdYrWtdFxgcgf?rnDJ|sUsN89mo;;vMDey(dpy`3
zhDEz|Sw+rVBu`JXfzs{w8;e%|m8d&@1b8Ip645Zs^nCUxfA^<E0}QxW7QRcYB@joo
z)7p{vCo8OJT$aC0_}Ird^XIw3s|20@K<~6olW5LQJ`|PO+->Rc{Y#w&OReof4ZFXO
zFT}hC9NPEP-=qn33jDOidgD53KW1$Zh(+I8wJh9<y-GRq`LFEW&Fo4hpIM1g=aZ)^
zxrBbUd+fz!6$U-U5*k!xIBr0`pK{!`Iu$LlAEZ0*d&tW2Gb2vb5!K<M%D3XugMPmj
z2b0XeWBM|dpYNQDj2bMY>NurSCQZBy1G<;He!AwhRFJ*-;qlE{<u$T>Onh0|@H^|Y
z<FfB(x&%&R+gov1bfJk)@n2UXM{g&^yH2jSk>&4Yw{;xoBy%)KegHuI(X@{rsJ)fN
z`J~P6ZA|xufu80-oyd-Az{y{;4Y4OfmAdZ(pDe8m6J?LCC*RytvfQRc2`j{My&0Os
z7=>^nZc^B<+w{iH!H9*QtDEHEQyc8fH+msbg$m0Db6Pew<F%5oyP3Yr%6qmU^OXiU
ztWQ6<@Lq6hsMuIrEy6N_FA7=dn_ZP~nY4bK1(Yx3M2A35R=~MR^izlu<|TLH^u3h~
zh%Rb9V=eS%%7A~=HhAZ~p4d*|tB5|X5Bshw8A_MvAq1uo$m7jw3h~=o8P(V<-e&}&
z?z7o($Vx62k>%l=Y2-7OKhOW7*R!p0c8P$yD@*DxG2nhB;vUH~o6@$iy4YFap%{o=
zUB%zxrIyL|=93v=a_>L@L*yNY9R8LrzHuKhd){0Xy|e;5Jfd&)Gpr>B%bLtOkI?Ry
z8?D?%>tdYBvhl+$`}p*yMLBK?1@}3;v<S~k3|bT~f0`J^Y^%b|WlR`EJ|&vJYjG0U
zJn3mPv+U_A%2GI4kDtr>r^)Le)9O>_)~wEG^EtTQKtr@(u~*G`J=<pfL*9p#_?bq`
z6ip`F9HM#D5VhE!pMR{KmuycM18Q}7Jf7>pm@lz$TGtKRD76{T`rBaB%$si3b5k|n
z-q-ybiEE)hIzq%N(+W4EFD{nqC%wd&EYGMD$FoJ*UFbYuV$zlQU}IT=<6eFGCYGr<
zSsOdQ2`*8lv4X6sWE0GMkZIxENh`KyZYG?+DhElBo{Qa?<yg1SqOG0^>GOV|%L)nI
z+4AGT(0-M}idu>ubrw6LAwRxBet9?skiykYn;PS3i6YWO`arfUPg=pJGL4xEv3Q8{
z>+=#c*K=-bA$`5q0qrJBZ-{~pO5WbZ_Uu}Gl9|yCd;azDTsfulevUCpJHfd5v4oQb
zmjoL3*7>;pcPVz=j1}#D;ivnJxYi?HX&;outF(>=Uj9Uv|3F`0f8Mw5H+y6J1(ll#
z=2&)|RBDDMPQmp`hNyYo`MQcNO#S|~Qiws|2KdhfXd6X0;mO|&Y7AIH+nS;Oq$W(4
z0w0JdNDscp|G3p;2m;6^)J}MdrAJ*GDd^yB{=_3jTYX-^QDF9hVJZHEP^BpgUis)P
z5zLh44{gU|*G0p;33&BJQp}qc(oGZ9ysjo(L~8d^O3kJXt-&_*>2q4fDo&rS<5l8=
zr!Cd_B76MtM)wW{tzMJ7p>U)SiHZ$4H;8llypxDXp5xIo$iskhhFlxMSmD<(#44^|
zj4=C0__DuzVjQrA4O)Vw``0P?pM5Q^#J=xF%4aH)V_do#vZ@V|ar`Mx$KL;f)L{=N
zzMU~S1A;p`Xl)6*Fm{rbf;!K2OsNb&EPPLFD&{B9*NIrt+vTgaVF1HhNpVW(mk?op
zCN2Af4XHzH&@g?_{c*B8##!;JyBQ4#D-9w00~Wd3y-IRVy7*N@26as9{`&y3%pK*a
zk;SKd9aj-WLf`&J!Cs|&#9E8Pe<1&8Gw^pa-|ra#6tMQs=bkQsEyzuq&UlU9J=&aL
z$Ow5*2O9@13$N>UW%_+r&08g-*1KWNL-r@*!_MoZFR?MdMPe>?QiDAb<){1U&1dRW
z^&M&4?Ln8l{AdSTy<=L1RlOZFI%|F}nSo1dgC?31{8kK^UCH3kc@>$JTm0G7P)1@~
ztLQZ+6L)=pYqT=PbBg`>TZ{id9SW8G9>2ErcOF>EhuEKJQA`(ma#e#)mhOiZ6>Qs0
zdB*GJ*%!s<><kI3G1>%4T$i8vjNiX7zy48uf1f3z^zr05HQ<hDxGPnR%~&6FSuPU6
z1hUD8!m><^0#Cbr4^twdA~UKv9i(H6r-(MM^Onq~vTV;_h31cQam-0<+n-Om=|BPx
zi9%9Ao}9Q`t@jG6*DNLEZ0e8+Kygvl?goh5mI9gZK&FX$h(_Z;(xA(-?hn6Wva9be
z;d>hAxCab#m&>wVPH$<iZ8^}wzDoW46`;TwA>E&Gj0*s-8K|^`(#PN6*oMD5sl+6U
z7*9_&=&$RFL$Sp9{Asy-g#Kb++rWYxnrsZbhjVMH%P1Wce6isrASo^d6q<rvY+~PU
zjbsw%4~^V^tXO{ilXMu-5hdmX0PmRaEB(FTQ${Rw;u}2J48v(d$bTT?y@DOtMCn1s
zee4S)Ew89M_t8<Je3+sBbGS101P8y`gCt=8T56FJuZoD7R<CPbdarzt$$_8V;|@PD
zU+(40<ev@{&|!93dzg3|5ZiD{gOP1-5`Yjw<JaXmj|5VPkSXzzF>w<F?&ox7J#U=O
z@@X!1LfXV{p+K0Xn2=b1E>(aw%+)FIveUUxvk`s`pWuum1^d}zKLB*~b0+bgDeI?J
zZD-f9;g?;E?H{2fIA8|jcW_IJLrKp(E$LJFU|Dy5=QN|_qh^49q+-#skJ)uaf#j)Z
z%>jy;S!T^^K)u!f7u{6QdgqH)z(R3M+HC<Y{6tuX6x&3g^&swHCZ{_p;=QX9)&Lp{
zE`89C84OyA&A~<nZ@*k*6AL=4b172l)P;)X3_6FTVrGT6ClD7PPeA`ppR})1^&cn2
z4^xWcI(q*vDI)2Tybc=VR6Sa-<v(ab>@YpC_fMt_i1j`BXQ6LO4dRUDzTQ@v8jz6c
z-_uHN^)W_V6;t9<W8Xkewn0Ka;(ZP3<HJko$MgZfqH}N67DU>_a_I*dN82{td@Pb7
zxEJ)i7qXr&$zLp6TQEYD6@1(Lv;l`q<2SHN_DLrT1-pbOZ{WyF4&Z;O?IEt4g3Qp0
zt+F#F!sM6y+x1$YR|C<Yn%cJiKn#HRMvebno)s5%;S}al%r#_s_3cL1iHmQ~SYBW7
zOa3;7#@~o9(Mgil+#P!Y<{ju|Wtrc5Huq<|=5jZ$?UeRfTk;7p<M4tfNf*;fkr6mu
zJz;mxFEPguEbati*M3M{VD-rDSOeWFQ5r=0_#HuGw2ktgHZYFuu=NPUA_EA;Sl~Zd
zS^kxy9ZrzRMkzrW!ny%q$$U?BtF`AZ^}H?K?$gJdM-mvx*~I4mku#ffa;ZRnJ3*X-
ztFo^Xn4$wqF4nCqk6kiU?~vF6*6mb@#;(7fq_jU-JTnjIg0%KZ8C2^iFFs+*;2ArC
z{lSLb8KJ?bQ#<SV_auc_R@X_1YyDu0*j=PWzWHz|?E>_q+&K#socQ!w^D*lMk)z|+
zSrza3b)Ei1hobp<CA3`SJ(@c@7p{&#rLr#^(~kobfhp&#n(*`i*q;(~x|gBQ({pM_
zitl&<@Uey5Fc;g0v0||LUa4p@{Rhfxxl>G*!M`ez;+_oZG%q_9FgiI$0XLFWffm|-
zpbwmvFC>~>Ju2)v+EZnoxZSlhbH+HtZI3m^wFiC&eOdoGMoGQ+-r8Xj@r$CvPVX6i
z_IW-&jq~lg=*A3ox?uAl_09$Mr{j0P{WuZsl$iJg*r>Whyq8VFIX%Ac<;CrxS_}H4
zVteo#$94aL(u={c3x2mJ->FGXBq9S{(_x#e`0@`g)XDFc6Y6n4-S3~MT*H@N1~9~`
z925^EJJ2E%;5F6E5cDmEaahTs|DnOyp9duAi}3`}hhOO?kGyx?84WthmANMRQ3=1{
z5&EF+H^LjV1S}EWznJ~E<ea@%PZ5qa>B?XFtXXw65cYp7WP&q^BV1@}F9wUGa^IlX
zrJav)Xe46au+Sz4ajAvqD^Z#QU#bi4Ux1JT9cLrHmws|z#m+YR@2BH1()v?6VkYq&
zf`&QZ4|u`s5!5^hHTjo>S|56aqKURQ0oJoh9h*q;y9>K4os9n2f;(-2#4M9U*ZaBt
zb}so_5SEF$cqg*XSkPq<uGY{OZ5HU85I~iM?wKTuSZ#u&oJfCpm{L9oFE6)}4bRw=
zPRsbb0}>ilteZ(1w&y+XnG&6`kql-~){)KhF+gI>+j{-Jq2D%_4|kgzWMFyn_{swQ
z4y4SPQXqQj0NA>ib#vSO5<rKmX-U`u7IF&C1PKg)YM-*oajo%toC)~c`y1Hzr-^!g
zYK&0O0x6D(HCWyXoJiqMw_eQ;hFODcl~e~8b|AT1Y1qF43yjKg?3yAxVx>MV`9uYs
zkAfEzXy9z{zu)s$h6KT)WXeD>n(p?3T?14N#BMA0brsxZ5AA)u`F4^sasiZZY3q8-
zHIdkFU<sAaAL#rKRGD+{SS*0nwaqH*G$Yl+)UBPDUC#2OS~(js9myy%+7IcOq|v}N
zK%?rkzNy!YyIp9iMYvreyOo(~f&+Q9AJTbx0E9F^3mwF(_|UdkJ+bHNrm+Ozjpdz<
z0Bwf%YIi!56S@40p#<O<hfK9Z_Ag-51_x50M#LX4K3(@JZvm2-gg}p9XS>(`?sH%y
z!SAM*O7C7`8aaz<Aqt~?9EjLd?>4eqLI6}CX$q}CozMFJaEqOc8{X~YH~)<+B`e^&
z%j|eo!j0$^?i#zN0R1ah5FOpRo9a&^UP?fCmp*f~czzAN9_3WkJ&3K`l~xuC&ZuO9
zFN=;hiVny9;XzM6o}o^6@_WO}A8#0(*u?MjbZZClSH!t(A0ytFo;}08ty+Ijw;g#V
zl~ykYU9eM&%-<M&$=DZ6Leq6?9tAkB_zphagj^xXFkGEUF2qs3?Vld%BEfbb>n!|$
z?XKN$R6rSdQ9?iw()X;kQ$H=Qnz_$VDzD3iR=T}lXSjYOb?zV5P}ckXpzVT7kdDjb
zi(><o(}!1Dzr6eCeDx7mb_%?^i`Q)BCoFljYKU)K6RH2ahS?ygxMchr2I|tKB)=iV
z$E+;imC_C$4XWy!tQw}okYOc_pQ49O8ZT7uh51<cM?#)rJ3?V$Zn5C{&VcLbFa6+O
z%)p^cN`K)H*BDg+#r;?dn(6HL$35xmPMSN8c3B1)p$nF38Jj7in<bl{Ckk3QP<rb~
zQM@@C8Aw~qTE70xjPa%{lPNCn5dWf7W$}3FBX~4}kf;^BcW^;*beed+n!C~+k+wv9
zSpzS5u{0l=?2>Us0m^fbNxaHz|MWIr8CwJ5erc%tqtS`V3aWIjN^X>Vz0LmAO2^B;
zc+@p$yZD5myt8N>d5jBbExA{Hb++Mt5jk;H8vGwf&rRb#4AuhD&nDnOnm%1|EYh7h
z6f<ULg}U`08;u6kYThO{uQaA;q4lm4_9mDgPj6=rIu2TsjKQ*Ec?L}6Q^NccIK7sE
zJ^{`hU>K5?FvyiO(MLQRp{P9=FW|b84?l`@X{z0PMD6MQXlv!Ullw%|DTbav@hshd
z!KnPnlb2PBw%}7fs<C9uGIpA6^h&_sN7%>tos1}%4C0%+IN!sD;wImACVw7Xk!z{I
zClcwhIC~c~9#3jWj4FPFj{fP@pRrQI$}^OIng0Ln;)QdHEmk-#x~GHY{{!){UBNC4
zpBd^!5@e!S@3kD_7MXXUak5uJ?C2Y7#Fk}&-5Fgit&Ev81;K#Tuv-$~qinT8es%~H
zl#`lQ#Fy#Vf3QMO3Pn#w;EE}9T<%oaZjJ}r7>C?M>`mSOK=sKDj_~WUezm3(r_5`i
z&dR2Q>QApAJ4LB4K2{S?ext`X?P>~xdr<_W&CB*Sw%jGk(6$wR+KBbXQ_Q6J{H^s)
z7dariL+^Ssz9Pd^Z&cl6yF_qvvMht{ST0Rf$(tVrzsQ77N@O2VwMtrkeL@$MZEM7b
zH?ReuPvnQ)Yl%SY0ZDQ&EbWrISPz>bCcv&J%HrXL5MqI9DUo$|kF+FzSko^4q?X50
zTw3h|+rH92Q;a`5J9P?0v{0_4jt5Y5vvZ|`V~2SLT$hrCIqOwI|08MbL0;phfwoPN
zXu-$bUJqrDDdbzI@l`2rmF1j1hxuPZY77Q>AM))+pho>&^eHx@5j>t@5$d|aXE$Hv
zQCsx;O*}`c_#<TsUBFrSHvBu{N{v0$JID9mw*YEk$neT+0+0}l+3_lr@H^te#qlcw
zz7+zjcG(NVH<aC*qQ`+TT8<qoRdtWHeXphfLNW;_beXnrO-{>;Ml?Bb9}pGYvOlt|
zm#td2^-HAKU#NVlA6wKq_}hSHa43p#znBDRK@tjMOMa6+>-+XI8?E(HT=ue8fro{K
z(AVW@P1A+Nh(p`yY%VX8J<Fxxt5nzBR9`kW>pQ>Ie^f>HB2;2n+x38Sl7(vGTaY_r
z&`Q~}cOhqQWiIWolEKiw=K=3v>B`~pgcVIe3;E9^UE^x1XW_!sPlj^D_l=ewEh0I#
zf0d7qG@iy{UAT|>H({=Y<;zS!hr=kjZYR!LH3qdCxX`H>!!ZtTZp1!NVqPP^k_T+c
zhH!)Is-N1OyCoW_s!T#tvlOJS=mLA5JMna0QG{#~!W-X8^EL7W*X;w+v$O>hX_2gA
zHr@Wamjhz~$m*C#wA<>Od#;%d2z@v@d-_4N-t$<;EjS=ke)P%5%~^K{5~;Fo8iP2@
zU6hY9Em4Lq5}VkyhUrjU^Nh_E?au5SQ10;YRQ-95>!(XPu*&mu(eHB)EQzKzt)|7<
z>_5<>pLn=wp8R^yttU86O5Uvk;N*%7Ur=mliw>56`(%|~ylkB+{8WJldPDg;1H8Zo
zv~HHR1hTFjy3U<wS{MSc`0p(5+Bti7p<Q-Bft+x8fr~4(KSh3seFGDDbFDVA7}RNJ
zc5eRYSqMhjM(oJ&U)@jxhe{g1C>2oE=3)1Yk4!PyHNLo3n0;X}e|p?~bOtLC6{nzH
z29)4nU|5WVA0`stMhpPU3Kbp}ZkfqG>@tSQ$3iM&{NXf61sK5f-~vEr^?WukA|}?Q
z$r8$&jWc+OqOroiZ<7Q@<Pdi?LX6<I-q!m#CCl^zA=Z)>o@^1p*6DoWnjpx<niH&O
zvAV2Rsix@LriFsPFyCU+>di%*;%o+*0nK)`8O;U7R0@VfQurmly8aMx8cl$UVe$DE
zevin_NwUm9QQAwUCKOA^qN6%5&xh2vNgdKD(Xna*TRTex)+LHBH$xDOMipK(rLNCM
zp!GeA>hm801eITqpOp(BR7T-24#0+C+I&Hb39pf;h~f-0dVLTwlZ`aA7_XOEN)BC`
z%^{C+aW}C1s>?cEt296K1w`>gA~YYok#TnT>AOZvIn-Hy(Uv}Y<(uILR#fUU;Qw$f
z^TH_1Xjv!ThJ6`1(kp68(^=96aqibJ-)_O;D-4(Mc1$H*-@1QqhI&<w-mh-yl=rBJ
zFCbJB$lhhfJR~|@vt>=Gojb{Y>dUJZIjX?DuHdv~c{nriw+a^QNp1^9VYHTg@&SK_
z_f@_l4+n&CGMWQhu9xNLtk$b={>Te96xDsihdJxX0@K=v2@O%zie^(gZj4;fTokMS
z)OM2>9<%CQR=i|&26l6Db&0K_S8V>RYCe&>O1GeSJ>n*u`)V@(*3TP~>a}yn$KT1=
zh~OUMd|V{nQ+<oQ8#8Rxd2Cl4$f)?NWU1(JgV1npzq5_NU%SK8JyDhWefHa=mqRO#
zeG(gmRFf=0{iA@@(s-hlJlgFgrSW|E<FDB=vIz_$<M_A3@hN4`ClR++(>u`?yA1x5
z#l?&+uinZ7Xy0T|v=pLBXy`O2BOCGsMa~dwvD?Tsq*EVqqv`dG-<TTg+W%as?AeXx
zb**mNP5y167ALfU<TH{)F~7u@;M;3cDd)1V1isr6j0L0tQ*O;TlIEJy{2uZ<<USbp
z<XvWn%roqTR0BoBoV_a`P@P<7`;0nF3?o*Dtw)THg$Bvj%Oy~{mlZWDP7f7>8k*HS
zhR)b%g?tZvPjAykjXj<9sisds>Kd#fYc}}o0)ufU%Y4nL&yLiDvi>TQQ0xt>`F2Y3
zz70N^fd8r5Vraiz<;FkJ;l>U+x5xUMBHFtN7q+fm8n!|~V@@cL7++wS3>C7V1J#JY
zOQ1~X?hEBVhkCCQTdqp!Va>X~T3{!={OQfEvD49RTw&g`qY7-sd3l#yBV$+@mHMwn
z1yv}fHJgm854670>~j*}lZaE$ez#7R*|MmCs>qP~ZAA1iTG?pfjzA>6GU8%j&mr%B
z>iC?%ehUx;eoR^AJ`y`vsH&=~CR&6yDz}m!=a>8zC^Txj(2`f>sm<*%m(ng6e$5KE
z(}^V?_Pi_>C;;r76H2kG#LcZhn=X_VOJ8j-dZphZWVL*?ygsH}gb&ct6bo{BqHlRz
zR5Wcm;hw1e3`x@;pyk<vb&*5H6;;koB~&l|+GFTqWSrkllQRX(SaDqS<|*x|`Lx4~
ze=qG+EA-(h8d~sgeUUesX2H^-9ka9J71_-%M;@_qKD<ngiab$Fx~~n@OH8+U>F<GZ
z9@wn%k75*R=7=-~8~TKwPMuZArb8}bJFihg%KGxje<)}I)Ko>N?&l~3dBs>LZe`-k
zdzop*&I%AYR+$~*C<|t<YD3k{Q{)Lo75|p%W#NDqD^Ik&3P^m-Q>cr}`eep`Z`!D7
z>ath0gr*`Dr|Hn#P78PbX9b-ONasE_!L`p{*RyYZTrXMF*Z5+c{w?bDu(l<Q7zW$7
z7OPTKY=p+HoXJp-$CjS^`d(O;pShTv!mAh`8b*8MzsgGMGXZo*_R|s1^<7(rnbe6H
ztj=Nq^H`6H7f?=7QTEBQA(9&5g>CcX6xZZ!c4#<<<FEKs9Me%^wj?F?M0awK<PIuF
zTv=W5Barr@vAvb&Q`s!aKln9JV#<1&PPm)HA^xf1Xa3;_(UG=ehAh`MJn>yfY9@my
zH5jtJxVlgo$=4y63>)q4**P`3QRg%a_{DikSJjBE+spCZXIWA5d8B2Q*<xLgL}j0z
zmf&oIN?&m9QdZPFg^S>c@?d-)YnDmM!*PGknvU1M$0E1k+u4cbydmkm16((dWYk`C
zVupQz0sBkAJ+0@E5gBweqg7M9>>L<mkdC07F(r5?MzJ|imlAu5($phT+j@A!er^~*
zVNf(Dx@;{`|AA)uaIQ*Bm%6DUD}qDMP&`SDGx;xW-D9=6s~67-f3>33>wLInOeLu0
zH|8i?9mU?>lgm^Z+(->BPut4*smiR~2bJ*UhFq)ICf5{p5=12U2D?upXsns|chZ?$
zY)El=nlZ~{oKIjwW&42Eg@%>~-j^Hf$3WC!=-bstOlj;ZTf@L;dmlV1C_{$Tbt3B|
zF>S!ku#qTpY&(bP1te3vuXOU;3a}gc-WME_Wp4cZ2QOgoPNZ~|XS>QF?W!{}21&{D
zWeFKUbL(>OC~ro2*6$P(9r9HS7U!5P59aGhO&)Vn?Z5w(a~>UM;sD5nuj5}K>HQdS
z%Y$q|0bQy|!i`>Kn6Z_C2Nr%>kCpJXGKH!a9C$I>FNzkvBTh@R1X3-Jhx7EJqjJEq
zTF+Em>|yVwSsPmv6!G#O<}16g1l7!3Y$@P+O{T0W_jPnt4+ZjWA8CI0I_k2U(YT-q
zPb;8ohVk%TGF&5b?k3JKW)s^@``iy?aNOZPvuqr^g-W-L=#>GpSr!6cAE1K0dLDM3
z<wqf#qkTZ&_zRDYX4>3Y1--}0vlA(`m=M><5vL!|xkwol5nP*7jzOkK$tux~u-O{q
ziujnXgOX2F!VT5td0?lQqQ$dz9VL958)vGKF&)!uXz-!r=J}~cfMMTXGy3q=$En#$
zgB!Y0-P=tJj4Ea5m%}x!0la4QSJZ+*X6}CkoSYZ}u`1G2r}M=fwD$dk(&|3P_xdqR
z>*DM|e-j1lq1-vAYAYBB8O#a16IW8?U5?J$iDgy11+Bej!?=IG@-R15B@c}PpO%oA
zxGk2^kFuO3HJ~vWubrx5@%_?PpOey#{kF7IU^Cx(qQ#HzbP^3r+YhC4%h(56ILe@1
z3Y?hXvCq?gTPOl@l4p@rJ+DjnNEC7vIPtjhxHQ;fcan!$FE<jpXax^c3<5A!qZn+w
z%^?>fk^Pdv6d4n=FBK_OHcqY`itl4}28}`5blu;%S*2#VS6+(KWa6@)R_HcOEhW_;
z1IAP;Ya<-;Qah0E8VFmo$7BtZsmIK&a@S!3K_%+GUEOp`9sfLwY~6fa&^ui;3_Zgq
z-zwNUUh4RJ#k%*aWDK&YW+$HSl-XYywVHV>49#T89DERs*}yMvJO4u?{JWWF{Ly|E
z^{Q8JEUTV@nDRy542~Eoe@k~@B%RrTF=u9O*gQV4F)uEH(utFQp+UjnhXjTeGib)r
zOt%EKQu$@}fundeN87)yVX{XDr@n(Fdbnkxx|)~GUzo;fm@J_D0w4qLR|Rmb^~IJ~
zsvp}+tfG}bBX?N-jkfG!4{I(IrpwHlXc^hNPN@0eBz8f0-B*zM3-Z5X#!7tqO}D0U
z<){|^-X3eyO^kcuw;ao<G33F#x$MWc>b}Uo+|<%=Yy40}CU~Y$RKsi|XOW=v9PQa=
z&5NePVpf;H)G)M<#D=p|#jK7P@f~rFWV91qg4>Ex=Z1+n9F_j6>F*_UzbP3OkfpI+
zK9pOSQBTcQaE_?7_9~IpKQtQj1-72Rj(Enk%ZP~7lqicDX@`mXko;(00NOQ5ir7&7
zg1{#Ew=tCPVP9muJ!MBVC%z$!Ou}6T2b`5B9$;6dB@wGt&@}?G|Mgm>IVZX=e2&!6
z6|!Y~Da;~uzmb~J5yA1~{83U54voO)7w^2TwmY3hobtWL-J7#&iTKceQzKnQut6O0
zP5X1w>0!gv`lAfPSMx)vHdC-PV;=Q$QH;wn+ODRr<(qM<aeRLbGqzqIeArFtZFhno
za~%7P**B(f&d&??w;swvr>RhJuZ?KY3P0U|RZiY=PWL~@Vx{d?yurhAi9y=4SN%3W
zEs;<tcTroi#y}E!zu?1`|NqjPWViOt5s8iam|o7#rXv-Em#iw`RVgFIa5ZP&KBotL
z6>`x_OwX{^G6M3wt@#5iB@o>O_Rn2UvkhEt^a>q<uHc(6MSJcrPsZEAZm9{65gSIH
zZK=EIJ(T?e8aeytv}#q65wxvcNFxTfo$Hxa&85_Z?RQ`c7b!T`C@Yd%5kbiOCO*UN
zB7vD5)3kp|2>eQl+x%}s=eeMD#U?%N*IMLrQ61OcL^9QyzfB%Dplj%bR%jiu|EEHS
z?69azk3F;kzEPj2$N$n5kBl@V!d+*7vWn97G@PEBZznHiJ#*E4B0BfVj%Xe81nG_-
z!Vew!h8fyB_^T$vydD-(Ud7YVjJ1BAM9-R+Yhg70`W!8g%QIXrTz+$=yfY4HU3I8;
zmABihuU(_LpP2zFT>@kOsUD@EaL`rR7ru`%@DB}Z)qu;WEb^KDf(r?_aO%!;^KZkB
za^(6JV+$p1_}n@7*Mn#*C5_?Sv)DTx9iQeTD&PM=Cy6k8QC2I3{@G$uZpiM^bZqtW
z3{}B*ulz;0%<^9YgW=n6VT3Edz9vN52Tsdqz&ITt$;1f2jt=|8cct~meYy8JXOYA;
z`5CUcae#cUN9cPJZan#A@eoFLcZaMx*Vp4p#C0F1PS8RARWB9ESTE?x(4`9yc*NcC
zaEOWBKDDCwxPXkekHIelI5q?NA22!JM*C~roT|9th`qV=vt?nDF!~l?oMmIi&@8k0
zd>(M7wr~l%qedkZo5Z*ujc^@4m#Tf*pCV<P-Q<@ExZcTOVGXJX1$+a89fz&wIo}4y
zVrK+UN7Il}bK%U>+$m;hLME;w@8n^J-n7K7z^O%B&+F%q^JD*smf=&^Uz0=>>ZEw<
ztTj(ht<@`$Oa8nSrXMI`e$u(5<Sv$#UhaIHbL>#Rl(Ri16QI;NU&^z!^77iu--Equ
zsLXFr1ExF1i@7PzS0fGlV!~$h&7(9OO+=XQgxH^a0hz^Klv8eZAdjJf2!8y6!SLsP
z2;do++y@mYktIP3^1PYuDm+Yhl*?)(cYE2iJgBcYQ?_am$&0s`ycaw5FgJLFxYB|P
zvTrFvaYpz_19Am?Vi6W4xOCvw%O2md7%>cf4fr*Opi&V|5_~`hM_vi8_8;i_gpx^K
zdX;flRbbSwIP`H-;XWs*LQZ-cWlH9PZ2*<hig3SvgSdJAW=Bbkzw6@M_VZvcyJgMT
zy+L88`rCa8Hh={oDrkND=08vnX9ahO%g4C@D!6b+R~GlZqLSIMgJ}^Q(vxKy(AuL3
zAd*6~^@x=Y)KE&-EB?-`HR}nneC!DJ@70qMNn$;*fmRPNO1fjK4d4YN;ks}Q7BE7%
z%aAK1zVHalmDf(4OQ77={7VQi*u>K&Xuh8-S3h*UFO3iS`I0$l*G9~jcveL&xNI#@
zVCGFjlT?K#^h7IiLS1A2yEOoC&lT|3t)g_3!i`+N$QQ7z3ak2>*0+<n&cWK}&~6R*
z4^wcOsvW}CnSo72mFOs3>REr?3@2~AYrE%37(Cjh6}vLs`Uy=Yju`S{?l&S#JI{@%
zN_5JKD<Neo_s`oq$6lh|^Y5?n{L_0ec(N1wX4ApJ$cCN^!27hkF04-~DQLyd2X78*
z_62moPZ#~eB%{ynQ`UQRASDgq%Y|M_JnU!_5Ves|DEd%W|EVCKTa`s&=Z!r8E9}H}
zVl7{-j^@93xo+9~$)sUba8fqpaXKG&FiPX0j@6Gx*b?p~8B~`FBpeY;x$iyKkHDF4
zw`CXqE3y$X*G7<bul+*ou1aL%uRC4w;!inkt;LLdh(Sh>#Hfuic~}ekpFj>QgV&tm
z5R<#fiosD);H2bAeaWb3<BjiVIseDeRYpbCb>SgL2@z?Dp&KL>BnDAB1{gp}>245d
z2Bf<i0qGW`r4bk!q#I-iX~~fqzx#fFS&Lcg-h0m3`|PKV2oIOH<q_*XX3r!?3&FN%
zTduHQGp^)(dzm~U%T4%>M@kn$@b+*5aI#hY2L|i^$k%m<qd0lVXj4GbF06Dl25>3;
zL1WsA7Id5QzlH2{gf^T6;(Tz6aIy|Ou?i<{dDN(QyO6+^D;8@D6y^utl4?Di0oWbD
zLU>R{-DRInqi>C~2)&sJ^R((t+Rb}YlKBTZzX~y>V3f!X_FMl$r_r6sn&Cl(3xBUf
zy}_CdbDUWXhwSqYAlhe6m@?d*83C`u7s3p<s?aq%sGsm{3nt7!w|NzrR0MblA4ZS}
z$_k#y5HB)8MJVt7fu>cbyB+)zmPuS@*6YiEX|4Dh<dO5Tf+Cu3%8%r_+Z<^KEF^Fk
zHnhni30+@)tuv@q#>H}?aeIk1RjzoOk=O93BPn4ZeM#^t6T0zGesfsR!#xj;C-VK1
z!V(9%PrHZvD)#_$|KG&R7tC_+F$65S%^<oMX=Aa?3>unmCtm+RihKRqWwiXK$F6dH
z3njA)XWtSJ|CUPC#up@CCW}&HKjPapJ)W6n|B==-QRf3fEVhDvkZfKQERtIvHkIzr
z;=mZDG2sAov#?|Ji}&cUZzr@^BFNssKIqC`E?>wskI^5GxiCiXmOP-p;x!k6OiLs9
zer2kqPeP2rEO?nP3#TtQ69UN0vur-s$2S>TFTI2_4UOG$9h|X&SX71k=0U!4GMVo2
zFHbP{fTdZP&?f}y<~K0Gr-n`?kD@TrCnWbkZ2N&msGH2<Z#2hpG5cyC<`@9PaQff)
z)qkFP|Du+<2+Pxzc$oxUhHWDL52VSld0A|yN$&JXVEx3Z?1!_%onjKmm#SJsF-d@u
zIuHkkPbnsB(<ML?S7CpkVmlI<?f`DB6lV6e7U)*`2ePZzr^sfXTRzBo96lr<OD@{g
zdY~yfeoWklgTYbx)VfSuF$GRQOke>RYzfYr3VgLej-OheciCO9$~}F!wIVIHPE>u_
zBvlwCRXBdp3oxB)zj#6AASKy_X(Z%j>lS_wG0D5P%gh`SPYXaSd@+ls8v;BSS;zy`
z5|TbvFFMQiY1Ufbzrkd#!$>KN6JUUYRPL*Qy3tqvK=$NV4`mf@(hk;&9}fjZr1%>o
z9~Q$%TTp*<KVRwB<*_|L$|qM7S;(&<4ebH(vCjb6&KV#4x9y120lNAKIi>uXFjun8
z@}>hMmiGQn0C@=h#EJPGkZxMac9fQC4jjSH1a=o~C?cYEF@}J~6q_-ad2jxHw)~Y0
z@&y<0#0Ij!I)gs@%LaPTwnEaR{-b4yyMH!@eTCB78}s`>C-~EXVP-(KEn4VJRDu3B
z&7PK~_VO~$8Q~}Yy%B829j^Lg+fl}DX^$TOXh*6Lld%hZTN3!{NgW{71!~Exlq2%=
zO^6Rw$u>MRvhH}Xq@EptT7}h>@Q`Jg$_+LJOCQN-K(}LCu2xm!9?LM#t>El0loNqz
zZbcK&>x#J7f|v>dTZ_ZVufO29p!*RWG=91l4ueMvusfz&27@M)3ZQbuOa!OU`?Gd<
z%mVcE5=;-IXv|LB`Jb-aP4YY@i^J<HTw$Y)pgymmzAaX?#7T4)haAHtFFBa)lk*f~
zsj#F!;$)ugd*xS!Tz>ATS3jo+UvGn6jZS%9Yi;EG19_5n<GQs@By!zk$p;PX2m|LY
zyjRgZf&<xFOnL5cD;d5}TZDtxIxao&5G^zv+6*~8aRA?5pzL}6FzPVmT5>NAirG|S
z!j$<1Cznby2o;<F0>xWGS(e`693LIyZ;JTO_2d6i+Kts@w?COOy!hQd6H9YWF1{=T
z*sZ_CLH{;fw6{EDG%EAB15;$PJ|AIH=!k?F5s+cGB*$3-d&JUKXl%+BpWBS@v4tI-
zFS{M3uZbIfF|xtKHmOe>XQw44&onEM^f{$%>F&2vMYcwOfH6-mp)i*`);Qq);m5QU
z*9u-QS*pI`!BFwpLQaIyZL(rDh~}Z2|Ep52n8c=~t$6pS?9h<q<sta7K`^EGtt1EZ
zNIOFoit3e>Qh^6fs1N}SZW(qPg=!xA;{d?j(=~`(ynIyMTkSa(=G-ivf6MhsLg%In
zs07iW5qKkUZ(QPgi{osKC6?H(2(>u#@>UFhqZP$EEQ7z|&)K3E^SM3KkmXx3bQE`M
zjDsN(cFzAifu9j)-ckO`d0t}~$M+~1BK`0YQRMxpV%=cZ+0u6WZQ&gk0?`I>Fq2Bl
z(TVJ7Z-M-IN<B#Qf&<9ODvEkY#aa|{lbdoB0@RV&9*DAiQ2gaQ_)k7z;wxcf!yVul
z&$5t%O$wCfB3wD<)F-Xr4trtmmTL(unyfz`&rCR0_wp=V+_cu|JAK+bEFZ>udl;K|
zSDk$8Q-1@5nBpos2GI>Ul}>x$lWUG%Z2-b+jaVt;Dp&KFM*N<)f0+PXqZu1M1>MSz
zF_8wWZ~Q%XTm_3%e@(#qoD0E~0}Y^)hF<WUf0xuJINs=+UryF6OE0yUbVgv0(f#6<
zA^do~kYXyVfS>s8o!ea-B3-u4EVNFvlJ`qCEy1jjkvBw>{HCjY)4P*wAdbAp5WdD9
zaEWd2Hr8N6!YyS#Q|@yNPuhQG$De?PyfO{vK1-MSALs?*t|h?nl~BylG)nCFeF#5b
zi$Aw@?^T+b>3vIAiopX~-TP9{5o_nf12&QBpFA0S^9xe2NIjyZ$5Km)g(>_2BUCeh
z-=$8gQ^Bg;8!C%Ge@IHWB+GB2?cJbDNx9K(U1z;x3U&FQ=rpzJ57CEsqKp~RC}|)=
zO2(<pKL_IAs@QvIk{toM&{QO>bh5y)Pre|(cE~L39Ur-<x=1^aFu34k_*C7eD|&x<
zAW^%qnJ}ER{Hqo%^tm(T(<;fSs_TK48ja^*dm?=DQNu(%7P{t`WD@?EFDp6kBF5iV
zEwxi%h{fNKya$`4!~NrrY1>jl6)TS2Hivr~tUS}EiJOFgl3ZTLCX?6H3_Cdvzfcfc
zj(t1!y66V7I<%P$h%&7kH3)EPx$!#6_wZ_=nyT-f3(u`0o9r~ronGqkKy*u(Br`Pf
zk|>JC3hwtz05DDO4auEX9~W^E(6GcS3SQ=$%gt8A@Sa*PX!(C%&(8$6C@1n2f}z&U
z0Lo(aDyF*jf=&a^-PcL{Rwb`MOS;g>i%dBn!p=ogkN65Doe~DbFsqRKiUI}NX*`N|
z@&5#mD<ru)Z3ni$Rn>hZ-Sr@pz<jk32b0wOVSEWxAxb<J+SJOjqLtn2qd)Gy4{J2U
z>c8l_!JW7$w$J#1K=$`so&5vd%wRoiO$@^eX=Q11g~g#Xbg?Da#4+apL(czIt8)P<
zj7kF?bt2s&64;Wo@6@&LsDa)UE88)=T5V-y{m4;GYD8(gx;VUuL6cu=!Go`~`mV-s
zxZ6F?{AZgO`gRgtms=;>w3K6ycAY=Ex0O|17z=p=XkjDt`F~g*Gongn%lbTd5vXkd
z&DG;^&E@?CL{Px566a_=fQ#fTmR^rQH_&{(s4c#gj1lsnf#OmKi%xC_jFWVUICq`6
zJLLZZ)yYJtQX_9He~=i#@tV|C=kcp(_|s3`%K-&XDeq*T5a48G7=67`j95`aeqFP}
z%fXGQD!O@MXErE(Rn&b0;?!*hK<6S~bHKbSZ}DnXE+@R%!1K!goAo^y0@oA|ouEqh
zyA<h78|*PqLEb$L<S-QL+8vkn-&6Y@1bE;y0l5kC0Ta#G5(Q9FHMvHb{?s2YTJs;y
z@#Wm-E+RIxztrXZy?B55Xu&=25P4@y0a{sKT)F7ED52sY3xysWDg4SpEIs}@=8b=%
zA*hoo_&Lk%*<6vP0Iq)=kgyS?fm_LI0#Krsl7DmhX7ucABX6U#B4}$7sI?i$$I`G4
z0G34-S)Ui1(Bs{ab{hC*${f{K+Yzg?Kq$}7pb@%Cw<dI}h9qb^y&8V3hiqHGnl#bc
zrtiyCG3`|*$(MW@6zpMdpL|S9QSZ#^E-$<0#8OUQK~o)_6fm>zFH?jE^5VJ@&)&CL
z=Axzq?;B)Fb{ZbNPzQK6X$)cezvHjoR%=j(yub~<;zZ7tuNnPbKRuz6{;ES!?R($Y
zA+1}?<8Tm!w@l&}1IHdA%wOL>db@9nn{LA37~Y|K#sodv1vp1yhJDrjLAb7COq8n4
z;yXJFu7mv|E9w-8O;e}N7UfV=INIT{?^DDgFylz)gp$b+Si6tdt)qM4Pk#}_>?h@E
zfy!~+iSU}5jXsX?JPfA0PkA;M^!WOxBjcJ;*HnTeQOo&%R#zWpdWz|-nv5MZroM%Z
zZL!4l1~Qu3P7HnQyWB1>Jp2-1C_d4tZl~~>7IG@2eT6hIO?s?wr<R>32QYBshmlXU
z`)>0v9qLi}e&4m?%P9yZ9KtcsT`ROEhCJ7@{vzvF*D8KAQBKuJY?A=iiPHBi|78iy
z6QJ}}>ntqQyx>CtSp-jdX$fsVyaJ%CMc=go9vx#X-|2$yo$w&hZ;)a*EogAML=r7B
z`^G8j{W^M#l49()(=Tml$1ThItTf&8^zGC@DY2?oH1L6JN(pz}!p;s=uEr3?lP-}g
z>g9;LT#Js(S9@o(@@b49!?xt)_%=f&9u)>Fug+i!gWn0#N(H)r56gshpdcULh%epL
z_1uqb($&0*EMHL|w0`8!*a-eqUpsbwADmA<8RVBKMk!o-8NewZPiU^<rr;N6+hzay
zhh6ZWewGOme|4k8rLxzUaix{-7Uui5y@Y{6O)k%7E6RM~gKasdCu7`07V;0<-7x_9
zaeSobKN_sIPhCFJO@Yrr{6ObHt$DDckAJ6~CVi6mQ_COLHR_0JO6+CA{4Ty(;Ihzd
z2NCjc&en+jO&J<X%V>*(b9~JFxo+n1cWrYZ@Fyk-o<OT@DV;$<m4{;yt1Js$?AL$z
zg6}@tfdnA-UY29O$LDRjQug=Mz?JyLbN=3_?pW|<+H;wt6YU@sR2h8Ka-BQl8+Q@P
z&bYI`;*SS<OKgh{q2g$IC^CQMK2{Wd08jN8KT;Mx7F67!l-z%lynrP`>J&R4%a^^9
z<)XCMsU{At*_YP?9Bhz>F}fLYwHvGI{y`#GOok1}8~RSc)pA_4-4D{`(w`OdX<{a4
ztI|Fw5mKvs$Hwo@?pfH|2fo<_*I70?Quy4zGg)OTT`FK-s)V=5;tz+6SE8~W#t7j@
zD<?qw%)S&Pzi>R#7|Nv2lb$u(U{xi+2JO;wht?E+7$;wh=-w5t4q|mE9Mv$a;bv3c
zHmb^HO%pInW^#?mZFHlTopMqUG#?k%f9vX9?-a*I09NKRU)UG~F{D0JXL(7^8L%-}
z-sj}4H-v1o{H$S6LaHt$XV@@LjqTn5?3%fsp4jfJ5w6>)6#^YIlCh~g{uYjyfuA7S
zPVQhU^90y0T^1RYp59<JuQd%t0;!6GPwEBo*coP~fak(Cb|9;-e|(x4d=HL=rP*jG
zs>Nd;P967a!TN6n+*#5(T-WqKhK!4*2ep*3*L9rR*}!a+AjHyhFd_1*)u)U-h}1vg
zISIH!#PDvJJV3`UM<J=Kl%X-5{fieX&x1%EFECw}i5_NH=&`r4yK1^hL$j6>zkVLX
zl|)qCFnjO$^*2lZIBroQbr&eaz?{|lsK7bt;Ufik@e=>q52R%m?74KFa{V01WV!NO
zSiDb)Fn=#fl}u@w&QgLe%XG;@w&*)kt+?uDF8AaPVO)vsj-qYmPDdTxWx5I<m$!#b
z&Yu3(m4S^5!a=2z5MzUyk1(!Siqz3EYQ|SF$9B3+O(D&hOzyuM?X|)-br#8Ex6y=a
ztyhUh>!zXUopyyh$13ub?}`-Aq!o}8bM}1SOiL~LNc;-EUOJQ65XPuZZN+2PA5Xnx
z)d+6E1hBcH^N4+}z!ejB`O)bg<%NE)1J_d-X}8bkl5N4;r6;d{mfzRsXy6(eljoBT
zm3n6@iIcAjm<7@mF6Gin&ywUuNe4)kM}G+YPIjY#+jnzWQg7lrt@<0b($B2SN<&@H
z&12f)koVOmV%hMCifrt$oKizA4f#b#vlAzEUlci%R~bs+N;olCc~R~clWRlzruy6o
zs+`sxRH#)LJW<S8xAy9O<EonC!(yn>qYf@1n0iVAO_D93OyKwLxGra`^AehPma#iu
zY=f<M+feK#M0H+j(h8VchcUO3el1zb63G^~rI{!fWd{s$!k5Gfevsn?pSv&R!1>TE
zWs7G(m>1vO9w@feO?YNnMHw1TzTrNXn{O8QEcq$qJIP$acdWA*9Mw4NgQ2~(V&5lq
z&Ysjao0XplQ)AC%q-Q3eIlI;Js!HhWsCPdlLgk=>WvP0_Zokx;UND%?j8Hyu)gpY?
z9yF%R%yapbp;6s?<&q1T^!%yiQfKEZZu;*EcNNzJYM(jPQ|sildQrm6Ii;ZZ`TWul
zjkd`Cw^58W4{>LbjF@`QPh@?9-^!(CpuolW4v)BLKSXWH#B#l!t0oqFHNFWr8XZoR
zkJ0Ap=o!d;Y<sn@CeQzFXd_6MwK<X&k63oUEpAP^@vE?KEeESbuGGF}ij<t(_OQZm
zUab5ORF!V#T%gWmWHD1t*LILi2XIxO<%x`6JDHr#I4pu)Tc@4KEgZ^t*6w8WTvLy|
z<J=pVR1<{nj1U(D*1?C}+?S`ySMj&q19^09lcY(bA$Aj9OY%b}dT#@cV#|<g!m6yn
z6DaK(GB8CobE<P`u~w#l>x{=&>0Q^PpA=g$GtXi?up2U!#7vRJT3Iu-k`^8%nY?3J
zG98ZsQu$Ixmetva8)DA5*c#4m;u@a@R!AGos|ja)`JMLddhUQl-09^`t}fBtNs?>7
zyMahNYpDK^Mj?yjy}gJ0s0qQ5`tKbM&gj6vbFJd`Bv5Nlnc3&byp`jdDbb6>a>oqm
z%zW^WMP;6V+e>XOTb!m{*l^LUyBaN(mY_yw(ck4O=M>KkEs9VcB4cji!l`r%2jRTl
z3Z^G?Ly2p}Ld#{nf?_40k*8gx$K<n3&*Egu%L&VI$R`BSsEdRwo0{W^n_U?iLg7&N
zD7edhA-CX(rs$o;A7L3XW`(v?NUYR$=pz=uvOerJ)3qCv0N1kf<H4Td!=>NyT>?YW
zpDKn}6qQI(f6AMWdKTLjCg)Z6<wpa^u@rVWY~I_gy!z-IAYoS7-sdLA)ZV+n2U21~
ziV+5Bv~5{r#k92oF}MolrQU4e%z-RI41pMt5?R-!&sUlYW<gGm+-$K3u>sxpsV21|
zhP%E|v(}*SqmKBv4gDaIgV#8hU~{!pkyLrU#4eC8@HmHK?XH5k`1Z`sof_IF-CE9~
zm>%03jYZ_bX`-}KWx)^@yj6M{pgqm1f1oP6OD|p|WgGAM1l3x`@Jr8JYz(B&ii2(`
zNp1@|&?u9AwYDDn?DG?b-8~s2*T~=}KH8_D^cA%oF=_Y-Yx3dr?$cQxNei%RNR*2!
zjCd*C@WidCZ{Tt_P%VYJikBUua07>)!3&WGn>Fv&REOPs(Pf_I#jJgidUZQro?R5-
z#`614J(QS{C|ivJ<#eJ>)Wph~O?Gl1Km<Kk_f9%sqYZLBQ6?li3zm7h<T$;o9wr<-
z%`m&NDABHX+v4nVzO3!e=~#O3POWj8m$NNmdFoTmhhOqShFPgJ-rPRA4?2+=h?ib7
zGB`AMwoyB$AL#e0-5$G+nZ+sq38FLyL6-$R?uJKe>o3YENK=cQGY>@8L5fRCSL72-
zf;5CDa^a&+eIGr?lv#T)se#So_(F2Z&y35(%6-TiUuILYq?|b6+rRTG>kV0wK}BsH
zi83a}P6TrQ*iQ`I$jd)5nob?R(Nv;$@C<s3LqUWNFul0!cYCe-%Ns}f($-n~+0A%I
zP}SJ|l%t%k?u5r?9gU8~Aa+UDEX%tdJ^a0RgNX*$=R5npW;I|@t)ZL?BO>iY)x*O4
zi_HqjAb^x4o5O~~B34u6`rO!7v1f3z$Ubq~QEZ}&ZtiUk76+YmqsXX&RliPTtKV?P
zUi`}ke@Miu=F-9Ccl-FQG7B7eKDvZil^=p@5ZvzX$|&NmLLnXzW6!da;~J`XvNrF<
z2He##KXErsqlS&@KxUsm`E$kXBzEFzJX5}4Ij!J+aHQ<%qiNFWalD8eiy|F@PL-Ez
z`ap&osu@i}bFfL2Gi{>c3Ml1Kb9E=b1T89_w4$PZw!*lE=(JTN;ctGb{^gt8Y#mDr
zqr6&^Fgbsl|D7u+Z=muWs}k3PU*TmHW6$S$v()g$OP2nDSS`B@I_`^H&zgk$U2Bb!
z*6)30!#)tU=9sU{2?Z(3kx(k^6sQ&^j=ZHqc6dHbR&clZT`G1V+OPb)o<#Ygb{)Tz
z%{U?gqTX<6uDO#!dQp>|NvTsSKBgb^ceCshR{3VSJ&|WMnXt{YtQRJgQF2yqo3}eE
zr<E?*faSRXN#dADVpgPK9N>zwR`z=KFWqM22k+NLDI7R4b7I}12$l4a_V>bV!Em_V
zw_mLbVa;MDv@A;*XHOPXH+<nN4nb$6hqkx%-LSd#9gmfWwih4E79;nvnreqfQsd*R
z@z>t}{JLrTpg7#A(H-Vr1y(Cb82CHTP0VYjW%9T8qMEsHybuOw4T*2Zx4SmKGtz!a
z<eRG{n9xG;g;lmHiA{3mG%tXgF{*vHm>(lnj=g1FTC8eN&e|cN6XG{TeHM_CQHr<n
z5}qown2(R8es-=^g(#MS$G6E)WIeHsCWRPGo(<9ONrtf;?*wuq8Mr6;0xQuST;Xx6
zJaF{}EuwLJ(6|~?uH)t|U-@Ita{BLY*^h$P&ufwgghl7-1fmpEwa?SW<=kRv;ODBr
z^HT{!ul-3-G7c{uq(1g)+8uw5Ig%72MQ7~(v<01Hb_H?CCJ%tO)%df0#{Me6h@L0m
z9$gq|V3Yg#ujS4>Sf2%|Te9>atMJiD5;ttE761m={l^$-w!6^T<P<#+L28CZem0K#
zH;Cv-=Fjnu4KYGbK~{ta2zV{kaq$oSBj4jn!KGm(K5{!LIoMW_>*vxPsZ*InZG(ZF
z+(yn1a;R&#W!y*VM{C`DZ}^-BTzNBqo)`Xj&q|1&U>ABg>;8CR)w#!RYH1=q%R78K
zD#1V;d9nkIrNqv9^NNU~i#ySAB@c*8k2RnKU1oM4e7e}K*KuM6cRiD#z-y}oP}@?%
zw=}<?G~6SG$UAwKONU9u$d}&KfZZY%&P5-?R)@Gb@^tyXIk0XV^u_{KTQ-Cfm``Gv
zkIQI%?*K)Q(I!I>c~`oLUs;SS**Ho^NK3CHG@cKI-+{@yWru~&2c;ubR~|w;f!TN`
z7slz4E1Q_2_^<Fgf*|5y^Y{i=m1Y3JPRo;>3A23Pa%YgD2q=fjqYu6(^qB4juA^7g
zn|wR}P@_f4%yd@#8byY_3ib+-UQbci=st1znd3XFo4JChj6N7DI{(v`+c}hlhk|^s
zCp{u90zK8G^ESCv&=fhz0U=JJ8gl(sb}S*PT9U#XtfRggW<jaVZLXaf{%I+ZVtvij
zH&`l>V6jB+-)c-&;P~0!kMjg>*X;cb(wz{YT~sAWhi<w|#}*|bZHAB1Ha=cYi1frW
zepN)>y-(mjxi)w5##|~~g`)7+X$}`l?+a<VV|IVq)IM;-$EBR9WP)wPVBP=J%v`xp
z05F0+n<uIO+k&t6RxZj!B4ATparYa*F=xvJl+6`vJm}+|i-)hy#U-5L=}8Pgw$^l2
zXmI@Tv}dasg%j;u73+IzV_~UtUGs(|p$g=>NDZE1p*ivdx}j#EsZb|F%`ur3C7bY!
z(dptuo8NjJQ_1~mH!EzI|NSbfx#_@(jJ?$2v6oZ__j6*VmHkne>zM5#Tf@Wd0pAY3
z0i92)D2J-V-IeLmmh3NS%v~p%9xlaMthdmOmDx9u53hd(dw%sP3K6UFV#`|bSL41G
z8~E#W*zl)-KPvclYw@|fv^C2fg~S8AUWK1sob~Fr77CT4uv@{WGCIg%G$cfOL(k*(
zHKJQk^|kIPSOI`E#*3-K3!(?0fh84fG5)!`e;Bn69Z*9VkgFUGrry)j^VhC<S2^(a
zRsjKH@opDCaPtwBs)$BDW+da*4=d<eTE+tvV1TSceKTmYv<Ufq6}~bAd!PhmYpx?w
zlOq2LV}+PznK7MhaY`HN+>MD+Y9Qub<z1PN=`qc^?|i+(mz-pG5!?YFCs5!djt>3!
zQ?t$k2Ch)$yh}8A1>pD0l}9W7aL)7m3w*n|B0=T7(e$qTeEjWG%y-mYl%Gb!nZr5z
zM7dazp(G0bV1LYjvMKV(6ZylN4yHIYac%xP=<J@QP8?Z=+3x*!c9TLIQj)*)T3-1s
zuvD94fD{0FYax5r?>uoYQoINf6I`^uZz_H83${@YE2INlh>ZF91+QF4Tr%_VC7bs9
zW%c7-xY@H7K4j6aRb*E3&{*C6miLvl9sL;FlH<=e@mC8w-%HtDm;}wl3j8;Y+~AW{
z%ws@A@21!EdJUh>uMX?3Us5DHXlzaR&QJ~{OOW`(_};Gy{^z0itu;OOz}|z~d0a$i
zL4irpdCR?JsY{)HI?d=?F!X3MIk~$T80|VKXWkV<+=Tq!+lB6iJX>kHv&?^RS3Ysq
zW*Fx?_S#?+$xh3NSW3vE+?j>(n03Y3!J3vltQ(+z=q7RPotaCX>p%Jj;wm!HcD(`y
zs;=Co2<N=iu=OkE;+LN|R)tWrrejR0KZdCy&F`4Mym$Y(b;n#Dx@VqhpLobz6t}-U
z0kPvb{$hjmM~=%iB_q$Ha*RAGyJ_&jZ@jlkHC}!2yuXhr$m_?C^6HI}q*%K#A3#Zc
zFrkh~U~0KpDPr_X7g#@RD&Mx3*%$KA+eK$J4}o#G4fwusCy0m?2b~HKG^BqpteFMV
zf9p*#RBGO7{sz7;7ry6uy3n;2)(1JU78&4PmiespQybB!JY<7pU4Aj26@LgI7zd<B
z>R1{G<ZQt|(D#PGMD|E8-H?0A6eD2qNc}e!mz*(sLzg{xeOwU4>pl2AwKH)NH_t}L
z`LaIV^kLBpuEpaHv8aSWYQ)#?P{qA!Mi!b5mL*}izzjvfg!vF36Rqp9C5hlmQGHck
z*zrmI^bRh(cQ=t3IUCDJH_u!24^%L^Ht<T7iVUg(eE%R77-_5ctvI7km&i2rI9`rP
z-rIaUd|fT+F$Zva!!#{}T1WFeT6wZb_{tF0e~r<eqIbo_Tal>055!(pydNt=`p<rG
zFjowgsBj;ct@y)}Nv=jmkee7YyJ#L$))#`c&xNI{D^FXHk%vykuJBGG!rX_~D%bHO
zvd^|`d?d^Y8HsBq%PY_b6a0J%2zg!@0Z5MIWH}3B#J35}73Gq?1HAj_`olUn@yH44
zD24>BTb8)FI)Sh9jZ3ZM5W5+?(kP<5bxv_^T?e`M(O`8782J!TN{-imi~Xpa1I5Rp
zFAKW~fu4v;nI(qb`6x?&BY@+WXL}**JE*WBwY>|(&dza*KAsEt^rj6g_a~S}=pgd0
z%>W>e3>)*3Tw7W}H~fH|!jB`Ft%upt%||n8U|Vks1|4$CVxxBJ;g_Y(04L}fCBR2B
zGNTOfNcFmiE3g9Qy(3D{lUbDsG2m*{Nm<|q!5H(49W?O*$_`v{%U8ewU;6)|=fd-2
z;#wQRXqtJvEHx_19np4Q9j^W)Bk+4}r|%RV@g14_{w!mdkPA~gvV1d#ZyLJqWVr6n
z_<$wed;QS~I;*6Wt+(I@!+N!vBe`A98<`8fEd6vG9-Hb*2kn%Y=IFdj%736g93=^X
zK<#Ws{j6B2tqOl;?U;9!n`PdObJ!G!=ujmH)0@cwaINv&bllUO-opEzTFwvT@uGI`
zD>Qjfk&bVFx8}=w_X|g+OOGhdKPtrEH$oL4Un{$hjlTH@s!jO?IHg#dVh*hWxieQt
zGym^{fw;Hx89a0EMAVGxgsqhBw6#Ky`}6kHM#%c+OZVuhuv^bRpEhmR9jObd#dy16
zM8(uSo!X>VxtS|uhF6X+_|!K<%`@Vd+>Z^(x1+SYn&P2HQc{jR2hM`P(w!15pd1R!
ztJDx|v!Lg51b1cscm67t5GjU@`ZfUc2A2jM9Lk^mgp*Ctv(<dS3lB($)D~lGUYNOw
zitLu`7{%GsBDAD?z&nq@lZkx{e6Xy%YM!`$S6tS_t8MTkA6L{O)~YWD<ZuS#2554|
z%7EfL$@=y-U4!hfwcwYTgcqMhtK4}>zy@Bw&8n^L#wXRzLb_Q!bp0>>D<Hg>lGwn0
zusWTJY(?oJB5zx+yJF6zPZ*OVxTk^HLq2{7IOQ9p>os~cF~8fr?PbyKpL!mkrqme$
z1pBo&((`gSqx1fOzABr`K)0w78)`C4;R5@(S|Jw=?JV~t03&6RsX#cUCL3VOJZOQQ
z@;3k|R6x%^khHM*>faLTBIHoX?)@$~QOd)x=S%v}X3KvZ(FPo4<(X?_u!~vM2A?LS
znx>Th1HEp5=yOt^yflrOu#*lJ3EPx)y&43JLj*>{BM#>=VBobDqT8)hUMb4byvxQw
z$E8SZ^{-GblH>hTzHF%nOxtvBCLiH^@_2v%aRrVonguL=Kx{zn?OxS&ZEya$r=k!{
zW<>NMzpC=dPvh<Ry0`;t3D*YWBt6r2vy;k<drmxb(}?#oOnTM__RaOKocs$$V#gS*
znE!BTj=A-WjbpMy9tdWInuG7JimXG$&yEMtq7QN@o&TP7I{C&yKZ9Ub@ABj83=!SA
z4ZK8&+kTZ^$@CQU`o9yUVOM_9ZMR3dhez=7CsGZr8|G}~SY=N^P+wMiq|ay@Wq%#r
z9B{-K)OnGDN#!``m8xv5xYyfio1wb>Oi4!s0#@PiuQbLuCvLXHE-09lc!;v?1-g!)
z04bpA;b)(Yf=2^ox?H^|mJj_3Wd`1v4{6ym<7<X}jT8Z#x@dXBhu>Ci4<~yt{HJXY
zRs!Yq8sc_iW^+>@0~-~0E0|^ep5MFE^g@}q_r+b;*k3lDz%UCAX|*2mvT=2}_GSNm
zfeBIoI%+Gth)Wr*%Jw^$k}4GGlN4#IztTm1u_MV@X-tAt&KR0H!IqWKT3r1aW&Mr6
z021k(cqH&x5<mfMN@-(<o}Ji{++I=#DMEgy1L_P!V)8!_;{Zg9v-Z)V`yyZ0N&D3G
zTLQOfL#(|hyXAyd%s8x&6lUlxGg#LQ`%A$HqK|(;ignm9&xjb=EJu@Hl7;myEj{bR
zG~72+iyO+_NZZgDdqK}117<`~px8ltj653f@oHH;>-ct?YsYBCaqr(E9jJwEmQVr$
z&?bVJZ-VXMd%D^Q-Kvf$Ap~;E??dlS5@BRa2w^GXM<WfP%Nf!^^@Ty{**At?#O!S|
z?(Kf-nzoE_h|2yd!VMP5N7Tza@lRU$`urIZofUDEEM~}h(<l@3&E@=ES1nv!u<#l4
z?(c{BNk1D0ua6v0k7sFRyAjC7G7#X*kWVTbf+$pX-=EnEdm?=G;)ZN4gG4*Q!ke-S
zJu8;}zROBe^;S{=W17h^6Q$`84G6e@%Oij*{DFob(U-S7t${vRvJ>k^nnBChDQ{Lb
zhgW=_0LoN5op8w6i4Do^%meA!7^@5G($(TyBaZ5e%nR(4>j*K*Zjaj;ltkH3?qWbn
z77b~eJl(rhz)A%8UAUGGtJThBo5>fzd?>Mo6)4WdePAc9E;}5Mu|kUnQUtW|CwO?Z
zxfMTmjFfJ9+*MO*()rrYMFIUbSTlQeHP{;pP$&$HIg_)+4FQZNmin$qAA0n(!s!>p
z#~%3FAQ9TKx~VMyoKgcBJ{B-yi$O%21(6RUP`xDOJ{A0%;`g)D0r;6amCx}$FHYQQ
zA2RPOMp8F5K@=(pLQ}BKi7z+H@vjkEv|PX>Z#o#yIa#&mQk0E~pxr*1m*uh~lO3po
z5RIUViX(<&wRQ*O-&e&1`<axr_!q0PSQbg%LX?-_@6`g5!QwM3&G|S0k;HJ+<h30@
zJ34B%gl;dwTE_&5h3HK7pCli}|0&iAa+z-iuak#bLwpPoy)nwJ+1aj#;sxDrbg_nw
z-a&!7da1=K*p@To8t=rdD#&p!1lUgFG<;slxC50i?Ku*<l)J2-kg4C&e~)vtklrr;
zq=&rg%h|1^DG~x`X3*)n3qoZS+pSc)IiU^mw1{$2!eVbD&nHllW@l&P_NX-2L4m|A
zphAucThl2*eN39IUyQxi)!Koi#*TPyT#?Jo^|Itz<6}d{?M`&W=S8HnTnE7!X>2X$
z<(SMH8}WKXxhSo-TVA@FnZLTADq(AaM-oXXdG9eT^X6msMZ4BW8Q|ECA@b}Opb?^Q
zIGSGer^No5k(;g=b3<UAO(XtdLCOa%*%sKv*Vuwy)x3r~-_~LsUYFpW2#iZFK4bV)
z+}skYKKDIW)?ZGGM<|!IiRMzg=)8tZ4DiBSC>nU5sVhHz9sIGU;#`iLr(?TC{3t8-
zS&^*YNXzN(f}%{K$?F0I=dyAdjTKoWEkB7<BfDc5;-`gkrOsRG>yRm|eLPmJbga&4
z9^jK(mB~l3sup6{#sKD{h_`Dhb*;Kxt%syYGjPy-m<k4tsk{<oL87W$Faww}G2YBZ
z$78@TALo9*N(&#?`|X<>cU6H(NZOp4l-{|jT)x-%hznwE3~x|;onZD^-2m+Qlcx!W
z%<<{UVES=9kRcUO`+WgO!ml7}{-_1g)StMgQS}J?)KBH;d-_l&c*xrMBsmISss;m(
z#sqvSd?5qL(@cPv_HzNefmc>tZ~xn@Pq)n3f5HmRWgax!=^=_&Ui=h>*&YEFWbU~+
z^0pK;3xI!15a+6xa~6iLvp0~%n{WP8v*QIE2x89-uyLy2OX40llfEj*_rcN>(Vdch
z{}04bNB$uA=wk=~oTeOMuFI!<x!wxt=UK8ReyP(uH&zUYRIFWaoLJ&lJZdBXa+RM@
z#4Zc&4N}dPzg8gyoJNc_W<K#Swv1g*_*biJFIhvZ+o3wl(V;_R@Q&z+qYcf2teLPY
zrH{O0)Kcm^Oe{f$II!=ItIJsp2@OsRQi73}R{iY4>iWzJN{g4w-*$w*(6Y<Hj|?Ao
zUhXWCqYB}%4W4vL<Zl=T62?6zQUv~iV1$1)ca+<+cchD4c+@v1S+E@Kv1oq#>L9qc
z1I`Rfn-DiM-K9HeyGLhaxxwUPf4;Taw{;+KzEl$_;=ij7CQ+uebpd5P<|GqZ6Qc;Q
z{Ysm=NdCofVT0|b^liO?m61nB$j1YntroRgM1#5R#TYhEl?LAC@LuaK>-5yx6WE=K
z#nA4K=(EqXAobEbv|tqM`3maA*>kDylQ`0&fqvgLr2D2vVL<f6-(;NI6)lmgpfLU&
zztcdjprfG!myz6=$tT|KacODSXdm!0X-m{k#M2l;As5qD=WY30OX%sY%diw@Em>Fx
z1ZmfLXLDYo?e6XbjFhYj-iBg!QU&k2268l`P4*O=J2|mRc4QS_oCYhi@sixBdR>yA
z(ycaZAzMpBKZ~n82%p&u<hdSxHD3H&Dg_aWt*4x`x(c1Ds$b1ZA8Imw{ryw(?%zXX
zs|c31H_4r63`}jgOi<pCL2XF7Z#F>`a{agICg?Tco!|WA*A@f(*VwFTZHK~wM*#Q2
zIEr&8na>Q|c2yB3F7G$?PN9j5NTLqNc@QV5Ay%9g*=mf0Z#Bl`mGDR_vVyl7!V}l3
z43x+fOk0!G*F|mkzQ6l}g(@$?XYLm|z4A5jcUNZlK0)XhHJkUN?4UIVRr5kud+y_;
zxH0puaj)zBgpg$~#CBsrJlaQNauw3$PXJI}AafaMlR1gzTsI!2gc^$dK{S{vt_b{X
zsC0f#lm=<n4qG6iO(rNk*)H(nI*w~UKgK@`0_%`@FythSDQ04sDloNk$7H&|&~oqI
z-O6j>u{0fXd5-pNES1u`D_Rn#;rdOut;@`O;f03s58m1RvDSFKx*X%<s!5~$oK`ag
z`0>ZQx+Wk#_9cJ!F-4}P+saa<cr9CuAGhMm?Bw`kz-EYB*wZ;Udq~gcXfuJJuH+<H
znE<-fugsE|jd}GmfKNwl6=+)1GY7AfiD%0pJ{!ps#RB}_)=apU3{m&{*sB%i^xyK(
z6;UvUJJuJxU@bQ}<!TU^@`>MCX*Ec1Y{I)*D={Y9ZN6#4lR4iy^7~#0>b4K=1@^ph
zu+P0F4@@m$Lu@e?t`NwQGuPXx16^I{S5@<^`f%5avhiZ~HbT6X|I%bAt8i$S!@4m~
z^-3Cp*$j^5(eNm<wRd#~c6q8A=yU>rMGhQ^SVdYQ)yI7~5f;FerG`gFw*JerGgPzk
zPUz*}xHAgpewcZduh4IzLW%LXF!8ROm{v%(PA!L0b3j=6oQaXuQ07=o$M9Bv#@mqv
z;!(<lyZh_{2=Lnp{odvgAcglX?qPbuimsXZ?-teIBVFdMRPd<q(SbJpr|eIzJBb&?
zHkOR_(kLA=El;!FC*u1)I;m~m`0CQ1GVnR#k2gq^-DtWZ<ro44+a#y&e#W5w%L{I1
z6SMII?A5(vss}BvC`<rl|G}$R#hpN5f-onQ7pQ*aTC(v&f9|~|dE*o;*piuXqSy@_
zM{;>^tlPn#t9QzDN=Tu+T5nB${2wUQXC{a4ZsjSiIkEHsAUfOkfrowmu+H@X=4!AN
z2=u@H$1MdL7N3bI*U+$o2A$s`3(T(?l^{oSS#`B|D}Ck*QzG5w<REX-+~)+Z9bU$9
z#d_Cy;*Cpe=G*U4=cM8^aba0nB=J_Tn)uAU|MKv&{;E1+fx<$C#k2It6T?Uzh3k5@
ztorRqLX$8?O^G~R57g6u@SE4V`Z@Ara6MG!>iL(C+pz}OY<)k3jTi@h5BQp8I9aij
z*c<FB>K8H?<ND627_1tK5fl1mHA*C#CS|u4NWh)x9&<M~y!bitUFqrz25ZcaOcC17
z)qQ-R`lc=?msaE|fybjvJLf~cgv~f=+=ldJ#dm9Q@=F;hLDg8JXTxIUYF!yEN&cO{
zvkQJv7)SMsynb9tT^KGwpDi_1cBbyCYTjq^Oat7(e9gJ?ed{9yZJFy(Nwi+;wR@fc
zFJ6yJzNzBP)O{ffZO@(Emu4M0*F&yy$Husq5FcKuXH}WtEUg7mr5|61zsCE-_~)O^
zgW_cb<wD(6pUVMC1h9-fr${&87)CAK$UKNFrzz;Ry$1N2(=0E1ii+wu+-52s`2a41
zFnZgU9xTjXlHLC70_8W;&3BTDFAOJnVk(_6=3FOD=icUg`ilubT^KRKSw1bT*doj2
zPXA2#$OvMWpbmbW1!`}a?kg3xRNQ#Pc}BC$mSbH;WIJ%admV+E%W9T(cZ}YV5_)O%
z&4*8oV&Qo%gi)C8a_6g|zPC+vz1WE^Z*?z|=k|m_dquvl55almTvr=eXR7o&eeE~;
z3it)7S6{KeD)zwRIzp|D6iGB5Ue>74rsf1s?CPgGM#4(CN6!GmsJn{vl=HgvzggxT
z5$_$?$<Oa93Xp+gEW4e=O418nxDcO`&A0D{X~Fr`h3Y%-O2=^8cxFrgyWLzb=I=cA
zUtf}2yeIKN<#{EuDRRs;S2-6pH^#oC!2GURqFvZ5J1PG*Javzn@Y9L-5=nkU0P|n9
zC*RLcZd5VPif!a@FcGLJBy)+lq3<%VNa)iJxCA^3`y6Fu0ji2m{`BZnf==Ck0B$jp
znQ7R#)IQDej`5}5s=lBRxx>-T3{pdm<6+M2q(pM2(`v0UYHy6esOS!P21G+F`G>r@
z=aFB1uY>!QBS%*&Dbn>V&ozgq<TR^hLyT@v=#8UznZ>uv&NB)c6x~iMw|48i8fPY1
zpOnumm8{;p%+k9bM{EynW_hAXxa#Kjrdr3m6BDnDniM#u3e!MXT0Dw94Hl?sc$<Zc
zyAC<~xX&fQAh~(94z~iG5Bw|tqhtS<a}MckFxGihia4d=U4_Dxj8f#A72&8oN(^iK
zvlVNG)b72kz!!Rhs74Q!mklNjmg+C9+8AqMXrCeMEbE>MAl<}D8b=hnq@mm;de&Hq
z7h__|A&ATU)`vTMRl{8awg+AmirwNT+C-mSpa$=LDTrLZ&iKxzK=+|+$mmpuXjmL*
zl_y#85Ft-_srVkIL4U2P+9RD?sVVg8IKXr>U#6X@i%nWOExw}D<Es^uaJP_IulOZO
zC#$hde51r=w+`Ino+pqrD)I{t00a=#QP-S{qFYVe^Z&vFGZ$M2r0O&jEqGF?nJe#$
zC$Qo-Y^x<R|AF+@Kl9-A<Y&~G^-aHVe+K<h(tegagJCc5HeO5pv>le_ap+wlJPsRO
z^;gs8|9gx4S}ptt#!<~f)Ucx(zvg;q`*;v`)2%R9`Cu6sS{gGgcnsKL@oaa+DmbYL
zaK{}WU6rnMF_&V7{B9FdfmkuFDvc2bmm*bPsN(Fvnd34V;A#Q7;UaU_JFZd?Y0C_2
z+lRZoH*V$$YJx@|H-LC4zge9D;bYrSI`^mtVm&k>czxzMbY_X4E(QWpI`ze_eY6hy
zCGZBDg1RR*ZQk$Z+P$VZ=+0Nzx2dgp<K=LAS@Im_VmBgpQF5(ElTXlxqGrWe(IzXi
zF?RnXnALKMqH_h32p)XI37!iS=jmr~<rI+O&IEIawn`;SFg!&16tl%tcq=Dn_B|CJ
zdrwIwAYsn2;;#PGq0gOG3p-4zi(5yv(Uw1*!!;_Gj}7e}DBYS*^tT%A9uw6@{FMa<
zV(>FweW7s1lfssFKwbf*O7QWI!^O>9jNQkeo=VbX*9n;NXLEv=L>hR43AW2|0ek)L
zUnMU?m5qF@GRS4DFeFn&XDe3+x?X!tpOc$1*)+bYpDpJ+P5HwWl87PijvsND4Q-Bk
zbvw`as70(q;nRW{xzDVv)hjL?iNF(mZPC)!Msfr1Yn5geh(T?Wk41X|^1$e3g?l4T
z@Z>Epy=WX5@BC;xRH~0BttalRJ{wftFIu}w9`XqBbe3xHZTQv&MQX+SZT#uBCK6?(
z$f1nh>p}7KvI&l2r@beKve!_7jVNRzrv(jRQ&ZCZl30tSlLW(MfknCzOQ$+;ZO*Kk
z%^6g&{^Ye&sz4j?4<tHEA7@KNDYE|(uCH<0qK&V5#!$GL`!#-`EJ=weGTuyzSk^TB
zr|aIU<n>Y?tGm2EML46H$vGU`%GjYts$jaDso2suSO*B|LS6pa#NRgZY3+n~rIJ&L
zWW75;VxjFIpGIAOKaJ8waGu7@s0ngN5`fy{ux<<Y3?|DTm-j$4wM8n8MPsHBBr6ov
z5`nD~6fuh(Vi`;EH%$QjDK|3%XK3sLRaI5)Y%rG&|B8vORhZ$hPDa`tcfHZEqzl(G
z_Ei?gyVIzOR>`cw=c@dRkKn;-=T@1Y7_C1_g6x=EMcckC^(XV=2uQ(<dvgQdO^Xb~
zjm7i?=QfVoxm<hl3V@4!us@H)hTt3+#YY@5@Z|p`$X(^Bc}jP_vKz0g;Z?+{@zVNQ
zw<rncNL{yQoGb7Y$Q#gNOJ_+5>Nmu#y|aJ*yfTp?7<aBtIEnWwy_ZOSF0lZ<luwqH
z`p+D*s%Wxjj5kqfORwpd%!^-<5q&t4|2RVXadn)lLt`!mh`*?%^g0iUv-3!YoK4{z
zQdZd3EfT)bVS+o!Fjtq?(+5L}y^riXm|wa0I8*1Za!L-b%W&#frF=+c2(qzn(*aw+
zAr4x#q#}cTd27js4XfR#hk`%|Y+Ez(v62?wlHd|wj&HI|TwAXV!;*JA=&qoVpG9VI
zVoy(+Vz%n&OBPSYUG=!4Xt8hQUXQ2zcDMt)Mb9BHIVxgzx>(oWZP4P|P>@cZ@i*|c
zetgpszHQjvTy^iF<XdTv1J^mOdLa5H;%Fx3)eB=~84u0#sM^FWccZQMoV9d9%7U0N
zqv-x68ybnzlPG@tn;%(;rd5I{DLM}ihW`0GJLA7<7a~U20D#clgK4P2zi@e0tgkp-
zg69^0N~i=z`_clEo2mfT#V`r8co16T7;Gw?k?gm~=&POn4OwdQt&S1z^-v8vYSZnS
zm$6xE!xhk|y)v5nisHF{&;CiKhvd)EW@`7y48xpntCdI0u~R{L-ZvtP7x(9CAFb$U
zq@%b31^1HzQm{DV7IF@g{}`kaw{&YG`phaql1t`$E=4ZGw8U8b)j&p%f-(AyQikHp
zLWrkf62754tpzNr6|TI4A$TFE62oeypwHn9s(|b=^D5J;Ps2BMrh@Gw?+9R3U8JaR
zS^)6fo?ef-Hqq_YmIgJdU*i1cc4LWjtAP@H(x-^LUeA-u$5tBrCEQGJSKE@>LMSk}
z6>_9yCcK8C7lX?*N8}uTN46!(7?~yxf0FE#f|0MZ?xKN6HC5(_7sJ4$cKWW-c>_6H
zMoKb15=wVN)elnIWAG<xgr+w9Np#1oN)Uu^8~Vk)oWy0K_TP^1O&eqX(Z+NX-npix
ziuzd%G;MAn2?>f`0KR1DRU(8PV|emL5wkx@+B1GKWH(j+$W!S4N%9!${cZ3?%p^1Y
z3StD-Lkv=x<QoFei<#oZ&VzRl<8*RocjS$Vd97If1HAUqqPP0eu`oj=Kxm-Dh5B1m
zO3DOwQ;WaKD!lH#{z461^GOU|5<7Srk1ie)K5QGGCgQ`KYY#b1nOqBCp26j8pQ?0?
z#7j32eUf@faXUAM`Yj9>LO$qiAdKtNo?4Z(k6A85@02UK7@bRX0aHrBqLu4gRqBg}
zV=N+!+s87H!)koht?NRDFWi(mA0Zv7T^r<BEGiB!jaK|AxWe8H;HCpZ8!Y5S$pbP;
zfY%*Z%4vF5mbVuD0OxMSzZTGmNhJ;g1DVF23A2k!U7g{6E|!_;_C?`fG7|KPR_$<z
z*spx#?Zm5S=-Dty|GqnI>rfccqa9`IBrNf$NvB=5bJYj1K^MwZ*JTe*Gj-3Ucn7Oo
zo#`-N(F;Z`!JZvoKawlJlZ4H5{4aDvaFWBp|NQbH?8#lJ!yXc?8@P+{RRZ)nflM!+
zFr-sK<Y1Ua#+Fv`kv0F1B!9}!sI8Bv6c+xY2UHw!<0J1>A=BHNLD4&d8=ssXqRZCD
zhVJ`;uM-4Myc>E>XkSa>iK6hCdoU@SfV$rSSmcX~X-v^6sMay*3pHzkh8GI|W&CIu
z4>C`rvwSWrwxC(EeO|v?i~prAE%!=a$;wR+UCzfsCOBe(m82kYtHwI`V)%EVByd}P
zTAUObf4GH~=q}R4E|Bdyy$bTD-mI)kXdaWQBmrik2c<@vzd9}Ii80fsnh(s3ukEd9
z7u~g)2ur-bH|ktymp`%523~YG^thVyG2?X&^Mqriy3le=z|HGrLM&i(?fH1xgM^!(
zL%R2+ZJH2ryCYdD1s*L=o`BBNiH1z22qgkBX?d@ra0zSUFFgxcN(5y~NGO}%_ySUs
z_qnk=u2;S*zD-=?F^1XppZrzx?tO5X2=MV*I51f%s<eoxrBSlgJQ36*RB%bJ|8`oT
zy<3Q5T`m0JKc$KcK?&o!I}GxNH_J0OsFroQ`+_i8^U|amKeyN)Qmh!se33LH)wFvv
zT}vcf;gJO?crDW+>+)>`$W7lYxj&~P9C1CYn@Y_Dk9h%bp%u5O*)yo;U2{7}39bo3
z+2-?K<nr?Gf)Z0Ev0INtU?=hde+(Vk+|}fmw}KX9xe4<wh&8uEbxT={YLSaZh<Sxd
z9*fed=23su42+K1+5^<JU#7)`XEJm=fub<%Pv8@3aE%3fp5XU4)P_bkf|$m9bDh`U
zaKWpUFAa690Q|-f@HmGnTIv%YynrsER(1-By~9Rtd^q=IXC`c)TsBQl?_c0Hsaos}
z0|5jP!AC;o#AVBsKAa^ygRr|$*c~4CV$u^KeusgVs4Pu)Fsw;NsuxElYRz=uQSk?t
zmjxt$N(A8mdcBm~To8<*@Gh+fv!6y@DDFRRkA#i5e+WoKT$a(m9DG~-HRHd4Z#2v!
ztkG1+xT60^W4A_3&E8qz)6NEVE4@m?`?wzg+FeJL7AYp!?Z@gV%urEw!?x8~!C^L$
z)gmdaIsP&wO2fB0B*ve?3{eewOIhLl)DmFD`Tr;B3!{2Z+1uxDC~DCVf*9n-_BT+S
z*54Vxi;Xb8D$3`VWoZWm9H^@LOn+MSIOnC3>YYv=Cr)jiPVfm<_ui3b(4U@sbgzbG
zM)F+d<9+APfXIKK`F!55Kq@3o&<v}G(8@~k=-lEZp>qAWA)znir+JZJw6jQTNLLH;
z-krk6cJWtD&B|=00<B__0<S;UJRR5lcCT+WNZZ#U^0{L>2mM=?%L;_qYEJR#gxg<W
zgEM7g8=`Nla`>7}4m-s!6XFkKD8>>7C<$YHN8%5ZMYi}_tIeS&Bk=!mbd^z2b!~KL
zB}M5*kW!Q`fuT#fOG$~5?jDd7fuUnWLSSg5Q&Lhor8}ghh8Skv@A~~>Ef#QxbI&<X
z?EUPGj&s?h55G#CCZ;-A6K-OwQ`Ow0nN#WX`89nOAPdO@K&jAcK#OLs6qgT565q^J
zae2m|=2uq-&;v@%AIwp}BB=;N>Rn{ObBh=vS-4oor6D&ASwj6c>?`ua(E|kk8xAEG
z=K%y;p(r`5J&?1;7-&3O=={;ySo%XPOomL!p;8$5R)qcR0@&3V!*!T#p~$2J;>EDL
z5{rEu5;?uDWPo;2+lhwwwenu@x7i`%CU8O{!<f(bqyZVO7*X<fA-r#pFu|RrfIzp*
z0=!yW>WF|O73)-(<kBxKl$IuW0jaaHrf8F?LxRQaMRu-l@q=Bd7tGS<I_?jV??dp?
z8l_B1&M65-ooxo1OVer9tSVU9eSAyvYW;0#YU>ODyAmN1s*0%vgP=8Ddc^z~<n<8M
zt7d~IQs&;Jm_8x*>>*bg44{raS7yGjJjzL({>(iN2M#K{=AlM=IjzPv5ackQE{hFZ
zKZ(t{L`u>x1>JE9P1`iV8kM9!jnd=L@0Ku_j}Ls)rPX$O`I2lMPi(%Q;66nB?ip)s
z6W|_e&ioB-jm5Dka7`a9uOCa<aj-1DKYXD<HTR2uca`~Cx6sT?Z}!xf2|x@8Wti>l
zm=E6HW%RK$fkK_Pz^AIZL}u1lk5&Z$VN^w_isRgH`{yv^YAA~_n=W|bm|#xLf}0=4
zF{=DqSYUpM6dv#$H7Z*lBT7Y8a4=*3KrR)>snIfkkWRs(-4jB;uNx67vbi_}UH1}-
z?euw#cg?F}`^FuBSu%#9-4Lag7@qG-41rH|kfG9-jh2A=^C(wG1lbL`$q=aqf{cT3
zrA9aI6repBqlzdPl;x8D-%Odt9TT+vNy4xC?o!rui_!6KvH6cn4g0Nty^Eh+O>HSX
z9H3l!3t?{B3J>%huvh_pr_7<MH;!=B@8-BETs5qSu}=O`U;5V4NPu#>-%R*>!d(0D
z%RI@ClDE3Ssue@q+$qSwVpo~onK;#C6ZX|cw<ibh!YEFGmTqGpbWI#%U~s~ovLm6<
z&3sB(TrrJ{<(0v-RD$jLa$Dpvqm*)sI0CP2Wd!bbM+a%>mwx-0CGfr{iaLJSQKSI9
zO98<}xsVIEzL@cqD(!G*fI4=$uR!?VapBCiwL0@p)M^fhCWWqmxkD_4u5)1}ad20*
z_HiO~)5c91n8>>-Q-tYBwvWOCoM{me9o=gs-8Wo$gvWI_q8TFuXu-ofU4O%3PSN8d
z^3I+jhZ9oprc*ehCY~s%pTuGa4Fa2ncL`&>mW%qM7x{zz%-J1qun)i`Zz3?xszWb+
zSTe(b9lsfqqM5+KjI|qSc?7?`Ks$zv^tu=Kx}$G-$ZD4aZP(sa13DK)pP6ibc-~Cl
z_Kbd7b^_=?)IiwPjrkg)<7frbSSZ`=?*%9Z{Y*znP*a1tT5TUkPtg|erXz9flms!m
z4;y2XySgYTwe<VsTo=b7dx(;mx`FiNg}v*n*F4$G6gFimln+|e1zvdvxycmr6A(yR
zCbXrR#J}a`)roF@mz1v(bscGj-jJcuTkbebzDf)BE1BDnxow~wpCJ2N-b9x1BHp0@
z-5P!TT6T0a6MS?bL$Qc_)EBbm=l%z{BjUeThTDwI*h)n$Hvg{Kh9b;j>2(PU-ft_Q
zh^Mhb+ZsK?@W1sUu>m7{0;+&8r1L`Qk}f031<(NZ=Ehqe3;FFk?)n@E*NUNWD&epr
zRA>IFE_UrJI?3om+4j%Ohk#zWAckVvFSGyf2->O$(yacaHB``FfG)<)t~M{d^*Vfi
zEnwg-DXV`=J*KQlmpEc8j>4M+5-96LYV3C`w@yd0jMx9Rykxsf4m<$0J!|#R6a9tt
z+NW5cMx4$=6g3))uc>?HrjC?B>AJK4d&%t8B=qizR!)2O*9?lfq*1N1FESbScI%!y
zj6d06qalI_vm+Y7)Y=;Xt;OSO7}UlE#4C>h;Tzlxo)!TUQoy6zP{o}1KriQ>6JUlE
z7$4KRBM$*$iI>ftHpdqn@7Xd8#fHa*e@6sq7Ix?(-aPQ(_oct!4Lya%(WjgA(ST@B
zwm#Sa$nO)A1KeYSo<yZ`cO+|BrW%vjB|M?EU{$#+Gx9-(@1j^dwB$bMa_Op66V>1(
zL)u4UCB%oZu8OR(SS{I@7xJ~CfkmQDZ1he5qp8cmlQ22VCCjK;iS457$eJVtZ;lM5
zR0>Qh8(XCJ&p>}T?(aqpHr5d=pXuXtX;S?<8*c&6W!OGTI2NA2Yvitfdb;@1$l<wd
zN1m|QvIv&rv694@fi=u$9j+Uyd<Mv?`SdI0IwuCe4Y6%}@;rU9VGynQ?`T}=gKt?o
zD%79Ngr)uh_+sQs<@=gCrk#J09<=u(Zc8FN6k1#VahFfvcN6b^YN3v2+vx)5#BTPQ
zBj)+AIkZKFyx|hK@!tC9S~}t#DI{uaFs)Bq1T}v^c{9y2pInTU-V$1>yI29TAfn0>
zyI+uh1S9I2Z4S%;%9KtL4Gm^0gZZeWNRRp+V=js+l_8_1zr~Cu-JbNM4h~?fboN#{
z?`9$tS^ooB_^4c}NtRI92Tunwfs0fK>)rs^VQ<HZ`@ug>hg;4@hkjiHD4+>=v2eDg
zQ^s!T?FrV;C3V@T6va^gzzR>wY@6TSg5#~S*LgrFvu}Tu0gz>>PCXp4S(tev{7*b%
z<vA`Ew&-oyVQR49tQOvI!(-9!`mvHo0*>VMX6O9GU<X?L`r)|?%Yh=k4Dk6aD^q!F
zX2A&oKh<?1hvMKGsdVZ@40egrm$oR*I=xtqqlVcvsZg=fh!oFH>r5!eRi}uHKpLb0
z;%UdAO818zGIJc2zku3O2F-DjVZ=PA_btE&aMZtQ&j#4|iImBY_`mpTY6YYWMuX3`
zM}h@)t);K^Y5?6B;9RO(5#INFh)Y6G%aBpUs(=@|NHeXuC6kN6RuQCoJ`O8S?00{-
zND#UktI$MkF<lztCl61}t^M81K(pTRnPHvGwEZK~Wsk^i@yacgg3mVB{{z)K(EK)%
z3|S8*5fUuEZ)~vmF3j5C)_Jx~*67HD9ll!|0mxdcdX?cHHfv2fB7DcB=d+L$BNW@F
zW`vSMVYgOI%%&i{=h=4mux|i2MAbm~K4cl($c>vp9AH+-oxBbmcKByE^<;zq^X~Kk
zQU+Y4pw<HZ(FTC)h&2ytj*}MwAnyM_4wl8iiy>ZE&x%hwv|g%{9&4sA4O;uu+<9sX
zPYK*NWrA1rMonws4}aS)zS9*GFMOT$hD~(z1Lu|ozv6HuLiKpH9`TW{us}t*SZxGa
zvwfPrp8HObpCGY4q&Mq`L{gb+-yS4=8e0Vv=tSpV0G?h)ys+uAJ-2(VrUSWiy4AJw
z`u#gNo##NBlQg1i6MI3Vt}!qTJXa`77gpPE?lYhU0v0lXY$0QrPDvSu!x#(Ur2fe1
zA!nU#<f8OjDbOWA1!_5Tr(yidEg$Iwbx_Lbf#c**Ykg+gEfRQ(+he>GhWQT!Y}Qb^
z3j}zZ9Uy<=mHb#&!9EAxLl;Ej8hUXG=`<WA5x%x<WLEkYeX1Y1$`5Oa-*f8^{2pm_
znWrtCS(5<pp+<{JwU2+H!+p)*lL<WWr=NW`n=<bmh+ONT1<N_h*#=om9=*Y}k_q))
z>`tzo15VbNkCI&cQN)!?DdUH7F#``RyS7?N<5-e4^Y;fSrWu=AMDn?jTe(xAERV`P
z(V2qBdX@F_SWZvPeb;0^axkA=d4_sMn%bw~lXCoETk{5qnXbO1F<C0T4oUM_aHR>k
z><SAe{Qy2f?s$GqCNtlrOM6;RuPyJk?(;NpSWo`>*TJ)pH2tL&`&U9@Otbk8H;aiT
zWyKzQ42E&7e$Beyw<9t8LK8I19e-RlO>IOTu7tF85>7NvT86!0*Qq&7Sc}x5I;oIb
zVwH}pQCI)$@wM<kDv(gl=8rc4vlh@EF%g-Dj{m^H;AuQk2k)fS{9hd?Gd5vvtuK&&
zz>N!kobAbS)1HyK-jnOf?)yI|$$8GPCV~YA>^u~cxTwPQ_T;WHEK}ZRb@{@O_|?6U
z575r&V|}oUZj}rqv@{^G<x`B<zN6Dc9)}9GkWEus_J`j8-pf_jb^1(z;n2%<F1Y8y
zZssBwF8Dq<SX`K#@Z?P>8NeW$D|$-ldi5I@6$@$_S_Qu9SW<hfd)m85)oCeb0_U-^
z6*Uv+{MnLsh!Y;53=%(g(Q4EHaf?2mbnXu>xp)PQdgHFy`(oKdeP9NzNBm)Eng*z+
ztgzZSInK#%^cY>}tMXz6=k+r|?g)jBJ&K;O;?FcSe@H-bBl|#=rFTh_Cv8Tc_q8Lc
zn8TjNOpN-#@v-=ik<4Qtra4UDsx>Bb38M$uN(kUhAG|+6B<mfQvUj2!+o}jD1<l9?
z8kAcNP)$C60ObzB{DfEhq9B6V8WUerb3OGD?bpomOH<{_ZoW7oh`9Eyex7?lnZvYZ
z@vT(a{F*F{_rxw;i-P3nMXlN{BaCbXL1`ak#WahebMcvsgr%p+E2LlU-b_`17iYNI
zIuQe2BT(F5{?X*uI)6g@=7I8zfuS?_rs|~TfM%xb&Uj$lZ|`8H*VGtco?H9xIx8M`
zy|s79BP@9~omSh}RG3qEr%PK2yKAFQCqQ*>$b1egBKe41y`h+X{vCgFEf?u-F!_x$
zo+;?Ab|yklL@9M8paG=1*K!-O@EC=MXzzjDLe1}Z<wB<LXQ#q&Iw{s)i6l0X+plI4
zzI+siZU;&XJpmhzlZ^|^D8G@;siO<%YG0H8;8p*y7h}y-DD_yF(Ow`dh>*(6$Gks7
z<46{9OZ_Xvk;T+E1zOMCWR{P7mm2EM|9!1KtNl~ah-FZ#ZSJQMby4+B=}IP}2}1Yy
zu-hva&~YChb92oA(t7)vBhAo&xveHb^qpxQpA0^<f!(!;>*GWy-Q6a@{(SnG$$9F&
ze-6*p2O+#NA<n;q@-0#9$j&=S-v4xXK_@*>Oj`4{`mldXg#g`nlR$@eM;PQwjk-V%
z4zw%qUUq+M6s(qNq)RkiNIKuw)M}l;Z)hyV=`H!qy4FT2ix}T&z7>7)Tlfp(4>!ii
zeRI?$WdPBaEPBX%g?!5^6+&nF0>L5w7ax`_^`*UG;vLOCmu$>aO{R~2UdOfI<UrE;
zYQK?juyacFfoylX=R=Tx_OhuYCoHshVJ~;uJt`oEqA|VxJ_k}u6w~fL)TdoiN)o|5
zRX7Hf1Y?c5_RH28d^Q-_5v_cdsTbE8*HxR^0ifpM;G*f*SHxs861q-uQI<tUs`Oee
zTow)3YWru!HNw=3I)%6gT20eW({@xTuzbal6vUaI_i(Nsy=pv3BagaaPUG#qmg2#-
z>Q}#JN7V>LS`wU^H%$vY$UVA_!{2M7E#}QG^KS{YpDGJ`-1KN!bl1`7bi=7odfQ!w
zT127*AH$E?qsXxhj0x8N=-)NKTqL`b?A9oG$CUbsA@BIDxbk-^nW14bek*k0NI>#~
zl95Ip|JLS2)T<l)kFQ6t8{J4(Jk_4g1l&>`%8+N&dEmb^lMan_Ih2M@o{$Fnmt(JK
zJLN8iC-7^cq!HBkn=8sC-`4e?J7#}*Xz@o-mn2U5Ei0^zkK*EkAJBberRnDm84v@D
zRFnXX-nao)Hac_JHiq47s!Ql_Wb@s>>?rBjirDv%Hps^ca94kkX{TYR%0Etmp{Std
zG@7LhQ>d2<Oc^z6O1~e%Bne>!Q_NW`2#wetP?Pohfzc4Fa5XtW_S1y0l4|q)x}@G=
zn08Mtu|4?k{^y?$xlsrGY%yC|9p$a{l~)nExIR<dn2T6of@DXWz8P6sVD5$}>sfPn
zFWw(`r(fG&V`ZIKM~a9L*c&P1kF{(`(i#aHXrd$>F_boba;ihSy%Glugj3@!N49)2
zIxFU#L-tc@x$)pSG80v&?8icr1W5WhX;0PdBGiup4Dx<>4ByOg!wqQkU=aQEca<qO
z6Zi!Rg6CkNou;I^3oMgi*6XWXm{jP&0#e9W@pC3Zh7jM5DVh@NBG%53dmJPxG%Z<N
zzIUjtmOnl^csR-)rICii_N-mC$azfMwdb2MQCQsce3ZFY8TrG=ZK+=gT{HWS^R^!=
z${2J@V)U^`#Mt2SytlEPrfx}E?gpC;py;4%uiNIbi{Tfq&inc$rpbM@R-asuYo}Vy
zbA}xn7~Xz%6Ig-#l58WYeFR?I41J+A9yis-y=gNrmuJ??+?^XVQxj8V=9>H#mN&*l
zMB!3VS!g)l{qXV--jmi>ZrRK>1K)pH;dI}_9+%FProInc;J4zJ?0UO3FP{<lKem0W
zvdJd}acx{c&p5AMLL_vDT#TUU5_@98!y1my3gc_#cKpGj6x@d;*_y@2X1}-HVQN-s
zG5wp0o{iTh@ijM0Uq~GLyt1*4eRn>*x09ckH0)xyq98TRi=T~V<gpMW8akZDF8Pv-
zr3NAAY!{O@t8ySpc=zM76lbrP5-UX<r$KOpWs9QM#JOcR<zWJZWue$M0HYsj9yTr1
z<3G5W`_Tw=RqSuPAB)dtTe_Q=P7;Tq<QU^qL8RSAX};FRK6P&Q;3C#);LGuo)SIxc
zQW=2AQ~Q`@(<#S4?AFOGlCoj<!a3BM2bDV6>U7gsD%eQz3@<7T%86@A#2T;$YLEF7
ziVb+`*$sG9<+}1-_SrnM(u;O(m|2*A@g_90TtuXCQh9qxvCj2x!fqAUQa9jr`p$)o
zoSP|<&OM<(My!iL-zBJKW;Tjm{xM(hp}?;13puQMh9~eXi3cYxjfq6Q75nzqA-a&)
z`;ryk?nho5I^Dq+@_b(x9u<7;G;LPeZZYnBQO;ntyVY7M3I7%RW-Nu-8{8J#-`t*j
zVm-3VbVZYEeMGyp+7vJNaHgfi{Ed6Mi*y5Y>=X4fPh-AcBc!WR2UC*CqN!zlupq<F
z^7Ijz{sR2ELLbGVZ*)~%{@VEWseEdc_D5F!xmVD#W^M>7W)nheJ-=4Dhgg@QC;M1=
z2v|Z47Ho31@jVEh!(A7Zug&1qgpc&G;F1jlCF2cP?jP4}P8x*2CWuMSjIEPx02wjl
zjp|11#ycm<%Tj070;8YW&e=mkGO&|s^oL6Lx`2~Pfx+?l9B*S2g2K3)Q0hZT!&_41
zvh>anjab0$mx!;UMgrocUz<esaQ^V?NX_<C%{Nv{J%{Q}Ui$06Y0o$<uG0G7Ewooe
z$V<zeiys;{Fh#|xcO*kz6a-nmYNE{YrQG%<@Ngj(;Ct@*v$Zr0{<?XZP}=Cw$eRd7
z6VRHSAjP#Uzia<6(CzHyuF^oB@YuVR^xIDx!6XhhuwJTj6$LhosWXEOeAC4nhwYIB
zQzjyh)G0-~P0=E)?$|^_1UaTvq}F))+BMN$>fn;j0X16Z$WZB&XS=Om`?!An+us$l
z4&dL4dR`PqTuMVA-SF<$C}p(Hp_$C1yr<bn?4}5(xGyaRHeccggmx|jz**%iZ47u$
zXo=aF4QmOHV0=h~JvLf-2e6J&U;6a4K7Gw<$Nx_M+j2EKFP~s9J@j+2nuzCWy<#2C
zAlsoX(K`v7eHq%14A<hNRHV-p%<ONpie4=Y0z7N`%Ia|_#J!2>DoBR1R(VfF$4C<E
z#F4lN>BUq(jqN*X?$C`nCL!=JqIgj9RCXdnzdz3BzHBd*AjGjEFQK!Dg$v*q+s9fF
z9bc9g;qmpWF!sISrucQI>m(JuVPwkN?ieY<pi66D!+tIjo0z7Plg4IyIV$MlnWXX{
zE>oOg#^nea5nHq4o?J+1^HTNpfe>*xvFri2k8R*g8_ianHbCK%t+qKy45=?trQJ4&
z|9Uo;SgaG)$4@DeyrRV2^KuWnVhe}))rJfkdvd2KsOst9f#ALhD<`AOox#U_^!C=&
z$6taOIA_4D>Vt4tyYj-P5Y3P@Fad!ZSk0rnW=qPyPyh#Oz|`Q=CrP^s=cR*?RR5ZR
z8DWqz(nIF8lGJ{(Y46WHi!S|s%QfF5b>0i|aGAJUr{9uT^)tNow3n3MhQ@sOuP;j$
zMY`xogSoK7>SZTDTvY2`L<0@)$i>CZ;i*f%l!Eea2tj$4I@2_FIy+%Y!huJ%HfWQf
z<5;}HB|l9^EQOa?TQD_`@81k2?FC6?2qvZ@Q<|_M`O^$MLJswMNV8{?EN^zz_2T1l
zeMgwCSo8^%AwFcL^-eUFr+ND$KVJ`Gm#yoqr0-o6O8GH=HKih?N55BVba<VjxheQb
zY!5qAb4}J1W*1$vv~Tc5D<bYZq~4r(Vds};f)t*us^Ie+_i@Od)joVVHngWn-F_`U
ztM;qTqBll#K7!J-<D78mm3mtSW{7J2SNR(o`O{H3p|1)+VIkHpHGX6GGV5EGqc`ot
z^^}AL!_DI&ODvamP<eVQ<pxVzKh|~}Lx^_)Q~Zvo{unqaQaxm%OJl^JBsZYJl}0kb
z=K{X+Rx<qS@U894qzN9&mD3d^MC92})?e2F@@&FfuRP-7srvL~u70u&&GW{DE8DE%
z(eBrPpwf~^z>^z;Yx$hrOzqO{@hzEHr`k)dpNA?`dh@Z>)-N88ks%x@j`Y&T08a_>
zLQT&La$Vf_>y3)S*(gGdl`$^tU#%sm`TS+RTf6%J1F7MhAJY%t1y0~CbDpV?&CJHI
zeA;Ffds>H6A|*y~<C4UDdVDuAz&MuwJ^^nll%P^C#Q?V3jb9hP-W>6*Mi&}eipbt*
z8s&%VCe6}59bOSS8UXXYw^%NZj}f(*F!)khxgK+x$i*ll9Oho3P#D8DZrKx2#jQfe
z`x*5!d|n@K;AyF<&&krl0<2xhzU$QJmyM^qn{ZA30eSb!o`-v4RhDX6;+w4`B##E^
zZ=yZ562%inUsjpO8W(g|<UTfAUS7DZD5F$n@vh`rRQlK5BGw6JfW3dY%i_#QS#OdJ
z6LGJHTMh{e{pwEe<ILfCtO1E(s_f@c-*&$<2=3J%^eEh|e5@Xg(`j1wgbop%KWYL?
zxGGdhvK9Xi#F1?#)VJY@(Ex4Zj6K(veacUgjVxt&?<Xg_na6N9oBFd@e19>MF+KTj
z0~|Y{_kMvAQIY$TID7`)J;~u(dlYZxu}yw#rgPg%GFiiJM54j&)tg%Dy!j&6Q<L5d
zWBgsZeihnsJN>b7l~V8og3oP-L&O06RAdz7xwAK~r}S4-!Dh{y=c9gHKNr@fvc(UZ
z?!#61g^C0P+r&$5j2>fQ1lzn`Y@|2^F=A?2TJSeItu&1gt4;g_Px6;wcM9efk@Cas
z9D^N(Q(_6Szw;^?;gPrns^frEx#;BSllu~Wn;+2!j#$(S6BpH6%ac2K;DZ@7MC0pU
zt+~)VC}Gl79=^3OZf1V>5riX|{MTo{-;0PI`^az%DnHGPq3=c;&s8vo5lkr0O+btD
zw{%fh9BYerKU}BzCvi^aiYW*-+Kn@sB0Z$WF@81@Qm%>hU{Jsw{Y#)L=-Ybkd!QFH
zfumlYC^{D0sMies$$dACqgk8@)PJv`{ka|L&~neKr=b*N88J&|!Y={`R3-qxX_hWp
ztoO}7JfeoewGFMW5GV|KnsqKn!5k3*3>)Wg*}Aqf_#uz=6sq%v{nY~P62~%o_2kFf
zsb~S^v83jblJ|-EJ-NO5n&&m$-URcypsjF8z}oeJ;fv*Hx8O)2c~*1(Yj)^AfY4``
z03AFq?MlJt^XE6Gbm{}eu&&KF;VH|zIjkX~4^6)<&foTR|7*o(TE6YwbnUm18GcH<
z$9!`!{Ufn?^HpD2amo`WYm%d5c$V{~Ua!w^82SJNO^;t(38~b?qGoBYLF(wlY#EFl
zdfz)Ne+H(ctp*yXu|0YAPV>ean5^x0Q@6=BOv`ui54M<wWz&VtT`~@8=&av=uYW}Y
z-}<ZeL0!z|*{W2kKG(9FEBJJk`<rIS&Q{8yifyHU2>z=F1BP9rqFkNbVDM^k=0mFy
zL0CBe73}NhL*a{hm}%92ura7v>e1N(JeQE5|5B^iG)K%?B2!1}`cq-LpYuh-F$TuL
zP5d>e-n>q!cmn=$^U64Lwz8A1n0IRgYt6pi>*om~xRkoGuMB1Vnb=cYXXrBqJN2iV
z49yF&dZio}nQm%HXmwV}{ds_fJIn!gqhm#C!k8dAM9^A<tEL%r*!i!EO!!#NGyMnj
z8}r}%tS@ZCKfvbJq0L|358YP5S}eJlXfvV1=7B@8=HydEu)atv3m5g5fF}S*vQ)x}
zhWT;{=;LaT{|Zly#^Akl;0Jbxr1O8EbyuKIRQPDGLd5?%Xv#(|^q_!aB+x}@pvUC}
z(ne}<RD6ohEu<%W)(AfhMABQG3#g3p0!{ezxu1XPJGtMz2kWa<+Y+#=MgOVq&!VnK
z0I#Tl;<O$&JzhpD7%(&eIAg$V`=q-n`<Q_InndnNzY=%3xD%I#Z09<=_5(f9U!<>K
zRXe457SifMqJ$A{Z_7S7FzNl^9UQnGrwsa@UX;DXR8O2h5&Mk8PzQ4+OwxC$CWkxb
zx6DKId3~e6%kXYiL7pvdoHGs{HDJXk+0WA=UTo~3y8AhU^Z6vrnW@j5s!Q8-Vf>P(
zyQ)<G7%pGZvVSTTJ8Xx``1siUz=Be>a&pP@r?vR_+Ncob%#F29J5Z?jo*UPZmi~*T
zGGm>Lv0K8J<W7Zt&ec;I0#)a6RH+I_%(+V?7;p6TXe5~^1iBpV&5!?Q;J%4V`F#xY
zzSc!z9PPh(ce|I4#1l48H$5@O02{?L3kjUQ+<1AW&j788P)7X3dg$%%qhJNUJe5N9
zs0=EB%Oo+pzYv4s*JPcyADp3I@&Q*;KWZ^|$J?@*lg9{6EilZhXrYCY(^!36Z!TMy
zPlt4A><*D!<EW`gH`eED43!bgf4KoWiK&$5(1A+e8VlP+IJ~51J4)~U57fZRXEL6B
zYsdp#6FQ-KnzW1a%<0J)0*9aFVTCOCSPwJgPVd579FCcu$;?b}si3&S(%i73P_G<a
zY5oV*ZL9wRPj^15pR?16nyH-rgU2@<K31WODgpO=jtqkvjNf@rUM^5Ui&PmN|5`h{
z4GAgH*N2Sk5kY-c|9t!|>vVj*-C=bwQ-zB}R)oGUP6Q^A`_pxHUfl=&0>t!(W0a;c
zv~oa<AH*xSUKsx@4S5Aa!#{^gC5!VSeR&T~;jRmEe_sIALRiCd6Il+jh3_<h!@%h*
zd@C_4E@9KzHb{1bz;&gtv^i>&K@F+I#D*9jJvl39(+Z2iPjewdxisg^|D*@a(fN&6
z<W6PANX}DNw7Lx-xDh9mV=pVE!+7ixXnsNq_F1^QyAegbJR;H4Hs+TkYU@Ur$+&Ey
zKH8(CiKZCY|3IqQ=%>Q&c44g+CS>nvH;YWj^`XT|_|T6MR@Pz77Pp50L-(XF7He=*
zO8X*5e|9&^DEF8seEhFs?!LNc40z{M8>|Anrz$)F<L~$W2QQ?Xi;Lj|blywQjw`-2
z)n(19)jlyH^w}?gxz-dijirC=n1^ly+f#o58jLPF`E20c4^W4iO;y<<aLENg8k~%O
z$^iIB_8OMpMR+I=Z~UIDV{sL@{n_gyQQ+2;X+YAJz7seiK)(H6WvZ^H@guC-NoeO1
zAE2gj@VyBHWSDom0(rJ);@<~M?wmT$1VoftB`8^SNJ+V)e=kGRj6ZyAcX7^uZL-BC
z*1%ubt)$Nyqu9OTsVJKuMt(?5XqrhnI@P_*IP6Fe4Jmjl8U59ix$GI=BY9Hr)_)-F
zdjJB8RC!Ur!rTCHB5R=}QfmuwhRB}8@(7=sG(jCL2Ep?TA*o$8$OoM*!1A5`yLgMC
zc0B|5bL(4k>IQZyLjeEjt4ZA-vKw6@2hbkMq!R~2f#u*RlK%-a4rC(`Elj(l<J?b-
zxg`!7Q6{%I&3txT3ZB`7&jEXlG|g|#2#BXs*k?^q(s*BiZw07B)eJ-ieI)}tz^JWz
zo^NIf%TQbAf$L>LJy*JH5`hu)zX+_2m;R#(2knw09S^sfaW)8fQ~qB1r?9z<V3<|$
z_c>q%!AutSZTq3Hf7ppO6+2yJHM7(v^R@nzNTrh!)qxANjgjA$rz^ZTY|WuKxKeI?
zc@Z1DfC$AecTGYa7F+_O2(1y%THZ{7mxUkB)by+Ydko8bN~Aa}JYeBc<raY#)gE2E
zaH@sSqa<5ONu#2UK=V8)<p;c*y`aayt2a%3+s1sAvCXV<0~i=_ymV`Iy4}x!V%i;+
z$O*%d4*GZ5vqau4$r^{qbgerFenXBHxKMYUb)b`Y9#IB$3NG`X#?u`9Eq#q+Ks&j7
z`p5v4ygbV+;P}O@wwWczm$AO{2Z*w!n|U?h1zy7!-IPcT5$P-Xs-oPhy8!gVvZH65
zUx=XP?W`sg(1G+EsUd&|@^I<+Gn0jGlitBMxb&2=L|L#;ENmq6)kEu?%`lJkxRv>S
zDB%n2wA3?n#VSf$SIClcwA4K1sHIR;Z2LeY3#p^=VVeQK3i`FG5uj>TurM+&Bvw(1
zxAJBL9wyyff}i(A(_0ki9`K0F<VylSXf6V7O*K}EUf{(S$T(eMPf|s`5djOQ9-oW@
zo2lZey~#bvH|Xc&qv`m*YGxkDD`1r&!Z@-{M=flc`zv2!9jhB{a;rHAtnUqNG>D+X
zIf%8e|3GvyR^SVw4(Rm-MhL>DW7(j-**`74t=A-1yi;GxoMz`C22)Ce83h;^jX`U+
z2mq$c-3;-Z>bYm*WJtZ#Fli9V0Ld_CU0)nIU1>Dm1iY?7ZVw65`I4)ZQ7r2<Wb`O7
zC!hZBkP5fY_SU{!3adk>9h&4<eMArQ8?gi?hLg}pm;KOnAQAVbcu%ya!v7mG7j*q+
zJgU8oX|O(T8F%H`)GLHCWiES@`n-njt8WNLW836a<s8nL+$DS9d6`YJ8T770*Y6;F
z(~smKaVnTUg|}U=8;GKSo858V=ta?>PHx@1n(HEJF$QDv-2V%W7#J}?i&jPNai=n^
z*nGbRjyo6XSiX=NuIX`%^E^Ovhpn*yK~4_52KnS%sr+|MWffIwItLJpzg|GQU^i2=
z{K>wz(tUOW`2in@Qo@jd&jwIlldg|&FwX$RsCrMdqhevO(Hj5`f@G31JK$i<gE0^b
zk;4$;yO1??xIu$9zR-N=6-Un8_Zj2GWQq4B*wk?CEL1QYWdoke7x+tt%(hve4mTtg
z$dMkhC2O-QG%hy4vCGLlfn!npm_Hk<m`7?m;sP-CgxVkUQ{ZqK97*KZ*Xb-3VeK%V
z-$JB6hI0GIKzFXSITyj027u6^zW8bD|LmaswE1-iAGC{_qd<@qEb`3{vpI!t(Cf11
zsS|W<Cv>SVf4;byTTYi{Cns$-9Dc$kw3EXJ-P$|`sLEY+#V^#LTMLQd<C&g@CqW4I
z&s?@_2){C)??fH$9=9h$VWvEPLw%N18v^0-0`FNs)T)iNm<vF4>)EPcyu^@nJdl@_
zd$w2hhN6=_ua56#?IOuEL~Jk@VQ9xtyxhFT8o+W8c(2)|o=xJ@)B8HNTuRV7@k=|3
zPCIt!pujvCG8f4BR1`v&zncy7Nks}5<pK<dFs<4tB6DJ(J!1^>_{U{XG*Y_dJ$ka{
zO$9P~LF(<ziB6-K=pq@=Pl~Q3%+`3}2VA)zsd%P9o86W=k|PJAM^vBg4vdu1v%q5N
zt6S|OM`h4YfF~I$&aK@->u_cWbv&OiG}b*rDo})$*Uq2Y%^0JKflrz^;N)-IKyZiO
zXBJq_(s@pon6d;!??VG<;}TAI`Lbv&u$c()1%JhCq4EEsQq)+ZB^`YU4ggKe6kxjE
zGuRKhPH@kKdYh-$a79aoLS#l2J}BOqa=(JOhvPgil=C~Vpct2)#`qm@9+0SfcL^|t
zkYSMS_xquJ2|Dqu-pRQ>#mB7#7|Elss}&6_nzN!6=4;@jUM9q8>Zzq96joD!&R=$q
z37r9zQ)v=HC!@KZSyn&t$LKgxWjU~pFqzAa03-XCoB4RsQi8_Bbd4FJO<?(YM)O4Q
zb4u761<K2n3;*0^z-juusuq{EtMg2hwlDA3#VEmn!8C*W#E=iAKv-Kb$+WQd2u=eX
zwgGm$+WxIk%jl}nCk-G4^%pJFqM74=|E(6hriW(Zdo~jw7CpU+o}0<v%b|i#Ew=^1
z3qKrDeeIR1++dT|ID~ecp&e9oLS1WC7+{+L@;}z4OIfc0w2*cmUEm3OKX51$T?w~@
z_BP66E~e85ncz<HXk<xHA?IF4yQ|C0gJaZi$XZyTfMK2M9f2u;>I8&;NJuvf4TQ%n
zEG6~41DEnRDi$?so6hY-&xJlSHYWM@T;WbwXi1IWZpnaYSc7W9erI}5x*uWo0C{E!
zUe_AMeoDl`5{y`eb~&0X81X_MF*Wej$xik2c^+y6+Tq$wt;k$K@Z~r)S|qAg*Isg6
ztV=R#DoJNDZx}unms>Y8eRWT)d#fiB@<#T=G?XiALznv47nG}5wC1GwZu6|}fW(x)
z^>NUlHlP*3Wv`XFvREbcS{u(>B!bi><`NX^j^bi|VZ?c$q0aFlBv@`93t;07y969K
z!esDR<6<{yGO?V+ZKm5DDr?n5haIvQ1x+ena9_K|T(WqY8j8+U{u~l&VGOF}rZ7qt
z{+whPpVN~+jCJnlc%oWqH0vbWv$%ZLFK6gHd-da7Ag0PFCtnQlRNx|#^N25e9!H(b
zd-|xFtQ>A3v7GJi>lBh&Vi3md=p%DQ(Mw--=kIfKHLeD|v++Vnz+4>VaDHnxOK0r~
z?V8B+I7WoeH?Wc)w`#i!G0SkB@0mYwr$bFgJQ4WX>SP%})m6+}vEese8GTO#95@+b
zJ#O&%BlSyQbdM2Ly_f-3%a$*}Npghn&o?j`=H;G`bpx_5F9opMjCMN`(Rh5%pEMn3
zfS`4TG!PopoD5p)M)w%VproB;kpS3cgiXf5c3tIids%eutO^!h!Z|<`Jw5ghyip3U
z{wARIALxPtMB0oUN<CONCfOEsHy!!4)1pq}ra=^Z^+X(biEtraQYwB<2TC>R)eITn
z+)``gUL8p~)vkfLjzZmUrwMz9!@d2KQ2?tmstza2{xQr`)6A^^fAPtc@MHN8O{Z_A
zq3x~NmJMv!uX6_{o*IVQV5E+J|AD;mcKF0L7{^rXZ4mgufQ8=dlh(D05RsYNPYLth
zTytI828zb`pDU#Ux)F45KDRMYMybeN1r(7qdy@|!C^a|AUVjmal_^IQ=4z&P$+N#$
z>iGS5Z#Ai?5oCwfl;S357h5Rm&pqYKTN<P%vU%WI`8>v|t)9@clo>Gz@D9BpKN<_f
zEUv{c2A0Y`VpNTmf&W4{Tygcps*!1@PTf{%b0V&2_9r=daFj%<4m!RRm@3Q_*yW!-
zLZ)b%#NNiX+uW#g2z0GGh;5&BBfCq6<*z%&y|lIrvrYmny1?sCGpAJ^u9PW&A93Tw
z$jB)<y#(5-KHUjISz`Oi+;mn=UoFXyQ9L5ea^iDZ8;zNd&$0dkebV7XZ;VQ5{LJyH
zCO}=8s#a!N9@M4)00?bm6xNIjnQKPwjtt%Fmjn0BOJwB$Z(qNa6C+g_{qH`m)DIdK
zj2rio54=L8*Q|W~9lf-hM<N{i*Xxbq_;oyIhEMn|eAXE7rTLdRt>3u;eqjErfG9+W
zSKOWdGo@UwUSA;PG6hZGZxes{><tJAyxRtPzuPjtEOup4^<v-!K^rMGOa0i1uvRHb
zOhuj^w(i>643K5>-hj`kfS~WCO@lu;IYIVQm`}jD$FT+oO97#Dbv=ayv+ULqk=Ru~
zeeLGspQYQmh~d>4OqiE!X*Dv#fM<T)JJ11=)cOXcBj10lPAs25VH_X!{lQWDACI_)
ziNY{rBu?|@quaaZezRz-&17F?5BZ%yJ)B%<&G+HjjhYEkM4sdE^18A4-WvRO<~x24
z?r-|XY5hFeIRPI>p%0Mz8myEB{Oh?#3-pXNTI}RWMWMkYuLA)wio}m)Xo;!Y>aAC0
zaRISD*!ZfMk6TRxNFfe==dfD>8SuLPC^G!yzyrg`{p|yvfa~^n5jLk!=X!8D(9nX%
z>uHAswOK;&eoS{Qy1Zn#i<=Iawj9_-*#w5pbTwPfEEO!_T_ZlfSqBLGU8nW4!AJq<
zFn!}daD~Iud9s_o&93f%B|^{YMK<IS#spK(+djn7SjxPPr@$7MI9&8g%Y|R|La;xn
zZ5ei!XFG~p{@aiZsMM8d*+RavJ^AB^J!tf>VCy%FZuAeWmZE$MPqi+Vrbd#nQt<&x
zN5tY_(`cX%`V(!R@k%Lql9f~OO3AA-(KmszSAfitp-8LW>!78^`_Wem^&4T0dzf2}
zV(?<ttzsG3bt!H@7F+O6ZLSO#_NzMMuWgktjRR9ukUrpU#IJ!hU>E8B2SVTvLwtG)
z-sk4ev6`a=@Bh%!)J6N!*<k(opft7n!L1xWozmC)1>bX_`%b8tHrchix?K$USLaR%
z(80*X8|qVCDO3Pqk&q@$b7RvowB2|@Bs)T~HG8b3U$E~(pSz7jIMM5^xSR$ymZT~+
z_eOd(*Dv1FBaJ!<tM#ZhGsn7f6~W*5b?kN1-)vA>!%Pc86LcExZeKZ@7<_lXeON%P
zD(A}Zd>pVV#z^kjA@%ML%opRBk21zv32oEkkJ>r{uPmJO-kp)XRnmM70{4{nmuS)H
zeXp}F#Dl$+q6obD)+PL%l{dWP4KT!_EA$t9|6^GM+SX@mluKjw0M@9eMt8`3w(rzw
zm`5mW`(VXI>pSigZKVo}ve)kS+l)*GnZm#++V5nlyhdw)wavu_3p9UObVi$yALQu4
za98<OaHM#*qfu{P<3kqz=#dT6$Hds}(YW|m7ea+^1^xpKN~r=a)xXs>N%LBe2-;8P
zUzPMuB((WATw~9y9=ZAy$6P%oyAuMT=qiyhHLzn<%>aO9;Jf%y)Z83A_Ze?kTC=q6
zWa;~s?gMXK@bBJ^+p>4>GZ_F2wwdWBlM+0uR-bzfD(q>qgDm!gM`8P6>gTQmtFzj{
z{5sr?&zl#_`I(QBly1Up9reKX1VTU!A}@}*Yn(ie{Zu&<)@kzoPFhfH)wY5kA%^RF
zeD#grlcvYf_?lO(OBIstbM)rmu?qcf_<Ylk+9U%Tqoj)&#B)Zx!xH9&GlV#($@J^9
zS-ISoiw}TCzz5(8Q?W}M%V69eQo@-q3|f4f`g}xJv}DDwvS`NQa~5`-m)=w^?~keV
zhl%9Bg;@CEi@m{1<d;G}Njf~yUvtoS5Y=Ke&Bxw`z#l7;xeM+IYdw(;rpk=Xu`b7)
z3}PJsMoe{$BJ(&Wn%t%{_&nY;1I)g0Gx#)OoI2JLIN92G)z@L*t-1MNGvKpm1b!L3
z8*q{8-q*hM@mpN{4C{v@7XuljR=US${waJ)uC6-osth!8ldLRd)5lCITbRZld*um!
z2_LY4rySk+(-^xvl!{G~A*B|jR~0QIC_Pjc<#eID$2s6ptgrRm?J*L=?0}EvhOfPR
zS$r4kv2>~geu|#LAfJ!Z|7adAkoxsGKKKUQ$##*z^bAGWTYrt0`~#-=?;H9`x-VR$
z%agekXESjEmKj$E;By@7FAaZzv}|-;+IYxPTpsKzhK{@$R=|B0-#z}eYbqGQ!RC^|
z7W{;H?0ZJXvVW7Q$B>`$eQ-B(4QK+7OhCqO>dRtI^1G8BNBc9jd&o@k;OC4PoxtS!
z@di16%*^4R&76;{&r9muZNryhE$Sd^KS^5AN)UN>rvlzmDuDDSOxxOUh|C&f8lV6X
z1v~u*qHIl=r`WBT9V2?zlX*!=-dcC`TQ~6Kfl~UokMwZR9y)R6NWjl>hV6@2(^-A+
z3}ZtL!z5!qf?x*6nEP42XZ*`!^tRTSFps%hbbzC7uv)CVgpeYqxULjk;p0fuEzfJi
z7Xg)%EFAEzfVwbKZg0U7=a}M&3l*Y$a7I*|&Ecpj5_PMe54*N$-YgaFQewEj83T2d
zQ#HBrSfypmPrAoS?z$!ktY(#Np-lh2xJbAyF(1C5S!QJf7%i($Esq$k2E-7VPmWvO
z-yW;w+)t|umhLi-Oy_re@=sS42*f)*)~lEtzQ7NHHq2#GjCe4w<D3=Pi14*Yxf?O$
z?-o3hxxCIJ6nOD#&0FSh?wf$Qeayg~=`(BS<`A0aA=NV*)K;$SVptMqCbdA-Vh%rp
z^RB3@wvZW&8n4afX*$g>24HY5C|tLz^|wwA4XB`9=9+vs?HyHqG8TAMG7zp%pGfjc
zo8>z1p&;>_7%O%_wGUasAu1R&?|GzwjrsK?x;ZY_#whvhov_1=uEeyQ;K%W}2bxE|
zm9GPbGo6FJKhsOd(~V}ZPj>t@AejUUu+$T1@!?=dS)QI#CE!Ua?li5oS?zTrXb^Wg
z_iVmc{7hUpp(;wcR5w2t^>qVfA~4k>cp_F-_iW}RAuf)Te>pz#`1sd*qwJHX9~IiC
zoSeTvZq)%bzNfWCQ{U`JdbYw0NA&ou5h6A#&4v8x<<UtRbdhmy%1ta$`7&2!s==;U
zy{G9&^WQ3qek}x^$%QrqMS8hEV`RCp1;Qo+;6=J}J4#wh&K#EHxBGDhsm3bH^ln#W
zhX{F>|3GIa)KZ>?X%y%Q>5mO@RkpKHnX|C9MQ)6)O;pjtW2Lc$vgUBeclz2ua#^dK
z`VG44t;ICwMXlC2<r3N=_j!i_h_>qCtu8t(gDqt3Z?PiwcO%ZjQR+vRQL5E72(1R=
z3{_+O`rqU!36DHHbwEEOeawNR=c)ug&AzF0XO~_;$veTMyv@BK0!s^lL@YL2Bpd3T
zs3IOzQ2;7*V0B$uXZ@Pp!o@JT+yN<`WcpMFTOir3d&j)KH``2+NDcNLC@msm1}x{Z
zJSs0(gf9JQ&OkaR0n?P@Hcb<GQGe9BsFvaqz-pZmW=mZozhd)ztF#QyJiD<LquuDk
zaE(aH{2DR0IpPRu3l<P`@VnHI=@28gh>!1LdIozu?P@`OpY?&!;`_?d5B?z`y~!GG
zx@#>0&_INir}6LKWzCB?qT=0M6~SLe+l%7cmESpjO~+}_qDR38?EUFIhi(iZZ-m-{
znunpSJUt7L$DO=%pa2ie=MFl-F=?7R(HRc3PB@3^)Z_@!X6c0zdZizWYx`UbSL>T!
zKNM=x_>YNUSa{H>lZ5W?8)j1fmc@1C&1QP*k&RQB+`(16VmdBbZDwNYh5qQ<k8VvD
zY1Nfj2$5@icX{=4Q%P6VX?t#lM{c7uz4}4MgXKVjzR2bKuZM_if1P+$&KewrBM$<K
z4O*PEQRDMxj1Th6-sF61<bUo&`^V8luzS=P_1fh&6Xy^2CX>uE5d5%HWO^TC35RWR
z6~#W9Jncet{Wd_lt@TYeSG4OXze!`=y;V6*bX0wdwL4y^()rw;Xqhh44{@xPB9u+~
zrTM-*ABsCK${RnBjISshL}ZhaDBZSnYb02hv%7rMXF+ShWBDUeON<fEIJ)n5f-E;1
z4thE9IfVJa{zS87tX8`POrhp;at!qQ9LzfUm^Oth##=X{Hz|&R_?iOdUHJ|?vMvYx
z;X&e3^%YXypu|5xr~?VzYN{?+U}u`lUYLZ-cNmfegg0mFr6|OcZiT^|ek)8Uh3DUw
zw%HJX7-k(lwWKg*8o0q|PcL|lVOsjk{<7nyQ@@Z5Xvb!wE^c@sheG<~OTI1)r8k=*
z4o$H_V%p+lBSFwrxtg=~8SQx0$@4eKa<MVpVN#CWpgZr)VkXTg1r}!W>DoMxtWn&=
zvX5(iQ;7u~%9UzGZXvQMt6z7w(S3L1>b5MT%NQa11lhe+#6?E^2boN)+!s&@TsbX7
zFt_YDJ&$X>O%k2`G)2@-7%DV`B1%aB8ag5GyeZ&ly3-no<|aPp8tl5~CUzY666&c?
zRwLQ2{AoKy%Xs(PF7#3V-nXgBx+e2&l)mDw&F?S`Uha3r7kwagqzkG4y<?7k$pf6+
zO1XDBW4`utSsmI^?eG*@wmw0q@0l?3f_Z}3_jcj0H$stL7^Xld!Gx-)jG^v<Om1<h
zKB1IspF3S_`3F+QfG17Y1JqAgK+MUJ0|=17VHX*c_$B=jZY3w42<w5XGL}BH>*ITN
z&boCSuVNXo$IGdiIwJCV$}((FC_?NfX#47_;C)HILFZ|iT|dk8ENDFz|25URl{Q*X
zt@I&_m(JohhqDQ5IIFdUbyy1JC*%06JGh6$z&*~sc1#T0&U(P~oQR}-1OJm3gKIs~
zsYM02L7#5)nM}aH3dxgZ&SW0r$3d~Lj;F#UkcuT|up(C6lz!=YkWlD-H<Sl9I<9jA
z|8VsOBJj`!D^H<P1RoF!v6JrnR7idT@FgwDv!`hK6Zbko>iwG!;qLKTvMPFUbRaE0
zCK+%%7kl>JS-#%%RVk&CxFj5;XeXt?WlbUm>bTs@kCH8=rL|TjfQt&hrjcBqZv4(b
zXDQ=rmx?U~al-1KE9}<_uzpJT21@xF;Kk|sZ5U5`9ywr(z}Sj~`agY~jmx&7$Ql}O
z4ZznsFJ!|#13nG=mK&u_a-g2tc7h@+`GZETcieG>jNdBot|>N~FZ15Ja@GD-(%>r$
z%}vEnx<dBuxqr26Wlv$_DsvK7UR{<dK(wGe#pgajdn|fLR)$zBk1wVqE&De!S}v6S
zyH(-@2@nyGdo1XiC0JG`lbIp1k{D-Rrzz)Ss9=174VYJGiH}kFqLQ&afKZDo={l01
zHfkmZ5a(4u_WF)b7!JiGWC^WtN-c)+n=VJ9iubkKKUdQz>zRGS3jZzrE!>4nV=bOf
z{1dM$+wP;0dCZmla$iLUDWQEH+1t_vIX;6<9Gx#Tfv@)TY>foP2&TMg*Mjo+uj~rn
zKHVl3>Av|L<Td{ZRTdmC?sb!DV;!PTxQ8nQ2;%DK^%aye!`~Au8+pC3S`>V2KSKzA
zPGeF%F#x-Ez)7v2q;?(NNe)PXFEmapVi&VS9pSlr`S8ITSLu;A4GkizYlFN4kx1Fg
z@eEZMs85}r({H=PLNg>)E+5$RxB6~|4nRUa1&ub`m^OdPc`v@g#&lakCUiTWwaxBZ
zQfHdT_<Fkge!uWcg$_<G&{S#mIY~b;+;D4%QM}Un4KML#sLUVf)YxbojzR-D@xeQ~
znGu)cVquqO&c$)Fx^4kp#RJc&yZ7(QLJuTGGq15n=4lS!@<b2alD@W$GkU(!gueWe
z)_Tc!SY|lJ*ZI|b_9i}0GU3KzEY8Xk)me4m@zT8oYrIn3GH&2&c}`lAt-I35!V(i$
zqPFyL{Fsi+Rf&3sDo+%j)Pu5P@8@T`O3Em1nPDxUXu?AC2;80kAiZ3b`{5-;(K4yz
z&l_#lo7+(IKF)-;$aW~ly_Tu$uJ4o3z-bdZHjJ6gv=HHTGYt*zKszffBbZ^vj&ooo
zWgm{~L`v&^m1ms<JHdGUj3Y-?OD$#`9pQ@%z&thh<2<aH<3VhaRy7^VxoTK3%vUwR
zpkfLhC5}jC#G*V+_lkh~9}*VwqBy{fH{@gfhX_uZl)q{zJN?9Q!J+v-+KbW987!Gc
zSppu9JpgS!KG$}}F6o<M!B=uGjRU;KceG?9aR#%=0`U3YQrO#OUfRgAZ#mgjRN%b+
z0q6h=`@Ht^3E!zw1nI_#IK7vfDMFG;ehb!6yO7w?6^m{&@Z4jPGqa!B*2Z=9*vdfh
zF`w!%&f8(R@Q%GEg($u>!#C4j%`E-YHLT@AP`epMd?6s7h<T{)D7I^IcGSS-aF*Mk
z9QMb-=CPZd&$YoQ$bkG4J<+p;(=O~nDooP58l*M2QjI+nr_pTWuEPGFyE`#ybO{A_
zQh?gB(ZsGp+c_N9Y!ew$w^r44O9^NjTMu;wlzeh)RrV(T(9$-E4Wtn<`yyx>bFT~`
zukUAVdud1-Rme)ExW6qY3R<})gX0Ka;1cGF7%y^8*kw!W^&&T*%jHkGsl)6Yz=Q$H
z{z<4dVT-ZQ8uO>s<Jn}W&nmJyFzKzOhem|&$hN{6rS%Je5vcngNtb{JZWjWyC-64+
z=0V|e+C8)|3}s+H)a)WX%X+;?a9OPQ{;9}bj?%TuW$1U3>Lj3%KO*%8-r88*FMEE?
ztP2?vdG)=)DD$Bh&)W4I7dCBy;rL0x^FJDf<m-UtLW4zVX?(W%u8<98GH+oi6zT~Y
zmz==G=PhP8$-7z@<*Q~sKXbh#(z~TPQ0lEEm~Q7_wYYV5;$ISql41Xcf|mf^$+AHg
z$nx-nU*Y#W)|1ufmD$dXQBGXw_xnhY%u$}F@c%fv>bNHRw>!E)q;m*JgCLEJfl7BH
zA>G~02oa@5OAqM~q#FSdkVZzgbW8X4d++D{n-62$_cyNVoO7Ksx6VW3kX5gKHz8XL
zG@$kC9yrsRsQyyg>3D{!=6fE1j%Q&#PeNQ7+Jje<rsD_!w6&PUXB2Q)@#=rF)PIJ;
zQBLCpmf{W83P7K}4`*@Kcfa!myixyUYc^~$xE|9mmzJEjZV3Enq!mjEDTmKg2(mr<
zf)1Gs<;D^mcXRdJW81%<%8-|qcQXp=!rh?)cZw;6jy;=q&!Gd0E=&6^7G^$g(QRFQ
zD!WUhbn#P?#=t2wn!Hm7oDu*akM%$(00~8I$uSaZ<q0g><RkM&aLft{-NeU5=fMaz
z1@XL!>+mu7pc=E;t%4g@#i#YA&z<d7?pxf_SCO1lh|p|BXpwWSXZ~en>Udi$o?B3|
zmQmsAyJh?c_AAk^Bx$uA^z%diTJ;FLuD|LS*$_+K8H!T2=Pfl`sTN9EGjV?kN&W4G
zSRjLkUD5N}gXjD5M}HQ@USEu&j>OgQDrdIam)lGvKTALEx^Wi|(Xt`j>E#PiCh%>g
zy7!x`eHw6N31BX=%nwIh@pI>Ik-8jDKa9xMh>uLCrqert2cqfYDB5@WjbI*j*=_<R
zQB*0!{y`4efaD;f-7WNu4jo%)6KvK=>@Yt^UdY(WW9~w{eE?JzT6p397-CcdYfII5
zSG*L{73cqeA5egc5b^!dx%&s_#llKB$Bh<LVeq`PHa!!VTpqUGqmnE)Uh@VJqBmNc
zll&|kf?i}<LCco{j;lHmH$bpNj;NMVjBB^cbk1ePM+AK?Z4+JS2#BkentFlO+wEHs
zU{h~P-m6MW)?lIUi`+0hs_$gpc@3>rXR2AYTYQt4vullVoX3k}*I%BU6>6z)viLy#
z`vEg~+52rq$wm7x8~S3}+)5sLwr$n@Pm~(tp9jUs^5XZYPyeu(D)?MNt<`3{ov?HA
zM5eXpn;cBoJ$VXEjd9)L=m7%H=uQ0ZugWP~`M1W(0$&rtoU8h8C|eAf->ko1{0hkn
zMEh!}##i`v#|IbcZZi#i{A!1<*U{y7wT0MLxoPg#_}9|?AY%fH)^;ujXpG-F>-O#a
z0KZyUay*}mDytB$nSuV*OcO8_Z~h%nH@&px%6a_(Sbs@ohxQF;D5q4BH^qz7-EvBV
z<fBr^2gX=Gsxj~}E5SmslJe$`hp>KeC(DTxrEKtUY2{0f0OXYd^U?I}vHp_(HDt&V
zbw_rKtc_uq+D)MU1rF;T&b$#8AZS3+AUVtS4HR-W5k~<YfjhE}L)L=(MGI*DY*1--
z!g|Oz;{f*(jqIAQxin4Y4g;`i(?p_eIupoCs2wA+<pAsZwJ}Oqe$uGamv=!y21$$8
zsv_s@$rjRLzvKkCHt<94SQu7Bh31(ZE=~Y12NOY9I?Wr}=WXi@BU8|YIRDF1@mx&`
zC!7C)T7M#Tnn9`WUqk0*p~mqmCY<~=X5bq`0M(NHh`tQnnqdIMZ4Nd9n)e)~Vc-7;
zTG0K_>;<CGn`XR^wnlOFf5jFZs9=Hq)3#s{d#W-Rnm4|>R02@DGry2lw)lKvxmPKs
zFk>5!cdx8OrauGvE#ldx<}7T-ozQ$mPIS<3bq?$#lm4fcmQfewZf4fYm3(?P#4ApL
z8y^=j`!o$W>q*sZ)t(x%@0Dw6t_oHFrD&D!lr9<vc!#B^Z{<4|>gKjP@P;5qYSp7r
zvdhw(Kr(f4RXkK7cLakIF>UmWt71J%34QngtZ5#64ICvZ)H}~N)>Pwzbi|jK>Pf#0
zs@ca{ynXR^SE_p7dS3p&&lMfzgKhrPw>~QU_N7Cfc+P-(DSGp6THVu&l(gC{2K50q
z4(In~JK(4^0EWcw6u)rW<+rbt36&QgZQ}=q<098iN_fYfNto&EcQ3<5j%aYsWe)cJ
zW0ub}Y!w+`^^6Y<dc+O2EXxO+GIap&FYGF=%kiymo?Je1dnS4%VCvcR2r{}cF5Yo=
zSTS@)-L+maPTv}hMD~Z<LHGR24#l9?PJFDtBQ@fjZBwU3aX9fXA)<;w<%=OK7W2w;
zMamNwCDgzehx&)$#<VG*22a+U@GL8W0j%>}`DjYi`2lrhXqwfhBSzS$%%IFUU|q2>
z=SUZ&%3MSl?w+~6e)xo}Fw)5=WWn4fs88rpue7OM7*wWVz|<V+v{EqtxNLHKnJ7&U
zYS@w%YRU8Uc<3fJuvxP=>@!=t*dv9eJ441V8A^w*_TM2_-t52zF9cSBPoCg+&+BM<
z?foYh>1Sfk?_SwbSH&OfQkJIz+>EUSz(r-h^lb_I{ri@hJ~doEzvCp4V_B3pTBO?+
zj`J~&8+tsX`@Fvb%-0@=auN!4(m=YGx9z9E?k`R8_?svF_LAZ1<0Q`_O}Bjx<p&=u
zbgKG0h%5ttAE<LLu8358W?GCO(Ql*Gudm%~bBU!_{Uz~aANb4l+{0ityLinGM!nbu
zvW~*HWL3<tbPOxeFIv#RBdf=K>4y}_>2HSnV@g)7Sb037L3UA0*92xVV~W#+wB#Ze
z7#B{n>#+JPkr{vM@!CPA6lwivxQ=u&eGq&+*HHI;s^fnC&m^km6Go>m)%hL&NhXx6
zOv$gi)c*%s1{7pQD`90j(?`=cjJhpm6c<jDQG2bFJr&mhIdrb?Izo|X$}?xT?(;z%
zZ{Wh(wsRw`g%N8#n^>JW0Rg@O4j7R$xC}@Birp`iY6p}D(t7esmUX(?En2Rl4<F(;
zGMgt`cY+6)7y79&1Nfh)l|6`IBpxkPd!5wbDDk%*soOhVC((J79w!DVPqm<Xi3a=z
z34^{A<C;#5ZaVcjHvn=vHB%^oUE5)VG0nYgdwk9t;UGXzV?2hQh__8ub9+VIk5%g?
zIh5ZY)_C@k^YIry9+I-Rtb%d>PcY_XXmskyqVf0U3p6E83=v>exW@^8#8AA|;}0Zv
z^VPk@KvO+ymKa?4_WQVX3g33+mw~MB2)zI`o48-U$71o;0~xxB?fnutAd@n*hY%8G
zMOA=B3t{ct1Vp{<ExLO;;dO*7CKRcVhv1+oqBtEd>QlsZgKidifOyi?QETzbatY_}
zA<<(rm{75&Z4aVDOo8QnOX6cFge3DfPn6SO9{IrG!tYDK!)>;hMlAZ1^GKWK4K*MM
z!erA4#}xU|>04xXf}0MW-azcUOFnNxYtqUeDoH2*j?t6(um$76Wl^>sSdp5yPjq@c
z7jj(Jtm!98tAqu<gvh~Xx(Cv&)fo5ZY<#yf5xep~w{(7d`yc4w*kzjZ$Xn~nETtu^
zLGQu0N|Q2RQz@y%b?m<_+Fzq*ttijgX5m1TZme#3zhcDlFVb=EOR!9+1`gBp_p2%*
zTQ2B1e$(KC8jpVDVFl798MY{bVfPc$@TMh2DyYOUG=ItM-^=yHfuefh%u_)0Bm0Vb
zUAHvFC2U7Yc+H=R#onAxX({6*z;GURRV6XxvKFk}1p|WUt|~8@3r?2)@hLwZytGI2
zYy6Q3*LwNoi_6{UeQFpkyun!f)Er^ms*ikmeAn~=tY%e|5&+v1=tIqnX~h-}Pu7I>
zhj`DYqD2aaacSv&SJ$qAG9*FGz8TnRPRn5+9lqKYHmxq`DZPb)$SpuIvwSA&25;)}
zM@GN$2^f4h;SOJtygRw#xCi=#bz|~`?5I$Goz|!$PH9KKwK&2I-gi&7jEufsEek(Z
zGG(+byZp<ve;7o}rpY<%Zcn)xJ)}UZL7F_Kykr@@!VB3+akWA_`<wIhjxDl9Zn3+E
zvd!#gMJ&+cTpc=IRWC~Hwt88q6eo^sm%PP<Rw~Yg5}@#9$&tHqM>lbOJi}NjTi{|&
z>#<{BYP;eiyVikA@mW6@ctIC{ovTKD8=vDW&wMPWx|-F9_ni{ww^{~3h5uGK-F*NQ
zKeMF`KRslS<&xJL-6bkISFr7kF-KFgkKq05VVN`xQ(D;``b4t#QfQy!jN{(Ohq-jt
z^n~%h2|8>D`7u>`oWshxM{W%MrY=NqVB98D43=l6Z=}H1@cVLHNdIdJmcU$B`V!cO
zl*EzUBT)%Zwerx@Av}=4A`+ZjI~Cw5sJ951S_kVIx-SAoOZ>kay8D=AoyITt`WPW+
zOrMDzFm|T4BB{rx$zBh9ITBBpeFYdgMj(k6T?a-M@E$%E>DqZW4{U*7cTTd-x3puq
zxttw#hzzQxzXF23$jXAsWkxB>ksOjtDij)tjBV~mJJ5f+<PxgULl3sC_t|Pc6hs|D
z2Z076`_B(SkzbNmW#4quu^z<Mz{mMGEHrr7dD`9U5`gv#&INquXYW8)OFGb{%=LH1
zT-Po-E}a9!VgT8P3Dgr>FQs3bVCl7SBEcvpv*v!-=Ji>`KOJ&lfPe8t35&P{=P|Vd
zUdSYt!7COy$M1-Fx6;-++uqnycnI=CO75mk1K=2B%hN4Z#vJP1FG%~jtW?<AOS3&S
zJ5%0iFhR;dCccacOPSzrQ!Uv8yUtxkW#FvsBMA$K!&iup_2uTHqjl^{=oUFW;<`>h
z<l(7?uXCg@@-f!2y_VS1-=impLY9V@xX8<~xd(+K%|8U@&#S-Ru8dtVviCb2SX$Z<
znP{FD1_SorrDV5LwWd=>C%qd)&wzif>}#t6!|JTiUYEKZ|3EHmd;Iif2)Ec|M8x&5
zWLfCSx5RRJHe)NAu!S7)URW>x_1gIrJ<4g>*6pi-vtSfm@3C6SnCUj(Ul;E&L7vZo
z3dbs<;G;yxYR{+5CI&nZ5M6PwKdH)o-NhhQ3G27tp3FIJo&&~l_#SN$7eL@hVBKZE
z$jTB>4E`G5ia>{QZ@cIIXP;UR>rkQ5gRs_Pt%+a|nJzYXdiyQ=Fp((L8=s9WaJGzT
zf)~3lcN+1gPrV@pGEpTU!A_ijmLHyLA4R5Sx3K9$=a^zQ%E-#sckWk0PkF>lW)CZW
z$%Ok9;3gHoeoMJY43!@1EOj>+)uK7d#Iq-&s$B1x9f?)?)v`Nd=9$_GF!b+h(mp&O
z(*+nn`$@z;IPGES%q(sS)!cw^wVZs3lfQgi`Ggh-?6!yliuy0F<e5H;tnq5Oz={^G
z0L;hWt#_bTkH4<kl4UDg?6|9b+K4C)=bkK?pE4*0SW~*qP9(rgQMJ(3n66RdB*A%&
z=A6ICkN2t5M&oOz6lz3jb54Q+$ElR%bJowVXoZe&^szKSM@SBdE7P4MAlPN7L@BHi
z2lOs5PXX4%27DGqziflrzww%GxmZH^mIS`DC0A}N|HsJmFUvYaa7PUH9HV48h;VG<
z7rzAj&+d84r%DG-tt&SQsnn1$b(ag-HI5u&;7xc_Vi-HPrha~LA_sZt6#v;K;Y(K=
zSV4MD<6we%lQQ^$Yo|imKX>C5koeVFK&&aOE-muK1rp};h9h1UM_>!`<H}(eP&j`w
zi4V%14*rfSuIhr<1=3q9;p(aDv_$Wh7}l{LO`YH$r&Zk{=)`N`1*Je^PIHEGj8G5z
zZGx7aW9UN0>io%A%;qK2QQ(<OzW-4md?f!2>-LHRuNLdS{(x$Rf#rW7YY+s#iYrx$
z9F_i*>?B39Jihkiu1WFtaZkz9rA;iYthxma2TT~xsfD7g3(e$NtOs2C*wqoxNa*33
z`0XCkytQv22dIc@aU5MA%|Ae559UyeF0|LKs9U6vNfs;B0k7GqiUD%#P?Oc=m#V-I
z+F0CgnCGU9pf+ZB+&mVmI>8Zn6PWMrI-qH(wSo0PU2I(}>{{Y+Z!t%~XUaq9qFRvC
zrvooRon{(mqtLSvi=&=$Gv2@WtyZO>%8*PZ<+V;3T232rQ|mbYR+mdUPkS;9OVli(
zR#NKMcK3oCl&7`SGOs;^_ecVr&h~s2m)~`e5+jFo@%tF6%s+Lx8$6u-yl($`saa-u
zr!l0XXW;?Ty7{mMn1z}Ad-2M(_i}=gxQM~gvX(7xqI62##l&o}K00w>Ax8ZyS6_^#
zs5s*wR0z2C%LcEnE!1b)Upz=#UlovWvs?h;fg&y@&#AhdNZPGe-~2;KT;wB|7hX))
zU0U!+7Bnx;x0+tFPiE3thAhK=wO|CfQO2{c3}jJ5l&GXL4ri`7^#@Ozc}SXvJyBI`
zSm+rV462=>1zS=`#ri4$0u5HT{u=>`|9tgiu;@`MbAmd5X)3&NeC>_e+m0rz6xJrq
zH`zkvR69x(dqP_2$Tg_w93=Wha_M&^H_bZSaAs(uP?Rs|rk}-mBh2+R`4J9lzeSfz
zvE-g~yJzH}8;!bGkhL2Z5&pSa(Tj@mdkbBg|Ab?XPaxT8CX3|~Q<<TTWJw9>Nd2%@
zbXreB79+`GaRP805xHy~P*AKn>-XFGGKkDiw1FnyRFSlY)=oSyPU7G?3j;2--e-Fz
zA|)al(7Bbm6J;l)eCNPcV>5gWQa(1%NdS_$#7MKOmo8iZ-%=3bG$9^O+c@X=oK2ff
zK=wc^lXmBqIQV6U=Y(zHy6v4oPo&7g(wd`W#Z&xDTOUVZ^x{TMXz5<<|3K<+<{m9K
zJL~Z>@T9c}2H657I8}uxIadeYo-IMtb5CC5JSodny$%f&S%fjiPrC8+k}mSWl%TEH
z(_8@rrgfLn=gI+%d5iZ_v5_Xg<bFQd5lRm~mI}kWm+!MKGoMWw%aQnJ!+HGDq+qv9
zS9ipkJ<7$O)^dN$do>Kfvi{#uWFki2-w{D9s3g0I_Yv@)5H{9)n&M85aaC!>Js<C+
zeX%Ds+dtgL8WZdXbFnLjF8pboTDaKj{Nrg<b?tAScf~dVad`48?7H~&5?iN%wb@WL
zbx)U)uO87>6oo#+%<H!-B$Ah28@X+EEak;<X_^`R@IMefC%8n7y^AeDit-pK$~sm7
zZ?mR>T)?L?snqD*NY#6pV|<^*_C)rwTLrIYcXS)=HD4c&iPY5hWdL4byb)&d$@-Y%
z{#dofX$(*L+`c>$=@8W-wQFHs_f)RGN{jgsp=pJK#q^L;=9U5Dp-jPD;e~tQC|KvP
zh?QKx>g7c@dHbAlG=Z%Y1ghIrQy$2pl{w;mI7tLGg@e7{^;1Z=T26ddNyzw3mZR%^
z!T=tQi%!saaqdY4)E=JVn{creyoW4wQ>?j$!OpoK5&BQj_>?u9FrZXArjY+RFz^Dl
zdqDg@P=^LdfT3e|gy-~!Z`Qu0Zhr+xAqluUgYerg%QC^oA|G8uhVi6+sRSRhehp+9
zH#fAtgGJlr<OmO5>-~c3mz4|)4m;E{-tYn`Ip;=Esg=;y^0@u6__gtcJ>0<3xX(kV
z)wt**6S^{@1X*D9#0RDPjEf+y-@ogjNrZ^g*Ev_bdsj1GeZnyPlHL=c&-lC;Yi~OI
z5Igecf;?~hRKpL|Ap%vMOo_fop5<m%m%zG;_amuBR%R~b4<mYmVNS>K$jGX|ptfDF
zZ<#<Gk08!)N#S3<wAxEXeX$H3xd+UTmz?lzGvfMpqu3tZ?A9Jzu=_*O8;vAz{$*kQ
zW(|x-vL|Z1L-%~)7imyNKjy{_LuXvb?p%``<eSI$iAvQJ=qDgxh1#TkF|K<$l6#rY
znP>^s#)?xcE*}4qBRcd}G)-5Hxa6c*;*ygxbBbU?nSH_*It9EAUC6a8dg_BUDp}1g
z>myiSR#6(`9pa3QWFk}ZE58cIloq4$?}bNi*|-GOf?Wga%fVYcI}`7|10BYD@G0eI
ze+Rsg(zfgK&*-$j0cFp8{6a2qKt<ZgS$we<{xaUV7um$^S`6`D+`MzWCw2`ocC1sf
zB?sMbq#+NXE24^Xl=zi%Qr?{R9i`@PvSqJ{mr~V}W2_r53?gRne;WNHYpbAna4+h2
zrv<cAsj@o!Ah1AU&=s#vk>IvS+5}L-U+EpXR;&C9tX25Ywv*pXUm)Qsj{)RT$B}MX
ztb*H0f0ix(r$g=cRW#3-nuqmNzA0T3U!4)U)K>DT@F193f|~*b3SM&6?snn~Y+dgk
z+dJs_?1JJ{=Jo9GgUzhTetYKZy@wi;@+auAK6}6C&YS^zYT(m*PjxZ>UyqB$)=QN6
z8u6Wg0~S+Xw)>-UCg#%}Ey><xdHrb5jbT}6;5X)AVyjI4X9{;$c9#3en(usUA2KME
zG%cAO(XQ~fe{4A?2b>hWwo9(FoXVfK+AjvM8!Sux^7n9UNQk_A5xZ-!#Wn2k4f3*y
z=fJ;L^Gj*^wNGJ>4-rMHfCSTphCc5^X7TPxqO-u_!QC|7-?vPWFyrZjFYe=gGFb)I
zs%}t@WvprK>(A+frCiCsp&V2&9tRs(S1fLv%1;edvJhkzoB0Oz?reEeam^b=84#MP
ze5~t|SX{)8{L%fUoUVY@Z2(4${NVIxVZT^qA_?YIFj+e^q-xp3V!Q<6S&oDy@2Kh&
z7i_U`(xLRt@gs?{S3{*aA4op-a@JDzRI(;3Jv*1XJTxFbR(tbt1>WwoMc~XaYvX;K
z!ZWQ}7OC2YoSThcJZ)-u3g%$NbJ6W=alv6sEb8(pz0r7cp%@W=%JrZhUqoCav*JKL
zfy*W6!LwodGxlWx^W9EX$fxaW+H2B2Dpi+=u>ChDTo$GeN_Ka8@i(j`7vN@R`kmWF
z0RsxQYbG2y($;SeHeMg{qq5&f5fIo&KmDaoPPJx)WNWjY%3<7juRkP{Rq|2_1@O}0
zb$7i#ETB@26{$m1#$xunbYC++4oDW*rFWPNqHDL10ySy1Mp)KeS_b&brDR=7NMa!K
zi<RJ*+B0MQfp92$ZOAh|iOkes!HYyj(h_g??a<ZXYd;D@$uqB#ApZeR%|yB5TZ83U
zu^W=S^6Ith5`k<hD7OwILB>x&SIl`jQMQVLR4Tb&tvzapdGbN-s8e?*L0c){CX`pe
z|9m0#?Jta>(qc{uB{%e0Zv~YyR@rPV>&zA@c@ZH#VE@t0w4e0&jaR=SM<EH1mLqqN
zP*_iXB!kUQcro%k6)kE&9v~BdZp;FC>-Dul6pcNydbZAvReIjN*zYOI&Ci{F)vy@B
zITn@ZXhe{e`M3o5uiEU^I0>^b+E5(7ZcqIOIMg5m3J%C0*SQDq*|G<-uhOU=`WEZi
zXVR2=Fk;U1Ju9-vhF?NgYQR=L5Bl?6{G(s6%VGSQU(r4f!9Ec!(nH*j{d!6#c4(%8
z%U8~?S9=%a((iU@sfw*>letZkYv!OFedyt7d#yG`o-jm-S>l`pMq5Qln&j{C&?<8W
z_4r?HonA`AyI;$`FRl66_;I$-R*S%$L;u{y!qQX7U``rEmR8v&rYZ%h+<2(e*bLs6
zWhhIw<(ZOr>n;fejQuf9VcI>6_{y#P6=!);JPn>m#bo4#sMiXv#01lYUf!<}9@x0!
zFVBg6b)sY)9vlBk_V7A9I%uAx5)%NgW%7t?_rJ2@wRsXyij5a*EpSl(8ljSK`Xe%&
zhgO^v0^!EyYjTzx#}|o7PI6Mv4S;W|YjsA=O%t{xX^@B}E7ATI`KX<&fT6RNuJATO
zlRdlrH=fH*p#_=C6g_v+JVwPg1iZ;8IaFR)0!^R9im$wR0a&Mz8X~F%#C>r~5(4*c
zk+Kjr+C9fZW>`$Dp2Yi1Q5Lt`$AckCF5RhIsk6uZjt&do5(D-NH5~SQ5ICA;Tr<cI
zE!$H(E;ndQfe{FC{3f)Ti-k~8lw`cZj4-mq!vmK9fiP3Wq_P9vDn{0lBE<G-bl$By
z$ySypGL0p->&TGN7Gqg97WUXTbevt1;T8+aiVvK)Inf}Gwa;UM^k?bii_(cuT^*qb
zS;r4gf^;z1z|xziA_EDUK}o4d$`89u&yq4@%KI^2==MX|gS39#6N2nh2PKNnZ~xYE
zKV+gsJ~Ri#CMT!$?1ICK2Z8T`k-2`c$0ekipGItf#r&f%4I?);%UYjSk`hj9-f^eJ
z%65J#&*q&kleUAm2G><$W51y^#qaT0ej&<2manLyjX$V+hy1|8T*jRB6*L*RKNyrG
z_GeO;`RNLM^rxsu#a&sl3;av0sjrTopf4n@E7Z8w`o~yWWI^j>P8RxsS#WJl3Tr%%
zd;KVPx&cGpdn8Gtb-_kBn{b8Bn@GhH1<n_bZ_1o<3yz9`%!N$`M+}0Hh@s*;<%&AQ
z--#xYh<Fa}*#3~S$w`yMnApZ-It&(4h@-;%eF5icIPVK~!eGUC|FV|R1;BaW7pW&O
zoJn9mfT>lv<wGSYi9Y6%fYftg3U!j|1Nw!A#Bjo-i$}eQL4>iah;XXL3UJ2$9qM%-
zPTQQ0wGg*yE2v5xg61jx*qZDIZF<V=gxAsP{vMOy!mAjZP4YZckS)OB5}u>{8Qb@L
zS7R0W$u6lDxC?QQvAQrkBO>5V{z$qq>?A~oEb-#2O;OeX^TLy|53=G=6@x5FrVoES
z!xI1lQ=^#uY`aVTB-&s-O<sx%3gr&A?ny1yKFmi@U@0Zb&7%{fU-6A<=Wdq}Dew6e
z)?!vvzNd2MMz&GnGzgUmF-WD8SS>o#-nx&Kd~~4Qc?KcjN`*MRgzWVeyxj!ta?b0@
zV%zLwwWcOIOfW{N;n}|aABftq46m*<OFM8RluMa>9JB651XOn}IVK6Wz?;pji0FBA
z(hE;c=?t30CWIr}c}D$uYfXvu_L7gmf{%_V8pDF|IM1T^+u=#kGLcn{F`VE$>=b2b
z<ZHk~P?m(PJ^Zd1`{TM;knVNvO&P`jktl{I<tx9S-A?VQ>gu-UPj$)d@pB5pR782b
z@`2r-PUxEOuu})=s##TqMr?AgWYP+@^xm=WQeH`3j%l-JZX`5Dm9c(-kmz8_ugB&?
zetGIgK%9PYG{!y8V6)#J)2P(MEg)6keyDwQ?yNVOWl_Ll7v3#c{ws^|Oh-T&@1lyl
z`|nTs)2O_-L>#|A3gNbfaBoxSM*x5L9L4r*-3{Bn=I*U4?VZLen>l{>Ppg<BgNS4Z
zxAe6wz*5V?I&|=@80#x!vWi?FVg=0UpXFUrR;-H!icz<Ne+_3?AcYebWmb&&Y>yT3
z<GL9SYe{7x0LcE1^KWdsbi^YYrTYi(p?fVHrsDsBChTrX1`JPz6=$ontdGDVAKxER
zq#n!G=q)Zhq*zZ+TEXtN))I`Lo*}rq>1C$Mid7NS&(anbE)dT_B}TT4e4dDkDwxy%
zK$a54;;yLQ@|Y|}c0<EGZI6!C#J%td{6`+cwzL}Y*U)uQ?37p5KDE23WgS}D+^b~8
zR?3eAc#oYD6F2g#8Jrlsk36H?0>Yh}fGsg~&5C^vSS9<Fde-w2nA%K?0y&M0#SK;d
zxo!9MSLi=_Toa>fMEftKF=!<-lz~c#mkM|^9{?xy9>!hA`)p7n-(*y7*o$mEWHn}r
z&eCcnRWF?!BFIk*hHbqXLGzfSzuwh)UFO;VIG5KF`|eaE6l|gx&sNivD4)IuK?$)<
zbsZ5IN+W(fW6x6Nng0j68PgXAP{WKmcnMcJ^al*56sNnfH-%=5{hnA?eWjbh8n8VF
zG{n++%pL;-UrtS@_<j?B%qWf;O^H~Km3uyV3Gb`8>kFadxMi+%M-8BSG=Yy5ei_#2
zI1lBMv3`&#O-x>M=H&=524J^OjD^P2pJBJ4awWWHn!b(&M9hQ5;8Ql)!LI2869R|K
zy>}DmrA;fp!6LIP*5&X22g(ztaSl&<SAPFz`#odowP3KNL+dy3<J44uz7dN;W5Na!
zZb;iM24@WNpQTxkIVhI)>LgWmWZfRh{(PeUa&!y1xc$VUco2>0lsiQSCh*aMHLMnr
z=O_3>*9((KZLJ2;GU12l+ReK^Ewl{(<+zv9>U-I@b1r4SVfrBy*F51XQHu3g2J0ZO
zL?d<8G-z;X6=(Lb4S;C-#XZFJ7U%txh-dd>8wEmFmITY0>5nn|wK+%9%M)m41Jk_@
zAD8JyuikyCT%7-7+u|``Ebw1-52}`UPkh~WjhST1#u!@4_n?LS8A!6YR=xkTGX}q!
z1<0u$Z<GUV>098ZnzxwK8pE{WdA_&u00mI-VM@Wv-DR-mzp-hg`fthc(kKWfhR#d=
zv+m&QLDvtuvJ9=w-B5sYKb-#I0X;`aGLHbiS1=qM*xG3kiX%vl1-|oY>qTF{&x$ja
zt+(pv+&UJM8rj#o&hVDwbxnpiiKs3RHxpOIIEqL&6Tf*avOrJmyqCLRuW7PC*!_(C
zlZ=V^7mSzNpDWm!T2gn#bQEAqA~i3&e!$xr*!?~P?fPF<CD`M1btrFtXPUOA+~z8B
z^3*R0^e5kyA#*uX*?g8vt!1YC2Kil-W?_y2;E|<X|0N~e2nGoo9M4GCkK6t}lII^V
zY)lkuHGd^>O;z1y(Ift}{Bo(c62N;tTT7&fS|WW7FO=DQF9G2;A8*Q#z$T(`9Iqbf
zU*THnJoV~SUc^ixYPb8fl#TBDYY-5+yo>syj_+x7ol7DMm&?Xh@{Ds{t7?W;%b~uy
z$>HAbp1yYoj&uErMwYkKPTcC^#>vQ84&)xAA2TNobwX1;02PO8tIY8`fOcwL#}`!u
z%pxjAc<QmK=_A0$lIDj>@<o=sDbzoEK?g=VQI68)ersxYbE3L9@W+S~g5$2%3Qx}g
z5r<6hKQRZ)pQ2Nd1^dIV(kXw~POh)M<NU!x^)ak_L98-#F&UU{^B-|8<9M|ZN1R^T
z#<FYJY<@#Y@1*uW&^gk?G^nte)Sar{M8)6=;v}B2m*`6(1@(;O!$!M2PxOuZ&xXPC
zek!K<@On%g9Z{!GTpw|9Xps3okPTs)CM{iPU|1}5CYfKe2Q2s-*fQJVBd#e!sCw_o
z?tke9O~+Y(o8n3bZ*ZX{f@bfm6BKp5(Y+%0xkf)1`V%%oP2q<Iu8mc~Bl8kB$(3m|
zV(Khfi^av)e$ocT6!L_R8HTRtyCJkscnfouU1mQ3`~UEAv}Ij^d0(rqt-OfP=j>ki
zJte@@6>Ya{Dm@6De+f`_F0r6CPw#*=k+u1CG96g8uDCcB+Qg9ulAurEVZvMR3-3XV
zOYA1Eu?mM7K2)hBUl-KlUB176X^!sVT)IHq=F0sK1d6RvBrQg~Ty#uMT&SQo)AQ_B
zH7|8|@;6KYW0nAVw1mt)Vzk$uCJklnLF+$hotC}3B9YWApj;DsB)cP7Br7n+Rhe?b
zqcN@n9}U9ywOtq=7dLecRO{C|=Qf#p<<$t&SPsQWVe@0uM9H+?e?<MU8bmo4l7HCM
z{Q$18(iF1o_F`7X|LD5gEg!<^y6U>SkYl;C1-%P3!XKtiJqg@D-~!${MO81PZ0jQy
z{&Q8(MP*NE$V^m*J&(DnpwMVKwhdYUgx{0+n+$MjKYTn%N5I-=7rS{UPG#jpSO;cn
zQoE~?a|S~X=eDaCgyadI1q!1a%`oUSD80opgpf{`D94dkZlL!IsHZ|`QLehr=37Wt
zSzyh|p{b<gS>xk^MP+jK%`l8sD`k)s&#v)>m9KAwF4jg;(F4#DW3PQMuLbDJ$;KO(
zGh~+Q)suz7JwLXVPQ{RtndPVjiK^<rr`#{DQwM_RgVe2C5?<q64gAr!pFWBiVy>Wv
zTXD5xHr~fm2%*OI!ABKTCKKVrHHeU4n+za>AXH&Z+8G13qT;@E{NGbD-bbYip|~b-
zbMigf)wUj*M23VBcbI6t1$5ev(B{X`7C>JHu=SF~&6el}ZFkFTD^`9_z}iGLBzPnI
zh4A@)hBCmB0Oy=u_>#T<LX!gYlt)V|U*zFD)C_(*iKVwzHp>4EOLwM8;hz;kMIUF7
z{%sj*ryr9J0DM_&I8kL|Am;ZatLI~(4^t6glIW?HdtM+^52vvb13lEl+}|J<YYP=X
zSY$l{VdKxzN7Trqev%bop}2R%EeC3VIe>#NJ+R6;`Qrfx+*{a)8APVb0rPuO%)f(F
zG08hst;wYp{@{SsK3`*w(|mWAUO-;q_{~j;p^3|IuP~gOw%R}R;U`4K1sPAh3sMa6
zUP;^dMn~$GXO1@?`&tW}V~`0~v1&6pntWybAajhmo*uDfmOvIm{}HBrYQCsgX{iO+
zOK1KX1@|UQ&ACUeR(!sqagD6VfV(>QRI_W+8+@}`PFk!QUa8dqZl!?itGc;SK8(l1
zH%F&6it~4ae8E$#L-f*LL;u*<;#J$KaFC_C+Yz8Iyya)ot0e6jvlXwcoa&8D;CIm~
zGS!GfC4%{p{P(?-ek<AXNr^491bYfR;0BH`GiD+5|3D&DHh5-Y)1i*@0+3xTAyk>;
zg!x6boG0%3paFa@PPT<d#!Ti{kUbUa^I_NsFBhsGBz&yo1#2>Qe;}U<JU!V#12lJK
z;A5rSbxL415K%?hQTi{?0k3|Nn$^()1aES(-$$I5-X)Q3%z#lxv51$uBo%USOSxAj
z=-0XT#9G)!(MxfmazEO@qf?-c&-9^4SmzAeON`WtZkaf3ktE=#NlG8OHnsxSQXq~7
z@akTuuv!lxE!}Sxzk+R`K^s>?CodgG`8DN2R=Q*JBDbR{qJPdC1GJRP^p*ItkFG8X
zkpCt$^=7&7pmtp{+n>;ln~cP`B1<vMm*LG*%ipyvVy2tr1xGykaz=1uW}cc1;A*6-
z!y11^;k#HXeIoP10YS=gZktT>&ENKOE|RW_N&q-NPE~R`l5en%wKQ?jqEC#P#dm%4
zUN64Q_L)$*bJU9mS*vR4vvd{$=;}gj@%aSqSmf%<fL=+;hUHb-v_Vf7Jg=YOTxRdz
ziF{Cn`3OA{^~<__o4BuVUlxB)P_a<6RK0@utG@E`bTO|UaJeD^d<8}zvS<<w+~swc
z{VL)*N3w*32iTI%+=HQw18uK0j*Tqt>G`l)UjHIHs>-;pW}$WI|9W;XHukJDCS9s{
z6wd=k)V@&??B1CQ@tleS-I0uRj}*QAafh4x^dU0atoDYF=Xv(1Z}u%pc#PzE-6EwE
z$-fKT+8QG)9ism9!cb#4R7=C)6%N}>We5Kcg$L*BM|GBupanC5^{6?|0wS=}^n9Yv
zBT8K<p+ahFWr5{N8?mdeLmL&+u2yvdyo2wWCcX=ZqqJpMr{Yxs5zkFsi&R49<z|$2
z*J#O)P(Ns4d3k5yAf9?NTJJA0;$qvbyIPQPRM6iU=tnx@^{j&Z22gfhnpgl*OZep`
zw*M`)MetOzbV%8JTK;AD2Sv99s9UG!8t_z9lB->_{2AgNgRtQH8t?uAM-Z6Wnkl?|
z_54(9w!2BQU?=qrBfm?}zTcXmlR-<9dxtCF&0!t;$xL|DuRQCDma^MXe)quwh0BfM
zH9W=lq*;gS-wt7V25s^1Vq|EHr~<=-jRehwuzh8$W|J&%sA+Tz7HE;3mr_3uc$)~@
z(7}hOT2mrjBZZ3l;JVEPDd+PcYYttD!QQcP#|9IFIYFztz9Ph}Nuy&QkgiXH&omus
zB7QC`d~cJ)yEAaepKr!Cjtbtc*t;%XfA^l^U=7`gBoB$Z1oQ0gg|?Rd>y~)oX@mE`
zQDrqRfQw)Yra<hfbFkow)O01{@M1VDtCfKlsXt#@W;35y0#w;qs6i$7=Jub-pk2z#
zcZq(E2AinOSiYB*(#Lc9^4h2wy8qzR)XLxUNBES>W~l=R2eJ;m*g2HUh+X&T3v?5R
z6F~q3ju>+8Dc<U0H}`jMo^JsqFYF#*D8(+tmzy5BE<`!^uALwR9N|xf9F&+{4-s<N
z7>%4bFFu`U9B4n^GFl0=OPkF;%FQ!a#=6x4t=U;OxxSzc2DUi8bcY@EoCG0Lpr<Z^
zxTK8_)1#Z_0=m#uvhsdGK9>aDttq8z&T7_Q1kZhZU4U*;P2V6x?BRYo2E1ayo$$Q<
z3{~v`1ms~9PO2CR?Pr`l*n_9OE_oHW);8^~A-4617Fx_+??0RY%Bup=*xj4Cn8WrY
z`pKq83(Dq(_(bmxS`^PhN2}fh!p;0o;NYQ=b{sC6XhC=~WTu+x!&BLB{5HM2IBf-Z
z3^{paK1ptaewE{M5&lF=(D%6VVmm+Qy<9l>g8sHu?#wc^(yMj)a{>!q36Jg{EKaAz
z+yYeoxph6yN|bg_{l&tx0JLHL#f`ckkQlH}a2uh=D!=>BIq=^49@)~9E7QOMBQ#oX
zrNvTf(LPz$`}nE`Z~hpsy96W`C)j!Lg(1j>{x#nP{FrwZs1JpJy-+`ChBKII2Wio(
z<3HynbeRqoWfA^mz!E<euzbx4xJw&RZ@)mSwCLYB&q$jtl2syAHB5H8TgIhu{%c6+
z6pt3Ia#0_TQKwGwahlQsSwi<w2Ay-DUEOHS@_rTs_P-f9a~B;<s>JEgF=n-3<WH9U
zuUmfOT+Xe4Sm?L%;I^7cmG{pB-PAoUa;a?%+(bks>zB|$SDv*!b;FD5kFcql9Hs$B
z=?CEy`m4INY*|y>8#kN;pfTwA&n&G{lw|Fonr44Y+a!)zS+xbMQ2cVf0etytz#UK?
z(-oNOOpII`6FFgh%P86(;3>#o6v28B_#5+}njO#<Q|M6ReSm{uWlK|pHn*IBrD>@T
zNzi|A3eNs^ks>H!6<W_-<;ek*E6#9JomQHH&yN$U2VUZ}+Paz`c9-@n$U&rLfKY=*
zwD+2*|5zJ2Zh+;=JazF)0@va16BQbGUzhYdtK>OduYM&4{_Xzxt!cL42y<!aA@`gI
za$g0T_!dygD&&sADZGLhq>P+hl3eitN?XUuzC3xQ|ACakgD#7O&69xx$ZtKEUy$`d
zG#j4HTLh>d=$%a#YbBerx)L4LzSO`ruVk-!zJB;c!BH92?Z$<1=<4JFZLoQC1f+Y-
z?ro)sK<6N<1!#2sp3QxvVi2*gf6#doF)k!ajg3c3A7pWDsX<+W-~WLrXoi21yU(cw
z>j&lJ`#w5XjqUDryCiyk#scDZOJSVgsr0v-5jf@lZW>U$+{IJ9gmZ@cfC|Y;&5>o-
zwHI)e$;KS0iklLwGcLH|&(^+<w;pZLUR$h}o5BOzw>~CFjFeeKSbFq$PG$>Gi(m@T
ziTic>KC4h(l<bOOj%=7!6_l7N8Em)9+g-BW{xfuAgBceQpixOGia$7&daMO#2Hk%X
zR_qjD4;F#TWgUrA8qP{(@G9v+jZ^R1;kVf;VF+}kWyT6@8y!Mg%r9!w3FO%QiBRJJ
zFpYN#kUH6?CH>*xvl}1Oz4)!}`;(!itzd-4MifUOa4|hw`KM_B^x3;<gs%u?WtcQ*
z=j=vWWDeCG3ztXFOl=TvVin*fA+U1uTPjtmrhVEJz(p2GXQ2GmCA}dJK>4{V_eeGJ
z@2+@bJNU#ay{~`Igwn)*n>={QSiNNtypcrQ15D(b4xWCkSA2{L3Ytb({Qw8+%HLb1
z&8t5Kl`57|p0Gmm!glgYbE^Y9!g^_T)v5XFDNyBjwGi&_F45gv+#LVjbG1@zJkUO{
zgX471$^nc49;_DRR%tap3Hvr(0<@|7Kj$<yQII7Ru*V4nuy>EEZ&Ln*!8OOu;oWXf
z`tsRqZ8mYQ%XOP<$0%iz(G-+IU;$C|zaEB~>Yi&#3Ljh(-3ZOvN^{#OS-N+1fMQMK
z+^6rxwb%u5Vi(SLmr4q2ERw!1kB=X_I0z4l|9-1y#Uvh}-;myYoUSxfR+-SQTettq
zXMigiV_DP?nxHTxYvS#c!sv?;bF2H)_yl~$V|`_u>cz}9CA9Wjo;Sj@tKcU9m5dJ7
zaDP3Tdv)@HAwTTOjEvLunfHOG#zjr@vAWo^BXt_`{2Qr20KH0WdBndedC<sTx3u%z
zldA@cos#nL1D8oBcfRWdv+FTXd56VCAa)(QFLv1x(a-WnPqRZ1k+FYXIuXm*HUgpv
zCPl^xr-C3tP&MW0&$W&zn->QLP5gG*9<a$@7Jj1ncHQq=W)H&h91C|&#Yjt@nEDcO
z6L(4LBEB5$$sH(HzU=%hYeKtq`Ml0p%WO#_q#@{B;z&~DOY<ulR%MJqMypJ^Qq`gx
z7hu$}KoNHHV~p;aqcHgw-p!ZPa>#``g|RT>s@iIktnv93EAB{u-u+3%(<P&&gzKJA
z0C9P9Oby@;@R4{#weqgx7U+CM;*xzMf+iuO66NMP8BA}9ykY}_vhY7Kwd+G)sc7C=
zduW;p99Ww<$|5cqzT8;K|1y`dUC=St{S-{mui$gD1n46j1}9-x2UKmfzQ2(saP2Xn
z8dnVH8J9QER22~X=w-Bj@hu#-z@n?34mX^!89JdaqQMB~{#wDjt{3NXi|tSsHBU8o
zS%Cc@lUoVfuob#qQ(GwhPU8QH49IDX3-;?&EE?$ONCbd{WhWOPB$En@V&sodN9X|L
zLgjlQ@7D7^u*aZCr24z?v0NU9@p=r@vdSw9y9f;QD6J9DCrP75b=Vd_e|`3sP|0*9
zc*g8P=h4vN+2U~lHr;>l)53Kj^*WXWdiT=doFLdFh5uI;J-am{kb7tR{RMnq#Z?p#
zmI)CDpA-;$X!yST=Pw<ws0el3;z$-l+jmjlfYPo4h46vxaIFMGsmPHwD_^GJbkL9s
z`S9-cOL)fAOz4PKgOh{u+a@5sCj!a#-$SFh#}k3s88?vJoHJhH?2CxF^!f)W-oL%x
zNAHilkJZ|OOAA4wz1ftJlvvkAw-?4z4pT??M0|;(3**bX=f(OXUy??6-9BzQFv-!4
z*=t<9Rtmn9l|rcOJ>8Ma#Ggz?s6^hVNA4SrX;FIV5n5P$n*;{us-w`il(VhP;~Hgb
zWKJ2OQa^Elz_@2jAUgEx0x>_cutDBXy~$_Q-Zp{ab0mq~K-@Q72hu~_%+!0nu3~XX
z)6`yr<iGbS?>Zy$Z5Nd+8>=2#RK`$43SD&LCOLtpe%i7|?^nP5gsYS7^kO!jxX1oM
zip8Op_UDBLJGf45{<szyjf(gmDAVR!=w@}2fCi``I;;$6hSa$OJ2-elv@L|X8~Fy=
zl#{>#2e#dDP=S=d6D#On<3iQCKLuLcKYULBU*KhL)GBv;(e*=kcgNK9JxS|V_a^=_
z`uA&2UG2A*-7Vm^1)l*;e^M;>)c{v*tkvPWFzNx38;%H$=CLSj<r4+Pi;Ch*Qql^<
zKsI~y+|G3FcMl=?$So7!SqSUlG-=vS%N(tz$eVqQ<fERUjxX+Y<^BEPv=qyT@$l9J
z>u<nQgKuN4rWqY5K5JrzC`bUxMVCl7_@BjOoFw;**?qW<!hxkHgIb4o<ALp$<;^=i
z*!(W%*o>J1tUI=zqz;$`NzET*{eoX`7bG1cQ&i25x&5YaL4Gtl3am5bTbjVB3USZs
zit;r4IT~O_t{>V{LGFhC+^4+HK6hQG)l^-w@t8j#?`%Rldol8Qc9Vh4Uh*(@)ac)c
ztqcF${|_QnXdTogVS8{WN=WQvMDZ{0iy=SS$89rp@lu};4=*&MK1g0t)g}nW=M1HR
z?MjuBH7{^i_E+N~BCA{&c#EI*p^|mKeV%l<oe1G~kU_jE8}V(Ktkmarv5iC7m9Pxf
z;5xjaIi`4V-^K5FBCph7o_aoS^8Kq*jqCIe27@H)TvF~I@`zVg!I2R0jm$VZbt6QZ
zOYZ%Yz5ddLsvBO5ap{?3AVbZL_hIW4c~R6w=cr=M0k-jZ6Kj;;*C%YP?;S&O;w`VV
zWHKwe&z=wXX(%=y=%a_tvqTn_!CLZy95(WJVYUAQMOhW5@Y<Op3{#m$aU^XUCPoTJ
z;67!apZw63cgyQ3#<6CKBWBpQVLDwXe(6XqFqrKPzfLeEk(5+t7CIROmY&8tQCtan
z9~R(<oIau!UTAD4YF_kXs;7&&D$%vTfLdm??bkO(%$T6f)-`Xb9Yeaz8sH5tX2XR)
zTp#$AW=Wcx3*@(8eAHD*3a*bZ#%0nY%RX75nb&)-zQ@1oB$Rr&Q7-Q(I>8`v`KZBt
zC{xsemfkQQj7|M*IhtJvzykJkr6Pg=(^vKE-YSz|_h49oHA1m|r&wXuM)K*~qGiIU
z;aUTnrgy?8(-A(^eW;fPELW>e#+bVcSAK_qE<bK}3bGgPlrBUi1^{cXw{9XLmOHA_
zF{nZfF6RXN3aGsubBP3si<ZGL&by+ONvMM|sgL+6caE-s>5Z57{j`;<xSMrdh&?<l
z(lOuXS>g)En*lEcM-qm~0|RVq)r4V*b^Y>DT|sj1TSFnH-h`GnCGCk>OR-J%73R3M
z&gR^jujQZRX=a?_JfD-v>sL#0r?nC`61y<%z~UtaUpp)3vlKkzoLh{@Xvv(fW2A3#
z_b1AARYNUjkHz{Xc&yhB2Bnj8NXld7u215&=U&vhjtlF!fS0v2L-d1{M};1LS0~DN
z4*pfoe|(Bz2vEPKw&}}KEX<dv9_FAKa8olWo6il$S8?`kzM=!iWrcEE_rH|IH77KO
zMqbONuo1}u=H2Y7>ycSIu;T~&Qs9a^1T={I8bF<}mi^|*QXV3~V$ic3XyF#gLNlv8
zmsfC})%b_va!1FdzRT)45!yGJlX7kIZeLI(6^?CUpG)-KrAVA1s^03%dIP?3BrfDL
z7Rr<}1)QVyPKe*$6{j9Jjr#eYMGo&N+HOr(kj!JZM{m}S(O^^s5u#Qh(Za{I0t%kv
zLTbS|aSAwJm2rb(^FkDf1dtYWh=1hrJ)caUF@$sEwkQb?sIzILHlrd!V<<m+P^5n%
zT@V@2NUd|fvS*$y^&Oz{yb{IedNUudRY6(g`B?F(HW4fI-_KI=s(3fLO4e1OpY`9r
z7AUgpZB61v)W4RwN0G>Lq%&4EAr2I&aQ6*~y6RLKl&V+L!>c(W>=^h;hBhJ2FaN0u
zb)N+J(e9fOWX)S!V(n|!yZ;V*rQ7kkZiJ|Ue<ZNm$3CM<nJe{nK(pFmW#3~gbs#u<
zDD}1evsD8=2yG3HPSxZW%mdDm3^(D~yvzZikKd3^v1_jcuOyER*_y)3xp^&MO@<R*
z^qkU(h;+eYX#be}HKsD^G8U5X>WD9DI}PwFIN>EF6vV*x+sUn|4BpbS8`oMplxa+$
zT-eM#mjGtztg+DKhqfV+8j!XsqOyTZo&x4PURjg+=8&nLt4&ILkF~(o%Wr(zX8c=3
z(VUdPtvfVM6s$LZ!}}|RIXGSiNciA;*}bqPlg`p;QBsd_oc+aqdOD67?~O{2tn2U1
zJ7fkUsl1AQnn!$CBhG;zVmuCmJPvCrg03Q@mTZ|7&UgLhZW0swYNPCJ??c~eX7Wh<
z5mY5Tr0;(qz6QOdEU84P*nlA>C-#Kl&>7}mlV%$(9}KG4Ysm)-N(CWAl_)2ya#O|%
zqqC*OBuxPgeV|Z3!Y<W((aPB+wC1rLBht%;I6>=OEw8PVSkM<CR08gTH&06zHP0|q
zBcbtH#Mb1AyQjra|7u7pnuiq6khZ|qZ^G$w;w$}+c$`Uc``Qw8+jUB|R$_p$R+z|2
zm$InPfKZBKnOpF*P$8rn2rKH6)PxWeFPBZDMHsEOaX%0zQM)jbAE`^@v3RM!d`XK@
z7g5Cu85-0KDpdL@1pcd{eKux9?g9@}fEq`X(rp9OuOPLAUg+-QfjPHsx(mEomN7q|
zf-(sZTVM!UfqDnKL_eY*r|<^VbUTsxo`@2V`0!2?xO-RQ;uDj+@HpqbEa~|qEaBC#
z_R<v)I1(ybniF-4;=<I4nnV)fvc)6m*VD%(%O8*6?Xm>~9(Xt&Je)&lddrY&X{2{Y
zgAQ%6eJvG3zVK>tR=ooLJ@O^2BUP5D1B)?CFQ?u^=(0rVvG4cbUrmQ(N!?T>TsI4e
zLrpD)FQVW~57~QfH9PA8?w6m7@nd+dXp<6wnJ~qs&(c2S3u_Yi>X;lC!qb1cX(5$u
zj(Cp^BJOFI3in9NiQhp{sy!2cRetE2Pdsv9gP^y7psyTFAr~fb_)iP-p_QrPR#I|n
z5<B8E1W!f$X27vh^4?REApQ7I)>MvDgL~Bu<8faMF`P>tA-&rK;_^~7)$R%}!yl61
zKhK{oTz%j1aqTrX27y0gl;S@I3F(K}v|n<&B40s__98tAuG?YCn@Gw;F=FybpRX+$
zzc;>eE$>33L86)YLBUvR{HZ#h6uVv|39V)0c#(dv7AcMbg61O`vUN#iP74IyAio}J
zHx7sIUQ`ihN^HPi?8^@SfQ=#9^&;O3wTOx>6Pj}?Ul!wd?bbrm#mAB^71`#fJT36(
z`XvT%Fu4ghTu45qzqj(xf(Lch!BsHx=7~~|xG>wRHj`B_*ctUkX<-=PXr<Z=hI%~8
z0X?pH3ChnDLM-cK#?4q*H}V|&{xJOF9%_6fQl_z{-w@-YJQimSx0p@-$E4rv{z;&B
zO3aak=bxps+YMzRi+C^wj!@j6zF9qoOO_br&@ohoFm3^|+rgW&JuXcC%n4#gHJdZ|
zK<RqKbdb(w3+Lf%X6(=9aEXac73+Jw1%?=8*E1WYvoX;BadZ}LO}=j%-)IRDq*X?#
zq|yQkBc!`a>Dr_bkQgHbq`M{p5`$6FU4nEox*KWf=KDUs_aE>$@VR&2*L7a!^*P_O
zwynX?4)6YPnll~9vMSJ>XIY7C<#GPB+}3g&mS(2}cN4@CvuJpaQE4C}!{4>}?JF~E
z)gZRN`Tu_WH0pMI)Sy)0TBk(pPu=k`f+NQHncR4+&!+!NU7}WZh0_<Qrk+nE3ztuR
zlw6Gk%3B~AKt3<L@zGaayEU=(!ysZugOjAqSjtDBr>|EOa$Z)ySS8oYgliyYsYv}s
zI9&P0$Gy1y&N-wpJL{QBc>Kq*#-c9q9?LdO-G<sc9sH#GSE}9;KiO!`^U$sW?Y~OA
z&epOkd+Mw$FLnPUn{B2y>4xdDy=~dP<AkuNwZ-l0#1f0-4RP>Fb~10P$aJ{174fFK
z=tyC5EXb>M45C1;^2ZqY4@bJx-*EB_#cXQd3mW3OZU#H#AECRZ=`f&q@@G3ef>nxZ
zG1^kYsdpf8mqG8RN}Ys#@-?6OONJ9%NJBmQ+Axp~lO$`=<Uu-FE@3`YdxcQYYmnQ8
z9AaD8vwegvxvkdMyZZHD%;g1Lsp}t-Knc6<aV%g{K!>4l>bFTPcVN@00e?W=C;}#+
z66%-qOQdPLxw_V@v9}!n*jkYaYeQj(hwR|oz%Mp=SN=EgkoI(A+uJ76OeI)steZRg
zMV3tTDs-av44nw5%G{<$1*t`5RTp%OA=$?h4XVzF%1&CGUTN~{Eb?Zd91G+`_t~Hz
zr^8jUCLk~g1`2sBD_)I(J!-xfbiPbseVWO|=&zGK2|n?>#-5b<7UTnIKLIJQ;nWBf
zen2sM&4l1M7JZ4&dhZTNmA7j>M1d@Otae>qmJ_5}s$cECWxOf^_r9z8a&3{Gk1OFF
zd5+`H=_MIW+Oj5i`jxz?mXx!{UYK+UKye)u`+1peOOhVv@Z4kOcHp|TU!!@b?qI<s
zfX-mZ(J5l@{+7}M&HRiNh;LvlFJX!zL3TGmqZHztpgY!(Lxx1a$N>!V1tjr|e{bzA
z`-CT1_524ib_$vzQ8D;_sl^wgmuHY>dT$Uk8`~?h9I28SER=h=nQ*CXSmx3~i73z_
zu^fo@XTVxQ-hI8{VM=(%_ag)@#SM2k&r&bj45_On1=l5b2()X1AIZkzd5U)Hy@UjV
zK6By!1{Ny)CY<Wn<6YICGGoS=E}v|g@2GKrX}V&Ag~!Z1eJ%0>CmyZK1#N4~1;~S=
z-eY^{Vk%Vly1ryRNK2x+#iV-{I=zdy6<%h%8YJ|IK}{(8py1sSYZbHPe@1ZVKV%rq
z`>ZDAB_g)7x+}EeJ`?>B4w?ca!O1*JVTHl$fTb^h2n8~ai&0Fx!<U>}-*p4HNp;Y!
z635urw}{zN1Sd_RTccL(+NggPftN|;ht?GZa}x>WoJ^VjEj5J!pK_B$;Y?daK)NKR
zRyosN8{BFG`VUl457o~{WU}H+bU|BY&|b;wl#Z{45Htzy8OV*(llf{UHkzD!goVT(
ztVB=YTyRM?f++8V3AA6?==?S#6NA2rD`PTHLPU@s<>LNv1xd?W1x*QtIs@|3xp^~a
zP_~AJ?+%r7cdIRbFeI00({i<SrA2pM_x`QP!MtB$hx;Sw(XIb~pfUmF&G~@ixtW3s
zc-X<K(A!JQeu8B8J4}ZAgU~Wf1!4s$+NsRIWh5tD)q5+f_}gx9QF&T;j35RG{-%Oa
z3UAie4c|C)KF2C#2|kPmUtnHsRX#UM6LnnI<sCIr>LnqCD8&WTc>z;Yu7~}aUX9Z%
z>E-)c+)e^3U?+2<nqDV7S(B%4N*C>LexSd9DYhnH@^RcOuBxR7{6*ZmTlKl{q?e@6
zs}6FI&?)mRHL?VY0A^sE7Stsp@hT+4@31ONPl<pJMuQQS1F?*4wB(L?5nT;s0N3I-
zCX?iI$<v$hkr}s*nvA+r`cCz89q0-9*Gv~R1A6(}FLVChF>nhjiO)eLomm$|cE*A8
zJbSDQT4>oc<2&7KVDzT0DdBgPdfo|k#rgAZ3j25`j@a+fL&sm_4F&g!$5WzhO_l2H
zUp;3|cJy+#JDHfR!onmRvzFxGQ9q+X)(EoyTqhU#c?X@qdqDU5LZ!^M-RDg~(+>YT
zRG9S;IvU!o=|=Kh=^1dmU>IHI)!*fbZ01<Eg2mb!ASo?7esRu&Y%_nj9x|5k(^UvN
zjREFD;td&d>p6S;F;^kmyJrBvK8|~zTz#MRx;)Q8c(8S2>@4O+4cX;SXTPNx2h004
zZi6zfkF?fTmfEYf;E|YwHlllwi@+es$ZdLVElLd96-(te%1=qQABdnyfAzwx_C{_V
zS(gSKDt`5Y&ZSnp3imFX^VIvZ65#<4=m01D6%GFdT?+pW<s)QWVpQRre8BUC<=?xt
zCH9Jr<@pD*qv|=9)QXdbE^{x^<uO#?^y{d^^pf+e?h%_*M;`SfxccdWeq?-({{_nX
z4*&IRHlE`o6X9JfzBnk0aXK<W9JnzLe;wsNU}n9Sycmr608~rHKD#b}I#wLx(7K}8
ze3yeEG_31J1OZ*OiXJmW^vW0dLfj~wB`sPm7&snZ!pS;=9t!bDwE%LuYjuJ%+r;x*
zpv;OMT0j2$T~ho3)mBxr$Z>Ho?XCvyr(52gNND4rLgifHieQOU>mq@FS&LlZ4`?Or
zUsW>33OTYNltiLeaLW29x;uwdqr{a!`@Pf|9AukP5HB^(oz%EbkES~mB{Yuo;kGEv
zS<1ZnIu}z!?DI_Jb48ivu7Zt=AusNy0b_A0uu{#jg4g7$r{o7N`jwdd9tKw+2wUJ2
zxOHt;T|JM1AXlzkc;i<!4d9B3xzsjRsp)>aqu#iLN>s*_b?lsT9EhT+o1iC*wS?0=
z3}D)G@e20{E&J<gVO7pvuN(X|WLxX?89#TH`57>s(g}~P|2>%(3z#EuQqJ8ozKoVW
zxw`<m(usn7$+ieZU5QX?KcbRE@}+qt?_+P>1fD7iuV|~eDZ0%Ne8TEDeaKABSD!e|
z2!25CKV6q-M&=1C+FK=M_O&uMlCFOLF72mGG6OZ;RccdXN_sFy?ax^C-D+VV*>YQh
zZslDRgQL1ThJsojSI()Msx7f8y!Gh9u{8u1|6xS|A@>|$!h$ug+zPG)6<iL(@$`Ky
zm8&)X%7U2crGQT@=VaY|sZI6=amLjOI08%blHVRn-3S#DKXd9{_@sMou0ovQ%eLb5
zIu(GJ0JfvTe;Fh@g#X}W`5M6afe71)2Q#DoA@-GkwImo{TmW3^k5~|LNjg!U_O1Ov
zD^0FXg#WaIg%B`tkbOV49=U7gy%NmCMv-;XU=RFiF*K0GeXRVNZjkhYrIOxETPhoD
z<|XPw?P#T1`%9WJE-P4B$gtJ~ONUz|B6(C+1IA6b)Yu690XcfjWV?TO;Hg0ncB92U
zU4xWSU2sdUoc>veXJ|?C$-85OOD6(9R!d*4-l-sqBmhnLVrLZLPgU^T3uL@&f5t2i
zFM3wRijKd%Ub}^_(@cY>)T78%-fH1!)zjVhIG%UvBv`!<nb;s~WhohS@pw316%gv^
z%o&;Kka&AelNpxX!C+neq!wOFwkL*VFlLQ3U3~mkU{JZ@PXC)dl@IEXX~KzkxS2Z@
z*c9;{+5c(M^c<LF1}jw><NneA3Ow(qlY_gK0mjqz<AW`O8a!|E`(|-G`3A~c!w(6E
zYJCYYdvh^=ToepXh8h8l+8v*ju6?B%BlXTD+)SY`7bIBheZZ0~HO%lC8Ku*SmfN@4
zZVB;E23eV!mH{T-JGcr-!4zIpgFWuEev8ce@1yp6Q}eaJeN@>~w)0|~=zNg3+dBQq
zJ7}wXkQs$9#Cl8f;A~K&<gbZ!rOXZiJkWU7avggxw-BsS^Dp`8bC{aAEZ<{#M>*)K
zxg8M4fK?N5(8Iq5%Sif@+U3TyC(3R3sS@xVv@w9pGwr}<Nl<C_H;=$WRsVthJw*m9
zlz&+NI>z(Jr<7xL5fEHYx%f^6!G@dV=Ajdg-=|&fIE4`6>bJh8ty}uOMQ3<K+$l%7
zc0!Lw_oj9gto7nM>c{DBY|u5viiRG>rhNZ_8~~rqrmE(bH#KmHYVqdg@u01ium6GS
z2SK6LO{ziX98aDePf(3*cnBx%wOk6Z&h6jKMrPFYbZVo74ht*DFB-<c#Xs*izh&9h
zcQPAVzGQe$vVDS!^6v)r^NKjmSd?P+&Rrk>&{~eWn=F)ao%U%LDXY>v0A$76MG$nf
zICOl1yb`wT=JjRiAFGPp=h0hFhf9=&ApIHXnss=sqn!X8M0O!eVwgRp`hmj1cm51q
z_&!waX_VN0z`<%PZBzg76_A>U3&2sfL%bB3c1CPR`80T%v*<svXag6^E;jjz$Iu}4
zf1pR~pf}vPj*~fzSr+N9%s{l0>Gv#&MqPBsKWPMSH(>9d;lT8E?~ka!xE~E^uFiad
zGWr2Aiv0Wi3tERAdFWV`u49N~dAa7n_&-PGM=TZES7ReK@@eQd#u1a(ju=YSw|0yl
zcVp!6Cevuc>&VUOcaO&u#rsIB_fh0p>~#hMHf1|CZ=y~Yw74e=fOFq_!BTPuypn%e
zKV2fPcj#YRiFW1DF}7*f8ALwu3(FbstNICMWnhSL6;Nc%;+OeElr!fD8%8>c+)u~e
z@!eB>;ARfHu(BKVW63qGeho}vy06X)2McE65-{^`N(q5e8naJAF?qh<yM1DL%PDVZ
z@`P*a;~;ghJeD5a?|^u0d&f{H?`}UzIOEA#>t|Gy=J3XHZ;G@C3%&DxMe~|}N7k)n
z+)r>)`9ILrWsU9~9Me#)p|gEKzDFzgWY+?@{unCG&+)CwvK3@;O?}JBU+beFR%Km2
zM@_jP-Tff@EyP8u1k3S6kVzs-15b+0K4sDpauA?g&Uf;ObSX*gm7`d9j(ox?n!fr4
z^i>?u^=beGUhN^~gXLXDm3_rucM|L#r;~s#Zj{8l7T50J7>RD~+c>(<^UK42Zub|L
z+QHTS-Ti*uQ)Jq>s}Iwvjoy{`0u9q(U3MGqZ?m-jK<}F@cVsm1Q~tpOYU_<$LXBC;
z5RNUUSlc4^d+av^J9q$?Uzcy(y4(u}GD#kvN}c(-$j`h+#u%#i=*SV8G|UWF`m^J>
z(W|Vzk6>->R|*qAEbuP?U=m4()gh}X$X_d}Oxp@#x8k=hcehxaUgdOu?tSE8D?p@C
zUUjZH=Q<NoF^2v5F<U&ibf`U88U<i1fIPQzDzNjboZ6VOU)Xm#*01?O8mb7Vbs#qX
zb^>m;zyA~B?9TFk|49H@MG?hB?KjbV?GC8=&N@Zs=plF6r_Qw02EVf@$!E51A5Gkl
zmlse-nMs!q4>jFafhoeB1hys===N2Sl?8X3<xHo)H>-2QXGMm%r~cw=#VZ>a?2Sg0
ziw@0?(Wf86hTLJ-7u%Zj#Xy}Oa|QIEHdPsGgFqEyWjStHB0aF8Hpuxd<B!G*&Bw6%
z?%9JmiQKU&lnr!pA#TrLqGC$44a<Z(C0N%g&h5~>rnbgOzSrK$rq6SU(mH2$I~P?i
zr+-mutJO71U2zi>4*PV}{=|LnOBQjUvgL7<giJ;!tdAKKmj`8>a8b)fZWMDJs+oJ|
zLq63)j65lHKayB~{?+a9PGSAF;e*$yb$)_ZhC7k|G;w58fB#Malv7eXa{VbR&W}X7
z;Sw=Ngro=$%j<V5a$xii|M)NZA@HAeF@eLjP;kiXz|*$h`3?!Ebd4>MWW>UT@>vlK
zsV~Y2f5_SFFUF2qV|7`<S=0|Aw0jusE$30@-<5#kOsSq*9E@(7^_Wk4r2yP(Dh~!*
zvQh{4eBFnsp7^wjj>p0AGgTj4yfVJWQI(rwFulE==RM<4c(4dWafy}srBVqM?c?4k
zc8{zUA+mpy_nI?HG<pGW$eHMsJkjeCkXrIzs!Dh~0++bj))v-W=><GU=5^GnuUH&u
z-?POSRXTWmuHbgwc4>do2pHx#Wq4HcB;9UygD=PoD`4lE5|bG~?q&mZyxuIm4zhxi
zekHBNDq0|}>%bWn5MqJVtuWCVyuvbw3w;AS(*3g6*>D$*{STBaEj|bpLqY28bDH_6
z-!piO`3-Y9Y{#h?oUV4z@PGcRS4=Y@+53ncIH(xW-gqW)b{sHuvcyMz>6ScIkqFD=
z`vE7*$n}Z9+N~hBhd`6&@MW-bPX_yL1P22S8RP}B>BS8bkv*dFHJr>2-UJMHd`qxS
zh;8cHKuh1XW9~@r?G{-u*7AA;I|Lj(snDZ+UA>Wmw`Vc|BQ~*f?SSo6h1^#(yZzN&
z_U=2Q-vRfN&^!pN1=zmP+r6BCmd(9cY>C|(jS`%l{&m}=hGgKzKg+n?`kcJ;R{M=<
z`S1@%!fMSM@d!%a?Ycb<zd_54ii92fw_s2AZOGBpqg;X$QL*@dOI-mc>)31#H9}B0
z+-SP!1jamEFi3-Q6xS;{9!stg9->GtGLHOTsx7zi!E}#!I5v3^e>=Y!Bwz0gT{YWU
z@)X3fec8O$mniHOvh0(&_<T-v7RnT0;dP#i|CkNmt3DlYPerMc4Hnx!t*Y>Ox{9`Y
zZdz{^iCpZ2TK8z)hk_)6F{I580*@c<I?n9&0he~P!z)p$Lpj`1eBnjqCckTi70oss
zA<Lop(7PAH-CC*|bdfyfNwFQQ)E7TZ<_ao&Z^EaXzdx}W*{mF%9Y1n&<l7NYATlxl
z4WIi4&4U#nZ#}lV8QY7Cl+=eki5SOe)4WZkbFftY!5{yDu@A+&?D#)~{4s)`%#Y_y
zN7kSt0Ir8hP(WcIk{FM`czGIt$7O!dZW>hnk?f3l_JC@MpW41ATMFIl=J@5t=gwOj
z$LWoMI8(4+4&bGe+qZhC_Ykr3^9!KNobI0rj%UmRZ=7O1(o7Zi72yOjEZej_b#!N=
zt|35v>y8urJhNo9yHUdg=mw+u{RsSD91F=@{8}6KCB{c*DJ~QOyHyeHKg}cF#=Ff!
zhGOs1hUC5rcw4hmFjqD#43+x%hr_BZ^2Iv*D2bhVfQp8){z>$*Mt)3!BJ15Udl`{E
z3xEStq_b^G?B(7w1eOQkysQ{9?XQV%dUNFf+L7$1>_S@ANQj&uSoZV&TW3oQ@Y*5V
z^CMJglRsgA-&}Ke<K_-wOqtB~WGp&&5YU}!fEphsi`ZgHk&bvQiLho(-S{Ji+Pix4
zo3@EjMogqbbvN2u+h|VrP$=tGK(@^xF}cRov8Fmj{2!Oc;<2Hm*UvWAoU`KBmuWAg
znt}F6d+p|neQ%+BZOi{&b+UQ~htjqav&dhPWR{Dwa{xenwm52zWGvsJ;-`d{`Q846
z+?Sg2|3K>2FUPUq!k99LvF^38j0h3P(F$ZuvoL$j5A#yIt{{(>Gjhk3JVzU6bJt(A
z@~dSFOvdD))*|lZ^2DQ>uLlX5sWCQLy?OZ1?TUm0RUAQ;l+k0qp?YfK=C!9)Wuy}{
zVul~mp8I;zqvftS1E~hu&Q`u<krBK}>uvn%W2UWAOVld9N58M5(jfnqB{kF95k@wd
zNW3~^(UFb^1jvnYf897^mt;H@3<oTBVJ+a(PJMpZMj|lXRrqtklKa^B*TUF?VMOa4
zT#`!}JmhZ6lIrLXVFl+$*xg8T5qzX7m&nee)e7nRE3@NF29m^X4|p~H2s?$YsGis#
z1*4EfqD9K$GdCz{@*b^&)@MKvDZsYRBFnf>A@#fHMfu(EJ~XetHV^(tUI-4Z4yK(=
zCn)Q9@fP`WHI<6S7%`WiR%h|$rpY3s@xgq9&Q<q?s!3N3a%+%qO$9RND0%aqlkj7<
zKZ}-zzhKytUAZgWt_3EVJ>U=-m5spHg`F&M7hDvQy<-W*;)8bVaGrmfw}Qo$zGe70
z`~9@sA6cc!QQ3eORAhs)54#E}XTD~Tc@b6JY44@+zI9Kpn6H21{(6}J-sZ!eB=F*w
z#L~yJM-^o@{X1HHgcdV-W@7X?A`&X22f*5Z4g*%xEe=6va;v?!qzaB_F^FEA@cr$?
z?@y7W?k*T&SsgW`wyz3C^AxQgP9*GhQ;Tmzf5)p&<`5UNDJ<IN^kn0=@_sJJygJ0a
zaTWqq(cmej@}2Fdy(QHqowY%({T{B59E<oN3hZxC)`|dH^yfVg>)4~)>-6;-(fdT~
zT_hMl?4)mvC){!V@$`uFQ)Np>VmV!!Bm4yuNyV&XX>cO`16g3Wt?PY#5>UD+a+>$0
zt_V7Y8mCgpE5Y3JZTY#^>Z%eH|5Jgu@ikrYKGQtrJv-j^8#R;f%~eqUsiIryg`qe$
zHjcsMzVXgy?W=*v<(pGa8W>hIyuByl)D$M{&$-8!6*>?yLrxmA@87#ARP5N#865!d
zm?mJ+jT^5>9Bb<s8-x|ic93e_d;)k@Ri^Swiztsq*a7qMx4hp>EoE+dl366JM*@Hi
zE?c^Fv6Hu^LL`dk_ptZ>u)~byF9^lu*vW02OE3fXbpTipWCWf2iu_fh-X26y<#%@b
z>C}W1lcHvVzt91mrj!*zV<oS)>e`+?5cF^0ai<pjt|b-ShLsrD>s->c9)1dV`5QRs
zt&(CI8MNJUVj69^ECB!kfvNC6(wP0U2jVVF1sRiVl-3h~OS?52gFtt9(5j}!eD29T
zDWR_$1MaX$EgY<TE{C4aO(<@LN%8Ljn8(_Mz_Xly#ey)LHOHs}sHggk?i3M9pYDEN
znSCKt+c-1%-SWf41j7!o<cw#F{-{63gSvhORh{Z?;iLXbJ*};?t$Wd#QEdFVU0w8&
z_d`oV4_HOAKFom|o&lf#DNb>(!)IfzjhL<+;f8Pax#hn~cN)VxXm)X3x4DK3iIbe1
z_->kC@DiQj<oJl|hOBr|uGPZ78N=zW&IJDh`LBNMw3x0R{~=Ny<@ZZ*3;xxGlvCc-
zdxD<F#_u5-_(PlUnJQFP&J@WfFaf?2#oZe|pDzUC$y7+IHyZA#)43g}r(3f379;OC
z7_iFS!yfxUa{8_UN!Ft6)_Be}h)>00#d)^kK1qA;n(G!V?_}npz&gs;uGDdlXIJ;Q
zv2)@qUI3V|b)3_zR4dX!&M~1kOiy_dfQLAN$_r)AYV(~LdNvUL3hx_A&GprXT9r`I
zf^{)L$&Fl*-Cn^Khf)buwygyhb>n>PuVacP3mo49IX(;7aFIqM=-h92)T_4NALaL`
zS6JlJPNhB(OoALzsNZ;G6VP-$mpDD3VW#!yYpovxe6THi3R9%&y?GJ{;_=NxT|YeG
z|GgZ7g|ppHGG?H&yOIXqKA3z~WtLMf!+65+$S+gm@)t03?!u-Sn~#tS1v5h6i!<Qp
zE@&z(GujlFs?V@=OC{$)=3a>!=%uaq=<~ztu17{#nLQ?~h~I{+`j^qUn?QXi?+I^V
z48vM%G)=*XHndQ68e0wKg~;%*=644sOZUBWWHqp|D>l3EIAmPI`+D-Lb|=x?^L5qz
zjHGb$QCc=-0kiW#*^O=b0q3F1Q*GIh&qp6Sxy+yIF=m(Ka_2Zd|Nbr`wN&lx^r}|b
z%sd{jdqwui$YhYCW3I2DgRIUH1)7cCuB`NOXfFKY3FT!iu?Z!)(9X;gwVjIxW!Ws(
z876Z5f+~eL2n;*yctkH>T<daqb(G_!U+YenvdOhQNtt>#>XH;4_PF9uYkCXhF68=*
z)e&dU#Jiai{`jXgP1{-v?EFIDgY7!;+w~LKKl})Bi(USpJs4SQVpH8MnS@o^dY>S?
zZaWfXJ9F@0^L_VNDyiJO2>k^nF73%dOjk_Bhl(Ux;>?2*>Cb40-$pco3}h$k+A}ko
zd&hCCzPY|ezsDKr{U$>=%zCZP=?Ehihete@7cX<L8EXL6>h>Vc$eMUkq+k&HO|-~n
z^0~;PK=Gl&Ek(|P58T}97okd^K5)qgd*U`1e=Z}E;5g?M`CEdb=aqcJqNg|+lY<a$
z10M~3Mf;zL32j0KumtKSR^4c?BIhc_0e@5(meTnv_%z>zerd*2a=oXJya2;mYkl(v
z;$6-vQ2T35y36zNrFI?ZvBpUx>az<c001*eu@Pm$#>?uh<6hcC_%E^ZZfCkk1pzg~
z8?Kl*kDF+Y;DPi54T&nSZnm^iT)6GIuj`f*&#r#p>`|KM8@+D0OG{1d2Wje<q7fSY
z&5<{+lpgU-P1ZN=+F%a|zb|ckte&btA9E0_P$LN8zuruvwZ@>SF5&uR#csk=M?JiL
zwkGYrxHD``2=i3_8Lkl(mdx38zMte`sR&`pR2#qQEjwoE=Klxl(^Ov=o~&fU9+)`^
zY)%{e$i-STr_m9}vW`q}@p3C3rymZ=<u7HzD>rLJ<ZiW+Uc{E+^L4wUrHB9;7dv|n
z-EE=k5co=Qe=K|96>?&2=~)5Yh)24cR07usihgV1xP+y+60s^jiSA?(1th<XR7ZH}
zO-aXv`lVj}jFomrB<hnq3uFDY7OuGJ40LDOvXLQ;a;3%Au{p~4;Z^V8yW3^o%p@9;
zq*1i&D!<o`Q7Lz40zOEhnzBpX@@l-F#z&X3r@!o(*u{&qP`2Cp?q-7<ksT3;ktr+J
z5NGT+T~`SpYB@3g8I(Bv#i(+nNT<d(JbU9j=qKEvQ7yAOj^ghvAI88<*Fo|!lZl-H
z7Z|j_LNIf{aKSAm4-E0Ooz{x$;^&|T9gf9z@pj3rXvB5Bv0b8Or5^UilfB=96X?3n
zK6LAp{wR9Y3Bxx?chczd9@i4DEP6dt_FzYHYcZCZik0_?|8R*CwS^6LpL}^iaIxrc
z$`$He!BjO9j||d*ekM?H*oZVxZ$7K^pl!lkXXh~;MhDzA!VaFfKAA^pM8v3<Fh8}#
zJ<2b5=c2=Oj1`w33!r;?J%)KXqU~>)zMAT9#&~*|oB-QvPoaM%%N*4<tmLAB|6<Wi
zZMPQ=3J$I2B_(gvwp@%Vl5GnWFPC4@CYt&scv#8)ab~z0r1#FP45iT+3h65WGepb5
zqW>zkYtiFM`}?l@Q4<e^cTzwZe$>Q;f6ER^Hygpru-Vwxq{eR;3kvuRfDgSva=Rm1
z;J85%iu5Ce4~$=^K>JydU{y{RY>X0~KgC%3Q%HL(DOVg&3E;hC^VpV(#a%ki<2Td5
zp$oMZ^s>CE3e-Zt^z_YpSo|N`nx>$f64#$bbKIL#{rv7Eg91fL-@&CG-{2}0@3ol)
z%wyX{9M!4(;eXCp+SQeGQ{ZcL1yR@<-Yf*{gSG!Ra-&a-L}a=bjp<_{_AV-fM<Xa=
zc6zpZYI;()9;yISaU`)t-QFu_y3ydXK{+{*LBYsh+CkfrlyP*sC>54~DQeo}Cih#I
z5^gw1tEb7|j;AqQvs~VOMAxfL@PN57Wdv7--(xeywpQYl`kX$OFGNFRZCimn4{Em~
zi9P~ADvfs>eTLUINtSW-#GHL%a&<15-jdRVYm>qH!^Ch+&c~giHtMS)*BW?>Iu!-&
zlr330l&mjJ`+oh<r@5iwrr0)g<%{dxLJ_=oJE4df%E1qTJEYxHaunBz6A6O+69QdS
zdxu;(?$j4>P;%lN{@>>yU$kA-)RsAJeKeB@)3tDT6?Vq!7H;Lzm5^SrtODp44d!LH
z3sh8N=#jV0_hz4jEA88X3wsS*Lr^yv_8BZP9QrjAgCVgk-Lc`9*nO<REy#i-=Derc
zPwfH2eo75dS9ThI6sNN~J0N2Qb{$rv&Z!0MzN`HMQ$u6R9)g4nb7Rvj-uYm0^ltdc
z&zm`Mx#FEKhx5Q6&bTg#rK2CZR)Hc7{sYnf&S84$J3gj<F_{2v1vtNW3PkU$#v;j0
z;7?!Qp57J^(>d>7GMK5jx*elbqwf0Pf7;ybb=sevoSYmg5a6?BDQQ9O{1MytN|`IY
z7wA+SQioiSLG+uK8*+C!hdi=^amGJkya0=9>kqGN6C0<2pJ3a-(T|QqgJenPtbbk?
zrQSp;lXi5@UZ?q=QcUf?59%`2J_%c&{E^OXpDnUxhWTz+SCqb9GXUuBViBKyd2id+
zYN_{e34dY_m6kfq7NE+qj#b$F9?iKvk{u0sQAiPFl<y`SV!4>BvQ@$x4bwR-e4p}Y
zeK{`thjv{Tyo$GPEtnYrKNT*dqX(8${4t$Qlm_2jPP`{lDLq;3U+IrWbG8pUkl@6H
z^c+r)w>qYUu&Vgc6*as!_=4>(JaiVt3*Qrrh@2~Y-a%~=;JsQm5xvpHhR8knU9$8r
z^OeT}@9aZG@n$ZuD8Uc9(HLc`jdhV{s!BPmkS2Q_`0}wMedxCO-OSCHVhns!@L476
zLG79v#k!^KmdXGw<lXdX9uGa?1HQGJ%Pf4pqo{9uyNb2&%y>Q(Za}itW(L64T1A+f
znstO7xOhNB^U*a{Pj1ca4|zF;gn1Xw>INGWbG1Q~MHHaoCdME+ns8rbJE9xImw9g}
zbEQ@3u)YV8Qn2EpaEt27(9Kz+3f%37au<}Se5!rPBk=T^7!;P^gDgt*i5y*z<=as5
zYa06=YI$E{+NSZbXXuI@-17eG@_SjqxgqlF>RY40QkP>D00-#hgzX19*S09W2j{SW
z^)AB6JcHcG|3Jk-SN}_vx~>p+h2h~@f7K+tcu5ta)E0N5PIQi@%VFKDkI7W>O#aKu
zz=YWDqeJ!^dxIj4-)A9n<HaR0n(;!KTZ%C%7OBUtZ*SWP$AY+(FG_Q$z-C@5qVdc3
zpZ}F*1bW=UTfaLJ-XcV=iSf!F-&a`vk6_G46UY+HlGIX_XHIw5#^yc2|1T)!w8s3e
zs;JRZYlj2lopJvvBmO0x3Ll&F=Vl@y_}8eCSbeBf3gg#s;!-e!i&K9%fgyhjufzb~
zA<8^?WBSTw4!TclrCH=&u5i^YWFsE85l7({m`VakjS4g3S=#%h#CRYwcjst4>XjG2
z=}Q(eZ)S-q9-Frct*>TW;rL)S<p})fa@B|bKbb_MDSE-W#pyx^7}<&EC%N2b6319k
zbtS7`6P1hi=w?Z?Bt&)=Ks-e5<q~Cq`ke71be9=28N|itHwQ>L?y#RHnM)=RG%Vod
zjLgY72OY9z{E5Eke<10IjC#1gumR+B@^-uPO|<<%&jnmk#Q{yo0<4zsk55Kh+t*HG
z|HAnmuWzXX5?oUsvV>qXmksfi^nba#L?0`neRn0rw<G<`$Tli$N5a+jdinVrfc1Al
zy#zVr#2owCOF{6%qsS;(rI>?N)NhyMmQ)0&$d$X$?+$gn0sAVlK0n8PZbYE_mfowO
z(aELzICqW+l+xn#XCi@<<LWRAUHymCc{ZH<LX~;C)MWnX+~@q-CV@8=x%%<*%>5An
z^w#qFm(cZ70NId}IflC64M=cv?U-T5p|sq-OXCHc0bAGDI7^#0Y|73w3p!AwR840A
za?xVcN>(#Tr+p@v+Bee9x^65>i^0kCIPP#9>)c59cu};pz*qOhbYt#%;(1yizvD}x
zH=KXSIg%#jH6Se<n(z1hB`+|{m0llcqt0=+qbAVrHGt)t?u_NPoF@wQ82rZeKM{2!
zYgur;_zURK9XXneH^R$cOEHDpJ6*?OmPKT&XDi3zM;HOj_}+B&=}C~v^Qn7_x@%y-
zBxRT7+hB$K$Ek_e=37Iv?EP4+oyAKd5Tcv-8rTnR#yDLOEsE|4R~sF_QtbO}BR-oh
zJG-`3p}~%W-sPM0Ip0DXMNQgA{(fx`owlU!IS+VGVs>TENdS8i+N%_DFYU1$-9{{k
z6LN{OzMT@SUcjbPFd7%LXUKP`XY~275ZI}jQ+OG6QmYetZ<;5LCt0w5i(<(v<!nck
z%QLXC&UuHM8@MzrEdmDhH^xbjmT{|FBmb8#wRdW0a(2e&ck=HIrc2*ija%+5TgeoN
zp5kNVlO;QYSN;QewO*gLB@9l4@J=f4?rS!ovK*cEbr77o;i3e{3M<R|8NzF9a!*;$
zSQg~)sg{{!g$ZZEtMW&XJ@$fGME4K#=JPoHmVU9?e)J5v@BdImD*8$tcMQJ~z3W=^
zaw01(2}K_=RjQ?Hgr^=OyZ3ju>Vyh+zaXP~{hG$hxe`w1J2KB{@&b$&`$#N=bH{G#
zdW*EPbBzZmC6K{#u;)M4UNS`5`PdX9N_tsTT?Ov{YN`+q;t5b1t2D9#j$7TTU?Ps3
zc}OX=EC17X4~RtB9->?owtq5|=N=;!^RH0a-V%0Hk#HAv@W%2MR%Ee!ixR56C3oN)
zG&8=33egjyH}hb7L|qF?>JEcC%zhm%F$>$X-kIn1_ld1G6NEU=_-N-DESke^Y8V2p
z8<A0vztdNO5$I>m$h*&=vlwlN2SQZ7`W?@|E_agWjE(SjIqbNyegJ-Sq_(zJ;|(k>
zXo-_dnS@$16Dm<ndkdD#g<0SoOd6k-6s*)hJcgKK&Sm-SuzeCbyc`#K0|HM5tL}L$
zEbmvSI$ZLjYo|&P74YB2|I`P~2%QqQuCUJzC4uA9FAF)C_(<HTpD}QHKOXDRwevNC
z#=bcN?Q*xgw5BhCbr##D>Ccp87ifWcmAnwI8FgmAqJebeE<HYYatoJwN`if#8r^gZ
z|DDXlJ3DhrluKy{IJkZ}%d0m7*1LRXt}4;1oRJ2|TBkB(4jL*OhUgEFQAcAqoeoX!
z@mv&MVgb3ZwArZ>^TC5VtC^Khty247=?-2_MQdHl58J)}yIHv=tX11jeS>T=rq0LX
zd#(JEWPTY47S2A#y7d!X>-kpB<JRt<OCbQy`q}m?D>;iCd0>cB-7TaWSa_6U<~hVp
z!IuWa%s6!4WRdTxoJ8}x2gIDaXhei)SAU)+oC2cnw0_MFD|5L&!}u?W^MfbyoGw7n
zv4r8T?&FTbx43|3MVq6Q@Y}xrzZ}H<N*edLCo_=N<NviE-u+@t18I$??Ky`WS7z+2
z#{@LJd$MbNO{_Y_wo?7p{8Ur6Eg*UR<lI3r##Q!3k0M|yX+U1g=Eb2&GWYFHF2TA+
zYfc{()kh0d9t0P&WnL!oU6<w2v_VqjV(#(aDYKrC?;5^7idv!7BttnK-7S+M`OZ8g
zxseJCy4f*WFaQ---zA&mk9&Kq`<$lH&&zSz$1!gxLw_Us=sp1Rfkck0b0=B(a`ZkW
zs)PqMA?@&;uA&iYBputjfCXYMIMDbL(JS>gA2T=9xFn$Ktd8WqpNqR90c*&N%RzR&
z>~YUrE*Hc!IZE<Jf6`U;mqcV)cFq8^9|AT!5)N);tMYyiRQ@j#jh1Q$CgV8%19>O4
zWh_|6CaJ2~N@SzsSOfgL4j#NLb<<_7YK_*|eb!)EZ;#y!yu@Wye*7knIV%3GiX;D`
zAKrvbbQ=)<U0WuRJKiHivo>5Ub*Ro~l8(%uD*!;n{!GXAyr8n?SdSrOR{-@lrz?CF
z=przRkLw&en;1dx;!C$>m>NIx;YG99&#bMFg-NW&HAM?=yBtjiphB%Hj@@fsj)<Ve
zX4bYQ*|zF@A4}56{F22wlpg>Jdz@8z!hHaoaN~|M`Ex9<`-7OfYN02Jxq!SB6Y;Cm
z$X_tSC(-nbCg)#4=iQJqb2X6rlGiFX`@kneq8`qu`m~HuC!dwcGmA{8uEl!Zy7H?x
zg{r{(&wjXG&NO@R?^kItm;V}_#q|O_Ei&B{Goc5g<|%$l5_`fJ;{QNPf?eZj#;jWN
z<QE1yif$x`1xgu!PSu8acO~O@D5H6%#Qjxzw#c*99MJkUQ4R3|Zb&|f0r*Hm6YKh@
zC1WSd_fB_eW6WIpQUhPUSx)5U{r;(io$@!CTi~B@%Ch&Xc4wQEH|Em)4+J%G5$j#=
zfVW1`k|YH$RNS`D9^IUvyqApQ)z5YNb>`gTT{evh@`=t|#;#}7%X0Z&i<>5mI!ffh
z+lRl@Y_MYAm3cor?di(3GJUK2?KPr~zQpj6BJqBUyZM4DljzLqc)rbG9R1p2j_ON|
zr+0CL6T4b=seDfRwi<8Kb>$W4Y*byf5Sdiq2UvHUhdd=yJO6VMd7gXZ#GHBLEO`Nr
zO2>YFuZaUXZ>NHASk_6w2a3I}AAbyt$rN0^^NKqoyAr2&nASfS`sr$*W2bpsKHt@|
zVVj!iNb%|==0}~&J@*>I=pB^ifpB+*p_6yJk1(f&i+TysJX^y*34kJ+GWWMIEuln?
zAb!{^tteSZ7kOp444y;B?&UQv^@9Xe!i}+9)^TjS5A%hfea2k5B=O|r`)9N3q4%@e
zDq<QCiE>w9i=F@HO#|D@e^eVNNs<>~MCWagG4z1di)ZAQXHQaa$20%s;dbnfZEm!r
zVS*P9Kp#05B&wM*wPGJ7C$GgAd6?<5%5$|ZNQmofqB;~4lB(+6?pK7Ik+AGYlFydY
zV_`y;{?@gc^U+m%_+$+>U$C$Eb}aKZI}XqZ9E?X374E=wmr_7jXGCfgfgF%~jmBpP
z!29IbpE&XzvM-0vCEIxL7j{`VVmaO)?`|;e4dPSYSb($^WnPl;$Vfi;lD|H>hP#8W
zkbH6YyDVJbew40oby0e$X~G5~*D21kCbxOL(zD-K!Vpke<Ec!;Xcw?Y8(#7vQ!LQ;
zZ-o1A3^Omc52^k5RApt7`oX;CYQEMt$?=3>)D+d%osS3m`b*S!DBX(Mh18gjU8#bD
zZ=LV{94u+;u-GqUCRK~j{^cmHOt=|zWJ2IWX7munfUA=QmYf6q%PqBMSN0Vk$KJTO
zEz#xMEToW^zFA&PcW_7uFz=pB;^B#b&g@8384wvvgOICk5{Qf(FTo8>pkg%cIE6RW
z0JaAFM9G`+z$HA3#if^vKm7XyU_T_5yq9F|aS}Wdz4%R9TL+D$#e*b176`U)s2gkU
zE09`eDn8|0C_iNz52z|@f?YTqD3)lu>bh(iBS3kyxrmvP@e4LhGyV<(@bNY+-VG*~
zWzGXy!RFLnt(GOd@{0**CBq|kG#)Zu$^Qaq-W76GkUiP!GOG2sZ)|q4nJPf&pi%yt
z^99)x%WVbsC+3sqauSIK1jSRpT$248xeAb9F=k?dgEK8j{*xfbLFplM%$9ByRZA0;
z?2|81m-RsJP|HMbXhC3C!AXd6KCg~3O9u(Bby(v0ea{#Yz|AQVxDnc7hx27?+)9K|
z0pu2^x1aG(cxF+^^nLMWbCjH4x7+2zs>}6HAz<zo+L>z~{Hj7evk3n1<Q~fP*0bJ7
z`Wu`2tFKgqlpp@bdA{%!^Yw}5;PZLSvK#)4x1PBKZpQP6X0zpl4I#NVT)@yFwrFdn
zQuQPsc@@&VU#DHWNb}_LU-@P}qVucWg5gVsfSgde8{h7GLcRW_weKRZLZ`6d1fpAx
z0R6r5!$53b_uZP>jd&?>ReXY8;8N`qGr}pVwTHRJ8#iLV>avKT))lNtNzLa8YBb5X
znJj8zzI8=W1Zcv37e{h5JIz$F0MCA%_>ttJlDz04p6BL&WeFxnTm>%(=K=h%YZ0)!
zN7vmfXO3K(V7={RCN=&diO*fWCkKRu20}-mN~CZwPhsZoQ0hm<7G4vI-DaoY7hOY?
zT~Lg@MZng2L3!wo5lX95{`RZY|40`8(~v7<Y>bp-Kk+M<&b*2{Rj!g==19G@qr!Go
z9s|Gol~ys^%$%6S=HH@!m9=q}Z=|$u8g);vFi2m*>waHU?r>g4+=n+?N>5au@#L<J
zYnr|KnaW{PUkf=1$2*`U^C7x+(fN7~E=#7g{Y9b*D@pUeAM$W=Q6LFfsf?-ld2NAu
zCHmx7S?k_7=cq#)))S$ZQL5Mu!%RIR!xhYGP_cLucYf4J4V}|JDDyqLsg|a%CjGWj
z6HfPgeWJ{X_)!etL^e_(zMyq^B%gYe=~%5Y4EL_?Ku}GF&N$JNG_()Ls7y$@e*_Gh
zb}hN1&det~^!GZAFONETtGH))Rpj%99EJ+=Sww2CFVLLuJ%!igcPA?E;bmJ9ipD#z
z-;V?C(zoX5Fq35ZAg{9MD=LzYI_pB~mROvCBwdZ#{=7257Cj<h&~3|@N^QC4on`+_
zQTV1{kY8E39l6et+2@aUqb4#o0@zCQZp^v_FWVqWw$s1JZ#xxkW#8;Q7WRa9N**@E
zh6(u8S&S_?O=d>4HOYWPmv3~DdzZtnOBB0RBsd;s0ts-sNzE4{_+_uBpO&<iqs4Y`
ziAx;o3%69uNQUx&#yMaNX}fL5U(26)NewdKLPiP=kR0F(IE(-n>R*Y>^>MjjdE7K$
z64z2dgJOTzR4iVP#w(s879G#g-0qa$R2Z(>QGjyVMM#;%^>t5e=2F09Ta*pyfGLT>
zK)8g1**%^XZ4Ene)xP8Jc!1#O*ze(6g3O4AeCQr^bRQ@Z5h{W(GR?BrqA;TiLOKJ^
zPVL~Do}mO*Z)*<y-W|ad#yPk>|94>&VXupTWvQw`po4gd#jEo>xWx>>LC}|2v5QuY
z&9}**ZszdM9(zDINaAq%44%{v`&X`Clb-ppzBFX<!2mcDUcZB@tDM_7d@x2SPP7?I
zXQ9k?Q={cOzvdtzT0(b=vabgUtE!2^-*3(R$xGP9!g&6WYzIkFX&KuA+b)lW??*vc
z)W0|LqYFNFi`8xnfq;F`SaUZ)jpxgf_s-KBZ3?xwGk$wwa^lKb4;<IsDwQG;a-5@|
z(#?OFL!_kM;7c+@D*40$TXz?IejkM?F8|lr;dd4K?SGZoR<}ug+EQ59x^I!#_tR^F
zFXL7Nhj21f*#LT2s4+Vv8ofaH%iFS_#%m&`Zl0rXq!lu&Rd#ryf%EOGoBNG4_~0R*
zx^TlBIN}@OFQLc68E>3g6K|Y4-&<p)x@R5fkWF3w+z}4OIScP40%K=(UQcOgi0goL
z2O30I<?Ebm78D*Pdquwup&O>pdSKFi$>{Fur;|P8Du1gQ4P7dTM8Vz}e<(lTg}v*?
z7x^e*IT!pQ_3>RKNcYS>Q+2$<7QDO@a~Pz0!qWy^g&(@70S44x!=FP0(QEg(lHjT`
zZh->jj3rU@6LEIvAd=&J2^FgXxB>LLO(+x9S+;DV0xmW1pw^=mPz1BYI#z{2?6!{$
zss^8$JpekhSl8F(S@S!j0J)IwP?EeVqi>d%!isfXw_x&ZP@No<LPv4JG_Q*34%U5R
zSK(itHO%%#$pfczFe&v(UKRP?Cvk>edVefE5<K|f<^{U%jfs489ZQ-}M%LpOJJ2ku
z5NXEg8o3O`;cDnWm`>*2@85qVbB&Ehd+Q^;$(26MnK0IV6L(R0pJ~^3gf2z+=Z9@r
z$WL36OviQV3QrjVRq-B@lV<ejWJmIj2(4(Z>P_cR9*nrqux$Y*o;i}@Cpv?Lb+hg-
zK*;JKHDQkxIrle!j|o31L1TxK;&MEo`o+`chD<3P{HXAtR;|QL%@-VGrRn-OM}2^t
zAtTxUX9rw11;j=N31ZKGUz`yUAUJ<kkB*xu>>*@Ecm%T~PD8hq+CJh~?-m5Q>~Pk@
zWPE3TUi_v8RgShFJx#ySU>c)1=Gm|iU1l&d5ReaO)nSb>vQ)HJdssMq+Jg?tBTXuc
z&6MWoIe&kDsN|~7wx31tuI5Q<%})SHWRm^q2NaK|KSSJmV&sUUZ~LXlVYufkT>wx!
zmdY1Ufn{HP9`S>{a1=|&st%zHglC>G7Q=5;dDmflej@0I@AF6Kju<If|AJS7W%V~y
zp-bj0D97U7HMO|VYCFM{0|{dVi6|{@6sG5RfBbw)5S&~~1EeSeflV7Kufnb@#)u?V
ztN4l?HkHlPtC>F<L_0DA&$WMUZAzRagQDr!uh}K|L&7wBOPT$i0z-Fu>tCz5e>wRZ
zA|T&2BmHo4b2KLn1BSr6C&YvG_v6~%a^y^wUg4|5N2M~WOp9Db%2xBdcs5KI79y{M
zB<YoDDz=hBj|5Mw3%6M82+Q-;VKn>07!`>qO(MZn-iu?=3-1i`=`Yn2J)-pi5<x<A
z)h#<0qn39&pJdE(2v+3@Yjz?#(KJIJ(mmn1ofd61^-d`_azYRzbF39Tq3%-z=W{Uy
zdK{S;C6^TSVd1gNfz8y12*F6&iSLZlXo<{ELw8E9Vs{6yRbz0UfhhD~441&|E`I4_
zU;yEa;ONES1`qZvCa^<c=VTZV!0pD-7GG33VzTDKKfBG7?vFVm)HniYQ+^%}O}Xu=
z0dI`-)*b!PDMn^V6ga7P8s2egET@p<Nhtgk9*%?HL+*9rc{Ac?d(pzMjZmlf;$rW#
zbt%V|e0ON?1Ry~_LU4Q_j&ONuue2R?NnBQ23W?%A-L1WawGZp~RkmfUrcZiqm7Gf1
z)lrn}&pD&C*tg?l70>%uVryJ%($2a3B^-2KFLRJ3;GV#3Uyg_Cg8{_l1U+<Z5g%%#
zdfoU)*G#uyF#YA*Gr1ve4yu@k8LddI#2D4_`jEE_MSM$aO3)dq#@FeV`*9qH;gOv=
z53QPil;6+%Op)v!WE(tNknIvLar6evdWDv))TFT@8pFj0*A#agZFb6iovc1?2@25i
zNtL{>f373fuEywXMvIp}3?f^1z7%l@MGn08qz6FHr~$94304N>^8Y}tKNx>fy;5P|
z{&wH!qO>NMUr~(`sL!Q;8q39EEY8CCbZBrFKn@m-m@W)wUM5#W&&^gzx~2&qg^J5@
zxPga>PMh;D-r)JHZ>DW*|NO`O+zAm<Q)+Tf#i&|rU8x&9RMQ=y0IaK&S}2KD<KikN
zuGN1_$L7TII-_LL-LE*07)~Dg4OIm$8NS@A50*y*!A$y;DqmDzI^E)FJa5qw-Y%4=
z{<P<f!M%S$kv}TSYG4v~GpL=PMMV@jjDadE#Cm5`c^MU#Bt<_TE)g+Q(B7K3I%kR9
z9<kk=$b4Cw%HfYl&|_tEXt+7cr7;S7x7eQRo-6EaarCNq{X&x|m)B0DfAKB(#os#O
z&%1*&4n{&*+x8JHs&<w)^Tg(+q{07zK6L+8mEXLyekk4O_rjk|41sz*T&y5px}sT<
z95-=hXbd@>%7c9Rx8ur_dmF{MWcM><P*`r*we`+hh%SmTr0B#%<v)-<{40c<d3k91
z@I<$~U`7t<meYGSqsEYcBnYkZ28!xk4VJ=rJK*M8ck<=Ks7@x*Ibfev_Fi#XjlX`-
z2crPAf|s`(az6_Lj$!bo)9huL^IhJ{i1#-3$YHTq(<Jqj_vU|b!o3=&G6T#h5q9LI
zeA|?o&ftQDO21wCHStTqR{M#bKG-*js*u+dN)m=yrso*d=oW!St#1er(0YI9!8<v-
zfb!%uAe%K6-boL5RB^;iZL2xF(S;)Qy2rBPyWD>#=p9bE3z;WKIhE3bQ5(YKDsINa
z!ZINgDXfi_sLhSqF#4uJ%?rr+<sB!qd=@vMP$6eT9QVy1(nxx=cEXRWi8+r9;hVgG
zJu-8nd6-_#W{cNT_vaO#-owwwvMAo=#~duL##;)_TAOL6+RkS2sXlR3Il7+sVsS!v
z;j<BCX!GS?V;Ex>iXz9>>p>L7NSOLFF}<*==eWN(y$I_6roGRw;a$toi=;i4jwBxt
z$LHm)C}aD~SfBsAv8N5B2LHZeJWb|rds38q+@ozTk9X~!g&(Wv$ZJe0&iTmkxhOGF
z2}O2Od59Mv&a{OIhIWLjSvAIKk3te82aXS(koJcszXR7V$gk;ZVU_*&4W1`8e@M_y
zET0=p6*&_GE4@wBXSza0J+@ed#>M(*DWW?BC=26aq%=$NXD%NaFZ%Nza&Ks+W=d?9
z=VfXImsbXh%ZrvyFozv&DG_{G4HFy`*GaN(m6V6;k)$^<^nde5(eUh#>$vTl1jYV*
zJbz-OFJ{0WUy``5vsrGS&%&#|t0Jp2v5|046^#I4WY30gkKFcA2522$zPSv3d?TOt
zTulQM<SH4ey8c1?`Y$&*wRhjUDRZp_lJRyv5IHdbNbL^sRM1^ssF4}>s93;nwrd85
z=EQ`Wt$-QA5)(x;lGt^WrOEzw^6)z?oTPc<q46jk@}a`JWLYx>CdRcqJHhxNa<E?x
zDyH}Q!QEcQc!;j>hLpG}MQ@qC=;p6)&#l1;^q94Bh3{@$w5K?!;TR_K5Yg*#0VCsq
zoOM=-klL?GBahD=avwfetvE1bb@X@JMoBX~E1wG5SN{D>UdVXs>DFof16L5+X0-qt
zD^Dc0DfH#x!;B=nNHt<%PW~~Mo5@a)(G$xZBty6%E+ye#PFfo#N`RJ4$n7-*S9<OU
z{T7K;e_09_rHxkXl<5V+iHIeQh_fz+>+@fYA>bJR6|2yoi<}AQ9ke~&F0mCkd6La?
zglp<V<hp2ue{#q?k$2`^yPEr;m_+TSU)MHJh9V-rquOeAtKD=RIc_A;?Y3mwvNi?B
z=d1?sbojTQFY~GXkE833r~3Q<7a5Vr-q*^^zCxMF-h1zPagD4HmqaCdyVjL!Tq3e5
zBby}mBAX(zv&VJs=lA~p{_>y4`@Y}jyv}(&U(Z1bSJ!t>wEnu4q!w7*cvcAz$0IN~
z>#um`)@8Yc6<9&eI5Q@5>cp*uf~~dv6&eQ2&hX<w?hesW_MnmTK~>Cp+``MTFYd(o
z`tDxe$l_8WY_iV>t^9y=uAHOq)SAzCB9N|fY6vKQYO#>uCMQ(oP3Z0<Lu_RHypMm-
zMX>&pDn7Sp=vr2<CX&=K_^b+c$`DIGbvIggM`y_FUnMcj1t?rnj#8#{H2=JgkY3*G
z<O~!(2WKo*L~$3dA+bFdP%53SgBWwrUfj@uH&w~HEaVBZsry3RLU~TC3J=&8q?iW^
z9hBpFzN^*|-M(x94ZrIc%VAA~DZigzGTrUWaZtUYYD7n*(QA75;546awjg)6i#H42
zqoS)SF8wH2U&u&J*Qh?oK>0Hv<PK%JLiMCl7xv$9BeKd5JoFCqy&PdIvu!x^d=XPH
zww2l(8}=;d7!&(wgEGa?XnC_lItnC2WLI)y>TEV+%>}xFuGpvC@clzlsInd!4q182
zda~rV9g@jdQoN-{vK;D*o9Su3fZJy99w)MA=^o5q-4#)6l2}0zUww}L3jKJ(^?F;?
z@)}18Jjr)&5U27XLzh;IU~bsOpu84>_}8DcP=>gem!*Gz`S#ggskO5z7wQF-&&~P6
zK}N?vXVV9I_JB|XgIK9SnP+#eYRR}kS9u8Ux6JKG3hBDl3V9eO(T$Jg@oUnK>YKTy
zpAZl>K9yQ704IPtp-pX$zm+MI1WHR+-bP)Gg2hEJLk?=Jki)ZxwT&OrpDH)6(t*5a
z$UTxFn%RtkRfQ+YIb2{R3gy$6>*Jlt0t*3$>}cBnKE;rV2Ww&1#>5QI=I*|aXa5fb
zKSs)I)g+njr`D>H=U(A9V~g<TC_0+MYSf8U=?W#8!h4A+#QW#&oO5Y)5+(86J%4nz
z$`qxPPeHYJ$((>RulI)X)dSVHaYMyhnp#@Qb4YSOr-S53(+KEa;g_L9mJcD7ftt5G
z)88sKm}fL4QC2IA%>-_R(_#mPtFn<>Xyk2ckqd^}hO{q-CafN~uZ)VR_?mAXHiSU(
zhDxa##_tT9DB7HU_pHAnnjy)~Ffz1GkX(M4c2`homo}Bh=k7N;he<DW@=J5rk7_dY
zWJvP17RtX3;5W~aR2r+eIs=}?8jBZt%lWve#xIWf^qZ<iBji4AuU&2wans6r^fQy|
z>QBjouYT}sGV>Mi4a)2-e;Y@rF-1{oz7FIIB+I8d4*?$oE)o?frc#6+SqC2TfU_j!
z7NO^_Z<>?YRITZdDlhOF5(W2EV)SRCr*eL4sOXxGfUc^EhyMPPbQjz;UUBGy`RUxH
z>8P-JYnKTpvgQ&j5@(=$&cQ~@+J-0`+wk{~^8ECtkb508ZNS4{vNc;4P8vBA$Jr+V
zww;~|C>=fKDEg>>Z5boO3Noi1n>}F$(aCSV_xYnSxBK!?fv?W8WR-PYwxsjAnq)LM
zRleGD=D=f3q?!{q%aJL&slM4n`3Ns6Zaos#`(4DVB*Jj(8PqL{g#DRsq|ajhM5Su(
zvBGx3p{3baoKdc_+Y<I|I7zH9QV7WA{;B=F{}oodFQQh;t}$R`gdw!5&n-A){wYOw
zOP333fXv-Y6nuDB#6gd8P*l{S_+>xUSpQ{XZ~e>3{%|wxk9;3=(mF+LXK5a|%FmGF
zcw2a$kO%MEjFk&NErb24=IejBc}8vd9_!j_w((v_xz?7_{_g8-Lq5I?9i7xc-YWSM
zH*ze4Tfj}TX*Ak;vOOV{J9<J=b`$<*iSmbf&zkwGpo^09(a_SfT%g6)>0Ar#d=<@<
zPB~S!CA~G@sMjK?5-!Zw4NY{VnTQ0+g_Wnu(XpYD5D~HX;h8kv=j$SG(Uq3+Y4zW?
zxewr!$}{)2Ija64sffjDJB*1AEj)6~rueuc5h+D78|r~@E+G-Sisor+GFAaa!XNk@
z40Aes+&b>sY(PtK5j>P$1`cDm`P*<Wu@Eda7W`MZ>YE@z`Q(&QKK03*`MXtwai-AL
zD8rrlXLf~e*_E>s=oQDMt}SB0^3r{iNYujWU=WuQnj%*H_Kx`N3pay@M@2CQ0C9y_
zR>qA0mrB#s^qySli~%quNjrhV%Zv2V^Hk{XWpX=@8x3%~|BLy#=pb!@IKzkbrNfZe
z3}=Vc9hVy)BeCo)$vZf6J&2#m`mEcYb``n(O)H&T4?}Mj^?x8GXYfBZz;S7Uc}*y}
zBjEDi0!^@)P~OLRW3TB@q<cg!OFn@ip^LphVUJYr-RGP1zN{VLUMG%VpY9G@&?}bF
zzD&2(3cFN@aOn!TPQRAc*gaR)CpF>;dOn&h_0mUG>X0u@=)nP)yn0xcWDHEO7f>E%
z7|x}?Xwe|w5u))ar$IMGJ`;{TqIDUJ?K`Wg>k_$X&5&rZIC(&H|InYkm4ud5=e&zH
zezU`6kyRk}0n4UHn7V(t{CD9>(ez=m=@>>(dkc5Y%cC!8ktX3x+HA1-!x8Yh{?lLn
zn!&Q4@Jv}3^H(2v!A}P@wnURtMAQgJ9GEMt3<&b2d}bk*Lr3L=9u!5S59Je!uO2N`
zONBmd8#r?DCrA5eW|=6=QzNcD(}&`yLO*x#;j;`EeR_m4|4dF}seEj%P>t$@Z9plZ
zuJoH`#mVL)U}F2XordZ*_<@zdnLzr}s*2)1t~z7cZ>XDvX;H$#ls+^)`C;p@ast$z
zisqL4NoCWuzp=OWQD1|}b`t8-e67bB`upPmROYUszw%<>>VZE>8mA!yzF$OwUk7C8
z%BM^|O5yOcTKVzHjEh5i;4X?TYsM_uE-NUPHL6Z9`8KXBB=~-r8-VRLn2=T!{+cDT
zJgwD)Hw=7#Q#JQv`L!!!q1QMcgYp^Y67~rLs;tR)GBU6BOYE{SnWjU>jR<>(rRb<|
z#BG0_L%rJovn6gavW+o4`Ssl7DvbZ)o@Pw+qbJc1G3s0wfug~YHPLb*HJBwn+HrJj
z_fXB~#@HXgvB4|AFUV9lUFhE51M+TC6S342H^pK@_0!72LYLWVuWR$T!$<YmwSRRO
zPVlHe%kMMr71^gb2Fn?M!%f};8kf$JwuhzS)1UpqSY@5-D<dlqQ6|NDgs26HZXx2f
zQds+M%zk%Ah0VI#P)_h=h0!~VGVI9`u=B5KR+VenFr8HQUcz5L9RYf5)++uy-;_>>
z@8K{*y|Xj?cgSiyWn4-PM{BK&*VF_X5iDi}{%2^KCNhG60l`uyqVb~gh0Fn$S6yy9
zEGLH6e#MDA-SGMyP<y|zqwVGdc{M}DVK#gij|3k8mc@zV5Ct6RVq3ecqU%raF?qX+
zc_nXvwEmy7d@H~+*x%?2zHRu1tZ?ILgagp3(UL0hWfYQVn-3ezAt~nTn!dLH^YPFG
zYJsA1iRz`cskgPFjJ^JlU6(U%(?>h^yY+l!uTNANZJN(vE72!jSoun#s-`vduy0YV
zKA6Gk1O8FZ?yn`>9fB8a#%V}23(oFw2s>t)posXwm+!jFh>+rJnyvjhRg)VvHxzYH
zbE0Utddy~FGUu8z#D6><2;ZP;{}0rxAsO8eh|s50T6m4SZQtD`cS8gSeR7H(wmmm$
z!kW_F_=pWehBjOyA_qT^_9gbgNsP0~lS}uhhA-|yOZ?MHzeE5iOhiq+DE%j&wSTiv
zofLf_xZW5?>DryqMm%(^kCVH^Bx18)blxA2HhuRdSnGNJ=8UsbAgSb4#(G!_cvD36
zeCxnl8eBtUNXK!50D<kz+G)W8hK8+cIQi-Vu~>!KdLxYP=Qd`NS3g{aaZf3qcTB&%
z3aJH%!1iIl6z-z?GkjpW+Y#{}NbcIN;D9y7yC5`vY+-&#Y5P6Qj|0|Za#P*T3JY+Z
zENyfe1sH)4c6o<b1Cfnr)0W^5z)$cjO_1@gzP<dxuKL_WOVS#ZD;1Zv_tx<7r=%Re
z(&A1j<%wpqW&frE*}uK#y_J%%c~}ITjG^P@;G6xA6f78SlO1hF?xty#EzFb_Kq9F#
z*PBlm=-jJ2%`86&X<f%Tt`l$&AF{N0iJvN6O)O`SE<l~G<6Qp3^V1uQ%=fauRZZEj
zTbOwwCt3VRxk(<ek6(P~ehr=pu^Uz+=aY^;qZEG8Md3_+Zli1IKCB)7z|a5f*@E{y
z=s;mA-e2mpw|aH2?&54#MU&CI@Xk%A`#|J=g}@T$c)7me<D@X6J%nqklSMk74Kb_*
zjxq%bKCmb$8E?vlQneZfb@|)3JkwYv>xGEh^PX}<To|QYpcVH?A5~y+CstB1;~gQ3
zL1({H7OF{L#nm^^JJsSL9#?rr9q?xzRqPXxJN0RN(WZ5B=dH^t4xLeEVLQnYx%1H}
zk102ZuSf99)WA!xcP)~5j$cWLBdk?P&NvaAU|1lb)G=1hCx|#EJ2qfZyeVgD9c(cu
z^kur~c-zDr#@OprXp{C&mTNM9%f9zq0VUnrIZLzD9H%t$J6^d}>$bmgIUuApFJb9<
zXOk1V$5yamlX2o>MNYT{{Y$#GaKh!$s&<8)k!@9xU2ea&APR7{BHO$gJ)Kb5V}th1
zKaWBF;9XqY(N~5UF2yiX**Fl(?V1Q(Pd{1IzXfaR^eM8PC$<RbO1$8WWk1(aY;A|%
zmePK}WKXk?z75=>WhL9%z~Nfy_#n%D?qqFi=vNuS3{SFyoY6~}&B<WC$Xr=Xjj28W
zb{voU-)TO@<O$Tdz_>%36EYdP++1XsAR2imt!ewgU4PG@J!nb*vKA(=u3U6t`&6H1
zg7ZDjGZsU-sR!XY?ftGDqBP8OaYt!-x(4y2G|RBK>o~`6Njjvv$z+dI;{4@MJM777
zc&iX`IkkKU#%Z?|p*&fdr*ji#J`qjwEL8SJN^21oyJa5G&oJn6Z>e#yg0mZC))YuH
zUNICcN9oejbVtr7SaSI4uW((BHD~!g^8+O*RqIcmR$=Q#aWTy);>hPrt+i)0@y3m!
zap#*`(^#xY^DS4*5k7_c0eXf;&98jgnBGjVppL1wyZknb!^4fzvTB2Q0Cs(=h>F6p
zBKf94n*^X*r?ly+MAQta(2A<;n-<-g8sRz>n;B7r3a6O?F#hB3a=t>!*|RC~s~>bO
zWqBQ(8ool0Xo8JSWG%P7hyh7M+DKf_rf6V4e#fY3;Y==k@^nJJzG3)HUEW#w$ZTP}
zQq8q%&MO7K536E@vs_mdgo!5pO{%Kj<&wTsDGMo|DA^WHYImjLR;iO7vOW`2{vovJ
z%e&rmRy(DV8~2oiBvr#TpE>Sf+b~X?RO)>rz{yST%G&XmU}kL!$@tzC^Q|~qq|o+#
z&rO7S+%n>mB|CRaw5t&^GrPay-cXgWa@T|uTa2dienrF9Y^-9>7sgL`QPwgH13(@H
zI5-w=+GgrOiR~Q#xA8f`^`T6=7t_1TX>o=uLWZ9T+t@LLQL(Py?FaUz_zr&2F86#h
z7Gh~_erLt@WLs}@Q6zaq{bnb#SU}MaE9m-|aWkj>fu6hf3H?EHZ1GluTl|YxICG;Y
zH<rH78&Sre7QtQbM<;QR-+Oi&KfWtzR}xb{nMh-Pma!-FD6xcsY;z6wOqdWl7CpfL
zn4>T=f0M`1EB{U(VK>IAjk8w{msN?ExsD&JJ%7G$7O{}KM=c;7{k&?+a&a)HlK_cD
z0k2c;Cc?grQ@g6NjOu2*%BZWs*~fl2D(wJvwEIM>UhZfy$yqZ%n-qoF*lO6!e0+65
z*ZELMPC{1lwXKprw^N1eerP6qgNG7Fr2T{nckTyw7rKB%zyJ5~;k|g{LNV*2);chz
zlsW~|x_#ym;9@vJdLsKI#_n+-O&jFYz@jv}Ek#Lt+wfsgaBVQ*AIe&+pjEm00}aj|
z<G~y=8iFou8SI)frw(|*{BC1%wkmZ|H%Y47D!t@Sin^$Gg5j2PWT*m~)nUJd2txq6
zLsw4q?lRhIHa2ROMirmpFQ0q_TBp<|i{+G>%-@Pp*(Ev^T7oY6P0l4dq<t1&H(9tF
zP+L(7xa=b`=yeo7&^K}+v9y)!&hw8-!H1?1mKs6$nt{+?Xf7p%j)(N%3(KN9H<qiA
zj-Z3)J1z$D@bR11z&5yg<oLtjTh(e1+H!M_3li}hkO)`cbQ!N8VUz6)M8@LDMFIKi
zyV?^dju&|>rzTd4_|=m;Ci|@w%rZhCXf=7O5Q)6~HqlF}h`0;e@X`wUoTl`mlLXlp
zlfZTwo-Gm&Fj{VnzcO(aqWYpFl_DK5jtB<|!V<#FO=-5S`C^MTX(@{2i4u<H%DLH^
z()EmH3DZMID(|Fwmn<K&JC=bLIsSrqxPQLBG;I(XQG~Bt<(ej<S*Uj>_eUtHi4Mx_
zccz2Ib8|!;9As!tM-r84<PfIP3kace2<ZO7C#}&cUc89f!}cwL(r>i`g=)gjX7`=v
z#0lN+$RAZ2IoiG>l6Qa&!JnzDK{j67M_6!qTS~{c%J<d;gx=f2*{Z6npy>|2#oC^G
zEq>QvB0;7Z4X8%9yd74M)jat6>(gkpB+&4=b|hH`vuPVkSlU)SXm~80ou7I+f|BO*
ziZQx@zl>?t@_Mcf)T7w-)*Wa&wv0a_m?KP<YI#BW7ff7=@JCY6S2#cYx{L&WoxGhi
z_q}F|E6q5fA*0>KaD2Np--EOrbD*$ing33ws&A@ASh-^R>#(6wPt3%b-;C<P65PY+
zvO>u{p9@kz1WeQ8=trRylAFgy?_1<;y*HdE#7Q;zJCz`RfE&)h&w*bdzzm$tl0~*8
z>D2+$wuom6r!I#-_OT#fIO;x-><-?!?o2y-I7VKERKEv7{qo!7o0l=AX#hRk&ZM~{
z6VjUH*n)M&G#_z&8pcNhdSGq=82J(w$P`?#e_sNrC%lX!t6e$gIR#R?s@ujw`N^j#
z$@H7r<=L!MDui-@22-+y>&BeQBT}l%k|T860H+v#xXTA5`+=H0I~JroSk46y9-SP8
z*5nmtQ2-0zo%M3sd4k;DxxN34b<xpVA>!llNE%wTN%VWoX*qgAa?K+PlDi1<N42Fm
zsJ`Sj_lt$(v_1FV@8SZNo#F_eh)!8ia?BH$gZnl52+I}!4Za^rR$)^X-CpVVXVADx
zkI$|$&*N8<dIH31hMwlV?W)wXB%Ub0<8Nc5RV`nqM~3yha{2UtCfpV<cL}CMTYLeX
zU)3aM(NCUdES_y!{b_4Ekt>wm^QjxoMIK@cx#FPql!@A78#@ow4yYwt8dQ$&<zed-
zJX@SPDq5o{G58wEKuF{6MdS>{tycM~kAeZ0jC=-_=`_WGQg{qhV^@@}Q>|}fEgYS>
zv#SX8>B(VYwH~kBs_RcPLpaG92IP&l^KB0r`Uh|(0agtn1W3d}qNEu8LM+dT-);G(
z_GQA4LG8>1a95SC(I?Cm0?o%X1z)w`$+B|F;Y%>;fl$1fq`{K_4#P<nB`Rx}2^F^f
zXSQJ6W}2Y2;%yhF7seznw%mzAnvx<X9(`o<=9)fi+PMU82hzO9DvzV39=8Y`X_MhA
zFRHPwPPJyqd3zm9Qt^7{qVFXavf;LxpNhO5y<g`{1ty}UH4kE`ytOa(b$_yzMVIjm
z3N=$-v`Cd2Ysl{NI2u;M>4b<DTX>%z$Fx^~7f?qK>uYn$+_<*r&!x3M;8vRia9q90
zN0FA@txFBy1t*YE9bL5C;yN=a!vIu};l0vV1=S^Da!{wo$y-^f<8_Qba0_oBzwWHZ
zqmRx$Omv#2<=Rl3-9i|LG;}oqtxs&0?i$QCe=Qwyo%-+5otd|xoRBR!ZIv~PiMDfX
zu(ZLYnDxt_`UU30-rtojksciz*v)5dUji;k*lOGw!~iqEW4xTjtE5?#oDl3}U<-S*
z@lC%`47@X&!uz#8IC94{TFxvd#9~eHRhs^fJiT@pW~me~+4{>Nkk`ib1&ZV~DHmR!
zxIWSKnqutUNO+A@K${-?>6hM)CqWJhcXs<FV19Dl7~kSuf4Z91q;o1_AoLldef5Cf
zh44q)V_Gh#iu<A}0#VK-=4!HI0Ma_|qW)#27o7S>cr~ESUI^o^Tq=ZSJTog!f1+@x
zZDs4(t4%&V6-e51>sLtdCFS$({565h;L{3PU;7uc>qnKJZHFoIq@vP=?Ma!L|MYAy
z!~v7+%3ae@bF6vPHKzGdp9!H9+)b{Vus&nav%z0ZAeKixX0kZTDsByO+tp>a`wvv=
z4Z4uE@<jGVATq9Bf+}bYcX7*h$1aAy1;y&KzS>m-j(g(G@YH2EW!1U6*vZaBGaRdL
z4BOLL3bkR!UK9(pzw7asS*-g;vTZ!UR2}Piy?R_jFwADyGR^vzS+Mcft+Zui_$NO?
z{MP$f{Obv{M(G7~=z9>M$<pK$U^;4)d*MS;4yf5fG@Mu5a?d9$z794KyA^vM5$38_
z9tZXNY+T@GD6-W1cv)FW7L6dcn?v2+u?7?VFcVMHTdN6dbxXrP8Q2TVo=Y_@lC=MB
zQl6@Ut#tY&t1Q(rU4J&o;CSR-gZd8?%y|FSEEC^@2_6qtS+(z(_2K$E@Rhn>;=ejz
z>QYJ~f+>kQ*dL`qTC%ZY<ObY~CnI}m^3`qIdqxNDd`c9u$O~rSuiGXBhN;l%tf69B
zuFX2_+@w`+Z1#q2<9dm(;;t#OB0jbKvB*|2`p)kmqDyQp%q0*1RQIuKoOPw3@iRn}
z!kMUU(^yZiF8_5>t6^i8N+$zRUFj7Jn4QM{APrFdN0X;3f7;8is(h0Q88rLrGyl%k
z&vS?9wDO&S_E~pw6z<0@g=v7~GMwxjC9B|MMHS~uq1;tt=JFzPM?|=;3P5?dYT#>v
z486VrA0ifkONl{eAImZY5;}%Dm@X{=AeZY?YUL%GLW|&%9wla?%~eZoc!ef8u9?cf
zj9jiURivZo6Q8e-spRR2jJDY6Cco@Ssq1E3W})7Ch5)jNz|iAXpt8wJ7QG|E_w+&d
zvi8K1KjdpCW$9V6`S}K>{cS=mQQE$%ib%k`oBiPoYg_p8gcUS|BP2botV(PpF+O0v
zXnp4P`!#)@raN~Qie9%;{rKU16JI?si3??0-6lD()}GrsFcn8v`LFA~0G|ur3C}|&
zEO=#n8Rvp_8@{oob-$U=4i)u#fe;0|W^-z1s{A%NK4*_$NFPx9^*2r-D_s4e1HC>S
z64=L=q<?-zBTI9hviJ;AuQVvsJ#80P$*r(s#hXR^AE>~WH@$U^(@@K{9&l%ScL1%P
zJ4dA+S_*D{N(1~D()P&|?lUV9RSO}1>e_8!mcmr-%S{xfbeilg`<yoT-Xa`W8!Bmv
z)Y|#>!iNXoY6g-FN^6SH(X3t5+o3MSt%0!XY2rycw}~|pEM(oK2I%Q{h^tn~YW_YQ
zTUdJiCvjQ1GP}RtP1)lUfeh&&V-D}BaoZlGMy<Gs)zU>TLcDoRU?196I%1<t@TKUC
z6Q?It+lcCrOdScd*UyXW)xG>DMXMbbtNI$Vjh}l3%`Eup7hLDQ^<OO1135P3+StOk
z5}?T!C;Bi!t>mMS;nr|t8P)B7>ES!ctN(aR*zLG7eNbSpnp&4KiR<yifHL$QTgrds
zVNug@Jg=XE;U?(-&SvlkBX>@mLC744pRZPX|DKN9tt3L1{M_0Bh_77DdH;<JvI5q0
zc9^>^!p8hWN-U*%PMXTGHDqqD_BrpbzS-UttD)`J%i{c$kEC1;m<mg_*4FZ?kPUUX
zFK?if)}Y&Qp81Uu3V!S817vZ2-PTgRMCCJRw)kf9VZndaV}a7Yu$x?;uXD<6(WG>p
zEKtz4qrnwZGkR<@P`5Kwvu4cJ()SC}P_;cM@6%aGU2d4{)=KSo(h>`wSpX;xnh5t<
ziYrvBlOKlFe1~nA$1fYusP#a9y5n*i(Ps*^$Q}LO!mhyXSkJ^%9LJ7Hy%MRI>X^%K
zPrpssn*;+t#3mdr0AG7v>uAu+nrCT3_{(^wb!X4$yvM0Rz$5}D&Z>E(8M&sUw;|7R
zqI$7xBc%>wNLV!vca<s%shwI{q&UBAGg1-A4crAQ`~U{hzS%U{zJ;B3x(B>D?e~10
z!aWcDqJ$c{?Q1`m0!;8Kp9-e>2{oHi>6dAK<rObR=5w)31+kcZrFbm$P!7%5kpVV-
z79q>YrAXQmc3o#mf1falc{{!`5>ts{i+TC(#1Oc$MwYYXmc$$s@=QkOa8K8nb9Smr
zUa0A-Pqe*Wmsb#+^DNx-rckzf7yuV9k&U2Pn)(S&057n;`w#RD3_3-TSVpsORF+%;
zFpT-HV9#=4ly<bTzWKX|I{AUfNQv1ZJ4gS9Cp`u4*JLF=m3yWR(3luGJlXiy=_9;%
zyE6NTh?9qW1<{H)d8q$GVpnyXDyoL*3i3A_u&4G-aV`<78*cZh3BkM9Q(uyIRB}p~
z0uh4SOKi97-99uZ_Lh`B^btt24uoTQjgZxvX~6=D%lhkcCp!3evLzk#=+DY)XQjF`
zvx^p4&Ms4Sg?@m)=a$;RFgVpbckD6E`WhXn(iCFS6}sx!qof2PMdS`3KB^a&{jdD>
z!~BYr-yaTN?3j4{`g^&;QhMH`TRI2YzX#ZQ#%`v7;>WQ6<Q(1MOa@Pn{`&H8xygW^
z_-cKdGI#M?{_?q8SNy@f)MbTuu9!cP(la4XSt-65!G?-H{r&YOb-uXihZh2CH}Vtj
zm^;9A$?z+h2O#cLaQ2?@F~pA1Z|}*8XBy2!ps^;j#Z%jKcS0WfTu#e^Wbh^NN0ppf
z)-kz(2^X?_d}%gc()S48(@8F#wbykS?-3P;;T1l#w9hQ6biSdv=s+&}YP6=^*K#$u
zjeIC5BJ+og_f^ISd)$Ot0AE~TL3XLX@Ua7*J9poilJJsSey#jQXdM;Ql&`1=@5?2*
z*zn=DAhK3tAnHZ0MVgvE^`FiHtW@I-)L>)cxM<do9)#Q=FuLnkAr+8R+s`c?#>$vL
z>bJ=Gj%o(~*MeBj7dKx2kY4hECyXdJ|8m|7R~jL~AU#4H*}=L=TF)fe5zf|<pt%!r
z#}D4t%t8Gp`!;!G#xm{T$m*Z;4V3OL;7x<Xa`Sa2k`D8)BdhoQ4o_6L;?W;0+D=%m
zG7Vlni-~Muco+oEefS`%2LftZP#5)Jhwj_RF{Rx~s0jWE%H4Nh2<GKBp<Ig$ML%sU
zQT`?!RpQP1UF)t@6-l?xAC&Row^yW`qqX!46MQlIw0D1_M=R{9zuW&ZiWDbB-y(kE
zW}jwaLYAdqPChqdz4X=Qw&2|KF1P$u?|J2|UB#)Q^!DK(Gp!fnH=xoAb1B_Rmyy$|
zLB+7$c&1Ij>gBnkw)P8fuW7O7wi87SxqXJY?bXP9gU~5M5Aantc-<0xKwV;I-x~KL
zfFuEuIup+nwWVi9W_pRsC(0Uk8WU6i$l?_waq@aV{<ONFL1#&Y%}0kR=4tOmExT(d
z>mot+OR}z5h?&YGbBPxWYwfK2wlC#D!=tBzcX(NxmVvq^`@qv@vVA?UO8O*D=tgAp
z9&u3GSRpR!#vz&siL&w-wwe56BE6m_qkQJ~A*SlMvQ$DaGv<Bz*b@E4+iS{fk&kuS
z6||vM5sk5$I>Rl*EQ~Y`Yf)x1X0dXFkf8##b-{mVWRNI~b+WyNmI90W0B3WkQAubd
zoar`dFH_56v<d$vjNkOWog+@wu*OkBBKn4LGc4_o!`@s~HW}I-$nwzP3;0G&COgoi
zBNXK$j>W+ix)VcYXI1{8ggfgkAR6(D-*bQ!)*bu{q;iYE9!=M5wxmiw5Jt-N+X}Cn
z^ftRqRmReuPLlb!x_AC3LvO5T^<Rau;`6kwD~p%&gahHUzMURjeTus$KUuHMY;GTv
z|3klXD<j#}_xc{=Vk%9W0=Ses1b9ABn`@6@-GF>z{EaEmSApT{Z^4-2KPMO6Ipq1M
z6LD%Ko96=^e3;n#$99BBxnJ6@e)vsUb}dnk5BY}})SE{Vht^q!YowGVb*6Pqv=rfw
zI}|ZgwQl&|{jI`jicdNGuT6>7sfG_PF%Oc-D}A!_9t`Z+NIv?J^`cbL?NI+Irv4<$
zB$=j5t3;|e<#K9ERPJ8J8KgId;hv#T@f?ZqReb$|WnL;>I$e%q0mCb94#t|5;P?yj
zEq%E=MoZ*#*al|JrBLK6L9Q09$>?Qr$l)WWa}A!{q>sTm$6m=t7Rd){8$tW}xTggw
zk~h`FQy#3lXQ&fqj(Cd~^VZG{gL1)gN6FDb#3LEXrMB{7c%Sw+TZeanv9>OQj5YwK
zL)Y*atrjI#BfluN2p5*V>V-e-8*{zaKW_a}V;#9hm?(dhv^x3lso(|Y)=`C&zf&hP
zuHt-n!$aj!@^`0Byr^Q|Fz99U_V3khYGSbnR9bg4d9RB6jmSMB$Lal7F%Tl*5dIgJ
z!z#9F5P+dxx3z>NUQ5khE60~~XAdck6_7*&w2{jcO=I_Cp#itrRAD0S5*hrClPryf
zkEiiNxx0_e^czFOMoy7W6GI8>At<`7lvh!RfC9Q}1ogm+o4Vl^5LcMYo4CrtMDX!A
zH}=kUTKlka_DsGEb;C&TE+(HwriWj>)W_g>AKYn@=F^()4@917`RLgEHp(FZKY<e6
zGR?t_r+xhp@h|l?qp4nP{p@zvN;%yMS9;aDD&1(vM(oQnsDR=I9;)XUmy&^H{U|k~
zBBIV(FbaOm_H0;K9(D?^2oJd-CGu4A*aDX8^MtYWyU>{L_<qv})6^F?IMW9b@dc&-
zkWa2|$wl5_Q6kmimGcTVhR6{0>s<XH#Zr(XQBraEDa412p6DTzbvC%&XkB$wu?&B@
z^#enT#Qz%9bTys3_dCy@21s(Xba$+8zRf#4c6H4LHC0KV=2kCSqr9c~=-%{+RsqYF
zSgCHNd~v7HpshAQ9WYU4P%oEciHWZ1ecerM=pGlLAHT|I>cvmLDF-2XkOkAA=&F%u
z)~$L&zGeKtX6FFTmNjN7Su@Ou_huOtcMtf&!U`}ln{`qdgH7N0ef-9*Vyo`ov!rk~
zLCp4%FLaK4HoXb(_ta{Ue^O4cInm{|1cn#BhJDXCx0=_Yh1ESG3Xc!XSYipJWv(pW
z>E00$2^T5W3*8$CIvG)|)nK62(RFb*`SwPrfff>U@522?_?Fc16P>G>mq#>Luq(5t
zfH-eb69}Gq%3~ViEpt{Cp;LN!M!h|#>&Q0}256i-HI!JAZh^w=o)3Rfd=P)hH}TZp
zn8PnJu!t)|0qOB3H#nHCR4CEqYtq)|0QUPkpjR7V^|=G+j^zBXlZ)yjfn-_v+s5I^
zFp-EdqK!{<<d@UrZ3>KNwD(1>7;e{7w2Npsa-45dbn110ZW-OsGJ5mAApd6Btty|0
z^aS9}bS`pQ*<fN^pu-8R+T7SefUJTRDw6brlV>b@tA+*GSx~noA0*GMSq>%?Ne$f(
zTiFQzz&oJiV?Eho6(rBG4tYp!<;IeI!Pw^EZ%tgS&G_AVr$LP+%wzbAkz6ugGU>a6
z^Epw0F_Xv7c}?R34@Zfs$b>q=G)#7UC%le|m&*NAV;{X(_DR}_tiVY|I29cXSEy&8
zpi5`IDZWN6Z<;@mv;@yKrFQcxv?lxkc_ppyy-<*yvJ4N-m~PYE*@M{`Cb-h`yEXDA
z1slwvF+o-jKKx$a%4IdjzDWZg9ZVb=$SF8o;*-Ow2fwLjRa5@edMvP@Ddin>in6X$
zdT?}x=1ZGowJYE>DnnZ`#s{<BcUFSFNnvuGi}L;v$yVsB)<tnwq-oWzvlKuwY(HRo
zSC0<^r|)zLBAke|gY>C|{-;ZgB`LD7$mF^3<5xJ)Mvm!>VE;u=5I?w`pFuzr0WfJ|
zj`r2ZHn)ZvfW)33()0!#thG>2bJNfUPSbTZ>ISrGd2cCDqQJZ|Hw)}%9yI<;>v}xo
ze?2zVfoyo8ZU{b)lG1r2r!&DVML*blSZW(r?+H*ko=R;SoUE4nDB?{2r=(;ur5Q^T
z9{s%tx}M<+jC;0_-1CoKe?WX5r?DRY*8l_+(XV><98PcaZFkx(X-wE(+39o$P>8iC
zxxP7WZMze#gCcufAjC0Be6p`C&R*`IO5S2BxdwFag)#DIy5%=w=aS_sv4XyDR2_aE
zr5SoN8@mxyP6*r8vzRCIOc{4hCKT<KvIy@NPmr#%%LTyCnt#KY=%Z0Gl}G0Lngpv*
z_0G3^#4fUtE&oSE3aua}mYwnQ-Ljc_7O)j>osfq9)!m?7i;Yg>e7k(?j!&)L=rTH%
zM*p5F-N^Rm|3FCXtHXtIudmbyW8kTaC=+ht`gfjr;eQ#-6WLQO#-Bn4<|Q-XzpzN-
z?#eXjQ~3Co_i2&uJdlFH4s9=}rxX0fgQ$N^qMe1vh9N%(+x29DoTdT98&JXC&%eTD
zuzyljhL<cG*qip}i>Mxw)Y5gsHQ57yvqPue+ozS$6@dO{w50uag>~BFkcJMzxrh<3
zA9b!VO&!Sm<e4(e)~Pqi4dQeHeDJGNfsb#*fswF@KdD4s*z3pp8PS6vPpLOFXL%Es
zExi2HH_WKW%$Z7qRkLV6X8bDQi>M5jN;8jBg&1g(R)c$ZPMqUzEF!QWjhxM{w7Ql$
zh%y>)11A<v3HIJ1Joz|WZp_5{@MCG7p86SDqh$=a=;BAyQO$PT4?g-26m<9!=ocG;
zk0$`x#FJ?vm$fe*f+H<v+ogmSS)OTf@L%ojd|5gJa(1yprz2TU`Sn7cy$Y^LZC473
zyEKJ<$}j8s7-Bsmrqj+fMf6~gl)7GtG6!|mI!vBh2)QjN8R&WND|?a}Wk{JU%|=Z=
zewo>Ai5|M_@M7IssVrX3-%EJ|_<=ra1+$v4S~x;?t3<24inEk+#FBnXJJQ+xIIFI2
zq03}Rc~!3!GrcF8o2w0TnQPPQnJGlXE{#}cq5Df!iE4CSyS3^0NAwX_Qp<y=`9Vqs
zz_5K+y0PC!RnA^OxGu=QmmV!Yd|{jQt#gR!D<k9=9%&88u>d<*1jq&Ptxe8~ny^bJ
zWZB3UA1XleMfYx{%GSJwY$9rjz1D(j+Wv{>M4tD{4ZJb-iS5lIWR&7Y%23J)eD(H8
z`8+gHAtxr<MrM`6Bxo*ByY&X46X2F~>sco8HZ2ihMZQ|IcP`p(k#c(K+;1Ic8=R(v
zBCW*f(p-@(NUQ^9Ajt7**cD8S87qL62J*Yl6GoM~ecaQxQR$wY`~WLu`U7csRE>a2
zxVy@uNGG2MbI^Tbco(1s`+)VWC}H(qJ@UyBgA5G$iCb@#Q4dOrjYb3)*P+$eqr?Ok
zVnM|&3cDD@EE7L*r~dw>*}y%`&)x-Gmq_&&mozK0h5uX(q6!s%8@PI&I}uuxY@GuU
z3_Q_CMq&{&A%*T$&LWD}R?(XOO8tH#?qgYd?Fwhf@drMaY=zN_>@H`rKJ)$-YB{_q
z!^S{V1JjYs07(Vv7~V5^Ql%F`c?>ByS=^{2jWAj*U_y4DEOI%P(Z#gzNqcmqY662~
z`Yghq+wvyI-W<3(!>`UN5g)iGD@7jWa==FdR4f@lGwoTI5Q>w-B=|xAz?p$iMjMJK
zokwihW&QJUiB=lA+bDI-hT<JF`Tz_S=Bvu8J|K3%XJNu;HKO?Ja)Qbs7$854<Fk!c
zzXbTTNHGW3dj%AGU7Atu7G=Tx%jYbNB=r0;sDBOD?^vW6Oy0x?@GAo~EJc(^n5~N|
zG~YbDm%|*!`8_6pcKGa;`67(s3ZkR3_9U5`!<!o)q)+L&oF6av=J~llyjW$Vm7_Qk
z{?)eF@_)l5A=QgPYx6GzYLOW-m3It8h;8@bV%P2NG=tPdJ-@?}bGI|WE6Zv&L|P_h
z6gnmg<Yl@Vo+f&TwdS+zw|s%WZ!v6Lfd7M9rJb2sUF`S_6fRnDjca3ev`Y7VLrFfe
zAT^wt=01`<?Nl)_O2sVw>%8*{2Rys2rQDsE=txO&$AW5(`XGEaoP3Zi&ZSNpEdJ`<
z8I=K36Ivc4X0@Z~(;-Pzx<ATJAlG9E?DCLhe;chDY-9}KNnA^*9KuM=rLI;$DS9=?
z$Ej17MbZ{r?(NU>(XYDHgv-pg3rmzv8s9_5mC3B+inKi(i*E|8c{UnCBiGt~3fMyZ
z{4n@h|4;71AN(80nI7>HG@LpOaBpr5mioT0J56(;1+L>Wily2GPO)B9M&=yY4I6*Y
zo2o1Rw7jQVe}$&W3JYBgLt|pz=llCvv9~}+00^^)x08<w^|WfGNGy~XzWx=6W{ESt
z1q-c$Z4!>~7i`cjY%CD=_q>0uMIY888Fa2^a;VEa(|6_C<P=H#C#(}|0iRiE1RyGe
z*TRF+gE@zuD#qviAHY|>-oTVKLDpk8%CF}i8>r@!s=413V6w4Sl{<0;0o)|w?wAt{
z->WUxK2=T<uB1wrURa<ROQ${P0Ea&{8o)##vXq%M5~4>LdEUis?k)k;zg{y++Yp$)
z8IY7C)G#Vlvp>?%%r#&6$(I_#&d-$ysKKh0qg~hV_bVTH&rhBwVCnHc1>R8v8Ngz8
zZD=Zl9Gv4fR~9Ox%<qS|hP^#N-PmT0PB9a#m!)o?bL0?aJiL|Ls6uAEGoa_=@Fifp
z^z@PD9v-Mq>SiZZM6WPKc*`t(&;w`EJO_Yf6N=uuc9wsX-HTJG;^U9-n6j#u4l<y>
z>XAEt>U&0<lf)Z}Q3j|&tV;bBP}ixpli<MrK>Pl+)!%3in%fHn%Q!`%FW{$l<Fx9S
zNF*MK8yaBOTMZujr|T?2pY=x3+iKb!ge}^|&tbLB^YD-3PAf&Tvv3LkKqqybltEf@
zn5B`^{k{%8eKOFx{*$)|<8+tpoM<<plD9o%cpSxX&8GI5B!$sv#wSdUuXJDjr}7!Q
zj^x@-EWsR9<NtaI!)HR+*9Dt^;;OzX-DV^&?IO5pom55Su5<5vqPgT`A`V=r4QXlP
z%KqKiClB^=6v^<V9uBJt+?sOC$IQp7VCspl4<XjnBxD~`J=)AlW~c^h-2VersrDq8
zL7OouKkcQ4Z%!dI9oVpcS(4imOsu|popHZfgc|pRD`(e(XljHeF-RI`_@5O+CE;;d
zq{{u|s$KotDevG+4MDr@l+@Yehr7?5!%jqGLvH0@ZHxFlN!YA!&=f|Wplcp2Htd82
z&on+Ah2?7f;a$_b4w4iFIFV}RX=#?xJ0Lm8e$m^yuf%KEezTb25z}FgU;xt1Y|EUF
zpy=xK74?$SVq<9h`7qj+OfaW{V#ac4{m%hCA|Xo`&{>R#uayh{e{Fx{PMR81+7Br;
zT1>Py&@kTvSEIkg)}<(r9qvVRY<CFJFM=Na-3wk!deIt*9>QG$Or8+4JItTSKC4Fi
z#OCdbAl)><=@rabTYsjoM}t;4&MBf&Ge;%uGMIgla)SyPig#goCF^**f#gv4=ObXV
z<>@&`i+r5><#@MI5WJ6NTQ#z{YSE!Vp9m3eEwrfjCeA=fhw6>UrY!^v1TR~J)26oT
z$lf*|e93uT7OWZT5LIlVCHJu7ygFeBrSSjhcSJR+-c)HTx^Q|OKv68Vy0hh~vI6lY
zU6;KwwKIPk^UmNzoGjdzq{^q-eTolwf{5FveG}B-s1OHbV6zcbIX{T_SXydNvY6yM
z8PG;uryY}$^m;$i8yFtBcYqH}3l|;B)#dkIG-@OYXHF&BndkqHJ4`Zn*Uq>-P-Ov4
zx9^annN|dEkgs|-uYCnc_ChYIGLCP5LtS0)-;KeU{DIEx1}+m$%y%PV?wV;EM;~b|
z%9^f<7t$)9`tW8w%tki#g=lr}xEfVn73fjr4dVow5e7Cx)Xl1dY<}C}@i%K02f_(S
zFMm(8vnj4#4C>wKawq0w?B^o6m(-f>%W{Q^gHz_fS_I&T9ocgZw%nn&`WHz_q_5oJ
zp*~~)tCJ8Xm9eK`&m_ka7<xx81~7KXTTERxr$JYQn2?vEVe*(?3}t6eo;S2{%~vCa
z{=S&_K+r7rRZt!G6~Dcm_`7&ijCYqjKEUsNB3thoJ}2g7^*dRop1Kj1bGjd54=!FT
zd`JW8mhh6s4@4i(X0!r1*}e`oKMT7;E{JQ`4U{zPj0^u|zV{9>j`&=hh8xOq6K7Y_
zV|kR#$9ZIk<D4_;GE+OPaq^myDaJ~jZ30vdoe`aUocmOupf9wI<`OYfnb<snKWL6P
z<u-Ta<mR}a(hoL61dAhNfR8>3KTO89-(&Yx9eCIb1o8X>JRl0%HfIG?bcEHd6WBxE
z0!yPl<PT0^lrR9tt(g)Fv|+Ra&4A`<(bj*0fum((>+hL|wJ^y0bL2ilr44W&Qx#mI
z1l3HIN!V1XyhYhSXs;GUFScZnnU2yYsDU1PvsZ2Xm8Ha`>Z+`XFcv9djM=F@_VYgf
z9e~H6Z--x)wwfUq_VuP#Nc}W^A*R7h#rpENm%6rm%!<%~o!wjwA1&|P>dCXx-RZyF
zPv9}IXqU6xJpi)1YQ&GVZge(WBR!-nUE2$jy?Y}$%aindNceY5Xe#7o|A8N(X}La|
z`gx{Q44&?&Hfg_xEt!AFOJbLL0%x0icPpoT_IAM2==Lfj4!(n(XO&9eIxWfJ(fijo
zJsv5kk4kdPCu?sOVRgf0iqrSSF6d+<bT0gJ9DX+mZq8N-ex$Py;Kg=#&hv<6<}*76
zthaz|tIZ6^w`R6Te&}dVlnY(82rm*A*u=>)`#-=rXIi64sbOfh&1pcqHVO?f{25HR
zGyMPo;@c`ti?PlB;4Pc-@2aQ8jbvN*!GXH_PG3xsh5cU*HCjWhdTJrU2;Z~0??B`n
zz3!SV(?r+Stjf`~I@I58Yj#ojK)CR9i5OvCMF2r9?bK2_`G<EoMPus%oXa<7`2`o$
zOx`s24s_SbL`CFCdK*&yede|DNHZL?t`0Pnq|C$u4&b6ygHkV9=DhNHqf&)yL^IoZ
zCPF&#!dST1@dD$<(2KnLx+^#5OQMfu`w!hUby2WK?c4LC3rKZ#*oOJ)kvuSfkXYB~
zov=$`zw{GyBkY5{vHkE7-r%#O=2wxxB_r3ee^*_gDb=8%A}Cv9Fiz3?@N&?|rfdhI
zes+)Y6TPKk0n%(YDdM%I%JD@&+J$#Jt=L#>P<b16oME=J-33?268hKNBCW|MPV)Md
z>a@VBiJ_fEiUtU>>?3~#$u^C`RLnNA^4okZDLO^pl4H4Q3BERmd9&Os^n+nv(+}(t
zw=6Q1CO5Xa$r(OeH^16{xDi%ehZ$PR!3Aq?gh=3pJ@lZ`F|$Xh@nq@uB5YfwCn+YY
zeAJmLeoU}j3~KN*sk-k-uTLvfzl7FEUz|jT7n$j6ls4@cB-?-OK8?;Y>2<3fps5sT
zU^4?!bj(s?t^oSL+b3zc5pO5MWUYuN=MICvqsr&ZVg^Gr@7Bm%nmc-CevY|3In?RW
z9KNT!d=jsHd+=4w>M@hb#SB>=gU4Ao;0KeS+61-vIyVxv1=ALX{NW?q&wR18Q6U;j
zC2AZo<HU7n7!?I<rV;Za!i?mS4axDgp%(6a@%gx_{L~y!fi)!A&tZ^cWt26%N3CgU
z((VHIrzfU$7%t7X8FPCK?~jdsO_3?ZqIhXO{f#|Re7ytJXJhI0%qNi5iJkp0Ytk|)
znFIJ#;p+q!lWL?#fZ&rMO9fz381kdh`)^<FihpFx-b`E&T27Awp#OQy+M$@%cl9X;
zwp|)p&E))<lQLq4(>04F8WxR!_c05fu}j8b;_H%+{Aql|dC2E&g7Jv0MGwe_X!xhX
zfX?YM*{_<OK&bXduBO<SDbS6uy&E&jw@71-P!S>GU)`IC*hs7`r=><;_Z#}ZUxZU&
z=!C15``7m+`K9f7xS`t!>s8}0^1Tf1iKk)`1q#zSM(E9Wk3g+Qjg!?rs=gviZ%%Lx
zGnO{8;z1iUvuG{vjMl3bOTVyXJ^qK7hnD#4C^q#6xzlfUso6sX{MqiAr?ligTgZOB
z_zi;P0`ip!Mz~9#da{pM=u@0SJ7=QE!=y{_6~$MX#en}nj!lEz2<5XqRFp!+aR@_i
z1j=o<9n)^z4*ST$dHo)6k-{m)2G>d`wbxMJeR-Q_b+;XBei?C>vJ0#)ODuseP`x?}
z;~E<it`q`YwRqidc-B5xpa383^8qO(MmDDjYu2N?Da}OOFMCr%p@#77I!GUir*HcH
z*34h%>EtgADgfuDcV5eA(xw%>=f)6g&?%iN;i2-67g~j5ph5h$97aPbcjlz1-k0`0
zn%b(R$$M(Hoy~CPUCb-BNyPGNvTU8QWY^niH@9Xo!j;J;I7qhROsNXbw{T+Qv$3KP
zof3k3{?DS&koSjrRR4jv=P8D7PHKgN&}ki&UzM8=Rjif7xSfV#Mev;?#|ZVUpW_UP
z2lN*quay@`?df;bQM5#7<zdZHc9h;4PAxhYX4(NGrqT6VF+iDIs<ZnJbP-B*fSx72
zzCLp03Hc}NJ-hwzWio*NG+i51D<`!*MT6d~czFGm)%Pztk^Km3ksM75;xqUF98zVP
zDr|32KNaTh*j%95L_Y!K@06YdRrS=nwS!ViEl_;hW(;l&xSV-@`1TVXGDiMm*6x8{
zRapH%_`(gA*O$dkEM^bB;D>1#x1x&Xxe^Z}@YYhCaRo;uAs$CXAz3{$a=JE)78HF3
zKaUzlZI<+oXw;oZOvETR_qcrl{RbKtO}n8iL(G0%+O!c^UKKMT$C!L_^ec&Qv-qat
zyGJi4fd;_nIMWn4K8YG-_-ai_Oe&cTzjI7;<$oY;65=VKP(I6lC-9Z%r&)U1lj+HZ
zxzx73=>BPS;|4{sci{IJYQqUTf*P>UUYHWAxm0Ebhq){7Yt4m}rF;2Dk?0eCzG)jr
z>7*HnqX<*kXsSxsbrQ%K@UVG?y?2Qnu$8}xO+Nt4y9r@2kkxNNMuZ=qgNI64DkW_o
z6(EWVH^MfWDH`$&cAvXs3gNXV%QLnxcx6g8;e>2UzPHE;wZ5%CtDe)4mGuLS=Kb8N
zFS4ywdQNI(^^?>5DkxFunJ~&%-|m%T<T~U7>91%ikjkgIC|Ctfr+2;re91&=Y8M^U
zr~K?>KZ!cGtBs&+Y|MMOP(^hN6~6pk)Fy}e6*8xF1FWh#n^Mo&>EP#8+Xi|t=T>&(
zVN7xCoQ#iq5bS^E2sMg3bw&7MU!~@KgASNZ583Z59NDJR83KT9F)fKs5;gEiy$~l`
z|9zvXMQ%WTSl!KGPka5gj}uY!;<2X!Obx&U>vQfi(JZoL{+x<on9-4QU#V0=Alb+Y
zn-9NC;+s)y;%_?04wVQ0l32>MCVSN96wWs#S!vh1^>%zMNiguJFGdau95!!!gxy%C
zd|4^|s@fX|pj6Hsj&^oJT8Fa2nvotgwe=;)fN4*c?asECL0Cw~ad6f&Ws(Ee5D#uV
zMrlIaSkl(vzV*T9?6|o`6wWgF_QG-7Zy(%}w<L#b+eUNgf-O_vgJUf>PD$aq^Hig8
z4iu)?NXO|aH0MjBCA_)$Ww=&lQ`86Z+FF}L{7Rm%a<_vNBfO>g>zsqaWQXoEpV`-3
zjyV~n2Qy_g<bL9r|ACUQsb%s`dActmf5$O=uWQS}N)P`qOKcKWgcd($taVzDLvbRY
ze2s%t@Y=8jwX^rVYWR=UfCZP5f|25j%B=nCet_vAhiI0NZR4>0+GFeV*ii{-wylw9
z!TjiimNZG|zzBleJ^Z1mvL;{q{O1N3@<XD9c-2~vCV~zi-cyeI{$}>OswV$qh@*KE
zJor`UT-L>}#onVuD)q+n-Q(n&>smLKHB19zPgCf*7y+SF{fMiHH)SDr5;h}hLo)75
z2b^=7vtb!&rGU!F9Z5z*y_$SD-FLQ`ehKaE-$@Sods#udEpiuk#V!~ohh>D&&EeEb
zYY|Y;`M)JjL)038j41g?{aSvc>^_}_zZoPtrC1I47PPdPZd4|*+$M2g21$I3qj_pY
z`f+i4GZ5Nu^n=e2k4lEO=`(j4O1IuR$7NR;w;1b3nn`i0gloGcKLTh@>2PAG`QP}1
z&%-@q2AZKvu9V(~8LJ*-1R&IE`ze9p1L^6s-#QT;tD!u}7Y7?lXO*e;!_G#_3u`{%
z%9=Jb<Y)I06*zO=vUtd!{jpmn%uP@^$MCoM?Ezc=y+|Sr#Of%Qe=5hh8KzDzKopHX
zqE6k{{pF_UxJ>+TJL6;yk?!cjALK!M-J%9StHZaSzdP{hg8p15xVoLZ|K0e1B%O6Y
zQ}6%w2?c3Tx`u#shzz6$DBX>uN{&tya12Bdk#0r|iP7DSq=585x}`%JHrVGm-{12e
ze+|w#<39I&y<gXL<y}S_F`1YDSpctyn{)A4I$ZWSWN1aj%~vYS7PvoEhX)m3_S01x
z6MaiG@d%z{2EEY{E_!sf=d2JZC<Uc|?EpaNC{5dg5k_BOtj0w`)@PeHg3rgwsEHl=
zp^`aROj#6Una<eaLjaSncdIAXII4ri==Aulo?E;k{e!8<TTIlz&UyFzGbG~F7KQn8
zBqz@_F!v2|WEiccVkl{zcwm_PX=C2{fzM<s@~XIVUIC<g?<F<~yaq!N$$~$vs22k~
z*S7@D2^KCCAOh|iRYk;9=7&EP%Ib%Ifm)i?jZRO_#>~Z*>#-NSv%LzGHh~<hXSReF
zbKW9e>&r5~Q#8TNjV(>Ff?lvmxiav6o?IAzm{zL1ZE{BBHlZqW@$<)mrNFxZJn0Rd
z?;L^^#l^^rKo5na6aO;lU-k0}$($<XtJMfRJ@>kBVIS44(<kiRS#jiN659q1i~}}x
z0Sb@(pJa0@B=gr!TP7BB-qFV&c)WB9u6PmjHX5(|(%L;^t2r8OVOzELS69@Gw;nuO
zOdMSO*l1@x@t`5J|4vt#*!{XN=V7!AU~_arhuk~8uj==W>bBP$X%*=>!tto(WRR^V
zQP*TV)NWfHrtWJve*jkXb2e$zD53LMk+80}l=T<n$$7#SAUCa=(KD2D<0CD<07kk_
zJh*WKwxS)*O(PMN<pEC@0buD}xlpwS`FpWL#I_y!{JO)rZkrGtSp%Gbj}^7(?`5Mx
zB!`=Hh9ozy3j6$qc}D?q-E%W5W=DNnZn{1#X;2?%%4Q~er^mv=UhlyYQT0NKxT(w}
zGcnV!?IiK|SdoqS7pvDC?H^N6wC~%kHLHmHu2TIyh5~idSovogU~;s*BbR_)yUJgY
zBRk$%6VnXC)Y!TbY{`1ad<aN>jq7gywYk`Tc(pfE-F#M|#&bMw^zj+{I{bp<B#io8
ziY-MOC*be=5N}^&(`A*P&&2w;1bJ`kIH)v5#EsQ^n6wQK&Mdbfq839juOYDto70K@
z4+o~d<p?pPj6eTP5Y9%WIh0NN*(no4+A>v#3<}-V5#Y9>`*kHD6Xg(7N;#4s*0ncV
zXuBur@+G&2X3^NyiHVKij=yHtpqipiLX0j4{m|4p;($uJ&jxFH@J5$v*Fd$@b4KAd
z%;<YW;346BTKCh*r`u$EE<FKCUgp(1-X>9N*Q-=Yn(A`nvNVL@*hmPomk$sp^@;I2
zd9PMrcmY<1h;Y#E5HWeMRmGqX2C{(0*WQ93;BO3#x=5Q!nF&*hFB*7<rq%izT%ZD)
z<XXZO=oqQhSGYgiI%C1Fww_$<8tQK$6VD={NZwQn19uYO)TM#6$P)fB>Xm88M0Dyy
z_$fH){FQjZ2aNG&Hz~!Yg0q#oI6i!(mp4f8R#T(NPzv#`!Of`dbCg2TSbFstFFU$d
zZZW3A6?R_?<zyw;!N1lJdX|HURCV)u5_?)gL+$9f4kiG!aW>5|UtINv%YtX|lbZGs
z6$6Y^T49+$Kq>uN#D93!Q!}B`kkf@of_2{zMWE$gL1DL$UMKHaa8gb&(=uG(g@BwH
z@zFLNXl`q-3)x?hP}n>Irn>^;TMKXAyKRT*K<o&I!gdWMdon#xV*0`RhWG{MVP8O5
zss=x|nK0-aVySt+vJf`)<0}6dKKn7eT&nA4HwuF;kn1oZxkRxvi^Xze21VlebbbCC
z!uAa6P2k(+SfT-*lp<m!{DaV2CK^a_CK%RKy0OO#n$o_*Pn9luuc?N~0iM#}2A&b#
zP}Sc)ywH9q(b}$7_=OclpMmxZ-kHWJWf_q?v`c}6`|T%INhRA}BkJx)Y{5wxW|iDn
zqd7~Ult;N5CuE2>PqO2y6=KGs!=jFpvGTqu!q1=uRJDRxNE1{uEF0QhLy~h}03Vw)
z-i%}RCX|*&`EMZb44XD+CqGA(#P*}q$wZm%p+9j^ZzIbI1<MTIso){f?LPA@;&G-P
zzJw2p8E8CylVVec&n58aG?|V}u8?bl@Ly3_{J7yKJuCgkE3*EHm9+N<Uhyk&ct=fA
zd(RqG5xRi}lxvXdg?<~HQKBVxP`pu+e!VqK<+H0Q{@Ht=G*W}u<8eZwQEarlBI_aV
z0{BZF@iA3*^u(uN#~fk@uizJ2r=baXZ2UhGk?q%pDau4IjPMt|PmRKf{|T!yv0Pi8
z6bj;J7Aw?|d+%Qv8*Y1Yi*D$M#;)>4`a}<G#}bZ@KVJCiZ{ZbH>vf+zkBwN<Rd>Ie
znvcMA0kmvzW9;ZWl^do%44(9|#w+UZ9=!m9f6|XK-VeuXpJg>WNU&=_VColr-~^JJ
zE?RssA3ahp*(s(>I0<-ZGX@mtadEU2!p`;!8;)4G<0n&9*k^`*h=2qspdWZGEs_RL
zHP$P#G4PT@Q6|KXS<Ze$)sB@+Y0=y&{}AT~{(0<44LAXIL?OEl@3cp*DgW#dw<pLz
z+v)!R6;<!iY1)wBRkdYQ3gLD1bK$)@F;5d(^1zxn-$W$=nQ+XM(QmtuJqT&Csmb42
zyIn;ZdTqPmxI|M!>LJQ*e)4J`EnkyOB&2`#JpX>bV~7VHs9f<+Lfq40M2R)y>2JLP
zFzwiqFES9X${`+^8w?Klwdu<!LDPjJ%4gyNQq)L>e~F#tY)qzaB|H%41OLwI+|%1I
z0M0>U5;-Jo2cnpR>@?ab$W^`sWBizcq2b5lWij1Vb*G3-4_~zmrj2ddr3y%loY4ax
z_#ckkRoz!qk1Z16{@<#PjngxuJ6)O1X)|g9+Q;fSL_N0eY_~PF-2cNfRj5}_GCI@V
z2500z1|Dzc*eQPhlKIYdD9_Om(k;-4fq?eMrof%eKrgf*vK&w6>&8_C1!JO|Zpb!@
z@6$Y!(h}1^`zy(lmuqcd@yFT^ESCNMq8RtP3Iih2mY!&EAN4qYB^;lIHQtL|8n{N_
z1uk*^Dyxy^IJeldOXrP#GH}mJ_K)D-C3eZKrmND1_m6&ZJR7EAUrxermT#}0bdQ(8
z{1GqyAgJ3$X=j)q_KRz#fg5d*@i&g<qA2`Fj1r1#<RY2?_T=9l>7&yQSGGU*!fa|Q
zUParg!i8Tv-D;~ak8(3fb)|eD4-M5ApHg@&FvyB_`><>HtThT*PS!)H%LQI)n`Dyi
zK~JbINb!_>84H}QRuXz4hcKKiDovJaTlER9y8v=8C7biHqHKc1Tn-Nr9NaPCEo0;h
z1K=GNmZn8{*KGPe^;Mk2#0Ti__Yq=e_N-V_fA;Y6iQUVT_&!nxC83-XV+j@qQp+LA
zAkw*Noqt68`Yr~azkH7?%6sRUO*yGrV-_9r=Ixs=^c?R;1$s^MMb11T16L!zAErdU
z%SfOM$k{V>YkK(0`_QIDZqUP;Le37~j`2`G{U|MSm=v>W>bhtlwuHS@m_yy9*u}fc
z20o;Crq$=TgsfYL&7EQq?6FmCIxop})}lI>X4&K4a>P+cM-#9D^+l2eH~s~lHTWZo
zozJnx+*AMIQD));P))L98{~AC87OF0q^Yq0-MGsJ5kP+kf8!7y9H?-CT`lE>!cJbm
z+Tza^Dhu$G?HVAb`{FR@Fsn4^L@4oY{l0qlRn*c;;@rqLTG>~5?A@WUCRPqYc$moG
zIY4lV1?;7{)E$iS8{|Nw6CO@*a6aUTNz<EnPl7vWm$e<ss^(`)Wk}4sTOBD&%S2qo
zJ50SgrLcDt48@^zzOUY`+$nKNRUkUMF(6r?)-LVN#U>oPq4+DDc)1hwMXaC^CpZ<W
zGh1qFA1i0^SOFCs`90JVD77NAq#5b`93-Kea?-N(JU;ZeX*z9&GfePdgZzE|)YmsW
zU)0(KLm3vh>Tk#&K4%M@epUa#=`BUl;kC)PC-47O<j_tCeb_pEe5g&@ZM@B_RdpC;
zG_&r{_+4}3uFND%KFt<!2V{NC3&FR6i?q{zY2$xGjC&G~6V@{-s@Xo6*}VV*90~9D
z^azFYAB9y;gm+J>cN6#{^d*ElgJ(f+{+B))zwhhT`Q_ywdb!xz#m<^AO%Y)+<N-G9
zK!qNE%_EiqP9GE^rtQ4xVQEB~7sJ0VWbfcttQwR_jt<?F2cvGi6_1Q0chts8H3!g=
z{Mjn$a(iaF>O0(}YZc!8h_HPv90Kq~EEIA5$WaX<yU)Q?31Zy{GL$n#{`B<gV!tV8
zL&R}?_rK-8Mu+>#11H9iaU!#L4=LPmlY3zW|N4^e>23^UUO@1LM{WSt9gsnQDc8jw
zuVtJMCJFwJMv+ciw~Z%_YRyQsQPZo%Pb>ReavIb&-GD4AvK9^m60tBEk&1E^CFbih
z(`udI^_H5@*c#yXy!&B(zTU;A`(ELbkx_XW#n}t)5!_h<|KeNzX`1jGj;{Ss)8LsM
z#iUKF2}`<%TcQugn<Md8K8x*h4~M*#8cqy&z|q6l;>2NoUZx$F=*3ejcc(*>$L_O(
z+(C${Fz;ci)LjERWp~Iyxb~tH`*h8zWq{qV8<lV5fH$g_P(A9YOsL6G!IXz)Lan4i
z{mYt>-o{*0tbFeS<RLlY3*ukpm_Nf>p9#%u)%yJ3j=D9vs{SQON666>w^xFf*VRrQ
z+Nej6K({pU04>C)Hkj9W`@pEz7jR^M-uOd{&o1oseoyq8Sx;P-&6CIOpuh0+xbv${
zXmF+O9K2uXFm(?~Yr0a%dJAMWJcH)yh!avTK3{eD6JK&^DRImHF<RRnF#_w#zyA?>
zr-~GZcR5peCfH3Z-kGADJ<rZu==aYp-o$J^A1PC9KJVjTbbO5$t0u>OUC31Np+Bkf
ziy)`n)=UjdiFQ2YYeoHI$Z;fIn$E}Itt@KH_<*rD4mGVSP)h+8_ndZe!^rdAYJ^I+
zG{H*|cvbOxPDq&vShb;@!7<#UQ_0x(M;P)v>^M=~ej@c~ZV}Q6%;g(Kf}2LmA6zmP
z&2549C6b62Xwexug8hjKYHyP{vgg!>bEO7++31-b*h{aJH?BI<SkMhlSFo^!O^5ms
zFODxDk2#9hT>JlmXMsG&Q1b9ez6fvm-(hTvh}O&24;#aM{8tM)wug%1e=W<+5F4hd
zkLiidH`)m~n>*^VpLIGk3m!C;c)zd%-kXlgpbD3h=9yWllnLm|mg+YhuEsz)UFqfm
zs5#dP_R9Ix48#+Lys9?U+WUMvAKenGC_v=ebq#Zo7;__iM_v8%Sys=>Z&V!u25kSh
zQK@dt$9+n_AZ>rtR#mvP9<c6v1V{0Qx;moTg%18KXLc?K$-LrSb(L%X25gZ_N8w9>
zj)&a-oh_cF%=e%-fsIDKj-4u~8;fjRe?k9CvRB#|=~4F0yXS_FP;`uq&EB}(!Z*yZ
zbgLlAO6prNgS1EyTZ`L>5>hwfr6~`Vz3_Y@YN<&PDwJW#PoEx%hDFJS|M2wBMK29J
zmt7es&J%u^G2QsRf>84hoh6>`gq>MPD{mHJsr}I+4*-D?q3TY|ss}9L=pz4T!8)9e
zuOoeVs*$OB4F<<X_OkJ%JKQI<M+#BUVei~--4U60^3RMX(=KX=-qb3}>YG`z(%0SI
zmnYa@zS0wp&l_4X-&H{q-<gJG1{UQEl+oQ(l&Ah7ED#?=ckVm^RDN0fH%}0zobv2a
zW2N}Ik5;;afok$20ouq_{)c<3kCxQwn7$}Ixk!=PBQ)NTWhOM8rhemQce}^iIc@*3
zzMu(%$bVbQDp|9lgPx*9;4PJE!dLw@yG1gh-*kqLz-3-YmLo4NOV2IxjZ_!k+YG^O
ze@{9o6Q>t&-EElUe0SV1IfgyJ2#b%RsaDV%>}%fo>2fmdrY~Zx5C;A^Aur$g44zv}
zj@u3E!e?9=F>lk<3Abie{<*w>6#!|_4iNL=uLe_UI_$u#+->Iu4<&1NRbLvG-IS0v
zVNR)A>bLSwCf(oiWAL#`;+|o$|0@}unBcVhdn|SJtV`C<Zy!tm1KPx^j>&-)@6vBY
zdxUp3Q9y1B?IqgZu50QCD4Ky#-b_>Ybm4a|W-A}`dTh8*J-F0VWw~klJ0EQzg4y~*
zwjrAIJwcVF$NbB$IDEy8Bj?KNa*LI6nybUFYnt!|R=Y#5fus8jug!#gydc%rAWa|n
zRl8bsrDI*^3k6IjJOmYB_Dc4`1F~G;#bbsh8MyrTI&hM9n(SlTLeAAz@h{+O@v5wf
zX$M40`=uEMSX-zR8I<>hf4cgEG!s~Yx>t4?#A2^Ll&y#is>$RR?%Ym)4*(Y#heMx?
zad(2r$FuSO-e>51-dxsL-$DVn8o6(EWGoLEv*|)F=Je?&tvtnkEA5^l;uF6IMBLPK
zgI;KD=78F#m3Z$;${4hGIfwqD;WgfRXF>q6rk#&*E1}+Sb)H)SIyH*J7j%|Jf!9IU
zRPXo+a4XXx)B+|MWJ!}xVJF%zRI-!4wIAC<4g->U?jpp}v%Xg7XtP5hTa?iY^|H_N
z{#uLBVSxUL{;#pEg2BWH6&Ne%`YbC(CP_kexOn5ctUqCM{#pG~uZMIPVFm(mNdyB~
zp=NNY&ZAfSvVJv?Re2ZNx;=Q`UwqslAe4A;e-2vz9`fDqD}g+J#y>iNCH1tqeE%bF
z^|xpr;`udJj8X7N05Zck%D|6setmZ#TA2U6?Xy*L)xyQe2izdI`NDah#A?LF3^ydA
z;P=-zz)MwfLFpPnGV=i2Fl@3ct4}E*O)0as$3rjAVvrg1HFwoQZ0~Sb3lBr8L|?{&
zg9xKx0@PqXJ;c#kY_VhhXpANP5zC$q1C6sv@JK59Eqj+?fOyy_ig?4MHXqMesP}!p
z4jE5Op>sp>x61<W6ejMUp!puiv2n_{@@Eb2V)g5T@~CO!L>;pm@E^M)f#bBJNCs_x
z_VZ6Y1sR&;OqI4LJ_2=zsG%myLA)zFgQ0}FuQEX}<tepHBKn^9lOc?DlYuP7j5x56
zg-o{1TBo=Xi755Qme;o`vZH7s__{6QIb&hbv)Z0~P%HW2|FW~H7ocGUSv`09(*>!f
zcn9?=mkXLA5@j2Mu?pR35po$+ZGO8Dx*w)pJ}qw9nUTohna%!pqH9{0*5<%*@v6Y9
z`hnyRz~4T1v7X7M!8oOmUI>dd<Z$!@MN5>`E1(V)FTqwMib-D<P=!;G$($`e`#y8+
zO&cAUMfbRvvyW)bJgoXTO#m_kx}pNjnB2-&Sr;se4@bavjnX6@MDi|`mzs1vdpB1r
zV`oMEsjsPyCEhXqhlff!;+zp3yos*CfoB-52j<<0*Gwog3WzxNDwOuq`8($j3_(|r
ze=;KXml{JpUd`m~0D;}glTH*Riej@SlC}RZF&_4bdr*bpwdt|ZP4+pk)jN>}nU0FE
zSsMMDnclN<9A0Gp$p>#@vd6c(J2+N6zWVssV&HnY!>2PnX1E7(+>AaWEC8Y2!Uv{>
zw!_i<`%se{TZ4#`jB7*1i(v|Q`oW940?+(OfO1hp0$Dkq7@6?zUhGz~h+EPvLI`<v
zRAIUN^!3{bmKDLslxIvf!%u!QaNxj7lv&<96P}XCrsdM2mCCEopsxjHu1gx0(fka{
zKN_AzZ_=9<MwnBslFvA0*q8T3MFS7A{J3H7lpPrDH0Lb3>P(K#1=r`>_fC9jOc@ft
zi+wy+VqE<3N26M<H1A#HESL40D`C@U#2OdG(c)w8>=5&ppFgedZU1osK&%4nyL=hv
z+{%ML;<1vmFuqg&+TkV3oXZ@?56v@-w=K%}$3{Z)EA9#s5^r+RCuc5CD<?B9U1x0k
zRqkEUNiqS5KQ(*sn1@0xLNCH9s~Gs95KGbX4>M@{10|V0%3_g<!}bw87Q6nA3$iTd
z_}WX^bH}qtWubTQi|qNW&Suv>cHX;c%EZebN(tF5*Z)c;?8@kRO+1-o?(*`}eA#OZ
zzCIZnA616o|KO+H;NjdvAVA__XS1*3qYS}+E2j)fhX(bZ2aa92VHB!w#?d~LtnfPM
z%U}@h;4{{KykBnjUy*`i!`$&#RDE(9NV59*-EFbKIh{ex^a86-dLdc)Bhbm}z`{^*
z6J1|;>a9gtA&!Vo5+M|@RP=k`4wJdK8`Y#E0Dv8CyM|jML@NhS>5G`qr09;2wv2RJ
z&>^#O2gvBt8ECXl1#SB?w*!_(yV?4da)~kV2nc2PC3FNf*BkWY%6zXqU3@_y<+0+#
zE0<sx>ifaoR#5YS%*XCZ{!ZscSPWz|xodl~WwPOz{$UN~GfMa<y^%j(d*yPpF+W3}
zkj#PpSlNZQY5Ls>6i*?&;CHY6UB?(mBn<GiHW-IvID9(T;g!i|HfI+14jR8o5YNlK
zJd71sf(@3SUohw+K|G;1<>oQ#H)G5)mCb#GxQ9gA0W*6r#r)G-Wxe454+s^mo`Imd
zp*X4{9W;|~RF)k)z%V62VCg#Y8<C`Sz^~I#xndSYs=I2zWrKT=qvrzL6OsouDHji_
z(X1cmD>tEqdQG}5weS_=vaafASZB-<thk)ADIlmwt!DZKl+VY~)bVmjvGH?ar$Ia%
z2v0Q$x3si=6Z`z6sE~~9B`|+dI*u&36o!CKAI2dK(PV7gA~rX%%?TkQ63P9LO|ffo
zBhyjutBYLXnG#s45}PL@@@hAlK7{J_qq_I31c%U|Lu*C#W6&{L80vW&n1P>Z->wF{
zy71IQypNzS5qP#2La^Nk?}jN_&~<w2^E<zy+boG@ca>4dZh`C}GeL#I@7|aNC_t1=
zDBm`4WAEi|Jf?OYT9G*aOu4Z8v7IW!A@Rh{kYz~}urIv!y>ez~P=UWMkQBcgBIvaQ
zQwRP6dVo~@xVrnXB}PTvl#euhcTc@_Wxk@4ln#?=@#*Sk63IhfH@@>fGOe>&C()00
z?79=k>1?v$ocxN8G8qmy-d1Xvm#RiHzYrXh&;KA=SPNs2usxi~r~z+d+)Iyna+*&M
z*WT<KFK-wuin+4{Zq$Pb;LhD2be^;auNG3Mgwy%8ZQmgjrpg*gT$$1F(eANJUz9Fr
zdsQy62?NafeH1Vs;|=Yf#RxX{kYPpn5Bc<g#UF2q<ZD%WB?XtXsjGLtUmWT^w*W+l
z-wIDK2>Jn2-tWDHlld}^CGaiormLdKRWqnWV%E%f=*16sgJp8$l3sJMrB=I~0*d4c
zjGTMVH0%<F!<01j%~b$frLJ?1Nyhpr>E;l43xA>3O{n`TU?}pJqTof0zZ2_!c)@XB
z%PVR$Aa38_q_)+2+QBeo1zBU;xdzQ(n90~(eI6E~O3ZVcxWA=;ue<w}(%<B^7&Wwk
z`-CiiDGXNGT&`C5vE%Aah6|FVDktQ|k^_suy<pD7g9o~{W^Z8;s0UyPHrv>8DGGA$
zztz06<DAmM!iqgEr{wTPbz!%pvtsQPvk`Sm6=HU+hcM%Do+-Tb8Ks5KsC%MBnSm>V
z=S%9Glb_-|?WOn6G7-o_W*;B$4at?JNlPt`O&XBp-lowm%X70oi90;92x(E={OX1=
zX=sjwWME~qFNdar$46qXQzZj89K>k8PUw3))p)!+w3W1IuHE`@<nofS_+=x-l#b_Q
zc7k>BJ#%XGtH;T|5g#eO)-Eo6u<%`ZWw$w1yYkpoiK{tr%hk_z+cch+<n#q2_j@|3
zBuB>92EYoSd(`<Z>vC32NBqp9{VBTU-3um#?Z^;Rb!&1Xt@AT{_+vMqV-W}vCTlH#
zh@`Y(A~Sg^WWbDtU#9hL>pvTK(?wtA>N05S)P34Fe8>tti6438T>q>PhURdJBK3?9
z4z%G_K=+D?NMuU7zrAU(tLIOAWf#jsb1q$YmvZ(4Z9-hnQQHCuGQ<mvIma7m8Qi$y
zOdXz4(|B`RtdsfqO+6=^Mt$aic&kw&4vWIy+$T<HiV7k%a4OUI4^Om+7{!mAo7t8|
zZ~lkZnFLGd^}*yLuTGP@;Fs@8#DP*k4&odX8!*Saz7VYh_t#H)kN$W(R+jW>L5+|I
zqbwWyEHq*sHbo7ooAX_H?-J*{SvgiZwEXi#=d_Lk@43#w^KAZnXHw#0vW*q6m7-so
z8nH<#4ri=`n%llYB*ItxPM6s?aY>)xRFyA*p0BK4ajdMCL29QP{Ewzd)i`!p9lq+f
zCiw~e_bW~Yx&j?HUbO)J)@E&?7f)hh3I)ZHK66DQ9dUSzHv{Fbo+Hd5!oa7tC<VL@
zJ_INe6D!hgVQNa5z^UYOMI~bqwSrd+?>>7MHc(+{H;Q`0{!YOqayK5b>FFvz<g>q*
zNlrS~=ymNL)zM!=RAPLj1FjY2B8yCx(87kD&ba}Z5(NNuTHBZ&70aASc@gIO-oaIt
zcQy?BrJOin6Q$|UE^ER+^KUi7-|;dpO~_bgB<`bdm=h3gTTw|LZ2b&axbchWWw-j>
zlI%KE^q5_=u7va0|CThzm4RInXd=%0F*Js7sP+A^%K(VxyF1Gq^Q8ET0w5sc#$u83
zCU-NMIr?NxhzP24i3&6qZP3wfz*PTwPA%HBg_uEP2Xscj?sITpbxURmX5{P;kaeGp
z2rl+?3EtTYK-CoE!}#@aS=!hW7IQ!jrWm_g)_~D~S0#F~yrQlv{6o@q5sEA*JGOLt
zH&pZOe4$J$HDn%jZ^dEy*Uv2Z8`Rxb6E~0MFR=bVV|?MkZDXM0LDSqHrn2zAE_gQy
zw$4);1FgHP!2j^h9?}_SfvI(FL$DHHHWtwSmh_d28NtuV0y#E4_BNmpJu8o*#Obt1
zYp1YOvqu4y7#vAOJ*07&yQ<k@{Ub3;zgoVL)D_wi9PF+XdrO(;n#G1Uhfn;+{l(=S
zzc?<k7jv&<kqkbEQ3!TDg@qYh>fG}~$~Q@nzi-gY2+tna1EAnTDW&dRAvJ8hFrGw3
z*s`kU4{)fQ0@ae^@h|X3vDlhlu6(s-W23HuwJ1<WOT==nV#O^odv2tw)h>p|@5DPi
zwsfqGbu7G<(Tp_kE*0ZFFesb}5nb3<!Kvr?8BG1%H)H<$*HF_--u2O;%ugw5)o@hk
zh2g-c!$3~{GuLm1kXBdL*ad=8Si`21W0Kefo&Ca)?)$Zt^%ARBD-1%ZE;;XbP(AFa
zjhX8|jg51+4S6>kqSde_N<znrZz@yef4L-LMK(h_4Y{c<i`qY1xMtag6nkDzZ0(gP
z+;YvAL<@q1T7V2R<0;g_ws1*<{Bv*9ZzAyCKZ)DDb)Q`vf?ao%09CQ*?yDYNcxQam
z;S=!uZr&EwD9{P^RJf{L_{@crxRI7F33>A%n2AnbE$?Vpuf5fwh*!<%O!|KFRpD#l
z2URNyC98KT5<hAd<wi7S&#@PTTDby;4-U^qI2WN}Px~@hV~-s3NiKI~yX$Wc0__6w
zDRN_z9pamDCq)!TnZbvNfF4yF8RueJ@)TjGu)L;1k0<WDMEa|T?M$&{Vvxn%>JnSm
zxj+-!TJRLmQX`E@Mj_L?=|Ge!rB=Hv9x98=uGzv1eQ46Z^kfj^mrOg2zIcLdv51<u
z95GZKnzNH1bBRyLGSOfGr`X}PpaVw9igPHupxgR~V`WtkPSFV$eirM|N5dcsp=Wj_
zE=pA`78m<^xTzVjQ}dUd(I%%KUvP}2d(^S8d4C-VAO*T5pY%6!2emaRjVbAfR?@F_
z19k~WZGA8%S9CH7$`E~~0fZ9~u7?PNna{(vTEECwtGm^!VlfC&Y;FnMo+bg45vMBU
zk<^oC5&uo%)q`_U&7NlWb8OkVwHbTYdijEiyGP*|nh^B9tYG3iNBqgz;KK2^UppOb
zb(0(AO~DX@4CCMGI0p~95ZtkZ=GL%Ie9R5<-@Zw?(}Y`>`GRlYbUwO_+dZDE6{J!y
z^ekf+@hp1ul&ZK-@$ER5l<YUQ@20zr4Oyz!L{$F}l_E$drW+wUg*9kC7q?_cWg-hz
zx$I#J!QHT0B90J|UMc+M7jERO+SOZ>NKr^u%g2zw0DtHMDB3SGy2Y~kN;A+U1sW@;
z&XFDbSBt$+*3JVNiW@J?(!9;2koS>|NxFGy#@tGD<CijkP3D_ErhEr=Vy{DCO*~uQ
zHeK)_L?oJ}EI*`X=TE$5Z$Xvb%Df(Er+}3;F4jfCp!9719p}|}P}H!ckMH}3F-X3G
z*9?cumz0LAfm`XF)^c@2?H?FX9qDE4EeTX^hHwYl1j0Qo1+@9SxsvLiZT*3Mg)H*g
zcZYh;SNY6>3gq+g9D%HFlXgr?%Cj`JL6=`lLS7VVe}EaB?6J@>PK|?*hHmE|c}>5O
zXHq!VeyP2eNj<2Y;zqwYj{z77-k<s!;zure19|HR;W`y*>?=q4;jPT-9l=v3CH5%j
z+W9?J&c<<n!17opLoFrRc7Yv;G{kVbh^MeGPWQG>h{prRyBMRG0#vcAkkZ1!>-_s-
z0XYL#?q~m7`|lqmNox@)AX`g`O&Ykwb~9p86G}5ype5*MDsRo6$JVARkBxK`77{Wg
zh&LQlbYTp10()0cogx`^R2J~d7}Or=T+Ss=R!EuWu^P>8)8%fYbK4B-#|Bc0SFR&g
z@!voEyh4#hJA_-mwf#}>#wx<f^>cKU0QPO=9N=ktYUCRl(<GtMS)ad<9v_@c+tBje
zzl}`W5u^E|>bzhAL;kkv(CsKU5!Sb!bWoqiTAfGW7`3sSXb1k`DY`YUqf7b-*=nM4
ztHWf#?LuW;CuCzs5%pW=amu`Y*k5UYEYh}>9WhSew<BxC3!Jo@_?Ej0RpTPSW0DA#
z^&=G5Oh2a^&B)mKiUG^sjk&zZF!fFO9KW2^wVUov7vOtz-y}s|ZrgeAN+LQ-J-*A<
z;+{-mE!#wh9;?2%{;S@RB&89lh5qP8#AxJ#k+A>|OS_tjU&{N_#@mk@)wKBT<<ok2
z!L&cb(82!qEMPmEqj}>9_^im1*Pri+%OUJ`gM|c-is>Fq@&J*1)O;|ebT1FfJ^si|
zRFF>wX+jWEb2NKNUFa)Fvzam`zQJZUCWz2z&@tz=0@RJ+=|o#2>n3)(uB9R7sf|+h
zIx3-Ce%8ggz9AOGAsn;yJ!U;(Bg$tML+Y9)t9?_<tzi!m=i8nvjUcERu55REEma3O
zn;08kN6egPQnHN#p63SY&LD)H3_qlekgb@!V#c7`Bu>(MUyrhMni1jM6y-G~%8p8N
zh;7^WSBxKHFtF%-jyhDD<Sk@+OL01!e36fRX^+g*7i(4gb-I8sAbk|ehww@#+1Gp6
z2k>Z`cuH=c;l&_LKQGSP4t>HYS|%d^fGp6Uj?H)nEBVGvLvA-@VZg}5ZZWY{XkDoo
z{~R{Jnf5gx0OSSSL`pSMah+#{_AYu-@G(xcc07oq-eYK4b}01ITeaJu4w$dzsGhps
zhW7oR@}%3#sg?dH`ZqHKeDAqpxsVnFJ+r`uLzrPX?=`$b+~{TG{@H7g=KCZdU#*P(
z#YDJ5k{jQ9S*K2d6b<g^wENmrMh4(14S=u?F-wtPm839%_HU%hT^5Ru)Hk{nWq5D@
z1z8YL@CjaxftNP0{ZZ1=%S{-A@Ua!!p%BpNqp((5cdHEq)JZNCs8xM04S{!j$a(oQ
z$$u~>dA|w`(-YN|qw3Ik95Yl5%>BLpl=Cr-QlqVd5LSS5+PR6!@ql_gWE-1S^bHT$
zuFeFRzlAQooP#XVdU)UB8FOF$%>PN4=er!j&AWA8c*OnMz2vVJ{?CDS1u66eC>l>A
zWz1k#$&C9fMxKA`zR4)@IyBtqmwp*+gaN;mTP_7;r5{ObmNRt6DuC3U3Rv_pJIlde
zjKZBqM&QoMj`e&L_mV!@NZa=@Ffl2`k#)`_H^e;aPtLay=QL!}2ar|c{Kt4e(_A<B
z*RQQK-fw|JsMJHTFQX@l1B~Oymi|m4A_CB8X~t}7DQGCkTD9lTu1Z%1=wLDi9%2HQ
z7yl`ZF}(Ys^w$bU`=Ew02wyAn9mt}DcNF5!F~S#@{2!k2HfM;CQ|wy)Ti<M{k~P3=
zG0f1%cc!a1H&zJ7m%N2D(gx(kE{7RB*cATF%UPxdZTGVKd6jeT)%(?eX2!x42PUWW
z^e457Z33Z(Ci5B^+jyjQqUFDX0!Cp__C1KQjsY2$=(0X+_hTWOgA&m1bnKIclbd38
z#vHn#9UsN;0({SJX=$v*#<)JG5eIH<gh<~Tn+s$t3dr65`8@vmGu8Etog&q9vY5w&
zC;3>Vu?GV5;ZMEWN65%|S=xHe!T3^f9SW;1`Xj%di0h}7qwNEb(Ht>L;c|r#3z2&Z
zXQ9pbC?>p}{Ya15>c)fKq9a}BIp*_*zQ?4KYMBA0NKKs`qW35J>WsxV?s3RKAA0%M
z28siOBupzeMq0|M#`SWwp;y%U^rkypwD|Pb*Robfmp5@vM;fLxvWa)&@?Ty>GSQF#
z?bqo;FRBRmrAw82@kd=8Q@BUjl-NqLMg~{vc{k981al$1okI50?-7Tg?1o?1>-EOm
z-k^LG>O8-L_CY5(BoCVHuBd~-ts?UJ#tQDuxaawfpR@0Uhdzq<EAJ5THat?lbAN-5
zXeaRI8S@8c^X-E+48jgnSGe44HAVSg0C^or7Y7?wmfw}z9#t5*9wz_^T{OMc`#3&K
z0@=@ub$KEDlS8=e!&QzBL{H%HwISZ=>YGoK$U@qHcN>fvl=4uerhdpfK0#SL?dsU>
z5ax+4-QdyQJLlO@uarXKOy=Ohr)t^hypy?piR}{uSk6#V>af%K(DTBic(d>JB?lQ1
z1gE-u)Q|UldEm=AB%!HtFBmb1#H+l@6os@RQ(8ICcegHYT*6q9qap0YJ_CQn+%ZP|
zf45%g+cl%YsYB~YicrZst3C0G59@ZMEk6&;<Rl#GS;k)*6VdYG<Oep?$17G+I4Hy@
zEz^9%6!gmZn`#Y!UemDx4#U#eC&cYMcR=<IPC0~CR7m&f8R#_ye@m@AXL5VPl-zi`
zg&d9+R^;@J8g`$MRg}7j-|6|ffV7B+)w--BA$r`?`>KMPs$A@Xn+pU5>Xf?n&H*pP
zobwb9$*A#}IgayRW?=a4;RB7QAIiUz7%uZ2e&7DPiWnDc=8rfjJtQ=&ag(pD0Yd6Y
z2UGpr8;t#Uu|q0BnN_KKgj9jUtu-+(!oR3rET}t0*YY~{@m#Q-*_2_Pgi1?BXzVA`
zNi=+S{PJ$D7x0%W255Wf@b`NC+B^xVFD_K$HY0d$SUCR2X`KS7*N#r$GlRS5Hbsam
zZy3g?-m^y!zg=sd>~pKJi$cVg5u7zf`X@&BaC=FW8y0QHsCW-%6*HoS5%q;H$CtS7
zkItj1!?y{NO@wDP|C*@z8U-aK$0|=4!Kwxb>E7a|ZAKN1e2{Gv-t;&~&D7y-(fBau
zC1E?)tw#2$8@=rl(xg_xV)o6{r$dR)ZfJO9jftdN+wg)S2asmrr)veRXOHCmeJId4
z2cVc4r2~zM>z#Tj-j49*=&rGO_pW?7D#Q_}yVi7Hn~B7Ui~Yu?Uckx{PL%!_bTn=C
z=_<pmQ*b#4oDECchw0yJ#(+@^d)``GW7*(wh`?KJ22(<ujny`aU*XSNDx$U8T_6D~
zFwk7>dNTI#Sun88T+Syk-J89eb&@*=hhK_cxjo?yMBBSuuUf|1863`hcN%H5?G8=6
zE9koMn}dkyJ!jw`XnAkbpKF3{(Fl5YN1xOOIIJSKfenLW=bO{nmkKC^Zi&}R$vt`g
z)<?0=O(2R;QuCtUsi!mt=lIWWwUh349{np2EXr>5qUtWS)7bO0SNJ(1v7*kJnug<v
z8`h!Q_+PJZV2A*h$LcL64#<eJR!!z7kh1p(3NuX^{avBb;Cr{H2!7Q)jBNa+2;fIR
zm$ZZai1%aLtCC3p72-jUr?U7aBj*bZs7%X0C_Vy)3=IbX$2g>;#Dm7kLB>}r4FM9b
z7p-bf3i#ODjFHezBWx>UYA4wI!P|zZiN+`S<rllAW(OfBg<_B+v}jQ2qtl*;6I=Tf
zzdk5pj0k=@=#%bhE94l>sNRb`SjwyJGvT%1$|z#M5vs+197&g;8^}G;R$03YyApnT
z+gt$gBs=~2pw9{Hi=T>4S3H-XjZ@UMHT6F12$3M%i}9krk16N>Y9!6Gz7+iZe?br4
z6d`ti0!2Kj3GB5&H-X6m@Jz&8FuB=4IQlI}C0~&9gr_+62VFMTWCS2dl;2FS%DB0i
zTeK4H<&WR*|L`18xk1N~s;&&uFoW1h&DWBO-l)WwbPMCB@L_o&q<d~?sEj4K1h(ob
zAxSc>tk1?#p_wPUR=s%v@C~gOJY15Le5EQM{n$LzVT$3XPZ~I9BFHg;n*~YDQaH+b
zr(l#~@6)gyDAi@LN6H>V2A^)Tr8-(k#=abRDIiufFU|@Tfh;QuOvuE$$@W|eYn{<9
zh)_+&^}q0Snf2tP^;8znO4myve}kv+sd&VWH8a19X4ix>Mg6<#Sp0m!uexuhClP*e
zM3AA{C)#2In#t-9v!)%T4l{4h1b}c}^<VCX9t0lh?}HviCU?wto*ocaNxZSI{pKZ_
z2Qn>5P;oivtN%ziMPd9|`DE|W(~&wC`T2rx5{$u{rmL9hqWKk_z4<oe=cFZsIz%#0
zoa$=tn?vVwW9hq#5*+Q6WKkh7M*X@rSzP0+mT>y~<K|Q%mKv1&#M8r>V9;G9242r;
zn~Qcje4*f2llPC71PmnNlParWnR1q(UAKsrG4dZ<%*bdGKHp*%;9cfMA4`QCE}(!7
z)70>k{3C)p?J6eUvYASU+HR55j3CCZfOUCvd2QrrM~rWaWjOItsk+rl7+|q82Sg~t
zCo}nK%vJ*OWTZrPG<l7SpZ?zcgYF<)U?Y;7*`3c4Ew*6hjkkddd_}(z07`&#SPv2J
z>qGf~1JbYskWp<1@N>Wd;Bs}VljiH|k@v@)OQq=fGWv(n0Utq)miH%y7oZq{m+l%J
zN68O^68J3yyTtEm8QHsxc}VmyBSD0->&abJd1gQY342PZrjZ5LmwGz2gUg;f$5ufY
zcOmU$!!0K1w;ufIgg3+Fia7^EQ-hwBQTB=<@fKS6&%d%68G$IW(r}Ep@ooY1ROE!N
zhcZvdnMuadD&gayIsQ(*(fl;zyGbJQvV<?EN|8=z6Jns7;A+gGo5kflODZH*dB4~y
z%b^>%2!Z=yS~z(NBVg_UC7%5$3l7kmhOXr;h5it`65yZJ))Q3LyNS?V{yD-W8Pe|I
z<Y^^VJh6piqXU#M+2?<&T8tF~6ZmIIgPp$mC}=F~w}g7<2zomR2DwXo5Gh8cOwL1!
z3+75Q<5EH<ifC~w`F5KVe?74dni9aQhv)MqwpU<6$Lu=4&bB+2S05+1;PC%pw%uK{
zsbEDBAlQ(A{?Vviei@EUR2e`=rY$T<4ZBo{PC(_p(SF3B;UTnjWX~RZ7lWD$MC50U
zqDN~ppL`a)0N*uiW?|;WutNMbaL4MN{fF=_o2>D&filDiXz!5t5BT{lH+kp2JAG;L
zM99sBU^p;K3r`!#DVA<-hF?E2@TztioXJuT8V1q?(i-MbXPw5Msot1qV|cZ#;&+>i
z2PGq^hMlA_pP->m2aQcP^#z2pq|xQ}17nqTIAWbwb+=gv<KIfhZ1NuNiZ@^;y%`x(
zCX)IF+s+DwpsWj)o`TAi86M9oTM36k;VVBPz{<!`bi0t4g?LB^6ucI_orqm-%W5A+
zS6l3?)qIyl_M%S;u&nU6{mmDB&Ocp?gi5gyN$+?29>@P=ORD~Y<+^`-x?Vhru+mn$
z{CEnZovH7dvAcOqkA<n1tP6jP)0!`5AbiTg8EpN~?m{!*gC5xrO|PH=E6MqN*1HD$
z?AZb=WqIQjqD&K(WVA&W`D2riW``JQMe3vRLB=_<GoqMz*x<OVaFzd4|4!y$MJUGL
zHvznNWNbLUU!hDug}J-(_QS&C|D_(MOmJZ_Sp0+Y31}hc0<n1j%LlY*ZMzxuEm<XP
zYS(*rSTG%n<<8B(W%)472I1ZY$!uSo1ib?{hwEHgo0ZyFR8BxC3UH83eveL-l0(o}
zfbSo+JLgGO`>J<a-2_1bumLk!hyv{YTC{A0XgY0fBZ|p(<nZlegK0l)Xd9h6PXb(|
zFSz2KjZQ7OLNh-`L*2cMczK2wq9HJ8y#ObQxMnZ94}vbwF>?j6C3W{fxYUVx^_$%S
z+r?7VcsXCi-jdJ6AvR$nAf^igO%Z?5wMipdEAo07HSJMYs7o?YRJ)J|D~1&@&JbAn
zZ}(s2Om^+Q5M*P1iO)@iiwDsr63ah^rQ=AMWvz$-Y#ptp%KL6U9m=uZx^v~(<TD!z
zpYrW#MkgO~O%g%o84ERh{l1c*`qipRccC9n-dfJ~V9Jd%w9!^4CH;A`hAm9i9>?Dx
zCwxjbMk8D0{R<Ch18H<588*Ua9-S6o$-jQ{4<SYyjVpTi2aoqdND23!u?GKDE2c%h
z4&hrWb;8}(m#>crm<Ig|48*s$bUB_0^47YfP*Hn6j*~EPuj}(f8pL6V!R4O0hb$GD
zKvqj|%xhlB_a#LB>OgJyQ!DzL3$EC!5>Z|y;%}^X8U_8IyhwkoWXXnH)C{alH*J?1
zO4R3ODgfx^bxt%1<nO%dErqmhjCVu7(vkk;78y;NTL#Y7YC8r54wskmx%!&DQ1UCK
zCqM9I`MIWn9CsWT+I0ALYKtJpn#pLZB@Q^9QC%|Pq*+!F6K6;WPlVp>J;R%;4=iAP
zh(Pvh@kt#TwO<L<mxbS>S;-~J4j@aV!;*Q~;Lji{;{qU;+VA>*)eY5%R0}Oht|=$^
zCJSFH%cn&0&-7(r^BtC!hn{YLI^!%ehhs4*{7ug<6rX9Q9p3~*_=x1&Hs@6<Y|y!z
znR!?Q*|T@YZ=iquY!8KXPyFTt)h%uOolI712f3i_-HTB_*ipz$7a^dJjON<te*G#h
zj%On5yx7ftT&2`wEZHq=xonZ_BGyeens?WDa!xzMYTvSRmY7bc%De%xZr{Tm9hv+%
zUV4U>V$zcQlFgag<)Afsq$LO+QU0VO(|+6dBQP1$mYjcmuc27nt^osGB+J%C4QzFO
zQ=3e4J6@<LLSBs+i8<f&SPcPNH|I&v0mq6^;-do{{qNzUn;@jQL3R)AO0|=0Jqn~s
z_bPvUOxB+J>L)5-o|9d8)9tDc&&pLjX#ZK_;S*)|gR762Ho%`>q_PzifPG|FD5!)6
zhfe9-zKeXVcL@`M-RbIde6k=9<d9n)g0DK3!rh^Or15kEpd5|D+Z|$4weGPmI9EM9
z{I@FCmXG;_ZoQQuUQF+3E=skv+LGr75Xp_+hwf5S8@AoaX=Ga;;9dmtju=8+tZ8`p
z=c#<V*ds#<kK4+@Hw>$F6qY8Q&Cmy)S2}`XvtG@URbqKV@WU*D<yS{{GvV88zx_$j
z^(bt^1Tt6uPYagMz9A~`Qysp$C-H6Vc;~|$!@Cm0r(hMr4#g6J{a)^<{<KRAvJcT?
z|4NYE-|;^#F5#c<oKOuVdw7QHUAhs}ene6~8U`XX=~pZS&qjTM><xxKZACOsQ%cS$
zE7XNs+h=n$5)|Dfn%R?jh#j#bS{(DuwmX5bT&J1<;Y+PD<joc6ix$oFs}qS{^{mSo
z{fWw1`<2YVlv2qS`k5ubVSY)W`HMo*vTM<%pSZxx56$fc>yQ9hWPzh09tRtH(>Cs$
zld8XczDTVms`33ADcF#-HPz>5@3!e&0K#V~c@iDV-mh?A*7IPzI*x-KMo4A8s_&4u
zhGINb1GxJ-Sc(SeX)C1lg%vdLDfSOCJs&qZo&-db^s51_m_e52grnu6g_xl?v6@z%
zXzq7cF1FRzFta;H70#b)y^wym%v)v#HM`Wdx3X_q4C8ZvM{9L>jYu}?S%nvWWdErL
zK7Rhf;B-#of<&d?Y-Md#TBJYC>E8~-NAEVUlEg2!^GQ-Zyjhn)k`R^71A8}q|7F{_
znmQT03p$`b5$^4DQz5XuAe{6Oq1AXxkk4T6)grrbH=)w2Z*8O*1^*?-iV1=0mKXjH
zJ6stQSZ&LSSjhi^85cQzaO0Oewx+ou5bZLjAy`O-x({}By=8U@&F-#%<r&I}q=oHI
zCOb?I6S%$Z$|2n^U3!*)&}I1J4tDv|d)pEihC8%okXe8aGg8C&nd%!@$-MhC&zX!}
z5b07{_!ojY?rIi-eK|}(0@I0^va8PYAv$pU&5Rz%_3J;{gI0WF>;2F0ffnFn_%m#T
zyK|0zl@hI(2m(mb#H2)aj-E{9#PH@ly!{$UvirnMrTu^OPnGZLr>h6AN|5$#+)l;@
zVe_cQ+67#z@zMd6<~xG+k(BCM8XIJBSz*<QnCJDKZ7)Fam*)P5r)max7rIuW&9ccX
z0c|XHz4J(cuT7s(P4fib(AH2zAt_94M)T8rlYvES!K=z=F2JN>P+KNAK`P+{@Z0CE
zi+9#YkiWU`y_V3TPZnr!m}cszG_@F3G6-++J+Mi1`kKo`IR`+#U3v$z=^a5Et#iA&
zsrL9QFksbh)P3muMEQu@t`M9)ZpNtUsqGm0z;6T`)^baOyC5sviS!XAQRr}h95M?e
z;$ng`pxyiGI2K~hd_VH2S36lcGw@a8na1%Ko4>YCz?bcHyY#7&@(G!uxd8BC{|h#x
zPe@b8*bfP~c1%5F2T|Y(=DuPj_|VE>jhb(EPYt6rmBucOSmD(gsAr-L&PBSytUz7O
z$~?2Vl(qEW@hQ5;u;a}sl$iaz&|v!c#}<8%k>NcxgK8TyP2d0U@N!(Ls9N)WK@PLj
zMK8jp^pq}sR7xaH&Pad{I3b5lkoRgI;mw8=hO4oOYH#67sBiUKqnzK%<v`RlKSN>B
zj~5|zq6=Rp8}3x3toN3TbYtfcM!mc^OUp=di-8lH8~~Sm2yEk+=)H=r!2K}qSn35F
zZTNy2{3arYy{Tvfl|N~RHBp|ddgx>`O8#!&s0&dYcT>}!*Dzm(flYuEDpM{|6<Mjj
zG1Y<q`-|U7E6d4l-_<O)iZ<dryjvWist7c3u)G(=sn>QsdONLFHJP!Uuv2lgP~_3W
z=q^Fz+i0Yif4P+ey(;T@SLOw2)n{Sji+Zw8bAX<3$P@8?_aC0(`4o*k)Q7zVNZ(vB
zW)lO_Pc+~}eTI@PPgzHJ7BN#DBR?FP<8VAhDdsW`EiwN5lmUYYNw1(wAVc5tgwlvQ
z022_JD_Z#hAXGxWhl-ELtXT;&1_5L_IPT{Ur>!Qpz!cOs;550Q%7!~6+R)m#yB`ze
zmUAC|aG&vvG1g88s~XZKvJPiX_9){5@uUv|s7#WLvcgu%z)n3EC)VS0DXviJ!U_S5
z_zWgj{*f4!uelvgX2dM;F{F}>U7FhhRBB8?A%C|;eC#EEp;5j5D>r*jShBe7lE>XL
zf~p<l0kH0@c`M+q5SI!3{tRH_88Y?9lK9IMH^4xdwoS)s@$H(ztkZDoPi0>lyrw$T
z_^Ja&c4xPgpTS0izOd)U0fobj#wxV2zNG>iS9UvmRX^*s*8am2F}IsfkzF!~rT=iX
zU{LC!+xs<2LbKYHs_~BJ$pt|O^^yyK)QXhw%N@FUlQ82SYdvWwXvIPB*!FnC&skxe
z2t}<e*MaD&*aCTuKdhkTUU~7E;_t2_D+;**=Te0kuZFVbOTU~`y->8&Vlz&dvi>sW
zfU>f*%?&=nx(05Qmd6|bOY^P0gj8dd$<5JR#@wE&p{u+3^V`q0*HeArx%+1>FP-j6
zQe0i1sf$-#$d-VsCj;B}k)@N2aQkKY`xn4*4hE36_PV;dD0N^*j=XfIAbzffG}{U#
z`Vs~EafUlVJ!a6vw$`&}T^WUE5L7v$pV4mLzm|A3kc+46A$5$1QY&~U0~DVBcm#KR
z6~m%0y`Od7Kjk+rewX77jPX&(%mDlC%3<|#RA?Ac@HfRTlFXX?D<8bGg9G)dcd)S-
zjWOGH!!nHhOPaUai%<C5YdH?50Dr*HJF+NC`TOR_Nwx4cs68_Yb|A_qdza+K4MbRF
z<MJFC1KyTCjI{dUt-NzzwRh<_^0_netZQQq`X3(D=c@;z2fCxen<e%ZQrkq372>n(
z93gr4B?E`Ayl0{4^+?yVNK;ApryR8F-BzZDC-uh$lEy{j(-1b@pC5FDJCEb|n0vLd
zT09{5IzjD<jr87jixb;>-2dSfMZx$_Lpi4D!Wnd>_qz>Q_Tv<+pKe1I^G&Bazr4}(
zlG)|*?P(l0cui|-Q&X+;bbIlAK0{!()Knb%O`ga9qv*WD*?QkF9;;}LQq+!Bt5nsV
z(W+T{)UH`1sG_J5p{i9ytfKZxY_(TgqeiHjvG?Aib|sSE?|lDqU0ibIob#S@p7*)$
z=W|yZD6ccYb1nFZklR2~APMbewdFxgEPbWi0ej2(ECAC%OrJj=+B*m9x=lCGueD#7
zPE#=M(G+|7NK6(!+9QuU)ue9_srk{lP{LT;z&G8@FIR?OS9r3K>GC5X_t6vWqm1mz
z&0*X=xYCV7@Ht!i+6a4V8a4ZSEejs!%4gAsvd@$-lml&MmxIqko}Kp*C&1aNA?_|$
zeS2oJz2xLc8q_o?Hg?I8VVHRt$(2kB8>3{Ep%tSm7Ux{aTH$zFl}B9D62~+Xj0)mP
zs=!|Q);M~M2I!n=Dm6&GdiVa0i1YM%MuK61XhI?XIQDjzH#94=;y)_ko=0&>m#xqE
zWsw}a;ljy@&A4gmp0088Y#sOeC^XrRpZCm;QgReZrrn|OHs_^~`Zp5*5m9C7FMHtJ
z{;zkfew>IpZK}d#jUm}Ozs0P&?VlQ@o`^b=TmOzvcB<448na~7dk2AQmqEHlaTpJ%
zdQW`fgLDm>b~?kJQ7fL!n8@b8zUs}=YMkY7Z3iVfJ>GqMhH~Jz*z>!T-Vz$A66rEE
zr%2Yv9qYQa`z3k|k0lJ0y#jA9n^w~*R&2?Sg<ndy&)yY7to2i_JXS;_Ch~9@q_Co`
zOIX{2I|y%nN}oFT7zZ4bxr#VQ^}GA63OODA$A?k|EVKRisYK*ITETZ~G`LR3bR*|)
zOh@$|T8Gi&!Cs}RU1h3)FL>6_BE@>+)SCpY6*UHcYjlk3XI)LO+VfOsj)ogbUtlEw
zcN_G!JG<>5vCa&E-W8K<pJ^>Vwu^<kd#P@}p85g&<mRp{>4SeBqvak@2$=*LH`~>R
zinrWiypG<`H|}P<j4>uQ*lfdEu=OZ@_!=W*uC##N)>fcw{!H-0yNv*BL2^+CTqF+N
zIeNH$x!SNCA~No|#r4tIR3+|5c`^t0!=O^GKR2-T*n#=FMB)U0S5bE%fgct#lKTwn
z_&mwR6X|C*Q?K2}H{*9G%wQ|~k>TnkWlkP8YA9Z+*Jnsy+eTL&^3ov0v-s9$8GK_g
z*{Eo@W>bbb=oc+;q0{hM`sTLQj5-}xeuI?8p9KVSfGMp8o}bD8#5kr{_tb93X%7Bl
zdApTwov`$V+KEGTLG*EuKQh^%Qw7OXaAYF1QKJF2CS3;{th;yjIsB$?s!oN1=A6S3
zihwJ#)R`E^9*>a@YAszB^EjGJxLr9}G}!Z%a^7^(%Q8GP$`)_hKhY0S7M0X?nqc+w
zWAzN!7AA@HM+<p61c#1`S<gLSE2M0>ks~g{S17jz(KWAcy@elqws~%?cFV2&JI%bX
z!ogU|j&;@1qP+;)zNq9&DYt;4E@WnwDf^(@f#Um*@!xl1Q?{E9E*l;dju;c7HRX22
zbN!4m?>|BWg$S*laoF9DyeL&IFsQE}UwayU0+8dPrQ-^qGXpTXusHM3N?IFLDCD{H
z-H|V~Ov!s0Vibue_Y%~L9pt1g2SClS&+$ZF_Lt?tM#jO(?I_XRV8yI^H7djnB@(Db
zR}EcR*KtwM8H*>?C7!{E)~Ulc)gY|Yz|K_=-wIu8n*}}pK05Nn=2h<g*xc^LZLXTx
zrf;{@CaOq&LB-E^j2nx?hJo%Vz-Tpbrwy@#iA;;mJ;anv7JPr?=59R2{QL8uvjD09
zSyIfA9biBsT3<n_q2N^P3K8wg@X~kb4hX@Nu70x;*no`L9-fn;lccW2uQDVY(>ogi
z1>j%r&gY2e?meaByFPyI_U<6%%H(t|13hW6b+nYHnu2BiL>{~Z<t1Cp@@g<mdaz=;
zV+;^2b@xtp$?2V+5i(g6#^rG%EDV+2NZOJzf+)Y6<jT20+lOqz7gxz_4Pxd_vF@1G
zA8(GO%ao4C=qgB1srJ%eQD<w*$jBgGl{Q$?GjV3cz9L|omVx~J_wUe_34D-;)vLaf
zSi23BNN=`2YuIjTd8eu9%j>N4VLA9A*3nDbyhLp|@Jlpr>@25?%bQD-$4@%Qm2-|1
zRz~6?HRUzSh~$5S&j;U%OFC*_2h%ScKT+pn&&i<d_sBI&s}!EtuhyDQ5A6LN;z3f&
zk6q%=N<n99Zu!hPZ2d)(#=YQa|Bjt+vh_q~>jr>NXkWouihz-f8_w9dD--xPD;J>f
z2Nhio>ykf&-Q88ymnmJnv`p}EWde@@2l8o7n2)vdd_jA}1J(TS>`0Azb5DTgNzvti
zDdwUS{7}QYlBZ^JK6aQrelra(WR{S983C6Z`yi>On8u4n2EyVh{8@%xjiK2oMtccb
zs`X&{5{N2__x!3xqgzevfuat)8qcmdmO`VlM+h{J$hW4W%iDr12CElB(}(9iVF0_v
z?_!-M74Iyh{@K!g2s7t`6xi;1qJ4jXA&k(e(gJYU=;<|YSRoYkZgg=)HQiYAquXo{
zZ%}f0qAnsd#hffQOAddHIW3to8C~`4ZpN9_OXX!82P`LJ<j>JPa1J+4_C9;YnGdr(
zu03{56Fe<!EGznC5~xMh9r?5J5qrA#=X++A0R|x?CIg(eA^mvFQ3jM^(3lT`GN@#G
z@wUS9=;5>|g?+raKY5P6BnxYm<aKFz5)?%7lTf<*o;&5&>IM?VDhIO-o!;UeFWz`H
zZ^9a`T~1{B<)Sd)V`y=$3FRQq5oWt3EItTw<2);UcL#f3I6$UUO7pRgQ9`KLy4cV4
zStG{t&1x0P%>@II0RfOp^WgnyG1Esi@+a-qpTa#?88V_ZBa{6x!QN>k!?<VM^Ut>w
z?}=*9ZCs+I-SCm8C4V0JDqjH+KArSIF48nL;gF3i7u<N*3rN)Cqd`r_CeBwrdxJ7-
z5x$*8s`csp0nLXg>75YY@`J`<iz4>}sVs%-9TJcH^*reodB`I&^HdJkFlS$Vk(imc
zmj7vpV)r8eA50-r*{;FUoik?p{>Hs^0B+BxMHgn{cLjtCC6Ex4e&DcrqnFu!IvYH_
zUivBytia;4Te5b#b0GOfjtX8Hy6sCp%Vcupa9#(t*R5?#to?8TLWdV`b_bo-nFhT~
z3pmk&eXUG-#OBO2nfkc52W;)cyTl2Rj_bMqV(#JZbv(8^$!o(|FdquWCytG~==(7^
zsU?K0<|iF8QgM45{21R1!npU9eG9oyimWC%&<KyU?WPyuRV~ag4gvvn(zdV_TRd6b
z`D#wzg0(xQx`-m^)t8PLn#eulNJ(dWDiDcQ&3|h+Cvq`oj81D7=ojm%-@ow{u@RXI
zQ}>5l<DBPY6jFfV0W80T(%dgbDlLYyHp!7M+mP%H^5*!(KB?cJQuUV3MTtn#S;hP8
zsJ*8T{?nnw+PRwj`Pz-a=-X|ckIwp!)Q2A#NiOZQbV`z(72OJqf5D@g@<IFiN7XBI
zGBxXrh)@g&fz!=#MRJFmNMq@eG|?GiYYDIExf^IQOim086!7Cz&s$o+CnI5IpZ)y4
zZ>2i`=2YDpa*ii=c63Md29N^BYK&JSfQDbW{@TY_DxdW<=2WfGU->EICd=3ppL!#5
zy@A~GeZ;c407IA1(idV&@n;<nz97f(b>U5j;*EzrUb*eO7lYC$^!}<IL0^{_XdqId
z(*?M6V;m%%8-$|!i-R5lTza$Vvq2^2Z(6pd5ss5)K;)Hn$P>V;@AM+qbv5NX1+WCd
zee@qtUN<m-R=7LpXL@cD6C{|~5)oS{!R_yTT|2<{EJ6%04UdHnVU+l}C#c<Z@CSf9
z_zBbXpxOXWf9{p5YJEQHev&ipCi>;)YG17vBAo@!iMMiLPGUi|BCP%>D*;#VPtt;T
z=>W3de3jyP;D_pJR5jX~Ptj2{$h0p=0D>y{mtWcJ#?FTPi8es2sh+wWb%h=>)J5I<
zrNns8XD24X?OTeJ=2UNhIOwTzwT^4T);KmiJU%Jx&Auu<^;k;9`(-cSE3$Gk5AlbE
zWKey|Bs_;b`4)R*t%l6H8n`lL10PNm32bJk422En2HUkuNZnKm2lNKm6WV=}ZYrpp
zJmxUGm<dTKC8_$ZaE^6ZK^k;$!m=sN<Z6&Bd@b_PRkEdI?lxOj1}NwOB2MxQ&G--0
zC#lU$#lxR?q)*Kq=B~3Z3=+>_@iYxYV4a|N(~_8!DxeBRhGlP8N7s@lB*Z)!B_q~j
zyWgLMn{TgZ#xh3J36m+9gEuUkE%@t<NbVumOqt?9kOwPR8S}$UHj)&26mRN4#r>uD
z3C@hnM_wnaF{NADTbqdx5}nQJJweqJP!fw9xLHVsEpAAX`Wgl}jB!VkUpEDVGMOx$
zq6NSw!^g#r<IYZIVZMRsjqsfhZ~eM*e@EQOm3AXlhKoSn2F-^PM0o{5U3C84w14zS
zUQ0fYa@F9Zc*8(}%gq?6`)x}TvXQ(#;?lRekcpKh5j<WDgO>>MghAusQBU)md~Phk
z!gk&*s}(Os#6Rka{0R6fNwuZIEwfBXT81Cyopquld`YhONyE7|H6o(dA#wcrbOyYk
z1en-7MgQC05EA3&7Qn$FIgFBI{Av^t?W6s&<H~Uu_2g+!-R8HkNX{OuBZw#{ZO{`@
z%Jc!+z7-QD9c`{Pd{5*4FATx42V@uTFSOZ#9`IcbJ2V4Z|MupMr>QWUjBD(0Y^u4)
zyXB?4FM08PXP66iBS>m++IZT;X&Nxe?r59P<+?fl8v(h34m@i9vAe`)SFs{1dA0F2
zcMNVC-tz7|&wHv-uy#2XcB4=nT%Oxok&>SE*`K>N!zrZ-NYYE8sTg_>pDY>3Cz4&6
zqhnsR3zM690}Zex1C`PU8~)q{>~f+imiu1~t7CHpjfsR6g=9h4DNP`25&y_heOCxq
z{p7qnhOfzlf1|9)=%Gi{$h9FM=N-pa-{SYGU#4eZ#<tzHVlnE0gJjy($379}_ujK?
zRu1~#EM79U@`E-0&J5kYlrYV(VBP$@IqYc`llA7ZBK4R%D=zZ&S8g<#TL4QchkF`?
zxh$oKzt!t=C*->VN!?`2o~(Vt1H<adVMaR?VW2*=SfeUfxu^rjIdZ{i_jOX^p=o%~
zfwj>>f*QGn3RCoM1xJFSdC8#(@36RS{9Pq}qn)9At{<u{*}+j&VHY@$e$~KVK2glp
zR_kADukmJ&Y{hJkn*%CK$2KO?Co185sv$*<c7L)ztrmX>ctg|7(bD60d1)v;!wQ0r
zh$PtQ-6MN_f7>G@ovSjVvWqFHfpqW{)jO)bOXj|rMZF|4e%giTs+jv5IS*aZ22|wH
zeAm89TLiObrsBOQ4iGmp<+p*1K`U{}KT}zVp9VKN9vn3&$nW=tOXqk!jcDEE%~^rU
zEr5Rp%kRYuTkSJB4DdV8V>5Ppnk`YD0X@8Tzs|$=t`Qxj^r=UKr@4jZ{w;NLk+8vB
znD4wz{PWJ?6>Z9^fRLacUuxzR@+y(n=UKpxcs9ir@)vq`?C&?*=}yYm$aa+)05O5?
zab+%lhSDt=o50bh4Mh%kY!Y1m-|g<gDQOx<*{-O%VBgvgYlZ^&n1m{{)*ZE!P8L+E
z;K>7cDNVxfWs-~Alq04Esag)S8KSuHXB5j2m1W4|=eIGpRsDYx0gt4B^9hC(tjqPv
zC^QqoUMQCO%2MW#G7nbbRgt-Q*N=gCl}9V*aj|Uov=Gb8V3TusylxJz-3i~i+(5qW
zO_ldF17w09LrO_HtKkps@PK9WT2w!z>-u{c|9mSg(qPUZCNK+`DfDfc$GQwx&5}z-
zeS1F6i9amn+xZ7P%1SNi+7)E@*dngp%p-o9(l^LG6JY9y$~Ab!fP&~{xXU^d?Y6vs
zRY(Varca$^03fy1u<t(jB7!?9=%S10c*1~9)UEx+L43TgT2KMcH32L#+EH5gmLl0H
zV34FQ;;aW`0qv3-aGv`qZ`*g9yiP9!OYD(dX(dWV3{mjb#`)SC34wK;ZV&rX-S=jt
zoXwcB=pd=Rhl_drZh*u3`oCT%1=fQ9z+nD=AcS;>+w3`ipSv2yHW1w~2pmD`&OdQo
z&2&2Deva+l#7qP89T8w$oP?zLr{Cb>=r)C@@?h8Q(=ZvHq>gtQ-<wt@3ng4i8$62u
z#lSUz{^e(gY|$0aAWc=$MthYbq~GII6c>9Qd}Nse5&xEEYQBYp+!1}q-5};tW22IV
z;IGd)7<}4P$)7&&5S(bnpK*A9bW=CLZL;WR^Wv2;5~cpK=;>&*kdoy|2)h+i-@~u2
zWq$+{+bpLqOIM$DbY0Q_>n2g%SyR(#d22^6Cxq+!i&-t_ZP9?7f3hrtMP!pv$;M7p
z*pZNo@;kmsjafF?s?JLs&{Yp|WvFkM$n)7X%f~%MH$^ID{}A|_jHff4`0$=$Gx{7#
zh|liD;`7Z)(&19m5zn3LC#W`87ZA(Rl`q362N8_G3Wr9QZ|#aFWtcgko&&G354{VB
zMd>)^F;3YM$vy3nSFCB)s(9-J`rg(Bz6R^ppKXus)e<PwFFY778$JOI$*TGS72Ysn
z;r)=H4_|tpt;4pC7S(b!N(LJXf_H0(X1&C&VcZV#nz}UV&BJ*%t2T6ajl}dJa%mF7
z<<s-jb41qO&hIRlnT~M(pIEW?KU!+l?C)`crtuphpsg5exc^60;>)Le*e~rtrGJ+G
zN|~a@IokADo~W#q5+?+g(zGzw<VGwaUq-()w|s4@fc}1C=G7zQ?UzxXY}Z1V{L*($
zTEuUui~^`MKveCcSp({493OEv4P`NL8D?8V5{p0&kPk&GSkJU^FYZ#m7Tf&0RGQ0F
zGx=CI_z#9d+7<YK3PPrZ{DL3Vc}LL)j1leE2Km-AW;u5;9nS|FT^v+}+#f4#`3MX?
zoa*skEN9wu6f?F6yWeDU?(r-3E?uaPHQ(ufP+d&bxHTUWOY4Q}hqXsp0L}WfFrYG2
z8^^vx2@mYnuK%akEL%N<&1_!Ghftt7ytK2pOm3@0Jzn1q51ksqEb1BxJqDl50A>d4
z9Wg@uK^U=#^_oI@_Vje`ALNL{JZ4)sxcwWO^uI%C3f{1xL&QR!n2MJ;*&V^gE$mj2
zhnG|#>=cZLns5v<s2*kw{x?H%qZAc!0u>9Z84aL7)NOz6TGRv56!?vGSl+c`l)}U<
z5Dj@`mx{7W75+RE#Ta&}uv?mWM$~yxtTBK((N?N;@!)kv=+Qs+c0vt2RxsX-APmex
zaU`O7ic4Y~>(9Z0aR66AFO4NeRi6PlL7~t<3y%OhN5h3rm7n~k|8g@%hD3j?^*TcY
z_%sb^+l9j`X@9cu)mV?g>(@xYNc6(-L(3=Cl#Ud;T^Gg-7m;o2#8)!t4bRH)kQmtP
z?%?Io7p**$VnD%TU?*KQtLKvA`je+4enRBQ+wkR})bf93WZKQ0kM^E&{|_WXsb}j~
zp@itzef927t(QzKD(7MztR^b;vIN{-*4_TtoG#a;=qjWBD|eh}mm|76u;EV<sl34E
zmtL!wg=xog{qA5+lK~j}!#k!ThwPbvu=$?*)rpo~Mxn^xJ)N|KtkZ<vbjF5Qablfy
zGUR-+z(ZWc>~LaJmFT7B_IKJdDlx5CU3V&ni}p*S-$7$~_?&x3_U!wQkh8IbxotIv
z1qJZY9bFl&n~)ZVKZyB4yuJQ#KMDfgzv<-894cE>`bbvk9n3tr3*<ZyfZNPuY4EsK
z)ZxyRu>Rs-u=jq1=tvwCf70!A)V2FM)c~k}T#-%g_%=H}O+ZpH`)D@K!6E$`ax(#D
z-Aqm^33ORyZrzU4?Ev&M&x<P&P1J3OU<@8vV3IlLo<)d~+=f2i>LyF{Vg>$tgp986
zp(iH4MHMB|dt~f)vfZAotiKA#o2kNu;}Or0jKI8|6+6<$)F<w)bsxS}m%d6wWAjHa
zbd(H0kHC*NU+@t`J{nA>ga4&RsL|bd8}&cX#w_`D>AxxDv0B?X<;9B<s--dqIJAA{
z?gQW18UO_%Mt<O3B`0_Y5{dJukki+c!QFHm<#;VoMx@yG;u{fWg#A>I53BE$tY~0d
zlC1<|nc5v&fS8nU_~RlkB|SFqtQC%3{bj*2S+F5^vDk;sgTffU0LA&8nmH}@Y0K^I
zzm|+U`&aqKjoUtJjP6&Jx_6=ar2{STZxMwbT~e3eF)%M$u5A5K9&Z*&n5<;u8$+$_
zUu~g9zh{fGV5ZrA{@P3}6!9Eo@_MA#wV2FK8n>tytKth=%60$-v3-?7Q_gcHg4p#U
ziKHS$J^5M(?DP~~F8tfju&Kgw+EhBs6!Yt)IWnMMHxF0KgS{^1>!fU8A^mpoA?rt+
z^yzGl|L2E4pg}m4HGAE6FMS2-i&7J~M!czEINgl2<pVb^$3Q0)an($PVuZ&6cZLJo
zneLdJVp6>43OG(tZc?D%@*p83Cq?Ck+XGZ-VtV}q=kf;hqtPViu~XZX_2k1nN<a=J
z)01s&R`3`wHqB$(gMV9FuVX#G731D|%)4&$ZNvJ7W<e0#fPy>RRCXcuaDs2R;pW1-
z9vSaDx?#IKIJ0;3w=a`R&Y4B5aI$5TBcpXRfgW_tfO*CA)@@oPJMXWD(U2D+7P^y`
z*Hgf+BgQ}OcW~jli>Ef3*%U*Z6)TFdTX{Dck)@KDxoF7Im~7NrYVlJ4gJx{!SPJLv
zqpZs%J?BEVuj}%=y-(chZX+D^y0SGuJCh$rJ`DL&2+gJqj#?D<brIIIAJjVz%~0L=
z{LuNXrl$Sk3m|{Hy{1wPGv_O^hd}WP*fdIwj{)BdTH82YzqlZ89l+)^G@#dbWjAJ_
z3`~M$@1OOjMBdnsZ!USU;>F9zAzrwnr~h&ud`1nruok1xIg1mW)gQcn|IRP0bKTf9
z%Y$j$MANuH%Ep_Io^S3!RTlzO4->S$F};7h?v8Jj#F^9w8{->+c5G-4%zWJ6XxdK1
z+|XBK%pUgVhb0Z}ro&Ulo?vUq%O3KXEu!)?fiXYnsGH_thEteep&YjWhQ(N-20{pS
zuo0a21a=hS3P)Ge1Yj+l$8VOlcLS5rzeo%$uXPCrlj$tnyT-(FT_>d^5L)cA8<<C?
z95-rQ<aH%E6dwt^|NJ?|T!;u+yDqgOu_p>j04|>ivR#oKx{9TM-^{q`(p<yw=q*zX
zi0((cDn1+6tU6Aj*i&)&>_5cPlJQ>KJomXeUiG=Wmw7u&{@J?5y#`H0p|K0aigyWc
zAKQT-1|k|iukcd|5&QQc`_C~)FfHzgZ5tJ3&c*^D<tjf<A`?Iw&c;H%$nBp30Ck@=
zEc4^adUJmN(_F8!rMhi_Q{RJ}xl)?8W4FkX2;>uBB8NvCZg|eDH}?;2U~NSg)aj>=
zaAb%#P|=s>>whML#{skXPZHDg`W8x(&w`8WyGj#AzdK{4S3*{%|7sM1|Ix})^dPkb
zl7sjWwE{9uvq!p35dMClChLNX#aKFLY#s0dtmJ?{5z-&oDFHa$=WGHQRjEa(V)SF>
z{gqHmcv9Fc6XlbZEqy(>Xk5>JLd%jP@o;>|y_!bOTHfh^!SyIdpC6`Z;_C%Do`vm6
zk-Z-S=WIx7U1aawi4!6}6ELm*7-y>AYhmbwm@j@%<8`h0jPng)L5qMYV~9W>NYffx
zfKTawaO-^v<Uy1ZDU{KV*dq^n<*S*n6f<E8uWae4H$Kz=!=~O6e*0;pvmhE?)x94>
z5{`kF#M85}@Um4qukWI`j3@q^_*x#^sN;OKKbL(0G*UGjt3T8TEGlEId>LxM5HqNV
z^wEE~7dLrIHcevi>w#G7HmCaSVrm&cfy#MyWY#uZcKO3Q%pFg0of~{b%q*$C8{nbe
z^rnX1L_|5x9r^D%8bHU-p%fH9`w<tUp|z4%=XcIsQ4SLDTuY(NHb8TwMVEDLj*o=g
zER*gdy~Z^U<AHw0%c8u9vgI=Y8SQ}sXT(H<5#?ltC;F%YgjlTbTOr68fXzJP+hq({
zkOjPKKV8@G<NG%vu(-oX;8_uzG5L@V{M>ozV@X(NzUHGT%3M?J(v|5srD>vIoaVE8
z4TXYB2ePb(+y!<J19AMIiPpub2>x0XvXLo=m7e@QG9KE9S&9jc2GUAj(h@U;me2Fu
zxRW{MKl*KD<><deO~zBQeC03cf$mHh)iHRvLY90Yo*B=F?xBBukEP7jsQ6&Vo1R^}
zrgA^8IaRHFm$`0R@%fu3S6R%(TmESi2P2D-l+a_q5<$9|Bk@M^%QIU7V~+Qn5WDdj
zA;uW)8@8FCHE#U-?)_{n-RD=*7@=`-IXtW*7V)w#2srOf6*7bPH&{>+ec2uSPnEk<
zK4r!NpZr67!}NKH-zk(m1ai}Kod2uS2KIzd6+FSN?^;J8yZKC4YOx;4$d)2-w@FnK
zV&V--XwUFOCauqziZ#!Acb$IeY1^4EPxI%B-NV<?KTO&RE4djvDSwL2!8$gMjGRYI
zWU9~x`v1sAZsw>pe-5g=b86EKx#=-nncK_<aAjZDv_nFSf8m@W(6-J(rm!kArPyb2
zZ>u=F+xD~#+O7t>9YSs<@6%8Z<tHAxvoIjPHt^@_&zo*MY5wF@;hedFOVss}0h}ii
zd%9wkbpU|_=Z((11yUFn0Lr`_OVF%+4u=V5?CXV1{*;LT?yxvhh0AdG&Hq5LDZ>)#
zCO&?-|79%7)d9wiKN>%WaF0=k3SK(@{s;1o2|M6{&v0;mFRheKDNOB9ULSQ#jFX+0
zr9&GaW{ZK6XS!hHn~P}3QE`u70mBK}KrzBZhM2^J6ieJ`{7gbRyOS5%<U-Kbx`4~%
z-Y`)+$OzfBHaSTxI-P-z?gog3*--M2SF$j;F77>h|33b1Aosgm-^npSiki6u1p<uP
zUoGY-3#ID3X|hQRaA%82_Nl-;O<q2?k^f9~%OO}?%D;FKFVzTVsRY;?bs*{enq3u9
z!-iduk0a94^oCiyjR|CJ=*c1qx@xI?<@xe_1?E!%dkbXKzTTUX2CVD5ZbaMh5L1E3
zKmUdN@m^EtCjIa@fg&Q9R)WgU@Y2ppm7)VxK(%Fl_r-^ZTNiV+fciu^mXj770Y0HK
zK6sMt4G!Ra%s#`Z%=hJk@(Wm=PjN4V-LPSgc5D)$JzrOP=D5b*q-ZR!-#qp^(h_yh
zzBf7dkIx>)<sZnCeEV8dq89d)YpTO<HhnVV6RTo0_n9!N+BRiw_b1S<Z_soa|LlBl
z>&i$Pk2ax0O~pf#pgr{0@2PPadEB1<Lf~WE=Ytsa;-wG$?PS}ccbp23>>IW4X6-YL
zD8w4DuRdx81y%nLA1cr%(@zVqH}1bI8On5Q2(*{S^{drkDF-h8Gb5Ccsuxu)T~W(z
z0%*7dAj^cS4H*+xDP5o%bQ$srEyix$#0XOKM>&Yepz`GLAw&t?5ojS)?j!P|tSPPN
zaMoaL$AC<OlJ%OZ*x{c0n-50Zr++21`9_%#m|wZ&rpgBlW?@^ZUzt9@xhPo(aF#FO
zshXp7a(#>0$GS}!%4E0x`D8>M1Y3AGW8f(tE;^1c3@j#~mM&<x>T;U4UBnt+xi$_K
z@44=GR*JQb;bFW_O<z1<B7R*Z2mk01*oSibLa~@pj;yXG%VI9QQCNK6ZC~Oa>V-!O
zzj5Ozwdw?Dd<%LrTlsj2$?}F^xvPapaTDQqP`kB){t_VgG4)8yeY@piSq;|JY#--z
z-lu76cp5RGM(LX4w-cjYuG4hCczx{i=X1b;@dA;3L*M-PvpE|<Bz$6glWnfJ2|&^;
z=C(Nao#$shzbV_%{sf9T|FFa45HiBsKFbcEKTeHA)!}712|O2kajhk6s`fuQWGuj9
ziKXWlT?b7p>_nEFN~Iq)SHT%t6MM<b^YOWW>kgcLKv!Hwi}Ef^VGoE<`e^y8^7hsk
z5I=W-$z-LREMieigFn4PJfJjaSLV|Ch5`UGEY*fmPbsU>4e@1~6n~&+r9)o=k(s7|
z@2p5sHpmOmhmXnvNlDPVvF);X5E29S=LJEEnQ&3{A}wUDi9m>~C_k!eme2@DzG^h=
z`YXUA1X_bLL4Os^%{3A~0EY6#w7XuogsAY=0ma?c9x^Zwv=be6z5@QM2*rxmH7}|j
z<_1T26(N86<Q5vQZ?^!*JOjwAbO#jc`TE&>4ch@P>KUyh$LG{x{8>=2Fi{Bd3AIr8
zKnKWcBipyuCE(G(A2g-kQcKRC?ixTt57>e+iD&soZ_+XSB#^)CdJH1t722~&EX9Pf
zh2F`ybi{XacH*C=!<7!qB@|L$U_#n8SyZ6I*w?t(G+fEhm>Lt<t@u}DbTO6u)(fg5
zeW^zP<)=SSy=@9DdY$?MkJ7r>1I^$c0G*np1GNfu>n-kgi47lxNdJITO6Q;7!^3O5
zQwQ7fVP*hqeY9BN>?*|Ee^PLGz&+?F#%$u7fDqv>+4xN-aRgKnBKQ^a^FAz%SLYes
zg3^R@U`eCoE0L$Tuf5YuaCf$s-;Ty_i;c+TN#}Y^Jd}hLlz;Vij@;nkZ-iC~mUZ}&
z9I3H{EtF=t%J;%cY<`+0r>LKm9aohd^y@bli?J7j`Xc9z$Xg}_wnx9!Fy*|c@7heg
zhck1UGT9;s`0r)dSKG^Pp3#huX4+Yvw;KF}hIN(R_6yDZ^7IY9NM0_go!x8<<(Jy#
zpjuC5SYv<G*?!HmngYc}obJA&&y$u-`gpXoMWl$ik>*)GcmzHgAqD&dcVc%Ry@veM
z_j&+$JWhPJ&nB_^Oi7o(g^e)2P!WHN*EDP?lC&_amR|_s1q`ktHDjZ-m$itc-%g!H
zfWBxqj31v&){I3|_3iZMxm0=-M6qSp%xy_8@jnJpCM3^^!NB$Ik*uQQ1*ck+szy$b
z88rFw+aOEQ{5aAzb=r=dD|5twiXZ^x8OEpN&dJ`o^!#*rUne3=#rfGsf}X;#k443K
zbd}%?jTcq{_KP^zB+oGI3om;*+3m}i+RWqE^Gxl{SjtyTGxkD%<>#G^bNA(HPt85g
zIWkvLqIu5w>RFUxNjH^&H}F?2iv&qB0|BH)9xU(yWUV`L+N<)`aD!$`G#SRxs@-#9
zrse`(j{Mp9IUL?@M7#wVifWr=J@t%H5&0%qWx2|Y5OrjqlcVNV*@;dWu2cYjkJBms
zcG3G#&-u87MsabGO)7UR(xWu-58fa+Qtb|_%=4A4$7kpUG^*Fz%(c*lOQ$Xq=(%gp
zny>zynjZdU4NAr<p4HZjcXIVEo?#t@DY*X;neXh>h6ldzReFOW4ro%s`}=p*jmRUP
znRKY;3xby2m<n|p$%qh3p!p&@R(blNRYkHt4=T&!SPY0WWOI7h*P(N1&bu!P6ko+t
z6ONV7=uHr=JEef$Z8*{hWx?p$w_O9vm9=qX;&hW9y_-uEh@n22iuV;!&ZX~Gtg<K_
z6wZBY|HWxx?_`WrHuvd5B6|%pYy0R#a|GfjBWub18c~=P?3uT;lm9w3(i>lItLJu+
zlg+w0kNihz?Yoy69-f+&6ZuMHr=&yv87D5ZzI~RQFh@U@4w{<hDlJx3asY-I)^pPg
z5WjOWzI5UnwQ`LO@U8`62iYv743#kPENBIVwEdp`rKcKh;=}hz0fBo(Fclq?l}uso
ze0SSbK^G5R^E*ER(>Q^PafEx5`9=-Hasz%0M!7%9S^UCQKgoGL#V|tdhKI(p*oHjM
zPLXp!6v^6fCXSU<<(2}H6RMZ>oWDWlY+&p)u6R$kOE#llH_3%32Va(gGjj2&^8$RZ
z%Hu}USDxH98!w0XW!?@t@C%=!mnwNAhu+akgstNnz|#T!0}C&IGOgB!#z|M1XgXs9
zU|F+vnJ?FafR<kEG@6`W2iqR+Ylt6@)E}KX(re*_<KimL-acN~1Uu>E$;On&eWjeu
z?$*E1zaf=0kc9|Np}nCRrhbs|-VWfc@b)YF3M*D+AbSdu&(M78s`0Ap9`Vym?Jz8J
zb7bC7z_^=jt>Je!B)mTNZ-Pd@9mI$0N$hGmBO2wA#5i?4V?t|Xk-qQZT`*4j%~rBI
z*u%Nx3aVLN+WIadj4p^qnAH0q<XifKEHy4+J1tYpfWr-ykntO*)}CJVMmjwrY2D&u
zGZyDX6p`@C?~a}$Zc`2XvW;Cz{Prj{=i~daB)5T^!1ITu*3h<UoZi#L7tPC|qj^U_
z!Rjk@(am)n6NwkH^KK8$<1Um&IKnD?amWod#%zeGiueCOiXKpl_!+nv(%SH!mN#qY
zY+^AzjYB9d+2w-M=%E)oKT^uX6Zf%5QT*NMJ$$b3*~&_}IY=jT@ErDbM7n0c?hf)|
zhs1UVr)Ixsw;u9Sbk-e&s2X-|D09O~zu|w=foDP4z;7w}-EGdJl3F=;x^>@#P^@ma
zd=Ifu+P<0{SN$~PV}mk`{bmjm98}O@0$10FYi=A;3{8oAj{P`a>wL)gEzVxsT-6rz
zUw8kbT{T$LMnrW$<J|`MAOzkam|^gCXf^>hCh@ybUZq;p{-1Wf_qnXr35tDu_|h|a
zO+~o+@b;eE$?Z~Ci!7G=V-38iK^Bj`EbQOs$GiSLzIX)W@3npeOc*=bbnms^iy1&!
zRth~2JD4+_eFA-#+6~40!r}L=yz<`;D8(8*8f=*D?+*(xpU4cnIfFs@U7Cv5NAQX=
z#T$lVEBz@KLGt{Q30ypkbdl0YlrI9d;=fQd9Hr;muH{S=MsXQvHIPZMRaqXhT~lcG
zhw7YQzsWQ<F<<~M`#_lVWR_mLC<O)u@*RtVMl*Qb!YmfW4BMr61^x2Nfvemve(6Bf
zv6(z19+8zn>6gpyKf)h6gc(c2i|%w1{+gfjwUP_O9-D;iOAKG#bQ<3f(D?+A;0t%%
zwIx8S!kw2ezs9vFTI6fkUAGrwZqw}J-RY>YHOXGq|A88MWKw-etJVBw^G&W4tf+=j
zmUQnCWj+VmR2d5W%a|)u8dJAa<YMsy$W~&}ZwXbM;RZ7P+clhh?O#ZRxCCOsXy~6l
z)q|F6T4_nlZFY4|6I%qP8xdaeM+5j0I)=ZCOuB(5h3H#s5Mb}P;ZE8dRTJ?BBKnx3
zbH!T|u}~>d)6*m<GsqL&JD0?xFUicZ=<{w$nIQVdvu15D>&}6G+JQz(oa8?2VO=VO
z4@=r*_{xC19c7Wokf|CHabQR-zvkk$B)yunyo}KZFPq#ZAzT+O2^Px!MgA1~qcS})
z77zJEIT=?~6nbn*n%)$lbzQG;s4p>-r=q^K_uSy`{2+M5)c*C5t0C$>)whcfPcN5*
zh(joCLq2>_YsHl1(A8KEstK7Yxy++_&S8XDo5$)s3}{kOff>rmU~t-lGN@=yc-|e8
zN4%UieizO=!@+SYwv6JfI5V{663-A!HfP3w-FerY<lQ{*9x#qLGUTM8N@K#x<lFW7
zA+5c?x|8s^o#i=SsxCDbWW4a?6mZ)Wm6E9$e#EG>S`_ECDX+gwZ~cIz)$f{t#DLnr
zcX~?jL%i^feTB<j=s>A}7AYGm($k1c*OumpO7$Izf_~9KR78e>FZaxql>h@Pe`gfy
z=Wlaoa5AA|zDFHj+)}n-mE{_0N>gFuQ-||=wxwOTS;r5|E%<0Yr+5I-wHx!nZw@|9
zGr1G#soGN7Wy{>($abJcWsdkXeL8NW{9|1S>^Y*p!uc3HGFEQ4MlkbG3y(gIt+|G3
zKaTx)E&M-_-XR|*)b!nA?wT4kL726p<na~w7$u2@Of*35T5URrq_>#<*;AupkRqb~
z9X-~*^r3^W-~7Gs>IS^D?O8J5iIN5_hrfwIN{rox=2+QZ1qpsIqQ~LLMNBAhc_I(z
z9YH->jW?8s&ct3fs%5vF?Wy%&G=q01GoB@B^+9erHmLb+YQsOFXqn`9-C56Rzi-YB
zH|V#?5M@eeyET;^>vDD9!?QmTMulc0SpJmVc>0_6;h*U)+wuGBiNyRkVN0FW>Ek_(
zaCQyI$&$~7^swZe@|YCCM;fI)!WIj_nEcWwH2E`SHRPh-jsdiw&kmzH!E<_pa;8WA
zM={Z|1pGUk=hR7s?D*i>CT57m1d*-BzTDK8xHXxWv;MF@KAis%ud=$JkGAc(r6obs
zWQwgbNm4Dy?+<_)04)q5Hs+cXip2S{qNNVBU+5vKz+ZS0PL!|dVW3+EI^F!FX`zHw
zHIb+U<T-}v<8MGtD*<v~5Z}2d9)#=<H)!B1Vt-#1`UAq;faXiw2=8H<fq_6AJWg}e
z&X1VPEva_G`F9BB>_%lY?R+jx0(!Sa47;1NY*ccb)vu~n%KlP4N>hfR88}cej^iQ<
zq#~$2)NQg{dwc%skLriyAx|I5S057YI?yLkkoZc7J~-9ZLhst8mMJVE*t6Jxna}4G
zl9R6Zk|O*Fsb>?0q2(GH@ar*Q!1cXNVn3B?%GYL2Z(}{m&`9|v>CC^7@e$>D&Y^;I
zt9NS$P;CdcIq>#$@uuznK&5Ib`cHLl)6cdBGIJ>NC%*~6C98eb!yc^4+(_pRT|Tg`
z8up|dlw#P+FnrYam#go*U%J;)LRO7Y^z?DyFm45tUq<vQccDlCkPr8&_E~eW5o#=f
zO+lC~eOKW5hl~xAq0a^3Q;*cLgZKuoipVl7hrv)G?hgqm3ik%(^?=sK@s5EN*O2O;
zLckPWr{+uT3pM9Sxy~GJk@0eV{nf0W>)5z|t1Rv_cukF}aWuZ0C_VN4#I|fsiDZ8K
zrMK@Bo!i_+SnK<Zy|0|fR7yzV{F(t*Lq0B9Un-%Hz=mM=X-q2xKt=2<oeOX3spC$k
zUpM|1SsMnh17-z<CxzgX(|=>{qaWyF?+}D<C3!WU#f8;xoDN&v4wE4XdD4CL2VUAz
zF91J*`{+^I>Z<+eLRzauS%@pb{fsxKk83qi{{sO-Q@H{1c@)18!@cyA8Bdj2vW~Z*
zo%!H^Vd>?Cs4pOOVqEU|AL#ozISa(EN^f}c3Ft<|7IR+|Fd@K%On&zo^S4AWNf@WO
z9(*teWBQ5_&i!2=Tic{%toG;AJq^e%a>Lxl<oo-umDz_%t_>S?fu2ESstpEqLP1w(
zTU<=Sqm4-!E2-9F;@2`0LqFcDL(Z+7hT2(n&dv3;9ql))9YRCSx}APhADmNNoeyE|
zd<#5%!)w+{Gc0T631MIE^d^RuJ%sNRk&VZ72|=uN#7)${$jh*2`AeTWS%#RhikGi#
zz7ic1Mi$!#!xVZRL8<hre4#TGn0`s~jjJ+O{f?}y#f;zU>#<lXOT>8z15>+H2sSV7
z>*=(S@u!{V;$6I|A7j+Td8d7bV1&ZMmbic<dX!t-JWKh7SFO3ro}QK=b5RInZCviv
z7gu=_9(bbPp=kXLw@-fZ<is!Xwpl8(G2~X-oZxeY__K2I{dp}`VD5#QK_2fo?8%<|
zyG~7RK@~Vumx5b~z5mkw=2iTLOaTKnPgpvDo7ByRcrJf0Ua_wWD;=H~c&Jom=JeqN
z_j7t~&zQmG?QQMpLw76j;Copqw$zj}iX49kv`Vr!6<U*bGGNiIaf<5k|H@hB>=o)H
z6A8QOym9+No?=Om>zin^4-)A`x!Kli28qJBn=w}3bgp>x0tR__i6c$XYx`qzZK4&}
zxj*=}9$xQD80K0J$tQ2I3%$9k(UQsxl=r@6eT5O|mTS?MIm^N`#SVxDljtMu%}s_g
zv~nOB`O-JlciG+YwlB6m3xKVC8;dY}@`V>=@v(-(CCEwzzNY)B<Ca?^BacSYO#8qs
z+-HQ0eA~=)z<pV;=dQSrjMPMzRP$`EWc?5H!$<A&p+sHe+jI;}Qzs@47eml6>&=n3
zf4H@XQg?dDGBNy9i7LH^)jrcio;z+ap|Svoy&pUe4#UF>*+a5IZfbmGy3T;o&dKN9
zDBH;oziWUg?P8bRStAC^!UrwyK6<A$tycQ<l94`XR&v{&G+vB}<z&MfMm8rRUz3ja
zsuZ7^UzP7XcmhakEyiuk=c}J%2TvWvv@UG30_UEaFPM3b%|X;eXCjSx5U5{mbI?kP
zP2bD@+*cHLNlC<~ykyJ(k>TlV+I4MBG#pC%<N9!%7;YldPIx+`BBk-G>k{^Jxrwwm
z;(@RA+V5N26pv}B$&NhI{CD2LT$|rF_JlU&mA>lIPJPz1==?Z&_r8R2#@lr@+w1x9
zsU*VJKrN*7=~+c7+o1r(k{|bGt#1pIEGUhJIY{;V)#T(3Sj>6uNWZaK?f1!WxDr`R
zoq%k#T*KtJ%B2aLaAP{>Cw^wmgcsk#4iA~^gNHLP`d@}*1dW0^U}kk=&d3|bx${{Q
z`HxOI-{b}pAE}gnP@tzYGNT-gdTs+}&~e^uZypq8zioR9%Fz~(Q9zy~oXclt+-9#?
z^2gdo!Al>5uQi()`w##<Sq3&=&|fypD{rQT@%1#tb=tIp*Y86VO7G(7i@);Ad8dy9
zCpenadCZbvb~AWUisnJ)9GZehw0t|9p=R!{V3yDr>AH;)#X)1`=g;%Rqi1Bh6#Rx|
zKEwzr?hoPj3EvIvThOuqtQvhnN@6E7JSwXBV<NmWh8Y8|AN8qdzsCoDtSu%r?05MF
zo2y?xmAZ{g)5olsBDyy+k9z6HkhLBr;EY4&wQ4lEh-%@@>{R|@pU2-PEaR&AaK|Q%
znPqZI<7&8@ZWl76_cG1cibyLm{(K&jx!_BAP#boZ5OIcXjC~Zi+YUrpbMY+zkSFJe
zK6*7emf7#%e}qra-eF@f!p!hjp$C`r1G*y3xA<}RXH6Av>VwN2KN^bq{jIQ~wtvzb
z_dsbARu(g*zXqP*dtJjMFIz_iGYivCst0%uK1ka-dZB&||JZ$`U4#h!c4h4wj+#lw
z#l%cL^YFjj<tDh84Lx1xBI&G4Je|L(_E^b1GeCLigNJ<A%Cg}QhDZ(@X{k-p6i4gA
zFU&q{&d?v8L0N-Sm`F4<-(|&Z?doecDYA2l0Zqsb*y_9zIPEDWpT}&+&zEwbkW@vR
ziE0q<nwTT@nXcUz75_hwp~lslKlt~RWPxFr%U~Dic@g6tZLAfL5FS8Uup7|4*y?zO
zPvO$9JAnobdo_3pR{NzdbDsrSchRxWgM-P{GNLZ#ff<~~<1*gMSSC1ZYR2DJ)uY@W
zcN4j9o%z~dnDDpW@`1U>((R@NY=Y^JBgSe>GU>#Z`X9>(50Wd>7o8Ik$(9PruYEMa
zoqARkm|o_CtyQ~LZyR_!+vhQ@K`F26CtU!L3cq);+vdbeeqyWXRkY98IU0}4atIC=
zK^E=mhvR-l96bK`v~vLgB&F^0gFj-d)>V53Sx7KiEkaup$7j;mg0kF24=o}N2%#Rk
zJ94+~Aud^KwjKl-mvSZ~tI;XyhjXANrhx$leNox!(RQQ>plgu<4BJ@A&(s`55`(+5
z?)VJn)HBJktJshG8K8}Cz@)o@jTgxrw<AOgFe))9nQA2ejj5P>VJHR4&`PB|)($uM
z&N?kU$nbiVjf3-C5P%k3T$v2Ul;Cb=$TiR9)}i5`vb4LiMH2XI1unmFAKhgQmBpO(
z{OT_q`*#78wbc#6Vw?m4Uz%$^l^KN%z#r@51EZh$z#@;C_PgZ{NUU_XlN|mB!YU>h
zDn-_5d6$Ar+3gwS{yu42AB%3-?A=T64Y>)Wz`Xj|F;f_ePc*r|8{sQmGIh+%VYMfe
z92U9w^+MbnIapRkppaytzvzS<AAqidO-E%a2m}7OjFMKnmDetlHD}VQU$BEylp~yG
zHEA&(WUM(;C+Jq#0rKo0Q;4{0TbkFk_4M2}J97Wvp5c*95cPlV#BjS485Xc?F%=mh
z#ydGEH}|<-FiA|&q&4-B_qr!wCo|@-rx#IZ22M1ojGBECWtc%@N3clABCFIVnV@!R
zNpo{$xw}Gx-d?@vXYI5+tD~PTO<;B%L7(+qFc(FC5POxH7CL0~CBHGmR(8+U_;+Pi
zo*evyn7ig!W<QoJZOFdSw`np(!G~^N>vnsi($v&3>F`>Z{Xw}``-8;qL{eem5@umc
z;nLV(Z2#{4%(%M{K1Mjzpmx$U_&hkYN~J))_}eFMYQki^RtwNj(f0q834@|2OIcCS
z3s&^z?WG4ug-akh^MrL;?n3(NGCl{_R$C5iBCJ&3<<g-l2YH^?PZzhKpp_jtLz>?O
zDkI{w^ao-m&^l}DHoTaU;)11=r62rjXr&3AJ68TmuhhK#_sqxx?=}I#;y?yBAXR%e
z02U^TVu@8r-BAyL#w*k581I>e0CJ87({nV*MYdxzp1l+|mfp~E=Z5evT=Jl_B`mk6
zgybx5+MfKX!EmsoIeNCs!Y}Q%spi*GNr*IA3~g3d>V(BH%xyXie8Q@6t^nK;qkr&G
zpQfHoSR5|?3dhl<T#TJRQH9%quFEK}2an`-m+`Mq9^yRoxh6nTMUOZxzPs?*ce2Zj
z5p*_B3t_WyDRMO*uNqUlIWBc&;;c6Jp*5gKDJVkd!vBYNWJN#Vf)$o!e+z_y+12cx
z-}VCe{G8*?8;_{xPps9%nN-t;hzk=A^b!xxI-&XR<QAnEmi+J2lEu#UEdj=j#h7%`
zUwZLbryA)WseUN`Xy}d&Lq~!?Hj#X_Q9hU6XvZ4PW7qo+VvI{?kl)cwt0E^+K=I|E
zS@b2v%sXUd`&Y!RrV+D9^YE+(DeED0B0wg+JU+t+(>nT_!ux=WgOxq>zr-Vyov9w%
zEp#<tC!0tvvrSO`DX_I;D3_6=xgaU25gy@hqw0f}RH;p=EQ<}zFzy7z+=^QZW<D28
z;J@tNv*!i#HkyTmCE`yOQvT9EcZrW3VsYl5?R0moNYOcW=8KuhllK-v(}%I7Rcf=z
zXxj?6W+t2Feu0+pi`<2tT$Ba0;bm+e<D(EBE~vn>l`$ZPyUclFCVn6h8EjiZ3A|lB
z{y^4do+lnEtA*{}6Wzg;)3oKaKh~bLyF7+jf~`YK9<v?adSF**50l+nKlWjdaTr61
z2Er;-<J88?K=$TgDqyDly8;hAXfMBkfJ~NTIQ}|Jh7If4MLU}ekUjK0Xq7m3#gUi0
z759@GvrB*>VqQJ~y5Ci7OO`s}chFWK%dWk=)YQCWfam_i9y=fArA;AALqAvo^a?dS
z3vbHps?cAb<zZGfc&^$@(MNy(Dkm-3Vyo%!_i8#r4k1fLvKiJ@v^ZorHuQ+@jNuM&
z+NGD|)M$Ik<wkW1I^?b0*ZqPYwjmANr5{n^><uqk$8H@^%i92AeW=NQ-Y7NFR*&X`
z6O-y*ME3_i$@^fGaPs3>0~h)AW%gwJ^M19tLSVUt?ZlPGZb%2oA}=I0-fO2>(|8a|
zm;MfFOT2Lfp*}N)FqL2}Q;-YWwS)i@T0;}(l+kJUThwnQqz6HsBu>!)F<mleT1!Tz
zmk_!AMQH9koWxEb><t!Pl^}@*hPDH4AwQcm@o$U?T!^I{9msbI;dxIKUy9!Ne#`*A
z7wb$U7ugf~#OX)T8e;4qNStUU6Df2il39p*dkZ}2opBoedr<MWjZb-##G2*8IwF=0
z-8FtP9VkwHWXNF_@};aPkUfU?;jj1*QqhLN52(%1rXS`3*am~yXw>iU%s*2znhs5D
z2il0H^fyiRC=10`Wj@&!+-F>(S8W#+OHuZs433VICx*FH+^Z>bds&F04wYkbNKF+h
z*X)n15CHzNW1)5HvH@y1x?Roke9Eeq{et12iEM6J;wjAd^uYXopqk3Rfv_ZG`53}^
zC%+a~^xpYL3RSiA-f`D%>6H_5zrW_xgNp!bx^R8>Bl84tP$^lVteXAmGh$8`)aKa@
zJ%#B`A7y;Icxyv&EiwxEX@QsfsPuapxQy68-0Y910<URC9+|oodv)z@aTn+s)^2wq
z)&()dS<@%~pqc>)DQ&^O%RBT$MR$@-E_znEZa8~^`wwNqLEk~-bLlm|mE$ZMvU6Q%
z`)J3nndE)O?DTMY+Wd`v{*jEgKSn4Q#3T>&+0j|$jVcQLhsv$KOLGtV#!zI$7HqYx
z_r-?~)ZKbM+vxOGbWD}*9Ax>6#6^t6{1~vOZWGm*5HiO9<N~0D-zUGMGv``j?b_FV
zY2qriTN`r!?tBAKYw{D{`a4GFjv)jX`=zP(Rh08_{?i8!cmF<+-SLiGddWMXAdj_2
zYLrq;qNM;I?qLWG_I>Nj3$X;ar76j$(!maP+uX|@`?|L8DUKCCe*Bg1G1rkfSdx|$
zjWFe%M9K3Bu<b3PVy88-SNq8VQR-r8k68-}<<KHER`c%(=Y2xsJ|@ca8wquyL>1T#
zmxkVYojK3+61_H_#Bhf0$dQQ_v7<}Q7rilxZpr3Fwf{x+x#xwLs)0P3Hwqw8(mj<m
zn=bZ_|L5qu!`b})Hy(S_p*E>ftEjyRT59jwElLr4Z$cHV6}yCr8nO4*)+SWdh&^l6
z-kXr`@A>@x#dW!^oIK|_=YHS!>(+8+9-nnJad+b_(8{^nH<3Ox=2CO@MFA#>$fH6T
zzbZu%1JF3^z3t%+9DdoRfA`fj^1DIOP1s3<C8SQ=7&})9o|XI<?&~nHM<p~1jXAUe
zrkqV_^11P0=NP)nAdvBRQ9pH|?k#yLmRDx5wBzq2L;dJj7!>#>bZ+m0W2QGwfzv_+
zLJ<Ee-*DJP5y$=i>|1StV0kQ3H#ZGHLDFuP>}t3*SY5B9!Fyw#@y=9y3QT*c(_c_`
z*(!!#T3CR)>)m%1Wlvz(35fr|v%A*&5cgN?0H1I)&GR`<{sqh$+ayb%;p<Ge;sR&;
zta;b!B5m;?^deT7bpC~VD;Z$xf2Lkkwzk*9mhC9BYE6h4Wb5?Q@NFfV;}1Pm1hrwN
z)9M5OI!v9WQzx>fN#<@YaI%VYby!8XF?+$<EIyP6WbuiXs?FK<?pHwD^RGa&VTWG<
zZfc@VV*a^&(|HjNGs$A(3cQrUM@6g}wM3h>H(5d&R=oYZn{{ojURyOeQ!1E--|~iy
zRoLe0)|9r;g<(p<@n<8nC7DVA53_zX05rWu^uX9?LdboL5e@rUZgLGQ<2>2>GA)pu
zwKYV#pt%2I$uxP-ZRKszhu`;Ok~_;V+if3VB9;#p;;A$D73oPQEjL4K<)he)%L1@k
zwnr7~m~&OI+``Slwl3~>ha2I#!%_r&*htwuZ(k;Ctp9A|1IXI3Q_O|@a&Z0GFo|j#
z<mBqrEh(lZu7B$GX!;EGYrV-rk7LVO7R#h3d{K*h(_aWzfn8tcQ7HeiTAi53-4x+Q
z45tlXU1c<TLU@Y-5GLx+WG+8vx`1yBKda2Ly9}TSFZ({+zK~`<C+<8CvKbe66y_Yo
zc57&&hKX5fHB@|%Eg&4=+`oC(rZ8Br4l9DN)fuX$7skJPeY+*WqzI7%=B{}CRP>PJ
zBQrQQ5S2Ej*rN$3fch7#RJtP7R^~t~A^!Fc-o6^B{bPYNVUR)Anc(0xx#gCUCtBe{
zl0vxX$J<g%;=2NsL3RdYk=PEC#s_8FWmg@Cv2^Mg)A+=Ra{nR@Pp7bN&<K(XRJ_8O
zEF9Z_senRyTz=eCn$x#AO3}TMO<&EvD=4mBs0Uw;(2_>^#(}5>B3M5$7NaX?YX%xN
zw{@7lHovah-QuOrtLP9w$y!&+QtIx1_xWp@tE*)I>sG{*s#%*L*KL+`mb>`}HPp{$
zuwbD+LohN2L@O?s?VnvcS-6^CY}uKA)1MJw|K8@}T5r1>p<^+u>qzDhby-@2X1;qB
zhH;4%p1^QUG%_gm^61uW6#7o&*r^uYFj;F`pT!E1{G`Jxt#GP_pDBvs28)=YEB^<Q
z^F~9Sa(sQGJ3?+dm!?_fDiu#-t4#|1J~=yct)vKGr{{e0r8suzfbH>fS|mlHtWmCN
zi7sWqj?+hDsBd$>M#LVU+%5zA1_7d-U!06Ylt<wV_I@d2uvPb066318Y0aWg*JY_(
zf^LdEdB@vEZ!F)xR_7(;-e{ZFp1N~)ux+CdZ+7rTzaRtvP5LiHw>?G%jmpR(ufwD+
zP^_FK8>gpYr1@gI-{O~YLLJ{oSl&*z-fBC-?7BCz$7$*fV0LEJG$Ee2D_T4?=w8_Q
zEXQnVv9{7>6-Ai1%eJ|r%U#Xd^zXbGsD{q&hh^ho;k3lBpk2PI;Ekm1rj`v4Z<8=|
z0p9OCU{fk(npf3tX-kql$Y144kojG@C{(aVM?NbEWW_|b%E%0_BGsObO*XT=0)nWd
zjhOVX|AD3u?=TZbs;`3TFTOrLi+8=z6KwDbh?F{P%8ZTK1KpiV6)oE)mMw+9PW4C8
zw7QR==Aap!UzZ&K?)m{C#nW$6^AQV}zJ5fRZklQ0RVl2&C0|MtNJX?e;-;F`1(I#g
z7zzPKnYpCqixkLr<waDOg)Oq^nN#9$dR^!CFyD@-6rQWh4fzZ1Xnmf)wlfoTq6d$a
zg?EjJ_Eu^Ha=@3)%2O-<3|q<Xqd6+MM9O~*cnMq*>}znhq9tYw_f6gg@AtmsASW^4
zt2kLM#d~Bi?NLamEkDa>;o4#DjtmjShD+}o2u$TEU2~uqeYyU;euat6S9;&EPRO|b
zUy*$|OG1k{I6H(P1aP%SF57Ov(6pUz5TzuZ;E24QkiaEq@&5acX>xs{HQPG@#WS=y
zNUr>(WA_MZ{_D18cwi%KPKV?+G$oYpdCkB$<s$3PlZnotZGZUC+x=T8ywH+&<l@6B
zaKDU;3>rSr7MgjP_s}1XMu6Ty4cwU<iRW)7qsBQ*kESa}%8gY2Ogta)Q9K(lcc1k+
zKspVwRT>b%_sR{zf|Fhcc>{GgQi4po+|^5EtE|tYBngrBeUxn);LH>mJA@$chx?qo
z!y`C(ZHYONS}>Hk&Ewo`S(V@*6>g}kU6827t&pcjScP~XMD#xp%ed%P&%a+c@v*8C
zVjc<>t}_=!xM>W~+y=*PWa2Mu#dWC&;P#)-`{Zd9Laz3?FNTx4G$CkL_NgRf$_T;T
z9I>2}@%_^a*sWi>ucp16S?y(?(p_C&%nie4H7%xm;gKwV?U}ivg-lv-n5IbRr;>To
zWRrij;P5iw8iR<Wq+oBs>bd!vSl*@4bcYL|%NBF?8aP;mO$4eN$wq$1G5nEc6wgT6
zxnhX?ABeTM-l_N4xj9$I$%RCX&L#d&B&&z0{-W5D)!=i8#$b(1QkMCK<l~%svL?zI
zJMR{sv!$6j$OGkgUy^H#RD=Bc*xr^&Y^*qk1;a!ZGXyC-BP?$bPmla~CHZCQ^@QcV
zYDKjD3;pBh_#Co%E<z*Llefgibjfl?r46I`C9{b9ll6o`HXjyTlG~vXlCkjha`Q-R
zVzg7g{R&ySieeJ4A-UtBO!R_ASk89FxP1ATNW+!GUbo<H8GW&6NcE)4wDmhdVt-^Y
zRAX6w)a9mGELzn>hX6n1bQF;=uQ_<iwLLHHu-C?EyOCoDYt*nEH7U1aJHvbJCT7|R
zO1<O3hQ*e6QopL=!>F&U%l$<v@(%gu<NI0E0wzklmpcf)axjOVt|G66dF|_Kmv;Sq
z6V;-^g0O?%Imbz9tmbHLx7_s`(yba=^e5LgfjFNX<4oUwQuD>qHv*1=6*1`;7PxOI
ztZ{RItcZ2#uK|H5)@!9e)@L@f-P~yhVD|8<p)VsU^-G<&aW>J}7yIx3&}$JK=c&Tx
z8>9cZSkmb0oZc$-tbcrt9Wn<yPGilgH+V>Tb;qR)ceU(2*w{V1B6I@84(pvOyzJ$$
ztJUHipBQXVpA1zJ8`+1J`rAA8Z5|nFPkkP20VKemz>VphQ(Y)_ym)4!vdAeOw*I92
zj5g-gcbm`R@1!?Lh{IdK7euQk)97skU>N!5eY#}3pm)RDKQ&p%akrx~=KAR5CM`aA
zL&F+^yFa7Ed|1DnstZ@b=-0WW)oe1Cyx~^0{OmS^yxai_kXON1*MlRM+j#X*!EE~k
z>`a`49HK^0pb9j{;U!Px?a~g8%hjE%H&m*GHpLo~&NHC#BM_<EeqUZ(Ca1iDJb$DS
z3el)j9ww&sD~juVXHUWKILBk+dc)sfl@-??krsa=lT*lNF-i@kE+|S=_)~di{<O`M
zIh!SN2_f#QtURYG@AxPN<~--Rfbgcf)KIG8B}8TZ5A<Qwx3mRptI8IqHrJo`YS0F*
zBdTT0<@)ZQ8gCJ#$`9~mI_<ptAhv<m_O4u_w%nCG11u4QH7LUUFiOSGIqM$t;HOx0
z&5l!SJ>P#dC%(aWVrx~Ya`7{8{!@BrXYu{&0acHVbPzl8t;@aI$OXeW0WbHgDni>a
z6;;>9{*lAlYeSXjs^9YmKq585ppAlB!o25hx4V_Kv_N%&;{7={TUV)0a)~-z1k1qi
z7Xcl03u;GQ0||q#qo&C|>O=0SuU*)r#5!g?-2fwY+Q-CyJHmM{r9%}{&x>TJ5*311
zJ+~%WllEk>bUjzqrp={J9vHDAu=ob-ukU@Jb*)2u1znG)%@p=2bCJt)*_Wlemc4!q
zZ%BiAXJUmdhN*_SJ%=rA7{T!8jp!~yC0pr5(xdj6N|w&YsW0Qt4Gk)BpC5V>TTH)K
z^?gG{bCZlzY|YzklVYG-x~*jCvN>^@b2yq~xwsZqYwIhK(tNV?Q2-cClCk9mSQsmG
z@%Frp>X@9ZQ7ANQF%5R+lYS%1J*p>OI(Y3fUa(;F%Ay7A)mw8;d$?bIFl7za(j!fF
zJN(C}NymC*oSaw!oSF+<#gOw%^)xB-Y^|v5eft-Y4EpoL>9a3g*%~Jm4fnN7#e2Aa
z&%8amNPTPD-LDXxRd0sASwVoN8XKN5Wzl}W9Ck#r2oqq77G&&OksPnzNm^R_U)P#c
z3fM=|JpHqlyAduPlW93nOmbGPw=BkqkM`B4U%5xDB7H#hI(K^=@|ZJ-oY>cMv9N^f
zFLpAr)lj-W$b^PyzK{L7M%U%U`5l#dY}pqnRy?urX@m)*wD?=zH)<m6?%zs&%yJGY
zlO7IhKk8?u{D>VTOenP^#cA5<L4J5?tGXS`r!sBMRq-dMud!Sd$0$t@C?42ly3a(k
z33+NchiaBOqEW#UNY^I&_X-XKas=8~J4zXK3(L-g%Ibm642ZY3b8t6onrE$2&AkE*
zRlg`n*stw>k`+^_J=)J~v3z}_`wQXfPA1g`ul6)adhsNY8EKxds`lA6rrOEcP{L%f
zD)opK;~spUsLBYtT1hdfdu_eHt?j&c-B%Ey=Eq^|<$<A$^?pBEn(f|FD016-mvnGh
z%wGjq8Q3N)NqZT&>Afh&?@}Qr*W4OOn!Hljr;y<spGL3-C}!`I5Yvus@2Efl$(=X2
zv@~QlC7?;SKTX{SPrxO22K59|*DEE`v8f@jpD4<ibu*q-9l^0ThPUJRJYe~x|Nhk|
z7xB`3l^w)Tv8iE;un=2YB;X5gWk9+A;D+;uLc>vWqYmq~R~Vw7&9^7Ei8+|&w+}B@
z!BOmz4wc<r@;uE+q*E6FOt;;l9m=${%z%}NRTc~c3`~g#?S6&emRiN0A)s#Qk~pc1
zpsx-{I{jXtq-o-k#gL`p4+qF>#wx1E3*i$zqD_{i%3lb&;|*!eQg@DiwyjT_bmGn$
z+V_}4;v|t!YM5_cGiT4L7jPl81b6FJs=no4+t<As^UQeZ#h1hZR1|?)4KHokCJjTl
z|It&=9x7V6ks?%YF7yAI2UaC}X4Y=;aU#4YQ%_2o<~?4hH&=^gSB8UwkMsX(Z)z={
zjH#%%y%^Go+<sk;_m<$Hc3;iE^!nThOO?vs-q>?|gc9yqlF_8Q$Rt1^3OXx-3dG#j
zplea#X+2Cewo(^;&(s+<_w6F)%I{D#E6r}aguj^Mf<Sd_f*p=dax;qm16iRfl{x?D
zra+jCGk~bF;L!CbL2nZ}70}ms5i^wTDFsl6k=tNZo(GFC%KK|g(C{^WX&eA=L79>q
zsZF@Gp?`nAo_Jr?@3)snrm0N*QUIaqgT9F=;S5y^or>F1;S(&;Rj?AnV^0C}5J3Ru
z?(rD6c2tyL58i#_z5Gb{{ifiDr29{v`Nlospy5>_<tv;`kI+n^^`q^k2~P2x3l|XY
zMN6rm7+FpmoxYJPoTE3@n}|6Xvybv9$}mD(NOQa|kU+j~7VlZqp9;mf{<JvFqlj9r
z&TPF9W3+R>b|RLY6mpHx{T{0tY%TO832CE65v{tt`B%^Kxq`>qa;3hAVhjc0#~ZzV
z5gh?t3@x6=ugK_3oKLQgEzUynktu(K_k{tG>?JzcQ7P}`hNBYr=R4iJLMScGkI9Du
z{R$RtqSIpIZu9VZ(5up2ExT^h+9XpP?T3I7MfH*oZzCfgyhE`6<XAsJSM8YG7s{1`
zl}q=rh1mU785#dZ_a&0E!77U8(Hsj|LBBMLu-#EE(5ReC_kL`79Tv>-ER^mm$y|?H
zI(ki`N07v$Fi;a2lp(@E)umLTb^PdG|IX*%{G_K%qfdUP>@ipx3CQ<QKI6G{YDt{I
zH(vv=Q_;Pin~=ZSAoUH6#rFi;YVXtH1OLLEs&Suc_a8`v(uhA~AX{lY%cBrn(J|km
z#Eu^tesHT%Xw>Rs#Nm7Dkh#Ni=RNm46+dT<N=gdA&28o6!^YRaLAIYR5^AhNc}v3C
z*f+w#*xWFG;MP)VWO4jE=2)ChO_5`7H+3oJX*S~t2QB5tY@7aRh`H8$;!Da`C_a0j
z^I&ET9Q8Qkl6yTt=}_@LaZF=<C>8sBxJq-FsIjO|r%eIaoY9T!-&DlC81~wW5QERA
zK2Zt{->m>Is_jqS7{DRrITew(EKALyC~N5LLGzLr$zmOP9l=)6s3x%De(hqh<w*FF
zXo#i*{5G@r)4?aeUe8d>Y&y;Uwe?WjG%t=SgZsF!pC1az8u}m$yqx=igOe$VRNv$8
zpN;m7Au1&ZHMI>gnia(dgEjE0tNE)5RoO5kbirFc>z>0Mwd#oXQf}4!3I9MJh&>Tg
z>UT>ep3#e3liJp$5)GYK>QmDm+;-u`Gkscuql0KD3+RBNK3|r8J%DX~C@nJd3UVQt
z%gmx?$1!_H?5b%b%)3Su*S%>5p-4*ex;$RpoB{i2d@c8#GEH~Ffue!|JTGrv^N*X6
zAyql}r=P-yOmgFuwkLlPa^+RO!u4EMb+pHT<o&uLiKI5N67)RP8;N*n)t_ot;D}Wu
z&R(A<818cK&#`H6qY%D@g1QS?8pl_&n*DEoc<viC{`>?Wzj`m9z_}JxLvnfWsgffi
z6@+)7*)}9upKq8NhR9ef@a4BDddcSTM@6b!(ZCHz#z@m%3cIZFopE7#$MB?715`jN
zI$Z?P7kVje#8u$>V_(_HIS&2NE8JnczDnFMp-k5IEbpbi32*dkMW#Bgqzp#6i4k7g
z=|?)MoaZRvmpQ)0WZl@wFx?;zhK-0XwwcZHWv`P&PK^lO<)*NO@_zbxlIw|pf{;#8
z;Ml-*mg8;39!7C~Q>uPm15T-hW#K)dH%)c^-Dtu(hy1dK280$w>ZG$*h{eXE=<fk}
zT}9fFi~V!ckt-vgW=$m28A+rC)J#;ErK|($w$$CEq{_>w+NzeH4xnvJkZO}YPt}SV
z%|a)9P@x4z`;KvYjxG1l4=6><2FSJz`xUG*et!Ux9;d$1+Yj*eW38@oSZIKISX}tI
z3E}@h`FNU5_S+!hf|Evvw|4PC7?liE50y;Bc^(CxU{Ij5&a=?mTD-&8u=>O7!?#3i
zS*4YGZ}1*25+C-lr*_w;U2iCcCh&hx4{XujN7$Op-%pmg^EY<ho(tO_hNa@p9}E02
zXdRqTz7y7VOf6r=X&Xglqyha$fET}Wo2osLMnv{b8)Qj5sI(k<-6-~zS8+K2#z>{~
zZ|m>>KxOvso*HA@fg`ivBlCApMWD73!jJ@2x3hd{Y8ZK<lKT(R{Y)Bd6vBj%ur6to
z5a_MZB6&hAbzq$CD<E$2%u(&qT&*a}0;g1G7ZeeT+&4jXp}cXUD1557Gxr{hAm5il
z8cm~T-)US(<t^;E6ws+LkEdH0r{c_1bLYJkW5;*sX}V|pc4IkOCO^Ohhe4MtlNh?P
zp2PoI;q-|s!mJtqWRa_II@O=XIik%8!!KArrOSK4$HoeSCCH9|$SvOGcbRv0n#o%;
z`F|DJr<p5~t5<aB%)1z!`?M}-*X$}x#j&ZlJF(eW;OdJ_f^2^)1o;dD@3$!{`0okr
zB1_7HNeDjd<_v{VM~{ST;^vr~Ew-NZypaX_aV6brN^bS=H71$uxH+3S3kcGzkiKF1
z>iR>0-fvURcd*>}0wLdZxA64Fmn$Ou@2J>y%q{H4N8iU&>CG`NHgCFLxp;{Ll+(3^
zR<@fnT%=!?RQdWQ{P_4HcTb+z(vR)XolLD&VWZRu{($e3kZcN-$i*rzejP8#cwTb?
zcMIv*AwiCjq-WA+xzm5^wenHWt|HBQhRyJxrV`hzw-k?TcXe7OpL2YypM_s29x7W?
zJ#B1rLvVMVvAhlxcV#k~bG1u_^wdk0?N?b20g3uzhz4;{7|mcIOYo%Wi~euLXk58w
zD*R=hlP9>fK>e!Z5rq?CN{z{!Tpw1g(IJqdsZG8HbcVjS2f*~e%+xOz$StzA8Phl=
zSoOwt?ARC{Dx+6bA#$TdARR&Rx-e~V;q$zvCSs~WjnHASt}4Jx0S5X>O3bItl0t4`
z$upug6QKPP0HiI+VwdrMAPYADGy@3FfWD1rL8Cm?<^p%Qsw4L%EZ>jRI}_UOCsnU#
zJF{xRvyD{#o5_mWxIi{|bjNl?or|OA1@qM}gOqEbXG19>H)YAYeUeyNcY(6MmtAGU
z&_Xxa>dyo<K^}20cBY@B0Y*GG?oZQOD<c<Jhx&!Kl<;DyTIk0{GF%tMkTh-om!7VG
zsF9Xo0xn_41$fi1WfQR}ZGr-=&1KIb&9A(#4)!>^4(ltyE_ECnT3>M2h3pYOAdG)S
zL%n0=?uZpaQi9h~jX8eA(|pl@p_Ur{{rtjh|7jtpgjP6->s!J8FEcQ96}~SZ=SEhX
zp)fdAnf+7q3Q&s*4aj_>xh3vDzojm;y9YsZzpOoJJ!te`zIe<joQ%|X(mb(ll>;!i
zD&L2)@RtfvhaJlEv{1IROb8^0WZNYVZn7BJUz+)L)y6xt??mpI|4MX!GO)(Ek<5Rt
z&%RiKzSg&9aToXUyf8&KK2Ehr1-*I@jL^3Uu<~i^Rr`6=_zZfyw`ra#kMmRw7h`os
zT@mpx&C^`nM1*}PZTd>;{q?O5jq=$@4Rni4COeF3yh3Fv(ijZWOU%9qRqAJctuj)i
z7px65wWtE~S%P8i)B?aG4v+CZFSeoogY>|&pHjaO7n(VMDAc{GVgm*ly$Q@n;h)z<
z^g;ONQOonLvZP-t`4eC49KiOA#O9%_U_<*GdDXe-kA}}|*nu@SK$mW-&A>I1JNA<b
z3FfGX6a@nIfqx~|J@<f@dHvZHA{F~~239_{eiLYIkl<#Bt5%V|q$L{Y*$RgFrGWEO
z)$GPeZrcWMNcQq)6;1)a9Dm7g>l9UVXbY1}U?#|S1B=g?>?#lI(iZ0dee7{7P19WV
zJ_38Us33kbw&DDHQ^GThIGkwWjp9jzA>4pSt?ldPkz;3=QK#Gs__@dPsWg>UZn+`y
zJ0hybEOYH;LJu_vPKv2C&0yCtPwv!Ep)tMByV}BoW0g?OPdkE3`R<4`V|g;9eOpa|
zdoB9jIaiV0qz){g6$N|0_~^Qkj(fINZzzAE4t$k0K;oVo_n6aX%E(hD^2Uh2ZEQCH
zK(+AUtz3J_EgAtIM8N+*3386ce{bjNv5`*=)J&cVIcZ;>-xJ;LqjL81{A%dFrl$Z$
z@%%<4L(F6*T#L3Izdt0q6nRa){y&hdy^BI^B<@aluQKL&)!F|*ZkbJQSrq*(X|P)e
zs_JN?_(5cW_%l)}R9cz8GbP}%nXs}SqxN^AUYg(WkQ1RE&FUO^p;33`8}_=H6M3O6
z#D0H^Y-mvpH=iKu9s}7dK)N7umK<ZlEXaTvpI1Z)wCCgaKZT_?&nV06k9KTbyue}5
zHT_XrxRcqh*#lL8I9)liF#dF;4Nq}mVa+XeIg#g|qQM(0O;z`+46WeMIm0UGCJ0Kc
zi~Z05X%M`r`UIn+U2b-IdE2IFRZeb9k*?Z-e>Z&pboU=7v6-V}w%|U}DRXHDjoh0-
zPnLE#PR-ml=|7(=`A3n=YH-TomK63Kx@kDkF9CIekp}|e!KFY<Bah7J&c**g>3ClB
z?Nh*cG0DevTZ`WO*oA^8>douP*i$j-OH`(>L124SSe#0dWySmH5d|&hJzlcu8NjzA
z4vtcrLc~$~8UeNtm74Ee%N1eDUz7R;+JCGGcrx7bnN~LXCAqia$@_cj$!F7aRI&IM
zn({05?6_@C$a7nZ7uIK`0bx2JTil|9CTh9W#VOND*;_x;r!G$-4~-)M8k!(atJlF7
z<As8}V+YHJyWsFbT#vHqoy{O%eMqx#<k&b}1oY>mzP!YChr2VUk78RH+*Ku;;Ir`p
z+~D|^!yRsht+%K@;X-m>6mG`@=N=?CO(089gw7~OhK);zNglMF#qjsu@)3tI-I^LJ
ze=D$jIn8YzkmJ9e7+FV(<Uls&mt9_po27ZpG55pPz@3xdO3aD6p~VDu$!flK1nU^G
z8*)%d-4?jVZ2>^+#|<-D;N(oPX{D;wQsD0x(KFi9QYXUOHtSnQiYL$aDX8b1H)na5
z=Y*mb#9D>7n-Ny~tVTI7hZ5S*W>cV=w7N+J^knC0^!hlMZC8i>64FzEaBBatiIX1<
zqdoE+Ef6k|KaN%MTy~i-wS$7fj6$nT1x~h|uWAbK?^fPghZ$jr+tdNjpB|94NOzdZ
zmadHg+D<Lr+K;5VHH<+kYoyy=vn@g^i=Ea_VOLC`G^$`o&@6ObyyJS`{ra{0UhwT{
z3FVzO`<P(nX{kggA`Z_re{x{s<Q{CH#C*iSCSxMmb6>A2dKcGh$UQGs44~I<vTomI
zQe&xxG%C4J%xuvW>aHL~c;JVi(_xW$mHPPd?50%Ur&<W%cbpkQi`2Se(e{mBYu|+}
z%&=8zOZcs)0F?M$WA4V$*!6|7JGQdBR3(0jH*V-Vu_BLqvu3$%@x@zbNSpD`J#T+`
z&;Kq?J6b)@0*38L>MQA6O1C>zPY7HKp50FCCT2c=^=0Lsl*q$#Z$pX>s?zRW(cM^u
z#g$I~KxR0$HUF<FxTieHYuT79ZRyHW>ZJZZXHI3gqeh`XuHxQ<sA(}@h(P2fu62|>
zp=3**s1{v^>1Y(Qma4bEDUxm+x{uKWHtDZY0Utz!+0uDOT+{XlsEbkS;F^bt$fwUQ
zhD-2lG0fWyM&*?Q^v?<guTXqS70Z%~<1}k(?_W>d%k>#08Bg2&6J|92`M;NaWSP^?
zhN#;<62mE)+aCQeROTn*Mqi-0rynxAuX)#4vYGIVs|ah~cGVZJ2o92442-$Syf;pf
zEKv=hxSr99U;OxQGJxSUioreLxHaC9FVzT$0JKE4C|$rH40b+#NRu%@(`(oqkRJU~
zue!GMM}o(ZJ3Bavw`nSPNB<Nz{ERZv{qulaH;Id(aZm5>YsvcpTKtVxtCL^A2jh+D
z*HW(5VFa|%qFBjZ?!#qO-l3vh7llw&p-@l#_H5~Y=S?@%kV@4y598m6-ohaFJeAtQ
zo#no=67a!P!p}%F=>w~b)QQ~l=nDx)NMQL;;@?4YI@iLN5ij?7<p+nK!~nG_Uj5oC
znaGQlvXT5wwAYR{(6;hA>$y*8p{VVQ@%x@FuLs=*<qPZM`1<*C>`%`f6y{3{w8t+)
z=He6JH&CP6l~LGKEuc9w!Ln95MVmQuzkfzOnXMhIO%2%GeJZ(!0~-zxJ=}R)c30gK
zyP(tpztEQ3F(+pe@CKH@4Br^uV{QFg7Z~|7{t)Zvw%BfqtaOaTy%B;fpnx9F?L-9&
z3E;XfmA_hZ42hl$hymdF&qE|c<HBGIVq;aN)tdj^M0jD%0-vtMrhvax!LxxhhzSog
zjNIZ!O*Ytc&m^B|&|7eZwAlhYw&i(I7Fh2O0U>$-LK9Mo8dyFe588zSVWqPS$kBZ*
z+(H{6O$|<}IKlY(#1<H|4?m{aZ<ZH}Sv+Vs+z-ZF`lRrx7L?blj<8{&s8fq~o{o7A
z<KZ;>u4?h9EMz6mgt$Lg5ZQno&pHRrGED%+H87W*Ul@OFy67<{*1ie$Z(QbuchyC+
z%B{Dec4%9a{(+;A^YG}J{0UDDp8I{sqNxh6)jfjC)ms(z`suGRhfVR`vHll+jgxNw
zeM)tBl;*oRSp_7lB@%OE*y&heUgGp}p`j(bkxC(`KN{XBS-dn%_X2z&@ZVPb`IG)x
zsfp&qC+2g*h(Q$0W{IsiFBoH?+N%8hFpg;d1%bINp=r}l$ll^k;hYa)NOKC_H2-AL
zd#LM$FU{bk+(wos%1lGewozABsf6**S7~#lW_{ZOaBRT%H!#e=b~n`o{IZEK!si}a
z?^#K7-1}U2`Bt&fdw_Fs4rtnOlR15L;g^j>9RCNosJ+Xw#sgsHD?z7fVvGD<)BMYZ
zS}%!vG!}<@{v(<u6m3O?LDj*Bh}sKz1_x0%b|<QFjFv?$tQGa7`obY*8fOl4KWYew
zaatC*UH<Vj{!#gGHx}RVI4A0934YTsM>+5NVuE}iVcs!(R@y#RR0>3)&}?akP0$zc
zdZ4X&lu$X8)1&6$6)?fd6pefLs%kE6VMfreJ1pFA>R>3|9QX}>O*_Ug*+uu3I2Efi
z7`7h=&W~-l9AzV_TJBE88i;S(Chzg$-J4{$?MtN$s+3ypm$u-#d54ne>L-dQz#8~r
zn>4S+@d?Txu2MC(y#2U;U;foS4l>BzEtSS{V;-@$cMz;Mft7h9EcPWMiChNdrD>0S
zOHu(>ue3O1zEN;$TT2pA%%}!Pzo+Lf;Ae84+7EVs`;}m)!^A}QriuG^mVnJh!TtA{
zcB%#2iUa=xt-8VfC3O}2n#>FtpvNG9ce}IOfbT7|qOJUR6HoEc@1RT)PY_mr-RY^v
zNFTs2;m4h9Tg(6@m!15SYk-HwCZl3M=Vi$3r=-&ewF@t?k9XgGMhE0~6Pm?YE_%q?
z7qwgP(tav_7STm=Xuznw=jJalpWKw`A_&^p!ac%^{0CI)4FM^9wY_nr)Uf_cU}v!(
zZst0Q01{eLBa&ISQ0*T|O?M@0r5lk%2;d0w$6M=Vr0$y@NhkThyzSA5;lJP`zA78c
z)v}l8dC`67Lb4FLHIEEd&p%st>7a0^REI%>9l3Et`q3CY>sCNlsDlQw)cg1If{tyA
zh(_ih$2<D21(9%B?z^2&!$rK<cwW?|7U#aQBffp48v6HNc%`gcV&tJ6+uuoB@8WQ>
zDEP{&`8^qmkUMD9=h?G7GSm9Qcno2ihx=E58tuk=lP-^%;=Eww{uhlXb-Dz=Ryg{^
z)3c~rQy-l_>VDQo6!i@_eN~7Dz&1y?a>OIQgKb}^y-zMR14+y_L-xjD(D`RDbo|Gl
zk7b({naGSz+g-&eH{oPQl17jj4wKMkTEmuE$n@dh+66}W`bDK>WM4k+G3JZO4{n@1
zdbI)18LMFoIbH?r_krD7JmEF>_w}e$uT$?-Y3e3iVdb7pk2qNUF!vpoETgYoi9Ina
zqwdd-qZ&bXe8qF;hR6kpSNY?21*SI0XNk)Kbd0w9GS#<7mImTWs65=d!`!#!N=aEy
zU=v1t5=RZZ)8VD8NnP&1igTxjkhwR2zm-L!Uvsin@CEq%eC2oj^~23WHGh)W+x6?e
zY_kP>H>E%*5siAL2vs(18uZv*eo}7b_~!}OK3AQ^dvI6lCB&{{0OG8aJp6p7nzjBS
zIRd>@LY-W4<e#pvQ6QszB_+vObLIqUm<yffSqyEUd7%$rO@_ZGD8ZYY+P0bnRd+wM
zw>W*lk~PzuA;YxspE7wTHm}KtowH-!p+`#WF0V^tdgebvoOiX^SmA`?qg~s>AjqB&
z_zU(0!KgR~^d?Z+`44QlxH@J(yyp%4Ph_6yI^7Qv);b=1Q7EdU>j(I9l6&^-TZ$mw
zNXSHw3TC>pJIsfbLqqqc7v!+a+GMtfN4f<sbXcA^_6L6p8f$cc@p18%SUWFd3X6sP
zLwN#)6VJKgg^UgsJP}F~X)Rj{jdm7}pMHS*qheli{&l-RJ!wW3ZF0!!7J(fxiU0_C
zydt%LcaAp4k2d-ZXOi*4=CmvRv%9*U#-_i#kcNr?t9o$f>srrZKnT-YzC_bb<#q*G
zB>%TYfQ$T@Wk^$Ds0#N*1&@M-qIx;Zxmmw2E#|-E$k+vD;lJ150=ccp+LIBs309k5
zUz^O>&SCo%#3njPcsmV9mo|B^1EAl*05{u4688x5LI*e7-qnZr8-(vP*#4aaY>l6`
zWM%uWUIT=3KU_{G174<%*f%(8TdA{o<Kc}$23SGARGw~`<ZT^XdRvW(;%SN+EC9cj
zpz<N~gm&QzUUtj&>u>b?z4H(6Fo^bwJezrv@uc630`6<cADZ9x=Ll5)LS}mJT8Ic9
zDd$L5>Sv5^`agV3QawB#7oldloP1Jue)#Ibb+_g>nxKTZqOxd&^X=m^vBSOV%+oLk
z(>p#^uB{VHxac^-$0Fm8;1SJ}>I6ym=cNuaXC;YW>De0}geAo5d+;R?d-yZ|2;M}%
zE*Lnne;@DaN*MRZHsS+aj?D7%6!bs2r>V3^{|Bo128#5((i01&wP`zZz&yznI7?@g
zw7Us88)N%KbJL9mV&*<^L|TlehiwI}&orq{EpZJSGJNkN?QRU^7Fl4#Dj=TPv9Um8
zak*ZNW2BVpvbj|Q^jWyT;0+~UDi?!iEWpe3@YBX#*VizmNQ~i)q<@ENSa;N^T=NeB
zEuxUd$6&7^f^Efz%wJi&n#us$5e8OF^WA;Fd&1UCW!qX;UaIH~^z$!M%FXyuf@!@*
zg7sQh9}jL^E2J$X3lPk{VC@gDTx1aOJBVy>M&GLm4F3D}%y?8TjEz@iaiyQ1^byT`
zV+M;k4_jstR;NX2-i2gEO(nuNj9Ml022XQiXWZ7cF8=1CY~_3d>`k)8YbL%4fkjR?
z@i5xJ8e4yR##2id2|FF&Q8C;gP_F0gCxAN+D^a$Y9Zj&SMuD`Se8DT)PZGj}SfWV#
z5^_my<Tw2Of1vkH?g=-MpkO==F$)yS5}nJ5x0-{R;5*Rmmi+095i;!}U`W#iSLWpj
ztd@L!sqM(Am%kPQ`@E4fz*R#}ZMCl=NooC>(Pv2Qv_n7SY-rHpajyya@!75!CLq)y
zX?TN<1nDG5bia5ur+NMokc6BgG%|u-x=~ISp8x&%V0)^hk1{W+1XeG$3YZV$kU{?V
zH$5w>YnR#cthqVmEC2KY&~MM*%7*eWOz;owN9y*cM*%(?U?oD!dv-)@2F~ZTahTB;
zLYf}Bb%y!bFW^#+xHN@=g0fs<`IK;uRP(WXZ(Kr()PRO*<2=2kN^$E*9&LGrBXG_c
zqC8#XwRlsz2AC(C=pyi@*XBQB<`pvY0zP<&w7HS|WS?50IGL4ZZJ~|qrBpxJ%RHS5
zr`>J-sfvuEotkPi;dmcTalpfLx6LV-E4+)KZZ3`A$Mh>Sbb3sjH?6pWE(?K-7R_RK
z*puwL@=Enzvk|(QKZCU1O$Y|38sL`)M5`?5jOBjaZa4m+D=I}YS!NmVx%Rhp@H@oR
z4K{}{iN@T7q33;N3uOCc@I!>-c%%Je@gcnBjZ#>BV-v@n{HsQ)qFt(KJ^Zp&4jJ*Q
z-Jn;a8;CZl9*MW-?XAWC1KGT_-JF;S-ay<4Q33G{Zid6QxV-xzB8j@$0lm3@C(u1X
z!Jzj)HYeDeIxghfPHy7BSC53YGl)DcV+bZoTA08y=2FURTS+qi$~cOye5FJQ&YcRy
zh8aS!K$^F6N2T`Y#y8dTY!P@a+-U&aPrw9uQ6l2_^`1LP%OmiYl}Y!uip4Z0-F+Gw
zWz~TRfab`^X@W3vZI{Ys%X{5&UatK+xf|_yxNAgjJ{G|)kk#>5&Zy%kX{J|6lY|Y+
z!&sB2B`M}4&&wnzl?Vxm{bfbVaj(>=hXvnhkA7M**poc!Fqik!2dut?%OiFZ>Agln
ztk+rf!5+0}eC%Y3Y@TMJHNnV}a<S&*a)~}S;7THrIq55DFl6t+BNJW6@Ui}ePON`Y
zoFm?B1<rU`M9;L)+E?~L-m&Jh++E-w3Dx%NV!Ud|%@6N|+%(Kxllm{b&Ml~1r7wI)
zh+sU9G;`K@{JCg<`|@3oGc>66kNYFVGuvSyi`|13tRh>n*yOlxeorWl7&;^P{6esB
z5Z(-6N02l0MCze>n^M=>I&DPTZ{5|otJG1=F`Im^<{2J%f1PlXO=2Yz#SW{?1E;8j
z2fcQH)FZFDV%)L9V4%9&FMpyd7TM$Hc^`W*QtIUQXaH6xmOKUcyIv^OjNh|C0(I$g
zjxzSD*PkvQ7?l?~hO_)GX4MqOZ$&&Fn@;5tp7)hvr4vmm>Gfwp{Fn-3dvUp@(4RT@
zjlD}aUf;UaV*iFe0RQPo%Qs(bA)1s$Q>=hFJrid@k1DY1<zH%%928eC=687!PP%ph
z3a_5}xAXLb8vY}Nbm57!N$`#m+t4uklz>Q=fSm$R$!%GB*UXW^QD<{Ti<~n#0Mhj|
zo5tCuG46CJ)nmZMdNoj=ntKN1LV+4Gv|}?jhW39TS!0ixW>An3a&G!Deuj(gcy8O|
zwaZfgTD>knSF?kkcn77*C|jtHDyJ&hDa^5OAx_;7`hFi<bh8@XiocD>f*hZw9*!Eo
zY@H~>f}^?RvtzT6X4@yO2cCNA6GNxMpfQ`pMC}I$k|ZPOHFLkFcB26QLDs>F>iQjS
z@HWXQDnaH#*?-Y{4@$*6L{;m$UTT9uB){YbEwo-#g^JCmVJ{zF_BnPNJR*Ig2J%K^
z(>gtK?I)8uG>rQPe&)(>Ua{V)>{sqr9Oo_-nIhjOBz`|KysPar@w~{X=0VwkjIVq-
zp36bLcIUmgoxsw{gYFK22&9G<>AYTtA#lAQmoKdj4CL}Rg}b5}#&7;ChLpY^qS4n*
z!F8qLyS8q5_PM<K*z{48)Imk{Fm);JgAMLpXOK@B|ES%n-|l!mRKO@YeVyTKm`ivB
z=G$?p`5<xf;et~l+9jC<mv$&Iz(yH!B=#?3r0QuY!|+@(WS4_r0W-h<4Ys!Wyc;g^
z8`vDBb*D1>$8KJ6$uk(%Py=DuwL9Lh7TO}WPlG=Qw)KcVMt)lQx@nOdNr?Q!mGqF`
zgwtVvSIv0s=Mj25&+k+G(`=SY{OtAP^yZK|9{hLX)L%NoXs4loNPs@Y(UO{(+^OF>
z8BxYU#=OtVYGOOtE>pnX8s9+IRh%xD<-u=i<HT>bg?5u%!=<*MGb*b09EkrNFLNac
zG~eE;O*+^nhW*Y<^wc%Z&bR0n5>*K=8FVBi`X{~l^O-=VVLEK8GD}eJ!DIdNLXk!5
z`wx)s9PzUS5+ReCBef+1b&PktkvmjYiGfYwTO>6_0gMw(Ml{}P?};n|!`2-LCJZU{
zsxa%d3g>neJJ+w`9hMNrN5E&|*azaCS1v1Q3aWm(v^HFCJB|{vBskS%xOJ-M|DI^c
z1TvCE4?3!!lN1TgMw84^6RT<qF;3tP^jgnLC#%TtsyyT!9qpi-`;V20xa=7e^w=gP
zdIqt&|Fln<L1CDjSdiQHJe=1{);{42N4@}eTHIw7b!f>f{SrN=0Eoy9uA+1hQ1V-n
z@Wl3JJpI$%_I$46Gba;bdxEKm`+KdH;m0_m%_fAh|1kYj+6%{5K<lT^4irV9)P0=^
z%=nS-l3+vKVYDBX6c-js+0NDzi5SWM>x9Hm)iRu9({_6PmzIP_v8_hy(NlSe@X<AY
zl6b^G<CMhDqu~5*b1M9v3x_};x{;Ed95Sx0M%3Y~Wi&*|-*LPTSA>2-(JhAyGNft<
zFlMGDmtD@T>Zmkts@XgCKX^p46wZexNm*I<Q<xNWk{DPPU7LvwY)wv!{>=A46S8P|
z$HPe3d{O6@bh)iZ-wX;#Nj~GM`Y<#}e^OkUR87&xMI<cV1}p(1V7~}BKIvZ8dc7=g
zjLgVxv%20%!y~if1)iJAbJR6}-OUuYW+W!d@;uL@gbn$kr^4A!?evrF!hV+K`k--^
z(>r{AzN~I(Ku@lZT!hchz&;@kGcLovHYVegqZ4)|q@l(L>8^MDCGGIV(A3K3?MTIs
z!`qzupI8iN8Y2hc3KORS$lJ4&)O|YZct(XZOOnzyv}j(TZ_CJSh@e7Rmwdg{Oa;{Z
zU{d#{SvGJZ9KV?$(nI2omr`pX8?b3&wWxn6&WuPG((CgKHZ8^ql6o|Q`+U~6wS)gV
zmVgDr(n<pojRY#P6u$DE>7hoxpEBX48TYY<iw^XR=Zf|I(QKX;w;AgDrONn|$|Uem
zv={tEtXG3vvBmOKU#_O*daSi%$mwZol<=XJKoI()(Pf_Xn6l|AivhzZ_+0vy*VM`K
zl#ORTET|2B2~-mr0b^H4G_NvC>N>nXb99N)y#@S5!-~rdwSKy-NIC!vh)QYib*}x=
z?N9#p&hz5SEdc2DUG$FFSNtrgp7;qu4obUJ(r0!Y9Bg?fpTHiy%pge=TCdXG8!i1^
z?p?A?DuW2X_5C<M3%_<-$1=&qNo<+Ii|84pKEba8l+<36STv%GRMzL<E3nGPAO4%1
zaB)nGl6vxZf9|r<fAO?~d6NS}`%lxl#gyvtiK?(`G6n&1&w8Khz&UDHOLg)+<LnW8
zGGsG+Z7$hTxU-pHDdK*`g^JGW`RRYf*B3AGYnoZS_*9^h))v)&`QCpn)Xg%YDI#Du
z6Iiej7-{G0_2jXBDOD(J9TINz{t&NwpyiSl?`dx(J)4db(f1Y(UWc5sJb_ucUr2Ka
zEzi&4BkjDVwm)|B1DXjiOF7)_9K=MA=u`HmHo*y!P*%4i`4arl>CFaBbP#F#!Ir!e
ze(ghGT}en-x8=(1K|c;74%Ntxebk1#c?wTZ0vSIzW{lWfIHXPoacL+`A&n{>`7MyM
zJ-@#dSf^pCDM}HrTS#As{hhj7<;D>xW=zA+EP?YEGy<GX6O7{Y8y1f$yT@d&&|Q3L
z^ERWHEfS&cRSd5Km(b#wq8&T$PTO*xG|!Q#L&$Uf?07Zx92cD)4E~y@3?A+LtkU9s
zbzyr>+Y*1);FL5HLjU9u+e|Up^Lc`I5qpmKB2}-3T>E%VPfzCJfsQBv;E-N+WAMpc
zM>mJ)F$2>scqdt#J@E+M5<cGeb7RR~F;u;{&s}E!xkxPlQ=@7;o=*x-Y?L$Z4P6bt
z95%HDD_@mOQ&7Y+3MXFYkqkKsrzfk}za<keYRPe^DP?=62b+fXm5Z7sGOU^;oJI`D
zmnb^uiq*9`ybF~stLkJ6xWSm~{5XBRWS}Zles9yw=|LcBkV__s=+#Cvn1>%WOB?-J
zgc=$aS!7jrgsTkcd0+c_H=`<B>&nwp=CHkmIVeph4X-zHL&&r%8GcmF)wCzaTeV!5
zSz)GkCg?oj11H~Z)9aPkvS78ybuMeLWZ}_A+bF^%#uXmCwQOs=+vt^lt@^AL)Bf-(
z=m|>E&SoMduquCvI)<xJV3kx#y2zvUYjFTgj~|F(517;Oi&~6Ao9KQKN+b(HW{Xux
zH;R>MinM>#alXk5DJj@$81#-!dzU;gujVHOrnj(6zZ;5@{^R^9IQXbn{I`=ljnnz_
z2d0((;+`F~?7p?|Xmb&5L9BnF`XI^1qx=LbzWgGrVX86h$Q}LHG4RaC3SkNFFEBfs
zUFRj2i}^{9w=rmecX)Hgd|h0HWExEN79=Tus8Q3|A=Ly)kkCB)EJ<p|fdb{P@u#}q
z<5KsK-;s8}WckUa6ju=$$uvl93}=p0=|_egYJ2fUu*azBx3VX}t)ZT%l576;?Ym#P
z`<ew&+B}f}Oz)sj+5$xL6QAbHwJSQe_hzs3$3GG>RP9Zr@^l;8`Q=8^NTmxQXW&`i
zWA4*Ju)i+)pN`pqMNtylM(JnqZ8E~{4kg`tyCjE;{qjwtMAZ_v$g4}0%Uwm8NFP#~
z@v=-`BB04!q4QmV#HH(H_3@b#KZl}Vo=ii)jh^w{;N70>wi&7`?MtZoe+u^J%1X_!
zOGEab1Q>$Xl~r~AZzA+F?Lcl55Y|bhiiWD{VD_7zlD|eDX0&kL9Ex?0-B<kqWLw^1
zw^2)-sU3Q^1gB;jx->6)GTg(oDFRo{-7~n>?jp4)_z^;G?v`s!ry41a$<po(ZZ|1T
z?4^!Bf%dB#E+}zrart|nd{vo`w0P2OqeJ(~TW+GnI$XxT;NIk5uYE0@lka1HJ_VFu
zAH!*jwr3|$Dukk1TOvZ2&Oow7r}4>7lS9<_I!Vn8A3=qamWLQhKQZ9Y#3lE{(chA*
zpH-EYGG)#bWgDl@aB1Fp;mJh*CbC1L@`F|MMz#;eLh!=lg$I%5d(&9wYyFx5iOt$R
zgVt7cmh?9rl>)t$5+npm*>p(R-xUEG$;mGrpvpx*QYb@-TxXwg@CxrKq|2ya8&y0z
zOA4cRhwdi6fhWeS1s2*XK2<tXx)s+xLh`q>r{dmx)7QP{1YiSZg2`3uTlgt<L_#GE
z^&i@KCWIi*{dUibYo=>)P0PoHOt8yF?*BZXs2&~02ToFhgF~2F4yI)@o71JvJggr7
zIZ(}II(<~kEKeKXxaD4$&TPKLUgt&zxO6ftsfq@zvdz%#JGN$}gQ4!8ho`Xf?e%~_
z#RY8mo`u+QV?f}mA-Yw_j2O|t+o_r44QJ|5g&<pV=pyrf#1{N=e5~s0g{J)mpYH!s
z9oxUcEV#Ju=J*LA4r5=Ks~lji{YhPUo1Ulhr{%omvo+UZKs|Q5%JYjh+jR^l<cP_b
z^;f6kGeFKi>1Y-^=1M7%FjX6xe^T`3o%;&LOno1i_B39DxiVo)(l3?WDtf38FPguR
z3hQFctMDC%k?(0&N_Kw3*18lg3+da29w_`Olh>wWU~U~`7&}^y;%RHAIDwYuT;eAU
zRm&VDSO10dCq4f}Eh+anl&6N;;-{4y^cdbBA<=@y$*=0)mMRQavV~1Eh0-Bh&i!n@
zD!m#tsKeL4YtmKwABa5GXgaF}@mOA18%uO8w-X-9+oSd!BI@MYT$(>%XJtEW7QMSQ
z8bm&-X_3wlT#$;Jd}7f@2N|chKZR_c63r6yOT5k>AZc*@m((nG@w8li&y6wBR|HS~
zQJHL9sD#;%{x%NGMhVlhDtg4nlmO!^OA5Pi5>4hRyakFZmThWPug^)`gcHsg;$Be1
zHxqnw3WC`r8uPDV#P-<pF=~v9fk>~3e0eI^zot+f=&pCc^IsWt5|A0LLi!sw1q<$5
z+dM(hKcf@Y_pkK?0kn>MZxDNNXw&qSSpVZ3JDyTHEXBuh3viSy9>av#I}d@y+HKb7
z^Jg27r}2Q~59(8UUaiC>&$(Ktxu^zUJ3c#F^~d3v?nuNOY^MMttG3teB+O!;I}Vp0
zNwrO8)n4$RTb(?<n0w+-w71@>c`q&oJFmq8A&-jVzMn{8gwMrJeEa3!SzS@F8P{!Y
zv?hebDN;%@H6LyNQm9l1YOjH7OpfNBd9JIt19R9?Ic`#HdoEGIRgdN^uPK4dJlliC
zS5vv4E1PKq+OTWlWaCvd51isjO2m+}kHJVI?%d(X+pYVuFUlVdpJ~YB8?wzCK~5hg
z=+;d<fEwHV-O*vVJmr(Xh)w?S<#NAbeOxPRz6_(QYQNQM5+#yttZCGn*(&{Tsq*vE
zNOf6>0H**nVoy*ui}80nbN+~vDluRd!Xi!m6;AxiI_!@wMB9uR_q5HLwJDQo=H)&H
zMJh8EFmDU<EC!iIOboufG#5)w3m!>3zAPiFItwVcKkWDl%kFePFkg^-Cgbc{RFTT}
z=mgw8{2!l(;mb>s#}5yjIwvZq$)WqeyhX3Akoz$-;i_b#^ua(zD5Ezn_P4w;CSe2q
zox(YFyQ%n%e$t9h|1IyDab^U7K-eI>$RjWJxA{(i5{8`rDYE$P<5HEW#DQ(Jb~3r$
z$9w^sCmaGqfhInhQZdk22zo=COAA0S=wN*Z0R&D_&c!g5cST)7#_<Pv=!;!Dc#2?J
zr~7;(i#0S;tjD_?{{3Cv1TgCd15XBvL8fp2`ohbYF-JTkbn4f-8IMBYc=_%)kAe~J
zmBHN?GY;Y-yUSuhWZ9!lJ#<SUUcD6rO-g8}#Wb_)m33p-QCF=)vExR9+OZigUQ8_m
z_mwb&!j0WK0s!(Da`xskb}pP2J?=#s`WimgX7oy<!IB=RowzF_)bJVV7P$e4UU2La
z1210}oH!ZgY*gL##qp^yU`>@G@IB_ZyD`CkQS=i1V5cXs>sV>Lf@FD;OyOigmGvRZ
zB6Y`7Nv0#Y_a?YI^MOPbil7;*mU~5`--IlvUh1&jksRyj`RgD8{^sQ7L)Url`@>~~
z%0rbR$1eYaWK8v2K6j3uzuxz65y(e(Uvn&M>(csVJd^d+SD6)i?(hM*4zG~znMN*)
zNms01DD{p}YEP_CP4gO{#`nc1nnLSDgZBPFdyM0~5OT=N&f*gCW&|b7Yb+C334^MF
zBG=A3+dbn<@j$ize{lMECk|&q5DF@?!Zf(a8Xe*s-CO*0-|wC$Rlt~2yJ2!d+!mv*
z2U#j+{^|376rFcGmG2+M4?>ZdY)(dGmK=K=lD%i5kbUe~_8}SBGBdLGUdJ90hh!bc
zUPak^bH?}g{QmL}FTBok-_LztpX+*G=k@W9gq8<MqhY1ufrP|FChd}^=NVXK<t@KZ
z+>#o@GD_4h3X{GbDj2V+H^FR*tl{fI&pYh%_nK9bMr+`<32qHy;ndGIH>u@QLmS<E
ztvwJ^mAC6j6V>nIN!j>2VYdSWod&D{LeF*r+AVL$2rhtDtoYj<E_O9KRMrXC)znk8
zv0?FULa%&PVt)CWayL|DmL*RYhy=(yYWIIP8xyxWB<GjExLb48!p;8ODQt>0G20{w
zbCmC>-~KDB3fNP82t2FB9^~u-y2iAP*S)ps<nzj!{P`5jnDzvgvM5Dm$_RTE#f#6<
zBOb8h*sF$aX^ZPWVY%>s4&5m+!2g;wJbH6-^!Vv~kj#G|xhr_zHsOHTP9Mc>h5V+O
zdrDE*nUf1ZQ+b7X8aX8I0spO%N=2DKnAjg1#-)^hA@K`v;TcrRgSo(t?{B3_UU!L;
ztUcDGy5v{enk2e!ei{HOO&fxlvdOb}%})LtO}Iz;(9Ahk>hI|5VawhTGw33Xl3S%v
z-p{2gg`L-5uD{Ll%p+>yWD3fVMgCg5CaZwcG{b`qMr-=X+tU_N=k&&2aat&r5SV1J
z24&f1UYQ9K8&+%&9Kr?@n|-RPcLqL9gOB5kdk=z({-XXr<${sad71x3i6)v=MOX1O
zxF@D)B(+-8R^`6zgb(w31*f-=G*yrQraBY32mz<Xc1#BVE)pXW5z~y|reM|uxL~)H
z#xr%NB1P(nC2yol+jK~Pru7_QtRnJO7DAw1*JAP)MtV{vbl4@*q-}hAW-^A1mMJC-
z<LO!X1C9W_!n}&k25-ke$v)(*KL`~92KRM<y7uF$t07oKTVxM@c1DfmBY40Y!)Pn0
zw4<%5OWPDQ!FW4U*SLGAh;f@rIA@X5O7ImbTMXqir=m_i(`C9GdxY}6!p!|Fn=~BD
zy&|~KP_*-m6EEqMJ5#vt`rx%}t}Zy9NC}NN2v$qp%kr3Rm@{(0AYk&}?^<RX0sm63
z!jJzzpF;K#=7x}gKS=l9D#;0qQDpxlE23PTZFD+hpybP)3{3Pv4*=ctgT1cz1*l&=
z70^FSEnv8b)TNXA{JG-n39txzHMl0n;i!8P82hyTf!;r?({qvN3APX?lBgmZDtIU0
z4m|Y{q}6=Jy2X<Ntyk20m=Nf#v2XjiVEeA31Yo)joBdY^t5=|9tIj<Z$b~fn)0uza
z4d-`eYg%>%t-f3Drbe2#C2H`07>r<#ef@!S0Lx1x7oqN1!+%I?+RN7P8s$v?__H&Q
z$%FwPNLHR*Wn2B$zVP|B6o^X#dk0n9V9UBb_?c}`z<IKuZ~Er4in>ZZrklfijfFz;
zEleq`#fu91zCar5H{6IsJi#wn6KGNe8Pd4A`}~uAE%8qmKZAH7zJsFKPt(P`|ED`*
z+m2LHa_-2$UYA4TAGHT!U<5ZlBhaH5!|Kt0|9nuSs0yBzijh!+71$7!>creh8}h3Y
zzFgR6#vDKDGwrR3D+)|Z(Uv@as9z^G<et8uurH#)b8-(;|KxIzo^b9mp|tGZv=_f|
z4|<4dKJ-#7=V<-ez+c^;*-by(<ZW&U6qu`mt8(mDKt&U?c`}@e*JKmsZ+-iOF$xE|
z^a0<Yf>DVkgrQGwvL?Y&aUq0BBh?S^9na*R@qb2LL=Ekw%P;M`dO1TLH0Qt;3i<f2
z30G;lZVNWkXRiWE%gm~9;pG?3-*2)gBi>U<yuMt9MU1{+Q*4*$O)eI1-S0i61|CiK
zeVMR{#Zc%Gt6|2=v`FS{2ecTyf`-c>Vcag!SuuT3&|>t}_fiTX7?0*4-Y80`6)(`T
zvzkepZQ9Y3uPT?7YQ7jgUbqtM1ep><gM=gHh$VMSoYqcG?_F|+itoD}aK;Vgt8c51
zRFt$MGKwjtYXzWMkx!@&mpr~RaW;?7J>o~3+CQA>&U6`R55(~o2`6;hOR;Zukax?=
ze8R1Z=;Ia#vZghfGe(yO*i^h@Y&a;25<axc1)`d74URvMz4r+l*YsAwJ%JN}0&ERw
z7#4ks^<D~-)-DnsW>V3#{xi7O+&A#|9q?{0(gvRn)(1P%JaD2X??YHqc|5^SHsM)R
zuui%N*mreP(S#zpJog5!XhyJh^W8*@#)9HtsfadyF3Nq>h2O5X#Q-{`euOH;qhcKg
z6M{qYKM25`o@v#Tv9|$CucWg}PU5%BU+;sam-3X0rPBt0alV4A4{$aq*N`@k+vt{b
z%6Pp#PnBO5oBc)fk{<G}qeq3<MMsV=jK%3y)ZwBh{!g()M*${1KUn!SgLF3d`Vtgq
zaFf-}YHpntT5&mM)q0y8cQHurTV3BjL<wD}GQaSmI!q2JjN1cw(1r@Q&zi><JK&PF
z{4S#0B+9P{Yk>Xf?>8-*r5Z7-S=N7>@hZ|}f_KPWs~fSkYgaSS{Q#staH<J2+JjZ5
zvA92klR=v<Ui5WeLn9t>FuRrRrGGucUp$#QT4;2D7dYj>vZ8`jk4xE}UssUoOC5zP
z(6Dh{eZU5NgDw{1f3z=3=rAS*BsYJ}#NMV5t!)-do0`1YZ3J7R@0&Jjmjo?Du4Yb{
z&C$<NP-{`jq?rB(T0s1K^$Y!(3$cp|JKvrc(Ci|{6n%k#ns&r#Rhu0?l#A(T6Rsru
zk*Q2rSV#QrX^4><7w2`)$SUzIhn*o?N*8<D^6lL(wLc~?AKUp20S!mcCZFT?xC;1D
zC6LjuFbe|uZ{?qm|M^`e0m7L>-YDthl~zD^UL&o%wJ<yhAvl1?5n~V}D}Ok>7p{Jp
zORP%PJDy2Je=7`~s{kJvFhbl46%*}C$q(*&aPn@K=D0W8G0`vlKSBUnDtdI37(nm(
zP?bx5&=J3gqQfFedXgt^@!7-l&qbj7WFSM|!h{AeW;5}CjSfCa0x(a*&6-L7P5))b
z@FCwsz&F{qwwpn4*v_XQM1pSVPyI?$z$(Z7<^JW8+Tu2AZI0)8DcgG!Ob3j8$&v6~
z<?H`I#3|Ilv>6x^Y7fX2aIcJZmXIX&*$>!?A!+c_9krW7g>vK3BR7x*(ix!IR)7++
z13k*Jagr{DZp;`3Ccp}T7@`fP(+JQ+?`-IGvO(r<vpjmc<plXF+UK(IZ>Q<p=JF1Q
z!tq2}<WN^Mqo)lbN4Q11S11cyWnCFD2aG)u`;%*0`k&j!QI$d7kh6!B<z!l04(0Hm
zCmfM~j3T}@14nx>5%ll`z(38lt$1I22ja+QzAtp{hb+)J7;}9tBAtGCKR~C_$gLCE
zqpjj2b6V4Z5z5)hQncRD){4t6W}h!mUWXnXaS7no%!*}Y0yegK9|hWH;+b-iJI*|=
z#$oqYG^^f$k9d@!N0-GCvo>M;4(M(NvuzW^NuC5PJ7&Tx`FxK=lIF<;M>*T4jwGEv
z@)981UqFA{N$Y;{tyfIhvv9uWwHt!g`>L`6C5Rlk%=h0a5n&c`a0<CB1fCxy04>9E
zAsqbSqVjVA%t<~lNf$F;MnR>zl9B7Ve||UTdoj_O(;e{bj<(~uEC3F=9aX(_i;QiZ
zFi@X(ngwf~G_oC`m!U?3$}q&L*r2WL3#JqWieCd<XcUB*8dJwuOzrs7PvqN*sFo7;
zKM-X(<~Ifftl6l!q;~M(G^1m2&?@kOhi;}WZx4&aJ=rIv8{$JZKPq#1jiun2X|{8}
zAlgG@K7}abX|9E2ofb86{53)<ltcAvcKGtnz2rVl>vWfewF{b_;eHxc?u5041Ku@;
z*G)|K+?E4`=n3lTmXedLbZ1};mO6x{;xeJlf2x+)iL;vmT#GPHbh5AOu}`RHPssne
zOy_<3S_XH2`<I}URu||@xum2W>-M87vS^3C@549uv6!OY>a0k{=pM-Foi`x6p%}O0
ziX|)cTeNfK?iUGcIFPyoDOEcC@N^>mqu4tOto?GpW-Gb6t35FfDlJ*9Uk?7ndAkMa
zV-9}zy`SKmu7B}o`Qxw+OmmHI9eqClz+B$Uv7fz+EA}t!Q(-W2U*}pD5-{DP1*g9N
zK$4voL)IZL**Z~oFOcrn*ZSA%DFj7YGiUg=oWvuaio)rq)^-vPm}LIwYM3<7%!AKs
z+PA&+apC%gm{BYSRX<j4trz}*)klnCrSO+{DcUBE)+wSUZu=%{TavfE#_`vajRK;4
zp0v=PDK9hm-se74?<*gQUZGf>+RIw#^*j7S^O@_7_guGi?qgN+LxvWRHha`vu3ueu
z&dX}!%gS$RzZ0Qj%6%Nw32MWzunm>zqBnA*4-U~k%$SAKzPZh9TjcnxFd5-*fbBT2
z#TY-1TEF9809<uiv^C{8jH8nkWF36z32j^pc&I060cfgekR156&EGAV%CAw%@lBhL
zkQM>xT_47i{<ATW2TZb(WgJBlwS18qiYDXe+lVox%UmknQ3c(QCk$rNfEEf|eZ4}t
zr4v3?iYH<{0NWz$NtcQShNC>Pq%@Mn)o)zVjI!N|k-#P|xVbOMxx>13#GUKGc4}hn
z0;e11{--TW>i0Uct$$7ISUunEdbNh(gS27-T<-(c(riB78Q8|__h8}7-<X<vb?p{{
z&m5WmEs(lqRpJ~8%+0$jNOEq@2g$3P4DQE663a{D?XM&;4~X_+oc7GhhcVB={b7L2
z;^<6T5=n)M?4AP=xGK7rycBcwZ5MAy?9cLL3vQ!U>G=l)EI$rLWdC?Nd$+G-X`OyQ
z_Qu$^ZO+uHkuWf#__Rxr&+sx-P9dM1g0e$(jGw9&pgmVPWT%cn=AFF~vx0ys9h8`h
z?MgXV!%E8sr-+ouycnb?UQ68se*5`DOAJ5ob!>_e5d1PQlqZqeXLt%FAPO>nC6we2
z3=cM@gIXzs)};)yKKTV`ugU$5TJx0)l3_IL*+I5J+Eu;X$d@Gbs{EB2#w?`2Xx}3X
zrJS#I^$}3E(jM7pA9Nh_ba!Qpn_!arTv0!~iOTOv`lXM)4UfY)g)f*6%_sjg(7o!I
z9kt9S(4S0M4nTXE;Yt+!ScoQluJY|A6IGNkV{uzDO=HC8x*4H;fm!vJ?`hQ2L$@%<
z?q~8bqHX!|VdVt!3k5&&{lU6lvKDL8m=8^X&fbiJfak(@0z<bX$7G!X41$Kh8FQ`>
z&L-z9k3T{qfO7poKi7V(1(>-n#I)i%ODiN>cmb-h>-z~V`cGE}gCY+j>pz{?ViQOf
zy`56x4jSBR`Sok_t?0)Rf&mYd_m!*Yw;VlAf=bKuep6PP?x#y)Dte>#1cP!HOZk3H
zjIw&ZZ(p7_Su{sJYMVVfU8<3pn2Tj=sFkDOy-cWUP771KqT2|rem1Pk1hmBuZCECK
zndT25ri+|2<D&2x>?P3Po?T1h%kv$SRIYAg%1nHtM?{iW1zgF%aik3;%;Nc5R~gk%
zX8F;|^v&HAjEqqT`@zZnb$;@ILf-qW?)OMnbd<s(D6kYrx*>p`O@?CXIX5b69oT5$
z&xKd*ALL6K#uz|vNhX8$Qj)jNkM;#ffB&Mw0<6iq4$its{<5feTAEqojkbIu41<<#
z_aiPqTx*_U_{{wY-d6#fYs9T=m$w#^eY&L*f9+jofxa>f3}^ldR4rJ~bPJOD_7Wb0
z{#@p`OR{A^YQ2UEcP}7eqB&U%`{)!vNE5-n_E@eZmyUKxnzFyp9}+S0BQO{<33PJ?
z=2;U=+67F4e8<@C;-<kE2VgvLPY!saSGELq_gI{ly+RdPaDvV;xlW>Wu#NZg_mHm5
z1SPOaO+WF}(}`Y<Y0RT!#WU*GtH3!ST<4v*hn!Zb3jC(NJ4B)Nsl5LLR~+ld%*&a@
ztP}1{D4I4obyTv|n`bcXwYK<(dyKuW95-@fHQbusO5k1LY@+P5fgp%7@RM`kWU`8V
zGIWD@x5TQl?h9gu53kZu^`@glSAICYaDDW05Mn?78)?h42D^eeOJc@HSLOJT8bDc1
zOg_>R!*?8<_IobHsK|3C#SxQHS){$-mNsePg}Oibw$v2kIO+Qe+J!ckN0Yl#Yj~YS
zfcL|){HJ}(cKj5MCLnkHj?w$xJVlQ-W=nL*`=3pe%izoahMBcf93X_O{S1iT49j0d
zd{~Y18QRd)r_UZh@IRZ=o~v-uFW4ahjpYP%8@p4;0<da#0(SJ&9~u1t3-O~GkVWuQ
z6(AmL)@%4!bbpcCMhN1%Zz*Pur-^-n9P`s{Vor6GHc0&DCYM!yFU{xW+oeC>51rsG
zj!#58#F17`h1<8x-yTx{8YiH&7rvBARy!BUN`G#75KIZ}hz^O>7w;~9@{=fe$(2j@
z&-N)H2YX?ruN;{?4V+j>O;83;OHR1PeP5l`&PjZ(D9E+N4Zcv|8_azk5xw`rK1VE@
zGk?(jkO~9oOT>6{KV2xEa8J+jHP88iuua~kc=I;oS&`kRO!oe-xOT3mqgET!+y+dB
z7*##b(}ib;>Sd2-E9V#7udT~m%`Tc6hpDut6G|%bI-MDz@t{{vtHt3{w*d5yvJnto
zr~_-vB^Dbb)u==0)>@n?b!1Dx8rFO*k@eW4@0XAwwV6!sXJE5NB#=yX`Fs%bE*3DK
zw-7@$1fTOkgw!)UGHI#2XETGKe*ZreYJd)MW+EHWnG|!s=COQ5+T8*zwM&UA6>K9e
z%?>R#n>thoXJfn5%M?z&i!p1st(K90Ykaf!T;6!*ttL(9K_>5N($tjPQ4ZzaC;2vr
z;60uY7th6p{H7Ql;BiV~yyBIrVXWPV_IxfH$ga&9OLAz>grBhV&Oyai%-ihCc&-BX
z-@kC=FTaaY+!yS5cbpAEptvu3<xP_Ad<OK$pk{2TPMlv(4mN~3M^GGt6=%a>UMxH~
z-4-5zTzHz8j*_J;i5GL|lC=LQdsX5rP>9`qNu@yiaxthlZa2P-eKYMRkNQzI-t>pI
zfOx^xCy&IMmxA?e(iw8&%8&()y^3K);DwU(;0O(l`@w)V1fie9XM&yRr~e$3OM;IK
zwbSZ}q+@X(3<!T?LRKHgh0vW{PD-_D-5Nh`ZUosMzUavYwivtVByUd+sG%0Qd2J#X
zrUxs2L+$O;URk;ZU=zQgaz2cajB4?6kE9$b%iS@%Cm~bUk2%qJ6og$Y^}8H1qL)_h
zv)<Zu@+{ifNQ$2*fV{aUKmOJem+uV(-uJ7c@K9a3zRjei`6Wb9sr(=H!oVsQw&?4f
z_{iAMk58tC_PTJ|a%GLt6jx57^D_#wE(17bOU&=dMzbf6U2I9wB?9^MFu}hm|2ny8
zu#jn?a?-0`%FtiU{G!&tV?a<0t9ixP2u))k>=X-gU42(fVXeCArCMV8VCmq-MR%I9
z<jiIpf`#`vwmsxd|Ncxj6KbaDZAGwdc+@;IEl(mpBzb^Hns~-be=o5XTEakB-d?|w
z!h#4^ES3<L1bp-hx4u;$*MZ5MFbyECTH>6PJiSC?CBGLFt8}&^N8R@2KqV3$hrlDl
zD~T60E&`A)7b1yHj?QE4jvEuTj!fFM1*F;HefzMGWoYDhE#!l6>}lDC-lr~;#rxKw
zoD8+|oWt~x$iPA!LDel2ct~DwihPxdFr_G`VSUW1-JxF-;FRX+fu3&DVT^NA*tLgm
z^|-v2mkAvSLAPNRoQn7hF1X_vrg;lJQ$!b^qnlU4Y4+>r?2W|eV$#n}U&1yK4#s^a
zXFqq-FwR0UgqB_sy8=snc}Y5x%KatXnrGb4G#DP$Z5i8Xrn?AMimc{;VH5!t*i%Gi
z$WI2my!rMM?#GcpabXhB%|hOleEEY3fS^RE{Yp?>chY~HM|_o6bJsdJ-Dbd|Y_=%S
zpU!F`ub|?`tRK+Dwe}J9RY>vXoi!|s&@2iJ*_Tf}v7=^PeJ204;{GIniZeuIx0~~)
z|M=ELrbUu1BQ6z~zJaSvJ!+bNGVzt;)}U@Q)MY#*_4k`CdRKrDz<IhqO4X&z7deoa
z)Nu7s>MYj_0grh0-G>D)*UN0B(l8&fE}Xk7Zf+Rg@L<p6C4;T)5}9o5GOL30?KI6>
z<#N{Vnw#e5^aDWZa_wE$yWE&3^b9NgdUu?xSAg4c-$t2}K3CmJ<3x!TB4aeJ`Sm&E
z4EEkbYZ$Oo-6b9z_q?R8+J*g`BhBNGt9(}mFcK|Zv4<MfFD`RE&Gx94&zbTNco3k#
zIS=BueXS8R+I+Ets<jrwOcNZ<ew9>ba9ZAw)%Q%glS&IBVmmV~X83x;trcKhBCeO9
zJ<Y7r)FS7WeO!D;Fhgz&gfV26knLI%(-Ay)F8`iuPs3$D(!+c@MT@M4yj8QNun5Ct
zn-T;kYeT$O`ogljnRgjT{hU)MVKa>G<+FpEx_baD%-`dQ<kxK3E#EgHOK^$?`QHX?
zd1w1;z-r0I$a`)&?7|{kZpPQWUlD$UZ!F3GF#5;}xSW8-Y|xlP^L-<Mr!5@f)gu4W
z<)qAJXxgAcZS2?i_of<!Qn$K6b_93dAqZvcGx!!)8unt)fDU?_c54Xgg!YHNUk_ti
zKtk=yhy;9Ek$+xcJJUD#<#z5%C>=@W+d<D0;8W<Q-4edvDKN!SRjbP1!F!2+)Fy%T
zmOiRRrYPKgLju#1aDf6iT6b}hrINnAWQB-~j0~s_UzqOx)hDkhys@m_Ps+zbp7S$l
zUsgh}zrjjcDf|1BJozN*ckOQMmW;cA@(6VDMHxerY;YO3?`GD4RZdl2Mh!^C$_qNz
z+6$SwOUm;nv3yK-bD@@$cSn6|fifDP6@ZlgD&;i)V8>2!AfTr+O$WNpRn~s3HVR+w
zlJ5V&@ewdZ{-V@TFXLaLN)0iskUeV^aGkUzT20mE`+t+TT)7RWJJ%6J`SWGzSJ!mt
zg<W^$`>fw}qb|WsdhMN_;Z8X|TQ!dWibHr}Q=Zm(PKJK_jnG-bb$M6p#LaqWzysZv
z-HNB5K={;s;zW7FctmerfN}a(c`GZLqfRsUH;KrY$l`%HyQ8%ujh)3F-XB027q28}
zgvwQBWO#)bdUOY%g3|&1a9)Zb;R%C7PS~}<!**VrU-gvB!X^&jA<2FsKU*1IGgEMk
z{)-&*B4$^Y1C}ClK_mKp^U$|sbE(BfQE&;7&|O7R+%uqfOHGLGFRrHPKpXS0?M>1E
zfZnSz)qA44l4E5+_*0qH`B(MoX1e+46CLiPTK**T16Cz2DzgO5Xj>`qgy87>d&NDd
z>`lR6d>{V<X+9!ehW{2LNHelEV+}B*_?5Z-i|AV4N{~(EyB949G~%Tgxp_s;xKOmv
zkXmKqgvSP6E;)Edi2JMCWXB_|Q&?Ehf1taN4^e)(X;kkFo(@zIyRW_Z={euxW~PHG
zKh0s6Cd;_`7wsfW^3sBA%F1PbC82A!r8K!zp=h-A1*s0d;+^6TkUO@LQgm-jgpdt)
z2|P$k<XsholA5Ti)(8vqllP3>YvL~dsehLf)!29}FVGPEdz49X+YvyDgJGW^qUoW2
zEne{B2w9Zf;qaYv!rDbY0i71W^>?sbr!bUW!roqH8C*)e!RY4fL~>EfK48>>2&2;p
zGwc?c`$54u_Can~a-T}KhNmA{P@Nq$s&+MtsOoY4WLZ&1IotDGoeLuE^&o*@f2QB^
zy66XUlf+lq5=u4lVKM23JWUI~tAR@;T1yTt#L1XFynp)m{EN$j{Hw7bl;DMC`b36|
zt&L!R@mm(-cZ1DgowVrJ5mV=wYXIWuYD=?R6x0<zvzhhd*0CMVcRxED%5UHHR#XjL
zvts*9t=o(Il|D>tgzRx>#YUaedm6W;{U&PV9?~MAH$Oasruy^0wXr!Bmu@>aB?K7T
zx!N{xP~VbSIm-RrUN(2TJ<&rH0ibEGK7w6-p0}<Up#D5m%Kq&JeDs&iHh(pzZi|!F
zl6JApT8*&p+l?#Fu!Ge?{KTv-_D3q!73`HR8o7$@<<L_8m^E;InhyLVP{&c8dP|@O
zL_yysN6k?6LZUSFLV^_&v6M-)>NXY0W4BLHMdA{{mU>&g-H>^+r)xcuY^`Wl=i<C>
zKiydkP+Ikey0P+ya?e>F(x46)K8uO-u9^X9uNQ5i$MB_M>TM6)tWBO)7AR%k%wR*J
z2FR{&W^zsex@lrp-c`l7km%kgCL=&#rP6V8YC?cSw_}o1igSw0uGE?e>^J#%@&V|J
z=Q3HNu+LvTlTjf5tuJ2VQsy|F8+NWALqd3^41Q1gE}=wQ;vh?p)IN_Z2R<Q-j;)mO
zW>4B$qdO_LOf%?E%)dLW*JO-aO}#$9XF#D((7%1^us|&5excVZoK<vEnjQcCg}CWZ
z5u19M2dkJ&T;fwzI5Nhg2b~#|WkS_yKzsuHz3F;!S7My1>-TZj49CSp#6u0qfT7`>
zHDJ06=TX1pK+WD>K|Aq-YV_?;uX2@#BAkZMxqP0oSeSx{+@#ylXuP~;?V)T^WBE!l
z5Wq<|9%K~ND*hIl)z{IM@(U~vI>?IrspdPK?N9Lfb$fA^eOrWA-+EI?y833{--H&3
zpMgYN@?u);bEB9S3&TXKEgZ_WESrkgGm`(BJU^SN<a_ar(WmxNwb)EjX;eM%a;`G^
zDqgZX6s)*eDV##@wO9qdW&mt%IgcjkelG*Q-X2)rb$~ddOY%<JG<npe>&Lu2{iKbV
z9p&1DP`94s-rqijM=wapA4p&-VWZ`aeSgi`0eRCtjE1pU>FnM@1AeNMev%7{OvaB?
zsT$X>obHUP0^JZ5lp)$8J)KVoTeFKAmK&t5?!tCFOAl^@xUmM+wH2aNDH_($i53}*
zrXC=zKa*PwdzgOsOZ{}7-u=qIg8l-;;Zp{@qio3nEq1^DoPPw(6{)>w1)m%+C%)4n
z#WgHRPMgoWvQ7%us%pzAmI`Jq;P3V_i|;v9CqMnocmFFdT5V!pj~SNt3drbw$>N+<
z+dLq}-Z2arseppr$rGIv)O4zs_oMkPicc?0+%J*|&dZl{dbl=csQze4+x8+W#AW_e
zM0{RcGZG5-Wv(k{oz~99d(G`KoR)J>TNCB#DCjD76gsmIOQz`CbIs~F5>Ct?DoUY;
zCkl$0{Xyw7mU#iyu8@K+bN<8l3(=7&!*I{JwJZ`d`e%GM7ckxOHGp9wF6fT7#oCrj
zY<tGJ^ESw$`4{O>#COM6qd1f33lmkH6NHOxwi(x3-d2}r=l6)9Dqq*cnV!0^8A>fX
z`L~ceD{rpMeQOZ{#ru|;|L#$IsAGP>v=GY$HUpbBC65b^(wuJ=x|;AjLYB&e<Hw%0
z#lwp@|Mme0yD3~nY22Mg`}6+k$TGmkYdMx<Wf)oHhrBYg)EUaWuWh{opV`@$@!}h;
zrXNYvOxZO7JZuF3^QAD%w+2dx5~KS8UYrXHc`Me-@3k9H<pCL-=oTpjzz$ofHpltm
zUC3l+95G0CZBNi|dhTpJX?ZV7#%06uho0434(oV~jK>ptvr(#V=T9!_?)s-#zUzMx
zj(`z5_x-Eo0uVOz(#aOStPYEjD0g$W1MOZikR{ja6wnGM29?eB`t#T=p0G$7lHKE~
zqaXsbVHWnW2vzjJSM%>dn|$vFEfxSE#YNW<sbKw{Ptz=F_29jynR$i)<bqjR*y5}V
z2gw(PVji1fZwqeSOX0Q)b!%wG<lXa+a@2&8e`)YHJfX6Zxo;IOmK_OHa*GOXj?NA?
z4O;4=CcVAqrp8pR*qN1(&~WB==q~yA(|$Gf&k9t0e=fGh|8F~ltl+^qUgq*cIbyjq
zDqPK803f5bvzX)OA|hCP%7gmNwo+)qtCJGi9cB0j8xG4i#?ii2n&AivvApdx&lbLo
z{@T>#tM#Ox9!~EYJ_6*6K%!>rVr{QyURf?>+r*l}RsPKB_|Zq;@hUb${h+jI$pZyi
z`O3Gg!e91v%jv4hS7^nz53bPy<<6!zkiV8!@eoVr!v%WBo}o<oc-)C3vm^UC%a|cl
z_*?koVdVjD^w$smB8gWGTFB`6<Kw4)6k^qZibZTkzvz(;sksY&^N##xWwhAY=yDnM
zjsY&k+;i+&NrC>OvrEW1`8g91F&~$AE|0<zR>B>2%Z{8>vKE!kJZ`gT@E6a7vRz+C
zL){e*8naw{4MKv|Y;eg&<FQgMi1LBfRR|l6%x*2E6bC@n3+=^a2exj`08OvvI;l^`
zD#cf~#FQ|UlfgLc&upV;*Ww+`s|&)AIyDNCX$G#43Lfa%phz?3F=i1ssH`m(;j)Wa
zNxE%-()vQAqQOG@<0y>J&}(O*XTb;Ry+;SU3qGP(N18UXX5qt=s-v4*CuQJk)j6hl
z9cewzSBT@qi#+JDs9wjlgQN*7ycx~ZOib`n1|O?=nM()oet*O7(SiD9rE?A@<aE@^
z$nz)*?hJNrH?t{eSP&;e71cV@KH^qn@sIQfaAo;KVNO4&Ugq!KN>il|gzq+=RVfe*
zhT`~&UPrS-&hmWM!xFUJbuA3~60a%waV<A(iDOYZme!tQ4!MDw1U|p-T|6vdz0K}t
z7jS&_fva0PH0?s5JjL7eowK+*?a#)8w~z)|O6V<mug1_MZlAvDg4{@@raA*T|M_Z3
zW1!u~c`+QkvI8%X-0hff6#-C0!M(=AxT)JaWx-W%lL#Af;O#N*AC6F#)TV@$4fUE4
zZ$)Q%I#XXk#%}lcZdhtKw1X3|%|yUFQCQ9XgbP0UM4|XUP)vLiW_WJ35W~~4Vxg0_
zN>`>kJ0EHX$876+aMSpG?zuoa9}GekoTH?=63<F0xLz%t>GXXYtbo^FnC!hLorwp@
zU}Q{WbJc;y2+HgV>JLtBbZghD?ynOtgV=k(!I&ztmfWs3DKS8pNGI7xb*!2?@Jvfu
zsrJL3piu%6u<z))Q~W;rz<5bFbG&Z_STO(kVV|^7;73DgdJVl)z0NPEs}p(kdAHC1
z16`}uc#iG+U(gK{%zq?bt$;>=UMz;BcDAmi>|10Z0)Q#=x9#MejuO|WS_YziW$rb6
z^{5PJFF<Z4=+TWzJrO>-e#kQc)Dn&c62khCDy*{e69r|#*)LfAy8@@IIAB4~Yr@GL
zrZ>xC$3VfOhREQ^;!_B<q`OOuG5!bRF1$v-KkOdbM_DgqXbVq(O2NF+95NV=yCf4e
z33pVVNcBFXgslgIEBkbND2Vvj%tj2o=Iix$iRIT`C#a_h`TR!Rvh%MkLQpEBB=Q)i
z!J3(li5@noS)BsJdKkIf#VwCrvz~NB^+L-+;qM(xu#P~nb5xs4m+7UL#qNvbzviTu
z<Z2GG-?-jm(sux};#r;Lvl~}MEdTDxTVX<&R!=wI`kp@YgBBLJ>}C1ZC@0*xE4nM9
zdWonua*a^D)S6B1orxkZeY&M%9uH*2|BWzw+n3fOQSY6*dt-CwKhPW$-_5&-eSwSy
zBnWTd<1tsf=)Jj$2&vKXu6xkeYIeu=Gggg?I&lzI5~R*$+f;{<Q4z2b?if8&zYB<!
zB#oZg(a1?XhUe)M7D@4kqvuYR`#|nCXavNbXjV9F2n{$<=4(QK-qO=o;I=DGt7)P*
zT)R3gW>zUxd&(mhp4H<5v>msIy$NZawvjNIAqgIby|H^xxYqvYmnUH5qu@ARS-NO<
z9~?7xCLUrj!p1}9UyzPf{tk8|Y`nJcS;7Npnc~S+W{$?IWCzA764Yq?ZGl|R1<ACw
zOsr-4#Z5(YIG$#3sr8^C#_-SR3q|MQLA6=HA7^$Pw%1W~>hq90Ha{d$%_b_!h19$a
z-(_h2V)|kIRW$UsY5B<Ut;nya<1yasKYwzdiW6p5T8s8yNGN{GFO>tGc{wZ*OFJD^
z*){h}i9Mi1DH`@uWFM(h_QDln<#i(ZvqKdQIx?pm$p&&B;HN6<JWIZn{|$Ip(X&!K
zR4G4%Tyq6Ifm4yNGRSqzcGqBO3u~HH*=Mrpi^?R~-^LIf5?g9!|7HBx=PGwim^4O0
zoblY;ZK9Sx_jglkY|!k_qIqvamh5u0>~^K+<XKF?hiY7oo1;?7^lDgIWSP?k>#=CI
z%Qz!d6NF{A)z*?7cMtE^kj?DQZN7?i=N*=N#jWeW26Vyw;WDd-3}#@n;-pylGv@uy
z7n=o`N?ipM+Xn0_&bt6U_xfBfSVVzR+vEtwrRffkd33O?Bc&-95DHCG_fGqw<1&EH
z#>>gpd&~?AEi#x<xjWsT7y!Ras8z)R{>?YLI1MVyX2!4CH^(sy==IQtb-rKjnr?uN
zOA_|XW&L4!s3O2U<DPQXSH>dblXy`Oe4=)5cy_Jv=^P_~Ole#mVV6%cTG#`2FytA0
z?U7OM!r}rby9?(?=-#mBdUZ%0Naoluqx9f1Imad;4SWee6E?fK^OR6&&1}l!X4r6`
z6V|?3mEk8JwDCglT?=3iADR^IyQ#|rwD!see=uKE4gh`ls7Qgnw^2BosTUl<dntQ!
z)53L~73b%(k-f#c0?5C|iAva4W%%2CK~iNC%x#8#0u=;qGcbOj-LTC<Cme1c4`_kQ
z=l?2@O4ALIU91;Od&+$_Fu<H8Ug)=Pk$uS~>A+B_Tf3XvT=Q52|0NXoRtB9Z&qRbn
z-jTj%S`V^Bz+Q7|Lb0RRT>D{w7V_J;lagJ2`G8IiyjA_*HVnB)M}S`eSvGw^K^BOx
z-N2CC#5R#Xinl;4+zsN#Lq#{3d4AI<;D*{%zy8#8f4%rlXFK2z71YwZvJlAla;8Pw
z;FsB|wCh~aea3uW?Tbw*L9LTgN&hc5Ly9$DB1VAJr|+^Boxdw>q@L_#z715c$%7MR
zgwVIS&3~$4ie89M33=X-$q4*(lY6H5gBXulp%lh?>orCF+&~@U;c!qu4X5*a)CpS?
z&~*P2X%_BD*yq5Grm*4tSI=1d*6GpvSQVS|l3*`o%k&BP0Xk5WacZb?7Ajt6$6s9Y
z+Q`8yjq(Vf<1hjQt$uaCqXwT@qB#KHzMC-*Ts4hu(GL1(z%Qd9KLAA);#bh(*p3j-
zy+KK5X+S<#ye8^_fsPQnMR`p;YaxYcZek9|Lsje@BVN7PwUUIj051#Y9t*Q2(#fa5
z6)HAN($#J#sE~Bh5V7ZaW?P3K;U{iCVeyHS4V;eki)iD|&pQOb*(y;cE+78}hHE=(
zYe!nRP^R{09ls$g+JzOedA7QLRW0QU-LMJy5rR!DGStZ}mw_Xv*wN&2u+Kk!2im8?
z0-A#Nz5~83%D0?1_=^$nv9w{~%2hW`SBwQ_mMu;^f1C0$OX!5SXQk!#ugKsdFzz!S
zSZ)Ek%`6I_KQ?fcl@OL8D_eACT|T#Q#1vbk85Z|2@p_V|w|=r>&2Rp8S|`eBnI#EM
zqYmgjm!|)L%6caeu-@auB@*1fL)|%GTUQuiP-%E|Q%fD_R`nin>smyj9u8GZA2VR)
z$zcQ|eghy9;Jb7ZHKyO?sJVYe9v`hIF(01%LUL$a>=^SPQ2!Xy(gKsssNXL7b8tNw
zO`v#{>-u)I{tm!j9HYOz@4v#Mu$K;bc)S~zCrIV3+t!47?16far{7mu=kVuuh(AN!
zRXL%3_Q2?*>a_vVGoJuoBVXe5P?th^1^OV1{%D}HKa^@pTZFc!ppXL-x{<&DiLc(C
zvY}2s_&0flXaDrCU<)^(&D;~JLJuCWd&KH{AXs;socN+Sc3tQh)%7K?HNe)E%peZr
zuK$4&P;79G|3G=KxaRDL*nn}Za@NyPr@lZTh+pmec~i<>n6^6&tTIFsm_YU^bNPK4
zQzL)J;ciC<I$KxvOl{&l0eB&9AqUCw-^&57Z@l`A&jJ;eBy8P*qQ$3ORN;-Ya|Y!-
za}t+;I77oXXo8<R^X$1W-RL7mY{xtKR4QuA<h=dgMUxl#!cr}+2D+VgX8~mXXkRaq
zQCW#v$x=3VL$DW8em%*lV>ChV1y1`J^_pMA=fN+`^jAM#h6+72^4$PF4=w4^js<d8
z#>;$*>(7bwCsh4O^hACUi7RnbdVE>|C(wa|6n*kU>Sq6Wq5#*@uR$-oe+F2G@;r0S
zRuK=!UvRX}NoR-lpnqt)Z27GH=KCn*lkyeqy%@?%&pbf9@;=~HR2x4$GjiXTP_9Y8
zCbHviil4DJV8(F5B#7M)pW~v7e0ph8l$WjVf@0&mh<*xOy$_6@!=%eydl&Ce{-uOf
z6}}D6YgIGH6={)^s^-qYdV<)CTbu@A&i7?LylYDQ+FtEh_=Z==4>|e3&<qBn>-?KD
zyw%|Lq<++E=d#gF@Hf#ibMc~BI#JDUrY+(|Z8z0-*3oPWMu4@h%DZ&l#YH+{fHWrQ
zd2gc-G-lg(m-!ncS44s5J@i;wci)_b$7Bn}27+vqz6LO8Z%2;4QRsbQ4oNK{v>dA-
zE{&slt|Iq+P^x)}Aonb6IZJ+^1jMM(Yp`rc%?N>fKjV^L&(itSMes!?Of{wG@aCTu
zWu_Pp1oHbiFguOLj?wurLY36qd_E1)0T&c8&XJ<Tb(356RHo*j;Heuu!pDax5x9|e
zOMlDQbT#!qwM<}1l4~JJgr6wR&2(FL6i&d<!}U<EU=3uPnMZJiN(C&paEY`QRD@B|
zUim2j-9OQJtE)RizmV9o2vV$32n8VX2l8#D@phU)=_`R@y3F0tuD!M{d6%M!vqDI6
zr;spM=)^%qT0J5t0LA9EmEWYVgP)75H5qGA^VJeJ8S7=fBZ{%W1}_<7`L;~ao`b!L
z^9F2YhF31SbC8Jx&7N5Ws;hDWc=N?8=<bVK`|!Z3oS<Ypxejw0MgkkayQR8#1PA~h
zKT4lyk+9?%#g!X);#SY6g=>EiSe4-xla`&L7+W{klp#IU2Wg)OjsQQSo$tqd|9mQo
z%_OC2R=1?&>F}6TxXTA)_Uj!5{JbFLD=?s~JZ*5M)IAyoe6Q30fttiPm$Eimy|caw
zwfH{|`aTgLKUk6ey;Jf?VR%lXi$DpeE!eCcwBBjf<TYHrEFViR1gw0ma{i^U<P+=d
zB%#7^2lIBx_fj$m6iPga_rP2^w+~G6Uws0NrLm2vbKmp2`_Jz{&0cdmx+=YWSyf+4
zTDyHu;?JOEhH6{^`+L!mWvBefN!H-157!3N+dkPK${i!3TRoq6CMj5${E-^O+3LBy
z)Xr6fN{W3^hUJeKt0&XVM$kRFJOBt1%tj!SnpmUaBFF`XG?cT~=$Z#}RsD+0{51Zh
zc;5#Zgtk9Y)A>+<v=TLJbgU$diVHM&4s#-4e`SFtAY0qvA2c?)!Zeo|PDc?yxl7c2
z>|E+!td6Qb-b}Zh7;RmEg+>|IzX3mPTDtOyuU=$N5}9x@Dl$ab=z;F*y4Ytf4&{!|
z17~AUK1pp2!|`IPJm4U#cY!-dptIC2mQ2T$+j)0%<T+nirlS+DDIU?Z#HREwY~YF2
zaaDc+udOZtW9%>ZD3O-*-!QLqOfQ)dtC+TW&p}qi!5o&4V!V1elMY8pH(mRNJ^laW
z;yniVfOGg!7AWw|9>|KnVqbhZUE4F`D0zuP8ck}{!-Z2}0k1%g4urIm=n_GcyN-m4
z>}{jJegvLmnKaFoaJOuwOS`h7EnQ|T<80RG3N8#nHf-kT`jTK~&G`g@7rZ56&F0@v
z5d~aST2oD?E@{G0etBd~J#mS3u;hAdXl#*YFVD$;AQGMu{J^lx;rte2ogcbC_Acrc
z)f><6xR^24Vc@;Hj3OBQGygDhr<Kavgky3)|K?MX$Dxi>!IazO!57awy`fz8Sc%7O
z555)Wpoq+fBiBd+S~p%jFwqI|9eSov>!wSofeG!=D=V)Nk{(*qeS(r6{wXq2JoSq0
z12=<qocQ-`{x3V1`f>gSHtn^aEc$*K(~Bm|myS^_F}RO{Yl(@Tk?rVH*KW&Yo@q4g
z&@}lcSAi7`dn0SYo8o_99%u!#e~0>u|4EPv0DamudqI`Xh<?xF$UGS7mA-Is!>48T
z!U`^$6+Kc!N%WCmi|&V1OQ-vvSkUF5NK0nX+ck$<5V7XNp+u&ecfiZeNx2&pwT$3B
z&Q~T{*RJ}6zz&yD(Tp^Q`~@5Cm~rVhJaTP<#!UA%*UXiC1}w{<QT9jeyyPyFFrAhV
z-BHJ~W#(yD?a*IlFlY(yWyHctlQwrijFPBMQDyr&30P4_B5Sm6IFr3vs%m}DK(;26
zahHOx0}V|544J_%p3r0>&Eda?;0tAp7fsCq2Xbd-ByaV5^y?jFlWk_yFx&E_pZbc0
z#3Egq*mJ%(zJ(gtZ`vRgELvzsjnj1YqWb{9Ta03{Wq68DD2B|+As(#nIX1!mwS<{<
zTjVn5_Rx+0c<Qj}Y>mCAnT_xJO&u_L0vWw!x0&@r0;hU46${N4()x$*&K*C?)Rjm9
z-j19s<-$5_@PoaKd=>xcNA?qoy|lzojQHI3=6$&U<Dz#!;{D$+dySfqk1gQF-d63j
z4@(<M|H{a2i@hAso7xenvq@0VaY6xQ^MgsUy%l2MC5YN7^aGM<45S**DzQw8%4&jX
zAzfq|c7PBPY`YIzUj1s)K5KC{dvT2$*w$jK85a{W*a??<f2Xn;EPTFad!s++E{o1v
zN*DQPvg|n*^BMcfB|ZW%Vda-^*LLyMMnU$o5qtPUFA5X?$o@Ex`})I}Ak9r$TC@aW
z*W`p8`BA6=xw_A<;<NO%A;%VD>~HHh^pIr#)<jUAqvM<M%UI%UCc>6GuTp{s(&a{u
zR0jBd`5GMj<BXU9p+ig%SeYUEno)-;&fMuAJ$?2~b}2@m)mZ*{E|thc2b%AZhIv!F
zmk^E`TQMB$7E^lg7clR~D8xFnGZmY|siC8t4v1C0GqS;x(p7PZ-TTPdwDa~@imSs{
zlb%L^OgoS}N3;_Yw|(1*u-JfI+GzZ-QNr+W7WWj0uxGcG!fh6|p8756VjQqev5wN!
zHD@c}zD?i`_sROYmb-^^4T{R`YsICMwW<moQt+Xg+ivV#Fe9k))=0Z$QGaBKhO7{|
z_u~mU<PGGFIz5VwU5sqdLlT3Y=84V$g<_Z^WJOD>g04t+dWxCZlUb~OnzO~)XFU6X
zu}Gj=PUPyA+|4rhNJEVtEp?1NlMUZCEBZo3(XW7;gS01^hGVP;Skhjxhw&9zHW?_y
zo<8Kr7}%ZHr<aT8L;KJ{y`HNoIJWIe;A!uE+}f`tb>ru%BOM=g0SDyl-YP;nKg(PE
zHgd3R)UxKt)9#w4&Rg<Eh%ZTSwUAe>KF6jf3}pqW6XrxiiH2aK>jo+&YjrCV0g6`4
z36;yZw9uWfv8Rg{QP5pAxwg_oS{+5s<+`!Bh_R=a7kgfaUu(*c{UJW-u29+psyez7
zu^im4V#ThG&O9X?*l1gv>iQKYDvI<$4YS-*XAcco5C5Xz_D;58m(}n5nTmNW?4)8@
zFULjB^9O2s)b6Xc57Jvby_7p~>7Lq2kk;$CGXPpuN3zDKG|m3o<FE)w@GGNuYCKAs
z_itS1NfQ$<mMfpqEn2?0!7+VGTBK9TFvkeG@apGM`~d5F-V#+@te25{mg?n7j9~wk
zCg;L|Oj(jcofwTKNk3DG6x-)2O>YU6X@;`5H~7>)o*wrE%JOTpVi>1?hIMSXV`|1E
z<0bisxi@OPU)^c7L|Ro{pQz>rc*k<zl8~g-|73AtYG@e28}$i2e8!P<>)~`0h+B$?
z3&NafSQ;YfJx}4?sPu4A#A5xOB@I=KF=t68llYH7>pFt+#xqxH;DllLO#rEN_W@L2
zQ!({!vzz>|4ymU`gYs#Zz4t!<NJ|ed&MbuI+XKCL&qk<A&g2~u2%BIgp6>oJaTw^T
zN*}NvGu$A4&lEh^AjZ3OWm${9_z4oQF;F@C0-qwS7xOYL70DB}eRaVr_S)5#HRx*N
zSYLtCBv&V7IP`Lm>&@yG;S6beX?M*TyBNVaKOaTz@EfsPAh*-Cm`xPxc=LZB8XT4c
z^#(AH$<-wj5-W0pV4IXXZ0ZAn%%H^4nXlf_ip3(kMKE~<wwp3?6;fV(8~h~&UnCWf
zX99X8Lm6E!=)rr|L_1pI8DYJ1L(ONz6{I)_-j~Mw;hvu^n}i-w&zS!=HyZ&U)izyD
zaA*Y92piAK2`)a{Nzo?KHb&+s04;eBTB<kl5QR0o3sjZ}+uOfJ<UE<rW&8VrJ=IV!
zEsp^YcC_ietmX27mBWLan7G9<L;qIx^9fOPO3&OCSZOdMG$@C?TUzf<yjzUA^SFF-
z;i@3`yerOU#W)T@3hs0-foM8)MKgwJ-TTJkn^d-V+~+`C$)KkAX!#V{0Ru>q&HAnT
z`vdL39`UvjG-i*STn`mUMOc`9Ak0Z#_`kFG{=gb%-IBVi50W0^iTgLG2@yepsX3PB
z$&{Xpl;)Ht&!6{gWd#7FvS&#fxD-RVc@ryy*8Jrlx&N~_HOW$ied_nqpB<O~4nUXb
zBlIIaFX4%dDGQ|jRG%O<jJmtu4FZJZwYSRjAb;1#+}SEX2I~tkmt7TA|F<t|-;~?l
zpjt0;@=lK!ky=^ST+79OU;lr2ivFp_O(C23Gl|W}vk`)W_3eH-S4IYaMEN%Mx#Z7R
zn&kIQU9Wg@fu>y(<dF?K2Jp<UbhJWu`2LSJCcG=`IR?<G*I7y!F_PF_5nQ2Y&mq*s
zI?K9;YpV+cxN}~vY6E5f#zE-MF5}-X8GWQGYutTQu_507A4Fy|2JR;xso6(s_DdIF
zVI@yxI>^SKfp2ht;H5VCbj7(;^1=x;NwW;TaS4}Cjb|NfZwKAlH^q6>VG%)rExZ{H
zdEefE13;6G%am>z;aN)T0V{Z>>H`E5;JnpE<;F{~3SVw4X2$jyP|7b&V9*io^v_oC
z%}arSG7&eT7h<A2vp>8(0TV95*MrZ2v&aDZjRkD&-OCZ-zX4gwxkBCudak7w0jK2O
zcz{;TOd?lzAha<sHVoJpf>nkT>zg)MlZuVtuo#n(hWl!JF^+je{~Cv64hBJDwLTZn
z5GD1?QHs7hNe!f6z6yz9FOy+f$ufXwb-EwB1TiHEZk)XDPYYj@H6UN|{JE$O5U_?c
zd)}LKa2=PNJw3sfid_HIBZ4<SaHn@o*;DL6YD&CQz4hl30lGv}g$s4DP1tP$`rE(4
z^nCyjZ!SQc@CTK*21&lk2LN&9k$}qpI|41aVfP>G5_n$veJ`fnjRJQn@GH6dCuW@}
zT$XlM5B6^C6XShAC|_10<c9W2`3GP93%Wn{`~E$TZc%bw>Q{A*ayy}u8NWR28E>a8
zSWf3L26cZ_Mg`%>9p1edn6@Nq%QSc>>8`80`s1TUISP*EOy4ej#bALXd%*P%?@wam
zJrYPcCkcylesiCt_h+)pI(Jm3Td=m~)=r>zI<l?mcxN`{kvpGx+<}vo9l5{<*TS8N
zsmh-_cPWGB+-po7|1^7<P|8(`R&gR`T7y?3QwTaaLW#L?GU(@T%p{i@0N>u?mv*B4
zYSDw7Y2s;`)5ZIkDGz>d!^J{ge*}H5mU1syn?svTM6<qT&q>%1px9U$e(t3*>XPV0
ziSiPHYveJM)N>FW11CVXuDjn4ln5#FPWL6=Gv+gJ6Sx%3$D|IFr{Cm~1oN4YSO3do
zCj9Z(Vd;lJtK@GovXu=&YPm7ZOXqYTIHVv)%-5Ll#Z6(Nn<EMGp_rXZPfnTRBL*4_
zx`bS|EPGz|fv$@7Ju9i_igwLHxy0vOy2gtpr<w2FvNYdLN3@iWV}5PnDiepN4Ud*j
z@E0JiK48X_Bvl%m`Hf<WEnxbr7(U^(z{JE$H!b`nzrka*jqa{(l7c*Lfpqyq-?io5
z*xH^+#LyQU$OgBu`t`C##2axR&s6$6L2v@wYO@!kfFS6x_g+hWg<rB_AY7(~E)-*Y
z+gz)x*WNZ0ycx9$kMIiCmV9GItq}j2eWA+aN>etDIMXt?+X+9B>iUxL01^7!7^OqI
z(384<!|&-bAQrN&8Y3D#=dsTpyS5y8W1Yx`gb*;cw{zj;#^qC&$A7qnf@{F8U0`2o
zGWyf=WX$(#GLS!mUtcKIKW%|>1n6a1^;IqMDu&NYW|Qgc)t&+kqZrA4@8@FijL@K8
zq#Fi8-5VEe*m$w?y^p<OQ@3vUFI9g2Zg`9)gVn!hJWJE9C>^ok_j1d`0Q?a-b7(vR
z6Sv76{b^JJCfNiK2<}>fUE)J8{sJbrDz?;@zrVFu!2&|ovJ~@XlkPo@5o7EzCc9=+
ztkm5w9}T)mdhjhz-1}AJS1YQuHRD>J18K!b?Q1zv<&Xc~Uq|sQGqT9fnCY^=d7eaF
zP$r&Na!TAF>wP-o@6)NG-^dEsw?A&!o^)eAat&`(R9Cd%G~Nr^Ke~-c4}MnRnxr1K
z&0jSC#y0Fu)RL<J<%TW#h<iA&LbVaW&n5Hh=5(NK!VErtNQJHcA4O*!*3{dF@c|-A
zqcp-OMUa%yF+xJRMN&fP?id4+kQyZ*AR*n|DK!z17~S37Ft*=&-oN4E;@Y0`oNwIs
z=Z5F%s$MZ<jY1)YK47Xox0PFyJHoM069L%FLka&$+KZt9QR-Ukw@*?;x)x`~7r<F@
zkY97iS?1ObxvWrid1CsuLFG;Ulu%c=*V86}V!GR}6&Z}Uw$?*d6Q4pDDQS{M=vRWV
zpUWXM!%S>Ju)P=q5f)+Oi@z5_?mT?|hZccXmAW7Uic?0tnLIr?SD<m}jIwR0i~i-U
z{g7=P&iNiY!gQjyfLGx8KL549C5x$`mP=Q$u#%gmDZS2Hn2L<@!35)reunLKw!M43
z><{DL^g8}&76*<#uu+PA=dj0Xc+IDs!SDutb30PPr;Eu}GJCMS6te?zzh&zhPJf_F
z-Rk?#Mi)rYt;`~QqMdaK`!pKdlk0M&Xe%Pl=U}qpul0buH}|Jw!bD;~=$piwK;B1^
zp11V*XtUIjREMMkt`}|pH|-|^>ef1C94``D-qA3GOJe-;uDocyw{!^SVBl-v-57#q
zz`UWK8}Pb#)&kif5%OlAy3`%g^62uFynRs610%J3jKDj1ebvb0q8HNjM2jEes0W1p
zU%YTVKEiomXS17S4{x*&{W2cRbf`gNgaTi_B&$8uDVfS7_OpleGt={WmAhHdpnOz(
zlT4ix<g#@$$8W`_f*c}&DVcZrRQfOQ>0J~o438qb-7UNc90vY0jkxcS5j<2EcP`;t
zy_AGe|HKY-Z7{wE0&!1s9>=CM_wvAKFF?Af>XWDE_L<i>cG0WXJm>aLS}tCccNEQ%
zXG<o<`HAK~N?%&CePnk`ca?B6SyqOId_i^)t?xJxo24XIolMZEWVyP17MPf5G#uPA
zNb&|TmbM9`$PfilS-w;ldcf#c<~qZ!Ltw@7K@mjB%vRmt`~2x6$>H8D>2GB`!<jEX
zw#o=ByBL9W8tP;?{ve8sig>H?HI%+Hh#s_g=&=GsGUL!cHj*dx{TcGnSi=<N(*e76
zLlo=4JPrHZb7i6Zk0zBrUPvYDvfEsR$9HkfNM>c|LcW$6^4)a^)f|Dg5I4%~JdyQ&
z#?bBY<h`b|gr>Km*K5I)4$9J7Da*kH>PD*>Y;WTOqHHI;+^!)L<^zbP{W$pgAAtk)
zS0Q{?DL|@vVZtSA@*aK30Jj#IKjM)7;LBmdSGR?9!OEK3_AgA$BbPaNhyL@8Y>hEG
z;nRkjeGUg=`2<G4ANnGjwN*DAc%>a~CjJApl7OI}nvutfG!tHh45n@f5rN{%LRgXx
z6t1g%v6eh*8fUKm54O`xg!xhSt=FFR4t`ext#z3V$GpJ+UeRDgSLri!BfNrRh6lMk
z`RMo>(8w~p0dgV%m(Xz?7Lq;VRtn(HPqCA496fvTGqzk@FNxmU5gac`kl8?RtarUF
zIs>+(PPcT3NS=|UA9Db?XD^m}PZ3#;7!#D{JzKHh^lp+2wL)ch*V$z#Fhu4=P)FuF
zCrSSY!uSU-?u59;*MN`oNJ?#M05$*z9=g7}7Kl6Z+_*cmcQChoeC~wbkvySV4y05a
z4Y^&Zz#5Aj`0iqbrTtIvnR#TUnw05Zy?Ax>vy$7j4+o)Px?O}@6m{50ESGsl`i*g*
z48qxVuo?W%Ra}R5zCuy;rG7!3M^a2wp%<V&_R;uOgZ*bueM+(sCO6L~J&-P>ZXoA9
zUn%uQG3_bIr;V7(_<qgBTf61C);#?A!qV-j91;InwrjutTjhx=TpNYmcIzk&iOlEd
zhn^8V0PCvodW}mP`y!{QH2+T1hSXyXiz2-SIJkSU_!>RjlIf>n6s&hPlv7TAsdTZL
zHB@9XUQJj@c=v9tol$SgvPZp5@Jrm0q)HJU5AwByaxZU7jhxUOaUf9Z)%nx`){`%y
zk_e9627-trfY1K=K=IJnKCXTM_34rP-UeT>qYhuhvnOV!%2Em<SPEZ{<|Qsf0W-bl
zzDJ6aUObFGZHnG|IYS>BI?;6!H>>FGa?2QWC~BMT9@EjyHZ7W?U}2NTN1)|`KKgM5
zCkst-Jqjwf_b9Yo?iW7J(*aT~c8G$lbrDxPxQ!!Z)ZM%@hr{4gjUq#9tKD;bM6Iu{
z7fVOeQ=M|a037rW_>Am9rM#Y0y4a`{vSU0onmOi8$GY8b`|sp!`y=iIq*qB)UZ8qE
zNw6W&FVg6`=KWPNqe*}KA#^<@Nf1>fz5~5dHj$G)j8kgWiM}xC*<A?Gc6|vX?;)Eu
zYjEsXr<va3DinI`DcD8t4&rzY%<rdXEd{i6ZT2Zj{j<Y)&nu*;-8e_d(dd_3IMs7x
z$m;0L=wK$gHUC@xj<C#)_b1p|U_j3Yf)jHW-f0qIgDmOCRS#0&_@lL~GP+p74`^9m
zU2dffmM8R$ao%aYj)q3goPvS$8l1er>5QAx3)V^^*gHCr-Rx@xp^8h%4|{~t(K1oX
zR?}(3BfvHlepy2Lz3dsdKJ!0NhXF~&*v1~m!iwIfDcQ`u*TMneAYELxg1y-5BjBp{
zPeQ*qj3e2HFYB#45n?b}B^P|kJO{7k?Tzc^gKTk%<XbGxm-#Px>9uo0hL$nz69W+{
zgCxEc^Obf2d6m#{kBh-P8FujpIB!MT>QFC|(5!!Lyn09%72cRDfX`;IgmwiN!KyCo
zq-ae_{Adm}l<aLKa&;KDSLuOEi|(Zmp~+4+W*ocfTLf!Ul*Q)GSDlRFHe^R2meK^6
z^2Z|~4?wu2ievG1ie&{a{}?u5&NxGjYR%Fu7AIV2a~`nCX!ivofVG8lIN4na$0B{E
z*N*bKI!ITeEyhZ1e@}siDuQP#ieSk3?eQ7CF06>_zSXlLTX|1-s>tOwJci8tKaf7&
z`!3P`s316CY+@23^0@XKtif)I?iu_MMHTP>u{?XN`~HQ8B_CP}VDj&hDoW3H!b74l
z6)n~2Cb5^@B`B>HOW|E!f)*;>;VIRRPTzvc(yO!QYc1r$Tuk#QyIZI>H>yG`nidia
zHd;DkT^oNPcJ+X_u$N)p!u8kY^I#HLo|MY<&2~w+ch1M6*2%|ArkO#vg@O)h%X>}}
zFnh$TP_0;^W?z*1ZtLGrCM%pB>q7j$4j}jt`Lc>OQ*AGkCo_yIWXwy;FEix-;+mIZ
zE{6B0LB!pjEmd>{b$MP!GoS+e$-ftiy!wo|c~rVB*Cy$Adu;;&lc@A&`~?Fd2zuQ9
zY&I=|t%+nbF`<>wQg&BaDZ)Y<-ovlC)NWqoPY^-=jA8P=7-!i!$r=0}U=<^*a4{H*
zU(mx44Pf}^y{MsnXSD#3Aop_sRMxc{Sq>$R>7nCO%%|#`1Ca?!Mh^DIpToyn`gyr_
z%oJA*95WL<1v~Ozd9B#J&tEnlC?e(6$QoOK*t{3%<F;%Sy&-!ddSw=?n_{n#NT{IB
zZP2r?Bgd>Jmkh<NRFNs>B#2u(jx7b2_LDy%r!^ya^qJ6b)E4P?;85p@NHdHq#$?(Y
zZ3WlRO|*-*N2Z~jAYF5FOwjd3U|Z#0psv(AR%swvg$AS$Sxg2GjAPKxX>iNumJ%z%
z8sfp~$rIC_V~HtGn!t-?6;-x*UmD%vi-nyng_SC^Ex;9{g%7`Z>-a9Du;q%2%lcH3
zu&Zr60{~4V^%=<ErUyn~aXHufPS>HcwP3XZW;U0nhudhLRH?@*F8A!y5AM^QVW&}<
zz9qeZ>AEoZ?;PK(&5R9{hEzXK0P)v$`QoSO4pEy4k9QSE4FQqY2XTU!adADZ{idYB
z8YkQ&%x2lyqJ3#LyH?Y#((jLNoxOf%Y`k&X<Epxfi1Zk41neaeOZ#l1_2xrj#n6U!
zIdQw?AJk{$u)02O-^Tgl5DmM)H_Clh%dELhx_yA?pEok^1ULfJ$9=V@n|*l`r}{1|
zI82-gaox=q-BjX6zOku1oCM7e^xpqpbEs$T%q7CaPL$oi3&R})qNIRuJ+&O6DI5#{
zMikl-MQgKR4)nDo6_H?j?PDFKBHwTgbDhT*bOj$;IIeiB-!A$k?RG`E?}&fZZasc*
z$uLNTw{th;HyNicf~GMD0vmQ8_e<b7U@7L;ngjj=4aTyZOrVt=upQ_6@KuI3mySx{
z>Vg^>ob)D~JGf+F-~;j0Wa0C<U4TB+7C4K}{L&7<VhN^iext-P-)L&D$Tn6gxVi{|
zVe})f{iQ7|S5Gb*g90W-Dm^sm@jsI~PfPzS7KylU<#$=^xE_W4z%j-`$rxjju^(*V
z)^-3>j&JBjhY_kIKfD%mwfug#=*Es=yLkjtzm|G{r359t&Mps6a%iURuMBDb&Zi4K
zMtw1RhRBu{ytL12>aknY#MDFAHPP?F-UUa(1r?B%KB>KK8@JsndghKNGuvWFM$Rsm
zlh!Ko0r(1K*Bq8swm;JbI~yeyoZv-9QgrfJ=^1B%cu|D%Tul~yR*3wREMmP|^*QYU
z8|CVnDNE2+R+nkA$>VqLMk!otz=ge<rY>&)p@fg<VQmiZffT8;;daB9A(y98wb@DP
zP@ucDCoxw~QQ)6xu|Pc@c0zIw2-zNf?<}nTa4M4V0zYdxi1d{)T4zrg?(yX5u1YVX
z`}sU_`>oTK*k17Y`;qd&$@;;^K&sKa_9P0tqn)&;{&B%KR4+>YSxTgd*W8z};wLX!
z0D9hEv0oRnI<dw&U=J16y8l3{tdrtA(Lt}&#E+V$4@y1mSxEH5+|l+%ZCQ|C*&ebJ
zLhYx8@b$?ouL|ER?*Bks-}x@D@c0j}9%t_>d@(|QYFAYFOm;&Hs3PP=?pqbRPFVEK
z*850(Bk-1^^pg5`aWABETwhjG%bY&`t;}j(rbFBQW_w#XT#EiDx$n0T-W-_S+H_wU
zG97gJK#PWn<&;KKnDUyE!JNGLw$ie6pw}E4w1Ft(e3(%oaC@vF^|IQenOmr$eHnSH
zBmASBsWtMxRbTU<!tnHJ*A06qx^ox3?RB4dIiyRJB%D!t-lo@mMMV#UFoJIh2b-n=
zL0V<nx$i7+8cQCAh(3VToWbWI_=DkJB}m5ipYS#ADU8-!H`uUY_7qO`!)}kQ0qe)_
zewLF1TK2^*sV1FjGVHIWIeGiqr&u8O&*q-(>cPey>GHe6SYTc;;7+U8tI*)m<rxZu
z+gR?jx?i?&NHuAB!dR3>+}*Gk(VcXA#xpaUMi0cM@|;GTqS~*Jjlc{1@K}yF|I`kG
zVzmdYa=1eS?}1Vwsv3f!WOBy+4@513GD6BmZ=LJz(FfDAjZSaA50`pe_+?bT>4><u
zx<vTK&*S?$#8olL>T)aTaqf$dr2ZGlh7jA?oyQf!(&yI!+!M)+W-T{cqj?DltSkru
z_9@J_K4ZxY+efksIuG9e*qk#T@*}%8Xerx0pcpbU7IpQ93XNw(=LpwJSX~RH`nlQA
zrzFlxUYF2CW6FN^BNlLg`X@I~HosDCUJxwv4Zso_yykiL3c0XjFIc+!ryG-LofYC&
zN`8EpA#4&&mNet`7E|Le=7?C~GC$1l`mHJ_aHxE@$9(HZ*ZDaujQ*^+$1d?H_K;<&
z&@G{;i>a);kc@mVAy!;g6Fc7;h>uDO*->DoZ|zw5Whx>D4EM8yoZg&4#%@umrV}Dg
z^l+y7s?t5aA1M}{$@l}n&+UhMc5{Ltn-gBW-Ka^};IQKK-KgaIC>rglWwwL8&hO^f
zju$lS4#NS^(|tPW30PhqH++3bK>ew2OywIl0J-*T6x`?NeIT24lVkOzlXXW&;8r){
zY86z6HKZH}?bFCVj)fE2%(lOgwsOt9ntO?BL0Y?x@y3B<f1Dy%YSG}Lsy!t-aiN5F
zD@g9%&8(P_{RyTyXf1I`hvz=bz@(Nm51ED>slOce;%`Aa;O&qo&PkU(gx5!26|xws
zw&@P9XPySz8(w@Jb9bIWKd~1YbIEvqybS3dbM{*-7TZQo;16ni<peccExT^T-vqST
zKLKKiSVqmoM22q!*3u!2e?^wW7`yEaXxDT5L>-FmQuENHgBjbc9P==ilgnzCn|t`R
zst%ZJrg&&EWd!XBXa(qP9|(2#0C1kSnAChH=x(47X7de%gg<aZjKObp&+X^VD(F0p
zK#n~he_y^}E(TM?X8Yi&k&BN_H80KG6i;VTo?>74Zz=bMslV@1RB4sPE=BY4UnN<v
zelp?fupWH)IksN-d^gd-eM{9x)B@q?_FktjWu?BkTU7F*5MOSIF*>|k>;h8ewc0QB
zly*PLLnLCIBeJu8s_o?dgT+&(A(<z@w|nF3Rxh$*i=7@#j*)>Lhw69LL+~Y8t^Et2
zXd6XcY<U*6MdoX&@fhWbap>XZcvIv>e6y-YR@!6ze@*#{NOE%c{tqcY-4@5=k$v^D
z`f03lAMa&7)U@HLZ`K%mb0XU!D(2>MzaO>c&2!FE$yeRgsV7Dcxo&=tEmi}C#Y9=v
zpLZLm?6YEIBnEQLHkTzS&mtcytss4Y!*O+R075h0X=8FBv52}X*h4q1*r07TYTC;O
zV}MEye;qbYP6Hsr!91H2%(NBXzaGBD6qSnKr@J8?QKW!w;NJJ?g}uR)kW|sf1a|M7
zM|0=K%V&l!uZ3Q=Ol!c$x_?S38GMUFzs^QbRs>WW-F}ektOrF)w+|yYz~6*2On%{0
zc&PBU%ONpp7D362bEl36F#vA>q(8l|YQ(Q(hHu1g9}OOUxdbCnsnm=V#_V)o8ChtO
z1HFzhlV%a+qtpZcS;<9We^M^CA_rgOT<U2FE9(BuHV;1`%n%+XxjXmoIDI1kNBJXg
z^?uCQ>Us{xQ5To4yocM77j+nm8`L5*#t>>ca7zdLu62wO3ep``&nOeq_;V`@!Z}F`
zE3UDKNjE>>QF~&p{SP+GW$R-hHnDLog`mxU7?u@H&-rx0nV_x-w|v3Q8((>j2q$*F
zrM&sVI6pyizA5JH@uAVKV@-dAmxS-2y}Y3H*uifGYeJZy9!jY(cIf+j)_j?zvBM{m
zANkv2R2foX?NLgZG;#IaqzM*Hua#S*E7a(nv-sQAyRV1eiR&lF2y$h?+wJyq4WCgb
zv7cYZ3OtP_p(U<QNF<Q&XVQq%Bq6^h5PGsJ?us4`&B`rR7_ZN9ujRj9lqu&_e^uWr
zRZ>u2y$lIP6ev5^$9D;CGZp5M?-KU4eU^B(m1d}zp{#fN49Lc5N>|DL5sI@@SoAnI
zQLtg8gmPiW4f8uWYXTHovU79G_9t$Ygk=hn(=G=;&eZ#C%1(9(4TcmRD{0<Zgzn1_
z(=Vk*!N>kdO{L8ph7dS%5me%9xIp?GqotO%fjY$-r@8JIQ*#ct9(Ja2ccaeVO+$P_
zwP&{FZiO&WU1c$2vr&tzLB{J5ArMreeHitDJ$<ca{z_34Ao2MSQ@(GscPlC7WL@@_
zpiuTI;)s@$>c?fK|NHNCN`_Jg-&MsbZQKIh5tm1~8V%S6!}Vgq*#x|BdQpl)T2^uh
zw7M=CqvLQ}`|VBY94#-RPT_g$fEeBJYc00TFN88IZBvhMcv_h1dxe{_FD2ZL(|<U7
z>A2P7T@*oDGd@J#NJai!F<7ju29~cl%4}1J;by#P-13x36C76Z&IMg+5{sT&3%8|s
za!mI7SJ-A}Xc)&#L*PA%cUf-oV?~3O>$C0VVSc;2HoR6nq8*@<tdRLl-K#6*><XJ_
zZ78Qoa1$VS#<@6H3Y|?|MI6^4{6C<o626L9Ac`Qwqb;bu^T!l_va<cl)boF2LvHRe
zCo?Q0iO}0}0x_fwHX9imkEC0+@`?4wety7Pyb#+?*ZpZsE!M)cR__eyn~k4wQOTdu
zK5aoZGulOdy@-DOaQCcpk`4tqMP~L+KddOswyA$AEmfirma;}Sz!~!1vqDfJrgzT>
zxMmf!5rSFm^qDhuWn<y+rNT(h3p&vH;tmDPY`yEe5BhAv&qzahm#vDU!0>TlQVOBe
zh!I`=Xs`RW3osPM{lQH3P4<pnYwk6v)%}2d&v4<Z4~ku3LRFpsOo5ARUu8x9>X1>?
z@ar8*zLTb!W*aF1x*pazICDTK6}<K13N0i?ScJtJ=4ZuD)#;uY18J|QfvQK6?`we8
zYW#=M3=<2`rFmxx6@R{u2lv|%``cIj8v>7ql$s=ESFck&o(@4*SK(#=31&}gLCOUm
zfHvLUEc2jdBv*=)G&jh2yH5XVSQoq0G6x@PxpUM0VRqQ*!XkUo&)?!{X5J}02Z9M|
zJlP9F9E}F(gAYxWKT|UoVXCkV9P^h}iEOeL4})9se!Q=xS_iA?M8iIIZMG7l4c=$G
zOFnI8YSu4#hc*YF&7byzOofdagB(tzx(le^{cU#G+V0RAsN5#_D~Z*sa4E-CyrPq?
z#|g9(QOg&)B9O5ahZ2YYj?Q(eEXRiTCIsG0&HmbXd#3qras1{DAX9Ov<{^fuf8wc>
zjKau{Z4OLpp(n%EoSEBM%!kZzc#oJzbI=W0pblLLz0o|`&CMXwq*zBJbjWSK!3y3Z
z=t{YEsOYyCXFr)0%$zK-P^9)m$zC4PIo;y61s(M%_4wtu{u;@aa^N>?KOZd-M7Op$
zlT!BDv}ZSMTyUOQhwjgJNU`yg?sstp>30M1MVnuqxm`QxIK7xUTaif0E}}A0=TM1o
zbzi~T@dMgLP=4!DvKVz=0v1Wd<{R}(G;Seu=Sd;8KjG<Flc?CCnqj+idnkj=SjmC`
z3ln=2Nyy`URFoSq%Q`czk@73SqH>UDjt{Dw3PVbFib2Y$r^C!#(67(P@jJ=<-A);i
z_{{6O1{!twP7f5~Vbt+Ap{g>3Mr~m0!Wa7Dm-jLH7MAeEeDMmj80PnYc!B}AFQp#<
zb0&KaaDfkZ&V-G?C6qW%&G+2-?h<qS2{oYxY@2F&5vD&z25p*yAfbjGhaZ#*_~{u;
zJi3$lR%Pp_W{B&^%5ZclOG<wS8Gn-9Z;I0PtNh(d{=ue#nN{4oa-Ag&p?*`uizp+9
z`_e45KrWl7{`mww;N>hr`^__S=RCmvYPUN7Qv^MvPY8S^QElZZyq^0ajYp`F&MzG1
zp=m0jpKMY27BBM{VuJ5N;s_R69my#Mf>bT=9&T9chDQ_&T2vXr7${Mz^I26vO6wXc
zQl7>FlOdN<TrLL{QtzH9cZJDff@N(2YG>Ee?RSLxJ|2Arf;_3YW1-4&0Ci~LC|_Ww
zSj=}sbl_luO%@doEb@OdUmk0ivb`n1cq?D$yeV{|wX#!RthN{9^|Xz4*5jZ<x2%O&
z{8aSla0hZKC~jN@xKHbB%A{y$FQ+^sar7FI<E)&=6|*>Jb5C+Y{^-E+dUr^d*+KrF
z0Z&?Cj9~3^wl>ma;;;AWE({-?W~|2S2G=$tKe9ObC#VQj&?!H_$-er3Umo#R%UfXt
zok^dNS|O>xb0eyiw!Zt0u`=x=qt-P?<`na(P~jR|Q;^udCC=R{*iX4qT<4X~uWhU8
z!}zGVZ|5_{l!U%Z4K!Dvn+*#bjTXZ3o{%hkv;F>^!79iT|DS%g*$1U0W{%FWex<s;
zk2RZEv5M%jwww2HvUoQNA5|*>{DM^zS6+*b$DJ;Df5R!=uX741#Xa|3Y38Jg@t8}x
z;&HT*OIq&6dI4v4AE~tdoKkTitJkQPR*ukI(w+&5EZk-0elEhSK11l5L1T1zX@oMo
z*W}}n+3NsZT<epJn%iU3&MHlFLVT?<UoD@~!GgW-z-tPLbme@f-1RD=)fKo6Y_Jpo
zl2(V-ck6U{Sc;10h!OV<tK7sgM*2@|fd{jDM7l}6Du4Pby{p=EnyG1e?^wO!fkG)L
z8}mI!Q8*=L#R|Wr6d0t>bMX0-yc{k6=I$KH(G014?Vj~4@@&ivx%5+_icBdbmaY4U
zIu|=IZne6#4PAx^|M;1QYs?OBQt0XLI+P;ueI$TAR1_M1B^I~Pe5qfGH3+AC$>w5$
zH<c_Mna7}ox2w=^*>jVjCg&~Z<4@Ty&~9#nNO{OHrl9EJDJ1&n3+c_;H?JRz#zeSH
zg%8zfxcW-gn%|!^4qvjy-~6=v`+2bWAHSfw3%TK=LF3n&g@55d`^w&!!^`8Y`GFHZ
z6#IlxVdkKYjp>U{tcx!25|(EM${3fYKm*#=NOwedu8p8D3GXr5uoBaQ^u4D~se5_L
z6Nz*e)b^W0XC4qG#nw+w3%y`a_!-V7>8635n9ScW4%6;wx~04XX;(C=x{}crP|u+%
z$GdH^=zpR=)x$RtOi0QTuR-x5Mj$qU(QH_&X7RPtvrRk0<!^IMTns0r4||^UHRibz
zl(?zW!%`k&$K$V70p`5lvKI0_h-*FWbCSq$_QfSQOb0tsO%&ed40Q8CDOrzSY{|(W
zm-F#!sB@I=zvyja(&e3eeZ^BAUr?#--Z}eb>A;s>6l#*qCA3(7LsTl~ya`{rE}8Vk
z;Ep=+&Q}(01mWgk|J5`(wj^|xtG|D0Hxx&Ub{xj1sA!M;4<uZ|d}mpi*Zp*>O-`vx
zNJTYP^vpoLXiQxWT3buo&vNl6NtsBeqrTKF;N~+|i>e~6!vbJ|DWNyz=O3=4W~#}0
z`D7RQ>dGA!HOeeJ^^ry-vGneEUpapFkLI0qY+Q>YO4V+~?E_LONLD8OxA2ppB<!$6
zq+f)Z6h}O~Rk<*&K3Lk$BowozE>!s;298XEfr_60@lt(;)dO{>ziztgHeLj#=ZR!=
zK=+0Acp~>c3826Gae_}*4+nD|0_^NOQHGHwN$sw;=53T;0ElzrLKuVR<cMa6CXGn*
z0%T|8o-BJ)=6AGR`3+hS5O1;TgcQY4*dwvH9y$y|Yi?K1&DAHukF_|!A2k7hk#!9y
zyH*5cmkTghyl1SWu5_oIv@@WeWTZ6z165{znpkF5pjm$#8U42b?EM!cMV(O4q@7?X
zo$ICvKg7%AI^qbKOB*Z+8B!zzg7oT~!KdqW9L>cAPo93MyM@{HdwIk_Bz+2uVcKbR
zL)6R8oH4QLqijxzaZs*W_Escy=zgYN^}K0H?{L^UN6cj5m$cFEppPcc(rGF6E8kaN
z)f8Wn7)-In3zueF=x;UsINeyJyjrIsuWy$WI;JG9;crvp#vzqR>3;{EQ^NXYTd8A5
zTIK<r0or3%{{4?;2duzS$P;e=P+_$M;<&8jbE;M3G26(h7TgB-P_Zirc@@taIt}N+
zk-&3h%M6KlcV{bND7{O9yN2{EEz(VChC3DK$Pm2^L47PzoI$?@l4K*2GsHxK5o%G|
z&;CN!uWfgKQJKu!{pmVAQTjip=KaP3bXy_#o71oT;u^92eu*I*6--N<eN#ey*qV;p
z(l?E?Ouu}q>KDP!Z7n%`=CaR=|9WGjXZH8Q3)^-LM>ys(u3~wNaRsxl!UTvm4MT<p
z;bmG@HOzsBaW|09*J`>5maqSTT*s~sB}9#Nv#o(Zh=Qv73!n{`Og9MHx0<oc;yct-
zl?zx2(KMB#(vFoxIQ<Ms;J(w|3G1+1bAmKch~0DPbqz9jPGLBgos&H<nQqua&^r--
z_Z1==4$Pcp!<@jaQ{-KRM*5eLvslTJ5go3JPfB#Ya!H43#1rY%b3gxLRHmZlW%dY-
zbEKO~*aaV9m46*^eNWOiZ+T!#7PuAi<SpB;zuv2DdX`rw5BqCyldv54og46PB7de-
znXK^U;``AG=ULnn{znD>a{Q=&a|Zq}To(iZXk26aa<V&v<!*YAmKQLt;vNN8u!!fm
zQbFnQvkLBgLbLY70U+VOpn!it&4suJlOE@iA9VlHY`Q!1OT-XH&YIvaxcrH`Ke03D
zJKVak_7cmH%Lw>;?h1UZv(Bb1t;kKK8CI;667+;cO*qBj$Mo{eB_0!ZrEuo5wa>7~
zK^j!*h(PUA9<{$iCMM5MYA|Ph_wkh8Na3CwyTi*tv95jOi#!Jj$#t~S$pT<Bd!3!G
zz>eNZh>N00{e6-1fP5w#IXB2wNdhsp%M<&7n2hC{^VE~HM&sH^FXqJsc6OG@^x0nY
z(Jswiv7<DvjI6w`Mk*xDckv{g+%;kK%ZKVx46m$v7eW-e!wSa}IuC%CpXYeRKt>je
z$C2JduYQy0E9;p%y-|As)fc}$?H|1hm7&7#5A}@9uF%9aHj$<#_C`1Sd}bBN#)P(S
zzfR?UCjaRfyiJC%@ht-`4~i{wEiduT!Bv|Fxx!hbHEFoX-Gfe0<`wc;KiIvb1Qltu
zze3b*OaII}Kh6-XQH%0Ew5|E;R-899W!xTg0YXUKTd_XZwB!=>g1-Xg60GVpbXIR4
zBcq;bcA0lbT1l0FP)y~E#8xN6Op2w;XOj>8QCUbWju)4{m-+NgD2gp}^r;LXj|+fY
zSP7yG?>RxFUw0Y#TzOF49vj*Kz39h6kdvJJh}tMFqcD7}OAPDTTS!s_Lt9M<bIBJN
z<D8p`-KB?>d#)@j3P|USxrLxAJkHIM06IzWK(-a)2E$IK2!w`Z9JHG8f0F)Tdj`qh
zGh81X$8D(||HZtJdi;5kXl|!0b8vd8>gUd$#tZ=?sbIRRxX}qu-GKt=Q=}(toT|+!
zF!TTL^0!R)orjT}>Z9|<VHv5<<Ix$~*E~s5SQA}5QInl~uIRw^oH^g3g5mJ{iVSeh
zu$giFr(14VtxQoxUlA>8VBt)LvQJAqwl<FY|DkK7`Dw)I9`TFPMqO8J-TaM`Oli+_
zSJQ6?%ob%BPnC%`JChMNC%+EQCec1Az<yJ={?4gvFO@j6m_$oW2n6-kvzm(k^(9yS
zgUzgc{;63C2|eCrZr<bw*p^V@L{O#iF2p3GCi~hJH_3RPq-`^X%pL(iDL&oiN0Ql(
zqw&`%GVcAO91NAoMvC2z`$0OU^p|ng&6<A-)Ty<^nze8BL#*h)!np(DNBK^|(_pD{
ziutW!0g71iOSCytyPk~_!e=;Oq(H^7eu5#t<&)_8R&mxVX3*PC^8%2lUCN%T%RlH+
zfdi3L`yvyJ0TMN*W=}2Ojz*=xSp4+h=#8~_azKi(tK8S{3u=~(a{3t>yV?<EY}~<z
zg^d8oh|`U#z$VRl9g_tx4CM1T7L~g1P=C{v%`b`F4(xS{`w@x1GDaQqX%3K^D9tr-
zEnMzaS4+0K=MlyEBHod+)Nis)TT1#D2hokpfH-Hk%PPADSE@$&5q2Shfg4`%%A|!3
z{Q^#y%&6XirZvwa3>vlolF$jJ(kQ=g`}E8nu~jj0(*HZTsMp@{1y)ucC+-kD#xp3R
zX<e~JPnuojPj=%~jB%FwOnDt_cJHjup5hgiR8UyJS^83=5vKK*<CXFrLCr^mTOr@o
z3r&h88k4fVeHxz!lm~__pbMcEs(QD++$}}vq7HdC{9FxZ84gqfGrp?ktDgkYm*1Z!
z_`OA&O-OMmR@Xf1IQKuhDTGBUbMScpySjkC5Kzr-4M?z<|1SF!*f!Ud%QAWA1_!wG
zE2gv(JGJBwB2Sg=U6&Zcl!lp<7~Sn6bqjYw;OpA}`bCB3LX;K^C76B@zb6frdqgMQ
zlbJsCm7)h|C6fD?#aWoYeoymx9xEa)Dt3FWvcxuCmtFgGhVgTPq>@F9g3T?C#tPR^
z!GJqUlJq5)`EE&%kw~TYg!xIr!0qD?%GYd^v6a7NI4wcfIgbHfRg;q{0kDIS$vuAj
zA1KX&P~vXVtzyZ!=RGoAw|vjBkLcrlGbPSPmlr@%=5v^>NYn5&_rstD(1ef;2RR73
zScqwQ$H6K9NW#Z)yR!`}-E4Doj;83En}B{*xN$qz<f=RW<Fs*k43w(y_0i%x@Y!!5
zri!#&L-Kbrj4ONAs|k8~Mu48^`Y<^t0YuzS1UEW*iJ0Hq#cCEC=~|Rfoc~|%q1RO_
z^q6eKe>pTkYr)rlH-k+l=^VN)L(f-WD($luL3dwDJvu1nq<wzb|B(@Qhx$K|rc33y
z0qY40dN;I27U+@w4tH=g*D7LS!^LTmTbijJfo~HJNJjiqz@+RtWtf8B7fcO><Cw2O
zZ;0PbcYt_W=XR^DZRiHs^=MM7O?a)eMEvixro#_4vx12~FqhLIzPZl3(}cua<m)hZ
zN}IGLCnRN}4y{F^znK2b_9bkw`{1Hz`kFv(s-Ys$h?E>}dFk8dO$pofLL5tGgi(V}
zSwYls;zTB6GZoLj0;+tqL+Z1lV1f#5@dLr^RCSx}P5`0z@RX#!mLL6?qnb^u5bm_u
z<xy~igf*Ah=p|!@`A$TEWXI*CFXN{OT{Q)-DL%4ARGTLxw$wiM+Ve!Z!F6e`6uv$v
z5EG*tG+)-JTptU2Z5Q&sN+|Qbv6R4HSGpwxolkc~dDS*`hyMj^+J*6#xtq^yAFUeW
zQhb9n<9Jm^&_qSwyN26h7Z1)Ud%>tzMU#Mc^zG^UJ>&D|7jOm2M=`P$&yJc$CPFZr
zT^5suF$=}g1BGbGKm0B<&<f5b0P)8UB_5|U+_~Ns>moW#w1*xr{5=l}YJsjB47amw
zI>~2sCKoag*Cc5<lIFp1nbq;Y{+O@VyDFZ_-#P=@VdCT8>$Uy^o!<1tb%{Yft3Q=^
z)8BT|2XF&wDyRgnid@_$;MOx_K<Lj36BiUJ|LQYiL>s-lS1zxcqvopG<5bnLU$>Qt
z@TH;*DH6BuNX&(OPS?2ZmMSZp)LypoJw=EWAIb>`s3jwP@wONCIF}$I<d58N7TPF>
zezI}3Nj*MmnddF0edm!WcQMn?=&-MWi;s0Tn?!e93*$%f!M7d~?<U3d?8=u^JeX2%
zCX1^sIemp?rA`%kdRbF7Q%n;KKQHCD8C568x~GhVUX-#l2>xLY=$Nk1=+#jTiX7Qh
z=x(_Rr#LdS8p$ylcG5XC46j~?`uY@8J30L$<U+_s#mw(N$@GiLL&c2a`b_W+ViwcM
zD!5Gd5`nC_(96<&tMY2Lf3k-f*gumQc!vR+K-Lj2ZG+CDQ}+dH(!pGb)%U~y8x;%m
z#d&jINDj-OL&m=aLZ$uM?`KwYC_c>Ft4TZjez(&=yzBSqwu&-QtpAm-OMvxaCdQ5+
zf@ND|_IJNTh)MfK_C@3UuKu(2pqw2kqRWyD*?K&ZKsNx}Jyzcj7TUMM9OyPbvaDmf
zp3B<0wpVY}Lf?fx#bUYMpe`(?U^7QX>8G~*+k&qG2q2XYj6Jp91|XUL12w9P4*pc^
z;!dR4O;WDC@za#OU>?Wh_2y-gO4pm<13+GrG*!HX&l9jZMU&*vGs@WFo#?TUD?-0~
z@j?Xot;M~!E;*yIs{WrjLH@&FTk+xa;Gphz(xoryuQEg3=LEFxjqM1&9-5q5-vUF{
zc+j+^cB{lQEG3Dzr3X_++k$RH<obgL^?`Sk1;EfI&QjVKSGt~9zRFwz1X+ODf!|F6
zl)q`FFM4HFOEFvBfYfhVh?9Y0w;YM7e2EJ_ByqZ-md65rdw=|K!zMcAYc}9X$ZE;H
zIg#OVkoaM?rB(ZDv+6n|U*IZx{z=uH2Fn#8=lHL(?~kJP2_=GY%6wdx${jXMzqrT=
z>Mij&=028mI>HC(Co%?>^e=C!(|dO?4=oDAd@NIKA~9A}3`RFGnbBzjupRQ_11F1!
z;o??=8VX*`x4|x)BXb9=eLDO#G;)Eki&o*9_M{Ta(r(Ec`;Bev3xYjCEM#@{E5C?&
zqfFs{pdN{!;Z}83w@WCt^~;U>f#_msqSQ^!o9&)c5KbEh(?!{883Zb|zP(sd)Z6l)
z^QR(gkMBnD@LQ;GK_Z#lY!3H(Y!9lHp&V$w!`N)omBEmq(1nh7*k9EYtH;y(&4eFL
zuu;uV%sH=@fhkNs%JaEXq4n>>&de!s!jSVEyiR+(d|$Y;H0sxGcp)sJH(}*A7eF~e
z0(<&DXEB-)A=L$Myo?zpvNG|M2_mS1Ztq2OLw(`#?o0ieH`=cBE`j2qej5Jn-#D&1
zzdWRtL})dTWvp)gn-{hOLar;0;=VZ6rXr52aARd$r|R98pO-xYUdC$To1X>xlQTVf
zq7)|~)v~72ir2FMfuO<S%&s=mbKz$iF>nxm4*i_%JiZ2a7^}_zS?wDXZ6*YMk+OXP
zc*=!kOnKFpRpg&ypTJ**p)%6RzHZMMqa^|1%oeAyQ3pv#0k!TZ0ub9hyuwV_sNqQw
z_&*SkR0?=`3$O>((n*_2s(Xw%CY}@DMaMx-ICo!EN1quDG+zQsbCwwF#MEPG^L<_g
z!}Ceryz>`navkB_B)Uq|)?T;}g(E}4Q2^nxre@086!@Ga+2vt#;wL)!s?n!<v-gVQ
z7Q*XG^)_`=jo7_a@V;JW@7n8Gkw;xBxa&c~Yr^}ltH$H!9M-|RAn;XWN%*(&%K$9Q
zL%T7dtkDB_Spbb%VQR(i*VoG;=ov6zspc&u7!D%4C!VlT0Ft3DbuaLM;6=ids^QXj
zDEKr-K0|ThE%=n5Xl8S;urt&v<cEIp-O-C=Te5*e{fv8z9a8?Q|K5A)ZGZ!!7|Lc&
z)}py&e*_D%!a@cm#U2L&24pAjcBkEOuCc(@&Gv*4QSNSWf!WPDb`h5W;J{oaR+9eI
zoGb~IAI}p@!5C&A3yIa6lDoP*mO8u0Q#-j=2WALF*>}5Y+$<=_>lU<f_nwayH-sFz
zzN-Sn9S+R*288$}XJ7A{O1=)#+3{Eq$a&N`yxPEiJNtWkt1vC_brDYJ(|I=`pn~~g
ziBGE)5SnO<wuwmaE>~|F)eDOnCnJpyGE*dd40&8n+qD@<2heE?(LuqFXCK`iK)U9|
zx$U82(I5#WJ!*Qs`ZohZu%$os5&GkJWEa9v{ap<vRuttX_aER1u{Ug2u$km$A1PLm
zVVQE&msJ;Sk|h86Q<|+w9&s=zm=&U+&Jn5AbRU}U2(M9-X5lFO#(Y;mjg!}xo5p3A
z7{nQ)3ti=C)kb%)C+s7z0M_aAy4!4FQYdCYS1Hov^vq68`Qqm<cfbm=7NpLJEpStJ
z^3iurw=nNX@H#Y8I~-TOJ5|M0RJ5$C*oy^z-bk6NEPLf)4^+H3;D1F~$EF0=S`V4_
zqZ~!jdt(|}b1&vKMZ^dH>C1cfj5oy}=>;rPgd{mWy3l9<&$Ykjl;FWdTy<f*EdB1^
zh(*yZpA-ikQ-g19$gkE?`QlAnQrC7BC5tESPGwQ|Mt<jO=H2ixP8Z6{a~5-Z3nmVa
z;SKqd|JyIv(S%s*Q1#RIX3lv<m8ol=G}EuBq??D|Q3tWZyGp`<t{M>e8uXe;dFkF1
zyn9*6IeK{&*jSv0nPZTjLYjWS>Mb9{Iw9`EGO)M#PEYmSefG(Kf^_Ud^T5ee8OzY#
z;cfP5ZXjQf=15tibUk1AakNL-;2nVemb|fC&z)jtTLvI<$`8SWzs2{)ZGgGdw3_sj
znCxtwgbqdjiHM%{n})X;(_8sWG!ZVt#Y0CTx;S~iuB@M2|LxpBP4|c!?iT|WOBZk$
zzvv7-TULgz$fW|aZXTs!cMmM)RgCVcDfzY+`iLop^Z)#<8z<1Bui!C{9E681=<?6{
z#GnRt@MK4FkpqJ%g7eqB9K9FFzPXYA599=RE{l{;N@2SwEEZ+Z+smbNJl1uXTVgcQ
ztAeu##$2mlKPX|cSD#~nrd3c=m5+$)M-D}tYu`BjNjp^Jj~n*1<YDe=J?$B)=>8m1
zwMBgfoM6hHz!I`y>~6u^dm%dT&L7RfIe-e-`!~oiIopdh-3vxTYwWIs4v!9t;4R2e
zy5<g%@->Rz_t)W7_%7YW>!uC-XSSFMtjo2nsgDM7(C#)w#xU8zfE_o5`wxsd(<@qM
z#`q!78gfydl4S4=*&?$t>~<@A<Ab`Fqt=2snkG8O(Uz#+m(SgzX20?gGv{+&3dPby
zQrqD0M4`U{-JJcz55djgj!qLD+Sy}1r$O_&5^TfU2IE@ax(9bz;pM7QcM2`5as&-F
z!0#@Hul-)%RkrS$YfV5mejqEf3tBD(9%uxB6SXTT-qTn<-CO^EwyROrBUKS(6_p&D
zh*5&2dNn0Ohn1+R7u$YR<l;U7$p$zVh>EDF`46O*w^x6_Y9-y;hdrXW`IMQspR@i5
zx*|mLy~0X@oZ?W~dTMzL*1h#3IBl?^iOH2<v<lK`0JMH*XCR=|0&Y9)N0%wc;hT#h
z2AEUoW)dBS(~wtmcHgPH4R0AY6EbY1+2sdxgZ}e;BknjC50ee;3lMj2nKnjgnC=vF
zXkMJ3P)?2W)nqq04TEQmGBO*s0ZaerC9dGr`Arl^_NPh0xw+WAt<ysT$BZky=0$ZF
z{ekQCcNeRuXf*Y@+kYSp22E%9Ky(QIsJj3r=LXoQBmr4(N!d+xd~LeWY9f+h*k@>K
z--Kok=d-2ko?vdcr7^|u>fI6WNTRxGJWt5(WcDYX=^I`U>A%9JCQ9uhWot(61B0bv
zX>j2OvHX?KTeX)HIZ0!GQiD4Qumn+G>(!++0v7-~%dEKV;OiKFdfo@I1-5om`k=UB
z*_xA+Zb43@jJXg91@YSF3gXcare}JM;=^1j^z`kLMT~9?(lJV3Dw9R9$%Z3N>`NQd
z$(GKOs!V(0`&T!&hZXN_aYwUdl^CcDFaJ51{kfWW!u(mTE1>b!1Et&zHzwm8p%N>p
zOs=6P=a=~d4h-2sownvo-^(i$kCxb49juzh>$5KPAF_Uu^4+Sftm4_oxSsNWmJGmE
z;<-qyRKLnI=wJV)9Jx_})clzXdaIG7Kc*EpTKww%xvPS{lZOh)nK4<38E05D*;)oG
zKacN$@PvH7@E^27^wWcu;*m&hEo&pPUv|-J#w@^Kgd4uXnnpwRHAHUc!-5XHM^%7U
zl?k@ja{3JV>%+=_pxU3IYr^v(mO#!KHHFwI<Ls&<j&xh8;F`L&pD6_9kq#`6P>Q6(
zLccGO=Hq$)uS`#8*42_`KKus?qsDzNsZ=I_<9WZ`!Q~*nA3XS>v?$kKf9jIk1`P?>
z*L1Sd=ZIGGCp&wI)2nm(5V}6gfI%tEx63b4X;vs<$||fjYvQwe@|@)RNEOjidD6+@
z8hny(*;XwPOYu#SO@W(1-}~j9@8$BYz1Q~}Guryjh?9YP5r-1TVd#`N*dpE^6@;v!
z7@m@9E?(25Xy!6@X~r!?zi2ncbtE$(w4|SNZtRy^tVMVzT`86-GTmo80$TYVpsD0>
z{SPEtuTz;_@$`J5E`S(_6*Zr^zF}S#BdF7XTbaHfm|LFTD$zicE9YUj<6w40vXkym
z;I0?}eBHrh2k(KQIwIxj`CvbLI?bujME)IKRPv6`tXS7Sm^zzp(CIYTc@C!NZY%S~
z^MND0KsjxjrGzZPDI7Y!IFjq{e`CL@5wz6bmWdh(_ei|{*E?FX79C^h8}vJ*a|K~J
z$v^7ZxB8qt3w=|Z+H318;)J-474<cnwz&^-zPD{ArKe7!yRGzNe0^DB^WulYua<Yx
zTQwQI!uI^v&hKak_UbGO?56m-{t~|{G>T`lIIhs5hVv10sZGI9cGFJio(M+8xmJ?0
zV#0@ykM)mOP#+Q3oo36j%AbrCautKrzaNR9M0RR|rFC}%((A5x_`EkgnZ9`C{K|`a
zkMi-z)P494t(bKEM!w3c2y$nHxMbUHEa$stTM0ZSvRZ~rrOIL-e&KVIvrZsd6qY6i
zqBOUDV9E-q9vE|upds9IgiU`+Zgl&vzC;|o3JA-2^slaPfQU#-8JP8@N8Y4#3scW~
z!|*lc;$o0YhD@7wy}(njJ*Wdq42c!LXTf_Ua0550#BzKA-&|WEEU-eB>K@7j4=Dj}
zaGp82o!j=Ni9eSXsFPLqbBgtbjU;gL6*2fp**U{Xe32Ii_r<>0y>ksjKQ-sIQ@#tV
z-jIMXXgB$=nwhj9m9n?OlzI&*eF?pPZgA7{zH5V%p>M^r4yY2_lpiT}m0VCWlOdsh
z!ly1%n4hO{EUH7XPecH8XYV`#r0XPcAtVe{Aic^NjGXj}@1^eckMS)2S5(3Oz&IW@
z4V@~7Mjp+Iq86G8QQB}9^O{?3I5GGn=V8NiqzU)}UMQOXR#Fb>At!S|TlT8lUOv0}
z>A_3-%36(}zPwTT2XfF=Hpz_@?_JH=H4dxu7~QynibU^SKnBGzFDd8$zIen%Mb_0=
zJ;3D&Ieg9n!%3q#&G7t4BLJlEN^^}kMu~PERUq_nn%#T_+fw)-d)B{>S9;3-e8kB7
zz)6$VAxDvmL*2LX&2Pb7jksy!1ex;_n3BId6Xey3z*W|dA-zVXXWwm>Jv_GX5XqiU
zqewfWBX<{Jgd^Y>`?OEk2CpZ?*x~;RcaX46wWR32+$!ma%~Kqz|ExqjsWJZV@LBt`
zaT|q^&U=?=hd;fYvV{)??SgBhErVe%=?&RjGM@$LozEy{mWLta&-E<|1hbq~LPr6L
zbXsV*D_IUCPbEZ_N5uT9B;pNQc$*~|z|wodyzqD94h4*f575Mc<J&tEc^ath-|kXF
zpE5A9kM<!E3kfn~PVdU+L-x;gake#4G&g4f@pgf+Vg#f_{wcfa^a{Z;W*<7y#n>U#
z+uj9h(rh8nOQ%=P^a|45=du}ZW8c2!So2Vx5|?wWD@HnQr8z+?SJOQ?8qLy3-(O6b
z#M#ocT013XbP)oh5K1@Jrw0>Lh_~kL-FP$Upo9iS2r1kBv=G@<O7<M%UkRro_H;fU
z@Vc_|g-no%#|-f(3u(<KGIFbI6)T67wyudT%()H&hQ+@G7>KHK?ak?s=Zasyw8dqs
zlB4|A2)*v-xLR>ZHcEu;8BAU*r`@W+ag@_H<M<o%vldA079Nr~4N+VfT#4bP&rKY_
z*N2-gh1m9|+WZ>W_5`&_f~Ier-rf;{-1mJ{kQlnu9TK*EnvGMZY*#MXHIkNjYqvX;
zd7pa%y6uVIz+2!gtc9mh5;XId9qcJOjHfj*>m5e;c;`uapo05hgA>^b$;+uKMFC5<
ze;zV~pQdO*<mg~dva2Cp+*XW|5%4OY){fTs66ao+Z0`>^5r%4j!lYJ#C7#x+R+;w~
z3}!cES6(fami1@@v8w|sGjKID?o>YN;8bh<h2BM618MJ7GE`x4)z;cuAD(`GduY_?
zZJ((jA}o>BpoHb%?)&yZ5H*)a?%>36mqUX{JAWIqXC}JfL?`Jf6c$i;^iA1W8GEhL
z@zKtUEBD8HS9{F^FZQM%eCGwO{Qu&Ir}mwp;-3C&zr}uNelT=@rMUez9uQ615IlP}
zsd?b=_uSq4?x`9+wp+a!ZM4pmIVvgUn77?}3+K{2kVupl`X}82fq(d?C_UjyR+1wh
z7iy_UvU=xI#0XaZ>gue_fhmo-ahf^z?cLQdC+P)49V|70DLatxywbJrLv~$~{Soy}
zEI|%oqB|0CsI;8*TC;R3(^G<F{G*nrXpXf5Q{2PA4dhfp_8YK|h4T$SznYmdXV^Bd
zSZKgg9ZOBgw1#`DX|X<R9!t7W%DGhs)`F_P)Di%ntFG1R4)#0--BS2%bTpnx(*IN1
zV@yRs4zv{<SvXi>SKu2=E=2=5_sJO$?C?06e7Z-^vSYR2A6O5Xm@c<+<{5+@S>5So
z^if!`PRRfRcA&uBNvK%}mHMS(ez^E7J8|ASAaWOneA+;><&zS6opQDEcljIdgu3fr
z!=n3Bgz)vT5p;>nse0|k^Dk+@23m_>nx*|25f#BA;zn1ap?DA|Pb9C9teJtD*)1Qo
zrwbsySq8eb$Omqp-DE%$UOHVog|z;BM$)JXG4ReULFc2~b_F;PhHWc)nJ>-KK?wJt
zwfHAubEhTHw_o%{b5OQKGS+W0(o*06uw-pjBRA@|=L<ybTNi#<x=T@U;_z3W5@)+>
zea`fR!CC^kKj+dcu|T_J0ObN4<8PPINBr<ju$R<J++Qb0Wz0Coy}*su!{ZzL6qYjZ
zNDBHx=PXc(EfCdAca`gjaf%q0{C*9=AI4d2`{wvVhU-5N`3RtmT4L~>REz3%B@*($
zQ=I&vET}9c?XNi6ATlRC9e&BJ&MZOI5)Kjdy}2$Qx;Z?`;B&`aw?*1le9V8|IMtjq
z90VXDR8T~=p+{AW*E)2;fl`IvY3bO5wt*~iv#;csg94fL@4j~i_XBjg_N`oZ6_!J*
zZK_2QM?Mt)K)W)()jLB7?<))7`-KWZNxicRZyc36?PYU!$6{k$w`Ush73V&sM_}9t
ziZ~#ZxR@fj7~J^JkFi@GDne4vY#!yr&2vUO6d-Qx-HvS0!cl+ZRa;;_o`u9dS4(Mm
zOsY?3{QR)V%ZF&mmG_6&ucBPV2@~;-kq_|3zd3udYmif@B|ukSgn86XGrRTk`+gt6
zMQvTIW!|O4(c*vA9M$sr!OMcpD>+C8Ay1!=fu9$1FmgtiO&9`M$|nACK#>%vWLfTQ
z)P*_Y|G#oA9k=M?|2Vqpu%`aEJzCnJYZ6j|fOHN-LIg&GgrIb{(t|Hb!$4AMbf?lt
zC@~Pp(J9>xBgW=?e(%3ryLKIRKJh&Fb4LlaCW{^bZ^kSABqwKQxf@hNCsgfyD7klG
znvQ$;QF_4&xkzU1m-g<;Wh3a8hlV1$#y6VTZ5lAdK$-8`dL-;odq|bmMhg`|p5zmB
z{dSU^24K@zJC|ILK8_}ovZ-#-fB0fUXZ}Og9Eb8@a*V=4RoacKs`o6Ju0lKS*0Rdg
zJdw^lv0$Z{t*>3jZ2>#YMWOb1u=e(9$=@@JXA`{WZn1OQTIt{aksfJF<&ly^Z2Vk$
z-nu_1UD6yG{SWj;&MJUyGQPw)VfLKXxD)VZ^EGl2@4n(1V~<q)+_hOYBGRWIPq#=%
ztcxtA`Ql)VWIvV+pg>VaZplIygoA-gdbnuzv#qEnQsLqf<x>?jk%l`NRt%DOZMB#i
z2saJ5HeE#IdId)UCXn+E{0u-qjd`Q0^%w`_Z1lXGB*JG3Bv!P(k_khzeeoZJoN#LN
zaL{Km;Tx`x7L%6mKIPt7qd>M?0JlxOSmJX<&bno_%Y4@hhX~?6-AP?5I{A>_+&5M(
z2{~ca&K8ExkOTNhy8~4nxBP!a`$et|qb@Bt7T@zd;#p3OaBQqkbYE)i0F`kkY(3%G
zoR>B5+)q1Gm^FEHGx_W9$cj($MW5`w0fc^gb7BFv8RMp3SwwA_<X!#aTj6~RIU_fq
zbsaWSsMN6-7SDWGN37%Dy{i(st%9!S|F3SK^|--Pw{^y5gq<re+i+LzmG>j?h2}YS
zku2)EVzt%G=&>GtQmp0n16L#iFiosgoAv#sc1+56$x#izZ}}Vc(GEK1oA2vt5ROZz
zggX(wXydL0nj~}o-Lrq7%U#$i)09ONke_%dE<GjwbK)U#jEb*dyO(0_hB(kwtozZg
zW+!Cu948Aa5<U$8E0PRLA9{1|0Q^S0YxQyRwg28dIfD@GHsh;w%})SosN+bHBga+Y
z--48u%DdKH2wC@R><FBsbgZbqsbvU;RrBu#0451TlQxLAe2e5-t3yQ6=UEEJKg;!1
zCsLBdes(dHEQ8a(%v8nil)|^w#kh66Ly+>(!%siQ0tvnIOe~R5^R1KxhgQNHo7>D`
zTwfduwn(T3$RO6LL3OTkvX-?lkzj}wY#b6`9onvHis29e<*`ud3T15+1LbHEDy;}Z
zl>pf+<E$YaC|Lb%!S;B9<aZXdP7}r48{l@FstSEf%Xw>nzo1M(Y)yE6wfn-s$t#8d
z24oA9KP-)M8Dxm6A9eFo_A8m?!++=zpwILVqypwO<f$d|Ru>m!*Z34|lKhiE%v^w^
z?<>1?(?)#HM;f6RF7MRvlRlC+-}EFF)QvF<p1KOH4mE0X8CJgdndHoy4Jlr9eDst4
zTCdPKJY2!KP;H&*&rNwK5#9H?-gi!F7qnJ%UNDaq@#3Vfao=`pJOmNB&+o6*U=yYa
zDFh8$E(Xipp0qYY+8f>kr`E@W?iueDVZ-#ZpII{Am7CZIybCXml=moqjjiK&Pq(ZI
zobwKrUB3m4IXjQ|er@ZFC=A5NtI*+#RQgvbo4jt8%lV-*^GE&cfE*(zWw967wLbq`
zz6<LUab-e)lh3;)0c^Ceov;j6k#v;2mKwS>!Lu0ASE1`&*(wzyu5cmNHggiC9PqJ(
zJ^G`^4S_b}1$W}&@<Wjl7N3zL{uj67T<_U03voOdTMm&;^GaS|h;BdRyAF`Uyzf~d
z1h!JXMm0G<fz7BPig}x-86+@8Y&|sH&Vv=wwwQ<T7YzD%Q!_Y=e74O!CC5tQ!7lKN
zR+@3^%H)xv(16c06fbV)0CNLjfZb={A23L8CE|;_B!Es{<=p0hPuO5Na<ePcH&IDP
zo{FTKdz=0yB(=j@Knm1*$zLLSq8iimpJ5vU-UmR?Z42kt<m@)4h2Tbq-Dt(c2oSwL
zqAr$O*t3COL`?#z0Vo8COv)!5ai&ir=XO^*XKNn;ZPlefP_q@RLrdZ|l=DMg>|vN1
zTJsI$R5%5|qRW_GDku33U($rS&$=@cUEcTK`=Q_U{TUi@vFCsiSoN5A3jmr8i-z9?
zGixY+H<w745E-D3^l_HwNX9<X2W6I-erNJ~Rj0f96moN;=1j2%^D=c%sSWhG7B}I!
zN&g+Tu0NQz;!$aD=~k!prCTc7FlS=IEZf)J7c~h#ym~N2o*F$|GOqbnrl;^ba)y#D
zW-f^Ms@wHawm!K-DB<jCAn0D{(Kz(3ekozqTl0lrZg%%k>l3vA=Qq3j$gAI--4hMB
z9O1Y)ZJE1>q*}53iSb!5+7SfAy<8U$pyeHecdFAyw<x8|=Q{7zCBn_gEF0bk-SrgT
zM(u_oaY(pqGhRZ5n-eE@9Ny}Pwx3a@v+q4d40F;f%`VieyUQEuj@gc}GKg;|*&g_S
zyh=j=Y`>7h%F}-!&Asl{oXDY)@Pkssrn;M((z@1s@Gc&x9VG#<&+Cy5s_BPmudiH+
zdFJ?kEm=0drn%h$D4Jit2_!RY3n|jzR;aNAi@^r^dbbMmE?)t7+i+E(h>9pPBuFoP
za@5Q(C9n~npHc~Z*F=pwn)mC>`Tnh^)NZXx)G6b}I(9!Z4(2Q(eHJ;U^IRl22)4zf
z!m}XGIg0jUn=3b!x5(Q3^0;t8oJ+@v2%06}n!B$_w&E~FZZ(U9f24iS-RXXr`03*3
zFqGv{S<gVJ!heNd$iJ-H_V<ly^Wwi~HX|8my{kxpSE26*i>jkP+J@mK=DjlwQJdCj
zlNMe4iZAKS+~j7*0`%l$#+R~E2QLU>GIp=c8*fHyR8(CGDbJlK0rju0)zbzhz})CM
zFN6kRJL!48a(O9k>nbqm9kLRuCts2w%(Me+44+;_LHEHeptkItV3pa79>&qn0N5o{
z`q0FOBS}ra(dGQ~SNi888<Ms|It0d=vq;I!@3S2wufuxmb>vuVI*7HX#HGD{FSmE4
zl71`zfmRY$o&pR}iFBLl*4kN29FywA#WdldFQ-uPQ%eVX+?#~JR55ZayY@yn&m_<8
zL>MXdYav0JofP2XSk2xvo*F7}!{P;{WuH7CW%%wLK9!c8*_cm4=Z;v#Bh9l>6};cX
zED(GST_}jd?Lu2kzlxj8X%9<i=aBi9*>rv}__bR@x+AOW@xXpO`KTWc%`)-Tr}`gA
zFwdTcCBf;w+edqhcvsGA*1lU7N_k_2(rS?QchhD9sGUNVW6*_VdkF&AYOzZuu5(u5
zGlH+t)s8c<T$YstSO<_Kl`!l(OqlQ2)<!m^q|{}3flNNQGe&&$%D+;Tx!^}LPsd{p
zB~g|3gP7dOi5apkfu}7#0~O~BPDNoXfAJ<yM|TbT(rS9PIu|asLZ31EK7>s5L;i{_
zWhM(R?(mnR8s*N*LsDRNZ<E_GufF*`M%B^v%0xmsX%Kc@3@ct;p?yl&j3qO@#9+4Y
zV&46-ffb`Xa!OaPx#4LDQ`Ec$&C#UVWF{Q*d<wXT58=1FF$&0%h$poK*4U~sLWC_(
zav8pCSWNU^rRfuE?4D!exWDWaJiww&#@EHVu82VIss2@M@Br{ULlZgv?TdkTm(0+D
z8jx;`=Z^^k>)&3%8jn=Em9Pn+Lb=Q+A&m)#9Vxr_%U{KMU?riTM(YbxdY!s6+-o`>
zd5LqCZp+4<-thmH>fyUeT@$)qkCREV?+ueznFaTLbAh8B&5UkdF$H}B=$5@QIibvH
z%fPtBW%OESW_lsSj0Y`C$v$}$`X}HGXS0$TI=94<yp$hvlt&y~_-9R)5kgd~ngiMF
zi@wrvQu42oT>1{5N$ZogpU$u!hzn+50_lp6f!iB;z~}%2N=np#$pYR*>G5>*5TQAG
z>GgLLTg<HW3_~6s=OlhmTDSF7y&hi0d8;)zo|LK#I{Zwb+L)-JFXRK`C5;53h+2^G
zHed3r;V8F7m*~3=Z^PpH4{z-kj+kjR9iNAv?>$p<VN!h4+R&ET{N(88Wd%^8eB>c&
z<WQ@D-ClyxGWOe(TmYg`P8{p{1JU#a+1jrHQuisfKHqb1^zSaoky$9*69h)2)kV8`
zn@1ldy#gj`5XHdQ4Ic4yh6Ysf>!%0P_1}O&EsVq$>R}&f)2qCBhwZ9Rj2_K6fh(i+
zr5K38M=8-(aHX0Z*Qa;SSnh)<`A$7-hyuOptu}vQD@7NS@TvBC4D`&$WT00L@v;=#
z{#uWEF8Y5d0s0zx#s@jFM8gn_-k`w)JA6bjh<&PI^G4y%Q0~tFR6;5KMT5Khm$0gy
zahDOuQn7{SPdtH{QyLJeoW=g&Ww6c!%t=#q=YW*8r8MXL_ST$ZTmYFpIvyjj>YO0G
zo(Zx%d^(M3Qd_hx28sw51+#a_dwi7WiWRRJ0@hoAuiJp-AUMeb4OiA9=jxAm7b=67
zvI8GvDq&kzdJ=+FxQ9LAE4u10GQ`7C|3EKjR=({MMc5MHh%{Uq)BATLJE<sDr)9pn
zWJQi@y7dvTi5+S+ySD&Ji9XU|OIm`%*f1<0U2;r6Oh(tkgZpbucb7E?#C|S%3H#;8
z#ZW$5;~wmc!x%+$-*?M|^e6Vm{1{@wnpP~n=>Z%WUI-Oj6cHNJ-8T<!J2m#)z~@g#
zQ%1RTU|2q!^N*s9GKPoetPf`M9GMi&zfP7xmP@VpI^zpT{-n2F674V<M~=CP;>&FN
zzLhbGAQ|R<aeg&QGj6|n-66W)l1XT+1?l+_w2<;qz*Dd4EmLgLh)ig4#cx&~PEewg
zJLHvX;UHl+qFqx(Nis5YF>&J~hp2|z#k){JTl5X3<@v!cTS1u#>^GwRAyQJv5_Dg?
z+dlSC%A?849%akF*VLVu<^nBQG~DV$YRRAZ?Y>wU{*O3&9kA9f+^a%v)NxT2CGc7p
zZNv}0&kMY&ggJFUynceN+;NQ}HR6C91~S|FvWSBnRxZ5OXFNMW-eC}jO{KpqPsdnv
zZGN%>BWVD_g~<qBRG>?qt!0DLF*1eZjyRcV2%MryQZwI-4mQSx+<yeT?cAc_bBoVt
zT}9eYG7G+`AT&+Ekny|pALIvgB{IS1+mh|Ur^Bi~S!rupDp7Z^{;;HYh>q1qOKTu{
zF8KLj7Ktu_e8np<UvFTykzg(v$E&(;j<fdLLOER}6eSul4`B-&iH>}6@))pETlTzB
zq5^hW{m4?R-XYVxJ7aD`cXUAOF^9zi8{Y*V&zWPUE~>0L>WqZB(d(&LKUYEht5?rf
zj7Dj8#d(b*sc7_EK0Kj!bZYtdd%fB8)8doWr4h*dTIKhj9O-(VGlYi5?Ix{1@AxQ!
zFMcsfl&^zxl-#Xmcmh`y-L|V8%oYUyIP=ZR=N8S@v#^_5X%X5j-;Yk<OQ)aVoqcVa
z49_3dO*fph&MuO8*S+pRBT-zLa^tf}GL}iG;a-~!8xR9@gecES$t6@0)TLR&>FvJk
zb98-8Al2kb!~O_B^w$kxftlt#dFX7DC{Uok-<A^Z+a{ox+fqgw^ui2l<3ze2hTMlb
zh))k-%&mFq@(7(>gDzX*Nt*bD>h>vTbO_GGu28<w25y~(3XRlvoVQ`p$$I92g6feq
zIpw)veKPqE-dec+mX&j7LB!DQ1S{Q!$9zEn+<@lzK&t-SDWM0OO=iq6C>CTjR4I-A
z2jb4hA)CBD?mZ9q%jWbaK>W*g@I^JkxR1PGx8hCaVI6F@RD;+E*N0MuAt!;FJOqAF
zEx^)nb{jODnRAgtM1Pge8u-<(gc(ZtOw{8OHSm?cGOAvoSsxfvC?Va2QJNv(PeJ3C
zmoQw1G(3XVV?pX-SlIm9)q_q1;2C6s7=K6+2bJ9vzpkZ54t%}`(9CkMg?R*sZyRtl
zpK5y{A9gA0bSI^kcgjZ$)3lBQrm_3_>1HVCVk6gw1y=A$k_m-to%eB=ZgUi;l*0v5
zdPf*=eb(?D68Z~xnV4Kx9IoM;kvjB2emn&Hm`Mr$fqDuDUIEX!uOHD`_H9$FrnI%7
zhhctk)tfdYt0P&Qd2i+b5A*0tpv%wlgzuI1IHfSPa<QF8`S))?bbx!IUGZ;%$3LcQ
zl8g^j#pOpRUHb?Ro)4!TFVNxzzZy%PX`&%}uT=j0?$19^tPbIsil1oQ=^H4vWkO_@
zR)+sOg|2|<YSMpoFAsXRA=Tn8m(39Izu;6nkA+&{cTu4Ss*wId37G{pw-|Ue1S4u}
z<z04u_z$#~@1yl9>#D61Y~?sh471+{%C1DjR>QNLau(t#hJe5N#bexZIYzq2KuRIr
zqvO5r)Yd$v0`v^?@~cw8hQQo}^`Vheu<46nNdx4|`giA+j{qhDA8~R4a%eFezP6<L
zAE%5a*O%K^a3QKc{XM;)f3D2&uBNM`BB9-1X?fwT%=&9z$Yz_wk@WTr3U6hu%~JMQ
z#`k6y_Pv3(d&zrdYBvc^8T}@l9WC7_H@KQ2haAnP;3JBBhRFLHawh?0_!1e}<AKNk
zUTg-S#rF#kJ^Oj?)8BJf4r}zW(p~^Iz$cu~uV2wW<T!7v1v;cuORA?sOCKyq*51>S
z+Mf>qlrj&`)ZA0_VXIG?^)VgNQLGW7H#&4InGx{z&2M&)%aQE)Tm&Lr!~4h@KXaK|
zPeDr>J_-9w(3>1ewyOt5-Rf|tOs&eP6{{~Jc>Cm>zDq7mZ~;H0LMpjm+C}Y9X$jPI
z1?%LF-l|xv$t9W8ucJ#SgiVS4M}o0SaWbv7JU|RqG^1-eXXhO0<kJDT=6?(60e}S|
zJI6J81c9d9nJ@?lu%2uw5ub@-@q7pVyKfjj6K$490Qh{d-f8q4_fyj0cPIC1Dq+Nw
zJjd#WO%mi?2bQgM7s*CqMtemiNBthnDT>?rXt_Z<$`HSb<4_VGTfm)=9HSqNQ?GPg
zJ<1Aev_u-n*XgwL`I4K5`wRip@uU9xpy5}o2M(rTyr@g_ca1`Wj)j_&(L|T33cvX!
zPNt?6oX>%FL*=9$-(>j<bP{G-`S49JcW`U6iSM1KP7^!{arg#WzNCvF``NN}rX75$
zvCPl_4%y5IY!tq~Gu?B%2hF||n$B)}n_1*G*$nI8b}a14bO7&nQ9n<|kZXdrd?CQ#
zV}A?}O-U`cym5tZs_dM{jzl2-pt`<^`SriGy?dK}kV)f;kPtzr6^U>{sR<Ab1bd`X
z#g0J|d0V=dpiIZep2{zW^usGWnY2Fya>my89HXF3*MWXd(?VvIwOyf#afc4@b;k0C
zSHJeNx%~H&!N6oYNnD8P<tueO>5;Y4O#EKhf+_w<(}?#@3i!UG2t2J{^P+$Bv>etf
z#>Ha;Am`ouqHBVT+H}O6xYh}v2oHqDhiEChSkB@L@Aag<G&LxdKZU|*9EWf<a|=5e
zMV7S6@TJ`eL;>nP^}|<Vj(Rq?aeCAbEqpAVL{0)2T=~jL%Kcd;8{|o``=iC=Ge<q@
zvOH^8^CgF(#bX?RJr|l!1F>MQ?#k7oeIF`l@r|x(v~4x=ETYJ$x`gG%-5=k?2kTox
z_AbV{-a0}Wf;4-HP)Xh^G5VE$VF||CKm;Qjmv>)<n#zwz&ovlL*Iiw_(vc@l?6C6*
zk^|DMuQ0bJ3cs+uqm+8J#>k9#CbH*WY{k}udz^f1&I`m#47yi`pIOv)a3$_zJihlX
zx2)w!bg~2NANZ&BIyXov`(lR4{*gC2)o|1tK=S=38Y38G(iL*}83h`*r7-U~@Z!Rg
zb#j=Ec($fqk<7=EZ5$UkxrMkIB5TDNPq3?)+d?2DG2o^(*hp#j3}x2yk?UQf8s~IQ
zXcq3l9O=;BH-zh?WMooHvR)$mL&eHT{G+SOSE3q0LT)QCT^G3W3w-_6eK*AXGqv`u
z>`taSyPKnE@UbE6TBQnVp#)#mL#`e^XF)VeL(IuQUw=pzA+KtpAjgIu#xHC!&2KJc
z%YvCz1u;X@Kw29Pd9t(r%=;fmixTf$xYpR@#z^%6Se#?-+E?w*4m8irv7o2NljSDV
zdRkd)Vb$vHHzGV!Xp692POO8B%`=Al+D#<Q5Oj49R{WCtq(I_6!6g^!^L7LY#9mKc
zW89;z+<(;scMuqT+*rOc-^ofq&PIZX_&g~mqq@<gw|s$|7ITP#*cvKiN#_ahPB#$g
ze!K69dH}4GG6nXDqy#~WsEdTe>qu2yzy<F1#{P~M*uG!7pK*NWTyW$298D7Ks_|di
zb6UuOzFKtt(m&ASU2<5v78`pLzr-8w-1XaW;1V;pay8QorqRPUKIMuebo4R+Br1z>
z_OCq=PO-R$r`hC^YncEYI@>htk}>aP?b_2n8;)*jD4N1v({l3~_+ye;fC-}mV>0hY
z+BU$F03BJtb<LS}om%(+M_779bG7vET_L!4jK|dFj0?=x6?{zg2S(!*AK%n^`)u#a
ziqXt*Mv+9j>`~H(@iPMJL#E`C<0lWHnsyaKp0#l|o~j{@jFt~+M~_4g=PL#wQOVM0
z39^9TMp5JHEuZzL2yhR0UAOgAA4c=^dJ59ymo%cs&4c~4mWjG9JKvPVo;6Gcg*Me)
z=O-|&Jqz~4(NvaRCnmTTkgq^+6(z7$exLpcXx&eoA$abG>B_R@HLc-~&*x$Z={0U7
z7%dn-RdO|3TN(I-DNk&awskPL>wjT!5E|*N4=fjpd}ag2VpOpe!i>|*0EWIlCI<-+
zHZy?%T+Z4zz~c0aYnDXB%0qAu;(gX7fk_+S5jPrHV%bsoTLc&EU`hSa)kq)E;Z;Qb
zlIbnIYEFXZ4TDcU@3AuL?jL4KtC}mYeeOgTOUSNPh~}B_u{TO9WbHBBJ@POCz?u)i
zDw??@-ak7*0YnAUc-oOgJkQ^X+zx8ufM7(3)4=69|JaED|0~HK)+MqyA8KOd=B*B%
zofce!`90#C)iDp-#bC+IB*7p2;glT7JLV|le^s%pSMGq;AsKgnSX^z`n;m>84i>(-
z2U&e&9{dXmP+mq(+WvtEVM6Oh?@vl%x&o}A?Rt<%F&5fK1PNU~cJ<F$e?)~WtQzQI
ziU9eZ<5UoTB-@Ke2Va5lO5L4YA=SX_Wsvn*v5aK|O&LreAZQDoVKxxu96)x~)RV9Y
z2#<iI&U}Ki`BUs+ssnO0FD`#|UX_Xoc$=;s5T9;LC@4?hg`9pN{O04`L<Wu@rS{Z5
z`)Y2wN_-}QQ}dvC9hI!DW!!VWoGeBZJH-*o2d6iIx0fO?e+{D7vOY4WLuG?MoEkG*
zo?J7KX#l3uuxiz1_VEzc#O+x%b(^#h4zu(H+O`O`LR#NTX0+wf{E@phUsFJF<It!7
z7I<dj$R=NZP5<1iqYzG0MXbChQ^w-By>|}?VqM|-tX2AlO5Qm?ch3i!Nu;ox3Kxo|
z<K{z4cy-1=s%0sP=5a;z5G%Qh8#Ba2L9nx7h)OtqfQQx_HhvGPCGnqVMu7MB>S*yU
zGmy>m7pne=XO**!^?{;&{=5etRblNBcB!Jd_P5i(jJR?Hlk>wsHtMsyeVKmf-D~Y&
zQN*sn(^RdQD2wLcRHci4CzY&T&}Ne21u3w=oSfado*{r!n#|gX=>&56w?clzp^k#5
z_nE@Z9Wk%E+>3u8|0RWXEsbV2_Mp@T%?}&;KTmn?&O)g*Cm6<^t6hJ3UJ~aD`g%{B
zQ+vlK=5pDN4E(%}iO)aflM-ZF2eK(Or)APsGQA2XJH&m0HGl~1J;-v2cx}`IxFaes
z!O0NSxCNHqBiN6@UuW)V4uv5vK4E~P-tBrd7n?rIl)W1;w|=<IHk;=l(=MT1WE|%K
zxxK(Mg;I^)$%N;6dG)9G*`(YYEhywySg$T=B5v+I4A!Dv#f)iVUncDk1A_Vo)Rd3A
zC80NCxeT8aOtCXFJk=U<^3PUsZ*_AOZc1UlL{e{RZFrWh^N7Kej_cB${ei?qz=>)7
z`f0ciNvD(bYMH^Ya}!~Lr!InWo*<%aMAn`LG`^Z6C>lKkk_8kUtWV2Rz(Es0Um{)l
zd278^cZ<z|jdkKSxRmYZO$osx)iHzhVG1<{LR5d&>ZNY_?t<8Q{;vB~2?b~mdR_!q
z8mIM|aDyCAfL=qWqMx(4$rJBQG(^6N|M;>B7Ae0k=O`nyaXd>Bd|lae>S(kd#ig}$
z;$KAEX8z*A2h{}`8<b6ZDCK`7Y^Ag;AIHM#88+2Sb$uVHDpAIH1v}DMLlxp#dvkrH
zlI89isnHP;p@)%ho63hdltZt?teX56OT|g%<s?c!#Yb&e>2PpQ`>0^*sq+#L*v697
z8!K~a!&2rI>fmE`(#x~+7fu08*-zTw*Tj6Y_eR>SsP6(L|E4mY(&jOmNh=h{e4Fpj
zpwjvt;E^{0)J8FHUJ|MQ1KH?s<eiF9j?N))*QL}nFH2+XNApdAD+&rZJ8lPP`0U@2
zLoP54E0G`CJI@7*T+rlNY`h(?){<9<D@TBo{lyIZ9blkzJFfRS5feod>}qr?%Bhu0
zE~0D*5!(Ngf4G~vWqMOr%m2`Pu`2Kiz4rO^Nlz`4cQD>C9X@-dbNs{*O{oq*bU51q
z-RgI(a<qa!41nadWGwGHfkK<!tY^b+%jziU+t6c_H41rSz<TGzUxJRU-=NGar_72G
zP;}(A-n05DAbGcqTB#`(Bzhf>JCObV<Xep-zf|NO!{GB_S&Z`AcPUMT!6L8F9kA;)
zrE49Ll9gV~#Xp5jlv2C5xRvXh_rZQ8SsgyPKqMwWWiO?l$+*j|U4vB9-G|xkSKV_i
zOqj(_^3ih4pzoAs1@(!tu|s;*W)KsV4QzZL*lqBF|AB5NO~{Ay_iXH5_wzskKS-54
z`&@1lR%XRiAt0wsB3iNC0_b&mrGK_VM>5PifSK#miqRz3sAp#p8&gVx`{H`5_2|Cg
zI;v6mVMJ>Z0`v1UCSa#6$t7zL!bn=wof9P9&3(DhBs!fcCrY=;y_5R(l3}dY%iGWY
zI2Vy4iF<JK-(T~~<4j^VQ!}%LGHPDW<+L?c@vP6$k}!IW;*#B3s!jjY<YI?WSG#q`
z`O&dtbvv<4g|AQTN8ywM^G?KL7kU0!3V)n7kKnHStY2sdw*meW|1cYCj4ETh8}wAd
zK~WaNqqY>`1M(c241Yb=MxqyZH@Ui6DJ(n_NbN<<ogE}u(yC(ztoclvcr*D2^v8YI
z*}9t!BFT}>B)B#`$w;vjxdGDK|4pzf3mi54QvriiymxbBv>_khr^6yeC%0$)c-pSa
zYNJog78`{fO&`_^a7qKIMv0c!uJp%h2$u<%<Bn{n!P3PGN5Gi0Os==HT}x`=+V7bs
z+xX%|9x<!+OXbgzgr2>s>6kzj?K;>7KbfCzi2E~^fQeW*wGbm5p;{zj+$$sX!e}w>
z<5}13Byf&5j6rW@?NP4kGnpVxQt;|vk*k?foa-!vRxC8`I`e0OT*PR}Jbj-I?|hS2
zfK4^uw2u@jD)Mhh4z{bXd~LD$4nL>c{_crJm8kV&Yuqr;-IEo*h4=kc0E2T%nl3N!
zu%tQq;_@FTUG3H-kF2yWS)}{hV``U4*EQLG*TGUc#{G6$zw2)^;M1-3y~YQpE^0@P
zXW(C<^~Sh|T8a|%+OEsth+SpBSR;9#v#w)&{*}8YFOgjsd35eyJuuC0&+ppFD}0Ky
z#Ff<p!~*v&WVQL|b!HYlokFSCW}UY0xSBUfwWKKYp;6*-wqk!F3P3WeXs-b2efI8A
z4Ueqe&>9ZyMXMOU8Q*LhlLwc_z;<kGM8PkJI6{>nYXzwxe-#SLa6Ty4+B6mlyo+*r
zqf<OkaGdvHAMt*#5P)#KupakBY^xK-Ak7>JWJ4=))6RMI&1d<2s4oF$-X=;vG(v1m
zP69Ixamz-Ql5x47nv}a2*KW{<!US<fuKm#>6pynJn$6+@j-CSVLdI4*yoZ&<J9fB&
z8&7wr#W|loi}Yt&t%(L$YKAA53*VA`wkPTPp1&4+m*vrFor@3#Pb50d=bMWUVQ^<T
zKl8axCimMVzh3r9K&bC`0rOU`$@9WJP1yP^)QUlmmF$F~@jURzTGNOvmyH3uYeED2
zB~FEEJFp%rD<h7SfnVQw$tyD{=eIIAmy_k@wQgm^67-<=R>bF%cH>~Cp5qr6Qlfco
zH+@D-_;}|QuM*ZhOLK@pA<oS_*ph;76C4tyxU~t~)Ia#NzZUZ{wt!>FfT7ksYz8C7
zh}s*0>mYbp|2FyPO70&>RFTeTNKF?3QCKanr2=R;@{`n872pF4IhKYbxVO5`Fe~#`
zuKaR-y(URj0NHtm*<~?L&&|*e^FY{T1$(JO@TPLo-0rSx-s3^PrdqpqiqR<DlY?N1
z`b&QQ(x&nP7b$JXk~kiWn)jvzzWW0>(h)soojRW`cGa!T^v46ZcxoL+X(CM~Xkk-L
z@|t!<UyhYkW@DMCS}Ur{9V%uiN_Y68lEkqb9B&>|1b%50IaNi#zbtTK=PNRE6P4z}
z>SxF^^=o#YHrzXtf3X!R0H;~-paU9~<4oqh2dNYSHrpkNTX{@Jxuy7Xt?QqQ6&`;#
zTpJ6=O^iJ^I(;2>_QqQWxTjzF3%w>LSqW3S<MObMl>qB%Dm;nuL`%PEbA7CjZ+J?3
z{lsW6BouK{($rcha^un>Pt9`+$ha2&7U$yawQPMprNFd)yMcR7>fp!Qn?i)<QlXVL
z))(cEbf$+6@7DyJJ*PBQ;OrP3awtsrbcyAIG+%1{Fv}xpwgmjEpH<_k7>!g2W@z)i
zEUDk)e#zz8_m0(4*KQ!vol(aR=M!!)l|>$xJmRTuC1cq5oM$v(|A;?+sc0jN;?F{0
zlAdF<SiRlu#z)RB+Nvg<8pc?*>qWm35)RkKZ(gVyE8yi9Gli5P1$_Y;PnccvaW%uU
z9RsR>_jSch)7f`1g9#b(j-fLXzLGj6*KpTGlxnmeZ2GM<dL`x~+OA=xe|<-VV^`)U
zX5x2v=UPdaiRA%b6i_8D3I#O+WcGCsbL0ASp)0*E_-rxm)|w`E75nOUdYkq2`i(yR
zpAfc2aKI@+pfyeHDu(;5+Zfyh@IF^{fBkTVOXz#1*R|0x<P_H(@F-awU?aWTE%VP&
zW7Xz^eFq%R?V_8mDEO>T8e;A_BV8`Ji`nSo{Q|4I15ghv4#iTW98*Lt#kfpmf^hGB
z_TH8#FgO0h-X_T6X<AY`{-tP>kS}ZLzsV#F0#fq6Kjd3+8dI7tf#lJ0?3nsE=iCKQ
zrNE0Fd&1)a>xu~N^~Tv54D@sTXaJd@!h|6yvO=V^IxUBBz=rjETM<SfMH<GNyx8P`
zUp_5h^7jQcAZl0=^I=%KFY*K_?$Z=aPTBwDaRBNwI`juA$DOtc0bfn)eZ5@=#s23&
zx1zEMzrOgLyBpIWu0;to0Y(Ie8sZ%f%r-!nFm*E6Ns6pTnk%CC@hQ<dQQuc1$U$Zk
zjss=r)r5(x;g>uW{LdQ8q^;_wVWk2z<5UI4__LMCC`aUWj5~Uy?vL8siT|pqUwPN6
zVAI0co7Vu&9b@fR2L!CCQ%Ntj;D>TD<u(oDic;jSi|9@Fso3Ao;;tC)c7akVWkhYr
z3P#tBGYId!`h1ec2)RW4&n*;a=Gb9>-GlV7$!{0Q-Jc#ACH+t?&vy9^^sgZ)sA^~G
zoF)uteM`^#t{jiUaUSL634h^jWQA%}aS<jA%pAonOijKseDx3H4RpEMuEs`kl04Wy
zdW;i2wmiQl3KAjVafYo_J55CKpgp=)-lIl7E+r08?m&rqH3`4byffQPqvfWcKON(2
z-ibRT=B*osx~nCF!;3+HC>SV|Y6@Nt8GmkCutJke*Vnwyw3lUlDBl9gUQ7H<zM4V%
z?P?DBp6`G9J(FybHlkqB82w^%$Vv`ACiDHyI2BiyA>=@>MNHmDi;pGs>qj3cPN3wu
z<-Pfuyh5Ch`}OT9AXP0S=`y9)m`Dklc{f`APEEK<W4etWpQhw!uI#^^)lR#}gf0n3
z)vUtx?UaEI*a$C1GBO#ID0)1d(<`;O<FF{Eb+HvzwsU&gB(jj2#~qqoW;u~QGFGU6
z7M45v7XWs`O(rJK@&IU<1C<!mgbn<>R@qco0PF&|Z(^-Cm}Ya@Clw-C$9Tz*_a5<R
zegh8=auh=nL!y3Q<F5HJZy)Upkb_BBqsVoeqpe9c>Hr<JDJbPSVPoC)Q#f`*EOw3g
z%Bt(V3tI;Cv<w<$-bB~e`PrXFGRiILmsvsX(7xiM9A_ghLZfGDAtG45_%i1rZ#%`y
zb#e3SNS&oHC$$n{|B@VQqvSBRyNesyF~UP%Ag5X2K?UO28ZwgX_G7q(uzPoG%Du_C
z3VPIZ+C8^&Ui@(X0MAhH!d&+Q$Is@O|H8J_0OUdnQp~Y?`{(QM4nbR}R2kvh$1d1S
zlKLSXSKqVJWMqhnyee>UO+f|AKr4AA2<oK-n@NBn1jG71GTA3G5tR^KDu1LhxglHR
z!V<i;I9@iW{}SSRyy5P(RfOwrCi`gV2|ph;R$ytf>VF-MJKD3nRxuB2(+nFm2VAq_
zA3+7E=d<8PU$i(K+cbHoJ+r;fA89Et8xoREDgFJQuQ)l-i(ARQ(*nH^xUl&}Prw4t
zEKx3av5*et-OffOMB0$t1%aSfTD;>vvnOw@LP|ox*uo-?lk2PUM{mEyI;(mgm>9e+
z-c|1s{ZF2>JWl30UP~y1jO6{Fw;Zn{4L&nqh$~l%Qy#9v0|x#Jrkb0|o2ABxL(qo_
z*h0Yt=5nIwqtrsJ({9#ws;T5>^#cB2yPL?6sam>X%I^8P`a37X_?LlqDVDzy53H!~
zYwUe6ZHKk-!K+r1&&;g%8Vh|ZkZynPy-%KDb&9=Cc)-5!C>giq7}KL#Se|CC)DFN9
ztDXS!A#{BqQ+X}E3KTYQr4e`iZ54iWkWGDlsQGeD%Oz2+@UG%{=Dy^}XVEdY(X$f7
z1E-gVX42I1A0`JY_PuK9Z0r|x?Kn8!RS%8+=~69bQuqeF9YC%ROIhrX4n&^>(v%_&
zQCHUP0MGpZ>7#;;tW<~idk_SQ%UuUt{de`WeUe3oedc$zTJxSZbW>y66eIDG;*m;*
zIrM-$jR(txm%UYDNl6S5$ApLzINT1MJ{jfdf^Gs4PM0sd+*t@F`M5$F1)j<OkaTUo
znz2Gui#N#f&O`$)(*0G`6mOsB%-EVFv<~xMn{GU4I}t{6$KJ&K2SnRZ3+61nmV_3o
zi*-DfU_D2ca}-&U%G$j8&<j?E0=>P0c$`4Gwjx%G{v5xhY0SVz6T~CeOoNsoQ;<|;
z2*^a>9>~&yejsZ*q5Dua22_gGpB^5>vhF$UZ<xc_uSkVA>&e*@lxi<yQ$&0Y2P?Zy
z;vGS00?b|J0H2sUDr2$!ug|U`GrgLwDn4ygZDscQNm<vL*HXwxHLmZ4%caDo@AFb@
zo5#1wsBOI)TsVHycTpN-Rh?`mTd)?TdwH(h=3N9I6{0K-);n`XAU2Jvg}@D^<-2K~
zhL$WCBX6&ftZ5mpjkfED{9ZB#Bf#xhgP(*gW#8_E^%vqsJ^z73UeU{kTi>D>)?F)z
zfD`5@xR5d5rIBZ|_C#JHCcfb~(cT~#@=N)mL_R|oaY$l!^(B-CH##ZlS^nT!Q1*a6
zOZ!l1P@yL#|H&8F=!*6YEn@`NzK_HuM4X+8K)VeTUe<L-WT0=U-3mFUNemV-P#AJB
z2zy3t9xbACLzf3%21va4V%-zC;cVY28!RuA<KBFBIBO5tu!+l<y^r<&ba9+x>yUO{
zf>fUE&-cLSEina&BL@Bz*U{yUbi^C}mdKX_@Anj{yc}2M6r$njkYkpKF;b%V%=j+X
zAh>bifvML9wv?v?m|bE6BHbgSFo;C4{D%8I?~`^LwV3V!&Sl>ClrwLOavOeH7ZDG(
zLNPl`j=>M#;HMI0B^VWB*fJ3!%|_<F<eAD3TpF_fYB1c!;X5h4dzT%NVm*n{3<!D*
znd@Faktb{77V1VO2@#qP6sa&0U!Bj}TMQ3KY0k@cheE%7kq_H7w3!y*>JEIrVz{JB
zsn<<W{S}z~{MGdkcnvGo5aG6DjbVx!Dl8p&4Ax}?geLPsW_0e?l#-bDpyzGQ>t)>q
zJJ!R~NizfQ<v%bf!3t~1os<LB6sMFnU06a43Qaza-jeg`C%~dY4DNkgxcIgrSm=4D
z#5Y`SVh^$PUcg!?`j!(LilGVeMqt0P#m%NU-7<ou<Y5{l?+vE~RSjJhseMZ+--@8L
zlTS44(K)AXK5K=`@a8>E@D4=VA8^k62Rh8QX7Yvy=`~f$KCCQ#NTLZK_^R%{c9<qI
z>UO>8OE2N3z3M%G8qjH_#X3&O4W^-6wx_8*EcHxQ6zC2_p0#*sC?VhTo{Kl`CD}Jg
z7yQ-mrBtt_BfBR*0xK48q_l)T>yrkke8rrUHqE!QGdujEY~KPF)kgDZ%wHm0W|)f`
zOfCgP)pBamo><3%f!7LrD^*pm-KOH`%YIm@)SEq<yO|>E5@BA3gZ(O*U-Gcq$#S-D
z+NK@~p$4w+%IkSBY6N5d8<<55>2`zXl~EI6kC=m905<u&>jlXEMi*^ij>x<Mq1Q6R
z+Rr3e4Z?Q#PIjALKenG_2%F7D;VJZ$=PE3AP3O?%l#?oV;DXy>GA(uYaCd)kVw!0q
z5?M(%>olQ$%{GkA32IlS<x6jV95DK_#_pnS3_qX*8IGK1-eq47lr-g(<Wl~<8XEUt
z#(rV>;`@dwV6~-4M$YB=Jm7b+#Dfk=t0HZ)Xz3@QU{d`)j(pP(Ap@yS92g((Q7jiV
zi>(|Ci}GMa(s4vMasIiTZm)yoo1*&;><J*L1Am;)V}>@jI4`ZA!5tw^Rt;mi(V`$V
zNI+G_g<{uU%MP`M+Y%%6E>L8<CGXy!w_uiyM~7b=NP12;->9lxrJU>0kIxj>OJ5w{
zqCyr*`d6MrHj{~}bld0TvnAGA9_i2TtLS(-3CrI2td^V6{@y(>@VVjJhcQB)WvI%g
z0`;Ko2g3IN({=}_V6_U1Ny|(`WL-?Q;jM$^um&zp0w}`;Cm^X`*J<PWTxU^v?%{w>
zJY}UyCN_iqMFu@gz|#^>2yVlry1ZR^aOU_oAiNKMU(ZWouHbw!`&9A1L?thtK2)Kl
zSSAOD$K*|g6c<U?x9<BE7cjo%%mCQ7Pz6&tQbhZ*>MoF4wUF#;xQl<0`UXEOCwDe$
zRVS8>Ly1%$f%nu}^X}nLHIM#**mUBqhKb$pvn49Sl`<R2oFbIB2k$A5k+pFq=Ce0p
zwn9Y@XH1f=%o%h=2FRytGHOIpt<=kG8av$Hx07d9V{^*vh03-<1z!>M@ZF$WFfA2!
zLx$3Tl9`g^bxY#id~&d)j!$$baDruFsd(!ma-LtD&4&`qqL^Q2F*u{aYGS3Y2!W4*
zU1F%<&R1NW)(7e(_%OSN5;;J5e_WwltVlgv)_Pl4-u10vb$T6s^;r@lsbK^t_h*w7
zDJ&!g`0%ejPMvEpg=BWPNu$d{kOhyKW5Ctohdx@pr*Q4b(71)2)Aj#F=QK?E2XK3_
znk{gl&^t*RE{mSCOn&KV=B}R*nglA{kssnnYHNr%EgZ>P2)!5Bq34wx`>)?B{DBdQ
z9XHO>{+^d+1vt-+6lLO+;`C2RA)lq3(m;2K-aD#JqYJJ*@5BINtu|l(W%uv75N1k{
zK2u}8`_eqI6q-1-F(`OJ1nz0nIp?()%gs6aK9jqP6DQXcKITq?N49rv?=%<Rxq_=u
zDqrT4YBImI?|^3An5@lt9!(YqYDM0!-B#%?yG<)?=5r~!B`RUYx_*!KwX8L5bG=lN
zCI`!17D?Q;N<UX6(c{I>%QCaYB$Xex`sF7y+}YCH*3!N^6!)6Lya?N&D~Xx7p}(5p
zzeBGj{yAxD^4xkFA~zk!vCi;e<;bsmdZETn|A?tDjTn{&;71b~(LrCODkP1J^#(pH
zJ{Kx+gnTz|(k?LoB$<H2$9idht5CVf(hPU#Q<$weq9ZWwN-#5EC&AxUO?qFiF$V!!
zp#YmdQZ{vT5_vMPj;+!mP>sB|dA!u2%*IC*`yP+dM<gLYM_<j{?(aqSO+32{J6q><
z9sx#HjREY8?%%Vl+a>ef#t&&2_s%czjzsr6YHh_y(XA_lQG)Pi)On<hE~JY|3kvSW
z-54*13G^pMpSmr2{sIIVP77=ghyQ_Sw?dh|@91We>;4y5EPH5bg-LVq->KAQs?$-M
zwc*?y%yV*wr$ZCLL1Z9he^*3WZ`ctL{_e+30kee|)ybMHE))D<Nx;VC*FTV+hs0bN
z*wjkey_oF7tngN<ySp$jqvMM>Hz0{Mgy`x>6qcW3T9A2wzqEH*qGCNbqcqxA6IT8y
z(5@`DLr)Elk)+OYUoWb$bhAc>8Z8Vd25F+4atL+Hi~oV5zdsGyY28JNo6qlQh6ENN
zTl40e9#dbOkd*M^dlOe6Ar4BHMHub^*yauyu<`unAoC`-WC>dQn=LZQ_PaP5JeS#(
zOPK_`!*9hg{jTk{?GFR%@UvVUHy&(Rq#-R<R*kq?nsm=K!<)q-NNGIoa{cZc?3)R;
zT6KVg6gP#R9_?H$gjAmG#N}C9_o;J%?sCBt^aI`I+H-fMiL8;#B#MY35dA|XjoB)5
z9b30jz5r~H%0s3KRG%XiK4pS_(7%X|7%RfqmcPto=)RZLLF^Pd<wFDU02eSNI?e02
zAn~&?`VV~GI_y!+UgI8fimg^St{=TH!x6+8ve%mQi=vfL@bqdazlcTb0ynaZ2G7+u
z&;n^&DcMPVZ4hokR{dQo5$@t`us(CffV2V{YWq9Bp<0W2Jh6VZ**+1v{%T?KXSqGI
zxebK|ot*LFp@;ub8slarfltCoSUwbDl#P5B)9l^b&ar&6r2Y97Y-tb5uDBDI_aQy@
z40lek%YISYbRzKc%fdr8&Je<TUFNX($3hL6>*wDd93yaz;t@^V@6}N|fRvcuo@XOo
ztzE}8NDIJ{EXc5=c`EBv-zS%N!ABDe;>w9LkvwfNC2b$0V!cB`0|ER<^_$uDWC~!*
z#}TUxoy_(wYXL(~id^|uA)B|#m)3?6pUaZZoscJhnU;J5i_o#J^ynQ~A{CR;yYw!P
zrEiX4)#i8SZy}v;Guy;FC#nNRbNkA{s;D;cW%=)#B$Pbb`ojZuR{@ak7e!X48w5Bk
zheMmXRf*M~0B?Ob<s4oMSH{IC4TvYw<=H)}_y+GDqmJrtb7l9)%64Pa!3Vnk^?oMk
zFm9P~%}UF1An1br%Kug+czL0CkfwhDXrnz@!h+I%->!YXd}Xv|{akWD8Z<dQD3%nN
zAiq9&RrGwSC_?oC|Hj3@uBm(JjT0+6Ie|zpQ!4f<svP%wQu5=Br-*tX<<1AYGG)dM
zb@ToV!wn(xX}@WqGf$g5>SMCDwuqwcf1m<YnvWMHuRc~h|I(zq$2V)t&NN-vyx9~T
zd;>J#h7TyC8NBy?=rx#5mO|{J0jgA!%<i_$(?bJ}mdVR<(xHNYL<BY<(R^?2v4yZ8
zYJ<h#5XdS5Qm8?MJ`2kkVy?cUcb{meE&j_eud$sjdQY@%i6&BSYMYD`30RVLZ9t#k
zzG=f6{ek$&h?D7}Zucq6k3l~Fv!^QA`@%bt#|aGWcxc88-ZtM3zeMOLSng{9ZPVL*
zJE}_FO8`3YGv36ai#aiXGI4(b@5}B(qMntO3%paqEX|kivXGGDSD8&gd=6a!IHlZ$
z^1>b&y=F<S+?y|<44HPBzu!8K$%lA|=sih~Ty@FnHk%v-&eH(04gc|GY{OP|(_7}~
z4`1&CJ5yQlfqZkMMA{dRe;_rU8w15_H_@K#V1}uB`iK+?7lm!HTA@gK_CnR$LMB2*
zp*w|)Ic7RQRDG_En;ti;-;jnJP41RC+%KDBTY;ub*6%aDsCh`DFq=oFRpZ!Rk7n%)
z@DO>i|DpSTWj1~dkgK~}c=QISQA5KNPl;*`P(@f?{LmR4k%f})!n=SJS5r<62ts?E
zh*c#raSitVRL^iB&a_{pO|Q)#yu(QDoS8;yAp&IGJ)Rbiv`l_|_tCCcW@;587=?A*
zFJEcJ6KK1-D53{s(GJcdt3*+hJCOdGPctTzRY^yz65HT-N7Ke3_77U0Jd|kAfxn(x
zcpfxF*bC-1KbAd0Q(H8u2Ey*&6mzy3=>k=5l2MJ_Gy(kaUGDGaFqu!tYV{v2Bqs&k
zN^FQ4bydt_;AH8m$^TYsOrh6oL_%}og+JSL<O9dCUn?Z<x(*cbwqozS92fc+bbiR{
zml|(k@gSzjjw`pXqI{xul)5bWcsZ<aaa$;81DGs0)FFpflQ@qhZG$6Cqpsg_`~!)f
zqec?$^(=$)10Z#I1Q1s%>caOKH5$2KRG|u`?-$t(eeL+-@+}iI@1B|Xg9)*Jp!H7j
zBh!?fTeYugofOdbzfwbkre(yMwuIy*eD@8~U!5F0GgmKVt4=bCPm5d3%Kn?1pu*lf
zwhrFc1|lQ6Kc=s4+-OwN-E=B?-s<_^;!C^;S~-%W8OMGq{IK<IN0NzYy=QOXLz=wC
zp|v74{XC-!!<(+Z+)2J#<R6H>F3Q+CQsoy^tUYz4lI3SIoNVZp`Yv_pn`gw<)|tsn
zZij0j&E-{i{EZ-%gcJKa7UR|TTEK|#d`^Xbe~c4+o!*LU1d;T5P`8)f2O9ChUZsff
z(mG_R2JDWjg+WWCGn{7nlyy*w$q}so4>bM1paJ(k+K-@*v4HF4uAGU`WHOHCALv?L
zDC)-N@-~+b($x5hddMz(g{EH!-C08)`$VDVA81O;Ld`rKvQrj0Rs*XRc9Q80#ce)X
zaC02;trC{wm2WDhBM)mm#dC3i|36cC4ANZ0?j?O>K<2EqhQGosKQfAIwES<#F!ke5
z8NcVaB5@*RtoBq6{A(Ez+Mql>AukqyI-m9W4B~v5-#Dqy;>P?*@^m1k`M%C;szJ)U
zvr<En+^L}mjHHE^cNvkTljC@!G%;8|Spi9_<uiI;ra8xNMG~-0s)?)w-@p<B-7D(M
zo8%xL2V}Ct<-?gEtIS^ka?)d9^f2Xna=1^Od$TYj-~_!^soD6u<RSYINJxE%pyb8O
zr{p4ifnjp&vy#*7%fUS-q3f49B%}W9?wXm7C!dshnA2~q#b0nMfG4h4&&zHl__}6q
znXs5*FnS`hle%f!r?0aRJe@7a<I<{N#dRA4f*u@GbN<yVZoiu=WeAdd_zzSSh1HUQ
zP?+Fh2I(1)+}U!X#dz_nk(f!#Klf692s1xfEq1(nb`RVR(RSQcnn-32s{aQfD7T*Q
z@qqaYGhDjyS^lvh&^wvnlclXka%8kEhlUsczy@ojR>=+-^(f=dk=ObvwUIOBpWs*D
zRqlTEQm)C<QYnmJx|WI*_$ER*58^yW0gfG09c+~iPR8^&Je$d}_2jqx<|p85G<P28
z_;vn#Mf%?JS|1uO*jADWY_~Rkl#>Fh>MG~b{${d9+sJ>VM+AWUX$L>*w2o(^4))Wr
zr~hGsRxHH@vwvmj+i|s}P!MD{m83VoYM1fp4rifa>&xrTlepsW2L~k?%Y0MJvM%?~
zqmb0Mz!{!4K%F+efZ8Z#<BPJUdl(1k+hYXUDMn;)KUTaZgkh$Zhe8iz?1$o*fU5mb
zPSbOi54N1QdejdV)k7>Kbg!9=&d5^$KBy#~J_}GF^KS%%bO^j#KGjLO^5EYrDGu}k
zrizJi)J7vt!+m{sR{lost}pi$8HtD9THg3`QT<fW{UUUKGs)H}7?@dJ?%OsBx=?WE
z=rAMhw?9JP>%Id1I8pbf_5iSsXdO(`#MI?En(jjO0UAlzWwlXq@8=LRDdboT@Zi5R
zVVj>g_W&K$i&g|SwiY7j(H#u?mFmOl2p8SP5%pQ#_sefxB7*~o5(?aI=@0mT{-_wg
z_0<pQ@<)GuBLU%CF2fH_;&p(r?+K?Z#AdD017xJy)mK<}b#7ZC$*c|$!76i_)u>k&
zT<nXV)=KhoKo%+P-=Os-a=5a&cBuqRz4CDi{ueN329@N}8oIfKSZcbK&-@Y&Lp0Tm
zn&aVUg-<sAtVq;8zH<P6e9NsrnU&4!iub8W<{z~Hw);Qynm<+HF&~K@T#HMe9M&n8
z>L#;|PAB>WLRlKm5!bBr<o9boU-Y`Cy$z1)Q*R?qLj-ut0wh0x5dF%0Yoiw1P|T$I
zUm>Lz6>w|4fo2F0sEntVTmC%N))MX6@e2C3e4OcywvUKZa0|Z5Bx?Sg>Sg;ve)E6V
z_7<L2ZDcxP$;!)d<rEtCSJ8XYzFL^)voZL&{rn5ZYR^>zo==b$TJ((XY)|H?tRoX}
zDe>jk9^hQ5+1rC*BN@bJ<04*9++Z<o<z$We3xMDS>9v@oHs*jRxSZk8XW4Qp`DNXa
z|3K{j$I)3vMfLq%d}t&Ekxo%cDd`+Q>F!hzkPb<yVL&9Lk(3%brIZ#4i2-pKItC=A
zyJ3cz|8sxOJJyoL3-7t-p0mGufA+M)K<<44M*{W<*h!fp??i@=`|T6_hh5sGk%O)J
zn2gv#=69TeP4N2P?m@LcV@%8HHHr`T|LPvNulNV9a5c$z)1~XpyVRJ8z1nIno@UqR
zPk?*`CS!~exrKtCx-GsgzHhH>bbFsoo__xY_U}(u3jfZe1D!xiZ+1jH!u!5kamOTU
zIB~O=uyBda$B~Pd5A%W>+(cw+7U+i$l|*E(>O)*<IRK&PvKriSnI+BqB3#fw>XU>Q
z%I=OCFe+I;J#&2-E}>!mthKyeioD!m?*h^@K-AdjOI<r7IUA<&SA4u<H#hA4GOt(o
zpHduw-m(g>YnL88L8JGY`_6@WJ?c(!|G-VM{ZyYZQuNsHOP9&Y*>4({o7oxl7l+YP
zZ7J)3GIubY)LmC^k5;|;U>Ph|^l*^F;nbZXF9*Jfqw8$~)~8B4CQN`D!wvqOj^P;K
zWtw5Y-BvMZpS~#cb|BeDo>dP;uXBGu=aS)X#6$rO)&C--vHgJZ0JHS&^TE0(vd?iG
zyLDm6lJ1173#~0YaN_BB8~ttZ;SkrxV8v$O`=qweAv+D<@iFaLd)NhrnrC3Cz;(QL
zkBmM`?VWKr04t}05Z+Jo;M~ox4LG?6y&h4--gTi{L~eA|SEe0h_7O7j{Gio6T2J&i
z;YNS1j4EPkdk$*l4P=SPsB;75uRo{UsQTCSNS1AL9LD?JxWCwz0uG{)lkEp$m<Ro}
zW2Y&$k|_tr6u<5*$G)$fi7W~VRwA|&oxaVV_AI^e5&IO$b}GnlPEI4(7Cka#knd07
zN*K;axW>)BpBwb;WOD6geDKjl9Z7WR9fC=w54%?WuCWA4`6#Jz5MIPohH;Le0SNdo
zrH;yb@=s|uu60O?5%`#2HNLc5$MHh<g2_57V>7C(P2reKCxsU(4$;vJY^^2)<|pf)
zRjN0t#Y?Tn@$VWdrdGUMZ75kFMu-@}y0g-#=-yi4s;~~sQ&_pt_Zh)T8|#J6hAECZ
z>vY3-;h#>2=<(-YQFoFUKeymZj~V_hLk1TAUEr;?uh(5?(b$kX6cI~guEFs&8L7-S
zq4~Bx5~-bvM>pn%!LCQD9Zreho(jlKJ==$aQJb!V>X;&@)S&jL!7S?b3WAil27Lnk
zyPJxnK;Q{_WWZGJQYQ0&_XE=ZE=zvAo9{<}Olu+}sPx|>!}`4ehXbGJvFEmc{ok#=
zhX>Y$-j1&az*X~$Zm~;#I>37uWhfZ^odu$=1<K!h&FTHajbT1<N_RVsMXpp8I2;47
z$!@95j15~>6UG^sNLSQb^DIE(tcZ1Z=H{`#)MTRvWz22gjx9O2n8~(w_IkE~LgUlC
zyHu8P=Ki0>Jx(~ZVvA!yws1JkX%H>(vwg?WAzR!Jz%v_51j^YqoSPPq5aat5NNcZb
zIfXVS0KkbovO%8-h)853k6A<B5{bjV(vqM!6eCqdo_NZcdjAYaU)(Ci2pbPk&ixxI
z#;~`g;Zo<39?ZrLUq#5C_+7ryAQ8$831aZ*QRgWXfBJbr%K3z+gxRcS^n7geNK{MQ
zQ+E-kXpz1mjwf~XaEw8!K-N!ryo{Upm_x-+L!45ni1OXyj{>Z#dQAPbUjVQEajtH}
zRLR?T@=8#0xEr{U3yB6kF9OgzZgVny^lRv{y(@=OcJU7o`)@Iz^kFA(t>cHx1%hk*
zkbqvQ9qBPC91~|y7o2&`h->aSN#r@e7K4v-&B^g5#b-RejKi*yU6`E;|A_faRY(^F
zh5uET;)lHfG@oAz9#LTTdn?@W=J?orGtmz(e`HJdDhQ0Ux4!<!96y8_oAB9!bAf~M
zY2EsD9V-QzHYO7?oL*PtiJG@(6I30dXLNH}gyd(qvFIOFJYPcgzU$IngCqr-ro<(b
zJ1vI5i-W*d$76zoD=S0sb9t*TM7i>3Oq@CUyF2FmR$28^9SeY)@-Gpimt5qf&U-2@
zc$7#=PP~RYlp8rg=Lc6&cNA5|lGr{y6}KUjtxrsZP7DLR2o(i>S~9lJ5<`UClmUmz
z$!i)(jDL~M4q3Q~@&z3p&8+{#ho)*IM!eMWJ3)fqjT-b<IYuwOeZZ0gn@fa?lcpco
zz^2FBsbV`kV!=*MXb=(q+y=o@r?QZA;JjT~p#75Re;_rs&?mxIv&ml`EvD@eaiv0k
zX-V@;pJP{WKlxAZJ^gWzNP;otpA$b=^F*>KS}E7h*ZMg5h91(90<i`L0kTEb(EF~n
z>nvH|CwUIj$(f?3luaChuyqjK#5!O0vsQ@QBp!8~aL@K%h^+k=Y+aR}&y|;gQZ>Us
zhrA`t1<*DZ|04a$wy30^%Nn5?jNy^nDq}#^QeX=*Xr}*rdYb+ulC_1U0F+#qTH9p@
z59Tt*5=jcjsN`_Ge)@|KX$Y7d8vdJ6#$R{wDG*QT03R=DUPsPAY4KjAuopaH?bO$R
zDp|qi{cboF0u+n4)ih!L3kZ;y&WdP7=$j7jE76kc-%n54W9TTw$k_<~SqgQy6969y
zdNdSYEa*z1M#gqY;kN1VgnFHN%?p42bfArrs7-g~2ve?`?rP{dW=HlceWowU&jTvB
zx4D;$rX5drWV6;VXYH4eC0xMww~h`rHV=+Mvg(7NZtb@#id%J7EKQH@m8E@y;%QJW
z9ISm&BJF3w3B@#di8DQM_;w*s*mZ7w(nm4wz?(io{QcPf^KTs@V3J^^%B0>;p?BO;
z8~SY$M$Sbz5}coW=di2ElU+q@N41pyPeL7=9jGx-{|91`D>R@HCg=zY-|2>&xK{Q{
zviQCQV#uAw*8S*@iPR{$Gcovixi{rfq2f5`n)lA_<Df0&uG@1bWYu3?S*q+GT<w=m
z2)>h2@Ja_z^aq&6NR$0K&%uU(yQG3^Vy9D}$@$Cs5U+BGl(N}vg%Jex1^AVZ+{ZRl
za+5GJt2Pd|;R`$;4I<{ixTI@t-YJPki!O##O;r~X9CwdqUmWY^hmxhq%h+{cOI_IF
zIA$XwbwO0}U(tyMR1sx&P4rk-y{HQ4!!gMB_y;d075AT~$}yDD)4g&Lt-7Uo?>{U*
zE<wo@Z1MdFud;wwJ<(4f5!$BVA)eW*t`jig26A^p8P%Ifat0_`R`s+re;#=JI1MQ}
z9Ygt$Sf>$_#hpvPqB5kOWsc1a#7n5#E$-R)`+eS{-1h!_`WZ@u?TiQz2x%G7&F%m&
zCtXF2LdCgB9G@{v-?8@0>bt`{1;8&CNC8^l;trb=ai$_&6H14PC!mVf;$nVGK5*3U
zD7WMCrt8cXD!jc|PwO(5B)QX`Cs>iG?rFJjB7Eki7D9-S2}pXJ@);BY1tN$wH--PA
zzQKKvr)(`ur>eWsk~s=jN&OeKm6lT{`e~^>2R^#Em2XBxN=p|+s-hVHEovGX^T$hJ
z%<V<J8zQ20ujeqJ)?t8tf4IrJPxWcgXAvcBrhD+Vn@Ip|K3hMqW`H4jl-Z*2W=Q^P
z$lH*ao*T{I`H<A@DKBWI$};DBj|BC;tMy2F|CF{R<TqcMkZqRG*}F~)$0tH`tO0|*
zpX#*UseS>#v~Kf%mzF-*(iCGl_HV{T+h)zHB>TjguD*VGGfUH0Z#~Wav?~7DW_d>v
z$xn4(`+ITqgh_`=W0o5;n*B(=BS{*q){xq@t_8njO$o2{^(zw31Qxy>(ydxRI^IhJ
zZ>#_p#*%fWD?#;}vNy0}<}@G*p-K{ZiNmcKvY8v|uO&X%pUuWt1G+)sJo<@2Y+Gy#
zG4FFvU_UEN(p6;ZcwCvs1wOXV3DAAfb;CPtqHZ{S4^VqcksgLV4`AfKWybW2y#!27
zmO6OH;4Mb7(Wij_x8vT`L#D22&GohU(0DsHYO)U2r9}4HWJ->cPemS|GD26GN2#ki
z&*f73=~mlrkoi9Ggf6gq71U_0DBLOnxS8jSuP!;FSIyoq=mdUo^nN$}Op3*Cs{>h^
zOYF`YeTWZxzMXy`pj@;&61nY<+g-FM8FQsx27f~6<%T}IJu-zd6T1mzR>I*qMWNj;
z%wC^aw)~OxYnD;ki4-lfTMr*uSSG*iG)x|dQc8MIxf7Mer(eIPI9e=h^8j~B{9O-L
zQGM%70#??u)_u$>ANl=&AFpU)XE@xD{qDVtcr1qP9a+7)Th%O@EG?C#=QTgc6>~Ky
zV~W$UYVS8M@u2eoJ50RdN+~BnSnvg#TY7gq1NQa$PokGouED>Cs4GJrFx8;CQ<(EB
z*2YuIa$V=d;YPF^y-)1Ltmub(k&xyO+II8Qi{GZmS$JPHz8DZr8<YJ1E!_Qqr?zcg
z+o+|hLeXle^KAZgAUtvykW3BV3H5wR8&j=K-w~ibyo24G%P3Y<x6E|#lJzfo%6Qea
zV<*@LjM|wEZesS#ZaqyIFn|2e=E|-CTQ4g#r<<7MJs$$aC4X(VBGp!mjh^glwa0U0
zTs_KR%ad(fcZ4_9FkI_;(%&3ODFz|6M%t1!)xz4dryb~Si@Fvfs^L15_zbfFlJ+(D
z==)-Z1?pDeDtzqa`ZrSx-kb!1Gk){FlrN{2n=n716yqZ9b*7O5B2bh~%2=-ROtNxX
zRH%=}+a7P|4W+nxZO`AA?6IEs_X|urT+80vm_$pcts;38@T#I)8~X`U7w-5+-qtp9
zHlczx;sfvZI8NJ~%0(Zi>*B_K3W){&>DbY~F{#v=jstmtucqj(CR%jDzTsWE5v%x*
zejn*Tk(9Qmpd1fGx3hqVQId@({cXO}s~$51iE3APHYeYHbdjpW#J?~nN5<_)oP@}D
zv7P)#Hv3IAkQWmQeRUG*iBJSnX~S|43OAV6Bc2uzPfOi}39Yz&x(Ma#`yWV?`tnf&
z2UW$m;<(HuUEf;mTlr2{%{Z}7^OU^<E;S0f?4xJ#mDS7gTX#;K=-R&M(1oq9fa=L?
z!Au3oN-@r#Vn}2+Uhj1QYpw}YI7b~bYPE8b;!=BEVT-v<+1EfRejs?0`tLk@E0rl`
zLq|U+i^J+gXho?PN>Be)*=)l?GozHl2<z(IU;ZD>e0k4Kp85|1gj}Y6<3`&|k538-
zRA4K$X|D8)Hp;`+7Q}WeoXg&cJ(D80@Dn48y-kS6U)2F8Hr@Mot(b_z$^3v%1EJBC
zgh}mn64MvGU8<Q^33WQTR|Vu@S>EkbiaI_T6n=Hf&UyC4A)YcE<ucyFTLf4Z!t})1
zA3<3&H<+ia9CrNFpYBI~8&6B_fL|23{3bE+_}D6aNp2KuwHQH<ui%%MGTV?syHpl!
zgkWJ)gyLG{Z{l%kEFPkOjc5C!nhAF0>Du{Hll?>aE8f>0^t#Kx=kdQvc6{}^eTKOp
zxZNt0(7)fq;S6tL!Zo+xBMM@QnWM9a_wQc%pl3gzq`kioKzoC}n*BUw0a5lSE}3NQ
z*8TaXGpR-%K+-UoRVpdu!5&2Rl^bRp|0}!S{0M;=-Y_2bdYm%UN$L@2#8m$HQVt<|
zgc5#g|14SK--AI0f@~<cZhl_9Pcq|0nJsy0znB`sVx4uK#&ktkzd&zk5#=4)gu2M>
z<sCZp;#Q5X9iBoyaQ}g?^q$Xun_I0&c<?8r=KzpX7mjUUV0WrflXWUAWchTPZIFh9
zAXM)LEK`(#JguV&WK5&XQ%qfrC0V~mEAA$I5d>*zO}VPFrP?jSovr1Ec!~26+!e5e
z8*Wy!cNuQExL+68T-*j%B#~$&A;*w~@S;kn(=JWr-FIM1_o{mN$*-tn&F9BtPJkdg
zFFbv&-5BvW5UpXGJ-V>R68{C-SPDvez`h;mg2!SxnZZXtJaBO<rcwB4Y8(o0vbEzs
z^eL)TG;u^n0QtWX&i^uZP6;5XPphPCob3IK;7rjw&8JOghrZyy;59u@2X*6)lEjVT
zrvSj>;?G@ELnArx%Jw(BN)5Df!~g?7@;W!cYY%<JpVjbzz?|DR;7qkJeOi9Smr?To
z7k*xdZzdqn!03<PF>ubVXgO*Q#>lM#b{e!1IDUZ~&qMQo#Jf%{%#sWI<U8JxtM%}`
zEM3nl+@bn)J0N`eBv|{j*WgTncu8m_C{D@t)e=;I<dcx&-|OcJ)LLe2BPh6a`b}og
z5MDWMWX4kIvoFguty}GW_Cd#(Li<)Oss)|;UUKOI<vK59!~AduGsmk~l*^z5^G5p2
z)l&(4nr`7CWVkaGi}zlXP-kMG<?t2;9L+lB;yr8Z8GML^J7_i?{N#+{fnNlKBm^l~
zBeUd`$Nter_bh-`geUd=dXCM6KIN}_4nA|(_@MD;86Ui2{6_7}-b`KcKMz}A0qjdy
z6WDxbnmx;V#jVU(zqidvq9jP)z~mtvs6YZnPM0>UejrrA32L{J){?*Rw@Q)aCwFj`
zd~!a=X}R;#d#Oix`rnnf?Wp~J)M-g1sQ(U*dS9{E%g)kacDtpgetT>snJb*-8_(9c
znd~}mF5%D`v-v(po13cWvRZM}lhpP?QI?o<rq(j4Bt?#dahR3BoM(<Z0QJbgXFpA|
zs3V%E*wvi}`Hcu}1gfI`bg>ikmg$1=;S+SiHs@_9xRW7w4A=LOXFDV1S2XAuIPqY^
zgEZuVw_GO7+vDyT<&?}*lew2uqily+id`n7<*s-lhb-(7o(S`2FX3%TZ`e4)LJq59
z0fI-1=f7t`!{w48FP#PA70{+-p2Q+jISa835<<gdMnNdA*`MLNg7H8+>HSptrlq4p
z&kL)Vb7j4-oU`TH*&Nhz3I`sDVDh=^LLh<Q-HV#0-Xw=>uq0T3xTQw=mdUzXC3pHi
z`9Uk`MObYiOh|zDR1Y>bUb(_L)s{+UY&`qVjHZ@?b(MeQKQFuI+*`)wejMH~*6q!D
z5L39u(iNsTYCwr2i{4?}UTl!HTS;}>y#cnu_BUo?ZdXqdbuL2m8+Ij&YvH}R9F-cO
zT8048;-s%DUl{HW>+dSrB)WDk@H!?kG`jLfsm^?f3vK0Qqxk4>R?BTT^Z4;C5naC5
z2Hlk3*9Ye+@AOu5CaP>aLWtH<JldXtf5gZer^IgJDgW?EUIhe_DlqC>{^9RyB#Ai8
zX_g84(I3vHm@!3Q<6=a@(xOQv^KUD5{1?|)xsbxcCbO=;kA=*R<kNL&T^&;79~=mL
z0_0DJBGx_Hjb$yWB=3Ak1JhpLUSPJCy~(ik{1X`t4V}YYI5;qphLRqyw@2o{6m3lP
z$<eQSO9i}KOBqlRq6l3Qp9rnQfBqO9?394dDJuj^wc7lU(s_SMFT1j4^_7OYcaCY+
zwEq?dUpCuGOsQ0-J7mXEMxHj~>vNj2-NBx@2gi{(x}Jp)`!h@AYz1@X2mBHyHSm1R
zajoT3A8+uSCp}}WYZ*MP{e01fuB87Z<6m;>ce-L2`+1%<Z+^wR;Hu;nMmxnpNyrZV
zX@VAua&%7Mi1-|YkCl|kXVKH_mBoGQ10#+%$g@hJhPL#|k+xkWS|;(9A&(_0#Ad!R
z<yZ#n?C^u!VXdg!2mf16&g364K02RIuRgcx^2n_5lWGTFEG!B1&MQ0@wIY9OAB++C
zYY9b}H#H7rkX}g$UlrWind^<fWe}j(F3(c&t_%hMTD$1cuje(E!}C|GCfYS_c9gB6
zkq6U~#WlcYl_D{6UF3jU<R51C)_)z7x-{IsIi&<Is*pIUQKuhPh%9>L&bfW?Td^YI
z@rvXW?gN-v`N^+*!FVF_+&3Mwq`+Trf!~oo<jAX&a<mCyjR)mxhxeSVN8t$h5l?RA
zt%}*dRNb4+aky3r1xkyj>d6JLqH0BY)&?XA0ISvropSnuqpihU)LqE|X^5V(qI73n
zYFGpM8zUV@t2kCuU~a*$G!EBAAVCtUf&maj_le)N4}k8eOahw%(>gl?qCWbHvIoz?
zZ%Rj}PoNNXQrz*QT1sI9UL1Il@i5-ORVpgwkRWmj7$`MpkcX?DZX9xQm>z1hzK_c8
z=Iv278B6yY@zi<^i{`!3DXlN%3E2?G^Yl25j|iaBhm@qwzoLnPz@S#u*vz!^<$s0k
z(nT(fQr2@E>SaV}4zioCu}y{ZWf%|=QLUkG`_lkwZ<!Va;evZ!Oq5u_ZbJyzV)%=m
zVdKRjyjKX846jH-ur0$Ef+p6=Q{)e}VVE7`!{$(O%`Rk1KGk3}$OiZOW5m{(4c3)G
zzcndR>Ki}nC2^UUYt!AgSG;Tq_O&+JrAQ{VEKae)pF8*qFnv}?9f<v=Oe!~6PslWT
zA=){?lQg*sK5lf&4D9uyX-KAuN17Zj-#^*xJDz5?OILnPuj043C4R0LM<TkdaFy$f
zYQF!j(Rt@f8EB4~EInfzP)rV)IX6r0rofYh!p-*Y8gVS5T61U*_cLops^N|b0;_#>
z(E60(vLR5ns{WcX8*pUV?2cAjZYQ{cA66EaEfKULazX{^@fo_O?ydKIVm)Q7<SDh6
zwH!&q!L`x?EaqWCgJ%j1bf-1aoaE|5V#7tGJuSt?AE*9-RjYDut&~>m(jdM9^D{zt
zTZ28awudZ3pt|BBvK16}qJ^A8JF7_#YL4;tnICd|3UzFdp835O=RcuXrFd9FT?Z1r
z$~?Zi8G^3bV%>;vMd62K&=Y2MU2|7OBgeo>l9@avjR=w!3KjC7woDk-HxQ&aq}JT&
z*0UJREV)k+9CW%HPhnN-JEhj6MJ)WKE<Y?4Z!!|wtiNJ<Wn(O#WY~@|N}f(|t#anM
zaGq)qr^s_^N`9iEps|%ZzOUMCopXCNDB%&nowz~^p?saZu)(R&EAOjMho>vp60s0k
z#=lqc^|84U?(D4{n5=c5(I)tJc%5aoRhY4cWrJ2>1o0pRIm|iZZpd^f=%JDIy~my_
zC{;*|r~#z_MdF^0V%=;RJ-wY@2;zt%SBXH|aLy?Eef^rAtmE_hwg%}qG=8aMt`$M&
z;rY>4Mt^Bql!!fqB^MMt<#F$}K~wP$UPS_>ko^BZWz~wuxem(3MWZ4}%up^>d>4fT
z{u7L3MiQcTd!kymH7W5E_!Ql6mBi|68i<uHw?^FekCVBwnNm`)eK`hNId08&oEW0c
zSb7hdwngOvFyMJufR^`FT|6vnObt-Y4G4Q&CqI1P0#0S(<cCrOZ-2Cc7b>70i;2${
zH1n@)cQsHbv9MNZWR0H&aJz3lRJwhp&z_((<GEC2&CitLnTfwQm40T?t(Z|)ZQI21
z>^UF4PgQHUHZ2%W0~OuNgdt`BQZsaIhNLHxK2~3p$Oc4!CmhB~qc048@@_WU6b?*c
zzZ;{d7l7_z9V9Tu@+#d^s@!<(xXTQCfdE-D$PU2He&H+VxvbQ%;tm;h+=^3P!JkF#
zxK^y#IN*MgjE@twzOp;{_L5=Asnnw7bJvnO%&5imnM9Ty`vp}Op57~NQ^E5+fzok`
z|AAzcEa^L|y$dl7b|o;j0(7^n;V_#rtI^`T%`d#rUpKf*y%TPJvwW`|nPVl|M<6^Y
z0`OR@#{8RlkYdNa<@a6Dku1y`)k{j#o^OKfe?$C|JBr9Z?_P~9xG%l$eWOE9FVG{g
z%U%7XXH1}d!v6qt{kYy&rV{Gt0?00cmg<;kJki!km9Xo#-6^<-4B5q%cddU5H+L2L
zi>mtUR$gd$UXaeoDHo|^pP+@bxx^>@iuiv$61_r@Epx=>zoc#$)xJt1^lc=Dmjzdd
z>J=APZ?SjRxR#nsME+ikg4-C+0wg1ne=T9?VE>EhuPUio!EEo$Qtv}Oc5A}5jnrRr
zmtq1JlUkigx{358G@eT?U@j0Gs67&T;o+lZJRA4XA2jna*Z1_8H{o338!(^veD?<j
zx6d>cB7lv+jpBJHbXzHY!|JDis3Qa5pmR2qult6#W0G!0k1_Ryj<-%S%viuK-V$C^
zJpbXw{3kL{nQ?eb<57lo{qw{@cKvdTp?bvGFNUQwjfs67pDiLZo>JUh9i$hYRg&u=
z@p)l|@h-S}cE#fDmPcrm*0TV!vHdOxbLueodw>HHg^wZgnQY-<lG=m{pHvpe8FLDw
z#uPNSQVv3Y1y4U#gy$+L`G+1Z!i+Y09`a3W5#UswhclLY(%XaFuWZW|DMi;jMxY&j
zN<)+asy?{Ffq*`(@npWKt>>`n^5^}`5$AANNR0P4osW=mz#LzNuj$;9_KMwq>l@G1
zMMCU~;Ly4P3tdCyF4rgbe6LG4*C~Il(P75qwJN2TsK7|3egMI?1!E2hln@96Z{*U?
z_5c3sEB9e2TajHq`?pTYSS0D&le4!U-86RNX|I(Nt`q33$H}0JVG2y}jE`ss@#DiJ
zCT=;wNcJ4MU;WVLW{X9ff(*BOvH0e!c<JP*{N=)AX24HThu@ZWrLDhH_h<WjvtC9a
zy<G4`>rn)82l}fm;H!Z=-`qE78a-LyIGPpcI8{1(B<16zFf2~gC*j`q&o%#w2^dV6
z`eaN^kyOf0CfOP~oGl0|$dt=w)o9@V!H3A2k}8MR;lY|-7QO!qyt6SJz9JAJ4)-~>
z#@5rw<chq4fD{C)!;%5MIO-fSoicw|q}tGNTag4^#s84I@1JSDQ&J+buLs?@Cc&aW
zKxOD>=^x5R^tt|jT`s2sF$V}~S9FsN%lYvj#{x4TXy-&lYP`@(ukJQ&F_QtjrF3gW
zHp0TynlO7HIpoQFn0K9<Q5I^@Nxr&;?YR$lbw={~Z<##RZ0pf+K_Ph84gb6cjP)YP
zD3KwzmsNS{jSlCpA6%9_cbf1YuS9gp2Rxn>N-sMi6Y9Lc+l9?r1#MOeUQ`!PHvb6z
zSia(W_T1Gbkhg8(py=HWTYN$9zuAxIl!c8Uo6v^{Nd>dt!fB7?nwD!;mKWu{J_+qw
zm~=d}m#NU4Da#EzTBXWF*mzmSsXi0S-;lWf*&&EocaUx)s;@q4fjcw+$|<UFt{VA`
zl8HWuqR`;6Pe)d3X`5j5d?`>^VE-!hLsL=j4y8fftM;~RyYKIjG9-)@k1o$y_}Yk;
zO?*Wyyw}MyfHkX_r>ht6qeG1-h2wDA31bj$HjQ^A@QGV?tmIGN!hMD5@y_J-ji(+k
zB?04ruXMky>cJ?we-PKWKZXsHIh2^!UGO*t_ME=5=RqF}$r|p6VM%`PZd1eN2c@m|
zb;5(E19szye2G(R?V#Z#tNcV2?f<;H7E`nezFu<o+jNK8t>>cNp0`@<Dc?*nPF1)i
zuSk~o?CQuqS<F`~<pr`Fxp^4c)l}VoE7!BG#!8tzTU;V=r=pkIYjYmk#(CbD>7f%u
z#X$=I(rK)Pog~8(Tlz(>%YX}@&sO@8F36OfWh$F+S;J><Jzrdq(;)z<k9IX~jdiP}
z6kfF|(|w@ByA{BAAx;!eqCFl3h5v%tDDW<XDbN$hHeHX@iB-6qo_6`%$?a0s$Hn_{
z4}uIe!{qY?0Af*{kvNLiED<(VmvW;%5s2H~)d{U*WBKQA1fE}yq{}v(FuBV@z%dUw
zXZ%lxTcO_R4;}Y%m6)DUw;L<X`j^XpP%p9~Hpijb{-!j3An{eDtRn_LiN`{RYi$=>
z!F}#rjQjBp?yVSQ>;LlT@5S*zvo-|Z^+!Xla3-)tbMHw6!zC`0YcAEdGpv_=(<Q|w
zhj_7Kn2)i#+V+Ph{V<j6MtqKD4fyX_b`O7iGMft8>DGVNAoRQGG)7r>vg8=9D*j<z
zMdF^Kd7-$isf{U1!=c930$~y#4#yDh_t$N4IR39BCUHt}rtbZRXa57i+(5CTbBj1D
zfs}sm@7!6`hJ)BDx}e4R&+Ot+jqs|d;lXS{w`&@tHA*$w7kq$y(?|Qd5m`>6I?WW^
z8HS$jahiSgjd!C`x*Rt)^KU=Id{>7wCAOaB_-{ukj%LgIrym!aj9WHF*ob?p+j}e*
zWjcYGL%{1m0yq8-<?53aL^XjK)jzpN*GQRvhjg`NI%<^rN5{Kb;z|sZe#n|}u72ef
zQ_itsU9Rzq)dkmdk_PdKV(YY)`kM=$92DC}hcA8Cf8&YuI-Rn*Am!?8_vljIl*TZ9
zQH-p?D|3xH{zDD4<}v6^lp0WUQH5WE^sjUY0xe5<vA9gyiYS^T3g?wNPF)(=QKrQ`
zKdr~(4!2!^5Kaa%_E}r^JLBk`#5Sl>h$tG43vA_hi4)0Z@M4#yVv0+iz5}0*@!=cR
z?2?Hzo#M9m>%O`wZ66$_?Xsz3znAiW{UO9g8T+|z4-(Y4=iV}aa4RkH<@tX?Gp&ew
zyn4j`GwB8am`?6S!@;sI2a=anuz}XTrYqi!M*M`h@7QjZqxrTqUEFM;5x#2&?`)|p
zttbai?rO+(Jb3L<XWwE)6MN4;L!a~lvwc@e`+R?bTn3|QrCa|K1=-vv94*Vn@RVM7
zX2{dOW_zsVjcP-xoNRQRU;j{NGlx>S8Dpy!eYugCj;gel-g_<^iV*=-^$h|0E`9f(
z!mfhLMCXj$C)&@rROIeTiXGN@nFd@Bd`xYPPPw6@Z5z1`;P~?0&G<k&3(40{{9v+N
z7l2@3Jf(d~efqitbNJBE^UeaOd|3vc-vILlr<-E*-;J{(bHV?C-nx6v8Qo<V6|h+F
z78v#j)cF5|q!K`4j)E$nZ`}U?(5uJ;7oa;SBm#r_a#!6m&p_piD$4^LMe<TL(p)W?
zV8F~H9b~ox!RjerxV^`R-*M|9&H;Yn4a5IHuQP7k=xo@uJkZBg&^7un=&+s#^rwcr
zFm0;t-9U<2(LL}Q>o+8_N(SA+cY@1Oyj+x;*^@kJsd(;X4fJC^IT?&K|MB<I8}}1r
zEzAC~HY?`=kQxvWE5GrTysaQalK?cwqtx~lNp;LcrOLPi=8Sja35Q5qszi27I!jp!
z`x&#l>Y59DB}FlBhgm;1`&bK>n9*Z*vgCQ*?7aB@4Y^zx_2_jkN#{lBa^}hyd)`eo
zG`~22n*Q|(c4^Wt98J@1p}(g3Yxza?>l0Msv!^NOZLKiPqT=6+=ZB0HLd9$44&S8v
z;MYD{0S(lTBLDs4xN>Q?cz^eVna}o;L@`EI|3+K99k-ds@veEQVJFVFwVnM3pvHVG
z)n<Iz?1U_dH^)P)FY++a>)-H|vkSGrM;w4`L_~bzO%0qyHHyO%(4bCWmm#4J4Q|Bp
zLCvB(3JPNi^o89|Is<RT+W@DN5P#{Q4heH;^yO3YXDy+l=a?T7s({y&YGB;W{7khA
zHT2~mWa{yBfB{q1@^ca`?Y#X9&swK?1?55GY_sXQsrU0ug$qSQp4P9R9ZuA1gDU9Q
zPt@dYU(hC=4SNT~i}!nMCMj)gQr84c9xR>f_4yk5tyhzv<6@hDg*IhzQw6)VYaZ%8
z<*uitv-Q)V4ayvP&x<`*?fR&_c~cBW50kWuvw#7Q*Q=_kFxZ0*aJP~IFb9||_PEnJ
z{Ie8pJ6Z5idbjXV;7AY1sNm@<aHt`CP0PRMzU-;*+Rx{JQ8%2+i*lb2y_I7_6<rH{
zWs-6ODpREIvI|3)>GxM|8c|cb1H=>PSmfGY4R-H5l6oH{U`t<n=y%<s&Z~gnKl#A%
zvszOd*xV3n7}Up}DEmTrG10~D%VfE9ZNs#NkDhqQtMu*mzb}Gp^<=2SlmKvaS^6){
zr<B*8K*I&#jZ&O@j|kKSi3C||?0Me<_>#cd9cOrQG>`GFw(h&)1@C@Uh~_wn-%UuG
z%WFE;!`Z#Srmw|)|8jmAqWoqp0v4{&{o~B7_hdP-D=!Len->pMMa304Y4oDcRquw3
zF~Tu)*b7Arg7KttBN4|_4|Tc;SNz6#m^kivCr$Eaf@3K2?$_WO-sm&^1z;o<!R+uV
z=nZsp0el?a`sQSnz-`EdHYkAP9!ED3!}-JbQqz;O%tiN$UnVJaF7vm7_cn0B({=CH
zE({3W;d*>2M&sunQ#f80k(%2~&EY?#=SIn9N?=sIZ%#<qeot2#PKjvsr^>~Dl1P%@
zre7ea-y9_1NwA6ulx`%Ms&GAbLy{d~7zt*-&cBAg`*BzoGxh~;Wu5dAmETe=b3ml=
zXXWs=vpkX;GrwMvJ}5=e(>|r0Vq;&Yxz6|N+;M(KP5L3z>2ppzj}bQMA$~kS%~vpJ
zxQkN3q-%t!esxG71ivtD`@|HZnj&-bD{9>}JNmnlf@Z~|qB)5UU^5%&!n-Wm>*hp`
z*ptjwDDri{??T|fgEH3tB%JeBa00q4U2_Xc3SQ>{<TbJRM8F$jmp+i(Pa4;~ucyd0
zt;s!_0)}0bVnU6)CZcxC5`sYufWPfgBi{PRRmH6$uMbSYZ&w37Ruwc%FkKEzEW-0?
z_UKbmLElcbp`(trL)jRqfv>?`1ZPzhGc6yVHZ_JObs4f3f9?Fd87YrNDJq|{ibHAA
z5$jc#2yPce&bQkJh?m!$`>gmII~};@Rn%0<<>bE$7MEKP2jw0ncsd`K$#k++R$8D2
zNUjnhDV7VE5rA&_jAK(d9t+-V?oc2;m?F<qj}>N%*}r9k8M*xlr_53v-SZ&v0jNy;
z-=^O(t?*s+70th9z5P6FJr~Z02VJ9z^F>8Tc{Q)CVk9^e4q{KMSadp``8{6xAE?!Z
zS^S*3hZC@Iiy7fh-hlPs$gqt?@r#q>WD-Oea1ww%EJWG73rqZ?|5HVL*y0pECvKtE
zA7uN|6kZr!{9XNuDw=6)hr0CKQgruz(_-7>>)M31gZd-9BLx@ywTUoUVk>XNZf#kR
zi`2?eD8-E5+Rk@aszb-aM>oDaDpoJqd&!h^fX$Y&n%g(!=An$IyksmFLE5n?RT>$4
zE#QB(awPd$BZ`|LkP;N~zZoaB<6=nafbW_upFOm_xqb?a62Iojg-Yj$<`eHm&bEf_
z+Z8c^*e|)oj)XnvIAj;T=!eg!UMk$Dz$Sr@6K60Z;=A9z=}9Jc+1K1!arHB)k-Sj)
zy<g+%_B_juYJi7N7W>gT;rWWPQBJdjya?D>hrFbL)EGQgWyTz)?uLion{or#9nyMP
zz;Cvvg<OU*N_jU)ma`8-R46<IkCmv{pBRBRhV#*hhQMMH6V`r-;9V3CxYZHdkKl(J
zO!j<0<gIwqfnX=;e-O=9LyFCFrxGa0q6KnSD?mXaa<CYwA~{W2wY%7}G4UOD2m+qL
zJwXhWV2Qrpe?PLF)81G80pt_0O)jxG`T31j0sX^T`&wLt=mnhxX>6RtqorSEfa714
zYo<ktSD=*RV0!zNDJJU$M?`U$iW*P?8=gV7>3yi65!J>DZBm|=kl1#IkeQ~h%V@06
zfFJ0vbG9StcT=oDku8+3&Z9SQ9n7YH5Ir`j9wsDUdx$B~JTqn=O2>rU>V=i{?MA-9
zBh2kT#q`R3=Ks;+^ZSz;ME9vXDhf&%R8ikhHF6CC@T|oAx)#_C9%_sU1ZFCK{H74Q
zOI2Ovu=TV(<jG43-52jo;je>=UiQ2Nf(2zT_T${7X6#Fc>&eKYyU8RKY~)j3uomTP
z8MKq6nvTMEx2?YN`YYrf&@mdik-p`KVNPoBW=N6ZT~4b%4he2&|7bu|Htr4E7IPp-
z>#2L{!od5rin@tcLg$r@U6kDUvA%GiTG%ZS$bH_m!M$$*Y0y$)M3fktq~BN{IA**R
zcFctgtX;oa3Q*@ApJcRg4Ls8P@X$=c#AUlVAr%_m@Z_HwcU*y<^glD5Q(gIiFHGvd
z$HqeQ0^5)@i1jh3_$*rhC^=@WIg;e*DOc6I&fEpv4%9bn&z1eBxwlwD&o!_3OdIJq
zLcVqCZKMaZ;fOTQRu>ozPM`dVcLFSQUNt=hnh!H<{STO~tD)aYR`Uu;>|9<+(t89i
zLe7<FA@O}dVw?^;t|Oimyu<-_yRq7U#}5`w==YgV76O=Qv*SiCP<%{p-b^SVbEPlD
z%Up`Q?MbgC@}7JZZ4&KlgohK+^x>`jeaDYi@_2mO(=>(s(17XULl7$X5S7V2X{hFt
zwp^xv@b($0?NCHxUuYQ>@g#(gA=jYqe%AG(Zra6}C?kvV5S@wY!E{&|R&t#F@#m}F
zyK2_>5G<<UDlY&mnhtc=PWGjAgDUQMej2;lo^XwHv_%mO#~a@mL!0Xu%7oObAKuTJ
zci>FhjnDM1<9^KI+rMN03XpsETM@~RR1wg)tde5OdfT)jk23*a67v)uv`D#-5Bz%V
z@n7ieqQ*Dq>Iw2}etBZ>Y_H=glDt%h>3xn4@M@l~kjE}f6b6q?#fPj2I9!Y4z1yE-
z<g~1$o2p;txb@dc+<(5Y*`@^9!HuWZn>_?wdR!OXQ)>x<<1c8U4FWt>JC&I?rj4n}
zpLZBi>&24fMq$)Wf$g%i+7LJk4^K<D-diMtmFrWW(nm1!EWjRCCBdfdJwl7a&k10&
zp_TteQuUBq)<SzVIC1o%7W6dV+dE|NTj<D~)RWR-q|N&0JwauQV6iVGRq|w@w(47~
zX97sN7uS;9gWAS(!V3q?ak5Dzvua^*d%0-3LbXOXe;33obws|-@*HzKZ5)oMX&UZG
zg|NgEwKmdq)vtyC1&WInKAFBGZB`|kl*zT}39SSR)s?!_p8ymsIts{cSiZ#^-sJkZ
zbT)1O>4*N*A!X71X&4!@z2_JIqT;VKUIQtXQcs*sBkhYK0Hp%BSIKVHK3i2ldWI*J
z4*JcDu3%0G-Xs)+b&dJ`7IRJ1U1ts)uh@E&TPi6O5HG_NLi8vSQf4E>y2qXq04dJy
zB;Is(*$0<yv$j+=a)AD)pi$0F9~L$T$^{`m%<{hZd9~dkA)eJb3=Zu3Ia0mSFP}6;
z0MiP&aaBib(=5h=K9C1#JDDp{hcwQ18i0P_hnjp^yEKL8isGi6%2WCS*WN3Pt(1cd
zf)4Po3n2DNiTm2}Z}Qn?X#i(UGKzMkM=)1;4db~ImSWtQ!{mNNid+V@l?x!ti~mvH
z-0kZ&D=5eaX?nlV5Knl_M3^>pY(T`J*z326AF?_PL($Vz5mPCAu1iuJr63QNtJclR
zCD!@$AAtrhA5|VhJWQ6N+g?FwGy!;z)zgxF63yZg)YZ5V`c>jmSC1M1r~qaj0dkhC
z^#E@ony?2`3<lA0(C@TQ4Ui>#V>`Xq5)W)$`b&pIATCTMZcV~V&EUA=7DNP%ThSH5
z@|C)}A+Ghgf@p5ezN~Cff8}_59-hvAn*ve0@jQ)=r`Ou20nz-K{&h+w#n)0H539z0
zmUDE1DGc8%1vD(yzgyOEQ_vW$b!(eQB#sMV^)X$Ytt<0PEkfv^GSc9<>hO<7OlqM8
z$~J3;d6-|a(cTjL_ZuS|1Mqyz^*<TBp|FFPefFlk)v5fwF)qj{ws`nQnLbvrJap1y
zT2ngqWbnV>SDQR}AUdN0MyF#D=>cCdePn6SS1m<O<DiG3FHN@dKs!9N3o2ZNWi3VR
z#v86{Z#xZEBR%R2pQtxYw}tgHUNTj6j|Nerk;A65v&S}Jv;7<?9Ob-M1#1RobOg&{
zI%K;JRU(Yu@LU${X$vn3&1>n0t^sW7jAwAYNH?)6H=q`UROYZXf(tj)1Kscl@h@`8
zc8(IY@qtUo{G3JFbr14ey|PPWU{Vli{`HT4Z8Vz+V+c;>-(4H=NmumQ*K(Xq`Rm!e
z=1S)7d){6+Po6Rq0kA4ak5&n6WUg4r-kl7~e_GHBp)hfpd+pgCOvh2qv5>o%?3AZ?
z7!L{!GUG-TYF<ijmFtsR3;%IaP#`kXWih+`F5YoqS@U-MGL}>GT_DwB6~5uxB71lM
zyb-^GnJ8{^i%pv8zea(*XEpNMENXa^i8!^4AidpWtF=f4wR4<!eFTU46wZ4&(HS!x
zt2y;yGtn8lRY`sCPb|+nyyIzLb0CRk(u$JaA986Y6-P+hF*yK!pw`Tip&p0<M~Hop
ziUjib^pdHTCP?eCfzBSQ|1H3{wsEny*r^JdU$`u)kNbFR;(evERcTAEA`?2aF%|z}
z4MSwZQl#!P$U006seGxQX=uJ!E_{`hKqHePnB0ya>F-oG`vSpvK&_xxLdiMo_NP<1
zLXT?QnN{AU60sM)1_MN%gcrYF)+h|x;1ClT`Q2jE#{hZZBgx(OH%ES|y&qPLW6VSc
zYPSe(O?T`6eS&Vxi(U>sb}d&L(nzD*sCRRkuA_T*??6<;$=c1hRewGQ3q-c9s)fFb
zhe1BU6?)g(a4Y1_*E*y7%T<UP)XQ*pvr7^$7agatkjoLfYR6t^vw%<SvgX;XCd`Xc
zqZ3=^nAu9Ips}cDd*8Z4j*E%ym!Z#nNas!)x*ie?jC51IvruA37SqS;q^bW<KSG>=
zz%BE6p1Sl!4GjsZ#mw%dn?lDU*w%h@qYA<NdcMRJ_|ZI~@Mm>h{cDbn$`f#x%l!o6
z_R(`2{N)e%o#E~MTb;w;{${AG%WQ!BU8`XthU28TMc3sdYq+$7b(}C(Yqn`{k-DBA
z+;r(%#xje}b?G`KNb~>|#?rxo+leoJ5kMv<l4URc@EWJ@(-}Rn&CRnp544MmhjaP?
zF<XMd#SqirXP4KHA(b4;N(?M2fg}M-5$TuZ>>MxPs512N*V)N{E#tgjco%T-+O<Q^
z7^<@0a@)CfE&wIgZ8fGNo#|-$bge+T4Joy%e>3ZR_XzL^?0w@v-novfS^A|zxsKCj
zQxT3QxYPnBmL&i`_BxgcuR!_m^Hb3<+28nGNZtk+EWdip8^Wek^jcN|5rU)XCXh!a
zsPFjPKBAEI6FH{}HDstdh1y!J%MPgA9W7dj0dn7othr|R6F*LFyyzb(0U65+q3^|&
z;2-;_VqJ3m)n=tM+>E?Sr-cFtUTbK_9;R9{1fY4{tg&Ow{p$t56=4*gflbmRN_$dG
zZ1eCnOagphMF)l0lPpIF!00Ur<v0ncilFEksZ$TTwP&N$zZ$+;fjs9ExD(^Uu@w2#
z!V12+TwmZr70(_A_BvM*+_`u&tgsS(2iy3Vqh7HwY>Eii>x!?q(%fy9ZWkY_Mj+V*
zW*F_Pd?9%FIm-ewA5QT>(%Uk1`iDu6M6bEu97qGCckS|q-?XAPM&VH%*`Di^dRrbE
zEUp`i=XLF2i|sheK&mgSxiz@QQ?^gPNwUQ(O+tSe+LM*=OJ6Y3eU<w>T5eOa=}k^O
zz&zR!Yih>AbGAW{R;XDY|Lbmr;IY9+GM}v4sb?7S$8IYTTj?*P39#S(s5v`au1+Qh
zy4gG}yL(?>zkY7eX4uJib<NmUL%pt9?D_3Q<T&3Ydc2;PapF=_+LdQ1Xz0#lWu7?|
z^=gaIpX{>uziY%Am(ddI1<DW0Uui!3#NKE;tP5CPdo{d95ht5dt=Civ2~)AL&TNbg
zt#0#Oa~yRI+~dam`vZOqtNf7$L2kavt{NQ2CbetTIuZ9UP=AxJ60MA9(`aYu(vjIQ
zvF8n~eD_ywR5!<%?R@$Be}%#k@8~dsTrIN}G~4$z_W0Gl)PWzJL|zW@M;za%aueVb
z6R33z!o<AWD1C44_>I-3+h|cy><~BGgQr((4H~a8nh20+m;{i|P>@#KzH`&KU?H83
z6oPzLJ~`O-W0@s{O{U{$n&HTxfe<o6;VZ?Q4wl}dck`8$Vj6nMm5CgAxppUqB^zN!
zD`wygqlVanl;zY5+_m^3J{NI1&97*tjePrPPa%1HZpvdIiC$7Q0vSNJNbjP=wPPH2
zugS@T2vxSVmGp+M-`~12m`rkSkLYYSBE?CYU&;g~Zp_>iX_lyk8`HpL#&kKE(aX6V
zzd_^<a(=q(+>J&mYKSA+aw+t4o@ts6h0b{8n%zOV;9!#c==Gd<M7<Isv-QjMd-DH~
z7$1cKEj5%5)C9J#3gXi+X+Q>cQY!A*M4a|}kN4zyt16v`%gfKcNbk-@*6tZWMxXQ@
z=<zA?M5l~8^P}-JmbnR8t!YwhIR3d(^-~^wJy?E~fG<~gQKIXgFW5<4U9~bW*0Ja@
zAY4_IH|Uqr;Za%0N2wid*1rA3fpY&)&)W9B%wo5Qg65;|$WNCH_K#Y1oTtYnu#QnJ
z4-|{<(e;j}Yt2}2Jm2G_Hh3U@-1t}cu9cwm>9al5#mB>!Oc%DN;uG)JnHbkJIS%kN
zoQ>a*e1^#$U)SnCO3AkWmwY)~vhVA|{okCBb+)|xC+gAdgnZKC=2m%8JK}|g_6Q54
z_a*R;RW%$Z$yUOGAsh4NFK0b@g*jdi%!DS<@?i41y^7c~>ctc($+e6K+Xzqp4&z$h
z_$QG%Z!uj`s2XPXzvqo($}apmFbzFPuqE#O!5JD*2^Eph%P#8m)pEvG3vhd{U3vjF
z@dQ(sJ1!CB&SM#mCSE3Rokkc36Ju~x+WwGhb#PpuI4ka85l0~2^fxH{S=-Sk^tA0s
z>_W13T4709%CA-$-&g7tx~7Bn&a>i1e;s;R9T=<r2Wq>B8#5n8+KU<qMON_We__0H
zg?{rdd(9>yJ+w-s+Z&6c^_1f-b{OYFNOT!Gu={>yFU{OHql`&r%<^}FJ7~3{p7Z`@
zs8j`dd=oaFsv6MFTsz3AiUjpJzT^HDHZ$i*iGMUt?V#c9uQ3{S>a#l=Aprel{tixK
zc_wF+^5As`>e-wRrWCkBT-Gei_`ms}bk$oXi_5r29tHaqnG16nKRv5BKyyiOp!^L2
zZ*}3==WmSI?0Z=g?uqShuIC2SzTK@H1y<e6juOmc;`GPp6LsH;FIR{s$wv60{{z)l
z7I=a5(S&8xSNsiMiBXgv|H{%85n{q~sU_>*L#Jd7t9G}+JD;Jw4r8tlOt~|s${3H#
z%5-150{S%GJTtL6w$!<Y<821s^f&u_RA%GYB9me<pKRA3-_B69kx+S9Fmo__256#&
zZ~NdgV0^r1GagVdPoST-;v1=jE-Yd3zH;%t)>X%rSMwvUylt<(Yi%%Kti8GQGtzdN
zVT&?e9*@!MUsZ#}@)f>w)mk4>FA)H@i8}X?Il@Q}2k!LD+PwVgr|kMAGjd-p{Rw`5
z;6BoGd)PTU??XtAHXv-1lA@8eILORn+K&G!L4G<ANCs&$`RMMkBKzX9{2qV{F_W+j
zv1hqDw5T^55&<ulVVqj#4h+v%Bsdc+1;7yc;|dp%ebC(;O*kD0+3fBJWXhVMh8l=^
z0$c?<WKWr@Dr9K`tYy|R9Y=83fu3Zt4R6<Ef2kZ^nj2EzIWqfDAzG$Rg2?vf4um1|
zwX(fWz4)Q6o}X0zsU<i>gHpWjtH`fW=KR1)Z1M#wKz@llY%3Q*EoGzT5XcJtd7$|9
zO%v{O!o|Nyas}gpxnb(bGI~AryYQY>RnY_Al~XJ)_ELioLsbMw+;`j9RGBi_w?`rY
zBuvNcQ^c_QgsnxZu&Zj-=*B*b-)99|@gbS!(cYdj+AyjwKz-~#$e}jaSi^t+etYN;
zvLR2yqj|tUcZC4+hY|$FJbjPAR`U1^1B8mX3LwBT0I2*A?tzaxqYwR)E4D<`+l%_j
zBFqoT)AlYRa&{&E5bxhA{y<Mrr8_>?z2&a_vz}XB@*z;G3>~wT=<=tJpg#NxZ(oU$
zSuOvE`Xc$m9Vs$*S9%)&yU?wG_wfCJtVd~F-u`UvEWN1TrX3JVGRF-~1+L}lpr=YF
zJ-A2AAeHrQ6Vv{S8ol-+a(ug{c{Y<b{{vaz;Z6nxK{=8IBzMiox~F@&Z&-A`T(Y=*
zcVjj|q&zA38R$%x0IB2x@BD~6GK;vsv}5@=^0=?qD@?JdJ@yvJ<)&k7bx9~)^jX(|
znB7kqx^Gq@@EZFZ3W&C<4#zk4knp1nw_JnU?!iZGSih}&3CxQ`OBo~vpo1H3Z+?FY
zGf>6HtKHpBbKJ(^>B=JVB<V+xnD%P!+0moHR`YW4{pZxTKEEgNs9Km41*7r<HzXLY
zzJ#S!jI@nkR{sywB4qK_Ll3gUT(G{4CCow_w^J}D)^xenlk|uuRJ{_R$aTFOIn={V
zcZX+jB+FFhVGYwCA-SiDi%9kA!T{|s0|J=POU-)}JdJk|T-hejTYsIxfBr=UCfIpn
z1&jefPqT!i%BV}mL~!l*H+CN(t~;HJ6dtOe%k`KP%RMH#_eF$K%&2_2ls%G%uZ|_6
zAB!5uZa);W+V2q+gQvK?DBnY-TofOl#e?eGLNdO2TKcR!Hch8$?C04u2e@mcTGPF~
zKUBR9x_}GK`zzJkk<XVm7vdJAxc-{azG+f;(IDSsi%}oU_)g$O*^&b>?gfypgwf}{
zW5Izfv%9STCb{Z0$Em1Ie*EVZ?c7Hd+SB&knG$2LZBE<fxZ4A_yq(nis30|;*~nZB
zHy^{8k~+y2(2}Um^s2|jaEJtfFn&cp_5KdpGcNLf99?x>lke9aAPi7S0qIdnNOx`s
zlF}vJ(%n)6k&qe<0t(VdDjm`((%sVCFkpjy-{<%K#~*AT*zV_?b6@9*GKDWC#jr``
z0kq8cqgRDSIj_w5T$`2!wTW2NKyJTTH_;p4gpS$c`^^F#4&p27eCYms^@{JDB+Xqw
zF=<05Y2C_q$#;HDkcFV=e2UN_F(urQYyiJAr#!#dcXO&8h^(mH3(w8SRWaw4)A{&A
z<2x|XN-AiqBS(8wc)WuwtymM*IYLKT7(w`Q0Yru4FDK4>SrYmMH6$X_KQVU>?4`o(
z_aF4<0O4OAUTh_!cWAK41oA=H^XbUY)q=W2W!7~A>}G`d;JlH4A$>E?M6*+2#)Z@c
z{ftDePA9S|x66TP3DbvTXf<!lMW_AMZ0li36$2&@RhY?!obSFo^^lq7iKhB>c&Os@
zYO*kv4<<o*qXTbt#veE*v|wAR9=vl#V(N+yb&u_GJspNU%1K3K3ikNb9E5Z3OT!Ok
z2&Ww9*^Y*;h}5_%tshi?=c{<v*t%2Iu2T5>Y$m)){)RjfPujU!7orm*=Tt!kTxMv4
zd$hCFT(U9HXBWl6;YN^)D?AN3zz>(WLPOM>mi|rkb54>nVbaO^sKn=Onj}R|eNN1I
zMDd&L0pqy%Lg?GjOP;jQqk!3H(;sqgsiDoqBQ}#vcrq|L+tP-}id~;2vN`NTO0!3H
zFRCcK_GVPnI42Tr+E0@`Io9U&|G@{2V)#{q85V^=CQo~ckGy1vTqNJ>_pF8;84zk&
z7b++m=A>ZOjG~UTh-s8=Zwk@4rQ#0b&s62ZT=ElseT1*>Br4{=qVN4l|5+HaP`5R@
zpB4s`V~eR-ZZ2XIiW9Fakbj1p>XRo|OG=mar5;<6EK5Qgi;Prvv<LQ=S2lxW#Tq3-
zp_c8FiE&0xn-6P+=-;Y&rPZ-sZ}V#t$th{H#NKlA*Q*H;Gmo{igJ|lL6S!&F#tDh*
ziN$KYmWny5E9Z-+wtP3Yi%dhtgO{vU{}Eb9qU|5{jy`K0&L$qdd$jG00Pq4-nL<l^
za(WyzKTCLl;Evl<x(@_4XlILs{M8h8ddPch0w5bpelqmwcKZ#92a8EkMkJTFnvWv?
z1O1P;%Lo1Hu;wspsDY9ou?9qdx~}Q-_v}t9mQkdeXN5Rp$SDg8-X=#4He+`$c7~`J
zi`H4C9Vu<DmfrB~r4hatlvzDFLO%hc8$DWw#VYvbF2e$FOQ01`#fo`tS-}Tz+!G5{
z6Q8(<YO{H?ty~wH^4t~TR*5k@aBkP9-E)RacqWh(nbbA<Z`r2nvCvs1$s0R4u>1!y
z=Cfs}f8VR#bZO1dd#TYDBmRznIbkMV<P(kTNJx(~me9woIV1Vs3%FJ1;S-K6w{Ufw
z>_}F>HJORy@ynpU!6PgV=`5!!jgaFk3o-iu)u7*9EGv61l5*<50N(&ZpnusqfbK7W
zQ88@tAzMx>t_t>*|1r`OmzcT>cB)-7u4!%MaX7*pkE>4lovmKz?e~H3ZS3ImL<7AH
z8LeJ?r7IPM<_U_|Xg(7LEEV_GiL|DMF=;@UEBBV<!f5M1P^%2~!J>%?*PGn;WgU&&
z6diufTM41XoX;xeIjCygNjy{6tK{pB>QK9JQ`qq1X_l>8&tMOwme%ig-glg=vqR{H
zOmmeFvnL||jM-twnvcq>R-gJBSWmH3vd`4Z<zA5wRB7Dmc~qJKJ8UfmufxSu$Hj7D
zZfg^a5SGP(L~HP{(pZB7?r7TsQ@nKM^vg>VkF+q*amomP(cJt+Xkclcd?gAE$?4^g
z`ue_EkWpG}U-z#BI^B}rOpFRIiQ5OsN?Qe6De<7}ORw^3xe5Vk#}X;G9B`40>sgi@
z^48HV;01(&Z*@i^%F^ym$2PO%Ub=AZX9zf|8edRQkKd4FYo|UC$#@&r5Tj>ck+4d+
zm!I8-NAq7F@2hP76v}$Uwj+^~6Tsm3V%+&A-RX{282c7ZgkDkd7zF{&F|&zvjd9Ls
zcVt<!J|(_TIhXBzxc882J?~Q8&OcKQX)p!pue#u_mrwbRUWpvc8xN8vkjOe3bN00^
zZ1U%Fv|CBcdcU`nHMyn_oNk>^9C^om)HYtt{Pg!Pj>1P|4%*A?Nd%f7Dpw>m(#5=Z
z{sX1jrD*si&o2GtvwW9Vak=4*Re%=ymidD<`Ow(djxW}MuDa;;LtF2<Gb`(~Vjsah
z<<l(K`U_wmG_(H;AYCd;9KK7KSCfQqst9vyp&b55ZZ&uSX}If5zu6v_G;Z*#ES?m1
z9#0tr>||0x7b=?WxXB?Q98X<*G7&F@Zzv2LTZVI9Bm-XJn5AlpZlgS*UPBgBc<Xlf
ztxo$$l|YrPOt6P0S38qst5tOau4G8N%+Tv^dFOzG1Go9@NsV->rqGJo1*{JLo|CuM
z>4F!vg)^=x^x%OIH9*m63Uu#3-^5t)-g>Chu%bhPW#tg+^;&iD#>sQXDbue1bj|1A
z4baw8!z8SDd7|C@9G_x{MtG52Od(DS@YD8=N<DMpkwkN?#LWhKx5rW9PIuzREuq{*
zPdlIXUw>x!<y{ibqHL0pLzi%&M{zcjpOk&!aRuNg(#5>oewPqr1XBiXaRl|iSE^0)
z)k-_9I*ozGJ>d^vj@&y432Yj=8Z44<i%NZ8gurP>Ju<iq5^6@r=f2KzXg}NVj0xYX
zHy%1`v-9u=UX*hKrI9C8p`ecvGSO%7aUmdHrxx3V8kRjbpCo@;lRl8IXIXk{1^rA7
z9nxy($Ww4<dIWgg#?`H|O_9bK{=Dfd&ZSs<mijXhef(pyFM#HvVc}*$J+_a=do0@J
zSMVHpm4MGVt7p*9{UeRZBFto)tM$}t@HZ;$c(r~*q4UE;c?oI#t#a4eH&?^(>r!l%
z(gP*Ym*1X4>kY40l!04Jh{qm5Ve|Q$GbNoPV+8tTd1K5;=6!=W3P_H_o<p|RY^DAJ
z`I1k4s2nUuCw>8n(GLJ|3R?4BgPc86MDA2FCnxgKciU*<rieyUu`dkN7@70-^0Zk%
zbo7X;tLR)BhDM1gQ`h_>TKSM<F^`NW+Zo;NoW+2Z&Y>okPfzYu26yhM9t_s24Mdw}
z!P7Q4z{67E2l=4@5z)qp3+hyX?bTzIYTt-%cgigr`mr(GE5O6B9yRgv_2hNFc)IM`
z={Roq`rY#Vjd|pz8UwAn_;2X_jK-0)A>x#$koqb}GYD2H0-LfyQ36Xi{}3rJ&)3(0
zVGZ}dT8nuvVQKsG7B=n=btDRou=S^a5fpEH%HaqfH;}fWx3jI$LB2idU5dC5W*pO`
zBK#r67$sRvg);yGcsI`)z&p**uU<04=2qj0TPtjktH~^uvxDT2$uF?uX`JqKTqV(*
z01segj$f6WQ$IL(@K(F2!a&gf1KyN-4yvAS_4b2?AQOrv21a7<=;^8zRXf$6w7$(I
zpx`kyY#SST`NKb0ahMGwF->IsM(gXR(p@GZ#)h+Lb-gU?)t%JbC!EQuc6(|dQ6S@t
zl!3|eS_QVwJ~5XTotwXr>3T2Fv3wsd?qg2EyG-bT>B<A$HuS)_vy&eF)xo<BUG7B?
z_dm4C_psFG(*^-uo-n6lmRyrkMVItXdJuPYG*8t43Yysquk&~paZ=^3-37WXkq=?n
zk(O>im67kxw$-gVFDSyZ>y_U;rztLR0cX0T=DuG1S$MASqX#1`7hqNWcH_2(KHWG<
zH7oSCMRi@M4~h;2P=H@Q=Y)H@7d`@m2i*QPX<!JudR(`p?<TC>_>tCuQBs>-fI8(s
z%38gqiGAz2G6ome<k{Pu8*esFk#}tztHOutK1c&p(x+c7voo<#pj6{Qa5kJ=)KCTr
zoX|rpB;;v>sL3()?jv2rUZd$xE}CGE?VK1|y;;MkQ~q24+o1tvqj`H-&;3K%2;Il)
zcig@mM+U}JB9DU+f>7xs2kqbhS@<ODGT4VI@6GXgyqSE@0T)NdS+u!`U>U4kxioAp
zC-i;Fa=6m@!9eBTa12;u>(ORca-?MSGD545^Hx~m_vY@Lk1nNA#iz8EZ0UZKve1Z*
z7d1}~c0h&@miMj15=?l>x?N4oU!n)+fusF<%dExZ3CUWsH3GSq(<1zL^YfTlXwri{
zj;6ncin>|QgIQLPWI>tB6z<JhoSxp<!(XRd(KrlqRy&;oEiX&D)X4(i<1A!OlDA_p
z)*LiR1nY?fBqP@MMEVT$NnYqpgxYV1{q>K_AA0G0Hq!Hy#&7)@qzX=BKxe3R<iLQO
zy2cY$_{Dk3@>KrWwBhgyDU1;0ws=K3cxQeFz=ni2+)a1z`4Y&Jh1zE?ZW*ul*j=8f
z#CdT3^IK8!Wx>o(k`txhT|KNomI90tp`#1ZP!%{*JsmtEa5=V`=g=a{0kzsZl!=lr
zUr?GiwodjKr0}R(6zh5`04{c{tdEaQdmol|J}6xE>*X?R<qA9O%hTJi#E^@>q0*eK
z{uyqgT$$f;X8)d+yeV4n2)h}q=x?1QzZ_ei4P^u%%dcDLhE9mPqu|ElD*VRR*TVMZ
z`-Fm9Kqj(1O?qmcO9RVZ9hTO;au9f!kPIQGB^vGXG(=aUQ$Gq>9}T9=E-Nu;0HUQs
zrAuqb)muwzZf;a{)EmoP1{pmb7Jol<xP}~OlL5{yaluPCC>`wRnd@X?yMYM_o%WRq
zevmqF8TYM(ki8B6HHau9uihY7iuefY1@Nyj140s?ibkk+9DIQ)Pq|`<;n5_Cmwx0=
zsNfcGgAUV<cRUp*9k{~#`f>ZUTP5sVHSlbDcB;N%>r3?2s+SRL$?pN24kOemJE*=<
zf#gp%CjOl$a8ieFm(ka9l>E;*>qibS#cke|yOcUv9LppOG}95<Ene?Bx3W6zNsQxK
zum4tU{43{s_pOkDy3N&m`|;jg3AJ!=+j7!L;H1!E`Z8_CSSdNa{aNL(&1rn_SO7Sp
zN}0Bb1zZIxb!D6WgGJHfN<Sjsp-qTm_B1$!ymQi=aIoZa!F|AVc=z@@4D@4T!>bqB
zS}ZW9l!T4!*bDL2ltYC)7X&dd@MY9I-{Xi~zkN-F{F_^3gKx{|_Dum=wBJ47C^`RN
zFi~nSBSDmVzQR~il~lre|C_CvZq{hwJ4`72JRq4{WKrGhSZ7c1I**8@c;90^YtK&l
zr<}3<NkMR@u&Iy>f5-Oj2dVYI=~&Am<3ajiSGuqq-DTUp%9R|lM-iV@J?j0-vXIY4
zC*i9`-5ENXz_g41g9J>M6?X{s8<U_z4yb?{;V*J7tkyqPiO~z{bxlm2(yw-xX)uqy
z+zBZt<`kr8qWc5m^d&1m{-%CT;ChQB-=6liKMVP5e70{GcvJvf0eEp579*-E^e~EI
zz%hu$YFKPYf4$@swqGkmWYtM>i{w83^)vZKV^k?M*QO|NSeAH<FECZ8a~`u;J9Zx!
zjAi7Ub@X_sVG!A8GvML+N%HO!Lnyb#Ly;|cO}$mYv?lJ<2FU-dRBk2H9R2IQZzQ`w
zd_y(0dHNV<Fwo!)pRpSKLs`XQu_6Cf^gd>gh7T5tG<w}rD%vB3DmMtoBPe4)|7*BF
z)}O1!a=p%V;iFeoW`px;;t7%fxEWzgQ&n`avG6V-6X2VRMi;gJ4X3{Zh_QK2S*gDn
zW!R}%9F4xyb%UfEF12DuG~2bw$I9rYSZ7XAcPtFuUntAV-gf6BZgKga4F#6xCvRin
z)clw<Uu#tEPQeTcA-_E|&689;{T}Z|{flWp>`?;y<CO0++gc6U!AQa!qr*3zJ$Jgs
zJ`w0>S=4cn-duL;zXx29@<YatT30LD19<>}VOas+KL+d%)F@G#B){2U$J!5328{F<
z5UZVd87BvtgwyN41xw`NO6|_BUx#+vIW|>hbLk*KL$Z5WU7Ey4yJ*1j8gHVy3w*4|
z5K-2n)XWi;?QzW=lYs`mbB;?x4XL>iJKizzxRX@A3LQJLV|nlb!InnE?AM>;xpTsA
z6?q8}{1?l_O(SCd0mq7K2x(8{JOXEDuF6Qe=J-rh)=~^|!MYpY1YT?Cn<dhNzT6Sb
z`=@vM^TS(oQ9Ss28GAvn4|$Zu1v6`ia8{N}3O~2^^KYSgW!@Y`Ukd}HJ24dWWdN6V
zneQh2+W<M%^ZB|o@B>?JrQD0($w|K~I4^D;8E&Kku{6v{41cUwrDAkXSfK3Q7tp}?
z`C}c53HQK+2gf-iMJOQI+P^Ns^w-e4k`nUZ%Ah1RZ=9F4zX&1jw!HTB`!k9M1{PC8
zm=hgZ#3aq!k1^ML90YaWC)c)binCYf71nCEkbU;Sv2XN2e+p5yh+lg#;y#_%g?QF$
z`&;W))+k*yA6s$Kj$8e)w0y=pQ-xs8muk<zPA~ZQM^?(oKDn&UJo~yF>SR-uOdFqv
zN>U{$W*^GF$lnkEx4DL-POy)W4SLM|b}O1qBH<z5Y^DQvE)r1Kj72bi7N|R6|9O~8
z`pt-v8w3-KU#T#C)em8H_Sox~O%pbS@+8`zxf%H}<6Ys8Efbor%BFOiEgOe6r*Vvk
zDh<L~kCxF1j^e_HCSZ}J=1m|Fy?%ML!yR%<Fe1C^9L4=O{HVTIN|DMXe>yxzS8c<-
z5k646JFY{mBHA2%pSbCU78hoD8`68CyL8oO#K7tcJ3kEDU(G_b0@SvFU)OnrA79lr
zRj@XCa(tZAv3MN|du@bcoKC?k>AniEgK0a~8@sPiS=if3N5TSrRH-BZUz`E64Z>XY
zy3^zAf#sk!3{{_$)AK#TLOJZvrunP#i{al?SY6_kI7QvhZW7j`kNb2HnjL8!L8=x&
zK%kL_(FkXhgS&><p^|M-mM0mynH5R#W?%I5<ur?1&~NXjM$naf3)(q~6v?&jUK#4_
zhebIu?^pNO>ac$@F$xo|ErN*AMCHnw{(-SM3i8CmqqUZ0@jZv+ZgY~A=AowU@NwPq
z+Yrx!n;z<2VbkyD1XN%kj?B4D;pkC9Uci)$xdzeO|3EMqk|MENyH_LKx!vXTFk?pC
z6r5&mZF*jP{>`x$9jke73VQN*h&oZ@K~k|dt{+M*$9<UlwwgWmu=Z6`dRoGj)7xy#
zPwJV{Ve61j)no2_5?;y=5uh=Y79$E^xIFY@U8ef>Z_14C;4ruY*9{XqdcyGpTed?*
zq;!sd?{74n&RoxhOJ`1rw7l4@OEhf%&9k+#JX{+6tPdZWuh-NuW0PtA@5Qbhe@Jot
zZ1(-lrC~b5H*QS`n?z#maeyx07vNm}(iv%wEF_&k6al2MPXW_*J_~L)SxG_CwuKve
zx!NA81dGzdQr3S)6nE?$NB*QtZ`O-@bBhRze^tKe6ApqE7Jvmp1MK{axIk`FFa`p$
zlVeq<2h!mA8O0*7+{DbVoA$ykUZJU^;_EO*6TeXoEP@&D_aH02U}8b-;>x1@6Er^*
z&B<S~hlR0Ia85}N$dv!igJ<n#ahHd`WHvRmLrS5uT+9)>Aq}H8Py)F1o5B{wv2g+~
z`Io2s_SglZFM=hf@MJMewR&S|{eqKu<`fI*-EVqxk#N+EPgR}O2T}lyr6xds3aAc{
zdB?y;JpWcU_<~>V_Pe#z5?#WUd%YJLh<9!rj^n$=PP;ySp}34-xQYb2;-`!ev4kbb
z)|p#3H(T>`{ON#c9J8qaIa2KaP#RZ2)VDl29IMb~r{GHlRqMqvGe<w<kxZOu-ea91
zFCmlccdn9NSx%1XF@8&%aTgp0wl-O_WlWMT_z=~Jhsp{Im)ga(lj-E!NXF&<fqmuY
zpQoQbU6e~W;`{_4i+)l@HK-g-9}?0bs`rhw2w<;*I?%XPq5coFJ&$lH21a@Uq2U{6
z8@4&}Bj#tp8^AV)3%IDk;+a?d(-J5IZ{gPmIvX4|FyT)fCOUu#&lFTYo9XIKIloiE
z?p%<c>h+0ok@>As=KCd9U%a$7<)C}GT@CCwsIIHp@r_4G_*HT&lgZPi-V5kDXV`v{
zen{U2Dfm<~;C}7Fv8n}GeNU+pyPEq@TV4Y`0{UfVDb>zokjwz{c1YpBBn{KYMi*zU
z{ecgTOl5~uV;MBN)gxJo)7K5_xUaA{&Q8j{xzXjy&Qma+t(J_NDW3%O=*8beQ*G-&
zBH@*Im*$p(OS%1-lmn61SaEA1kFtPRS)T05g+VC>{~xxdK%%%);2ACuuHf3#GdK*8
z1+YFy3Hq#_K_&si;jOL}f8`sBT;@Y8KAtscb;@$Ga>N}RCR2w6lq~!T*O0(s%N6B3
ze|6&GO^C{H<dP1j@o_T!iZo}hk$Mp?^ZB3fiRSOoEmE)SK`T%oSuLWXi-(O7<K4A>
ztW+hxzOw%f_tmYPwuMIsSbVecRUF_1YZTD1=@EJLh-4Cgl<<-11rPRDL(D%KBY2lG
zrZv`+v~meetJkJYf0u>%p&!3huO&erB<=-pY_AyXmO18233?2oy}!+uMSZ#nMlZmm
zcEU_@>;sse{v8Z_IMNMQA4fh(g`IJR1-&3_ybo?z-Hds6R#dg>>Mn7SAC|%@!Nr@J
z3XnSkQiqH2hL>&7GuG=)Pk;hFChbXN*f3F1Ib{3AeEGVJ9d|U1j4l0|QAe#m`ffQ7
zx%F@6bEWr0{3IiarUK=fx_pOzecDoJ4PdLUwUTNP`b9KVu{q9id-A%$5QSChUF)@s
z5rddvS%L_5d7-y2Bv#|13HxdH>PSfUsRt4ZfoW11=|ZN!7mB6IBBS4LxpF%Dqc^$w
zv(N_24{LYA|9hL7J+V~yovxYf#~5XUJ<%3MGm+y{^-i(d{Hc6KsQ^Ih#}-{?N#KF`
zGfA%@s|lN#jQ5k%@1MSx$6<z(zw~T4@p_mBFyL<WzO(d!lJ8{@vxzWtsm3pzcfB-9
zfSLXgWoC4?*_Z5CZRMLH%xW9N_wV&JfM)3xAzGhnAc^5=;6CJ=^T*Hj>wrlQ#4&eD
z3<N-xk(ZcsY`#ws-vcxM&r#V#(v!PTYi~#uC<Wb8|BU%=Ud4bQdNTknfUwR50vn9F
z29;X>J<}Z8_>`F3P@Vhd(>ZyZ+>3^ZZ<VT#%Rf{?`F<uHXL+>F4&7P5#@rYc2fg(+
zj&%ils6tuWt$Y{P;caSIo=YOXnb!YYZ!Tul9F}%)4Yy9uD4tW6`Wp*;0G_KPHB&bO
zwpi;cA*|x0+lVMpWyB3fe1Vf6_@;5!HJCGO`ubPT<ENr|)CFio6E+~4-K%aA8}0A=
zF#T#(90h}<{V#W+0Va&Z;|Ee5s-<K)ok0jAeavbKt|GJ~%fi?kpK=sEM7tz(eHLR8
z?)d@rA1L1Ljt0$c&UX=DO{azA4%)maa(Bl&IzN@63Ga6QL59r#FvO_M7QvNP3v60~
zW(_9mGn|Lq*IR-rH87pCbnt<xu#?_#yl#It4K4I=q?N>b1O;n=ZQ3)yi)M%+9;jyb
zEE(&~-(-S=dVti;ChN-;afY~ixWqTDuM*N9=~xGWW$9ZFn*!Pk5{tA^5~5{qw1#>Q
z3u-o^AzRAnm!d|Mg8_IMnz?z?iYbXHy`kac{Tmu~YSdxbsP)(J7&9lVaH<~Bq#I{9
zSI?AKTvWh(pI8b>W179{O8NzrqzS7txKK`(UQ_Wy(&vY@yUS}nBOzOO(<a**3>sm(
ze<5PQPnM`?Ri~K0zvL^3aLq3=B~dibY+~3hTYf{dQO@T%(bzEazu)}H^k-?XXODAn
zKS1KLjikRIxkr(xzaLuR5dG<P0-LB|lJaV!92Qq-3B=P?aGoxBTkv5NH|EPI>ZlMe
zpX&Nbv*S>=nTwooQ=yLmWYe_W*U)D66xk5=oOYvFq`83UK<tDxOeW6lR#_O2iZYty
z`v_~m&Ub!mq_cJPpZ*5;I@2VnyBwNZ>NdI4V>@Y&P!o@A=GtAx*cn9>8CL2vmRQ3_
zJ#@!!T+&AwjW_JuCAQ7^{5*(o;C)3Q$|cWNVAhRHltBaBK_2h6!O@TN2t_l&AaDuY
z&Iw-*i}5(uIR;h~DN}&*WSHh%v^i~&<(O@e%VU$Ip1L?`jV}+cWHrcFUU@iv!kQKZ
zO@sRyd;b|RvXt3wgmP9#T{CwGjgDZ>K>$a*ykA@pNZNpHs==Qf0Ddu`wUf)3*VRru
ze2G|Vc!Dyq9P95O0s7YSC;PzRqDKu5UkSfO8=Kp%`zA}i@lbKQzL6DCq66Y0v~iiT
zUj4gz-_r#BvXknsz#T&)4_>Ur@lSV!1%2`xFnVph@hpB)9mum1v<!mS#^y?bXT#Ua
zg%^$F2G02_l8O$U-QT-wl$F3OoCKcKP2wznQO;BN4k%qE+7->}t|qR0=<aL+8=N>{
zgpP_C*=IbxaEX9hg;V&5fb~@Fc^*;PlsDN;ZxAuDL(o?|sUK9}LxX{?iyXW!GNbCx
zg#j0Rvar7~As^F1=hPGx8(9b3^EMNU3r$_S^$Albk$ArbBK|22pk6<oqILB5jy^Ua
zcUKG%&mZ&?`JT+NIgpAETNN*3t^W*c({vyjDrI<sl2y=puVeKd0!9{kd9|c>0_KJ>
zy-7%B@Q>2cfp`n83*%;#ypGvoY-8`=HLcaMuaat?mA!2l9@u|T{qkS_2l=U->yE3J
z(Vu)%Hz0j5*f<r<q%GZktfZbnv%LT=R+D5_y*ZEQGKqEenAh{#$liUw;2eqqKJEy|
z>|<{5T3pzEiiVn(avXNqw`Fe4IK=U><(;vQNdN*<|CZrr)le(vbA}|yWIg!v)jxcE
z|07c1rNV7$wpdFH@PA@?3jXc0D^Ro@HLGHrj^GA|Y|BtBTMlu3UXV-};DN^>jmzJr
z@i5GxI6W?qwRkw%(bk+AIQ3j@MwzxG?Q-vdbN-yWH`jCMC*sr(sQxZ%wf6vtSlu4`
z#Y8;|=9eL!znIt9wvrSq!1Ku@|CkoXsPz7SpvA0g1}41$i@NLfnZZZ0c!9`brtlse
zyk!$QR3oEK$2#p8s(%dqRvoQgcOYAgCvH8$h?!4$Vbj@<2PgmpZnc?P!$Vi=`OYpZ
z!e7c<Q|MJ*_sd}tJI~w!?{1?kE}sUMUmBtCrLn6#`QC9xt*$Md{?E>BZh%>ero;1*
zxWTO($ujuQszRx;M*1F2=3S&u)_E)F`bB9VkvRBCuIY@be{iJe=xb;jrf%(4;X7+o
z>WTEIJ@(wf)wY?L;I;Flf>7@77Qt_u^@@;)$^>XoAn`TFSsy|n1>mdZVZR-rkXe#4
z3Ea}<Epy=CeELSPU#4s<>gs$3@U_rYE0}+UQy0Rkil1#XnYcRwUeQkV&sJ5(+dTbM
zgc+OCi`?57sPa-r^CXu?kx?AyXg-3SWjGuNe9rC83Npu{zF??$Wq;1_goRCPMDjR`
z%Q`BKq>>v{DrK<bnO^ZnY?%YL&if^^LO=c+x<wE0T6yt2Kk0<Cd9JSQ{s#<8rH7e;
zqs3PXDR;@BwA0{H&tV#3gKr#HQ&DtIlqdBDALXGEq~?}DN<sfqrPGxxZ78HYP5t0i
zgxa~1E{XcJ3NKl3-lxc??MG>qG^We_PaF%$(#EKZtR_ZH-d5(ON%fpO4_77gk4~mk
zCFyQ?UNapA^JYJxDK!}iv}uhd?rBt=a2KRin=`qevcQlNk-W1+5AT4GL*$hej-VXb
zUf-_LZ~uYxy_)kh1D{;#c^D+#I$~trnv((WWjyaabHp+=&q5}#;;onFL$z_rw!M<c
zKb;<@gu)LhBwAq_md|p*-RfrlP@Y%o>u(K)i1>HEujqx0R4av?Oa?v$mBjNJr;=V&
zH=gUXKBkO{bOyh(z22?lMN%ewsudp;7Z*14=GMwQ{W9cA!gh64meCUszU%$vNt4v2
z%4t)D261e`2^WZMN=kRgI=^@w-F7nq2wU)HraV|T9S*}+zqM1QfJIqKDtR-HVt0FW
za4sC22dL3N&_LoU?if<*K3<Kd{6lkGfEO9S=%y(yg>QE$PS0jAG143#CILR-<AUQh
z32;tpr+{$!HA}>PiZ<<U!)B*PEaSo?!uOeAbt>r)M?8HOH_fGsg?{6ymsvh8hKPHA
z1?fu-d)@^68Y<LOK0<R#ICHZ@sPl8Zi>)Bg>DU!3C8XtylN3>0hS289Hy;(uzwjq%
zr!_^}QpyGsF(oc$FTA_?Te^ZzVdbRU`LNsrt$#Z*yQpz3^5D<uz~JJ4Mu~+ml6_^`
z7|rbdQ~ojH6iW;5{8`DeE-I_>YY^YxBoddpd~T01LB%^Q%T%RvK{%ZXtW~Dr{ISKC
z0;AR~Cz*ev9ck?KGlM&OHYh?X&dTDp2Rleu8BLFwG|#(pXWjm(cPx0@udnItDJ1~*
z0~(<sqc7oGr#R;O<%*mqqny;wboXH@rop*h;GNGYLu!X*I~&Z^=emy)I|C_F0elS_
z?j_TgDyWyGhjj;RZXM>MRrJtH$T^UMb6*ClEdjZ<r~MW$vS3G$nA1UyS+4tm=&9y6
zyIL?Eov#8`;;kOvwk96pj-Y{e;CsSYEORumEt_uvKe&oW=oZeM-nJ?J=(?OmPW2Kl
zx^Y!mFmPkEkC*|#_$3)xVmJPjLz%OCT6Nb1=>$Rjj-Olu5C`Y~K)+v491RUGUt+E$
zpOmiB*Me;Ka$Pw9#euLdqMq+`c&4k^04Fln6aAZMs;*y5S-12+l#mP8P)M31!KN7&
zwvlLWBxZhl%Lc6yD`!)i80TTtI$_8-qEWW^vFR(xU|&NK8DBt5G#VJZ{{NnlY>?mj
z(%_NVYM#$lhe^$0fHBv;e&^tLSmSM0Vodm($<X)s#?qI{4^c%5el?unvdZUelk3{h
z@n)@?z!`^nX;HV)O^54KnSrm0YGEQ=;W%-`YWl$nfAn#`4qol6IsGR1;G-FwIu){z
z&!7)d2sqBe8}=*2LJ#I_whOAhePAmMi@sjaf2TRgq7&<k{@^|JW1sDjaSiNxH1i2&
zVp68tcq@VLSyqzID_k*SIfQm9pj!M23vD=_%1g)+c9IoHAE5X66-xV1Zl70E$JW82
zh-?$PbB0JaRK9W&>GH2lL`A6R&avPt)h5C_?MZVNe{}eEtD-9zXQ}v?EJLNs2F#Y#
zhs8<Ytuk{j2k!lq;7>HMiELeGiN?^vj59pvNp`o|^p1NBT(k^z>*Z!OcU<PsD^Qfq
z^jk}=xx*38wS(#$BTkHWl-@Lax9j{=`Jt#hCCqvNJq;?})U(d5<=yOK&(__&;h5W3
zGhQ)8h{QAj`P$^c)rO46jo|ZQoamV^zbH5ogny1JK=TuqoqFTsX-K@X6x>K*EJODS
z9H1Xrm)~fFA(fIxMmwvnI?#H`G13$Cg!On9<&rsLdK2Q?G=7eO<C21FzjOrOKI;3{
zs@Gv3-@@U@P*Yr>UhG>UJu0Caj=J1d`A`J<m6j{b-Q97PH;vk|4mfZ!_?MF>m6qnI
zICSTGQ<y0q#BDQ1j)n3c`!KJ1_78Ec#K<K^hPy*u^%TaShu=TvZ3{4e23Ff(;W{-W
z848+R5r4xIzL)*n)BkrF&~xCWh*W`(U7llRSRD8n)Fv42@_SxL5QU=WsG%j~Q3_M<
zwjIFgTe|QCeVd@0sPh2g?2;`Uk3>n=JObh`1z3?jgS+ACB3ZKEo>(sysKHdCy*R%~
z*1uYCpdL!`4Rp<u`y`=cA;&JZN0XMK0QtbeR$VEN3}#a2BN3Vu@?lGm_K<m6Kl_=w
z{~1EQ2s1v}u*KK|QHlCH3C0sxiz4UlM<kd3PvVyO6!;eQl{~gDkLse{)o9$=fC0DC
za(GeoTU&-D4p`mQ@v>19YCs806fpKET5wFQp79*F0s7V#@O#87x9ixhwbJ;pQHYrh
zjpHtWuL*_fY~Y{qJ8+-~E$4PHv<k>O2UvY5ggbV3&PB`-Fa=zo0cjj(&yI2p{!bAr
zCq`+2%6d1$D@xkH1Fh>Rb#xZ1HSf<PlK57mE}sX{dfh&ki!opXfV0W$6`flbUGx;u
zPJ{A-<ELPIkSNVLx~3F%tfQKB>8py?!Aw<KLsfE}^;#7=eE;r&$0xBXw48o1m}1}T
zRyru~K7#R4?|m3itM7iVj90oM7qWFH`h-N422a)Uo0VKp!JM%Arh2p063<uoKa**-
z_dlBMs=yD|fFBtu6eRoy(VzBl6A$67{PGSH7SFtQ(FoS^gs%!!7n?Le_TzJ{W%n-m
zwB0g8r0ubc-)MFS-?>WcB--o$6_vh^!r*q6(39~;wXq#4KO{YON<joz(Pc4w1B-Gk
z`>e@K)=dmAQvy3QTE)5$22cO}7Q|6DeaGRu%VQZF!@bR@>@)5dEr)z-7}J2~^hAln
zzx&ZRjuGo(viMGfoD$B^1UY@HVoN=ccWK${$qZg|k>>XHq3RyDo_u~Qc!Xz<MKqgC
zf=cT`0wFJsiEkk49DQ~5>y{53A5DeTwdqp!>N*u?h4yX@u-NkGCW$=fHy@}xB`C_Y
zFGfWP8&-fNarUju;Qugld+f3~oqS`GVh(tHX0rUR5DLN7f+S1~{4`6>do#MC(QC>D
zn}w!t%CliDYy|wSot|4ZCdcu4bTg%4Vc?3atcYQiv~nR}1vt00ZKc+s5_ixN1`$n{
z4lU<>D7=425<AX{o?nB#Tv6PV8C3rsqWB00Ggwm5lEODXKUS~W5>i-xfvdCsj-_!L
z+wxBwdK_05q5I(($v4jrmG7+~X2FhB$F3|oU&N&k+8RVv*IrDR!3jZ=Y2jC<1$490
zqhEza4P6%$Er_J+S|ibO%UO2F*H(UOUi(>cENahywiSd1oXd#k+<=5fXlp5EP?pba
z(9OD!|0<j5=48kcGlNaH2+e_QuO~=Sma<NAQQ3`I!B<P@IXl0(YV4{AJ@8|#cqLuu
z;lpda^FkcP%(Bnr3>}ziY^ZV2J4GT{5@(YhbJTgSzsKc#$IgsioRVd=`MCO}kkmf9
z^Ala*bl%>p30=UvD?ONs4;wN-9x3Z8^hPpdlq%QNQLfa%UN$(<#&;=BX9Sr<web|(
zG8I`}R9<rdk_HbC<ypa<=B*zC3~pTZS(lc|ltjrR^4ukTNiU?V401~c-pGBy?=m;7
ziL+)X8)8gN9E_`gN?31pRubQnXP@)4bIA^2{wCbar&Q~l;Gz1)A<!#P;fsFAQdv^O
z)Qqn0h=Oq74y5%bW5O+v-)!h}=R(d8&{f2iom2%HCgPCHsnE6+ZE_R<-WkQa`JBiZ
z4;&|OgiLH;LpMm&*|EB%{c|$ngCjXb>*vN+nlw4$Ff1_d{`Lh5+UjV7|3Fo5Zt%jM
zy@+fcMJHX4@Yg+9G>!#owwW<n33_HCg=rm7e?Q^1YI7QM<Bmp^s(ZT0J`j{$jnFtb
z_?fPJ)<u>WJ7n;)UslQS9j0ilT0v6p*W`3OvY#0nB)77tlIUdpCJwiB&uxp)WbotI
zX*S4T`iyP8Jo`6<CuU;3k)LOI{c8fplfAm?C;PrB${bu>tv@SB$cb1@sE$KE%mKL$
z)om&nitp>znQ>glC9+0!>v>Fn8Mb6OVCna>&zgS~<=;PkS5;3{Q8UE>Q3-Vn@TsVH
z6z->vD+etvH1!bp!hgW|Ntx|)#fl2Q*omMf+-1Kf_XQtJ!rKo;gGhe?(bA5$R+isj
z1pk`)$qMczb-{8jgw6xuIHE4XmnZz%^dVg&LwLd68<|q_z_#U;CX=yQ3vkP|J6CfF
zxo6;-Vh9&1>DAhe4FMQIDxDtACDP(~cyJfTOFB6V@e_G*A9{aM=pbcQ`-^5GVAAE3
z?st^iFrM9aEV#`7$I)_*18HhPYG8f~!J=&-qQm>0BZBBa&G%!;1syA+4wY4o@8xg_
z6)l?c2xR>~M+uT0;fgIe?e2WI8=&fY{ZLl%EVKtYw3@nh_=}F`DB!sGQOCmK(%GCd
z{%MxOgs=kLY7<Hq<~&;)&IDd@)H4mx8{LKe@#q8GfAR8rFfj3(Jb$aR1h-7PYN4|C
zRZ1O_gCu#$k(2ed8owD)Ls=l$`g5-|Q7b@|$8K<c6AVr5pYT!mr?N1116+4lvJ(7+
z{({Ya%S5>0Em-6>cC_OI>Zx_|DJ%3%PGDB%t?hyC!`ANkOW^e!B4NmCXP_b7Dhj=h
zzYzz#pJ&JKr7|D>xdE0jK{U%d+rHnL=rG>bXU?2Zr{aMsduo$;e;2CiOmL8G4&zy`
zbqe)OIk=lL4?eJTd8!7bsMFtBZ~rt|V_@U7UXtSM@T?JC|DAfu%0$ujcOYTRn0!sG
z^Ia?Aw<EKm3!7)0UmkwQnj4MX(UB~YB3m?8Xm7bBCH>UM)>J?$+=pt+W#-F^;?Rrd
zcAqnIcES=HKRa&?88dnuzCM57QbjqiACvp%Y}w+3f47QbW3y)htI=*k9-D(VrpL}D
zY_q{3*}qC=o-&62^j*UD^_8Wz_`iWiK(8LR8hRT7U(VywGN)LkfbDgXI6C>~-z89v
z2dm4Qxdf_Gzp~Z12h^#IHKTxdq-0ozdbhXnD8zs?*TS9#Q+LlQ6U=gG^tj3>C2cAf
zry~Q{ClcV0syO`mpS{Ac#Aw@L=OTQ$7(k()wu^UOFBq*Y&DjKH8Ru5AAx{dIt1{mu
zToLZ*C~sIJvZ4R9xy)XsR*xzKqV$_)>Z8yt0T?1x%;X%g??OKMnJSN_G4E48@l*_n
zs)R@f)1%>B6R3El;D>6+onKst&}Wb8T2FG`aUJZBw_XN*!>SAWH??YRPaJc?-Is58
z;Qe)REpy_jBo=jFW)LrZA!jr)wg^JA#<gbHXF#yY8@@9dGTj+?Kl6dR{<DVYEih_K
zEh$eAfzk30cX_sf{;a<cSIN?yMH;wAU802#<b)G6(rCK&;ycu|olFz!$#f3K;mC8W
zpSQ9U=2^SaU1BA<gvL)Gb<Yx305Z_LqsDy%RgN{lKTdn%lv@vWyE%UV<n^oc4RP>F
zRpOlKpZ2rVe-m;7gkRHt{pq$kLc>-T(1;`=c(<Ely-+4X$x5T2P=TY46X06j;2WTq
zF-9PX@bt<ZE$gC;dKMX<*6^Ta`rP*s=*xgJHzN<Vi^>glnaSF|eY;kYUhn~dFugEU
zR1TuMd?+{%`j)f#nmKdO%#^*^O$c(M;E=!jb`*z_1<|TbQ~Z$@n|@%yVbgHp9n`d%
zt$IjRUfI<-+{P7Ru%C~biNYOoySA;O_j}uAQx_t6yz##!9({81)2`1bO=dA4NrTI5
zLvy;|KXolz?8GZjRTBA9`1*?ops44ON;{PFZf8F(&Q-T>8cJy1*?y-6fMW`k%x76%
zTUSH>dqiI}>4OZ&ZZ(7C{C8j3Hr<SXR9ouT(JhXM%2$p7>98%j0*2!9s^6v0E|wUJ
z+pB*_9P^h*YZPH~(JN{u0a?4B2ZUxMTJO6@g-7&gB1<bT@MnUR$|5jzJvZ+|vh8aq
z!N_Tg9rkJKnnS(!+1j=*wgB@!0gh^~s$Yp0#etx@>Bd<b?#N}ZSIi^P;7c;}HF#0t
zo6rn(h%zSAL>F#3>-VH-?7J|tL%@{Rjs@U#LME_}s`v`fNVI`%E#t&B-A5m``-9R+
zVJkd4PYs=R#1Xevzu7hdwtB4ezIftPB<?`lZq7$xQMK1AK;}da2r{E-WzEPH+Pjx#
zr+pKS)3g!FBmvLp%*pk<W}kG)2|;VWX9z3X>^{!<G6*x{Fz+D@7|XTn!(mF1p9~#d
z{mD?QB0p7U0d>j)YjkK=M_Lo*)>&jF`a6;?#jn947+(cv$Ri;8+$qZpbrUY%KYY0?
z^hISgpeTNUq_$ZDCKvXNf}Rl+ClTBTnGk%Ru0zX%o`M~{+Zk&&X@4Fz6lKvfYc+op
zJk~90oRqaR1-m;ui99r@Z81%jijZ6viK%d_ONAU5B7UnrQ=%pkvO6z(Y){5^DpjjW
zsHiy=y|Gezs#X7x*S}=DyIMzi*i#4}<_fU-itHdR2A_mo^*txc6n^Xqn@|s_+n%;q
z$^8|m*DS0?W(+DFC=u$Lt+TwBZ2zo^577^e3r-E+1Hu7iLbgk8X9_mx8AS-KAxBfj
z=994=v|f9uSQ^KXn(*;~4G*m^bPU{~49(@9hrZ4s#veS6(x~QKCYox$bOL1OP)0*m
zw^nD3vYkTnx_>EdjToGFK%gA0NO3OPI5)w@7ZmWr_FGMky9|#evc>0vo7-iR!J2)!
ztO%s9?m(aDr#OcrlHadxQ?$72odr1JKEvy`ARb+?qjMGR>l9#-J)f(i4ex$kzR6(`
zl3BWBGPlk4J|9uq$D2qb5-^O&-aekzfz{T#46woCmE7)SZ(lC*0XA2-yU~w>YO4RS
zlTLg;aBgb`Pfr5VyyJ)MX+)*c90L=+XoPv`h}^DIg#fYA6`c+iV5Wmu;{ygQFi^*$
zTtDwPPt#tfvvU14o}wcEKy%)yYyjs3)k%rEF91PPdPQ!JRROgomacqc%i6`t!?}jU
z%Vs93RtxEoS79Dfya{IK>XI9&x1LXMkeOqy`eg`!J_RfbyQO=86J@8v^70nvL{RCm
zmOcNQwbs_9BV4n{QGD><Kf5z6v)cZ)08h^BK55@*c2Q3L`IrbY&t|@6an&OB+fMC^
zsjFE#{}n7Z<c|;DfqvHLzbVtZta{=>f>>5+>(od6Y2$<KUCzdM>x!G&m62J^5PN-;
zZ*fV~ap*kHg@!f}fK}sfXW~4(+Cfe2$TB$v(^V1uNjaIGX_!dd9o6WZDLQM<?UCxt
z(ps-%x1fG^-bdH{)6`}><y3_P;OqnHO2Kf*#zHw*W?~N3Ms-CVt~fCc$#J<Fd5&Gv
zGX8p{0agjto*-+A<qG~WhO~{&Nh~=pq6~OS)=VDYCEwj=J0s*S9t8<27AY@CgSB>E
z_j8WN%B_5j3AC9^n-ICL=~p!QnZGFr(V6JvB5Q9doim#HV3ACQIW?NLE@*)HP(x0&
z39d>9Nc-U|>g(3hJ|mKT_W|Pf9J{^xAMTtHSLHogQ_nF51GgK9V>Jrnn^>v=%Mm8(
zl3w5APmzOY4-GZ9KeX-rgRgYZPV(}1PX%BrrL-oK;dT~M|A9O+$^R$z$i(?IZ4pSO
zA|>Zp5(}HGriZI9h0!2NOEY@YabtdYA4ZIT0Njs&IL|m+7-yMAaqe2!?G~vqchBh{
zrD0LP{t2K$0JV(vws@Yw!ty^5C=Y)iTG$rs(#SHQoOgga?;q6Noz~4gOML@caAN|R
zr8a{6AIX)n7iQPUoGDSHWJ9{-e|6R2Ip87tER)=>gu)5)R5U2biB}p+#qFL|v^OaI
zX|6@;@z!$|^t;al8^VwX-h16D30~+m`)vJl$oV=?F!sd5&(eP+wPKjm$}MIlw+%d&
zn@r@2IvTI7(^mcdz8i5&uZK7}X1%#C>GLRm%UPHN7#<Jcr5ErTIb;~a{Y}v6J0-!8
zzuJ$X8bMoA8y~kfA%ZrDjiQT}aSb<~4kr2WqY3A-A){kW=NXR0LZ-4>DKOXykv>m~
z?j^q)!!>MGniKf<2=K*p<4CMW_yu6Mimpq5t*%?<)Li$?n@jHx*VY)JP0BWS3+$in
z$2Bu6_w(v|!uU7xyb(N)PtYH<_GdFNWFzHazJAtaCDM_#acvX1Wu>EEe_Up0?T0Jm
zDU(F5WDxo9u2GfIcE|O+ynKA}rIa|koD?=Wqb6m)Smx?>(V+qY-eiyY?oDSSJUyqK
zu6|RHEMcRZgk%-*<(dseXg|Tzy4DQQCgS5E!drrzUjPa^8t&rzyW1N)VEnLH{sya~
zA^~EtS*W+K2?UQEqQ@oVGyknTyN%JCsO!3^5`eE({9G?p?wWo9(=XGAJSO+@{|_Y7
zpZGjiWs-TH2mViY?C6;Fe)PcOAVBYRo}o3w0rt7HWV}Ma_b>j{2*~~+Ls1jv&nJmj
z^eUfyASX9gUt$mG5Y`;h`om^YX#G-Y&+EV*8*|L0_$M}OP3Unvg}?|6&VeJvRGprg
zsn|`Shy?Tf($r<4K##eD3Jxn_@EM0fQ6Y2kL>~Pug;w4K9?ZYwP%~np$K{e`KaS8B
z=k>KIo2%?gX-C*`JUb+n1KIbEH=lPcng3dv9jy@477kI*&y2+}oC?4<c%aNcJ9c8f
z;oZM^#p9Iyw70U?zV5SMF`~nhc8R=m%EfiOAY}VvLS7s|zo6{2FmBSCJ}%vy74nHg
za6wmZOX%(1dPT%SUMmrNKPRev8=omYz>+l=xn0GyM)S{W#tF+OUR>#Ym@>FZLbu~A
zN$zWO=9ptrb}Q?_pAMsPpVInYl=!sv`?^3-1`n(1W2@IEM3PShPWV59g`WIaWy^I9
z8TH>xQiF1|B{lRplc0O3f7}>NQ=UxJ*H}qn0UEBx;{k|G5c*ub`~ARNJ(O^%zeC-T
zrShPtV<zvW-?0&SZ!PIOgwlzM29h<XsgD4Dcv87z#Y!kjhjpgj!t*-;y(eemJ*(@$
zb`4-W8SH7dZ-vPrwDcSUv_NZp`1k*T`qO;q)jGCY9-hNCb!oMlEqv!i0FJzF+jP^#
z6-M%eDu3{C|EV@hY)-H|Q?4cp21;=AW5nY}_{9Q?hsw)Yc;qxm{v_FZ`Ta+ClXNKG
zg28EZeh(&?O8DQoM#%ENVBD9dq-2;9hzj<0SJ446o+~SO&b|2S%Ue-V0gp9dkj7Ji
zZEHsKxWzdewRta%i~)_>D%9x<J}OIZ@;%$>ApD=gcVk{MvPkQzvUh58(~+whKOL>P
zs-lFVcALD-ku+b}qDU<W=7A4cL-^T#z~-4r_*}Re4Q1VNMsrB!=m8H?PfvmCTAhfr
zqu$vxYtRko$u8H29|Ju`Jt85~YhQs)Sxa-5sGVOBf8OKG9wT4Shtw=^)K%WHN=f6(
z(#8lM?2y2He#|w&I&HJWO0C~rR^kZG_kF_eesQRs9Pi&8O1*gxW@RLJ8aefw;g|<0
zfAL{2ZyBVu%0FWovy?cYnBYe3s_cCBuJ;4zg&*NvT6klN+2TMD{F%2@F049$r!~xC
z(VpO@t)o8+UV~$E_a*>YI@fh}-`wJsQN(c;oF~~n?dR9`+_Ycv@3_Qw#F<cue$A)S
z`0Q_))TLveDga`S37pWIfuXh*o~-cb+R7nJ($OYwzDf~YukT{?^3F!vNl&VDj&>7z
zO`bGAxZq#~{{2#r7FZtR?8uu}ia7;nGbnZ5lq~O|-b}hV)b3$*md?pfzP>&lCbX9u
zi@r+sj}K{ec;1_3)%XVlJDDCXv_Ife3ER*5>b-(v!DSufE=p=oX5e40iu0fz+&w88
zTel5xmra5>|J9sb<TewabVfR&3h204<~3PfwCR+Hjv#%ZO99i`{v{fnz#$iP)^EI5
zdX^(g#5tCaw+V!&g~bC!m^)9(U<jdIH??7a4+vCA#`O<13UF8Tx!X%9NN0rf_E{ev
zhsj*?)As&k-{~6oNgm!u8*=jPwlbw+uNfj_p1{%5OT%g%PKvThG#F;!Xc8x|SSW<D
z|6bK|7RUG$V%R4-A~Fz2N0D=dR0(KEtPHv0XJG+#E~+?h=1eKM@@HYin6&(MuE~KL
zMEjq_+YWUcY*Cgu7k=v8#g<-Rx_XVnP=K0(PL%&-HBiu~x6h?Ecm*%_x;E0;d@JDo
z6Y?iiF!|6#AGViy1=1b%*$`0Ro(M+HOl|Ce2E&#ZVznCM$qZZ?QgVTopZMV$o9lPo
zU?M^(^$!peWEp&2!n4g#3Ha-#fdh^Zq4ORH0NKsoYcR2l_N&839ZJ;BCG8$q7#2zp
zw5F0l>2G|ufg9DQ?uV%R4@s@FfT6*==rQBsmFtbK53$u0J7*sQP&%}IEy=r-#=kkj
zdr@sMA`6_m%|xmMc;S_`J8$b>T^|A?tZ=2+U9~^5l=yc=Eq!`8%Q)n$_^Vs5fatI@
zIZ$NQT{Ig-Pv?r^sB7lix0>9SW{uJZ8OZ8rLyeP2fQTgK2xW2o+1Nmtf@3Jf!O70;
zX*fXp8IxMQo>Yh9t_&%%D?}agqME609$Dp56gP^l;qf2zrf6%~_}i{Z<w~VXZ8w#g
z_wfI{b4mo)n<C^|;ol6SZ$_YM)CF<5b+r&j5FpjSkFTM2=$Ce&?M6DnHvc7E{Ser1
z`JQs~OgVfmuNZFQ<lK4pw*)AGNiXyL%{rfa5xW7nbmAq9R4HP+)FXBP$tMFiq(=kO
z4IIYZi)D{~FFoLpa#pdZ37JaqjtEqbhp8+oBohbqLhmSm(}-VO{FmR~>)R2$zt|kS
z`tnIej$NYUgu9S>ZV~VO<v?>8ZbEd(Z7j6ER^!vIbBfQH^JNSILncdp`qcmxkw>H$
z)l({dk(tm}mR<LPo*8E)!j3nhhmPPZFuv~m-~8a;3{LnzA^i4~J$gU6TN?L{v)et(
z&DGkuZp{SfxW>8;3Bi2L-HF$s9QFTEbk=cAy=@pD9TI|o^bioFMY=XZO6ism1nExc
zfglY7k#MAR2+|=bjY^MhhIBWK?S0ShKmOSEIh;Lv&U4@Qb$u^~y@iKz*7)#^GA83m
z3F`NeK)l3B{BHc%g4C5Lm}0l>#6tZ@eJiY1=xXJ2{O93_Dc}-0O<&sIs9yuD--rSs
zW8F(9FNXy(dryb4P!nB`n$Lg?i|1X`1?kr^?O1`9KEWWv6q|guZXY7dkt5@*qFf<r
zC6gAm&e!yopcQ;Vn%Mr1c)5uXHSILdNa~$=cU8g!r+k7wWu4Er_1w7hBJ-<Wx!Fj?
zKH^cobvYw44>YVTbKprVc`g&EZ)QB6?3;k$i78kSXr)Z686HGwxzk!ggn=zmv6}MX
zPDC29Ho772B*pRNX++Xo5g`n?`V^ebKdhlq$^P+1c=2|CXEkmDSnNMEbQB9&p{=@I
zaR)KC?|?~iTO4jb<zbbRqNiJa;H^D$GzU{$t$uBdA1LY%9W8aIHDmkTH<IUMf6qk)
z8*9UU!J*GH^|_6V%{wA9NM3Y0dr!RSc562P2t@ewRt0Kpb`&ZfY*dcon&sc`nJ}h5
zG<U@uD0?CiQ*`2IW#<$kzp7pQ5twN4d$8_gwdvjmV|yYe%;QG(c!>quit;nNubUS{
zaRbttQ{c4scj;Bb9}dxdjYfRliHj$c9UxnBird=rbbaJw4x07##dHp#=F@VwAIJIK
zpB`jiSCm}8Nls}HTGx2Mw;nb6)&dY#X+Y?VN9l#e4cMGN5pueh@E8fa>&73>-Mp^g
z%)(MRq<LO_46Wc9UUzowlHIg#R9pzH2oQM@6c>*c(zQ}(bFaSFc?_7(dxUNCZf;#d
zoD|j*MTJIufGWA2Pt51_4EkCduKT3ixVQOfhJ@=)DquzgH1oXY;=rM>^!0>s1bbfP
zxxr#@buXpI+y$9q<+>=Zl6iPu+aP=LV<znhs;IMUpWEHwDtw&t{tNQq3htit3KGXU
zxlgkGrhQzd8aTI8xDz1+M3ipAiyrxJcZ9k822{~v7P1mn`EZ#BK=lcz)?lxG**q6G
z07jaS$^y3EJ&!y6fQYxEghP2?ZHyfx@=M?lUkV`t=XTW~2XfGuaXjr<(bGwORI9!g
z>$7@hdM5DEMd9!ypy&GY2qAx`VRNkF4Is54Jdx$X3o<y!H3RTT`jO2)Q|7yDgMw={
zjrBtIi0`|^-waV~6k&Qb51ZqK)VbuK9II7Q?doOC?0-WjO)U?rWR7tu<jMijZm^RF
zQ=Wk+4$;+B&A}_v{#oV-fN$8;4*Qn?Q;Y({UXi(DpG-!NEgC3kUxpqwlurH2Cmkuf
ziG*KT;bDJmB&%;ofiP=$^PWa#{S;kZBj?AuuQ%e8i!dp}hs`N!?-hj})*p&!s9y{a
z$j<He*&I^i9mmB3Ikjg@u7yIkcY5S7gV6MxAiy;ENkBdo&GD8qz1@nk)6q;7d5-=w
zFgBCv>-ugs-upI1{c71FgFhT*Du%OPXnBfF?ho2ro5ALgrPo%pWw7~ji;V@`waWV3
z>CsG^WsHWDG0cmWt%f{;2S)j+XIS&vBaNlVjDM-@<P0C1Njo@vVbIOsF5w~j291ua
zyM>F72U&k(6h|aRwc-N}fuC>Qt3wnXB}+HjzIB8@UvzbE#uUoaP^1=fFMDav(nM%X
zJz)7=)Lc$Wbuw}e`y($GuRj*KB|H2~>Ns0p<FjGYWX8=S4tPg`UPOTx%M<SLY#{W6
zN}PkxA{XOiaFSDZa!z+SH1eGDyrBqP@YK>t8F`WBW<h_4rv+iC!>1q~3k(={NtM!t
zYxv~jVX0YIB#BE|V>Mt@yZxSwAerDaTTwFtrmu!7QvFg5RdU3-_2<m`cs%W|-H7L@
z<hmE*oc+_~{zCo^GFvwhBq1tZa7gZ`(;V|@g6?aBf|qnXgyFH-6)}gW2Ry(&HChze
zXy<}rSTowf@DQ=HIYL$eAoWp=boMC%)Q?^53YM4~oK4YXvDXjYm{z+UaTBlo#-5-~
zsCFegtuBTUHiJ4QU<e)X1bi**wCJAdNV1WBShyTKD$F~&sKVPwl=QXs+-Vp%RnFYz
zS2d5!H{#{KItaVpB(n*BCD1rPbp2NWATMWOsk1!OP2LCl6}i*)0SPVpPlb~cB}}~}
z%#)X!5S9llZ!NogpZwZS(E=9d*C<lcCK)T(<qm|a!v<Zc%DoaF7Tue1+uiyl<SkHt
znq^pzd2^u_eTCbV%O!9Z$@d(jXKLAQT~UMk@{cHqYxRF_CS0;-=RRx(xur^CIc6%D
z4&7XmLB9q-Bcykz=fm{Jarkd7ADHnyoV>i)DA9f}AGKkA7cpW_f0=LgXEboVwIp87
zGc&IdkaU6iK~Bxl4L4&JBfGgg6p7YdJs~I4nWBkrIxprS4VCNr>wlJ-WX|FH8srKk
zjuqWu5v!sFf7J2+=`R^M?K~!v${><^t*5^3q4oZ2tgP?1e6fh#=i!ahes^Lf7S?~C
z8MNvUf$&UTuS*7C&f)pxk9)=|5<gQNY4OreOevHpLlngi+c#52czmn|hgHAR`>fW~
z^tE1(@~QCU#HPMDb7Fj!YnCVQ=2JeT+fdzCH1WkLuYD`6)K9XkmlcBx^~WyhC$!c}
zcl!U7o@Dfi*L2+>$EM;U{So2}CfAhfVw6{63GeH9#)^3roWX{q1(gc;xqMbPW`2uf
zlE<3vv`Z;xrk_P7zZcJBuo8|_b_E8m?)FhN*i<{*5|;(P4mD=~8-6^A=;WAY`qGqu
zcjUB=yy)Y@es5OBO=-+x^(YJdV&R8dzc2kKua%y)0p{o&NxA$C<U68`X|rQur&j&p
zq&j=J95vT=kxxE|ywu#rKF$9y3RKeq@3f`;r49`_XT=Irt|-$ReD;?W|Cx+D)GP&2
z#UVdZ9=f`7U~ody_>J%WCW+YAgajI%Opy_;p$%UTUrH8%?GxW809yYL&0ULaX85b5
z4NZCOBgNX|pLM3&eH2>#i3S%$Rmxlb8M*BD4!Fo>({l(uRkgG@mbXoPgA6n0_)S*r
z@VaoYhCW|mLq*F}=oJXq94SpckpN`?UaoCS2wlFj<-@#Ne}x;p2SN|mU`6FpyYi1{
zXT!G~&O*wAs~q5n%~1NXq_iJWTWI$hn!?vJAf_K#tGLO-?TJ<>3HD4^v8c6Gf;-a3
zD$^DLU7>Q0y^7OB+`1gI+2bHlj0x=TON{3$pF_1vq^CM290t$Qfdw-<`v<OpZ?IoZ
zksY|4(uTLpd*;CT<y9N>oC?rXRS2)&PT`?dG=Pxu4yj<#f1x2N_K=Y{kmtm<03fGR
zhh&wxGBll+4^Nf5r7`(CvAvkB%kx_1iRi5X_Usa=L9_wrw2=GM$qTmXQ>dH}k@HIb
ze;~YKY4UQg*bvlQrxQGd+&(12-sR(C2kLZix-yddKSvbJCBvqc?mk}%T?yt&o!150
z_^S9=JQIdEk@+pF5$13J5ozt*SRzenqc4P}C_e0^nrI@k)$Ih<M=-ufX8pZP?Zn&g
z1XmGd_pax1^*_^mI%p`E#RG%qOU2>Es@HWQ1FsEI7936vt^Nn{IURMV8PZBC{6Pk6
zTv9F<4n-@>(ST{^yJkR1y^CJv+eU^gwZ%V`6c@zxnDP?&HacJ39dhGT)2Xj&0k0|k
z2YRZg75?!cMtiDQa;$*EW_TOCB#QH}eF6vC#^A0Dq`4~T_kktQCB+ib5UJ?%SN01R
zwdX}9+@-_vWZ3bE;lX+Ihgbf{i{iHe;dq!hBc#t&LP58><(1R7mip1)uTmFp8;F~H
z6U9uxwSb$*Pul(JUxdUT>+QWX3pbbED2HtH^YU5aMpDJOntPrwKt`8kerm&wIaQdk
z!Q*>Be;}Xl>^Q-{xjVF|=G%MS`HKs>ycNbQ_MNA{6#9zk%~!}_x&p&R*`is76rDhx
zr?!RZp3<kOQSB-`M&GvXP(Xv8Ef#b&x=0~+Q_Pr~?_JmD`5IGPQ5TE|71>|NBnH?#
zokzJ+M?9gc-&xaN6)x!rH73JQ{ZKqDiNH4RtM~dzk&_Rj&fmDDJ711G@UF_c^-X}a
zI|eV?cK!Qevnc95(|XGePQ-l_+PN5=#)#gIb7Z_)3I6Gw<1YJ}9%#po*X~Dpzwq2$
zNgjI7IKf<F>EQrfDEk_4(m5@ZT1k6b!V-uRm$0zs%686qD-&m>w6*uNC1<P#HyKjI
zLX!5;erv?JDt+hbg3WhCWx>4KzjYq|)&b}D(GCbK##BVK#Vv)RHQ#;o`GbWW{NMxl
z>;|<fPo6%rwPEDmP{$*+KR(IAW&H1$+3HI4v*U_sm|(m&5|J=hyS9X7DyxZw)rRAT
zd|&^0KD&^Ii6`lHZrYuVOOlh4T>datTb=>v%iP;<JG`FJlQWKZVv|*5j*1yAGXGUK
z+b3z_Y1ZgTm`9B<H{uSe-ZpC#|Fj8_0Y$u?GO+sF0<6Pi#|8PJN46mndQ2f;cM%@E
zgh$zWHZL_mI{;`5#KgjU+Rhv*y6##qKoMM{T|P)tV8JR&cRZf#NWPUoL<+?j0r5z4
zL98;bOBosfB5=A@_~7!0!qp+T;pO$ff(Nkhc9}vSXplgb3nRi=L*z|WkfJqOzz_WN
zxBXRTW>p_Ex)_Rf8@mx;s9khrV?+C<T4mWW07Iud)?$~+aF^{>SDx8#%$Vdn?F@wW
z;lIH@4xUTa$)vspMnGXt$GxkLsoJ$#!|*_xHn|@-s9!9qV`@D{;I%22G@$j$p{}#7
zRRt~V1d?*O2C8JJ^&_zAYz|1yh_gI&RfDJh9Vb|A+><+ed|vd}w2%rLlg~O|VY$Ev
z)JGYjpbOE;pzo(y3d#d!0gZqmEJ3f&SDoT5ry<7CCLL4rDxakvq7*uet}*OTePyMk
zjAEn5snv<MQ1h}=l(F*pe*4&xo7IWnK-m~E+b1a5s&G+6m}=@Is4l@4XdO|yl6r1Q
zI)EKH#j^=HwY+u&__|ETPO7I{;Y{H9W|rgH!`B$Z9OmD7C@nA~BgPh~j+INS1H|MK
zqU}yjG~f{3#VN$(F`_V{SnJdSKOm{*{6mvd-W5}Y%^_R1?+D4aO|s?lV<0auCx83!
z!R-`zb$00eYN~a<D+SKX!TTWnuG%W9ShN;p>#qDDal^Ok;$<LLp``2Tr461tHy+_v
zt}N>coEAJeEl-5g?t(S*?ONV-8O}aea)<vQL%z8q2s5cHae&ZeO6bOrODY$Xp@%$=
zHI(uUCT)0SOYoB*uihaW4j0=y6?S-tC%&9NyeAM^@Ub0w2IUpRi>kEi5FiYxML5m~
zAU)kbhJJ~M6%1(2MQIoK0_HY#!=Z?OEJH=O;$3w9jib`ccHtYE`2-PAAisPivk;eZ
zSRMO?Jn*ka(|45@B<6NujI!!7pQ-1-iUj08R{R=<fejd#2lgnFCOrL0G^YoqX7zgm
zQT2{9rXQFA5~jANqk<0doqncBQLP05t1xsuX3?&9DTxPO1=NaTg?R<z!lBFGS&cX%
zup_+7`x<Nf8aR6<9=y(Ge}*Ssb8sCk22_&GwuS1Bu<;LyqE!*4kb<v1slTI#IjMzb
z8NNGm&ffRd60RV_+h5+h;IVe_gl*T&<lI=5WB&&dot?OhLN`l-O*8(SK6nP^X0{h2
zsXgV`#ypiD)0hHT;ORp51sAbsG4`9lgGX6ggC$Nv2VGQD{o9ai(!`4#*RXRTEmhw@
z{I?c3@Rgt2odLztq|dfaa4u+bMFp%CGP-OpNdu<_qmE;TyOO=f5uhd?Cacxc>m-1K
z%x~Bk^lebGETd=C<9(Oi<pywO^{0?nZVIxA1NqlXaSTgXgzQ#PBoo~SKf6OXp8N}Q
z5nJ30n#xd^oQ3Xko?_P32xA%|vBI~=@QX;<YVGoGKFd6m{MsEtfZ+{CpoQ|PJgmzN
zm>sqbU2E|WmKK&T37o-}`(@l>%Dc_&xvRhq6E@p_^i+fGl7|KwOA=@s_QyDiWzeBR
z-dAn_$S$Ny9X~SCL!@Wi*FwMq&cO|2;98y1$kH^i&H<yl8@2ZfZLYwrnoM-p9J~8u
zIA%^7c=LGxLe1rZw$6+q4?QQM69_+4y;>;=JxpH>Hb~qsF-R~IA-iJe=Q(BLv|ePL
zE5he6oY@>*e0oo=`t&%a>F6P4iBvhbpPI7O>M$<srW2Sl0?6FlFJx}Vk6!;uqzSwz
zk!9tw2?K$T_2KbH+ROF9z$&XUX`XH5D=$=V8ma<V%E>eXUpFMy=e6%C8aNtSo0<(<
ztZng9XPWi&YD3Sg68GOUpN~$YkQFE_9TpAP{AG2-RpKL(HDKo`Jqn7Iu*u7w{-Y+|
z>gU0PoC&Rys0H1A1)Js!SWI5hU#f4Cr!t3h?4J93tSrm^ML*2`^c_R`!1>u+K!Qom
zz)urO1c^Do#4V<YRH944=L<XNyW~o{xb)>sB`AH{&tLN;G0m)YL<jy7p_I|SJMWZC
zyh2x>^5?aeR}f*pI$cDGVix`%AiWJpr?mcro;8EF6iKtxQ|4~s<VMi+@k}%n{mW6m
z6i~k+=h5bGxtj#|?Gm=t7WIoCXzCp9f|Vd2-p=PMg^m<P<Sl3G_v}*D+yWA0>OnP5
zTV&pceWOoJG4UBzp(SDLW*uxS6>+Pt2uq6!t;`ZvkK!2GB}imd+x8Izqfrrj^jF>G
z4<2BeOA^9~Q5b}c^PMwuNKPGeuAH#2kdO9EMb)|yd^M2Pyx9z0UUv**2_3_8E!@WZ
zR;p6C7k5zycF)H5?Zx%ro@~T{@|UWwQpf!uG2iAP+o`cuj$$?6tn{a$Jy27nAGMNb
z`hKx?C1EyI=REV%I4j;&Ckn47ygg}ykH@BqXA5PLWyXDv?PUa1<XZFhe`eJhHZ90`
zXoA#)WaWXDh2ty1cKOZVT6j-^bX2t&M*ixz9>e7Th*SO%b_ApeaF?$wI}3N?KFr_C
z1Fdg0^T10n!eDvNFrsy>Gg<lG*vF-l;lwk6!`u=@-c!Y*CVPc!s}hhefDRB%);Kga
z8|UnRSc=Z-6xo-L)mQII^SFzE4@8aI0pX0P=VfNS3-uxU-zn{+%8E|5ikmk(g74}X
zN%_^+&wv?P-+;m~qTaDo*%h3A{`E!ZX;}k?!o;tmZ{Us0XJ?y(E+Ho4W>aI_dS$0r
zxE$}ppZ<zf9;I@sPIY(YUV@DBBu9Kw?E;RUP0!0W?c;EJm{_RP1^<kp4Ie45U$}R+
z0%5Jl%Jm!}sO%ar3g1&$KV-one*rK?O-cw1U=&;u{H}M%JlB&m*q^5W!VHKuvY^sl
zg=6o&eHSH=dnbA6q~OkuSH7d>@dPa2$mD#d5%9px13F(xAS=U)H%v8XGnw7Y%9OzR
zjv=4)zs6?QFZ(uRm?Y37>QQx0X&OG=1NECrtgyh-sNkM)HcofKQ0|ODG<z5yC5@m*
zI`?`0O}b(sokd7%C3q2`cws1cK#d62Ea4J<yp{Pa{NX9hNVcgx>&HUr%l-RdJI|w%
z?_k>bYEME>wO}(h%0G6VxkWnct<#q(pr>EQ&?N{V-vZ$)E2dK*47V95vcB+^V!-?|
zq%k+0DnoQY^xW@Nr`b$TH+8vb|8mbC57p@Jc>$7xpqKc(_pUnd2D*an&H6!fcbt{T
z@NCh$^W+dDkW#zs1HUZA-j%>y_VGX05M2D;)NA@t&00%!L>)#jA=XMF#KR#Qd;|0r
zf7YVUPj_2@Ff64$7p*=?W?cQMXBmBC_a>6Z{cPMoe<BdjH>7$!o>wm$`*h5Lb)F<D
z6~lu+dcGb5$)B2>>T^$=dMI}{RTI0~<1P9QGABP8s9$gr^Y(o^CzjUYV%a}0-BC)4
zEf3rHWWqNCdU^s#AOe#g1A+;<W`<>-c~Rx{O36GS@2>fn@2Be{?>{r5NkcSE;(H(A
zWORD1Ec4K~6er~|J2$C?v4n4wsvUg!IHd|#bQWJ#c!>A)`q7?K+Hus|GeaSN+#j}Y
zVbX#Gi#al?EjhVwIQRn-r%9$ROghh1DvzcuWLcP=SvEb|Q`<^we++WzI4Iq5ihN@t
zD_**l4o2_Optz%wZGyo$%HU7@Q$&9`(Nn-hGS=vSUJKC#;qLdw-|JuvX%?aqb87#D
zuRZ`u#2#pI#OGfz{{sQp%N(kMBQ?OPEhmVpvE13|t`)k}0ysx%4ez0QYCvsZP+7dg
zH_ZXn*A_?M+sIho@8H(oq`u~eH-?^28IHv?Y^cBHUS9Gbcfdb6arxOpS<ap%FdCN4
z7MU`qLnmU{XY^*HM=zwJZC@A4S30Dy8)0g>5Xg26-r(7<1VEZ+IM_pB`u&Qse?Ehp
zes-03eUCU{f;r9H%-i>TO6VX}%byQ|Vs^Lt5a!O;%puhA;px8UE9ldY+fCkD(pU8f
zPvg!HoNiB5G9i0X!1d~z^{3+<Eert-ta|0{VoX)lXV?TyDDxDoF<2={;Dubp@%__e
zfb;<8350oN1{?Bcm*hOjC#F8`(-YKi2CpOZxntgs&eKq2hiki2zkRXhSgqY5=DVz%
z^>2!D!&A+MPKX);4S`qjr$gBJ`bT8<P5&lF)@)>;&E9g5SP4%dAPQbIlfFILU;XFy
zdx6_s+sGc!9vb*@z8I|?^Il5a%4P-8+ee<atkQMD3wn2gK~poHj@^?2bho#X*4Ihe
zE)q1wvM;3!;CZHotWQb3hVvBS1iL>&Nz9LKkA~l(#PVh3@Es(E6j%cG^-O!cIbUz5
zQ&WwJ@$FJ_k8D$i5Q#Q2yhh{x&D-E!(c)zY7Ix;$ij0dGC$(KkEC=6QxB3iPJC$D1
zRSaGuBFOGY#i)FPg{)i2)}uQ(cAD_Q_Gp5p_1FK5e%R9wC3EaLiC0rwh4I`wMM}Fq
z(6l28ejoTq7iK$OI+UxfZKKUfn@A+_LKuMl@HzPh41-OrOh5K2#fHK-n>QW*`3NHi
z9`76K_x!ZZz6EyvaDd<=t>g0b=GsY#)%N7Bc{MD=NxALhE~FQj^g`EJC)Cipz{6J;
z6I;ON1@s&~_H`{R5U=qEb%;-jH-GDaPM2Mg=yZPlR?c7oAlgf2dv`ozZu5yKsU4Og
zwL)+W?E6fuYZpnNC#0cc6#2ssu{7cBvWcIl@KnOUC#kz=k0;Q$Db+X^WMVqH4*Dse
z@Nj|5Hu~shkAVBC^CQKp!OKN$h3NaI<0z<I@SQax*o1lAwFodiWd|$d=K~aKFjC;j
zDI}={Gb*x|CJpM{C<pcixXJ}!lvw9!V~!`n!z^U_XK21V%LiRAs@^~KBT1>TpZ725
zRsyy@78FP`A@YBqR<#9eQ8!g-8h34ZUjIxby*p=epp|bKJRY@}*5nd6h5Mv(pDffu
z_S2>4X_<3Emq0-!)qtaRLWlq}hVCoyN!ejxu5UtH3OApuI-CNg`9F0@&sH}S1LWn(
zKl}IWP`Ku?1kjS4hODF0^8sAoA5Q<2C_i@8su)xM#`Af8(mPTh0HjJ$V`DK+e}nJj
z#gpJ5JS@!tVPc#!KCGyaDi`835%dDs<Ew4GXI*V~?-Ku=<DRO;-|xFg-Y{h$(g$=I
z`HQuWvnh3F>g~sWEH`~exm!(lu)EnrNwGY4&S}rmSO2|Gn0AbCAgYcCjpn)%1CEON
zNzow<M@UV(PqRsH(y|~0IaeVeXvw>91NB01^wHP~a`gllwn{v)yd}}htFp_1_Hl#M
z)<O*?N}T%=r_^sr<sE@BbIbi*LiCQOCWJmr9J0y>^waVu8a?Jk#I;?KsBca`#<F|C
zhf@z8L)V!a1V&IlP)6S-8Ww#XT%~4vsc+7xpIj9UVj;|V*X4iK6JM5(^u7l&Xki1%
zBabI8>H%Qp8EmzL1+1#0a*uYefSp8JbgldZC#nTA33EuW`Tb%j!Y_R_p>VqZMIR;4
z`G;tcC?zfKJzAULAon3BS^N8ZWQM4wgnc|(UbiKt=SK&teYA0Y<n}m{eC=k|Q$lL2
zEZ_gt63S=rgr-kz3V^TLB-j<A-99qG`3(wtj9$;6+~l4C&oN^yg;dF4KT*rS5P3vY
zY{ENceX}<ck8f!F&<#KdpyIP8vSq{as~>Pee95sO8Ph{XpK)MUCWd-cx<2Yt#`rWs
zz5fSdu2fZ;P`_;wz8orM6pzda?&_P!r_JbRboxQHu4-P*1K;?A+xw4Wr!k;m8Q<zK
z1}pk;vDfK_k1*s^B?4I#Z07PDUvf;*F=9aY*#;d~qwxA#J1^A^xmfYIjZ0*LP&E$@
zLe~78y3+O2eQW+roHDl$fu>_ThCqQKKJJmuxWOi||D~A38B4;aQ`??eeG<G`SCht5
znb(30ubO{eRng7(h`I24O0<+)BQLh0ZOsYWQwYl^aqdDTaNidCOF7<}5R=wF`G<$5
zP!|;)f_j{TXD`+zZcX}S2>!O(PFqKZo~S|6UOERBh|@}V&)PaJ`G2IR9~fue{zgl5
z&w2Ix#S`uwo;hW_%6+dWU`T`A;^}gqwTKa}%kvC31?>OI^c(XvA+06Q_~|<{z}C@#
zReZ)&<$oz38ZDaZ9`mMax`qgYXpyz3Nx9O$18RdF%O{d%9LJOJWEzHGRqkcu{YiM;
zO=|s%jp{slbKrcl@gGsg;!l#*LI?qlby>qH{phx6gyw9#{fJdaMfa%~S_H>|^e*+k
z=<#+XSOO+90=UALN~*IKb@nc#fexnVwc91@hz&VqW2Z&x!HXgY#|-J387*r!FtX!&
z&gDvENQ@`_Q6>W6<R7G)>@945y{aSLSS1N%Ti$J$f;IS#>1M-x08c+-xHFb2sQblK
z>ZOy@jj8#$DA364>Q}nLxciCMqOwWJkAA|US#LISGU<pSi>*Is50*G?_b}*UlZ_MJ
zGgeGFS3}-N9`<vv_}0fV+mGv(J?>h6sC6zh+W|g_=?0pJMXb(}y&HsY-vdO#O4}dF
zi^X4(mdo&7W2w|=Jp?IHKnW1}cFOZ<jrZKNaEY@9<?(wWWFy;z??)(VJ#7EFjG-u(
zVd_ibRPd^4kiWYI-d37+sIv(Afsqv@V$BAPBquU-3EqYq15lt&=1JA3v*-Ccfl{cz
zwV=2WZHhg!=jYjXN4s~EdE_gHpd~EO;7@!xexcC(1vMV$IoUuzbek$Qs_@<YM!6b{
zKN68Z?ch#gE``4w2Eb?>=61p^wb6S;9|b6;BiIL+keA;LPO>W~?~LVYjRo!njg*73
zs&=4}AIfb+H<91{7ll~!^_0ur;Iq*!E}^QVe9)5YxRT=%Rnn60#(2AO_{d5*7kKMs
z%#K12mZp8X#sdjrY--BgFZ_?@!&|BFFe{C@!8}%_TOGr9;{;uY0)!$xFDYw)1HH>G
zF$r<zm}#P{RLMXK`c=Yz$GMt@FxX7O-BGD01?!VZoo$jE0ipY+j3!`yEBLiz*W6DC
z#4&sj?K3dhU;yAwxG@!0!2Kq%2-_tLjR%hK?+atJ<UYL=#V`>6`NrMkSTdzJW->UL
zmQ3B1An?W0rSGcyzgohEYE5AlgLnz=o!H)nbJU7Gfl=f$2va)oheh7>Q@*z6J}DbZ
z$SPQ90|U=N#yU4yxulxBDqOVugR_|5Xj1-9<(lm->;6q1A>va^10Up+bBU}qEu>2#
zqamiBpIJC7Fh}YEQ6cYN!0)*}*gp|axC3A$0v&G3^<=*I);|Q>3V^QDlPUC<(mo)-
z=4k4yIG<r;qeCA4c}Ze2Gx$w8Dof#lZ6@~A=rhqD%1ywmrf>cD!~7iO^)r^g{il%X
zZQLopz~GW>-(}yiht>_0@h+eZYVTE7m0%kunuDfb49|U}ZiuBtD)!Ao<0NG<U%4PA
zMQkKvU9b^D{gu&RC!pI9)aiSm=XpGn6BfC86W#*CXo?-RD?jNOz;563_T01qr%Y9V
zg2eTRR<cQVH&vci@g`^Zwg_x)kgFY&iPNd2ZJO!dv^)66jZ&_hso(fzwxY^2oOs)f
zNB6FJswMmO$L*P8QZD+cvF@uy=Dxd1{&1al*rJq+Vk_E)<=31Ho3eM4)oK1r0-TAL
zPT`F?dRj)b?-Jl&ri_iJUt5)|-jK@>uhciB7M2grd{-}(zhUREIYtcDw|60w)n$7^
zG90R+8b4b>Lv5~bQ<QlwY7Al~XzuLlfU<zOEmXE&M{YmRSxUB!qlJHdKd$E|b~?6c
zkTXe!*;~yfI!aJ6d^^d3mEyy{BM&(lB<H?sV!=DOlKMaA{EuVeM3Z0nYh)jv0iNE8
z?b>qVUzIIxKk;@A@fqiJ)RW-~nrPM*?cZmV*NM-Cpb-M&@0Yz_by7Cir03MhY}F5B
zRXzW=$q!p7g;_gu)2ICp^jMU5+?{lRfcN^vi#xg!p--Y`p^heg=;?<OmwB86(kZ=<
zcXjf}_Nl$D$@6rOWRt9qCI(kBx2HV51&b64Dtw{BUfRM*_gaAySkzrcDV)Sfpw~iT
z*7pe`>;&!*M*%(y)IJEI6Qoh`+;a*$30c?As%@JFh<kXy&a){S&tx_yJTr_nCL+J~
zP<lE34>W%VV&DT;=|V`poXx(;zj=<+u#|cU#W+1`i3iS_vA?J&s|cZ#Qj%)wkm=lD
zS~@LsUN>p35JBH};-4I=xS5Z~9V#U7;Yk-$AM(FJ_c}|yxfA#Fx-W7{UX}sh09C!l
zQQnU#kd`kCfj?%I+2a}9c-*kXU~Do)R>=DC*B0489a(`A3RaEqJx6j%2-^fmMo;*-
zsetwA#1~Arwq+Y&Ylw7KQ-u1fmX4_2b1XdH(T5b5gH~@|`PAH~sY8$Swc}lc&$_p<
zczTJC)f7J349?PAPBw_Sy|e;Q83;ez!kaoIS-g~RZkv+`ib>fe<m*{TrP{*IvsZaS
zyNLLq2^)br$^Pf9xhv0`$Nso-g?s{*yG>Y=Yo50$j;P_@1m=N3ykImvbT9gcD2{@x
z)nCs|syt7lC#Nib|Ft)O0x$bDF@@g>?n^}SURh21B&&k}k0Bq~MBLGqe}MPJ_uFk`
zVcKU&?<CBg&&>B}zXIRwT;8EhJBtmu`NLP;Hh;>TbO$?71Jcz_Uvi&xf%!e&-<_Mi
z*i#K491k@#*f-i~6-TSq(EKWVzQ549lsQK+r>`c~VLSVTa?|;xf81i~=IJ6Ea2#h3
zOO45b9-V5a1Rxt{2bS;exJ4gyJ#6#(To;sJ*P!3G*Zx3?a$JA0uMgLBQeKXDUqe~B
zb(TfEf!}*oj<-^IgGY)>`5Jh>kxoLmvJ#v0@_I6ZHT|Vcx*A2pM#MuoIHJE`C4pea
zK4q`B+9m5iVsRs#eqDd`Oo}hY0EJ-&-;je08O7U|zGhQu#C^Gey$Nj=1YHlFmBX4E
zKYIv-(^Qr1S0&cCUgZ<3M)~S3Eq6@?6hUZ^q&e4?so>Lcpj3TpjguhMx|REW_PzC=
z^s%OAxcMhJGXWig8?b>=R_fsGLs^WIJ71qn9civKqc%sM)xS7EU<<fjsZzoPKFlKZ
z&3c4!Mo>1)xfin$eH4F9T??7XCI!-4JkeKH(0LkA*GY_7)Y!sTcuV<gPkPIfQb}3s
z0t;?a*~WRYkljD)%X%tHvqHJsA<zHot?2#I|LP&EWl84P=DiilhU8nX?ACI7?{4Sh
zaMHdF-Bq2%pTr$M!6rp#=&8E#FsV#F+`P4CZNaSs9y0v%zp|60k4h<tfe1D&InC!>
z*s+P^vs%=?_L&c@MqPjSz7CwEXZ37x6_FPF)FJ+F>*WZD_>N4~Lro<pLQib#qc&Cd
zAZ7uOM^@6%Z?j^6U+tWq4Z{c@==ji;NB&kPX^v)aR`lCFUeYh8zCf;AV=nU`JS}N0
zMAe`q(DX<P%lE}VCDpo47Yt@ymBLb3bA*jXvr3*}DZhy_$%)DLlwvNGqlA4uM#34f
z>}k1shPV2XvN)P&E*$U93(#)mbX#ODaXNliL<s&DbdMd+MT1n!#k4HmsxiImcdQRj
zoPVb)Z3>uV=UqZjBWyh6PJZxzdZB6Ht11+XgyE8~>MQ?-p2idTJx@&weJ!ONAb`)>
z)+Wfmmq}#zY?46;{shVfBuZal5ruafY3-`-^L)gKv4<~S5j1j4{R1COqVzeA*Y0ri
zo4V|Gh2)x$Hhto|=K<8za*j)c#hs;sOATL-!_@%l!F?>}5Q^|WHCaO$#G=x3UlYQc
z2R+?dHC5tZR4G~&P8+QK*6@1thYT~tAkD6<wh!bm({5k4E9RJaO}--pc84VR#3=Sl
zc62T9XjjRBS`D}1jB1t4TbIRM&pqoPb_{L6VsDsIlU(o_(tsly%B-8R{d{<g8Mtf_
zkdzQyix&@8MRRLty!4cN;WC-%lv;{Yhv3_Kj5gB{JqoupzE^ytSAtadoOFbG|1-Fw
zf%W1eOTd}d{aq9dPIV_u9rF?1t{x?YiONz6kf>mt12wlITHw6GDQ8ljj`H?p+a1`G
zcd!0bg8Cl7d?k8XxT}^O@II7wgyoTr*L+KIvt<Y1G$vlj*M6Kt0t8}B*04Oj@=Gs0
zQq41;>KrSnSi6O3%*p{T*~<41x*jyQ%a)Z85uC}<3Yw~6nx7aCUNJ6RDRLg6Vmj_k
z*;BU4d%)#!%~h;TqDXU;1vmGWX96!E6n)O%Q?yL`3mU=h2_eMaFHbs30)m0W?A|6e
z(3vnEx}{Jd9UkjbGe<9@{Z6+z-UkVciru8vT*^kHOI7c+0C8k_iDP&e8xD5XR1^de
zu7jTaHixzTcWnNR+a=HtF&CGI7E)FET^V$$O(*^8%vvFLlhjy=2i9XB2J;I2#Pb8i
zLqnM?82H}s+`TB`T7Pk?Y`LNM_dz_%*|fADgIINyZxAtGBzfv&1G`y<mVHmN`HTXx
z;YNkS2QsXuT&c>lP?-iK<cOKaY)A$-cX)pY%*_}4`i}D(3Qv-@mU%#BooL+KXhWSr
zh20PjsYAr&c3BDqq@ejF5!J)@dN_N01zkwi;n&ZZRIgP{`yoOqA+_HwMpt;2uc#~!
z?oiv*(#<yEnskiwqv&!8zfs;_r|PznA64!=|NAfFRJiFT-7oeH%cx4?D{5B-P$=*!
zu<!bxT%zC0ZDy$r^1}wQxLW;RRV=IpHq*eI_iQEb2WuD#bsl4>TIFw#)gfO+yG|0=
z{#9qel@<!oMwNnoJpq@dbQV@k_`DP{%#V~ashgv$Wg7?9lW=I@>uqY&(b<DZnIkHL
zZ>(0IknbxlIt#X_E~sCE*OkMXWTmV?LP;_LLRVZl4Y(vkWwazUGg@9FVSz_wqZwsX
zQ8^Lz)qD63EPNU|ggEyeJW+$%S}y~R6Ha(buLO3jS<NqgF??%~`GTIzGq(%hd4rbw
zINayCy{|`82M;F;xa6u(UB3$binp)L%BmAs4-Ujr9L%!o>V0_cq+2oH-%E@E^~=l3
zfzW4<ITmtrSpcCNOAwy?C+QKy$NmhKPE(ax*N?zCzg#<7z_6~55nB6w+<P*UHmQR`
z+VenqiYR6SKQcDU-TXo<AE6Aq@{j1R{Smn;{)es)SXFK06IO53>9^?)D5Ui%+W5$O
za6>A!|4ixJA3nT8kp0wKb5FRUA^XF4I7r{jc1Z(Fj8EjFWiQ35g&JC<+u8J!T8jn6
zM_5;G@>Qs&#r#}|YgSr{Bm#SzHon2g5Oc0UuZD0Hn&*S2C}Vx*28Y{LA82ieWT5Tz
z{4$IV{1D`wEurX^JEM62fzjuF95q+^fT4lS^7ccj=Y^><&1ly5+JP(G!-!XRf)#zj
zP>Fhj?SYs+>lLj)&$v(R77|Yd-VauK@Q^i^I$o!rxwYtk<ZegYRp!hCV0y}4t{YkP
z-OZq+#d<A(hHJYNr*ece5%iff<xfnD=DeFx#)dzgUjYBs*LkxyD<N=RpY02>npLuY
znDepTifX0wUH14%B<yU`<s&ZuVip(_dX6_GHu2U}l}6PiX<m*pa7(c2I5M)@{82Y9
z0(bVFqlv%!t8^gg*I=j}#3o{YfR91o(vPz&#mjTlaldrmE4*<oVywi0>IWva6pq3V
zLZpZ$KKGsT#4g(iMtpztc~nbVf2IW6jRdUvEa6U~_(`J<N3`n7MlL>w2Jz0ksz<K3
zJ0c@`BL2xI)Uttiy0xdmGR=K*mC9ZZHZ<SWuu3Xi(d6&_QZb?|wm&?50_E!?Y8}Ca
zQkC5nMdzYK4+zeF)`HK5B-~#)!c7)nNW1#}u2?4QTbp8MmQdwi?IzeS-$fJ(r$5@-
zCCWAF2UppEvSJ1&>qeq}mXZgnU7ErV7J4C&MJ^~WXa>#oy_f4$1p5zcg*<~zJwBmT
z5UqL_WeWJhRt=615)C`CMJU#&Fj0b}!icQ%yq@IU=IvrM&T5IX4EmAo@@Ubb>b4#^
z;kNro+0e>jIdRiZ+gS|$CVt?#!er^<XtBhavc3hb3MZtPd&*Y^OLdS9Y~CXm%Nn+Y
zC2Gdo$l`kw(sz@yZcMt#!1SV`_2huROYR^V>6Y&w%K8!0eK(2Qv+GF#SsFR)MEJDe
z1<#H`*9<K#9w>$ewWBwIw4VcG;G~jw^;3u4ueO%_+)@~la4}Z18{76+iM!hLo3si-
z(z#%zAK+MC<aCLK!7Y$v$%~G0+Q+D0EGucQ4WUu%IIM8p9Bx%8?+}UHi}_+{E`-{i
z_l^UuU){v-qenuse&phEGHPi_!!LTvjY<+JHCXhN^7Qo;STme^AU&$5jG#{qiEQA`
z!0jq+ho2VtLs<!c<eoF*?q$I8i<HBK!k`fflix$9YZMpeHrvyp5nQt#{{#K5R4;c(
zBG&yMC<$rX0HRoZcCPuz!AVP(a>4-zGMgWf#|`=C*sC*+bbClU2K7VCA{g&GjTCmz
z5C&}%XP%%-bVD_pbV+pb0B8mMOga}HX4AwCN!iF26JVoErzL_e6=9K+(E!eMiSz?b
zss5DTsS|3|R?$~LPW!GDHEsw9-M`*i5da<e9Ka^ovq;a99`=N>KUObvV3PvPt59uL
zj^hHx-jw9nA)6pWgG&NxzLj1r=qKE}$~`@aUJs$D{&Vahc(FW}e-r%axwBd?`^eb3
z>Q!GDOB45QoFE-1cJ*Bt|I_<&_z!c`zZzHxPqYbeZrQ#W7t2Zqg}|X2Q!V7uhjR=T
zvIvDAtKt38BRh^Ly;f`JcoGkjZWsQ>A4oI}XlAxCHSwqYwmPQq$MCf%rt`L(u(TWp
zK-fg&Ii>iL8*F1}o?R8J8Cxjz2|`ixkN0>qXJaf*o+yl&>yK<Tw>`i`&C*PGSGPU1
zW;jrse0Z|L#u?H-R<rSCaD$uZI)$<)#qzC7aK1eT5m?f0OEC1{P@aqq%Le*~;$A{l
z(lx0q?R2)tRs0?-uVsoxBGU5P&ak)Sm-*JB5}ya2FPhPhI*z|t;&<O#YO9so7u*;#
zw{uNR&du44FLowMZwW?=;R?RCDU&T43{=bwy8=qcI-#Zeg$VB*#|ZUl_1kLoL04q7
z3Ucm#mL52Zk-@H>4v)GoLPj*P-L|e<7u&O<#|JW~gk>MOMD8nsaY?id)`!?};*sab
zt|&PxPR^|B?MAK-36Q1W3K-$H+`B$ZRXrz|s1hET3i+T9s}t=<Uz2+7A*<Gh6!4d8
z?ih)pU6<}>mBaSPL6VLLowtG@R6Qw0UXh^4^R*97O6zFmwNWUeZoXr0>We&6rN=`P
z5jKAnLmMU$?5Szyh*UJ?D`p0uTV(*V*?m2FVHtw#jv4+oIE%;Hns4s#KABczrWiXi
z@oPBE6MIQ+U-0A!LS(QCq$uPgFBu8$i74AygO!=zxt0fakg|)%{DOSRb^F*6TptID
zMq9ob#+|drEa-oqi#S`zm8&(PJ6BmfD|qy3AvY-kV+w2{^=hQOZ<;vR7lHKJV#Xyl
zmL@k~&S_nQot;#_wdU?xE`qR6jl;^=f~s&iq)&(V9Mlf`mBhQG(|F!J8AH?BV5#Fl
zDs0?xSL3pp4ucql`!d|jQ`*tVRjX9EVfp&3+m>fM7hY?>gV|n<dC6tWvkQ(YE%$D8
z&GybST*+f@pdV{w{J};4>$agJf9S_b3+K;^sqxmU3Wk)i)xu|Q+F;#|;xArj<yebD
zG^8{<Qw)G5`TLZVvZn|}y+;PIkc+)w&%(4;euizBtCpJLZt$;gy5HJm-%Zk<a!|<D
z1a0N|YP!ZQIuO;CH2x11Ly0@D+JWO4HPu(`WgF{wy8H9^bg6V*6K&MNhHe@3XgByR
zHaRB<y2Q<lCKoXRZVZ^7`^Sj31z2y-9ZD*j<MQKfZ1l^5GsUWCpHL&)V>IjO*oY5I
znlRd9bzjKrqy%QaH}WfUEzdM?*E9+wflmqSmBuGWTem+fX~Fj#>8RtCR>+~YwA}7K
z@HRM_;<UbVlj<^`D3K6JCO6CawUmXrFJvG1cDl<GzYP)po!k9PF6m$vw(O$}!c&|4
zC6$?abTL)3Gq<HIb-<YIBYEcSHxK!;UTF3aI_VWO&Ms8DlTXzW>O<_qdB_?F<RiyF
z_j0RO6U~uLvL8dqlb!p#+=~-gNprgpm7FVNtpxh__Ku{`8PCgN@dXKEpa1H@@B|B0
zRsAzyNS8E8Zl=l2Ln$X^>S@8CO;1!x7y(HL!;Qby!-+Pp<^I<+N@UT<<extAf(}<0
zJE9@f0D-)ey)!J5_KEKh&<#IU?v9!=d|e<un2?0SJl&jb6>0)(2nN)arlza{!azvp
zne#XhC0PcI7A30}yWCWJPc`_7<#Clw9*qT`)#4gjz!dVN>0JcL7)l+}MS+S};r#GG
zIjkc1bvY!s?L`QQz82$5gDPF{T^gHV@oY}_ybT-cew^p5p!QNd_goylJ{CF4($d@w
zL81bxp~?^b2g2E^%F)AQ#LMbEz^H$L6<{Sx2n<s#Qo7)0{X!`}ghvl3{VJ``^%ne;
zhOdf5_KpE6$<H7l?L%jN-=$Op1(>aN5mUlYr$J_Kqj;yA9URfzx8LvGp*bK!?BI0P
zu{jpBf$(u&3utvgpYg6WPS>BS-%Tb;=z3?g>?85iNKbc+DMEv)g%b=S<Shz)XXQln
z6S;1FNPwdpOI6z4nn8hU6Yt2d-7%=Yt-n}=<8;57@-X~F?eQ2ZWwMNTjT~yRf)xuT
zB=64Uhel(qq?bMubx8Rn3K)JZx%<4#tNTqpFL3(=2$W_V@|xvFZjR&IYflU<Om6QW
znOw;|Khr1WiSbN+4`1Rsobpv?`ScMLTmfU&!4LA0SFzDw#myGHP-Zfs0<?~5u0B4p
zU%)54@}jl_rq6>AR?nRf8vcD!a$&FDol<;>OmV%Gkv1rCB?EWSscJd3tvY;qPRGUi
zu>@5k5qHro8J+F3Xpq<MSKO)gi1p8iHp^B#pX+OX6ZEr6sz0S^>@sTSM-AqF><!b2
z^G^X*w^yU%@m9h*=@F#hTb54JvYBlGhA8lRee9~IW<)iQ`16*|)|S*iIj|4#j>*y&
zMMj#;0?i5D%F9cxZjZ~EeZC_fnM>h{6U!NW+q+=Utj-%<+&YvG5c~F^dyZjcZd<g=
zT3&dQI>Zk-zNl8&_4{2?gsVeZq*nUqekN*vrR-0!GexL6l~=%R#hWY>yG7FHtoORK
z%`vZoH$xQimGZ~MUVJNVy_aCD5#<B?vqCPp-P7LgKS-XxCkSnyY|8qfrtp}+;BqUR
zPBl8ub2)GuQUZV{l!0u++@NW$iN<E=>3zU{zciF`FQH2gg*PSIX9lB`AIxe7s}x&O
z&cVBU)UN}}WX1dkx4YgQk;~p_o}RD%4LO&mGn1eEea;8IVPW67Q%qop8MJw74AhJA
z)LpxEo_cvCeT3vwHP`th(E0`%DFLPsGtpCUbm|Rom7Nu|Cmj_+cT?&>c|VfcWN{`p
z`ix2{LtftR)}CWu2Z*^cNL!Hc;I%!u%Ipd{f?t)ZL>E<u`T}n)!!5naP3jm8{X%a1
z%I2&vJ5a!!(Jhhje(QONdI^B9u>8p`x0{fE*O}X05i9qJZRVf~X}6*@226!*3I@D_
zvws9?H|{=b`7OTU83(EWl=c=q!#`0eGhh4*6hk%TYAB1feC2pxi6QcfdgLEoE95L)
z%K)6rQ@M5gs)*DbYQU?5T$G#|4I*Rg4Aw6$z^qOdz-Z<lD!v??(~~!5oN3y0t=H*9
z6+c5Z&Wyez4GM0UIn^u*vGzXDWIO#r@bNogCbisZ49S|!5{`~6fK2p_#cSf>Jbh>R
z)m24qp&+$?tX(LhehI+ar$RX1VQZs*R9QCGBJC0|CI66jcr)=#yO#t{nc-T(M)PhP
z7X7oV%Z@ly<MtE}-i{27O6v<YypFYAbeG}5o{JeHeFapAuT|6Us+~oh1KXYtz=%gc
zZy-#_@U43+(SL=xMW@8-5Wv~@L;5yxF#Qj7oS+}NSlxAhVd>F8+%C(_N8w(yc;L8t
z5`{CiXnU`zOYQ6>ME$quE?l8`X33kst+SzfQkzJzn&FsJau=|g3)$!8y39c50B6+j
z6Yl8|C|bzyU3T-vZNY{ZQ!gT5a4heJ1)!MxH2IeaTlGy|5G-foYXMhIX-75EalgRH
zyGnd6t`%MY?*NDcs|GAgidy2zfcC`bWhg_3{<%iW#c=sl&v}x@Z*q_&c5EE=Hs$iN
zm}<x5Hj>kjYQ2skcpU+#hWnwR+h;UUZ>e{1Ux*KCNFW$fdnkJ<g`!Y{60#vY{}GoK
z*%(?k!nher5(lU#pz}qp?&@!4Yj1>T&3Dq3wnUf#Rq?AS`P)q9K!i0IsOSk1rF?YS
zE>C3uyXI3_v!>9@k{qbY+lka8NAlc+LK$87yM6gS2ydf%8xCp)5v)(K9&eNT<)7v=
zR`vu+bNzUSoq$i;EvBH@_P4*go|dzr4Y&s=NEV%dkRb0vQ)?T#w$6Bcfy;dJs&97(
zMTB}cO-DxWSjr?XX#i1yy6+3mE7&l(lfWe)4a?92EVJk31iN;Fv$&b`s6NI@su=%^
zXO4u;<)UGtFPQ%a@^#kI)YJJ*{dY6l+sLr^{c;1I`bYMpnWHW8^_3Ue-XlgWQ<s+f
zX+JqJPRDrxITeJw9mu<CVv}goluR$>s`N$Xpe#R;pQ#6L*=^3Hg_@k-K${;BITSuP
zx_qMfR^@kq6Qs35O~up^%MSM1e0D)t#HiKr<o4L}Lae}QM&@tjK|yvC0%$M)nWF60
zrvlV5#MmF~>zBAhHKjj39sRz)i_E>BNuCnZ_;)-smR}_8dbCEqpO;^-@eE9y&b<2i
zrt#UydzPb3?rLx2s1z?VER^$JlV|*&oZHZKzOC@Ovsx1QpGQZ?%ag5iLR0U&>%DjD
zC*E7;semy2vUcq+YE_ijaa=U}UlIOYMoG?NMJ<Ne(@-bv8<p=8-W<R!YSv;T{L&SW
zfkhXfIMCqek8AX?tQWBq5&r{eXvvYAVEZSK-v9C{^<Z`mYhF*d_m%rp^C$^8TvR(9
z>9!T#8mI#Cr-O5%PtAqn<)WO#qZJ;&mp;omJfLd&@lC~pgW<}Qu%ih0gA@H!Vr0U`
z=6vy@@bKpg?@n-^KDlah>;>{ITX60o4^ga3_t<=P-Zd{r#ZDP)rUy!DdALmLf1bJ<
zr^FnrPik+Q4JeVPnEFR)XltwiL<{`kPR0BRB-}}1qlzj2!E1#y$~ZUmTc3I8F@iGg
z_>K!Pe{EV9tXhnhCndih#!DjmrdTBu4KA3fvu1}poo1=UWUr<@nH5W47e$Sg^+U0b
zH044!r0$==m={t1nz_=Vo;x$%E)XQi?TzHDlzR-0eTr_SugE(=y!=NrZzixPR_R`0
zu{78rVEhBGgN=5h3;aA8?(~CipV+UT4ezqNbG1x13-Y%jq+j6h^0FwX?_Jv@LmKxz
zXVMKbrJiG+-Kog=Hb}elm5qO;j#qG{T=xfHmdml>YQt<Q0X<+g{Gsr|Zc0{h?p$y*
zBvB0kY5EPDY?T|)XJwmZ_H+&3Z<xT;ZV;kt!f*6zer%b-D4qI4gSPH@h1cV+(AS^A
zA=8f+?^Sx)AsxH2tJF=B?~W7na5rv@Hc=tSB3Rdd&!6w5Qa>|TKkZcvZ)p9Ck-M`_
zneB^QYrTJlyLR$b&MiC7TN^^HYA!Z>Pr)Z?c9Sx;noJ2W!QEr%Pd!w}C(1@1tu0y+
z?nhiM|JTn>OA@~wJpX=tkP|X61>G=B_J_Td1E}~P^ys2K-x&Q8$@(0`{9lBa=(PFQ
z`rLm%XB<zCN>o-G!PO3|3`m*fW}vGQ?(e{8ZXb<W-bJZQQm$r(Qoh+=ciuwJCjO^>
z2NVB>U{<`3)%-+(qB9r@hCYEF+vW0K(DI#evrsrc4dw(oD9YYT`oLK8ksje<Z|*Hk
z)s~2k*^RH-Ejy>*$bb5!053Anq)R{vL!3a|>f9OPscA_%FDT-BGhsD8VSfS)lJVdB
z_CM<!f7I~GGpA8ASmfO=2^UCIcCb{j4HlvfDgHl2R~gpS+r|k2l^D`JN|98$Hv|ch
z?gjyY(JfM=L29IQH_{CvAT<z??vjx191Qlp=l^|h?K<b#bH}fC2|rV1>7L%z{X!~U
zUq?|xjI8o2i)1GBPyT>r+RH=|^9vugI94j$*UJ6BnD=MC2Jfex8htq9OHm(r3{-Mh
z<onaR+R?f|p-osmk$Y~+t-dQQaK}P&DGs9obq-vfEvdV*>Zk=&^nyUI>~1TZjxOa`
z_+`WHrke!zSI4*_LhZ~JjJ`_7l#1J3ptK9W*R{wb4)ko|lu!>TT*^XHrOJs8j?DaI
z{!Ng+a{b}JfEtLl9oczUT<n|`I$dIqZ6x{3pi3~@^!C^7V-UJ&@|-XQzAl)3aczYt
z;qUz5t3GT8nyrC5@9xi^2VXA$r{xJr66oH~<2cni#eAUSD|~Yd8eD8nv0nu-CgVTI
z90wk3tvbz;L$;?R3_0N4zs~#Q&JvM8yLOsnf9%r)`5zW%F=lyo>3At`fNSr}8f){g
z?6MS0^^)ylOF+eagf3?03>S1I#?)4U2TX{x?#~+hoGQB4xzbzYGXSF<e?#}a7-~Rr
z0FjY(k&;yqY29cVOzw{xmq3)L_-p$kx9VK_wera9)sYMQC`}g@O5{De&%b$~^bE8{
zvF}Mm&fyee7N^r~hyJ7A%z0^^S2qUe!j^{Qs8#3Y886!JGNBD#0JVj;B>?;)wK>2o
zIqLJ6S1J7osfauOyoII>P7bvml9~_neMgvdT-Zk3p$vK|;Xby3`;$m|sBCZ%jU#!N
zD1+nUqUo%<6*>(B7y1}oML?GO{iec<(BuHO09h`Qc`fGeXA^WA^WXWaf%ql7lgiB~
zs|_6zLmQf#XBL@4`-y??kfGS<Cc7uGrvP#rv+77qKmJ1h(=9>pQ=aJ{0ww39K|B}v
z@1`7DFT4$u!!GGjDB#hi!>2mLG3QqJ`_tQlb$aaClUr@|FwX&ThpGov*<8A5TxW+C
zwzieo5(vY0SH(sCL5Yd-n#epNn8EgrxAd+$@g7T;1H$EphG>|xxn!-nFsqNeK6o!4
zh_-xj-&2=K64OffYHP-FL~*jZgiQ9(<P&eEbs*KV+Ix876{YW-a`cRd@Sppe0p*-u
zyjdfjxBfp9HGmzdadM<9^`2_xW5M%;z-Gfs^k?kl`)4{Vty;VPVx*#!4n}oEji?}Z
z4C8mw@#5Sl?PP^1*$d`T{wLRQ&-7h&A={}go^NKKkJWIgA6AR;N&N*{`3{@Z){LLX
zA6PPTcdW##T6A&Eru1w#Y`aud%@MI>ZiyaOdn#1EG)_xJV>LicA~t_VjA(3uE>}QX
zg?hqbOoEYwTAw9eim#HqTq?lZu>lf{&PZ}c&JDBS-{pKF2Jiz1LF?KC6FOF$2xVCN
zc#3P{b`W<S`On4Qv04c78nH%Zzi7YJ-F!E)2Yw|l;^#g(v^Nw6_<3XuZVtE8P8){Q
zY=`~`<t((en%>Va_!@u@?G-d`VFh@PKYF)8pT=N}6~GBL{XQ5tl9_Xr#aQ&r&$F0r
zB}(P?5wLZz!+CT@d_B=HBXdKsGuI4S562U49?=lI_TG8Oo-A#32_akBKKS#JFp=0p
z+d`!9KcR5WLv3Z=U);GZpzjQ%JaF^@Os#!Fu|((R;SxNLICN&d3_DAUXe$&{34Q`R
zZ?aKeE(W?Gm!e-xg7E494oto^*l9K$iy@XI>!qmC3EJn1dqAy=we5dcc^?T@Q=8F=
z|HI<j%=6{J)8^}NyBG@mqG~;-u9yr}Zn`^K+`PdBJm`=1h#py$(Ngs5p8LzL4RGwq
zE*#9?=G31=H+g+OE!r}7B@iZe$V_DDyX-ko!bjRx<;v9y2QIE@v-1>$+$Cqvx*yQB
znzQ5G=`NY79osDGUMxH9DcSro_@YfF_-cHLeR3kr?i1UACcR&UuHlPCx7F~5HaYZ2
zQS#no!Y_Sa-X#&11W-j~XkXfbWX+pzX>Mk0U@m=**8ED9#db$dk9br*p3Bn}{_Rb|
z!|922$rSdisnBuTXgyO$a7s6%`B|h{U_6i*%bg?|nyV#h8cQ<0{&!k;dpB8wkT(E`
z{%i!<YnC3M*#9hCQsBOTkcHK+xQ-$jJWH6!T9KpfYs%r5wWI>a#$~jJZW=k%#?EGY
zX}i<?cCW%5(=cXHOhMyP&n>W+K11U)>G&#QpUk7Ti|LrkWq$9_9(3e{8MzP{04=%+
zTmmSTmk)VTVF(Z1xjx@7w4x-)sQ|zooO&72)IBZz-z+nU5B-cNngA}7>u50&(9C}Q
zX=)!R_gEIXCKTGMCK!_hYNV4JZ}Bu`W4_IiX3AXDi=|F_d^IXh9R@Bkxj52l4ISzW
zC<AK_VDb2xg<-R~Y)k_J0lRm9*uZhGeH54>4iWd9z<mN(5!DLSVE@}?1MdTymeNgG
zJ#>BORRwgNyb;6MUIG*VvtfMy<J^=%g+BTDK&7!-@zO6s!suUF9ez_;eT%-}tN!E@
zHFMD3{=!=FRHmJr>Yu2hs7)y?M!C1Lz_Q9VSPxovIWc$&GQy85L2NwowF%+|l0EEx
z3Fu;RAkrwxj3yB)27r(*0p@Ek#7ny~i>QOW%dYZ21BCSpQ+3}zn3n^A<tv%lw?1rj
zM(K;Nn43p34=|}1lD4qTwP>uWj;jptzQ^Ea6@ZDu++;%TGB+V_3|<I!9~2z3()wn1
z3t-@%Zwi8S{bh6Xmdf0@rX|8|<e0h8*s7uu8brEQVw=^hYxB5Kfj9ZZnqqz_maff@
z7Q;@hk5oud6~xnipHgoXjjH)7>;X-*s8zOiu|WHoR1vrx8uTBXQ69ibpbM3~_8tDJ
zU!y=MV(F{zWZeQ-UA-a7Yo`fj&%&Dtc1uI6%<CQ*iT<0dE{kf~9TdSn`j23hJ4PRZ
zCG9<fow@j@95nLr)+WV)ZVGS+1}pyn%CmIAx*}vmX_c$xk)<F&!NgYD?^t(9B7vlY
zYMznfHY`EHqFem6AG6;I1nNv}%xGdt#_sWhxC!&fM47Y@y%A~sRanm|ZYq`r`bF>k
z>Y3WgyVr%q#u89~J2B<pqcd)g1kewmMW3AE-%;(Cr6ZdWN6sjwARPi^11_RrIIn~o
z+s(04G2V7(ezGNR;{`Ked~UN0>eyYZ*#$)k(C3}Jdn_l_a`<KF2#Xzxtye|W?Y}fR
zxy{2%1^!+OD*`RJ{1-wSpJNXUMc>AeLF@hJR>mIax(c!Icyq*~cL6LM6Xi^FGw(*s
zT6Y#338I^mCx?-L?cbg;wV}W^Kkvwui22w3&J`ZsjBTm`4@~PMd#wfZ!#2*r+>57<
z=+iB%O#2KsqTgjqJ*@;+7`jfHM<aT^*`>;I>c`X(wiF<$=e~vtQ6wB1^ViDC@sBqk
zl_n4}AVl`!0<Z0TGH%x~Y-F8Y>$}+}f2Oi(4MX8l+$7L>S-NmL$){`$);k}GJ~7x>
zEkG8QQ>V4!&Kqp#8m;yew20^IwwQbUu0vXq4r|VZ2v)H&^gk>=u@d0dtAjI|ByCim
zrZW3{^Qbl#RVEsFW!fz~ou^=L;ZPG={K^Z7o_RSb<heV7YW_e>bq4>p7Ys=iu%oUH
zaW=-CDaSQ{W$LJqoIbu3cH*dybu@H4nypie;9J_hXw37?U6So+P4<ACm}IKhbk0%n
zwb`;;aY$F@Wfa;HQRMk%O27JjTP%Z|o_aB9`4I|a164H8{Cp7wu}BONE4}TIxM+ZI
zi>QN6+&@)@NZ5p(&igy(_#AWQ+f7nuYPB+%|K)m9x%ateA$R#HK$Z?~zc@SQRE%&6
zrfs*nDsz9&Te(*;mcisP{xr_(hd77;`nD9g{tfSM2SBX?-Vj{P1PcgPt;7QGjmW8o
z#qdtW4`WkeI8_J`?0W<9La0o3GUbXE;3IRK;Uz$kc``sWpE9pZ&pRmBBpoCP^jqUW
z70AyjK^O9)#_>Phv%6vU3ovMO@#@m+EvjYX2pT!q77Z%gAcS8C31e-u27J=OW$gSQ
z5HV1J#bAA=3gOL3ffq64eUHDYoZO94zw7>!V7glbdsunRZ#*DMgnS@i+D??x3`DmW
z*8XyJGj=J5VF#M?Y!}kSXLsIb1A%4&OZ^gw;IrND2(_lIxn>*lD{T1R7fsOS%K^;u
zJG}gZJ3AT~bw-hKeE9WXr5_L|(gsr~se0G@3UZ*IXI@8mV_=(@x&g#s*anANjj=yx
zZdY1$a1<Llxse$EI7i~v8M-f_7knn%P|KgVrwZYb2c$onvq7BcSKB58fqs@**QSoK
zLX$WIj=F<q?}wn9^TC+$^2jLD#wbX(hCs)>0}r-C+D`o-JXH#2^v%}mcRJ>H-_PN^
zeJJvrmZHqKox?6v`sV-+8wS~Jb+KGGX0gJl-#7OWzWJ}4TIlSXIg`rE*V3G7)#XfY
zO}pD=9!rV4Z)O;5K2(Atwlpz~0CZVw`d-f>&;)eDuec-};=_iy&9_2CrVzRO;ZhO`
zb>chq7|?}XwSfIjpJ+Du{-k}r7e2bX<<;Xzu9oCTQVyDJV2(gBuT~)|Hkx^Pbdx=Y
zUfa{rahezhlwa^`=FS*4W!bem<n>Wb@}@=+qjP^8ywaLtGUK&$1O+zLXl8df1v}CP
z+zRtg9m?Eh1A$dqrgZmtnS$BgLPheO3`~&Hoc@VGNnUaN41yX$om|tPb#Ks3Jhzxn
zpq|w9$U4#rJxt-JOJ-y<nW(V&1Omj<1-vBUlwX>s3-fV)&c;D=UEnY6=y8$Y>$xXG
z;_w}B(--UtyvGl8=Lg8j$(l&#u)j$jdjN*>VF}zdKl+-+E9UthUy^kgD9X{T`B|6Q
z`sa%HIQwtN(PLQN!q=hUW^F*PV}6>j<Z&(rR<=8P#3k_c&+W-<O$;G(nFkAGyU0)S
z`QP_6m)k*{tzRgts3w_qqylxo&r~*_*v}sm8!J^kYnYOc&u&(|&S83W>+l3H=b_DA
zW$${^&Z`@)=LFYC9Xr<X822!$hL@DxH-|p*E{8Wad70c!Y)%4m*^(%VSusT2s|;>$
z&wI{8u<xrEG<TW4^d$xTvIN3C8T2=FDYcYM%%1KW!)KuA22IASI0i=zT@&gfqAyo{
zx4Z`gF=R`x1C@%|fa7>P_Yn(A`n;`-hwg&Z{nv~OhMeBfgD5X#8nj8{5#ExpGa1B^
z)MuRV_qXnkD1b!;t!pkL2$;eG+D=s4H)ms!9Ykh|PwBRq)^KJ}+xq&0N+{;*Jfs>R
zb*|O-nTj)Q7eUykeFKtR=6-OV;n(;YZC;gFa4?azi?4XD|M+k1Nzg;KqO_V3$W<}Z
zJp5XZ>Oo%g2*Perj63G~vTmgNG!ogm-R>9&1fdMH(ZB!7)Hy?%%bBvt0vrCgp{1}l
zG*&`|`_{*PNlNnN$*58$Whcj0O8t#+icsw{ab$X6Nd-x8ZT<F6?GI)N2fN96i}!SZ
zvtJH}!gDSE(A9RId*RCD3}<)gEXr!Dk}>Ph-|joPO;rL%10_{kxBp^1nVFjP(Od)g
zdgSplw$5N))O7#0Ky;6_SDA$%9j^d++L!l!Q*`KeZ{j9c7^TZQ$03XE&Xj)W%y55h
z=QjMmJBvB}N*%cw;QOYy`r(a)gFEHir%?2_OuN(OAeUSlwsAUNA1h^oSdv?z8c8BJ
z)!t9<au=2Ga`1o%eZ17~ylcOitMR53jqho8jCkTrqm=JlQh*eX*wQm09<dNb$jV;m
zfKucWyRAFAS&<H|5H~O-Ju#ya?#La`bzr!Y-n1UZ_SFG~n$JfZn}3e^PQjW=oTa*?
zcc~YRND{}{L@{L2@{uF<f~s`070d*~gt^5m!qpGoOOQPavEJn`&Zsh)4xc_|27gT*
z)WD3-(%eVd9i<kd6`GmR^K5M<deJ_4YKSlejxN$kFqQGqueYPQKkabRB|5*QCcU}b
zNExVNdQ=8hv+qOYGbJRIJ!IP6KX(q)X@NVx#33&`cop0scO?XfPm;+yV8LT5(=i)<
zK%B@oKfiJR_kQ;x)u{1D@Ojbi5w^(~^ud2Ug7>!E#gO7mMRl#c7Ez32fL_)^ePt^9
zTg4iUscAyoUO<6IXFDC8j3M1(+wmG})~3sCK<WP4=~{F!IUvXrN3^`0780WF)p(_d
zdzz1O9yJDW@*0+!n#td8_XvgX%100nvn@sI<C@q}$>Eh)=;bc*Wj=QLn|NYKXjMLh
zg?<AKmu@oNp(R%W)#ob&PkP2}x|!TLmk~piVo#rSGt64<iUy~7?j(;-WxdUS-1mD-
zs2h3HmhyV$ELYhcC`0Ri{(RXtC8cMy+tZ>F_MmF4PSWd2_}6MO2HW<?NFX#ku6}P+
zY=2RiC`^W+uABhi<#}f)sB6lcUWH^gr8MEFA02TrSP;ec0GC&<zIDcYjv4{Q^!R1@
z9|OP=x)?JunSTB((nR?EKUz!T06qmOp8sLxHkT&RQnN8!SCwx}0Th0{KB!Tmi<4V;
zLY_Te2g}!gnbv=n!6lX}sOXKEL={Ee9_ct(Km*z9{Jg=+5#b7#Tr73XOgOWk{(!y!
zsq6<e-}uYE4Z>MlU0t?v4rr=f^Gb?6C@KA*r`&p$2Me9fl*MT$_@;PnR_^-<(vgG<
zDr)qXj6}VfdD?66xqsBOpLX0}$74?CvVCqRqR1+vySgP-rT{-3C#MavwSy_Jk+xS2
zAmn+jA(3gNUJHL(K@p+U0toW8-Mhna)#niRKM*CN7%uWDXHKaf0bhVIz^n<I<65sl
zanutuQ~&-Ut|AvQulQd)p--;!(}%}GA!FuJ^o0Sae1ew9@&rNOK7#rKnTc1Qz?XZ_
zlS-Fs?@k@(@8Upc7`^hWZ&uOwhkdLxG|2_3)*!E%Ygb>KeN}YIOOH+gD4)<}Uz=PZ
zCxDy(8eu{wBW34-qqwLpjh=*CBy}#g1U4~J-Gfl~0e#<v6(8b!dX76C(R7dAKYT&n
z2Qb`)%8XlJB#~o|Ki&$7-@uWV>BoZVO!VF+0S#Kx9-~y)#(mcx)DDW8f0%uRf?$0Z
zGa7{I6`_xjjM~TofzTRCJ}c*D45cA3cTJKlVZ!esds{vjSw?_NH{P9jd^&H2x5RWm
zTSez7auzhnY4xzF^pSl+Xo^ok0lHZIDB=$@Rw~7-iaj+4KYy!H6+d0cIKDrd5$P7b
z!mnQmT`Tclhwn7&<TPbKXVpo^y0{X@o0gqKr2yH7k|!ev1JDK{G*|}bWO>}rL^l-^
z*G~bQ^6EenD5Q3~u2VJYMcVMXOIa*I5PCl*)<3ducg^?NrO=a3NE_R)pC>99<OHeh
zm{~e{I&Yx^OKJpIqXug{s`kof{=>RCndwE0?RGxsvHUdVkO@2n0zX`-QROnps#)Fd
zVO@N)6W=c;=?Bieqg}KZ?!TjGyO_R$HxF}+d;dI%*W3kQQLeL1z*pgkEcNe@pS^Ti
zP(p5`EblTu^l#?lq^ReUBm%B$(R`2cmO9MshEHxd%lakkw&YMprNbVD;WTgddJ4H8
zSUx|qW%{Q47g+v_NOo^7%Ed?88Uekk$o#Lx;iF(RiI!OL^Dofjaj$A_N&hOVhfF?P
zKqnH339#OqqX5h`3RJ4U?Tp9U%g;8A;}12WG`tR^)}6i}138x;Bfb~{wYfkkFeKgo
zojbn1S~AnV{m(PXOq{^q|HHZ&6~0%;L7=YS=<RgMtp1y5SI_PHiqQU>o#Q>^xiJ5k
zQ`?^X&MxN!s+8Isb?LQ3z#0RXZ%~zF2ZWw&r(wv5<=ns@<&o|VmXeW~(tr_~qMSyP
zxcIZuz?2#s<9$&N)||??75&WA<Jypa<j_;P!o|3Os`!wx@ZG*2iZ9yBo#=T<B+i?#
zxmO)5?h`A(%0zbyxLewnl%`(Qnpqg>ui5_v8IRx~oZ9pGIN_w^Hxz-w^vDfah#?!r
z$r0m+lnva(H7Bs+tZ^kJBSx8rnq^@__kag(<i3aszgxz>EX!z~C9so~WNiAJxqj>F
zv5$v^GiI`KVR{Al4B0e%c9?{ud>39-Vt-H-dsCf!GiDO7&%><BtqTo2O<tn7C|na=
z?bwybgbaVH`yZCk-v=08e2qaOcj8`~25xs<&DrQN9AI$Z%euQf=C~>)<}eIYU3!UB
zIa3xgRS9A`i@JId#E$uC(S}y=I8YX%SVA-<v>j<OlH3E}-^I8mVYY|&&i?e_qsTYS
zjLt228Zy8tz|xQ$AT>!M(9=KH+m*HtH^;RQL<Rq9l&&eTb|x+_*+1udj5mW97HvP7
zu4Vu#v}%25H`_9hVB<YOfoNiC{{thULn<;f*6wIFcZHRuA=p;4{iQ8^m%V_@RXVCn
z0>K>&p3Jk?6RGY`Ek2FDHnj^aK-}AZnh@%BH;156<!WCFL%)8!C&r;Z@};n1S5$j<
zDdM;xxHs@}vdPARl*Pr_{!J0A#N!_hL0}423<SY>%c3~k({rE|b$JfoT;$iRqH`+0
zrKZ@dfY}Ya4@UaRu&vF{Bd%z`ht)ExFX~s$e{!fiEGDVyD=q4@?aTtDwa^M<nC<%%
zE4)+P5hQY+hav`A$f$R>JjM6&st>KjxZzR!*Z+AE^MJpSz*ovFSeafVfWG$1T~dIa
zt&pGZO$M?88G?qk?!73cUIgkLZ(`JY7!*5`ho2zo)zAj=lr_cvF6QD|#qXJtze+ky
zQ}US+?2KFB%w|oQ2PaNWn++q~&7$18m<9Su_W80jF7RK6VP0>l*GMjC!8o_yGheQ2
zrs{Y@3Zw;`rk|F9ng=RQ_NZ2>9j0Jd_u|~qB-xX_^9c)f!fH`{6+i9VC4KL)jNn~W
zSz$)qkT8|{G5NB9S|jNB*kv(J79;S}9I=Gb$xmMKWRE2%-c*#TI&KCd^9LktnpVcv
z)%qy*sCU47JOpl;E&xBD&1(r%P<$>N0-w!UxllthRgNI|yCry76v72@JN~s_+3Stt
z=GuNh_{IsXsHSgkUX|s5wZ#GRqMz47K|ZIK#-G1C13u#j!%YlCKv30*?lyANE%b0O
z!A}3th1+c=z9gDtSX@-<Zl{{y-IOTtWa#{b=5XQrrch6Ozs$I%=NwsInbL)bGMauc
z(!Wr7w&n%4oGfM`_XL7VfHT{RPj`y2Z?v^?u?sZL@4pcW3fuG5afxgJ@>P2mp`4UG
zX7k_FDM$hx!YPo=bqUx)LvENEEZMu7oO?T^z042Om#&@t{Fo!D1-rlh!>UprsCX;E
z;|THb*fmNQcs_GkCs0?xG@_1KY%rm0-JEmg+%_c!t;U>|#;g#2T8lzs%Y-qpHq)>!
zV{{_>$9HfRE-nk2d0Et#u@wuo=kzD1Z9nu}DPsZoJmLhTn3TwVZGfhBFRygB5^@=q
z=hRH@&=RY_>=BIxn{yr%bP3&ywwtY8244z*s+GLv`~1Hyl)`&ux9(dy{ibmEEA7K#
zm)wq<0vZk2kD_eHdBqOq)N@+;D2j|a#RuAf)kVD${_Wy&Sl});u*z=fs~uI7_<?q1
zU4*Zc5-aKkChRaZVRb3AEPqaymad>1F=fjr!kT<&HFW$yea6UH&DU~|-8%pD5g|Z9
zZ~NYpzeiW_2fa;Die2(?*5KKX;LUjrUSV&r)W1l$5ti@nr`R`1w}|F<4?#%qo;%6s
zooX4O2hCt6&(Jf9%SkU<k>hq(NK=G5IFi);CW-tQrWR~d#_Q?BI4a}$J|~OrDEP1^
z!M+G(qemcmZY$*>L&qjNMcFF#YfZ0wYf4C055#)0JCp9u%Q=Mh!@NlKXD{}@89mvP
zqqW}aAiJRfJj-~5sM#zd?&xZyIGhPa;VgH0;a?MBFo1q#jHuyKe*49t)Ohn_7yYyj
z?<ZSw{`0JhZyS%j85_C5z9H`)FXDT%NmrP7Grv!FE*^?~c~eO}heHj~=)HTYtC2+d
zWK>?bDrtyTeJ+~Um3RL4NF-2&6OA0oDc5yCy^Vjl$?&XKq9Zm9TZ3DKWWX}8^8z|*
ziM0jHC)1z4;ia`PmP=tR$<U*xqnPF9r92L3xVZlt%T6JGz(ilI|7+gBarQ%E3t)}K
z`x@1C)%7ndR@!@7vHxohV2jNNQFcd_F7UT30Pt^Ry(lBFQdKKdr1Jo1I6@~VC9lu!
zc*(V;cEHTg%ztk1Ywh$Ybe%ILF;2t+x>ESl&1(9pa2_oYn+tH|J1zhR;Ft}EPO=Wi
z$f<uqUp9!<6ndr%{OVX!BZN!NSkQ?tg`Xk%Clly#7n|@as+b_dG&d#hN1YWmCJ5Su
zdI}xy6|`|=y5*FFMn5m{y8Z%LEL5A`-AWZpeHs;XiF$JIw01Uuf+P|Mwx}7pqq8{O
zu0-y1o*Wo4sYe;Jl*K7FgRN(k0laa36o<Pu!o?iC=W@03ALie=a@-K$H}kJ<W=*oT
zP7+&Y@(O1`A{0Zxj>od@jhj^pnSK?Ks<h&|Q2pvKLrrv51$ephTUYJLXTo~8Vm^9g
zuW#66ty%z1RIKr<`__98eYLp9zdFx>DWF*uGuZNyvSi5oM4F1$3`$}Em;?Fx3X|E<
zStgCT@=xJa4o~suDhaR!7-b3_34w2|P|eKTd~ro=@G9B06YV**iSbwg#+8fNs)sDu
zFM*$8KD8Hv)-MNDH~=O1(-T-BhfYkMrc&LmQlP<j-7!^_@M`#zUo^;Z9T&gS_cu7N
z_a<Y)qbPQhhMQ!nRxl=0aW%R90t<+=f&uXp9^UEiZxA=~Z#%BCz)7>(W4I-F)XW{x
z^N9>%V+?ezGa=yIg{662m~hml>6-OZNe|t${_777%pPMJFL8CRgj2A1KW;9jm?t9m
zehve0TZ4K`by}kH0#g|!d!QhT%zL@}-Dd^7|Mouon@^Bd1-VtE_AX+)axnrqZ(fW)
za6Q{tTDWNWof|;Rja>@XIdbg&QqbM><!6L2(6s8}&s{N%$HNzdepc<r&tt<+q6_HE
z^onnJNCBnjYX_3ow3LeWzcEuYH{jF==w1%kX^vj<J$y|ppIEqQT0vB)YfF0|4js=Y
zL$FwXbKo?V^+LUHoOR9wUhVI75dFv=lHnu3bS|sjEbO@y!hgNzb};ZUAj<%L>%el?
z%u+wYaC)3ik_GV3@DoOJ=8{0aavsuf@^WtxE&GFX3Y9w#4uO1jbofQXNt$Emx0AT8
zdo6E1cR+7e6k0@{t{p^{tyPHwY)Qp6t+MH9_-V|q(THT%u^(8@=|WAn{#)W#j+3t^
zN&P30xfw4S^naoVyauN(E7E!s@@d+3reguqSE!=;trIOH7uB?o&#C{<3y<C@@;+C9
zj|Aos|MME)L_QSDAexT<lToZ41+YB6?Zf?pGhOe{A+}qBK&Mh)zsNO6O9gGJnF<1S
zr{dJhbXXof2vsR|C)D%TJ`w%4q(jK@=)^-$Z}hoBz=*bdO)#xwaqLdLy&Nlqy$QhG
znQAkA&e*L*M)YvoUjUHS7o4NMw*e#`a*PxVPI^7Nc+|Ac^qWG)8wfaU<&?cX*A7+x
z=Cs>;s^$`7zL{j)DHmlwRCKRQ{=3A>?PLp^_Zt<}?DMm>pUTUj>%5)tTuE7-n?+SS
z^$lXC*F=fO9AzUK2=cv`oeIC8%lS`THmc>f<^ihD-xukt?6Zt@U)!z+%$T^Q2)M!?
zsEQ!`b=sH$L>ooVH$Xj-c;173lW&h<vBDH1P{f81p%xCnfC9+%8GW)b3ZP_<bVV`j
z9urYxAGcG@`)l5;u*Towlt2X114drl1GwF*ZVNXHqp$f2mS>W=jFB}kytJtKfXzIu
znU`lamA6mIfQ{Sp*|S6|WJ6|2V2`+GK)^-UR_Gz1AzhpTWgg98@RWofyn;AwLywy_
zt9;_s^cEEB^Aq>hf4s-|4XIZIHbwU8AGL~Vfr@k#HO@3?4BSql9Y!}=!TzA$ARYw1
zN#cbmbk0lJpFF;mAa}5WCy?7h@YRl*u{wF9|5WmSwzqhpf1Caot!FKXm4Wb=K4l=s
zr`=#?%!xlUKjYl=&D0m!<BDet-T3lR0XcVJ3PT|gHXEr@j6jP$CYR@-`MzL3=`>BH
zTN~(KdU-2fkC-bF<QJv$*ui@_i%SLe{m!S0`ix|pO`#IM&7YVyUikh+X9F8y$&|4>
zzs<#%`dt_?q5PW=4N$d+Dt+I=?c(czI8DUQ6OOg+WGwBapBnXjtMxb1_Mhj6v(!(2
z!#U3{j$u-HL|j|N3_8%$aHH(wAHdzoa_XE}?%{s4l&mO88BT_Rk!UjC<0-Wo;b!x=
z<@M;W_4@jD-)#mj2@9aiRR`Bz*ZPOb7`W!ibGUv1-4m23`^!7w94d9V8a#dP1X6FX
zl-jt(JQ(=}ymn(#faL5O{Bqhb*1nK((g55^#OEAX#E$eK!-Wa@p73z_YZns5|6xg0
z6bBVc8CvkSkinlSoCTCF6Do{N)`YGPKt+?(YdGmn`hIq4lh_9VJmn|;(p6b!rC^#C
z_ZI7T6eHJ?edc3yEtv5?7}Ih0SI-CFe&XRy8H+8I3J3;HWZcF`_w5D8{L^u|?O1BA
zpq&X=T+LqS@gPuiyn{0~2hysR4cd|Ur3ec9_%+@{-0|r4hi*I2Fg6esUKVxqG^EZM
z&^B0TLfB@!gRk*9_6FX1t-yj8Y!vVDo0j^=Ygbzbr8$8pXi|s)ryT&Mv~;T9g%C`p
zUJ?7(J`Uh-6}I-t$va+(odzc6-&OoicgDx@@BxC*jB=j6y!kWHGf2Sx*%|LtD`_ob
zMNz+K(Q$9lJ`7vK2$ec!Cds(+QbIo}tGMSu)yRd^{&}E*e%{5N3T9<yNG#m#koa}G
z$u5Q&H!BFx5fvT~z47~cFiuzJ6`(uEWH^Rynksi7BEi<)Ye}z>^(5A)q1!vdTnS>H
zEp7ifXaQ@fsyH_f;z|Nhv{~B+j`-N(mlOtkTqv7UU_MwFt5FsAXLHp-G;c~@sN$N~
z{994wYz0_;QenaKS~TDORu^SWp`QBs$UZmYn}4?YZTLe?8^A7U=7LFV2J97&p{MQf
zT28BIZci9)hRa@sJEd41RqLuH*GS$^z1H4^<;_d{bhdFp?+3L9NWJ<%k564yy&S@I
zR1;IWG{jiT_#h`rnFx;bQtjz%H~%DDjUTH=`g~t(RIcsV&T*<YE~x@p0{znxXQ<NS
zwx{!9l8PQ7OwT5bRkk)yAKtreTrV_kQsU-RJo@6s>Ci71PsT~e;MOKi{_QGF4(4HK
zX)ivdtk>FOC)U^L8+(T3DQbi|?%`rG`S<C$cMR@q0fam%V6PDcELt8n$!s1m+<E0c
z37pDjb!A(+)1n_GMAutQrb}^y6xum<@c`lFdj){=6ageN5ilyg1-r4`R{+ES(oGvB
zU_{ByrK(eFYz#2U?I4a=zt|#i%aoB3&Jk+y&dXO$a9FhWjO19c*Di#8Z~K7Cbe*`Y
zpOpzLO*g3Vm-_(xMBK)1U~wCSHeeoWcn{Z<0Zb;iK`{Qd!m4rNdi}osvRF_E6}=W$
zCkZYg+z2YdS-YqfbSiu$6Ux-7<Ma>}Nnd!s+ZOvDVL2ubb^Tx`aT(q{4eo6sTI8x7
z{^xe5JqcL#EQ-q=6JveMBU`q@pTaG5Q<74J$eh3S0~t+Al*Sfu*iw=^7_p3v(cA+E
z{qq^`jil4rWoc{F6`2g_#aszsH78$~zxe^un=19LsGNtw@4m^DXxN3+fy6ZdjNVRc
z9<|18SvgzUdeKZj;Hv@kgs%zZou=;{OtLDXoA68ZuU9*MLERUwjr@J%yAEYqn7u{-
zgt0klOCG2r3jSVBJxZnsbV`@pbm1HmYhpYLi-d<7nNM)~tFJrDp4BWH55VY^mRm+i
z)FpJjg-imL7XCqD^3@Vo$zDL?S*JwuZYNpU-?LBBX&In0*$bbgoCl0}bIfZ^6O`n3
zj9q+xDcv|~zi4a{LS=f(_^xWcQ{NQ{!maIEoe3oVc${S?##TNcEz|xY*R%^wDyh-o
z%bMFAC%x0QbS}2J_)U0VU3=<0|7oj)>GWja7KQpvCB^B#5k$`L&5CN4ey5=bE6{D|
zz$*5wbLla+rK}UD{af&AWEZTgkEAF=UJeKk`h)xIiUI+tRQObXoeymKqtvcHLgU2!
zMMCp&Pb<H<RkhE5pK;q$*4AUlDAkmq*6*uiWA6HWr>!p&M?mIwpbHtR5)=DOta$BY
z?nBJ71elxrc!<sz0~?iIKRfP0e3}h!?pFW7mN%HNWKwHrLcR+N=7ROWN0>P`dPpE9
z+xe;jm=A#2U~#jQ-P|TZQu<a1TVk&qNhEVKYDA|RjmVT2J9K~o%CwGOa0zG~AA(gD
zN+)CNB+=h}ihYpTNR?H>`XSr*s;WN!m(s(w@nUGcikj#tU>;_&2z%UFw{%rZYPVV1
zhnoFxy1X!)lI{6uOFJ@>@brRAa8G&F0#<34m}JOGaG>_8AasJD%YnzoR4|yI_CO0n
zl#hGUlXxJX=F0PqFUcdA3GxFL^Ql;&$0?SnY_SkdQUDd|JJ0tqn{P4lM{DDFz>Bfd
z?9L99ym&dFUht<5DChaykL*@7rL_@<@iZd|(so!9UsL}~ev6+myke9TBT*mM+3f28
zW{a;^P(Tjh@rvV9d;ZfWm9VI#Rx-taW(&Zr((KDPP&`VQn5HPQ+aL>N#02lew?Kn2
z!B5V36M(;@z2`hbeI3mX+={(nqvYD{kl48iy(r(Byp&afVOP+-;;TwVqT6~l3PnpH
z{+-)V1yjr#6`V+wr`cxnkGQw-@1pT_@{IlL8n^Jr-smh1ggVbe?p#v(er~#@#_RKo
z4%U8a_DB=qi&ebJ6R_MfpYKx=(t50pQzNt}i%7M)he0NaIk)7IB~<MBQidWB1D~5>
z2={mAuMb?8t&6e`vr!-|E|v-ya}bk&w7ewVud)GANADQ_RtwI!S~GI=h&IB0!c<?G
z@Mh{DTC-}8jmB>2v=rZM_9SFO(q;!R38Gsq`;O0_yx0tFxoj4b0yMp!0j*cjQwj{l
z<6)pUMJO(u9Sf?_b=5ssF6|i+^cz`;dK|TcZa7I<IXVVL+2Kmr`+ko-WIHV*T(ME0
zQ4l*g->3yl%A8t1EiAukD*_N)mk!?f2RvrZCs(CFLUC$*&Du)=>@{ImpHdD2QlNbM
z18xZ#wWQ)MztVpNn$?dBlApZ0HiZSTEI)AlJ>#3<z19QAiJ>xO@p;qv++-*)16AZ9
z=K!}6+IVHN;~xqs6Lv+#+kkn$lkdvE#W1%csebd1QQ-aBc|Y@RECW#iv=r9%%pNa{
zr9VyYm~<@8x9k99!>nG=9fxyoIw{<0tq#2vz?5Q_Hb0yedt;xz-|+?fyv-~}9#?aQ
z)?+Ka+m#nfR){b|>>}N^96$9QDv;e&DIE?yx@#d}S#(?WDhJF2jd8F7@R$K9%VTt6
zG8cw5Qwl=Q+@<5qp#63cop<#{_0_%lh--n4cRqd|NfG4zD~c18A}P`5KHvhWKYJpk
z$;hlunr#a!h^6myYk~Ve_&xoOA6A#3S&!I|wy#|PhPaJ1fHJq}5bOOV9bwv=K!2uS
zp;{a<=Aml0=|0ect?T%q)8M}Si|z3YPlxk+(d?dFk)0A;ZqvP%M%O<SU^z|V7Yo57
z0KL#{;zhEgjb#8@7bXR*=!~>p0{mR<6R5Qn8*zcObupM;zzkv&pvLE@gQb^3_nAt~
ziB02M8?06ubzYd7a!u5SBfIQBPI`84xEgm0%VC~<F9T|3Z$L0>sX3t}D04jsa3dI+
zyi7gLi_spfNh+eZ6uYVH>y1+IKj%LIUi#x$AKJDT2{FVZiFvn{fESFFqTFy8xLOZr
zvehVi$e$f3uhO?_ct{57^wjOVJwS)RLN*l$pl$b+*z4a_+y}aIB%s6#se>Dm7pmCe
zKPGfPpA)oGj2%folNf$niXb-dwBd~p%2YVrPWzR3o~r}|0xeGH7Y!hrrF_y9-o%#Q
z@d`_c7GvQP)I6zx)(IsA0>FI`0z;O=kc|uIVS#SpiCW4J68K+XmhnqZHk$jrzW0+>
z1jh_hw1)TUmd5||AwRi9&Yl-Iaw#dgq)|E?N?7bxpy=?ra?A2~{K#b}ll#4U+#coL
zGQvR77Tn>%qb3WboChT8-?Zn@ocfRY`^p(#;sThqt~^gmlH0Vk_S`@Ta>N=1naQs$
z{TKh?&L*)|$PJOpa+$B-;gdK#wg7Rwu?N25lQl^v%C3l}?k1s+!({STLbJ1;AEALf
zcjNeObG76<#`1)y?Ly#5=4mDTHL~_?wrBjL2oAJEtZRz=0J?9YGejZq(b?J&+rvKa
zVYJSym)wn0^k#z6fe{!mTgL_ekh?N^vk~wTPR$f-hg0R-Rkz9Xj&VTsdh~7F@3`b$
z37xWmOv`v&aG{2ju_b-bvTs50AdkmNM}*Hm$jry1WA-nJ?t;tH=BH`0n>R3&V>KbK
zLV%q2GQhq6L@5zFl&sRp_NAC$v3%IJytvOwNry;8zoMq*`t#A0yMjq>Z^QPCi$2C6
zfdJ|`j<3JatP!Z2z<HpY>0CULbI#z~LTr%NuQhP9&L&-1getYvcgk48TxmUfJ=u&s
zYX|_O?z=bDKY>epO;^XK@b3rt)^#<e=bg;ph9Cm}sb@}2+}r5JI`GOU=eTpK>kZ$#
zo2rWqhu-&(Q$7AXDF&Wgq-J0u615%lsy33H9zF@`7P>m!j3s|fu-fqP?D;)=+?U<Q
z<zrF8pYg9Af6K+6Qc+k$*;yy@5v#1y$3^k%yJ1Ex;v957U>Z-K-2fp+z<R^#zf~W0
zlaw^AlrsDTP^u_aU;O?ph#9qN{!_L2;2CpiWSdb%DQTOBxuqalGbdSk`9CZJ;FF)O
z@hUJc?(0pqg-gK)Wjha<npAb&NY{WTTN-S|PJrum#_*`LkhE0XpVxuSqtY!6CeBIz
zJ1CgG>Wnk}E8bq#vlE#=>2`M(1VIXJAuy7hvbT>P=jlo5L%mAu1@e`cbalmtoSU)6
zy)*>26?VQsg|Mf1b2GCW-WpFybFS*83--&M)tE|2SCEgiK3v+%pRSyVu>(-8Ox!k|
zE5U=on-iJ#$<04z;NAx9-nr+l=eW6pq3iDy&kAb`@`*hvU@t{7EX)ha%?&51!Ci>>
zdp%#2vE^2$1LBR$_%q{3%}bMUN$NSXN!<qa*i6^C%ZDC3Vj#-(jaGis0`7#p_361N
z1isxA)G8Wv*n7WVe)GAUx_|bKk0IzDKLHg;DxLuDO$3ro=4~FKGl494vX~Fxp-8B5
z&Fagr;qSk^S*vOy%lHD_G6Be`(qm8ME#Qk?A&!>xn9n5m(l{Z4wy7b8D$BJMlKB)=
zHN`U&8%I{-^6uSO-aKM#KXj1w`+Uua2sRj&4sVft*T^XT&CPz;Eox!}EMNYz$cwMY
zc_8MapH;Q3NWE|9O&(u>qVRMhi+V2W$TD4UT>c(xtS#S`?L~J5Ee$IIy`9^UTg!Sb
z14y8|c@LlQzgVGo;QF>dd$`sst;UteGXgjYk#@N-yL(Sk&u05iir(WnD58y)nP?lN
zE2?XjYUvsB0K;!No4OSnfAD1XSGwPEHznd%V&97TC*Fz$4@*~cpQa3Lay$0rM#Kc`
zquF#<e#gWA`jmEk@%QMkEPFV&@AHZN*Zpta`fl3R_`8MMW8%w#*I?@KljR79G|stX
zbtdwRwC%iu3%ala-z+Aaa+*z8X^ysjVyj!Ll$%0<<@{-=lKbS#F|E%<7*Z59%dx~A
zwhm^lN(rJbb<I7Qx%X|T@1{&_2e+D6!OZ-LL9O8kgB7I!%D%_TLg~oh$o5;K6Z-8^
z<Q8nC<bX$jJt6e|?Ku8-pHC`syK6=OJzFtnonU%aYggjiD?ugwhkXaTPqjb2djPq|
z6s`kWQc<3ZHEJ_g^<}8Mc~_l<9^tNg>`6*C5Nz(I3AgSq!|Q<rX|R=n=ZDr_#>`R7
zbxx2s$?ch(@1Caq&E6?pO!bV?KQ4fVQ{ft3@jh2yjiEi{JgBz&Yvm8P_EpVa%3Fo2
z2&+i(I?k^uaZDyq0k+a@|HF!XwoCQjy;|7UpcME;xr?d^%SK^yda8S!zL6NnsT6u_
zcc$6^4Bap8GTqMHLG8Gr>q?%Ic0=nVoFu8vp-_$;6-zMSEoIE_;;#j!{;jm+2&eO@
zZy}&XAbdY9IHursKufrZYJuVt@K?J5J9(U3$=}eoAI#1NU;Kvcxqh?yTJeq2Nm*zj
ztDDl(vi`*^(GfbU1C4hZjGEbq6wrxot)x2cgFD#Xc1h?TLxN%{XRsNu{e|mA!zRN<
zhqTDfQQ|j?!oODs2DUm=Z=Om#a83JeaR!x33rIYrnUt_%V8L}6E3Zsi9w6J`3mB?u
zyGj&&(h4c8l_yjYJt52;EYeI*BP<{0oIihgMNqAkw5CBHGy00bI`hDcoQAy)syx`;
z_1?8?Waaxm4RtvgTCi14)=tI}Zn-6A-}@w+_4$W)WpL-ZvAb80J|VtV|IhDDiyo#%
zHNqq)!kpPL6oZqxVq7x<`@U7hkAj14%wEEpT|sx^mVV(I<#N>T<t9uploER~t-s6S
zub8|Bfj*tDXbLCTrM4sDwr6amaO0I?e*e}-4PNC{hK6NxpPki4u<G3Ngo-5jOJO0S
z7nOZGnX;JnVu3rmS+2lKTgFChzMRtF3w8s>ZxAT)z5s(%)th5uN^2k4|JEnSz$1<A
zuZM&VOsTX(Pu?cMc0nWHbzSYB7aYdjS!*Q(KdTHHO{TQf%SlA_xL3pgPC!>~B$3q}
zo&2dI?Z`;m)s{}ZkMitmk5_@q+8sErj?mb#R!l+K>R))!SRT6)Gu<c!o|Lb!h=4uC
z$fokSZ432kI_%uVha&PY_Pgk~PI-K>;6@{){Dg*k4?-3;Qf3#m6q4^^FP=d2s#dm-
z75|Sfo$WP>p`^g}a?~?~m`*VJIZK*?`nnNc&^F==ABo5!1in!ADoXgt6GD5RtD5lR
zOKY$<i$+UrF>)N)x>#XA^yb@sc*K$=&E@FpwF4Ce-n8Z9%vH?ll*UJqopWF{aCwD!
zhT^k(7Qxs270e^Y?zyC<JI7AL&5Cfos#)b~0=vP50Uv*6aisc3A^(uyW5&E6#(4Rp
z_Y_jA$n*FyS(OWC{v6Ct1m}WPTquLO-4Omvm(7O)<VE(8kA~)@EBgBGzDNzpj9DqI
z@@Ao&z7RCCoarw7HA-cxm#$d2#(A^8R1iVVf7H|r=u=uvEHwmm;jLb5W62z5f-*B+
zqDUeruJR<EFz=;9l==w=ZWs1}9$sl*(ysvVDz<<sF?3|^mNu@vAzo-bQbuC3sUvn(
zBq8zl7u}M{>S9YH=dyfCvlYI_OYD4Y-xL<2SXyz9<lcC^Yi9hg#BE>Tx8+$v-LcSf
zZpHLh2T@~wjOW?cbT>)tr%CufEanaAplYIHg`3Rl<;O*11x9gvSAUTYR1)b9Mj6hY
zhXF8pgPErx9dLio{KvWIe)_f+`I{1ICU$9N^@<80Z0uPgY^;ESQO;x$K0b{RGO$)q
zC*y~90I>AqPT2*UMCx&p8L{tkG(^UO(xb1kYWb0A)Y2F7L1D%|;gR?LoAa3tMh830
zCUG+#^2~7m>F}z8mx|XzLXYIb6dZ*!fHbeVn^O2k2Zqp391mAoi8YkB#cwW4Dd#+b
zS@Q;Ch!AKnKqScPM0js!da5ezc%5khNfliZ4G*~5vJSL^?>O3pg7CvDh=5$7pY=<b
zZWC8Lq^(HEcJ-2cMZs^R`%RzDHtq7xX9|O-{4lzNMB}596fe^m|3#JRxWhFBMbe_$
znSWA4@-kiion9H6hp%^@GFGEoiSV!27po#y_!ZDdbC)qcHmkDVu-XE9mWWqdPbGCW
z-?g7(9KMcK2;l*6Xv|mW+5fNv5H<z=93;ms)+@*M@WU@^(8*$CJ>aFIhGY8f%1S=%
zLmY5DTh7;t5~CP2r1-7dURe4dU*tT52Dhz@d|#-bm-~xoem~|W-x>Du^e8$pqi2&w
z2;M7Qh9d}Zh5k@A2W@>tTZi3cYUk%`XJrUT@74jY_%SBk4ZV&mngRxe0gF$em-cSs
z%ofne95|i!`hj$t=%WWt1N<D&TMdJb<h&Ejhq$7=4Re#@vYe;CvAR5nu6|NX<r{ci
z02=hYpuB}lx)$0wz_MJfY}X1kmm7HXa>9|G<A`PlJ^gRua(QP|+9P`$`#OLE&S1L>
z3n8Y4|7H<8ws$#<gFgDa48E=axM&v069q~C=^nv+&Y^RUqxS&GYHEaH?eKw{%|8f0
zoap8h2L)-7LRg>gXiQ$mYF@`Z!B=tH+*6}kWcm3pU)pIT;dy?YTNp$qOia!o`x?Gb
zgw}pb1a}*I@EFBz(kO~L+n0Y&Zs&4dsjwPK5o9+bl#fOF7ktf0tv`9clB)zhrEB21
z>=oQ%W}3m4U>8U^A3XKNEBtGw*ZlF<l7hz=PQll^S^S@kPz^kV#hUbNHqwA_mRX_g
ztsQ{A|9Gw6JCT9+n@yn$S#J-x@pXkNCJA&Gd-LZPZ02%{!8i$orog5-d+H3{9c}ZC
zPCx};gxYej#qz;6jq8q_fwtIZj^`|_*(%Q-s}jSUYPB&DLo(ny#dd~wm`#X7Q2y<I
zSW91j;I*$@mS>rS0g@wej$F=Qg6q|SdlB}{@)El3d<E4Eb4Q)gnsfMg@qGn;oBB!<
zy!5plj$pODDsuh;Da5F)`;neEB+pG7Kqba<d6p=qYL>AFk}*1uLyztz&@JsuZ6(y1
z>l_aZR?E7<)n;B))*x3Hv_+VT!3bEP1dY}T+KvqR{<Wp3e&`ted9O&xKYiusW-qvy
z>BVSqj6*qQFC#NtbN(nU`)=H+`Pv1Al2ojq6#qVpF<&VK1vEXmiez{M4(CtJ95D~n
zJHS2AWRx`J^9TsPo4I&sSX%}w$0Dm<izkAdQ~LGjAa&GG7yr%K0*Mz5NZ!DH_zxre
zHT{pYSy#m(nT@vOwL4k@L8qA7)q9NR?CEOx&d#*)TC)CVM5O}pNW7nA=Av2Q*7mjh
z@J=RHaW3VLF^QCPfX^_645!J<#b^b5(oHVhC+akRH*{4($9TPlx(k#%F2(aaEq&tB
z@(yuR&O{mMv+|jfb}#b>exiGl|CFHBLuL0v_TOVN3`J0pQ<0oK<Q));kzX%c1QN(A
zC{-_ON~HPSHs)rC?28^9T?Qz~8spSuq3R!+|Ea^XD0A=3qKuzUK~JVY;k-9wH)IUx
zaVhSPQ-AK_rVSoR*hY?LAKr{ig||i)AxFslrVtUH|G+}+*Tm5V_u?fl(f9Cf8IlVr
zNREme!stWC=^<S77>0Z^k@7z*AdG>y(5|QgamJed*o&9I<rfe)m|9HN6&retrHH2J
zwwSo_jKthkbd4025!Fq6AQfpZDgemHguahT5v21B6hVK_ZtT5P*$C|4a_Tk#|1wuL
zhRF8%svdlH9N6~X7#TsH^Yu_sO<w(a^!d}j9IgK`4*B0ajEn7r7vqVX;oNuc_JdWl
z;4XiBsI1W&RV|GrrGanqZeT@bQyS-aC0Mc@N5jL$tV&ENjP~~k)CJa^4zl0-T~0ke
zEf9{u(fH?)02y>4|LI8ezT<%2Xr#1KNt)iw*|~B3e@RwJKDm_WmZW6N5x|3UCxIYe
z-bGso3llq=<TX_K`c1~<_=Kh>kOTXeC&Gge<0p`|Vqi-42(L@d(=Eo{MupYhwGCb2
zC%Z&hGds)Q!=SBRR8odk;~I;9s{imH>R5y0Md&tbN4;8^Qjn9)7IM-{V0+(v-@YKo
zaO>WImb^$UH}QBX;AX97O0S(@tv=}2Y}7bW%WOHN0$vguFw@Nn4j~qK+wl>i4S4c6
zz$&;IHwmV74V&Jku^1-Y)l%whj~Kzmk|CrQ!vGm~Y_2h{Sqn$^blB_mq;%0YZW^%h
zHf;0<Jiyw^<1=cM;G37smlWOeMy;z75vu$q4N`1n9K76hH_j<nr^hMX{elO%_IdYg
zcQN2BO^dGnsmMq^->!lecK`XAE{g2~9O=po&m1b2AvI~Eau5k??2p4RfJ-dr<BL6e
zt>WukijSDT)P=rEy<AcCoM8Re+39y-*nNsvAR$I>PoEX+we>Aq10Ta{{8Y$tKm{w)
znjl~vK<T<1IuWa{X+c*@B+Me9ZLr7L4n|S{TQN`VrRk^lRw+8r2rl-f@ec?8&Qxv3
zb-Q#!qp{KtX1S0z9GKe@7t$ps;NZcZh8|_I2Ux|Y-+hhEj*9%-ge^8#NW)DiYX5nz
zXY;VwZBJL*crxWs>4x&CA=h87Z08?>plwNp?0;A;zl>wF0T$rO+C4f5Pj;2P5jg_h
zQ)Oa_;h-8o<Wpcv+Rq(j%kp2A14NtJVPq0Pn-Q>Tq8`L6C77%n*`QBaHiWE|U>Q3c
zeGKMTh>RC2ebOoSLjPARuq)7|?$_`6z{8F^2P*@U+FP$X(fFn2Ke_KFt%JIf?@#}P
zZBT=SD)OrJo&5AqoMn!}OChb5Nj+~~TK%7+^NwcwZNs=xRIMttiPdVYnza+EW{s*@
zTkY6;3)P}ls8JMAd(_^vHlb?I+Iv$mLn6QT+xI``kdxy(p8I+3`?@|?nD9h_ZRDi*
z&KqOzkr1ep3rL5*e_e??2QRS6R_u&7<6#$)v!bEJn@7Z+wUn0s`J0z*?kzV{Uf<wl
z;W-T%K5jlxzv~HWsV+#N@|OwqE>dp2=dZs=@F!c^CmB@4$}&3E?DMAVlMyI;800>!
z7kpYk_?afFoKQ{dbGMKX<X#6EZ{s0P5ykWMUbBdd_pYo8<<tq!Z0+XX%FFFrS=)=c
zrRiBO7g$ivmoitXfm=%Zqb!S`3G*Cie2pb){CJlc`yJQdVmD@p<^*G)C6i*QJiwHo
zn3?sl@R>9@tU*Hw(c}<@EolLKuCPXL8|wzWq}>M6C?(`?)avEqWY;J*RU=$pI1Q{@
zu?WwD8mOz5D6K5;p$2SK4B;>?d42zuNXpIIhVgDbj!^MVB;w&hcwaq21DO7QDV2Hi
zOXG5&w4?q!Kas`{OYjAwt4(q@0&+aTh>y}Z8mP8b!E!f69XlQ~kEc}#w%8#~k&q)x
zUFKf8O&cXR5d0boh_K(z#_|WPe+8oBz^g7u!ij%NSDF~(sk`vvq;^be^pU5Wm%ORv
z&)I>_kIHgNTtn;hJVV`Qd#cM%zW5TwHce)FqGL|7D!x9eAr2?!TlXcrDtVHy(5uuQ
zlmxF5yPS2)@Va!izkTlrFW;}YvYba24>*QDt(lcsw%&D+R<68W3f_>r(jzNz8WE|n
z#t~`)xp8Kp+rmfkbcQ`QNtmneUMpfC%B36%3{L+p69#_Ksf!z}sDo7^vG)>t!89os
z?TI*Xu~4d5cSqMvp4)xJBBuu-m?C7+zCu2f=dT$JvVxAF>m(H}^|dN^61MiBh9cZk
zWkY}DQ?Lp)IPSb(Q~ccI2jD?xmD6PBf3<dS_mt@<A;>jvMSaqxHgv*dDFK=#tvL{^
zCX#ABcV_rSd9B00KGNh&Ea!}8Qfx&+i6WWT#&_6&>E020>)E2f3t1_;P{&U<<hs>E
zpSAN;71g+HeD938$;yCqsV~clyVKl;es_jI0b5r=5!f>1O2^97VCIKxd00}GFR7}m
z!nfS(cWj-HG;iYz6GYianhS9wlk^Oy;jCv$9{{-pDP>9z$d3Jj5y11YW@eW<J|@Y1
zDBL(vcNRdh?*K@Pq^X;`CUc88YfzfaAk-eumIjzN4xToJ_*IcnZ-sRy9}}$CyYBEq
zynaHE>0hMy@s*(Pfj0P2^DcjLxf3wFJ0XW%4XX$?6+XST0B{a?mF*mDur??-m&w{`
zJ_1_~rNZ8sPFfcbAh{R%&9S(T$@5$pQ0QBE*35`&thw})V8psg4qQp^V{Yebmj!Bd
zPZtJ&a2}lChb)1D4?*_;%tO#R-RMB+-sxB^I#Ll=hq#gilHuNR{i;c7-kDFAed|t7
zT08&@mA{ACr>+|^h&};$Y)qrQ&yYDPW0MPgh85k83H}8Z)cfB(#d^?_`1ESC+3vG%
z?!y*}E2F+!Q+OU7d?^5P%*+KhGTcm3R;?><xzK~u<^SPKG?H+s>_=C_WNSfKFHgU~
zFXD_HC`Hf(FG+R&C`tzZv}A|YD3B6HYFY=3jKRnXF0|C8hZN6L=8GI2>#$C{<iq7h
z3uhx8>c01Pv8>6Mq0dT2Y!4f7Jd!03dU_uLDrLe(Ue)sumrs7JH{=tHuFohOQ4twg
zAyn$^0*C9dLvfEi-tSZ>(53ov5vzTY8}TpM9J2us{$J!SuSywNGVKsq8T2{LB^IjV
zE8D(!8<kMIld0bw0zGl4<ktw&wv(&T^FBPWJ?WR$kXB2Xnqk#6W6s=P{aRB0Uf{=s
zLuP~5lTq&vU#uP5ATd+p5?l`F4FBQ1$5;6B!dxXed{37r!n=3>5b!B!vr$hxY=K1X
zTPj{2krI2|$3ESwa8P&mWr5XcyHPkk%~EDY6);hL7RHp|K8)wyUFI0a+W;b)fpW3N
zHQs$Y0ZfqWD&m=6GT#2?zIBAvo$F%;Nq_+A5g4swi93+SRC=(!fLDA!>jvMjuQD?G
z!D6T$w=uz1jT`!1JW*-NvT)-FQ9U9o*T0qKj7$ykH*;2WSG{G)P3P+^9amQG69CAl
z61()NFLp!D<KK?Od*@@d7uuj4dc$+I4oVesn&<TKA05+eKD3jF5hu1t*0RG=2+OK{
z7lk1s>2D{ES5A^0*;&6TiJ{9ib^A?D3UiHy0o)bh_>ZStsa8!@6Y*Rma;CB==KOL^
z5vMo4KBUv#!!a7HOGXP`Sy$c|BwV50fP5;@xO)<!WD28SD2E~2cJ?&g7(W8TFBR}y
z{w9%9MDL;3_Cst5UCtx7YbW$H0{yDkt;Oa)JOIx1=!;8sqlU+ka(2YF0h9eF;9ej{
z<nW-BQR|NheU=0EO)}HbU*Aaaz3Vyor^kpqu!k3dI4pjDsyA~5n_p<xh?VB<e+&&#
zYdLzEIa7HI8H2N)IMVCSkY2k?1LXqWDp<S}g6+tn9)bRrCfXD&rI#|7c;E>w2u!Fp
zin=3FyJ`?ql+Vxnr+WC!vB-I*MGoE|e|vF-(k-0eJ)_jk)cyJW06WJ&3MJ1f8Vr<7
z0=NanK1=3W@qGO3_%?GZMM9qU`AK%kfT$E(Mwtp=Y(q7JbI0bDn^kUrPF#Cw^q2+d
z9HmCoSuuiauh(<sS+00`D^E0tu^Cw-&WrXl>ROT-#R&8X10jVh6MEKLka*r*V`FzZ
z*$`;r$xN9)MrGRph=M^>j4bBlr8AMJPI#RK1p5t3U__N)`^N$*0toJYTR%vA<JRw=
zphp(@<%cI^xj<C@&+f0E99#$Ta5WN8E0#C$#1Miy{|_(w->}gW|7@}5iWcAAE|O|=
zD^zUl`TH<zG&B>fJoli;9=!ei*#`l<>q?Wef;;6wxmC>fLx4iH3-NY_s5_iwN3I)t
zuAK1tVL5LsSq6kJa`B)yBDYi8zu-r=j~L)jXb$TmdZeY<SXCPL{VwS~|M;tjo?s+J
zv897<4S?*br$9NUzXiI{>Od-+3pVASCG++Uxyy$uF0o#H;7zU5rurC_y!({Cud%H;
zEcuXkwQ;O_EjUSaFz;JGI|wdzPLS;1LOS}##BCzqjXnT&dH~NY|NJUXr8~WgW&0a_
zCTGp>q!3Z%2tE+Kl$41fHvoOsaHCs{BssLPK^b%Dk8|y#^xUc(oUl58DMo<ccS-PD
z|3KrTOF74=KBfpz+B9-Xe-5jV&-P2ZXx<Re02HUN`0~XF5)rP;>757|;b<SXeHR*R
z>@$VY>>Z42t;pA_thW(#a+}_y=HAVlzK~*knb^ebPCN4};4jt4f_8%<WwWdHF}s0z
z%HD<3SKt5e-lShV<l@#txc64T0}F%aKUWH*v?Z+STJ+L$v;g_;tWeS)+8zu<Yuy;i
z6ryPS*^FitmQzih)b$sEn?XQ7J@_EI@h~(mA1u^nw?4H|_&W0Iv-?2OV++qjPNrcr
z^Iz?cH<K29eo!p|%mzXFGT+pvYXQa%a-EU~@l?he65pGTH92<!Gq^))(r<PiTHqd-
znZcjKK4;Qf%xL*8u*o?0$wXHN%K>3G=kWeiS*d_YU<bgG8H+J7;%jk%gUdB=)3aY?
ztngrM@<WQ<b#-1L?4#d`K_nVd5)&ZwLmj7;`%Oy8iysPU(D6~&dTgmF8R8@wn0bC_
z3Bf`APrfVETz;Zz3^WKxHctw>{;0}1YjIo`aZ&8Sq}XlnyW>YQ@GKW0NavoZG1eWt
zU9p^nKQ=I?{IX6WB>_p;|Ca(PU>Wf@R1XLXwG6!k7u9`vIb$P*(apk4jz;--s@%M?
zUMeBD@psbT{%aW;^^jvs%)j5gcrkMbc+C9X;P~>iEB6Ea-ChS%HQMh_wOcw=!t;ok
zdjm>|Q`gRSZ0rx-7Izz_OSNK4*zUKubnLyX3RDy)My#!2fmGS8`V$=0ASEBS|1*-E
z=Aj_H*wqU{kfRuWfr~6y`=%Mj>!}E+>F3@_o<Gd^_u5%Tc=i`qkaQ9gEyf~cJcfm8
z3b!2`LN~4Fzg|`l0iUSTQ;BdP_FGmBEy@YzD$cT74U@U2DDXW0TZxpa{JCUFWZSnm
z7uCL(%MT|_n70Msfo@pNK**!TP0Sc)&%up?IagfH2FpZIg{?3d`90=1Af`uUZRr75
zR^-*=s`<Uk=T+OiQ{;+I;v;v{cdAP&F9>OQT<V_O_*Brh*T#njq~1M>NqB`JrGF-5
zrAq1ZL&=5lE~;AW0;P9P^24g1c&O32$~)wc)UjhZainNB%grP~zJJd1JyJI-9T08N
zVn{}Gd0V}$tA-_2V8GXxx-<N@j?trFK*)bsK$%Y4kCF|0;QVW&$VtadOn+}H@J!Xm
zjN1RVM#vLF;7H!~`G-lUa^^Bm3($X6+G%hEXhgeVCmbZZPa#d-db0Hvsd#qJqW?y(
z55+(l|JrQ6C31Vi_X@DVQ)n9@*ML^K!xH7>xv?OT_>4IBfRVe$AIB)u=~043c-agP
z=-c|5#r{McFtNA3L$m@dGeIJy>4wjcX?%c<UHIzA=t3D-w0Xx-X*t3l-pTo9Dx(V1
z8Sf9M)Mm;nUS`|25(9@3CsU`mQ2ABs%5k6x*6rp>fBULxP1B7<Awghsr+7&IVUyD#
zYzDHWP7m0RR>0kbZcP0vr~4N)=xJS?>B>Qj<+G&9nqPyDrLAf6kjAo%1)zA+4MQBm
zU6Lv9A`tU)vH**0JXP;om%6B6#9s+@$H|7;mY^sW@8K6XsT4o}kGef>pz-ftS3uOh
zUyhr?cXl-H{lGi2>L*jCle>QyCf*YVYkJ$$Z>W~YuCo`R$tKppZ}<z2g5phCP(dxu
zmVUMa@7`sB76lUY*FX}LkbBK{&%S9`T~@ce)_y4NmSKX7nXt#NdC1g$imn9F;}<uF
z(WMONVH&ZZhQ{@oZM+T{EG?L+OfqzCf$5IDCK_Mki*t3V^_ol8g;V?{wGv|c^Zn86
z1tUG1=P^&*8{jVPe{>%m7Ls-{V_kDw9$*N(*KwQrfI~1AJ<DfZvi$QGLMUmHp<<Hg
zsINm*cxgnfKqNpc{g2jC?BBOdYz&_kJLc86-@y;tR_C1J%OLaL4;F&Z?VA(SdpKHr
zpI}kEjZtwfe{&?^)i5BZAC`d@y4PwjVDy|b|CnY7QlTfQr{H8ppr2C6B4AoSlK8U^
z=(Z=v-R1_aPJWOswMaciv+fes1B-%}GTD^%f&9tkXO&+nJEq1x-|0Y)`sD(Fq^L?5
z!2n4IE&d!hqL7lz9!I2;P5(+>c?vnxqUcm5u_!{Nqrqet%?)U<8p&Rh*i&W{2!i!M
z@fwZu{PvP?+)bq*gyKNt^zDcYU8!MrYvam=HQQfRN~G^6__e*x*LZSr+)gFm7mK_5
zAL|;0(V5KM((j+E#ew7<2#e_hg*F3hsMIZ|>J1=#N~Zg0b<~&ah+Riy*Q||ouy^;)
z3!e~1z5npauEZuQcAN3iuPcLa)XX18pI+<EcKh-A1^kk$kvE+ObBwEi9;=i9QZ!8l
zo8YLE?^bKi=SaVB>kY2Xc(old&^i+*`y<qq$?8sx-LQ|CpsR;$Eq!`ms`=tu9>zk8
zyOkodz+4hv#=oqqW!`IH>)+<OeNgL;rv#SZ<4Ixj=5QKqe$Vsloz8RO*s%EZW-4q=
zB4w5UC%Tg3irrIA^A)fb9z_b-u6o6d-$oTjz=c2+>>O@%?vU|?%uhcwv^-pq;D%f=
zGYCtwv2MX$m{kFJhcVs|nCGGqVmir<vWX}x?YydRJN)@b>eqviz0jUQ-m|8&Tss-`
zXFHHA9^w8pDay1&Yr)-Xce;5dP+|2u>}pzUVecL>SG4b1iTpcQx1swcQKRmzsIf4V
zURUwwwBiM!xQtT1w+EZdnSsICtCyq<@PsT~f*4b1t?L}|_~bIY5h_fTeYelCaH$5u
z<#WtCmPv;^?t&cY)nsk#fB70}VAfLvt#dL?+<~n%whr>tycam_V;KC7D&Gaf1vy@O
zO1)P9-i6{+>vKLpZy#c=B~eXSN!Q9VBUZQp-Pr?naISkLbJUfgDc$|}Qw^FO2Nnml
z`MB}vSn^Q`@bnlY`h1$?Zb#~iWzNZ^cC(fDW5iOe(*xUYM?#1Mk8H!PcR)HOr0X&o
zTUKtE^#bsdFwlkMC6La<G$?>sNIHsPVs%w!$aGGat`63xxt#+s0z&6chLT2uSDfjL
z#6yN|KRraL|4yWf-CB*TiLC}P&43^ANH$r+6=pu7tiA73qjfArnN_DpiA^GMF#FHP
zF5dUn*8-4jD6kmn%CL~ROy&1}G3nSCgCk@3iFN&929}i99*2OpojThn0<(t)t^y7o
zpO=mR5J6~2*>jY@Zs+|6$Ob%HShsL#TcYiVBp?Wp<tXV`{!;AOU)d4ua|csRjsb$<
zIj2o67dH0f?^6*kr(PEVoT_%RmU+_TVwOw<(6rHmqc1yUJ=DdA-!2fagow)Ho#>4y
z+c2CzF0ddHlKs^}T%K)W$`#&pvYi5L-C(2VS@Mvlqk2!9oIzi;r>#xgO)|2vKu{La
zWS-Q%5BJh~>(jj=%$1No6DC*{Q4#glC`hk-74ureR(8f+dPW6E8~gcG-=`5XOTyNj
z$mFypBhI+29SShZf|R6I;%*EK|M>LFnm(8DQ1u>mi8S8omjk?GHES3mkf_b=(~db`
z=5)G^+x^}U9(}Se?a8xvlQh~tc)n&(wL6CYm={cmn7W1beW#oG+hWU0B5&NXTkkYz
z!WJBbDmCdbJoMVhfy@_(R?;VaxA{c7GxP29<pZkU@kg0ETqhS(E-l->mrH#R4BxMP
zghT~Lrk9fCPH;GBSvRZ9-{&h(=jS!0*ZJ2!_hpvEk3;o8(FTbN)2TbE=WdZqd|N51
z11A0afp#U8@3jusLQ{GD0~o_sMjPk}PFlt}8TqK8ka}+)E@$^?#kJl=n7`w}8oK*p
zbS9imtGqyHP&Gk1xTR!s#(VtgMG#68SRO+8$(#E~^W>TFKc^EMWI90hf$Wu(V)L5L
zdmliyrLgKF6;!x-rqbuz9aCVFZMDv9$D+LG9%`(+?r#`Qn0zQz9;G>f<gq)vkkxas
zwj|}$BZv(LcB~)!Uy|&_02Q4(i|ieh7PParhI`uqwU?<~x3`z2$u_y~7;cKrwA*vk
z>G*W4Mt1283T)2Tl>d`TdNY-`qo(01Y~O%q(-h;TuSWNSGVl$EdPQxZvFobBu6@FH
zXBZAwk9;*O1nTHIr|q@NcGAZ&+bmp&QCRD<;|{4bybN#)MaP{<9lUY-(oo^+tc@{U
z0>aV*K_PmC&Woi3K@v&H^KwGt$=8uX@a_Wb2ac=B4E+5Cww5=O_){@{e=eG~6se4x
z0q8briyFX<37D(PFSiuB^HD%dJhJ~HG$yk7Ogw&9B9u$vv8LqFq-^y_l-aD4>1#rI
zh3Tf?SrK5L{p4i3Xk)wCRXTVISl9eFKQ``ZT0GcS(&A85`XGxoKc~vsmzPtV;_0cg
z*$!ZU{cr?mjMFS$1h)h<8qzZ*NU#M?+A*B{q&`ZfGAo2B#oy@}uKx4S{nq`~KhAeR
zF-(c(2O1(PnMK0#LpA;YQuK%@Bpzz)IAkeQi=1SXbIKNRdO-e{JA_x1t_&%~e*471
z9{P++iDwg7?G2l!3i&V<(LYZchUb26@@saxomU8BP9#vemMyenk0vFu!T85d%M12Y
zi$&>JyTr8LO;FdwIUOucGuCHhv>S#>KX5d%{d;)(l=#I~h*u_)fPkUH%YMmW9W$n_
zL_(hJsh)3j&ly|xx{4B+9K5})+J=55oLBhdSMhCyQ3dA8%F^?n;_&pw&>psuhMgBy
z8cGo*j=Vw|!9MGW`^Ik)81G)vZmgAyF$(tHOj-BLe2nx0MCgvw-UFjcQmm*x6~U@v
z%hfE9f?@s%E{i5PF<|q&D4Vm(WRvV7Z&k<4^EY9`qj%CC+7>jOxgX!llay54tzUW$
z=C<KJd-K%=gabDJD|%lE`EU=a={f(5=88r2p1F3LNXV7ze4Ch-f6RfN;y5pKc8ivn
zNeAMtV;f}*{&)s4IiiTJL8!y5%L<FeJz;F&`eji_ljbHV4O@C%w=lwR>e0qwQuP(_
z*UKe^^rL!(gf%BqfIQT=BBfT~c7IQ&gw1c2NJtbsSxSxj?s~p3k=>!sFWPx&&U=OB
zZuO*C0ZX3(88$r{WaA49ws`u~P7et57vNB$%Eqp6KiQk<B2;SG<2Ca1Bfx{eyg=1P
z*t919u%p)Ji=?Qq+f}R1?Z@((?X3<H0Bn+B)ogNKPE&bV#0!Adt|9^ztPa)=E+OJW
zLGja^Xgd^Kg7I?cHRz#P>S7w|R#XS{5GpmGM0Q?89EIg<A_oV+Sf*lEuQq)8Lq?&4
zu!m6pU&z@pJ+9u?sqeDQTH0ky28`o85s8)Ln=w=o6|X7I8cCpC(jCz@w*6~u2{eVo
zSLUh0jhYM9TJr{$Za_KWvu=A-ryeX`++W~x!P(Nm(_87EW_3Z3)e4I?13MOuR_<H6
z!7Sg>d@hkHHB_9`yWK(-IUzJ@O#ig~_Pjm4klr<JyI|LGe?F--k;jegP%wyJihK3@
zgEwAa=FVh~ak!;zGLC?`LOt{0DO=LfA(<zydA<a;HxVxQ+}R^D(#U0qI7sNXOj4$a
zq+s4W>r`bRp<&Z~HCx)SqMDuugqIFeY*~Q+`RMt00(yg7dd<sFQ1AEmEUMD)pRf?t
z9vbd_d{(;H$0FmXkoSY(^uve$_Wi%(qT!Qn;%328c7<_G<O&-J!f)cqG%dj{b5}*5
z<q7-mH_HetCLz}PpTajNI-WFgAB{e=V<l0)!}<f$pnhYXkQ?O#&i9eKV}oE69-!OI
zwDzyuOAa(aUHmn9x1#hhKqx#xsvxP}az(6$>RYi57yb{OQsHZXfzA<4K%Q;(HtMDt
zoFV?hwO;8T?HK@#ROMg#k5=cW;(zcNHv1Y~Fd~Q2GSfCm{0O$Oo~>{~P&=TWOJpGw
zCX#UvDxN&yDz<3T8ZZ>${xM@`7M;9<ncGh6s~BiLv%?A-53euDo>QR(UIZILE8vet
zo4)}8l)gV!0^bTR&~8rn)Xg|jO_!_vux8q!8;x;5CAqaYbOvSyhQGp)=<e65F1JA4
zPiDTcFP^q*%QH+jqV(dlEN{Hxrd0aq*%5*d37f?3>Yo&jj4^5cIW*3a<zWYjTBFL2
z*5y=h2f9c~hlLxC%zgqc$kcRt=I&^BI2YS0FwW7U1HfzXwlJ6d+6UjNgMy0?m%~s+
zglt$4QNGSs(lw*7|M1?vDUK2_{HvC^W7{%gRLfs$Ux%+jR*{IGX$l-bile+Q2z@7%
zRK-}i+=lCKH9cdkzeB*m5&MA?@jP#wkL~$GOt%wRUr&fRgmuCRrzR<iQu04WC0ti}
zVW?jF_E5H00bfuhoyffJxKF%~EZ~6bd(3|s9pAV^Lk%vfX70ZFoV<vca#_V}ueRo1
z?rBhdfM&i3E*lReNX9t5VrA6E64!8^_{=CcTJutd{xu%gCKqCG^cYcM=LdG4b59Oc
zEZQ`|>~)N<<I#^e(QbBL96S|L-c;$L13<${U0!*aD-4k)d#m(v{>GL4h3H=cL-`N(
z-q~l96_O6me}nA?My*uKzd+WweXb3Dy#Pl73m++W?|tuU;d60sr@$A<aXS+cReNS&
zYeSd_|7$kRW{b9>0mv#KInoTCBP;4K_oOfb_6u+g-CkGNJ?7qdcZ-WR__!^hr||px
zl%0ZEfP5-`o#G{IC^m#(ItnEo6ZVD?1PsW450$O3yd8$y=B>U6Rw#S8$gj$F01&Av
ztiJGB-{=E<=L+?#1+{ZN9f_EV@j<%Nvr(<5_@pyFNm=vMiu<iQL%6v7IIn+)dc6->
z^DP#pdTFgg7QzeAf%Yo-Ut}c*&RQ<BIp<qHW@4=>&JgOmgw1eIN+Mmv8-GLhM(&+S
zu`rIHH2BW1CikbcNcWyA?TEkn%;v3ReHo*eqIB_vVN7P<m&JPo8ybOQ)|fGcJxvGk
zo(W3`Q)<J|Oh11*{EcLZR#WK?*}HreU9#v#rb*Dn^^G3zZSKKm6M0Pi4RIBDlN}8W
zGZtynn(S=O;#n|cKLp4Pwk~6<v#pzIP!^}~%UTErx*56VPMV!f2MaEE5R9lkHx9GH
z(Ke}-TKcfZj4gyIsZxA3R8=o%GIV^M1(77zZfxbz^Rk0g@GI_SPhHFjNcZE0b+(Q@
zLJ?BF2sJ8xIIFG805K+5^^P6xp?}siHvw2bmr${d*uA*SH4tA|&m@qF<Am|#);)B<
zhgAz=mTtW=iK7IMiq-~?l?YgaN>fQDD+q=RLp6>faMN@Iy@C8|Mx<yYg$8ire4-UE
z(@07g%aEEgW*(QbtfiD+zE^YnUA&ddC9^n*4^xmJUoqDGX6Yi@$Xj(O_`N4vp-(lF
zt)OKX(->l$NW}(<U)X6*cB^|sMP=fRQDpKMcbfx{{U>58hh&X}5>=Clns}f&gR-8h
z<B-#*%JB{!n8UMwo$%Wp5E^59$@)|!%JkW&?@D;CP1MV}g|rk5%jB0A)m)XKRr>HK
zZl0|vR+XA>-i-PEm|167LkwR1JmuFW8TgJytkNV$;s67I^z;2}{`aM~H*pt4t$Nx8
z%16mwXTG%f9%;Xy5O{N4l&}d1oSN$`9q2Rn%)~#wY;y*56zcO7nWe;si9wsMIrZzu
z@7<zDman%{`tpnMkboOs{NAoF$@gmu-$H4v91-#!w{Or~Hb_nQ0euzi#`6SXzy8ov
zs!Qe6Wpl*Q*t}~>e#UDIT>+<+PXX_Lc*IY^e+qez3E_o?&jZz;QD*rqsT!&g%1j<)
z`Vqj6%veq0KzYE8blx+Pi~_dfB?Jzg7jY9&<Fj!^q7&htS%Y3_*onq%9FGMn6rEuj
z8II}lC747`fQI6$%V8QRw`c6`cMAxS(awh32@+PgBjF#foJE40#F%d%-sKcVSZSLX
zs_C3|-~A8IGd9{1MGNVnNxRBLe~i4_;Dvy?&x#dTHv-n8V1NzIHR*NQ(*mT4-iLLo
zaZ%%<HxNLZj@t`RdB90UachNc)JFJeP3*qwfR};Um(W>|RMtk9VSJshY4a_p_g&(_
z)mJsTV1$DD{Golg8^_gxs?Yd)gFo#bd~)wF%@lGl)c%Ke@Y+YyFwVG2tNpyRs^!gt
z@l!cN+UGw#1D<CClpNyQ4#PzJP3t{%SMm5}RZ3~Ee~;$-!)k)Dswv&C=06q{!o!X}
z4AbM2-^|Gtvvp@q97H6B-4JSNdS1T3k6;8+Q5Kg6nF6@BLtFNrINQ3<FN9p_m2Sl9
z<GCTWfXQI?g?Wo9z{b&E-Y^IGKH{1P6Zk5p1Haj5o03zW_pJx)a3od3`gd^LQk+ka
zYuXg+ig9Id>&!dq-XT`-(O{3=r^->~wQCKaiEq^YpGNsR!VBq^IjzGmp+(`zg5f0*
zBe~NeyY&9oRew6v%e?=?yD!9Z#2&PrxM#eEX?g@(eVfbw7Wk+BLG=qak}h)5zRzDX
zotm|0lvU(8QG$aSN9*2D5b7hb!Gq`qAwgKTlp{RHPVxc@OsA>|Ge#$U47DltnLjx-
zk?pmnphI`!76)^%DEZi@-}d(1ANR}c^{7pL`D?nf4<$MoO8&X?ZsqU4sZ<xYYcmh+
z-D<Jhr-lN8fV+)ZlLa=Ugx&AJa+b_339~heq1I%ql6RWKOi5oFb8ga5-(*_3P?Jz1
z!oSH1+r{FVGyerCr2r5s2C+!7rCl>@o$51hAwu47NDS@S+O62?7gM<I8&;6|Jul9<
zp!F~=>Bblla!c#>dF`WkcGuepgl;3^HYuN67`QI&WlA;U@3XEgKIPs+EZn>+B_*|#
zBNG3iX&FT@2gJ6tCORa!x4*XD6;>V2f3n%_CI8F5_cA7fZWw+A6<zmEW(ZGV*+_t%
zj^^+1ZB50@JC)cP4Il&GiRPgmW5Wpn30hG{^jvkX0K&Gyaz=pw$%NU|tB&=9M;p5T
zRke1u4@$q<tW<V~%6x76U}w})`l#8&$GYhr2^7d!NmE5$Y4t$-DeKA8cHT_A!+iRI
zP%7)up9#NqKIPR03YnhufHVH>Jn-Wh$yQ@h$2|p4qSo1k<DU8r+3_9!k2OG&N`+Ri
zo|)Fr(`Z)rR0fny{=G)epwIPq?;#HwA=B^**#-YkNWm}+5Td3Z5LXfR!9Gra9VJ-M
z*>oAuC!#_j(<|5^K7f51r9S)0`p7aAII>6&d8WxzsapdG6s}ldc`95t5c#-FbD*tF
zu`&P-nnBLw)8}v`+7A*g&~8XXvo^=wvs7Jvn4MsLaVql$M5YcT&&Ev!$-d|zfqyHm
z$oa7$AWS&M=6Kit<Z~@{R)wVU>A@PG{Nl(|wPR~X2IkM8c9pp8Ii^^d^eM%d%~T6{
z<uZNEJqdN~nM8jlE#0e>TPV#psI8W3D`s;7M7b>S7^iTQX=%#DmX^QmBX={A&7<D$
z$ANW{^*7%7`V7XQJEe>K7|kH@nQiKBJHJ>e%e6hK#0IXS;d-jT)<A&P0$+W`QD|9^
z{wclQu|t*?i8yRd2nED46pHRWAtcB`>A)%X#y^vPj4C=#p`zMTNC<@eR3(8y_jIxt
z0WJchvA$r?FfM#gOPVdF{1=Z_OQ9Lp3;q59Tv6h$(RCLg0z#@z;EHP&SFyhr9oCvL
zzL#SaH_>NXKzF-TV86E<o-)~MFe$VUCa3Ax+ixnefq<%h=YL~1XxSE}7?ZN30PQkg
zpoq)zE%cakhI<jXDw}Q;@ydj}^B*D&>)cf`O1qrVY-W5X9JAFBU?);0FVu4Vsl;{5
z*};5Y`O<D)o-I{tT0&KRzkxNrAV<+nHaY8NI(@ui$3RO?wJgq=?~8TqGk8)$P-b<S
z8-q*D*@8I2r({Wy4xN#(+><rqcX?cWbgJ+Ke4xjd>DOwP@7|f02kR_Na*#mYyOJE0
zW%}gm^U2WrQx}%E*QM;?D7zoQ2XdhIcaR9#*dRy^24DA>wqPBfLw8c`7%!mujX?AA
zO~_e{FMFcDyUUOkAYg>QlpaQg^3v5#)g^IYjS;u0rK<TN!Z(?g{|fd}HG?R~^tG(a
zJIc4Cw->LoX<iRfftQxgN6{)(n{H^VOh`OO8i0yBw1)VD(5wK`OY#Z-YlLr^=2}}$
zo*l(SAsb!F>Fj4ff<Pf8NG2yNir~LB{xUd$Hx!a3Q3=Iglbo_GPAXG6`I(o%dVSD`
zr`j<W7Q77#)@3rgOLc7rEW-zD<&QRHsH~O?%qR!QY2f|g_hYjulzo*$%eAF*5@JX{
zh34u3T;xE+&*bANn5|=eS-(o#Ya*RW$BaeVgcaYUA4*otRG$@rom#noRnfOK4mM2b
z9&s}E1^KOGI55zPl@B#C0e=9xp1jdJE(KA$eDc|kg_Ae$OG$30&jxC3G&-O+!d35)
z^Z|{0*-ems5hSJ%;@kZ~COER5IKQYAuu9&&Qdb5Lrr_(F!(2f-<ho1?v2s>Vjz}>O
zJLz-@dQ>So%V!YTRJ_447fQRfE<=PDdU6SRW=yOnT~w_yhzG2bPvc7t6eCD=7eB67
z0*|d-&sKsp`Zexxla_3T=<!qh>_?ZC#J*BHwd43xm0sK5W8tn&_D6NH?-Xe62e9ZG
zTpn^*vr*+T7J6jlYquqZ(X{#vmRA)orVEp|1bafCHpEV)mo$vXmD0bRW&jEHhTL0E
zr>>0uUT3-Z1PEuz$zhv*8yZv#W3o8X^x~n5=}@P*ie~jBC_V3!xwrA9$2jc3FHwf=
z{A?|@7$n{eFI2ol+;0Yny-U^Y^?a~wKRGtWF|>My$k`eM$XEBD{knP}ZumU(G3?qE
z4~UpXQ3IpsBvmq%?zBJG#mOgyKyic)n`C6&oav3kR!MPGsSdNBj8v)&hpygw$<s$g
zp08o;QDV=-3pp^iZ4JO=>x0D`*w2zdgzHo0uB+m-_C)whn81H{wtE9Y4`}{og1d_C
zw@rdWpk-)rB*Z0)P+j&xRK@1Xry`;n`@E_LAz6Wwz0!AVV5MxSy14s6t`erIKz#%e
z{;~esu|CynEb1Q$mgqSjeztHfe!wkRCa}6dw84!zE-wDSk9XY&N7Fgt^Box9hlGOv
z*&GvhW8*|{1ph`dhAP@Wt8X>M9HgZ;iGYw{ZM0gw4}=G#R5ZB0B;db!OZ4hCHUAmO
z;cAEjhBzFwOt-4z&Wm8&>-iY}b+-W@RagRyh7sNMGtVd=Qy#d7cs>nYp;GoE4htHi
zv(rT{i@2vHKp|+&M-bnx(Vq@OA$f$SvXZQwMHITq0w2?4;ZS}e5L)9I6}D$n>ii)!
zN;%hPLmP}Fu4gu$h#cQO@n3TsT&ECvqLao`L>Hd&4)r*nA0hrt;kcpd&a8xRKujFC
z;qJ6Rh6Iv~dgb6{D2F}+M(TV$@qzkHb*FZlo?Wu3GN_F^NN;p~oRHQ@7k#4#JIRvw
zr#of_r*iQIEOSZzxqnZFW#ZcWQK$mxk#1A`l<R+ZFQwSdCpV<zJ8P{+t@N!-qv!oI
z6>%*p4MKZtoPI-#I}1L*agwxRVD;_l4HFzkL!p+wK6*xs7<f?`QI!hWD_|RXfp&Y#
z1?1Eo#8{x!8w^cj%|lYA?0Yje5NYE;u4&Aje>1L}+{LfgRO6+vHL5mO&2xYcJT2q|
zFofm+UuLJUPP|F4VDDWU#&cu5EPwIA>%aC==Rito<P)o}8StM5PKXDCSHXR_lqUc#
z%q$w{G@5JQ;R3|v&(^0<t0uxTevtUrbU1Ey_;ZE5VbC8OcQQc2l^bS?jEur^7*J<r
zu>4EYK3J3EPfmrz8aR%N?-8?Ybr5rA$x3_&{#L?#RNes!NGS5*02y>>?TFPxh7%NT
zSM^a`wnjq3Yai$)KMD=K*a#(#tsa}j^^em(n&JAZWhSGjds;wH1OFiCN50hbkO#|2
z)qhY7iD!Z<+8@q?P(ad>SUiF71jk#_)lFBny}h0;_XiSY1EKX{?X!U_Ht^^8hmQ1b
z#wJ0sDluiU^mbI(V2QndSIjpn{qegMW4wmjrf-5^2PEwbia5HWSp<<=5)~=7x#7;4
z8Z1#zI&z$Ij`tUMo^2Vgwby|DRld3|QroIey_GU9AAPp~H!yxbjz1vR)_Q$ODs*20
zoR{ZDKj#~V$eUiNcKC$7n_tN9+sZ`w04$j=&!@Dmz<d0Dd@gXk5Vz9iY^@EXxR>t*
z6)oVEHbB~tw0jLsk~lX}+OVOoy?zF$twZ0PDSaxmW~E186*#r(aZ~=Uj`lPOk|NEQ
zKJj<%!@RYt3+P1+`z7LF8)NwUjsO%W)~2Eqt5EUm=$4UcDK02U2NH8`baMxcF3zQ8
z?qll0q!r}M>1w!99~8niR?fu(e%KZ~?R*pZNmbSgm@g=U^z#Okt!9JewQrIEhVn**
z|A+JFjpC*9qYb`?jHHM{LpLT9nc&2Z_4>E?78vbbO)NQZ{99Ks1sWB#vL-Zw28-)J
z^R0(*^bd^5n)evR9kKP6p0!MYDmugc_l1Lh*QiM_z+AJS*US;9IqZ*({@{3XKoiNe
zKNVkaa0(kTFo$(0`nPYg+?@&)>qmXuR-U%#504Sk^uK8B`VTKKBG<{b?y_do8AxJl
zn;h%AD6!~ciX79=1JY#rPG-J)v~PmSnE=gLYeWd<2mWq<9aW4EVV3F#>xuAnGqo?b
zP@EoqNe)e$rJvcwKN`S`rS{tm`zeE0PV-5O7=;^`qHGI&SA%VZoCSv|iiQ*8vZTu<
z#&f`Ky$dHk>in)#3a!doR72l${4q@mY5#(|&O21z!E!Vr&MtUZd`juNW+bmGO>d1`
zW}2sFv(FH@Mc;3dJ-%iEDL^Hxj3;Rs49KirAm{s}J%uV%I(T|Ccj_yMe=}!0C++4F
zUP`*B*D#)2Rg_rtBF&QlpmXT0`2>-pacf*X(|>`aR$oSDY9B5j*Yc7H<Hm?jCh9$q
z$D`PLIjy15<>M5Vk5heeI6UR#pgIL+I}jV|Q4e`m&CET61566&qbC35DJ4BPqwM)}
z$`~fgp@gt|KT6qCeHBwL#OYKE3<Hh;N`<iyNrQpY5=VO5Ar^XZo6_`pjqAGn4jPI*
zYlQTU0jjDaIR<yxj$fJcjfo_BfdAa2M<NOhpw~%03Jx$Pku=EM?O<yv<jkQzEs}^9
z>-;k>iaXM0d)SJ*0m0PWPvS6jJ5Ta~h>yqBtbmSeMQmfeoTKv-yxBO~U)fyLvm=!c
ztx>wYgMiXBQ@A~xN3_wVUjk(HM+R&DpXzW&>?cJk5_l6JvhE6mT*p02AiB7hh0GqJ
zpwkqy@U!mSca=2<ZIev@lb<Dfp0IoJ_8?kS@KN!$BV_GK3&?kls<eXcq%Tdxm3bx8
zVT_-iG5sR<9_S>+j1K4m*Z|nIsNPxaL~D7&<*Il>EeeECR$v3K!~DC(SLYka8p{4C
zfpvRlot;^+8I;^Ljsdx0T&y{9_Pcy<CULLTQkE8?E6+&MYj_A=w?6>%<fYbIdRV@<
z{Pn4u1@<!q{^y05k|<PxC=KobtKNkz&<C#2@7OBA3lwmnDf)=1j?2WKK>mKo9eATl
zhzFH!JG&eS5!Pw1Dm`Xj+Q^aIG}I8R_r~Ky!c9H2Br@MR--*5@!t)$1-3N*>aw`3j
z)sYGF21);><bp7BpW-rygc@k^1W&n?80FpejX>JuS!!CRB;e;mk>Dx9(x%_GE$lZj
z`x`UfbJfcVJV1~lbFV=VY|47SK5TP_RjJk(aGjMJEMweOTDDs~D(8>L-|3H*lyIYn
z8bc34X*+i`3<p*Y1W9lCywvDj<uh2Smbyy0X4bq?4Q`lfTq;O{Uw(`R=<E0;-U|U>
zduBDj!J*c0dfGA);-FT^LfnaUuum`bls^}X^rCO&kLMy%JjXStq61MQ26R@}2H4C=
zMX8s}b3R3Yo5uVs`V01HbT63or|dN(JRe6rw74;-K8IWR2|4X+y;#tc-r7qHclDG;
zX$aZ@Jyy|xa15Z8W@7H4{|%XbNm2oYIqzFqA8wo$m}%>K^~wgi6o`B<r~YY4$;EgK
z^;lgfG|k`|&3))@zQ1zTubpdbZSKS+L)}5GTTW1O5<f2cE8?V3n?wt;RbaoIGi%%r
zo6i2zHL9))t`B6#KAlt4{*V!Rp1-HsPUY+THA_IkwRJS7__Vmd7*L5^<aPc#Tx3~C
z2yq9F^F$JcV8TcMYLv@&;3#2CtSm{3csIjH{7CGOaJIX|UxE<zuj;usVSjAw@=_h%
z8ikR^H)AFvW4}L;N4Tm0)(W4K_$FOn<Y_MY4HAMnT@0EAEKg=J5ngeDZ&+yz2yx&5
z0FTfFd}&cm{w?f4rz5g{S(JUF9XQhNbEP$Np^9Md%)zva_H5^!^*KyHbeWMbTTziV
zl|$E6<8PpB0#uA!-;gVyVZBDz!cF7pHRrk~Z~E3do(FapQ79)C|B!y$Xe96+6#d2y
zuVHX$WjRNd9h>B-Fj~PEm*nhi<BZ$&U7eg~WoGEL!Ay&;PLE<kz-q<MB2r*OgKHjx
z1$Xx75?6$c8WS+3Z_g!>*g9mPye#O!<4F(XH(B6lLKn^q*on_`$p|(SNF?K|+j;eV
zj_Z<;qNi<68d?ryR(*>H*V5%Bvv!u#>DH&cv(caKH<|OU?+XjFnF=J#u^7m;M?Cz|
zbrs3gQju<{q>-Wbtbv`RO+M72S{qvB1!E!mxdF`2mFG#UGf;muKljhC`3^qU^Dguj
zv+aofzRu;%O*pw#gm`HD@Y<5+q<lwd@+(mRIg!|&u@FR91CuGpC56>?CAsP7ya)Jt
zqDA2x&6j{|Xo)&7dYHX-98c0{_%$QN`W%vAZjvfiG^-oNI~(Kzs^p^06X4Jdr^Y%E
zf&ix=Y-@#em+gtYbAbPUc-{u-A$+p@dK=)B{B2d>1SijU>R<L!Ly1gyqmh>mWrliJ
z?gH;_2>nw~dcaWJn4g~uKpEbJiIBuRL*epy=F^uS{j}6hK7+M7Y3v&txYsH}?%7{P
zenDI$rR9=OR_#-arY0X{Ivr$|vR~VVG-giXrY7kjLRcbEOpq2~%OEf_wZE(c0#-VQ
z(64821__z#4*68k5!!Ak_NTzx=;|0zxgL1(6hCElz6BJ#38<e{zXUEk`(?vZDQrw)
zSmVcY^&tn{XQUZAv!qO2htL>z7fsW2BJuhK&dYAn$I&I;Y_8WM`rIvXN1rZ@!++@B
z-MjMv6Rv7YReSKpChE&<m9avx6FCgdenDIx6)Vs1$_|`P3+uL?yrMWKNbStOO)blL
zHS~9wP-&VOy>)Y3UflP6<+L+P*RW3)*n;bx-fV~8fBX>u=s?#0o%x{x{o1Fc+Oc*x
zhV+CVKvEq457~-#W$EoOhG1cT;V;<v99aRs@TjhfB~{#`4%q;9sz9n}p9kPowmGqW
zNq_YnkXZg%an*+{lD|c~G?h?(?V-`J379j~SyF}jynDQa4hYT+Jx&#``uI-mLo)c#
zOK+sK^nu9dv)Qd&i+w?$No{>@Ebk-q_RoAAx2h`3gD0u4pKlR@r<MEIjEsJ>Bpvk0
znjOIe1PZJtB@31!pI>Q9IEY|8ChA6`l4|cn<Xrf!Px$I`Bu!oFyk%3a^s2EzI>+g_
z3sgnj7y4ZQByye<g?g%epLD7e##GAn$?o0s*x=A!V@&V3la=GBPwxfpj^7s&QmJ?&
zZTCZqP6as=k?-_-B{(5)JDtg5Zfpa=52_H+losy(ZqIh1i=)1EBfM(48V0yu(2oAC
z_6qqZHHZK3dT3$ULdF9mH_gZmAj=DC6)v(GNSNt`w%6hLq|3HB{yQwrxJBye{i`K)
zm*^1<xxlF!wDB(a58zpnedd$%ShKkFuXYCh-6*bG8?Hs&4}dEpZCoFYR;qmH-)tHb
z1NC<`xDGxH8h7V1`lfic*x#X^HE7*L?88l250E&O@5Oz6zw(j&WPUZO<zPg3A~swp
zXKoPD@L1tU_49n>(9$MlDhx**jdy3!^5!THLcTza`>`7In#kv8^<SyInVih_R7Um|
zo+`2HU^$2UzoJaR=Ac@x9p?~DJkEpGcbliGjF|crw3--BsA}|uK?Tr=yB^ubQW^VQ
zvSoF;Za&jkPwgyPells@zdH!ney2SB%Z8gz7pXLx%ZKtDpDZ-;QSSqhvX1w9JXO#Q
z^#61jUrjw+cM$490PnWN#2)ey8j`GLfOm&*N?cvwT#1p45$j0a2OO&F<k%q}g|P-k
z_J=Fs(0K=M53KO&*-WNZOfKP8s5gEbj>8XvI>tjXmUJ`~D{~#j!gWmcJo5QyqHFdw
zx%LAkWfYY%{ivgZ6@6)Gn}A_7Mc^%<4Fu;kj1(3ihX&~=xSXU_S=1On>cl{c%6Yj1
zA~b4yXL`Y+(L!Qmj%|aX6dn!4#xW=F(xuAkSnfaxR3^gHzG}F4@b~z<Zf<Oq_if?!
zdl)KbctqAB(5`Kq;G*B-Vq`>qPLRlQHdM-&a{Vh|%}dp0I{LTHQ0ir$(_r~9wR2aP
z%z7^Psp=F-^k&@2)9`eVX=-;8FD5hPt&_@jKmoWLSZ})DJ^)=jLjw>N)9;~1+UrlK
zspfoSv8Nq`xrI#TWk;z=o#5@PV1u;;f!bW30yYs(--?#end}c@yMb-@-wv>~?Mf42
zKxnkp-r4KrXX%OUZz7K}^-+%wKdjSA0o6-!Z6UGq#|rvFE?C%eMIuM<va3WT+U-}(
z={usJOeg=C+aR7v#=I`i9V};^5D?l+(gGx%J{q)7^=Glv$6u#V*A1h!FD6bGA2zBn
z#jYGP;mxqonRSTe#>Al=sheAp*}_%CU#{#Q{t){L&zpMYRngM@qX5<-&xAOM?<SU=
zA!Oy%Kbh`8{koOxvnibs>cUQ}s5>c?KPSm}9$Me|N0VS)`0CTqnQnh9RFAmpV%TfN
zdS>N&9rZ<Ne{!i1kM}~&Y(NoL5QbU9>XVSW^iG3nt3g`SF|yte?9Hk(LV0!(toLbc
zSkZBDcog%tK-76|PhHXo=oyr0^SsiR?ae<hQtXi!ery(IacNutW@t<D{etI*H%447
z?S?)781++*XCk#@=A||a+6yCERK*jurY-KO<+VDdXG^&|@1m_5-xvw^TLZiqlO{=Z
zCj@o6U1;r#Ef{a0|0{dW%}sCa*CGo}tv1feSjstL#r14nutex1C@_jiJi4xA=9vJ7
z_IDeqO&LKb+Rk)zhbBc_%grP4ANub`yMfm!c!KAn^We5|V>|PtZua6BXF0m;5vDpT
zP?zcxFwGlkvtOKvx@5~N*a3Yi23ns_msI59@vIT|>93Va-h>zzYHIlsz9Yxn%zQQ4
zv;GzrxK&zHl<LIpKG-%B{@J7_K!*6;kLkwABCfyWQ>5iaad%Qeh|FSNKgi+${Ltzm
zRjWT5;ei_o5kI|F7MQ}E%S!Mzm;)-eHsf}F1B%jsvZ|6l3rXAZB*jCz9$C@TK8^*<
zeq}o>DvG8D`1-J5(#<ueVmIo&0rew2xj?-)=%Rt!Uh?+5aF+GK@2b9H$qCpP{aD>Q
zNjt7r6@DmzdS}llhQpt{#Hf(!H!nq40uvfuh;Y}>6xtD}O#>Ul`276|0w%Q%x(XlE
zJL&Ai`$S^sia*tj*o5tLMie?o*MH<v3b<_J^pSsi5;t#O>F=PFmVFB=Lxx`hl??cm
zQXKV)Um%{t$?#B)8Pya(Loa?Uk=~P860BL0-1~%T+i|!O`n`o&;UC(YE-EsX<KAj0
z?es~xsP*WEY#49#^o8#oMtyBe%FI-Q=N}r}D|x2DHC5l$q{-3)_4Wt#EEx<lPo~8E
zoS8GIFr_iRK6d>FgDM*u6oBaMdFNo~p`&(`*aZ@p6nphO1LBkb&FVx*<aOlRW73Ny
zc~&0aZc=don13eagb%JpXU9$%(k_2?u8J3h3pMH1mAm3^e7FJOid5Z%;d@TLSwMTa
zdvN9w!FCau14>^Fa6yz7gQ$KplZS;k;y3L$)Bvn_YAxK@cqe9TWAb4H@VH?sQkhAr
zfwLsnEU15IGA@Q-yA3+eYY#RLO+lO_?y26@jq_c2ySKJj!ks{(o+=AzK3dWsg8&Z3
zd}hEhMpT5LnSZ*@sJ*7%&V(Q8NE`CBr>6!VSHGRuFA;m6T%gWVgqLQ$rI~Z=R)qJ|
z-}8^kv*djhb=_}9<+fjWX2R@({PT8i2MB<fye8X|pVqyOd&U$6f2dk%0U<C`$mejx
z6VM9>>V)OTQ&iYmEh=Lx6lFoD_uk~gM$2m5p<ZyjI>mdBRu+J^*XiPVqcra>S2N5l
z9lv<$BJ!YlyD4)=^M&x{*`k+@_+@s|Z%aSPK01a*4cmpRY@|bl(V@#a`6$Pz@etf(
zBG)Z-I$eJu#GLGB5$%BMKi2$w^cjsecNnG7&8*a=%r$FEaE|h1pC5HW9ZPN5H-fBz
zT_Iul5q8JcST6kSB-{nh<->#9i=?{Sb*JK=Kb<Vr7I!9UH&Ns@)fNJgA(Rf(nZZ&r
zupvnIzlOK@YJxQjOgaml<NAKZ?<eTwv)Pl*58fl1`n_UkqtAZ42~Z#yT>?-0q1g|W
zQkm?ueUBpzrjg2(P)_Y!h9b_tSgvsRO&?xDD!)0sLYRLiat0W-H;C7^{HezX@GOWA
zQm&fP%#teSx>iN9cM;A0+oE<$xRNrT8NpC;$v9(G(!D;8##zQ%+e84D5xq+ibr^Py
z;8`h@@^+D<8m^wfn`qcm8I}DpK}EG+`}E8{1t<G1UVcyOYazKO;)P?;tXdp-fIr*C
z=(9*SM&IlBoE;u4RPQ8paCPu{YF{*f7|w(pW#n4^Y?93+Jk$+N{RBL7dW8Wg2xxF9
z$v}_P&2ixw;miFS*<gB&Oy|ty#QVW}7Y~j68Sf%9>I27QshzVJV?!L5@SmV4Q|}@(
ze*#TCV;hw(B$IJtIg~ZZLo%T5BDVXJ*Q49O9~q&0v~hQQk$Dp!#s%`wy_U=JgEcc@
z8N!7az(rU1aZABijF3*7;YAN0DMUvHLH|V3=qqrc#^Y(!7Lp!p%!d~^mPXXz-Hhk5
z?4n#oPhQ}ki-8_Mf#S>VvFKO%<uDMM72p9XE#xcaaqzu$ApGJIq|0Bx-nE)o1V4(m
zLTx=+SbW&^5a4<RCTOq+z6oj5R5<-`Gww|yEl%MwGU0*N?Hj4oQUr`0ZmfnH@nA<T
z<Bt~=lJ0dS8xvu|bI@AY(2J*Z6q;X|3%C|%s!?<~`1+}@{x7pi>w`tdu>c9LOwKp=
zHj^nyq{uYrb3m^RuT&OX#P;Z7e&6dQF>jE#6p!$%pf}yFf4s@{dMpK7hIl`ITbf56
zGFrszJ1N$!ov|4v$ubG4sdo-Rcc>e`=W?-7F~1YQGwz63kQQd?OJ3kJ_z$o4JiGa~
zO~Uo&Ywr+#>d#TMF*SP78?B{fbwu9O%+(A%AEw-9w7D2&?f5^A&O02gu8ZP2Q6tgY
zC<#GCFlv|~dheo!Aklm8MD#LRLJ&mnC3*=_heYqu8NH7>%<z6U-(T@O!Q<XJ_uPHf
zUi-J694`<^@#r%+RYW{e__l}j*XE<}_OR71Pi5OyWBKOaLE344YOfRUxOiJUFwyE)
zX!S^)egw+~SdQ;L(BjOh1rW!hI_I<FxVv~duNhdO{t_0Q6YhdY>v3T2bKbZAQ*Lw#
ze{AyoRvg83gqcK649NUBAor*_St$^1JqwPJrY4NF#<iap@keV(s*9tW@Pesb&@PGt
zRQIat_sf$qW6;+P*jm0hdoWD+Qphj6gALUtNkg$~Uft#xa00v;LjZ)VHF&M3BNx?(
zclvxre$_gn%YfNuFMWD5C^W1>5dh4)w7A_Ly+qZkLC=QoaYA`SqlFE+MFIj4c104S
zKXl!VK5CW<JEDGcYpg!)%mQG$huvc-3Q~61>Rv%kk-@*auDgpN6*VdI&CzIl;XqXN
zUqwv7U<fhbqJOy)=L7f#i52yblw3|<7Gz6(VLrE?aHaN9NWsVb?MwmF6dUhZKg<KY
z9Xx`azC^4(hs!)@G|Z^L^p@Bim1|-7JePg|xGv?wr(cGT2;;|bRUD4HkVs%FARr4!
zXof8F$Zqgf<;97N3SIjGS9XF8+O^*K4#tXcs1d@ws%t@pik0E#bSN*o5=eyUFZN|-
zt`#M5(XXou0WjisFcCwpyHxqm2G3=?QTZv{Lwk|Q#w9>u8yai<*Y$$wET%fkoSe;$
zehc9HU6w_J+RWi5AK<@IXz9)RAwITJL6iBRi1O}Y3w>GD%8?Y`>spa(JkS<oNpQoZ
zOyK`4kKX+iZ%?qR2%4eF=ewrZQld62aE8sRx^`#~k!S3h`xcTHwh~9=?(4qSwY6R=
zftdj?p6*@3eL&q5oWES%0umuCEqqt=aw8BxT>xj>oZ~)pqi}}^{6v#;<rm9m<#%)Q
zlvhc9Cn`>tb-fy^;acnqC@aFdz)yET%u@oq;n>>|J;P>GnS0~^Pk%3Qz>aaK0#Kig
z(s985OZO50V0z$H`Q`VL5caNs-jveJ6M9iamJy(z=L>?`yX}f<v7eq^em~&SG}c5Z
zI{H1|Uo|xV67LXQn4qq=7bk~|DIthU_=YV>dSXOL<oY!E8k6pv{1g?b1gU?M1CUzh
z?UK1Kdjps%TE#@kgLdglJ*)UZLU4E$_Y~Md+!u9C{iTzUFdY2#vTUvg*>>*68Dxud
z@)vC3=NqD87cMtuNDldIiZWhuooc-n``#hy2u<i>(#7ePAoa!mPPp)OXE!v3fuf9Q
zns+^me<NtsIL+5Xlk9p_Dl?35u|Ww=h7F#mv>ogfl(Ppe;o?_cJ3pjK$&-vtxm$BI
zX%J*KaqWtXxT5N<vBT~}AzF-oEWAi=PJXZhUN77olz9CB0mhccs1|WC!tT!1A)J$i
z0}pnZ7MgCIVdF&6CnwsSpNnwY|HvMU*;|M}AI^)+%)5qk_1iA4%CJYpyutIjtlT}k
zzyrB6p|2`94-}%GJ?@Jol(xmOyTlKD<P>gI%qwC3sNdN~xG)q=-WY(^RbGTO%6aVD
zKQ6Uhg+G_exd<JDJeU30B$#@C#E;<wl6-%gqql1ktYmesH%h*R$TCGr2h~Z(kD*kn
z1<v-)YOnuk=@OqZcuTsb%PJ6k#;iJ2<(U*Qo)No?ogc%#9&MOuQR8X^2dr%X{((xC
zOg9YA9@6`Z1TV;<p?3pKakIsG#jEsQrrM!uvcHQb<f^(u8mL!1bVcJ2+ZFn3&<(T5
zcx)dMJAs2(OE%FJ)+9_FYmtz{CXO_55RW{vkQ`!SgDInkd-EjDhE+>YFz~hX!u(j(
zBl!)E|FHP1y7&F)N+_s1a@}WO|2V^6c0c0B{c98u+0UaQrtdK})4GYDYd!;VeLh7y
zK=c$g>-~^3FD29uMunSk#Yv_fNk4v(P?^K92Wz#r8~6H{*Od47b_&{rc^$GfOsU;j
zvY{}_m*z2GM+7Vf{dZsa7jv?w#v=JCR;Qm}7|P>TAJME+|MX5wi*$LE{AHf7(=Ly%
zB*OXwK)(Wj9y_NgLZFM*M1RbTn#{(BO=Y^VpU>)%+<<_wE7e_$Uwj()%C9Y*IrtKE
z8g1hAs>CWs!MGxU*WBf&zv8$qqwMVRbx{3f-uu4O2pCcgevhvKp_{@&@30){fuv^v
zLj-Jl=#aZ&{Z20kJpfQ{LMIsrzO~z!BKyTJD(JF^%wfUYnckm$NbZq;Qi42Ur$k<u
zr2Z-t6noc5gq>zHJ^j%^OqbU+<B~JKWm0ZDZM9j_)!{ixgut<56Rky%y0Qm9SyK3W
zlv&X($CO(S8>p!H<d}|C|L9e!ZcW6+VK5R_Z5Iuh%NuYF%u|${imc1$;@z@F6U(fR
z@Hcf|g3rJ2?yl}5#7;70IYX%TELlG(_UpPlwxi#Ab84K6=2F6i=$RY4)=tu**nWNI
zCEl{y2m<pDLIq+YFmK+6qf>%E2b%2u)*K>4{ENDNLIh>76oSPbDXMxyWmF{JfV7=&
zE*6bhf>Xk`&TcNKkfnRvXZhdX%@bq6LufPzX*6@Sgp`5ix%?goxz0Kk)L6aHneok1
zOEG_n(R|A1o%C4SBz@Wn$25%FV!FG=zS6fY3FKy6wZTYquY(QgDS&X+!Uqd;%^L8(
zegpVR&C5T;Z^!vBXAy@P>@_v9&(E;vA>X)DP}M6CZxO<G($u8)Y``)OESYPRRIHIm
zBslSq^<8-gG4Z2d`HYRM=)##8x}pmGdKmcn&wZ!xEracp@YULi*9ABkRc;5P87{b6
zaPZARdq3)*x2ayhO0)G}#LhyXbklqNvzUfL*scfw`Sw$szUR&JCDEx^&7%>=Cdlxr
zwlqyv&vnA=t#oih_c~+E#`ODtzQV857<slHX~lJQv|<e1Il0s>4jLtu@%Skw>K<Re
z@HB-V(<O!|-ml>B4NJW<!Nu&a<nX`4K1m*e6oe_gqm3vqqWXC*2wNAfqK<dPdbGw|
zGFbu4jLviGKk+aT0hlsB8<t6Z5v<ccl9>dDk80I&`E_H14wFel;9t&?Lmjf({G5sf
zc(WhL(C_KUb10I#lQ`|$QRy~|eU58qN`)6eHdaTI&B@?Jd~JRSEw%6}J4LeZ^nf++
z>fxf;IM;Ainm1UvZ2p%@gRQ{y^e<rewubTk_CQT!fw7K{)#a^Sw5R_pfa5YEobW9X
z>H1K>{)lk0Fab>WCNkctuH>#jj_#&l4XKt=I(L-u{$1)>F|&uyaML8^LF~Ahs)BA<
z{i(5oFMz4m)JQwVhaUY&XjNtRI8c*VKJfejZ{itVc{-VnGLZ_UrbjAd7rX*c8`!uG
z49T0u*oX4s!U<;gTQz$sfkxKBNA0zj{cOmHj6LU@D=K_|1$Ve?K@uDCwdym7BlxpX
zhaHi)lG5$86GDi?LfRx}IxK%yc-9e!G)W(vQ%T*y3feF5ZE{TblBoIJ*c_#NvSmu5
z7EE8vJ~!W(qTn2Y1!P=jwlb}Vv5aViIPaUEA9tAoXhQq0^FzSO(f=w;V6tXeKlm@F
zqPs1_(<zFat9KWrjC!+A_MAhom9IwL&AobR3TW^Bv^clBFBC-u&zB})<O7Oh;1SfU
zZIIj0@{<B)H=XFl)Jf$o2COdNOtRHXDERWa1V-^U`J9vJLOA!z%;NI%FSvIhgLCo0
zxspes8>cO<z9%o=qRK}_v|*V7tmK92^ALmW+OE1wt~IqcQfD4Yoh;MeYHbk930N)(
zLTZE9?>Lx8#H+xik*`f~kMZ9@BVEXaUQxKcMk)B{W<_4~vx?AzyH{3`1*4OxJ|a82
z`0rsvA*AVqxFystPb+z{N3Q)zb#c}^r?A<<30=#^4*UN8UZ3u8Jd6L@QW^``WDQ##
zOx84I*}}K~!i<yC=K2||Rkxfhd*i9|&8dy@bC-U=-j^k2mBa{b4rrELmTpfzx3TK*
zzQ1HkqljrZb>DlT8Psrrd>{Ht)z9Q~qr~j7`u*8$(7L7>qoRB_knlER>G%otd&Jkl
z0QdCY>CwdzPH7yTxLpZ65WBW;c2abvZ}WK4d-aw)c?y)8o&eMen71!t5%~%m`XE+;
zK$9tA>c)1oB-;c%I$59Ld`FG|nGsaeE{Fh3VAF4*%ZiWxVadw2yFcFLk*%_=3;%^F
zGZYpai@P+yrP;YhfdMKEqS}BKF~O^a%2Jep16(gF-wIXtMFSa_T>h^Q%szdjzKU>k
zM&AAk+q-W+VEM6aE6-~0=?VewG+#rsn<HX=s+LNAC+3N6?I2-UaU_zX`SzM{oVa5}
z=ru%D1pZSI*fvwcKiA`~vWN0!xjYj456k@7HJ|j9q%?xxga7TMWw8qbU`&DlB3zK3
zI)XRn3Q18hjzh+15?n8OcMTwV_YcKe-d$K}gJ{ja+~_=%8ev5m<OAEW0hAaANHL1v
z=YqT+!fhS~=09oLp#JWf)%KJdX7X)q|MGo(ZkUe8@+T}fArxO>qJ(rMH6JB^iH-uu
zAe|r^LykzVe*{fj-Puh?zd2_AXjC3q2uiwYI(|v{W-7f~q<m=@7}}3@z8sJo^0**T
zVKlaY1jM7Y-57hjGu=OuG_Oq~*VV;v)Z#VKGh=Z<?<0Lovu~%m>Mvsmhg0iAx?-`G
zfsNKfEgnw{x7tUytFEDOO^j>K%c44_lI1lN!B#<uveN$C<=ah#&Lr^kJ}CMNuN9;z
zn>qa3LW$TjJoWWjH|UMe9mstV?mO`<B|<8JEmLQxpatTRveHUzR5<=7+XT6bZ>hR&
z_S%SqHd<g`sW=yZS#%}IV~#3xnf8`}G#vYuPr)mJT5|<<N}ZHL+yXF6e?tl~^-iA@
zh<9K@i#gt)edGvHQ2as{O51~R+zaC(P}rbp*1&C;CWJIh5h#}Xu>dF2gSRPFq2xhd
zvIDJ(i=_<!ZU`W?5II$!T%O;1@t`#Rh7$N-`A^||Kt_b_riiZpn>AP%i5kKM;=1)u
zBeMzK+F0FRafhtaPi_F+qHAFs4j1~~h2<`Wm=4!i-#CzQTPArD;qb2Fcl&fSNG3jT
zhyo!W`WqtV?zUMb)ml21uru}tC)n$UBbZw9X%{$wJTg0^ATsX*hwsMqljpKX@B~6#
zE}`3sW87d(g8f^`AlIJKhjGLhCLsLqS#7)sGPu;|VP5!@t*|Mo-oRN;;2JA)*IZ|U
zG8hx+O*K)qYhQ4j8`OY320V`P)yjkC5+UwccdgYwV3(^O-^c^EKqR&Vgy!SNJh{~r
zlMHEB2p1na;`6=qL*8#G%=x3aZ>n!ENn-b+;=rYF#;kkXe|5u`9D=|mOd09+ta`u`
z?$#&QaB!zW%WqM}${fGy<PIxKT6b74wJB-^%Qvj+BonI-&Ds9KwV57>b<0flggqP-
zdqi<vcmN;<vicWj08lW-f&bLF^}3%IJ0tK_jpz!!6kt}eJ6LyeOG|DHIr?4^x3LHx
zqS2u|(F8t%9`rF^DOKgKd`W?d6ud}5LZ`l&c1_ZK%Hhf$c8QmTEZkjo0#|P}nP1Hu
zIH?-8z>j;l58%e{Je>KM4XBJL=@MVsaZXq`Zc`84@#K#L%oMXlAH>!K`Gw$F7o=Oh
zgftiuU$4;mEn{Fj!jkSn{krD(f0DC4!O;yczYPL+xkp&RM+%d^$x*i@kZdh>IEHN=
zJr^2)#htJgotxXF3>e|!C6HRC$vHir8s;)J7{ga5<6d%^<H#mwH4pH}pFS-;@Z$#Z
zZS~CmcCx2JJKpW3sw_Y{{tUzK(FIyRp7V!4PXefpR;vVQD3w8q%grFNH)a$jzm{1!
z?#_WX$4uhdH6b2wk1}xvPn$A=FILU7ssP5k|7(wJ@>cYW$vx#yX$sV>DWU|Nu-?9U
zbNe3_v4x5HW2J=FdFg#sy#nP4ik11`M)g2m&wc2m8_b>};;H_t>X@A>PQks&KnUSd
z<ku@Qd?iK>vCHzfbsY_|A@*G0;m8ab>%~6EvBM5Hya&mlYmp22+If+TR^c!i{Wm?e
zHebJ%{fBiLYr;+H3`+c4%<hx>T6dB%XTF&6=&|Gz!c%Hm;7BaJ+1@0j{_J!n+>3*y
za0*AZbhr1o5UNHDZM-PtdRC-p(ON=5VHYdzDzIzIz?l|a3e{D@I=EG-4$OPy`k5Zd
znbwg3@A{+jBDL`QJ?^Ew&%EdNxgp#GY0Bo9O2VZmTmTw@)K3EKM@=Z$Ym>)y6+RDA
zS0azDn#8^+6s$mXj?o!vge>>JL{&czDYcY}Ff(cp$bJ&|FIkaHf+!3avr5N2jU{4V
z{v~xa#n}IRzP~Vot9qgRuA-28;NkV2#{J*Pp=~fdBK8H1P{=xWI_PNuz$nvn*&zAz
z73XQa4dD6<Sp<4P=U6r%@8T%qFj`OVX;Ts$)gmo3xKz1t%TMo(*LeZ@K1fndEry3B
zKcCzlYCq#8jSo^Pa!c&^+0mrFV%2&@Kk}a0$}kuYFJLXUc7-#pEIOft?nDNuX7npD
zlt%<OfJWcIWiu_!9VWAh5~UK1TplZENM-|n@({zCZ20{c_!kF+)m@MnRt4_gAbb)D
zpn{?60+wQNfIToCsF}-729%1iHywukEV;M;n2f%Crv`b^vY1<s+~?ug_!G5mvFRU+
zr{Q^LH%H)zyTm|{Tn@T%{0}Qmk9)&pmWdsAPX@_Ss7PFJnkUz*FaxxqYh0zWsF3;Q
zYug(#7xv|WGG)~3G8pa>v+1#?gw4NgapuQsNJ8Ml@lq>EyKlHE0R|bfj>K#^{8$k1
zN~nwNx7F&NiAbeqVs%K03t_2^054L&!rddz?Q)sH@;OJC*(k{!vD+{eP;p71S^NxF
z&DR!7RN&x12S!ftJN+gYc)fW=(yjb{MrimX7y!5yVS9RlP7{BHZg}rBf_<GwVwPWR
z-e&fm38y25v+t?d4G+YI1ap>c>*;?;@|O(A2;wMKNd-c!JN&{~W}-cp&AN7~Pp-?3
z3ijg#jiNBbp(2d3lWBox!3}XmyNGO9->k&0MC!{|Z9dDu*vPB0Y)r4qY+P6+c;u<l
zP1N0`bp0fCt>h2FvdS8i{3Y$H_`xpIOp1u=o4#F&ygV|W=7~4-fX6)o3@;!T8Sq%B
zr|oX$+7`^?n#&Bqu+>}BWLx`?>AKcANC;+AK7^zd?zaAi^@hd1>{PejdKm`KbUh6o
zhBY#mG(Br!cnL`gHvAqROzkjQpCF?|bv|w&=qvXHyJlW-iJaG&mxxt9USd5URf+g)
z|I7Yx=NtAf0rLfM8Q;Q=VzUmfj@PPtM?`#63_l)gN!Wk~wC-o8Cj8{hEyat!IjG-n
z0E_(f0_kJrpM_GsWd)~~#p|6`iCKzNeYkxz<~`x3fb>9Vd_l?bZ8m2GG$nA~f`oG>
zH!wek0fjS6rv<po9(Bi#!y*W8qmEJxAW(d}ivnJ{f&bVG1+OQy>sx~8CcWwDk=C-g
zd`&y(hJ=km=VXv^hMmMSVA;{`Xh;OdmTb?v9VmoqL%6l+|2mIc6oV*#<XAY~ImnsV
z{tnjU=V%1W7ruBv2^%Pt$KLob5SSXKol7kadg2TDT$b>75+b#yYKzG4M`dEcS=h2z
zZwxVjrk6Y_&?<1~pru^+3@^I%kbC1?UjIf1+LJ_&+ed5ky9W^d82g%wT=`m$0fK|S
zpqJs?L9E?OgN_&_AejssAju1oo3OAiigO?C6QU?KikmcA3l%5^3s$M%$QQ}9FOp$9
z8XJO)CevS)X*R2a{skG9Yj8A+AN0(&BE92Z@!y?mXwvSz_u+AyI=;>$tt&rpE}?9J
z9$RL5Nd@FC*WSKxumQ3OA9ZknR3bHL{uV0?KxLFjr-G^lB$c4V`nhkPWP>d5-$I0b
z=sl6!1l+jI@lFI3X*=`eY1mprm7zjEeRpY+L^^t-Qjw+~Ds$;gJfcm}K<;s@6XQF}
zp#GP2hKd^mP9?+81j)Y#_Pv6GSW+WOk`4`S4_Kyq5wyX9NkOI9U6!*Mq~M4k<pb3#
zGE*$#Y@i>f0lb%+KH$E@qCf)-(jg|B-&nWDd4%xy<pq%oGNZxwz`3~TT4QJjtE9D3
zA1TxjW=1%&(&WhhzTFzmk_TA(%p9KIO%7zv77kdcZJyfqO$;Z;D~B)XYfXl_E+t-M
zOeA}(FRLgUeb2RI>EEwA?aXt_st#Ex*=M-BtjD`?%f<pIn~%)YK8jQ;=7B3oCt*Ev
zEjK3*F!r3M9sO5v;Wsn58|q3pN{Bf;Jw5;sSu6iq=t!eSgtkW$<0B44rFrBuTT{pw
zb}dT$sUb%+iD=(dRJ~-23k@o*W&E?Y_R~2rs4Vw165f6fK^{8L*)!B>35j3c*cI=X
zI3k7zB$5^KTqp<^63M#3AcDVP!!x5o2XfzjnA%J^u_t)dpKD&S$GxnZq#!m5YaT^R
zW_Qv|!8xr^3_B@{MhH&#pt2q^+cknLWPz3h2&D*~fsckrXs;*m4L(0YiSXu_NZDrR
zisW2LOy?a5*35=VJU!h`3_tO_1Q*Cm=<Tou3lG15RVBB3+&6MhczxJxh++<750$Vg
zu(bevg%T@HHLxo3=45AXcdawcY(DJ-=9FDew=0E4r;ev9h4LN9s6?0IPQm$Ouip|Y
zX6{5q3BP`cL*WXb*c$JN#9YcsEJXVNVR)f-Iu>leK|%><=FMh#JS}m*X_af7dQWLG
z-gTfwIn<2+8<NfD${8&FU;;v=t4eKET6rl!5dh8WsTcdhb5^Te?uxatuwGL(47Z`e
z>Q!~LAB!?>3st!Ogr7LfWwLH8+|)WKFMblfHcNO9(Fl?$d6z{}z56SaM(6_I3NSOd
zH9-gJvwBRej-LBn<oQZShQR*>>ltC^Nh%lZ5SJ=8f>G%j^u)1J<v)Bimi5A2HD~{I
z9gLUAZ4i6%N#wxS`9qqw`60_xh>bY6gj&kWVhXaqHJHXBs*+xV_^yMj^ZY>)?^|RG
z*B^b5%8%>0FrPxk(0%)&M3_~Hc#`^cTlh+2y7niF=dr<`B}n0^rtLAE0lJrq`p1&m
ze64qzV$7$!mJX;VV&@9}Oo^Yr`4D{be0kVfAoKMIAzg51lB-rFw<6{~|8VB>6xa*u
z8_fCn;s`|7XTv;Hk{1g-%`&yw42R18d#na_K>Ix`9W%R!U@dV0kh|UL`|<9Z%*V&-
zIL~0TW=z&t6#mvZ{O!wUhq%+3(+1=DW?6Zdez5xbg(PFhuUK!&Y)Nh3-jD4+M`ZsM
z{P`oH1XFvdCWP7()UFKA{Vg+uo$$p7gc5&g35LzN433SAIqK3Hb|r@mX^(&8m1$h2
z_NT&~*QJOChqg*d_0!<Q*)L?d(s$v1Z{$;B1-*h+FX?v!AB+FJ-ugxr4<vLA&{JkZ
zx%sxsgON%8q<T804jRF)0hp?I6$gS0iqb*{0wVYOuY}i*Zbz>zg>uv#K{s}Z9p@^!
z3qXVDJoISKU@X2;f$+-?Bu*`a{%@xcX}CBucbNY7nV5yncXUUZiEv#G@)Vl?umb4I
zqT=8EjjqZ@TLQBab2^%TDdxZe$-s1%{Ukq<2c`%vk)Nf)RE`{^_j4n&|4dFd1AQJl
zSH!(kWY9vAsnxFWcaY>Kx3N)s@Hju+R*}`=6L1xRBs`&M-(%md>-6)oDEqP$DvvOv
zN5~`R3CBJDWFZS(>)U#6$c$OX8~=hk75>>wN&VnH3s%fCO29Q|@>LKo1J9ESaN)fO
z#GG>mSmrk)<qvFls&cqbHb{C~E!XR&od3@?+j6B*{oXu<ljnlR-Ym+8(ifR)OddUk
zE(uf43CFnlv>ZjKybw}>63TB|v~o=A_n&$-4GRzFMtH0)_)ox3o&tI%kKVL!_#b6X
zit=%STa?ZqCAt@0R<?0^m#x_~JjC*`wIs_h342GW^AoWq>RauGvY`*7UD#3~W&Wr0
zkEKj{JxW$$qy^KrbA)s=#xh+aSU%Np8ZjjaI_iJ+HT`8@nEk=4YG^weE3#2`C{A=G
z@t;jw5N@xzorO2PH`{${T$gA^4qeDc(7a+6kv-2%U#Q~y5?u+=LnJzoHN@>{P+D^^
zw-iB`I(Z|_1BE<`+!zO>sF;EeW1Ydz7LR{XtQ!L5nHl~j|C|@=>G0u_pLOCuWop34
zxXjqG|8)tFXD;(`9Jv?U13U~W-ixi4beG#jnnbG2cb3?>DtHb}HThxLJp@7cFAp-=
zaeU;0<BX!Z4}U{_3$NLeC0REy^|)h2Shlc7b|fF${dPV9P(?GaJ1ufiOL1*ddKoG#
zcItn`R)VL4UDDqc=m_=J@Mr#MN0?BFOePIqbz(d91pGg56~}czgeIi-cSDFO8oG4^
zqn%rHG-2yTX6Mt0A6f+6g%FAct~-x_HDGpPq)^trjz`L`#DX=of1(;kdh8(aGbJ(%
zK4dEm_pTDdh+7hlN|*eHWwG~ls~aOPK({kMOL%NTQEV4AK-+t7SS-csfo4?K5jRfS
z%QSUZglvapp8zQC;jVqF?(5RUzU#FV8sXbFs#j9X!KaDgF8QTmhUv&c!sjboGlosG
z@wZrHqG%5T$*+%3>8mppCkyCSaqfspzaSLxC`2Bu8e0O#{Hk}Ihh3<nf2N~Bhp*&8
zkJ_|D3TrS8(Lp?Nv*6ECmSc@<*<V{{l-WMCh#fyldr`qly1eXh6uY0>C-DK=rim72
zKxL`H>Y)00<W7~1IMCT;(TV6n6Ef+Yoi>c&oJOEg$=!4etX3tVL*MZYFD}f{LyeSr
zN|@HP{!hFWei^N7tE00r*0rUF2}l1!N?5(>jc!(7MJRqnkcZj}D+&rFi2;)Xotmg(
zl5gS65vDGWEOIZLgC6Ah#=6BDKLdF4k9OZEy^PJfoxMxQo?w6AyEyM%>9%1qoX}(i
z1aBWH&$&iIzmKrK606qc=#Eg=Z<B8`%YP_!K>Xm6etpGE`!3S%W_l4M?r}d@Ry$bT
z@np`Oz(x-@kwTcqSMrGkV~)@q(`18ji`js5;nj)JkD)5=-y%T~eA1aA4_;df3J-q*
zic%(qXkX*MS)2y&W@^eP^JL!_j7!$K>N%Z0UhwZndJ$GKfdUpS1~!npa{2Mfhg;Zu
ziI*9f!9ZXl--{=7dm|jS3%%LTPa19+zBA&gH7<TJ4R9`E@B-9MJl~UZ1EbS{Vp@Jr
z<pCd?B2~i3Y6V$So1E6X7j`64+<q?4NiT|(+9W>eZw&6F>RF#o;il)hVO{2fNDDxh
z31dvL1~><%cEln#$uyXKP?H^x@_7Nqj<LrTc4MpYDzTw=eNjt6EsDvS*g{1(h=&tz
zuqrXkAZLYraz=yvm21QF_z{(7I<ibxrk?kU97i>s79PdMD>68X6@Pw_K!>tTHeNbX
zr44NIQ2MNZn(N9Sx4F<}-xinu{*hSg1KehGgJ_IMHls4WJqaWAZt`ZpBpn~FJBRME
zEiPZ6zSz2>39}g0)Q0L;cZ2@UDwDju{XBwbkm+PliH5-+WtZd=m0uPwx_nF6#|T@o
zCSNp{tMol*MO!u}mKCyX`(iWu>ncWrJ;i7#AFGiHlsdS~KF2*$7nN8fr;ZvoSoBR-
z2A%!YtSt`d(JU%sWC9hj3Y=HBj9wG&DgJFNfgTiNA?K*efrZNJK6azW)jvxbtj&$6
z{!O5DKRWxwJkyTiu7N$-(@ej`Z<S->+?cSR=9e330?a-dRpet~EF!f_@{odJMS0c$
zY5*K$KG{1J()&V>bXWVon~;2fvs7sVM;;TQ+>{x>%O^Y4BUdfDxdZjj$$3oQ+y3%)
zny_E=7h+KUx;Xcdy&Q9SS9F0kt>ULCtSFL1#N_7=KH_TTIDdxG`_-AnT0q<713NIZ
z?)TjpBq-SPM_NkKldm3!%{DlJCoFsa1ZR6zTkQLnjg77aDA<v0m#{6owYsFE68QF8
zMS(z?N{CR54_4(yIaXR3S^?F#{AmN8s@{{0uMt1eeV6`%tgxy{Io<sdW1l>A(bb`G
zqVj`p<6Ud|Hb<sHV??V3{6PBm9zhmMuqj2Alt$(^JU@WtebP|&-hKA|!(>U(2MW^F
zR#NlSIY?T+RguXNw<e|@(r|M0lbMi@&ZWphb)6(WXsvS@FnwjmmI%U7L?xC+Z7Xb(
z$qHsv0F`hfh#QzO<*ppWu;x*$V*Xwn0FVbc=+=7OF8(W4{^odaOVrBMnyzMo=cRd?
zz%6lDAhQcB(+B$Yvjj>4jvn}&k7om?X}PgXhP7=}bS36<;Y=z(BWz*BhR=H41@=@V
zMT@J0rGujLCvfRI+(R)<pMsQ%K}^48`m=%wt2`-D0V)YGXNaAJY|n3e3I=p{+yMpR
zsff59-v)S-JqJSSt;VC@YCGd|@0cSq3O+^a(0Oj{)>4#}9A8nwMPt3TbqwZf(9_}O
za~U>6?=ifM2^Z5YU%%5`lrbPw=zIGpO7nMLxN*IiTM`k0X>doP`*bMMnxzyZ-dM~@
zIJ?`xxaO$or#;t}mWuHiNVk9#oRk-`(6=AMTsB0+KZK0kzA;@m&SJo-e|9a5i~9Jh
z`H?Vh*l<;K$Dalj#B?I}8@bs{T+zq=X9LYy{S3xl89Dy34!&I)=2<(ex4Jjj@hi+T
z)^z7|=gZOm)~d!$C?6}=9l{tWcYqUH+CA0823ou4^-`jbTWnwtcgd#`(uhJPOkYmx
zk#0?-b<#Qi^hUO%aix-~$6kt^X3WleJd<ZE+c|kWC>ggF_3)gJg%Fwq1+#9v&5iGn
zr)@mYiI3=<i{1_1E7Q0@t88*Rd;G@JX?%?jh!&ESB6G6EP>G}<-e*8uZw{M<{|?pc
zOrs7^7!Zvu7p&kqq72R}-YTP*faDt*K=Q~P`gK939#BKc-E%nRstKNe#)QNu2rZO7
zQVM+Px`T7};pERhr3fT}xD&L{MC;dE@-s-9g0ecvOfoq+h_{rO?c#TiI)sI*ex(hc
zSy<uCmRxycyiSo}iOg$j>~h8b`B!(PG=bmLBeyvh9xLteG`v^_(P*=5`|yu=h~T?1
zY2R|V@@y#2LfoSu?%eszDXV)<JZsOq7e*|!&93fe*at~=y*=I*xH|$@!T{>d__gL$
zoYg|wF745IBj)QB*wBZMf~@!2{iT$;c%Zm#JkjRGz<!>mY8BiIm^=>yx@Hz?ni3HM
z!3~BA`6&NCbdFZVLJMJedokBW3a^|i`%f?O0<W*}ax(0{1qzy{ccj6pc=7*K73>w1
zsl}Qfe&hQ7@J`(ZME1-oD<)d1UOj|_4T?N>15)m484`+YF*ZXS<CA1iCEas6{P)1U
z62RH<_`T#m2_rMH!W{+~6lk^9TuIR@V%qQ1W~1b^+)u5hVuwP=78Bc}ufPDl!zt>t
ztHjvCF*z^%j|^%`ZGqIUcQM=uIxq6QeltZAtrsQT06iO|KvC1s7dtmtJHI6b8ADdT
zyW@5z1yCCOSwDE$<@Vqj{37gqZYwRz1-4fsGaV%w<$d>zp((O3{JGIVw!Ut@VW?Py
z9iu`mw4WZ*n*Yn#$w6W4b{<|!RnW&E$i`ZB%csYnkX=Fu7|KeRdDWaB#1#w8hCYEj
zofr)cyr*VFr7G~ZKMA5KQs-5$qw*7|gKO&~a471ZGf-)DV5UFzIczXP9Q~9u$X7Bd
z;yhFG-hUFHeq^+Z3>>T@xMVK>ZEiQg6!Ru=I#LEw#N3v0wV8ZmG_sLp;zvZYSqC&U
z8{f}(BCd;M5A7caGc$o!GJxzCtna}2>Jzrd)tfPNLwNtGkhO8w8n2wa@iXydmsn_H
zgZAjI+u<`xKuCX(lG>jgwdf?=Vft5WY6~9BtL4BTGe8f;FK%it;>Au3`jYX_bo2rM
zb+YaOzZ-yjH_LQwG9gZ@bT`Pj6*V#5nUeCwps!j<65rBH|39v&?Y|5j0=}0p`jYcM
ztPGFvU4sT-4(0q>8=%d3X9j9ob`WiH{k03r43w#G{tqk3A?S6g^qg@0@4rBNm9g?h
zoK^^8#Q@0R%B7O7>aQHRFvhd_X3|FvQB?~_R$P>nTWWYl@QTkI*gJ{=v(bxG7>W#l
zO?uyx&`00u&}X;=D*r-@j?9Hgw<3jHS<U+lGLX+pl7Ykl?@3^>$$O5R?M+%u$7>NN
zyHHUklu9Ah&N_6KnTTg4E)gNaB050{FAw}P_KI7s*~1JAuFM}Df;xeiQia?Ng9Fc&
zYd}-a9KdF9NLIWWZQ2hRClA0W0UzVb6#0IFq3+?6nVwQ^L!*T=uJ-;DZylke46;Er
zkKAktrJl7=7o2YY5SNGp)P!8Jec9?F&H&5|?_1x{_~&fF`I%F`$?)4!)Fl<^yVIHT
zmxNkLcgDapm2(F3Z9LFl^qmSrQr_bc&ZgT$pZ9Vhln6vW9TP$K&Voc4?0ps1nykB$
z5>dkbvwV62qUv7`u{RoKA6V}Xcd5|PUj@^u288hrkK!Qct2pbT@9x7J<%KJY**U)U
zQYJR0LQ<<~@Lvr6+Sl;QBU8R$6rTxy1Ss>Kmz8s;iQl?j75+L@f5RZs+<@!rEB-{c
ztM>A(hpQ%N6^w1+E33A6E@X9}0il{q=M6_SzR@JN*I{bB2%l##0Aw3%iBF+`<!{p0
zK~XKR6o{+vWM;Br2Tj&%MmU><hp+)#j?U0}jFGF$Q?8aVV>~-%4keA42e(s@-h#w3
zmrLO+pyl)R#>3|s{HHqTQ+|@OU+#H{H^D~}+wcC;kjV6*i703bqP6mT?ZDYhGB*OZ
z$6)RJRj!r%JS}FKOp|jJGCk$-of|#ww#yTJ+MmZID1KSeyKeGO!J30<2aE$iSnO<B
zFJnJ9s?%#chzF_ZY64aVrpKrzJA&{cZYXqfI@AHsy_*OoL;eEz8+9Imq)LJNkp~5K
zL>f;_@9f@BUVJfij!)kA9~XeGb5F^vSqBgU5rB6B&`$ti#YCN$dh@lA3hTIvXEO&F
zn-KGK7Je+f6`b+Upzw|$1Tm}myVxUNLClsa$nHNZr*UoRb5_hQPL^-ybHJ}!m>c>}
zIVu(0a{3#bUln3+YegpzoYq@qJJ|ik%4YmSQmoU)-{_m?0MrO@>1zAK<7hz<W)RlN
z`ab&*VmTy17Te9kAn&PGdEE^u<*uzE__{j7Rq@VNqu6EtTl0s;%B=d)=Tj@yB=fiU
zxVJhjhGPxWF2`ICo?CP8yInh2m@sF>7x)DFl<T}5>=G<bf*Kd`$E@Hsu0P2UqzMIQ
zia&gm_?J4}v#nkz1DhpEeB>pn*nGYIh1BaQ;C{3cZq)%ZXrYe}7cgVjS2cD0+*6m^
zj`Y*m)8R@hoIk}umT5i%Je)}K;?;8s=MF8rp@RJ_X}|M}vNx~0TyFfF173Y7uWqh<
zh0UByFI9R!Gy6CCj5vT&Ixf6-?oi<%ta<#g$_jl8-?>?;KG}AY;)5Y(A?+K$wYW~g
z-}wyZKP(IfsW@60!;R=Irw~LM9e|>ZG;WA6&(M$-!~4szS}LMR2t!2MQf(f}dC``P
z+j%K-*bHivT(?8H`=AV3*BHei`qU3_p`-&~pEc<0Jw1?;R$SnYg8$T0C%${bC+-cY
zn#@=Mb)<gD2zUo0$e_(qp28MSh3cxC38`>A{{#C_uDl+XLZ#|GtoXgGYn|F1irDJH
zjU_M>kr1pViUW8=L3G$>{aO@6@NXktoWTvC2PUAOlDXkJBs3&Iq+DQj?r0|0gb+L#
z=B6JNet2zj#Gi<nO7HQve95T*HOPCg*)<V`L5{6!f3s1Pg)Q#@rKUh3MTg%7-)mnV
zd7TG~s74$PhWjrCTl0jqdA_-7Ag>TCp1}!EYUs;2@PAl`RRqGLgJq;+E;M#GJr%hY
z4Zz;-h?7FyMQIGO9;ZdIW6Bc9Lm#l1ic2+}OH+lczi86JIR%K6k_IWASUuP8-XQ8H
zR<{yYgmUfcSduLYc&#%4{8$P%W}4oe#QUOjyV>rC<h{W7)Pm9x;KVLSO`IVye|<(4
zO?#k%sEfZfPk(8|fv@Oce3cms(6qE)TZxqliw~o^5ly@hd@sB;WItO<2Va1zO4&hX
zE?PpTT~4m1+D=5NED1jOJ<*}{{lE>56}CUqloE-XoyTW%D9A&vx<kOv>&1yA`z>*a
zPpQ3kGd^~5=!NN&<;<lYHjcP2v$rnwACk4!n49B4mKo>O9^Oam$8<YY255sHiYr-9
zJQuiC?JJ1{flc8^PxS)~!(JAa6)AT4uXz2ibhnpr$1D1w@Xc3F=xBD5J*ndD`M@(=
zIh6aD%WW^rO1mk{y2BY1Q=a>G?j$8}TuMkwBsHi#!s;Ydns)K^lnhgaXgiQ=*`{*0
z5qjtFe0L%B5tc<Ta3WroN#Ak;0*Iu6mXnR`FN+3qwJG_;m>fJVmZ+ll{p%HJXq3mX
z{kyy+#49a-Eqs7~Q-ar>>z}5X51dz`;YHTX5&WD_;}oPuaJ#3%U;+>F6zaMrWnGc5
zp09Uxh2`h$ZbwGFJ)*>ZEeK|ODM=Q;VK@*|Dsh}t$c*k<E&)-_JKt!>Fl+GSom!S|
zIO<ibKiv@}^eHVCR6q*nd&SD4be|&4njnVO_71)}kZZy!@j$K*kc*Rx<$f%ApuTW-
zTKG}|IRdOmpN7IV1__`?`rp@`z@kDAgJdoL<vegRvW49?;s~wwpF2Z$?UMgVof&UM
zA2`t6Hd9vt`~Gn<?CbQMadsO`Vjcz=wwf&etKWsj9{1i*9wjU%X&#c>O2parxY$-X
z6b~A%#fOn%ktL!D%N|F17q2~>zzV>YLB1{3n9UT(*=V!K#7V3TB9q{p5Os=u#+3N`
z8Eyv5Waj;1r;eyMP8%bBYfFNv_;QYNMX|}#clWX7fVjkC|B?q&C*l@Qe!<C>VEyM4
zxm%8gJ!8wKhhJXJBW9~01*Co-40xNxEB7Q7Klq&$a?EQ9<z$=Pl-RXgvdOR)h+I!n
zv;ws!^<+qowyl`blP4kduTeSd?O!H!mecsbp*sXwA#+0+kMC!>yZ$nSr=rWm@6X@J
zbHzGmiA}x#b@?w$mh828dl3|&rtskO4o#W{M0dha3NAyC!iy?ImAyOvpAx29YVbta
zLCY)8B~h33Sc~`a>t<>xi!+)n6};;~^6A^Q<vWWQWp?0wlFz^XdSpX%$68g|v@r0g
zXThC)Fix7ULZF8j2H#8om3$r<ufxbsIk;rXgT!!#^74oOjT&>kxhk9L{?h<z_{o1|
z9(|tMxHF&WHhy^{vFZdmOqIqyO#s3&Pj{9wGkgsO-QP>S$_({&(C2z&F9<65_hCyZ
z!$wM#VIROm4W0B;ALECnR<gl-d}7aAui48f2v<UwF;TmAil4GY#{vXc!ehO0JPPet
z&yZ^#-PD4AZKDg=u`kQRdx-s)hG4SNr>11rTS?~!(lo@j+!$B46Ls|4a1gS`o@1>-
z0MN9|>37woB-tzqaWt8)b?BHiWpuL#6l=eGjXdy`egIUWg)B6ak87X?CCyO{q0sRA
z+dSf<4KgNAwOnan-&1KQ)a_<jv>&^Ir2Uj*z5S309-%bhI=o@oh{IOzcxOSo6_d5g
z9W`KZ!{(I5-p~opXJ=}_5^X8I$z=a1x#+G~%nkU6tm7$ed4s762Jnvm+QOMfY`=ot
zTiH2piSbup*U1m#ukr|t4tzxInM@qjt`9QXui9h$u~B-eWp;fV!dU-d(GYN-IT!$D
zUfyEg5n4J`FE1tv&NVES&!1LUXGk8_31HW?u=U$_#a>jkKLDu!Ps{_2G;ytY;QB&^
zR*mN#FggMI>@PclnhowZBsM(Rmy5=#2r_Xj94=@C^!_oU>6X*dIE~=_%!cLsS%%G`
zSP2NFY=RoR>Nih?8%)%UkPA(IXOV~)8zO?FVdHdfh|rxwDf>D0?w?xqtt+BuZ0;Wq
zj)Rs-6XyY*%#NF5$viQh9N7Gk0DKWBS^aY)MXSYu2I$32DT{b(Qt<H#+g>{`748;n
zvK1?U(qezNZf1Dd#<j1G+da2)vYZ>p0N^+7^x`wdLw=EQVV?R|gq_`Eli@z6AXsKG
zK6@>NU6M<v8ZSKk$=|tLvCn__6TTt~nmeJ&p%P*)bbnLg3Xb}i+#2wegg6C?w-|Ol
z!g*3<ouK$OmClZKzhjEwypJn%>Yi7+L9}cALBl=wCe)x1LS6@JXS(LB(?f-21Yc={
zsF3AGGZy^0;0zsK)FiU28c@2tDK|&Sfz#j|yT+}^;)9dxO}C@AR5VxL3xF3){bo7g
z6+x7eq)<V%SakA%;uTFI1vfe2PvGP<Z~TX}GB5W-34f&52fT(@&2|P^3D98zwE{&l
zpuhYn-c=qu7D5@|pmb1YlQqTSWrX3*rduV(_|}e6%~8$Ft2TGs-n(qB45R@DVyALp
z&Ga__{4LtgCM!O-*p`GtYv{XTJG(&GOoZG*;-@Y+JtU(%_cWSbplvJn;Gb7b;^j*l
zaLqQ2SsaJa1R)lO)wm9`htm5SHnKyS@0vs=HJA=c)Kt``sx;Wekb)E$d!>?>!^8G3
z<8GtgQ;dCArLMJG?J$*}H0ke&orDN)CtiHEF!8n`Y%L@(@hx8>TTwK>vO^5eOw<g=
z5*<xe4HeI;2%H5|n*l>OCNIhrLSny#e)3&eu8W3ka91I0Z;5zLu0%eDAIpy@wFLwJ
z$|{j6Ad|fR!_q$YE;6T+co7(3KF~N)9hH6Kx;Ytr@od0bM(u@lb3&0?@Ieg_+Z%*%
zXET56pkEEP^hE<s3dmw%8NDr(=bgt>AQz7CSzeB-K}Mi9fDQ7(y3#cvE88<u{0uK9
zBdM|zfVI<OxUpk^M}-f4mMmm7q0WAATiLpZmwn4t^%dye!ZGx~&)J3d(_kSf$G%gU
zKDYj6ZbXO$2@+wjZu|1H{y7Zw)Tue{xm#c09ghf7s!WVWab21&#C{HxJq(FcNjXS#
z`>_VoY5XCn`9bK6g*y(x>((=%p;;tAAIWStw%S5C<;DGDR%I<K9JNuSjsVLh6NCVM
zO<R-WzPx};tjd2@r<31MfKGmC@LIGBQfaS=QsZ<CUe_F-%IbfEi_-Quk^dEHYh1%x
z=Te~?6?KVw4d1?GLz<#kpSkqpyHJ_c4m>Uq2V+0ptq=d`AL5z$g`dQ96mnL61>BT%
zjy9`L`nX+Gvq<LKkD|fYwm8=qcG_3IU-1Dz%6rhkK#=--{^(01a)Q&=`}Hz_B(Ief
zlLqW0-1b6RzA82Y&aYwGN}Z(g2kweLtrFfCYAHQR%|46FlZb5OAb+7}gZ^1MO&)bm
zNkn`9b`@~__ROxidCs30R)`dP-ygdN+}Y8hwVEW`!;_a=^1D4<0Jfk*a@(1jzqLU&
zO_TTUhfWp}kNm22R?JM*8M2J%>Ecsfy-{SzIcH6gmVp*w#cVd$^R*C#mD-p=^ykm{
zzXMHgPrIV{{4apt-eRm^1>R?pm7O?WW+ketIYGiaY$6q1rjVTf_*;2Uf_sVbtjR0w
zx_zLoAg_JHICQmSR~j)|gMKBaJ3-h8-n%8*ar7GDj}lI4S%o=abYLX=U8{hGjw5WE
z-#VFPMj4=}F0d;L6vP!d<|O+j!51b!{Yv;hHR3@0EN{nqWqm^|2Of|R!QHvLY$v2|
z<nZozseC1FqDCZTPXWjyc{>Nl4t7@7!k}YsEa44<v=k>;DdDZ_0e9FzDv(Xg*;xjI
zuO!JK0!5tOr~PWX9ZezBWBH|L2PoxDA#1|=lC+Uab5W3tGLxP`0?0(TntbX8BX$ow
zw<ige*sUN3EqY^4ET4S;<&p>WcG>U)qNIuycf&+SteNW+K)O}ET1*CbL}i*$eCeP)
z@!LsYjsQX6${qjj4MJAx%m-vR=x!*X`a6TjGy<iH*Icr==7PinrHVd_rJ*qw*e3Un
zJ{H_5LcRih%*gw7!YOJuPbW44$^KjCGJ^ENXXxL-#h*h*Tpo`~D1@lQU{oQ{nVlsT
z2erMn*XL;%qP)Mmr4pP$4@xWq6=RMWq3t^*#`;L%?KKh7?HVvJv>ZlBf1s&9NoY6)
zQ^EQZ@^~dFSXyXRn8Y{pLPSP)F|o19M0spE9(y571V9bw@y%n)f82hI%F@Qo{rr<m
zZsloLa7q~Jjr!FxEB|fj*t(L-MUm;vGsPd1wM-j;)a!0N2-o__Z9U^f8fo`r3@C%R
z^rkqpGxWHRY0}XyYVugJsG~h;I+4u&i43-Lx;pr9A@Q!kq)CfU6t1KVxNoL%xi-n^
zBwIhDCXDb;d^W{sC=vLaVLkh?-pL`S-iJg5tXut=>1dZrG2DgksYYJw@7@O4k#3s_
ztHT{Muy(PF{rrDn(d0B0A~{EfSoK*ETiaiOyKgE`%A)%i7`qeb9IJeZPRG06&V1hJ
z+S&()6gP#e^Djx$l<Ws+1sW2F%JuGzU|9mE0|&lw<%<!qJ>%hoNIOCdaU)|t0*^>p
z96{B)u|{#5XNwayA#6!53JcoK%p@;2{KAB8a!|*ZJ)<+kh8oBFmT%^;X`=Vz!t{K7
zjJ)^TgGPCJP%c`yc(^D4xs<m2<8BbpwF0&MV4oib8HaMD_P#m!XdnqwvGg@Qy)qvy
zggoi8aE;Y$WSzTYU*(ApX|szC!La-Mlr6nwusf~VIZYdDEn?U%Tzw|S5~dDX$Sim$
z<5ImK4NNi+nQbO~<$|ro%C6b$2!-o>)79H+&A4?c4ARum{UdhEPep1N2zt&MCJ4*`
z<o4_orUbJW(B7t=NdlEki(Qpl8RAvZtuA)R`eRwx3d^gRXv|YaPRTQ={aCYo_u<!H
zPoaOyLTAXyZ_ZDo<KR77PQ7MgAmcQY$jEehYZ7|<$A4HGF57_>ua1uWb>|&))<hR@
z(4JJG9g=J%$M6LZZk>H{;M3y7z-<hf)z9kk;Sj`Hc22|C;fNJuoq+l4=>cH(;ws27
z`T_s;w}d|m44{=@P=it4YzFVL_Jq5DE*0nxVbOyQk7<GJR5kL12C@giAG*bXl1FjE
zp9q0FC;YLECV#k#1G!XJ29oXqb;AY{r01M?<qU3q0~)r<bMRC1c6tQ$San#yvM%mj
zx&N+c$ww+mHL}b437OHs0iI1-hM@Yu>VjRrY8y1ett4UKy|8d+mT#hJ(qfyx4sMZ?
z&hX9)_#Attu(~8UInau4tdA(TJLDNlR4N;ZDCdSKk?bkQS35U2n{B)es4Yz_%de4(
zzo(}8UMO{T7=csskJPYE*$z6JP@Kz@b`Ys4^gOfNoBZsRzz<vgj^X71949HRFR-qQ
zSST}KsGFVHj0B+#GH{cK`zvgv71qhAFWR}%JSo2NFq3S+EUH8Ee2xoH4^b7W(eYtZ
zEu~}e4Wq8{Zufv6nsc?nl=3pqSER4zc3aYlJq{Zv1h4#nq#OE8U6TO=j{L_LK;R_1
zfm`z<amWqen)@71k*Rw#ju&#8X?#q~=JKbA*LM=jZL29{8PHlDP6=F(?P#)4PZ26W
z{=*W+<!Mf^7^UHapzRV6de3oQhcI+>(oDct+=H5Rl-H}6NO@qtCUHeHnVgsuNNkvN
z`Vk*ohbN9?FzWs0<`j0SIS&D5x3NUEO5ds$*-HUy<eo0<Y29LMOoxX6bblKCp=mU=
zaA(^PHVZo(Ve@-H5Zr(r1w7l0>)K8D^bi0^rS644YJqo4yo>)Osp?lV;Q;`Ts+!k+
zaJikqw1eSfNDEDUs3iqVy~j0jqRWLYs=r%Jz*o=Q19anWC19Uf%{^kVHi7n9r!Q_|
zi>{KSW<~lhrd*Z%_pOuTZkyp3#R;ma+6}7okoi1Cp}U`zOt4&zyPSpsqnSkUkifF)
zIJB<nsLz1X=0l$MNb=N&tb-AClSxc<GhW-!ewa1*<F(nl<^Y)amp0uEvuB{o*q}P4
zK=tBdx&f)SaiJ{11INBph|ru9KSpD@ZbvoyjXH37`eE@AJNLNSphrf|T-zKqRBTM=
zvemCbs&Y?@RQXJ^zuG_wgaHrkgQsQd+GqaOmTA5zGu(9<4)4lURO(d-Wg@HYgp@n<
zv9FU8iz`H9oG{&6R$L23EZpf^v7&!O^QTqr2;R1jzl7K=8(uMO{HP8T=Oj_|;eeV_
zc30`=9IrXs(Z#xa^{ymL+gZ{I-R`Ot=7PTPzvNR|q3`0@**kV94AMEqJvTutWfpjB
zh-)34g#j$p$AXW0X&t4_T5qRE)>V^-h%}2dIyt`i872V{+jDri%iP86lxsIPqr*CY
zV9UDhwynV9f>L&wf9KTAlGa;eZzI-Z3dD6tQ}Tz8eT_&*R+O#Hk~9x%0~xZ-SKC$b
z(Rv{D5-_B>a%U?(?2wG~U$*rTdX${dSau!E@de(=1H0;MgGUd7jwkL)s&hNY0qZ%=
z*2QV1qwCX~fHl3|?o;ek0hVQl=c@-%$A#G!Vnsm3(T%@&f3uy$5VvmfUhJ_*$TE-}
zzwqqlD{S20S$g05+V%{c8q5<%a-+Fcy1Wmyr&Y=5QPeenH_x<v>lVIe_!0E5&OAHR
ze@!PS{4G>8i}kAblQWETuhe5~3Y<G{9P(OF>fnDIon=6jUDt&P0a0KirH4=u5F{l8
z21L43LPP}Vlx`4^W+(wiO1hEmZb|8`p?m0@_dCz`k3TTO9p~(`_gdE?*qPe{X`FoH
z&-2mUQ>R@)5FNX!j-LNvT)a-ivoB#BJ&Wu88eJXa>|??8V0KaGsq_>L#*ln)lvJ*z
zmD7fF^hT6YqR88P&W%qxv`aJ-rnjfuVsaz6ne<c*1O`LBWx^Rm!6nXLgz@nv5SF$?
z;-Cpk{=J2)$vE(}Y>u4hQyx*Jr}Jc(rCe3U!?%v-Oeq3{wB}f(XH4ZI->|=$8ZPx9
zS{_T=nU9Pm`df*YXEJW}YaS_yphHEJ3C&-9%XC6l!8=mHM)Qstt^WvXV;aR3ntn3I
z>m&VNi^?oK>*)6#d-?H$mx5HGWbMZ{Lms3pmXS?qFUHMAlD>Cich&s<Q^@}Cj`<57
z&1~pJ(c{%OEJkUcUtj`{NkaShUor^syRG%T19|WfX(=H%U=ycCydvDm+B}6Wm?iof
zDE>56ZX@BDa4w80Qi|4^OXTR0EU{pysEuSA3O*Ymdg-MUGJ|+e704Q9$GD<bd!_B+
zZOF1fsdD(sy)<}jJbUA(Pg}lsDm^KjP1RA3$fHT#)l=^fyVc49^?Wz_W!sS<548jp
z8}+TG_Yjm)I~wu1d?=m7$RFE4HqL!dS)6f_^7V`wq!+RD^K5y=J>iBr;=mO=(4(m7
z96gp-7fXL6ugRU3Z5bxdr$h<<hcPd*7@;{9^J#$U*;ciJ%MgPfAaN@^_!OmTfW6g!
zfiKxGZAweRcVNI-x^s}80<wW1fRg2VE#AtB&C@omd%B4MAhm&pHi6Hs(A5=7Y=6$<
z%f9fBuN84=;c?C{1uXQxrXFzI8ss}t;BQv{KF(ji6QgXAP7b7@qRVtUt;dO7G#lZP
z(MwgBU|OUMzu7^JCvB#P^5x4%oq+4?1M&tvw(jYbkO2zbh8%(e7VDaI<RQVYi13nu
zEyPg+^6*0i;YnX-*;0XOxLwFy1A!M{f9IZ8P&^pPb<buTSjB&f^yqa^7Io)`UR%jd
zfmv4&T<7aM*MDc1xrFxmCh@d>64d@L({Z}%f2ILi>^%90Pl8Tb^Y5o-aOC=#Tjne$
zs#hAF0?}id*ivX>Yu&GpNtdxg?*z@31qXSCam;C=TqaV7#lDSWTaQGWj^y)WmbTFS
zK_h8BCyFvGL5D^M_QUv^p3%YaW!fxRXRh_IJm1LmD4t9MeTw9QzsWS&(Y`GY8F#qo
zy>&9WYnraUDZ$Gu4M9{YL%j-qy~zUmw}?;Nx(ytrPqM5UapWPjYfW%vhSrde4Jp+H
z-9}b-)th11Qs#=Yg>w#`ljQZd@>ERo%E;|(G2_bYuOpbsW{weVe>y_@o{eByBr)#i
z{YHyVXg*YXOtQ^=*sp;de#iLf(x@O0f@_lf7cYYh)Be^?De@Z)Ij{RS{D)6U_iw0&
z#R)#F4=;L}<%M)Uwwsmz;}gsh@^v4PcR1STPuE;nj9B$Y*-wvZ=U3%~9(r67pPcIW
z_7g2;7xY%k4SIMhI}|z+1ib(DR@)3^9W9y&`(0978GLD%?89C#S~c}~OflvB0HKc=
z<E@Vm-R^b!XhF}DK=Akz#JHgbIp*yA;7Q4O!7rsTa^E#fZAaR{wAabv;sB{YQz9&?
z=f!i)h(Yf^{f?9W3+qP2DcLl&#CG{Bq{@mDWX<s1da-=El)7JsVqxt&2|Q>0JqlY!
z2`Ycg!xvr$RKn&#)LeKhE<>j91QKuv&bpP-`&C>DTa0cfFWT+{1Q&WAOB$oG>8uQ>
z!h7skl0Dm#FmvGc)j$mXTslRLHGD^j$Ki@D+*4!$z=BlP|1gkMT~6s=rl3vr`|<#I
zx2Gbp$Rajm3n$;%cREd1jTwhW6wi1Uuueq3z@`wx(`HzQ-CuZ40N&uP24-{U#e(&R
ztG_t6F^$NvqIAlYa)b9<llgSv%pFN7NijZd)E37H`@SAA(dSmGPa7kBk|Qrze)~QB
z06ljtI3L2`LlZx#8~A<m=ogw;fEg!RtXvK3X4*ahXgIy9lG$%@_K66S{hh{T{&V8o
zG>8h%8{3=zkijJWPR($!B8ICh9gY*3)^DVMh+PWwP0&bF^?VxGapXMPmd6EuR_8IM
ze<Yq`cn^AFI(r`^^`V?f|Lnc?+E*Iob98=ehuecJ6DmlOto*1;J1qu(!hL%RjBpg5
z^MNgv_~$zcE6%pr`t*f)bXI)Xa|Nr+*b7rnFLWwUs~bt%)Cgxz6`ALYH*TI>%sJ7+
z!=j1Ard|{I2peyTko1e9AL8`QpJh(+=-kv=$Qn!%lVQG=p}X{oSiX1IGt^OsXLUCt
zB=^>s-q1IZKi{)9%cYSd9aj0H_M}H?I16{!#@u`9ER>xTbgzCAEv;2Rg1KQ+@PfSV
zRhRe6oBp2a83QA0Vw}+%DURr&cT3MIID=f-ee#VS8Mq~#tOc$%T1=o(@*@&#h6IU(
zU)lO}RgLd<Z}_JlQF$=eum@2;ude5cI;heK;`4wyBk6`XaV4Du){R}+Ftm+o4O3D}
z&X}r+GM-U-JT1$4ZSc#Cwvl_pI2`N<j%#e33*X_axlU7n?a(3r_26XA@w_BNM6thq
zQql8I_Hcp<v$R+p*>%w1dlbd*Ch|ZG>JT)En0j_cSDVX@A%0w+<A#iQvt_3B7ushG
znsvpW=&TK$P73Hy;e_ahRsUBbwC^P^_M9DHZfR>dhB}i5p*^Zjis^l>!re)_Ad&kT
zy?d6I>=H&s?D*QJSD@u)!W(IEkw4r>4gW=X{#aHpCQ^0(z<8P_SA3&f;$QVwam(xy
zlQp@3IZTt?_u<j16gVHrKwm>A+I+^$#NA6X=H!Gpx;`&2xQxorgM<5wGrVT$#k2ca
zfMM+ZZ$~EEa6BbW%S`8c(z$B=ZTZa>^X){@Dl2C^H~nnJ-U*4gj98_dz+N%QlQ^NZ
zh;j&6xurI*bD_g&EtFw+cOXFpyLd6avH$bZ1f9<D=^tX5EKWc!`sC+z6`pWqHRE8n
z&Tuhg=F@U_A_T;Y<G%Cx6{r;R3iTt*{1(b_O*mhkP=Thz*u*ggbhun`SK|z!evTE>
zTTF||IKRBHr!r1Rh|IQBz}1!~L*?$6z+Uub9DP`=nWCg^JlNThYjDk-UF36=&Zedl
zsu?GipCfuh?Rqc#XjRSb;6vZ&(FQZA9N)+T0B>v@%cgK05k<KAbV~icl@9Xj$g3NY
zxxAoJ?SD$Q2YCHw1oj;O<|KJsHPk6Tokqyv5&W-WE+={W-@V9qbh(+xwF?{?^ea83
zT)f%}hKH~A<!@~>p-0%Ri=rQMixBPD2cv~|*_n7-l*Rm0FPUG}EUAgaVde>jm2@EY
zNuF4B&Azz`R1be!Wb-=mD?5IZY+(v|6Q=S5$oeKLH2T{wbN%c(9%3selvQjYKCz*Q
z{?Ocikb>!Z?opo&B**bu2~3k4Y>ee1@5BG3G1g<V<qVS2#x;#$X6|*Jz|Ymorc$6?
zD=80K!ErnBD7C>Ub}rdlz5rBC46}IkWd0JON?m9a#@S=#lRLRK^f_J*@PIdDz))*4
zVs#nrfw~DRdfrQgtw;%iTftC&nrx$v_<hg48u3vHFyTmLsV<Jhw81}rJOnD2p?Zp+
z7u^^fmNyr^2G#sUIeY7;?vfXxS|-}ls>`+5V*WttZfR{Lq&4S7{gS6wX1cQRAP=f9
zm1S)XuZ=wu24V~gcmGxIl9sFNr=Axck7Uafl>JYCThnmcA3G|6$IMG}9)5riqsSUW
zJtnShH&XDhf3mU>W8Rwclo)!)+>kCjL4%;_O!7BVoP~^s$D>(8XmT*&4s6tf4)Q~z
zfSwsZHEK5iVvlYdfU!I*o64)7?6RGIy>^Nc%;koWDZxV=bJp0<9o_Q>YXMQ<Bb94S
zjTBna1q7O2X0IvsC*M*#>Fr*z9z25NqJKay%<3dzHrS&f{9sme_3k%_;~Ri0Pf{Hx
zJg>Y6lLW?;90BKMBRKEQj0ql*=V-&nLW3k5&!Y@{()JqDyGsop`~pZ&aV5N3&T*8Y
zXevf2BCO@J%)^45ab&9e%WYMcY~GT@Fv7%lZZt{4*Kmbu&TJx{m;YiHNcAe*Jw5y;
zK5(CFsIcQ6=j=cQ7JiPHgWUS>f695Dd=#Mb)z6;8jqdfT6FzFl2TG;I@3-|tBA?E3
z#EDW??rW5YW-}h|Wo;|ofyV0c+cf@z2ef8PKrorO1o2rG*e{t`2Rq;QQa|L*eS3Q@
z6Ked7!GjyQOvYK`U&yom#P^4!H}gZ}aQuzd-pZaCO=QS4S(m>0@88(YMk+jVBfpvN
zIxv=6Ce^NFCRM1`KY5uImj&Bg5Y&q=q7yK3w<JH<oru-t2;MvbNnN16h6nSXEF9r2
zR?2y^<p%bdfUW7dt$~zEqaStX-rOUH*Pr|<RgE55Cf{bE@*sqkS(&RA6A%4XpO2!(
z|A#>fXn$2|;_B(P38$-z%-`PnI;S7Qcc_L*_qwV5$JZ9=LLTxRR&AhMlZJ79+<|%|
z6Z>y(y0@Bh6qWCGD5S%mQCwggbJamiA~&6SX90Z#3kEpg*fb@WWO%Cc5FxG}XO9=^
zKheeOKeP`Gj>(R$l#8#sNB}ISiD7g)_=N8~n<G1a*tU1&1y&d;l2`C>)l7UMtGf=i
zs{pD+_A_%iG#{qsHrtR>W{>ZA-PsT~A3TzqZ{7TUF09G?m9?Pog+ReY)QglO|9c$n
z#T}`lw;tP$as)LfpH41~kr>AzMwDUi-K`1s?~?Vz{_#tm9@!G9mx(+7!+5C$$-$5^
zFIrf7VH<!+yA@u&wQ%r!9>Y`H(a(}zkjp1n)Ot$&)nLk4-QQZz;5!xXguWY>!aT#t
zJ`BCIH;5*0<viTmNL3Yz@2KYi8s1^t!mAby*g|^^TgNj6AoJ1B#yxBvE!sxz>|WR{
zzRoLHGiP+AXdB~X%i8?rIzZ0qBh#>NUx3d;AY(azkP!b5gMKI7SVuM@LkMfJx&C*P
z9=+@R&+R&L!lN+!`Oy2GaSd74P&1gYG+td1cDEyvX|nD>Zi&Mcn<502<48Wo>1^WM
znFk_jAfc3mm62{j1@N#uG|j8wAKp^F1KpX>oTpfMvjV5>P1vwS5CE$<wdizlqS|8R
zRAyAG$TLmJFc#&fp?)$;-<&XB_t4qUoF?sm7|i2B`NL5KK=lZ(#qfM>sZv`a=U%n-
zFP@B0^#gN+nra4F+t=+&V?X4HhN?IStN+NudZ1x?)}C|gTDJ~mrf;|G@Nqsi>Ak~4
zD2Ga}dL;=9#yM@z<iQ{Ew0r#oCnL|S<+Z0hye+Gq8rPnukn?D<{vi(kvXv8G`<j9D
z5&>^&%DZX%aKf4f-?Qxdr#U=Ti*{1o117WOvVC6?jtw)*1W6o^G+2Z9*L*F(qSRKH
zccD`1Yu3O4rXT!)G7}pxu_?b5Q#A@M!Jw)^<R<-XzBtub7M<3OSs@{wCM)hvIr<(@
zAg1$@8lZ2xMkzR7g;aUleM%1~fc-hs?eUd77eMfHRKfQC^!_UxbN94#SaN*ex+p<G
zBlqtooOr91DKlOXl=HgdOtIdt_fDG*XU+w_ILCEy?R#wo#7NubNQDslzaP~OaLYA0
z%I7#3616nY`gT3yS@!Dtr=PV0eCDGX80gWlo2o+b+}LV5R^g=}`ib^c0|^?g9w3|8
z*E(48{n^d^3_bgA?PFN_rDax^h(f_^mH8hspe^Q~0D*Xd^y!}2)bw#74oLba2}1E_
z<Ejs{SnpG`Y|Cas@aUHnD)<lhJuy7?R9+*j&Q1d8DkaFLyIeE8|C9p{MK?IcQhI6U
z1S;yHO`i0F+IA?14WQ-z3lz`vmWeHgnX{sX0kVbp>(3LINQ2opX-33!fc!->rz`|o
z#*Zm+^=-?7X~AR(U{X8}f@^@kPO_+1ZS2yVt;$nPpjr6+I<40uj1iHI6XE}1$QaK*
z@U5aV(D*_L9C;f>QDwSZ5*TntxiseL$1y+8$i8de+7+*SX6f-^Q=031%{_ZT{>D9#
zxi{`VwKtSRhUd0+aYyN4d9l3^FR+d$pXah(!UM0g1J_>nivzy=e+m@6{%gjO8a7P5
z{U!<ddB=clOR&QZFD#fW2!h;`V!_Z-Jw*@NGhlI%@^0d+O!2FfAQYjfWPE-YW^eYN
ze9>CV<;~%->L*Wdrl@tn5;w4PnqSXvtvUa^FyFcX<RdkiooLuP-aYcat(JXPW?-4#
zNBYI2%NC5Yk;Dg2;p?tABQw3^UAY92>H`u#5BIH|ZiS^sk*p(bY`x9zYJC}8X)-^(
z8SVY(eZcE<<D1|Q+V&XFo343PJrOW`16&>J0`ZRy>;{i*)p2)D*3-^wFnS(Zy{8Lz
zZBTBGdlF}Qj?<_ey3X@wAn-sbH6&4;IPCna)YCfmyAtzjMJGgJuSr%5{)H6RG4I3f
zujNTkAH2b0pQx+?5+!)X2w9?Q<K`=_#iE%}KF~CdgCyd8_H@*amumLVyH;NA@Om##
zcq08MOVp%Q-}ENZD(@-r*8OhIXC+zqez)7*x-0E?be;|A77d;fb$JDa$xmz&tArbu
zstW8)MvScolNhj2{#&P7bNae`Xg9($`bm0@{C#R3<UCF9VzFE9<(VnWb=mzqLs|x9
zTguB26R_~;Y4=4Itic#=qNC)gW!qi@)wfJiI-J^~lj!ClPw#Qv_mu-}%Qg$ur-xLE
z!eI4qE&jDgX_EX$3`a>onF4mbsai3LYkgIt^I7Mw)H!azn%BNJ!U@eVRb=h?&PM|8
zeh!E=e3)VE@nD#k%?Dzf#1!)`ywV*3sUJ7L|3tUHw-7N-&pIwisg&*r^pRZU*z_tO
z^b7~H*g7)fJ`|qMk1E*fLhifYu}|MUuQA3ynK3CZJU}YiuLRY$T7BXv6MeTuuTa+f
zLj1Y6Pn(!D^ceA5R3dMCq8C*&)geW7Q;ng#;U1HJofxBkl?<rzrqHN&-sTR=C;igz
z&^%2K4x(RmfxVoIP_T>h^5_ZZ;F|0aM($#mj1>rmopUxe<*a*ZYIf;Y{amC}2ejOY
z7JfqIP*!z&B`g5HqG~pKIelU>R{8706xH`hpKLc3%ZP%#IQX^oIsRCH?vyxn61L0P
z*0$xqs)WqP6K{YaK=hxU*U&bt+-hQ5KZ~K>fY;~ZjviO%uM7!JyRw@eM}<N8kIo2n
znF#IFr%b{f#;a>LA|uju_`f@2cg!iI|LnhMeshZ_ExppCT564V3)QeQ7<%AGVF~+F
z%}~E^=P7_;=V!d#b)tD%z**JIG^hMeXu*AD>Um9sZ_>kY!M>LBM!IiYu-P5C#}K+=
zA+BEf+zdg)XTO0jXXGzy%+_G9o`LypS9-^|GH=7*rzvaxVB4&!Dr-1py8wfOce0f3
zCqB5=oK2+9Li;YU@kX6<R59~KmxONAaO<a?-=X>YE`a@Wj^8{sJ#(`X?r+<B*P?hm
z(Z3QQG>*G#e|wlr0grG_o#|Znt5gRWlH5KM2`d+5fgKc>u1P|NiW(679V_m!PdA(X
z)M)-c5_qv}!uxFL$EowbAJt@UEtRqcpSfVXvFk12u+S%Qye;;m$an-nCfHxQB5Rao
zL>(hPPvW)gj#0~e3q<Q~{<=@ikexIZ%3Nbhr%rJsFhztl**j!0QTlwhmXpjV7@l#B
z-ppBCy=tTXAim6r@d*|s@Os0fcI(fu6(5pN_l$UJ+_E$_Z`8zaFy@7L24I(sYNci}
zpLJuJJa8}5VU2}nlB(B62*mJWwjWjI*o#;HegWf!*!+WrI!j|e47#|s43748hwCSM
zmoU;7eh<vIt}wBw#PE?77_AMf>fRy!<n~xy5O~LCqMH7F5<aTh+o-utdUn=Fs~K`}
zN^scdJBwS}y2@LQ%><iD_O>^x?=TBU=9OFn+GW-`)p9FuSL!|NX0rvaBcYP_s4kqZ
ze@Ku1|FpbD8t~Xx3p0&B$|C+Yj`Fmr8lZ12$5ZH?26M|GwCl*e&pueAOS~Sq;=>Zm
zbr~{WuMD)E>TA}|uZQ$i@phFmHecS<@{c2F0y{dEFZ)4AhIXMi)@*<61cwIY>dNii
z#zy4*3vr@`1*d01^SxvxYszYDT_ou~-?ONvD*1vHJ)X8GAS8rENnPsY>oJHjbQW`i
zFHAerxue&$cuMnl3wZkiTddS={b-yVnN7<0v7{5mWB9zo{T?Z%V!f%;<+E9MjoQ(>
zjNP?<@)~XN?8KV3v#gQC`_4;{j9|hKcXs`=IjBUeLhqPCLTYR>TxZCP5ZLWnoWK+;
zP$P;%*R<n!aex%zYKl-^O%)*0q#AKsOGDr$@_r})JDd))yPu&+EIaz8mF}HzVMeEl
z8&qm6nc6mU`x=D0`gMiJIu8*sp8BL)+~_E{zeV+1<}GeR^po9RyHcKVzrfbxyc4B4
zoKL(li>V2q!Ckb2l$gT;S!g5T@+RD}jqv}pozBEAa6Tm;f*lazy#MZh&!dE%8D+-X
zjJ(GXcz5;s^`2-pnpW%Boog0XxpQj*fsyKRPcDpojISd8VodchY3)C7g!=N+cG<$l
zOF#sMzk^Eg7)o1dW?Zm#&y&-Th^o9_Yywhx)(ZQ2b2j=t(8rLKvlOf}y{%UAev|v6
z?T5n~Gk;KGbZA?`&uJX*k>OF^dPHkFkfdpWOlLX<c<LGqgx<&mky<D7>>xZJ{snvN
z(vuAhf`eTU%&I~yk0pgwN#C_rgPXK^c4QClNVetYUT!>rtjhSCwnlD2{ur<vDUG#;
zAI`#%ix4^->ww?CK}n-Wmb)h%d3>CI_E>^4u>0xW*bCG?p{RR=rcL^*M{o88$}jGz
zWS8Mk1^bJZ82q`;V=@BJ(g=#z;L`pa+k8Q*`MtKV9=3;9n`rIma!-qSVlH+uDyp6n
zfX?aL0iGfP=7K#N*TTPI7n(RrwT#z@|KNht5=$@t7+t&B_%(vLV^GCldg4O-jvN8u
z+&Jw~eQ*BSkF3dGWobT_z<XP>ENUQx6cTuP_q@D*ZJvJ9p9eu`6Z1qVOLX0(#K3^2
zAQNWsUIvfWrCa0`iK-K$?kDAz?6vH8-3juqi2?KfzB<a8s;=(P($(^^F{hA*8;_br
z^Zoj1uxq7y(5&`Nv|3d|TIZMHgt4~e>jUwb-<axW${Mz9a&Oaqnt+VR!|HF$zpxj;
zS@y@`cMK0H*is&xY$;B{!p&0~liFQV+p$6ZyAPp)H?y|^CvWUI6S%BFzchW8d4VUG
z#ywEuSu9)MLF6dY>Tz(p(fO8}jQ|Lg<KyCc4JoyT-Fj&O+1$sj8;0DP@*=)ZLkt)5
za)h|YPI3;HqF#>@+@I4DP7|J7B4K|kVO1_9ct@pp-r){S6Um>H9cIzTYyRc=qU2A&
zdypyq4e$&MUSJ*?hOBUqjTBIHDhgkaljUj6|G3pOA4?t%a#t8q9dKfR9%-aMp2a*h
zB!zo!F^Xi72Gt=av;uFHTE+?L#ZVG7d#kBzM4Kt);5d?S<t8_*Z|Aqv?G$D2JCx3{
zTKHwW8VloO{dow+W`Ko#X;>z+!%plne~8>a(k63MG5J3i!aQQ{<tXkeKlL6ZiTI@`
ziEY11XY9*Cqi8mQk2H~AM<YF}KS2n0A-!>U&BETC`N3~A7_UGxy0C?QD^%`g>>BZi
zh%o}Y<!=W)Wz(=>Cf>NMg6J#v1?bD@E^0|9T`PL}sG7p=bP2YBqHVqZ&(uK-15}Tf
zhdVHx_^p!H_lRy7IZAwJm|F^O@&IQaZ_WQ&{X&rrevMk7Cr+LsI3y%|03v<gr9co!
zs!N~&Rl|v2<K*`n;2Futg_7>%cV5cw)%-SkWJ-RkNPNh))#1p+#{-p8;t~SD{VTcD
z=1I1YZf@+LYQNGs?c-vToX&54kKB(3*}vMEj(qggplo0Jd=OkKbOWF#saGcwF#Wm~
z+930LX8QY`&d%452NwCD$`ijZ|Lj)wCByBG6rk#p%-%1R4$yxcb!?m?=)`4QelE}c
z%CW|0=E2+q0kd-E0$k;VWe^%)Z5jI~OK*KGdgQi5i47es0yZX~o+I^RRrTqEX_CyI
zhrq({%bwx`(n3Y{v*pg3*X9nb$pT{9R`4Aj^cD0#>)VKo^r{JRso-H3J!|vGD~t=W
z^yAp2R#Yy=E{-jwbM@AffIX?22x{czgLG}OE@N2eD?HqHc-1`Bi}Jr7GeM?mAKYj}
zQ$xEna+cykUNRzYGh+sg3wPf+39eE6x-amRy_pp{qyVvpRnEcd?6!0$C0ir8#rDX{
zRW{6!`z+t(ljHwkgd^<d%aV~pv2|#2ff|=ozDNw={VLQN9oy3&&=PA@A`qyXs9QL7
zMjyQJ+N8SQ^Rc$L3h$(vfe`>on!GX9;va~Vgl;FZn*H^D#syg>$Faw0EA^z`Q@vI>
zx)2+XRCFNG7XXsF`EaUlBM<7t&ocks!*71dmRLe4+Ay#PTmNSHQE>U{>caK0x*c;r
z#HK%s^c+iN2T7MtYVXe`+1>Li9Uq%sfTxP%m!0?s158qaJV~Yn;6kxcR`ItKXYg~5
z>v1rpJUua>XwP5nemWl>VSGKxWc+*aaJa9xYzX1_&rUaTzwctR5K6lHz`Ld^eme;4
z1}u~EYyVmrl`$+>0-d*n;biB>8@-1AjxK?#qpP7G`uwNS*W5Hwsp9|IA&~~N_+*&5
z&iErs&O7mN{ZGet0Vfsj#M+8$r_O6uOBUtN^h0+MJ3<C-!+wq7xVCh}6Q+Im7r8ax
z6t)IMZ*+twyx+;*#9<ubu+EFh-32jkH(LgjLqm=oH>rO*Kft?pA`#xvjSz2f&||s5
zfb}G~g&Mlc!)P@g|KiN-B@Gk&lAs+Sdke+hyg>|<S5H3L+;bFOF+t2w5I&=HnOh!<
zA+7!^e_3NbmlgNWOyx_IS0r@-OPtEv!E3tRpgGQM8;(C8j@>k<GFzbI%Uq{lDpL;g
zQt{;42H@RAxIQ#$u^~x(k)DENVHvwZo35<)xuR;!j#WOialTUFs{4yiOg1Fb6?#Q*
zkOUt6>6!>{eVjhy+jijZ?+`%#`KKuq&4_Red>46F@bJ92;0`7l@ogO~@E%Rfkz}8E
zWM0kqD|@@pQ}RZG|3(OU(kXsb48M9i+}^N4fkx$(1%Bne^fn(=!wsz;ZCh`18WG9?
zu|-dR*WO_iuOExzoY=V$rA*|t>tsBsB|O9Re+688og26WXFG}j=NR89gO|%5ccnjv
z1LHC4oeEgZ*Hd}+g?`a8!0XmP;ql3}>4ed|hy&}RsOY-F&W;O@O+Cm2P`dGbF8ZDv
z2}T4;Z=*ch3g*;2H?xeMSpF;TANgn1e!PS*09RrH@f9!yjF6zkTtE=qBy0AbJ(<3)
z5MDZ)-ed$loa`N~I%&pNkRGk-re$~P=H@61d%22X93a*Q%BNM9+V*Rz<_XR5cVlW_
zTFlN1h>~*BugxT&iy6}DYZmp_(4BDgwa|c$o}OYlm@*ni;!WH{gmG@cy6pA8PwcJX
z>Q1+rDsR-5*cR$eOg~-;_}HAa;q^o5Cy*405tk-g8DcM};_q7%`yxpdTxKPq^~mXJ
z%lxr~PoX|SIhOnxjc>dDi%B<2CmBq+mVh`7fzI7#QdBmw=FL?8FFDPzS3Rj0smyk+
zU8-Xdn4tpo@<RT#HEf+98nKzivFY{<%c_2?c!+u;%rBx7@&bvR=KOhCr|kfHU&Cn{
zj;@wBDQX@Fe$k(9#~}r>8Ttlfr{~fH#00+21bJUlX7frL6#MR=&eu|OE~$9Ad<x$+
z1wj%Hdvo5$>&oeFf(FQ`{5OWWB#i*YumG6C0D5+c7DWZs7AlRgVypBr*uoYnti1X*
z$KduZi>^|GkE)u^u!7hrx=B<2QqQi?aX+^zzH7?+ev)n*Z2W11&OWo~-AM*M1X7=)
zLym8kjkvl8jgPmgue|0ZAQ~o~<DQ%TRF5gD0^*=G$`r^_CwtS2_lJMEa&KS$lm;(<
z=lw`T@yKzX({?@3<|+!mXEEaR*$Ey*nwQm6CZ{<L_?-iV?iyzL5{ar+owuF|k?WiK
zbB?!H9ipURM&pmeF$(T~t+9aGE_sA<Gi6Su?mdLN|I9PB>BG=JGxdXT(=<*MqFyin
zH%CY@84>NNPVE4rN*;t@_h);f25hMSFG4Vqsjnl(J#nSB-|p(hNl^`)H-i*4Oz{p(
zeF&k)q00vhOZ2KvO5)F&Upf-Aj&34ao=p((VABG}u?d-8aJTrA`cvWhzsOui6(c+a
zk%jUbdbT)gL`1<XP5hA@qNTLc36ru{NfU(UCdv`Q2KEr~=qDRO_s5h+h=TiqLhk@y
z`%A6y=$xVytmI4KjK_*A|HIImK+a_w;YpDB-Y(~n%iEvZoYp~drTLev)(J~xYyM(1
zc{4)p?&2T-WqT#fiGuS(zgDXa6p}BV!aK<ZcZZuq1L-IBL10SMZ_(k|i?x_5g&`He
z@*8dLhJr1xl>cFrD_-~*huo}v3wR1!rK}_jfGedDDu@agN0#>=4XNF-6v_`4t9W9|
zUbvPbVL~6y79|di=;_AYPF}BTg-DH!dS^NAq*W*Lm%Ml1Xgz8$+K)2)F1m(So{h8d
z@9cjVhr~xJwojFNyqkL}K_8j+RdO5XH^^Sl=g;0Fy}WypsbeffBpx)BidhZ1dh&DL
zmT`WFt{zFHzVo@hXaNwt^Sg*23Fb2sCz0FCb=46YQElp)_Z1H?l7z)L*hk(X9vD@L
zlz$8q$an73_VefkiYjT&?#SP@<Yr=SkFx*mWJEL3&lK_QOdYhr<F$-BRbMPr1dWuj
zq_#cYX>_+}B~?1Lfo)}f@*-BN4VqOI6io*Ne;3j~F3Sb!?uPM@_d&N4>2sdCNN=eV
zurA)163&7+7ki=mi^&miH+Od%K6|(IAgOX}Jv)WkdMh>y0gU1;&87_?lgjZ^;v*d{
zS^S^dx(><6&50*Wp>RT$koLYW&}~&x!;af*oo}l}<ELxpBxIJD|7dUf;p9U?Upl2P
z5u8S9|I5%LIKlO?%z9UCw4(6>>p6<E;(o&XtnGJ`IzIAmQgrJpa^@X1w!fjL(bd|;
z?$^Ys{1~7{z~3Y26bFIgqYe2dDL2>(4IUr;T-kIw7%w9w8&0*bAS9nYN!$@B^Sgh4
z|JnOHve8k+;LEURpKDq&xv_DL<WD+CsRh8uKltm1Tnqs%I27m7zO2R8UboS#Y4*Ma
z>TvRz?Wdq5_mRm0%tV*lelV@cVi0Q=z_!+p0d=`#?F5&#^?|<4r{K6JzE$aSBJOr(
zA*`dL{=L*oMRyc+^c@J7W}EcHnSdk2vPex@GRT<w@ln~Xt-gEEgw6pFj;al9AczIh
z-FoCw7Ikz(CkOqS-wacAlF@jk@a^0565%HKJVE&+_~Cz)Z2M4yD~vnX&6x+9*#(nS
zJR5>;wt<B?Pqg!<_^{=5yJCD%OwY(5hy|m1Dj1)9?<X8NCe-7|*ed#-D!<j26(e_5
zBV(~m#->6iIpS9tj~;(1OYy$$1-eiD?|@Lhb#L}>8=CXco@$OAS1wn49w2S<-5hPX
zK@5-9cEk3n9X>cW{JIY=Nqn=_TS__k9W|)eJNq0t1vmisne_|?pL{$=u~-6%=o(AW
zDoCNCoy-LSJ89$P%|Zy0ip*qx2C6TOG99aV3LglU5_mqAXMDmGeDuB0cJ*3!RZe^}
zCqi?=Tuob^HIH`Ow0?4eU_SOd!<1uHuOHjf7l?^tIn%{_{k4-#rk({3yI*iE1=kmQ
zrCOo!35;=9d$DUv7!lYV+*_PqVK23cR&K@jv(JY?o6b)|^qbJ0zcMp$7Z5?PC!Mt9
z|H1L~NaGnrx1MeOXyP-=D7_q@-kjH&yd-$zG}9~h>O85PL>_+mf;>76Mx=)wUx%DZ
zo1;&se<CAy##H~hX)1KhvJ!nD^L*;r%76ppL;hMao!iCpnCovVH>8@~*)vZB*~8Z&
zsR!17a;e(Apb)7v->e4&YTZMXAK8KFoRl{Rb(35caV_lo{r68A#0x!`)^F|ki!yiZ
zQ?dtoF9Br_cUcjM#pGKxWhf@{l6mig=9Qm@w|}H~=>+R{7pAs@2cQ7AAf79}(V#`I
zq+b?n{trW5@>HzG2ftKO^p!U*)%zvj?Npp*zSqN^WW$^U2_!p@#P3^yfb=-V0tFhf
z7PuUV_76WC^bwm+1sz9rq74{W&oYP-jfi*H8zcV(pVLm7tVJ<=<$_7+S+49jNc_Nq
zM&Y%C<+S%Na#Ryr>8e#xva`~MY#b8h+--x+2pRyB{KpC=FiQraHk3wLAQMuMO8o4D
zX>TtD#{DcG`T%<T%Yf*e=GM3^_m#?=c<Hjb5<P9X)IiED0^=E~kk302j6T>yuO?o=
zwnxtT$ZbV|#l`GB>-}zuyPqOMwCY$g)$%cdkBAepHu?09g|t>t02*cE_t{c@0$|0c
z&0=_6G1KbFzV*QFSe|<OWxb%U>OuKtEPtILaN9HJH_2kXt5nj;otMLor-UA<;qie-
z_hT+HAxgCs<ZQ{g$n@L4OmW6)&~Ofhc@obvjB-^;ukb$zm>9(qxUVdDJ%;}g)|jH^
z!l{lvD@&UvY2Yi^?u7FKl0|2+rDTg<me3iQe_J@X8H0mx=2zZ%dxk{6M3n7vZLWWI
zlJF>_7sg|KZ@B4p`PS&(*bh9D+L8NG6yd&g-PHTRm2S7uayw!$j`nN|@!9&~>+1=Q
zwAsAsySyz4p>2$8^&dW8+-jd(_lj<K>3rR8XbenB0fnGd1C@)xRlHk#ok?aH06&HA
z@`Q1wLdJr+Ov{3~Qc~yJ#ZHuk++U+os{DzUH%o}uwv;m%sSYj6koZ^gcB=ec+Mo!K
z`Rcod76M9)4j!i1cuKp#jf4Ljilw`<!a=@tAkJ?(TH;9_YcqyI%Twe2M6sph0!VN>
zOrY<^q*+U3>37o_L#sagR#VI5Z^qW2T-*>qa^J<Uj^Al3Annx2V;yq5)-i6KjBsFv
z9Y3<4J9o9Y_J5TLC`u5bnf&2370(r|qThO4_yoSq9F+Y<{k@2p^BHzQWz(}n2{Cd<
z37UgU-8hvtKTKs?W>q>9`gGSnz5_+|U|<`jI$r(eR#3wM6Y<q2nk`^d);O2R|1I1u
zxj?!l!QZ=XWaGog#p~>u!I9pATnOaj;m9vWfP8d5<VRhSkg8YC2A*6~74xh{)T${a
zjsUnf9|NUZlq`U6*B#j~;rYcu%E|Kd#-FUF5g)|rwjM|1p=?;`EZ=u{v_F?P%WSi%
zY0ZT<K9idHoC&U2T)W61WK>)GINN>WSPV}A*llV$zg;tr=P<C?lj;9hlZ30W6R-V}
zkR^GodTE*0c~RIU$hxDM7h*GGS_#SFX0j)fKn6LedPZJ_L9d?eyjKa%dzXs-nQh3_
z7T8PQm_N#;X6tQoZ-6-txIfRL@16<UYk2BZSk75}#qt$kpR>$x+SuAtl;DPbY<d%*
z!q@W#p?VPY&X!S2(AWC6_Skfj>Fs#a5U0U2=@dWLD2z?N>T`-WO@ExG9e%rT%13Kq
zh$T!bUJSi(Skk><%JflHl-Z-|@5Ks8K{Zb#6B%sd>Fd-@hR0BiI^TY)C92IWU}Xy!
zfBav=FGOWGpWCM(AZX0W#@CV+dRWT#$f$3jX;yQ`ptCFSw-h_Q3QxEUinDYfbcT2)
zy2`(&_S^C69TIb!Gi;{n)o=0`OVL>wEWhnZgJCbtXK+BJ?E7_eExv9bOTLz&Tn~mV
zIey$|65J7eU0AXvY$_B^n?h7={7Qf-VD2}hj;wiwy(Pr$<*y5N@Mc&G@LDL<z1N~T
zLNr4z0<oSu0wo|<a2JpLVw|e_T$Ds9|D<{wR+jaP0q2h#>^^Vrgx{{5F6ZY{pWKx`
zm=T}AY~VlZaa|!gTi)+mX7(G<{dRKw=UuV<Ar7I~?VrID?1OG~mhFElBSX&_$BL(m
zoc6-EP@W^F${c~`*-WT;?1KjoCncgV=Xuh}gsn)eUgbY(`Vv0|s!R3+my&r7c9aZX
zsrC0Kz~3tK=+Vi>=50mg?PxIV6kYzrtFiup{@Y~yw@<7-$B=qEb%+wnUnKB#a#XN;
zkC-yUg!81RsQU%^P%2IzLz&&#Y6eB$4D1oMRF=pvBJV*N{Y?I{;kf5@qi+PF3)~s2
z)qX8@(C*hdUWoX%4*_pz#MQTUiTh)lTeX&Fl~i+CaQy;k$VIdP75ZF7R4fL9h>$Z?
zUQ_(KPz;|B_;2(Zw?KQJCJDFt=`447a4jna{?^?y+5u2=Jbd3BOK|vI;>}%sZfisW
zfh?)h@>mI2OWxQBpX#D^R1Jw{RisQ{`(vYSywGmV3KS7CEmbJLH|%iu^<0e8MB0yv
zIcY>>#gTZ9=eS?x!8H^2`%)ey8Nj%EpNApcKO&_{&)lm05(BDf!18xe%Xk0l8_m^<
zN`l7>kHkPEai)Eh_ucq!>}tV-n>Xfs3}QY!O7?hjE<VeF)L*Y;`e~d_fPkqqn<PqB
zdJg7AMb=(uVIB8OYH!#Qwn|#wzYvbMs^HD>8RMfn?N>G{Fx;`-o_$o>swR}btpD%Q
z#Br-dC{HkWKm364;RXM{Ra+s)a*0b(jfscRwb?yRb%EP#C1sW&S@ri;f3KWWB4f&X
zk9zebGc0dCX7JDX+w$(4^Y9or;-|x7+<&Qp^;V<H6QyJDcHAG0c{R#!E1-3Xe>2LP
zff7$vC9c2d7P`t)dEmSA-N&l;!Yt<L7WW}&?fHEgm%*gCIwLFPtw$LqB5!ktcvZ>t
zj-?B1E{j@C#<bEAGrn50oX%xQEHm(qv<x+IwpyUvryt})PYN^{;O=vlgQN?KY<+z{
z^0IOMb7~#g5gYO3Y+Nh%auZs;)(Piqd-6nebkxYDH4uDOw9i${!~e#l3c4OuNsZ4%
zU?N&r*{WNB;CxU1RaojTPP5K=d(h;r7QN@e5I2Qsuyvd&^xdzsZoj~0^i~zJ<HYq%
z$m<f!sTIhyy}%2fxz$Nx!El!qTG8s8vT>vzkLIO_2nfD!bdXUlx8v&=mkoVI^+URa
zujdiUkfQG)tg*M%>bvFs3Qf*Ov0%p7IeD=*wKm)ygU8*x$O9hQtaXzdaWQ)ZHP^pS
zX`Q;6t@SO}`MBv*{yFg4Rog1ye=BJ@mQ@qc_B-&g9O);5Ep2n?RUf<%qJi^A0oAat
z&U45I@+=8nnSxRR^nU!j6-sjA?ronNBi_U#AT|jqQi3iCpHU6Tz6y7qw6U>E4HkP~
z=2L5Q+dJ5H4!yTB`EV6B&mdQ*O6ytzy;9)cpgP&;%`d<Ux9QmW8)FI}gnF3K6<6_&
z{f_A4ysfU{x~28=VGcz!NuvfYquY5eSs3#1murnB6`y=;{=6_1nKiKjCHm*j9hUE{
zChRE~J0kQR)BmK*2H&M#TlGeGh~weVEo+!w7;i;%lcTEgn=US1JAAy!!keoe!)%`z
z)XXE*D+N1)!`XX`2ctN!eIJirLCE;+S=4Xqmww2N9=~}3hpQ|#4EUe;eKO!gP%Mb=
z4!esIFi!X$SQK)7Sa-IlYEQI#LRxbcur0q<Oy{KyPIz6_Ad2CKONpUBY<3v$Heuf%
zEUpi0vZ?}IcU3j$Q$*R^S3aLe{tp9tM~A4aG-a*p_KPyJRT|@bLIvd+R&E=+``dkg
z{quRcPEFZB^G}L~hZp=@S!)!x|7_^{6{cGleRV`VQPM%IcZ`F$)J|tu*{ZmVdu+%S
zD}nef)w>5?<GNQtadoU>-59#yTBy)np91U0BLfUSuUF#da?)#jeHgxC7O$6>G47BE
zPlBcv(i*}#Wfsp*Yd@M;%_wU&+Yh?U@8i1+{)aJ@+A_&xi5M40au9jd54{O(66G{|
zN`tyORY;?*c!~c8-u$6Dcs1-@uB`9As($)@uF<d9Gk$+l5iK4_d|s(lr=Dch(bg#S
zNaMJ<s}YO2)ZK?kynh0gG`t^4(=YO|9p>kFD{2!l>6Fc*p2{=+3^Gk?n(}i0cn`nx
z;W>NcDCf=Tkvihqbwe#-k;*DhN5Oc`?`O8XPR~SnFjx8CjKjX!S?;W$H<;JK&VW99
z6er6(r&Qd%TrROe_f0@3qF9uz3e@1^@Ek!jvD|?7C6}tNRnW)(VT5Toct<{ZpRN#b
zwfX@*T<|J56A#S8U_TVn$ZC4@Enz&;Jz|Gvsmpszy<;he#Q55fkj;x+D4~Jhh=<q>
zXuJ!X(cGJuK$rI9@S$2`5>OF{Pu1j9RnEu}85pE89G|B%5BlBirh!hc>e45lO1TFB
zW>$0TwAT#`!}#=xK{4!Rqi4k%;U;_Gl9`s6C#D*nE7jZ#_GFfWJf~=^WS}R^lXlvd
zHbVdX7ibzPe4e$h50$=!jWhX!Qhb%83LA?GhA9vJm<=|(vVSjLpNWuIWnq5Z^?@ec
zncT>7E#4desB{+wM(A;SO_+CgX3jT4j1d#jdvf!s$FaN3Y!z1eLeM?NIZsCks=)5A
zf1cYI%!8!U!qY1o${Un^p!S&77X?Vi50}&z#|oZjVC=ZuReO}0sJ9jU!sy9v(5D%C
zueEA}4`Zm_MByFadW}$`qNKff#Kk98eQ$vFafKU$dMZ`D4j=CG!yZjyfPML-)`sZZ
zcUetuf;^HngWtasu0EOVK#8N-&LXl@rANO=E&B#FVx`BG`!T%kvhdO~ArWPdL}lYl
zYgVmEA^x^Jy_E<^i67O5T`8<HpjRBXMZn9cyW-D8JBpP}J#g{G{^A!|`lqQh6*FU?
z_uEWcdeN}{*!<$!oqzdC?noDl(J?KZEd%=&s^cbHXWJ4`pG}RMF)%o+;uluX+a(eJ
zd->(NP{+hq>$%^Qx^m)?sXL(vG2EThR*x#rLorL$5WDb{g~0ffb(B_5c~R<oOtjEE
zR7zsfC2o*}Rs5Eao2%@**<$@6wvRH<5K0ve;+2uBm${g&6sLlrgk`$UZQd~6a^xsZ
z`)Ur}&k^y2)zx3#k%P13DF)hRy@R;!1>yt6BJsluXSCq4hZD_}{WY_>8G{h%5}3&#
ze-nledKntM6y$yY=z_fkJe>pZEH&J}+thX*{UeuAcuM1f<d{O2#XtTu+lg*oZl*N|
zAR*^jbe^NQS(Xjv4+=@d<nlO66AQk@LO*eU*W$Jp^hpbGUL2qI3GuP@Iw3G7p6t*~
z!E(535?UFFUCsdX?N_4F`K}l)TW^Q`(jFRnEM}m`hfbu}?}L`TPY(Mz9DQAg?D!R}
zJWlJ17w+Z$#cOy1lgUb7%LLlUI?DMBSf`O2K_(~p(;dfHe0(Wh;nr6l`{%h1RZI8P
zu#>v=b>B#t(4OUh1*=v8=JwJj?l<^RQ=xqz&2O&YX=j6yZwcIc6f2#47U$Z;5eT*N
zRU;UL=hCkZ6z`+5WbY(QCPtlyp82DVek}_P$;%Zz4YRY$VIvbhyS6r@-<iPbf~v9S
z-*V>v4@0(wvH9&Jm5WE#s$k?8)#yXJP^vmd?Xny%%FFwl*^tkk({FH#{GOFY@dy16
z19A*R54?*i`%9kOTg_%ij=%7WN2;Uo#H*9|zsoLkndMZ6TUTg2=bTx~P3lat%6$v9
zH%idXW*L~%Nw?)?OVc9Uww6(5R@KlaQ6y?_(eJ3OaA!O<qzt@A-m`_R#aeB0hEuus
z;HX6@-m;t+g4C!nO!5)=JZs+iPjN3;{k?R;P#@Zm`}bCSYd>ea^HWkBJaU;bx92JY
z5=A`&(}5+Nc0%P}jL0dX94rN#D?&4=J{I=GANg!0azcy}lSAR(xh_&q%0`J^&{O?l
zCFL^sXX#gSF3XI~TsPyX;b*lQ_0Ir}mC)vXTpSd?$%a?MwtO5x4&8G+BZppmFBWFf
zfPDG*gDk0GmYrF?e(%Q?nCopH7jOjdKsDvOsf)i(D?zHY3`$&LpzN+fI~7U34clLn
z9`EBYa6uj#1kX$pI4&T5ct1C%KDbr-k@&~@kjQ%<`jJf~y)?0(%Wp-C;2*fzpZg)a
z!Z+0d&V-`%1ijn(`Tg0}Ds@IlVzZ~=PdgC>Dj&Z2&1EQ4D`xD-Iklczd2Tl_(T!A!
zeeJ2#?DWhPH-}zM^1FXL6TgTd!4=NM?Eqn&(MqhS9O5fazNng&dmNK={6#*(aYnjb
znPcbZ*1ZWITrlC!n-dkU-^4!4R#xon1ClXM9iuzOk?{keORUtV-#%k+HpH`*@fYI&
zO?ET!{6l6~ut4?Da~gVG@noe*_d6<cpgVwvJ*K~H&?;Evcpz*Y2ASLe;D~28R>w@n
z@QWAX>=j1WCM;gw%@*L_G*=Q@WCT*!ovqFWg%v6Xyw7I@{#O+fM2svk?kxn~HA6Z{
z@BT?pxtAYG%keMb2))9*SYQi~Z~7>^P(yXbf>?T0zjvX9J?&y-;S3Z-(a?-s?BDCq
zMQV)fCGNTd0`qOF$=ot0Ph7InL)n3DrKfUG*CAc#+N=s(XWX_$I>P*uL^oq#X-0P_
zJKly;nn7~LbNHaxn~6C0xDK(LSbtH1!2htn>58AlK|$<2_Lx%hDnvuikc3K?!(>B+
z@2$1SV0!xtp<yiQC3>c@SV0eW?9oRSsE-ID5(={$HRe<wlaIWZ>w}ov?fBW&BTrJU
z9S4UNesnuqt~JWg#4X$tv6ZaVJvP~oW(yv6atnL*F@9@iE&It;Y6zAT`c!B6?zt5n
z#SDF8LF;i6#j0%*>}V91UC%x8Zg|~gWqddmc-}X4+r(3JVo~1L?X^+9Rel|MPIo+Q
zowM~BGVkx0KQh2hF8`ZA(pfG$Ey(!vvsA;wUV&+kT12l#?r(dNT~MhtMk#o)We6N<
ziW5#QI$q@Wwy?c#r_Oh=uVHKJA^c$IrsqPy9OL!y#ImGt?^R%f%Z&`1|M_urrqHbh
zJag0=;>0*uJAw#Z+AI49*0Cqp%C|DD>5VSeYB=R9-UKwWJj<Yc7--=1>!<Kp{?pt4
zG{diSFDY}ZmA|xx8%uonlZIbTc&ZGZh5+p!$5BBh8$a96IT6FuW;ORpX`Q}oDiOu4
ze}!-QEU=ZE1agDBYB}MqSjnOSzlr2S(E^~bm}qF}@S%zVCBVajQ>PZt-s9$%f&Z4h
zbAWfL@h=nQuebRT>wzweVe4|Ds28vmrZ)!PIA`OAB(3I8$J=)c8+GoA8-d=#B=M>+
zd@0%MlUBsawF;jTc(6usk{XV0e1LEchiUibfpzeVM-Rr3mOWl(`A}D}s_|GhydA}2
zFzh$%|1!#6TJxlf2ffJ_(xtCU^+fRgRLPG(DwvQt=1t&#UvDE5={;t$SU^D2mG~@h
zy#_W%$G&yZ+eiJ_c3>eq*IOVrkzl-bRA{r>xTdl;^5Mb@Y)Y0Gs-ZQugdY@xJ~diS
zSJ5Zri_d>z)zr-Qbzb&CrsCG#2x^o(Q;v;H%y1JfyHa+;B4OZJxEXEXj;$<b6z`hK
z80U{!<gD=6o60?L&Tk{Kl?Cn^6FAvo`n5U4PHQu^N!3^WF@c}{^eKNvr)3rMgl1Gv
zbRg?KSS&CLLYJ5)PEWEu4qqeeFVML%u71mGW7VLO%%3qUzuNl;^#80Zn|#sFLAk@h
zN9?jFpKP~$HXo=WQkvgI1}d~=s*>e{A*NTYOvq`nz%G4NA#*V4GE40k+=|XAu0?_H
z@Dz<-i$-}jQi6pg&e&c0#_JSNbqN#&0+UhqcI+`<8m~2L^Q1hDwX{RO1M<Fb&YohY
zs5fy7Zw&bJ@om%Gqe9AsGR#zGUCch3#6T_(2>yHRXaei=m)6=%dYHyFutAjE5@&?n
zYuPJmY)#lLjkYl66NoE6A*m+P0xq5nEa>0IPu^yG3CMUmye}q(Uy)-m89r7gOyu!p
z%^_Uf>xGKOMqX@@MIk*XQ3Ny~=I83KYtMu~n*SkC`CQ!|`z`b5b)3Tb%AVY@*Q25~
zedSE<gfp%h?pyZR8W+?6q`st$w*P5)Hw;buo{B|!WULal`f^gx>ETGm$dyKGSherJ
z2lOi`<5Zd6?7G3cw7{T5Pa-uXBUJnyg<IvW<?BgI2T;}*JQXJCayz@s4(=M<kRw`%
zzT~RVA3r|^`tykUf;D{Ee%f2diC4Js2fmEY2$NvnG^lDs1#GhDO`AN&dxH;_qYlNZ
zNBFLOgfZITdeHhN47IQ_pd80b7(`%z#m+2b?v^VU@^U_ExK)MY5eMu^Uwgy{Xpt?s
z9i8C&UmHJJ*3UU5sE@CFhuMA%Mn$irRTok(ifglT^YqhBDOk8ch!>d)&iaQm>>(e8
znTJK`b1Gxy%x-1vdY@<Bm=&q!?bOl^JyU{6sFDW?et#wT#*C{sO@&7-FQ}TuW$7Bb
z=CqrK?vbVbOXV0~QDB#{&&;!S@H}ps1_7=QeRgcBJBa*(5Ww|}pX%!sH3JYUG|!y{
zgw2A|J$33vnU9E$6ncyvR*)#QxwcUjyl?-Dy!XJH(5Oweu<~hqhmF=V*^!v6;)i)c
zb2(t>C;7v$G1HqzU){MLXozkJpNqYK#M<nMh<qE^2-vTtLj4~}XB`#Q_qFjs1Vmct
zE=543I|f8jLb|0?x*LH3=^RR>WRUJ|5Kvm0p&N!8ddMM$@9+A)|FIT}%dENQp1aSp
zpZ$4o6T}9_ZW~BXKBh4VrT|uFBdl)3X$~$F=ywDi1zt`LZu}BflmeVh9rk)Bg&E=;
zfOhipPOyOR+v8PJooaH;SVz4Cvc-FBbw>Vrp71E3!3;Z)=93}hhgNd^*}c(yo0xQV
ztoF*LDRzy4g#*aH=_O6M^rHhG%%sE5$K_5pnBreFOs1YD+AK|C3*J8!@Vga6Ac0KH
zR+n@q`p`q;@>U7RShLKgcC=9WMblj`H%r>c#{QokI+yQLx;DK&Bd1Z1&PSXB0R+&K
zNx<>~Xq>w-d{r*j6P~zKm-qR8xBSeP<Pc~3H#-OD^9^7=rAbKln2e+OpM;R2!~j@L
zI_yjd<trSVt}K`tZ;6ELTajyj43;=6>Nesz#pxi&8I~yLG>HW1aF8_}CNSZlW8k03
zz^Wd(m}_??R~W{B0k~4PI`)<+FpGvB9SCWplDagu_!!-=y@@ZlM3IkQQFC388i-@h
zL}LsziAxhPl)$XJ33yan&EKgI7xKNLE)XdKvp27G2#Xt7yKzDq;Kk)IasAn}o=ofD
z*QSm##L$M25-`{{8f9%1L<|`kXl<gFOR5kw^rXxm*-C_+XAN6g=%%ZS3Ru1$3SAp1
zXZn4TN?9m!c+^7oLF{}Z_ifuB-B+3cDY{$jQ?fQsNU6|)T#B(i-tN@KVg|>=7xBCi
z4V-gN#q<uaX=Bu#Z$yVAKX|j|$vm6F1$)n3Y`%NAzb<(c?~!zW!F*C5;|I&a!1We;
z{G-<`Iqo0Wg_=$;hHF5UN~e-<d=-{kS`hFDh32@g4l*M+_G5-6M#~KYpjqBb>nfO<
zGG#^iVBcNaI&4F<IC!V+_UtuUVAWfF7<M&n4a~LfzvLsZo^=vh+Shii;ux=>4QUTx
zvYRNfKJY7qKAK|&MxIt9a4aD`Cs{}7k(#MGYW@i5wJ)MM#|BX79(DZqq80|L;PUlQ
zCz?WF_I{rVceU5gOYiZ2EO%K>cRT8VPbsNjLJF#YIr*tq(FIkn)9<)pwB8laP7WY_
z<zPhD_3i!hczOAs5*o=_kMhQJdRgH0y_-G3K@?*@xb-aKcf^mTX2ylB<OIcJ+KQ_g
zsOCKTz<Y>(_ZPN8`Pf_Gvd5-3yT*~IQOI$r4=`R93FG?!_?~3x{sW<S`gIv@;Km4L
z`7`Q3v0ls0h*yi>k|ex@LjRnCz(K(`<J_5Le)(j-qp%LOiIh|s9zu+}WT@Rqj#Kty
zwAK?lPgk?=Qw=|@UN$DD4@Lp#jrb~L*&u&-dB}R0<(XRNOx6l@Fw@0BVC&>KkqGdT
zF?8}pX}FNuZONd`|I{jlTR9U9;K5_k1Na}sm1OJez4gqKeaS>-$l@GG!j>Vo@tN>S
zX0EiTTcp&_PU51dD8g|FXJ!4@h$I$}rCCOD)F_h*-?*hf5{6mVYKw-K_p1+kWUKSH
zi`&QO1zj-XqP#M*sJB2sq@5OT>|x%g9`_G=QRj5B<O1hAARRi{nnArd(ia3tfEMl;
zmb9sI(N$uFdikB_HthosGA`pA54NV7B+kHrf}O%c%C)qvho`Qbh98BeswC)aOfRMF
z-)1&`Aw8gOYA}8d{?)GMH}PCETUOC+CM4??4YRaJ`k1<w0EDS<wqUc)c^-Y9>6|N%
ziyL|Z+yT-Yqq*lQ3Cy3je}q{!#a5~;Ui$tAl2AaIjWfC0%sV)m7&R$0^%qfaEzaQ#
zJ*ta&8Rn7K`+X~u3?w*<n=SRW1bjmHAE?zKAd~%lHSd<PO^rFCi7_k2!m6^f#3vT4
zAj~&YWzH<mA^kT?Kf}}xr~|4Z8Hc&70}BtYUoqbt(NEGOVTy_o;bV8Wse80ZY+{T#
zyuyXTJi<ZesFXwPcun=a$0PycxcqHXro<$j<Zzjvn5!Es6Am4?YSsw#dGG6+?2N2*
zImX=BpMvZ|C9rD;k=2~S7gO#KKYnSy3b!h|VzE@WIRKpTgn*}$b8JcnoBUPj$Z0x%
zf=4f-V!20s>&=ImA#}o&tC40S*YjDY{4F2e^$=yk(2r%5L-j4^gvtf9-o^gW9tYEf
z8Jk!M3{mE)U!~+7EBez$j(b6$o~M^&dGK96&zDdHHnSilhQKnV`zN-sAd2XVLg1#V
z&}~vAA}VdMU+gYKEPW3+-vrKmk1q4?fGlN%F<uX8U3QnZFc&(QWgvdk@1bW7;nvCF
z<?4_8n<HU~U8?lHHI;q+d=#Ufm-R&<^yxtUfo#x^;^qPHIzt=iyQGG@I8qBrI6RW{
zC8&ks<DHUFxd-F1<0Nm?)_Z*lt@|ru**8-B?j(10S_hKaBm~3g>)Gq6kqwm)$3FZ~
zKI8vuNNz$NS}zKL5bL5u!^P6F`HbY2GnUZe!XH70qk8=3hsp~W1W7X;(C%XOeP@la
zy2s6uVkRIQ>7OZMaKEi(DxuDCpi1_Fq@806Vf}I_s?3h*<i?>cnPYEedFu1aW9W0>
zi-G8Y3*jI#$+&AL*%2DY6=fre2~mH2(+-LlBdNhxnrZ$?I%!7|bvUJ>Urt4ql4_V%
z81`g=T+p{#(>Gp1n<u@&mgBddYTqNYIifb{Paf^73pmI!K4WNB%@J9Ztt0yTge0he
z3+<zB`4`Ld>P{o`sC|jpH~$nE=%P!IrVL>KWT^!!_nI$3sqmjj-@z|ZHx>p`JYJ1b
zzq%L($tQ~TZGxSNCC_9N67BrmPm=m%>d%UdUTiACjCY=@PS33`xQwRmwpK~~^|+tN
zA&&RNND<a5P6a~M2QgD11Bq7RViTWZFr`q%`k`FSS1SoxTrYgeB<j9_E`}O)8vsg?
zG|Lqr4#D*GPfaoru89BEkp7)RTr^tUe^*CvI0J1&cAZXG7YUD$JYM;Fb(17_QZe_g
z9rvOa<XNOO2}iF}7yd9;Q`=CEl*X?F3c`Z~J%G9G{5XENosq8|Yy3Zuvz;YmM&W#*
z*u=P+{r(z)ZG^v8@@QK<Z<kB&L<g~zZg7%AfG~yY_#B4_AvUCiJ<fO;RLW6n5nz7=
z`TE+|QH8~e%U<pfPjrfU5T)7<z<kiOgpd3_e^ADRqv(;@^!r~$@#m>apEJoUke36z
z>2rHv>1j!G*c!mkrM=*gQ^<T_QK*v^1hL-v6cCJ`*%w96ebyoE-q^R2*(}<vkKJfC
zwE6peSHX~xqV8DmHW8S=iv@&+Z_tZn<;OO?D%mWF7+_fN8{*zD>AY<9BmtSn+_^oq
zidL%c1%1IEtHAyz1atBXM1td`+ci1kHs}dwVs`!Ap=oiqI-Rwi;ScFOfKg6LP0|+0
z_F$z3V45})mP*|92{^~pp1X~u@}Cz08Ab%Bxs`#B$g$$26nrNS=gP9T8=Q_`*_aM=
z%S^L`s+%8$?k8zP?ERsX#FJ^xdE6whr@Gcnz;_|6YJ$<{GeRJcBhE4v4sm{=sKR)S
z0j7*M91KLtqx$Agmir3c&z~JNm^$2q6>Wt<i-qR`+f*Ren+Fmb>CcWbgYo8P!K$`O
zoS3T89co}(^qjy{lx7{`Kr6e=p03V?qzGAfOX(n{&U<O>tQ;YAx@;M=3FW#tyxBV+
z6=xUVo=N?84_X^%&Kty6X%WBPEUbLfP#XyB%3broe^sjtjAUekRDDwn#mof)p3XXX
znx7=vm99bn#1W8jsxAdhOgT55q#3a>`1s7&8o<;a+$_eyq^uLvJ)s*8!u?NhWr`J)
zfWwx0l=$@=R6z)943lCC%qv4fn^uzQmz_>U)!|=8%$QLhJH(>@10AQR%e)HZAZ=s%
zn4=^k6zFtnIG_mbutU6_CV3z(w(FxmkBZ|0!ctuRrmYA>0nQ?Pyc+T&T+K`3vTQbH
z&vm3hw|^PmGbM(r3^=fkhUu;5uP+K=)RG>TR<44whIzo2`Rm%L=M`k-U!7`vD`gRS
zKT$TaaV-d~Bg6nKNPJLNy(IK!K8_~(jSIES7L$&qIj(7=z#d73vXr@}3D_o%M0=Xf
zxAmBVOi}hY!}{Oa6+kAa4FGT~$e*Vo#}|lG3Vc*V4i@8UQpu9y%)alz7P&z@vWCBa
zf37wMbTRXgvL|o<1C0&daiyc;5tXlblsIA<SeN{KuSS@KseZ=*S#u%h)J0Wa5Nx>X
zsFmumXs<{b;!Xu}*kbG73*IrS`p5mU9YjrffFilC!AM+>jq!k$RQlR4v_&klcO@)}
z<=>CbL=V^nib2V765<1%SvLoaDl?35o>T-gX9Wq5Uf;k8ubZ$}Ke91cHlMxH?BG`;
z2KGoNLGL4o43Lr1YN$1eS41)L=tBRVJ24RF!KyABU1i|45Eh(-1PMB)xh%NvnbfP>
zECH{uwm_@*!XsoRpjE0k5v6{s;B{r<KAM+2PswCf3&d7UT9(g}W`ze9kyk4K*l7~v
z5y`&Y_%mTW6&pK5*>)=M(^6sonaGVEqyhOknlER}L(gX7{XxLMntx1j0H3BNe~ogU
zp&8Qp-mnjhrPY{M$a~Vo&Frg>%t9pXE!$PCzYXm^=<}zwRcxL<?{aG-JMI;|b<w<k
z`iN~wUjnT+z$H={NDSas^ap6<(A&j|KT$Xl{{3iLOB6$@(^Z~UwvvCo6f@wu?Ej6o
z0K_dN(hJ>Yu99~FrXPI0#CPs8xrx4gUBsI=AzCDljf=1I_x}z1zIEIgb$rJvhoIAT
zW&4gf`~`r(e-t}D`Z#b2MABDez%ul~IvH*!zrHZ$SIs0+(Dl9hD%O;?c9uaBr~9SM
z`T7F4oQVXv<c-&1XZ{AB8c<vWYqyKa4X}KU*qTrNyj3hC(9(bBhZs*W*nkW5x};m(
zY*+9^B)4z*p67V;W%h|WcA^gQZ?<z}xH_3@<)3)>dgiVwy@&YpKKBILmkCU_$3VD5
zWOTzTf!O9-FCd?OuiUK$e4JuN6UbD_wzy|25fM$jk2j>ywY_LIZE|lI!~&psZxHUq
zF?7}YW~4Kot{%5_=qdFI<QsY%VD6s&`q#|1<rOrrK!6i_UmbG<My7AHQp|dugW3IL
z{s4@hQQ@)g9BcJQg4u>%P2y)pL8Uk>4KuL&_a6uExcxPsn6#qk!<a7ZDNyXnT~Q2?
zlZiAcg?n8e3jm=K5>J$CuXz@jtKoNx;nurTZ-?~Pr(JC1(V`bycue*)e8{o_Bm-H-
zGFGFd#<Qu~ZRnOf?|~qa0CkZSrxWSYXDIf&!^Uo#vIfu_DK=N7mz_G=P`u&p<L8ob
z@9v*Z;dd#c?k@y^;9cb`(2vhR-6(p;N=&R4B|Qi{lRxD{xU4&X07!ymn9PLw{X%;R
z=H2i63oI)L`pxXUe>lw{fPax|s1uP1)Az8KNJ75Cg@oxs96LT<Z@P9TosM_Sg?5Xa
zDAOIj3~bZSr;H{UY^I=3;7+A7@VzejsyUe|JriV9WIg*>z>e@RiZE>@lp(M*>r(%W
zo-SCDp}}0eQ7NoO!0(5NH1gv_Kp)T3X2*+?>OPU!!ZM;!0#3w2VXWq4UEHaJhtZV;
zw_AtR+$gSth?B&w49n9_0Jx4_%(uIb8FTk749({pI33)N*?y|re*6&F>>3736l1*>
z@J1#4$0<eFJ0~~TSz;6XsDFByy%HWJh3Ob^$hIx^a5MVD;oY-uJ}8AA*(KXDc&IOb
zWn&ytm)J@a1KmF;1v<B$%hUF6PL}3q(tQhAT@LphQH)2DF$rct0{9EE=Rk~zTQF!K
zAK-}-pK{*W#Q`ibu{<foRc+3y4MzlqQL|V|4~AA^?F$%J7qj(VcbyD9&v^{ISz0(K
zj~?y5CDdjj9S#M5+Vs3GQ}KMOAhy&$^_UoHA=sRR1VkYdbmi`Y4rRvMQV|rxQYb#{
zy-|f*p4~hWR-w+AUc`m4LCD6jl)q1D{@N$W!+#Nb8iWSxRYn=w{T18_(J-vv+^a!U
zD(4W}2@_l~0dswbhNt$lp+vcg9MTWS%yeY3I$h<nJH9f(Ea=1|rMrO4Hu|pCsYP~m
z<}s&VoRm(g>T}I$7T%@??_AEu#ZF1?9_g^pc>ad2b`?zl7OW2ys6m%{fK#^k9_;7p
z+v|y^SN&41?X|R^3Z|~Ge{uudodNpumb;PRBS)czy&nA4;;~{6W4rzUisws8w8xR|
zq-b<`>(*uVx*b+xE6;Fb)b*W$nv}F#y>m4G_4L`sXHyG2KwZ%Q7OHQ8cRvdoJP!V#
zc31E#$B=m?peG$H>*cXuJcL7|*&ZgjhyX2fA@mQ>HBUm|2;~EXlcnLHb8~Zlt@YWR
zt0aIqp-Z&k*H{`G;4$?t;F7)N;r*6J!geqZP@jqQU@q|XGxSd;Mt7Rc6+muAE*k{b
zbem*Q#}9CDqf0agCxBHa0`6uWlfTQ~@AqVL%IuvxhLJ|Ue#=<Fe&+1?9JLsw*%bNf
zW9P;yMJ)S%&rUD1d(3S;`k)2tb4eZ1Ea=uk=N|4i=*Lcw9j0aZBY6a{L=CxW{!(DB
zPda1YiY(GHU2b`~{_zuYcD|c&?g}sWmb(Ha!;q6pfv6tQ#de}nA@9gm5##jRqipOf
z?_Tadldn_(%1W)X(B@v0bhz-b=hpjxnu|*BKrVfQN41O|lV$NwKDjh&wv<*g7~6j%
z3x4~?<Ges(D};KLMtD>yXC&#i{hs{t1hW(yLX1~vTOHpt<0LrrlW{7vhthtI7_8c(
zNvI({XRwg9!qCEY^gue}N0|N4hNMQe^Y%G51pvl3v7EmKC=<eZ0fMfo$$#^fOZIaP
z!2ACo&}_aD*lj>I764^smL<Ss$YaKdq@`p`eyowr!AHZ|qMl@3Z3MTN15o|G-;Q1X
zprz@f_&_}0Ft>t~RGf<6J3>z(-bklZ*h)eRQe#caoJ`s8^s}dQDF=$Z_oNX8t+4wK
zWMxv!F3I!<dXQ<=$u}xpf|csE*k^vBN>VAPeDiDH4cap^0q1#V;jWnjBs>>8Yeik<
zd?LB5*u~qS0Vc9>ivs>a{KhJ|OQ9Myj|p(--863*Lcs1K_w^z4QB%UtkRm`|!X`%E
zrx^B2&~281yZY_thYt_ceEv*|!y{D71FlB>a(7?4tsk%E)yU-ji2YT>!@*e8;AMGG
zGnVS6VOO4dIv#SU&{f{*-3ru1s{PZQH&bT?`%0h{PVmZ#{lKiS;+D{<WI%U}%VlL<
z-Sc7o!*Gg<XyAeUu&+ji;j`|TWlg!I(%p4|GGOxy3p&tlq-3)9Hv?n1aK(xWz~J2m
znV$oO5MPAdcTa<ukbrAtL~(&Qhw1rU$bq`r!na>g^hMVd_MP3A+xITlK5<NL3SSTg
z-LpqxzXH5BQCfpJ%RNDMt9vctCHIRPtj%Plh}IaFg@8B8%a8V_LSzRZ)koBXQaL*%
z6dZSKO&s^{|MFHBh|(gNK|lyRM|x#5_?H4(Cv`sdSj2~vhfDM~F#xf=yxH1){$|p7
zmgKHU4w;}J98s?rfc|xD4{|%nRc=1ZB1VgqQ2kNP32#ljXNxITtQHr|AyIuJkpesy
zH_qomh6GOQ7Fd|umg6i)IMYd7AC;vQuEcg(AWYkf%h@|+Nt_&IQwoId2$1BF+Sbu<
z`RXr)v?LtCe9sG92#j$to5`XU*q)_*L;B12oorG8J29Ho`zEz1C?v2yjNP${_z`W3
z1fujdPr{SdMmVIqwJ2fbe!mxF#SUm2D-hg{4@-T{g(9q=j}1$hki6$h;uV=D)Q71g
zV0IttcV_eTgHh%~9P!hNX3uYQIWNQU;gSjJ%%buv)Mt52@gfeNRl1hBEWGFqBs%Dt
zL7z@A9zaz6ViUj*X+~vj$IDIzK2=SsJ>@V(_)y?o>ZdTRoSI$@ju<dfr8$o*rAf=;
z0%IVLE~&9RSQz;1<`gChZFAhVJm#{w1dD9fYt?`K(<}e7;Or!ZEEeFe7Zczv?PO=^
z5G2#_Fo=x+!7JoIn9>`CzD1Yc3U8!@A3(3|Wm3!5Z@mW0MR&ytu`_r`MZCMD6&I4|
z<Q4jOF0+BqjrC%|uV=V^TP6M7`UvqSe8}!`oNsO8U&2`_k57vWfhK`w<|Ao=h<`H3
z`?)V}&o!N<^14L^1Oom966nt1#T&@2c;|oY*JcCOr%pseE_Mj@pmbj8PWL!TYaG?M
z2xn~0?**n_n9xCwiNs~n=oG=IxT^dH!!vi0kaJ^;aZC1qD7*$S-=JOt9D119l;OW-
zf^;eq&`Nz<SjGC>a*sbI(bn6-#(~MI?<<gk?gzyl7na1r_AOEeS>co1mU04}quLz|
z!_7Hcg{c#hI@9S0^~H8L+%tdODlQO*J1#fCz}DZS1I%TIa?05mw1-m~8@okac@<)y
zZwWQOQq4L&5FCqLUxYoYnai-bdp3~*W#7T98(YDZIJP1PZ%~@PLOJaO0k<2maeWYK
zknXb<@e2U?+|+l>%v&Q|tdU7`9VUOWkpV~6-o>z5BWpuwASdZEzL5n$MYfop#U(e}
zT#;G>A3S4x$U*->cdyayBK!eVAzy&tbIAhelqoGPIWH#Jp(X4C^U`viynRLhdoi>3
zMxI0;tof5J(|fy+bdiekE|ptKgT@KizMfL_MK;XBaVMCv$=rDI3(0CJOxrHD%FgUa
z7tz5P_1A@T-w~gZ@Q3&Zq2t2}zhKtIQ+eZ}9)DTMH{CGRU^Gm1=ZQ5^X_)YGM)(xV
z_L0o4UBp$7QVKz!o3Tx=gcg#`1_S?RSguoBAs0NAxFqkeYWcD48*)uocaJ3RFb6se
zNL*><3JRdVuPDg&v=2BUIK##SLeKLBlA2Js9@|+y+Zl}+sQw%I?D;Xx$x0ZF-S5t6
zm5W{xa~h*68MS;w;etPwsolaE>|#sPicY-f)z?ZvH&;bz{NFccN_QNjgd3B_;B{f`
z`GiT$AwU^bNHn#%WUM{FTad+`6<S}%7-qY;0oEp9!^RKqKbh0a@=?`Cc_G{zp9FDh
zbP4%-Xq#ULjCJgpqZN<OnwL2_0Q`(m@zcKVEZ`&f_nw=~tmo+*8-<CcI_t58w^wY~
zs3Il;wa(Mil^=E_Q4M+Vt)CxT&R%SfI?|mMeZcOIVBl|cn!76E2)h!2voK#GwHQpy
z1FU9U#<eg7Rp7h2IE-BWcqQPF43j3kgYz*Sju5OD%Pl-hyNxNHU14^+FNRulV*D*(
z=8t`uvlo@nlQcO2+*siK!u~=9F<;|h;#xk&i*KtZ$trC`p}T_0mmSaC`B|jgNgf1?
zfY&K&31;Lj633+kt#JAKTgnw{QMe?>(O^>@g@neDA3#=amJSf=?cIMAziKuW+MVH_
zb>u%3t1&&CH<lRQ#}_|-Gpj_KhIlkDMxUY*SAdBw;&!D5YHt$<!#){!lM6g1tu`b+
zzh<M(S;!%_g<;|gcAvx~jbFwrsNrw*&7>Iohq8d;N?(mhH&G|X;vo>#!pphu?Y67%
zK)C&vv`G?(u|8QOBSz)3*Ik)-0O#{Zw}xE)gw{9k&h@9SgZ$>B7^IO=Z4@&w+Bhkr
z{sPuL3A>%)SO&qE+-$12?6*z;#k6%gblt>CRH&A>HUm_>P?(xWh$0revI95P_n3cs
z<C0UldJ;FEaHQ0{oo`NJ96DPSp!MltY!&kGF9N&jAF08JII5pxGO3>KokuXS#F0>*
zVjVVzi$*F4zVTMN%TX#jOxI=OvviTC(=2w(_gk(J-&dXT8fIWkZ2>khpnLx#coevU
z*%KOXcoI7OfjIWyfN!;=pJOIP7W|XtVnZf>)T!wW@`a$av5DH>^-I3|Xg!;xCc~DR
z@X};8`|Gc^x7f%1Npm{y1BEzcK74>Wr(#95UUbJ*z?{#wW{&5Zn`A#@8*921CDbY6
zb*joi3KZM_rsq87uGmvhISoEk_A)a=o7g>F{j_dOP=>S@h>Jw3yO1GwZ+%XIqMf{B
zx$KZypJ>-wn9giJ^xo(+(BRHN4V|fJnhcV;c<P%m*aRMa=hMsl0>7buJ!I6MkcTki
zwh9YqWj6NT=$`s^t3xG4J3d?Gx-cwqDCcvG>(F4;py;xxUmTt>a?&ZF=t}fk#P<`I
zAY5s_M}#|nJq|MzQGKZUf|~nFPAsi@246;J!PR40y>a1MATj2}&2|BV>hFHflNT57
z9aOuuK1WS#f0Jv=DR33cJz1$dDpVQIktU#@m2)XFeQ82x+jTIt9Vc*n_K|uAtF%Ut
z{@VGPv9O?x!fLqDIcYs6_;W-l73Dh$0e-CDwQ25>qoTlgktuq&scCUbey1T=Z<)*|
z+Z>aGHxEghWl}3k+B`}K_G5k$l&N+~gfpC(31`ajv>v+f-6ZKI35+N7Z7fXtC|2U1
zGn6j19<Xz%aK|xvAmvRgAwD!WGt&3*ULLGrEV{(_`}!*W>TlJ9i2j`EzO{|#<QQ<g
zKnSY`u(_Lm9;B^0E8|>m31$+4g!4be<h_}1vI2?qaS|P+g~}L*B)Hb+b;EtW;(peK
z5nIz0F@^IJFqRaS#@BrCKNw-#mvCdlFjRx*a&{l7;M(*%GTL=_yOBYKgMoq2U^a=1
z+>>uRQ>cZE`{zygr;94t%izB9sz}S%VE@e<l<LB>)}3$GN48`t?V2F9OdopG2rD|>
zBdp%Ne=4R86Kcc8#K(6<q+J+U*w??)fA{De4*y1<Hr2u0|0k5@dH^6(Hpa#43cN|r
zpYexu9$DXtp2PAHFy1rr;1OWCe_Ib>Aq)CdQnB&2P`<`$%u&CjcB1PLdR0=$@I*#4
zmE;#TKV6T{EmUNUF<ok0_)x2JtDs}mcz*Tg&)bvj#1-2Z@l(wSyQn_e?IJcuBhVFr
z^1`=bTpysi!>WjwI`>+WVmm2>*dvXu8EAv~iGP+RLju-rtWw|Gzwr<PJXqXj4I?6=
z%udWVgyT|gfzFWI*z^l*^1%{;the5pO{%t$x<OUmnr$Sgio6Z(*TgK}8N10>(JF`2
zL2vCyYI0tFh-FY?q}>dit0{W*qf`KP5sKMxc!w^10!B<_#As4Lyl2^#Ym`5d71%rb
znZjQ8h5lS+EX#uU#hU_OKz`2He2Uo4&Ill^t95Th$VlouD7s_&zRAzZM*_qI5SsxE
zK|Z_+)qC!i!5;n~p&69=ARx-~2lC54KznZmt;J@CX)`>yBTFHr$aDGZ;~g9yeNL}?
zuTece|I%70!nnH5Fh_SYX{G{`fd2?m#}d@<WbG%>gfhdi9HXCBITBXRbb*1V9)sX*
z<2VyeYe0C3SE=1PHQkrfko`7_tXbnm2x4QsW{H=)52okZ+1>^^>&FdavjmKBiu40Z
z7pt0)fBYRy*OE2G?YqhB-HCdZ`L7ZuD}LMsuc?u=43=USNZ@8siwFQBu^IPUJiMVX
zNJdNHq!+H!;<J>!X;xeRZ^JJM1;;pqf_M91dBmDYP<PItu{@A>LxV?A_f3iof3Zwq
zD%u$n{EY3Te~K*KCX(NR#wpd`LK{=3C<hfFmd3H<jX3T?QeXB1f^b#<Z@}C(xXSpU
zqexj^6{~IJgk6!@q?jZcd8P2NDEugzNrM08aiXurdK3?9#DN0HT;lS3R%Bu*{IRY1
z6Xf6J=fIBqL5~UjW)p8ay*dz7f*0=EA~>Mb!5QL+&h4&$0;>c{553%^#!2h*e)N>m
zpXmBecEo{1FHY*&ok(7RAA|H!rq4P|>;&hY_OkgFJA;hRjxJbzjaR{v>LKH<TsrHS
z!kdvdI~kx7ppXa)Wi}zaO;R(b9`z;d3Hs{m>pct-*(Bba%9E{OcG&>{8;iX@VUW^b
z68|uC;VsP~$&@~7!gGp&6yv7sS;2u0V_RfRqer0>bGr_0JGr9U-<IHP1HmMYl}Y8E
z!Tu(QlOjJ_30~d@x5-?x+u)`PLBIgW4CH+^18d&J-qg9p`kb0#(ppLWbjVS&LQFFs
z_d0tC^8!1ScIGGBN9T_mNUg?_5<Z~W&;slp-mRDI6Vr;cAnETyV~6St-~`^n1<)pO
zNpaue^o|vYsdI_`#vVHUbUES(SGMwJL&b}M2f6nI8Hx6dZMsVMzYpWy3DWXl?ZipG
zf1B*b3}2OXhak4)7KL*b4#+48oCI<1dD;P3kma7!2SyAIOFEVR)2=v_ic~&fmJP>g
zIl6vXQLjHq!soY#nIO7$aSNC7v4-HgsyN5rUE!ntI%H8oW(vU%o;J-2kr3}acH4TT
z>7ojpjKfAb)}8XVlLAa4{w_MpOg$Q7q@6OY+{9iL?*)<?F{6fZhe<IV0hXe2AckwC
zI`9{j2XV2kGFjsSrDzTG2bVY!HJg8>1zF28-63k}>IT4Y5U=Eh@6xu**?E$@$BsBS
zhM7g;h7d6lwMwOTVZ(vhu~!-%?%hjM;KkO(z&UrftVaU{X4a;zU~h~hkFe{@sxQ@k
zKhpehdpS=$jTUTDKV$dmh_;?FCV!>?4%8ja9Xn9T{Sb{|A))WTy)irAWm-y<!d}Ah
z0*V-`j54KO>)uV;Or3DzRJQI9C+|#0F-;b|6HfW_?J>A#l7s+R8nk|sV#KC4%K$ve
za>t#*RF{;^exi|QBOp)w^<^IM7Y!^ELP=N2{1=r@?a~!|*Olp!w^PSxg@)I8Ufr+~
zA$uO;aG?qste4-`ZnAW~!4-f}xbFePa};B+$EyP}pHtdUg+*T~jiSFH+z#XlAMF}>
zexwgfBhiYHdzFf}(u6&y&veJ)a;N<xZ)y^d!YC3+VEvE{p$Mmnqj=J72RHO%->LJE
zs}FI-m*pQ$Jng|V;4S49vM^M-+aBi}QD~KIY0w=67@T=RM4uJswkv3q<jac7By<Y;
zOu7B9`6Tk2ue1G5EVt`lA)Kd7kOY_tG-Ew$l3M^E0@gYKLwkGoq92f5_5^MuYjp=G
zxXRYxb>3>JsQj+u##|YpTJ~_oF*U1l7@?i~mJ2M-A_Ff%D0~w@Z&WaI0Uy~CANka6
zmbLPC`51VFws6cpyj?m!j^gF(8%C~SE#&1;cp_^ID9XO6e06V*#J}uSP4N?Nxl`zd
zaLJBgIL9bsKY52&SwB?TJA3(sKKA#_-X>So0V}!?>=do0c$cVar>-kuxB$}Oj4v)_
zHp4DO5qeA=iBMA#2rw@ZeH#?W56nRQvo7eAwvn6%_{SHvdUs49nEc6*8Fo|W;WPp!
z;YB(0gDB!gT_z5fJFIy83WrI^5ar^YUbyE_Ig-maS@1j`@Ytw!`3-Q|;t66(s_HED
z%?rowf06iXQ0{#)x8N?6VVnFKbh2G08gpLrqiSq2m=7QI^pq9>v$y7rB0;G^h#mae
z%?d#pS7L~QH!HmG@9h!6HSw2$K?=-u&<bYwMI*N8%b>6dhqnlBhP*3hrOAvAftmqU
zeEh@HX`J*lq4*D9-kb)imD}~dnHuAj#1MR{8bri?WYMM+-{ay%s~^JIO_~`{3f<bx
z6IJux>A^SKKrbz`yFUX=xKU0*EB}K1O<BS);G~R;HvdKswU_6r0$})cZRaK6b>bEa
zk-vE-qg+6|>k`LJmcOo2pQufEI37awNl|FwnqLmgKGj$F_w^<bdRlJd_EKA)9J>)K
z-<;C^rS}0glE&URrgwb}Q*ox8?>(ZLO`<K99(nh;b}U->^&DB#RKdUgD`hoeE4=xL
zGFWKmq=)a-&L=By+e`_O0A&h3;g0l(L7<IslE&^*AXP>c=4VCrYoOG@iqpaNlM;Pe
zh^Z7@bftK4(%UF7G&Y;D6Mxjc|3?%0I`{kVY<}O9HR3%S+K`R_ahHTpl)d$C;+r5n
z9m6u>`ksI$kWGi(2HZGEb3sWO^MW8x^Oj$>E84DKT^2mur@_r`xNjtO7CfeX!2!^4
zbT?~c>alWXqM8Yl5Y&BKCWZ(Vkk1=U%fa#?b?$d(zrX%ff@Kn_JDJ(3U%DpNed`m|
zrsd`7EtIh%h8W9CSkOI}H@)!<!lW|Qizs<4M4T)S&`@#sw3N`a!|gbdOEpUh>EhWT
zLt_0~rpS|#gM|5XW#Al>CB@>7#+;i;9R8CI34V~aPll|sa!fsT*z;FS2>8mlrcZUp
zGKm8k7R(0tISz~g7kEIjA=OlUvcPk#`(p~~Y0rEqRZVzC8B>@lQ}(*aF25!t<?F?a
zt*&$O9z)uh<o4q(MqrQ*tqf#z>ww=iD5I^Gh*oU_vPH4971pC3BSt>;1B4g|TKPaQ
z*!NP^4JDnX6>f>vvtG~qfEY>62E4esPzh5Xq_VYnueSw#B!D)ELTAGzzo-V*=u}0N
z|L(iikbJ5QC7!#fkx4IPExLPl!lC@ZB>*_X&6&XJ2JF!%ml@(*a=?qA`n+JjAMtNw
zO)FwU$_E5D=~eA_je@y57~JxzYF+6;E!0_&trAVcN#FM4v|RZYd*=I??{*oVCn>X%
zne2Zoz!_A=@Nt1_?UdLCLQ%$`-w<*$i*H}Ry-3(es%aDV1FWU(R*FWr?#^K7Nr?#3
z0@IU2tglJF;<8{7hbYpKL-CyK8~}cWE+Q|>`W!LkkSp@Bdb`-MBPt+j+1;imBZ;}9
zHsOv_XuZ-tL9YM(pI6+aqQ<tHejhM)L5oE%mTzlU&V#q;3}))CsELDFKPB2rOvRsJ
zpP$BiRg@XNSYxIj%(%=*AL8sU0C`v)8(Ii%^EUp?dRq=giNc*6A<oEkEb6<@fW7IZ
zEHk}zHf2cK@IptBL5ff9c%HG?aEkTPr~0ud9=*C~>7XNf!vIZ(zPbE6{SX>+n;E8i
z<6#vf^goau?vO4!p@tz;bzX)$UgGuKWsYx!hIjAtz?sAY-RkNNV)o|fzeimU&nuI;
z*^@+-jnuVb&CaZC1_64qd5?A>DEh?z38&c?h4}-i*~hW<jQEQqmiDyIZU^)i{j~Xq
zEc8mGG+!#yTsd9z8l?0IaMQnDeGeOrSNzlzaS<0Vd3eKL+W%((Xh@C+#r59-zI79J
zm>bE4UvXyd)2iiokBjZnwRenUQ&%MCageTBPNgs}DVsws{#|ur8SYl1`~09lyZDW^
zygRb0sqNUPDnL1P+9x$WdAgcxH?&rk4W1k*A&GGzIZ?VOU}SG+zl#Yx)7W@=PnsSr
zS;VBxCASt0x~^2d5oSSAAgmwo0S<xAMdRpAA@g9ioAHMeXrV&zq~8Ub@JA`mkdalH
zb`M>}y1=Gw&#}U#Ne1(G^v5@#`UpG7pI6~Prg^`$Hg80p4ph9QJfw8BQ8|D~y*^Z{
zb97?_TJS(5vpWewK2M$F>ph<^lQeiG9Op%M>KpLcD$T`<61>lpaE{d~CHzTQ#&+x%
zAa*@k&X%!DgUUL<p6oI8N;Thc2HawrpA7W)uodu0V66{5={a(i)Qw%=C%d!38@Fod
zthawiIK<N5$mz4%@~(>Sp%;6MtY@ekd^SH$vt<NZ9)1~;EPF0I;@Hmq$?iW8E>bq)
z1Q6v_F3$(;aXkm~?aI0a?r=CK&#N}rP?a7BSL{2(-|uho9ZZrt{pGUf3oIn$i){A<
z+ZeC6Q|EW*u9HYwDoy82pJokc7Tfz9n%1scB_90@nT!o&2s*GsYhTmy;dsB%G&K<N
z%<M!&-3t-D+JP=-dFKB1C~!H5+syqC$l2i>Rdl3CVv4Bn=vHq1wD5H6qJ&DhMXPUh
zDB~rS1c{_FK_VMD%wYnKwgLxN`kk8;ZoVm~S@|i$IAwT}w<u&toOk<H*?cXQvA%Pm
zRXgrb4w(DgXwgI~dcAZl4r(dl4R@*ekyHlx{2!=7wOgXOK@y+h3oGB{j?m@Qdbs9|
zpasb~O(jHa{J6qdbU-iB8~Z^kXp#ae$=_naG7)f-nQ*K$fo@S+ozdmw?j=n%hx!={
zc<-IM^%Z8KzCVm|`cqQ!;4ivLlLOnD$=<`a^tYdT>_x97jL4LQ#)5yA;;FB*is8pi
zHe^g03mxR-n-LYW0F&iR=tib>mJL*)e6F4C#lj!CBNF2};I_wt8GYk?dZiy~1n4;3
zy^^V)L3wgXNPgzhwf^(y*9Y&L22G}LYptt47>P+N*h$(O+<<8J&j87-Mfq>vf1ua(
zsCC;|rd7UwO;<r@DvZZFDo!TKmfPwU;2?dBRym@(H$*H|{|9>9Dkb^}#HtYpxQ;Gc
zt_wL%b3S5k82#QRgH`a~se5B#{*t&)7h%FJ@P~U~?qUVB&$ICav1Q|+Xq772!D!Gq
zkGc%UuX}R2dsGGNz)XnIl*wtTbKc)7^!qzJ3tQ}`_fNQIwZUE~yHgWYt2OI++f6dR
z3$Wt)0?#yW8I$vl6~VL?fMl_lku)|Md~;Yl`m5vvRD#ssU1C<*Vq!{kglVMz<qLek
z^@R8R0ylBg)xkJF>-e=qKyHqcgC2WRda&k|hnY$sg#fKG#to_ZN=O0csz>f3cg-EP
zumFAe3b1N<6o}sH=<Hv{een<5H#1lideXfeDt;WJ*ExZ|P=SY3=-MK>FAI&0yrZh%
zTeVk!-n{9$ajI--Fr$^)`UyCbO(tGr&?va1ovFUK2uz<Xy^?M>Er&=iwQ0cyd!_Yf
z<t}pUFJzfKuO~y%t-ory$hGEgS_8eCP>#R$BVnA|+9l{u;c3`YJ304K&1!iy7xFpm
zP#Pqx)wY?wbZ!qXYY8!t1`jW|UISXLSIeG7z4|X@4CesZ8A?8X$gaS_0QEP(Cb*S2
z^Lg%ayF1AsaM9|AzF0PK+Ss=N4h4SS@3GYwIh)4rKL6Eh&iV9i(&g`6t`*7q3+Ex_
z_SO3&`Vf2skAYGwsR-qY+>sLbHp)b71D6r#ax`FKKi#D;g8`tElF-?mfX5i?&(I!T
zw=342#&vC(&cG-Cfr{A!?d)+r!-y1h34F(<ic7V8_0LJtICq-MoHiU1!`qWrx~ANH
zTi5YO1!3<&xd)HNB92;?lC~3l?RPKc4`Tq%f{XdlpR}vOrf4tTb!F7P#=%RC4u&+W
z&QAbJMA{V+uUSm-4jrq_<*^05tmzf@!l<K{pAw^u9}e|*k1Y3cp&e@gdp{n+2w^%U
zpx6blB4uhyaIeiG!1E(~Lf^Xy`pf~RlIuySC>^@|XZarNY?j~%*bOq$=+!o}r?6_J
zxF2B)IFJ2O>!1#XFp|s)j|FxbI&K?1xOtdkW}m+~B6brGI7cCWc<q|LaV*hVo*ZU)
zUdQ@8sGiyz;}BHEr&;%i5w*8TVP6$3&LIx=wI4X$gahtNI=Der2zpk8b!sjU8NA2m
zS40=6a_u6BT`gUV4XoQRh=%E1SLmWpcP_H%OAhoh%|NPAG(VsN0{0U4{JhN)CJ037
z*r9(ii+0wY_h1FoW3Rw4u>322L{)`H(d#L}ACcMZ8Bx2&bs~6wn-LWt&tvO+`u{*>
z%lo~2Mo86pR#Ln|@k+0D!D6xZRAR?(f+(i=zb%*)YN&%eJ5euQ^Re`o6h%&S-Btsr
z>&Wm|Q9AXM3}dQxCtmCQBh)vcy&z|mzyb~xp04wO9QzDqwV>TbiOce|J2sCeTW{p*
zuJ&|K8s??Om}Y5m6gm%`goy)s@aEoSTqajV1dbpZOJM}9BpC{09XLX0n>fGUnl;<O
zLXh?6aDP^}`$GV9>Ii7GzwI9Z@6YC?y3h1LvMJG<WoIG~5Vi4{xmnkxauP_d`PNLW
z1h_KY(Vv*Ek5q0ZVML1@&&_9oSs)Y&f6D~|-Sjq5ud{H%@0-gI-QV(UM!NvbjrZq#
z-x9y&@d!2-$<x;Ja1@$WYvcPN&HhX|5hMI|wLmR{=lfry#n7b2;5Yacd+wFmlrnRL
zjdi6V!|MIFVig0{4I!`bV=$a=4Xc^|^|!wavy|>R27Pdwvnm@Y-Lo$WP|cfB1juBL
zSJuOy#P+rP{H-AsuJ?Uu<sS0-Q>oU&a_98#yi6|knIE3pBZq0hnmmH%h2fJ=nOHe@
zairh4@91?b*Q<X~qBeH0_Yc8y>|wg{H_+MHU8DDt-JxMkauKraVjJ97Ber<Ir-m&w
zDe~F+L7KBLl_P#7UTe%=<~z7Sp6suIULpGo12#_%23esaZu&0T(BQV6!Q*5iM*aL9
z#*afHlD|B6j3+m)WB<scUZJGJtbepA`9E~;8+wO7mc8UEPb+U(yoUQWf+J@^-E(N;
zm(*s&vq0J6#oih2kTV-hw=6w+(u)y4I!Zc=Hr00aIC$bIa!DWV+c8ekjJ|k~E5jca
zI0xGUNQ?pC0K-oYaMYy0o;fd|;`^ZnB(Wy~)ty^vE|iT+*8)!uWl2ehS6f3GWa3A}
z19*Lv?rO~KbvE`xyS`|E7s!EXZFJlkMIH>fW1})@@nl=bmg1Fk8m>X<W%e3G-Wvsd
z3fU<8CiOb)f`gp6_xxlycxME7Zz;@o#yuW@JX!591WDKRzG=NLoTo!jA7JJFw)P8n
z6?`V+F-yL_o>n)!?2s+7QV7{<4bq(`+f$Hnh+jI-{Uf2Z9xFqjcIOX=MwaV@+W=CW
z=PWO#C`j{WBXEQW;(tewZcx*&3PNgxTl~sOhWyg5jJKfLrjtEzNOoA9W<p)OFpe`d
z`_`3V5vaf?$zOm(cWL02S!K5deJgb*hslk&F)tH8oPBt!9p37a;(2#@EIT^ybY3r|
z7|HO9^AVhsLLr>Qe<Qs9)}v<Z3=kG<Mp*v?l>~S**pe+qd(PE@y|e})`SM@Xu!2V=
zXg3iP+g!4Z;vBaP%;U${mON8|I3Q1i;Uw1W1nz!9Dg#7yiSJ}*-*j%=1%EJ<qlqT(
zo~$gl`ILVZ^iJ{z4N4?ST*IDIO5LR`Os3tlTx)$XYW8KY+jxUX_2m2I=u@3VwhVn5
zw>$YKhtFxmX>^)mtkGFvuM(TFvks-XwO2+}aM_~)&B0hAKnkCgIFP@q#9Dk_>fJ5@
zb;}qw{YEY$cT$8t;O}<j*56lp`$aW(r&C(yYlf8QlMY%R@q1#v7XZbSGYy8mV!qV@
zVBakt2ZM|E+^6%XA}n1^O~uAa3LwObuLUn7nK48U1ekgZ)WkyEj_ithsJ6Uw-{2Jq
z7Yk)t_}V<rS7)4tjy03G^%};RAC4%^@bAai&G0UY`St~t{gjZ75M#g9!hE;sv(`z7
zjEgbA&Ir`LyJ&d_St6gA@&cua%EK;kyi`6Gme2u)%BcEOrmmHp3M!g@Or5sNFZWHx
zE}iyed64k%e;_pjQ;lzBr`P7uBd=#^ZEv&9*MRqQCZ+~DB2;#$vS~K(XxTMzkl8?=
zS7_pDGbV9Q!j*oAQt}-hCkE!Ow3>J?v;{xHUkI2C9HW?kks`H7+SBpqAKRf`rT+(#
zHU!R$w%D-yp&zwUg&dd#^MlXT;OQ6dF=aV2?A3?Ox8Y*Nkx>WzOZse>ZZ$>O31<mE
zAXrG@1hd}9#$>7wyL(3YSAtZ+lQj{YE&=LcQU&EpiF$gp4c*x(MHEW<VKcPp9&Z?a
z{c^43woAl<Vh{gPP9xot^Qb>!^Sz83le~6OxM}F^md-4<79efOyAw;LGG33c`F=S`
z3RCazc=5n(y|yS5HblXSc9#(~wZ^P8DDTfY<~-E)8^F$pzxXB3Ty8HD<<1#Wo6XR;
z;K5yU16U<ZUdcHJhFd}$_j)_@5VMveTzmfIEt1}_*X{T9SoNOV3b%{#{PiYMfh*Ew
zG?f?nY~QHGx)|(|<8_NAH+izi8h>={QYqC)>o67xT};+*Nt0sDk;QB;5LsXbKVUb5
z?@N7ar?aZkCZFJ$^*lDf{wV^)e=E`ZNo(K;^*UD!#$k_g<9q&)jacrad!6k+3Hk8e
z<>Axj6Dn%*;9ZX*=35l3f;qb@`@JCA&CubeY0BRgX@GPQzto09T4v#qqR_QUTloFS
z;VKRIXv%%x-><JPuBvqA#Yw@ye*K4YY5;yu-TYXjUViSB(^gQM!5AO!2<AFwX+Y^1
zSIqwT@!$HB^YO9v>W}>j)-fxwhh&OW1W9wQFIpdD4)j**Lap@{j^1!w1xn~=6|Q$Z
zd~V-<DZqEVt^0oCy8r?8sc*1+$~Q^hE>i%C|LT6P&AL*S!ot^ospk1wu!b+|58zy|
zl}=|Iz}V^kT}a6)1Z7e^7^8*$4|IWy>}ija1r|)r$$fU7<g7~tw!&o1mHf0vk3OJ$
zxNqWwAs80YR+ux<tg)yHbo~!5K0!(nHLL6yT1SXGJ@oyw%1<GWqW5iFk0NA(>hlab
zH>0NI?k_ya7La>BkA7a3w72QqQ%Bu+<`5h1)8_HND|PjITo19guN39#z~7alH&9)*
z>RPa3IE!&#o$HaYc_+9Mn<M_IWrhhXNqD|ck6zXNO~NLQ%-Cbng{LI3+mi(75|!Jv
z{BDf}zqf6+_b3&%5fdbpu=rG9^7+o~<y^0$Ooe4bjceNZgFGh(b@}?Gl1m0#?3eTQ
zj`K!YAaMq)JI>gGJ;KiYO|eVi(uEaR93IEgxRkmjqqr4bZkCp-pa#^_<GXYFW|C?K
z4_rhPvD8ww({q{5{xVM5P#55k%U0Bi26hCWsUGBl(Mr$zZ?>fObk@^NT#oTHH?044
zAqs(*YEh{(<pBMI#qdS|RALqahx}2<O**aFp92PZRPw^tH^mr0g)m}d>Dqz(o;vTP
zV%DRDYT_28@!a2COVq1`*VTl0>;EqHT?KS7$i9O|uZvKe{CoFjbyvBo=v7jF4z+_T
z2-%gVl?XsA3VE45E&wcG{YJ~2;in1)(YH*!Ab|f-q%rxOF29K>I3I^b%Bbi=2;mRO
zcL7=-%E7K{0Fl5!&Iw3P6EsQL<Krykp?|J**qDI84Iz(=DbHkTad9S+UE!%W#cc}k
zTKiQ0&JL>+v9aWQ34nv0s8QR-JBtq|Y0{)DEy}%L@67Sw_31~l9ZUx4`E}M9KqUZN
z>&sSIq;ShkhPA*mlo{;qdO+p=h>K;z#QMw2rF)9D%OB50wl;2@3U2ii4x=)jD1Cg8
z`0s>BJg(g*zw12?Slg9uNWtdD3k0_F&&aDPxdfkQltR3T#YSJy=nwTgSyJ@r(yL40
zg71lDtN2<Ib~ng9yH6n-Jt>z6UHC!VR&c7XhIJUD{{a7DS&<%E{ax$s?LCDiklLmp
zUvJnUtx5|AToZ&v0$BZKoilmRo(wg!kE;spU4^YjC0UrSQCAwNvp|-c(w#qFe_+=1
z73%qS=4-<Wf(;^m(6zFQS%W#BU_@J)D3euykBm9c&J3w=kV9R*ro#N;H^}TU{&cGB
zuGzrmo2lUz{QR9X6?xV6Lp=SNgyZFE?2h5>43~yJm#^gXs21?e#RuQo-*U3aovm?j
z&1k1;&G}E*t4s)muF6*pYjYnpcD6LmJMCu)tZlY|0r7e%E&I}dVs;PAIA>n(xWJav
zDovjxAY&C@F|vI6d&tJ*LtW_C!9MDpqxn<V=l;p<2ac;Z0EAi*CDCGPED-nM$y~mG
zSc>^qcZRy_$1)>THNUf79fi^B4sBGFdYjN+96<_{c;nashk(2D0l)G?J_lK>op9j9
zAqre2^HSO^!5G<S6HLT=_e_B5x*}Mb&;MVuNXPxrqCK@o7JWv61vQUwgj3;u%G?h5
z1-u~vX7?D+?f1_BC2s`lFtl{M^(c4qpmyM@C?}*o(BvLMN3;7rL&)ik=!kbW@)-;8
zy+6VoW5X-~uwuuI(F$1d@B_as39Szg`{g?vojV|70G3OM*WB9+A26cF1vQY)2-o%m
zCWhQ^5tZ%#rY<N$!SPkQUjiSB*X{SM0~F059>C9R8rY%vyLFm;x?P@gY(6ug?`2SZ
zU}sO*njEZ~+$bbRiihQPRxPNgLG+%CKlDCvJy4Xk;Bu90b6dJ-*_~5;Hj2db*3z~*
z*7}cY$hYS2aF&vhb=&V@**f<F;-wI~S(V2_0GTCtqoINkP{>%OBdM446aPZjw}>K>
zHM^!`&B%C`1{me<uY@X!{_Z?C!oO3{YlUAhggb40WGke5o`LOY6x__4qSa6;=(H5L
z|LuMV#pxIgoyzcq2fY0c1ZGMX3SLa<rWEYBW@xger`MtSWBfrqX>7WTtR6<1h4mTg
z-t*Y}K;4JA;U?MtuCIiJE`I%&D1DLnWr_94O0v?DESR>}iAuj~*`t0ZIkJM~<g&Dz
zyO>YrP&OXEe#i)3Q@mso5(x(mp<`l^)m`NZCo9EDBmR$$&uRcktN|q69sv2(3v&EH
zrKIyM;w6c(R>AHbA0?@DO-wH%S%=GYkOw*g40K)fudA5g&x1w2bt{+#G_EVj_43Zw
zN8R{=d`7IGI4#V-;QR+TlJ}%pI|AS)@w|76ZA8o`6;ALX3hERUXjzxc4{qSMQL*%I
zS#28kd{1~9{l2{pd^_Qdg9yw;r62ZhX{gI9VDq?Po%aC=B8<ZzqpeX$=f6S9S3QKd
zkQ{$dqn8<n&yXA5y0TaN3s*A@X{w6XQqMk=Vi9V#Sqqb%G(@J!v!{){o68}PH=F#D
z;1AC<pZqHGi79G3Et?9S2zpvnQuG5`L*Y7->5wl67YL$UQ9SKt`oq<V4prZ38u%Ya
zR~^<=--dw+LnK5xhk&GjbZ>;DbPFg5N{57WN=c3e0qHJ5r8@^A-5o=^b1<0SdA~oo
zF0R4O`Ni|x&mA~u{o34JhZbWYM9aByGg~Gt&|=G8=HkN|4jzLd(|vh_yyC`=&ejtE
z+^n(LDw*2)H^kH`+ri!a=9T<EEPprU=O2JYs_z_(fisnmko6w+J~*BHWJ~vk(@U3R
zi}O2Ue8|0n%)J7ZmNUf{#em<+S9Y;?rhl5wM9^f$IMOc~aL9m!A9W$o+Z0x~s=NSM
zug(y2rM9K#ce|;$4HYd)=gcYH$ePe_{vc>FymVJPC*wVwu~2Ic;h2&J1ZZ{tJa*<=
z`@Ps72Y#+R{DyWUE(8O8d{3>-)>7Ed-$<IpC@4dJI{V2&W5@wHjgLt#=%u}ubrA49
zWUB{c)hUfZo}#(N)_1HvANwf=u2gyP_-BMS+^(zv46WEI`x6N%|JEu*Hfk1lEg4-(
z_}dr|;5mE6ev~JDQ;hdAEt`qe;S1bctnkVHagcn>6+_@RJJByy3_t%iNr!>^wD^=w
z7>nbh6h4I-;3+)-uvlYrxKTi&vS#sK{R(?1{F3j2ITIN5kuIq&K6Y6y#d&I7A$r%~
zvWi<q{I#rhYfFyA;!^ySJWK{HHd;zUL34`Rzf{SgcRCUDc-PY}{OdX9l53Z$<oPUj
z!`S8oZ=1W)Fut6$*15XB&&^y=u%>hTxf(9*%iePq^GljMcNMx|ZVtdv>r>_(l0W>C
zdnSJGHezzj+uiihtMz&(TJ0l2O(>1*xp#+-pkBwXI@io(CvnVQmX*Dd=c1|f_bXhA
zZ)gdrVXc-I<m?eV3v!tE5qn;h@I!UmMduVIFzU0O>(c%i;On6hG0pj9HIT?;AXl(`
ze2!k1tb0Z~9P03u1>#fF3OHoNCe~c`6DcBlb;xR2!Q-W%JTpSu@p?tgQfbb?^+o(l
z*My|mV*9MP+1?3r=$gc*e!D3jkqRzK?`Nw!^cz7UCbE;B)?B@TURy=#>>Bz#xQG(f
zt-`TSSv4wIF{e$pIz(V&x8Xs^_P&hi4&cBbWON%!?@nEaW(yD8&OrhyaTbZ5&qTi+
zuQ!0fue$PQ=tLg82qZy<_c;`^M~|-JlFjc}YLHXPpOt7Q>~QYzX}q9lE7@@~E*WNi
zab1Q3jN@Il9RV4!LBb^+hZvd<l!v9)K<W0w{K4H`p~nOG3dQiN56mv*3(8-WgV>v-
zrUD(h{ep0&lS&il{Mx`2xLFgUY@)a^o)novvCV1Kxq`vJQY@#U>}<%?8MULKfiYJV
zwL>NSt8H0FX1aZ*>TmlDAHf<JY`aC4KC%0gj>Zz$d-TXpwh8V1v~4mPmm^W#eKzet
zM{v&gwW~ZyC0_&PW$9dH^WGA%;k!#m2i^u|`z1sk7)1yZ^k(#;N*^#Z^fpJvc^4&K
ztLQeh=Fjzi1Q^zi0Vkzz_Qd=6>m2nX@oykU?`Jxvh5UO1j#;v>)g_MNqCO4~i-St@
zH~8a9%2XhPowooxpVsoNo%P4_4{x&`3_J366p{5*<P=GvqWWYP1mjw@1W8$^=EI4)
z7%;|ev3m6)rtt2%(MWUBO_q&xKkY~EI)Mbn!SOYA8YZr$9|KG?G;8->T2n#f?A2Re
z<LjmmFs)4mo}@5oJdr={<0ns3oBA5p#dJ9+6!>oM`<)tzhH>@xD0!E9HMoN=r1uEc
z+5u#Rl%8O61&6F>g`Wp7w$t#`MKl4kd)5>r;g{pMLRw2y+~0r$;=tuxK!6@<cbO?}
z_AVPR3~T`ro&@i>scSwlbNaogff&0eVQ|*VtR(CRx53d~FZ0M*eF<ca6?B)tFTx;d
z`euhjYV}V<t^Q%T#;@8N(OD+=hq`0CdjaH??KSL+64B5}=V5Ws+_dbc>Y6R_CO~5Z
zFuq@Pyh$dxj8d{<2;{;7uv!A(%Jt^@a57xeze}BPs25|re?f9rN|~{xaozww*1|nq
z&wP5FZ8(b7>i|^o^NW%Em`iISm~kKyQA`~ox3e%*Gu#81<j{unEZFS5zojf80;@i{
zh7tUBCfVzYL>n#cHcm8z*FAj5;|W*WzO%)yx=$#KE0_2rmTTKAgRY>2)};U~SKTgF
z-8>XMikiwfi5#B(?hTExp~;`gko)-LIeN+=gDda>4TS;Zk++U>>So7e&c0!P5-p*}
z-3~U>)UQ&F0VE-!cp+8YX_(GtfqzlFSR@T!+~`JH-7u|Z%rteW?;+;tEF>07bzwQ&
z=%!pcf-PJ4n=pXV!PKU>*L|OvT_&Dlrd8W%CX+t_k2F~O9sUaQq+zaesj)fWe=WYW
z8MkQnZv9?FfLbwRPl0PE!?ngS0d!d$s_#s;yDneqT5?hh46O!lr20XP75}j2jV<_=
z8$i&h@ef7So^*cJLY*T}?$3-;Wzfb_0L>O4TxAttTtY%d>Qh&h75W`(G&IGx3SslI
zDn!mXy2GFsi0C3#-1?jIl`OzlRs4~Y*{%tmKc~2DE@&1Duqly~4f*7lBhwvEZQ0u}
z5?~^-eIFw46`{+5ks3r!)Q30ahxGNb`s#>&ao2zae3gD-8yq7gTS3xdv8u&^nVY3c
zsegw88C&<>GG8_xPgap^sMB90qcen9e@kSy-}4j>TxzRa<vdYIs-4z!Y@G%;32H*0
z#Li!rb4q<Ea>3NZWohB6V^}<}@U$_LI{1Dsjo?zC1H0KfHUny|T9r{3_-UzGzX)m0
zr2wP{Sb8%3_i4SRA)?5RTdjIpB&S(j7)zti$J4**)J7luA8zD1)Auw6=96@Ws67mi
ztyFHbzXJ+FX&{ePKYnx7WzTd9a`LSdOj+7-JZXYR1g2`*kFVI`DFfH3I{E{DsoW;o
zcAP{mB_);eOWz0^dF}b<dXrZBix)ygnxrYjFFH#;^09|Tiy*zW=K%A)DZp?tKIgi5
zhX3>%nw|;k)?ru()uD$0%dPCIu3P3a62a-0goW>(ITYe03|=zW1HeFNj<H)zy?<iD
z<)KS>Kp={MmX}gO_@pQU-p2Q~s7xu`VLsB9jiLS0P2O;3j{j38XhNjQpVy?N2fg}>
zQ_8hai&D6%Rn*c6W1Z0(7q%#zUt`>dsZ>JP4J9dLywy1jm&^zgvNq6iVr2?+M+%G5
z)NJu|LY@cy4AxRFnS1j<(9ywT1eW4<8=mP;2l*)!i%<(R9+9wWV{zF6cwBAjFC<VG
zv0OsiLnU<TJhI{;a8pBSDd|es^D}xtq=%Y-6YhDhcQSoi3hYmh>+LFX+%&OXB@fzF
zc1g#+>g;o6>29tpxqoj7%=CM@JpU{Wl47pu$H3+d5_0e4J2@oc;vyIwU@0#Duuj5F
z@wT>v!KI5jd?9R$@H%A2BN+zmX`xT1-U)!IvhcTOZV^PLn*m^wnIj!rMCZ60CWRB)
zsfBmGf2#%A=Lbf|Kw>Fe=_PviW=03a{20&a19Y+6sFl=qWH(cMGd1^7L|?OzV>}YB
zVPi&TD|TZbe?&e-wB{&E!04SG7jXIC<X$75DlHy<ea7X4Gl*>C2QOLphXJClM|eHX
zj|btOfRmSS+%PvV*Ajpco)+Muqfui56?ZbfxKqMTq#KJN5aTO2EcT5Vp^ZyUh8SX&
zLck^iC#MB3kibHqW8GZwBTMM^bXlU;Wo-hjDAGi|*v1B`7xFzI`Sa>aFs`G^lFKXE
zJ-2N{5?KPcW+OxDlPdxT4?r7tzl=?L<kmCJQP8xGGmjoSwjs!;!^%d!#~d$zzM*Cx
zqm9#~va9S>a##c1_q<`6{v`}KJ#~PF>ZTcuV^cSVoG?v}8D}+~LhF4@l)=qfehSr)
z7Q%?dp+5J~?>jbvS6@0LzMu+TYWQ8;ag14ueF}V>y8L&k^a>v3x@U}xdt&t;?0$|i
zILPK62kwMg(4?bc`-=&xqn|k_B3i;e?>iMfZu<S4-|2?E3IUd)Ql}X^bp6J5!J%oG
zoBzfYg|W3_qv}&ZosaFS6$8fRkDDvmaw=;F&+!k_s&qGi>L#4+8p|r*nG(SgR6ijY
z=t&;b^x=c6E*U*ANAukY8{%)}&RH`ql~QtDbNu;<XYN!-zVfYFOJd*oUQZj=TiVx@
zeU`YH^qZHJuUq-c)CGTe(ix6zV(W}<NUJXQ?=$C~W>l~6PJv&!pa7M=A4LG5##^r7
zD-pxEmvp-Qq}RZbA}}}&&zF$-dTj^CJXzKrScnhuH=3k~q*}j=5^tv2?<|31Bk7Km
zo#y)tpls8>8*XzIgis;Ik5V&8QGu5`IH(h5;s*6>6#3tiXU+HfY2q6{7R{z>|6xJ+
zF^?ty?-HJuVau+q#93~~Dq*o<Cp@|0XtneUU`!%=5V^Hsa9j6|$W7;K!?V?)Nh|_O
zy9~H^d%SPPJIf-*hm%-0(Ioy;{U_mx>2G2JX}8-KO9d*PEe&6Q?l{BuwU=`wHUsd2
zYA3&kUgWk`LtB9tg+CHk^5v&#jqeQ|2Fe?}KSZkhuEW)hXZ+&kry6mM4ed)+7Xrd@
z#^{3Z!6^RYVAH5YGm@_XQ!6F^ux3>qzJGvuAh!;)09L?4Kpdcx+a2M|pH<YqNnO04
z82H9~kR>Eaa-hO;Gk%}u;ev?-7D-SB);^)n3pCsjA#H2n&p@&ga#pQnOC{qsvnlEj
z_iJ<98B$ctzY;5lFmEvCs^`ZRyDG#?j05D4RGJG0`xG;h)rMDrgR!dZ^izg~O#axz
zOcIurHoJE&pdHSLw-d=(t@@*IBD0ua>e1#?nUj&c20Gmxjz^ghy*@fwM=|%Duyu|}
zH~6kmPxowIxEyDnvJ}5}jJRAt))-zU0P|2irH8*S7L7iXl;>M#u+Dk3RQ|X4(P7L~
z#ro?n5OMIV5H|m*f30&O4SZazknwrs;ukB>vWv{gPrlc20Fh~kli3rZ!!h;_XnNin
zGK25z*iPyHtnNYLP!voj6Nt{QnM+r|^D{4W5H;n$BF8q`pE&Wry?Uo1F+5p(ELgH@
zm^)GR?%C4uKP+GB3LT^Q-&ig*pj`5Bw=?^OkWEDavVn&)iElJ@;m0p^?=f`~izX%}
zwV%$WGusuY>P2S1qX+Ae#rPXR;$4+1*oi|i?m~f1W}t6_VTV!6Z|GhrATmn!6hN;g
z5O;NewMdyMA=@lpX5uN5f#9MPNQ;(bQegx$Su{T_*~N;tdXT*sM)a<Lqs!(W))S7#
zxQ}+X2{56A%`0tS2^7($tZxo9UEnm6{Im)BXaPl+t-OuV{9}ozwp}82spFo|;1!AS
zD0Ec3h`9lJrd8Oz-A=YTg9dg4==&c|^^q@NMqS^n=&(3jK4*N(?E&dw&gOQ9z(Vzg
z`z*INkEh&O9h^g8Vd8b_RFdg^H&)TX!(YGC{M;VRkymNIAh}G!P)r0m?nI9vZUFUa
z;de=_>qUV10bl&uXq)c2O&-SE#w&iY)%;qxjV~$Xj!Sq}=)MVm6V1a<t>XNt0oHb>
zz&BT|dh(O;ZmS`!*Td!PsfGV8qW9!UpsOw6c3;?{M?5XG%Of}7NKO;2*Z}GM*a$H9
ztrrjb6s431h=xE;*Ts|qhMH~f;7@CJmEC=3sL@i0Md6wiPK1f8e;A-3{Yos-6?`0p
z^@o;W7sRm#ey9D7@)Lu8K*g|q4w<T64y*OPmgtvan!aX8e^9NgkawG|bYmHrLZfc*
zPsZgv1dsru7GR{Ul$Yxjcan4IQhJs9Tv+JgYEZ!`y<X&cbkbQ~3<o{H$58$bn+HkT
z!q!<jOpk2t+ibA^%Tkb2u{q6os}8JkewOPXf4dg@>jT#~{M}Kz$hs=!7}np?zsJ(4
zBEmME8Xjc;Sxv*i=uP(h*Cf?;w&%hF7yTogh9*;9t8R#z{53~7K{iR2qNI!N_pmWu
zT7$0raKuHmC)xs)b9p4YLnO49=G)=T5(bLb+epp*WN^#sArE!2oFxh|9P2D6FH}FW
z&zj_Oaz;fOt*w9C>%BE7sH;~d-!9vgp%uIlh%HoTK<EFgc5g9>0o9R>f8-)LaFh*K
z-{6%9;(vWTa~qa<NY(^7IF}h3$~B7d8@`!B%KkuTqt<4KopV}O)!S@~oL`@2!Zifd
zh#JP8W7Ft4xC1O=X5o=Ji#zoXb#43DeTa@>HA>O00KKM1#~BZW4b{vxj9`qmifQ-|
z5A5UDuRa8h8#w0;3)!X}xcxP?Ty!b<*wmc*BJPJt$N{JE3<csipCWYO!_jhuGYnd8
zgX!yVz--9z$B-#>E<ZLY-SYC^l>?YSZd7BmTg4}sLZh%cR*#!<vh^yxhT9ktADK@t
z=P#-F(eA}Jsa#7dFJYvnqd=eDL@xurBQDg$w|^Ef#JIAy75oi9M}0ZOm(Cx*2>mvt
z<!_68TxV1_Bhd_4IseWJP_q%eHhgAoc5Ty02hy5IUi<y<HY)I{I39f4i)j1sJ<NHE
zVMU+g<Qq~%qqBXg8ZTk`B3E$hJ7anwW@#cAk)fHps236HESMuKbI~X5$L`9Ho;%;;
zXf&!9UgltYH~<W?$q}=^uBF0nv4PFr4H4fQrlvmP07_Glx3Gzbb%ik_pZ#0EK+#0R
z9+%RobY{?lXC1_xk?ZW*A!3&M*~zEt!c0F+&3&b@lz_vKA)k>aXEJP9S;`=qktJyD
zmcR_9@Hme5%bmj0ldRXkwn`M7-2y_bfv84BXVi59T-DyICVZj(2jxB2{7EHC(nk$n
zs{}uOhnPS=?@OntUVTQ6ZxMICF0!X;JFbq&*n8d;Jw2&&TUv%=I^QE4di<~08E$oO
zqP@y@sts_jhb-bz+2=H8fW=>V>jLgqq&S0*mJl72L>-6&LT+aLWs2}hsAuEVl{pUH
zt-;r^O7hKGSS(1j*3>c0$)5wKF1y0*c~sH>HaioKooUrw!qG1lmSckI41-Mi%s+oj
zKMMF56dG!Ewis+WUI<m=ablKY+pPvJfFY-f(<STM2>8(jMWgd!W_UCGRq5Nk-n(KQ
z*{eb@M5L`;i6yotE~tvX?of^Gm>-<i_vt%ja)5Ox#Djdv2Hi2;PecVu(j>K04fN*q
zkJsItJ!S>j1KwJt?J*r)6vEZN^c@_(&})Ab=R0&%i@7;cs@Vvix-{4os)VLjmmRqS
z4tS*55ndF8Nw%_085E3RVFnxGg{{-XqNeJTKQ<@ohHpA;t6>1hv2XZ_GOzF{>yk+h
z>T#Kg(Ii*}fXv%dqp=4mr$lmAfvQieXx<OFIm96cwbhmOKEUuhbu6b>&-uIUpGBPw
zvWs^Jz-jBf$!f^C@YwNn*{XFL05-zm)q6XdkwSGKQT{PM?IHk?cq?{MjED8J%@uDR
zD6fNcVkJ&4UyA{jz7+L-y2X|_Z<9$Vc6*A?B;z?i4|WYTQ(lUV2G|DHT!IprV80to
z`V6@4DA{Mh0Qm$hAi)ompjvn@#`)&_Y7UV_Vm3ZsiOwGLcd^bSoQBnm4za%-QkHt>
zoO9`#C|ybe&>6gr&k27Lh97HcJ~9*Z>k81GEvwi^a`ekY$@hB$+C;URXO5e9oY;my
z(sp9NUeaX|u=F)fu&?p(xSUaH^BsTZ%L@7hac|z;5lOzV)a_1VK^5@Cado3K)`HKO
zt|*L9{Rd>27_jt0#tLtX`2C1~kG4549RIh5=Vx#m$4SU_y34L!$2wQDWl$6r!1>R2
zrZB6$(ScQQW0$v6Bq-haulv9FZ^ON+-tF3MvxHOFF=gS8__##LZp6wqEmI?lC`lWD
zIxar}s3EaPWH@`e6N1l834IL6P*Hc6iLjY`iKF}*Mt3_&i{Nj79mr$)EsKE9!Rz(_
zK*Iw^nvT!bJrF;i%x*G{+4l*_qDw|hMB_;0t@{e=Nc98UdOE<u(4RZm(M*ehH)8Eq
zbh+7ph7)8zShYt|(*McG_;uy{1-*WMI8KQm2lTSL>TuGM3b)Oz&-wMv<We`S$&Z-8
z2ywiWph;hDMX*53Jsy#Mrs~Avu|(2gl;TO>;=9C~FAReEd{WZ>4-_yH^MG9NA66_S
z&cI|PR=>$<kqI3+10LATG^Rl7wKA0e$+bUcp7mmmM1V$sg?EX$!-3AsC^`~uIvtzg
z#lq2a&|bHFXe%k!GZeShG^|38OP(s=*WM&_zye@W@&?<#5deWBzb{}X(s1hB)Or3-
z`VB)%@Jvc&<meH7HcDRMGs2!>CX?3XFR<}uJ8GP7Y#%?`U1(gbeL{6j(z48{9)l?Q
z6|wWnh`0f*IzVz+``&FP-fo7;dgP10x@+M4HC7-3VEe8LT~3w+-gt<c>E|jLWef)m
zoF{0${l+CS>ppGO2UvMB%?b$Z4;MHVh9c>!q=lm6@zH|tYdx!U2C6$&iNL!H9dHBS
z+oxbv5?iuL5qzKG?jsK`pA1j%?mRQf`Lq!~Jh>6=Sda+z111<hreWK8&>edUcl+*-
zT7<WgvvRHdeuc1+AYrq<llLx6;AwvC9IBUef8z{q3G$n9k$x@scVYndfv%N$i5w#&
z@?g841>;{bI;I00^hWD$e>>iO+ap0K@oI`A0Mk*sZImfV`S{0Y(C6_vsgxMAnXkZs
z{-K}$$_?%Tu(Ki;kJW-(qTB;0;*XX&V6j++P@X0ONK@xOtU$<reND^EE`a{62HxAX
zO0go7M91nm1J}vF&`WKO;rV)HA4c5%y3?=|+@Nc3VTMkZu29$0KkVqw@DsOzJdGAD
z_9|xK@cMkygpJENbF8wLn~kb^w~ls+!6QG-lZ`Fx08}H7s#Z$3hoD;pjuzK2p|Y6M
zu<B5oRGSjd(YPj@3?X~wd3@~K37U~WyVVvKSDA}PGVSe)z@`CXZYU-hX!{gZVBa1V
z&u68AfKnTG#Aw-$P}IK&6H2J#eSILCxS@8%+*~qw;1<I%YV7mcD2~o5;8*uHH+@yh
zr$1)`aWB-}B?7(@Z4lOD?<}_Hci9(yZn-OfAHOKWj2A0l%EqvdC*qI9P;VD)nXPtX
zj@imgy`1K$Hq&r5SB^7k7E)6AuYz+dwHXY0m|BN^`P39jW(|*|Gh4(<cCgltaMjd&
zR2o<vY3`rC$h&?E0`Ls_DNEByZCAe}H6{Kl8hk+Y@$@)|GynH`oK$4fk$ov}YNTnJ
zWpcu`RsFO-z|+7}hf)E_*dxUWuA9N&EkO5kVDiH&2*Yg>(dW^$P!#Qh3uGtgJ5i-C
zCCu>%v028_?kbT2Tu(tXm$|nVj26gaTg>8{KjL5gyHSxtDN_ZQ!@I7XC&K#Eqe5Ob
zWzzErt>=zrJ*K)WTkNaoeC3wi3B*$+fzIY@u5+=x-u`WV!H6m|>=soYOaV8Mk8f0r
z5icr0bZ0W8Ui<B>G9O*gk1=<nRMiNV95Ddfost@2^WdH<+AB?ak7;yTrBBE!#K3(t
z87xghgk{GU+6meBKsExNL^dUC&Yc9kj-G}ru$H@8HO$=1ylX*@Rukq|xHG{0brM96
zNaH?Qudp0Xhv*tTDzkTlC;Z(1`yP|r^J#-!>>=m%L-@9uwT=|Oxwj`UrGo+dU)`L{
zsK0?5c?qtg0y%PGWr>Jh9S*ivVOZ{vdpkJ^_<_2xe<|koB=%n_#_f!)jvsXq5UDik
zi|1}iSG?uR&yxL(#=siSg_0pIfHs4!rx<kZZBC+C?e8a929x}|d;oa%Ju*Ag+7t~;
zPm*CEAmXI*U;)+caT3jZ9pHJ$m}MyC$0-i$ghp$cJyZ?A5c_imw|?T`k);U@o+H$A
ztk_wvKaT9+>Nf+oz}w3u4-qK+;5FB|`?UpWLkbDPw)?gM+|dC|HOE|3ga+vErZ2DE
zgA+SNoSV5@ZAhpEVW6Kfv>5I#58%U`KObJdCm<HAPiQr<X+m$tO|#!IYXcXwsm%W+
zgT61ZguY&hmDq&+2C%rVi=<(n)#7|~AXMjPi$idq|I`iBpWPMNr{Xw!UjAAlNk!}`
z#Q$mX)8Bf34_r)?44f4k-bQzTgGF$kQ!Me2%~Dm4<wODS^rlFb!lk1DEmz<=OS}K#
zJEn$Z>@efHj`sBTM{t%ryD7|{A2Hu*%d<{YHY%Uh=RC%0;+Y+rIw#jtXis?f+7dkb
zN#ROeC74ZFMcN~4CK&y~ELB0vUtFkPWN1b%AUuelx9{-B-6Y%I2-R(Z!)F!7`8)0c
zw)q@35ogtJwEa-yB^+@GudM@1vhU%`k4?h@;&ryBm{Y_=GqMa2YSXgn9<^~M?l0J#
z&_0&dH0DJUBe*Q4SRH<jj<$g`+CJ<)6+g1i1rkTA{)}&40V!({>hiIB1h=R99xSBp
zv2uzFI({TqK+P-ZHS|kH6TLa}+v}%>2BjW*H7*~3UR$HmH$BL|GYO=1-v;l~+eyn$
zj)wDM-y?Yg>bzU+?MRkBN>AiL1%uC{z40#>Z1)73QN{*q%_OG((bUOYt_$UlNPwYh
zO6%LKgNBs$4!{v2u-jNgEacIV0uBT4X40wIEckcuI2dUoHKcm>TX1rd`rMqJ@__Fi
z-cFgFq`b-6pdPygxFh?zq`6Y!B&U*Om;H9y>qBnehJz0WDg#j}!gyi}VQu_CjrI_)
zs1dWPcY!X+>CVox{OINL2eJV(hSgLer0%&N?E7?4KfHMgaA582c~MJ42RcEu6GW7A
zq$z7?f^?giP-}BjPvPHfBR~FO^|2j)SQ~@Y{m%Nc<{?I12sUn34~K5#^nbhJ7N*a~
zFgN~<ejSiTtXW=KTo+eEGAvXSp`m$}OFZr9fVCxD#6QP}#W&HIRI=x^DwOsh`y*}g
z&TOS@yrd(8Kg?LhgXdWg6A3HCRQKf!b$6@M{=RAYxRb~lFQ6Q%k8m~OM1ttuizy|{
z4jG^<a0w<Q2R+Bic_-K|zss)a*^VfKNWY|;IxXAGI+<twMXt5deVsWK%tpsQR&L>M
zaHjy-=%jEgRmAG&BEywJD8!1DYRLu%ZGR;`as^Y!MP&~VM)--=$z;<%$;n2RB8oJD
zSJ6rrZp}WoQSz0bha}2TFieG5G77fN)1V!uq5+#Pqw6vF0`-Nz1DY*!TQoqP6)SP?
z{DSJDJL+P=?w1RWipD(YPm_FS4z}zwrDgjTH-Cr_IzGsJ;_W1PT_6|5-aD)CF#(Ce
zjgqZ?Q+pF{xm^Aa>&hUbZO(e8kTxK_!|RAK%OYir=4Ag#``@R*&PN%)en>^R_4_2+
z{Vq=Ys>jjZIhk^C>9`!YBBj$zqmq{fVQE0>{cUKBjr6Why%4WTYx(g2JLz`H3Nysi
z`Uv4_i#;NA{qA?=D3B?&k^Zd1?;t}baNc;&P=B)atn#@u_F$pJbUr<P5@WD(K|1jV
zU45$ov<kx@PTIjjOzgSJM`dUu#aKh6BRTTD^{%$cMyAy^|Mw!O_1yD!&~HA66B<72
zUy5Uy57V3m1$@J+I#4QAuL3KVFG?4CUGmm{qG<j87zoVv%(~Jiv)m(x)tV_bAWdDn
z!3K-Hry=8mw_4e3tnXRQQQ97qPt8b{Rbqd`XtmcPBQd0_!lHN22uU8YNr&53ZTQu%
zu87u>->=dA_nziK+;B7FY}iBfhBO@*SGk|o;WaZX7`Ri{S(>bvxUE-fi;nRpfGbud
zczFxCC^U*v^zh#g!@8)PJ;l9J+;&_wj=huh)9`Cs@+>)q%fI(>Aw_)^vCIQ@q=e@c
z&bOAW8@<hVC1K#fb<2A7I8E=~ug+v;3@_zy5cIWiF1(SK_eA4NK{ZAluFJxMO9Uys
zgT+ROC&0U=H&fq#r}Ab-XpzXOqaANpe`LMbbm)`cqOBbR92!DTy(#%8+2J!;Qo`jF
zgKfyEC%CFoX5R4~7V+@gEw4O3{W3?h3kRPNG92#w{k+J>C+&p<IrVXp?<c;8JEsI9
z&#9$06YVTF)U^&*9eT4jpg`4H_j$>98@3#iGm~-`4zv+ey+HrBfpOnyedZc{z7k)8
z4*AandKEm_osH2hhBkb+#7HlN0KDs+N6<}AM&g8a=ehy9sq?5f82CpF-7ZaABL)BT
zr&+a|Cmh!?v|+-0kK?4in(R}P`voO?z4EmjO;Dyrmj0J{LxrcK^pm!90scibM&Si?
z{2x}<STp>~&GLiM9fCEWnW2JoD-+WiTrF@Gbi33(El&BlRJ&11WYWui|Dm#6(($dm
z#spHQ2`-?(b!*+moIrgND)U~d<9gXBq{rehmN%Ae_S;IHwt3z2X6xx@eU*btJ@D_A
zgvj0OWK*kd<1fi6`o(oI0$Bp(+tp&#wrjJ>3(vS#GUGTY5xuPEVhHqspd4wf+xot(
zk+Tlk=kcWx%4v?6nH?PTz8o^YFt@opAh_sj5x?s*$<KW1cJRmc%OoSi51M5>><hoC
z-SuU$?=O%Tuu)`zy-D<=gqT3DF(Dq)MD;nf^Dqkq$*|$elcUre57s*u4NT|6s1Xt}
z(KNn(sNMXwT2mLJpz6n0ma=t;=XI=GN;j0hTkeGw*z9#z7Wm^=X}{n@ntdZscXN=b
ze;s&C7aq=s<A@Fj$d8qoN8_cE{JBE0hYd>}NWkuXz4{1lvmhaOE0A;1>3s;?2PKe)
zrZGtp**7%9kJ5eU)a?tBkq3<oXGGk*u|fKW_1TNz{1=sgAvv|*=qL7eTaz9p9Na;M
z(IHJO5nVL3IcsXLQZZ-0`cv>qJ=SFxMSMGHLgvR7t<Z~k_`U&Ew<KKj<?RDw^S6S#
zOnk%6i2~5%)q2}tyk`-hunpko>Sk(U|KqqVb>0W+ia$jU62#?*5OD{?u2NG&wi+YO
zO1^2T>Mu?7g4KRZJEP<ao*ItC16$M%7@p!MKfL}1FDAkvt#f1=JX=B}>~QKDPb6C&
zk|K-w)fu1E4Gt;$4_V(#MuZ;xM*fK>u_Et<p?%f2w{Mgn9`XAbHfwGd<Um5wch5oU
z_0#{Re?=KFeus-R#&|FG>uCVU<8z_eV<YnqY_}U}7*czp#+w^JQ<{vj)TADTojjkI
z;#FK>`e6Y6oyI<G6G&$4z`d!uss`wK+xUq+AG_Qi+2))??;=o(4DEKt!Gr-%gNx55
z7G$;?ATxDDi#L)plv3}5qrxF1bDiDFBQv{6h7YvM&`8iq@Ylrs{JGCpZlwn%MKYKd
z!NiOUFQLWtG(4Fh%ul4%4U#k_pNS{;B9_MRyieVANS3>)t;_rZRbx;!9P9^e;)8ZG
zv>x#Z7tzweeN6R}U~PNU#($QF8Im7UEB*1e;3zdV<o#nzO2tn_qU$Qb{b0HFxM;Y<
z9EpR)x1c^KU#7UpdsZJ9P<F(7{a9}jIj#0L`@U-evm1}&cd@<Ia(4fK<)6QpT@Ysj
zqDJMP!=AsWm*ll!<d_2RrBXG|2Nv}P*GdHZLSV+|3_9HjD(dWKqv}I5LHwD$3khb4
z6H=biWg)#1KhK!L^e!YxhE2eF6A`P;U;GWSKMm8!@-V;HQ6|Ulr=4jI_|QNnyLqsE
zGihc#OLuRoA+3+xMa_)QUVPZ0gTDlbH%bM;Sp(8gd6_>SrlsVTQaYufnwT~mbT8qO
z959cf50scUBirRXOXUH~IL-QKZ5;3mK@-tm2C3e%K2_|-miE|&6mcf?vL+IygX7CS
z+pFK{mXIZo7v2&E#&V(RyNIEqoQGKiLLhbw7x*7m_CCUL^}LAGD>xd*3N+<%uWk#W
ze612=^1IW6g&fGzF&F!l2D;A*G#0{%Z<vW7oY-DQkkc^$xCfvytf)ZZd%S<$NP_?f
zv}zQCebHI|u>R<$$vLm4myYdI8H4x%9ui(cSuJFjmmf0^`~VDb9%}J4&bPbtD;Hp%
z)JyX`1U0?8E3?6M$+vsnae6w6KHwyYsKX-OO`H44$klb~ut##sjJ=~wL58aLG)tw1
zNsYVnN4#tm*OV6Aqu$7BXK2@_$#^0?2k?=SO`oVLIbR;$?P^9jW1~}%b+lL^JxOPT
zKw-bCn4L|TT>Y{Zlfw3`dU@3}aEO$86PYzr=^5_Pe*&&4kP+nZ11zB!t-m(cK@m+2
zKAxo|O<t%c?|o>y+GndR*~Eq_@b;+0%RqUF-AW@f#(y$<!X1t?#SiMzGgb-_T#p#n
z-R^A>I@535&fi~=ch*R;(AM1F_mIf-PzVLkG=MB=@JGc1U|hqFO8QPeRCBK$4nJ+3
z7P;Rq*!yS$a`1XPj5S~h_eqcvxA3XVQNIjln_7_i%1d>h^$#nIZU1V3ZJVLp)vjHx
zX*`F-c3p;G4K2*IWAN^^(FcF({{*0;e~5ZO086^#{j>@8%l2({a_sR~5{<X@ySoc%
zXov;_3;dJ<P#9U;5%v6vz~Bz^T}dMu6X9h-LA#bUHCnG&nLPW%y3B!g`MIZcka5%Z
z1K$a^b2MRw_WJ&8%v}NFMv#OiDm5Qxm<l4R{ndSa^s965QcAVAl(d&oD!$&;Rv{xp
zv*sH0l?8q-(f7LDTtM(1ilNsbl2<poaU`XP1P-U=_5MlfZK;^4==B?xQ7+h;STSDN
z)UPQ5znv+FUKfz8qQP^v#D*`8YyCZ9Yx~K|+)I}4XJv*x3SZbZ-@8r3Qz|wTW9JCM
zEjXY|lMS2oN*1^>QbM^;CfTHIfu;}68gg&B7U&s;6_1MR3oxhO&ax<QCZ9hIb9EV)
zEd(kdV=&S$MEWeSzgUxCF&9hukN+y*_tOyNs4K1#%uoxYsyQ~F{~hT56%o#(XZh#3
z+gO5DN9glsjuVNREkIH=9H|T*y7J~fRtG+8hN+NR6<NFS3laJ&`KA`|a5a0h%i)ED
z#>R}{$(|<hcZRuO?q9C(CfVFC@_qMNhSH69LO1{i$%^%5>Ut48J9+Wx(>Fc!Q*Zrg
zD&!Eavu#}mbF}QO7)V|PeM?0_hcxUTkt2=<Kv|#ik&JucL|f+V>lG4f0~Nhzj#t9(
zkduE3mH&{SP4#UvmOtDBq~jP@F8c6<EN8ahvk74N`boqzs3D%oWk(e0Pp#X|IUrYS
zDkKzQdxv7bk+3CB<xAH2M$84JUQpPpj2|((o)`B?gMFssX7)%fZ93q_*(%kJ>(;K=
zi<46N#=S8)uj*6zvd3x}9vbH^@cgn_<jM5R71nSj`yJcx#HEXAk|dIS0jk7;?u~lz
z5<}Br`weN6pfW%#FwKQ>Jym`_?j-dDIDFpbL%AAZ9I+(RWlCT8Ub{ZvY7cc&$2Rx!
zaOv`DZz+SXN3y~8k)zdu`hYC&kKzL*hTnmgdm^WJ`Cf`l*pt86g?eq^1c5%Aq;sT7
zcgzWo!Rau9KbYldk;FGYG24(-H?9AgJGEZ;i>n*mTODABX)HdF8c}o$?o*ZGx1-Jx
zkUwm0LYCU=Jmz=Ly=BT5oq2!g-c!R$@XoCm-s7RFG|H!OIFr4?Fd4aYIN~-~?N~6A
z&altX^}w%3_{nQ~VsyPJ<Gl62T^JGebaixbeh?jKZX;~sSJgaJ`*PP5aRseJ9*s!H
z#NO({YCe@XgeRSP6oO41etmA_ehAL6jaG)7|EakY9s;W2UcaRnPYYY6uuF0L8w>Hh
zQQ%LBrKy@BLs-ziewf*u^8FbLN9gvsy+BFatEOf@27h4B=`Vzmwy~x(M(@|BbS`72
z$GiSvy>UKJfGjivUp}=KgHw~%HEW(K$`8-Y^%DMv6}1b{6RiJXO{)<_O34@W%;=)5
z0MN7TIp<;{`an3N{W0RMo!DQwjH>G^<n(6nY8VU9ql7kSNK1`KbC&dra6y&-#=`+B
z5xxG069<+^UbiDWl5+r`C8^OL&3StJ-<b~>;T3`~Z#E&OdVEM$X`XcWb$K_+M01o7
z`0u8fy>wMg|7K?Q?c)B1out!0;dueXdV2j<gzb&HEX}0dG2e=rQXuy=%t&@Ba?-^2
z<hAf#d9_<&z7M$_0pKvT*^7+_x8WNN9kmx)Bu9D}3Yy7ZzgUK%gs*`tQZlbJEe9tX
zBzQWo%6|UsuxsOaNP~Y{xutU<CH4f{yM03)N9bdb-msv4nLZqjVP~K1YeV2RvkQ8?
z`cN|ydIvEcPtu*-_`9V%3iGX!0g}Tf#hbnWqR9x<7@kJ%tVfI*37aOiqPkV)^1H4D
zC$S3(0N?0VDCAr+<(KXTL^l_C11>QiMKa7?R|48t%z0K+E*I}@!=z+PuzB0WlkT`n
zpnMZbShcr2?00Om9{ly1rR3Pd(f(e9_|<q`tl~nGCHs{DHb>OAPRN^C<rSex%+6;k
zXp4&)ROlyYvpzjX^?`XTnMphcX`@qzP~k?hm$QkqPYr?{pc9&?Bh#sZt=W#{SMs4!
z;tsE~VYHTlz;u14kiKJWw2$LNqbddJ0BZNH*hVCV4Chcwlc1(OPY)OG0gC`ax8bKo
zF<#udYyRa-l3PV)pcV1KrZ3y*ihDa2WG3)Md22ZkKAI?v<Cdc4xJ6sI&g>nNr({Fh
z7D+XB8Chqw#M_!tm#86U`aN%PFKo>5jWC_pqCO9%8J96VSMe70n6s-ni7{v+cukC0
zwkhdUcm#NO?<$}oOL0E&0-W%TZ(5sl^`m}-7(LVH?h&0HmXKXRmnlM>lHkg&o03e-
zZS|W^hgPO3*&j)?D1*!GtwWw|xlQqU6@uSNkrorbwKesjED7wUD+Klb!$R*hPWo0f
zJ^S0?oWG_kYWL$DvY38reaAtwSQ7e6`Q{9mNVU$F#DY|0<hmGFeby&djr{_SPyhiE
zz;z4vCS0#(+3(Ld_jri^3OUjQ+yOF&aL&ULo3*<#yMRXF9tLhb_H<rwlaJ4i@mCl?
zRR5Xb`7UoMn&&y+LkIsL06e%g4kT)ZUn{tb?_|trP;|$wII1?|{TOcf3*Yg^xZ@^F
zQ%z_Kw&O@ACLJz_nc{_>X1}mcPU?}UjIbYoNDt-w)lpiHmDP35#DZu53evGX*souO
znk_Wf3ta58zZw@4XfgW#_2w)d+uIq0IahXOsF!??iIU_V?gL>TbEibnZuAPL%Zhen
z8<{U9)vR}9$&G9bAG05q5F>uXaqHRIl#4P$0xp7voT-e%o*`XOWOwC!0IT(6Rba63
zYQbJ_r+!4m_d}ptTwRLWy4ME}i=$E><~Up??2Ubahc7Ll5wI#nzjsb}ln?P420Dv0
z@w%7aCs7~GvlTHCH|#u1x31HofJd)?7_9fp?#}T0KnqWtzi->yIq|O*7f_qKE`)d2
zV~10khAfRS=ba`wZY*dil~NZ6cE95$`;r_a*jc4;QvK~(l@ypIl;k|xHP0%+NXz_T
zJI#tg8xST<#aLuvc+;`Z=o5ChJu#&BoZ_6+$ZQ`S-pGQG&M?i|2a}ETi(Wr2)<PlQ
z6j!*L*b|G|q`Axd1ywbo!N@+GNfj*t#}P@8Otov(hJAO(Q#FWPSgU$K&sGBX4zEQ|
zokC?4C|}j4vIBw&ju*3hqn?L<%sGj-Q!Chp7k|`^!mBE8Bx-9<$lGeMY9E*Xz!n5?
zQde9k4v!!bV!FkSk}X4sl$4Xk|0Fvq%<x>O1NTrLWuA84Rn)$5ehKo-F7yRx@)^uo
z&ZBoYu^`=ew8DOjbkzVtj7vd4vGtqgeC2z&z%RTc+i$*{vPH*<@?Xi>0H<<+D&%ZL
z6TKECM5IAzvyj~T(?rAnez&LR7Kn_I+5|9c+9SF?T31p`EI)KGBevDVq6B9KnR9Ec
z806B^V;nhp%ff*;6$M~ezS74q7h1T_erBIRo56$wI!1>*+JaDXt`ONIp1(1*#d6YL
z*!btg+6C~jVQNx5Wrs`Mke(p>JZG9x8Z>Vpy`GNOZ$rc_!97iB<LmT_b;+y2huF}3
zAf$Wt@Hz%N;w|?}ukKGe1{0)kCGxV3{TneOpw2ul=cPR7BEfx2F(kpauc3)&8VpRj
zNHN?70NU8*5NafN;G+wa^Kh*0l}__9Nqi|P(Yw0<bshE)7etoN<&uUS%Z9p43=M^5
zp1iumRr#uiJ_ys4fz|5AM5A>4qi2%2`n8w;^YDqa&#sCB>e@e>rk!#!6I&TYkQZgy
zlO`Vbiwp%AV^Nwyyx*_;3({v9i&HG$1$FSvG|ltW?JRDkr$Blj2BmD6dHn}pgXvvj
zFyeXGZJ!GIeCUP~I-%iZ9T5&`r3pWmGWytcoxg^SUmyU<r18%a=uFR2ofci>I-1Ru
z;1E<Y46xA3BEm0<5Mb&3Zzk&R;`}NKvh!+XCqEfFXG;bjDO2CuOc_Y<7uZGxd;sQ=
zwq;bWCdPvpwJx`--2P$B-6m+Gn`DoS<pNVU$G$J!)e!rLAp2;;V*g>)?5Zv^X-VId
z;kHNR_#SL8Ms20_h~E7rV`&_*lU>hT*`<+IGzOw$J#>q>-x*`WjYD4*Y(qcPOTXZz
zM|texP1N#@D*$MjA+AgN)8l#ob4ff`_yTI46A@$eD4o@rkR4rMX7VBCekR4k59984
z+u_ngDOBUY1>C90O^Gb4cXnD;gM10#XkQifzt0i($(3E}9{mARKnKtQd~qPHmE`VT
zd~}TiB;ytGYTyQ7Vsrvv<{LitP3LZbz#;=i3Iy9462JnVhnkPfT}toN;QMKtmpmk|
z!tBxdpsL5k(UPgRR)9bYzYxGQ;1PF3PfwOOM9P4uooFmL;L!)$(KScw@I~cYHXJ1J
z{ly3~qwJR3(T!IRrpCRj24Q~-qyJ%n@&^cd`XWj1mn%}Czb28Kr)P`U2b!wQe$wwr
zR;&<JQeK|wW^FeFGFCa%qwq`Zd!S(22lAZL!aN;yU<3<qz$#{Kqa_-g5ennl?Hf*z
z0|KmGXY#j6XJ1BZrKXg67sAE#X)YaRWrPlSG#<DFaS|10l!QPS3w1#`z@~+3!w~o&
zAUEtPcRkRb&T`7CSs_9xR&((2?d0oUK`#hpJdxx<TX9XLFK&3jQbA>^!u~2}#cL$x
zkkjhWSB2HeXD&+_1}zhx@4gemo@)ta(}vyn-Hf>0m5a2rCv=?`vJ@}uDi#%%-(_nf
z+>|q_LK8Rm$wW<wZE#|X6UtV4e@OqvlLkxa0liY}-iI$L8~WfX2ZUGA$H#cZnxz7q
z=VE4d3F)E|(iacHT1Us-qJAeXYAbanZfMNOzac$k$a><CC|!8*fF7gQe<~ag)S2&d
zu7IaRfalg>(f)3rg(vQ-P@uKhi<`A3rpx6FfJ#%9v~?Cof@aI`GjyW<mIYE%#Mu=E
zRNjfWJJ{sod2fDNAB>KcGR>T$>UqbNd&a>iU>;kW)Jqn?989Am*WTGzO0y3?=@WP7
z-a?OIu;>HoN~Mg`m+B`H#SZ@)_SiVzcqBu7%(d0=&S87xZoB`jxg6r<?3!YAV5x=H
zz*}rZXYYU%;WBULsqkwb86{vLP0!Ihq8_#LLHV3mGQKVfq%bAzWyjq9H(&}}=WJr%
zY!JVE&OyVB3b<5)0v{8sCG;qp7<J}voaaoo68;ZMr_dLuAdJ(cG`+Lm0kjH!O1d6V
zniW$L)MFqsplQSkQD@*xW+r-~gvy9PMQE`mY=RCrNb{wH5S4>Rp1QL=YK_CQnySFC
zGBjETlp1{kI6D#-4J^};6V96v=CNjmU+&AE8~}(*6;IsdXAINSlHU(GtiuLjvVG%R
z@cSrfei;TXl!p|26$+S1#F+$+8bar*jqGVFK01B$kARJ2e0rnzk=@iM0Z<{F+}FD_
zjldR)B#3?x9$8&=R;$zzDO~--DoSxUkCG1zpt5aCx+n&}Z6>PS{7JeStd1G{IeJRy
z($5`_8EZ9n^B0i}4vvaFs-6Qt^~(XIl=M@EAG?&HvAto(Nd{D^6MBB7ajRk8r>Xz2
zB->Xx%uFX9I@Jzec5#oA3{!%}pgqM$h{SRjSJDBk#>zV#X<1C&c5rpXT|*N~^~P2a
zqdnFu&6sPeK1!OEM~*xnDOs<#;M}jM{}|j{@0&73Z!Jf{*Hj7yJP?CSiwGBZ5tC#A
zTY9KN93+o|rn$yy!7^euYJ+yVaQk;UI)1)_a%QsIg`T(VI_D&pc<Z6#hG`E0ht#HL
z@nE@0wP%gk@vzm-zMyic<vi_LqN4b%!Bi^cq~HhH!*9Q^Rq8VFsL%7RA57xa6=gZ4
zQuRSKN#<1pyuu|eDuF!YNcm?~wUU9&O}SPT_6x>wes#A<p^lUI-9@)1nM<*1nO)it
z`e@PpMVb;K0-#@dJ)l|40Rl8op^06O<Hxc0wHqQUAxAZ^qXg5zabci0LS$OsXy1pG
zZd%MY6|)3rlJ7=l4J<*9GGvhq{Dz;mcZ!<;Dg=?*MFW@gX@)DxUJvH81OPrl*o}VH
z=3Y2v=uKeI({1^_>3%8aP2Cqi{?bMmGcdWcISDUx={5H;AHy3w{q|k!*{!!#0aUPl
zIhed;hg;kaQeH;i?LR2Yg@PHdY^Bl~;;i1WDYx+y!6H<h@7V6><=K4S6T^%nFr-BC
ztvle{;vBrUN6)O}57eoEyd$>io=4<gFIjcz`V-+d)=%#g`29#dmfHT<UjQw^d4oxf
ze`k?9)l+Ah;Ush#<b=uXKj7r|Hf+yqH^IQL^9P=I6SXvYs-TMyJnROUI@Q<#((KaT
zv<Hrl-d_R61cnhPEMWH;M4_GnPZF`MfduHkPhD_|s@)c1vHmzynVDk~ShfQdZmdk%
zBB6Qq=2m^g=k-U!UC4<9zo#}D(1~q^FwhGi1(aENk!qGaq&Fk!o!<b$X{%v0q;i0D
zNm=^iTnS(30XD!SKthY7gGcH+O0yID4$m%&Xs_}Gzos!R8LG8YO=5Ss!LMthKAyBE
zhEza2qyQe{r&+#-|FFzjIs&B2N=#abfC5JRs_#=R%2MS~W4oe{HSpV4@%W(60S+z-
zy)FoYR&L-|7$o93I{;YDyV-)|y7o<hO|#sYmUXRAbnz}oO#k;4D1#SF#8%?RAKmny
zf<~CTUTf7U-jW43oVx|{XKe5$Pa|-CUxz0SJ{7t+Np4Dv>*Tb^e(3t*DuCnsyUCI1
zU_-l!@M>FiT-#GQu&Y?{_bZ7qIwsH<4;4-CV)Sm@6I*x%RcBQdOpz>h)KlcZ!_s8q
z4FlA?wpwzdQoeL|u=~am-XBjr>E&z->4-;L71xX>u2^_VT32JHYi4Kuw0>v2-zB;%
zHA_*{ETRn_L4}Xk!i9pAu?RMYvk+nemeArhhD#oyR9i-zp17tynT70(P4jM>Mn>QJ
zG;Yp+SW3z0Y|aSPOxWIsyZy1idZDFk7RIf3`(~dDFOxZ1UY5~Wl`Kf=jGWubSGJ^&
z0f%{4zZvbv5MLa?+&>{llaSsSd}TJik)Yb1#a*fj#9WqdSfA9+_0o@ds8WORLEt*i
zWY=B?0RIwLdR6xYNrp>vE?KiSGoVF?ilw8hiq#1&K0lfBU58b<NAz8(iW|UA7&)tu
zkKO?QXcpw?P{>qC%1_#lersN7UFANcjK#%y)bG6uDr$$SUj)!R3?*T1@>)MQ$ZV(q
zWsX9>`S*xR%7L?wzGOOm>s7Bj`4v~yW`3Z$MgCeO=Ul53Az614R9cF0CMjZ0*N5fd
z@gy3yt0&QRgwQvwx0};F8^t_lJ*=_24Q$zd`d&&y)&kqL#xgpL<Q-khQM&7oW=!9c
zpeWuz*;=u-R?L+gL#Hfz7eYkuyp)0MVa*m)Yl3;ae?C5W3c2_3I*I+`@JfuO9`FPa
z157aX0S=TKN%^VvH)nlUqt`$0y^1NxFr+j~kX4dA<c*dT9h<Bz3qY>m1U&f0M}`a?
zd?#Y%&ANyj8x}py@(Q$`!Mi3nfOY=MH!H&jB}oIbmG%;T*gC7+y$JO|x(Ma_`=?=~
z+gs0HX+7r)v4r_J+*)P(G2o*ogAZ`^M!&pKIn&)8W@3D55$N*xHp)2I6ZmJfXWVk+
zf&KBVM4tcpSWgQ6c$)^!5OApIa3`limjulXye$0*GQp5aVkvIx_)l5=hu<2iV?=m%
zxSzSNKF&HyA!#Q;X}SBm1PyO#nmPhEM-_0hx2N*Y?f@5Jj4l2Px}?L50a~_tlgLhJ
zBLGhUdF?Y%+lN`V*ue@pADc?ui8vKOPb4?KQN|YaFiBzWOegyZSBk(U={+t>NFMF^
zAN?IIWg++Lb2Hz~kSEE?GgFIdz@Ib+4L#GeY+-8}MJZge%p7TStd`}T{JnGh)6#@t
zV;AP_kzjGdTRL`Xv*YCD$s)Jdh8B>Uyl!jt4fxYxX3ScbFa>|A)FhU_V@tm5fPItr
zVi~osW-D~z^uQcF<!SsNjWrd&pkCctG&GXsdMN8ONiN=~b<zmZ#_X>k{)vc7>chH&
zZyZ<9NxEfPGU2DrVKFZO$Z<y#n8NT8EsMcK{mB^V9*v83eMM2&@|V->0t(<c(n-Zm
zC?oFozWOngR5;rT_zzP(K0f@$qcQFE!`Elhu-Dkn!SGK^j!YpoY9m{Uvjlgs$>Ux;
z&rk4uMgIi$p3fMFB=P`H1LRu{c-TijA6!dVJ)+IpG4}X~WI}7XOFz$Ml6K3m;D%7n
ze{K|~mR1zJnR471GCOLd-r-gedL#OaD`F~Gwb>x2#W^_w+_(`W0LYx`uo&PW`@0uK
z(C5K&v6bMwjrvu!Ntx03LNvD4H|Q*i`F|Z<Wk8c{7Y0d5mF^e{f^<l3Akrn>f`FuS
z=Rmq!q(K^_ly0dJ(%s$N8?e3K<M(^i*!|q+oa<Z>>*@Oe8*qtvj=cHmvDL_&>SxTw
z*O2tg*R!(L$^x>J;(enItcSmeJ7|*vn?KGJ|0S!vH9-R?<tXu^&u<=Kc0FB1&M%p<
zwSak_M#$82-U#^hN4BO>!8SV=)fWq2bAkcMj~ZO5p4Qd2=a3TbnC>U3Uyd&FO8M%G
zR`v+F1RF-0+Oxwe;-rP3qZnvJNvx;Ae`vX19^R5ow2wq?&<kR;^9tg>#31QGM47tw
z7|a13Bdl10H^X!3W{=^p5QJRZht~gu>2GwMWq8egk$bEQAvTb7C3N2;x%;$qHiwwR
zx!^#*BD-g-%Dy>)I1V~LAM>9vI=aQ5y?k@8`8?3<0%W>t0Pfo)$KaPQ0NfBc{-xz*
zDyxqSW%&q7aYxmCqgCYd-VNlH&HTx?J;vH0Yg18VTk_Ju!bE+wek|&`hL2U;7jQJs
z7IQ{k++!AFTaUY&8M^lti2sN7b41+BR|CW;-gTdLpxX&to{~$u3b_^n6PruVg!K(k
z7?NaZJ)S>@8x$zxc7AI#hE{w3t)3HaB;$jRl0uWHB=0pkV=-d<bKV7{)Kd;T^1D>j
z>Pvz!NmRgODgNi*VHea1@CM~|!@>Bwz+whc;L^POlR^~kRrmy;;Y*{LfIEc_oBVhv
z&3K;DS~Qnq^lI`_syEJwRLtJ@EX%$%A|;&md_3SyUFueCdnyz>|CY4xyqE^;XL>s@
zVk3XakOK~HmavT;E`7%rmkn%+26ej~boZJu7*;45MpMPvT5BwqB_4Dv7UN3O2V)CZ
z;o;2Xv6cwUe9HSML9*E0^S(NBVmGxpK>fCw)AX{?JifcRr^=S`S&)k;3Cg>4NqaVP
z7r9vdi@H|t02cm*0`n=41dT|UrgRO)X|0LRRxGM2z})50?a3R>j-{W_vEINNmON7Q
zd8pYzI+H0T$*7DHGPyVp&G1P;mM+Dvol7+Z$@5bjh9X84oA7%C6bp9!W3zVo<+q%t
zgm}(ytyS3+G~_&s5A9rz!snkYF={Syt+@vZ^vRVqy=nZ!WfHIFbtG{AL;DPJ#<N1^
zEA0UtW1)#M^rj-%g!u56-=H(ADz-sZ2ieR3&ZrZlMZetWxtyD$+l)AnaiK}`;TM3g
zT%2;mfJxf52|@8yQz${eD%yBkU;#AYD#tFBKi^Sgnd^V@=b9D!hrPj|D*fh)>yo?c
z(+$hd4ytMm{F;Vv(T%l-D3Kl8y65A??Io|yt_Ogq65x@p#Sd}`@j!%HRDa#ULE75i
z7184klkCa5-T-&7jxv6-SB2U#L6Ud$e%>^nS4WrI8~$-j$Of=!6R+M}QS2Z!at&cP
zBR-NzAU2`Y59%2Nh+DaUn?Ouu?Hw0Q2e1*3RbdF>j2~eM1h9lMST{L(oW&oBXcDCL
zI9^GA&Gj>7-YE|C#+bx-^2^+hb~1jv#RbS6aDg=d55Fy90^CYMnF<)ay3E}?ewEP;
zk`hxIb>ce^KjIgCiN%-IL8L38FB6}a5OOH0Wm@{?q+Da<g5Pu+CF0Tkhelj-pbRBD
zWIRs{-ZugeF}I3Oh54L2vL&?V=p_h)cii`Ndkt(&w8`)^Z3o47&*F+yUqc!N^+{8B
zl0=W=0ifRald%9v#1?&<M*4Lj#D(`7u#AQ--VYcdzJmvBIvwX0JRSXfysfUPy4Gye
z<D2Q;FLtEFCXF+lBr2}E$nF_9yifWnA`Xqk6%6ZIb8@|l*lh`$6*%erS+ng)S=!%j
zhRgiH(~ZVv*-E@&@y`GfAw2dJ(3JKs=`g9XuDd~ITd*%A8f75xJ?0-^&W0|0z(a^k
zQ1q56g7Zdi)No|$H}!a(-S1qXl{L!$&~!6WANBFgtyxhR@q7Q;_g|0}-odS?k9VKG
zp_bT91zS((h!)Kcxj9S?ftUSgH8piIOsSYzwyG&hS!Sy=neq~A_&kVr<niV_Tvuw4
z!^C$@rBjkkmK*BC2GHC3DO!XE7G$-!quwj}5|lVa_d0NUoW;eN-QtFFw<NwtY(U#$
z)Hhkb#HiVFlTS@qBil}$@RG2gLvLzYcHrD6;*VwQl7v(#3lPr%gxe8+)XVq_{F%YJ
zmP@<Rb5+)&qvdeK9DM=8E#DP)A^u%x+Fe}1vepFLr>m0)x;X3vRoq+BnsIIoKo@@!
zRzR^>SHiUH4`R;A^T3dtObpO6$$OIg08&%_5(UXSG71L&T;m&I1m~F*xK_x!ST(aw
z38S>wYQ)}89&2~FsQREUrdEC-eO8tvw%b%3t%XBx{|9KU_<0@=BJE0BFLoK=&tV5@
zsS&3HIwAH?8D<OBYUM6l<ubOgGXr!f&2!r7MFg^?F`vOt28)Ko=%Q6j<-i{$;%tSc
z-3H=jy@Jk0TvUFnlA~`tx~kICXQ*_T$r3-j%Vmozd9YIafTzSzD%RQkeepJ{4KWcw
zJB#^|)@9*xOXPUM6-c|NQp}PC2L~yoqL-qWYGEYAeJbz#R6Z}v-<xVnZKTV-T?gWb
zgyHT34+G#jm%L_>S9u@$#!>@bM(Cq98pELx+rcHZ_xS-OVw$_eAW>Xg&)n$|fDy<g
zHNdY%6<NMB9BZj<(ydo7Y`aTDY}ONpo1<++Zq*BT1&|@)woYHq6O5f4P(6t-jzZB+
z$^PaYAcuov>~tik=P?r2hN@-q7He=ynn(%uAPrpU!jagg-g$Nu>tA08N)U<a$}Vz-
z*iA&-l2J|CYgIiDyb-X*MxPbL5ys|``{)X!8p?!uUgC(5O%n1=$C=?EH&m(ZD~QY}
zODs6DDr`lA5N+GErW<ks{^iK7-rR($-^b*pPX;L;Uk}?^w%IEa^;B{&whANXs@ncp
zuvys@|J1FX*xAduSs<<5v+egE;i=CXwTNN6K2VcvhWY1yzzIvqSrG6~x)TOlb+{V)
ztj@Csvc&HKDz9l5TOmCrtLXCr$>sqXj^d4&w*S!FBl2w0V5eyq6OmPA?sm9C$?PPD
zSUA1pxIX<R%TdZ)<~H|VqW>N)j7nrQfF@5^w68!c)oQjDIj??yMtn93zEhlnG@jh~
z!>>^O`}T30Dn*M8&h}q@YBg0Ku-cpxY69i=*-$HS?}X46=l~~DJB9K0y*?*`Al}^x
zmTwwNvi)9T2I+pBen;Iv1JTBhv{MkYYfSL|PzyOtcx|XVZML!}!_IznXWdFA@AdIQ
z^QU1umV`Jzuj8sctve22&592%HuKo{J)c@=LZZ?L)&=hgDsFPIhVehzLTI6i&gbP>
z{EG5G<lyhj-n+sW={V8Tf2bNwpYGxO^RoMfV?0lmc{Kun(l22Wulo9E!>a}H%M{5$
z0B=<1xP;Moj4@~Ush5*)3d6o6*&O01=TJ6&-ht8a@b+;(f;@nqd;+Z>aoOw5sMsb9
zF})ZRn5we<;#5_*B@PQ#oP0i85`KcSOd~1oS8zYs5MGjpNC<}OQo3h<iY69}WH=_W
zeKjK(hKQ*mb|Sf-7-sw>7F1|6JQR~t_zlS}Rdlcqo$jAMi@(a)2)Y05peZr1bP&Z~
zM$+itQ-gLQjuJpvkjr^AcqjpbVgU}r-H1R>an)az_uMNYBhFyeA9Bo6Yl%_dvC;&g
z$gbNFE?IIp=&O=qj>kq^-bW@+YL_EwMIx&h&lCNEo)%w`ckzu=?gDUgW&9>NMsWU!
zZT)g4HDMJH#muS>kNR{$l-Nk`6M$tKbiSIw<5$cou^4(jn=x^Axy&HBM=F5Z`H$|N
zQmQuq+jmt4znr|IXK{oRafrixRbcn=fA<iRgm_(-%zti$%h;wIUmU<<s}H`)$cihO
zF5pteTaqc%DKQ|np`sxNv$YNu5g133b)xummb30m%n9aIGI|fT_AKw!rYg<nduwI!
z_C!u?-D&PDa=VMSYTdbJww6f<_w7Wt`p9Qvx|RH%%^%HH$=$J2xn*+148FnpD@r2M
zXBK&3pCI;LI#;Jpu+7jR&}<>jpSqeWy5t0a^4-fQ-cR+I8dgcLA3wzH`oJ4rVIotu
zsE$V7`+dUqUot~GO5!koVDBaH&)}md)^b)&R<4b=Hq?_GyTelH-UY$ig|1%YtSJJl
z^XZ+?mL!Rzd}F@eul=)c?oUcOl1*zJ$tS{Y7GKYExt?rE#ZbDmBiVVkUUG&ssGq91
z6{!6FEYc8<LXeh~=;s14=KiD_@-!mJn+Jn<jPWRpD*z1UZ9BL%l}J}{k2SY0G+X4q
zG4Px}@rb|n0#;ZVZ#c3t;0*})!yA7u(j+g~2kE-SAGbX(`0sVK7=v-{fW76Kz!WA8
zbQ%Di{U!!?IkLPj9Db^i+r`0XHK+QhfBy=8g65MDYaE`8m%|i8d}p)zUL17*<Vb@z
zT;m*{AK}Vd7-7uW^Z^=uLgO?sbozXb+RLr}_tr#WcnN=~J8>Zc`L<$N0CwC!u^sJ9
zM>N_QPTDv3_`b&}=HB$Z-S7F<@FB6OG+Muc%Ysi?j<<6W;(f+d{8`EPmO<rSk;~*S
z(8LfXldak!1oBjUvPNf&LGeXsqXLKYEM{GiPj125g4N;*Vcqi3buqhoxxLfs9S!Vt
zCsCgdlVl5j1Yr?De;(wFh*N+ZdSlefLBwaQc4y;zuxqNx@PVq87>;5lQ}HMOQgpxT
zK^gARNfp<3MnuKu>;=V9Mx6{d_)HUXtY0Y;2^iW1@tlZ&nmvvXQ%Q3M3HAiX;QIMq
zrTi6D298f&^wZy~MnA%oJN5C61@e6ZRXH3am<d~>RV(8PqUvc!T3In4qUv`$MwXiU
zfEZEfXiScw)wcCn<I`B5NwYOE$?b1P#uQ7tPNX5Qnj#99(qr#aHU;$IzP!Ui!iRSc
z(ECH_JX_2g_1tQ~ae$w@d=(oUH>@73xY5=i=Ca~dVu6kG2=d&1{JVSy?A$-5z-|9S
zWBMg@H?Uhr)0<X1Sg%1~^#B;F()8-aa!n>AqJTvN^_x(0VYmw-#msu(dfCM$xQC+X
z*BJ%<L#z#V1XuUzQ(R#QfNdK4PF%&e33a-Lf<v}c2k<I3D)Is4Yoh<{*8OC4DA(94
z`E%b;jQg3ei<h^=!^Dp3z>PY=8p&<`P(iGAntM?oWgJ8Qtl2de%zs0x6~CdB`XSfO
zh(Uc6TsN_qEy-reGzx8j_5;bU)1KyTz{zz<O*n=z;0r%A;(|*ASpo=B|5&Cg^z%Ww
z%il&;PnSKR?_36c$CO;OAkQ)-Y@FfZ$ACdv=LYfX1c&<vty;KL*FdhPxM{|qBZ+P3
zLfg*4lqui`Jzc%2q9FN+eGj?FMV%qnUC!SjJ67zf*zqEE0C`j;y7^1DmpW$YP8oY5
zF(?Y?ifN&+VK=%^3cA>t^B7yX(PIf1Y4irJmg(nkWj0X!=&vQs&Uu;>7mqCrhN1H8
zk0{Bf&3=z7yfWPY#p99rTV|xw-XXxf1QuE``dq6falKJJN=q<zLT?dFm$%N7h5A+L
z-mRH&S@GxP_%xs%A@i){99WiSW{-|{zupVcV53J%<L0*{Bsphlm%A*xm)jRB;c%@6
zF`9~v;b#Fy0OlsVFNAiP*?KuM`tFxfF5j*z?C~0e&}<9Ny}7yun6zOf-`}`N%S?qq
zUFw7)i}%FP9__v-3B~Y|D5|wu=708sRs+<P`~eTqvEvaz1rtt&i;`FIMb8t7XPk47
z^jpj*i||-HC{eFQz6|t{><AdWE2@nBwF6dN^DJV{#6_6nO1Rk8jgC>hbK;+N|5@gi
zX+uXBQ<UB;HX;_(awqC+g#7WO(`Yl_E}NF;Z_N{5Ck~NEF^l<O;FS6UpGn!o{<kP1
z@v*+&j|a>6(Vm595N}-d6RBx8ci7n`s9wkTNms2|oLZ}9a?he`^Iy4hfv#Wfu`K=z
zKZ*%WR9L}ItTiL7w{%}wpIsfQ3DCXhx(OG*GgsWK5o#|c-ZB%rP@!j<`o5u;coLPe
zFY2X*oH$yEWw-W$rla!I|6)SU6X#jAQsVDi0E&;X@Vd84uJY>&yCQuK3(4jpd%h8K
zBF2x|ynSLplJK|*CrrM?eVy+p*2WJM$7eD3K?d)-$2=c>0os`#-uwE7E%FO4e+tqn
za(>-Dby*(HH3$A=WhgmDSDhuy$?j97eKMwDzgn5mR1z-PC?gQtW!*#xIZtWo;jEIt
zmdbBaaoUO?4H}?xH4I{2K@~$Db^~iump=hn5)ILzF(jKDZFI92aZP(PWxzh?V=clS
zr)s?rMK;w(VAwfR&9WCIrzJ%{Kkjf8r1ZVeRi)CF#n~EqmSH_37%qHCf#%LT_uepO
z9pji?61H37L9i=x`)i9{>4ooiXSqf9-%WJu7ekCyA+?-yw6|q^UPaEdf6@%cz*d`e
z3q-9<-E9#anH=Tb#w?~KQKpG-L@Y-vZH3e(`2i@mlo2oZIOnAZ`?im7fLRMHN5=S1
zb62s%a@q6GAc&$aMyfxgHzY=R+Y{@cbKxV%jGx2#@Ma2GrAzbut1}QIudySCB?|TU
z9)t12E3jd+H(rW~%u{vJy~2A|L4QH*P0>}5p^~?V)I&Eo6_U-J+WPkk(uR;YLMgi{
zMy--Vwk$1~$^VGRU*m!%Qem&%s-eK$-NQUdgG>$Gt1S65OSHky2P<YS_MDs~-Zv+W
z$W0XyEqVO6uj&LMK-pah78*5gKMgzDGiT4SllsiYrZgmC(CRYP&fyg4&bS@vZ4e}4
zfoF7jR2ux0hxEJFleHp6v07uy@4myxbgb&K<-MPNL>w5c7N63DJC6R2I;CPszA5fH
zK>hg<j4J2PHNdm3K~7MYUiWi+yX^PL9nD~Vhi{LTn+BRppo1*d$)Lns;p5x_f($Op
zC#R&;yE?c_JD@1*uRNroXpKhbD(KTtyZwST(D;Rly|0{9qnkbeuJC8<iWjo;vAa*@
zF(NO<EQ>+*ZPG>V&%eqc`9SxY@sV}c52aoA$0MJ(GBIxWhzm4|)6i2tw6#Ll3b9+g
ze*JZ+;V1r32do(K%#SbQ;n*BJ`?q6ZoIK*!J}%ZC;SL6l52qnmGZ%i|OLVPScj6ih
z<i&gmgL64q)6V-k?0=thPB*9>=>VE8hFZ2x4gw<H`14}sOs@{Jf@d8PwJIhQf6<<h
zzwv!b=4LI#8921fpi>qeUbjP~Cog<6c9oykoXQ$q6?}m+d_y{W;eQ%n=zK7&Gj~gr
zwSL-22=j6A@>P<s2R()|eP``ULn`(Iw)6@>PpNWuj<CY1sR{+M9dX|l{q%;tD<D(W
zUpyIFdf(=z-If3JH>Fp`W1wfRi_aH<-1FqM28!prV|VhEwWKc_5WGRh^$udzPj^Wn
z>bj=Qf0Zh2tJ~OO*d*qJOT!AvYlceczbhUS)-icve((=0We%kaJI>IN7IAegf4ln4
z)F0FKHOirMp~uL1Iw;t<P$=<<FpGI}g>}Vqbaeo0#0b=$$#QV43t-Xg7%p!<a8vtj
zs_Xrxm!1re4-xz&rhF_lbpk9W7o%@m801Rm$WbyhG3)nKgdQd~$vJX6Di2>CZciz<
z>X{1Sjd9dRJyj6N8h;9GqaO4Wdzu|mrzIZuiSSU&`TjbG!h<>=0#b~ym#imcaWV?x
zwkki8v*A3=?JoTf?aRtW<mKSUbc4_Rtv-e8uzx+C6ZwB=GKPihWnnPeZt#orID%R(
zF`&pFO^<D^C^^de0J9-b@^t_ViRC)P|6lnRV76`}-OH_Gf*e<|JFn}Tpgt}Hd@Wbl
zj8%Aw{sXka-s&~1{lV!IE%e`aqS-QF;$CHTi(JD1`WA()A=0fRC!JwKpL4VFL+AbU
z0dg_Qk<>PC!wLhi6r)2wm&sYX0r;C;AJb6JTFJ)lZ^36q+c~dh%vmW|kh0eQaAa+V
zMusAu+9}qr*E67P*HfeE;6Fa5PVYoO$Tqy~%wFnZ=oZkgD_Y&o7VbH>e`l~Pa;jb8
z4!%xR7LXk8AfHT5qyPxhP0$nj_bp`|xj3aOY7~vtsc&7j=xR~GbuH$aXCvRqqMjrM
zq$y2sGMxT#jKBTXOy1P82%S6?g^o!pKge{G_w^QTm3_(ZB#Ud>Z?J7MTq1^}Rqz}%
zus6FmP@OfB_2s?=Azwis;5NlVnAO>@ajFc$VCJoc_MB?3rtPmWqBQRLxG-n)_7<Bk
z?4F|~DBKB(dwi%N3<IRMy&tIQ_S+}SjrjX<nhHhxBfitS;mqsezOf%z)?{5Rj_O|N
zLMZ-+*5WLUPZv2SAT_amAEmxY$moPudz8SD87y7DewGGNN0FW#iz#RK>udq^rciRa
z*y0PFl!7x_w*&2^z7};cPbGvl;7ak+C=0P7CJ)44@)i%q4!`~nts$&5Y3}i5hHXqd
z56X>!a)E7VNqH4sI@NveAUDj7d=z|rKATC|6+3YEWt<rTSLJ-RZZMn+1*p?9tZ|?(
zn<M9984WGi*?%rYV3mp;^iwnr_J76<64NnY3@f#eyE&60?#EXY1YpCLnD-eA#^haW
z^pc?Q>oVPUQ~baZ&>6bM939hRLT-%xfjO3ct=^`%1nN$-AJv*GvqhGdp`D-{K|!Bg
z{`Z4yfi0sX4!T#Nkh$aBol}Hdo++eK#<ldwqvGmaNKj5Qb7O(F)pkH}p><;X-@J>}
zAlmn<FK5xlhC0u*FihrN?$9#aX|#sa1qz+LRv7d7{)cE8p^)XH?j(%<)9b5L!YJ;w
zqMganB^LeXe%F|g5l?Hf$RX|>O;YWTq<CDR9^M=N{+&^0!nX{gDTDzZT<-L)>7c1T
zG-#zf>_TSkXysIUYZkLbtWIr?cV#f8IpatMTg^D0|Im;=r#q=>lxSAfr29LbAJulG
zYi@+Oj|nYx>23e|^DPIY@|>@h_f)SdkS$a$Hzfv`q~*f|X^e)ydb(=5r~*)N>6w_Z
z+ytP8e;v^0Vh$eVH*~R0d(N{6I$E(!yr4T}5i=Xg0c)ZJPO${fvp0k}@!~Ct9G{M=
zitnRcFX^a7RtNUa%in3D1dZEtOS#_%Lc56J6HYbU!QcH6=419{QR#lPLKo~YarwO3
zpD!E=LCctE_o0w2ZQz#Yo<Z;b1X_XIUjybkFJg&buz_1$HL62`Kret%5=0ia$~t{<
zH`RF#WRf#ZXC>ao5Pv33H!2=DkMVQNPNPp{hQC|TjkJL1R=J{HsHpsYSQkD9&fb#2
zH~9y{t$j#$&}B9?Ty;?pG?Eh6c?7%!bk4bLr_gonA+Gw;R<gG)=*QOfitwP!W>uf<
zaSl4u^N~PArZa29Jx;jWxVJ_?i6E@~<N$Jk;Mr<`bmuEA^#?c<LC)E^IOw{@>*_&w
z)&Wgr*og(DBB6%oRWHPb%h0WwQ{!7dOe!Qkz>bhxKn9;@*{6bFR55XWpS=BbLaX9C
zfAlJ>=sm0SSIgJSHb41brS~K<^FI?;cqX?T6C_Kf*+>QMHMobE-uT3EgkOfMjK$x@
z$}@f7A9X#F8InJiL8Vj=Hqb9yrW|I7#?@Fg@QyfFP+I^)Z)H3EB97I{3nAQo8OGXj
z!DuveSs6@VQM_9$x{U4`{`q#dTB=B23D+t}VXR15Ao_&|0uNhE!wd+p@d=>Bxbv4n
z`LowvaAm+eHWv>1Z3Hv%wStDa0^?+He0JLEL=ckqnpD%dBzk`HtPH1(@DCmAbstoT
za4KDbD4aJ7_0(Hp9;bWVMmC3yTSHtJ^7;TM;OXZM$aK@)AHm>TH+F?V@NN-#B45l`
za9E(=Qr|@mIhC3OuR1U@o4PpL9zqrk{>BZFAGKbUL4H*>Js_d&k`(bVdhU&`fQK)%
z`{NMKDQ%Ki4tu7J&YtJrt(<v)_8>EH;zYx@hrCklre9@igFTZ2{N`6*wmW`*-wABr
zZp!tp#rTsS#{CNgA-80Sqwm8HuLZD(;R@Ur-LfT9p8s@{@F;k0=5Qs}_|KLvj#a0C
z-SY$8lJhIbS|LAGn@lOjq(r+5K*BYaL#11-)!PdNnLcCS{C#K$8O^2-EqUy0K0A_n
z3s7$WY%B>-paf3Iwg(IY1Q=Z6haW9K@=e{OcQ8a#i9WKVY-p(zoJTM&mNj-e0%xHa
zn<Jw+yo+<b?TMG1nJbPpD~OO0GJZAm3Xf5P*m!vgBhGGkD`sUlzLKf64TE`CZ2)R;
z3Yz!{*;}!REnZ-bZJ0o5g*kKkg0USe=t~}>tQJ{6U8y-a_j@K94=or{U<^u1gvu}a
z7hgPt934o~5@+)YU+ut@$#-)f`i#=8(C&!(+cEW**o1>1>}G~b)k<ESXBqEmyBH+q
zcDxrPPm-+lEFqpFA0LA=&RDbvgQ(Gu*`;WuQF{FW6{;KNV;z4Nc3B5+j?|QF##X*M
zl{9NMwC?K7c!lu-@!*9rvXXri!hmA~K3(M~&b>e|-BZ$=+Uzcfc``k`YH37FVKMz)
zGhiIC1=Mg4j0Du*gz6E8H5sF+%KY~FEQF}5+j`2nuIZcx^fy9-rddiDbXoSr%%<VA
z;o;QjvqZSSuOW~bIp0GQBd0W1iBs(5F<_5o6Rg!tSVsyFfjEA}R6N*42fp`kp(~6D
z#Inq$&@l5@JQ=IdRlbiM1-@4FUd!cBmwnAIfH|b=j|#EIz9c45^Q#<ji8A^DyN||}
zmu#c`QowupxqBgapMz;~HwfSz6-knQZ_DTdq~O#}=QDTZC~aF6kN?m>chO7rZy!7!
zdkz17@DF`L*+JO>dj+}?;11)~L+;Nl)yoP#95;?aOfE{YU68~iR)=ipz|9n8yodCY
zUi#<w==%1tLG9rXa8A0$0$Xv;MVZ;oRjFEn;--zP8^l3u02g%#c-sIY!?1mCpFOLk
z{qQEu^I>_4sKSFL5_hXsz=)6={(d?>W1Dz3#Y>S<q=f~_K1f}8G+1Bq#k`31Hgp1$
zDifoK0^5!|l=Jt<u!YZLF1|i-yU19T_fO4IWAD#xyZ0V>#>;Kq{DZmX%CZONGo=vU
zotsxFURG)nCg7Ve2i8k~eL6Tb`<;tb`0r(a8&N-e{0$RIJb<)w-oO#F5nNP(ahKUS
zHv-J&8Fp04Qn9^jD$5!qa&pMn5;lbQ9j2ygVoBI8pa1<Vhpb<oauP{SQF*K3=cT)=
z_`<L<JeaINENz@5>o_fx-Dyf7q6xS2os6s5G(VSBZpq`dAoqM4@PrvdkdFdC`SX=H
zdAK|n8J$Qq1gpN4pp#sPqw2>RGRdbN08zu)Mp;-g2IJr4t*H^=VsfD$(Q@y+LU@i1
z1wnM&zog^u>~c~44OWX|BJ^R>s-lFEpAuOm0&FcZD_?!X8A`D5$9gyCfl;s&Ut#%M
zx98sbh{g?dBkzX)!nr1BpBF`{k2O39EdmjY*g7vcZI+;BCZExbI6y%992+MR3(}x1
z$eJL)J8$ta&S${$LX;awxxTl{5Qg{=JEStsUEln90x4rIl>>rjc92tXz9I}mS$=}W
zpX4KhZe4*cy#l))^QT{7Ok<JCtK!5e<7Z|C^;4CVAp93lVhtA?i%80>xam5&flQ-F
z(%N~PGCFn!xWaJ{+EX)VYp@z>q#-rUC;7@}dVC)ksL#9b-)bJo23qA(7+8JlhqU(b
zwtcoPq1~Itn>Hp<B^bWd0*yzdyQx4xNIF|b`YuyQ4Ci+@=WD=W)dY=JhM)SNKhd<E
zGx@TFE7d}AcNOxmt?f#%Lmd4qLFcveSq$K)VdvFqXDSC`kQA<}ts8zxMLw~2plmGq
z_bXwYh0k-PY!8+lK>3gfw|_NOyoeKZDi5140q4GSuQ0de!D=)0#lx!aP&)+y&!+XR
zap1N|AI0*Q-|4z5!~hzZ4wMw39}9hjg>l4`Rb7UXTS!IXyuKF(U9q{Z4UroeJ_K9P
z4In6XeNmCPX`qn$_Lu9g5#Win$UUzbv#?##VZj*3i_^fA`da1htd#D75i7dd0z-*k
z#WmAT3e|3617W`!!OObVG|1G)@~0hJPVA}aZ>?C7CDj;1gsX^>=o9aF-qLGf!6t<_
zzW(fzJaQ~otK|cpmKerIlP+b+s577{boSDwelQefFZX)1tBBKxyeucqD|xyGDlt*~
z*0tU36}0rG0_I0ez1B+*V8nJqJE!5Wvnc9*UEF>Rqpem`%uF@^=F9L*9y%Lz3d~XL
zPLuVw4~<yR1sK^xM?UzZ*~tI(FWa}cvcT+?4Kv5wM=^bdEjq`^(IzXp(K**p-%8?K
zJrdeytL{J}eLTr%Y}439OE&9V5qSL&;3)RcBI^fF{#|4~URGLLNZ$BToJzZf0w*2}
z;-P&1j~A*FjG$%B*5?`GFU$TzBRl?nO<)7-ej5jKUk;~hq^@yaT6;;uyVH_g&p30s
zpzx+Ml{!cZ4nFwZax(`xnUec@YWS_g5~G$Cl4I+5vb61jQ6({30A}pa#uNYm)K=L7
zdB_I7^M7dEln?{2bGxkF^(4`a+T89R#vaJ~fp%ZKO5l^`%Ikd`5IM$0)pOR)PpRP?
zBibIfrmxFR9>Ettd_{LHPM{sO$qQSw8|fRIM>`FeW=oEL+?Hd_k7L=!Ti+6~)KEEa
z>RuJikV%mo%OuBF+F7j(fLhcOheJhb9AxvzO<Mi;RN?4AqdNFF5NpS>>t?eitUX}i
zZ}b}6HWU68;lqdO+)`-3(OM;`VfPe!elx-XrktE;*1Tbj-!qz@<&Id|dnU53QI+pO
z8GwkVyHHY}KT-?3zU}v9qmS)lJU@-geo}kGLcKLw;?3M(1wxLqzZS&*nR@lzH?H33
z*D1M}8eHz$DPS|;Rf=`ShYf9<@j0T#JC(+_#E7Y!%RO&RvBa~efIH^}y0S@u@wJ|u
zEP5NjOeB8>#Chm!WZKfyjY6sB)IEJ=wd)N%D_7mH0P2wGWW!~IKQ<QY0+5W_L;1)N
z!O3X(ck=DSNQU_^Z%Rovqw$gxO+7h@SbCb$>)3<_=mK`g!;|e??wqVS{Q6*8C2r)c
zP1Ro<K9T!cK^=_t7xNsSdley~uUe)g8FBA?&^Us%#neWT&^8-P+!YrmuiexTPX@ah
zDp(R^U7&MO)J>0I;&W@pMr@nDNrHPZ;(4`9ACHyK;z%G`cr>^$NLjQm@q_Y2%q>|j
z=g&7iY=p{h7}xD3eD*TlfNE3%{>a@ADBOyVcYvl878`k8$JwgHjuTErj7|<ROlqat
z{Id6J=mIZ<vXdJ=1IBTi6;C`65x!O)9N&z=E8{!zFlB1;Zmd6eQumWP(xR@L6~J}E
ziAI0J@c2@P4LVz4H6{4<4dc~wr+M=+LGD|XD)gQ`<e`V8U1Ri@h1xWT3_ud<7?ea)
zfaM8FKhTetF#Qv9nNFNYFre;>L6Y$P1@GQohFc;w6KcaU29`Z=g?7RC@qow+=$hNc
z5B=v!F>1|4rZ4IFBRjTTQ9y)BI>um_asV0S#LqN5knos!{ElJ^XH3XxG$fWBKWbHo
z7I!@>7jQyXq35&wBJd&}PGOKPKqrCTEAfz_JASO4hTDU}lK13bpj1>NzYKVlPtTLG
z_vH<^NziHELj(eXu4zkMFIgnxg%EfM=y4f^_r6fwrb?CH3o;;f^<|MMu$1UCH?*1E
z4rgk#nr*?1c-a!liI}W8{hTeQfns7h`6^tVY^S^5=S3;LQ)}>+Hx`yWH=7?dL{&3N
z<R8mHv}--bEj8c-s|Mt*;p+QT#B}(UEx6a2vN&u|z(q+SjiCi;gEi{x{&0?M5raN|
zm4V$D0Nu$0KiCzih)&BpKVwjQ)est>P91a*^+O-%z3gmpPUWAP@?L6o*121Lv@~AL
zlyQ3}+#~lr0V!+i%@o16$wCWwvcu|8RciMOXcAwi0%j^|>>K%FOHkgrpD$xRkyICf
zLSf4vb5c%mXz!>SRJpil&I=(+gh9Kiyeqx|^-GeZVJ|5-rlRPjclhm%wyFTel5n&R
zD6$Glogh`7RWai9)@|?rp=)ha{)9K@HS-t4R?`<ho#YP`YJ}6KZm>-dUW;OBh14qN
zV`ncJ&Oy0*#-n{Jt=6ooiEC8drT2Iw7?JUkz_{^L6uG|l|3V)G;m$s|8?|eQjSB3k
zvY|h<z#+`7WPQb-phkFTj3Io>_ZCR3`e%&O{;+rVeeC1SO#SvQ=hC@<S@ETX_%mQ(
zrxG+2|J0b?W8K$XprG5+uw~sJ%S}$B8LOt}vNTt>RgRHwYuW$xvMf7X)snJbt%+6>
z7^<J8!`_rYj-jE}T#ep<n)Bc0Ho;E!v)X;_wZRvHKkEl%9tHg=3^+rT-?D2@;?FBF
z%8mBQp=*LVDlQjq?SYnkO`xhP){opmtZjVt7+VH{de--`kx~Noq#~E(kSUD7AM#J@
zRt$-BJg2$ymN<v@m#-Vq6UVA5_k}9v07RAa6hN!j!+QPGb<<xu_r@d<C^E5+3S~q|
zjQ5<3wG;7AmjFP~pyy&l3^3}Ey4!V9n`{ofp#QPuag9UwZZm5Ul^=%ONBB5T0(N!K
zZeFv3bm1H3oDT9Sxi^o#o6WBUD|S{QYsc<nB;8k}X;tF$3US;zs3#M#Ef_s|rYrIe
z*cS%JjFOEQZnKwO5cCGhzK$(3E<YvV5kN3F$@whGhPR^hTZtaR$!O*e4tm*1J(-(=
zN>_*Ac47Tu=qNJg5q?FjkyjG@O5ghEGUTi%E(Tytr4~X|<{eTn5pzBAxBOgM^7Fcj
zIQ6z4mkMiQ7aj>Qnu^@=Hr9N7wT8hNnI4O!CI)*}jaq5wx%4ORg$|Fd$i?Ze^;EKj
zrv+xv5WJ;h7wCN)wk`T5-&hEz>YaDVR%Hztom@vm7~c(*u<-1$R+2xTj#cdvQe@pz
z6Wz@UW&@N089P7fLc0(i7mwmv<2K)}{7;Z#LhLDApnQ6!U!X!OFucg|x&Ap=Y6)$(
z)<mHphQK?#L}x_4MFIdut*(lOLTnhG>zA<x_y_*unEx7QXpJ9xWREyU=B5LJYm6=y
zXsCP!S!8sI<HKP^D&9`mMQqEKBP8q}bUMUGG++3L^*#eD#DcG2Z>9Y6#BnwSaAI)G
z)l#tr82ZQ0dJISPJlChK`kk}B)FnJ*G}DKhQgSCJ?yIO~7-w9E5WN=o_6IO`XzyC)
zbVXPu!25Rqn})@PiDd;tl|p@j#-yioPfH0yOF?(I0Y8FV`8iN8mi|nxK+mdD1|RiH
zV@@I^VK}cEC%flK9`fNc-@kBrKugtzf(n4PGbGm#x)Je!rgj7T6YL0_Nd2Gew&FB2
z>i3%AcAp+J6g|9b0b{<7ca|Jwv!iZH*T7Zw)X8@z)DA?<)4ItYHQO1wJ21vymVw8x
zS&+R@ZdG;%oF@+M=Ciu6Uy}|qh8QROLB@Zcmwu4}xPpPxMe07Xxv2s;Pe8Nrj}1+G
zB~%5+KEH|6_a5cRR>`z6a0_x3bzIuf7(#_`Fa=h$YvaZC4YD#`6|P;)#r1U-0ae;2
z!40+}t+)q|<%rn~4?kN@((V^a5JB2(^?0`JeY(#$dfA-zFoWKnZek5$P$X%Ja~J3J
zWJD;V`(p!=SDMNa*LMXgcAsx(LaDG^uS*SenipE1?@4$}VF*ERMhzpA&yBQz=`upm
zwZn34`gu&$_oK#qPYg=H&_~|u8*&@Z@24*}&{e1QM=o{KK3)Yhm6U{jAn=CaAj^NC
zUUe=dF|q!G=my1=N-Ipoy<m6NO~<y?A)mB&HOC&_CAKj+^w8UgoT}LZTk4SD4_?N9
z^MJO$9Mrp*S@XAC__!&LsGIQFQh7)#6RA^rpPrC$#-?DOGl^Z}MNp*Feav)%?Oh|g
z_@I}>*BIg=nP@rFMgI<$IS_ch7@Tg!Cbl;e_jEm=KD9Z-x3O0E)V8qlZN|uLq-)(h
zG?X0U%K^2rm+@L6c20{!;-iVs>WI-MA_jx1@MYlGNc@gA*GHA3NXh^alv|&L=X1jY
zJlXjI`Ue^LPm`!~`S}Ok?9#-Y9wTL0AO_Ro4@4}tg4!Tz0BCf3sBm#U$z>MH!A?8L
ztA#}zwxPK`vMW?9^4mfEs<tWOUDuW^Q(enrl(3Q~*~p4wwoUn^ixF?w2uqVUU3hb8
zXrVI3Glemu89llDY%Ap*4flI4;bNiRMa4=+1io|lq)%BalDd2_f|T_@I+P!;T_R4$
zBI^oi!Myu~?^a(=4!bCsH)+@<hLVLd(z7ov_Fu&8m6*%1jmCIYt3ADRLf>QD&2uET
z$!}u4JTkhQ|KTCR4X4(sj}JxE$W?;1lq?Y!MZXBkV|paCfX8eCXZfr0UNHxcUf23(
z`FrXV8=W<7K0jD)MjAVntr|7@*Bbe*oM8o^<F*(Tt_RIG3QQFmVrmfNJqYSGPI3N{
zr71DGQtakvjC5G(oMyyXOI86hbyBe<0<(ejmBG^@gW4TEl)(06rQe^+Mm2*s*m{76
zjVeFo?H_?b_trgOu52%kKF3(*376KV^x>p*TqCNO95F<Bnix6MRfT%H>fcZ#(*Xi!
zC!FttBIB>BBHfO@a1Y*3+|qnLcmaTA3!O81P}txHuhG>T%1m`Ds@Bx-9pmpc^&e|0
zpl$rBNkg;3JulmA{X=<aRUMbGPPvHlw>6bL38bmGo}Tt*9JSRg2gn>8s6}v{w^9&J
zn+5J#F>EhypYRL$Ua2bC6|dLrNi;q;j$#(`8z`X@u5b=D`b2SA*yrKIS@_pUyi8wC
z(iLfq`qRP@+K}Kns>(6mw!0PjSk|qX+>O$v?K||Idj!n^HCOAnBU4nfbA!6wa&yKN
zHQwh#yvRUDaak<U6JyG~BUfh}TGmq%b{6!fQO3xl5KPkQ6d*}@X9g|uj28cX^g-fp
z+v7B%Ys>sRb*Oq3N5aL$X0Q7W6kNx45;OO~VP|PNK$~WHARG5!S<~ft{O5uZyPnry
zXoG@+41UbO)}q0^GoI6@Xan;^Vw}4EI{Uw3htS2>H5|5N>l81l?^6-}YKl=_yUn8;
za2+L+Wz&X@T%!+-d=2;_Kttmpy?uV!j5UOgz=Ld1M#SID-@BDpdU9YS5pO7_xnyxk
z(g$kpezGu9BU)lY8zK@7o-CxMOE*t@<l%U+r_mB8O_^GIs4$}L`0S9QkuU7N8m`$&
z0$8rU3<H}QP61Y4_ts0jMmIyjNRF6fqfWx!f|8<l?$KAj-x7G8Vref3iNUW=*g==F
zfgVqCW<8{_%n-Fx8S9zq?Kn?%YICJfq#LfTZ$4%08f}#~KvKDVn-H2}!HyQX4g*~W
zVMb6<7irVx#RT+yjvxwMM`jM=(H=T{&Cy%wbc?;}5jAy}LeGNZr~=2NfbYfW_8^e!
zdz>=iYVpLKwXhr=H0S2u3hDUVXBIR;qr?WEEPNPS>a};a?x$34e#E_06$7klaw&t-
aY*^xaHVeNliag`RWN>&*oXYUu!v6p{hif4K

diff --git a/tests/data/pseudo_mapillary_dataset/v1.2/__CRyFzoDOXn6unQ6a3DnQ.png b/tests/data/pseudo_mapillary_dataset/v1.2/__CRyFzoDOXn6unQ6a3DnQ.png
index 018a53b3a46d2aceb3bac0bf457dc0829d867f0f..2c648b7ef82f997bccac0595e4b6a25c9f00c9d8 100644
GIT binary patch
delta 233
zcmaEGmgN<@VrPJ#J1>_M7Xt$WucwDg5Rgs*VGd>>>28ynwo#Fnxt@Vxsi%u$NX4AD
z*Di7%P~dS53@_*}`~Nj6YC@EW*rzK>-}xqd7It#lbBoKh{&(yOWhPbUt~Q5CCDCM_
zML|ueKc==wv~g|Z*#Ak{Wsy$HjMJ)7>s2S**mY>J!1j-fAEk3$5=;bJ3pLpm8Rod8
z^f;bd)!%YqMz=<<l#*$hQj~47%BQ3wZca(de_CEL7QhMI+1-|W?1(Ab69#lVgQu&X
J%Q~loCIF!;Ph|iA

literal 75488
zcmeFZXIN9q6EMCZfzYvoNQod-1?*CSAkw8MRVl`60Xsqz2rUGaYlBF)P}Bqj3s~tA
zuLW#?2NfGd!E!`EAqWV_J12nmcc16|fBAoYeI7rYow~ETGqbZ34!b(r%1J9rBZTDa
z?N+TtNP&xx%q2-Oj4W)~$3TdTTvxkW^Y!(S0NuNH@Ak=)H~2T!hox=ZdWLN=dhA$D
zK|#T<f*b~e@hR;X+k(A&_imx)m$c2BZES4P!q&f=W;Tk@DB3)VYHHZ*(a}+h0*g;M
z3vD<zZjX*;3}x&{&_o4lqoeF!NNw}68}HyBo87FdySYG3S66rT?Ae>yISB~aY)-=p
zHlI9slFeo#<oc^XO&}1wdxwr4n-(fVO9KgJn-K!U^$2}JuAA8w76|PII)nr?8ZAtk
znB)KZ_x~*L|IY%L+;2}rLdbrVrF+<!ZzB&A=GcekHucO9Q_<!ww{V&{U|DN?VW=wK
z?HMaz>ziFCyxccmw%1zp&dKBclTF=u8dXn52dGMKs*r`nUteS9zWBO%d-s%=Kh+Pn
zY-f|#JGr6OgZJtU-}U&YIlbTY&sU1EY~jaM;z-T$$?!GRs?KLAP1>}Yjgh<J_0e~W
zzuFt;4RqG!eljOn$`{v17m1;4igxsUR!du;e%I6iOYU7cq0(hkbn5tmSs4TAp+o+*
zUfkIN1&&HrPGguj+xnZ*&DhwOz1O=#BeiCWNd}i3j-EOL<rW+7DwiJ&y>h89DzQl4
zhOrL_&UUAWv)ApCduOm|<Ycd7RQIM!k0*Pdrp2HBLJuS{Oz@4j@phZ+<&UvBvHPTe
z)4faL?1#MS!9#9Ck)P%qJx}q}s(Ej)ux$qVl$7<^P<6wn5b8R0?II0J`Op)mOOR2j
z&@QIyi+;A*{TbWDIwrRV&3brN1}(C$69&k4{=ltvrsx#SfQg>SDn~|%Lid<&^=jGX
z|Ja0!?EqwT{EiH|ZeRB^F#(XTyS2MoaPLO(J{zFb`t%Pmrnjo|6r8wLV5wzEY8A-n
zrZ8s(jJY_T7#jnoMVwcnu|#_jUMPWAl<+&`_bZT-9W&k7SEuH^Cl;rOUOtO@qW-q6
zp}Mz_7T-ZJe&@jYE+$yXN*vr25&4TLTt015dypaiOa{r|W*-wlp}Uhs3RUuK4bdfD
zcM2i9&Sp%X<g7|mlyt>PBuCj&UK|*%X8jZstYyiI7;YY8xD3Z-kR!gljbIoz#;}Q(
zXNczU+l~<o6~-7AC#zKf!vswcL!~i>&a7cEfrClH0HGn{&2y=FHr%@-JgO0z$7?$v
zqRw^76#NCUU0Gsefr*Lye^BN4I)HlqGh1Y}3Dh+#3R$4fs_nPh0bG?|h`6fq1B}q6
zbDtwu+<1_ukh^A#>spp1S)jp6_z&uQemrnJ_c`o8sBSE2vOt;TOrQ?<D&Lp71iI1>
z=7~_5fEr)NUvoyV9dvaMlO<5)2~?rGGGFSFE%&aIbv1$75d^3@F8nno1sp*22$ly0
z%4&ZCYS(JzeNyx6xp)0Oej;@3-U+DHwY)WHf>Q+7oxs)Pmx$|^Rm#><mmGlW!3TiK
z>)5&C)`I|fo>P*b3{c&+g05=;b<>W>4`y#DQkPbPu3EXEKyG&spi&dgJ0%J*KwZlK
z3k3giCQ$qD2D)h$Er;#=JPJlRW24>I1E*>hnZSv79w9*%oGMEoa9iR6lQr11c+;<@
zaU_O^U-eMK@sW-4{bq-@&KG+;wLQp+ZVTcrbwtKoE6l62NVKxzsO;9Ir;`|y{XP%f
z-9?WQ3syNbr9Ef`en%Ev{9@9o{_QLNdDJV>$_I|N4*evFF_TUmPIsb@d>?(ZH_(ZD
zx07eP2wgh=`M~Inygc=hc)J{d1I)phwG=GFavo6dVg0%jBPlL@X%&H-w+J>z$AQrz
zeqQ$Q2D&^QoJqDYQiAQlRQ=waE)>Q+-uuOh*l{|GVQISAF;%?0Y~MsHb&;y)NesED
z&qL*^^pV!9%VS>v^;uzx1Y3)l)!n^c_${OwqrB9td4K4dn=+d5Ec|xW<uA|jYEz}=
z*>UfxT7O=QE}iWUi}86Dr;yn(#XAX%C0)A>d0Th?_#J9hM-Mh~WH^B&y=D0%#%#a5
zp%yuM-;F!Eu^!;6_|JI~?EB0!T`@C+^~u_&DQV!T(pH`aNzZqbjjpR-<Z^QL6z_Ce
ze8i(C+mZL$?DxMTRwSBjykW=K2=>!kc!|VVr+R3pd&KN}&@;7IJ}}J}+>l_WF3Ik!
z>hJARm~nZs_Zje&U(GL*7~#7Dh6?*C`WJ24MDYZdlFLfmfpWGbjr!LOnY-Lrg<w~_
z2=ynUsvD=iRo&{nl9(hnneb-&R9_*1`f=@{!p@4ekj;xIgp2pvrvjr9PTE6tA1hiG
z9hgfQfPKBIZ`Nxhpw5>dMjOcoW>E%UQFrwz!)Sn<#86^WMMG2GRLTIXNz^{&H%Oq^
z7cx@4yZPhG29j6>IMfY(hnAx6u6@3vxz!u#FwKjPpGzRMxmg`8Wt8wTbG8C(2k-c+
za>#6r*~<uFSQ(w|LJSR+!jOmQ%eU0<GBdUz46W<914CY>FMRsL%1qf*VyNw*9I9|N
zeeqTzyv&3h4?{i;uSG)*J}_j=)`214yYFF$nS3J4K)zKE%+k0!nv4qFYkT*{SY*k|
zw;Ef@_c!ij6JrUzo|aj)a;?)X<rf7m{)fa)|GKqQEnZ71IAi7c+487j?XpL2LGdMQ
zIgX0<v(3kVDCOyoJx(06Ol1KCmg|8Fs!43Gg50oVHJ5maBCwa4^08plntE<#vqnur
zCg~f*UX8x%DkzM<l@oJOp@+Ezl}iR^IP@*1BLDo8Ei4rXavKd^^a9G+&8(P<@;%JI
zPz0#p)VT^!bWb+59EmgYQxfdvsN}ktU?lcu2krjiH)<~Z;z4l4r97PXq1ODQ(vi!H
zYZ}5yDzj@g+8o@Zioyyu?~Iu%+r#ul)gaOBHKRo@cny-gnDM$rxcrhM_b%^|&5%KU
zhnR)?{hHsNGurWMNPcR&(dBdRZ(DUeLX$ie6!k5i2hOSD$b+HWcc~;=!C$^H7o~fc
zUPuR6u6xRE;g%U7o`-D5o+Xx9SEO5~S<1Uz%=kWQZKF85<jA_q)f=~f>AV)SZ;<wz
zfqJAR`ihUxTy(^P(rEFo{jz%uw_K4%<O>-MEz%q_ziEPP9F<RAMSIPrm+B(fvwt~k
z=>EZUL5h;W-WK<3e|Wc_Lq-RV%pB<q=H`Wnm8|664R+YiZ87naKoaf?Qmg!6x~owm
zpu0R%?&*G@y*6|vQgVIh`m(KPsipkfuh$Px^Aksh+!vgv@`HKUqjafY@3rYpyiXd)
zDECP0aHj(|&q}PsnS1vfYp2HaM#Q$9zPfFXBFijuvW2*%{Kc<V4^Q(YBMA?qV^x{3
zp4Lc<Vtnc1h<5OxG%~u<aem<KYnsb4iYqv|f8H2scoiblR%Z5h6~5OylNQfkvSHN~
zKZGRqhs(y8Dz@Wn^cB?g>9B6cI>>?=1DB0-dGOFhB`=TGq&8C7C;T$+wA8{bRAaB@
zsH8Q9O*S6wK}I(&PW4VCb5sJ$<IhCxLrP8eNs(qX4LEY2+Aeq<xck=!WK^-E!Hd8d
zIQvmK`0Gs)BeL;O_cNMHD7l_ZqegEpK6EB*3o41*aefT#@@wVb;e({s83uCAo8Yu0
zNaV;_$`4~Z<&1y-gMwtzB?{HxB!2h0IKTZ%hnT?6_hdO0mQB`T5eT{bVoI=ZAF0*g
z*OMlu5$co-ZY}n7ta%1Iq5R9j(1uF1cur013g!8;sT*dX-RG;HJAD?bPohzO2i`cK
z61fhQ9G7=n<|kv}2F%Vsn-cte3#rxoltL489@-@p+*-JFZq56T5~%B3-xH@|vHA?4
z+<u*-(y|-1YAYwcW9p;J<7huRCD873oh44`V)bWe)aJ$OEEBqxq9FB7iOXv7(?K(*
zWV!ZNJtP#0ZLRs8(nZN3Tgq1~dLSW&LZ9uPmb-}b#ga?zb~mKiZkUd`_^&6e_7bZ<
z2(0vcEov+0p?8kw2h$TMISN4LbuH#hj0Y+?xwOr&Nzy`xqY_s5*Jw%4H56p%bZCRg
zWVSyT&Hv8ty`5kl&-KS{GiReFP$KT}Q1yK<kIy!v0W1~?HEUuO46dlBZ%{(J`O)9_
zL+Fbgm#psVvqIW`ChFove&P3`FZM9xw+@B~EY_z^-w*ptpMbXNe%>n_M0jBzI(^<J
zMlCTiu#}HvMvv&SwxN;}Z^Dar#IERb5^zDAhp+q2f8~=}Z5*nb5;{lzDHdy++%C}3
zDNZa?q_T%DsO*1RKJ-x$J<zC$bt=D=*lQ?(`aPC+EM3-L&`3HoyC$~n3Z+zo%Fy0-
ze)o<&g;7fwk{p#UUGK8Q5Ltf~voQVV*GBRKT1_n5?X)yHmbd*$rSEH(rgeE|(3MH;
z7WeXBh@nGni$3|!{}#}F$;%aemI|h|e`Ar5X8y_Gy2d`4;+KVb>|}~DH+bV+#9s6K
zSgB6=ulo@lZ>9^RI4U)zC0mh&|I?I+lKc%-rM25gDq1zMypD?!XjSU!((2Q!`<;Ee
zWLjyK@|!*8%|esh7PhPH`Ks05xXggPiDEp-^V%+CVfQd4q9VWX9iycT$xm*#@O^rl
zgru~rx_;#PGvlLr#g?z+lF7PnmZO~Vq?!F;ZiQv{Z%2_-U|uBmT`H*FN5mk#X;X^;
z{e+Vz`N&fqeYv>#5xx0&$L?!;HllK=U<PI1Tq<IEEc^r-91MNEYyrEHVr+EapG-0`
zDaZ(MS=#qc`M32V7q7JPeJu&mr^}Y<oMwIW+wUaHFtn6Eb~YGC>}Y9;rZ(%!pG${q
zB#IJg)CaER`;f)5Mjc{wVCj&jMA1<iRboxWeq^E3X#0O14IoB;nGbE1D2gX=D+%0m
z5$>@0(0+-cID+qO;QN0cHB{7TO17^2ZC*Zxd&sqli7X5isl@1=<NM|07^i8}L-h>M
z*Z<1XQk|o$qq92KD+{zO<z>&_$4DsCcUFkYjJ_Gm-rQWwh73!|@+jEhSLwn}S@XU+
zbzR@F9r;j<>#O-r;>ad+<0JaI=d+pu8($&+sqGdDvxXebr-IqusBv7(-ahwf3aopB
z{HL^AL@4Z!eQJo<<*!XCD<W>?7ne6=Rgx-Tr5<E;ikaS~psp>WN|B%O+~yu<Qwi#K
za15tdSEaxG(m*B2<dE-$d8b)#eL6E#1mMjA@jm^c?u&@A-DO$dtAnv{g6pxD`b8Z_
z5o0S1wen-lVW>XAgVEwe65Plt{CdZc>?awVbCzDtR--cZ)p-(h&Vc0HOBX|*zK3}z
z_|5oY!zDjmyg?H&loLJsYOG@u0AY3S5;3IRv(H1pcghzBF8T7}77fHO$oA@MZX~l{
z)^jfxOQMY0Jip5B7wj&euxnElL%G6@UftpIX%<}auEqYd5yP{4e_ynhm<Ax&v`rU7
zCHk3g380>`D^x;)H0BWm^U|pN3n3p&53cSx2Ze`7Xs1J-Bp68olaWA0^F;*8c7{N3
zOGI!Xy%~(U3!g#)t`@922;Jg4Qs4wv3ZqHr8`l8ROmZJKB#w%#%7{Glxns8?63B}P
zTn#HXAY{rD5tItyaDO`?BKU}P0D-NDAjPo|2-L<13@ZH*iunH`xSP*%{ox80x-X)y
zeji*Sd@9i7sOYAxpNrU<30tfl9!1$OHSb10F|>SJ%tH6uGrnihs7G#Ypdoh0&yOqP
z(kZ`TyIi&Lfdb`rulb83x4{fPZci6SIfwnO*1w-pv>0Ylux<)s-`dYxSvB`g0maz$
zV&Hx<n%}8=P@uJO2}k9E2fc#CW|^*>9k$K;5RJP1=BZ|6k=f~N=RYeAyyN=L2g{(C
zXgc+pSG))4<N0_{4yC-hbm05Pjnjer#eT>@8+R>PIV{0|Z`~J>95PberS%UgMn}QA
z`SO}7sATi`NfIUE-Vk>j`ZC@lf%vRgqkB#QSYX$Jx=B=2`{qlW<!<szSiiNExyw;d
zZHJlCM{@?GtGX}tK)R|^aV&0c7e$2NM>R%4&o3@j`r=6-TzDSNC8O#Jhq$x5CDMR{
zLz505+`G6~sbe=ooIr?4A|omwT<wzZBoIabp{V8YVx`V#Ml^_+qVxd?78o`#ZVZL*
z&C{t;uz?6B7E6*xD*X%P4wau(EDkq_W-R8YlxQy~C$U5PbMJ(O3WwF|sFRMZ;*uLz
zZC!?f9&{{L`kt26(!!VItbwR_uI9T0at_Os&}?q#Jzeg*(g=2y@3f3}NT65Pz^FOR
ziVn~+rmO?57kcXfH6l~Os`+{E+X8(J$tmpu54tUc`eqwt*)X4gDuvzP!M*k=zeED-
z!pDq~w<aUUgJuD3!QC7QBwb+uv+EEp`zI457d%*`jC6a-WNk{XUT>i;gLLKbDW?FG
zgLN$YyX6(W=fGRwzvZLbOccmCFN+n2I;3yqY^4|ntz%6iqlld;mcM>F<Jju@V>Id&
z$GX1|BmVe8yOw4>zf)4DAinOy*U6%9MQbGRx2Al@MV8=bN(|^nN$g!dTe!EYLRgEZ
zE+$M!pzVC4A155iY&d^1XQrk6G&_P@gXc_MclQ~!r<A9#rz}`A$msN~N3^Jz&%!|M
zKyWSM*mWiJ>e@O9e3n_B)j~^CSVpee10*=~6!d5{R!x$617Yr<&`1I;-I-?jOTy)A
zy+~bsUcdrWwDGzuwk&LIyl7Ug8uVi%cH`2=w5T|pePaT&u)9hqY}bF#H0j6T>hvG9
zC0GNXZJR5L^@n;U268-M$IhWAz+LIqKcH@2-v#YJ*Z>|_8=!3zp{-Bc&anYBEdovP
zKWJO9UO?OZA2e-xBHV;TXaRkHYX@3$$@{RWGf~*~{|MEkCz03z|3N#5X#(2T|Dfs7
zlSynH5t>fl*i88tEOXdS5!%|sF@xySQ%UUV|DfH(HUV0o2+cWhGiN_cVJ_5B*zqE?
z&q6!xKwH9L#R1yp|DesIXOP&o|3Q0!B?B5mgyxX=7v~Ugn@>MQVpBzEc|u+7Ku8Hc
zV%KM)f$isIU<*2@j|nxPpC+*jmzL3@BJ!AeBD6lN0nongQ{;7brI<gYKuVtD&oUvS
z4V7ISVN)iib23NOQhqU4tquvi49jUzA$iR0qKzcSt6qe@zj$n5*Ya*==Gd;0!AWu`
zvadh}>)&rvD6&ZXN|pt|?kh)FnfdIZXsa$hkyQ`1fkMz^Pk?ZYofA>R`TnAJo?Xjp
zy^#VbW!QwX@X5gL#|>$0*?#Bhot&ja*kY{$cJzxJVN@oz=rnQtSe&GW0Xvs-v?!m?
z%uek<IM2s<@dUfO+IB6^?K2-sDTBwHi|Y~WbfvI<re`;k!-8O^P0uB<4R6n|{FUI`
zq3+`91i_bA4W#!QHSAiRZ5wHmDv%1!$rPTEK(_}}DEN@E;RzR4M=n{8PhA2M;??Y0
zo`|32a8?30UHS!Bh~|$LzdQ~8)|&Pl=HQ60figu;o&?sv*ZSJIoWE(*^$v;KQR~?a
z3%IwBI$l#1hudMjJIj-d5=Z`y71Di^4D@utndV~Gl~LG-PjrKtld<De40HStXCX+^
zqZg6bhk0Y#@rCasP%gJtJJ5>ID;`{CD9+%d0bf_v0WvC1yP_4ingHcN1lWMPbAAHI
znUz3B%TjCSKnac9$qNA2Zj0M+c8fq~fGSyj4sn%u%A=Z~phdU|rxrk~S-E7?e?nf<
z4lKF|zax*{tt>lC1J81q7jKG;ZZj1uQ$SmLg)qbj#HVr0Eah*U$ohc<CD?RI91u;#
zjTO)_Jyi>%DWaX#hXib_lYAG9RVgf?BAetcH6^(874WI%$S8%`BPfAAK94RWu{ZK|
zP$hIAl;NeoLQ~b$2+Er74s}t8p@P4ReGe<;%=$(~Wcxh%V=i3s7HpF`QnEMM$B2Yr
zl%)0x30yHgc^Oz&89%FlWVKXHf~WvGL4X+JATj(faM#H+F*1j+lAhI%1b<_f$#)@n
z--2%gDt$jwBdD_areq0;X_b;U0ceS6TJxGrjUYMjO;+ngf_m%@SyKek1BUbc%#4gg
zpdKV>#U7H|AXI4KlYyaOlbO*x03~I8M}h(D8Tq^jL{dQSEKMR9t04%?p*NG*K6arB
zvalrSygXABq=0{qoecNcBw-L0?bh%!H-f8-?+LX|B-q7kpgw>&F&9f#MJ0*MAwdwt
zAZu0;taws_y3%ooK6Z6b74pOe$(tbVOvm$KB^}FR7`h-#gZ`YvK5ai1gB5wUu>PjF
z7$+7YAV&x_r!JjL3nO_D##Q@*1akaYlEi&a27?k+$$2K_jxGqZWD$EP<qA#d03j?f
z1hr;isuZh9gs_bu%-!SwgCY|4n8Yr3NS`DNS(X>i7WSdf*uL>iQu~Mmetb8{9$;wC
zN+F}rROi_>U{Wo74Y2SqIY@(LP9G<l!68;9d5p+M@&gb#jS=mh{kLcxL_}o=Y0i*Z
zh={!KF`|?#kmST4BU-~sBTmK`ku|<fB<T<he1jsNP|pij;t-3RI!3ff5(@D_9%Doa
zv+Y2Vhlt4CL`0O%qXN-}F`_f+S&$N4=8K5FH&@x-o`G7AFl8-ILFr&{fpUM076Jo_
z1XK*tRr;e<|9lVk?KbZk(no9=Yyk!8U;}M!2j2BAK}eA|#_nzU%+itR|9(F{uU9%K
zj?m|EaSd$?N`E~57v6B)a`0;-LRajnC-Gn><q0h$(97hpIk@1lvgneIsufqeCN>)*
z&qUrXV-s4zr!GWASz}5^J1A^M4EmVH!zpStNU$B#qlANcv*{;D?E5?`NgFtD>ewRS
z;9wHRkQIR-P9EfGO4`82QO806WMdM`P!WMnlGxiu3=$JZ6~BYct5$(OHoBbHH@o^h
z)L@3WYA=!C0Ctsp9t^F3hs&YW+GEEU1YRexPx9tciIi>yuX-smI?8-6I1c+ZUid}i
zBWIN;5<Ie+k)VnHSYkKC%F!=-Q7ebpARuZ;>X!28Omgkal4XFVSwmvq#k9y%VbiYQ
zsG#Ngstb(>9SA@irb>330L<}QU?epT(8MN_uTKDIO-4pUiHx8a!KBE&<A7IlRgH|M
zTFQfLMj^9G;7&270ZJw|C>Aog9qwdkzr$ylCy=y&+*f*;hDM;bWH4gnF>eceDaJWa
zR{kI4pZ1M1tHBB5&tS7!m-#awNZ2LrN38}}pIGwb_M!^mW^fXkeuhSnD_(R|0Fe1O
zs7%O!BRvi}>PWZ+n{iNy&=){+#-ty0Oazegn1)4V1Zej-=;An)Nck~P*PJFpBdD8S
z9H$x)a|1QXgx&<h{~M@cOxBoL9*<Lz$cseEi>Uq=WP^<{6jALSXUL<1TU5uRWAi10
zY4lel_FKC#8{!YaEH)+^7zP{_ZaWe<<B_qYuq*O}VK52Wm{o?;2>1JaZ0dpy_)PH3
z24kR#<ScO7HP{ca>)<SHaeDyGRW&r41?97}EQnw^;~+00KpfL;GBAR)$t)#n011My
zPO%1{nu?zUD(!Jly4nyDSYWtVFM#Ia4*{f^X<!7~Z>OC?3}Q&)!Ld?M7_wshA|p+^
zc$p`#Q)gjq>ZrysK;{VqfmxUgLX*<3%*cRvyOg&KA=-S^`9^aI4p33H@Ge`&SkF;;
z#cd`b_66ou!99v`(d<fa2lhB4_N0in96}tdQp^ob(jlQ5LhZZ|@lSBv<#20+{<d$F
zUJagd7Iqp0CGDP`0oUZEyigLNX=dshtsn#$l99!#GIs_E1SR=X5u44tAdm(@dX<w9
z8sS@s6Zb+V{2)SK44U+cC_v;`NI@0>`0CgtlEI94A#?@_Q){PrLs{vk-5zmd;etEF
zS_3Fi2n{#PanOGILJ??;Dq9Fe0AWhkG;a=#y5FH&1aggqx-BDbjLKlTHyom$4r5en
zW5oefJVxa_JtG^a90`yY?iq`NDT;-jgc=FcGcpOPZjpxGv9AGCD0Bu;+Lh@UP!9rz
z01Cx@V@pLK=m8R@cTLX#@BP!k5I`}we{4R0@`UCH&Eds~Zv}H^VjW<?69zLfpd`KD
zVGkJ1#$+ACAB?6~DT~ldd~<BLh-e`~2T~5iUx_aS8@jN-mj@dJ*f!0*vzqvZIFB#`
zPusqZJ9CI{hLDWfO6pba8&V0sVqTdC8B<2n@gMly!b+tlkn#;N)dpb;-s<>pCp{}>
z0WtBP_`=U5_K96D@23}5_WVVx<2Q^YfY@5JMlrkU=Rb~jhy`?PcnxRfen**Zq@FkA
zpZm8hCX#~ib&C56DUKk`;P_U^3zijrJ=c}WfO_jI{!=0~_#E#0ymHDVC^tvk$oK?7
zm45VSL1QeGI2egD;F+uBqR!qmeI`ZHAodvp>IeOO%MA+rsh$uB=wClWg1RZO?cBG6
zjLE?Ad?b`8ihmjzJo1;E0SKxE0e}#);qkfee4;Ay>TFOX8MzI(PCsZUJ{L}s{F1m?
zD5JXN+=a;b-f+j>ubXiL34Cv--WX_U<V*(}CteGeLEk-0j?y6Qjo{@$Y$;|cT0)Yt
z-`-^#V(i9^IIv5<i7plG*cJ-0wRPw`68j;)LGl-z6mxv09C~8VWK$1&WxqpRAY$yt
zmvfrIXl}&q<ho<^WFf42B?iTU3}2Ik9Ec^~QnQ{RK|8jWQVB{F3%L^LQ(A)N7YK0W
ze7LI^l`>T=13;7^A*z($A!!1lqVd@vYQCRs{Ye^C-j2|3`&c3#WWjQPnL9R47WP$f
zRF-QH7nya0hJ!6DARSr7awnrj4xcA8d#a$^)yfrCNT99UT8%FqA%DvRx26aOMBkcU
z+SeTxeGiMi=LGK1yeDoP<jf)rYu7*J#?|Y8z8BdAOnq)L;{(Xkqu(a6^>{;44rgTc
zTFReERck?lY1nM>bl<tecM1_<r(tyQyp#haG-|Db%O1p#$BQ^t4vxNDvJP=ef#AIH
zj{N+U@EyRnh3`b>jyrDitwiw85WG{F`|jw_3AheF557+_WA3=n$KV0*eU^FjYSAiU
zIy_=}pHgZUrX|n&(E{^#WqFfPuY;npqn+0P6gifQ?q;R@9mluvJBFZRM<s>0HNL}M
zJYZrkM!=0E*pIDb<fa+;n`YR*)jV5RmvZKVy`lIcb4X4n25R?u;brE3Fe;gidl%sa
zw?!B_KvKzU*{g`3xedOvnz+`&z^4UeOq)j7pbKy*SW&~K2wDBix;{|Uj%7|pGIpWr
zarOZrgralk*(A0&Zz$1{7g9<GMU%4N@;!{rv|DeIJOnIe6SwRqhM93ZUT+C;degIN
zkzfk8&TbDruXb{K{rxI@)&*|XQzX#9!tIvfY6(-@>)##SmVEmrxy*@y82fNLUL}*N
zV8yj^^Xb)&iizmUs6=Q5f76Nm*odi$rTo)x%FFT7@6P{tB8~=Vs>h!@hISWGj2B;x
z`M~RDI+m}4Gh|n$s+ZE$1h=lh)>rlREuC|BJ(!0CA^0KQN)u-HO0Lz-HaDH9>bmE3
zUWo04r?ekowl*K9#jnqM;QT9BT`%hrlz#ciNp9Gd2zb)d&&)K%hkl<6z95EFxblwj
z4mzE1ST2NY?BVShiMtjqje@+(3}5SIUJIGj?%Mw0i+#)Q(@FL)ytZu7>!jVUAnfa|
zF^a?zzq{QDLCE(+ty7jmb;mJ^@y?FLQCMRB0}{J}$?WkkSs$QXv(c@1@OsTAF=UpW
z;L>d0_*D$>zAj^XhS?yt7bf>e0blJGPm7;V*QuYPAcemBnpiic)i(4=2EW4gQ7(T!
zhEN?pnYjix@Po%{xy*nuwAE#+y^`gz7gE8m>LVmYXfC`V=1hFjN66s{`_!!*&E_D1
z74Dq5q0C|snlKy>8{fER1&SoqzBtTpNVcUIS4^9^N`ywnw`aPV7>8SP@6J7IFG7n<
zz0!D+=aZ}oXi3V}A~Z$(@644Z3tzi%@5+>}8$(NSejVXhtyL`*95#FT@w6~I#7@NQ
zBi!(UcDTOOSyw+3P0O-u=N@gpWMA!?_od&=)_<5yLd}kfU4FbpN%|a>EExsf^sLFK
zwUYTo-mocg+SK;%zAO#VwDw@7rdOEDu)k^XpE1pRs}p(IlTd3W^QXM7>aiQp@KP$Y
z`|8?`Qz<A+$FEA$K3xMIK*9{@Nxygbx8v1h6lSP;N7GJG!w+<X;pmJ}DH4iyEDrKC
zk+YvfNYWlzJVF*j!)eYRxXh_j=G44DD0Ka`<>zNI8qo54kjeMql7Q!IdP?-^;U5V7
z_A7YMFu7(q*oK?s7_<6!7!veghu_(k{Z>k##Vcax@xsz<dF1V5lKj@uOa1PY_U|iM
zCY2|L;63Ufe^Y5bvugpA6%2Ww8%*6+sGy<(rqQzGE;G1O+?By6_ccGMlR)$IRG-f0
z4JDkOOi(*S8T~j<LUSF8LoPF4?RDX(_}eAsC+0>OA%->1F-Uec>4GK+8Qi$<;iWop
zbV;}AStH*kK}w`}p809vRm2wO@A#F(yuSc$3xzzL7m9A?(@;?k(=9utYne8*DWwW|
zzqbElD~8fioIB#M_Ycm%6jQR?H#qfMAi*i@V5N`A>x`4M_;f7!YwYVRD)M$KyI#!q
zIS#o`*nE0{T1Lk<#P;Av3>{?hugZcLzRnBtMRXZd^fz<gij=NJGc;>9TCv<o=!sra
zvpWCou_dsFxoRE=B|9t|*n`j61ic!!c(&7#;0&f^aR2bs_988M0klQ)?ybwB#XI5a
z#F3GXUhP*nNe+o{Q#IDx3*AT?eOR6(wA%j2bujE(?7B2!IIlf(ADGXkUqmPusG*Tb
zRRnMt18CC0Ipof{zYe-V=^{W_OvAvFe%-xkb80rGZ%vj#4C%zRgYQD^_r8RNmh_)i
zvZ(cenndsGZnqDYV6Dub<|#oXgf8>Bw?*&%Iu0#9>W#ue#6HbBRi}8{<L~QYmhwY4
zvZ1xRUwH0(VPxTy0C=+4|JCRTf-Gi>bN1*@rmiLQweH`(;wdrIm%S%@;5T!&rLAbJ
z7RI*rW-o6UmBtrx;03~TUq&D>yY{-x^!MLpeyb*dqJ=*-<)F%PD`ME=M4qUQ@$JQ)
zTO{=EpHgUYnRE;~rTj+%RG?NQ4-HCDjOD=k=u;EKp4}<cvuCAB)|B=lA67dF9owRL
zzd=-l8vnLFd>3As_B$q;A@)_ty(Q4i7>%E#BBN<q^3dJ_c|<QlhcxcJSB7cw1JsZ}
z37bw%h8|K2)=v`J%<mQdq*3#pEtI678avUI;w}kaBZ=zQm3c9?b5s)S5?3L%IhH8~
z*&gH*i^b55)UK)CM`-bynC29ebAp*6I6^U2Nm5Hi=q6?<HW%6k?O2<|&~v+ZcrkpR
zBm6=^CAxkz!3JPwpXiF%A=pP!<m{UF8A4rgv|Kk+^pu)l@8XW&Hk(h{2|Z$~S=YqS
zPCFfmB500_!!)5ja+v9Zs8YcY!?%%;x&1QnAZW&m!=@^t*2J-Hp5^-Va1#3?UsLP?
zaK9j=NT9UT1ZocW<?~pw5|l2=l-b&#Y+4o+C>CNj(PD5<MZ(RHHKf;4a;TQ_@q8+T
z>O!U(qJt;{dOnFQ#lMTbfJfa+R2iPk@uOHAqs6yjn;^xsDidczHLqG!Z4JRC5p*)V
zFA>VZb#iXyZ?Yy##Fs^6x5>>zu_O`0dJ@~ze$TJ~;;2fxS_cx)d7)8^ATW)iLMUPc
z;ach?phq=7zzi8(60#KD9VVnDt05&9Rv{Hi6`)8gTrcNTJ|h={`X$0wRCI{z|1q{4
zEbmL)6gT2pY8i0^nJL^jlKop^PfEgMDy4|aSpR+oRH+jjiF=9*eq1#JtkZ_=Afb9|
zmIrk!bPbjW_an48%^xG~X3OVQY9REKR~*97<EY3x?vX|oWV}+vn@fwoiw%h(SN+Np
z<j2qg>do4L&~~2JUZSg8-qBD2K?O`prB!5AFG<vTL-<qfJ9yu_*l7w1TFL5`7=RPH
z5s!i=*g2JZ$!4%<MMCfq-;(`rlHeI1SeC*=GB156n@+5n{{qC$!`?0tKsFAVC?f%A
zqTC8A5YO+26ILl)DMxgS-NklL(RW8ysswQ$HsT-2$j<N?nl9pDi5MI4&Y3wP{ZC7R
z6R%uGP7w)HC$Vqx6t}WHiM45VM2yL}$IP7hmhw8h#;K6Rvuq{4fW}hzd~uYU+MGZ#
zfoa>Y){)qQy#Bw47xyzs&Fc_D4L_(vgHUaZH;E%{uKz*OH2@_yGf-<SW@;pu1Yar5
zn^9{T_SR5f0bi;9fkYX0hoK-0zS8`6qE<Cb#!zrU^aV+C5bmT%?2=l?LStlfL3l(a
z2%M6ET_IH4PYHu%f}owqz|N44jE)ICWrD1TuWob1P4^EVbwLl`bX-*u1!EEO1f9@A
zs!=ITvan#qif0_8#m~iNO@<q`zaNQk1xJMb6coh^^<?Xb5Y<Q)oA52u8Cy9jSM2uK
zqk0FHqd45E;~lZLQ;@r3VIJxL&tT8mCdM|w?@wcZKQgc{bVjbU$`fMqpu1TMmy?F#
zV&OTo1FUS%Iw8h(!%TJ2DD-Ka6Pk;oYF@evYKF#K?Mmp8Fvl-XC3-u3ll==3!;#fO
zX@#0vBQJd(3e&F)6#IUP7QX{4pMfG%n~g}Xz|2eVR2kH4UzmoVsS#Ly6-T4`d)Yp)
zIBQsBGGi~kYYMvoIHok;Mcy8)<CIo?h<hXDgW{;(ixoqG_n3Ia=uUdXZ3*<o(J%o$
zhjie{+uzrFAA^GvK9IDS%281pDv|6QbwC$Vnx~WCb?q)$Va7SD4YJ6KpS}vcfrRMw
z^`~FHG?E1~@y<zXctMH$zTL{?$9x37dOn4?{;5~^r#eT<pq=*Jap(ZV<2@k(CcSj@
zeHCjeg$AaIFx{W$)<Qw*JTD6b_0sp1bkpbgd&Jn;Sh+ePLz>Zid&}47%Sc7Hgcz0B
zD;3uxE}HZ?5xcmPL_8mKt9Ta@GIrP(hNEN9pJ;0P@={w1NuZC(sG)w~nYpPWO@-Q;
zEZj;JTm~hQ{o7E<WuXIApbGg{a`Pty{nZ9k!Exft|0}eF38zp6BT~Twb1UDF;K89!
zj=fHj_-Z8?l?a<91e+<w!>P@^NXdh>k<4)BsQh*)j6kwFmH8y2C6@9rymWIUk>vjj
zK?xy#1u+#XJHr5U3F4kQE;osNN$4pd2nHr6{3#?!`@&6#=!)Ni@0-N#!XlK=Q82C#
zYc3@xTPP-hR)FmJl`3NOmaJYeb|{b~`A;SV&aDg~2^2Xh(e{Q%(BdTjTc{O^oK?Jj
zYgE85o`+t+)YFA;BrQ$~S>k92nCMlSiMh_M^d<?Q$`I{P$VI+M%@<HBT>Mw?m)Rp{
zhwil~2)0``HZ%v>^3!!u3FxJOU!DS0+_zKFG*}QTRw)IFRLvB`2Tf9%7m&iVDvd}M
zGK41Gr;u5Se<~uLPpkM|&dA)Z+YUjmAz0y}4qUa;HPIK?!5i@D)8IaKQxg4xou^%S
zSnQI1r2@&~04+Wgo24fR#!gQ{6j%?#$_%l2nw4TC3rMsSFd2P;5G#kOAz0EDx1P@M
z$1hWn1muay!rRhD*}^h1+5{ZevG#~(*s|(K?6a_p8kJRIt7(<cC?W?|(64+T_RgDi
zlf)i^RNI1;DPD43xE2aQz~uztOLXvE&?X5Jx57JTw8~>UWYIgw$Eq<O19;q$kws77
z@-h|QqR6nrpMt*wCvsAV$rz;xYsC=MJioiM`o)#32sgQoNboDk<jwrzX$UH5kcgKX
zS=g~wkl0$V6SXR*keO-zs}VyBl4pm)2dI+gH3fMm(&8JjSqm+8;C>VYE%X~5SsoIB
zb1DxYfhfl;e1cwJ9pLgI=Iz3t&dhOObtBXaHDfDQoJ5I!We`FeAkWmSv?rfQZC(sf
zgkt;+)|w>m*bV8S1f*^JWjolF*kfon0%?`ltfhi9A{41;)NCvk=E}h&vJr9?<v<@L
z2If@S!Gj6}bnVIr@^Df!Gz~o_qD%8Xu{Zf%RFnhx(IRYUc@a;DA;O(NDaDZLnbbT3
z5edkdwC4KQL4G3z<!D*Td+|c|G1lYaBoqi~#u7YJHN%Ou2%$1aAJ(xVsGqq0Qiu(e
zCExVs53v!B-D1cBJeC-~ORXedI0K<oQo*|1W<0jsJ`sw>@SLX43ypxHe+ayL0^$^0
zRb9!C)e2=o_-T)3We54LLm~??+&L;ocwW(r<)R|DGuP^b@RPzZP5L_$I|8oOT7K}0
zObj~2OW=iK3pN{3_@Chk3qs3RUL2CNQ-B8c+Z5wz4)LV=H7w{$D%PnvyVhh9TMfGo
zxe@GL2YfX;<)E+&n$$Qd4*U>Opa%Ui6pY|HpIR%C<H>R+qp4HdUFZ2JSR5C!AqxWz
z>&rCQJBa=U=$DG$j%UCzOoX>32rG~H=fxn!gJu)Bkz7dMEdy2AX^`S+*PM-IZh~&L
zHbrE?wVH*$L|G0B{)i1Fu*D~w<y(&m??C}$6#){W-wuiE5xW{dNzRij4#NR~x`=~`
zHDe2oOQRy#LR&FwvAGV39*8|cF}{&(FxA_hl?BxZkaL!KRv?YVO+&5VYMuCQ;#<?y
z&LX0dJaDexJfri%Zxp0EyXNdwW~sm(bDN5YG~*>kBD>ioIwCeS8=P{Cmwo5Ma)mrv
zqvmWSvrg~@yFLlgpin}^-^AYG2h2vqxmP1zlpX6<BDSQZydN)udMGUm>gV98e%VnK
zj?JUXkPtL@F_R3`l-9G9#Sld@*v_t6;g}9xfrQGYwsTVxXiBy$4Kc*ju9-cr$-;;$
zTunjHIB2yV9@*yL`H<zGpv6}(#qQW)A(K%Kykn5<6er2fp(_H1$?ZlQ04<*YS=lX{
zB&#_AI>02~F`58vva=;XN+iSrs=tZ1Un~w7LZRclo!2B;jS0{ZruZG&1n90^z@%fd
zCqM~I>YYgwpf<bENwR-HT&Cn5$q5jY4<;R>(Pxs73CKzkfs#QM>`^NK$^HSQF{Lg2
zSqowMaD<KEg||ew8Kw{I_6%%3WiS2^rVpw0Gvd`08|QG>zH!n4zK$kzwQ^JrC105>
z>F5GwAZLm(bOKmSN>e+IP?Th_l1tek+B~{43H_SXZj{56xAY_~MnbrOTHq?2OTs`9
z1TLA4LH`;43<N;|iNp_)yoQ|zRiPPN)1iOTD!wfUf?p}wq;$>x+aVDIL9eK+p6V)Y
z%7h@dvcGA1^jWYRAgF*j#S(rc1v3Ic-ncd=L%0(JK}K4Ft)b}QuR##xbFuu3k}I+6
zAV>ym;ut!46)yk;L1=uC1|1uAbs)$91R40*OyXw2jG!8$<Y#g`r)q-TcWf7BgdYz?
zkYnzqsoK{2u$II8AcD$6%`5W{Xm+M8Bv9j^8CW<aY68?XyUDiRV*;dxMN#}FK)W?m
z?dshoK-yR=h5o;w^C2sf?OkjUTONL<V{O8f_;f%!B`X0TRmc#JGHJ&jNj=r0tHSz&
zGgibcl#`~O@?@ESRY1L^*ulj#oyCPhCKv|7(k`CNHZ$kIzi_yl)kE?zWT%4#snp-Y
z8o)g8hTDI_nfGk@*^~S{m@E~3ilmuo7q@q%o8yE6c4a3HePC;+t0f{tWX>m;8prQR
zJvE@Kk%*iRf}@S{-{ez%EHgOJaCdUXjxUy{F0K@YQAFN6lQ(Odl5=1*{sR<%nC)Y4
ziz%tpOJi-I0MvDhlM;Bdm*;5lszHGWP(aJiK3qO<@&tZ_z1P|d@_O3|{{C2MN;~^y
zQWog*6!baC)VjYs=LPRGkcYrxY5UpFln=DT2SFV1voIiMPhIcEG8aROLA~AB$>-~E
zsmuGr`qL&@oMvkGxks+NsM_+BKfy+)$-eS=cKzDw(3lBUZ|y_Zs>>w=UM5#m2_s>4
zkXv^0O!MQk18zK*s-@A@N$3<<WCiZJ{nE3^mqXYMb_!5zd<o0wQkHyV=a!JpnNDHs
z2FHm}SCbS6v#_MJfW>crT&B@!B(xsrt#H?Z?|o}dsbM>-iw_9dAPIgiCC9hQ|0geg
zTcllsYReRi43!7SEJITa_#NhEPQ6yAI)yV%sKMVBxC}-)&(!mKIe13fw9<n|or5fP
zfL(R{9K80K=a<UwQN>A8s2<WfABQ|_NoL*lg6lr^EDKmasC}kk`OL%DH>FR=rSpAo
zY1?XZTncD1;CFgJBc70uiA@C!7Jvrn3AyL7&-=>BKHjXAU}UH$tKpGvw4&_#mup2k
zxPS#7P>i4Gs;+h6D}2h1tvh5mK^x+z^MZ=s9ng!Cgz7!$4jFfbe_6qAyKG2)H!-S&
z2VnA0GL*(P_F4Usg>mu_Uk4_%iK8-Ovhzh@+vs$2YJ%OkkV~41p14koPN*alIL6p{
z+v#4!5=Sh*$S&8SYrvL;N>Yl28()3!s9<K$TGlF<HRMzCE05}rR3!G9i$kyljc-wm
z=jHBj;j8~Fy;3b$hfjvd!@c^W@NvE{`S#0hmF06MxMevnNR587D^s4+AgTw!ZF%lj
z?poaT-Nn0Wg4Rz+u)l1jKN1;#!(7(caa_Ws{B1UT^{xZCpYQyU;IZWB1z}v~i*FXo
z=TAtuv{WiJx?snfGg5i{0GK>H63p;yalv)KQmddPN)z@SOzXynNQV`*`|eZ!vBqbD
zzA3c$n;s9`ey!7Y&$PPVLG)ETgdcJFd6@9C&)d9SFzpO9IT1-HRsSEo5m}F~wP!!L
z+t<PDbD`7h<k@1c&`DkjsWIYk--aIp4u>pIYgo3S;QJhd%IC-??2zynEDrRTugG-H
z6&_bCUz?a(xP(1fO=Dak!Jf}Y^r9MH7~I>0AN?rzW7@b@)ZZq}j=1UWR;Fp%?N{hQ
z*byNYIKf-~9{C4rf9*fL+$Z5?;ZpVjHBI^)I1<nV7C~LB7j^OY8QJO&>9Yh%btlx4
z5SkBtD(5e+bZFT?)hWCBoo}<?K^!k0?BfXSGv78U@%I!IZ+h)5Txd13%@VVM?Fy-8
z<PWpQY1gWhW&HnI9%p9HvV--9_GPMP*LQ{e)@?Vt)t=K5lg8OYv+n61!=VW~xwiHS
z_K2NEF&3;-c+~gUu%*H1Uo4re-+r9P(i&G5Io(tKdG3yyHeHK^l&7?#`R!AF9{G{=
zpYMvv*?+#}+NFQ8P0gHH4sd$r)R4Y@6x&}FVdnC`-+98`Z&42??36OMyYa6d)Hj2t
z#y2Ka*Q=@U#Xoh|`#l=Q&!y|-k`1%|Hm|QucdCO}@`++>arI5)E{%az5gV3`J8yJf
zzxU>ecT+o~-;cX%@^k%5jr&(7-WW}77>^LH7ccqyJTk*#)1Aj-f<=Bo*si%hR>%9B
zjE5n_-~Qod>F+w`x0`>+3g-B~?HE~YyTSAilJtk0akYue;TM09zOpL!*Y}^OtzeA@
zFp`7c<wmt%=2(8Z%O7z^``%dB*_sUYj7Kr5?!J8gp)Uh=c^g(tFi$nOx5IEG3;(Ah
zZ#<OcV0c((Zp$LSQi}=Z`hL0}f0mgy+?3({LE<xZUv69E7d1E@GRf{`)1Ext7oMBs
z^+yB#<EQW3du{b2e*BB1_S9)fB=60?R^cb@+@05?IlXG<gg9wGmroB)(cOMH=1z#K
zzq!6E=fxrq^)(YnUww5y`YY4j`+oe<skYRntKjLPRCT8bq(>@sZNJ}`xeu29L3(t!
z>)Vy5ZZFhVPaqYX`BK{jNF#UtAk`fH_O0-t+mhuO6N*nWZpds}5?&xdO&-rF*vbLd
zu9w>+dc-W8u<wPv+NR|@gzkMhe~_jG6kM+&kQPrM>F&)nDc{lO-Dmp;Njl)%_456R
z9?^f0E(8^rMC|DI{`fDFSl+qo#fR!VqL=>R6r^ury5pDki}*jBI%?+x?Aeul@mJVH
zrV`Y2_`|m=KSHKwyG%^jz_j`F$j#_0AIJ_9d*xu;!`EIz@dfm(i3vYn{_YHYUl{LA
z!$eYLaq|3&*G}oxdQn#=kfxbrWM&G(Gv0VPCc<g?38&?9-22y-g*tjsr4whveQ0g2
z?c-Z72S4lHu0N~z2a{_1_Lg&9ghAAu@w9-<3^LojgL(V&Bd^tU<A*Oo=gqB^{im-)
zKAb?h5qfS{q2s%dk4JOIV{}fX+un$${WWy2+dIeOG3kxz^kT2b(JZN+M;a~)W9fuN
z$mcgdE4o_>se=z4y>17O$6eAX)0xFOQKM?IJ$|E)`!Wqv$AcjIQ|*J!nJrc6ltH{h
z@iyyUe81xOsL?F>;FwkN2p$@!ft``>)Ozbyv|Qv2V}2=>k>lZuw7%T6cxa^TIkN0(
z>3|<VB@?&~O<leHYppH)Ll$WjW~(JbhA0`#erfQr(;&uh$x5!GV(A<z%GIhNDVKW|
zmk(EZI&r<4oSsd`lEE8Kwv?}bb-$wNedl^B%3y-ViUAJ34&oN{pag!~-n=`a{3XxQ
z;GyWc%zkj?Q|GPX9jTP?k8&P<8ua<#TPL-nU4C_Mo%SeBZHE`9*)^m$Wm&~O&3>0O
zYIbyA_@az&19s5=6nHUb&$5bg=sH3raQCS9v~1ZO7J8LKE37<w?I^EW3t2!WTJH|S
z;h~UKLH8U-B`2SAyXpJy?Tv92zY+?rB&nq%1f2>NZqs9j-V9xo3Pwb|2swFBx^{FI
zYS)lZ7qrqW_Ly8^7*+D7|Dv^jjH7kB{rIgn=W^1$sP}j8ACm0R{-41kFxYngibQyv
zkA9gm%NHJvU@p5-7k7oI8&2@N;enO7M3ud|PummhvP98gg5}jykD|UkzMm@>Y%PzT
zz>g;ud%Be-MwPze)AsCh)ADktgBy1+%;f61CsFMk_a!8IY#RR^+_AU($Kz~2sh+vZ
ze)Z%!TuIM@8GeKr?r6k*djD$Ht4Z`*KsO|zM^dn;SN3&Y6&|OCU*D1Y8SDiKLH(Qi
zSLn}gD{_XP?CL7zpPQRE0chr5qNm(`Mq9CW;ZWh33AWV6b3ZM9WhwNG6o<9e${1!&
z02CXK><=A$z!`3Rk+8vJLZbPVzHiNiW~%Lq>m%z%6n#zTMkEBkLV#aO-v4&nP)>aC
z>W<8ECW|3P{FECt`ObSy-w?U9CJufnKw^6UV!~JbpNH+Z8!7@|Nudx=7CvA2AZGc@
z_J?YU?MP4nQ{B+{*KquA%jl6T$a0EwE#-}p11zJ@mW)OXN{jc;14h=s=wxJ!d%Ks<
z@cpCi@2<lpngKg{YY(l)FmK>!qh9F*`zP%o-0X`#s`HyJR1@r=#%`3_Zy8<oAXFm!
z+5GNGzVIGYM_^fVdzMufJ|9SawY#AWaxm{y8a2bgDPcu^=L};)`z;_eKjryA0?n{u
z%eeBZ`P;aoy}!I%Af*tTgG|Kzjl|%JzJKwVl07{UGXMyGW<}txOq~D{rpR{}4?p@n
z8d_t~4xo3_lj%vYzTF#*O@#^#oQsS{zLvj#bYPnBnMNq%$L*inQyI!tI|+}P1V8Dx
z3ZD})(0L2LL}lowT4ova)NM%n19ph3@Ji~g*e`nb6iJZpF}Eh>0)Hg}#8bo5=d^@3
z32P|m0$4A1t$O=ejhOEq_z5XQ{ElSx$A~zMZf-ka4KATTGEHIH;Q2!P#MOum{hJJf
zT}LXyle)`%SzE<W3P=dqHmyDL=<tt5UVt{TfWKg2l-_;$NX5RS?h^MuID^qG8ZE;|
zgipZkAodexR8u~zSnqFN2W;Wb1TYL*bPRg_fO{%;ov=+dqc0*M2T;58hJ4TF6M6sg
ze|pp`y&XRZD#LDi!nfj9ANdzK(u?pykY<1CiTVV-+6l282nkUfGxv7<ED%A8yZYl$
z|H-3f^u;8kPZ)+N(_@#E7Y{Rl<kToN(eiiQX6r1qQwXIJRyP+P{Ld$K(D#3!w<&|}
z|NAKcKQu>5;F>cY#nH0!YZ}JtZ}54ZmVM!WKKtXXn-@QfF!yI|7emvC<qDtDetlZ_
zzn?SOlmGn;37^p(GOY0M55LC^wCr>L@_XD%8~to)-g5bWhK|C}jwOxa;n^B4E?^3H
za%C74a)wFZtGF6qB>0br2K6T&8C-&L6KuT%Q2p^UTGi{S#`*N6B;qeVuuCa%6}Bhx
zs=-96#3J9dj4oWE;gSeEO$eUVal@Wq1Zd9P2Nr{#aA>w9$j(Uim`)F8?F5%P8FtHI
ziSW0!L$m*IJtNg~O=Him%~ib5z!@G&jMCe)xy4b}Heey32{cV+IDX&o_2t0BX!|;l
z1)by!gVIs?@D80JE&4L>iiD8J6~4rlh2ka5BZ%8_kvRB95Mzu^##u&R7x@`8P-}C7
z_+S$YI`|NDsG?-!Y3-qpp+69<h9CE>{$$5(Dg2l4w`KF^(%*Ip&WH_-M~sD3&hR18
zDGvvU55Fn&%z8Png1EWC@6t1#bkVA|BoOCPjlhkF8_xP4T-lz8|G{0INb4S0zJW*8
zK^D-GZgeurGWxAZ#l?h*`^5*NA_x^52o+yXZC}<UQW2us>fC+Y{-{$_EE!A#zun4s
zl0d5xQrmyP+Jc%Igy^SnW|{5yL)hlToVJ?Q6#guUfgTRxkAWDS>^^NBO|Kb=hef{v
z-a7fUY!62*Q9GO!3>y&ECmEmCUivS$rL!#kpA)XJ75;`9(O(XKRRe@9&E%MQ{t@!z
z(>`u`U&#vC^zh70enNP+chJI^;gm;nF?$1lBn*@R?f(V94}MSyq0he@4dW^<5w;gt
z6Z{E@Gr$--O~k_u9yXkZ>B5heGn|TPE=$5$OxR0co9iddYo^08!@IuG=>$u)aQJ}~
zT1{+$PafRHpU~%tN}vn!U$IVAv^q2BIY!!$qipRRu_hcTdm}98Yxpe#+lSx@HbBMT
zJaT)@YIca0!55Ho8|K%H_`D<`1Hfq*mrG0ljshZnv&AsEE-^TI8-DI0pn%@YEQ#=a
ziJ=BP*&!XB(Eh#~nlD%9ZQ_Q`@A>0;LyT&&M;|fZ%#8bXW&&mK=mzit$O&8$ZYI;y
zNT)}0=fb9fXA6eOXU_1>q|nGBk(-3HE@o(U)Kt{Fd{+DCBNc6Ne8NBGlQ_d~)$v)R
zjC;wnmgEL7WX|bGZVasTO#{l{;W^y{43Xp9&ZB{!)G`nse5TPo;7jad_*)DawQaPP
z77-O;)y#{Q(Yg;K=+6~IH2Ui8zir#meKm=}s|66@&{Mfd?V}g=ve&k#Pak}CORcDy
zSda9{oOdyQtK>X?O&fjHNN51H7^7^e<?UXDiWPHi!2%Ffh9{rba;qNi1OwI+k*4k=
zZPe$@raofXatX)OyQD^;e<1q}Aqbv_*@M$02A_@kulJeo;ZO2(Yg&RM{#G7^oC}4(
z%JmLTY5&X`w%S|0X*gb34>9hBYI}^s;M?M@O^`%5c!&=sf0KVPc5EL%rj5>g7_)sH
zm;CPjXWELlZKXZY+VmwPBt0VCQ>^^^?Sl=!VK=?AUdL7NYRB_o7k>%mj?VwfQa&h#
z*r5_XA-Ho?TD2iO3=#(zbympt?Ab7S&U(2_FcH@P$DBHtT{R5J#_o<y+znrTyoXRl
z$k;_0B+LDT-$%F>%p*3wg=sfu`0k495UaZ`UJ;EfN{ky$ogo8>zy<d-;uPj&wpli7
zWQrSG@XOSQF!!`Vp{MCl|J>0hCNQKzsPOcRbWcwh7%f#gBJ#$ZF$b*^S5X3~l?DF|
zO}${u$JZv(R%Erk7$NME`g6e5e$03OZu32^NWDR$>UyZQ-yM%VQ1m}2HJ>nG{{YQC
zD+@L(A9hauk!WEQN2TD#uhFG#Ta_t;lGbCeD-wfU$49%pq=R)|w2r<#Cbjs>kI6}6
zA=-m7c=7n?rufm3qb@CHm0Q{WWV`0R(5`74r#-?M#vhILdzt@+Cj|1T5%$7D8%s5p
z9?^2TE43?l{jQ1`>TFbx%=c$2IK&ui7zPx3(NT5Fm+L8<JNmX|Xvj<9w)4EAim%!C
z{8nVI-ie9)tNWw4;WlivYft3x(ZnsZ>E13!)hp>(os;@?k-Nyn=G3&L{SF;%tgf2W
ze(B1y#AY?zHZN}7824?{+pCIyhYnTQvHO*Of9d2#vy@NY67BiaG|OmL*5kM<*ovU&
z54lVCBoeVeo1?N223GLu*ju&biR;1tq3g@zV*b8|^HGv$Bq`F&v?)>{q;-s>O$}O6
z4MK=Ety9e~Nl0cY32msP9cf=CLPHdjq;=4nn)artX{K48`;O1|_x(Mu=lOT$+;h)<
z&%O8D^9Boz<vzajcqM1+r@hHYRPMhEZXA_^>qW6HKDeA8<B<r~r>babq0IOup#s;D
zucPzzNwf7vHm4WlPlgAmS=Y(3OoG+BnZ2KelQ8G;If$4;$<lDv@p$VYD(V6`o=M!-
zC1u)YpfNJ-RF3DH>9j9I*WJYr$$|r`JcyUQ*YyULMgBq#6a5Nua97mF$Wgb|J3-c}
zxkQ#-Z*_pJ?t>SN{(A499BDecbwo2-=e9eVF8&N4mhY2gdzv4Z-IJ;xz&Tf5Nnd@7
z#OSuql9B3`;vKMpw~9R~`gEg<4>)gHY3!+Z&pOl7!83-PHhlN0^NDD&buxI+Xyiqu
zm0bRrTFdXYE(!k8dbi_On};qd<_B15z$&A$gx9WoW-`gjfHtx%&+kUQV$|>ZwplAu
z;Ye+&yp4{^+nt?ST-P{->BH1s*%o)B&BKy4@B=*X1p(Q62@mCO?<UkGx`ZV7q#6^g
zKa@-wcJAX}+I1mC9oKe1;*$MaIrfIkv5*U;LBDU^^%{#SN#Lvv1euRS)n%y|!O=33
zrl?D+wGSctMEI#Z$wJHVuqM3R1o-+c;Z<5Ed>)!<>zC67f9|+#p#y5#LEEgOJLyN~
zYxR(#C2JUL4foB_&g(1oB#7bHc99BDf}n2=g0xunEKj~D)k5#qVRhKc1N_N#iL{=d
zKm3nr>0x44<WS-@8kAPg4ebztmN^pR4pbv{*ikdVilUrfK2H-k*Pk7=0vnJ)M0Y!4
z+JkWI9|^EPsqo4+gIVt|CN;h}@;`kWoS#t_&+J*;xe)5W>%o3{)~TsUqo=p8qF&x%
zG`~fj!dg^tR!T{Lo@7RBpThwE=G-6FPoL%CzD&=B{{rK2m{&-a8YpLvMf*c-&%@_b
z-0hku$1b*^o=mH;;Z3}9=KuN!(T36vyc@-dP5@c=L5WMck`WrDJ8uS<FYUUc|1pi2
z-F0sOG6(wEV)logxv-~6p;?VYB*tNUKW{7&3o5pcQ#h*uRl8xT+{{F(MLB)iPxGvC
z$!0FZjXG?O#%N;ZBk*Pv?4d=YH=1cNDKF+FLuYwsUk$!TFiVvp`0}$hI54{`n4RVZ
zW}mv-aL>66af}orSQNqe8N(yi)7vRetqC`P=+HoP^_!65TLu-x3{&69&nlMu??>?B
zH4P-%eTb#~P0QSBVbxC%cqvjy&C)&im-Q*cp?yi12L+~8&nDdB&4d#3Ie9vu+X+x4
zv+zWk+o^SLP}Ji$1LgGkpPBNA&*<%3n$zFuCba7Lhc*i@pF4GXaE#}5YjFOJI*uuJ
zWNieJzKo`&aoG0xoaVEOSe3hm=F7o<BCmh{%izq~=W_DS%CL-#f6wQF|Ac=3{`Zh0
zvd`f7oK<9TjR(AefwZMBY`{$wps?Fsmo_Ggbc!{Ej@nTePl#oT(frF+<?a4U`AH&8
zJuTtsFs>Gzs~Ewr;6{X{v9<zwGSRfW-gW!)Inrl$u(-8_6IsHtJbHUrefzwr0|f|q
zT9W4}<#v2oF2=gWmi9x{d>I=*?lmB86F1cMag;$(Esn}`4OV$<$M=5mh!fclZ&Ai7
zc8J7&!a)H)y5+}Two6C%>`&n2opE4=)yEr{i^}Pw8kcM0shv$Cu&y^|$goxHCtk0%
zAzizZLLBJnQGvoZ{(qC!usi)Xs`Z6ykGS)T{YSBsHYbSn5-iqMROS(a-tXre>oXTv
zVYJ-*nBFXqD3q;)j8eUBR_h2C9r5G~{e8yaOsG*)lGm4O<XvJ*BHo>`KEq!4alIsO
zEZ5Cj-<A|Lx0BTd@)U`xMOY$<)pu8yk%c7MlH`URR3S`G9LVLRuojm&Cq78A5C~E(
zX4#v^h#=BFa3Zvu+J>%Qd(n$u)?~^;Smt-d^kT}vQh=qlsnxG9v*&xidd#uTX&uFi
zC>RZCiPLDhcA{4TPhFV!J)JZ7`29avktN{@uvQJaPhx+(QYvvi|F&p*in}IVYaxI{
ztz(sktFbEY|7M_`{ey^!daur<lz<?+fj*ene<SY>@ghrKm{@!6A(|Tpc#W1}U(c!h
z`7Vd)$Y5kO#>1PnIk1UkL{9bPGBNv-MSHzK)+_N=n?9K2b#p>ncx!77N1FrQX-I%J
z1Qz!=r=z4<+-qsJq+{?oh{S*bRAyWH*4vJz+v~w!90ihf3FRzwmLtIkX~mB|rq61d
z4g?7d=zI`m!TPmJJDUALPsp<XuSg|8YlJqPdSuvbi*t99L{%twLkcF&yWLNzwMA`j
zu_Zy=qdE(r_b55ak7Zt6%wavx;WQILqcNDAhD)61z5Dsc4!iJ^X&{M(XU6X(9QV_R
zE-2C!b}``tJb=+HssDaUF5-4dE=CACb}g_R#3;O&%Q^hKii2nb_f-o7+OlS<5Aio2
zKEfXmgKf+LIyXX`{%s38*E=E(2844MUFV(t?2#N?Qfw|pKrvs=wgtxtHj5-$S3%3~
zD`@8+l0tGZ^9Xpknvw}3+WLQSVGPm>7+C^PQwq;*?9VtFlEN{5{)8hf*7(Cpt2V2n
z#)hwa_z>S)4BofGa}OqRh@R@v*EVkyJ`;l@8dzY{&V+X*R0~Vj+oCVxzXI!;Jh>RD
zX)<e*g&wgb{U*6@T#%U?IlYXbJEz8KI$_MB2$Dh6aMobK&y<qTgLRx$#Qppi?hbqf
z1Hjc)ZF)7jJ{EPy;%SA*fhmz?g&Bi|5>8IHXGG4)urz!Jm|2Xlmr5^jH86FV=)wCO
zb)qBx%Q@k^8{aWpb7mu)gf=Napvd(#&K~7)k0f@1Vp^hJ!JE5DNn^KMw<%eMwcAfT
zmMDFhQu!B64QCtCmOoj-=i;p_ZiyqNeETrnf9D1TW`Y6^&vUXAP2pupdy%Y}l=460
z^7ar^X+x9KBA*yTvtJh}y6n@)U);~=iTUK`hv2Q#cW{ZSC@Oh_5>a}>r%sA_&Ux9<
zW4=^f_Okim`Mp%q$lNq+>VWl)Q$Bh`ai`CW0Y8s2W7gb!hAj<ZD8kf}IY_QMnuJ--
zJ`8kh2XrhCeVHp)q=`p7cY2kkY8yTKJiyZ-t%fM^9(m$}_n08xZf`ycbhR8ub^6up
zDwuUMy-<Hl8&OKrZf<gDFr;(C=FfM3<?_(tuLA=hwT1~edrZ8}lWUi1R>dA)KhX`L
z4Ee{;kZi}a@jLKIVWkt&w|f0YaQ||C*)4v$8DGagXVu`vai?(Y*f>?;_HuFGlvbDl
zJD7k8om9I|Ech$-zIuE%g&3`oWe~Bed0vy(oJ8#Ej%<MT*=CN93U65)Zu$@6TCOkW
zbE!Ynu85lnpVwr57*SZq3`z+;JrO48x*z>7Mq&NYYy>gF5Tzep(X65!5s#$VC*>JN
z(wr!rzb*f=wAPCfA`;H%bHZEH{l5%wZP+jx_M)RvPg0k`32|>S+9%w+f)|!r`(<D(
zsm_zaRD0Kcub#>C*(^Q)@6W-DzI~nH6me8_p?UwNcWFy_leU?yqrwuiQ&ZM|Wo%gU
zHd4?WuLy;wY5MmLWNSy5lyPfk({oW5{^T32L+d7{P$e#323921MN={MY&ARcjIMc4
z;+I!#v#K!yvFUsQ>oD+&8)%>4lpc{O$%`w@9VXP((IX{!KU^oY0kopo`7R%U99ATb
z4rIqN%0T(uYHaJ!jWuE)1Hrhz^K5uvVqBykk0EWM1He1X{6G45!5-^KHLSTf!W(xZ
z&SQKd>niB&TSb<?rq`zcJ_<7DPTnB~#Gu9913tjM>=#Km%0opX1AFj&11VOSep9I7
z%->gl+}vhfcOG^769LMea_6I>DN1W1Ox}`oBJUb9?$zTzFLrx9?hqpwwa<;)DABl<
zoSq`|{CyM(Kc1N9Enps?h_f&YaLK7(#^<nJTxs~!tV$c(${<d#69{!+Z@5*|^i0J<
zbW=Q79_%v_DtL$5^sX-sYvH_b>KsB&&lMi|l{OQ8Z~>*Id4q6;%2Yjp>ec~f?xmep
zm2kg~_PK!B$-8Rq<pg!D5wl(wi})(qKO=vk4Q_h=4Rk-(al>sBo3{y^JpAV{;=%SX
z#W!=?uwLCY;=dttP3Nv=`x|DA@2IHiT<MR3q4}?}>@q8_?rIu*>GN48=<C;pX4xBc
zVMNl@%$?aUb2xHT9D^Qxu^r7tfxXZgb^75W6eP_HQf;4qR$BR@^eu^?{LR`DR=g@P
z%vXWCkd2xE_W6>$4)qDAzBco!+{IXt&O2~4a|G*^R+;s8F4wR5%?4{Cdb<06yfjy3
zO`$TS1n;q4Jr#)F9dMj|Du-=-Un9lKRrkN$Rcl_8myH!!)Mp9C%E@&*&!gb&0q792
zxd>0eZ(=V=h^A*pn)D8cMHeQtNs$lHr3u}G@Uk!@X)HUk7E-!V_o4(B9*pxL3z(=W
z;iP}bYN*_5o^c^Y;E|Y@2b3#APLB;)!JfAA`qGgH=DTPvdM&_;2A9W2hJxk=63Q89
zAJ6DWK~$oW=7bi)zhE0ZY&Gl_k%E%w5!C@uz5YjtAnA(;cS<pD$fm=7mmF49butV-
z2Fq5#&}n)8m(I?}!E$e}8;q_=!;2|s($9AaYf?w`xhvRCVAuXwLPGoIdI)dyj-$FY
zW!#)tLHE7SB^!iIkNH#GJi!KIOB59|1|MP;o%nzz)mhsG*-4QF&WUb2CZrI4dAsP9
zH_U)e%p)6z@AiR{LW$*mjcAhB!2R?+*O3?(=+wu^H%&boN2iL_aXz!ew#-tK(_CdC
zh3>nsS2o)2PW69NrJ1*X10A<I;yB0alfX|hVnMl8iR37Jf^X2dD`Y`<qLKY~@B7S;
z5H?dM2sXs3%VYs4hz%;So0*$Z_fKt%k%u~9J$x^bia4%_`VeT_YE_NKxI?P(yDr>7
zqgYvo;q@&Bq}6)eb9=#1{iU;WFV!awzdr6H9TC_v4zI>b!nV_UUQAW5PleL8>DHQb
zU)YLXsxD=RUWjUF)-u+%iV+-04AcAhA|j@4*C{S6?wB4`XvM(XA&PELD}8n@QGG(?
z^;uo1h`4<VGxn^797g6&fHe*5HDiuw(^2BSBk@x3rhnWAM>Q%LC^Xl9XS}&@K>9|V
z_j1ZHGDe*==Yj8@Vi`EYIa*AQ9Q$iX)U!7@&*YBWivkQ+DWY;U^0hivG~79CCK`L*
zH**UBHnMld)J3S`mrW&io(y5F6SwtY`?bi{+kB`b{pM7f`{2~Xow1TI(C0(qPNh6F
zHa$nTmkBzT<1NUGuIvVo&-YSkf;Zr%0X!EfjS-xrpoRt%407nzoBDpzMr%5dE6mnl
zz2HN;<>M~Ytkx;v<*0G1)yAng_JT@JZnwte=I6U%6yV+lpfDf{4pAm#p>~6ZAU*N?
zNgA!{kXvMSpQ0+_YJzaa%#Pzz6AVbtV2YG`+tIYU1GW6QSGwu7XaQAjidNxY9xc8#
zIAxmyRwwH=PQyC9=tOZdt*oN9{~(ycy}t}iyFXC-50AmkszyhtfO|upB?YGr+a%#J
zw_}d2<ZCV}F8^0RnUcJj_2PAOJefx~ny6_Wo45?jtc;%4JV8Ywtzajc+&hsyHB<VP
zz^?VJl|?$MLN`F9&1l9F&EL{EQ=PPOab(smu4j?H>JQZUUf=0iRYp^`4X|!R=8)$$
z3&Qss712ZQ{7XOnm2{XsJ&gD(#=umNVURAg_<F~065+)>H!!LCHM?wK9CD~w8D-&b
z+iSswxSgjvO~K`uL`$SH1WI;}QAy0{=*Ze5i5K_Oyu=V93NMs}9YeGN7Nw)2Gb>L-
z%~fdy&choV<(_O{@YRv8_#@21r9oD$GAv0k)KR>%wf}Ood3^9G)Z|Q{Xvx4pUU7a8
zcpEO!_zfw^n|j@+KT=96ebg*$qZ{k1e#b}E(8Bb(D<Ya_e?{B7%`S>VRcsH!fb(++
z@A-9*&p+I7YA2^keeh{8i8M7e+uwX9;#dE>L9U)>m-Kq#R|Z`O4(}yyUeKV2xwY=|
zK*_NCI->+8aSa(WIrH;{+%Rs#KHtS$KMR^aXo&EAvh2>jac~kZaqK)E9F+Gow2qv{
z5;>&FRyKntY-C2x-_4E<iL}n@uLLXv%pJ7X;DW+ii7gdMSmM)*1>oBIl%jES&d7Ws
zvvT&Cb>XYo3X6t6sFVMLIx9x7r?X+%r~xUjsJTsGKjiLSQ;*_@_^!A=+iy`9xIjq^
z3|{!hHGex%@$b720JoL1spNWN#*46@`}^jN^cT2neg9Utum>vMM#rz_4bl#F4Up3p
zGg!haNYYTBN@~gI;#(M>QxFkcNl3h%-AXsG9xJ2!t%LGJ_7^s9^6YQ>(mc9e)UYt|
zoRjMx5%@tQhSBa<$!JW5X(U+?n^c(D5b-;8d^~U1DRd2uSq)1-uvYhv1T^OB_U25)
zT|r>I5?@5N*KP;vnQ3nAd^JBQ<4tLp{=u)>s-)NN>B3`^Xwn^M5N}|9aMAbNVlDM(
zlICq`Ub%W{^-xNWj~{E4_^{z*-qb+G$U%mcquG!6*LBV#P13w3b=qVQ>-sVYgA01{
zta*(e$EkSxOptsFJFA*BSi{8JI&bag=cp5NNvUrU>{44I>kUIeQNpYHh&qF7{c0Xv
zI^4CJLaH0;kOohShKTtEUU^@#bK=t@8%qPLxg%cTY}2va-^H#xIHS4r?1G;>OGWd6
z6*bF%{m9pgC~-Q)alEs&b9kA_?cl_A%AEdYZgdA|@hqXy)vL}hvS~bk^$Pjif@mya
zysQ5a{I2+crL9sm`!=Q!^!6UT*aDvheDL*+w_&0dIRNuYO!egO6}IFB2l`hh1(l5?
zGOX5Ry}oQ#kEM2s?E8RMc=s&O-dKw^_|UZ%90ynA#zZ;|+^#J{YI)|&92{+Hk6cm>
z-^{iD;c|Bx8si3qDCvd&^Z54om_xDC_*(*?_P5V7Qyj?Rm!I;z4o}~OHmG7W#eZ$k
zpSI!7R{YirJ8EuMV>93MEiKPz1zQ$eDCJ8`GQO@#Y{2}pPKsBeURu>U7%xgi4^{_X
znD}h*+poadR*4m`&UD(Dy14N`#hq&$q5R6_>>Dk0yiy}_x;Eoky?xyM+FY2@rn93T
zoPeM#yB7G_U5I8LgtSt512hZJP<`-Wu<r!p;cvfu7-isk(|H)B&CbeeoD~fG7P@XB
zk0u(S3FM8_7{&ECN_y=>IW^DRmWa_280lZ>lRlE`Mo@|3RJ0Ez_}s*o+(ExQOB**<
z5OSU$Tn)?q=7j~>3(c3ZAI-9qp)7)c_TKC6yBzz-QhjWg5i9}9z_)vOAOKu_UT&2$
zK@ow|=+Hzr&mpiY3_{w6%@WOTjQhb7MK(V({3}sdp+c>gx*<C}IOCr_07Cc3!QilV
zU|XDBw=yC&(H9-lIeK(2Uo<q~NhRrigw6n0M%wz!E;3IVKMiA(%X?<@-`I96XM2f1
z@UsEgX4H~V4U_GCA2~WKbyY`i|IB4U63Xwtt^umyr@?t6K38L&Dt9o<;I9fZ{+oeE
zSg)Y`X7ds{Z&Tm5xEGX~G#2oyZq(axGernAqx`r-Jvt`X$RAK-VXHlh9V;C7GPx3*
zG8+dhCQI-&QY{>=kGk``dS8w|b=*RdM{-bvZlqHfvC+=+MYSogDtL#1B~HZ%jwj;7
zt2z6nE_GIX1@`c{Zys$>dKlYk!?+ynK3!6q0*oPd1_quXgA0l+6~%hM|AV>u^by~k
z>j72-BRblBq^LF(31dAzS^_KByQ>@a;4pt||AW&~#u~QVnZS>=<BkNF%)Donj=->Q
zo?6gtpKt|x&5qi&kd&3^5x7)A<xKOh%pMOzneVBwiyQcM7#7XjKe`<kNk$~!SA=eA
zdUpB*>(tf`$unFC>CFu$uwd@|CC!ws(s6zly_9BRXxluq(VQ`kgy+?leqQKUD#aT_
zJ)BMvfD@i$8~<o{+=|Mb(_oLJQU^xw+!}GJdC{lJS<2cJ?RXNG0c);hL31_picoRV
z&b3e{{(e_Z4?o=^(5L}sy7S)o&V01=rDx|$K={e2%)<5;odxv=!jyZCCdIg6m$2-S
zl?<1fjCZI1p!>Zpu>nhnTnmNi1d;Z%`mvr{6dvtQD28o6Oy_6_Y<*jf`oh*XW=+Lh
z=pJzyq0rabm=xhgI>R*JC~K1WeqV;ZGRQ7K)GG$THM>%LW`1HL0u-SPmIb@vKRuhg
z+5wxh*`0*H(g9{e;>@B-g9L<*WkE}lN``d_8~Pu>##}PUu5qj+4n*@lW|7GHA#6hs
zPRq~#K^#nNo584y+ZuNmqdhy^f-lsm%>cuWM*KeYS3H0p454QkyFi`P{aXo-QGwdJ
z^P6&wvwe1_j;KT|9tIRY8st24w2z7EG*ShnK<+JH7Y2>2hM14Ry^>7F?3!IAfrgce
z#dV8dxA~Dwz~`mWCK~K|lrVOwNj$J<Hy-(8qdmeHvjfn)LP3{afMe~Eakcb_v#=xa
zpNNFq3G0TAiP{ibaG~nn@*4>xZ8A?u6(`L+Cw=5s9wrL{EX%88T79YSRC9F=3W3aR
zQ5^^xX6hqxKnU6?H6Blk+{<6WD#B4|LYJ8Gr+8}CxhL$}?>Bz#8P`*dIH<a(W<S4(
z$md=6Uk7Q~igf4(pwOk@pGMz5Dk}=1l0f#ww5xn&0jkd)p7W3KT{f^wy)WDrHfes5
z=nN8KmKa4u00)+MTT#9bM6FiQK&PGJGImR;$SDp<`*I+~=#`7r@%732bq|1zX+^vG
zcT4j+G{K%=^J(7%5WX_NP4bM(SRhr*$CT3exZ)TAVQ)&`vQ$r!Q4=T^Z`a5v%xN2T
zprFN}`R{<g#djUi06ytc8dG-+2P)OX6aK5~_&A5ix($zR_+9;H$HbWfHIpY`SK%D4
z2L&NYNuV6%>D^-3Zh~jG(RC|cAV`}1XV#uqf=<c11Q|K&MB*+o5|kK!r>X=~Rs651
z$aSZ!Wu+oswzzI^emQm^haJ7b*4k?yg<6tiQD_7ldr8?J_Prz{KHmZ@R8W25U#XiN
zpOE8n_Dz|pB$m`&`^!F9TbG}{NI4Vmj-Q(IVH#c9{kcYxm#SUG51Ns2nW9Dovk#0g
zdqs?Ush=KZw*b~bxyhxM=f~ys@byD$b-q~8#b+9puj!9YzETijN30E?JM{PWGcuG8
zB)^Xa;2-C(qNj8qD21MGjrU$d-G%M%O3@Ra2FAd(;OCE(o1Q$%J2{|NGdEV5C|56X
z{FqJ!aspepE%%Gfe}3Su|1=-iMU`Rivl3nSf>|%l{k=BTEr79t3Eg7kc6$CmpVJ3g
zbX^XPzZ$<WB5!D-TFTI+%npJiPaK)#%j~asa1I%G%F3s2TyK0+2BALJr&FF)MgZr|
z$F{S~e~~nK2QnoiVmym+RD65Q14dhzZ%SO>&yNl^&0cucyO6#7BGAP^LfL_U<AFCl
zf(`?^senQ^I0rvgsVif&mymod8ReZW1V7cpzv8EQIUsFNG9)u_E85aMgzeAHVzh-H
z?P&I#uUL|Mu{4kK%|soL4Wxf1r!&!kwfLtJR&+FvXovajkdhVl<LJ6O<Mp=~mLu2x
z2;&ouu-I59+C#vZr&)UOP*cRy5PIScjwM~6yF}ZI6M74+8YRr}`3kd^=bZ?S`qtd`
zGAXgiQpE^Cw;6|{g1pNyb>0@asF|zx)5G7T8D9;aoJmF=v0l&-X)kc>s(YOK2eqS<
z1e2&9Q`eN^F?IeHxmmM*>r{cM$!T~-_5Gco-H_g<SdEtczJyU|rNQ$4MUvtnqDM9g
zUl_HIez5lnU&(?-w9KF1vdQX5E5Q;AVEudB`74;`wA~deLYUx^JkCJBU9F)3;TJY1
zyOhGAFUaHV3N{8W*h0tA3e=?^>>(r%ZHWG~l#Mc}bm9m4=l*!;R?kspbaYw~PAtee
zIwp!_N{gNerJ^EFfk<Y>+VQB6b6kT?n=vTkO!wQgI2lBZ$>)@n#&H@KW-yWFwfYgo
zGZeDmXG@;6t^_y5ORdHpwTo;ff10J;K)I9W#p~9v3ByaXE-&bwBgZy>Ct#VvS*T4Z
zVlB(bnkvf<EH|I+c5Abb!$-0r7T|&r?6K1#wkoJ>>nO}?-Y8*|+K=4BXugHU1s~=o
zPCOcWrbHunm<YP<+X^)pJ~NL=RDVTYwtrV2s7ATu%4o5)<M+x#<S6%qwtB&@cE+zx
z4}#YMpG{H`wMsaOlZ2mMz3J;51QLs6J?9uQEk`bvl7vOUyd9~TZm=dD&~*Hoh^9_Q
z06V_9-UQ0QA+h>&>ka{w=7HXrK`hQ4?0{_~c_|y$(aSCeiqT@ESsvgI!81F5q%?e#
zA~RT>NB+*7h;Fliap~6Y+MA0YMUc&sPqE?}F3VXnhgWT7&H8ROFM-tz*Pb0^L|VG?
zIjP!oDc%E<^yo7CoSdH0XPl~kZ5=c(U2&W>fX_s8+lnap&0UqX`|M0a-FB1(fq+uC
zMqgI3nqIW1Wdwx!eV$7ce%vPho(eG*Tvd8!(~LjL3S5vi2oIBXgtOP|X^UDEAkn=U
zwHf32J8m$D)BgiR7F1I79Meo^Ak1ql;+ULG@~k=EP39$Xwy3XZAz(OXmlWvQqHF2J
zS9Q-sD?u8=A^e0=1!@WH4r5@L$~g`PB+v}(6y2V-7|fWjV~?5nMo=XVj7a8;l;#2!
zHKW~OcQ#AyS6)IT%HDy6aE*{b903s1r4Ro<5SREF#A)4-)K=Qn|C-2y;H`}1n}aWg
zQFa{WKePTi!Rf*0*9MErlQUi8au6eM49;W7Hmzj%gO9#eqfxl#_KAS}eul8qk#Iyc
z$)d<;1pYwN_otj!Tdr`@z$YU0>CNp^98-^i+F*&D|AoefG5<=LF#*u<jKmu3AHilK
zWa_ZK=cVGDybf^B1qaIS_c#q(u5xMt8j%B)^0;RztopznlSL}FxI#-t+zhDmxTO7G
zc(4}tKg@4U4qjA|gj_I7RbU;s9B%B^9A<0>2uI|oE%z$D^;weVHUF3oXpSh6X)__~
zZ9|hSRDhV0ykpz^n@=)UeA`FxfL#DI1d%XH>{ohAB`SfgV>B7|%ai@Lx^gt0UjJiX
z6Cg&1Z>Zn0Tur#4$Pup5^L|&SGHvU2O!mJlVn5-yvL)XWd|Ofc8?)Eq&ZpX~S;0$o
zQZrp)?}5o|%Tc-tllex5joS9|HgS0Css8wlxu#FOfMEY6B-u+DCS;8^okZsx;^#Nt
zjxYe*%tiw1?0@X@->E#>(Bhq=+wQV*IZl*~(_SAos*-;(+W%u!`w94eNm5I;XXPOe
z{Vu-iQX^TI`$zuMyXeyM4s%HupUliWiC$cgo3iyE4mKXLXT>28K^b@5Or+xfg8RHe
zlcIjJB9=7@Iel{bQvOhR<Mko_L+jNM8mI3#zB~e`wBbMPzo$;;rbmD#2mzMGO5~$9
zG?{n>2xE0*qwtf)jXHTJ`^sbaoENZVPk>{2MAjeB6`_~rZU2HE`U`r|zWG@0zo6Q5
zgUmmmT2A6|V4*(`VJ*IGQ{I@%u|(*wEk5Xb#>D;=fMF0-DKngK|DOQ+*yN$Nzz(}5
zc?Q=H*kPtGt@3Z;Fm|}>m>0o*YU(W&QMed~0I?{)!=ok@SmREt$X@+6qs=Vyb?wtj
z!E#@15ew$%XhM%%A4a(SPk@{G<1cgnB6S2v!&gnbTE;MU-vE%lQ*AHJdK^Z|CQ-SV
zanQ8vdkMd-NIsVtTQ0-Kuet|E9?kw(t=EjF?gV$$Rc3iyj59_=(Z^<5OmH?!eSgeY
ze117A?Dz$;pmOhq+^mT0*SW{!U+yZpjdYEZY-3I1T(i-*tVwHd6$Tp6OMip?4DjcF
z-42j)X4S;YP2`XT{$w)S2eXQv17Mat>-ZmF*tZveZ2<7GRsJtc$Pw<^urQEc@=%}%
zR00Q3{)I{#Pq<C|{xTRNF4vrYY6r+oGJDd7ISRX#E#j$K4)Y3N3c=rSh<~=3!5vk)
zz5KO0>v)I_`+<cxKu;bDm633?Z7cl?NU2$Kh=079F*B5Ud-LmcFd!$#LKpz{zu_Cq
zX|U~s{u~(AS{s&+s$E+Q-ucB!`y8JRwa>}?xuzNX!nAFrupi~hu-i<Q9O560V@&m?
zDmuJg#yT9bfB3d&q;LnhSAP-ct2DI(jxF1<A}gAO9foDY&)~m5blqLcyzrK72BRO1
znMw=b+Zg45HMR0K5)a1+`;m2UkdS6+tJ=^k@ka~f3v=Q+)bcHl7}50<B+?U+cuQc<
z_6iW5Q<%+3mdjy2G|*SPZpCOCrhZY2zA=TuEKq4jS>PE^X~2JTkZ;@kdE!HAYQZ0#
zC(~V51dT{aXy?Rr!h&W<@|1+#I>MZ$p)jbomfjAKeK#&vfyCa~65pS2pmlrr4(|8S
z;v(;Lxu_6j)wc9w8@y5%tl=yRUFjqNI^g*ws0sDKM}J9Qw<a(sCO2+bx7LG;%0f9{
z1gT<0-Vv-{zQp%yoG<I(Ky?pBwiX~;sftS%uZH?yyP}<nzJnGMzx%eADPHP1v$N7q
z>o3Y@Hv!6Px3pUkFAvmhf{|u?ju8)cC5tD!#PdJq=WrGNb|_X){RD5A6D;+8!x2hp
zB#@`B0+bc9Je!k!>*2uVX(yf4y0A7cPe-gDXuB@}-*l4zzV<IU%7C1us%>e^e{$V5
z!5l1-nL(t$Hwmtbo}}Fn<befe8&+i7rf-KCSxG?dqHzq~YyxVx5f5}NW8-YWBC@zq
zyo{X%WcvOD*5X`Z*otgUliY)mi0PwZ=gmo(E^)z_j4@=EHk}KqW^4WlQ2HqSO%+&i
ziVPc96MB$;e7Xi{L<+|J!OLy0UJcdWFpJIsnbey5h^HW!$;twrH~??^;~Db{qT&7<
zR*dXnYJXf=b~9!T4>azAdzF!F7XVQq<BvE4k3%f{L_>WyT>b!R&@uKDH}EaV89_}P
zu+S}7(ZNB$lb`!w`)`K{_svO2K&M5Tr#W#N&Gipi{2=!0zz7mJ`724Db$zXlu<l?z
zB8_HJdEy@DiOJ)MuBB`P#(?6bv@_-n<G>2Q*HuZM%x^Lf>0g9Td4>L)zS>d>ylapj
z8;~SCgeRVz_t_c!2(Yx_NLwi!p8-oKjzKm@L3#!=Diw0!)hwX&Zi%(iN~p&+)8Zgj
zZnr}5V5c4sRICh}`wv*Zp!CM$29JFavx!KTW{%mtdUKHpz4E?U^dr%Z5sB@eqb~Jf
zfzi4%(c%qs+FXF}ON_K;D?!WL`)L+T^x(VOQoI&TT-Fn`^n>fa7mvyTr2+mTuLtmh
zXL_5sDZ7SqIX7PtVM=aEm(?~i6?xau6eX}fcn}NV*8q9cNb*b*1NcExkW8?G@o-A;
z`IniXlPQ3AS_^52<^ONkd%=9d*yu(M)tCjtVh9``!Xef6AG?XBp9cJGfw-CSzgSbt
z8a;#8o@lbC$&Rdo{P(apLkw2-8QsA5@vKxbPNjO}&D$@~Ql!Zmh?Xqi8DPX+4k%V0
zS}Yc_M+@75B5H?>Ti${t@~ak|ne&tNGPd3Nv$I&i3pX#>D{wHs*zs_?F*$Axg6-py
zi7W+QU*KNenFB0AA1iXN%41NNhvv?7ezI6(L~?5L2+?u4_5I;baMcR2G@|7pM1h&P
z*P^O~5AG`afrL}hq|LoftY&|msON=eGB2gk@_kB7Zf~%jq@qb4zgRrL4YaRkHxMrn
zmqJ&%9VXha%iGf?dvbn)Mk?o}5z<tKwj>O{FeY0U#0btN=23#(s5F-dLId!RAH1Dc
zf!~$f!HQg^N#Z+b=0@S%g)4{<tqV01H1WKDqQB^I|8F^y{n;iLZhe;r94w4uEi!_m
zZ_#P2$V^d^CkF^ri^_>Vn;0$Dqa)5<l%%Y`1^Rf9zzY=(a2&Wj5g7mn;Ffa=P+B>f
zZj^(fdCl!kZGXTQ&C`JDe^0Ph_#JCIWzG1#6nS_99ez&mX%C?Rj(VF5t*8^SSC=U1
zckE0ZCz?o~LR_?+`OIaCg$;Bg60VeX*)vtuHccb^i5VRQs!#VarFd;{nbrXfv;HNC
zVAXL^f_xr59R0b%S(@P-cX2;oGu2r+QY`#jN~`8Y5`L_xYd@~s0mw#V41qiH^^>G_
zBZ&*K%{^#fhR+?PBF^seu&cjnhhpb&*50;3{VXW4?k8bpN0h+)G@{VjWO??U3#~vt
z`k*hAc>W+i^g--o6ewhMaQ}J_Z6FutTixk6<(+xkBDRn*SXm+)!p(Ut#XI=#m=y86
z3;)i8%m0qKjy5oei+|U-pBDqh#9d_MRn*CbfTmhT?N#cAwBfC=LSy1U5+An&`ML`2
zbLg)oiw3Y>csaNB(tCVs^NrCfLEazFY;Dd!8!&z^N3H@lGX>`PfmW^Qucj}o1X+lS
zbxfVDu?MAb-+i+&V^;PzwdlQ3!4~6^5s5o}CJ%&AF`~6N)X*TBxrxn*ij9nv2gl63
zlg&LkKr#h#OCqv^tB^4X+X?*_8F5q2{A1xmQN1#3b-<V!wuJuhTOoKP@j=_Pe;?3;
zYshALTDc`wap&jJ%Q(BNW*^q{_muWPZF)T5rWxku2syp{KiH)rnnIsEX<D<+f^ExE
z;AurK8x5!#`$O8dA4pmRbsm*y>01ga5De3R==OrOrXvyU-zBG&@@-E`oW;A#PusdG
z6d<ea^q1ab52|H;0!+>ZGbU^nt|4f8Plcs}-dErGFFwXHp}TrQ$#phqhT;3EvOzlK
zYoVm{cUPo)m4R~=gi1$Dhd&v9d+sAju->|{BKZQ>gicc8ef4LZ%H_Q*Im;HZ%{Boc
zXRZW7-UMEMJG45#TI{!+WpvynGN#Vb?DmZJGdT+J{cu}bMe^COc{FK)eZJ<w$F-o>
zsg&{R?#_Xv^y~kbZb?Kc;fXK(kY}ba{S7M1LA$3!o!;|hsN}3VT?z;)K2*9|(`U_(
zMMl?vBR+}7_U9v)89qOhmxnp^%g3kZ9bkLM{q-*meZi5|(x9QAyD7dw8{{+nV}KvV
zcPm0d{=?^5Eu2V!;n(P(&|RH?^?k`2;rjsVPr$n<En|hHZIxJ%i&=rj!<oVZ-N{x2
z3-QJli(P50<r(PG&(P9LlW*V<B78gm9G?0a{1NJ!at-?YlD!uW-5H9M$lJ{ScHSiQ
zFY4hlRN5xC4^3ASHx1f>nXjJ!hBy{GxZq`vK*d8O_KWMO*m3KCxA$=$A3L4Zru%|O
zng`p(CUUxB>>pJ;svw&kSo!97#NqEtTirR&x&k)AHnG8H@+P?NIRNbkcTIqr?{6o?
z{u9g;t#{8Pdv;op9o64lKUZ+~wErsYdynp46N~eYHV98uRNiZNx@OG-<(OTEJQe+x
zNF6)yK_M}*BmU_Vz@yH!q37pawo0cK@xF{!C54jBY~HW0(*o+cQuTG<MtYYb?fcsU
z^-JTs<=FShOINgn?nn-JlZ5zqOZSvf1QkRvSy1DW>Ny4&g>K*jVxD-#?zpfd;viNs
z^wgC{hpSG$@j2Zb`&<FS9{T-V4@3{O#u@NT=0owEl+m?e7x(sSSPS<=w~w!O=vo-2
z>EG^4L^Cf8(7y-<KDC^@OFC`tBiDaepDq?1rCL^9g>Ac-zryG$Jkph#s<?N*bLgR+
z_Wr$7_s#@0j7mmO(~ZMNJSe!e5J`*_Hvhs?Enhqa!}b^R75@y|M^#$0cdzs8p<NFC
zy_1P&0xkX>mWdTb^(aBqf@k1n$gnWHIU$dr_*Ijhrr6qUS{aExl8!LNA~gX;HQ>0O
zHY%RahXr-6H4xkSflxp2*0p|_F98MR%6xXc9i8I%MP*@-+}}a>P3Q=(St(;kW(Y{@
z!zz5x^b@ZuJ7n0Wa}{R3_GQK`$!l_?;uEJE^Y*WS+{XFj^^7Z^c){nyGlObd7lT*#
zm#kplyHOYVsK2Ib;M33Zoic1sV_fI3?<I@~FBW#Okp2kv@4^Oj+~$v%wyc7z#rm>U
z$ll#En>Mp9fCde(JJO2|n7R1(4Ie)fSTQ0Q5vTobQanG65fKDp5uY}^9y*vRKuH>F
zUZ20`ijnc?AbMBD08ulZU@e>y-EbX8D+$U+(no7jVg%L4wO!XjflBkGlEyhp1u3qW
zWga2yw*gKag-<oH{UwBg{+jl(PteI0J+RwYHFL4aade~|S`zX70<j&wZVlK!)b@gZ
z{QD!zu$w)FUa?v$R3HV#h?)KMVcFIXKUUwV^`T-&pGMZu4uU)UqtFj5k`RL#-bfef
z1znS$H!LQus~YmC>URO`*-|SDGxJw)BUW{%pRYFB*gqXTdHQ6WXf(0T3#_%mU!>2g
zpl6k{x{}7P<3$;+7=%Z1RN1|~VCdOibk<{f;o#Yp1Z3>a!6PM)UuM-KyB^XGQAu+G
zvqe}@>5%U{__o(iE3so?mbCtGbjR95GwNVYqr%KQhlM%qs}~Ujn9^jyCya~%9pfR#
zPOwzxcN0Mmw16qhmtk$PubsbnHc+?LiuLg0>zVBrYCpz&`t9+4#pi)evG)*J5Qjs6
z=0t9*h)+5wlAWvZk+9#{uYx`n<elyD%#3l(v-7)&q=7fcg1C5WL&$zjk6ut0zfx}?
z^@wnPfbC4V&vGF9M~N{}N$RDUxvEAH%a3Gis>TA!l#)HD;ulWPV59)QR*9=2y7`?u
z1dIlBXv`IyE<`QU&u`$|d`M7q)ubPF!7)l|&7>1ruk`N167%VZU*%|&0bM*(R#^$!
z^s2eHwpH`<zuy=(ZBs6AJ8tD46LoF3>9?fZg26LP2V~4XpFMu*NPqEB$Xay2b_p*}
z9kUwhk+y2w5k0803i{;MSjtZsZYJv%Oqh9tc%dl6cI~+MVgiZ7mMN$jIZ`UcdTb5S
zM{pCuY!jCX&|;pyT2;WKWkExm@_}bM6*RE_(yHQu`z+55Uv?y8sOmC!a%}{j8oOCF
zTy(B07+;}u%NaD21TA2*`R@(ki1GOw)&iU8*7iva9-`U?h6oNN%Chm9$l=}8301|#
zQoLro7X6{a5fEV?J4gRoyJtqdXegSBkUy(baxvNk_i5|jp{C$9Cb;5@HCW$y8{6Ol
zX@e!Y>CS67v^@dST^Y7=2kW$xIaa#wr`nm&s-IVvfvO38Iw>-$K!|3VPk}~pcBjFz
zvcWleU||{?s!@JsR+Hb<$`>XcftKKns(;W1I+s$%N0USdaCLDeu^ZIw$ha`WuL8@^
zU1vsb)@KjDGybuGf=z3ZH*y7qC_z|JbCdTBf-Rm9JljNn2tKZb5b;M!hh>4TlulsD
zf|}uK<6rQIY<X=ucyo1eOp15e3AAF(0PS&yCYc2Wuu>AGWY~oTKEHE-AvoOH*?SD!
zErOHVn7BdEp-aKM^|^?U&u;)yEk8^})1DAcIM%jY`~)3ql3|<jrjOyXW(JKX4-Q((
zf#=edphWh=$Z{p9t-$RpHd~taz{<;9SE+Z<_DsN*9|d?RyobZ5&S+tl0Vx5^%>NF)
zWdqv4`^ZGDEum+*ly;IOd5Rs$LGPk7uPkX^Rl;|feA6K*?CLDF@XtUq!-0~06`<a4
z*TD?90yjUb3f5v@Q3kCow=gp)-jAc>5mxjao+VxH(_)kkh}fHP)QhI6+dQb4e6J?J
zXnTPV^jyV!S*Plzs$sX6N>dtM8|g-wGlK`w^y3cX^x89{0a(!!!d9ghijX&_n<wj8
zGR&(Q-$!{B688^GkkzY8Ot*6v#d094FJ%QjUX${JEU=w<u5UxlayD1h8|Q5H2-RGm
zBIjmU1{!Q*F>PcO@R~AC52*BwPZgSUsJ>CQdpTR}#+V>h-)ZLj_UiVsfUZPhAyF|Z
z(Xc;FiuZOi=z^w&ZQZ`j5YS%eH8OKvnz!_0sAx}WK4E8f@6f@jahvXh4QH#8rFqv6
zcW(qsb3Aw{Qi8iG%l7FgY{<+&qaJp*GKbjCZC2SZ$DTU%L5H(5^ymg{;QOOq^3cuv
zusB(^c1H^>vmT9l&;x)O&N!<wQ*+tW@=*Nc7cXxiq2p!S-KhQvzaoY}09hKe@6eqe
zi2M4AVF&Bwzm};$Ge1H_`%-fW8@l^ghpRU4S{zAN8U2Pu8ri2|8&qDBmam4uCVS;>
zs#A%{%dB$GO@5CE_C-DzdQ1D5AVJ@DX7AoA!296<=}_vfuU2G%XCf(Gx;av?kq-KV
z#Kwe%Z6UA!M<(coa~#*Sxbnu)C;jV3j8{Uxrb2(%r9L7c)nQTSS1mTBuODv2B6r%0
zJryA_v$ib)13nF5&I+t4XdR0l>%5`zq<_PRJQU}Gv%Cg4?6gWf*6`u7oC<U>nbWij
zEBY;FHnw3wa%oF#$A+BDk`FAs>os%ra9bj}w6)Tk`#Sgyc<BY(LG4->;ifrtox^yQ
z?ey#otUNVxRQ4MwW9O9+l<zlUe?osva$&#m2<Qg!W>MH^=H22@xmSS9GiZ8N@k*#P
zUN8_mq5zdP@LI%&sg`(h`k4-^KAqtcTg!*dUu1fNGVy@st9Ofom;HntComaJnHMaI
zF*}z;)Lq6lV)9Zzk7RPXa)+wwhVj!|%ZA5Zq{m>r)&)w(-7O6IN4*bB6&R1E2*@rm
zf^RhIF-jShSoB6bvt=2Oh)mFZ=fR6)dhMGR1>BBvB9nDci&Dg|Y3rJ{<WG<s7CFD7
za0&0B_}eThH6}`&oeZjTn$}=jr8+*QZ<-C-nm?=>O3DiD`++VUt!ncA;55g1Ha@Mn
zT^_<0t%I!B%~5o*#L3%=(1G35iypS9Fr}#KyG}E%wYkNfVP<q$`|&yD_AlmUId?Ji
zCYmJ`6|j@uw!VzKe%VmqEN9aX>=mZ|Y3KSuzn^oUqeKkG6uN6cS7<o-87&SApkkz^
z*8<R`LH%_5{%3EP`Wu|<dA~yfJ9*Y$tx4fFTO+A?Q7w<K#0^>aB|Ms!p!SPFI*fd2
zQ0A42vD-flloSg3uNum9g^;5red0990x4|6AnUzwgw(ZifYMyMAlr#OkA5P5POJg2
zl$dyCh)8cF8)F9DHKn&VoJmI`4A^e+NM*>Od3b^XK1p>CjXx6Q{=q<Wdh5gC1mpBk
zPopLh0@PuoT7W?&bOqYkVzjuEmc<UmyHjc3k|-M8bIIiO>Z~cLQ_XLBe;U9uJ<=Ge
z8F{>vJ*-|D9ZugGNX;XrpqZ;yLn`x!sFrTzC{@qJ-d<DO8*5$szpjd{9Y015^S#pP
z*vEOL2oq;Sk0iQ197?1uXAjo(f#z9hDo#{O96>O<OxN2HjFWMh==Lfw>M>|0*Eyl<
zLViD1D&@1(V$m4RsgOsYe<N7<Co#yC@{p;@MQ%GX&Vc?f5lzb<ZoKO*C_k~MW8Mfi
zGfM#XUt$i``zv~ae<~IX11p!<vWM~yIV#K>EZnvfrd^0zFLq&sim~&|EtB0;gm{vA
zk^zrM0VDM3xS8Nc>V*G(c-3aBJZZgt^g7LT{}Y0>Q9-|Do(%g33i*8hTF8@D<jiSg
z0!^9#n@m`%0_u_~SW^)$Zm-SX;B|rW%MG6N8#zewCJ~6klDz)ZlpDx7(4%I$l1|Bt
zOTZG(!z9^JagS?M$Mr==fPNf^&NHX4tJAGXp>)IJ)G*=mBcB(OP>^_dH56y`7#&x_
znOj|ue0=RxCoHj9y$%)47;$&mOO)!Wk4i8}?wm#=vH*Vp*m+h2=9!_Caj+I$+SPN}
z$R8$pNUrr8pQ|os|J-c8i@v%XCzt<tBYPyVd-BwqN74<7P@E@%?F1{wjS#h~Bl_v{
zIo~%o3rLH^{>7-5pV4^m;2}#T$Uy<39Vr_ObBRZW2T>=YzP`(-o&ojcuVmO*XP-qR
za6KoGtXTzFVvIBupb1*x5l&;|5}x>ixn1Sk$?XKJoEj%Qe|X*ZgFqGgW=U>wF?ALD
z5tMBnEN@G2b0n%QutJ!D>XnJekJ_xa%3w3F5)!%?N%+5J>TWp64GS@&+qZK##ar!u
zSz3Zi{jsnVS>&7twjpp>Hpu2db8UVDzfAkbiLIzenl9F2{C|Kz(~X@=*(W=Uh;sH-
z?jM@pPS{Z?^PfJ&ph;ZMUu0=;c!RSdn$b%~KU9KmCR6uN@}4vdUG#eO=7dFPw3{}$
zZkuBpbDj5Ui*2C!G&9<*`uk<spkp8sIz`v#S;1gCqk%_!vA*gk$xEBqq+~Yv3Qemp
zWUjzcE#=Jni}<d%YggjmM2*gsNb;UgmS-#lk<&##^m{2GsulR+J9t|H=QI3mxFQ(v
zJQn~yz%B1v%I;hMoR;E^Gu6c+jBL=-oaVMC4X={50IzCk^?8O^uWxyS{t0TsNM*h}
zR7&&hocBFze^o4R3X@T{gL(5u;M{_LM|T*7F|<53Z#Y@V)ucB^9UHO%FA+*S$$|$h
zrqdsR&~xOW31|E_7A(kzAa!lg#DaHDv2C)dGVD}lx$nS<ZpIJV8@Z^rXwpTtY!E%W
zIm;Q}o=**UcK5){rXnjUg;)0}8BLn;ti6L^XIl}YeHxIU-TPj!)niR|X!UOX?Nq<i
z*H{rM6dI0%P-KD2xiQP_sd>`8k!-MQejFQF$3N7HUgfuDI^XL``BJtTN(mTNX@hU)
z3Nm={BO6pz|BGD5*Ka-ZzhL;QAOisN_16on*QD#JbLm(Sdlc-deG`zS4VMi|uB5$*
zDo{GE2cA3XAH*@&Y1}r~15MlUQJwnOel<E?RYYE&)K}eHXwbhO{p0l3ERagaqft|5
z9~xpsKWi&gs~+u~or@+5#1*3-mArwWjCoMRF6O<93nqF#X#O41@(yj_`=!0|?NS$n
zY`qLyiP^DwK+OedGI=;g@P=hTSL<^C#NYXtzO4jiFgADpDk#q&LG1=|4IgY+X}S;I
zs>BP}jbiTHDiC0fq_d`efB``tp??RYuV6p2F^@jG{NQxafn#$tD~o;9tc0nznlzKi
zEbVWgf_sDqf@RErv8YqW$}1}O_s)NZE@gj4DsEcJE@dh@4d_`BLm))+H&wErMfUq~
z4rt||){G~qwoUy+8`N80w3ac7mvJe5b;waV!r^fy^3;_i?buZSdsytu+%I+7E;dfP
z3)l{cIB(7u3$wrp!`z5XqPW`e&hnK(n!TGrL|kTnPlJv_Y}@-Lc~9c!7y+gO+s_zq
zOBVd3<I_)Hl;%~6d7x`Z%|zJiCgc9CbYH)gA}t_F*!JG@(4|9Prekg%n0x@<yOTr(
zpO7?HNXc5n-`#>>w{;1uN5)q}pZc1$rq0|Nl#Y10;$EzlhaPNT_VSRWxsJ0ulttSF
ziey*w$`fhEpOVOe=veJF;M5De{!8}0`OhBBzu?s?A*qLi<J3ibj5cWHmDRARs@Y!=
zYTo2QZK`u*YTMJ+pZFit8s^$x0AIDMBkU;njcj`jQrLqX(md9(HeEJJ45z;v!5G~J
zg{1%BUj_Bq&%9S&%pvXvP2w=oE&&w0&YzK<vh2sp5X;#UUSL^KN9ahof8fcUYAz+8
zlyO^7fSn|77eyxb_fj^}D)Y;Lf>ea_RcR$&CH^2d*6IPUe5Kt+|HA4^MNBx?Z+{z_
zk+tduxShi*szQ13g7<VL@=Pr@^T3ZOtVjctFXot%viI}dhYWt4Tafm3H0t-phu_v?
z`ybNF2!h~5{90bm;;|6wpli4*a5|eX(Z03wXAkK7g@0F$p6D%5im7p7#$7o_7EHUv
zf=;38v@L9|^by-wA8<Ijf!75Gwtkk%sn<S@D_50(#KJ2!WxqTGQkYLo>#>=5D8f8b
zSV^xW*X6uQz9BHh%2l`GH<pTRmF?g5ov;As3Q6(Ueq%QS#B<v=?JJ8wnG|z13VKJ1
z7erItI_Jb!q<L{-d5HR$e|6cZZTd>EOQm=q*qJZ8x6n6cBHnJXrfMtkXoiu3lZjcX
z^R?(w@aA+|MG-n~dxw$pljOkqyN+P9oufsc-{ISXwkDY<$D+kdBuS1vgv80QQ?(C=
zToWff_W>fyZ+Nul-p%<p!61%kC1Cq?j~ul&W|zI(1yu7vT^trl&Dz8+%O)v89cxAC
zQ*FzF=!c@MVz;eTy2)}jcx87#rVdw8K?(Yz9h0~jEb^k&(3E+<F}+YlVEaB(5$597
zGM8<B$}ktPl9CZwek+s*?;@6H0Bf7RQD;fb+Q?4M7V}YRrH+%hL$gKe;x>1LIX_7X
zdIPxFv{_S~?mypF%#GNrO#g`$P2jMZp9dnaqTJ@f`T6*C2i>=W++o_w`+GXVoSxjd
z`0lO)JZJ;mpKlO0!g1bmD^PrI<}ocK>JzP2GQu@c%pC+9jtQlp&|+lPx3*fFnJse<
zIeV5Zeph|!!()Qt8juij_p=?_Bo`kxri;zJs9E6*n5~X6;UPvz%77uECf*rwI>gHD
zfU@g*J#Q1BQR-9lglp;X#mK?LW9yS8BlabV=k2M3obY3bB#|$wt#o*nsCO0=TIbhQ
zfx%~8`V2C*T)$%f_6j)lQ3ESsCDEaOD)HFr7LbZbuVA;e@uz5fzR`529J|xjOVu=L
zO0?~e`SUlN+EcI6e;TYc1XdRd61e)Lx)F_+${S?Zlj>q_6;{N=Bf;G_CIjEW5+3P)
zs|Xo}lh)=VyEgGX4UV7t9Cp(fgugu-R<Qj&@7HlPUM>X(p%BeVG?5r1h&>!r=bPwO
ziNM#<ZaPy&$N8SRKagaDwHFJ#uEc&&ftc*Hy6=e(dNr}gqmY=W2pu*@9t4MIpp!-&
zH#KoMvCoAzqS<Rdr0RVHNaa>OD8LO$?lfDqI!%+V5iekp>r%fI7t*b{3*6MQ!V<1T
zE~`7SzX%)-gRKRr<vjbjHQBCAGQuNK9QhS3c7||+ZXpr0<eD%k-uHg|z5?q|C1D9A
z!2h_>&3wR$$?5qCHIm-2+CIVt9YcF+oMHqQ?GN@3-~gKF0yeep(%h(&v9VJ*gkxnR
z;r>^&_Ihsl4NjLws;t3$XW7F(<aO<m5eI<ALa5rabMLYJW%NRg>jwQ^`wFCY=HKeH
za<~5=JP`^r)FT;Tm*j?7b^ES1-7*R0r*L#kmu@{P+6lCi&#BdXRq&6WlF<PeKR9cR
z_h%0eUS4G=6%m<80&M{^H-mmc?7(_jf-~j(65;sOr*)TnTUIy&KE@TH&$eE|?FYOc
zqy6>R2IdwQsF*CTj;?w&c+BxXV~z<+t~45`DW$St-pAKK&%l_?2fPc={<`c^(EXq+
z<l9S7WjW!m(V?M&qotuItv+>}3WAA$fSw3=X`=r-@oMDeq0=R3|BY-VFrt0tTN62I
z|DO^2XtL-@uW!Fjor6c*MNb6Qn`lA#OQQ6LPCQ40r`h6qMW{^3T_EjqeQwK!HIOBN
zq>_(3Tu$U#e81K>-|`yR^jdjr|F57B*T#!0_$R4;6=>QKi1f;p%I)x0l4Z*;FjHhh
z8$kxx4Xrr+e;9l7K&Zd(e|#|3LQ<)0lNObtk}ZbURFW1dq_T`sschLAGltQq6k()A
zWi6$K(oVKfiYaA^CbEr~!dQl3FbuxuIraL!-@niA^T+qkdCooeo^$TG_j#Y^o^u|E
zv0NU7!JZc15xtR%GG&^0(C`L=*e8&mMcGtFPl<4ija<X5ejcR#Q0I_qt0A$%_6;G`
z9+a>FcA(08Jo<M#&556w`cTBpDocDMj?8Dq{%Nk-I&kKnyzZT!(h$ZHa2b^BQ(s5@
zDs6OfZW=L-mWjL@l>~EpG+!4p#yh6Ma!5xnO|<qzuT&gMMa~Kvny6M&rfhmo&x&ws
z=K2ns=jF{0Zdmi-gfAMQ2lQ{LGYby8IP`w9ce{|;AuRbQ^>bgqhI-iUj=ew=Cp=dF
zQ`xy&aE|8n5y=;09iH3(`yPB2Fw#8Pk0Q5EY<q0Dp*)-df*nkaGBd|G)_EM?fGDIF
zml2hs1gKbW-znaeOi^n75hL#HacOO`;|6kh8$0928eq-6<Pm~oHf=BYyz3rm{`DXW
z=5XM?y#N(ua+0QNBw!u3^q|d*)gQpaa8Dz*PH%f0u<_4uKWwK4eE)I0G<Ne67~lp&
zIpQ>SH9%vg$jugPv7NqmfH7UeGM%QwDUaRbqTOuA<#+N9{2evDo_|a3>VxuO#C?1{
zXcdgQ_YI5+fzgnLZX-7-7@;TjFBOahg}oelUlo}{I$;-Dk|y;YJk>D|JTJJoD+<Ir
zoy~1kauo!8xq+cr3?(w$rFv9NG+DHXGk&DgdLQ=1Sh2^4=pbi22^{!JdFHxYk?Vum
z0A@Ict9u+iIAUGH{B*w@)^&~5!uz$@(PKw#3vVx6m&MyDai`DM2h)&U4PZU$Xi=;p
zRowd1#iLn1w6U6PTdkovmdwkZs_U1QyPQ8!C-G{(zX?kuVh5lEgTo3(^Wi;B&TAgn
zMkNtDt>+HQE?O$Hz&WyK(H8hB=r}<eE3#M)xFao)#n0J^7ByGq6~7w$71*IsP}=eP
zwrgXHe~aCba?I&}Dn8PUu!wu!MN3H_j&K4*9Tf<(K@&4xl$8iS=AA4T$=0@F;?+qh
z(g6?t<t2)i>v5|X254N3o4y0-;{{YJNPK7|{R;ChZ&pYzX<}b0!AhCA{^jV1K6Ci-
zuK9o_28S^P!A4>Pq4!$D5>dd<lXs4EJw6)tc3@Y<hJQKnLlfJ=9s=6fT~N)*n9@y!
zgyjRRk6b-H1+5?I-ECPOEVg3NGO0ZJ-`k8KL#DdX&hwJ)8Je#k<NCrQf@k<}D{J`Z
zc}I`f_a{phNRbg{whA|_>DW#4X}hKbKxaE>lsR0BePaXPEsf}+0E0-LU_n>YT7~v|
zFiRNvjl*gMF;>FI&H#*fn9YwiGF*{|(cR1Y-b(5^zwuZ4Jx7o64)+o<s_#L$5V5rd
zLmQY*1v>yVPs?RWWxV6avo>Sqj0u6(70?O{?Qv;yo%m+Ew)Ul^YQ<i5Va9r}Z9Pv}
z;(*ITK=!yx=Sbnx{J&euix_B$1b+xj3~OKJsZ^Z&zXWLF!0v~D+j5tVm(EO2_)fz(
zt`t0H4ZUToP!({~ON6zv=pQF{WET78h4fHmzGO{&mzdDI8yLs(l`b%C&cdDT@hR+0
zCuo_E`32L<nP&cF!&JJU>RIl<H=cV*BMSZCk8T$XSuj)h_E1AyYyZ@O@xG(40-Q%n
z7^m*Qcl0}4Mp;l{8xiM1^zLyYc!e1P;-|FBpA`{5K9BojEQdtWN~A~4BA?md=1sLK
zW;!;Exz5bxTAH>I_qq`AJx&@?Nm9%`f9zyUhXu2~z+NcPA2L{>oGj5VIWvK;F)duk
z<;RJgF*DcZwFPqdEeQlqXNf+~bG%U-{w~A#a4=%uI+Ub?#pB$gMcZVFa1bS*bB)q=
zT!Nb(wxu<3@Z7+bM>jm3_qXkz_#_JmrUD?B+gmo<H+;50>{h4ncYN;A*B4}oUI@8H
zl&)g}ZhAzod(TfwXk(F^QQ3q1(nljVXT2^#9nC8rnSF<}==<Otu6BSuI5kf15xTXf
zr1X&1Fd6eic_*NnDPoiVj(NVt1N98_BpGvDovUqV4<EQNE57YNKAb6Az%AIa>3%iC
z<mGs58is#}t3BHPeW%fCgFplS-+GVNpj!XscU+sRJ+M9IKeWoT1z9>X_}wPcjh*#!
z#H7d)VO{)*?{2d)Uti2q`iJt@h89Q35|b?JR!Rf~57R5p0yHr=$!vkBa|p^-Hj{d6
zU-hm%|JnWBeAz4q;UmeF;|0o^0~vs_OOH~uvbbFUMdBlO*~t=jUa`@JYAKafJB{uh
z=HCnZeZ){7#ij>Jb`=w`_xr(lh(03P?N8FoG(?s8+eXIoacw@FfYOl-PNO=8weFwN
z(OwJxWo`QD5rR^%Ieo%*aHS2?%y(0MwGHLlJ-BjnGxa2S+&Xhg-^cK`q4c^mo||MV
zRh~Jp-clA>a(dxcb-0!$+TS}%GQ+Z}y<<x8$zwlWX&RM1_P4wjW2_M@E49$|KjIur
zmx!Zo#Z(crrm4&p)a#x}!SG-B7PgU=CtIeZUy3gxqIUheekyIQUv|K%*tswibs#K|
z|3RT|=(^)1gn{{$33qryMR*OB=$p<Q$s56U+%C8Gs~2e4d1^&CO^X{FJaNd1al6Gg
zb2J9Sc_RFtH_-a?mxnp(_`b+q$-a$)D2qntsny}M#oXACiO@}f4*Wy7jKbZS{$)aX
z1R?xS|9|WTpsT4`rU)yS)wn)ONr6;jD%mE%rc6oTCf@Q<CGuG3BiGiF%AKV_s9ia*
zabM&eJMb2~<N3@ydBvp<qCo1|f)JcGRES9tHxzk;UpUz=u(r^&jl?dqEG?ZSU*Y_B
z76Hc+(9Pj;jiMDel!PC=iLufB7KDxJs4QO~nweG|MiX1^w>%$0L>l_l`X7<j9A;x|
zoVjf8b4#2VO4H`oI_+Y_3?s3!Kvz0OJeUj2YS@-@sxl$c&1Bk!N}fwJ`;Q7GBEE9@
zL&$;~`hE=Kdwn)8YSRbZnS+xS)Y35hj3+Q^?f)1RN9zr0+&g7B-tU}fBQHv#h<=nn
zRgU_n;I)OzUn$MNGG2=|zAZt<YsFu)n|obZAOjbcn-^{smb4c-Sxm2H;#Y{aCGj0T
zN10NzUg)owtinYRWjvn<n<O*WVv0KM^k?SQNM`QufD9FZhW)fPb1e6_7i}i&{)b64
z5toc_i`MWf8%1VO(N#Gbu6HF?vh#o$b1c4;6umBvcjJvwZm<|K!|esLu+v=%SS>C`
zJDop_n|{qy<qmb-c=L$VV)MLBubU*b?)6{eSA=M=%8b9Xk+hj!d@OZrifomU9lJxE
z6k}}2bn`Ej46E#_6s`I2&x`6h2JT1u9!4z^2d}QSkridj*>F0I;>cr-*o|F<vjnM+
z!W*l^u44m(wXJ%n0s7w;$lJHLayKr!Gv=@}Lpf?wN~h`v61+QBEai5$W`^L}j(QK|
zfq+XawY*6G>J<rk@?ZzXWIBjjhpI4~)c7a$gupufd~VR~q11#+1z<Ag`-7q%y5J*_
z3-6r=ESQA2Qc~!;L|)+=$Lf&M^-Qz-dZXyJG+{X|!;PEWJajR^z5wR@eL!&Z!GFn+
z<uK~PP>C|n=-iDfH&Gjk9jv;cDCjjkUb=};t-+{~I_@0VkKDoknJ(9<P2<^)w7}0>
z>Tu$L-T-y(PtD+lDnHk*f$=M^pm;jH0J{YV<v@&ol8%?R2~!Y!KFPGYjF0;H6Z!m$
zktM!OY<an!jjWd!yP?)UOv)T^R!AmAip`JF6~vH3=00O}7I4CoFsvU}EKPsEE+)j@
zcvT5_34fRUKd|i0vnIj-c9#}di@RYgswXH3@=SjhNm`ctFD)yFFqB>2J8|U}vaN}~
zs*U;=a!=Z3yf!jg>l(&aG4k~RB!j<m_NES3?!jfp#AG`&RIRykqEYk+_7;WGFUDn*
z7!~CIA#nW<!CA-vJH1sn*}mlzEzmmZ{g8O*y{1ft9@EnAbG^ZS*ivemzM?|@TGD<D
zQ)sTWcglMFw3sp0M+TBewqm3>^B@b-NLV)bBuaBCo7bj|{~jfmx)Y*T6d)!|8Y0Ag
z(s&wg372r?qP}~%BTq3DLqQgXl1lv$3;`Y=nre_CMrUV})L;nM-S<sx9yeUeEYvNV
zNQ<iH_TZ*ZE<XNoD9|l$e|kyh&gKs&r~iL@17=}n=|t-E5;*p2h#GFDKCEVxWqw2!
z|MwODgPl~K*;~pjDmf2mN+zyG?a}6P63vKj<*ZJ6>mX)rKdIrhf!&a?1bj<Mh*^8n
zISMl$lmz|NkF9fT6cq%8nUQPgUCba{)Q)j$S%|6fm6(GpvPRdl1JBKH(V|)>*UYa4
z?#hBP7B-Eo&Mm@l78Ghio$iSyNjQl_{d<H4OO`VU8LuZUM&+6^%~Gs_YhE^nf8i}Q
zoKq-7ec$`Xkn_FzF`ShGUh<o8I$m)R6h&vU^+)cH;igwy8?zqtb4yC=tdS?SSj!yP
z|KFO=;<>)<!Ek08^7&RlLa8$T&o`qnR)WCfq`*##JZ}rzmiyA}xx5IL0=>aY!u?)0
z|D1+x#$qnJYk2)7oHZeZL8;}PNmMI}MTI{E)~P%b0Kx{#aTZ!Gv4UwToCvpGV#L&U
z5R9=7rq?x~2Q*MBFhiHKNXma^)Md)ST!%}MM-zoT<b8)|j?G+t=JQRDRFzt^QSOL{
zIN{=a$?C|TxHm_Odz*DA(j5O(gBxKRl`?mxXDVd>jZw?w2&w2Zf2TznnU+dAM=^Hh
zQ9wV=Gtv~lK#f~A>hw54{*fUcFWsOW9sb{KJL!0(Y+Si8i)|N@QiGdrNC+l>!X&vJ
zMG5|HEVJft;Ru@-wQ593z)N}ED#Y+#-F)V6m5Y*ZkN!KsQpf}cv5n3%AyDNLFUF$k
z9_4sh^Zt*8LupD{(K3H`5?N#?(VxedHvuBQ);a-I>PM$7=9{DB=SkiM3NRK`%VA~I
zDzuzv(kI{g`dzpNnrDuRh?8tZG5@y%5_Iq|4M$@vtB`7RCL_Dr;x!UY-5tI6WeGD+
z_1DJgxY91qk7rICf(`=NZOH3JPBK94gUD4}d7|)U+Ntvx{`w@;nmeP&2ZG6gXk-F+
z^z8iUm81(-VXCf?dN*!wWai~6M@OtKLn6l%CF?zH-^BjyDgvI&>$Y7uPpm7d#k1!g
zoDp~aS=d+W3g5obVJrk=89K3vpTC9Pg^s><)e~U>Z6J|xRiwd2w1`0fASQDiH-6;t
zW2lv`B;@mT?w=XY9eH`0mwCWOgUikx+C}Pn&htS>*IB}Pa`lpIuNL?C=bfMqvop<A
zw`y3a)q|}ngHqjLgkAc;69L}FsdQZ}*QkYX8p=iSu#-#XdqU93oi3`2QJw}MN)}1#
zI<j@8IZb$)f9uqMJD-*137wM<NI9q{c_Vek(L5182GNH@PyCYAOdG6|(4MSoc{`UB
zjyk;!#6_`(8FI)zmR6^+#R0f@H#QVp?X0SVG6Y@C&LT}WARAYjv*-v6-~*Csm8+#F
zRXlR`B+2c;PWeg{K_{<23X{2hHflCqQ0G)Y8r4{Wu;nZ|4peY?HUVhR7hH(Ft6Z_7
z_ybl<yarL2<>hxR@WMEz!1|n2bdXCMDbB@lY6D{XDXTfkKf&(hWKc`<N=L6kLC7$L
zV62MI{BkW7;rJyWp-M$Ro$nc;<ieWRfsi~`!mGXk5@{LKU4zmw=Z6`Bmx%g+1Op@x
z>tP)&75#I5TSS~QYy1fMwGNPQ=41oOv@}Y6W$C!{gN%V+e@T|sPO0|>LTUW<^dvmW
zOX<8><}_VD0*kDWlVL`eLMSn0V`iQs{5LnuEVGU7L$b}27d7Y==*-!bHHcMPz-7l8
zq1Gk5&2uzjJCzzD8h-J%@cmgG2rp#&z+Xx5S2^#4M>;Y)hkjZvUCGQ#@`MWc=Lwm;
zbp3=a2#fVf__Yl&;%rz7@Yja(H!?NoJ~97D*f?*LC4(*31oJdRt;>Ad%hF(n;4rwy
z)jvy%HNL#YP(-YJSKSg+#Z}&bO{NPAeHPKvFwgTJc@kM4nD;<=?F-Y$a-{21p~s|3
zVwh3ZZ_rbyR5bB?>xpTOhR<}UaO0fq$eZ1$&p-5#FU>XcHLBv9VJp6T=1qYj0H@3s
zB}lB)gQRiZ{7a`B=#wjr8XKH`Cio4demxIi!4BNN9$+gsffWGQH-N+wZK1~^%&NjM
z?e3v5plFvy^~Q<eOvc)*g$O{+Z);=E1<BT;AYrT40FhVrU|E^3O|>o(Se2LLhVnW_
zO>;$bH0v2DqCp6J`%6XNQw)Z%FsjyLrqTfR1{muTS=9Fxe+SevC>nzVW3L^_kP5-y
zg7BdCu#f=xkX{bdG!3LLgDa#60GmVoUdALMr{SVytBS_bW(j!e3sCJExY}6=C(G^M
zly&_BOC=A5G6E5i6<}x&1Fi<hka`E&WJ7*|Jwm*~;5FgmX&CTt@4nCCnkS)N_R_x{
znH+rIKP7`|fwIE}h=JV7?--p1?4ecbn5`EBBn+;6SX34TKrC~)<mHGWuR6DQ+Mp@`
zVYD2{9x>dpI-o!o)qWjqfmZ};cU```ut61d+K!r5fXsH@l`GA?e@1jgSa-4i&@Y4$
z_jx6|+9>UnG<kOG-zFMJlVb<JN}A9p$J33F1~pf1H8=n10~#b%9<%@4-w%BxW4hwm
zF_2dnD`)>z@`Q%znuW+woYOrz3UX|x4WCD>+hbp7#3TwuSjH3~sT?P0&aG|Ms0wAp
zU~6>{V(~JU!a`tr%h{PvB;nmTN1+5T0J`J$pFya`mi|k1O+q!L@Q3Qq(J%>><yqW-
zL#R5iz9l}VZ&UzicXqVlo0x{qFM6v=%E+i_O;Da5WSc`w>bF);7#QgSv65TM!U}J|
zz&6x0M?}&U_O1QDK(ZuEmpaIiy?b9c!a*T$uodAu<(q_qen0uwGkOAu#Y}?rF1>4w
zL1|eeD!N&XYb6oq*fj}bP&Uj5;p%R_0MW((?BIVM<mCt?Y;L0sOVn}Axeei}6#~2<
zt)2tlQRsCq|GN$3WPVw_stl3kwqy{F*tqxKCnfMi4f1F$UhLQrXau$p&@sJ$C`_4y
zz~Ml#LKWp_P0ckhe~WOn>bU825c6QaM9j;Wu1lDiT8`fTc;Z0Yayx%q!lEs07;4gu
z8QH4re%2xB<wg;Pu&P*A(vhise}60JD*-BUV`c{MaiGzcg#^$j$ZkhPE@u6&G&PsN
z;F`GFrT@}kzm#-|h`v=QR7<pk5*aXO^f7tN&pI%7JxuxYMM%tL4TuGkmNK8?!NKZh
znEB5JB`F5$Kn^rXtLZ44z$?l9N$ix9LO}${@OH!t`ej94xf2Jg%+fSdKzXgFra{aP
z#F3aD6sAuMoD6R(!l6*{pfK=mgTg-0`QHeRmBUra(x?Nw4nPHL%RhhE$MLxYmar>9
zQwH^9A+8qc-$GCh@aPaV=1yrV0v`YNGGhM1{?z|tW2i5C;>x$S5B!V^@`;*g)RWXF
zdIeE)q@gwn+G68}IDQK-BU6nq15=}loBqqWXy7EV?Fn$6r^Xd8Vg41<n1fx*(liAz
zO{i%$Xp1>Z^2+~TpQ&@OyIGnhKx=Ur_QF6YE2(y+!*ZBiKT^6k28H?#77yvYf1iz3
z?7fRZUH{*nb=qvL4Ww#aq`7d2ff-fuiHiY&Qw#U!*)<N)2%f2E%A=kvmON8Pp5K0w
zpI!xuRgfqaXcdxO+KC0}ueuVn6j4v0c(ml%wRU14JX6+Ik~}j)+OhxFXP1o9U&*WJ
z%tk#)d;oz1!|L3BF6PLw$iH4-Pmi2HMITcLj#5LODX_?$@NE1vD%$1WXG)HdKR04e
zzYRx4oA}ATo|z*$1e(;#t2E}A?N&`&k3o4UQ`0h$X9n+#Ii~Q;co_;lCM3_6=Djz@
zo2+HsHd~EqA3$5!C<bGy$QA>EfL3Gj=jS$u#I7@e^)fyxvr$DRxLQY0mfE48sv8_D
z?#tI|Ed=nCzkQij>MqNOh5^hCQSEJaAZFFkktVbLh=CaQTdh%0akEnzfj$|AO2$Xf
zKI6JK?YwGad=h7&ip&7(2y6?p&F{R;4l8Ll9rK_AsEW@}Vt)?zpV^Qi4N+oU0ABU(
zfFaYkS{BuE`_E72EI}aA&Z}O%OBs5xz}2b(b4cZPmAPCohItlaEGNRR1%}q3+5x2*
zjC2kFsG+oA8%O?y`T*@1TrG5rMvC>y%R+h2%yf)AwXb}gAtktD5iotJQW_Od%U~x!
z*9y<vX@B_rFCusa0OtVQhJtI1VT3wIme?dUKE|P#VS}0~U|Ut^!fE9!=DDnhLxGY=
zS#g*y*jUi;#d`HQpPzXv!~ED$RK;Ah1#A|Wk6UrmNCABSNh}9TxSEDxnTw_q6$MwH
zN}+bnk#x0k6)xlSz|<7dE>6OA8b<yOL{v$-&tTZrLaNEdlsQ~VbtVaU=7plBF+h5K
zD<(rDWF&hGp@ifT5hS$+QDekD8)9{c6w3F}ciG-DsOx%v{@5HNCTy_F2**p%^=#1=
z6yVRnjb`(5$lJJDJNzqldTqc7RK=;k|9I0F^Ut(HJWSz}Y$?fFU(P&hUSf3lk&U>#
zx-w4uUcb;f_zM#iEvp!eaI=;f6NjMU$*6HbhYp^!Sa8y_{3E#+gQQTtaU!4Zd6`rI
zj#H?I%yPJf1`whlT|Ef;KP#YG-GM_rYTaBMlzow2E(e$A4Dq+``T;g@6bD#N=)Rjo
z<Bx_%KoAeg3*gv6<2#fEReF@Eo1c@kg6GJfAlnBSHh@-$l#xQoEoH(oORK>}J*aM$
z@CB8lkp^dIX7fb1RsEv4PbwFp4kTiLgCM8`Q*jvS_1$X-xsDK%k{OewzwK145~ZTw
z1B92ct>@G{h{*mYRg7G0gRL!0V%P$+Zvjj+9#T`JqK6a^Hh&+XW%dmD+D?yFHf36j
z?~+4`oFjCGxTt%~VUpNwBzrb0e+z9XD6=6>d=x2wT9`R+kU3Pn0rf-)Q9uWr3ZpC0
z7BK4}tC+0OagiPrldHHWc~ZZM>9{~N$x;mGUQJnqIuL__(ns<g@Esi@VPpMy@mc{d
zHtRe*oV|#vsjEKp$v)N?^#p}0w*vWk7I1z3sADd-223&yg3BLPv*t;3_KU-NC26#f
z8yipVHP*|p7>brd!10V=@k_K6L?uH$*F`ATrMf`$+it5>2v1EJS;P2r3?qeB94!Y|
z7{N)pYvA~Yy1bKC;6USC!sOn9DKW<(zidQ4LR6DN@JD40Zgb`w!KV+o8&RjdspK%K
z_=C-iMaUI-w(Q1kn1(;rG)q)i>|%pfMvGD?4jx=;8VOnH=D2bw9K_AkwVh`9uwyo@
zrW<CxX`Afm&15PI(p43RzehqAql(r_nssLuxTyBR=79RGBuMpfu*sE*o)qZn;nOgb
zjbXIvU$X8EW=ujnxhtvKDkL@q2n}%Ma3j2(wgticI8DVMO-EKRb5{x~N~3!rn9xar
z9~Mj{2T{eznAmOJvZ6L!RZ_Q(j|u8D+}yz9uO*nwEasMBX~SMEuBBvl-Y5#*D+=u3
zkf}VMTSD2?ojsZM9aRB=smSADIijCu#W6&_%NOBYEC=!WNo@e90JMv?@-ZBVQUS4|
z00Mp>8SGRRxSJ|*td`zVn56BJ$F~63cUT$-q2{}S01C9&@ngt?U_i6I(=axJv3GTf
zn=iqHB~tR5p%e^=_sBs`l<Zf20I}-SXbk=~D8-i++a>FM#*o?k2Uty=3u!`0rc`n_
z^mMt?nWjts9gmCRvbJGE8A~-$McTM>D7FIn%DYLm>dT(g{(-9KR}kET@l)i8oADJc
z5e4zpjM0LN7>X0*wjFKULa=%+6<u;^9N8Dn)}TdqA7ONhU>lIJfP+>N2K2rL?Cy`G
zyl@&t3kM8Bl_mTwV9<x=Ga~CAX2_HwiNk2R6DdKCtwUcx3)>_lkPCD;-koNAr4lzC
zByEcp)ku~QKnOv-6-4GlIZ=}ON&{xn)SIH*f$$SDD1!PNZXEd#OxsoX=39io)R=Ff
z73`wfKt2NR0By$VEbJ0btZ?N}hvaA#1DTVWY|KoU^m#OVY1@o<b?6j#W`k-IF!-Ao
z%7(+VE-vVB1=Cxy;~J}T4b-`gaL(H_m&;Je%E8!7AS7K6f#g#OW~|^K{w#*_Oq;uO
z!D}6#jc`;PlM1~J-YlX53Kgp;IIk%10mJ#M&P@hczsaEnKvrPy_F87WK>Bf$s=!7b
zDGxpe8HaUz(&xLZMdc5ue%Ix=Cy9atbfP|O{X?;aISdp?&G}q3)bz@{hM|~-&|FpJ
ztovj|m7<h+Ts!c@I}xm2!VIZ#XF=7IUGurbFsU0znS3X-2#R&+Q?;7X!rhR)iqQt)
zsQ75i%+dQ8$NX7EexCs}Ww=E$8wERQlnq}g7p-0zwr@bz(vAw7=blpv?#q}qH_e!N
zu`+N>k@N`_DtsU=>y&#%7_tK9;mV;T#!Waa!|7fE9t-%F_#2oRzv~!Q!mOglkP$qS
z{UvuGB3K3mX>tt^1OXo=2(~H2q}*7}WTY--rgTa_b~A?3eb{2DXt$H9!M4_`aMSN|
zz`uqWxBXAkTT7VFo24J$UcrQbZd3&ZEqaC)xf+Yt2IFdrke7qS^rL_p2+qE&%l&au
zO8JcE0?u@r&0(zdTev$K>jqJ6X+}F~3=A{-EMhr!l3!p0u1N|}lEtVfaDgasv}m~S
zSd_WhGC0=&NKGDesjS2OacoGG_slx&HeE$fnW;J1=#dnFYWGBo=xEVSs#p}U&pN#s
znXWDcq?ZPWRmctTosWwGw1cF`zH%Qk)M<l$++$|fGA17EA;rdKwDWaIrBVES=^5^j
zyXAz>5#5sEpI~X1FnE}4Z!U(V94`*|IRJo*-SXAeXE@Jc70<_&L+DA>EnM3wcQ}E;
zY+Zpf=pCrEQX@;OKK=7I4_f=gTA!(o`LpI%;-<gv!?nG1D=Jw+6@STvzY4wKuO+y0
z<gX_<o%H#!r}R(st;q(?=82{?-dPiJouI{1NsA1O<1CE<|1=C|GOn>}Ao#cp3WEAI
z;QA|Hjaz+0|I}c<R}O|Fy8flB*5(PE80K;zDbEc}bSOL>5+f`6K6cKUFd77MrDE_`
zF&sT+%G>j|HP<pZ6qj!A+zd7xJWU`|F!KtAvy2%6{~0I>()B2l*MgGLL$(9R_Z+V8
zTyFD#F4xXm-*0@4S35YWKI4+K$(!IvF~mY#C;U0wH=o}s)s`DHZ5H1!(D&+_4nPhD
z*AxXNiUMt_)y4w{D$f&achlqphwdYX3V0g=xa(48<*D<>+{v!<<cX7p3^E*26c7rm
znW~`krTQ4ErA<h9zr}^1Am~nribA7MHj*B}t(P3K|5J$`gL$`bqDKma0(8<F%b0{+
zLzzodr`F*dp4(Hc$c35OC{%?mm23~FDww441q+PrXx032z-~l^e}RI}<ZV=P^=EMA
z4!pxkn-QSA?0BgYD>4{`LaCxfSD-KpPG`tu&5CZ1pi>c5W8-{PtLb+ASQKh77J~<c
zL6D04N&$19HQO>Msp9i)HEs!haMH+fy1ff&lmaQd(8((!tS4ZU-y_or9T{g!Anvn}
z(K&_>5x+K4mO{0|`2?yGoEgU0G+3Thee+qi%)p_aRg>F3psz(4sPRU@ezg;30304&
z)Q41Z!%$Z(eC7gvE7_Jxz775w_b*tcy6Ojp!#v`^IuwG_XaMaYE0c2J`ZJ6VXYw9}
zvHVWk{H5Q<k@8#JZyCoUfwaCsr(mrhN$TA-!D|R}@FkUvTe{uxrgfz!QnWJibz;B=
zvV&HzoffzlN;awDX!WccLYrsHNwUPYujAZtzp%w~5YH9DM*Vi&^hO1ogTA9>`(OrB
zRZzNR=zM2AI}G`-Q9xWTyDQ~HAy@F?cPVhPy%Fl~c&=<U-ANqVS?{vW9Mx`$7C|QN
z{ba~efZzp@VL)6O#?exKOe?eC*%E1#Sv&rDIR;n$%OxpEolChQ?vPgsKI0-UTA0Xk
z6>gV`zNv@|VrISBdjw*2xEeNlXwP9|HMhdEWn@vuS1>hTc}?zJY!pMz*PH1Q?z3+0
zq>^#2g!iqU^JDe%Nm;0hPZA#Tvc}aG7le>sU}iG74b~1wKQpJp-_qrkUQhQX@v^}i
z7eaFk|9q(JEdb=KikdEfoK}Ku)KERzBH}SW?snO#M8|`|?MqrHW&5#fq9f*Vdm&Zv
zc1Od^ekfwf_TVhI9T*qL?rJ+(otsa}nbWcRoI!B3AC-*ll@m2T7$0V688WxbZ0XO1
zvxQOaVR(h4eoj_^Bkl*Zh=dm9=7)>%2^!qwna|zSH0(jZOV8^VPjg9{=U}1vld6S*
z<iI2hXM=q*eiF`fiPs~8p1Zzpb9PBmbvSY9G){%~2`m5$fz?j|gqlh|46);nCfY6g
ze{I>Xs-zMhhcwwmE3l)n7I2N?#C6qa{2*L;>ix)|PE3K0lGe4o$S60EQ5bu;FPCa?
zN4~yTKLD2|OQW}3Sqin)kE(NP4w^8N?pMu&ApW}C?x0sM`!AQsTFlP(IS0VPN0GOM
z8rK!-P4rRIbedjWz{EPcs6iUE3M#;!X5{k~pnVt1$cb*~F$9ZpL)>Wv_x*kQ(4s<K
zis}ky?RM~w%Y#={@Jm5}g<RO;qJpYNOPEWxhJ^+`%+N&quh4zOig7ott98fG%Z!JH
z19?G#3c*GBn_eW*GxQ}b4jMBZUtYja8r)kB4F863rmDg~HZc+>%#i|bDLxUy0f<+M
zug>S!i^8Fe>+tVJaQLz9biYlG+<jQvJ51M~(|-LBH~__IfI*}vAbfuB|B|nQQz`Hh
z_tA$ZN_ij9MayyJx0c6<{roO_a=WIxf8<g!p|8n-Io!dTH<=z`o|&%Lr>MeZOxLAM
z)uP?B%*erXZpSO>GqC_dr4dB{jy#3SWLl6n%_+1<trKG7pL<(OeVTm#K2o+%6<13-
zL<wg{MjjHLgH{;)=Qv!Hwds8o!EjQ<nxdkDi&IOO2P<cepKLTLC@x^-Wkg0>&gFu0
zDz<c$;NuSLT&_mONcia>yqe}#T8KBRUu(1`?<235t|8r?h(^X-4+yX8TnJS0$1MRo
zariu?9~f%dZDLz{lFQ=J`af-<m@8UzWWj8~&X*96=<6hecx6&~<Z{;bOEl$YQ}@UB
zM+)Ak@hQuJW~@1n$E%@hC`f3~BFL)ugai>c-G16FpPa2sxINv)Yb@YC-O(8p;o=c_
zP<TYDWnV9xi?C4+bGh<m6K>r1P=UZ+?Kym>t6NMN5b1R^PHUd34qo_H3Q@u*5-#fH
zc7_}=?2%INzIT3VxZ3txQOg}&nnvtzXIho>T+l^JXZ9DqR}kE-0>=t94ZSyFE6q6L
z0sceC)oqcy8dY6)VVpE#2%mxh^Tysro*4P)%xu9O{hWWkt$<|qPFL$~Q#&&5Zsa*}
z$l@<_*9C~Wj-ZL>=&@?tbF-S4QPZTzip<nZ`zoIR@|y~}#zI8kLulf~JAYa%r>1S@
z&)U%8dSx)V1i#?{@4OshFW1>rtNcBMJ908Tah^hQs7B%L3o3%H8L|D4*TqrnyqT!m
zG%1^ub4gYLlcjV|U&NYy)woMOX88QZ%ydoTHxq&;k3PZ72=MMJnf$JkX61p*-*|hm
zzRvXhA!nma$Ojc9-OV}1TFO+MU*yP(A?Ll36?v4lCTJ@Em@rnHsc^!Zrt*{}8~oaM
zS)yBj*4pHZVl=VtONjOL1!pzyEn}*h6=5=eWVaU0PfoB&>1J6@hHZJ+HXB9wHc@b}
zK*t6SV+)TtE@LXrd+mg_IH=-Z^*PROG9686=_%0MAv}&Mx|ch5hS;6~Zf|Q1oK8+(
zvQ7+{PSKmmq>`<YEp2HjzrGxAsb${h*!Sh8&lG1n2g*gek!BC!(IWpxfMM`DXrnEO
z2l0<`wF~tM<1qR)*`JFvt|&87n5<$!nD@grWfWnAS2~|txSUz(Y|}z8#@>X=z1?u@
zbd=Z<tV+1vRaT^VrGc{YtZvw^W;v%aP1Ha)n`pocgv^PDQAPaYq$iZsf}iICu3tiY
ze7}Qgur1Ek{#C74O2u0)P3G+6fSy`GPX)DZxG1-skk}BQ<)6IT7<&Vw>(F=n??7hP
z9B&8NEH9Ye_tv_*sZjYo$qd!<HE(!7jdLBN>O4huk`+Nn)M+YVr!5UWO>PVpb?OAH
z&K&JHd%bjg=cS3X`2X)f2C~Gh$UvIdBXxU#@J`{*5AmC61?`6`v2D)Q{qJSg5`~3x
zg%&r;{Wh{oq}s20rWI1fuh7ICp8h=U#*1x+)U<hyzovq0FEu{SC6_Oi6^j!oKTgxl
z&=uNc<^i%Ie?`F_0{LA|wvyoMIlczYp)|{X;#gtEuqbifkc^f1Smnbub%}mmxP+H`
zXw{xvDxc74?fo4XI`P)*GDiQv7oEtLZY&YmHf~%>XZqPs=fGLfmZY#YB|*ttu6GN+
zDzYjkdAd6*N41MOuB|?qVV?TA0Z}x@FSfiXUq7;3@4OhT8r2X^C&&R`n*za1AsyK;
zywcjcZaa+ALD<z2(XrJ8U?#m|%0o$Yj*X+_!ark*lyxQ_4><>_{5vL~jy*RF#c7o8
z)!pEm10|6a-B$d@1_=Vab=M9$8fIpN&MCBD6pe=<9E;Q>)O^){spoR<whYQeGV_y_
z1aFr0-TXcF?kwf8)u~T!x>g6>xjz0f-sT3&H75)IGn>D7k5EUd=&nZfBMg$N{82gZ
zOYEn`J$&ZJ3F*=Ifj4ro^&=VPGmhzIJwc7Zo)d5J(?eGH<jqk@vE?VXvzyWFiJn?8
zVUQ#Ik87zEu$$#b=``-$Ilh`4>*sf?hJVRmX35~TG8K1+?x%ywjC<7v`zjnmI_qOy
z%b;Ly_xm6NCjS(~?*|pmD(Xxay?Rh)YJ{cd6RDheo=;2g2<gEF4dFk2r*~!7s6~D+
z>pwRcVtZ=lSh=|IpmX2?kU6MDGD~+Mf{yet|7_F;!`*Fm<0?NIO>#Nvc!F)NmIgPb
z=Vf2NehbTBUvD*ey7YrHUqhm;)q>k|xl26-7l<EUoK+I&eYHFq(ws)zU3zgS5%6H-
z>jJ-SQ7KB&+}9}o`5~$1-?eZRqdS^m_SWfm!mvxku}F=iI|SzM@*kw#<OuWgp4H(j
z81ioS>)(5A=w<H8;}^fW1ZqZWlEQ$~+lQ7jBRq%o3P|shZkjmYJeQMV{RVEsHI`wO
z<ya9$7uPUfRqXOIr*CBKbT+9AhK%oo<p)DfKXV;VJy=P;i9d+1y4$Y(tSsmZQeh*a
zs|ZujKq&L3>~EC`-^ji#|94XEqeb(^%I;KuT6`Z<Ft-$U=1lEzn(DPqYUzP4w#v-m
zFr)T2&V1d!Is{GByNi@`jD1rJG}rVtk1q|6>FWd6YnyMXD&4W;UYKX^Io<tZ(mK0@
zD$;*#=AkXMbojhcPhG<lE=5js|Lv9X1o@|v-ho~2vjv_p<b9EI3-X8e<%*vb>kl5F
z7tZ;+Xm=|LUO$fX&;=J2wRBhabYrXKZT_X~U~!<W=l$VLK2tA>&7eI&twOoX++S7%
z?L`4mtvdhJ9>P+ZQH%%HaT;vmHFb(xt7iC0_M}4l1<$lsa7CKzxRu5tih2cE_TJ>l
zq}BS7x|DMRNv)qlteKMu{CM8oaQpNI^Ra3+mTI@JEahKYw5K^nOw~~8a+W9wHYGQE
zQ-&eQIqGgi_QXohy`1?D)Ba(B?Xbl!|Eso$Lr@E^ZL+u(m7;5M@?0RChP!69=*XX8
zy~gm(Ufs}3tWUDIt}ie2;Phqg??UP979Rgsd-^zQ;qrCDgDG+=nX}&aCoXO7+C?L1
z{qR-J?XI6!lM++>IAFpkFK{|Bmt-dO*Ah}NnPQ#P@qBw3vMx8y%A;k#{6(aSJh3{c
zEM%gOjI9)Kvod^d&s6djGq%v%98qQ?9Z<9fKFEC-iodabwS%VM$;zG8tX2Jr^#;Q?
zr;jD-+-z3QcTnLKzv^M+W&E;yz*Ckzy~W4@-W85J(Zq%lJU`E?seXmBBh59gNlV`B
z%To;B;(_vQ`CnrUFG~E!l)J@`{RRT*Zi2)|Bs-~3K4W5XP?M4%VlFoXFQ=|+b~2P&
zy6;PydGT2lSt4t_KQYYOdS-rvn{$R1n{aG6$`QMRFqiG7<fT*1Vin}}-^9SJ+Z^t&
zr(6m`>;_(u6j}d-%0x7gzrIY^<xC!P?ep7940dK6+im$_L+_c*><A?<>0H$>1(c^4
z2B@|-Y~2(wMNS`7+jrS%lv?VwJy47J?(^E!j)@=fHTo8ed*|+_9}?b|UigD8Gx8q4
zmKkVIW07=sQQC6A#k+aEW#@|ojM3t+wr&zWiC?co?F?EKq0Vkr^7`jdS64ja5RFr(
zgliK`H}r2y6~D9hR_C7IY+AJ(j-mnoG?a4g@VHq6zSoDHP7O3PKWsaITB^7Sa4gtV
zF&wd8n7!rd*Dh{`8dw5%HO<av8aU5Q83t_wd%}YE%$V#HE%&JXK1pvoh}v=y`yVP-
zpmJE;bS7yQLUs532yXg5ll@`IjHS_(>zb|`p+Db-5!fZOvYcy0qK<+ETsXCtqz)#h
zY+J!JknM{<4ghr6tFt@<_J%#<SHGB-f8e9)!=G(oZfwihS=$DrCWJ;n^Wq<xMvD|9
zb@1l%3oDqjfKI_Crj)esMrq?6!O?2I{i*{6S2=qt`g<?X3m5%^_o!t_6u%tTR!vq-
zH`zdmFWocw>Y{)Fqn-0D2ce$*3UXNe-QX8t9zn4rh4)DAi(SL;a4(*`0s?+EqKW$T
z*wF7xG%<VBU+tI8%tM_wE}31<>7_!V!?pvD72aq(EqTxufcmidKSR~{Ii{Pe!+Eas
z(v=snUf52b+`<0fYjpo;G+Rk6T)yNQZ>>D--k?}K0qKiw#T1%ri!}ab-_v?Ikjd7M
zyKq=eH0;><u~|6k$=W`3L{_nw(&`|5C8OX<i7p?HmleSoG~hR>@5R}EaIv!HJx%h4
zgxVy_k-8dTTbsl74@ZuPFW%yN5M0WHsJF92qobz&5JlZ54ZH|a6l_}3Y+f}}zI@x_
z+8`k7s0nMxKlz;4yz=0qbGm!$ul2Uk$8`UBKJ-_nrMR}QyIAR_hB#0CqZ-wzCQMyI
zH~U8K+I|ny9s3PB?LtMxVH9@6oc7|wuuu?FmyoDtm;uR(<C?Ll#>~t!-M<i$7L!xo
z4St%1ie9~p=3y01dkQ~@Dj!NI2`q~vX$|gZPHOju;i~1#ns<F2b2u^NoFOg2i!GXM
zj|nfZi%fd24QUpWejLIHb<pP76HIdOsWhq>7NF~}6{(|W9`Rb1ht^@JzR{GuHn736
zDJ}k%@Z-3mN15;1Y?7+9*51hd<)O!mkiD371RN!&p5Dr9cT;ps9qzu=IhX4~H4Qqa
z2-S*XUzNK1jE?>^?YeWcY(o^Ti+{kNhoLQ%m}kAzEPWB=px#xZTD^R~<1v-L-0E=c
zT_2TQG!4b3cWS?9397Z5MuXGq1}gn`*?y)T6H^`BAMgJb=_;+YC(=|W==eBr92aAS
ztvdCXs`)l^UDr>i>gCM%bNwA>baB>o(Wc}d*^i7G7WG@VOx}EO@a1LQFE?x0amD-{
z(QDbU9g02~n`xZA2Wf=3r?*PluMgVoB96D5RTL~fe7mSs3pY)QHD$OHln<DesE(b{
zJ9XW#b1dX{z{{M0lDX~Ic$I@xC&#7Czz2HFh^hmhkDYcJH$H9^IZ%WqCKT;%@f*Z&
znzH(h8a!mKe;%kWOTTzUc9&>MtNg$t`pheIxO1eEsrm38s`vtc(;UB~C<w~1Cb*}Y
zN!h&j?>G*=sy4N-7mz*WXxp1QIBY?FbZGyKzv5u_#JDfv_Ybs4Ic%1oHDX``&e}Fv
zKWQiJhC<7`M^R|e_N7gZLr&o0qO5eQ9mKPKUc<Wr;hM)2jqxGB7s-m0g$e?1jn=CR
z4N8;)l%klIyBu|HV2mK5*-d!?H&*ol?MCnAGr9wx*Em1wrcAkx6m-3-Gs>GOM=x-R
zY&mZ^`~Y~q0@<(e1?t?XIC7(!l0f>bWzmm+a8VuMN~G7dC&qrZecJr_Runm`ub}H&
zQvn@__d7+_9<vx`N?zZ3YnhI@<2!KHQOQ2QyT-+qH;?2L1tGakjWuDX3*;D+rvr~?
zA90~Xg$=9zZXp>DXUK1JjVwQAISi#FFKnQSkHpUspet4O(8e@g$G9oa;pVF57TxH5
z{Pr2qc)T?>!g$tHgOEkQi;~mak7k56W>%b{tG@Dd_!Ny{WH(|MIvp14zt3z4ckT<R
za>Pv(P54VkDYm{zm>$loow+3(eZFd-wYcDcpDDr%|9&=S?#$qLYju={kH+=FO?`X4
z7P0jY`RK0z3)*vlR>&bxE-q%pwh`W_Z_YF(D{Y#c-=Nc8*r?rd-<u|%zUwUid*u9M
z&y6R_Vk69yvDe3w9P!f~uBS=b7LO}UWdjN(mKg*e*$mUFC|I4Xx)>|3UB&iQ9dsL1
z38>R&-gUS~@$4RYNEKIfJ5F;bI}dzUkI!OE@}3?%TSB*fb1FS`AuehQwRA^!%r+J-
z>1<e&jCet5%x&>(LFsy1?d>-2%iRcJ%D27m+K4DK{Q@P=)L^=>v7n;gS=VEW`Fb1B
z>K(Wi?9kkpp?bDq5}oY07^{et`|hJUXg4SqaAgtqaO~H>ul(;Gt#5yiOPFZ(%-d;P
z^MurQu-%lNl>byKBNwqd{q^oNyYC08j@j&KPua%WoD?MdAtP2RJL?9Swz<25y1hGV
zv+aIDPmynbe``m?nJizUp-<}>X?#^7rnBfvv@;%uAXg<AcsE&}8e9{)=)etZh3?nM
z!uMxr49;Tv4`r*STQ^15$AC0G_Sjd3>z?wqoH`ntyPL*I#u&{TfAFUM%Q1J4Q55A|
zV7nYY#%f@t;+3I*)@yF2uG?TnZ**On+}`@C;vL;FS5Yeii;J>@GfeyQDu*qZXN8Tx
zZ#hM?R7Ftaz0BcbNtmnW4|naUfl80el><xtInp6?>#Hk*!xz9Sq}77yyQA}Rk&kl5
zMe9!96Z!BtjI#w1YTO{7?Kx?L-p6TAPA&pclTY&slb;2iRdmVRHf&*a8}=?L)k+|z
zWqc>lTUf1mn6=nSEwbt!vm}mFu52w!<Vww5-P>BMzr=5`9b+<dt<!stcYHU<#HjvK
zn&?2sa6(TVsb0d|c^>QAw{>LEbqwF&@Qmk}0n>Nd#NX~-*&%`~!&(}I4fRiXk9{}b
z=B395xZOmD#~8|&P0uUma9_UFF%4ZYahcaV8Cma-GWgKQxG|+DIQt7|ZOgGo5Zbj)
zzZeVq4W-A{uDiqw=`vNR9r~cdaHUl{_OA@k;<7&kZU0tT<zSn+H&UJJajcJ16D2ER
z+GdQOYMn0>m|Hg)?Jga*SH=s6XJw{M)z4miqElM^fpy@(?{;^idECg~XJ*UD5uFp*
z=c*3kR5dL%BISg;X@qOfC`J=3G|rPGjxDtsjU7Mb-!_{v)}!)?`8&hhr10`;FOGCf
zp0&>auRSeOS#UD0)Gs)8jym_L#!uRk1hy_;7VFpNKC<W=;k8?|-Kxp4JBrlO(ec12
zf?q;!<KljD``19L@>SBu(}EKw7c4v|lnNnK-=AKAvqlO6(p+ben!bGKHonilGKNwO
z9_5>K$`glrI1^(Hj7??REHhsV?`aTh-=#U_ALB^hrCT3d5OhM(VQhR3&eJ@P;q3TE
z1?Rc8`{Wk=yR6jmoozB!%pZ(~*}B|cu`|DH#8&4nm^6u7G*mU78g0IxzQYyNdxxif
zY<=wYBXJm`w0C1lzki-ni?O<2rS~}2<D8X$pI_*ry4Y`PD^k+>BR;p|tSf#{`c-Gf
z+fq#?M!s6kbfv<fy1wK^;MuRvy32hxz0m85DP8|%Y-Zx^D$8Hom@zmBoQG~gN1&Te
z&`r)%#D^rp=E2u$$IsoJ5$h&;-YrXFiKZXC&i%;NR=u1xfj-!reeI;GpeouZEo=WJ
zM%wW$a>VV4@7+}`FNQa^_jDWQs9v&+_OYKFyOIq>a#Lowy0r&#(gT?j6Hj__x7IwC
zr#okA`HEP#XQq;u^EjO|M6(vfun7wfwYl7%W*rxCww`KEwpM<9<j}=mC0xDGCck0g
ztgGHoIvjo0*3~xTL`Jqq@5wsWAXDa&xzLw>k+*<7JpaLj{8(EmPKW0Gv+$i&zpAFy
zl1RA`rzVy5lo!h6H%Uvar`r|QF<(;#9eoVzYF&RtQrhQ!@c@oU53N^y-+#M7!`bmb
z77yR%MlJQ6tdwJI&y|{@y^;yPUU=4MJm_t;u2%mxi_s);57eF)z4}y;<SsjL>WA>3
zS3LD2i(X1;KO&jRxXeg%=5mEix~AdVHYs<<&I})FSifdTpbUPn^IVdR`7Py;0shp_
znYf7?4;f=Un$H;n_I;ba?5(^HC<d9c&75yD%UoDz(s-F2mN7^~6`>6KO7Xzi#zj3F
zv!E1#K2dX=s@oOu_RZH5Y4EYCN+E|&=tWM{jqoGpmd+iif6{yQ1Y7=XBzrXIEKgC@
zY3eq)^D(Y%OwhRUh_YU84l6urFE^6g&zTjKHlQePmy+x-RY)0c@F5(y*JU&?c;4}?
zYmD{cGuSyf6IuuU@z-{JkTJB5&8ThAqgwq6Am>grsy~s-4yik71^1rTbIk^cHY#IR
zQ#y;YRi+v!<1D)|=!icsl;GIW5TgSfeR(i3#z<^3HQa~o*-NL~H&PTxq4ROwX`zc*
zj?~hmcgp0pq`TN(+#<gx#xpg#Q4?Ilyb<w~N4dcMZ5*ut=DERnW}v~zt?C#(7rR}^
z7qX4^(^N5D%6eTn^{3&Y-s9*%dwrBv-zxoTm%G{`7G<Jde(d1AE-9g?)@M=t=4aPE
zRMVWMBJlhD7r4?hL<?o6_rxNBXaz-9o*GXS&W6<aY@{d%3^$k!p0r66rloY=`spCH
zp-j|NUte?39zNI<Uvk`|v24chFZQ;ehrEYL>)Tkv_W?<mP-^I<Car&ubz*uBFcJWa
zr132DtCzpgpK|o?5|wzDk%lHd9$Yl{e2Y)CE1l9N-gEmMo9<)t?lj|LG=^2I$5~;0
z=4An{J12B;ZQ%5lzv86z9JH$@uFvh!@Rt|gHZCXilXf1`tlQce6wRSizFXxfcaYe_
zx`$tI?tnk29R2ipoxc@BL7=j)5QK0T$-mo~pI`rS2>*Qgkg!g8qtGhnM5D0cIWN=L
zi2Z#KMc2T*^RjsZV37Bic?GoG7e=_g{7_An5w$et+gfr{k~+4(+gyK$oWQu?Qs92+
z-F!XIN?5;?3aveEl`@c8w9tD>j3&Mwov)B_ElOs>o<^V*$2v|1-O1I~&OMq@@bktq
z-g$#7ueWXWZ4^Gq;c?dZ{2iFN#|De@d=x2l$LC(>#i)H;(LS>wgy|P|J1>75Hkr7v
zzbxR`KG#bJ4quZlbeS@^x7%M?6%v&OPH>U(HtfP`^`<Tx(jih}w>~bzh@hD%?A*$-
z+>}^@#mDe{*){uD5wb7NTd?-@QZ{3!^q*n9qVNTG`*9iJuI2V*zmpl$<HR1z9960n
zUa-x&rz<%lJY4H4xudGBjqdtrzhIx5{%S9;05)T5-PNi=1-gdUCi#K8TjWK*^a{#1
z=`>hP4Gq^3w!^9{=O&QrSWB_PgXYU76;#S<T#OFA?0c`b!@0J?k4}jQ-M6?B$;Eo(
zQB0e@+r#kaD{0phq(r={zVQ76EA>XL_e2)6emS3;5~b5~Gqzev6dTO_{FwAvj>hoX
zdNEEj^&cTCLFwLlt61K0-m2d_Rx=G=)<%9T9ntwlpjx>J9ISi0&ZZN?`+86BkoO#>
z-|$n=zJB@4-g`1z=+kHS7Hkab+Eccb_-r7@8&GcFxZpKaPo+<!UFxw}4cdz^${ZQ4
zaKKuPhFTO=8b-1WOfMS7Z@c?s@GQ=G=KjK6CwUHcNC|gBORoOq{@c%1J?plUY2*1f
zS1tU0ThD0Ghuy~lf2TxcG(3#0PPEo1eo=lxDwC`8X+1IbI&ROs3A=Y+cI*U~k8kMi
zpN~QZF$~ipo<S!rK|RyNWPYWfkoo)`|91$`zmBcG@8A>hDe?*F^@X~VzfR0qU`xxM
zkbgV!mwx-twIlH}$m(TjbF@1;6JDKUocIQx-bZ_yMQNE`VFN#(-fK9l8|;(s`RM7$
zp-qox&C)l|BMm=4S67#AE7Xg0A#_>Y!7}C72zZ*EOA?+(v9n~<xgP{(BdctZdRv}*
zZz=4w>F_*Qb|9wb)fx8%3tR^uki07$?`2!Y^K4g_9QItsjNj-maqMp5E?U<|&evSA
z)#DIWV&SIpIno0eY+sXGiFwtwho!1E(aqMT?O9x0-(9l8R^y{NCq{e*$xlfbihi{!
za2@Xpnn)LGN7l0HH;wg$=XPn{nTk48=3LqHn(RJr|H)mwedXO{c0Y^jKBe3Jp8L&R
z*GXBI>ni6O>1~ze|Iuysrj6JPdgXQNUtK5D$!AKhi{i%bh&H>G?d$9*j&iSm#=p7y
zQ#rFaVa}tCAzf<boy!Z~*P@A+UM&jTz-vSk@2f;iT+Pf46Z{z3*RI(S{oOY}xLNrD
zUpm;nrrgKt(xl$ePMpTQo0iFW!)`%l`D1Eaf7=Y~J5g_E{C!b?Nq1w^+CmKL%Q3gi
z!Qm&h)|Q?Z$@;oqL&qL@-d`g0#2KDw9KD=9S;Z7>-o9t?Yhw%ZOj*}AYKj8s-Sw@0
zU*4S0w+amX(V#E3%74yEEZB#yD|pdzG0*knuGSm0;l;18tqD)pZ%UMIy1H$^+4HmK
zOgv{9)YmPAjM9m!qPzaDniDLFY1g_EtSu*tGJV1XUx!@y4QHHgIvdqxO%yE2HSvp>
z>%yOft6h85bijFfCq>r`N6Xap5GDlKHTxB6hK5SbVp&F>84a>w@%rv|ro?FwDu2Bu
zCCj-yjZ0%c;VbSflkvPA_-@eUWM}QY;kALMsHG*ZJ|wRDJ=oNcUbv~hzj8++?+Q>Q
z6eCp6E~kBa!nb%xdc-QK33>9W?p^v$j$2y`ni%LGqJ8Ak(8~f#erQv3wTl+p#Ax6`
z#2KMp!u{h?uX7G_hCPMPOiP570Nn;u4Q_2*G||W3N!$C2l&OTOrFwoE+ZL#52tak`
z#IF-ypYTPGNm9?(j5Avtj<q}FcCHOPV~iH{{B*%%%wBvBy}I76vAD04?Hi%{ed>W>
zM2MODhdhmk?mzB)%|FaB$|XH2-k|!a;8|d9egAbc#zl-SBp$eOmU4X4x>tIuJPrFn
z%xjpo&gbv-5d97)%5^o`ck`oAZ(C(K<0;Q&QS^_)QP(0ZGp!p+A?wA%#33|wNvvc*
z{}^5NaE@VAn3+2#&-GzR$34A0Ky;ob(!I9IJL($IGE=9aG-3`HYf>AMw!XUY6|c0x
zKUSCBpYu2>XqI3pz2RcG@??}L+X*{=m?>U8e8#$`p|m+wj|rACK@vH1Zj@gfLfai*
zdm+G0{J=p!Oz1mVav?rSxcXO~r&is@zR4gLN1k%3$9>m>g~mI|yISqG(~?FDnR$UX
z17Fkz=Pa@N@uJ(WyYPc5FKCY|;|1kZ(X?y9z6_r25|7Gq-OWOA>$O!rq-#NzcRxk6
zJyH+^9MZS=mRjj|Ftn|=@I%r^n+JLL9}JU?IN|E$4?LAgCmYAoU0C0atU*7|yWG6$
zm&eF}EsaqBf7-jwh9;V5y$FIz6H)09MMXg=(mN3qk){G-p$do!N(n7=gMuhR1QewA
z5|DtXC|ywqH6Vs2RU##n&_XYFHoWh>|KNUlzh!pMJm<`rGc&uJndhi96o&}jZAxFT
zthWfbGOuj0Sru^b#y(PhXX>5NJP<AmCPw=(iL0i7m^(_+r<5D;eS@qZe;2Ywl_TWI
zN&=mU>_Vlh$h<Lk+V8cSk2FlA$c2lm_E*>iG_`0Q3lZ|Rp06LO=ENinZ0?yijL%W(
zea86k21;SEZ@iu?)Iq{iq{?(I(0aG_tA;h_*o-W%yuI@M^4apn4@t%w2Glo9Xpt6K
z!AFEwmR4}3iF!LwNs7V~a`I(_o`B-L?9QUOg~0tW#Z}FPXCICo^zSIoOGOYR=X=&O
z{4pahm3~e-wuV$CY(9&zEn7RYS(m!WRhgL=Y_HL^T&Ykl`=WJ9yu<Sv$l3h+0NLV$
zkxK=aj*ov!Pn%bX$Sar2X4M&k@i~_Z-`S5L&xRotl}S#!?=A&y5x4VB|JL1YNqcl!
zoDeEL-|e|)zjXE9i-Hu=aR=?O{($p~rz|!j2F`-iG)2WBByC$K?HLEkOTU4yBHLq0
zjqj68e_2pFnb0f@9SL`8iY+bN6cz`lEZ>EHlBm-UjagP%FDGiB=pni*^q}ka4SXs^
za2`N)l`DfK(b_XQT(LV}uQg;wHNa}<h{fiKL61^IsP>eDrR%`e@rfmuLXe9&IH-JJ
z6F7bDh2I}&Z`|+G;4e)|R7u+Un?WAWOJ>#mocqbA8$w18jR{!@e$hHP|0rI{mvujR
zV%Mlbi+4ulXR_0H^_bU>#CDR@hAoq_-upE4546sQ$=E#?2K0X0JF}NCt>$rE@2ZOq
z$}^DbbHTq;y1mbHGx?cp*&2sS48lQIK@P7({apC*SXC4`>AO__G{`}w1U|;AC?ub6
zcFG>E^S$5DbFG-_C704p>cVjEC}}{~b8!v3JUL3u=<+cHtJw3nZu469mBy%&EW0sh
zN41Q6=Y3;)+}_w}FFap}a6rCxc@1Q}--;m!#uu6$KT$_2<cK$!`5VueZ11tWubiGQ
z#hJ7BANfZX3}>)fuRwN$=8<(i^2l~5VT=tMbl<=WolNwrf6efh&0d|Pi7_h_X(#bK
zXN7IbK>v7L`ealuQ0I9?D8*EGP!1Vz=LxBJPN$~8)5SI3$p6Pb^{O#ulEUpIvv9{k
zmM^U0+$FHjykup}Hm>bd1^ZLw^o%VNMp1(<Hd@NsH;rh-q1Sq1?zE31;>gx0r+c6e
z4J2mHX~u(7APvM^OY-pEc{Q1i-rB7D8q2$Rm}6vPXeQenmY?0vnGIf$<feDx@v(lU
zqs~;>D`X)PsrhjxbbKy)dbm+8Wn*K3v5~LQ2N$?U%3LWmA1}tvr0huVO2wGA7i$#<
z(Nz?A;Ut6+w>;j${OuS@BxOs?J7X<$_S-6B*;?z*bJ&s-0`X>vUZxo5zsu=_4pXVQ
zaX?I^wQ0xc@g53`?=);RTIey-+!VWZ@qIEy<eP*8=Qzbt9~_B{pMsn7_eE78UJIL(
zZ}|uOmvzi_p;wm@B;_}I-dOPy#p;`c7;%hJZXf|#PZxi>ui8;c59^R`ISj-F$8;>t
zc+{9_pp)|iZqtm0UmK61XdXF9Aig}|_$u62eSP8lD_FdE@BBfYix!fonrMR`?@YE2
zTPmZ}%&Z>o+T+$~r?Y@rm<d{ukOM?N?<u>5Z(CzI7o0uv3tv`?1pB4483<CHj9tY@
z)lbbLM2Mu)^!=Db`JVQQKNY@FE*7Ilk;w%<k3*MK3H2bC4)-BKmQ7ca0M*^tRg|O|
zV#bluN>a??g{%Cmct3-Vb(KF6g&>+%R%s`kBydI+l__jhDNHeBvU^qKeU7A9)k?4!
zjZvD6V<wSRHSDhiN;1&)VIz_w2lO=pBh^f4^Be})`f{cJtC3PGQExa#VKoKkHDSMg
z=>bamvzlKYjRh$)q^RKEs)`r2!dks9V+qfH=WfYYxR1LOR@wjHA{R77jJ`$_%VYA-
z*nTk~M{T51NJ4KBoL=ZY+Rux=_9srnm%ci*&2OpdqGV=OadfZSVSAm0ZwJRL8qd7p
zGna7F4bZ1iz+W9Y<r*_S_cJQba?2X@)jSAfcb*byCB+tB!6aS)t~%R|jz!tp-{N^;
z9wl<M@-yQ)H+gzBTD|ksflM2qDg>yy8~^$7>n;9)9@WGbh4%O1V9Y{i%~UjfNpzDn
zdtv^Dns530aSJ#wpmQUhpM9h-R-spdTc*9@Wx-<CY-{UqVxYvNK8VTN@n&U-Udmlp
z-n5yJ-}@QUdL#6(^$+;GDnGPazI_%p`q1umbx5fKakNdf2aveKdXBGE=#{y>FI)mX
zb2gEh27i9!X1jLj2~58Zd&bwG7M+qg+ci7T*&~Ra7I=zqF!&^gmrL~0E!FcrLFfP#
ziokB5Pp(}}{L@)s`^iTr0qg<;A}te&Uk|_@_*vny0u<<d1KF3eeC$JM`^ha6Q5xOD
z+?lRJq@T>b_l3`0JWC`y<gLp)dHc%on6vwS7ADU>%>&Mxo%yWyMd{n|=W2iwJK{2y
z<$;j*#}8jE<5`fx=~G=re_I;N{q^)k2{&WTv`AnQ=fF@Rv8swAg>%sVfP;N<IIG(1
zE-@5MNG1~DaP^a%rh0!E*zpJW6LDQ0CScFhSFXbsF0R+S$a+cZl{>$CRWLdwd%UY?
z`Y%AY(mw{HSLP;_Cn6m7Vbm_r-gAgc6I8=J$C>Vnco%;twu}$KrZvm1-hUpz{@YTp
znY3JQP7iu7Zd9zV*T4@ymGf80d^j_YD;TxQH8qZZ*_VEbg@)V3HxP{%9J}Xe)*vQN
zfLW{YP4b1=hYu4F4u>&nNLqTtgbYETDXaD#iy`*e<E}=5sVpN7&?hA++2pRGv4t<@
z{)Y_2fPLx~k}Ld&&tYXbk-~*Oy7k8hw%@}mOa^X9`MVJ=Wxw4}J5(KFk<$8?!s@7j
zY)zk<P%G}ruL54+B7ep4xa(uo&bJXHjz`dbis^*gCHD}GXC1qj-6hQiAApCx(~Zeh
zi1|*rlgL*6gXjVZO)wh4$t5>`In1_lv4KnUt;15s!3|yxZ?)KbYL&$vFjkD5UsNDk
zz-CCWCoj)Oz8>V`5fQN2u6o9g&ibBaxki5Ws#$jZ{@ONggtro?RqIc$wSB;o9h@|8
zbvlSnq<n<c>{pmS2h=Qm<zjq$cWJ?WTSjo+1=tm}4#FhAlhv#E&l`>}(~vC}*#;Nu
zcF71i(0N8ZMAa^siKEi+&lSAC%Xh8px0`B}fo%0^f=wi|F@LJ%Ne2yWYzfYnI<ch3
zF3pM*&hj}PdW`UUH%F!ZD7}u--M5?P>2;EuNQ#tgpOijdLq9M8u9o(6OfU0TyFFLC
zNK@eeS=LyEd|x-evRoeua@Chz4^!FZ<?vC9^)=7xuoMr~K@e{K3imCWj^EW6i-^2Z
z`CR(|`Q4p*%VQpyu^LKu1WTF&va2*hGK7hLD{gzlb~S!22Ck4_N`CbDB_uJwOkgyT
z`h!gl_FFkBf=6QhuVROOV0xiuNG+&1E8$7yX-Y%BJWLK8^E>UQppUhx@`Tis-jd@t
zUQiAJM>-!=UzwR_@tFt~t&{mWl{2|!t28xd%~AHytkR4_<J*4ZR>hvjB5YKUn~T+q
zHK_I&I)OqH=&(Zu*acZM9rd2t^xz%O;*8*}XX;2PoWu_o)d#Q6zbmI0%s0+hPh$LR
z`EF_Qb6ncoZgO8@X4tP4rI>43f!sTPVmO#88JO4w8p}IE45&)34jB<P8s(0q;$rK$
zRJEysWF4MAKSOKz&Lph$2^>z1E&<E@cCKYP(tqE4_JawTf#L(l0%rUFaxV6cT@1g2
znK0^_>vH)v(olgG!TVU4yDD7%6TI>BR^p1^o;e5O6u+mt!vDBOInImVcpjNxDlTjc
zl{blue<Z%-{Q(<4f**cTpRw9uQAuIvvXMak#8mjpOI|-TrMw!#6!+{{b*4|x#p474
zyYQ+Kj**I`FI*YCfolu2b@{}rn<|$UGz{*%Q1e!Q?-QP&y19?(Gna0FB`uzP5``^2
zuNOHN5ra6DK|LLq$fK!fcd*tdu<B8Dh%s)E1wD|hr-gMWycFqUt1xEe3P~tik(<QO
zv?z8xtkoO2jjH)j^c+h2qRhtP*d)zSDQC?eJ7Mtq0}FaS-u;0ZGwQE8a}6g?l;6Y&
zyd~as?|f5K$e?Mcjpark78$OwDYUpI55An9BhcRa-U2keIQIgrva<QYT|;|x11{1Y
zyqwg-DxTMiW#EiP+^nVIYER<*othCBQ?@u%Hu(*40Y~h7+s^~S`ujF(o<|=SR$`%h
z?pXxtTQW&PMjjb(wRg6hBHidHA|U&$J*PTYqdKGnH^{eIwRr6|cKLSv%#j9Ho<SAJ
zt}KQeZHlG|4qDn_K?a5buP>iYL{#T&$XIT4$6aO9SXXynl~26BX*n@$toM-#J^164
zu0cTg#v_JQ0_m8@vBvzI$lD+RD|3Tjpr%lr_nfWmMVXbw<+hP}uulTq%xPX*_rZEu
zC8r;-ApBisfwaq#$qlAkfjEZ{?JDNgq3z~1UaqK3rX+XX;U7jX`F^xT59(|=4?k}<
zBVH0d;N*OHfCU}7d$pjz#5wctafTYZ_~#oBVno)*DS5*XGT_3N=wiD~5Raz(-Gib;
zf3b<`r+S!jFY9WGQ=lPp;~Z7o*i-nSGdSy>Dc`_tYQ$ci%{sq!l)A{K?#?^#k&~VO
zM~(5I9>r+*Jw<<JLg$N6TuhqJMtN_i(1jW_XUzdzxvw_uSJB7?td;W{Nm0pGYy{`4
z!us(-|9frHAxWzN^8tI$;6%URw^i2g_5vBTA|~}NVltsBP=0>v3_HoV_EQ2g`dX-a
zV7R$@i06cMMxD%f#d6Go_C3=iLM3f``Td2wM}JQ~)=`8ijQjfqa5*7oFdLsS^#qdb
zy;u#o2Z9-fewuvM!4T<jpA{|K$}H(;=+k5(<f7~0<(!+$Kae0rc=5bq^pqQoxA!$C
zyFh&|_n^@t5pmH&C^k2FaT2Gu9yxBz3w<;7TJ|N$*51a0W633pd~SmW^ZcKgSk!s`
z)vm3Rp)@aZFG}pW-d}eCm$RwT!Vc+x3L(JHFWV3z;CP+$!&gY*qsFnt7AtL^UBgut
zHoq_4_&_-;X{<iSE~f|yn(UY#3r<8@2-}38o;v%9RfJzL!X~FGq5I^EYyCf-;&Q6K
zhK(4Y7>hnpW(KaP%U8^vB~ZcPvXtkqG(<JG*}~Ssr#C{GBW!==QN<)$dri#19|H}}
z`@NxEHI@G~z|4zdUR3?3!*>HBHnXFxHSocZ7IV^Cgo;V;Zjym{fzO%%lkj6e;6UoH
zO!IlLGBt|aQqWxsm!t3<Smf`WFnTFSNJR}^9W+<Pl|2LBm20YUgE^o#raSgKEOX9}
zot%*UW??3#WQZ?L+WJL!9ImpuX+rD!L=hI&q8-@a^2la@QcQLn8r=m>Aly`8Upp7;
z&fjyDXH3zsv^Z(=SKDJYl~p0rt^r4qyc%Y!L>T4H0EPbJ)UQXu__YqTNF0>jtn*wl
z)@C_7N?!h@xgL=lF)TxFaVGHXhCbxa&|?T}h5Pnng1y7lMNCuP6A^3}sDp0rN>_QR
z;~Fs9OB9Au^LO020ZwL1Dd^=OBUK7B3Jo45CTFOw<`pyYxo@dHkDS;;I-(XaX#CSJ
z7lMLuGc(Iz9E#it_WN~|DpwFJ+4?Z9uvT?B?<<gJP!TTxy7|<i>S~!FUdx?e1Jn(b
z7KuGd{`FoI+YFtvlmm;#NdtIOo!J|`t=y2c-;T?@Maau*4xOs(lg}I%_;VK^BY&sG
zOCc6d9^pFHKT?>44VoVBf|^sy$`wtF*fAA&#}5A7WxxaCv;w4_?nptxL>l*QC{EkM
ztJ+Lmwkbgte5ESvD)O{QAZhi7dXE~{>YSZA>rOXdjQXrlL>#I)xHDi+KMF%o<#GO9
zcjXPYk0h`BT6txsVY_-u_!?|&JvFXS7ziKxM|k=n)@t&lWvwvEq+GJ)ekw*rc;i>%
zt796rn|F3<<WO@Z1y4aW`v26>$1c0yHyo)D=}x(Rd977qWZ(LHV&tRka1Khkub#(B
z1ZDo~E=WIJrCia}s1*ltPM|U-6>vha*>bH3SJg|e{fwRA6tyjz*C-2+kIdUUqfQ!D
z#no!EL)Nzd-DjSUTj!z%L29>7scWP%PRQ)8T<Z&l%6nOv&Xw<(ZLEa1+iCgeE6bf4
znJRud9>Y37S58?Otm`=wTGQ-=T<chS#r>=){IrUdu88_KH{o9&OE~j62CvF*+<=0@
zOw5+EDGfJ?VBh7#E2@S1_u`1b=&s8>gTGN#Q5wEa{;J^|?uwWRRb@O_DTW}~yoebg
zQb!3da-ik)YWM<Lj(Y3Vy05R{jYbE~_sJ}@=BW`}t=A3q>cfz=IH{#F!^h{%d-&K_
z#_!Leg1<hocJPfYSPy)<w#2iXSR5WHY^Tmi;q7rS@uC*p3OEDRnBx+Bb!dyH&tsR}
zY!n#%`J30TU*7stXnc6PedP4G%qIUjU`rFa-h>AcVc>zH<|ZfG@0quhY`&Xn6bv4M
z{4e)GkZ7dtd8EnZ9;-f7;~!0*)ZOaYwst93`zvc7tbT-`jy%H|3ljH-klkS4bDV-j
zT=ON+?3Bw5R(&3=>6$(ThtxBzY*ViNE6<ISq|5ID`!Sz>VWY{#y)<du{8JTuc%!}c
z-2_Abf%U}yHR_s&D;1ZVx(+g(u>NRw>=p~@e0V9L)yTe}zSt@28imIz`9pW4u(JW@
zxM{bT>Aww6#0C3W(b)Qv5Y#^#`pmw9&DX`V0$c}gvTlwa;i0_@t(gSkuXj_&>3%A}
z1+NEDPL;_c2WnTt!k47uT1*-@{<L-+UTqI9q&R|2MW>30;;aMhA2)76L1@$EB?gkQ
zyKO1w{3Fp`w}7J=>TGvqU!Sf1yzt?N|6&oK1=Sw%*f&+ui1Bhi19#tDQl-BZ?O;FH
z=rXjS7UIj>a#!3wz;z7Gx<39mmX-w!I@s+144S<aAPLS=;!x|)D9UAkx`nzSSLe&y
zN*5mtd$BfN+(mmGT16M9&FqNx0dXuvw=AQa1zpNe=@oF8TP@r{_Vt14(uL;T{)^+R
z>)*5o=?3|Dc^g#oK-O-gkN%fv$NGtPu_;Coh8f8x2}VXX5t@v>_p?4wr`5e=MAU10
z1D4vnEaulL-VX>_c2Gf(Sb97Zxu&k`g<3#R6_V>*v)5(Qldd<e_0B}|%(tUX&xmpQ
zcOAzQB_{iaKW<t>K@%VYgAA#}T?*s(#3tL9_otymmcR2@59{i<?)Bwp(2%IEvDdVj
z@!kL_KvZE;zl0=pxQl`<`}aof^V_j-W&nc<@YCv#xkQqbtImV2IF2_0@a^(jmf*B*
z?xX2oT+W2Tj1ajp1m*uENsY}(?9KbCPs@VLe%>?Cg4#jL*eZ>8r@iYtR~!LLTZYO<
zaDp)>VL$n4?c|t^lWK9y;=BHw;?0q0mbkIBxw1vteftL051m%55co?r&)<Zm){jBp
z`EQ$X*8UCylf|?~^ckx*`yjNi1YXZN#q@QBcKMnpIPROb11-?aG2ii{-JuP+ZCE%^
zduma-GYKT>`nlENGbgalE={x@_1HUAf{XXE>spck+$2EB4chq@L+mo|r7xO{123||
zsi))mmZXTnHp%s^lkHtOrWdG1D$~~?Ye`a?zd236<zXvA#9Ge5A-glhmHOk_H?!-_
zt~I4%kpP`S8=vgJm3duC@)U=pGbn8ug+AHf3@<8F`kCekK!1WSh#LuVHiFUn=;$A*
z-YO4`;c0RQeX<p4sfn@K;9IdgecaFf$7vluUkb#ne%LA!_)<KOrQ?3&E(n#+G0lz3
zd2kJ*hGG(W7&%Scc9nW_mf1wQiEA)frRIEOdshbDC|`W&m3uEZA-sW;T@R;xiT@b`
zb^uwo8tRu#w`*(=Rf~T)Xiby|&P{(2ZC*GSV6ksKGo4xZBEDrW)OX(FZpu}4Gw$BK
zAcs`DeKTg`X|3pXc}K9kq05N%(JFPXC+Orqc$F%vQ<Nc@#oo72O_GVj5+4aAFN921
z#st*)zVH2d-p_YtPlw;W8p>Kg+Oa30ZH~8hL0-ldJ!2-sPID&o=$<vcnT7`}-1F0U
zz=k}A{K@sFQHLeF9vba}N==05a{71K<{6k#Znx&ym+VLxVQX6zT%)Uk7}Dyd=>-m+
z$<iZ$KmZppg~B;F3S-nf_EfSh+5OGfE1=c8XTdM*D`jgd9q~+$_WLCSp1O3Flu0G>
ztjJ`QCyuRwO*f3LYsP=(vU@4r(j{ClLzP++b4?4l%>{j~rqpTV`&4Cv&)K0a4NviW
zl!iadC=a>Eq6Gds@jM1Mz;RxW$Uoxh%SWK15XyI0_(Ty8S<E-19;?IK+;FK(?dfKU
z+}hsD7rB)%1xK>c?N3PzTQ`@bCEHQlyCBv)LlBK)j^41%ITq{LX~Jh*q<M6>l`#b}
zchNl|q}^M(V`mH7yjXWZdU=vl9XK&37g%_tWgz*h@SUI|nQSsGlNtqvvkv~hKbKei
z=7ers@vs3Wb8SVr$$8qm4`-Ixmw0KS1U}pNu9r8GhKOrRu2z+bB2ZB_rA7nqQ&%T%
zg^iSsLq(shs}Pdwj%Jg75+jq1?g%5XZ)G|jS^nia#sIPAb4)GZ9GpxrYF=!?`n|5f
z>IB}5XCiiQO5fcO8je&s;ikD+Dg=S&;Hs)rpT@dlgc6;r8a88WOVYOCM+2}o2bS)5
zJkg}YH6$$#qQDY-;>(Hc2Z{tD>Ec$94qx*ZLtOm31!mvmBg|Zy1UYI#aoIPKMb^KP
z`#c4qnovqbRk}}Wh$umo6KCz7V~&n#*5SXizui{9<kd^kp{>;0;$ByZ`XOj5w{=ni
zH|8Xbsj%}tq^&yo%gxKXfFWeR`uFp<CvGGS2QEJU>$KaK9U6+JlvQQ={0upJ8yhM2
zrbP5Kf17Sjr|R}z7T$A<`xl&+Z9PJ_JH=w74>`#}U{}uMS`<ZB;2GcmCX}TmdOfII
zNI?Z1InOCW^gMUnYsK0Bxw7$BNk+&!zpN0Sm;CYSo_Vs(^@u-F#*;~!V>Hn{B6pIL
z!V5U&tjgq2@fab%VE3-<ofIzllZ^ghvgpgd*@o}DLUr+5TSE+Yd-WP9`?s@n6vR$-
zTLIEDlTz9RQilR&6Comw(cy10NOG*%_*b^2fpTCwPg^PHWVbm4-gD@(*PROyny<wg
zY`^3iqxx(+b*vWa_OgCRi6NcZ(hg7&JK22`u*3jdQ_{lqsXDN67O$+>uv((A7O&W9
zmdbeZX8#|NpCih*z83C+l<;K*Qu)cBuK@<jRs*-K51duxcO8euZPipC-V_=c^avZ5
z-tD^&8cL_UuPX5Qv(MlVId<36=+;)ZwSvgXKd>w@RYClHS>3kTRyqU~;C2Ad!hk^N
z0}yKII5gJgo$t8e3<yfFd1VFo{NykEI|5rDA}jv1lpGrGewGhT)iXkwxETsF$=J*$
z8$lF5n4Fk0I(1(JUHRKVqOJId88|k_0ufC6N$j|sLQQ0A$wEn@#<VEjtH%9@veI3c
z00l*|=uh>b_;8ceR5hDc7c^#lbo9;QGJ-otAV|?HiDZBi!{>)#)Jm?bOgG9o5Z6C9
z37x%d6A^I>sPD7%Fa??ED<YVbiG}*8`R|++eKIA7{>~Nwy0e;1Q!|ffO2g#nC~&J$
zxm?Q^0RN!A`Fc!k?P0+7B9U82IYEl<YEVNaC!XAJf0!&Q7C<I(#J@w-*Pj6lGS{yN
zkzV3*@GQvIXvdC3l?73}XSe%PC5=bGbTHRsKQdAGU!4&qKi|lF(UGVG-|uq*_W=b0
zRP=o3eh(&C4gYLj;3>7R6*bTtS<&lSa_G-@n2-%*4@xMzN?ZJUfUNdKg?QgsbMXO7
z>-8txfD-|NCUXrbcS+oF_cRF$@k24fuP_KBLGvnEZTKc@o+SMyU=<yomvd;@XnP@~
zeEW!DxCL;_>8!Hc1XCmHsGFDyqs%sGqOz>!;;m4CEE^10*309dc#>q}j;ax&<8zHO
zPvdQpjqe7G|KLa}*za&r3N-z&vCyw+oP+e&N7x*NudYc)?a}NDiD&1ur98=YKa^xa
zvR<etk&?=BMg3{}5=KpVAIGHWseH$`W8okGiW$em8}sG>nOqRfWZ4}&TZVt+CQn>-
zxl(=krg_Ktdg2<eSJBMI@TC=OZ>~y?s0q;~a~eUtvb%mUKjx!+3+h`Y>?_ovu|95?
z1?iCKnEMloayVcMwZIKwBVND%kd2N=Sx7Tebt>GI<hu*DD4UYVaaBDG`3WQjIV{*N
zYka*^fjBIyG5?^n#i%1?V5JWnC5LKoI7gN9v|}ONV5@*d5#BMopujafL(Gp%dX$iw
ztywwu1^lB5h$Btw-NPw2*=98es-9m9tKPnUU-vd5iJE3s?iv!mwNf_*G7K<4ou)z^
zGB}6gp5F*6KeMWeLu2Eu92NKXO)UF0K51$@tu5RZ@p}%2!i^gq`Yd_LbqZ8Wg%_XG
z#Na7bf&1w?yxLRUTWrM>L}&lmQ$B)#>zH&(D9cCqcE#TLt^2dr*RL?G?iDpy;LX@0
z*gLZSw}#C~FmXTVN5_1_iIb!S@BT@I)TLmrT_Ir01@FBm9X_4zHer_T`Ms(l{)xgs
zuZ72DoxJ4wd`o8Z1^x;ynS;oHIxUo1vliy!l3GOwv3q+q82AMOdb53wN}&&tkKdoY
zMF4tFjp)xQiH7m@EDT8o))hx;!URxPgnqi>9Og0LSX>OV)c5dX_oSP69WbF5Q;v-5
za-W(++!k3Q+Q0z5G=I)2xI&!0>N$THLen8`Rmk(56#G<DcVPg?g3v7noVQY_k~v~R
zB<osXDo(Rk?Gb<lV<vzg9tgG-1~iA^yR+(nV46xMqp8tfzLek!Np_7Fu;6`ckC0~`
zK%4}Ku;6hRF;68!)Rg$wH3iU4uxqdiJ_m@{1|g3;sh5+ap~AqncIO?$cRPYtYnjnQ
zmzY*>+UifIO8DE~!0U9)>grVAi3PqJill@`n5f6rtFfT%`P5zr0=16eZ-r1<_;5<g
z_$>{}kl7T>9i^6AIDUl`js9+ojeYaAq%94kw+e}CKhm}OEp>nsKT#Xu|3g@v1FDIp
zJdZF{Pbe1#*{#`<zjIu`rpSLc=lI;pQ#x2a_c5SvOL6L20|fb96KXHUIiTvbu{^O~
zGltUk%%3nVQ5+BtrPhve_H8mlkkUJqbX!y6=m}(NZpdx&ihuW3Sh*EoG|DkmbT6Vz
z^v#M9SoQ^vr{%_+VlVwZCm=J#?NtTt7v?@1zeieFZKWbaPO^OqO}~~c*SAm1>3dLQ
z-zot9oT-wQVM-ixtj73dN<R~Marte#%Va_k7o&#Tm;eL~#ZxdGX6k8pa7JZC^0P4W
zUfZjuWceR@$SU0V?(irOa3q<VTC@%0#1`{KkisduyJ``(r^W3rX1sgYXvntO_D%|d
zf+lgSDweeHfO#(R@YS~c%%^rh?2SF|5JDgM13N$Da*TVEWY@^P*ic2J9xt0b?`8H+
zMW+O0{%Dt01A$v6%P0)xl>cmG0aFz(Gb7vMtKpw&_*CC-%6e7rf}r@F`<v4uH`N2q
zur;#OTw=aG6n>^><E>5=)6V@6it^^L$Q-h*Z8vF<c;n*j!6)iHYp+7#`~0S3DEL0e
z;vw}idu5WZ#d=bp`jmj?+)yb5Y2{OV46mx^fut(arLrH6bjtY|Gfyv9;u)ZzyChm-
zy3aLdK5~0Blja2~A@@umxg3I04LsDxPA2{Qy&JvA^fh=~h_CoB(N6?|<Z>U49eXOP
zat&+dCzg1i;z+`B1>BeFrlqK;_p22K*ia%{#eQ&oslp00Z4<tp-XnO5P`k}owqMdy
z+p=#yfCGYl<vkiZeF&xOi`5~rOzr8%#s=IDH~>L0ILR@&%^bH}MC2Cd_&H3?X7`rr
z0&J3&hjPw@`YS-P_*E+`X_wM*7wx*O(G3*{8qY3E>{v{yYrv>24G%y6+^^Is#R)-%
zFqFEOYY`&Q;$)f;TP^Q+EDNASGz~?iKSISFBr}L|AMP8-)zkn%nqHQ`?GgVq20@kc
zj5Dvp6N#KqPynu6`D*NH6WGhm7`l3VV{Ky#Xv<SckoAbGT0u~y?|lxPwMwx<Kv1Qr
z0}40QpejN(3N&Y`v46$4HOjLOf+leJ%BC~FlGx_^zSdlW=da}}7A<*a#b(Z99XJ>d
z!z6H@!zlM!Un@GZ1gkkiMW?|UQS;D52lYPlrs@GO=dizk$>aJidB}?Cy)CIk7_D9#
zO1X)g(P4$OUQzBEzLB>5jZB_>TEnTUKH~r`zNXl<9@el)Knia?tZ@c>SV6z@3`gCI
zJ3exei>;W{8Yr&S;OS4?lm}HtXz&przp~op2ea&c&Z1bi@+g{7F={gcK|DWw`XYIt
zpgW|miBb=;Em_dNau}V-yT1&AaY4cbe+kB-*XrxHyZnXME>F2?T0;=UblHuCp=2>~
za69_9+M+0oSxPaVNkd0%6>rBv?Puv+lG0D$Yp&0kln=s7#OYL(*z$XC0o~(f*3##r
zED*?9_Ob5=Z33_^rhp~Mnu}E2S5N8zMGH5Wa}#2|Ce-9_o*;na0PNckbe&#&%lA+5
z&9(l<%EV;ee~O2VlRz=?Feuss9yoxfM9S-H%F_jSfZi9fM#9CgQ~wq(kh1!S?R@_h
z4M=Hy#Nt)J<V_bgg^RCx{w-R-#VzwaZsUev(J3mT7|z^x5NA?$hu4i8w>(ZPe^BPa
z2!fQ3pq+&((Z0QL%)pSW9Yb75ulq>9ZvwE}0rZB2m{~OVS0*zeIV$0Xt>hfz+3`UT
zC+SsRSJxOQ-V6m?W)RezR`yDDePab9r~-q}-u4h(URs>R2(D4uN8nCJn~1qNb4CKz
zc)TQdxMYChbUcoDEw6*5*^BTR1YT>-&CHCUSlz~PMs)3?*DMH|{(%pW92Oq?08cvv
zay2o2(L{12!Nz#!l|{0GhUS??N`T_1aeqDV{<tn^ca1OUX&>Nej98<=kJHwdNiX|e
zgCZR7PWch!WZ;kvnfgPZ*nw*$2QVowwwKm{r%Q-CpX0A3D7LBB?-V8f8Zs%9B|xqp
zp#B%`_7_$pN6%%Dx`+`1xw&r5XkoPr(*?~yi}mqku^oHeE}3@Go7-c`f>J<ogzck0
z^t&*U8WQ!e+Q~oZ&gw&Y$T=J!W3v?KMkroQYC$t8AIoc{t1&R~Lh&Oxba6XX1xSAr
zK{EFU3O^wI2NC>=;%Nw&w{$#S0@`~p5_LV)9QKp3=_+-aCg9rx#Dr@d^Tr6CHOX1w
zB$WVay)+!7N<1Qz4Ss*3od#2I5#>q5al#R#N7%NBIy>OIdsmjG4NSjc@u%8^2o|Cz
z`Gw<J7{NcL;O&sa4JOpRI8~K!M5s4OXzMoZJb-vkiQ+g)IARIjG_R|3K@c`WCChe?
z+a9x|VNP5Qup-K&-kk}_F^mKB+%ywVBc77@NQ`jA+~cWcZZepP2*&*#ElkQl)hr9i
z80dJ5dr<~>YhA!wajuUf1R+d4j1{@a`wLaRiI@_1L(sAOLJBiR@SCa5iU>&-)L6xp
ztf{~{WH(|dXs|kJ;A+>z;S1UuIh6b00{91G4Y+a`r?;U^I|i&UBf0uNg_XdJBnQAe
zjt4K(pc6k+4sTyk-wQ!)w>_*<PQZ4)02f%n1q<+5;uzf27lFCSOkl>vs}vJ~UHGye
zI}SI=jhK>UQvRO*XpWN<4IC~HzFH|EIp%O6Lmyr1Yw$(wGFBTy;oVVkC9CWMC+Ppw
ze<8s7Gp!9GAopL0*Eq*@2+6^Rv)w4CfWQp8MXIa>0Tcot3IS&ulzPL%g$gpXr<c_M
znhVfpx!05WeuG%eEu4cVS*Xqs@T)5095)ic5C{t707S)tQ6_+21(Y~R{hMzPAjvsQ
zdJPSQQsx7+vD)zzaHb9nU1Ja5YS3T<5Bexv$pT->fFeLj4b@2F7S<&|RKp`FJVT`h
z@S9=*4?a}Gi(}p31_SjZ7>c}F9>Fk0Z5XVI!NhC@%pV|k1N}xQoVY>+3?_&%7kp3v
z0})<wteHS;0y6&yANoWT)CHOiD9ktA0Sz7yrNU;1f>8@AEdwKSr_wQu;2U_Ius)3u
z>};#14<#pVauEnS2pZuc1A=MrL-YXI#rF_>#<5O8g!)QMxPqw!Vgb~2AJY-BpusLd
zh)@9uR(OV?Up@m@1MC+r#;_j&>BeyOL0GjRwicun0nGp~0`T*zGy{?YWZwW5?868?
z(gCFQHG)jaec^DsZvuQC7_kJ<+)2PdqelqChA@!+c`Uqv2ZG{2?%Us2V4y=tj?y$3
zND=^@gB|JwfP%s55Yz*J_QDpGaFJcOp97$~qJ&{#*ctjd*jjZu&`U&ULN}W|EXD}h
z8+eM|-c&H@B{WUYeK-y9V9M(to4szIW$A*Tg)luO1UNB<v!ei!3L~U-5VR=f5E)kU
z4Jc0gK%cKbhMU@Hx+2g?z73Of#A1M`dxst)&j5l3-J%QFS_8W!dXRx6$uo$L^j^u_
zPnNDG)1k21*jn;?`nszH)<9!;3X=vN=hoZlYY<w^;??xoH}e2lI*S8v7coG9VKH>V
zy@9T`he=sKn@)BOT@oYM9IbQ%{D+VhCr0pYdojJDJAz=dPaQ?SEP@fN>-s{!ym*9Q
z<5WqXRJ9Z_g3O&eA>%GeurWEL43C6VK*X$#+i{rsUN>IDs}b<pGOmxUy+PS=5bzlD
zwK#Z+hrlW-4QCI4027?_v!C?A1D+5<k+7$3fG#;g{}G7@Wr$&hSNfo%7{Nw3f^L8m
z*AHNb!^a6}*B@eGB`1#&(qiBa^4RMJeuG#5^zRfp0+_tTVQG-4Ck@U75cCm<z^~EP
z4>5wclQ7`FB5!~Q{N4;F`T<N0K;%BqNk;)LJPTfxq3b{daJoZ5Pk~4Vcuj;Afi%eg
zB^D8S?hdR7m=(njMC^gcvF||SCPwh`DOVr@LdxwNjB<=%!*&_`I1Jn;_=g|-fYm{%
zK>!*G+6CJS?SmCVClUYM_|GN(1;c;C;J=ySzd7;0)!_eof!x?;xWQ{L?KE?)7OcjQ
N?ghj1h3Bj>{{xzZyM_P&

diff --git a/tests/data/pseudo_mapillary_dataset/v2.0/__CRyFzoDOXn6unQ6a3DnQ.png b/tests/data/pseudo_mapillary_dataset/v2.0/__CRyFzoDOXn6unQ6a3DnQ.png
index a8b4b62357dfae32357067b4c55b85222425a70e..809256d931297ddff2bfd945fcf3ea0336e3f815 100644
GIT binary patch
delta 233
zcmdmThUFEzVrPJ#J1>_M7Xt$WucwDg5Rgs*VGd>>>28ynwo#Fnxt@Vxsi%u$NX4AD
z*Di7%P~dS5{9drO?0;xf)PyJ#u}@c&zVl7^EbQd8=N6Z1{qNWn%1o-xU2P7PN}|a;
zi-MX`e@tzWXye+*vHz2@%OahY8K+gF)~imqvFp%cf$bj|KT7AiB$x=c7HYCBGR$#F
z>2W-_s=wvJjBbryDJ9c1r6}8El}|}W+?<k@|FpbhEPxZZv%96-76`nU7X@@YgQu&X
J%Q~loCIEqUPL2Qo

literal 75316
zcmeFZc|6qH8#sQ(3}XqEM1{tdP)w^VBa_N9mde&f(`})Z7^)Ell~%?sWvONeg;r9S
zZntPdZ<RJnm(n|hn6l^lyhrZ6pWo~I`~UaHZ(d&ab>HVa+j-78&-0w;Jg4KUT<jF(
zr^_RR6dmlBuR%zekC4J;Su(WDZw_W7L`JKe+*b&VjF1Qo=Fc3=r~UQUUlnK0+z{Sa
ze;{QrUwbfLhsWa$=Id_XevW4|dg@elet!O7zTRMd_F%p~o6Y`|a*Aie+bj8rbwBg|
z;-zfex^m^p6!;xj|9*-U{EZ?sinflT>QTvWFkf>pUt=(T`e6RF!F=_>{HcTas)PAc
zpmQ)^WiWs8VE%-`e1&n~iG%sd@Hh53_FtQPn@`#ES4Q2a7#&R;O4}8yi}JNbM|p!t
zYwM{S?|HnY*|WFiYt5cLTU%RuD=&M>l+jp(R&GrhEYKRftTlK=Yp_sjut;mLSPRSF
zdPeetVIs5&v$7h@*ZP0_iN=5L-y`@#=r3r1|2cJP%6<h}3JlI_D?-3wJwl(*s;xX5
z8-(@(LrJ3uG)AM*{2kE&dHL07wZA`5`2T<ZAJV`})HM~65OP?~bU$$J>j-PFp2Mx2
zZ=DAxzFx487Lc<F7d1Px)$+5RO&>9=Oj!ALg(<5|MfG5&%L63?XO9P`Dqd~Sn)ZED
zGw=Ke8Bz3der?F}G;j+|ExtACIP6LOTDLP@3c2bX4gZkR+~X(jui|M?z4^dg10xi$
z>5osT-}?8&<$PUCVk))nvUDf$EGO$$ZolUrv3OCRoNQp};h)i}s9%r%-T2jzmYv(a
zERk}QhDmmnpEU2~UG?jc$0N8UUBMjbX;Q<q>JReV(_U!pUq@HZQ13S|8w#)Tnyka4
z#hm<Xwwc7{n&$3l&>p>a=4M6LB+m!3mtFYx7l|{jA$oxqx#Y>(h_?PU%|q%Pfs|LX
zsz2y(mDi&*7j9Z5C*Y#%xotZVL}e87jm!UdB_-O5wGJP#9Xj+$@8m^_r+)PZqxr2<
z(WivWcGqv4J_S+N&74)N!&LH$KU<3E$zuD6-CagmRu87`km{J!7BKD6c?Gn<p;l}c
z^6firyF1CCcq&sVH9qqWqQ{BdEBza^vaJ7Hc~EK>0Bhp+6wq~t+MgSSe)fys7zWOU
zVOn58YG_un*7wS9?^^3)W>ueuK`J;X`=GS-+`2Ak%N71^tMx`}nY$%zReF*(V*+li
z-Kcq`f1GPp?a~t(H7acZh6JCE&(@#%K&I9KJO2HHpl5x?0TNrgylS|DVI5|{)sTl7
zNfCdR<{jZ=_7DPnkd+9u9=oW9JhA<c3EsZC5<Vv#YJrbKgEqlu=4o1t6cC)n2qm!%
z88H%q^T!CLi^bABA?Mt8g5bR|f;+K#HI#zwdq@zZjuCv~5Vr{kR!x!+JT*qpfDuk&
z>ucIc2-5d_p-k1S{=mh^>S!vq?@tMKeU1xz9`K&ch$OK!HL3pt8ilE-qm<`CA_COl
zH)!E(Mihyy%4i=dTx1<aKRrhE1hzmOc|H%S=vogl)n6K;YREWDVozdJ{SRmYW(xv5
z54!tb&_YAT5fWRGkxPIcGCBP>#S>&r|I<wZS_Yu^+p*a$>_s4}k=0QGG=>1>8lA={
zuK@JIg)IbVa4CQ$=3<we*vu%6LL>7S5Ww4)0Np?9bQvW@ulhrNU=She{#yXL#TT2+
zVmlL57XwwzFbP$T&gl!1wR>S1Q1!%uZ*^^GT|mWVIk3Hfs^J2V)et}{7FqAp+7m_b
zggucynUJ-9e<^^HtDfiBv3CGfLpo@{JS-PLD~2}T$eXnG94&_R#Tr_fW37GbZXBPq
zHiH&p{Dl!sVmo_R5wKm%8xE6f`1e(RWZXl=`Gu_`A0CFA#e{0vUY{EIQ7*7FJ5v|f
zy$Y^a`nsXsH@oV*Hd9G0Df0;`K33Q}(s?V>nq;oz41k$pwhYgMquISb<cGL-^kUWd
zxlE;o#LTCt_*5qO*OQ#g@cxLlB{yIQf!M`q=+*O}KO^4O*T?;`)mz2ZhcOs1&Vptb
z2E)%%GQ+!PE{l{hhRtV=;}g)6&lVs2Z;8c;1YN3xZY?T4QAqyPnvfYDV6GGfn<7(u
zScbPktl2#?6(BqIeYWM_mlpaiM3>KZ9U3jZm^;&IszLE|iToHUK3vl~az8dRtaEL;
zhznL_Rfr>5q+?Or*Qd%Dd~thzq%@4`!sl}`yhUQIt}bJ4_xT`iDc0n+fED-56;Z)w
zM$_ot&$sQAw#!|1;NRE(IBOA_Bk16a-Z`I}xmaDl*a!?tQu+&2oEBR@QX8ek#kMAj
zt^ubte(q#Z6xX?LsRH+tVWNXn2M~2WvrZAQzAShj(bXPraB8aD949c1D~<xug8KoZ
z<yllMlefCX3qgF<v{$J3+NbLyec??b_bx1wItj*Obz?4o7Jb`2dNZ>xJZJYQ(HCIl
z-nCB=Ep+Z_?l{=oemq4M4A-^6nq8<R)iZIVA*AWY>TB9kpu56C@(k2}@%h%#n;H8L
z#qK_emO^WOEYW)D(bm!1=lVjA1{^_4K_{2Pb!VW`=YJHBZmbDq*pxDP&A`dCC|(gA
zdc`gtef`X`G0cL=TMDgSx#yvE_0oojub;g4GBjx-OPIZv+x*CAzenv4GlmjjjlI2d
z7K11HzA*wcfe)g+z`Iy!%M5fN`@rSC&)+$rD2r(N83aw2LN1pm_izrPP0)1hRWvkR
z4#_X+{La~r_7hDH6QSt>G%5CQg3*4E_*Tw!NmEYAgdR>1QU<8fqxYfdi;gbCTSH_E
ztFNeWSO#V0oooO0i)W>&A=&~Pu;>k<LYqeWl_;x>8KMPI8r$pq4wI4V%V&WMC0Gjd
zBP(q+(1D!2NhNYUoL$INHZW~@;yfi}<+ix0Ih}IQViC`aV*d2P0}X;u`rpo6E6wSm
zT~QjJp0kt4sCLS;?y1bo&IxQXQ%NN+>mw2^Sfnz1#k#sanY3G{db82XdV>D;@Q!_J
zlW8%x-D`tT%kcz!#8a~k{|ns$5zf9n4*XWnztemo+R9s9v^`2A$ISvG@v0nW^=;S_
zmpdf&n#sR^*eKTmb+3B#KHM1e;)6m#)YTu>QjwO?w0HhTn3=H(?3qlZAfp*yXRI)h
zN1Ig_3^~W$2Y>67zx#%NLYWC#?s4jC$u*j5s&w&LTFeer#XiMAFB#sY6OmV{HgAS8
zc`R(&^w@hEx?uG1#|966?j5NmU|XK<lo?jY>yWZp|DZU$0QBU6Vu1Pj2ZtlHgT2wQ
zg0z=h4KQt+166H*<<)H?(TdosDm_4XhP;cQyw2gI2%{hmq;B)zT)44p4`(%skqb=Q
zbnoH!Rc#j#{qPCHu!^dB2I(BFdNWDYvMMb8q?Bl)(RT4WoaWk22{=lN`Iz*TRvBD2
z0Zq8{hf!q)ECVOhE*rSk_4)Lk+LO+L&iRO*opAng)#g1>8lEqFRSe7I(S*D|bSg9C
zdpHg#S1xevnp9`OCmlr3IT1M=GOM~?n{*DMsMU<c@h5g6QMP=}_jkv&Tzx64K->A;
z-8#|@h{sf&&|1>U%q*16K1_=VzS+FoWfKWK3=W@CsR`3yi&jv~=Ug7q3H&LK=!Nys
z{h)H#w{xxx=md63A$oEBmi}*R`MG4NOS;vY_gqnncPmmxx|WP1KbFjK<=_8%y{V3`
z&rGy3Bt)iC6LiZ!LO?J2t`j)?k;L}%H7M4iQq1c@l+6dfAbMFM`9K6ex1MxqR(0gX
z=kLW2NbCdcIYk6ax9yWfZFRfIqW&7i=5kn+GT9Ii4!_u|Xx{x81xUBA90S{MebLrY
z1+qy0-1NIc#9mRfnGvPYFMKoo+UOBd%VZZtABK`_U`vtbhU%sUX<osS1^f3?4wk9&
zwgZz51^QdNI;2D%;xl(}HhMd$P2_(ig<oEzfV`e>>&yuy`PuWy5ewHZ3#picHm;1z
zJ6j{2tq+1c_mg`wa18}a)6CghHkFqH#OyBWZ*6}fB??|RvkYI0-cD{4ZQA3>Z+xPN
zHm>M6b9S$E_B_CRxn25AWg`-;Sg3UycSq}0#=u720od|)`_7t3XPYyX?(Vu4^|f&i
zYO#2$xSpY8Jh4r5XV#4BijQPeD0s#nF>I8xp~67frxYou@IvEkCts<$Xd2b}l8?>L
z3L~_UbzM8Hkdm#yR64Y(l&2B84wa^?>^0StvzZBKm$r^B`IV0X=Iwd7scaI@1;k(d
z;McxS+ej_z(<fANbWk}c?PAnO>w8d-@P>LAz6_OtdQR65RXqYdvUbq>u}CD=t&W^w
z&=6N|Isv7wS^5(TLmWM5YJU|M1)I^>a3&YGLR?VAl?5Gk_h6!g?zMMMv+nMVF$V^(
zj{msWmP~4KJYmpuOEtXNi`+_pwszP(XOTrmUew%iRv13-FLe}Xy2cjH^e|OKYHKVy
z7w_&es8CgpgYlY|hP^0Xf;QTHEDkNdlLfKgoG6V0JL-S#8-9RV%H(|;pFAu763p8y
z8_2F)z$~mLr8zWS3cXp<P%)iOVJdO<?{+2eNXd$2?X1ur9i%N2+iXPVou$!3w?&^a
z3%|y6UUqXqzOsR|zw36A(EYq=LA6tVUflo6cs8$<Vm>jDQ;vA?FPv^ybqpTg(9tkO
z1R<Ec`PI!xG<)a6_tD-XZRNq=<XaF^sqNgx1&CI({c&UCi`wRm?KjZR$!#{+fCm{}
zaLjo>;#~gs&%s;L#fdcPHKP<obj)yCV4vBKgrSZZY9i|>4O!ziixEw*^>JhKi(Pw*
z{k_p05UX%|GvXai(B2>6W?FW?;vng(c6B6a${r0==l$r^oyt6~#y^@XPzbCbl)qRB
zeZC?g@TBvqKO4Q13uIHa8B>wiWB$iZ|1ZI2Z%XLAXB2aKR9P|^l^IP70tx=S^YyH{
z$TLbqec6W^64LZ|dYgKd`@uV8?gaJ%rqYD-0quyFDKFC)?Ofhta%YxIaWakiaMf)N
zvRNt}-TCW+Pw3e&UGnRdeDan{jTR{TY;PjbdgyGJG5Pg!J~?`}k0r`Z?7jGZZM{yk
zhGm5<AirJ)u$LsT^%B_dtT0RRYa5_DyBX*v{$E>D6B9e{UGRy>@*ab=y|f8nQxl`1
zwW($0oue|{=``xmIyR1YJ~hv7Q%`bF&iJ-|x`;)L_@t1GEX>V5Y0ddEckhi|JCG@%
zv$-Ll$@Zsdp~aWXZr2v(k?!hLM_Rk=F#@xu;zkhuyz<UNneKBmD)+$EqJ`_tQTD|K
z+wMrav)qCi-`33#xkYLCb=8=3_b8y2owt<k)oShe@~!iRuRn5?4a~l3cSm&8l*HTh
z##(0SfzrH^yY;d6NLFAdb22YWovn~Xg<GpMhC4pwH2w6noJH+EMx(ChR><!jGD2x@
z?>jR>HfO6bm2QZ4s=gMlK=kV|XSv-NvG@J_?i&?<D?se^ab7=Kgpnp-kn2*sZQ{tq
zWp)MJuYcMY08s9L76}EFR_4c;C~#ntZ%;3pgy^S33%G3;Z0rCaXJ9%BsSK3mQ%&SJ
z`qh!1>HYwaT3f*F>L8WN1!gC|+CV{0?e&FCeLHRT1BT$c5(&ALy?GhxqaX{rY{qFX
zS(NrN#=E>ZnI{XfK0j~-p&G|rhzlcUVa773+tFeL?3;!0KJyUI3p0e+F#Cx3C<)z7
za)EOKSy7-i0kz!ZoIpUHR?bGKNa#iZ(&gfC07^0WFVJxSx|G^vig=2cK0(QcTZzzO
z`&5D*7ax&AuW8<p8=!s>_9-BCG>1T#o$3P!bH@-ia?26AHHHv~{{RFX3BqGx10bCI
ze?eHh#9i4)%MmoPR)YW9TPe3<TB#kM{9w&4X;fTQv3vHxNi8Z&r70a{EQF|gT#r6(
zkg^8TaP_AG1qC$S+UVDvAld}dyz<+HkmH{GBS%dYVFVk$T|;Q$Rl}(k8>LcUX{=ww
zl0tQ_j=F!|uMYtlb*JjHy(n9#D4bZTcNsR{&HNZMw94OhHpNu&38?9cXZ;Lxskcle
zq2cH@pyzq#yCRx$FhlN5!F?l&`Kp4C5QRG4y?nU)<7QRR-pddk8MT-1JlwA+BKq?O
zC{*OaO_n9Umzo1xQ)qE20JS8k9ifZnjsa9n0DuFNWNqJ5BmjdG_Mw(bYGL&1J)-FZ
zg@!3q6nij}dhtE=G7~5ao(2G3?ml`=#uz{cjf#G9U&)Xg<q3df3*|t>&hp(sfALH-
z87Slp=>foj6qzlJikD$cBoDd*Knwu9Y81&60HXkKD>Pl^Vx#g?S3Y@#6a>ky+jmSq
z6|&T|Q{2*b&kvwzbP<U+l9_Waz)ak>IPQV+DbQED-gYw-@U(uRdRMGgbL)2$6%S79
zT=iEO6nh|3hTMd;4q2))>GDjab5o`@ArYyzp8Z!S_fSwSOI8M!RiYF`|4Z5qPM>hl
zEw1abUJQ-JCmRH7y+xwU09t*PduW5l3JQ3PB?ax(Ks7WTsJ?pM6@3!S^|}l=Zv|kz
z^VK_VDMjdRJW8Y1e4$?=@uX^>urCi;44)2wlj@R!@26zY2`kg+)qB5w?z;yE#g-e}
z>!+bh;=2?6HVf&W@d1u`0qY0cWzh5kt7Y(amIBrSCLAA@%w?P)@#gv@F$aGt;h0n1
zDPX{={R0-i+BSYgxoz1(m4&ePd$H^4=yl7AX#)Q)zR5GnGf=`^@f;cC6Y3#@4_W5e
zNyyFSXFfn8R?%ZxSVWcBZ<ZfuP?|tJfO||6baka^Nl>$GxKqi<wA?6KJfc~D@l5tK
zSo!wAwIw+fxZc}hp{H^KxXR<3C!o9C*Ct?Q2b^NIMuosEX){idcxpZ=%t0CDFLe@u
zjRd~)Q1_ot=G!;7Fg4TV(kHdq92e8!^c1>I2A^Sd$#zV*c&&#>6lD5@78Xqn9usa6
zRu95`*#_h4&Q=-|ZY6g*oT$p>3E^Jqre~{ya1L=>P|F#w&HReW`&@UGg<$E8@O=}I
z)pw%_Sl|A&aXX_{f^hnbSQ5{`=LmD~mr}=S=Q^;+j|J@@-0K3meRK0>M!wv15bliF
zN(O0#suG&Zw_C_GhK-e&S&c-tMSp_k?0y`Z<+p-QK7#2^LkHSC)IoEXw4PJ0!2Vpt
z)gz<0yZ;r=-LZBnYKfEx7tI};uQhny1oXa7BHXID?NJcvt}<dIlXyd8!hLxz(cDg9
z)qE7tAQ5gJBS8+LUz;o9jWVc{D-kZoZa&izj82NyQzT+YgsT$U&+;QI7ZyDYm9|TS
zOVfHp`3AzR=gx;?^q6qi#k6cl&A7ATwxgC<iEy^uDJlygj0?oyOhAWzTu{JD_B*AH
zO{)pyT6jf19LYLd<5b5djBxG()cvy8#J;&vJ8Vq2axq5+RdAc6@jI3RSBY?bG)5+%
zW`-~aKPllaB;%THALol&3Ua;q6}NRQ^d*aFDn_1;`oFAG6Lft$<})_cN5njW+$(83
z)bfItWR>{oFwT>BrkTOa!KT>HFD2yC?OpwVT-7>$#dX_356Sc|#&m()-<wqh{$JB#
z-%$3z_)m+E5#-#Z@gWO=?_wq#L;Um@0wAZgoH=+a7JutpcbG<<?x4H_$lY<~SL8)o
zq^c|gGvSH35#)R(3%c-2O*rKTxMU};6B%tfG&f4DsrhPYW;R49=?-y#da`H*zvANk
z!73GZl{Ono9I`)$zMIQpeL)*_va(ZvgQN0J;BZ#UzWJ%#`KYL6AjoV6m<>zoHk(0D
zmt*=<Ucgkd@YRaweQ&M|*0*ovwF}uq0O1%1n1!3>@heWcUDK4-2RYoio@CTFax7BJ
zIG12z2+8Ki9PIjZbfD#LhDr6A$lq9OYy4=`eBflrC?@fa3tHv!!Q%<V?`2R9zh;)7
zEqH4oc%Oh^oE?<{bXRd9b&;A<sPE@QbmcBV0p7TK)KBPg;l`4YT5^pZ<jlz51it1d
zU<JN1YOkd09AG6X>3w$Klb;Ew7I1{YEuw0m%ZZyqMh)>wy7u7N7U1`k(8gtD$7x`M
zt_Wf*5xs(=%uE7l9h46swjVwv$_he`_{{G}REnumq5(+-H&;fd3^i@&lOgEfYyChX
z9`=oVACy%tE~TQCiJe;N2{dZHkZO(SNt_;0DeSB{3^9qfS+I*LV^AHr2EPp?bTuvM
z7O?ysYr_y*1Ai6y0d(QQ{Ypk;hg_vo;DokeTV^742a90#A=qIFT7yWm3KNpmK)ciN
z^U7#~zNSThG<3xiUF_doQuuM8ZjfO?w+4@sn%Rd$$FM8p`*4KZf$sn;BX3Lk66i|G
z6cfX`P2K`s=8|E}X|$w6y6#+}Rxc9OVfV<ok}g9aIM>^XPM37`AW;kUNOA}>#3unk
z(?%=$9Oz2O>_(z~>^b=&oX-q#k}}%Jv<PK8ffLbZG?92L`~AujU`lcYxt1tE5$}$i
z1a2rv96&`TI^NcF8qkQ>`i4Z?1ohO1VBHsBiJGW1mNO&@0Oz!lTMRRv5Ia--G`Jx9
z+F;bO1{)x6fdl6>JP&4)RTjaX4a{^IFG#$T4%CUK;M8Csu!H$G$EBho!6O|OFQ=kH
zgA5zG5-{UyeMTZ_;SAZMa2is<dNok#1rFujY+$yGORS-!LYg{k#~S-M$YG^pniN~`
zxYO{>z|7s^Fq<M__JqVMa7>*z0pbc@fgP;Fbz|%1T!I!P$2^2?vOPf1kqgN)uVfeP
zYEY>mz8Xk)SRA3jH0S<Cni@sSO5zyO2HC#>$z=>_ul6y?JV=nrj?i2n>X0CL;A2Qh
znZRj<a13b;H-*?4V@MA8ItizvG-uF-kPy!USC1klIe83ei!275Jjak?we5k^Ith}y
zg#;;AKm{c4F(i%D%)gOHD3l;|KVKSJF%`9(;!I$I<+1LcH@zf6AAy1-4DJpwG)lrX
z|M?#NvDtbroIH3c*gOi{0Q9$pEZaLU{on6zPfi^gQANl=Fh>4Kx#0jDd{8W_YN7yE
zO775>o(HC6bdEnJrfZzc$LpKOXo;?-EgvG=EQ~x2t#us}d#R8*9~Ebgi5BjtycMw-
zV{#2AX@Mi<{uaWJ!6)&4{O0J!rIAsAL+->jU>74^E`z2fDru{O{R+1S7s@uoCq&JI
zWfUWZIB9A^EKU80q-z^uPs1ru`y^dk!J7TJW3_kGv;}ltxx8v2qF;G8$Zrh*OSM!G
zvk1}8bH0i`6ZtEy4;dvo#3*eXW3d~tXW@?{iMUP~zp99y>Ub{+&<0g$Gs;LjLqV@h
zA$a|zf?SD>ycVed8x0cDppm`POJNHhQfWh?dHA`=T`-GgOeOR+#bjC<99JsjAl@zF
zREs76SC9%>3N2-Fz>xSyL7c1aJ&!K;8(RxM7P$__aTY@A5PP!;P9QWS%Tckn#b&k^
zh%&31#Jhr#$O|U5@w6alcI;Dd0-*>xvolQTaGsO}UKcqPqKy=D8UUZh2Bd-j7zi$Q
zY*%;+z})`@KFcW=ZKas=iM{V3=#ZWTdtdAa8&${Kln#;K6P9ZTYMGDykV>4?R$L}#
zLznJYR{={Ix-5Qom5MilEzuk6I>{nTgyR_Z;!-grjtlk1BrK40E&JV7Hiq@zE=O!c
z%1y#cg4JkBhZwJb6(=G1f9ZPio0mi_#dpVeY0~L%V0-c#>pxv4dSe8~u$GPSvLVb{
zLwu)N+6fvJiw47YYD|ax%&&w=?3MncQ%!PELc5b{)Y4AEx^s-%k6NV0hA#5Q<p@*k
zEm7ETGU2jXes@uE!hp}wG^NjAD!q4f<s$Z4{6ORznC0u@%Ty$j9IKWFHnqahH59Rz
z;~|kabQOyKqN1aTd)3lnX;dxy+Czv<|J`*}{2H(lT-4Gaxt8hR8jjfNI45!du#Skk
z0gG><mIm>ekG*RIVpH&d$Z4>jj)?oIs0Vu^6$GnR0hdPT7|Tn+$&pVs6__DJo2xmO
zZVX9Hz7GlUiaFOsH(;$U<5Cg2fIW~>ffcQQ&qc`Ik*e?%!U0o310c<AG^Q^ikebMd
zcaBpidM`nmgwP+@O{qi)k~2cG4khwVU~5eU`$>qVn_)y>D&Zu9c*i(-A}K&}<Z2=$
zg`Jlo(x@yPvJ9V1HI0g;04~W#7V$c<3@H|L?ZT6xYfgq?u?$mbH{VAd@hY%0QoEpQ
zDt-mJ480ADAyctC-bVrP3V(Oa!fz5?zp)aVpeyq?!Id~<3_cr<@!Fj<h9#6z0D_)l
zSl&j(km1;!GKQ5W)eFPgF6lCAG@>&kT@o>_N?nI8PdtN=P}7(WH&?rpo8%C$>9;aG
zCBmCz7}LQzKo^Yb7gjFiCc%;nc}$<XlbWcIFys`Ao>I(<R}-qy`8^3M@jVDt+Z!l6
zg=6XrVX8!*bLgf(FUbe=$xrC6`_T=Fg<B3qQplzT|9UA@KkYbt%XK1T^Y+n~OW}+(
z@T#}uPQk*_Fi5}H|B<jPuXFldz_Pl2d!BXJ$J=VrXCQ@kwni61pqh@d(q3WJrU{=Q
zdfHR=^dMqyHSPHONkitrd1+ZR>f#-Y781|+z-qOu%AbF+?!k$^*rEOnIKBtHWwQ?%
zt_AD5c*jB_Dmb`aEx3q6%;T)n+aWMmRQu&ZXEIw3*bAN!u|fO3jW5b46Ip}}H_|?V
zS7n?yncooU0h!^GQ?EmWkWbyW`iDg^9OrjGXD7gx4PI)J??d&35Mu6^c8E|n_qAU5
zdW1a*NM1N}3ZjS*Gn2<YvQq&-G2a&e_HBA{p<Bp?WXbF7fJ0>DR+@L>&(x@7U=f{u
z53GKx|7!P&sdFGIoiW8}Jz|^q>(Bkwcayz>Ai29q3LQ$W(W#a!I70xR+qhyP5O*dH
z2x%KEPSHU4vw|3KJGVL0m|%Br5yuI3Aigl_7ih+ryONBqvq~m$K%1wr1%Tvj5t~gc
zh$OA&Nc0ukM}gcNyFh$O2F*&1)%^?(V*_z34fHga;4xm$A&xA!g{`t&$x75#L{28&
zc6Dcf6^mfCcP!j4_U77?Q4p(P5(nI~rbNE=WwF_i4*tr|#E|F(7EB2nfwN+$fbfz9
zoaxM^qXXb^LIrl<CNFZdm<FQ*5XIdQw8M8aXDV}3mhDD9IYv-rMtnnmoTKEsUGhDP
zxxsW9d{;^Ok8n(xGiI><`Hto+W?l)?HmQz`##(2fv}I*k*?(P~sMaQ0jYCq)Nn3MG
zz~kGK;hTx$#CM}xfW5;pg}|0eVzCVR#8)zYExhrUw0XcP?g7xDz1q~>bvneiJC{R7
zz4j$jtzOI@>)#9W>fohz2-6+=-bpz6KDFT&3&y^;laY#JiMj&oa4C(d<XF24v0d;v
zTg)F#9tCw<3W+eGh;#nxVa|~V@Y5MsG%>kluhKlrD!O3mU2xF))4ASzoD94hAsNih
zBBpD5YK__U_`+|BFwd^s<-|PuYIvm<e%1W9p<Tl(xv+yg-cZlluc?+;_(et1u#AlA
zS$&#b@ilnwzYV@x7g@d>O_;XC%sM0*#>%U*v4M?XP+?*gpkf}UZ(bT_aS8ZsZ>$%B
zFq^Vb_2m|+?_hbD-~$uTQ`3w{fpEcXxUT)0pd}$;ZtrLjHv|A7M7hKq?TjPhl$yUa
zm`dKmi4~C8fegSLos1YxV&?~li=Q#hEXFsyJO7R%gFI7Xm%nB0@1|4C7yj7UB<S)l
z(7LXMT5>saFqg837^wR><4iUPOWd$9^EN_e*mL`GPM;EsZ>#doz-7>7(+;y;B-H6p
zqI(1@w}ca(;@24#_?@tvXKB*tz???DyM0V2Z1_vJBEAT^`r`)&<Wct;3w?84%~CHQ
z{_6bI#0ot0gn=;<t;7Xwe9jx6BwCE4UAxO*Mdc-pe1t3o_Y*QOhfuhh{c<kN3g1w<
zda)}Bg|PbcX9(Rwl%h0FoYP?7?;^bBJCKl)<NjGif*B!3Q5ud@CS-|qhuyn15b_lS
zCB|UiEp(YmMZxLTc$IrAvhlI77%<YjvOuM+drir}_3ABB$SNh))!M${3wW`+FZ|J!
z?o$ZW3T7nD#Lkq#F{em;&W2^BheTWODc&0_TpOS!D7jGA?}#r2Mw=lx>9`+<<lo)8
zgEDi!L$zz1;0b3DPV<Js8#S)-dDYBGkUQdJndoX>7}lx&aQoL5zvD3!RBGIq*UM6y
zZALM-N=~ztaA4pYGuB!#ZbKcITRii|U$#={eSG07IbmX=FMz3}FPDIM;oJ;|vPEy;
zrhP%)Y6;k(_}JHm0^P)K02Y6Cg#^q1Pb$B~*?29B7Gn@qKgKlK<?TsFFMYU8KQPB4
zHsydl;?2OXm8Wr>1Jh|SRo8kYVEwbbOJNDy=gR_^72or~O2mu9&RgE)EL{UNDqHa5
zH~w58h3>N2J4>-fd)+7vEmoXBX+>uEGQ?BH-dJXH=vWHS!*ug(<8x<DL@m*rkyt(N
z6CCa84_C$ZgSiKxSsArl<WS;h-pAl_L(;tYmjMO!&u#p39llTxF4ec-XT<elWm(j{
z!Q!|r=4{W0v0%1%>YFS;PUTG7pR$(;N#GC1#j6JQ^i+{izi-}jS36qk#J29`T$7P`
z1Fa<Vgk=zDfDdk25~Y!8AD2`4Dcl0F_ux)@O})b=u=w{?a9q5%Gnb5}ro?{C!ERT<
z*}^J5({-lPNB|P$WB1-WmGzcFOyVlAdttX==?qjX;4CcRcUqdPB(M#GxBP8KMxIG~
z+t=g8t?2}|mRm_q7#*=!;87-tE*6ELHb{N^cyzf|8eN{<_`F@XAr>kv59ly*t<Q?D
zBA&Ex*I*Lo!8}E#Qmw$?rJ9@d6jYqeahsXcX$ArPhcjZq;Lbnoq)<wdOGgIw;o&)8
zlbq?k$+^!4iPEtn<?Afoq@AI~<YI|mV&7y^(OS2%>zi05(;*V--pF-toYzo~P=RCL
zPZiv8%QVmh%Qb(`cJ5Tfo`ip?FmCh(k9l7KUoDO3xt!2u$CzomCbvNZ=}tmUMvX0%
z!o*X_ux|7jut7g1nd~!kfr>LP?4mrFUdMA#I(ER2Q2<?f57xojPaW@g2_18Zj-0WM
z2JAY4vF6+Zxxm*nNr&LCbwEl{(&0GPp~JX5h5>aab0r-IBI^6A`)2QhLc7h0+Y{k7
zNWO2)!0Y`E`(9~7%THUlruwr}ruTW5+uxU$@$WBwma7hdKSRE~wb}5&x+q%Ap0~>L
z5$_~7t=6Ez<JffwP2b(ff->p`vEX9up`yvY;ZYikztEo|2xE4*%pCp6nazZ{*Tp-R
zJ|mh2vixWE|Keyf;c5=rYM|}Y$EEu!MpUtF6p{q>IkbJ;7U$ou+ryc}gvEO0ZQMe{
zV;yX4tvz9tv5XJpBL(5t6;aFNSm}cnk!+19jay%qwjy-&)`IGKNgk|t-R@T;G+_se
zUn#fmfIa{Ic08Vn=qYN3nR_+WGifo;FkNNDp5v%d11GF?+%^(Awc^-)bD+ekwL-k}
zv-d3l0}_It0jw$7N>KFj+Jw=I&_jNqIs}d}n%H$^L^IBi95yWlb~I$O(qaSKB}ya2
zJ`Of;%~(WRY{%7;LgM(&DQiJ@4D8}0lzoMhC0au<{~E6qkI-qseTpYcMymJ{1zk#3
zn!FZPpEstfg0fdyEQg5OQfOy@L=LzV>DS~o@TZ5RkVc}3atqW;3<>NE5jf#Cqy>X;
z<zA42bD4``3mg-N1cYNy7^`(EcH{m97Mj0Tfo(t#G?<G-26zrq0)lSbzopP{e5_mx
zc)d`efhj7!%UO;VfqcoCA|$$oeMc_<&Wk&lj5-{=$dDS2X~a~(zpflBC;6HJ#fspL
z&mb`r5|t3S>QBiv<ZNIyBs72s;ygzkjleQBWfYNkX9OqFF_3l>cQ-_3_9bW{R4`SF
zyJe7xi6%*;4t!HHKfsa`Hbk)XqBMT8;Fhd~i-j&FQgcH>B9W?(pPs1>mT?5z0w>g?
z;zH#KP!AoBe^5dbOv>BH4IoFQ_!OK0lYP1(p&AmnVPw?m(Dg$Emrfu^H;ET7Fypp>
z%lVqBHH1VHu>z}rU<tbjM4MCo7ddDmfd&V^Kd=r<;tV|`G$WzxN^z5t6Rf9j$>Gef
z{3^K~w6lpj7ojryqA#Ma1jQyL#CwRbEQr(D9ibNmWuFm;D9u^HzrPoECLy>1P9;Oy
zq<8~&6Wo#t%>vo$VBN6%6_L$pv5^u{-Mtt8NJ2}D%MX*GI2^PpPeK|gO%)_-5NiWB
z5g{e}u0{m4e6Q!0yCQT)V78YB)kt4cnjpEg2P;@C3L;3Fsv(gvu0Mkf%LOEX-F;ph
zqF5YF%;8xX6kx|Kl6mb+unPmTKf8PtSwo*-_m+f)6MTduVs~ud4j_cF7TQQlXiP+F
z*K$K;X2YT_5zmrBEXS^A=%a+S9b(VLk4z)(qK1ThlhNAcTn`yPa1JE=2L;0Trg&1>
z#I^t%E{nw5AuQR#i=~)r#QS(6NXnP1XTwP`MzDV>O0(l?%h*GKqZ4;Oi6<xU+RTHz
zQkB3=9hF`aD@`D(VW>hgxY!Yhe=5)?GL`IvYSU3^lK8CxT?>c^)u7VysQ6C>Iuw(}
z2peV~^^M$mX?3uVt=KMDB}V0cOKk)ts9+sR=+vz8_fi{=6JIPyU+9*<l-dYZM+Lj1
zjM{_^>v$bdXS$M0mExTfYbgXkae0k>(K0lV@53f-2UmPbypn>vg<f8~+p>X6bj#I9
zHZ$=IRkou9&<@qD<*t(^oXP@h!(?<Lp=k|iDtOx@@hu8^iFFu?EGXvZ5`5ATWZvgV
zuZ41RH>^MfO|kbEpp(GbksB?=TYweJ7QK}K3Q!AQtRydrfUl&cT)1Qw_s9_iqV0k{
zBlLP!d9YOX5n4<T)}e~-CN!Cm4nT}!j_WHREl1OIWMxqO;heZo8f_AqIiba%W*6>9
zDTp`<^oi=mC5Gi(l4z-;MoWT(z6h<|$URGGfxNqcu#b*BlYMkaOJGieM(++wq0h$U
zOQlvV2gh9bGjlE^Lca;s?9fhdS8ZXVZ~C{PI(zOGN;YKn`Wj7^y{nvzjD-7Fpy@EK
zs*EFk4Qgb_^y*LI!F9@^pMDG84*fs@%ej`6Y)BKCW$v-3R!F18tfC`G3>DB1dp&Sb
z39+KXCh}m~XO_P|6MIM*Oj{F$bPW9L^P`P;of%1VS}ZRsk_D1Cw#8V8ol&<Nw~x%G
zMQK>Sz2&4iI19Z>@fk!=mKCGC*xw_jLXM{|EMcId5J5$2cD#)AC&5Bqq|AFR7ue6P
zO}{y6iPo;*-Xpg_DZrs(|Hgz?bSR<eD=MABRO-TZX`s|(9~_nH5MS>!P(xzVM^p+L
z>%v%?a9!Z@H!6jTkO-ldB`VY|uOQK3J4OiAtdLA<(>s&~4+1K&P%U)P(R4R@3RTgY
z@L*-$2Z7lllmo+#6Ju174Q4zY8AB9eM+`+4|2TmcEF0LbTTYVVCpSGtYh!6KOR<wQ
zq>Tqp;CX=HbIX;a>b$wiWcI!&jc}Gf=rGYogj%2wyi%BIi!AK@eNcBKEoKvDtb_Il
z_nV-8aQUYAib=ec*psQq3L@=PafPhSO>v4eQKZ|iU%pss)vR(Kl4voIbTo}a?)Ijh
zs5pielZ6@Up<IEP5h99LU2*5hylCvs6r=$I$Q4`5iF|N<c~k?FWXmm}u<wX}Qiv+f
zVZM(E>9tO|8Og?wskBtM-w9<pm^z_4aF?5~JG0P!p_e{_tK9qkc(Mw_*_v`F9nKwg
z+#i&dTyY?UsQ>FXE{~GBY*IdzWCO(~O+vHPJP%=?HaZ6CVsdq**Sc_3q<G*zW(w8Z
zc-sVCGz2#w0lMYcQckAjVE*A0_ukPoAN4x=GZ0;!sgxz?^WY5#8Z?o5A}yvC3pEy5
zVWD6-z*ef^BdTmEToJOoFj6mk(bSedu>vTH1T9!%9dksg!c?$EP%+;pC|S=lcJN<-
z0#-+9bUON%ATPcT+|k2EexKSDNIIJ0!$xcw2>tC%?;u-8e-lKX#8iqCr26o#N=zZl
zY7BPARHTkQkw;G*iD+I^on~AvM4~n#L~c4lT80hDp*axfFTj)4v#*Q)kV4?|y4|^p
zWIpScC%`oW0H!waN$Xi%I;a>-X_3Hd8%!}v77?z7g(pvgOYsqe!a-l_xj{0Q5}GXG
z3_>yA&2P#k)i|1JAdwe@M)v*~vJ;v?<OO%;X9Z?Ed5xGQR6oI7oyN{Cf~4O^s5OEB
z*b`Tr(UL6oB%!ZRjeT95qu9NQn*~k_yq6vKqfEbExjjNv;EN5)L&?JlO*F)-m$;BW
zBX0`5s3`jcEk+j`T2d?!V~7Yqz!#WOJrkOyBHk=;8YxY6kpsd8@T~ewC11h*VD@@k
z8ayl1_L}1vnrY751>lguwyo!eQa|y1i1Z_vv(%=)BX_a7ASHMV-r(SSv`R0Dry{gm
zE^s!#36Csrh$C{vQ5r^q{h=*JSP<m>0B|y{IaA%6+X5lPq_$PM<sIbvj&YE{c83$R
zz$=`+1fK?e!-a1fFaD%_N|*5-s^KQKt<v{~*O`(K1#W4#VcLiyY=>JcsG<2Hh(@yZ
zP#@G%Mlqk_7(=RC&5eR2ok8{aH5L<jS{T&b6G5gU?u61EmG?mQ4Nm34AQD{rUx7Oq
zxxh=wH8R<rTo*{-sI;w`<E;#V0}*%uh4p1RydW$Q0yHS#-ifEd$vzIQjo@j{W8p=q
z*TzI;$|9hU3gKXZc!~^yf~@nAoGqwGPz5Dqw3x-%6_Qnw)?I`mWCQ(lGBiYL_;Cf)
z4IXkahLeVqwIGe$Cl~0amqFuArlN;{pUgQSdW_YpBBCPyncyVFGf4|hD^RuRXW%`n
zI6-VBjUdjjwZ)f3stTwOw!(%;cg&T4I)|~0gdohQ^DJA-UWvbvL#vkYZMWcok$HmL
zS;z)f+7%&LCWo(;iV)NrEKF6JR(eaEO+iq6VjGHQMm`t%Y9kv^mlAf99L=hQ=o^li
z3_%d}VM-?ClOYLOX5XhYVJ<^~gmft8;&>%3^>y5-QfRqs;AcI!Q@$ZyNI_8P$LGVv
zt}9nd3PD;@+gOuHj}<ScpwCWx+qGqpY#M$>7S+Lff*TyEd-j+c#PX09IS7|-@q%_8
zWMdYkA;UMJsoQf+fC3brQ;7Sx@vfu%y)^Ze<6W}2Ow{J_u7`ZM#aqdx!$|?Q%S2o@
zYPEo>i)>7zG*-qJ($tracTK_NqnP7eN8@W~>bB!u8n{xF_ITIB_)ePovhgk&J~3+2
zc-P7V6K!=ScRol6y!0ep2EYqyDUT9eHsf7$;0F1wcq<GaygM74OWB7%g5kp|xF>*1
zUMvxY4`J~|2e=p&j#Ef1)RtwrLZ-uoVm`sZ+je3~CM1F~WCPV*En;YM7*L8iII)eM
z$x&pk<t~Kr!l}~+*ND0-_5()n@`#6-Q`X_nfe~0!k}yd2n&ix+%v2&fwolwDv;$G0
zHgsiDr}i<&IACN=F+VlC(RO08)@g*ofYBO@V>H8YMmcbTT*F-qg9S$JxL(vb@or!Q
zZmt+}rp&|N03(Q%_6aY_uEDOuh`=$ESzeP43w(i*8t5dYQ|Fj{Eif_xMsqb+^7)y-
z$Qu}KEIUP`F=mhu#I*D>NE=6tllvfiCp*YewnIEEc+6u1iR}_`0I&rctt#k{wfLuN
znMGW7(Ri1>pjUR#aU9FGEH1lXylatQNVe>suH_c|?A-CL6#}vx_rF~$+Yir5%#1}y
z6W;5b;LsGG$~n(wXp)cxgx;#S&GclIbT_UAs04ygBP?>Ep25N^Vh)H0-fWvdVTX;2
zpAU|MVjwhlVy}iBI9K-<Ru8&?t=$msBKWW*`?xR{)I){0KDrt97xyh&z;cDbD#2jw
zEaGKa59g$e3&7{-Dn1}Nn=qhC_bvEbZG8Fk<0|RiTq`Mb10qpJ?DWEk)P;A%2Vg^k
z^-dPd*rB21$Hl*c0B}w>b}+-}=jw*BRuBMgnNkyC1@o3<s|u<>fKYgVq_62<8(_n-
zj{^Z9h=c-+gdUALopJbvghBzGdLwq6{!M|g;Um%&ea1`@5l28#j^l}aHU$o~fc^>4
zoyrpCYt%(yy}%A$H$YNafDCTrh!25y;45DW7UW&WRMvm%E}T0~ViE52C9nUmr)9-S
z);JlLvP5p)((}UDuEB9qsfnEe>**TL*HaIK;R7%_IE_4U*uRGAT;rFga*oNhmO=|b
zBV6qKi?tVZ*SDkGcr8eUULjryatu@tCO^CByYK_a#gsuK5w9@<nD{EAeeDkGGoSCS
zDv1*FKtu>nq=mM5e>T|d;M!l;Y@UpfC!=h*oK#Cv63S<3<$Tw6-hYT?uM9cMS1{bw
zWl1%64yJ#KS@;g0t20h`1-{1OO0T(d2)E#WAio@16QtQ>F-|iz$we4sk@eEuw<KYl
zyS~s3pW<6J3n$5;I>?6ZaxB57#m4TzR6q`RRnh=BDjJ$Iga&%ZhIlMyqUjtetnCP-
z-YOO!h7mxH&k7s3;V{TA+~+u)lnEL*4bPTVTL`oqXFe^7tUYQvPAiCI@ba{H^Kg<i
z<rd2oM)VL~U731&L<nj>l!)iS&CfDWDdZQV@!~=4Fd1l%{5Fn!Qa0CP@cXEI7Tojv
zmgQBvLV-9jf^SI)87DVKFUbS1s+eR!R&s~~4!7Wykba#zZud(kKt>~p$l&aOH%_ds
z3yw>>!pdFYQb!jC3U4@1;&0vXn6S$o^Wb7;IV^TKSDTLn8jT2Qe^^pu9e-21oa^Q!
zoY{NRg?eu@J_&RNc@5QI`#iDk-j^R{FPX#8fqet10>LZo<nRjb^)qE+gm$314N)4e
zUM#$bDet$b?}e+OW1u=Xl;x+da38!EyEBBQkuolv=h?%KOJADrsX2TfTL8jAoUKsM
zl`B@s@QBbkmyii#fS0Ii*YC3y&TPN?H~E7=d<v*Rtohcc)o^5vYJSc6zk?@2RR=_z
zmkW(Du-erZzpBf-z~KiuK^>6lhotbMM#1f?_T>wFK{j|WaOr8?lLE_Q*JB<pg`$i!
zcwA7CajHuEEY-;BxSQ!B-lR-zhA!+txP^C(Ni+;=eNgja%g0@c?87nkwV>x5xD0=H
z^$*A9;F~Jn*AD)1(AH`NcO}dw6!2I6>{~M!J7dZFSfS}+-n>j5h92w(pmZnWYEnhx
ztk{$--wG7jr>g9g9S|=CC_RsLcWmCNOTB-!|Dz23VUQpOq=YvUr9bldSYN}v$h~t8
z<*h#TorY_}3_#(W^_>|j@v~p{Y+5|E{OPKP2l!$>Xavf}Hd)nN6Yeg07?rACLvu~g
zN<e5XloiA#TMj?W@w4h{jGo@M8nXp0LtNVZ;>mWaUm3bH{%s0)kr6o3^Q2+n(~ILm
zv>cumdPv~w@LO0Lm8(Y?JBni*TtWDw6muJe+lLuj?&ki__ujw${U+azYWyG{mzW8%
zD9Q!$xVL$YozrXo=X>^u)rL*;f9nZ-d^~h>?QrDcitWD_Ch4(9->#e8y}QF+{@#OR
zcjL|mnG4D{zHh7lZ3<UiUcBk7to8F(4bH!9t<BZPhxX|8EkC<y$#3(HZpwGu%&61d
z6Y=r4M<Ks3DriWVA9tfwSpVCHtjag?dFN<VUzqCRI_5QO^3o6NDI8t!E%e(sT9VQ6
zhM(M}^-T@`0!1D8mffrSE#k*NKo*;dG{s>8-J;Cj{)V^4x8r6^MI7hz$A8#;*;*d*
zyf<E{;?QreM{>-_Z?Lwo#y&K-j!Pg^`Tmww>1*+Q@VD!uUg9kAxr6sP`I_*@i8~rN
z-Yze!<#bB@3uKhGp`+i)ca!yR7mJczq=SOIGxOSB{v!d-Szz{ZIR3GZ)jvQrc0q26
zGxL7_tCc*xv+s8F**`EnJI-!dd*bb@+iTs26UN!i<`kw_`u%WvX_qt(WC1dzu2l92
zvl<7w6m&WM&dy$^k9Ol>0B`<KZ)xRXWsh)^e}DqBE${5=b^k&A2grz8cKr?jMbO8A
zW(U$Nhj#V2D=N(z7kou5$9KPTX8yf<g5M!P_QUwEUkjgad70%juHT&+k7_!nGdxBf
z{R8w@{Fkpq05sEi9LP~4ucmW7!*k^MKR|!RfBst7xFz{tAR~?Znx?l5&w+n|MCU($
zz49R_IqM%v@){><YSOJee|#9H)N)t%(VGqL+Vib5$Jffa{n<<I>>A$qp#7f#*Z=I>
z9&shBpr1D$-mKaj5%}}vuk$<O48{k%D8$UyRZ}bPC+8oa?f$_b^&j^+ZkjU=bR=ZE
zuR)kr&d-<QamT7%z6V0;IvgA~jfXzyWknL+bnQy;u=xqo8yyeEA?xln-MUiWo5|Wl
z{~b{v&98Cqre}2B?ol1ze05Ecx31KU<QT&)9*bPiH%-5Hy_5Sk4qW){YpH%+tKMh!
zG6HLpP0#+09C$yK9(<eDT<IHi_gZ!R?^vMj{ncBH&Y`|uW_UN2Ty*ZYkL7(*diagm
zTuF^SR6iOR*2)_9(b=~z?hE~^uS=g9-amK*_S%?F2Ka_=dz&kBqu<YrC!^i^)ui>7
zS|vk=hJKbCRl7E>c=IIpx2wv&sS<prv52KOvF%s+UW8_VoqARC;@jc~Q;#Wai_F}5
z2Jv}ddZEh8@0)wm-k!cSx|D<a;#p9|w?0ZE`)W||okz{PUQ!OeY@Fh)%`hY(c%gt!
zXFPqU*i^J=Ip2SFPljn)CR9Z^%Leiu)_nT5tE(Y>VYR+FqJt%_d;R8a*te1O`b?jL
zwjQbWt}Mip0o%Hvz4xcE?<5o^@;bo5?a8Qp=ViU|vQG7`u1lY%<2yhkC|&U@$oAjV
z9{|w{3eW^;u0&OYeYpQXKI-nzqmNAzejiM2+@!;X9>)}n6LVG-e^Z!Q6k=Un&~@nx
zyu*N#Efgy(^q5py8+I3JRZ%HijMurZXtD15z7xD;iv>vJrW!f);@QiJthqgd8;r`F
zxErO=3l$J8S+7&YOl^iv_1TTH7$zk21yp#;Xma22cPBFxdt^%7IT_+oxI!|hCcQP<
z@xE%WDHKVfLa1Z8;enMZhn2m4MDq`HU8Lq12ZQGlN=<)U-u2``j$+^nCG->uU>171
z-R=v!{W_24AMB>@<yZ@Vfdt@%r{(P(4`gI}RyO?G7_@Kb@6@H1Ds8@d#kh0wMpK3<
z2|boftngcfxO@%2>&_osA1Ras;$O+=cpHY#Q102@;51J5W}^3<f-qOgK>WM+fvgo?
zF5?~LZtLzChh1cbw`{$&$$XrwQq78Qv0{c++dKb#RT*kN7ULZzHLBk}^_-R-s44hX
z$r<MucCO>il}!hiRJ-2jPZ=^T<#5?j2p%G!@^dHO?AbJ3z9+1~A_NzUKxd$-GV^uU
zHdOTc@u{Ius)Gt9w;|1!9$(4vw511YVRF_&MgHf!ZKp;9=+%kvo`6K8Sa}t1AM`7a
zL=O)$6kw%7N`pNsE^2uBzR_N>s(j}<AOs0~v|u2-sJix6f1+AmsV^*|IZ$r+w9SQ|
z<?`L2$SrW3eA=US+EUNfKDRro;|OvdK+b4p^l-pw{|P-8HZ*Zr_;FZ6P<H6_(LXjT
z?>qHsV@{Pcl*Pg=2R%7mBVyINxq*cAPk^bLVcvH|rq6*VzlBe8tf!6s9QIO%KG6k=
zxyb#k%s|PYh8ldrHJHfVf^u*`G7R|VR@g?TqlY(y#r`9P2eV1%?o8NnqI3fGan#){
z@&0$S#D7uHY|viLd@p`;xHoqzELMVdo<dLfii#gfl6y>e>5=BRnZMsS5XKJw<_FnH
zIKR4n#jk-U|90=-_c`{QZg7cnLOj^;Y@-Lvrrc^`Y<k4lzR<c7+GZ4;)jEUFO+tV#
z(N^wl`zwqX^GU>I126B8|Ef041Y+<CgaA7xw?*ny_ASEWL1R!O_*Cc|Z|2(LoXV;N
z4r_pe$?2%OLGjI_>Efp_2C!Y9ddfZGOI&&sQyu?-X)fB(W?HGkSU^IKz~%PB2|XsG
z(l>mu1#mwLD<bVl-|>@H|8yVn-_Z74&-EYlE74Z#+VC?V0x{zsLwj{<^$&8l!<GOU
zgYb!MS9SgcZdNr%qD5f6ZXe3JU0rVr93T=+V`b5lRS$CgVDS<I8~7FWNyk;$8S&tH
ziEY#vWtGr|p9c<vUOz6bu5|YN&$k=j^}nA%{92Fy^s@M_|NY#>HwHU6kI?3Oxt=p8
ztQd<(NM7=(&~yAhpNA?pv^gi<ZEqF+PSDYlsZ48DeC|J=c1&xBe?L><vuc$8553z~
z6M78)rFYv(smFhR&%n+VnVIPb9fA4Xm`NEZDSEk4tu5@oa0)$^Q_PVK)Fu<P$B3vV
zp{Hgr!*A-i#(_pGh-nRt9{yw0r$qc3_O&j|>f{MMS}QWO&LR{{5DuXZ-28RSim@0h
zD52}G$~`Pl?`~MQu)3i{93eGrKntW*7rD3LS3$F28K3G;Z`(8TTg*RH1NEw(oVbf8
zjwECP<!uDzgotHLKOcoV)Pf}NzKCsdFCuS4tHF>y1MZC<6TI4fS+-rt`kE?!4=aw4
zttV`MJZv!{T}e-EWQJeSB6gz{P}>?JGw^^*EazVEONnpP+PpgU!S;Cy_S|W^7k|@S
zV&fBc1@tovW_bC(h=bIFS?z<mj3p!ll}EfsUuAm~K0$dO`UJz8b)8Xdy0(?5rKdwm
zjeh1CGyIXn1W1_Pk{MVO^e<EOwuZ~!{fYBi3~1abj@H$`WRrkufNbD`mwsjsGyIK&
z??OW0#nJ=864O~P5qNT&S|=eeQM&Jx6U^@mOSi-lVNJv9t+b~{X-j`l+rI0#y1F2q
z4k&B>vuLY~HvAE&8!9cGJ_Yl$zU>=L4@NwBqPKa|)PVt7-%K4US^_@Q>C-m8n)txN
zNA=?ropNclFpYsyXbMc>^@EezRuD!Sxxk*ePE2YlyaL!>Z&<wr7TGyO+&qbPXHpNY
ziyP8~2?!!SK`A1AP}v)fe9vDOM-sH4f*I-{{?h@E3V19S-oF%k7gj%!Ow&0%pbvA3
zOrY@fX^tDeJ;91$0mex}P@%^?F&FAMY@jfSeio132=NjW7@+I8dRu%uI3<yuL?G#d
zdkE9dQ~4jZVuhZky~N{*$)JnH%~?}!!*r^{BU_?i9+kpvI8juO0-%7HZ4noJ_ZG1>
zL{OZ>wrGrcU%5>awGc2FV|?9!Z#|(BFHlL&f?fR4_K_llW)WY#^y-38FpHz-HgrWu
zLzOT=Lo@pBuJ~L#$i+iigPxJW{MGLzW85RIh8+fWGv~TNb=EMLDk5b-c4}YEU)qI#
z9~&aDsW+e6W|w%kHCpHk6!IoT4Z}8ahWcVZ{!HVZSml&Vu<1gGElQSRW>WOyRAz;K
zF34|VHb9F2&D?aM3`FX6^|K{*bf<vk)rRz4qz9UGy81T~YZEL%TFnTpxv3t$vf*-*
zo^hR7Vf-kR@j_XGV>Gkvmt7lr&?z%ekv|m%{tUv<<`+wB^1Av?fXP;V-FgD(JdtH~
zE?us)>Wd%0`R7eyIE3G5cj5aFle^CTMIgdapEqz$zDN1YT$pLN!$!U4nr#uR(94p2
z;108Ps6u9-Q)|@i9U%;{O|t%^H4injb{R7kl8_NWV2boW=w9X3W4jQZs?f7cnc<hK
z{7+bFwZhXJ(2}r$`71Z6xhXyPI*mHpL$yu$nx*>~d}=Q9*Mfx67uRUi(i64J@EcV@
zA4lxDJ7M7us<w448ZJ3qISdbiN>5y)%`B|0cY`fg*F_uM@K=;Z%OJ7DrFSd$z@~1|
zv6deAPRNbESt<9F6h%DOIVWvS+`^&&QdabE?Iw7z!+TPu*rUR*-Z*B>&#N)R?V?9u
zo|BB85Zk-1CWcly;QLD2TonBB2VrLXK85p_*8g!2l#~2e5{=xrzO;IS07i1jy@Akl
z_L(?l#kzs;k6G)WDYcc*)EQf*j}`<%*=sh(#ifkd-F7x#twDk|qs{iWjUJfPHWYNX
zEDHq9!?b1^J*wXV1FVVAEcpI652i?%AAKkd%nI1xWd>1q>E{W+FIqG89@P^r`$ZmY
zsr&Q33Rk{uvgc^?_Ki-_w3+9t$NJvTn(uxe9dTqT38xQ7oShdb!?0eKkSkfXCukA3
zzBh;TH&^zHHS<X!vxnujt=|)6<um5q^JiDjEF6xA`1sQlZZYe=Qj-oYlK($!eS2Jt
z+xKuzB^8BK=rW@ar9w!$jFEKHg;41-;Sj=*Zd20?6Q@HmQ%UGDCzYr)NJ_Vn(BoE2
z65S>m@^qV;rlz^S`>CAo`F%d`-_P26ueJ8tYp=ETTI=D(q!v!?=5sW&nkScbaG9h&
z_wheES4p1|d5UjpRt`;R$O3R{mrA%~E*IA&-16`luZX<RT1s61&~-|m`mEOEbri@O
z*p<?xj`cLPlERnNZXLMq4%L79JFs=Q?(#(W0J3;-7(cJVN%Rp8`8+L?`;~><`|<{v
z<-(r4zc8_S`ShGucZSXYlYeKyVH)>ZHxE2BXlBtX@4fFpwgOa1Bwpcbc51>_|J=MZ
zb&RzZaA+yA^J4S(xf?#_H#)E8&D?{_mP@q+&LaJzA^pg)d}e2X;vA<GyUAa~(;U<;
zZ|oo41+H)8`kT9m<9xg4MMci8aQg+1t2mk+x^TlkpEyXHn{&smEaJpv_HZgtyQ1nn
z1#cmdWY5VA2hBGdrtUoNu)An>x>6x7gg!gEb1?YnUsd!>Q&=n4r5cSYfHs1=>{302
z7`EVA4fHVs6Z@3c!D*j}f49XIrM5z64iA3|P*r~vTX#?8P4KTz$`ir&Cv<K;mwD}v
zgROG6f=P-HKk+o7L0R}#e^va$UPg`lpb7Wtl5FX_jj0Ygo&n1t<}vVE`~8(VuWzHb
zBs>%s*PQOzxuk51^k&$K__c`kSFkwn0!?15I4}6ouOHSyKR<Y^E2lIETES)CkU;5a
zWyje<>7t|jN9np><b`7A4DX-bqc_7=#oOrvpG~1O<Q-bx8xI$eUowhHM}MssbN~LT
zP5RmHf|{Rre>VqSqNZ^A%@=I<i@e&>p}ki-7qk>hKa{697+*z{x$c7y8grxA`8z7;
z`xohhbM2ZzX0Xq9niB=NYcif3p)tF{uIylt`B8q@p~TW$KK3D~T2WZceuV9AXP-PH
zuzo<hj;cQh=N+ujJ}yB@?@B#r*1YI|PU*Zg`9GW=1dASj3B5FBEtISBcF0a8RWr}0
zKbFkhM02p1m<;yr$!nVg6&wnInP@zR`=nB==jZyiIYbZEI#hNUI3InQ?Jb&PezAZ5
zp^&u<(i4`g8J5ky&KfcP;wk#@<)>I^Bp=_V_@6nNA0czNHBdv`;X{X#fJO`W{|x@p
zVA4+@+KowxARYQZ5`Vt3!e&Q+d8j{vdBHd52TvO{KMChQ1(t)tT(AH0C9#p3wt45N
zcw8Q^xECq(%*A#?^uuT5(GOCi=+8V2?LB{P7J|-N|BjOzl;n4rJfMrc(rkT5;$UwM
z9Qwt`-U*l*^Et_qui65#irF!N>LA?RvfL{jr*_#+Iwv5%aFxO{RZ2|?ruw^#8?s`^
z;e2*H>DI_oUV~r^WPD#RXZe8DmB8xUy<qjuLj20sLB%g@G<mCG?PN$D-IB*QK9Q1h
z8&swOH=M+{EN1p5`7)c*H%|UaUKW4)K7*{vX3{-)e616y{}=4l0Hdef4HIGf8s*(;
z5cow<237<)g8y6b;rrtC$=@}hwXZfO>TtiL6EVPT5wlm#kkytN9KZUyY-{=YH)9h-
z%f>P3pDBf0avpyX;53$o^N1A|>=E@oKF1Hx=S#s=fhU8+g6VIbvEqW=qL#-O_?h}+
z(mh}tsqFVR?^t<(r>N}lWxhD;j2?$w_x>xQfhyNyNlvixjrA~<wS~ovcrIvg%BdR*
znn9T43eUS?3VX43v+z;TI0`WUEEt!mS#i@a56LOvg}u37f6a|d+m}XSR*Pg`E6l<0
zfn<m7W3g92@~jEOFs)ScStYgE?<tzc{S{1;hmS9nlVxMyqFN4tUD%8z`F}hKmY{yT
z%;FL(sR@#bx1T5F)#LQB0fBkq^j=D;9;vU}$fDogSil~)sN+wz8Oh<@%Vdq>xniU|
z)l7?{d%gS8YMN}mxta7;Ma4#l@r%yq0Mp+HVyvmvJ{v5udi;PN!2XhLNH2t162Sd*
z8O?mm-~a9yO#RT#;*#8bRGwm%sVIOfLraU=#b<Ym6dzad#q6feDZS}Bhga;5f0dOc
zldK(}ewbFKHgkAy-5Ia4Qe~4Po8V?p0jW@_fF;GlT{o;)bVHIWS)<>>fCCH-V2&zd
z9nSL)zEg!YHOU1SwU>7^!^t~<m$8-BjILdBHc(X7paN?;-us%+i75v+2A0;mtX99w
zRdndNJ4|)S{+b}k#25nv(U3_>aI(-yn$mNF-*@NDA6S_qlB%3#427n2C+TL8#P_br
zHl+J4pHj6aDa564dCW4n;?_?V>fs;J3B)%>0%|F!8D9zYrF35|yiPg`TS!xE!*bDr
zL~yl4s`4)7SA2h+&-P@o=+Dv+OJ-6@xQ7)t+FHQI>`0Ss&jAjO!YdP~FE#iI!$f*@
zT@~Mi50dZ{KobIooBSh0Wmxcck}Ej`34ti|YH`Y38LtkxG0g%4MT$gF45+Y}j;4FY
zS{piv;zKOp<}r}Ut^oQT5FOwjn@!?*@64sbZs2DtfW`>Tt7;9SuQ?pQo+_*4f|^)l
z;lgX()M{7MhPSR{PDQ{f2sreo{VBv#u>I5feE3m5zma4%jZWP;{-e&Fq7eVRqBJHb
zOGH-2ZI3;0$~eBL#7z2?jFd-%RT#@_H)gn_R++hzML0yw1FYY=GMds^p|8KQFbZBs
zuyItCx1yk}&kZj769|r6YX<2c*r3W=w94OK)FKB?*VGaLvDDHu2UnfzvJrN)HDqGW
z<D<bjb)#7w_0*?1xO`5R4YFt0C|psy%h#1|T<k{XF@ev3tX<=dZ{5r4gKo1>l7Q)T
zvb<QuktzIj2zfG)4uf#J$sU$gZ5Pe=-z_>M&zN4jFPEPhv@HIwl2y`sa!`JakT>=`
zVO|XF*B7IBN{NZ|ru;y`lo<gcYggSEJ=OV|Nk8&2Jk85?@jl7<CLn1DOUdeGxlcO4
zEeAKkUNy+fIq1F%e4V-g(X)1uNxULaNBS7?pg<!FPgm|Ym3(SRGMVJYR>mn|U<BhB
zO4eCc(&ReWr+B;>2itzj`BaFwyx?LuyE|43vnKxZVVTf5MblzT6)}z*v^ZJm!7sgB
zP(hc-N<wWVhwhna##nDBSHlgq19b8t;bxg24L2bBh`0%02uR-T4J~NqULY$G-pT8F
zh0%Pe-wa-+`E8?VQ5Y`SdUJ!LgP_s~|1+4xoyV)gtTt1A3S3+ZH=55k?tbDJIq+4Q
ziI|(X#bD?x4wz!TU-q$8D3bfV&A=f?NH2UrFQ4qip<0>0P!6Aa^-+1Rx%^5rd+2mL
zN}YGgm1GTtf<0aZ_IL-)r?+jNWRzh|7>%v9tGuLZpF`!vVM$CVQiMtuf=*Yq@imC!
zIHF{;mvrJKmt6j_Sa*;!JYK<xseElcTR3rw?$IG~Fy!Fv|7F7LCybAgjEFbcX85Mj
zQV&w*$7n~f`*F-<kubF;E}s3cj}$;InwfT<T|gF|JUUpcEsXsbZ{Kb98WYKH_#_K$
z$Ox>3THttgQ{qw4y%`=x2+kyTi^r3Rb(~>+ZW^azh4gWG1@ZO8RJ*RP9YgVt{-Pg8
z<joH28I5ZDRf}Uog=U8RqZ6*O^$g9U#J77{H*33Op<xrhXXFbGBzFscyzdMgIZCzm
z<muRx(wBRMPDCXdGTtZdpOylv8p8oe<3RSW(d$m#cN-Zg9Qa-LaF61XNpDMS4)9+p
zS7Mt+Vo!{rETW4VJ5~^?4Vl1Au!^hhZT6Gp&LDrKbktBT3=fT~*_&!TkM}LjF8gao
zHsQ^8>XYfM3ynw?Om-w`b7C@=<2!rvObA=bDr^N=1*ntLL^b_d${n?CGwmOp?b_`C
zp;idz7vwYz4tZjZe+v~~#>(Ud(pUU7U~9M2tg7CelqX;q;?doa_QAm%dkQhSSda#w
z)eN5uT9GcI<?_1CliOf_U_}0n4vlb1lIQ8lMyyTaYAT@ydzlZcICKqwAJ3`yX=Mr2
z*$xwEN!P=1;+PpzPA|6)4&cCx<+(h<gd1SjUN7QWcYGikVopqc1R>1b3g;Y^YzC@=
zeu3x#cxN(~Id-+^)4+U1Ig`WzwJ9YPt}}6l&ftzdH}Yzn)I6+tb~_;0EVk$Jms$`C
zh`+~Q3rN{UD|^IzOH9(YT*HgFBG>94m5)15!SPbt4KUDv>>P4f+m=KA?cAWcT~uFf
z!j@O$FVPKR`Y72xV|eiW1V$LN;%S^UlxR8?aQ38?J;oIi%M2||ktxfH8*$`@q{(1=
zsQ9?xHg*_S2BOm2X=P7PnZyP|#%kV)BzZ*7KC(1fakMs^ru(XNT7iY0Nsg<@hYl@~
ztuDn);^YG@(b_L3*JFd*tB`maxQ%R*!m@f-I2j%r(ZijBJ+0W{x^ar+Xi7%ZFcL)z
ziJ)YamvcucM%-*Rj#yh@zEPHjX8*GxoE@|Qk|qM9;o_X|>!0%)n{^3|{5tM{`N`r@
z`ta<DZf`_LtJz)cFQkYudIh1$0ZV!UiT4N&MV~t6Ok=zA8kvvw(b|3vh0d&%9@#&d
z=G6V<iFM^!ueexAqVp_fIIZo;kb&>ilTV2wVD>32sR+_LJaI%Yd<;(`@8qhG<L;vw
z^E$)`O`wKPeW0zk@Ny0I5I3Bg6D63$kUPZn?BG>USl+}sL{hh4o1Vwc7G5&4yg#5g
z+|`nTmiIXm+0sli5Y77N5cw56YH;9VK=96?Lk|QcNMcfSBgYR2hG9P{W-XZ}w`usE
z6Az+hQ)HFa*^_D@^;E&NYU{mAIC`Mq>uX0Bxve`E2+a&(z!o?;+`R{sh^^v99Kj2E
z49qOPdQ9Q_N|VQh^+NX7CIG&-ZQ!1v5C3eF8$+m=kqa+ZRKJc)ka&Yo2DnOQ8LJ4}
zJl4lM?<|O;qRe@>e%gO~+f^f-$18H5!<+q=CNFXNndiz9jzHkz>UnP~4Q0wJ0$@!;
zi&TWgM#!E}4IgYdQi0r#33_WGR9ofBLhsv+AYku5mUBiBr4}dIn}VnY=Vo7nvVbcf
z4ply7x~VT+1L0m)E-&1<64G2mIKa>OAUUN(010jiYb#TLO`9ARe*6N3NKUbK?}@*~
ze$T<?tU|<jZRL3i(TnOH-sCnuDKo-nJWE)>X+>!7X;LN}(B{57<J#o<6wUVM7$j{z
zc^Qp@>Hf$)mSDS(W8OZw6%6&9Gcnm@#Pxr1z(<8}=ItrOe3@Ng4Rt&oeW;(o0T#0J
zawrTjE$WBn@S;u<YZ_PBs5m7MeN&>%zdt4<)NDRnfmkC69r~Pky_0*WX5m+%iOC!z
zuHK7dVA~USOs&|lnBy@p`6qZ*n9$-R>^Fh9@~-_!Q&(JRs5{NNw71OO;`LYau3p>A
zHHYR>Lns&{rZ^DSKKjiPdF)U~h%?~a2Qwt0s#X@e_f3-Vmb_D|?f!P6NWL;!pUOK9
zR}Tz<5ahWZwR3qtBZ;OjG=tMx3&JE!YZXGq9K+XHSlLs3y6j-Km>KY-x;q#MkY9Ha
z8c%PG3kH|0u|Y59WOb{>0=v`|6bWppGrg!GM<tHvj6%gMb87O3b>xRz?oS-;c{qm$
z9vBotPB&8|r?28QIfpE7LpCddzB5l&wHd0~T~|h?*f%}JLQWy*n21J^RGpes;f3-;
z4fmtw^nC0D5u`L1AU6WT{*`(FF(lfywlWb*THk0rK6=S_a};)RnZb8*ZC&ex)HX+K
zk^+?IuzgG8aiS=xd|2MpJ{%i|gn|j+o$<s~yc)-cP3BNWHhELkdDX*oM5k5@cA|<$
zVav}|@_?}446>iY8?%vZq%oDoa`4>|R0dOJhZ--#soRc}7$I1N+?3fSqQ%M0<nqr6
z?4XXI(}mM9ogbZ=ys>q%0xDB>e~2x9_K<rp5}v~x{T`fI!KDowIw32LZAYb!b}RZm
z9tzSV#hr|*tpyVKpym*^Zq$rR{5s4fe*YzS_#`5M9YZQkZix01G#Mf1n(&X{V2!wD
z#hJL~1U4=+2oE}VD6HY0qH$pkh%?8(6`UM8?$k63p3NNR@9Q|ieKwp07L1-0*>PXS
z2+p{FpRhnU_#_TnR~BAzVZ4p$yMS{!OOd52dtDZAGOJcm9IFGr>Hap*E1CC7>=ocs
zAwZ(|54%)((o5p15~i&7vY`ND9LkJ1M;?V`4v&v^{50su5SRyjwH+jVVL`Q1_VC0;
zh^jO!Lo?trPEDs^ne6+-gu|<&gdf4L`(|K2{|jpbS^G96Rd#D}G8qJUWK_KEfU7{@
zi{cI+O8z{1xRpp^v(jrDhC|JhJM|EmI)MZCM2AE3z!7YnfIQN~V+rFM*>TnHKR&Oj
zz3s&fsCpFrMS8a&B@R5NC|ntGrEv$diqLF=zf+R~EUN1h-0zw=y7x=)=OOWR&}bnF
zbL<$W8&OM##QGeQstNxPve5RhJ&A+c*7%$?6yL@O2>bB3Eo$slfmvK)m*)PZPp$W<
zBZ&Zk?+ekG^zvL_i4W3FamA!g|AgDMRaAW76b@PG$#Ebqu5ji4dWgPA*vH%jeD*8@
z7A!qy$Q)?UL)tt{U_uYitX@5j*Ro5z>QUxwVXl0)UXojez<7L}Z6b4eI{CHqDUzOD
zl+gL}Xd`Gyv#;qontYp6l!(s}7F3IKMc1-la-%Jf-5|euGqoEbf6DvP_)^+wEsnNp
z^~PFvU>cY0s;Wj6TYmMI#P%V)l{uGO>C{V55#}w&$YSA3Y6@QQ8mF<I322NjXQQtD
zS@Apb>@KfQ8G{>0HD?hCd8Xyy`p&1^fk<PU^Rz58a_%aOTtoL2S7S*QgoRkyIIb5I
z^c0J4@~&n>McBG;?m0^_5ObyQp02ys9)%b;+E{BNn$iDtE0rD0A5;XLGa@j1_cDCk
zd?z#-4M)NPPf4px3?-g%MTFwLvRU8}C*%YJgy$G{ooFaa-tDj)lERU6&*8qSZT)J<
zf&AtynSZ^bt{)_@C>Sr`5I63j`3CX%il9eHIP-KRXCGo=HQD`WF6!iM><C<sIGke(
zImD04A*v4Ht5Y*()>$`Qfm!J8Q&GT%%^h_egj&><2t&+Iz`tC(3EQNL0x|MXEpX8h
z%ndp%H+nuba|hVoryh*U3ATcyVV`H+xQ^~i+5{dbpaF~hBT740cXe2ndp=c1;NCYM
zJevcoyTz9Q%n6!qAUy08hRY!2$BD~-nn(Ksw&qF?oOs`ogxCjO)M+j`<)PVoINEJO
z;zzP-xS@O7gwD{R;oD%>91~l<+$aPG;x8jeXtbE4ok0*VqA6J_tcSI(iMOirBMx&v
zeA}?;=RLH_x!gJ7bw{;<g;2v;PnHa<1k^_t1jMCjY>akA7H&LqV$cWS906GEL~K2p
zQSy^49l*){&dOljul1m2RsVy`_rvbVI5HpTm|J&LhZ7|KTY{rxnX~TI?#jri&iV}k
zha(sF;!Jd3nJqT>lY>Em#D^*`9=v#SXVv41{)G{~X+ZR2^&4N=X>&l$IJPNth$4wh
z@eTTQ7Tk}+?$Hxb_Lql`BV<y0|3~JUB^)PTQ9C$9)nLzqsJE+cAxrjd{+CJz@q7-x
z;HEw>+JIvX_R*OYv=bc0U#FJ_jP0Q*KJ!+xp>Lea3zokV)q-OSx?K#~Z`siGG9Mgm
zjlzc;y@2~Q*NHavwFHm=8h3oHj`+JO%oS|lkmjL(H?Zs|EhDg>1aPf$v!1XR${Rk2
z;3{tTk~Os@JW~j`Z9fq#OyC#Y_u^ZF+yNFx$%`|``1SZ&6G{b0Y6@9R$!b1Dk>Gs5
zJ>R#l>Ve=mJu)K|u;v#1<%AtD;ki1(OCSvc$bu(r>~$mBlHreSa$%jX4Hzq}z6NOj
zC|dKR503rK?letoFs|$yLYRwS{M7xj;r*<XTIaEbFM$YNuYjm<>><5RCFs!Qa9uZp
z&=%yn<&oehd1=4^!W}=r9mzbN&PMTiNd2<J6%cqTe@t|4;y|<k40Y!<oH<c~$jKpa
z!gwZ7=JZ5W4!0e@204L=ew{Jw=>K;j4c?B8dK$bjM$=B#nRplK<LbX6{^WlAv2{}`
z{1h#h7)R8k(t+Y#1Ni+q4b2^O=JZ)EYy7&#pe-@tShbmp^Mql%=b!G`$gxR6_od;m
z-KNLVuq0W*O^>SkR9Gvz*B!vrHgO`SVBQu3%HIl?aNghAw3yR}y9wvFi2ezVw5~$L
zWN2sbXGC}(&IxxQEamvF3MX%CIs!j(C<^FKMy@cv?KR&>Q)pJmT1r*`h9Wu8lEc_f
z-rls8bs*l4S*PcZ2vUrxWq(9HSV!TC2kq<tvt1VVCIOL^HC?SH5o>A=AeTf=Bk#5+
zkfbY42uRM4Nnw#TXYTT#)=>V=8Y}`)+Q+N$#7SR?`I#8GQg%Pb8CU^f3pkx_D#Ady
zF;A`$m}bD*8^5FNmELY--MF=0zqhC&SedXl1#@C7jX|Hsa~}Hijivw5>Yumc$u+Z(
zxqsPoeLi-Kh8NvIObcYv{zV*oi?Z;}h2wGRgKd>JJ1+0*RzM_nGT-4d{FWU}FBnQg
z75Ka+f;$uZrmX4yfC}LssKR7VSwPQ?sPaz7&0{PCUUXL`?BhDuwQ{Q?T|v@--xSM>
zg^WUZ>i8q_dr`+4Y+ZHk{!XRFjS%N5D?K9}h%?K1yn*XQEMv!z!FGc`yY%g&qsj8(
z*<lBmXv`<?AJO$oUS8}B*uq0Jo3p5dBobc2FXgOoC0RmV;5oDC4^X0?rFTC;GIWZ@
zOh0uo9@v$Rt=+Tx7QH&Ny=pWSk#bRq>?nx0^kvrAA=>?r7N>KPfiv5?3i4u#ybNL`
zdmQ(6&k5DOcxGqS2xWRicey67Y>JR8=)PA;XbiKcOOuC__X&OF_dsF=_3op9Z;!{g
zNBp*ogwG5a2k-Ab9tiQsm@%~Fmli{1p<Jw|%#iuC7&0#1y`7o6^}X%VYZf&(fWW6X
z6h~)+Ot(}J(*nOOdpf!SGJEnk6SENic<vK*-lM-wpX!-jt1YyFU#YtSafZuc+sq;M
z)lJB)w+@iqOsP5ItgcL`f4gtxp86s0d|v!KSLfgz;J~@iTR}0q0`O}(V-|9pZ1;mF
z=4g2#?$PF4HN(`UFS#eSSMiKy5C^vK;&;Vpko{#u{uAUr9CsdA$ie0G48CnO+4Isd
ze4r=yGxMpmz{+x&!PmI_=KgGOTIwIq3nxoRHbV&#>d&_!-@2?_@7^lpRA?o3a)yS?
zy9l#@Vla;1#|7?WwG-gV4L^Sxb7!0@NtsEhaioGDDOKFg#P9WX@_L<A@rzS|+p&c&
zLXIt<6FlaHY;aB$ddHdZ+#w}Go)KAZT(gmUkMQb;c2-1#_0zlvI5Okvpgk*e{M5^-
zQ+I!D=?bBep)x^Q3jUTRXQyR}C!Q$p9sAqNY|B6t{){jDX~6t{_<ziglgM3oxpu%&
zt=>;ZV+td&1#~XURI~bJW+v@wZQXyk<5BgB?1uV-Jg&~u0EaNGUEm{9Wt8wA53t*5
z5kryb)0lud4p6NsjCU5fO!ks!*8ZP&Xz~oD*GRA47C8*JS8QCB9cN!)97pB**MhW+
z`KcDe87!3-mJ~^aCxCjFWQyTFuh_7rE6(75P#?UuJdAcj>0+cZF3nfwT!UI-16BX<
z5n(Ow)nC%B%{F#X!C|JEjfz+U9NcFV)~@&+qQObn3%qBZ9Hr0J;9V77BYjdo9{zm=
z{^w#=eVbR+l#o=9%KrwzAW*_}6$xsSCK+wE`_d02)ZiTo=o8168UW$aFb*Pi<xgWh
zu!Pfi85uAOjySbEzC_|olYgklVR^-^d*4*Uxu}xjSr<IRxX5`tM`Ys{`)s)$=R#j6
zU%<gclos-PgWamFEMtFQ^Ya+gnRC!PTS&L8)8i!K_NFL$FEe=4m9M!JynpmXxnYJ2
zHrVltG7KH7L{*6DN6vvYR8cV|_GN1D;u&k8S({fIybdbR)Wga?GvBeA<Cd9w)sB=q
z)0*lGe<P#8OYV}44sex)uQR+f_bHT`bv1SsXzF8g=9KZZaL#Xi7{s9k`PGbs8I)=h
zi0<pjB9LDU3dc`or8q<?Jw>B@I}S18$7>=c%V(soG>*nR_0y95&={iE#>Qs-arz9r
zUc(h-OR@WS7<R6^{G>5h(tidX3A3CQz92c8yq6=WJA4*NQ`+yEc*afCxqw3<`Xx8l
zN`ADkezXNnpWy0ml$x%j!p7C0b@uT08~l1>$T;Xa>1Wu{_~CH|J>7!&bA~$LHXlo|
zCJym8EBCx%`Ddj$5D;Ydj-}zl&*w*o%CAogsKo*fz3AzWFtD&&e(~m2@%%aAScjsY
z&g`FmU}1jP%=rjf4q35!7o8h$b3U_2Gy-a>t^BW(eyRUD&A)H4Ang?M)&I^$%!=$6
z{%{K}2d&FV=s!L2-XbOS{{k!vdT{{m1ptEP66(FiuNBoh+_uQt-Tpo5Jx?R%7Zx;=
z3BVpa`RVZ51)gxIAugi<ACqz=LQ+0+xIpj6bD=DI{S1=gbrVQxHQ?BPcEX&InsSwS
zXBr*Q*F|AuXBFsAf`7)_hIRO~X|ZY{-;r9{{LQ-7ZTlA4EwH8q+z?yQgel80EK~^G
zy(Mvs#eK#@n6-=1f+uF5i;$LIJ2e=@N*qT{vlgu1<jz!ltHrsu${jQQCDwq{JD`+5
zz$l0~#7%W50lzv?0M_@20t;XN?=10P7TL!C%yI}`YPeNo?uYP5u|Hb$p7AMYi+m|!
zA_8oHvg>&mF^`It8kTs{8gH$UelZ@177YQQDtWu>|A2BM)HRn$R{|h)-e`oKR3oF`
zyo)@PuNRlWKTsQBg4}M^1pzU0VCw^slt3D_uosT5+!GBeoLJfQ1v~`}Ad1_Wwc744
ze)WSbSlLhVc89F1jqKjtT?Oh7(*Hw}YvIUZ7Wa9-k}wmE@~G(LhUZ?0_+wM*G-r^l
zQ2F09D<S7J0_I4n#j}0?*@&%ME;iCgy5M)OY$ajHdVFIbOZAJ(v}CIwY;*bV8asau
z-Pl<*t7H0ri$D+VXNvG5Lq|~%_;Do2VM};jV^HSm9HKR&=s*A>W_j0hM;E4Qu@(nU
zA+EU@eaHb;J27)bfjV2z052eBE*yQ}3`O#u{5Nq;E&?(41bX@$PDA+ohDhAGwtybH
z^QPdS8>~?>bGQ*gfAecIP)Bz%SYGyb-o>peh*0@FeOFDPYCMB#U^AMm7q#Raf4Asf
z<28ci&ubd>;Q-?m@qS!ja@nPNep{E%zW7p=hg$#i8mWKT;qJ@+1?~^_S3Qh&MSZRo
zV;#QWpBGAO#z3(@=-4#9Q($GE{Oc@D`+UfD9V0?b$9-b_6x<*R0ZCEhpD;n~*?9iH
zbQHR*DL}<;Pq99D1YT6qT5;FQ4fR>YM@e|y%B$H&!D7`k(~`6}7^nTKr5}th*DUaH
zuL!yKd0vodydNrXBNR<1#OC|~N@H~lw~0K!?>yzJQ{CW1!(E(Y(3W(z*+%GR6gVIC
zkrWB%W?|oI1>I|>zAejVUwBzSAwD>~b~gg-&56GeR5e>Y{X)1Uf-47YX*bH>pxl$n
zGM|#aO<0+`(KS}H-9Iln*49SM(=okLF@a3$hwbiv*3z)(T$tOmgtRLOEiZYyVa8$>
za-aXfvhge2`(|T`Ly0B}+ud8)lD7!-ZT}CX=M1D8%iiyf^OyA31}zNw9Zhl`nI^yt
zgNMAHq8Y|cp^yep$azuy;DX;$odG(*M5!6>)oi88^W15L&9?ULvnuaKs8N?mElNCS
z^6OAO--^0&)NqZ_;>2{;`wI7wEC>0YAW@C4%60>fI2NYa&kwmU)x)$n%oV1qrSI}w
zYgCHod_IsHF*dZ&uCN*7e;AwN&{D_(1SYvvjLc`@p92E%ms|kaAq(;KTPOrSlWb!3
za?So0D#-gkmk1aJQa>I5Y)j*e3s5m@yPC=7uN_KKJ?nx}RmO!N4y^dhcxJaU(aew5
zDJ(DB>vf^bfBr=4xSFsnUMGko4dvUB<a7<!f7iTUdhr_R%fkqJ(TWx74|h~eMqL6A
zxhNzW`1|M_qe#+n&R-*a&gI)pIytF7+&&F8q}j&&k3biw@|w5I-Ywb%+FW*KXnVX+
zgTHr}M7qgE$CDA`Oh08>@By5qXndE*)tSZp<a^!ig(=*Fzy%~op5dRv#_`MSJ!e(s
zPxE`t{V>pZj;9Bk7`QMUaREgOiu0538K0Kj*8@+8=Zt6AvH>e|Vs3H6z*|KIqVKy?
z{FWOKtMfHrpDXf7A&4Z8cvoFaq>;2hiw@>5U1u<xGt&weT(mGOKLMZ7V{?BgCsqHP
z;(uq`1ZG<+GO%g0;6)50y9S;-$YJ3M6Epk8QWAz5w5*ceZTJ=QQ^{(yCSm}ADo6-S
zRea!8HLdqnLYRRYJ78x6r$*zxcBdSR+8|0F{|DKrZXeAZ%r&F_-XL?m1#>0*iuo?7
zKyz2dc+%zO17%7=fdMWv=RWuo;fy9lX7od5+}^0wml(1tr`42yYfkpZY<d6J1o_BU
zx%gYP)T9IFhJwYlcws+3Lb=CiM%341W&Vw8-7x)&w-|25T-^3>TW@!<_GY?xo$T&w
z<n3(^4+j+f6gCY28^>QU-4dNuFO8Dp82jYCg!W!sngm3=o`H9IFL1vcMg$`W2*xtL
z-DwhxyS#U)Ao#wlam*CLtN@pW$~pNQ9v#T`n}b+~<0;Ye^7suJ{|peu0_1zvuqp+|
zBQe=+_6}Y&GJB*IhSi?!1<D$^xR8lU!Ngx`N*mv!x_lnG4fL3`N+UqJ@*N{D6mZo4
zxfr32oJa7NS~AP}3d<|=v*59?IL=Jxm;tdM7S;5ZA=8|PB+&tjlL^%AMO9uvcJ(T0
z<*{sPCMLGxVEX5J-y*@cIlN|8ulBj5nVop9B)s1QR_=VzRQSHS`=MX{8E$JoaZ_fj
z<U3Zz1aAAh88v%=BH72aaKqsDa2tLyn(q7EIWw$15VwgUN#e)+kLPQ#q`bJr1*pyU
z#0SO-yOapJLDVAwRPq|0C6g}--4uVDqJM7XjNl=_WTOK5=DYF(mUqLnp0sTiT#mHA
zMM0B6Qok06hiyoi*0O*c>L2yjNSv%^2Q2S|X-<3ukmGhY@7v4lAlycRXgdbT&OBVU
zAp`u2a$5LxK3gN#u&#BRmwn9E?<Kx0tJ&gXU2)~HIXnGn7?ARI2?SGaxlHQ@zzOF|
zr$rItoehHY&HV-ZEA^!PV0*8sls#?4EE1kaQ+0t8`g<cv+-c<bs)d%iUO8K>Q}Tjc
z8+8WnMFQT%tWC!{@K7mCHJ<!w$`m@&qWpOUgn{x~+QLG;aueUVGV%|p%SOpt0`u_F
z?AC8vNgW@1xvr#9w0y}A`PiP=nm<6(jcH>b15MU-D~!wVL^%aq@(JF_TqNoHi0}8X
zxISDTe@nkUNKBDLr($G38Zp)1w4`(|@Ww9&sWPWMn+FYifi(dp$hcf+s|zOZk$T10
z4{4430OL!S4%cTR<I83XGhWo8IMgCL``}rXmo>`cW&s-_h$5*w?Nxwc7L0r>&5i$~
zPU2DfdatdZ$JOI%Pw96wIgpd=H7LZK2YbNXLqJeoVh|op1QPx4(A<&NrMC$)L-hn9
z4_7*$Zrht6IeZReu6XUu$wBrjvC{wtE?s~oI@1RRIgD{7>c<w5<TA0ZCD{jmR`DhF
z%f3wG%EB!WN=Nuw>#IReB1KaBre#d~T=6ejb+0>9b>R3C4mWZ{fLG-uv#9JHlit3p
zJ7SrX%XE_Qtj9M+doO%b``CsOw*x#a%p%!AWVdEt@MBTO;oz-+Mf=Lo<SaD`F@fJ(
zG2emp@-b9LR_6t^>(|>?ACl~)VN7|tUV(-^Kzc2<d>U2;N9-`jX3Z!^LpT=<sdnVN
zMIm-vDrTcDOMY<Sd8c|%SlL!nC{txJ$q2k^e){EItqV-U>#asmg|cIUddBfgcVA3)
z_M^n7`J!K90TZJme9LYb!1pA&_@P>V&KWk<<cXcSG0#x5h0Sts-FfFZ4o%}4L_=Nr
z>rs-mw}Fd~0eHws3*3ERP%8e+U<!Ex{&T%aG%$Sut<@SJsYfMhk_qdbd-5A=12rD&
z^yc)~dFc)uENrzZ#o@)?Y-$aeEf~<n$#O_CkpNiN^i83sslasq@IhXiUT1JL*Kzo&
zrF7+*0T-HXV#CwUu)@i8nr?K^D|jrR?NU{o_jd}B@q5f0xzse?{lnIoef@kMZE2a9
z_PTASFv0MeL*gM;;gcGz$chyZPKV%hgp}?%7~h^%9|X*IN5$xafi$aohPAde;QB9-
zf*7twXba<}$k~2X{Cp&}i+!~*8*Rz@Id^y=hoWC(e-}KgWySJ`CxI$2nwU*U3*U@7
zpS*$4eu(A#5G(q-GSY5XiI4(t^Npmj<x4c%Cgns8o-ZiqVVpkc1s+nY=!Q>i>wtSu
zl#T6PWzf_ZVw{{KxWPYQcg<n(@D{^pN{vgVRi!&HC00$8G-}(7!6}H$sTa5Fa^AP+
z{-c(8bmEyxL33{zpD^<7TcsAq3D6Ud&|{8m+8@iAMlMR3&=7U^ZiCKJ2ObvI60V3>
zJ8`;lXc{^8upu*sCPt+=hBbqCDXYxiIN4*n9~rorKD>BcGoGe+AT#fz36%8MCP54w
zxWwI-vHyiNz;-_|IDY(La7UrT8`lT*AD{dOm3tXji`O@IQo9X;!C`CtiN+gh?(Oos
zFHAu7&WRZc>9E)2v7Kc775qo6nuqrim=*5_hX5Ul2pt9Uu%)kWy8Ryf8O@!qd06UK
z(vXLGBpMrQuYX)kq>(>udP)yFJ6jWY*cum~j8`rXHL{P5jsXf`uU<lpyZxt)f8Mib
zCcXPkZFX1bC^dpQ776cY=y1Ra4X&BMl(0(Dcsiwfc6Cr{eC!t;`Ln>&iwwPKZVFTB
z@T9dJ4OgO;EZ~65jNBvxdw|jQ#P-^AVC(LBV7nP8(||`inT?o(T_&LkhX9|#HrP;{
z5k76PMJ7K#qu6!@P-;Rk*Czf<$!R7-k2IUy8{4NR*BlxIwH0<xY=K{y(Uu!!i3WG>
zaYve9-rw!{Yd#7TH2nDw39w(gDsL%Jg1NO=SqX%amd-C71sCs!Mwy{6CouRoP8rzl
zTJ-VaN81F(n-9J({8`|5Y#OIT1SeBUmUbl6HCn*F;8d%|+lpP3_~Y1l0Qs@;=S2iE
zX@gAyz}_g)$QkVNS;CBN-DOF!+cm%SFk#>Kxf=ds_Xyuy06In<O`yA;1(f^ZA%a8D
z%-Q=SXV#KkuP?W5*%%acaL$Q~F7ME`aZ0Og&iCs#g`f_Y1hnSPamMj~SeKO#-Y%Lv
zuUQn6v%~e&`c9oi=dh#K<2K_|2zStK4UdA3EWGN+%O&)>e9g9l<Z`fQ>fxIQkAim*
z&r@56bGF86f99`;9F=!{N!Q+1b{e|e{7z5hjVDbPUatZYPO%!wR|S>mzRua7hLPT^
z9#*r3e>%yI?7Zh1dz*Lj=>^5ZKqIhq2#1f$p4>|)6j}|$|LnQ>gCb$ebvWLox!~aS
zZ8D1P%Lu->5%9|o`)T_R^h5vH@0Xjmr%4Y3e(`T66i$p!u1=7!nLFfXgt{E>`}e@G
z!heU&;e}xLZ2z&U{#fjH3Uzyu^uWxpQjo1v5f2*pZ=9$!>U+0?Gb~{hKUj(FUbES&
zIdJ&=(TA8pa8Mo2j(h?xpzyF96%FEixqHrDRS$1Ev3<D7vQ{lD){yh@!cns~4{vLY
zzxZMJw@!5fLcW!XSN0ajI(S0ahVS#C_i~n%-pA?|cgyGCkM(80w%bRR_vO|PKhWYh
z^9emco}lh+SOj{{twvG?E+zl!f(vvHc%;o1g3?;sU0y+hXO2Fs7*G-}=@*}8%p!@|
zvfi>T`))(ddtX36?FO<v*#)Dbzv=cAt5(?0<DJIpzkhvUWRHF1y~Ny?-KAO_lfSvn
zGBQ)%OsC4(IC)+@HaPON9JC@diNv+=)1K`z4v!|md;M4?SQ0Qny;^-TVi)fp9IQ%D
zkklRU0*{Z8x?+ZsO~kHAa}SJ~{>JHjS)s~{g73xlyESi1%Qmk7#;WV5=6P`kar8TQ
znr`<`98j3@G}6oGuGdH&Et-ld$xxTD!1sV_3wY=SB|kpRLBDn#Eo1yZwgbhld}+Ce
zgCi$_M+|rTNI;kJQ?^m!(sF=d%QNf@hN)<LM$SFm(y`@_zkUt(+D+t$dtO5mD#C%l
zS`tm(`<DD+A*Z}z!dS`XQ?V@P4qfHy62kkNzOmZZH{faXJ5b9Q|IJ0ii<`vzEn0d6
zhSb4bWQ@nh@&t){imsB7-r6=H{dcIwo1oa0slgWjokw6oEWE{QTW0)fYb;ehb|w`s
zGHX^ACN^MY-)VR2o^U}=#Xza<M(Os`JNcijlK4hzj(taCkaB0Z{H@)blM@A<i|k1f
zoTDy>9Ulw2jM}ljCEX$|-@KAIbki|*0qC`!SpZ;*?NshZrFZJvlPV!)VYEtuq;=iL
zZ{O=cgVE#mb@$*<iX*En#|9iJCo2`9D_|qYvE-~fT3*aq36GKucZOqS4Vgx4cJD*9
z+@6BVlTU*8^P``C*k+PeZC)M^gT=H#FY$l^6Zk$@EP3KWryZ7b7qb3Qj;32ea>>UI
z#tt-;>qlpt72WIko1Y!30c7K23z}~9Vbha8_rzZ9u7(bMIO+wxZ|NOkI@SH4KRr$(
zoANxcGSNS)D(^6DE`u(3dq?h*mP`FkZx=OLCGt&6Txb<;%^&01V$^O8{i+1^qqG95
zkXU7C^2nWXrbtCdWnS!gcF7bvaM#nm6tXGcr%x@Mg2rFVxouuLy6AEH$1_@>d=SrD
z523V$nR(xLMKVwKxM*|Mf}dKjS-#V3IjbU61#EH54D4NfwA{XTW&bD=r6*U#-JOS(
z4d1=73c|=hO4Z4#ad7yrfnlrjbq_c-ClD{Y*q+YTGqcBb%nU7E#1YGHjVoeK2N%u-
zMns(zBnLGE7w<)ai=$~t0mIJ6#q#-OB|;`&>14#E#DBj2yqswYa`nI??~jRl-73Nk
zEzqv6fIk<!hpQIge}kv-B`2Z)cq;%eYE&kq*<)og=&g!S%G?h0j8hw^%FFT=y|TK<
zH!3;GL({9Fmb9`4C&PqInZ~C|(QF(Cyr^V0E=6%vz+*)N_}#)O$!H@AR&Um4sXs(x
zNrADaqMm|XIuiCmm8UM0268FHhI^oKoEzv(95HD*1!?vOK<<e>5>@r)?1w+Y8a#A3
z)k%Rgb|nEsNIF0Et{I>vvIN;S`E5tA6v;pQ7lTphegC|E^_LdMmnW{Ta~PnW?a6DZ
z&?kZxdrq{n8;wgWAZ~&0F>INNFdvv)>5AZ_ZuoNJH0)ci>#W5;gOjr@<yX*TpL!<f
zJGc<rw6Obdr4chDn4zr7GiIfQLy<WbW_K*KkeW_@KT47P8jy>>_K|<Gz%kpUYy$#R
zXAjt}2PnESIw`?QLj8wN<PL2?v2GewAM#FjKB2fX)#|<k{DV`Ign^=Y@J}->PGD2+
zTwP8yE36WYtqX|Vp;3*1-kAc8vHf15EGvL?)p)wiqTW@Y^DM~Q-n${H63t8xey0p>
z9-G*c@{6SmK2bk9*ZEte$E*yJHgWXSvuY%3(^|ld0IkDr81{WCnnKHRfTASygyExS
z3PQg<FrNlKQlk<p!F*Qb^*PCU*HoUS$-P7?)WNT;vb^K}0__T5<=_u*(e&G2CUC!E
z-I{l#nc1r+o`fs-#XU*Zz4khs=F2tcbH+06m>d+<YJ#GLyihPM4lWOF9zfG`zs`)y
zRJT`aJn2%+&jjOE#D036AQ|henRI3Yc}#Rt4PR-!5>zkN@{1UK9<*lflVW^?G{5im
zN1zaUH(djE;>gQVi<9QOpj~#K2MP(J>dH3YN9>`VdA110E#=@}wL+z?C-NO_9<ipk
zf?)s6gYkj_wh~UC`biNSj@0V*@wE(xUx8TJ@ihXV={|s@^EAJ|*e<x3JGAaO0|Y&e
z@N@?`Z(xPJ)=(*bjsAp#Vhf&P`Q}!ndkWY6XX%9f+hVWSB^<o*WW^;)C&;>1R<bz*
zD={<bMs_Z%UGaI$0qTVj3|wQ4Oal=NPO97i7+l*paNUR<@ZO+RSy*Ny->msWFd2k2
z{83aH>ZqR+4jR#`x+V&&fZQ))WgfEEqu3eZRZ1g*^80e1BlLGig#h}U_C7jg%ByYd
zY;H0k2>oxO$@@9Y&Y(%_a{DH4xRYcV|Lx|s*vt}V8vc6DUkiO>b*{z*P!Q>MdR=u7
z5+t5Ai9>P53*T#TykzoulEt9mY>JYN;?(0}e5e{cuPnzLo6}TrQt)E<d6_q78}<1a
zyp<^s_uH%dt+fdRKh$HfO)$B05mt8lrLxWPIpHGLit%NzxM>l~Hq<_oVyAz)WB5|-
z;l6*~0la5ZBu=Rr8ROWOSXm{6@vK;fmHjdy3mM8bS5`pxu3Pl)m>L>))V_mamwCG5
zuP*@+YW;zIu1C+LfIPHOv5}?az@Z7ui%iYA%EC0d5Ol6pz<MS}IA^%Bqkq!6J>Py^
z%=!3t$L1GxsaoFfHtMz{cO^m)m90&P4?wM72~|k#k28nn@lKk{`rfYsntwTTEVZdm
zgQW`;tDyC`?8{QlTU`QAXch!k4ZnzH432gfap$)=&sF1j$lE9Ii3t*^b2JE{xH69%
zI8FhHneRLIik<`Qr%_$!RekC#&BXT9*kZA&L;U>#J5>)Q;n>vpD{4IRd6JG4G&|;v
zS~zIUdqNlP{Wi63Mf-}{_Q;L|JHPOb#xEYj-*S`2KpHbuZoxB*jDNO~LTp}V1})o4
z9c#L~FlYPJVmZ}+4^?~8ykvtP8sUVRnntoVA)}@nFP~%+d&<yq=QA|6@|Yn-AN;<^
zi|^k3w7?Q5bbQ^|mdXK1%J^55Vb$h1T3g?wT<Xt>7sXac8^~kly%LCC4w$(-3`!Ez
zuhQg?)tE)evMo3n=Qbsa9V0v4qO#F+$=6&htn3_`+&BD2I)*v%_h?6N5Y6!%x-T>J
zF8EEsMIb!V%}+%^eRzMm^jj|VtO_AMNxs&LmZ2-mn`1ebcjwS}TO;T=yOU;l-(gMD
zw5T5PEEJU5Hpn#yc2J(CW_;EbXuwgDQBILGlRJM5#T~}VLfpa6p<gl<alBormUp8A
zvjV2Lp_5(zAt?GX+Dn%(0hZGO%l*Zk&tZVZ1WEC$p#!V1bysuGp9!A2NisJYRSs;L
zEqt&e=0uwZBXAOo7@JLqzrcms&lEY!)<WE|iP~Fe^3!!dFhL7xOTQ(3*Xl;WnGSPy
z#Xq4xQ5OEQHRgD;2P0Sn=c<ED!mz}9hLgQ$`Pff+=RZae`^38ndXy~@tC6fEbShBn
zeZjIu<O`31hsJN9>2f%iS_W1;&+TtNP^2PT4zcC#9TjSzlf<h<oVBTj%xe+8f!L`#
zb%#ZI_b$CTJQ!uT#pW2TO=YsK)Zk8RPcwz+>s6s56emy7N16p^f!{?W1I`<Ct*T9o
z(&DsW?D*kt&<rj&JIHqD_%k|q)mH?a&|a0y1JcV@4+)Qz)UdSAc))r<&jg6i@#~Hm
zL51X)Um$xEo<a-_k>xtV&tnhPK@}%=Vl^C9d1<Z{4Xsnw0iJiCm055ZO_zSnrE39l
zNZg^RQNRb&U&P6@zJpH8<xj58Pdl(=YKdxTI)64?FCYBMp=uapTS5Z^anWrWKK3KJ
zSXpQQ4KK0c+D0Lxl!Px>1rKtj$T=zZkM-d{SqC-vSDm2+{Ylra+TxLd0$MyaV`4|E
zB3YZ0X`smq((|D;c*hdAzz%-?fOCm_>mGT~fct}uP=+~g@T?=QP?bk_3dXUktD|o8
zpO4nyS<}nUhSrHzVKsgz3750{pP?ucTikiDI&clLRe4=gY;&G1l()oQt6SR8^-J02
z+K1j<@Y0@rK<re+<h$>&Ip!_z^VaCbp8)^!;|?SA2ctOh=Ckij;G}h+8~0WkHRF^*
zjte{HPKZFW+#bq1Rwe%Iw?g<~?Kw2Nqr7*KrUcwU-#>vH=)56nW&C(wHbVD=%$q{&
zPW)?@lCZnfpfCo+_hPWL=<9W(We9o7dgN7D2d-no911bC?W&L6NGh6X#v8(t{tR_6
z0PX87_%XV0l7kr8ss{s!;1Bb!H+PZ4N){0RT<i#vt=rFBRsp~4%TOX@^T%^^kPSK^
z0;HEv=O)bI#Ru7Xjy_Akl1_v==z-ZB_%UVt`#B2{u))dy12*&wH9lzrx@&;+c1#eL
z4gRbP%&)^a`=_Q90N8x5xear8_CdDZL(iIZIe2oCq(g2F<<bn<#_<;mGXS|7o5U`0
z6uU2lVtn$7aLu{B2z*?xu>A3g26C}M%vwkj|K8+Kr9mC&As;KL<-gA!24~9VOTV!y
z&jz)4_Ck(r)x=+D_OFp9;(G9tnyxv#P?m1gD_3?5XqJDm9P~4=axx?aFLt4Ef3@pb
zTHG-=khueV7IVBjNmvc(uTfh#Y>O&DS|7OAI#`FkvF9!nVq9Cdp955(BOJ{Z#>}PY
zZ(;Sy85+1C(VHoI_pmRGF%kM1B#(fjF%$%n*`qaijm}JTVvf%6D8C@fHGkUf-mfIQ
z_8X}84{RM1v;qt44#(!yC0S(x??DZA@=HR~d1nrQ)V!x*_?oJ$Cl@BY$`vu8G>n}X
z_~+$2sD=2RcV_WFz^%UE^CL^>>?K5!mQ6ffdjrkxEVot?0+k#wsUH4o@Qr;=UCh}(
zU^8&ClMrfpTb_qdh-cemkH1}R|I*v0%Ijx?=<kP)Izu_=?>~<vIN7xP_taL<q2#Hl
z#~-Y{g-oq?s3!l7y9((untWOW<{vf!h#x-d3Fb$*buCRvIP8At(uaoUF`#Wl+i=n7
zD<h2Eh+H2Bf|!m;_Vx}zv_i|atU$mv;9spdjHe|UMG6WYZvW}OEJVaMq8mekS22fD
zQ3jJ#twAG@n=aAitbI12FF$nMNE3JO>6IA|3#gl+UCXdE%&+#;rTEpnJY%NKtJ3)#
zT(E+5o*akOhzGvKgubQ<fp7R;8#p~@T^P@IN2w52`b1M7ZR5Bu+eRb5Z+~Qn3FN3a
z%i!hJZZtX95(H)F@&KA6ihN=<kKOhfQplywtoX);LKL9gm**_nb_Do;cM@s}8mTLV
z^(mOm@0&oc94XfXgha$q&YfAkiV1dS1CE%_2+=huHs{wTX+p{T7;o_NA9~r7$Bk5N
zWTe9f;6wJEkll}rRtsM|+?!gtu~Do-==tm2^BEU!HHBEDauFC-HepE#5|<Q|o-j@E
zz7Gw<7`cjscdBazuWfeBTJalPg<?0qNM*Kvh~(_Ht7v9(d%q!b4-H>@8vI13T<ow!
z`ptVra;_Uep|PHjjWbPiHP6DHln-fwE)VBF>vO8jYH%s?UZjK9uY-d4^`lm~X)~hv
zCIyWOE^>b57s5ZZ?HZc-zFlO9@#ZA%kPU9N)!}$(2QTKZK@&6&r(kcj2REd;Z_Z=X
zwz%U6$l*($!y_1K-3Grz0O<`rRQf8Ycs(f6l#7=9py<bTkaGuRiXk^<*!?;ejmj=c
zeD&qjh|jhgXy)s7Ly)TqQLjkg^AnpO+dVPyG_n`)mb!+RyP`yXi!FiFB4Gk>brIa=
z*aEUv@q+FD9kLk`?~7p|qTVIbJ3Lf~^`4f&5{@5D^HggBw(Izy<F;F9d3Jd=P^BrT
z#lkT~^WER<DH4opoi!v6^{#)GK3KPFA9421WixAqUq%ZmN*d<$&Ed(Mx*3ge;Fc^#
zQ}@Ia8p(Ii9C2dCwMO!acPoB_uZ2|l`oCc}EfHQ=I}0nzJ1$lx^s$Y|h8%dQoXtba
zN0>l{T-n~sR{kDh2RY9UYe0LA64xf4RU-5m$(@@GK@D77qihXQj~YZZH-mCB`SY~H
zS<zEbffeRhhf@EJ**4;q`ZY>Ia;yY2>IA*7fc|*RS|;<!u%8;Bt$pzKfMl$L>HYv`
zo3XNbJFq+UNfH#uv-3^i8c6fdUZIo87IFJ%j+U^Q>5F{sR6M}#RswP7lPA>h&n5{s
z*MN&|auH|T-eEJ;GLKaFHb<ND!9#RaZ8dB=r59)vG^*vka&OjHeaK3{E0U7~8WJoL
zHhm;ZeW4arnQMl9@vGbnzJc~`fD;lZTBZ$puwg13em)E_N>UMG9Fz%EL#{3d7i-tW
z#__*CJ}8kGN-h1guGM93+dmzyS(CpKvJ_=h&x<v^(O5%1QVUmH74TyOXzpH)TxtWg
z2&G%;LB)+;gN;GU?dR4d1-l$D`i<gkH1kNRX6(uv&>O6bDx?q_(`14|v{!||F+1wM
zJ|?fa+9h^vv3d~p!2aK3K--pmjKhjKeJLS^CaRztpNwh=x;r+iCrQRIadD)A4)H_J
zj(s%xn*=b}rFba`zL4g^o;nN{vq0QxX&XlorF!Jy37Y&63*^|BpyVIh*za(*5DHXH
zM@@bg9$s$$=;f8_!_RFBxKlc8o97ZvUMlgIalJlh0rvweNl1_|nG(;*G&Iwe3CflH
zn8{{PbI;V!y;rJ(pWpj;=u!@O-Z9=ss*=@>4UjDmR?HC%o=VeFj$@KtmjiKBvOd-D
zYin}#zULcfHhNo=9)~=R=RGsVcDhn(o<Q=^RZ!e`j8lp_Pen<{&%y0r8CMsbX>+Z-
zJ`;6oyq6$hG<oC@md~+urTKzIl!U8-DoTy$U1M)uV*m8D8eXc}cCBvg-LhJ>0pNYe
zTgzS_qAIzDs`9Fg<c<EI{v?H+je~ilI|JR?oU}O75?AV=>8l{rxAqzFFbEa1myt{Q
zmmP^+`L~TbEkj#4g2r3&oUtS_sh~l8vnkV;);t6Q_B|-mi@{%50q8-lfGwp906oWe
zd@Jm$W0ab^fS%2e?Zo68tOF?TPI;m0WoZnb&;Immz^G(Jd>^7wKA*XXH0gw$DSwYC
z5nNN{jx^2III$Y<radz`-#N;(*W%KHqTj?{q(~T|m0lRl?OCg#jwA^%33yE+d<fQo
z(N~eehnhk<yXIfdn4!LMAI;Z<AUcNb-HGkq52Rc27*G&fP$s@8)AOTw4G2#H0l1W0
zz3>mr%r0&z)!~%8=8$xt&3kDT+Cn7mRy*$t=o7WC8E*`yybta4m_KPWgZr*U97PMi
zj#fKX1XZ~q%M1#*EWrYlhIb4ez&aF8p>${6@E>#Rexr0(mA9a+ILIyM`13x>G7#%;
zOp-8h%EGU*Xo%|tO23%v|I||Ft)3$O`ljJ-l@lp-d}J@*-krl+mQh@*mJ`M@Nf>Sd
z&jd-5=r3x#hdTyAzDeHHV%uH?3C;zvGNw-Xk|C_a_k)q!#}YgwCqA^n6p3F7`@)bi
zMbZL;da;VxgS~Q)w}7juyqcf5>C*#u!_(d()|BaxX9KAO7F|6a|M(tCBX$dTa0W&3
zIjv-r+-pnq<lxK5<@S#k{M9vdZXfJErG&1$LUYNv$3IS-Xu%jpoUKD+Xq<`zW{`0e
zo)bYHeK|G&WYZwIx@Feh-`JhRc1t(47QwLR2=PPX74i}3$vi`N6ufNowU~9aXGX9g
zcz$nEUmMuh{^aU6vwr*@X%0qO?EUB4s3-5jhx*kCL|h6xai{^!_2rCXWk2|C6%#AF
zti!7yaKr(okJk5|I=vP18`EAedgWg5bDC3qb9weovehS=4LLZ#`!M`RvT<R{70Vo)
zGwc7+_3rUdZ{Pp;$Ss5;l_E^KI1wtj8=6xpgi2Cjrc$ZIxL*cC<CIg9kxJ!OB9$_v
z+|4M(=t7a)jmv0E?qghrF@Ec%&gb)fe;(i8pRd<zuf5k^d+q(&d+oKJYrUtzNUy{)
z%5UKtuVu{>4mklzTVMm4iDRW#O$A_u%wYEjA7Yk!SgcURr1Kn1aZ{M$*uD|Z%6<Pf
z7me*&P;-LhZ1##0;Lfvf=sA9YTcEV?4QAq3&g~n+I<upF0ndMnXzqI1V-bblOW^fg
zK)cEbQd?M%1<CwqfqR}j@OcsVRL{<d)5CS_ZP?X*s-=I~Qd?%|rUcv-r?paCVbT-7
zYiolPSj_z$eMW$~IA&8bwQ7Fa*OWQa`#u6jj(x?gHYzkz4};8EttrXS1?|HSBtP{B
zOTF$7mV+G9#MTq)*}HE1YGUqGi`}xjzjfpJDG!Q#@y<ZV0wjqQ_K0DHLt{40Qxc+6
zzNG`d8%V$6RvC3K>)!@o%iQj`7ZQOfved;w9o8HAl@9A>K1srN?7cwR8J{2`V}mCm
zdl;vSvRnnD>^jIG7A!<BjBbR`Xvp_GJUvV3m86#YOr$!uc2pF{e-lK#6%o<4{g+Cb
zE1Z734yeFg41R#6!=295^8FL3_?`~Cm&UK1H-lg4uQ{=DG`hS!>pW!TPJXeRC4WsY
zMPJG4<h7Sk0pUA&bh`~(x6Jf%vu1bOzXSwwIrH{rNWpW2EQm&rK4x}BOny+IgeUnJ
z9enMtbS$;hRx$4yFKh8?;(aW7G}z4svR~dtFZi^f9oSPYs?#Gm&Nw=&>}FZXv$V2=
z97kW<C97`#QmmYiRV-CKTS)FzxEuxyp!5Wnokz>LKg!bPYPHf!MPeI6^p?!*qAXBw
zSFFsXxM{&za8=|Y#g!+Q$LEGkH<?kN@pW_NzD>HML^q?sbvG%^Iy32{0tB@Tx@}%e
zVH;ejB$?<$sedx~Jz}y>`}_y(L5sltSpTsp(Xr#R-xp_mFCZ;fXn{$%MQdJeruW24
zh~r!^52j3amQuSyt(-#LI<s>x_{!mkC_@|O;%Hf!OLJ+?S#Yv<$zqD&hrGUPOY+ly
zbs*zedG3f~bFs1Hs3|Hei?FC_8fs#p%;ZCNAvJG<-lh7fJ)YK-;6J$)_2ZT4n)2K_
zGo&|9w5ZS<RhLwEqqR|e4MmGfnF5|%K4G;P($pN`BvmSz<sh@rjftP%%)k?&OV2*Y
z3}OPyj<CBwOFVG<y@>VtQ-W!lNT%a0^Q&eqdKA*040$Yky9$;ruw9MD&HYSuK73p0
zd&Ez}=XGCIWOt_i9>sUr=+Ov=4~>0!PO~~=t#ub)z(G#qcYDl`@w%L69|nI~1Wqcg
ziIV%RCkoTBtlYna<QV3;bQh#{9$&$FZACMpsn1LpGSXM_b9V|KIfht%jbzh8*iKIU
zfr06zv$4x|O8#Cb{waeM)b2hcQhU)rz2p#d#nTD-z1QsxVX?;n*1!@c<~BD63(a(s
zEmccfFK6zP6YeCc)EZAjX1+m(MCgJ`!!nozw@EVLFAH2hlFRcL!4_{t={K^g(eyBd
zWlzSK5*It1^(vk{FMmFw@9ZBcGOz{i|8^7Ce21WDQEzJidCfZreXgww=v>9ZUlSbM
z;n1?ElmAbmF*Ep0-24HVW^;I+-CcD-a5E9VtMqZr!i5Xt@)6|la|!Y-MN}No=~(Eo
z&a=6!x+Pm}V05nXwm<K2hGk^E9i-Gc!fCFoNF6@D8o+mj>UIXC_P%Ub2j-@rqZ!Ba
zUWEU!8PP&j{Z=Ank_7)BvxY5;9hL8Bb)oJBMDBQ_Rs7-c4UF`#$%dSZ&9+*}B{$8a
zckchC-OqanGIz2O$&Ow!3!9kSNwJLQJVO(#xn+IU6#7_iR`a8i)U3cC*Ss}RCpj*Q
zzqBj#7pv1Cv$PFea%6XOc?pAX_H{;0y)w&vYB)9tSAVPGO0>Rnz-E!VR{ztAcF<xg
zdSsV*@Nu(Cnw(+Bn|=cU-d579SZ5b@!OSCfVEdA-$-Ebf>qQmw$R~Sb{@}%mN+tQp
z_jL!yi_%{|tnrKvcTI?IE!4vicePL5GOTm`tSSb{3jbwI=U6H%88&n&Z=M{t$i!_m
ztIQHk^cLruX~aP*jp_Ye`(10BL{E_ZmtsvS@fXEAvY`3&im8x~*%5!R^va>U`}8u?
zE@PDahKRw%J=s_hw)s&lBnkd=epB&R6SxWH<%f_AOKL2J&9K6^IYqeA;Oyq{Y7rle
z-}Os?>q$=*Tu<$3Ml(|y%NqIpyxf(n`9e;GGod12)SlWGC)&OH_u?dlIQ-ahjNZh-
zv7fM;p4_d56<WkuR!Gkl&BW-M@e-7N5wUNJcANi81kvDyfMLG;EO<6|46I?zkxRET
z<Tvr_eVfJj4>YJ<DGn7OgIQt0L{-9Cl*dilB(iS;;AQe!9NYqu+PiwyncWyH&GN}0
zF}x-wLWjE`P-nxw*p6Qpi}Z=zJpSQ-`}DU{bhu+ecFj`9eF*jKK5*Hl%L^p<!I!Z#
zJ`(5{tr5wrPG^eGdkP}O`PKpDeyEgvzZX<2xW|O(z%`DS^9?4fi_~brQHLZz`Q1RD
zFPMUJ+V|ArDrnX8|FkNG&8_K)<CS$MxtWmESxne0cwk98vOy#IB&E5sxbn${5;OV@
zXSpav>t74;#w{uc;tl4nySr!I#y;k*ja<Q!PZU_i(^KzHw+ei}jNBcPk>ro77Bh32
z7l)2hD&n*K_t1$UL-)Hup)o^!1AhV?X=$JWL5>(Zi%kqsD^j@R$n?+GNh6({$zo4b
zio@?Np6o<N;#nM#w_6(YqSJ%=XW&ZYCJSyhrxi*~81z<C=3KPEKY_sLtJjORoh-I2
z=*k!(i}+ml&z4hpAG@>NOu&b9LE!H=W|1D>t{>odb)nF=T0AsIiMpsfoI@f$YyMwU
zn;Aw1GeWh<11v&(r=35k1g+N=>r!!d0aT7KidoWq|Mwq63Ixy&SOW5o6G$q8Jk1)y
z&B=Wf`rYd{A5G7v$Z$95{jlgPYt(M-L1icXhvszI&}B(2<7ItuSm7z%5BAL9MA8ei
zUPoMV`Q4d-(K_nIc+r&Ovu%i>a?8nnxX5O4zP>SUAVjMdvP0aVg==k!GyTuw0jSLi
zSEg<hvW>&(NW~9tk~GfYy<Rj)lEKk(3^yA%);YD7AkB4FJQ%r@J_8=t#Y*~Vb)EdC
zQNJjC8+_Pf3b>vizICHncu8iQ6xVs;3kOY_>eE$ZO`362l?qa!bYR;Llx8Ar3T{%C
zE-HVQEnSYZ8m4;oL-t9*n54HH*TKr-7-hQU=4kodpUC87>Pi|X!kUB_ND*%Gu(J_k
zNYtK*R7HIs)pA@J+jZW7HgzhkvBIo^<g&JV|8Kd9BU4#|)BGm5Gg{EUc9}_{<@|mu
z>07Lc{qzWL){79O|65B}BAlya0_R?UOnkai4H!Dnk{>>|OHv}VNMp2gTl^MhWL@#{
z6iu=Dy`-Mtpd;N_oHuU{H;hKhM??!I#ja!SN6xpv-5onF^h8Ai@Z;UC+<o{z`B}x8
zeiM_66>`TFYbI*sN!z+180ephlHm7?#a;fZczo4j@!^Fs4^Y?s#%%k6VK8qvP!__4
z6Nq!kSFc?NLyJTFd?!rnmJRcN%{+#&4WAm=T%p4ljV=F^L3rGK+C-O;9MJv=m3{M<
z__dL>$IzPo2aU6eMODW{*jt|Gj$no7mFsTxMOGYt9WYWyWgd|L+5ggnONi{PXD^T0
zQPGj}EROqZnGmpu81%Y#_W&>6XrM4w#C~JMFk+lOf(GmM#YED2K>_T7R`Lhg_UR2q
z;1|(6wP`d@B$&7@p3{|zqslJx(dBq9ny8n+R6m)_Q|U>sAPXklv*kGsa2>|+AjJOk
zXBDHFS)@lxTzCFwPdCl)nel)C^@(pB{n>;^;4R~C<S{7)0NwN>#i}B@+W*PREz-sS
zDXvj{ibY0xtpxw$25N_&4$k~s=@n7wX|>Aj;HHE))`)vb@?&8tF8h&4+Q?hVHHuHM
zc!&q*Ifq01PRS9k!F&GUe3)YAP&vPq{+H@x;ibypUKn2>{BgBWk{4zqKV`wtj*JZ_
z>80tbeso&_y9AmoGwdt{7rjUU+fpg{YvrC0)Wr5OmEe~o3;6zz+e`NJZ(7ow03w&*
z7#v*`xzlXw0W}yQqX_fSFA!&+!m3Z#Pi?3<?7bRQxDWr|RknkFp*RFIr3U|8#me^L
zvg_~J55{Q~Nune(sTloz)Hl+If9K~0z02Sv&wtLT;{Ov2flLg&L%o*fk#zy*EgehO
zpw8X-r6e+oN@7b_G+cP$Jq-0G%jYcR9-MnhRg%B2JDRSgq!#7(djL_$0G9D=AMRk_
zG3RE_dHWeN7K#tts9(dnoU?3a@c$IctwD;NJWR=U_z_eS9o};G=kR-fX&;m!^afc+
z#F5$9o`sjb4cB7Z8YTVXc150zXgTt8^u52<|0!nnH(uJEY#yPjblikdBY5GR^-;X?
z@LObSu5?laSpejElKwhLv5c(d<-6KZEHf)bLNvjP?JuG%q^uV=8Tx~?`T9~W?`cOg
zI&xo>=-8ndWHu>pS)5Jl=MKT@#MxDn>}6%)r#D%6{`d-Gl*5_DL&KXTh%7NL^)3rR
zG>K)$*D+%DZ$No6x{xzS^kO&4cH^a0!T_(ql2pvQx;D50?ckt-YF<%+7*51s5)#)2
zU8Suwl?<KTS!d=*$!1GOeT>B+6_6JdrEE77DiE9iMd@q3-gVq1lPwl?dpB}^)%!J=
zZW)BjSI`SJ?Pv$}8h;hq*XPSn=f5Jh58J%OS(QHEd9peEC{u~WX`I==XQ+Uuzhoz`
z4tgmKIksWV(457!OscTTK#r@^ojD^mmdj8b|KNzAtx=1M`rK}&3`BCgr|%Z>pEh`m
zJFRUy#KDSIx<fO|8f5a2jls$Efv}T~@#-MUgW+r1rw<Y{QDaAV4f>aO0_yK(PCb$4
zI@I5?xJvE&{KHya9yJB6Y@(zs7$8GFw;R7K0(kfXUsI);s0NAFK}`G6m<3Nn4TEfG
zs|_b-y3h{kRZ6E0i4@;rWqCl>I(#&;FgbGHe_79Htl5g%`jnNWsfU@1U6id2Z4D67
zfaoo%^3~0vv|=7h@6<RFAi}}E>9|R_G7DmZZ{_eUkM~V)7b1|&eD6Qyxx6*YP@lGh
z4qvr#5SWUUsKr!}^<wNWG-zipv{TgmTJulLAS5OS`-C)2?OL>X#1c_dflOD}p$13V
zDr7!TyJb!}#uMbYJdtIn{dyszQr7h|r+(E%_y?3Boen74VtN)*91iXV(h=t|)%;P1
z=a#bE_?ms{@O85o!J;oqGYo?$vv&zZ!!Xg2YhWmqP{vm~K6||4?WdlbL@ykN-Od{+
zF{UCC&=@Wf)wmQFvB%nBycAK=PBI}@7DL<2X!OuS`KZ0gafsy9x}_owx{RfQt&sBw
zs!QzdWEb-?^RJ?t``~?(pE-kY%{*dk2})D3TwqQ~lZD(lSh+HB{7x03zzbB;4b>e^
zZcf*0@W-x0bb#I=a}H0j6zC6f+@Zp(j(K(gZ~uXPh*0&Wm$ZH9BftRvgbHt$p(1Xk
zErkj(a&!H-op6zE5g-yZp;h)3td2wcCeHZ>6ofx~Yx}vP?;xoXROM6EQhNB@WxS#w
zgrd!rS(LmPPgg7dVGUk9be18G%I)Ew>95uMgJu4TNE!4s&d7hJ@(Mn^6Gz?I$OzpH
zj2J&~^rja*tVxGCS1FGA?!*TqP>+W<pwm7(sa>R;jf_UN4k~Xewr)KlbCC+-+>2=w
zIQj(xkKQ6tw*lfw0Vb~8KvO#bJP&y1Wl&q}C=>qxyFR<A-6XaTC0pJFb;66BvgqQ!
zo+v(T1~JygSs&2OtmbvF?5zFzw1^4ekd-D-8KS8-2EMfu0Q#dlMa*O|NFgRbdL(!X
zSpQobHDgVgh(c=Lm)%YB*hR^XcS1!;{%66%#wZ_q0^)>5+k|YI@8W9buPl{B*)LK;
z&-PP$r-XpXzwdWVzn^vC`)#D=f1jUjWpw_di_8M!Cyu^h^N?p|1A}ja$nw9Q|L=Er
ze&*<hly_b%|NsA-boeOP)E{0$T0KntF*W;(tINpqQR)EltjkD0#+E_)k!SyTcvuwW
znt+C9IDP!bb8J(z0KoNRO|6QG<dG!wDSC*i_x=AoTLFp_@?9eJS$jJmh@%0{3Wj%A
zw0+ZJ3kQ1Ak2zRMTiuc8LM-i$f!m#37O2WeKp|3u39iih;7w3RbrS)437G>r#K6T?
zO)g_c>;n{#iel|shx>umcr;rdSbb=fJv7CIzJSE9q9IBO3UvNkKoR=(&^mhrDUiDt
zDFFAAnU29>d=#pAJ%f+v>AA+u<rNXAsE>f+qyZ}Pit}xerT%g`zlB{aND8J7S)i7r
z9Hov;O+h<*DgF)!*|(fUvK#=LS>$|Di-2%`L16pq#qmHbf*$fh%w!r7$dS|!?H@rP
z$^dc=JG3I${-Eq%IEEs;I0F!lCSzea>&r7oBJx7%*9)%4_lHi|yhZl+Q2YUQWFzB$
zUOXNtVl+DZB?Xo3g}|h9Uverc!ckGNzz|q|m-?M+_^%f;I{)_#6lv6^AvB)9Xar9|
zTGW}v=CX7dZr30sQ6vP~*kw;mjerD!1qgba$kvG2l-kx__Ny~GSYaGG#_<2~A}k}g
zetzO?H45blE^Bwt3vgwdY(JbDK3yK(g>^@va@l7nbDrOm)-&i3I`h~$Ts~rYD5T39
z`DDM?)|Wnb9T6Ncy~CW)iAF`eUh3zK7(Umw@t%$5j;38<zfciF<*mlnfg3j#s>e-s
zPIfkql?O(n7U6}~fjJnunL{h1g(;^MdH;c`JoN#bCGeNf3*gXhmpwBg7%>r+2SS?&
z9MSLcPb<vmVK*!ZovTq%@1f15TzTT!wtx$xb)#v0^)5yds6{Ly#2$=vy=<b4Ju~q=
zP6UOZAi*vH;wTdBhdcSeO64Lej(}t<`7r9&7u<N~^#6PTHMFBdLa2Zpb#{b5az3={
zB^HGOwGu$+wjv^yi0Sa@SLTFP=zr5vKawJA=Vj>TL}w$n{0wyS$YKqmD~V0P^}!Aw
zC+^5DK^=`lvmqAv@PHFjm5H&dcQIIsI$?4K3p-E%nOJH1KDgf5p>g5}QWPc<<PthO
zu!4!fW4z>D4WywcIR!6fa^Rt3_;mQ>D~wOmpQxz*nIr}uf=ZEw=td5GqRz6SsG~Q2
zQ{QIJ<ILmaT@B?>Ck%d3XE;X%hmG#AAaw3rlp;xiweu=YyleDz<5c-=Na74G5=ey`
zi5o-cMfU9zcjUxTM*$H~6DxOXps9Pl%haph#dHM<frd*5b~2o!A+{9Q89#xF3Oo!r
zah8@y(Qn-tya{lQQAV9u^Sh|y-_zlJP?Yb3igE&}Er+)4S9VQaZsb*}R*RyZ_c&4J
zk{Hbzj7!TaOv~AGk2#mZmMujcjYhK}71XVPmAx3Ip`Cn($39f0w3rE~(StqIRipf8
zFhX!hLNs(D8ZCJtMXzRll?jTnj=={gVuM*$2y?`X*qtUSiqeI@6;kBZk(szO%@d8H
z(`#3we9n_o)S)wv466tM<|4^z#eKyv19PPPtVl%2e|^xU$B3wQNk_iJ-xXE)TFQ?G
z10L7AY~cl4p@mzCsS$@XDV7Cw0K$TlEizp!>w6Sc33hIzEMy8p<-tM@P*~rN>LTzc
zK7dAvJPjzZR6iDRuFlEIpo)#Li&Y>PrG^0gsL8mb;jzqbVYvzF59kUS9^qGdVm-DF
zq=BSHLsG9=fDn+304+}-M*+W8%I^WAU8%aqVI)MN(A=lyqzFohO$h9RK406Sgdm<n
zf`AE-3M5TKRqi3Dz{G_d79uFP=?GsBEp(F0+eK!mk@Gp6t7WpwP{rohIwL6KSBPF%
zgj%40hU@`)qIhUh!6@Ex2gWxkK?G&{$0EI!rZg7<Sx{(b1rnM)<AINWCX;>v=C>$n
zFGvFv?zS$rtEXdbv9>>stYBReKrZqF{Tr}C1TmJy*YOkn!P=QBhZRz19Y^ud=ew|2
zL5jO?kUfd;-Zf%i9ziYD|AQr1$GBt)F4gPr*+Q^v#P_LpS?;2XIt(yzfi}?s=k3mE
zA$T~Xi=x(%Q!JsGY_JTp%@p1nlq>(am{jTH@Aumn=~`xE9~P4&0i%m76zN@erq6`N
z!(Dr{gLecg13C(S9}u~H5n68%l6?Pe3W&{go(yo}>Ji?9>z%L5ppH6zMt-T{UeMs<
zbqqX&*g+<M8v1U?i7O4*UDuH4<I4SFCLq{v+mJi+p6o&k-#43=A^Ak1zQ1Y!fhfKR
z32sL{)?k3p9_C`Zj<Vt{3-}41_NP!MtjKFYARHBz7x+YpM1frx+JfyD;pceaV(q7q
z+MhI<F;uPzY9$RV{W{MtLp|TK$StBq`dDD*=UQ3r3k0M)Jpwne-Z`xXRe3y3lAopl
z%mWDbfya>)bshNWqdwIT5`eGmqGZ7daFRluut3_sWwM$TMuZz|%lW)1k6epeB2j^h
zjGWy^QQyoZErM=WEi&T&oDnR+7ivV#T8qbb^tei(R;@$&rHV|AduYhZ7$^sc;M9<q
z85r<{#Wxa=2Ua6eXaW@Ma}uaKXa+z)T{3+{hRbDy3Hyz7NPn~RI1EVLEjTi}Yo(Pm
zbC#i8)6oF)B>8ih4BRCn;<1+E_QTYugAB0W`oa+4FjOM9s8k2C2n9+=@PBATPOe#5
z-!bvG1d=F84|$Euk05e*C<sx1I|FVqKE^)@`9bs8fh-r{5N~K>^K*&v+NIno3@slv
zDX6V_Sehx8w2_>$1L;#V8lQ@$PfYVrZA<-nAIor?(+_YzRm7i1b(f0q0njLwzA*pE
z8h2Rf%ZYOo!e&Iu`=7H2fwq=nvdGu;Qm7T0N1ZTRte8EjZY7)!<6ym<oRq$Fch2<=
zQU_F61d9i(dvogFP?b(n+$KPnh>YBVc^)TbqG;?)X*Ty?h*m}wZ&_H*?*&*1N6An(
zT&1r&XjcNA-)~TF-upxX$x)$aPk~MO7X*-g2+dH^WDqb?Tt@&ihtg%y<xi0;gg$=c
zaDXtngO1tbFU~K+<9J_o$$6r>Z;CC}4F++thTdlx<BL8N`mgTT|6A|5XXwbeoLDvD
z7hhSFD+P^DLDK`f&{QZ5DR5Ck2M@wQ1WDF2c%I?_8jxarT@C=Pk)h*AaUrH35|kXb
zTfrKQ^!=(YZ<Z$#HK@P>XqzH?71sMuks4TWqEyBBZO}zF)*=*?<MB2J3Ss8GlRRdG
z0fSo2{8<RVx3Cw@Nrj|@$?~g^sb#;DLbanXO+6_|Z1J^)dW`nPENt1E7|oj)go>ry
zrx0hQAMXa~#_r2Y@bBPVCcmtg_d<1_65|8*3ZzhcQMZD1Mjpfc0#e*V(L*XbPYE87
zG5*;(*gKUz|40KtR=$HjHuYtf0}vk95`H4iu7O@Ni7Q!(Fu^@E%*cXv1xPv;^<Ijb
z^{cC3jE!H93<kg>*+Mt#*03<MOKw1<rZ@(!1B~WBlxC|DFG4af4Mq~e>N4(mgw@2)
zSfTF{Coz82;u-)+h5oHjmOH9>fQn{L$qc3u2l8PQY_V{XY+Md9T*D%!lpsjj7%@Ho
zufUXi0gnFhiU<P`nWe4B3a*=Rfl(>BD9ugRg!HtLI@~yV?#RO!wRZR+F6G{q;+knL
z<64A@#0*Pu?=LQ__oNnI!@zlg`?=(SY&3Ir@TVGas014SP=KCpeooy<VTP)*^jDRr
zc^Im|4VXy4Jvb+#Dt*b}U};YSO@o`D571R_$P=N#fP_M$sX72UD86>mf)S~{6J`et
zAqdl~9YMz5&-S7$SVUeULYye958eC4_y8eNktiNYFOPbJ%xGP4*l^X`0D(UxTT)aV
zLZv?QA(d#6@Y#PgV`<_<na=sGor?`y!hZN{P5WOU6T$c^2>M(i#@F<a=H3VtiFvVR
z@y}{cp~7a|FC+45xu;v@No49Kkpbb2Bqq0<m7Ze6Xso&f`wZZM91dU{1&v~%&BalD
z|NBNC!X1}jNsCLMu@aW1ixsvWBbO6gD}6a=rXbcPojCRtq<0mKPeL#3r|d#fh33Vh
z@vxKcU5o89(d{laSp0+4yq1Km*k-Koy>+xX1`Wq(m}To3NgEk-Q;3}RmN6dLfgP!T
z4(s3_tdD@Qnc7nX%MBn-qfm1*E}dX9P`_)*2+J1V5i;?zcysehwe%i<&9f*MiIP!3
zDB!4m4$_RGrWT*#Q?@c1*OT!`U+l@@PGo@smIT2ABx5BcogNg*0TMekR>jBOiTIzB
zJ+6l#`a05k*j*l}Qv26;Dehc)V}E1GmfzjFjgH(;nVt{O)lp!@z{DALkGH4*2F}aF
z&di=H$S(kA(t7HANUrz9$Bd_ymL-_xLgD?k8np-_q@U7YIB#U6-!);(U9np5?)lk^
zrA<bAs)vpB{E{J5f9f+@eTA-T3bKQ$rSGQwi4}eVB*Lw(#l_(i!u(J}jasOmC~_K9
zf~t;dF=B#boQ<piyOsx^f)Ta+_36GLBd6e$<M4{O)Q!8z0&D_(LF9Ek=4T5m4Erd0
zHWW)uM%iVVW<!9&oKt`=KaeHE8u>!c+e0D5rapU9K)weEaSod!Mnp6XQ9e%O@PlN*
zN^q}qDK4%h3!3WT%Lv;5<>U76m(9RuD}=tsYefvvV&IF{XV7m4xIW*&nEP8sNeL|f
zRzlw1@0g%$M`hGeG8&(VjvSuF(hPz=T&Z8ONsb$1Su&8H6YqgKu~GPG_P!Wjg<M{I
z?C6`WU@Mn@76Mpe&pVkf*xL}R5Exj5SI~O0tG@emyCq0*dv&^kltodnKzTyi%B9?w
z$4{=2WUlN%6PW!q4zNiHC5PLQ1*x%;{HeC5VJO|vnX=x;&m_e{C-*Qdm!P85#rV*m
z8Eg&<oIjUkL?$>BCObt@s2MAY9`wQYT4YQ)5B3kA5x>u}h*1;@1!pbW<t)Nd?zQx{
zr@(V}(u~B0*WNo2eP53iR=)=~-jQ#ZB}&0@=!KbbxB3cy_zn>Q@SB3J_15Iw%?N&<
zJA91UN4M~qiymFO1XT&Reb!__Ts_tTo8Wwho7?p?OiXtKe9)&P1+z7UmNUY2D3qX^
zdJKOP#Ah4NjxK+7D|phrQ{N{L++dq6`<g8a=1b&dMNr-F<4=G>plsA&X?1d}Hqm*g
zEj`BJO;LIt6p0ssB@5}@CYW!MDOwC>o3LXZIg!Jr1qkiHk|DQRjioAIYZ<g6lz9^D
zBAXasTEZvmG8S;hKaf+V)AZ&ibPi7D-hEiT09ccie+chSt_0v4+Ehp(!&2ga^M^Uu
z^HMqEz4X@QqS56{&P@A{TIFr4QQgnP_}9evw(tX|u3PF?&3`F$DSY<?9He%1wOY7D
zONb#BCxnmlkI{6MztJ9)GS$3L2cA5a6w@o(p6xl1w`kCiS<ce4Q(;Y8lg1Q-r;5?|
zhJ4Jysb~ALXM)?awYM6hy0?q*$<UI%I6ny@J7>*`H_wWN7Wt2*4o|F9(SW?Pz%+yt
zJF893m}7-zweq9~X!eT$O8v>X@T|SksFZtXJOv%uyM6}*AEZM&qT(h1BqX2A*2Ww_
zb$?o{-koXNcM{2j9%+gD5C(s5y@7$;;<lVq6Mtt({!bk%Rxo$<`QE5s#bVwRw7_nm
z3;epg!0Ns8A$4I^2eTr|_JSN&5m#`h$cJL-a7}$-92^OsGvrD4(d^W|vffjKYr~Fr
z)HdImqt-N3ErG02G;of1y_qD;1_Ky%WTr5L|JWG++B^LvZ{NdriA&)pRw2cme6GTB
zc+@)`Y3xQxf|#2!gu(2SE=&E4lXVnecVnu^f{jf2%ibx=`+5xRg`}_ICZjxQ?nH%F
zVf`^;X5PoHrEpY$h%5kgcD6sns<8m0+MbWJ;+CA=&cj(Xl4h@V!{K7!6PQ2K&P0d1
zK#poGEsumH(V`+|C}8P7>-4`3d4LDA6=}eI3JxUr{f#t;an6oe;xhRJVkN#Lq4Du(
zh-_$uUuX5Xw$;rtT;9?XiFFFO3=txvsyk-DD0*DInG`Gdl0D#y^K4(^EaP{#g|WyW
zAAT9@8SyJZgNDc{3T=f~&@s7(6iC__NyLhp1bFlWhd3z&zd@aUy%Vlvof``cx)2<d
z`34c;F`~udTDX@&U(diFR%&i4hGgBh_U)b4=9GvOZ@|*lVuf{5&@^N3(DiZ6ruTsc
zBXFpW$=Vf`!!s9gy@|%x-N({$48-^aKYHKZH;RGlDdDVkYO`dfrffH8yq_39Y(kum
z|NN-cNVNWb?BIp2wFFprs?^hIJ2>TCdYDV7q;GJQFkS$VR}K_QPhH)dh~TAuA*}b!
zx~a``S(=K-PWQr{W!#GVZD9$cb6H{O!cae7x8br~lqv@mdeCAu`ACQ1e_>R-pE4RT
zW>owB%*r7-Y+ajN_-I3D1)g|QL>KwfC}U~w!@*G4l|MxKG5!91;L0I+Y#s49Jp_R7
zbuc}P)fAkfjK;?~O7ev@ovU13o!`T;^m&ivvEx&pZKo$moL0$V4J=YsZK8(5k)L<a
zmSdUi(XoTiTF~SanKA<VB>|_E6K|_0Rtf7v(^9Tinpo&oCqQ6JhzUPG)~9gzC05Kt
z$)Em)kn?INC+Wk_zJ}N(KGx*$Z8DJMqb+1LtMzciDppL|Xaz%m`N5Z19DOs-ID1Us
z;^&eT$gDW*tbPZFj)EmQR)M7gJ7yjsp~#|b(>;$38K+~H`q^J-FJcwi4AR1$=2~p2
zI0`bJ_4wY{=b?$EeSO5#kgs`$&W^pWqrosq=w#k3(|W=0#msc`vy|izX`lKo!+m5m
zYrtrHt;OJEoP`=UHS=^zavB~x5c#zewp5MEm7sfICoF;q1m@a+1Fr$8e&XruosPZd
zo3bqgW3^e%D-aDhbw`HVXFY4en0Rfvm9fiV-_E8@3an3k9u`L;Y)2lw`stV+F8J1<
zE#qSa-6xm-_4A~dN&g4Kt7wlU_$4oYcsBIu;{{Pyvy@gNtQ{8%g{ZHkejjcRFUQ({
znIJ!(xf3wMD6%|#h;vy2(b+pq<nreS@V6PpkI3ee;me$h>>kT;=OPz2n6G{oA@d#}
zO&DaVbxeE**Zu4*oF^hhPX*S-Q}zBo&<k^Ok$?C6oT@zy&eM^_2PpV@Isrpq{2*A*
zYkCW<C#>~MkuinM_wszU0_&DmhbA8#+0;!IXbI;(#a_7xj*pSux$1`ZcoHZ?OYXcU
zmv3@l-e&CEMJ{jrG8eu@N7~3{1H;Iu7;RaQtw7txa1kw?otP39Kg~1}tz7w9XfO!V
zAs$Ut2-CpYKm3rY!Qf<>FjQnpXZnH`ewEtTd3z>aG#Jd?Tz>_Y)v5RZ6;}4FB0o}z
zHSx3qtc19>=yIKho|aw<@yRwseUxj1*FOsz7<!(Nne3lNoz2@DqR{GFeSRD$0Y~nN
z6=I=|yPZkj6V#28c;2YujJ@m^X!;f`ZqvLEGlf$t#t*ldzJ|_DY9FDM6b#95uUyj=
zJXvq)wVl(6^0A7qbAg1f<nsNqJv5WX=y|sUhwOlYls_2@UFUZMa5Kw-g%HnpJ$Ej1
z*MF1Piid`IU-U}2rH@I1yrIKq6<EAOD_AjRr9;s-=3muj27^E_rUY^R87b~x9JZMg
zWx<W&kR4LA0kMcoE6YY47UzGZ<j$r<|98!hLdy!NSq5_|`=K<KbC{6Ci2aK~?Y0h-
zm*MKgxsFY?3#-m1cFCfWc-`eIS+Gaf&PqQ(X?#E|Tk2O@tUVg9{UQGI^k#-xns@r>
zK5;yK*z%$&M^?ngO8&;L{(f7jp5J&toPY7dbSyf%s|Yjoyi`1N577bT`t{Mokpz6x
zUy$cSC1NCa!or;jY_#4Ytj5~stA`C)2SW6pM`n@u@BTSSagR5LRokzh@4}{9qyS9x
z{^77w?uL+q(oWs(`>0Og5z4gu&m){vXn#@OPUP~I{<QqYeb7FX?hHG%*C5h**elw?
zFJ$|d&I?}B+|;tb^m^ya`=i~3=?3Y%AO8;Qvp{lq`{eV^_i8Vjf&8@T#e4Us-_<dz
zyN-9Kuf^<K(=%}aPLCD8$@O{`$%X%tYhiIC$K_i+Gs)rGRj2k(gq^BN*QP4_59ixF
zl+1x6qLH594fP{i`_R`SpT_$82Z-??km$Z66#Q+pUhs>UA%g~dLerq+7;ZkOq+Q=`
z^y+-%&+^)Ts_x9IQNJg0Exz>C$QRFPAF7@9ZFIPQh?xAp^wi)ip#M_FoEe(jHS;Vy
zro3fG3{!EhaO2pXM{=$~A*IJ*TUr0sC_KrV3ZwQ}Dcz!i2e7gkk~N^y&(4qq-I#fb
z4CV~=5^1)8Q9)XketVRnRQBUbSZ_D}!}klUhaXo_j|?)>?IJTc?Yy~b--MsTXYxG~
zy0)O4dELb;S#Z8FEB@j*r96-{)WCATg^-_}4(lDvU45$$ghDvt2}i?0XY(S`Cw9Hr
zJst^~hbg5&{}bC)btdg)`%dxDeUoybC0<kIo7CRTR02+!VkrIS87yx6_H6OG+Yw((
zvWk}d)(tBuu5K>(Rz)@cNd<9!i?`D#C28(QlV>kA*>S-4di*C}tVOI{tkbtXC;YSE
zlH+3v1-1m0C>dfvhcq|#_(n$Zh}WAO+|0JHIB@tlj8LDorC7#}zX403M_ypQ4Y7R8
zrRnC&Y{IxaCsp*ff*%C0dQbDS)RPvUs5r~(F7M4)lhvV$EWP950XJm0<*KnxU;19-
zb9zL~lX*Y>6)^O$cB5KB^H%Xtn{kQI0)LzY|1j)4s%~sKwktj<GXILw*y)Bj$?j`v
zYm3N&46#r>=a5ghs_>2z6(nW)N&>~m3=FFA%0J?G*5$9>cy{*08k9$ACU#+eOJC{r
zK8ieTEU=U(8~MdPI{eVdRFbmMh3T5IRR67vy|P^U*$ueX?yM2+XXUg?e`~_JC~cw-
zB8ufKcIlLC#1~xj3f8u)xxV49P=4B7t(t`_hPwpSpGy5cCXr@KR1$Ih65R;edJApI
z{7h(xo>I<4$8YXbCrsB}LaQ5A>NV^g&yb+{)r=wpHbnJBf*=Q2jTIGG>~eu@=ofqU
z@Y%h$&F0NX+CXSjFGQ;w(GbF$5>#KNUh~+}G;5-!$nSZPh_)P_q%I@|DQBSTpLVE?
z8r63JL8&AVT&vFYVgGJP`(J`aWvs<im(h?!3;&>5+}L@Dv=T}e)m-T;&|}oZ4L`ir
z$8*2YU%SV>xoFzi(+5?*sp1|gci@e$HiK$SNuOQbGI`8Q_5ek)Y50atyN3fser>C}
zZ1zCsijRqLS8~0l3Ex`;sSZS=e;Wi2`Ix-Ef*|GY2{0CQ0-asEhd<CY>zCEn)#z_=
zFjOunoTne%)fa5TnHTfH%G<*-2`AAZqc<e^c8?GMXru%?7n&4$r9&X7&*6G6%yzs(
zo@wj3fwrIpT-+9>b(YbJN^y*_mpI=5j1Rj;Nsp-H&a}eDF|p7?O+Q+SFM)-Ofvp(h
zJ`haFmoqcCr*j@^w@;fHYzbxG={ksFPfQ8IecGhCo-o$5WkKN`_Ky@<)>dKegA#2k
zSnF$eA0ADN3)4f2tomz@xH}gzr_b-^r0pi!ilo#`O-u})F9RHXeki2+!%3J~dS`#F
zfa|EPV_(0wT(qUct2H{(9o~B^yi3;6awt?TdERONGA%IdFAhfBXGxj-7wSSDn!X83
z`aXDKnmxS37^`-;KtCu{iFIimCV!nG-uqzaOQ(g`<&EsJZx7Eq=u|vKoekolBE}qK
zxUdcJsE`ke?6QwmWMK`=+>4a3YRX@+)WRp`trx~J0%vubvWBcOi&j?teZ0P2a^V%4
zp1G17J~mHiiOZW%3|3A?%WJi+j)BOSj;I@<G^?iCJyp%m>z$vL;Po^s@=<3G1&}Oe
zvc>rurMQh<OU*2OsreNEzSZUYzS?*QOW9lF|E^K>nZ2Ph{j3|!I;LQ<w82c~g!F4R
zJ38_>1rFhs!?zb(Y8wPwV}#Si>#MTmxtdnF_J;iW^6U6~3udOMQf`jzsBY8~i~pfg
z@BKTz<NRr|`O_2l9c5Bn-T}FgV&E=}nY}UZlpAfI>~!u&o6)UN*J+Xi&5=hb_=Y7|
zwPI0{?^}-%gB>8mJUuM|Y;w2Ch33Jysn9oV%)`0S_KFu#Wo!ugQTbO=((wx?u_V|*
zU!TAPP!sq%+y_%$2m39tX=-n`;e(%;hV}>9FCT2`4?7$zRd$niM0B<L0G~gp-lYgP
zVLQb5=<Kio+<K7waC^oF%Y}PtZw{uj52u<>hT5M!nk)TYDL-c)!6>S3Ih(!6;!U)A
z|3!yR&l6<xCnwaE`0Vqsg2r3V5^L1<*NWvhWsJ!MZRY4mez6@B2xei+VOvU~XnJ3Y
zPZ`QDlig2|bh^k=X3KKtsMQHYgZ-Ga1i`75n@c0z?1}9nw?3*rkQYLKU`u@09}`q`
zsX_{d$??5Ku5TBb-uW;Fm)krQ@RvqxQ=jd(@X^v|yzioa>VFlPom5}N0;5HZNt1uD
zN)oz$b8EGMaN^G0^TzF+BVVHRnv3f08|o2M5}JOFZM;zG=jK9O5ZRGD`in>H<t))u
zPDxpuEroq+s8`uTmfNmM<n<G+M|BaB@r|b8ouxFMnwYV78%!3<EetBG#Q~2cM~!r`
zYK{eQwki6I(V&5zq`{39C7!3h=Trp`jCpyAa4<{r@Utv|cQZ<yztYWup|A8t)1Jqg
zuinUTzYyemm4LNq3^6Qee<(|6)+S=s+?)J4u4+nbJ&q;HFBzg(Y#$v`&PLNAtm9j#
zT18*+icp)cy170O%+vl*2O%+0LP%Dc5}S|z1tb>}EVR|z^gA$!;rUb=di2|=dpX^X
zs%d%kkAl}Gp&d52y<2I&niXvJs=uFj)<J!w-*xx*oEoEZ3#y(Q`-;|A266PcS(qx2
z=MDhb@XBX6jg`nbw6MR1$?d1atnliUX3Kzh+NS(4Sw-^Gr?j@qeD70v)#vv*qo-{7
ziD+JH@%ywM8LqapWa#wjkFMhQKO^5-$TI_7$>y0Cm5Sz;a_>p--X^KG&H7;;K@H)X
zw&#5BlX=DdRYUh}-oxUmwCq1v&MRcN*ll-8WN3$k|G25qMk~ca_q1;E4!(hoEZ>!k
z&n4I$H6*ByaCV=*lUp<GQQvvNx+-`h<OHZ1i*j>V&(Ql5kPzIr_^%0nDp(U{9>MgL
z;$APc>$u28N500k|E?e%D%ia$@8h(`#QO_QeMK89U+^}!oTvw&5gFyREIr%(l==x?
zM2$g+;@GavP2PrH6uMbPAy}an*1fu+O0!6&I(<~8>xfun#?yns((EYsFL~(5uzI&m
z42OfP)S8Wq_0mSZIioPt|8!-~<iZ-le1E4v&|VPQ-)ul~SrTij9u_!d{s>Kfpn#<f
zXS8puK2`K4>6-e>nu%bwBy{|r9aS$j$#6eQ9<Kd3dA-Y`Bk|b27XuL6KUw5a)1c=m
zpoy)zZ87p;IP@@<giQr-saUEatM6KPn}Req>aA+W#SApl*L-D#YyH4*73SXMPxncJ
zfi^;Y?rVJ0OoY_)O%ZjIFWCv;r=($d)f-DQd+#jG<;Rv!7mJ1N?3eR4fV81zsUL8;
ziD5ftV9ZXhTAnl8x7R50<kSlzkFJTzp$4`KAxzDUf<FLeot9p5dGvY7KN&SS9dBN2
zTFUK=aqRp!`Qk*Y`5HlcOxSjrzUIm4dJFEx))Gd?nmo%(O_}nA2ZKIEfe6~rmTJ8b
zr!ET4_~f*)pQn>Y`jm^LW}XH}8qKmTB^L|^hdmrS%O)!hw3e?%YBQAWyE9YPo?bB=
zmLGgF^g^YY_?-lcuM+Ls6vzVd2Xgs5ZO*MJ#Ns+lX5_$ZO26aQ6DJ-`q3GX6x(&fx
zIdEDlyoi?cXR^_w$Z4PY$0y${Uzp;=Sk9~(!tE_o$+Nrk(Kh|`I<rl?DPSQ4d-<22
zCabsR9t?}ZUkmn0+y=O*TJ!Te<I}YmM%PK~$OYS&GoATMXTzQ=B(E$6pM*QF-Qflg
zjE}b(BwwUOD~PJRlAOs3ku>5fz(R015Iuij&O5^MT+2n3`ML#RQk8bdi4WE)`S?p8
zt<~KeTed;+J@PYh`B1ORjx_np&2w^E>92^(_bj{kNv*r6SGFV5gOa4Whklsu!c<;m
z*uIxOL0{;fJg$2G*kglJ^-GcxEMES28JZRZkqnksIpp$})kN1RnUxmjC%0T*-Fz2Q
zNoZ0jeh(Jd_7%w%g(GWAorJ*8{+1zS0m2XAqo2<blT?NFRmODQF@vnnjj#1!vtY86
z`{3<fowUpAL{(l&&b%Nl6o#m>>WlVdvq(>cou-#MqnUhWL8gL>l5sw7ok79p#!bk&
zDY??(!uXD5Ynmz0aKB3Nn+Y`4%;p*|q=?p3bn(V@;c%5|nr7~!!9sESEfJ=vl|Nbm
zT5<y;Q9Au~kaG31i|?S<-1+uyUrMv;`oPk17v@iA!@YYKrh0BTtZ4q~#azO^WpT^?
z^u!ivu6C&(#lyxuzSKh}?VoLZ%6XE-2kDpM!~S3edhE-x82w%}`?uZ40j7m()qdYK
zZc{owe{mWI!VT*|8W|aAYPm@B^#N+hY~R(FziK$d+SNp0N~Dv^xv0%egPpVXF?r|L
z&V#A?o>p!KiMd2G(c(&-=U^tJNDi_aG8YRy+*<J6{@vY^QrvvgA!Z**BJ>CKeEYNZ
zoXHox&3oTK+ivZrePv(ItujvFjr)^aG@U8TbE&Q8mvW!KjL}KGy6w^IARqjzqi*wB
z=rQwh+^dseuW3&FsV8fGwYyMt&iP<5;ZowhbhD&<-y6YGGq1_zqzfLtJ!l8bnoUmf
zE@ms;_e>_C)t}V}F+(1ddRLYz{sqCQ!n`nk%2tui&%B~O*(cf6I+t_r@YiZ_dvrvX
z>*wkcNY-BSX?X3XW!z`VAOEh#SwT%o?h=bNeH3B_(lwWI2gdPSZiwZ(y`B@NX9(%u
zRoBZq6w7|xIks}h<%A!{|Hm`KI(`@0(k`K9Q?RrF78j<VyQaZ)e%$qI)%Uvhcd-$T
z!7@HMNOfY^G>kBrsY<PW?G@J*-u*qjIKpwoCu85Zxm9<M%|?}!dO1cWpwrL!WuqC5
z*U}0DwpU;0B-e#SsYFbTZi9fJ86IJNev%qQ{hC}KKDkSN<k~e8&F5#BOA2h#x5T!*
z5-SS}zlN5t`{}^h90Cr$D=}W2)7RHD8l_I7jAn<J?vLfUGd+<rN=*5OC*yFWk?5G5
z7Nw1i_6=VnWIp{Fk+J1$<DnD{Ms(tg>j|}>yW1F^7oPVLjd#~Jey^*htcw^Z6)$e|
zm{Zdar8xLZsn5M<MtXl%j+h-VS_rg5uE5P+5iYf6#@{sXI-W3(?OHuBy1?(gHT-ho
zP0eza??wj~GgbF1yoc;n-S*k@VT|eEzs5@rp1txYazQT__b6DM$!0r$#%$gjY`!&`
zC-t(>PP<W!6(^#e^5BRn-Q@G*W!#%<b4t|Y4vgo$Z`^ivpStM?Y9z3Y9<yJS<(MKc
zi}a1RB2Fk0=VxAWG&9aLi*Dv5y6Y^2bJGdOGR85&dXFm1Lo7afy$!isu*Y@VlMmXb
zoL9oQt4Hto#a5AOc;zRoMa>&}pY!zbOe4$3?eSC>)RN;tn61ZW-yL<-cm~lEIR|EC
zraMxwIEs6J(K}L`dSS?4)yoEAyv?E<O1-*8Y3k#Xl6x;%*UiV#OW7I~{Dbo(QqS_O
zt{-zH_gJT|@QnRFslbuaz9syD*~pkc==Vs-4wM0X*u3GG2-9I^Hu_QLmKxz5d}nAv
zm*7>JCCzW;>Ky1&MV7-qXLiq(xDpLzvgnr_q`2i%F*<1pSkc*$1#`oIWwrxFm*i(i
zZ=2QEetv8+&7ALDcsBd-TlySNF>ImO?Db&fPT6F&flU$HT@SpX#MsscrShD|?^#Ee
zS1@9_)Y?}(-#L7JnevxlayW&gG7~k*4vUF?^wqpZ_z^D{@99+HG|CSPCq`CK#rk#(
z5g#0%-C3M_PE9jY6O4ss{C5ymI@F(k@V)Y3``WwXf=ouuKv5(xR2pn-eE(CxPs{oD
zmX=|aTAd5sB9>$J{0m$6ROL!u%dEd7zPry@1Jie=fmv6hMK1r?Ib$<9ZvRI4R$c9b
zaRC}CD!w#5M=B0BF}aca^Gl>4HZqd;k5lPF>v~de>g?o+zpuE-@34tnXjZW6yT!|N
zwvMz@U(Qne^JsK~$(kK$a7nsa)o6^wjGxlgtT~yO%Eyz&J2mBxWzD5qvi5dy@-%qO
zF9$EVH!$ZWcUKu}Vur06n9X~cN3j-{$OcbR60ud_(<%SeUvhM6{=}%C-&%wA1jue`
z88LR(sZ{;T-SkjuO~#jFFw9fdk<6r(FM6NwJ~iJRi#7G47_AEJ<%YPv(O6Med-p3i
zz{U)eTne5eJ)ef|+#7kfFrPyYzj(S<1G#s8GXG;qd7>~)Pp=Jf@jaz(V>VA@U?FLO
znseUL%Zc01?tnZ>>xkanowW3y5%xEBU2~XKZ>yW|s38)^tA7@34>;_XE}~`~S;5ym
z{?3=vs<*AP=p~vF=9ZwRs7`oI#d0#2Dc9)<H$p8VNG+U-8#m@J*f;96$<1hbgcFDN
z48Af9a15*wAz4ShC{Y^jk;-J#-(F-|VbhvvVy_FfUo^Lr;);}d_W<<(P*)IBbK@W}
ztUD)5h05f9v4UY8$)eYpuZZheld1IJ-D&)rtAKpQXmn<{wIw|WI&vir++i(tHtUqP
zPb*fmf6aHOnRqQ!zJn|I=Z5y~3K-2ydgaAGevwzZ;w`ai&9o)&3$}aj1RxBN(viic
zJ8#@@Bc@UNlV0-PUgo*3e`YX5JbGx>>?7{$>NG4-<l6qpCPmiyVVMIMZPC5FXpK?o
z;HIwOxvO2n11*mR`Nt!6*-~BhH#=n<IhIv<CX1f+>T2~E#3cD3h~wiL4otP+bLk5|
z&#y7b0DzCkh@x>E(}73YTN4yf-`qQQoY;DER(Hki4;kXR8|EuA5A3+&0Z~sAb3|3}
zKDrUyAN#IG`*S1SQqMhxhoww6hpr#x_3axC3Ay-<|L#RaMV7Np&cvaE*;*&MI~tg~
zORWpXRzT~fDkG2J!m3BZ0k2x*nI@bKU1OFBxES<0mC$VUy~O$|_r$KfJ{&jQigV{H
zlw!4<Ohi2rg(KVcy}X<a4AiQYQiLx!k#0lDy(-*P&v!L4FA|yVIEi=;$RKyZzKc_n
z&^0mE@?hbiYiNNjwN-3ZZ}rM&y%P55`M~w-THk6W;4%^}<YvM#KX9b%)5ig9#Ck^9
zV0q&7tnZ0wbMr109~&jyM1!s2Wf9vwWzQNeZO)>fU~ROW-q2wC&4Fsh>A;c#d^nzc
zdtNv)Jx*1}+d%ij^q~8dBgBw$eO9+_886HE;__Xq;`W^B5l!3|nSFQv%Yb@~iakzO
z+-w%U^XR%$cFjF*8Ww5iQ)Y1bimSgTYQ$e>We^EJQb{SzZu0R))hR41qe>pp?)0b9
zubEq-(HrMCp1M%`1ry6tR#hy&ZLh|vkw~I#_x@%)Uh#O-wk>q4E|=-f^7{CR($Svr
zh6e=|KP>Lza-S|cZlZk4N`Xfal6{E3=)IPgUnY&GqX}EMw7#;x!p*-L4oiME1;^WC
z)5HJP@Zm`nja7FS_oC$banl>xGMX*g75rm=Z4Yo*U$GD0Ka%3|N|OJ#RT^!ZcZ2cZ
zUOUsRK)xVb@iD%ybhLH+ZC)R}7k3Z$ympz3nVfd4cJb}5ma$zg{Soqfl^<9*UHUf2
zCkLJ;ms5pi#3c2aKxRST(@T1Plgm7aFV5=wOd3DgQh9VQvGJ{3Z5<{)-*b8Cf$#iP
ztfV;zqf+UU@N(=r@%^C`H+Ob)AcB<gJ)-`G#~#|cw$W@(*8Mt0f8T?bHhr(AMq<B)
zt+-)(WaKK(mHcTkKZg@7V01SaRm-+LE`Oi7tFg~bwxyv=VEn=?T{V6(+$#KQIQaH|
z3%`=9Uh`@wtnTqyJg+_OfX=ZJ%|ph03GKaLOUdx6PX1(Si0x{O!a$cBOD9^#5A>*<
zivI5DO?<d%N05j~<{74b{*Aee(|vFLsQrLRd^C|<tnwp5EYu}oTCJBq*cbbl?`^<o
zA?ZRowUdm(uAZ8copVDW54fr2R*juT75g2PE68iV<PG1e8jJhNmi$Yywi<IgZemTb
zbRBHVci06NSW7y;<eG0gjUOHB%NvOZ3U8X+IKS^>oN<MXzcTIbq2|2dHQqPkw)w31
zvZ=M0%{@0&jThKwpc(96GF0&@==84pdi%M#!}ZqI_IcwRGj&yb9LdY*wly(flL1M#
z^~K5d#)CxsQa{~w_n-#+Y*?A17+?4`i*TLr>T^(;^<L+^F?0R19)#(>=OYmT;WtBk
zja<_jV|P4#r}fggik7{bC}|!<Q>b#TeTTXCrl=e+)2m+F1zk3YX{L>s8=NB$R+&6o
zuQzf<B@o(Nd2CP6g_h}|Tev|?E_dy7onytC`crp;y~*LP3QKgiv1i(vQ#~YxhliK%
z4gB%G)2H5Eui@f$8OA!<xioge$F`vc`I_xFFNba4MF`c@WJr1@|5Q$t%M0xcJ^STH
zm#)u|7+i;J(kM^kv&JjGSLa%$!xM3pxK-h&bv0Xx*!p94f`dHZ1YBi{N8`^WbF}<#
z<OQ~dUidcEb#dmPYM8%~Yi(of3MH2v_YH>T`ZJp^{5es{7oV64ztYLAqXOFEoDP?V
z;g(ci&E3xa!zC#-d(ZIb=W4a4TBG1945nh=w%W;zJykS%9`D)y${`=pn{v#<ZO!En
z^t#KyKH%Qwn3mEZbAyY~1OslS9KBQ}ca-C#tXqC~1&AdHf<lko+g_)4v`BMD@BLs|
za(HHSXs$kcb^DQ2_LbqW7gtihag>VCOjvEcdA3Y@B&Pjz+!mjL&+~S8GG{Ql-ChBp
z5|d~+i$>$mmw&81-Iy`)HcyAv^dQl6zD@YJCnFt~C2WY@Wh6UC!f~uCPz4`3;(b%M
zOqmn8k2WwoklyJ`T>XA5cSrx9$*WS8s=c^zd)9vABu&Z7HZSnBCKGWhN}*-Pef3PI
zdw%wMErr?NCenfdx%2LKYh45OR+m+&Y@m8EtNxASJf$aVN5N&uHRQbc6PnE9?boUP
z%O~hfAtsxoQ~@{MRj=&*UTltOeK}xm<da1B#!s=QQwb~Y{6%b1-f%W8^GXEMfq3W-
zRtkQrSN+pQt5LrT<nWj9gRxM*kk)tH@kYVP&!H!~4Vg~{O;SlN%)w-N&gJl&Il=a)
zSK{#Kd7ioZXXCOHZE1&-lDoi>275odxb3>A*HM4m>XNTToZ$W0_$K_a_-nj2lC#;>
z6o;y6^>KrB?`-^n-n_&-olWinJN35v9>pEE)?;Wt%D4Ju6B-Ba+S8w?-_6(|q3hN8
zz~uFnIOc*3_WET15cy2lp(dk>SS@L8mlbJBcrLx0sDFbubARG(%V(NZlDp~r9nz@=
z;S*d#ZghY6jnOc#pfjsd3uNvLAG?j4)U}1Zn#G&Rvuioy2JFlE$q}(~*#Wbv^WQ?B
zv09GHscq2Q#@VF#`AGLCVf_N%@=YEl=WR~cWhZg|VJlp_oVfIlqUbd-#DLn+lVje@
zjM-cE^hbCTaA_GkCEK{m-P>`*gL~Fuw7Y0wV*l2Q4mm$_gTbRcip&{4^)_G4%@4P_
zf@$;wli4^r+-$GPlK<1!(4>}hHZL(X_<8sFFd43fL2yN^B5Qu-CvVLO*{Ok>6K}^<
z7jQl6Qb~#Qz}M&)yCDxX-!6rK;INiv$Q_M+<2E`=ljIAmNWG}dciVA4REEE9WMA%a
z5mvn1WjY_k+({|epmKk2O7OD${v{6?G3RMRIy>QtW@}OBC!@A#+yAe<FOP@vd;7nO
zNVcTazD0`=Wf@zOvKH+s*`iRQm}th5C|WFIDHTRCNGmDJ*i($eXeeaQgt3if?AvqQ
z)93R%&+qs8{qy_(``;|rb)D;6=Q_)M?sMMnI{u#N1)IGtxVbx}5i%}jntP(OSucDR
z)}>HQ+zN-@bOUto<=f0(`N!2hN*>l~bJ|(A^Oo(h<(Dl<C0y=Xsb^vYYvt>7BQNi|
z_fBC}X41k}=Q`Ga<{6#g)MNSO+ti-+8^XJE-YHBiiq}FRXW{fdT8OX?tNFQ{MD7uW
zQ}|h$s3^Q?IOJ~MAUH#fnJ{<mEB$%HIKy+z{A#a9&PEe=CnEh0KD-(yCoNy}O-Y7Y
z`0{a6M@hs)z23C?_aiE@i(7Ay|J=2-mjZxt<?7I0k-m1ynzPTi4jLRFJn5U3r}iz!
zQ)yddRyF);@5XmbXhaIUpdI-cyR=TvYXS7O39SXa$X*fNj&)B}7rC~Ni_l-`l{RqC
zMvA06_2dPgk?iW)!<rK@;c0Z)HfVN}UrOi3fsA*Xt0aWIHl48i#wqek<GHca^|Py)
zK=UWV>Q_FDcYiv)c$<rBKqGFFT*?zAfk|m-iiE?`7VlH=pYgtDuWy=bkx=$BD={HN
zXDCtUGoSnv5js3kB7N0iUqI-45_`JqmXQ)}PQ~l-zd^HnHa-=|bKgIREl0B?`X1l=
zPF~_kZ&GsU&A%F(x^Hpu;^qi+Xm>?UyC2_P{31DCj-^^$nIp<*KT$il)}$BTS>?OD
zK`(kqPA_XY$g=YcT=e+KiL^@E%&EX#_lpYI>u4h`#7&J>tQ3;+zL)9OiHi+I(+$4M
z_f_Q2Sj{~crFL*(0wUbxsb^v(Aq5JTUa~r29BxmGzu^^J6idNNk_Ur?{YUSmdw4KC
zKgsLT`q=I151}SLXpWgb?EDA^GW;ywjWW3L((@)sKd+aW7|iM&*UDpCcSqaydCyTA
zEFpb$(eyQWX#c7pl_TB;G@HD}l1<)aN(uKZ%x-RyYVp>~c()IjGA_SQ#h2mpu!|d>
zPIKd3n5#%Ojzp`8JWAT-9{W6O;B$dt?T(zoUmlW6`J>zoNey|=*99l;ZTYVEyQr|C
zoAM1CT$ICJX*CRhpUXB3r5!}0in>9qj)ucu?vP6bqTCIV8nn{HP!+n~`w@Io&!t0K
zu^rZgfD9klcGmlZyRtCYoTXHMCBHA>{-EhiajBLYm<&~`laai$E45Cje2eUj-Wpjb
z74I-N;m5E|i}$@0T+~tSX!Wf1DotxcQ}hx>@BJ{&(*DI)v_(uNs9)*|rJ8KdN3JhW
z=u|E)(g5rmAtAq&?V)}pnfc-DyzZ34Vcv6(PMSc2L!|2bI<6P|QjZ75pK2}hcO&1p
z@dXt<b%UC}<Tb86$0wYbX&r42t<VV=d#OM@6DL{Am7&d|w4K)paRQAzvv(t(x$z%+
z{?$momvDNjb@cN*Xl&UD-5oUKVYmwLc%AsOTrQqrL*C?jzBHsr|0W@7ay=hiZKTMf
zLSJ3f<!S!CgQbGBBHcuzruQCb)1=`Qd^;u!61{etJUI6VIB#0-CBglGNVTV8f`7{s
z<#@<$9sQP2QLy~R9j?nib$656;st7<?{BBe#s5)FYx1!RE;?0{KS7C@q8><e?YQ`8
zK~ryX++C#@E@?m%Y@V9Dq!n6PTmJlE$B0?D$EMc-sOu#$U%R~TQcvzajZSnK*X0Wo
zC;461w6>eSC<__9t5#mH&o-lVE8K5xC&&Ao4K6y?nm<8^n5sVj=fDa)EBI+qy(3!X
ztFd*@!KG&Zj_VYQPr$4f&;DvTs7Os{NSk-aup(C8%D65*l!D*3r5dkT8sC=JeJ8`j
zyX%tnr!kp$)x@U|a2mA#w6V5v^mL3}%NaQI^oGl7P_x-+LWXMbxkT`tp3akoyw4D_
z2M{tKkTJw|m=PRZwo(W82<yFRbr7x%kx`AF(=1}oI9qm#%!@FTzdq^>E7XO1klfIf
znAekjWCr{9tTu}NZZMkV;iRuAcoG{JS<O;pU%4^dU7c8>>Vr1^uHqM3zB<^t?W@OC
z=rx$kPjFo9SEeXApv$qnlHe+49_mH<N2$C#vBYo++CO$zz}~&S1ulKIwHZbm4t5w3
zPAYAszFIG!_o~xDIKZpg)KX)1(YZv>(_jB_L*6$4w}fiYp3me?!HHjGZagpZU{V9@
zemtrP`fiyhvw@2?pw(=Yd`>-P;#;6rv}c8GGVKrh<Of{{^bj-u_vO=k*gAMw@5S7j
z6f5)YsK)q<Kqq~6^;UVETE=wjjAqd!^PHvq>3JCYzmi5WrU-i<$@CrI#%HsG>&%Gp
z+r;q4s<Nf#826#wr{?+m#XAah;~VmRiJ+ck2)`)Wd)S=lt$4ra6hXgFfoicnLNBxD
zG*sn_X`RM=J9mkIcpIsPS;$%&oOrOM;oV6)V%-6vw+dtkVQ(J}$fz_wjRhQq1!trY
z__aY^hc@J^u~d`wrM4ikL^ul4D^7p$c+1}Yb=*2GsnkJolb2<1(Y_XH2qto}nb%r?
zu_vdKHmX{osMY5+_eigDOve7BUH<(IdARB;ypJEqsK(lT-QK<mZ<80kc_dEom^M2R
zikd3lz@<|=G_5gLlT}-romhe?ogTXLzE6W&=M`m&<Wbs)xX4mpk*&R8chk1J-iaWD
zmKNTloYVQeU$sIr4@xs$w5P?+CrKLaC+57U8DdV&^I!G4Ut~;>%m6;NhmrbeeWp<X
zSIf06HRdG+m(<;HekxJ<=DvQJ?ozj8T#mZ5HC$<05BKiyci1~D&4_s~CH+jBqNV1#
z?q5s1Fy$vUf1!C`>fDI$E2;6bE!rEQQF}WY1oK234hBXQ?IVa};G`K1n`Zq5kLgVj
z-^%N=%Qy6B*Rp;0uxqkfh6~OGevw){-?HZg+{Ne&FxY62phy+A*F`*r4tX73f~&I7
zV&W%-1M`=-{;HM_`D$@g%g^Cjg^Ew*8hnDw1}xn>(gL&y;c+f&{-9a~peviJWjbR^
zE(96XJijs2Be=OgMfmOJD!%m6!j#U?S`XpgioB8f2aJ@wklIzVrOB5UU7Mc`F59OU
zYpo7i8B>HMj48sQt2nge9zAG^ipMvn=EY~PG>=R<cU+qlD%RD+Yp~0K#OTvj9jA}(
z0|B0=gRoN@3lx@j75l`_t!Etmp?<!|d#mYUSJ<Foy;HKy?)##LZu)YS3hK6zzNxZ$
zQu4mY`lXVADdJ+jqSC;0ddKXVRgb@nC^RuT(>8gW3NAYM|I(GJO&%FY*>vEZH6MK!
zRrqASg3IkBPtzdLXhs-0{tBpJqrMAkIwV#Z<egtXVRiFnPl=!(0F|}tS;hX6^L%&J
z%(Afk-M%3HXvTb6ll$4^kfN<;jl+G@xtZ#7<#SOJU44(j&(ASgp3QlV@$C6$$r(&|
zhWN5Ur5f+Fyi>?w>-+=%Sp_TAmJi&sj!B`0r<NV17TRKt9x_~9jF{6LiVc)zv&mQB
z_^L~k#rOqDeAJ53_FD?}l<J1Ty{g#2(;3~udmSG08s<5#&9PcWQcDEq$@Z%Q^oK~m
z#G2R>v+y;t=oQkuKZX@;_XZ!pHy-M`MZL>y9l2>VOib;oleCS--Ik1-LD<gFB)aPD
z4yipyoruEy*A53>s<Jah_F#@NnhuS#%@d!>7`|xzKXrC@h8ELV;Y%g#V>U$Lfoo<4
zc_E&X2muqvP<l1amaw<GK(qp^im>$utHz=lZ-(<4=3ZPMOIuoPR3ccI*11#O|5D~7
z8R__*7(Lc#;i@2Fs+oaVTt-He1<x#zhpDr4jVFAptLkU?dEno1{2cFC%6{b%UifWp
zdQ3*TwI{|usDdSoq~r9eb**QY&1eD%{(|Gx%ircCMCkK;JX_R0g(RQVxSy$XGkmG@
zjy$1+aM3H)fh9MCCq|i$($1$5WOu3ZA(rWx)F|WG+$c*cL7@7PpELZlnTzMf=<&<O
zyC>R&>5GL|O|MMV4Y?#0dv@LPT1asIN-}9pK;RD8;qgfN@d}#^{&D|kVM3?~j{vJV
zY-7av-<i^BgVx<yIK?P-ahs+BP;4$8&b{t(^lArJ)@__`DUl@Babqo`D&Ye4Zp9Y$
zQCW)kZi<ui**)QIE`f=GowqkKO{E4)bC*84d*fyza00@|ykBr-QE)z}s$HQg(RYB@
z9reBGZi?hw{mW~IFf94WS-B79O5?6Q%XYatn5W(zyMf~>(_oGS%Ifbe0(NPBJ!5<M
zP@jIISCzX5KSwq6_#Kgvr1qp$%;n?EJx>t~xXNVzO6&QS$Ov!1_impP+x<aa`mAQ;
z8KuC)fp^#loTLdEm3Lb{6|jbDUjfe7FrKu9M1W(;2^YQ*tI|!UWGQ0mxqp?QD$hN!
z**NhqP|~gyL~POu=kKr^M-R9WX>6CDHa5;NVf}8@W+8vqcI}Hvv)3-Iq@1OMJJB86
z_jz-b8UN#s0@ZNK_-b$GZeq6NOg-h=A>GM}#!%ct+$P?%LP~jL&tY$_tlYn0m4f>M
zO*0yUh3B2WQKt=!Oq?onmyP(Vb`Lg2HSEl6CBM?%(f&hljqpAsA5>8HOW<{|Co_7t
zyayrFl1K2$a>hm>XL_cz>poj)qQ~znoVC_Ay_GAv==Ao*{e(+1L%*?0d(0}sKMZWa
zY~K5!J^8E-(X21<S$0bCNy^<Gy6vLf4=gWIW9~c6&&=%Zm<(AkFs}?BeUmDB&ZV*0
z=jNq9`z|IeTsv01c$N~TL=+n7d|9^#>5Bd9&WN7ScxtV>YdtT;xt^Mf(Js9n8gYe{
z@d%u%mfn`s5tVlN2G3V<L`Ai|U6q^>D*gaqPH$cDxf)m#F5cQ<wM&wk7;AV8Q!H&!
zH7Y^YLeAMy3hhm;1WQ+s-wtW8x!Bd^6L@KOpJLL|EtI(cbH_#Y<BG2Ff2!AQMwE7c
zgbg8GKW8JE(1wvW$(uNSnOB{;ARK4Os-ny438%q9@p!lgNY|+F{fITV94##N)0np}
z_gj7U@O<O%TZbqJS6ah-Hjalz9#dO^q=WD#=qXyTy%wTj<1#ek6W~5+deJuc8pna)
zKDrMHK_)EzMhs81AEdnon;WZoKh}4x7@2Dxh(1)fx`K?_TuDp+vu_1bC&Q^d57yvk
zw%e{fgxh`wx&8_bZ$GIq*@4QEWfMAq&k>}L$Z<2L$eU-j<9meIPn)WXAL~bDM`jzx
z!KA=nlS_5|Gbt;P#QmH&)&712ID4rCR`cthTMR!-CZ9EoA<;J5*Bs_J8`y_qA6bD|
z%5loS=w<}~uAbpyQ;DgB!TQ9FYr?PfWK3-_t8)3K+N+5Al2np|xk^R=d6pA}95t)~
zJw@lugug@SQXg@-o#`UA#kxh9HSv8odG|iF*}_<_g`|~{GBa|{d>WhadVq{A@x)aa
zPgbUEe>35HV!5P&8CD`~9K{@%{yzJoO%Y9s3g1%+rD8~#TiPp*5))69UK8oqL-Ic1
zDe>exMwo}qdWTtTl)rprs$$R(Q~Fe#(?&CO17-2th;|b0dTAUf5iWFGi#+6-L`%i5
z?U4-8)38r6AcX#D<0KxGA!xr50l?lLi^m9FKXdjIg~c1iO%y+T>nqn|j=>#<3>wK%
zC(k@%+KD-ubh09T6+oK-eL*yd^kwz9W8^m%uq?uOBmGOSNQ4tl|BN4_S0J8S+uJ<J
z87|vZgBMJ%35ZX}g%F0za6f1D9=qrp94E#vBy{|c)~_ab#Hp~9=<T|19(nR30Abl1
zD6g;2FTzNbcwD<bnP=id)vDQED|gBE)xc#T*IwLkX*L&vAL}uqMQ_Lvz#4qL)uPOH
zQ>!58ZDCAG>wgdSi2dIdF-%6_PBmAmI)cdcm>s~L(8pdrEkg~9V5V`!o?!;6^#q12
zm}3o^?t8@iZ@vA@-*DLs3s3e=5|3++`G(*-;QV`4)m|ab+c>;o^hk%>M}He6=(zc&
zX&WXVrNkN=_)Oba(66dKRFIjrc>K(uk1~2Jm^JgEvO9wKzinGGy8>19jjWZZVa<lI
zUp#noOo{P<?6?PWpAUDX)y&^J0bs3vS|No`V)C_2t-hxLpTv}v^T&kpqJeAJlAfGj
zp-r^^OVpZ@hl<{T6Nq6E{SOyK&kSEw3-)K3SQWmEYUj426eXKZj<C;`>_W<(r1|-U
zu-DtdeC@ET_o#47giPn`cTv?rBduHU;OQ}dMtbxP+T$X#twT=VWYbpae5+x^q(>-t
zY8}9C8=Rva?&Nq1(58O|!BZPdo|c&veS@t&HB7L-U@@n;y!J*Y58k8qz5!wCPC!>W
zi~eWvzz)DcW(PoisMxk9kd>GOI77e0*t};zbk*$0_Mx8XAiJp>_~^dgx4o&ftlZ>w
zwk_)TpOJ;9C8|gnGwrfpEL*|07B1yB-w>;6X=jND3XXR%9{RI&HcrPTlvu=1i)I4y
zZtEr<M7tO$4q{1Zup_J?kW-i-yK5a|t8_rjk4476-efdQfj4huBwNLSg?YcF7$YYl
z!;Q$*7JkW@$g7m~JJm1pU1~xZm~{fPc0JRpko-^}k%%Lu*W~-aVg9-?5g{)PxXV0Q
zF)x&robbs4I!k6p(z%{I5Dmv&@_b0jc(9gH-W}nsk$VeEO01lUV(FCydWfl_9sRzq
z$D2;*g!}24#U}|QfaA)j)NHIB<(_SoR&x$oY&&H~DVAQdfz=inXa*oc<{49`n0QK1
z6Hqy6R|-)2Sqw4##AgZFaB-pkgVe&k9-d~}m0sY@NjWlZIouq$3Q<u``jwETG%y74
zxVJtpN{uE+0dHhKBX@bULw=|)cY;2=c;p4XZ?9|KN~AAFXn2^eaUJE&;4{wgz4$&b
z%I`GMr7yoL!&l1DFfTLSgB7;FMK=Shy8+Qo#kqO{H8<?f1ca&G>+IRcc=+|=EBciY
zjstU+uJxL$5X+sCzgp8=28!NFFlI##^-P!1)-wci&W$w`3T36X{<Z*ypp?0!+GqN3
z!`24#!PnI42OzAF<Tv+EHU}=p!!u`#`$<Yf3C_=O{hF>!fnU#%ve`5ZzbN*(Bsx%o
z1eXsbJsz=(n(74>`G;TAU)9^rr1i{4A6iLsYV74kROFIc{K$O+w>y9WuxqpWMeI^p
zZ}hTXeaK$Rt33`o0tuZWQ{J0yGG_u6V#{MUf7Ad70W+5=DP{pi65HX;-SchQxuyKX
z0=q<hsP{OMJ~)5t058q4F_#;8t7zLYPj(qR$Bn0ngln|NUf?}G-cT5sm24&W_$`Zf
z-S$K+cdM01d|c#E06pirq6-9;C&&BjT*6Q_JvDP~cG0+**0=Uh-?a5DF-!40*%d)G
z<|b1H%odC=w&VKh)I(FwW8dQhpS7-@pIsNiTv|HsFYFT08UaWdY4U!_Z1<!)GAzt(
zr>W(*0+O=fQ;G;%%u&nUPYr0E1XO>Mui1zo`6W0f)<e=e!2Y)lyGp$!t??uFhhT5N
z>l%~#%Xi!LTtDH0Zfa8QIT?=_Ar6Af&mBAU?UhDVsJ>H`cV%g6kCUQtH`Y`cx=o56
zFg~swY-cpoi`|sYwUG1OHgUI?=t_j&OliuFIr|iLfibt+BNxe;Qg5!R@tPdh3AS?@
z`r{~`&c6_w?I^L^hkqqvVYX??gUOeWhzieMWF=Kgoe!49Z8@(MHLsS`H65BhcEc%8
z8p(Qwb7aMnvH|<!t<mEvBOM7tyT|4GH7Y%%w9aG7S%S4a<;I={h{IuK8C<z_n!wl-
z!P$UV^{S#Pds<=-sohp_8tOGuN*7<KqwbTs#IEB)Ha-#>TBK`e?!<QZ3dA1z<rAw<
zl}LRd?W}5Lvs<z|uX4lqzMecu1XiK;(nQjG9lr67)Vo&A2C@3z{*m+J$ekSD)-x@E
zlx>MU7khJ3lREvwczFd){c%82+|xIUihiW+JVy<w9waR%$|p~OLB{Ttx<W{o5$0W#
zDXj&^J==v{Wt>+NZNi*2JudK^5Z+!yt;F5w+<fw@Ja?`*pa?LF4CM4(VnrCy-CIL*
zYv2Bn8a*v4kV3dCS!`Z~3tiTH@vxA8XfG0EMZX?kN}#6$s#da_vY*Ljv3kqGpM}e!
zmTI>LWTz%5(hZVJHN>+cyRyC`h?H5=q%6}c;jWDIZfe_+sn(Aji^<->vL}SIlbiUS
zjEvfca(i3fvgJWWPf*@QnbCg14pyI|qRBPt+sP5bzFCntkks1pL})D8Si#%ymLy1?
zrMwX~w`!FDx+9H<KhJ&MOb3}+Eie3DF~wHd+912s5Oir|YgQ=&;KX^8Sf*P-`MgZ>
zj$jwDnuEia%a&qEOS50NhL~3@(=8UlmfG7)9K2T`?hic%L+A~Ud||)op;A(n*U7@(
z8=qg(O8O&2PxS{JOFzC)IP#~>$iZa=G8E%6m`b16=+h0ic&dgH7)v<@^G~(vtWyNf
zJn<M4E^aM2=U@$T@hXEAbWxbpW}Q0~rjw_t<BP6S)&zw29kxk#T1XHPv{lN=KoBAG
z_(@0RJ$}qdSbDAZ`K4Ra?h-Jv!87UY{!-q_=W-2um!uartwJ15GT$30>tEX)oM<&w
z=QZt??Dr)h<5gYySo-A!6m9HT2JVb>JgGncTc_mbQn37iR`k0z=cH@v-3GWmwgRD;
z`(6)WH*N*CE58kEe5b6uS#HVr;#QYe^|`Vc90Vcu!;t|VW~R6m(c5!b**AIWNmHQ%
zWx!n`2Y^QM^WmY!)T-SzIMHt&>=#)Tb!=!jd2#UBq&7gtrR7k}2;-rcqr_?D^?^F-
zwZ(k_9e-4wyivC?*#*U`sM`KGOpnzf%Jg+ayN&3LiK_b6x}R*(a|hIvs{zcH9x<dM
zM-?f?eg8b8hBn_0CA;CLEid2Wn^8cTRe%4-)`>EbMDIvP)_T+KCF4InxcG`Xbqz3c
zf;Ny-DMtx&#%mdEI-0e%E`hy2R1)5<Ypp`d{z>!zrfTLOYXFXW`C_zdCDH%i0&Pz#
zP^zv#PDTIy{|#^tZaBJZ+?|j*(dOCfVmC}_*^%vpLVG!EVWxY;kxELqb$lc1yz?@X
z2_N}gUVVy05qpBJlVd4o2rG37(u~EY4)G$<!7?oE{G}-YTL7?8R<LcXrHeKLlH$*9
zw~@UQ$5nm)xIb*(?StaQ#Nm!=Sy(wJxxl;H==~LX(@$nIn<%*49Yb4+AnK>hF)v_J
z%X%;lS1=BQ$X&n-PPAR<&9EDySMSJnVWY0?W<K+XCzT6z@Zg&in>~(@mESp%3J)zb
zKCsm}vv(@o4s}9FvT+st_~~I=qHknyt?|jP17~{+svt?4?|7fQ&@=-`S!D#ezO9V@
zosS*d_~~uUuIJK}-?}{?bO{*v@;2d>dSRt1#A;()9div+=QSHc<vmfZ*|X!qmBSNl
zj&w9w1ut`0d?=RAeY%dVtbW*aSa%V3G&?(_DZg<e4fgpDK%>0cKTiVaNaXeQq=v2Z
z*wc)YMB%T&yNoY>{rao7z`qg<<<7dz{ZKXV1vE({>m}}Rys6dsdz-KZulYN~pKjlI
zIkA6$4_d!f@dXor?%D#-B45&X+sf-dSOqw6Whyr=yQjZ?eJ%ZRpWna_kHnO8`=#IB
zz9{zKAdF}cY-LS9pwg@8iYR~b{{7EPm878=<ZIQG-`&HdOFwv7D6-(jN0Cf9rkneO
zGSwu$d}ojD1xJm;YyqbilC3OR&BZxu>7oZx&^~7{X|KqA*<WI1q?389J_;WsveX*(
z(01Sdl+rGgJuGVHKMJJYfGy07dmBTl>XG8b%LtOTZ@w?n>Ga%;bV1^RQK6(mjZ)EU
z|1cXm(g1zC?N<FL6Mcd417dndcdy5mR2}fvtKE0s*vGIaly+me8}Jhm1jH2eqr>#p
zjGKz-ol*y}8olFsG}B8UmS2&aJ=~Lr)|YHVu_P!8!^Tm{o*U0DDjW<sQ>iDaH+)`N
zyg4IVa*6oH(1BlH2nkXUo)cqa?wNUcNg>!j*{#?2*GGdrS*lLDbK6^Qe)5AV1bNbB
zZI$$6bzx8Nw3z=<&2`uknsS5g@L8}GpCY;VSkmzKF0fVR%OtAAk-q91@Zwbj4PJ@g
zlj(GeX-V?Q6c!vBY>o{47AZaU2$H)i3}<X@PW$7N9IW@4CwYSq1W%)yQAcSEtDJPb
zT4m@uXm!IPiVGRFz@+X>>+^c$7E*K-{ClU9?n8fQp#Hil_3{k)%|FF@GQ;1-k!r4t
zgy@~&nciU{N1cA^bg}OoQ$CfTPI(mdYepUrR1l=i)Ebw`cJ{coiSb=M-x{<2U`f+@
z4a^^m^ybEi?!5ucxzb~i(6(Kcl;@YzTqfSM%FrH_C;duUJzkvtxQ4H3wrk2yv*c%#
z-?C`Ov1$bIkBRI*%WU!QQKVMDWs@7*f{V;9P4(LR84qY)xaE0sC4vk+`YU2a)Of|*
zSP&?kd-Hdz^a=ziOcSS^CSdGmBpIT2u#-nleBFLH@AIU1c9&@90ylza%eB}4pij(x
zdnc2;P2g+T^JA87lno<UBK!v9wN?lcWJKq)-KC!#wJ0$D<kPc2<sE;*(``D1z<~T;
z1B$lwf9RrfR6s;v1@}1CJE9^NZQ7;8vwv&YFQaAb_$%^bTIL-M6><72(yF4H%`mbD
zjA%q##kPKut}$0_LX0=T8g0gHd0?)S+Hxwl#!`8<-r5jE&XTz(b_8RVKmYi+qAOoW
zCXZ30Gk@y^`BVP=gUKMUi@w-~C763Iys=&>EfB&NTBdx_rb|lq{h~(a(rN^8jTz|^
zq932D=_E|fWUJj34tjDZw@g3RdBVkG7LbhU720X~<UV#`=?`A4(I)au1MeqS0(6I}
ze@3;jjS%G7QB1O*DUGSs9=uTR`pJ;gawxZCGU5H0sMgYYF#qsvp9(z|bB5@06LUP_
z{NWm{3*Q58P6J@?vojP@p{dot){r7XOjp=|<e86u@)ndqC-!Zh!SmyU0-1Ltnf#;0
z@;h@ENXfhiB1j)@GrMXGNNS&Hw{7ohIZu$LcOi%a8K>*JE`e6Vji3Ei#`Q(~y&G*_
z5kb`KC`r0}wY`V1c1x=L`wM;v;;+`sV-SQG>(OVo&Ko}k1qk0r#TiM>dCZz4$l8Z0
zeIAuoe@<ZS7D0jc&V2TwU#}maFzurx7H-jx1}LP;eVIuso71iu{S55$*F})cinev_
z;YpPM95-B1A#%O&8p%@%QZEin8C(7aNRIp?=E<AWcYoIsMi3wKFmIEJ-mK%qP2q=5
zU&ZGH0$jAi1Duxc9#@`1*dENTsGgjengw`oHA_l@u9*5w{a}A;S@#0Qf8Ku?irb!4
zt1tMtWDeeJy5@(DdnS9zAV_LjPQj~=*gQijE3ja7P{j_7g=#H`KE=Y?+d3e_!-Y64
zDWD8sy~tHT=B1IBeV>O{kCQ5bR-uEMikxI^z+^&R1h&Hy$wKke$}W&o3vw)Tase`6
z(e*Tncm@x#wQXnOb^JClYy-EAPTOHeEclUqrj#eTgKAFiLW(Mcxl0BcdrDvnhfIzw
z$Q$SL+rs!`C<ypmP^u2odE~7R#f}?4EWC1rJ#ek_9D>BqzqHx@an=_c|0=!GABD2b
zC*#znt+lLa!9^oVh%j#O8ZcHPpXlXn_CF5k3yr_D;w1qLZV4<k$!Q_@pcwpIYt?d7
zfK=r`b5BVbf-utj@Ik?6=33t^*IbdRL<i$@Hkf!5R}#6jc-bWAl0Ik6rFI9W5>>Aa
zz^E%>8bkO^`^MMq5>=o&7QNL62qWaNG38O1wt;@IM5QR0P?nRdags;^u)~V$BiGOX
z9iV6HRc056Fx1fCIBaE}mg=E?TkW;k5^4*}i=9#L{mygi2q=NE(}yq*O<Htz1xthu
zN}}L@K}_;-e4K48Ffam-AyO7h&(!-Gx&2>b2bssDTn5AcHI|Os7L{|w;9p}WF>zHb
z>f&Gw_3ZUd$*(;{$^76M+LRj~jWD7+4&9Ln>qhHkVc{}vs;UGOZCBB$<V%_cp1i36
z*xvF-U`+<qJV%KMBVhQ0C5#6<dr%Q(+D`oIDsK=$fk}~@@vsczgkV%wvf3#i065@7
z1p7H5&>@TCvuIJOR7W*bv=qL6C=3HW@}GC%jwFI4nqZ<$3h_9skdq)>1crLz$^7_y
zdn;gkK$8qfM!!nac2ON)>_*XF5$$-KY}E8{<|-Y5y?{^*6;O&5VvIq}72)5m6r40K
z1jX${)J~{sol<)h)Oj<CR#@iE+%E+zoBMiTR}QkxoM|j&4qu^0h@FMWxG6+y%i|t2
z^bO`N<JwTC%{H9+iduw?Z-eS@CjIj@eq1J4VvZlkbRg#&>2LII%Y=2van|zM1-M<p
zfI9x}NF?fjrD}UkJD*qojwX(3js>r`XRrijO)p1vCB3>WUM4K?Ij3g%!MHus3e=Q%
zcaAFTS=27B_Uczi;;23__4NkaWQ<uKM^&Bvr|q6hm;rt7QvBbZH{1p-`rqHp>0>~{
z5~f1my(Fv8hag9`CDA6ib=XA9F%~@shWs@83fsd(BVp$HWfgsX5KvC4|H!R_BdUx^
z(;GnG2VKzCoM^<$T(`VkA4a7kDz@M6aO*T$_|B*@@4@sYM3=M$xc6dQ*fP*hAV|NQ
zEgevx|3|<8RzgNZqXJxLr>WH{1i{5bGS>u4d`;WAU`*HnV|xP5GEbBNhP$=s$6>}@
zB>PdG$b@+@*T4?*8nC$Cwh@45<1DOa-mqaT*k=t(eK~5%Im{=|v_6=-F&5U>xv)Zi
z=psut1Q^VpmEulG1J3$6OvO!e8UX)=M+*(Y(X%*<uo+>d8#wJqcMAwdi&(czByqz~
zxkIwaWVP3}cz8f$nt?zzJV^sRqZf1IKLWejn+o|j0)GQnk;d-_=;f32U4J91W{1h1
z7GWGwZT~GzkA=YTF{vF;?PA=6o2IbugE*5l`~aH!zZHnE!}bP^bmTup#^KyNq1{9N
zRbY^9{6w)rl4P3&Bf>fak=btBDh`<-E7{XYM!^Z+(~B1YHCGB6_b>rEiHx#j8w&*F
zZ2u9U)2kPs{!cap6~qFof;14Mqd3=Pof#?s4xB{xM*Bfo7`&(g%7J)X6g)2>Gb*+n
zR$xkzGYBDprm!`K@~LwWr-PE|V~ckoVbO8pkbF|7J)|}Y>RP4;pli@_9q1q5WNo{W
zp%3l{gzhqKx?rFQu>$%Ff+!N-j-q1{I^e3^g0z9L4M3j}MAS5F#wu8X2VDZHh2ZW3
zRKDZ0@0`)6D;pOM`~;4P-JCws^#lM~{^`$pboj{;cv2BW1GrcP&=215A#{v0Ja_HI
z3RwV{A)+RY72@Z7kjDze$FD|*8HB~>m7i<M86=wb5i8Q}1fPomcX@&(RFpTO<1eDQ
zmT~nA>UOUpwfi}z#+Jm2gWDlUkCSA=0Mr6Z12+986pyrvn_CCyDtO_A0I2Dp`gOo2
z3%mlbK!bs|={YI{be8Atqe2rPv=tSy1cqWjxCWsO;9CkRbOMAz<v<APa#aL%pw5_B
zv3DCP1n{hz&?&IX9fWS9LOCELhzeOkl=pHhp+aNoaq!rP90F$8$?Kef6@ipHcP^PT
z>efR=($J~kF=WwBbc#^h4L)uK%MO<y0xyqqa^Zy>wfiXnAo!sib@=&(4d>@=3e;`@
z2ZzBM2AIoC&d7#bf_TP6a@yz_WZobe@2fjN>A4F>sUM=T0XKXNjlC_v6_(chl?4=b
zrKUm@4H{uXag7|i;Fahgyl;VOVb(FOo?7J0$NQ{<B`n?caoVgO26CoAH9E%tE~1zA
z6YO7e(9e|AcT}O%LbwdITbT#$@Pqd&xOEagQ6&IG5m5sq!C67h1dTYY_IljfFM&=(
zYA`6=i(qm50}!^yC*?Rk3BYu3{)7`WwHTQ&=4~$&cfQOaSfV#(kW;!7pVwnkwZFoU
zwqmH$KOwQ#eMf<Z5jDUZHba{Q=o-Sdb3R1Lgz+8Vfa>mpzJyNh2qY5`oxU8721~qu
z&q;h4Q=(BE>N_;wYBbjXFI5N-*b(HBB2^Y$FO~h`*165Gm>?6j7BzEOltDxj&A}~L
z;uso9;L<VTBpkH1DcbF_V8-5!8aV|<jN$pM>?^kp;Ln49K-en*kBA7rC}S;}(hj!4
z62YIfVfg?c*D+$?$ptX7?l%~Lnfa(WYGf-_*77bGxzDZhEoDdkLy%5{xez~d#RDv&
zGy+Hvf_jFmKnq1U3n_#fEe~0ZrU<eYh5SWi&}|1~U(kOP{u8DDq{e^x!+%DN{|uG?
inIHbYC&jL1F2w@}XUm)_;b{v&%nn)}c)Q;r_`d)jjOKp;


From cb2d8fe085427e904e360c3497dfd1c1927666e9 Mon Sep 17 00:00:00 2001
From: Junhwa Song <ethan9867@gmail.com>
Date: Wed, 15 Mar 2023 20:36:47 +0900
Subject: [PATCH 17/32] [Enhance] Support multi-band image for Mosaic (#2748)

## Modification

I changed the hardcoded 3 channel length to dynamic channel length in
`np.full` function arguments.
This modification enables `RandomMosaic` transform to support
multispectral image (e.g. RGB image with NIR band) or bi-temporal image
pairs for change detection task.

## Checklist

1. Pre-commit or other linting tools are used to fix the potential lint
issues.
2. The modification is covered by complete unit tests. If not, please
add more unit test to ensure the correctness.
3. If the modification has potential influence on downstream projects,
this PR should be tested with downstream projects, like MMDet or
MMDet3D.
4. The documentation has been modified accordingly, like docstring or
example tutorials.
---
 mmseg/datasets/transforms/transforms.py |  3 ++-
 tests/test_datasets/test_transform.py   | 11 +++++++++++
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/mmseg/datasets/transforms/transforms.py b/mmseg/datasets/transforms/transforms.py
index 4f5316026f..fb7e2a0e66 100644
--- a/mmseg/datasets/transforms/transforms.py
+++ b/mmseg/datasets/transforms/transforms.py
@@ -1062,8 +1062,9 @@ def _mosaic_transform_img(self, results: dict) -> dict:
 
         assert 'mix_results' in results
         if len(results['img'].shape) == 3:
+            c = results['img'].shape[2]
             mosaic_img = np.full(
-                (int(self.img_scale[0] * 2), int(self.img_scale[1] * 2), 3),
+                (int(self.img_scale[0] * 2), int(self.img_scale[1] * 2), c),
                 self.pad_val,
                 dtype=results['img'].dtype)
         else:
diff --git a/tests/test_datasets/test_transform.py b/tests/test_datasets/test_transform.py
index a9136bebc8..92d6c6106d 100644
--- a/tests/test_datasets/test_transform.py
+++ b/tests/test_datasets/test_transform.py
@@ -639,6 +639,17 @@ def test_mosaic():
     results = mosaic_module(results)
     assert results['img'].shape[:2] == (20, 24)
 
+    results = dict()
+    results['img'] = np.concatenate((img, img), axis=2)
+    results['gt_semantic_seg'] = seg
+    results['seg_fields'] = ['gt_semantic_seg']
+
+    transform = dict(type='RandomMosaic', prob=1, img_scale=(10, 12))
+    mosaic_module = TRANSFORMS.build(transform)
+    results['mix_results'] = [copy.deepcopy(results)] * 3
+    results = mosaic_module(results)
+    assert results['img'].shape[2] == 6
+
 
 def test_cutout():
     # test prob

From ff8d9719886a1ff0a5302027152173514573c9ce Mon Sep 17 00:00:00 2001
From: MengzhangLI <mcmong@pku.edu.cn>
Date: Thu, 16 Mar 2023 16:49:15 +0800
Subject: [PATCH 18/32] [Feature] Support SegNeXt in MMSegmentation 2.0 (#2654)

## Motivation

Support SegNeXt in MMSeg 1.x branch.

0.x PR: https://github.com/open-mmlab/mmsegmentation/pull/2600

---------

Co-authored-by: xiexinch <xiexinch@outlook.com>
---
 README.md                                     |   1 +
 README_zh-CN.md                               |   1 +
 configs/segnext/README.md                     |  63 +++
 configs/segnext/segnext.yml                   | 103 ++++
 ...mscan-b_1xb16-adamw-160k_ade20k-512x512.py |  28 ++
 ...mscan-l_1xb16-adamw-160k_ade20k-512x512.py |  27 +
 ...mscan-s_1xb16-adamw-160k_ade20k-512x512.py |  27 +
 ...mscan-t_1xb16-adamw-160k_ade20k-512x512.py |  84 ++++
 mmseg/models/backbones/__init__.py            |   3 +-
 mmseg/models/backbones/mscan.py               | 467 ++++++++++++++++++
 mmseg/models/decode_heads/__init__.py         |   3 +-
 mmseg/models/decode_heads/ham_head.py         | 257 ++++++++++
 model-index.yml                               |   1 +
 .../test_models/test_backbones/test_mscan.py  |  69 +++
 tests/test_models/test_heads/test_ham_head.py |  44 ++
 15 files changed, 1176 insertions(+), 2 deletions(-)
 create mode 100644 configs/segnext/README.md
 create mode 100644 configs/segnext/segnext.yml
 create mode 100644 configs/segnext/segnext_mscan-b_1xb16-adamw-160k_ade20k-512x512.py
 create mode 100644 configs/segnext/segnext_mscan-l_1xb16-adamw-160k_ade20k-512x512.py
 create mode 100644 configs/segnext/segnext_mscan-s_1xb16-adamw-160k_ade20k-512x512.py
 create mode 100644 configs/segnext/segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512.py
 create mode 100644 mmseg/models/backbones/mscan.py
 create mode 100644 mmseg/models/decode_heads/ham_head.py
 create mode 100644 tests/test_models/test_backbones/test_mscan.py
 create mode 100644 tests/test_models/test_heads/test_ham_head.py

diff --git a/README.md b/README.md
index 69f751b9e5..a17557cb81 100644
--- a/README.md
+++ b/README.md
@@ -117,6 +117,7 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
 - [x] [ConvNeXt (CVPR'2022)](configs/convnext)
 - [x] [MAE (CVPR'2022)](configs/mae)
 - [x] [PoolFormer (CVPR'2022)](configs/poolformer)
+- [x] [SegNeXt (NeurIPS'2022)](configs/segnext)
 
 </details>
 
diff --git a/README_zh-CN.md b/README_zh-CN.md
index 709e6ef195..e09b515ab5 100644
--- a/README_zh-CN.md
+++ b/README_zh-CN.md
@@ -98,6 +98,7 @@ MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 O
 - [x] [ConvNeXt (CVPR'2022)](configs/convnext)
 - [x] [MAE (CVPR'2022)](configs/mae)
 - [x] [PoolFormer (CVPR'2022)](configs/poolformer)
+- [x] [SegNeXt (NeurIPS'2022)](configs/segnext)
 
 </details>
 
diff --git a/configs/segnext/README.md b/configs/segnext/README.md
new file mode 100644
index 0000000000..315f4e23e8
--- /dev/null
+++ b/configs/segnext/README.md
@@ -0,0 +1,63 @@
+# SegNeXt
+
+> [SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation](https://arxiv.org/abs/2209.08575)
+
+## Introduction
+
+<!-- [ALGORITHM] -->
+
+<a href="https://github.com/visual-attention-network/segnext">Official Repo</a>
+
+<a href="https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/mscan.py#L328">Code Snippet</a>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+We present SegNeXt, a simple convolutional network architecture for semantic segmentation. Recent transformer-based models have dominated the field of semantic segmentation due to the efficiency of self-attention in encoding spatial information. In this paper, we show that convolutional attention is a more efficient and effective way to encode contextual information than the self-attention mechanism in transformers. By re-examining the characteristics owned by successful segmentation models, we discover several key components leading to the performance improvement of segmentation models. This motivates us to design a novel convolutional attention network that uses cheap convolutional operations. Without bells and whistles, our SegNeXt significantly improves the performance of previous state-of-the-art methods on popular benchmarks, including ADE20K, Cityscapes, COCO-Stuff, Pascal VOC, Pascal Context, and iSAID. Notably, SegNeXt outperforms EfficientNet-L2 w/ NAS-FPN and achieves 90.6% mIoU on the Pascal VOC 2012 test leaderboard using only 1/10 parameters of it. On average, SegNeXt achieves about 2.0% mIoU improvements compared to the state-of-the-art methods on the ADE20K datasets with the same or fewer computations. Code is available at [this https URL](https://github.com/uyzhang/JSeg) (Jittor) and [this https URL](https://github.com/Visual-Attention-Network/SegNeXt) (Pytorch).
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/24582831/215688018-5d4c8366-7793-4fdf-9397-960a09fac951.png" width="70%"/>
+</div>
+
+## Results and models
+
+### ADE20K
+
+| Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) | config                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                                                   |
+| ------- | -------- | --------- | ------- | -------- | -------------- | ----- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| SegNeXt | MSCAN-T  | 512x512   | 160000  | 17.88    | 52.38          | 41.50 | 42.59         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segnext/segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k_20230210_140244-05bd8466.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k_20230210_140244.log.json) |
+| SegNeXt | MSCAN-S  | 512x512   | 160000  | 21.47    | 42.27          | 44.16 | 45.81         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segnext/segnext_mscan-s_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k_20230214_113014-43013668.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k_20230214_113014.log.json) |
+| SegNeXt | MSCAN-B  | 512x512   | 160000  | 31.03    | 35.15          | 48.03 | 49.68         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segnext/segnext_mscan-b_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k_20230209_172053-b6f6c70c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k_20230209_172053.log.json) |
+| SegNeXt | MSCAN-L  | 512x512   | 160000  | 43.32    | 22.91          | 50.99 | 52.10         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segnext/segnext_mscan-l_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k_20230209_172055-19b14b63.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k_20230209_172055.log.json) |
+
+Note:
+
+- When we integrated SegNeXt into MMSegmentation, we modified some layers' names to make them more precise and concise without changing the model architecture. Therefore, the keys of pre-trained weights are different from the [original weights](https://cloud.tsinghua.edu.cn/d/c15b25a6745946618462/), but don't worry about these changes. we have converted them and uploaded the checkpoints, you might find URL of pre-trained checkpoints in config files and can use them directly for training.
+
+- The total batch size is 16. We trained for SegNeXt with a single GPU as the performance degrades significantly when using`SyncBN` (mainly in `OverlapPatchEmbed` modules of `MSCAN`) of PyTorch 1.9.
+
+- There will be subtle differences when model testing as Non-negative Matrix Factorization (NMF) in `LightHamHead` will be initialized randomly. To control this randomness, please set the random seed when model testing. You can modify [`./tools/test.py`](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/tools/test.py) like:
+
+```python
+def main():
+    from mmengine.runner import seg_random_seed
+    random_seed = xxx # set random seed recorded in training log
+    set_random_seed(random_seed, deterministic=False)
+    ...
+```
+
+- This model performance is sensitive to the seed values used, please refer to the log file for the specific settings of the seed. If you choose a different seed, the results might differ from the table results. Take SegNeXt Large for example, its results range from 49.60 to 51.0.
+
+## Citation
+
+```bibtex
+@article{guo2022segnext,
+  title={SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation},
+  author={Guo, Meng-Hao and Lu, Cheng-Ze and Hou, Qibin and Liu, Zhengning and Cheng, Ming-Ming and Hu, Shi-Min},
+  journal={arXiv preprint arXiv:2209.08575},
+  year={2022}
+}
+```
diff --git a/configs/segnext/segnext.yml b/configs/segnext/segnext.yml
new file mode 100644
index 0000000000..3bcdea8403
--- /dev/null
+++ b/configs/segnext/segnext.yml
@@ -0,0 +1,103 @@
+Collections:
+- Name: SegNeXt
+  Metadata:
+    Training Data:
+    - ADE20K
+  Paper:
+    URL: https://arxiv.org/abs/2209.08575
+    Title: 'SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation'
+  README: configs/segnext/README.md
+  Code:
+    URL: https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/mscan.py#L328
+    Version: dev-1.x
+  Converted From:
+    Code: https://github.com/visual-attention-network/segnext
+Models:
+- Name: segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512
+  In Collection: SegNeXt
+  Metadata:
+    backbone: MSCAN-T
+    crop size: (512,512)
+    lr schd: 160000
+    inference time (ms/im):
+    - value: 19.09
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    Training Memory (GB): 17.88
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 41.5
+      mIoU(ms+flip): 42.59
+  Config: configs/segnext/segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k_20230210_140244-05bd8466.pth
+- Name: segnext_mscan-s_1xb16-adamw-160k_ade20k-512x512
+  In Collection: SegNeXt
+  Metadata:
+    backbone: MSCAN-S
+    crop size: (512,512)
+    lr schd: 160000
+    inference time (ms/im):
+    - value: 23.66
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    Training Memory (GB): 21.47
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 44.16
+      mIoU(ms+flip): 45.81
+  Config: configs/segnext/segnext_mscan-s_1xb16-adamw-160k_ade20k-512x512.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k_20230214_113014-43013668.pth
+- Name: segnext_mscan-b_1xb16-adamw-160k_ade20k-512x512
+  In Collection: SegNeXt
+  Metadata:
+    backbone: MSCAN-B
+    crop size: (512,512)
+    lr schd: 160000
+    inference time (ms/im):
+    - value: 28.45
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    Training Memory (GB): 31.03
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 48.03
+      mIoU(ms+flip): 49.68
+  Config: configs/segnext/segnext_mscan-b_1xb16-adamw-160k_ade20k-512x512.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k_20230209_172053-b6f6c70c.pth
+- Name: segnext_mscan-l_1xb16-adamw-160k_ade20k-512x512
+  In Collection: SegNeXt
+  Metadata:
+    backbone: MSCAN-L
+    crop size: (512,512)
+    lr schd: 160000
+    inference time (ms/im):
+    - value: 43.65
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    Training Memory (GB): 43.32
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 50.99
+      mIoU(ms+flip): 52.1
+  Config: configs/segnext/segnext_mscan-l_1xb16-adamw-160k_ade20k-512x512.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k_20230209_172055-19b14b63.pth
diff --git a/configs/segnext/segnext_mscan-b_1xb16-adamw-160k_ade20k-512x512.py b/configs/segnext/segnext_mscan-b_1xb16-adamw-160k_ade20k-512x512.py
new file mode 100644
index 0000000000..000f448483
--- /dev/null
+++ b/configs/segnext/segnext_mscan-b_1xb16-adamw-160k_ade20k-512x512.py
@@ -0,0 +1,28 @@
+_base_ = './segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512.py'
+
+# model settings
+checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segnext/mscan_b_20230227-3ab7d230.pth'  # noqa
+ham_norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    backbone=dict(
+        embed_dims=[64, 128, 320, 512],
+        depths=[3, 3, 12, 3],
+        init_cfg=dict(type='Pretrained', checkpoint=checkpoint_file),
+        drop_path_rate=0.1,
+        norm_cfg=dict(type='BN', requires_grad=True)),
+    decode_head=dict(
+        type='LightHamHead',
+        in_channels=[128, 320, 512],
+        in_index=[1, 2, 3],
+        channels=512,
+        ham_channels=512,
+        dropout_ratio=0.1,
+        num_classes=150,
+        norm_cfg=ham_norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))
diff --git a/configs/segnext/segnext_mscan-l_1xb16-adamw-160k_ade20k-512x512.py b/configs/segnext/segnext_mscan-l_1xb16-adamw-160k_ade20k-512x512.py
new file mode 100644
index 0000000000..212d0a8557
--- /dev/null
+++ b/configs/segnext/segnext_mscan-l_1xb16-adamw-160k_ade20k-512x512.py
@@ -0,0 +1,27 @@
+_base_ = './segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512.py'
+# model settings
+checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segnext/mscan_l_20230227-cef260d4.pth'  # noqa
+ham_norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    backbone=dict(
+        embed_dims=[64, 128, 320, 512],
+        depths=[3, 5, 27, 3],
+        init_cfg=dict(type='Pretrained', checkpoint=checkpoint_file),
+        drop_path_rate=0.3,
+        norm_cfg=dict(type='BN', requires_grad=True)),
+    decode_head=dict(
+        type='LightHamHead',
+        in_channels=[128, 320, 512],
+        in_index=[1, 2, 3],
+        channels=1024,
+        ham_channels=1024,
+        dropout_ratio=0.1,
+        num_classes=150,
+        norm_cfg=ham_norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))
diff --git a/configs/segnext/segnext_mscan-s_1xb16-adamw-160k_ade20k-512x512.py b/configs/segnext/segnext_mscan-s_1xb16-adamw-160k_ade20k-512x512.py
new file mode 100644
index 0000000000..9a90779a60
--- /dev/null
+++ b/configs/segnext/segnext_mscan-s_1xb16-adamw-160k_ade20k-512x512.py
@@ -0,0 +1,27 @@
+_base_ = './segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512.py'
+# model settings
+checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segnext/mscan_s_20230227-f33ccdf2.pth'  # noqa
+ham_norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    backbone=dict(
+        embed_dims=[64, 128, 320, 512],
+        depths=[2, 2, 4, 2],
+        init_cfg=dict(type='Pretrained', checkpoint=checkpoint_file),
+        norm_cfg=dict(type='BN', requires_grad=True)),
+    decode_head=dict(
+        type='LightHamHead',
+        in_channels=[128, 320, 512],
+        in_index=[1, 2, 3],
+        channels=256,
+        ham_channels=256,
+        ham_kwargs=dict(MD_R=16),
+        dropout_ratio=0.1,
+        num_classes=150,
+        norm_cfg=ham_norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))
diff --git a/configs/segnext/segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512.py b/configs/segnext/segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512.py
new file mode 100644
index 0000000000..c8d6da85ff
--- /dev/null
+++ b/configs/segnext/segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512.py
@@ -0,0 +1,84 @@
+_base_ = [
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py',
+    '../_base_/datasets/ade20k.py'
+]
+# model settings
+checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segnext/mscan_t_20230227-119e8c9f.pth'  # noqa
+ham_norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+crop_size = (512, 512)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255,
+    size=(512, 512),
+    test_cfg=dict(size_divisor=32))
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    pretrained=None,
+    backbone=dict(
+        type='MSCAN',
+        init_cfg=dict(type='Pretrained', checkpoint=checkpoint_file),
+        embed_dims=[32, 64, 160, 256],
+        mlp_ratios=[8, 8, 4, 4],
+        drop_rate=0.0,
+        drop_path_rate=0.1,
+        depths=[3, 3, 5, 2],
+        attention_kernel_sizes=[5, [1, 7], [1, 11], [1, 21]],
+        attention_kernel_paddings=[2, [0, 3], [0, 5], [0, 10]],
+        act_cfg=dict(type='GELU'),
+        norm_cfg=dict(type='BN', requires_grad=True)),
+    decode_head=dict(
+        type='LightHamHead',
+        in_channels=[64, 160, 256],
+        in_index=[1, 2, 3],
+        channels=256,
+        ham_channels=256,
+        dropout_ratio=0.1,
+        num_classes=150,
+        norm_cfg=ham_norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+        ham_kwargs=dict(
+            MD_S=1,
+            MD_R=16,
+            train_steps=6,
+            eval_steps=7,
+            inv_t=100,
+            rand_init=True)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))
+
+# dataset settings
+train_dataloader = dict(batch_size=16)
+
+# optimizer
+optim_wrapper = dict(
+    _delete_=True,
+    type='OptimWrapper',
+    optimizer=dict(
+        type='AdamW', lr=0.00006, betas=(0.9, 0.999), weight_decay=0.01),
+    paramwise_cfg=dict(
+        custom_keys={
+            'pos_block': dict(decay_mult=0.),
+            'norm': dict(decay_mult=0.),
+            'head': dict(lr_mult=10.)
+        }))
+
+param_scheduler = [
+    dict(
+        type='LinearLR', start_factor=1e-6, by_epoch=False, begin=0, end=1500),
+    dict(
+        type='PolyLR',
+        power=1.0,
+        begin=1500,
+        end=160000,
+        eta_min=0.0,
+        by_epoch=False,
+    )
+]
diff --git a/mmseg/models/backbones/__init__.py b/mmseg/models/backbones/__init__.py
index 909b54f3ec..e3107306ea 100644
--- a/mmseg/models/backbones/__init__.py
+++ b/mmseg/models/backbones/__init__.py
@@ -11,6 +11,7 @@
 from .mit import MixVisionTransformer
 from .mobilenet_v2 import MobileNetV2
 from .mobilenet_v3 import MobileNetV3
+from .mscan import MSCAN
 from .pidnet import PIDNet
 from .resnest import ResNeSt
 from .resnet import ResNet, ResNetV1c, ResNetV1d
@@ -27,5 +28,5 @@
     'ResNeSt', 'MobileNetV2', 'UNet', 'CGNet', 'MobileNetV3',
     'VisionTransformer', 'SwinTransformer', 'MixVisionTransformer',
     'BiSeNetV1', 'BiSeNetV2', 'ICNet', 'TIMMBackbone', 'ERFNet', 'PCPVT',
-    'SVT', 'STDCNet', 'STDCContextPathNet', 'BEiT', 'MAE', 'PIDNet'
+    'SVT', 'STDCNet', 'STDCContextPathNet', 'BEiT', 'MAE', 'PIDNet', 'MSCAN'
 ]
diff --git a/mmseg/models/backbones/mscan.py b/mmseg/models/backbones/mscan.py
new file mode 100644
index 0000000000..7150cb7a1c
--- /dev/null
+++ b/mmseg/models/backbones/mscan.py
@@ -0,0 +1,467 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+# Originally from https://github.com/visual-attention-network/segnext
+# Licensed under the Apache License, Version 2.0 (the "License")
+import math
+import warnings
+
+import torch
+import torch.nn as nn
+from mmcv.cnn import build_activation_layer, build_norm_layer
+from mmcv.cnn.bricks import DropPath
+from mmengine.model import BaseModule
+from mmengine.model.weight_init import (constant_init, normal_init,
+                                        trunc_normal_init)
+
+from mmseg.registry import MODELS
+
+
+class Mlp(BaseModule):
+    """Multi Layer Perceptron (MLP) Module.
+
+    Args:
+        in_features (int): The dimension of input features.
+        hidden_features (int): The dimension of hidden features.
+            Defaults: None.
+        out_features (int): The dimension of output features.
+            Defaults: None.
+        act_cfg (dict): Config dict for activation layer in block.
+            Default: dict(type='GELU').
+        drop (float): The number of dropout rate in MLP block.
+            Defaults: 0.0.
+    """
+
+    def __init__(self,
+                 in_features,
+                 hidden_features=None,
+                 out_features=None,
+                 act_cfg=dict(type='GELU'),
+                 drop=0.):
+        super().__init__()
+        out_features = out_features or in_features
+        hidden_features = hidden_features or in_features
+        self.fc1 = nn.Conv2d(in_features, hidden_features, 1)
+        self.dwconv = nn.Conv2d(
+            hidden_features,
+            hidden_features,
+            3,
+            1,
+            1,
+            bias=True,
+            groups=hidden_features)
+        self.act = build_activation_layer(act_cfg)
+        self.fc2 = nn.Conv2d(hidden_features, out_features, 1)
+        self.drop = nn.Dropout(drop)
+
+    def forward(self, x):
+        """Forward function."""
+
+        x = self.fc1(x)
+
+        x = self.dwconv(x)
+        x = self.act(x)
+        x = self.drop(x)
+        x = self.fc2(x)
+        x = self.drop(x)
+
+        return x
+
+
+class StemConv(BaseModule):
+    """Stem Block at the beginning of Semantic Branch.
+
+    Args:
+        in_channels (int): The dimension of input channels.
+        out_channels (int): The dimension of output channels.
+        act_cfg (dict): Config dict for activation layer in block.
+            Default: dict(type='GELU').
+        norm_cfg (dict): Config dict for normalization layer.
+            Defaults: dict(type='SyncBN', requires_grad=True).
+    """
+
+    def __init__(self,
+                 in_channels,
+                 out_channels,
+                 act_cfg=dict(type='GELU'),
+                 norm_cfg=dict(type='SyncBN', requires_grad=True)):
+        super().__init__()
+
+        self.proj = nn.Sequential(
+            nn.Conv2d(
+                in_channels,
+                out_channels // 2,
+                kernel_size=(3, 3),
+                stride=(2, 2),
+                padding=(1, 1)),
+            build_norm_layer(norm_cfg, out_channels // 2)[1],
+            build_activation_layer(act_cfg),
+            nn.Conv2d(
+                out_channels // 2,
+                out_channels,
+                kernel_size=(3, 3),
+                stride=(2, 2),
+                padding=(1, 1)),
+            build_norm_layer(norm_cfg, out_channels)[1],
+        )
+
+    def forward(self, x):
+        """Forward function."""
+
+        x = self.proj(x)
+        _, _, H, W = x.size()
+        x = x.flatten(2).transpose(1, 2)
+        return x, H, W
+
+
+class MSCAAttention(BaseModule):
+    """Attention Module in Multi-Scale Convolutional Attention Module (MSCA).
+
+    Args:
+        channels (int): The dimension of channels.
+        kernel_sizes (list): The size of attention
+            kernel. Defaults: [5, [1, 7], [1, 11], [1, 21]].
+        paddings (list): The number of
+            corresponding padding value in attention module.
+            Defaults: [2, [0, 3], [0, 5], [0, 10]].
+    """
+
+    def __init__(self,
+                 channels,
+                 kernel_sizes=[5, [1, 7], [1, 11], [1, 21]],
+                 paddings=[2, [0, 3], [0, 5], [0, 10]]):
+        super().__init__()
+        self.conv0 = nn.Conv2d(
+            channels,
+            channels,
+            kernel_size=kernel_sizes[0],
+            padding=paddings[0],
+            groups=channels)
+        for i, (kernel_size,
+                padding) in enumerate(zip(kernel_sizes[1:], paddings[1:])):
+            kernel_size_ = [kernel_size, kernel_size[::-1]]
+            padding_ = [padding, padding[::-1]]
+            conv_name = [f'conv{i}_1', f'conv{i}_2']
+            for i_kernel, i_pad, i_conv in zip(kernel_size_, padding_,
+                                               conv_name):
+                self.add_module(
+                    i_conv,
+                    nn.Conv2d(
+                        channels,
+                        channels,
+                        tuple(i_kernel),
+                        padding=i_pad,
+                        groups=channels))
+        self.conv3 = nn.Conv2d(channels, channels, 1)
+
+    def forward(self, x):
+        """Forward function."""
+
+        u = x.clone()
+
+        attn = self.conv0(x)
+
+        # Multi-Scale Feature extraction
+        attn_0 = self.conv0_1(attn)
+        attn_0 = self.conv0_2(attn_0)
+
+        attn_1 = self.conv1_1(attn)
+        attn_1 = self.conv1_2(attn_1)
+
+        attn_2 = self.conv2_1(attn)
+        attn_2 = self.conv2_2(attn_2)
+
+        attn = attn + attn_0 + attn_1 + attn_2
+        # Channel Mixing
+        attn = self.conv3(attn)
+
+        # Convolutional Attention
+        x = attn * u
+
+        return x
+
+
+class MSCASpatialAttention(BaseModule):
+    """Spatial Attention Module in Multi-Scale Convolutional Attention Module
+    (MSCA).
+
+    Args:
+        in_channels (int): The dimension of channels.
+        attention_kernel_sizes (list): The size of attention
+            kernel. Defaults: [5, [1, 7], [1, 11], [1, 21]].
+        attention_kernel_paddings (list): The number of
+            corresponding padding value in attention module.
+            Defaults: [2, [0, 3], [0, 5], [0, 10]].
+        act_cfg (dict): Config dict for activation layer in block.
+            Default: dict(type='GELU').
+    """
+
+    def __init__(self,
+                 in_channels,
+                 attention_kernel_sizes=[5, [1, 7], [1, 11], [1, 21]],
+                 attention_kernel_paddings=[2, [0, 3], [0, 5], [0, 10]],
+                 act_cfg=dict(type='GELU')):
+        super().__init__()
+        self.proj_1 = nn.Conv2d(in_channels, in_channels, 1)
+        self.activation = build_activation_layer(act_cfg)
+        self.spatial_gating_unit = MSCAAttention(in_channels,
+                                                 attention_kernel_sizes,
+                                                 attention_kernel_paddings)
+        self.proj_2 = nn.Conv2d(in_channels, in_channels, 1)
+
+    def forward(self, x):
+        """Forward function."""
+
+        shorcut = x.clone()
+        x = self.proj_1(x)
+        x = self.activation(x)
+        x = self.spatial_gating_unit(x)
+        x = self.proj_2(x)
+        x = x + shorcut
+        return x
+
+
+class MSCABlock(BaseModule):
+    """Basic Multi-Scale Convolutional Attention Block. It leverage the large-
+    kernel attention (LKA) mechanism to build both channel and spatial
+    attention. In each branch, it uses two depth-wise strip convolutions to
+    approximate standard depth-wise convolutions with large kernels. The kernel
+    size for each branch is set to 7, 11, and 21, respectively.
+
+    Args:
+        channels (int): The dimension of channels.
+        attention_kernel_sizes (list): The size of attention
+            kernel. Defaults: [5, [1, 7], [1, 11], [1, 21]].
+        attention_kernel_paddings (list): The number of
+            corresponding padding value in attention module.
+            Defaults: [2, [0, 3], [0, 5], [0, 10]].
+        mlp_ratio (float): The ratio of multiple input dimension to
+            calculate hidden feature in MLP layer. Defaults: 4.0.
+        drop (float): The number of dropout rate in MLP block.
+            Defaults: 0.0.
+        drop_path (float): The ratio of drop paths.
+            Defaults: 0.0.
+        act_cfg (dict): Config dict for activation layer in block.
+            Default: dict(type='GELU').
+        norm_cfg (dict): Config dict for normalization layer.
+            Defaults: dict(type='SyncBN', requires_grad=True).
+    """
+
+    def __init__(self,
+                 channels,
+                 attention_kernel_sizes=[5, [1, 7], [1, 11], [1, 21]],
+                 attention_kernel_paddings=[2, [0, 3], [0, 5], [0, 10]],
+                 mlp_ratio=4.,
+                 drop=0.,
+                 drop_path=0.,
+                 act_cfg=dict(type='GELU'),
+                 norm_cfg=dict(type='SyncBN', requires_grad=True)):
+        super().__init__()
+        self.norm1 = build_norm_layer(norm_cfg, channels)[1]
+        self.attn = MSCASpatialAttention(channels, attention_kernel_sizes,
+                                         attention_kernel_paddings, act_cfg)
+        self.drop_path = DropPath(
+            drop_path) if drop_path > 0. else nn.Identity()
+        self.norm2 = build_norm_layer(norm_cfg, channels)[1]
+        mlp_hidden_channels = int(channels * mlp_ratio)
+        self.mlp = Mlp(
+            in_features=channels,
+            hidden_features=mlp_hidden_channels,
+            act_cfg=act_cfg,
+            drop=drop)
+        layer_scale_init_value = 1e-2
+        self.layer_scale_1 = nn.Parameter(
+            layer_scale_init_value * torch.ones(channels), requires_grad=True)
+        self.layer_scale_2 = nn.Parameter(
+            layer_scale_init_value * torch.ones(channels), requires_grad=True)
+
+    def forward(self, x, H, W):
+        """Forward function."""
+
+        B, N, C = x.shape
+        x = x.permute(0, 2, 1).view(B, C, H, W)
+        x = x + self.drop_path(
+            self.layer_scale_1.unsqueeze(-1).unsqueeze(-1) *
+            self.attn(self.norm1(x)))
+        x = x + self.drop_path(
+            self.layer_scale_2.unsqueeze(-1).unsqueeze(-1) *
+            self.mlp(self.norm2(x)))
+        x = x.view(B, C, N).permute(0, 2, 1)
+        return x
+
+
+class OverlapPatchEmbed(BaseModule):
+    """Image to Patch Embedding.
+
+    Args:
+        patch_size (int): The patch size.
+            Defaults: 7.
+        stride (int): Stride of the convolutional layer.
+            Default: 4.
+        in_channels (int): The number of input channels.
+            Defaults: 3.
+        embed_dims (int): The dimensions of embedding.
+            Defaults: 768.
+        norm_cfg (dict): Config dict for normalization layer.
+            Defaults: dict(type='SyncBN', requires_grad=True).
+    """
+
+    def __init__(self,
+                 patch_size=7,
+                 stride=4,
+                 in_channels=3,
+                 embed_dim=768,
+                 norm_cfg=dict(type='SyncBN', requires_grad=True)):
+        super().__init__()
+
+        self.proj = nn.Conv2d(
+            in_channels,
+            embed_dim,
+            kernel_size=patch_size,
+            stride=stride,
+            padding=patch_size // 2)
+        self.norm = build_norm_layer(norm_cfg, embed_dim)[1]
+
+    def forward(self, x):
+        """Forward function."""
+
+        x = self.proj(x)
+        _, _, H, W = x.shape
+        x = self.norm(x)
+
+        x = x.flatten(2).transpose(1, 2)
+
+        return x, H, W
+
+
+@MODELS.register_module()
+class MSCAN(BaseModule):
+    """SegNeXt Multi-Scale Convolutional Attention Network (MCSAN) backbone.
+
+    This backbone is the implementation of `SegNeXt: Rethinking
+    Convolutional Attention Design for Semantic
+    Segmentation <https://arxiv.org/abs/2209.08575>`_.
+    Inspiration from https://github.com/visual-attention-network/segnext.
+
+    Args:
+        in_channels (int): The number of input channels. Defaults: 3.
+        embed_dims (list[int]): Embedding dimension.
+            Defaults: [64, 128, 256, 512].
+        mlp_ratios (list[int]): Ratio of mlp hidden dim to embedding dim.
+            Defaults: [4, 4, 4, 4].
+        drop_rate (float): Dropout rate. Defaults: 0.
+        drop_path_rate (float): Stochastic depth rate. Defaults: 0.
+        depths (list[int]): Depths of each Swin Transformer stage.
+            Default: [3, 4, 6, 3].
+        num_stages (int): MSCAN stages. Default: 4.
+        attention_kernel_sizes (list): Size of attention kernel in
+            Attention Module (Figure 2(b) of original paper).
+            Defaults: [5, [1, 7], [1, 11], [1, 21]].
+        attention_kernel_paddings (list): Size of attention paddings
+            in Attention Module (Figure 2(b) of original paper).
+            Defaults: [2, [0, 3], [0, 5], [0, 10]].
+        norm_cfg (dict): Config of norm layers.
+            Defaults: dict(type='SyncBN', requires_grad=True).
+        pretrained (str, optional): model pretrained path.
+            Default: None.
+        init_cfg (dict or list[dict], optional): Initialization config dict.
+            Default: None.
+    """
+
+    def __init__(self,
+                 in_channels=3,
+                 embed_dims=[64, 128, 256, 512],
+                 mlp_ratios=[4, 4, 4, 4],
+                 drop_rate=0.,
+                 drop_path_rate=0.,
+                 depths=[3, 4, 6, 3],
+                 num_stages=4,
+                 attention_kernel_sizes=[5, [1, 7], [1, 11], [1, 21]],
+                 attention_kernel_paddings=[2, [0, 3], [0, 5], [0, 10]],
+                 act_cfg=dict(type='GELU'),
+                 norm_cfg=dict(type='SyncBN', requires_grad=True),
+                 pretrained=None,
+                 init_cfg=None):
+        super().__init__(init_cfg=init_cfg)
+
+        assert not (init_cfg and pretrained), \
+            'init_cfg and pretrained cannot be set at the same time'
+        if isinstance(pretrained, str):
+            warnings.warn('DeprecationWarning: pretrained is deprecated, '
+                          'please use "init_cfg" instead')
+            self.init_cfg = dict(type='Pretrained', checkpoint=pretrained)
+        elif pretrained is not None:
+            raise TypeError('pretrained must be a str or None')
+
+        self.depths = depths
+        self.num_stages = num_stages
+
+        dpr = [
+            x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))
+        ]  # stochastic depth decay rule
+        cur = 0
+
+        for i in range(num_stages):
+            if i == 0:
+                patch_embed = StemConv(3, embed_dims[0], norm_cfg=norm_cfg)
+            else:
+                patch_embed = OverlapPatchEmbed(
+                    patch_size=7 if i == 0 else 3,
+                    stride=4 if i == 0 else 2,
+                    in_channels=in_channels if i == 0 else embed_dims[i - 1],
+                    embed_dim=embed_dims[i],
+                    norm_cfg=norm_cfg)
+
+            block = nn.ModuleList([
+                MSCABlock(
+                    channels=embed_dims[i],
+                    attention_kernel_sizes=attention_kernel_sizes,
+                    attention_kernel_paddings=attention_kernel_paddings,
+                    mlp_ratio=mlp_ratios[i],
+                    drop=drop_rate,
+                    drop_path=dpr[cur + j],
+                    act_cfg=act_cfg,
+                    norm_cfg=norm_cfg) for j in range(depths[i])
+            ])
+            norm = nn.LayerNorm(embed_dims[i])
+            cur += depths[i]
+
+            setattr(self, f'patch_embed{i + 1}', patch_embed)
+            setattr(self, f'block{i + 1}', block)
+            setattr(self, f'norm{i + 1}', norm)
+
+    def init_weights(self):
+        """Initialize modules of MSCAN."""
+
+        print('init cfg', self.init_cfg)
+        if self.init_cfg is None:
+            for m in self.modules():
+                if isinstance(m, nn.Linear):
+                    trunc_normal_init(m, std=.02, bias=0.)
+                elif isinstance(m, nn.LayerNorm):
+                    constant_init(m, val=1.0, bias=0.)
+                elif isinstance(m, nn.Conv2d):
+                    fan_out = m.kernel_size[0] * m.kernel_size[
+                        1] * m.out_channels
+                    fan_out //= m.groups
+                    normal_init(
+                        m, mean=0, std=math.sqrt(2.0 / fan_out), bias=0)
+        else:
+            super().init_weights()
+
+    def forward(self, x):
+        """Forward function."""
+
+        B = x.shape[0]
+        outs = []
+
+        for i in range(self.num_stages):
+            patch_embed = getattr(self, f'patch_embed{i + 1}')
+            block = getattr(self, f'block{i + 1}')
+            norm = getattr(self, f'norm{i + 1}')
+            x, H, W = patch_embed(x)
+            for blk in block:
+                x = blk(x, H, W)
+            x = norm(x)
+            x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
+            outs.append(x)
+
+        return outs
diff --git a/mmseg/models/decode_heads/__init__.py b/mmseg/models/decode_heads/__init__.py
index e6eeafc248..18235456bc 100644
--- a/mmseg/models/decode_heads/__init__.py
+++ b/mmseg/models/decode_heads/__init__.py
@@ -12,6 +12,7 @@
 from .fcn_head import FCNHead
 from .fpn_head import FPNHead
 from .gc_head import GCHead
+from .ham_head import LightHamHead
 from .isa_head import ISAHead
 from .knet_head import IterativeDecodeHead, KernelUpdateHead, KernelUpdator
 from .lraspp_head import LRASPPHead
@@ -40,5 +41,5 @@
     'SETRMLAHead', 'DPTHead', 'SETRMLAHead', 'SegmenterMaskTransformerHead',
     'SegformerHead', 'ISAHead', 'STDCHead', 'IterativeDecodeHead',
     'KernelUpdateHead', 'KernelUpdator', 'MaskFormerHead', 'Mask2FormerHead',
-    'PIDHead'
+    'LightHamHead', 'PIDHead'
 ]
diff --git a/mmseg/models/decode_heads/ham_head.py b/mmseg/models/decode_heads/ham_head.py
new file mode 100644
index 0000000000..d80025f77d
--- /dev/null
+++ b/mmseg/models/decode_heads/ham_head.py
@@ -0,0 +1,257 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+# Originally from https://github.com/visual-attention-network/segnext
+# Licensed under the Apache License, Version 2.0 (the "License")
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from mmcv.cnn import ConvModule
+
+from mmseg.registry import MODELS
+from ..utils import resize
+from .decode_head import BaseDecodeHead
+
+
+class Matrix_Decomposition_2D_Base(nn.Module):
+    """Base class of 2D Matrix Decomposition.
+
+    Args:
+        MD_S (int): The number of spatial coefficient in
+            Matrix Decomposition, it may be used for calculation
+            of the number of latent dimension D in Matrix
+            Decomposition. Defaults: 1.
+        MD_R (int): The number of latent dimension R in
+            Matrix Decomposition. Defaults: 64.
+        train_steps (int): The number of iteration steps in
+            Multiplicative Update (MU) rule to solve Non-negative
+            Matrix Factorization (NMF) in training. Defaults: 6.
+        eval_steps (int): The number of iteration steps in
+            Multiplicative Update (MU) rule to solve Non-negative
+            Matrix Factorization (NMF) in evaluation. Defaults: 7.
+        inv_t (int): Inverted multiple number to make coefficient
+            smaller in softmax. Defaults: 100.
+        rand_init (bool): Whether to initialize randomly.
+            Defaults: True.
+    """
+
+    def __init__(self,
+                 MD_S=1,
+                 MD_R=64,
+                 train_steps=6,
+                 eval_steps=7,
+                 inv_t=100,
+                 rand_init=True):
+        super().__init__()
+
+        self.S = MD_S
+        self.R = MD_R
+
+        self.train_steps = train_steps
+        self.eval_steps = eval_steps
+
+        self.inv_t = inv_t
+
+        self.rand_init = rand_init
+
+    def _build_bases(self, B, S, D, R, cuda=False):
+        raise NotImplementedError
+
+    def local_step(self, x, bases, coef):
+        raise NotImplementedError
+
+    def local_inference(self, x, bases):
+        # (B * S, D, N)^T @ (B * S, D, R) -> (B * S, N, R)
+        coef = torch.bmm(x.transpose(1, 2), bases)
+        coef = F.softmax(self.inv_t * coef, dim=-1)
+
+        steps = self.train_steps if self.training else self.eval_steps
+        for _ in range(steps):
+            bases, coef = self.local_step(x, bases, coef)
+
+        return bases, coef
+
+    def compute_coef(self, x, bases, coef):
+        raise NotImplementedError
+
+    def forward(self, x, return_bases=False):
+        """Forward Function."""
+        B, C, H, W = x.shape
+
+        # (B, C, H, W) -> (B * S, D, N)
+        D = C // self.S
+        N = H * W
+        x = x.view(B * self.S, D, N)
+        cuda = 'cuda' in str(x.device)
+        if not self.rand_init and not hasattr(self, 'bases'):
+            bases = self._build_bases(1, self.S, D, self.R, cuda=cuda)
+            self.register_buffer('bases', bases)
+
+        # (S, D, R) -> (B * S, D, R)
+        if self.rand_init:
+            bases = self._build_bases(B, self.S, D, self.R, cuda=cuda)
+        else:
+            bases = self.bases.repeat(B, 1, 1)
+
+        bases, coef = self.local_inference(x, bases)
+
+        # (B * S, N, R)
+        coef = self.compute_coef(x, bases, coef)
+
+        # (B * S, D, R) @ (B * S, N, R)^T -> (B * S, D, N)
+        x = torch.bmm(bases, coef.transpose(1, 2))
+
+        # (B * S, D, N) -> (B, C, H, W)
+        x = x.view(B, C, H, W)
+
+        return x
+
+
+class NMF2D(Matrix_Decomposition_2D_Base):
+    """Non-negative Matrix Factorization (NMF) module.
+
+    It is inherited from ``Matrix_Decomposition_2D_Base`` module.
+    """
+
+    def __init__(self, args=dict()):
+        super().__init__(**args)
+
+        self.inv_t = 1
+
+    def _build_bases(self, B, S, D, R, cuda=False):
+        """Build bases in initialization."""
+        if cuda:
+            bases = torch.rand((B * S, D, R)).cuda()
+        else:
+            bases = torch.rand((B * S, D, R))
+
+        bases = F.normalize(bases, dim=1)
+
+        return bases
+
+    def local_step(self, x, bases, coef):
+        """Local step in iteration to renew bases and coefficient."""
+        # (B * S, D, N)^T @ (B * S, D, R) -> (B * S, N, R)
+        numerator = torch.bmm(x.transpose(1, 2), bases)
+        # (B * S, N, R) @ [(B * S, D, R)^T @ (B * S, D, R)] -> (B * S, N, R)
+        denominator = coef.bmm(bases.transpose(1, 2).bmm(bases))
+        # Multiplicative Update
+        coef = coef * numerator / (denominator + 1e-6)
+
+        # (B * S, D, N) @ (B * S, N, R) -> (B * S, D, R)
+        numerator = torch.bmm(x, coef)
+        # (B * S, D, R) @ [(B * S, N, R)^T @ (B * S, N, R)] -> (B * S, D, R)
+        denominator = bases.bmm(coef.transpose(1, 2).bmm(coef))
+        # Multiplicative Update
+        bases = bases * numerator / (denominator + 1e-6)
+
+        return bases, coef
+
+    def compute_coef(self, x, bases, coef):
+        """Compute coefficient."""
+        # (B * S, D, N)^T @ (B * S, D, R) -> (B * S, N, R)
+        numerator = torch.bmm(x.transpose(1, 2), bases)
+        # (B * S, N, R) @ (B * S, D, R)^T @ (B * S, D, R) -> (B * S, N, R)
+        denominator = coef.bmm(bases.transpose(1, 2).bmm(bases))
+        # multiplication update
+        coef = coef * numerator / (denominator + 1e-6)
+
+        return coef
+
+
+class Hamburger(nn.Module):
+    """Hamburger Module. It consists of one slice of "ham" (matrix
+    decomposition) and two slices of "bread" (linear transformation).
+
+    Args:
+        ham_channels (int): Input and output channels of feature.
+        ham_kwargs (dict): Config of matrix decomposition module.
+        norm_cfg (dict | None): Config of norm layers.
+    """
+
+    def __init__(self,
+                 ham_channels=512,
+                 ham_kwargs=dict(),
+                 norm_cfg=None,
+                 **kwargs):
+        super().__init__()
+
+        self.ham_in = ConvModule(
+            ham_channels, ham_channels, 1, norm_cfg=None, act_cfg=None)
+
+        self.ham = NMF2D(ham_kwargs)
+
+        self.ham_out = ConvModule(
+            ham_channels, ham_channels, 1, norm_cfg=norm_cfg, act_cfg=None)
+
+    def forward(self, x):
+        enjoy = self.ham_in(x)
+        enjoy = F.relu(enjoy, inplace=True)
+        enjoy = self.ham(enjoy)
+        enjoy = self.ham_out(enjoy)
+        ham = F.relu(x + enjoy, inplace=True)
+
+        return ham
+
+
+@MODELS.register_module()
+class LightHamHead(BaseDecodeHead):
+    """SegNeXt decode head.
+
+    This decode head is the implementation of `SegNeXt: Rethinking
+    Convolutional Attention Design for Semantic
+    Segmentation <https://arxiv.org/abs/2209.08575>`_.
+    Inspiration from https://github.com/visual-attention-network/segnext.
+
+    Specifically, LightHamHead is inspired by HamNet from
+    `Is Attention Better Than Matrix Decomposition?
+    <https://arxiv.org/abs/2109.04553>`.
+
+    Args:
+        ham_channels (int): input channels for Hamburger.
+            Defaults: 512.
+        ham_kwargs (int): kwagrs for Ham. Defaults: dict().
+    """
+
+    def __init__(self, ham_channels=512, ham_kwargs=dict(), **kwargs):
+        super().__init__(input_transform='multiple_select', **kwargs)
+        self.ham_channels = ham_channels
+
+        self.squeeze = ConvModule(
+            sum(self.in_channels),
+            self.ham_channels,
+            1,
+            conv_cfg=self.conv_cfg,
+            norm_cfg=self.norm_cfg,
+            act_cfg=self.act_cfg)
+
+        self.hamburger = Hamburger(ham_channels, ham_kwargs, **kwargs)
+
+        self.align = ConvModule(
+            self.ham_channels,
+            self.channels,
+            1,
+            conv_cfg=self.conv_cfg,
+            norm_cfg=self.norm_cfg,
+            act_cfg=self.act_cfg)
+
+    def forward(self, inputs):
+        """Forward function."""
+        inputs = self._transform_inputs(inputs)
+
+        inputs = [
+            resize(
+                level,
+                size=inputs[0].shape[2:],
+                mode='bilinear',
+                align_corners=self.align_corners) for level in inputs
+        ]
+
+        inputs = torch.cat(inputs, dim=1)
+        # apply a conv block to squeeze feature map
+        x = self.squeeze(inputs)
+        # apply hamburger module
+        x = self.hamburger(x)
+
+        # apply a conv block to align feature map
+        output = self.align(x)
+        output = self.cls_seg(output)
+        return output
diff --git a/model-index.yml b/model-index.yml
index be7210e120..130031a303 100644
--- a/model-index.yml
+++ b/model-index.yml
@@ -39,6 +39,7 @@ Import:
 - configs/resnest/resnest.yml
 - configs/segformer/segformer.yml
 - configs/segmenter/segmenter.yml
+- configs/segnext/segnext.yml
 - configs/sem_fpn/sem_fpn.yml
 - configs/setr/setr.yml
 - configs/stdc/stdc.yml
diff --git a/tests/test_models/test_backbones/test_mscan.py b/tests/test_models/test_backbones/test_mscan.py
new file mode 100644
index 0000000000..84dfb8e450
--- /dev/null
+++ b/tests/test_models/test_backbones/test_mscan.py
@@ -0,0 +1,69 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+import torch
+
+from mmseg.models.backbones import MSCAN
+from mmseg.models.backbones.mscan import (MSCAAttention, MSCASpatialAttention,
+                                          OverlapPatchEmbed, StemConv)
+
+
+def test_mscan_backbone():
+    # Test MSCAN Standard Forward
+    model = MSCAN(
+        embed_dims=[8, 16, 32, 64],
+        norm_cfg=dict(type='BN', requires_grad=True))
+    model.init_weights()
+    model.train()
+    batch_size = 2
+    imgs = torch.randn(batch_size, 3, 64, 128)
+    feat = model(imgs)
+
+    assert len(feat) == 4
+    # output for segment Head
+    assert feat[0].shape == torch.Size([batch_size, 8, 16, 32])
+    assert feat[1].shape == torch.Size([batch_size, 16, 8, 16])
+    assert feat[2].shape == torch.Size([batch_size, 32, 4, 8])
+    assert feat[3].shape == torch.Size([batch_size, 64, 2, 4])
+
+    # Test input with rare shape
+    batch_size = 2
+    imgs = torch.randn(batch_size, 3, 95, 27)
+    feat = model(imgs)
+    assert len(feat) == 4
+
+
+def test_mscan_overlap_patch_embed_module():
+    x_overlap_patch_embed = OverlapPatchEmbed(
+        norm_cfg=dict(type='BN', requires_grad=True))
+    assert x_overlap_patch_embed.proj.in_channels == 3
+    assert x_overlap_patch_embed.norm.weight.shape == torch.Size([768])
+    x = torch.randn(2, 3, 16, 32)
+    x_out, H, W = x_overlap_patch_embed(x)
+    assert x_out.shape == torch.Size([2, 32, 768])
+
+
+def test_mscan_spatial_attention_module():
+    x_spatial_attention = MSCASpatialAttention(8)
+    assert x_spatial_attention.proj_1.kernel_size == (1, 1)
+    assert x_spatial_attention.proj_2.stride == (1, 1)
+    x = torch.randn(2, 8, 16, 32)
+    x_out = x_spatial_attention(x)
+    assert x_out.shape == torch.Size([2, 8, 16, 32])
+
+
+def test_mscan_attention_module():
+    x_attention = MSCAAttention(8)
+    assert x_attention.conv0.weight.shape[0] == 8
+    assert x_attention.conv3.kernel_size == (1, 1)
+    x = torch.randn(2, 8, 16, 32)
+    x_out = x_attention(x)
+    assert x_out.shape == torch.Size([2, 8, 16, 32])
+
+
+def test_mscan_stem_module():
+    x_stem = StemConv(8, 8, norm_cfg=dict(type='BN', requires_grad=True))
+    assert x_stem.proj[0].weight.shape[0] == 4
+    assert x_stem.proj[-1].weight.shape[0] == 8
+    x = torch.randn(2, 8, 16, 32)
+    x_out, H, W = x_stem(x)
+    assert x_out.shape == torch.Size([2, 32, 8])
+    assert (H, W) == (4, 8)
diff --git a/tests/test_models/test_heads/test_ham_head.py b/tests/test_models/test_heads/test_ham_head.py
new file mode 100644
index 0000000000..f802d2d8db
--- /dev/null
+++ b/tests/test_models/test_heads/test_ham_head.py
@@ -0,0 +1,44 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+import torch
+
+from mmseg.models.decode_heads import LightHamHead
+from .utils import _conv_has_norm, to_cuda
+
+ham_norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+
+def test_ham_head():
+
+    # test without sync_bn
+    head = LightHamHead(
+        in_channels=[16, 32, 64],
+        in_index=[1, 2, 3],
+        channels=64,
+        ham_channels=64,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=ham_norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+        ham_kwargs=dict(
+            MD_S=1,
+            MD_R=64,
+            train_steps=6,
+            eval_steps=7,
+            inv_t=100,
+            rand_init=True))
+    assert not _conv_has_norm(head, sync_bn=False)
+
+    inputs = [
+        torch.randn(1, 8, 32, 32),
+        torch.randn(1, 16, 16, 16),
+        torch.randn(1, 32, 8, 8),
+        torch.randn(1, 64, 4, 4)
+    ]
+    if torch.cuda.is_available():
+        head, inputs = to_cuda(head, inputs)
+    assert head.in_channels == [16, 32, 64]
+    assert head.hamburger.ham_in.in_channels == 64
+    outputs = head(inputs)
+    assert outputs.shape == (1, head.num_classes, 16, 16)

From 6d63e77600c61e10b7f55c9056e3da359093ef91 Mon Sep 17 00:00:00 2001
From: Haolan He <61172629+BLUE-coconut@users.noreply.github.com>
Date: Fri, 17 Mar 2023 17:35:38 +0800
Subject: [PATCH 19/32] [Docs] add deeplabv3 model structure (#2426)

as title
---
 configs/deeplabv3/README.md | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/configs/deeplabv3/README.md b/configs/deeplabv3/README.md
index 4c80ffaf91..b37836ab21 100644
--- a/configs/deeplabv3/README.md
+++ b/configs/deeplabv3/README.md
@@ -22,6 +22,11 @@ In this work, we revisit atrous convolution, a powerful tool to explicitly adjus
 <img src="https://user-images.githubusercontent.com/24582831/142900575-f30a7755-09aa-406a-bf78-45893a61ee9a.png" width="80%"/>
 </div>
 
+<div align=center >
+<img alt="DEEPLABv3_ResNet-D8" src="https://user-images.githubusercontent.com/61172629/209305311-87ff9e36-b7cd-46d7-8b4c-9e26e10c27d0.jpg"/>
+DEEPLABv3_ResNet-D8 model structure
+</div>
+
 ## Citation
 
 ```bibtext

From f6de1aad81967e04961600288e58b5369332b75d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E8=B0=A2=E6=98=95=E8=BE=B0?= <xiexinch@outlook.com>
Date: Fri, 17 Mar 2023 19:12:58 +0800
Subject: [PATCH 20/32] [Dev] update update-model-index pre-commit hook (#2667)

---
 .dev/md2yml.py                                |  317 ----
 .dev/update_model_index.py                    |  292 ++++
 .pre-commit-config.yaml                       |    5 +-
 configs/ann/README.md                         |   68 +-
 configs/ann/ann.yml                           |  305 ----
 configs/ann/metafile.yaml                     |  391 +++++
 configs/apcnet/README.md                      |   50 +-
 configs/apcnet/apcnet.yml                     |  232 ---
 configs/apcnet/metafile.yaml                  |  296 ++++
 configs/beit/README.md                        |   34 +-
 configs/beit/beit.yml                         |   45 -
 configs/beit/metafile.yaml                    |   49 +
 configs/bisenetv1/README.md                   |   56 +-
 configs/bisenetv1/bisenetv1.yml               |  234 ---
 configs/bisenetv1/metafile.yaml               |  275 ++++
 configs/bisenetv2/README.md                   |   36 +-
 configs/bisenetv2/bisenetv2.yml               |   88 --
 configs/bisenetv2/metafile.yaml               |  114 ++
 configs/ccnet/README.md                       |   68 +-
 configs/ccnet/ccnet.yml                       |  305 ----
 configs/ccnet/metafile.yaml                   |  391 +++++
 configs/cgnet/README.md                       |   20 +-
 configs/cgnet/cgnet.yml                       |   59 -
 configs/cgnet/metafile.yaml                   |   61 +
 configs/convnext/README.md                    |   38 +-
 configs/convnext/convnext.yml                 |  133 --
 configs/convnext/metafile.yaml                |  145 ++
 configs/danet/README.md                       |   68 +-
 configs/danet/danet.yml                       |  301 ----
 configs/danet/metafile.yaml                   |  387 +++++
 configs/deeplabv3/README.md                   |  138 +-
 configs/deeplabv3/deeplabv3.yml               |  756 ----------
 configs/deeplabv3/metafile.yaml               |  985 +++++++++++++
 configs/deeplabv3plus/README.md               |  144 +-
 configs/deeplabv3plus/deeplabv3plus.yml       |  872 -----------
 configs/deeplabv3plus/metafile.yaml           | 1041 +++++++++++++
 configs/dmnet/README.md                       |   50 +-
 configs/dmnet/dmnet.yml                       |  232 ---
 configs/dmnet/metafile.yaml                   |  296 ++++
 configs/dnlnet/README.md                      |   52 +-
 configs/dnlnet/dnlnet.yml                     |  228 ---
 configs/dnlnet/metafile.yaml                  |  292 ++++
 configs/dpt/README.md                         |   44 +-
 configs/dpt/dpt.yml                           |   37 -
 configs/dpt/metafile.yaml                     |   37 +
 configs/emanet/README.md                      |   24 +-
 configs/emanet/emanet.yml                     |  103 --
 configs/emanet/metafile.yaml                  |  109 ++
 configs/encnet/README.md                      |   50 +-
 configs/encnet/encnet.yml                     |  232 ---
 configs/encnet/metafile.yaml                  |  296 ++++
 configs/erfnet/README.md                      |   34 +-
 configs/erfnet/erfnet.yml                     |   37 -
 configs/erfnet/metafile.yaml                  |   37 +
 configs/fastfcn/README.md                     |   56 +-
 configs/fastfcn/fastfcn.yml                   |  235 ---
 configs/fastfcn/metafile.yaml                 |  311 ++++
 configs/fastscnn/README.md                    |   18 +-
 .../fastscnn/{fastscnn.yml => metafile.yaml}  |   36 +-
 configs/fcn/README.md                         |  134 +-
 configs/fcn/fcn.yml                           |  827 -----------
 configs/fcn/metafile.yaml                     |  997 +++++++++++++
 configs/gcnet/README.md                       |   68 +-
 configs/gcnet/gcnet.yml                       |  305 ----
 configs/gcnet/metafile.yaml                   |  391 +++++
 configs/hrnet/README.md                       |  134 +-
 configs/hrnet/hrnet.yml                       |  695 ---------
 configs/hrnet/metafile.yaml                   |  874 +++++++++++
 configs/icnet/README.md                       |   44 +-
 configs/icnet/icnet.yml                       |  207 ---
 configs/icnet/metafile.yaml                   |  298 ++++
 configs/isanet/README.md                      |   68 +-
 configs/isanet/isanet.yml                     |  369 -----
 configs/isanet/metafile.yaml                  |  399 +++++
 configs/knet/README.md                        |   40 +-
 configs/knet/knet.yml                         |  169 ---
 configs/knet/metafile.yaml                    |  188 +++
 configs/mae/README.md                         |   30 +-
 configs/mae/mae.yml                           |   23 -
 configs/mae/metafile.yaml                     |   25 +
 configs/mask2former/README.md                 |   68 +-
 configs/mask2former/mask2former.yml           |  290 ----
 configs/mask2former/metafile.yaml             |  314 ++++
 configs/maskformer/README.md                  |   38 +-
 configs/maskformer/maskformer.yml             |  101 --
 configs/maskformer/metafile.yaml              |  111 ++
 configs/mobilenet_v2/README.md                |   42 +-
 configs/mobilenet_v2/metafile.yaml            |  186 +++
 configs/mobilenet_v2/mobilenet_v2.yml         |  170 ---
 configs/mobilenet_v3/README.md                |   24 +-
 configs/mobilenet_v3/metafile.yaml            |  109 ++
 configs/mobilenet_v3/mobilenet_v3.yml         |  103 --
 configs/nonlocal_net/README.md                |   68 +-
 configs/nonlocal_net/metafile.yaml            |  387 +++++
 configs/nonlocal_net/nonlocal_net.yml         |  301 ----
 configs/ocrnet/README.md                      |   98 +-
 configs/ocrnet/metafile.yaml                  |  577 ++++++++
 configs/ocrnet/ocrnet.yml                     |  438 ------
 configs/pidnet/README.md                      |   10 +-
 configs/pidnet/metafile.yaml                  |   85 ++
 configs/pidnet/pidnet.yml                     |   81 -
 configs/point_rend/README.md                  |   34 +-
 configs/point_rend/metafile.yaml              |  110 ++
 configs/point_rend/point_rend.yml             |  104 --
 configs/poolformer/README.md                  |   16 +-
 configs/poolformer/metafile.yaml              |  116 ++
 configs/poolformer/poolformer.yml             |  106 --
 configs/psanet/README.md                      |   68 +-
 configs/psanet/metafile.yaml                  |  391 +++++
 configs/psanet/psanet.yml                     |  305 ----
 configs/pspnet/README.md                      |  194 +--
 configs/pspnet/metafile.yaml                  | 1303 +++++++++++++++++
 configs/pspnet/pspnet.yml                     | 1077 --------------
 configs/resnest/README.md                     |   42 +-
 configs/resnest/metafile.yaml                 |  193 +++
 configs/resnest/resnest.yml                   |  177 ---
 configs/segformer/README.md                   |   58 +-
 configs/segformer/metafile.yaml               |  340 +++++
 configs/segformer/segformer.yml               |  303 ----
 configs/segmenter/README.md                   |   50 +-
 configs/segmenter/metafile.yaml               |  138 ++
 configs/segmenter/segmenter.yml               |  125 --
 configs/segnext/README.md                     |   12 +-
 configs/segnext/metafile.yaml                 |  109 ++
 configs/segnext/segnext.yml                   |  103 --
 configs/sem_fpn/README.md                     |   34 +-
 configs/sem_fpn/metafile.yaml                 |  110 ++
 configs/sem_fpn/sem_fpn.yml                   |  104 --
 configs/setr/README.md                        |   46 +-
 configs/setr/metafile.yaml                    |  197 +++
 configs/setr/setr.yml                         |  164 ---
 configs/stdc/README.md                        |   38 +-
 configs/stdc/metafile.yaml                    |  107 ++
 configs/stdc/stdc.yml                         |   87 --
 configs/swin/README.md                        |   40 +-
 configs/swin/metafile.yaml                    |  143 ++
 configs/swin/swin.yml                         |  117 --
 configs/twins/README.md                       |   52 +-
 configs/twins/metafile.yaml                   |  289 ++++
 configs/twins/twins.yml                       |  265 ----
 configs/unet/README.md                        |   98 +-
 configs/unet/metafile.yaml                    |  642 ++++++++
 configs/unet/unet.yml                         |  377 -----
 configs/upernet/README.md                     |   68 +-
 configs/upernet/metafile.yaml                 |  391 +++++
 configs/upernet/upernet.yml                   |  305 ----
 configs/vit/README.md                         |   50 +-
 configs/vit/metafile.yaml                     |  265 ++++
 configs/vit/vit.yml                           |  243 ---
 ...n_mln_upernet_8xb2-160k_ade20k-512x512.py} |    0
 model-index.yml                               |   98 +-
 151 files changed, 17070 insertions(+), 14265 deletions(-)
 delete mode 100755 .dev/md2yml.py
 create mode 100755 .dev/update_model_index.py
 delete mode 100644 configs/ann/ann.yml
 create mode 100644 configs/ann/metafile.yaml
 delete mode 100644 configs/apcnet/apcnet.yml
 create mode 100644 configs/apcnet/metafile.yaml
 delete mode 100644 configs/beit/beit.yml
 create mode 100644 configs/beit/metafile.yaml
 delete mode 100644 configs/bisenetv1/bisenetv1.yml
 create mode 100644 configs/bisenetv1/metafile.yaml
 delete mode 100644 configs/bisenetv2/bisenetv2.yml
 create mode 100644 configs/bisenetv2/metafile.yaml
 delete mode 100644 configs/ccnet/ccnet.yml
 create mode 100644 configs/ccnet/metafile.yaml
 delete mode 100644 configs/cgnet/cgnet.yml
 create mode 100644 configs/cgnet/metafile.yaml
 delete mode 100644 configs/convnext/convnext.yml
 create mode 100644 configs/convnext/metafile.yaml
 delete mode 100644 configs/danet/danet.yml
 create mode 100644 configs/danet/metafile.yaml
 delete mode 100644 configs/deeplabv3/deeplabv3.yml
 create mode 100644 configs/deeplabv3/metafile.yaml
 delete mode 100644 configs/deeplabv3plus/deeplabv3plus.yml
 create mode 100644 configs/deeplabv3plus/metafile.yaml
 delete mode 100644 configs/dmnet/dmnet.yml
 create mode 100644 configs/dmnet/metafile.yaml
 delete mode 100644 configs/dnlnet/dnlnet.yml
 create mode 100644 configs/dnlnet/metafile.yaml
 delete mode 100644 configs/dpt/dpt.yml
 create mode 100644 configs/dpt/metafile.yaml
 delete mode 100644 configs/emanet/emanet.yml
 create mode 100644 configs/emanet/metafile.yaml
 delete mode 100644 configs/encnet/encnet.yml
 create mode 100644 configs/encnet/metafile.yaml
 delete mode 100644 configs/erfnet/erfnet.yml
 create mode 100644 configs/erfnet/metafile.yaml
 delete mode 100644 configs/fastfcn/fastfcn.yml
 create mode 100644 configs/fastfcn/metafile.yaml
 rename configs/fastscnn/{fastscnn.yml => metafile.yaml} (50%)
 delete mode 100644 configs/fcn/fcn.yml
 create mode 100644 configs/fcn/metafile.yaml
 delete mode 100644 configs/gcnet/gcnet.yml
 create mode 100644 configs/gcnet/metafile.yaml
 delete mode 100644 configs/hrnet/hrnet.yml
 create mode 100644 configs/hrnet/metafile.yaml
 delete mode 100644 configs/icnet/icnet.yml
 create mode 100644 configs/icnet/metafile.yaml
 delete mode 100644 configs/isanet/isanet.yml
 create mode 100644 configs/isanet/metafile.yaml
 delete mode 100644 configs/knet/knet.yml
 create mode 100644 configs/knet/metafile.yaml
 delete mode 100644 configs/mae/mae.yml
 create mode 100644 configs/mae/metafile.yaml
 delete mode 100644 configs/mask2former/mask2former.yml
 create mode 100644 configs/mask2former/metafile.yaml
 delete mode 100644 configs/maskformer/maskformer.yml
 create mode 100644 configs/maskformer/metafile.yaml
 create mode 100644 configs/mobilenet_v2/metafile.yaml
 delete mode 100644 configs/mobilenet_v2/mobilenet_v2.yml
 create mode 100644 configs/mobilenet_v3/metafile.yaml
 delete mode 100644 configs/mobilenet_v3/mobilenet_v3.yml
 create mode 100644 configs/nonlocal_net/metafile.yaml
 delete mode 100644 configs/nonlocal_net/nonlocal_net.yml
 create mode 100644 configs/ocrnet/metafile.yaml
 delete mode 100644 configs/ocrnet/ocrnet.yml
 create mode 100644 configs/pidnet/metafile.yaml
 delete mode 100644 configs/pidnet/pidnet.yml
 create mode 100644 configs/point_rend/metafile.yaml
 delete mode 100644 configs/point_rend/point_rend.yml
 create mode 100644 configs/poolformer/metafile.yaml
 delete mode 100644 configs/poolformer/poolformer.yml
 create mode 100644 configs/psanet/metafile.yaml
 delete mode 100644 configs/psanet/psanet.yml
 create mode 100644 configs/pspnet/metafile.yaml
 delete mode 100644 configs/pspnet/pspnet.yml
 create mode 100644 configs/resnest/metafile.yaml
 delete mode 100644 configs/resnest/resnest.yml
 create mode 100644 configs/segformer/metafile.yaml
 delete mode 100644 configs/segformer/segformer.yml
 create mode 100644 configs/segmenter/metafile.yaml
 delete mode 100644 configs/segmenter/segmenter.yml
 create mode 100644 configs/segnext/metafile.yaml
 delete mode 100644 configs/segnext/segnext.yml
 create mode 100644 configs/sem_fpn/metafile.yaml
 delete mode 100644 configs/sem_fpn/sem_fpn.yml
 create mode 100644 configs/setr/metafile.yaml
 delete mode 100644 configs/setr/setr.yml
 create mode 100644 configs/stdc/metafile.yaml
 delete mode 100644 configs/stdc/stdc.yml
 create mode 100644 configs/swin/metafile.yaml
 delete mode 100644 configs/swin/swin.yml
 create mode 100644 configs/twins/metafile.yaml
 delete mode 100644 configs/twins/twins.yml
 create mode 100644 configs/unet/metafile.yaml
 delete mode 100644 configs/unet/unet.yml
 create mode 100644 configs/upernet/metafile.yaml
 delete mode 100644 configs/upernet/upernet.yml
 create mode 100644 configs/vit/metafile.yaml
 delete mode 100644 configs/vit/vit.yml
 rename configs/vit/{vit_deit-s16-ln_mln_upernet_512x512_160k_ade20k-512x512.py => vit_deit-s16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py} (100%)

diff --git a/.dev/md2yml.py b/.dev/md2yml.py
deleted file mode 100755
index fc9c67e470..0000000000
--- a/.dev/md2yml.py
+++ /dev/null
@@ -1,317 +0,0 @@
-#!/usr/bin/env python
-
-# Copyright (c) OpenMMLab. All rights reserved.
-# This tool is used to update model-index.yml which is required by MIM, and
-# will be automatically called as a pre-commit hook. The updating will be
-# triggered if any change of model information (.md files in configs/) has been
-# detected before a commit.
-
-import glob
-import os
-import os.path as osp
-import re
-import sys
-
-from lxml import etree
-from mmengine.fileio import dump
-
-MMSEG_ROOT = osp.dirname(osp.dirname(osp.dirname(__file__)))
-
-COLLECTIONS = [
-    'ANN', 'APCNet', 'BiSeNetV1', 'BiSeNetV2', 'CCNet', 'CGNet', 'DANet',
-    'DeepLabV3', 'DeepLabV3+', 'DMNet', 'DNLNet', 'DPT', 'EMANet', 'EncNet',
-    'ERFNet', 'FastFCN', 'FastSCNN', 'FCN', 'GCNet', 'ICNet', 'ISANet', 'KNet',
-    'NonLocalNet', 'OCRNet', 'PointRend', 'PSANet', 'PSPNet', 'Segformer',
-    'Segmenter', 'FPN', 'SETR', 'STDC', 'UNet', 'UPerNet'
-]
-COLLECTIONS_TEMP = []
-
-
-def dump_yaml_and_check_difference(obj, filename, sort_keys=False):
-    """Dump object to a yaml file, and check if the file content is different
-    from the original.
-
-    Args:
-        obj (any): The python object to be dumped.
-        filename (str): YAML filename to dump the object to.
-        sort_keys (str); Sort key by dictionary order.
-    Returns:
-        Bool: If the target YAML file is different from the original.
-    """
-
-    str_dump = dump(obj, None, file_format='yaml', sort_keys=sort_keys)
-    if osp.isfile(filename):
-        file_exists = True
-        with open(filename, encoding='utf-8') as f:
-            str_orig = f.read()
-    else:
-        file_exists = False
-        str_orig = None
-
-    if file_exists and str_orig == str_dump:
-        is_different = False
-    else:
-        is_different = True
-        with open(filename, 'w', encoding='utf-8') as f:
-            f.write(str_dump)
-
-    return is_different
-
-
-def parse_md(md_file):
-    """Parse .md file and convert it to a .yml file which can be used for MIM.
-
-    Args:
-        md_file (str): Path to .md file.
-    Returns:
-        Bool: If the target YAML file is different from the original.
-    """
-    collection_name = osp.split(osp.dirname(md_file))[1]
-    configs = os.listdir(osp.dirname(md_file))
-
-    collection = dict(
-        Name=collection_name,
-        Metadata={'Training Data': []},
-        Paper={
-            'URL': '',
-            'Title': ''
-        },
-        README=md_file,
-        Code={
-            'URL': '',
-            'Version': ''
-        })
-    collection.update({'Converted From': {'Weights': '', 'Code': ''}})
-    models = []
-    datasets = []
-    paper_url = None
-    paper_title = None
-    code_url = None
-    code_version = None
-    repo_url = None
-
-    # To avoid re-counting number of backbone model in OpenMMLab,
-    # if certain model in configs folder is backbone whose name is already
-    # recorded in MMClassification, then the `COLLECTION` dict of this model
-    # in MMSegmentation should be deleted, and `In Collection` in `Models`
-    # should be set with head or neck of this config file.
-    is_backbone = None
-
-    with open(md_file, encoding='UTF-8') as md:
-        lines = md.readlines()
-        i = 0
-        current_dataset = ''
-        while i < len(lines):
-            line = lines[i].strip()
-            # In latest README.md the title and url are in the third line.
-            if i == 2:
-                paper_url = lines[i].split('](')[1].split(')')[0]
-                paper_title = lines[i].split('](')[0].split('[')[1]
-            if len(line) == 0:
-                i += 1
-                continue
-            elif line[:3] == '<a ':
-                content = etree.HTML(line)
-                node = content.xpath('//a')[0]
-                if node.text == 'Code Snippet':
-                    code_url = node.get('href', None)
-                    assert code_url is not None, (
-                        f'{collection_name} hasn\'t code snippet url.')
-                    # version extraction
-                    filter_str = r'blob/(.*)/mm'
-                    pattern = re.compile(filter_str)
-                    code_version = pattern.findall(code_url)
-                    assert len(code_version) == 1, (
-                        f'false regular expression ({filter_str}) use.')
-                    code_version = code_version[0]
-                elif node.text == 'Official Repo':
-                    repo_url = node.get('href', None)
-                    assert repo_url is not None, (
-                        f'{collection_name} hasn\'t official repo url.')
-                i += 1
-            elif line[:4] == '### ':
-                datasets.append(line[4:])
-                current_dataset = line[4:]
-                i += 2
-            elif line[:15] == '<!-- [BACKBONE]':
-                is_backbone = True
-                i += 1
-            elif (line[0] == '|' and (i + 1) < len(lines)
-                  and lines[i + 1][:3] == '| -' and 'Method' in line
-                  and 'Crop Size' in line and 'Mem (GB)' in line):
-                cols = [col.strip() for col in line.split('|')]
-                method_id = cols.index('Method')
-                backbone_id = cols.index('Backbone')
-                crop_size_id = cols.index('Crop Size')
-                lr_schd_id = cols.index('Lr schd')
-                mem_id = cols.index('Mem (GB)')
-                fps_id = cols.index('Inf time (fps)')
-                try:
-                    ss_id = cols.index('mIoU')
-                except ValueError:
-                    ss_id = cols.index('Dice')
-                try:
-                    ms_id = cols.index('mIoU(ms+flip)')
-                except ValueError:
-                    ms_id = False
-                config_id = cols.index('config')
-                download_id = cols.index('download')
-                j = i + 2
-                while j < len(lines) and lines[j][0] == '|':
-                    els = [el.strip() for el in lines[j].split('|')]
-                    config = ''
-                    model_name = ''
-                    weight = ''
-                    for fn in configs:
-                        if fn in els[config_id]:
-                            left = els[download_id].index(
-                                'https://download.openmmlab.com')
-                            right = els[download_id].index('.pth') + 4
-                            weight = els[download_id][left:right]
-                            config = f'configs/{collection_name}/{fn}'
-                            model_name = fn[:-3]
-                    fps = els[fps_id] if els[fps_id] != '-' and els[
-                        fps_id] != '' else -1
-                    mem = els[mem_id].split(
-                        '\\'
-                    )[0] if els[mem_id] != '-' and els[mem_id] != '' else -1
-                    crop_size = els[crop_size_id].split('x')
-                    assert len(crop_size) == 2
-                    method = els[method_id].split()[0].split('-')[-1]
-                    model = {
-                        'Name':
-                        model_name,
-                        'In Collection':
-                        method,
-                        'Metadata': {
-                            'backbone': els[backbone_id],
-                            'crop size': f'({crop_size[0]},{crop_size[1]})',
-                            'lr schd': int(els[lr_schd_id]),
-                        },
-                        'Results': [
-                            {
-                                'Task': 'Semantic Segmentation',
-                                'Dataset': current_dataset,
-                                'Metrics': {
-                                    cols[ss_id]: float(els[ss_id]),
-                                },
-                            },
-                        ],
-                        'Config':
-                        config,
-                        'Weights':
-                        weight,
-                    }
-                    if fps != -1:
-                        try:
-                            fps = float(fps)
-                        except Exception:
-                            j += 1
-                            continue
-                        model['Metadata']['inference time (ms/im)'] = [{
-                            'value':
-                            round(1000 / float(fps), 2),
-                            'hardware':
-                            'V100',
-                            'backend':
-                            'PyTorch',
-                            'batch size':
-                            1,
-                            'mode':
-                            'FP32' if 'amp' not in config else 'AMP',
-                            'resolution':
-                            f'({crop_size[0]},{crop_size[1]})'
-                        }]
-                    if mem != -1:
-                        model['Metadata']['Training Memory (GB)'] = float(mem)
-                    # Only have semantic segmentation now
-                    if ms_id and els[ms_id] != '-' and els[ms_id] != '':
-                        model['Results'][0]['Metrics'][
-                            'mIoU(ms+flip)'] = float(els[ms_id])
-                    models.append(model)
-                    j += 1
-                i = j
-            else:
-                i += 1
-    flag = (code_url is not None) and (paper_url is not None) and (repo_url
-                                                                   is not None)
-    assert flag, f'{collection_name} readme error'
-    collection['Name'] = method
-    collection['Metadata']['Training Data'] = datasets
-    collection['Code']['URL'] = code_url
-    collection['Code']['Version'] = code_version
-    collection['Paper']['URL'] = paper_url
-    collection['Paper']['Title'] = paper_title
-    collection['Converted From']['Code'] = repo_url
-    # ['Converted From']['Weights] miss
-    # remove empty attribute
-    check_key_list = ['Code', 'Paper', 'Converted From']
-    for check_key in check_key_list:
-        key_list = list(collection[check_key].keys())
-        for key in key_list:
-            if check_key not in collection:
-                break
-            if collection[check_key][key] == '':
-                if len(collection[check_key].keys()) == 1:
-                    collection.pop(check_key)
-                else:
-                    collection[check_key].pop(key)
-    yml_file = f'{md_file[:-9]}{collection_name}.yml'
-    if is_backbone:
-        if collection['Name'] not in COLLECTIONS:
-            result = {
-                'Collections': [collection],
-                'Models': models,
-                'Yml': yml_file
-            }
-            COLLECTIONS_TEMP.append(result)
-            return False
-        else:
-            result = {'Models': models}
-    else:
-        COLLECTIONS.append(collection['Name'])
-        result = {'Collections': [collection], 'Models': models}
-    return dump_yaml_and_check_difference(result, yml_file)
-
-
-def update_model_index():
-    """Update model-index.yml according to model .md files.
-
-    Returns:
-        Bool: If the updated model-index.yml is different from the original.
-    """
-    configs_dir = osp.join(MMSEG_ROOT, 'configs')
-    yml_files = glob.glob(osp.join(configs_dir, '**', '*.yml'), recursive=True)
-    yml_files.sort()
-
-    # add .replace('\\', '/') to avoid Windows Style path
-    model_index = {
-        'Import': [
-            osp.relpath(yml_file, MMSEG_ROOT).replace('\\', '/')
-            for yml_file in yml_files
-        ]
-    }
-    model_index_file = osp.join(MMSEG_ROOT, 'model-index.yml')
-    is_different = dump_yaml_and_check_difference(model_index,
-                                                  model_index_file)
-
-    return is_different
-
-
-if __name__ == '__main__':
-    file_list = [fn for fn in sys.argv[1:] if osp.basename(fn) == 'README.md']
-    if not file_list:
-        sys.exit(0)
-    file_modified = False
-    for fn in file_list:
-        file_modified |= parse_md(fn)
-
-    for result in COLLECTIONS_TEMP:
-        collection = result['Collections'][0]
-        yml_file = result.pop('Yml', None)
-        if collection['Name'] in COLLECTIONS:
-            result.pop('Collections')
-        file_modified |= dump_yaml_and_check_difference(result, yml_file)
-
-    file_modified |= update_model_index()
-    sys.exit(1 if file_modified else 0)
diff --git a/.dev/update_model_index.py b/.dev/update_model_index.py
new file mode 100755
index 0000000000..ae30fc3bff
--- /dev/null
+++ b/.dev/update_model_index.py
@@ -0,0 +1,292 @@
+#!/usr/bin/env python
+
+# Copyright (c) OpenMMLab. All rights reserved.
+# This tool is used to update model-index.yml which is required by MIM, and
+# will be automatically called as a pre-commit hook. The updating will be
+# triggered if any change of model information (.md files in configs/) has been
+# detected before a commit.
+
+import os
+import os.path as osp
+import re
+import sys
+from typing import List, Tuple
+
+import yaml
+
+MMSEG_ROOT = osp.abspath(osp.join(osp.dirname(__file__), '..'))
+
+
+def get_collection_name_list(md_file_list: List[str]) -> List[str]:
+    """Get the list of collection names."""
+    collection_name_list: List[str] = []
+    for md_file in md_file_list:
+        with open(md_file) as f:
+            lines = f.readlines()
+            collection_name = lines[0].split('#')[1].strip()
+            collection_name_list.append(collection_name)
+    return collection_name_list
+
+
+def get_md_file_list() -> Tuple[List[str], List[str]]:
+    """Get the list of md files."""
+    md_file_list: List[str] = []
+    md_dir_list: List[str] = []
+    for root, _, files in os.walk(osp.join(MMSEG_ROOT, 'configs')):
+        for file in files:
+            if file.endswith('.md'):
+                md_file_list.append(osp.join(root, file))
+                md_dir_list.append(root)
+                break
+    return md_file_list, md_dir_list
+
+
+def get_model_info(md_file: str, config_dir: str,
+                   collection_name_list: List[str]) -> Tuple[dict, str]:
+    """Get model information from md file."""
+    datasets: List[str] = []
+    models: List[dict] = []
+    current_dataset: str = ''
+    paper_name: str = ''
+    paper_url: str = ''
+    code_url: str = ''
+    is_backbone: bool = False
+    is_dataset: bool = False
+    collection_name: str = ''
+    with open(md_file) as f:
+        lines: List[str] = f.readlines()
+        i: int = 0
+
+        while i < len(lines):
+            line: str = lines[i].strip()
+            if len(line) == 0:
+                i += 1
+                continue
+            # get paper name and url
+            if re.match(r'> \[.*\]+\([a-zA-Z]+://[^\s]*\)', line):
+                paper_info = line.split('](')
+                paper_name = paper_info[0][paper_info[0].index('[') + 1:]
+                paper_url = paper_info[1][:len(paper_info[1]) - 1]
+
+            # get code info
+            if 'Code Snippet' in line:
+                code_url = line.split('"')[1].split('"')[0]
+
+            if line.startswith('<!-- [BACKBONE]'):
+                is_backbone = True
+
+            if line.startswith('<!-- [DATASET]'):
+                is_dataset = True
+
+            # get dataset names
+            if line.startswith('###'):
+                current_dataset = line.split('###')[1].strip()
+                datasets.append(current_dataset)
+
+            # get model info key id
+            if (line[0] == '|' and (i + 1) < len(lines)
+                    and lines[i + 1][:3] == '| -' and 'Method' in line
+                    and 'Crop Size' in line and 'Mem (GB)' in line):
+                keys: List[str] = [key.strip() for key in line.split('|')]
+                crop_size_idx: int = keys.index('Crop Size')
+                mem_idx: int = keys.index('Mem (GB)')
+                assert 'Device' in keys, f'No Device in {md_file}'
+                device_idx: int = keys.index('Device')
+
+                if 'mIoU' in keys:
+                    ss_idx = keys.index('mIoU')
+                elif 'mDice' in keys:
+                    ss_idx = keys.index('mDice')
+                else:
+                    raise ValueError(f'No mIoU or mDice in {md_file}')
+                if 'mIoU(ms+flip)' in keys:
+                    ms_idx = keys.index('mIoU(ms+flip)')
+                elif 'Dice' in keys:
+                    ms_idx = keys.index('Dice')
+                else:
+                    ms_idx = -1
+                config_idx = keys.index('config')
+                download_idx = keys.index('download')
+                j: int = i + 2
+                while j < len(lines) and lines[j][0] == '|':
+                    values = [value.strip() for value in lines[j].split('|')]
+                    # get config name
+                    try:
+                        config_url = re.findall(r'[a-zA-Z]+://[^\s]*py',
+                                                values[config_idx])[0]
+                        config_name = config_url.split('/')[-1]
+                        model_name = config_name.replace('.py', '')
+                    except IndexError:
+                        raise ValueError(
+                            f'config url is not found in {md_file}')
+
+                    # get model name
+                    try:
+                        weight_url = re.findall(r'[a-zA-Z]+://[^\s]*pth',
+                                                values[download_idx])[0]
+                        log_url = re.findall(r'[a-zA-Z]+://[^\s]*.json',
+                                             values[download_idx + 1])[0]
+                    except IndexError:
+                        raise ValueError(
+                            f'url is not found in {values[download_idx]}')
+
+                    # get batch size
+                    bs = re.findall(r'[0-9]*xb[0-9]*',
+                                    config_name)[0].split('xb')
+                    batch_size = int(bs[0]) * int(bs[1])
+
+                    # get crop size
+                    crop_size = values[crop_size_idx].split('x')
+                    crop_size = [int(crop_size[0]), int(crop_size[1])]
+
+                    mem = values[mem_idx].split('\\')[0] if values[
+                        mem_idx] != '-' and values[mem_idx] != '' else -1
+
+                    method = values[keys.index('Method')].strip()
+                    # method = [method.strip()] if '+' not in method else [
+                    #     m.strip() for m in method.split('+')
+                    # ]
+                    # split method name:
+                    if ' + ' in method:
+                        method = [m.strip() for m in method.split(' + ')]
+                    elif ' ' in method:
+                        method = [m for m in method.split(' ')]
+                    else:
+                        method = [method]
+                    backone: str = re.findall(
+                        r'[^\s]*', values[keys.index('Backbone')].strip())[0]
+                    archs = [backone] + method
+                    collection_name = method[0]
+                    config_path = osp.join('configs',
+                                           config_dir.split('/')[-1],
+                                           config_name)
+                    model = {
+                        'Name': model_name,
+                        'In Collection': collection_name,
+                        'Results': {
+                            'Task': 'Semantic Segmentation',
+                            'Dataset': current_dataset,
+                            'Metrics': {
+                                keys[ss_idx]: float(values[ss_idx])
+                            }
+                        },
+                        'Config': config_path,
+                        'Metadata': {
+                            'Training Data':
+                            current_dataset,
+                            'Batch Size':
+                            batch_size,
+                            'Architecture':
+                            archs,
+                            'Training Resources':
+                            f'{bs[0]}x {values[device_idx]} GPUS',
+                        },
+                        'Weights': weight_url,
+                        'Training log': log_url,
+                        'Paper': {
+                            'Title': paper_name,
+                            'URL': paper_url
+                        },
+                        'Code': code_url,
+                        'Framework': 'PyTorch'
+                    }
+                    if ms_idx != -1 and values[ms_idx] != '-' and values[
+                            ms_idx] != '':
+                        model['Results']['Metrics'].update(
+                            {keys[ms_idx]: float(values[ms_idx])})
+                    if mem != -1:
+                        model['Metadata']['Memory (GB)'] = float(mem)
+                    models.append(model)
+                    j += 1
+                i = j
+            i += 1
+
+    if not (is_dataset
+            or is_backbone) or collection_name not in collection_name_list:
+        collection = {
+            'Name': collection_name,
+            'License': 'Apache License 2.0',
+            'Metadata': {
+                'Training Data': datasets
+            },
+            'Paper': {
+                'Title': paper_name,
+                'URL': paper_url,
+            },
+            'README': osp.join('configs',
+                               config_dir.split('/')[-1], 'README.md'),
+            'Frameworks': ['PyTorch'],
+        }
+        results = {
+            'Collections': [collection],
+            'Models': models
+        }, collection_name
+    else:
+        results = {'Models': models}, ''
+
+    return results
+
+
+def dump_yaml_and_check_difference(model_info: dict, filename: str) -> bool:
+    """dump yaml file and check difference with the original file.
+
+    Args:
+        model_info (dict): model info dict.
+        filename (str): filename to save.
+    """
+    str_dump = yaml.dump(model_info, sort_keys=False)
+    if osp.isfile(filename):
+        file_exist = True
+        with open(filename, encoding='utf-8') as f:
+            str_orig = f.read()
+    else:
+        str_orig = None
+        file_exist = False
+
+    if file_exist and str_orig == str_dump:
+        is_different = False
+    else:
+        is_different = True
+        with open(filename, 'w', encoding='utf-8') as f:
+            f.write(str_dump)
+
+    return is_different
+
+
+def update_model_index(config_dir_list: List[str]) -> bool:
+    """update model index."""
+    yml_files = [
+        osp.join('configs',
+                 dir_name.split('/')[-1], 'metafile.yaml')
+        for dir_name in config_dir_list
+    ]
+    yml_files.sort()
+
+    model_index = {
+        'Import': [
+            osp.relpath(yml_file, MMSEG_ROOT).replace('\\', '/')
+            for yml_file in yml_files
+        ]
+    }
+    model_index_file = osp.join(MMSEG_ROOT, 'model-index.yml')
+    return dump_yaml_and_check_difference(model_index, model_index_file)
+
+
+if __name__ == '__main__':
+    # get md file list
+    md_file_list, config_dir_list = get_md_file_list()
+    file_modified = False
+    collection_name_list: List[str] = get_collection_name_list(md_file_list)
+    # hard code to add 'FPN'
+    collection_name_list.append('FPN')
+    # parse md file
+    for md_file, config_dir in zip(md_file_list, config_dir_list):
+        results, collection_name = get_model_info(md_file, config_dir,
+                                                  collection_name_list)
+        filename = osp.join(config_dir, 'metafile.yaml')
+        file_modified |= dump_yaml_and_check_difference(results, filename)
+        if collection_name != '':
+            collection_name_list.append(collection_name)
+
+    file_modified |= update_model_index(config_dir_list)
+    sys.exit(1 if file_modified else 0)
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index 70952b7c9e..3bc3fd09a8 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -47,10 +47,9 @@ repos:
       - id: update-model-index
         name: update-model-index
         description: Collect model information and update model-index.yml
-        entry: .dev/md2yml.py
-        additional_dependencies: [mmengine, lxml, opencv-python]
+        entry: .dev/update_model_index.py
+        additional_dependencies: [pyyaml]
         language: python
-        files: ^configs/.*\.md$
         require_serial: true
   - repo: https://github.com/asottile/pyupgrade
     rev: v3.0.0
diff --git a/configs/ann/README.md b/configs/ann/README.md
index 6cb8bc70b0..cbc1be2dc1 100644
--- a/configs/ann/README.md
+++ b/configs/ann/README.md
@@ -1,6 +1,6 @@
 # ANN
 
-[Asymmetric Non-local Neural Networks for Semantic Segmentation](https://arxiv.org/abs/1908.07678)
+> [Asymmetric Non-local Neural Networks for Semantic Segmentation](https://arxiv.org/abs/1908.07678)
 
 ## Introduction
 
@@ -22,6 +22,39 @@ The non-local module works as a particularly useful technique for semantic segme
 <img src="https://user-images.githubusercontent.com/24582831/142898322-3bbd578c-e488-4bae-9c14-7598adac5cbd.png" width="70%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                               |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ANN    | R-50-D8  | 512x1024  |   40000 | 6        | 3.71           | V100   | 77.40 |         78.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_40k_cityscapes/ann_r50-d8_512x1024_40k_cityscapes_20200605_095211-049fc292.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_40k_cityscapes/ann_r50-d8_512x1024_40k_cityscapes_20200605_095211.log.json)     |
+| ANN    | R-101-D8 | 512x1024  |   40000 | 9.5      | 2.55           | V100   | 76.55 |         78.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_40k_cityscapes/ann_r101-d8_512x1024_40k_cityscapes_20200605_095243-adf6eece.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_40k_cityscapes/ann_r101-d8_512x1024_40k_cityscapes_20200605_095243.log.json) |
+| ANN    | R-50-D8  | 769x769   |   40000 | 6.8      | 1.70           | V100   | 78.89 |         80.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_40k_cityscapes/ann_r50-d8_769x769_40k_cityscapes_20200530_025712-2b46b04d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_40k_cityscapes/ann_r50-d8_769x769_40k_cityscapes_20200530_025712.log.json)         |
+| ANN    | R-101-D8 | 769x769   |   40000 | 10.7     | 1.15           | V100   | 79.32 |         80.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_40k_cityscapes/ann_r101-d8_769x769_40k_cityscapes_20200530_025720-059bff28.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_40k_cityscapes/ann_r101-d8_769x769_40k_cityscapes_20200530_025720.log.json)     |
+| ANN    | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 77.34 |         78.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_80k_cityscapes/ann_r50-d8_512x1024_80k_cityscapes_20200607_101911-5a9ad545.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_80k_cityscapes/ann_r50-d8_512x1024_80k_cityscapes_20200607_101911.log.json)     |
+| ANN    | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 77.14 |         78.81 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_80k_cityscapes/ann_r101-d8_512x1024_80k_cityscapes_20200607_013728-aceccc6e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_80k_cityscapes/ann_r101-d8_512x1024_80k_cityscapes_20200607_013728.log.json) |
+| ANN    | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 78.88 |         80.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_80k_cityscapes/ann_r50-d8_769x769_80k_cityscapes_20200607_044426-cc7ff323.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_80k_cityscapes/ann_r50-d8_769x769_80k_cityscapes_20200607_044426.log.json)         |
+| ANN    | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 78.80 |         80.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_80k_cityscapes/ann_r101-d8_769x769_80k_cityscapes_20200607_013713-a9d4be8d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_80k_cityscapes/ann_r101-d8_769x769_80k_cityscapes_20200607_013713.log.json)     |
+
+### ADE20K
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                                               |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ANN    | R-50-D8  | 512x512   |   80000 | 9.1      | 21.01          | V100   | 41.01 |         42.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_80k_ade20k/ann_r50-d8_512x512_80k_ade20k_20200615_014818-26f75e11.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_80k_ade20k/ann_r50-d8_512x512_80k_ade20k_20200615_014818.log.json)         |
+| ANN    | R-101-D8 | 512x512   |   80000 | 12.5     | 14.12          | V100   | 42.94 |         44.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_80k_ade20k/ann_r101-d8_512x512_80k_ade20k_20200615_014818-c0153543.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_80k_ade20k/ann_r101-d8_512x512_80k_ade20k_20200615_014818.log.json)     |
+| ANN    | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 41.74 |         42.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_160k_ade20k/ann_r50-d8_512x512_160k_ade20k_20200615_231733-892247bc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_160k_ade20k/ann_r50-d8_512x512_160k_ade20k_20200615_231733.log.json)     |
+| ANN    | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 42.94 |         44.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_160k_ade20k/ann_r101-d8_512x512_160k_ade20k_20200615_231733-955eb1ec.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_160k_ade20k/ann_r101-d8_512x512_160k_ade20k_20200615_231733.log.json) |
+
+### Pascal VOC 2012 + Aug
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                   | download                                                                                                                                                                                                                                                                                                                   |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ANN    | R-50-D8  | 512x512   |   20000 | 6        | 20.92          | V100   | 74.86 |         76.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_20k_voc12aug/ann_r50-d8_512x512_20k_voc12aug_20200617_222246-dfcb1c62.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_20k_voc12aug/ann_r50-d8_512x512_20k_voc12aug_20200617_222246.log.json)     |
+| ANN    | R-101-D8 | 512x512   |   20000 | 9.5      | 13.94          | V100   | 77.47 |         78.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_20k_voc12aug/ann_r101-d8_512x512_20k_voc12aug_20200617_222246-2fad0042.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_20k_voc12aug/ann_r101-d8_512x512_20k_voc12aug_20200617_222246.log.json) |
+| ANN    | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 76.56 |         77.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_40k_voc12aug/ann_r50-d8_512x512_40k_voc12aug_20200613_231314-b5dac322.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_40k_voc12aug/ann_r50-d8_512x512_40k_voc12aug_20200613_231314.log.json)     |
+| ANN    | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 76.70 |         78.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_40k_voc12aug/ann_r101-d8_512x512_40k_voc12aug_20200613_231314-bd205bbe.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_40k_voc12aug/ann_r101-d8_512x512_40k_voc12aug_20200613_231314.log.json) |
+
 ## Citation
 
 ```bibtex
@@ -33,36 +66,3 @@ The non-local module works as a particularly useful technique for semantic segme
   year={2019}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                               |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| ANN    | R-50-D8  | 512x1024  |   40000 | 6        | 3.71           | 77.40 |         78.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_40k_cityscapes/ann_r50-d8_512x1024_40k_cityscapes_20200605_095211-049fc292.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_40k_cityscapes/ann_r50-d8_512x1024_40k_cityscapes_20200605_095211.log.json)     |
-| ANN    | R-101-D8 | 512x1024  |   40000 | 9.5      | 2.55           | 76.55 |         78.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_40k_cityscapes/ann_r101-d8_512x1024_40k_cityscapes_20200605_095243-adf6eece.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_40k_cityscapes/ann_r101-d8_512x1024_40k_cityscapes_20200605_095243.log.json) |
-| ANN    | R-50-D8  | 769x769   |   40000 | 6.8      | 1.70           | 78.89 |         80.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_40k_cityscapes/ann_r50-d8_769x769_40k_cityscapes_20200530_025712-2b46b04d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_40k_cityscapes/ann_r50-d8_769x769_40k_cityscapes_20200530_025712.log.json)         |
-| ANN    | R-101-D8 | 769x769   |   40000 | 10.7     | 1.15           | 79.32 |         80.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_40k_cityscapes/ann_r101-d8_769x769_40k_cityscapes_20200530_025720-059bff28.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_40k_cityscapes/ann_r101-d8_769x769_40k_cityscapes_20200530_025720.log.json)     |
-| ANN    | R-50-D8  | 512x1024  |   80000 | -        | -              | 77.34 |         78.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_80k_cityscapes/ann_r50-d8_512x1024_80k_cityscapes_20200607_101911-5a9ad545.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_80k_cityscapes/ann_r50-d8_512x1024_80k_cityscapes_20200607_101911.log.json)     |
-| ANN    | R-101-D8 | 512x1024  |   80000 | -        | -              | 77.14 |         78.81 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_80k_cityscapes/ann_r101-d8_512x1024_80k_cityscapes_20200607_013728-aceccc6e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_80k_cityscapes/ann_r101-d8_512x1024_80k_cityscapes_20200607_013728.log.json) |
-| ANN    | R-50-D8  | 769x769   |   80000 | -        | -              | 78.88 |         80.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_80k_cityscapes/ann_r50-d8_769x769_80k_cityscapes_20200607_044426-cc7ff323.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_80k_cityscapes/ann_r50-d8_769x769_80k_cityscapes_20200607_044426.log.json)         |
-| ANN    | R-101-D8 | 769x769   |   80000 | -        | -              | 78.80 |         80.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_80k_cityscapes/ann_r101-d8_769x769_80k_cityscapes_20200607_013713-a9d4be8d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_80k_cityscapes/ann_r101-d8_769x769_80k_cityscapes_20200607_013713.log.json)     |
-
-### ADE20K
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                                               |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| ANN    | R-50-D8  | 512x512   |   80000 | 9.1      | 21.01          | 41.01 |         42.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_80k_ade20k/ann_r50-d8_512x512_80k_ade20k_20200615_014818-26f75e11.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_80k_ade20k/ann_r50-d8_512x512_80k_ade20k_20200615_014818.log.json)         |
-| ANN    | R-101-D8 | 512x512   |   80000 | 12.5     | 14.12          | 42.94 |         44.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_80k_ade20k/ann_r101-d8_512x512_80k_ade20k_20200615_014818-c0153543.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_80k_ade20k/ann_r101-d8_512x512_80k_ade20k_20200615_014818.log.json)     |
-| ANN    | R-50-D8  | 512x512   |  160000 | -        | -              | 41.74 |         42.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_160k_ade20k/ann_r50-d8_512x512_160k_ade20k_20200615_231733-892247bc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_160k_ade20k/ann_r50-d8_512x512_160k_ade20k_20200615_231733.log.json)     |
-| ANN    | R-101-D8 | 512x512   |  160000 | -        | -              | 42.94 |         44.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_160k_ade20k/ann_r101-d8_512x512_160k_ade20k_20200615_231733-955eb1ec.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_160k_ade20k/ann_r101-d8_512x512_160k_ade20k_20200615_231733.log.json) |
-
-### Pascal VOC 2012 + Aug
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                   | download                                                                                                                                                                                                                                                                                                                   |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| ANN    | R-50-D8  | 512x512   |   20000 | 6        | 20.92          | 74.86 |         76.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_20k_voc12aug/ann_r50-d8_512x512_20k_voc12aug_20200617_222246-dfcb1c62.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_20k_voc12aug/ann_r50-d8_512x512_20k_voc12aug_20200617_222246.log.json)     |
-| ANN    | R-101-D8 | 512x512   |   20000 | 9.5      | 13.94          | 77.47 |         78.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_20k_voc12aug/ann_r101-d8_512x512_20k_voc12aug_20200617_222246-2fad0042.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_20k_voc12aug/ann_r101-d8_512x512_20k_voc12aug_20200617_222246.log.json) |
-| ANN    | R-50-D8  | 512x512   |   40000 | -        | -              | 76.56 |         77.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_40k_voc12aug/ann_r50-d8_512x512_40k_voc12aug_20200613_231314-b5dac322.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_40k_voc12aug/ann_r50-d8_512x512_40k_voc12aug_20200613_231314.log.json)     |
-| ANN    | R-101-D8 | 512x512   |   40000 | -        | -              | 76.70 |         78.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_40k_voc12aug/ann_r101-d8_512x512_40k_voc12aug_20200613_231314-bd205bbe.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_40k_voc12aug/ann_r101-d8_512x512_40k_voc12aug_20200613_231314.log.json) |
diff --git a/configs/ann/ann.yml b/configs/ann/ann.yml
deleted file mode 100644
index 36721992f9..0000000000
--- a/configs/ann/ann.yml
+++ /dev/null
@@ -1,305 +0,0 @@
-Collections:
-- Name: ANN
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-    - Pascal VOC 2012 + Aug
-  Paper:
-    URL: https://arxiv.org/abs/1908.07678
-    Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
-  README: configs/ann/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ann_head.py#L185
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/MendelXu/ANN
-Models:
-- Name: ann_r50-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: ANN
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 269.54
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 6.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.4
-      mIoU(ms+flip): 78.57
-  Config: configs/ann/ann_r50-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_40k_cityscapes/ann_r50-d8_512x1024_40k_cityscapes_20200605_095211-049fc292.pth
-- Name: ann_r101-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: ANN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 392.16
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 9.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.55
-      mIoU(ms+flip): 78.85
-  Config: configs/ann/ann_r101-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_40k_cityscapes/ann_r101-d8_512x1024_40k_cityscapes_20200605_095243-adf6eece.pth
-- Name: ann_r50-d8_4xb2-40k_cityscapes-769x769
-  In Collection: ANN
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 588.24
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 6.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.89
-      mIoU(ms+flip): 80.46
-  Config: configs/ann/ann_r50-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_40k_cityscapes/ann_r50-d8_769x769_40k_cityscapes_20200530_025712-2b46b04d.pth
-- Name: ann_r101-d8_4xb2-40k_cityscapes-769x769
-  In Collection: ANN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 869.57
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 10.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.32
-      mIoU(ms+flip): 80.94
-  Config: configs/ann/ann_r101-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_40k_cityscapes/ann_r101-d8_769x769_40k_cityscapes_20200530_025720-059bff28.pth
-- Name: ann_r50-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: ANN
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.34
-      mIoU(ms+flip): 78.65
-  Config: configs/ann/ann_r50-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_80k_cityscapes/ann_r50-d8_512x1024_80k_cityscapes_20200607_101911-5a9ad545.pth
-- Name: ann_r101-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: ANN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.14
-      mIoU(ms+flip): 78.81
-  Config: configs/ann/ann_r101-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_80k_cityscapes/ann_r101-d8_512x1024_80k_cityscapes_20200607_013728-aceccc6e.pth
-- Name: ann_r50-d8_4xb2-80k_cityscapes-769x769
-  In Collection: ANN
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.88
-      mIoU(ms+flip): 80.57
-  Config: configs/ann/ann_r50-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_80k_cityscapes/ann_r50-d8_769x769_80k_cityscapes_20200607_044426-cc7ff323.pth
-- Name: ann_r101-d8_4xb2-80k_cityscapes-769x769
-  In Collection: ANN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.8
-      mIoU(ms+flip): 80.34
-  Config: configs/ann/ann_r101-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_80k_cityscapes/ann_r101-d8_769x769_80k_cityscapes_20200607_013713-a9d4be8d.pth
-- Name: ann_r50-d8_4xb4-80k_ade20k-512x512
-  In Collection: ANN
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 47.6
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 41.01
-      mIoU(ms+flip): 42.3
-  Config: configs/ann/ann_r50-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_80k_ade20k/ann_r50-d8_512x512_80k_ade20k_20200615_014818-26f75e11.pth
-- Name: ann_r101-d8_4xb4-80k_ade20k-512x512
-  In Collection: ANN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 70.82
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 12.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.94
-      mIoU(ms+flip): 44.18
-  Config: configs/ann/ann_r101-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_80k_ade20k/ann_r101-d8_512x512_80k_ade20k_20200615_014818-c0153543.pth
-- Name: ann_r50-d8_4xb4-160k_ade20k-512x512
-  In Collection: ANN
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 41.74
-      mIoU(ms+flip): 42.62
-  Config: configs/ann/ann_r50-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_160k_ade20k/ann_r50-d8_512x512_160k_ade20k_20200615_231733-892247bc.pth
-- Name: ann_r101-d8_4xb4-160k_ade20k-512x512
-  In Collection: ANN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.94
-      mIoU(ms+flip): 44.06
-  Config: configs/ann/ann_r101-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_160k_ade20k/ann_r101-d8_512x512_160k_ade20k_20200615_231733-955eb1ec.pth
-- Name: ann_r50-d8_4xb4-20k_voc12aug-512x512
-  In Collection: ANN
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 47.8
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 74.86
-      mIoU(ms+flip): 76.13
-  Config: configs/ann/ann_r50-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_20k_voc12aug/ann_r50-d8_512x512_20k_voc12aug_20200617_222246-dfcb1c62.pth
-- Name: ann_r101-d8_4xb4-20k_voc12aug-512x512
-  In Collection: ANN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 71.74
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 77.47
-      mIoU(ms+flip): 78.7
-  Config: configs/ann/ann_r101-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_20k_voc12aug/ann_r101-d8_512x512_20k_voc12aug_20200617_222246-2fad0042.pth
-- Name: ann_r50-d8_4xb4-40k_voc12aug-512x512
-  In Collection: ANN
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 76.56
-      mIoU(ms+flip): 77.51
-  Config: configs/ann/ann_r50-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_40k_voc12aug/ann_r50-d8_512x512_40k_voc12aug_20200613_231314-b5dac322.pth
-- Name: ann_r101-d8_4xb4-40k_voc12aug-512x512
-  In Collection: ANN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 76.7
-      mIoU(ms+flip): 78.06
-  Config: configs/ann/ann_r101-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_40k_voc12aug/ann_r101-d8_512x512_40k_voc12aug_20200613_231314-bd205bbe.pth
diff --git a/configs/ann/metafile.yaml b/configs/ann/metafile.yaml
new file mode 100644
index 0000000000..0d118681fd
--- /dev/null
+++ b/configs/ann/metafile.yaml
@@ -0,0 +1,391 @@
+Collections:
+- Name: ANN
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - ADE20K
+    - Pascal VOC 2012 + Aug
+  Paper:
+    Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1908.07678
+  README: configs/ann/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: ann_r50-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: ANN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.4
+      mIoU(ms+flip): 78.57
+  Config: configs/ann/ann_r50-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - ANN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_40k_cityscapes/ann_r50-d8_512x1024_40k_cityscapes_20200605_095211-049fc292.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_40k_cityscapes/ann_r50-d8_512x1024_40k_cityscapes_20200605_095211.log.json
+  Paper:
+    Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1908.07678
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ann_head.py#L185
+  Framework: PyTorch
+- Name: ann_r101-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: ANN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.55
+      mIoU(ms+flip): 78.85
+  Config: configs/ann/ann_r101-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - ANN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_40k_cityscapes/ann_r101-d8_512x1024_40k_cityscapes_20200605_095243-adf6eece.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_40k_cityscapes/ann_r101-d8_512x1024_40k_cityscapes_20200605_095243.log.json
+  Paper:
+    Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1908.07678
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ann_head.py#L185
+  Framework: PyTorch
+- Name: ann_r50-d8_4xb2-40k_cityscapes-769x769
+  In Collection: ANN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.89
+      mIoU(ms+flip): 80.46
+  Config: configs/ann/ann_r50-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - ANN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_40k_cityscapes/ann_r50-d8_769x769_40k_cityscapes_20200530_025712-2b46b04d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_40k_cityscapes/ann_r50-d8_769x769_40k_cityscapes_20200530_025712.log.json
+  Paper:
+    Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1908.07678
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ann_head.py#L185
+  Framework: PyTorch
+- Name: ann_r101-d8_4xb2-40k_cityscapes-769x769
+  In Collection: ANN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.32
+      mIoU(ms+flip): 80.94
+  Config: configs/ann/ann_r101-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - ANN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_40k_cityscapes/ann_r101-d8_769x769_40k_cityscapes_20200530_025720-059bff28.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_40k_cityscapes/ann_r101-d8_769x769_40k_cityscapes_20200530_025720.log.json
+  Paper:
+    Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1908.07678
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ann_head.py#L185
+  Framework: PyTorch
+- Name: ann_r50-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: ANN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.34
+      mIoU(ms+flip): 78.65
+  Config: configs/ann/ann_r50-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - ANN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_80k_cityscapes/ann_r50-d8_512x1024_80k_cityscapes_20200607_101911-5a9ad545.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_80k_cityscapes/ann_r50-d8_512x1024_80k_cityscapes_20200607_101911.log.json
+  Paper:
+    Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1908.07678
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ann_head.py#L185
+  Framework: PyTorch
+- Name: ann_r101-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: ANN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.14
+      mIoU(ms+flip): 78.81
+  Config: configs/ann/ann_r101-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - ANN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_80k_cityscapes/ann_r101-d8_512x1024_80k_cityscapes_20200607_013728-aceccc6e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_80k_cityscapes/ann_r101-d8_512x1024_80k_cityscapes_20200607_013728.log.json
+  Paper:
+    Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1908.07678
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ann_head.py#L185
+  Framework: PyTorch
+- Name: ann_r50-d8_4xb2-80k_cityscapes-769x769
+  In Collection: ANN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.88
+      mIoU(ms+flip): 80.57
+  Config: configs/ann/ann_r50-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - ANN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_80k_cityscapes/ann_r50-d8_769x769_80k_cityscapes_20200607_044426-cc7ff323.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_80k_cityscapes/ann_r50-d8_769x769_80k_cityscapes_20200607_044426.log.json
+  Paper:
+    Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1908.07678
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ann_head.py#L185
+  Framework: PyTorch
+- Name: ann_r101-d8_4xb2-80k_cityscapes-769x769
+  In Collection: ANN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.8
+      mIoU(ms+flip): 80.34
+  Config: configs/ann/ann_r101-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - ANN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_80k_cityscapes/ann_r101-d8_769x769_80k_cityscapes_20200607_013713-a9d4be8d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_80k_cityscapes/ann_r101-d8_769x769_80k_cityscapes_20200607_013713.log.json
+  Paper:
+    Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1908.07678
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ann_head.py#L185
+  Framework: PyTorch
+- Name: ann_r50-d8_4xb4-80k_ade20k-512x512
+  In Collection: ANN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 41.01
+      mIoU(ms+flip): 42.3
+  Config: configs/ann/ann_r50-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - ANN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_80k_ade20k/ann_r50-d8_512x512_80k_ade20k_20200615_014818-26f75e11.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_80k_ade20k/ann_r50-d8_512x512_80k_ade20k_20200615_014818.log.json
+  Paper:
+    Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1908.07678
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ann_head.py#L185
+  Framework: PyTorch
+- Name: ann_r101-d8_4xb4-80k_ade20k-512x512
+  In Collection: ANN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.94
+      mIoU(ms+flip): 44.18
+  Config: configs/ann/ann_r101-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - ANN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 12.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_80k_ade20k/ann_r101-d8_512x512_80k_ade20k_20200615_014818-c0153543.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_80k_ade20k/ann_r101-d8_512x512_80k_ade20k_20200615_014818.log.json
+  Paper:
+    Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1908.07678
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ann_head.py#L185
+  Framework: PyTorch
+- Name: ann_r50-d8_4xb4-160k_ade20k-512x512
+  In Collection: ANN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 41.74
+      mIoU(ms+flip): 42.62
+  Config: configs/ann/ann_r50-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - ANN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_160k_ade20k/ann_r50-d8_512x512_160k_ade20k_20200615_231733-892247bc.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_160k_ade20k/ann_r50-d8_512x512_160k_ade20k_20200615_231733.log.json
+  Paper:
+    Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1908.07678
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ann_head.py#L185
+  Framework: PyTorch
+- Name: ann_r101-d8_4xb4-160k_ade20k-512x512
+  In Collection: ANN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.94
+      mIoU(ms+flip): 44.06
+  Config: configs/ann/ann_r101-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - ANN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_160k_ade20k/ann_r101-d8_512x512_160k_ade20k_20200615_231733-955eb1ec.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_160k_ade20k/ann_r101-d8_512x512_160k_ade20k_20200615_231733.log.json
+  Paper:
+    Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1908.07678
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ann_head.py#L185
+  Framework: PyTorch
+- Name: ann_r50-d8_4xb4-20k_voc12aug-512x512
+  In Collection: ANN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 74.86
+      mIoU(ms+flip): 76.13
+  Config: configs/ann/ann_r50-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - ANN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_20k_voc12aug/ann_r50-d8_512x512_20k_voc12aug_20200617_222246-dfcb1c62.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_20k_voc12aug/ann_r50-d8_512x512_20k_voc12aug_20200617_222246.log.json
+  Paper:
+    Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1908.07678
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ann_head.py#L185
+  Framework: PyTorch
+- Name: ann_r101-d8_4xb4-20k_voc12aug-512x512
+  In Collection: ANN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 77.47
+      mIoU(ms+flip): 78.7
+  Config: configs/ann/ann_r101-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - ANN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_20k_voc12aug/ann_r101-d8_512x512_20k_voc12aug_20200617_222246-2fad0042.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_20k_voc12aug/ann_r101-d8_512x512_20k_voc12aug_20200617_222246.log.json
+  Paper:
+    Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1908.07678
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ann_head.py#L185
+  Framework: PyTorch
+- Name: ann_r50-d8_4xb4-40k_voc12aug-512x512
+  In Collection: ANN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 76.56
+      mIoU(ms+flip): 77.51
+  Config: configs/ann/ann_r50-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - ANN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_40k_voc12aug/ann_r50-d8_512x512_40k_voc12aug_20200613_231314-b5dac322.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_40k_voc12aug/ann_r50-d8_512x512_40k_voc12aug_20200613_231314.log.json
+  Paper:
+    Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1908.07678
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ann_head.py#L185
+  Framework: PyTorch
+- Name: ann_r101-d8_4xb4-40k_voc12aug-512x512
+  In Collection: ANN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 76.7
+      mIoU(ms+flip): 78.06
+  Config: configs/ann/ann_r101-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - ANN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_40k_voc12aug/ann_r101-d8_512x512_40k_voc12aug_20200613_231314-bd205bbe.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_40k_voc12aug/ann_r101-d8_512x512_40k_voc12aug_20200613_231314.log.json
+  Paper:
+    Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1908.07678
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ann_head.py#L185
+  Framework: PyTorch
diff --git a/configs/apcnet/README.md b/configs/apcnet/README.md
index 11fb1a1454..0d7f1d6614 100644
--- a/configs/apcnet/README.md
+++ b/configs/apcnet/README.md
@@ -1,6 +1,6 @@
 # APCNet
 
-[Adaptive Pyramid Context Network for Semantic Segmentation](https://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html)
+> [Adaptive Pyramid Context Network for Semantic Segmentation](https://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html)
 
 ## Introduction
 
@@ -22,6 +22,30 @@ Recent studies witnessed that context features can significantly improve the per
 <img src="https://user-images.githubusercontent.com/24582831/142898638-e1c0c6ae-9270-448e-aa01-bbac3a236db5.png" width="70%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| APCNet | R-50-D8  | 512x1024  |   40000 | 7.7      | 3.57           | V100   | 78.02 |         79.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_40k_cityscapes/apcnet_r50-d8_512x1024_40k_cityscapes_20201214_115717-5e88fa33.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_40k_cityscapes/apcnet_r50-d8_512x1024_40k_cityscapes-20201214_115717.log.json)     |
+| APCNet | R-101-D8 | 512x1024  |   40000 | 11.2     | 2.15           | V100   | 79.08 |         80.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_40k_cityscapes/apcnet_r101-d8_512x1024_40k_cityscapes_20201214_115716-abc9d111.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_40k_cityscapes/apcnet_r101-d8_512x1024_40k_cityscapes-20201214_115716.log.json) |
+| APCNet | R-50-D8  | 769x769   |   40000 | 8.7      | 1.52           | V100   | 77.89 |         79.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_40k_cityscapes/apcnet_r50-d8_769x769_40k_cityscapes_20201214_115717-2a2628d7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_40k_cityscapes/apcnet_r50-d8_769x769_40k_cityscapes-20201214_115717.log.json)         |
+| APCNet | R-101-D8 | 769x769   |   40000 | 12.7     | 1.03           | V100   | 77.96 |         79.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_40k_cityscapes/apcnet_r101-d8_769x769_40k_cityscapes_20201214_115718-b650de90.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_40k_cityscapes/apcnet_r101-d8_769x769_40k_cityscapes-20201214_115718.log.json)     |
+| APCNet | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 78.96 |         79.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_80k_cityscapes/apcnet_r50-d8_512x1024_80k_cityscapes_20201214_115716-987f51e3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_80k_cityscapes/apcnet_r50-d8_512x1024_80k_cityscapes-20201214_115716.log.json)     |
+| APCNet | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 79.64 |         80.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_80k_cityscapes/apcnet_r101-d8_512x1024_80k_cityscapes_20201214_115705-b1ff208a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_80k_cityscapes/apcnet_r101-d8_512x1024_80k_cityscapes-20201214_115705.log.json) |
+| APCNet | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 78.79 |         80.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_80k_cityscapes/apcnet_r50-d8_769x769_80k_cityscapes_20201214_115718-7ea9fa12.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_80k_cityscapes/apcnet_r50-d8_769x769_80k_cityscapes-20201214_115718.log.json)         |
+| APCNet | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 78.45 |         79.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_80k_cityscapes/apcnet_r101-d8_769x769_80k_cityscapes_20201214_115716-a7fbc2ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_80k_cityscapes/apcnet_r101-d8_769x769_80k_cityscapes-20201214_115716.log.json)     |
+
+### ADE20K
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| APCNet | R-50-D8  | 512x512   |   80000 | 10.1     | 19.61          | V100   | 42.20 |         43.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_80k_ade20k/apcnet_r50-d8_512x512_80k_ade20k_20201214_115705-a8626293.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_80k_ade20k/apcnet_r50-d8_512x512_80k_ade20k-20201214_115705.log.json)         |
+| APCNet | R-101-D8 | 512x512   |   80000 | 13.6     | 13.10          | V100   | 45.54 |         46.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_80k_ade20k/apcnet_r101-d8_512x512_80k_ade20k_20201214_115704-c656c3fb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_80k_ade20k/apcnet_r101-d8_512x512_80k_ade20k-20201214_115704.log.json)     |
+| APCNet | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 43.40 |         43.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_160k_ade20k/apcnet_r50-d8_512x512_160k_ade20k_20201214_115706-25fb92c2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_160k_ade20k/apcnet_r50-d8_512x512_160k_ade20k-20201214_115706.log.json)     |
+| APCNet | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 45.41 |         46.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_160k_ade20k/apcnet_r101-d8_512x512_160k_ade20k_20201214_115705-73f9a8d7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_160k_ade20k/apcnet_r101-d8_512x512_160k_ade20k-20201214_115705.log.json) |
+
 ## Citation
 
 ```bibtex
@@ -33,27 +57,3 @@ month = {June},
 year = {2019}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| APCNet | R-50-D8  | 512x1024  |   40000 | 7.7      | 3.57           | 78.02 |         79.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_40k_cityscapes/apcnet_r50-d8_512x1024_40k_cityscapes_20201214_115717-5e88fa33.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_40k_cityscapes/apcnet_r50-d8_512x1024_40k_cityscapes-20201214_115717.log.json)     |
-| APCNet | R-101-D8 | 512x1024  |   40000 | 11.2     | 2.15           | 79.08 |         80.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_40k_cityscapes/apcnet_r101-d8_512x1024_40k_cityscapes_20201214_115716-abc9d111.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_40k_cityscapes/apcnet_r101-d8_512x1024_40k_cityscapes-20201214_115716.log.json) |
-| APCNet | R-50-D8  | 769x769   |   40000 | 8.7      | 1.52           | 77.89 |         79.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_40k_cityscapes/apcnet_r50-d8_769x769_40k_cityscapes_20201214_115717-2a2628d7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_40k_cityscapes/apcnet_r50-d8_769x769_40k_cityscapes-20201214_115717.log.json)         |
-| APCNet | R-101-D8 | 769x769   |   40000 | 12.7     | 1.03           | 77.96 |         79.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_40k_cityscapes/apcnet_r101-d8_769x769_40k_cityscapes_20201214_115718-b650de90.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_40k_cityscapes/apcnet_r101-d8_769x769_40k_cityscapes-20201214_115718.log.json)     |
-| APCNet | R-50-D8  | 512x1024  |   80000 | -        | -              | 78.96 |         79.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_80k_cityscapes/apcnet_r50-d8_512x1024_80k_cityscapes_20201214_115716-987f51e3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_80k_cityscapes/apcnet_r50-d8_512x1024_80k_cityscapes-20201214_115716.log.json)     |
-| APCNet | R-101-D8 | 512x1024  |   80000 | -        | -              | 79.64 |         80.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_80k_cityscapes/apcnet_r101-d8_512x1024_80k_cityscapes_20201214_115705-b1ff208a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_80k_cityscapes/apcnet_r101-d8_512x1024_80k_cityscapes-20201214_115705.log.json) |
-| APCNet | R-50-D8  | 769x769   |   80000 | -        | -              | 78.79 |         80.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_80k_cityscapes/apcnet_r50-d8_769x769_80k_cityscapes_20201214_115718-7ea9fa12.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_80k_cityscapes/apcnet_r50-d8_769x769_80k_cityscapes-20201214_115718.log.json)         |
-| APCNet | R-101-D8 | 769x769   |   80000 | -        | -              | 78.45 |         79.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_80k_cityscapes/apcnet_r101-d8_769x769_80k_cityscapes_20201214_115716-a7fbc2ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_80k_cityscapes/apcnet_r101-d8_769x769_80k_cityscapes-20201214_115716.log.json)     |
-
-### ADE20K
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| APCNet | R-50-D8  | 512x512   |   80000 | 10.1     | 19.61          | 42.20 |         43.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_80k_ade20k/apcnet_r50-d8_512x512_80k_ade20k_20201214_115705-a8626293.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_80k_ade20k/apcnet_r50-d8_512x512_80k_ade20k-20201214_115705.log.json)         |
-| APCNet | R-101-D8 | 512x512   |   80000 | 13.6     | 13.10          | 45.54 |         46.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_80k_ade20k/apcnet_r101-d8_512x512_80k_ade20k_20201214_115704-c656c3fb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_80k_ade20k/apcnet_r101-d8_512x512_80k_ade20k-20201214_115704.log.json)     |
-| APCNet | R-50-D8  | 512x512   |  160000 | -        | -              | 43.40 |         43.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_160k_ade20k/apcnet_r50-d8_512x512_160k_ade20k_20201214_115706-25fb92c2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_160k_ade20k/apcnet_r50-d8_512x512_160k_ade20k-20201214_115706.log.json)     |
-| APCNet | R-101-D8 | 512x512   |  160000 | -        | -              | 45.41 |         46.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_160k_ade20k/apcnet_r101-d8_512x512_160k_ade20k_20201214_115705-73f9a8d7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_160k_ade20k/apcnet_r101-d8_512x512_160k_ade20k-20201214_115705.log.json) |
diff --git a/configs/apcnet/apcnet.yml b/configs/apcnet/apcnet.yml
deleted file mode 100644
index 737da973d4..0000000000
--- a/configs/apcnet/apcnet.yml
+++ /dev/null
@@ -1,232 +0,0 @@
-Collections:
-- Name: APCNet
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-  Paper:
-    URL: https://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html
-    Title: Adaptive Pyramid Context Network for Semantic Segmentation
-  README: configs/apcnet/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/Junjun2016/APCNet
-Models:
-- Name: apcnet_r50-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: APCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 280.11
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 7.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.02
-      mIoU(ms+flip): 79.26
-  Config: configs/apcnet/apcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_40k_cityscapes/apcnet_r50-d8_512x1024_40k_cityscapes_20201214_115717-5e88fa33.pth
-- Name: apcnet_r101-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: APCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 465.12
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 11.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.08
-      mIoU(ms+flip): 80.34
-  Config: configs/apcnet/apcnet_r101-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_40k_cityscapes/apcnet_r101-d8_512x1024_40k_cityscapes_20201214_115716-abc9d111.pth
-- Name: apcnet_r50-d8_4xb2-40k_cityscapes-769x769
-  In Collection: APCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 657.89
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 8.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.89
-      mIoU(ms+flip): 79.75
-  Config: configs/apcnet/apcnet_r50-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_40k_cityscapes/apcnet_r50-d8_769x769_40k_cityscapes_20201214_115717-2a2628d7.pth
-- Name: apcnet_r101-d8_4xb2-40k_cityscapes-769x769
-  In Collection: APCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 970.87
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 12.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.96
-      mIoU(ms+flip): 79.24
-  Config: configs/apcnet/apcnet_r101-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_40k_cityscapes/apcnet_r101-d8_769x769_40k_cityscapes_20201214_115718-b650de90.pth
-- Name: apcnet_r50-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: APCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.96
-      mIoU(ms+flip): 79.94
-  Config: configs/apcnet/apcnet_r50-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_80k_cityscapes/apcnet_r50-d8_512x1024_80k_cityscapes_20201214_115716-987f51e3.pth
-- Name: apcnet_r101-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: APCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.64
-      mIoU(ms+flip): 80.61
-  Config: configs/apcnet/apcnet_r101-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_80k_cityscapes/apcnet_r101-d8_512x1024_80k_cityscapes_20201214_115705-b1ff208a.pth
-- Name: apcnet_r50-d8_4xb2-80k_cityscapes-769x769
-  In Collection: APCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.79
-      mIoU(ms+flip): 80.35
-  Config: configs/apcnet/apcnet_r50-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_80k_cityscapes/apcnet_r50-d8_769x769_80k_cityscapes_20201214_115718-7ea9fa12.pth
-- Name: apcnet_r101-d8_4xb2-80k_cityscapes-769x769
-  In Collection: APCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.45
-      mIoU(ms+flip): 79.91
-  Config: configs/apcnet/apcnet_r101-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_80k_cityscapes/apcnet_r101-d8_769x769_80k_cityscapes_20201214_115716-a7fbc2ab.pth
-- Name: apcnet_r50-d8_4xb4-80k_ade20k-512x512
-  In Collection: APCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 50.99
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 10.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.2
-      mIoU(ms+flip): 43.3
-  Config: configs/apcnet/apcnet_r50-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_80k_ade20k/apcnet_r50-d8_512x512_80k_ade20k_20201214_115705-a8626293.pth
-- Name: apcnet_r101-d8_4xb4-80k_ade20k-512x512
-  In Collection: APCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 76.34
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 13.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.54
-      mIoU(ms+flip): 46.65
-  Config: configs/apcnet/apcnet_r101-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_80k_ade20k/apcnet_r101-d8_512x512_80k_ade20k_20201214_115704-c656c3fb.pth
-- Name: apcnet_r50-d8_4xb4-160k_ade20k-512x512
-  In Collection: APCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.4
-      mIoU(ms+flip): 43.94
-  Config: configs/apcnet/apcnet_r50-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_160k_ade20k/apcnet_r50-d8_512x512_160k_ade20k_20201214_115706-25fb92c2.pth
-- Name: apcnet_r101-d8_4xb4-160k_ade20k-512x512
-  In Collection: APCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.41
-      mIoU(ms+flip): 46.63
-  Config: configs/apcnet/apcnet_r101-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_160k_ade20k/apcnet_r101-d8_512x512_160k_ade20k_20201214_115705-73f9a8d7.pth
diff --git a/configs/apcnet/metafile.yaml b/configs/apcnet/metafile.yaml
new file mode 100644
index 0000000000..3f4072c8fd
--- /dev/null
+++ b/configs/apcnet/metafile.yaml
@@ -0,0 +1,296 @@
+Collections:
+- Name: APCNet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - ADE20K
+  Paper:
+    Title: Adaptive Pyramid Context Network for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html
+  README: configs/apcnet/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: apcnet_r50-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: APCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.02
+      mIoU(ms+flip): 79.26
+  Config: configs/apcnet/apcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - APCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_40k_cityscapes/apcnet_r50-d8_512x1024_40k_cityscapes_20201214_115717-5e88fa33.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_40k_cityscapes/apcnet_r50-d8_512x1024_40k_cityscapes-20201214_115717.log.json
+  Paper:
+    Title: Adaptive Pyramid Context Network for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: apcnet_r101-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: APCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.08
+      mIoU(ms+flip): 80.34
+  Config: configs/apcnet/apcnet_r101-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - APCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 11.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_40k_cityscapes/apcnet_r101-d8_512x1024_40k_cityscapes_20201214_115716-abc9d111.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_40k_cityscapes/apcnet_r101-d8_512x1024_40k_cityscapes-20201214_115716.log.json
+  Paper:
+    Title: Adaptive Pyramid Context Network for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: apcnet_r50-d8_4xb2-40k_cityscapes-769x769
+  In Collection: APCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.89
+      mIoU(ms+flip): 79.75
+  Config: configs/apcnet/apcnet_r50-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - APCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_40k_cityscapes/apcnet_r50-d8_769x769_40k_cityscapes_20201214_115717-2a2628d7.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_40k_cityscapes/apcnet_r50-d8_769x769_40k_cityscapes-20201214_115717.log.json
+  Paper:
+    Title: Adaptive Pyramid Context Network for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: apcnet_r101-d8_4xb2-40k_cityscapes-769x769
+  In Collection: APCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.96
+      mIoU(ms+flip): 79.24
+  Config: configs/apcnet/apcnet_r101-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - APCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 12.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_40k_cityscapes/apcnet_r101-d8_769x769_40k_cityscapes_20201214_115718-b650de90.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_40k_cityscapes/apcnet_r101-d8_769x769_40k_cityscapes-20201214_115718.log.json
+  Paper:
+    Title: Adaptive Pyramid Context Network for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: apcnet_r50-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: APCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.96
+      mIoU(ms+flip): 79.94
+  Config: configs/apcnet/apcnet_r50-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - APCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_80k_cityscapes/apcnet_r50-d8_512x1024_80k_cityscapes_20201214_115716-987f51e3.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_80k_cityscapes/apcnet_r50-d8_512x1024_80k_cityscapes-20201214_115716.log.json
+  Paper:
+    Title: Adaptive Pyramid Context Network for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: apcnet_r101-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: APCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.64
+      mIoU(ms+flip): 80.61
+  Config: configs/apcnet/apcnet_r101-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - APCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_80k_cityscapes/apcnet_r101-d8_512x1024_80k_cityscapes_20201214_115705-b1ff208a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_80k_cityscapes/apcnet_r101-d8_512x1024_80k_cityscapes-20201214_115705.log.json
+  Paper:
+    Title: Adaptive Pyramid Context Network for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: apcnet_r50-d8_4xb2-80k_cityscapes-769x769
+  In Collection: APCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.79
+      mIoU(ms+flip): 80.35
+  Config: configs/apcnet/apcnet_r50-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - APCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_80k_cityscapes/apcnet_r50-d8_769x769_80k_cityscapes_20201214_115718-7ea9fa12.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_80k_cityscapes/apcnet_r50-d8_769x769_80k_cityscapes-20201214_115718.log.json
+  Paper:
+    Title: Adaptive Pyramid Context Network for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: apcnet_r101-d8_4xb2-80k_cityscapes-769x769
+  In Collection: APCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.45
+      mIoU(ms+flip): 79.91
+  Config: configs/apcnet/apcnet_r101-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - APCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_80k_cityscapes/apcnet_r101-d8_769x769_80k_cityscapes_20201214_115716-a7fbc2ab.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_80k_cityscapes/apcnet_r101-d8_769x769_80k_cityscapes-20201214_115716.log.json
+  Paper:
+    Title: Adaptive Pyramid Context Network for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: apcnet_r50-d8_4xb4-80k_ade20k-512x512
+  In Collection: APCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.2
+      mIoU(ms+flip): 43.3
+  Config: configs/apcnet/apcnet_r50-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - APCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_80k_ade20k/apcnet_r50-d8_512x512_80k_ade20k_20201214_115705-a8626293.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_80k_ade20k/apcnet_r50-d8_512x512_80k_ade20k-20201214_115705.log.json
+  Paper:
+    Title: Adaptive Pyramid Context Network for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: apcnet_r101-d8_4xb4-80k_ade20k-512x512
+  In Collection: APCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.54
+      mIoU(ms+flip): 46.65
+  Config: configs/apcnet/apcnet_r101-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - APCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 13.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_80k_ade20k/apcnet_r101-d8_512x512_80k_ade20k_20201214_115704-c656c3fb.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_80k_ade20k/apcnet_r101-d8_512x512_80k_ade20k-20201214_115704.log.json
+  Paper:
+    Title: Adaptive Pyramid Context Network for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: apcnet_r50-d8_4xb4-160k_ade20k-512x512
+  In Collection: APCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.4
+      mIoU(ms+flip): 43.94
+  Config: configs/apcnet/apcnet_r50-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - APCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_160k_ade20k/apcnet_r50-d8_512x512_160k_ade20k_20201214_115706-25fb92c2.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_160k_ade20k/apcnet_r50-d8_512x512_160k_ade20k-20201214_115706.log.json
+  Paper:
+    Title: Adaptive Pyramid Context Network for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: apcnet_r101-d8_4xb4-160k_ade20k-512x512
+  In Collection: APCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.41
+      mIoU(ms+flip): 46.63
+  Config: configs/apcnet/apcnet_r101-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - APCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_160k_ade20k/apcnet_r101-d8_512x512_160k_ade20k_20201214_115705-73f9a8d7.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_160k_ade20k/apcnet_r101-d8_512x512_160k_ade20k-20201214_115705.log.json
+  Paper:
+    Title: Adaptive Pyramid Context Network for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
diff --git a/configs/beit/README.md b/configs/beit/README.md
index 380d788741..8e34e29410 100644
--- a/configs/beit/README.md
+++ b/configs/beit/README.md
@@ -1,6 +1,6 @@
 # BEiT
 
-[BEiT: BERT Pre-Training of Image Transformers](https://arxiv.org/abs/2106.08254)
+> [BEiT: BERT Pre-Training of Image Transformers](https://arxiv.org/abs/2106.08254)
 
 ## Introduction
 
@@ -22,18 +22,6 @@ We introduce a self-supervised vision representation model BEiT, which stands fo
 <img src="https://user-images.githubusercontent.com/93248678/160155758-781c9a45-b1d7-4530-9015-88eca6645006.png" width="70%"/>
 </div>
 
-## Citation
-
-```bibtex
-@inproceedings{beit,
-      title={{BEiT}: {BERT} Pre-Training of Image Transformers},
-      author={Hangbo Bao and Li Dong and Songhao Piao and Furu Wei},
-      booktitle={International Conference on Learning Representations},
-      year={2022},
-      url={https://openreview.net/forum?id=p-BhZSz59o4}
-}
-```
-
 ## Usage
 
 To use other repositories' pre-trained models, it is necessary to convert keys.
@@ -79,7 +67,19 @@ upernet_beit-large_fp16_8x1_640x640_160k_ade20k-8fc0dd5d.pth $GPUS --eval mIoU
 
 ### ADE20K
 
-| Method  | Backbone | Crop Size | pretrain     | pretrain img size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) | config                                                                                                                              | download                                                                                                                                                                                                                                                                                                                                                 |
-| ------- | -------- | --------- | ------------ | ----------------- | ---------- | ------- | -------- | -------------- | ----- | ------------: | ----------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UPerNet | BEiT-B   | 640x640   | ImageNet-22K | 224x224           | 16         | 160000  | 15.88    | 2.00           | 53.08 |         53.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/beit/beit-base_upernet_8xb2-160k_ade20k-640x640.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-base_8x2_640x640_160k_ade20k/upernet_beit-base_8x2_640x640_160k_ade20k-eead221d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-base_8x2_640x640_160k_ade20k/upernet_beit-base_8x2_640x640_160k_ade20k.log.json)                         |
-| UPerNet | BEiT-L   | 640x640   | ImageNet-22K | 224x224           | 8          | 320000  | 22.64    | 0.96           | 56.33 |         56.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/beit/beit-large_upernet_8xb1-amp-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-large_fp16_8x1_640x640_160k_ade20k/upernet_beit-large_fp16_8x1_640x640_160k_ade20k-8fc0dd5d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-large_fp16_8x1_640x640_160k_ade20k/upernet_beit-large_fp16_8x1_640x640_160k_ade20k.log.json) |
+| Method  | Backbone | Crop Size | pretrain     | pretrain img size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                              | download                                                                                                                                                                                                                                                                                                                                                 |
+| ------- | -------- | --------- | ------------ | ----------------- | ---------- | ------- | -------- | -------------- | ------ | ----- | ------------: | ----------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UPerNet | BEiT-B   | 640x640   | ImageNet-22K | 224x224           | 16         | 160000  | 15.88    | 2.00           | V100   | 53.08 |         53.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/beit/beit-base_upernet_8xb2-160k_ade20k-640x640.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-base_8x2_640x640_160k_ade20k/upernet_beit-base_8x2_640x640_160k_ade20k-eead221d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-base_8x2_640x640_160k_ade20k/upernet_beit-base_8x2_640x640_160k_ade20k.log.json)                         |
+| UPerNet | BEiT-L   | 640x640   | ImageNet-22K | 224x224           | 8          | 320000  | 22.64    | 0.96           | V100   | 56.33 |         56.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/beit/beit-large_upernet_8xb1-amp-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-large_fp16_8x1_640x640_160k_ade20k/upernet_beit-large_fp16_8x1_640x640_160k_ade20k-8fc0dd5d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-large_fp16_8x1_640x640_160k_ade20k/upernet_beit-large_fp16_8x1_640x640_160k_ade20k.log.json) |
+
+## Citation
+
+```bibtex
+@inproceedings{beit,
+      title={{BEiT}: {BERT} Pre-Training of Image Transformers},
+      author={Hangbo Bao and Li Dong and Songhao Piao and Furu Wei},
+      booktitle={International Conference on Learning Representations},
+      year={2022},
+      url={https://openreview.net/forum?id=p-BhZSz59o4}
+}
+```
diff --git a/configs/beit/beit.yml b/configs/beit/beit.yml
deleted file mode 100644
index f6cc0160bf..0000000000
--- a/configs/beit/beit.yml
+++ /dev/null
@@ -1,45 +0,0 @@
-Models:
-- Name: beit-base_upernet_8xb2-160k_ade20k-640x640
-  In Collection: UPerNet
-  Metadata:
-    backbone: BEiT-B
-    crop size: (640,640)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 500.0
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (640,640)
-    Training Memory (GB): 15.88
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 53.08
-      mIoU(ms+flip): 53.84
-  Config: configs/beit/beit-base_upernet_8xb2-160k_ade20k-640x640.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-base_8x2_640x640_160k_ade20k/upernet_beit-base_8x2_640x640_160k_ade20k-eead221d.pth
-- Name: beit-large_upernet_8xb1-amp-160k_ade20k-640x640
-  In Collection: UPerNet
-  Metadata:
-    backbone: BEiT-L
-    crop size: (640,640)
-    lr schd: 320000
-    inference time (ms/im):
-    - value: 1041.67
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: AMP
-      resolution: (640,640)
-    Training Memory (GB): 22.64
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 56.33
-      mIoU(ms+flip): 56.84
-  Config: configs/beit/beit-large_upernet_8xb1-amp-160k_ade20k-640x640.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-large_fp16_8x1_640x640_160k_ade20k/upernet_beit-large_fp16_8x1_640x640_160k_ade20k-8fc0dd5d.pth
diff --git a/configs/beit/metafile.yaml b/configs/beit/metafile.yaml
new file mode 100644
index 0000000000..ef6124e8dc
--- /dev/null
+++ b/configs/beit/metafile.yaml
@@ -0,0 +1,49 @@
+Models:
+- Name: beit-base_upernet_8xb2-160k_ade20k-640x640
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 53.08
+      mIoU(ms+flip): 53.84
+  Config: configs/beit/beit-base_upernet_8xb2-160k_ade20k-640x640.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - BEiT-B
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 15.88
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-base_8x2_640x640_160k_ade20k/upernet_beit-base_8x2_640x640_160k_ade20k-eead221d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-base_8x2_640x640_160k_ade20k/upernet_beit-base_8x2_640x640_160k_ade20k.log.json
+  Paper:
+    Title: 'BEiT: BERT Pre-Training of Image Transformers'
+    URL: https://arxiv.org/abs/2106.08254
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.23.0/mmseg/models/backbones/beit.py#1404
+  Framework: PyTorch
+- Name: beit-large_upernet_8xb1-amp-160k_ade20k-640x640
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 56.33
+      mIoU(ms+flip): 56.84
+  Config: configs/beit/beit-large_upernet_8xb1-amp-160k_ade20k-640x640.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 8
+    Architecture:
+    - BEiT-L
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 22.64
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-large_fp16_8x1_640x640_160k_ade20k/upernet_beit-large_fp16_8x1_640x640_160k_ade20k-8fc0dd5d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-large_fp16_8x1_640x640_160k_ade20k/upernet_beit-large_fp16_8x1_640x640_160k_ade20k.log.json
+  Paper:
+    Title: 'BEiT: BERT Pre-Training of Image Transformers'
+    URL: https://arxiv.org/abs/2106.08254
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.23.0/mmseg/models/backbones/beit.py#1404
+  Framework: PyTorch
diff --git a/configs/bisenetv1/README.md b/configs/bisenetv1/README.md
index 72fdd474cb..c895fdfe63 100644
--- a/configs/bisenetv1/README.md
+++ b/configs/bisenetv1/README.md
@@ -1,6 +1,6 @@
 # BiSeNetV1
 
-[BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://arxiv.org/abs/1808.00897)
+> [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://arxiv.org/abs/1808.00897)
 
 ## Introduction
 
@@ -22,43 +22,43 @@ Semantic segmentation requires both rich spatial information and sizeable recept
 <img src="https://user-images.githubusercontent.com/24582831/142898839-a0a78148-848a-41b2-8682-b1f61ac004ba.png" width="70%"/>
 </div>
 
-## Citation
-
-```bibtex
-@inproceedings{yu2018bisenet,
-  title={Bisenet: Bilateral segmentation network for real-time semantic segmentation},
-  author={Yu, Changqian and Wang, Jingbo and Peng, Chao and Gao, Changxin and Yu, Gang and Sang, Nong},
-  booktitle={Proceedings of the European conference on computer vision (ECCV)},
-  pages={325--341},
-  year={2018}
-}
-```
-
 ## Results and models
 
 ### Cityscapes
 
-| Method                  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                             | download                                                                                                                                                                                                                                                                                                                                                                                                                               |
-| ----------------------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| BiSeNetV1 (No Pretrain) | R-18-D32 | 1024x1024 |  160000 | 5.69     | 31.77          | 74.44 | 77.05         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r18-d32_4xb4-160k_cityscapes-1024x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes_20210922_172239-c55e78e2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes_20210922_172239.log.json)                                     |
-| BiSeNetV1               | R-18-D32 | 1024x1024 |  160000 | 5.69     | 31.77          | 74.37 | 76.91         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r18-d32-in1k-pre_4xb4-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210905_220251-8ba80eff.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210905_220251.log.json) |
-| BiSeNetV1 (4x8)         | R-18-D32 | 1024x1024 |  160000 | 11.17    | 31.77          | 75.16 | 77.24         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r18-d32-in1k-pre_4xb8-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes_20210905_220322-bb8db75f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes_20210905_220322.log.json) |
-| BiSeNetV1 (No Pretrain) | R-50-D32 | 1024x1024 |  160000 | 15.39    | 7.71           | 76.92 | 78.87         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r50-d32_4xb4-160k_cityscapes-1024x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes_20210923_222639-7b28a2a6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes_20210923_222639.log.json)                                     |
-| BiSeNetV1               | R-50-D32 | 1024x1024 |  160000 | 15.39    | 7.71           | 77.68 | 79.57         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r50-d32-in1k-pre_4xb4-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210917_234628-8b304447.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210917_234628.log.json) |
+| Method    | Backbone               | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                             | download                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| --------- | ---------------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| BiSeNetV1 | R-18-D32 (No Pretrain) | 1024x1024 |  160000 | 5.69     | 31.77          | V100   | 74.44 | 77.05         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r18-d32_4xb4-160k_cityscapes-1024x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes_20210922_172239-c55e78e2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes_20210922_172239.log.json)                                     |
+| BiSeNetV1 | R-18-D32               | 1024x1024 |  160000 | 5.69     | 31.77          | V100   | 74.37 | 76.91         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r18-d32-in1k-pre_4xb4-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210905_220251-8ba80eff.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210905_220251.log.json) |
+| BiSeNetV1 | R-18-D32 (4x8)         | 1024x1024 |  160000 | 11.17    | 31.77          | V100   | 75.16 | 77.24         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r18-d32-in1k-pre_4xb8-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes_20210905_220322-bb8db75f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes_20210905_220322.log.json) |
+| BiSeNetV1 | R-50-D32 (No Pretrain) | 1024x1024 |  160000 | 15.39    | 7.71           | V100   | 76.92 | 78.87         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r50-d32_4xb4-160k_cityscapes-1024x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes_20210923_222639-7b28a2a6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes_20210923_222639.log.json)                                     |
+| BiSeNetV1 | R-50-D32               | 1024x1024 |  160000 | 15.39    | 7.71           | V100   | 77.68 | 79.57         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r50-d32-in1k-pre_4xb4-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210917_234628-8b304447.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210917_234628.log.json) |
 
 ### COCO-Stuff 164k
 
-| Method                  | Backbone  | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                                | download                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
-| ----------------------- | --------- | --------- | ------: | -------- | -------------- | ----: | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| BiSeNetV1 (No Pretrain) | R-18-D32  | 512x512   |  160000 | -        | -              | 25.45 | 26.15         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r18-d32_4xb4-160k_coco-stuff164k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211022_054328-046aa2f2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211022_054328.log.json)                                         |
-| BiSeNetV1               | R-18-D32  | 512x512   |  160000 | 6.33     | 74.24          | 28.55 | 29.26         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r18-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211023_013100-f700dbf7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211023_013100.log.json)     |
-| BiSeNetV1 (No Pretrain) | R-50-D32  | 512x512   |  160000 | -        | -              | 29.82 | 30.33         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r50-d32_4xb4-160k_coco-stuff164k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_040616-d2bb0df4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_040616.log.json)                                         |
-| BiSeNetV1               | R-50-D32  | 512x512   |  160000 | 9.28     | 32.60          | 34.88 | 35.37         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r50-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_181932-66747911.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_181932.log.json)     |
-| BiSeNetV1 (No Pretrain) | R-101-D32 | 512x512   |  160000 | -        | -              | 31.14 | 31.76         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r50-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211102_164147-c6b32c3b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211102_164147.log.json)                                     |
-| BiSeNetV1               | R-101-D32 | 512x512   |  160000 | 10.36    | 25.25          | 37.38 | 37.99         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r101-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_225220-28c8f092.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_225220.log.json) |
+| Method    | Backbone                | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                                | download                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
+| --------- | ----------------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| BiSeNetV1 | R-18-D32 (No Pretrain)  | 512x512   |  160000 | -        | -              | V100   | 25.45 | 26.15         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r18-d32_4xb4-160k_coco-stuff164k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211022_054328-046aa2f2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211022_054328.log.json)                                         |
+| BiSeNetV1 | R-18-D32                | 512x512   |  160000 | 6.33     | 74.24          | V100   | 28.55 | 29.26         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r18-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211023_013100-f700dbf7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211023_013100.log.json)     |
+| BiSeNetV1 | R-50-D32 (No Pretrain)  | 512x512   |  160000 | -        | -              | V100   | 29.82 | 30.33         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r50-d32_4xb4-160k_coco-stuff164k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_040616-d2bb0df4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_040616.log.json)                                         |
+| BiSeNetV1 | R-50-D32                | 512x512   |  160000 | 9.28     | 32.60          | V100   | 34.88 | 35.37         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r50-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_181932-66747911.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_181932.log.json)     |
+| BiSeNetV1 | R-101-D32 (No Pretrain) | 512x512   |  160000 | -        | -              | V100   | 31.14 | 31.76         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r50-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211102_164147-c6b32c3b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211102_164147.log.json)                                     |
+| BiSeNetV1 | R-101-D32               | 512x512   |  160000 | 10.36    | 25.25          | V100   | 37.38 | 37.99         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r101-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_225220-28c8f092.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_225220.log.json) |
 
 Note:
 
 - `4x8`: Using 4 GPUs with 8 samples per GPU in training.
 - For BiSeNetV1 on Cityscapes dataset, default setting is 4 GPUs with 4 samples per GPU in training.
 - `No Pretrain` means the model is trained from scratch.
+
+## Citation
+
+```bibtex
+@inproceedings{yu2018bisenet,
+  title={Bisenet: Bilateral segmentation network for real-time semantic segmentation},
+  author={Yu, Changqian and Wang, Jingbo and Peng, Chao and Gao, Changxin and Yu, Gang and Sang, Nong},
+  booktitle={Proceedings of the European conference on computer vision (ECCV)},
+  pages={325--341},
+  year={2018}
+}
+```
diff --git a/configs/bisenetv1/bisenetv1.yml b/configs/bisenetv1/bisenetv1.yml
deleted file mode 100644
index f5aade4de4..0000000000
--- a/configs/bisenetv1/bisenetv1.yml
+++ /dev/null
@@ -1,234 +0,0 @@
-Collections:
-- Name: BiSeNetV1
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - COCO-Stuff 164k
-  Paper:
-    URL: https://arxiv.org/abs/1808.00897
-    Title: 'BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation'
-  README: configs/bisenetv1/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv1.py#L266
-    Version: v0.18.0
-  Converted From:
-    Code: https://github.com/ycszen/TorchSeg/tree/master/model/bisenet
-Models:
-- Name: bisenetv1_r18-d32_4xb4-160k_cityscapes-1024x1024
-  In Collection: BiSeNetV1
-  Metadata:
-    backbone: R-18-D32
-    crop size: (1024,1024)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 31.48
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (1024,1024)
-    Training Memory (GB): 5.69
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 74.44
-      mIoU(ms+flip): 77.05
-  Config: configs/bisenetv1/bisenetv1_r18-d32_4xb4-160k_cityscapes-1024x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes_20210922_172239-c55e78e2.pth
-- Name: bisenetv1_r18-d32-in1k-pre_4xb4-160k_cityscapes-1024x1024
-  In Collection: BiSeNetV1
-  Metadata:
-    backbone: R-18-D32
-    crop size: (1024,1024)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 31.48
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (1024,1024)
-    Training Memory (GB): 5.69
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 74.37
-      mIoU(ms+flip): 76.91
-  Config: configs/bisenetv1/bisenetv1_r18-d32-in1k-pre_4xb4-160k_cityscapes-1024x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210905_220251-8ba80eff.pth
-- Name: bisenetv1_r18-d32-in1k-pre_4xb8-160k_cityscapes-1024x1024
-  In Collection: BiSeNetV1
-  Metadata:
-    backbone: R-18-D32
-    crop size: (1024,1024)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 31.48
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (1024,1024)
-    Training Memory (GB): 11.17
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 75.16
-      mIoU(ms+flip): 77.24
-  Config: configs/bisenetv1/bisenetv1_r18-d32-in1k-pre_4xb8-160k_cityscapes-1024x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes_20210905_220322-bb8db75f.pth
-- Name: bisenetv1_r50-d32_4xb4-160k_cityscapes-1024x1024
-  In Collection: BiSeNetV1
-  Metadata:
-    backbone: R-50-D32
-    crop size: (1024,1024)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 129.7
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (1024,1024)
-    Training Memory (GB): 15.39
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.92
-      mIoU(ms+flip): 78.87
-  Config: configs/bisenetv1/bisenetv1_r50-d32_4xb4-160k_cityscapes-1024x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes_20210923_222639-7b28a2a6.pth
-- Name: bisenetv1_r50-d32-in1k-pre_4xb4-160k_cityscapes-1024x1024
-  In Collection: BiSeNetV1
-  Metadata:
-    backbone: R-50-D32
-    crop size: (1024,1024)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 129.7
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (1024,1024)
-    Training Memory (GB): 15.39
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.68
-      mIoU(ms+flip): 79.57
-  Config: configs/bisenetv1/bisenetv1_r50-d32-in1k-pre_4xb4-160k_cityscapes-1024x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210917_234628-8b304447.pth
-- Name: bisenetv1_r18-d32_4xb4-160k_coco-stuff164k-512x512
-  In Collection: BiSeNetV1
-  Metadata:
-    backbone: R-18-D32
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 164k
-    Metrics:
-      mIoU: 25.45
-      mIoU(ms+flip): 26.15
-  Config: configs/bisenetv1/bisenetv1_r18-d32_4xb4-160k_coco-stuff164k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211022_054328-046aa2f2.pth
-- Name: bisenetv1_r18-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512
-  In Collection: BiSeNetV1
-  Metadata:
-    backbone: R-18-D32
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 13.47
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.33
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 164k
-    Metrics:
-      mIoU: 28.55
-      mIoU(ms+flip): 29.26
-  Config: configs/bisenetv1/bisenetv1_r18-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211023_013100-f700dbf7.pth
-- Name: bisenetv1_r50-d32_4xb4-160k_coco-stuff164k-512x512
-  In Collection: BiSeNetV1
-  Metadata:
-    backbone: R-50-D32
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 164k
-    Metrics:
-      mIoU: 29.82
-      mIoU(ms+flip): 30.33
-  Config: configs/bisenetv1/bisenetv1_r50-d32_4xb4-160k_coco-stuff164k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_040616-d2bb0df4.pth
-- Name: bisenetv1_r50-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512
-  In Collection: BiSeNetV1
-  Metadata:
-    backbone: R-50-D32
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 30.67
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.28
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 164k
-    Metrics:
-      mIoU: 34.88
-      mIoU(ms+flip): 35.37
-  Config: configs/bisenetv1/bisenetv1_r50-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_181932-66747911.pth
-- Name: bisenetv1_r50-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512
-  In Collection: BiSeNetV1
-  Metadata:
-    backbone: R-101-D32
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 164k
-    Metrics:
-      mIoU: 31.14
-      mIoU(ms+flip): 31.76
-  Config: configs/bisenetv1/bisenetv1_r50-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211102_164147-c6b32c3b.pth
-- Name: bisenetv1_r101-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512
-  In Collection: BiSeNetV1
-  Metadata:
-    backbone: R-101-D32
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 39.6
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 10.36
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 164k
-    Metrics:
-      mIoU: 37.38
-      mIoU(ms+flip): 37.99
-  Config: configs/bisenetv1/bisenetv1_r101-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_225220-28c8f092.pth
diff --git a/configs/bisenetv1/metafile.yaml b/configs/bisenetv1/metafile.yaml
new file mode 100644
index 0000000000..e37f632b2f
--- /dev/null
+++ b/configs/bisenetv1/metafile.yaml
@@ -0,0 +1,275 @@
+Collections:
+- Name: BiSeNetV1
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - COCO-Stuff 164k
+  Paper:
+    Title: 'BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation'
+    URL: https://arxiv.org/abs/1808.00897
+  README: configs/bisenetv1/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: bisenetv1_r18-d32_4xb4-160k_cityscapes-1024x1024
+  In Collection: BiSeNetV1
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 74.44
+      mIoU(ms+flip): 77.05
+  Config: configs/bisenetv1/bisenetv1_r18-d32_4xb4-160k_cityscapes-1024x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - R-18-D32
+    - BiSeNetV1
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.69
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes_20210922_172239-c55e78e2.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes_20210922_172239.log.json
+  Paper:
+    Title: 'BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation'
+    URL: https://arxiv.org/abs/1808.00897
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv1.py#L266
+  Framework: PyTorch
+- Name: bisenetv1_r18-d32-in1k-pre_4xb4-160k_cityscapes-1024x1024
+  In Collection: BiSeNetV1
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 74.37
+      mIoU(ms+flip): 76.91
+  Config: configs/bisenetv1/bisenetv1_r18-d32-in1k-pre_4xb4-160k_cityscapes-1024x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - R-18-D32
+    - BiSeNetV1
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.69
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210905_220251-8ba80eff.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210905_220251.log.json
+  Paper:
+    Title: 'BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation'
+    URL: https://arxiv.org/abs/1808.00897
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv1.py#L266
+  Framework: PyTorch
+- Name: bisenetv1_r18-d32-in1k-pre_4xb8-160k_cityscapes-1024x1024
+  In Collection: BiSeNetV1
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 75.16
+      mIoU(ms+flip): 77.24
+  Config: configs/bisenetv1/bisenetv1_r18-d32-in1k-pre_4xb8-160k_cityscapes-1024x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 32
+    Architecture:
+    - R-18-D32
+    - BiSeNetV1
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 11.17
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes_20210905_220322-bb8db75f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes_20210905_220322.log.json
+  Paper:
+    Title: 'BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation'
+    URL: https://arxiv.org/abs/1808.00897
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv1.py#L266
+  Framework: PyTorch
+- Name: bisenetv1_r50-d32_4xb4-160k_cityscapes-1024x1024
+  In Collection: BiSeNetV1
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.92
+      mIoU(ms+flip): 78.87
+  Config: configs/bisenetv1/bisenetv1_r50-d32_4xb4-160k_cityscapes-1024x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - R-50-D32
+    - BiSeNetV1
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 15.39
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes_20210923_222639-7b28a2a6.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes_20210923_222639.log.json
+  Paper:
+    Title: 'BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation'
+    URL: https://arxiv.org/abs/1808.00897
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv1.py#L266
+  Framework: PyTorch
+- Name: bisenetv1_r50-d32-in1k-pre_4xb4-160k_cityscapes-1024x1024
+  In Collection: BiSeNetV1
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.68
+      mIoU(ms+flip): 79.57
+  Config: configs/bisenetv1/bisenetv1_r50-d32-in1k-pre_4xb4-160k_cityscapes-1024x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - R-50-D32
+    - BiSeNetV1
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 15.39
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210917_234628-8b304447.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210917_234628.log.json
+  Paper:
+    Title: 'BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation'
+    URL: https://arxiv.org/abs/1808.00897
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv1.py#L266
+  Framework: PyTorch
+- Name: bisenetv1_r18-d32_4xb4-160k_coco-stuff164k-512x512
+  In Collection: BiSeNetV1
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 25.45
+      mIoU(ms+flip): 26.15
+  Config: configs/bisenetv1/bisenetv1_r18-d32_4xb4-160k_coco-stuff164k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 164k
+    Batch Size: 16
+    Architecture:
+    - R-18-D32
+    - BiSeNetV1
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211022_054328-046aa2f2.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211022_054328.log.json
+  Paper:
+    Title: 'BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation'
+    URL: https://arxiv.org/abs/1808.00897
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv1.py#L266
+  Framework: PyTorch
+- Name: bisenetv1_r18-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512
+  In Collection: BiSeNetV1
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 28.55
+      mIoU(ms+flip): 29.26
+  Config: configs/bisenetv1/bisenetv1_r18-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 164k
+    Batch Size: 16
+    Architecture:
+    - R-18-D32
+    - BiSeNetV1
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.33
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211023_013100-f700dbf7.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211023_013100.log.json
+  Paper:
+    Title: 'BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation'
+    URL: https://arxiv.org/abs/1808.00897
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv1.py#L266
+  Framework: PyTorch
+- Name: bisenetv1_r50-d32_4xb4-160k_coco-stuff164k-512x512
+  In Collection: BiSeNetV1
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 29.82
+      mIoU(ms+flip): 30.33
+  Config: configs/bisenetv1/bisenetv1_r50-d32_4xb4-160k_coco-stuff164k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 164k
+    Batch Size: 16
+    Architecture:
+    - R-50-D32
+    - BiSeNetV1
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_040616-d2bb0df4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_040616.log.json
+  Paper:
+    Title: 'BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation'
+    URL: https://arxiv.org/abs/1808.00897
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv1.py#L266
+  Framework: PyTorch
+- Name: bisenetv1_r50-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512
+  In Collection: BiSeNetV1
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 34.88
+      mIoU(ms+flip): 35.37
+  Config: configs/bisenetv1/bisenetv1_r50-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 164k
+    Batch Size: 16
+    Architecture:
+    - R-50-D32
+    - BiSeNetV1
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.28
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_181932-66747911.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_181932.log.json
+  Paper:
+    Title: 'BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation'
+    URL: https://arxiv.org/abs/1808.00897
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv1.py#L266
+  Framework: PyTorch
+- Name: bisenetv1_r50-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512
+  In Collection: BiSeNetV1
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 31.14
+      mIoU(ms+flip): 31.76
+  Config: configs/bisenetv1/bisenetv1_r50-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 164k
+    Batch Size: 16
+    Architecture:
+    - R-101-D32
+    - BiSeNetV1
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211102_164147-c6b32c3b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211102_164147.log.json
+  Paper:
+    Title: 'BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation'
+    URL: https://arxiv.org/abs/1808.00897
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv1.py#L266
+  Framework: PyTorch
+- Name: bisenetv1_r101-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512
+  In Collection: BiSeNetV1
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 37.38
+      mIoU(ms+flip): 37.99
+  Config: configs/bisenetv1/bisenetv1_r101-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 164k
+    Batch Size: 16
+    Architecture:
+    - R-101-D32
+    - BiSeNetV1
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.36
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_225220-28c8f092.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_225220.log.json
+  Paper:
+    Title: 'BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation'
+    URL: https://arxiv.org/abs/1808.00897
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv1.py#L266
+  Framework: PyTorch
diff --git a/configs/bisenetv2/README.md b/configs/bisenetv2/README.md
index 7cde5c02c1..1f44c01f36 100644
--- a/configs/bisenetv2/README.md
+++ b/configs/bisenetv2/README.md
@@ -1,6 +1,6 @@
 # BiSeNetV2
 
-[Bisenet v2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation](https://arxiv.org/abs/2004.02147)
+> [Bisenet v2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation](https://arxiv.org/abs/2004.02147)
 
 ## Introduction
 
@@ -22,6 +22,23 @@ The low-level details and high-level semantics are both essential to the semanti
 <img src="https://user-images.githubusercontent.com/24582831/142898966-ec4a81da-b4b0-41ee-b083-1d964582c18a.png" width="70%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method    | Backbone         | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                                                               |
+| --------- | ---------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| BiSeNetV2 | BiSeNetV2        | 1024x1024 |  160000 | 7.64     | 31.77          | V100   | 73.21 |         75.74 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv2/bisenetv2_fcn_4xb4-160k_cityscapes-1024x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes_20210902_015551-bcf10f09.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes_20210902_015551.log.json)                     |
+| BiSeNetV2 | BiSeNetV2 (OHEM) | 1024x1024 |  160000 | 7.64     | -              | V100   | 73.57 |         75.80 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv2/bisenetv2_fcn_4xb4-ohem-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes_20210902_112947-5f8103b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes_20210902_112947.log.json) |
+| BiSeNetV2 | BiSeNetV2 (4x8)  | 1024x1024 |  160000 | 15.05    | -              | V100   | 75.76 |         77.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv2/bisenetv2_fcn_4xb8-160k_cityscapes-1024x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes_20210903_000032-e1a2eed6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes_20210903_000032.log.json)                     |
+| BiSeNetV2 | BiSeNetV2 (FP16) | 1024x1024 |  160000 | 5.77     | 36.65          | V100   | 73.07 |         75.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv2/bisenetv2_fcn_4xb4-amp-160k_cityscapes-1024x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes_20210902_045942-b979777b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes_20210902_045942.log.json) |
+
+Note:
+
+- `OHEM` means Online Hard Example Mining (OHEM) is adopted in training.
+- `FP16` means Mixed Precision (FP16) is adopted in training.
+- `4x8` means 4 GPUs with 8 samples per GPU in training.
+
 ## Citation
 
 ```bibtex
@@ -34,20 +51,3 @@ The low-level details and high-level semantics are both essential to the semanti
   publisher={Springer}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method           | Backbone  | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                                                               |
-| ---------------- | --------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| BiSeNetV2        | BiSeNetV2 | 1024x1024 |  160000 | 7.64     | 31.77          | 73.21 |         75.74 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv2/bisenetv2_fcn_4xb4-160k_cityscapes-1024x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes_20210902_015551-bcf10f09.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes_20210902_015551.log.json)                     |
-| BiSeNetV2 (OHEM) | BiSeNetV2 | 1024x1024 |  160000 | 7.64     | -              | 73.57 |         75.80 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv2/bisenetv2_fcn_4xb4-ohem-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes_20210902_112947-5f8103b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes_20210902_112947.log.json) |
-| BiSeNetV2 (4x8)  | BiSeNetV2 | 1024x1024 |  160000 | 15.05    | -              | 75.76 |         77.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv2/bisenetv2_fcn_4xb8-160k_cityscapes-1024x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes_20210903_000032-e1a2eed6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes_20210903_000032.log.json)                     |
-| BiSeNetV2 (FP16) | BiSeNetV2 | 1024x1024 |  160000 | 5.77     | 36.65          | 73.07 |         75.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv2/bisenetv2_fcn_4xb4-amp-160k_cityscapes-1024x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes_20210902_045942-b979777b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes_20210902_045942.log.json) |
-
-Note:
-
-- `OHEM` means Online Hard Example Mining (OHEM) is adopted in training.
-- `FP16` means Mixed Precision (FP16) is adopted in training.
-- `4x8` means 4 GPUs with 8 samples per GPU in training.
diff --git a/configs/bisenetv2/bisenetv2.yml b/configs/bisenetv2/bisenetv2.yml
deleted file mode 100644
index 70c4326a55..0000000000
--- a/configs/bisenetv2/bisenetv2.yml
+++ /dev/null
@@ -1,88 +0,0 @@
-Collections:
-- Name: BiSeNetV2
-  Metadata:
-    Training Data:
-    - Cityscapes
-  Paper:
-    URL: https://arxiv.org/abs/2004.02147
-    Title: 'Bisenet v2: Bilateral Network with Guided Aggregation for Real-time Semantic
-      Segmentation'
-  README: configs/bisenetv2/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv2.py#L545
-    Version: v0.18.0
-Models:
-- Name: bisenetv2_fcn_4xb4-160k_cityscapes-1024x1024
-  In Collection: BiSeNetV2
-  Metadata:
-    backbone: BiSeNetV2
-    crop size: (1024,1024)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 31.48
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (1024,1024)
-    Training Memory (GB): 7.64
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 73.21
-      mIoU(ms+flip): 75.74
-  Config: configs/bisenetv2/bisenetv2_fcn_4xb4-160k_cityscapes-1024x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes_20210902_015551-bcf10f09.pth
-- Name: bisenetv2_fcn_4xb4-ohem-160k_cityscapes-1024x1024
-  In Collection: BiSeNetV2
-  Metadata:
-    backbone: BiSeNetV2
-    crop size: (1024,1024)
-    lr schd: 160000
-    Training Memory (GB): 7.64
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 73.57
-      mIoU(ms+flip): 75.8
-  Config: configs/bisenetv2/bisenetv2_fcn_4xb4-ohem-160k_cityscapes-1024x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes_20210902_112947-5f8103b4.pth
-- Name: bisenetv2_fcn_4xb8-160k_cityscapes-1024x1024
-  In Collection: BiSeNetV2
-  Metadata:
-    backbone: BiSeNetV2
-    crop size: (1024,1024)
-    lr schd: 160000
-    Training Memory (GB): 15.05
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 75.76
-      mIoU(ms+flip): 77.79
-  Config: configs/bisenetv2/bisenetv2_fcn_4xb8-160k_cityscapes-1024x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes_20210903_000032-e1a2eed6.pth
-- Name: bisenetv2_fcn_4xb4-amp-160k_cityscapes-1024x1024
-  In Collection: BiSeNetV2
-  Metadata:
-    backbone: BiSeNetV2
-    crop size: (1024,1024)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 27.29
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: AMP
-      resolution: (1024,1024)
-    Training Memory (GB): 5.77
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 73.07
-      mIoU(ms+flip): 75.13
-  Config: configs/bisenetv2/bisenetv2_fcn_4xb4-amp-160k_cityscapes-1024x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes_20210902_045942-b979777b.pth
diff --git a/configs/bisenetv2/metafile.yaml b/configs/bisenetv2/metafile.yaml
new file mode 100644
index 0000000000..5430ec3071
--- /dev/null
+++ b/configs/bisenetv2/metafile.yaml
@@ -0,0 +1,114 @@
+Collections:
+- Name: BiSeNetV2
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+  Paper:
+    Title: 'Bisenet v2: Bilateral Network with Guided Aggregation for Real-time Semantic
+      Segmentation'
+    URL: https://arxiv.org/abs/2004.02147
+  README: configs/bisenetv2/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: bisenetv2_fcn_4xb4-160k_cityscapes-1024x1024
+  In Collection: BiSeNetV2
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 73.21
+      mIoU(ms+flip): 75.74
+  Config: configs/bisenetv2/bisenetv2_fcn_4xb4-160k_cityscapes-1024x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - BiSeNetV2
+    - BiSeNetV2
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.64
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes_20210902_015551-bcf10f09.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes_20210902_015551.log.json
+  Paper:
+    Title: 'Bisenet v2: Bilateral Network with Guided Aggregation for Real-time Semantic
+      Segmentation'
+    URL: https://arxiv.org/abs/2004.02147
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv2.py#L545
+  Framework: PyTorch
+- Name: bisenetv2_fcn_4xb4-ohem-160k_cityscapes-1024x1024
+  In Collection: BiSeNetV2
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 73.57
+      mIoU(ms+flip): 75.8
+  Config: configs/bisenetv2/bisenetv2_fcn_4xb4-ohem-160k_cityscapes-1024x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - BiSeNetV2
+    - BiSeNetV2
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.64
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes_20210902_112947-5f8103b4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes_20210902_112947.log.json
+  Paper:
+    Title: 'Bisenet v2: Bilateral Network with Guided Aggregation for Real-time Semantic
+      Segmentation'
+    URL: https://arxiv.org/abs/2004.02147
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv2.py#L545
+  Framework: PyTorch
+- Name: bisenetv2_fcn_4xb8-160k_cityscapes-1024x1024
+  In Collection: BiSeNetV2
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 75.76
+      mIoU(ms+flip): 77.79
+  Config: configs/bisenetv2/bisenetv2_fcn_4xb8-160k_cityscapes-1024x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 32
+    Architecture:
+    - BiSeNetV2
+    - BiSeNetV2
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 15.05
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes_20210903_000032-e1a2eed6.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes_20210903_000032.log.json
+  Paper:
+    Title: 'Bisenet v2: Bilateral Network with Guided Aggregation for Real-time Semantic
+      Segmentation'
+    URL: https://arxiv.org/abs/2004.02147
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv2.py#L545
+  Framework: PyTorch
+- Name: bisenetv2_fcn_4xb4-amp-160k_cityscapes-1024x1024
+  In Collection: BiSeNetV2
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 73.07
+      mIoU(ms+flip): 75.13
+  Config: configs/bisenetv2/bisenetv2_fcn_4xb4-amp-160k_cityscapes-1024x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - BiSeNetV2
+    - BiSeNetV2
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.77
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes_20210902_045942-b979777b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes_20210902_045942.log.json
+  Paper:
+    Title: 'Bisenet v2: Bilateral Network with Guided Aggregation for Real-time Semantic
+      Segmentation'
+    URL: https://arxiv.org/abs/2004.02147
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv2.py#L545
+  Framework: PyTorch
diff --git a/configs/ccnet/README.md b/configs/ccnet/README.md
index 9d110f4df9..c7a0163495 100644
--- a/configs/ccnet/README.md
+++ b/configs/ccnet/README.md
@@ -1,6 +1,6 @@
 # CCNet
 
-[CCNet: Criss-Cross Attention for Semantic Segmentation](https://arxiv.org/abs/1811.11721)
+> [CCNet: Criss-Cross Attention for Semantic Segmentation](https://arxiv.org/abs/1811.11721)
 
 ## Introduction
 
@@ -22,46 +22,46 @@ Contextual information is vital in visual understanding problems, such as semant
 <img src="https://user-images.githubusercontent.com/24582831/142899159-b329c12a-0fde-44df-8718-def6cfb004e4.png" width="70%"/>
 </div>
 
-## Citation
-
-```bibtex
-@article{huang2018ccnet,
-    title={CCNet: Criss-Cross Attention for Semantic Segmentation},
-    author={Huang, Zilong and Wang, Xinggang and Huang, Lichao and Huang, Chang and Wei, Yunchao and Liu, Wenyu},
-    booktitle={ICCV},
-    year={2019}
-}
-```
-
 ## Results and models
 
 ### Cityscapes
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| CCNet  | R-50-D8  | 512x1024  |   40000 | 6        | 3.32           | 77.76 |         78.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_40k_cityscapes/ccnet_r50-d8_512x1024_40k_cityscapes_20200616_142517-4123f401.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_40k_cityscapes/ccnet_r50-d8_512x1024_40k_cityscapes_20200616_142517.log.json)     |
-| CCNet  | R-101-D8 | 512x1024  |   40000 | 9.5      | 2.31           | 76.35 |         78.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_40k_cityscapes/ccnet_r101-d8_512x1024_40k_cityscapes_20200616_142540-a3b84ba6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_40k_cityscapes/ccnet_r101-d8_512x1024_40k_cityscapes_20200616_142540.log.json) |
-| CCNet  | R-50-D8  | 769x769   |   40000 | 6.8      | 1.43           | 78.46 |         79.93 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_40k_cityscapes/ccnet_r50-d8_769x769_40k_cityscapes_20200616_145125-76d11884.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_40k_cityscapes/ccnet_r50-d8_769x769_40k_cityscapes_20200616_145125.log.json)         |
-| CCNet  | R-101-D8 | 769x769   |   40000 | 10.7     | 1.01           | 76.94 |         78.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_40k_cityscapes/ccnet_r101-d8_769x769_40k_cityscapes_20200617_101428-4f57c8d0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_40k_cityscapes/ccnet_r101-d8_769x769_40k_cityscapes_20200617_101428.log.json)     |
-| CCNet  | R-50-D8  | 512x1024  |   80000 | -        | -              | 79.03 |         80.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_80k_cityscapes/ccnet_r50-d8_512x1024_80k_cityscapes_20200617_010421-869a3423.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_80k_cityscapes/ccnet_r50-d8_512x1024_80k_cityscapes_20200617_010421.log.json)     |
-| CCNet  | R-101-D8 | 512x1024  |   80000 | -        | -              | 78.87 |         79.90 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_80k_cityscapes/ccnet_r101-d8_512x1024_80k_cityscapes_20200617_203935-ffae8917.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_80k_cityscapes/ccnet_r101-d8_512x1024_80k_cityscapes_20200617_203935.log.json) |
-| CCNet  | R-50-D8  | 769x769   |   80000 | -        | -              | 79.29 |         81.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_80k_cityscapes/ccnet_r50-d8_769x769_80k_cityscapes_20200617_010421-73eed8ca.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_80k_cityscapes/ccnet_r50-d8_769x769_80k_cityscapes_20200617_010421.log.json)         |
-| CCNet  | R-101-D8 | 769x769   |   80000 | -        | -              | 79.45 |         80.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_80k_cityscapes/ccnet_r101-d8_769x769_80k_cityscapes_20200618_011502-ad3cd481.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_80k_cityscapes/ccnet_r101-d8_769x769_80k_cityscapes_20200618_011502.log.json)     |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| CCNet  | R-50-D8  | 512x1024  |   40000 | 6        | 3.32           | V100   | 77.76 |         78.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_40k_cityscapes/ccnet_r50-d8_512x1024_40k_cityscapes_20200616_142517-4123f401.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_40k_cityscapes/ccnet_r50-d8_512x1024_40k_cityscapes_20200616_142517.log.json)     |
+| CCNet  | R-101-D8 | 512x1024  |   40000 | 9.5      | 2.31           | V100   | 76.35 |         78.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_40k_cityscapes/ccnet_r101-d8_512x1024_40k_cityscapes_20200616_142540-a3b84ba6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_40k_cityscapes/ccnet_r101-d8_512x1024_40k_cityscapes_20200616_142540.log.json) |
+| CCNet  | R-50-D8  | 769x769   |   40000 | 6.8      | 1.43           | V100   | 78.46 |         79.93 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_40k_cityscapes/ccnet_r50-d8_769x769_40k_cityscapes_20200616_145125-76d11884.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_40k_cityscapes/ccnet_r50-d8_769x769_40k_cityscapes_20200616_145125.log.json)         |
+| CCNet  | R-101-D8 | 769x769   |   40000 | 10.7     | 1.01           | V100   | 76.94 |         78.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_40k_cityscapes/ccnet_r101-d8_769x769_40k_cityscapes_20200617_101428-4f57c8d0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_40k_cityscapes/ccnet_r101-d8_769x769_40k_cityscapes_20200617_101428.log.json)     |
+| CCNet  | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 79.03 |         80.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_80k_cityscapes/ccnet_r50-d8_512x1024_80k_cityscapes_20200617_010421-869a3423.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_80k_cityscapes/ccnet_r50-d8_512x1024_80k_cityscapes_20200617_010421.log.json)     |
+| CCNet  | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 78.87 |         79.90 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_80k_cityscapes/ccnet_r101-d8_512x1024_80k_cityscapes_20200617_203935-ffae8917.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_80k_cityscapes/ccnet_r101-d8_512x1024_80k_cityscapes_20200617_203935.log.json) |
+| CCNet  | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 79.29 |         81.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_80k_cityscapes/ccnet_r50-d8_769x769_80k_cityscapes_20200617_010421-73eed8ca.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_80k_cityscapes/ccnet_r50-d8_769x769_80k_cityscapes_20200617_010421.log.json)         |
+| CCNet  | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 79.45 |         80.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_80k_cityscapes/ccnet_r101-d8_769x769_80k_cityscapes_20200618_011502-ad3cd481.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_80k_cityscapes/ccnet_r101-d8_769x769_80k_cityscapes_20200618_011502.log.json)     |
 
 ### ADE20K
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| CCNet  | R-50-D8  | 512x512   |   80000 | 8.8      | 20.89          | 41.78 |         42.98 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_80k_ade20k/ccnet_r50-d8_512x512_80k_ade20k_20200615_014848-aa37f61e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_80k_ade20k/ccnet_r50-d8_512x512_80k_ade20k_20200615_014848.log.json)         |
-| CCNet  | R-101-D8 | 512x512   |   80000 | 12.2     | 14.11          | 43.97 |         45.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_80k_ade20k/ccnet_r101-d8_512x512_80k_ade20k_20200615_014848-1f4929a3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_80k_ade20k/ccnet_r101-d8_512x512_80k_ade20k_20200615_014848.log.json)     |
-| CCNet  | R-50-D8  | 512x512   |  160000 | -        | -              | 42.08 |         43.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_160k_ade20k/ccnet_r50-d8_512x512_160k_ade20k_20200616_084435-7c97193b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_160k_ade20k/ccnet_r50-d8_512x512_160k_ade20k_20200616_084435.log.json)     |
-| CCNet  | R-101-D8 | 512x512   |  160000 | -        | -              | 43.71 |         45.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_160k_ade20k/ccnet_r101-d8_512x512_160k_ade20k_20200616_000644-e849e007.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_160k_ade20k/ccnet_r101-d8_512x512_160k_ade20k_20200616_000644.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| CCNet  | R-50-D8  | 512x512   |   80000 | 8.8      | 20.89          | V100   | 41.78 |         42.98 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_80k_ade20k/ccnet_r50-d8_512x512_80k_ade20k_20200615_014848-aa37f61e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_80k_ade20k/ccnet_r50-d8_512x512_80k_ade20k_20200615_014848.log.json)         |
+| CCNet  | R-101-D8 | 512x512   |   80000 | 12.2     | 14.11          | V100   | 43.97 |         45.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_80k_ade20k/ccnet_r101-d8_512x512_80k_ade20k_20200615_014848-1f4929a3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_80k_ade20k/ccnet_r101-d8_512x512_80k_ade20k_20200615_014848.log.json)     |
+| CCNet  | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 42.08 |         43.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_160k_ade20k/ccnet_r50-d8_512x512_160k_ade20k_20200616_084435-7c97193b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_160k_ade20k/ccnet_r50-d8_512x512_160k_ade20k_20200616_084435.log.json)     |
+| CCNet  | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 43.71 |         45.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_160k_ade20k/ccnet_r101-d8_512x512_160k_ade20k_20200616_000644-e849e007.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_160k_ade20k/ccnet_r101-d8_512x512_160k_ade20k_20200616_000644.log.json) |
 
 ### Pascal VOC 2012 + Aug
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                               |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| CCNet  | R-50-D8  | 512x512   |   20000 | 6        | 20.45          | 76.17 |         77.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_20k_voc12aug/ccnet_r50-d8_512x512_20k_voc12aug_20200617_193212-fad81784.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_20k_voc12aug/ccnet_r50-d8_512x512_20k_voc12aug_20200617_193212.log.json)     |
-| CCNet  | R-101-D8 | 512x512   |   20000 | 9.5      | 13.64          | 77.27 |         79.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_20k_voc12aug/ccnet_r101-d8_512x512_20k_voc12aug_20200617_193212-0007b61d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_20k_voc12aug/ccnet_r101-d8_512x512_20k_voc12aug_20200617_193212.log.json) |
-| CCNet  | R-50-D8  | 512x512   |   40000 | -        | -              | 75.96 |         77.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_40k_voc12aug/ccnet_r50-d8_512x512_40k_voc12aug_20200613_232127-c2a15f02.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_40k_voc12aug/ccnet_r50-d8_512x512_40k_voc12aug_20200613_232127.log.json)     |
-| CCNet  | R-101-D8 | 512x512   |   40000 | -        | -              | 77.87 |         78.90 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_40k_voc12aug/ccnet_r101-d8_512x512_40k_voc12aug_20200613_232127-c30da577.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_40k_voc12aug/ccnet_r101-d8_512x512_40k_voc12aug_20200613_232127.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                               |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| CCNet  | R-50-D8  | 512x512   |   20000 | 6        | 20.45          | V100   | 76.17 |         77.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_20k_voc12aug/ccnet_r50-d8_512x512_20k_voc12aug_20200617_193212-fad81784.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_20k_voc12aug/ccnet_r50-d8_512x512_20k_voc12aug_20200617_193212.log.json)     |
+| CCNet  | R-101-D8 | 512x512   |   20000 | 9.5      | 13.64          | V100   | 77.27 |         79.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_20k_voc12aug/ccnet_r101-d8_512x512_20k_voc12aug_20200617_193212-0007b61d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_20k_voc12aug/ccnet_r101-d8_512x512_20k_voc12aug_20200617_193212.log.json) |
+| CCNet  | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 75.96 |         77.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_40k_voc12aug/ccnet_r50-d8_512x512_40k_voc12aug_20200613_232127-c2a15f02.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_40k_voc12aug/ccnet_r50-d8_512x512_40k_voc12aug_20200613_232127.log.json)     |
+| CCNet  | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 77.87 |         78.90 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_40k_voc12aug/ccnet_r101-d8_512x512_40k_voc12aug_20200613_232127-c30da577.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_40k_voc12aug/ccnet_r101-d8_512x512_40k_voc12aug_20200613_232127.log.json) |
+
+## Citation
+
+```bibtex
+@article{huang2018ccnet,
+    title={CCNet: Criss-Cross Attention for Semantic Segmentation},
+    author={Huang, Zilong and Wang, Xinggang and Huang, Lichao and Huang, Chang and Wei, Yunchao and Liu, Wenyu},
+    booktitle={ICCV},
+    year={2019}
+}
+```
diff --git a/configs/ccnet/ccnet.yml b/configs/ccnet/ccnet.yml
deleted file mode 100644
index b05863dacb..0000000000
--- a/configs/ccnet/ccnet.yml
+++ /dev/null
@@ -1,305 +0,0 @@
-Collections:
-- Name: CCNet
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-    - Pascal VOC 2012 + Aug
-  Paper:
-    URL: https://arxiv.org/abs/1811.11721
-    Title: 'CCNet: Criss-Cross Attention for Semantic Segmentation'
-  README: configs/ccnet/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/speedinghzl/CCNet
-Models:
-- Name: ccnet_r50-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: CCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 301.2
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 6.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.76
-      mIoU(ms+flip): 78.87
-  Config: configs/ccnet/ccnet_r50-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_40k_cityscapes/ccnet_r50-d8_512x1024_40k_cityscapes_20200616_142517-4123f401.pth
-- Name: ccnet_r101-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: CCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 432.9
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 9.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.35
-      mIoU(ms+flip): 78.19
-  Config: configs/ccnet/ccnet_r101-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_40k_cityscapes/ccnet_r101-d8_512x1024_40k_cityscapes_20200616_142540-a3b84ba6.pth
-- Name: ccnet_r50-d8_4xb2-40k_cityscapes-769x769
-  In Collection: CCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 699.3
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 6.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.46
-      mIoU(ms+flip): 79.93
-  Config: configs/ccnet/ccnet_r50-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_40k_cityscapes/ccnet_r50-d8_769x769_40k_cityscapes_20200616_145125-76d11884.pth
-- Name: ccnet_r101-d8_4xb2-40k_cityscapes-769x769
-  In Collection: CCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 990.1
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 10.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.94
-      mIoU(ms+flip): 78.62
-  Config: configs/ccnet/ccnet_r101-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_40k_cityscapes/ccnet_r101-d8_769x769_40k_cityscapes_20200617_101428-4f57c8d0.pth
-- Name: ccnet_r50-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: CCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.03
-      mIoU(ms+flip): 80.16
-  Config: configs/ccnet/ccnet_r50-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_80k_cityscapes/ccnet_r50-d8_512x1024_80k_cityscapes_20200617_010421-869a3423.pth
-- Name: ccnet_r101-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: CCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.87
-      mIoU(ms+flip): 79.9
-  Config: configs/ccnet/ccnet_r101-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_80k_cityscapes/ccnet_r101-d8_512x1024_80k_cityscapes_20200617_203935-ffae8917.pth
-- Name: ccnet_r50-d8_4xb2-80k_cityscapes-769x769
-  In Collection: CCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.29
-      mIoU(ms+flip): 81.08
-  Config: configs/ccnet/ccnet_r50-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_80k_cityscapes/ccnet_r50-d8_769x769_80k_cityscapes_20200617_010421-73eed8ca.pth
-- Name: ccnet_r101-d8_4xb2-80k_cityscapes-769x769
-  In Collection: CCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.45
-      mIoU(ms+flip): 80.66
-  Config: configs/ccnet/ccnet_r101-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_80k_cityscapes/ccnet_r101-d8_769x769_80k_cityscapes_20200618_011502-ad3cd481.pth
-- Name: ccnet_r50-d8_4xb4-80k_ade20k-512x512
-  In Collection: CCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 47.87
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 8.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 41.78
-      mIoU(ms+flip): 42.98
-  Config: configs/ccnet/ccnet_r50-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_80k_ade20k/ccnet_r50-d8_512x512_80k_ade20k_20200615_014848-aa37f61e.pth
-- Name: ccnet_r101-d8_4xb4-80k_ade20k-512x512
-  In Collection: CCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 70.87
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 12.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.97
-      mIoU(ms+flip): 45.13
-  Config: configs/ccnet/ccnet_r101-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_80k_ade20k/ccnet_r101-d8_512x512_80k_ade20k_20200615_014848-1f4929a3.pth
-- Name: ccnet_r50-d8_4xb4-160k_ade20k-512x512
-  In Collection: CCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.08
-      mIoU(ms+flip): 43.13
-  Config: configs/ccnet/ccnet_r50-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_160k_ade20k/ccnet_r50-d8_512x512_160k_ade20k_20200616_084435-7c97193b.pth
-- Name: ccnet_r101-d8_4xb4-160k_ade20k-512x512
-  In Collection: CCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.71
-      mIoU(ms+flip): 45.04
-  Config: configs/ccnet/ccnet_r101-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_160k_ade20k/ccnet_r101-d8_512x512_160k_ade20k_20200616_000644-e849e007.pth
-- Name: ccnet_r50-d8_4xb4-20k_voc12aug-512x512
-  In Collection: CCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 48.9
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 76.17
-      mIoU(ms+flip): 77.51
-  Config: configs/ccnet/ccnet_r50-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_20k_voc12aug/ccnet_r50-d8_512x512_20k_voc12aug_20200617_193212-fad81784.pth
-- Name: ccnet_r101-d8_4xb4-20k_voc12aug-512x512
-  In Collection: CCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 73.31
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 77.27
-      mIoU(ms+flip): 79.02
-  Config: configs/ccnet/ccnet_r101-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_20k_voc12aug/ccnet_r101-d8_512x512_20k_voc12aug_20200617_193212-0007b61d.pth
-- Name: ccnet_r50-d8_4xb4-40k_voc12aug-512x512
-  In Collection: CCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 75.96
-      mIoU(ms+flip): 77.04
-  Config: configs/ccnet/ccnet_r50-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_40k_voc12aug/ccnet_r50-d8_512x512_40k_voc12aug_20200613_232127-c2a15f02.pth
-- Name: ccnet_r101-d8_4xb4-40k_voc12aug-512x512
-  In Collection: CCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 77.87
-      mIoU(ms+flip): 78.9
-  Config: configs/ccnet/ccnet_r101-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_40k_voc12aug/ccnet_r101-d8_512x512_40k_voc12aug_20200613_232127-c30da577.pth
diff --git a/configs/ccnet/metafile.yaml b/configs/ccnet/metafile.yaml
new file mode 100644
index 0000000000..62e5694e47
--- /dev/null
+++ b/configs/ccnet/metafile.yaml
@@ -0,0 +1,391 @@
+Collections:
+- Name: CCNet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - ADE20K
+    - Pascal VOC 2012 + Aug
+  Paper:
+    Title: 'CCNet: Criss-Cross Attention for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.11721
+  README: configs/ccnet/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: ccnet_r50-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: CCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.76
+      mIoU(ms+flip): 78.87
+  Config: configs/ccnet/ccnet_r50-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - CCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_40k_cityscapes/ccnet_r50-d8_512x1024_40k_cityscapes_20200616_142517-4123f401.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_40k_cityscapes/ccnet_r50-d8_512x1024_40k_cityscapes_20200616_142517.log.json
+  Paper:
+    Title: 'CCNet: Criss-Cross Attention for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.11721
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: ccnet_r101-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: CCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.35
+      mIoU(ms+flip): 78.19
+  Config: configs/ccnet/ccnet_r101-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - CCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_40k_cityscapes/ccnet_r101-d8_512x1024_40k_cityscapes_20200616_142540-a3b84ba6.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_40k_cityscapes/ccnet_r101-d8_512x1024_40k_cityscapes_20200616_142540.log.json
+  Paper:
+    Title: 'CCNet: Criss-Cross Attention for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.11721
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: ccnet_r50-d8_4xb2-40k_cityscapes-769x769
+  In Collection: CCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.46
+      mIoU(ms+flip): 79.93
+  Config: configs/ccnet/ccnet_r50-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - CCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_40k_cityscapes/ccnet_r50-d8_769x769_40k_cityscapes_20200616_145125-76d11884.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_40k_cityscapes/ccnet_r50-d8_769x769_40k_cityscapes_20200616_145125.log.json
+  Paper:
+    Title: 'CCNet: Criss-Cross Attention for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.11721
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: ccnet_r101-d8_4xb2-40k_cityscapes-769x769
+  In Collection: CCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.94
+      mIoU(ms+flip): 78.62
+  Config: configs/ccnet/ccnet_r101-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - CCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_40k_cityscapes/ccnet_r101-d8_769x769_40k_cityscapes_20200617_101428-4f57c8d0.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_40k_cityscapes/ccnet_r101-d8_769x769_40k_cityscapes_20200617_101428.log.json
+  Paper:
+    Title: 'CCNet: Criss-Cross Attention for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.11721
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: ccnet_r50-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: CCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.03
+      mIoU(ms+flip): 80.16
+  Config: configs/ccnet/ccnet_r50-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - CCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_80k_cityscapes/ccnet_r50-d8_512x1024_80k_cityscapes_20200617_010421-869a3423.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_80k_cityscapes/ccnet_r50-d8_512x1024_80k_cityscapes_20200617_010421.log.json
+  Paper:
+    Title: 'CCNet: Criss-Cross Attention for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.11721
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: ccnet_r101-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: CCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.87
+      mIoU(ms+flip): 79.9
+  Config: configs/ccnet/ccnet_r101-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - CCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_80k_cityscapes/ccnet_r101-d8_512x1024_80k_cityscapes_20200617_203935-ffae8917.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_80k_cityscapes/ccnet_r101-d8_512x1024_80k_cityscapes_20200617_203935.log.json
+  Paper:
+    Title: 'CCNet: Criss-Cross Attention for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.11721
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: ccnet_r50-d8_4xb2-80k_cityscapes-769x769
+  In Collection: CCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.29
+      mIoU(ms+flip): 81.08
+  Config: configs/ccnet/ccnet_r50-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - CCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_80k_cityscapes/ccnet_r50-d8_769x769_80k_cityscapes_20200617_010421-73eed8ca.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_80k_cityscapes/ccnet_r50-d8_769x769_80k_cityscapes_20200617_010421.log.json
+  Paper:
+    Title: 'CCNet: Criss-Cross Attention for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.11721
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: ccnet_r101-d8_4xb2-80k_cityscapes-769x769
+  In Collection: CCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.45
+      mIoU(ms+flip): 80.66
+  Config: configs/ccnet/ccnet_r101-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - CCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_80k_cityscapes/ccnet_r101-d8_769x769_80k_cityscapes_20200618_011502-ad3cd481.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_80k_cityscapes/ccnet_r101-d8_769x769_80k_cityscapes_20200618_011502.log.json
+  Paper:
+    Title: 'CCNet: Criss-Cross Attention for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.11721
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: ccnet_r50-d8_4xb4-80k_ade20k-512x512
+  In Collection: CCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 41.78
+      mIoU(ms+flip): 42.98
+  Config: configs/ccnet/ccnet_r50-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - CCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_80k_ade20k/ccnet_r50-d8_512x512_80k_ade20k_20200615_014848-aa37f61e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_80k_ade20k/ccnet_r50-d8_512x512_80k_ade20k_20200615_014848.log.json
+  Paper:
+    Title: 'CCNet: Criss-Cross Attention for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.11721
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: ccnet_r101-d8_4xb4-80k_ade20k-512x512
+  In Collection: CCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.97
+      mIoU(ms+flip): 45.13
+  Config: configs/ccnet/ccnet_r101-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - CCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 12.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_80k_ade20k/ccnet_r101-d8_512x512_80k_ade20k_20200615_014848-1f4929a3.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_80k_ade20k/ccnet_r101-d8_512x512_80k_ade20k_20200615_014848.log.json
+  Paper:
+    Title: 'CCNet: Criss-Cross Attention for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.11721
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: ccnet_r50-d8_4xb4-160k_ade20k-512x512
+  In Collection: CCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.08
+      mIoU(ms+flip): 43.13
+  Config: configs/ccnet/ccnet_r50-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - CCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_160k_ade20k/ccnet_r50-d8_512x512_160k_ade20k_20200616_084435-7c97193b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_160k_ade20k/ccnet_r50-d8_512x512_160k_ade20k_20200616_084435.log.json
+  Paper:
+    Title: 'CCNet: Criss-Cross Attention for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.11721
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: ccnet_r101-d8_4xb4-160k_ade20k-512x512
+  In Collection: CCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.71
+      mIoU(ms+flip): 45.04
+  Config: configs/ccnet/ccnet_r101-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - CCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_160k_ade20k/ccnet_r101-d8_512x512_160k_ade20k_20200616_000644-e849e007.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_160k_ade20k/ccnet_r101-d8_512x512_160k_ade20k_20200616_000644.log.json
+  Paper:
+    Title: 'CCNet: Criss-Cross Attention for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.11721
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: ccnet_r50-d8_4xb4-20k_voc12aug-512x512
+  In Collection: CCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 76.17
+      mIoU(ms+flip): 77.51
+  Config: configs/ccnet/ccnet_r50-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - CCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_20k_voc12aug/ccnet_r50-d8_512x512_20k_voc12aug_20200617_193212-fad81784.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_20k_voc12aug/ccnet_r50-d8_512x512_20k_voc12aug_20200617_193212.log.json
+  Paper:
+    Title: 'CCNet: Criss-Cross Attention for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.11721
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: ccnet_r101-d8_4xb4-20k_voc12aug-512x512
+  In Collection: CCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 77.27
+      mIoU(ms+flip): 79.02
+  Config: configs/ccnet/ccnet_r101-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - CCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_20k_voc12aug/ccnet_r101-d8_512x512_20k_voc12aug_20200617_193212-0007b61d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_20k_voc12aug/ccnet_r101-d8_512x512_20k_voc12aug_20200617_193212.log.json
+  Paper:
+    Title: 'CCNet: Criss-Cross Attention for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.11721
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: ccnet_r50-d8_4xb4-40k_voc12aug-512x512
+  In Collection: CCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 75.96
+      mIoU(ms+flip): 77.04
+  Config: configs/ccnet/ccnet_r50-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - CCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_40k_voc12aug/ccnet_r50-d8_512x512_40k_voc12aug_20200613_232127-c2a15f02.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_40k_voc12aug/ccnet_r50-d8_512x512_40k_voc12aug_20200613_232127.log.json
+  Paper:
+    Title: 'CCNet: Criss-Cross Attention for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.11721
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
+- Name: ccnet_r101-d8_4xb4-40k_voc12aug-512x512
+  In Collection: CCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 77.87
+      mIoU(ms+flip): 78.9
+  Config: configs/ccnet/ccnet_r101-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - CCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_40k_voc12aug/ccnet_r101-d8_512x512_40k_voc12aug_20200613_232127-c30da577.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_40k_voc12aug/ccnet_r101-d8_512x512_40k_voc12aug_20200613_232127.log.json
+  Paper:
+    Title: 'CCNet: Criss-Cross Attention for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.11721
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
+  Framework: PyTorch
diff --git a/configs/cgnet/README.md b/configs/cgnet/README.md
index 709d0c0b8f..60cde58291 100644
--- a/configs/cgnet/README.md
+++ b/configs/cgnet/README.md
@@ -1,6 +1,6 @@
 # CGNet
 
-[CGNet: A Light-weight Context Guided Network for Semantic Segmentation](https://arxiv.org/abs/1811.08201)
+> [CGNet: A Light-weight Context Guided Network for Semantic Segmentation](https://arxiv.org/abs/1811.08201)
 
 ## Introduction
 
@@ -22,6 +22,15 @@ The demand of applying semantic segmentation model on mobile devices has been in
 <img src="https://user-images.githubusercontent.com/24582831/142900351-89559574-79cc-4f57-8f69-5d88765ec38d.png" width="80%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| CGNet  | M3N21    | 680x680   |   60000 | 7.5      | 30.51          | V100   | 65.63 |         68.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/cgnet/cgnet_fcn_4xb4-60k_cityscapes-680x680.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_680x680_60k_cityscapes/cgnet_680x680_60k_cityscapes_20201101_110253-4c0b2f2d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_680x680_60k_cityscapes/cgnet_680x680_60k_cityscapes-20201101_110253.log.json)     |
+| CGNet  | M3N21    | 512x1024  |   60000 | 8.3      | 31.14          | V100   | 68.27 |         70.33 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/cgnet/cgnet_fcn_4xb8-60k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_512x1024_60k_cityscapes/cgnet_512x1024_60k_cityscapes_20201101_110254-124ea03b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_512x1024_60k_cityscapes/cgnet_512x1024_60k_cityscapes-20201101_110254.log.json) |
+
 ## Citation
 
 ```bibtext
@@ -35,12 +44,3 @@ The demand of applying semantic segmentation model on mobile devices has been in
   publisher={IEEE}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| CGNet  | M3N21    | 680x680   |   60000 | 7.5      | 30.51          | 65.63 |         68.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/cgnet/cgnet_fcn_4xb4-60k_cityscapes-680x680.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_680x680_60k_cityscapes/cgnet_680x680_60k_cityscapes_20201101_110253-4c0b2f2d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_680x680_60k_cityscapes/cgnet_680x680_60k_cityscapes-20201101_110253.log.json)     |
-| CGNet  | M3N21    | 512x1024  |   60000 | 8.3      | 31.14          | 68.27 |         70.33 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/cgnet/cgnet_fcn_4xb8-60k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_512x1024_60k_cityscapes/cgnet_512x1024_60k_cityscapes_20201101_110254-124ea03b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_512x1024_60k_cityscapes/cgnet_512x1024_60k_cityscapes-20201101_110254.log.json) |
diff --git a/configs/cgnet/cgnet.yml b/configs/cgnet/cgnet.yml
deleted file mode 100644
index be79b89355..0000000000
--- a/configs/cgnet/cgnet.yml
+++ /dev/null
@@ -1,59 +0,0 @@
-Collections:
-- Name: CGNet
-  Metadata:
-    Training Data:
-    - Cityscapes
-  Paper:
-    URL: https://arxiv.org/abs/1811.08201
-    Title: 'CGNet: A Light-weight Context Guided Network for Semantic Segmentation'
-  README: configs/cgnet/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/cgnet.py#L187
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/wutianyiRosun/CGNet
-Models:
-- Name: cgnet_fcn_4xb4-60k_cityscapes-680x680
-  In Collection: CGNet
-  Metadata:
-    backbone: M3N21
-    crop size: (680,680)
-    lr schd: 60000
-    inference time (ms/im):
-    - value: 32.78
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (680,680)
-    Training Memory (GB): 7.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 65.63
-      mIoU(ms+flip): 68.04
-  Config: configs/cgnet/cgnet_fcn_4xb4-60k_cityscapes-680x680.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_680x680_60k_cityscapes/cgnet_680x680_60k_cityscapes_20201101_110253-4c0b2f2d.pth
-- Name: cgnet_fcn_4xb8-60k_cityscapes-512x1024
-  In Collection: CGNet
-  Metadata:
-    backbone: M3N21
-    crop size: (512,1024)
-    lr schd: 60000
-    inference time (ms/im):
-    - value: 32.11
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 8.3
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 68.27
-      mIoU(ms+flip): 70.33
-  Config: configs/cgnet/cgnet_fcn_4xb8-60k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_512x1024_60k_cityscapes/cgnet_512x1024_60k_cityscapes_20201101_110254-124ea03b.pth
diff --git a/configs/cgnet/metafile.yaml b/configs/cgnet/metafile.yaml
new file mode 100644
index 0000000000..063fc8b3c6
--- /dev/null
+++ b/configs/cgnet/metafile.yaml
@@ -0,0 +1,61 @@
+Collections:
+- Name: CGNet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+  Paper:
+    Title: 'CGNet: A Light-weight Context Guided Network for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.08201
+  README: configs/cgnet/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: cgnet_fcn_4xb4-60k_cityscapes-680x680
+  In Collection: CGNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 65.63
+      mIoU(ms+flip): 68.04
+  Config: configs/cgnet/cgnet_fcn_4xb4-60k_cityscapes-680x680.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - M3N21
+    - CGNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_680x680_60k_cityscapes/cgnet_680x680_60k_cityscapes_20201101_110253-4c0b2f2d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_680x680_60k_cityscapes/cgnet_680x680_60k_cityscapes-20201101_110253.log.json
+  Paper:
+    Title: 'CGNet: A Light-weight Context Guided Network for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.08201
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/cgnet.py#L187
+  Framework: PyTorch
+- Name: cgnet_fcn_4xb8-60k_cityscapes-512x1024
+  In Collection: CGNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 68.27
+      mIoU(ms+flip): 70.33
+  Config: configs/cgnet/cgnet_fcn_4xb8-60k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 32
+    Architecture:
+    - M3N21
+    - CGNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.3
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_512x1024_60k_cityscapes/cgnet_512x1024_60k_cityscapes_20201101_110254-124ea03b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_512x1024_60k_cityscapes/cgnet_512x1024_60k_cityscapes-20201101_110254.log.json
+  Paper:
+    Title: 'CGNet: A Light-weight Context Guided Network for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1811.08201
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/cgnet.py#L187
+  Framework: PyTorch
diff --git a/configs/convnext/README.md b/configs/convnext/README.md
index 6a826b9d6a..91339377c0 100644
--- a/configs/convnext/README.md
+++ b/configs/convnext/README.md
@@ -1,6 +1,6 @@
 # ConvNeXt
 
-[A ConvNet for the 2020s](https://arxiv.org/abs/2201.03545)
+> [A ConvNet for the 2020s](https://arxiv.org/abs/2201.03545)
 
 ## Introduction
 
@@ -22,15 +22,6 @@ The "Roaring 20s" of visual recognition began with the introduction of Vision Tr
 <img src="https://user-images.githubusercontent.com/8370623/148624004-e9581042-ea4d-4e10-b3bd-42c92b02053b.png" width="90%"/>
 </div>
 
-```bibtex
-@article{liu2022convnet,
-  title={A ConvNet for the 2020s},
-  author={Liu, Zhuang and Mao, Hanzi and Wu, Chao-Yuan and Feichtenhofer, Christoph and Darrell, Trevor and Xie, Saining},
-  journal={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
-  year={2022}
-}
-```
-
 ### Usage
 
 - ConvNeXt backbone needs to install [MMClassification](https://github.com/open-mmlab/mmclassification) first, which has abundant backbones for downstream tasks.
@@ -58,15 +49,26 @@ The pre-trained models on ImageNet-1k or ImageNet-21k are used to fine-tune on t
 
 ### ADE20K
 
-| Method  | Backbone    | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) | config                                                                                                                                       | download                                                                                                                                                                                                                                                                                                                                                                                             |
-| ------- | ----------- | --------- | ------- | -------- | -------------- | ----- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UPerNet | ConvNeXt-T  | 512x512   | 160000  | 4.23     | 19.90          | 46.11 | 46.62         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/convnext/convnext-tiny_upernet_8xb2-amp-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_tiny_fp16_512x512_160k_ade20k/upernet_convnext_tiny_fp16_512x512_160k_ade20k_20220227_124553-cad485de.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_tiny_fp16_512x512_160k_ade20k/upernet_convnext_tiny_fp16_512x512_160k_ade20k_20220227_124553.log.json)         |
-| UPerNet | ConvNeXt-S  | 512x512   | 160000  | 5.16     | 15.18          | 48.56 | 49.02         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/convnext/convnext-small_upernet_8xb2-amp-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_small_fp16_512x512_160k_ade20k/upernet_convnext_small_fp16_512x512_160k_ade20k_20220227_131208-1b1e394f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_small_fp16_512x512_160k_ade20k/upernet_convnext_small_fp16_512x512_160k_ade20k_20220227_131208.log.json)     |
-| UPerNet | ConvNeXt-B  | 512x512   | 160000  | 6.33     | 14.41          | 48.71 | 49.54         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/convnext/convnext-base_upernet_8xb2-amp-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_512x512_160k_ade20k/upernet_convnext_base_fp16_512x512_160k_ade20k_20220227_181227-02a24fc6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_512x512_160k_ade20k/upernet_convnext_base_fp16_512x512_160k_ade20k_20220227_181227.log.json)         |
-| UPerNet | ConvNeXt-B  | 640x640   | 160000  | 8.53     | 10.88          | 52.13 | 52.66         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/convnext/convnext-base_upernet_8xb2-amp-160k_ade20k-640x640.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_640x640_160k_ade20k/upernet_convnext_base_fp16_640x640_160k_ade20k_20220227_182859-9280e39b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_640x640_160k_ade20k/upernet_convnext_base_fp16_640x640_160k_ade20k_20220227_182859.log.json)         |
-| UPerNet | ConvNeXt-L  | 640x640   | 160000  | 12.08    | 7.69           | 53.16 | 53.38         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/convnext/convnext-large_upernet_8xb2-amp-160k_ade20k-640x640.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_large_fp16_640x640_160k_ade20k/upernet_convnext_large_fp16_640x640_160k_ade20k_20220226_040532-e57aa54d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_large_fp16_640x640_160k_ade20k/upernet_convnext_large_fp16_640x640_160k_ade20k_20220226_040532.log.json)     |
-| UPerNet | ConvNeXt-XL | 640x640   | 160000  | 26.16\*  | 6.33           | 53.58 | 54.11         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/convnext/convnext-xlarge_upernet_8xb2-amp-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_xlarge_fp16_640x640_160k_ade20k/upernet_convnext_xlarge_fp16_640x640_160k_ade20k_20220226_080344-95fc38c2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_xlarge_fp16_640x640_160k_ade20k/upernet_convnext_xlarge_fp16_640x640_160k_ade20k_20220226_080344.log.json) |
+| Method  | Backbone    | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                                       | download                                                                                                                                                                                                                                                                                                                                                                                             |
+| ------- | ----------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UPerNet | ConvNeXt-T  | 512x512   | 160000  | 4.23     | 19.90          | V100   | 46.11 | 46.62         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/convnext/convnext-tiny_upernet_8xb2-amp-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_tiny_fp16_512x512_160k_ade20k/upernet_convnext_tiny_fp16_512x512_160k_ade20k_20220227_124553-cad485de.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_tiny_fp16_512x512_160k_ade20k/upernet_convnext_tiny_fp16_512x512_160k_ade20k_20220227_124553.log.json)         |
+| UPerNet | ConvNeXt-S  | 512x512   | 160000  | 5.16     | 15.18          | V100   | 48.56 | 49.02         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/convnext/convnext-small_upernet_8xb2-amp-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_small_fp16_512x512_160k_ade20k/upernet_convnext_small_fp16_512x512_160k_ade20k_20220227_131208-1b1e394f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_small_fp16_512x512_160k_ade20k/upernet_convnext_small_fp16_512x512_160k_ade20k_20220227_131208.log.json)     |
+| UPerNet | ConvNeXt-B  | 512x512   | 160000  | 6.33     | 14.41          | V100   | 48.71 | 49.54         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/convnext/convnext-base_upernet_8xb2-amp-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_512x512_160k_ade20k/upernet_convnext_base_fp16_512x512_160k_ade20k_20220227_181227-02a24fc6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_512x512_160k_ade20k/upernet_convnext_base_fp16_512x512_160k_ade20k_20220227_181227.log.json)         |
+| UPerNet | ConvNeXt-B  | 640x640   | 160000  | 8.53     | 10.88          | V100   | 52.13 | 52.66         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/convnext/convnext-base_upernet_8xb2-amp-160k_ade20k-640x640.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_640x640_160k_ade20k/upernet_convnext_base_fp16_640x640_160k_ade20k_20220227_182859-9280e39b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_640x640_160k_ade20k/upernet_convnext_base_fp16_640x640_160k_ade20k_20220227_182859.log.json)         |
+| UPerNet | ConvNeXt-L  | 640x640   | 160000  | 12.08    | 7.69           | V100   | 53.16 | 53.38         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/convnext/convnext-large_upernet_8xb2-amp-160k_ade20k-640x640.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_large_fp16_640x640_160k_ade20k/upernet_convnext_large_fp16_640x640_160k_ade20k_20220226_040532-e57aa54d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_large_fp16_640x640_160k_ade20k/upernet_convnext_large_fp16_640x640_160k_ade20k_20220226_040532.log.json)     |
+| UPerNet | ConvNeXt-XL | 640x640   | 160000  | 26.16\*  | 6.33           | V100   | 53.58 | 54.11         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/convnext/convnext-xlarge_upernet_8xb2-amp-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_xlarge_fp16_640x640_160k_ade20k/upernet_convnext_xlarge_fp16_640x640_160k_ade20k_20220226_080344-95fc38c2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_xlarge_fp16_640x640_160k_ade20k/upernet_convnext_xlarge_fp16_640x640_160k_ade20k_20220226_080344.log.json) |
 
 Note:
 
 - `Mem (GB)` with * is collected when `cudnn_benchmark=True`, and hardware is V100.
+
+## Citation
+
+```bibtex
+@article{liu2022convnet,
+  title={A ConvNet for the 2020s},
+  author={Liu, Zhuang and Mao, Hanzi and Wu, Chao-Yuan and Feichtenhofer, Christoph and Darrell, Trevor and Xie, Saining},
+  journal={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+  year={2022}
+}
+```
diff --git a/configs/convnext/convnext.yml b/configs/convnext/convnext.yml
deleted file mode 100644
index 2162e0c50c..0000000000
--- a/configs/convnext/convnext.yml
+++ /dev/null
@@ -1,133 +0,0 @@
-Models:
-- Name: convnext-tiny_upernet_8xb2-amp-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: ConvNeXt-T
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 50.25
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: AMP
-      resolution: (512,512)
-    Training Memory (GB): 4.23
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 46.11
-      mIoU(ms+flip): 46.62
-  Config: configs/convnext/convnext-tiny_upernet_8xb2-amp-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_tiny_fp16_512x512_160k_ade20k/upernet_convnext_tiny_fp16_512x512_160k_ade20k_20220227_124553-cad485de.pth
-- Name: convnext-small_upernet_8xb2-amp-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: ConvNeXt-S
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 65.88
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: AMP
-      resolution: (512,512)
-    Training Memory (GB): 5.16
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 48.56
-      mIoU(ms+flip): 49.02
-  Config: configs/convnext/convnext-small_upernet_8xb2-amp-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_small_fp16_512x512_160k_ade20k/upernet_convnext_small_fp16_512x512_160k_ade20k_20220227_131208-1b1e394f.pth
-- Name: convnext-base_upernet_8xb2-amp-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: ConvNeXt-B
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 69.4
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: AMP
-      resolution: (512,512)
-    Training Memory (GB): 6.33
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 48.71
-      mIoU(ms+flip): 49.54
-  Config: configs/convnext/convnext-base_upernet_8xb2-amp-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_512x512_160k_ade20k/upernet_convnext_base_fp16_512x512_160k_ade20k_20220227_181227-02a24fc6.pth
-- Name: convnext-base_upernet_8xb2-amp-160k_ade20k-640x640
-  In Collection: UPerNet
-  Metadata:
-    backbone: ConvNeXt-B
-    crop size: (640,640)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 91.91
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: AMP
-      resolution: (640,640)
-    Training Memory (GB): 8.53
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 52.13
-      mIoU(ms+flip): 52.66
-  Config: configs/convnext/convnext-base_upernet_8xb2-amp-160k_ade20k-640x640.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_640x640_160k_ade20k/upernet_convnext_base_fp16_640x640_160k_ade20k_20220227_182859-9280e39b.pth
-- Name: convnext-large_upernet_8xb2-amp-160k_ade20k-640x640
-  In Collection: UPerNet
-  Metadata:
-    backbone: ConvNeXt-L
-    crop size: (640,640)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 130.04
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: AMP
-      resolution: (640,640)
-    Training Memory (GB): 12.08
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 53.16
-      mIoU(ms+flip): 53.38
-  Config: configs/convnext/convnext-large_upernet_8xb2-amp-160k_ade20k-640x640.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_large_fp16_640x640_160k_ade20k/upernet_convnext_large_fp16_640x640_160k_ade20k_20220226_040532-e57aa54d.pth
-- Name: convnext-xlarge_upernet_8xb2-amp-160k_ade20k-640x640
-  In Collection: UPerNet
-  Metadata:
-    backbone: ConvNeXt-XL
-    crop size: (640,640)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 157.98
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: AMP
-      resolution: (640,640)
-    Training Memory (GB): 26.16
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 53.58
-      mIoU(ms+flip): 54.11
-  Config: configs/convnext/convnext-xlarge_upernet_8xb2-amp-160k_ade20k-640x640.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_xlarge_fp16_640x640_160k_ade20k/upernet_convnext_xlarge_fp16_640x640_160k_ade20k_20220226_080344-95fc38c2.pth
diff --git a/configs/convnext/metafile.yaml b/configs/convnext/metafile.yaml
new file mode 100644
index 0000000000..8340a373c2
--- /dev/null
+++ b/configs/convnext/metafile.yaml
@@ -0,0 +1,145 @@
+Models:
+- Name: convnext-tiny_upernet_8xb2-amp-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 46.11
+      mIoU(ms+flip): 46.62
+  Config: configs/convnext/convnext-tiny_upernet_8xb2-amp-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - ConvNeXt-T
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 4.23
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_tiny_fp16_512x512_160k_ade20k/upernet_convnext_tiny_fp16_512x512_160k_ade20k_20220227_124553-cad485de.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_tiny_fp16_512x512_160k_ade20k/upernet_convnext_tiny_fp16_512x512_160k_ade20k_20220227_124553.log.json
+  Paper:
+    Title: A ConvNet for the 2020s
+    URL: https://arxiv.org/abs/2201.03545
+  Code: https://github.com/open-mmlab/mmclassification/blob/v0.20.1/mmcls/models/backbones/convnext.py#L133
+  Framework: PyTorch
+- Name: convnext-small_upernet_8xb2-amp-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 48.56
+      mIoU(ms+flip): 49.02
+  Config: configs/convnext/convnext-small_upernet_8xb2-amp-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - ConvNeXt-S
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 5.16
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_small_fp16_512x512_160k_ade20k/upernet_convnext_small_fp16_512x512_160k_ade20k_20220227_131208-1b1e394f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_small_fp16_512x512_160k_ade20k/upernet_convnext_small_fp16_512x512_160k_ade20k_20220227_131208.log.json
+  Paper:
+    Title: A ConvNet for the 2020s
+    URL: https://arxiv.org/abs/2201.03545
+  Code: https://github.com/open-mmlab/mmclassification/blob/v0.20.1/mmcls/models/backbones/convnext.py#L133
+  Framework: PyTorch
+- Name: convnext-base_upernet_8xb2-amp-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 48.71
+      mIoU(ms+flip): 49.54
+  Config: configs/convnext/convnext-base_upernet_8xb2-amp-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - ConvNeXt-B
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 6.33
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_512x512_160k_ade20k/upernet_convnext_base_fp16_512x512_160k_ade20k_20220227_181227-02a24fc6.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_512x512_160k_ade20k/upernet_convnext_base_fp16_512x512_160k_ade20k_20220227_181227.log.json
+  Paper:
+    Title: A ConvNet for the 2020s
+    URL: https://arxiv.org/abs/2201.03545
+  Code: https://github.com/open-mmlab/mmclassification/blob/v0.20.1/mmcls/models/backbones/convnext.py#L133
+  Framework: PyTorch
+- Name: convnext-base_upernet_8xb2-amp-160k_ade20k-640x640
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 52.13
+      mIoU(ms+flip): 52.66
+  Config: configs/convnext/convnext-base_upernet_8xb2-amp-160k_ade20k-640x640.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - ConvNeXt-B
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 8.53
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_640x640_160k_ade20k/upernet_convnext_base_fp16_640x640_160k_ade20k_20220227_182859-9280e39b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_640x640_160k_ade20k/upernet_convnext_base_fp16_640x640_160k_ade20k_20220227_182859.log.json
+  Paper:
+    Title: A ConvNet for the 2020s
+    URL: https://arxiv.org/abs/2201.03545
+  Code: https://github.com/open-mmlab/mmclassification/blob/v0.20.1/mmcls/models/backbones/convnext.py#L133
+  Framework: PyTorch
+- Name: convnext-large_upernet_8xb2-amp-160k_ade20k-640x640
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 53.16
+      mIoU(ms+flip): 53.38
+  Config: configs/convnext/convnext-large_upernet_8xb2-amp-160k_ade20k-640x640.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - ConvNeXt-L
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 12.08
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_large_fp16_640x640_160k_ade20k/upernet_convnext_large_fp16_640x640_160k_ade20k_20220226_040532-e57aa54d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_large_fp16_640x640_160k_ade20k/upernet_convnext_large_fp16_640x640_160k_ade20k_20220226_040532.log.json
+  Paper:
+    Title: A ConvNet for the 2020s
+    URL: https://arxiv.org/abs/2201.03545
+  Code: https://github.com/open-mmlab/mmclassification/blob/v0.20.1/mmcls/models/backbones/convnext.py#L133
+  Framework: PyTorch
+- Name: convnext-xlarge_upernet_8xb2-amp-160k_ade20k-640x640
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 53.58
+      mIoU(ms+flip): 54.11
+  Config: configs/convnext/convnext-xlarge_upernet_8xb2-amp-160k_ade20k-640x640.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - ConvNeXt-XL
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 26.16
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_xlarge_fp16_640x640_160k_ade20k/upernet_convnext_xlarge_fp16_640x640_160k_ade20k_20220226_080344-95fc38c2.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_xlarge_fp16_640x640_160k_ade20k/upernet_convnext_xlarge_fp16_640x640_160k_ade20k_20220226_080344.log.json
+  Paper:
+    Title: A ConvNet for the 2020s
+    URL: https://arxiv.org/abs/2201.03545
+  Code: https://github.com/open-mmlab/mmclassification/blob/v0.20.1/mmcls/models/backbones/convnext.py#L133
+  Framework: PyTorch
diff --git a/configs/danet/README.md b/configs/danet/README.md
index 52059e93a5..b5841e23be 100644
--- a/configs/danet/README.md
+++ b/configs/danet/README.md
@@ -1,6 +1,6 @@
 # DANet
 
-[Dual Attention Network for Scene Segmentation](https://arxiv.org/abs/1809.02983)
+> [Dual Attention Network for Scene Segmentation](https://arxiv.org/abs/1809.02983)
 
 ## Introduction
 
@@ -22,46 +22,46 @@ In this paper, we address the scene segmentation task by capturing rich contextu
 <img src="https://user-images.githubusercontent.com/24582831/142900467-f832fdb9-3b7d-47d3-8e80-e6ee9303bdfb.png" width="70%"/>
 </div>
 
-## Citation
-
-```bibtex
-@article{fu2018dual,
-  title={Dual Attention Network for Scene Segmentation},
-  author={Jun Fu, Jing Liu, Haijie Tian, Yong Li, Yongjun Bao, Zhiwei Fang,and Hanqing Lu},
-  booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
-  year={2019}
-}
-```
-
 ## Results and models
 
 ### Cityscapes
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DANet  | R-50-D8  | 512x1024  |   40000 | 7.4      | 2.66           | 78.74 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_40k_cityscapes/danet_r50-d8_512x1024_40k_cityscapes_20200605_191324-c0dbfa5f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_40k_cityscapes/danet_r50-d8_512x1024_40k_cityscapes_20200605_191324.log.json)     |
-| DANet  | R-101-D8 | 512x1024  |   40000 | 10.9     | 1.99           | 80.52 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_40k_cityscapes/danet_r101-d8_512x1024_40k_cityscapes_20200605_200831-c57a7157.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_40k_cityscapes/danet_r101-d8_512x1024_40k_cityscapes_20200605_200831.log.json) |
-| DANet  | R-50-D8  | 769x769   |   40000 | 8.8      | 1.56           | 78.88 | 80.62         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_40k_cityscapes/danet_r50-d8_769x769_40k_cityscapes_20200530_025703-76681c60.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_40k_cityscapes/danet_r50-d8_769x769_40k_cityscapes_20200530_025703.log.json)         |
-| DANet  | R-101-D8 | 769x769   |   40000 | 12.8     | 1.07           | 79.88 | 81.47         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_40k_cityscapes/danet_r101-d8_769x769_40k_cityscapes_20200530_025717-dcb7fd4e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_40k_cityscapes/danet_r101-d8_769x769_40k_cityscapes_20200530_025717.log.json)     |
-| DANet  | R-50-D8  | 512x1024  |   80000 | -        | -              | 79.34 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_80k_cityscapes/danet_r50-d8_512x1024_80k_cityscapes_20200607_133029-2bfa2293.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_80k_cityscapes/danet_r50-d8_512x1024_80k_cityscapes_20200607_133029.log.json)     |
-| DANet  | R-101-D8 | 512x1024  |   80000 | -        | -              | 80.41 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_80k_cityscapes/danet_r101-d8_512x1024_80k_cityscapes_20200607_132918-955e6350.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_80k_cityscapes/danet_r101-d8_512x1024_80k_cityscapes_20200607_132918.log.json) |
-| DANet  | R-50-D8  | 769x769   |   80000 | -        | -              | 79.27 | 80.96         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_80k_cityscapes/danet_r50-d8_769x769_80k_cityscapes_20200607_132954-495689b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_80k_cityscapes/danet_r50-d8_769x769_80k_cityscapes_20200607_132954.log.json)         |
-| DANet  | R-101-D8 | 769x769   |   80000 | -        | -              | 80.47 | 82.02         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_80k_cityscapes/danet_r101-d8_769x769_80k_cityscapes_20200607_132918-f3a929e7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_80k_cityscapes/danet_r101-d8_769x769_80k_cityscapes_20200607_132918.log.json)     |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DANet  | R-50-D8  | 512x1024  |   40000 | 7.4      | 2.66           | V100   | 78.74 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_40k_cityscapes/danet_r50-d8_512x1024_40k_cityscapes_20200605_191324-c0dbfa5f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_40k_cityscapes/danet_r50-d8_512x1024_40k_cityscapes_20200605_191324.log.json)     |
+| DANet  | R-101-D8 | 512x1024  |   40000 | 10.9     | 1.99           | V100   | 80.52 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_40k_cityscapes/danet_r101-d8_512x1024_40k_cityscapes_20200605_200831-c57a7157.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_40k_cityscapes/danet_r101-d8_512x1024_40k_cityscapes_20200605_200831.log.json) |
+| DANet  | R-50-D8  | 769x769   |   40000 | 8.8      | 1.56           | V100   | 78.88 | 80.62         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_40k_cityscapes/danet_r50-d8_769x769_40k_cityscapes_20200530_025703-76681c60.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_40k_cityscapes/danet_r50-d8_769x769_40k_cityscapes_20200530_025703.log.json)         |
+| DANet  | R-101-D8 | 769x769   |   40000 | 12.8     | 1.07           | V100   | 79.88 | 81.47         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_40k_cityscapes/danet_r101-d8_769x769_40k_cityscapes_20200530_025717-dcb7fd4e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_40k_cityscapes/danet_r101-d8_769x769_40k_cityscapes_20200530_025717.log.json)     |
+| DANet  | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 79.34 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_80k_cityscapes/danet_r50-d8_512x1024_80k_cityscapes_20200607_133029-2bfa2293.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_80k_cityscapes/danet_r50-d8_512x1024_80k_cityscapes_20200607_133029.log.json)     |
+| DANet  | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 80.41 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_80k_cityscapes/danet_r101-d8_512x1024_80k_cityscapes_20200607_132918-955e6350.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_80k_cityscapes/danet_r101-d8_512x1024_80k_cityscapes_20200607_132918.log.json) |
+| DANet  | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 79.27 | 80.96         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_80k_cityscapes/danet_r50-d8_769x769_80k_cityscapes_20200607_132954-495689b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_80k_cityscapes/danet_r50-d8_769x769_80k_cityscapes_20200607_132954.log.json)         |
+| DANet  | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 80.47 | 82.02         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_80k_cityscapes/danet_r101-d8_769x769_80k_cityscapes_20200607_132918-f3a929e7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_80k_cityscapes/danet_r101-d8_769x769_80k_cityscapes_20200607_132918.log.json)     |
 
 ### ADE20K
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DANet  | R-50-D8  | 512x512   |   80000 | 11.5     | 21.20          | 41.66 |         42.90 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_80k_ade20k/danet_r50-d8_512x512_80k_ade20k_20200615_015125-edb18e08.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_80k_ade20k/danet_r50-d8_512x512_80k_ade20k_20200615_015125.log.json)         |
-| DANet  | R-101-D8 | 512x512   |   80000 | 15       | 14.18          | 43.64 |         45.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_80k_ade20k/danet_r101-d8_512x512_80k_ade20k_20200615_015126-d0357c73.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_80k_ade20k/danet_r101-d8_512x512_80k_ade20k_20200615_015126.log.json)     |
-| DANet  | R-50-D8  | 512x512   |  160000 | -        | -              | 42.45 |         43.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_160k_ade20k/danet_r50-d8_512x512_160k_ade20k_20200616_082340-9cb35dcd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_160k_ade20k/danet_r50-d8_512x512_160k_ade20k_20200616_082340.log.json)     |
-| DANet  | R-101-D8 | 512x512   |  160000 | -        | -              | 44.17 |         45.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_160k_ade20k/danet_r101-d8_512x512_160k_ade20k_20200616_082348-23bf12f9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_160k_ade20k/danet_r101-d8_512x512_160k_ade20k_20200616_082348.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DANet  | R-50-D8  | 512x512   |   80000 | 11.5     | 21.20          | V100   | 41.66 |         42.90 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_80k_ade20k/danet_r50-d8_512x512_80k_ade20k_20200615_015125-edb18e08.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_80k_ade20k/danet_r50-d8_512x512_80k_ade20k_20200615_015125.log.json)         |
+| DANet  | R-101-D8 | 512x512   |   80000 | 15       | 14.18          | V100   | 43.64 |         45.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_80k_ade20k/danet_r101-d8_512x512_80k_ade20k_20200615_015126-d0357c73.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_80k_ade20k/danet_r101-d8_512x512_80k_ade20k_20200615_015126.log.json)     |
+| DANet  | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 42.45 |         43.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_160k_ade20k/danet_r50-d8_512x512_160k_ade20k_20200616_082340-9cb35dcd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_160k_ade20k/danet_r50-d8_512x512_160k_ade20k_20200616_082340.log.json)     |
+| DANet  | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 44.17 |         45.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_160k_ade20k/danet_r101-d8_512x512_160k_ade20k_20200616_082348-23bf12f9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_160k_ade20k/danet_r101-d8_512x512_160k_ade20k_20200616_082348.log.json) |
 
 ### Pascal VOC 2012 + Aug
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                               |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DANet  | R-50-D8  | 512x512   |   20000 | 6.5      | 20.94          | 74.45 |         75.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_20k_voc12aug/danet_r50-d8_512x512_20k_voc12aug_20200618_070026-9e9e3ab3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_20k_voc12aug/danet_r50-d8_512x512_20k_voc12aug_20200618_070026.log.json)     |
-| DANet  | R-101-D8 | 512x512   |   20000 | 9.9      | 13.76          | 76.02 |         77.23 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_20k_voc12aug/danet_r101-d8_512x512_20k_voc12aug_20200618_070026-d48d23b2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_20k_voc12aug/danet_r101-d8_512x512_20k_voc12aug_20200618_070026.log.json) |
-| DANet  | R-50-D8  | 512x512   |   40000 | -        | -              | 76.37 |         77.29 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_40k_voc12aug/danet_r50-d8_512x512_40k_voc12aug_20200613_235526-426e3a64.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_40k_voc12aug/danet_r50-d8_512x512_40k_voc12aug_20200613_235526.log.json)     |
-| DANet  | R-101-D8 | 512x512   |   40000 | -        | -              | 76.51 |         77.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_40k_voc12aug/danet_r101-d8_512x512_40k_voc12aug_20200613_223031-788e232a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_40k_voc12aug/danet_r101-d8_512x512_40k_voc12aug_20200613_223031.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                               |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DANet  | R-50-D8  | 512x512   |   20000 | 6.5      | 20.94          | V100   | 74.45 |         75.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_20k_voc12aug/danet_r50-d8_512x512_20k_voc12aug_20200618_070026-9e9e3ab3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_20k_voc12aug/danet_r50-d8_512x512_20k_voc12aug_20200618_070026.log.json)     |
+| DANet  | R-101-D8 | 512x512   |   20000 | 9.9      | 13.76          | V100   | 76.02 |         77.23 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_20k_voc12aug/danet_r101-d8_512x512_20k_voc12aug_20200618_070026-d48d23b2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_20k_voc12aug/danet_r101-d8_512x512_20k_voc12aug_20200618_070026.log.json) |
+| DANet  | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 76.37 |         77.29 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_40k_voc12aug/danet_r50-d8_512x512_40k_voc12aug_20200613_235526-426e3a64.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_40k_voc12aug/danet_r50-d8_512x512_40k_voc12aug_20200613_235526.log.json)     |
+| DANet  | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 76.51 |         77.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_40k_voc12aug/danet_r101-d8_512x512_40k_voc12aug_20200613_223031-788e232a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_40k_voc12aug/danet_r101-d8_512x512_40k_voc12aug_20200613_223031.log.json) |
+
+## Citation
+
+```bibtex
+@article{fu2018dual,
+  title={Dual Attention Network for Scene Segmentation},
+  author={Jun Fu, Jing Liu, Haijie Tian, Yong Li, Yongjun Bao, Zhiwei Fang,and Hanqing Lu},
+  booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
+  year={2019}
+}
+```
diff --git a/configs/danet/danet.yml b/configs/danet/danet.yml
deleted file mode 100644
index 2a6658e428..0000000000
--- a/configs/danet/danet.yml
+++ /dev/null
@@ -1,301 +0,0 @@
-Collections:
-- Name: DANet
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-    - Pascal VOC 2012 + Aug
-  Paper:
-    URL: https://arxiv.org/abs/1809.02983
-    Title: Dual Attention Network for Scene Segmentation
-  README: configs/danet/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/junfu1115/DANet/
-Models:
-- Name: danet_r50-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: DANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 375.94
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 7.4
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.74
-  Config: configs/danet/danet_r50-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_40k_cityscapes/danet_r50-d8_512x1024_40k_cityscapes_20200605_191324-c0dbfa5f.pth
-- Name: danet_r101-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: DANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 502.51
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 10.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.52
-  Config: configs/danet/danet_r101-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_40k_cityscapes/danet_r101-d8_512x1024_40k_cityscapes_20200605_200831-c57a7157.pth
-- Name: danet_r50-d8_4xb2-40k_cityscapes-769x769
-  In Collection: DANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 641.03
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 8.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.88
-      mIoU(ms+flip): 80.62
-  Config: configs/danet/danet_r50-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_40k_cityscapes/danet_r50-d8_769x769_40k_cityscapes_20200530_025703-76681c60.pth
-- Name: danet_r101-d8_4xb2-40k_cityscapes-769x769
-  In Collection: DANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 934.58
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 12.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.88
-      mIoU(ms+flip): 81.47
-  Config: configs/danet/danet_r101-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_40k_cityscapes/danet_r101-d8_769x769_40k_cityscapes_20200530_025717-dcb7fd4e.pth
-- Name: danet_r50-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: DANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.34
-  Config: configs/danet/danet_r50-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_80k_cityscapes/danet_r50-d8_512x1024_80k_cityscapes_20200607_133029-2bfa2293.pth
-- Name: danet_r101-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: DANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.41
-  Config: configs/danet/danet_r101-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_80k_cityscapes/danet_r101-d8_512x1024_80k_cityscapes_20200607_132918-955e6350.pth
-- Name: danet_r50-d8_4xb2-80k_cityscapes-769x769
-  In Collection: DANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.27
-      mIoU(ms+flip): 80.96
-  Config: configs/danet/danet_r50-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_80k_cityscapes/danet_r50-d8_769x769_80k_cityscapes_20200607_132954-495689b4.pth
-- Name: danet_r101-d8_4xb2-80k_cityscapes-769x769
-  In Collection: DANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.47
-      mIoU(ms+flip): 82.02
-  Config: configs/danet/danet_r101-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_80k_cityscapes/danet_r101-d8_769x769_80k_cityscapes_20200607_132918-f3a929e7.pth
-- Name: danet_r50-d8_4xb4-80k_ade20k-512x512
-  In Collection: DANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 47.17
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 11.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 41.66
-      mIoU(ms+flip): 42.9
-  Config: configs/danet/danet_r50-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_80k_ade20k/danet_r50-d8_512x512_80k_ade20k_20200615_015125-edb18e08.pth
-- Name: danet_r101-d8_4xb4-80k_ade20k-512x512
-  In Collection: DANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 70.52
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 15.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.64
-      mIoU(ms+flip): 45.19
-  Config: configs/danet/danet_r101-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_80k_ade20k/danet_r101-d8_512x512_80k_ade20k_20200615_015126-d0357c73.pth
-- Name: danet_r50-d8_4xb4-160k_ade20k-512x512
-  In Collection: DANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.45
-      mIoU(ms+flip): 43.25
-  Config: configs/danet/danet_r50-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_160k_ade20k/danet_r50-d8_512x512_160k_ade20k_20200616_082340-9cb35dcd.pth
-- Name: danet_r101-d8_4xb4-160k_ade20k-512x512
-  In Collection: DANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 44.17
-      mIoU(ms+flip): 45.02
-  Config: configs/danet/danet_r101-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_160k_ade20k/danet_r101-d8_512x512_160k_ade20k_20200616_082348-23bf12f9.pth
-- Name: danet_r50-d8_4xb4-20k_voc12aug-512x512
-  In Collection: DANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 47.76
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 74.45
-      mIoU(ms+flip): 75.69
-  Config: configs/danet/danet_r50-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_20k_voc12aug/danet_r50-d8_512x512_20k_voc12aug_20200618_070026-9e9e3ab3.pth
-- Name: danet_r101-d8_4xb4-20k_voc12aug-512x512
-  In Collection: DANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 72.67
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 76.02
-      mIoU(ms+flip): 77.23
-  Config: configs/danet/danet_r101-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_20k_voc12aug/danet_r101-d8_512x512_20k_voc12aug_20200618_070026-d48d23b2.pth
-- Name: danet_r50-d8_4xb4-40k_voc12aug-512x512
-  In Collection: DANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 76.37
-      mIoU(ms+flip): 77.29
-  Config: configs/danet/danet_r50-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_40k_voc12aug/danet_r50-d8_512x512_40k_voc12aug_20200613_235526-426e3a64.pth
-- Name: danet_r101-d8_4xb4-40k_voc12aug-512x512
-  In Collection: DANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 76.51
-      mIoU(ms+flip): 77.32
-  Config: configs/danet/danet_r101-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_40k_voc12aug/danet_r101-d8_512x512_40k_voc12aug_20200613_223031-788e232a.pth
diff --git a/configs/danet/metafile.yaml b/configs/danet/metafile.yaml
new file mode 100644
index 0000000000..daff925baf
--- /dev/null
+++ b/configs/danet/metafile.yaml
@@ -0,0 +1,387 @@
+Collections:
+- Name: DANet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - ADE20K
+    - Pascal VOC 2012 + Aug
+  Paper:
+    Title: Dual Attention Network for Scene Segmentation
+    URL: https://arxiv.org/abs/1809.02983
+  README: configs/danet/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: danet_r50-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: DANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.74
+  Config: configs/danet/danet_r50-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.4
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_40k_cityscapes/danet_r50-d8_512x1024_40k_cityscapes_20200605_191324-c0dbfa5f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_40k_cityscapes/danet_r50-d8_512x1024_40k_cityscapes_20200605_191324.log.json
+  Paper:
+    Title: Dual Attention Network for Scene Segmentation
+    URL: https://arxiv.org/abs/1809.02983
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
+  Framework: PyTorch
+- Name: danet_r101-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: DANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.52
+  Config: configs/danet/danet_r101-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_40k_cityscapes/danet_r101-d8_512x1024_40k_cityscapes_20200605_200831-c57a7157.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_40k_cityscapes/danet_r101-d8_512x1024_40k_cityscapes_20200605_200831.log.json
+  Paper:
+    Title: Dual Attention Network for Scene Segmentation
+    URL: https://arxiv.org/abs/1809.02983
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
+  Framework: PyTorch
+- Name: danet_r50-d8_4xb2-40k_cityscapes-769x769
+  In Collection: DANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.88
+      mIoU(ms+flip): 80.62
+  Config: configs/danet/danet_r50-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_40k_cityscapes/danet_r50-d8_769x769_40k_cityscapes_20200530_025703-76681c60.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_40k_cityscapes/danet_r50-d8_769x769_40k_cityscapes_20200530_025703.log.json
+  Paper:
+    Title: Dual Attention Network for Scene Segmentation
+    URL: https://arxiv.org/abs/1809.02983
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
+  Framework: PyTorch
+- Name: danet_r101-d8_4xb2-40k_cityscapes-769x769
+  In Collection: DANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.88
+      mIoU(ms+flip): 81.47
+  Config: configs/danet/danet_r101-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 12.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_40k_cityscapes/danet_r101-d8_769x769_40k_cityscapes_20200530_025717-dcb7fd4e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_40k_cityscapes/danet_r101-d8_769x769_40k_cityscapes_20200530_025717.log.json
+  Paper:
+    Title: Dual Attention Network for Scene Segmentation
+    URL: https://arxiv.org/abs/1809.02983
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
+  Framework: PyTorch
+- Name: danet_r50-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: DANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.34
+  Config: configs/danet/danet_r50-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DANet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_80k_cityscapes/danet_r50-d8_512x1024_80k_cityscapes_20200607_133029-2bfa2293.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_80k_cityscapes/danet_r50-d8_512x1024_80k_cityscapes_20200607_133029.log.json
+  Paper:
+    Title: Dual Attention Network for Scene Segmentation
+    URL: https://arxiv.org/abs/1809.02983
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
+  Framework: PyTorch
+- Name: danet_r101-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: DANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.41
+  Config: configs/danet/danet_r101-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DANet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_80k_cityscapes/danet_r101-d8_512x1024_80k_cityscapes_20200607_132918-955e6350.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_80k_cityscapes/danet_r101-d8_512x1024_80k_cityscapes_20200607_132918.log.json
+  Paper:
+    Title: Dual Attention Network for Scene Segmentation
+    URL: https://arxiv.org/abs/1809.02983
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
+  Framework: PyTorch
+- Name: danet_r50-d8_4xb2-80k_cityscapes-769x769
+  In Collection: DANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.27
+      mIoU(ms+flip): 80.96
+  Config: configs/danet/danet_r50-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DANet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_80k_cityscapes/danet_r50-d8_769x769_80k_cityscapes_20200607_132954-495689b4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_80k_cityscapes/danet_r50-d8_769x769_80k_cityscapes_20200607_132954.log.json
+  Paper:
+    Title: Dual Attention Network for Scene Segmentation
+    URL: https://arxiv.org/abs/1809.02983
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
+  Framework: PyTorch
+- Name: danet_r101-d8_4xb2-80k_cityscapes-769x769
+  In Collection: DANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.47
+      mIoU(ms+flip): 82.02
+  Config: configs/danet/danet_r101-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DANet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_80k_cityscapes/danet_r101-d8_769x769_80k_cityscapes_20200607_132918-f3a929e7.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_80k_cityscapes/danet_r101-d8_769x769_80k_cityscapes_20200607_132918.log.json
+  Paper:
+    Title: Dual Attention Network for Scene Segmentation
+    URL: https://arxiv.org/abs/1809.02983
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
+  Framework: PyTorch
+- Name: danet_r50-d8_4xb4-80k_ade20k-512x512
+  In Collection: DANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 41.66
+      mIoU(ms+flip): 42.9
+  Config: configs/danet/danet_r50-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 11.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_80k_ade20k/danet_r50-d8_512x512_80k_ade20k_20200615_015125-edb18e08.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_80k_ade20k/danet_r50-d8_512x512_80k_ade20k_20200615_015125.log.json
+  Paper:
+    Title: Dual Attention Network for Scene Segmentation
+    URL: https://arxiv.org/abs/1809.02983
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
+  Framework: PyTorch
+- Name: danet_r101-d8_4xb4-80k_ade20k-512x512
+  In Collection: DANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.64
+      mIoU(ms+flip): 45.19
+  Config: configs/danet/danet_r101-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 15.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_80k_ade20k/danet_r101-d8_512x512_80k_ade20k_20200615_015126-d0357c73.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_80k_ade20k/danet_r101-d8_512x512_80k_ade20k_20200615_015126.log.json
+  Paper:
+    Title: Dual Attention Network for Scene Segmentation
+    URL: https://arxiv.org/abs/1809.02983
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
+  Framework: PyTorch
+- Name: danet_r50-d8_4xb4-160k_ade20k-512x512
+  In Collection: DANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.45
+      mIoU(ms+flip): 43.25
+  Config: configs/danet/danet_r50-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DANet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_160k_ade20k/danet_r50-d8_512x512_160k_ade20k_20200616_082340-9cb35dcd.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_160k_ade20k/danet_r50-d8_512x512_160k_ade20k_20200616_082340.log.json
+  Paper:
+    Title: Dual Attention Network for Scene Segmentation
+    URL: https://arxiv.org/abs/1809.02983
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
+  Framework: PyTorch
+- Name: danet_r101-d8_4xb4-160k_ade20k-512x512
+  In Collection: DANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 44.17
+      mIoU(ms+flip): 45.02
+  Config: configs/danet/danet_r101-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DANet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_160k_ade20k/danet_r101-d8_512x512_160k_ade20k_20200616_082348-23bf12f9.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_160k_ade20k/danet_r101-d8_512x512_160k_ade20k_20200616_082348.log.json
+  Paper:
+    Title: Dual Attention Network for Scene Segmentation
+    URL: https://arxiv.org/abs/1809.02983
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
+  Framework: PyTorch
+- Name: danet_r50-d8_4xb4-20k_voc12aug-512x512
+  In Collection: DANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 74.45
+      mIoU(ms+flip): 75.69
+  Config: configs/danet/danet_r50-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_20k_voc12aug/danet_r50-d8_512x512_20k_voc12aug_20200618_070026-9e9e3ab3.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_20k_voc12aug/danet_r50-d8_512x512_20k_voc12aug_20200618_070026.log.json
+  Paper:
+    Title: Dual Attention Network for Scene Segmentation
+    URL: https://arxiv.org/abs/1809.02983
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
+  Framework: PyTorch
+- Name: danet_r101-d8_4xb4-20k_voc12aug-512x512
+  In Collection: DANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 76.02
+      mIoU(ms+flip): 77.23
+  Config: configs/danet/danet_r101-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_20k_voc12aug/danet_r101-d8_512x512_20k_voc12aug_20200618_070026-d48d23b2.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_20k_voc12aug/danet_r101-d8_512x512_20k_voc12aug_20200618_070026.log.json
+  Paper:
+    Title: Dual Attention Network for Scene Segmentation
+    URL: https://arxiv.org/abs/1809.02983
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
+  Framework: PyTorch
+- Name: danet_r50-d8_4xb4-40k_voc12aug-512x512
+  In Collection: DANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 76.37
+      mIoU(ms+flip): 77.29
+  Config: configs/danet/danet_r50-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DANet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_40k_voc12aug/danet_r50-d8_512x512_40k_voc12aug_20200613_235526-426e3a64.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_40k_voc12aug/danet_r50-d8_512x512_40k_voc12aug_20200613_235526.log.json
+  Paper:
+    Title: Dual Attention Network for Scene Segmentation
+    URL: https://arxiv.org/abs/1809.02983
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
+  Framework: PyTorch
+- Name: danet_r101-d8_4xb4-40k_voc12aug-512x512
+  In Collection: DANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 76.51
+      mIoU(ms+flip): 77.32
+  Config: configs/danet/danet_r101-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DANet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_40k_voc12aug/danet_r101-d8_512x512_40k_voc12aug_20200613_223031-788e232a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_40k_voc12aug/danet_r101-d8_512x512_40k_voc12aug_20200613_223031.log.json
+  Paper:
+    Title: Dual Attention Network for Scene Segmentation
+    URL: https://arxiv.org/abs/1809.02983
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
+  Framework: PyTorch
diff --git a/configs/deeplabv3/README.md b/configs/deeplabv3/README.md
index b37836ab21..836db6a9a5 100644
--- a/configs/deeplabv3/README.md
+++ b/configs/deeplabv3/README.md
@@ -1,6 +1,6 @@
 # DeepLabV3
 
-[Rethinking atrous convolution for semantic image segmentation](https://arxiv.org/abs/1706.05587)
+> [Rethinking atrous convolution for semantic image segmentation](https://arxiv.org/abs/1706.05587)
 
 ## Introduction
 
@@ -18,105 +18,101 @@ In this work, we revisit atrous convolution, a powerful tool to explicitly adjus
 
 <!-- [IMAGE] -->
 
-<div align=center>
-<img src="https://user-images.githubusercontent.com/24582831/142900575-f30a7755-09aa-406a-bf78-45893a61ee9a.png" width="80%"/>
-</div>
-
 <div align=center >
 <img alt="DEEPLABv3_ResNet-D8" src="https://user-images.githubusercontent.com/61172629/209305311-87ff9e36-b7cd-46d7-8b4c-9e26e10c27d0.jpg"/>
 DEEPLABv3_ResNet-D8 model structure
 </div>
 
-## Citation
-
-```bibtext
-@article{chen2017rethinking,
-  title={Rethinking atrous convolution for semantic image segmentation},
-  author={Chen, Liang-Chieh and Papandreou, George and Schroff, Florian and Adam, Hartwig},
-  journal={arXiv preprint arXiv:1706.05587},
-  year={2017}
-}
-```
-
 ## Results and models
 
 ### Cityscapes
 
-| Method           | Backbone        | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                                                               |
-| ---------------- | --------------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| DeepLabV3        | R-50-D8         | 512x1024  |   40000 | 6.1      | 2.57           | 79.09 |         80.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes/deeplabv3_r50-d8_512x1024_40k_cityscapes_20200605_022449-acadc2f8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes/deeplabv3_r50-d8_512x1024_40k_cityscapes_20200605_022449.log.json)                                 |
-| DeepLabV3        | R-101-D8        | 512x1024  |   40000 | 9.6      | 1.92           | 77.12 |         79.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb2-40k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_40k_cityscapes/deeplabv3_r101-d8_512x1024_40k_cityscapes_20200605_012241-7fd3f799.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_40k_cityscapes/deeplabv3_r101-d8_512x1024_40k_cityscapes_20200605_012241.log.json)                             |
-| DeepLabV3        | R-50-D8         | 769x769   |   40000 | 6.9      | 1.11           | 78.58 |         79.89 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_cityscapes-769x769.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_40k_cityscapes/deeplabv3_r50-d8_769x769_40k_cityscapes_20200606_113723-7eda553c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_40k_cityscapes/deeplabv3_r50-d8_769x769_40k_cityscapes_20200606_113723.log.json)                                     |
-| DeepLabV3        | R-101-D8        | 769x769   |   40000 | 10.9     | 0.83           | 79.27 |         80.11 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb2-40k_cityscapes-769x769.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_40k_cityscapes/deeplabv3_r101-d8_769x769_40k_cityscapes_20200606_113809-c64f889f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_40k_cityscapes/deeplabv3_r101-d8_769x769_40k_cityscapes_20200606_113809.log.json)                                 |
-| DeepLabV3        | R-18-D8         | 512x1024  |   80000 | 1.7      | 13.78          | 76.70 |         78.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r18-d8_4xb2-80k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_512x1024_80k_cityscapes/deeplabv3_r18-d8_512x1024_80k_cityscapes_20201225_021506-23dffbe2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_512x1024_80k_cityscapes/deeplabv3_r18-d8_512x1024_80k_cityscapes-20201225_021506.log.json)                                 |
-| DeepLabV3        | R-50-D8         | 512x1024  |   80000 | -        | -              | 79.32 |         80.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb2-80k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_80k_cityscapes/deeplabv3_r50-d8_512x1024_80k_cityscapes_20200606_113404-b92cfdd4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_80k_cityscapes/deeplabv3_r50-d8_512x1024_80k_cityscapes_20200606_113404.log.json)                                 |
-| DeepLabV3        | R-101-D8        | 512x1024  |   80000 | -        | -              | 80.20 |         81.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb2-80k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_80k_cityscapes/deeplabv3_r101-d8_512x1024_80k_cityscapes_20200606_113503-9e428899.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_80k_cityscapes/deeplabv3_r101-d8_512x1024_80k_cityscapes_20200606_113503.log.json)                             |
-| DeepLabV3 (FP16) | R-101-D8        | 512x1024  |   80000 | 5.75     | 3.86           | 80.48 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920-774d9cec.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920.log.json)         |
-| DeepLabV3        | R-18-D8         | 769x769   |   80000 | 1.9      | 5.55           | 76.60 |         78.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r18-d8_4xb2-80k_cityscapes-769x769.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_769x769_80k_cityscapes/deeplabv3_r18-d8_769x769_80k_cityscapes_20201225_021506-6452126a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_769x769_80k_cityscapes/deeplabv3_r18-d8_769x769_80k_cityscapes-20201225_021506.log.json)                                     |
-| DeepLabV3        | R-50-D8         | 769x769   |   80000 | -        | -              | 79.89 |         81.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb2-80k_cityscapes-769x769.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_80k_cityscapes/deeplabv3_r50-d8_769x769_80k_cityscapes_20200606_221338-788d6228.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_80k_cityscapes/deeplabv3_r50-d8_769x769_80k_cityscapes_20200606_221338.log.json)                                     |
-| DeepLabV3        | R-101-D8        | 769x769   |   80000 | -        | -              | 79.67 |         80.81 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb2-80k_cityscapes-769x769.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_80k_cityscapes/deeplabv3_r101-d8_769x769_80k_cityscapes_20200607_013353-60e95418.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_80k_cityscapes/deeplabv3_r101-d8_769x769_80k_cityscapes_20200607_013353.log.json)                                 |
-| DeepLabV3        | R-101-D16-MG124 | 512x1024  |   40000 | 4.7      | - 6.96         | 76.71 |         78.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d16-mg124_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes_20200908_005644-67b0c992.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes-20200908_005644.log.json) |
-| DeepLabV3        | R-101-D16-MG124 | 512x1024  |   80000 | -        | -              | 78.36 |         79.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d16-mg124_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes_20200908_005644-57bb8425.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes-20200908_005644.log.json) |
-| DeepLabV3        | R-18b-D8        | 512x1024  |   80000 | 1.6      | 13.93          | 76.26 |         77.88 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r18b-d8_4xb2-80k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_512x1024_80k_cityscapes/deeplabv3_r18b-d8_512x1024_80k_cityscapes_20201225_094144-46040cef.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_512x1024_80k_cityscapes/deeplabv3_r18b-d8_512x1024_80k_cityscapes-20201225_094144.log.json)                             |
-| DeepLabV3        | R-50b-D8        | 512x1024  |   80000 | 6.0      | 2.74           | 79.63 |         80.98 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50b-d8_4xb2-80k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_512x1024_80k_cityscapes/deeplabv3_r50b-d8_512x1024_80k_cityscapes_20201225_155148-ec368954.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_512x1024_80k_cityscapes/deeplabv3_r50b-d8_512x1024_80k_cityscapes-20201225_155148.log.json)                             |
-| DeepLabV3        | R-101b-D8       | 512x1024  |   80000 | 9.5      | 1.81           | 80.01 |         81.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101b-d8_4xb2-80k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_512x1024_80k_cityscapes/deeplabv3_r101b-d8_512x1024_80k_cityscapes_20201226_171821-8fd49503.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_512x1024_80k_cityscapes/deeplabv3_r101b-d8_512x1024_80k_cityscapes-20201226_171821.log.json)                         |
-| DeepLabV3        | R-18b-D8        | 769x769   |   80000 | 1.8      | 5.79           | 75.63 |         77.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r18b-d8_4xb2-80k_cityscapes-769x769.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_769x769_80k_cityscapes/deeplabv3_r18b-d8_769x769_80k_cityscapes_20201225_094144-fdc985d9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_769x769_80k_cityscapes/deeplabv3_r18b-d8_769x769_80k_cityscapes-20201225_094144.log.json)                                 |
-| DeepLabV3        | R-50b-D8        | 769x769   |   80000 | 6.8      | 1.16           | 78.80 |         80.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50b-d8_4xb2-80k_cityscapes-769x769.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_769x769_80k_cityscapes/deeplabv3_r50b-d8_769x769_80k_cityscapes_20201225_155404-87fb0cf4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_769x769_80k_cityscapes/deeplabv3_r50b-d8_769x769_80k_cityscapes-20201225_155404.log.json)                                 |
-| DeepLabV3        | R-101b-D8       | 769x769   |   80000 | 10.7     | 0.82           | 79.41 |         80.73 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101b-d8_4xb2-80k_cityscapes-769x769.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_769x769_80k_cityscapes/deeplabv3_r101b-d8_769x769_80k_cityscapes_20201226_190843-9142ee57.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_769x769_80k_cityscapes/deeplabv3_r101b-d8_769x769_80k_cityscapes-20201226_190843.log.json)                             |
+| Method           | Backbone        | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                                                               |
+| ---------------- | --------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| DeepLabV3        | R-50-D8         | 512x1024  |   40000 | 6.1      | 2.57           | V100   | 79.09 |         80.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes/deeplabv3_r50-d8_512x1024_40k_cityscapes_20200605_022449-acadc2f8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes/deeplabv3_r50-d8_512x1024_40k_cityscapes_20200605_022449.log.json)                                 |
+| DeepLabV3        | R-101-D8        | 512x1024  |   40000 | 9.6      | 1.92           | V100   | 77.12 |         79.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb2-40k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_40k_cityscapes/deeplabv3_r101-d8_512x1024_40k_cityscapes_20200605_012241-7fd3f799.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_40k_cityscapes/deeplabv3_r101-d8_512x1024_40k_cityscapes_20200605_012241.log.json)                             |
+| DeepLabV3        | R-50-D8         | 769x769   |   40000 | 6.9      | 1.11           | V100   | 78.58 |         79.89 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_cityscapes-769x769.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_40k_cityscapes/deeplabv3_r50-d8_769x769_40k_cityscapes_20200606_113723-7eda553c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_40k_cityscapes/deeplabv3_r50-d8_769x769_40k_cityscapes_20200606_113723.log.json)                                     |
+| DeepLabV3        | R-101-D8        | 769x769   |   40000 | 10.9     | 0.83           | V100   | 79.27 |         80.11 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb2-40k_cityscapes-769x769.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_40k_cityscapes/deeplabv3_r101-d8_769x769_40k_cityscapes_20200606_113809-c64f889f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_40k_cityscapes/deeplabv3_r101-d8_769x769_40k_cityscapes_20200606_113809.log.json)                                 |
+| DeepLabV3        | R-18-D8         | 512x1024  |   80000 | 1.7      | 13.78          | V100   | 76.70 |         78.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r18-d8_4xb2-80k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_512x1024_80k_cityscapes/deeplabv3_r18-d8_512x1024_80k_cityscapes_20201225_021506-23dffbe2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_512x1024_80k_cityscapes/deeplabv3_r18-d8_512x1024_80k_cityscapes-20201225_021506.log.json)                                 |
+| DeepLabV3        | R-50-D8         | 512x1024  |   80000 | -        | -              | V100   | 79.32 |         80.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb2-80k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_80k_cityscapes/deeplabv3_r50-d8_512x1024_80k_cityscapes_20200606_113404-b92cfdd4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_80k_cityscapes/deeplabv3_r50-d8_512x1024_80k_cityscapes_20200606_113404.log.json)                                 |
+| DeepLabV3        | R-101-D8        | 512x1024  |   80000 | -        | -              | V100   | 80.20 |         81.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb2-80k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_80k_cityscapes/deeplabv3_r101-d8_512x1024_80k_cityscapes_20200606_113503-9e428899.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_80k_cityscapes/deeplabv3_r101-d8_512x1024_80k_cityscapes_20200606_113503.log.json)                             |
+| DeepLabV3 (FP16) | R-101-D8        | 512x1024  |   80000 | 5.75     | 3.86           | V100   | 80.48 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920-774d9cec.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920.log.json)         |
+| DeepLabV3        | R-18-D8         | 769x769   |   80000 | 1.9      | 5.55           | V100   | 76.60 |         78.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r18-d8_4xb2-80k_cityscapes-769x769.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_769x769_80k_cityscapes/deeplabv3_r18-d8_769x769_80k_cityscapes_20201225_021506-6452126a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_769x769_80k_cityscapes/deeplabv3_r18-d8_769x769_80k_cityscapes-20201225_021506.log.json)                                     |
+| DeepLabV3        | R-50-D8         | 769x769   |   80000 | -        | -              | V100   | 79.89 |         81.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb2-80k_cityscapes-769x769.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_80k_cityscapes/deeplabv3_r50-d8_769x769_80k_cityscapes_20200606_221338-788d6228.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_80k_cityscapes/deeplabv3_r50-d8_769x769_80k_cityscapes_20200606_221338.log.json)                                     |
+| DeepLabV3        | R-101-D8        | 769x769   |   80000 | -        | -              | V100   | 79.67 |         80.81 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb2-80k_cityscapes-769x769.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_80k_cityscapes/deeplabv3_r101-d8_769x769_80k_cityscapes_20200607_013353-60e95418.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_80k_cityscapes/deeplabv3_r101-d8_769x769_80k_cityscapes_20200607_013353.log.json)                                 |
+| DeepLabV3        | R-101-D16-MG124 | 512x1024  |   40000 | 4.7      | 6.96           | V100   | 76.71 |         78.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d16-mg124_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes_20200908_005644-67b0c992.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes-20200908_005644.log.json) |
+| DeepLabV3        | R-101-D16-MG124 | 512x1024  |   80000 | -        | -              | V100   | 78.36 |         79.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d16-mg124_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes_20200908_005644-57bb8425.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes-20200908_005644.log.json) |
+| DeepLabV3        | R-18b-D8        | 512x1024  |   80000 | 1.6      | 13.93          | V100   | 76.26 |         77.88 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r18b-d8_4xb2-80k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_512x1024_80k_cityscapes/deeplabv3_r18b-d8_512x1024_80k_cityscapes_20201225_094144-46040cef.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_512x1024_80k_cityscapes/deeplabv3_r18b-d8_512x1024_80k_cityscapes-20201225_094144.log.json)                             |
+| DeepLabV3        | R-50b-D8        | 512x1024  |   80000 | 6.0      | 2.74           | V100   | 79.63 |         80.98 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50b-d8_4xb2-80k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_512x1024_80k_cityscapes/deeplabv3_r50b-d8_512x1024_80k_cityscapes_20201225_155148-ec368954.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_512x1024_80k_cityscapes/deeplabv3_r50b-d8_512x1024_80k_cityscapes-20201225_155148.log.json)                             |
+| DeepLabV3        | R-101b-D8       | 512x1024  |   80000 | 9.5      | 1.81           | V100   | 80.01 |         81.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101b-d8_4xb2-80k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_512x1024_80k_cityscapes/deeplabv3_r101b-d8_512x1024_80k_cityscapes_20201226_171821-8fd49503.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_512x1024_80k_cityscapes/deeplabv3_r101b-d8_512x1024_80k_cityscapes-20201226_171821.log.json)                         |
+| DeepLabV3        | R-18b-D8        | 769x769   |   80000 | 1.8      | 5.79           | V100   | 75.63 |         77.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r18b-d8_4xb2-80k_cityscapes-769x769.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_769x769_80k_cityscapes/deeplabv3_r18b-d8_769x769_80k_cityscapes_20201225_094144-fdc985d9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_769x769_80k_cityscapes/deeplabv3_r18b-d8_769x769_80k_cityscapes-20201225_094144.log.json)                                 |
+| DeepLabV3        | R-50b-D8        | 769x769   |   80000 | 6.8      | 1.16           | V100   | 78.80 |         80.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50b-d8_4xb2-80k_cityscapes-769x769.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_769x769_80k_cityscapes/deeplabv3_r50b-d8_769x769_80k_cityscapes_20201225_155404-87fb0cf4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_769x769_80k_cityscapes/deeplabv3_r50b-d8_769x769_80k_cityscapes-20201225_155404.log.json)                                 |
+| DeepLabV3        | R-101b-D8       | 769x769   |   80000 | 10.7     | 0.82           | V100   | 79.41 |         80.73 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101b-d8_4xb2-80k_cityscapes-769x769.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_769x769_80k_cityscapes/deeplabv3_r101b-d8_769x769_80k_cityscapes_20201226_190843-9142ee57.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_769x769_80k_cityscapes/deeplabv3_r101b-d8_769x769_80k_cityscapes-20201226_190843.log.json)                             |
 
 ### ADE20K
 
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                              | download                                                                                                                                                                                                                                                                                                                                                   |
-| --------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3 | R-50-D8  | 512x512   |   80000 | 8.9      | 14.76          | 42.42 |         43.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_80k_ade20k/deeplabv3_r50-d8_512x512_80k_ade20k_20200614_185028-0bb3f844.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_80k_ade20k/deeplabv3_r50-d8_512x512_80k_ade20k_20200614_185028.log.json)         |
-| DeepLabV3 | R-101-D8 | 512x512   |   80000 | 12.4     | 10.14          | 44.08 |         45.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_80k_ade20k/deeplabv3_r101-d8_512x512_80k_ade20k_20200615_021256-d89c7fa4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_80k_ade20k/deeplabv3_r101-d8_512x512_80k_ade20k_20200615_021256.log.json)     |
-| DeepLabV3 | R-50-D8  | 512x512   |  160000 | -        | -              | 42.66 |         44.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_160k_ade20k/deeplabv3_r50-d8_512x512_160k_ade20k_20200615_123227-5d0ee427.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_160k_ade20k/deeplabv3_r50-d8_512x512_160k_ade20k_20200615_123227.log.json)     |
-| DeepLabV3 | R-101-D8 | 512x512   |  160000 | -        | -              | 45.00 |         46.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_160k_ade20k/deeplabv3_r101-d8_512x512_160k_ade20k_20200615_105816-b1f72b3b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_160k_ade20k/deeplabv3_r101-d8_512x512_160k_ade20k_20200615_105816.log.json) |
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                              | download                                                                                                                                                                                                                                                                                                                                                   |
+| --------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3 | R-50-D8  | 512x512   |   80000 | 8.9      | 14.76          | V100   | 42.42 |         43.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_80k_ade20k/deeplabv3_r50-d8_512x512_80k_ade20k_20200614_185028-0bb3f844.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_80k_ade20k/deeplabv3_r50-d8_512x512_80k_ade20k_20200614_185028.log.json)         |
+| DeepLabV3 | R-101-D8 | 512x512   |   80000 | 12.4     | 10.14          | V100   | 44.08 |         45.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_80k_ade20k/deeplabv3_r101-d8_512x512_80k_ade20k_20200615_021256-d89c7fa4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_80k_ade20k/deeplabv3_r101-d8_512x512_80k_ade20k_20200615_021256.log.json)     |
+| DeepLabV3 | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 42.66 |         44.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_160k_ade20k/deeplabv3_r50-d8_512x512_160k_ade20k_20200615_123227-5d0ee427.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_160k_ade20k/deeplabv3_r50-d8_512x512_160k_ade20k_20200615_123227.log.json)     |
+| DeepLabV3 | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 45.00 |         46.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_160k_ade20k/deeplabv3_r101-d8_512x512_160k_ade20k_20200615_105816-b1f72b3b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_160k_ade20k/deeplabv3_r101-d8_512x512_160k_ade20k_20200615_105816.log.json) |
 
 ### Pascal VOC 2012 + Aug
 
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                               | download                                                                                                                                                                                                                                                                                                                                                       |
-| --------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3 | R-50-D8  | 512x512   |   20000 | 6.1      | 13.88          | 76.17 |         77.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_20k_voc12aug/deeplabv3_r50-d8_512x512_20k_voc12aug_20200617_010906-596905ef.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_20k_voc12aug/deeplabv3_r50-d8_512x512_20k_voc12aug_20200617_010906.log.json)     |
-| DeepLabV3 | R-101-D8 | 512x512   |   20000 | 9.6      | 9.81           | 78.70 |         79.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_20k_voc12aug/deeplabv3_r101-d8_512x512_20k_voc12aug_20200617_010932-8d13832f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_20k_voc12aug/deeplabv3_r101-d8_512x512_20k_voc12aug_20200617_010932.log.json) |
-| DeepLabV3 | R-50-D8  | 512x512   |   40000 | -        | -              | 77.68 |         78.78 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_40k_voc12aug/deeplabv3_r50-d8_512x512_40k_voc12aug_20200613_161546-2ae96e7e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_40k_voc12aug/deeplabv3_r50-d8_512x512_40k_voc12aug_20200613_161546.log.json)     |
-| DeepLabV3 | R-101-D8 | 512x512   |   40000 | -        | -              | 77.92 |         79.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_40k_voc12aug/deeplabv3_r101-d8_512x512_40k_voc12aug_20200613_161432-0017d784.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_40k_voc12aug/deeplabv3_r101-d8_512x512_40k_voc12aug_20200613_161432.log.json) |
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                               | download                                                                                                                                                                                                                                                                                                                                                       |
+| --------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3 | R-50-D8  | 512x512   |   20000 | 6.1      | 13.88          | V100   | 76.17 |         77.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_20k_voc12aug/deeplabv3_r50-d8_512x512_20k_voc12aug_20200617_010906-596905ef.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_20k_voc12aug/deeplabv3_r50-d8_512x512_20k_voc12aug_20200617_010906.log.json)     |
+| DeepLabV3 | R-101-D8 | 512x512   |   20000 | 9.6      | 9.81           | V100   | 78.70 |         79.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_20k_voc12aug/deeplabv3_r101-d8_512x512_20k_voc12aug_20200617_010932-8d13832f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_20k_voc12aug/deeplabv3_r101-d8_512x512_20k_voc12aug_20200617_010932.log.json) |
+| DeepLabV3 | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 77.68 |         78.78 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_40k_voc12aug/deeplabv3_r50-d8_512x512_40k_voc12aug_20200613_161546-2ae96e7e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_40k_voc12aug/deeplabv3_r50-d8_512x512_40k_voc12aug_20200613_161546.log.json)     |
+| DeepLabV3 | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 77.92 |         79.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_40k_voc12aug/deeplabv3_r101-d8_512x512_40k_voc12aug_20200613_161432-0017d784.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_40k_voc12aug/deeplabv3_r101-d8_512x512_40k_voc12aug_20200613_161432.log.json) |
 
 ### Pascal Context
 
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                                               |
-| --------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3 | R-101-D8 | 480x480   |   40000 | 9.2      | 7.09           | 46.55 |         47.81 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context/deeplabv3_r101-d8_480x480_40k_pascal_context_20200911_204118-1aa27336.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context/deeplabv3_r101-d8_480x480_40k_pascal_context-20200911_204118.log.json) |
-| DeepLabV3 | R-101-D8 | 480x480   |   80000 | -        | -              | 46.42 |         47.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context/deeplabv3_r101-d8_480x480_80k_pascal_context_20200911_170155-2a21fff3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context/deeplabv3_r101-d8_480x480_80k_pascal_context-20200911_170155.log.json) |
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                                               |
+| --------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3 | R-101-D8 | 480x480   |   40000 | 9.2      | 7.09           | V100   | 46.55 |         47.81 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context/deeplabv3_r101-d8_480x480_40k_pascal_context_20200911_204118-1aa27336.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context/deeplabv3_r101-d8_480x480_40k_pascal_context-20200911_204118.log.json) |
+| DeepLabV3 | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 46.42 |         47.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context/deeplabv3_r101-d8_480x480_80k_pascal_context_20200911_170155-2a21fff3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context/deeplabv3_r101-d8_480x480_80k_pascal_context-20200911_170155.log.json) |
 
 ### Pascal Context 59
 
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                                                           |
-| --------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3 | R-101-D8 | 480x480   |   40000 | -        | -              | 52.61 |         54.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context_59/deeplabv3_r101-d8_480x480_40k_pascal_context_59_20210416_110332-cb08ea46.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context_59/deeplabv3_r101-d8_480x480_40k_pascal_context_59-20210416_110332.log.json) |
-| DeepLabV3 | R-101-D8 | 480x480   |   80000 | -        | -              | 52.46 |         54.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context_59/deeplabv3_r101-d8_480x480_80k_pascal_context_59_20210416_113002-26303993.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context_59/deeplabv3_r101-d8_480x480_80k_pascal_context_59-20210416_113002.log.json) |
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                                                           |
+| --------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3 | R-101-D8 | 480x480   |   40000 | -        | -              | V100   | 52.61 |         54.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context_59/deeplabv3_r101-d8_480x480_40k_pascal_context_59_20210416_110332-cb08ea46.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context_59/deeplabv3_r101-d8_480x480_40k_pascal_context_59-20210416_110332.log.json) |
+| DeepLabV3 | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 52.46 |         54.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context_59/deeplabv3_r101-d8_480x480_80k_pascal_context_59_20210416_113002-26303993.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context_59/deeplabv3_r101-d8_480x480_80k_pascal_context_59-20210416_113002.log.json) |
 
 ### COCO-Stuff 10k
 
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                    | download                                                                                                                                                                                                                                                                                                                                                                                           |
-| --------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3 | R-50-D8  | 512x512   |   20000 | 9.6      | 10.8           | 34.66 |         36.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-20k_coco-stuff10k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025-b35f789d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025.log.json)     |
-| DeepLabV3 | R-101-D8 | 512x512   |   20000 | 13.2     | 8.7            | 37.30 |         38.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-20k_coco-stuff10k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025-c49752cb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025.log.json) |
-| DeepLabV3 | R-50-D8  | 512x512   |   40000 | -        | -              | 35.73 |         37.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-40k_coco-stuff10k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305-dc76f3ff.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305.log.json)     |
-| DeepLabV3 | R-101-D8 | 512x512   |   40000 | -        | -              | 37.81 |         38.80 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_coco-stuff10k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305-636cb433.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305.log.json) |
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                    | download                                                                                                                                                                                                                                                                                                                                                                                           |
+| --------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3 | R-50-D8  | 512x512   |   20000 | 9.6      | 10.8           | V100   | 34.66 |         36.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-20k_coco-stuff10k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025-b35f789d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025.log.json)     |
+| DeepLabV3 | R-101-D8 | 512x512   |   20000 | 13.2     | 8.7            | V100   | 37.30 |         38.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-20k_coco-stuff10k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025-c49752cb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025.log.json) |
+| DeepLabV3 | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 35.73 |         37.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-40k_coco-stuff10k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305-dc76f3ff.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305.log.json)     |
+| DeepLabV3 | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 37.81 |         38.80 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_coco-stuff10k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305-636cb433.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305.log.json) |
 
 ### COCO-Stuff 164k
 
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                                                                                   |
-| --------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3 | R-50-D8  | 512x512   |   80000 | 9.6      | 10.8           | 39.38 |         40.03 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-80k_coco-stuff164k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k_20210709_163016-88675c24.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k_20210709_163016.log.json)         |
-| DeepLabV3 | R-101-D8 | 512x512   |   80000 | 13.2     | 8.7            | 40.87 |         41.50 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k_20210709_201252-13600dc2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k_20210709_201252.log.json)     |
-| DeepLabV3 | R-50-D8  | 512x512   |  160000 | -        | -              | 41.09 |         41.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k_20210709_163016-49f2812b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k_20210709_163016.log.json)     |
-| DeepLabV3 | R-101-D8 | 512x512   |  160000 | -        | -              | 41.82 |         42.49 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-160k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k_20210709_155402-f035acfd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k_20210709_155402.log.json) |
-| DeepLabV3 | R-50-D8  | 512x512   |  320000 | -        | -              | 41.37 |         42.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-320k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k_20210709_155403-51b21115.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k_20210709_155403.log.json)     |
-| DeepLabV3 | R-101-D8 | 512x512   |  320000 | -        | -              | 42.61 |         43.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-320k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k_20210709_155402-3cbca14d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k_20210709_155402.log.json) |
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                                                                                   |
+| --------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3 | R-50-D8  | 512x512   |   80000 | 9.6      | 10.8           | V100   | 39.38 |         40.03 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-80k_coco-stuff164k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k_20210709_163016-88675c24.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k_20210709_163016.log.json)         |
+| DeepLabV3 | R-101-D8 | 512x512   |   80000 | 13.2     | 8.7            | V100   | 40.87 |         41.50 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k_20210709_201252-13600dc2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k_20210709_201252.log.json)     |
+| DeepLabV3 | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 41.09 |         41.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k_20210709_163016-49f2812b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k_20210709_163016.log.json)     |
+| DeepLabV3 | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 41.82 |         42.49 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-160k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k_20210709_155402-f035acfd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k_20210709_155402.log.json) |
+| DeepLabV3 | R-50-D8  | 512x512   |  320000 | -        | -              | V100   | 41.37 |         42.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-320k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k_20210709_155403-51b21115.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k_20210709_155403.log.json)     |
+| DeepLabV3 | R-101-D8 | 512x512   |  320000 | -        | -              | V100   | 42.61 |         43.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-320k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k_20210709_155402-3cbca14d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k_20210709_155402.log.json) |
 
 Note:
 
 - `D-8` here corresponding to the output stride 8 setting for DeepLab series.
 - `FP16` means Mixed Precision (FP16) is adopted in training.
+
+## Citation
+
+```bibtext
+@article{chen2017rethinking,
+  title={Rethinking atrous convolution for semantic image segmentation},
+  author={Chen, Liang-Chieh and Papandreou, George and Schroff, Florian and Adam, Hartwig},
+  journal={arXiv preprint arXiv:1706.05587},
+  year={2017}
+}
+```
diff --git a/configs/deeplabv3/deeplabv3.yml b/configs/deeplabv3/deeplabv3.yml
deleted file mode 100644
index 6196212992..0000000000
--- a/configs/deeplabv3/deeplabv3.yml
+++ /dev/null
@@ -1,756 +0,0 @@
-Collections:
-- Name: DeepLabV3
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-    - Pascal VOC 2012 + Aug
-    - Pascal Context
-    - Pascal Context 59
-    - COCO-Stuff 10k
-    - COCO-Stuff 164k
-  Paper:
-    URL: https://arxiv.org/abs/1706.05587
-    Title: Rethinking atrous convolution for semantic image segmentation
-  README: configs/deeplabv3/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/tensorflow/models/tree/master/research/deeplab
-Models:
-- Name: deeplabv3_r50-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 389.11
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 6.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.09
-      mIoU(ms+flip): 80.45
-  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes/deeplabv3_r50-d8_512x1024_40k_cityscapes_20200605_022449-acadc2f8.pth
-- Name: deeplabv3_r101-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 520.83
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 9.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.12
-      mIoU(ms+flip): 79.61
-  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_40k_cityscapes/deeplabv3_r101-d8_512x1024_40k_cityscapes_20200605_012241-7fd3f799.pth
-- Name: deeplabv3_r50-d8_4xb2-40k_cityscapes-769x769
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 900.9
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 6.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.58
-      mIoU(ms+flip): 79.89
-  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_40k_cityscapes/deeplabv3_r50-d8_769x769_40k_cityscapes_20200606_113723-7eda553c.pth
-- Name: deeplabv3_r101-d8_4xb2-40k_cityscapes-769x769
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 1204.82
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 10.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.27
-      mIoU(ms+flip): 80.11
-  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_40k_cityscapes/deeplabv3_r101-d8_769x769_40k_cityscapes_20200606_113809-c64f889f.pth
-- Name: deeplabv3_r18-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-18-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 72.57
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 1.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.7
-      mIoU(ms+flip): 78.27
-  Config: configs/deeplabv3/deeplabv3_r18-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_512x1024_80k_cityscapes/deeplabv3_r18-d8_512x1024_80k_cityscapes_20201225_021506-23dffbe2.pth
-- Name: deeplabv3_r50-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.32
-      mIoU(ms+flip): 80.57
-  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_80k_cityscapes/deeplabv3_r50-d8_512x1024_80k_cityscapes_20200606_113404-b92cfdd4.pth
-- Name: deeplabv3_r101-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.2
-      mIoU(ms+flip): 81.21
-  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_80k_cityscapes/deeplabv3_r101-d8_512x1024_80k_cityscapes_20200606_113503-9e428899.pth
-- Name: deeplabv3_r101-d8_4xb2-amp-80k_cityscapes-512x1024
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 259.07
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: AMP
-      resolution: (512,1024)
-    Training Memory (GB): 5.75
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.48
-  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920-774d9cec.pth
-- Name: deeplabv3_r18-d8_4xb2-80k_cityscapes-769x769
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-18-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 180.18
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 1.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.6
-      mIoU(ms+flip): 78.26
-  Config: configs/deeplabv3/deeplabv3_r18-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_769x769_80k_cityscapes/deeplabv3_r18-d8_769x769_80k_cityscapes_20201225_021506-6452126a.pth
-- Name: deeplabv3_r50-d8_4xb2-80k_cityscapes-769x769
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.89
-      mIoU(ms+flip): 81.06
-  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_80k_cityscapes/deeplabv3_r50-d8_769x769_80k_cityscapes_20200606_221338-788d6228.pth
-- Name: deeplabv3_r101-d8_4xb2-80k_cityscapes-769x769
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.67
-      mIoU(ms+flip): 80.81
-  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_80k_cityscapes/deeplabv3_r101-d8_769x769_80k_cityscapes_20200607_013353-60e95418.pth
-- Name: deeplabv3_r101-d16-mg124_4xb2-80k_cityscapes-512x1024
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101-D16-MG124
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.36
-      mIoU(ms+flip): 79.84
-  Config: configs/deeplabv3/deeplabv3_r101-d16-mg124_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes_20200908_005644-57bb8425.pth
-- Name: deeplabv3_r18b-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-18b-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 71.79
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 1.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.26
-      mIoU(ms+flip): 77.88
-  Config: configs/deeplabv3/deeplabv3_r18b-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_512x1024_80k_cityscapes/deeplabv3_r18b-d8_512x1024_80k_cityscapes_20201225_094144-46040cef.pth
-- Name: deeplabv3_r50b-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-50b-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 364.96
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 6.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.63
-      mIoU(ms+flip): 80.98
-  Config: configs/deeplabv3/deeplabv3_r50b-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_512x1024_80k_cityscapes/deeplabv3_r50b-d8_512x1024_80k_cityscapes_20201225_155148-ec368954.pth
-- Name: deeplabv3_r101b-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101b-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 552.49
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 9.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.01
-      mIoU(ms+flip): 81.21
-  Config: configs/deeplabv3/deeplabv3_r101b-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_512x1024_80k_cityscapes/deeplabv3_r101b-d8_512x1024_80k_cityscapes_20201226_171821-8fd49503.pth
-- Name: deeplabv3_r18b-d8_4xb2-80k_cityscapes-769x769
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-18b-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 172.71
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 1.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 75.63
-      mIoU(ms+flip): 77.51
-  Config: configs/deeplabv3/deeplabv3_r18b-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_769x769_80k_cityscapes/deeplabv3_r18b-d8_769x769_80k_cityscapes_20201225_094144-fdc985d9.pth
-- Name: deeplabv3_r50b-d8_4xb2-80k_cityscapes-769x769
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-50b-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 862.07
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 6.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.8
-      mIoU(ms+flip): 80.27
-  Config: configs/deeplabv3/deeplabv3_r50b-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_769x769_80k_cityscapes/deeplabv3_r50b-d8_769x769_80k_cityscapes_20201225_155404-87fb0cf4.pth
-- Name: deeplabv3_r101b-d8_4xb2-80k_cityscapes-769x769
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101b-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 1219.51
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 10.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.41
-      mIoU(ms+flip): 80.73
-  Config: configs/deeplabv3/deeplabv3_r101b-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_769x769_80k_cityscapes/deeplabv3_r101b-d8_769x769_80k_cityscapes_20201226_190843-9142ee57.pth
-- Name: deeplabv3_r50-d8_4xb4-80k_ade20k-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 67.75
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 8.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.42
-      mIoU(ms+flip): 43.28
-  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_80k_ade20k/deeplabv3_r50-d8_512x512_80k_ade20k_20200614_185028-0bb3f844.pth
-- Name: deeplabv3_r101-d8_4xb4-80k_ade20k-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 98.62
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 12.4
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 44.08
-      mIoU(ms+flip): 45.19
-  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_80k_ade20k/deeplabv3_r101-d8_512x512_80k_ade20k_20200615_021256-d89c7fa4.pth
-- Name: deeplabv3_r50-d8_4xb4-160k_ade20k-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.66
-      mIoU(ms+flip): 44.09
-  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_160k_ade20k/deeplabv3_r50-d8_512x512_160k_ade20k_20200615_123227-5d0ee427.pth
-- Name: deeplabv3_r101-d8_4xb4-160k_ade20k-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.0
-      mIoU(ms+flip): 46.66
-  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_160k_ade20k/deeplabv3_r101-d8_512x512_160k_ade20k_20200615_105816-b1f72b3b.pth
-- Name: deeplabv3_r50-d8_4xb4-20k_voc12aug-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 72.05
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 76.17
-      mIoU(ms+flip): 77.42
-  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_20k_voc12aug/deeplabv3_r50-d8_512x512_20k_voc12aug_20200617_010906-596905ef.pth
-- Name: deeplabv3_r101-d8_4xb4-20k_voc12aug-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 101.94
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 78.7
-      mIoU(ms+flip): 79.95
-  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_20k_voc12aug/deeplabv3_r101-d8_512x512_20k_voc12aug_20200617_010932-8d13832f.pth
-- Name: deeplabv3_r50-d8_4xb4-40k_voc12aug-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 77.68
-      mIoU(ms+flip): 78.78
-  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_40k_voc12aug/deeplabv3_r50-d8_512x512_40k_voc12aug_20200613_161546-2ae96e7e.pth
-- Name: deeplabv3_r101-d8_4xb4-40k_voc12aug-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 77.92
-      mIoU(ms+flip): 79.18
-  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_40k_voc12aug/deeplabv3_r101-d8_512x512_40k_voc12aug_20200613_161432-0017d784.pth
-- Name: deeplabv3_r101-d8_4xb4-40k_pascal-context-480x480
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101-D8
-    crop size: (480,480)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 141.04
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (480,480)
-    Training Memory (GB): 9.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context
-    Metrics:
-      mIoU: 46.55
-      mIoU(ms+flip): 47.81
-  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_pascal-context-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context/deeplabv3_r101-d8_480x480_40k_pascal_context_20200911_204118-1aa27336.pth
-- Name: deeplabv3_r101-d8_4xb4-80k_pascal-context-480x480
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101-D8
-    crop size: (480,480)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context
-    Metrics:
-      mIoU: 46.42
-      mIoU(ms+flip): 47.53
-  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_pascal-context-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context/deeplabv3_r101-d8_480x480_80k_pascal_context_20200911_170155-2a21fff3.pth
-- Name: deeplabv3_r101-d8_4xb4-40k_pascal-context-59-480x480
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101-D8
-    crop size: (480,480)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context 59
-    Metrics:
-      mIoU: 52.61
-      mIoU(ms+flip): 54.28
-  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_pascal-context-59-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context_59/deeplabv3_r101-d8_480x480_40k_pascal_context_59_20210416_110332-cb08ea46.pth
-- Name: deeplabv3_r101-d8_4xb4-80k_pascal-context-59-480x480
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101-D8
-    crop size: (480,480)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context 59
-    Metrics:
-      mIoU: 52.46
-      mIoU(ms+flip): 54.09
-  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_pascal-context-59-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context_59/deeplabv3_r101-d8_480x480_80k_pascal_context_59_20210416_113002-26303993.pth
-- Name: deeplabv3_r50-d8_4xb4-20k_coco-stuff10k-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 92.59
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 10k
-    Metrics:
-      mIoU: 34.66
-      mIoU(ms+flip): 36.08
-  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb4-20k_coco-stuff10k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025-b35f789d.pth
-- Name: deeplabv3_r101-d8_4xb4-20k_coco-stuff10k-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 114.94
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 13.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 10k
-    Metrics:
-      mIoU: 37.3
-      mIoU(ms+flip): 38.42
-  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-20k_coco-stuff10k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025-c49752cb.pth
-- Name: deeplabv3_r50-d8_4xb4-40k_coco-stuff10k-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 10k
-    Metrics:
-      mIoU: 35.73
-      mIoU(ms+flip): 37.09
-  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb4-40k_coco-stuff10k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305-dc76f3ff.pth
-- Name: deeplabv3_r101-d8_4xb4-40k_coco-stuff10k-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 10k
-    Metrics:
-      mIoU: 37.81
-      mIoU(ms+flip): 38.8
-  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_coco-stuff10k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305-636cb433.pth
-- Name: deeplabv3_r50-d8_4xb4-80k_coco-stuff164k-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 92.59
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 164k
-    Metrics:
-      mIoU: 39.38
-      mIoU(ms+flip): 40.03
-  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb4-80k_coco-stuff164k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k_20210709_163016-88675c24.pth
-- Name: deeplabv3_r101-d8_4xb4-80k_coco-stuff164k-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 114.94
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 13.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 164k
-    Metrics:
-      mIoU: 40.87
-      mIoU(ms+flip): 41.5
-  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_coco-stuff164k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k_20210709_201252-13600dc2.pth
-- Name: deeplabv3_r50-d8_4xb4-160k_coco-stuff164k-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 164k
-    Metrics:
-      mIoU: 41.09
-      mIoU(ms+flip): 41.69
-  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb4-160k_coco-stuff164k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k_20210709_163016-49f2812b.pth
-- Name: deeplabv3_r101-d8_4xb4-160k_coco-stuff164k-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 164k
-    Metrics:
-      mIoU: 41.82
-      mIoU(ms+flip): 42.49
-  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-160k_coco-stuff164k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k_20210709_155402-f035acfd.pth
-- Name: deeplabv3_r50-d8_4xb4-320k_coco-stuff164k-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 320000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 164k
-    Metrics:
-      mIoU: 41.37
-      mIoU(ms+flip): 42.22
-  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb4-320k_coco-stuff164k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k_20210709_155403-51b21115.pth
-- Name: deeplabv3_r101-d8_4xb4-320k_coco-stuff164k-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 320000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 164k
-    Metrics:
-      mIoU: 42.61
-      mIoU(ms+flip): 43.42
-  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-320k_coco-stuff164k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k_20210709_155402-3cbca14d.pth
diff --git a/configs/deeplabv3/metafile.yaml b/configs/deeplabv3/metafile.yaml
new file mode 100644
index 0000000000..650f7d695d
--- /dev/null
+++ b/configs/deeplabv3/metafile.yaml
@@ -0,0 +1,985 @@
+Collections:
+- Name: DeepLabV3
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - ADE20K
+    - Pascal VOC 2012 + Aug
+    - Pascal Context
+    - Pascal Context 59
+    - COCO-Stuff 10k
+    - COCO-Stuff 164k
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  README: configs/deeplabv3/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: deeplabv3_r50-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.09
+      mIoU(ms+flip): 80.45
+  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes/deeplabv3_r50-d8_512x1024_40k_cityscapes_20200605_022449-acadc2f8.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes/deeplabv3_r50-d8_512x1024_40k_cityscapes_20200605_022449.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.12
+      mIoU(ms+flip): 79.61
+  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_40k_cityscapes/deeplabv3_r101-d8_512x1024_40k_cityscapes_20200605_012241-7fd3f799.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_40k_cityscapes/deeplabv3_r101-d8_512x1024_40k_cityscapes_20200605_012241.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r50-d8_4xb2-40k_cityscapes-769x769
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.58
+      mIoU(ms+flip): 79.89
+  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_40k_cityscapes/deeplabv3_r50-d8_769x769_40k_cityscapes_20200606_113723-7eda553c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_40k_cityscapes/deeplabv3_r50-d8_769x769_40k_cityscapes_20200606_113723.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d8_4xb2-40k_cityscapes-769x769
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.27
+      mIoU(ms+flip): 80.11
+  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_40k_cityscapes/deeplabv3_r101-d8_769x769_40k_cityscapes_20200606_113809-c64f889f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_40k_cityscapes/deeplabv3_r101-d8_769x769_40k_cityscapes_20200606_113809.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r18-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.7
+      mIoU(ms+flip): 78.27
+  Config: configs/deeplabv3/deeplabv3_r18-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_512x1024_80k_cityscapes/deeplabv3_r18-d8_512x1024_80k_cityscapes_20201225_021506-23dffbe2.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_512x1024_80k_cityscapes/deeplabv3_r18-d8_512x1024_80k_cityscapes-20201225_021506.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r50-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.32
+      mIoU(ms+flip): 80.57
+  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_80k_cityscapes/deeplabv3_r50-d8_512x1024_80k_cityscapes_20200606_113404-b92cfdd4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_80k_cityscapes/deeplabv3_r50-d8_512x1024_80k_cityscapes_20200606_113404.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.2
+      mIoU(ms+flip): 81.21
+  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_80k_cityscapes/deeplabv3_r101-d8_512x1024_80k_cityscapes_20200606_113503-9e428899.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_80k_cityscapes/deeplabv3_r101-d8_512x1024_80k_cityscapes_20200606_113503.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d8_4xb2-amp-80k_cityscapes-512x1024
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.48
+  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DeepLabV3
+    - (FP16)
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.75
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920-774d9cec.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r18-d8_4xb2-80k_cityscapes-769x769
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.6
+      mIoU(ms+flip): 78.26
+  Config: configs/deeplabv3/deeplabv3_r18-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_769x769_80k_cityscapes/deeplabv3_r18-d8_769x769_80k_cityscapes_20201225_021506-6452126a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_769x769_80k_cityscapes/deeplabv3_r18-d8_769x769_80k_cityscapes-20201225_021506.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r50-d8_4xb2-80k_cityscapes-769x769
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.89
+      mIoU(ms+flip): 81.06
+  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_80k_cityscapes/deeplabv3_r50-d8_769x769_80k_cityscapes_20200606_221338-788d6228.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_80k_cityscapes/deeplabv3_r50-d8_769x769_80k_cityscapes_20200606_221338.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d8_4xb2-80k_cityscapes-769x769
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.67
+      mIoU(ms+flip): 80.81
+  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_80k_cityscapes/deeplabv3_r101-d8_769x769_80k_cityscapes_20200607_013353-60e95418.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_80k_cityscapes/deeplabv3_r101-d8_769x769_80k_cityscapes_20200607_013353.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d16-mg124_4xb2-40k_cityscapes-512x1024
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.71
+      mIoU(ms+flip): 78.63
+  Config: configs/deeplabv3/deeplabv3_r101-d16-mg124_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D16-MG124
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 4.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes_20200908_005644-67b0c992.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes-20200908_005644.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d16-mg124_4xb2-80k_cityscapes-512x1024
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.36
+      mIoU(ms+flip): 79.84
+  Config: configs/deeplabv3/deeplabv3_r101-d16-mg124_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D16-MG124
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes_20200908_005644-57bb8425.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes-20200908_005644.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r18b-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.26
+      mIoU(ms+flip): 77.88
+  Config: configs/deeplabv3/deeplabv3_r18b-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18b-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_512x1024_80k_cityscapes/deeplabv3_r18b-d8_512x1024_80k_cityscapes_20201225_094144-46040cef.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_512x1024_80k_cityscapes/deeplabv3_r18b-d8_512x1024_80k_cityscapes-20201225_094144.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r50b-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.63
+      mIoU(ms+flip): 80.98
+  Config: configs/deeplabv3/deeplabv3_r50b-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50b-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_512x1024_80k_cityscapes/deeplabv3_r50b-d8_512x1024_80k_cityscapes_20201225_155148-ec368954.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_512x1024_80k_cityscapes/deeplabv3_r50b-d8_512x1024_80k_cityscapes-20201225_155148.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101b-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.01
+      mIoU(ms+flip): 81.21
+  Config: configs/deeplabv3/deeplabv3_r101b-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101b-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_512x1024_80k_cityscapes/deeplabv3_r101b-d8_512x1024_80k_cityscapes_20201226_171821-8fd49503.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_512x1024_80k_cityscapes/deeplabv3_r101b-d8_512x1024_80k_cityscapes-20201226_171821.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r18b-d8_4xb2-80k_cityscapes-769x769
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 75.63
+      mIoU(ms+flip): 77.51
+  Config: configs/deeplabv3/deeplabv3_r18b-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18b-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_769x769_80k_cityscapes/deeplabv3_r18b-d8_769x769_80k_cityscapes_20201225_094144-fdc985d9.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_769x769_80k_cityscapes/deeplabv3_r18b-d8_769x769_80k_cityscapes-20201225_094144.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r50b-d8_4xb2-80k_cityscapes-769x769
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.8
+      mIoU(ms+flip): 80.27
+  Config: configs/deeplabv3/deeplabv3_r50b-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50b-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_769x769_80k_cityscapes/deeplabv3_r50b-d8_769x769_80k_cityscapes_20201225_155404-87fb0cf4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_769x769_80k_cityscapes/deeplabv3_r50b-d8_769x769_80k_cityscapes-20201225_155404.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101b-d8_4xb2-80k_cityscapes-769x769
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.41
+      mIoU(ms+flip): 80.73
+  Config: configs/deeplabv3/deeplabv3_r101b-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101b-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_769x769_80k_cityscapes/deeplabv3_r101b-d8_769x769_80k_cityscapes_20201226_190843-9142ee57.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_769x769_80k_cityscapes/deeplabv3_r101b-d8_769x769_80k_cityscapes-20201226_190843.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r50-d8_4xb4-80k_ade20k-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.42
+      mIoU(ms+flip): 43.28
+  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_80k_ade20k/deeplabv3_r50-d8_512x512_80k_ade20k_20200614_185028-0bb3f844.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_80k_ade20k/deeplabv3_r50-d8_512x512_80k_ade20k_20200614_185028.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d8_4xb4-80k_ade20k-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 44.08
+      mIoU(ms+flip): 45.19
+  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 12.4
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_80k_ade20k/deeplabv3_r101-d8_512x512_80k_ade20k_20200615_021256-d89c7fa4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_80k_ade20k/deeplabv3_r101-d8_512x512_80k_ade20k_20200615_021256.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r50-d8_4xb4-160k_ade20k-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.66
+      mIoU(ms+flip): 44.09
+  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_160k_ade20k/deeplabv3_r50-d8_512x512_160k_ade20k_20200615_123227-5d0ee427.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_160k_ade20k/deeplabv3_r50-d8_512x512_160k_ade20k_20200615_123227.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d8_4xb4-160k_ade20k-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.0
+      mIoU(ms+flip): 46.66
+  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_160k_ade20k/deeplabv3_r101-d8_512x512_160k_ade20k_20200615_105816-b1f72b3b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_160k_ade20k/deeplabv3_r101-d8_512x512_160k_ade20k_20200615_105816.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r50-d8_4xb4-20k_voc12aug-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 76.17
+      mIoU(ms+flip): 77.42
+  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_20k_voc12aug/deeplabv3_r50-d8_512x512_20k_voc12aug_20200617_010906-596905ef.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_20k_voc12aug/deeplabv3_r50-d8_512x512_20k_voc12aug_20200617_010906.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d8_4xb4-20k_voc12aug-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 78.7
+      mIoU(ms+flip): 79.95
+  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_20k_voc12aug/deeplabv3_r101-d8_512x512_20k_voc12aug_20200617_010932-8d13832f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_20k_voc12aug/deeplabv3_r101-d8_512x512_20k_voc12aug_20200617_010932.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r50-d8_4xb4-40k_voc12aug-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 77.68
+      mIoU(ms+flip): 78.78
+  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_40k_voc12aug/deeplabv3_r50-d8_512x512_40k_voc12aug_20200613_161546-2ae96e7e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_40k_voc12aug/deeplabv3_r50-d8_512x512_40k_voc12aug_20200613_161546.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d8_4xb4-40k_voc12aug-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 77.92
+      mIoU(ms+flip): 79.18
+  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_40k_voc12aug/deeplabv3_r101-d8_512x512_40k_voc12aug_20200613_161432-0017d784.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_40k_voc12aug/deeplabv3_r101-d8_512x512_40k_voc12aug_20200613_161432.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d8_4xb4-40k_pascal-context-480x480
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context
+    Metrics:
+      mIoU: 46.55
+      mIoU(ms+flip): 47.81
+  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_pascal-context-480x480.py
+  Metadata:
+    Training Data: Pascal Context
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context/deeplabv3_r101-d8_480x480_40k_pascal_context_20200911_204118-1aa27336.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context/deeplabv3_r101-d8_480x480_40k_pascal_context-20200911_204118.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d8_4xb4-80k_pascal-context-480x480
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context
+    Metrics:
+      mIoU: 46.42
+      mIoU(ms+flip): 47.53
+  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_pascal-context-480x480.py
+  Metadata:
+    Training Data: Pascal Context
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context/deeplabv3_r101-d8_480x480_80k_pascal_context_20200911_170155-2a21fff3.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context/deeplabv3_r101-d8_480x480_80k_pascal_context-20200911_170155.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d8_4xb4-40k_pascal-context-59-480x480
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context 59
+    Metrics:
+      mIoU: 52.61
+      mIoU(ms+flip): 54.28
+  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_pascal-context-59-480x480.py
+  Metadata:
+    Training Data: Pascal Context 59
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context_59/deeplabv3_r101-d8_480x480_40k_pascal_context_59_20210416_110332-cb08ea46.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context_59/deeplabv3_r101-d8_480x480_40k_pascal_context_59-20210416_110332.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d8_4xb4-80k_pascal-context-59-480x480
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context 59
+    Metrics:
+      mIoU: 52.46
+      mIoU(ms+flip): 54.09
+  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_pascal-context-59-480x480.py
+  Metadata:
+    Training Data: Pascal Context 59
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context_59/deeplabv3_r101-d8_480x480_80k_pascal_context_59_20210416_113002-26303993.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context_59/deeplabv3_r101-d8_480x480_80k_pascal_context_59-20210416_113002.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r50-d8_4xb4-20k_coco-stuff10k-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 10k
+    Metrics:
+      mIoU: 34.66
+      mIoU(ms+flip): 36.08
+  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb4-20k_coco-stuff10k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 10k
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025-b35f789d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d8_4xb4-20k_coco-stuff10k-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 10k
+    Metrics:
+      mIoU: 37.3
+      mIoU(ms+flip): 38.42
+  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-20k_coco-stuff10k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 10k
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 13.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025-c49752cb.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r50-d8_4xb4-40k_coco-stuff10k-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 10k
+    Metrics:
+      mIoU: 35.73
+      mIoU(ms+flip): 37.09
+  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb4-40k_coco-stuff10k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 10k
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305-dc76f3ff.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d8_4xb4-40k_coco-stuff10k-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 10k
+    Metrics:
+      mIoU: 37.81
+      mIoU(ms+flip): 38.8
+  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_coco-stuff10k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 10k
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305-636cb433.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r50-d8_4xb4-80k_coco-stuff164k-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 39.38
+      mIoU(ms+flip): 40.03
+  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb4-80k_coco-stuff164k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 164k
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k_20210709_163016-88675c24.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k_20210709_163016.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d8_4xb4-80k_coco-stuff164k-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 40.87
+      mIoU(ms+flip): 41.5
+  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_coco-stuff164k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 164k
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 13.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k_20210709_201252-13600dc2.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k_20210709_201252.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r50-d8_4xb4-160k_coco-stuff164k-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 41.09
+      mIoU(ms+flip): 41.69
+  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb4-160k_coco-stuff164k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 164k
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k_20210709_163016-49f2812b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k_20210709_163016.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d8_4xb4-160k_coco-stuff164k-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 41.82
+      mIoU(ms+flip): 42.49
+  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-160k_coco-stuff164k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 164k
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k_20210709_155402-f035acfd.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k_20210709_155402.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r50-d8_4xb4-320k_coco-stuff164k-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 41.37
+      mIoU(ms+flip): 42.22
+  Config: configs/deeplabv3/deeplabv3_r50-d8_4xb4-320k_coco-stuff164k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 164k
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k_20210709_155403-51b21115.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k_20210709_155403.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
+- Name: deeplabv3_r101-d8_4xb4-320k_coco-stuff164k-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 42.61
+      mIoU(ms+flip): 43.42
+  Config: configs/deeplabv3/deeplabv3_r101-d8_4xb4-320k_coco-stuff164k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 164k
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k_20210709_155402-3cbca14d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k_20210709_155402.log.json
+  Paper:
+    Title: Rethinking atrous convolution for semantic image segmentation
+    URL: https://arxiv.org/abs/1706.05587
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
+  Framework: PyTorch
diff --git a/configs/deeplabv3plus/README.md b/configs/deeplabv3plus/README.md
index f60f547391..15c51a504a 100644
--- a/configs/deeplabv3plus/README.md
+++ b/configs/deeplabv3plus/README.md
@@ -1,6 +1,6 @@
 # DeepLabV3+
 
-[Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://arxiv.org/abs/1802.02611)
+> [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://arxiv.org/abs/1802.02611)
 
 ## Introduction
 
@@ -22,107 +22,96 @@ Spatial pyramid pooling module or encode-decoder structure are used in deep neur
 <img src="https://user-images.githubusercontent.com/24582831/142900680-3e2c3098-8341-4760-bbfd-b1d7d29968ea.png" width="70%"/>
 </div>
 
-## Citation
-
-```bibtex
-@inproceedings{deeplabv3plus2018,
-  title={Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation},
-  author={Liang-Chieh Chen and Yukun Zhu and George Papandreou and Florian Schroff and Hartwig Adam},
-  booktitle={ECCV},
-  year={2018}
-}
-```
-
 ## Results and models
 
 ### Cityscapes
 
-| Method            | Backbone        | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                                                                                       |
-| ----------------- | --------------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| DeepLabV3+        | R-50-D8         | 512x1024  |   40000 | 7.5      | 3.94           | 79.61 |         81.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-40k_cityscapes-512x1024.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_40k_cityscapes/deeplabv3plus_r50-d8_512x1024_40k_cityscapes_20200605_094610-d222ffcd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_40k_cityscapes/deeplabv3plus_r50-d8_512x1024_40k_cityscapes_20200605_094610.log.json)                                 |
-| DeepLabV3+        | R-101-D8        | 512x1024  |   40000 | 11       | 2.60           | 80.21 |         81.82 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-40k_cityscapes-512x1024.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_40k_cityscapes/deeplabv3plus_r101-d8_512x1024_40k_cityscapes_20200605_094614-3769eecf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_40k_cityscapes/deeplabv3plus_r101-d8_512x1024_40k_cityscapes_20200605_094614.log.json)                             |
-| DeepLabV3+        | R-50-D8         | 769x769   |   40000 | 8.5      | 1.72           | 78.97 |         80.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-40k_cityscapes-769x769.py)                  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_40k_cityscapes/deeplabv3plus_r50-d8_769x769_40k_cityscapes_20200606_114143-1dcb0e3c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_40k_cityscapes/deeplabv3plus_r50-d8_769x769_40k_cityscapes_20200606_114143.log.json)                                     |
-| DeepLabV3+        | R-101-D8        | 769x769   |   40000 | 12.5     | 1.15           | 79.46 |         80.50 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-40k_cityscapes-769x769.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_40k_cityscapes/deeplabv3plus_r101-d8_769x769_40k_cityscapes_20200606_114304-ff414b9e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_40k_cityscapes/deeplabv3plus_r101-d8_769x769_40k_cityscapes_20200606_114304.log.json)                                 |
-| DeepLabV3+        | R-18-D8         | 512x1024  |   80000 | 2.2      | 14.27          | 76.89 |         78.76 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb2-80k_cityscapes-512x1024.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x1024_80k_cityscapes/deeplabv3plus_r18-d8_512x1024_80k_cityscapes_20201226_080942-cff257fe.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x1024_80k_cityscapes/deeplabv3plus_r18-d8_512x1024_80k_cityscapes-20201226_080942.log.json)                                 |
-| DeepLabV3+        | R-50-D8         | 512x1024  |   80000 | -        | -              | 80.09 |         81.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-512x1024.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes/deeplabv3plus_r50-d8_512x1024_80k_cityscapes_20200606_114049-f9fb496d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes/deeplabv3plus_r50-d8_512x1024_80k_cityscapes_20200606_114049.log.json)                                 |
-| DeepLabV3+        | R-101-D8        | 512x1024  |   80000 | -        | -              | 80.97 |         82.03 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-80k_cityscapes-512x1024.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143-068fcfe9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143.log.json)                             |
-| DeepLabV3+ (FP16) | R-101-D8        | 512x1024  |   80000 | 6.35     | 7.87           | 80.46 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920-f1104f4b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920.log.json)         |
-| DeepLabV3+        | R-18-D8         | 769x769   |   80000 | 2.5      | 5.74           | 76.26 |         77.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb2-80k_cityscapes-769x769.py)                  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_769x769_80k_cityscapes/deeplabv3plus_r18-d8_769x769_80k_cityscapes_20201226_083346-f326e06a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_769x769_80k_cityscapes/deeplabv3plus_r18-d8_769x769_80k_cityscapes-20201226_083346.log.json)                                     |
-| DeepLabV3+        | R-50-D8         | 769x769   |   80000 | -        | -              | 79.83 |         81.48 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-769x769.py)                  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes/deeplabv3plus_r50-d8_769x769_80k_cityscapes_20200606_210233-0e9dfdc4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes/deeplabv3plus_r50-d8_769x769_80k_cityscapes_20200606_210233.log.json)                                     |
-| DeepLabV3+        | R-101-D8        | 769x769   |   80000 | -        | -              | 80.65 |         81.47 | [config<sup>\[1\]</sup>](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes/deeplabv3plus_r101-d8_769x769_80k_cityscapes_20220406_154720-dfcc0b68.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes/deeplabv3plus_r101-d8_769x769_80k_cityscapes_20220406_154720.log.json)                                 |
-| DeepLabV3+        | R-101-D16-MG124 | 512x1024  |   40000 | 5.8      | 7.48           | 79.09 |         80.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/ddeeplabv3plus_r101-d16-mg124_4xb2-40k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes_20200908_005644-cf9ce186.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes-20200908_005644.log.json) |
-| DeepLabV3+        | R-101-D16-MG124 | 512x1024  |   80000 | 9.9      | -              | 79.90 |         81.33 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d16-mg124_4xb2-80k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes_20200908_005644-ee6158e0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes-20200908_005644.log.json) |
-| DeepLabV3+        | R-18b-D8        | 512x1024  |   80000 | 2.1      | 14.95          | 75.87 |         77.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18b-d8_4xb2-80k_cityscapes-512x1024.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes_20201226_090828-e451abd9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes-20201226_090828.log.json)                             |
-| DeepLabV3+        | R-50b-D8        | 512x1024  |   80000 | 7.4      | 3.94           | 80.28 |         81.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50b-d8_4xb2-80k_cityscapes-512x1024.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes_20201225_213645-a97e4e43.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes-20201225_213645.log.json)                             |
-| DeepLabV3+        | R-101b-D8       | 512x1024  |   80000 | 10.9     | 2.60           | 80.16 |         81.41 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101b-d8_4xb2-80k_cityscapes-512x1024.py)               | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes_20201226_190843-9c3c93a4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes-20201226_190843.log.json)                         |
-| DeepLabV3+        | R-18b-D8        | 769x769   |   80000 | 2.4      | 5.96           | 76.36 |         78.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18b-d8_4xb2-80k_cityscapes-769x769.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_769x769_80k_cityscapes/deeplabv3plus_r18b-d8_769x769_80k_cityscapes_20201226_151312-2c868aff.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_769x769_80k_cityscapes/deeplabv3plus_r18b-d8_769x769_80k_cityscapes-20201226_151312.log.json)                                 |
-| DeepLabV3+        | R-50b-D8        | 769x769   |   80000 | 8.4      | 1.72           | 79.41 |         80.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50b-d8_4xb2-80k_cityscapes-769x769.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_769x769_80k_cityscapes/deeplabv3plus_r50b-d8_769x769_80k_cityscapes_20201225_224655-8b596d1c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_769x769_80k_cityscapes/deeplabv3plus_r50b-d8_769x769_80k_cityscapes-20201225_224655.log.json)                                 |
-| DeepLabV3+        | R-101b-D8       | 769x769   |   80000 | 12.3     | 1.10           | 79.88 |         81.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101b-d8_4xb2-80k_cityscapes-769x769.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_769x769_80k_cityscapes/deeplabv3plus_r101b-d8_769x769_80k_cityscapes_20201226_205041-227cdf7c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_769x769_80k_cityscapes/deeplabv3plus_r101b-d8_769x769_80k_cityscapes-20201226_205041.log.json)                             |
+| Method            | Backbone        | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                                                                                       |
+| ----------------- | --------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| DeepLabV3+        | R-50-D8         | 512x1024  |   40000 | 7.5      | 3.94           | V100   | 79.61 |         81.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-40k_cityscapes-512x1024.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_40k_cityscapes/deeplabv3plus_r50-d8_512x1024_40k_cityscapes_20200605_094610-d222ffcd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_40k_cityscapes/deeplabv3plus_r50-d8_512x1024_40k_cityscapes_20200605_094610.log.json)                                 |
+| DeepLabV3+        | R-101-D8        | 512x1024  |   40000 | 11       | 2.60           | V100   | 80.21 |         81.82 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-40k_cityscapes-512x1024.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_40k_cityscapes/deeplabv3plus_r101-d8_512x1024_40k_cityscapes_20200605_094614-3769eecf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_40k_cityscapes/deeplabv3plus_r101-d8_512x1024_40k_cityscapes_20200605_094614.log.json)                             |
+| DeepLabV3+        | R-50-D8         | 769x769   |   40000 | 8.5      | 1.72           | V100   | 78.97 |         80.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-40k_cityscapes-769x769.py)                  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_40k_cityscapes/deeplabv3plus_r50-d8_769x769_40k_cityscapes_20200606_114143-1dcb0e3c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_40k_cityscapes/deeplabv3plus_r50-d8_769x769_40k_cityscapes_20200606_114143.log.json)                                     |
+| DeepLabV3+        | R-101-D8        | 769x769   |   40000 | 12.5     | 1.15           | V100   | 79.46 |         80.50 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-40k_cityscapes-769x769.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_40k_cityscapes/deeplabv3plus_r101-d8_769x769_40k_cityscapes_20200606_114304-ff414b9e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_40k_cityscapes/deeplabv3plus_r101-d8_769x769_40k_cityscapes_20200606_114304.log.json)                                 |
+| DeepLabV3+        | R-18-D8         | 512x1024  |   80000 | 2.2      | 14.27          | V100   | 76.89 |         78.76 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb2-80k_cityscapes-512x1024.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x1024_80k_cityscapes/deeplabv3plus_r18-d8_512x1024_80k_cityscapes_20201226_080942-cff257fe.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x1024_80k_cityscapes/deeplabv3plus_r18-d8_512x1024_80k_cityscapes-20201226_080942.log.json)                                 |
+| DeepLabV3+        | R-50-D8         | 512x1024  |   80000 | -        | -              | V100   | 80.09 |         81.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-512x1024.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes/deeplabv3plus_r50-d8_512x1024_80k_cityscapes_20200606_114049-f9fb496d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes/deeplabv3plus_r50-d8_512x1024_80k_cityscapes_20200606_114049.log.json)                                 |
+| DeepLabV3+        | R-101-D8        | 512x1024  |   80000 | -        | -              | V100   | 80.97 |         82.03 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-80k_cityscapes-512x1024.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143-068fcfe9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143.log.json)                             |
+| DeepLabV3+ (FP16) | R-101-D8        | 512x1024  |   80000 | 6.35     | 7.87           | V100   | 80.46 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920-f1104f4b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920.log.json)         |
+| DeepLabV3+        | R-18-D8         | 769x769   |   80000 | 2.5      | 5.74           | V100   | 76.26 |         77.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb2-80k_cityscapes-769x769.py)                  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_769x769_80k_cityscapes/deeplabv3plus_r18-d8_769x769_80k_cityscapes_20201226_083346-f326e06a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_769x769_80k_cityscapes/deeplabv3plus_r18-d8_769x769_80k_cityscapes-20201226_083346.log.json)                                     |
+| DeepLabV3+        | R-50-D8         | 769x769   |   80000 | -        | -              | V100   | 79.83 |         81.48 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-769x769.py)                  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes/deeplabv3plus_r50-d8_769x769_80k_cityscapes_20200606_210233-0e9dfdc4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes/deeplabv3plus_r50-d8_769x769_80k_cityscapes_20200606_210233.log.json)                                     |
+| DeepLabV3+        | R-101-D8        | 769x769   |   80000 | -        | -              | V100   | 80.65 |         81.47 | [config<sup>\[1\]</sup>](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes/deeplabv3plus_r101-d8_769x769_80k_cityscapes_20220406_154720-dfcc0b68.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes/deeplabv3plus_r101-d8_769x769_80k_cityscapes_20220406_154720.log.json)                                 |
+| DeepLabV3+        | R-101-D16-MG124 | 512x1024  |   40000 | 5.8      | 7.48           | V100   | 79.09 |         80.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/ddeeplabv3plus_r101-d16-mg124_4xb2-40k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes_20200908_005644-cf9ce186.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes-20200908_005644.log.json) |
+| DeepLabV3+        | R-101-D16-MG124 | 512x1024  |   80000 | 9.9      | -              | V100   | 79.90 |         81.33 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d16-mg124_4xb2-80k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes_20200908_005644-ee6158e0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes-20200908_005644.log.json) |
+| DeepLabV3+        | R-18b-D8        | 512x1024  |   80000 | 2.1      | 14.95          | V100   | 75.87 |         77.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18b-d8_4xb2-80k_cityscapes-512x1024.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes_20201226_090828-e451abd9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes-20201226_090828.log.json)                             |
+| DeepLabV3+        | R-50b-D8        | 512x1024  |   80000 | 7.4      | 3.94           | V100   | 80.28 |         81.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50b-d8_4xb2-80k_cityscapes-512x1024.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes_20201225_213645-a97e4e43.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes-20201225_213645.log.json)                             |
+| DeepLabV3+        | R-101b-D8       | 512x1024  |   80000 | 10.9     | 2.60           | V100   | 80.16 |         81.41 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101b-d8_4xb2-80k_cityscapes-512x1024.py)               | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes_20201226_190843-9c3c93a4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes-20201226_190843.log.json)                         |
+| DeepLabV3+        | R-18b-D8        | 769x769   |   80000 | 2.4      | 5.96           | V100   | 76.36 |         78.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18b-d8_4xb2-80k_cityscapes-769x769.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_769x769_80k_cityscapes/deeplabv3plus_r18b-d8_769x769_80k_cityscapes_20201226_151312-2c868aff.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_769x769_80k_cityscapes/deeplabv3plus_r18b-d8_769x769_80k_cityscapes-20201226_151312.log.json)                                 |
+| DeepLabV3+        | R-50b-D8        | 769x769   |   80000 | 8.4      | 1.72           | V100   | 79.41 |         80.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50b-d8_4xb2-80k_cityscapes-769x769.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_769x769_80k_cityscapes/deeplabv3plus_r50b-d8_769x769_80k_cityscapes_20201225_224655-8b596d1c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_769x769_80k_cityscapes/deeplabv3plus_r50b-d8_769x769_80k_cityscapes-20201225_224655.log.json)                                 |
+| DeepLabV3+        | R-101b-D8       | 769x769   |   80000 | 12.3     | 1.10           | V100   | 79.88 |         81.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101b-d8_4xb2-80k_cityscapes-769x769.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_769x769_80k_cityscapes/deeplabv3plus_r101b-d8_769x769_80k_cityscapes_20201226_205041-227cdf7c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_769x769_80k_cityscapes/deeplabv3plus_r101b-d8_769x769_80k_cityscapes-20201226_205041.log.json)                             |
 
 \[1\] The training of the model is sensitive to random seed, and the seed to train it is 1111.
 
 ### ADE20K
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                                                           |
-| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3+ | R-50-D8  | 512x512   |   80000 | 10.6     | 21.01          | 42.72 |         43.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_ade20k/deeplabv3plus_r50-d8_512x512_80k_ade20k_20200614_185028-bf1400d8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_ade20k/deeplabv3plus_r50-d8_512x512_80k_ade20k_20200614_185028.log.json)         |
-| DeepLabV3+ | R-101-D8 | 512x512   |   80000 | 14.1     | 14.16          | 44.60 |         46.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_ade20k/deeplabv3plus_r101-d8_512x512_80k_ade20k_20200615_014139-d5730af7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_ade20k/deeplabv3plus_r101-d8_512x512_80k_ade20k_20200615_014139.log.json)     |
-| DeepLabV3+ | R-50-D8  | 512x512   |  160000 | -        | -              | 43.95 |         44.93 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_160k_ade20k/deeplabv3plus_r50-d8_512x512_160k_ade20k_20200615_124504-6135c7e0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_160k_ade20k/deeplabv3plus_r50-d8_512x512_160k_ade20k_20200615_124504.log.json)     |
-| DeepLabV3+ | R-101-D8 | 512x512   |  160000 | -        | -              | 45.47 |         46.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_160k_ade20k/deeplabv3plus_r101-d8_512x512_160k_ade20k_20200615_123232-38ed86bb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_160k_ade20k/deeplabv3plus_r101-d8_512x512_160k_ade20k_20200615_123232.log.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                                                           |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3+ | R-50-D8  | 512x512   |   80000 | 10.6     | 21.01          | V100   | 42.72 |         43.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_ade20k/deeplabv3plus_r50-d8_512x512_80k_ade20k_20200614_185028-bf1400d8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_ade20k/deeplabv3plus_r50-d8_512x512_80k_ade20k_20200614_185028.log.json)         |
+| DeepLabV3+ | R-101-D8 | 512x512   |   80000 | 14.1     | 14.16          | V100   | 44.60 |         46.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_ade20k/deeplabv3plus_r101-d8_512x512_80k_ade20k_20200615_014139-d5730af7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_ade20k/deeplabv3plus_r101-d8_512x512_80k_ade20k_20200615_014139.log.json)     |
+| DeepLabV3+ | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 43.95 |         44.93 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_160k_ade20k/deeplabv3plus_r50-d8_512x512_160k_ade20k_20200615_124504-6135c7e0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_160k_ade20k/deeplabv3plus_r50-d8_512x512_160k_ade20k_20200615_124504.log.json)     |
+| DeepLabV3+ | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 45.47 |         46.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_160k_ade20k/deeplabv3plus_r101-d8_512x512_160k_ade20k_20200615_123232-38ed86bb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_160k_ade20k/deeplabv3plus_r101-d8_512x512_160k_ade20k_20200615_123232.log.json) |
 
 ### Pascal VOC 2012 + Aug
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                       | download                                                                                                                                                                                                                                                                                                                                                                               |
-| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3+ | R-50-D8  | 512x512   |   20000 | 7.6      | 21             | 75.93 |         77.50 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_20k_voc12aug/deeplabv3plus_r50-d8_512x512_20k_voc12aug_20200617_102323-aad58ef1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_20k_voc12aug/deeplabv3plus_r50-d8_512x512_20k_voc12aug_20200617_102323.log.json)     |
-| DeepLabV3+ | R-101-D8 | 512x512   |   20000 | 11       | 13.88          | 77.22 |         78.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_20k_voc12aug/deeplabv3plus_r101-d8_512x512_20k_voc12aug_20200617_102345-c7ff3d56.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_20k_voc12aug/deeplabv3plus_r101-d8_512x512_20k_voc12aug_20200617_102345.log.json) |
-| DeepLabV3+ | R-50-D8  | 512x512   |   40000 | -        | -              | 76.81 |         77.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_40k_voc12aug/deeplabv3plus_r50-d8_512x512_40k_voc12aug_20200613_161759-e1b43aa9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_40k_voc12aug/deeplabv3plus_r50-d8_512x512_40k_voc12aug_20200613_161759.log.json)     |
-| DeepLabV3+ | R-101-D8 | 512x512   |   40000 | -        | -              | 78.62 |         79.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_40k_voc12aug/deeplabv3plus_r101-d8_512x512_40k_voc12aug_20200613_205333-faf03387.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_40k_voc12aug/deeplabv3plus_r101-d8_512x512_40k_voc12aug_20200613_205333.log.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                       | download                                                                                                                                                                                                                                                                                                                                                                               |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3+ | R-50-D8  | 512x512   |   20000 | 7.6      | 21             | V100   | 75.93 |         77.50 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_20k_voc12aug/deeplabv3plus_r50-d8_512x512_20k_voc12aug_20200617_102323-aad58ef1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_20k_voc12aug/deeplabv3plus_r50-d8_512x512_20k_voc12aug_20200617_102323.log.json)     |
+| DeepLabV3+ | R-101-D8 | 512x512   |   20000 | 11       | 13.88          | V100   | 77.22 |         78.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_20k_voc12aug/deeplabv3plus_r101-d8_512x512_20k_voc12aug_20200617_102345-c7ff3d56.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_20k_voc12aug/deeplabv3plus_r101-d8_512x512_20k_voc12aug_20200617_102345.log.json) |
+| DeepLabV3+ | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 76.81 |         77.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_40k_voc12aug/deeplabv3plus_r50-d8_512x512_40k_voc12aug_20200613_161759-e1b43aa9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_40k_voc12aug/deeplabv3plus_r50-d8_512x512_40k_voc12aug_20200613_161759.log.json)     |
+| DeepLabV3+ | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 78.62 |         79.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_40k_voc12aug/deeplabv3plus_r101-d8_512x512_40k_voc12aug_20200613_205333-faf03387.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_40k_voc12aug/deeplabv3plus_r101-d8_512x512_40k_voc12aug_20200613_205333.log.json) |
 
 ### Pascal Context
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                                                                       |
-| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3+ | R-101-D8 | 480x480   |   40000 | -        | 9.09           | 47.30 |         48.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context/deeplabv3plus_r101-d8_480x480_40k_pascal_context_20200911_165459-d3c8a29e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context/deeplabv3plus_r101-d8_480x480_40k_pascal_context-20200911_165459.log.json) |
-| DeepLabV3+ | R-101-D8 | 480x480   |   80000 | -        | -              | 47.23 |         48.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context/deeplabv3plus_r101-d8_480x480_80k_pascal_context_20200911_155322-145d3ee8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context/deeplabv3plus_r101-d8_480x480_80k_pascal_context-20200911_155322.log.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                                                                       |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3+ | R-101-D8 | 480x480   |   40000 | -        | 9.09           | V100   | 47.30 |         48.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context/deeplabv3plus_r101-d8_480x480_40k_pascal_context_20200911_165459-d3c8a29e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context/deeplabv3plus_r101-d8_480x480_40k_pascal_context-20200911_165459.log.json) |
+| DeepLabV3+ | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 47.23 |         48.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context/deeplabv3plus_r101-d8_480x480_80k_pascal_context_20200911_155322-145d3ee8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context/deeplabv3plus_r101-d8_480x480_80k_pascal_context-20200911_155322.log.json) |
 
 ### Pascal Context 59
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                                | download                                                                                                                                                                                                                                                                                                                                                                                                                   |
-| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3+ | R-101-D8 | 480x480   |   40000 | -        | -              | 52.86 |         54.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59_20210416_111233-ed937f15.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59-20210416_111233.log.json) |
-| DeepLabV3+ | R-101-D8 | 480x480   |   80000 | -        | -              |  53.2 |         54.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59_20210416_111127-7ca0331d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59-20210416_111127.log.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                                | download                                                                                                                                                                                                                                                                                                                                                                                                                   |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3+ | R-101-D8 | 480x480   |   40000 | -        | -              | V100   | 52.86 |         54.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59_20210416_111233-ed937f15.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59-20210416_111233.log.json) |
+| DeepLabV3+ | R-101-D8 | 480x480   |   80000 | -        | -              | V100   |  53.2 |         54.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59_20210416_111127-7ca0331d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59-20210416_111127.log.json) |
 
 ### LoveDA
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                                       |
-| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| DeepLabV3+ | R-18-D8  | 512x512   |   80000 | 1.93     | 25.57          | 50.28 |         50.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_loveda-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_loveda/deeplabv3plus_r18-d8_512x512_80k_loveda_20211104_132800-ce0fa0ca.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_loveda/deeplabv3plus_r18-d8_512x512_80k_loveda_20211104_132800.log.json)     |
-| DeepLabV3+ | R-50-D8  | 512x512   |   80000 | 7.37     | 6.00           | 50.99 |         50.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_loveda-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_loveda/deeplabv3plus_r50-d8_512x512_80k_loveda_20211105_080442-f0720392.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_loveda/deeplabv3plus_r50-d8_512x512_80k_loveda_20211105_080442.log.json)     |
-| DeepLabV3+ | R-101-D8 | 512x512   |   80000 | 10.84    | 4.33           | 51.47 |         51.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_loveda-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_loveda/deeplabv3plus_r101-d8_512x512_80k_loveda_20211105_110759-4c1f297e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_loveda/deeplabv3plus_r101-d8_512x512_80k_loveda_20211105_110759.log.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                                       |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| DeepLabV3+ | R-18-D8  | 512x512   |   80000 | 1.93     | 25.57          | V100   | 50.28 |         50.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_loveda-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_loveda/deeplabv3plus_r18-d8_512x512_80k_loveda_20211104_132800-ce0fa0ca.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_loveda/deeplabv3plus_r18-d8_512x512_80k_loveda_20211104_132800.log.json)     |
+| DeepLabV3+ | R-50-D8  | 512x512   |   80000 | 7.37     | 6.00           | V100   | 50.99 |         50.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_loveda-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_loveda/deeplabv3plus_r50-d8_512x512_80k_loveda_20211105_080442-f0720392.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_loveda/deeplabv3plus_r50-d8_512x512_80k_loveda_20211105_080442.log.json)     |
+| DeepLabV3+ | R-101-D8 | 512x512   |   80000 | 10.84    | 4.33           | V100   | 51.47 |         51.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_loveda-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_loveda/deeplabv3plus_r101-d8_512x512_80k_loveda_20211105_110759-4c1f297e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_loveda/deeplabv3plus_r101-d8_512x512_80k_loveda_20211105_110759.log.json) |
 
 ### Potsdam
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                                                           |
-| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3+ | R-18-D8  | 512x512   |   80000 | 1.91     | 81.68          | 77.09 |         78.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_potsdam/deeplabv3plus_r18-d8_512x512_80k_potsdam_20211219_020601-75fd5bc3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_potsdam/deeplabv3plus_r18-d8_512x512_80k_potsdam_20211219_020601.log.json)     |
-| DeepLabV3+ | R-50-D8  | 512x512   |   80000 | 7.36     | 26.44          | 78.33 |         79.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_potsdam/deeplabv3plus_r50-d8_512x512_80k_potsdam_20211219_031508-7e7a2b24.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_potsdam/deeplabv3plus_r50-d8_512x512_80k_potsdam_20211219_031508.log.json)     |
-| DeepLabV3+ | R-101-D8 | 512x512   |   80000 | 10.83    | 17.56          |  78.7 |         79.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_potsdam-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_potsdam/deeplabv3plus_r101-d8_512x512_80k_potsdam_20211219_031508-8b112708.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_potsdam/deeplabv3plus_r101-d8_512x512_80k_potsdam_20211219_031508.log.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                                                           |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3+ | R-18-D8  | 512x512   |   80000 | 1.91     | 81.68          | V100   | 77.09 |         78.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_potsdam/deeplabv3plus_r18-d8_512x512_80k_potsdam_20211219_020601-75fd5bc3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_potsdam/deeplabv3plus_r18-d8_512x512_80k_potsdam_20211219_020601.log.json)     |
+| DeepLabV3+ | R-50-D8  | 512x512   |   80000 | 7.36     | 26.44          | V100   | 78.33 |         79.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_potsdam/deeplabv3plus_r50-d8_512x512_80k_potsdam_20211219_031508-7e7a2b24.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_potsdam/deeplabv3plus_r50-d8_512x512_80k_potsdam_20211219_031508.log.json)     |
+| DeepLabV3+ | R-101-D8 | 512x512   |   80000 | 10.83    | 17.56          | V100   |  78.7 |         79.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_potsdam-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_potsdam/deeplabv3plus_r101-d8_512x512_80k_potsdam_20211219_031508-8b112708.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_potsdam/deeplabv3plus_r101-d8_512x512_80k_potsdam_20211219_031508.log.json) |
 
 ### Vaihingen
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                                                                   |
-| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3+ | R-18-D8  | 512x512   |   80000 | 1.91     | 72.79          | 72.50 |         74.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen_20211231_230805-7626a263.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen_20211231_230805.log.json)     |
-| DeepLabV3+ | R-50-D8  | 512x512   |   80000 | 7.36     | 26.91          | 73.97 |         75.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen_20211231_230816-5040938d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen_20211231_230816.log.json)     |
-| DeepLabV3+ | R-101-D8 | 512x512   |   80000 | 10.83    | 18.59          | 73.06 |         74.14 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_vaihingen-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen_20211231_230816-8a095afa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen_20211231_230816.log.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                                                                   |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3+ | R-18-D8  | 512x512   |   80000 | 1.91     | 72.79          | V100   | 72.50 |         74.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen_20211231_230805-7626a263.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen_20211231_230805.log.json)     |
+| DeepLabV3+ | R-50-D8  | 512x512   |   80000 | 7.36     | 26.91          | V100   | 73.97 |         75.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen_20211231_230816-5040938d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen_20211231_230816.log.json)     |
+| DeepLabV3+ | R-101-D8 | 512x512   |   80000 | 10.83    | 18.59          | V100   | 73.06 |         74.14 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_vaihingen-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen_20211231_230816-8a095afa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen_20211231_230816.log.json) |
 
 ### iSAID
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                   | download                                                                                                                                                                                                                                                                                                                                                                               |
-| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3+ | R-18-D8  | 896x896   |   80000 | 6.19     | 24.81          | 61.35 |         62.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid_20220110_180526-7059991d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid_20220110_180526.log.json) |
-| DeepLabV3+ | R-50-D8  | 896x896   |   80000 | 21.45    | 8.42           | 67.06 |         68.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid_20220110_180526-598be439.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid_20220110_180526.log.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                   | download                                                                                                                                                                                                                                                                                                                                                                               |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3+ | R-18-D8  | 896x896   |   80000 | 6.19     | 24.81          | V100   | 61.35 |         62.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid_20220110_180526-7059991d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid_20220110_180526.log.json) |
+| DeepLabV3+ | R-50-D8  | 896x896   |   80000 | 21.45    | 8.42           | V100   | 67.06 |         68.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid_20220110_180526-598be439.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid_20220110_180526.log.json) |
 
 ### Mapillary Vistas v1.2
 
@@ -136,3 +125,14 @@ Note:
 - `MG-124` stands for multi-grid dilation in the last stage of ResNet.
 - `FP16` means Mixed Precision (FP16) is adopted in training.
 - `896x896` is the Crop Size of iSAID dataset, which is followed by the implementation of [PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation](https://arxiv.org/pdf/2103.06564.pdf)
+
+## Citation
+
+```bibtex
+@inproceedings{deeplabv3plus2018,
+  title={Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation},
+  author={Liang-Chieh Chen and Yukun Zhu and George Papandreou and Florian Schroff and Hartwig Adam},
+  booktitle={ECCV},
+  year={2018}
+}
+```
diff --git a/configs/deeplabv3plus/deeplabv3plus.yml b/configs/deeplabv3plus/deeplabv3plus.yml
deleted file mode 100644
index 949cbcecc0..0000000000
--- a/configs/deeplabv3plus/deeplabv3plus.yml
+++ /dev/null
@@ -1,872 +0,0 @@
-Collections:
-- Name: DeepLabV3+
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-    - Pascal VOC 2012 + Aug
-    - Pascal Context
-    - Pascal Context 59
-    - LoveDA
-    - Potsdam
-    - Vaihingen
-    - iSAID
-    - Mapillary Vistas v1.2
-  Paper:
-    URL: https://arxiv.org/abs/1802.02611
-    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
-  README: configs/deeplabv3plus/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/tensorflow/models/tree/master/research/deeplab
-Models:
-- Name: deeplabv3plus_r50-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 253.81
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 7.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.61
-      mIoU(ms+flip): 81.01
-  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_40k_cityscapes/deeplabv3plus_r50-d8_512x1024_40k_cityscapes_20200605_094610-d222ffcd.pth
-- Name: deeplabv3plus_r101-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 384.62
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 11.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.21
-      mIoU(ms+flip): 81.82
-  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_40k_cityscapes/deeplabv3plus_r101-d8_512x1024_40k_cityscapes_20200605_094614-3769eecf.pth
-- Name: deeplabv3plus_r50-d8_4xb2-40k_cityscapes-769x769
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 581.4
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 8.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.97
-      mIoU(ms+flip): 80.46
-  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_40k_cityscapes/deeplabv3plus_r50-d8_769x769_40k_cityscapes_20200606_114143-1dcb0e3c.pth
-- Name: deeplabv3plus_r101-d8_4xb2-40k_cityscapes-769x769
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 869.57
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 12.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.46
-      mIoU(ms+flip): 80.5
-  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_40k_cityscapes/deeplabv3plus_r101-d8_769x769_40k_cityscapes_20200606_114304-ff414b9e.pth
-- Name: deeplabv3plus_r18-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-18-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 70.08
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 2.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.89
-      mIoU(ms+flip): 78.76
-  Config: configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x1024_80k_cityscapes/deeplabv3plus_r18-d8_512x1024_80k_cityscapes_20201226_080942-cff257fe.pth
-- Name: deeplabv3plus_r50-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.09
-      mIoU(ms+flip): 81.13
-  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes/deeplabv3plus_r50-d8_512x1024_80k_cityscapes_20200606_114049-f9fb496d.pth
-- Name: deeplabv3plus_r101-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.97
-      mIoU(ms+flip): 82.03
-  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143-068fcfe9.pth
-- Name: deeplabv3plus_r101-d8_4xb2-amp-80k_cityscapes-512x1024
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 127.06
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: AMP
-      resolution: (512,1024)
-    Training Memory (GB): 6.35
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.46
-  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920-f1104f4b.pth
-- Name: deeplabv3plus_r18-d8_4xb2-80k_cityscapes-769x769
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-18-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 174.22
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 2.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.26
-      mIoU(ms+flip): 77.91
-  Config: configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_769x769_80k_cityscapes/deeplabv3plus_r18-d8_769x769_80k_cityscapes_20201226_083346-f326e06a.pth
-- Name: deeplabv3plus_r50-d8_4xb2-80k_cityscapes-769x769
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.83
-      mIoU(ms+flip): 81.48
-  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes/deeplabv3plus_r50-d8_769x769_80k_cityscapes_20200606_210233-0e9dfdc4.pth
-- Name: deeplabv3plus_r101-d8_4xb2-80k_cityscapes-769x769
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.65
-      mIoU(ms+flip): 81.47
-  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes/deeplabv3plus_r101-d8_769x769_80k_cityscapes_20220406_154720-dfcc0b68.pth
-- Name: deeplabv3plus_r101-d16-mg124_4xb2-40k_cityscapes-512x1024
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101-D16-MG124
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 133.69
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 5.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.09
-      mIoU(ms+flip): 80.36
-  Config: configs/deeplabv3plus/deeplabv3plus_r101-d16-mg124_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes_20200908_005644-cf9ce186.pth
-- Name: deeplabv3plus_r101-d16-mg124_4xb2-80k_cityscapes-512x1024
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101-D16-MG124
-    crop size: (512,1024)
-    lr schd: 80000
-    Training Memory (GB): 9.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.9
-      mIoU(ms+flip): 81.33
-  Config: configs/deeplabv3plus/deeplabv3plus_r101-d16-mg124_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes_20200908_005644-ee6158e0.pth
-- Name: deeplabv3plus_r18b-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-18b-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 66.89
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 2.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 75.87
-      mIoU(ms+flip): 77.52
-  Config: configs/deeplabv3plus/deeplabv3plus_r18b-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes_20201226_090828-e451abd9.pth
-- Name: deeplabv3plus_r50b-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-50b-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 253.81
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 7.4
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.28
-      mIoU(ms+flip): 81.44
-  Config: configs/deeplabv3plus/deeplabv3plus_r50b-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes_20201225_213645-a97e4e43.pth
-- Name: deeplabv3plus_r101b-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101b-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 384.62
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 10.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.16
-      mIoU(ms+flip): 81.41
-  Config: configs/deeplabv3plus/deeplabv3plus_r101b-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes_20201226_190843-9c3c93a4.pth
-- Name: deeplabv3plus_r18b-d8_4xb2-80k_cityscapes-769x769
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-18b-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 167.79
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 2.4
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.36
-      mIoU(ms+flip): 78.24
-  Config: configs/deeplabv3plus/deeplabv3plus_r18b-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_769x769_80k_cityscapes/deeplabv3plus_r18b-d8_769x769_80k_cityscapes_20201226_151312-2c868aff.pth
-- Name: deeplabv3plus_r50b-d8_4xb2-80k_cityscapes-769x769
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-50b-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 581.4
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 8.4
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.41
-      mIoU(ms+flip): 80.56
-  Config: configs/deeplabv3plus/deeplabv3plus_r50b-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_769x769_80k_cityscapes/deeplabv3plus_r50b-d8_769x769_80k_cityscapes_20201225_224655-8b596d1c.pth
-- Name: deeplabv3plus_r101b-d8_4xb2-80k_cityscapes-769x769
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101b-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 909.09
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 12.3
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.88
-      mIoU(ms+flip): 81.46
-  Config: configs/deeplabv3plus/deeplabv3plus_r101b-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_769x769_80k_cityscapes/deeplabv3plus_r101b-d8_769x769_80k_cityscapes_20201226_205041-227cdf7c.pth
-- Name: deeplabv3plus_r50-d8_4xb4-80k_ade20k-512x512
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 47.6
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 10.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.72
-      mIoU(ms+flip): 43.75
-  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_ade20k/deeplabv3plus_r50-d8_512x512_80k_ade20k_20200614_185028-bf1400d8.pth
-- Name: deeplabv3plus_r101-d8_4xb4-160k_ade20k-512x512
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 70.62
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 14.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 44.6
-      mIoU(ms+flip): 46.06
-  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_ade20k/deeplabv3plus_r101-d8_512x512_80k_ade20k_20200615_014139-d5730af7.pth
-- Name: deeplabv3plus_r50-d8_4xb4-160k_ade20k-512x512
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.95
-      mIoU(ms+flip): 44.93
-  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_160k_ade20k/deeplabv3plus_r50-d8_512x512_160k_ade20k_20200615_124504-6135c7e0.pth
-- Name: deeplabv3plus_r101-d8_4xb4-160k_ade20k-512x512
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.47
-      mIoU(ms+flip): 46.35
-  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_160k_ade20k/deeplabv3plus_r101-d8_512x512_160k_ade20k_20200615_123232-38ed86bb.pth
-- Name: deeplabv3plus_r50-d8_4xb4-20k_voc12aug-512x512
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 47.62
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 7.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 75.93
-      mIoU(ms+flip): 77.5
-  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_20k_voc12aug/deeplabv3plus_r50-d8_512x512_20k_voc12aug_20200617_102323-aad58ef1.pth
-- Name: deeplabv3plus_r101-d8_4xb4-20k_voc12aug-512x512
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 72.05
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 11.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 77.22
-      mIoU(ms+flip): 78.59
-  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_20k_voc12aug/deeplabv3plus_r101-d8_512x512_20k_voc12aug_20200617_102345-c7ff3d56.pth
-- Name: deeplabv3plus_r50-d8_4xb4-40k_voc12aug-512x512
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 76.81
-      mIoU(ms+flip): 77.57
-  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_40k_voc12aug/deeplabv3plus_r50-d8_512x512_40k_voc12aug_20200613_161759-e1b43aa9.pth
-- Name: deeplabv3plus_r101-d8_4xb4-40k_voc12aug-512x512
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 78.62
-      mIoU(ms+flip): 79.53
-  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_40k_voc12aug/deeplabv3plus_r101-d8_512x512_40k_voc12aug_20200613_205333-faf03387.pth
-- Name: deeplabv3plus_r50-d8_4xb4-40k_pascal-context-480x480
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101-D8
-    crop size: (480,480)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 110.01
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (480,480)
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context
-    Metrics:
-      mIoU: 47.3
-      mIoU(ms+flip): 48.47
-  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-40k_pascal-context-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context/deeplabv3plus_r101-d8_480x480_40k_pascal_context_20200911_165459-d3c8a29e.pth
-- Name: deeplabv3plus_r50-d8_4xb4-80k_pascal-context-480x480
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101-D8
-    crop size: (480,480)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context
-    Metrics:
-      mIoU: 47.23
-      mIoU(ms+flip): 48.26
-  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_pascal-context-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context/deeplabv3plus_r101-d8_480x480_80k_pascal_context_20200911_155322-145d3ee8.pth
-- Name: deeplabv3plus_r101-d8_4xb4-40k_pascal-context-59-480x480
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101-D8
-    crop size: (480,480)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context 59
-    Metrics:
-      mIoU: 52.86
-      mIoU(ms+flip): 54.54
-  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-40k_pascal-context-59-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59_20210416_111233-ed937f15.pth
-- Name: deeplabv3plus_r101-d8_4xb4-80k_pascal-context-59-480x480
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101-D8
-    crop size: (480,480)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context 59
-    Metrics:
-      mIoU: 53.2
-      mIoU(ms+flip): 54.67
-  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_pascal-context-59-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59_20210416_111127-7ca0331d.pth
-- Name: deeplabv3plus_r18-d8_4xb4-80k_loveda-512x512
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-18-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 39.11
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 1.93
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: LoveDA
-    Metrics:
-      mIoU: 50.28
-      mIoU(ms+flip): 50.47
-  Config: configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_loveda-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_loveda/deeplabv3plus_r18-d8_512x512_80k_loveda_20211104_132800-ce0fa0ca.pth
-- Name: deeplabv3plus_r50-d8_4xb4-80k_loveda-512x512
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 166.67
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 7.37
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: LoveDA
-    Metrics:
-      mIoU: 50.99
-      mIoU(ms+flip): 50.65
-  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_loveda-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_loveda/deeplabv3plus_r50-d8_512x512_80k_loveda_20211105_080442-f0720392.pth
-- Name: deeplabv3plus_r101-d8_4xb4-80k_loveda-512x512
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 230.95
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 10.84
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: LoveDA
-    Metrics:
-      mIoU: 51.47
-      mIoU(ms+flip): 51.32
-  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_loveda-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_loveda/deeplabv3plus_r101-d8_512x512_80k_loveda_20211105_110759-4c1f297e.pth
-- Name: deeplabv3plus_r18-d8_4xb4-80k_potsdam-512x512
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-18-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 12.24
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 1.91
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Potsdam
-    Metrics:
-      mIoU: 77.09
-      mIoU(ms+flip): 78.44
-  Config: configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_potsdam-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_potsdam/deeplabv3plus_r18-d8_512x512_80k_potsdam_20211219_020601-75fd5bc3.pth
-- Name: deeplabv3plus_r50-d8_4xb4-80k_potsdam-512x512
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 37.82
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 7.36
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Potsdam
-    Metrics:
-      mIoU: 78.33
-      mIoU(ms+flip): 79.27
-  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_potsdam-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_potsdam/deeplabv3plus_r50-d8_512x512_80k_potsdam_20211219_031508-7e7a2b24.pth
-- Name: deeplabv3plus_r101-d8_4xb4-80k_potsdam-512x512
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 56.95
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 10.83
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Potsdam
-    Metrics:
-      mIoU: 78.7
-      mIoU(ms+flip): 79.47
-  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_potsdam-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_potsdam/deeplabv3plus_r101-d8_512x512_80k_potsdam_20211219_031508-8b112708.pth
-- Name: deeplabv3plus_r18-d8_4xb4-80k_vaihingen-512x512
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-18-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 13.74
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 1.91
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Vaihingen
-    Metrics:
-      mIoU: 72.5
-      mIoU(ms+flip): 74.13
-  Config: configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_vaihingen-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen_20211231_230805-7626a263.pth
-- Name: deeplabv3plus_r50-d8_4xb4-80k_vaihingen-512x512
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 37.16
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 7.36
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Vaihingen
-    Metrics:
-      mIoU: 73.97
-      mIoU(ms+flip): 75.05
-  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_vaihingen-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen_20211231_230816-5040938d.pth
-- Name: deeplabv3plus_r101-d8_4xb4-80k_vaihingen-512x512
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 53.79
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 10.83
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Vaihingen
-    Metrics:
-      mIoU: 73.06
-      mIoU(ms+flip): 74.14
-  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_vaihingen-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen_20211231_230816-8a095afa.pth
-- Name: deeplabv3plus_r18-d8_4xb4-80k_isaid-896x896
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-18-D8
-    crop size: (896,896)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 40.31
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (896,896)
-    Training Memory (GB): 6.19
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: iSAID
-    Metrics:
-      mIoU: 61.35
-      mIoU(ms+flip): 62.61
-  Config: configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_isaid-896x896.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid_20220110_180526-7059991d.pth
-- Name: deeplabv3plus_r50-d8_4xb4-80k_isaid-896x896
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-50-D8
-    crop size: (896,896)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 118.76
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (896,896)
-    Training Memory (GB): 21.45
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: iSAID
-    Metrics:
-      mIoU: 67.06
-      mIoU(ms+flip): 68.02
-  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_isaid-896x896.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid_20220110_180526-598be439.pth
-- Name: deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: R-50-D8
-    crop size: (1280,1280)
-    lr schd: 300000
-    inference time (ms/im):
-    - value: 55.8
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (1280,1280)
-    Training Memory (GB): 24.04
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Mapillary Vistas v1.2
-    Metrics:
-      mIoU: 47.35
-  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280_20230301_110504-655f8e43.pth
diff --git a/configs/deeplabv3plus/metafile.yaml b/configs/deeplabv3plus/metafile.yaml
new file mode 100644
index 0000000000..b41de4dee2
--- /dev/null
+++ b/configs/deeplabv3plus/metafile.yaml
@@ -0,0 +1,1041 @@
+Collections:
+- Name: DeepLabV3+
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - ADE20K
+    - Pascal VOC 2012 + Aug
+    - Pascal Context
+    - Pascal Context 59
+    - LoveDA
+    - Potsdam
+    - Vaihingen
+    - iSAID
+    - Mapillary Vistas v1.2
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  README: configs/deeplabv3plus/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: deeplabv3plus_r50-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.61
+      mIoU(ms+flip): 81.01
+  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_40k_cityscapes/deeplabv3plus_r50-d8_512x1024_40k_cityscapes_20200605_094610-d222ffcd.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_40k_cityscapes/deeplabv3plus_r50-d8_512x1024_40k_cityscapes_20200605_094610.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r101-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.21
+      mIoU(ms+flip): 81.82
+  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 11.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_40k_cityscapes/deeplabv3plus_r101-d8_512x1024_40k_cityscapes_20200605_094614-3769eecf.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_40k_cityscapes/deeplabv3plus_r101-d8_512x1024_40k_cityscapes_20200605_094614.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r50-d8_4xb2-40k_cityscapes-769x769
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.97
+      mIoU(ms+flip): 80.46
+  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_40k_cityscapes/deeplabv3plus_r50-d8_769x769_40k_cityscapes_20200606_114143-1dcb0e3c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_40k_cityscapes/deeplabv3plus_r50-d8_769x769_40k_cityscapes_20200606_114143.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r101-d8_4xb2-40k_cityscapes-769x769
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.46
+      mIoU(ms+flip): 80.5
+  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 12.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_40k_cityscapes/deeplabv3plus_r101-d8_769x769_40k_cityscapes_20200606_114304-ff414b9e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_40k_cityscapes/deeplabv3plus_r101-d8_769x769_40k_cityscapes_20200606_114304.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r18-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.89
+      mIoU(ms+flip): 78.76
+  Config: configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 2.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x1024_80k_cityscapes/deeplabv3plus_r18-d8_512x1024_80k_cityscapes_20201226_080942-cff257fe.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x1024_80k_cityscapes/deeplabv3plus_r18-d8_512x1024_80k_cityscapes-20201226_080942.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r50-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.09
+      mIoU(ms+flip): 81.13
+  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes/deeplabv3plus_r50-d8_512x1024_80k_cityscapes_20200606_114049-f9fb496d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes/deeplabv3plus_r50-d8_512x1024_80k_cityscapes_20200606_114049.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r101-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.97
+      mIoU(ms+flip): 82.03
+  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143-068fcfe9.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r101-d8_4xb2-amp-80k_cityscapes-512x1024
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.46
+  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DeepLabV3+
+    - (FP16)
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.35
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920-f1104f4b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r18-d8_4xb2-80k_cityscapes-769x769
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.26
+      mIoU(ms+flip): 77.91
+  Config: configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 2.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_769x769_80k_cityscapes/deeplabv3plus_r18-d8_769x769_80k_cityscapes_20201226_083346-f326e06a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_769x769_80k_cityscapes/deeplabv3plus_r18-d8_769x769_80k_cityscapes-20201226_083346.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r50-d8_4xb2-80k_cityscapes-769x769
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.83
+      mIoU(ms+flip): 81.48
+  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes/deeplabv3plus_r50-d8_769x769_80k_cityscapes_20200606_210233-0e9dfdc4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes/deeplabv3plus_r50-d8_769x769_80k_cityscapes_20200606_210233.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r101-d8_4xb2-80k_cityscapes-769x769
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.65
+      mIoU(ms+flip): 81.47
+  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes/deeplabv3plus_r101-d8_769x769_80k_cityscapes_20220406_154720-dfcc0b68.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes/deeplabv3plus_r101-d8_769x769_80k_cityscapes_20220406_154720.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: ddeeplabv3plus_r101-d16-mg124_4xb2-40k_cityscapes-512x1024
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.09
+      mIoU(ms+flip): 80.36
+  Config: configs/deeplabv3plus/ddeeplabv3plus_r101-d16-mg124_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D16-MG124
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes_20200908_005644-cf9ce186.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes-20200908_005644.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r101-d16-mg124_4xb2-80k_cityscapes-512x1024
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.9
+      mIoU(ms+flip): 81.33
+  Config: configs/deeplabv3plus/deeplabv3plus_r101-d16-mg124_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D16-MG124
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes_20200908_005644-ee6158e0.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes-20200908_005644.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r18b-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 75.87
+      mIoU(ms+flip): 77.52
+  Config: configs/deeplabv3plus/deeplabv3plus_r18b-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18b-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 2.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes_20201226_090828-e451abd9.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes-20201226_090828.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r50b-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.28
+      mIoU(ms+flip): 81.44
+  Config: configs/deeplabv3plus/deeplabv3plus_r50b-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50b-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.4
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes_20201225_213645-a97e4e43.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes-20201225_213645.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r101b-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.16
+      mIoU(ms+flip): 81.41
+  Config: configs/deeplabv3plus/deeplabv3plus_r101b-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101b-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes_20201226_190843-9c3c93a4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes-20201226_190843.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r18b-d8_4xb2-80k_cityscapes-769x769
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.36
+      mIoU(ms+flip): 78.24
+  Config: configs/deeplabv3plus/deeplabv3plus_r18b-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18b-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 2.4
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_769x769_80k_cityscapes/deeplabv3plus_r18b-d8_769x769_80k_cityscapes_20201226_151312-2c868aff.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_769x769_80k_cityscapes/deeplabv3plus_r18b-d8_769x769_80k_cityscapes-20201226_151312.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r50b-d8_4xb2-80k_cityscapes-769x769
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.41
+      mIoU(ms+flip): 80.56
+  Config: configs/deeplabv3plus/deeplabv3plus_r50b-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50b-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.4
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_769x769_80k_cityscapes/deeplabv3plus_r50b-d8_769x769_80k_cityscapes_20201225_224655-8b596d1c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_769x769_80k_cityscapes/deeplabv3plus_r50b-d8_769x769_80k_cityscapes-20201225_224655.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r101b-d8_4xb2-80k_cityscapes-769x769
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.88
+      mIoU(ms+flip): 81.46
+  Config: configs/deeplabv3plus/deeplabv3plus_r101b-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101b-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 12.3
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_769x769_80k_cityscapes/deeplabv3plus_r101b-d8_769x769_80k_cityscapes_20201226_205041-227cdf7c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_769x769_80k_cityscapes/deeplabv3plus_r101b-d8_769x769_80k_cityscapes-20201226_205041.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r50-d8_4xb4-80k_ade20k-512x512
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.72
+      mIoU(ms+flip): 43.75
+  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_ade20k/deeplabv3plus_r50-d8_512x512_80k_ade20k_20200614_185028-bf1400d8.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_ade20k/deeplabv3plus_r50-d8_512x512_80k_ade20k_20200614_185028.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r101-d8_4xb4-160k_ade20k-512x512
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 44.6
+      mIoU(ms+flip): 46.06
+  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 14.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_ade20k/deeplabv3plus_r101-d8_512x512_80k_ade20k_20200615_014139-d5730af7.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_ade20k/deeplabv3plus_r101-d8_512x512_80k_ade20k_20200615_014139.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r50-d8_4xb4-160k_ade20k-512x512
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.95
+      mIoU(ms+flip): 44.93
+  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_160k_ade20k/deeplabv3plus_r50-d8_512x512_160k_ade20k_20200615_124504-6135c7e0.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_160k_ade20k/deeplabv3plus_r50-d8_512x512_160k_ade20k_20200615_124504.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r101-d8_4xb4-160k_ade20k-512x512
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.47
+      mIoU(ms+flip): 46.35
+  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_160k_ade20k/deeplabv3plus_r101-d8_512x512_160k_ade20k_20200615_123232-38ed86bb.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_160k_ade20k/deeplabv3plus_r101-d8_512x512_160k_ade20k_20200615_123232.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r50-d8_4xb4-20k_voc12aug-512x512
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 75.93
+      mIoU(ms+flip): 77.5
+  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_20k_voc12aug/deeplabv3plus_r50-d8_512x512_20k_voc12aug_20200617_102323-aad58ef1.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_20k_voc12aug/deeplabv3plus_r50-d8_512x512_20k_voc12aug_20200617_102323.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r101-d8_4xb4-20k_voc12aug-512x512
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 77.22
+      mIoU(ms+flip): 78.59
+  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 11.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_20k_voc12aug/deeplabv3plus_r101-d8_512x512_20k_voc12aug_20200617_102345-c7ff3d56.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_20k_voc12aug/deeplabv3plus_r101-d8_512x512_20k_voc12aug_20200617_102345.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r50-d8_4xb4-40k_voc12aug-512x512
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 76.81
+      mIoU(ms+flip): 77.57
+  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_40k_voc12aug/deeplabv3plus_r50-d8_512x512_40k_voc12aug_20200613_161759-e1b43aa9.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_40k_voc12aug/deeplabv3plus_r50-d8_512x512_40k_voc12aug_20200613_161759.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r101-d8_4xb4-40k_voc12aug-512x512
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 78.62
+      mIoU(ms+flip): 79.53
+  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_40k_voc12aug/deeplabv3plus_r101-d8_512x512_40k_voc12aug_20200613_205333-faf03387.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_40k_voc12aug/deeplabv3plus_r101-d8_512x512_40k_voc12aug_20200613_205333.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r50-d8_4xb4-40k_pascal-context-480x480
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context
+    Metrics:
+      mIoU: 47.3
+      mIoU(ms+flip): 48.47
+  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-40k_pascal-context-480x480.py
+  Metadata:
+    Training Data: Pascal Context
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context/deeplabv3plus_r101-d8_480x480_40k_pascal_context_20200911_165459-d3c8a29e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context/deeplabv3plus_r101-d8_480x480_40k_pascal_context-20200911_165459.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r50-d8_4xb4-80k_pascal-context-480x480
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context
+    Metrics:
+      mIoU: 47.23
+      mIoU(ms+flip): 48.26
+  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_pascal-context-480x480.py
+  Metadata:
+    Training Data: Pascal Context
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context/deeplabv3plus_r101-d8_480x480_80k_pascal_context_20200911_155322-145d3ee8.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context/deeplabv3plus_r101-d8_480x480_80k_pascal_context-20200911_155322.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r101-d8_4xb4-40k_pascal-context-59-480x480
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context 59
+    Metrics:
+      mIoU: 52.86
+      mIoU(ms+flip): 54.54
+  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-40k_pascal-context-59-480x480.py
+  Metadata:
+    Training Data: Pascal Context 59
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59_20210416_111233-ed937f15.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59-20210416_111233.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r101-d8_4xb4-80k_pascal-context-59-480x480
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context 59
+    Metrics:
+      mIoU: 53.2
+      mIoU(ms+flip): 54.67
+  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_pascal-context-59-480x480.py
+  Metadata:
+    Training Data: Pascal Context 59
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59_20210416_111127-7ca0331d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59-20210416_111127.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r18-d8_4xb4-80k_loveda-512x512
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: LoveDA
+    Metrics:
+      mIoU: 50.28
+      mIoU(ms+flip): 50.47
+  Config: configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_loveda-512x512.py
+  Metadata:
+    Training Data: LoveDA
+    Batch Size: 16
+    Architecture:
+    - R-18-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.93
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_loveda/deeplabv3plus_r18-d8_512x512_80k_loveda_20211104_132800-ce0fa0ca.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_loveda/deeplabv3plus_r18-d8_512x512_80k_loveda_20211104_132800.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r50-d8_4xb4-80k_loveda-512x512
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: LoveDA
+    Metrics:
+      mIoU: 50.99
+      mIoU(ms+flip): 50.65
+  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_loveda-512x512.py
+  Metadata:
+    Training Data: LoveDA
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.37
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_loveda/deeplabv3plus_r50-d8_512x512_80k_loveda_20211105_080442-f0720392.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_loveda/deeplabv3plus_r50-d8_512x512_80k_loveda_20211105_080442.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r101-d8_4xb4-80k_loveda-512x512
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: LoveDA
+    Metrics:
+      mIoU: 51.47
+      mIoU(ms+flip): 51.32
+  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_loveda-512x512.py
+  Metadata:
+    Training Data: LoveDA
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.84
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_loveda/deeplabv3plus_r101-d8_512x512_80k_loveda_20211105_110759-4c1f297e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_loveda/deeplabv3plus_r101-d8_512x512_80k_loveda_20211105_110759.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r18-d8_4xb4-80k_potsdam-512x512
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Potsdam
+    Metrics:
+      mIoU: 77.09
+      mIoU(ms+flip): 78.44
+  Config: configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_potsdam-512x512.py
+  Metadata:
+    Training Data: Potsdam
+    Batch Size: 16
+    Architecture:
+    - R-18-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.91
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_potsdam/deeplabv3plus_r18-d8_512x512_80k_potsdam_20211219_020601-75fd5bc3.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_potsdam/deeplabv3plus_r18-d8_512x512_80k_potsdam_20211219_020601.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r50-d8_4xb4-80k_potsdam-512x512
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Potsdam
+    Metrics:
+      mIoU: 78.33
+      mIoU(ms+flip): 79.27
+  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_potsdam-512x512.py
+  Metadata:
+    Training Data: Potsdam
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.36
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_potsdam/deeplabv3plus_r50-d8_512x512_80k_potsdam_20211219_031508-7e7a2b24.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_potsdam/deeplabv3plus_r50-d8_512x512_80k_potsdam_20211219_031508.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r101-d8_4xb4-80k_potsdam-512x512
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Potsdam
+    Metrics:
+      mIoU: 78.7
+      mIoU(ms+flip): 79.47
+  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_potsdam-512x512.py
+  Metadata:
+    Training Data: Potsdam
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.83
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_potsdam/deeplabv3plus_r101-d8_512x512_80k_potsdam_20211219_031508-8b112708.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_potsdam/deeplabv3plus_r101-d8_512x512_80k_potsdam_20211219_031508.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r18-d8_4xb4-80k_vaihingen-512x512
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Vaihingen
+    Metrics:
+      mIoU: 72.5
+      mIoU(ms+flip): 74.13
+  Config: configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_vaihingen-512x512.py
+  Metadata:
+    Training Data: Vaihingen
+    Batch Size: 16
+    Architecture:
+    - R-18-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.91
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen_20211231_230805-7626a263.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen_20211231_230805.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r50-d8_4xb4-80k_vaihingen-512x512
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Vaihingen
+    Metrics:
+      mIoU: 73.97
+      mIoU(ms+flip): 75.05
+  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_vaihingen-512x512.py
+  Metadata:
+    Training Data: Vaihingen
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.36
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen_20211231_230816-5040938d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen_20211231_230816.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r101-d8_4xb4-80k_vaihingen-512x512
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Vaihingen
+    Metrics:
+      mIoU: 73.06
+      mIoU(ms+flip): 74.14
+  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_vaihingen-512x512.py
+  Metadata:
+    Training Data: Vaihingen
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.83
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen_20211231_230816-8a095afa.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen_20211231_230816.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r18-d8_4xb4-80k_isaid-896x896
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: iSAID
+    Metrics:
+      mIoU: 61.35
+      mIoU(ms+flip): 62.61
+  Config: configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_isaid-896x896.py
+  Metadata:
+    Training Data: iSAID
+    Batch Size: 16
+    Architecture:
+    - R-18-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.19
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid_20220110_180526-7059991d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid_20220110_180526.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r50-d8_4xb4-80k_isaid-896x896
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: iSAID
+    Metrics:
+      mIoU: 67.06
+      mIoU(ms+flip): 68.02
+  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_isaid-896x896.py
+  Metadata:
+    Training Data: iSAID
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 21.45
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid_20220110_180526-598be439.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid_20220110_180526.log.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
+- Name: deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Mapillary Vistas v1.2
+    Metrics:
+      mIoU: 47.35
+  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280.py
+  Metadata:
+    Training Data: Mapillary Vistas v1.2
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DeepLabV3+
+    Training Resources: 4x A100 GPUS
+    Memory (GB): 24.04
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280_20230301_110504-655f8e43.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280_20230301_110504.json
+  Paper:
+    Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
+    URL: https://arxiv.org/abs/1802.02611
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
+  Framework: PyTorch
diff --git a/configs/dmnet/README.md b/configs/dmnet/README.md
index 535740ddd3..6004c06ccb 100644
--- a/configs/dmnet/README.md
+++ b/configs/dmnet/README.md
@@ -1,6 +1,6 @@
 # DMNet
 
-[Dynamic Multi-scale Filters for Semantic Segmentation](https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf)
+> [Dynamic Multi-scale Filters for Semantic Segmentation](https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf)
 
 ## Introduction
 
@@ -22,6 +22,30 @@ Multi-scale representation provides an effective way toaddress scale variation o
 <img src="https://user-images.githubusercontent.com/24582831/142900781-6215763f-8b71-4e0b-a6b1-c41372db2aa0.png" width="70%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DMNet  | R-50-D8  | 512x1024  |   40000 | 7.0      | 3.66           | V100   | 77.78 |         79.14 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_40k_cityscapes/dmnet_r50-d8_512x1024_40k_cityscapes_20201215_042326-615373cf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_40k_cityscapes/dmnet_r50-d8_512x1024_40k_cityscapes-20201215_042326.log.json)     |
+| DMNet  | R-101-D8 | 512x1024  |   40000 | 10.6     | 2.54           | V100   | 78.37 |         79.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_40k_cityscapes/dmnet_r101-d8_512x1024_40k_cityscapes_20201215_043100-8291e976.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_40k_cityscapes/dmnet_r101-d8_512x1024_40k_cityscapes-20201215_043100.log.json) |
+| DMNet  | R-50-D8  | 769x769   |   40000 | 7.9      | 1.57           | V100   | 78.49 |         80.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_40k_cityscapes/dmnet_r50-d8_769x769_40k_cityscapes_20201215_093706-e7f0e23e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_40k_cityscapes/dmnet_r50-d8_769x769_40k_cityscapes-20201215_093706.log.json)         |
+| DMNet  | R-101-D8 | 769x769   |   40000 | 12.0     | 1.01           | V100   | 77.62 |         78.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_40k_cityscapes/dmnet_r101-d8_769x769_40k_cityscapes_20201215_081348-a74261f6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_40k_cityscapes/dmnet_r101-d8_769x769_40k_cityscapes-20201215_081348.log.json)     |
+| DMNet  | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 79.07 |         80.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_80k_cityscapes/dmnet_r50-d8_512x1024_80k_cityscapes_20201215_053728-3c8893b9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_80k_cityscapes/dmnet_r50-d8_512x1024_80k_cityscapes-20201215_053728.log.json)     |
+| DMNet  | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 79.64 |         80.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_80k_cityscapes/dmnet_r101-d8_512x1024_80k_cityscapes_20201215_031718-fa081cb8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_80k_cityscapes/dmnet_r101-d8_512x1024_80k_cityscapes-20201215_031718.log.json) |
+| DMNet  | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 79.22 |         80.55 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_80k_cityscapes/dmnet_r50-d8_769x769_80k_cityscapes_20201215_034006-6060840e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_80k_cityscapes/dmnet_r50-d8_769x769_80k_cityscapes-20201215_034006.log.json)         |
+| DMNet  | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 79.19 |         80.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_80k_cityscapes/dmnet_r101-d8_769x769_80k_cityscapes_20201215_082810-7f0de59a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_80k_cityscapes/dmnet_r101-d8_769x769_80k_cityscapes-20201215_082810.log.json)     |
+
+### ADE20K
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DMNet  | R-50-D8  | 512x512   |   80000 | 9.4      | 20.95          | V100   | 42.37 |         43.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_80k_ade20k/dmnet_r50-d8_512x512_80k_ade20k_20201215_144744-f89092a6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_80k_ade20k/dmnet_r50-d8_512x512_80k_ade20k-20201215_144744.log.json)         |
+| DMNet  | R-101-D8 | 512x512   |   80000 | 13.0     | 13.88          | V100   | 45.34 |         46.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_80k_ade20k/dmnet_r101-d8_512x512_80k_ade20k_20201215_104812-bfa45311.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_80k_ade20k/dmnet_r101-d8_512x512_80k_ade20k-20201215_104812.log.json)     |
+| DMNet  | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 43.15 |         44.17 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_160k_ade20k/dmnet_r50-d8_512x512_160k_ade20k_20201215_115313-025ab3f9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_160k_ade20k/dmnet_r50-d8_512x512_160k_ade20k-20201215_115313.log.json)     |
+| DMNet  | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 45.42 |         46.76 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_160k_ade20k/dmnet_r101-d8_512x512_160k_ade20k_20201215_111145-a0bc02ef.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_160k_ade20k/dmnet_r101-d8_512x512_160k_ade20k-20201215_111145.log.json) |
+
 ## Citation
 
 ```bibtex
@@ -33,27 +57,3 @@ month = {October},
 year = {2019}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DMNet  | R-50-D8  | 512x1024  |   40000 | 7.0      | 3.66           | 77.78 |         79.14 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_40k_cityscapes/dmnet_r50-d8_512x1024_40k_cityscapes_20201215_042326-615373cf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_40k_cityscapes/dmnet_r50-d8_512x1024_40k_cityscapes-20201215_042326.log.json)     |
-| DMNet  | R-101-D8 | 512x1024  |   40000 | 10.6     | 2.54           | 78.37 |         79.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_40k_cityscapes/dmnet_r101-d8_512x1024_40k_cityscapes_20201215_043100-8291e976.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_40k_cityscapes/dmnet_r101-d8_512x1024_40k_cityscapes-20201215_043100.log.json) |
-| DMNet  | R-50-D8  | 769x769   |   40000 | 7.9      | 1.57           | 78.49 |         80.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_40k_cityscapes/dmnet_r50-d8_769x769_40k_cityscapes_20201215_093706-e7f0e23e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_40k_cityscapes/dmnet_r50-d8_769x769_40k_cityscapes-20201215_093706.log.json)         |
-| DMNet  | R-101-D8 | 769x769   |   40000 | 12.0     | 1.01           | 77.62 |         78.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_40k_cityscapes/dmnet_r101-d8_769x769_40k_cityscapes_20201215_081348-a74261f6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_40k_cityscapes/dmnet_r101-d8_769x769_40k_cityscapes-20201215_081348.log.json)     |
-| DMNet  | R-50-D8  | 512x1024  |   80000 | -        | -              | 79.07 |         80.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_80k_cityscapes/dmnet_r50-d8_512x1024_80k_cityscapes_20201215_053728-3c8893b9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_80k_cityscapes/dmnet_r50-d8_512x1024_80k_cityscapes-20201215_053728.log.json)     |
-| DMNet  | R-101-D8 | 512x1024  |   80000 | -        | -              | 79.64 |         80.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_80k_cityscapes/dmnet_r101-d8_512x1024_80k_cityscapes_20201215_031718-fa081cb8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_80k_cityscapes/dmnet_r101-d8_512x1024_80k_cityscapes-20201215_031718.log.json) |
-| DMNet  | R-50-D8  | 769x769   |   80000 | -        | -              | 79.22 |         80.55 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_80k_cityscapes/dmnet_r50-d8_769x769_80k_cityscapes_20201215_034006-6060840e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_80k_cityscapes/dmnet_r50-d8_769x769_80k_cityscapes-20201215_034006.log.json)         |
-| DMNet  | R-101-D8 | 769x769   |   80000 | -        | -              | 79.19 |         80.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_80k_cityscapes/dmnet_r101-d8_769x769_80k_cityscapes_20201215_082810-7f0de59a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_80k_cityscapes/dmnet_r101-d8_769x769_80k_cityscapes-20201215_082810.log.json)     |
-
-### ADE20K
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DMNet  | R-50-D8  | 512x512   |   80000 | 9.4      | 20.95          | 42.37 |         43.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_80k_ade20k/dmnet_r50-d8_512x512_80k_ade20k_20201215_144744-f89092a6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_80k_ade20k/dmnet_r50-d8_512x512_80k_ade20k-20201215_144744.log.json)         |
-| DMNet  | R-101-D8 | 512x512   |   80000 | 13.0     | 13.88          | 45.34 |         46.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_80k_ade20k/dmnet_r101-d8_512x512_80k_ade20k_20201215_104812-bfa45311.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_80k_ade20k/dmnet_r101-d8_512x512_80k_ade20k-20201215_104812.log.json)     |
-| DMNet  | R-50-D8  | 512x512   |  160000 | -        | -              | 43.15 |         44.17 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_160k_ade20k/dmnet_r50-d8_512x512_160k_ade20k_20201215_115313-025ab3f9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_160k_ade20k/dmnet_r50-d8_512x512_160k_ade20k-20201215_115313.log.json)     |
-| DMNet  | R-101-D8 | 512x512   |  160000 | -        | -              | 45.42 |         46.76 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_160k_ade20k/dmnet_r101-d8_512x512_160k_ade20k_20201215_111145-a0bc02ef.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_160k_ade20k/dmnet_r101-d8_512x512_160k_ade20k-20201215_111145.log.json) |
diff --git a/configs/dmnet/dmnet.yml b/configs/dmnet/dmnet.yml
deleted file mode 100644
index dfb80ba7e1..0000000000
--- a/configs/dmnet/dmnet.yml
+++ /dev/null
@@ -1,232 +0,0 @@
-Collections:
-- Name: DMNet
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-  Paper:
-    URL: https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf
-    Title: Dynamic Multi-scale Filters for Semantic Segmentation
-  README: configs/dmnet/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dm_head.py#L93
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/Junjun2016/DMNet
-Models:
-- Name: dmnet_r50-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: DMNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 273.22
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 7.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.78
-      mIoU(ms+flip): 79.14
-  Config: configs/dmnet/dmnet_r50-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_40k_cityscapes/dmnet_r50-d8_512x1024_40k_cityscapes_20201215_042326-615373cf.pth
-- Name: dmnet_r101-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: DMNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 393.7
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 10.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.37
-      mIoU(ms+flip): 79.72
-  Config: configs/dmnet/dmnet_r101-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_40k_cityscapes/dmnet_r101-d8_512x1024_40k_cityscapes_20201215_043100-8291e976.pth
-- Name: dmnet_r50-d8_4xb2-40k_cityscapes-769x769
-  In Collection: DMNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 636.94
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 7.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.49
-      mIoU(ms+flip): 80.27
-  Config: configs/dmnet/dmnet_r50-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_40k_cityscapes/dmnet_r50-d8_769x769_40k_cityscapes_20201215_093706-e7f0e23e.pth
-- Name: dmnet_r101-d8_4xb2-40k_cityscapes-769x769
-  In Collection: DMNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 990.1
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 12.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.62
-      mIoU(ms+flip): 78.94
-  Config: configs/dmnet/dmnet_r101-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_40k_cityscapes/dmnet_r101-d8_769x769_40k_cityscapes_20201215_081348-a74261f6.pth
-- Name: dmnet_r50-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: DMNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.07
-      mIoU(ms+flip): 80.22
-  Config: configs/dmnet/dmnet_r50-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_80k_cityscapes/dmnet_r50-d8_512x1024_80k_cityscapes_20201215_053728-3c8893b9.pth
-- Name: dmnet_r101-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: DMNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.64
-      mIoU(ms+flip): 80.67
-  Config: configs/dmnet/dmnet_r101-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_80k_cityscapes/dmnet_r101-d8_512x1024_80k_cityscapes_20201215_031718-fa081cb8.pth
-- Name: dmnet_r50-d8_4xb2-80k_cityscapes-769x769
-  In Collection: DMNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.22
-      mIoU(ms+flip): 80.55
-  Config: configs/dmnet/dmnet_r50-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_80k_cityscapes/dmnet_r50-d8_769x769_80k_cityscapes_20201215_034006-6060840e.pth
-- Name: dmnet_r101-d8_4xb2-80k_cityscapes-769x769
-  In Collection: DMNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.19
-      mIoU(ms+flip): 80.65
-  Config: configs/dmnet/dmnet_r101-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_80k_cityscapes/dmnet_r101-d8_769x769_80k_cityscapes_20201215_082810-7f0de59a.pth
-- Name: dmnet_r50-d8_4xb4-80k_ade20k-512x512
-  In Collection: DMNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 47.73
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.4
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.37
-      mIoU(ms+flip): 43.62
-  Config: configs/dmnet/dmnet_r50-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_80k_ade20k/dmnet_r50-d8_512x512_80k_ade20k_20201215_144744-f89092a6.pth
-- Name: dmnet_r101-d8_4xb4-80k_ade20k-512x512
-  In Collection: DMNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 72.05
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 13.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.34
-      mIoU(ms+flip): 46.13
-  Config: configs/dmnet/dmnet_r101-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_80k_ade20k/dmnet_r101-d8_512x512_80k_ade20k_20201215_104812-bfa45311.pth
-- Name: dmnet_r50-d8_4xb4-160k_ade20k-512x512
-  In Collection: DMNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.15
-      mIoU(ms+flip): 44.17
-  Config: configs/dmnet/dmnet_r50-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_160k_ade20k/dmnet_r50-d8_512x512_160k_ade20k_20201215_115313-025ab3f9.pth
-- Name: dmnet_r101-d8_4xb4-160k_ade20k-512x512
-  In Collection: DMNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.42
-      mIoU(ms+flip): 46.76
-  Config: configs/dmnet/dmnet_r101-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_160k_ade20k/dmnet_r101-d8_512x512_160k_ade20k_20201215_111145-a0bc02ef.pth
diff --git a/configs/dmnet/metafile.yaml b/configs/dmnet/metafile.yaml
new file mode 100644
index 0000000000..7f5e536753
--- /dev/null
+++ b/configs/dmnet/metafile.yaml
@@ -0,0 +1,296 @@
+Collections:
+- Name: DMNet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - ADE20K
+  Paper:
+    Title: Dynamic Multi-scale Filters for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf
+  README: configs/dmnet/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: dmnet_r50-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: DMNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.78
+      mIoU(ms+flip): 79.14
+  Config: configs/dmnet/dmnet_r50-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DMNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_40k_cityscapes/dmnet_r50-d8_512x1024_40k_cityscapes_20201215_042326-615373cf.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_40k_cityscapes/dmnet_r50-d8_512x1024_40k_cityscapes-20201215_042326.log.json
+  Paper:
+    Title: Dynamic Multi-scale Filters for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dm_head.py#L93
+  Framework: PyTorch
+- Name: dmnet_r101-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: DMNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.37
+      mIoU(ms+flip): 79.72
+  Config: configs/dmnet/dmnet_r101-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DMNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_40k_cityscapes/dmnet_r101-d8_512x1024_40k_cityscapes_20201215_043100-8291e976.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_40k_cityscapes/dmnet_r101-d8_512x1024_40k_cityscapes-20201215_043100.log.json
+  Paper:
+    Title: Dynamic Multi-scale Filters for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dm_head.py#L93
+  Framework: PyTorch
+- Name: dmnet_r50-d8_4xb2-40k_cityscapes-769x769
+  In Collection: DMNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.49
+      mIoU(ms+flip): 80.27
+  Config: configs/dmnet/dmnet_r50-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DMNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_40k_cityscapes/dmnet_r50-d8_769x769_40k_cityscapes_20201215_093706-e7f0e23e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_40k_cityscapes/dmnet_r50-d8_769x769_40k_cityscapes-20201215_093706.log.json
+  Paper:
+    Title: Dynamic Multi-scale Filters for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dm_head.py#L93
+  Framework: PyTorch
+- Name: dmnet_r101-d8_4xb2-40k_cityscapes-769x769
+  In Collection: DMNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.62
+      mIoU(ms+flip): 78.94
+  Config: configs/dmnet/dmnet_r101-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DMNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 12.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_40k_cityscapes/dmnet_r101-d8_769x769_40k_cityscapes_20201215_081348-a74261f6.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_40k_cityscapes/dmnet_r101-d8_769x769_40k_cityscapes-20201215_081348.log.json
+  Paper:
+    Title: Dynamic Multi-scale Filters for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dm_head.py#L93
+  Framework: PyTorch
+- Name: dmnet_r50-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: DMNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.07
+      mIoU(ms+flip): 80.22
+  Config: configs/dmnet/dmnet_r50-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DMNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_80k_cityscapes/dmnet_r50-d8_512x1024_80k_cityscapes_20201215_053728-3c8893b9.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_80k_cityscapes/dmnet_r50-d8_512x1024_80k_cityscapes-20201215_053728.log.json
+  Paper:
+    Title: Dynamic Multi-scale Filters for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dm_head.py#L93
+  Framework: PyTorch
+- Name: dmnet_r101-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: DMNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.64
+      mIoU(ms+flip): 80.67
+  Config: configs/dmnet/dmnet_r101-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DMNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_80k_cityscapes/dmnet_r101-d8_512x1024_80k_cityscapes_20201215_031718-fa081cb8.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_80k_cityscapes/dmnet_r101-d8_512x1024_80k_cityscapes-20201215_031718.log.json
+  Paper:
+    Title: Dynamic Multi-scale Filters for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dm_head.py#L93
+  Framework: PyTorch
+- Name: dmnet_r50-d8_4xb2-80k_cityscapes-769x769
+  In Collection: DMNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.22
+      mIoU(ms+flip): 80.55
+  Config: configs/dmnet/dmnet_r50-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DMNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_80k_cityscapes/dmnet_r50-d8_769x769_80k_cityscapes_20201215_034006-6060840e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_80k_cityscapes/dmnet_r50-d8_769x769_80k_cityscapes-20201215_034006.log.json
+  Paper:
+    Title: Dynamic Multi-scale Filters for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dm_head.py#L93
+  Framework: PyTorch
+- Name: dmnet_r101-d8_4xb2-80k_cityscapes-769x769
+  In Collection: DMNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.19
+      mIoU(ms+flip): 80.65
+  Config: configs/dmnet/dmnet_r101-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DMNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_80k_cityscapes/dmnet_r101-d8_769x769_80k_cityscapes_20201215_082810-7f0de59a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_80k_cityscapes/dmnet_r101-d8_769x769_80k_cityscapes-20201215_082810.log.json
+  Paper:
+    Title: Dynamic Multi-scale Filters for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dm_head.py#L93
+  Framework: PyTorch
+- Name: dmnet_r50-d8_4xb4-80k_ade20k-512x512
+  In Collection: DMNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.37
+      mIoU(ms+flip): 43.62
+  Config: configs/dmnet/dmnet_r50-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DMNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.4
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_80k_ade20k/dmnet_r50-d8_512x512_80k_ade20k_20201215_144744-f89092a6.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_80k_ade20k/dmnet_r50-d8_512x512_80k_ade20k-20201215_144744.log.json
+  Paper:
+    Title: Dynamic Multi-scale Filters for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dm_head.py#L93
+  Framework: PyTorch
+- Name: dmnet_r101-d8_4xb4-80k_ade20k-512x512
+  In Collection: DMNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.34
+      mIoU(ms+flip): 46.13
+  Config: configs/dmnet/dmnet_r101-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DMNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 13.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_80k_ade20k/dmnet_r101-d8_512x512_80k_ade20k_20201215_104812-bfa45311.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_80k_ade20k/dmnet_r101-d8_512x512_80k_ade20k-20201215_104812.log.json
+  Paper:
+    Title: Dynamic Multi-scale Filters for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dm_head.py#L93
+  Framework: PyTorch
+- Name: dmnet_r50-d8_4xb4-160k_ade20k-512x512
+  In Collection: DMNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.15
+      mIoU(ms+flip): 44.17
+  Config: configs/dmnet/dmnet_r50-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DMNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_160k_ade20k/dmnet_r50-d8_512x512_160k_ade20k_20201215_115313-025ab3f9.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_160k_ade20k/dmnet_r50-d8_512x512_160k_ade20k-20201215_115313.log.json
+  Paper:
+    Title: Dynamic Multi-scale Filters for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dm_head.py#L93
+  Framework: PyTorch
+- Name: dmnet_r101-d8_4xb4-160k_ade20k-512x512
+  In Collection: DMNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.42
+      mIoU(ms+flip): 46.76
+  Config: configs/dmnet/dmnet_r101-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DMNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_160k_ade20k/dmnet_r101-d8_512x512_160k_ade20k_20201215_111145-a0bc02ef.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_160k_ade20k/dmnet_r101-d8_512x512_160k_ade20k-20201215_111145.log.json
+  Paper:
+    Title: Dynamic Multi-scale Filters for Semantic Segmentation
+    URL: https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dm_head.py#L93
+  Framework: PyTorch
diff --git a/configs/dnlnet/README.md b/configs/dnlnet/README.md
index ab24549ed6..12338c730c 100644
--- a/configs/dnlnet/README.md
+++ b/configs/dnlnet/README.md
@@ -1,6 +1,6 @@
 # DNLNet
 
-[Disentangled Non-Local Neural Networks](https://arxiv.org/abs/2006.06668)
+> [Disentangled Non-Local Neural Networks](https://arxiv.org/abs/2006.06668)
 
 ## Introduction
 
@@ -22,7 +22,31 @@ The non-local block is a popular module for strengthening the context modeling a
 <img src="https://user-images.githubusercontent.com/24582831/142900944-b8d93301-d2ce-488e-a461-b0813f96be49.png" width="70%"/>
 </div>
 
-## Citation
+## Results and models (in progress)
+
+### Cityscapes
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                     |
+| ------ | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DNLNet | R-50-D8  | 512x1024  |   40000 |      7.3 | 2.56           | V100   | 78.61 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_40k_cityscapes/dnl_r50-d8_512x1024_40k_cityscapes_20200904_233629-53d4ea93.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_40k_cityscapes/dnl_r50-d8_512x1024_40k_cityscapes-20200904_233629.log.json)     |
+| DNLNet | R-101-D8 | 512x1024  |   40000 |     10.9 | 1.96           | V100   | 78.31 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_40k_cityscapes/dnl_r101-d8_512x1024_40k_cityscapes_20200904_233629-9928ffef.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_40k_cityscapes/dnl_r101-d8_512x1024_40k_cityscapes-20200904_233629.log.json) |
+| DNLNet | R-50-D8  | 769x769   |   40000 |      9.2 | 1.50           | V100   | 78.44 | 80.27         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_40k_cityscapes/dnl_r50-d8_769x769_40k_cityscapes_20200820_232206-0f283785.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_40k_cityscapes/dnl_r50-d8_769x769_40k_cityscapes-20200820_232206.log.json)         |
+| DNLNet | R-101-D8 | 769x769   |   40000 |     12.6 | 1.02           | V100   | 76.39 | 77.77         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_40k_cityscapes/dnl_r101-d8_769x769_40k_cityscapes_20200820_171256-76c596df.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_40k_cityscapes/dnl_r101-d8_769x769_40k_cityscapes-20200820_171256.log.json)     |
+| DNLNet | R-50-D8  | 512x1024  |   80000 |        - | -              | V100   | 79.33 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_80k_cityscapes/dnl_r50-d8_512x1024_80k_cityscapes_20200904_233629-58b2f778.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_80k_cityscapes/dnl_r50-d8_512x1024_80k_cityscapes-20200904_233629.log.json)     |
+| DNLNet | R-101-D8 | 512x1024  |   80000 |        - | -              | V100   | 80.41 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_80k_cityscapes/dnl_r101-d8_512x1024_80k_cityscapes_20200904_233629-758e2dd4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_80k_cityscapes/dnl_r101-d8_512x1024_80k_cityscapes-20200904_233629.log.json) |
+| DNLNet | R-50-D8  | 769x769   |   80000 |        - | -              | V100   | 79.36 | 80.70         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_80k_cityscapes/dnl_r50-d8_769x769_80k_cityscapes_20200820_011925-366bc4c7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_80k_cityscapes/dnl_r50-d8_769x769_80k_cityscapes-20200820_011925.log.json)         |
+| DNLNet | R-101-D8 | 769x769   |   80000 |        - | -              | V100   | 79.41 | 80.68         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_80k_cityscapes/dnl_r101-d8_769x769_80k_cityscapes_20200821_051111-95ff84ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_80k_cityscapes/dnl_r101-d8_769x769_80k_cityscapes-20200821_051111.log.json)     |
+
+### ADE20K
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                     | download                                                                                                                                                                                                                                                                                                                     |
+| ------ | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DNLNet | R-50-D8  | 512x512   |   80000 |      8.8 | 20.66          | V100   | 41.76 | 42.99         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_80k_ade20k/dnl_r50-d8_512x512_80k_ade20k_20200826_183354-1cf6e0c1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_80k_ade20k/dnl_r50-d8_512x512_80k_ade20k-20200826_183354.log.json)         |
+| DNLNet | R-101-D8 | 512x512   |   80000 |     12.8 | 12.54          | V100   | 43.76 | 44.91         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_80k_ade20k/dnl_r101-d8_512x512_80k_ade20k_20200826_183354-d820d6ea.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_80k_ade20k/dnl_r101-d8_512x512_80k_ade20k-20200826_183354.log.json)     |
+| DNLNet | R-50-D8  | 512x512   |  160000 |        - | -              | V100   | 41.87 | 43.01         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_160k_ade20k/dnl_r50-d8_512x512_160k_ade20k_20200826_183350-37837798.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_160k_ade20k/dnl_r50-d8_512x512_160k_ade20k-20200826_183350.log.json)     |
+| DNLNet | R-101-D8 | 512x512   |  160000 |        - | -              | V100   | 44.25 | 45.78         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_160k_ade20k/dnl_r101-d8_512x512_160k_ade20k_20200826_183350-ed522c61.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_160k_ade20k/dnl_r101-d8_512x512_160k_ade20k-20200826_183350.log.json) |
+
+## Notes
 
 This example is to reproduce ["Disentangled Non-Local Neural Networks"](https://arxiv.org/abs/2006.06668) for semantic segmentation. It is still in progress.
 
@@ -36,27 +60,3 @@ This example is to reproduce ["Disentangled Non-Local Neural Networks"](https://
     booktitle={ECCV}
 }
 ```
-
-## Results and models (in progress)
-
-### Cityscapes
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                     |
-| ------ | -------- | --------- | ------: | -------: | -------------- | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DNLNet | R-50-D8  | 512x1024  |   40000 |      7.3 | 2.56           | 78.61 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_40k_cityscapes/dnl_r50-d8_512x1024_40k_cityscapes_20200904_233629-53d4ea93.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_40k_cityscapes/dnl_r50-d8_512x1024_40k_cityscapes-20200904_233629.log.json)     |
-| DNLNet | R-101-D8 | 512x1024  |   40000 |     10.9 | 1.96           | 78.31 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_40k_cityscapes/dnl_r101-d8_512x1024_40k_cityscapes_20200904_233629-9928ffef.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_40k_cityscapes/dnl_r101-d8_512x1024_40k_cityscapes-20200904_233629.log.json) |
-| DNLNet | R-50-D8  | 769x769   |   40000 |      9.2 | 1.50           | 78.44 | 80.27         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_40k_cityscapes/dnl_r50-d8_769x769_40k_cityscapes_20200820_232206-0f283785.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_40k_cityscapes/dnl_r50-d8_769x769_40k_cityscapes-20200820_232206.log.json)         |
-| DNLNet | R-101-D8 | 769x769   |   40000 |     12.6 | 1.02           | 76.39 | 77.77         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_40k_cityscapes/dnl_r101-d8_769x769_40k_cityscapes_20200820_171256-76c596df.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_40k_cityscapes/dnl_r101-d8_769x769_40k_cityscapes-20200820_171256.log.json)     |
-| DNLNet | R-50-D8  | 512x1024  |   80000 |        - | -              | 79.33 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_80k_cityscapes/dnl_r50-d8_512x1024_80k_cityscapes_20200904_233629-58b2f778.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_80k_cityscapes/dnl_r50-d8_512x1024_80k_cityscapes-20200904_233629.log.json)     |
-| DNLNet | R-101-D8 | 512x1024  |   80000 |        - | -              | 80.41 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_80k_cityscapes/dnl_r101-d8_512x1024_80k_cityscapes_20200904_233629-758e2dd4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_80k_cityscapes/dnl_r101-d8_512x1024_80k_cityscapes-20200904_233629.log.json) |
-| DNLNet | R-50-D8  | 769x769   |   80000 |        - | -              | 79.36 | 80.70         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_80k_cityscapes/dnl_r50-d8_769x769_80k_cityscapes_20200820_011925-366bc4c7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_80k_cityscapes/dnl_r50-d8_769x769_80k_cityscapes-20200820_011925.log.json)         |
-| DNLNet | R-101-D8 | 769x769   |   80000 |        - | -              | 79.41 | 80.68         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_80k_cityscapes/dnl_r101-d8_769x769_80k_cityscapes_20200821_051111-95ff84ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_80k_cityscapes/dnl_r101-d8_769x769_80k_cityscapes-20200821_051111.log.json)     |
-
-### ADE20K
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                     | download                                                                                                                                                                                                                                                                                                                     |
-| ------ | -------- | --------- | ------: | -------: | -------------- | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DNLNet | R-50-D8  | 512x512   |   80000 |      8.8 | 20.66          | 41.76 | 42.99         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_80k_ade20k/dnl_r50-d8_512x512_80k_ade20k_20200826_183354-1cf6e0c1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_80k_ade20k/dnl_r50-d8_512x512_80k_ade20k-20200826_183354.log.json)         |
-| DNLNet | R-101-D8 | 512x512   |   80000 |     12.8 | 12.54          | 43.76 | 44.91         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_80k_ade20k/dnl_r101-d8_512x512_80k_ade20k_20200826_183354-d820d6ea.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_80k_ade20k/dnl_r101-d8_512x512_80k_ade20k-20200826_183354.log.json)     |
-| DNLNet | R-50-D8  | 512x512   |  160000 |        - | -              | 41.87 | 43.01         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_160k_ade20k/dnl_r50-d8_512x512_160k_ade20k_20200826_183350-37837798.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_160k_ade20k/dnl_r50-d8_512x512_160k_ade20k-20200826_183350.log.json)     |
-| DNLNet | R-101-D8 | 512x512   |  160000 |        - | -              | 44.25 | 45.78         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_160k_ade20k/dnl_r101-d8_512x512_160k_ade20k_20200826_183350-ed522c61.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_160k_ade20k/dnl_r101-d8_512x512_160k_ade20k-20200826_183350.log.json) |
diff --git a/configs/dnlnet/dnlnet.yml b/configs/dnlnet/dnlnet.yml
deleted file mode 100644
index ae65dbbaca..0000000000
--- a/configs/dnlnet/dnlnet.yml
+++ /dev/null
@@ -1,228 +0,0 @@
-Collections:
-- Name: DNLNet
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-  Paper:
-    URL: https://arxiv.org/abs/2006.06668
-    Title: Disentangled Non-Local Neural Networks
-  README: configs/dnlnet/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dnl_head.py#L88
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/yinmh17/DNL-Semantic-Segmentation
-Models:
-- Name: dnl_r50-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: DNLNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 390.62
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 7.3
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.61
-  Config: configs/dnlnet/dnl_r50-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_40k_cityscapes/dnl_r50-d8_512x1024_40k_cityscapes_20200904_233629-53d4ea93.pth
-- Name: dnl_r101-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: DNLNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 510.2
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 10.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.31
-  Config: configs/dnlnet/dnl_r101-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_40k_cityscapes/dnl_r101-d8_512x1024_40k_cityscapes_20200904_233629-9928ffef.pth
-- Name: dnl_r50-d8_4xb2-40k_cityscapes-769x769
-  In Collection: DNLNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 666.67
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 9.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.44
-      mIoU(ms+flip): 80.27
-  Config: configs/dnlnet/dnl_r50-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_40k_cityscapes/dnl_r50-d8_769x769_40k_cityscapes_20200820_232206-0f283785.pth
-- Name: dnl_r101-d8_4xb2-40k_cityscapes-769x769
-  In Collection: DNLNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 980.39
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 12.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.39
-      mIoU(ms+flip): 77.77
-  Config: configs/dnlnet/dnl_r101-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_40k_cityscapes/dnl_r101-d8_769x769_40k_cityscapes_20200820_171256-76c596df.pth
-- Name: dnl_r50-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: DNLNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.33
-  Config: configs/dnlnet/dnl_r50-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_80k_cityscapes/dnl_r50-d8_512x1024_80k_cityscapes_20200904_233629-58b2f778.pth
-- Name: dnl_r101-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: DNLNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.41
-  Config: configs/dnlnet/dnl_r101-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_80k_cityscapes/dnl_r101-d8_512x1024_80k_cityscapes_20200904_233629-758e2dd4.pth
-- Name: dnl_r50-d8_4xb2-80k_cityscapes-769x769
-  In Collection: DNLNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.36
-      mIoU(ms+flip): 80.7
-  Config: configs/dnlnet/dnl_r50-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_80k_cityscapes/dnl_r50-d8_769x769_80k_cityscapes_20200820_011925-366bc4c7.pth
-- Name: dnl_r101-d8_4xb2-80k_cityscapes-769x769
-  In Collection: DNLNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.41
-      mIoU(ms+flip): 80.68
-  Config: configs/dnlnet/dnl_r101-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_80k_cityscapes/dnl_r101-d8_769x769_80k_cityscapes_20200821_051111-95ff84ab.pth
-- Name: dnl_r50-d8_4xb4-80k_ade20k-512x512
-  In Collection: DNLNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 48.4
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 8.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 41.76
-      mIoU(ms+flip): 42.99
-  Config: configs/dnlnet/dnl_r50-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_80k_ade20k/dnl_r50-d8_512x512_80k_ade20k_20200826_183354-1cf6e0c1.pth
-- Name: dnl_r101-d8_4xb4-80k_ade20k-512x512
-  In Collection: DNLNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 79.74
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 12.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.76
-      mIoU(ms+flip): 44.91
-  Config: configs/dnlnet/dnl_r101-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_80k_ade20k/dnl_r101-d8_512x512_80k_ade20k_20200826_183354-d820d6ea.pth
-- Name: dnl_r50-d8_4xb4-160k_ade20k-512x512
-  In Collection: DNLNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 41.87
-      mIoU(ms+flip): 43.01
-  Config: configs/dnlnet/dnl_r50-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_160k_ade20k/dnl_r50-d8_512x512_160k_ade20k_20200826_183350-37837798.pth
-- Name: dnl_r101-d8_4xb4-160k_ade20k-512x512
-  In Collection: DNLNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 44.25
-      mIoU(ms+flip): 45.78
-  Config: configs/dnlnet/dnl_r101-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_160k_ade20k/dnl_r101-d8_512x512_160k_ade20k_20200826_183350-ed522c61.pth
diff --git a/configs/dnlnet/metafile.yaml b/configs/dnlnet/metafile.yaml
new file mode 100644
index 0000000000..22e48d3dc5
--- /dev/null
+++ b/configs/dnlnet/metafile.yaml
@@ -0,0 +1,292 @@
+Collections:
+- Name: DNLNet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - ADE20K
+  Paper:
+    Title: Disentangled Non-Local Neural Networks
+    URL: https://arxiv.org/abs/2006.06668
+  README: configs/dnlnet/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: dnl_r50-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: DNLNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.61
+  Config: configs/dnlnet/dnl_r50-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DNLNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.3
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_40k_cityscapes/dnl_r50-d8_512x1024_40k_cityscapes_20200904_233629-53d4ea93.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_40k_cityscapes/dnl_r50-d8_512x1024_40k_cityscapes-20200904_233629.log.json
+  Paper:
+    Title: Disentangled Non-Local Neural Networks
+    URL: https://arxiv.org/abs/2006.06668
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dnl_head.py#L88
+  Framework: PyTorch
+- Name: dnl_r101-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: DNLNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.31
+  Config: configs/dnlnet/dnl_r101-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DNLNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_40k_cityscapes/dnl_r101-d8_512x1024_40k_cityscapes_20200904_233629-9928ffef.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_40k_cityscapes/dnl_r101-d8_512x1024_40k_cityscapes-20200904_233629.log.json
+  Paper:
+    Title: Disentangled Non-Local Neural Networks
+    URL: https://arxiv.org/abs/2006.06668
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dnl_head.py#L88
+  Framework: PyTorch
+- Name: dnl_r50-d8_4xb2-40k_cityscapes-769x769
+  In Collection: DNLNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.44
+      mIoU(ms+flip): 80.27
+  Config: configs/dnlnet/dnl_r50-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DNLNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_40k_cityscapes/dnl_r50-d8_769x769_40k_cityscapes_20200820_232206-0f283785.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_40k_cityscapes/dnl_r50-d8_769x769_40k_cityscapes-20200820_232206.log.json
+  Paper:
+    Title: Disentangled Non-Local Neural Networks
+    URL: https://arxiv.org/abs/2006.06668
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dnl_head.py#L88
+  Framework: PyTorch
+- Name: dnl_r101-d8_4xb2-40k_cityscapes-769x769
+  In Collection: DNLNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.39
+      mIoU(ms+flip): 77.77
+  Config: configs/dnlnet/dnl_r101-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DNLNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 12.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_40k_cityscapes/dnl_r101-d8_769x769_40k_cityscapes_20200820_171256-76c596df.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_40k_cityscapes/dnl_r101-d8_769x769_40k_cityscapes-20200820_171256.log.json
+  Paper:
+    Title: Disentangled Non-Local Neural Networks
+    URL: https://arxiv.org/abs/2006.06668
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dnl_head.py#L88
+  Framework: PyTorch
+- Name: dnl_r50-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: DNLNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.33
+  Config: configs/dnlnet/dnl_r50-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DNLNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_80k_cityscapes/dnl_r50-d8_512x1024_80k_cityscapes_20200904_233629-58b2f778.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_80k_cityscapes/dnl_r50-d8_512x1024_80k_cityscapes-20200904_233629.log.json
+  Paper:
+    Title: Disentangled Non-Local Neural Networks
+    URL: https://arxiv.org/abs/2006.06668
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dnl_head.py#L88
+  Framework: PyTorch
+- Name: dnl_r101-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: DNLNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.41
+  Config: configs/dnlnet/dnl_r101-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DNLNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_80k_cityscapes/dnl_r101-d8_512x1024_80k_cityscapes_20200904_233629-758e2dd4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_80k_cityscapes/dnl_r101-d8_512x1024_80k_cityscapes-20200904_233629.log.json
+  Paper:
+    Title: Disentangled Non-Local Neural Networks
+    URL: https://arxiv.org/abs/2006.06668
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dnl_head.py#L88
+  Framework: PyTorch
+- Name: dnl_r50-d8_4xb2-80k_cityscapes-769x769
+  In Collection: DNLNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.36
+      mIoU(ms+flip): 80.7
+  Config: configs/dnlnet/dnl_r50-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - DNLNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_80k_cityscapes/dnl_r50-d8_769x769_80k_cityscapes_20200820_011925-366bc4c7.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_80k_cityscapes/dnl_r50-d8_769x769_80k_cityscapes-20200820_011925.log.json
+  Paper:
+    Title: Disentangled Non-Local Neural Networks
+    URL: https://arxiv.org/abs/2006.06668
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dnl_head.py#L88
+  Framework: PyTorch
+- Name: dnl_r101-d8_4xb2-80k_cityscapes-769x769
+  In Collection: DNLNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.41
+      mIoU(ms+flip): 80.68
+  Config: configs/dnlnet/dnl_r101-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - DNLNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_80k_cityscapes/dnl_r101-d8_769x769_80k_cityscapes_20200821_051111-95ff84ab.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_80k_cityscapes/dnl_r101-d8_769x769_80k_cityscapes-20200821_051111.log.json
+  Paper:
+    Title: Disentangled Non-Local Neural Networks
+    URL: https://arxiv.org/abs/2006.06668
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dnl_head.py#L88
+  Framework: PyTorch
+- Name: dnl_r50-d8_4xb4-80k_ade20k-512x512
+  In Collection: DNLNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 41.76
+      mIoU(ms+flip): 42.99
+  Config: configs/dnlnet/dnl_r50-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DNLNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_80k_ade20k/dnl_r50-d8_512x512_80k_ade20k_20200826_183354-1cf6e0c1.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_80k_ade20k/dnl_r50-d8_512x512_80k_ade20k-20200826_183354.log.json
+  Paper:
+    Title: Disentangled Non-Local Neural Networks
+    URL: https://arxiv.org/abs/2006.06668
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dnl_head.py#L88
+  Framework: PyTorch
+- Name: dnl_r101-d8_4xb4-80k_ade20k-512x512
+  In Collection: DNLNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.76
+      mIoU(ms+flip): 44.91
+  Config: configs/dnlnet/dnl_r101-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DNLNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 12.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_80k_ade20k/dnl_r101-d8_512x512_80k_ade20k_20200826_183354-d820d6ea.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_80k_ade20k/dnl_r101-d8_512x512_80k_ade20k-20200826_183354.log.json
+  Paper:
+    Title: Disentangled Non-Local Neural Networks
+    URL: https://arxiv.org/abs/2006.06668
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dnl_head.py#L88
+  Framework: PyTorch
+- Name: dnl_r50-d8_4xb4-160k_ade20k-512x512
+  In Collection: DNLNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 41.87
+      mIoU(ms+flip): 43.01
+  Config: configs/dnlnet/dnl_r50-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - DNLNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_160k_ade20k/dnl_r50-d8_512x512_160k_ade20k_20200826_183350-37837798.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_160k_ade20k/dnl_r50-d8_512x512_160k_ade20k-20200826_183350.log.json
+  Paper:
+    Title: Disentangled Non-Local Neural Networks
+    URL: https://arxiv.org/abs/2006.06668
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dnl_head.py#L88
+  Framework: PyTorch
+- Name: dnl_r101-d8_4xb4-160k_ade20k-512x512
+  In Collection: DNLNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 44.25
+      mIoU(ms+flip): 45.78
+  Config: configs/dnlnet/dnl_r101-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - DNLNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_160k_ade20k/dnl_r101-d8_512x512_160k_ade20k_20200826_183350-ed522c61.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_160k_ade20k/dnl_r101-d8_512x512_160k_ade20k-20200826_183350.log.json
+  Paper:
+    Title: Disentangled Non-Local Neural Networks
+    URL: https://arxiv.org/abs/2006.06668
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dnl_head.py#L88
+  Framework: PyTorch
diff --git a/configs/dpt/README.md b/configs/dpt/README.md
index 41d73ea57a..432d1dd226 100644
--- a/configs/dpt/README.md
+++ b/configs/dpt/README.md
@@ -1,6 +1,6 @@
 # DPT
 
-[Vision Transformer for Dense Prediction](https://arxiv.org/abs/2103.13413)
+> [Vision Transformer for Dense Prediction](https://arxiv.org/abs/2103.13413)
 
 ## Introduction
 
@@ -22,24 +22,6 @@ We introduce dense vision transformers, an architecture that leverages vision tr
 <img src="https://user-images.githubusercontent.com/24582831/142901057-00aabea5-dab4-43d3-a14a-5f73eb5dd9b9.png" width="80%"/>
 </div>
 
-## Citation
-
-```bibtex
-@article{dosoViTskiy2020,
-  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
-  author={DosoViTskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and  Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
-  journal={arXiv preprint arXiv:2010.11929},
-  year={2020}
-}
-
-@article{Ranftl2021,
-  author    = {Ren\'{e} Ranftl and Alexey Bochkovskiy and Vladlen Koltun},
-  title     = {Vision Transformers for Dense Prediction},
-  journal   = {ArXiv preprint},
-  year      = {2021},
-}
-```
-
 ## Usage
 
 To use other repositories' pre-trained models, it is necessary to convert keys.
@@ -62,6 +44,24 @@ This script convert model from `PRETRAIN_PATH` and store the converted model in
 
 ### ADE20K
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                               |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| DPT    | ViT-B    | 512x512   |  160000 | 8.09     | 10.41          | 46.97 |         48.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dpt/dpt_vit-b16_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dpt/dpt_vit-b16_512x512_160k_ade20k/dpt_vit-b16_512x512_160k_ade20k-db31cf52.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dpt/dpt_vit-b16_512x512_160k_ade20k/dpt_vit-b16_512x512_160k_ade20k-20210809_172025.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                               |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| DPT    | ViT-B    | 512x512   |  160000 | 8.09     | 10.41          | V100   | 46.97 |         48.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dpt/dpt_vit-b16_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dpt/dpt_vit-b16_512x512_160k_ade20k/dpt_vit-b16_512x512_160k_ade20k-db31cf52.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dpt/dpt_vit-b16_512x512_160k_ade20k/dpt_vit-b16_512x512_160k_ade20k-20210809_172025.log.json) |
+
+## Citation
+
+```bibtex
+@article{dosoViTskiy2020,
+  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
+  author={DosoViTskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and  Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
+  journal={arXiv preprint arXiv:2010.11929},
+  year={2020}
+}
+
+@article{Ranftl2021,
+  author    = {Ren\'{e} Ranftl and Alexey Bochkovskiy and Vladlen Koltun},
+  title     = {Vision Transformers for Dense Prediction},
+  journal   = {ArXiv preprint},
+  year      = {2021},
+}
+```
diff --git a/configs/dpt/dpt.yml b/configs/dpt/dpt.yml
deleted file mode 100644
index 32324d3459..0000000000
--- a/configs/dpt/dpt.yml
+++ /dev/null
@@ -1,37 +0,0 @@
-Collections:
-- Name: DPT
-  Metadata:
-    Training Data:
-    - ADE20K
-  Paper:
-    URL: https://arxiv.org/abs/2103.13413
-    Title: Vision Transformer for Dense Prediction
-  README: configs/dpt/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dpt_head.py#L215
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/isl-org/DPT
-Models:
-- Name: dpt_vit-b16_8xb2-160k_ade20k-512x512
-  In Collection: DPT
-  Metadata:
-    backbone: ViT-B
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 96.06
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 8.09
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 46.97
-      mIoU(ms+flip): 48.34
-  Config: configs/dpt/dpt_vit-b16_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dpt/dpt_vit-b16_512x512_160k_ade20k/dpt_vit-b16_512x512_160k_ade20k-db31cf52.pth
diff --git a/configs/dpt/metafile.yaml b/configs/dpt/metafile.yaml
new file mode 100644
index 0000000000..b721e041b6
--- /dev/null
+++ b/configs/dpt/metafile.yaml
@@ -0,0 +1,37 @@
+Collections:
+- Name: DPT
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - ADE20K
+  Paper:
+    Title: Vision Transformer for Dense Prediction
+    URL: https://arxiv.org/abs/2103.13413
+  README: configs/dpt/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: dpt_vit-b16_8xb2-160k_ade20k-512x512
+  In Collection: DPT
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 46.97
+      mIoU(ms+flip): 48.34
+  Config: configs/dpt/dpt_vit-b16_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - ViT-B
+    - DPT
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 8.09
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dpt/dpt_vit-b16_512x512_160k_ade20k/dpt_vit-b16_512x512_160k_ade20k-db31cf52.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/dpt/dpt_vit-b16_512x512_160k_ade20k/dpt_vit-b16_512x512_160k_ade20k-20210809_172025.log.json
+  Paper:
+    Title: Vision Transformer for Dense Prediction
+    URL: https://arxiv.org/abs/2103.13413
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dpt_head.py#L215
+  Framework: PyTorch
diff --git a/configs/emanet/README.md b/configs/emanet/README.md
index 5a9bfc326a..8ffaf471ca 100644
--- a/configs/emanet/README.md
+++ b/configs/emanet/README.md
@@ -1,6 +1,6 @@
 # EMANet
 
-[Expectation-Maximization Attention Networks for Semantic Segmentation](https://arxiv.org/abs/1907.13426)
+> [Expectation-Maximization Attention Networks for Semantic Segmentation](https://arxiv.org/abs/1907.13426)
 
 ## Introduction
 
@@ -22,6 +22,17 @@ Self-attention mechanism has been widely used for various tasks. It is designed
 <img src="https://user-images.githubusercontent.com/24582831/142901186-7bfe15e2-805a-420e-81b0-74f214f20a36.png" width="80%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| EMANet | R-50-D8  | 512x1024  |   80000 |      5.4 | 4.58           | V100   | 77.59 | 79.44         | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/emanet/eemanet_r50-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r50-d8_512x1024_80k_cityscapes/emanet_r50-d8_512x1024_80k_cityscapes_20200901_100301-c43fcef1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r50-d8_512x1024_80k_cityscapes/emanet_r50-d8_512x1024_80k_cityscapes-20200901_100301.log.json)     |
+| EMANet | R-101-D8 | 512x1024  |   80000 |      6.2 | 2.87           | V100   | 79.10 | 81.21         | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/emanet/emanet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r101-d8_512x1024_80k_cityscapes/emanet_r101-d8_512x1024_80k_cityscapes_20200901_100301-2d970745.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r101-d8_512x1024_80k_cityscapes/emanet_r101-d8_512x1024_80k_cityscapes-20200901_100301.log.json) |
+| EMANet | R-50-D8  | 769x769   |   80000 |      8.9 | 1.97           | V100   | 79.33 | 80.49         | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/emanet/emanet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r50-d8_769x769_80k_cityscapes/emanet_r50-d8_769x769_80k_cityscapes_20200901_100301-16f8de52.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r50-d8_769x769_80k_cityscapes/emanet_r50-d8_769x769_80k_cityscapes-20200901_100301.log.json)         |
+| EMANet | R-101-D8 | 769x769   |   80000 |     10.1 | 1.22           | V100   | 79.62 | 81.00         | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/emanet/emanet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r101-d8_769x769_80k_cityscapes/emanet_r101-d8_769x769_80k_cityscapes_20200901_100301-47a324ce.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r101-d8_769x769_80k_cityscapes/emanet_r101-d8_769x769_80k_cityscapes-20200901_100301.log.json)     |
+
 ## Citation
 
 ```bibtex
@@ -33,14 +44,3 @@ Self-attention mechanism has been widely used for various tasks. It is designed
   year={2019}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------: | -------: | -------------- | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| EMANet | R-50-D8  | 512x1024  |   80000 |      5.4 | 4.58           | 77.59 | 79.44         | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/emanet/eemanet_r50-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r50-d8_512x1024_80k_cityscapes/emanet_r50-d8_512x1024_80k_cityscapes_20200901_100301-c43fcef1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r50-d8_512x1024_80k_cityscapes/emanet_r50-d8_512x1024_80k_cityscapes-20200901_100301.log.json)     |
-| EMANet | R-101-D8 | 512x1024  |   80000 |      6.2 | 2.87           | 79.10 | 81.21         | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/emanet/emanet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r101-d8_512x1024_80k_cityscapes/emanet_r101-d8_512x1024_80k_cityscapes_20200901_100301-2d970745.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r101-d8_512x1024_80k_cityscapes/emanet_r101-d8_512x1024_80k_cityscapes-20200901_100301.log.json) |
-| EMANet | R-50-D8  | 769x769   |   80000 |      8.9 | 1.97           | 79.33 | 80.49         | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/emanet/emanet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r50-d8_769x769_80k_cityscapes/emanet_r50-d8_769x769_80k_cityscapes_20200901_100301-16f8de52.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r50-d8_769x769_80k_cityscapes/emanet_r50-d8_769x769_80k_cityscapes-20200901_100301.log.json)         |
-| EMANet | R-101-D8 | 769x769   |   80000 |     10.1 | 1.22           | 79.62 | 81.00         | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/emanet/emanet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r101-d8_769x769_80k_cityscapes/emanet_r101-d8_769x769_80k_cityscapes_20200901_100301-47a324ce.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r101-d8_769x769_80k_cityscapes/emanet_r101-d8_769x769_80k_cityscapes-20200901_100301.log.json)     |
diff --git a/configs/emanet/emanet.yml b/configs/emanet/emanet.yml
deleted file mode 100644
index ac194f2a0f..0000000000
--- a/configs/emanet/emanet.yml
+++ /dev/null
@@ -1,103 +0,0 @@
-Collections:
-- Name: EMANet
-  Metadata:
-    Training Data:
-    - Cityscapes
-  Paper:
-    URL: https://arxiv.org/abs/1907.13426
-    Title: Expectation-Maximization Attention Networks for Semantic Segmentation
-  README: configs/emanet/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ema_head.py#L80
-    Version: v0.17.0
-  Converted From:
-    Code: https://xialipku.github.io/EMANet
-Models:
-- Name: emanet_r50-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: EMANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 218.34
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 5.4
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.59
-      mIoU(ms+flip): 79.44
-  Config: configs/emanet/emanet_r50-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r50-d8_512x1024_80k_cityscapes/emanet_r50-d8_512x1024_80k_cityscapes_20200901_100301-c43fcef1.pth
-- Name: emanet_r101-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: EMANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 348.43
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 6.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.1
-      mIoU(ms+flip): 81.21
-  Config: configs/emanet/emanet_r101-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r101-d8_512x1024_80k_cityscapes/emanet_r101-d8_512x1024_80k_cityscapes_20200901_100301-2d970745.pth
-- Name: emanet_r50-d8_4xb2-80k_cityscapes-769x769
-  In Collection: EMANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 507.61
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 8.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.33
-      mIoU(ms+flip): 80.49
-  Config: configs/emanet/emanet_r50-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r50-d8_769x769_80k_cityscapes/emanet_r50-d8_769x769_80k_cityscapes_20200901_100301-16f8de52.pth
-- Name: emanet_r101-d8_4xb2-80k_cityscapes-769x769
-  In Collection: EMANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 819.67
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 10.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.62
-      mIoU(ms+flip): 81.0
-  Config: configs/emanet/emanet_r101-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r101-d8_769x769_80k_cityscapes/emanet_r101-d8_769x769_80k_cityscapes_20200901_100301-47a324ce.pth
diff --git a/configs/emanet/metafile.yaml b/configs/emanet/metafile.yaml
new file mode 100644
index 0000000000..b2a6b09ed7
--- /dev/null
+++ b/configs/emanet/metafile.yaml
@@ -0,0 +1,109 @@
+Collections:
+- Name: EMANet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+  Paper:
+    Title: Expectation-Maximization Attention Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.13426
+  README: configs/emanet/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: eemanet_r50-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: EMANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.59
+      mIoU(ms+flip): 79.44
+  Config: configs/emanet/eemanet_r50-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - EMANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.4
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r50-d8_512x1024_80k_cityscapes/emanet_r50-d8_512x1024_80k_cityscapes_20200901_100301-c43fcef1.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r50-d8_512x1024_80k_cityscapes/emanet_r50-d8_512x1024_80k_cityscapes-20200901_100301.log.json
+  Paper:
+    Title: Expectation-Maximization Attention Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.13426
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ema_head.py#L80
+  Framework: PyTorch
+- Name: emanet_r101-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: EMANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.1
+      mIoU(ms+flip): 81.21
+  Config: configs/emanet/emanet_r101-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - EMANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r101-d8_512x1024_80k_cityscapes/emanet_r101-d8_512x1024_80k_cityscapes_20200901_100301-2d970745.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r101-d8_512x1024_80k_cityscapes/emanet_r101-d8_512x1024_80k_cityscapes-20200901_100301.log.json
+  Paper:
+    Title: Expectation-Maximization Attention Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.13426
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ema_head.py#L80
+  Framework: PyTorch
+- Name: emanet_r50-d8_4xb2-80k_cityscapes-769x769
+  In Collection: EMANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.33
+      mIoU(ms+flip): 80.49
+  Config: configs/emanet/emanet_r50-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - EMANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r50-d8_769x769_80k_cityscapes/emanet_r50-d8_769x769_80k_cityscapes_20200901_100301-16f8de52.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r50-d8_769x769_80k_cityscapes/emanet_r50-d8_769x769_80k_cityscapes-20200901_100301.log.json
+  Paper:
+    Title: Expectation-Maximization Attention Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.13426
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ema_head.py#L80
+  Framework: PyTorch
+- Name: emanet_r101-d8_4xb2-80k_cityscapes-769x769
+  In Collection: EMANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.62
+      mIoU(ms+flip): 81.0
+  Config: configs/emanet/emanet_r101-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - EMANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r101-d8_769x769_80k_cityscapes/emanet_r101-d8_769x769_80k_cityscapes_20200901_100301-47a324ce.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r101-d8_769x769_80k_cityscapes/emanet_r101-d8_769x769_80k_cityscapes-20200901_100301.log.json
+  Paper:
+    Title: Expectation-Maximization Attention Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.13426
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ema_head.py#L80
+  Framework: PyTorch
diff --git a/configs/encnet/README.md b/configs/encnet/README.md
index 7be0c6d926..31bbd98c6b 100644
--- a/configs/encnet/README.md
+++ b/configs/encnet/README.md
@@ -1,6 +1,6 @@
 # EncNet
 
-[Context Encoding for Semantic Segmentation](https://arxiv.org/abs/1803.08904)
+> [Context Encoding for Semantic Segmentation](https://arxiv.org/abs/1803.08904)
 
 ## Introduction
 
@@ -22,6 +22,30 @@ Recent work has made significant progress in improving spatial resolution for pi
 <img src="https://user-images.githubusercontent.com/24582831/142901276-b364fbbf-3bdb-4000-9d31-b9a135e30935.png" width="70%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| EncNet | R-50-D8  | 512x1024  |   40000 | 8.6      | 4.58           | V100   | 75.67 |         77.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_40k_cityscapes/encnet_r50-d8_512x1024_40k_cityscapes_20200621_220958-68638a47.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_40k_cityscapes/encnet_r50-d8_512x1024_40k_cityscapes-20200621_220958.log.json)     |
+| EncNet | R-101-D8 | 512x1024  |   40000 | 12.1     | 2.66           | V100   | 75.81 |         77.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_40k_cityscapes/encnet_r101-d8_512x1024_40k_cityscapes_20200621_220933-35e0a3e8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_40k_cityscapes/encnet_r101-d8_512x1024_40k_cityscapes-20200621_220933.log.json) |
+| EncNet | R-50-D8  | 769x769   |   40000 | 9.8      | 1.82           | V100   | 76.24 |         77.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_40k_cityscapes/encnet_r50-d8_769x769_40k_cityscapes_20200621_220958-3bcd2884.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_40k_cityscapes/encnet_r50-d8_769x769_40k_cityscapes-20200621_220958.log.json)         |
+| EncNet | R-101-D8 | 769x769   |   40000 | 13.7     | 1.26           | V100   | 74.25 |         76.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_40k_cityscapes/encnet_r101-d8_769x769_40k_cityscapes_20200621_220933-2fafed55.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_40k_cityscapes/encnet_r101-d8_769x769_40k_cityscapes-20200621_220933.log.json)     |
+| EncNet | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 77.94 |         79.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_80k_cityscapes/encnet_r50-d8_512x1024_80k_cityscapes_20200622_003554-fc5c5624.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_80k_cityscapes/encnet_r50-d8_512x1024_80k_cityscapes-20200622_003554.log.json)     |
+| EncNet | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 78.55 |         79.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_80k_cityscapes/encnet_r101-d8_512x1024_80k_cityscapes_20200622_003555-1de64bec.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_80k_cityscapes/encnet_r101-d8_512x1024_80k_cityscapes-20200622_003555.log.json) |
+| EncNet | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 77.44 |         78.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_80k_cityscapes/encnet_r50-d8_769x769_80k_cityscapes_20200622_003554-55096dcb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_80k_cityscapes/encnet_r50-d8_769x769_80k_cityscapes-20200622_003554.log.json)         |
+| EncNet | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 76.10 |         76.97 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_80k_cityscapes/encnet_r101-d8_769x769_80k_cityscapes_20200622_003555-470ef79d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_80k_cityscapes/encnet_r101-d8_769x769_80k_cityscapes-20200622_003555.log.json)     |
+
+### ADE20K
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| EncNet | R-50-D8  | 512x512   |   80000 | 10.1     | 22.81          | V100   | 39.53 |         41.17 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_80k_ade20k/encnet_r50-d8_512x512_80k_ade20k_20200622_042412-44b46b04.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_80k_ade20k/encnet_r50-d8_512x512_80k_ade20k-20200622_042412.log.json)         |
+| EncNet | R-101-D8 | 512x512   |   80000 | 13.6     | 14.87          | V100   | 42.11 |         43.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_80k_ade20k/encnet_r101-d8_512x512_80k_ade20k_20200622_101128-dd35e237.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_80k_ade20k/encnet_r101-d8_512x512_80k_ade20k-20200622_101128.log.json)     |
+| EncNet | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 40.10 |         41.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_160k_ade20k/encnet_r50-d8_512x512_160k_ade20k_20200622_101059-b2db95e0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_160k_ade20k/encnet_r50-d8_512x512_160k_ade20k-20200622_101059.log.json)     |
+| EncNet | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 42.61 |         44.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_160k_ade20k/encnet_r101-d8_512x512_160k_ade20k_20200622_073348-7989641f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_160k_ade20k/encnet_r101-d8_512x512_160k_ade20k-20200622_073348.log.json) |
+
 ## Citation
 
 ```bibtex
@@ -33,27 +57,3 @@ month = {June},
 year = {2018}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| EncNet | R-50-D8  | 512x1024  |   40000 | 8.6      | 4.58           | 75.67 |         77.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_40k_cityscapes/encnet_r50-d8_512x1024_40k_cityscapes_20200621_220958-68638a47.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_40k_cityscapes/encnet_r50-d8_512x1024_40k_cityscapes-20200621_220958.log.json)     |
-| EncNet | R-101-D8 | 512x1024  |   40000 | 12.1     | 2.66           | 75.81 |         77.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_40k_cityscapes/encnet_r101-d8_512x1024_40k_cityscapes_20200621_220933-35e0a3e8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_40k_cityscapes/encnet_r101-d8_512x1024_40k_cityscapes-20200621_220933.log.json) |
-| EncNet | R-50-D8  | 769x769   |   40000 | 9.8      | 1.82           | 76.24 |         77.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_40k_cityscapes/encnet_r50-d8_769x769_40k_cityscapes_20200621_220958-3bcd2884.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_40k_cityscapes/encnet_r50-d8_769x769_40k_cityscapes-20200621_220958.log.json)         |
-| EncNet | R-101-D8 | 769x769   |   40000 | 13.7     | 1.26           | 74.25 |         76.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_40k_cityscapes/encnet_r101-d8_769x769_40k_cityscapes_20200621_220933-2fafed55.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_40k_cityscapes/encnet_r101-d8_769x769_40k_cityscapes-20200621_220933.log.json)     |
-| EncNet | R-50-D8  | 512x1024  |   80000 | -        | -              | 77.94 |         79.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_80k_cityscapes/encnet_r50-d8_512x1024_80k_cityscapes_20200622_003554-fc5c5624.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_80k_cityscapes/encnet_r50-d8_512x1024_80k_cityscapes-20200622_003554.log.json)     |
-| EncNet | R-101-D8 | 512x1024  |   80000 | -        | -              | 78.55 |         79.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_80k_cityscapes/encnet_r101-d8_512x1024_80k_cityscapes_20200622_003555-1de64bec.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_80k_cityscapes/encnet_r101-d8_512x1024_80k_cityscapes-20200622_003555.log.json) |
-| EncNet | R-50-D8  | 769x769   |   80000 | -        | -              | 77.44 |         78.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_80k_cityscapes/encnet_r50-d8_769x769_80k_cityscapes_20200622_003554-55096dcb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_80k_cityscapes/encnet_r50-d8_769x769_80k_cityscapes-20200622_003554.log.json)         |
-| EncNet | R-101-D8 | 769x769   |   80000 | -        | -              | 76.10 |         76.97 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_80k_cityscapes/encnet_r101-d8_769x769_80k_cityscapes_20200622_003555-470ef79d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_80k_cityscapes/encnet_r101-d8_769x769_80k_cityscapes-20200622_003555.log.json)     |
-
-### ADE20K
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| EncNet | R-50-D8  | 512x512   |   80000 | 10.1     | 22.81          | 39.53 |         41.17 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_80k_ade20k/encnet_r50-d8_512x512_80k_ade20k_20200622_042412-44b46b04.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_80k_ade20k/encnet_r50-d8_512x512_80k_ade20k-20200622_042412.log.json)         |
-| EncNet | R-101-D8 | 512x512   |   80000 | 13.6     | 14.87          | 42.11 |         43.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_80k_ade20k/encnet_r101-d8_512x512_80k_ade20k_20200622_101128-dd35e237.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_80k_ade20k/encnet_r101-d8_512x512_80k_ade20k-20200622_101128.log.json)     |
-| EncNet | R-50-D8  | 512x512   |  160000 | -        | -              | 40.10 |         41.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_160k_ade20k/encnet_r50-d8_512x512_160k_ade20k_20200622_101059-b2db95e0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_160k_ade20k/encnet_r50-d8_512x512_160k_ade20k-20200622_101059.log.json)     |
-| EncNet | R-101-D8 | 512x512   |  160000 | -        | -              | 42.61 |         44.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_160k_ade20k/encnet_r101-d8_512x512_160k_ade20k_20200622_073348-7989641f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_160k_ade20k/encnet_r101-d8_512x512_160k_ade20k-20200622_073348.log.json) |
diff --git a/configs/encnet/encnet.yml b/configs/encnet/encnet.yml
deleted file mode 100644
index bea147b286..0000000000
--- a/configs/encnet/encnet.yml
+++ /dev/null
@@ -1,232 +0,0 @@
-Collections:
-- Name: EncNet
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-  Paper:
-    URL: https://arxiv.org/abs/1803.08904
-    Title: Context Encoding for Semantic Segmentation
-  README: configs/encnet/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/enc_head.py#L63
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/zhanghang1989/PyTorch-Encoding
-Models:
-- Name: encnet_r50-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: EncNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 218.34
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 8.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 75.67
-      mIoU(ms+flip): 77.08
-  Config: configs/encnet/encnet_r50-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_40k_cityscapes/encnet_r50-d8_512x1024_40k_cityscapes_20200621_220958-68638a47.pth
-- Name: encnet_r101-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: EncNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 375.94
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 12.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 75.81
-      mIoU(ms+flip): 77.21
-  Config: configs/encnet/encnet_r101-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_40k_cityscapes/encnet_r101-d8_512x1024_40k_cityscapes_20200621_220933-35e0a3e8.pth
-- Name: encnet_r50-d8_4xb2-40k_cityscapes-769x769
-  In Collection: EncNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 549.45
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 9.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.24
-      mIoU(ms+flip): 77.85
-  Config: configs/encnet/encnet_r50-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_40k_cityscapes/encnet_r50-d8_769x769_40k_cityscapes_20200621_220958-3bcd2884.pth
-- Name: encnet_r101-d8_4xb2-40k_cityscapes-769x769
-  In Collection: EncNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 793.65
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 13.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 74.25
-      mIoU(ms+flip): 76.25
-  Config: configs/encnet/encnet_r101-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_40k_cityscapes/encnet_r101-d8_769x769_40k_cityscapes_20200621_220933-2fafed55.pth
-- Name: encnet_r50-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: EncNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.94
-      mIoU(ms+flip): 79.13
-  Config: configs/encnet/encnet_r50-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_80k_cityscapes/encnet_r50-d8_512x1024_80k_cityscapes_20200622_003554-fc5c5624.pth
-- Name: encnet_r101-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: EncNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.55
-      mIoU(ms+flip): 79.47
-  Config: configs/encnet/encnet_r101-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_80k_cityscapes/encnet_r101-d8_512x1024_80k_cityscapes_20200622_003555-1de64bec.pth
-- Name: encnet_r50-d8_4xb2-80k_cityscapes-769x769
-  In Collection: EncNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.44
-      mIoU(ms+flip): 78.72
-  Config: configs/encnet/encnet_r50-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_80k_cityscapes/encnet_r50-d8_769x769_80k_cityscapes_20200622_003554-55096dcb.pth
-- Name: encnet_r101-d8_4xb2-80k_cityscapes-769x769
-  In Collection: EncNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.1
-      mIoU(ms+flip): 76.97
-  Config: configs/encnet/encnet_r101-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_80k_cityscapes/encnet_r101-d8_769x769_80k_cityscapes_20200622_003555-470ef79d.pth
-- Name: encnet_r50-d8_4xb4-80k_ade20k-512x512
-  In Collection: EncNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 43.84
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 10.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 39.53
-      mIoU(ms+flip): 41.17
-  Config: configs/encnet/encnet_r50-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_80k_ade20k/encnet_r50-d8_512x512_80k_ade20k_20200622_042412-44b46b04.pth
-- Name: encnet_r101-d8_4xb4-80k_ade20k-512x512
-  In Collection: EncNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 67.25
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 13.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.11
-      mIoU(ms+flip): 43.61
-  Config: configs/encnet/encnet_r101-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_80k_ade20k/encnet_r101-d8_512x512_80k_ade20k_20200622_101128-dd35e237.pth
-- Name: encnet_r50-d8_4xb4-160k_ade20k-512x512
-  In Collection: EncNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 40.1
-      mIoU(ms+flip): 41.71
-  Config: configs/encnet/encnet_r50-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_160k_ade20k/encnet_r50-d8_512x512_160k_ade20k_20200622_101059-b2db95e0.pth
-- Name: encnet_r101-d8_4xb4-160k_ade20k-512x512
-  In Collection: EncNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.61
-      mIoU(ms+flip): 44.01
-  Config: configs/encnet/encnet_r101-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_160k_ade20k/encnet_r101-d8_512x512_160k_ade20k_20200622_073348-7989641f.pth
diff --git a/configs/encnet/metafile.yaml b/configs/encnet/metafile.yaml
new file mode 100644
index 0000000000..0dbdcfaab3
--- /dev/null
+++ b/configs/encnet/metafile.yaml
@@ -0,0 +1,296 @@
+Collections:
+- Name: EncNet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - ADE20K
+  Paper:
+    Title: Context Encoding for Semantic Segmentation
+    URL: https://arxiv.org/abs/1803.08904
+  README: configs/encnet/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: encnet_r50-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: EncNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 75.67
+      mIoU(ms+flip): 77.08
+  Config: configs/encnet/encnet_r50-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - EncNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_40k_cityscapes/encnet_r50-d8_512x1024_40k_cityscapes_20200621_220958-68638a47.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_40k_cityscapes/encnet_r50-d8_512x1024_40k_cityscapes-20200621_220958.log.json
+  Paper:
+    Title: Context Encoding for Semantic Segmentation
+    URL: https://arxiv.org/abs/1803.08904
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/enc_head.py#L63
+  Framework: PyTorch
+- Name: encnet_r101-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: EncNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 75.81
+      mIoU(ms+flip): 77.21
+  Config: configs/encnet/encnet_r101-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - EncNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 12.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_40k_cityscapes/encnet_r101-d8_512x1024_40k_cityscapes_20200621_220933-35e0a3e8.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_40k_cityscapes/encnet_r101-d8_512x1024_40k_cityscapes-20200621_220933.log.json
+  Paper:
+    Title: Context Encoding for Semantic Segmentation
+    URL: https://arxiv.org/abs/1803.08904
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/enc_head.py#L63
+  Framework: PyTorch
+- Name: encnet_r50-d8_4xb2-40k_cityscapes-769x769
+  In Collection: EncNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.24
+      mIoU(ms+flip): 77.85
+  Config: configs/encnet/encnet_r50-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - EncNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_40k_cityscapes/encnet_r50-d8_769x769_40k_cityscapes_20200621_220958-3bcd2884.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_40k_cityscapes/encnet_r50-d8_769x769_40k_cityscapes-20200621_220958.log.json
+  Paper:
+    Title: Context Encoding for Semantic Segmentation
+    URL: https://arxiv.org/abs/1803.08904
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/enc_head.py#L63
+  Framework: PyTorch
+- Name: encnet_r101-d8_4xb2-40k_cityscapes-769x769
+  In Collection: EncNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 74.25
+      mIoU(ms+flip): 76.25
+  Config: configs/encnet/encnet_r101-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - EncNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 13.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_40k_cityscapes/encnet_r101-d8_769x769_40k_cityscapes_20200621_220933-2fafed55.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_40k_cityscapes/encnet_r101-d8_769x769_40k_cityscapes-20200621_220933.log.json
+  Paper:
+    Title: Context Encoding for Semantic Segmentation
+    URL: https://arxiv.org/abs/1803.08904
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/enc_head.py#L63
+  Framework: PyTorch
+- Name: encnet_r50-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: EncNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.94
+      mIoU(ms+flip): 79.13
+  Config: configs/encnet/encnet_r50-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - EncNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_80k_cityscapes/encnet_r50-d8_512x1024_80k_cityscapes_20200622_003554-fc5c5624.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_80k_cityscapes/encnet_r50-d8_512x1024_80k_cityscapes-20200622_003554.log.json
+  Paper:
+    Title: Context Encoding for Semantic Segmentation
+    URL: https://arxiv.org/abs/1803.08904
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/enc_head.py#L63
+  Framework: PyTorch
+- Name: encnet_r101-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: EncNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.55
+      mIoU(ms+flip): 79.47
+  Config: configs/encnet/encnet_r101-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - EncNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_80k_cityscapes/encnet_r101-d8_512x1024_80k_cityscapes_20200622_003555-1de64bec.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_80k_cityscapes/encnet_r101-d8_512x1024_80k_cityscapes-20200622_003555.log.json
+  Paper:
+    Title: Context Encoding for Semantic Segmentation
+    URL: https://arxiv.org/abs/1803.08904
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/enc_head.py#L63
+  Framework: PyTorch
+- Name: encnet_r50-d8_4xb2-80k_cityscapes-769x769
+  In Collection: EncNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.44
+      mIoU(ms+flip): 78.72
+  Config: configs/encnet/encnet_r50-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - EncNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_80k_cityscapes/encnet_r50-d8_769x769_80k_cityscapes_20200622_003554-55096dcb.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_80k_cityscapes/encnet_r50-d8_769x769_80k_cityscapes-20200622_003554.log.json
+  Paper:
+    Title: Context Encoding for Semantic Segmentation
+    URL: https://arxiv.org/abs/1803.08904
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/enc_head.py#L63
+  Framework: PyTorch
+- Name: encnet_r101-d8_4xb2-80k_cityscapes-769x769
+  In Collection: EncNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.1
+      mIoU(ms+flip): 76.97
+  Config: configs/encnet/encnet_r101-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - EncNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_80k_cityscapes/encnet_r101-d8_769x769_80k_cityscapes_20200622_003555-470ef79d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_80k_cityscapes/encnet_r101-d8_769x769_80k_cityscapes-20200622_003555.log.json
+  Paper:
+    Title: Context Encoding for Semantic Segmentation
+    URL: https://arxiv.org/abs/1803.08904
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/enc_head.py#L63
+  Framework: PyTorch
+- Name: encnet_r50-d8_4xb4-80k_ade20k-512x512
+  In Collection: EncNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 39.53
+      mIoU(ms+flip): 41.17
+  Config: configs/encnet/encnet_r50-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - EncNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_80k_ade20k/encnet_r50-d8_512x512_80k_ade20k_20200622_042412-44b46b04.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_80k_ade20k/encnet_r50-d8_512x512_80k_ade20k-20200622_042412.log.json
+  Paper:
+    Title: Context Encoding for Semantic Segmentation
+    URL: https://arxiv.org/abs/1803.08904
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/enc_head.py#L63
+  Framework: PyTorch
+- Name: encnet_r101-d8_4xb4-80k_ade20k-512x512
+  In Collection: EncNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.11
+      mIoU(ms+flip): 43.61
+  Config: configs/encnet/encnet_r101-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - EncNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 13.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_80k_ade20k/encnet_r101-d8_512x512_80k_ade20k_20200622_101128-dd35e237.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_80k_ade20k/encnet_r101-d8_512x512_80k_ade20k-20200622_101128.log.json
+  Paper:
+    Title: Context Encoding for Semantic Segmentation
+    URL: https://arxiv.org/abs/1803.08904
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/enc_head.py#L63
+  Framework: PyTorch
+- Name: encnet_r50-d8_4xb4-160k_ade20k-512x512
+  In Collection: EncNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 40.1
+      mIoU(ms+flip): 41.71
+  Config: configs/encnet/encnet_r50-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - EncNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_160k_ade20k/encnet_r50-d8_512x512_160k_ade20k_20200622_101059-b2db95e0.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_160k_ade20k/encnet_r50-d8_512x512_160k_ade20k-20200622_101059.log.json
+  Paper:
+    Title: Context Encoding for Semantic Segmentation
+    URL: https://arxiv.org/abs/1803.08904
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/enc_head.py#L63
+  Framework: PyTorch
+- Name: encnet_r101-d8_4xb4-160k_ade20k-512x512
+  In Collection: EncNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.61
+      mIoU(ms+flip): 44.01
+  Config: configs/encnet/encnet_r101-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - EncNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_160k_ade20k/encnet_r101-d8_512x512_160k_ade20k_20200622_073348-7989641f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_160k_ade20k/encnet_r101-d8_512x512_160k_ade20k-20200622_073348.log.json
+  Paper:
+    Title: Context Encoding for Semantic Segmentation
+    URL: https://arxiv.org/abs/1803.08904
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/enc_head.py#L63
+  Framework: PyTorch
diff --git a/configs/erfnet/README.md b/configs/erfnet/README.md
index 4f7d21572a..e29afc485d 100644
--- a/configs/erfnet/README.md
+++ b/configs/erfnet/README.md
@@ -1,6 +1,6 @@
 # ERFNet
 
-[ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation](http://www.robesafe.uah.es/personal/eduardo.romera/pdfs/Romera17tits.pdf)
+> [ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation](http://www.robesafe.uah.es/personal/eduardo.romera/pdfs/Romera17tits.pdf)
 
 ## Introduction
 
@@ -22,6 +22,22 @@ Semantic segmentation is a challenging task that addresses most of the perceptio
 <img src="https://user-images.githubusercontent.com/24582831/143479729-ea7951f6-1a3c-47d6-aaee-62c5759c0638.png" width="60%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                     |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ---: | ------------- | ------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| ERFNet | ERFNet   | 512x1024  |  160000 | 6.04     | 15.26          | V100   | 72.5 | 74.75         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/erfnet/erfnet_fcn_4xb4-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/erfnet/erfnet_fcn_4x4_512x1024_160k_cityscapes/erfnet_fcn_4x4_512x1024_160k_cityscapes_20220704_162145-dc90157a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/erfnet/erfnet_fcn_4x4_512x1024_160k_cityscapes/erfnet_fcn_4x4_512x1024_160k_cityscapes_20220704_162145.log.json) |
+
+Note:
+
+- The model is trained from scratch.
+
+- Last deconvolution layer in the [original paper](https://github.com/Eromera/erfnet_pytorch/blob/master/train/erfnet.py#L123) is replaced by a naive `FCNHead` decoder head and a bilinear upsampling layer, found more effective and efficient.
+
+- This model performance is sensitive to the seed values used, please refer to the log file for the specific settings of the seed. If you choose a different seed, the results might differ from the table results.
+
 ## Citation
 
 ```bibtex
@@ -36,19 +52,3 @@ Semantic segmentation is a challenging task that addresses most of the perceptio
   publisher={IEEE}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                     |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ---: | ------------- | ------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| ERFNet | ERFNet   | 512x1024  |  160000 | 6.04     | 15.26          | 72.5 | 74.75         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/erfnet/erfnet_fcn_4xb4-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/erfnet/erfnet_fcn_4x4_512x1024_160k_cityscapes/erfnet_fcn_4x4_512x1024_160k_cityscapes_20220704_162145-dc90157a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/erfnet/erfnet_fcn_4x4_512x1024_160k_cityscapes/erfnet_fcn_4x4_512x1024_160k_cityscapes_20220704_162145.log.json) |
-
-Note:
-
-- The model is trained from scratch.
-
-- Last deconvolution layer in the [original paper](https://github.com/Eromera/erfnet_pytorch/blob/master/train/erfnet.py#L123) is replaced by a naive `FCNHead` decoder head and a bilinear upsampling layer, found more effective and efficient.
-
-- This model performance is sensitive to the seed values used, please refer to the log file for the specific settings of the seed. If you choose a different seed, the results might differ from the table results.
diff --git a/configs/erfnet/erfnet.yml b/configs/erfnet/erfnet.yml
deleted file mode 100644
index 5f87f020cf..0000000000
--- a/configs/erfnet/erfnet.yml
+++ /dev/null
@@ -1,37 +0,0 @@
-Collections:
-- Name: ERFNet
-  Metadata:
-    Training Data:
-    - Cityscapes
-  Paper:
-    URL: http://www.robesafe.uah.es/personal/eduardo.romera/pdfs/Romera17tits.pdf
-    Title: 'ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation'
-  README: configs/erfnet/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/erfnet.py#L321
-    Version: v0.20.0
-  Converted From:
-    Code: https://github.com/Eromera/erfnet_pytorch
-Models:
-- Name: erfnet_fcn_4xb4-160k_cityscapes-512x1024
-  In Collection: ERFNet
-  Metadata:
-    backbone: ERFNet
-    crop size: (512,1024)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 65.53
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 6.04
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 72.5
-      mIoU(ms+flip): 74.75
-  Config: configs/erfnet/erfnet_fcn_4xb4-160k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/erfnet/erfnet_fcn_4x4_512x1024_160k_cityscapes/erfnet_fcn_4x4_512x1024_160k_cityscapes_20220704_162145-dc90157a.pth
diff --git a/configs/erfnet/metafile.yaml b/configs/erfnet/metafile.yaml
new file mode 100644
index 0000000000..bf514124ee
--- /dev/null
+++ b/configs/erfnet/metafile.yaml
@@ -0,0 +1,37 @@
+Collections:
+- Name: ERFNet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+  Paper:
+    Title: 'ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation'
+    URL: http://www.robesafe.uah.es/personal/eduardo.romera/pdfs/Romera17tits.pdf
+  README: configs/erfnet/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: erfnet_fcn_4xb4-160k_cityscapes-512x1024
+  In Collection: ERFNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 72.5
+      mIoU(ms+flip): 74.75
+  Config: configs/erfnet/erfnet_fcn_4xb4-160k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - ERFNet
+    - ERFNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.04
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/erfnet/erfnet_fcn_4x4_512x1024_160k_cityscapes/erfnet_fcn_4x4_512x1024_160k_cityscapes_20220704_162145-dc90157a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/erfnet/erfnet_fcn_4x4_512x1024_160k_cityscapes/erfnet_fcn_4x4_512x1024_160k_cityscapes_20220704_162145.log.json
+  Paper:
+    Title: 'ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation'
+    URL: http://www.robesafe.uah.es/personal/eduardo.romera/pdfs/Romera17tits.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/erfnet.py#L321
+  Framework: PyTorch
diff --git a/configs/fastfcn/README.md b/configs/fastfcn/README.md
index feedfa33a8..0b26a33edd 100644
--- a/configs/fastfcn/README.md
+++ b/configs/fastfcn/README.md
@@ -1,6 +1,6 @@
 # FastFCN
 
-[FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation](https://arxiv.org/abs/1903.11816)
+> [FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation](https://arxiv.org/abs/1903.11816)
 
 ## Introduction
 
@@ -22,42 +22,42 @@ Modern approaches for semantic segmentation usually employ dilated convolutions
 <img src="https://user-images.githubusercontent.com/24582831/142901374-6e0252ab-6e0f-4acd-86ad-1e9f49be3185.png" width="70%"/>
 </div>
 
-## Citation
-
-```bibtex
-@article{wu2019fastfcn,
-title={Fastfcn: Rethinking dilated convolution in the backbone for semantic segmentation},
-author={Wu, Huikai and Zhang, Junge and Huang, Kaiqi and Liang, Kongming and Yu, Yizhou},
-journal={arXiv preprint arXiv:1903.11816},
-year={2019}
-}
-```
-
 ## Results and models
 
 ### Cityscapes
 
-| Method                    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                       | download                                                                                                                                                                                                                                                                                                                                                                                                           |
-| ------------------------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| FastFCN + DeepLabV3       | R-50-D32 | 512x1024  |   80000 | 5.67     | 2.64           | 79.12 | 80.58         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes_20210928_053722-5d1a2648.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes_20210928_053722.log.json)                 |
-| FastFCN + DeepLabV3 (4x4) | R-50-D32 | 512x1024  |   80000 | 9.79     | -              | 79.52 | 80.91         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357-72220849.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357.log.json) |
-| FastFCN + PSPNet          | R-50-D32 | 512x1024  |   80000 | 5.67     | 4.40           | 79.26 | 80.86         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes_20210928_053722-57749bed.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes_20210928_053722.log.json)                     |
-| FastFCN + PSPNet (4x4)    | R-50-D32 | 512x1024  |   80000 | 9.94     | -              | 78.76 | 80.03         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841-77e87b0a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841.log.json)     |
-| FastFCN + EncNet          | R-50-D32 | 512x1024  |   80000 | 8.15     | 4.77           | 77.97 | 79.92         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes_20210928_030036-78da5046.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes_20210928_030036.log.json)                     |
-| FastFCN + EncNet (4x4)    | R-50-D32 | 512x1024  |   80000 | 15.45    | -              |  78.6 | 80.25         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217-e1eb6dbb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217.log.json)     |
+| Method              | Backbone       | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                       | download                                                                                                                                                                                                                                                                                                                                                                                                           |
+| ------------------- | -------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| FastFCN + DeepLabV3 | R-50-D32       | 512x1024  |   80000 | 5.67     | 2.64           | V100   | 79.12 | 80.58         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes_20210928_053722-5d1a2648.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes_20210928_053722.log.json)                 |
+| FastFCN + DeepLabV3 | R-50-D32 (4x4) | 512x1024  |   80000 | 9.79     | -              | V100   | 79.52 | 80.91         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357-72220849.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357.log.json) |
+| FastFCN + PSPNet    | R-50-D32       | 512x1024  |   80000 | 5.67     | 4.40           | V100   | 79.26 | 80.86         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes_20210928_053722-57749bed.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes_20210928_053722.log.json)                     |
+| FastFCN + PSPNet    | R-50-D32 (4x4) | 512x1024  |   80000 | 9.94     | -              | V100   | 78.76 | 80.03         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841-77e87b0a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841.log.json)     |
+| FastFCN + EncNet    | R-50-D32       | 512x1024  |   80000 | 8.15     | 4.77           | V100   | 77.97 | 79.92         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes_20210928_030036-78da5046.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes_20210928_030036.log.json)                     |
+| FastFCN + EncNet    | R-50-D32 (4x4) | 512x1024  |   80000 | 15.45    | -              | V100   |  78.6 | 80.25         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217-e1eb6dbb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217.log.json)     |
 
 ### ADE20K
 
-| Method              | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                   | download                                                                                                                                                                                                                                                                                                                                                                           |
-| ------------------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FastFCN + DeepLabV3 | R-50-D32 | 512x1024  |   80000 | 8.46     | 12.06          | 41.88 | 42.91         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k_20211013_190619-3aa40f2d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k_20211013_190619.log.json)     |
-| FastFCN + DeepLabV3 | R-50-D32 | 512x1024  |  160000 | -        | -              | 43.58 | 44.92         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k_20211008_152246-27036aee.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k_20211008_152246.log.json) |
-| FastFCN + PSPNet    | R-50-D32 | 512x1024  |   80000 | 8.02     | 19.21          | 41.40 | 42.12         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k_20210930_225137-993d07c8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k_20210930_225137.log.json)         |
-| FastFCN + PSPNet    | R-50-D32 | 512x1024  |  160000 | -        | -              | 42.63 | 43.71         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k_20211008_105455-e8f5a2fd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k_20211008_105455.log.json)     |
-| FastFCN + EncNet    | R-50-D32 | 512x1024  |   80000 | 9.67     | 17.23          | 40.88 | 42.36         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k_20210930_225214-65aef6dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k_20210930_225214.log.json)         |
-| FastFCN + EncNet    | R-50-D32 | 512x1024  |  160000 | -        | -              | 42.50 | 44.21         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k_20211008_105456-d875ce3c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k_20211008_105456.log.json)     |
+| Method              | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                   | download                                                                                                                                                                                                                                                                                                                                                                           |
+| ------------------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FastFCN + DeepLabV3 | R-50-D32 | 512x1024  |   80000 | 8.46     | 12.06          | V100   | 41.88 | 42.91         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k_20211013_190619-3aa40f2d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k_20211013_190619.log.json)     |
+| FastFCN + DeepLabV3 | R-50-D32 | 512x1024  |  160000 | -        | -              | V100   | 43.58 | 44.92         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k_20211008_152246-27036aee.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k_20211008_152246.log.json) |
+| FastFCN + PSPNet    | R-50-D32 | 512x1024  |   80000 | 8.02     | 19.21          | V100   | 41.40 | 42.12         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k_20210930_225137-993d07c8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k_20210930_225137.log.json)         |
+| FastFCN + PSPNet    | R-50-D32 | 512x1024  |  160000 | -        | -              | V100   | 42.63 | 43.71         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k_20211008_105455-e8f5a2fd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k_20211008_105455.log.json)     |
+| FastFCN + EncNet    | R-50-D32 | 512x1024  |   80000 | 9.67     | 17.23          | V100   | 40.88 | 42.36         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k_20210930_225214-65aef6dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k_20210930_225214.log.json)         |
+| FastFCN + EncNet    | R-50-D32 | 512x1024  |  160000 | -        | -              | V100   | 42.50 | 44.21         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k_20211008_105456-d875ce3c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k_20211008_105456.log.json)     |
 
 Note:
 
 - `4x4` means 4 GPUs with 4 samples per GPU in training, default setting is 4 GPUs with 2 samples per GPU in training.
 - Results of [DeepLabV3 (mIoU: 79.32)](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3), [PSPNet (mIoU: 78.55)](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet) and [ENCNet (mIoU: 77.94)](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet) can be found in each original repository.
+
+## Citation
+
+```bibtex
+@article{wu2019fastfcn,
+title={Fastfcn: Rethinking dilated convolution in the backbone for semantic segmentation},
+author={Wu, Huikai and Zhang, Junge and Huang, Kaiqi and Liang, Kongming and Yu, Yizhou},
+journal={arXiv preprint arXiv:1903.11816},
+year={2019}
+}
+```
diff --git a/configs/fastfcn/fastfcn.yml b/configs/fastfcn/fastfcn.yml
deleted file mode 100644
index 6b4d3bc121..0000000000
--- a/configs/fastfcn/fastfcn.yml
+++ /dev/null
@@ -1,235 +0,0 @@
-Collections:
-- Name: FastFCN
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-  Paper:
-    URL: https://arxiv.org/abs/1903.11816
-    Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
-  README: configs/fastfcn/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
-    Version: v0.18.0
-  Converted From:
-    Code: https://github.com/wuhuikai/FastFCN
-Models:
-- Name: fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024
-  In Collection: FastFCN
-  Metadata:
-    backbone: R-50-D32
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 378.79
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 5.67
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.12
-      mIoU(ms+flip): 80.58
-  Config: configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes_20210928_053722-5d1a2648.pth
-- Name: fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024
-  In Collection: FastFCN
-  Metadata:
-    backbone: R-50-D32
-    crop size: (512,1024)
-    lr schd: 80000
-    Training Memory (GB): 9.79
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.52
-      mIoU(ms+flip): 80.91
-  Config: configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357-72220849.pth
-- Name: fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024
-  In Collection: FastFCN
-  Metadata:
-    backbone: R-50-D32
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 227.27
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 5.67
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.26
-      mIoU(ms+flip): 80.86
-  Config: configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes_20210928_053722-57749bed.pth
-- Name: fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024
-  In Collection: FastFCN
-  Metadata:
-    backbone: R-50-D32
-    crop size: (512,1024)
-    lr schd: 80000
-    Training Memory (GB): 9.94
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.76
-      mIoU(ms+flip): 80.03
-  Config: configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841-77e87b0a.pth
-- Name: fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024
-  In Collection: FastFCN
-  Metadata:
-    backbone: R-50-D32
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 209.64
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 8.15
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.97
-      mIoU(ms+flip): 79.92
-  Config: configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes_20210928_030036-78da5046.pth
-- Name: fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024
-  In Collection: FastFCN
-  Metadata:
-    backbone: R-50-D32
-    crop size: (512,1024)
-    lr schd: 80000
-    Training Memory (GB): 15.45
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.6
-      mIoU(ms+flip): 80.25
-  Config: configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217-e1eb6dbb.pth
-- Name: fastfcn_r50-d32_jpu_aspp_4xb4-80k_ade20k-512x512
-  In Collection: FastFCN
-  Metadata:
-    backbone: R-50-D32
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 82.92
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 8.46
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 41.88
-      mIoU(ms+flip): 42.91
-  Config: configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k_20211013_190619-3aa40f2d.pth
-- Name: fastfcn_r50-d32_jpu_aspp_4xb4-160k_ade20k-512x512
-  In Collection: FastFCN
-  Metadata:
-    backbone: R-50-D32
-    crop size: (512,1024)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.58
-      mIoU(ms+flip): 44.92
-  Config: configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k_20211008_152246-27036aee.pth
-- Name: fastfcn_r50-d32_jpu_psp_4xb4-80k_ade20k-512x512
-  In Collection: FastFCN
-  Metadata:
-    backbone: R-50-D32
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 52.06
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 8.02
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 41.4
-      mIoU(ms+flip): 42.12
-  Config: configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k_20210930_225137-993d07c8.pth
-- Name: fastfcn_r50-d32_jpu_psp_4xb4-160k_ade20k-512x512
-  In Collection: FastFCN
-  Metadata:
-    backbone: R-50-D32
-    crop size: (512,1024)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.63
-      mIoU(ms+flip): 43.71
-  Config: configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k_20211008_105455-e8f5a2fd.pth
-- Name: fastfcn_r50-d32_jpu_enc_4xb4-80k_ade20k-512x512
-  In Collection: FastFCN
-  Metadata:
-    backbone: R-50-D32
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 58.04
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 9.67
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 40.88
-      mIoU(ms+flip): 42.36
-  Config: configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k_20210930_225214-65aef6dd.pth
-- Name: fastfcn_r50-d32_jpu_enc_4xb4-160k_ade20k-512x512
-  In Collection: FastFCN
-  Metadata:
-    backbone: R-50-D32
-    crop size: (512,1024)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.5
-      mIoU(ms+flip): 44.21
-  Config: configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k_20211008_105456-d875ce3c.pth
diff --git a/configs/fastfcn/metafile.yaml b/configs/fastfcn/metafile.yaml
new file mode 100644
index 0000000000..f5fe03ca45
--- /dev/null
+++ b/configs/fastfcn/metafile.yaml
@@ -0,0 +1,311 @@
+Collections:
+- Name: FastFCN
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - ADE20K
+  Paper:
+    Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1903.11816
+  README: configs/fastfcn/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024
+  In Collection: FastFCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.12
+      mIoU(ms+flip): 80.58
+  Config: configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D32
+    - FastFCN
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.67
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes_20210928_053722-5d1a2648.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes_20210928_053722.log.json
+  Paper:
+    Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1903.11816
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
+  Framework: PyTorch
+- Name: fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024
+  In Collection: FastFCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.52
+      mIoU(ms+flip): 80.91
+  Config: configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D32
+    - FastFCN
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.79
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357-72220849.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357.log.json
+  Paper:
+    Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1903.11816
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
+  Framework: PyTorch
+- Name: fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024
+  In Collection: FastFCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.26
+      mIoU(ms+flip): 80.86
+  Config: configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D32
+    - FastFCN
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.67
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes_20210928_053722-57749bed.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes_20210928_053722.log.json
+  Paper:
+    Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1903.11816
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
+  Framework: PyTorch
+- Name: fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024
+  In Collection: FastFCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.76
+      mIoU(ms+flip): 80.03
+  Config: configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D32
+    - FastFCN
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.94
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841-77e87b0a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841.log.json
+  Paper:
+    Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1903.11816
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
+  Framework: PyTorch
+- Name: fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024
+  In Collection: FastFCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.97
+      mIoU(ms+flip): 79.92
+  Config: configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D32
+    - FastFCN
+    - EncNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.15
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes_20210928_030036-78da5046.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes_20210928_030036.log.json
+  Paper:
+    Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1903.11816
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
+  Framework: PyTorch
+- Name: fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024
+  In Collection: FastFCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.6
+      mIoU(ms+flip): 80.25
+  Config: configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D32
+    - FastFCN
+    - EncNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 15.45
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217-e1eb6dbb.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217.log.json
+  Paper:
+    Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1903.11816
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
+  Framework: PyTorch
+- Name: fastfcn_r50-d32_jpu_aspp_4xb4-80k_ade20k-512x512
+  In Collection: FastFCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 41.88
+      mIoU(ms+flip): 42.91
+  Config: configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D32
+    - FastFCN
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.46
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k_20211013_190619-3aa40f2d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k_20211013_190619.log.json
+  Paper:
+    Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1903.11816
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
+  Framework: PyTorch
+- Name: fastfcn_r50-d32_jpu_aspp_4xb4-160k_ade20k-512x512
+  In Collection: FastFCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.58
+      mIoU(ms+flip): 44.92
+  Config: configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D32
+    - FastFCN
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k_20211008_152246-27036aee.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k_20211008_152246.log.json
+  Paper:
+    Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1903.11816
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
+  Framework: PyTorch
+- Name: fastfcn_r50-d32_jpu_psp_4xb4-80k_ade20k-512x512
+  In Collection: FastFCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 41.4
+      mIoU(ms+flip): 42.12
+  Config: configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D32
+    - FastFCN
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.02
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k_20210930_225137-993d07c8.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k_20210930_225137.log.json
+  Paper:
+    Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1903.11816
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
+  Framework: PyTorch
+- Name: fastfcn_r50-d32_jpu_psp_4xb4-160k_ade20k-512x512
+  In Collection: FastFCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.63
+      mIoU(ms+flip): 43.71
+  Config: configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D32
+    - FastFCN
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k_20211008_105455-e8f5a2fd.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k_20211008_105455.log.json
+  Paper:
+    Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1903.11816
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
+  Framework: PyTorch
+- Name: fastfcn_r50-d32_jpu_enc_4xb4-80k_ade20k-512x512
+  In Collection: FastFCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 40.88
+      mIoU(ms+flip): 42.36
+  Config: configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D32
+    - FastFCN
+    - EncNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.67
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k_20210930_225214-65aef6dd.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k_20210930_225214.log.json
+  Paper:
+    Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1903.11816
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
+  Framework: PyTorch
+- Name: fastfcn_r50-d32_jpu_enc_4xb4-160k_ade20k-512x512
+  In Collection: FastFCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.5
+      mIoU(ms+flip): 44.21
+  Config: configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D32
+    - FastFCN
+    - EncNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k_20211008_105456-d875ce3c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k_20211008_105456.log.json
+  Paper:
+    Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
+    URL: https://arxiv.org/abs/1903.11816
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
+  Framework: PyTorch
diff --git a/configs/fastscnn/README.md b/configs/fastscnn/README.md
index 3e06903ae5..ea3449fd2c 100644
--- a/configs/fastscnn/README.md
+++ b/configs/fastscnn/README.md
@@ -1,6 +1,6 @@
 # Fast-SCNN
 
-[Fast-SCNN for Semantic Segmentation](https://arxiv.org/abs/1902.04502)
+> [Fast-SCNN for Semantic Segmentation](https://arxiv.org/abs/1902.04502)
 
 ## Introduction
 
@@ -22,6 +22,14 @@ The encoder-decoder framework is state-of-the-art for offline semantic image seg
 <img src="https://user-images.githubusercontent.com/24582831/142901444-705b4ff4-6d1e-409b-899a-37bf3a6b69ce.png" width="80%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method   | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                               |
+| -------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| FastSCNN | FastSCNN | 512x1024  |  160000 | 3.3      | 56.45          | V100   | 70.96 | 72.65         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastscnn/fast_scnn_8xb4-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_lr0.12_8x4_160k_cityscapes/fast_scnn_lr0.12_8x4_160k_cityscapes_20210630_164853-0cec9937.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_lr0.12_8x4_160k_cityscapes/fast_scnn_lr0.12_8x4_160k_cityscapes_20210630_164853.log.json) |
+
 ## Citation
 
 ```bibtex
@@ -32,11 +40,3 @@ The encoder-decoder framework is state-of-the-art for offline semantic image seg
   year={2019}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method   | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                               |
-| -------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| FastSCNN | FastSCNN | 512x1024  |  160000 | 3.3      | 56.45          | 70.96 | 72.65         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastscnn/fast_scnn_8xb4-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_lr0.12_8x4_160k_cityscapes/fast_scnn_lr0.12_8x4_160k_cityscapes_20210630_164853-0cec9937.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_lr0.12_8x4_160k_cityscapes/fast_scnn_lr0.12_8x4_160k_cityscapes_20210630_164853.log.json) |
diff --git a/configs/fastscnn/fastscnn.yml b/configs/fastscnn/metafile.yaml
similarity index 50%
rename from configs/fastscnn/fastscnn.yml
rename to configs/fastscnn/metafile.yaml
index 13215c2fb1..9e33c902db 100644
--- a/configs/fastscnn/fastscnn.yml
+++ b/configs/fastscnn/metafile.yaml
@@ -1,35 +1,37 @@
 Collections:
 - Name: FastSCNN
+  License: Apache License 2.0
   Metadata:
     Training Data:
     - Cityscapes
   Paper:
-    URL: https://arxiv.org/abs/1902.04502
     Title: Fast-SCNN for Semantic Segmentation
+    URL: https://arxiv.org/abs/1902.04502
   README: configs/fastscnn/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/fast_scnn.py#L272
-    Version: v0.17.0
+  Frameworks:
+  - PyTorch
 Models:
 - Name: fast_scnn_8xb4-160k_cityscapes-512x1024
   In Collection: FastSCNN
-  Metadata:
-    backbone: FastSCNN
-    crop size: (512,1024)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 17.71
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 3.3
   Results:
-  - Task: Semantic Segmentation
+    Task: Semantic Segmentation
     Dataset: Cityscapes
     Metrics:
       mIoU: 70.96
       mIoU(ms+flip): 72.65
   Config: configs/fastscnn/fast_scnn_8xb4-160k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 32
+    Architecture:
+    - FastSCNN
+    - FastSCNN
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 3.3
   Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_lr0.12_8x4_160k_cityscapes/fast_scnn_lr0.12_8x4_160k_cityscapes_20210630_164853-0cec9937.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_lr0.12_8x4_160k_cityscapes/fast_scnn_lr0.12_8x4_160k_cityscapes_20210630_164853.log.json
+  Paper:
+    Title: Fast-SCNN for Semantic Segmentation
+    URL: https://arxiv.org/abs/1902.04502
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/fast_scnn.py#L272
+  Framework: PyTorch
diff --git a/configs/fcn/README.md b/configs/fcn/README.md
index 4b887f19e4..6134933710 100644
--- a/configs/fcn/README.md
+++ b/configs/fcn/README.md
@@ -1,6 +1,6 @@
 # FCN
 
-[Fully Convolutional Networks for Semantic Segmentation](https://arxiv.org/abs/1411.4038)
+> [Fully Convolutional Networks for Semantic Segmentation](https://arxiv.org/abs/1411.4038)
 
 ## Introduction
 
@@ -22,90 +22,90 @@ Convolutional networks are powerful visual models that yield hierarchies of feat
 <img src="https://user-images.githubusercontent.com/24582831/142901525-fd0d2bf4-9a47-4143-85f5-3cee8849eaa4.png" width="70%"/>
 </div>
 
-## Citation
-
-```bibtex
-@article{shelhamer2017fully,
-  title={Fully convolutional networks for semantic segmentation},
-  author={Shelhamer, Evan and Long, Jonathan and Darrell, Trevor},
-  journal={IEEE transactions on pattern analysis and machine intelligence},
-  volume={39},
-  number={4},
-  pages={640--651},
-  year={2017},
-  publisher={IEEE Trans Pattern Anal Mach Intell}
-}
-```
-
 ## Results and models
 
 ### Cityscapes
 
-| Method     | Backbone   | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                   |
-| ---------- | ---------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN        | R-50-D8    | 512x1024  |   40000 | 5.7      | 4.17           | 72.25 |         73.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_40k_cityscapes/fcn_r50-d8_512x1024_40k_cityscapes_20200604_192608-efe53f0d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_40k_cityscapes/fcn_r50-d8_512x1024_40k_cityscapes_20200604_192608.log.json)                         |
-| FCN        | R-101-D8   | 512x1024  |   40000 | 9.2      | 2.66           | 75.45 |         76.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb2-40k_cityscapes-512x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_40k_cityscapes/fcn_r101-d8_512x1024_40k_cityscapes_20200604_181852-a883d3a1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_40k_cityscapes/fcn_r101-d8_512x1024_40k_cityscapes_20200604_181852.log.json)                     |
-| FCN        | R-50-D8    | 769x769   |   40000 | 6.5      | 1.80           | 71.47 |         72.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-769x769.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_40k_cityscapes/fcn_r50-d8_769x769_40k_cityscapes_20200606_113104-977b5d02.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_40k_cityscapes/fcn_r50-d8_769x769_40k_cityscapes_20200606_113104.log.json)                             |
-| FCN        | R-101-D8   | 769x769   |   40000 | 10.4     | 1.19           | 73.93 |         75.14 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb2-40k_cityscapes-769x769.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_40k_cityscapes/fcn_r101-d8_769x769_40k_cityscapes_20200606_113208-7d4ab69c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_40k_cityscapes/fcn_r101-d8_769x769_40k_cityscapes_20200606_113208.log.json)                         |
-| FCN        | R-18-D8    | 512x1024  |   80000 | 1.7      | 14.65          | 71.11 |         72.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_512x1024_80k_cityscapes/fcn_r18-d8_512x1024_80k_cityscapes_20201225_021327-6c50f8b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_512x1024_80k_cityscapes/fcn_r18-d8_512x1024_80k_cityscapes-20201225_021327.log.json)                         |
-| FCN        | R-50-D8    | 512x1024  |   80000 | -        |                | 73.61 |         74.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb2-80k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_80k_cityscapes/fcn_r50-d8_512x1024_80k_cityscapes_20200606_113019-03aa804d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_80k_cityscapes/fcn_r50-d8_512x1024_80k_cityscapes_20200606_113019.log.json)                         |
-| FCN        | R-101-D8   | 512x1024  |   80000 | -        | -              | 75.13 |         75.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb2-80k_cityscapes-512x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_80k_cityscapes/fcn_r101-d8_512x1024_80k_cityscapes_20200606_113038-3fb937eb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_80k_cityscapes/fcn_r101-d8_512x1024_80k_cityscapes_20200606_113038.log.json)                     |
-| FCN (FP16) | R-101-D8   | 512x1024  |   80000 | 5.37     | 8.64           | 76.80 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_fp16_512x1024_80k_cityscapes/fcn_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230921-fb13e883.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_fp16_512x1024_80k_cityscapes/fcn_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230921.log.json) |
-| FCN        | R-18-D8    | 769x769   |   80000 | 1.9      | 6.40           | 70.80 |         73.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-769x769.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_769x769_80k_cityscapes/fcn_r18-d8_769x769_80k_cityscapes_20201225_021451-9739d1b8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_769x769_80k_cityscapes/fcn_r18-d8_769x769_80k_cityscapes-20201225_021451.log.json)                             |
-| FCN        | R-50-D8    | 769x769   |   80000 | -        | -              | 72.64 |         73.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb2-80k_cityscapes-769x769.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_80k_cityscapes/fcn_r50-d8_769x769_80k_cityscapes_20200606_195749-f5caeabc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_80k_cityscapes/fcn_r50-d8_769x769_80k_cityscapes_20200606_195749.log.json)                             |
-| FCN        | R-101-D8   | 769x769   |   80000 | -        | -              | 75.52 |         76.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb2-80k_cityscapes-769x769.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_80k_cityscapes/fcn_r101-d8_769x769_80k_cityscapes_20200606_214354-45cbac68.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_80k_cityscapes/fcn_r101-d8_769x769_80k_cityscapes_20200606_214354.log.json)                         |
-| FCN        | R-18b-D8   | 512x1024  |   80000 | 1.6      | 16.74          | 70.24 |         72.77 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r18b-d8_4xb2-80k_cityscapes-512x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_512x1024_80k_cityscapes/fcn_r18b-d8_512x1024_80k_cityscapes_20201225_230143-92c0f445.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_512x1024_80k_cityscapes/fcn_r18b-d8_512x1024_80k_cityscapes-20201225_230143.log.json)                     |
-| FCN        | R-50b-D8   | 512x1024  |   80000 | 5.6      | 4.20           | 75.65 |         77.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50b-d8_4xb2-80k_cityscapes-512x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_512x1024_80k_cityscapes/fcn_r50b-d8_512x1024_80k_cityscapes_20201225_094221-82957416.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_512x1024_80k_cityscapes/fcn_r50b-d8_512x1024_80k_cityscapes-20201225_094221.log.json)                     |
-| FCN        | R-101b-D8  | 512x1024  |   80000 | 9.1      | 2.73           | 77.37 |         78.77 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101b-d8_4xb2-80k_cityscapes-512x1024.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_512x1024_80k_cityscapes/fcn_r101b-d8_512x1024_80k_cityscapes_20201226_160213-4543858f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_512x1024_80k_cityscapes/fcn_r101b-d8_512x1024_80k_cityscapes-20201226_160213.log.json)                 |
-| FCN        | R-18b-D8   | 769x769   |   80000 | 1.7      | 6.70           | 69.66 |         72.07 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r18b-d8_4xb2-80k_cityscapes-769x769.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_769x769_80k_cityscapes/fcn_r18b-d8_769x769_80k_cityscapes_20201226_004430-32d504e5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_769x769_80k_cityscapes/fcn_r18b-d8_769x769_80k_cityscapes-20201226_004430.log.json)                         |
-| FCN        | R-50b-D8   | 769x769   |   80000 | 6.3      | 1.82           | 73.83 |         76.60 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50b-d8_4xb2-80k_cityscapes-769x769.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_769x769_80k_cityscapes/fcn_r50b-d8_769x769_80k_cityscapes_20201225_094223-94552d38.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_769x769_80k_cityscapes/fcn_r50b-d8_769x769_80k_cityscapes-20201225_094223.log.json)                         |
-| FCN        | R-101b-D8  | 769x769   |   80000 | 10.3     | 1.15           | 77.02 |         78.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101b-d8_4xb2-80k_cityscapes-769x769.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_769x769_80k_cityscapes/fcn_r101b-d8_769x769_80k_cityscapes_20201226_170012-82be37e2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_769x769_80k_cityscapes/fcn_r101b-d8_769x769_80k_cityscapes-20201226_170012.log.json)                     |
-| FCN (D6)   | R-50-D16   | 512x1024  |   40000 | 3.4      | 10.22          | 77.06 |         78.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r50-d16_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes_20210305_130133-98d5d1bc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes-20210305_130133.log.json)         |
-| FCN (D6)   | R-50-D16   | 512x1024  |   80000 | -        | 10.35          | 77.27 |         78.88 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r50-d16_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_80k_cityscapes_20210306_115604-133c292f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_80k_cityscapes-20210306_115604.log.json)         |
-| FCN (D6)   | R-50-D16   | 769x769   |   40000 | 3.7      | 4.17           | 76.82 |         78.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r50-d16_4xb2-40k_cityscapes-769x769.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes_20210305_185744-1aab18ed.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes-20210305_185744.log.json)             |
-| FCN (D6)   | R-50-D16   | 769x769   |   80000 | -        | 4.15           | 77.04 |         78.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r50-d16_4xb2-80k_cityscapes-769x769.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes_20210305_200413-109d88eb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes-20210305_200413.log.json)             |
-| FCN (D6)   | R-101-D16  | 512x1024  |   40000 | 4.5      | 8.04           | 77.36 |         79.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r101-d16_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes_20210305_130337-9cf2b450.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes-20210305_130337.log.json)     |
-| FCN (D6)   | R-101-D16  | 512x1024  |   80000 | -        | 8.26           | 78.46 |         80.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r101-d16_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes_20210308_102747-cb336445.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes-20210308_102747.log.json)     |
-| FCN (D6)   | R-101-D16  | 769x769   |   40000 | 5.0      | 3.12           | 77.28 |         78.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r101-d16_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes_20210308_102453-60b114e9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes-20210308_102453.log.json)         |
-| FCN (D6)   | R-101-D16  | 769x769   |   80000 | -        | 3.21           | 78.06 |         79.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r101-d16_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes_20210306_120016-e33adc4f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes-20210306_120016.log.json)         |
-| FCN (D6)   | R-50b-D16  | 512x1024  |   80000 | 3.2      | 10.16          | 76.99 |         79.03 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r50b-d16_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_512x1024_80k_cityscapes/fcn_d6_r50b-d16_512x1024_80k_cityscapes_20210311_125550-6a0b62e9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_512x1024_80k_cityscapes/fcn_d6_r50b_d16_512x1024_80k_cityscapes-20210311_125550.log.json)     |
-| FCN (D6)   | R-50b-D16  | 769x769   |   80000 | 3.6      | 4.17           | 76.86 |         78.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r50b-d16_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_769x769_80k_cityscapes/fcn_d6_r50b-d16_769x769_80k_cityscapes_20210311_131012-d665f231.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_769x769_80k_cityscapes/fcn_d6_r50b_d16_769x769_80k_cityscapes-20210311_131012.log.json)         |
-| FCN (D6)   | R-101b-D16 | 512x1024  |   80000 | 4.3      | 8.46           | 77.72 |         79.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r101b-d16_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_512x1024_80k_cityscapes/fcn_d6_r101b-d16_512x1024_80k_cityscapes_20210311_144305-3f2eb5b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_512x1024_80k_cityscapes/fcn_d6_r101b_d16_512x1024_80k_cityscapes-20210311_144305.log.json) |
-| FCN (D6)   | R-101b-D16 | 769x769   |   80000 | 4.8      | 3.32           | 77.34 |         78.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r101b-d16_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_769x769_80k_cityscapes/fcn_d6_r101b-d16_769x769_80k_cityscapes_20210311_154527-c4d8bfbc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_769x769_80k_cityscapes/fcn_d6_r101b_d16_769x769_80k_cityscapes-20210311_154527.log.json)     |
+| Method     | Backbone   | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device   |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                   |
+| ---------- | ---------- | --------- | ------: | -------- | -------------- | -------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN        | R-50-D8    | 512x1024  |   40000 | 5.7      | 4.17           | V100     | 72.25 |         73.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_40k_cityscapes/fcn_r50-d8_512x1024_40k_cityscapes_20200604_192608-efe53f0d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_40k_cityscapes/fcn_r50-d8_512x1024_40k_cityscapes_20200604_192608.log.json)                         |
+| FCN        | R-101-D8   | 512x1024  |   40000 | 9.2      | 2.66           | V100     | 75.45 |         76.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb2-40k_cityscapes-512x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_40k_cityscapes/fcn_r101-d8_512x1024_40k_cityscapes_20200604_181852-a883d3a1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_40k_cityscapes/fcn_r101-d8_512x1024_40k_cityscapes_20200604_181852.log.json)                     |
+| FCN        | R-50-D8    | 769x769   |   40000 | 6.5      | 1.80           | V100     | 71.47 |         72.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-769x769.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_40k_cityscapes/fcn_r50-d8_769x769_40k_cityscapes_20200606_113104-977b5d02.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_40k_cityscapes/fcn_r50-d8_769x769_40k_cityscapes_20200606_113104.log.json)                             |
+| FCN        | R-101-D8   | 769x769   |   40000 | 10.4     | 1.19           | V100     | 73.93 |         75.14 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb2-40k_cityscapes-769x769.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_40k_cityscapes/fcn_r101-d8_769x769_40k_cityscapes_20200606_113208-7d4ab69c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_40k_cityscapes/fcn_r101-d8_769x769_40k_cityscapes_20200606_113208.log.json)                         |
+| FCN        | R-18-D8    | 512x1024  |   80000 | 1.7      | 14.65          | V100     | 71.11 |         72.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_512x1024_80k_cityscapes/fcn_r18-d8_512x1024_80k_cityscapes_20201225_021327-6c50f8b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_512x1024_80k_cityscapes/fcn_r18-d8_512x1024_80k_cityscapes-20201225_021327.log.json)                         |
+| FCN        | R-50-D8    | 512x1024  |   80000 | -        |                | V100     | 73.61 |         74.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb2-80k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_80k_cityscapes/fcn_r50-d8_512x1024_80k_cityscapes_20200606_113019-03aa804d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_80k_cityscapes/fcn_r50-d8_512x1024_80k_cityscapes_20200606_113019.log.json)                         |
+| FCN        | R-101-D8   | 512x1024  |   80000 | -        | -              | V100     | 75.13 |         75.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb2-80k_cityscapes-512x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_80k_cityscapes/fcn_r101-d8_512x1024_80k_cityscapes_20200606_113038-3fb937eb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_80k_cityscapes/fcn_r101-d8_512x1024_80k_cityscapes_20200606_113038.log.json)                     |
+| FCN (FP16) | R-101-D8   | 512x1024  |   80000 | 5.37     | 8.64           | V100     | 76.80 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_fp16_512x1024_80k_cityscapes/fcn_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230921-fb13e883.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_fp16_512x1024_80k_cityscapes/fcn_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230921.log.json) |
+| FCN        | R-18-D8    | 769x769   |   80000 | 1.9      | 6.40           | V100     | 70.80 |         73.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-769x769.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_769x769_80k_cityscapes/fcn_r18-d8_769x769_80k_cityscapes_20201225_021451-9739d1b8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_769x769_80k_cityscapes/fcn_r18-d8_769x769_80k_cityscapes-20201225_021451.log.json)                             |
+| FCN        | R-50-D8    | 769x769   |   80000 | -        | -              | V100     | 72.64 |         73.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb2-80k_cityscapes-769x769.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_80k_cityscapes/fcn_r50-d8_769x769_80k_cityscapes_20200606_195749-f5caeabc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_80k_cityscapes/fcn_r50-d8_769x769_80k_cityscapes_20200606_195749.log.json)                             |
+| FCN        | R-101-D8   | 769x769   |   80000 | -        | -              | V100     | 75.52 |         76.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb2-80k_cityscapes-769x769.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_80k_cityscapes/fcn_r101-d8_769x769_80k_cityscapes_20200606_214354-45cbac68.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_80k_cityscapes/fcn_r101-d8_769x769_80k_cityscapes_20200606_214354.log.json)                         |
+| FCN        | R-18b-D8   | 512x1024  |   80000 | 1.6      | 16.74          | V100     | 70.24 |         72.77 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r18b-d8_4xb2-80k_cityscapes-512x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_512x1024_80k_cityscapes/fcn_r18b-d8_512x1024_80k_cityscapes_20201225_230143-92c0f445.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_512x1024_80k_cityscapes/fcn_r18b-d8_512x1024_80k_cityscapes-20201225_230143.log.json)                     |
+| FCN        | R-50b-D8   | 512x1024  |   80000 | 5.6      | 4.20           | V100     | 75.65 |         77.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50b-d8_4xb2-80k_cityscapes-512x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_512x1024_80k_cityscapes/fcn_r50b-d8_512x1024_80k_cityscapes_20201225_094221-82957416.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_512x1024_80k_cityscapes/fcn_r50b-d8_512x1024_80k_cityscapes-20201225_094221.log.json)                     |
+| FCN        | R-101b-D8  | 512x1024  |   80000 | 9.1      | 2.73           | V100     | 77.37 |         78.77 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101b-d8_4xb2-80k_cityscapes-512x1024.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_512x1024_80k_cityscapes/fcn_r101b-d8_512x1024_80k_cityscapes_20201226_160213-4543858f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_512x1024_80k_cityscapes/fcn_r101b-d8_512x1024_80k_cityscapes-20201226_160213.log.json)                 |
+| FCN        | R-18b-D8   | 769x769   |   80000 | 1.7      | 6.70           | V100     | 69.66 |         72.07 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r18b-d8_4xb2-80k_cityscapes-769x769.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_769x769_80k_cityscapes/fcn_r18b-d8_769x769_80k_cityscapes_20201226_004430-32d504e5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_769x769_80k_cityscapes/fcn_r18b-d8_769x769_80k_cityscapes-20201226_004430.log.json)                         |
+| FCN        | R-50b-D8   | 769x769   |   80000 | 6.3      | 1.82           | V100     | 73.83 |         76.60 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50b-d8_4xb2-80k_cityscapes-769x769.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_769x769_80k_cityscapes/fcn_r50b-d8_769x769_80k_cityscapes_20201225_094223-94552d38.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_769x769_80k_cityscapes/fcn_r50b-d8_769x769_80k_cityscapes-20201225_094223.log.json)                         |
+| FCN        | R-101b-D8  | 769x769   |   80000 | 10.3     | 1.15           | V100     | 77.02 |         78.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101b-d8_4xb2-80k_cityscapes-769x769.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_769x769_80k_cityscapes/fcn_r101b-d8_769x769_80k_cityscapes_20201226_170012-82be37e2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_769x769_80k_cityscapes/fcn_r101b-d8_769x769_80k_cityscapes-20201226_170012.log.json)                     |
+| FCN (D6)   | R-50-D16   | 512x1024  |   40000 | 3.4      | 10.22          | TITAN Xp | 77.06 |         78.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r50-d16_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes_20210305_130133-98d5d1bc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes-20210305_130133.log.json)         |
+| FCN (D6)   | R-50-D16   | 512x1024  |   80000 | -        | 10.35          | TITAN Xp | 77.27 |         78.88 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r50-d16_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_80k_cityscapes_20210306_115604-133c292f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_80k_cityscapes-20210306_115604.log.json)         |
+| FCN (D6)   | R-50-D16   | 769x769   |   40000 | 3.7      | 4.17           | TITAN Xp | 76.82 |         78.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r50-d16_4xb2-40k_cityscapes-769x769.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes_20210305_185744-1aab18ed.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes-20210305_185744.log.json)             |
+| FCN (D6)   | R-50-D16   | 769x769   |   80000 | -        | 4.15           | TITAN Xp | 77.04 |         78.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r50-d16_4xb2-80k_cityscapes-769x769.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes_20210305_200413-109d88eb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes-20210305_200413.log.json)             |
+| FCN (D6)   | R-101-D16  | 512x1024  |   40000 | 4.5      | 8.04           | TITAN Xp | 77.36 |         79.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r101-d16_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes_20210305_130337-9cf2b450.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes-20210305_130337.log.json)     |
+| FCN (D6)   | R-101-D16  | 512x1024  |   80000 | -        | 8.26           | TITAN Xp | 78.46 |         80.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r101-d16_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes_20210308_102747-cb336445.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes-20210308_102747.log.json)     |
+| FCN (D6)   | R-101-D16  | 769x769   |   40000 | 5.0      | 3.12           | TITAN Xp | 77.28 |         78.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r101-d16_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes_20210308_102453-60b114e9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes-20210308_102453.log.json)         |
+| FCN (D6)   | R-101-D16  | 769x769   |   80000 | -        | 3.21           | TITAN Xp | 78.06 |         79.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r101-d16_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes_20210306_120016-e33adc4f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes-20210306_120016.log.json)         |
+| FCN (D6)   | R-50b-D16  | 512x1024  |   80000 | 3.2      | 10.16          | TITAN Xp | 76.99 |         79.03 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r50b-d16_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_512x1024_80k_cityscapes/fcn_d6_r50b-d16_512x1024_80k_cityscapes_20210311_125550-6a0b62e9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_512x1024_80k_cityscapes/fcn_d6_r50b_d16_512x1024_80k_cityscapes-20210311_125550.log.json)     |
+| FCN (D6)   | R-50b-D16  | 769x769   |   80000 | 3.6      | 4.17           | TITAN Xp | 76.86 |         78.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r50b-d16_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_769x769_80k_cityscapes/fcn_d6_r50b-d16_769x769_80k_cityscapes_20210311_131012-d665f231.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_769x769_80k_cityscapes/fcn_d6_r50b_d16_769x769_80k_cityscapes-20210311_131012.log.json)         |
+| FCN (D6)   | R-101b-D16 | 512x1024  |   80000 | 4.3      | 8.46           | TITAN Xp | 77.72 |         79.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r101b-d16_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_512x1024_80k_cityscapes/fcn_d6_r101b-d16_512x1024_80k_cityscapes_20210311_144305-3f2eb5b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_512x1024_80k_cityscapes/fcn_d6_r101b_d16_512x1024_80k_cityscapes-20210311_144305.log.json) |
+| FCN (D6)   | R-101b-D16 | 769x769   |   80000 | 4.8      | 3.32           | TITAN Xp | 77.34 |         78.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r101b-d16_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_769x769_80k_cityscapes/fcn_d6_r101b-d16_769x769_80k_cityscapes_20210311_154527-c4d8bfbc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_769x769_80k_cityscapes/fcn_d6_r101b_d16_769x769_80k_cityscapes-20210311_154527.log.json)     |
 
 ### ADE20K
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                                               |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN    | R-50-D8  | 512x512   |   80000 | 8.5      | 23.49          | 35.94 |         37.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_80k_ade20k/fcn_r50-d8_512x512_80k_ade20k_20200614_144016-f8ac5082.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_80k_ade20k/fcn_r50-d8_512x512_80k_ade20k_20200614_144016.log.json)         |
-| FCN    | R-101-D8 | 512x512   |   80000 | 12       | 14.78          | 39.61 |         40.83 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-80k_ade20k-512x512.pyy) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_80k_ade20k/fcn_r101-d8_512x512_80k_ade20k_20200615_014143-bc1809f7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_80k_ade20k/fcn_r101-d8_512x512_80k_ade20k_20200615_014143.log.json)     |
-| FCN    | R-50-D8  | 512x512   |  160000 | -        | -              | 36.10 |         38.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_160k_ade20k/fcn_r50-d8_512x512_160k_ade20k_20200615_100713-4edbc3b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_160k_ade20k/fcn_r50-d8_512x512_160k_ade20k_20200615_100713.log.json)     |
-| FCN    | R-101-D8 | 512x512   |  160000 | -        | -              | 39.91 |         41.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_160k_ade20k/fcn_r101-d8_512x512_160k_ade20k_20200615_105816-fd192bd5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_160k_ade20k/fcn_r101-d8_512x512_160k_ade20k_20200615_105816.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                                               |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN    | R-50-D8  | 512x512   |   80000 | 8.5      | 23.49          | V100   | 35.94 |         37.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_80k_ade20k/fcn_r50-d8_512x512_80k_ade20k_20200614_144016-f8ac5082.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_80k_ade20k/fcn_r50-d8_512x512_80k_ade20k_20200614_144016.log.json)         |
+| FCN    | R-101-D8 | 512x512   |   80000 | 12       | 14.78          | V100   | 39.61 |         40.83 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-80k_ade20k-512x512.pyy) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_80k_ade20k/fcn_r101-d8_512x512_80k_ade20k_20200615_014143-bc1809f7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_80k_ade20k/fcn_r101-d8_512x512_80k_ade20k_20200615_014143.log.json)     |
+| FCN    | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 36.10 |         38.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_160k_ade20k/fcn_r50-d8_512x512_160k_ade20k_20200615_100713-4edbc3b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_160k_ade20k/fcn_r50-d8_512x512_160k_ade20k_20200615_100713.log.json)     |
+| FCN    | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 39.91 |         41.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_160k_ade20k/fcn_r101-d8_512x512_160k_ade20k_20200615_105816-fd192bd5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_160k_ade20k/fcn_r101-d8_512x512_160k_ade20k_20200615_105816.log.json) |
 
 ### Pascal VOC 2012 + Aug
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                   | download                                                                                                                                                                                                                                                                                                                   |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN    | R-50-D8  | 512x512   |   20000 | 5.7      | 23.28          | 67.08 |         69.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_20k_voc12aug/fcn_r50-d8_512x512_20k_voc12aug_20200617_010715-52dc5306.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_20k_voc12aug/fcn_r50-d8_512x512_20k_voc12aug_20200617_010715.log.json)     |
-| FCN    | R-101-D8 | 512x512   |   20000 | 9.2      | 14.81          | 71.16 |         73.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_20k_voc12aug/fcn_r101-d8_512x512_20k_voc12aug_20200617_010842-0bb4e798.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_20k_voc12aug/fcn_r101-d8_512x512_20k_voc12aug_20200617_010842.log.json) |
-| FCN    | R-50-D8  | 512x512   |   40000 | -        | -              | 66.97 |         69.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_40k_voc12aug/fcn_r50-d8_512x512_40k_voc12aug_20200613_161222-5e2dbf40.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_40k_voc12aug/fcn_r50-d8_512x512_40k_voc12aug_20200613_161222.log.json)     |
-| FCN    | R-101-D8 | 512x512   |   40000 | -        | -              | 69.91 |         72.38 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_40k_voc12aug/fcn_r101-d8_512x512_40k_voc12aug_20200613_161240-4c8bcefd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_40k_voc12aug/fcn_r101-d8_512x512_40k_voc12aug_20200613_161240.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                   | download                                                                                                                                                                                                                                                                                                                   |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN    | R-50-D8  | 512x512   |   20000 | 5.7      | 23.28          | V100   | 67.08 |         69.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_20k_voc12aug/fcn_r50-d8_512x512_20k_voc12aug_20200617_010715-52dc5306.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_20k_voc12aug/fcn_r50-d8_512x512_20k_voc12aug_20200617_010715.log.json)     |
+| FCN    | R-101-D8 | 512x512   |   20000 | 9.2      | 14.81          | V100   | 71.16 |         73.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_20k_voc12aug/fcn_r101-d8_512x512_20k_voc12aug_20200617_010842-0bb4e798.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_20k_voc12aug/fcn_r101-d8_512x512_20k_voc12aug_20200617_010842.log.json) |
+| FCN    | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 66.97 |         69.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_40k_voc12aug/fcn_r50-d8_512x512_40k_voc12aug_20200613_161222-5e2dbf40.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_40k_voc12aug/fcn_r50-d8_512x512_40k_voc12aug_20200613_161222.log.json)     |
+| FCN    | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 69.91 |         72.38 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_40k_voc12aug/fcn_r101-d8_512x512_40k_voc12aug_20200613_161240-4c8bcefd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_40k_voc12aug/fcn_r101-d8_512x512_40k_voc12aug_20200613_161240.log.json) |
 
 ### Pascal Context
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN    | R-101-D8 | 480x480   |   40000 | -        | 9.93           | 44.43 |         45.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context_20210421_154757-b5e97937.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context-20210421_154757.log.json) |
-| FCN    | R-101-D8 | 480x480   |   80000 | -        | -              | 44.13 |         45.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context_20210421_163310-4711813f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context-20210421_163310.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN    | R-101-D8 | 480x480   |   40000 | -        | 9.93           | V100   | 44.43 |         45.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context_20210421_154757-b5e97937.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context-20210421_154757.log.json) |
+| FCN    | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 44.13 |         45.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context_20210421_163310-4711813f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context-20210421_163310.log.json) |
 
 ### Pascal Context 59
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                       |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN    | R-101-D8 | 480x480   |   40000 | -        | -              | 48.42 |          50.4 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context_59/fcn_r101-d8_480x480_40k_pascal_context_59_20210415_230724-8cf83682.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context_59/fcn_r101-d8_480x480_40k_pascal_context_59-20210415_230724.log.json) |
-| FCN    | R-101-D8 | 480x480   |   80000 | -        | -              | 49.35 |         51.38 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context_59/fcn_r101-d8_480x480_80k_pascal_context_59_20210416_110804-9a6f2c94.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context_59/fcn_r101-d8_480x480_80k_pascal_context_59-20210416_110804.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                       |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN    | R-101-D8 | 480x480   |   40000 | -        | -              | V100   | 48.42 |          50.4 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context_59/fcn_r101-d8_480x480_40k_pascal_context_59_20210415_230724-8cf83682.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context_59/fcn_r101-d8_480x480_40k_pascal_context_59-20210415_230724.log.json) |
+| FCN    | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 49.35 |         51.38 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context_59/fcn_r101-d8_480x480_80k_pascal_context_59_20210416_110804-9a6f2c94.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context_59/fcn_r101-d8_480x480_80k_pascal_context_59-20210416_110804.log.json) |
 
 Note:
 
 - `FP16` means Mixed Precision (FP16) is adopted in training.
 - `FCN D6` means dilation rate of convolution operator in FCN is 6.
+
+## Citation
+
+```bibtex
+@article{shelhamer2017fully,
+  title={Fully convolutional networks for semantic segmentation},
+  author={Shelhamer, Evan and Long, Jonathan and Darrell, Trevor},
+  journal={IEEE transactions on pattern analysis and machine intelligence},
+  volume={39},
+  number={4},
+  pages={640--651},
+  year={2017},
+  publisher={IEEE Trans Pattern Anal Mach Intell}
+}
+```
diff --git a/configs/fcn/fcn.yml b/configs/fcn/fcn.yml
deleted file mode 100644
index 71c4b2d122..0000000000
--- a/configs/fcn/fcn.yml
+++ /dev/null
@@ -1,827 +0,0 @@
-Collections:
-- Name: FCN
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-    - Pascal VOC 2012 + Aug
-    - Pascal Context
-    - Pascal Context 59
-  Paper:
-    URL: https://arxiv.org/abs/1411.4038
-    Title: Fully Convolutional Networks for Semantic Segmentation
-  README: configs/fcn/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/BVLC/caffe/wiki/Model-Zoo#fcn
-Models:
-- Name: fcn_r50-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 239.81
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 5.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 72.25
-      mIoU(ms+flip): 73.36
-  Config: configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_40k_cityscapes/fcn_r50-d8_512x1024_40k_cityscapes_20200604_192608-efe53f0d.pth
-- Name: fcn_r101-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 375.94
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 9.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 75.45
-      mIoU(ms+flip): 76.58
-  Config: configs/fcn/fcn_r101-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_40k_cityscapes/fcn_r101-d8_512x1024_40k_cityscapes_20200604_181852-a883d3a1.pth
-- Name: fcn_r50-d8_4xb2-40k_cityscapes-769x769
-  In Collection: FCN
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 555.56
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 6.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 71.47
-      mIoU(ms+flip): 72.54
-  Config: configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_40k_cityscapes/fcn_r50-d8_769x769_40k_cityscapes_20200606_113104-977b5d02.pth
-- Name: fcn_r101-d8_4xb2-40k_cityscapes-769x769
-  In Collection: FCN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 840.34
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 10.4
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 73.93
-      mIoU(ms+flip): 75.14
-  Config: configs/fcn/fcn_r101-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_40k_cityscapes/fcn_r101-d8_769x769_40k_cityscapes_20200606_113208-7d4ab69c.pth
-- Name: fcn_r18-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: R-18-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 68.26
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 1.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 71.11
-      mIoU(ms+flip): 72.91
-  Config: configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_512x1024_80k_cityscapes/fcn_r18-d8_512x1024_80k_cityscapes_20201225_021327-6c50f8b4.pth
-- Name: fcn_r50-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 73.61
-      mIoU(ms+flip): 74.24
-  Config: configs/fcn/fcn_r50-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_80k_cityscapes/fcn_r50-d8_512x1024_80k_cityscapes_20200606_113019-03aa804d.pth
-- Name: fcn_r101-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 75.13
-      mIoU(ms+flip): 75.94
-  Config: configs/fcn/fcn_r101-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_80k_cityscapes/fcn_r101-d8_512x1024_80k_cityscapes_20200606_113038-3fb937eb.pth
-- Name: fcn_r101-d8_4xb2-amp-80k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 115.74
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: AMP
-      resolution: (512,1024)
-    Training Memory (GB): 5.37
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.8
-  Config: configs/fcn/fcn_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_fp16_512x1024_80k_cityscapes/fcn_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230921-fb13e883.pth
-- Name: fcn_r18-d8_4xb2-80k_cityscapes-769x769
-  In Collection: FCN
-  Metadata:
-    backbone: R-18-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 156.25
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 1.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 70.8
-      mIoU(ms+flip): 73.16
-  Config: configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_769x769_80k_cityscapes/fcn_r18-d8_769x769_80k_cityscapes_20201225_021451-9739d1b8.pth
-- Name: fcn_r50-d8_4xb2-80k_cityscapes-769x769
-  In Collection: FCN
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 72.64
-      mIoU(ms+flip): 73.32
-  Config: configs/fcn/fcn_r50-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_80k_cityscapes/fcn_r50-d8_769x769_80k_cityscapes_20200606_195749-f5caeabc.pth
-- Name: fcn_r101-d8_4xb2-80k_cityscapes-769x769
-  In Collection: FCN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 75.52
-      mIoU(ms+flip): 76.61
-  Config: configs/fcn/fcn_r101-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_80k_cityscapes/fcn_r101-d8_769x769_80k_cityscapes_20200606_214354-45cbac68.pth
-- Name: fcn_r18b-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: R-18b-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 59.74
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 1.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 70.24
-      mIoU(ms+flip): 72.77
-  Config: configs/fcn/fcn_r18b-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_512x1024_80k_cityscapes/fcn_r18b-d8_512x1024_80k_cityscapes_20201225_230143-92c0f445.pth
-- Name: fcn_r50b-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: R-50b-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 238.1
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 5.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 75.65
-      mIoU(ms+flip): 77.59
-  Config: configs/fcn/fcn_r50b-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_512x1024_80k_cityscapes/fcn_r50b-d8_512x1024_80k_cityscapes_20201225_094221-82957416.pth
-- Name: fcn_r101b-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: R-101b-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 366.3
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 9.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.37
-      mIoU(ms+flip): 78.77
-  Config: configs/fcn/fcn_r101b-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_512x1024_80k_cityscapes/fcn_r101b-d8_512x1024_80k_cityscapes_20201226_160213-4543858f.pth
-- Name: fcn_r18b-d8_4xb2-80k_cityscapes-769x769
-  In Collection: FCN
-  Metadata:
-    backbone: R-18b-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 149.25
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 1.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 69.66
-      mIoU(ms+flip): 72.07
-  Config: configs/fcn/fcn_r18b-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_769x769_80k_cityscapes/fcn_r18b-d8_769x769_80k_cityscapes_20201226_004430-32d504e5.pth
-- Name: fcn_r50b-d8_4xb2-80k_cityscapes-769x769
-  In Collection: FCN
-  Metadata:
-    backbone: R-50b-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 549.45
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 6.3
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 73.83
-      mIoU(ms+flip): 76.6
-  Config: configs/fcn/fcn_r50b-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_769x769_80k_cityscapes/fcn_r50b-d8_769x769_80k_cityscapes_20201225_094223-94552d38.pth
-- Name: fcn_r101b-d8_4xb2-80k_cityscapes-769x769
-  In Collection: FCN
-  Metadata:
-    backbone: R-101b-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 869.57
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 10.3
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.02
-      mIoU(ms+flip): 78.67
-  Config: configs/fcn/fcn_r101b-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_769x769_80k_cityscapes/fcn_r101b-d8_769x769_80k_cityscapes_20201226_170012-82be37e2.pth
-- Name: fcn-d6_r50-d16_4xb2-40k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: R-50-D16
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 97.85
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 3.4
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.06
-      mIoU(ms+flip): 78.85
-  Config: configs/fcn/fcn-d6_r50-d16_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes_20210305_130133-98d5d1bc.pth
-- Name: fcn-d6_r50-d16_4xb2-80k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: R-50-D16
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 96.62
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.27
-      mIoU(ms+flip): 78.88
-  Config: configs/fcn/fcn-d6_r50-d16_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_80k_cityscapes_20210306_115604-133c292f.pth
-- Name: fcn-d6_r50-d16_4xb2-40k_cityscapes-769x769
-  In Collection: FCN
-  Metadata:
-    backbone: R-50-D16
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 239.81
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 3.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.82
-      mIoU(ms+flip): 78.22
-  Config: configs/fcn/fcn-d6_r50-d16_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes_20210305_185744-1aab18ed.pth
-- Name: fcn-d6_r50-d16_4xb2-80k_cityscapes-769x769
-  In Collection: FCN
-  Metadata:
-    backbone: R-50-D16
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 240.96
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.04
-      mIoU(ms+flip): 78.4
-  Config: configs/fcn/fcn-d6_r50-d16_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes_20210305_200413-109d88eb.pth
-- Name: fcn-d6_r101-d16_4xb2-40k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: R-101-D16
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 124.38
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 4.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.36
-      mIoU(ms+flip): 79.18
-  Config: configs/fcn/fcn-d6_r101-d16_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes_20210305_130337-9cf2b450.pth
-- Name: fcn-d6_r101-d16_4xb2-80k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: R-101-D16
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 121.07
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.46
-      mIoU(ms+flip): 80.42
-  Config: configs/fcn/fcn-d6_r101-d16_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes_20210308_102747-cb336445.pth
-- Name: fcn-d6_r101-d16_4xb2-40k_cityscapes-769x769
-  In Collection: FCN
-  Metadata:
-    backbone: R-101-D16
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 320.51
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 5.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.28
-      mIoU(ms+flip): 78.95
-  Config: configs/fcn/fcn-d6_r101-d16_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes_20210308_102453-60b114e9.pth
-- Name: fcn-d6_r101-d16_4xb2-80k_cityscapes-769x769
-  In Collection: FCN
-  Metadata:
-    backbone: R-101-D16
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 311.53
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.06
-      mIoU(ms+flip): 79.58
-  Config: configs/fcn/fcn-d6_r101-d16_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes_20210306_120016-e33adc4f.pth
-- Name: fcn-d6_r50b-d16_4xb2-80k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: R-50b-D16
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 98.43
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 3.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.99
-      mIoU(ms+flip): 79.03
-  Config: configs/fcn/fcn-d6_r50b-d16_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_512x1024_80k_cityscapes/fcn_d6_r50b-d16_512x1024_80k_cityscapes_20210311_125550-6a0b62e9.pth
-- Name: fcn-d6_r50b-d16_4xb2-80k_cityscapes-769x769
-  In Collection: FCN
-  Metadata:
-    backbone: R-50b-D16
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 239.81
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 3.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.86
-      mIoU(ms+flip): 78.52
-  Config: configs/fcn/fcn-d6_r50b-d16_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_769x769_80k_cityscapes/fcn_d6_r50b-d16_769x769_80k_cityscapes_20210311_131012-d665f231.pth
-- Name: fcn-d6_r101b-d16_4xb2-80k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: R-101b-D16
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 118.2
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 4.3
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.72
-      mIoU(ms+flip): 79.53
-  Config: configs/fcn/fcn-d6_r101b-d16_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_512x1024_80k_cityscapes/fcn_d6_r101b-d16_512x1024_80k_cityscapes_20210311_144305-3f2eb5b4.pth
-- Name: fcn-d6_r101b-d16_4xb2-80k_cityscapes-769x769
-  In Collection: FCN
-  Metadata:
-    backbone: R-101b-D16
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 301.2
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 4.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.34
-      mIoU(ms+flip): 78.91
-  Config: configs/fcn/fcn-d6_r101b-d16_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_769x769_80k_cityscapes/fcn_d6_r101b-d16_769x769_80k_cityscapes_20210311_154527-c4d8bfbc.pth
-- Name: fcn_r50-d8_4xb4-80k_ade20k-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 42.57
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 8.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 35.94
-      mIoU(ms+flip): 37.94
-  Config: configs/fcn/fcn_r50-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_80k_ade20k/fcn_r50-d8_512x512_80k_ade20k_20200614_144016-f8ac5082.pth
-- Name: fcn_r101-d8_4xb4-80k_ade20k-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 67.66
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 12.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 39.61
-      mIoU(ms+flip): 40.83
-  Config: configs/fcn/fcn_r101-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_80k_ade20k/fcn_r101-d8_512x512_80k_ade20k_20200615_014143-bc1809f7.pth
-- Name: fcn_r50-d8_4xb4-160k_ade20k-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 36.1
-      mIoU(ms+flip): 38.08
-  Config: configs/fcn/fcn_r50-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_160k_ade20k/fcn_r50-d8_512x512_160k_ade20k_20200615_100713-4edbc3b4.pth
-- Name: fcn_r101-d8_4xb4-160k_ade20k-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 39.91
-      mIoU(ms+flip): 41.4
-  Config: configs/fcn/fcn_r101-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_160k_ade20k/fcn_r101-d8_512x512_160k_ade20k_20200615_105816-fd192bd5.pth
-- Name: fcn_r50-d8_4xb4-20k_voc12aug-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 42.96
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 5.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 67.08
-      mIoU(ms+flip): 69.94
-  Config: configs/fcn/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_20k_voc12aug/fcn_r50-d8_512x512_20k_voc12aug_20200617_010715-52dc5306.pth
-- Name: fcn_r101-d8_4xb4-20k_voc12aug-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 67.52
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 71.16
-      mIoU(ms+flip): 73.57
-  Config: configs/fcn/fcn_r101-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_20k_voc12aug/fcn_r101-d8_512x512_20k_voc12aug_20200617_010842-0bb4e798.pth
-- Name: fcn_r50-d8_4xb4-40k_voc12aug-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 66.97
-      mIoU(ms+flip): 69.04
-  Config: configs/fcn/fcn_r50-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_40k_voc12aug/fcn_r50-d8_512x512_40k_voc12aug_20200613_161222-5e2dbf40.pth
-- Name: fcn_r101-d8_4xb4-40k_voc12aug-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 69.91
-      mIoU(ms+flip): 72.38
-  Config: configs/fcn/fcn_r101-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_40k_voc12aug/fcn_r101-d8_512x512_40k_voc12aug_20200613_161240-4c8bcefd.pth
-- Name: fcn_r101-d8_4xb4-40k_pascal-context-480x480
-  In Collection: FCN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (480,480)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 100.7
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (480,480)
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context
-    Metrics:
-      mIoU: 44.43
-      mIoU(ms+flip): 45.63
-  Config: configs/fcn/fcn_r101-d8_4xb4-40k_pascal-context-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context_20210421_154757-b5e97937.pth
-- Name: fcn_r101-d8_4xb4-80k_pascal-context-480x480
-  In Collection: FCN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (480,480)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context
-    Metrics:
-      mIoU: 44.13
-      mIoU(ms+flip): 45.26
-  Config: configs/fcn/fcn_r101-d8_4xb4-80k_pascal-context-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context_20210421_163310-4711813f.pth
-- Name: fcn_r101-d8_4xb4-40k_pascal-context-59-480x480
-  In Collection: FCN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (480,480)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context 59
-    Metrics:
-      mIoU: 48.42
-      mIoU(ms+flip): 50.4
-  Config: configs/fcn/fcn_r101-d8_4xb4-40k_pascal-context-59-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context_59/fcn_r101-d8_480x480_40k_pascal_context_59_20210415_230724-8cf83682.pth
-- Name: fcn_r101-d8_4xb4-80k_pascal-context-59-480x480
-  In Collection: FCN
-  Metadata:
-    backbone: R-101-D8
-    crop size: (480,480)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context 59
-    Metrics:
-      mIoU: 49.35
-      mIoU(ms+flip): 51.38
-  Config: configs/fcn/fcn_r101-d8_4xb4-80k_pascal-context-59-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context_59/fcn_r101-d8_480x480_80k_pascal_context_59_20210416_110804-9a6f2c94.pth
diff --git a/configs/fcn/metafile.yaml b/configs/fcn/metafile.yaml
new file mode 100644
index 0000000000..f3d80f652e
--- /dev/null
+++ b/configs/fcn/metafile.yaml
@@ -0,0 +1,997 @@
+Collections:
+- Name: FCN
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - ADE20K
+    - Pascal VOC 2012 + Aug
+    - Pascal Context
+    - Pascal Context 59
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  README: configs/fcn/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: fcn_r50-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 72.25
+      mIoU(ms+flip): 73.36
+  Config: configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_40k_cityscapes/fcn_r50-d8_512x1024_40k_cityscapes_20200604_192608-efe53f0d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_40k_cityscapes/fcn_r50-d8_512x1024_40k_cityscapes_20200604_192608.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r101-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 75.45
+      mIoU(ms+flip): 76.58
+  Config: configs/fcn/fcn_r101-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_40k_cityscapes/fcn_r101-d8_512x1024_40k_cityscapes_20200604_181852-a883d3a1.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_40k_cityscapes/fcn_r101-d8_512x1024_40k_cityscapes_20200604_181852.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r50-d8_4xb2-40k_cityscapes-769x769
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 71.47
+      mIoU(ms+flip): 72.54
+  Config: configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_40k_cityscapes/fcn_r50-d8_769x769_40k_cityscapes_20200606_113104-977b5d02.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_40k_cityscapes/fcn_r50-d8_769x769_40k_cityscapes_20200606_113104.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r101-d8_4xb2-40k_cityscapes-769x769
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 73.93
+      mIoU(ms+flip): 75.14
+  Config: configs/fcn/fcn_r101-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.4
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_40k_cityscapes/fcn_r101-d8_769x769_40k_cityscapes_20200606_113208-7d4ab69c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_40k_cityscapes/fcn_r101-d8_769x769_40k_cityscapes_20200606_113208.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r18-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 71.11
+      mIoU(ms+flip): 72.91
+  Config: configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_512x1024_80k_cityscapes/fcn_r18-d8_512x1024_80k_cityscapes_20201225_021327-6c50f8b4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_512x1024_80k_cityscapes/fcn_r18-d8_512x1024_80k_cityscapes-20201225_021327.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r50-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 73.61
+      mIoU(ms+flip): 74.24
+  Config: configs/fcn/fcn_r50-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_80k_cityscapes/fcn_r50-d8_512x1024_80k_cityscapes_20200606_113019-03aa804d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_80k_cityscapes/fcn_r50-d8_512x1024_80k_cityscapes_20200606_113019.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r101-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 75.13
+      mIoU(ms+flip): 75.94
+  Config: configs/fcn/fcn_r101-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_80k_cityscapes/fcn_r101-d8_512x1024_80k_cityscapes_20200606_113038-3fb937eb.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_80k_cityscapes/fcn_r101-d8_512x1024_80k_cityscapes_20200606_113038.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r101-d8_4xb2-amp-80k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.8
+  Config: configs/fcn/fcn_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - FCN
+    - (FP16)
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.37
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_fp16_512x1024_80k_cityscapes/fcn_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230921-fb13e883.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_fp16_512x1024_80k_cityscapes/fcn_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230921.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r18-d8_4xb2-80k_cityscapes-769x769
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 70.8
+      mIoU(ms+flip): 73.16
+  Config: configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_769x769_80k_cityscapes/fcn_r18-d8_769x769_80k_cityscapes_20201225_021451-9739d1b8.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_769x769_80k_cityscapes/fcn_r18-d8_769x769_80k_cityscapes-20201225_021451.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r50-d8_4xb2-80k_cityscapes-769x769
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 72.64
+      mIoU(ms+flip): 73.32
+  Config: configs/fcn/fcn_r50-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_80k_cityscapes/fcn_r50-d8_769x769_80k_cityscapes_20200606_195749-f5caeabc.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_80k_cityscapes/fcn_r50-d8_769x769_80k_cityscapes_20200606_195749.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r101-d8_4xb2-80k_cityscapes-769x769
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 75.52
+      mIoU(ms+flip): 76.61
+  Config: configs/fcn/fcn_r101-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_80k_cityscapes/fcn_r101-d8_769x769_80k_cityscapes_20200606_214354-45cbac68.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_80k_cityscapes/fcn_r101-d8_769x769_80k_cityscapes_20200606_214354.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r18b-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 70.24
+      mIoU(ms+flip): 72.77
+  Config: configs/fcn/fcn_r18b-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18b-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_512x1024_80k_cityscapes/fcn_r18b-d8_512x1024_80k_cityscapes_20201225_230143-92c0f445.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_512x1024_80k_cityscapes/fcn_r18b-d8_512x1024_80k_cityscapes-20201225_230143.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r50b-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 75.65
+      mIoU(ms+flip): 77.59
+  Config: configs/fcn/fcn_r50b-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50b-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_512x1024_80k_cityscapes/fcn_r50b-d8_512x1024_80k_cityscapes_20201225_094221-82957416.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_512x1024_80k_cityscapes/fcn_r50b-d8_512x1024_80k_cityscapes-20201225_094221.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r101b-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.37
+      mIoU(ms+flip): 78.77
+  Config: configs/fcn/fcn_r101b-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101b-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_512x1024_80k_cityscapes/fcn_r101b-d8_512x1024_80k_cityscapes_20201226_160213-4543858f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_512x1024_80k_cityscapes/fcn_r101b-d8_512x1024_80k_cityscapes-20201226_160213.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r18b-d8_4xb2-80k_cityscapes-769x769
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 69.66
+      mIoU(ms+flip): 72.07
+  Config: configs/fcn/fcn_r18b-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18b-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_769x769_80k_cityscapes/fcn_r18b-d8_769x769_80k_cityscapes_20201226_004430-32d504e5.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_769x769_80k_cityscapes/fcn_r18b-d8_769x769_80k_cityscapes-20201226_004430.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r50b-d8_4xb2-80k_cityscapes-769x769
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 73.83
+      mIoU(ms+flip): 76.6
+  Config: configs/fcn/fcn_r50b-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50b-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.3
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_769x769_80k_cityscapes/fcn_r50b-d8_769x769_80k_cityscapes_20201225_094223-94552d38.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_769x769_80k_cityscapes/fcn_r50b-d8_769x769_80k_cityscapes-20201225_094223.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r101b-d8_4xb2-80k_cityscapes-769x769
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.02
+      mIoU(ms+flip): 78.67
+  Config: configs/fcn/fcn_r101b-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101b-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.3
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_769x769_80k_cityscapes/fcn_r101b-d8_769x769_80k_cityscapes_20201226_170012-82be37e2.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_769x769_80k_cityscapes/fcn_r101b-d8_769x769_80k_cityscapes-20201226_170012.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn-d6_r50-d16_4xb2-40k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.06
+      mIoU(ms+flip): 78.85
+  Config: configs/fcn/fcn-d6_r50-d16_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D16
+    - FCN
+    - (D6)
+    Training Resources: 4x TITAN Xp GPUS
+    Memory (GB): 3.4
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes_20210305_130133-98d5d1bc.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes-20210305_130133.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn-d6_r50-d16_4xb2-80k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.27
+      mIoU(ms+flip): 78.88
+  Config: configs/fcn/fcn-d6_r50-d16_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D16
+    - FCN
+    - (D6)
+    Training Resources: 4x TITAN Xp GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_80k_cityscapes_20210306_115604-133c292f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_80k_cityscapes-20210306_115604.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn-d6_r50-d16_4xb2-40k_cityscapes-769x769
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.82
+      mIoU(ms+flip): 78.22
+  Config: configs/fcn/fcn-d6_r50-d16_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D16
+    - FCN
+    - (D6)
+    Training Resources: 4x TITAN Xp GPUS
+    Memory (GB): 3.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes_20210305_185744-1aab18ed.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes-20210305_185744.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn-d6_r50-d16_4xb2-80k_cityscapes-769x769
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.04
+      mIoU(ms+flip): 78.4
+  Config: configs/fcn/fcn-d6_r50-d16_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D16
+    - FCN
+    - (D6)
+    Training Resources: 4x TITAN Xp GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes_20210305_200413-109d88eb.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes-20210305_200413.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn-d6_r101-d16_4xb2-40k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.36
+      mIoU(ms+flip): 79.18
+  Config: configs/fcn/fcn-d6_r101-d16_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D16
+    - FCN
+    - (D6)
+    Training Resources: 4x TITAN Xp GPUS
+    Memory (GB): 4.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes_20210305_130337-9cf2b450.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes-20210305_130337.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn-d6_r101-d16_4xb2-80k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.46
+      mIoU(ms+flip): 80.42
+  Config: configs/fcn/fcn-d6_r101-d16_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D16
+    - FCN
+    - (D6)
+    Training Resources: 4x TITAN Xp GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes_20210308_102747-cb336445.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes-20210308_102747.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn-d6_r101-d16_4xb2-40k_cityscapes-769x769
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.28
+      mIoU(ms+flip): 78.95
+  Config: configs/fcn/fcn-d6_r101-d16_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D16
+    - FCN
+    - (D6)
+    Training Resources: 4x TITAN Xp GPUS
+    Memory (GB): 5.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes_20210308_102453-60b114e9.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes-20210308_102453.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn-d6_r101-d16_4xb2-80k_cityscapes-769x769
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.06
+      mIoU(ms+flip): 79.58
+  Config: configs/fcn/fcn-d6_r101-d16_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D16
+    - FCN
+    - (D6)
+    Training Resources: 4x TITAN Xp GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes_20210306_120016-e33adc4f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes-20210306_120016.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn-d6_r50b-d16_4xb2-80k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.99
+      mIoU(ms+flip): 79.03
+  Config: configs/fcn/fcn-d6_r50b-d16_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50b-D16
+    - FCN
+    - (D6)
+    Training Resources: 4x TITAN Xp GPUS
+    Memory (GB): 3.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_512x1024_80k_cityscapes/fcn_d6_r50b-d16_512x1024_80k_cityscapes_20210311_125550-6a0b62e9.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_512x1024_80k_cityscapes/fcn_d6_r50b_d16_512x1024_80k_cityscapes-20210311_125550.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn-d6_r50b-d16_4xb2-80k_cityscapes-769x769
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.86
+      mIoU(ms+flip): 78.52
+  Config: configs/fcn/fcn-d6_r50b-d16_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50b-D16
+    - FCN
+    - (D6)
+    Training Resources: 4x TITAN Xp GPUS
+    Memory (GB): 3.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_769x769_80k_cityscapes/fcn_d6_r50b-d16_769x769_80k_cityscapes_20210311_131012-d665f231.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_769x769_80k_cityscapes/fcn_d6_r50b_d16_769x769_80k_cityscapes-20210311_131012.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn-d6_r101b-d16_4xb2-80k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.72
+      mIoU(ms+flip): 79.53
+  Config: configs/fcn/fcn-d6_r101b-d16_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101b-D16
+    - FCN
+    - (D6)
+    Training Resources: 4x TITAN Xp GPUS
+    Memory (GB): 4.3
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_512x1024_80k_cityscapes/fcn_d6_r101b-d16_512x1024_80k_cityscapes_20210311_144305-3f2eb5b4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_512x1024_80k_cityscapes/fcn_d6_r101b_d16_512x1024_80k_cityscapes-20210311_144305.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn-d6_r101b-d16_4xb2-80k_cityscapes-769x769
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.34
+      mIoU(ms+flip): 78.91
+  Config: configs/fcn/fcn-d6_r101b-d16_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101b-D16
+    - FCN
+    - (D6)
+    Training Resources: 4x TITAN Xp GPUS
+    Memory (GB): 4.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_769x769_80k_cityscapes/fcn_d6_r101b-d16_769x769_80k_cityscapes_20210311_154527-c4d8bfbc.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_769x769_80k_cityscapes/fcn_d6_r101b_d16_769x769_80k_cityscapes-20210311_154527.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r50-d8_4xb4-80k_ade20k-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 35.94
+      mIoU(ms+flip): 37.94
+  Config: configs/fcn/fcn_r50-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_80k_ade20k/fcn_r50-d8_512x512_80k_ade20k_20200614_144016-f8ac5082.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_80k_ade20k/fcn_r50-d8_512x512_80k_ade20k_20200614_144016.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r101-d8_4xb4-80k_ade20k-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 39.61
+      mIoU(ms+flip): 40.83
+  Config: configs/fcn/fcn_r101-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 12.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_80k_ade20k/fcn_r101-d8_512x512_80k_ade20k_20200615_014143-bc1809f7.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_80k_ade20k/fcn_r101-d8_512x512_80k_ade20k_20200615_014143.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r50-d8_4xb4-160k_ade20k-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 36.1
+      mIoU(ms+flip): 38.08
+  Config: configs/fcn/fcn_r50-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_160k_ade20k/fcn_r50-d8_512x512_160k_ade20k_20200615_100713-4edbc3b4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_160k_ade20k/fcn_r50-d8_512x512_160k_ade20k_20200615_100713.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r101-d8_4xb4-160k_ade20k-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 39.91
+      mIoU(ms+flip): 41.4
+  Config: configs/fcn/fcn_r101-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_160k_ade20k/fcn_r101-d8_512x512_160k_ade20k_20200615_105816-fd192bd5.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_160k_ade20k/fcn_r101-d8_512x512_160k_ade20k_20200615_105816.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r50-d8_4xb4-20k_voc12aug-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 67.08
+      mIoU(ms+flip): 69.94
+  Config: configs/fcn/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_20k_voc12aug/fcn_r50-d8_512x512_20k_voc12aug_20200617_010715-52dc5306.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_20k_voc12aug/fcn_r50-d8_512x512_20k_voc12aug_20200617_010715.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r101-d8_4xb4-20k_voc12aug-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 71.16
+      mIoU(ms+flip): 73.57
+  Config: configs/fcn/fcn_r101-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_20k_voc12aug/fcn_r101-d8_512x512_20k_voc12aug_20200617_010842-0bb4e798.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_20k_voc12aug/fcn_r101-d8_512x512_20k_voc12aug_20200617_010842.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r50-d8_4xb4-40k_voc12aug-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 66.97
+      mIoU(ms+flip): 69.04
+  Config: configs/fcn/fcn_r50-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_40k_voc12aug/fcn_r50-d8_512x512_40k_voc12aug_20200613_161222-5e2dbf40.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_40k_voc12aug/fcn_r50-d8_512x512_40k_voc12aug_20200613_161222.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r101-d8_4xb4-40k_voc12aug-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 69.91
+      mIoU(ms+flip): 72.38
+  Config: configs/fcn/fcn_r101-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_40k_voc12aug/fcn_r101-d8_512x512_40k_voc12aug_20200613_161240-4c8bcefd.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_40k_voc12aug/fcn_r101-d8_512x512_40k_voc12aug_20200613_161240.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r101-d8_4xb4-40k_pascal-context-480x480
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context
+    Metrics:
+      mIoU: 44.43
+      mIoU(ms+flip): 45.63
+  Config: configs/fcn/fcn_r101-d8_4xb4-40k_pascal-context-480x480.py
+  Metadata:
+    Training Data: Pascal Context
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context_20210421_154757-b5e97937.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context-20210421_154757.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r101-d8_4xb4-80k_pascal-context-480x480
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context
+    Metrics:
+      mIoU: 44.13
+      mIoU(ms+flip): 45.26
+  Config: configs/fcn/fcn_r101-d8_4xb4-80k_pascal-context-480x480.py
+  Metadata:
+    Training Data: Pascal Context
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context_20210421_163310-4711813f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context-20210421_163310.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r101-d8_4xb4-40k_pascal-context-59-480x480
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context 59
+    Metrics:
+      mIoU: 48.42
+      mIoU(ms+flip): 50.4
+  Config: configs/fcn/fcn_r101-d8_4xb4-40k_pascal-context-59-480x480.py
+  Metadata:
+    Training Data: Pascal Context 59
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context_59/fcn_r101-d8_480x480_40k_pascal_context_59_20210415_230724-8cf83682.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context_59/fcn_r101-d8_480x480_40k_pascal_context_59-20210415_230724.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
+- Name: fcn_r101-d8_4xb4-80k_pascal-context-59-480x480
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context 59
+    Metrics:
+      mIoU: 49.35
+      mIoU(ms+flip): 51.38
+  Config: configs/fcn/fcn_r101-d8_4xb4-80k_pascal-context-59-480x480.py
+  Metadata:
+    Training Data: Pascal Context 59
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context_59/fcn_r101-d8_480x480_80k_pascal_context_59_20210416_110804-9a6f2c94.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context_59/fcn_r101-d8_480x480_80k_pascal_context_59-20210416_110804.log.json
+  Paper:
+    Title: Fully Convolutional Networks for Semantic Segmentation
+    URL: https://arxiv.org/abs/1411.4038
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
+  Framework: PyTorch
diff --git a/configs/gcnet/README.md b/configs/gcnet/README.md
index fa37f76468..26a478808f 100644
--- a/configs/gcnet/README.md
+++ b/configs/gcnet/README.md
@@ -1,6 +1,6 @@
 # GCNet
 
-[GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond](https://arxiv.org/abs/1904.11492)
+> [GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond](https://arxiv.org/abs/1904.11492)
 
 ## Introduction
 
@@ -22,6 +22,39 @@ The Non-Local Network (NLNet) presents a pioneering approach for capturing long-
 <img src="https://user-images.githubusercontent.com/24582831/142901601-ad17922e-2538-4b48-9f51-84a57d44b12b.png" width="80%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| GCNet  | R-50-D8  | 512x1024  |   40000 | 5.8      | 3.93           | V100   | 77.69 |         78.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes/gcnet_r50-d8_512x1024_40k_cityscapes_20200618_074436-4b0fd17b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes/gcnet_r50-d8_512x1024_40k_cityscapes_20200618_074436.log.json)     |
+| GCNet  | R-101-D8 | 512x1024  |   40000 | 9.2      | 2.61           | V100   | 78.28 |         79.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes/gcnet_r101-d8_512x1024_40k_cityscapes_20200618_074436-5e62567f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes/gcnet_r101-d8_512x1024_40k_cityscapes_20200618_074436.log.json) |
+| GCNet  | R-50-D8  | 769x769   |   40000 | 6.5      | 1.67           | V100   | 78.12 |         80.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-769x769.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_40k_cityscapes/gcnet_r50-d8_769x769_40k_cityscapes_20200618_182814-a26f4471.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_40k_cityscapes/gcnet_r50-d8_769x769_40k_cityscapes_20200618_182814.log.json)         |
+| GCNet  | R-101-D8 | 769x769   |   40000 | 10.5     | 1.13           | V100   | 78.95 |         80.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_40k_cityscapes/gcnet_r101-d8_769x769_40k_cityscapes_20200619_092550-ca4f0a84.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_40k_cityscapes/gcnet_r101-d8_769x769_40k_cityscapes_20200619_092550.log.json)     |
+| GCNet  | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 78.48 |         80.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes/gcnet_r50-d8_512x1024_80k_cityscapes_20200618_074450-ef8f069b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes/gcnet_r50-d8_512x1024_80k_cityscapes_20200618_074450.log.json)     |
+| GCNet  | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 79.03 |         79.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb2-80k_cityscapes-512x1024.pyy) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes/gcnet_r101-d8_512x1024_80k_cityscapes_20200618_074450-778ebf69.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes/gcnet_r101-d8_512x1024_80k_cityscapes_20200618_074450.log.json) |
+| GCNet  | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 78.68 |         80.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb2-80k_cityscapes-769x769.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_80k_cityscapes/gcnet_r50-d8_769x769_80k_cityscapes_20200619_092516-4839565b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_80k_cityscapes/gcnet_r50-d8_769x769_80k_cityscapes_20200619_092516.log.json)         |
+| GCNet  | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 79.18 |         80.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_80k_cityscapes/gcnet_r101-d8_769x769_80k_cityscapes_20200619_092628-8e043423.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_80k_cityscapes/gcnet_r101-d8_769x769_80k_cityscapes_20200619_092628.log.json)     |
+
+### ADE20K
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| GCNet  | R-50-D8  | 512x512   |   80000 | 8.5      | 23.38          | V100   | 41.47 |         42.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_80k_ade20k/gcnet_r50-d8_512x512_80k_ade20k_20200614_185146-91a6da41.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_80k_ade20k/gcnet_r50-d8_512x512_80k_ade20k_20200614_185146.log.json)         |
+| GCNet  | R-101-D8 | 512x512   |   80000 | 12       | 15.20          | V100   | 42.82 |         44.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_80k_ade20k/gcnet_r101-d8_512x512_80k_ade20k_20200615_020811-c3fcb6dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_80k_ade20k/gcnet_r101-d8_512x512_80k_ade20k_20200615_020811.log.json)     |
+| GCNet  | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 42.37 |         43.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_160k_ade20k/gcnet_r50-d8_512x512_160k_ade20k_20200615_224122-d95f3e1f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_160k_ade20k/gcnet_r50-d8_512x512_160k_ade20k_20200615_224122.log.json)     |
+| GCNet  | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 43.69 |         45.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_160k_ade20k/gcnet_r101-d8_512x512_160k_ade20k_20200615_225406-615528d7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_160k_ade20k/gcnet_r101-d8_512x512_160k_ade20k_20200615_225406.log.json) |
+
+### Pascal VOC 2012 + Aug
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                               |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| GCNet  | R-50-D8  | 512x512   |   20000 | 5.8      | 23.35          | V100   | 76.42 |         77.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_20k_voc12aug/gcnet_r50-d8_512x512_20k_voc12aug_20200617_165701-3cbfdab1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_20k_voc12aug/gcnet_r50-d8_512x512_20k_voc12aug_20200617_165701.log.json)     |
+| GCNet  | R-101-D8 | 512x512   |   20000 | 9.2      | 14.80          | V100   | 77.41 |         78.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_20k_voc12aug/gcnet_r101-d8_512x512_20k_voc12aug_20200617_165713-6c720aa9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_20k_voc12aug/gcnet_r101-d8_512x512_20k_voc12aug_20200617_165713.log.json) |
+| GCNet  | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 76.24 |         77.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_40k_voc12aug/gcnet_r50-d8_512x512_40k_voc12aug_20200613_195105-9797336d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_40k_voc12aug/gcnet_r50-d8_512x512_40k_voc12aug_20200613_195105.log.json)     |
+| GCNet  | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 77.84 |         78.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_40k_voc12aug/gcnet_r101-d8_512x512_40k_voc12aug_20200613_185806-1e38208d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_40k_voc12aug/gcnet_r101-d8_512x512_40k_voc12aug_20200613_185806.log.json) |
+
 ## Citation
 
 ```bibtex
@@ -33,36 +66,3 @@ The Non-Local Network (NLNet) presents a pioneering approach for capturing long-
   year={2019}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| GCNet  | R-50-D8  | 512x1024  |   40000 | 5.8      | 3.93           | 77.69 |         78.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes/gcnet_r50-d8_512x1024_40k_cityscapes_20200618_074436-4b0fd17b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes/gcnet_r50-d8_512x1024_40k_cityscapes_20200618_074436.log.json)     |
-| GCNet  | R-101-D8 | 512x1024  |   40000 | 9.2      | 2.61           | 78.28 |         79.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes/gcnet_r101-d8_512x1024_40k_cityscapes_20200618_074436-5e62567f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes/gcnet_r101-d8_512x1024_40k_cityscapes_20200618_074436.log.json) |
-| GCNet  | R-50-D8  | 769x769   |   40000 | 6.5      | 1.67           | 78.12 |         80.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-769x769.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_40k_cityscapes/gcnet_r50-d8_769x769_40k_cityscapes_20200618_182814-a26f4471.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_40k_cityscapes/gcnet_r50-d8_769x769_40k_cityscapes_20200618_182814.log.json)         |
-| GCNet  | R-101-D8 | 769x769   |   40000 | 10.5     | 1.13           | 78.95 |         80.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_40k_cityscapes/gcnet_r101-d8_769x769_40k_cityscapes_20200619_092550-ca4f0a84.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_40k_cityscapes/gcnet_r101-d8_769x769_40k_cityscapes_20200619_092550.log.json)     |
-| GCNet  | R-50-D8  | 512x1024  |   80000 | -        | -              | 78.48 |         80.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes/gcnet_r50-d8_512x1024_80k_cityscapes_20200618_074450-ef8f069b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes/gcnet_r50-d8_512x1024_80k_cityscapes_20200618_074450.log.json)     |
-| GCNet  | R-101-D8 | 512x1024  |   80000 | -        | -              | 79.03 |         79.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb2-80k_cityscapes-512x1024.pyy) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes/gcnet_r101-d8_512x1024_80k_cityscapes_20200618_074450-778ebf69.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes/gcnet_r101-d8_512x1024_80k_cityscapes_20200618_074450.log.json) |
-| GCNet  | R-50-D8  | 769x769   |   80000 | -        | -              | 78.68 |         80.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb2-80k_cityscapes-769x769.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_80k_cityscapes/gcnet_r50-d8_769x769_80k_cityscapes_20200619_092516-4839565b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_80k_cityscapes/gcnet_r50-d8_769x769_80k_cityscapes_20200619_092516.log.json)         |
-| GCNet  | R-101-D8 | 769x769   |   80000 | -        | -              | 79.18 |         80.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_80k_cityscapes/gcnet_r101-d8_769x769_80k_cityscapes_20200619_092628-8e043423.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_80k_cityscapes/gcnet_r101-d8_769x769_80k_cityscapes_20200619_092628.log.json)     |
-
-### ADE20K
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| GCNet  | R-50-D8  | 512x512   |   80000 | 8.5      | 23.38          | 41.47 |         42.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_80k_ade20k/gcnet_r50-d8_512x512_80k_ade20k_20200614_185146-91a6da41.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_80k_ade20k/gcnet_r50-d8_512x512_80k_ade20k_20200614_185146.log.json)         |
-| GCNet  | R-101-D8 | 512x512   |   80000 | 12       | 15.20          | 42.82 |         44.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_80k_ade20k/gcnet_r101-d8_512x512_80k_ade20k_20200615_020811-c3fcb6dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_80k_ade20k/gcnet_r101-d8_512x512_80k_ade20k_20200615_020811.log.json)     |
-| GCNet  | R-50-D8  | 512x512   |  160000 | -        | -              | 42.37 |         43.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_160k_ade20k/gcnet_r50-d8_512x512_160k_ade20k_20200615_224122-d95f3e1f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_160k_ade20k/gcnet_r50-d8_512x512_160k_ade20k_20200615_224122.log.json)     |
-| GCNet  | R-101-D8 | 512x512   |  160000 | -        | -              | 43.69 |         45.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_160k_ade20k/gcnet_r101-d8_512x512_160k_ade20k_20200615_225406-615528d7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_160k_ade20k/gcnet_r101-d8_512x512_160k_ade20k_20200615_225406.log.json) |
-
-### Pascal VOC 2012 + Aug
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                               |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| GCNet  | R-50-D8  | 512x512   |   20000 | 5.8      | 23.35          | 76.42 |         77.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_20k_voc12aug/gcnet_r50-d8_512x512_20k_voc12aug_20200617_165701-3cbfdab1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_20k_voc12aug/gcnet_r50-d8_512x512_20k_voc12aug_20200617_165701.log.json)     |
-| GCNet  | R-101-D8 | 512x512   |   20000 | 9.2      | 14.80          | 77.41 |         78.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_20k_voc12aug/gcnet_r101-d8_512x512_20k_voc12aug_20200617_165713-6c720aa9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_20k_voc12aug/gcnet_r101-d8_512x512_20k_voc12aug_20200617_165713.log.json) |
-| GCNet  | R-50-D8  | 512x512   |   40000 | -        | -              | 76.24 |         77.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_40k_voc12aug/gcnet_r50-d8_512x512_40k_voc12aug_20200613_195105-9797336d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_40k_voc12aug/gcnet_r50-d8_512x512_40k_voc12aug_20200613_195105.log.json)     |
-| GCNet  | R-101-D8 | 512x512   |   40000 | -        | -              | 77.84 |         78.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_40k_voc12aug/gcnet_r101-d8_512x512_40k_voc12aug_20200613_185806-1e38208d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_40k_voc12aug/gcnet_r101-d8_512x512_40k_voc12aug_20200613_185806.log.json) |
diff --git a/configs/gcnet/gcnet.yml b/configs/gcnet/gcnet.yml
deleted file mode 100644
index dfd8cf56c4..0000000000
--- a/configs/gcnet/gcnet.yml
+++ /dev/null
@@ -1,305 +0,0 @@
-Collections:
-- Name: GCNet
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-    - Pascal VOC 2012 + Aug
-  Paper:
-    URL: https://arxiv.org/abs/1904.11492
-    Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
-  README: configs/gcnet/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/xvjiarui/GCNet
-Models:
-- Name: gcnet_r50-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: GCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 254.45
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 5.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.69
-      mIoU(ms+flip): 78.56
-  Config: configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes/gcnet_r50-d8_512x1024_40k_cityscapes_20200618_074436-4b0fd17b.pth
-- Name: gcnet_r101-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: GCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 383.14
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 9.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.28
-      mIoU(ms+flip): 79.34
-  Config: configs/gcnet/gcnet_r101-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes/gcnet_r101-d8_512x1024_40k_cityscapes_20200618_074436-5e62567f.pth
-- Name: gcnet_r50-d8_4xb2-40k_cityscapes-769x769
-  In Collection: GCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 598.8
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 6.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.12
-      mIoU(ms+flip): 80.09
-  Config: configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_40k_cityscapes/gcnet_r50-d8_769x769_40k_cityscapes_20200618_182814-a26f4471.pth
-- Name: gcnet_r101-d8_4xb2-40k_cityscapes-769x769
-  In Collection: GCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 884.96
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 10.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.95
-      mIoU(ms+flip): 80.71
-  Config: configs/gcnet/gcnet_r101-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_40k_cityscapes/gcnet_r101-d8_769x769_40k_cityscapes_20200619_092550-ca4f0a84.pth
-- Name: gcnet_r50-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: GCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.48
-      mIoU(ms+flip): 80.01
-  Config: configs/gcnet/gcnet_r50-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes/gcnet_r50-d8_512x1024_80k_cityscapes_20200618_074450-ef8f069b.pth
-- Name: gcnet_r101-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: GCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.03
-      mIoU(ms+flip): 79.84
-  Config: configs/gcnet/gcnet_r101-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes/gcnet_r101-d8_512x1024_80k_cityscapes_20200618_074450-778ebf69.pth
-- Name: gcnet_r50-d8_4xb2-80k_cityscapes-769x769
-  In Collection: GCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.68
-      mIoU(ms+flip): 80.66
-  Config: configs/gcnet/gcnet_r50-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_80k_cityscapes/gcnet_r50-d8_769x769_80k_cityscapes_20200619_092516-4839565b.pth
-- Name: gcnet_r101-d8_4xb2-80k_cityscapes-769x769
-  In Collection: GCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.18
-      mIoU(ms+flip): 80.71
-  Config: configs/gcnet/gcnet_r101-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_80k_cityscapes/gcnet_r101-d8_769x769_80k_cityscapes_20200619_092628-8e043423.pth
-- Name: gcnet_r50-d8_4xb4-80k_ade20k-512x512
-  In Collection: GCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 42.77
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 8.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 41.47
-      mIoU(ms+flip): 42.85
-  Config: configs/gcnet/gcnet_r50-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_80k_ade20k/gcnet_r50-d8_512x512_80k_ade20k_20200614_185146-91a6da41.pth
-- Name: gcnet_r101-d8_4xb4-80k_ade20k-512x512
-  In Collection: GCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 65.79
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 12.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.82
-      mIoU(ms+flip): 44.54
-  Config: configs/gcnet/gcnet_r101-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_80k_ade20k/gcnet_r101-d8_512x512_80k_ade20k_20200615_020811-c3fcb6dd.pth
-- Name: gcnet_r50-d8_4xb4-160k_ade20k-512x512
-  In Collection: GCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.37
-      mIoU(ms+flip): 43.52
-  Config: configs/gcnet/gcnet_r50-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_160k_ade20k/gcnet_r50-d8_512x512_160k_ade20k_20200615_224122-d95f3e1f.pth
-- Name: gcnet_r101-d8_4xb4-160k_ade20k-512x512
-  In Collection: GCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.69
-      mIoU(ms+flip): 45.21
-  Config: configs/gcnet/gcnet_r101-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_160k_ade20k/gcnet_r101-d8_512x512_160k_ade20k_20200615_225406-615528d7.pth
-- Name: gcnet_r50-d8_4xb4-20k_voc12aug-512x512
-  In Collection: GCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 42.83
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 5.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 76.42
-      mIoU(ms+flip): 77.51
-  Config: configs/gcnet/gcnet_r50-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_20k_voc12aug/gcnet_r50-d8_512x512_20k_voc12aug_20200617_165701-3cbfdab1.pth
-- Name: gcnet_r101-d8_4xb4-20k_voc12aug-512x512
-  In Collection: GCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 67.57
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 77.41
-      mIoU(ms+flip): 78.56
-  Config: configs/gcnet/gcnet_r101-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_20k_voc12aug/gcnet_r101-d8_512x512_20k_voc12aug_20200617_165713-6c720aa9.pth
-- Name: gcnet_r50-d8_4xb4-40k_voc12aug-512x512
-  In Collection: GCNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 76.24
-      mIoU(ms+flip): 77.63
-  Config: configs/gcnet/gcnet_r50-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_40k_voc12aug/gcnet_r50-d8_512x512_40k_voc12aug_20200613_195105-9797336d.pth
-- Name: gcnet_r101-d8_4xb4-40k_voc12aug-512x512
-  In Collection: GCNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 77.84
-      mIoU(ms+flip): 78.59
-  Config: configs/gcnet/gcnet_r101-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_40k_voc12aug/gcnet_r101-d8_512x512_40k_voc12aug_20200613_185806-1e38208d.pth
diff --git a/configs/gcnet/metafile.yaml b/configs/gcnet/metafile.yaml
new file mode 100644
index 0000000000..1f3c4623a0
--- /dev/null
+++ b/configs/gcnet/metafile.yaml
@@ -0,0 +1,391 @@
+Collections:
+- Name: GCNet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - ADE20K
+    - Pascal VOC 2012 + Aug
+  Paper:
+    Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
+    URL: https://arxiv.org/abs/1904.11492
+  README: configs/gcnet/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: gcnet_r50-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: GCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.69
+      mIoU(ms+flip): 78.56
+  Config: configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - GCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes/gcnet_r50-d8_512x1024_40k_cityscapes_20200618_074436-4b0fd17b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes/gcnet_r50-d8_512x1024_40k_cityscapes_20200618_074436.log.json
+  Paper:
+    Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
+    URL: https://arxiv.org/abs/1904.11492
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
+  Framework: PyTorch
+- Name: gcnet_r101-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: GCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.28
+      mIoU(ms+flip): 79.34
+  Config: configs/gcnet/gcnet_r101-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - GCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes/gcnet_r101-d8_512x1024_40k_cityscapes_20200618_074436-5e62567f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes/gcnet_r101-d8_512x1024_40k_cityscapes_20200618_074436.log.json
+  Paper:
+    Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
+    URL: https://arxiv.org/abs/1904.11492
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
+  Framework: PyTorch
+- Name: gcnet_r50-d8_4xb2-40k_cityscapes-769x769
+  In Collection: GCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.12
+      mIoU(ms+flip): 80.09
+  Config: configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - GCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_40k_cityscapes/gcnet_r50-d8_769x769_40k_cityscapes_20200618_182814-a26f4471.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_40k_cityscapes/gcnet_r50-d8_769x769_40k_cityscapes_20200618_182814.log.json
+  Paper:
+    Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
+    URL: https://arxiv.org/abs/1904.11492
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
+  Framework: PyTorch
+- Name: gcnet_r101-d8_4xb2-40k_cityscapes-769x769
+  In Collection: GCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.95
+      mIoU(ms+flip): 80.71
+  Config: configs/gcnet/gcnet_r101-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - GCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_40k_cityscapes/gcnet_r101-d8_769x769_40k_cityscapes_20200619_092550-ca4f0a84.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_40k_cityscapes/gcnet_r101-d8_769x769_40k_cityscapes_20200619_092550.log.json
+  Paper:
+    Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
+    URL: https://arxiv.org/abs/1904.11492
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
+  Framework: PyTorch
+- Name: gcnet_r50-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: GCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.48
+      mIoU(ms+flip): 80.01
+  Config: configs/gcnet/gcnet_r50-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - GCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes/gcnet_r50-d8_512x1024_80k_cityscapes_20200618_074450-ef8f069b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes/gcnet_r50-d8_512x1024_80k_cityscapes_20200618_074450.log.json
+  Paper:
+    Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
+    URL: https://arxiv.org/abs/1904.11492
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
+  Framework: PyTorch
+- Name: gcnet_r101-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: GCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.03
+      mIoU(ms+flip): 79.84
+  Config: configs/gcnet/gcnet_r101-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - GCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes/gcnet_r101-d8_512x1024_80k_cityscapes_20200618_074450-778ebf69.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes/gcnet_r101-d8_512x1024_80k_cityscapes_20200618_074450.log.json
+  Paper:
+    Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
+    URL: https://arxiv.org/abs/1904.11492
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
+  Framework: PyTorch
+- Name: gcnet_r50-d8_4xb2-80k_cityscapes-769x769
+  In Collection: GCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.68
+      mIoU(ms+flip): 80.66
+  Config: configs/gcnet/gcnet_r50-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - GCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_80k_cityscapes/gcnet_r50-d8_769x769_80k_cityscapes_20200619_092516-4839565b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_80k_cityscapes/gcnet_r50-d8_769x769_80k_cityscapes_20200619_092516.log.json
+  Paper:
+    Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
+    URL: https://arxiv.org/abs/1904.11492
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
+  Framework: PyTorch
+- Name: gcnet_r101-d8_4xb2-80k_cityscapes-769x769
+  In Collection: GCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.18
+      mIoU(ms+flip): 80.71
+  Config: configs/gcnet/gcnet_r101-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - GCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_80k_cityscapes/gcnet_r101-d8_769x769_80k_cityscapes_20200619_092628-8e043423.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_80k_cityscapes/gcnet_r101-d8_769x769_80k_cityscapes_20200619_092628.log.json
+  Paper:
+    Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
+    URL: https://arxiv.org/abs/1904.11492
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
+  Framework: PyTorch
+- Name: gcnet_r50-d8_4xb4-80k_ade20k-512x512
+  In Collection: GCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 41.47
+      mIoU(ms+flip): 42.85
+  Config: configs/gcnet/gcnet_r50-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - GCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_80k_ade20k/gcnet_r50-d8_512x512_80k_ade20k_20200614_185146-91a6da41.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_80k_ade20k/gcnet_r50-d8_512x512_80k_ade20k_20200614_185146.log.json
+  Paper:
+    Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
+    URL: https://arxiv.org/abs/1904.11492
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
+  Framework: PyTorch
+- Name: gcnet_r101-d8_4xb4-80k_ade20k-512x512
+  In Collection: GCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.82
+      mIoU(ms+flip): 44.54
+  Config: configs/gcnet/gcnet_r101-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - GCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 12.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_80k_ade20k/gcnet_r101-d8_512x512_80k_ade20k_20200615_020811-c3fcb6dd.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_80k_ade20k/gcnet_r101-d8_512x512_80k_ade20k_20200615_020811.log.json
+  Paper:
+    Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
+    URL: https://arxiv.org/abs/1904.11492
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
+  Framework: PyTorch
+- Name: gcnet_r50-d8_4xb4-160k_ade20k-512x512
+  In Collection: GCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.37
+      mIoU(ms+flip): 43.52
+  Config: configs/gcnet/gcnet_r50-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - GCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_160k_ade20k/gcnet_r50-d8_512x512_160k_ade20k_20200615_224122-d95f3e1f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_160k_ade20k/gcnet_r50-d8_512x512_160k_ade20k_20200615_224122.log.json
+  Paper:
+    Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
+    URL: https://arxiv.org/abs/1904.11492
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
+  Framework: PyTorch
+- Name: gcnet_r101-d8_4xb4-160k_ade20k-512x512
+  In Collection: GCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.69
+      mIoU(ms+flip): 45.21
+  Config: configs/gcnet/gcnet_r101-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - GCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_160k_ade20k/gcnet_r101-d8_512x512_160k_ade20k_20200615_225406-615528d7.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_160k_ade20k/gcnet_r101-d8_512x512_160k_ade20k_20200615_225406.log.json
+  Paper:
+    Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
+    URL: https://arxiv.org/abs/1904.11492
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
+  Framework: PyTorch
+- Name: gcnet_r50-d8_4xb4-20k_voc12aug-512x512
+  In Collection: GCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 76.42
+      mIoU(ms+flip): 77.51
+  Config: configs/gcnet/gcnet_r50-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - GCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_20k_voc12aug/gcnet_r50-d8_512x512_20k_voc12aug_20200617_165701-3cbfdab1.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_20k_voc12aug/gcnet_r50-d8_512x512_20k_voc12aug_20200617_165701.log.json
+  Paper:
+    Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
+    URL: https://arxiv.org/abs/1904.11492
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
+  Framework: PyTorch
+- Name: gcnet_r101-d8_4xb4-20k_voc12aug-512x512
+  In Collection: GCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 77.41
+      mIoU(ms+flip): 78.56
+  Config: configs/gcnet/gcnet_r101-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - GCNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_20k_voc12aug/gcnet_r101-d8_512x512_20k_voc12aug_20200617_165713-6c720aa9.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_20k_voc12aug/gcnet_r101-d8_512x512_20k_voc12aug_20200617_165713.log.json
+  Paper:
+    Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
+    URL: https://arxiv.org/abs/1904.11492
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
+  Framework: PyTorch
+- Name: gcnet_r50-d8_4xb4-40k_voc12aug-512x512
+  In Collection: GCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 76.24
+      mIoU(ms+flip): 77.63
+  Config: configs/gcnet/gcnet_r50-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - GCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_40k_voc12aug/gcnet_r50-d8_512x512_40k_voc12aug_20200613_195105-9797336d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_40k_voc12aug/gcnet_r50-d8_512x512_40k_voc12aug_20200613_195105.log.json
+  Paper:
+    Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
+    URL: https://arxiv.org/abs/1904.11492
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
+  Framework: PyTorch
+- Name: gcnet_r101-d8_4xb4-40k_voc12aug-512x512
+  In Collection: GCNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 77.84
+      mIoU(ms+flip): 78.59
+  Config: configs/gcnet/gcnet_r101-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - GCNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_40k_voc12aug/gcnet_r101-d8_512x512_40k_voc12aug_20200613_185806-1e38208d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_40k_voc12aug/gcnet_r101-d8_512x512_40k_voc12aug_20200613_185806.log.json
+  Paper:
+    Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
+    URL: https://arxiv.org/abs/1904.11492
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
+  Framework: PyTorch
diff --git a/configs/hrnet/README.md b/configs/hrnet/README.md
index f85683b63f..38a6bd0e76 100644
--- a/configs/hrnet/README.md
+++ b/configs/hrnet/README.md
@@ -1,6 +1,6 @@
 # HRNet
 
-[Deep High-Resolution Representation Learning for Human Pose Estimation](https://arxiv.org/abs/1908.07919)
+> [Deep High-Resolution Representation Learning for Human Pose Estimation](https://arxiv.org/abs/1908.07919)
 
 ## Introduction
 
@@ -22,101 +22,101 @@ High-resolution representations are essential for position-sensitive vision prob
 <img src="https://user-images.githubusercontent.com/24582831/142901680-64c285bc-669f-4924-b054-46a2f07c5427.png" width="80%"/>
 </div>
 
-## Citation
-
-```bibtext
-@inproceedings{SunXLW19,
-  title={Deep High-Resolution Representation Learning for Human Pose Estimation},
-  author={Ke Sun and Bin Xiao and Dong Liu and Jingdong Wang},
-  booktitle={CVPR},
-  year={2019}
-}
-```
-
 ## Results and models
 
 ### Cityscapes
 
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                               |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN    | HRNetV2p-W18-Small | 512x1024  |   40000 | 1.7      | 23.74          | 73.86 |         75.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_40k_cityscapes/fcn_hr18s_512x1024_40k_cityscapes_20200601_014216-93db27d0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_40k_cityscapes/fcn_hr18s_512x1024_40k_cityscapes_20200601_014216.log.json)     |
-| FCN    | HRNetV2p-W18       | 512x1024  |   40000 | 2.9      | 12.97          | 77.19 |         78.92 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_40k_cityscapes/fcn_hr18_512x1024_40k_cityscapes_20200601_014216-f196fb4e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_40k_cityscapes/fcn_hr18_512x1024_40k_cityscapes_20200601_014216.log.json)         |
-| FCN    | HRNetV2p-W48       | 512x1024  |   40000 | 6.2      | 6.42           | 78.48 |         79.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_40k_cityscapes/fcn_hr48_512x1024_40k_cityscapes_20200601_014240-a989b146.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_40k_cityscapes/fcn_hr48_512x1024_40k_cityscapes_20200601_014240.log.json)         |
-| FCN    | HRNetV2p-W18-Small | 512x1024  |   80000 | -        | -              | 75.31 |         77.48 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_80k_cityscapes/fcn_hr18s_512x1024_80k_cityscapes_20200601_202700-1462b75d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_80k_cityscapes/fcn_hr18s_512x1024_80k_cityscapes_20200601_202700.log.json)     |
-| FCN    | HRNetV2p-W18       | 512x1024  |   80000 | -        | -              | 78.65 |         80.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_80k_cityscapes/fcn_hr18_512x1024_80k_cityscapes_20200601_223255-4e7b345e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_80k_cityscapes/fcn_hr18_512x1024_80k_cityscapes_20200601_223255.log.json)         |
-| FCN    | HRNetV2p-W48       | 512x1024  |   80000 | -        | -              | 79.93 |         80.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_80k_cityscapes/fcn_hr48_512x1024_80k_cityscapes_20200601_202606-58ea95d6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_80k_cityscapes/fcn_hr48_512x1024_80k_cityscapes_20200601_202606.log.json)         |
-| FCN    | HRNetV2p-W18-Small | 512x1024  |  160000 | -        | -              | 76.31 |         78.31 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb2-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_160k_cityscapes/fcn_hr18s_512x1024_160k_cityscapes_20200602_190901-4a0797ea.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_160k_cityscapes/fcn_hr18s_512x1024_160k_cityscapes_20200602_190901.log.json) |
-| FCN    | HRNetV2p-W18       | 512x1024  |  160000 | -        | -              | 78.80 |         80.74 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb2-160k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_160k_cityscapes/fcn_hr18_512x1024_160k_cityscapes_20200602_190822-221e4a4f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_160k_cityscapes/fcn_hr18_512x1024_160k_cityscapes_20200602_190822.log.json)     |
-| FCN    | HRNetV2p-W48       | 512x1024  |  160000 | -        | -              | 80.65 |         81.92 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb2-160k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_160k_cityscapes/fcn_hr48_512x1024_160k_cityscapes_20200602_190946-59b7973e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_160k_cityscapes/fcn_hr48_512x1024_160k_cityscapes_20200602_190946.log.json)     |
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                               |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN    | HRNetV2p-W18-Small | 512x1024  |   40000 | 1.7      | 23.74          | V100   | 73.86 |         75.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_40k_cityscapes/fcn_hr18s_512x1024_40k_cityscapes_20200601_014216-93db27d0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_40k_cityscapes/fcn_hr18s_512x1024_40k_cityscapes_20200601_014216.log.json)     |
+| FCN    | HRNetV2p-W18       | 512x1024  |   40000 | 2.9      | 12.97          | V100   | 77.19 |         78.92 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_40k_cityscapes/fcn_hr18_512x1024_40k_cityscapes_20200601_014216-f196fb4e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_40k_cityscapes/fcn_hr18_512x1024_40k_cityscapes_20200601_014216.log.json)         |
+| FCN    | HRNetV2p-W48       | 512x1024  |   40000 | 6.2      | 6.42           | V100   | 78.48 |         79.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_40k_cityscapes/fcn_hr48_512x1024_40k_cityscapes_20200601_014240-a989b146.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_40k_cityscapes/fcn_hr48_512x1024_40k_cityscapes_20200601_014240.log.json)         |
+| FCN    | HRNetV2p-W18-Small | 512x1024  |   80000 | -        | -              | V100   | 75.31 |         77.48 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_80k_cityscapes/fcn_hr18s_512x1024_80k_cityscapes_20200601_202700-1462b75d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_80k_cityscapes/fcn_hr18s_512x1024_80k_cityscapes_20200601_202700.log.json)     |
+| FCN    | HRNetV2p-W18       | 512x1024  |   80000 | -        | -              | V100   | 78.65 |         80.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_80k_cityscapes/fcn_hr18_512x1024_80k_cityscapes_20200601_223255-4e7b345e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_80k_cityscapes/fcn_hr18_512x1024_80k_cityscapes_20200601_223255.log.json)         |
+| FCN    | HRNetV2p-W48       | 512x1024  |   80000 | -        | -              | V100   | 79.93 |         80.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_80k_cityscapes/fcn_hr48_512x1024_80k_cityscapes_20200601_202606-58ea95d6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_80k_cityscapes/fcn_hr48_512x1024_80k_cityscapes_20200601_202606.log.json)         |
+| FCN    | HRNetV2p-W18-Small | 512x1024  |  160000 | -        | -              | V100   | 76.31 |         78.31 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb2-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_160k_cityscapes/fcn_hr18s_512x1024_160k_cityscapes_20200602_190901-4a0797ea.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_160k_cityscapes/fcn_hr18s_512x1024_160k_cityscapes_20200602_190901.log.json) |
+| FCN    | HRNetV2p-W18       | 512x1024  |  160000 | -        | -              | V100   | 78.80 |         80.74 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb2-160k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_160k_cityscapes/fcn_hr18_512x1024_160k_cityscapes_20200602_190822-221e4a4f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_160k_cityscapes/fcn_hr18_512x1024_160k_cityscapes_20200602_190822.log.json)     |
+| FCN    | HRNetV2p-W48       | 512x1024  |  160000 | -        | -              | V100   | 80.65 |         81.92 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb2-160k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_160k_cityscapes/fcn_hr48_512x1024_160k_cityscapes_20200602_190946-59b7973e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_160k_cityscapes/fcn_hr48_512x1024_160k_cityscapes_20200602_190946.log.json)     |
 
 ### ADE20K
 
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                                           |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| FCN    | HRNetV2p-W18-Small | 512x512   |   80000 | 3.8      | 38.66          | 31.38 |         32.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_ade20k/fcn_hr18s_512x512_80k_ade20k_20200614_144345-77fc814a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_ade20k/fcn_hr18s_512x512_80k_ade20k_20200614_144345.log.json)     |
-| FCN    | HRNetV2p-W18       | 512x512   |   80000 | 4.9      | 22.57          | 36.27 |         37.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20210827_114910-6c9382c0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20210827_114910.log.json)         |
-| FCN    | HRNetV2p-W48       | 512x512   |   80000 | 8.2      | 21.23          | 41.90 |         43.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_ade20k/fcn_hr48_512x512_80k_ade20k_20200614_193946-7ba5258d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_ade20k/fcn_hr48_512x512_80k_ade20k_20200614_193946.log.json)         |
-| FCN    | HRNetV2p-W18-Small | 512x512   |  160000 | -        | -              | 33.07 |         34.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20210829_174739-f1e7c2e7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20210829_174739.log.json) |
-| FCN    | HRNetV2p-W18       | 512x512   |  160000 | -        | -              | 36.79 |         38.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_160k_ade20k/fcn_hr18_512x512_160k_ade20k_20200614_214426-ca961836.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_160k_ade20k/fcn_hr18_512x512_160k_ade20k_20200614_214426.log.json)     |
-| FCN    | HRNetV2p-W48       | 512x512   |  160000 | -        | -              | 42.02 |         43.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_160k_ade20k/fcn_hr48_512x512_160k_ade20k_20200614_214407-a52fc02c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_160k_ade20k/fcn_hr48_512x512_160k_ade20k_20200614_214407.log.json)     |
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                                           |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| FCN    | HRNetV2p-W18-Small | 512x512   |   80000 | 3.8      | 38.66          | V100   | 31.38 |         32.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_ade20k/fcn_hr18s_512x512_80k_ade20k_20200614_144345-77fc814a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_ade20k/fcn_hr18s_512x512_80k_ade20k_20200614_144345.log.json)     |
+| FCN    | HRNetV2p-W18       | 512x512   |   80000 | 4.9      | 22.57          | V100   | 36.27 |         37.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20210827_114910-6c9382c0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20210827_114910.log.json)         |
+| FCN    | HRNetV2p-W48       | 512x512   |   80000 | 8.2      | 21.23          | V100   | 41.90 |         43.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_ade20k/fcn_hr48_512x512_80k_ade20k_20200614_193946-7ba5258d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_ade20k/fcn_hr48_512x512_80k_ade20k_20200614_193946.log.json)         |
+| FCN    | HRNetV2p-W18-Small | 512x512   |  160000 | -        | -              | V100   | 33.07 |         34.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20210829_174739-f1e7c2e7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20210829_174739.log.json) |
+| FCN    | HRNetV2p-W18       | 512x512   |  160000 | -        | -              | V100   | 36.79 |         38.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_160k_ade20k/fcn_hr18_512x512_160k_ade20k_20200614_214426-ca961836.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_160k_ade20k/fcn_hr18_512x512_160k_ade20k_20200614_214426.log.json)     |
+| FCN    | HRNetV2p-W48       | 512x512   |  160000 | -        | -              | V100   | 42.02 |         43.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_160k_ade20k/fcn_hr48_512x512_160k_ade20k_20200614_214407-a52fc02c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_160k_ade20k/fcn_hr48_512x512_160k_ade20k_20200614_214407.log.json)     |
 
 ### Pascal VOC 2012 + Aug
 
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                   | download                                                                                                                                                                                                                                                                                                               |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN    | HRNetV2p-W18-Small | 512x512   |   20000 | 1.8      | 43.36          |  65.5 |         68.89 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20210829_174910-0aceadb4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20210829_174910.log.json) |
-| FCN    | HRNetV2p-W18       | 512x512   |   20000 | 2.9      | 23.48          | 72.30 |         74.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_20k_voc12aug/fcn_hr18_512x512_20k_voc12aug_20200617_224503-488d45f7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_20k_voc12aug/fcn_hr18_512x512_20k_voc12aug_20200617_224503.log.json)     |
-| FCN    | HRNetV2p-W48       | 512x512   |   20000 | 6.2      | 22.05          | 75.87 |         78.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_20k_voc12aug/fcn_hr48_512x512_20k_voc12aug_20200617_224419-89de05cd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_20k_voc12aug/fcn_hr48_512x512_20k_voc12aug_20200617_224419.log.json)     |
-| FCN    | HRNetV2p-W18-Small | 512x512   |   40000 | -        | -              | 66.61 |         70.00 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_40k_voc12aug/fcn_hr18s_512x512_40k_voc12aug_20200614_000648-4f8d6e7f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_40k_voc12aug/fcn_hr18s_512x512_40k_voc12aug_20200614_000648.log.json) |
-| FCN    | HRNetV2p-W18       | 512x512   |   40000 | -        | -              | 72.90 |         75.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_40k_voc12aug/fcn_hr18_512x512_40k_voc12aug_20200613_224401-1b4b76cd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_40k_voc12aug/fcn_hr18_512x512_40k_voc12aug_20200613_224401.log.json)     |
-| FCN    | HRNetV2p-W48       | 512x512   |   40000 | -        | -              | 76.24 |         78.49 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_40k_voc12aug/fcn_hr48_512x512_40k_voc12aug_20200613_222111-1b0f18bc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_40k_voc12aug/fcn_hr48_512x512_40k_voc12aug_20200613_222111.log.json)     |
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                   | download                                                                                                                                                                                                                                                                                                               |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN    | HRNetV2p-W18-Small | 512x512   |   20000 | 1.8      | 43.36          | V100   |  65.5 |         68.89 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20210829_174910-0aceadb4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20210829_174910.log.json) |
+| FCN    | HRNetV2p-W18       | 512x512   |   20000 | 2.9      | 23.48          | V100   | 72.30 |         74.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_20k_voc12aug/fcn_hr18_512x512_20k_voc12aug_20200617_224503-488d45f7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_20k_voc12aug/fcn_hr18_512x512_20k_voc12aug_20200617_224503.log.json)     |
+| FCN    | HRNetV2p-W48       | 512x512   |   20000 | 6.2      | 22.05          | V100   | 75.87 |         78.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_20k_voc12aug/fcn_hr48_512x512_20k_voc12aug_20200617_224419-89de05cd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_20k_voc12aug/fcn_hr48_512x512_20k_voc12aug_20200617_224419.log.json)     |
+| FCN    | HRNetV2p-W18-Small | 512x512   |   40000 | -        | -              | V100   | 66.61 |         70.00 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_40k_voc12aug/fcn_hr18s_512x512_40k_voc12aug_20200614_000648-4f8d6e7f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_40k_voc12aug/fcn_hr18s_512x512_40k_voc12aug_20200614_000648.log.json) |
+| FCN    | HRNetV2p-W18       | 512x512   |   40000 | -        | -              | V100   | 72.90 |         75.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_40k_voc12aug/fcn_hr18_512x512_40k_voc12aug_20200613_224401-1b4b76cd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_40k_voc12aug/fcn_hr18_512x512_40k_voc12aug_20200613_224401.log.json)     |
+| FCN    | HRNetV2p-W48       | 512x512   |   40000 | -        | -              | V100   | 76.24 |         78.49 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_40k_voc12aug/fcn_hr48_512x512_40k_voc12aug_20200613_222111-1b0f18bc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_40k_voc12aug/fcn_hr48_512x512_40k_voc12aug_20200613_222111.log.json)     |
 
 ### Pascal Context
 
-| Method | Backbone     | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                   |
-| ------ | ------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| FCN    | HRNetV2p-W48 | 480x480   |   40000 | 6.1      | 8.86           | 45.14 |         47.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context/fcn_hr48_480x480_40k_pascal_context_20200911_164852-667d00b0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context/fcn_hr48_480x480_40k_pascal_context-20200911_164852.log.json) |
-| FCN    | HRNetV2p-W48 | 480x480   |   80000 | -        | -              | 45.84 |         47.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context/fcn_hr48_480x480_80k_pascal_context_20200911_155322-847a6711.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context/fcn_hr48_480x480_80k_pascal_context-20200911_155322.log.json) |
+| Method | Backbone     | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                   |
+| ------ | ------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| FCN    | HRNetV2p-W48 | 480x480   |   40000 | 6.1      | 8.86           | V100   | 45.14 |         47.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context/fcn_hr48_480x480_40k_pascal_context_20200911_164852-667d00b0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context/fcn_hr48_480x480_40k_pascal_context-20200911_164852.log.json) |
+| FCN    | HRNetV2p-W48 | 480x480   |   80000 | -        | -              | V100   | 45.84 |         47.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context/fcn_hr48_480x480_80k_pascal_context_20200911_155322-847a6711.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context/fcn_hr48_480x480_80k_pascal_context-20200911_155322.log.json) |
 
 ### Pascal Context 59
 
-| Method | Backbone     | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                               |
-| ------ | ------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| FCN    | HRNetV2p-W48 | 480x480   |   40000 | -        | -              | 50.33 |         52.83 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context_59/fcn_hr48_480x480_40k_pascal_context_59_20210410_122738-b808b8b2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context_59/fcn_hr48_480x480_40k_pascal_context_59-20210410_122738.log.json) |
-| FCN    | HRNetV2p-W48 | 480x480   |   80000 | -        | -              | 51.12 |         53.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59_20210411_003240-3ae7081e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59-20210411_003240.log.json) |
+| Method | Backbone     | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                               |
+| ------ | ------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| FCN    | HRNetV2p-W48 | 480x480   |   40000 | -        | -              | V100   | 50.33 |         52.83 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context_59/fcn_hr48_480x480_40k_pascal_context_59_20210410_122738-b808b8b2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context_59/fcn_hr48_480x480_40k_pascal_context_59-20210410_122738.log.json) |
+| FCN    | HRNetV2p-W48 | 480x480   |   80000 | -        | -              | V100   | 51.12 |         53.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59_20210411_003240-3ae7081e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59-20210411_003240.log.json) |
 
 ### LoveDA
 
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                                       |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN    | HRNetV2p-W18-Small | 512x512   |   80000 | 1.59     | 24.87          | 49.28 |         49.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-80k_loveda-512x512.pyy) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_loveda/fcn_hr18s_512x512_80k_loveda_20211210_203228-60a86a7a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_loveda/fcn_hr18s_512x512_80k_loveda_20211210_203228.log.json) |
-| FCN    | HRNetV2p-W18       | 512x512   |   80000 | 2.76     | 12.92          | 50.81 |         50.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-80k_loveda-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_loveda/fcn_hr18_512x512_80k_loveda_20211210_203952-93d9c3b3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_loveda/fcn_hr18_512x512_80k_loveda_20211210_203952.log.json)     |
-| FCN    | HRNetV2p-W48       | 512x512   |   80000 | 6.20     | 9.61           | 51.42 |         51.64 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_loveda-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_loveda/fcn_hr48_512x512_80k_loveda_20211211_044756-67072f55.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_loveda/fcn_hr48_512x512_80k_loveda_20211211_044756.log.json)     |
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                                       |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN    | HRNetV2p-W18-Small | 512x512   |   80000 | 1.59     | 24.87          | V100   | 49.28 |         49.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-80k_loveda-512x512.pyy) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_loveda/fcn_hr18s_512x512_80k_loveda_20211210_203228-60a86a7a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_loveda/fcn_hr18s_512x512_80k_loveda_20211210_203228.log.json) |
+| FCN    | HRNetV2p-W18       | 512x512   |   80000 | 2.76     | 12.92          | V100   | 50.81 |         50.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-80k_loveda-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_loveda/fcn_hr18_512x512_80k_loveda_20211210_203952-93d9c3b3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_loveda/fcn_hr18_512x512_80k_loveda_20211210_203952.log.json)     |
+| FCN    | HRNetV2p-W48       | 512x512   |   80000 | 6.20     | 9.61           | V100   | 51.42 |         51.64 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_loveda-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_loveda/fcn_hr48_512x512_80k_loveda_20211211_044756-67072f55.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_loveda/fcn_hr48_512x512_80k_loveda_20211211_044756.log.json)     |
 
 ### Potsdam
 
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                                           |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| FCN    | HRNetV2p-W18-Small | 512x512   |   80000 | 1.58     | 36.00          | 77.64 |          78.8 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-80k_potsdam-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_potsdam/fcn_hr18s_512x512_80k_potsdam_20211218_205517-ba32af63.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_potsdam/fcn_hr18s_512x512_80k_potsdam_20211218_205517.log.json) |
-| FCN    | HRNetV2p-W18       | 512x512   |   80000 | 2.76     | 19.25          | 78.26 |         79.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_potsdam/fcn_hr18_512x512_80k_potsdam_20211218_205517-5d0387ad.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_potsdam/fcn_hr18_512x512_80k_potsdam_20211218_205517.log.json)     |
-| FCN    | HRNetV2p-W48       | 512x512   |   80000 | 6.20     | 16.42          | 78.39 |         79.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_potsdam/fcn_hr48_512x512_80k_potsdam_20211219_020601-97434c78.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_potsdam/fcn_hr48_512x512_80k_potsdam_20211219_020601.log.json)     |
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                                           |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| FCN    | HRNetV2p-W18-Small | 512x512   |   80000 | 1.58     | 36.00          | V100   | 77.64 |          78.8 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-80k_potsdam-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_potsdam/fcn_hr18s_512x512_80k_potsdam_20211218_205517-ba32af63.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_potsdam/fcn_hr18s_512x512_80k_potsdam_20211218_205517.log.json) |
+| FCN    | HRNetV2p-W18       | 512x512   |   80000 | 2.76     | 19.25          | V100   | 78.26 |         79.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_potsdam/fcn_hr18_512x512_80k_potsdam_20211218_205517-5d0387ad.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_potsdam/fcn_hr18_512x512_80k_potsdam_20211218_205517.log.json)     |
+| FCN    | HRNetV2p-W48       | 512x512   |   80000 | 6.20     | 16.42          | V100   | 78.39 |         79.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_potsdam/fcn_hr48_512x512_80k_potsdam_20211219_020601-97434c78.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_potsdam/fcn_hr48_512x512_80k_potsdam_20211219_020601.log.json)     |
 
 ### Vaihingen
 
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                    | download                                                                                                                                                                                                                                                                                                                                   |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| FCN    | HRNetV2p-W18-Small | 512x512   |   80000 | 1.58     | 38.11          | 71.81 |          73.1 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-80k_vaihingen-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_512x512_80k_vaihingen/fcn_hr18s_4x4_512x512_80k_vaihingen_20211231_230909-b23aae02.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_512x512_80k_vaihingen/fcn_hr18s_4x4_512x512_80k_vaihingen_20211231_230909.log.json) |
-| FCN    | HRNetV2p-W18       | 512x512   |   80000 | 2.76     | 19.55          | 72.57 |         74.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_512x512_80k_vaihingen/fcn_hr18_4x4_512x512_80k_vaihingen_20211231_231216-2ec3ae8a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_512x512_80k_vaihingen/fcn_hr18_4x4_512x512_80k_vaihingen_20211231_231216.log.json)     |
-| FCN    | HRNetV2p-W48       | 512x512   |   80000 | 6.20     | 17.25          | 72.50 |         73.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_512x512_80k_vaihingen/fcn_hr48_4x4_512x512_80k_vaihingen_20211231_231244-7133cb22.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_512x512_80k_vaihingen/fcn_hr48_4x4_512x512_80k_vaihingen_20211231_231244.log.json)     |
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                    | download                                                                                                                                                                                                                                                                                                                                   |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| FCN    | HRNetV2p-W18-Small | 512x512   |   80000 | 1.58     | 38.11          | V100   | 71.81 |          73.1 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-80k_vaihingen-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_512x512_80k_vaihingen/fcn_hr18s_4x4_512x512_80k_vaihingen_20211231_230909-b23aae02.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_512x512_80k_vaihingen/fcn_hr18s_4x4_512x512_80k_vaihingen_20211231_230909.log.json) |
+| FCN    | HRNetV2p-W18       | 512x512   |   80000 | 2.76     | 19.55          | V100   | 72.57 |         74.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_512x512_80k_vaihingen/fcn_hr18_4x4_512x512_80k_vaihingen_20211231_231216-2ec3ae8a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_512x512_80k_vaihingen/fcn_hr18_4x4_512x512_80k_vaihingen_20211231_231216.log.json)     |
+| FCN    | HRNetV2p-W48       | 512x512   |   80000 | 6.20     | 17.25          | V100   | 72.50 |         73.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_512x512_80k_vaihingen/fcn_hr48_4x4_512x512_80k_vaihingen_20211231_231244-7133cb22.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_512x512_80k_vaihingen/fcn_hr48_4x4_512x512_80k_vaihingen_20211231_231244.log.json)     |
 
 ### iSAID
 
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                | download                                                                                                                                                                                                                                                                                                                   |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN    | HRNetV2p-W18-Small | 896x896   |   80000 | 4.95     | 13.84          | 62.30 |         62.97 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_896x896_80k_isaid/fcn_hr18s_4x4_896x896_80k_isaid_20220118_001603-3cc0769b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_896x896_80k_isaid/fcn_hr18s_4x4_896x896_80k_isaid_20220118_001603.log.json) |
-| FCN    | HRNetV2p-W18       | 896x896   |   80000 | 8.30     | 7.71           | 65.06 |         65.60 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-80k_isaid-896x896.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_896x896_80k_isaid/fcn_hr18_4x4_896x896_80k_isaid_20220110_182230-49bf752e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_896x896_80k_isaid/fcn_hr18_4x4_896x896_80k_isaid_20220110_182230.log.json)     |
-| FCN    | HRNetV2p-W48       | 896x896   |   80000 | 16.89    | 7.34           | 67.80 |         68.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_isaid-896x896.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_896x896_80k_isaid/fcn_hr48_4x4_896x896_80k_isaid_20220114_174643-547fc420.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_896x896_80k_isaid/fcn_hr48_4x4_896x896_80k_isaid_20220114_174643.log.json)     |
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                | download                                                                                                                                                                                                                                                                                                                   |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN    | HRNetV2p-W18-Small | 896x896   |   80000 | 4.95     | 13.84          | V100   | 62.30 |         62.97 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_896x896_80k_isaid/fcn_hr18s_4x4_896x896_80k_isaid_20220118_001603-3cc0769b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_896x896_80k_isaid/fcn_hr18s_4x4_896x896_80k_isaid_20220118_001603.log.json) |
+| FCN    | HRNetV2p-W18       | 896x896   |   80000 | 8.30     | 7.71           | V100   | 65.06 |         65.60 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-80k_isaid-896x896.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_896x896_80k_isaid/fcn_hr18_4x4_896x896_80k_isaid_20220110_182230-49bf752e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_896x896_80k_isaid/fcn_hr18_4x4_896x896_80k_isaid_20220110_182230.log.json)     |
+| FCN    | HRNetV2p-W48       | 896x896   |   80000 | 16.89    | 7.34           | V100   | 67.80 |         68.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_isaid-896x896.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_896x896_80k_isaid/fcn_hr48_4x4_896x896_80k_isaid_20220114_174643-547fc420.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_896x896_80k_isaid/fcn_hr48_4x4_896x896_80k_isaid_20220114_174643.log.json)     |
 
 Note:
 
 - `896x896` is the Crop Size of iSAID dataset, which is followed by the implementation of [PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation](https://arxiv.org/pdf/2103.06564.pdf)
+
+## Citation
+
+```bibtext
+@inproceedings{SunXLW19,
+  title={Deep High-Resolution Representation Learning for Human Pose Estimation},
+  author={Ke Sun and Bin Xiao and Dong Liu and Jingdong Wang},
+  booktitle={CVPR},
+  year={2019}
+}
+```
diff --git a/configs/hrnet/hrnet.yml b/configs/hrnet/hrnet.yml
deleted file mode 100644
index 77f556e17a..0000000000
--- a/configs/hrnet/hrnet.yml
+++ /dev/null
@@ -1,695 +0,0 @@
-Models:
-- Name: fcn_hr18s_4xb2-40k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18-Small
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 42.12
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 1.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 73.86
-      mIoU(ms+flip): 75.91
-  Config: configs/hrnet/fcn_hr18s_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_40k_cityscapes/fcn_hr18s_512x1024_40k_cityscapes_20200601_014216-93db27d0.pth
-- Name: fcn_hr18_4xb2-40k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 77.1
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 2.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.19
-      mIoU(ms+flip): 78.92
-  Config: configs/hrnet/fcn_hr18_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_40k_cityscapes/fcn_hr18_512x1024_40k_cityscapes_20200601_014216-f196fb4e.pth
-- Name: fcn_hr48_4xb2-40k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 155.76
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 6.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.48
-      mIoU(ms+flip): 79.69
-  Config: configs/hrnet/fcn_hr48_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_40k_cityscapes/fcn_hr48_512x1024_40k_cityscapes_20200601_014240-a989b146.pth
-- Name: fcn_hr18s_4xb2-80k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18-Small
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 75.31
-      mIoU(ms+flip): 77.48
-  Config: configs/hrnet/fcn_hr18s_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_80k_cityscapes/fcn_hr18s_512x1024_80k_cityscapes_20200601_202700-1462b75d.pth
-- Name: fcn_hr18_4xb2-80k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.65
-      mIoU(ms+flip): 80.35
-  Config: configs/hrnet/fcn_hr18_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_80k_cityscapes/fcn_hr18_512x1024_80k_cityscapes_20200601_223255-4e7b345e.pth
-- Name: fcn_hr48_4xb2-80k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.93
-      mIoU(ms+flip): 80.72
-  Config: configs/hrnet/fcn_hr48_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_80k_cityscapes/fcn_hr48_512x1024_80k_cityscapes_20200601_202606-58ea95d6.pth
-- Name: fcn_hr18s_4xb2-160k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18-Small
-    crop size: (512,1024)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.31
-      mIoU(ms+flip): 78.31
-  Config: configs/hrnet/fcn_hr18s_4xb2-160k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_160k_cityscapes/fcn_hr18s_512x1024_160k_cityscapes_20200602_190901-4a0797ea.pth
-- Name: fcn_hr18_4xb2-160k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18
-    crop size: (512,1024)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.8
-      mIoU(ms+flip): 80.74
-  Config: configs/hrnet/fcn_hr18_4xb2-160k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_160k_cityscapes/fcn_hr18_512x1024_160k_cityscapes_20200602_190822-221e4a4f.pth
-- Name: fcn_hr48_4xb2-160k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (512,1024)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.65
-      mIoU(ms+flip): 81.92
-  Config: configs/hrnet/fcn_hr48_4xb2-160k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_160k_cityscapes/fcn_hr48_512x1024_160k_cityscapes_20200602_190946-59b7973e.pth
-- Name: fcn_hr18s_4xb4-80k_ade20k-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18-Small
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 25.87
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 3.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 31.38
-      mIoU(ms+flip): 32.45
-  Config: configs/hrnet/fcn_hr18s_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_ade20k/fcn_hr18s_512x512_80k_ade20k_20200614_144345-77fc814a.pth
-- Name: fcn_hr18_4xb4-80k_ade20k-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 44.31
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 4.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 36.27
-      mIoU(ms+flip): 37.28
-  Config: configs/hrnet/fcn_hr18_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20210827_114910-6c9382c0.pth
-- Name: fcn_hr48_4xb4-80k_ade20k-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 47.1
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 8.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 41.9
-      mIoU(ms+flip): 43.27
-  Config: configs/hrnet/fcn_hr48_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_ade20k/fcn_hr48_512x512_80k_ade20k_20200614_193946-7ba5258d.pth
-- Name: fcn_hr18s_4xb4-160k_ade20k-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18-Small
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 33.07
-      mIoU(ms+flip): 34.56
-  Config: configs/hrnet/fcn_hr18s_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20210829_174739-f1e7c2e7.pth
-- Name: fcn_hr18_4xb4-160k_ade20k-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 36.79
-      mIoU(ms+flip): 38.58
-  Config: configs/hrnet/fcn_hr18_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_160k_ade20k/fcn_hr18_512x512_160k_ade20k_20200614_214426-ca961836.pth
-- Name: fcn_hr48_4xb4-160k_ade20k-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.02
-      mIoU(ms+flip): 43.86
-  Config: configs/hrnet/fcn_hr48_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_160k_ade20k/fcn_hr48_512x512_160k_ade20k_20200614_214407-a52fc02c.pth
-- Name: fcn_hr18s_4xb4-20k_voc12aug-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18-Small
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 23.06
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 1.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 65.5
-      mIoU(ms+flip): 68.89
-  Config: configs/hrnet/fcn_hr18s_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20210829_174910-0aceadb4.pth
-- Name: fcn_hr18_4xb4-20k_voc12aug-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 42.59
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 2.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 72.3
-      mIoU(ms+flip): 74.71
-  Config: configs/hrnet/fcn_hr18_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_20k_voc12aug/fcn_hr18_512x512_20k_voc12aug_20200617_224503-488d45f7.pth
-- Name: fcn_hr48_4xb4-20k_voc12aug-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 45.35
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 75.87
-      mIoU(ms+flip): 78.58
-  Config: configs/hrnet/fcn_hr48_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_20k_voc12aug/fcn_hr48_512x512_20k_voc12aug_20200617_224419-89de05cd.pth
-- Name: fcn_hr18s_4xb4-40k_voc12aug-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18-Small
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 66.61
-      mIoU(ms+flip): 70.0
-  Config: configs/hrnet/fcn_hr18s_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_40k_voc12aug/fcn_hr18s_512x512_40k_voc12aug_20200614_000648-4f8d6e7f.pth
-- Name: fcn_hr18_4xb4-40k_voc12aug-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 72.9
-      mIoU(ms+flip): 75.59
-  Config: configs/hrnet/fcn_hr18_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_40k_voc12aug/fcn_hr18_512x512_40k_voc12aug_20200613_224401-1b4b76cd.pth
-- Name: fcn_hr48_4xb4-40k_voc12aug-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 76.24
-      mIoU(ms+flip): 78.49
-  Config: configs/hrnet/fcn_hr48_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_40k_voc12aug/fcn_hr48_512x512_40k_voc12aug_20200613_222111-1b0f18bc.pth
-- Name: fcn_hr48_4xb4-40k_pascal-context-480x480
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (480,480)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 112.87
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (480,480)
-    Training Memory (GB): 6.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context
-    Metrics:
-      mIoU: 45.14
-      mIoU(ms+flip): 47.42
-  Config: configs/hrnet/fcn_hr48_4xb4-40k_pascal-context-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context/fcn_hr48_480x480_40k_pascal_context_20200911_164852-667d00b0.pth
-- Name: fcn_hr48_4xb4-80k_pascal-context-480x480
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (480,480)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context
-    Metrics:
-      mIoU: 45.84
-      mIoU(ms+flip): 47.84
-  Config: configs/hrnet/fcn_hr48_4xb4-80k_pascal-context-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context/fcn_hr48_480x480_80k_pascal_context_20200911_155322-847a6711.pth
-- Name: fcn_hr48_4xb4-40k_pascal-context-59-480x480
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (480,480)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context 59
-    Metrics:
-      mIoU: 50.33
-      mIoU(ms+flip): 52.83
-  Config: configs/hrnet/fcn_hr48_4xb4-40k_pascal-context-59-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context_59/fcn_hr48_480x480_40k_pascal_context_59_20210410_122738-b808b8b2.pth
-- Name: fcn_hr48_4xb4-80k_pascal-context-59-480x480
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (480,480)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context 59
-    Metrics:
-      mIoU: 51.12
-      mIoU(ms+flip): 53.56
-  Config: configs/hrnet/fcn_hr48_4xb4-80k_pascal-context-59-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59_20210411_003240-3ae7081e.pth
-- Name: fcn_hr18s_4xb4-80k_loveda-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18-Small
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 40.21
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 1.59
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: LoveDA
-    Metrics:
-      mIoU: 49.28
-      mIoU(ms+flip): 49.42
-  Config: configs/hrnet/fcn_hr18s_4xb4-80k_loveda-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_loveda/fcn_hr18s_512x512_80k_loveda_20211210_203228-60a86a7a.pth
-- Name: fcn_hr18_4xb4-80k_loveda-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 77.4
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 2.76
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: LoveDA
-    Metrics:
-      mIoU: 50.81
-      mIoU(ms+flip): 50.95
-  Config: configs/hrnet/fcn_hr18_4xb4-80k_loveda-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_loveda/fcn_hr18_512x512_80k_loveda_20211210_203952-93d9c3b3.pth
-- Name: fcn_hr48_4xb4-80k_loveda-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 104.06
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: LoveDA
-    Metrics:
-      mIoU: 51.42
-      mIoU(ms+flip): 51.64
-  Config: configs/hrnet/fcn_hr48_4xb4-80k_loveda-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_loveda/fcn_hr48_512x512_80k_loveda_20211211_044756-67072f55.pth
-- Name: fcn_hr18s_4xb4-80k_potsdam-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18-Small
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 27.78
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 1.58
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Potsdam
-    Metrics:
-      mIoU: 77.64
-      mIoU(ms+flip): 78.8
-  Config: configs/hrnet/fcn_hr18s_4xb4-80k_potsdam-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_potsdam/fcn_hr18s_512x512_80k_potsdam_20211218_205517-ba32af63.pth
-- Name: fcn_hr18_4xb4-80k_potsdam-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 51.95
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 2.76
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Potsdam
-    Metrics:
-      mIoU: 78.26
-      mIoU(ms+flip): 79.24
-  Config: configs/hrnet/fcn_hr18_4xb4-80k_potsdam-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_potsdam/fcn_hr18_512x512_80k_potsdam_20211218_205517-5d0387ad.pth
-- Name: fcn_hr48_4xb4-80k_potsdam-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 60.9
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Potsdam
-    Metrics:
-      mIoU: 78.39
-      mIoU(ms+flip): 79.34
-  Config: configs/hrnet/fcn_hr48_4xb4-80k_potsdam-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_potsdam/fcn_hr48_512x512_80k_potsdam_20211219_020601-97434c78.pth
-- Name: fcn_hr18s_4xb4-80k_vaihingen-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18-Small
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 26.24
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 1.58
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Vaihingen
-    Metrics:
-      mIoU: 71.81
-      mIoU(ms+flip): 73.1
-  Config: configs/hrnet/fcn_hr18s_4xb4-80k_vaihingen-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_512x512_80k_vaihingen/fcn_hr18s_4x4_512x512_80k_vaihingen_20211231_230909-b23aae02.pth
-- Name: fcn_hr18_4xb4-80k_vaihingen-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 51.15
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 2.76
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Vaihingen
-    Metrics:
-      mIoU: 72.57
-      mIoU(ms+flip): 74.09
-  Config: configs/hrnet/fcn_hr18_4xb4-80k_vaihingen-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_512x512_80k_vaihingen/fcn_hr18_4x4_512x512_80k_vaihingen_20211231_231216-2ec3ae8a.pth
-- Name: fcn_hr48_4xb4-80k_vaihingen-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 57.97
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Vaihingen
-    Metrics:
-      mIoU: 72.5
-      mIoU(ms+flip): 73.52
-  Config: configs/hrnet/fcn_hr48_4xb4-80k_vaihingen-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_512x512_80k_vaihingen/fcn_hr48_4x4_512x512_80k_vaihingen_20211231_231244-7133cb22.pth
-- Name: fcn_hr18s_4xb4-80k_isaid-896x896
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18-Small
-    crop size: (896,896)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 72.25
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (896,896)
-    Training Memory (GB): 4.95
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: iSAID
-    Metrics:
-      mIoU: 62.3
-      mIoU(ms+flip): 62.97
-  Config: configs/hrnet/fcn_hr18s_4xb4-80k_isaid-896x896.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_896x896_80k_isaid/fcn_hr18s_4x4_896x896_80k_isaid_20220118_001603-3cc0769b.pth
-- Name: fcn_hr18_4xb4-80k_isaid-896x896
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W18
-    crop size: (896,896)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 129.7
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (896,896)
-    Training Memory (GB): 8.3
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: iSAID
-    Metrics:
-      mIoU: 65.06
-      mIoU(ms+flip): 65.6
-  Config: configs/hrnet/fcn_hr18_4xb4-80k_isaid-896x896.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_896x896_80k_isaid/fcn_hr18_4x4_896x896_80k_isaid_20220110_182230-49bf752e.pth
-- Name: fcn_hr48_4xb4-80k_isaid-896x896
-  In Collection: FCN
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (896,896)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 136.24
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (896,896)
-    Training Memory (GB): 16.89
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: iSAID
-    Metrics:
-      mIoU: 67.8
-      mIoU(ms+flip): 68.53
-  Config: configs/hrnet/fcn_hr48_4xb4-80k_isaid-896x896.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_896x896_80k_isaid/fcn_hr48_4x4_896x896_80k_isaid_20220114_174643-547fc420.pth
diff --git a/configs/hrnet/metafile.yaml b/configs/hrnet/metafile.yaml
new file mode 100644
index 0000000000..11c30165a5
--- /dev/null
+++ b/configs/hrnet/metafile.yaml
@@ -0,0 +1,874 @@
+Models:
+- Name: fcn_hr18s_4xb2-40k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 73.86
+      mIoU(ms+flip): 75.91
+  Config: configs/hrnet/fcn_hr18s_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - HRNetV2p-W18-Small
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_40k_cityscapes/fcn_hr18s_512x1024_40k_cityscapes_20200601_014216-93db27d0.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_40k_cityscapes/fcn_hr18s_512x1024_40k_cityscapes_20200601_014216.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18_4xb2-40k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.19
+      mIoU(ms+flip): 78.92
+  Config: configs/hrnet/fcn_hr18_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - HRNetV2p-W18
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 2.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_40k_cityscapes/fcn_hr18_512x1024_40k_cityscapes_20200601_014216-f196fb4e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_40k_cityscapes/fcn_hr18_512x1024_40k_cityscapes_20200601_014216.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr48_4xb2-40k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.48
+      mIoU(ms+flip): 79.69
+  Config: configs/hrnet/fcn_hr48_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - HRNetV2p-W48
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_40k_cityscapes/fcn_hr48_512x1024_40k_cityscapes_20200601_014240-a989b146.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_40k_cityscapes/fcn_hr48_512x1024_40k_cityscapes_20200601_014240.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18s_4xb2-80k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 75.31
+      mIoU(ms+flip): 77.48
+  Config: configs/hrnet/fcn_hr18s_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - HRNetV2p-W18-Small
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_80k_cityscapes/fcn_hr18s_512x1024_80k_cityscapes_20200601_202700-1462b75d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_80k_cityscapes/fcn_hr18s_512x1024_80k_cityscapes_20200601_202700.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18_4xb2-80k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.65
+      mIoU(ms+flip): 80.35
+  Config: configs/hrnet/fcn_hr18_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - HRNetV2p-W18
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_80k_cityscapes/fcn_hr18_512x1024_80k_cityscapes_20200601_223255-4e7b345e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_80k_cityscapes/fcn_hr18_512x1024_80k_cityscapes_20200601_223255.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr48_4xb2-80k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.93
+      mIoU(ms+flip): 80.72
+  Config: configs/hrnet/fcn_hr48_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - HRNetV2p-W48
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_80k_cityscapes/fcn_hr48_512x1024_80k_cityscapes_20200601_202606-58ea95d6.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_80k_cityscapes/fcn_hr48_512x1024_80k_cityscapes_20200601_202606.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18s_4xb2-160k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.31
+      mIoU(ms+flip): 78.31
+  Config: configs/hrnet/fcn_hr18s_4xb2-160k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - HRNetV2p-W18-Small
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_160k_cityscapes/fcn_hr18s_512x1024_160k_cityscapes_20200602_190901-4a0797ea.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_160k_cityscapes/fcn_hr18s_512x1024_160k_cityscapes_20200602_190901.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18_4xb2-160k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.8
+      mIoU(ms+flip): 80.74
+  Config: configs/hrnet/fcn_hr18_4xb2-160k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - HRNetV2p-W18
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_160k_cityscapes/fcn_hr18_512x1024_160k_cityscapes_20200602_190822-221e4a4f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_160k_cityscapes/fcn_hr18_512x1024_160k_cityscapes_20200602_190822.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr48_4xb2-160k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.65
+      mIoU(ms+flip): 81.92
+  Config: configs/hrnet/fcn_hr48_4xb2-160k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - HRNetV2p-W48
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_160k_cityscapes/fcn_hr48_512x1024_160k_cityscapes_20200602_190946-59b7973e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_160k_cityscapes/fcn_hr48_512x1024_160k_cityscapes_20200602_190946.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18s_4xb4-80k_ade20k-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 31.38
+      mIoU(ms+flip): 32.45
+  Config: configs/hrnet/fcn_hr18s_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18-Small
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 3.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_ade20k/fcn_hr18s_512x512_80k_ade20k_20200614_144345-77fc814a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_ade20k/fcn_hr18s_512x512_80k_ade20k_20200614_144345.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18_4xb4-80k_ade20k-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 36.27
+      mIoU(ms+flip): 37.28
+  Config: configs/hrnet/fcn_hr18_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 4.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20210827_114910-6c9382c0.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20210827_114910.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr48_4xb4-80k_ade20k-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 41.9
+      mIoU(ms+flip): 43.27
+  Config: configs/hrnet/fcn_hr48_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W48
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_ade20k/fcn_hr48_512x512_80k_ade20k_20200614_193946-7ba5258d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_ade20k/fcn_hr48_512x512_80k_ade20k_20200614_193946.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18s_4xb4-160k_ade20k-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 33.07
+      mIoU(ms+flip): 34.56
+  Config: configs/hrnet/fcn_hr18s_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18-Small
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20210829_174739-f1e7c2e7.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20210829_174739.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18_4xb4-160k_ade20k-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 36.79
+      mIoU(ms+flip): 38.58
+  Config: configs/hrnet/fcn_hr18_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_160k_ade20k/fcn_hr18_512x512_160k_ade20k_20200614_214426-ca961836.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_160k_ade20k/fcn_hr18_512x512_160k_ade20k_20200614_214426.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr48_4xb4-160k_ade20k-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.02
+      mIoU(ms+flip): 43.86
+  Config: configs/hrnet/fcn_hr48_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W48
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_160k_ade20k/fcn_hr48_512x512_160k_ade20k_20200614_214407-a52fc02c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_160k_ade20k/fcn_hr48_512x512_160k_ade20k_20200614_214407.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18s_4xb4-20k_voc12aug-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 65.5
+      mIoU(ms+flip): 68.89
+  Config: configs/hrnet/fcn_hr18s_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18-Small
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20210829_174910-0aceadb4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20210829_174910.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18_4xb4-20k_voc12aug-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 72.3
+      mIoU(ms+flip): 74.71
+  Config: configs/hrnet/fcn_hr18_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 2.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_20k_voc12aug/fcn_hr18_512x512_20k_voc12aug_20200617_224503-488d45f7.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_20k_voc12aug/fcn_hr18_512x512_20k_voc12aug_20200617_224503.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr48_4xb4-20k_voc12aug-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 75.87
+      mIoU(ms+flip): 78.58
+  Config: configs/hrnet/fcn_hr48_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W48
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_20k_voc12aug/fcn_hr48_512x512_20k_voc12aug_20200617_224419-89de05cd.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_20k_voc12aug/fcn_hr48_512x512_20k_voc12aug_20200617_224419.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18s_4xb4-40k_voc12aug-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 66.61
+      mIoU(ms+flip): 70.0
+  Config: configs/hrnet/fcn_hr18s_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18-Small
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_40k_voc12aug/fcn_hr18s_512x512_40k_voc12aug_20200614_000648-4f8d6e7f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_40k_voc12aug/fcn_hr18s_512x512_40k_voc12aug_20200614_000648.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18_4xb4-40k_voc12aug-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 72.9
+      mIoU(ms+flip): 75.59
+  Config: configs/hrnet/fcn_hr18_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_40k_voc12aug/fcn_hr18_512x512_40k_voc12aug_20200613_224401-1b4b76cd.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_40k_voc12aug/fcn_hr18_512x512_40k_voc12aug_20200613_224401.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr48_4xb4-40k_voc12aug-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 76.24
+      mIoU(ms+flip): 78.49
+  Config: configs/hrnet/fcn_hr48_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W48
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_40k_voc12aug/fcn_hr48_512x512_40k_voc12aug_20200613_222111-1b0f18bc.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_40k_voc12aug/fcn_hr48_512x512_40k_voc12aug_20200613_222111.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr48_4xb4-40k_pascal-context-480x480
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context
+    Metrics:
+      mIoU: 45.14
+      mIoU(ms+flip): 47.42
+  Config: configs/hrnet/fcn_hr48_4xb4-40k_pascal-context-480x480.py
+  Metadata:
+    Training Data: Pascal Context
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W48
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context/fcn_hr48_480x480_40k_pascal_context_20200911_164852-667d00b0.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context/fcn_hr48_480x480_40k_pascal_context-20200911_164852.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr48_4xb4-80k_pascal-context-480x480
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context
+    Metrics:
+      mIoU: 45.84
+      mIoU(ms+flip): 47.84
+  Config: configs/hrnet/fcn_hr48_4xb4-80k_pascal-context-480x480.py
+  Metadata:
+    Training Data: Pascal Context
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W48
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context/fcn_hr48_480x480_80k_pascal_context_20200911_155322-847a6711.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context/fcn_hr48_480x480_80k_pascal_context-20200911_155322.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr48_4xb4-40k_pascal-context-59-480x480
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context 59
+    Metrics:
+      mIoU: 50.33
+      mIoU(ms+flip): 52.83
+  Config: configs/hrnet/fcn_hr48_4xb4-40k_pascal-context-59-480x480.py
+  Metadata:
+    Training Data: Pascal Context 59
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W48
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context_59/fcn_hr48_480x480_40k_pascal_context_59_20210410_122738-b808b8b2.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context_59/fcn_hr48_480x480_40k_pascal_context_59-20210410_122738.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr48_4xb4-80k_pascal-context-59-480x480
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context 59
+    Metrics:
+      mIoU: 51.12
+      mIoU(ms+flip): 53.56
+  Config: configs/hrnet/fcn_hr48_4xb4-80k_pascal-context-59-480x480.py
+  Metadata:
+    Training Data: Pascal Context 59
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W48
+    - FCN
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59_20210411_003240-3ae7081e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59-20210411_003240.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18s_4xb4-80k_loveda-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: LoveDA
+    Metrics:
+      mIoU: 49.28
+      mIoU(ms+flip): 49.42
+  Config: configs/hrnet/fcn_hr18s_4xb4-80k_loveda-512x512.py
+  Metadata:
+    Training Data: LoveDA
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18-Small
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.59
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_loveda/fcn_hr18s_512x512_80k_loveda_20211210_203228-60a86a7a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_loveda/fcn_hr18s_512x512_80k_loveda_20211210_203228.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18_4xb4-80k_loveda-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: LoveDA
+    Metrics:
+      mIoU: 50.81
+      mIoU(ms+flip): 50.95
+  Config: configs/hrnet/fcn_hr18_4xb4-80k_loveda-512x512.py
+  Metadata:
+    Training Data: LoveDA
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 2.76
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_loveda/fcn_hr18_512x512_80k_loveda_20211210_203952-93d9c3b3.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_loveda/fcn_hr18_512x512_80k_loveda_20211210_203952.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr48_4xb4-80k_loveda-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: LoveDA
+    Metrics:
+      mIoU: 51.42
+      mIoU(ms+flip): 51.64
+  Config: configs/hrnet/fcn_hr48_4xb4-80k_loveda-512x512.py
+  Metadata:
+    Training Data: LoveDA
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W48
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_loveda/fcn_hr48_512x512_80k_loveda_20211211_044756-67072f55.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_loveda/fcn_hr48_512x512_80k_loveda_20211211_044756.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18s_4xb4-80k_potsdam-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Potsdam
+    Metrics:
+      mIoU: 77.64
+      mIoU(ms+flip): 78.8
+  Config: configs/hrnet/fcn_hr18s_4xb4-80k_potsdam-512x512.py
+  Metadata:
+    Training Data: Potsdam
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18-Small
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.58
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_potsdam/fcn_hr18s_512x512_80k_potsdam_20211218_205517-ba32af63.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_potsdam/fcn_hr18s_512x512_80k_potsdam_20211218_205517.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18_4xb4-80k_potsdam-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Potsdam
+    Metrics:
+      mIoU: 78.26
+      mIoU(ms+flip): 79.24
+  Config: configs/hrnet/fcn_hr18_4xb4-80k_potsdam-512x512.py
+  Metadata:
+    Training Data: Potsdam
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 2.76
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_potsdam/fcn_hr18_512x512_80k_potsdam_20211218_205517-5d0387ad.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_potsdam/fcn_hr18_512x512_80k_potsdam_20211218_205517.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr48_4xb4-80k_potsdam-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Potsdam
+    Metrics:
+      mIoU: 78.39
+      mIoU(ms+flip): 79.34
+  Config: configs/hrnet/fcn_hr48_4xb4-80k_potsdam-512x512.py
+  Metadata:
+    Training Data: Potsdam
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W48
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_potsdam/fcn_hr48_512x512_80k_potsdam_20211219_020601-97434c78.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_potsdam/fcn_hr48_512x512_80k_potsdam_20211219_020601.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18s_4xb4-80k_vaihingen-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Vaihingen
+    Metrics:
+      mIoU: 71.81
+      mIoU(ms+flip): 73.1
+  Config: configs/hrnet/fcn_hr18s_4xb4-80k_vaihingen-512x512.py
+  Metadata:
+    Training Data: Vaihingen
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18-Small
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.58
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_512x512_80k_vaihingen/fcn_hr18s_4x4_512x512_80k_vaihingen_20211231_230909-b23aae02.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_512x512_80k_vaihingen/fcn_hr18s_4x4_512x512_80k_vaihingen_20211231_230909.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18_4xb4-80k_vaihingen-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Vaihingen
+    Metrics:
+      mIoU: 72.57
+      mIoU(ms+flip): 74.09
+  Config: configs/hrnet/fcn_hr18_4xb4-80k_vaihingen-512x512.py
+  Metadata:
+    Training Data: Vaihingen
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 2.76
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_512x512_80k_vaihingen/fcn_hr18_4x4_512x512_80k_vaihingen_20211231_231216-2ec3ae8a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_512x512_80k_vaihingen/fcn_hr18_4x4_512x512_80k_vaihingen_20211231_231216.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr48_4xb4-80k_vaihingen-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Vaihingen
+    Metrics:
+      mIoU: 72.5
+      mIoU(ms+flip): 73.52
+  Config: configs/hrnet/fcn_hr48_4xb4-80k_vaihingen-512x512.py
+  Metadata:
+    Training Data: Vaihingen
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W48
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_512x512_80k_vaihingen/fcn_hr48_4x4_512x512_80k_vaihingen_20211231_231244-7133cb22.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_512x512_80k_vaihingen/fcn_hr48_4x4_512x512_80k_vaihingen_20211231_231244.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18s_4xb4-80k_isaid-896x896
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: iSAID
+    Metrics:
+      mIoU: 62.3
+      mIoU(ms+flip): 62.97
+  Config: configs/hrnet/fcn_hr18s_4xb4-80k_isaid-896x896.py
+  Metadata:
+    Training Data: iSAID
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18-Small
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 4.95
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_896x896_80k_isaid/fcn_hr18s_4x4_896x896_80k_isaid_20220118_001603-3cc0769b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_896x896_80k_isaid/fcn_hr18s_4x4_896x896_80k_isaid_20220118_001603.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr18_4xb4-80k_isaid-896x896
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: iSAID
+    Metrics:
+      mIoU: 65.06
+      mIoU(ms+flip): 65.6
+  Config: configs/hrnet/fcn_hr18_4xb4-80k_isaid-896x896.py
+  Metadata:
+    Training Data: iSAID
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.3
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_896x896_80k_isaid/fcn_hr18_4x4_896x896_80k_isaid_20220110_182230-49bf752e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_896x896_80k_isaid/fcn_hr18_4x4_896x896_80k_isaid_20220110_182230.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
+- Name: fcn_hr48_4xb4-80k_isaid-896x896
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: iSAID
+    Metrics:
+      mIoU: 67.8
+      mIoU(ms+flip): 68.53
+  Config: configs/hrnet/fcn_hr48_4xb4-80k_isaid-896x896.py
+  Metadata:
+    Training Data: iSAID
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W48
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 16.89
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_896x896_80k_isaid/fcn_hr48_4x4_896x896_80k_isaid_20220114_174643-547fc420.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_896x896_80k_isaid/fcn_hr48_4x4_896x896_80k_isaid_20220114_174643.log.json
+  Paper:
+    Title: Deep High-Resolution Representation Learning for Human Pose Estimation
+    URL: https://arxiv.org/abs/1908.07919
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
+  Framework: PyTorch
diff --git a/configs/icnet/README.md b/configs/icnet/README.md
index 134f53b29f..2b58c2eed8 100644
--- a/configs/icnet/README.md
+++ b/configs/icnet/README.md
@@ -1,6 +1,6 @@
 # ICNet
 
-[ICNet for Real-time Semantic Segmentation on High-resolution Images](https://arxiv.org/abs/1704.08545)
+> [ICNet for Real-time Semantic Segmentation on High-resolution Images](https://arxiv.org/abs/1704.08545)
 
 ## Introduction
 
@@ -22,6 +22,27 @@ We focus on the challenging task of real-time semantic segmentation in this pape
 <img src="https://user-images.githubusercontent.com/24582831/142901772-4570455d-7b27-44ae-a690-47dd9fde8445.png" width="70%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method           | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                   | download                                                                                                                                                                                                                                                                                                                                                                               |
+| ---------------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ICNet            | R-18-D8  | 832x832   |   80000 | 1.70     | 27.12          | V100   | 68.14 |         70.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r18-d8_4xb2-80k_cityscapes-832x832.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_80k_cityscapes/icnet_r18-d8_832x832_80k_cityscapes_20210925_225521-2e36638d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_80k_cityscapes/icnet_r18-d8_832x832_80k_cityscapes_20210925_225521.log.json)                                             |
+| ICNet            | R-18-D8  | 832x832   |  160000 | -        | -              | V100   | 71.64 |         74.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r18-d8_4xb2-160k_cityscapes-832x832.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_160k_cityscapes/icnet_r18-d8_832x832_160k_cityscapes_20210925_230153-2c6eb6e0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_160k_cityscapes/icnet_r18-d8_832x832_160k_cityscapes_20210925_230153.log.json)                                         |
+| ICNet (in1k-pre) | R-18-D8  | 832x832   |   80000 | -        | -              | V100   | 72.51 |         74.78 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r18-d8-in1k-pre_4xb2-80k_cityscapes-832x832.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes_20210925_230354-1cbe3022.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes_20210925_230354.log.json)         |
+| ICNet (in1k-pre) | R-18-D8  | 832x832   |  160000 | -        | -              | V100   | 74.43 |         76.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r18-d8-in1k-pre_4xb2-160k_cityscapes-832x832.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes_20210926_052702-619c8ae1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes_20210926_052702.log.json)     |
+| ICNet            | R-50-D8  | 832x832   |   80000 | 2.53     | 20.08          | V100   | 68.91 |         69.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r50-d8_4xb2-80k_cityscapes-832x832.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_80k_cityscapes/icnet_r50-d8_832x832_80k_cityscapes_20210926_044625-c6407341.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_80k_cityscapes/icnet_r50-d8_832x832_80k_cityscapes_20210926_044625.log.json)                                             |
+| ICNet            | R-50-D8  | 832x832   |  160000 | -        | -              | V100   | 73.82 |         75.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r50-d8_4xb2-160k_cityscapes-832x832.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_160k_cityscapes/icnet_r50-d8_832x832_160k_cityscapes_20210925_232612-a95f0d4e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_160k_cityscapes/icnet_r50-d8_832x832_160k_cityscapes_20210925_232612.log.json)                                         |
+| ICNet (in1k-pre) | R-50-D8  | 832x832   |   80000 | -        | -              | V100   | 74.58 |         76.41 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r50-d8-in1k-pre_4xb2-80k_cityscapes-832x832.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes_20210926_032943-1743dc7b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes_20210926_032943.log.json)         |
+| ICNet (in1k-pre) | R-50-D8  | 832x832   |  160000 | -        | -              | V100   | 76.29 |         78.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r50-d8-in1k-pre_4xb2-160k_cityscapes-832x832.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes_20210926_042715-ce310aea.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes_20210926_042715.log.json)     |
+| ICNet            | R-101-D8 | 832x832   |   80000 | 3.08     | 16.95          | V100   | 70.28 |         71.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r101-d8_4xb2-80k_cityscapes-832x832.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_80k_cityscapes/icnet_r101-d8_832x832_80k_cityscapes_20210926_072447-b52f936e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_80k_cityscapes/icnet_r101-d8_832x832_80k_cityscapes_20210926_072447.log.json)                                         |
+| ICNet            | R-101-D8 | 832x832   |  160000 | -        | -              | V100   | 73.80 |         76.10 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r101-d8_4xb2-160k_cityscapes-832x832.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_160k_cityscapes/icnet_r101-d8_832x832_160k_cityscapes_20210926_092350-3a1ebf1a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_160k_cityscapes/icnet_r101-d8_832x832_160k_cityscapes_20210926_092350.log.json)                                     |
+| ICNet (in1k-pre) | R-101-D8 | 832x832   |   80000 | -        | -              | V100   | 75.57 |         77.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r101-d8-in1k-pre_4xb2-80k_cityscapes-832x832.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes_20210926_020414-7ceb12c5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes_20210926_020414.log.json)     |
+| ICNet (in1k-pre) | R-101-D8 | 832x832   |  160000 | -        | -              | V100   | 76.15 |         77.98 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r101-d8-in1k-pre_4xb2-160k_cityscapes-832x832.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes_20210925_232612-9484ae8a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes_20210925_232612.log.json) |
+
+Note: `in1k-pre` means pretrained model is used.
+
 ## Citation
 
 ```bibtext
@@ -33,24 +54,3 @@ We focus on the challenging task of real-time semantic segmentation in this pape
   year={2018}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method           | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                   | download                                                                                                                                                                                                                                                                                                                                                                               |
-| ---------------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| ICNet            | R-18-D8  | 832x832   |   80000 | 1.70     | 27.12          | 68.14 |         70.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r18-d8_4xb2-80k_cityscapes-832x832.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_80k_cityscapes/icnet_r18-d8_832x832_80k_cityscapes_20210925_225521-2e36638d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_80k_cityscapes/icnet_r18-d8_832x832_80k_cityscapes_20210925_225521.log.json)                                             |
-| ICNet            | R-18-D8  | 832x832   |  160000 | -        | -              | 71.64 |         74.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r18-d8_4xb2-160k_cityscapes-832x832.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_160k_cityscapes/icnet_r18-d8_832x832_160k_cityscapes_20210925_230153-2c6eb6e0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_160k_cityscapes/icnet_r18-d8_832x832_160k_cityscapes_20210925_230153.log.json)                                         |
-| ICNet (in1k-pre) | R-18-D8  | 832x832   |   80000 | -        | -              | 72.51 |         74.78 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r18-d8-in1k-pre_4xb2-80k_cityscapes-832x832.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes_20210925_230354-1cbe3022.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes_20210925_230354.log.json)         |
-| ICNet (in1k-pre) | R-18-D8  | 832x832   |  160000 | -        | -              | 74.43 |         76.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r18-d8-in1k-pre_4xb2-160k_cityscapes-832x832.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes_20210926_052702-619c8ae1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes_20210926_052702.log.json)     |
-| ICNet            | R-50-D8  | 832x832   |   80000 | 2.53     | 20.08          | 68.91 |         69.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r50-d8_4xb2-80k_cityscapes-832x832.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_80k_cityscapes/icnet_r50-d8_832x832_80k_cityscapes_20210926_044625-c6407341.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_80k_cityscapes/icnet_r50-d8_832x832_80k_cityscapes_20210926_044625.log.json)                                             |
-| ICNet            | R-50-D8  | 832x832   |  160000 | -        | -              | 73.82 |         75.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r50-d8_4xb2-160k_cityscapes-832x832.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_160k_cityscapes/icnet_r50-d8_832x832_160k_cityscapes_20210925_232612-a95f0d4e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_160k_cityscapes/icnet_r50-d8_832x832_160k_cityscapes_20210925_232612.log.json)                                         |
-| ICNet (in1k-pre) | R-50-D8  | 832x832   |   80000 | -        | -              | 74.58 |         76.41 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r50-d8-in1k-pre_4xb2-80k_cityscapes-832x832.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes_20210926_032943-1743dc7b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes_20210926_032943.log.json)         |
-| ICNet (in1k-pre) | R-50-D8  | 832x832   |  160000 | -        | -              | 76.29 |         78.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r50-d8-in1k-pre_4xb2-160k_cityscapes-832x832.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes_20210926_042715-ce310aea.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes_20210926_042715.log.json)     |
-| ICNet            | R-101-D8 | 832x832   |   80000 | 3.08     | 16.95          | 70.28 |         71.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r101-d8_4xb2-80k_cityscapes-832x832.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_80k_cityscapes/icnet_r101-d8_832x832_80k_cityscapes_20210926_072447-b52f936e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_80k_cityscapes/icnet_r101-d8_832x832_80k_cityscapes_20210926_072447.log.json)                                         |
-| ICNet            | R-101-D8 | 832x832   |  160000 | -        | -              | 73.80 |         76.10 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r101-d8_4xb2-160k_cityscapes-832x832.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_160k_cityscapes/icnet_r101-d8_832x832_160k_cityscapes_20210926_092350-3a1ebf1a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_160k_cityscapes/icnet_r101-d8_832x832_160k_cityscapes_20210926_092350.log.json)                                     |
-| ICNet (in1k-pre) | R-101-D8 | 832x832   |   80000 | -        | -              | 75.57 |         77.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r101-d8-in1k-pre_4xb2-80k_cityscapes-832x832.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes_20210926_020414-7ceb12c5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes_20210926_020414.log.json)     |
-| ICNet (in1k-pre) | R-101-D8 | 832x832   |  160000 | -        | -              | 76.15 |         77.98 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r101-d8-in1k-pre_4xb2-160k_cityscapes-832x832.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes_20210925_232612-9484ae8a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes_20210925_232612.log.json) |
-
-Note: `in1k-pre` means pretrained model is used.
diff --git a/configs/icnet/icnet.yml b/configs/icnet/icnet.yml
deleted file mode 100644
index 5ded544726..0000000000
--- a/configs/icnet/icnet.yml
+++ /dev/null
@@ -1,207 +0,0 @@
-Collections:
-- Name: ICNet
-  Metadata:
-    Training Data:
-    - Cityscapes
-  Paper:
-    URL: https://arxiv.org/abs/1704.08545
-    Title: ICNet for Real-time Semantic Segmentation on High-resolution Images
-  README: configs/icnet/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/ic_neck.py#L77
-    Version: v0.18.0
-  Converted From:
-    Code: https://github.com/hszhao/ICNet
-Models:
-- Name: icnet_r18-d8_4xb2-80k_cityscapes-832x832
-  In Collection: ICNet
-  Metadata:
-    backbone: R-18-D8
-    crop size: (832,832)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 36.87
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (832,832)
-    Training Memory (GB): 1.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 68.14
-      mIoU(ms+flip): 70.16
-  Config: configs/icnet/icnet_r18-d8_4xb2-80k_cityscapes-832x832.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_80k_cityscapes/icnet_r18-d8_832x832_80k_cityscapes_20210925_225521-2e36638d.pth
-- Name: icnet_r18-d8_4xb2-160k_cityscapes-832x832
-  In Collection: ICNet
-  Metadata:
-    backbone: R-18-D8
-    crop size: (832,832)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 71.64
-      mIoU(ms+flip): 74.18
-  Config: configs/icnet/icnet_r18-d8_4xb2-160k_cityscapes-832x832.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_160k_cityscapes/icnet_r18-d8_832x832_160k_cityscapes_20210925_230153-2c6eb6e0.pth
-- Name: icnet_r18-d8-in1k-pre_4xb2-80k_cityscapes-832x832
-  In Collection: ICNet
-  Metadata:
-    backbone: R-18-D8
-    crop size: (832,832)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 72.51
-      mIoU(ms+flip): 74.78
-  Config: configs/icnet/icnet_r18-d8-in1k-pre_4xb2-80k_cityscapes-832x832.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes_20210925_230354-1cbe3022.pth
-- Name: icnet_r18-d8-in1k-pre_4xb2-160k_cityscapes-832x832
-  In Collection: ICNet
-  Metadata:
-    backbone: R-18-D8
-    crop size: (832,832)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 74.43
-      mIoU(ms+flip): 76.72
-  Config: configs/icnet/icnet_r18-d8-in1k-pre_4xb2-160k_cityscapes-832x832.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes_20210926_052702-619c8ae1.pth
-- Name: icnet_r50-d8_4xb2-80k_cityscapes-832x832
-  In Collection: ICNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (832,832)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 49.8
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (832,832)
-    Training Memory (GB): 2.53
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 68.91
-      mIoU(ms+flip): 69.72
-  Config: configs/icnet/icnet_r50-d8_4xb2-80k_cityscapes-832x832.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_80k_cityscapes/icnet_r50-d8_832x832_80k_cityscapes_20210926_044625-c6407341.pth
-- Name: icnet_r50-d8_4xb2-160k_cityscapes-832x832
-  In Collection: ICNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (832,832)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 73.82
-      mIoU(ms+flip): 75.67
-  Config: configs/icnet/icnet_r50-d8_4xb2-160k_cityscapes-832x832.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_160k_cityscapes/icnet_r50-d8_832x832_160k_cityscapes_20210925_232612-a95f0d4e.pth
-- Name: icnet_r50-d8-in1k-pre_4xb2-80k_cityscapes-832x832
-  In Collection: ICNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (832,832)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 74.58
-      mIoU(ms+flip): 76.41
-  Config: configs/icnet/icnet_r50-d8-in1k-pre_4xb2-80k_cityscapes-832x832.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes_20210926_032943-1743dc7b.pth
-- Name: icnet_r50-d8-in1k-pre_4xb2-160k_cityscapes-832x832
-  In Collection: ICNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (832,832)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.29
-      mIoU(ms+flip): 78.09
-  Config: configs/icnet/icnet_r50-d8-in1k-pre_4xb2-160k_cityscapes-832x832.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes_20210926_042715-ce310aea.pth
-- Name: icnet_r101-d8_4xb2-80k_cityscapes-832x832
-  In Collection: ICNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (832,832)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 59.0
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (832,832)
-    Training Memory (GB): 3.08
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 70.28
-      mIoU(ms+flip): 71.95
-  Config: configs/icnet/icnet_r101-d8_4xb2-80k_cityscapes-832x832.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_80k_cityscapes/icnet_r101-d8_832x832_80k_cityscapes_20210926_072447-b52f936e.pth
-- Name: icnet_r101-d8_4xb2-160k_cityscapes-832x832
-  In Collection: ICNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (832,832)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 73.8
-      mIoU(ms+flip): 76.1
-  Config: configs/icnet/icnet_r101-d8_4xb2-160k_cityscapes-832x832.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_160k_cityscapes/icnet_r101-d8_832x832_160k_cityscapes_20210926_092350-3a1ebf1a.pth
-- Name: icnet_r101-d8-in1k-pre_4xb2-80k_cityscapes-832x832
-  In Collection: ICNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (832,832)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 75.57
-      mIoU(ms+flip): 77.86
-  Config: configs/icnet/icnet_r101-d8-in1k-pre_4xb2-80k_cityscapes-832x832.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes_20210926_020414-7ceb12c5.pth
-- Name: icnet_r101-d8-in1k-pre_4xb2-160k_cityscapes-832x832
-  In Collection: ICNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (832,832)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.15
-      mIoU(ms+flip): 77.98
-  Config: configs/icnet/icnet_r101-d8-in1k-pre_4xb2-160k_cityscapes-832x832.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes_20210925_232612-9484ae8a.pth
diff --git a/configs/icnet/metafile.yaml b/configs/icnet/metafile.yaml
new file mode 100644
index 0000000000..1d843ee4b6
--- /dev/null
+++ b/configs/icnet/metafile.yaml
@@ -0,0 +1,298 @@
+Collections:
+- Name: ICNet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+  Paper:
+    Title: ICNet for Real-time Semantic Segmentation on High-resolution Images
+    URL: https://arxiv.org/abs/1704.08545
+  README: configs/icnet/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: icnet_r18-d8_4xb2-80k_cityscapes-832x832
+  In Collection: ICNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 68.14
+      mIoU(ms+flip): 70.16
+  Config: configs/icnet/icnet_r18-d8_4xb2-80k_cityscapes-832x832.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18-D8
+    - ICNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_80k_cityscapes/icnet_r18-d8_832x832_80k_cityscapes_20210925_225521-2e36638d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_80k_cityscapes/icnet_r18-d8_832x832_80k_cityscapes_20210925_225521.log.json
+  Paper:
+    Title: ICNet for Real-time Semantic Segmentation on High-resolution Images
+    URL: https://arxiv.org/abs/1704.08545
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/ic_neck.py#L77
+  Framework: PyTorch
+- Name: icnet_r18-d8_4xb2-160k_cityscapes-832x832
+  In Collection: ICNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 71.64
+      mIoU(ms+flip): 74.18
+  Config: configs/icnet/icnet_r18-d8_4xb2-160k_cityscapes-832x832.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18-D8
+    - ICNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_160k_cityscapes/icnet_r18-d8_832x832_160k_cityscapes_20210925_230153-2c6eb6e0.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_160k_cityscapes/icnet_r18-d8_832x832_160k_cityscapes_20210925_230153.log.json
+  Paper:
+    Title: ICNet for Real-time Semantic Segmentation on High-resolution Images
+    URL: https://arxiv.org/abs/1704.08545
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/ic_neck.py#L77
+  Framework: PyTorch
+- Name: icnet_r18-d8-in1k-pre_4xb2-80k_cityscapes-832x832
+  In Collection: ICNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 72.51
+      mIoU(ms+flip): 74.78
+  Config: configs/icnet/icnet_r18-d8-in1k-pre_4xb2-80k_cityscapes-832x832.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18-D8
+    - ICNet
+    - (in1k-pre)
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes_20210925_230354-1cbe3022.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes_20210925_230354.log.json
+  Paper:
+    Title: ICNet for Real-time Semantic Segmentation on High-resolution Images
+    URL: https://arxiv.org/abs/1704.08545
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/ic_neck.py#L77
+  Framework: PyTorch
+- Name: icnet_r18-d8-in1k-pre_4xb2-160k_cityscapes-832x832
+  In Collection: ICNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 74.43
+      mIoU(ms+flip): 76.72
+  Config: configs/icnet/icnet_r18-d8-in1k-pre_4xb2-160k_cityscapes-832x832.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18-D8
+    - ICNet
+    - (in1k-pre)
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes_20210926_052702-619c8ae1.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes_20210926_052702.log.json
+  Paper:
+    Title: ICNet for Real-time Semantic Segmentation on High-resolution Images
+    URL: https://arxiv.org/abs/1704.08545
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/ic_neck.py#L77
+  Framework: PyTorch
+- Name: icnet_r50-d8_4xb2-80k_cityscapes-832x832
+  In Collection: ICNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 68.91
+      mIoU(ms+flip): 69.72
+  Config: configs/icnet/icnet_r50-d8_4xb2-80k_cityscapes-832x832.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - ICNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 2.53
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_80k_cityscapes/icnet_r50-d8_832x832_80k_cityscapes_20210926_044625-c6407341.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_80k_cityscapes/icnet_r50-d8_832x832_80k_cityscapes_20210926_044625.log.json
+  Paper:
+    Title: ICNet for Real-time Semantic Segmentation on High-resolution Images
+    URL: https://arxiv.org/abs/1704.08545
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/ic_neck.py#L77
+  Framework: PyTorch
+- Name: icnet_r50-d8_4xb2-160k_cityscapes-832x832
+  In Collection: ICNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 73.82
+      mIoU(ms+flip): 75.67
+  Config: configs/icnet/icnet_r50-d8_4xb2-160k_cityscapes-832x832.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - ICNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_160k_cityscapes/icnet_r50-d8_832x832_160k_cityscapes_20210925_232612-a95f0d4e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_160k_cityscapes/icnet_r50-d8_832x832_160k_cityscapes_20210925_232612.log.json
+  Paper:
+    Title: ICNet for Real-time Semantic Segmentation on High-resolution Images
+    URL: https://arxiv.org/abs/1704.08545
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/ic_neck.py#L77
+  Framework: PyTorch
+- Name: icnet_r50-d8-in1k-pre_4xb2-80k_cityscapes-832x832
+  In Collection: ICNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 74.58
+      mIoU(ms+flip): 76.41
+  Config: configs/icnet/icnet_r50-d8-in1k-pre_4xb2-80k_cityscapes-832x832.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - ICNet
+    - (in1k-pre)
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes_20210926_032943-1743dc7b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes_20210926_032943.log.json
+  Paper:
+    Title: ICNet for Real-time Semantic Segmentation on High-resolution Images
+    URL: https://arxiv.org/abs/1704.08545
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/ic_neck.py#L77
+  Framework: PyTorch
+- Name: icnet_r50-d8-in1k-pre_4xb2-160k_cityscapes-832x832
+  In Collection: ICNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.29
+      mIoU(ms+flip): 78.09
+  Config: configs/icnet/icnet_r50-d8-in1k-pre_4xb2-160k_cityscapes-832x832.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - ICNet
+    - (in1k-pre)
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes_20210926_042715-ce310aea.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes_20210926_042715.log.json
+  Paper:
+    Title: ICNet for Real-time Semantic Segmentation on High-resolution Images
+    URL: https://arxiv.org/abs/1704.08545
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/ic_neck.py#L77
+  Framework: PyTorch
+- Name: icnet_r101-d8_4xb2-80k_cityscapes-832x832
+  In Collection: ICNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 70.28
+      mIoU(ms+flip): 71.95
+  Config: configs/icnet/icnet_r101-d8_4xb2-80k_cityscapes-832x832.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - ICNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 3.08
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_80k_cityscapes/icnet_r101-d8_832x832_80k_cityscapes_20210926_072447-b52f936e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_80k_cityscapes/icnet_r101-d8_832x832_80k_cityscapes_20210926_072447.log.json
+  Paper:
+    Title: ICNet for Real-time Semantic Segmentation on High-resolution Images
+    URL: https://arxiv.org/abs/1704.08545
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/ic_neck.py#L77
+  Framework: PyTorch
+- Name: icnet_r101-d8_4xb2-160k_cityscapes-832x832
+  In Collection: ICNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 73.8
+      mIoU(ms+flip): 76.1
+  Config: configs/icnet/icnet_r101-d8_4xb2-160k_cityscapes-832x832.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - ICNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_160k_cityscapes/icnet_r101-d8_832x832_160k_cityscapes_20210926_092350-3a1ebf1a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_160k_cityscapes/icnet_r101-d8_832x832_160k_cityscapes_20210926_092350.log.json
+  Paper:
+    Title: ICNet for Real-time Semantic Segmentation on High-resolution Images
+    URL: https://arxiv.org/abs/1704.08545
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/ic_neck.py#L77
+  Framework: PyTorch
+- Name: icnet_r101-d8-in1k-pre_4xb2-80k_cityscapes-832x832
+  In Collection: ICNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 75.57
+      mIoU(ms+flip): 77.86
+  Config: configs/icnet/icnet_r101-d8-in1k-pre_4xb2-80k_cityscapes-832x832.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - ICNet
+    - (in1k-pre)
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes_20210926_020414-7ceb12c5.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes_20210926_020414.log.json
+  Paper:
+    Title: ICNet for Real-time Semantic Segmentation on High-resolution Images
+    URL: https://arxiv.org/abs/1704.08545
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/ic_neck.py#L77
+  Framework: PyTorch
+- Name: icnet_r101-d8-in1k-pre_4xb2-160k_cityscapes-832x832
+  In Collection: ICNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.15
+      mIoU(ms+flip): 77.98
+  Config: configs/icnet/icnet_r101-d8-in1k-pre_4xb2-160k_cityscapes-832x832.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - ICNet
+    - (in1k-pre)
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes_20210925_232612-9484ae8a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes_20210925_232612.log.json
+  Paper:
+    Title: ICNet for Real-time Semantic Segmentation on High-resolution Images
+    URL: https://arxiv.org/abs/1704.08545
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/ic_neck.py#L77
+  Framework: PyTorch
diff --git a/configs/isanet/README.md b/configs/isanet/README.md
index db93dae234..da9f0104c5 100644
--- a/configs/isanet/README.md
+++ b/configs/isanet/README.md
@@ -1,6 +1,6 @@
 # ISANet
 
-[Interlaced Sparse Self-Attention for Semantic Segmentation](https://arxiv.org/abs/1907.12273)
+> [Interlaced Sparse Self-Attention for Semantic Segmentation](https://arxiv.org/abs/1907.12273)
 
 ## Introduction
 
@@ -22,6 +22,39 @@ In this paper, we present a so-called interlaced sparse self-attention approach
 <img src="https://user-images.githubusercontent.com/24582831/142901868-03d80da4-b9c0-4df9-8509-5f684ba9dadc.png" width="80%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) |                                                                                                                            config | download                                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------- | -------: | -------------- | ------ | ----- | ------------: | --------------------------------------------------------------------------------------------------------------------------------: | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ISANet | R-50-D8  | 512x1024  | 40000   |    5.869 | 2.91           | V100   | 78.49 |         79.44 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_40k_cityscapes/isanet_r50-d8_512x1024_40k_cityscapes_20210901_054739-981bd763.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_40k_cityscapes/isanet_r50-d8_512x1024_40k_cityscapes_20210901_054739.log.json)     |
+| ISANet | R-50-D8  | 512x1024  | 80000   |    5.869 | 2.91           | V100   | 78.68 |         80.25 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_80k_cityscapes/isanet_r50-d8_512x1024_80k_cityscapes_20210901_074202-89384497.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_80k_cityscapes/isanet_r50-d8_512x1024_80k_cityscapes_20210901_074202.log.json)     |
+| ISANet | R-50-D8  | 769x769   | 40000   |    6.759 | 1.54           | V100   | 78.70 |         80.28 |   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb2-40k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_40k_cityscapes/isanet_r50-d8_769x769_40k_cityscapes_20210903_050200-4ae7e65b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_40k_cityscapes/isanet_r50-d8_769x769_40k_cityscapes_20210903_050200.log.json)         |
+| ISANet | R-50-D8  | 769x769   | 80000   |    6.759 | 1.54           | V100   | 79.29 |         80.53 |   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_80k_cityscapes/isanet_r50-d8_769x769_80k_cityscapes_20210903_101126-99b54519.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_80k_cityscapes/isanet_r50-d8_769x769_80k_cityscapes_20210903_101126.log.json)         |
+| ISANet | R-101-D8 | 512x1024  | 40000   |    9.425 | 2.35           | V100   | 79.58 |         81.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_40k_cityscapes/isanet_r101-d8_512x1024_40k_cityscapes_20210901_145553-293e6bd6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_40k_cityscapes/isanet_r101-d8_512x1024_40k_cityscapes_20210901_145553.log.json) |
+| ISANet | R-101-D8 | 512x1024  | 80000   |    9.425 | 2.35           | V100   | 80.32 |         81.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_80k_cityscapes/isanet_r101-d8_512x1024_80k_cityscapes_20210901_145243-5b99c9b2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_80k_cityscapes/isanet_r101-d8_512x1024_80k_cityscapes_20210901_145243.log.json) |
+| ISANet | R-101-D8 | 769x769   | 40000   |   10.815 | 0.92           | V100   | 79.68 |         80.95 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb2-40k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_40k_cityscapes/isanet_r101-d8_769x769_40k_cityscapes_20210903_111320-509e7224.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_40k_cityscapes/isanet_r101-d8_769x769_40k_cityscapes_20210903_111320.log.json)     |
+| ISANet | R-101-D8 | 769x769   | 80000   |   10.815 | 0.92           | V100   | 80.61 |         81.59 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_80k_cityscapes/isanet_r101-d8_769x769_80k_cityscapes_20210903_111319-24f71dfa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_80k_cityscapes/isanet_r101-d8_769x769_80k_cityscapes_20210903_111319.log.json)     |
+
+### ADE20K
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) |                                                                                                                        config | download                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------- | -------: | -------------- | ------ | ----- | ------------: | ----------------------------------------------------------------------------------------------------------------------------: | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ISANet | R-50-D8  | 512x512   | 80000   |      9.0 | 22.55          | V100   | 41.12 |         42.35 |   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_80k_ade20k/isanet_r50-d8_512x512_80k_ade20k_20210903_124557-6ed83a0c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_80k_ade20k/isanet_r50-d8_512x512_80k_ade20k_20210903_124557.log.json)         |
+| ISANet | R-50-D8  | 512x512   | 160000  |      9.0 | 22.55          | V100   | 42.59 |         43.07 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_160k_ade20k/isanet_r50-d8_512x512_160k_ade20k_20210903_104850-f752d0a3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_160k_ade20k/isanet_r50-d8_512x512_160k_ade20k_20210903_104850.log.json)     |
+| ISANet | R-101-D8 | 512x512   | 80000   |   12.562 | 10.56          | V100   | 43.51 |         44.38 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_80k_ade20k/isanet_r101-d8_512x512_80k_ade20k_20210903_162056-68b235c2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_80k_ade20k/isanet_r101-d8_512x512_80k_ade20k_20210903_162056.log.json)     |
+| ISANet | R-101-D8 | 512x512   | 160000  |   12.562 | 10.56          | V100   | 43.80 |          45.4 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_160k_ade20k/isanet_r101-d8_512x512_160k_ade20k_20210903_211431-a7879dcd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_160k_ade20k/isanet_r101-d8_512x512_160k_ade20k_20210903_211431.log.json) |
+
+### Pascal VOC 2012 + Aug
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) |                                                                                                                         config | download                                                                                                                                                                                                                                                                                                                                     |
+| ------ | -------- | --------- | ------- | -------: | -------------- | ------ | ----- | ------------: | -----------------------------------------------------------------------------------------------------------------------------: | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ISANet | R-50-D8  | 512x512   | 20000   |      5.9 | 23.08          | V100   | 76.78 |         77.79 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_20k_voc12aug/isanet_r50-d8_512x512_20k_voc12aug_20210901_164838-79d59b80.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_20k_voc12aug/isanet_r50-d8_512x512_20k_voc12aug_20210901_164838.log.json)     |
+| ISANet | R-50-D8  | 512x512   | 40000   |      5.9 | 23.08          | V100   | 76.20 |         77.22 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_40k_voc12aug/isanet_r50-d8_512x512_40k_voc12aug_20210901_151349-7d08a54e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_40k_voc12aug/isanet_r50-d8_512x512_40k_voc12aug_20210901_151349.log.json)     |
+| ISANet | R-101-D8 | 512x512   | 20000   |    9.465 | 7.42           | V100   | 78.46 |         79.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_20k_voc12aug/isanet_r101-d8_512x512_20k_voc12aug_20210901_115805-3ccbf355.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_20k_voc12aug/isanet_r101-d8_512x512_20k_voc12aug_20210901_115805.log.json) |
+| ISANet | R-101-D8 | 512x512   | 40000   |    9.465 | 7.42           | V100   | 78.12 |         79.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_40k_voc12aug/isanet_r101-d8_512x512_40k_voc12aug_20210901_145814-bc71233b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_40k_voc12aug/isanet_r101-d8_512x512_40k_voc12aug_20210901_145814.log.json) |
+
 ## Citation
 
 ```bibetex
@@ -45,36 +78,3 @@ The technical report above is also presented at:
   publisher={Springer}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) |                                                                                                                            config | download                                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------- | -------: | -------------- | ----- | ------------: | --------------------------------------------------------------------------------------------------------------------------------: | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| ISANet | R-50-D8  | 512x1024  | 40000   |    5.869 | 2.91           | 78.49 |         79.44 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_40k_cityscapes/isanet_r50-d8_512x1024_40k_cityscapes_20210901_054739-981bd763.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_40k_cityscapes/isanet_r50-d8_512x1024_40k_cityscapes_20210901_054739.log.json)     |
-| ISANet | R-50-D8  | 512x1024  | 80000   |    5.869 | 2.91           | 78.68 |         80.25 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_80k_cityscapes/isanet_r50-d8_512x1024_80k_cityscapes_20210901_074202-89384497.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_80k_cityscapes/isanet_r50-d8_512x1024_80k_cityscapes_20210901_074202.log.json)     |
-| ISANet | R-50-D8  | 769x769   | 40000   |    6.759 | 1.54           | 78.70 |         80.28 |   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb2-40k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_40k_cityscapes/isanet_r50-d8_769x769_40k_cityscapes_20210903_050200-4ae7e65b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_40k_cityscapes/isanet_r50-d8_769x769_40k_cityscapes_20210903_050200.log.json)         |
-| ISANet | R-50-D8  | 769x769   | 80000   |    6.759 | 1.54           | 79.29 |         80.53 |   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_80k_cityscapes/isanet_r50-d8_769x769_80k_cityscapes_20210903_101126-99b54519.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_80k_cityscapes/isanet_r50-d8_769x769_80k_cityscapes_20210903_101126.log.json)         |
-| ISANet | R-101-D8 | 512x1024  | 40000   |    9.425 | 2.35           | 79.58 |         81.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_40k_cityscapes/isanet_r101-d8_512x1024_40k_cityscapes_20210901_145553-293e6bd6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_40k_cityscapes/isanet_r101-d8_512x1024_40k_cityscapes_20210901_145553.log.json) |
-| ISANet | R-101-D8 | 512x1024  | 80000   |    9.425 | 2.35           | 80.32 |         81.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_80k_cityscapes/isanet_r101-d8_512x1024_80k_cityscapes_20210901_145243-5b99c9b2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_80k_cityscapes/isanet_r101-d8_512x1024_80k_cityscapes_20210901_145243.log.json) |
-| ISANet | R-101-D8 | 769x769   | 40000   |   10.815 | 0.92           | 79.68 |         80.95 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb2-40k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_40k_cityscapes/isanet_r101-d8_769x769_40k_cityscapes_20210903_111320-509e7224.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_40k_cityscapes/isanet_r101-d8_769x769_40k_cityscapes_20210903_111320.log.json)     |
-| ISANet | R-101-D8 | 769x769   | 80000   |   10.815 | 0.92           | 80.61 |         81.59 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_80k_cityscapes/isanet_r101-d8_769x769_80k_cityscapes_20210903_111319-24f71dfa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_80k_cityscapes/isanet_r101-d8_769x769_80k_cityscapes_20210903_111319.log.json)     |
-
-### ADE20K
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) |                                                                                                                        config | download                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------- | -------: | -------------- | ----- | ------------: | ----------------------------------------------------------------------------------------------------------------------------: | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| ISANet | R-50-D8  | 512x512   | 80000   |      9.0 | 22.55          | 41.12 |         42.35 |   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_80k_ade20k/isanet_r50-d8_512x512_80k_ade20k_20210903_124557-6ed83a0c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_80k_ade20k/isanet_r50-d8_512x512_80k_ade20k_20210903_124557.log.json)         |
-| ISANet | R-50-D8  | 512x512   | 160000  |      9.0 | 22.55          | 42.59 |         43.07 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_160k_ade20k/isanet_r50-d8_512x512_160k_ade20k_20210903_104850-f752d0a3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_160k_ade20k/isanet_r50-d8_512x512_160k_ade20k_20210903_104850.log.json)     |
-| ISANet | R-101-D8 | 512x512   | 80000   |   12.562 | 10.56          | 43.51 |         44.38 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_80k_ade20k/isanet_r101-d8_512x512_80k_ade20k_20210903_162056-68b235c2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_80k_ade20k/isanet_r101-d8_512x512_80k_ade20k_20210903_162056.log.json)     |
-| ISANet | R-101-D8 | 512x512   | 160000  |   12.562 | 10.56          | 43.80 |          45.4 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_160k_ade20k/isanet_r101-d8_512x512_160k_ade20k_20210903_211431-a7879dcd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_160k_ade20k/isanet_r101-d8_512x512_160k_ade20k_20210903_211431.log.json) |
-
-### Pascal VOC 2012 + Aug
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) |                                                                                                                         config | download                                                                                                                                                                                                                                                                                                                                     |
-| ------ | -------- | --------- | ------- | -------: | -------------- | ----- | ------------: | -----------------------------------------------------------------------------------------------------------------------------: | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| ISANet | R-50-D8  | 512x512   | 20000   |      5.9 | 23.08          | 76.78 |         77.79 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_20k_voc12aug/isanet_r50-d8_512x512_20k_voc12aug_20210901_164838-79d59b80.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_20k_voc12aug/isanet_r50-d8_512x512_20k_voc12aug_20210901_164838.log.json)     |
-| ISANet | R-50-D8  | 512x512   | 40000   |      5.9 | 23.08          | 76.20 |         77.22 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_40k_voc12aug/isanet_r50-d8_512x512_40k_voc12aug_20210901_151349-7d08a54e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_40k_voc12aug/isanet_r50-d8_512x512_40k_voc12aug_20210901_151349.log.json)     |
-| ISANet | R-101-D8 | 512x512   | 20000   |    9.465 | 7.42           | 78.46 |         79.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_20k_voc12aug/isanet_r101-d8_512x512_20k_voc12aug_20210901_115805-3ccbf355.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_20k_voc12aug/isanet_r101-d8_512x512_20k_voc12aug_20210901_115805.log.json) |
-| ISANet | R-101-D8 | 512x512   | 40000   |    9.465 | 7.42           | 78.12 |         79.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_40k_voc12aug/isanet_r101-d8_512x512_40k_voc12aug_20210901_145814-bc71233b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_40k_voc12aug/isanet_r101-d8_512x512_40k_voc12aug_20210901_145814.log.json) |
diff --git a/configs/isanet/isanet.yml b/configs/isanet/isanet.yml
deleted file mode 100644
index 405b3c1231..0000000000
--- a/configs/isanet/isanet.yml
+++ /dev/null
@@ -1,369 +0,0 @@
-Collections:
-- Name: ISANet
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-    - Pascal VOC 2012 + Aug
-  Paper:
-    URL: https://arxiv.org/abs/1907.12273
-    Title: Interlaced Sparse Self-Attention for Semantic Segmentation
-  README: configs/isanet/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/decode_heads/isa_head.py#L58
-    Version: v0.18.0
-  Converted From:
-    Code: https://github.com/openseg-group/openseg.pytorch
-Models:
-- Name: isanet_r50-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: ISANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 343.64
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 5.869
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.49
-      mIoU(ms+flip): 79.44
-  Config: configs/isanet/isanet_r50-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_40k_cityscapes/isanet_r50-d8_512x1024_40k_cityscapes_20210901_054739-981bd763.pth
-- Name: isanet_r50-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: ISANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 343.64
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 5.869
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.68
-      mIoU(ms+flip): 80.25
-  Config: configs/isanet/isanet_r50-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_80k_cityscapes/isanet_r50-d8_512x1024_80k_cityscapes_20210901_074202-89384497.pth
-- Name: isanet_r50-d8_4xb2-40k_cityscapes-769x769
-  In Collection: ISANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 649.35
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 6.759
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.7
-      mIoU(ms+flip): 80.28
-  Config: configs/isanet/isanet_r50-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_40k_cityscapes/isanet_r50-d8_769x769_40k_cityscapes_20210903_050200-4ae7e65b.pth
-- Name: isanet_r50-d8_4xb2-80k_cityscapes-769x769
-  In Collection: ISANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 649.35
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 6.759
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.29
-      mIoU(ms+flip): 80.53
-  Config: configs/isanet/isanet_r50-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_80k_cityscapes/isanet_r50-d8_769x769_80k_cityscapes_20210903_101126-99b54519.pth
-- Name: isanet_r101-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: ISANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 425.53
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 9.425
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.58
-      mIoU(ms+flip): 81.05
-  Config: configs/isanet/isanet_r101-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_40k_cityscapes/isanet_r101-d8_512x1024_40k_cityscapes_20210901_145553-293e6bd6.pth
-- Name: isanet_r101-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: ISANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 425.53
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 9.425
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.32
-      mIoU(ms+flip): 81.58
-  Config: configs/isanet/isanet_r101-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_80k_cityscapes/isanet_r101-d8_512x1024_80k_cityscapes_20210901_145243-5b99c9b2.pth
-- Name: isanet_r101-d8_4xb2-40k_cityscapes-769x769
-  In Collection: ISANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 1086.96
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 10.815
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.68
-      mIoU(ms+flip): 80.95
-  Config: configs/isanet/isanet_r101-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_40k_cityscapes/isanet_r101-d8_769x769_40k_cityscapes_20210903_111320-509e7224.pth
-- Name: isanet_r101-d8_4xb2-80k_cityscapes-769x769
-  In Collection: ISANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 1086.96
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 10.815
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.61
-      mIoU(ms+flip): 81.59
-  Config: configs/isanet/isanet_r101-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_80k_cityscapes/isanet_r101-d8_769x769_80k_cityscapes_20210903_111319-24f71dfa.pth
-- Name: isanet_r50-d8_4xb4-80k_ade20k-512x512
-  In Collection: ISANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 44.35
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 41.12
-      mIoU(ms+flip): 42.35
-  Config: configs/isanet/isanet_r50-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_80k_ade20k/isanet_r50-d8_512x512_80k_ade20k_20210903_124557-6ed83a0c.pth
-- Name: isanet_r50-d8_4xb4-160k_ade20k-512x512
-  In Collection: ISANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 44.35
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.59
-      mIoU(ms+flip): 43.07
-  Config: configs/isanet/isanet_r50-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_160k_ade20k/isanet_r50-d8_512x512_160k_ade20k_20210903_104850-f752d0a3.pth
-- Name: isanet_r101-d8_4xb4-80k_ade20k-512x512
-  In Collection: ISANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 94.7
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 12.562
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.51
-      mIoU(ms+flip): 44.38
-  Config: configs/isanet/isanet_r101-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_80k_ade20k/isanet_r101-d8_512x512_80k_ade20k_20210903_162056-68b235c2.pth
-- Name: isanet_r101-d8_4xb4-160k_ade20k-512x512
-  In Collection: ISANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 94.7
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 12.562
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.8
-      mIoU(ms+flip): 45.4
-  Config: configs/isanet/isanet_r101-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_160k_ade20k/isanet_r101-d8_512x512_160k_ade20k_20210903_211431-a7879dcd.pth
-- Name: isanet_r50-d8_4xb4-20k_voc12aug-512x512
-  In Collection: ISANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 43.33
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 5.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 76.78
-      mIoU(ms+flip): 77.79
-  Config: configs/isanet/isanet_r50-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_20k_voc12aug/isanet_r50-d8_512x512_20k_voc12aug_20210901_164838-79d59b80.pth
-- Name: isanet_r50-d8_4xb4-40k_voc12aug-512x512
-  In Collection: ISANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 43.33
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 5.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 76.2
-      mIoU(ms+flip): 77.22
-  Config: configs/isanet/isanet_r50-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_40k_voc12aug/isanet_r50-d8_512x512_40k_voc12aug_20210901_151349-7d08a54e.pth
-- Name: isanet_r101-d8_4xb4-20k_voc12aug-512x512
-  In Collection: ISANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 134.77
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.465
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 78.46
-      mIoU(ms+flip): 79.16
-  Config: configs/isanet/isanet_r101-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_20k_voc12aug/isanet_r101-d8_512x512_20k_voc12aug_20210901_115805-3ccbf355.pth
-- Name: isanet_r101-d8_4xb4-40k_voc12aug-512x512
-  In Collection: ISANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 134.77
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.465
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 78.12
-      mIoU(ms+flip): 79.04
-  Config: configs/isanet/isanet_r101-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_40k_voc12aug/isanet_r101-d8_512x512_40k_voc12aug_20210901_145814-bc71233b.pth
diff --git a/configs/isanet/metafile.yaml b/configs/isanet/metafile.yaml
new file mode 100644
index 0000000000..ad394eabb2
--- /dev/null
+++ b/configs/isanet/metafile.yaml
@@ -0,0 +1,399 @@
+Collections:
+- Name: ISANet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - ADE20K
+    - Pascal VOC 2012 + Aug
+  Paper:
+    Title: Interlaced Sparse Self-Attention for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.12273
+  README: configs/isanet/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: isanet_r50-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: ISANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.49
+      mIoU(ms+flip): 79.44
+  Config: configs/isanet/isanet_r50-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - ISANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.869
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_40k_cityscapes/isanet_r50-d8_512x1024_40k_cityscapes_20210901_054739-981bd763.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_40k_cityscapes/isanet_r50-d8_512x1024_40k_cityscapes_20210901_054739.log.json
+  Paper:
+    Title: Interlaced Sparse Self-Attention for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.12273
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/decode_heads/isa_head.py#L58
+  Framework: PyTorch
+- Name: isanet_r50-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: ISANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.68
+      mIoU(ms+flip): 80.25
+  Config: configs/isanet/isanet_r50-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - ISANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.869
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_80k_cityscapes/isanet_r50-d8_512x1024_80k_cityscapes_20210901_074202-89384497.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_80k_cityscapes/isanet_r50-d8_512x1024_80k_cityscapes_20210901_074202.log.json
+  Paper:
+    Title: Interlaced Sparse Self-Attention for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.12273
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/decode_heads/isa_head.py#L58
+  Framework: PyTorch
+- Name: isanet_r50-d8_4xb2-40k_cityscapes-769x769
+  In Collection: ISANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.7
+      mIoU(ms+flip): 80.28
+  Config: configs/isanet/isanet_r50-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - ISANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.759
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_40k_cityscapes/isanet_r50-d8_769x769_40k_cityscapes_20210903_050200-4ae7e65b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_40k_cityscapes/isanet_r50-d8_769x769_40k_cityscapes_20210903_050200.log.json
+  Paper:
+    Title: Interlaced Sparse Self-Attention for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.12273
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/decode_heads/isa_head.py#L58
+  Framework: PyTorch
+- Name: isanet_r50-d8_4xb2-80k_cityscapes-769x769
+  In Collection: ISANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.29
+      mIoU(ms+flip): 80.53
+  Config: configs/isanet/isanet_r50-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - ISANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.759
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_80k_cityscapes/isanet_r50-d8_769x769_80k_cityscapes_20210903_101126-99b54519.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_80k_cityscapes/isanet_r50-d8_769x769_80k_cityscapes_20210903_101126.log.json
+  Paper:
+    Title: Interlaced Sparse Self-Attention for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.12273
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/decode_heads/isa_head.py#L58
+  Framework: PyTorch
+- Name: isanet_r101-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: ISANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.58
+      mIoU(ms+flip): 81.05
+  Config: configs/isanet/isanet_r101-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - ISANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.425
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_40k_cityscapes/isanet_r101-d8_512x1024_40k_cityscapes_20210901_145553-293e6bd6.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_40k_cityscapes/isanet_r101-d8_512x1024_40k_cityscapes_20210901_145553.log.json
+  Paper:
+    Title: Interlaced Sparse Self-Attention for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.12273
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/decode_heads/isa_head.py#L58
+  Framework: PyTorch
+- Name: isanet_r101-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: ISANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.32
+      mIoU(ms+flip): 81.58
+  Config: configs/isanet/isanet_r101-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - ISANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.425
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_80k_cityscapes/isanet_r101-d8_512x1024_80k_cityscapes_20210901_145243-5b99c9b2.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_80k_cityscapes/isanet_r101-d8_512x1024_80k_cityscapes_20210901_145243.log.json
+  Paper:
+    Title: Interlaced Sparse Self-Attention for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.12273
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/decode_heads/isa_head.py#L58
+  Framework: PyTorch
+- Name: isanet_r101-d8_4xb2-40k_cityscapes-769x769
+  In Collection: ISANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.68
+      mIoU(ms+flip): 80.95
+  Config: configs/isanet/isanet_r101-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - ISANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.815
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_40k_cityscapes/isanet_r101-d8_769x769_40k_cityscapes_20210903_111320-509e7224.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_40k_cityscapes/isanet_r101-d8_769x769_40k_cityscapes_20210903_111320.log.json
+  Paper:
+    Title: Interlaced Sparse Self-Attention for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.12273
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/decode_heads/isa_head.py#L58
+  Framework: PyTorch
+- Name: isanet_r101-d8_4xb2-80k_cityscapes-769x769
+  In Collection: ISANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.61
+      mIoU(ms+flip): 81.59
+  Config: configs/isanet/isanet_r101-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - ISANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.815
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_80k_cityscapes/isanet_r101-d8_769x769_80k_cityscapes_20210903_111319-24f71dfa.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_80k_cityscapes/isanet_r101-d8_769x769_80k_cityscapes_20210903_111319.log.json
+  Paper:
+    Title: Interlaced Sparse Self-Attention for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.12273
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/decode_heads/isa_head.py#L58
+  Framework: PyTorch
+- Name: isanet_r50-d8_4xb4-80k_ade20k-512x512
+  In Collection: ISANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 41.12
+      mIoU(ms+flip): 42.35
+  Config: configs/isanet/isanet_r50-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - ISANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_80k_ade20k/isanet_r50-d8_512x512_80k_ade20k_20210903_124557-6ed83a0c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_80k_ade20k/isanet_r50-d8_512x512_80k_ade20k_20210903_124557.log.json
+  Paper:
+    Title: Interlaced Sparse Self-Attention for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.12273
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/decode_heads/isa_head.py#L58
+  Framework: PyTorch
+- Name: isanet_r50-d8_4xb4-160k_ade20k-512x512
+  In Collection: ISANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.59
+      mIoU(ms+flip): 43.07
+  Config: configs/isanet/isanet_r50-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - ISANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_160k_ade20k/isanet_r50-d8_512x512_160k_ade20k_20210903_104850-f752d0a3.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_160k_ade20k/isanet_r50-d8_512x512_160k_ade20k_20210903_104850.log.json
+  Paper:
+    Title: Interlaced Sparse Self-Attention for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.12273
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/decode_heads/isa_head.py#L58
+  Framework: PyTorch
+- Name: isanet_r101-d8_4xb4-80k_ade20k-512x512
+  In Collection: ISANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.51
+      mIoU(ms+flip): 44.38
+  Config: configs/isanet/isanet_r101-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - ISANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 12.562
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_80k_ade20k/isanet_r101-d8_512x512_80k_ade20k_20210903_162056-68b235c2.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_80k_ade20k/isanet_r101-d8_512x512_80k_ade20k_20210903_162056.log.json
+  Paper:
+    Title: Interlaced Sparse Self-Attention for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.12273
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/decode_heads/isa_head.py#L58
+  Framework: PyTorch
+- Name: isanet_r101-d8_4xb4-160k_ade20k-512x512
+  In Collection: ISANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.8
+      mIoU(ms+flip): 45.4
+  Config: configs/isanet/isanet_r101-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - ISANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 12.562
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_160k_ade20k/isanet_r101-d8_512x512_160k_ade20k_20210903_211431-a7879dcd.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_160k_ade20k/isanet_r101-d8_512x512_160k_ade20k_20210903_211431.log.json
+  Paper:
+    Title: Interlaced Sparse Self-Attention for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.12273
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/decode_heads/isa_head.py#L58
+  Framework: PyTorch
+- Name: isanet_r50-d8_4xb4-20k_voc12aug-512x512
+  In Collection: ISANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 76.78
+      mIoU(ms+flip): 77.79
+  Config: configs/isanet/isanet_r50-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - ISANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_20k_voc12aug/isanet_r50-d8_512x512_20k_voc12aug_20210901_164838-79d59b80.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_20k_voc12aug/isanet_r50-d8_512x512_20k_voc12aug_20210901_164838.log.json
+  Paper:
+    Title: Interlaced Sparse Self-Attention for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.12273
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/decode_heads/isa_head.py#L58
+  Framework: PyTorch
+- Name: isanet_r50-d8_4xb4-40k_voc12aug-512x512
+  In Collection: ISANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 76.2
+      mIoU(ms+flip): 77.22
+  Config: configs/isanet/isanet_r50-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - ISANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_40k_voc12aug/isanet_r50-d8_512x512_40k_voc12aug_20210901_151349-7d08a54e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_40k_voc12aug/isanet_r50-d8_512x512_40k_voc12aug_20210901_151349.log.json
+  Paper:
+    Title: Interlaced Sparse Self-Attention for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.12273
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/decode_heads/isa_head.py#L58
+  Framework: PyTorch
+- Name: isanet_r101-d8_4xb4-20k_voc12aug-512x512
+  In Collection: ISANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 78.46
+      mIoU(ms+flip): 79.16
+  Config: configs/isanet/isanet_r101-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - ISANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.465
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_20k_voc12aug/isanet_r101-d8_512x512_20k_voc12aug_20210901_115805-3ccbf355.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_20k_voc12aug/isanet_r101-d8_512x512_20k_voc12aug_20210901_115805.log.json
+  Paper:
+    Title: Interlaced Sparse Self-Attention for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.12273
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/decode_heads/isa_head.py#L58
+  Framework: PyTorch
+- Name: isanet_r101-d8_4xb4-40k_voc12aug-512x512
+  In Collection: ISANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 78.12
+      mIoU(ms+flip): 79.04
+  Config: configs/isanet/isanet_r101-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - ISANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.465
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_40k_voc12aug/isanet_r101-d8_512x512_40k_voc12aug_20210901_145814-bc71233b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_40k_voc12aug/isanet_r101-d8_512x512_40k_voc12aug_20210901_145814.log.json
+  Paper:
+    Title: Interlaced Sparse Self-Attention for Semantic Segmentation
+    URL: https://arxiv.org/abs/1907.12273
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/decode_heads/isa_head.py#L58
+  Framework: PyTorch
diff --git a/configs/knet/README.md b/configs/knet/README.md
index ed5bc06257..070c7256da 100644
--- a/configs/knet/README.md
+++ b/configs/knet/README.md
@@ -1,6 +1,6 @@
 # K-Net
 
-[K-Net: Towards Unified Image Segmentation](https://arxiv.org/abs/2106.14855)
+> [K-Net: Towards Unified Image Segmentation](https://arxiv.org/abs/2106.14855)
 
 ## Introduction
 
@@ -22,29 +22,31 @@ Semantic, instance, and panoptic segmentations have been addressed using differe
 <img src="https://user-images.githubusercontent.com/24582831/157008300-9f40905c-b8e8-4a2a-9593-c1177fa35b2c.png" width="90%"/>
 </div>
 
-```bibtex
-@inproceedings{zhang2021knet,
-    title={{K-Net: Towards} Unified Image Segmentation},
-    author={Wenwei Zhang and Jiangmiao Pang and Kai Chen and Chen Change Loy},
-    year={2021},
-    booktitle={NeurIPS},
-}
-```
-
 ## Results and models
 
 ### ADE20K
 
-| Method           | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) | config                                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                                                                         |
-| ---------------- | -------- | --------- | ------- | -------- | -------------- | ----- | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| KNet + FCN       | R-50-D8  | 512x512   | 80000   | 7.01     | 19.24          | 43.60 | 45.12         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_r50-d8_fcn_8xb2-adamw-80k_ade20k-512x512.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_043751-abcab920.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_043751.log.json)                         |
-| KNet + PSPNet    | R-50-D8  | 512x512   | 80000   | 6.98     | 20.04          | 44.18 | 45.58         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_r50-d8_pspnet_8xb2-adamw-80k_ade20k-512x512.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_054634-d2c72240.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_054634.log.json)             |
-| KNet + DeepLabV3 | R-50-D8  | 512x512   | 80000   | 7.42     | 12.10          | 45.06 | 46.11         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_r50-d8_deeplabv3_8xb2-adamw-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_041642-00c8fbeb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_041642.log.json) |
-| KNet + UperNet   | R-50-D8  | 512x512   | 80000   | 7.34     | 17.11          | 43.45 | 44.07         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_r50-d8_upernet_8xb2-adamw-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220304_125657-215753b0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220304_125657.log.json)         |
-| KNet + UperNet   | Swin-T   | 512x512   | 80000   | 7.57     | 15.56          | 45.84 | 46.27         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_swin-t_upernet_8xb2-adamw-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k_20220303_133059-7545e1dc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k_20220303_133059.log.json)         |
-| KNet + UperNet   | Swin-L   | 512x512   | 80000   | 13.5     | 8.29           | 52.05 | 53.24         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_swin-l_upernet_8xb2-adamw-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k_20220303_154559-d8da9a90.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k_20220303_154559.log.json)         |
-| KNet + UperNet   | Swin-L   | 640x640   | 80000   | 13.54    | 8.29           | 52.21 | 53.34         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_swin-l_upernet_8xb2-adamw-80k_ade20k-640x640.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k_20220301_220747-8787fc71.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k_20220301_220747.log.json)         |
+| Method           | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                                                                         |
+| ---------------- | -------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| KNet + FCN       | R-50-D8  | 512x512   | 80000   | 7.01     | 19.24          | V100   | 43.60 | 45.12         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_r50-d8_fcn_8xb2-adamw-80k_ade20k-512x512.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_043751-abcab920.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_043751.log.json)                         |
+| KNet + PSPNet    | R-50-D8  | 512x512   | 80000   | 6.98     | 20.04          | V100   | 44.18 | 45.58         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_r50-d8_pspnet_8xb2-adamw-80k_ade20k-512x512.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_054634-d2c72240.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_054634.log.json)             |
+| KNet + DeepLabV3 | R-50-D8  | 512x512   | 80000   | 7.42     | 12.10          | V100   | 45.06 | 46.11         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_r50-d8_deeplabv3_8xb2-adamw-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_041642-00c8fbeb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_041642.log.json) |
+| KNet + UperNet   | R-50-D8  | 512x512   | 80000   | 7.34     | 17.11          | V100   | 43.45 | 44.07         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_r50-d8_upernet_8xb2-adamw-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220304_125657-215753b0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220304_125657.log.json)         |
+| KNet + UperNet   | Swin-T   | 512x512   | 80000   | 7.57     | 15.56          | V100   | 45.84 | 46.27         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_swin-t_upernet_8xb2-adamw-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k_20220303_133059-7545e1dc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k_20220303_133059.log.json)         |
+| KNet + UperNet   | Swin-L   | 512x512   | 80000   | 13.5     | 8.29           | V100   | 52.05 | 53.24         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_swin-l_upernet_8xb2-adamw-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k_20220303_154559-d8da9a90.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k_20220303_154559.log.json)         |
+| KNet + UperNet   | Swin-L   | 640x640   | 80000   | 13.54    | 8.29           | V100   | 52.21 | 53.34         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_swin-l_upernet_8xb2-adamw-80k_ade20k-640x640.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k_20220301_220747-8787fc71.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k_20220301_220747.log.json)         |
 
 Note:
 
 - All experiments of K-Net are implemented with 8 V100 (32G) GPUs with 2 samplers per GPU.
+
+# Citation
+
+```bibtex
+@inproceedings{zhang2021knet,
+    title={{K-Net: Towards} Unified Image Segmentation},
+    author={Wenwei Zhang and Jiangmiao Pang and Kai Chen and Chen Change Loy},
+    year={2021},
+    booktitle={NeurIPS},
+}
+```
diff --git a/configs/knet/knet.yml b/configs/knet/knet.yml
deleted file mode 100644
index 1c98e4703c..0000000000
--- a/configs/knet/knet.yml
+++ /dev/null
@@ -1,169 +0,0 @@
-Collections:
-- Name: KNet
-  Metadata:
-    Training Data:
-    - ADE20K
-  Paper:
-    URL: https://arxiv.org/abs/2106.14855
-    Title: 'K-Net: Towards Unified Image Segmentation'
-  README: configs/knet/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.23.0/mmseg/models/decode_heads/knet_head.py#L392
-    Version: v0.23.0
-  Converted From:
-    Code: https://github.com/ZwwWayne/K-Net/
-Models:
-- Name: knet-s3_r50-d8_fcn_8xb2-adamw-80k_ade20k-512x512
-  In Collection: KNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 51.98
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 7.01
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.6
-      mIoU(ms+flip): 45.12
-  Config: configs/knet/knet-s3_r50-d8_fcn_8xb2-adamw-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_043751-abcab920.pth
-- Name: knet-s3_r50-d8_pspnet_8xb2-adamw-80k_ade20k-512x512
-  In Collection: KNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 49.9
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.98
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 44.18
-      mIoU(ms+flip): 45.58
-  Config: configs/knet/knet-s3_r50-d8_pspnet_8xb2-adamw-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_054634-d2c72240.pth
-- Name: knet-s3_r50-d8_deeplabv3_8xb2-adamw-80k_ade20k-512x512
-  In Collection: KNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 82.64
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 7.42
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.06
-      mIoU(ms+flip): 46.11
-  Config: configs/knet/knet-s3_r50-d8_deeplabv3_8xb2-adamw-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_041642-00c8fbeb.pth
-- Name: knet-s3_r50-d8_upernet_8xb2-adamw-80k_ade20k-512x512
-  In Collection: KNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 58.45
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 7.34
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.45
-      mIoU(ms+flip): 44.07
-  Config: configs/knet/knet-s3_r50-d8_upernet_8xb2-adamw-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220304_125657-215753b0.pth
-- Name: knet-s3_swin-t_upernet_8xb2-adamw-80k_ade20k-512x512
-  In Collection: KNet
-  Metadata:
-    backbone: Swin-T
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 64.27
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 7.57
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.84
-      mIoU(ms+flip): 46.27
-  Config: configs/knet/knet-s3_swin-t_upernet_8xb2-adamw-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k_20220303_133059-7545e1dc.pth
-- Name: knet-s3_swin-l_upernet_8xb2-adamw-80k_ade20k-512x512
-  In Collection: KNet
-  Metadata:
-    backbone: Swin-L
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 120.63
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 13.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 52.05
-      mIoU(ms+flip): 53.24
-  Config: configs/knet/knet-s3_swin-l_upernet_8xb2-adamw-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k_20220303_154559-d8da9a90.pth
-- Name: knet-s3_swin-l_upernet_8xb2-adamw-80k_ade20k-640x640
-  In Collection: KNet
-  Metadata:
-    backbone: Swin-L
-    crop size: (640,640)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 120.63
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (640,640)
-    Training Memory (GB): 13.54
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 52.21
-      mIoU(ms+flip): 53.34
-  Config: configs/knet/knet-s3_swin-l_upernet_8xb2-adamw-80k_ade20k-640x640.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k_20220301_220747-8787fc71.pth
diff --git a/configs/knet/metafile.yaml b/configs/knet/metafile.yaml
new file mode 100644
index 0000000000..0f4ab79609
--- /dev/null
+++ b/configs/knet/metafile.yaml
@@ -0,0 +1,188 @@
+Collections:
+- Name: KNet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - ADE20K
+  Paper:
+    Title: 'K-Net: Towards Unified Image Segmentation'
+    URL: https://arxiv.org/abs/2106.14855
+  README: configs/knet/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: knet-s3_r50-d8_fcn_8xb2-adamw-80k_ade20k-512x512
+  In Collection: KNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.6
+      mIoU(ms+flip): 45.12
+  Config: configs/knet/knet-s3_r50-d8_fcn_8xb2-adamw-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - KNet
+    - FCN
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 7.01
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_043751-abcab920.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_043751.log.json
+  Paper:
+    Title: 'K-Net: Towards Unified Image Segmentation'
+    URL: https://arxiv.org/abs/2106.14855
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.23.0/mmseg/models/decode_heads/knet_head.py#L392
+  Framework: PyTorch
+- Name: knet-s3_r50-d8_pspnet_8xb2-adamw-80k_ade20k-512x512
+  In Collection: KNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 44.18
+      mIoU(ms+flip): 45.58
+  Config: configs/knet/knet-s3_r50-d8_pspnet_8xb2-adamw-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - KNet
+    - PSPNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 6.98
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_054634-d2c72240.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_054634.log.json
+  Paper:
+    Title: 'K-Net: Towards Unified Image Segmentation'
+    URL: https://arxiv.org/abs/2106.14855
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.23.0/mmseg/models/decode_heads/knet_head.py#L392
+  Framework: PyTorch
+- Name: knet-s3_r50-d8_deeplabv3_8xb2-adamw-80k_ade20k-512x512
+  In Collection: KNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.06
+      mIoU(ms+flip): 46.11
+  Config: configs/knet/knet-s3_r50-d8_deeplabv3_8xb2-adamw-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - KNet
+    - DeepLabV3
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 7.42
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_041642-00c8fbeb.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_041642.log.json
+  Paper:
+    Title: 'K-Net: Towards Unified Image Segmentation'
+    URL: https://arxiv.org/abs/2106.14855
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.23.0/mmseg/models/decode_heads/knet_head.py#L392
+  Framework: PyTorch
+- Name: knet-s3_r50-d8_upernet_8xb2-adamw-80k_ade20k-512x512
+  In Collection: KNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.45
+      mIoU(ms+flip): 44.07
+  Config: configs/knet/knet-s3_r50-d8_upernet_8xb2-adamw-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - KNet
+    - UperNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 7.34
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220304_125657-215753b0.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220304_125657.log.json
+  Paper:
+    Title: 'K-Net: Towards Unified Image Segmentation'
+    URL: https://arxiv.org/abs/2106.14855
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.23.0/mmseg/models/decode_heads/knet_head.py#L392
+  Framework: PyTorch
+- Name: knet-s3_swin-t_upernet_8xb2-adamw-80k_ade20k-512x512
+  In Collection: KNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.84
+      mIoU(ms+flip): 46.27
+  Config: configs/knet/knet-s3_swin-t_upernet_8xb2-adamw-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Swin-T
+    - KNet
+    - UperNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 7.57
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k_20220303_133059-7545e1dc.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k_20220303_133059.log.json
+  Paper:
+    Title: 'K-Net: Towards Unified Image Segmentation'
+    URL: https://arxiv.org/abs/2106.14855
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.23.0/mmseg/models/decode_heads/knet_head.py#L392
+  Framework: PyTorch
+- Name: knet-s3_swin-l_upernet_8xb2-adamw-80k_ade20k-512x512
+  In Collection: KNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 52.05
+      mIoU(ms+flip): 53.24
+  Config: configs/knet/knet-s3_swin-l_upernet_8xb2-adamw-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Swin-L
+    - KNet
+    - UperNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 13.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k_20220303_154559-d8da9a90.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k_20220303_154559.log.json
+  Paper:
+    Title: 'K-Net: Towards Unified Image Segmentation'
+    URL: https://arxiv.org/abs/2106.14855
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.23.0/mmseg/models/decode_heads/knet_head.py#L392
+  Framework: PyTorch
+- Name: knet-s3_swin-l_upernet_8xb2-adamw-80k_ade20k-640x640
+  In Collection: KNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 52.21
+      mIoU(ms+flip): 53.34
+  Config: configs/knet/knet-s3_swin-l_upernet_8xb2-adamw-80k_ade20k-640x640.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Swin-L
+    - KNet
+    - UperNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 13.54
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k_20220301_220747-8787fc71.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k_20220301_220747.log.json
+  Paper:
+    Title: 'K-Net: Towards Unified Image Segmentation'
+    URL: https://arxiv.org/abs/2106.14855
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.23.0/mmseg/models/decode_heads/knet_head.py#L392
+  Framework: PyTorch
diff --git a/configs/mae/README.md b/configs/mae/README.md
index 330749732e..94ade08823 100644
--- a/configs/mae/README.md
+++ b/configs/mae/README.md
@@ -1,6 +1,6 @@
 # MAE
 
-[Masked Autoencoders Are Scalable Vision Learners](https://arxiv.org/abs/2111.06377)
+> [Masked Autoencoders Are Scalable Vision Learners](https://arxiv.org/abs/2111.06377)
 
 ## Introduction
 
@@ -22,17 +22,6 @@ This paper shows that masked autoencoders (MAE) are scalable self-supervised lea
 <img src="https://user-images.githubusercontent.com/24582831/165456416-1cba54bf-b1b5-4bdf-ad86-d6390de7f342.png" width="70%"/>
 </div>
 
-## Citation
-
-```bibtex
-@article{he2021masked,
-  title={Masked autoencoders are scalable vision learners},
-  author={He, Kaiming and Chen, Xinlei and Xie, Saining and Li, Yanghao and Doll{\'a}r, Piotr and Girshick, Ross},
-  journal={arXiv preprint arXiv:2111.06377},
-  year={2021}
-}
-```
-
 ## Usage
 
 To use other repositories' pre-trained models, it is necessary to convert keys.
@@ -77,6 +66,17 @@ upernet_mae-base_fp16_8x2_512x512_160k_ade20k_20220426_174752-f92a2975.pth $GPUS
 
 ### ADE20K
 
-| Method  | Backbone | Crop Size | pretrain    | pretrain img size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                                       |
-| ------- | -------- | --------- | ----------- | ----------------- | ---------- | ------- | -------- | -------------- | ----- | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| UPerNet | ViT-B    | 512x512   | ImageNet-1K | 224x224           | 16         | 160000  | 9.96     | 7.14           | 48.13 |         48.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mae/mae-base_upernet_8xb2-amp-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mae/upernet_mae-base_fp16_8x2_512x512_160k_ade20k/upernet_mae-base_fp16_8x2_512x512_160k_ade20k_20220426_174752-f92a2975.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mae/upernet_mae-base_fp16_8x2_512x512_160k_ade20k/upernet_mae-base_fp16_8x2_512x512_160k_ade20k_20220426_174752.log.json) |
+| Method  | Backbone | Crop Size | pretrain    | pretrain img size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                                       |
+| ------- | -------- | --------- | ----------- | ----------------- | ---------- | ------- | -------- | -------------- | ------ | ----- | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| UPerNet | ViT-B    | 512x512   | ImageNet-1K | 224x224           | 16         | 160000  | 9.96     | 7.14           | V100   | 48.13 |         48.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mae/mae-base_upernet_8xb2-amp-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mae/upernet_mae-base_fp16_8x2_512x512_160k_ade20k/upernet_mae-base_fp16_8x2_512x512_160k_ade20k_20220426_174752-f92a2975.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mae/upernet_mae-base_fp16_8x2_512x512_160k_ade20k/upernet_mae-base_fp16_8x2_512x512_160k_ade20k_20220426_174752.log.json) |
+
+## Citation
+
+```bibtex
+@article{he2021masked,
+  title={Masked autoencoders are scalable vision learners},
+  author={He, Kaiming and Chen, Xinlei and Xie, Saining and Li, Yanghao and Doll{\'a}r, Piotr and Girshick, Ross},
+  journal={arXiv preprint arXiv:2111.06377},
+  year={2021}
+}
+```
diff --git a/configs/mae/mae.yml b/configs/mae/mae.yml
deleted file mode 100644
index 72b2cc7f12..0000000000
--- a/configs/mae/mae.yml
+++ /dev/null
@@ -1,23 +0,0 @@
-Models:
-- Name: mae-base_upernet_8xb2-amp-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: ViT-B
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 140.06
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: AMP
-      resolution: (512,512)
-    Training Memory (GB): 9.96
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 48.13
-      mIoU(ms+flip): 48.7
-  Config: configs/mae/mae-base_upernet_8xb2-amp-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mae/upernet_mae-base_fp16_8x2_512x512_160k_ade20k/upernet_mae-base_fp16_8x2_512x512_160k_ade20k_20220426_174752-f92a2975.pth
diff --git a/configs/mae/metafile.yaml b/configs/mae/metafile.yaml
new file mode 100644
index 0000000000..567eafe131
--- /dev/null
+++ b/configs/mae/metafile.yaml
@@ -0,0 +1,25 @@
+Models:
+- Name: mae-base_upernet_8xb2-amp-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 48.13
+      mIoU(ms+flip): 48.7
+  Config: configs/mae/mae-base_upernet_8xb2-amp-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - ViT-B
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 9.96
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mae/upernet_mae-base_fp16_8x2_512x512_160k_ade20k/upernet_mae-base_fp16_8x2_512x512_160k_ade20k_20220426_174752-f92a2975.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mae/upernet_mae-base_fp16_8x2_512x512_160k_ade20k/upernet_mae-base_fp16_8x2_512x512_160k_ade20k_20220426_174752.log.json
+  Paper:
+    Title: Masked Autoencoders Are Scalable Vision Learners
+    URL: https://arxiv.org/abs/2111.06377
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.24.0/mmseg/models/backbones/mae.py#L46
+  Framework: PyTorch
diff --git a/configs/mask2former/README.md b/configs/mask2former/README.md
index 1861fec3b1..02639bef58 100644
--- a/configs/mask2former/README.md
+++ b/configs/mask2former/README.md
@@ -1,6 +1,6 @@
 # Mask2Former
 
-[Masked-attention Mask Transformer for Universal Image Segmentation](https://arxiv.org/abs/2112.01527)
+> [Masked-attention Mask Transformer for Universal Image Segmentation](https://arxiv.org/abs/2112.01527)
 
 ## Introduction
 
@@ -16,21 +16,6 @@
 
 Image segmentation is about grouping pixels with different semantics, e.g., category or instance membership, where each choice of semantics defines a task. While only the semantics of each task differ, current research focuses on designing specialized architectures for each task. We present Masked-attention Mask Transformer (Mask2Former), a new architecture capable of addressing any image segmentation task (panoptic, instance or semantic). Its key components include masked attention, which extracts localized features by constraining cross-attention within predicted mask regions. In addition to reducing the research effort by at least three times, it outperforms the best specialized architectures by a significant margin on four popular datasets. Most notably, Mask2Former sets a new state-of-the-art for panoptic segmentation (57.8 PQ on COCO), instance segmentation (50.1 AP on COCO) and semantic segmentation (57.7 mIoU on ADE20K).
 
-```bibtex
-@inproceedings{cheng2021mask2former,
-  title={Masked-attention Mask Transformer for Universal Image Segmentation},
-  author={Bowen Cheng and Ishan Misra and Alexander G. Schwing and Alexander Kirillov and Rohit Girdhar},
-  journal={CVPR},
-  year={2022}
-}
-@inproceedings{cheng2021maskformer,
-  title={Per-Pixel Classification is Not All You Need for Semantic Segmentation},
-  author={Bowen Cheng and Alexander G. Schwing and Alexander Kirillov},
-  journal={NeurIPS},
-  year={2021}
-}
-```
-
 ### Usage
 
 - Mask2Former model needs to install [MMDetection](https://github.com/open-mmlab/mmdetection) first.
@@ -43,26 +28,26 @@ pip install "mmdet>=3.0.0rc4"
 
 ### Cityscapes
 
-| Method      | Backbone       | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) |                                                                                                                                                       config | download                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
-| ----------- | -------------- | --------- | ------- | -------: | -------------- | ----- | ------------: | -----------------------------------------------------------------------------------------------------------------------------------------------------------: | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Mask2Former | R-50-D32       | 512x1024  | 90000   |     5806 | 9.17           | 80.44 |             - |                      [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024/mask2former_r50_8xb2-90k_cityscapes-512x1024_20221202_140802-ffd9d750.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024/mask2former_r50_8xb2-90k_cityscapes-512x1024_20221202_140802.json)                                                                                      |
-| Mask2Former | R-101-D32      | 512x1024  | 90000   |     6971 | 7.11           | 80.80 |             - |                     [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024/mask2former_r101_8xb2-90k_cityscapes-512x1024_20221130_031628-43e68666.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024/mask2former_r101_8xb2-90k_cityscapes-512x1024_20221130_031628.json))                                                                                 |
-| Mask2Former | Swin-T         | 512x1024  | 90000   |     6511 | 7.18           | 81.71 |             - |                   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024/mask2former_swin-t_8xb2-90k_cityscapes-512x1024_20221127_144501-36c59341.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024/mask2former_swin-t_8xb2-90k_cityscapes-512x1024_20221127_144501.json))                                                                         |
-| Mask2Former | Swin-S         | 512x1024  | 90000   |     8282 | 5.57           | 82.57 |             - |                   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024/mask2former_swin-s_8xb2-90k_cityscapes-512x1024_20221127_143802-9ab177f6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024/mask2former_swin-s_8xb2-90k_cityscapes-512x1024_20221127_143802.json))                                                                         |
-| Mask2Former | Swin-B (in22k) | 512x1024  | 90000   |    11152 | 4.32           | 83.52 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221203_045030-9a86a225.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221203_045030.json)) |
-| Mask2Former | Swin-L (in22k) | 512x1024  | 90000   |    16207 | 2.86           | 83.65 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221202_141901-28ad20f1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221202_141901.json)) |
+| Method      | Backbone       | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) |                                                                                                                                                       config | download                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
+| ----------- | -------------- | --------- | ------- | -------: | -------------- | ------ | ----- | ------------: | -----------------------------------------------------------------------------------------------------------------------------------------------------------: | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Mask2Former | R-50-D32       | 512x1024  | 90000   |     5.67 | 9.17           | A100   | 80.44 |             - |                      [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024/mask2former_r50_8xb2-90k_cityscapes-512x1024_20221202_140802-ffd9d750.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024/mask2former_r50_8xb2-90k_cityscapes-512x1024_20221202_140802.json)                                                                                      |
+| Mask2Former | R-101-D32      | 512x1024  | 90000   |     6.81 | 7.11           | A100   | 80.80 |             - |                     [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024/mask2former_r101_8xb2-90k_cityscapes-512x1024_20221130_031628-43e68666.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024/mask2former_r101_8xb2-90k_cityscapes-512x1024_20221130_031628.json))                                                                                 |
+| Mask2Former | Swin-T         | 512x1024  | 90000   |     6.36 | 7.18           | A100   | 81.71 |             - |                   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024/mask2former_swin-t_8xb2-90k_cityscapes-512x1024_20221127_144501-36c59341.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024/mask2former_swin-t_8xb2-90k_cityscapes-512x1024_20221127_144501.json))                                                                         |
+| Mask2Former | Swin-S         | 512x1024  | 90000   |     8.09 | 5.57           | A100   | 82.57 |             - |                   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024/mask2former_swin-s_8xb2-90k_cityscapes-512x1024_20221127_143802-9ab177f6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024/mask2former_swin-s_8xb2-90k_cityscapes-512x1024_20221127_143802.json))                                                                         |
+| Mask2Former | Swin-B (in22k) | 512x1024  | 90000   |    10.89 | 4.32           | A100   | 83.52 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221203_045030-9a86a225.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221203_045030.json)) |
+| Mask2Former | Swin-L (in22k) | 512x1024  | 90000   |    15.83 | 2.86           | A100   | 83.65 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221202_141901-28ad20f1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221202_141901.json)) |
 
 ### ADE20K
 
-| Method      | Backbone       | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) |                                                                                                                                                   config | download                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
-| ----------- | -------------- | --------- | ------- | -------: | -------------- | ----- | ------------: | -------------------------------------------------------------------------------------------------------------------------------------------------------: | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Mask2Former | R-50-D32       | 512x512   | 160000  |     3385 | 26.59          | 47.87 |             - |                      [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512/mask2former_r50_8xb2-160k_ade20k-512x512_20221204_000055-2d1f55f1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512/mask2former_r50_8xb2-160k_ade20k-512x512_20221204_000055.json))                                                                                     |
-| Mask2Former | R-101-D32      | 512x512   | 160000  |     4190 | 22.97          | 48.60 |             - |                     [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512/mask2former_r101_8xb2-160k_ade20k-512x512_20221203_233905-b7135890.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512/mask2former_r101_8xb2-160k_ade20k-512x512_20221203_233905.json))                                                                                 |
-| Mask2Former | Swin-T         | 512x512   | 160000  |     3826 | 23.82          | 48.66 |             - |                   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512/mask2former_swin-t_8xb2-160k_ade20k-512x512_20221203_234230-7d64e5dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512/mask2former_swin-t_8xb2-160k_ade20k-512x512_20221203_234230.json))                                                                         |
-| Mask2Former | Swin-S         | 512x512   | 160000  |     5034 | 19.69          | 51.24 |             - |                   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512/mask2former_swin-s_8xb2-160k_ade20k-512x512_20221204_143905-e715144e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512/mask2former_swin-s_8xb2-160k_ade20k-512x512_20221204_143905.json))                                                                         |
-| Mask2Former | Swin-B         | 640x640   | 160000  |     5795 | 12.48          | 52.44 |             - |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640_20221129_125118-a4a086d2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640_20221129_125118.json))     |
-| Mask2Former | Swin-B (in22k) | 640x640   | 160000  |     5795 | 12.43          | 53.90 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235230-7ec0f569.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235230.json)) |
-| Mask2Former | Swin-L (in22k) | 640x640   | 160000  |     9077 | 8.81           | 56.01 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235933-7120c214.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235933.json)) |
+| Method      | Backbone       | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) |                                                                                                                                                   config | download                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
+| ----------- | -------------- | --------- | ------- | -------: | -------------- | ------ | ----- | ------------: | -------------------------------------------------------------------------------------------------------------------------------------------------------: | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Mask2Former | R-50-D32       | 512x512   | 160000  |     3.31 | 26.59          | A100   | 47.87 |             - |                      [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512/mask2former_r50_8xb2-160k_ade20k-512x512_20221204_000055-2d1f55f1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512/mask2former_r50_8xb2-160k_ade20k-512x512_20221204_000055.json))                                                                                     |
+| Mask2Former | R-101-D32      | 512x512   | 160000  |     4.09 | 22.97          | A100   | 48.60 |             - |                     [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512/mask2former_r101_8xb2-160k_ade20k-512x512_20221203_233905-b7135890.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512/mask2former_r101_8xb2-160k_ade20k-512x512_20221203_233905.json))                                                                                 |
+| Mask2Former | Swin-T         | 512x512   | 160000  |     3826 | 23.82          | A100   | 48.66 |             - |                   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512/mask2former_swin-t_8xb2-160k_ade20k-512x512_20221203_234230-7d64e5dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512/mask2former_swin-t_8xb2-160k_ade20k-512x512_20221203_234230.json))                                                                         |
+| Mask2Former | Swin-S         | 512x512   | 160000  |     3.74 | 19.69          | A100   | 51.24 |             - |                   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512/mask2former_swin-s_8xb2-160k_ade20k-512x512_20221204_143905-e715144e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512/mask2former_swin-s_8xb2-160k_ade20k-512x512_20221204_143905.json))                                                                         |
+| Mask2Former | Swin-B         | 640x640   | 160000  |     5.66 | 12.48          | A100   | 52.44 |             - |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640_20221129_125118-a4a086d2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640_20221129_125118.json))     |
+| Mask2Former | Swin-B (in22k) | 640x640   | 160000  |     5.66 | 12.43          | A100   | 53.90 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235230-7ec0f569.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235230.json)) |
+| Mask2Former | Swin-L (in22k) | 640x640   | 160000  |     8.86 | 8.81           | A100   | 56.01 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235933-7120c214.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235933.json)) |
 
 Note:
 
@@ -70,3 +55,20 @@ Note:
 - As mentioned at [the official repo](https://github.com/facebookresearch/Mask2Former/issues/5), the results of Mask2Former are relatively not stable, the result of Mask2Former(swin-s) on ADE20K dataset in the table is the medium result obtained by training 5 times following the suggestion of the author.
 - The ResNet backbones utilized in MaskFormer models are standard `ResNet` rather than `ResNetV1c`.
 - Test time augmentation is not supported in MMSegmentation 1.x version yet, we would add "ms+flip" results as soon as possible.
+
+## Citation
+
+```bibtex
+@inproceedings{cheng2021mask2former,
+  title={Masked-attention Mask Transformer for Universal Image Segmentation},
+  author={Bowen Cheng and Ishan Misra and Alexander G. Schwing and Alexander Kirillov and Rohit Girdhar},
+  journal={CVPR},
+  year={2022}
+}
+@inproceedings{cheng2021maskformer,
+  title={Per-Pixel Classification is Not All You Need for Semantic Segmentation},
+  author={Bowen Cheng and Alexander G. Schwing and Alexander Kirillov},
+  journal={NeurIPS},
+  year={2021}
+}
+```
diff --git a/configs/mask2former/mask2former.yml b/configs/mask2former/mask2former.yml
deleted file mode 100644
index 4e33766c70..0000000000
--- a/configs/mask2former/mask2former.yml
+++ /dev/null
@@ -1,290 +0,0 @@
-Collections:
-- Name: Mask2Former
-  Metadata:
-    Training Data:
-    - Usage
-    - Cityscapes
-    - ADE20K
-  Paper:
-    URL: https://arxiv.org/abs/2112.01527
-    Title: Masked-attention Mask Transformer for Universal Image Segmentation
-  README: configs/mask2former/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
-    Version: 3.x
-  Converted From:
-    Code: https://github.com/facebookresearch/Mask2Former
-Models:
-- Name: mask2former_r50_8xb2-90k_cityscapes-512x1024
-  In Collection: Mask2Former
-  Metadata:
-    backbone: R-50-D32
-    crop size: (512,1024)
-    lr schd: 90000
-    inference time (ms/im):
-    - value: 109.05
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 5806.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.44
-  Config: configs/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024/mask2former_r50_8xb2-90k_cityscapes-512x1024_20221202_140802-ffd9d750.pth
-- Name: mask2former_r101_8xb2-90k_cityscapes-512x1024
-  In Collection: Mask2Former
-  Metadata:
-    backbone: R-101-D32
-    crop size: (512,1024)
-    lr schd: 90000
-    inference time (ms/im):
-    - value: 140.65
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 6971.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.8
-  Config: configs/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024/mask2former_r101_8xb2-90k_cityscapes-512x1024_20221130_031628-43e68666.pth
-- Name: mask2former_swin-t_8xb2-90k_cityscapes-512x1024
-  In Collection: Mask2Former
-  Metadata:
-    backbone: Swin-T
-    crop size: (512,1024)
-    lr schd: 90000
-    inference time (ms/im):
-    - value: 139.28
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 6511.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 81.71
-  Config: configs/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024/mask2former_swin-t_8xb2-90k_cityscapes-512x1024_20221127_144501-36c59341.pth
-- Name: mask2former_swin-s_8xb2-90k_cityscapes-512x1024
-  In Collection: Mask2Former
-  Metadata:
-    backbone: Swin-S
-    crop size: (512,1024)
-    lr schd: 90000
-    inference time (ms/im):
-    - value: 179.53
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 8282.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 82.57
-  Config: configs/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024/mask2former_swin-s_8xb2-90k_cityscapes-512x1024_20221127_143802-9ab177f6.pth
-- Name: mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024
-  In Collection: Mask2Former
-  Metadata:
-    backbone: Swin-B (in22k)
-    crop size: (512,1024)
-    lr schd: 90000
-    inference time (ms/im):
-    - value: 231.48
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 11152.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 83.52
-  Config: configs/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221203_045030-9a86a225.pth
-- Name: mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024
-  In Collection: Mask2Former
-  Metadata:
-    backbone: Swin-L (in22k)
-    crop size: (512,1024)
-    lr schd: 90000
-    inference time (ms/im):
-    - value: 349.65
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 16207.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 83.65
-  Config: configs/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221202_141901-28ad20f1.pth
-- Name: mask2former_r50_8xb2-160k_ade20k-512x512
-  In Collection: Mask2Former
-  Metadata:
-    backbone: R-50-D32
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 37.61
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 3385.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 47.87
-  Config: configs/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512/mask2former_r50_8xb2-160k_ade20k-512x512_20221204_000055-2d1f55f1.pth
-- Name: mask2former_r101_8xb2-160k_ade20k-512x512
-  In Collection: Mask2Former
-  Metadata:
-    backbone: R-101-D32
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 43.54
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 4190.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 48.6
-  Config: configs/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512/mask2former_r101_8xb2-160k_ade20k-512x512_20221203_233905-b7135890.pth
-- Name: mask2former_swin-t_8xb2-160k_ade20k-512x512
-  In Collection: Mask2Former
-  Metadata:
-    backbone: Swin-T
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 41.98
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 3826.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 48.66
-  Config: configs/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512/mask2former_swin-t_8xb2-160k_ade20k-512x512_20221203_234230-7d64e5dd.pth
-- Name: mask2former_swin-s_8xb2-160k_ade20k-512x512
-  In Collection: Mask2Former
-  Metadata:
-    backbone: Swin-S
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 50.79
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 5034.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 51.24
-  Config: configs/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512/mask2former_swin-s_8xb2-160k_ade20k-512x512_20221204_143905-e715144e.pth
-- Name: mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640
-  In Collection: Mask2Former
-  Metadata:
-    backbone: Swin-B
-    crop size: (640,640)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 80.13
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (640,640)
-    Training Memory (GB): 5795.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 52.44
-  Config: configs/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640_20221129_125118-a4a086d2.pth
-- Name: mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640
-  In Collection: Mask2Former
-  Metadata:
-    backbone: Swin-B (in22k)
-    crop size: (640,640)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 80.45
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (640,640)
-    Training Memory (GB): 5795.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 53.9
-  Config: configs/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235230-7ec0f569.pth
-- Name: mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640
-  In Collection: Mask2Former
-  Metadata:
-    backbone: Swin-L (in22k)
-    crop size: (640,640)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 113.51
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (640,640)
-    Training Memory (GB): 9077.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 56.01
-  Config: configs/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235933-7120c214.pth
diff --git a/configs/mask2former/metafile.yaml b/configs/mask2former/metafile.yaml
new file mode 100644
index 0000000000..090c95e7cf
--- /dev/null
+++ b/configs/mask2former/metafile.yaml
@@ -0,0 +1,314 @@
+Collections:
+- Name: Mask2Former
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Usage
+    - Cityscapes
+    - ADE20K
+  Paper:
+    Title: Masked-attention Mask Transformer for Universal Image Segmentation
+    URL: https://arxiv.org/abs/2112.01527
+  README: configs/mask2former/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: mask2former_r50_8xb2-90k_cityscapes-512x1024
+  In Collection: Mask2Former
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.44
+  Config: configs/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - R-50-D32
+    - Mask2Former
+    Training Resources: 8x A100 GPUS
+    Memory (GB): 5.67
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024/mask2former_r50_8xb2-90k_cityscapes-512x1024_20221202_140802-ffd9d750.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024/mask2former_r50_8xb2-90k_cityscapes-512x1024_20221202_140802.json
+  Paper:
+    Title: Masked-attention Mask Transformer for Universal Image Segmentation
+    URL: https://arxiv.org/abs/2112.01527
+  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
+  Framework: PyTorch
+- Name: mask2former_r101_8xb2-90k_cityscapes-512x1024
+  In Collection: Mask2Former
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.8
+  Config: configs/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - R-101-D32
+    - Mask2Former
+    Training Resources: 8x A100 GPUS
+    Memory (GB): 6.81
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024/mask2former_r101_8xb2-90k_cityscapes-512x1024_20221130_031628-43e68666.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024/mask2former_r101_8xb2-90k_cityscapes-512x1024_20221130_031628.json
+  Paper:
+    Title: Masked-attention Mask Transformer for Universal Image Segmentation
+    URL: https://arxiv.org/abs/2112.01527
+  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
+  Framework: PyTorch
+- Name: mask2former_swin-t_8xb2-90k_cityscapes-512x1024
+  In Collection: Mask2Former
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 81.71
+  Config: configs/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - Swin-T
+    - Mask2Former
+    Training Resources: 8x A100 GPUS
+    Memory (GB): 6.36
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024/mask2former_swin-t_8xb2-90k_cityscapes-512x1024_20221127_144501-36c59341.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024/mask2former_swin-t_8xb2-90k_cityscapes-512x1024_20221127_144501.json
+  Paper:
+    Title: Masked-attention Mask Transformer for Universal Image Segmentation
+    URL: https://arxiv.org/abs/2112.01527
+  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
+  Framework: PyTorch
+- Name: mask2former_swin-s_8xb2-90k_cityscapes-512x1024
+  In Collection: Mask2Former
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 82.57
+  Config: configs/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - Swin-S
+    - Mask2Former
+    Training Resources: 8x A100 GPUS
+    Memory (GB): 8.09
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024/mask2former_swin-s_8xb2-90k_cityscapes-512x1024_20221127_143802-9ab177f6.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024/mask2former_swin-s_8xb2-90k_cityscapes-512x1024_20221127_143802.json
+  Paper:
+    Title: Masked-attention Mask Transformer for Universal Image Segmentation
+    URL: https://arxiv.org/abs/2112.01527
+  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
+  Framework: PyTorch
+- Name: mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024
+  In Collection: Mask2Former
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 83.52
+  Config: configs/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - Swin-B
+    - Mask2Former
+    Training Resources: 8x A100 GPUS
+    Memory (GB): 10.89
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221203_045030-9a86a225.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221203_045030.json
+  Paper:
+    Title: Masked-attention Mask Transformer for Universal Image Segmentation
+    URL: https://arxiv.org/abs/2112.01527
+  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
+  Framework: PyTorch
+- Name: mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024
+  In Collection: Mask2Former
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 83.65
+  Config: configs/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - Swin-L
+    - Mask2Former
+    Training Resources: 8x A100 GPUS
+    Memory (GB): 15.83
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221202_141901-28ad20f1.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221202_141901.json
+  Paper:
+    Title: Masked-attention Mask Transformer for Universal Image Segmentation
+    URL: https://arxiv.org/abs/2112.01527
+  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
+  Framework: PyTorch
+- Name: mask2former_r50_8xb2-160k_ade20k-512x512
+  In Collection: Mask2Former
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 47.87
+  Config: configs/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D32
+    - Mask2Former
+    Training Resources: 8x A100 GPUS
+    Memory (GB): 3.31
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512/mask2former_r50_8xb2-160k_ade20k-512x512_20221204_000055-2d1f55f1.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512/mask2former_r50_8xb2-160k_ade20k-512x512_20221204_000055.json
+  Paper:
+    Title: Masked-attention Mask Transformer for Universal Image Segmentation
+    URL: https://arxiv.org/abs/2112.01527
+  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
+  Framework: PyTorch
+- Name: mask2former_r101_8xb2-160k_ade20k-512x512
+  In Collection: Mask2Former
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 48.6
+  Config: configs/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D32
+    - Mask2Former
+    Training Resources: 8x A100 GPUS
+    Memory (GB): 4.09
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512/mask2former_r101_8xb2-160k_ade20k-512x512_20221203_233905-b7135890.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512/mask2former_r101_8xb2-160k_ade20k-512x512_20221203_233905.json
+  Paper:
+    Title: Masked-attention Mask Transformer for Universal Image Segmentation
+    URL: https://arxiv.org/abs/2112.01527
+  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
+  Framework: PyTorch
+- Name: mask2former_swin-t_8xb2-160k_ade20k-512x512
+  In Collection: Mask2Former
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 48.66
+  Config: configs/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Swin-T
+    - Mask2Former
+    Training Resources: 8x A100 GPUS
+    Memory (GB): 3826.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512/mask2former_swin-t_8xb2-160k_ade20k-512x512_20221203_234230-7d64e5dd.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512/mask2former_swin-t_8xb2-160k_ade20k-512x512_20221203_234230.json
+  Paper:
+    Title: Masked-attention Mask Transformer for Universal Image Segmentation
+    URL: https://arxiv.org/abs/2112.01527
+  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
+  Framework: PyTorch
+- Name: mask2former_swin-s_8xb2-160k_ade20k-512x512
+  In Collection: Mask2Former
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 51.24
+  Config: configs/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Swin-S
+    - Mask2Former
+    Training Resources: 8x A100 GPUS
+    Memory (GB): 3.74
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512/mask2former_swin-s_8xb2-160k_ade20k-512x512_20221204_143905-e715144e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512/mask2former_swin-s_8xb2-160k_ade20k-512x512_20221204_143905.json
+  Paper:
+    Title: Masked-attention Mask Transformer for Universal Image Segmentation
+    URL: https://arxiv.org/abs/2112.01527
+  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
+  Framework: PyTorch
+- Name: mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640
+  In Collection: Mask2Former
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 52.44
+  Config: configs/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Swin-B
+    - Mask2Former
+    Training Resources: 8x A100 GPUS
+    Memory (GB): 5.66
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640_20221129_125118-a4a086d2.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640_20221129_125118.json
+  Paper:
+    Title: Masked-attention Mask Transformer for Universal Image Segmentation
+    URL: https://arxiv.org/abs/2112.01527
+  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
+  Framework: PyTorch
+- Name: mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640
+  In Collection: Mask2Former
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 53.9
+  Config: configs/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Swin-B
+    - Mask2Former
+    Training Resources: 8x A100 GPUS
+    Memory (GB): 5.66
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235230-7ec0f569.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235230.json
+  Paper:
+    Title: Masked-attention Mask Transformer for Universal Image Segmentation
+    URL: https://arxiv.org/abs/2112.01527
+  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
+  Framework: PyTorch
+- Name: mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640
+  In Collection: Mask2Former
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 56.01
+  Config: configs/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Swin-L
+    - Mask2Former
+    Training Resources: 8x A100 GPUS
+    Memory (GB): 8.86
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235933-7120c214.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235933.json
+  Paper:
+    Title: Masked-attention Mask Transformer for Universal Image Segmentation
+    URL: https://arxiv.org/abs/2112.01527
+  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
+  Framework: PyTorch
diff --git a/configs/maskformer/README.md b/configs/maskformer/README.md
index 0248dbb63c..aa54a27088 100644
--- a/configs/maskformer/README.md
+++ b/configs/maskformer/README.md
@@ -1,6 +1,6 @@
 # MaskFormer
 
-[MaskFormer: Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://arxiv.org/abs/2107.06278)
+> [MaskFormer: Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://arxiv.org/abs/2107.06278)
 
 ## Introduction
 
@@ -22,17 +22,6 @@ Modern approaches typically formulate semantic segmentation as a per-pixel class
 <img src="https://user-images.githubusercontent.com/24582831/199215459-ea507126-aafe-4823-8eb1-ae6487509d5c.png" width="90%"/>
 </div>
 
-```bibtex
-@article{cheng2021per,
-  title={Per-pixel classification is not all you need for semantic segmentation},
-  author={Cheng, Bowen and Schwing, Alex and Kirillov, Alexander},
-  journal={Advances in Neural Information Processing Systems},
-  volume={34},
-  pages={17864--17875},
-  year={2021}
-}
-```
-
 ### Usage
 
 - MaskFormer model needs to install [MMDetection](https://github.com/open-mmlab/mmdetection) first.
@@ -45,12 +34,12 @@ pip install "mmdet>=3.0.0rc4"
 
 ### ADE20K
 
-| Method     | Backbone  | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) | config                                                                                                                                       | download                                                                                                                                                                                                                                                                                                                                                                                                     |
-| ---------- | --------- | --------- | ------- | -------- | -------------- | ----- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| MaskFormer | R-50-D32  | 512x512   | 160000  | 3.29     | 42.20          | 44.29 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512/maskformer_r50-d32_8xb2-160k_ade20k-512x512_20221030_182724-3a9cfe45.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512/maskformer_r50-d32_8xb2-160k_ade20k-512x512_20221030_182724.json)                             |
-| MaskFormer | R-101-D32 | 512x512   | 160000  | 4.12     | 34.90          | 45.11 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512/maskformer_r101-d32_8xb2-160k_ade20k-512x512_20221031_223053-84adbfcb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512/maskformer_r101-d32_8xb2-160k_ade20k-512x512_20221031_223053.json)                         |
-| MaskFormer | Swin-T    | 512x512   | 160000  | 3.73     | 40.53          | 46.69 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512_20221114_232813-f14e7ce0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512_20221114_232813.json) |
-| MaskFormer | Swin-S    | 512x512   | 160000  | 5.33     | 26.98          | 49.36 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512_20221115_114710-723512c7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512_20221115_114710.json) |
+| Method     | Backbone  | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                                       | download                                                                                                                                                                                                                                                                                                                                                                                                     |
+| ---------- | --------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| MaskFormer | R-50-D32  | 512x512   | 160000  | 3.29     | A100           | 42.20  | 44.29 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512/maskformer_r50-d32_8xb2-160k_ade20k-512x512_20221030_182724-3a9cfe45.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512/maskformer_r50-d32_8xb2-160k_ade20k-512x512_20221030_182724.json)                             |
+| MaskFormer | R-101-D32 | 512x512   | 160000  | 4.12     | A100           | 34.90  | 45.11 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512/maskformer_r101-d32_8xb2-160k_ade20k-512x512_20221031_223053-84adbfcb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512/maskformer_r101-d32_8xb2-160k_ade20k-512x512_20221031_223053.json)                         |
+| MaskFormer | Swin-T    | 512x512   | 160000  | 3.73     | A100           | 40.53  | 46.69 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512_20221114_232813-f14e7ce0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512_20221114_232813.json) |
+| MaskFormer | Swin-S    | 512x512   | 160000  | 5.33     | A100           | 26.98  | 49.36 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512_20221115_114710-723512c7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512_20221115_114710.json) |
 
 Note:
 
@@ -58,3 +47,16 @@ Note:
 - The results of MaskFormer are relatively not stable.  The accuracy (mIoU) of model with `R-101-D32` is from 44.7 to 46.0, and with `Swin-S` is from 49.0 to 49.8.
 - The ResNet backbones utilized in MaskFormer models are standard `ResNet` rather than `ResNetV1c`.
 - Test time augmentation is not supported in MMSegmentation 1.x version yet, we would add "ms+flip" results as soon as possible.
+
+## Citation
+
+```bibtex
+@article{cheng2021per,
+  title={Per-pixel classification is not all you need for semantic segmentation},
+  author={Cheng, Bowen and Schwing, Alex and Kirillov, Alexander},
+  journal={Advances in Neural Information Processing Systems},
+  volume={34},
+  pages={17864--17875},
+  year={2021}
+}
+```
diff --git a/configs/maskformer/maskformer.yml b/configs/maskformer/maskformer.yml
deleted file mode 100644
index b499476a50..0000000000
--- a/configs/maskformer/maskformer.yml
+++ /dev/null
@@ -1,101 +0,0 @@
-Collections:
-- Name: MaskFormer
-  Metadata:
-    Training Data:
-    - Usage
-    - ADE20K
-  Paper:
-    URL: https://arxiv.org/abs/2107.06278
-    Title: 'MaskFormer: Per-Pixel Classification is Not All You Need for Semantic
-      Segmentation'
-  README: configs/maskformer/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmdetection/blob/dev-3.x/mmdet/models/dense_heads/maskformer_head.py#L21
-    Version: dev-3.x
-  Converted From:
-    Code: https://github.com/facebookresearch/MaskFormer/
-Models:
-- Name: maskformer_r50-d32_8xb2-160k_ade20k-512x512
-  In Collection: MaskFormer
-  Metadata:
-    backbone: R-50-D32
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 23.7
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 3.29
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 44.29
-  Config: configs/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512/maskformer_r50-d32_8xb2-160k_ade20k-512x512_20221030_182724-3a9cfe45.pth
-- Name: maskformer_r101-d32_8xb2-160k_ade20k-512x512
-  In Collection: MaskFormer
-  Metadata:
-    backbone: R-101-D32
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 28.65
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 4.12
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.11
-  Config: configs/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512/maskformer_r101-d32_8xb2-160k_ade20k-512x512_20221031_223053-84adbfcb.pth
-- Name: maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512
-  In Collection: MaskFormer
-  Metadata:
-    backbone: Swin-T
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 24.67
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 3.73
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 46.69
-  Config: configs/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512_20221114_232813-f14e7ce0.pth
-- Name: maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512
-  In Collection: MaskFormer
-  Metadata:
-    backbone: Swin-S
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 37.06
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 5.33
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 49.36
-  Config: configs/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512_20221115_114710-723512c7.pth
diff --git a/configs/maskformer/metafile.yaml b/configs/maskformer/metafile.yaml
new file mode 100644
index 0000000000..c9853e131f
--- /dev/null
+++ b/configs/maskformer/metafile.yaml
@@ -0,0 +1,111 @@
+Collections:
+- Name: MaskFormer
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Usage
+    - ADE20K
+  Paper:
+    Title: 'MaskFormer: Per-Pixel Classification is Not All You Need for Semantic
+      Segmentation'
+    URL: https://arxiv.org/abs/2107.06278
+  README: configs/maskformer/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: maskformer_r50-d32_8xb2-160k_ade20k-512x512
+  In Collection: MaskFormer
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 44.29
+  Config: configs/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D32
+    - MaskFormer
+    Training Resources: 8x 42.20 GPUS
+    Memory (GB): 3.29
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512/maskformer_r50-d32_8xb2-160k_ade20k-512x512_20221030_182724-3a9cfe45.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512/maskformer_r50-d32_8xb2-160k_ade20k-512x512_20221030_182724.json
+  Paper:
+    Title: 'MaskFormer: Per-Pixel Classification is Not All You Need for Semantic
+      Segmentation'
+    URL: https://arxiv.org/abs/2107.06278
+  Code: https://github.com/open-mmlab/mmdetection/blob/dev-3.x/mmdet/models/dense_heads/maskformer_head.py#L21
+  Framework: PyTorch
+- Name: maskformer_r101-d32_8xb2-160k_ade20k-512x512
+  In Collection: MaskFormer
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.11
+  Config: configs/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D32
+    - MaskFormer
+    Training Resources: 8x 34.90 GPUS
+    Memory (GB): 4.12
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512/maskformer_r101-d32_8xb2-160k_ade20k-512x512_20221031_223053-84adbfcb.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512/maskformer_r101-d32_8xb2-160k_ade20k-512x512_20221031_223053.json
+  Paper:
+    Title: 'MaskFormer: Per-Pixel Classification is Not All You Need for Semantic
+      Segmentation'
+    URL: https://arxiv.org/abs/2107.06278
+  Code: https://github.com/open-mmlab/mmdetection/blob/dev-3.x/mmdet/models/dense_heads/maskformer_head.py#L21
+  Framework: PyTorch
+- Name: maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512
+  In Collection: MaskFormer
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 46.69
+  Config: configs/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Swin-T
+    - MaskFormer
+    Training Resources: 8x 40.53 GPUS
+    Memory (GB): 3.73
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512_20221114_232813-f14e7ce0.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512_20221114_232813.json
+  Paper:
+    Title: 'MaskFormer: Per-Pixel Classification is Not All You Need for Semantic
+      Segmentation'
+    URL: https://arxiv.org/abs/2107.06278
+  Code: https://github.com/open-mmlab/mmdetection/blob/dev-3.x/mmdet/models/dense_heads/maskformer_head.py#L21
+  Framework: PyTorch
+- Name: maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512
+  In Collection: MaskFormer
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 49.36
+  Config: configs/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Swin-S
+    - MaskFormer
+    Training Resources: 8x 26.98 GPUS
+    Memory (GB): 5.33
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512_20221115_114710-723512c7.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512_20221115_114710.json
+  Paper:
+    Title: 'MaskFormer: Per-Pixel Classification is Not All You Need for Semantic
+      Segmentation'
+    URL: https://arxiv.org/abs/2107.06278
+  Code: https://github.com/open-mmlab/mmdetection/blob/dev-3.x/mmdet/models/dense_heads/maskformer_head.py#L21
+  Framework: PyTorch
diff --git a/configs/mobilenet_v2/README.md b/configs/mobilenet_v2/README.md
index 30f1fe3ce2..6d8e5945cb 100644
--- a/configs/mobilenet_v2/README.md
+++ b/configs/mobilenet_v2/README.md
@@ -1,6 +1,6 @@
 # MobileNetV2
 
-[MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://arxiv.org/abs/1801.04381)
+> [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://arxiv.org/abs/1801.04381)
 
 ## Introduction
 
@@ -23,6 +23,26 @@ The MobileNetV2 architecture is based on an inverted residual structure where th
 <img src="https://user-images.githubusercontent.com/24582831/142901935-fa22700e-4b77-477f-90b9-334a4197506f.png" width="50%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                                                                 |
+| ---------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN        | M-V2-D8  | 512x1024  |   80000 |      3.4 | 14.2           | A100   | 71.19 | 73.34         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024-20230224_185436-13fef4ea.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024_20230224_185436.json) |
+| PSPNet     | M-V2-D8  | 512x1024  |   80000 |      3.6 | 11.2           | V100   | 70.23 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_pspnet_4xb2-80k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x1024_80k_cityscapes/pspnet_m-v2-d8_512x1024_80k_cityscapes_20200825_124817-19e81d51.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x1024_80k_cityscapes/pspnet_m-v2-d8_512x1024_80k_cityscapes-20200825_124817.log.json)                                     |
+| DeepLabV3  | M-V2-D8  | 512x1024  |   80000 |      3.9 | 8.4            | V100   | 73.84 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3_4xb2-80k_cityscapes-512x1024.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x1024_80k_cityscapes/deeplabv3_m-v2-d8_512x1024_80k_cityscapes_20200825_124836-bef03590.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x1024_80k_cityscapes/deeplabv3_m-v2-d8_512x1024_80k_cityscapes-20200825_124836.log.json)                         |
+| DeepLabV3+ | M-V2-D8  | 512x1024  |   80000 |      5.1 | 8.4            | V100   | 75.20 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3plus_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes_20200825_124836-d256dd4b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes-20200825_124836.log.json)         |
+
+### ADE20K
+
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                             | download                                                                                                                                                                                                                                                                                                                                                                         |
+| ---------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN        | M-V2-D8  | 512x512   |  160000 |      6.5 | 64.4           | V100   | 19.71 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_fcn_4xb4-160k_ade20k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/fcn_m-v2-d8_512x512_160k_ade20k/fcn_m-v2-d8_512x512_160k_ade20k_20200825_214953-c40e1095.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/fcn_m-v2-d8_512x512_160k_ade20k/fcn_m-v2-d8_512x512_160k_ade20k-20200825_214953.log.json)                                         |
+| PSPNet     | M-V2-D8  | 512x512   |  160000 |      6.5 | 57.7           | V100   | 29.68 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_pspnet_4xb4-160k_ade20k-512x512.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x512_160k_ade20k/pspnet_m-v2-d8_512x512_160k_ade20k_20200825_214953-f5942f7a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x512_160k_ade20k/pspnet_m-v2-d8_512x512_160k_ade20k-20200825_214953.log.json)                             |
+| DeepLabV3  | M-V2-D8  | 512x512   |  160000 |      6.8 | 39.9           | V100   | 34.08 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3_4xb4-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x512_160k_ade20k/deeplabv3_m-v2-d8_512x512_160k_ade20k_20200825_223255-63986343.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x512_160k_ade20k/deeplabv3_m-v2-d8_512x512_160k_ade20k-20200825_223255.log.json)                 |
+| DeepLabV3+ | M-V2-D8  | 512x512   |  160000 |      8.2 | 43.1           | V100   | 34.02 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3plus_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x512_160k_ade20k/deeplabv3plus_m-v2-d8_512x512_160k_ade20k_20200825_223255-465a01d4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x512_160k_ade20k/deeplabv3plus_m-v2-d8_512x512_160k_ade20k-20200825_223255.log.json) |
+
 ## Citation
 
 ```bibtex
@@ -34,23 +54,3 @@ The MobileNetV2 architecture is based on an inverted residual structure where th
   year={2018}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                                                                 |
-| ---------- | -------- | --------- | ------: | -------: | -------------- | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN        | M-V2-D8  | 512x1024  |   80000 |      3.4 | 14.2           | 71.19 | 73.34         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024-20230224_185436-13fef4ea.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024_20230224_185436.json) |
-| PSPNet     | M-V2-D8  | 512x1024  |   80000 |      3.6 | 11.2           | 70.23 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_pspnet_4xb2-80k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x1024_80k_cityscapes/pspnet_m-v2-d8_512x1024_80k_cityscapes_20200825_124817-19e81d51.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x1024_80k_cityscapes/pspnet_m-v2-d8_512x1024_80k_cityscapes-20200825_124817.log.json)                                     |
-| DeepLabV3  | M-V2-D8  | 512x1024  |   80000 |      3.9 | 8.4            | 73.84 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3_4xb2-80k_cityscapes-512x1024.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x1024_80k_cityscapes/deeplabv3_m-v2-d8_512x1024_80k_cityscapes_20200825_124836-bef03590.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x1024_80k_cityscapes/deeplabv3_m-v2-d8_512x1024_80k_cityscapes-20200825_124836.log.json)                         |
-| DeepLabV3+ | M-V2-D8  | 512x1024  |   80000 |      5.1 | 8.4            | 75.20 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3plus_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes_20200825_124836-d256dd4b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes-20200825_124836.log.json)         |
-
-### ADE20K
-
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                             | download                                                                                                                                                                                                                                                                                                                                                                         |
-| ---------- | -------- | --------- | ------: | -------: | -------------- | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN        | M-V2-D8  | 512x512   |  160000 |      6.5 | 64.4           | 19.71 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_fcn_4xb4-160k_ade20k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/fcn_m-v2-d8_512x512_160k_ade20k/fcn_m-v2-d8_512x512_160k_ade20k_20200825_214953-c40e1095.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/fcn_m-v2-d8_512x512_160k_ade20k/fcn_m-v2-d8_512x512_160k_ade20k-20200825_214953.log.json)                                         |
-| PSPNet     | M-V2-D8  | 512x512   |  160000 |      6.5 | 57.7           | 29.68 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_pspnet_4xb4-160k_ade20k-512x512.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x512_160k_ade20k/pspnet_m-v2-d8_512x512_160k_ade20k_20200825_214953-f5942f7a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x512_160k_ade20k/pspnet_m-v2-d8_512x512_160k_ade20k-20200825_214953.log.json)                             |
-| DeepLabV3  | M-V2-D8  | 512x512   |  160000 |      6.8 | 39.9           | 34.08 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3_4xb4-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x512_160k_ade20k/deeplabv3_m-v2-d8_512x512_160k_ade20k_20200825_223255-63986343.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x512_160k_ade20k/deeplabv3_m-v2-d8_512x512_160k_ade20k-20200825_223255.log.json)                 |
-| DeepLabV3+ | M-V2-D8  | 512x512   |  160000 |      8.2 | 43.1           | 34.02 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3plus_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x512_160k_ade20k/deeplabv3plus_m-v2-d8_512x512_160k_ade20k_20200825_223255-465a01d4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x512_160k_ade20k/deeplabv3plus_m-v2-d8_512x512_160k_ade20k-20200825_223255.log.json) |
diff --git a/configs/mobilenet_v2/metafile.yaml b/configs/mobilenet_v2/metafile.yaml
new file mode 100644
index 0000000000..119c9ae7d6
--- /dev/null
+++ b/configs/mobilenet_v2/metafile.yaml
@@ -0,0 +1,186 @@
+Models:
+- Name: mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 71.19
+      mIoU(ms+flip): 73.34
+  Config: configs/mobilenet_v2/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - M-V2-D8
+    - FCN
+    Training Resources: 4x A100 GPUS
+    Memory (GB): 3.4
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024-20230224_185436-13fef4ea.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024_20230224_185436.json
+  Paper:
+    Title: 'MobileNetV2: Inverted Residuals and Linear Bottlenecks'
+    URL: https://arxiv.org/abs/1801.04381
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mobilenet_v2.py#L14
+  Framework: PyTorch
+- Name: mobilenet-v2-d8_pspnet_4xb2-80k_cityscapes-512x1024
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 70.23
+  Config: configs/mobilenet_v2/mobilenet-v2-d8_pspnet_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - M-V2-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 3.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x1024_80k_cityscapes/pspnet_m-v2-d8_512x1024_80k_cityscapes_20200825_124817-19e81d51.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x1024_80k_cityscapes/pspnet_m-v2-d8_512x1024_80k_cityscapes-20200825_124817.log.json
+  Paper:
+    Title: 'MobileNetV2: Inverted Residuals and Linear Bottlenecks'
+    URL: https://arxiv.org/abs/1801.04381
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mobilenet_v2.py#L14
+  Framework: PyTorch
+- Name: mobilenet-v2-d8_deeplabv3_4xb2-80k_cityscapes-512x1024
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 73.84
+  Config: configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - M-V2-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 3.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x1024_80k_cityscapes/deeplabv3_m-v2-d8_512x1024_80k_cityscapes_20200825_124836-bef03590.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x1024_80k_cityscapes/deeplabv3_m-v2-d8_512x1024_80k_cityscapes-20200825_124836.log.json
+  Paper:
+    Title: 'MobileNetV2: Inverted Residuals and Linear Bottlenecks'
+    URL: https://arxiv.org/abs/1801.04381
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mobilenet_v2.py#L14
+  Framework: PyTorch
+- Name: mobilenet-v2-d8_deeplabv3plus_4xb2-80k_cityscapes-512x1024
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 75.2
+  Config: configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3plus_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - M-V2-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes_20200825_124836-d256dd4b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes-20200825_124836.log.json
+  Paper:
+    Title: 'MobileNetV2: Inverted Residuals and Linear Bottlenecks'
+    URL: https://arxiv.org/abs/1801.04381
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mobilenet_v2.py#L14
+  Framework: PyTorch
+- Name: mobilenet-v2-d8_fcn_4xb4-160k_ade20k-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 19.71
+  Config: configs/mobilenet_v2/mobilenet-v2-d8_fcn_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - M-V2-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/fcn_m-v2-d8_512x512_160k_ade20k/fcn_m-v2-d8_512x512_160k_ade20k_20200825_214953-c40e1095.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/fcn_m-v2-d8_512x512_160k_ade20k/fcn_m-v2-d8_512x512_160k_ade20k-20200825_214953.log.json
+  Paper:
+    Title: 'MobileNetV2: Inverted Residuals and Linear Bottlenecks'
+    URL: https://arxiv.org/abs/1801.04381
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mobilenet_v2.py#L14
+  Framework: PyTorch
+- Name: mobilenet-v2-d8_pspnet_4xb4-160k_ade20k-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 29.68
+  Config: configs/mobilenet_v2/mobilenet-v2-d8_pspnet_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - M-V2-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x512_160k_ade20k/pspnet_m-v2-d8_512x512_160k_ade20k_20200825_214953-f5942f7a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x512_160k_ade20k/pspnet_m-v2-d8_512x512_160k_ade20k-20200825_214953.log.json
+  Paper:
+    Title: 'MobileNetV2: Inverted Residuals and Linear Bottlenecks'
+    URL: https://arxiv.org/abs/1801.04381
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mobilenet_v2.py#L14
+  Framework: PyTorch
+- Name: mobilenet-v2-d8_deeplabv3_4xb4-160k_ade20k-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 34.08
+  Config: configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - M-V2-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x512_160k_ade20k/deeplabv3_m-v2-d8_512x512_160k_ade20k_20200825_223255-63986343.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x512_160k_ade20k/deeplabv3_m-v2-d8_512x512_160k_ade20k-20200825_223255.log.json
+  Paper:
+    Title: 'MobileNetV2: Inverted Residuals and Linear Bottlenecks'
+    URL: https://arxiv.org/abs/1801.04381
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mobilenet_v2.py#L14
+  Framework: PyTorch
+- Name: mobilenet-v2-d8_deeplabv3plus_4xb4-160k_ade20k-512x512
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 34.02
+  Config: configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3plus_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - M-V2-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x512_160k_ade20k/deeplabv3plus_m-v2-d8_512x512_160k_ade20k_20200825_223255-465a01d4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x512_160k_ade20k/deeplabv3plus_m-v2-d8_512x512_160k_ade20k-20200825_223255.log.json
+  Paper:
+    Title: 'MobileNetV2: Inverted Residuals and Linear Bottlenecks'
+    URL: https://arxiv.org/abs/1801.04381
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mobilenet_v2.py#L14
+  Framework: PyTorch
diff --git a/configs/mobilenet_v2/mobilenet_v2.yml b/configs/mobilenet_v2/mobilenet_v2.yml
deleted file mode 100644
index 6d87401ce8..0000000000
--- a/configs/mobilenet_v2/mobilenet_v2.yml
+++ /dev/null
@@ -1,170 +0,0 @@
-Models:
-- Name: mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: M-V2-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 70.42
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 3.4
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 71.19
-      mIoU(ms+flip): 73.34
-  Config: configs/mobilenet_v2/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024-20230224_185436-13fef4ea.pth
-- Name: mobilenet-v2-d8_pspnet_4xb2-80k_cityscapes-512x1024
-  In Collection: PSPNet
-  Metadata:
-    backbone: M-V2-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 89.29
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 3.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 70.23
-  Config: configs/mobilenet_v2/mobilenet-v2-d8_pspnet_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x1024_80k_cityscapes/pspnet_m-v2-d8_512x1024_80k_cityscapes_20200825_124817-19e81d51.pth
-- Name: mobilenet-v2-d8_deeplabv3_4xb2-80k_cityscapes-512x1024
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: M-V2-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 119.05
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 3.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 73.84
-  Config: configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x1024_80k_cityscapes/deeplabv3_m-v2-d8_512x1024_80k_cityscapes_20200825_124836-bef03590.pth
-- Name: mobilenet-v2-d8_deeplabv3plus_4xb2-80k_cityscapes-512x1024
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: M-V2-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 119.05
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 5.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 75.2
-  Config: configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3plus_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes_20200825_124836-d256dd4b.pth
-- Name: mobilenet-v2-d8_fcn_4xb4-160k_ade20k-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: M-V2-D8
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 15.53
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 19.71
-  Config: configs/mobilenet_v2/mobilenet-v2-d8_fcn_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/fcn_m-v2-d8_512x512_160k_ade20k/fcn_m-v2-d8_512x512_160k_ade20k_20200825_214953-c40e1095.pth
-- Name: mobilenet-v2-d8_pspnet_4xb4-160k_ade20k-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: M-V2-D8
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 17.33
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 29.68
-  Config: configs/mobilenet_v2/mobilenet-v2-d8_pspnet_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x512_160k_ade20k/pspnet_m-v2-d8_512x512_160k_ade20k_20200825_214953-f5942f7a.pth
-- Name: mobilenet-v2-d8_deeplabv3_4xb4-160k_ade20k-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: M-V2-D8
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 25.06
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 34.08
-  Config: configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x512_160k_ade20k/deeplabv3_m-v2-d8_512x512_160k_ade20k_20200825_223255-63986343.pth
-- Name: mobilenet-v2-d8_deeplabv3plus_4xb4-160k_ade20k-512x512
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: M-V2-D8
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 23.2
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 8.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 34.02
-  Config: configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3plus_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x512_160k_ade20k/deeplabv3plus_m-v2-d8_512x512_160k_ade20k_20200825_223255-465a01d4.pth
diff --git a/configs/mobilenet_v3/README.md b/configs/mobilenet_v3/README.md
index c2fed06ccd..3b63db7e50 100644
--- a/configs/mobilenet_v3/README.md
+++ b/configs/mobilenet_v3/README.md
@@ -1,6 +1,6 @@
 # MobileNetV3
 
-[Searching for MobileNetV3](https://arxiv.org/abs/1905.02244)
+> [Searching for MobileNetV3](https://arxiv.org/abs/1905.02244)
 
 ## Introduction
 
@@ -24,6 +24,17 @@ We present the next generation of MobileNets based on a combination of complemen
 <img src="https://user-images.githubusercontent.com/24582831/142902036-3dc2e0c0-d475-4816-b1ac-961836b41f5c.png" width="60%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                                                                     |
+| ------ | ------------------ | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| LRASPP | M-V3-D8            | 512x1024  |  320000 |      8.9 | 15.22          | V100   | 69.54 | 70.89         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v3/mobilenet-v3-d8_lraspp_4xb4-320k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_512x1024_320k_cityscapes/lraspp_m-v3-d8_512x1024_320k_cityscapes_20201224_220337-cfe8fb07.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_512x1024_320k_cityscapes/lraspp_m-v3-d8_512x1024_320k_cityscapes-20201224_220337.log.json)                                     |
+| LRASPP | M-V3-D8 (scratch)  | 512x1024  |  320000 |      8.9 | 14.77          | V100   | 67.87 | 69.78         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v3/mobilenet-v3-d8-scratch_lraspp_4xb4-320k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes_20201224_220337-9f29cd72.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes-20201224_220337.log.json)     |
+| LRASPP | M-V3s-D8           | 512x1024  |  320000 |      5.3 | 23.64          | V100   | 64.11 | 66.42         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v3/mobilenet-v3-d8-s_lraspp_4xb4-320k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_512x1024_320k_cityscapes/lraspp_m-v3s-d8_512x1024_320k_cityscapes_20201224_223935-61565b34.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_512x1024_320k_cityscapes/lraspp_m-v3s-d8_512x1024_320k_cityscapes-20201224_223935.log.json)                                 |
+| LRASPP | M-V3s-D8 (scratch) | 512x1024  |  320000 |      5.3 | 24.50          | V100   | 62.74 | 65.01         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v3/mobilenet-v3-d8-scratch-s_lraspp_4xb4-320k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes_20201224_223935-03daeabb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes-20201224_223935.log.json) |
+
 ## Citation
 
 ```bibtex
@@ -37,14 +48,3 @@ We present the next generation of MobileNets based on a combination of complemen
   doi={10.1109/ICCV.2019.00140}}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                                                                     |
-| ------ | ------------------ | --------- | ------: | -------: | -------------- | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| LRASPP | M-V3-D8            | 512x1024  |  320000 |      8.9 | 15.22          | 69.54 | 70.89         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v3/mobilenet-v3-d8_lraspp_4xb4-320k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_512x1024_320k_cityscapes/lraspp_m-v3-d8_512x1024_320k_cityscapes_20201224_220337-cfe8fb07.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_512x1024_320k_cityscapes/lraspp_m-v3-d8_512x1024_320k_cityscapes-20201224_220337.log.json)                                     |
-| LRASPP | M-V3-D8 (scratch)  | 512x1024  |  320000 |      8.9 | 14.77          | 67.87 | 69.78         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v3/mobilenet-v3-d8-scratch_lraspp_4xb4-320k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes_20201224_220337-9f29cd72.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes-20201224_220337.log.json)     |
-| LRASPP | M-V3s-D8           | 512x1024  |  320000 |      5.3 | 23.64          | 64.11 | 66.42         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v3/mobilenet-v3-d8-s_lraspp_4xb4-320k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_512x1024_320k_cityscapes/lraspp_m-v3s-d8_512x1024_320k_cityscapes_20201224_223935-61565b34.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_512x1024_320k_cityscapes/lraspp_m-v3s-d8_512x1024_320k_cityscapes-20201224_223935.log.json)                                 |
-| LRASPP | M-V3s-D8 (scratch) | 512x1024  |  320000 |      5.3 | 24.50          | 62.74 | 65.01         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v3/mobilenet-v3-d8-scratch-s_lraspp_4xb4-320k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes_20201224_223935-03daeabb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes-20201224_223935.log.json) |
diff --git a/configs/mobilenet_v3/metafile.yaml b/configs/mobilenet_v3/metafile.yaml
new file mode 100644
index 0000000000..0351d3b8e4
--- /dev/null
+++ b/configs/mobilenet_v3/metafile.yaml
@@ -0,0 +1,109 @@
+Collections:
+- Name: LRASPP
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+  Paper:
+    Title: Searching for MobileNetV3
+    URL: https://arxiv.org/abs/1905.02244
+  README: configs/mobilenet_v3/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: mobilenet-v3-d8_lraspp_4xb4-320k_cityscapes-512x1024
+  In Collection: LRASPP
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 69.54
+      mIoU(ms+flip): 70.89
+  Config: configs/mobilenet_v3/mobilenet-v3-d8_lraspp_4xb4-320k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - M-V3-D8
+    - LRASPP
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_512x1024_320k_cityscapes/lraspp_m-v3-d8_512x1024_320k_cityscapes_20201224_220337-cfe8fb07.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_512x1024_320k_cityscapes/lraspp_m-v3-d8_512x1024_320k_cityscapes-20201224_220337.log.json
+  Paper:
+    Title: Searching for MobileNetV3
+    URL: https://arxiv.org/abs/1905.02244
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mobilenet_v3.py#L15
+  Framework: PyTorch
+- Name: mobilenet-v3-d8-scratch_lraspp_4xb4-320k_cityscapes-512x1024
+  In Collection: LRASPP
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 67.87
+      mIoU(ms+flip): 69.78
+  Config: configs/mobilenet_v3/mobilenet-v3-d8-scratch_lraspp_4xb4-320k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - M-V3-D8
+    - LRASPP
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes_20201224_220337-9f29cd72.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes-20201224_220337.log.json
+  Paper:
+    Title: Searching for MobileNetV3
+    URL: https://arxiv.org/abs/1905.02244
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mobilenet_v3.py#L15
+  Framework: PyTorch
+- Name: mobilenet-v3-d8-s_lraspp_4xb4-320k_cityscapes-512x1024
+  In Collection: LRASPP
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 64.11
+      mIoU(ms+flip): 66.42
+  Config: configs/mobilenet_v3/mobilenet-v3-d8-s_lraspp_4xb4-320k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - M-V3s-D8
+    - LRASPP
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.3
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_512x1024_320k_cityscapes/lraspp_m-v3s-d8_512x1024_320k_cityscapes_20201224_223935-61565b34.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_512x1024_320k_cityscapes/lraspp_m-v3s-d8_512x1024_320k_cityscapes-20201224_223935.log.json
+  Paper:
+    Title: Searching for MobileNetV3
+    URL: https://arxiv.org/abs/1905.02244
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mobilenet_v3.py#L15
+  Framework: PyTorch
+- Name: mobilenet-v3-d8-scratch-s_lraspp_4xb4-320k_cityscapes-512x1024
+  In Collection: LRASPP
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 62.74
+      mIoU(ms+flip): 65.01
+  Config: configs/mobilenet_v3/mobilenet-v3-d8-scratch-s_lraspp_4xb4-320k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - M-V3s-D8
+    - LRASPP
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.3
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes_20201224_223935-03daeabb.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes-20201224_223935.log.json
+  Paper:
+    Title: Searching for MobileNetV3
+    URL: https://arxiv.org/abs/1905.02244
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mobilenet_v3.py#L15
+  Framework: PyTorch
diff --git a/configs/mobilenet_v3/mobilenet_v3.yml b/configs/mobilenet_v3/mobilenet_v3.yml
deleted file mode 100644
index 067a150cea..0000000000
--- a/configs/mobilenet_v3/mobilenet_v3.yml
+++ /dev/null
@@ -1,103 +0,0 @@
-Collections:
-- Name: LRASPP
-  Metadata:
-    Training Data:
-    - Cityscapes
-  Paper:
-    URL: https://arxiv.org/abs/1905.02244
-    Title: Searching for MobileNetV3
-  README: configs/mobilenet_v3/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mobilenet_v3.py#L15
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/tensorflow/models/tree/master/research/deeplab
-Models:
-- Name: mobilenet-v3-d8_lraspp_4xb4-320k_cityscapes-512x1024
-  In Collection: LRASPP
-  Metadata:
-    backbone: M-V3-D8
-    crop size: (512,1024)
-    lr schd: 320000
-    inference time (ms/im):
-    - value: 65.7
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 8.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 69.54
-      mIoU(ms+flip): 70.89
-  Config: configs/mobilenet_v3/mobilenet-v3-d8_lraspp_4xb4-320k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_512x1024_320k_cityscapes/lraspp_m-v3-d8_512x1024_320k_cityscapes_20201224_220337-cfe8fb07.pth
-- Name: mobilenet-v3-d8-scratch_lraspp_4xb4-320k_cityscapes-512x1024
-  In Collection: LRASPP
-  Metadata:
-    backbone: M-V3-D8 (scratch)
-    crop size: (512,1024)
-    lr schd: 320000
-    inference time (ms/im):
-    - value: 67.7
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 8.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 67.87
-      mIoU(ms+flip): 69.78
-  Config: configs/mobilenet_v3/mobilenet-v3-d8-scratch_lraspp_4xb4-320k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes_20201224_220337-9f29cd72.pth
-- Name: mobilenet-v3-d8-s_lraspp_4xb4-320k_cityscapes-512x1024
-  In Collection: LRASPP
-  Metadata:
-    backbone: M-V3s-D8
-    crop size: (512,1024)
-    lr schd: 320000
-    inference time (ms/im):
-    - value: 42.3
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 5.3
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 64.11
-      mIoU(ms+flip): 66.42
-  Config: configs/mobilenet_v3/mobilenet-v3-d8-s_lraspp_4xb4-320k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_512x1024_320k_cityscapes/lraspp_m-v3s-d8_512x1024_320k_cityscapes_20201224_223935-61565b34.pth
-- Name: mobilenet-v3-d8-scratch-s_lraspp_4xb4-320k_cityscapes-512x1024
-  In Collection: LRASPP
-  Metadata:
-    backbone: M-V3s-D8 (scratch)
-    crop size: (512,1024)
-    lr schd: 320000
-    inference time (ms/im):
-    - value: 40.82
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 5.3
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 62.74
-      mIoU(ms+flip): 65.01
-  Config: configs/mobilenet_v3/mobilenet-v3-d8-scratch-s_lraspp_4xb4-320k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes_20201224_223935-03daeabb.pth
diff --git a/configs/nonlocal_net/README.md b/configs/nonlocal_net/README.md
index 80d45ab589..0a0fcf3725 100644
--- a/configs/nonlocal_net/README.md
+++ b/configs/nonlocal_net/README.md
@@ -1,6 +1,6 @@
 # NonLocal Net
 
-[Non-local Neural Networks](https://arxiv.org/abs/1711.07971)
+> [Non-local Neural Networks](https://arxiv.org/abs/1711.07971)
 
 ## Introduction
 
@@ -22,6 +22,39 @@ Both convolutional and recurrent operations are building blocks that process one
 <img src="https://user-images.githubusercontent.com/24582831/142902128-17e29678-bf12-4ff4-b3d6-a39b47dfd253.png" width="50%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method      | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                    | download                                                                                                                                                                                                                                                                                                                                                                     |
+| ----------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| NonLocalNet | R-50-D8  | 512x1024  |   40000 | 7.4      | 2.72           | V100   | 78.24 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_40k_cityscapes/nonlocal_r50-d8_512x1024_40k_cityscapes_20200605_210748-c75e81e3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_40k_cityscapes/nonlocal_r50-d8_512x1024_40k_cityscapes_20200605_210748.log.json)     |
+| NonLocalNet | R-101-D8 | 512x1024  |   40000 | 10.9     | 1.95           | V100   | 78.66 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_40k_cityscapes/nonlocal_r101-d8_512x1024_40k_cityscapes_20200605_210748-d63729fa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_40k_cityscapes/nonlocal_r101-d8_512x1024_40k_cityscapes_20200605_210748.log.json) |
+| NonLocalNet | R-50-D8  | 769x769   |   40000 | 8.9      | 1.52           | V100   | 78.33 | 79.92         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_40k_cityscapes/nonlocal_r50-d8_769x769_40k_cityscapes_20200530_045243-82ef6749.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_40k_cityscapes/nonlocal_r50-d8_769x769_40k_cityscapes_20200530_045243.log.json)         |
+| NonLocalNet | R-101-D8 | 769x769   |   40000 | 12.8     | 1.05           | V100   | 78.57 | 80.29         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_40k_cityscapes/nonlocal_r101-d8_769x769_40k_cityscapes_20200530_045348-8fe9a9dc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_40k_cityscapes/nonlocal_r101-d8_769x769_40k_cityscapes_20200530_045348.log.json)     |
+| NonLocalNet | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 78.01 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_80k_cityscapes/nonlocal_r50-d8_512x1024_80k_cityscapes_20200607_193518-d6839fae.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_80k_cityscapes/nonlocal_r50-d8_512x1024_80k_cityscapes_20200607_193518.log.json)     |
+| NonLocalNet | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 78.93 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_80k_cityscapes/nonlocal_r101-d8_512x1024_80k_cityscapes_20200607_183411-32700183.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_80k_cityscapes/nonlocal_r101-d8_512x1024_80k_cityscapes_20200607_183411.log.json) |
+| NonLocalNet | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 79.05 | 80.68         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_80k_cityscapes/nonlocal_r50-d8_769x769_80k_cityscapes_20200607_193506-1f9792f6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_80k_cityscapes/nonlocal_r50-d8_769x769_80k_cityscapes_20200607_193506.log.json)         |
+| NonLocalNet | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 79.40 | 80.85         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_80k_cityscapes/nonlocal_r101-d8_769x769_80k_cityscapes_20200607_183428-0e1fa4f9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_80k_cityscapes/nonlocal_r101-d8_769x769_80k_cityscapes_20200607_183428.log.json)     |
+
+### ADE20K
+
+| Method      | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                | download                                                                                                                                                                                                                                                                                                                                                     |
+| ----------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| NonLocalNet | R-50-D8  | 512x512   |   80000 | 9.1      | 21.37          | V100   | 40.75 |         42.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_80k_ade20k/nonlocal_r50-d8_512x512_80k_ade20k_20200615_015801-5ae0aa33.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_80k_ade20k/nonlocal_r50-d8_512x512_80k_ade20k_20200615_015801.log.json)         |
+| NonLocalNet | R-101-D8 | 512x512   |   80000 | 12.6     | 13.97          | V100   | 42.90 |         44.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_80k_ade20k/nonlocal_r101-d8_512x512_80k_ade20k_20200615_015758-24105919.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_80k_ade20k/nonlocal_r101-d8_512x512_80k_ade20k_20200615_015758.log.json)     |
+| NonLocalNet | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 42.03 |         43.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_160k_ade20k/nonlocal_r50-d8_512x512_160k_ade20k_20200616_005410-baef45e3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_160k_ade20k/nonlocal_r50-d8_512x512_160k_ade20k_20200616_005410.log.json)     |
+| NonLocalNet | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 44.63 |         45.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k/nonlocal_r101-d8_512x512_160k_ade20k_20210827_221502-7881aa1a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k/nonlocal_r101-d8_512x512_160k_ade20k_20210827_221502.log.json) |
+
+### Pascal VOC 2012 + Aug
+
+| Method      | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                         |
+| ----------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| NonLocalNet | R-50-D8  | 512x512   |   20000 | 6.4      | 21.21          | V100   | 76.20 |         77.12 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_20k_voc12aug/nonlocal_r50-d8_512x512_20k_voc12aug_20200617_222613-07f2a57c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_20k_voc12aug/nonlocal_r50-d8_512x512_20k_voc12aug_20200617_222613.log.json)     |
+| NonLocalNet | R-101-D8 | 512x512   |   20000 | 9.8      | 14.01          | V100   | 78.15 |         78.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_20k_voc12aug/nonlocal_r101-d8_512x512_20k_voc12aug_20200617_222615-948c68ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_20k_voc12aug/nonlocal_r101-d8_512x512_20k_voc12aug_20200617_222615.log.json) |
+| NonLocalNet | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 76.65 |         77.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_40k_voc12aug/nonlocal_r50-d8_512x512_40k_voc12aug_20200614_000028-0139d4a9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_40k_voc12aug/nonlocal_r50-d8_512x512_40k_voc12aug_20200614_000028.log.json)     |
+| NonLocalNet | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 78.27 |         79.12 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_40k_voc12aug/nonlocal_r101-d8_512x512_40k_voc12aug_20200614_000028-7e5ff470.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_40k_voc12aug/nonlocal_r101-d8_512x512_40k_voc12aug_20200614_000028.log.json) |
+
 ## Citation
 
 ```bibtex
@@ -33,36 +66,3 @@ Both convolutional and recurrent operations are building blocks that process one
   year={2018}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method      | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                    | download                                                                                                                                                                                                                                                                                                                                                                     |
-| ----------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| NonLocalNet | R-50-D8  | 512x1024  |   40000 | 7.4      | 2.72           | 78.24 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_40k_cityscapes/nonlocal_r50-d8_512x1024_40k_cityscapes_20200605_210748-c75e81e3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_40k_cityscapes/nonlocal_r50-d8_512x1024_40k_cityscapes_20200605_210748.log.json)     |
-| NonLocalNet | R-101-D8 | 512x1024  |   40000 | 10.9     | 1.95           | 78.66 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_40k_cityscapes/nonlocal_r101-d8_512x1024_40k_cityscapes_20200605_210748-d63729fa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_40k_cityscapes/nonlocal_r101-d8_512x1024_40k_cityscapes_20200605_210748.log.json) |
-| NonLocalNet | R-50-D8  | 769x769   |   40000 | 8.9      | 1.52           | 78.33 | 79.92         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_40k_cityscapes/nonlocal_r50-d8_769x769_40k_cityscapes_20200530_045243-82ef6749.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_40k_cityscapes/nonlocal_r50-d8_769x769_40k_cityscapes_20200530_045243.log.json)         |
-| NonLocalNet | R-101-D8 | 769x769   |   40000 | 12.8     | 1.05           | 78.57 | 80.29         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_40k_cityscapes/nonlocal_r101-d8_769x769_40k_cityscapes_20200530_045348-8fe9a9dc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_40k_cityscapes/nonlocal_r101-d8_769x769_40k_cityscapes_20200530_045348.log.json)     |
-| NonLocalNet | R-50-D8  | 512x1024  |   80000 | -        | -              | 78.01 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_80k_cityscapes/nonlocal_r50-d8_512x1024_80k_cityscapes_20200607_193518-d6839fae.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_80k_cityscapes/nonlocal_r50-d8_512x1024_80k_cityscapes_20200607_193518.log.json)     |
-| NonLocalNet | R-101-D8 | 512x1024  |   80000 | -        | -              | 78.93 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_80k_cityscapes/nonlocal_r101-d8_512x1024_80k_cityscapes_20200607_183411-32700183.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_80k_cityscapes/nonlocal_r101-d8_512x1024_80k_cityscapes_20200607_183411.log.json) |
-| NonLocalNet | R-50-D8  | 769x769   |   80000 | -        | -              | 79.05 | 80.68         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_80k_cityscapes/nonlocal_r50-d8_769x769_80k_cityscapes_20200607_193506-1f9792f6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_80k_cityscapes/nonlocal_r50-d8_769x769_80k_cityscapes_20200607_193506.log.json)         |
-| NonLocalNet | R-101-D8 | 769x769   |   80000 | -        | -              | 79.40 | 80.85         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_80k_cityscapes/nonlocal_r101-d8_769x769_80k_cityscapes_20200607_183428-0e1fa4f9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_80k_cityscapes/nonlocal_r101-d8_769x769_80k_cityscapes_20200607_183428.log.json)     |
-
-### ADE20K
-
-| Method      | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                | download                                                                                                                                                                                                                                                                                                                                                     |
-| ----------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| NonLocalNet | R-50-D8  | 512x512   |   80000 | 9.1      | 21.37          | 40.75 |         42.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_80k_ade20k/nonlocal_r50-d8_512x512_80k_ade20k_20200615_015801-5ae0aa33.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_80k_ade20k/nonlocal_r50-d8_512x512_80k_ade20k_20200615_015801.log.json)         |
-| NonLocalNet | R-101-D8 | 512x512   |   80000 | 12.6     | 13.97          | 42.90 |         44.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_80k_ade20k/nonlocal_r101-d8_512x512_80k_ade20k_20200615_015758-24105919.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_80k_ade20k/nonlocal_r101-d8_512x512_80k_ade20k_20200615_015758.log.json)     |
-| NonLocalNet | R-50-D8  | 512x512   |  160000 | -        | -              | 42.03 |         43.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_160k_ade20k/nonlocal_r50-d8_512x512_160k_ade20k_20200616_005410-baef45e3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_160k_ade20k/nonlocal_r50-d8_512x512_160k_ade20k_20200616_005410.log.json)     |
-| NonLocalNet | R-101-D8 | 512x512   |  160000 | -        | -              | 44.63 |         45.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k/nonlocal_r101-d8_512x512_160k_ade20k_20210827_221502-7881aa1a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k/nonlocal_r101-d8_512x512_160k_ade20k_20210827_221502.log.json) |
-
-### Pascal VOC 2012 + Aug
-
-| Method      | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                         |
-| ----------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| NonLocalNet | R-50-D8  | 512x512   |   20000 | 6.4      | 21.21          | 76.20 |         77.12 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_20k_voc12aug/nonlocal_r50-d8_512x512_20k_voc12aug_20200617_222613-07f2a57c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_20k_voc12aug/nonlocal_r50-d8_512x512_20k_voc12aug_20200617_222613.log.json)     |
-| NonLocalNet | R-101-D8 | 512x512   |   20000 | 9.8      | 14.01          | 78.15 |         78.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_20k_voc12aug/nonlocal_r101-d8_512x512_20k_voc12aug_20200617_222615-948c68ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_20k_voc12aug/nonlocal_r101-d8_512x512_20k_voc12aug_20200617_222615.log.json) |
-| NonLocalNet | R-50-D8  | 512x512   |   40000 | -        | -              | 76.65 |         77.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_40k_voc12aug/nonlocal_r50-d8_512x512_40k_voc12aug_20200614_000028-0139d4a9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_40k_voc12aug/nonlocal_r50-d8_512x512_40k_voc12aug_20200614_000028.log.json)     |
-| NonLocalNet | R-101-D8 | 512x512   |   40000 | -        | -              | 78.27 |         79.12 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_40k_voc12aug/nonlocal_r101-d8_512x512_40k_voc12aug_20200614_000028-7e5ff470.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_40k_voc12aug/nonlocal_r101-d8_512x512_40k_voc12aug_20200614_000028.log.json) |
diff --git a/configs/nonlocal_net/metafile.yaml b/configs/nonlocal_net/metafile.yaml
new file mode 100644
index 0000000000..69bd72570b
--- /dev/null
+++ b/configs/nonlocal_net/metafile.yaml
@@ -0,0 +1,387 @@
+Collections:
+- Name: NonLocalNet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - ADE20K
+    - Pascal VOC 2012 + Aug
+  Paper:
+    Title: Non-local Neural Networks
+    URL: https://arxiv.org/abs/1711.07971
+  README: configs/nonlocal_net/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: nonlocal_r50-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: NonLocalNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.24
+  Config: configs/nonlocal_net/nonlocal_r50-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - NonLocalNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.4
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_40k_cityscapes/nonlocal_r50-d8_512x1024_40k_cityscapes_20200605_210748-c75e81e3.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_40k_cityscapes/nonlocal_r50-d8_512x1024_40k_cityscapes_20200605_210748.log.json
+  Paper:
+    Title: Non-local Neural Networks
+    URL: https://arxiv.org/abs/1711.07971
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/nl_head.py#L10
+  Framework: PyTorch
+- Name: nonlocal_r101-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: NonLocalNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.66
+  Config: configs/nonlocal_net/nonlocal_r101-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - NonLocalNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_40k_cityscapes/nonlocal_r101-d8_512x1024_40k_cityscapes_20200605_210748-d63729fa.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_40k_cityscapes/nonlocal_r101-d8_512x1024_40k_cityscapes_20200605_210748.log.json
+  Paper:
+    Title: Non-local Neural Networks
+    URL: https://arxiv.org/abs/1711.07971
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/nl_head.py#L10
+  Framework: PyTorch
+- Name: nonlocal_r50-d8_4xb2-40k_cityscapes-769x769
+  In Collection: NonLocalNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.33
+      mIoU(ms+flip): 79.92
+  Config: configs/nonlocal_net/nonlocal_r50-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - NonLocalNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_40k_cityscapes/nonlocal_r50-d8_769x769_40k_cityscapes_20200530_045243-82ef6749.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_40k_cityscapes/nonlocal_r50-d8_769x769_40k_cityscapes_20200530_045243.log.json
+  Paper:
+    Title: Non-local Neural Networks
+    URL: https://arxiv.org/abs/1711.07971
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/nl_head.py#L10
+  Framework: PyTorch
+- Name: nonlocal_r101-d8_4xb2-40k_cityscapes-769x769
+  In Collection: NonLocalNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.57
+      mIoU(ms+flip): 80.29
+  Config: configs/nonlocal_net/nonlocal_r101-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - NonLocalNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 12.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_40k_cityscapes/nonlocal_r101-d8_769x769_40k_cityscapes_20200530_045348-8fe9a9dc.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_40k_cityscapes/nonlocal_r101-d8_769x769_40k_cityscapes_20200530_045348.log.json
+  Paper:
+    Title: Non-local Neural Networks
+    URL: https://arxiv.org/abs/1711.07971
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/nl_head.py#L10
+  Framework: PyTorch
+- Name: nonlocal_r50-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: NonLocalNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.01
+  Config: configs/nonlocal_net/nonlocal_r50-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - NonLocalNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_80k_cityscapes/nonlocal_r50-d8_512x1024_80k_cityscapes_20200607_193518-d6839fae.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_80k_cityscapes/nonlocal_r50-d8_512x1024_80k_cityscapes_20200607_193518.log.json
+  Paper:
+    Title: Non-local Neural Networks
+    URL: https://arxiv.org/abs/1711.07971
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/nl_head.py#L10
+  Framework: PyTorch
+- Name: nonlocal_r101-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: NonLocalNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.93
+  Config: configs/nonlocal_net/nonlocal_r101-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - NonLocalNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_80k_cityscapes/nonlocal_r101-d8_512x1024_80k_cityscapes_20200607_183411-32700183.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_80k_cityscapes/nonlocal_r101-d8_512x1024_80k_cityscapes_20200607_183411.log.json
+  Paper:
+    Title: Non-local Neural Networks
+    URL: https://arxiv.org/abs/1711.07971
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/nl_head.py#L10
+  Framework: PyTorch
+- Name: nonlocal_r50-d8_4xb2-80k_cityscapes-769x769
+  In Collection: NonLocalNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.05
+      mIoU(ms+flip): 80.68
+  Config: configs/nonlocal_net/nonlocal_r50-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - NonLocalNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_80k_cityscapes/nonlocal_r50-d8_769x769_80k_cityscapes_20200607_193506-1f9792f6.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_80k_cityscapes/nonlocal_r50-d8_769x769_80k_cityscapes_20200607_193506.log.json
+  Paper:
+    Title: Non-local Neural Networks
+    URL: https://arxiv.org/abs/1711.07971
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/nl_head.py#L10
+  Framework: PyTorch
+- Name: nonlocal_r101-d8_4xb2-80k_cityscapes-769x769
+  In Collection: NonLocalNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.4
+      mIoU(ms+flip): 80.85
+  Config: configs/nonlocal_net/nonlocal_r101-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - NonLocalNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_80k_cityscapes/nonlocal_r101-d8_769x769_80k_cityscapes_20200607_183428-0e1fa4f9.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_80k_cityscapes/nonlocal_r101-d8_769x769_80k_cityscapes_20200607_183428.log.json
+  Paper:
+    Title: Non-local Neural Networks
+    URL: https://arxiv.org/abs/1711.07971
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/nl_head.py#L10
+  Framework: PyTorch
+- Name: nonlocal_r50-d8_4xb4-80k_ade20k-512x512
+  In Collection: NonLocalNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 40.75
+      mIoU(ms+flip): 42.05
+  Config: configs/nonlocal_net/nonlocal_r50-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - NonLocalNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_80k_ade20k/nonlocal_r50-d8_512x512_80k_ade20k_20200615_015801-5ae0aa33.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_80k_ade20k/nonlocal_r50-d8_512x512_80k_ade20k_20200615_015801.log.json
+  Paper:
+    Title: Non-local Neural Networks
+    URL: https://arxiv.org/abs/1711.07971
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/nl_head.py#L10
+  Framework: PyTorch
+- Name: nonlocal_r101-d8_4xb4-80k_ade20k-512x512
+  In Collection: NonLocalNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.9
+      mIoU(ms+flip): 44.27
+  Config: configs/nonlocal_net/nonlocal_r101-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - NonLocalNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 12.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_80k_ade20k/nonlocal_r101-d8_512x512_80k_ade20k_20200615_015758-24105919.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_80k_ade20k/nonlocal_r101-d8_512x512_80k_ade20k_20200615_015758.log.json
+  Paper:
+    Title: Non-local Neural Networks
+    URL: https://arxiv.org/abs/1711.07971
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/nl_head.py#L10
+  Framework: PyTorch
+- Name: nonlocal_r50-d8_4xb4-160k_ade20k-512x512
+  In Collection: NonLocalNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.03
+      mIoU(ms+flip): 43.04
+  Config: configs/nonlocal_net/nonlocal_r50-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - NonLocalNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_160k_ade20k/nonlocal_r50-d8_512x512_160k_ade20k_20200616_005410-baef45e3.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_160k_ade20k/nonlocal_r50-d8_512x512_160k_ade20k_20200616_005410.log.json
+  Paper:
+    Title: Non-local Neural Networks
+    URL: https://arxiv.org/abs/1711.07971
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/nl_head.py#L10
+  Framework: PyTorch
+- Name: nonlocal_r101-d8_4xb4-160k_ade20k-512x512
+  In Collection: NonLocalNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 44.63
+      mIoU(ms+flip): 45.79
+  Config: configs/nonlocal_net/nonlocal_r101-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - NonLocalNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k/nonlocal_r101-d8_512x512_160k_ade20k_20210827_221502-7881aa1a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k/nonlocal_r101-d8_512x512_160k_ade20k_20210827_221502.log.json
+  Paper:
+    Title: Non-local Neural Networks
+    URL: https://arxiv.org/abs/1711.07971
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/nl_head.py#L10
+  Framework: PyTorch
+- Name: nonlocal_r50-d8_4xb4-20k_voc12aug-512x512
+  In Collection: NonLocalNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 76.2
+      mIoU(ms+flip): 77.12
+  Config: configs/nonlocal_net/nonlocal_r50-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - NonLocalNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.4
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_20k_voc12aug/nonlocal_r50-d8_512x512_20k_voc12aug_20200617_222613-07f2a57c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_20k_voc12aug/nonlocal_r50-d8_512x512_20k_voc12aug_20200617_222613.log.json
+  Paper:
+    Title: Non-local Neural Networks
+    URL: https://arxiv.org/abs/1711.07971
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/nl_head.py#L10
+  Framework: PyTorch
+- Name: nonlocal_r101-d8_4xb4-20k_voc12aug-512x512
+  In Collection: NonLocalNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 78.15
+      mIoU(ms+flip): 78.86
+  Config: configs/nonlocal_net/nonlocal_r101-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - NonLocalNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_20k_voc12aug/nonlocal_r101-d8_512x512_20k_voc12aug_20200617_222615-948c68ab.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_20k_voc12aug/nonlocal_r101-d8_512x512_20k_voc12aug_20200617_222615.log.json
+  Paper:
+    Title: Non-local Neural Networks
+    URL: https://arxiv.org/abs/1711.07971
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/nl_head.py#L10
+  Framework: PyTorch
+- Name: nonlocal_r50-d8_4xb4-40k_voc12aug-512x512
+  In Collection: NonLocalNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 76.65
+      mIoU(ms+flip): 77.47
+  Config: configs/nonlocal_net/nonlocal_r50-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - NonLocalNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_40k_voc12aug/nonlocal_r50-d8_512x512_40k_voc12aug_20200614_000028-0139d4a9.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_40k_voc12aug/nonlocal_r50-d8_512x512_40k_voc12aug_20200614_000028.log.json
+  Paper:
+    Title: Non-local Neural Networks
+    URL: https://arxiv.org/abs/1711.07971
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/nl_head.py#L10
+  Framework: PyTorch
+- Name: nonlocal_r101-d8_4xb4-40k_voc12aug-512x512
+  In Collection: NonLocalNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 78.27
+      mIoU(ms+flip): 79.12
+  Config: configs/nonlocal_net/nonlocal_r101-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - NonLocalNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_40k_voc12aug/nonlocal_r101-d8_512x512_40k_voc12aug_20200614_000028-7e5ff470.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_40k_voc12aug/nonlocal_r101-d8_512x512_40k_voc12aug_20200614_000028.log.json
+  Paper:
+    Title: Non-local Neural Networks
+    URL: https://arxiv.org/abs/1711.07971
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/nl_head.py#L10
+  Framework: PyTorch
diff --git a/configs/nonlocal_net/nonlocal_net.yml b/configs/nonlocal_net/nonlocal_net.yml
deleted file mode 100644
index 22f32c5abb..0000000000
--- a/configs/nonlocal_net/nonlocal_net.yml
+++ /dev/null
@@ -1,301 +0,0 @@
-Collections:
-- Name: NonLocalNet
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-    - Pascal VOC 2012 + Aug
-  Paper:
-    URL: https://arxiv.org/abs/1711.07971
-    Title: Non-local Neural Networks
-  README: configs/nonlocal_net/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/nl_head.py#L10
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/facebookresearch/video-nonlocal-net
-Models:
-- Name: nonlocal_r50-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: NonLocalNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 367.65
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 7.4
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.24
-  Config: configs/nonlocal_net/nonlocal_r50-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_40k_cityscapes/nonlocal_r50-d8_512x1024_40k_cityscapes_20200605_210748-c75e81e3.pth
-- Name: nonlocal_r101-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: NonLocalNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 512.82
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 10.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.66
-  Config: configs/nonlocal_net/nonlocal_r101-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_40k_cityscapes/nonlocal_r101-d8_512x1024_40k_cityscapes_20200605_210748-d63729fa.pth
-- Name: nonlocal_r50-d8_4xb2-40k_cityscapes-769x769
-  In Collection: NonLocalNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 657.89
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 8.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.33
-      mIoU(ms+flip): 79.92
-  Config: configs/nonlocal_net/nonlocal_r50-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_40k_cityscapes/nonlocal_r50-d8_769x769_40k_cityscapes_20200530_045243-82ef6749.pth
-- Name: nonlocal_r101-d8_4xb2-40k_cityscapes-769x769
-  In Collection: NonLocalNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 952.38
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 12.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.57
-      mIoU(ms+flip): 80.29
-  Config: configs/nonlocal_net/nonlocal_r101-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_40k_cityscapes/nonlocal_r101-d8_769x769_40k_cityscapes_20200530_045348-8fe9a9dc.pth
-- Name: nonlocal_r50-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: NonLocalNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.01
-  Config: configs/nonlocal_net/nonlocal_r50-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_80k_cityscapes/nonlocal_r50-d8_512x1024_80k_cityscapes_20200607_193518-d6839fae.pth
-- Name: nonlocal_r101-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: NonLocalNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.93
-  Config: configs/nonlocal_net/nonlocal_r101-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_80k_cityscapes/nonlocal_r101-d8_512x1024_80k_cityscapes_20200607_183411-32700183.pth
-- Name: nonlocal_r50-d8_4xb2-80k_cityscapes-769x769
-  In Collection: NonLocalNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.05
-      mIoU(ms+flip): 80.68
-  Config: configs/nonlocal_net/nonlocal_r50-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_80k_cityscapes/nonlocal_r50-d8_769x769_80k_cityscapes_20200607_193506-1f9792f6.pth
-- Name: nonlocal_r101-d8_4xb2-80k_cityscapes-769x769
-  In Collection: NonLocalNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.4
-      mIoU(ms+flip): 80.85
-  Config: configs/nonlocal_net/nonlocal_r101-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_80k_cityscapes/nonlocal_r101-d8_769x769_80k_cityscapes_20200607_183428-0e1fa4f9.pth
-- Name: nonlocal_r50-d8_4xb4-80k_ade20k-512x512
-  In Collection: NonLocalNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 46.79
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 40.75
-      mIoU(ms+flip): 42.05
-  Config: configs/nonlocal_net/nonlocal_r50-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_80k_ade20k/nonlocal_r50-d8_512x512_80k_ade20k_20200615_015801-5ae0aa33.pth
-- Name: nonlocal_r101-d8_4xb4-80k_ade20k-512x512
-  In Collection: NonLocalNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 71.58
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 12.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.9
-      mIoU(ms+flip): 44.27
-  Config: configs/nonlocal_net/nonlocal_r101-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_80k_ade20k/nonlocal_r101-d8_512x512_80k_ade20k_20200615_015758-24105919.pth
-- Name: nonlocal_r50-d8_4xb4-160k_ade20k-512x512
-  In Collection: NonLocalNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.03
-      mIoU(ms+flip): 43.04
-  Config: configs/nonlocal_net/nonlocal_r50-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_160k_ade20k/nonlocal_r50-d8_512x512_160k_ade20k_20200616_005410-baef45e3.pth
-- Name: nonlocal_r101-d8_4xb4-160k_ade20k-512x512
-  In Collection: NonLocalNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 44.63
-      mIoU(ms+flip): 45.79
-  Config: configs/nonlocal_net/nonlocal_r101-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k/nonlocal_r101-d8_512x512_160k_ade20k_20210827_221502-7881aa1a.pth
-- Name: nonlocal_r50-d8_4xb4-20k_voc12aug-512x512
-  In Collection: NonLocalNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 47.15
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.4
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 76.2
-      mIoU(ms+flip): 77.12
-  Config: configs/nonlocal_net/nonlocal_r50-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_20k_voc12aug/nonlocal_r50-d8_512x512_20k_voc12aug_20200617_222613-07f2a57c.pth
-- Name: nonlocal_r101-d8_4xb4-20k_voc12aug-512x512
-  In Collection: NonLocalNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 71.38
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 78.15
-      mIoU(ms+flip): 78.86
-  Config: configs/nonlocal_net/nonlocal_r101-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_20k_voc12aug/nonlocal_r101-d8_512x512_20k_voc12aug_20200617_222615-948c68ab.pth
-- Name: nonlocal_r50-d8_4xb4-40k_voc12aug-512x512
-  In Collection: NonLocalNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 76.65
-      mIoU(ms+flip): 77.47
-  Config: configs/nonlocal_net/nonlocal_r50-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_40k_voc12aug/nonlocal_r50-d8_512x512_40k_voc12aug_20200614_000028-0139d4a9.pth
-- Name: nonlocal_r101-d8_4xb4-40k_voc12aug-512x512
-  In Collection: NonLocalNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 78.27
-      mIoU(ms+flip): 79.12
-  Config: configs/nonlocal_net/nonlocal_r101-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_40k_voc12aug/nonlocal_r101-d8_512x512_40k_voc12aug_20200614_000028-7e5ff470.pth
diff --git a/configs/ocrnet/README.md b/configs/ocrnet/README.md
index 4bd9c7d0b0..5b078f59c2 100644
--- a/configs/ocrnet/README.md
+++ b/configs/ocrnet/README.md
@@ -1,6 +1,6 @@
 # OCRNet
 
-[Object-Contextual Representations for Semantic Segmentation](https://arxiv.org/abs/1909.11065)
+> [Object-Contextual Representations for Semantic Segmentation](https://arxiv.org/abs/1909.11065)
 
 ## Introduction
 
@@ -22,6 +22,54 @@ In this paper, we address the problem of semantic segmentation and focus on the
 <img src="https://user-images.githubusercontent.com/24582831/142902197-b06b1e04-57ab-44ac-adc8-cea6695bb236.png" width="70%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+#### HRNet backbone
+
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                         |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| OCRNet | HRNetV2p-W18-Small | 512x1024  |   40000 | 3.5      | 10.45          | A100   | 76.61 |         78.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024_20230227_145026-6c052a14.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024_20230227_145026.json) |
+| OCRNet | HRNetV2p-W18       | 512x1024  |   40000 | 4.7      | 7.50           | V100   | 77.72 |         79.49 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_40k_cityscapes/ocrnet_hr18_512x1024_40k_cityscapes_20200601_033320-401c5bdd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_40k_cityscapes/ocrnet_hr18_512x1024_40k_cityscapes_20200601_033320.log.json)                     |
+| OCRNet | HRNetV2p-W48       | 512x1024  |   40000 | 8        | 4.22           | V100   | 80.58 |         81.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb2-40k_cityscapes-512x1024.pyy)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_40k_cityscapes/ocrnet_hr48_512x1024_40k_cityscapes_20200601_033336-55b32491.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_40k_cityscapes/ocrnet_hr48_512x1024_40k_cityscapes_20200601_033336.log.json)                     |
+| OCRNet | HRNetV2p-W18-Small | 512x1024  |   80000 | -        | -              | V100   | 77.16 |         78.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_80k_cityscapes/ocrnet_hr18s_512x1024_80k_cityscapes_20200601_222735-55979e63.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_80k_cityscapes/ocrnet_hr18s_512x1024_80k_cityscapes_20200601_222735.log.json)                 |
+| OCRNet | HRNetV2p-W18       | 512x1024  |   80000 | -        | -              | V100   | 78.57 |         80.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_80k_cityscapes/ocrnet_hr18_512x1024_80k_cityscapes_20200614_230521-c2e1dd4a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_80k_cityscapes/ocrnet_hr18_512x1024_80k_cityscapes_20200614_230521.log.json)                     |
+| OCRNet | HRNetV2p-W48       | 512x1024  |   80000 | -        | -              | V100   | 80.70 |         81.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_80k_cityscapes/ocrnet_hr48_512x1024_80k_cityscapes_20200601_222752-9076bcdf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_80k_cityscapes/ocrnet_hr48_512x1024_80k_cityscapes_20200601_222752.log.json)                     |
+| OCRNet | HRNetV2p-W18-Small | 512x1024  |  160000 | -        | -              | V100   | 78.45 |         79.97 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb2-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_160k_cityscapes/ocrnet_hr18s_512x1024_160k_cityscapes_20200602_191005-f4a7af28.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_160k_cityscapes/ocrnet_hr18s_512x1024_160k_cityscapes_20200602_191005.log.json)             |
+| OCRNet | HRNetV2p-W18       | 512x1024  |  160000 | -        | -              | V100   | 79.47 |         80.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb2-160k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_160k_cityscapes/ocrnet_hr18_512x1024_160k_cityscapes_20200602_191001-b9172d0c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_160k_cityscapes/ocrnet_hr18_512x1024_160k_cityscapes_20200602_191001.log.json)                 |
+| OCRNet | HRNetV2p-W48       | 512x1024  |  160000 | -        | -              | V100   | 81.35 |         82.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb2-160k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_160k_cityscapes/ocrnet_hr48_512x1024_160k_cityscapes_20200602_191037-dfbf1b0c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_160k_cityscapes/ocrnet_hr48_512x1024_160k_cityscapes_20200602_191037.log.json)                 |
+
+#### ResNet backbone
+
+| Method | Backbone | Crop Size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ---------- | ------- | -------- | -------------- | ------ | ----- | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| OCRNet | R-101-D8 | 512x1024  | 8          | 40000   | -        | -              | V100   | 80.09 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes/ocrnet_r101-d8_512x1024_40k_b8_cityscapes_20200717_110721-02ac0f13.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes/ocrnet_r101-d8_512x1024_40k_b8_cityscapes_20200717_110721.log.json)     |
+| OCRNet | R-101-D8 | 512x1024  | 16         | 40000   | 8.8      | 3.02           | V100   | 80.30 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_r101-d8_8xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes/ocrnet_r101-d8_512x1024_40k_b16_cityscapes_20200723_193726-db500f80.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes/ocrnet_r101-d8_512x1024_40k_b16_cityscapes_20200723_193726.log.json) |
+| OCRNet | R-101-D8 | 512x1024  | 16         | 80000   | 8.8      | 3.02           | V100   | 80.81 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_r101-d8_8xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes/ocrnet_r101-d8_512x1024_80k_b16_cityscapes_20200723_192421-78688424.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes/ocrnet_r101-d8_512x1024_80k_b16_cityscapes_20200723_192421.log.json) |
+
+### ADE20K
+
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                     | download                                                                                                                                                                                                                                                                                                                         |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| OCRNet | HRNetV2p-W18-Small | 512x512   |   80000 | 6.7      | 28.98          | V100   | 35.06 |         35.80 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_80k_ade20k/ocrnet_hr18s_512x512_80k_ade20k_20200615_055600-e80b62af.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_80k_ade20k/ocrnet_hr18s_512x512_80k_ade20k_20200615_055600.log.json)     |
+| OCRNet | HRNetV2p-W18       | 512x512   |   80000 | 7.9      | 18.93          | V100   | 37.79 |         39.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_80k_ade20k/ocrnet_hr18_512x512_80k_ade20k_20200615_053157-d173d83b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_80k_ade20k/ocrnet_hr18_512x512_80k_ade20k_20200615_053157.log.json)         |
+| OCRNet | HRNetV2p-W48       | 512x512   |   80000 | 11.2     | 16.99          | V100   | 43.00 |         44.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_80k_ade20k/ocrnet_hr48_512x512_80k_ade20k_20200615_021518-d168c2d1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_80k_ade20k/ocrnet_hr48_512x512_80k_ade20k_20200615_021518.log.json)         |
+| OCRNet | HRNetV2p-W18-Small | 512x512   |  160000 | -        | -              | V100   | 37.19 |         38.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_160k_ade20k/ocrnet_hr18s_512x512_160k_ade20k_20200615_184505-8e913058.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_160k_ade20k/ocrnet_hr18s_512x512_160k_ade20k_20200615_184505.log.json) |
+| OCRNet | HRNetV2p-W18       | 512x512   |  160000 | -        | -              | V100   | 39.32 |         40.80 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_160k_ade20k/ocrnet_hr18_512x512_160k_ade20k_20200615_200940-d8fcd9d1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_160k_ade20k/ocrnet_hr18_512x512_160k_ade20k_20200615_200940.log.json)     |
+| OCRNet | HRNetV2p-W48       | 512x512   |  160000 | -        | -              | V100   | 43.25 |         44.88 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_160k_ade20k/ocrnet_hr48_512x512_160k_ade20k_20200615_184705-a073726d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_160k_ade20k/ocrnet_hr48_512x512_160k_ade20k_20200615_184705.log.json)     |
+
+### Pascal VOC 2012 + Aug
+
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                             |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| OCRNet | HRNetV2p-W18-Small | 512x512   |   20000 | 3.5      | 31.55          | V100   | 71.70 |         73.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_20k_voc12aug/ocrnet_hr18s_512x512_20k_voc12aug_20200617_233913-02b04fcb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_20k_voc12aug/ocrnet_hr18s_512x512_20k_voc12aug_20200617_233913.log.json) |
+| OCRNet | HRNetV2p-W18       | 512x512   |   20000 | 4.7      | 19.91          | V100   | 74.75 |         77.11 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_20k_voc12aug/ocrnet_hr18_512x512_20k_voc12aug_20200617_233932-8954cbb7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_20k_voc12aug/ocrnet_hr18_512x512_20k_voc12aug_20200617_233932.log.json)     |
+| OCRNet | HRNetV2p-W48       | 512x512   |   20000 | 8.1      | 17.83          | V100   | 77.72 |         79.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_20k_voc12aug/ocrnet_hr48_512x512_20k_voc12aug_20200617_233932-9e82080a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_20k_voc12aug/ocrnet_hr48_512x512_20k_voc12aug_20200617_233932.log.json)     |
+| OCRNet | HRNetV2p-W18-Small | 512x512   |   40000 | -        | -              | V100   | 72.76 |         74.60 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_40k_voc12aug/ocrnet_hr18s_512x512_40k_voc12aug_20200614_002025-42b587ac.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_40k_voc12aug/ocrnet_hr18s_512x512_40k_voc12aug_20200614_002025.log.json) |
+| OCRNet | HRNetV2p-W18       | 512x512   |   40000 | -        | -              | V100   | 74.98 |         77.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_40k_voc12aug/ocrnet_hr18_512x512_40k_voc12aug_20200614_015958-714302be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_40k_voc12aug/ocrnet_hr18_512x512_40k_voc12aug_20200614_015958.log.json)     |
+| OCRNet | HRNetV2p-W48       | 512x512   |   40000 | -        | -              | V100   | 77.14 |         79.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_40k_voc12aug/ocrnet_hr48_512x512_40k_voc12aug_20200614_015958-255bc5ce.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_40k_voc12aug/ocrnet_hr48_512x512_40k_voc12aug_20200614_015958.log.json)     |
+
 ## Citation
 
 ```bibtex
@@ -39,51 +87,3 @@ In this paper, we address the problem of semantic segmentation and focus on the
   year={2020}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-#### HRNet backbone
-
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                         |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| OCRNet | HRNetV2p-W18-Small | 512x1024  |   40000 | 3.5      | 10.45          | 76.61 |         78.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024_20230227_145026-6c052a14.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024_20230227_145026.json) |
-| OCRNet | HRNetV2p-W18       | 512x1024  |   40000 | 4.7      | 7.50           | 77.72 |         79.49 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_40k_cityscapes/ocrnet_hr18_512x1024_40k_cityscapes_20200601_033320-401c5bdd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_40k_cityscapes/ocrnet_hr18_512x1024_40k_cityscapes_20200601_033320.log.json)                     |
-| OCRNet | HRNetV2p-W48       | 512x1024  |   40000 | 8        | 4.22           | 80.58 |         81.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb2-40k_cityscapes-512x1024.pyy)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_40k_cityscapes/ocrnet_hr48_512x1024_40k_cityscapes_20200601_033336-55b32491.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_40k_cityscapes/ocrnet_hr48_512x1024_40k_cityscapes_20200601_033336.log.json)                     |
-| OCRNet | HRNetV2p-W18-Small | 512x1024  |   80000 | -        | -              | 77.16 |         78.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_80k_cityscapes/ocrnet_hr18s_512x1024_80k_cityscapes_20200601_222735-55979e63.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_80k_cityscapes/ocrnet_hr18s_512x1024_80k_cityscapes_20200601_222735.log.json)                 |
-| OCRNet | HRNetV2p-W18       | 512x1024  |   80000 | -        | -              | 78.57 |         80.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_80k_cityscapes/ocrnet_hr18_512x1024_80k_cityscapes_20200614_230521-c2e1dd4a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_80k_cityscapes/ocrnet_hr18_512x1024_80k_cityscapes_20200614_230521.log.json)                     |
-| OCRNet | HRNetV2p-W48       | 512x1024  |   80000 | -        | -              | 80.70 |         81.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_80k_cityscapes/ocrnet_hr48_512x1024_80k_cityscapes_20200601_222752-9076bcdf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_80k_cityscapes/ocrnet_hr48_512x1024_80k_cityscapes_20200601_222752.log.json)                     |
-| OCRNet | HRNetV2p-W18-Small | 512x1024  |  160000 | -        | -              | 78.45 |         79.97 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb2-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_160k_cityscapes/ocrnet_hr18s_512x1024_160k_cityscapes_20200602_191005-f4a7af28.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_160k_cityscapes/ocrnet_hr18s_512x1024_160k_cityscapes_20200602_191005.log.json)             |
-| OCRNet | HRNetV2p-W18       | 512x1024  |  160000 | -        | -              | 79.47 |         80.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb2-160k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_160k_cityscapes/ocrnet_hr18_512x1024_160k_cityscapes_20200602_191001-b9172d0c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_160k_cityscapes/ocrnet_hr18_512x1024_160k_cityscapes_20200602_191001.log.json)                 |
-| OCRNet | HRNetV2p-W48       | 512x1024  |  160000 | -        | -              | 81.35 |         82.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb2-160k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_160k_cityscapes/ocrnet_hr48_512x1024_160k_cityscapes_20200602_191037-dfbf1b0c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_160k_cityscapes/ocrnet_hr48_512x1024_160k_cityscapes_20200602_191037.log.json)                 |
-
-#### ResNet backbone
-
-| Method | Backbone | Crop Size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ---------- | ------- | -------- | -------------- | ----- | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| OCRNet | R-101-D8 | 512x1024  | 8          | 40000   | -        | -              | 80.09 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes/ocrnet_r101-d8_512x1024_40k_b8_cityscapes_20200717_110721-02ac0f13.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes/ocrnet_r101-d8_512x1024_40k_b8_cityscapes_20200717_110721.log.json)     |
-| OCRNet | R-101-D8 | 512x1024  | 16         | 40000   | 8.8      | 3.02           | 80.30 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_r101-d8_8xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes/ocrnet_r101-d8_512x1024_40k_b16_cityscapes_20200723_193726-db500f80.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes/ocrnet_r101-d8_512x1024_40k_b16_cityscapes_20200723_193726.log.json) |
-| OCRNet | R-101-D8 | 512x1024  | 16         | 80000   | 8.8      | 3.02           | 80.81 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_r101-d8_8xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes/ocrnet_r101-d8_512x1024_80k_b16_cityscapes_20200723_192421-78688424.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes/ocrnet_r101-d8_512x1024_80k_b16_cityscapes_20200723_192421.log.json) |
-
-### ADE20K
-
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                     | download                                                                                                                                                                                                                                                                                                                         |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| OCRNet | HRNetV2p-W18-Small | 512x512   |   80000 | 6.7      | 28.98          | 35.06 |         35.80 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_80k_ade20k/ocrnet_hr18s_512x512_80k_ade20k_20200615_055600-e80b62af.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_80k_ade20k/ocrnet_hr18s_512x512_80k_ade20k_20200615_055600.log.json)     |
-| OCRNet | HRNetV2p-W18       | 512x512   |   80000 | 7.9      | 18.93          | 37.79 |         39.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_80k_ade20k/ocrnet_hr18_512x512_80k_ade20k_20200615_053157-d173d83b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_80k_ade20k/ocrnet_hr18_512x512_80k_ade20k_20200615_053157.log.json)         |
-| OCRNet | HRNetV2p-W48       | 512x512   |   80000 | 11.2     | 16.99          | 43.00 |         44.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_80k_ade20k/ocrnet_hr48_512x512_80k_ade20k_20200615_021518-d168c2d1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_80k_ade20k/ocrnet_hr48_512x512_80k_ade20k_20200615_021518.log.json)         |
-| OCRNet | HRNetV2p-W18-Small | 512x512   |  160000 | -        | -              | 37.19 |         38.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_160k_ade20k/ocrnet_hr18s_512x512_160k_ade20k_20200615_184505-8e913058.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_160k_ade20k/ocrnet_hr18s_512x512_160k_ade20k_20200615_184505.log.json) |
-| OCRNet | HRNetV2p-W18       | 512x512   |  160000 | -        | -              | 39.32 |         40.80 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_160k_ade20k/ocrnet_hr18_512x512_160k_ade20k_20200615_200940-d8fcd9d1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_160k_ade20k/ocrnet_hr18_512x512_160k_ade20k_20200615_200940.log.json)     |
-| OCRNet | HRNetV2p-W48       | 512x512   |  160000 | -        | -              | 43.25 |         44.88 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_160k_ade20k/ocrnet_hr48_512x512_160k_ade20k_20200615_184705-a073726d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_160k_ade20k/ocrnet_hr48_512x512_160k_ade20k_20200615_184705.log.json)     |
-
-### Pascal VOC 2012 + Aug
-
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                             |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| OCRNet | HRNetV2p-W18-Small | 512x512   |   20000 | 3.5      | 31.55          | 71.70 |         73.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_20k_voc12aug/ocrnet_hr18s_512x512_20k_voc12aug_20200617_233913-02b04fcb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_20k_voc12aug/ocrnet_hr18s_512x512_20k_voc12aug_20200617_233913.log.json) |
-| OCRNet | HRNetV2p-W18       | 512x512   |   20000 | 4.7      | 19.91          | 74.75 |         77.11 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_20k_voc12aug/ocrnet_hr18_512x512_20k_voc12aug_20200617_233932-8954cbb7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_20k_voc12aug/ocrnet_hr18_512x512_20k_voc12aug_20200617_233932.log.json)     |
-| OCRNet | HRNetV2p-W48       | 512x512   |   20000 | 8.1      | 17.83          | 77.72 |         79.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_20k_voc12aug/ocrnet_hr48_512x512_20k_voc12aug_20200617_233932-9e82080a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_20k_voc12aug/ocrnet_hr48_512x512_20k_voc12aug_20200617_233932.log.json)     |
-| OCRNet | HRNetV2p-W18-Small | 512x512   |   40000 | -        | -              | 72.76 |         74.60 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_40k_voc12aug/ocrnet_hr18s_512x512_40k_voc12aug_20200614_002025-42b587ac.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_40k_voc12aug/ocrnet_hr18s_512x512_40k_voc12aug_20200614_002025.log.json) |
-| OCRNet | HRNetV2p-W18       | 512x512   |   40000 | -        | -              | 74.98 |         77.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_40k_voc12aug/ocrnet_hr18_512x512_40k_voc12aug_20200614_015958-714302be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_40k_voc12aug/ocrnet_hr18_512x512_40k_voc12aug_20200614_015958.log.json)     |
-| OCRNet | HRNetV2p-W48       | 512x512   |   40000 | -        | -              | 77.14 |         79.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_40k_voc12aug/ocrnet_hr48_512x512_40k_voc12aug_20200614_015958-255bc5ce.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_40k_voc12aug/ocrnet_hr48_512x512_40k_voc12aug_20200614_015958.log.json)     |
diff --git a/configs/ocrnet/metafile.yaml b/configs/ocrnet/metafile.yaml
new file mode 100644
index 0000000000..5467feb975
--- /dev/null
+++ b/configs/ocrnet/metafile.yaml
@@ -0,0 +1,577 @@
+Collections:
+- Name: OCRNet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - '# HRNet backbone'
+    - '# ResNet backbone'
+    - ADE20K
+    - Pascal VOC 2012 + Aug
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  README: configs/ocrnet/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: ocrnet_hr18s_4xb2-40k_cityscapes-512x1024
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: '# HRNet backbone'
+    Metrics:
+      mIoU: 76.61
+      mIoU(ms+flip): 78.01
+  Config: configs/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: '# HRNet backbone'
+    Batch Size: 8
+    Architecture:
+    - HRNetV2p-W18-Small
+    - OCRNet
+    Training Resources: 4x A100 GPUS
+    Memory (GB): 3.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024_20230227_145026-6c052a14.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024_20230227_145026.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr18_4xb2-40k_cityscapes-512x1024
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: '# HRNet backbone'
+    Metrics:
+      mIoU: 77.72
+      mIoU(ms+flip): 79.49
+  Config: configs/ocrnet/ocrnet_hr18_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: '# HRNet backbone'
+    Batch Size: 8
+    Architecture:
+    - HRNetV2p-W18
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 4.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_40k_cityscapes/ocrnet_hr18_512x1024_40k_cityscapes_20200601_033320-401c5bdd.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_40k_cityscapes/ocrnet_hr18_512x1024_40k_cityscapes_20200601_033320.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr48_4xb2-40k_cityscapes-512x1024
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: '# HRNet backbone'
+    Metrics:
+      mIoU: 80.58
+      mIoU(ms+flip): 81.79
+  Config: configs/ocrnet/ocrnet_hr48_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: '# HRNet backbone'
+    Batch Size: 8
+    Architecture:
+    - HRNetV2p-W48
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_40k_cityscapes/ocrnet_hr48_512x1024_40k_cityscapes_20200601_033336-55b32491.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_40k_cityscapes/ocrnet_hr48_512x1024_40k_cityscapes_20200601_033336.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr18s_4xb2-80k_cityscapes-512x1024
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: '# HRNet backbone'
+    Metrics:
+      mIoU: 77.16
+      mIoU(ms+flip): 78.66
+  Config: configs/ocrnet/ocrnet_hr18s_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: '# HRNet backbone'
+    Batch Size: 8
+    Architecture:
+    - HRNetV2p-W18-Small
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_80k_cityscapes/ocrnet_hr18s_512x1024_80k_cityscapes_20200601_222735-55979e63.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_80k_cityscapes/ocrnet_hr18s_512x1024_80k_cityscapes_20200601_222735.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr18_4xb2-80k_cityscapes-512x1024
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: '# HRNet backbone'
+    Metrics:
+      mIoU: 78.57
+      mIoU(ms+flip): 80.46
+  Config: configs/ocrnet/ocrnet_hr18_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: '# HRNet backbone'
+    Batch Size: 8
+    Architecture:
+    - HRNetV2p-W18
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_80k_cityscapes/ocrnet_hr18_512x1024_80k_cityscapes_20200614_230521-c2e1dd4a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_80k_cityscapes/ocrnet_hr18_512x1024_80k_cityscapes_20200614_230521.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr48_4xb2-80k_cityscapes-512x1024
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: '# HRNet backbone'
+    Metrics:
+      mIoU: 80.7
+      mIoU(ms+flip): 81.87
+  Config: configs/ocrnet/ocrnet_hr48_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: '# HRNet backbone'
+    Batch Size: 8
+    Architecture:
+    - HRNetV2p-W48
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_80k_cityscapes/ocrnet_hr48_512x1024_80k_cityscapes_20200601_222752-9076bcdf.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_80k_cityscapes/ocrnet_hr48_512x1024_80k_cityscapes_20200601_222752.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr18s_4xb2-160k_cityscapes-512x1024
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: '# HRNet backbone'
+    Metrics:
+      mIoU: 78.45
+      mIoU(ms+flip): 79.97
+  Config: configs/ocrnet/ocrnet_hr18s_4xb2-160k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: '# HRNet backbone'
+    Batch Size: 8
+    Architecture:
+    - HRNetV2p-W18-Small
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_160k_cityscapes/ocrnet_hr18s_512x1024_160k_cityscapes_20200602_191005-f4a7af28.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_160k_cityscapes/ocrnet_hr18s_512x1024_160k_cityscapes_20200602_191005.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr18_4xb2-160k_cityscapes-512x1024
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: '# HRNet backbone'
+    Metrics:
+      mIoU: 79.47
+      mIoU(ms+flip): 80.91
+  Config: configs/ocrnet/ocrnet_hr18_4xb2-160k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: '# HRNet backbone'
+    Batch Size: 8
+    Architecture:
+    - HRNetV2p-W18
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_160k_cityscapes/ocrnet_hr18_512x1024_160k_cityscapes_20200602_191001-b9172d0c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_160k_cityscapes/ocrnet_hr18_512x1024_160k_cityscapes_20200602_191001.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr48_4xb2-160k_cityscapes-512x1024
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: '# HRNet backbone'
+    Metrics:
+      mIoU: 81.35
+      mIoU(ms+flip): 82.7
+  Config: configs/ocrnet/ocrnet_hr48_4xb2-160k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: '# HRNet backbone'
+    Batch Size: 8
+    Architecture:
+    - HRNetV2p-W48
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_160k_cityscapes/ocrnet_hr48_512x1024_160k_cityscapes_20200602_191037-dfbf1b0c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_160k_cityscapes/ocrnet_hr48_512x1024_160k_cityscapes_20200602_191037.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_r101-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: '# ResNet backbone'
+    Metrics:
+      mIoU: 80.09
+  Config: configs/ocrnet/ocrnet_r101-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: '# ResNet backbone'
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes/ocrnet_r101-d8_512x1024_40k_b8_cityscapes_20200717_110721-02ac0f13.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes/ocrnet_r101-d8_512x1024_40k_b8_cityscapes_20200717_110721.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_r101-d8_8xb2-40k_cityscapes-512x1024
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: '# ResNet backbone'
+    Metrics:
+      mIoU: 80.3
+  Config: configs/ocrnet/ocrnet_r101-d8_8xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: '# ResNet backbone'
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - OCRNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 8.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes/ocrnet_r101-d8_512x1024_40k_b16_cityscapes_20200723_193726-db500f80.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes/ocrnet_r101-d8_512x1024_40k_b16_cityscapes_20200723_193726.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_r101-d8_8xb2-80k_cityscapes-512x1024
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: '# ResNet backbone'
+    Metrics:
+      mIoU: 80.81
+  Config: configs/ocrnet/ocrnet_r101-d8_8xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: '# ResNet backbone'
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - OCRNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 8.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes/ocrnet_r101-d8_512x1024_80k_b16_cityscapes_20200723_192421-78688424.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes/ocrnet_r101-d8_512x1024_80k_b16_cityscapes_20200723_192421.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr18s_4xb4-80k_ade20k-512x512
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 35.06
+      mIoU(ms+flip): 35.8
+  Config: configs/ocrnet/ocrnet_hr18s_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18-Small
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_80k_ade20k/ocrnet_hr18s_512x512_80k_ade20k_20200615_055600-e80b62af.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_80k_ade20k/ocrnet_hr18s_512x512_80k_ade20k_20200615_055600.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr18_4xb4-80k_ade20k-512x512
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 37.79
+      mIoU(ms+flip): 39.16
+  Config: configs/ocrnet/ocrnet_hr18_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_80k_ade20k/ocrnet_hr18_512x512_80k_ade20k_20200615_053157-d173d83b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_80k_ade20k/ocrnet_hr18_512x512_80k_ade20k_20200615_053157.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr48_4xb4-80k_ade20k-512x512
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.0
+      mIoU(ms+flip): 44.3
+  Config: configs/ocrnet/ocrnet_hr48_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W48
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 11.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_80k_ade20k/ocrnet_hr48_512x512_80k_ade20k_20200615_021518-d168c2d1.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_80k_ade20k/ocrnet_hr48_512x512_80k_ade20k_20200615_021518.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr18s_4xb4-80k_ade20k-512x512
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 37.19
+      mIoU(ms+flip): 38.4
+  Config: configs/ocrnet/ocrnet_hr18s_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18-Small
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_160k_ade20k/ocrnet_hr18s_512x512_160k_ade20k_20200615_184505-8e913058.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_160k_ade20k/ocrnet_hr18s_512x512_160k_ade20k_20200615_184505.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr18_4xb4-80k_ade20k-512x512
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 39.32
+      mIoU(ms+flip): 40.8
+  Config: configs/ocrnet/ocrnet_hr18_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_160k_ade20k/ocrnet_hr18_512x512_160k_ade20k_20200615_200940-d8fcd9d1.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_160k_ade20k/ocrnet_hr18_512x512_160k_ade20k_20200615_200940.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr48_4xb4-160k_ade20k-512x512
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.25
+      mIoU(ms+flip): 44.88
+  Config: configs/ocrnet/ocrnet_hr48_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W48
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_160k_ade20k/ocrnet_hr48_512x512_160k_ade20k_20200615_184705-a073726d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_160k_ade20k/ocrnet_hr48_512x512_160k_ade20k_20200615_184705.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr18s_4xb4-20k_voc12aug-512x512
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 71.7
+      mIoU(ms+flip): 73.84
+  Config: configs/ocrnet/ocrnet_hr18s_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18-Small
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 3.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_20k_voc12aug/ocrnet_hr18s_512x512_20k_voc12aug_20200617_233913-02b04fcb.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_20k_voc12aug/ocrnet_hr18s_512x512_20k_voc12aug_20200617_233913.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr18_4xb4-20k_voc12aug-512x512
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 74.75
+      mIoU(ms+flip): 77.11
+  Config: configs/ocrnet/ocrnet_hr18_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 4.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_20k_voc12aug/ocrnet_hr18_512x512_20k_voc12aug_20200617_233932-8954cbb7.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_20k_voc12aug/ocrnet_hr18_512x512_20k_voc12aug_20200617_233932.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr48_4xb4-20k_voc12aug-512x512
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 77.72
+      mIoU(ms+flip): 79.87
+  Config: configs/ocrnet/ocrnet_hr48_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W48
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_20k_voc12aug/ocrnet_hr48_512x512_20k_voc12aug_20200617_233932-9e82080a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_20k_voc12aug/ocrnet_hr48_512x512_20k_voc12aug_20200617_233932.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr18s_4xb4-40k_voc12aug-512x512
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 72.76
+      mIoU(ms+flip): 74.6
+  Config: configs/ocrnet/ocrnet_hr18s_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18-Small
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_40k_voc12aug/ocrnet_hr18s_512x512_40k_voc12aug_20200614_002025-42b587ac.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_40k_voc12aug/ocrnet_hr18s_512x512_40k_voc12aug_20200614_002025.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr18_4xb4-40k_voc12aug-512x512
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 74.98
+      mIoU(ms+flip): 77.4
+  Config: configs/ocrnet/ocrnet_hr18_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W18
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_40k_voc12aug/ocrnet_hr18_512x512_40k_voc12aug_20200614_015958-714302be.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_40k_voc12aug/ocrnet_hr18_512x512_40k_voc12aug_20200614_015958.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
+- Name: ocrnet_hr48_4xb4-40k_voc12aug-512x512
+  In Collection: OCRNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 77.14
+      mIoU(ms+flip): 79.71
+  Config: configs/ocrnet/ocrnet_hr48_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - HRNetV2p-W48
+    - OCRNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_40k_voc12aug/ocrnet_hr48_512x512_40k_voc12aug_20200614_015958-255bc5ce.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_40k_voc12aug/ocrnet_hr48_512x512_40k_voc12aug_20200614_015958.log.json
+  Paper:
+    Title: Object-Contextual Representations for Semantic Segmentation
+    URL: https://arxiv.org/abs/1909.11065
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
+  Framework: PyTorch
diff --git a/configs/ocrnet/ocrnet.yml b/configs/ocrnet/ocrnet.yml
deleted file mode 100644
index 20002e8864..0000000000
--- a/configs/ocrnet/ocrnet.yml
+++ /dev/null
@@ -1,438 +0,0 @@
-Collections:
-- Name: OCRNet
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-    - Pascal VOC 2012 + Aug
-  Paper:
-    URL: https://arxiv.org/abs/1909.11065
-    Title: Object-Contextual Representations for Semantic Segmentation
-  README: configs/ocrnet/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/openseg-group/OCNet.pytorch
-Models:
-- Name: ocrnet_hr18s_4xb2-40k_cityscapes-512x1024
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W18-Small
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 95.69
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 3.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.61
-      mIoU(ms+flip): 78.01
-  Config: configs/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024_20230227_145026-6c052a14.pth
-- Name: ocrnet_hr18_4xb2-40k_cityscapes-512x1024
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W18
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 133.33
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 4.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.72
-      mIoU(ms+flip): 79.49
-  Config: configs/ocrnet/ocrnet_hr18_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_40k_cityscapes/ocrnet_hr18_512x1024_40k_cityscapes_20200601_033320-401c5bdd.pth
-- Name: ocrnet_hr48_4xb2-40k_cityscapes-512x1024
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 236.97
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 8.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.58
-      mIoU(ms+flip): 81.79
-  Config: configs/ocrnet/ocrnet_hr48_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_40k_cityscapes/ocrnet_hr48_512x1024_40k_cityscapes_20200601_033336-55b32491.pth
-- Name: ocrnet_hr18s_4xb2-80k_cityscapes-512x1024
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W18-Small
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.16
-      mIoU(ms+flip): 78.66
-  Config: configs/ocrnet/ocrnet_hr18s_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_80k_cityscapes/ocrnet_hr18s_512x1024_80k_cityscapes_20200601_222735-55979e63.pth
-- Name: ocrnet_hr18_4xb2-80k_cityscapes-512x1024
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W18
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.57
-      mIoU(ms+flip): 80.46
-  Config: configs/ocrnet/ocrnet_hr18_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_80k_cityscapes/ocrnet_hr18_512x1024_80k_cityscapes_20200614_230521-c2e1dd4a.pth
-- Name: ocrnet_hr48_4xb2-80k_cityscapes-512x1024
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.7
-      mIoU(ms+flip): 81.87
-  Config: configs/ocrnet/ocrnet_hr48_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_80k_cityscapes/ocrnet_hr48_512x1024_80k_cityscapes_20200601_222752-9076bcdf.pth
-- Name: ocrnet_hr18s_4xb2-160k_cityscapes-512x1024
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W18-Small
-    crop size: (512,1024)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.45
-      mIoU(ms+flip): 79.97
-  Config: configs/ocrnet/ocrnet_hr18s_4xb2-160k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_160k_cityscapes/ocrnet_hr18s_512x1024_160k_cityscapes_20200602_191005-f4a7af28.pth
-- Name: ocrnet_hr18_4xb2-160k_cityscapes-512x1024
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W18
-    crop size: (512,1024)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.47
-      mIoU(ms+flip): 80.91
-  Config: configs/ocrnet/ocrnet_hr18_4xb2-160k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_160k_cityscapes/ocrnet_hr18_512x1024_160k_cityscapes_20200602_191001-b9172d0c.pth
-- Name: ocrnet_hr48_4xb2-160k_cityscapes-512x1024
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (512,1024)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 81.35
-      mIoU(ms+flip): 82.7
-  Config: configs/ocrnet/ocrnet_hr48_4xb2-160k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_160k_cityscapes/ocrnet_hr48_512x1024_160k_cityscapes_20200602_191037-dfbf1b0c.pth
-- Name: ocrnet_r101-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: OCRNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.09
-  Config: configs/ocrnet/ocrnet_r101-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes/ocrnet_r101-d8_512x1024_40k_b8_cityscapes_20200717_110721-02ac0f13.pth
-- Name: ocrnet_r101-d8_8xb2-40k_cityscapes-512x1024
-  In Collection: OCRNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 331.13
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 8.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.3
-  Config: configs/ocrnet/ocrnet_r101-d8_8xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes/ocrnet_r101-d8_512x1024_40k_b16_cityscapes_20200723_193726-db500f80.pth
-- Name: ocrnet_r101-d8_8xb2-80k_cityscapes-512x1024
-  In Collection: OCRNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 331.13
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 8.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.81
-  Config: configs/ocrnet/ocrnet_r101-d8_8xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes/ocrnet_r101-d8_512x1024_80k_b16_cityscapes_20200723_192421-78688424.pth
-- Name: ocrnet_hr18s_4xb4-80k_ade20k-512x512
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W18-Small
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 34.51
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 35.06
-      mIoU(ms+flip): 35.8
-  Config: configs/ocrnet/ocrnet_hr18s_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_80k_ade20k/ocrnet_hr18s_512x512_80k_ade20k_20200615_055600-e80b62af.pth
-- Name: ocrnet_hr18_4xb4-80k_ade20k-512x512
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W18
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 52.83
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 7.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 37.79
-      mIoU(ms+flip): 39.16
-  Config: configs/ocrnet/ocrnet_hr18_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_80k_ade20k/ocrnet_hr18_512x512_80k_ade20k_20200615_053157-d173d83b.pth
-- Name: ocrnet_hr48_4xb4-80k_ade20k-512x512
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 58.86
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 11.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.0
-      mIoU(ms+flip): 44.3
-  Config: configs/ocrnet/ocrnet_hr48_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_80k_ade20k/ocrnet_hr48_512x512_80k_ade20k_20200615_021518-d168c2d1.pth
-- Name: ocrnet_hr18s_4xb4-80k_ade20k-512x512
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W18-Small
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 37.19
-      mIoU(ms+flip): 38.4
-  Config: configs/ocrnet/ocrnet_hr18s_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_160k_ade20k/ocrnet_hr18s_512x512_160k_ade20k_20200615_184505-8e913058.pth
-- Name: ocrnet_hr18_4xb4-80k_ade20k-512x512
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W18
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 39.32
-      mIoU(ms+flip): 40.8
-  Config: configs/ocrnet/ocrnet_hr18_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_160k_ade20k/ocrnet_hr18_512x512_160k_ade20k_20200615_200940-d8fcd9d1.pth
-- Name: ocrnet_hr48_4xb4-160k_ade20k-512x512
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.25
-      mIoU(ms+flip): 44.88
-  Config: configs/ocrnet/ocrnet_hr48_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_160k_ade20k/ocrnet_hr48_512x512_160k_ade20k_20200615_184705-a073726d.pth
-- Name: ocrnet_hr18s_4xb4-20k_voc12aug-512x512
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W18-Small
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 31.7
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 3.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 71.7
-      mIoU(ms+flip): 73.84
-  Config: configs/ocrnet/ocrnet_hr18s_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_20k_voc12aug/ocrnet_hr18s_512x512_20k_voc12aug_20200617_233913-02b04fcb.pth
-- Name: ocrnet_hr18_4xb4-20k_voc12aug-512x512
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W18
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 50.23
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 4.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 74.75
-      mIoU(ms+flip): 77.11
-  Config: configs/ocrnet/ocrnet_hr18_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_20k_voc12aug/ocrnet_hr18_512x512_20k_voc12aug_20200617_233932-8954cbb7.pth
-- Name: ocrnet_hr48_4xb4-20k_voc12aug-512x512
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 56.09
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 8.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 77.72
-      mIoU(ms+flip): 79.87
-  Config: configs/ocrnet/ocrnet_hr48_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_20k_voc12aug/ocrnet_hr48_512x512_20k_voc12aug_20200617_233932-9e82080a.pth
-- Name: ocrnet_hr18s_4xb4-40k_voc12aug-512x512
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W18-Small
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 72.76
-      mIoU(ms+flip): 74.6
-  Config: configs/ocrnet/ocrnet_hr18s_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_40k_voc12aug/ocrnet_hr18s_512x512_40k_voc12aug_20200614_002025-42b587ac.pth
-- Name: ocrnet_hr18_4xb4-40k_voc12aug-512x512
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W18
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 74.98
-      mIoU(ms+flip): 77.4
-  Config: configs/ocrnet/ocrnet_hr18_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_40k_voc12aug/ocrnet_hr18_512x512_40k_voc12aug_20200614_015958-714302be.pth
-- Name: ocrnet_hr48_4xb4-40k_voc12aug-512x512
-  In Collection: OCRNet
-  Metadata:
-    backbone: HRNetV2p-W48
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 77.14
-      mIoU(ms+flip): 79.71
-  Config: configs/ocrnet/ocrnet_hr48_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_40k_voc12aug/ocrnet_hr48_512x512_40k_voc12aug_20200614_015958-255bc5ce.pth
diff --git a/configs/pidnet/README.md b/configs/pidnet/README.md
index 545b76e8b0..c8c3f24799 100644
--- a/configs/pidnet/README.md
+++ b/configs/pidnet/README.md
@@ -26,11 +26,11 @@ Two-branch network architecture has shown its efficiency and effectiveness for r
 
 ### Cityscapes
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------- | -------- | -------------- | ----- | ------------- | ----------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PIDNet | PIDNet-S | 1024x1024 | 120000  | 3.38     | 80.82          | 78.74 | 80.87         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700-bb8e3bcc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700.json) |
-| PIDNet | PIDNet-M | 1024x1024 | 120000  | 5.14     | 71.98          | 80.22 | 82.05         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452-f9bcdbf3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452.json) |
-| PIDNet | PIDNet-L | 1024x1024 | 120000  | 5.83     | 60.06          | 80.89 | 82.37         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514-0783ca6b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | ----------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PIDNet | PIDNet-S | 1024x1024 | 120000  | 3.38     | 80.82          | A100   | 78.74 | 80.87         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700-bb8e3bcc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700.json) |
+| PIDNet | PIDNet-M | 1024x1024 | 120000  | 5.14     | 71.98          | A100   | 80.22 | 82.05         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452-f9bcdbf3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452.json) |
+| PIDNet | PIDNet-L | 1024x1024 | 120000  | 5.83     | 60.06          | A100   | 80.89 | 82.37         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514-0783ca6b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514.json) |
 
 ## Notes
 
diff --git a/configs/pidnet/metafile.yaml b/configs/pidnet/metafile.yaml
new file mode 100644
index 0000000000..9102ec51c5
--- /dev/null
+++ b/configs/pidnet/metafile.yaml
@@ -0,0 +1,85 @@
+Collections:
+- Name: PIDNet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+  Paper:
+    Title: 'PIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller'
+    URL: https://arxiv.org/pdf/2206.02066.pdf
+  README: configs/pidnet/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: pidnet-s_2xb6-120k_1024x1024-cityscapes
+  In Collection: PIDNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.74
+      mIoU(ms+flip): 80.87
+  Config: configs/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 12
+    Architecture:
+    - PIDNet-S
+    - PIDNet
+    Training Resources: 2x A100 GPUS
+    Memory (GB): 3.38
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700-bb8e3bcc.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700.json
+  Paper:
+    Title: 'PIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller'
+    URL: https://arxiv.org/pdf/2206.02066.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/pidnet.py
+  Framework: PyTorch
+- Name: pidnet-m_2xb6-120k_1024x1024-cityscapes
+  In Collection: PIDNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.22
+      mIoU(ms+flip): 82.05
+  Config: configs/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 12
+    Architecture:
+    - PIDNet-M
+    - PIDNet
+    Training Resources: 2x A100 GPUS
+    Memory (GB): 5.14
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452-f9bcdbf3.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452.json
+  Paper:
+    Title: 'PIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller'
+    URL: https://arxiv.org/pdf/2206.02066.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/pidnet.py
+  Framework: PyTorch
+- Name: pidnet-l_2xb6-120k_1024x1024-cityscapes
+  In Collection: PIDNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.89
+      mIoU(ms+flip): 82.37
+  Config: configs/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 12
+    Architecture:
+    - PIDNet-L
+    - PIDNet
+    Training Resources: 2x A100 GPUS
+    Memory (GB): 5.83
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514-0783ca6b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514.json
+  Paper:
+    Title: 'PIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller'
+    URL: https://arxiv.org/pdf/2206.02066.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/pidnet.py
+  Framework: PyTorch
diff --git a/configs/pidnet/pidnet.yml b/configs/pidnet/pidnet.yml
deleted file mode 100644
index 7fe818ca7c..0000000000
--- a/configs/pidnet/pidnet.yml
+++ /dev/null
@@ -1,81 +0,0 @@
-Collections:
-- Name: PIDNet
-  Metadata:
-    Training Data:
-    - Cityscapes
-  Paper:
-    URL: https://arxiv.org/pdf/2206.02066.pdf
-    Title: 'PIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller'
-  README: configs/pidnet/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/pidnet.py
-    Version: dev-1.x
-  Converted From:
-    Code: https://github.com/XuJiacong/PIDNet
-Models:
-- Name: pidnet-s_2xb6-120k_1024x1024-cityscapes
-  In Collection: PIDNet
-  Metadata:
-    backbone: PIDNet-S
-    crop size: (1024,1024)
-    lr schd: 120000
-    inference time (ms/im):
-    - value: 12.37
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (1024,1024)
-    Training Memory (GB): 3.38
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.74
-      mIoU(ms+flip): 80.87
-  Config: configs/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700-bb8e3bcc.pth
-- Name: pidnet-m_2xb6-120k_1024x1024-cityscapes
-  In Collection: PIDNet
-  Metadata:
-    backbone: PIDNet-M
-    crop size: (1024,1024)
-    lr schd: 120000
-    inference time (ms/im):
-    - value: 13.89
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (1024,1024)
-    Training Memory (GB): 5.14
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.22
-      mIoU(ms+flip): 82.05
-  Config: configs/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452-f9bcdbf3.pth
-- Name: pidnet-l_2xb6-120k_1024x1024-cityscapes
-  In Collection: PIDNet
-  Metadata:
-    backbone: PIDNet-L
-    crop size: (1024,1024)
-    lr schd: 120000
-    inference time (ms/im):
-    - value: 16.65
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (1024,1024)
-    Training Memory (GB): 5.83
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.89
-      mIoU(ms+flip): 82.37
-  Config: configs/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514-0783ca6b.pth
diff --git a/configs/point_rend/README.md b/configs/point_rend/README.md
index 2690e7b9e6..9aab8e03ee 100644
--- a/configs/point_rend/README.md
+++ b/configs/point_rend/README.md
@@ -1,6 +1,6 @@
 # PointRend
 
-[PointRend: Image Segmentation as Rendering](https://arxiv.org/abs/1912.08193)
+> [PointRend: Image Segmentation as Rendering](https://arxiv.org/abs/1912.08193)
 
 ## Introduction
 
@@ -22,6 +22,22 @@ We present a new method for efficient high-quality image segmentation of objects
 <img src="https://user-images.githubusercontent.com/24582831/142902293-5db49cdd-4b1b-4940-9067-2acd6196c700.png" width="60%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                | download                                                                                                                                                                                                                                                                                                                                                         |
+| --------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PointRend | R-50     | 512x1024  |   80000 |      3.1 | 8.48           | V100   | 76.47 | 78.13         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/point_rend/pointrend_r50_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x1024_80k_cityscapes/pointrend_r50_512x1024_80k_cityscapes_20200711_015821-bb1ff523.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x1024_80k_cityscapes/pointrend_r50_512x1024_80k_cityscapes-20200715_214714.log.json)     |
+| PointRend | R-101    | 512x1024  |   80000 |      4.2 | 7.00           | V100   | 78.30 | 79.97         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/point_rend/pointrend_r101_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x1024_80k_cityscapes/pointrend_r101_512x1024_80k_cityscapes_20200711_170850-d0ca84be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x1024_80k_cityscapes/pointrend_r101_512x1024_80k_cityscapes-20200715_214824.log.json) |
+
+### ADE20K
+
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                         |
+| --------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| PointRend | R-50     | 512x512   |  160000 |      5.1 | 17.31          | V100   | 37.64 | 39.17         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/point_rend/pointrend_r50_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x512_160k_ade20k/pointrend_r50_512x512_160k_ade20k_20200807_232644-ac3febf2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x512_160k_ade20k/pointrend_r50_512x512_160k_ade20k-20200807_232644.log.json)     |
+| PointRend | R-101    | 512x512   |  160000 |      6.1 | 15.50          | V100   | 40.02 | 41.60         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/point_rend/pointrend_r101_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x512_160k_ade20k/pointrend_r101_512x512_160k_ade20k_20200808_030852-8834902a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x512_160k_ade20k/pointrend_r101_512x512_160k_ade20k-20200808_030852.log.json) |
+
 ## Citation
 
 ```bibtex
@@ -33,19 +49,3 @@ We present a new method for efficient high-quality image segmentation of objects
   year={2020}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                | download                                                                                                                                                                                                                                                                                                                                                         |
-| --------- | -------- | --------- | ------: | -------: | -------------- | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PointRend | R-50     | 512x1024  |   80000 |      3.1 | 8.48           | 76.47 | 78.13         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/point_rend/pointrend_r50_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x1024_80k_cityscapes/pointrend_r50_512x1024_80k_cityscapes_20200711_015821-bb1ff523.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x1024_80k_cityscapes/pointrend_r50_512x1024_80k_cityscapes-20200715_214714.log.json)     |
-| PointRend | R-101    | 512x1024  |   80000 |      4.2 | 7.00           | 78.30 | 79.97         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/point_rend/pointrend_r101_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x1024_80k_cityscapes/pointrend_r101_512x1024_80k_cityscapes_20200711_170850-d0ca84be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x1024_80k_cityscapes/pointrend_r101_512x1024_80k_cityscapes-20200715_214824.log.json) |
-
-### ADE20K
-
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                         |
-| --------- | -------- | --------- | ------: | -------: | -------------- | ----: | ------------- | --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| PointRend | R-50     | 512x512   |  160000 |      5.1 | 17.31          | 37.64 | 39.17         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/point_rend/pointrend_r50_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x512_160k_ade20k/pointrend_r50_512x512_160k_ade20k_20200807_232644-ac3febf2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x512_160k_ade20k/pointrend_r50_512x512_160k_ade20k-20200807_232644.log.json)     |
-| PointRend | R-101    | 512x512   |  160000 |      6.1 | 15.50          | 40.02 | 41.60         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/point_rend/pointrend_r101_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x512_160k_ade20k/pointrend_r101_512x512_160k_ade20k_20200808_030852-8834902a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x512_160k_ade20k/pointrend_r101_512x512_160k_ade20k-20200808_030852.log.json) |
diff --git a/configs/point_rend/metafile.yaml b/configs/point_rend/metafile.yaml
new file mode 100644
index 0000000000..064717c9df
--- /dev/null
+++ b/configs/point_rend/metafile.yaml
@@ -0,0 +1,110 @@
+Collections:
+- Name: PointRend
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - ADE20K
+  Paper:
+    Title: 'PointRend: Image Segmentation as Rendering'
+    URL: https://arxiv.org/abs/1912.08193
+  README: configs/point_rend/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: pointrend_r50_4xb2-80k_cityscapes-512x1024
+  In Collection: PointRend
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.47
+      mIoU(ms+flip): 78.13
+  Config: configs/point_rend/pointrend_r50_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50
+    - PointRend
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 3.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x1024_80k_cityscapes/pointrend_r50_512x1024_80k_cityscapes_20200711_015821-bb1ff523.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x1024_80k_cityscapes/pointrend_r50_512x1024_80k_cityscapes-20200715_214714.log.json
+  Paper:
+    Title: 'PointRend: Image Segmentation as Rendering'
+    URL: https://arxiv.org/abs/1912.08193
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/point_head.py#L36
+  Framework: PyTorch
+- Name: pointrend_r101_4xb2-80k_cityscapes-512x1024
+  In Collection: PointRend
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.3
+      mIoU(ms+flip): 79.97
+  Config: configs/point_rend/pointrend_r101_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101
+    - PointRend
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 4.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x1024_80k_cityscapes/pointrend_r101_512x1024_80k_cityscapes_20200711_170850-d0ca84be.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x1024_80k_cityscapes/pointrend_r101_512x1024_80k_cityscapes-20200715_214824.log.json
+  Paper:
+    Title: 'PointRend: Image Segmentation as Rendering'
+    URL: https://arxiv.org/abs/1912.08193
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/point_head.py#L36
+  Framework: PyTorch
+- Name: pointrend_r50_4xb4-160k_ade20k-512x512
+  In Collection: PointRend
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 37.64
+      mIoU(ms+flip): 39.17
+  Config: configs/point_rend/pointrend_r50_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50
+    - PointRend
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x512_160k_ade20k/pointrend_r50_512x512_160k_ade20k_20200807_232644-ac3febf2.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x512_160k_ade20k/pointrend_r50_512x512_160k_ade20k-20200807_232644.log.json
+  Paper:
+    Title: 'PointRend: Image Segmentation as Rendering'
+    URL: https://arxiv.org/abs/1912.08193
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/point_head.py#L36
+  Framework: PyTorch
+- Name: pointrend_r101_4xb4-160k_ade20k-512x512
+  In Collection: PointRend
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 40.02
+      mIoU(ms+flip): 41.6
+  Config: configs/point_rend/pointrend_r101_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101
+    - PointRend
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x512_160k_ade20k/pointrend_r101_512x512_160k_ade20k_20200808_030852-8834902a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x512_160k_ade20k/pointrend_r101_512x512_160k_ade20k-20200808_030852.log.json
+  Paper:
+    Title: 'PointRend: Image Segmentation as Rendering'
+    URL: https://arxiv.org/abs/1912.08193
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/point_head.py#L36
+  Framework: PyTorch
diff --git a/configs/point_rend/point_rend.yml b/configs/point_rend/point_rend.yml
deleted file mode 100644
index a4539081f3..0000000000
--- a/configs/point_rend/point_rend.yml
+++ /dev/null
@@ -1,104 +0,0 @@
-Collections:
-- Name: PointRend
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-  Paper:
-    URL: https://arxiv.org/abs/1912.08193
-    Title: 'PointRend: Image Segmentation as Rendering'
-  README: configs/point_rend/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/point_head.py#L36
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/facebookresearch/detectron2/tree/master/projects/PointRend
-Models:
-- Name: pointrend_r50_4xb2-80k_cityscapes-512x1024
-  In Collection: PointRend
-  Metadata:
-    backbone: R-50
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 117.92
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 3.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.47
-      mIoU(ms+flip): 78.13
-  Config: configs/point_rend/pointrend_r50_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x1024_80k_cityscapes/pointrend_r50_512x1024_80k_cityscapes_20200711_015821-bb1ff523.pth
-- Name: pointrend_r101_4xb2-80k_cityscapes-512x1024
-  In Collection: PointRend
-  Metadata:
-    backbone: R-101
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 142.86
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 4.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.3
-      mIoU(ms+flip): 79.97
-  Config: configs/point_rend/pointrend_r101_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x1024_80k_cityscapes/pointrend_r101_512x1024_80k_cityscapes_20200711_170850-d0ca84be.pth
-- Name: pointrend_r50_4xb4-160k_ade20k-512x512
-  In Collection: PointRend
-  Metadata:
-    backbone: R-50
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 57.77
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 5.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 37.64
-      mIoU(ms+flip): 39.17
-  Config: configs/point_rend/pointrend_r50_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x512_160k_ade20k/pointrend_r50_512x512_160k_ade20k_20200807_232644-ac3febf2.pth
-- Name: pointrend_r101_4xb4-160k_ade20k-512x512
-  In Collection: PointRend
-  Metadata:
-    backbone: R-101
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 64.52
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 40.02
-      mIoU(ms+flip): 41.6
-  Config: configs/point_rend/pointrend_r101_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x512_160k_ade20k/pointrend_r101_512x512_160k_ade20k_20200808_030852-8834902a.pth
diff --git a/configs/poolformer/README.md b/configs/poolformer/README.md
index 3bdd2ba3f1..ba563a9928 100644
--- a/configs/poolformer/README.md
+++ b/configs/poolformer/README.md
@@ -1,6 +1,6 @@
 # PoolFormer
 
-[MetaFormer is Actually What You Need for Vision](https://arxiv.org/abs/2111.11418)
+> [MetaFormer is Actually What You Need for Vision](https://arxiv.org/abs/2111.11418)
 
 ## Introduction
 
@@ -48,13 +48,13 @@ pip install "mmcls>=1.0.0rc0"
 
 ### ADE20K
 
-| Method | Backbone       | Crop Size | pretrain    | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) | mIoU\* | mIoU\*(ms+flip) | config                                                                                                                               | download                                                                                                                                                                                                                                                                                                                                                                     |
-| ------ | -------------- | --------- | ----------- | ---------- | ------- | -------- | -------------- | ----- | ------------: | ------ | --------------: | ------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FPN    | PoolFormer-S12 | 512x512   | ImageNet-1K | 32         | 40000   | 4.17     | 23.48          | 36.68 |             - | 37.07  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/poolformer/fpn_poolformer_s12_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k/fpn_poolformer_s12_8x4_512x512_40k_ade20k_20220501_115154-b5aa2f49.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k/fpn_poolformer_s12_8x4_512x512_40k_ade20k_20220501_115154.log.json) |
-| FPN    | PoolFormer-S24 | 512x512   | ImageNet-1K | 32         | 40000   | 5.47     | 15.74          | 40.12 |             - | 40.36  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/poolformer/fpn_poolformer_s24_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k/fpn_poolformer_s24_8x4_512x512_40k_ade20k_20220503_222049-394a7cf7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k/fpn_poolformer_s24_8x4_512x512_40k_ade20k_20220503_222049.log.json) |
-| FPN    | PoolFormer-S36 | 512x512   | ImageNet-1K | 32         | 40000   | 6.77     | 11.34          | 41.61 |             - | 41.81  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/poolformer/fpn_poolformer_s36_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s36_8x4_512x512_40k_ade20k/fpn_poolformer_s36_8x4_512x512_40k_ade20k_20220501_151122-b47e607d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s36_8x4_512x512_40k_ade20k/fpn_poolformer_s36_8x4_512x512_40k_ade20k_20220501_151122.log.json) |
-| FPN    | PoolFormer-M36 | 512x512   | ImageNet-1K | 32         | 40000   | 8.59     | 8.97           | 41.95 |             - | 42.35  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/poolformer/fpn_poolformer_m36_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k/fpn_poolformer_m36_8x4_512x512_40k_ade20k_20220501_164230-3dc83921.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k/fpn_poolformer_m36_8x4_512x512_40k_ade20k_20220501_164230.log.json) |
-| FPN    | PoolFormer-M48 | 512x512   | ImageNet-1K | 32         | 40000   | 10.48    | 6.69           | 42.43 |             - | 42.76  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/poolformer/fpn_poolformer_m48_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k/fpn_poolformer_m48_8x4_512x512_40k_ade20k_20220504_003923-64168d3b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k/fpn_poolformer_m48_8x4_512x512_40k_ade20k_20220504_003923.log.json) |
+| Method | Backbone       | Crop Size | pretrain    | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | mIoU\* | mIoU\*(ms+flip) | config                                                                                                                               | download                                                                                                                                                                                                                                                                                                                                                                     |
+| ------ | -------------- | --------- | ----------- | ---------- | ------- | -------- | -------------- | ------ | ----- | ------------: | ------ | --------------: | ------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FPN    | PoolFormer-S12 | 512x512   | ImageNet-1K | 32         | 40000   | 4.17     | 23.48          | V100   | 36.68 |             - | 37.07  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/poolformer/fpn_poolformer_s12_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k/fpn_poolformer_s12_8x4_512x512_40k_ade20k_20220501_115154-b5aa2f49.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k/fpn_poolformer_s12_8x4_512x512_40k_ade20k_20220501_115154.log.json) |
+| FPN    | PoolFormer-S24 | 512x512   | ImageNet-1K | 32         | 40000   | 5.47     | 15.74          | V100   | 40.12 |             - | 40.36  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/poolformer/fpn_poolformer_s24_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k/fpn_poolformer_s24_8x4_512x512_40k_ade20k_20220503_222049-394a7cf7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k/fpn_poolformer_s24_8x4_512x512_40k_ade20k_20220503_222049.log.json) |
+| FPN    | PoolFormer-S36 | 512x512   | ImageNet-1K | 32         | 40000   | 6.77     | 11.34          | V100   | 41.61 |             - | 41.81  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/poolformer/fpn_poolformer_s36_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s36_8x4_512x512_40k_ade20k/fpn_poolformer_s36_8x4_512x512_40k_ade20k_20220501_151122-b47e607d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s36_8x4_512x512_40k_ade20k/fpn_poolformer_s36_8x4_512x512_40k_ade20k_20220501_151122.log.json) |
+| FPN    | PoolFormer-M36 | 512x512   | ImageNet-1K | 32         | 40000   | 8.59     | 8.97           | V100   | 41.95 |             - | 42.35  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/poolformer/fpn_poolformer_m36_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k/fpn_poolformer_m36_8x4_512x512_40k_ade20k_20220501_164230-3dc83921.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k/fpn_poolformer_m36_8x4_512x512_40k_ade20k_20220501_164230.log.json) |
+| FPN    | PoolFormer-M48 | 512x512   | ImageNet-1K | 32         | 40000   | 10.48    | 6.69           | V100   | 42.43 |             - | 42.76  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/poolformer/fpn_poolformer_m48_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k/fpn_poolformer_m48_8x4_512x512_40k_ade20k_20220504_003923-64168d3b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k/fpn_poolformer_m48_8x4_512x512_40k_ade20k_20220504_003923.log.json) |
 
 Note:
 
diff --git a/configs/poolformer/metafile.yaml b/configs/poolformer/metafile.yaml
new file mode 100644
index 0000000000..12f402be65
--- /dev/null
+++ b/configs/poolformer/metafile.yaml
@@ -0,0 +1,116 @@
+Models:
+- Name: fpn_poolformer_s12_8xb4-40k_ade20k-512x512
+  In Collection: FPN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 36.68
+  Config: configs/poolformer/fpn_poolformer_s12_8xb4-40k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 32
+    Architecture:
+    - PoolFormer-S12
+    - FPN
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 4.17
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k/fpn_poolformer_s12_8x4_512x512_40k_ade20k_20220501_115154-b5aa2f49.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k/fpn_poolformer_s12_8x4_512x512_40k_ade20k_20220501_115154.log.json
+  Paper:
+    Title: MetaFormer is Actually What You Need for Vision
+    URL: https://arxiv.org/abs/2111.11418
+  Code: https://github.com/open-mmlab/mmclassification/blob/v0.23.0/mmcls/models/backbones/poolformer.py#L198
+  Framework: PyTorch
+- Name: fpn_poolformer_s24_8xb4-40k_ade20k-512x512
+  In Collection: FPN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 40.12
+  Config: configs/poolformer/fpn_poolformer_s24_8xb4-40k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 32
+    Architecture:
+    - PoolFormer-S24
+    - FPN
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 5.47
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k/fpn_poolformer_s24_8x4_512x512_40k_ade20k_20220503_222049-394a7cf7.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k/fpn_poolformer_s24_8x4_512x512_40k_ade20k_20220503_222049.log.json
+  Paper:
+    Title: MetaFormer is Actually What You Need for Vision
+    URL: https://arxiv.org/abs/2111.11418
+  Code: https://github.com/open-mmlab/mmclassification/blob/v0.23.0/mmcls/models/backbones/poolformer.py#L198
+  Framework: PyTorch
+- Name: fpn_poolformer_s36_8xb4-40k_ade20k-512x512
+  In Collection: FPN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 41.61
+  Config: configs/poolformer/fpn_poolformer_s36_8xb4-40k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 32
+    Architecture:
+    - PoolFormer-S36
+    - FPN
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 6.77
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s36_8x4_512x512_40k_ade20k/fpn_poolformer_s36_8x4_512x512_40k_ade20k_20220501_151122-b47e607d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s36_8x4_512x512_40k_ade20k/fpn_poolformer_s36_8x4_512x512_40k_ade20k_20220501_151122.log.json
+  Paper:
+    Title: MetaFormer is Actually What You Need for Vision
+    URL: https://arxiv.org/abs/2111.11418
+  Code: https://github.com/open-mmlab/mmclassification/blob/v0.23.0/mmcls/models/backbones/poolformer.py#L198
+  Framework: PyTorch
+- Name: fpn_poolformer_m36_8xb4-40k_ade20k-512x512
+  In Collection: FPN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 41.95
+  Config: configs/poolformer/fpn_poolformer_m36_8xb4-40k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 32
+    Architecture:
+    - PoolFormer-M36
+    - FPN
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 8.59
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k/fpn_poolformer_m36_8x4_512x512_40k_ade20k_20220501_164230-3dc83921.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k/fpn_poolformer_m36_8x4_512x512_40k_ade20k_20220501_164230.log.json
+  Paper:
+    Title: MetaFormer is Actually What You Need for Vision
+    URL: https://arxiv.org/abs/2111.11418
+  Code: https://github.com/open-mmlab/mmclassification/blob/v0.23.0/mmcls/models/backbones/poolformer.py#L198
+  Framework: PyTorch
+- Name: fpn_poolformer_m48_8xb4-40k_ade20k-512x512
+  In Collection: FPN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.43
+  Config: configs/poolformer/fpn_poolformer_m48_8xb4-40k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 32
+    Architecture:
+    - PoolFormer-M48
+    - FPN
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 10.48
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k/fpn_poolformer_m48_8x4_512x512_40k_ade20k_20220504_003923-64168d3b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k/fpn_poolformer_m48_8x4_512x512_40k_ade20k_20220504_003923.log.json
+  Paper:
+    Title: MetaFormer is Actually What You Need for Vision
+    URL: https://arxiv.org/abs/2111.11418
+  Code: https://github.com/open-mmlab/mmclassification/blob/v0.23.0/mmcls/models/backbones/poolformer.py#L198
+  Framework: PyTorch
diff --git a/configs/poolformer/poolformer.yml b/configs/poolformer/poolformer.yml
deleted file mode 100644
index fa5fc30125..0000000000
--- a/configs/poolformer/poolformer.yml
+++ /dev/null
@@ -1,106 +0,0 @@
-Models:
-- Name: fpn_poolformer_s12_8xb4-40k_ade20k-512x512
-  In Collection: FPN
-  Metadata:
-    backbone: PoolFormer-S12
-    crop size: (512,512)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 42.59
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 4.17
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 36.68
-  Config: configs/poolformer/fpn_poolformer_s12_8xb4-40k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k/fpn_poolformer_s12_8x4_512x512_40k_ade20k_20220501_115154-b5aa2f49.pth
-- Name: fpn_poolformer_s24_8xb4-40k_ade20k-512x512
-  In Collection: FPN
-  Metadata:
-    backbone: PoolFormer-S24
-    crop size: (512,512)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 63.53
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 5.47
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 40.12
-  Config: configs/poolformer/fpn_poolformer_s24_8xb4-40k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k/fpn_poolformer_s24_8x4_512x512_40k_ade20k_20220503_222049-394a7cf7.pth
-- Name: ''
-  In Collection: FPN
-  Metadata:
-    backbone: PoolFormer-S36
-    crop size: (512,512)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 88.18
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.77
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 41.61
-  Config: ''
-  Weights: ''
-- Name: fpn_poolformer_m36_8xb4-40k_ade20k-512x512
-  In Collection: FPN
-  Metadata:
-    backbone: PoolFormer-M36
-    crop size: (512,512)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 111.48
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 8.59
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 41.95
-  Config: configs/poolformer/fpn_poolformer_m36_8xb4-40k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k/fpn_poolformer_m36_8x4_512x512_40k_ade20k_20220501_164230-3dc83921.pth
-- Name: fpn_poolformer_m48_8xb4-40k_ade20k-512x512
-  In Collection: FPN
-  Metadata:
-    backbone: PoolFormer-M48
-    crop size: (512,512)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 149.48
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 10.48
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.43
-  Config: configs/poolformer/fpn_poolformer_m48_8xb4-40k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k/fpn_poolformer_m48_8x4_512x512_40k_ade20k_20220504_003923-64168d3b.pth
diff --git a/configs/psanet/README.md b/configs/psanet/README.md
index 7182e500a1..d657326120 100644
--- a/configs/psanet/README.md
+++ b/configs/psanet/README.md
@@ -1,6 +1,6 @@
 # PSANet
 
-[PSANet: Point-wise Spatial Attention Network for Scene Parsing](https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf)
+> [PSANet: Point-wise Spatial Attention Network for Scene Parsing](https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf)
 
 ## Introduction
 
@@ -22,6 +22,39 @@ We notice information flow in convolutional neural networksis  restricted  insid
 <img src="https://user-images.githubusercontent.com/24582831/142902367-0f29e8cb-5ac0-434b-98c4-b2af7c9c2e58.png" width="70%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSANet | R-50-D8  | 512x1024  |   40000 | 7        | 3.17           | V100   | 77.63 |         79.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_40k_cityscapes/psanet_r50-d8_512x1024_40k_cityscapes_20200606_103117-99fac37c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_40k_cityscapes/psanet_r50-d8_512x1024_40k_cityscapes_20200606_103117.log.json)     |
+| PSANet | R-101-D8 | 512x1024  |   40000 | 10.5     | 2.20           | V100   | 79.14 |         80.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_40k_cityscapes/psanet_r101-d8_512x1024_40k_cityscapes_20200606_001418-27b9cfa7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_40k_cityscapes/psanet_r101-d8_512x1024_40k_cityscapes_20200606_001418.log.json) |
+| PSANet | R-50-D8  | 769x769   |   40000 | 7.9      | 1.40           | V100   | 77.99 |         79.64 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_40k_cityscapes/psanet_r50-d8_769x769_40k_cityscapes_20200530_033717-d5365506.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_40k_cityscapes/psanet_r50-d8_769x769_40k_cityscapes_20200530_033717.log.json)         |
+| PSANet | R-101-D8 | 769x769   |   40000 | 11.9     | 0.98           | V100   | 78.43 |         80.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_40k_cityscapes/psanet_r101-d8_769x769_40k_cityscapes_20200530_035107-997da1e6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_40k_cityscapes/psanet_r101-d8_769x769_40k_cityscapes_20200530_035107.log.json)     |
+| PSANet | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 77.24 |         78.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_80k_cityscapes/psanet_r50-d8_512x1024_80k_cityscapes_20200606_161842-ab60a24f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_80k_cityscapes/psanet_r50-d8_512x1024_80k_cityscapes_20200606_161842.log.json)     |
+| PSANet | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 79.31 |         80.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_80k_cityscapes/psanet_r101-d8_512x1024_80k_cityscapes_20200606_161823-0f73a169.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_80k_cityscapes/psanet_r101-d8_512x1024_80k_cityscapes_20200606_161823.log.json) |
+| PSANet | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 79.31 |         80.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_80k_cityscapes/psanet_r50-d8_769x769_80k_cityscapes_20200606_225134-fe42f49e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_80k_cityscapes/psanet_r50-d8_769x769_80k_cityscapes_20200606_225134.log.json)         |
+| PSANet | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 79.69 |         80.89 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_80k_cityscapes/psanet_r101-d8_769x769_80k_cityscapes_20200606_214550-7665827b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_80k_cityscapes/psanet_r101-d8_769x769_80k_cityscapes_20200606_214550.log.json)     |
+
+### ADE20K
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSANet | R-50-D8  | 512x512   |   80000 | 9        | 18.91          | V100   | 41.14 |         41.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_80k_ade20k/psanet_r50-d8_512x512_80k_ade20k_20200614_144141-835e4b97.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_80k_ade20k/psanet_r50-d8_512x512_80k_ade20k_20200614_144141.log.json)         |
+| PSANet | R-101-D8 | 512x512   |   80000 | 12.5     | 13.13          | V100   | 43.80 |         44.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_80k_ade20k/psanet_r101-d8_512x512_80k_ade20k_20200614_185117-1fab60d4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_80k_ade20k/psanet_r101-d8_512x512_80k_ade20k_20200614_185117.log.json)     |
+| PSANet | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 41.67 |         42.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_160k_ade20k/psanet_r50-d8_512x512_160k_ade20k_20200615_161258-148077dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_160k_ade20k/psanet_r50-d8_512x512_160k_ade20k_20200615_161258.log.json)     |
+| PSANet | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 43.74 |         45.38 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_160k_ade20k/psanet_r101-d8_512x512_160k_ade20k_20200615_161537-dbfa564c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_160k_ade20k/psanet_r101-d8_512x512_160k_ade20k_20200615_161537.log.json) |
+
+### Pascal VOC 2012 + Aug
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                     |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSANet | R-50-D8  | 512x512   |   20000 | 6.9      | 18.24          | V100   | 76.39 |         77.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_20k_voc12aug/psanet_r50-d8_512x512_20k_voc12aug_20200617_102413-2f1bbaa1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_20k_voc12aug/psanet_r50-d8_512x512_20k_voc12aug_20200617_102413.log.json)     |
+| PSANet | R-101-D8 | 512x512   |   20000 | 10.4     | 12.63          | V100   | 77.91 |         79.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_20k_voc12aug/psanet_r101-d8_512x512_20k_voc12aug_20200617_110624-946fef11.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_20k_voc12aug/psanet_r101-d8_512x512_20k_voc12aug_20200617_110624.log.json) |
+| PSANet | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 76.30 |         77.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_40k_voc12aug/psanet_r50-d8_512x512_40k_voc12aug_20200613_161946-f596afb5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_40k_voc12aug/psanet_r50-d8_512x512_40k_voc12aug_20200613_161946.log.json)     |
+| PSANet | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 77.73 |         79.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_40k_voc12aug/psanet_r101-d8_512x512_40k_voc12aug_20200613_161946-1f560f9e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_40k_voc12aug/psanet_r101-d8_512x512_40k_voc12aug_20200613_161946.log.json) |
+
 ## Citation
 
 ```bibtex
@@ -33,36 +66,3 @@ We notice information flow in convolutional neural networksis  restricted  insid
   year={2018}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSANet | R-50-D8  | 512x1024  |   40000 | 7        | 3.17           | 77.63 |         79.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_40k_cityscapes/psanet_r50-d8_512x1024_40k_cityscapes_20200606_103117-99fac37c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_40k_cityscapes/psanet_r50-d8_512x1024_40k_cityscapes_20200606_103117.log.json)     |
-| PSANet | R-101-D8 | 512x1024  |   40000 | 10.5     | 2.20           | 79.14 |         80.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_40k_cityscapes/psanet_r101-d8_512x1024_40k_cityscapes_20200606_001418-27b9cfa7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_40k_cityscapes/psanet_r101-d8_512x1024_40k_cityscapes_20200606_001418.log.json) |
-| PSANet | R-50-D8  | 769x769   |   40000 | 7.9      | 1.40           | 77.99 |         79.64 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_40k_cityscapes/psanet_r50-d8_769x769_40k_cityscapes_20200530_033717-d5365506.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_40k_cityscapes/psanet_r50-d8_769x769_40k_cityscapes_20200530_033717.log.json)         |
-| PSANet | R-101-D8 | 769x769   |   40000 | 11.9     | 0.98           | 78.43 |         80.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_40k_cityscapes/psanet_r101-d8_769x769_40k_cityscapes_20200530_035107-997da1e6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_40k_cityscapes/psanet_r101-d8_769x769_40k_cityscapes_20200530_035107.log.json)     |
-| PSANet | R-50-D8  | 512x1024  |   80000 | -        | -              | 77.24 |         78.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_80k_cityscapes/psanet_r50-d8_512x1024_80k_cityscapes_20200606_161842-ab60a24f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_80k_cityscapes/psanet_r50-d8_512x1024_80k_cityscapes_20200606_161842.log.json)     |
-| PSANet | R-101-D8 | 512x1024  |   80000 | -        | -              | 79.31 |         80.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_80k_cityscapes/psanet_r101-d8_512x1024_80k_cityscapes_20200606_161823-0f73a169.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_80k_cityscapes/psanet_r101-d8_512x1024_80k_cityscapes_20200606_161823.log.json) |
-| PSANet | R-50-D8  | 769x769   |   80000 | -        | -              | 79.31 |         80.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_80k_cityscapes/psanet_r50-d8_769x769_80k_cityscapes_20200606_225134-fe42f49e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_80k_cityscapes/psanet_r50-d8_769x769_80k_cityscapes_20200606_225134.log.json)         |
-| PSANet | R-101-D8 | 769x769   |   80000 | -        | -              | 79.69 |         80.89 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_80k_cityscapes/psanet_r101-d8_769x769_80k_cityscapes_20200606_214550-7665827b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_80k_cityscapes/psanet_r101-d8_769x769_80k_cityscapes_20200606_214550.log.json)     |
-
-### ADE20K
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSANet | R-50-D8  | 512x512   |   80000 | 9        | 18.91          | 41.14 |         41.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_80k_ade20k/psanet_r50-d8_512x512_80k_ade20k_20200614_144141-835e4b97.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_80k_ade20k/psanet_r50-d8_512x512_80k_ade20k_20200614_144141.log.json)         |
-| PSANet | R-101-D8 | 512x512   |   80000 | 12.5     | 13.13          | 43.80 |         44.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_80k_ade20k/psanet_r101-d8_512x512_80k_ade20k_20200614_185117-1fab60d4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_80k_ade20k/psanet_r101-d8_512x512_80k_ade20k_20200614_185117.log.json)     |
-| PSANet | R-50-D8  | 512x512   |  160000 | -        | -              | 41.67 |         42.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_160k_ade20k/psanet_r50-d8_512x512_160k_ade20k_20200615_161258-148077dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_160k_ade20k/psanet_r50-d8_512x512_160k_ade20k_20200615_161258.log.json)     |
-| PSANet | R-101-D8 | 512x512   |  160000 | -        | -              | 43.74 |         45.38 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_160k_ade20k/psanet_r101-d8_512x512_160k_ade20k_20200615_161537-dbfa564c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_160k_ade20k/psanet_r101-d8_512x512_160k_ade20k_20200615_161537.log.json) |
-
-### Pascal VOC 2012 + Aug
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                     |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSANet | R-50-D8  | 512x512   |   20000 | 6.9      | 18.24          | 76.39 |         77.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_20k_voc12aug/psanet_r50-d8_512x512_20k_voc12aug_20200617_102413-2f1bbaa1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_20k_voc12aug/psanet_r50-d8_512x512_20k_voc12aug_20200617_102413.log.json)     |
-| PSANet | R-101-D8 | 512x512   |   20000 | 10.4     | 12.63          | 77.91 |         79.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_20k_voc12aug/psanet_r101-d8_512x512_20k_voc12aug_20200617_110624-946fef11.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_20k_voc12aug/psanet_r101-d8_512x512_20k_voc12aug_20200617_110624.log.json) |
-| PSANet | R-50-D8  | 512x512   |   40000 | -        | -              | 76.30 |         77.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_40k_voc12aug/psanet_r50-d8_512x512_40k_voc12aug_20200613_161946-f596afb5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_40k_voc12aug/psanet_r50-d8_512x512_40k_voc12aug_20200613_161946.log.json)     |
-| PSANet | R-101-D8 | 512x512   |   40000 | -        | -              | 77.73 |         79.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_40k_voc12aug/psanet_r101-d8_512x512_40k_voc12aug_20200613_161946-1f560f9e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_40k_voc12aug/psanet_r101-d8_512x512_40k_voc12aug_20200613_161946.log.json) |
diff --git a/configs/psanet/metafile.yaml b/configs/psanet/metafile.yaml
new file mode 100644
index 0000000000..3fbe6f6d3e
--- /dev/null
+++ b/configs/psanet/metafile.yaml
@@ -0,0 +1,391 @@
+Collections:
+- Name: PSANet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - ADE20K
+    - Pascal VOC 2012 + Aug
+  Paper:
+    Title: 'PSANet: Point-wise Spatial Attention Network for Scene Parsing'
+    URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf
+  README: configs/psanet/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: psanet_r50-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: PSANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.63
+      mIoU(ms+flip): 79.04
+  Config: configs/psanet/psanet_r50-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - PSANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_40k_cityscapes/psanet_r50-d8_512x1024_40k_cityscapes_20200606_103117-99fac37c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_40k_cityscapes/psanet_r50-d8_512x1024_40k_cityscapes_20200606_103117.log.json
+  Paper:
+    Title: 'PSANet: Point-wise Spatial Attention Network for Scene Parsing'
+    URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psa_head.py#L18
+  Framework: PyTorch
+- Name: psanet_r101-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: PSANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.14
+      mIoU(ms+flip): 80.19
+  Config: configs/psanet/psanet_r101-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - PSANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_40k_cityscapes/psanet_r101-d8_512x1024_40k_cityscapes_20200606_001418-27b9cfa7.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_40k_cityscapes/psanet_r101-d8_512x1024_40k_cityscapes_20200606_001418.log.json
+  Paper:
+    Title: 'PSANet: Point-wise Spatial Attention Network for Scene Parsing'
+    URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psa_head.py#L18
+  Framework: PyTorch
+- Name: psanet_r50-d8_4xb2-40k_cityscapes-769x769
+  In Collection: PSANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.99
+      mIoU(ms+flip): 79.64
+  Config: configs/psanet/psanet_r50-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - PSANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_40k_cityscapes/psanet_r50-d8_769x769_40k_cityscapes_20200530_033717-d5365506.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_40k_cityscapes/psanet_r50-d8_769x769_40k_cityscapes_20200530_033717.log.json
+  Paper:
+    Title: 'PSANet: Point-wise Spatial Attention Network for Scene Parsing'
+    URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psa_head.py#L18
+  Framework: PyTorch
+- Name: psanet_r101-d8_4xb2-40k_cityscapes-769x769
+  In Collection: PSANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.43
+      mIoU(ms+flip): 80.26
+  Config: configs/psanet/psanet_r101-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - PSANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 11.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_40k_cityscapes/psanet_r101-d8_769x769_40k_cityscapes_20200530_035107-997da1e6.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_40k_cityscapes/psanet_r101-d8_769x769_40k_cityscapes_20200530_035107.log.json
+  Paper:
+    Title: 'PSANet: Point-wise Spatial Attention Network for Scene Parsing'
+    URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psa_head.py#L18
+  Framework: PyTorch
+- Name: psanet_r50-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: PSANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.24
+      mIoU(ms+flip): 78.69
+  Config: configs/psanet/psanet_r50-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - PSANet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_80k_cityscapes/psanet_r50-d8_512x1024_80k_cityscapes_20200606_161842-ab60a24f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_80k_cityscapes/psanet_r50-d8_512x1024_80k_cityscapes_20200606_161842.log.json
+  Paper:
+    Title: 'PSANet: Point-wise Spatial Attention Network for Scene Parsing'
+    URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psa_head.py#L18
+  Framework: PyTorch
+- Name: psanet_r101-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: PSANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.31
+      mIoU(ms+flip): 80.53
+  Config: configs/psanet/psanet_r101-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - PSANet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_80k_cityscapes/psanet_r101-d8_512x1024_80k_cityscapes_20200606_161823-0f73a169.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_80k_cityscapes/psanet_r101-d8_512x1024_80k_cityscapes_20200606_161823.log.json
+  Paper:
+    Title: 'PSANet: Point-wise Spatial Attention Network for Scene Parsing'
+    URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psa_head.py#L18
+  Framework: PyTorch
+- Name: psanet_r50-d8_4xb2-80k_cityscapes-769x769
+  In Collection: PSANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.31
+      mIoU(ms+flip): 80.91
+  Config: configs/psanet/psanet_r50-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - PSANet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_80k_cityscapes/psanet_r50-d8_769x769_80k_cityscapes_20200606_225134-fe42f49e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_80k_cityscapes/psanet_r50-d8_769x769_80k_cityscapes_20200606_225134.log.json
+  Paper:
+    Title: 'PSANet: Point-wise Spatial Attention Network for Scene Parsing'
+    URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psa_head.py#L18
+  Framework: PyTorch
+- Name: psanet_r101-d8_4xb2-80k_cityscapes-769x769
+  In Collection: PSANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.69
+      mIoU(ms+flip): 80.89
+  Config: configs/psanet/psanet_r101-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - PSANet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_80k_cityscapes/psanet_r101-d8_769x769_80k_cityscapes_20200606_214550-7665827b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_80k_cityscapes/psanet_r101-d8_769x769_80k_cityscapes_20200606_214550.log.json
+  Paper:
+    Title: 'PSANet: Point-wise Spatial Attention Network for Scene Parsing'
+    URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psa_head.py#L18
+  Framework: PyTorch
+- Name: psanet_r50-d8_4xb4-80k_ade20k-512x512
+  In Collection: PSANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 41.14
+      mIoU(ms+flip): 41.91
+  Config: configs/psanet/psanet_r50-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - PSANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_80k_ade20k/psanet_r50-d8_512x512_80k_ade20k_20200614_144141-835e4b97.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_80k_ade20k/psanet_r50-d8_512x512_80k_ade20k_20200614_144141.log.json
+  Paper:
+    Title: 'PSANet: Point-wise Spatial Attention Network for Scene Parsing'
+    URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psa_head.py#L18
+  Framework: PyTorch
+- Name: psanet_r101-d8_4xb4-80k_ade20k-512x512
+  In Collection: PSANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.8
+      mIoU(ms+flip): 44.75
+  Config: configs/psanet/psanet_r101-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 12.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_80k_ade20k/psanet_r101-d8_512x512_80k_ade20k_20200614_185117-1fab60d4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_80k_ade20k/psanet_r101-d8_512x512_80k_ade20k_20200614_185117.log.json
+  Paper:
+    Title: 'PSANet: Point-wise Spatial Attention Network for Scene Parsing'
+    URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psa_head.py#L18
+  Framework: PyTorch
+- Name: psanet_r50-d8_4xb4-160k_ade20k-512x512
+  In Collection: PSANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 41.67
+      mIoU(ms+flip): 42.95
+  Config: configs/psanet/psanet_r50-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - PSANet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_160k_ade20k/psanet_r50-d8_512x512_160k_ade20k_20200615_161258-148077dd.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_160k_ade20k/psanet_r50-d8_512x512_160k_ade20k_20200615_161258.log.json
+  Paper:
+    Title: 'PSANet: Point-wise Spatial Attention Network for Scene Parsing'
+    URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psa_head.py#L18
+  Framework: PyTorch
+- Name: psanet_r101-d8_4xb4-160k_ade20k-512x512
+  In Collection: PSANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.74
+      mIoU(ms+flip): 45.38
+  Config: configs/psanet/psanet_r101-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSANet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_160k_ade20k/psanet_r101-d8_512x512_160k_ade20k_20200615_161537-dbfa564c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_160k_ade20k/psanet_r101-d8_512x512_160k_ade20k_20200615_161537.log.json
+  Paper:
+    Title: 'PSANet: Point-wise Spatial Attention Network for Scene Parsing'
+    URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psa_head.py#L18
+  Framework: PyTorch
+- Name: psanet_r50-d8_4xb4-20k_voc12aug-512x512
+  In Collection: PSANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 76.39
+      mIoU(ms+flip): 77.34
+  Config: configs/psanet/psanet_r50-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - PSANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_20k_voc12aug/psanet_r50-d8_512x512_20k_voc12aug_20200617_102413-2f1bbaa1.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_20k_voc12aug/psanet_r50-d8_512x512_20k_voc12aug_20200617_102413.log.json
+  Paper:
+    Title: 'PSANet: Point-wise Spatial Attention Network for Scene Parsing'
+    URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psa_head.py#L18
+  Framework: PyTorch
+- Name: psanet_r101-d8_4xb4-20k_voc12aug-512x512
+  In Collection: PSANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 77.91
+      mIoU(ms+flip): 79.3
+  Config: configs/psanet/psanet_r101-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSANet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.4
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_20k_voc12aug/psanet_r101-d8_512x512_20k_voc12aug_20200617_110624-946fef11.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_20k_voc12aug/psanet_r101-d8_512x512_20k_voc12aug_20200617_110624.log.json
+  Paper:
+    Title: 'PSANet: Point-wise Spatial Attention Network for Scene Parsing'
+    URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psa_head.py#L18
+  Framework: PyTorch
+- Name: psanet_r50-d8_4xb4-40k_voc12aug-512x512
+  In Collection: PSANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 76.3
+      mIoU(ms+flip): 77.35
+  Config: configs/psanet/psanet_r50-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - PSANet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_40k_voc12aug/psanet_r50-d8_512x512_40k_voc12aug_20200613_161946-f596afb5.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_40k_voc12aug/psanet_r50-d8_512x512_40k_voc12aug_20200613_161946.log.json
+  Paper:
+    Title: 'PSANet: Point-wise Spatial Attention Network for Scene Parsing'
+    URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psa_head.py#L18
+  Framework: PyTorch
+- Name: psanet_r101-d8_4xb4-40k_voc12aug-512x512
+  In Collection: PSANet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 77.73
+      mIoU(ms+flip): 79.05
+  Config: configs/psanet/psanet_r101-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSANet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_40k_voc12aug/psanet_r101-d8_512x512_40k_voc12aug_20200613_161946-1f560f9e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_40k_voc12aug/psanet_r101-d8_512x512_40k_voc12aug_20200613_161946.log.json
+  Paper:
+    Title: 'PSANet: Point-wise Spatial Attention Network for Scene Parsing'
+    URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psa_head.py#L18
+  Framework: PyTorch
diff --git a/configs/psanet/psanet.yml b/configs/psanet/psanet.yml
deleted file mode 100644
index fca1ac1b40..0000000000
--- a/configs/psanet/psanet.yml
+++ /dev/null
@@ -1,305 +0,0 @@
-Collections:
-- Name: PSANet
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-    - Pascal VOC 2012 + Aug
-  Paper:
-    URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf
-    Title: 'PSANet: Point-wise Spatial Attention Network for Scene Parsing'
-  README: configs/psanet/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psa_head.py#L18
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/hszhao/PSANet
-Models:
-- Name: psanet_r50-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: PSANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 315.46
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 7.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.63
-      mIoU(ms+flip): 79.04
-  Config: configs/psanet/psanet_r50-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_40k_cityscapes/psanet_r50-d8_512x1024_40k_cityscapes_20200606_103117-99fac37c.pth
-- Name: psanet_r101-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: PSANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 454.55
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 10.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.14
-      mIoU(ms+flip): 80.19
-  Config: configs/psanet/psanet_r101-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_40k_cityscapes/psanet_r101-d8_512x1024_40k_cityscapes_20200606_001418-27b9cfa7.pth
-- Name: psanet_r50-d8_4xb2-40k_cityscapes-769x769
-  In Collection: PSANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 714.29
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 7.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.99
-      mIoU(ms+flip): 79.64
-  Config: configs/psanet/psanet_r50-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_40k_cityscapes/psanet_r50-d8_769x769_40k_cityscapes_20200530_033717-d5365506.pth
-- Name: psanet_r101-d8_4xb2-40k_cityscapes-769x769
-  In Collection: PSANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 1020.41
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 11.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.43
-      mIoU(ms+flip): 80.26
-  Config: configs/psanet/psanet_r101-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_40k_cityscapes/psanet_r101-d8_769x769_40k_cityscapes_20200530_035107-997da1e6.pth
-- Name: psanet_r50-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: PSANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.24
-      mIoU(ms+flip): 78.69
-  Config: configs/psanet/psanet_r50-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_80k_cityscapes/psanet_r50-d8_512x1024_80k_cityscapes_20200606_161842-ab60a24f.pth
-- Name: psanet_r101-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: PSANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.31
-      mIoU(ms+flip): 80.53
-  Config: configs/psanet/psanet_r101-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_80k_cityscapes/psanet_r101-d8_512x1024_80k_cityscapes_20200606_161823-0f73a169.pth
-- Name: psanet_r50-d8_4xb2-80k_cityscapes-769x769
-  In Collection: PSANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.31
-      mIoU(ms+flip): 80.91
-  Config: configs/psanet/psanet_r50-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_80k_cityscapes/psanet_r50-d8_769x769_80k_cityscapes_20200606_225134-fe42f49e.pth
-- Name: psanet_r101-d8_4xb2-80k_cityscapes-769x769
-  In Collection: PSANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.69
-      mIoU(ms+flip): 80.89
-  Config: configs/psanet/psanet_r101-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_80k_cityscapes/psanet_r101-d8_769x769_80k_cityscapes_20200606_214550-7665827b.pth
-- Name: psanet_r50-d8_4xb4-80k_ade20k-512x512
-  In Collection: PSANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 52.88
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 41.14
-      mIoU(ms+flip): 41.91
-  Config: configs/psanet/psanet_r50-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_80k_ade20k/psanet_r50-d8_512x512_80k_ade20k_20200614_144141-835e4b97.pth
-- Name: psanet_r101-d8_4xb4-80k_ade20k-512x512
-  In Collection: PSANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 76.16
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 12.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.8
-      mIoU(ms+flip): 44.75
-  Config: configs/psanet/psanet_r101-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_80k_ade20k/psanet_r101-d8_512x512_80k_ade20k_20200614_185117-1fab60d4.pth
-- Name: psanet_r50-d8_4xb4-160k_ade20k-512x512
-  In Collection: PSANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 41.67
-      mIoU(ms+flip): 42.95
-  Config: configs/psanet/psanet_r50-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_160k_ade20k/psanet_r50-d8_512x512_160k_ade20k_20200615_161258-148077dd.pth
-- Name: psanet_r101-d8_4xb4-160k_ade20k-512x512
-  In Collection: PSANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.74
-      mIoU(ms+flip): 45.38
-  Config: configs/psanet/psanet_r101-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_160k_ade20k/psanet_r101-d8_512x512_160k_ade20k_20200615_161537-dbfa564c.pth
-- Name: psanet_r50-d8_4xb4-20k_voc12aug-512x512
-  In Collection: PSANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 54.82
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 76.39
-      mIoU(ms+flip): 77.34
-  Config: configs/psanet/psanet_r50-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_20k_voc12aug/psanet_r50-d8_512x512_20k_voc12aug_20200617_102413-2f1bbaa1.pth
-- Name: psanet_r101-d8_4xb4-20k_voc12aug-512x512
-  In Collection: PSANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 79.18
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 10.4
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 77.91
-      mIoU(ms+flip): 79.3
-  Config: configs/psanet/psanet_r101-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_20k_voc12aug/psanet_r101-d8_512x512_20k_voc12aug_20200617_110624-946fef11.pth
-- Name: psanet_r50-d8_4xb4-40k_voc12aug-512x512
-  In Collection: PSANet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 76.3
-      mIoU(ms+flip): 77.35
-  Config: configs/psanet/psanet_r50-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_40k_voc12aug/psanet_r50-d8_512x512_40k_voc12aug_20200613_161946-f596afb5.pth
-- Name: psanet_r101-d8_4xb4-40k_voc12aug-512x512
-  In Collection: PSANet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 77.73
-      mIoU(ms+flip): 79.05
-  Config: configs/psanet/psanet_r101-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_40k_voc12aug/psanet_r101-d8_512x512_40k_voc12aug_20200613_161946-1f560f9e.pth
diff --git a/configs/pspnet/README.md b/configs/pspnet/README.md
index 9135091102..e1c2c112cb 100644
--- a/configs/pspnet/README.md
+++ b/configs/pspnet/README.md
@@ -1,6 +1,6 @@
 # PSPNet
 
-[Pyramid Scene Parsing Network](https://arxiv.org/abs/1612.01105)
+> [Pyramid Scene Parsing Network](https://arxiv.org/abs/1612.01105)
 
 ## Introduction
 
@@ -27,85 +27,65 @@ Scene parsing is challenging for unrestricted open vocabulary and diverse scenes
 PSPNet-R50 D8 model structure
 </div>
 
-## Citation
-
-```bibtex
-@inproceedings{zhao2017pspnet,
-  title={Pyramid Scene Parsing Network},
-  author={Zhao, Hengshuang and Shi, Jianping and Qi, Xiaojuan and Wang, Xiaogang and Jia, Jiaya},
-  booktitle={CVPR},
-  year={2017}
-}
-```
-
-```bibtex
-@article{wightman2021resnet,
-  title={Resnet strikes back: An improved training procedure in timm},
-  author={Wightman, Ross and Touvron, Hugo and J{\'e}gou, Herv{\'e}},
-  journal={arXiv preprint arXiv:2110.00476},
-  year={2021}
-}
-```
-
 ## Results and models
 
 ### Cityscapes
 
-| Method        | Backbone      | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                                                                                                             |
-| ------------- | ------------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| PSPNet        | R-50-D8       | 512x1024  |   40000 | 6.1      | 4.07           | 77.85 |         79.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338.log.json)                                                                                 |
-| PSPNet        | R-101-D8      | 512x1024  |   40000 | 9.6      | 2.68           | 78.34 |         79.74 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb2-40k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751-467e7cf4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751.log.json)                                                                             |
-| PSPNet        | R-50-D8       | 769x769   |   40000 | 6.9      | 1.76           | 78.26 |         79.88 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-769x769.py)             | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_40k_cityscapes/pspnet_r50-d8_769x769_40k_cityscapes_20200606_112725-86638686.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_40k_cityscapes/pspnet_r50-d8_769x769_40k_cityscapes_20200606_112725.log.json)                                                                                     |
-| PSPNet        | R-101-D8      | 769x769   |   40000 | 10.9     | 1.15           | 79.08 |         80.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb2-40k_cityscapes-769x769.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_40k_cityscapes/pspnet_r101-d8_769x769_40k_cityscapes_20200606_112753-61c6f5be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_40k_cityscapes/pspnet_r101-d8_769x769_40k_cityscapes_20200606_112753.log.json)                                                                                 |
-| PSPNet        | R-18-D8       | 512x1024  |   80000 | 1.7      | 15.71          | 74.87 |         76.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18-d8_4xb2-80k_cityscapes-512x1024.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x1024_80k_cityscapes/pspnet_r18-d8_512x1024_80k_cityscapes_20201225_021458-09ffa746.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x1024_80k_cityscapes/pspnet_r18-d8_512x1024_80k_cityscapes-20201225_021458.log.json)                                                                                 |
-| PSPNet        | R-50-D8       | 512x1024  |   80000 | -        | -              | 78.55 |         79.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_512x1024_80k_cityscapes_20200606_112131-2376f12b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_512x1024_80k_cityscapes_20200606_112131.log.json)                                                                                 |
-| PSPNet        | R-50b-D8 rsb  | 512x1024  |   80000 | 6.2      | 3.82           | 78.47 |         79.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8-rsb_4xb2-adamw-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220315_123238-588c30be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220315_123238.log.json)                                           |
-| PSPNet        | R-101-D8      | 512x1024  |   80000 | -        | -              | 79.76 |         81.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes/pspnet_r101-d8_512x1024_80k_cityscapes_20200606_112211-e1e1100f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes/pspnet_r101-d8_512x1024_80k_cityscapes_20200606_112211.log.json)                                                                             |
-| PSPNet (FP16) | R-101-D8      | 512x1024  |   80000 | 5.34     | 8.77           | 79.46 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_fp16_512x1024_80k_cityscapes/pspnet_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230919-a0875e5c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_fp16_512x1024_80k_cityscapes/pspnet_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230919.log.json)                                                         |
-| PSPNet        | R-18-D8       | 769x769   |   80000 | 1.9      | 6.20           | 75.90 |         77.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18-d8_4xb2-80k_cityscapes-769x769.py)             | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_769x769_80k_cityscapes/pspnet_r18-d8_769x769_80k_cityscapes_20201225_021458-3deefc62.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_769x769_80k_cityscapes/pspnet_r18-d8_769x769_80k_cityscapes-20201225_021458.log.json)                                                                                     |
-| PSPNet        | R-50-D8       | 769x769   |   80000 | -        | -              | 79.59 |         80.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-769x769.py)             | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_80k_cityscapes/pspnet_r50-d8_769x769_80k_cityscapes_20200606_210121-5ccf03dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_80k_cityscapes/pspnet_r50-d8_769x769_80k_cityscapes_20200606_210121.log.json)                                                                                     |
-| PSPNet        | R-101-D8      | 769x769   |   80000 | -        | -              | 79.77 |         81.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb2-80k_cityscapes-769x769.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_80k_cityscapes/pspnet_r101-d8_769x769_80k_cityscapes_20200606_225055-dba412fa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_80k_cityscapes/pspnet_r101-d8_769x769_80k_cityscapes_20200606_225055.log.json)                                                                                 |
-| PSPNet        | R-18b-D8      | 512x1024  |   80000 | 1.5      | 16.28          | 74.23 |         75.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18b-d8_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_512x1024_80k_cityscapes/pspnet_r18b-d8_512x1024_80k_cityscapes_20201226_063116-26928a60.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_512x1024_80k_cityscapes/pspnet_r18b-d8_512x1024_80k_cityscapes-20201226_063116.log.json)                                                                             |
-| PSPNet        | R-50b-D8      | 512x1024  |   80000 | 6.0      | 4.30           | 78.22 |         79.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50b-d8_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_512x1024_80k_cityscapes/pspnet_r50b-d8_512x1024_80k_cityscapes_20201225_094315-6344287a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_512x1024_80k_cityscapes/pspnet_r50b-d8_512x1024_80k_cityscapes-20201225_094315.log.json)                                                                             |
-| PSPNet        | R-101b-D8     | 512x1024  |   80000 | 9.5      | 2.76           | 79.69 |         80.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101b-d8_4xb2-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes_20201226_170012-3a4d38ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes-20201226_170012.log.json)                                                                         |
-| PSPNet        | R-18b-D8      | 769x769   |   80000 | 1.7      | 6.41           | 74.92 |         76.90 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18b-d8_4xb2-80k_cityscapes-769x769.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_769x769_80k_cityscapes/pspnet_r18b-d8_769x769_80k_cityscapes_20201226_080942-bf98d186.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_769x769_80k_cityscapes/pspnet_r18b-d8_769x769_80k_cityscapes-20201226_080942.log.json)                                                                                 |
-| PSPNet        | R-50b-D8      | 769x769   |   80000 | 6.8      | 1.88           | 78.50 |         79.96 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50b-d8_4xb2-80k_cityscapes-769x769.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_769x769_80k_cityscapes/pspnet_r50b-d8_769x769_80k_cityscapes_20201225_094316-4c643cf6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_769x769_80k_cityscapes/pspnet_r50b-d8_769x769_80k_cityscapes-20201225_094316.log.json)                                                                                 |
-| PSPNet        | R-101b-D8     | 769x769   |   80000 | 10.8     | 1.17           | 78.87 |         80.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101b-d8_4xb2-80k_cityscapes-769x769.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_769x769_80k_cityscapes/pspnet_r101b-d8_769x769_80k_cityscapes_20201226_171823-f0e7c293.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_769x769_80k_cityscapes/pspnet_r101b-d8_769x769_80k_cityscapes-20201226_171823.log.json)                                                                             |
-| PSPNet        | R-50-D32      | 512x1024  |   80000 | 3.0      | 15.21          | 73.88 |         76.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50b-d32_4xb2-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_512x1024_80k_cityscapes/pspnet_r50-d32_512x1024_80k_cityscapes_20220316_224840-9092b254.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_512x1024_80k_cityscapes/pspnet_r50-d32_512x1024_80k_cityscapes_20220316_224840.log.json)                                                                             |
-| PSPNet        | R-50b-D32 rsb | 512x1024  |   80000 | 3.1      | 16.08          | 74.09 |         77.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d32_rsb_4xb2-adamw-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220316_141229-dd9c9610.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220316_141229.log.json) |
-| PSPNet        | R-50b-D32     | 512x1024  |   80000 | 2.9      | 15.41          | 72.61 |         75.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50b-d32_4xb2-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d32_512x1024_80k_cityscapes/pspnet_r50b-d32_512x1024_80k_cityscapes_20220311_152152-23bcaf8c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d32_512x1024_80k_cityscapes/pspnet_r50b-d32_512x1024_80k_cityscapes_20220311_152152.log.json)                                                                         |
+| Method        | Backbone      | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                                                                                                             |
+| ------------- | ------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| PSPNet        | R-50-D8       | 512x1024  |   40000 | 6.1      | 4.07           | V100   | 77.85 |         79.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338.log.json)                                                                                 |
+| PSPNet        | R-101-D8      | 512x1024  |   40000 | 9.6      | 2.68           | V100   | 78.34 |         79.74 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb2-40k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751-467e7cf4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751.log.json)                                                                             |
+| PSPNet        | R-50-D8       | 769x769   |   40000 | 6.9      | 1.76           | V100   | 78.26 |         79.88 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-769x769.py)             | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_40k_cityscapes/pspnet_r50-d8_769x769_40k_cityscapes_20200606_112725-86638686.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_40k_cityscapes/pspnet_r50-d8_769x769_40k_cityscapes_20200606_112725.log.json)                                                                                     |
+| PSPNet        | R-101-D8      | 769x769   |   40000 | 10.9     | 1.15           | V100   | 79.08 |         80.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb2-40k_cityscapes-769x769.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_40k_cityscapes/pspnet_r101-d8_769x769_40k_cityscapes_20200606_112753-61c6f5be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_40k_cityscapes/pspnet_r101-d8_769x769_40k_cityscapes_20200606_112753.log.json)                                                                                 |
+| PSPNet        | R-18-D8       | 512x1024  |   80000 | 1.7      | 15.71          | V100   | 74.87 |         76.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18-d8_4xb2-80k_cityscapes-512x1024.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x1024_80k_cityscapes/pspnet_r18-d8_512x1024_80k_cityscapes_20201225_021458-09ffa746.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x1024_80k_cityscapes/pspnet_r18-d8_512x1024_80k_cityscapes-20201225_021458.log.json)                                                                                 |
+| PSPNet        | R-50-D8       | 512x1024  |   80000 | -        | -              | V100   | 78.55 |         79.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_512x1024_80k_cityscapes_20200606_112131-2376f12b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_512x1024_80k_cityscapes_20200606_112131.log.json)                                                                                 |
+| PSPNet        | R-50b-D8 rsb  | 512x1024  |   80000 | 6.2      | 3.82           | V100   | 78.47 |         79.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8-rsb_4xb2-adamw-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220315_123238-588c30be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220315_123238.log.json)                                           |
+| PSPNet        | R-101-D8      | 512x1024  |   80000 | -        | -              | V100   | 79.76 |         81.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes/pspnet_r101-d8_512x1024_80k_cityscapes_20200606_112211-e1e1100f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes/pspnet_r101-d8_512x1024_80k_cityscapes_20200606_112211.log.json)                                                                             |
+| PSPNet (FP16) | R-101-D8      | 512x1024  |   80000 | 5.34     | 8.77           | V100   | 79.46 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_fp16_512x1024_80k_cityscapes/pspnet_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230919-a0875e5c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_fp16_512x1024_80k_cityscapes/pspnet_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230919.log.json)                                                         |
+| PSPNet        | R-18-D8       | 769x769   |   80000 | 1.9      | 6.20           | V100   | 75.90 |         77.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18-d8_4xb2-80k_cityscapes-769x769.py)             | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_769x769_80k_cityscapes/pspnet_r18-d8_769x769_80k_cityscapes_20201225_021458-3deefc62.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_769x769_80k_cityscapes/pspnet_r18-d8_769x769_80k_cityscapes-20201225_021458.log.json)                                                                                     |
+| PSPNet        | R-50-D8       | 769x769   |   80000 | -        | -              | V100   | 79.59 |         80.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-769x769.py)             | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_80k_cityscapes/pspnet_r50-d8_769x769_80k_cityscapes_20200606_210121-5ccf03dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_80k_cityscapes/pspnet_r50-d8_769x769_80k_cityscapes_20200606_210121.log.json)                                                                                     |
+| PSPNet        | R-101-D8      | 769x769   |   80000 | -        | -              | V100   | 79.77 |         81.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb2-80k_cityscapes-769x769.py)            | [model](https://download.oz1z1penmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_80k_cityscapes/pspnet_r101-d8_769x769_80k_cityscapes_20200606_225055-dba412fa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_80k_cityscapes/pspnet_r101-d8_769x769_80k_cityscapes_20200606_225055.log.json)                                                                             |
+| PSPNet        | R-18b-D8      | 512x1024  |   80000 | 1.5      | 16.28          | V100   | 74.23 |         75.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18b-d8_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_512x1024_80k_cityscapes/pspnet_r18b-d8_512x1024_80k_cityscapes_20201226_063116-26928a60.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_512x1024_80k_cityscapes/pspnet_r18b-d8_512x1024_80k_cityscapes-20201226_063116.log.json)                                                                             |
+| PSPNet        | R-50b-D8      | 512x1024  |   80000 | 6.0      | 4.30           | V100   | 78.22 |         79.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50b-d8_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_512x1024_80k_cityscapes/pspnet_r50b-d8_512x1024_80k_cityscapes_20201225_094315-6344287a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_512x1024_80k_cityscapes/pspnet_r50b-d8_512x1024_80k_cityscapes-20201225_094315.log.json)                                                                             |
+| PSPNet        | R-101b-D8     | 512x1024  |   80000 | 9.5      | 2.76           | V100   | 79.69 |         80.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101b-d8_4xb2-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes_20201226_170012-3a4d38ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes-20201226_170012.log.json)                                                                         |
+| PSPNet        | R-18b-D8      | 769x769   |   80000 | 1.7      | 6.41           | V100   | 74.92 |         76.90 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18b-d8_4xb2-80k_cityscapes-769x769.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_769x769_80k_cityscapes/pspnet_r18b-d8_769x769_80k_cityscapes_20201226_080942-bf98d186.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_769x769_80k_cityscapes/pspnet_r18b-d8_769x769_80k_cityscapes-20201226_080942.log.json)                                                                                 |
+| PSPNet        | R-50b-D8      | 769x769   |   80000 | 6.8      | 1.88           | V100   | 78.50 |         79.96 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50b-d8_4xb2-80k_cityscapes-769x769.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_769x769_80k_cityscapes/pspnet_r50b-d8_769x769_80k_cityscapes_20201225_094316-4c643cf6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_769x769_80k_cityscapes/pspnet_r50b-d8_769x769_80k_cityscapes-20201225_094316.log.json)                                                                                 |
+| PSPNet        | R-101b-D8     | 769x769   |   80000 | 10.8     | 1.17           | V100   | 78.87 |         80.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101b-d8_4xb2-80k_cityscapes-769x769.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_769x769_80k_cityscapes/pspnet_r101b-d8_769x769_80k_cityscapes_20201226_171823-f0e7c293.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_769x769_80k_cityscapes/pspnet_r101b-d8_769x769_80k_cityscapes-20201226_171823.log.json)                                                                             |
+| PSPNet        | R-50-D32      | 512x1024  |   80000 | 3.0      | 15.21          | V100   | 73.88 |         76.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50b-d32_4xb2-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_512x1024_80k_cityscapes/pspnet_r50-d32_512x1024_80k_cityscapes_20220316_224840-9092b254.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_512x1024_80k_cityscapes/pspnet_r50-d32_512x1024_80k_cityscapes_20220316_224840.log.json)                                                                             |
+| PSPNet        | R-50b-D32 rsb | 512x1024  |   80000 | 3.1      | 16.08          | V100   | 74.09 |         77.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d32_rsb_4xb2-adamw-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220316_141229-dd9c9610.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220316_141229.log.json) |
+| PSPNet        | R-50b-D32     | 512x1024  |   80000 | 2.9      | 15.41          | V100   | 72.61 |         75.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50b-d32_4xb2-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d32_512x1024_80k_cityscapes/pspnet_r50b-d32_512x1024_80k_cityscapes_20220311_152152-23bcaf8c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d32_512x1024_80k_cityscapes/pspnet_r50b-d32_512x1024_80k_cityscapes_20220311_152152.log.json)                                                                         |
 
 ### ADE20K
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSPNet | R-50-D8  | 512x512   |   80000 | 8.5      | 23.53          | 41.13 |         41.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_ade20k/pspnet_r50-d8_512x512_80k_ade20k_20200615_014128-15a8b914.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_ade20k/pspnet_r50-d8_512x512_80k_ade20k_20200615_014128.log.json)         |
-| PSPNet | R-101-D8 | 512x512   |   80000 | 12       | 15.30          | 43.57 |         44.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_ade20k/pspnet_r101-d8_512x512_80k_ade20k_20200614_031423-b6e782f0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_ade20k/pspnet_r101-d8_512x512_80k_ade20k_20200614_031423.log.json)     |
-| PSPNet | R-50-D8  | 512x512   |  160000 | -        | -              | 42.48 |         43.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_160k_ade20k/pspnet_r50-d8_512x512_160k_ade20k_20200615_184358-1890b0bd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_160k_ade20k/pspnet_r50-d8_512x512_160k_ade20k_20200615_184358.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |  160000 | -        | -              | 44.39 |         45.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_160k_ade20k/pspnet_r101-d8_512x512_160k_ade20k_20200615_100650-967c316f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_160k_ade20k/pspnet_r101-d8_512x512_160k_ade20k_20200615_100650.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSPNet | R-50-D8  | 512x512   |   80000 | 8.5      | 23.53          | V100   | 41.13 |         41.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_ade20k/pspnet_r50-d8_512x512_80k_ade20k_20200615_014128-15a8b914.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_ade20k/pspnet_r50-d8_512x512_80k_ade20k_20200615_014128.log.json)         |
+| PSPNet | R-101-D8 | 512x512   |   80000 | 12       | 15.30          | V100   | 43.57 |         44.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_ade20k/pspnet_r101-d8_512x512_80k_ade20k_20200614_031423-b6e782f0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_ade20k/pspnet_r101-d8_512x512_80k_ade20k_20200614_031423.log.json)     |
+| PSPNet | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 42.48 |         43.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_160k_ade20k/pspnet_r50-d8_512x512_160k_ade20k_20200615_184358-1890b0bd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_160k_ade20k/pspnet_r50-d8_512x512_160k_ade20k_20200615_184358.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 44.39 |         45.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_160k_ade20k/pspnet_r101-d8_512x512_160k_ade20k_20200615_100650-967c316f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_160k_ade20k/pspnet_r101-d8_512x512_160k_ade20k_20200615_100650.log.json) |
 
 ### Pascal VOC 2012 + Aug
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                     |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSPNet | R-50-D8  | 512x512   |   20000 | 6.1      | 23.59          | 76.78 |         77.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_20k_voc12aug/pspnet_r50-d8_512x512_20k_voc12aug_20200617_101958-ed5dfbd9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_20k_voc12aug/pspnet_r50-d8_512x512_20k_voc12aug_20200617_101958.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |   20000 | 9.6      | 15.02          | 78.47 |         79.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_20k_voc12aug/pspnet_r101-d8_512x512_20k_voc12aug_20200617_102003-4aef3c9a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_20k_voc12aug/pspnet_r101-d8_512x512_20k_voc12aug_20200617_102003.log.json) |
-| PSPNet | R-50-D8  | 512x512   |   40000 | -        | -              | 77.29 |         78.48 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_40k_voc12aug/pspnet_r50-d8_512x512_40k_voc12aug_20200613_161222-ae9c1b8c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_40k_voc12aug/pspnet_r50-d8_512x512_40k_voc12aug_20200613_161222.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |   40000 | -        | -              | 78.52 |         79.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_40k_voc12aug/pspnet_r101-d8_512x512_40k_voc12aug_20200613_161222-bc933b18.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_40k_voc12aug/pspnet_r101-d8_512x512_40k_voc12aug_20200613_161222.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                     |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSPNet | R-50-D8  | 512x512   |   20000 | 6.1      | 23.59          | V100   | 76.78 |         77.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_20k_voc12aug/pspnet_r50-d8_512x512_20k_voc12aug_20200617_101958-ed5dfbd9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_20k_voc12aug/pspnet_r50-d8_512x512_20k_voc12aug_20200617_101958.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |   20000 | 9.6      | 15.02          | V100   | 78.47 |         79.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_20k_voc12aug/pspnet_r101-d8_512x512_20k_voc12aug_20200617_102003-4aef3c9a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_20k_voc12aug/pspnet_r101-d8_512x512_20k_voc12aug_20200617_102003.log.json) |
+| PSPNet | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 77.29 |         78.48 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_40k_voc12aug/pspnet_r50-d8_512x512_40k_voc12aug_20200613_161222-ae9c1b8c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_40k_voc12aug/pspnet_r50-d8_512x512_40k_voc12aug_20200613_161222.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 78.52 |         79.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_40k_voc12aug/pspnet_r101-d8_512x512_40k_voc12aug_20200613_161222-bc933b18.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_40k_voc12aug/pspnet_r101-d8_512x512_40k_voc12aug_20200613_161222.log.json) |
 
 ### Pascal Context
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                               | download                                                                                                                                                                                                                                                                                                                                                             |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSPNet | R-101-D8 | 480x480   |   40000 | 8.8      | 9.68           | 46.60 |         47.78 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context/pspnet_r101-d8_480x480_40k_pascal_context_20200911_211210-bf0f5d7c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context/pspnet_r101-d8_480x480_40k_pascal_context-20200911_211210.log.json) |
-| PSPNet | R-101-D8 | 480x480   |   80000 | -        | -              | 46.03 |         47.15 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context/pspnet_r101-d8_480x480_80k_pascal_context_20200911_190530-c86d6233.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context/pspnet_r101-d8_480x480_80k_pascal_context-20200911_190530.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                               | download                                                                                                                                                                                                                                                                                                                                                             |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSPNet | R-101-D8 | 480x480   |   40000 | 8.8      | 9.68           | V100   | 46.60 |         47.78 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context/pspnet_r101-d8_480x480_40k_pascal_context_20200911_211210-bf0f5d7c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context/pspnet_r101-d8_480x480_40k_pascal_context-20200911_211210.log.json) |
+| PSPNet | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 46.03 |         47.15 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context/pspnet_r101-d8_480x480_80k_pascal_context_20200911_190530-c86d6233.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context/pspnet_r101-d8_480x480_80k_pascal_context-20200911_190530.log.json) |
 
 ### Pascal Context 59
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                  | download                                                                                                                                                                                                                                                                                                                                                                         |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSPNet | R-101-D8 | 480x480   |   40000 | -        | -              | 52.02 |         53.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context_59/pspnet_r101-d8_480x480_40k_pascal_context_59_20210416_114524-86d44cd4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context_59/pspnet_r101-d8_480x480_40k_pascal_context_59-20210416_114524.log.json) |
-| PSPNet | R-101-D8 | 480x480   |   80000 | -        | -              | 52.47 |         53.99 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context_59/pspnet_r101-d8_480x480_80k_pascal_context_59_20210416_114418-fa6caaa2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context_59/pspnet_r101-d8_480x480_80k_pascal_context_59-20210416_114418.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                  | download                                                                                                                                                                                                                                                                                                                                                                         |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSPNet | R-101-D8 | 480x480   |   40000 | -        | -              | V100   | 52.02 |         53.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context_59/pspnet_r101-d8_480x480_40k_pascal_context_59_20210416_114524-86d44cd4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context_59/pspnet_r101-d8_480x480_40k_pascal_context_59-20210416_114524.log.json) |
+| PSPNet | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 52.47 |         53.99 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context_59/pspnet_r101-d8_480x480_80k_pascal_context_59_20210416_114418-fa6caaa2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context_59/pspnet_r101-d8_480x480_80k_pascal_context_59-20210416_114418.log.json) |
 
 ### Dark Zurich and Nighttime Driving
 
@@ -125,54 +105,54 @@ We support evaluation results on these two datasets using models above trained o
 
 ### COCO-Stuff 10k
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                              | download                                                                                                                                                                                                                                                                                                                                                                         |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSPNet | R-50-D8  | 512x512   |   20000 | 9.6      | 20.5           | 35.69 |         36.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-20k_coco-stuff10k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k_20210820_203258-b88df27f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k_20210820_203258.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |   20000 | 13.2     | 11.1           | 37.26 |         38.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-20k_coco-stuff10k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k_20210820_232135-76aae482.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k_20210820_232135.log.json) |
-| PSPNet | R-50-D8  | 512x512   |   40000 | -        | -              | 36.33 |         37.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-40k_coco-stuff10k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_030857-92e2902b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_030857.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |   40000 | -        | -              | 37.76 |         38.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-40k_coco-stuff10k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_014022-831aec95.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_014022.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                              | download                                                                                                                                                                                                                                                                                                                                                                         |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSPNet | R-50-D8  | 512x512   |   20000 | 9.6      | 20.5           | V100   | 35.69 |         36.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-20k_coco-stuff10k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k_20210820_203258-b88df27f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k_20210820_203258.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |   20000 | 13.2     | 11.1           | V100   | 37.26 |         38.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-20k_coco-stuff10k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k_20210820_232135-76aae482.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k_20210820_232135.log.json) |
+| PSPNet | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 36.33 |         37.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-40k_coco-stuff10k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_030857-92e2902b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_030857.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 37.76 |         38.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-40k_coco-stuff10k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_014022-831aec95.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_014022.log.json) |
 
 ### COCO-Stuff 164k
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                | download                                                                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSPNet | R-50-D8  | 512x512   |   80000 | 9.6      | 20.5           | 38.80 |         39.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-80k_coco-stuff164k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034-0e41b2db.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034.log.json)         |
-| PSPNet | R-101-D8 | 512x512   |   80000 | 13.2     | 11.1           | 40.34 |         40.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034-7eb41789.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034.log.json)     |
-| PSPNet | R-50-D8  | 512x512   |  160000 | -        | -              | 39.64 |         39.97 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004-51276a57.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |  160000 | -        | -              | 41.28 |         41.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-160k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004-4af9621b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004.log.json) |
-| PSPNet | R-50-D8  | 512x512   |  320000 | -        | -              | 40.53 |         40.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-320k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004-be9610cc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |  320000 | -        | -              | 41.95 |         42.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-320k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004-72220c60.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                | download                                                                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSPNet | R-50-D8  | 512x512   |   80000 | 9.6      | 20.5           | V100   | 38.80 |         39.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-80k_coco-stuff164k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034-0e41b2db.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034.log.json)         |
+| PSPNet | R-101-D8 | 512x512   |   80000 | 13.2     | 11.1           | V100   | 40.34 |         40.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034-7eb41789.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034.log.json)     |
+| PSPNet | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 39.64 |         39.97 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004-51276a57.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 41.28 |         41.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-160k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004-4af9621b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004.log.json) |
+| PSPNet | R-50-D8  | 512x512   |  320000 | -        | -              | V100   | 40.53 |         40.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-320k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004-be9610cc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |  320000 | -        | -              | V100   | 41.95 |         42.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-320k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004-72220c60.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004.log.json) |
 
 ### LoveDA
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                             |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| PSPNet | R-18-D8  | 512x512   |   80000 | 1.45     | 26.87          | 48.62 |         47.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18-d8_4xb4-80k_loveda-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x512_80k_loveda/pspnet_r18-d8_512x512_80k_loveda_20211105_052100-b97697f1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x512_80k_loveda/pspnet_r18-d8_512x512_80k_loveda_20211105_052100.log.json)     |
-| PSPNet | R-50-D8  | 512x512   |   80000 | 6.14     | 6.60           | 50.46 |         50.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-80k_loveda-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_loveda/pspnet_r50-d8_512x512_80k_loveda_20211104_155728-88610f9f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_loveda/pspnet_r50-d8_512x512_80k_loveda_20211104_155728.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |   80000 | 9.61     | 4.58           | 51.86 |         51.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_loveda-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_loveda/pspnet_r101-d8_512x512_80k_loveda_20211104_153212-1c06c6a8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_loveda/pspnet_r101-d8_512x512_80k_loveda_20211104_153212.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                             |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| PSPNet | R-18-D8  | 512x512   |   80000 | 1.45     | 26.87          | V100   | 48.62 |         47.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18-d8_4xb4-80k_loveda-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x512_80k_loveda/pspnet_r18-d8_512x512_80k_loveda_20211105_052100-b97697f1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x512_80k_loveda/pspnet_r18-d8_512x512_80k_loveda_20211105_052100.log.json)     |
+| PSPNet | R-50-D8  | 512x512   |   80000 | 6.14     | 6.60           | V100   | 50.46 |         50.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-80k_loveda-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_loveda/pspnet_r50-d8_512x512_80k_loveda_20211104_155728-88610f9f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_loveda/pspnet_r50-d8_512x512_80k_loveda_20211104_155728.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |   80000 | 9.61     | 4.58           | V100   | 51.86 |         51.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_loveda-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_loveda/pspnet_r101-d8_512x512_80k_loveda_20211104_153212-1c06c6a8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_loveda/pspnet_r101-d8_512x512_80k_loveda_20211104_153212.log.json) |
 
 ### Potsdam
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSPNet | R-18-D8  | 512x512   |   80000 | 1.50     | 85.12          | 77.09 |         78.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18-d8_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_potsdam/pspnet_r18-d8_4x4_512x512_80k_potsdam_20211220_125612-7cd046e1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_potsdam/pspnet_r18-d8_4x4_512x512_80k_potsdam_20211220_125612.log.json)     |
-| PSPNet | R-50-D8  | 512x512   |   80000 | 6.14     | 30.21          | 78.12 |         78.98 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_potsdam/pspnet_r50-d8_4x4_512x512_80k_potsdam_20211219_043541-2dd5fe67.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_potsdam/pspnet_r50-d8_4x4_512x512_80k_potsdam_20211219_043541.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |   80000 | 9.61     | 19.40          | 78.62 |         79.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_potsdam-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_potsdam/pspnet_r101-d8_4x4_512x512_80k_potsdam_20211220_125612-aed036c4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_potsdam/pspnet_r101-d8_4x4_512x512_80k_potsdam_20211220_125612.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSPNet | R-18-D8  | 512x512   |   80000 | 1.50     | 85.12          | V100   | 77.09 |         78.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18-d8_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_potsdam/pspnet_r18-d8_4x4_512x512_80k_potsdam_20211220_125612-7cd046e1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_potsdam/pspnet_r18-d8_4x4_512x512_80k_potsdam_20211220_125612.log.json)     |
+| PSPNet | R-50-D8  | 512x512   |   80000 | 6.14     | 30.21          | V100   | 78.12 |         78.98 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_potsdam/pspnet_r50-d8_4x4_512x512_80k_potsdam_20211219_043541-2dd5fe67.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_potsdam/pspnet_r50-d8_4x4_512x512_80k_potsdam_20211219_043541.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |   80000 | 9.61     | 19.40          | V100   | 78.62 |         79.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_potsdam-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_potsdam/pspnet_r101-d8_4x4_512x512_80k_potsdam_20211220_125612-aed036c4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_potsdam/pspnet_r101-d8_4x4_512x512_80k_potsdam_20211220_125612.log.json) |
 
 ### Vaihingen
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                                         |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSPNet | R-18-D8  | 512x512   |   80000 | 1.45     | 85.06          | 71.46 |         73.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18-d8_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_vaihingen/pspnet_r18-d8_4x4_512x512_80k_vaihingen_20211228_160355-52a8a6f6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_vaihingen/pspnet_r18-d8_4x4_512x512_80k_vaihingen_20211228_160355.log.json)     |
-| PSPNet | R-50-D8  | 512x512   |   80000 | 6.14     | 30.29          | 72.36 |         73.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_vaihingen/pspnet_r50-d8_4x4_512x512_80k_vaihingen_20211228_160355-382f8f5b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_vaihingen/pspnet_r50-d8_4x4_512x512_80k_vaihingen_20211228_160355.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |   80000 | 9.61     | 19.97          | 72.61 |         74.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_vaihingen-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_vaihingen/pspnet_r101-d8_4x4_512x512_80k_vaihingen_20211231_230806-8eba0a09.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_vaihingen/pspnet_r101-d8_4x4_512x512_80k_vaihingen_20211231_230806.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                                         |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSPNet | R-18-D8  | 512x512   |   80000 | 1.45     | 85.06          | V100   | 71.46 |         73.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18-d8_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_vaihingen/pspnet_r18-d8_4x4_512x512_80k_vaihingen_20211228_160355-52a8a6f6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_vaihingen/pspnet_r18-d8_4x4_512x512_80k_vaihingen_20211228_160355.log.json)     |
+| PSPNet | R-50-D8  | 512x512   |   80000 | 6.14     | 30.29          | V100   | 72.36 |         73.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_vaihingen/pspnet_r50-d8_4x4_512x512_80k_vaihingen_20211228_160355-382f8f5b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_vaihingen/pspnet_r50-d8_4x4_512x512_80k_vaihingen_20211228_160355.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |   80000 | 9.61     | 19.97          | V100   | 72.61 |         74.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_vaihingen-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_vaihingen/pspnet_r101-d8_4x4_512x512_80k_vaihingen_20211231_230806-8eba0a09.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_vaihingen/pspnet_r101-d8_4x4_512x512_80k_vaihingen_20211231_230806.log.json) |
 
 ### iSAID
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                     |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSPNet | R-18-D8  | 896x896   |   80000 | 4.52     | 26.91          | 60.22 |         61.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_896x896_80k_isaid/pspnet_r18-d8_4x4_896x896_80k_isaid_20220110_180526-e84c0b6a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_896x896_80k_isaid/pspnet_r18-d8_4x4_896x896_80k_isaid_20220110_180526.log.json) |
-| PSPNet | R-50-D8  | 896x896   |   80000 | 16.58    | 8.88           | 65.36 |         66.48 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_896x896_80k_isaid/pspnet_r50-d8_4x4_896x896_80k_isaid_20220110_180629-1f21dc32.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_896x896_80k_isaid/pspnet_r50-d8_4x4_896x896_80k_isaid_20220110_180629.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                     |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSPNet | R-18-D8  | 896x896   |   80000 | 4.52     | 26.91          | V100   | 60.22 |         61.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_896x896_80k_isaid/pspnet_r18-d8_4x4_896x896_80k_isaid_20220110_180526-e84c0b6a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_896x896_80k_isaid/pspnet_r18-d8_4x4_896x896_80k_isaid_20220110_180526.log.json) |
+| PSPNet | R-50-D8  | 896x896   |   80000 | 16.58    | 8.88           | V100   | 65.36 |         66.48 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_896x896_80k_isaid/pspnet_r50-d8_4x4_896x896_80k_isaid_20220110_180629-1f21dc32.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_896x896_80k_isaid/pspnet_r50-d8_4x4_896x896_80k_isaid_20220110_180629.log.json) |
 
 Note:
 
@@ -180,3 +160,23 @@ Note:
 - `896x896` is the Crop Size of iSAID dataset, which is followed by the implementation of [PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation](https://arxiv.org/pdf/2103.06564.pdf)
 - `rsb` is short for 'Resnet strikes back'.
 - The `b` in `R-50b` means ResNetV1b, which is a standard ResNet backbone. In MMSegmentation, default backbone is ResNetV1c, which usually performs better in semantic segmentation task.
+
+## Citation
+
+```bibtex
+@inproceedings{zhao2017pspnet,
+  title={Pyramid Scene Parsing Network},
+  author={Zhao, Hengshuang and Shi, Jianping and Qi, Xiaojuan and Wang, Xiaogang and Jia, Jiaya},
+  booktitle={CVPR},
+  year={2017}
+}
+```
+
+```bibtex
+@article{wightman2021resnet,
+  title={Resnet strikes back: An improved training procedure in timm},
+  author={Wightman, Ross and Touvron, Hugo and J{\'e}gou, Herv{\'e}},
+  journal={arXiv preprint arXiv:2110.00476},
+  year={2021}
+}
+```
diff --git a/configs/pspnet/metafile.yaml b/configs/pspnet/metafile.yaml
new file mode 100644
index 0000000000..d00b89d5cf
--- /dev/null
+++ b/configs/pspnet/metafile.yaml
@@ -0,0 +1,1303 @@
+Collections:
+- Name: PSPNet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - ADE20K
+    - Pascal VOC 2012 + Aug
+    - Pascal Context
+    - Pascal Context 59
+    - Dark Zurich and Nighttime Driving
+    - COCO-Stuff 10k
+    - COCO-Stuff 164k
+    - LoveDA
+    - Potsdam
+    - Vaihingen
+    - iSAID
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  README: configs/pspnet/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: pspnet_r50-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.85
+      mIoU(ms+flip): 79.18
+  Config: configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb2-40k_cityscapes-512x1024
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.34
+      mIoU(ms+flip): 79.74
+  Config: configs/pspnet/pspnet_r101-d8_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751-467e7cf4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50-d8_4xb2-40k_cityscapes-769x769
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.26
+      mIoU(ms+flip): 79.88
+  Config: configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_40k_cityscapes/pspnet_r50-d8_769x769_40k_cityscapes_20200606_112725-86638686.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_40k_cityscapes/pspnet_r50-d8_769x769_40k_cityscapes_20200606_112725.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb2-40k_cityscapes-769x769
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.08
+      mIoU(ms+flip): 80.28
+  Config: configs/pspnet/pspnet_r101-d8_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_40k_cityscapes/pspnet_r101-d8_769x769_40k_cityscapes_20200606_112753-61c6f5be.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_40k_cityscapes/pspnet_r101-d8_769x769_40k_cityscapes_20200606_112753.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r18-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 74.87
+      mIoU(ms+flip): 76.04
+  Config: configs/pspnet/pspnet_r18-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x1024_80k_cityscapes/pspnet_r18-d8_512x1024_80k_cityscapes_20201225_021458-09ffa746.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x1024_80k_cityscapes/pspnet_r18-d8_512x1024_80k_cityscapes-20201225_021458.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.55
+      mIoU(ms+flip): 79.79
+  Config: configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_512x1024_80k_cityscapes_20200606_112131-2376f12b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_512x1024_80k_cityscapes_20200606_112131.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50-d8-rsb_4xb2-adamw-80k_cityscapes-512x1024
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.47
+      mIoU(ms+flip): 79.45
+  Config: configs/pspnet/pspnet_r50-d8-rsb_4xb2-adamw-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50b-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220315_123238-588c30be.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220315_123238.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.76
+      mIoU(ms+flip): 81.01
+  Config: configs/pspnet/pspnet_r101-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes/pspnet_r101-d8_512x1024_80k_cityscapes_20200606_112211-e1e1100f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes/pspnet_r101-d8_512x1024_80k_cityscapes_20200606_112211.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb2-amp-80k_cityscapes-512x1024
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.46
+  Config: configs/pspnet/pspnet_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    - (FP16)
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.34
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_fp16_512x1024_80k_cityscapes/pspnet_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230919-a0875e5c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_fp16_512x1024_80k_cityscapes/pspnet_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230919.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r18-d8_4xb2-80k_cityscapes-769x769
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 75.9
+      mIoU(ms+flip): 77.86
+  Config: configs/pspnet/pspnet_r18-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_769x769_80k_cityscapes/pspnet_r18-d8_769x769_80k_cityscapes_20201225_021458-3deefc62.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_769x769_80k_cityscapes/pspnet_r18-d8_769x769_80k_cityscapes-20201225_021458.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50-d8_4xb2-80k_cityscapes-769x769
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.59
+      mIoU(ms+flip): 80.69
+  Config: configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_80k_cityscapes/pspnet_r50-d8_769x769_80k_cityscapes_20200606_210121-5ccf03dd.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_80k_cityscapes/pspnet_r50-d8_769x769_80k_cityscapes_20200606_210121.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb2-80k_cityscapes-769x769
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.77
+      mIoU(ms+flip): 81.06
+  Config: configs/pspnet/pspnet_r101-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.oz1z1penmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_80k_cityscapes/pspnet_r101-d8_769x769_80k_cityscapes_20200606_225055-dba412fa.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_80k_cityscapes/pspnet_r101-d8_769x769_80k_cityscapes_20200606_225055.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r18b-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 74.23
+      mIoU(ms+flip): 75.79
+  Config: configs/pspnet/pspnet_r18b-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18b-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_512x1024_80k_cityscapes/pspnet_r18b-d8_512x1024_80k_cityscapes_20201226_063116-26928a60.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_512x1024_80k_cityscapes/pspnet_r18b-d8_512x1024_80k_cityscapes-20201226_063116.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50b-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.22
+      mIoU(ms+flip): 79.46
+  Config: configs/pspnet/pspnet_r50b-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50b-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_512x1024_80k_cityscapes/pspnet_r50b-d8_512x1024_80k_cityscapes_20201225_094315-6344287a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_512x1024_80k_cityscapes/pspnet_r50b-d8_512x1024_80k_cityscapes-20201225_094315.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101b-d8_4xb2-80k_cityscapes-512x1024
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.69
+      mIoU(ms+flip): 80.79
+  Config: configs/pspnet/pspnet_r101b-d8_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101b-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes_20201226_170012-3a4d38ab.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes-20201226_170012.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r18b-d8_4xb2-80k_cityscapes-769x769
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 74.92
+      mIoU(ms+flip): 76.9
+  Config: configs/pspnet/pspnet_r18b-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-18b-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.7
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_769x769_80k_cityscapes/pspnet_r18b-d8_769x769_80k_cityscapes_20201226_080942-bf98d186.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_769x769_80k_cityscapes/pspnet_r18b-d8_769x769_80k_cityscapes-20201226_080942.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50b-d8_4xb2-80k_cityscapes-769x769
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.5
+      mIoU(ms+flip): 79.96
+  Config: configs/pspnet/pspnet_r50b-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50b-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_769x769_80k_cityscapes/pspnet_r50b-d8_769x769_80k_cityscapes_20201225_094316-4c643cf6.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_769x769_80k_cityscapes/pspnet_r50b-d8_769x769_80k_cityscapes-20201225_094316.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101b-d8_4xb2-80k_cityscapes-769x769
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.87
+      mIoU(ms+flip): 80.04
+  Config: configs/pspnet/pspnet_r101b-d8_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101b-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 10.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_769x769_80k_cityscapes/pspnet_r101b-d8_769x769_80k_cityscapes_20201226_171823-f0e7c293.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_769x769_80k_cityscapes/pspnet_r101b-d8_769x769_80k_cityscapes-20201226_171823.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50b-d32_4xb2-80k_cityscapes-512x1024
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 73.88
+      mIoU(ms+flip): 76.85
+  Config: configs/pspnet/pspnet_r50b-d32_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50-D32
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 3.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_512x1024_80k_cityscapes/pspnet_r50-d32_512x1024_80k_cityscapes_20220316_224840-9092b254.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_512x1024_80k_cityscapes/pspnet_r50-d32_512x1024_80k_cityscapes_20220316_224840.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50-d32_rsb_4xb2-adamw-80k_cityscapes-512x1024
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 74.09
+      mIoU(ms+flip): 77.18
+  Config: configs/pspnet/pspnet_r50-d32_rsb_4xb2-adamw-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50b-D32
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 3.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220316_141229-dd9c9610.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220316_141229.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50b-d32_4xb2-80k_cityscapes-512x1024
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 72.61
+      mIoU(ms+flip): 75.51
+  Config: configs/pspnet/pspnet_r50b-d32_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50b-D32
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 2.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d32_512x1024_80k_cityscapes/pspnet_r50b-d32_512x1024_80k_cityscapes_20220311_152152-23bcaf8c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d32_512x1024_80k_cityscapes/pspnet_r50b-d32_512x1024_80k_cityscapes_20220311_152152.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50-d8_4xb4-80k_ade20k-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 41.13
+      mIoU(ms+flip): 41.94
+  Config: configs/pspnet/pspnet_r50-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_ade20k/pspnet_r50-d8_512x512_80k_ade20k_20200615_014128-15a8b914.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_ade20k/pspnet_r50-d8_512x512_80k_ade20k_20200615_014128.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb4-80k_ade20k-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.57
+      mIoU(ms+flip): 44.35
+  Config: configs/pspnet/pspnet_r101-d8_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 12.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_ade20k/pspnet_r101-d8_512x512_80k_ade20k_20200614_031423-b6e782f0.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_ade20k/pspnet_r101-d8_512x512_80k_ade20k_20200614_031423.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50-d8_4xb4-160k_ade20k-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.48
+      mIoU(ms+flip): 43.44
+  Config: configs/pspnet/pspnet_r50-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_160k_ade20k/pspnet_r50-d8_512x512_160k_ade20k_20200615_184358-1890b0bd.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_160k_ade20k/pspnet_r50-d8_512x512_160k_ade20k_20200615_184358.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb4-160k_ade20k-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 44.39
+      mIoU(ms+flip): 45.35
+  Config: configs/pspnet/pspnet_r101-d8_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_160k_ade20k/pspnet_r101-d8_512x512_160k_ade20k_20200615_100650-967c316f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_160k_ade20k/pspnet_r101-d8_512x512_160k_ade20k_20200615_100650.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50-d8_4xb4-20k_voc12aug-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 76.78
+      mIoU(ms+flip): 77.61
+  Config: configs/pspnet/pspnet_r50-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_20k_voc12aug/pspnet_r50-d8_512x512_20k_voc12aug_20200617_101958-ed5dfbd9.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_20k_voc12aug/pspnet_r50-d8_512x512_20k_voc12aug_20200617_101958.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb4-20k_voc12aug-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 78.47
+      mIoU(ms+flip): 79.25
+  Config: configs/pspnet/pspnet_r101-d8_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_20k_voc12aug/pspnet_r101-d8_512x512_20k_voc12aug_20200617_102003-4aef3c9a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_20k_voc12aug/pspnet_r101-d8_512x512_20k_voc12aug_20200617_102003.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50-d8_4xb4-40k_voc12aug-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 77.29
+      mIoU(ms+flip): 78.48
+  Config: configs/pspnet/pspnet_r50-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_40k_voc12aug/pspnet_r50-d8_512x512_40k_voc12aug_20200613_161222-ae9c1b8c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_40k_voc12aug/pspnet_r50-d8_512x512_40k_voc12aug_20200613_161222.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb4-40k_voc12aug-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 78.52
+      mIoU(ms+flip): 79.57
+  Config: configs/pspnet/pspnet_r101-d8_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_40k_voc12aug/pspnet_r101-d8_512x512_40k_voc12aug_20200613_161222-bc933b18.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_40k_voc12aug/pspnet_r101-d8_512x512_40k_voc12aug_20200613_161222.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb4-40k_pascal-context-480x480
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context
+    Metrics:
+      mIoU: 46.6
+      mIoU(ms+flip): 47.78
+  Config: configs/pspnet/pspnet_r101-d8_4xb4-40k_pascal-context-480x480.py
+  Metadata:
+    Training Data: Pascal Context
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context/pspnet_r101-d8_480x480_40k_pascal_context_20200911_211210-bf0f5d7c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context/pspnet_r101-d8_480x480_40k_pascal_context-20200911_211210.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb4-80k_pascal-context-480x480
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context
+    Metrics:
+      mIoU: 46.03
+      mIoU(ms+flip): 47.15
+  Config: configs/pspnet/pspnet_r101-d8_4xb4-80k_pascal-context-480x480.py
+  Metadata:
+    Training Data: Pascal Context
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context/pspnet_r101-d8_480x480_80k_pascal_context_20200911_190530-c86d6233.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context/pspnet_r101-d8_480x480_80k_pascal_context-20200911_190530.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb4-40k_pascal-context-59-480x480
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context 59
+    Metrics:
+      mIoU: 52.02
+      mIoU(ms+flip): 53.54
+  Config: configs/pspnet/pspnet_r101-d8_4xb4-40k_pascal-context-59-480x480.py
+  Metadata:
+    Training Data: Pascal Context 59
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context_59/pspnet_r101-d8_480x480_40k_pascal_context_59_20210416_114524-86d44cd4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context_59/pspnet_r101-d8_480x480_40k_pascal_context_59-20210416_114524.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb4-80k_pascal-context-59-480x480
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal Context 59
+    Metrics:
+      mIoU: 52.47
+      mIoU(ms+flip): 53.99
+  Config: configs/pspnet/pspnet_r101-d8_4xb4-80k_pascal-context-59-480x480.py
+  Metadata:
+    Training Data: Pascal Context 59
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context_59/pspnet_r101-d8_480x480_80k_pascal_context_59_20210416_114418-fa6caaa2.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context_59/pspnet_r101-d8_480x480_80k_pascal_context_59-20210416_114418.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50-d8_4xb4-20k_coco-stuff10k-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 10k
+    Metrics:
+      mIoU: 35.69
+      mIoU(ms+flip): 36.62
+  Config: configs/pspnet/pspnet_r50-d8_4xb4-20k_coco-stuff10k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 10k
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k_20210820_203258-b88df27f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k_20210820_203258.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb4-20k_coco-stuff10k-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 10k
+    Metrics:
+      mIoU: 37.26
+      mIoU(ms+flip): 38.52
+  Config: configs/pspnet/pspnet_r101-d8_4xb4-20k_coco-stuff10k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 10k
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 13.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k_20210820_232135-76aae482.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k_20210820_232135.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50-d8_4xb4-40k_coco-stuff10k-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 10k
+    Metrics:
+      mIoU: 36.33
+      mIoU(ms+flip): 37.24
+  Config: configs/pspnet/pspnet_r50-d8_4xb4-40k_coco-stuff10k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 10k
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_030857-92e2902b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_030857.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb4-40k_coco-stuff10k-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 10k
+    Metrics:
+      mIoU: 37.76
+      mIoU(ms+flip): 38.86
+  Config: configs/pspnet/pspnet_r101-d8_4xb4-40k_coco-stuff10k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 10k
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_014022-831aec95.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_014022.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50-d8_4xb4-80k_coco-stuff164k-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 38.8
+      mIoU(ms+flip): 39.19
+  Config: configs/pspnet/pspnet_r50-d8_4xb4-80k_coco-stuff164k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 164k
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034-0e41b2db.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb4-80k_coco-stuff164k-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 40.34
+      mIoU(ms+flip): 40.79
+  Config: configs/pspnet/pspnet_r101-d8_4xb4-80k_coco-stuff164k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 164k
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 13.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034-7eb41789.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50-d8_4xb4-160k_coco-stuff164k-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 39.64
+      mIoU(ms+flip): 39.97
+  Config: configs/pspnet/pspnet_r50-d8_4xb4-160k_coco-stuff164k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 164k
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004-51276a57.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb4-160k_coco-stuff164k-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 41.28
+      mIoU(ms+flip): 41.66
+  Config: configs/pspnet/pspnet_r101-d8_4xb4-160k_coco-stuff164k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 164k
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004-4af9621b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50-d8_4xb4-320k_coco-stuff164k-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 40.53
+      mIoU(ms+flip): 40.75
+  Config: configs/pspnet/pspnet_r50-d8_4xb4-320k_coco-stuff164k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 164k
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004-be9610cc.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb4-320k_coco-stuff164k-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 41.95
+      mIoU(ms+flip): 42.42
+  Config: configs/pspnet/pspnet_r101-d8_4xb4-320k_coco-stuff164k-512x512.py
+  Metadata:
+    Training Data: COCO-Stuff 164k
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004-72220c60.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r18-d8_4xb4-80k_loveda-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: LoveDA
+    Metrics:
+      mIoU: 48.62
+      mIoU(ms+flip): 47.57
+  Config: configs/pspnet/pspnet_r18-d8_4xb4-80k_loveda-512x512.py
+  Metadata:
+    Training Data: LoveDA
+    Batch Size: 16
+    Architecture:
+    - R-18-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.45
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x512_80k_loveda/pspnet_r18-d8_512x512_80k_loveda_20211105_052100-b97697f1.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x512_80k_loveda/pspnet_r18-d8_512x512_80k_loveda_20211105_052100.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50-d8_4xb4-80k_loveda-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: LoveDA
+    Metrics:
+      mIoU: 50.46
+      mIoU(ms+flip): 50.19
+  Config: configs/pspnet/pspnet_r50-d8_4xb4-80k_loveda-512x512.py
+  Metadata:
+    Training Data: LoveDA
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.14
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_loveda/pspnet_r50-d8_512x512_80k_loveda_20211104_155728-88610f9f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_loveda/pspnet_r50-d8_512x512_80k_loveda_20211104_155728.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb4-80k_loveda-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: LoveDA
+    Metrics:
+      mIoU: 51.86
+      mIoU(ms+flip): 51.34
+  Config: configs/pspnet/pspnet_r101-d8_4xb4-80k_loveda-512x512.py
+  Metadata:
+    Training Data: LoveDA
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.61
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_loveda/pspnet_r101-d8_512x512_80k_loveda_20211104_153212-1c06c6a8.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_loveda/pspnet_r101-d8_512x512_80k_loveda_20211104_153212.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r18-d8_4xb4-80k_potsdam-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Potsdam
+    Metrics:
+      mIoU: 77.09
+      mIoU(ms+flip): 78.3
+  Config: configs/pspnet/pspnet_r18-d8_4xb4-80k_potsdam-512x512.py
+  Metadata:
+    Training Data: Potsdam
+    Batch Size: 16
+    Architecture:
+    - R-18-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_potsdam/pspnet_r18-d8_4x4_512x512_80k_potsdam_20211220_125612-7cd046e1.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_potsdam/pspnet_r18-d8_4x4_512x512_80k_potsdam_20211220_125612.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50-d8_4xb4-80k_potsdam-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Potsdam
+    Metrics:
+      mIoU: 78.12
+      mIoU(ms+flip): 78.98
+  Config: configs/pspnet/pspnet_r50-d8_4xb4-80k_potsdam-512x512.py
+  Metadata:
+    Training Data: Potsdam
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.14
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_potsdam/pspnet_r50-d8_4x4_512x512_80k_potsdam_20211219_043541-2dd5fe67.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_potsdam/pspnet_r50-d8_4x4_512x512_80k_potsdam_20211219_043541.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb4-80k_potsdam-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Potsdam
+    Metrics:
+      mIoU: 78.62
+      mIoU(ms+flip): 79.47
+  Config: configs/pspnet/pspnet_r101-d8_4xb4-80k_potsdam-512x512.py
+  Metadata:
+    Training Data: Potsdam
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.61
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_potsdam/pspnet_r101-d8_4x4_512x512_80k_potsdam_20211220_125612-aed036c4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_potsdam/pspnet_r101-d8_4x4_512x512_80k_potsdam_20211220_125612.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r18-d8_4xb4-80k_vaihingen-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Vaihingen
+    Metrics:
+      mIoU: 71.46
+      mIoU(ms+flip): 73.36
+  Config: configs/pspnet/pspnet_r18-d8_4xb4-80k_vaihingen-512x512.py
+  Metadata:
+    Training Data: Vaihingen
+    Batch Size: 16
+    Architecture:
+    - R-18-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.45
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_vaihingen/pspnet_r18-d8_4x4_512x512_80k_vaihingen_20211228_160355-52a8a6f6.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_vaihingen/pspnet_r18-d8_4x4_512x512_80k_vaihingen_20211228_160355.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50-d8_4xb4-80k_vaihingen-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Vaihingen
+    Metrics:
+      mIoU: 72.36
+      mIoU(ms+flip): 73.75
+  Config: configs/pspnet/pspnet_r50-d8_4xb4-80k_vaihingen-512x512.py
+  Metadata:
+    Training Data: Vaihingen
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.14
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_vaihingen/pspnet_r50-d8_4x4_512x512_80k_vaihingen_20211228_160355-382f8f5b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_vaihingen/pspnet_r50-d8_4x4_512x512_80k_vaihingen_20211228_160355.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r101-d8_4xb4-80k_vaihingen-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Vaihingen
+    Metrics:
+      mIoU: 72.61
+      mIoU(ms+flip): 74.18
+  Config: configs/pspnet/pspnet_r101-d8_4xb4-80k_vaihingen-512x512.py
+  Metadata:
+    Training Data: Vaihingen
+    Batch Size: 16
+    Architecture:
+    - R-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.61
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_vaihingen/pspnet_r101-d8_4x4_512x512_80k_vaihingen_20211231_230806-8eba0a09.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_vaihingen/pspnet_r101-d8_4x4_512x512_80k_vaihingen_20211231_230806.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r18-d8_4xb4-80k_isaid-896x896
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: iSAID
+    Metrics:
+      mIoU: 60.22
+      mIoU(ms+flip): 61.25
+  Config: configs/pspnet/pspnet_r18-d8_4xb4-80k_isaid-896x896.py
+  Metadata:
+    Training Data: iSAID
+    Batch Size: 16
+    Architecture:
+    - R-18-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 4.52
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_896x896_80k_isaid/pspnet_r18-d8_4x4_896x896_80k_isaid_20220110_180526-e84c0b6a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_896x896_80k_isaid/pspnet_r18-d8_4x4_896x896_80k_isaid_20220110_180526.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
+- Name: pspnet_r50-d8_4xb4-80k_isaid-896x896
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: iSAID
+    Metrics:
+      mIoU: 65.36
+      mIoU(ms+flip): 66.48
+  Config: configs/pspnet/pspnet_r50-d8_4xb4-80k_isaid-896x896.py
+  Metadata:
+    Training Data: iSAID
+    Batch Size: 16
+    Architecture:
+    - R-50-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 16.58
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_896x896_80k_isaid/pspnet_r50-d8_4x4_896x896_80k_isaid_20220110_180629-1f21dc32.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_896x896_80k_isaid/pspnet_r50-d8_4x4_896x896_80k_isaid_20220110_180629.log.json
+  Paper:
+    Title: Pyramid Scene Parsing Network
+    URL: https://arxiv.org/abs/1612.01105
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
+  Framework: PyTorch
diff --git a/configs/pspnet/pspnet.yml b/configs/pspnet/pspnet.yml
deleted file mode 100644
index 7f811efd0f..0000000000
--- a/configs/pspnet/pspnet.yml
+++ /dev/null
@@ -1,1077 +0,0 @@
-Collections:
-- Name: PSPNet
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-    - Pascal VOC 2012 + Aug
-    - Pascal Context
-    - Pascal Context 59
-    - Dark Zurich and Nighttime Driving
-    - COCO-Stuff 10k
-    - COCO-Stuff 164k
-    - LoveDA
-    - Potsdam
-    - Vaihingen
-    - iSAID
-  Paper:
-    URL: https://arxiv.org/abs/1612.01105
-    Title: Pyramid Scene Parsing Network
-  README: configs/pspnet/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/hszhao/PSPNet
-Models:
-- Name: pspnet_r50-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 245.7
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 6.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.85
-      mIoU(ms+flip): 79.18
-  Config: configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth
-- Name: pspnet_r101-d8_4xb2-40k_cityscapes-512x1024
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 373.13
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 9.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.34
-      mIoU(ms+flip): 79.74
-  Config: configs/pspnet/pspnet_r101-d8_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751-467e7cf4.pth
-- Name: pspnet_r50-d8_4xb2-40k_cityscapes-769x769
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 568.18
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 6.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.26
-      mIoU(ms+flip): 79.88
-  Config: configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_40k_cityscapes/pspnet_r50-d8_769x769_40k_cityscapes_20200606_112725-86638686.pth
-- Name: pspnet_r101-d8_4xb2-40k_cityscapes-769x769
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 869.57
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 10.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.08
-      mIoU(ms+flip): 80.28
-  Config: configs/pspnet/pspnet_r101-d8_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_40k_cityscapes/pspnet_r101-d8_769x769_40k_cityscapes_20200606_112753-61c6f5be.pth
-- Name: pspnet_r18-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-18-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 63.65
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 1.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 74.87
-      mIoU(ms+flip): 76.04
-  Config: configs/pspnet/pspnet_r18-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x1024_80k_cityscapes/pspnet_r18-d8_512x1024_80k_cityscapes_20201225_021458-09ffa746.pth
-- Name: pspnet_r50-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.55
-      mIoU(ms+flip): 79.79
-  Config: configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_512x1024_80k_cityscapes_20200606_112131-2376f12b.pth
-- Name: pspnet_r50-d8-rsb_4xb2-adamw-80k_cityscapes-512x1024
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50b-D8 rsb
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 261.78
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 6.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.47
-      mIoU(ms+flip): 79.45
-  Config: configs/pspnet/pspnet_r50-d8-rsb_4xb2-adamw-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220315_123238-588c30be.pth
-- Name: pspnet_r101-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.76
-      mIoU(ms+flip): 81.01
-  Config: configs/pspnet/pspnet_r101-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes/pspnet_r101-d8_512x1024_80k_cityscapes_20200606_112211-e1e1100f.pth
-- Name: pspnet_r101-d8_4xb2-amp-80k_cityscapes-512x1024
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 114.03
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: AMP
-      resolution: (512,1024)
-    Training Memory (GB): 5.34
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.46
-  Config: configs/pspnet/pspnet_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_fp16_512x1024_80k_cityscapes/pspnet_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230919-a0875e5c.pth
-- Name: pspnet_r18-d8_4xb2-80k_cityscapes-769x769
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-18-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 161.29
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 1.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 75.9
-      mIoU(ms+flip): 77.86
-  Config: configs/pspnet/pspnet_r18-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_769x769_80k_cityscapes/pspnet_r18-d8_769x769_80k_cityscapes_20201225_021458-3deefc62.pth
-- Name: pspnet_r50-d8_4xb2-80k_cityscapes-769x769
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.59
-      mIoU(ms+flip): 80.69
-  Config: configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_80k_cityscapes/pspnet_r50-d8_769x769_80k_cityscapes_20200606_210121-5ccf03dd.pth
-- Name: pspnet_r101-d8_4xb2-80k_cityscapes-769x769
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.77
-      mIoU(ms+flip): 81.06
-  Config: configs/pspnet/pspnet_r101-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_80k_cityscapes/pspnet_r101-d8_769x769_80k_cityscapes_20200606_225055-dba412fa.pth
-- Name: pspnet_r18b-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-18b-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 61.43
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 1.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 74.23
-      mIoU(ms+flip): 75.79
-  Config: configs/pspnet/pspnet_r18b-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_512x1024_80k_cityscapes/pspnet_r18b-d8_512x1024_80k_cityscapes_20201226_063116-26928a60.pth
-- Name: pspnet_r50b-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50b-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 232.56
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 6.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.22
-      mIoU(ms+flip): 79.46
-  Config: configs/pspnet/pspnet_r50b-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_512x1024_80k_cityscapes/pspnet_r50b-d8_512x1024_80k_cityscapes_20201225_094315-6344287a.pth
-- Name: pspnet_r101b-d8_4xb2-80k_cityscapes-512x1024
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101b-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 362.32
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 9.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.69
-      mIoU(ms+flip): 80.79
-  Config: configs/pspnet/pspnet_r101b-d8_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes_20201226_170012-3a4d38ab.pth
-- Name: pspnet_r18b-d8_4xb2-80k_cityscapes-769x769
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-18b-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 156.01
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 1.7
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 74.92
-      mIoU(ms+flip): 76.9
-  Config: configs/pspnet/pspnet_r18b-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_769x769_80k_cityscapes/pspnet_r18b-d8_769x769_80k_cityscapes_20201226_080942-bf98d186.pth
-- Name: pspnet_r50b-d8_4xb2-80k_cityscapes-769x769
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50b-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 531.91
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 6.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.5
-      mIoU(ms+flip): 79.96
-  Config: configs/pspnet/pspnet_r50b-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_769x769_80k_cityscapes/pspnet_r50b-d8_769x769_80k_cityscapes_20201225_094316-4c643cf6.pth
-- Name: pspnet_r101b-d8_4xb2-80k_cityscapes-769x769
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101b-D8
-    crop size: (769,769)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 854.7
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 10.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.87
-      mIoU(ms+flip): 80.04
-  Config: configs/pspnet/pspnet_r101b-d8_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_769x769_80k_cityscapes/pspnet_r101b-d8_769x769_80k_cityscapes_20201226_171823-f0e7c293.pth
-- Name: pspnet_r50b-d32_4xb2-80k_cityscapes-512x1024
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50-D32
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 65.75
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 3.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 73.88
-      mIoU(ms+flip): 76.85
-  Config: configs/pspnet/pspnet_r50b-d32_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_512x1024_80k_cityscapes/pspnet_r50-d32_512x1024_80k_cityscapes_20220316_224840-9092b254.pth
-- Name: pspnet_r50-d32_rsb_4xb2-adamw-80k_cityscapes-512x1024
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50b-D32 rsb
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 62.19
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 3.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 74.09
-      mIoU(ms+flip): 77.18
-  Config: configs/pspnet/pspnet_r50-d32_rsb_4xb2-adamw-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220316_141229-dd9c9610.pth
-- Name: pspnet_r50b-d32_4xb2-80k_cityscapes-512x1024
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50b-D32
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 64.89
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 2.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 72.61
-      mIoU(ms+flip): 75.51
-  Config: configs/pspnet/pspnet_r50b-d32_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d32_512x1024_80k_cityscapes/pspnet_r50b-d32_512x1024_80k_cityscapes_20220311_152152-23bcaf8c.pth
-- Name: pspnet_r50-d8_4xb4-80k_ade20k-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 42.5
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 8.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 41.13
-      mIoU(ms+flip): 41.94
-  Config: configs/pspnet/pspnet_r50-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_ade20k/pspnet_r50-d8_512x512_80k_ade20k_20200615_014128-15a8b914.pth
-- Name: pspnet_r101-d8_4xb4-80k_ade20k-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 65.36
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 12.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.57
-      mIoU(ms+flip): 44.35
-  Config: configs/pspnet/pspnet_r101-d8_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_ade20k/pspnet_r101-d8_512x512_80k_ade20k_20200614_031423-b6e782f0.pth
-- Name: pspnet_r50-d8_4xb4-160k_ade20k-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.48
-      mIoU(ms+flip): 43.44
-  Config: configs/pspnet/pspnet_r50-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_160k_ade20k/pspnet_r50-d8_512x512_160k_ade20k_20200615_184358-1890b0bd.pth
-- Name: pspnet_r101-d8_4xb4-160k_ade20k-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 44.39
-      mIoU(ms+flip): 45.35
-  Config: configs/pspnet/pspnet_r101-d8_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_160k_ade20k/pspnet_r101-d8_512x512_160k_ade20k_20200615_100650-967c316f.pth
-- Name: pspnet_r50-d8_4xb4-20k_voc12aug-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 42.39
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 76.78
-      mIoU(ms+flip): 77.61
-  Config: configs/pspnet/pspnet_r50-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_20k_voc12aug/pspnet_r50-d8_512x512_20k_voc12aug_20200617_101958-ed5dfbd9.pth
-- Name: pspnet_r101-d8_4xb4-20k_voc12aug-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 66.58
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 78.47
-      mIoU(ms+flip): 79.25
-  Config: configs/pspnet/pspnet_r101-d8_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_20k_voc12aug/pspnet_r101-d8_512x512_20k_voc12aug_20200617_102003-4aef3c9a.pth
-- Name: pspnet_r50-d8_4xb4-40k_voc12aug-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 77.29
-      mIoU(ms+flip): 78.48
-  Config: configs/pspnet/pspnet_r50-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_40k_voc12aug/pspnet_r50-d8_512x512_40k_voc12aug_20200613_161222-ae9c1b8c.pth
-- Name: pspnet_r101-d8_4xb4-40k_voc12aug-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 78.52
-      mIoU(ms+flip): 79.57
-  Config: configs/pspnet/pspnet_r101-d8_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_40k_voc12aug/pspnet_r101-d8_512x512_40k_voc12aug_20200613_161222-bc933b18.pth
-- Name: pspnet_r101-d8_4xb4-40k_pascal-context-480x480
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (480,480)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 103.31
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (480,480)
-    Training Memory (GB): 8.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context
-    Metrics:
-      mIoU: 46.6
-      mIoU(ms+flip): 47.78
-  Config: configs/pspnet/pspnet_r101-d8_4xb4-40k_pascal-context-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context/pspnet_r101-d8_480x480_40k_pascal_context_20200911_211210-bf0f5d7c.pth
-- Name: pspnet_r101-d8_4xb4-80k_pascal-context-480x480
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (480,480)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context
-    Metrics:
-      mIoU: 46.03
-      mIoU(ms+flip): 47.15
-  Config: configs/pspnet/pspnet_r101-d8_4xb4-80k_pascal-context-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context/pspnet_r101-d8_480x480_80k_pascal_context_20200911_190530-c86d6233.pth
-- Name: pspnet_r101-d8_4xb4-40k_pascal-context-59-480x480
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (480,480)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context 59
-    Metrics:
-      mIoU: 52.02
-      mIoU(ms+flip): 53.54
-  Config: configs/pspnet/pspnet_r101-d8_4xb4-40k_pascal-context-59-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context_59/pspnet_r101-d8_480x480_40k_pascal_context_59_20210416_114524-86d44cd4.pth
-- Name: pspnet_r101-d8_4xb4-80k_pascal-context-59-480x480
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (480,480)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal Context 59
-    Metrics:
-      mIoU: 52.47
-      mIoU(ms+flip): 53.99
-  Config: configs/pspnet/pspnet_r101-d8_4xb4-80k_pascal-context-59-480x480.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context_59/pspnet_r101-d8_480x480_80k_pascal_context_59_20210416_114418-fa6caaa2.pth
-- Name: pspnet_r50-d8_4xb4-20k_coco-stuff10k-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 48.78
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 10k
-    Metrics:
-      mIoU: 35.69
-      mIoU(ms+flip): 36.62
-  Config: configs/pspnet/pspnet_r50-d8_4xb4-20k_coco-stuff10k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k_20210820_203258-b88df27f.pth
-- Name: pspnet_r101-d8_4xb4-20k_coco-stuff10k-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 90.09
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 13.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 10k
-    Metrics:
-      mIoU: 37.26
-      mIoU(ms+flip): 38.52
-  Config: configs/pspnet/pspnet_r101-d8_4xb4-20k_coco-stuff10k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k_20210820_232135-76aae482.pth
-- Name: pspnet_r50-d8_4xb4-40k_coco-stuff10k-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 10k
-    Metrics:
-      mIoU: 36.33
-      mIoU(ms+flip): 37.24
-  Config: configs/pspnet/pspnet_r50-d8_4xb4-40k_coco-stuff10k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_030857-92e2902b.pth
-- Name: pspnet_r101-d8_4xb4-40k_coco-stuff10k-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 10k
-    Metrics:
-      mIoU: 37.76
-      mIoU(ms+flip): 38.86
-  Config: configs/pspnet/pspnet_r101-d8_4xb4-40k_coco-stuff10k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_014022-831aec95.pth
-- Name: pspnet_r50-d8_4xb4-80k_coco-stuff164k-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 48.78
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 164k
-    Metrics:
-      mIoU: 38.8
-      mIoU(ms+flip): 39.19
-  Config: configs/pspnet/pspnet_r50-d8_4xb4-80k_coco-stuff164k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034-0e41b2db.pth
-- Name: pspnet_r101-d8_4xb4-80k_coco-stuff164k-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 90.09
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 13.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 164k
-    Metrics:
-      mIoU: 40.34
-      mIoU(ms+flip): 40.79
-  Config: configs/pspnet/pspnet_r101-d8_4xb4-80k_coco-stuff164k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034-7eb41789.pth
-- Name: pspnet_r50-d8_4xb4-160k_coco-stuff164k-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 164k
-    Metrics:
-      mIoU: 39.64
-      mIoU(ms+flip): 39.97
-  Config: configs/pspnet/pspnet_r50-d8_4xb4-160k_coco-stuff164k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004-51276a57.pth
-- Name: pspnet_r101-d8_4xb4-160k_coco-stuff164k-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 164k
-    Metrics:
-      mIoU: 41.28
-      mIoU(ms+flip): 41.66
-  Config: configs/pspnet/pspnet_r101-d8_4xb4-160k_coco-stuff164k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004-4af9621b.pth
-- Name: pspnet_r50-d8_4xb4-320k_coco-stuff164k-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 320000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 164k
-    Metrics:
-      mIoU: 40.53
-      mIoU(ms+flip): 40.75
-  Config: configs/pspnet/pspnet_r50-d8_4xb4-320k_coco-stuff164k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004-be9610cc.pth
-- Name: pspnet_r101-d8_4xb4-320k_coco-stuff164k-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 320000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: COCO-Stuff 164k
-    Metrics:
-      mIoU: 41.95
-      mIoU(ms+flip): 42.42
-  Config: configs/pspnet/pspnet_r101-d8_4xb4-320k_coco-stuff164k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004-72220c60.pth
-- Name: pspnet_r18-d8_4xb4-80k_loveda-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-18-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 37.22
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 1.45
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: LoveDA
-    Metrics:
-      mIoU: 48.62
-      mIoU(ms+flip): 47.57
-  Config: configs/pspnet/pspnet_r18-d8_4xb4-80k_loveda-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x512_80k_loveda/pspnet_r18-d8_512x512_80k_loveda_20211105_052100-b97697f1.pth
-- Name: pspnet_r50-d8_4xb4-80k_loveda-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 151.52
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.14
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: LoveDA
-    Metrics:
-      mIoU: 50.46
-      mIoU(ms+flip): 50.19
-  Config: configs/pspnet/pspnet_r50-d8_4xb4-80k_loveda-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_loveda/pspnet_r50-d8_512x512_80k_loveda_20211104_155728-88610f9f.pth
-- Name: pspnet_r101-d8_4xb4-80k_loveda-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 218.34
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.61
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: LoveDA
-    Metrics:
-      mIoU: 51.86
-      mIoU(ms+flip): 51.34
-  Config: configs/pspnet/pspnet_r101-d8_4xb4-80k_loveda-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_loveda/pspnet_r101-d8_512x512_80k_loveda_20211104_153212-1c06c6a8.pth
-- Name: pspnet_r18-d8_4xb4-80k_potsdam-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-18-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 11.75
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 1.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Potsdam
-    Metrics:
-      mIoU: 77.09
-      mIoU(ms+flip): 78.3
-  Config: configs/pspnet/pspnet_r18-d8_4xb4-80k_potsdam-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_potsdam/pspnet_r18-d8_4x4_512x512_80k_potsdam_20211220_125612-7cd046e1.pth
-- Name: pspnet_r50-d8_4xb4-80k_potsdam-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 33.1
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.14
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Potsdam
-    Metrics:
-      mIoU: 78.12
-      mIoU(ms+flip): 78.98
-  Config: configs/pspnet/pspnet_r50-d8_4xb4-80k_potsdam-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_potsdam/pspnet_r50-d8_4x4_512x512_80k_potsdam_20211219_043541-2dd5fe67.pth
-- Name: pspnet_r101-d8_4xb4-80k_potsdam-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 51.55
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.61
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Potsdam
-    Metrics:
-      mIoU: 78.62
-      mIoU(ms+flip): 79.47
-  Config: configs/pspnet/pspnet_r101-d8_4xb4-80k_potsdam-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_potsdam/pspnet_r101-d8_4x4_512x512_80k_potsdam_20211220_125612-aed036c4.pth
-- Name: pspnet_r18-d8_4xb4-80k_vaihingen-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-18-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 11.76
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 1.45
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Vaihingen
-    Metrics:
-      mIoU: 71.46
-      mIoU(ms+flip): 73.36
-  Config: configs/pspnet/pspnet_r18-d8_4xb4-80k_vaihingen-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_vaihingen/pspnet_r18-d8_4x4_512x512_80k_vaihingen_20211228_160355-52a8a6f6.pth
-- Name: pspnet_r50-d8_4xb4-80k_vaihingen-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 33.01
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.14
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Vaihingen
-    Metrics:
-      mIoU: 72.36
-      mIoU(ms+flip): 73.75
-  Config: configs/pspnet/pspnet_r50-d8_4xb4-80k_vaihingen-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_vaihingen/pspnet_r50-d8_4x4_512x512_80k_vaihingen_20211228_160355-382f8f5b.pth
-- Name: pspnet_r101-d8_4xb4-80k_vaihingen-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-101-D8
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 50.08
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.61
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Vaihingen
-    Metrics:
-      mIoU: 72.61
-      mIoU(ms+flip): 74.18
-  Config: configs/pspnet/pspnet_r101-d8_4xb4-80k_vaihingen-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_vaihingen/pspnet_r101-d8_4x4_512x512_80k_vaihingen_20211231_230806-8eba0a09.pth
-- Name: pspnet_r18-d8_4xb4-80k_isaid-896x896
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-18-D8
-    crop size: (896,896)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 37.16
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (896,896)
-    Training Memory (GB): 4.52
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: iSAID
-    Metrics:
-      mIoU: 60.22
-      mIoU(ms+flip): 61.25
-  Config: configs/pspnet/pspnet_r18-d8_4xb4-80k_isaid-896x896.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_896x896_80k_isaid/pspnet_r18-d8_4x4_896x896_80k_isaid_20220110_180526-e84c0b6a.pth
-- Name: pspnet_r50-d8_4xb4-80k_isaid-896x896
-  In Collection: PSPNet
-  Metadata:
-    backbone: R-50-D8
-    crop size: (896,896)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 112.61
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (896,896)
-    Training Memory (GB): 16.58
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: iSAID
-    Metrics:
-      mIoU: 65.36
-      mIoU(ms+flip): 66.48
-  Config: configs/pspnet/pspnet_r50-d8_4xb4-80k_isaid-896x896.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_896x896_80k_isaid/pspnet_r50-d8_4x4_896x896_80k_isaid_20220110_180629-1f21dc32.pth
diff --git a/configs/resnest/README.md b/configs/resnest/README.md
index 7f07d147b7..d27bbe2807 100644
--- a/configs/resnest/README.md
+++ b/configs/resnest/README.md
@@ -1,6 +1,6 @@
 # ResNeSt
 
-[ResNeSt: Split-Attention Networks](https://arxiv.org/abs/2004.08955)
+> [ResNeSt: Split-Attention Networks](https://arxiv.org/abs/2004.08955)
 
 ## Introduction
 
@@ -22,6 +22,26 @@ It is well known that featuremap attention and multi-path representation are imp
 <img src="https://user-images.githubusercontent.com/24582831/142902526-3cf33345-7e40-47a6-985e-4381857e21df.png" width="60%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                                               |
+| ---------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN        | S-101-D8 | 512x1024  |   80000 |     11.4 | 2.39           | V100   | 77.56 | 78.98         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_fcn_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x1024_80k_cityscapes/fcn_s101-d8_512x1024_80k_cityscapes_20200807_140631-f8d155b3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x1024_80k_cityscapes/fcn_s101-d8_512x1024_80k_cityscapes-20200807_140631.log.json)                                         |
+| PSPNet     | S-101-D8 | 512x1024  |   80000 |     11.8 | 2.52           | V100   | 78.57 | 79.19         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_pspnet_4xb2-80k_cityscapes512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x1024_80k_cityscapes/pspnet_s101-d8_512x1024_80k_cityscapes_20200807_140631-c75f3b99.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x1024_80k_cityscapes/pspnet_s101-d8_512x1024_80k_cityscapes-20200807_140631.log.json)                             |
+| DeepLabV3  | S-101-D8 | 512x1024  |   80000 |     11.9 | 1.88           | V100   | 79.67 | 80.51         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_deeplabv3_4xb2-80k_cityscapes-512x1024.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x1024_80k_cityscapes/deeplabv3_s101-d8_512x1024_80k_cityscapes_20200807_144429-b73c4270.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x1024_80k_cityscapes/deeplabv3_s101-d8_512x1024_80k_cityscapes-20200807_144429.log.json)                 |
+| DeepLabV3+ | S-101-D8 | 512x1024  |   80000 |     13.2 | 2.36           | V100   | 79.62 | 80.27         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_deeplabv3plus_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x1024_80k_cityscapes/deeplabv3plus_s101-d8_512x1024_80k_cityscapes_20200807_144429-1239eb43.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x1024_80k_cityscapes/deeplabv3plus_s101-d8_512x1024_80k_cityscapes-20200807_144429.log.json) |
+
+### ADE20K
+
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                               |
+| ---------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | --------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN        | S-101-D8 | 512x512   |  160000 |     14.2 | 12.86          | V100   | 45.62 | 46.16         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_fcn_4xb4-160k_ade20k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x512_160k_ade20k/fcn_s101-d8_512x512_160k_ade20k_20200807_145416-d3160329.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x512_160k_ade20k/fcn_s101-d8_512x512_160k_ade20k-20200807_145416.log.json)                                         |
+| PSPNet     | S-101-D8 | 512x512   |  160000 |     14.2 | 13.02          | V100   | 45.44 | 46.28         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_pspnet_4xb4-160k_ade20k-512x512.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x512_160k_ade20k/pspnet_s101-d8_512x512_160k_ade20k_20200807_145416-a6daa92a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x512_160k_ade20k/pspnet_s101-d8_512x512_160k_ade20k-20200807_145416.log.json)                             |
+| DeepLabV3  | S-101-D8 | 512x512   |  160000 |     14.6 | 9.28           | V100   | 45.71 | 46.59         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_deeplabv3_4xb4-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x512_160k_ade20k/deeplabv3_s101-d8_512x512_160k_ade20k_20200807_144503-17ecabe5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x512_160k_ade20k/deeplabv3_s101-d8_512x512_160k_ade20k-20200807_144503.log.json)                 |
+| DeepLabV3+ | S-101-D8 | 512x512   |  160000 |     16.2 | 11.96          | V100   | 46.47 | 47.27         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_deeplabv3plus_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x512_160k_ade20k/deeplabv3plus_s101-d8_512x512_160k_ade20k_20200807_144503-27b26226.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x512_160k_ade20k/deeplabv3plus_s101-d8_512x512_160k_ade20k-20200807_144503.log.json) |
+
 ## Citation
 
 ```bibtex
@@ -32,23 +52,3 @@ journal={arXiv preprint arXiv:2004.08955},
 year={2020}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                                               |
-| ---------- | -------- | --------- | ------: | -------: | -------------- | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN        | S-101-D8 | 512x1024  |   80000 |     11.4 | 2.39           | 77.56 | 78.98         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_fcn_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x1024_80k_cityscapes/fcn_s101-d8_512x1024_80k_cityscapes_20200807_140631-f8d155b3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x1024_80k_cityscapes/fcn_s101-d8_512x1024_80k_cityscapes-20200807_140631.log.json)                                         |
-| PSPNet     | S-101-D8 | 512x1024  |   80000 |     11.8 | 2.52           | 78.57 | 79.19         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_pspnet_4xb2-80k_cityscapes512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x1024_80k_cityscapes/pspnet_s101-d8_512x1024_80k_cityscapes_20200807_140631-c75f3b99.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x1024_80k_cityscapes/pspnet_s101-d8_512x1024_80k_cityscapes-20200807_140631.log.json)                             |
-| DeepLabV3  | S-101-D8 | 512x1024  |   80000 |     11.9 | 1.88           | 79.67 | 80.51         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_deeplabv3_4xb2-80k_cityscapes-512x1024.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x1024_80k_cityscapes/deeplabv3_s101-d8_512x1024_80k_cityscapes_20200807_144429-b73c4270.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x1024_80k_cityscapes/deeplabv3_s101-d8_512x1024_80k_cityscapes-20200807_144429.log.json)                 |
-| DeepLabV3+ | S-101-D8 | 512x1024  |   80000 |     13.2 | 2.36           | 79.62 | 80.27         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_deeplabv3plus_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x1024_80k_cityscapes/deeplabv3plus_s101-d8_512x1024_80k_cityscapes_20200807_144429-1239eb43.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x1024_80k_cityscapes/deeplabv3plus_s101-d8_512x1024_80k_cityscapes-20200807_144429.log.json) |
-
-### ADE20K
-
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                               |
-| ---------- | -------- | --------- | ------: | -------: | -------------- | ----: | ------------- | --------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN        | S-101-D8 | 512x512   |  160000 |     14.2 | 12.86          | 45.62 | 46.16         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_fcn_4xb4-160k_ade20k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x512_160k_ade20k/fcn_s101-d8_512x512_160k_ade20k_20200807_145416-d3160329.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x512_160k_ade20k/fcn_s101-d8_512x512_160k_ade20k-20200807_145416.log.json)                                         |
-| PSPNet     | S-101-D8 | 512x512   |  160000 |     14.2 | 13.02          | 45.44 | 46.28         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_pspnet_4xb4-160k_ade20k-512x512.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x512_160k_ade20k/pspnet_s101-d8_512x512_160k_ade20k_20200807_145416-a6daa92a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x512_160k_ade20k/pspnet_s101-d8_512x512_160k_ade20k-20200807_145416.log.json)                             |
-| DeepLabV3  | S-101-D8 | 512x512   |  160000 |     14.6 | 9.28           | 45.71 | 46.59         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_deeplabv3_4xb4-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x512_160k_ade20k/deeplabv3_s101-d8_512x512_160k_ade20k_20200807_144503-17ecabe5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x512_160k_ade20k/deeplabv3_s101-d8_512x512_160k_ade20k-20200807_144503.log.json)                 |
-| DeepLabV3+ | S-101-D8 | 512x512   |  160000 |     16.2 | 11.96          | 46.47 | 47.27         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_deeplabv3plus_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x512_160k_ade20k/deeplabv3plus_s101-d8_512x512_160k_ade20k_20200807_144503-27b26226.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x512_160k_ade20k/deeplabv3plus_s101-d8_512x512_160k_ade20k-20200807_144503.log.json) |
diff --git a/configs/resnest/metafile.yaml b/configs/resnest/metafile.yaml
new file mode 100644
index 0000000000..0b8d41ebfd
--- /dev/null
+++ b/configs/resnest/metafile.yaml
@@ -0,0 +1,193 @@
+Models:
+- Name: resnest_s101-d8_fcn_4xb2-80k_cityscapes-512x1024
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.56
+      mIoU(ms+flip): 78.98
+  Config: configs/resnest/resnest_s101-d8_fcn_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - S-101-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 11.4
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x1024_80k_cityscapes/fcn_s101-d8_512x1024_80k_cityscapes_20200807_140631-f8d155b3.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x1024_80k_cityscapes/fcn_s101-d8_512x1024_80k_cityscapes-20200807_140631.log.json
+  Paper:
+    Title: 'ResNeSt: Split-Attention Networks'
+    URL: https://arxiv.org/abs/2004.08955
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/resnest.py#L271
+  Framework: PyTorch
+- Name: resnest_s101-d8_pspnet_4xb2-80k_cityscapes512x1024
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.57
+      mIoU(ms+flip): 79.19
+  Config: configs/resnest/resnest_s101-d8_pspnet_4xb2-80k_cityscapes512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - S-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 11.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x1024_80k_cityscapes/pspnet_s101-d8_512x1024_80k_cityscapes_20200807_140631-c75f3b99.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x1024_80k_cityscapes/pspnet_s101-d8_512x1024_80k_cityscapes-20200807_140631.log.json
+  Paper:
+    Title: 'ResNeSt: Split-Attention Networks'
+    URL: https://arxiv.org/abs/2004.08955
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/resnest.py#L271
+  Framework: PyTorch
+- Name: resnest_s101-d8_deeplabv3_4xb2-80k_cityscapes-512x1024
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.67
+      mIoU(ms+flip): 80.51
+  Config: configs/resnest/resnest_s101-d8_deeplabv3_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - S-101-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 11.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x1024_80k_cityscapes/deeplabv3_s101-d8_512x1024_80k_cityscapes_20200807_144429-b73c4270.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x1024_80k_cityscapes/deeplabv3_s101-d8_512x1024_80k_cityscapes-20200807_144429.log.json
+  Paper:
+    Title: 'ResNeSt: Split-Attention Networks'
+    URL: https://arxiv.org/abs/2004.08955
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/resnest.py#L271
+  Framework: PyTorch
+- Name: resnest_s101-d8_deeplabv3plus_4xb2-80k_cityscapes-512x1024
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.62
+      mIoU(ms+flip): 80.27
+  Config: configs/resnest/resnest_s101-d8_deeplabv3plus_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - S-101-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 13.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x1024_80k_cityscapes/deeplabv3plus_s101-d8_512x1024_80k_cityscapes_20200807_144429-1239eb43.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x1024_80k_cityscapes/deeplabv3plus_s101-d8_512x1024_80k_cityscapes-20200807_144429.log.json
+  Paper:
+    Title: 'ResNeSt: Split-Attention Networks'
+    URL: https://arxiv.org/abs/2004.08955
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/resnest.py#L271
+  Framework: PyTorch
+- Name: resnest_s101-d8_fcn_4xb4-160k_ade20k-512x512
+  In Collection: FCN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.62
+      mIoU(ms+flip): 46.16
+  Config: configs/resnest/resnest_s101-d8_fcn_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - S-101-D8
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 14.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x512_160k_ade20k/fcn_s101-d8_512x512_160k_ade20k_20200807_145416-d3160329.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x512_160k_ade20k/fcn_s101-d8_512x512_160k_ade20k-20200807_145416.log.json
+  Paper:
+    Title: 'ResNeSt: Split-Attention Networks'
+    URL: https://arxiv.org/abs/2004.08955
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/resnest.py#L271
+  Framework: PyTorch
+- Name: resnest_s101-d8_pspnet_4xb4-160k_ade20k-512x512
+  In Collection: PSPNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.44
+      mIoU(ms+flip): 46.28
+  Config: configs/resnest/resnest_s101-d8_pspnet_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - S-101-D8
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 14.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x512_160k_ade20k/pspnet_s101-d8_512x512_160k_ade20k_20200807_145416-a6daa92a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x512_160k_ade20k/pspnet_s101-d8_512x512_160k_ade20k-20200807_145416.log.json
+  Paper:
+    Title: 'ResNeSt: Split-Attention Networks'
+    URL: https://arxiv.org/abs/2004.08955
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/resnest.py#L271
+  Framework: PyTorch
+- Name: resnest_s101-d8_deeplabv3_4xb4-160k_ade20k-512x512
+  In Collection: DeepLabV3
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.71
+      mIoU(ms+flip): 46.59
+  Config: configs/resnest/resnest_s101-d8_deeplabv3_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - S-101-D8
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 14.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x512_160k_ade20k/deeplabv3_s101-d8_512x512_160k_ade20k_20200807_144503-17ecabe5.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x512_160k_ade20k/deeplabv3_s101-d8_512x512_160k_ade20k-20200807_144503.log.json
+  Paper:
+    Title: 'ResNeSt: Split-Attention Networks'
+    URL: https://arxiv.org/abs/2004.08955
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/resnest.py#L271
+  Framework: PyTorch
+- Name: resnest_s101-d8_deeplabv3plus_4xb4-160k_ade20k-512x512
+  In Collection: DeepLabV3+
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 46.47
+      mIoU(ms+flip): 47.27
+  Config: configs/resnest/resnest_s101-d8_deeplabv3plus_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - S-101-D8
+    - DeepLabV3+
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 16.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x512_160k_ade20k/deeplabv3plus_s101-d8_512x512_160k_ade20k_20200807_144503-27b26226.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x512_160k_ade20k/deeplabv3plus_s101-d8_512x512_160k_ade20k-20200807_144503.log.json
+  Paper:
+    Title: 'ResNeSt: Split-Attention Networks'
+    URL: https://arxiv.org/abs/2004.08955
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/resnest.py#L271
+  Framework: PyTorch
diff --git a/configs/resnest/resnest.yml b/configs/resnest/resnest.yml
deleted file mode 100644
index ab897e3bd5..0000000000
--- a/configs/resnest/resnest.yml
+++ /dev/null
@@ -1,177 +0,0 @@
-Models:
-- Name: resnest_s101-d8_fcn_4xb2-80k_cityscapes-512x1024
-  In Collection: FCN
-  Metadata:
-    backbone: S-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 418.41
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 11.4
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.56
-      mIoU(ms+flip): 78.98
-  Config: configs/resnest/resnest_s101-d8_fcn_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x1024_80k_cityscapes/fcn_s101-d8_512x1024_80k_cityscapes_20200807_140631-f8d155b3.pth
-- Name: resnest_s101-d8_pspnet_4xb2-80k_cityscapes512x1024
-  In Collection: PSPNet
-  Metadata:
-    backbone: S-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 396.83
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 11.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.57
-      mIoU(ms+flip): 79.19
-  Config: configs/resnest/resnest_s101-d8_pspnet_4xb2-80k_cityscapes512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x1024_80k_cityscapes/pspnet_s101-d8_512x1024_80k_cityscapes_20200807_140631-c75f3b99.pth
-- Name: resnest_s101-d8_deeplabv3_4xb2-80k_cityscapes-512x1024
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: S-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 531.91
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 11.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.67
-      mIoU(ms+flip): 80.51
-  Config: configs/resnest/resnest_s101-d8_deeplabv3_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x1024_80k_cityscapes/deeplabv3_s101-d8_512x1024_80k_cityscapes_20200807_144429-b73c4270.pth
-- Name: resnest_s101-d8_deeplabv3plus_4xb2-80k_cityscapes-512x1024
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: S-101-D8
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 423.73
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 13.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.62
-      mIoU(ms+flip): 80.27
-  Config: configs/resnest/resnest_s101-d8_deeplabv3plus_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x1024_80k_cityscapes/deeplabv3plus_s101-d8_512x1024_80k_cityscapes_20200807_144429-1239eb43.pth
-- Name: resnest_s101-d8_fcn_4xb4-160k_ade20k-512x512
-  In Collection: FCN
-  Metadata:
-    backbone: S-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 77.76
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 14.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.62
-      mIoU(ms+flip): 46.16
-  Config: configs/resnest/resnest_s101-d8_fcn_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x512_160k_ade20k/fcn_s101-d8_512x512_160k_ade20k_20200807_145416-d3160329.pth
-- Name: resnest_s101-d8_pspnet_4xb4-160k_ade20k-512x512
-  In Collection: PSPNet
-  Metadata:
-    backbone: S-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 76.8
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 14.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.44
-      mIoU(ms+flip): 46.28
-  Config: configs/resnest/resnest_s101-d8_pspnet_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x512_160k_ade20k/pspnet_s101-d8_512x512_160k_ade20k_20200807_145416-a6daa92a.pth
-- Name: resnest_s101-d8_deeplabv3_4xb4-160k_ade20k-512x512
-  In Collection: DeepLabV3
-  Metadata:
-    backbone: S-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 107.76
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 14.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.71
-      mIoU(ms+flip): 46.59
-  Config: configs/resnest/resnest_s101-d8_deeplabv3_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x512_160k_ade20k/deeplabv3_s101-d8_512x512_160k_ade20k_20200807_144503-17ecabe5.pth
-- Name: resnest_s101-d8_deeplabv3plus_4xb4-160k_ade20k-512x512
-  In Collection: DeepLabV3+
-  Metadata:
-    backbone: S-101-D8
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 83.61
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 16.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 46.47
-      mIoU(ms+flip): 47.27
-  Config: configs/resnest/resnest_s101-d8_deeplabv3plus_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x512_160k_ade20k/deeplabv3plus_s101-d8_512x512_160k_ade20k_20200807_144503-27b26226.pth
diff --git a/configs/segformer/README.md b/configs/segformer/README.md
index be64099da3..5dbf1215bc 100644
--- a/configs/segformer/README.md
+++ b/configs/segformer/README.md
@@ -1,6 +1,6 @@
 # SegFormer
 
-[SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://arxiv.org/abs/2105.15203)
+> [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://arxiv.org/abs/2105.15203)
 
 ## Introduction
 
@@ -22,17 +22,6 @@ We present SegFormer, a simple, efficient yet powerful semantic segmentation fra
 <img src="https://user-images.githubusercontent.com/24582831/142902600-e188073e-5744-4ba9-8dbf-9316e55c74aa.png" width="70%"/>
 </div>
 
-## Citation
-
-```bibtex
-@article{xie2021segformer,
-  title={SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers},
-  author={Xie, Enze and Wang, Wenhai and Yu, Zhiding and Anandkumar, Anima and Alvarez, Jose M and Luo, Ping},
-  journal={arXiv preprint arXiv:2105.15203},
-  year={2021}
-}
-```
-
 ## Usage
 
 To use other repositories' pre-trained models, it is necessary to convert keys.
@@ -49,15 +38,15 @@ This script convert model from `PRETRAIN_PATH` and store the converted model in
 
 ### ADE20K
 
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                             | download                                                                                                                                                                                                                                                                                                                                               |
-| --------- | -------- | --------- | ------: | -------: | -------------- | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| Segformer | MIT-B0   | 512x512   |  160000 |      2.1 | 51.32          | 37.41 | 38.34         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b0_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_512x512_160k_ade20k/segformer_mit-b0_512x512_160k_ade20k_20210726_101530-8ffa8fda.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_512x512_160k_ade20k/segformer_mit-b0_512x512_160k_ade20k_20210726_101530.log.json) |
-| Segformer | MIT-B1   | 512x512   |  160000 |      2.6 | 47.66          | 40.97 | 42.54         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b1_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_512x512_160k_ade20k/segformer_mit-b1_512x512_160k_ade20k_20210726_112106-d70e859d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_512x512_160k_ade20k/segformer_mit-b1_512x512_160k_ade20k_20210726_112106.log.json) |
-| Segformer | MIT-B2   | 512x512   |  160000 |      3.6 | 30.88          | 45.58 | 47.03         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b2_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_512x512_160k_ade20k/segformer_mit-b2_512x512_160k_ade20k_20210726_112103-cbd414ac.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_512x512_160k_ade20k/segformer_mit-b2_512x512_160k_ade20k_20210726_112103.log.json) |
-| Segformer | MIT-B3   | 512x512   |  160000 |      4.8 | 22.11          | 47.82 | 48.81         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b3_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_512x512_160k_ade20k/segformer_mit-b3_512x512_160k_ade20k_20210726_081410-962b98d2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_512x512_160k_ade20k/segformer_mit-b3_512x512_160k_ade20k_20210726_081410.log.json) |
-| Segformer | MIT-B4   | 512x512   |  160000 |      6.1 | 15.45          | 48.46 | 49.76         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b4_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_512x512_160k_ade20k/segformer_mit-b4_512x512_160k_ade20k_20210728_183055-7f509d7d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_512x512_160k_ade20k/segformer_mit-b4_512x512_160k_ade20k_20210728_183055.log.json) |
-| Segformer | MIT-B5   | 512x512   |  160000 |      7.2 | 11.89          | 49.13 | 50.22         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b5_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_512x512_160k_ade20k/segformer_mit-b5_512x512_160k_ade20k_20210726_145235-94cedf59.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_512x512_160k_ade20k/segformer_mit-b5_512x512_160k_ade20k_20210726_145235.log.json) |
-| Segformer | MIT-B5   | 640x640   |  160000 |     11.5 | 11.30          | 49.62 | 50.36         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b5_8xb2-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_640x640_160k_ade20k/segformer_mit-b5_640x640_160k_ade20k_20210801_121243-41d2845b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_640x640_160k_ade20k/segformer_mit-b5_640x640_160k_ade20k_20210801_121243.log.json) |
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device   |  mIoU | mIoU(ms+flip) | config                                                                                                                             | download                                                                                                                                                                                                                                                                                                                                               |
+| --------- | -------- | --------- | ------: | -------: | -------------- | -------- | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| Segformer | MIT-B0   | 512x512   |  160000 |      2.1 | 51.32          | 1080 Ti  | 37.41 | 38.34         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b0_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_512x512_160k_ade20k/segformer_mit-b0_512x512_160k_ade20k_20210726_101530-8ffa8fda.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_512x512_160k_ade20k/segformer_mit-b0_512x512_160k_ade20k_20210726_101530.log.json) |
+| Segformer | MIT-B1   | 512x512   |  160000 |      2.6 | 47.66          | TITAN Xp | 40.97 | 42.54         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b1_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_512x512_160k_ade20k/segformer_mit-b1_512x512_160k_ade20k_20210726_112106-d70e859d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_512x512_160k_ade20k/segformer_mit-b1_512x512_160k_ade20k_20210726_112106.log.json) |
+| Segformer | MIT-B2   | 512x512   |  160000 |      3.6 | 30.88          | TITAN Xp | 45.58 | 47.03         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b2_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_512x512_160k_ade20k/segformer_mit-b2_512x512_160k_ade20k_20210726_112103-cbd414ac.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_512x512_160k_ade20k/segformer_mit-b2_512x512_160k_ade20k_20210726_112103.log.json) |
+| Segformer | MIT-B3   | 512x512   |  160000 |      4.8 | 22.11          | V100     | 47.82 | 48.81         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b3_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_512x512_160k_ade20k/segformer_mit-b3_512x512_160k_ade20k_20210726_081410-962b98d2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_512x512_160k_ade20k/segformer_mit-b3_512x512_160k_ade20k_20210726_081410.log.json) |
+| Segformer | MIT-B4   | 512x512   |  160000 |      6.1 | 15.45          | V100     | 48.46 | 49.76         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b4_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_512x512_160k_ade20k/segformer_mit-b4_512x512_160k_ade20k_20210728_183055-7f509d7d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_512x512_160k_ade20k/segformer_mit-b4_512x512_160k_ade20k_20210728_183055.log.json) |
+| Segformer | MIT-B5   | 512x512   |  160000 |      7.2 | 11.89          | V100     | 49.13 | 50.22         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b5_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_512x512_160k_ade20k/segformer_mit-b5_512x512_160k_ade20k_20210726_145235-94cedf59.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_512x512_160k_ade20k/segformer_mit-b5_512x512_160k_ade20k_20210726_145235.log.json) |
+| Segformer | MIT-B5   | 640x640   |  160000 |     11.5 | 11.30          | V100     | 49.62 | 50.36         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b5_8xb2-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_640x640_160k_ade20k/segformer_mit-b5_640x640_160k_ade20k_20210801_121243-41d2845b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_640x640_160k_ade20k/segformer_mit-b5_640x640_160k_ade20k_20210801_121243.log.json) |
 
 Evaluation with AlignedResize:
 
@@ -91,11 +80,22 @@ test_pipeline = [
 
 The lower fps result is caused by the sliding window inference scheme (window size:1024x1024).
 
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                   | download                                                                                                                                                                                                                                                                                                                                                                                       |
-| --------- | -------- | --------- | ------: | -------: | -------------- | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Segformer | MIT-B0   | 1024x1024 |  160000 |     3.64 | 4.74           | 76.54 | 78.22         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b0_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_8x1_1024x1024_160k_cityscapes/segformer_mit-b0_8x1_1024x1024_160k_cityscapes_20211208_101857-e7f88502.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_8x1_1024x1024_160k_cityscapes/segformer_mit-b0_8x1_1024x1024_160k_cityscapes_20211208_101857.log.json) |
-| Segformer | MIT-B1   | 1024x1024 |  160000 |     4.49 | 4.3            | 78.56 | 79.73         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b1_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_8x1_1024x1024_160k_cityscapes/segformer_mit-b1_8x1_1024x1024_160k_cityscapes_20211208_064213-655c7b3f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_8x1_1024x1024_160k_cityscapes/segformer_mit-b1_8x1_1024x1024_160k_cityscapes_20211208_064213.log.json) |
-| Segformer | MIT-B2   | 1024x1024 |  160000 |     7.42 | 3.36           | 81.08 | 82.18         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b2_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_8x1_1024x1024_160k_cityscapes/segformer_mit-b2_8x1_1024x1024_160k_cityscapes_20211207_134205-6096669a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_8x1_1024x1024_160k_cityscapes/segformer_mit-b2_8x1_1024x1024_160k_cityscapes_20211207_134205.log.json) |
-| Segformer | MIT-B3   | 1024x1024 |  160000 |    10.86 | 2.53           | 81.94 | 83.14         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b3_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_8x1_1024x1024_160k_cityscapes/segformer_mit-b3_8x1_1024x1024_160k_cityscapes_20211206_224823-a8f8a177.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_8x1_1024x1024_160k_cityscapes/segformer_mit-b3_8x1_1024x1024_160k_cityscapes_20211206_224823.log.json) |
-| Segformer | MIT-B4   | 1024x1024 |  160000 |    15.07 | 1.88           | 81.89 | 83.38         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b4_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_8x1_1024x1024_160k_cityscapes/segformer_mit-b4_8x1_1024x1024_160k_cityscapes_20211207_080709-07f6c333.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_8x1_1024x1024_160k_cityscapes/segformer_mit-b4_8x1_1024x1024_160k_cityscapes_20211207_080709.log.json) |
-| Segformer | MIT-B5   | 1024x1024 |  160000 |    18.00 | 1.39           | 82.25 | 83.48         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b5_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_8x1_1024x1024_160k_cityscapes/segformer_mit-b5_8x1_1024x1024_160k_cityscapes_20211206_072934-87a052ec.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_8x1_1024x1024_160k_cityscapes/segformer_mit-b5_8x1_1024x1024_160k_cityscapes_20211206_072934.log.json) |
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                   | download                                                                                                                                                                                                                                                                                                                                                                                       |
+| --------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Segformer | MIT-B0   | 1024x1024 |  160000 |     3.64 | 4.74           | V100   | 76.54 | 78.22         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b0_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_8x1_1024x1024_160k_cityscapes/segformer_mit-b0_8x1_1024x1024_160k_cityscapes_20211208_101857-e7f88502.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_8x1_1024x1024_160k_cityscapes/segformer_mit-b0_8x1_1024x1024_160k_cityscapes_20211208_101857.log.json) |
+| Segformer | MIT-B1   | 1024x1024 |  160000 |     4.49 | 4.3            | V100   | 78.56 | 79.73         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b1_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_8x1_1024x1024_160k_cityscapes/segformer_mit-b1_8x1_1024x1024_160k_cityscapes_20211208_064213-655c7b3f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_8x1_1024x1024_160k_cityscapes/segformer_mit-b1_8x1_1024x1024_160k_cityscapes_20211208_064213.log.json) |
+| Segformer | MIT-B2   | 1024x1024 |  160000 |     7.42 | 3.36           | V100   | 81.08 | 82.18         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b2_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_8x1_1024x1024_160k_cityscapes/segformer_mit-b2_8x1_1024x1024_160k_cityscapes_20211207_134205-6096669a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_8x1_1024x1024_160k_cityscapes/segformer_mit-b2_8x1_1024x1024_160k_cityscapes_20211207_134205.log.json) |
+| Segformer | MIT-B3   | 1024x1024 |  160000 |    10.86 | 2.53           | V100   | 81.94 | 83.14         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b3_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_8x1_1024x1024_160k_cityscapes/segformer_mit-b3_8x1_1024x1024_160k_cityscapes_20211206_224823-a8f8a177.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_8x1_1024x1024_160k_cityscapes/segformer_mit-b3_8x1_1024x1024_160k_cityscapes_20211206_224823.log.json) |
+| Segformer | MIT-B4   | 1024x1024 |  160000 |    15.07 | 1.88           | V100   | 81.89 | 83.38         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b4_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_8x1_1024x1024_160k_cityscapes/segformer_mit-b4_8x1_1024x1024_160k_cityscapes_20211207_080709-07f6c333.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_8x1_1024x1024_160k_cityscapes/segformer_mit-b4_8x1_1024x1024_160k_cityscapes_20211207_080709.log.json) |
+| Segformer | MIT-B5   | 1024x1024 |  160000 |    18.00 | 1.39           | V100   | 82.25 | 83.48         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b5_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_8x1_1024x1024_160k_cityscapes/segformer_mit-b5_8x1_1024x1024_160k_cityscapes_20211206_072934-87a052ec.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_8x1_1024x1024_160k_cityscapes/segformer_mit-b5_8x1_1024x1024_160k_cityscapes_20211206_072934.log.json) |
+
+## Citation
+
+```bibtex
+@article{xie2021segformer,
+  title={SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers},
+  author={Xie, Enze and Wang, Wenhai and Yu, Zhiding and Anandkumar, Anima and Alvarez, Jose M and Luo, Ping},
+  journal={arXiv preprint arXiv:2105.15203},
+  year={2021}
+}
+```
diff --git a/configs/segformer/metafile.yaml b/configs/segformer/metafile.yaml
new file mode 100644
index 0000000000..7fb38d745b
--- /dev/null
+++ b/configs/segformer/metafile.yaml
@@ -0,0 +1,340 @@
+Collections:
+- Name: Segformer
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - ADE20K
+    - Cityscapes
+  Paper:
+    Title: 'SegFormer: Simple and Efficient Design for Semantic Segmentation with
+      Transformers'
+    URL: https://arxiv.org/abs/2105.15203
+  README: configs/segformer/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: segformer_mit-b0_8xb2-160k_ade20k-512x512
+  In Collection: Segformer
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 37.41
+      mIoU(ms+flip): 38.34
+  Config: configs/segformer/segformer_mit-b0_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - MIT-B0
+    - Segformer
+    Training Resources: 8x 1080 Ti GPUS
+    Memory (GB): 2.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_512x512_160k_ade20k/segformer_mit-b0_512x512_160k_ade20k_20210726_101530-8ffa8fda.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_512x512_160k_ade20k/segformer_mit-b0_512x512_160k_ade20k_20210726_101530.log.json
+  Paper:
+    Title: 'SegFormer: Simple and Efficient Design for Semantic Segmentation with
+      Transformers'
+    URL: https://arxiv.org/abs/2105.15203
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mit.py#L246
+  Framework: PyTorch
+- Name: segformer_mit-b1_8xb2-160k_ade20k-512x512
+  In Collection: Segformer
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 40.97
+      mIoU(ms+flip): 42.54
+  Config: configs/segformer/segformer_mit-b1_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - MIT-B1
+    - Segformer
+    Training Resources: 8x TITAN Xp GPUS
+    Memory (GB): 2.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_512x512_160k_ade20k/segformer_mit-b1_512x512_160k_ade20k_20210726_112106-d70e859d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_512x512_160k_ade20k/segformer_mit-b1_512x512_160k_ade20k_20210726_112106.log.json
+  Paper:
+    Title: 'SegFormer: Simple and Efficient Design for Semantic Segmentation with
+      Transformers'
+    URL: https://arxiv.org/abs/2105.15203
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mit.py#L246
+  Framework: PyTorch
+- Name: segformer_mit-b2_8xb2-160k_ade20k-512x512
+  In Collection: Segformer
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.58
+      mIoU(ms+flip): 47.03
+  Config: configs/segformer/segformer_mit-b2_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - MIT-B2
+    - Segformer
+    Training Resources: 8x TITAN Xp GPUS
+    Memory (GB): 3.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_512x512_160k_ade20k/segformer_mit-b2_512x512_160k_ade20k_20210726_112103-cbd414ac.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_512x512_160k_ade20k/segformer_mit-b2_512x512_160k_ade20k_20210726_112103.log.json
+  Paper:
+    Title: 'SegFormer: Simple and Efficient Design for Semantic Segmentation with
+      Transformers'
+    URL: https://arxiv.org/abs/2105.15203
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mit.py#L246
+  Framework: PyTorch
+- Name: segformer_mit-b3_8xb2-160k_ade20k-512x512
+  In Collection: Segformer
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 47.82
+      mIoU(ms+flip): 48.81
+  Config: configs/segformer/segformer_mit-b3_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - MIT-B3
+    - Segformer
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 4.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_512x512_160k_ade20k/segformer_mit-b3_512x512_160k_ade20k_20210726_081410-962b98d2.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_512x512_160k_ade20k/segformer_mit-b3_512x512_160k_ade20k_20210726_081410.log.json
+  Paper:
+    Title: 'SegFormer: Simple and Efficient Design for Semantic Segmentation with
+      Transformers'
+    URL: https://arxiv.org/abs/2105.15203
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mit.py#L246
+  Framework: PyTorch
+- Name: segformer_mit-b4_8xb2-160k_ade20k-512x512
+  In Collection: Segformer
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 48.46
+      mIoU(ms+flip): 49.76
+  Config: configs/segformer/segformer_mit-b4_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - MIT-B4
+    - Segformer
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 6.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_512x512_160k_ade20k/segformer_mit-b4_512x512_160k_ade20k_20210728_183055-7f509d7d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_512x512_160k_ade20k/segformer_mit-b4_512x512_160k_ade20k_20210728_183055.log.json
+  Paper:
+    Title: 'SegFormer: Simple and Efficient Design for Semantic Segmentation with
+      Transformers'
+    URL: https://arxiv.org/abs/2105.15203
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mit.py#L246
+  Framework: PyTorch
+- Name: segformer_mit-b5_8xb2-160k_ade20k-512x512
+  In Collection: Segformer
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 49.13
+      mIoU(ms+flip): 50.22
+  Config: configs/segformer/segformer_mit-b5_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - MIT-B5
+    - Segformer
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 7.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_512x512_160k_ade20k/segformer_mit-b5_512x512_160k_ade20k_20210726_145235-94cedf59.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_512x512_160k_ade20k/segformer_mit-b5_512x512_160k_ade20k_20210726_145235.log.json
+  Paper:
+    Title: 'SegFormer: Simple and Efficient Design for Semantic Segmentation with
+      Transformers'
+    URL: https://arxiv.org/abs/2105.15203
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mit.py#L246
+  Framework: PyTorch
+- Name: segformer_mit-b5_8xb2-160k_ade20k-640x640
+  In Collection: Segformer
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 49.62
+      mIoU(ms+flip): 50.36
+  Config: configs/segformer/segformer_mit-b5_8xb2-160k_ade20k-640x640.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - MIT-B5
+    - Segformer
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 11.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_640x640_160k_ade20k/segformer_mit-b5_640x640_160k_ade20k_20210801_121243-41d2845b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_640x640_160k_ade20k/segformer_mit-b5_640x640_160k_ade20k_20210801_121243.log.json
+  Paper:
+    Title: 'SegFormer: Simple and Efficient Design for Semantic Segmentation with
+      Transformers'
+    URL: https://arxiv.org/abs/2105.15203
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mit.py#L246
+  Framework: PyTorch
+- Name: segformer_mit-b0_8xb1-160k_cityscapes-1024x1024
+  In Collection: Segformer
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.54
+      mIoU(ms+flip): 78.22
+  Config: configs/segformer/segformer_mit-b0_8xb1-160k_cityscapes-1024x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - MIT-B0
+    - Segformer
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 3.64
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_8x1_1024x1024_160k_cityscapes/segformer_mit-b0_8x1_1024x1024_160k_cityscapes_20211208_101857-e7f88502.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_8x1_1024x1024_160k_cityscapes/segformer_mit-b0_8x1_1024x1024_160k_cityscapes_20211208_101857.log.json
+  Paper:
+    Title: 'SegFormer: Simple and Efficient Design for Semantic Segmentation with
+      Transformers'
+    URL: https://arxiv.org/abs/2105.15203
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mit.py#L246
+  Framework: PyTorch
+- Name: segformer_mit-b1_8xb1-160k_cityscapes-1024x1024
+  In Collection: Segformer
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.56
+      mIoU(ms+flip): 79.73
+  Config: configs/segformer/segformer_mit-b1_8xb1-160k_cityscapes-1024x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - MIT-B1
+    - Segformer
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 4.49
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_8x1_1024x1024_160k_cityscapes/segformer_mit-b1_8x1_1024x1024_160k_cityscapes_20211208_064213-655c7b3f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_8x1_1024x1024_160k_cityscapes/segformer_mit-b1_8x1_1024x1024_160k_cityscapes_20211208_064213.log.json
+  Paper:
+    Title: 'SegFormer: Simple and Efficient Design for Semantic Segmentation with
+      Transformers'
+    URL: https://arxiv.org/abs/2105.15203
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mit.py#L246
+  Framework: PyTorch
+- Name: segformer_mit-b2_8xb1-160k_cityscapes-1024x1024
+  In Collection: Segformer
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 81.08
+      mIoU(ms+flip): 82.18
+  Config: configs/segformer/segformer_mit-b2_8xb1-160k_cityscapes-1024x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - MIT-B2
+    - Segformer
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 7.42
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_8x1_1024x1024_160k_cityscapes/segformer_mit-b2_8x1_1024x1024_160k_cityscapes_20211207_134205-6096669a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_8x1_1024x1024_160k_cityscapes/segformer_mit-b2_8x1_1024x1024_160k_cityscapes_20211207_134205.log.json
+  Paper:
+    Title: 'SegFormer: Simple and Efficient Design for Semantic Segmentation with
+      Transformers'
+    URL: https://arxiv.org/abs/2105.15203
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mit.py#L246
+  Framework: PyTorch
+- Name: segformer_mit-b3_8xb1-160k_cityscapes-1024x1024
+  In Collection: Segformer
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 81.94
+      mIoU(ms+flip): 83.14
+  Config: configs/segformer/segformer_mit-b3_8xb1-160k_cityscapes-1024x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - MIT-B3
+    - Segformer
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 10.86
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_8x1_1024x1024_160k_cityscapes/segformer_mit-b3_8x1_1024x1024_160k_cityscapes_20211206_224823-a8f8a177.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_8x1_1024x1024_160k_cityscapes/segformer_mit-b3_8x1_1024x1024_160k_cityscapes_20211206_224823.log.json
+  Paper:
+    Title: 'SegFormer: Simple and Efficient Design for Semantic Segmentation with
+      Transformers'
+    URL: https://arxiv.org/abs/2105.15203
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mit.py#L246
+  Framework: PyTorch
+- Name: segformer_mit-b4_8xb1-160k_cityscapes-1024x1024
+  In Collection: Segformer
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 81.89
+      mIoU(ms+flip): 83.38
+  Config: configs/segformer/segformer_mit-b4_8xb1-160k_cityscapes-1024x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - MIT-B4
+    - Segformer
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 15.07
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_8x1_1024x1024_160k_cityscapes/segformer_mit-b4_8x1_1024x1024_160k_cityscapes_20211207_080709-07f6c333.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_8x1_1024x1024_160k_cityscapes/segformer_mit-b4_8x1_1024x1024_160k_cityscapes_20211207_080709.log.json
+  Paper:
+    Title: 'SegFormer: Simple and Efficient Design for Semantic Segmentation with
+      Transformers'
+    URL: https://arxiv.org/abs/2105.15203
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mit.py#L246
+  Framework: PyTorch
+- Name: segformer_mit-b5_8xb1-160k_cityscapes-1024x1024
+  In Collection: Segformer
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 82.25
+      mIoU(ms+flip): 83.48
+  Config: configs/segformer/segformer_mit-b5_8xb1-160k_cityscapes-1024x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - MIT-B5
+    - Segformer
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 18.0
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_8x1_1024x1024_160k_cityscapes/segformer_mit-b5_8x1_1024x1024_160k_cityscapes_20211206_072934-87a052ec.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_8x1_1024x1024_160k_cityscapes/segformer_mit-b5_8x1_1024x1024_160k_cityscapes_20211206_072934.log.json
+  Paper:
+    Title: 'SegFormer: Simple and Efficient Design for Semantic Segmentation with
+      Transformers'
+    URL: https://arxiv.org/abs/2105.15203
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mit.py#L246
+  Framework: PyTorch
diff --git a/configs/segformer/segformer.yml b/configs/segformer/segformer.yml
deleted file mode 100644
index 4a3818e16e..0000000000
--- a/configs/segformer/segformer.yml
+++ /dev/null
@@ -1,303 +0,0 @@
-Collections:
-- Name: Segformer
-  Metadata:
-    Training Data:
-    - ADE20K
-    - Cityscapes
-  Paper:
-    URL: https://arxiv.org/abs/2105.15203
-    Title: 'SegFormer: Simple and Efficient Design for Semantic Segmentation with
-      Transformers'
-  README: configs/segformer/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mit.py#L246
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/NVlabs/SegFormer
-Models:
-- Name: segformer_mit-b0_8xb2-160k_ade20k-512x512
-  In Collection: Segformer
-  Metadata:
-    backbone: MIT-B0
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 19.49
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 2.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 37.41
-      mIoU(ms+flip): 38.34
-  Config: configs/segformer/segformer_mit-b0_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_512x512_160k_ade20k/segformer_mit-b0_512x512_160k_ade20k_20210726_101530-8ffa8fda.pth
-- Name: segformer_mit-b1_8xb2-160k_ade20k-512x512
-  In Collection: Segformer
-  Metadata:
-    backbone: MIT-B1
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 20.98
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 2.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 40.97
-      mIoU(ms+flip): 42.54
-  Config: configs/segformer/segformer_mit-b1_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_512x512_160k_ade20k/segformer_mit-b1_512x512_160k_ade20k_20210726_112106-d70e859d.pth
-- Name: segformer_mit-b2_8xb2-160k_ade20k-512x512
-  In Collection: Segformer
-  Metadata:
-    backbone: MIT-B2
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 32.38
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 3.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.58
-      mIoU(ms+flip): 47.03
-  Config: configs/segformer/segformer_mit-b2_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_512x512_160k_ade20k/segformer_mit-b2_512x512_160k_ade20k_20210726_112103-cbd414ac.pth
-- Name: segformer_mit-b3_8xb2-160k_ade20k-512x512
-  In Collection: Segformer
-  Metadata:
-    backbone: MIT-B3
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 45.23
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 4.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 47.82
-      mIoU(ms+flip): 48.81
-  Config: configs/segformer/segformer_mit-b3_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_512x512_160k_ade20k/segformer_mit-b3_512x512_160k_ade20k_20210726_081410-962b98d2.pth
-- Name: segformer_mit-b4_8xb2-160k_ade20k-512x512
-  In Collection: Segformer
-  Metadata:
-    backbone: MIT-B4
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 64.72
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 48.46
-      mIoU(ms+flip): 49.76
-  Config: configs/segformer/segformer_mit-b4_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_512x512_160k_ade20k/segformer_mit-b4_512x512_160k_ade20k_20210728_183055-7f509d7d.pth
-- Name: segformer_mit-b5_8xb2-160k_ade20k-512x512
-  In Collection: Segformer
-  Metadata:
-    backbone: MIT-B5
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 84.1
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 7.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 49.13
-      mIoU(ms+flip): 50.22
-  Config: configs/segformer/segformer_mit-b5_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_512x512_160k_ade20k/segformer_mit-b5_512x512_160k_ade20k_20210726_145235-94cedf59.pth
-- Name: segformer_mit-b5_8xb2-160k_ade20k-640x640
-  In Collection: Segformer
-  Metadata:
-    backbone: MIT-B5
-    crop size: (640,640)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 88.5
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (640,640)
-    Training Memory (GB): 11.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 49.62
-      mIoU(ms+flip): 50.36
-  Config: configs/segformer/segformer_mit-b5_8xb2-160k_ade20k-640x640.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_640x640_160k_ade20k/segformer_mit-b5_640x640_160k_ade20k_20210801_121243-41d2845b.pth
-- Name: segformer_mit-b0_8xb1-160k_cityscapes-1024x1024
-  In Collection: Segformer
-  Metadata:
-    backbone: MIT-B0
-    crop size: (1024,1024)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 210.97
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (1024,1024)
-    Training Memory (GB): 3.64
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.54
-      mIoU(ms+flip): 78.22
-  Config: configs/segformer/segformer_mit-b0_8xb1-160k_cityscapes-1024x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_8x1_1024x1024_160k_cityscapes/segformer_mit-b0_8x1_1024x1024_160k_cityscapes_20211208_101857-e7f88502.pth
-- Name: segformer_mit-b1_8xb1-160k_cityscapes-1024x1024
-  In Collection: Segformer
-  Metadata:
-    backbone: MIT-B1
-    crop size: (1024,1024)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 232.56
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (1024,1024)
-    Training Memory (GB): 4.49
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.56
-      mIoU(ms+flip): 79.73
-  Config: configs/segformer/segformer_mit-b1_8xb1-160k_cityscapes-1024x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_8x1_1024x1024_160k_cityscapes/segformer_mit-b1_8x1_1024x1024_160k_cityscapes_20211208_064213-655c7b3f.pth
-- Name: segformer_mit-b2_8xb1-160k_cityscapes-1024x1024
-  In Collection: Segformer
-  Metadata:
-    backbone: MIT-B2
-    crop size: (1024,1024)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 297.62
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (1024,1024)
-    Training Memory (GB): 7.42
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 81.08
-      mIoU(ms+flip): 82.18
-  Config: configs/segformer/segformer_mit-b2_8xb1-160k_cityscapes-1024x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_8x1_1024x1024_160k_cityscapes/segformer_mit-b2_8x1_1024x1024_160k_cityscapes_20211207_134205-6096669a.pth
-- Name: segformer_mit-b3_8xb1-160k_cityscapes-1024x1024
-  In Collection: Segformer
-  Metadata:
-    backbone: MIT-B3
-    crop size: (1024,1024)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 395.26
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (1024,1024)
-    Training Memory (GB): 10.86
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 81.94
-      mIoU(ms+flip): 83.14
-  Config: configs/segformer/segformer_mit-b3_8xb1-160k_cityscapes-1024x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_8x1_1024x1024_160k_cityscapes/segformer_mit-b3_8x1_1024x1024_160k_cityscapes_20211206_224823-a8f8a177.pth
-- Name: segformer_mit-b4_8xb1-160k_cityscapes-1024x1024
-  In Collection: Segformer
-  Metadata:
-    backbone: MIT-B4
-    crop size: (1024,1024)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 531.91
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (1024,1024)
-    Training Memory (GB): 15.07
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 81.89
-      mIoU(ms+flip): 83.38
-  Config: configs/segformer/segformer_mit-b4_8xb1-160k_cityscapes-1024x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_8x1_1024x1024_160k_cityscapes/segformer_mit-b4_8x1_1024x1024_160k_cityscapes_20211207_080709-07f6c333.pth
-- Name: segformer_mit-b5_8xb1-160k_cityscapes-1024x1024
-  In Collection: Segformer
-  Metadata:
-    backbone: MIT-B5
-    crop size: (1024,1024)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 719.42
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (1024,1024)
-    Training Memory (GB): 18.0
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 82.25
-      mIoU(ms+flip): 83.48
-  Config: configs/segformer/segformer_mit-b5_8xb1-160k_cityscapes-1024x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_8x1_1024x1024_160k_cityscapes/segformer_mit-b5_8x1_1024x1024_160k_cityscapes_20211206_072934-87a052ec.pth
diff --git a/configs/segmenter/README.md b/configs/segmenter/README.md
index 984ef9f510..a9a64ae421 100644
--- a/configs/segmenter/README.md
+++ b/configs/segmenter/README.md
@@ -1,6 +1,6 @@
 # Segmenter
 
-[Segmenter: Transformer for Semantic Segmentation](https://arxiv.org/abs/2105.05633)
+> [Segmenter: Transformer for Semantic Segmentation](https://arxiv.org/abs/2105.05633)
 
 ## Introduction
 
@@ -22,16 +22,6 @@ Image segmentation is often ambiguous at the level of individual image patches a
 <img src="https://user-images.githubusercontent.com/24582831/148507554-87eb80bd-02c7-4c31-b102-c6141e231ec8.png" width="70%"/>
 </div>
 
-```bibtex
-@inproceedings{strudel2021segmenter,
-  title={Segmenter: Transformer for semantic segmentation},
-  author={Strudel, Robin and Garcia, Ricardo and Laptev, Ivan and Schmid, Cordelia},
-  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
-  pages={7262--7272},
-  year={2021}
-}
-```
-
 ## Usage
 
 We have provided pretrained models converted from [ViT-AugReg](https://github.com/rwightman/pytorch-image-models/blob/f55c22bebf9d8afc449d317a723231ef72e0d662/timm/models/vision_transformer.py#L54-L106).
@@ -54,21 +44,33 @@ This script convert model from `PRETRAIN_PATH` and store the converted model in
 
 In our default setting, pretrained models and their corresponding [ViT-AugReg](https://github.com/rwightman/pytorch-image-models/blob/f55c22bebf9d8afc449d317a723231ef72e0d662/timm/models/vision_transformer.py#L54-L106) models could be defined below:
 
-| pretrained models     | original models                                                                                                                                                                   |
-| --------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| vit_tiny_p16_384.pth  | ['vit_tiny_patch16_384'](https://storage.googleapis.com/vit_models/augreg/Ti_16-i21k-300ep-lr_0.001-aug_none-wd_0.03-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.03-res_384.npz)   |
-| vit_small_p16_384.pth | ['vit_small_patch16_384'](https://storage.googleapis.com/vit_models/augreg/S_16-i21k-300ep-lr_0.001-aug_light1-wd_0.03-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.03-res_384.npz) |
-| vit_base_p16_384.pth  | ['vit_base_patch16_384'](https://storage.googleapis.com/vit_models/augreg/B_16-i21k-300ep-lr_0.001-aug_medium1-wd_0.1-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.01-res_384.npz)  |
-| vit_large_p16_384.pth | ['vit_large_patch16_384'](https://storage.googleapis.com/vit_models/augreg/L_16-i21k-300ep-lr_0.001-aug_medium1-wd_0.1-do_0.1-sd_0.1--imagenet2012-steps_20k-lr_0.01-res_384.npz) |
+| pretrained models     | original models                                                                                                                                                                 |
+| --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| vit_tiny_p16_384.pth  | [vit_tiny_patch16_384](https://storage.googleapis.com/vit_models/augreg/Ti_16-i21k-300ep-lr_0.001-aug_none-wd_0.03-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.03-res_384.npz)   |
+| vit_small_p16_384.pth | [vit_small_patch16_384](https://storage.googleapis.com/vit_models/augreg/S_16-i21k-300ep-lr_0.001-aug_light1-wd_0.03-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.03-res_384.npz) |
+| vit_base_p16_384.pth  | [vit_base_patch16_384](https://storage.googleapis.com/vit_models/augreg/B_16-i21k-300ep-lr_0.001-aug_medium1-wd_0.1-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.01-res_384.npz)  |
+| vit_large_p16_384.pth | [vit_large_patch16_384](https://storage.googleapis.com/vit_models/augreg/L_16-i21k-300ep-lr_0.001-aug_medium1-wd_0.1-do_0.1-sd_0.1--imagenet2012-steps_20k-lr_0.01-res_384.npz) |
 
 ## Results and models
 
 ### ADE20K
 
-| Method           | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) | config                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                                                       |
-| ---------------- | -------- | --------- | ------- | -------- | -------------- | ----- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Segmenter Mask   | ViT-T_16 | 512x512   | 160000  | 1.21     | 27.98          | 39.99 | 40.83         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segmenter/segmenter_vit-t_mask_8xb1-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-t_mask_8x1_512x512_160k_ade20k/segmenter_vit-t_mask_8x1_512x512_160k_ade20k_20220105_151706-ffcf7509.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-t_mask_8x1_512x512_160k_ade20k/segmenter_vit-t_mask_8x1_512x512_160k_ade20k_20220105_151706.log.json)         |
-| Segmenter Linear | ViT-S_16 | 512x512   | 160000  | 1.78     | 28.07          | 45.75 | 46.82         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segmenter/segmenter_vit-s_fcn_8xb1-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_linear_8x1_512x512_160k_ade20k/segmenter_vit-s_linear_8x1_512x512_160k_ade20k_20220105_151713-39658c46.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_linear_8x1_512x512_160k_ade20k/segmenter_vit-s_linear_8x1_512x512_160k_ade20k_20220105_151713.log.json) |
-| Segmenter Mask   | ViT-S_16 | 512x512   | 160000  | 2.03     | 24.80          | 46.19 | 47.85         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segmenter/segmenter_vit-s_mask_8xb1-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k/segmenter_vit-s_mask_8x1_512x512_160k_ade20k_20220105_151706-511bb103.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k/segmenter_vit-s_mask_8x1_512x512_160k_ade20k_20220105_151706.log.json)         |
-| Segmenter Mask   | ViT-B_16 | 512x512   | 160000  | 4.20     | 13.20          | 49.60 | 51.07         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segmenter/segmenter_vit-b_mask_8xb1-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k/segmenter_vit-b_mask_8x1_512x512_160k_ade20k_20220105_151706-bc533b08.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k/segmenter_vit-b_mask_8x1_512x512_160k_ade20k_20220105_151706.log.json)         |
-| Segmenter Mask   | ViT-L_16 | 640x640   | 160000  | 16.56    | 2.62           | 52.16 | 53.65         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segmenter/segmenter_vit-l_mask_8xb1-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k/segmenter_vit-l_mask_8x1_512x512_160k_ade20k_20220105_162750-7ef345be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k/segmenter_vit-l_mask_8x1_512x512_160k_ade20k_20220105_162750.log.json)         |
+| Method           | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                                                       |
+| ---------------- | -------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Segmenter Mask   | ViT-T_16 | 512x512   | 160000  | 1.21     | 27.98          | V100   | 39.99 | 40.83         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segmenter/segmenter_vit-t_mask_8xb1-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-t_mask_8x1_512x512_160k_ade20k/segmenter_vit-t_mask_8x1_512x512_160k_ade20k_20220105_151706-ffcf7509.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-t_mask_8x1_512x512_160k_ade20k/segmenter_vit-t_mask_8x1_512x512_160k_ade20k_20220105_151706.log.json)         |
+| Segmenter Linear | ViT-S_16 | 512x512   | 160000  | 1.78     | 28.07          | V100   | 45.75 | 46.82         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segmenter/segmenter_vit-s_fcn_8xb1-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_linear_8x1_512x512_160k_ade20k/segmenter_vit-s_linear_8x1_512x512_160k_ade20k_20220105_151713-39658c46.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_linear_8x1_512x512_160k_ade20k/segmenter_vit-s_linear_8x1_512x512_160k_ade20k_20220105_151713.log.json) |
+| Segmenter Mask   | ViT-S_16 | 512x512   | 160000  | 2.03     | 24.80          | V100   | 46.19 | 47.85         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segmenter/segmenter_vit-s_mask_8xb1-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k/segmenter_vit-s_mask_8x1_512x512_160k_ade20k_20220105_151706-511bb103.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k/segmenter_vit-s_mask_8x1_512x512_160k_ade20k_20220105_151706.log.json)         |
+| Segmenter Mask   | ViT-B_16 | 512x512   | 160000  | 4.20     | 13.20          | V100   | 49.60 | 51.07         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segmenter/segmenter_vit-b_mask_8xb1-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k/segmenter_vit-b_mask_8x1_512x512_160k_ade20k_20220105_151706-bc533b08.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k/segmenter_vit-b_mask_8x1_512x512_160k_ade20k_20220105_151706.log.json)         |
+| Segmenter Mask   | ViT-L_16 | 640x640   | 160000  | 16.56    | 2.62           | V100   | 52.16 | 53.65         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segmenter/segmenter_vit-l_mask_8xb1-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k/segmenter_vit-l_mask_8x1_512x512_160k_ade20k_20220105_162750-7ef345be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k/segmenter_vit-l_mask_8x1_512x512_160k_ade20k_20220105_162750.log.json)         |
+
+## Citation
+
+```bibtex
+@inproceedings{strudel2021segmenter,
+  title={Segmenter: Transformer for semantic segmentation},
+  author={Strudel, Robin and Garcia, Ricardo and Laptev, Ivan and Schmid, Cordelia},
+  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
+  pages={7262--7272},
+  year={2021}
+}
+```
diff --git a/configs/segmenter/metafile.yaml b/configs/segmenter/metafile.yaml
new file mode 100644
index 0000000000..ff2aa448bb
--- /dev/null
+++ b/configs/segmenter/metafile.yaml
@@ -0,0 +1,138 @@
+Collections:
+- Name: Segmenter
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - ADE20K
+  Paper:
+    Title: 'Segmenter: Transformer for Semantic Segmentation'
+    URL: https://arxiv.org/abs/2105.05633
+  README: configs/segmenter/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: segmenter_vit-t_mask_8xb1-160k_ade20k-512x512
+  In Collection: Segmenter
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 39.99
+      mIoU(ms+flip): 40.83
+  Config: configs/segmenter/segmenter_vit-t_mask_8xb1-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 8
+    Architecture:
+    - ViT-T_16
+    - Segmenter
+    - Mask
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 1.21
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-t_mask_8x1_512x512_160k_ade20k/segmenter_vit-t_mask_8x1_512x512_160k_ade20k_20220105_151706-ffcf7509.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-t_mask_8x1_512x512_160k_ade20k/segmenter_vit-t_mask_8x1_512x512_160k_ade20k_20220105_151706.log.json
+  Paper:
+    Title: 'Segmenter: Transformer for Semantic Segmentation'
+    URL: https://arxiv.org/abs/2105.05633
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.21.0/mmseg/models/decode_heads/segmenter_mask_head.py#L15
+  Framework: PyTorch
+- Name: segmenter_vit-s_fcn_8xb1-160k_ade20k-512x512
+  In Collection: Segmenter
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.75
+      mIoU(ms+flip): 46.82
+  Config: configs/segmenter/segmenter_vit-s_fcn_8xb1-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 8
+    Architecture:
+    - ViT-S_16
+    - Segmenter
+    - Linear
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 1.78
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_linear_8x1_512x512_160k_ade20k/segmenter_vit-s_linear_8x1_512x512_160k_ade20k_20220105_151713-39658c46.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_linear_8x1_512x512_160k_ade20k/segmenter_vit-s_linear_8x1_512x512_160k_ade20k_20220105_151713.log.json
+  Paper:
+    Title: 'Segmenter: Transformer for Semantic Segmentation'
+    URL: https://arxiv.org/abs/2105.05633
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.21.0/mmseg/models/decode_heads/segmenter_mask_head.py#L15
+  Framework: PyTorch
+- Name: segmenter_vit-s_mask_8xb1-160k_ade20k-512x512
+  In Collection: Segmenter
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 46.19
+      mIoU(ms+flip): 47.85
+  Config: configs/segmenter/segmenter_vit-s_mask_8xb1-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 8
+    Architecture:
+    - ViT-S_16
+    - Segmenter
+    - Mask
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 2.03
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k/segmenter_vit-s_mask_8x1_512x512_160k_ade20k_20220105_151706-511bb103.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k/segmenter_vit-s_mask_8x1_512x512_160k_ade20k_20220105_151706.log.json
+  Paper:
+    Title: 'Segmenter: Transformer for Semantic Segmentation'
+    URL: https://arxiv.org/abs/2105.05633
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.21.0/mmseg/models/decode_heads/segmenter_mask_head.py#L15
+  Framework: PyTorch
+- Name: segmenter_vit-b_mask_8xb1-160k_ade20k-512x512
+  In Collection: Segmenter
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 49.6
+      mIoU(ms+flip): 51.07
+  Config: configs/segmenter/segmenter_vit-b_mask_8xb1-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 8
+    Architecture:
+    - ViT-B_16
+    - Segmenter
+    - Mask
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 4.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k/segmenter_vit-b_mask_8x1_512x512_160k_ade20k_20220105_151706-bc533b08.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k/segmenter_vit-b_mask_8x1_512x512_160k_ade20k_20220105_151706.log.json
+  Paper:
+    Title: 'Segmenter: Transformer for Semantic Segmentation'
+    URL: https://arxiv.org/abs/2105.05633
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.21.0/mmseg/models/decode_heads/segmenter_mask_head.py#L15
+  Framework: PyTorch
+- Name: segmenter_vit-l_mask_8xb1-160k_ade20k-512x512
+  In Collection: Segmenter
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 52.16
+      mIoU(ms+flip): 53.65
+  Config: configs/segmenter/segmenter_vit-l_mask_8xb1-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 8
+    Architecture:
+    - ViT-L_16
+    - Segmenter
+    - Mask
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 16.56
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k/segmenter_vit-l_mask_8x1_512x512_160k_ade20k_20220105_162750-7ef345be.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k/segmenter_vit-l_mask_8x1_512x512_160k_ade20k_20220105_162750.log.json
+  Paper:
+    Title: 'Segmenter: Transformer for Semantic Segmentation'
+    URL: https://arxiv.org/abs/2105.05633
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.21.0/mmseg/models/decode_heads/segmenter_mask_head.py#L15
+  Framework: PyTorch
diff --git a/configs/segmenter/segmenter.yml b/configs/segmenter/segmenter.yml
deleted file mode 100644
index 1069f003b7..0000000000
--- a/configs/segmenter/segmenter.yml
+++ /dev/null
@@ -1,125 +0,0 @@
-Collections:
-- Name: Segmenter
-  Metadata:
-    Training Data:
-    - ADE20K
-  Paper:
-    URL: https://arxiv.org/abs/2105.05633
-    Title: 'Segmenter: Transformer for Semantic Segmentation'
-  README: configs/segmenter/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.21.0/mmseg/models/decode_heads/segmenter_mask_head.py#L15
-    Version: v0.21.0
-  Converted From:
-    Code: https://github.com/rstrudel/segmenter
-Models:
-- Name: segmenter_vit-t_mask_8xb1-160k_ade20k-512x512
-  In Collection: Segmenter
-  Metadata:
-    backbone: ViT-T_16
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 35.74
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 1.21
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 39.99
-      mIoU(ms+flip): 40.83
-  Config: configs/segmenter/segmenter_vit-t_mask_8xb1-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-t_mask_8x1_512x512_160k_ade20k/segmenter_vit-t_mask_8x1_512x512_160k_ade20k_20220105_151706-ffcf7509.pth
-- Name: segmenter_vit-s_fcn_8xb1-160k_ade20k-512x512
-  In Collection: Segmenter
-  Metadata:
-    backbone: ViT-S_16
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 35.63
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 1.78
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.75
-      mIoU(ms+flip): 46.82
-  Config: configs/segmenter/segmenter_vit-s_fcn_8xb1-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_linear_8x1_512x512_160k_ade20k/segmenter_vit-s_linear_8x1_512x512_160k_ade20k_20220105_151713-39658c46.pth
-- Name: segmenter_vit-s_mask_8xb1-160k_ade20k-512x512
-  In Collection: Segmenter
-  Metadata:
-    backbone: ViT-S_16
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 40.32
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 2.03
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 46.19
-      mIoU(ms+flip): 47.85
-  Config: configs/segmenter/segmenter_vit-s_mask_8xb1-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k/segmenter_vit-s_mask_8x1_512x512_160k_ade20k_20220105_151706-511bb103.pth
-- Name: segmenter_vit-b_mask_8xb1-160k_ade20k-512x512
-  In Collection: Segmenter
-  Metadata:
-    backbone: ViT-B_16
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 75.76
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 4.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 49.6
-      mIoU(ms+flip): 51.07
-  Config: configs/segmenter/segmenter_vit-b_mask_8xb1-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k/segmenter_vit-b_mask_8x1_512x512_160k_ade20k_20220105_151706-bc533b08.pth
-- Name: segmenter_vit-l_mask_8xb1-160k_ade20k-512x512
-  In Collection: Segmenter
-  Metadata:
-    backbone: ViT-L_16
-    crop size: (640,640)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 381.68
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (640,640)
-    Training Memory (GB): 16.56
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 52.16
-      mIoU(ms+flip): 53.65
-  Config: configs/segmenter/segmenter_vit-l_mask_8xb1-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k/segmenter_vit-l_mask_8x1_512x512_160k_ade20k_20220105_162750-7ef345be.pth
diff --git a/configs/segnext/README.md b/configs/segnext/README.md
index 315f4e23e8..06b63be546 100644
--- a/configs/segnext/README.md
+++ b/configs/segnext/README.md
@@ -26,12 +26,12 @@ We present SegNeXt, a simple convolutional network architecture for semantic seg
 
 ### ADE20K
 
-| Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) | config                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                                                   |
-| ------- | -------- | --------- | ------- | -------- | -------------- | ----- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| SegNeXt | MSCAN-T  | 512x512   | 160000  | 17.88    | 52.38          | 41.50 | 42.59         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segnext/segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k_20230210_140244-05bd8466.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k_20230210_140244.log.json) |
-| SegNeXt | MSCAN-S  | 512x512   | 160000  | 21.47    | 42.27          | 44.16 | 45.81         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segnext/segnext_mscan-s_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k_20230214_113014-43013668.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k_20230214_113014.log.json) |
-| SegNeXt | MSCAN-B  | 512x512   | 160000  | 31.03    | 35.15          | 48.03 | 49.68         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segnext/segnext_mscan-b_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k_20230209_172053-b6f6c70c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k_20230209_172053.log.json) |
-| SegNeXt | MSCAN-L  | 512x512   | 160000  | 43.32    | 22.91          | 50.99 | 52.10         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segnext/segnext_mscan-l_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k_20230209_172055-19b14b63.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k_20230209_172055.log.json) |
+| Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                                                   |
+| ------- | -------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| SegNeXt | MSCAN-T  | 512x512   | 160000  | 17.88    | 52.38          | A100   | 41.50 | 42.59         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segnext/segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k_20230210_140244-05bd8466.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k_20230210_140244.log.json) |
+| SegNeXt | MSCAN-S  | 512x512   | 160000  | 21.47    | 42.27          | A100   | 44.16 | 45.81         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segnext/segnext_mscan-s_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k_20230214_113014-43013668.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k_20230214_113014.log.json) |
+| SegNeXt | MSCAN-B  | 512x512   | 160000  | 31.03    | 35.15          | A100   | 48.03 | 49.68         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segnext/segnext_mscan-b_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k_20230209_172053-b6f6c70c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k_20230209_172053.log.json) |
+| SegNeXt | MSCAN-L  | 512x512   | 160000  | 43.32    | 22.91          | A100   | 50.99 | 52.10         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segnext/segnext_mscan-l_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k_20230209_172055-19b14b63.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k_20230209_172055.log.json) |
 
 Note:
 
diff --git a/configs/segnext/metafile.yaml b/configs/segnext/metafile.yaml
new file mode 100644
index 0000000000..faa11c9784
--- /dev/null
+++ b/configs/segnext/metafile.yaml
@@ -0,0 +1,109 @@
+Collections:
+- Name: SegNeXt
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - ADE20K
+  Paper:
+    Title: 'SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation'
+    URL: https://arxiv.org/abs/2209.08575
+  README: configs/segnext/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512
+  In Collection: SegNeXt
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 41.5
+      mIoU(ms+flip): 42.59
+  Config: configs/segnext/segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - MSCAN-T
+    - SegNeXt
+    Training Resources: 1x A100 GPUS
+    Memory (GB): 17.88
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k_20230210_140244-05bd8466.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k_20230210_140244.log.json
+  Paper:
+    Title: 'SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation'
+    URL: https://arxiv.org/abs/2209.08575
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/mscan.py#L328
+  Framework: PyTorch
+- Name: segnext_mscan-s_1xb16-adamw-160k_ade20k-512x512
+  In Collection: SegNeXt
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 44.16
+      mIoU(ms+flip): 45.81
+  Config: configs/segnext/segnext_mscan-s_1xb16-adamw-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - MSCAN-S
+    - SegNeXt
+    Training Resources: 1x A100 GPUS
+    Memory (GB): 21.47
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k_20230214_113014-43013668.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k_20230214_113014.log.json
+  Paper:
+    Title: 'SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation'
+    URL: https://arxiv.org/abs/2209.08575
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/mscan.py#L328
+  Framework: PyTorch
+- Name: segnext_mscan-b_1xb16-adamw-160k_ade20k-512x512
+  In Collection: SegNeXt
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 48.03
+      mIoU(ms+flip): 49.68
+  Config: configs/segnext/segnext_mscan-b_1xb16-adamw-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - MSCAN-B
+    - SegNeXt
+    Training Resources: 1x A100 GPUS
+    Memory (GB): 31.03
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k_20230209_172053-b6f6c70c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k_20230209_172053.log.json
+  Paper:
+    Title: 'SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation'
+    URL: https://arxiv.org/abs/2209.08575
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/mscan.py#L328
+  Framework: PyTorch
+- Name: segnext_mscan-l_1xb16-adamw-160k_ade20k-512x512
+  In Collection: SegNeXt
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 50.99
+      mIoU(ms+flip): 52.1
+  Config: configs/segnext/segnext_mscan-l_1xb16-adamw-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - MSCAN-L
+    - SegNeXt
+    Training Resources: 1x A100 GPUS
+    Memory (GB): 43.32
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k_20230209_172055-19b14b63.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k_20230209_172055.log.json
+  Paper:
+    Title: 'SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation'
+    URL: https://arxiv.org/abs/2209.08575
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/mscan.py#L328
+  Framework: PyTorch
diff --git a/configs/segnext/segnext.yml b/configs/segnext/segnext.yml
deleted file mode 100644
index 3bcdea8403..0000000000
--- a/configs/segnext/segnext.yml
+++ /dev/null
@@ -1,103 +0,0 @@
-Collections:
-- Name: SegNeXt
-  Metadata:
-    Training Data:
-    - ADE20K
-  Paper:
-    URL: https://arxiv.org/abs/2209.08575
-    Title: 'SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation'
-  README: configs/segnext/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/mscan.py#L328
-    Version: dev-1.x
-  Converted From:
-    Code: https://github.com/visual-attention-network/segnext
-Models:
-- Name: segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512
-  In Collection: SegNeXt
-  Metadata:
-    backbone: MSCAN-T
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 19.09
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 17.88
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 41.5
-      mIoU(ms+flip): 42.59
-  Config: configs/segnext/segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k_20230210_140244-05bd8466.pth
-- Name: segnext_mscan-s_1xb16-adamw-160k_ade20k-512x512
-  In Collection: SegNeXt
-  Metadata:
-    backbone: MSCAN-S
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 23.66
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 21.47
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 44.16
-      mIoU(ms+flip): 45.81
-  Config: configs/segnext/segnext_mscan-s_1xb16-adamw-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k_20230214_113014-43013668.pth
-- Name: segnext_mscan-b_1xb16-adamw-160k_ade20k-512x512
-  In Collection: SegNeXt
-  Metadata:
-    backbone: MSCAN-B
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 28.45
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 31.03
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 48.03
-      mIoU(ms+flip): 49.68
-  Config: configs/segnext/segnext_mscan-b_1xb16-adamw-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k_20230209_172053-b6f6c70c.pth
-- Name: segnext_mscan-l_1xb16-adamw-160k_ade20k-512x512
-  In Collection: SegNeXt
-  Metadata:
-    backbone: MSCAN-L
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 43.65
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 43.32
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 50.99
-      mIoU(ms+flip): 52.1
-  Config: configs/segnext/segnext_mscan-l_1xb16-adamw-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k_20230209_172055-19b14b63.pth
diff --git a/configs/sem_fpn/README.md b/configs/sem_fpn/README.md
index fcef72d2a5..8bbbd0eee0 100644
--- a/configs/sem_fpn/README.md
+++ b/configs/sem_fpn/README.md
@@ -1,6 +1,6 @@
 # Semantic FPN
 
-[Panoptic Feature Pyramid Networks](https://arxiv.org/abs/1901.02446)
+> [Panoptic Feature Pyramid Networks](https://arxiv.org/abs/1901.02446)
 
 ## Introduction
 
@@ -22,6 +22,22 @@ The recently introduced panoptic segmentation task has renewed our community's i
 <img src="https://user-images.githubusercontent.com/24582831/142902694-03ed2131-9104-467b-ace1-c74c62fb7177.png" width="60%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FPN    | R-50     | 512x1024  |   80000 |      2.8 | 13.54          | V100   | 74.52 | 76.08         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/sem_fpn/fpn_r50_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x1024_80k_cityscapes/fpn_r50_512x1024_80k_cityscapes_20200717_021437-94018a0d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x1024_80k_cityscapes/fpn_r50_512x1024_80k_cityscapes-20200717_021437.log.json)     |
+| FPN    | R-101    | 512x1024  |   80000 |      3.9 | 10.29          | V100   | 75.80 | 77.40         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/sem_fpn/fpn_r101_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x1024_80k_cityscapes/fpn_r101_512x1024_80k_cityscapes_20200717_012416-c5800d4c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x1024_80k_cityscapes/fpn_r101_512x1024_80k_cityscapes-20200717_012416.log.json) |
+
+### ADE20K
+
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                   | download                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| FPN    | R-50     | 512x512   |  160000 |      4.9 | 55.77          | V100   | 37.49 | 39.09         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/sem_fpn/fpn_r50_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x512_160k_ade20k/fpn_r50_512x512_160k_ade20k_20200718_131734-5b5a6ab9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x512_160k_ade20k/fpn_r50_512x512_160k_ade20k-20200718_131734.log.json)     |
+| FPN    | R-101    | 512x512   |  160000 |      5.9 | 40.58          | V100   | 39.35 | 40.72         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/sem_fpn/fpn_r101_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x512_160k_ade20k/fpn_r101_512x512_160k_ade20k_20200718_131734-306b5004.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x512_160k_ade20k/fpn_r101_512x512_160k_ade20k-20200718_131734.log.json) |
+
 ## Citation
 
 ```bibtex
@@ -33,19 +49,3 @@ The recently introduced panoptic segmentation task has renewed our community's i
   year={2019}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------: | -------------- | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FPN    | R-50     | 512x1024  |   80000 |      2.8 | 13.54          | 74.52 | 76.08         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/sem_fpn/fpn_r50_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x1024_80k_cityscapes/fpn_r50_512x1024_80k_cityscapes_20200717_021437-94018a0d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x1024_80k_cityscapes/fpn_r50_512x1024_80k_cityscapes-20200717_021437.log.json)     |
-| FPN    | R-101    | 512x1024  |   80000 |      3.9 | 10.29          | 75.80 | 77.40         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/sem_fpn/fpn_r101_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x1024_80k_cityscapes/fpn_r101_512x1024_80k_cityscapes_20200717_012416-c5800d4c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x1024_80k_cityscapes/fpn_r101_512x1024_80k_cityscapes-20200717_012416.log.json) |
-
-### ADE20K
-
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                   | download                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------: | -------------- | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| FPN    | R-50     | 512x512   |  160000 |      4.9 | 55.77          | 37.49 | 39.09         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/sem_fpn/fpn_r50_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x512_160k_ade20k/fpn_r50_512x512_160k_ade20k_20200718_131734-5b5a6ab9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x512_160k_ade20k/fpn_r50_512x512_160k_ade20k-20200718_131734.log.json)     |
-| FPN    | R-101    | 512x512   |  160000 |      5.9 | 40.58          | 39.35 | 40.72         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/sem_fpn/fpn_r101_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x512_160k_ade20k/fpn_r101_512x512_160k_ade20k_20200718_131734-306b5004.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x512_160k_ade20k/fpn_r101_512x512_160k_ade20k-20200718_131734.log.json) |
diff --git a/configs/sem_fpn/metafile.yaml b/configs/sem_fpn/metafile.yaml
new file mode 100644
index 0000000000..e734897245
--- /dev/null
+++ b/configs/sem_fpn/metafile.yaml
@@ -0,0 +1,110 @@
+Collections:
+- Name: FPN
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - ADE20K
+  Paper:
+    Title: Panoptic Feature Pyramid Networks
+    URL: https://arxiv.org/abs/1901.02446
+  README: configs/sem_fpn/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: fpn_r50_4xb2-80k_cityscapes-512x1024
+  In Collection: FPN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 74.52
+      mIoU(ms+flip): 76.08
+  Config: configs/sem_fpn/fpn_r50_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50
+    - FPN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 2.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x1024_80k_cityscapes/fpn_r50_512x1024_80k_cityscapes_20200717_021437-94018a0d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x1024_80k_cityscapes/fpn_r50_512x1024_80k_cityscapes-20200717_021437.log.json
+  Paper:
+    Title: Panoptic Feature Pyramid Networks
+    URL: https://arxiv.org/abs/1901.02446
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fpn_head.py#L12
+  Framework: PyTorch
+- Name: fpn_r101_4xb2-80k_cityscapes-512x1024
+  In Collection: FPN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 75.8
+      mIoU(ms+flip): 77.4
+  Config: configs/sem_fpn/fpn_r101_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101
+    - FPN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 3.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x1024_80k_cityscapes/fpn_r101_512x1024_80k_cityscapes_20200717_012416-c5800d4c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x1024_80k_cityscapes/fpn_r101_512x1024_80k_cityscapes-20200717_012416.log.json
+  Paper:
+    Title: Panoptic Feature Pyramid Networks
+    URL: https://arxiv.org/abs/1901.02446
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fpn_head.py#L12
+  Framework: PyTorch
+- Name: fpn_r50_4xb4-160k_ade20k-512x512
+  In Collection: FPN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 37.49
+      mIoU(ms+flip): 39.09
+  Config: configs/sem_fpn/fpn_r50_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50
+    - FPN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 4.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x512_160k_ade20k/fpn_r50_512x512_160k_ade20k_20200718_131734-5b5a6ab9.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x512_160k_ade20k/fpn_r50_512x512_160k_ade20k-20200718_131734.log.json
+  Paper:
+    Title: Panoptic Feature Pyramid Networks
+    URL: https://arxiv.org/abs/1901.02446
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fpn_head.py#L12
+  Framework: PyTorch
+- Name: fpn_r101_4xb4-160k_ade20k-512x512
+  In Collection: FPN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 39.35
+      mIoU(ms+flip): 40.72
+  Config: configs/sem_fpn/fpn_r101_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101
+    - FPN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 5.9
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x512_160k_ade20k/fpn_r101_512x512_160k_ade20k_20200718_131734-306b5004.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x512_160k_ade20k/fpn_r101_512x512_160k_ade20k-20200718_131734.log.json
+  Paper:
+    Title: Panoptic Feature Pyramid Networks
+    URL: https://arxiv.org/abs/1901.02446
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fpn_head.py#L12
+  Framework: PyTorch
diff --git a/configs/sem_fpn/sem_fpn.yml b/configs/sem_fpn/sem_fpn.yml
deleted file mode 100644
index 79ed0b81c4..0000000000
--- a/configs/sem_fpn/sem_fpn.yml
+++ /dev/null
@@ -1,104 +0,0 @@
-Collections:
-- Name: FPN
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-  Paper:
-    URL: https://arxiv.org/abs/1901.02446
-    Title: Panoptic Feature Pyramid Networks
-  README: configs/sem_fpn/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fpn_head.py#L12
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/facebookresearch/detectron2
-Models:
-- Name: fpn_r50_4xb2-80k_cityscapes-512x1024
-  In Collection: FPN
-  Metadata:
-    backbone: R-50
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 73.86
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 2.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 74.52
-      mIoU(ms+flip): 76.08
-  Config: configs/sem_fpn/fpn_r50_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x1024_80k_cityscapes/fpn_r50_512x1024_80k_cityscapes_20200717_021437-94018a0d.pth
-- Name: fpn_r101_4xb2-80k_cityscapes-512x1024
-  In Collection: FPN
-  Metadata:
-    backbone: R-101
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 97.18
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 3.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 75.8
-      mIoU(ms+flip): 77.4
-  Config: configs/sem_fpn/fpn_r101_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x1024_80k_cityscapes/fpn_r101_512x1024_80k_cityscapes_20200717_012416-c5800d4c.pth
-- Name: fpn_r50_4xb4-160k_ade20k-512x512
-  In Collection: FPN
-  Metadata:
-    backbone: R-50
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 17.93
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 4.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 37.49
-      mIoU(ms+flip): 39.09
-  Config: configs/sem_fpn/fpn_r50_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x512_160k_ade20k/fpn_r50_512x512_160k_ade20k_20200718_131734-5b5a6ab9.pth
-- Name: fpn_r101_4xb4-160k_ade20k-512x512
-  In Collection: FPN
-  Metadata:
-    backbone: R-101
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 24.64
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 5.9
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 39.35
-      mIoU(ms+flip): 40.72
-  Config: configs/sem_fpn/fpn_r101_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x512_160k_ade20k/fpn_r101_512x512_160k_ade20k_20200718_131734-306b5004.pth
diff --git a/configs/setr/README.md b/configs/setr/README.md
index 1aa3f245a7..556c625f41 100644
--- a/configs/setr/README.md
+++ b/configs/setr/README.md
@@ -1,6 +1,6 @@
 # SETR
 
-[Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://arxiv.org/abs/2012.15840)
+> [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://arxiv.org/abs/2012.15840)
 
 ## Introduction
 
@@ -26,17 +26,6 @@ Most recent semantic segmentation methods adopt a fully-convolutional network (F
 This head has two version head.
 ```
 
-## Citation
-
-```bibtex
-@article{zheng2020rethinking,
-  title={Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers},
-  author={Zheng, Sixiao and Lu, Jiachen and Zhao, Hengshuang and Zhu, Xiatian and Luo, Zekun and Wang, Yabiao and Fu, Yanwei and Feng, Jianfeng and Xiang, Tao and Torr, Philip HS and others},
-  journal={arXiv preprint arXiv:2012.15840},
-  year={2020}
-}
-```
-
 ## Usage
 
 You can download the pretrain from [here](https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_large_p16_384-b3be5167.pth). Then you can convert its keys with the script `vit2mmseg.py` in the tools directory.
@@ -58,17 +47,28 @@ This script convert the model from `PRETRAIN_PATH` and store the converted model
 
 ### ADE20K
 
-| Method     | Backbone | Crop Size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                             |
-| ---------- | -------- | --------- | ---------- | ------- | -------- | -------------- | ----- | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| SETR Naive | ViT-L    | 512x512   | 16         | 160000  | 18.40    | 4.72           | 48.28 |         49.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l_naive_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_512x512_160k_b16_ade20k/setr_naive_512x512_160k_b16_ade20k_20210619_191258-061f24f5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_512x512_160k_b16_ade20k/setr_naive_512x512_160k_b16_ade20k_20210619_191258.log.json) |
-| SETR PUP   | ViT-L    | 512x512   | 16         | 160000  | 19.54    | 4.50           | 48.24 |         49.99 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l_pup_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_512x512_160k_b16_ade20k/setr_pup_512x512_160k_b16_ade20k_20210619_191343-7e0ce826.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_512x512_160k_b16_ade20k/setr_pup_512x512_160k_b16_ade20k_20210619_191343.log.json)         |
-| SETR MLA   | ViT-L    | 512x512   | 8          | 160000  | 10.96    | -              | 47.34 |         49.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l-mla_8xb1-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b8_ade20k/setr_mla_512x512_160k_b8_ade20k_20210619_191118-c6d21df0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b8_ade20k/setr_mla_512x512_160k_b8_ade20k_20210619_191118.log.json)             |
-| SETR MLA   | ViT-L    | 512x512   | 16         | 160000  | 17.30    | 5.25           | 47.39 |         49.37 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l_mla_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b16_ade20k/setr_mla_512x512_160k_b16_ade20k_20210619_191057-f9741de7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b16_ade20k/setr_mla_512x512_160k_b16_ade20k_20210619_191057.log.json)         |
+| Method     | Backbone | Crop Size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                             |
+| ---------- | -------- | --------- | ---------- | ------- | -------- | -------------- | ------ | ----- | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| SETR Naive | ViT-L    | 512x512   | 16         | 160000  | 18.40    | 4.72           | V100   | 48.28 |         49.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l_naive_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_512x512_160k_b16_ade20k/setr_naive_512x512_160k_b16_ade20k_20210619_191258-061f24f5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_512x512_160k_b16_ade20k/setr_naive_512x512_160k_b16_ade20k_20210619_191258.log.json) |
+| SETR PUP   | ViT-L    | 512x512   | 16         | 160000  | 19.54    | 4.50           | V100   | 48.24 |         49.99 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l_pup_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_512x512_160k_b16_ade20k/setr_pup_512x512_160k_b16_ade20k_20210619_191343-7e0ce826.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_512x512_160k_b16_ade20k/setr_pup_512x512_160k_b16_ade20k_20210619_191343.log.json)         |
+| SETR MLA   | ViT-L    | 512x512   | 8          | 160000  | 10.96    | -              | V100   | 47.34 |         49.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l-mla_8xb1-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b8_ade20k/setr_mla_512x512_160k_b8_ade20k_20210619_191118-c6d21df0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b8_ade20k/setr_mla_512x512_160k_b8_ade20k_20210619_191118.log.json)             |
+| SETR MLA   | ViT-L    | 512x512   | 16         | 160000  | 17.30    | 5.25           | V100   | 47.39 |         49.37 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l_mla_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b16_ade20k/setr_mla_512x512_160k_b16_ade20k_20210619_191057-f9741de7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b16_ade20k/setr_mla_512x512_160k_b16_ade20k_20210619_191057.log.json)         |
 
 ### Cityscapes
 
-| Method     | Backbone | Crop Size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                                                 |
-| ---------- | -------- | --------- | ---------- | ------- | -------- | -------------- | ----- | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| SETR Naive | ViT-L    | 768x768   | 8          | 80000   | 24.06    | 0.39           | 78.10 |         80.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l_naive_8xb1-80k_cityscapes-768x768.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_vit-large_8x1_768x768_80k_cityscapes/setr_naive_vit-large_8x1_768x768_80k_cityscapes_20211123_000505-20728e80.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_vit-large_8x1_768x768_80k_cityscapes/setr_naive_vit-large_8x1_768x768_80k_cityscapes_20211123_000505.log.json) |
-| SETR PUP   | ViT-L    | 768x768   | 8          | 80000   | 27.96    | 0.37           | 79.21 |         81.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l_pup_8xb1-80k_cityscapes-768x768.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_vit-large_8x1_768x768_80k_cityscapes/setr_pup_vit-large_8x1_768x768_80k_cityscapes_20211122_155115-f6f37b8f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_vit-large_8x1_768x768_80k_cityscapes/setr_pup_vit-large_8x1_768x768_80k_cityscapes_20211122_155115.log.json)         |
-| SETR MLA   | ViT-L    | 768x768   | 8          | 80000   | 24.10    | 0.41           | 77.00 |         79.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l_mla_8xb1-80k_cityscapes-768x768.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_vit-large_8x1_768x768_80k_cityscapes/setr_mla_vit-large_8x1_768x768_80k_cityscapes_20211119_101003-7f8dccbe.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_vit-large_8x1_768x768_80k_cityscapes/setr_mla_vit-large_8x1_768x768_80k_cityscapes_20211119_101003.log.json)         |
+| Method     | Backbone | Crop Size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                                                 |
+| ---------- | -------- | --------- | ---------- | ------- | -------- | -------------- | ------ | ----- | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| SETR Naive | ViT-L    | 768x768   | 8          | 80000   | 24.06    | 0.39           | V100   | 78.10 |         80.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l_naive_8xb1-80k_cityscapes-768x768.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_vit-large_8x1_768x768_80k_cityscapes/setr_naive_vit-large_8x1_768x768_80k_cityscapes_20211123_000505-20728e80.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_vit-large_8x1_768x768_80k_cityscapes/setr_naive_vit-large_8x1_768x768_80k_cityscapes_20211123_000505.log.json) |
+| SETR PUP   | ViT-L    | 768x768   | 8          | 80000   | 27.96    | 0.37           | V100   | 79.21 |         81.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l_pup_8xb1-80k_cityscapes-768x768.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_vit-large_8x1_768x768_80k_cityscapes/setr_pup_vit-large_8x1_768x768_80k_cityscapes_20211122_155115-f6f37b8f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_vit-large_8x1_768x768_80k_cityscapes/setr_pup_vit-large_8x1_768x768_80k_cityscapes_20211122_155115.log.json)         |
+| SETR MLA   | ViT-L    | 768x768   | 8          | 80000   | 24.10    | 0.41           | V100   | 77.00 |         79.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l_mla_8xb1-80k_cityscapes-768x768.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_vit-large_8x1_768x768_80k_cityscapes/setr_mla_vit-large_8x1_768x768_80k_cityscapes_20211119_101003-7f8dccbe.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_vit-large_8x1_768x768_80k_cityscapes/setr_mla_vit-large_8x1_768x768_80k_cityscapes_20211119_101003.log.json)         |
+
+## Citation
+
+```bibtex
+@article{zheng2020rethinking,
+  title={Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers},
+  author={Zheng, Sixiao and Lu, Jiachen and Zhao, Hengshuang and Zhu, Xiatian and Luo, Zekun and Wang, Yabiao and Fu, Yanwei and Feng, Jianfeng and Xiang, Tao and Torr, Philip HS and others},
+  journal={arXiv preprint arXiv:2012.15840},
+  year={2020}
+}
+```
diff --git a/configs/setr/metafile.yaml b/configs/setr/metafile.yaml
new file mode 100644
index 0000000000..8e6bc087dd
--- /dev/null
+++ b/configs/setr/metafile.yaml
@@ -0,0 +1,197 @@
+Collections:
+- Name: SETR
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - ADE20K
+    - Cityscapes
+  Paper:
+    Title: Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective
+      with Transformers
+    URL: https://arxiv.org/abs/2012.15840
+  README: configs/setr/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: setr_vit-l_naive_8xb2-160k_ade20k-512x512
+  In Collection: SETR
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 48.28
+      mIoU(ms+flip): 49.56
+  Config: configs/setr/setr_vit-l_naive_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - ViT-L
+    - SETR
+    - Naive
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 18.4
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_512x512_160k_b16_ade20k/setr_naive_512x512_160k_b16_ade20k_20210619_191258-061f24f5.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_512x512_160k_b16_ade20k/setr_naive_512x512_160k_b16_ade20k_20210619_191258.log.json
+  Paper:
+    Title: Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective
+      with Transformers
+    URL: https://arxiv.org/abs/2012.15840
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/setr_up_head.py#L11
+  Framework: PyTorch
+- Name: setr_vit-l_pup_8xb2-160k_ade20k-512x512
+  In Collection: SETR
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 48.24
+      mIoU(ms+flip): 49.99
+  Config: configs/setr/setr_vit-l_pup_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - ViT-L
+    - SETR
+    - PUP
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 19.54
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_512x512_160k_b16_ade20k/setr_pup_512x512_160k_b16_ade20k_20210619_191343-7e0ce826.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_512x512_160k_b16_ade20k/setr_pup_512x512_160k_b16_ade20k_20210619_191343.log.json
+  Paper:
+    Title: Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective
+      with Transformers
+    URL: https://arxiv.org/abs/2012.15840
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/setr_up_head.py#L11
+  Framework: PyTorch
+- Name: setr_vit-l-mla_8xb1-160k_ade20k-512x512
+  In Collection: SETR
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 47.34
+      mIoU(ms+flip): 49.05
+  Config: configs/setr/setr_vit-l-mla_8xb1-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 8
+    Architecture:
+    - ViT-L
+    - SETR
+    - MLA
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 10.96
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b8_ade20k/setr_mla_512x512_160k_b8_ade20k_20210619_191118-c6d21df0.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b8_ade20k/setr_mla_512x512_160k_b8_ade20k_20210619_191118.log.json
+  Paper:
+    Title: Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective
+      with Transformers
+    URL: https://arxiv.org/abs/2012.15840
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/setr_up_head.py#L11
+  Framework: PyTorch
+- Name: setr_vit-l_mla_8xb2-160k_ade20k-512x512
+  In Collection: SETR
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 47.39
+      mIoU(ms+flip): 49.37
+  Config: configs/setr/setr_vit-l_mla_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - ViT-L
+    - SETR
+    - MLA
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 17.3
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b16_ade20k/setr_mla_512x512_160k_b16_ade20k_20210619_191057-f9741de7.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b16_ade20k/setr_mla_512x512_160k_b16_ade20k_20210619_191057.log.json
+  Paper:
+    Title: Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective
+      with Transformers
+    URL: https://arxiv.org/abs/2012.15840
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/setr_up_head.py#L11
+  Framework: PyTorch
+- Name: setr_vit-l_naive_8xb1-80k_cityscapes-768x768
+  In Collection: SETR
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.1
+      mIoU(ms+flip): 80.22
+  Config: configs/setr/setr_vit-l_naive_8xb1-80k_cityscapes-768x768.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - ViT-L
+    - SETR
+    - Naive
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 24.06
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_vit-large_8x1_768x768_80k_cityscapes/setr_naive_vit-large_8x1_768x768_80k_cityscapes_20211123_000505-20728e80.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_vit-large_8x1_768x768_80k_cityscapes/setr_naive_vit-large_8x1_768x768_80k_cityscapes_20211123_000505.log.json
+  Paper:
+    Title: Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective
+      with Transformers
+    URL: https://arxiv.org/abs/2012.15840
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/setr_up_head.py#L11
+  Framework: PyTorch
+- Name: setr_vit-l_pup_8xb1-80k_cityscapes-768x768
+  In Collection: SETR
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.21
+      mIoU(ms+flip): 81.02
+  Config: configs/setr/setr_vit-l_pup_8xb1-80k_cityscapes-768x768.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - ViT-L
+    - SETR
+    - PUP
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 27.96
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_vit-large_8x1_768x768_80k_cityscapes/setr_pup_vit-large_8x1_768x768_80k_cityscapes_20211122_155115-f6f37b8f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_vit-large_8x1_768x768_80k_cityscapes/setr_pup_vit-large_8x1_768x768_80k_cityscapes_20211122_155115.log.json
+  Paper:
+    Title: Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective
+      with Transformers
+    URL: https://arxiv.org/abs/2012.15840
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/setr_up_head.py#L11
+  Framework: PyTorch
+- Name: setr_vit-l_mla_8xb1-80k_cityscapes-768x768
+  In Collection: SETR
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.0
+      mIoU(ms+flip): 79.59
+  Config: configs/setr/setr_vit-l_mla_8xb1-80k_cityscapes-768x768.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - ViT-L
+    - SETR
+    - MLA
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 24.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_vit-large_8x1_768x768_80k_cityscapes/setr_mla_vit-large_8x1_768x768_80k_cityscapes_20211119_101003-7f8dccbe.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_vit-large_8x1_768x768_80k_cityscapes/setr_mla_vit-large_8x1_768x768_80k_cityscapes_20211119_101003.log.json
+  Paper:
+    Title: Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective
+      with Transformers
+    URL: https://arxiv.org/abs/2012.15840
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/setr_up_head.py#L11
+  Framework: PyTorch
diff --git a/configs/setr/setr.yml b/configs/setr/setr.yml
deleted file mode 100644
index 6a9987089d..0000000000
--- a/configs/setr/setr.yml
+++ /dev/null
@@ -1,164 +0,0 @@
-Collections:
-- Name: SETR
-  Metadata:
-    Training Data:
-    - ADE20K
-    - Cityscapes
-  Paper:
-    URL: https://arxiv.org/abs/2012.15840
-    Title: Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective
-      with Transformers
-  README: configs/setr/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/setr_up_head.py#L11
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/fudan-zvg/SETR
-Models:
-- Name: setr_vit-l_naive_8xb2-160k_ade20k-512x512
-  In Collection: SETR
-  Metadata:
-    backbone: ViT-L
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 211.86
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 18.4
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 48.28
-      mIoU(ms+flip): 49.56
-  Config: configs/setr/setr_vit-l_naive_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_512x512_160k_b16_ade20k/setr_naive_512x512_160k_b16_ade20k_20210619_191258-061f24f5.pth
-- Name: setr_vit-l_pup_8xb2-160k_ade20k-512x512
-  In Collection: SETR
-  Metadata:
-    backbone: ViT-L
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 222.22
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 19.54
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 48.24
-      mIoU(ms+flip): 49.99
-  Config: configs/setr/setr_vit-l_pup_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_512x512_160k_b16_ade20k/setr_pup_512x512_160k_b16_ade20k_20210619_191343-7e0ce826.pth
-- Name: setr_vit-l-mla_8xb1-160k_ade20k-512x512
-  In Collection: SETR
-  Metadata:
-    backbone: ViT-L
-    crop size: (512,512)
-    lr schd: 160000
-    Training Memory (GB): 10.96
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 47.34
-      mIoU(ms+flip): 49.05
-  Config: configs/setr/setr_vit-l-mla_8xb1-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b8_ade20k/setr_mla_512x512_160k_b8_ade20k_20210619_191118-c6d21df0.pth
-- Name: setr_vit-l_mla_8xb2-160k_ade20k-512x512
-  In Collection: SETR
-  Metadata:
-    backbone: ViT-L
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 190.48
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 17.3
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 47.39
-      mIoU(ms+flip): 49.37
-  Config: configs/setr/setr_vit-l_mla_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b16_ade20k/setr_mla_512x512_160k_b16_ade20k_20210619_191057-f9741de7.pth
-- Name: setr_vit-l_naive_8xb1-80k_cityscapes-768x768
-  In Collection: SETR
-  Metadata:
-    backbone: ViT-L
-    crop size: (768,768)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 2564.1
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (768,768)
-    Training Memory (GB): 24.06
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.1
-      mIoU(ms+flip): 80.22
-  Config: configs/setr/setr_vit-l_naive_8xb1-80k_cityscapes-768x768.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_vit-large_8x1_768x768_80k_cityscapes/setr_naive_vit-large_8x1_768x768_80k_cityscapes_20211123_000505-20728e80.pth
-- Name: setr_vit-l_pup_8xb1-80k_cityscapes-768x768
-  In Collection: SETR
-  Metadata:
-    backbone: ViT-L
-    crop size: (768,768)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 2702.7
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (768,768)
-    Training Memory (GB): 27.96
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.21
-      mIoU(ms+flip): 81.02
-  Config: configs/setr/setr_vit-l_pup_8xb1-80k_cityscapes-768x768.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_vit-large_8x1_768x768_80k_cityscapes/setr_pup_vit-large_8x1_768x768_80k_cityscapes_20211122_155115-f6f37b8f.pth
-- Name: setr_vit-l_mla_8xb1-80k_cityscapes-768x768
-  In Collection: SETR
-  Metadata:
-    backbone: ViT-L
-    crop size: (768,768)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 2439.02
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (768,768)
-    Training Memory (GB): 24.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.0
-      mIoU(ms+flip): 79.59
-  Config: configs/setr/setr_vit-l_mla_8xb1-80k_cityscapes-768x768.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_vit-large_8x1_768x768_80k_cityscapes/setr_mla_vit-large_8x1_768x768_80k_cityscapes_20211119_101003-7f8dccbe.pth
diff --git a/configs/stdc/README.md b/configs/stdc/README.md
index 639e6b6986..1efd65482f 100644
--- a/configs/stdc/README.md
+++ b/configs/stdc/README.md
@@ -1,6 +1,6 @@
 # STDC
 
-[Rethinking BiSeNet For Real-time Semantic Segmentation](https://arxiv.org/abs/2104.13188)
+> [Rethinking BiSeNet For Real-time Semantic Segmentation](https://arxiv.org/abs/2104.13188)
 
 ## Introduction
 
@@ -22,18 +22,6 @@ BiSeNet has been proved to be a popular two-stream network for real-time segment
 <img src="https://user-images.githubusercontent.com/24582831/143640374-d0709587-edb2-4821-bb60-340035f6ad8f.png" width="60%"/>
 </div>
 
-## Citation
-
-```bibtex
-@inproceedings{fan2021rethinking,
-  title={Rethinking BiSeNet For Real-time Semantic Segmentation},
-  author={Fan, Mingyuan and Lai, Shenqi and Huang, Junshi and Wei, Xiaoming and Chai, Zhenhua and Luo, Junfeng and Wei, Xiaolin},
-  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
-  pages={9716--9725},
-  year={2021}
-}
-```
-
 ## Usage
 
 We have provided [ImageNet Pretrained STDCNet Weights](https://drive.google.com/drive/folders/1wROFwRt8qWHD4jSo8Zu1gp1d6oYJ3ns1) models converted from [official repo](https://github.com/MichaelFan01/STDC-Seg).
@@ -58,12 +46,12 @@ This script convert model from `PRETRAIN_PATH` and store the converted model in
 
 ### Cityscapes
 
-| Method               | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                             |
-| -------------------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| STDC 1 (No Pretrain) | STDC1    | 512x1024  |   80000 | 7.15     | 23.06          | 71.82 | 73.89         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/stdc/stdc1_4xb12-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_512x1024_80k_cityscapes/stdc1_512x1024_80k_cityscapes_20220224_073048-74e6920a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_512x1024_80k_cityscapes/stdc1_512x1024_80k_cityscapes_20220224_073048.log.json)                                     |
-| STDC 1               | STDC1    | 512x1024  |   80000 | -        | -              | 74.94 | 76.97         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/stdc/stdc1_in1k-pre_4xb12-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_in1k-pre_512x1024_80k_cityscapes/stdc1_in1k-pre_512x1024_80k_cityscapes_20220224_141648-3d4c2981.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_in1k-pre_512x1024_80k_cityscapes/stdc1_in1k-pre_512x1024_80k_cityscapes_20220224_141648.log.json) |
-| STDC 2 (No Pretrain) | STDC2    | 512x1024  |   80000 | 8.27     | 23.71          | 73.15 | 76.13         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/stdc/stdc2_4xb12-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_512x1024_80k_cityscapes/stdc2_512x1024_80k_cityscapes_20220222_132015-fb1e3a1a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_512x1024_80k_cityscapes/stdc2_512x1024_80k_cityscapes_20220222_132015.log.json)                                     |
-| STDC 2               | STDC2    | 512x1024  |   80000 | -        | -              | 76.67 | 78.67         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/stdc/stdc2_in1k-pre_4xb12-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_in1k-pre_512x1024_80k_cityscapes/stdc2_in1k-pre_512x1024_80k_cityscapes_20220224_073048-1f8f0f6c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_in1k-pre_512x1024_80k_cityscapes/stdc2_in1k-pre_512x1024_80k_cityscapes_20220224_073048.log.json) |
+| Method | Backbone             | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                             |
+| ------ | -------------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| STDC   | STDC1 (No Pretrain)  | 512x1024  |   80000 | 7.15     | 23.06          | V100   | 71.82 | 73.89         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/stdc/stdc1_4xb12-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_512x1024_80k_cityscapes/stdc1_512x1024_80k_cityscapes_20220224_073048-74e6920a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_512x1024_80k_cityscapes/stdc1_512x1024_80k_cityscapes_20220224_073048.log.json)                                     |
+| STDC   | STDC1                | 512x1024  |   80000 | -        | -              | V100   | 74.94 | 76.97         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/stdc/stdc1_in1k-pre_4xb12-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_in1k-pre_512x1024_80k_cityscapes/stdc1_in1k-pre_512x1024_80k_cityscapes_20220224_141648-3d4c2981.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_in1k-pre_512x1024_80k_cityscapes/stdc1_in1k-pre_512x1024_80k_cityscapes_20220224_141648.log.json) |
+| STDC   | STDC2  (No Pretrain) | 512x1024  |   80000 | 8.27     | 23.71          | V100   | 73.15 | 76.13         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/stdc/stdc2_4xb12-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_512x1024_80k_cityscapes/stdc2_512x1024_80k_cityscapes_20220222_132015-fb1e3a1a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_512x1024_80k_cityscapes/stdc2_512x1024_80k_cityscapes_20220222_132015.log.json)                                     |
+| STDC   | STDC2                | 512x1024  |   80000 | -        | -              | V100   | 76.67 | 78.67         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/stdc/stdc2_in1k-pre_4xb12-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_in1k-pre_512x1024_80k_cityscapes/stdc2_in1k-pre_512x1024_80k_cityscapes_20220224_073048-1f8f0f6c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_in1k-pre_512x1024_80k_cityscapes/stdc2_in1k-pre_512x1024_80k_cityscapes_20220224_073048.log.json) |
 
 Note:
 
@@ -71,3 +59,15 @@ Note:
 - `No Pretrain` means the model is trained from scratch.
 - The FPS is for reference only. The environment is also different from paper setting, whose input size is `512x1024` and `768x1536`, i.e., 50% and 75% of our input size, respectively and using TensorRT.
 - The parameter `fusion_kernel` in `STDCHead` is not learnable. In official repo, `find_unused_parameters=True` is set [here](https://github.com/MichaelFan01/STDC-Seg/blob/59ff37fbd693b99972c76fcefe97caa14aeb619f/train.py#L220). You may check it by printing model parameters of original repo on your own.
+
+## Citation
+
+```bibtex
+@inproceedings{fan2021rethinking,
+  title={Rethinking BiSeNet For Real-time Semantic Segmentation},
+  author={Fan, Mingyuan and Lai, Shenqi and Huang, Junshi and Wei, Xiaoming and Chai, Zhenhua and Luo, Junfeng and Wei, Xiaolin},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
+  pages={9716--9725},
+  year={2021}
+}
+```
diff --git a/configs/stdc/metafile.yaml b/configs/stdc/metafile.yaml
new file mode 100644
index 0000000000..93cb14f50b
--- /dev/null
+++ b/configs/stdc/metafile.yaml
@@ -0,0 +1,107 @@
+Collections:
+- Name: STDC
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+  Paper:
+    Title: Rethinking BiSeNet For Real-time Semantic Segmentation
+    URL: https://arxiv.org/abs/2104.13188
+  README: configs/stdc/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: stdc1_4xb12-80k_cityscapes-512x1024
+  In Collection: STDC
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 71.82
+      mIoU(ms+flip): 73.89
+  Config: configs/stdc/stdc1_4xb12-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 48
+    Architecture:
+    - STDC1
+    - STDC
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.15
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_512x1024_80k_cityscapes/stdc1_512x1024_80k_cityscapes_20220224_073048-74e6920a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_512x1024_80k_cityscapes/stdc1_512x1024_80k_cityscapes_20220224_073048.log.json
+  Paper:
+    Title: Rethinking BiSeNet For Real-time Semantic Segmentation
+    URL: https://arxiv.org/abs/2104.13188
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/stdc.py#L394
+  Framework: PyTorch
+- Name: stdc1_in1k-pre_4xb12-80k_cityscapes-512x1024
+  In Collection: STDC
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 74.94
+      mIoU(ms+flip): 76.97
+  Config: configs/stdc/stdc1_in1k-pre_4xb12-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 48
+    Architecture:
+    - STDC1
+    - STDC
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_in1k-pre_512x1024_80k_cityscapes/stdc1_in1k-pre_512x1024_80k_cityscapes_20220224_141648-3d4c2981.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_in1k-pre_512x1024_80k_cityscapes/stdc1_in1k-pre_512x1024_80k_cityscapes_20220224_141648.log.json
+  Paper:
+    Title: Rethinking BiSeNet For Real-time Semantic Segmentation
+    URL: https://arxiv.org/abs/2104.13188
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/stdc.py#L394
+  Framework: PyTorch
+- Name: stdc2_4xb12-80k_cityscapes-512x1024
+  In Collection: STDC
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 73.15
+      mIoU(ms+flip): 76.13
+  Config: configs/stdc/stdc2_4xb12-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 48
+    Architecture:
+    - STDC2
+    - STDC
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.27
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_512x1024_80k_cityscapes/stdc2_512x1024_80k_cityscapes_20220222_132015-fb1e3a1a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_512x1024_80k_cityscapes/stdc2_512x1024_80k_cityscapes_20220222_132015.log.json
+  Paper:
+    Title: Rethinking BiSeNet For Real-time Semantic Segmentation
+    URL: https://arxiv.org/abs/2104.13188
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/stdc.py#L394
+  Framework: PyTorch
+- Name: stdc2_in1k-pre_4xb12-80k_cityscapes-512x1024
+  In Collection: STDC
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.67
+      mIoU(ms+flip): 78.67
+  Config: configs/stdc/stdc2_in1k-pre_4xb12-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 48
+    Architecture:
+    - STDC2
+    - STDC
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_in1k-pre_512x1024_80k_cityscapes/stdc2_in1k-pre_512x1024_80k_cityscapes_20220224_073048-1f8f0f6c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_in1k-pre_512x1024_80k_cityscapes/stdc2_in1k-pre_512x1024_80k_cityscapes_20220224_073048.log.json
+  Paper:
+    Title: Rethinking BiSeNet For Real-time Semantic Segmentation
+    URL: https://arxiv.org/abs/2104.13188
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/stdc.py#L394
+  Framework: PyTorch
diff --git a/configs/stdc/stdc.yml b/configs/stdc/stdc.yml
deleted file mode 100644
index 22fb37eeba..0000000000
--- a/configs/stdc/stdc.yml
+++ /dev/null
@@ -1,87 +0,0 @@
-Collections:
-- Name: STDC
-  Metadata:
-    Training Data:
-    - Cityscapes
-  Paper:
-    URL: https://arxiv.org/abs/2104.13188
-    Title: Rethinking BiSeNet For Real-time Semantic Segmentation
-  README: configs/stdc/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/stdc.py#L394
-    Version: v0.20.0
-  Converted From:
-    Code: https://github.com/MichaelFan01/STDC-Seg
-Models:
-- Name: stdc1_4xb12-80k_cityscapes-512x1024
-  In Collection: STDC
-  Metadata:
-    backbone: STDC1
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 43.37
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 7.15
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 71.82
-      mIoU(ms+flip): 73.89
-  Config: configs/stdc/stdc1_4xb12-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_512x1024_80k_cityscapes/stdc1_512x1024_80k_cityscapes_20220224_073048-74e6920a.pth
-- Name: stdc1_in1k-pre_4xb12-80k_cityscapes-512x1024
-  In Collection: STDC
-  Metadata:
-    backbone: STDC1
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 74.94
-      mIoU(ms+flip): 76.97
-  Config: configs/stdc/stdc1_in1k-pre_4xb12-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_in1k-pre_512x1024_80k_cityscapes/stdc1_in1k-pre_512x1024_80k_cityscapes_20220224_141648-3d4c2981.pth
-- Name: stdc2_4xb12-80k_cityscapes-512x1024
-  In Collection: STDC
-  Metadata:
-    backbone: STDC2
-    crop size: (512,1024)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 42.18
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 8.27
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 73.15
-      mIoU(ms+flip): 76.13
-  Config: configs/stdc/stdc2_4xb12-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_512x1024_80k_cityscapes/stdc2_512x1024_80k_cityscapes_20220222_132015-fb1e3a1a.pth
-- Name: stdc2_in1k-pre_4xb12-80k_cityscapes-512x1024
-  In Collection: STDC
-  Metadata:
-    backbone: STDC2
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 76.67
-      mIoU(ms+flip): 78.67
-  Config: configs/stdc/stdc2_in1k-pre_4xb12-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_in1k-pre_512x1024_80k_cityscapes/stdc2_in1k-pre_512x1024_80k_cityscapes_20220224_073048-1f8f0f6c.pth
diff --git a/configs/swin/README.md b/configs/swin/README.md
index 4ab20e80b8..18fcbae8bc 100644
--- a/configs/swin/README.md
+++ b/configs/swin/README.md
@@ -1,6 +1,6 @@
 # Swin Transformer
 
-[Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2103.14030)
+> [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2103.14030)
 
 ## Introduction
 
@@ -22,17 +22,6 @@ This paper presents a new vision Transformer, called Swin Transformer, that capa
 <img src="https://user-images.githubusercontent.com/24582831/142902882-3fb9014c-11b6-47e9-aa14-500dfe7cbb1c.png" width="80%"/>
 </div>
 
-## Citation
-
-```bibtex
-@article{liu2021Swin,
-  title={Swin Transformer: Hierarchical Vision Transformer using Shifted Windows},
-  author={Liu, Ze and Lin, Yutong and Cao, Yue and Hu, Han and Wei, Yixuan and Zhang, Zheng and Lin, Stephen and Guo, Baining},
-  journal={arXiv preprint arXiv:2103.14030},
-  year={2021}
-}
-```
-
 ## Usage
 
 We have provided pretrained models converted from [official repo](https://github.com/microsoft/Swin-Transformer)．
@@ -66,11 +55,22 @@ In our default setting, pretrained models and their corresponding [original mode
 
 ### ADE20K
 
-| Method  | Backbone | Crop Size | pretrain     | pretrain img size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) | config                                                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
-| ------- | -------- | --------- | ------------ | ----------------- | ---------- | ------- | -------- | -------------- | ----- | ------------: | --------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UPerNet | Swin-T   | 512x512   | ImageNet-1K  | 224x224           | 16         | 160000  | 5.02     | 21.06          | 44.41 |         45.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/swin-tiny-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210531_112542-e380ad3e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210531_112542.log.json)         |
-| UPerNet | Swin-S   | 512x512   | ImageNet-1K  | 224x224           | 16         | 160000  | 6.17     | 14.72          | 47.72 |         49.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/swin-small-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192015-ee2fff1c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192015.log.json)     |
-| UPerNet | Swin-B   | 512x512   | ImageNet-1K  | 224x224           | 16         | 160000  | 7.61     | 12.65          | 47.99 |         49.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/swin-base-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192340-593b0e13.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192340.log.json)         |
-| UPerNet | Swin-B   | 512x512   | ImageNet-22K | 224x224           | 16         | 160000  | -        | -              | 50.13 |          51.9 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/swin-base-patch4-window7-in22k-pre_upernet_8xb2-160k_ade20k-512x512.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K_20210526_211650-762e2178.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K_20210526_211650.log.json)     |
-| UPerNet | Swin-B   | 512x512   | ImageNet-1K  | 384x384           | 16         | 160000  | 8.52     | 12.10          | 48.35 |         49.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/swin-base-patch4-window12-in1k-384x384-pre_upernet_8xb2-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K_20210531_132020-05b22ea4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K_20210531_132020.log.json)     |
-| UPerNet | Swin-B   | 512x512   | ImageNet-22K | 384x384           | 16         | 160000  | -        | -              | 50.76 |          52.4 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/swin-base-patch4-window12-in22k-384x384-pre_upernet_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K_20210531_125459-429057bf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K_20210531_125459.log.json) |
+| Method  | Backbone | Crop Size | pretrain     | pretrain img size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
+| ------- | -------- | --------- | ------------ | ----------------- | ---------- | ------- | -------- | -------------- | ------ | ----- | ------------: | --------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UPerNet | Swin-T   | 512x512   | ImageNet-1K  | 224x224           | 16         | 160000  | 5.02     | 21.06          | V100   | 44.41 |         45.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/swin-tiny-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210531_112542-e380ad3e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210531_112542.log.json)         |
+| UPerNet | Swin-S   | 512x512   | ImageNet-1K  | 224x224           | 16         | 160000  | 6.17     | 14.72          | V100   | 47.72 |         49.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/swin-small-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192015-ee2fff1c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192015.log.json)     |
+| UPerNet | Swin-B   | 512x512   | ImageNet-1K  | 224x224           | 16         | 160000  | 7.61     | 12.65          | V100   | 47.99 |         49.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/swin-base-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192340-593b0e13.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192340.log.json)         |
+| UPerNet | Swin-B   | 512x512   | ImageNet-22K | 224x224           | 16         | 160000  | -        | -              | V100   | 50.13 |          51.9 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/swin-base-patch4-window7-in22k-pre_upernet_8xb2-160k_ade20k-512x512.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K_20210526_211650-762e2178.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K_20210526_211650.log.json)     |
+| UPerNet | Swin-B   | 512x512   | ImageNet-1K  | 384x384           | 16         | 160000  | 8.52     | 12.10          | V100   | 48.35 |         49.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/swin-base-patch4-window12-in1k-384x384-pre_upernet_8xb2-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K_20210531_132020-05b22ea4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K_20210531_132020.log.json)     |
+| UPerNet | Swin-B   | 512x512   | ImageNet-22K | 384x384           | 16         | 160000  | -        | -              | V100   | 50.76 |          52.4 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/swin-base-patch4-window12-in22k-384x384-pre_upernet_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K_20210531_125459-429057bf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K_20210531_125459.log.json) |
+
+## Citation
+
+```bibtex
+@article{liu2021Swin,
+  title={Swin Transformer: Hierarchical Vision Transformer using Shifted Windows},
+  author={Liu, Ze and Lin, Yutong and Cao, Yue and Hu, Han and Wei, Yixuan and Zhang, Zheng and Lin, Stephen and Guo, Baining},
+  journal={arXiv preprint arXiv:2103.14030},
+  year={2021}
+}
+```
diff --git a/configs/swin/metafile.yaml b/configs/swin/metafile.yaml
new file mode 100644
index 0000000000..67a4e07551
--- /dev/null
+++ b/configs/swin/metafile.yaml
@@ -0,0 +1,143 @@
+Models:
+- Name: swin-tiny-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 44.41
+      mIoU(ms+flip): 45.79
+  Config: configs/swin/swin-tiny-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Swin-T
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 5.02
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210531_112542-e380ad3e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210531_112542.log.json
+  Paper:
+    Title: 'Swin Transformer: Hierarchical Vision Transformer using Shifted Windows'
+    URL: https://arxiv.org/abs/2103.14030
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/swin.py#L524
+  Framework: PyTorch
+- Name: swin-small-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 47.72
+      mIoU(ms+flip): 49.24
+  Config: configs/swin/swin-small-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Swin-S
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 6.17
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192015-ee2fff1c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192015.log.json
+  Paper:
+    Title: 'Swin Transformer: Hierarchical Vision Transformer using Shifted Windows'
+    URL: https://arxiv.org/abs/2103.14030
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/swin.py#L524
+  Framework: PyTorch
+- Name: swin-base-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 47.99
+      mIoU(ms+flip): 49.57
+  Config: configs/swin/swin-base-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Swin-B
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 7.61
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192340-593b0e13.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192340.log.json
+  Paper:
+    Title: 'Swin Transformer: Hierarchical Vision Transformer using Shifted Windows'
+    URL: https://arxiv.org/abs/2103.14030
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/swin.py#L524
+  Framework: PyTorch
+- Name: swin-base-patch4-window7-in22k-pre_upernet_8xb2-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 50.13
+      mIoU(ms+flip): 51.9
+  Config: configs/swin/swin-base-patch4-window7-in22k-pre_upernet_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Swin-B
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K_20210526_211650-762e2178.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K_20210526_211650.log.json
+  Paper:
+    Title: 'Swin Transformer: Hierarchical Vision Transformer using Shifted Windows'
+    URL: https://arxiv.org/abs/2103.14030
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/swin.py#L524
+  Framework: PyTorch
+- Name: swin-base-patch4-window12-in1k-384x384-pre_upernet_8xb2-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 48.35
+      mIoU(ms+flip): 49.65
+  Config: configs/swin/swin-base-patch4-window12-in1k-384x384-pre_upernet_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Swin-B
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 8.52
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K_20210531_132020-05b22ea4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K_20210531_132020.log.json
+  Paper:
+    Title: 'Swin Transformer: Hierarchical Vision Transformer using Shifted Windows'
+    URL: https://arxiv.org/abs/2103.14030
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/swin.py#L524
+  Framework: PyTorch
+- Name: swin-base-patch4-window12-in22k-384x384-pre_upernet_8xb2-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 50.76
+      mIoU(ms+flip): 52.4
+  Config: configs/swin/swin-base-patch4-window12-in22k-384x384-pre_upernet_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Swin-B
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K_20210531_125459-429057bf.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K_20210531_125459.log.json
+  Paper:
+    Title: 'Swin Transformer: Hierarchical Vision Transformer using Shifted Windows'
+    URL: https://arxiv.org/abs/2103.14030
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/swin.py#L524
+  Framework: PyTorch
diff --git a/configs/swin/swin.yml b/configs/swin/swin.yml
deleted file mode 100644
index 783d839c8d..0000000000
--- a/configs/swin/swin.yml
+++ /dev/null
@@ -1,117 +0,0 @@
-Models:
-- Name: swin-tiny-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: Swin-T
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 47.48
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 5.02
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 44.41
-      mIoU(ms+flip): 45.79
-  Config: configs/swin/swin-tiny-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210531_112542-e380ad3e.pth
-- Name: swin-small-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: Swin-S
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 67.93
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.17
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 47.72
-      mIoU(ms+flip): 49.24
-  Config: configs/swin/swin-small-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192015-ee2fff1c.pth
-- Name: swin-base-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: Swin-B
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 79.05
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 7.61
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 47.99
-      mIoU(ms+flip): 49.57
-  Config: configs/swin/swin-base-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192340-593b0e13.pth
-- Name: swin-base-patch4-window7-in22k-pre_upernet_8xb2-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: Swin-B
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 50.13
-      mIoU(ms+flip): 51.9
-  Config: configs/swin/swin-base-patch4-window7-in22k-pre_upernet_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K_20210526_211650-762e2178.pth
-- Name: swin-base-patch4-window12-in1k-384x384-pre_upernet_8xb2-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: Swin-B
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 82.64
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 8.52
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 48.35
-      mIoU(ms+flip): 49.65
-  Config: configs/swin/swin-base-patch4-window12-in1k-384x384-pre_upernet_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K_20210531_132020-05b22ea4.pth
-- Name: swin-base-patch4-window12-in22k-384x384-pre_upernet_8xb2-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: Swin-B
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 50.76
-      mIoU(ms+flip): 52.4
-  Config: configs/swin/swin-base-patch4-window12-in22k-384x384-pre_upernet_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K_20210531_125459-429057bf.pth
diff --git a/configs/twins/README.md b/configs/twins/README.md
index 3e741802e6..306b65fac8 100644
--- a/configs/twins/README.md
+++ b/configs/twins/README.md
@@ -1,6 +1,6 @@
 # Twins
 
-[Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://arxiv.org/pdf/2104.13840.pdf)
+> [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://arxiv.org/pdf/2104.13840.pdf)
 
 ## Introduction
 
@@ -22,17 +22,6 @@ Very recently, a variety of vision transformer architectures for dense predictio
 <img src="https://user-images.githubusercontent.com/24582831/145021310-57826cf5-5e03-4c7c-9081-ffa744bdae27.png" width="80%"/>
 </div>
 
-## Citation
-
-```bibtex
-@article{chu2021twins,
-  title={Twins: Revisiting spatial attention design in vision transformers},
-  author={Chu, Xiangxiang and Tian, Zhi and Wang, Yuqing and Zhang, Bo and Ren, Haibing and Wei, Xiaolin and Xia, Huaxia and Shen, Chunhua},
-  journal={arXiv preprint arXiv:2104.13840},
-  year={2021}altgvt
-}
-```
-
 ## Usage
 
 We have provided pretrained models converted from [official repo](https://github.com/Meituan-AutoML/Twins).
@@ -55,22 +44,33 @@ python tools/model_converters/twins2mmseg.py ./alt_gvt_base.pth ./pretrained/alt
 
 ### ADE20K
 
-| Method              | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) | config                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                                                       |
-| ------------------- | -------- | --------- | ------- | -------- | -------------- | ----- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Twins-FPN           | PCPVT-S  | 512x512   | 80000   | 6.60     | 27.15          | 43.26 | 44.11         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_204132-41acd132.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_204132.log.json) |
-| Twins-UPerNet       | PCPVT-S  | 512x512   | 160000  | 9.67     | 14.24          | 46.04 | 46.92         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-s_uperhead_8xb4-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k_20211201_233537-8e99c07a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k_20211201_233537.log.json)         |
-| Twins-FPN           | PCPVT-B  | 512x512   | 80000   | 8.41     | 19.67          | 45.66 | 46.48         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141019-d396db72.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141019.log.json) |
-| Twins-UPerNet (8x2) | PCPVT-B  | 512x512   | 160000  | 6.46     | 12.04          | 47.91 | 48.64         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-b_uperhead_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k_20211130_141020-02094ea5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k_20211130_141020.log.json)         |
-| Twins-FPN           | PCPVT-L  | 512x512   | 80000   | 10.78    | 14.32          | 45.94 | 46.70         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_105226-bc6d61dc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_105226.log.json) |
-| Twins-UPerNet (8x2) | PCPVT-L  | 512x512   | 160000  | 7.82     | 10.70          | 49.35 | 50.08         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k_20211201_075053-c6095c07.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k_20211201_075053.log.json)         |
-| Twins-FPN           | SVT-S    | 512x512   | 80000   | 5.80     | 29.79          | 44.47 | 45.42         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_svt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141006-0a0d3317.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141006.log.json)         |
-| Twins-UPerNet (8x2) | SVT-S    | 512x512   | 160000  | 4.93     | 15.09          | 46.08 | 46.96         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_svt-s_uperhead_8xb2-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_uperhead_8x2_512x512_160k_ade20k/twins_svt-s_uperhead_8x2_512x512_160k_ade20k_20211130_141005-e48a2d94.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_uperhead_8x2_512x512_160k_ade20k/twins_svt-s_uperhead_8x2_512x512_160k_ade20k_20211130_141005.log.json)                 |
-| Twins-FPN           | SVT-B    | 512x512   | 80000   | 8.75     | 21.10          | 46.77 | 47.47         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_svt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_113849-88b2907c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_113849.log.json)         |
-| Twins-UPerNet (8x2) | SVT-B    | 512x512   | 160000  | 6.77     | 12.66          | 48.04 | 48.87         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_svt-b_uperhead_8xb2-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_uperhead_8x2_512x512_160k_ade20k/twins_svt-b_uperhead_8x2_512x512_160k_ade20k_20211202_040826-0943a1f1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_uperhead_8x2_512x512_160k_ade20k/twins_svt-b_uperhead_8x2_512x512_160k_ade20k_20211202_040826.log.json)                 |
-| Twins-FPN           | SVT-L    | 512x512   | 80000   | 11.20    | 17.80          | 46.55 | 47.74         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_svt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141005-1d59bee2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141005.log.json)         |
-| Twins-UPerNet (8x2) | SVT-L    | 512x512   | 160000  | 8.41     | 10.73          | 49.65 | 50.63         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_uperhead_8x2_512x512_160k_ade20k/twins_svt-l_uperhead_8x2_512x512_160k_ade20k_20211130_141005-3e2cae61.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_uperhead_8x2_512x512_160k_ade20k/twins_svt-l_uperhead_8x2_512x512_160k_ade20k_20211130_141005.log.json)                 |
+| Method  | Backbone            | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                                                       |
+| ------- | ------------------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FPN     | Twins-PCPVT-S       | 512x512   | 80000   | 6.60     | 27.15          | V100   | 43.26 | 44.11         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_204132-41acd132.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_204132.log.json) |
+| UPerNet | Twins-PCPVT-S       | 512x512   | 160000  | 9.67     | 14.24          | V100   | 46.04 | 46.92         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-s_uperhead_8xb4-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k_20211201_233537-8e99c07a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k_20211201_233537.log.json)         |
+| FPN     | Twins-PCPVT-B       | 512x512   | 80000   | 8.41     | 19.67          | V100   | 45.66 | 46.48         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141019-d396db72.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141019.log.json) |
+| UPerNet | Twins-PCPVT-B (8x2) | 512x512   | 160000  | 6.46     | 12.04          | V100   | 47.91 | 48.64         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-b_uperhead_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k_20211130_141020-02094ea5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k_20211130_141020.log.json)         |
+| FPN     | Twins-PCPVT-L       | 512x512   | 80000   | 10.78    | 14.32          | V100   | 45.94 | 46.70         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_105226-bc6d61dc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_105226.log.json) |
+| UPerNet | Twins-PCPVT-L (8x2) | 512x512   | 160000  | 7.82     | 10.70          | V100   | 49.35 | 50.08         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k_20211201_075053-c6095c07.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k_20211201_075053.log.json)         |
+| FPN     | Twins-SVT-S         | 512x512   | 80000   | 5.80     | 29.79          | V100   | 44.47 | 45.42         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_svt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141006-0a0d3317.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141006.log.json)         |
+| UPerNet | SVT-S  (8x2)        | 512x512   | 160000  | 4.93     | 15.09          | V100   | 46.08 | 46.96         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_svt-s_uperhead_8xb2-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_uperhead_8x2_512x512_160k_ade20k/twins_svt-s_uperhead_8x2_512x512_160k_ade20k_20211130_141005-e48a2d94.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_uperhead_8x2_512x512_160k_ade20k/twins_svt-s_uperhead_8x2_512x512_160k_ade20k_20211130_141005.log.json)                 |
+| FPN     | Twins-SVT-B         | 512x512   | 80000   | 8.75     | 21.10          | V100   | 46.77 | 47.47         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_svt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_113849-88b2907c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_113849.log.json)         |
+| UPerNet | Twins-SVT-B  (8x2)  | 512x512   | 160000  | 6.77     | 12.66          | V100   | 48.04 | 48.87         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_svt-b_uperhead_8xb2-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_uperhead_8x2_512x512_160k_ade20k/twins_svt-b_uperhead_8x2_512x512_160k_ade20k_20211202_040826-0943a1f1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_uperhead_8x2_512x512_160k_ade20k/twins_svt-b_uperhead_8x2_512x512_160k_ade20k_20211202_040826.log.json)                 |
+| FPN     | Twins-SVT-L         | 512x512   | 80000   | 11.20    | 17.80          | V100   | 46.55 | 47.74         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_svt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141005-1d59bee2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141005.log.json)         |
+| UPerNet | Twins-SVT-L  (8x2)  | 512x512   | 160000  | 8.41     | 10.73          | V100   | 49.65 | 50.63         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_uperhead_8x2_512x512_160k_ade20k/twins_svt-l_uperhead_8x2_512x512_160k_ade20k_20211130_141005-3e2cae61.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_uperhead_8x2_512x512_160k_ade20k/twins_svt-l_uperhead_8x2_512x512_160k_ade20k_20211130_141005.log.json)                 |
 
 Note:
 
 - `8x2` means 8 GPUs with 2 samples per GPU in training. Default setting of Twins on ADE20K is 8 GPUs with 4 samples per GPU in training.
 - `UPerNet` and `FPN` are decoder heads utilized in corresponding Twins model, which is `UPerHead` and `FPNHead`, respectively. Specifically, models in [official repo](https://github.com/Meituan-AutoML/Twins) all use `UPerHead`.
+
+## Citation
+
+```bibtex
+@article{chu2021twins,
+  title={Twins: Revisiting spatial attention design in vision transformers},
+  author={Chu, Xiangxiang and Tian, Zhi and Wang, Yuqing and Zhang, Bo and Ren, Haibing and Wei, Xiaolin and Xia, Huaxia and Shen, Chunhua},
+  journal={arXiv preprint arXiv:2104.13840},
+  year={2021}altgvt
+}
+```
diff --git a/configs/twins/metafile.yaml b/configs/twins/metafile.yaml
new file mode 100644
index 0000000000..0de78d9d2e
--- /dev/null
+++ b/configs/twins/metafile.yaml
@@ -0,0 +1,289 @@
+Models:
+- Name: twins_pcpvt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512
+  In Collection: FPN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.26
+      mIoU(ms+flip): 44.11
+  Config: configs/twins/twins_pcpvt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 32
+    Architecture:
+    - Twins-PCPVT-S
+    - FPN
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 6.6
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_204132-41acd132.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_204132.log.json
+  Paper:
+    Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
+    URL: https://arxiv.org/pdf/2104.13840.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
+  Framework: PyTorch
+- Name: twins_pcpvt-s_uperhead_8xb4-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 46.04
+      mIoU(ms+flip): 46.92
+  Config: configs/twins/twins_pcpvt-s_uperhead_8xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 32
+    Architecture:
+    - Twins-PCPVT-S
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 9.67
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k_20211201_233537-8e99c07a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k_20211201_233537.log.json
+  Paper:
+    Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
+    URL: https://arxiv.org/pdf/2104.13840.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
+  Framework: PyTorch
+- Name: twins_pcpvt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512
+  In Collection: FPN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.66
+      mIoU(ms+flip): 46.48
+  Config: configs/twins/twins_pcpvt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 32
+    Architecture:
+    - Twins-PCPVT-B
+    - FPN
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 8.41
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141019-d396db72.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141019.log.json
+  Paper:
+    Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
+    URL: https://arxiv.org/pdf/2104.13840.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
+  Framework: PyTorch
+- Name: twins_pcpvt-b_uperhead_8xb2-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 47.91
+      mIoU(ms+flip): 48.64
+  Config: configs/twins/twins_pcpvt-b_uperhead_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Twins-PCPVT-B
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 6.46
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k_20211130_141020-02094ea5.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k_20211130_141020.log.json
+  Paper:
+    Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
+    URL: https://arxiv.org/pdf/2104.13840.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
+  Framework: PyTorch
+- Name: twins_pcpvt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512
+  In Collection: FPN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.94
+      mIoU(ms+flip): 46.7
+  Config: configs/twins/twins_pcpvt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 32
+    Architecture:
+    - Twins-PCPVT-L
+    - FPN
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 10.78
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_105226-bc6d61dc.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_105226.log.json
+  Paper:
+    Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
+    URL: https://arxiv.org/pdf/2104.13840.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
+  Framework: PyTorch
+- Name: twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 49.35
+      mIoU(ms+flip): 50.08
+  Config: configs/twins/twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Twins-PCPVT-L
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 7.82
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k_20211201_075053-c6095c07.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k_20211201_075053.log.json
+  Paper:
+    Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
+    URL: https://arxiv.org/pdf/2104.13840.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
+  Framework: PyTorch
+- Name: twins_svt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512
+  In Collection: FPN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 44.47
+      mIoU(ms+flip): 45.42
+  Config: configs/twins/twins_svt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 32
+    Architecture:
+    - Twins-SVT-S
+    - FPN
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 5.8
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141006-0a0d3317.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141006.log.json
+  Paper:
+    Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
+    URL: https://arxiv.org/pdf/2104.13840.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
+  Framework: PyTorch
+- Name: twins_svt-s_uperhead_8xb2-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 46.08
+      mIoU(ms+flip): 46.96
+  Config: configs/twins/twins_svt-s_uperhead_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - SVT-S
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 4.93
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_uperhead_8x2_512x512_160k_ade20k/twins_svt-s_uperhead_8x2_512x512_160k_ade20k_20211130_141005-e48a2d94.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_uperhead_8x2_512x512_160k_ade20k/twins_svt-s_uperhead_8x2_512x512_160k_ade20k_20211130_141005.log.json
+  Paper:
+    Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
+    URL: https://arxiv.org/pdf/2104.13840.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
+  Framework: PyTorch
+- Name: twins_svt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512
+  In Collection: FPN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 46.77
+      mIoU(ms+flip): 47.47
+  Config: configs/twins/twins_svt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 32
+    Architecture:
+    - Twins-SVT-B
+    - FPN
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 8.75
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_113849-88b2907c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_113849.log.json
+  Paper:
+    Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
+    URL: https://arxiv.org/pdf/2104.13840.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
+  Framework: PyTorch
+- Name: twins_svt-b_uperhead_8xb2-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 48.04
+      mIoU(ms+flip): 48.87
+  Config: configs/twins/twins_svt-b_uperhead_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Twins-SVT-B
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 6.77
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_uperhead_8x2_512x512_160k_ade20k/twins_svt-b_uperhead_8x2_512x512_160k_ade20k_20211202_040826-0943a1f1.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_uperhead_8x2_512x512_160k_ade20k/twins_svt-b_uperhead_8x2_512x512_160k_ade20k_20211202_040826.log.json
+  Paper:
+    Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
+    URL: https://arxiv.org/pdf/2104.13840.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
+  Framework: PyTorch
+- Name: twins_svt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512
+  In Collection: FPN
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 46.55
+      mIoU(ms+flip): 47.74
+  Config: configs/twins/twins_svt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 32
+    Architecture:
+    - Twins-SVT-L
+    - FPN
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 11.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141005-1d59bee2.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141005.log.json
+  Paper:
+    Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
+    URL: https://arxiv.org/pdf/2104.13840.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
+  Framework: PyTorch
+- Name: twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 49.65
+      mIoU(ms+flip): 50.63
+  Config: configs/twins/twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - Twins-SVT-L
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 8.41
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_uperhead_8x2_512x512_160k_ade20k/twins_svt-l_uperhead_8x2_512x512_160k_ade20k_20211130_141005-3e2cae61.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_uperhead_8x2_512x512_160k_ade20k/twins_svt-l_uperhead_8x2_512x512_160k_ade20k_20211130_141005.log.json
+  Paper:
+    Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
+    URL: https://arxiv.org/pdf/2104.13840.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
+  Framework: PyTorch
diff --git a/configs/twins/twins.yml b/configs/twins/twins.yml
deleted file mode 100644
index 48d25c682f..0000000000
--- a/configs/twins/twins.yml
+++ /dev/null
@@ -1,265 +0,0 @@
-Models:
-- Name: twins_pcpvt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512
-  In Collection: FPN
-  Metadata:
-    backbone: PCPVT-S
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 36.83
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.6
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.26
-      mIoU(ms+flip): 44.11
-  Config: configs/twins/twins_pcpvt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_204132-41acd132.pth
-- Name: twins_pcpvt-s_uperhead_8xb4-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: PCPVT-S
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 70.22
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.67
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 46.04
-      mIoU(ms+flip): 46.92
-  Config: configs/twins/twins_pcpvt-s_uperhead_8xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k_20211201_233537-8e99c07a.pth
-- Name: twins_pcpvt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512
-  In Collection: FPN
-  Metadata:
-    backbone: PCPVT-B
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 50.84
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 8.41
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.66
-      mIoU(ms+flip): 46.48
-  Config: configs/twins/twins_pcpvt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141019-d396db72.pth
-- Name: twins_pcpvt-b_uperhead_8xb2-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: PCPVT-B
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 83.06
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.46
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 47.91
-      mIoU(ms+flip): 48.64
-  Config: configs/twins/twins_pcpvt-b_uperhead_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k_20211130_141020-02094ea5.pth
-- Name: twins_pcpvt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512
-  In Collection: FPN
-  Metadata:
-    backbone: PCPVT-L
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 69.83
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 10.78
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.94
-      mIoU(ms+flip): 46.7
-  Config: configs/twins/twins_pcpvt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_105226-bc6d61dc.pth
-- Name: twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: PCPVT-L
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 93.46
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 7.82
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 49.35
-      mIoU(ms+flip): 50.08
-  Config: configs/twins/twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k_20211201_075053-c6095c07.pth
-- Name: twins_svt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512
-  In Collection: FPN
-  Metadata:
-    backbone: SVT-S
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 33.57
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 5.8
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 44.47
-      mIoU(ms+flip): 45.42
-  Config: configs/twins/twins_svt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141006-0a0d3317.pth
-- Name: twins_svt-s_uperhead_8xb2-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: SVT-S
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 66.27
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 4.93
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 46.08
-      mIoU(ms+flip): 46.96
-  Config: configs/twins/twins_svt-s_uperhead_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_uperhead_8x2_512x512_160k_ade20k/twins_svt-s_uperhead_8x2_512x512_160k_ade20k_20211130_141005-e48a2d94.pth
-- Name: twins_svt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512
-  In Collection: FPN
-  Metadata:
-    backbone: SVT-B
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 47.39
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 8.75
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 46.77
-      mIoU(ms+flip): 47.47
-  Config: configs/twins/twins_svt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_113849-88b2907c.pth
-- Name: twins_svt-b_uperhead_8xb2-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: SVT-B
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 78.99
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.77
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 48.04
-      mIoU(ms+flip): 48.87
-  Config: configs/twins/twins_svt-b_uperhead_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_uperhead_8x2_512x512_160k_ade20k/twins_svt-b_uperhead_8x2_512x512_160k_ade20k_20211202_040826-0943a1f1.pth
-- Name: twins_svt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512
-  In Collection: FPN
-  Metadata:
-    backbone: SVT-L
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 56.18
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 11.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 46.55
-      mIoU(ms+flip): 47.74
-  Config: configs/twins/twins_svt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141005-1d59bee2.pth
-- Name: twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: SVT-L
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 93.2
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 8.41
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 49.65
-      mIoU(ms+flip): 50.63
-  Config: configs/twins/twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_uperhead_8x2_512x512_160k_ade20k/twins_svt-l_uperhead_8x2_512x512_160k_ade20k_20211130_141005-3e2cae61.pth
diff --git a/configs/unet/README.md b/configs/unet/README.md
index f3dc261c22..e42cd0f91e 100644
--- a/configs/unet/README.md
+++ b/configs/unet/README.md
@@ -1,6 +1,6 @@
 # UNet
 
-[U-Net: Convolutional Networks for Biomedical Image Segmentation](https://arxiv.org/abs/1505.04597)
+> [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://arxiv.org/abs/1505.04597)
 
 ## Introduction
 
@@ -22,71 +22,71 @@ There is large consent that successful training of deep networks requires many t
 <img src="https://user-images.githubusercontent.com/24582831/142902977-20fe689d-a147-4d92-9690-dbfde8b68dbe.png" width="70%"/>
 </div>
 
-## Citation
-
-```bibtex
-@inproceedings{ronneberger2015u,
-  title={U-net: Convolutional networks for biomedical image segmentation},
-  author={Ronneberger, Olaf and Fischer, Philipp and Brox, Thomas},
-  booktitle={International Conference on Medical image computing and computer-assisted intervention},
-  pages={234--241},
-  year={2015},
-  organization={Springer}
-}
-```
-
 ## Results and models
 
 ### Cityscapes
 
-| Method     | Backbone    | Loss          | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                                     |
-| ---------- | ----------- | ------------- | --------- | ------: | -------- | -------------- | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UNet + FCN | UNet-S5-D16 | Cross Entropy | 512x1024  |  160000 | 17.91    | 3.05           | 69.10 |         71.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes_20211210_145204-6860854e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes_20211210_145204.log.json) |
+| Method     | Backbone    | Loss          | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                                     |
+| ---------- | ----------- | ------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UNet + FCN | UNet-S5-D16 | Cross Entropy | 512x1024  |  160000 | 17.91    | 3.05           | V100   | 69.10 |         71.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes_20211210_145204-6860854e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes_20211210_145204.log.json) |
 
 ### DRIVE
 
-| Method           | Backbone    | Loss                 | Image Size | Crop Size | Stride | Lr schd | Mem (GB) | Inf time (fps) | mDice |  Dice | config                                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                                                                         |
-| ---------------- | ----------- | -------------------- | ---------- | --------- | -----: | ------- | -------- | -------------: | ----: | ----: | ---------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 584x565    | 64x64     |  42x42 | 40000   | 0.680    |              - | 88.38 | 78.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-40k_drive-64x64.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_64x64_40k_drive/fcn_unet_s5-d16_64x64_40k_drive_20201223_191051-5daf6d3b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_64x64_40k_drive/unet_s5-d16_64x64_40k_drive-20201223_191051.log.json)                                                                                                 |
-| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 584x565    | 64x64     |  42x42 | 40000   | 0.582    |              - | 88.71 | 79.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201820-785de5c2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201820.log.json)                         |
-| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 584x565    | 64x64     |  42x42 | 40000   | 0.599    |              - | 88.35 | 78.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-40k_drive-64x64.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_64x64_40k_drive/pspnet_unet_s5-d16_64x64_40k_drive_20201227_181818-aac73387.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_64x64_40k_drive/pspnet_unet_s5-d16_64x64_40k_drive-20201227_181818.log.json)                                                                             |
-| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 584x565    | 64x64     |  42x42 | 40000   | 0.585    |              - | 88.76 | 79.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201821-22b3e3ba.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201821.log.json)             |
-| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 584x565    | 64x64     |  42x42 | 40000   | 0.596    |              - | 88.38 | 78.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_drive-64x64.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_64x64_40k_drive/deeplabv3_unet_s5-d16_64x64_40k_drive_20201226_094047-0671ff20.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_64x64_40k_drive/deeplabv3_unet_s5-d16_64x64_40k_drive-20201226_094047.log.json)                                                                 |
-| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 584x565    | 64x64     |  42x42 | 40000   | 0.582    |              - | 88.84 | 79.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201825-6bf0efd7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201825.log.json) |
+| Method           | Backbone    | Loss                 | Image Size | Crop Size | Stride | Lr schd | Mem (GB) | Inf time (fps) | Device | mDice |  Dice | config                                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                                                                         |
+| ---------------- | ----------- | -------------------- | ---------- | --------- | -----: | ------- | -------- | -------------: | ------ | ----: | ----: | ---------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 584x565    | 64x64     |  42x42 | 40000   | 0.680    |              - | V100   | 88.38 | 78.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-40k_drive-64x64.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_64x64_40k_drive/fcn_unet_s5-d16_64x64_40k_drive_20201223_191051-5daf6d3b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_64x64_40k_drive/unet_s5-d16_64x64_40k_drive-20201223_191051.log.json)                                                                                                 |
+| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 584x565    | 64x64     |  42x42 | 40000   | 0.582    |              - | V100   | 88.71 | 79.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201820-785de5c2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201820.log.json)                         |
+| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 584x565    | 64x64     |  42x42 | 40000   | 0.599    |              - | V100   | 88.35 | 78.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-40k_drive-64x64.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_64x64_40k_drive/pspnet_unet_s5-d16_64x64_40k_drive_20201227_181818-aac73387.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_64x64_40k_drive/pspnet_unet_s5-d16_64x64_40k_drive-20201227_181818.log.json)                                                                             |
+| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 584x565    | 64x64     |  42x42 | 40000   | 0.585    |              - | V100   | 88.76 | 79.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201821-22b3e3ba.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201821.log.json)             |
+| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 584x565    | 64x64     |  42x42 | 40000   | 0.596    |              - | V100   | 88.38 | 78.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_drive-64x64.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_64x64_40k_drive/deeplabv3_unet_s5-d16_64x64_40k_drive_20201226_094047-0671ff20.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_64x64_40k_drive/deeplabv3_unet_s5-d16_64x64_40k_drive-20201226_094047.log.json)                                                                 |
+| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 584x565    | 64x64     |  42x42 | 40000   | 0.582    |              - | V100   | 88.84 | 79.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201825-6bf0efd7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201825.log.json) |
 
 ### STARE
 
-| Method           | Backbone    | Loss                 | Image Size | Crop Size | Stride | Lr schd | Mem (GB) | Inf time (fps) | mDice |  Dice | config                                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                                                                                 |
-| ---------------- | ----------- | -------------------- | ---------- | --------- | -----: | ------- | -------- | -------------: | ----: | ----: | ------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 605x700    | 128x128   |  85x85 | 40000   | 0.968    |              - | 89.78 | 81.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-40k_stare-128x128.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_stare/fcn_unet_s5-d16_128x128_40k_stare_20201223_191051-7d77e78b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_stare/unet_s5-d16_128x128_40k_stare-20201223_191051.log.json)                                                                                                 |
-| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 605x700    | 128x128   |  85x85 | 40000   | 0.986    |              - | 90.65 | 82.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201821-f75705a9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201821.log.json)                         |
-| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 605x700    | 128x128   |  85x85 | 40000   | 0.982    |              - | 89.89 | 81.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-40k_stare-128x128.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_stare/pspnet_unet_s5-d16_128x128_40k_stare_20201227_181818-3c2923c4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_stare/pspnet_unet_s5-d16_128x128_40k_stare-20201227_181818.log.json)                                                                             |
-| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 605x700    | 128x128   |  85x85 | 40000   | 1.028    |              - | 90.72 | 82.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201823-f1063ef7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201823.log.json)             |
-| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 605x700    | 128x128   |  85x85 | 40000   | 0.999    |              - | 89.73 | 80.93 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_stare-128x128.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_stare/deeplabv3_unet_s5-d16_128x128_40k_stare_20201226_094047-93dcb93c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_stare/deeplabv3_unet_s5-d16_128x128_40k_stare-20201226_094047.log.json)                                                                 |
-| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 605x700    | 128x128   |  85x85 | 40000   | 1.010    |              - | 90.65 | 82.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201825-21db614c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201825.log.json) |
+| Method           | Backbone    | Loss                 | Image Size | Crop Size | Stride | Lr schd | Mem (GB) | Inf time (fps) | Device | mDice |  Dice | config                                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                                                                                 |
+| ---------------- | ----------- | -------------------- | ---------- | --------- | -----: | ------- | -------- | -------------: | ------ | ----: | ----: | ------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 605x700    | 128x128   |  85x85 | 40000   | 0.968    |              - | V100   | 89.78 | 81.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-40k_stare-128x128.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_stare/fcn_unet_s5-d16_128x128_40k_stare_20201223_191051-7d77e78b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_stare/unet_s5-d16_128x128_40k_stare-20201223_191051.log.json)                                                                                                 |
+| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 605x700    | 128x128   |  85x85 | 40000   | 0.986    |              - | V100   | 90.65 | 82.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201821-f75705a9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201821.log.json)                         |
+| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 605x700    | 128x128   |  85x85 | 40000   | 0.982    |              - | V100   | 89.89 | 81.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-40k_stare-128x128.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_stare/pspnet_unet_s5-d16_128x128_40k_stare_20201227_181818-3c2923c4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_stare/pspnet_unet_s5-d16_128x128_40k_stare-20201227_181818.log.json)                                                                             |
+| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 605x700    | 128x128   |  85x85 | 40000   | 1.028    |              - | V100   | 90.72 | 82.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201823-f1063ef7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201823.log.json)             |
+| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 605x700    | 128x128   |  85x85 | 40000   | 0.999    |              - | V100   | 89.73 | 80.93 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_stare-128x128.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_stare/deeplabv3_unet_s5-d16_128x128_40k_stare_20201226_094047-93dcb93c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_stare/deeplabv3_unet_s5-d16_128x128_40k_stare-20201226_094047.log.json)                                                                 |
+| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 605x700    | 128x128   |  85x85 | 40000   | 1.010    |              - | V100   | 90.65 | 82.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201825-21db614c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201825.log.json) |
 
 ### CHASE_DB1
 
-| Method           | Backbone    | Loss                 | Image Size | Crop Size | Stride | Lr schd | Mem (GB) | Inf time (fps) | mDice |  Dice | config                                                                                                                                               | download                                                                                                                                                                                                                                                                                                                                                                                                                                 |
-| ---------------- | ----------- | -------------------- | ---------- | --------- | -----: | ------- | -------- | -------------: | ----: | ----: | ---------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 960x999    | 128x128   |  85x85 | 40000   | 0.968    |              - | 89.46 | 80.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-40k_chase-db1-128x128.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_chase_db1/fcn_unet_s5-d16_128x128_40k_chase_db1_20201223_191051-11543527.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_chase_db1/unet_s5-d16_128x128_40k_chase_db1-20201223_191051.log.json)                                                                                                 |
-| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 960x999    | 128x128   |  85x85 | 40000   | 0.986    |              - | 89.52 | 80.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201821-1c4eb7cf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201821.log.json)                         |
-| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 960x999    | 128x128   |  85x85 | 40000   | 0.982    |              - | 89.52 | 80.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-40k_chase-db1-128x128.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1/pspnet_unet_s5-d16_128x128_40k_chase_db1_20201227_181818-68d4e609.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1/pspnet_unet_s5-d16_128x128_40k_chase_db1-20201227_181818.log.json)                                                                             |
-| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 960x999    | 128x128   |  85x85 | 40000   | 1.028    |              - | 89.45 | 80.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201823-c0802c4d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201823.log.json)             |
-| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 960x999    | 128x128   |  85x85 | 40000   | 0.999    |              - | 89.57 | 80.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet_s5-d16_deeplabv3_4xb4-40k_chase-db1-128x128.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1/deeplabv3_unet_s5-d16_128x128_40k_chase_db1_20201226_094047-4c5aefa3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1/deeplabv3_unet_s5-d16_128x128_40k_chase_db1-20201226_094047.log.json)                                                                 |
-| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 960x999    | 128x128   |  85x85 | 40000   | 1.010    |              - | 89.49 | 80.37 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201825-4ef29df5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201825.log.json) |
+| Method           | Backbone    | Loss                 | Image Size | Crop Size | Stride | Lr schd | Mem (GB) | Inf time (fps) | Device | mDice |  Dice | config                                                                                                                                               | download                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+| ---------------- | ----------- | -------------------- | ---------- | --------- | -----: | ------- | -------- | -------------: | ------ | ----: | ----: | ---------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 960x999    | 128x128   |  85x85 | 40000   | 0.968    |              - | V100   | 89.46 | 80.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-40k_chase-db1-128x128.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_chase_db1/fcn_unet_s5-d16_128x128_40k_chase_db1_20201223_191051-11543527.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_chase_db1/unet_s5-d16_128x128_40k_chase_db1-20201223_191051.log.json)                                                                                                 |
+| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 960x999    | 128x128   |  85x85 | 40000   | 0.986    |              - | V100   | 89.52 | 80.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201821-1c4eb7cf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201821.log.json)                         |
+| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 960x999    | 128x128   |  85x85 | 40000   | 0.982    |              - | V100   | 89.52 | 80.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-40k_chase-db1-128x128.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1/pspnet_unet_s5-d16_128x128_40k_chase_db1_20201227_181818-68d4e609.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1/pspnet_unet_s5-d16_128x128_40k_chase_db1-20201227_181818.log.json)                                                                             |
+| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 960x999    | 128x128   |  85x85 | 40000   | 1.028    |              - | V100   | 89.45 | 80.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201823-c0802c4d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201823.log.json)             |
+| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 960x999    | 128x128   |  85x85 | 40000   | 0.999    |              - | V100   | 89.57 | 80.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet_s5-d16_deeplabv3_4xb4-40k_chase-db1-128x128.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1/deeplabv3_unet_s5-d16_128x128_40k_chase_db1_20201226_094047-4c5aefa3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1/deeplabv3_unet_s5-d16_128x128_40k_chase_db1-20201226_094047.log.json)                                                                 |
+| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 960x999    | 128x128   |  85x85 | 40000   | 1.010    |              - | V100   | 89.49 | 80.37 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201825-4ef29df5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201825.log.json) |
 
 ### HRF
 
-| Method           | Backbone    | Loss                 | Image Size | Crop Size |  Stride | Lr schd | Mem (GB) | Inf time (fps) | mDice |  Dice | config                                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                                                                         |
-| ---------------- | ----------- | -------------------- | ---------- | --------- | ------: | ------- | -------- | -------------: | ----: | ----: | ---------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 2336x3504  | 256x256   | 170x170 | 40000   | 2.525    |              - | 88.92 | 79.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-40k_hrf-256x256.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_256x256_40k_hrf/fcn_unet_s5-d16_256x256_40k_hrf_20201223_173724-d89cf1ed.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_256x256_40k_hrf/unet_s5-d16_256x256_40k_hrf-20201223_173724.log.json)                                                                                                 |
-| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 2336x3504  | 256x256   | 170x170 | 40000   | 2.623    |              - | 89.64 | 80.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201821-c314da8a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201821.log.json)                         |
-| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 2336x3504  | 256x256   | 170x170 | 40000   | 2.588    |              - | 89.24 | 80.07 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-40k_hrf-256x256.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_256x256_40k_hrf/pspnet_unet_s5-d16_256x256_40k_hrf_20201227_181818-fdb7e29b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_256x256_40k_hrf/pspnet_unet_s5-d16_256x256_40k_hrf-20201227_181818.log.json)                                                                             |
-| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 2336x3504  | 256x256   | 170x170 | 40000   | 2.798    |              - | 89.69 | 80.96 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201823-53d492fa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201823.log.json)             |
-| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 2336x3504  | 256x256   | 170x170 | 40000   | 2.604    |              - | 89.32 | 80.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_hrf-256x256.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf/deeplabv3_unet_s5-d16_256x256_40k_hrf_20201226_094047-3a1fdf85.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf/deeplabv3_unet_s5-d16_256x256_40k_hrf-20201226_094047.log.json)                                                                 |
-| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 2336x3504  | 256x256   | 170x170 | 40000   | 2.607    |              - | 89.56 | 80.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_202032-59daf7a4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_202032.log.json) |
+| Method           | Backbone    | Loss                 | Image Size | Crop Size |  Stride | Lr schd | Mem (GB) | Inf time (fps) | Device | mDice |  Dice | config                                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                                                                         |
+| ---------------- | ----------- | -------------------- | ---------- | --------- | ------: | ------- | -------- | -------------: | ------ | ----: | ----: | ---------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 2336x3504  | 256x256   | 170x170 | 40000   | 2.525    |              - | V100   | 88.92 | 79.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-40k_hrf-256x256.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_256x256_40k_hrf/fcn_unet_s5-d16_256x256_40k_hrf_20201223_173724-d89cf1ed.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_256x256_40k_hrf/unet_s5-d16_256x256_40k_hrf-20201223_173724.log.json)                                                                                                 |
+| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 2336x3504  | 256x256   | 170x170 | 40000   | 2.623    |              - | V100   | 89.64 | 80.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201821-c314da8a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201821.log.json)                         |
+| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 2336x3504  | 256x256   | 170x170 | 40000   | 2.588    |              - | V100   | 89.24 | 80.07 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-40k_hrf-256x256.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_256x256_40k_hrf/pspnet_unet_s5-d16_256x256_40k_hrf_20201227_181818-fdb7e29b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_256x256_40k_hrf/pspnet_unet_s5-d16_256x256_40k_hrf-20201227_181818.log.json)                                                                             |
+| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 2336x3504  | 256x256   | 170x170 | 40000   | 2.798    |              - | V100   | 89.69 | 80.96 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201823-53d492fa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201823.log.json)             |
+| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 2336x3504  | 256x256   | 170x170 | 40000   | 2.604    |              - | V100   | 89.32 | 80.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_hrf-256x256.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf/deeplabv3_unet_s5-d16_256x256_40k_hrf_20201226_094047-3a1fdf85.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf/deeplabv3_unet_s5-d16_256x256_40k_hrf-20201226_094047.log.json)                                                                 |
+| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 2336x3504  | 256x256   | 170x170 | 40000   | 2.607    |              - | V100   | 89.56 | 80.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_202032-59daf7a4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_202032.log.json) |
 
 Note:
 
 - In  `DRIVE`, `STARE`, `CHASE_DB1`, and `HRF` dataset, `mDice` is mean dice of background and vessel, while `Dice` is dice metric of vessel(foreground) only.
+
+## Citation
+
+```bibtex
+@inproceedings{ronneberger2015u,
+  title={U-net: Convolutional networks for biomedical image segmentation},
+  author={Ronneberger, Olaf and Fischer, Philipp and Brox, Thomas},
+  booktitle={International Conference on Medical image computing and computer-assisted intervention},
+  pages={234--241},
+  year={2015},
+  organization={Springer}
+}
+```
diff --git a/configs/unet/metafile.yaml b/configs/unet/metafile.yaml
new file mode 100644
index 0000000000..1eafbc6d08
--- /dev/null
+++ b/configs/unet/metafile.yaml
@@ -0,0 +1,642 @@
+Collections:
+- Name: UNet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - DRIVE
+    - STARE
+    - CHASE_DB1
+    - HRF
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  README: configs/unet/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: unet-s5-d16_fcn_4xb4-160k_cityscapes-512x1024
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 69.1
+      mIoU(ms+flip): 71.05
+  Config: configs/unet/unet-s5-d16_fcn_4xb4-160k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 17.91
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes_20211210_145204-6860854e.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes_20211210_145204.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_fcn_4xb4-40k_drive-64x64
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: DRIVE
+    Metrics:
+      mDice: 88.38
+      Dice: 78.67
+  Config: configs/unet/unet-s5-d16_fcn_4xb4-40k_drive-64x64.py
+  Metadata:
+    Training Data: DRIVE
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 0.68
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_64x64_40k_drive/fcn_unet_s5-d16_64x64_40k_drive_20201223_191051-5daf6d3b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_64x64_40k_drive/unet_s5-d16_64x64_40k_drive-20201223_191051.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_drive-64x64
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: DRIVE
+    Metrics:
+      mDice: 88.71
+      Dice: 79.32
+  Config: configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py
+  Metadata:
+    Training Data: DRIVE
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 0.582
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201820-785de5c2.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201820.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_pspnet_4xb4-40k_drive-64x64
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: DRIVE
+    Metrics:
+      mDice: 88.35
+      Dice: 78.62
+  Config: configs/unet/unet-s5-d16_pspnet_4xb4-40k_drive-64x64.py
+  Metadata:
+    Training Data: DRIVE
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 0.599
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_64x64_40k_drive/pspnet_unet_s5-d16_64x64_40k_drive_20201227_181818-aac73387.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_64x64_40k_drive/pspnet_unet_s5-d16_64x64_40k_drive-20201227_181818.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_drive-64x64
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: DRIVE
+    Metrics:
+      mDice: 88.76
+      Dice: 79.42
+  Config: configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py
+  Metadata:
+    Training Data: DRIVE
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 0.585
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201821-22b3e3ba.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201821.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_deeplabv3_4xb4-40k_drive-64x64
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: DRIVE
+    Metrics:
+      mDice: 88.38
+      Dice: 78.69
+  Config: configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_drive-64x64.py
+  Metadata:
+    Training Data: DRIVE
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 0.596
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_64x64_40k_drive/deeplabv3_unet_s5-d16_64x64_40k_drive_20201226_094047-0671ff20.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_64x64_40k_drive/deeplabv3_unet_s5-d16_64x64_40k_drive-20201226_094047.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_drive-64x64
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: DRIVE
+    Metrics:
+      mDice: 88.84
+      Dice: 79.56
+  Config: configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py
+  Metadata:
+    Training Data: DRIVE
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 0.582
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201825-6bf0efd7.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201825.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_fcn_4xb4-40k_stare-128x128
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: STARE
+    Metrics:
+      mDice: 89.78
+      Dice: 81.02
+  Config: configs/unet/unet-s5-d16_fcn_4xb4-40k_stare-128x128.py
+  Metadata:
+    Training Data: STARE
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 0.968
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_stare/fcn_unet_s5-d16_128x128_40k_stare_20201223_191051-7d77e78b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_stare/unet_s5-d16_128x128_40k_stare-20201223_191051.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_stare-128x128
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: STARE
+    Metrics:
+      mDice: 90.65
+      Dice: 82.7
+  Config: configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py
+  Metadata:
+    Training Data: STARE
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 0.986
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201821-f75705a9.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201821.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_pspnet_4xb4-40k_stare-128x128
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: STARE
+    Metrics:
+      mDice: 89.89
+      Dice: 81.22
+  Config: configs/unet/unet-s5-d16_pspnet_4xb4-40k_stare-128x128.py
+  Metadata:
+    Training Data: STARE
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 0.982
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_stare/pspnet_unet_s5-d16_128x128_40k_stare_20201227_181818-3c2923c4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_stare/pspnet_unet_s5-d16_128x128_40k_stare-20201227_181818.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_stare-128x128
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: STARE
+    Metrics:
+      mDice: 90.72
+      Dice: 82.84
+  Config: configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py
+  Metadata:
+    Training Data: STARE
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.028
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201823-f1063ef7.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201823.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_deeplabv3_4xb4-40k_stare-128x128
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: STARE
+    Metrics:
+      mDice: 89.73
+      Dice: 80.93
+  Config: configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_stare-128x128.py
+  Metadata:
+    Training Data: STARE
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 0.999
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_stare/deeplabv3_unet_s5-d16_128x128_40k_stare_20201226_094047-93dcb93c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_stare/deeplabv3_unet_s5-d16_128x128_40k_stare-20201226_094047.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_stare-128x128
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: STARE
+    Metrics:
+      mDice: 90.65
+      Dice: 82.71
+  Config: configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py
+  Metadata:
+    Training Data: STARE
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.01
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201825-21db614c.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201825.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_fcn_4xb4-40k_chase-db1-128x128
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: CHASE_DB1
+    Metrics:
+      mDice: 89.46
+      Dice: 80.24
+  Config: configs/unet/unet-s5-d16_fcn_4xb4-40k_chase-db1-128x128.py
+  Metadata:
+    Training Data: CHASE_DB1
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 0.968
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_chase_db1/fcn_unet_s5-d16_128x128_40k_chase_db1_20201223_191051-11543527.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_chase_db1/unet_s5-d16_128x128_40k_chase_db1-20201223_191051.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: CHASE_DB1
+    Metrics:
+      mDice: 89.52
+      Dice: 80.4
+  Config: configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py
+  Metadata:
+    Training Data: CHASE_DB1
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 0.986
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201821-1c4eb7cf.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201821.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_pspnet_4xb4-40k_chase-db1-128x128
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: CHASE_DB1
+    Metrics:
+      mDice: 89.52
+      Dice: 80.36
+  Config: configs/unet/unet-s5-d16_pspnet_4xb4-40k_chase-db1-128x128.py
+  Metadata:
+    Training Data: CHASE_DB1
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 0.982
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1/pspnet_unet_s5-d16_128x128_40k_chase_db1_20201227_181818-68d4e609.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1/pspnet_unet_s5-d16_128x128_40k_chase_db1-20201227_181818.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: CHASE_DB1
+    Metrics:
+      mDice: 89.45
+      Dice: 80.28
+  Config: configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py
+  Metadata:
+    Training Data: CHASE_DB1
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.028
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201823-c0802c4d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201823.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet_s5-d16_deeplabv3_4xb4-40k_chase-db1-128x128
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: CHASE_DB1
+    Metrics:
+      mDice: 89.57
+      Dice: 80.47
+  Config: configs/unet/unet_s5-d16_deeplabv3_4xb4-40k_chase-db1-128x128.py
+  Metadata:
+    Training Data: CHASE_DB1
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 0.999
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1/deeplabv3_unet_s5-d16_128x128_40k_chase_db1_20201226_094047-4c5aefa3.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1/deeplabv3_unet_s5-d16_128x128_40k_chase_db1-20201226_094047.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: CHASE_DB1
+    Metrics:
+      mDice: 89.49
+      Dice: 80.37
+  Config: configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py
+  Metadata:
+    Training Data: CHASE_DB1
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 1.01
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201825-4ef29df5.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201825.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_fcn_4xb4-40k_hrf-256x256
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: HRF
+    Metrics:
+      mDice: 88.92
+      Dice: 79.45
+  Config: configs/unet/unet-s5-d16_fcn_4xb4-40k_hrf-256x256.py
+  Metadata:
+    Training Data: HRF
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 2.525
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_256x256_40k_hrf/fcn_unet_s5-d16_256x256_40k_hrf_20201223_173724-d89cf1ed.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_256x256_40k_hrf/unet_s5-d16_256x256_40k_hrf-20201223_173724.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: HRF
+    Metrics:
+      mDice: 89.64
+      Dice: 80.87
+  Config: configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py
+  Metadata:
+    Training Data: HRF
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - FCN
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 2.623
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201821-c314da8a.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201821.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_pspnet_4xb4-40k_hrf-256x256
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: HRF
+    Metrics:
+      mDice: 89.24
+      Dice: 80.07
+  Config: configs/unet/unet-s5-d16_pspnet_4xb4-40k_hrf-256x256.py
+  Metadata:
+    Training Data: HRF
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 2.588
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_256x256_40k_hrf/pspnet_unet_s5-d16_256x256_40k_hrf_20201227_181818-fdb7e29b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_256x256_40k_hrf/pspnet_unet_s5-d16_256x256_40k_hrf-20201227_181818.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: HRF
+    Metrics:
+      mDice: 89.69
+      Dice: 80.96
+  Config: configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py
+  Metadata:
+    Training Data: HRF
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - PSPNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 2.798
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201823-53d492fa.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201823.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_deeplabv3_4xb4-40k_hrf-256x256
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: HRF
+    Metrics:
+      mDice: 89.32
+      Dice: 80.21
+  Config: configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_hrf-256x256.py
+  Metadata:
+    Training Data: HRF
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 2.604
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf/deeplabv3_unet_s5-d16_256x256_40k_hrf_20201226_094047-3a1fdf85.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf/deeplabv3_unet_s5-d16_256x256_40k_hrf-20201226_094047.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
+- Name: unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256
+  In Collection: UNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: HRF
+    Metrics:
+      mDice: 89.56
+      Dice: 80.71
+  Config: configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py
+  Metadata:
+    Training Data: HRF
+    Batch Size: 16
+    Architecture:
+    - UNet-S5-D16
+    - UNet
+    - DeepLabV3
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 2.607
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_202032-59daf7a4.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_202032.log.json
+  Paper:
+    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
+    URL: https://arxiv.org/abs/1505.04597
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
+  Framework: PyTorch
diff --git a/configs/unet/unet.yml b/configs/unet/unet.yml
deleted file mode 100644
index 4a01ce33e2..0000000000
--- a/configs/unet/unet.yml
+++ /dev/null
@@ -1,377 +0,0 @@
-Collections:
-- Name: UNet
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - DRIVE
-    - STARE
-    - CHASE_DB1
-    - HRF
-  Paper:
-    URL: https://arxiv.org/abs/1505.04597
-    Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
-  README: configs/unet/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
-    Version: v0.17.0
-  Converted From:
-    Code: http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net
-Models:
-- Name: unet-s5-d16_fcn_4xb4-160k_cityscapes-512x1024
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (512,1024)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 327.87
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 17.91
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 69.1
-      mIoU(ms+flip): 71.05
-  Config: configs/unet/unet-s5-d16_fcn_4xb4-160k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes_20211210_145204-6860854e.pth
-- Name: unet-s5-d16_fcn_4xb4-40k_drive-64x64
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (64,64)
-    lr schd: 40000
-    Training Memory (GB): 0.68
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: DRIVE
-    Metrics:
-      Dice: 78.67
-  Config: configs/unet/unet-s5-d16_fcn_4xb4-40k_drive-64x64.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_64x64_40k_drive/fcn_unet_s5-d16_64x64_40k_drive_20201223_191051-5daf6d3b.pth
-- Name: unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_drive-64x64
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (64,64)
-    lr schd: 40000
-    Training Memory (GB): 0.582
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: DRIVE
-    Metrics:
-      Dice: 79.32
-  Config: configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201820-785de5c2.pth
-- Name: unet-s5-d16_pspnet_4xb4-40k_drive-64x64
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (64,64)
-    lr schd: 40000
-    Training Memory (GB): 0.599
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: DRIVE
-    Metrics:
-      Dice: 78.62
-  Config: configs/unet/unet-s5-d16_pspnet_4xb4-40k_drive-64x64.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_64x64_40k_drive/pspnet_unet_s5-d16_64x64_40k_drive_20201227_181818-aac73387.pth
-- Name: unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_drive-64x64
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (64,64)
-    lr schd: 40000
-    Training Memory (GB): 0.585
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: DRIVE
-    Metrics:
-      Dice: 79.42
-  Config: configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201821-22b3e3ba.pth
-- Name: unet-s5-d16_deeplabv3_4xb4-40k_drive-64x64
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (64,64)
-    lr schd: 40000
-    Training Memory (GB): 0.596
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: DRIVE
-    Metrics:
-      Dice: 78.69
-  Config: configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_drive-64x64.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_64x64_40k_drive/deeplabv3_unet_s5-d16_64x64_40k_drive_20201226_094047-0671ff20.pth
-- Name: unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_drive-64x64
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (64,64)
-    lr schd: 40000
-    Training Memory (GB): 0.582
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: DRIVE
-    Metrics:
-      Dice: 79.56
-  Config: configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201825-6bf0efd7.pth
-- Name: unet-s5-d16_fcn_4xb4-40k_stare-128x128
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (128,128)
-    lr schd: 40000
-    Training Memory (GB): 0.968
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: STARE
-    Metrics:
-      Dice: 81.02
-  Config: configs/unet/unet-s5-d16_fcn_4xb4-40k_stare-128x128.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_stare/fcn_unet_s5-d16_128x128_40k_stare_20201223_191051-7d77e78b.pth
-- Name: unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_stare-128x128
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (128,128)
-    lr schd: 40000
-    Training Memory (GB): 0.986
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: STARE
-    Metrics:
-      Dice: 82.7
-  Config: configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201821-f75705a9.pth
-- Name: unet-s5-d16_pspnet_4xb4-40k_stare-128x128
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (128,128)
-    lr schd: 40000
-    Training Memory (GB): 0.982
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: STARE
-    Metrics:
-      Dice: 81.22
-  Config: configs/unet/unet-s5-d16_pspnet_4xb4-40k_stare-128x128.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_stare/pspnet_unet_s5-d16_128x128_40k_stare_20201227_181818-3c2923c4.pth
-- Name: unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_stare-128x128
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (128,128)
-    lr schd: 40000
-    Training Memory (GB): 1.028
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: STARE
-    Metrics:
-      Dice: 82.84
-  Config: configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201823-f1063ef7.pth
-- Name: unet-s5-d16_deeplabv3_4xb4-40k_stare-128x128
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (128,128)
-    lr schd: 40000
-    Training Memory (GB): 0.999
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: STARE
-    Metrics:
-      Dice: 80.93
-  Config: configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_stare-128x128.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_stare/deeplabv3_unet_s5-d16_128x128_40k_stare_20201226_094047-93dcb93c.pth
-- Name: unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_stare-128x128
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (128,128)
-    lr schd: 40000
-    Training Memory (GB): 1.01
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: STARE
-    Metrics:
-      Dice: 82.71
-  Config: configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201825-21db614c.pth
-- Name: unet-s5-d16_fcn_4xb4-40k_chase-db1-128x128
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (128,128)
-    lr schd: 40000
-    Training Memory (GB): 0.968
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: CHASE_DB1
-    Metrics:
-      Dice: 80.24
-  Config: configs/unet/unet-s5-d16_fcn_4xb4-40k_chase-db1-128x128.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_chase_db1/fcn_unet_s5-d16_128x128_40k_chase_db1_20201223_191051-11543527.pth
-- Name: unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (128,128)
-    lr schd: 40000
-    Training Memory (GB): 0.986
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: CHASE_DB1
-    Metrics:
-      Dice: 80.4
-  Config: configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201821-1c4eb7cf.pth
-- Name: unet-s5-d16_pspnet_4xb4-40k_chase-db1-128x128
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (128,128)
-    lr schd: 40000
-    Training Memory (GB): 0.982
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: CHASE_DB1
-    Metrics:
-      Dice: 80.36
-  Config: configs/unet/unet-s5-d16_pspnet_4xb4-40k_chase-db1-128x128.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1/pspnet_unet_s5-d16_128x128_40k_chase_db1_20201227_181818-68d4e609.pth
-- Name: unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (128,128)
-    lr schd: 40000
-    Training Memory (GB): 1.028
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: CHASE_DB1
-    Metrics:
-      Dice: 80.28
-  Config: configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201823-c0802c4d.pth
-- Name: unet_s5-d16_deeplabv3_4xb4-40k_chase-db1-128x128
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (128,128)
-    lr schd: 40000
-    Training Memory (GB): 0.999
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: CHASE_DB1
-    Metrics:
-      Dice: 80.47
-  Config: configs/unet/unet_s5-d16_deeplabv3_4xb4-40k_chase-db1-128x128.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1/deeplabv3_unet_s5-d16_128x128_40k_chase_db1_20201226_094047-4c5aefa3.pth
-- Name: unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (128,128)
-    lr schd: 40000
-    Training Memory (GB): 1.01
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: CHASE_DB1
-    Metrics:
-      Dice: 80.37
-  Config: configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201825-4ef29df5.pth
-- Name: unet-s5-d16_fcn_4xb4-40k_hrf-256x256
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (256,256)
-    lr schd: 40000
-    Training Memory (GB): 2.525
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: HRF
-    Metrics:
-      Dice: 79.45
-  Config: configs/unet/unet-s5-d16_fcn_4xb4-40k_hrf-256x256.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_256x256_40k_hrf/fcn_unet_s5-d16_256x256_40k_hrf_20201223_173724-d89cf1ed.pth
-- Name: unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (256,256)
-    lr schd: 40000
-    Training Memory (GB): 2.623
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: HRF
-    Metrics:
-      Dice: 80.87
-  Config: configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201821-c314da8a.pth
-- Name: unet-s5-d16_pspnet_4xb4-40k_hrf-256x256
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (256,256)
-    lr schd: 40000
-    Training Memory (GB): 2.588
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: HRF
-    Metrics:
-      Dice: 80.07
-  Config: configs/unet/unet-s5-d16_pspnet_4xb4-40k_hrf-256x256.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_256x256_40k_hrf/pspnet_unet_s5-d16_256x256_40k_hrf_20201227_181818-fdb7e29b.pth
-- Name: unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (256,256)
-    lr schd: 40000
-    Training Memory (GB): 2.798
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: HRF
-    Metrics:
-      Dice: 80.96
-  Config: configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201823-53d492fa.pth
-- Name: unet-s5-d16_deeplabv3_4xb4-40k_hrf-256x256
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (256,256)
-    lr schd: 40000
-    Training Memory (GB): 2.604
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: HRF
-    Metrics:
-      Dice: 80.21
-  Config: configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_hrf-256x256.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf/deeplabv3_unet_s5-d16_256x256_40k_hrf_20201226_094047-3a1fdf85.pth
-- Name: unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256
-  In Collection: UNet
-  Metadata:
-    backbone: UNet-S5-D16
-    crop size: (256,256)
-    lr schd: 40000
-    Training Memory (GB): 2.607
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: HRF
-    Metrics:
-      Dice: 80.71
-  Config: configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_202032-59daf7a4.pth
diff --git a/configs/upernet/README.md b/configs/upernet/README.md
index e4a5ee4381..7d128090bf 100644
--- a/configs/upernet/README.md
+++ b/configs/upernet/README.md
@@ -1,6 +1,6 @@
 # UPerNet
 
-[Unified Perceptual Parsing for Scene Understanding](https://arxiv.org/pdf/1807.10221.pdf)
+> [Unified Perceptual Parsing for Scene Understanding](https://arxiv.org/pdf/1807.10221.pdf)
 
 ## Introduction
 
@@ -22,6 +22,39 @@ Humans recognize the visual world at multiple levels: we effortlessly categorize
 <img src="https://user-images.githubusercontent.com/24582831/142903077-44e8e0da-7276-4bda-bd2b-0df1680ca845.png" width="70%"/>
 </div>
 
+## Results and models
+
+### Cityscapes
+
+| Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                           |
+| ------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UPerNet | R-50     | 512x1024  |   40000 | 6.4      | 4.25           | V100   | 77.10 |         78.37 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_40k_cityscapes/upernet_r50_512x1024_40k_cityscapes_20200605_094827-aa54cb54.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_40k_cityscapes/upernet_r50_512x1024_40k_cityscapes_20200605_094827.log.json)     |
+| UPerNet | R-101    | 512x1024  |   40000 | 7.4      | 3.79           | V100   | 78.69 |         80.11 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_40k_cityscapes/upernet_r101_512x1024_40k_cityscapes_20200605_094933-ebce3b10.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_40k_cityscapes/upernet_r101_512x1024_40k_cityscapes_20200605_094933.log.json) |
+| UPerNet | R-50     | 769x769   |   40000 | 7.2      | 1.76           | V100   | 77.98 |         79.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_40k_cityscapes/upernet_r50_769x769_40k_cityscapes_20200530_033048-92d21539.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_40k_cityscapes/upernet_r50_769x769_40k_cityscapes_20200530_033048.log.json)         |
+| UPerNet | R-101    | 769x769   |   40000 | 8.4      | 1.56           | V100   | 79.03 |         80.77 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_40k_cityscapes/upernet_r101_769x769_40k_cityscapes_20200530_040819-83c95d01.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_40k_cityscapes/upernet_r101_769x769_40k_cityscapes_20200530_040819.log.json)     |
+| UPerNet | R-50     | 512x1024  |   80000 | -        | -              | V100   | 78.19 |         79.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_80k_cityscapes/upernet_r50_512x1024_80k_cityscapes_20200607_052207-848beca8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_80k_cityscapes/upernet_r50_512x1024_80k_cityscapes_20200607_052207.log.json)     |
+| UPerNet | R-101    | 512x1024  |   80000 | -        | -              | V100   | 79.40 |         80.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_80k_cityscapes/upernet_r101_512x1024_80k_cityscapes_20200607_002403-f05f2345.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_80k_cityscapes/upernet_r101_512x1024_80k_cityscapes_20200607_002403.log.json) |
+| UPerNet | R-50     | 769x769   |   80000 | -        | -              | V100   | 79.39 |         80.92 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_80k_cityscapes/upernet_r50_769x769_80k_cityscapes_20200607_005107-82ae7d15.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_80k_cityscapes/upernet_r50_769x769_80k_cityscapes_20200607_005107.log.json)         |
+| UPerNet | R-101    | 769x769   |   80000 | -        | -              | V100   | 80.10 |         81.49 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_80k_cityscapes/upernet_r101_769x769_80k_cityscapes_20200607_001014-082fc334.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_80k_cityscapes/upernet_r101_769x769_80k_cityscapes_20200607_001014.log.json)     |
+
+### ADE20K
+
+| Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                           |
+| ------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UPerNet | R-50     | 512x512   |   80000 | 8.1      | 23.40          | V100   | 40.70 |         41.81 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_80k_ade20k/upernet_r50_512x512_80k_ade20k_20200614_144127-ecc8377b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_80k_ade20k/upernet_r50_512x512_80k_ade20k_20200614_144127.log.json)         |
+| UPerNet | R-101    | 512x512   |   80000 | 9.1      | 20.34          | V100   | 42.91 |         43.96 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_80k_ade20k/upernet_r101_512x512_80k_ade20k_20200614_185117-32e4db94.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_80k_ade20k/upernet_r101_512x512_80k_ade20k_20200614_185117.log.json)     |
+| UPerNet | R-50     | 512x512   |  160000 | -        | -              | V100   | 42.05 |         42.78 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_160k_ade20k/upernet_r50_512x512_160k_ade20k_20200615_184328-8534de8d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_160k_ade20k/upernet_r50_512x512_160k_ade20k_20200615_184328.log.json)     |
+| UPerNet | R-101    | 512x512   |  160000 | -        | -              | V100   | 43.82 |         44.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_160k_ade20k/upernet_r101_512x512_160k_ade20k_20200615_161951-91b32684.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_160k_ade20k/upernet_r101_512x512_160k_ade20k_20200615_161951.log.json) |
+
+### Pascal VOC 2012 + Aug
+
+| Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                               |
+| ------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UPerNet | R-50     | 512x512   |   20000 | 6.4      | 23.17          | V100   | 74.82 |         76.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_20k_voc12aug/upernet_r50_512x512_20k_voc12aug_20200617_165330-5b5890a7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_20k_voc12aug/upernet_r50_512x512_20k_voc12aug_20200617_165330.log.json)     |
+| UPerNet | R-101    | 512x512   |   20000 | 7.5      | 19.98          | V100   | 77.10 |         78.29 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_20k_voc12aug/upernet_r101_512x512_20k_voc12aug_20200617_165629-f14e7f27.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_20k_voc12aug/upernet_r101_512x512_20k_voc12aug_20200617_165629.log.json) |
+| UPerNet | R-50     | 512x512   |   40000 | -        | -              | V100   | 75.92 |         77.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_40k_voc12aug/upernet_r50_512x512_40k_voc12aug_20200613_162257-ca9bcc6b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_40k_voc12aug/upernet_r50_512x512_40k_voc12aug_20200613_162257.log.json)     |
+| UPerNet | R-101    | 512x512   |   40000 | -        | -              | V100   | 77.43 |         78.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_40k_voc12aug/upernet_r101_512x512_40k_voc12aug_20200613_163549-e26476ac.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_40k_voc12aug/upernet_r101_512x512_40k_voc12aug_20200613_163549.log.json) |
+
 ## Citation
 
 ```bibtex
@@ -33,36 +66,3 @@ Humans recognize the visual world at multiple levels: we effortlessly categorize
   year={2018}
 }
 ```
-
-## Results and models
-
-### Cityscapes
-
-| Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                           |
-| ------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UPerNet | R-50     | 512x1024  |   40000 | 6.4      | 4.25           | 77.10 |         78.37 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_40k_cityscapes/upernet_r50_512x1024_40k_cityscapes_20200605_094827-aa54cb54.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_40k_cityscapes/upernet_r50_512x1024_40k_cityscapes_20200605_094827.log.json)     |
-| UPerNet | R-101    | 512x1024  |   40000 | 7.4      | 3.79           | 78.69 |         80.11 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_40k_cityscapes/upernet_r101_512x1024_40k_cityscapes_20200605_094933-ebce3b10.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_40k_cityscapes/upernet_r101_512x1024_40k_cityscapes_20200605_094933.log.json) |
-| UPerNet | R-50     | 769x769   |   40000 | 7.2      | 1.76           | 77.98 |         79.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_40k_cityscapes/upernet_r50_769x769_40k_cityscapes_20200530_033048-92d21539.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_40k_cityscapes/upernet_r50_769x769_40k_cityscapes_20200530_033048.log.json)         |
-| UPerNet | R-101    | 769x769   |   40000 | 8.4      | 1.56           | 79.03 |         80.77 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_40k_cityscapes/upernet_r101_769x769_40k_cityscapes_20200530_040819-83c95d01.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_40k_cityscapes/upernet_r101_769x769_40k_cityscapes_20200530_040819.log.json)     |
-| UPerNet | R-50     | 512x1024  |   80000 | -        | -              | 78.19 |         79.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_80k_cityscapes/upernet_r50_512x1024_80k_cityscapes_20200607_052207-848beca8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_80k_cityscapes/upernet_r50_512x1024_80k_cityscapes_20200607_052207.log.json)     |
-| UPerNet | R-101    | 512x1024  |   80000 | -        | -              | 79.40 |         80.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_80k_cityscapes/upernet_r101_512x1024_80k_cityscapes_20200607_002403-f05f2345.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_80k_cityscapes/upernet_r101_512x1024_80k_cityscapes_20200607_002403.log.json) |
-| UPerNet | R-50     | 769x769   |   80000 | -        | -              | 79.39 |         80.92 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_80k_cityscapes/upernet_r50_769x769_80k_cityscapes_20200607_005107-82ae7d15.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_80k_cityscapes/upernet_r50_769x769_80k_cityscapes_20200607_005107.log.json)         |
-| UPerNet | R-101    | 769x769   |   80000 | -        | -              | 80.10 |         81.49 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_80k_cityscapes/upernet_r101_769x769_80k_cityscapes_20200607_001014-082fc334.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_80k_cityscapes/upernet_r101_769x769_80k_cityscapes_20200607_001014.log.json)     |
-
-### ADE20K
-
-| Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                           |
-| ------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UPerNet | R-50     | 512x512   |   80000 | 8.1      | 23.40          | 40.70 |         41.81 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_80k_ade20k/upernet_r50_512x512_80k_ade20k_20200614_144127-ecc8377b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_80k_ade20k/upernet_r50_512x512_80k_ade20k_20200614_144127.log.json)         |
-| UPerNet | R-101    | 512x512   |   80000 | 9.1      | 20.34          | 42.91 |         43.96 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_80k_ade20k/upernet_r101_512x512_80k_ade20k_20200614_185117-32e4db94.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_80k_ade20k/upernet_r101_512x512_80k_ade20k_20200614_185117.log.json)     |
-| UPerNet | R-50     | 512x512   |  160000 | -        | -              | 42.05 |         42.78 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_160k_ade20k/upernet_r50_512x512_160k_ade20k_20200615_184328-8534de8d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_160k_ade20k/upernet_r50_512x512_160k_ade20k_20200615_184328.log.json)     |
-| UPerNet | R-101    | 512x512   |  160000 | -        | -              | 43.82 |         44.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_160k_ade20k/upernet_r101_512x512_160k_ade20k_20200615_161951-91b32684.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_160k_ade20k/upernet_r101_512x512_160k_ade20k_20200615_161951.log.json) |
-
-### Pascal VOC 2012 + Aug
-
-| Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                               |
-| ------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UPerNet | R-50     | 512x512   |   20000 | 6.4      | 23.17          | 74.82 |         76.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_20k_voc12aug/upernet_r50_512x512_20k_voc12aug_20200617_165330-5b5890a7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_20k_voc12aug/upernet_r50_512x512_20k_voc12aug_20200617_165330.log.json)     |
-| UPerNet | R-101    | 512x512   |   20000 | 7.5      | 19.98          | 77.10 |         78.29 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_20k_voc12aug/upernet_r101_512x512_20k_voc12aug_20200617_165629-f14e7f27.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_20k_voc12aug/upernet_r101_512x512_20k_voc12aug_20200617_165629.log.json) |
-| UPerNet | R-50     | 512x512   |   40000 | -        | -              | 75.92 |         77.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_40k_voc12aug/upernet_r50_512x512_40k_voc12aug_20200613_162257-ca9bcc6b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_40k_voc12aug/upernet_r50_512x512_40k_voc12aug_20200613_162257.log.json)     |
-| UPerNet | R-101    | 512x512   |   40000 | -        | -              | 77.43 |         78.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_40k_voc12aug/upernet_r101_512x512_40k_voc12aug_20200613_163549-e26476ac.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_40k_voc12aug/upernet_r101_512x512_40k_voc12aug_20200613_163549.log.json) |
diff --git a/configs/upernet/metafile.yaml b/configs/upernet/metafile.yaml
new file mode 100644
index 0000000000..f6ad8187f2
--- /dev/null
+++ b/configs/upernet/metafile.yaml
@@ -0,0 +1,391 @@
+Collections:
+- Name: UPerNet
+  License: Apache License 2.0
+  Metadata:
+    Training Data:
+    - Cityscapes
+    - ADE20K
+    - Pascal VOC 2012 + Aug
+  Paper:
+    Title: Unified Perceptual Parsing for Scene Understanding
+    URL: https://arxiv.org/pdf/1807.10221.pdf
+  README: configs/upernet/README.md
+  Frameworks:
+  - PyTorch
+Models:
+- Name: upernet_r50_4xb2-40k_cityscapes-512x1024
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.1
+      mIoU(ms+flip): 78.37
+  Config: configs/upernet/upernet_r50_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50
+    - UPerNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.4
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_40k_cityscapes/upernet_r50_512x1024_40k_cityscapes_20200605_094827-aa54cb54.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_40k_cityscapes/upernet_r50_512x1024_40k_cityscapes_20200605_094827.log.json
+  Paper:
+    Title: Unified Perceptual Parsing for Scene Understanding
+    URL: https://arxiv.org/pdf/1807.10221.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/uper_head.py#L13
+  Framework: PyTorch
+- Name: upernet_r101_4xb2-40k_cityscapes-512x1024
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.69
+      mIoU(ms+flip): 80.11
+  Config: configs/upernet/upernet_r101_4xb2-40k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101
+    - UPerNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.4
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_40k_cityscapes/upernet_r101_512x1024_40k_cityscapes_20200605_094933-ebce3b10.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_40k_cityscapes/upernet_r101_512x1024_40k_cityscapes_20200605_094933.log.json
+  Paper:
+    Title: Unified Perceptual Parsing for Scene Understanding
+    URL: https://arxiv.org/pdf/1807.10221.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/uper_head.py#L13
+  Framework: PyTorch
+- Name: upernet_r50_4xb2-40k_cityscapes-769x769
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 77.98
+      mIoU(ms+flip): 79.7
+  Config: configs/upernet/upernet_r50_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50
+    - UPerNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_40k_cityscapes/upernet_r50_769x769_40k_cityscapes_20200530_033048-92d21539.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_40k_cityscapes/upernet_r50_769x769_40k_cityscapes_20200530_033048.log.json
+  Paper:
+    Title: Unified Perceptual Parsing for Scene Understanding
+    URL: https://arxiv.org/pdf/1807.10221.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/uper_head.py#L13
+  Framework: PyTorch
+- Name: upernet_r101_4xb2-40k_cityscapes-769x769
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.03
+      mIoU(ms+flip): 80.77
+  Config: configs/upernet/upernet_r101_4xb2-40k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101
+    - UPerNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.4
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_40k_cityscapes/upernet_r101_769x769_40k_cityscapes_20200530_040819-83c95d01.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_40k_cityscapes/upernet_r101_769x769_40k_cityscapes_20200530_040819.log.json
+  Paper:
+    Title: Unified Perceptual Parsing for Scene Understanding
+    URL: https://arxiv.org/pdf/1807.10221.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/uper_head.py#L13
+  Framework: PyTorch
+- Name: upernet_r50_4xb2-80k_cityscapes-512x1024
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 78.19
+      mIoU(ms+flip): 79.19
+  Config: configs/upernet/upernet_r50_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50
+    - UPerNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_80k_cityscapes/upernet_r50_512x1024_80k_cityscapes_20200607_052207-848beca8.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_80k_cityscapes/upernet_r50_512x1024_80k_cityscapes_20200607_052207.log.json
+  Paper:
+    Title: Unified Perceptual Parsing for Scene Understanding
+    URL: https://arxiv.org/pdf/1807.10221.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/uper_head.py#L13
+  Framework: PyTorch
+- Name: upernet_r101_4xb2-80k_cityscapes-512x1024
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.4
+      mIoU(ms+flip): 80.46
+  Config: configs/upernet/upernet_r101_4xb2-80k_cityscapes-512x1024.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101
+    - UPerNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_80k_cityscapes/upernet_r101_512x1024_80k_cityscapes_20200607_002403-f05f2345.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_80k_cityscapes/upernet_r101_512x1024_80k_cityscapes_20200607_002403.log.json
+  Paper:
+    Title: Unified Perceptual Parsing for Scene Understanding
+    URL: https://arxiv.org/pdf/1807.10221.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/uper_head.py#L13
+  Framework: PyTorch
+- Name: upernet_r50_4xb2-80k_cityscapes-769x769
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 79.39
+      mIoU(ms+flip): 80.92
+  Config: configs/upernet/upernet_r50_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-50
+    - UPerNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_80k_cityscapes/upernet_r50_769x769_80k_cityscapes_20200607_005107-82ae7d15.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_80k_cityscapes/upernet_r50_769x769_80k_cityscapes_20200607_005107.log.json
+  Paper:
+    Title: Unified Perceptual Parsing for Scene Understanding
+    URL: https://arxiv.org/pdf/1807.10221.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/uper_head.py#L13
+  Framework: PyTorch
+- Name: upernet_r101_4xb2-80k_cityscapes-769x769
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 80.1
+      mIoU(ms+flip): 81.49
+  Config: configs/upernet/upernet_r101_4xb2-80k_cityscapes-769x769.py
+  Metadata:
+    Training Data: Cityscapes
+    Batch Size: 8
+    Architecture:
+    - R-101
+    - UPerNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_80k_cityscapes/upernet_r101_769x769_80k_cityscapes_20200607_001014-082fc334.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_80k_cityscapes/upernet_r101_769x769_80k_cityscapes_20200607_001014.log.json
+  Paper:
+    Title: Unified Perceptual Parsing for Scene Understanding
+    URL: https://arxiv.org/pdf/1807.10221.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/uper_head.py#L13
+  Framework: PyTorch
+- Name: upernet_r50_4xb4-80k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 40.7
+      mIoU(ms+flip): 41.81
+  Config: configs/upernet/upernet_r50_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50
+    - UPerNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 8.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_80k_ade20k/upernet_r50_512x512_80k_ade20k_20200614_144127-ecc8377b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_80k_ade20k/upernet_r50_512x512_80k_ade20k_20200614_144127.log.json
+  Paper:
+    Title: Unified Perceptual Parsing for Scene Understanding
+    URL: https://arxiv.org/pdf/1807.10221.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/uper_head.py#L13
+  Framework: PyTorch
+- Name: upernet_r101_4xb4-80k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.91
+      mIoU(ms+flip): 43.96
+  Config: configs/upernet/upernet_r101_4xb4-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101
+    - UPerNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 9.1
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_80k_ade20k/upernet_r101_512x512_80k_ade20k_20200614_185117-32e4db94.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_80k_ade20k/upernet_r101_512x512_80k_ade20k_20200614_185117.log.json
+  Paper:
+    Title: Unified Perceptual Parsing for Scene Understanding
+    URL: https://arxiv.org/pdf/1807.10221.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/uper_head.py#L13
+  Framework: PyTorch
+- Name: upernet_r50_4xb4-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.05
+      mIoU(ms+flip): 42.78
+  Config: configs/upernet/upernet_r50_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-50
+    - UPerNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_160k_ade20k/upernet_r50_512x512_160k_ade20k_20200615_184328-8534de8d.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_160k_ade20k/upernet_r50_512x512_160k_ade20k_20200615_184328.log.json
+  Paper:
+    Title: Unified Perceptual Parsing for Scene Understanding
+    URL: https://arxiv.org/pdf/1807.10221.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/uper_head.py#L13
+  Framework: PyTorch
+- Name: upernet_r101_4xb4-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.82
+      mIoU(ms+flip): 44.85
+  Config: configs/upernet/upernet_r101_4xb4-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - R-101
+    - UPerNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_160k_ade20k/upernet_r101_512x512_160k_ade20k_20200615_161951-91b32684.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_160k_ade20k/upernet_r101_512x512_160k_ade20k_20200615_161951.log.json
+  Paper:
+    Title: Unified Perceptual Parsing for Scene Understanding
+    URL: https://arxiv.org/pdf/1807.10221.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/uper_head.py#L13
+  Framework: PyTorch
+- Name: upernet_r50_4xb4-20k_voc12aug-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 74.82
+      mIoU(ms+flip): 76.35
+  Config: configs/upernet/upernet_r50_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50
+    - UPerNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 6.4
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_20k_voc12aug/upernet_r50_512x512_20k_voc12aug_20200617_165330-5b5890a7.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_20k_voc12aug/upernet_r50_512x512_20k_voc12aug_20200617_165330.log.json
+  Paper:
+    Title: Unified Perceptual Parsing for Scene Understanding
+    URL: https://arxiv.org/pdf/1807.10221.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/uper_head.py#L13
+  Framework: PyTorch
+- Name: upernet_r101_4xb4-20k_voc12aug-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 77.1
+      mIoU(ms+flip): 78.29
+  Config: configs/upernet/upernet_r101_4xb4-20k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101
+    - UPerNet
+    Training Resources: 4x V100 GPUS
+    Memory (GB): 7.5
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_20k_voc12aug/upernet_r101_512x512_20k_voc12aug_20200617_165629-f14e7f27.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_20k_voc12aug/upernet_r101_512x512_20k_voc12aug_20200617_165629.log.json
+  Paper:
+    Title: Unified Perceptual Parsing for Scene Understanding
+    URL: https://arxiv.org/pdf/1807.10221.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/uper_head.py#L13
+  Framework: PyTorch
+- Name: upernet_r50_4xb4-40k_voc12aug-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 75.92
+      mIoU(ms+flip): 77.44
+  Config: configs/upernet/upernet_r50_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-50
+    - UPerNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_40k_voc12aug/upernet_r50_512x512_40k_voc12aug_20200613_162257-ca9bcc6b.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_40k_voc12aug/upernet_r50_512x512_40k_voc12aug_20200613_162257.log.json
+  Paper:
+    Title: Unified Perceptual Parsing for Scene Understanding
+    URL: https://arxiv.org/pdf/1807.10221.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/uper_head.py#L13
+  Framework: PyTorch
+- Name: upernet_r101_4xb4-40k_voc12aug-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 77.43
+      mIoU(ms+flip): 78.56
+  Config: configs/upernet/upernet_r101_4xb4-40k_voc12aug-512x512.py
+  Metadata:
+    Training Data: Pascal VOC 2012 + Aug
+    Batch Size: 16
+    Architecture:
+    - R-101
+    - UPerNet
+    Training Resources: 4x V100 GPUS
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_40k_voc12aug/upernet_r101_512x512_40k_voc12aug_20200613_163549-e26476ac.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_40k_voc12aug/upernet_r101_512x512_40k_voc12aug_20200613_163549.log.json
+  Paper:
+    Title: Unified Perceptual Parsing for Scene Understanding
+    URL: https://arxiv.org/pdf/1807.10221.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/uper_head.py#L13
+  Framework: PyTorch
diff --git a/configs/upernet/upernet.yml b/configs/upernet/upernet.yml
deleted file mode 100644
index 6892fcf06a..0000000000
--- a/configs/upernet/upernet.yml
+++ /dev/null
@@ -1,305 +0,0 @@
-Collections:
-- Name: UPerNet
-  Metadata:
-    Training Data:
-    - Cityscapes
-    - ADE20K
-    - Pascal VOC 2012 + Aug
-  Paper:
-    URL: https://arxiv.org/pdf/1807.10221.pdf
-    Title: Unified Perceptual Parsing for Scene Understanding
-  README: configs/upernet/README.md
-  Code:
-    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/uper_head.py#L13
-    Version: v0.17.0
-  Converted From:
-    Code: https://github.com/CSAILVision/unifiedparsing
-Models:
-- Name: upernet_r50_4xb2-40k_cityscapes-512x1024
-  In Collection: UPerNet
-  Metadata:
-    backbone: R-50
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 235.29
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 6.4
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.1
-      mIoU(ms+flip): 78.37
-  Config: configs/upernet/upernet_r50_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_40k_cityscapes/upernet_r50_512x1024_40k_cityscapes_20200605_094827-aa54cb54.pth
-- Name: upernet_r101_4xb2-40k_cityscapes-512x1024
-  In Collection: UPerNet
-  Metadata:
-    backbone: R-101
-    crop size: (512,1024)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 263.85
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,1024)
-    Training Memory (GB): 7.4
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.69
-      mIoU(ms+flip): 80.11
-  Config: configs/upernet/upernet_r101_4xb2-40k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_40k_cityscapes/upernet_r101_512x1024_40k_cityscapes_20200605_094933-ebce3b10.pth
-- Name: upernet_r50_4xb2-40k_cityscapes-769x769
-  In Collection: UPerNet
-  Metadata:
-    backbone: R-50
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 568.18
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 7.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 77.98
-      mIoU(ms+flip): 79.7
-  Config: configs/upernet/upernet_r50_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_40k_cityscapes/upernet_r50_769x769_40k_cityscapes_20200530_033048-92d21539.pth
-- Name: upernet_r101_4xb2-40k_cityscapes-769x769
-  In Collection: UPerNet
-  Metadata:
-    backbone: R-101
-    crop size: (769,769)
-    lr schd: 40000
-    inference time (ms/im):
-    - value: 641.03
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (769,769)
-    Training Memory (GB): 8.4
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.03
-      mIoU(ms+flip): 80.77
-  Config: configs/upernet/upernet_r101_4xb2-40k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_40k_cityscapes/upernet_r101_769x769_40k_cityscapes_20200530_040819-83c95d01.pth
-- Name: upernet_r50_4xb2-80k_cityscapes-512x1024
-  In Collection: UPerNet
-  Metadata:
-    backbone: R-50
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 78.19
-      mIoU(ms+flip): 79.19
-  Config: configs/upernet/upernet_r50_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_80k_cityscapes/upernet_r50_512x1024_80k_cityscapes_20200607_052207-848beca8.pth
-- Name: upernet_r101_4xb2-80k_cityscapes-512x1024
-  In Collection: UPerNet
-  Metadata:
-    backbone: R-101
-    crop size: (512,1024)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.4
-      mIoU(ms+flip): 80.46
-  Config: configs/upernet/upernet_r101_4xb2-80k_cityscapes-512x1024.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_80k_cityscapes/upernet_r101_512x1024_80k_cityscapes_20200607_002403-f05f2345.pth
-- Name: upernet_r50_4xb2-80k_cityscapes-769x769
-  In Collection: UPerNet
-  Metadata:
-    backbone: R-50
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 79.39
-      mIoU(ms+flip): 80.92
-  Config: configs/upernet/upernet_r50_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_80k_cityscapes/upernet_r50_769x769_80k_cityscapes_20200607_005107-82ae7d15.pth
-- Name: upernet_r101_4xb2-80k_cityscapes-769x769
-  In Collection: UPerNet
-  Metadata:
-    backbone: R-101
-    crop size: (769,769)
-    lr schd: 80000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Cityscapes
-    Metrics:
-      mIoU: 80.1
-      mIoU(ms+flip): 81.49
-  Config: configs/upernet/upernet_r101_4xb2-80k_cityscapes-769x769.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_80k_cityscapes/upernet_r101_769x769_80k_cityscapes_20200607_001014-082fc334.pth
-- Name: upernet_r50_4xb4-80k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: R-50
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 42.74
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 8.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 40.7
-      mIoU(ms+flip): 41.81
-  Config: configs/upernet/upernet_r50_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_80k_ade20k/upernet_r50_512x512_80k_ade20k_20200614_144127-ecc8377b.pth
-- Name: upernet_r101_4xb4-80k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: R-101
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 49.16
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.1
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.91
-      mIoU(ms+flip): 43.96
-  Config: configs/upernet/upernet_r101_4xb4-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_80k_ade20k/upernet_r101_512x512_80k_ade20k_20200614_185117-32e4db94.pth
-- Name: upernet_r50_4xb4-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: R-50
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.05
-      mIoU(ms+flip): 42.78
-  Config: configs/upernet/upernet_r50_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_160k_ade20k/upernet_r50_512x512_160k_ade20k_20200615_184328-8534de8d.pth
-- Name: upernet_r101_4xb4-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: R-101
-    crop size: (512,512)
-    lr schd: 160000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.82
-      mIoU(ms+flip): 44.85
-  Config: configs/upernet/upernet_r101_4xb4-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_160k_ade20k/upernet_r101_512x512_160k_ade20k_20200615_161951-91b32684.pth
-- Name: upernet_r50_4xb4-20k_voc12aug-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: R-50
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 43.16
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 6.4
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 74.82
-      mIoU(ms+flip): 76.35
-  Config: configs/upernet/upernet_r50_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_20k_voc12aug/upernet_r50_512x512_20k_voc12aug_20200617_165330-5b5890a7.pth
-- Name: upernet_r101_4xb4-20k_voc12aug-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: R-101
-    crop size: (512,512)
-    lr schd: 20000
-    inference time (ms/im):
-    - value: 50.05
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 7.5
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 77.1
-      mIoU(ms+flip): 78.29
-  Config: configs/upernet/upernet_r101_4xb4-20k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_20k_voc12aug/upernet_r101_512x512_20k_voc12aug_20200617_165629-f14e7f27.pth
-- Name: upernet_r50_4xb4-40k_voc12aug-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: R-50
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 75.92
-      mIoU(ms+flip): 77.44
-  Config: configs/upernet/upernet_r50_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_40k_voc12aug/upernet_r50_512x512_40k_voc12aug_20200613_162257-ca9bcc6b.pth
-- Name: upernet_r101_4xb4-40k_voc12aug-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: R-101
-    crop size: (512,512)
-    lr schd: 40000
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: Pascal VOC 2012 + Aug
-    Metrics:
-      mIoU: 77.43
-      mIoU(ms+flip): 78.56
-  Config: configs/upernet/upernet_r101_4xb4-40k_voc12aug-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_40k_voc12aug/upernet_r101_512x512_40k_voc12aug_20200613_163549-e26476ac.pth
diff --git a/configs/vit/README.md b/configs/vit/README.md
index b7f242549d..26601d498f 100644
--- a/configs/vit/README.md
+++ b/configs/vit/README.md
@@ -1,6 +1,6 @@
 # Vision Transformer
 
-[An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/pdf/2010.11929.pdf)
+> [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/pdf/2010.11929.pdf)
 
 ## Introduction
 
@@ -22,17 +22,6 @@ While the Transformer architecture has become the de-facto standard for natural
 <img src="https://user-images.githubusercontent.com/24582831/142903144-f80a12cc-8698-48ab-843c-49dedf558121.png" width="70%"/>
 </div>
 
-## Citation
-
-```bibtex
-@article{dosoViTskiy2020,
-  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
-  author={DosoViTskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and  Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
-  journal={arXiv preprint arXiv:2010.11929},
-  year={2020}
-}
-```
-
 ## Usage
 
 To use other repositories' pre-trained models, it is necessary to convert keys.
@@ -55,16 +44,27 @@ This script convert model from `PRETRAIN_PATH` and store the converted model in
 
 ### ADE20K
 
-| Method  | Backbone          | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                     | download                                                                                                                                                                                                                                                                                                                   |
-| ------- | ----------------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UPerNet | ViT-B + MLN       | 512x512   |   80000 | 9.20     | 6.94           | 47.71 |         49.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_vit-b16_mln_upernet_8xb2-80k_ade20k-512x512.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/upernet_vit-b16_mln_512x512_80k_ade20k_20210624_130547-0403cee1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/20210624_130547.log.json)                |
-| UPerNet | ViT-B + MLN       | 512x512   |  160000 | 9.20     | 7.58           | 46.75 |         48.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_vit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/upernet_vit-b16_mln_512x512_160k_ade20k_20210624_130547-852fa768.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/20210623_192432.log.json)             |
-| UPerNet | ViT-B + LN + MLN  | 512x512   |  160000 | 9.21     | 6.82           | 47.73 |         49.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_vit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/upernet_vit-b16_ln_mln_512x512_160k_ade20k_20210621_172828-f444c077.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/20210621_172828.log.json)    |
-| UPerNet | DeiT-S            | 512x512   |   80000 | 4.68     | 29.85          | 42.96 |         43.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-s16_upernet_8xb2-80k_ade20k-512x512.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/upernet_deit-s16_512x512_80k_ade20k_20210624_095228-afc93ec2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/20210624_095228.log.json)                         |
-| UPerNet | DeiT-S            | 512x512   |  160000 | 4.68     | 29.19          | 42.87 |         43.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-s16_upernet_8xb2-160k_ade20k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/upernet_deit-s16_512x512_160k_ade20k_20210621_160903-5110d916.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/20210621_160903.log.json)                      |
-| UPerNet | DeiT-S + MLN      | 512x512   |  160000 | 5.69     | 11.18          | 43.82 |         45.07 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-s16_mln_upernet_8xb2-160k_ade20k-512x512.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/upernet_deit-s16_mln_512x512_160k_ade20k_20210621_161021-fb9a5dfb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/20210621_161021.log.json)          |
-| UPerNet | DeiT-S + LN + MLN | 512x512   |  160000 | 5.69     | 12.39          | 43.52 |         45.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-s16-ln_mln_upernet_512x512_160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/upernet_deit-s16_ln_mln_512x512_160k_ade20k_20210621_161021-c0cd652f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/20210621_161021.log.json) |
-| UPerNet | DeiT-B            | 512x512   |   80000 | 7.75     | 9.69           | 45.24 |         46.73 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-b16_upernet_8xb2-80k_ade20k-512x512.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/upernet_deit-b16_512x512_80k_ade20k_20210624_130529-1e090789.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/20210624_130529.log.json)                         |
-| UPerNet | DeiT-B            | 512x512   |  160000 | 7.75     | 10.39          | 45.36 |         47.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-b16_upernet_8xb2-160k_ade20k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/upernet_deit-b16_512x512_160k_ade20k_20210621_180100-828705d7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/20210621_180100.log.json)                      |
-| UPerNet | DeiT-B + MLN      | 512x512   |  160000 | 9.21     | 7.78           | 45.46 |         47.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/upernet_deit-b16_mln_512x512_160k_ade20k_20210621_191949-4e1450f3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/20210621_191949.log.json)          |
-| UPerNet | DeiT-B + LN + MLN | 512x512   |  160000 | 9.21     | 7.75           | 45.37 |         47.23 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/upernet_deit-b16_ln_mln_512x512_160k_ade20k_20210623_153535-8a959c14.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/20210623_153535.log.json) |
+| Method  | Backbone          | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                  | download                                                                                                                                                                                                                                                                                                                   |
+| ------- | ----------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UPerNet | ViT-B + MLN       | 512x512   |   80000 | 9.20     | 6.94           | V100   | 47.71 |         49.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_vit-b16_mln_upernet_8xb2-80k_ade20k-512x512.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/upernet_vit-b16_mln_512x512_80k_ade20k_20210624_130547-0403cee1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/20210624_130547.log.json)                |
+| UPerNet | ViT-B + MLN       | 512x512   |  160000 | 9.20     | 7.58           | V100   | 46.75 |         48.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_vit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/upernet_vit-b16_mln_512x512_160k_ade20k_20210624_130547-852fa768.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/20210623_192432.log.json)             |
+| UPerNet | ViT-B + LN + MLN  | 512x512   |  160000 | 9.21     | 6.82           | V100   | 47.73 |         49.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_vit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/upernet_vit-b16_ln_mln_512x512_160k_ade20k_20210621_172828-f444c077.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/20210621_172828.log.json)    |
+| UPerNet | DeiT-S            | 512x512   |   80000 | 4.68     | 29.85          | V100   | 42.96 |         43.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-s16_upernet_8xb2-80k_ade20k-512x512.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/upernet_deit-s16_512x512_80k_ade20k_20210624_095228-afc93ec2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/20210624_095228.log.json)                         |
+| UPerNet | DeiT-S            | 512x512   |  160000 | 4.68     | 29.19          | V100   | 42.87 |         43.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-s16_upernet_8xb2-160k_ade20k-512x512.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/upernet_deit-s16_512x512_160k_ade20k_20210621_160903-5110d916.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/20210621_160903.log.json)                      |
+| UPerNet | DeiT-S + MLN      | 512x512   |  160000 | 5.69     | 11.18          | V100   | 43.82 |         45.07 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-s16_mln_upernet_8xb2-160k_ade20k-512x512.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/upernet_deit-s16_mln_512x512_160k_ade20k_20210621_161021-fb9a5dfb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/20210621_161021.log.json)          |
+| UPerNet | DeiT-S + LN + MLN | 512x512   |  160000 | 5.69     | 12.39          | V100   | 43.52 |         45.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-s16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/upernet_deit-s16_ln_mln_512x512_160k_ade20k_20210621_161021-c0cd652f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/20210621_161021.log.json) |
+| UPerNet | DeiT-B            | 512x512   |   80000 | 7.75     | 9.69           | V100   | 45.24 |         46.73 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-b16_upernet_8xb2-80k_ade20k-512x512.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/upernet_deit-b16_512x512_80k_ade20k_20210624_130529-1e090789.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/20210624_130529.log.json)                         |
+| UPerNet | DeiT-B            | 512x512   |  160000 | 7.75     | 10.39          | V100   | 45.36 |         47.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-b16_upernet_8xb2-160k_ade20k-512x512.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/upernet_deit-b16_512x512_160k_ade20k_20210621_180100-828705d7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/20210621_180100.log.json)                      |
+| UPerNet | DeiT-B + MLN      | 512x512   |  160000 | 9.21     | 7.78           | V100   | 45.46 |         47.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/upernet_deit-b16_mln_512x512_160k_ade20k_20210621_191949-4e1450f3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/20210621_191949.log.json)          |
+| UPerNet | DeiT-B + LN + MLN | 512x512   |  160000 | 9.21     | 7.75           | V100   | 45.37 |         47.23 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/upernet_deit-b16_ln_mln_512x512_160k_ade20k_20210623_153535-8a959c14.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/20210623_153535.log.json) |
+
+## Citation
+
+```bibtex
+@article{dosoViTskiy2020,
+  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
+  author={DosoViTskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and  Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
+  journal={arXiv preprint arXiv:2010.11929},
+  year={2020}
+}
+```
diff --git a/configs/vit/metafile.yaml b/configs/vit/metafile.yaml
new file mode 100644
index 0000000000..68e254a5f9
--- /dev/null
+++ b/configs/vit/metafile.yaml
@@ -0,0 +1,265 @@
+Models:
+- Name: vit_vit-b16_mln_upernet_8xb2-80k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 47.71
+      mIoU(ms+flip): 49.51
+  Config: configs/vit/vit_vit-b16_mln_upernet_8xb2-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - ViT-B
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 9.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/upernet_vit-b16_mln_512x512_80k_ade20k_20210624_130547-0403cee1.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/20210624_130547.log.json
+  Paper:
+    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
+    URL: https://arxiv.org/pdf/2010.11929.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
+  Framework: PyTorch
+- Name: vit_vit-b16_mln_upernet_8xb2-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 46.75
+      mIoU(ms+flip): 48.46
+  Config: configs/vit/vit_vit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - ViT-B
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 9.2
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/upernet_vit-b16_mln_512x512_160k_ade20k_20210624_130547-852fa768.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/20210623_192432.log.json
+  Paper:
+    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
+    URL: https://arxiv.org/pdf/2010.11929.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
+  Framework: PyTorch
+- Name: vit_vit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 47.73
+      mIoU(ms+flip): 49.95
+  Config: configs/vit/vit_vit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - ViT-B
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 9.21
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/upernet_vit-b16_ln_mln_512x512_160k_ade20k_20210621_172828-f444c077.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/20210621_172828.log.json
+  Paper:
+    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
+    URL: https://arxiv.org/pdf/2010.11929.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
+  Framework: PyTorch
+- Name: vit_deit-s16_upernet_8xb2-80k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.96
+      mIoU(ms+flip): 43.79
+  Config: configs/vit/vit_deit-s16_upernet_8xb2-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - DeiT-S
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 4.68
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/upernet_deit-s16_512x512_80k_ade20k_20210624_095228-afc93ec2.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/20210624_095228.log.json
+  Paper:
+    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
+    URL: https://arxiv.org/pdf/2010.11929.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
+  Framework: PyTorch
+- Name: vit_deit-s16_upernet_8xb2-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 42.87
+      mIoU(ms+flip): 43.79
+  Config: configs/vit/vit_deit-s16_upernet_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - DeiT-S
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 4.68
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/upernet_deit-s16_512x512_160k_ade20k_20210621_160903-5110d916.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/20210621_160903.log.json
+  Paper:
+    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
+    URL: https://arxiv.org/pdf/2010.11929.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
+  Framework: PyTorch
+- Name: vit_deit-s16_mln_upernet_8xb2-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.82
+      mIoU(ms+flip): 45.07
+  Config: configs/vit/vit_deit-s16_mln_upernet_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - DeiT-S
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 5.69
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/upernet_deit-s16_mln_512x512_160k_ade20k_20210621_161021-fb9a5dfb.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/20210621_161021.log.json
+  Paper:
+    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
+    URL: https://arxiv.org/pdf/2010.11929.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
+  Framework: PyTorch
+- Name: vit_deit-s16-ln_mln_upernet_8xb2-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 43.52
+      mIoU(ms+flip): 45.01
+  Config: configs/vit/vit_deit-s16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - DeiT-S
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 5.69
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/upernet_deit-s16_ln_mln_512x512_160k_ade20k_20210621_161021-c0cd652f.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/20210621_161021.log.json
+  Paper:
+    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
+    URL: https://arxiv.org/pdf/2010.11929.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
+  Framework: PyTorch
+- Name: vit_deit-b16_upernet_8xb2-80k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.24
+      mIoU(ms+flip): 46.73
+  Config: configs/vit/vit_deit-b16_upernet_8xb2-80k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - DeiT-B
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 7.75
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/upernet_deit-b16_512x512_80k_ade20k_20210624_130529-1e090789.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/20210624_130529.log.json
+  Paper:
+    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
+    URL: https://arxiv.org/pdf/2010.11929.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
+  Framework: PyTorch
+- Name: vit_deit-b16_upernet_8xb2-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.36
+      mIoU(ms+flip): 47.16
+  Config: configs/vit/vit_deit-b16_upernet_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - DeiT-B
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 7.75
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/upernet_deit-b16_512x512_160k_ade20k_20210621_180100-828705d7.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/20210621_180100.log.json
+  Paper:
+    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
+    URL: https://arxiv.org/pdf/2010.11929.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
+  Framework: PyTorch
+- Name: vit_deit-b16_mln_upernet_8xb2-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.46
+      mIoU(ms+flip): 47.16
+  Config: configs/vit/vit_deit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - DeiT-B
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 9.21
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/upernet_deit-b16_mln_512x512_160k_ade20k_20210621_191949-4e1450f3.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/20210621_191949.log.json
+  Paper:
+    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
+    URL: https://arxiv.org/pdf/2010.11929.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
+  Framework: PyTorch
+- Name: vit_deit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512
+  In Collection: UPerNet
+  Results:
+    Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 45.37
+      mIoU(ms+flip): 47.23
+  Config: configs/vit/vit_deit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py
+  Metadata:
+    Training Data: ADE20K
+    Batch Size: 16
+    Architecture:
+    - DeiT-B
+    - UPerNet
+    Training Resources: 8x V100 GPUS
+    Memory (GB): 9.21
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/upernet_deit-b16_ln_mln_512x512_160k_ade20k_20210623_153535-8a959c14.pth
+  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/20210623_153535.log.json
+  Paper:
+    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
+    URL: https://arxiv.org/pdf/2010.11929.pdf
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
+  Framework: PyTorch
diff --git a/configs/vit/vit.yml b/configs/vit/vit.yml
deleted file mode 100644
index 613d866ac4..0000000000
--- a/configs/vit/vit.yml
+++ /dev/null
@@ -1,243 +0,0 @@
-Models:
-- Name: vit_vit-b16_mln_upernet_8xb2-80k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: ViT-B + MLN
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 144.09
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 47.71
-      mIoU(ms+flip): 49.51
-  Config: configs/vit/vit_vit-b16_mln_upernet_8xb2-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/upernet_vit-b16_mln_512x512_80k_ade20k_20210624_130547-0403cee1.pth
-- Name: vit_vit-b16_mln_upernet_8xb2-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: ViT-B + MLN
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 131.93
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.2
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 46.75
-      mIoU(ms+flip): 48.46
-  Config: configs/vit/vit_vit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/upernet_vit-b16_mln_512x512_160k_ade20k_20210624_130547-852fa768.pth
-- Name: vit_vit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: ViT-B + LN + MLN
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 146.63
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.21
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 47.73
-      mIoU(ms+flip): 49.95
-  Config: configs/vit/vit_vit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/upernet_vit-b16_ln_mln_512x512_160k_ade20k_20210621_172828-f444c077.pth
-- Name: vit_deit-s16_upernet_8xb2-80k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: DeiT-S
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 33.5
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 4.68
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.96
-      mIoU(ms+flip): 43.79
-  Config: configs/vit/vit_deit-s16_upernet_8xb2-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/upernet_deit-s16_512x512_80k_ade20k_20210624_095228-afc93ec2.pth
-- Name: vit_deit-s16_upernet_8xb2-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: DeiT-S
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 34.26
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 4.68
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 42.87
-      mIoU(ms+flip): 43.79
-  Config: configs/vit/vit_deit-s16_upernet_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/upernet_deit-s16_512x512_160k_ade20k_20210621_160903-5110d916.pth
-- Name: vit_deit-s16_mln_upernet_8xb2-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: DeiT-S + MLN
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 89.45
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 5.69
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.82
-      mIoU(ms+flip): 45.07
-  Config: configs/vit/vit_deit-s16_mln_upernet_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/upernet_deit-s16_mln_512x512_160k_ade20k_20210621_161021-fb9a5dfb.pth
-- Name: vit_deit-s16-ln_mln_upernet_512x512_160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: DeiT-S + LN + MLN
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 80.71
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 5.69
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 43.52
-      mIoU(ms+flip): 45.01
-  Config: configs/vit/vit_deit-s16-ln_mln_upernet_512x512_160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/upernet_deit-s16_ln_mln_512x512_160k_ade20k_20210621_161021-c0cd652f.pth
-- Name: vit_deit-b16_upernet_8xb2-80k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: DeiT-B
-    crop size: (512,512)
-    lr schd: 80000
-    inference time (ms/im):
-    - value: 103.2
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 7.75
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.24
-      mIoU(ms+flip): 46.73
-  Config: configs/vit/vit_deit-b16_upernet_8xb2-80k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/upernet_deit-b16_512x512_80k_ade20k_20210624_130529-1e090789.pth
-- Name: vit_deit-b16_upernet_8xb2-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: DeiT-B
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 96.25
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 7.75
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.36
-      mIoU(ms+flip): 47.16
-  Config: configs/vit/vit_deit-b16_upernet_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/upernet_deit-b16_512x512_160k_ade20k_20210621_180100-828705d7.pth
-- Name: vit_deit-b16_mln_upernet_8xb2-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: DeiT-B + MLN
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 128.53
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.21
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.46
-      mIoU(ms+flip): 47.16
-  Config: configs/vit/vit_deit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/upernet_deit-b16_mln_512x512_160k_ade20k_20210621_191949-4e1450f3.pth
-- Name: vit_deit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512
-  In Collection: UPerNet
-  Metadata:
-    backbone: DeiT-B + LN + MLN
-    crop size: (512,512)
-    lr schd: 160000
-    inference time (ms/im):
-    - value: 129.03
-      hardware: V100
-      backend: PyTorch
-      batch size: 1
-      mode: FP32
-      resolution: (512,512)
-    Training Memory (GB): 9.21
-  Results:
-  - Task: Semantic Segmentation
-    Dataset: ADE20K
-    Metrics:
-      mIoU: 45.37
-      mIoU(ms+flip): 47.23
-  Config: configs/vit/vit_deit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/upernet_deit-b16_ln_mln_512x512_160k_ade20k_20210623_153535-8a959c14.pth
diff --git a/configs/vit/vit_deit-s16-ln_mln_upernet_512x512_160k_ade20k-512x512.py b/configs/vit/vit_deit-s16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py
similarity index 100%
rename from configs/vit/vit_deit-s16-ln_mln_upernet_512x512_160k_ade20k-512x512.py
rename to configs/vit/vit_deit-s16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py
diff --git a/model-index.yml b/model-index.yml
index 130031a303..5e87c386dd 100644
--- a/model-index.yml
+++ b/model-index.yml
@@ -1,50 +1,50 @@
 Import:
-- configs/ann/ann.yml
-- configs/apcnet/apcnet.yml
-- configs/beit/beit.yml
-- configs/bisenetv1/bisenetv1.yml
-- configs/bisenetv2/bisenetv2.yml
-- configs/ccnet/ccnet.yml
-- configs/cgnet/cgnet.yml
-- configs/convnext/convnext.yml
-- configs/danet/danet.yml
-- configs/deeplabv3/deeplabv3.yml
-- configs/deeplabv3plus/deeplabv3plus.yml
-- configs/dmnet/dmnet.yml
-- configs/dnlnet/dnlnet.yml
-- configs/dpt/dpt.yml
-- configs/emanet/emanet.yml
-- configs/encnet/encnet.yml
-- configs/erfnet/erfnet.yml
-- configs/fastfcn/fastfcn.yml
-- configs/fastscnn/fastscnn.yml
-- configs/fcn/fcn.yml
-- configs/gcnet/gcnet.yml
-- configs/hrnet/hrnet.yml
-- configs/icnet/icnet.yml
-- configs/isanet/isanet.yml
-- configs/knet/knet.yml
-- configs/mae/mae.yml
-- configs/mask2former/mask2former.yml
-- configs/maskformer/maskformer.yml
-- configs/mobilenet_v2/mobilenet_v2.yml
-- configs/mobilenet_v3/mobilenet_v3.yml
-- configs/nonlocal_net/nonlocal_net.yml
-- configs/ocrnet/ocrnet.yml
-- configs/pidnet/pidnet.yml
-- configs/point_rend/point_rend.yml
-- configs/poolformer/poolformer.yml
-- configs/psanet/psanet.yml
-- configs/pspnet/pspnet.yml
-- configs/resnest/resnest.yml
-- configs/segformer/segformer.yml
-- configs/segmenter/segmenter.yml
-- configs/segnext/segnext.yml
-- configs/sem_fpn/sem_fpn.yml
-- configs/setr/setr.yml
-- configs/stdc/stdc.yml
-- configs/swin/swin.yml
-- configs/twins/twins.yml
-- configs/unet/unet.yml
-- configs/upernet/upernet.yml
-- configs/vit/vit.yml
+- configs/ann/metafile.yaml
+- configs/apcnet/metafile.yaml
+- configs/beit/metafile.yaml
+- configs/bisenetv1/metafile.yaml
+- configs/bisenetv2/metafile.yaml
+- configs/ccnet/metafile.yaml
+- configs/cgnet/metafile.yaml
+- configs/convnext/metafile.yaml
+- configs/danet/metafile.yaml
+- configs/deeplabv3/metafile.yaml
+- configs/deeplabv3plus/metafile.yaml
+- configs/dmnet/metafile.yaml
+- configs/dnlnet/metafile.yaml
+- configs/dpt/metafile.yaml
+- configs/emanet/metafile.yaml
+- configs/encnet/metafile.yaml
+- configs/erfnet/metafile.yaml
+- configs/fastfcn/metafile.yaml
+- configs/fastscnn/metafile.yaml
+- configs/fcn/metafile.yaml
+- configs/gcnet/metafile.yaml
+- configs/hrnet/metafile.yaml
+- configs/icnet/metafile.yaml
+- configs/isanet/metafile.yaml
+- configs/knet/metafile.yaml
+- configs/mae/metafile.yaml
+- configs/mask2former/metafile.yaml
+- configs/maskformer/metafile.yaml
+- configs/mobilenet_v2/metafile.yaml
+- configs/mobilenet_v3/metafile.yaml
+- configs/nonlocal_net/metafile.yaml
+- configs/ocrnet/metafile.yaml
+- configs/pidnet/metafile.yaml
+- configs/point_rend/metafile.yaml
+- configs/poolformer/metafile.yaml
+- configs/psanet/metafile.yaml
+- configs/pspnet/metafile.yaml
+- configs/resnest/metafile.yaml
+- configs/segformer/metafile.yaml
+- configs/segmenter/metafile.yaml
+- configs/segnext/metafile.yaml
+- configs/sem_fpn/metafile.yaml
+- configs/setr/metafile.yaml
+- configs/stdc/metafile.yaml
+- configs/swin/metafile.yaml
+- configs/twins/metafile.yaml
+- configs/unet/metafile.yaml
+- configs/upernet/metafile.yaml
+- configs/vit/metafile.yaml

From ff95416c3b5ce8d62b9289f743531398efce534f Mon Sep 17 00:00:00 2001
From: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
Date: Fri, 17 Mar 2023 22:58:08 +0800
Subject: [PATCH 21/32] [Features]Support dump segment predition (#2712)

## Motivation

1. It is used to save the segmentation predictions as files and upload
these files to a test server

## Modification

1. Add output_file and format only in `IoUMetric`

## BC-breaking (Optional)

No

## Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases
here, and update the documentation.

## Checklist

1. Pre-commit or other linting tools are used to fix the potential lint
issues.
3. The modification is covered by complete unit tests. If not, please
add more unit test to ensure the correctness.
4. If the modification has potential influence on downstream projects,
this PR should be tested with downstream projects, like MMDet or
MMDet3D.
5. The documentation has been modified accordingly, like docstring or
example tutorials.
---
 docs/en/migration/interface.md                | 29 ++++++
 docs/en/user_guides/4_train_test.md           | 97 ++++++++++++++++++-
 docs/zh_cn/migration/interface.md             | 31 +++++-
 docs/zh_cn/user_guides/4_train_test.md        | 92 ++++++++++++++++++
 mmseg/datasets/transforms/formatting.py       |  2 +-
 mmseg/evaluation/metrics/citys_metric.py      | 15 ++-
 mmseg/evaluation/metrics/iou_metric.py        | 48 +++++++--
 .../test_metrics/test_citys_metric.py         | 27 ++----
 .../test_metrics/test_iou_metric.py           | 30 +++++-
 tools/test.py                                 |  9 ++
 10 files changed, 347 insertions(+), 33 deletions(-)

diff --git a/docs/en/migration/interface.md b/docs/en/migration/interface.md
index 3dab125ebc..46040d911f 100644
--- a/docs/en/migration/interface.md
+++ b/docs/en/migration/interface.md
@@ -65,6 +65,35 @@ Compared with MMSeg0.x, MMSeg1.x provides fewer command line arguments in `tools
 <td>--cfg-options randomness.deterministic=True</td>
 </table>
 
+## Test launch
+
+Similar to training launch, there are only common arguments in tools/test.py of MMSegmentation 1.x.
+Below is the difference in test scripts,
+please refer to [this documentation](../user_guides/4_train_test.md) for more details about test launch.
+
+<table class="docutils">
+<tr>
+<td>Function</td>
+<td>0.x</td>
+<td>1.x</td>
+</tr>
+<tr>
+<td>Evaluation metrics</td>
+<td>--eval mIoU</td>
+<td>--cfg-options test_evaluator.type=IoUMetric</td>
+</tr>
+<tr>
+<td>Whether to use test time augmentation</td>
+<td>--aug-test</td>
+<td>--tta</td>
+</tr>
+<tr>
+<td>Whether save the output results without perform evaluation</td>
+<td>--format-only</td>
+<td>--cfg-options test_evaluator.format_only=True</td>
+</tr>
+</table>
+
 ## Configuration file
 
 ### Model settings
diff --git a/docs/en/user_guides/4_train_test.md b/docs/en/user_guides/4_train_test.md
index 00e074ad39..9b2d17dc46 100644
--- a/docs/en/user_guides/4_train_test.md
+++ b/docs/en/user_guides/4_train_test.md
@@ -70,7 +70,7 @@ This tool accepts several optional arguments, including:
 export CUDA_VISIBLE_DEVICES=-1
 ```
 
-And then run the script [above](#testing-on-a-single-gpu).
+then run the script [above](#testing-on-a-single-gpu).
 
 ## Training and testing on multiple GPUs and multiple machines
 
@@ -218,3 +218,98 @@ You can check [the source code](../../../tools/slurm_test.sh) to review full arg
 CUDA_VISIBLE_DEVICES=0,1,2,3 GPUS=4 MASTER_PORT=29500 sh tools/slurm_train.sh ${PARTITION} ${JOB_NAME} config1.py ${WORK_DIR}
 CUDA_VISIBLE_DEVICES=4,5,6,7 GPUS=4 MASTER_PORT=29501 sh tools/slurm_train.sh ${PARTITION} ${JOB_NAME} config2.py ${WORK_DIR}
 ```
+
+## Testing and saving segment files
+
+### Basic Usage
+
+When you want to save the results, you can use `--out` to specify the output directory.
+
+```shell
+python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} --out ${OUTPUT_DIR}
+```
+
+Here is an example to save the predicted results from model `fcn_r50-d8_4xb4-80k_ade20k-512x512` on ADE20k validatation dataset.
+
+```shell
+python tools/test.py configs/fcn/fcn_r50-d8_4xb4-80k_ade20k-512x512.py ckpt/fcn_r50-d8_512x512_80k_ade20k_20200614_144016-f8ac5082.pth --out work_dirs/format_results
+```
+
+You also can modify the config file to define `output_dir`. We also take
+`fcn_r50-d8_4xb4-80k_ade20k-512x512` as example just add
+`test_evaluator` in `configs/fcn/fcn_r50-d8_4xb4-80k_ade20k-512x512.py`
+
+```python
+test_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'], output_dir='work_dirs/format_results')
+```
+
+then run command without `--out`:
+
+```shell
+python tools/test.py configs/fcn/fcn_r50-d8_4xb4-80k_ade20k-512x512.py ckpt/fcn_r50-d8_512x512_80k_ade20k_20200614_144016-f8ac5082.pth
+```
+
+If you would like to only save the predicted results without evaluation as annotation is not released by the official dataset, you can set `format_only=True` and modify `test_dataloader`.
+As there is no annotation in dataset, we remove `dict(type='LoadAnnotations')` from `test_dataloader` Here is the example configuration:
+
+```python
+test_evaluator = dict(
+    type='IoUMetric',
+    iou_metrics=['mIoU'],
+    format_only=True,
+    output_dir='work_dirs/format_results')
+test_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type = 'ADE20KDataset'
+        data_root='data/ade/release_test',
+        data_prefix=dict(img_path='testing'),
+        # we don't load annotation in test transform pipeline.
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='Resize', scale=(2048, 512), keep_ratio=True),
+            dict(type='PackSegInputs')
+        ]))
+```
+
+then run test command:
+
+```shell
+python tools/test.py configs/fcn/fcn_r50-d8_4xb4-80k_ade20k-512x512.py ckpt/fcn_r50-d8_512x512_80k_ade20k_20200614_144016-f8ac5082.pth
+```
+
+### Testing Cityscape dataset and save predicted segment files
+
+We recommend `CityscapesMetric` which is the wrapper of Cityscapes'sdk, when you want to
+save the predicted results of Cityscape test dataset to submit them in [Cityscape test server](https://www.cityscapes-dataset.com/submit/). Here is the example configuration:
+
+```python
+test_evaluator = dict(
+    type='CityscapesMetric',
+    format_only=True,
+    keep_results=True,
+    output_dir='work_dirs/format_results')
+test_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type='CityscapesDataset',
+        data_root='data/cityscapes/',
+        data_prefix=dict(img_path='leftImg8bit/test'),
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
+            dict(type='PackSegInputs')
+        ]))
+```
+
+then run test command, for example:
+
+```shell
+python tools/test.py configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-512x1024.py ckpt/fcn_r18-d8_512x1024_80k_cityscapes_20201225_021327-6c50f8b4.pth
+```
diff --git a/docs/zh_cn/migration/interface.md b/docs/zh_cn/migration/interface.md
index a329ce38a8..cd16d2cbc6 100644
--- a/docs/zh_cn/migration/interface.md
+++ b/docs/zh_cn/migration/interface.md
@@ -65,6 +65,33 @@ OpenMMLab 2.0 的主要改进是发布了 MMEngine，它为启动训练任务的
 <td>--cfg-options randomness.deterministic=True</td>
 </table>
 
+## 测试启动
+
+与训练启动类似，MMSegmentation 1.x 的测试启动脚本在 tools/test.py 中仅提供关键命令行参数，以下是测试启动脚本的区别，更多关于测试启动的细节请参考[这里](../user_guides/4_train_test.md)。
+
+<table class="docutils">
+<tr>
+<td>功能</td>
+<td>0.x</td>
+<td>1.x</td>
+</tr>
+<tr>
+<td>指定评测指标</td>
+<td>--eval mIoU</td>
+<td>--cfg-options test_evaluator.type=IoUMetric</td>
+</tr>
+<tr>
+<td>测试时数据增强</td>
+<td>--aug-test</td>
+<td>--tta</td>
+</tr>
+<tr>
+<td>测试时是否只保存预测结果不计算评测指标</td>
+<td>--format-only</td>
+<td>--cfg-options test_evaluator.format_only=True</td>
+</tr>
+</table>
+
 ## 配置文件
 
 ### 模型设置
@@ -98,7 +125,7 @@ OpenMMLab 2.0 的主要改进是发布了 MMEngine，它为启动训练任务的
 
 **data** 的更改：
 
-原版 `data` 字段被拆分为 `train_dataloader`、`val_dataloader` 和 `test_dataloader`。这允许我们以细粒度配置它们。例如，您可以在训练和测试期间指定不同的采样器和批次大小。
+原版 `data` 字段被拆分为 `train_dataloader`、`val_dataloader` 和 `test_dataloader`，允许我们以细粒度配置它们。例如，您可以在训练和测试期间指定不同的采样器和批次大小。
 `samples_per_gpu` 重命名为 `batch_size`。
 `workers_per_gpu` 重命名为 `num_workers`。
 
@@ -144,7 +171,7 @@ test_dataloader = val_dataloader
 </tr>
 </table>
 
-**流程**变更
+**数据增强变换流程**变更
 
 - 原始格式转换 **`ToTensor`**、**`ImageToTensor`**、**`Collect`** 组合为 [`PackSegInputs`](mmseg.datasets.transforms.PackSegInputs)
 - 我们不建议在数据集流程中执行 **`Normalize`** 和 **Pad**。请将其从流程中删除，并将其设置在 `data_preprocessor` 字段中。
diff --git a/docs/zh_cn/user_guides/4_train_test.md b/docs/zh_cn/user_guides/4_train_test.md
index 309e046b2d..f821acaf52 100644
--- a/docs/zh_cn/user_guides/4_train_test.md
+++ b/docs/zh_cn/user_guides/4_train_test.md
@@ -223,3 +223,95 @@ GPUS=4 sh tools/slurm_train.sh dev pspnet configs/pspnet/pspnet_r50-d8_512x1024_
 CUDA_VISIBLE_DEVICES=0,1,2,3 GPUS=4 MASTER_PORT=29500 sh tools/slurm_train.sh ${分区} ${任务名} config1.py ${工作路径}
 CUDA_VISIBLE_DEVICES=4,5,6,7 GPUS=4 MASTER_PORT=29501 sh tools/slurm_train.sh ${分区} ${任务名} config2.py ${工作路径}
 ```
+
+## 测试并保存分割结果
+
+### 基础使用
+
+当需要保存测试输出的分割结果，用 `--out` 指定分割结果输出路径
+
+```shell
+python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} --out ${OUTPUT_DIR}
+```
+
+以保存模型 `fcn_r50-d8_4xb4-80k_ade20k-512x512` 在 ADE20K 验证数据集上的结果为例：
+
+```shell
+python tools/test.py configs/fcn/fcn_r50-d8_4xb4-80k_ade20k-512x512.py ckpt/fcn_r50-d8_512x512_80k_ade20k_20200614_144016-f8ac5082.pth --out work_dirs/format_results
+```
+
+或者通过配置文件定义 `output_dir`。例如在 `configs/fcn/fcn_r50-d8_4xb4-80k_ade20k-512x512.py` 添加 `test_evaluator` 定义：
+
+```python
+test_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'], output_dir='work_dirs/format_results')
+```
+
+然后执行相同功能的命令不需要再使用 `--out`：
+
+```shell
+python tools/test.py configs/fcn/fcn_r50-d8_4xb4-80k_ade20k-512x512.py ckpt/fcn_r50-d8_512x512_80k_ade20k_20200614_144016-f8ac5082.pth
+```
+
+当测试的数据集没有提供标注，评测时没有真值可以参与计算，因此需要设置 `format_only=True`，
+同时需要修改 `test_dataloader`，由于没有标注，我们需要在数据增强变换中删掉 `dict(type='LoadAnnotations')`，以下是一个配置示例：
+
+```python
+test_evaluator = dict(
+    type='IoUMetric',
+    iou_metrics=['mIoU'],
+    format_only=True,
+    output_dir='work_dirs/format_results')
+test_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type = 'ADE20KDataset'
+        data_root='data/ade/release_test',
+        data_prefix=dict(img_path='testing'),
+        # 测试数据变换中没有加载标注
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='Resize', scale=(2048, 512), keep_ratio=True),
+            dict(type='PackSegInputs')
+        ]))
+```
+
+然后执行测试命令：
+
+```shell
+python tools/test.py configs/fcn/fcn_r50-d8_4xb4-80k_ade20k-512x512.py ckpt/fcn_r50-d8_512x512_80k_ade20k_20200614_144016-f8ac5082.pth
+```
+
+### 测试 Cityscapes 数据集并保存输出分割结果
+
+推荐使用 `CityscapesMetric` 来保存模型在 Cityscapes 数据集上的测试结果，以下是一个配置示例：
+
+```python
+test_evaluator = dict(
+    type='CityscapesMetric',
+    format_only=True,
+    keep_results=True,
+    output_dir='work_dirs/format_results')
+test_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type='CityscapesDataset',
+        data_root='data/cityscapes/',
+        data_prefix=dict(img_path='leftImg8bit/test'),
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
+            dict(type='PackSegInputs')
+        ]))
+```
+
+然后执行相同的命令，例如：
+
+```shell
+python tools/test.py configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-512x1024.py ckpt/fcn_r18-d8_512x1024_80k_cityscapes_20201225_021327-6c50f8b4.pth
+```
diff --git a/mmseg/datasets/transforms/formatting.py b/mmseg/datasets/transforms/formatting.py
index 46171d64f5..89fd883791 100644
--- a/mmseg/datasets/transforms/formatting.py
+++ b/mmseg/datasets/transforms/formatting.py
@@ -44,7 +44,7 @@ class PackSegInputs(BaseTransform):
     def __init__(self,
                  meta_keys=('img_path', 'seg_map_path', 'ori_shape',
                             'img_shape', 'pad_shape', 'scale_factor', 'flip',
-                            'flip_direction')):
+                            'flip_direction', 'reduce_zero_label')):
         self.meta_keys = meta_keys
 
     def transform(self, results: dict) -> dict:
diff --git a/mmseg/evaluation/metrics/citys_metric.py b/mmseg/evaluation/metrics/citys_metric.py
index a2c008b99d..32984653c3 100644
--- a/mmseg/evaluation/metrics/citys_metric.py
+++ b/mmseg/evaluation/metrics/citys_metric.py
@@ -51,7 +51,8 @@ def __init__(self,
                  format_only: bool = False,
                  keep_results: bool = False,
                  collect_device: str = 'cpu',
-                 prefix: Optional[str] = None) -> None:
+                 prefix: Optional[str] = None,
+                 **kwargs) -> None:
         super().__init__(collect_device=collect_device, prefix=prefix)
         if CSEval is None:
             raise ImportError('Please run "pip install cityscapesscripts" to '
@@ -97,10 +98,14 @@ def process(self, data_batch: dict, data_samples: Sequence[dict]) -> None:
                 osp.join(self.output_dir, f'{basename}.png'))
             output = Image.fromarray(pred_label.astype(np.uint8)).convert('P')
             output.save(png_filename)
-            # when evaluating with official cityscapesscripts,
-            # **_gtFine_labelIds.png is used
-            gt_filename = data_sample['seg_map_path'].replace(
-                'labelTrainIds.png', 'labelIds.png')
+            if self.format_only:
+                # format_only always for test dataset without ground truth
+                gt_filename = ''
+            else:
+                # when evaluating with official cityscapesscripts,
+                # **_gtFine_labelIds.png is used
+                gt_filename = data_sample['seg_map_path'].replace(
+                    'labelTrainIds.png', 'labelIds.png')
             self.results.append((png_filename, gt_filename))
 
     def compute_metrics(self, results: list) -> Dict[str, float]:
diff --git a/mmseg/evaluation/metrics/iou_metric.py b/mmseg/evaluation/metrics/iou_metric.py
index a152ef9dd6..16014c7400 100644
--- a/mmseg/evaluation/metrics/iou_metric.py
+++ b/mmseg/evaluation/metrics/iou_metric.py
@@ -1,11 +1,15 @@
 # Copyright (c) OpenMMLab. All rights reserved.
+import os.path as osp
 from collections import OrderedDict
 from typing import Dict, List, Optional, Sequence
 
 import numpy as np
 import torch
+from mmengine.dist import is_main_process
 from mmengine.evaluator import BaseMetric
 from mmengine.logging import MMLogger, print_log
+from mmengine.utils import mkdir_or_exist
+from PIL import Image
 from prettytable import PrettyTable
 
 from mmseg.registry import METRICS
@@ -27,6 +31,12 @@ class IoUMetric(BaseMetric):
         collect_device (str): Device name used for collecting results from
             different ranks during distributed training. Must be 'cpu' or
             'gpu'. Defaults to 'cpu'.
+        output_dir (str): The directory for output prediction. Defaults to
+            None.
+        format_only (bool): Only format result for results commit without
+            perform evaluation. It is useful when you want to save the result
+            to a specific format and submit it to the test server.
+            Defaults to False.
         prefix (str, optional): The prefix that will be added in the metric
             names to disambiguate homonymous metrics of different evaluators.
             If prefix is not provided in the argument, self.default_prefix
@@ -39,13 +49,20 @@ def __init__(self,
                  nan_to_num: Optional[int] = None,
                  beta: int = 1,
                  collect_device: str = 'cpu',
-                 prefix: Optional[str] = None) -> None:
+                 output_dir: Optional[str] = None,
+                 format_only: bool = False,
+                 prefix: Optional[str] = None,
+                 **kwargs) -> None:
         super().__init__(collect_device=collect_device, prefix=prefix)
 
         self.ignore_index = ignore_index
         self.metrics = iou_metrics
         self.nan_to_num = nan_to_num
         self.beta = beta
+        self.output_dir = output_dir
+        if self.output_dir and is_main_process():
+            mkdir_or_exist(self.output_dir)
+        self.format_only = format_only
 
     def process(self, data_batch: dict, data_samples: Sequence[dict]) -> None:
         """Process one batch of data and data_samples.
@@ -60,10 +77,27 @@ def process(self, data_batch: dict, data_samples: Sequence[dict]) -> None:
         num_classes = len(self.dataset_meta['classes'])
         for data_sample in data_samples:
             pred_label = data_sample['pred_sem_seg']['data'].squeeze()
-            label = data_sample['gt_sem_seg']['data'].squeeze().to(pred_label)
-            self.results.append(
-                self.intersect_and_union(pred_label, label, num_classes,
-                                         self.ignore_index))
+            # format_only always for test dataset without ground truth
+            if not self.format_only:
+                label = data_sample['gt_sem_seg']['data'].squeeze().to(
+                    pred_label)
+                self.results.append(
+                    self.intersect_and_union(pred_label, label, num_classes,
+                                             self.ignore_index))
+            # format_result
+            if self.output_dir is not None:
+                basename = osp.splitext(osp.basename(
+                    data_sample['img_path']))[0]
+                png_filename = osp.abspath(
+                    osp.join(self.output_dir, f'{basename}.png'))
+                output_mask = pred_label.cpu().numpy()
+                # The index range of official ADE20k dataset is from 0 to 150.
+                # But the index range of output is from 0 to 149.
+                # That is because we set reduce_zero_label=True.
+                if data_sample.get('reduce_zero_label', False):
+                    output_mask = output_mask + 1
+                output = Image.fromarray(output_mask.astype(np.uint8))
+                output.save(png_filename)
 
     def compute_metrics(self, results: list) -> Dict[str, float]:
         """Compute the metrics from processed results.
@@ -78,7 +112,9 @@ def compute_metrics(self, results: list) -> Dict[str, float]:
                 mRecall.
         """
         logger: MMLogger = MMLogger.get_current_instance()
-
+        if self.format_only:
+            logger.info(f'results are saved to {osp.dirname(self.output_dir)}')
+            return OrderedDict()
         # convert list of tuples to tuple of lists, e.g.
         # [(A_1, B_1, C_1, D_1), ...,  (A_n, B_n, C_n, D_n)] to
         # ([A_1, ..., A_n], ..., [D_1, ..., D_n])
diff --git a/tests/test_evaluation/test_metrics/test_citys_metric.py b/tests/test_evaluation/test_metrics/test_citys_metric.py
index 0a20b41aee..06f956f54a 100644
--- a/tests/test_evaluation/test_metrics/test_citys_metric.py
+++ b/tests/test_evaluation/test_metrics/test_citys_metric.py
@@ -1,11 +1,12 @@
 # Copyright (c) OpenMMLab. All rights reserved.
 import os.path as osp
+import shutil
 from unittest import TestCase
 
 import numpy as np
 import pytest
 import torch
-from mmengine.structures import BaseDataElement, PixelData
+from mmengine.structures import PixelData
 
 from mmseg.evaluation import CityscapesMetric
 from mmseg.structures import SegDataSample
@@ -36,20 +37,16 @@ def _demo_mm_inputs(self,
             image_shape = image_shapes[idx]
             _, h, w = image_shape
 
-            mm_inputs = dict()
             data_sample = SegDataSample()
             gt_semantic_seg = np.random.randint(
                 0, num_classes, (1, h, w), dtype=np.uint8)
             gt_semantic_seg = torch.LongTensor(gt_semantic_seg)
             gt_sem_seg_data = dict(data=gt_semantic_seg)
             data_sample.gt_sem_seg = PixelData(**gt_sem_seg_data)
-            mm_inputs['data_sample'] = data_sample.to_dict()
-            mm_inputs['data_sample'][
+            data_sample = data_sample.to_dict()
+            data_sample[
                 'seg_map_path'] = 'tests/data/pseudo_cityscapes_dataset/gtFine/val/frankfurt/frankfurt_000000_000294_gtFine_labelTrainIds.png'  # noqa
-
-            mm_inputs['seg_map_path'] = mm_inputs['data_sample'][
-                'seg_map_path']
-            packed_inputs.append(mm_inputs)
+            packed_inputs.append(data_sample)
 
         return packed_inputs
 
@@ -85,14 +82,11 @@ def _demo_mm_model_output(self,
 
         _predictions = []
         for pred in batch_datasampes:
-            if isinstance(pred, BaseDataElement):
-                test_data = pred.to_dict()
-                test_data[
-                    'img_path'] = 'tests/data/pseudo_cityscapes_dataset/leftImg8bit/val/frankfurt/frankfurt_000000_000294_leftImg8bit.png'  # noqa
-
-                _predictions.append(test_data)
-            else:
-                _predictions.append(pred)
+            test_data = pred.to_dict()
+            test_data[
+                'img_path'] = 'tests/data/pseudo_cityscapes_dataset/leftImg8bit/val/frankfurt/frankfurt_000000_000294_leftImg8bit.png'  # noqa
+            _predictions.append(test_data)
+
         return _predictions
 
     def test_evaluate(self):
@@ -122,5 +116,4 @@ def test_evaluate(self):
         metric.evaluate(2)
         assert osp.exists('tmp')
         assert osp.isfile('tmp/frankfurt_000000_000294_leftImg8bit.png')
-        import shutil
         shutil.rmtree('tmp')
diff --git a/tests/test_evaluation/test_metrics/test_iou_metric.py b/tests/test_evaluation/test_metrics/test_iou_metric.py
index a0bc922c31..7a0e9d53e3 100644
--- a/tests/test_evaluation/test_metrics/test_iou_metric.py
+++ b/tests/test_evaluation/test_metrics/test_iou_metric.py
@@ -1,4 +1,6 @@
 # Copyright (c) OpenMMLab. All rights reserved.
+import os.path as osp
+import shutil
 from unittest import TestCase
 
 import numpy as np
@@ -58,6 +60,8 @@ def _demo_mm_model_output(self,
                 data=torch.randn(num_classes, h, w))
             data_sample['pred_sem_seg'] = dict(
                 data=torch.randint(0, num_classes, (1, h, w)))
+            data_sample[
+                'img_path'] = 'tests/data/pseudo_dataset/imgs/00000_img.jpg'
         return data_samples
 
     def test_evaluate(self):
@@ -72,5 +76,29 @@ def test_evaluate(self):
             label_map=dict(),
             reduce_zero_label=False)
         iou_metric.process([0] * len(data_samples), data_samples)
-        res = iou_metric.evaluate(6)
+        res = iou_metric.evaluate(2)
         self.assertIsInstance(res, dict)
+
+        # test save segment file in output_dir
+        iou_metric = IoUMetric(iou_metrics=['mIoU'], output_dir='tmp')
+        iou_metric.dataset_meta = dict(
+            classes=['wall', 'building', 'sky', 'floor', 'tree'],
+            label_map=dict(),
+            reduce_zero_label=False)
+        iou_metric.process([0] * len(data_samples), data_samples)
+        assert osp.exists('tmp')
+        assert osp.isfile('tmp/00000_img.png')
+        shutil.rmtree('tmp')
+
+        # test format_only
+        iou_metric = IoUMetric(
+            iou_metrics=['mIoU'], output_dir='tmp', format_only=True)
+        iou_metric.dataset_meta = dict(
+            classes=['wall', 'building', 'sky', 'floor', 'tree'],
+            label_map=dict(),
+            reduce_zero_label=False)
+        iou_metric.process([0] * len(data_samples), data_samples)
+        assert iou_metric.results == []
+        assert osp.exists('tmp')
+        assert osp.isfile('tmp/00000_img.png')
+        shutil.rmtree('tmp')
diff --git a/tools/test.py b/tools/test.py
index 7bfde58206..64da2bc261 100644
--- a/tools/test.py
+++ b/tools/test.py
@@ -17,6 +17,10 @@ def parse_args():
         '--work-dir',
         help=('if specified, the evaluation metric results will be dumped'
               'into the directory as json'))
+    parser.add_argument(
+        '--out',
+        type=str,
+        help='The directory to save output prediction for offline evaluation')
     parser.add_argument(
         '--show', action='store_true', help='show prediction results')
     parser.add_argument(
@@ -100,6 +104,11 @@ def main():
         cfg.tta_model.module = cfg.model
         cfg.model = cfg.tta_model
 
+    # add output_dir in metric
+    if args.out is not None:
+        cfg.test_evaluator['output_dir'] = args.out
+        cfg.test_evaluator['keep_results'] = True
+
     # build the runner from config
     runner = Runner.from_cfg(cfg)
 

From 1896344e04ad3a919194b394d44da4e0b69d026b Mon Sep 17 00:00:00 2001
From: Tianlong Ai <50650583+AI-Tianlong@users.noreply.github.com>
Date: Tue, 21 Mar 2023 21:33:40 +0800
Subject: [PATCH 22/32] [Docs] Update zh_CN faq.md (#2769)

As title #2750
---
 docs/zh_cn/notes/faq.md | 116 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 113 insertions(+), 3 deletions(-)

diff --git a/docs/zh_cn/notes/faq.md b/docs/zh_cn/notes/faq.md
index 09fde025fd..d90329cf22 100644
--- a/docs/zh_cn/notes/faq.md
+++ b/docs/zh_cn/notes/faq.md
@@ -1,8 +1,118 @@
-# 常见问题解答（FAQ）（待更新）
+# 常见问题解答（FAQ）
 
-我们在这里列出了使用时的一些常见问题及其相应的解决方案。 如果您发现有一些问题被遗漏，请随时提 PR 丰富这个列表。 如果您无法在此获得帮助，请使用 [issue模板](https://github.com/open-mmlab/mmsegmentation/blob/master/.github/ISSUE_TEMPLATE/error-report.md/)创建问题，但是请在模板中填写所有必填信息，这有助于我们更快定位问题。
+我们在这里列出了使用时的一些常见问题及其相应的解决方案。 如果您发现有一些问题被遗漏，请随时提 PR 丰富这个列表。 如果您无法在此获得帮助，请使用 [issue模板](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/.github/ISSUE_TEMPLATE/error-report.md/)创建问题，但是请在模板中填写所有必填信息，这有助于我们更快定位问题。
+
+## 安装
+
+兼容的MMSegmentation和MMCV版本如下。请安装正确版本的MMCV以避免安装问题。
+
+| MMSegmentation version |          MMCV version          | MMEngine version  | MMClassification (optional) version | MMDetection (optional) version |
+| :--------------------: | :----------------------------: | :---------------: | :---------------------------------: | :----------------------------: |
+|     dev-1.x branch     |        mmcv >= 2.0.0rc4        | MMEngine >= 0.5.0 |           mmcls>=1.0.0rc0           |       mmdet >= 3.0.0rc6        |
+|       1.x branch       |        mmcv >= 2.0.0rc4        | MMEngine >= 0.5.0 |           mmcls>=1.0.0rc0           |       mmdet >= 3.0.0rc6        |
+|        1.0.0rc6        |        mmcv >= 2.0.0rc4        | MMEngine >= 0.5.0 |           mmcls>=1.0.0rc0           |       mmdet >= 3.0.0rc6        |
+|        1.0.0rc5        |        mmcv >= 2.0.0rc4        | MMEngine >= 0.2.0 |           mmcls>=1.0.0rc0           |        mmdet>=3.0.0rc6         |
+|        1.0.0rc4        |        mmcv == 2.0.0rc3        | MMEngine >= 0.1.0 |           mmcls>=1.0.0rc0           |  mmdet>=3.0.0rc4, \<=3.0.0rc5  |
+|        1.0.0rc3        |        mmcv == 2.0.0rc3        | MMEngine >= 0.1.0 |           mmcls>=1.0.0rc0           |  mmdet>=3.0.0rc4  \<=3.0.0rc5  |
+|        1.0.0rc2        |        mmcv == 2.0.0rc3        | MMEngine >= 0.1.0 |           mmcls>=1.0.0rc0           |  mmdet>=3.0.0rc4  \<=3.0.0rc5  |
+|        1.0.0rc1        | mmcv >= 2.0.0rc1, \<=2.0.0rc3> | MMEngine >= 0.1.0 |           mmcls>=1.0.0rc0           |          Not required          |
+|        1.0.0rc0        | mmcv >= 2.0.0rc1, \<=2.0.0rc3> | MMEngine >= 0.1.0 |           mmcls>=1.0.0rc0           |          Not required          |
+
+如果您已经安装了版本不合适的 mmcv，请先运行`pip uninstall mmcv`卸载已安装的 mmcv，如您先前安装的为 mmcv-full(存在于 OpenMMLab 1.x),请运行`pip uninstall mmcv-full`进行卸载。
+
+- 如出现"No module named 'mmcv'";
+  1. 使用`pip uninstall mmcv`卸载环境中现有的mmcv。
+  2. 按照[安装说明](../get_started#best-practices)安装对应的mmcv。
 
 ## 如何获知模型训练时需要的显卡数量
 
-- 看模型的config文件的命名。可以参考[学习配置文件](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/zh_cn/tutorials/config.md)中的`配置文件命名风格`部分。比如，对于名字为`segformer_mit-b0_8x1_1024x1024_160k_cityscapes.py`的config文件，`8x1`代表训练其对应的模型需要的卡数为8，每张卡中的batch size为1。
+- 看模型的config文件的命名。可以参考[学习配置文件](../user_guides/1_config.md)中的`配置文件命名风格`部分。比如，对于名字为`segformer_mit-b0_8xb1-160k_cityscapes-1024x1024.py`的config文件，`8xb1`代表训练其对应的模型需要的卡数为8，每张卡中的batch size为1。
 - 看模型的log文件。点开该模型的log文件，并在其中搜索`nGPU`，在`nGPU`后的数字个数即训练时所需的卡数。比如，在log文件中搜索`nGPU`得到`nGPU 0,1,2,3,4,5,6,7`的记录，则说明训练该模型需要使用八张卡。
+
+## auxiliary head 是什么
+
+简单来说，这是一个提高准确率的深度监督技术。在训练阶段，`decode_head` 用于输出语义分割的结果，`auxiliary_head` 只是增加了一个辅助损失，其产生的分割结果对你的模型结果没有影响，仅在在训练中起作用。您可以阅读这篇[论文](https://arxiv.org/pdf/1612.01105.pdf)了解更多信息。
+
+## 运行测试脚本时如何输出绘制分割掩膜的图像
+
+在测试脚本中，我们提供了`--out`参数来控制是否输出保存预测的分割掩膜图像。您可以运行以下命令输出测试结果:
+
+```shell
+python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} --out ${OUTPUT_DIR}
+```
+
+更多用例细节可查阅[文档](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/user_guides/4_train_test.md#%E6%B5%8B%E8%AF%95%E5%B9%B6%E4%BF%9D%E5%AD%98%E5%88%86%E5%89%B2%E7%BB%93%E6%9E%9C)，[PR #2712](https://github.com/open-mmlab/mmsegmentation/pull/2712)以及[迁移文档](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/migration/interface.md#%E6%B5%8B%E8%AF%95%E5%90%AF%E5%8A%A8)了解相关说明
+
+## 如何处理二值分割任务?
+
+MMSegmentation 使用 `num_classes` 和 `out_channels` 来控制模型最后一层 `self.conv_seg` 的输出. 更多细节可以参考 [这里](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/decode_heads/decode_head.py).
+
+`num_classes` 应该和数据集本身类别个数一致，当是二值分割时，数据集只有前景和背景两类, 所以 `num_classes` 为 2. `out_channels` 控制模型最后一层的输出的通道数，通常和 `num_classes` 相等, 但当二值分割时候, 可以有两种处理方法, 分别是：
+
+- 设置 `out_channels=2`, 在训练时以 Cross Entropy Loss 作为损失函数, 在推理时使用 `F.softmax()` 归一化 logits 值, 然后通过 `argmax()` 得到每个像素的预测结果.
+
+- 设置 `out_channels=1`, 在训练时以 Binary Cross Entropy Loss 作为损失函数, 在推理时使用 `F.sigmoid()` 和 `threshold` 得到预测结果, `threshold` 默认为 0.3.
+
+对于实现上述两种计算二值分割的方法, 需要在 `decode_head` 和 `auxiliary_head` 的配置里修改. 下面是对样例 [pspnet_unet_s5-d16.py](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/models/pspnet_unet_s5-d16.py) 做出的对应修改.
+
+- (1) `num_classes=2`, `out_channels=2` 并在 `CrossEntropyLoss` 里面设置 `use_sigmoid=False`.
+
+```python
+decode_head=dict(
+    type='PSPHead',
+    in_channels=64,
+    in_index=4,
+    num_classes=2,
+    out_channels=2,
+    loss_decode=dict(
+        type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+auxiliary_head=dict(
+    type='FCNHead',
+    in_channels=128,
+    in_index=3,
+    num_classes=2,
+    out_channels=2,
+    loss_decode=dict(
+        type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+```
+
+- (2) `num_classes=2`, `out_channels=1` 并在 `CrossEntropyLoss` 里面设置 `use_sigmoid=True`.
+
+```python
+decode_head=dict(
+    type='PSPHead',
+    in_channels=64,
+    in_index=4,
+    num_classes=2,
+    out_channels=1,
+    loss_decode=dict(
+        type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)),
+auxiliary_head=dict(
+    type='FCNHead',
+    in_channels=128,
+    in_index=3,
+    num_classes=2,
+    out_channels=1,
+    loss_decode=dict(
+        type='CrossEntropyLoss', use_sigmoid=True, loss_weight=0.4)),
+```
+
+## `reduce_zero_label` 的作用
+
+数据集中 `reduce_zero_label` 参数类型为布尔类型, 默认为 False, 它的功能是为了忽略数据集 label 0. 具体做法是将 label 0 改为 255, 其余 label 相应编号减 1, 同时 decode head 里将 255 设为 ignore index, 即不参与 loss 计算.
+以下是 `reduce_zero_label` 具体实现逻辑:
+
+```python
+if self.reduce_zero_label:
+    # avoid using underflow conversion
+    gt_semantic_seg[gt_semantic_seg == 0] = 255
+    gt_semantic_seg = gt_semantic_seg - 1
+    gt_semantic_seg[gt_semantic_seg == 254] = 255
+```
+
+关于您的数据集是否需要使用reduce_zero_label，有以下两类情况：
+
+- 例如在Potsdam数据集上，有 0-不透水面、1-建筑、2-低矮植被、3-树、4-汽车、5-杂乱，六类。但该数据集提供了两种RGB标签，一种为图像边缘处有黑色像素的标签，另一种是没有黑色边缘的标签。对于有黑色边缘的标签，在 [dataset_converters.py](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/tools/dataset_converters/potsdam.py)中，其将黑色边缘转换为label 0，其余标签分别为 1-不透水面、2-建筑、3-低矮植被、4-树、5-汽车、6-杂乱，那么此时，就应该在数据集[potsdam.py](https://github.com/open-mmlab/mmsegmentation/blob/ff95416c3b5ce8d62b9289f743531398efce534f/mmseg/datasets/potsdam.py#L23)中将`reduce_zero_label=True`。如果使用的是没有黑色边缘的标签，那么mask label中只有0-5，此时就应该使`reduce_zero_label=False`。需要结合您的实际情况来使用。
+- 例如在第0类为background类别的数据集上，如果您最终是需要将背景和您的其余类别分开时，是不需要使用`reduce_zero_label`的，此时在数据集中应该将其设置为`reduce_zero_label=False`
+
+**注意:** 使用 `reduce_zero_label` 请确认数据集原始类别个数, 如果只有两类, 需要关闭 `reduce_zero_label` 即设置 `reduce_zero_label=False`.

From 1ea397509e6498c3a4142438941f067283374ebd Mon Sep 17 00:00:00 2001
From: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
Date: Wed, 22 Mar 2023 14:37:54 +0800
Subject: [PATCH 23/32] [Doc] Refine training tricks documentation (#2755)

---
 docs/en/advanced_guides/training_tricks.md    | 43 ++++++----------
 docs/zh_cn/advanced_guides/training_tricks.md | 49 ++++++-------------
 2 files changed, 28 insertions(+), 64 deletions(-)

diff --git a/docs/en/advanced_guides/training_tricks.md b/docs/en/advanced_guides/training_tricks.md
index 8fa89131d5..bc4f72257d 100644
--- a/docs/en/advanced_guides/training_tricks.md
+++ b/docs/en/advanced_guides/training_tricks.md
@@ -1,4 +1,4 @@
-# \[WIP\] Training Tricks
+# Training Tricks
 
 MMSegmentation support following training tricks out of box.
 
@@ -9,18 +9,19 @@ In semantic segmentation, some methods make the LR of heads larger than backbone
 In MMSegmentation, you may add following lines to config to make the LR of heads 10 times of backbone.
 
 ```python
-optimizer=dict(
+optim_wrapper=dict(
     paramwise_cfg = dict(
         custom_keys={
             'head': dict(lr_mult=10.)}))
 ```
 
 With this modification, the LR of any parameter group with `'head'` in name will be multiplied by 10.
-You may refer to [MMCV doc](https://mmcv.readthedocs.io/en/latest/api.html#mmcv.runner.DefaultOptimizerConstructor) for further details.
+You may refer to [MMEngine documentation](https://mmengine.readthedocs.io/en/latest/tutorials/optim_wrapper.html#advanced-usages) for further details.
 
 ## Online Hard Example Mining (OHEM)
 
-We implement pixel sampler [here](https://github.com/open-mmlab/mmsegmentation/tree/master/mmseg/core/seg/sampler) for training sampling.
+We implement pixel sampler for training sampling, like OHEM (Online Hard Example Mining),
+which is used for remove the "easy" examples for model training.
 Here is an example config of training PSPNet with OHEM enabled.
 
 ```python
@@ -58,33 +59,17 @@ For loss calculation, we support multiple losses training concurrently. Here is
 ```python
 _base_ = './fcn_unet_s5-d16_64x64_40k_drive.py'
 model = dict(
-    decode_head=dict(loss_decode=[dict(type='CrossEntropyLoss', loss_name='loss_ce', loss_weight=1.0),
-            dict(type='DiceLoss', loss_name='loss_dice', loss_weight=3.0)]),
-    auxiliary_head=dict(loss_decode=[dict(type='CrossEntropyLoss', loss_name='loss_ce',loss_weight=1.0),
-            dict(type='DiceLoss', loss_name='loss_dice', loss_weight=3.0)]),
-    )
+    decode_head=dict(loss_decode=[
+        dict(type='CrossEntropyLoss', loss_name='loss_ce', loss_weight=1.0),
+        dict(type='DiceLoss', loss_name='loss_dice', loss_weight=3.0)
+    ]),
+    auxiliary_head=dict(loss_decode=[
+        dict(type='CrossEntropyLoss', loss_name='loss_ce', loss_weight=1.0),
+        dict(type='DiceLoss', loss_name='loss_dice', loss_weight=3.0)
+    ]),
+)
 ```
 
 In this way, `loss_weight` and `loss_name` will be weight and name in training log of corresponding loss, respectively.
 
 Note: If you want this loss item to be included into the backward graph, `loss_` must be the prefix of the name.
-
-## Ignore specified label index in loss calculation
-
-In default setting, `avg_non_ignore=False` which means each pixel counts for loss calculation although some of them belong to ignore-index labels.
-
-For loss calculation, we support ignore index of certain label by `avg_non_ignore` and `ignore_index`. In this way, the average loss would only be calculated in non-ignored labels which may achieve better performance, and here is the [reference](https://github.com/open-mmlab/mmsegmentation/pull/1409). Here is an example config of training `unet` on `Cityscapes` dataset: in loss calculation it would ignore label 0 which is background and loss average is only calculated on non-ignore labels:
-
-```python
-_base_ = './unet-s5-d16_fcn_4xb4-160k_cityscapes-512x1024.py'
-model = dict(
-    decode_head=dict(
-        ignore_index=0,
-        loss_decode=dict(
-            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0, avg_non_ignore=True),
-    auxiliary_head=dict(
-        ignore_index=0,
-        loss_decode=dict(
-            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0, avg_non_ignore=True)),
-    ))
-```
diff --git a/docs/zh_cn/advanced_guides/training_tricks.md b/docs/zh_cn/advanced_guides/training_tricks.md
index a33c0ea9cf..e5b8e4dae1 100644
--- a/docs/zh_cn/advanced_guides/training_tricks.md
+++ b/docs/zh_cn/advanced_guides/training_tricks.md
@@ -1,4 +1,4 @@
-# 训练技巧（待更新）
+# 训练技巧
 
 MMSegmentation 支持如下训练技巧：
 
@@ -9,17 +9,17 @@ MMSegmentation 支持如下训练技巧：
 在 MMSegmentation 里面，您也可以在配置文件里添加如下行来让解码头组件的学习率是主干组件的10倍。
 
 ```python
-optimizer=dict(
+optim_wrapper=dict(
     paramwise_cfg = dict(
         custom_keys={
             'head': dict(lr_mult=10.)}))
 ```
 
-通过这种修改，任何被分组到 `'head'` 的参数的学习率都将乘以10。您也可以参照 [MMCV 文档](https://mmcv.readthedocs.io/en/latest/api.html#mmcv.runner.DefaultOptimizerConstructor)  获取更详细的信息。
+通过这种修改，任何被分组到 `'head'` 的参数的学习率都将乘以10。您也可以参照 [MMEngine 文档](https://mmengine.readthedocs.io/zh_CN/latest/tutorials/optim_wrapper.html#id6)  获取更详细的信息。
 
 ## 在线难样本挖掘 (Online Hard Example Mining, OHEM)
 
-对于训练时采样，我们在 [这里](https://github.com/open-mmlab/mmsegmentation/tree/master/mmseg/core/seg/sampler) 做了像素采样器。
+MMSegmentation 中实现了像素采样器，训练时可以对特定像素进行采样，例如 OHEM(Online Hard Example Mining)，可以解决样本不平衡问题，
 如下例子是使用 PSPNet 训练并采用 OHEM 策略的配置：
 
 ```python
@@ -58,38 +58,17 @@ model=dict(
 ```python
 _base_ = './fcn_unet_s5-d16_64x64_40k_drive.py'
 model = dict(
-    decode_head=dict(loss_decode=[dict(type='CrossEntropyLoss', loss_name='loss_ce', loss_weight=1.0),
-            dict(type='DiceLoss', loss_name='loss_dice', loss_weight=3.0)]),
-    auxiliary_head=dict(loss_decode=[dict(type='CrossEntropyLoss', loss_name='loss_ce',loss_weight=1.0),
-            dict(type='DiceLoss', loss_name='loss_dice', loss_weight=3.0)]),
-    )
+    decode_head=dict(loss_decode=[
+        dict(type='CrossEntropyLoss', loss_name='loss_ce', loss_weight=1.0),
+        dict(type='DiceLoss', loss_name='loss_dice', loss_weight=3.0)
+    ]),
+    auxiliary_head=dict(loss_decode=[
+        dict(type='CrossEntropyLoss', loss_name='loss_ce', loss_weight=1.0),
+        dict(type='DiceLoss', loss_name='loss_dice', loss_weight=3.0)
+    ]),
+)
 ```
 
 通过这种方式，确定训练过程中损失函数的权重 `loss_weight` 和在训练日志里的名字 `loss_name`。
 
-注意： `loss_name` 的名字必须带有 `loss_` 前缀，这样它才能被包括在反传的图里。
-
-## 在损失函数中忽略特定的 label 类别
-
-默认设置 `avg_non_ignore=False`， 即每个像素都用来计算损失函数。尽管其中的一些像素属于需要被忽略的类别。
-
-对于训练时损失函数的计算，我们目前支持使用 `avg_non_ignore` 和 `ignore_index` 来忽略 label 特定的类别。 这样损失函数将只在非忽略类别像素中求平均值，会获得更好的表现。这里是[相关 PR](https://github.com/open-mmlab/mmsegmentation/pull/1409)。以 `unet` 使用 `Cityscapes` 数据集训练为例，
-在计算损失函数时，忽略 label 为0的背景，并且仅在不被忽略的像素上计算均值。配置文件写为:
-
-```python
-_base_ = './fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes.py'
-model = dict(
-    decode_head=dict(
-        ignore_index=0,
-        loss_decode=dict(
-            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0, avg_non_ignore=True),
-    auxiliary_head=dict(
-        ignore_index=0,
-        loss_decode=dict(
-            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0, avg_non_ignore=True)),
-    ))
-```
-
-通过这种方式，确定训练过程中损失函数的权重 `loss_weight` 和在训练日志里的名字 `loss_name`。
-
-注意： `loss_name` 的名字必须带有 `loss_` 前缀，这样它才能被包括在反传的图里。
+注意： `loss_name` 的名字必须带有 `loss_` 前缀，这样它才能被包括在计算图里。

From 3c26531e699c3977f2f9267f79cd7551de88c244 Mon Sep 17 00:00:00 2001
From: CSH <40987381+csatsurnh@users.noreply.github.com>
Date: Thu, 23 Mar 2023 15:42:16 +0800
Subject: [PATCH 24/32] [Doc] Update add_datasets docs (#2745)

---
 docs/en/advanced_guides/add_datasets.md    | 103 +++++++----
 docs/zh_cn/advanced_guides/add_datasets.md | 194 ++++++++++-----------
 2 files changed, 165 insertions(+), 132 deletions(-)

diff --git a/docs/en/advanced_guides/add_datasets.md b/docs/en/advanced_guides/add_datasets.md
index f33f3d32c6..fbfa36940c 100644
--- a/docs/en/advanced_guides/add_datasets.md
+++ b/docs/en/advanced_guides/add_datasets.md
@@ -1,4 +1,62 @@
-# \[WIP\] Add New Datasets
+# Add New Datasets
+
+## Add new custom dataset
+
+Here we show how to develop a new custom dataset.
+
+1. Create a new file `mmseg/datasets/example.py`
+
+   ```python
+   from mmseg.registry import DATASETS
+   from .basesegdataset import BaseSegDataset
+
+
+   @DATASETS.register_module()
+   class ExampleDataset(BaseSegDataset):
+
+       METAINFO = dict(
+           classes=('xxx', 'xxx', ...),
+           palette=[[x, x, x], [x, x, x], ...])
+
+       def __init__(self, aeg1, arg2):
+           pass
+   ```
+
+2. Import the module in `mmseg/datasets/__init__.py`
+
+   ```python
+   from .example import ExampleDataset
+   ```
+
+3. Use it by creating a new new dataset config file `configs/_base_/datasets/example_dataset.py`
+
+   ```python
+   dataset_type = 'ExampleDataset'
+   data_root = 'data/example/'
+   ...
+   ```
+
+4. Add dataset meta information in `mmseg/utils/class_names.py`
+
+   ```python
+   def example_classes():
+       return [
+           'xxx', 'xxx',
+           ...
+       ]
+
+   def example_palette():
+       return [
+           [x, x, x], [x, x, x],
+           ...
+       ]
+   dataset_aliases ={
+       'example': ['example', ...],
+       ...
+   }
+   ```
+
+**Note:** If the new dataset does not satisfy the mmseg requirements, a data preprocessing script needs to be prepared in `tools/dataset_converters/`
 
 ## Customize datasets by reorganizing data
 
@@ -26,26 +84,12 @@ An example of file structure is as followed.
 
 A training pair will consist of the files with same suffix in img_dir/ann_dir.
 
-If `split` argument is given, only part of the files in img_dir/ann_dir will be loaded.
-We may specify the prefix of files we would like to be included in the split txt.
+Some datasets don't release the test set or don't release the ground truth of the test set, and we cannot evaluate models locally without the ground truth of the test set, so we set the validation set as the default test set in config files.
 
-More specifically, for a split txt like following,
+About how to build your own datasets or implement a new dataset class please refer to the [datasets guide](./datasets.md) for more detailed information.
 
-```none
-xxx
-zzz
-```
-
-Only
-`data/my_dataset/img_dir/train/xxx{img_suffix}`,
-`data/my_dataset/img_dir/train/zzz{img_suffix}`,
-`data/my_dataset/ann_dir/train/xxx{seg_map_suffix}`,
-`data/my_dataset/ann_dir/train/zzz{seg_map_suffix}` will be loaded.
-
-:::{note}
-The annotations are images of shape (H, W), the value pixel should fall in range `[0, num_classes - 1]`.
+**Note:** The annotations are images of shape (H, W), the value pixel should fall in range `[0, num_classes - 1]`.
 You may use `'P'` mode of [pillow](https://pillow.readthedocs.io/en/stable/handbook/concepts.html#palette) to create your annotation image with color.
-:::
 
 ## Customize datasets by mixing dataset
 
@@ -59,14 +103,14 @@ For example, suppose the original dataset is `Dataset_A`, to repeat it, the conf
 
 ```python
 dataset_A_train = dict(
-        type='RepeatDataset',
-        times=N,
-        dataset=dict(  # This is the original config of Dataset_A
-            type='Dataset_A',
-            ...
-            pipeline=train_pipeline
-        )
+    type='RepeatDataset',
+    times=N,
+    dataset=dict(  # This is the original config of Dataset_A
+        type='Dataset_A',
+        ...
+        pipeline=train_pipeline
     )
+)
 ```
 
 ### Concatenate dataset
@@ -111,7 +155,9 @@ dataset_B_train = dict(
     )
 )
 train_dataloader = dict(
-    dataset=dict('ConcatDataset', datasets=[dataset_A_train, dataset_B_train]))
+    dataset=dict(
+        type='ConcatDataset',
+        datasets=[dataset_A_train, dataset_B_train]))
 
 val_dataloader = dict(dataset=dataset_A_val)
 test_dataloader = dict(dataset=dataset_A_test)
@@ -123,8 +169,7 @@ You can refer base dataset [tutorial](https://mmengine.readthedocs.io/en/latest/
 ### Multi-image Mix Dataset
 
 We use `MultiImageMixDataset` as a wrapper to mix images from multiple datasets.
-`MultiImageMixDataset` can be used by multiple images mixed data augmentation
-like mosaic and mixup.
+`MultiImageMixDataset` can be used by multiple images mixed data augmentation like mosaic and mixup.
 
 An example of using `MultiImageMixDataset` with `Mosaic` data augmentation:
 
@@ -139,8 +184,6 @@ train_pipeline = [
 train_dataset = dict(
     type='MultiImageMixDataset',
     dataset=dict(
-        classes=classes,
-        palette=palette,
         type=dataset_type,
         reduce_zero_label=False,
         img_dir=data_root + "images/train",
diff --git a/docs/zh_cn/advanced_guides/add_datasets.md b/docs/zh_cn/advanced_guides/add_datasets.md
index 4ea14934ed..22fbf3462f 100644
--- a/docs/zh_cn/advanced_guides/add_datasets.md
+++ b/docs/zh_cn/advanced_guides/add_datasets.md
@@ -1,4 +1,62 @@
-# 新增自定义数据集（待更新）
+# 新增自定义数据集
+
+## 新增自定义数据集
+
+在这里，我们展示如何构建一个新的数据集。
+
+1. 创建一个新文件 `mmseg/datasets/example.py`
+
+   ```python
+   from mmseg.registry import DATASETS
+   from .basesegdataset import BaseSegDataset
+
+
+   @DATASETS.register_module()
+   class ExampleDataset(BaseSegDataset):
+
+       METAINFO = dict(
+           classes=('xxx', 'xxx', ...),
+           palette=[[x, x, x], [x, x, x], ...])
+
+       def __init__(self, aeg1, arg2):
+           pass
+   ```
+
+2. 在 `mmseg/datasets/__init__.py` 中导入模块
+
+   ```python
+   from .example import ExampleDataset
+   ```
+
+3. 通过创建一个新的数据集配置文件 `configs/_base_/datasets/example_dataset.py` 来使用它
+
+   ```python
+   dataset_type = 'ExampleDataset'
+   data_root = 'data/example/'
+   ...
+   ```
+
+4. 在 `mmseg/utils/class_names.py` 中补充数据集元信息
+
+   ```python
+   def example_classes():
+       return [
+           'xxx', 'xxx',
+           ...
+       ]
+
+   def example_palette():
+       return [
+           [x, x, x], [x, x, x],
+           ...
+       ]
+   dataset_aliases ={
+       'example': ['example', ...],
+       ...
+   }
+   ```
+
+**注意：** 如果新数据集不满足 mmseg 的要求，则需要在 `tools/dataset_converters/` 中准备一个数据集预处理脚本
 
 ## 通过重新组织数据来定制数据集
 
@@ -26,30 +84,17 @@
 
 一个训练对将由 img_dir/ann_dir 里同样首缀的文件组成。
 
-如果给定 `split` 参数，只有部分在 img_dir/ann_dir 里的文件会被加载。
-我们可以对被包括在 split 文本里的文件指定前缀。
+有些数据集不会发布测试集或测试集的标注，如果没有测试集的标注，我们就无法在本地进行评估模型，因此我们在配置文件中将验证集设置为默认测试集。
 
-除此以外，一个 split 文本如下所示：
-
-```none
-xxx
-zzz
-```
+关于如何构建自己的数据集或实现新的数据集类，请参阅[数据集指南](./datasets.md)以获取更多详细信息。
 
-只有
-
-`data/my_dataset/img_dir/train/xxx{img_suffix}`,
-`data/my_dataset/img_dir/train/zzz{img_suffix}`,
-`data/my_dataset/ann_dir/train/xxx{seg_map_suffix}`,
-`data/my_dataset/ann_dir/train/zzz{seg_map_suffix}` 将被加载。
-
-注意：标注是跟图像同样的形状 (H, W)，其中的像素值的范围是 `[0, num_classes - 1]`。
+**注意：** 标注是跟图像同样的形状 (H, W)，其中的像素值的范围是 `[0, num_classes - 1]`。
 您也可以使用 [pillow](https://pillow.readthedocs.io/en/stable/handbook/concepts.html#palette) 的 `'P'` 模式去创建包含颜色的标注。
 
 ## 通过混合数据去定制数据集
 
 MMSegmentation 同样支持混合数据集去训练。
-当前它支持拼接 (concat), 重复 (repeat) 和多图混合 (multi-image mix)数据集。
+当前它支持拼接 (concat), 重复 (repeat) 和多图混合 (multi-image mix) 数据集。
 
 ### 重复数据集
 
@@ -58,79 +103,29 @@ MMSegmentation 同样支持混合数据集去训练。
 
 ```python
 dataset_A_train = dict(
-        type='RepeatDataset',
-        times=N,
-        dataset=dict(  # 这是 Dataset_A 数据集的原始配置
-            type='Dataset_A',
-            ...
-            pipeline=train_pipeline
-        )
+    type='RepeatDataset',
+    times=N,
+    dataset=dict(  # 这是 Dataset_A 数据集的原始配置
+        type='Dataset_A',
+        ...
+        pipeline=train_pipeline
     )
+)
 ```
 
 ### 拼接数据集
 
-有2种方式去拼接数据集。
-
-1. 如果您想拼接的数据集是同样的类型，但有不同的标注文件，
-   您可以按如下操作去拼接数据集的配置文件：
-
-   1. 您也许可以拼接两个标注文件夹 `ann_dir`
-
-      ```python
-      dataset_A_train = dict(
-          type='Dataset_A',
-          img_dir = 'img_dir',
-          ann_dir = ['anno_dir_1', 'anno_dir_2'],
-          pipeline=train_pipeline
-      )
-      ```
-
-   2. 您也可以去拼接两个 `split` 文件列表
-
-      ```python
-      dataset_A_train = dict(
-          type='Dataset_A',
-          img_dir = 'img_dir',
-          ann_dir = 'anno_dir',
-          split = ['split_1.txt', 'split_2.txt'],
-          pipeline=train_pipeline
-      )
-      ```
+如果要拼接不同的数据集，可以按如下方式连接数据集配置。
 
-   3. 您也可以同时拼接 `ann_dir` 文件夹和 `split` 文件列表
-
-      ```python
-      dataset_A_train = dict(
-          type='Dataset_A',
-          img_dir = 'img_dir',
-          ann_dir = ['anno_dir_1', 'anno_dir_2'],
-          split = ['split_1.txt', 'split_2.txt'],
-          pipeline=train_pipeline
-      )
-      ```
-
-      在这样的情况下， `ann_dir_1` 和 `ann_dir_2` 分别对应于 `split_1.txt` 和 `split_2.txt`
-
-2. 如果您想拼接不同的数据集，您可以如下去拼接数据集的配置文件：
-
-   ```python
-   dataset_A_train = dict()
-   dataset_B_train = dict()
-
-   data = dict(
-       imgs_per_gpu=2,
-       workers_per_gpu=2,
-       train = [
-           dataset_A_train,
-           dataset_B_train
-       ],
-       val = dataset_A_val,
-       test = dataset_A_test
-       )
-   ```
+```python
+dataset_A_train = dict()
+dataset_B_train = dict()
+concatenate_dataset = dict(
+    type='ConcatDataset',
+    datasets=[dataset_A_train, dataset_B_train])
+```
 
-一个更复杂的例子如下：分别重复 `Dataset_A` 和 `Dataset_B` N 次和 M 次，然后再去拼接重复后的数据集
+下面是一个更复杂的示例，它分别重复 `Dataset_A` 和 `Dataset_B` N 次和 M 次，然后连接重复的数据集。
 
 ```python
 dataset_A_train = dict(
@@ -159,41 +154,36 @@ dataset_B_train = dict(
         pipeline=train_pipeline
     )
 )
-data = dict(
-    imgs_per_gpu=2,
-    workers_per_gpu=2,
-    train = [
-        dataset_A_train,
-        dataset_B_train
-    ],
-    val = dataset_A_val,
-    test = dataset_A_test
-)
+train_dataloader = dict(
+    dataset=dict(
+        type='ConcatDataset',
+        datasets=[dataset_A_train, dataset_B_train]))
+
+val_dataloader = dict(dataset=dataset_A_val)
+test_dataloader = dict(dataset=dataset_A_test)
 
 ```
 
+您可以参考 mmengine 的基础数据集[教程](https://mmengine.readthedocs.io/zh_CN/latest/advanced_tutorials/basedataset.html)以了解更多详细信息
+
 ### 多图混合集
 
-我们使用 `MultiImageMixDataset` 作为包装(wrapper)去混合多个数据集的图片。
-`MultiImageMixDataset`可以被类似mosaic和mixup的多图混合数据増广使用。
+我们使用 `MultiImageMixDataset` 作为包装（wrapper）去混合多个数据集的图片。
+`MultiImageMixDataset`可以被类似 mosaic 和 mixup 的多图混合数据増广使用。
 
-`MultiImageMixDataset`与`Mosaic`数据増广一起使用的例子：
+`MultiImageMixDataset` 与 `Mosaic` 数据増广一起使用的例子：
 
 ```python
 train_pipeline = [
     dict(type='RandomMosaic', prob=1),
     dict(type='Resize', img_scale=(1024, 512), keep_ratio=True),
     dict(type='RandomFlip', prob=0.5),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
+    dict(type='PackSegInputs')
 ]
 
 train_dataset = dict(
     type='MultiImageMixDataset',
     dataset=dict(
-        classes=classes,
-        palette=palette,
         type=dataset_type,
         reduce_zero_label=False,
         img_dir=data_root + "images/train",

From 1dd65813f996c910a73c61cf01c3e474a0bc1a03 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E8=B0=A2=E6=98=95=E8=BE=B0?= <xiexinch@outlook.com>
Date: Thu, 30 Mar 2023 14:19:13 +0800
Subject: [PATCH 25/32] [Doc] Add English version document of the Training
 Engine (#2797)

---
 docs/en/advanced_guides/engine.md    | 280 ++++++++++++++++++++++++++-
 docs/zh_cn/advanced_guides/engine.md |  12 +-
 2 files changed, 286 insertions(+), 6 deletions(-)

diff --git a/docs/en/advanced_guides/engine.md b/docs/en/advanced_guides/engine.md
index eaa55b0c8c..0ed08fa4b5 100644
--- a/docs/en/advanced_guides/engine.md
+++ b/docs/en/advanced_guides/engine.md
@@ -1 +1,279 @@
-# Engine
+# Training Engine
+
+MMEngine defined some [basic loop controllers](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/loops.py) such as epoch-based training loop (`EpochBasedTrainLoop`), iteration-based training loop (`IterBasedTrainLoop`), standard validation loop (`ValLoop`), and standard testing loop (`TestLoop`).
+
+OpenMMLab's algorithm libraries like MMSegmentation abstract model training, testing, and inference as `Runner` to handle. Users can use the default `Runner` in MMEngine directly or modify the `Runner` to meet customized needs. This document mainly introduces how users can configure existing running settings, hooks, and optimizers' basic concepts and usage methods.
+
+## Configuring Runtime Settings
+
+### Configuring Training Iterations
+
+Loop controllers refer to the execution process during training, validation, and testing. `train_cfg`, `val_cfg`, and `test_cfg` are used to build these processes in the configuration file. MMSegmentation sets commonly used training iterations in `train_cfg` under the `configs/_base_/schedules` folder.
+For example, to train for 80,000 iterations using the iteration-based training loop (`IterBasedTrainLoop`) and perform validation every 8,000 iterations, you can set it as follows:
+
+```python
+train_cfg = dict(type='IterBasedTrainLoop', max_iters=80000, val_interval=8000)
+```
+
+### Configuring Training Optimizers
+
+Here's an example of a SGD optimizer:
+
+```python
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005),
+    clip_grad=None)
+```
+
+OpenMMLab supports all optimizers in PyTorch. For more details, please refer to the [MMEngine optimizer documentation](https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/optim_wrapper.md).
+
+It is worth emphasizing that `optim_wrapper` is a variable of `runner`, so when configuring the optimizer, the field to configure is the `optim_wrapper` field. For more information on using optimizers, see the [Optimizer](#Optimizer) section below.
+
+### Configuring Training Parameter Schedulers
+
+Before configuring the training parameter scheduler, it is recommended to first understand the basic concepts of parameter schedulers in the [MMEngine documentation](https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md).
+
+Here's an example of a parameter scheduler. During training, a linearly changing learning rate strategy is used for warm-up in the first 1,000 iterations. After the first 1,000 iterations until the 16,000 iterations in the end, the default polynomial learning rate decay is used:
+
+```python
+param_scheduler = [
+    dict(type='LinearLR', by_epoch=False, start_factor=0.1, begin=0, end=1000),
+    dict(
+        type='PolyLR',
+        eta_min=1e-4,
+        power=0.9,
+        begin=1000,
+        end=160000,
+        by_epoch=False,
+    )
+]
+```
+
+Note: When modifying the `max_iters` in `train_cfg`, make sure the parameters in the parameter scheduler `param_scheduler` are also modified accordingly.
+
+## Hook
+
+### Introduction
+
+OpenMMLab abstracts the model training and testing process as `Runner`. Inserting hooks can implement the corresponding functionality needed at different training and testing stages (such as "before and after each training iter", "before and after each validation iter", etc.) in `Runner`. For more introduction on hook mechanisms, please refer to [here](https://www.calltutors.com/blog/what-is-hook).
+
+Hooks used in `Runner` are divided into two categories:
+
+- Default hooks:
+
+They implement essential functions during training and are defined in the configuration file by `default_hooks` and passed to `Runner`. `Runner` registers them through the [`register_default_hooks`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/runner.py#L1780) method.
+
+Hooks have corresponding priorities; the higher the priority, the earlier the runner calls them. If the priorities are the same, the calling order is consistent with the hook registration order.
+
+It is not recommended for users to modify the default hook priorities. Please refer to the [MMEngine hooks documentation](https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/hook.md) to understand the hook priority definitions.
+
+The following are the default hooks used in MMSegmentation:
+
+|                                                           Hook                                                            |                                                          Function                                                          |     Priority      |
+| :-----------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------: | :---------------: |
+|            [IterTimerHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/iter_timer_hook.py)            |                                          Record the time spent on each iteration.                                          |    NORMAL (50)    |
+|               [LoggerHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/logger_hook.py)                | Collect log records from different components in `Runner` and output them to terminal, JSON file, tensorboard, wandb, etc. | BELOW_NORMAL (60) |
+|       [ParamSchedulerHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/param_scheduler_hook.py)       |                       Update some hyperparameters in the optimizer, such as learning rate momentum.                        |     LOW (70)      |
+|           [CheckpointHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/checkpoint_hook.py)            |                                              Regularly save checkpoint files.                                              |   VERY_LOW (90)   |
+|        [DistSamplerSeedHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/sampler_seed_hook.py)        |                                     Ensure the distributed sampler shuffle is enabled.                                     |    NORMAL (50)    |
+| [SegVisualizationHook](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/visualization/local_visualizer.py) |                                Visualize prediction results during validation and testing.                                 |    NORMAL (50)    |
+
+MMSegmentation registers some hooks with essential training functions in `default_hooks`:
+
+```python
+default_hooks = dict(
+    timer=dict(type='IterTimerHook'),
+    logger=dict(type='LoggerHook', interval=50, log_metric_by_epoch=False),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    checkpoint=dict(type='CheckpointHook', by_epoch=False, interval=32000),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    visualization=dict(type='SegVisualizationHook'))
+```
+
+All the default hooks mentioned above, except for `SegVisualizationHook`, are implemented in MMEngine. The `SegVisualizationHook` is a hook implemented in MMSegmentation, which will be introduced later.
+
+- Modifying default hooks
+
+We will use the `logger` and `checkpoint` in `default_hooks` as examples to demonstrate how to modify the default hooks in `default_hooks`.
+
+(1) Model saving configuration
+
+`default_hooks` uses the `checkpoint` field to initialize the [model saving hook (CheckpointHook)](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/checkpoint_hook.py#L19).
+
+```python
+checkpoint = dict(type='CheckpointHook', interval=1)
+```
+
+Users can set `max_keep_ckpts` to save only a small number of checkpoints or use `save_optimizer` to determine whether to save optimizer information. More details on related parameters can be found [here](https://mmengine.readthedocs.io/en/latest/api/generated/mmengine.hooks.CheckpointHook.html#checkpointhook).
+
+(2) Logging configuration
+
+The `LoggerHook` is used to collect log information from different components in `Runner` and write it to terminal, JSON files, tensorboard, wandb, etc.
+
+```python
+logger=dict(type='LoggerHook', interval=10)
+```
+
+In the latest 1.x version of MMSegmentation, some logger hooks (LoggerHook) such as `TextLoggerHook`, `WandbLoggerHook`, and `TensorboardLoggerHook` will no longer be used. Instead, MMEngine uses `LogProcessor` to handle the information processed by the aforementioned hooks, which are now in [`MessageHub`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/logging/message_hub.py#L17), [`WandbVisBackend`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/visualization/vis_backend.py#L324), and [`TensorboardVisBackend`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/visualization/vis_backend.py#L472).
+
+Detailed usage is as follows, configuring the visualizer and specifying the visualization backend at the same time, here using Tensorboard as the visualizer's backend:
+
+```python
+# TensorboardVisBackend
+visualizer = dict(
+    type='SegLocalVisualizer', vis_backends=[dict(type='TensorboardVisBackend')], name='visualizer')
+```
+
+For more related usage, please refer to [MMEngine Visualization Backend User Tutorial](https://github.com/open-mmlab/mmengine/blob/main/docs/en/advanced_tutorials/visualization.md).
+
+- Custom hooks
+
+Custom hooks are defined in the configuration through `custom_hooks`, and `Runner` registers them using the [`register_custom_hooks`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/runner.py#L1820) method.
+
+The priority of custom hooks needs to be set in the configuration file; if not, it will be set to `NORMAL` by default. The following are some custom hooks implemented in MMEngine:
+
+|                                                  Hook                                                  |                                                               Usage                                                                |
+| :----------------------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------: |
+|         [EMAHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/ema_hook.py)         |                                    Use Exponential Moving Average (EMA) during model training.                                     |
+| [EmptyCacheHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/empty_cache_hook.py)  |                                  Release all GPU memory not occupied by the cache during training                                  |
+| [SyncBuffersHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/sync_buffer_hook.py) | Synchronize the parameters in the model buffer, such as `running_mean` and `running_var` in BN, at the end of each training epoch. |
+
+The following is a use case for `EMAHook`, where the config file includes the configuration of the implemented custom hooks as members of the `custom_hooks` list.
+
+```python
+custom_hooks = [
+    dict(type='EMAHook', start_iters=500, priority='NORMAL')
+]
+```
+
+### SegVisualizationHook
+
+MMSegmentation implemented [`SegVisualizationHook`](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/engine/hooks/visualization_hook.py#L17), which is used to visualize prediction results during validation and testing.
+`SegVisualizationHook` overrides the `_after_iter` method in the base class `Hook`. During validation or testing, it calls the `add_datasample` method of `visualizer` to draw semantic segmentation results according to the specified iteration interval. The specific implementation is as follows:
+
+```python
+...
+@HOOKS.register_module()
+class SegVisualizationHook(Hook):
+...
+    def _after_iter(self,
+                    runner: Runner,
+                    batch_idx: int,
+                    data_batch: dict,
+                    outputs: Sequence[SegDataSample],
+                    mode: str = 'val') -> None:
+...
+        # If it's a training phase or self.draw is False, then skip it
+        if self.draw is False or mode == 'train':
+            return
+...
+        if self.every_n_inner_iters(batch_idx, self.interval):
+            for output in outputs:
+                img_path = output.img_path
+                img_bytes = self.file_client.get(img_path)
+                img = mmcv.imfrombytes(img_bytes, channel_order='rgb')
+                window_name = f'{mode}_{osp.basename(img_path)}'
+
+                self._visualizer.add_datasample(
+                    window_name,
+                    img,
+                    data_sample=output,
+                    show=self.show,
+                    wait_time=self.wait_time,
+                    step=runner.iter)
+
+```
+
+For more details about visualization, you can check [here](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/user_guides/visualization.md).
+
+## Optimizer
+
+In the previous configuration and runtime settings, we provided a simple example of configuring the training optimizer. This section will further detailly introduce  how to configure optimizers in MMSegmentation.
+
+## Optimizer Wrapper
+
+OpenMMLab 2.0 introduces an optimizer wrapper that supports different training strategies, including mixed-precision training, gradient accumulation, and gradient clipping. Users can choose the appropriate training strategy according to their needs. The optimizer wrapper also defines a standard parameter update process, allowing users to switch between different training strategies within the same code. For more information, please refer to the [MMEngine optimizer wrapper documentation](https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/optim_wrapper.md).
+
+Here are some common usage methods in MMSegmentation:
+
+#### Configuring PyTorch Supported Optimizers
+
+OpenMMLab 2.0 supports all native PyTorch optimizers, as referenced [here](https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/optim_wrapper.md).
+
+To set the optimizer used by the `Runner` during training in the configuration file, you need to define `optim_wrapper` instead of `optimizer`. Below is an example of configuring an optimizer during training:
+
+```python
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005),
+    clip_grad=None)
+```
+
+#### Configuring Gradient Clipping
+
+When the model training requires gradient clipping, you can configure it as shown in the following example:
+
+```python
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer,
+                        clip_grad=dict(max_norm=0.01, norm_type=2))
+```
+
+Here, `max_norm` refers to the maximum value of the gradient after clipping, and `norm_type` refers to the norm used when clipping the gradient. Related methods can be found in [torch.nn.utils.clip_grad_norm\_](https://pytorch.org/docs/stable/generated/torch.nn.utils.clip_grad_norm_.html).
+
+#### Configuring Mixed Precision Training
+
+When mixed precision training is needed to reduce memory usage, you can use `AmpOptimWrapper`. The specific configuration is as follows:
+
+```python
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='AmpOptimWrapper', optimizer=optimizer)
+```
+
+The default setting for `loss_scale` in [`AmpOptimWrapper`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/optim/optimizer/amp_optimizer_wrapper.py#L20) is `dynamic`.
+
+#### Configuring Hyperparameters for Different Layers of the Model Network
+
+In model training, if you want to set different optimization strategies for different parameters in the optimizer, such as setting different learning rates, weight decay, and other hyperparameters, you can achieve this by setting `paramwise_cfg` in the `optim_wrapper` of the configuration file.
+
+The following config file uses the [ViT `optim_wrapper`](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_vit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py#L15-L27) as an example to introduce the use of `paramwise_cfg` parameters. During training, the weight decay parameter coefficients for the `pos_embed`, `mask_token`, and `norm` modules are set to 0. That is, during training, the weight decay for these modules will be changed to `weight_decay * decay_mult`=0.
+
+```python
+optimizer = dict(
+        type='AdamW', lr=0.00006, betas=(0.9, 0.999), weight_decay=0.01)
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=optimizer,
+    paramwise_cfg=dict(
+        custom_keys={
+            'pos_embed': dict(decay_mult=0.),
+            'cls_token': dict(decay_mult=0.),
+            'norm': dict(decay_mult=0.)
+        }))
+```
+
+Here, `decay_mult` refers to the weight decay coefficient for the corresponding parameters. For more information on the usage of `paramwise_cfg`, please refer to the [MMEngine optimizer wrapper documentation](https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/optim_wrapper.md).
+
+### Optimizer Wrapper Constructor
+
+The default optimizer wrapper constructor [`DefaultOptimWrapperConstructor`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/optim/optimizer/default_constructor.py#L19) builds the optimizer used in training based on the input `optim_wrapper` and `paramwise_cfg` defined in the `optim_wrapper`. When the functionality of [`DefaultOptimWrapperConstructor`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/optim/optimizer/default_constructor.py#L19) does not meet the requirements, you can customize the optimizer wrapper constructor to implement the configuration of hyperparameters.
+
+MMSegmentation has implemented the [`LearningRateDecayOptimizerConstructor`](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/engine/optimizers/layer_decay_optimizer_constructor.py#L104), which can decay the learning rate of model parameters in the backbone networks of ConvNeXt, BEiT, and MAE models during training according to the defined decay ratio (`decay_rate`). The configuration in the configuration file is as follows:
+
+```python
+optim_wrapper = dict(
+    _delete_=True,
+    type='AmpOptimWrapper',
+    optimizer=dict(
+        type='AdamW', lr=0.0001, betas=(0.9, 0.999), weight_decay=0.05),
+    paramwise_cfg={
+        'decay_rate': 0.9,
+        'decay_type': 'stage_wise',
+        'num_layers': 12
+    },
+    constructor='LearningRateDecayOptimizerConstructor',
+    loss_scale='dynamic')
+```
+
+The purpose of `_delete_=True` is to ignore the inherited configuration in the OpenMMLab Config. In this code snippet, the inherited `optim_wrapper` configuration is ignored. For more information on `_delete_` fields, please refer to the [MMEngine documentation](https://github.com/open-mmlab/mmengine/blob/main/docs/en/advanced_tutorials/config.md#delete-key-in-dict).
diff --git a/docs/zh_cn/advanced_guides/engine.md b/docs/zh_cn/advanced_guides/engine.md
index a5746fcec8..7920ecfd87 100644
--- a/docs/zh_cn/advanced_guides/engine.md
+++ b/docs/zh_cn/advanced_guides/engine.md
@@ -61,7 +61,7 @@ OpenMMLab 将模型训练和测试过程抽象为 `Runner`, 插入钩子可以
 
 - 默认钩子 (default hooks)
 
-它们实现了训练时所必需的功能, 在配置文件中用 `default_hooks` 定义传给 `Runner`, `Runner` 通过 [`register_default_hooks`](https://github.com/open-mmlab/mmengine/blob/090104df21acd05a8aadae5a0d743a7da3314f6f/mmengine/runner/runner.py#L1780) 方法注册.
+它们实现了训练时所必需的功能, 在配置文件中用 `default_hooks` 定义传给 `Runner`, `Runner` 通过 [`register_default_hooks`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/runner.py#L1780) 方法注册.
 钩子有对应的优先级, 优先级越高, 越早被执行器调用. 如果优先级一样, 被调用的顺序和钩子注册的顺序一致.
 不建议用户修改默认钩子的优先级, 可以参考 [mmengine hooks 文档](https://github.com/open-mmlab/mmengine/blob/main/docs/zh_cn/tutorials/hook.md) 了解钩子优先级的定义.
 下面是 MMSegmentation 中所用到的默认钩子：
@@ -94,6 +94,7 @@ default_hooks = dict(
 以 `default_hooks` 里面的 `logger` 和 `checkpoint` 为例, 我们来介绍如何修改 `default_hooks` 中默认的钩子.
 
 (1) 模型保存配置
+
 `default_hooks` 使用 `checkpoint` 字段来初始化[模型保存钩子 (CheckpointHook)](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/checkpoint_hook.py#L19).
 
 ```python
@@ -104,6 +105,7 @@ checkpoint = dict(type='CheckpointHook', interval=1)
 更多相关参数的细节可以参考[这里](https://mmengine.readthedocs.io/zh_CN/latest/api/generated/mmengine.hooks.CheckpointHook.html#checkpointhook).
 
 (2) 日志配置
+
 `日志钩子 (LoggerHook)` 被用来收集 `执行器 (Runner)` 里面不同组件的日志信息然后写入终端, JSON 文件, tensorboard 和 wandb 等地方.
 
 ```python
@@ -126,7 +128,7 @@ visualizer = dict(
 
 - 自定义钩子 (custom hooks)
 
-自定义钩子在配置通过 `custom_hooks` 定义, `Runner` 通过 [`register_custom_hooks`](https://github.com/open-mmlab/mmengine/blob/090104df21acd05a8aadae5a0d743a7da3314f6f/mmengine/runner/runner.py#L1852) 方法注册.
+自定义钩子在配置通过 `custom_hooks` 定义, `Runner` 通过 [`register_custom_hooks`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/runner.py#L1820) 方法注册.
 自定义钩子优先级需要在配置文件里设置, 如果没有设置, 则会被默认设置为 `NORMAL`. 下面是部分 MMEngine 中实现的自定义钩子:
 
 |                                                  钩子                                                  |                                             用法                                             |
@@ -181,7 +183,7 @@ class SegVisualizationHook(Hook):
 
 ```
 
-关于可视化更多的细节可以查看[这里](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/user_guides/visualization.md).
+关于可视化更多的细节可以查看[这里](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/user_guides/visualization.md).
 
 ## 优化器
 
@@ -257,9 +259,9 @@ optim_wrapper = dict(
 
 ### 优化器封装构造器
 
-默认的优化器封装构造器 [`DefaultOptimWrapperConstructor`](https://github.com/open-mmlab/mmengine/blob/376251961da47ea8254ab808ae5c51e1430f18dc/mmengine/optim/optimizer/default_constructor.py#L19) 根据输入的 `optim_wrapper` 和 `optim_wrapper` 中定义的 `paramwise_cfg` 来构建训练中使用的优化器. 当 [`DefaultOptimWrapperConstructor`](https://github.com/open-mmlab/mmengine/blob/376251961da47ea8254ab808ae5c51e1430f18dc/mmengine/optim/optimizer/default_constructor.py#L19) 功能不能满足需求时, 可以自定义优化器封装构造器来实现超参数的配置.
+默认的优化器封装构造器 [`DefaultOptimWrapperConstructor`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/optim/optimizer/default_constructor.py#L19) 根据输入的 `optim_wrapper` 和 `optim_wrapper` 中定义的 `paramwise_cfg` 来构建训练中使用的优化器. 当 [`DefaultOptimWrapperConstructor`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/optim/optimizer/default_constructor.py#L19) 功能不能满足需求时, 可以自定义优化器封装构造器来实现超参数的配置.
 
-MMSegmentation 中的实现了 [`LearningRateDecayOptimizerConstructor`](https://github.com/open-mmlab/mmsegmentation/blob/b21df463d47447f33c28d9a4f46136ad64d34a40/mmseg/engine/optimizers/layer_decay_optimizer_constructor.py#L104), 可以对以 ConvNeXt, BEiT 和 MAE 为骨干网络的模型训练时, 骨干网络的模型参数的学习率按照定义的衰减比例（`decay_rate`）逐层递减, 在配置文件中的配置如下:
+MMSegmentation 中的实现了 [`LearningRateDecayOptimizerConstructor`](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/engine/optimizers/layer_decay_optimizer_constructor.py#L104), 可以对以 ConvNeXt, BEiT 和 MAE 为骨干网络的模型训练时, 骨干网络的模型参数的学习率按照定义的衰减比例（`decay_rate`）逐层递减, 在配置文件中的配置如下:
 
 ```python
 optim_wrapper = dict(

From 871e7ac1ff6bc5118b21c2d26507232094a98c41 Mon Sep 17 00:00:00 2001
From: Tianlong Ai <50650583+AI-Tianlong@users.noreply.github.com>
Date: Thu, 30 Mar 2023 14:50:13 +0800
Subject: [PATCH 26/32] [Doc] Fix invalid links and standardize Chinese and
 English punctuation marks at zh_CN faq.md  (#2790)

---
 docs/zh_cn/notes/faq.md | 44 ++++++++++++++++++++---------------------
 1 file changed, 22 insertions(+), 22 deletions(-)

diff --git a/docs/zh_cn/notes/faq.md b/docs/zh_cn/notes/faq.md
index d90329cf22..6c5264c378 100644
--- a/docs/zh_cn/notes/faq.md
+++ b/docs/zh_cn/notes/faq.md
@@ -1,10 +1,10 @@
 # 常见问题解答（FAQ）
 
-我们在这里列出了使用时的一些常见问题及其相应的解决方案。 如果您发现有一些问题被遗漏，请随时提 PR 丰富这个列表。 如果您无法在此获得帮助，请使用 [issue模板](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/.github/ISSUE_TEMPLATE/error-report.md/)创建问题，但是请在模板中填写所有必填信息，这有助于我们更快定位问题。
+我们在这里列出了使用时的一些常见问题及其相应的解决方案。 如果您发现有一些问题被遗漏，请随时提 PR 丰富这个列表。 如果您无法在此获得帮助，请使用 [issue 模板](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/.github/ISSUE_TEMPLATE/error-report.md/)创建问题，但是请在模板中填写所有必填信息，这有助于我们更快定位问题。
 
 ## 安装
 
-兼容的MMSegmentation和MMCV版本如下。请安装正确版本的MMCV以避免安装问题。
+兼容的 MMSegmentation 和 MMCV 版本如下。请安装正确版本的 MMCV 以避免安装问题。
 
 | MMSegmentation version |          MMCV version          | MMEngine version  | MMClassification (optional) version | MMDetection (optional) version |
 | :--------------------: | :----------------------------: | :---------------: | :---------------------------------: | :----------------------------: |
@@ -18,44 +18,44 @@
 |        1.0.0rc1        | mmcv >= 2.0.0rc1, \<=2.0.0rc3> | MMEngine >= 0.1.0 |           mmcls>=1.0.0rc0           |          Not required          |
 |        1.0.0rc0        | mmcv >= 2.0.0rc1, \<=2.0.0rc3> | MMEngine >= 0.1.0 |           mmcls>=1.0.0rc0           |          Not required          |
 
-如果您已经安装了版本不合适的 mmcv，请先运行`pip uninstall mmcv`卸载已安装的 mmcv，如您先前安装的为 mmcv-full(存在于 OpenMMLab 1.x),请运行`pip uninstall mmcv-full`进行卸载。
+如果您已经安装了版本不合适的 mmcv，请先运行`pip uninstall mmcv`卸载已安装的 mmcv，如您先前安装的为 mmcv-full（存在于 OpenMMLab 1.x），请运行`pip uninstall mmcv-full`进行卸载。
 
-- 如出现"No module named 'mmcv'";
-  1. 使用`pip uninstall mmcv`卸载环境中现有的mmcv。
-  2. 按照[安装说明](../get_started#best-practices)安装对应的mmcv。
+- 如出现 "No module named 'mmcv'"
+  1. 使用`pip uninstall mmcv`卸载环境中现有的 mmcv
+  2. 按照[安装说明](../get_started.md)安装对应的 mmcv
 
 ## 如何获知模型训练时需要的显卡数量
 
-- 看模型的config文件的命名。可以参考[学习配置文件](../user_guides/1_config.md)中的`配置文件命名风格`部分。比如，对于名字为`segformer_mit-b0_8xb1-160k_cityscapes-1024x1024.py`的config文件，`8xb1`代表训练其对应的模型需要的卡数为8，每张卡中的batch size为1。
-- 看模型的log文件。点开该模型的log文件，并在其中搜索`nGPU`，在`nGPU`后的数字个数即训练时所需的卡数。比如，在log文件中搜索`nGPU`得到`nGPU 0,1,2,3,4,5,6,7`的记录，则说明训练该模型需要使用八张卡。
+- 看模型的 config 文件命名。可以参考[了解配置文件](../user_guides/1_config.md)中的`配置文件命名风格`部分。比如，对于名字为`segformer_mit-b0_8xb1-160k_cityscapes-1024x1024.py`的 config 文件，`8xb1`代表训练其对应的模型需要的卡数为 8，每张卡中的 batch size 为 1。
+- 看模型的 log 文件。点开该模型的 log 文件，并在其中搜索`nGPU`，在`nGPU`后的数字个数即训练时所需的卡数。比如，在 log 文件中搜索`nGPU`得到`nGPU 0,1,2,3,4,5,6,7`的记录，则说明训练该模型需要使用八张卡。
 
 ## auxiliary head 是什么
 
-简单来说，这是一个提高准确率的深度监督技术。在训练阶段，`decode_head` 用于输出语义分割的结果，`auxiliary_head` 只是增加了一个辅助损失，其产生的分割结果对你的模型结果没有影响，仅在在训练中起作用。您可以阅读这篇[论文](https://arxiv.org/pdf/1612.01105.pdf)了解更多信息。
+简单来说，这是一个提高准确率的深度监督技术。在训练阶段，`decode_head`用于输出语义分割的结果，`auxiliary_head` 只是增加了一个辅助损失，其产生的分割结果对你的模型结果没有影响，仅在在训练中起作用。您可以阅读这篇[论文](https://arxiv.org/pdf/1612.01105.pdf)了解更多信息。
 
 ## 运行测试脚本时如何输出绘制分割掩膜的图像
 
-在测试脚本中，我们提供了`--out`参数来控制是否输出保存预测的分割掩膜图像。您可以运行以下命令输出测试结果:
+在测试脚本中，我们提供了`--out`参数来控制是否输出保存预测的分割掩膜图像。您可以运行以下命令输出测试结果：
 
 ```shell
 python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} --out ${OUTPUT_DIR}
 ```
 
-更多用例细节可查阅[文档](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/user_guides/4_train_test.md#%E6%B5%8B%E8%AF%95%E5%B9%B6%E4%BF%9D%E5%AD%98%E5%88%86%E5%89%B2%E7%BB%93%E6%9E%9C)，[PR #2712](https://github.com/open-mmlab/mmsegmentation/pull/2712)以及[迁移文档](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/migration/interface.md#%E6%B5%8B%E8%AF%95%E5%90%AF%E5%8A%A8)了解相关说明
+更多用例细节可查阅[文档](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/user_guides/4_train_test.md#%E6%B5%8B%E8%AF%95%E5%B9%B6%E4%BF%9D%E5%AD%98%E5%88%86%E5%89%B2%E7%BB%93%E6%9E%9C)，[PR #2712](https://github.com/open-mmlab/mmsegmentation/pull/2712) 以及[迁移文档](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/migration/interface.md#%E6%B5%8B%E8%AF%95%E5%90%AF%E5%8A%A8)了解相关说明。
 
 ## 如何处理二值分割任务?
 
-MMSegmentation 使用 `num_classes` 和 `out_channels` 来控制模型最后一层 `self.conv_seg` 的输出. 更多细节可以参考 [这里](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/decode_heads/decode_head.py).
+MMSegmentation 使用 `num_classes` 和 `out_channels` 来控制模型最后一层 `self.conv_seg` 的输出。更多细节可以参考 [这里](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/decode_heads/decode_head.py)。
 
-`num_classes` 应该和数据集本身类别个数一致，当是二值分割时，数据集只有前景和背景两类, 所以 `num_classes` 为 2. `out_channels` 控制模型最后一层的输出的通道数，通常和 `num_classes` 相等, 但当二值分割时候, 可以有两种处理方法, 分别是：
+`num_classes` 应该和数据集本身类别个数一致，当是二值分割时，数据集只有前景和背景两类，所以 `num_classes` 为 2. `out_channels` 控制模型最后一层的输出的通道数，通常和 `num_classes` 相等，但当二值分割时候，可以有两种处理方法, 分别是：
 
-- 设置 `out_channels=2`, 在训练时以 Cross Entropy Loss 作为损失函数, 在推理时使用 `F.softmax()` 归一化 logits 值, 然后通过 `argmax()` 得到每个像素的预测结果.
+- 设置 `out_channels=2`，在训练时以 Cross Entropy Loss 作为损失函数，在推理时使用 `F.softmax()` 归一化 logits 值，然后通过 `argmax()` 得到每个像素的预测结果。
 
-- 设置 `out_channels=1`, 在训练时以 Binary Cross Entropy Loss 作为损失函数, 在推理时使用 `F.sigmoid()` 和 `threshold` 得到预测结果, `threshold` 默认为 0.3.
+- 设置 `out_channels=1`，在训练时以 Binary Cross Entropy Loss 作为损失函数，在推理时使用 `F.sigmoid()` 和 `threshold` 得到预测结果，`threshold` 默认为 0.3。
 
-对于实现上述两种计算二值分割的方法, 需要在 `decode_head` 和 `auxiliary_head` 的配置里修改. 下面是对样例 [pspnet_unet_s5-d16.py](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/models/pspnet_unet_s5-d16.py) 做出的对应修改.
+对于实现上述两种计算二值分割的方法，需要在 `decode_head` 和 `auxiliary_head` 的配置里修改。下面是对样例 [pspnet_unet_s5-d16.py](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/models/pspnet_unet_s5-d16.py) 做出的对应修改。
 
-- (1) `num_classes=2`, `out_channels=2` 并在 `CrossEntropyLoss` 里面设置 `use_sigmoid=False`.
+- (1) `num_classes=2`, `out_channels=2` 并在 `CrossEntropyLoss` 里面设置 `use_sigmoid=False`。
 
 ```python
 decode_head=dict(
@@ -99,7 +99,7 @@ auxiliary_head=dict(
 
 ## `reduce_zero_label` 的作用
 
-数据集中 `reduce_zero_label` 参数类型为布尔类型, 默认为 False, 它的功能是为了忽略数据集 label 0. 具体做法是将 label 0 改为 255, 其余 label 相应编号减 1, 同时 decode head 里将 255 设为 ignore index, 即不参与 loss 计算.
+数据集中 `reduce_zero_label` 参数类型为布尔类型，默认为 False，它的功能是为了忽略数据集 label 0。具体做法是将 label 0 改为 255，其余 label 相应编号减 1，同时 decode head 里将 255 设为 ignore index，即不参与 loss 计算。
 以下是 `reduce_zero_label` 具体实现逻辑:
 
 ```python
@@ -110,9 +110,9 @@ if self.reduce_zero_label:
     gt_semantic_seg[gt_semantic_seg == 254] = 255
 ```
 
-关于您的数据集是否需要使用reduce_zero_label，有以下两类情况：
+关于您的数据集是否需要使用 reduce_zero_label，有以下两类情况：
 
-- 例如在Potsdam数据集上，有 0-不透水面、1-建筑、2-低矮植被、3-树、4-汽车、5-杂乱，六类。但该数据集提供了两种RGB标签，一种为图像边缘处有黑色像素的标签，另一种是没有黑色边缘的标签。对于有黑色边缘的标签，在 [dataset_converters.py](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/tools/dataset_converters/potsdam.py)中，其将黑色边缘转换为label 0，其余标签分别为 1-不透水面、2-建筑、3-低矮植被、4-树、5-汽车、6-杂乱，那么此时，就应该在数据集[potsdam.py](https://github.com/open-mmlab/mmsegmentation/blob/ff95416c3b5ce8d62b9289f743531398efce534f/mmseg/datasets/potsdam.py#L23)中将`reduce_zero_label=True`。如果使用的是没有黑色边缘的标签，那么mask label中只有0-5，此时就应该使`reduce_zero_label=False`。需要结合您的实际情况来使用。
-- 例如在第0类为background类别的数据集上，如果您最终是需要将背景和您的其余类别分开时，是不需要使用`reduce_zero_label`的，此时在数据集中应该将其设置为`reduce_zero_label=False`
+- 例如在 [Potsdam](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/en/user_guides/2_dataset_prepare.md#isprs-potsdam) 数据集上，有 0-不透水面、1-建筑、2-低矮植被、3-树、4-汽车、5-杂乱，六类。但该数据集提供了两种RGB标签，一种为图像边缘处有黑色像素的标签，另一种是没有黑色边缘的标签。对于有黑色边缘的标签，在 [dataset_converters.py](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/tools/dataset_converters/potsdam.py)中，其将黑色边缘转换为 label 0，其余标签分别为 1-不透水面、2-建筑、3-低矮植被、4-树、5-汽车、6-杂乱，那么此时，就应该在数据集 [potsdam.py](https://github.com/open-mmlab/mmsegmentation/blob/ff95416c3b5ce8d62b9289f743531398efce534f/mmseg/datasets/potsdam.py#L23) 中将`reduce_zero_label=True`。如果使用的是没有黑色边缘的标签，那么 mask label 中只有 0-5，此时就应该使`reduce_zero_label=False`。需要结合您的实际情况来使用。
+- 例如在第 0 类为background类别的数据集上，如果您最终是需要将背景和您的其余类别分开时，是不需要使用`reduce_zero_label`的，此时在数据集中应该将其设置为`reduce_zero_label=False`
 
-**注意:** 使用 `reduce_zero_label` 请确认数据集原始类别个数, 如果只有两类, 需要关闭 `reduce_zero_label` 即设置 `reduce_zero_label=False`.
+**注意:** 使用 `reduce_zero_label` 请确认数据集原始类别个数，如果只有两类，需要关闭 `reduce_zero_label` 即设置 `reduce_zero_label=False`。

From a7d2e28dcab70166663c61e26074939834d43fe8 Mon Sep 17 00:00:00 2001
From: CSH <40987381+csatsurnh@users.noreply.github.com>
Date: Thu, 30 Mar 2023 15:01:27 +0800
Subject: [PATCH 27/32] [Doc] Update dataset_prepare & inference (#2798)

---
 docs/en/user_guides/2_dataset_prepare.md    |  73 ++-
 docs/en/user_guides/3_inference.md          |  34 +-
 docs/zh_cn/user_guides/2_dataset_prepare.md | 619 +++++++++++++++++++-
 docs/zh_cn/user_guides/3_inference.md       | 245 +++++++-
 4 files changed, 907 insertions(+), 64 deletions(-)

diff --git a/docs/en/user_guides/2_dataset_prepare.md b/docs/en/user_guides/2_dataset_prepare.md
index 6c81d60f41..63a1a8bb4a 100644
--- a/docs/en/user_guides/2_dataset_prepare.md
+++ b/docs/en/user_guides/2_dataset_prepare.md
@@ -1,4 +1,4 @@
-## Prepare datasets
+# Tutorial 2: Prepare datasets
 
 It is recommended to symlink the dataset root to `$MMSEGMENTATION/data`.
 If your folder structure is different, you may need to change the corresponding paths in config files.
@@ -179,20 +179,19 @@ mmsegmentation
 |   │   │   │   └── polygons
 ```
 
-### Cityscapes
+## Cityscapes
 
 The data could be found [here](https://www.cityscapes-dataset.com/downloads/) after registration.
 
 By convention, `**labelTrainIds.png` are used for cityscapes training.
-We provided a [scripts](https://github.com/open-mmlab/mmsegmentation/blob/1.x/tools/dataset_converters/cityscapes.py) based on [cityscapesscripts](https://github.com/mcordts/cityscapesScripts)
-to generate `**labelTrainIds.png`.
+We provided a [script](https://github.com/open-mmlab/mmsegmentation/blob/1.x/tools/dataset_converters/cityscapes.py) based on [cityscapesscripts](https://github.com/mcordts/cityscapesScripts)to generate `**labelTrainIds.png`.
 
 ```shell
 # --nproc means 8 process for conversion, which could be omitted as well.
 python tools/dataset_converters/cityscapes.py data/cityscapes --nproc 8
 ```
 
-### Pascal VOC
+## Pascal VOC
 
 Pascal VOC 2012 could be downloaded from [here](http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar).
 Beside, most recent works on Pascal VOC dataset usually exploit extra augmentation data, which could be found [here](http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/semantic_contours/benchmark.tgz).
@@ -204,14 +203,14 @@ If you would like to use augmented VOC dataset, please run following command to
 python tools/dataset_converters/voc_aug.py data/VOCdevkit data/VOCdevkit/VOCaug --nproc 8
 ```
 
-Please refer to [concat dataset](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/advanced_guides/datasets.md) for details about how to concatenate them and train them together.
+Please refer to [concat dataset](../advanced_guides/add_datasets.md#concatenate-dataset) and [voc_aug config example](../../../configs/_base_/datasets/pascal_voc12_aug.py) for details about how to concatenate them and train them together.
 
-### ADE20K
+## ADE20K
 
 The training and validation set of ADE20K could be download from this [link](http://data.csail.mit.edu/places/ADEchallenge/ADEChallengeData2016.zip).
 We may also download test set from [here](http://data.csail.mit.edu/places/ADEchallenge/release_test.zip).
 
-### Pascal Context
+## Pascal Context
 
 The training and validation set of Pascal Context could be download from [here](http://host.robots.ox.ac.uk/pascal/VOC/voc2010/VOCtrainval_03-May-2010.tar). You may also download test set from [here](http://host.robots.ox.ac.uk:8080/eval/downloads/VOC2010test.tar) after registration.
 
@@ -223,7 +222,7 @@ If you would like to use Pascal Context dataset, please install [Detail](https:/
 python tools/dataset_converters/pascal_context.py data/VOCdevkit data/VOCdevkit/VOC2010/trainval_merged.json
 ```
 
-### COCO Stuff 10k
+## COCO Stuff 10k
 
 The data could be downloaded [here](http://calvin.inf.ed.ac.uk/wp-content/uploads/data/cocostuffdataset/cocostuff-10k-v1.1.zip) by wget.
 
@@ -243,7 +242,7 @@ python tools/dataset_converters/coco_stuff10k.py /path/to/coco_stuff10k --nproc
 
 By convention, mask labels in `/path/to/coco_stuff164k/annotations/*2014/*_labelTrainIds.png` are used for COCO Stuff 10k training and testing.
 
-### COCO Stuff 164k
+## COCO Stuff 164k
 
 For COCO Stuff 164k dataset, please run the following commands to download and convert the augmented dataset.
 
@@ -267,7 +266,7 @@ By convention, mask labels in `/path/to/coco_stuff164k/annotations/*2017/*_label
 
 The details of this dataset could be found at [here](https://github.com/nightrome/cocostuff#downloads).
 
-### CHASE DB1
+## CHASE DB1
 
 The training and validation set of CHASE DB1 could be download from [here](https://staffnet.kingston.ac.uk/~ku15565/CHASE_DB1/assets/CHASEDB1.zip).
 
@@ -279,7 +278,7 @@ python tools/dataset_converters/chase_db1.py /path/to/CHASEDB1.zip
 
 The script will make directory structure automatically.
 
-### DRIVE
+## DRIVE
 
 The training and validation set of DRIVE could be download from [here](https://drive.grand-challenge.org/). Before that, you should register an account. Currently '1st_manual' is not provided officially.
 
@@ -291,7 +290,7 @@ python tools/dataset_converters/drive.py /path/to/training.zip /path/to/test.zip
 
 The script will make directory structure automatically.
 
-### HRF
+## HRF
 
 First, download [healthy.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/healthy.zip), [glaucoma.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/glaucoma.zip), [diabetic_retinopathy.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/diabetic_retinopathy.zip), [healthy_manualsegm.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/healthy_manualsegm.zip), [glaucoma_manualsegm.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/glaucoma_manualsegm.zip) and [diabetic_retinopathy_manualsegm.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/diabetic_retinopathy_manualsegm.zip).
 
@@ -303,7 +302,7 @@ python tools/dataset_converters/hrf.py /path/to/healthy.zip /path/to/healthy_man
 
 The script will make directory structure automatically.
 
-### STARE
+## STARE
 
 First, download [stare-images.tar](http://cecas.clemson.edu/~ahoover/stare/probing/stare-images.tar), [labels-ah.tar](http://cecas.clemson.edu/~ahoover/stare/probing/labels-ah.tar) and [labels-vk.tar](http://cecas.clemson.edu/~ahoover/stare/probing/labels-vk.tar).
 
@@ -315,15 +314,15 @@ python tools/dataset_converters/stare.py /path/to/stare-images.tar /path/to/labe
 
 The script will make directory structure automatically.
 
-### Dark Zurich
+## Dark Zurich
 
 Since we only support test models on this dataset, you may only download [the validation set](https://data.vision.ee.ethz.ch/csakarid/shared/GCMA_UIoU/Dark_Zurich_val_anon.zip).
 
-### Nighttime Driving
+## Nighttime Driving
 
 Since we only support test models on this dataset, you may only download [the test set](http://data.vision.ee.ethz.ch/daid/NighttimeDriving/NighttimeDrivingTest.zip).
 
-### LoveDA
+## LoveDA
 
 The data could be downloaded from Google Drive [here](https://drive.google.com/drive/folders/1ibYV0qwn4yuuh068Rnc-w4tPi0U0c-ti?usp=sharing).
 
@@ -338,25 +337,24 @@ wget https://zenodo.org/record/5706578/files/Val.zip
 wget https://zenodo.org/record/5706578/files/Test.zip
 ```
 
-For LoveDA dataset, please run the following command to download and re-organize the dataset.
+For LoveDA dataset, please run the following command to re-organize the dataset.
 
 ```shell
 python tools/dataset_converters/loveda.py /path/to/loveDA
 ```
 
-Using trained model to predict test set of LoveDA and submit it to server can be found [here](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/user_guides/3_inference.md).
+Using trained model to predict test set of LoveDA and submit it to server can be found [here](https://codalab.lisn.upsaclay.fr/competitions/421).
 
 More details about LoveDA can be found [here](https://github.com/Junjue-Wang/LoveDA).
 
-### ISPRS Potsdam
+## ISPRS Potsdam
 
-The [Potsdam](https://www2.isprs.org/commissions/comm2/wg4/benchmark/2d-sem-label-potsdam/)
-dataset is for urban semantic segmentation used in the 2D Semantic Labeling Contest - Potsdam.
+The [Potsdam](https://www2.isprs.org/commissions/comm2/wg4/benchmark/2d-sem-label-potsdam/) dataset is for urban semantic segmentation used in the 2D Semantic Labeling Contest - Potsdam.
 
 The dataset can be requested at the challenge [homepage](https://www2.isprs.org/commissions/comm2/wg4/benchmark/data-request-form/).
 The '2_Ortho_RGB.zip' and '5_Labels_all_noBoundary.zip' are required.
 
-For Potsdam dataset, please run the following command to download and re-organize the dataset.
+For Potsdam dataset, please run the following command to re-organize the dataset.
 
 ```shell
 python tools/dataset_converters/potsdam.py /path/to/potsdam
@@ -364,29 +362,28 @@ python tools/dataset_converters/potsdam.py /path/to/potsdam
 
 In our default setting, it will generate 3456 images for training and 2016 images for validation.
 
-### ISPRS Vaihingen
+## ISPRS Vaihingen
 
-The [Vaihingen](https://www2.isprs.org/commissions/comm2/wg4/benchmark/2d-sem-label-vaihingen/)
-dataset is for urban semantic segmentation used in the 2D Semantic Labeling Contest - Vaihingen.
+The [Vaihingen](https://www2.isprs.org/commissions/comm2/wg4/benchmark/2d-sem-label-vaihingen/) dataset is for urban semantic segmentation used in the 2D Semantic Labeling Contest - Vaihingen.
 
 The dataset can be requested at the challenge [homepage](https://www2.isprs.org/commissions/comm2/wg4/benchmark/data-request-form/).
 The 'ISPRS_semantic_labeling_Vaihingen.zip' and 'ISPRS_semantic_labeling_Vaihingen_ground_truth_eroded_COMPLETE.zip' are required.
 
-For Vaihingen dataset, please run the following command to download and re-organize the dataset.
+For Vaihingen dataset, please run the following command to re-organize the dataset.
 
 ```shell
 python tools/dataset_converters/vaihingen.py /path/to/vaihingen
 ```
 
-In our default setting (`clip_size` =512, `stride_size`=256), it will generate 344 images for training and 398 images for validation.
+In our default setting (`clip_size`=512, `stride_size`=256), it will generate 344 images for training and 398 images for validation.
 
-### iSAID
+## iSAID
 
 The data images could be download from [DOTA-v1.0](https://captain-whu.github.io/DOTA/dataset.html) (train/val/test)
 
 The data annotations could be download from [iSAID](https://captain-whu.github.io/iSAID/dataset.html) (train/val)
 
-The dataset is a Large-scale Dataset for Instance Segmentation (also have segmantic segmentation) in Aerial Images.
+The dataset is a Large-scale Dataset for Instance Segmentation (also have semantic segmentation) in Aerial Images.
 
 You may need to follow the following structure for dataset preparation after downloading iSAID dataset.
 
@@ -415,7 +412,7 @@ You may need to follow the following structure for dataset preparation after dow
 python tools/dataset_converters/isaid.py /path/to/iSAID
 ```
 
-In our default setting (`patch_width`=896, `patch_height`=896,　`overlap_area`=384), it will generate 33978 images for training and 11644 images for validation.
+In our default setting (`patch_width`=896, `patch_height`=896, `overlap_area`=384), it will generate 33978 images for training and 11644 images for validation.
 
 ## LIP(Look Into Person) dataset
 
@@ -435,7 +432,7 @@ mv val_segmentations ../
 cd ..
 ```
 
-The contents of  LIP datasets include:
+The contents of LIP datasets include:
 
 ```none
 ├── data
@@ -456,10 +453,9 @@ The contents of  LIP datasets include:
 
 ## Synapse dataset
 
-This dataset could be download from [this page](https://www.synapse.org/#!Synapse:syn3193805/wiki/)
+This dataset could be download from [this page](https://www.synapse.org/#!Synapse:syn3193805/wiki/).
 
-To follow the data preparation setting of [TransUNet](https://arxiv.org/abs/2102.04306), which splits original training set (30 scans)
-into new training (18 scans) and validation set (12 scans). Please run the following command to prepare the dataset.
+To follow the data preparation setting of [TransUNet](https://arxiv.org/abs/2102.04306), which splits original training set (30 scans) into new training (18 scans) and validation set (12 scans). Please run the following command to prepare the dataset.
 
 ```shell
 unzip RawData.zip
@@ -532,10 +528,9 @@ Then, use this command to convert synapse dataset.
 python tools/dataset_converters/synapse.py --dataset-path /path/to/synapse
 ```
 
-Noted that MMSegmentation default evaluation metric (such as mean dice value) is calculated on 2D slice image,
-which is not comparable to results of 3D scan in some paper such as [TransUNet](https://arxiv.org/abs/2102.04306).
+Noted that MMSegmentation default evaluation metric (such as mean dice value) is calculated on 2D slice image, which is not comparable to results of 3D scan in some paper such as [TransUNet](https://arxiv.org/abs/2102.04306).
 
-### REFUGE
+## REFUGE
 
 Register in [REFUGE Challenge](https://refuge.grand-challenge.org) and download [REFUGE dataset](https://refuge.grand-challenge.org/REFUGE2Download).
 
@@ -624,4 +619,4 @@ It includes 400 images for training, 400 images for validation and 400 images fo
   ```
 
 - You could set Datasets version with `MapillaryDataset_v1` and `MapillaryDataset_v2` in your configs.
-  View the Mapillary Vistas Datasets config file here [V1.2](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/datasets/mapillary_v1.py) and  [V2.0](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/datasets/mapillary_v2.py)
+  View the Mapillary Vistas Datasets config file here [V1.2](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/datasets/mapillary_v1.py) and [V2.0](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/datasets/mapillary_v2.py)
diff --git a/docs/en/user_guides/3_inference.md b/docs/en/user_guides/3_inference.md
index c9f4e62f10..6650b2ed39 100644
--- a/docs/en/user_guides/3_inference.md
+++ b/docs/en/user_guides/3_inference.md
@@ -19,7 +19,7 @@ MMSegmentation provides several interfaces for users to easily use pre-trained m
 
 ## Inferencer
 
-We provides the most **convenient** way to use the model in MMSegmentation `MMSegInferencer`. You can get segmentation mask for an image with only 3 lines of code.
+We provide the most **convenient** way to use the model in MMSegmentation `MMSegInferencer`. You can get segmentation mask for an image with only 3 lines of code.
 
 ### Basic Usage
 
@@ -36,7 +36,7 @@ The following example shows how to use `MMSegInferencer` to perform inference on
 The visualization result should look like:
 
 <div align="center">
-https://user-images.githubusercontent.com/76149310/221507927-ae01e3a7-016f-4425-b966-7b19cbbe494e.png
+    <img src='https://user-images.githubusercontent.com/76149310/221507927-ae01e3a7-016f-4425-b966-7b19cbbe494e.png' />
 </div>
 
 Moreover, you can use `MMSegInferencer` to process a list of images:
@@ -44,7 +44,7 @@ Moreover, you can use `MMSegInferencer` to process a list of images:
 ```
 # Input a list of images
 >>> images = [image1, image2, ...] # image1 can be a file path or a np.ndarray
->>> inferencer(images, show=True, wait_time=0.5) # wait_time is delay time, and 0 means forever.
+>>> inferencer(images, show=True, wait_time=0.5) # wait_time is delay time, and 0 means forever
 
 # Or input image directory
 >>> images = $IMAGESDIR
@@ -56,13 +56,12 @@ Moreover, you can use `MMSegInferencer` to process a list of images:
 >>> inferencer(images, out_dir='outputs', img_out_dir='vis', pred_out_dir='pred')
 ```
 
-There is a optional parameter of inferencer, `return_datasamples`, whose default value is False, and
-return value of inferencer is a `dict` type by default, including 2 keys 'visualization' and 'predictions'.
+There is a optional parameter of inferencer, `return_datasamples`, whose default value is False, and return value of inferencer is a `dict` type by default, including 2 keys 'visualization' and 'predictions'.
 If `return_datasamples=True` inferencer will return [`SegDataSample`](../advanced_guides/structures.md), or list of it.
 
 ```
 result = inferencer('demo/demo.png')
-# result is a `dict` including 2 keys 'visualization' and 'predictions'.
+# result is a `dict` including 2 keys 'visualization' and 'predictions'
 # 'visualization' includes color segmentation map
 print(result['visualization'].shape)
 # (512, 683, 3)
@@ -92,18 +91,12 @@ print(type(results[0]))
 ### Initialization
 
 `MMSegInferencer` must be initialized from a `model`, which can be a model name or a `Config` even a path of config file.
-The model names can be found in models' metafile, like one model name of maskformer is `maskformer_r50-d32_8xb2-160k_ade20k-512x512`, and if input model name and the weights of the model will be download automatically. Below are other input parameters:
-
-- weights (str, optional) -  Path to the checkpoint. If it is not specified and model is a model name of metafile, the weights will be loaded
-  from metafile. Defaults to None.
-- classes (list, optional) - Input classes for result rendering, as the prediction of segmentation
-  model is a segment map with label indices, `classes` is a list which includes
-  items responding to the label indices. If classes is not defined, visualizer will take `cityscapes` classes by default. Defaults to None.
-- palette (list, optional) - Input palette for result rendering, which is a list of color palette
-  responding to the classes. If palette is not defined, visualizer will take `cityscapes` palette by default. Defaults to None.
-- dataset_name (str, optional)[Dataset name or alias](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/utils/class_names.py#L302-L317)
-  visulizer will use the meta information of the dataset i.e. classes and palette,
-  but the `classes` and `palette` have higher priority. Defaults to None.
+The model names can be found in models' metafile (configs/xxx/metafile.yaml), like one model name of maskformer is `maskformer_r50-d32_8xb2-160k_ade20k-512x512`, and if input model name and the weights of the model will be download automatically. Below are other input parameters:
+
+- weights (str, optional) -  Path to the checkpoint. If it is not specified and model is a model name of metafile, the weights will be loaded from metafile. Defaults to None.
+- classes (list, optional) - Input classes for result rendering, as the prediction of segmentation model is a segment map with label indices, `classes` is a list which includes items responding to the label indices. If classes is not defined, visualizer will take `cityscapes` classes by default. Defaults to None.
+- palette (list, optional) - Input palette for result rendering, which is a list of colors responding to the classes. If the palette is not defined, the visualizer will take the palette of `cityscapes` by default. Defaults to None.
+- dataset_name (str, optional) - [Dataset name or alias](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/utils/class_names.py#L302-L317), visualizer will use the meta information of the dataset i.e. classes and palette, but the `classes` and `palette` have higher priority. Defaults to None.
 - device (str, optional) - Device to run inference. If None, the available device will be automatically used. Defaults to None.
 - scope (str, optional) - The scope of the model. Defaults to 'mmseg'.
 
@@ -113,8 +106,7 @@ The model names can be found in models' metafile, like one model name of maskfor
 
 - show (bool) - Whether to display the image in a popup window. Defaults to False.
 - wait_time (float) - The interval of show (s). Defaults to 0.
-- img_out_dir (str) - Subdirectory of `out_dir`, used to save rendering color segmentation mask, so `out_dir` must be defined
-  if you would like to save predicted mask. Defaults to 'vis'.
+- img_out_dir (str) - Subdirectory of `out_dir`, used to save rendering color segmentation mask, so `out_dir` must be defined if you would like to save predicted mask. Defaults to 'vis'.
 - opacity (int, float) - The transparency of segmentation mask. Defaults to 0.8.
 
 The examples of these parameters is in [Basic Usage](#basic-usage)
@@ -245,7 +237,7 @@ vis_image = show_result_pyplot(model, img_path, result)
 # save the visualization result, the output image would be found at the path `work_dirs/result.png`
 vis_iamge = show_result_pyplot(model, img_path, result, out_file='work_dirs/result.png')
 
-# Modify the time of displaying images, note that 0 is the special value that means "forever".
+# Modify the time of displaying images, note that 0 is the special value that means "forever"
 vis_image = show_result_pyplot(model, img_path, result, wait_time=5)
 ```
 
diff --git a/docs/zh_cn/user_guides/2_dataset_prepare.md b/docs/zh_cn/user_guides/2_dataset_prepare.md
index c9c3606977..6d8cb18681 100644
--- a/docs/zh_cn/user_guides/2_dataset_prepare.md
+++ b/docs/zh_cn/user_guides/2_dataset_prepare.md
@@ -1,3 +1,618 @@
-## 准备数据集（待更新）
+# 教程2：准备数据集
 
-中文版文档支持中，请先阅读[英文版本](../../en/user_guides/2_dataset_prepare.md)
+我们建议将数据集根目录符号链接到 `$MMSEGMENTATION/data`。
+如果您的目录结构不同，您可能需要更改配置文件中相应的路径。
+
+```none
+mmsegmentation
+├── mmseg
+├── tools
+├── configs
+├── data
+│   ├── cityscapes
+│   │   ├── leftImg8bit
+│   │   │   ├── train
+│   │   │   ├── val
+│   │   ├── gtFine
+│   │   │   ├── train
+│   │   │   ├── val
+│   ├── VOCdevkit
+│   │   ├── VOC2012
+│   │   │   ├── JPEGImages
+│   │   │   ├── SegmentationClass
+│   │   │   ├── ImageSets
+│   │   │   │   ├── Segmentation
+│   │   ├── VOC2010
+│   │   │   ├── JPEGImages
+│   │   │   ├── SegmentationClassContext
+│   │   │   ├── ImageSets
+│   │   │   │   ├── SegmentationContext
+│   │   │   │   │   ├── train.txt
+│   │   │   │   │   ├── val.txt
+│   │   │   ├── trainval_merged.json
+│   │   ├── VOCaug
+│   │   │   ├── dataset
+│   │   │   │   ├── cls
+│   ├── ade
+│   │   ├── ADEChallengeData2016
+│   │   │   ├── annotations
+│   │   │   │   ├── training
+│   │   │   │   ├── validation
+│   │   │   ├── images
+│   │   │   │   ├── training
+│   │   │   │   ├── validation
+│   ├── coco_stuff10k
+│   │   ├── images
+│   │   │   ├── train2014
+│   │   │   ├── test2014
+│   │   ├── annotations
+│   │   │   ├── train2014
+│   │   │   ├── test2014
+│   │   ├── imagesLists
+│   │   │   ├── train.txt
+│   │   │   ├── test.txt
+│   │   │   ├── all.txt
+│   ├── coco_stuff164k
+│   │   ├── images
+│   │   │   ├── train2017
+│   │   │   ├── val2017
+│   │   ├── annotations
+│   │   │   ├── train2017
+│   │   │   ├── val2017
+│   ├── CHASE_DB1
+│   │   ├── images
+│   │   │   ├── training
+│   │   │   ├── validation
+│   │   ├── annotations
+│   │   │   ├── training
+│   │   │   ├── validation
+│   ├── DRIVE
+│   │   ├── images
+│   │   │   ├── training
+│   │   │   ├── validation
+│   │   ├── annotations
+│   │   │   ├── training
+│   │   │   ├── validation
+│   ├── HRF
+│   │   ├── images
+│   │   │   ├── training
+│   │   │   ├── validation
+│   │   ├── annotations
+│   │   │   ├── training
+│   │   │   ├── validation
+│   ├── STARE
+│   │   ├── images
+│   │   │   ├── training
+│   │   │   ├── validation
+│   │   ├── annotations
+│   │   │   ├── training
+│   │   │   ├── validation
+|   ├── dark_zurich
+|   │   ├── gps
+|   │   │   ├── val
+|   │   │   └── val_ref
+|   │   ├── gt
+|   │   │   └── val
+|   │   ├── LICENSE.txt
+|   │   ├── lists_file_names
+|   │   │   ├── val_filenames.txt
+|   │   │   └── val_ref_filenames.txt
+|   │   ├── README.md
+|   │   └── rgb_anon
+|   │   |   ├── val
+|   │   |   └── val_ref
+|   ├── NighttimeDrivingTest
+|   |   ├── gtCoarse_daytime_trainvaltest
+|   |   │   └── test
+|   |   │       └── night
+|   |   └── leftImg8bit
+|   |   |   └── test
+|   |   |       └── night
+│   ├── loveDA
+│   │   ├── img_dir
+│   │   │   ├── train
+│   │   │   ├── val
+│   │   │   ├── test
+│   │   ├── ann_dir
+│   │   │   ├── train
+│   │   │   ├── val
+│   ├── potsdam
+│   │   ├── img_dir
+│   │   │   ├── train
+│   │   │   ├── val
+│   │   ├── ann_dir
+│   │   │   ├── train
+│   │   │   ├── val
+│   ├── vaihingen
+│   │   ├── img_dir
+│   │   │   ├── train
+│   │   │   ├── val
+│   │   ├── ann_dir
+│   │   │   ├── train
+│   │   │   ├── val
+│   ├── iSAID
+│   │   ├── img_dir
+│   │   │   ├── train
+│   │   │   ├── val
+│   │   │   ├── test
+│   │   ├── ann_dir
+│   │   │   ├── train
+│   │   │   ├── val
+│   ├── synapse
+│   │   ├── img_dir
+│   │   │   ├── train
+│   │   │   ├── val
+│   │   ├── ann_dir
+│   │   │   ├── train
+│   │   │   ├── val
+│   ├── REFUGE
+│   │   ├── images
+│   │   │   ├── training
+│   │   │   ├── validation
+│   │   │   ├── test
+│   │   ├── annotations
+│   │   │   ├── training
+│   │   │   ├── validation
+│   │   │   ├── test
+│   ├── mapillary
+│   │   ├── training
+│   │   │   ├── images
+│   │   │   ├── v1.2
+|   │   │   │   ├── instances
+|   │   │   │   ├── labels
+|   │   │   │   └── panoptic
+│   │   │   ├── v2.0
+|   │   │   │   ├── instances
+|   │   │   │   ├── labels
+|   │   │   │   ├── panoptic
+|   │   │   │   └── polygons
+│   │   ├── validation
+│   │   │   ├── images
+|   │   │   ├── v1.2
+|   │   │   │   ├── instances
+|   │   │   │   ├── labels
+|   │   │   │   └── panoptic
+│   │   │   ├── v2.0
+|   │   │   │   ├── instances
+|   │   │   │   ├── labels
+|   │   │   │   ├── panoptic
+|   │   │   │   └── polygons
+```
+
+## Cityscapes
+
+Cityscapes [官方网站](https://www.cityscapes-dataset.com/)可以下载 Cityscapes 数据集，按照官网要求注册并登陆后，数据可以在[这里](https://www.cityscapes-dataset.com/downloads/)找到。
+
+按照惯例，`**labelTrainIds.png` 用于 cityscapes 训练。
+我们提供了一个基于 [cityscapesscripts](https://github.com/mcordts/cityscapesScripts) 的[脚本](https://github.com/open-mmlab/mmsegmentation/blob/1.x/tools/dataset_converters/cityscapes.py)用于生成 `**labelTrainIds.png`。
+
+```shell
+# --nproc 表示 8 个转换进程，也可以省略。
+python tools/dataset_converters/cityscapes.py data/cityscapes --nproc 8
+```
+
+## Pascal VOC
+
+Pascal VOC 2012 可从[此处](http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar)下载。
+此外，Pascal VOC 数据集的最新工作通常利用额外的增强数据，可以在[这里](http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/semantic_contours/benchmark.tgz)找到。
+
+如果您想使用增强的 VOC 数据集，请运行以下命令将增强数据的标注转换为正确的格式。
+
+```shell
+# --nproc 表示 8 个转换进程，也可以省略。
+python tools/dataset_converters/voc_aug.py data/VOCdevkit data/VOCdevkit/VOCaug --nproc 8
+```
+
+请参考[拼接数据集文档](../advanced_guides/add_datasets.md#拼接数据集)及 [voc_aug 配置示例](../../../configs/_base_/datasets/pascal_voc12_aug.py)以详细了解如何将它们拼接并合并训练。
+
+## ADE20K
+
+ADE20K 的训练和验证集可以从这个[链接](http://data.csail.mit.edu/places/ADEchallenge/ADEChallengeData2016.zip)下载。
+如果需要下载测试数据集，可以在[官网](http://host.robots.ox.ac.uk/)注册后，下载[测试集](http://host.robots.ox.ac.uk:8080/eval/downloads/VOC2010test.tar)。
+
+## Pascal Context
+
+Pascal Context 的训练和验证集可以从[此处](http://host.robots.ox.ac.uk/pascal/VOC/voc2010/VOCtrainval_03-May-2010.tar)下载。注册后，您也可以从[此处](http://host.robots.ox.ac.uk:8080/eval/downloads/VOC2010test.tar)下载测试集。
+
+从原始数据集中抽出部分数据作为验证集，您可以从[此处](https://codalabuser.blob.core.windows.net/public/trainval_merged.json)下载 trainval_merged.json 文件。
+
+请先安装 [Detail](https://github.com/zhanghang1989/detail-api) 工具然后运行以下命令将标注转换为正确的格式。
+
+```shell
+python tools/dataset_converters/pascal_context.py data/VOCdevkit data/VOCdevkit/VOC2010/trainval_merged.json
+```
+
+## COCO Stuff 10k
+
+数据可以通过 wget 在[这里](http://calvin.inf.ed.ac.uk/wp-content/uploads/data/cocostuffdataset/cocostuff-10k-v1.1.zip)下载。
+
+对于 COCO Stuff 10k 数据集，请运行以下命令下载并转换数据集。
+
+```shell
+# 下载
+mkdir coco_stuff10k && cd coco_stuff10k
+wget http://calvin.inf.ed.ac.uk/wp-content/uploads/data/cocostuffdataset/cocostuff-10k-v1.1.zip
+
+# 解压
+unzip cocostuff-10k-v1.1.zip
+
+# --nproc 表示 8 个转换进程，也可以省略。
+python tools/dataset_converters/coco_stuff10k.py /path/to/coco_stuff10k --nproc 8
+```
+
+按照惯例，`/path/to/coco_stuff164k/annotations/*2014/*_labelTrainIds.png` 中的 mask 标注用于 COCO Stuff 10k 的训练和测试。
+
+## COCO Stuff 164k
+
+对于 COCO Stuff 164k 数据集，请运行以下命令下载并转换增强的数据集。
+
+```shell
+# 下载
+mkdir coco_stuff164k && cd coco_stuff164k
+wget http://images.cocodataset.org/zips/train2017.zip
+wget http://images.cocodataset.org/zips/val2017.zip
+wget http://calvin.inf.ed.ac.uk/wp-content/uploads/data/cocostuffdataset/stuffthingmaps_trainval2017.zip
+
+# 解压
+unzip train2017.zip -d images/
+unzip val2017.zip -d images/
+unzip stuffthingmaps_trainval2017.zip -d annotations/
+
+# --nproc 表示 8 个转换进程，也可以省略。
+python tools/dataset_converters/coco_stuff164k.py /path/to/coco_stuff164k --nproc 8
+```
+
+按照惯例，`/path/to/coco_stuff164k/annotations/*2017/*_labelTrainIds.png` 中的 mask 标注用于 COCO Stuff 164k 的训练和测试。
+
+此数据集的详细信息可在[此处](https://github.com/nightrome/cocostuff#downloads)找到。
+
+## CHASE DB1
+
+CHASE DB1 的训练和验证集可以从[此处](https://staffnet.kingston.ac.uk/~ku15565/CHASE_DB1/assets/CHASEDB1.zip)下载。
+
+请运行以下命令，准备 CHASE DB1 数据集：
+
+```shell
+python tools/dataset_converters/chase_db1.py /path/to/CHASEDB1.zip
+```
+
+该脚本将自动调整数据集目录结构，使其满足 MMSegmentation 数据集加载要求。
+
+## DRIVE
+
+按照[官网](https://drive.grand-challenge.org/)要求，注册并登陆后，便可以下载 DRIVE 的训练和验证数据集。
+
+要将 DRIVE 数据集转换为 MMSegmentation 的格式，请运行以下命令：
+
+```shell
+python tools/dataset_converters/drive.py /path/to/training.zip /path/to/test.zip
+```
+
+该脚本将自动调整数据集目录结构，使其满足 MMSegmentation 数据集加载要求。
+
+## HRF
+
+请下载 [health.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/healthy.zip)、[glaucoma.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/glaucoma.zip)、[diabetic_retinopathy.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/diabetic_retinopathy.zip)、[healthy_manualsegm.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/healthy_manualsegm.zip)、[glaucoma_manualsegm.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/glaucoma_manualsegm.zip) 和 [diabetic_retinopathy_manualsegm.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/diabetic_retinopathy_manualsegm.zip)，无需解压，可以直接运行以下命令，准备 HRF 数据集：
+
+```shell
+python tools/dataset_converters/hrf.py /path/to/healthy.zip /path/to/healthy_manualsegm.zip /path/to/glaucoma.zip /path/to/glaucoma_manualsegm.zip /path/to/diabetic_retinopathy.zip /path/to/diabetic_retinopathy_manualsegm.zip
+```
+
+该脚本将自动调整数据集目录结构，使其满足 MMSegmentation 数据集加载要求。
+
+## STARE
+
+请下载 [stare images.tar](http://cecas.clemson.edu/~ahoover/stare/probing/stare-images.tar)、[labels-ah.tar](http://cecas.clemson.edu/~ahoover/stare/probing/labels-ah.tar) 和 [labels-vk.tar](http://cecas.clemson.edu/~ahoover/stare/probing/labels-vk.tar)，无需解压，可以直接运行以下命令，准备 STARE 数据集：
+
+```shell
+python tools/dataset_converters/stare.py /path/to/stare-images.tar /path/to/labels-ah.tar /path/to/labels-vk.tar
+```
+
+该脚本将自动调整数据集目录结构，使其满足 MMSegmentation 数据集加载要求。
+
+## Dark Zurich
+
+由于我们只支持在此数据集上的模型测试，因此您只需要下载并解压[验证数据集](https://data.vision.ee.ethz.ch/csakarid/shared/GCMA_UIoU/Dark_Zurich_val_anon.zip)。
+
+## Nighttime Driving
+
+由于我们只支持在此数据集上的模型测试，因此您只需要下载并解压[验证数据集](http://data.vision.ee.ethz.ch/daid/NighttimeDriving/NighttimeDrivingTest.zip)。
+
+## LoveDA
+
+数据可以从[此处](https://drive.google.com/drive/folders/1ibYV0qwn4yuuh068Rnc-w4tPi0U0c-ti?usp=sharing)下载 LaveDA 数据集。
+
+或者可以从 [zenodo](https://zenodo.org/record/5706578#.YZvN7SYRXdF) 下载。下载后，无需解压，直接运行以下命令：
+
+```shell
+# 下载 Train.zip
+wget https://zenodo.org/record/5706578/files/Train.zip
+# 下载 Val.zip
+wget https://zenodo.org/record/5706578/files/Val.zip
+# 下载 Test.zip
+wget https://zenodo.org/record/5706578/files/Test.zip
+```
+
+请对于 LoveDA 数据集，请运行以下命令调整数据集目录。
+
+```shell
+python tools/dataset_converters/loveda.py /path/to/loveDA
+```
+
+可将模型对 LoveDA 的测试集的预测结果上传至到数据集[测试服务器](https://codalab.lisn.upsaclay.fr/competitions/421)，查看评测结果。
+
+有关 LoveDA 的更多详细信息，可查看[此处](https://github.com/Junjue-Wang/LoveDA).
+
+## ISPRS Potsdam
+
+[Potsdam](https://www2.isprs.org/commissions/comm2/wg4/benchmark/2d-sem-label-potsdam/) 城市语义分割数据集用于 2D 语义分割竞赛 —— Potsdam。
+
+数据集可以在竞赛[主页](https://www2.isprs.org/commissions/comm2/wg4/benchmark/data-request-form/)上请求获得。
+实验中需要下载 '2_Ortho_RGB.zip' 和 '5_Labels_all_noBoundary.zip'。
+
+对于 Potsdam 数据集，请运行以下命令调整数据集目录。
+
+```shell
+python tools/dataset_converters/potsdam.py /path/to/potsdam
+```
+
+在我们的默认设置中，将生成 3456 张图像用于训练和 2016 张图像用于验证。
+
+## ISPRS Vaihingen
+
+[Vaihingen](https://www2.isprs.org/commissions/comm2/wg4/benchmark/2d-sem-label-vaihingen/) 城市语义分割数据集用于 2D 语义分割竞赛 —— Vaihingen。
+
+数据集可以在竞赛[主页](https://www2.isprs.org/commissions/comm2/wg4/benchmark/data-request-form/)上请求获得。
+实验中需要下载 'ISPRS_semantic_labeling_Vaihingen.zip' 和 'ISPRS_semantic_labeling_Vaihingen_ground_truth_eroded_COMPLETE.zip'。
+
+对于 Vaihingen 数据集，请运行以下命令调整数据集目录。
+
+```shell
+python tools/dataset_converters/vaihingen.py /path/to/vaihingen
+```
+
+在我们的默认设置（`clip_size`=512, `stride_size`=256）中，将生成 344 张图像用于训练和 398 张图像用于验证。
+
+## iSAID
+
+iSAID 数据集可从 [DOTA-v1.0](https://captain-whu.github.io/DOTA/dataset.html) 下载训练/验证/测试数据集的图像数据，
+
+并从 [iSAID](https://captain-whu.github.io/iSAID/dataset.html)下载训练/验证数据集的标注数据。
+
+该数据集是航空图像实例分割和语义分割任务的大规模数据集。
+
+下载 iSAID 数据集后，您可能需要按照以下结构进行数据集准备。
+
+```none
+├── data
+│   ├── iSAID
+│   │   ├── train
+│   │   │   ├── images
+│   │   │   │   ├── part1.zip
+│   │   │   │   ├── part2.zip
+│   │   │   │   ├── part3.zip
+│   │   │   ├── Semantic_masks
+│   │   │   │   ├── images.zip
+│   │   ├── val
+│   │   │   ├── images
+│   │   │   │   ├── part1.zip
+│   │   │   ├── Semantic_masks
+│   │   │   │   ├── images.zip
+│   │   ├── test
+│   │   │   ├── images
+│   │   │   │   ├── part1.zip
+│   │   │   │   ├── part2.zip
+```
+
+```shell
+python tools/dataset_converters/isaid.py /path/to/iSAID
+```
+
+在我们的默认设置（`patch_width`=896, `patch_height`=896, `overlap_area`=384）中，将生成 33978 张图像用于训练和 11644 张图像用于验证。
+
+## LIP(Look Into Person) dataset
+
+该数据集可以从[此页面](https://lip.sysuhcp.com/overview.php)下载。
+
+请运行以下命令来解压数据集。
+
+```shell
+unzip LIP.zip
+cd LIP
+unzip TrainVal_images.zip
+unzip TrainVal_parsing_annotations.zip
+cd TrainVal_parsing_annotations
+unzip TrainVal_parsing_annotations.zip
+mv train_segmentations ../
+mv val_segmentations ../
+cd ..
+```
+
+LIP 数据集的内容包括：
+
+```none
+├── data
+│   ├── LIP
+│   │   ├── train_images
+│   │   │   ├── 1000_1234574.jpg
+│   │   │   ├── ...
+│   │   ├── train_segmentations
+│   │   │   ├── 1000_1234574.png
+│   │   │   ├── ...
+│   │   ├── val_images
+│   │   │   ├── 100034_483681.jpg
+│   │   │   ├── ...
+│   │   ├── val_segmentations
+│   │   │   ├── 100034_483681.png
+│   │   │   ├── ...
+```
+
+## Synapse dataset
+
+此数据集可以从[此页面](https://www.synapse.org/#!Synapse:syn3193805/wiki/)下载。
+
+遵循 [TransUNet](https://arxiv.org/abs/2102.04306) 的数据准备设定，将原始训练集（30 次扫描）拆分为新的训练集（18 次扫描）和验证集（12 次扫描）。请运行以下命令来准备数据集。
+
+```shell
+unzip RawData.zip
+cd ./RawData/Training
+```
+
+然后创建 `train.txt` 和 `val.txt` 以拆分数据集。
+
+根据 TransUnet，以下是数据集的划分。
+
+train.txt
+
+```none
+img0005.nii.gz
+img0006.nii.gz
+img0007.nii.gz
+img0009.nii.gz
+img0010.nii.gz
+img0021.nii.gz
+img0023.nii.gz
+img0024.nii.gz
+img0026.nii.gz
+img0027.nii.gz
+img0028.nii.gz
+img0030.nii.gz
+img0031.nii.gz
+img0033.nii.gz
+img0034.nii.gz
+img0037.nii.gz
+img0039.nii.gz
+img0040.nii.gz
+```
+
+val.txt
+
+```none
+img0008.nii.gz
+img0022.nii.gz
+img0038.nii.gz
+img0036.nii.gz
+img0032.nii.gz
+img0002.nii.gz
+img0029.nii.gz
+img0003.nii.gz
+img0001.nii.gz
+img0004.nii.gz
+img0025.nii.gz
+img0035.nii.gz
+```
+
+synapse 数据集的内容包括：
+
+```none
+├── Training
+│   ├── img
+│   │   ├── img0001.nii.gz
+│   │   ├── img0002.nii.gz
+│   │   ├── ...
+│   ├── label
+│   │   ├── label0001.nii.gz
+│   │   ├── label0002.nii.gz
+│   │   ├── ...
+│   ├── train.txt
+│   ├── val.txt
+```
+
+然后，使用此命令转换 synapse 数据集。
+
+```shell
+python tools/dataset_converters/synapse.py --dataset-path /path/to/synapse
+```
+
+注意，MMSegmentation 的默认评估指标（例如 mean dice value）是在 2D 切片图像上计算的，这与 [TransUNet](https://arxiv.org/abs/2102.04306) 等一些论文中的 3D 扫描结果是不同的。
+
+## REFUGE
+
+在 [REFUGE Challenge](https://refuge.grand-challenge.org) 官网上注册并下载 [REFUGE 数据集](https://refuge.grand-challenge.org/REFUGE2Download)。
+
+然后，解压 `REFUGE2.zip`，原始数据集的内容包括：
+
+```none
+├── REFUGE2
+│   ├── REFUGE2
+│   │   ├── Annotation-Training400.zip
+│   │   ├── REFUGE-Test400.zip
+│   │   ├── REFUGE-Test-GT.zip
+│   │   ├── REFUGE-Training400.zip
+│   │   ├── REFUGE-Validation400.zip
+│   │   ├── REFUGE-Validation400-GT.zip
+│   ├── __MACOSX
+```
+
+请运行以下命令转换 REFUGE 数据集：
+
+```shell
+python tools/convert_datasets/refuge.py --raw_data_root=/path/to/refuge/REFUGE2/REFUGE2
+```
+
+脚本会将目录结构转换如下：
+
+```none
+│   ├── REFUGE
+│   │   ├── images
+│   │   │   ├── training
+│   │   │   ├── validation
+│   │   │   ├── test
+│   │   ├── annotations
+│   │   │   ├── training
+│   │   │   ├── validation
+│   │   │   ├── test
+```
+
+包含 400 张用于训练的图像、400 张用于验证的图像和 400 张用于测试的图像，这与 REFUGE 2018 数据集相同。
+
+## Mapillary Vistas Datasets
+
+- Mapillary Vistas [官方网站](https://www.mapillary.com/dataset/vistas) 可以下载 Mapillary Vistas 数据集，按照官网要求注册并登陆后，数据可以在[这里](https://www.mapillary.com/dataset/vistas)找到。
+
+- Mapillary Vistas 数据集使用 8-bit with color-palette 来存储标签。不需要进行转换操作。
+
+- 假设您已将数据集 zip 文件放在 `mmsegmentation/data/mapillary` 中
+
+- 请运行以下命令来解压数据集。
+
+  ```bash
+  cd data/mapillary
+  unzip An-ZjB1Zm61yAZG0ozTymz8I8NqI4x0MrYrh26dq7kPgfu8vf9ImrdaOAVOFYbJ2pNAgUnVGBmbue9lTgdBOb5BbKXIpFs0fpYWqACbrQDChAA2fdX0zS9PcHu7fY8c-FOvyBVxPNYNFQuM.zip
+  ```
+
+- 解压后，您将获得类似于此结构的 Mapillary Vistas 数据集。语义分割 mask 标签在 `labels` 文件夹中。
+
+  ```none
+  mmsegmentation
+  ├── mmseg
+  ├── tools
+  ├── configs
+  ├── data
+  │   ├── mapillary
+  │   │   ├── training
+  │   │   │   ├── images
+  │   │   │   ├── v1.2
+  |   │   │   │   ├── instances
+  |   │   │   │   ├── labels
+  |   │   │   │   └── panoptic
+  │   │   │   ├── v2.0
+  |   │   │   │   ├── instances
+  |   │   │   │   ├── labels
+  |   │   │   │   ├── panoptic
+  |   │   │   │   └── polygons
+  │   │   ├── validation
+  │   │   │   ├── images
+  |   │   │   ├── v1.2
+  |   │   │   │   ├── instances
+  |   │   │   │   ├── labels
+  |   │   │   │   └── panoptic
+  │   │   │   ├── v2.0
+  |   │   │   │   ├── instances
+  |   │   │   │   ├── labels
+  |   │   │   │   ├── panoptic
+  |   │   │   │   └── polygons
+  ```
+
+- 您可以在配置中使用 `MapillaryDataset_v1` 和 `Mapillary Dataset_v2` 设置数据集版本。
+  在此处 [V1.2](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/datasets/mapillary_v1.py) 和 [V2.0](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/datasets/mapillary_v2.py) 查看 Mapillary Vistas 数据集配置文件
diff --git a/docs/zh_cn/user_guides/3_inference.md b/docs/zh_cn/user_guides/3_inference.md
index d2fe60076f..ab68bb47e6 100644
--- a/docs/zh_cn/user_guides/3_inference.md
+++ b/docs/zh_cn/user_guides/3_inference.md
@@ -1,3 +1,244 @@
-## 使用预训练模型推理（待更新）
+# 教程3：使用预训练模型推理
 
-中文版文档支持中，请先阅读[英文版本](../../en/user_guides/3_inference.md)
+MMSegmentation 在 [Model Zoo](../Model_Zoo.md) 中为语义分割提供了预训练的模型，并支持多个标准数据集，包括 Cityscapes、ADE20K 等。
+本说明将展示如何使用现有模型对给定图像进行推理。
+关于如何在标准数据集上测试现有模型，请参阅本[指南](./4_train_test.md)
+
+MMSegmentation 为用户提供了数个接口，以便轻松使用预训练的模型进行推理。
+
+- [教程3：使用预训练模型推理](#教程3使用预训练模型推理)
+  - [推理器](#推理器)
+    - [基本使用](#基本使用)
+    - [初始化](#初始化)
+    - [可视化预测结果](#可视化预测结果)
+    - [模型列表](#模型列表)
+  - [推理 API](#推理-api)
+    - [mmseg.apis.init_model](#mmsegapisinit_model)
+    - [mmseg.apis.inference_model](#mmsegapisinference_model)
+    - [mmseg.apis.show_result_pyplot](#mmsegapisshow_result_pyplot)
+
+## 推理器
+
+在 MMSegmentation 中，我们提供了最**方便的**方式 `MMSegInferencer` 来使用模型。您只需 3 行代码就可以获得图像的分割掩膜。
+
+### 基本使用
+
+以下示例展示了如何使用 `MMSegInferencer` 对单个图像执行推理。
+
+```
+>>> from mmseg.apis import MMSegInferencer
+>>> # 将模型加载到内存中
+>>> inferencer = MMSegInferencer(model='deeplabv3plus_r18-d8_4xb2-80k_cityscapes-512x1024')
+>>> # 推理
+>>> inferencer('demo/demo.png', show=True)
+```
+
+可视化结果应如下所示：
+
+<div align="center">
+    <img src='https://user-images.githubusercontent.com/76149310/221507927-ae01e3a7-016f-4425-b966-7b19cbbe494e.png' />
+</div>
+
+此外，您可以使用 `MMSegInferencer` 来处理一个包含多张图片的 `list`：
+
+```
+# 输入一个图片 list
+>>> images = [image1, image2, ...] # image1 可以是文件路径或 np.ndarray
+>>> inferencer(images, show=True, wait_time=0.5) # wait_time 是延迟时间，0 表示无限
+
+# 或输入图像目录
+>>> images = $IMAGESDIR
+>>> inferencer(images, show=True, wait_time=0.5)
+
+# 保存可视化渲染彩色分割图和预测结果
+# out_dir 是保存输出结果的目录，img_out_dir 和 pred_out_dir 为 out_dir 的子目录
+# 以保存可视化渲染彩色分割图和预测结果
+>>> inferencer(images, out_dir='outputs', img_out_dir='vis', pred_out_dir='pred')
+```
+
+推理器有一个可选参数 `return_datasamples`，其默认值为 False，推理器的返回值默认为 `dict` 类型，包括 'visualization' 和 'predictions' 两个 key。
+如果 `return_datasamples=True` 推理器将返回 [`SegDataSample`](../advanced_guides/structures.md) 或其列表。
+
+```
+result = inferencer('demo/demo.png')
+# 结果是一个包含 'visualization' 和 'predictions' 两个 key 的 `dict`
+# 'visualization' 包含彩色分割图
+print(result['visualization'].shape)
+# (512, 683, 3)
+
+# 'predictions' 包含带有标签索引的分割掩膜
+print(result['predictions'].shape)
+# (512, 683)
+
+result = inferencer('demo/demo.png', return_datasamples=True)
+print(type(result))
+# <class 'mmseg.structures.seg_data_sample.SegDataSample'>
+
+# 输入一个图片 list
+results = inferencer(images)
+# 输出为列表
+print(type(results['visualization']), results['visualization'][0].shape)
+# <class 'list'> (512, 683, 3)
+print(type(results['predictions']), results['predictions'][0].shape)
+# <class 'list'> (512, 683)
+
+results = inferencer(images, return_datasamples=True)
+# <class 'list'>
+print(type(results[0]))
+# <class 'mmseg.structures.seg_data_sample.SegDataSample'>
+```
+
+### 初始化
+
+`MMSegInferencer` 必须使用 `model` 初始化，该 `model` 可以是模型名称或一个 `Config`，甚至可以是配置文件的路径。
+模型名称可以在模型的元文件（configs/xxx/metafile.yaml）中找到，比如 maskformer 的一个模型名称是 `maskformer_r50-d32_8xb2-160k_ade20k-512x512`，如果输入模型名称，模型的权重将自动下载。以下是其他输入参数：
+
+- weights（str，可选）- 权重的路径。如果未指定，并且模型是元文件中的模型名称，则权重将从元文件加载。默认为 None。
+- classes（list，可选）- 输入类别用于结果渲染，由于分割模型的预测结构是标签索引的分割图，`classes` 是一个相应的标签索引的类别列表。若 classes 没有定义，可视化工具将默认使用 `cityscapes` 的类别。默认为 None。
+- palette（list，可选）- 输入调色盘用于结果渲染，它是对应分类的配色列表。若 palette 没有定义，可视化工具将默认使用 `cityscapes` 的调色盘。默认为 None。
+- dataset_name（str，可选）- [数据集名称或别名](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/utils/class_names.py#L302-L317)，可视化工具将使用数据集的元信息，如类别和配色，但 `classes` 和 `palette` 具有更高的优先级。默认为 None。
+- device（str，可选）- 运行推理的设备。如果无，则会自动使用可用的设备。默认为 None。
+- scope（str，可选）- 模型的作用域。默认为 'mmseg'。
+
+### 可视化预测结果
+
+`MMSegInferencer` 有4个用于可视化预测的参数，您可以在初始化推理器时使用它们：
+
+- show（bool）- 是否弹出窗口显示图像。默认为 False。
+- wait_time（float）- 显示的间隔。默认值为 0。
+- img_out_dir（str）- `out_dir` 的子目录，用于保存渲染有色分割掩膜，因此如果要保存预测掩膜，则必须定义 `out_dir`。默认为 `vis`。
+- opacity（int，float）- 分割掩膜的透明度。默认值为 0.8。
+
+这些参数的示例请参考[基本使用](#基本使用)
+
+### 模型列表
+
+在 MMSegmentation 中有一个非常容易列出所有模型名称的方法
+
+```
+>>> from mmseg.apis import MMSegInferencer
+# models 是一个模型名称列表，它们将自动打印
+>>> models = MMSegInferencer.list_models('mmseg')
+```
+
+## 推理 API
+
+### mmseg.apis.init_model
+
+从配置文件初始化一个分割器。
+
+参数：
+
+- config（str，`Path` 或 `mmengine.Config`）- 配置文件路径或配置对象。
+- checkpoint（str，可选）- 权重路径。如果为 None，则模型将不会加载任何权重。
+- device（str，可选）- CPU/CUDA 设备选项。默认为 'cuda:0'。
+- cfg_options（dict，可选）- 用于覆盖所用配置中的某些设置的选项。
+
+返回值：
+
+- nn.Module：构建好的分割器。
+
+示例：
+
+```python
+from mmseg.apis import init_model
+
+config_path = 'configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024.py'
+checkpoint_path = 'checkpoints/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth'
+
+# 初始化不带权重的模型
+model = init_model(config_path)
+
+# 初始化模型并加载权重
+model = init_model(config_path, checkpoint_path)
+
+# 在 CPU 上的初始化模型并加载权重
+model = init_model(config_path, checkpoint_path, 'cpu')
+```
+
+### mmseg.apis.inference_model
+
+使用分割器推理图像。
+
+参数：
+
+- model（nn.Module）- 加载的分割器
+- imgs（str，np.ndarray 或 list\[str/np.ndarray\]）- 图像文件或加载的图像
+
+返回值：
+
+- `SegDataSample` 或 list\[`SegDataSample`\]：如果 imgs 是列表或元组，则返回相同长度的列表类型结果，否则直接返回分割结果。
+
+**注意：** [SegDataSample](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/structures/seg_data_sample.py) 是 MMSegmentation 的数据结构接口，用作不同组件之间的接口。`SegDataSample` 实现抽象数据元素 `mmengine.structures.BaseDataElement`，请参阅 [MMEngine](https://github.com/open-mmlab/mmengine) 中的数据元素[文档](https://mmengine.readthedocs.io/zh_CN/latest/advanced_tutorials/data_element.html)了解更多信息。
+
+`SegDataSample` 中的参数分为几个部分：
+
+- `gt_sem_seg`（`PixelData`）- 语义分割的标注。
+- `pred_sem_seg`（`PixelData`）- 语义分割的预测。
+- `seg_logits`（`PixelData`）- 模型最后一层的输出结果。
+
+**注意：** [PixelData](https://github.com/open-mmlab/mmengine/blob/main/mmengine/structures/pixel_data.py) 是像素级标注或预测的数据结构，请参阅 [MMEngine](https://github.com/open-mmlab/mmengine) 中的 PixelData [文档](https://mmengine.readthedocs.io/en/latest/advanced_tutorials/data_element.html)了解更多信息。
+
+示例：
+
+```python
+from mmseg.apis import init_model, inference_model
+
+config_path = 'configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024.py'
+checkpoint_path = 'checkpoints/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth'
+img_path = 'demo/demo.png'
+
+
+model = init_model(config_path, checkpoint_path)
+result = inference_model(model, img_path)
+```
+
+### mmseg.apis.show_result_pyplot
+
+在图像上可视化分割结果。
+
+参数：
+
+- model（nn.Module）- 加载的分割器。
+- img（str 或 np.ndarray）- 图像文件名或加载的图像。
+- result（`SegDataSample`）- SegDataSample 预测结果。
+- opacity（float）- 绘制分割图的不透明度。默认值为 `0.5`，必须在 `(0，1]` 范围内。
+- title（str）- pyplot 图的标题。默认值为 ''。
+- draw_gt（bool）- 是否绘制 GT SegDataSample。默认为 `True`。
+- draw_pred（draws_pred）- 是否绘制预测 SegDataSample。默认为 `True`。
+- wait_time（float）- 显示的间隔，0 是表示“无限”的特殊值。默认为 `0`。
+- show（bool）- 是否展示绘制的图像。默认为 `True`。
+- save_dir（str，可选）- 为所有存储后端保存的文件路径。如果为 `None`，则后端存储将不会保存任何数据。
+- out_file（str，可选）- 输出文件的路径。默认为 `None`。
+
+返回值：
+
+- np.ndarray：通道为 RGB 的绘制图像。
+
+示例：
+
+```python
+from mmseg.apis import init_model, inference_model, show_result_pyplot
+
+config_path = 'configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024.py'
+checkpoint_path = 'checkpoints/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth'
+img_path = 'demo/demo.png'
+
+
+# 从配置文件和权重文件构建模型
+model = init_model(config_path, checkpoint_path, device='cuda:0')
+
+# 推理给定图像
+result = inference_model(model, img_path)
+
+# 展示分割结果
+vis_image = show_result_pyplot(model, img_path, result)
+
+# 保存可视化结果，输出图像将在 `workdirs/result.png` 路径下找到
+vis_iamge = show_result_pyplot(model, img_path, result, out_file='work_dirs/result.png')
+
+# 修改展示图像的时间，注意 0 是表示“无限”的特殊值
+vis_image = show_result_pyplot(model, img_path, result, wait_time=5)
+```
+
+**注意：** 如果当前设备没有图形用户界面，建议将 `show` 设置为 `False`，并指定 `out_file` 或 `save_dir` 来保存结果。如果您想在窗口上显示结果，则不需要特殊设置。

From 9dbe415847bba1f98b1259ff16ea60ca9aeed069 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E8=B0=A2=E6=98=95=E8=BE=B0?= <xiexinch@outlook.com>
Date: Thu, 30 Mar 2023 15:02:09 +0800
Subject: [PATCH 28/32] [Doc] Add more social networking links (#2802)

---
 README.md       |  8 +++++++-
 README_zh-CN.md | 24 ++++++++++++++++++++++--
 2 files changed, 29 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index a17557cb81..b7855918f8 100644
--- a/README.md
+++ b/README.md
@@ -35,7 +35,7 @@ English | [简体中文](README_zh-CN.md)
 
 <div align="center">
   <a href="https://openmmlab.medium.com/" style="text-decoration:none;">
-    <img src="https://user-images.githubusercontent.com/25839884/218352562-cdded397-b0f3-4ca1-b8dd-a60df8dca75b.png" width="3%" alt="" /></a>
+    <img src="https://user-images.githubusercontent.com/25839884/219255827-67c1a27f-f8c5-46a9-811d-5e57448c61d1.png" width="3%" alt="" /></a>
   <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
   <a href="https://discord.gg/raweFPmdzG" style="text-decoration:none;">
     <img src="https://user-images.githubusercontent.com/25839884/218347213-c080267f-cbb6-443e-8532-8e1ed9a58ea9.png" width="3%" alt="" /></a>
@@ -45,6 +45,12 @@ English | [简体中文](README_zh-CN.md)
   <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
   <a href="https://www.youtube.com/openmmlab" style="text-decoration:none;">
     <img src="https://user-images.githubusercontent.com/25839884/218346691-ceb2116a-465a-40af-8424-9f30d2348ca9.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://space.bilibili.com/1293512903" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/219026751-d7d14cce-a7c9-4e82-9942-8375fca65b99.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://www.zhihu.com/people/openmmlab" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/219026120-ba71e48b-6e94-4bd4-b4e9-b7d175b5e362.png" width="3%" alt="" /></a>
 </div>
 
 ## Introduction
diff --git a/README_zh-CN.md b/README_zh-CN.md
index e09b515ab5..a4e404a710 100644
--- a/README_zh-CN.md
+++ b/README_zh-CN.md
@@ -17,8 +17,6 @@
     </sup>
   </div>
   <div>&nbsp;</div>
-</div>
-<br />
 
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/mmsegmentation)](https://pypi.org/project/mmsegmentation/)
 [![PyPI](https://img.shields.io/pypi/v/mmsegmentation)](https://pypi.org/project/mmsegmentation)
@@ -33,6 +31,28 @@
 
 [English](README.md) | 简体中文
 
+</div>
+
+<div align="center">
+  <a href="https://openmmlab.medium.com/" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/219255827-67c1a27f-f8c5-46a9-811d-5e57448c61d1.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://discord.gg/raweFPmdzG" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/218347213-c080267f-cbb6-443e-8532-8e1ed9a58ea9.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://twitter.com/OpenMMLab" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/218346637-d30c8a0f-3eba-4699-8131-512fb06d46db.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://www.youtube.com/openmmlab" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/218346691-ceb2116a-465a-40af-8424-9f30d2348ca9.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://space.bilibili.com/1293512903" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/219026751-d7d14cce-a7c9-4e82-9942-8375fca65b99.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://www.zhihu.com/people/openmmlab" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/219026120-ba71e48b-6e94-4bd4-b4e9-b7d175b5e362.png" width="3%" alt="" /></a>
+</div>
+
 ## 简介
 
 MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 OpenMMLab 项目的一部分。

From 15979db1ec46fca085defaf65c2d4f8ec376ae8a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E8=B0=A2=E6=98=95=E8=BE=B0?= <xiexinch@outlook.com>
Date: Thu, 30 Mar 2023 15:21:07 +0800
Subject: [PATCH 29/32] [Doc] Add custom metrics document (#2799)

---
 docs/en/advanced_guides/add_metrics.md    | 80 ++++++++++++++++++++++
 docs/zh_cn/advanced_guides/add_metrics.md | 82 ++++++++++++++++++++++-
 2 files changed, 161 insertions(+), 1 deletion(-)

diff --git a/docs/en/advanced_guides/add_metrics.md b/docs/en/advanced_guides/add_metrics.md
index 0a25a81fc4..0298826f05 100644
--- a/docs/en/advanced_guides/add_metrics.md
+++ b/docs/en/advanced_guides/add_metrics.md
@@ -1 +1,81 @@
 # Add New Metrics
+
+## Develop with the source code of MMSegmentation
+
+Here we show how to develop a new metric with an example of `CustomMetric` as the following.
+
+1. Create a new file `mmseg/evaluation/metrics/custom_metric.py`.
+
+   ```python
+   from typing import List, Sequence
+
+   from mmengine.evaluator import BaseMetric
+
+   from mmseg.registry import METRICS
+
+
+   @METRICS.register_module()
+   class CustomMetric(BaseMetric):
+
+       def __init__(self, arg1, arg2):
+           """
+           The metric first processes each batch of data_samples and predictions,
+           and appends the processed results to the results list. Then it
+           collects all results together from all ranks if distributed training
+           is used. Finally, it computes the metrics of the entire dataset.
+           """
+
+       def process(self, data_batch: dict, data_samples: Sequence[dict]) -> None:
+           pass
+
+       def compute_metrics(self, results: list) -> dict:
+           pass
+
+       def evaluate(self, size: int) -> dict:
+           pass
+   ```
+
+   In the above example, `CustomMetric` is a subclass of `BaseMetric`. It has three methods: `process`, `compute_metrics` and `evaluate`.
+
+   - `process()` process one batch of data samples and predictions. The processed results are stored in `self.results` which will be used to compute the metrics after all the data samples are processed. Please refer to [MMEngine documentation](https://github.com/open-mmlab/mmengine/blob/main/docs/en/design/evaluation.md) for more details.
+
+   - `compute_metrics()` is used to compute the metrics from the processed results.
+
+   - `evaluate()` is an interface to compute the metrics and return the results. It will be called by `ValLoop` or `TestLoop` in the `Runner`. In most cases, you don't need to override this method, but you can override it if you want to do some extra work.
+
+   **Note:** You might find the details of calling `evaluate()` method in the `Runner` [here](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/loops.py#L366). The `Runner` is the executor of the training and testing process, you can find more details about it at the [engine document](./engine.md).
+
+2. Import the new metric in `mmseg/evaluation/metrics/__init__.py`.
+
+   ```python
+   from .custom_metric import CustomMetric
+   __all__ = ['CustomMetric', ...]
+   ```
+
+3. Add the new metric to the config file.
+
+   ```python
+   val_evaluator = dict(type='CustomMetric', arg1=xxx, arg2=xxx)
+   test_evaluator = dict(type='CustomMetric', arg1=xxx, arg2=xxx)
+   ```
+
+## Develop with the released version of MMSegmentation
+
+The above example shows how to develop a new metric with the source code of MMSegmentation. If you want to develop a new metric with the released version of MMSegmentation, you can follow the following steps.
+
+1. Create a new file `/Path/to/metrics/custom_metric.py`, implement the `process`, `compute_metrics` and `evaluate` methods, `evaluate` method is optional.
+
+2. Import the new metric in your code or config file.
+
+   ```python
+   from path.to.metrics import CustomMetric
+   ```
+
+   or
+
+   ```python
+   custom_imports = dict(imports=['/Path/to/metrics'], allow_failed_imports=False)
+
+   val_evaluator = dict(type='CustomMetric', arg1=xxx, arg2=xxx)
+   test_evaluator = dict(type='CustomMetric', arg1=xxx, arg2=xxx)
+   ```
diff --git a/docs/zh_cn/advanced_guides/add_metrics.md b/docs/zh_cn/advanced_guides/add_metrics.md
index 3a371e357e..0637b44728 100644
--- a/docs/zh_cn/advanced_guides/add_metrics.md
+++ b/docs/zh_cn/advanced_guides/add_metrics.md
@@ -1 +1,81 @@
-# 新增评测指标 (待更新)
+# 新增评测指标
+
+## 使用 MMSegmentation 的源代码进行开发
+
+在这里，我们用 `CustomMetric` 作为例子来展示如何开发一个新的评测指标。
+
+1. 创建一个新文件 `mmseg/evaluation/metrics/custom_metric.py`。
+
+   ```python
+   from typing import List, Sequence
+
+   from mmengine.evaluator import BaseMetric
+
+   from mmseg.registry import METRICS
+
+
+   @METRICS.register_module()
+   class CustomMetric(BaseMetric):
+
+       def __init__(self, arg1, arg2):
+           """
+           The metric first processes each batch of data_samples and predictions,
+           and appends the processed results to the results list. Then it
+           collects all results together from all ranks if distributed training
+           is used. Finally, it computes the metrics of the entire dataset.
+           """
+
+       def process(self, data_batch: dict, data_samples: Sequence[dict]) -> None:
+           pass
+
+       def compute_metrics(self, results: list) -> dict:
+           pass
+
+       def evaluate(self, size: int) -> dict:
+           pass
+   ```
+
+   在上面的示例中，`CustomMetric` 是 `BaseMetric` 的子类。它有三个方法：`process`，`compute_metrics` 和 `evaluate`。
+
+   - `process()` 处理一批数据样本和预测。处理后的结果需要显示地传给 `self.results` ，将在处理所有数据样本后用于计算指标。更多细节请参考 [MMEngine 文档](https://github.com/open-mmlab/mmengine/blob/main/docs/zh_cn/design/evaluation.md)
+
+   - `compute_metrics()` 用于从处理后的结果中计算指标。
+
+   - `evaluate()` 是一个接口，用于计算指标并返回结果。它将由 `ValLoop` 或 `TestLoop` 在 `Runner` 中调用。在大多数情况下，您不需要重写此方法，但如果您想做一些额外的工作，可以重写它。
+
+   **注意：** 您可以在[这里](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/loops.py#L366) 找到 `Runner` 调用 `evaluate()` 方法的过程。`Runner` 是训练和测试过程的执行器，您可以在[训练引擎文档](./engine.md)中找到有关它的详细信息。
+
+2. 在 `mmseg/evaluation/metrics/__init__.py` 中导入新的指标。
+
+   ```python
+   from .custom_metric import CustomMetric
+   __all__ = ['CustomMetric', ...]
+   ```
+
+3. 在配置文件中设置新的评测指标
+
+   ```python
+   val_evaluator = dict(type='CustomMetric', arg1=xxx, arg2=xxx)
+   test_evaluator = dict(type='CustomMetric', arg1=xxx, arg2=xxx)
+   ```
+
+## 使用发布版本的 MMSegmentation 进行开发
+
+上面的示例展示了如何使用 MMSegmentation 的源代码开发新指标。如果您想使用 MMSegmentation 的发布版本开发新指标，可以按照以下步骤操作。
+
+1. 创建一个新文件 `/Path/to/metrics/custom_metric.py`，实现 `process`，`compute_metrics` 和 `evaluate` 方法，`evaluate` 方法是可选的。
+
+2. 在代码或配置文件中导入新的指标。
+
+   ```python
+   from path.to.metrics import CustomMetric
+   ```
+
+   或者
+
+   ```python
+   custom_imports = dict(imports=['/Path/to/metrics'], allow_failed_imports=False)
+
+   val_evaluator = dict(type='CustomMetric', arg1=xxx, arg2=xxx)
+   test_evaluator = dict(type='CustomMetric', arg1=xxx, arg2=xxx)
+   ```

From 23fb3a9812a110fe4ddbe67f37adb2c7e0281c05 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E8=B0=A2=E6=98=95=E8=BE=B0?= <xiexinch@outlook.com>
Date: Thu, 30 Mar 2023 16:43:15 +0800
Subject: [PATCH 30/32] [Fix] Fix accepting an unexpected argument `local-rank`
 in PyTorch 2.0 (#2812)

---
 tools/test.py  | 5 ++++-
 tools/train.py | 5 ++++-
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/tools/test.py b/tools/test.py
index 64da2bc261..058fdfc864 100644
--- a/tools/test.py
+++ b/tools/test.py
@@ -47,7 +47,10 @@ def parse_args():
         help='job launcher')
     parser.add_argument(
         '--tta', action='store_true', help='Test time augmentation')
-    parser.add_argument('--local_rank', type=int, default=0)
+    # When using PyTorch version >= 2.0.0, the `torch.distributed.launch`
+    # will pass the `--local-rank` parameter to `tools/train.py` instead
+    # of `--local_rank`.
+    parser.add_argument('--local_rank', '--local-rank', type=int, default=0)
     args = parser.parse_args()
     if 'LOCAL_RANK' not in os.environ:
         os.environ['LOCAL_RANK'] = str(args.local_rank)
diff --git a/tools/train.py b/tools/train.py
index 1721306664..10fdaa1874 100644
--- a/tools/train.py
+++ b/tools/train.py
@@ -40,7 +40,10 @@ def parse_args():
         choices=['none', 'pytorch', 'slurm', 'mpi'],
         default='none',
         help='job launcher')
-    parser.add_argument('--local_rank', type=int, default=0)
+    # When using PyTorch version >= 2.0.0, the `torch.distributed.launch`
+    # will pass the `--local-rank` parameter to `tools/train.py` instead
+    # of `--local_rank`.
+    parser.add_argument('--local_rank', '--local-rank', type=int, default=0)
     args = parser.parse_args()
     if 'LOCAL_RANK' not in os.environ:
         os.environ['LOCAL_RANK'] = str(args.local_rank)

From 58b43fc26ed4a58ee5e57bd5bbaae3c0b04942e5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E8=B0=A2=E6=98=95=E8=BE=B0?= <xiexinch@outlook.com>
Date: Thu, 30 Mar 2023 17:22:56 +0800
Subject: [PATCH 31/32] [Doc] Temporarily skip errors in building pdf docs at
 readthedocs (#2814)

---
 .readthedocs.yml | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/.readthedocs.yml b/.readthedocs.yml
index 6cfbf5d310..070c61832b 100644
--- a/.readthedocs.yml
+++ b/.readthedocs.yml
@@ -1,6 +1,7 @@
 version: 2
 
-formats: all
+formats:
+    - epub
 
 python:
   version: 3.7

From c448646a925d1ea00fa1fa1b89c95afc00c9a69b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E8=B0=A2=E6=98=95=E8=BE=B0?= <xiexinch@outlook.com>
Date: Fri, 31 Mar 2023 16:26:30 +0800
Subject: [PATCH 32/32] [Doc] Refine doc and fix links (#2821)

## Motivation

- Create the `main` branch

## Modification

Modify links from `dev-1.x` to `main`
---
 README.md                                     |   2 +-
 configs/ann/README.md                         |  44 ++---
 configs/apcnet/README.md                      |  32 ++--
 configs/beit/README.md                        |   8 +-
 configs/bisenetv1/README.md                   |  30 +--
 configs/bisenetv2/README.md                   |  12 +-
 configs/ccnet/README.md                       |  44 ++---
 configs/cgnet/README.md                       |   8 +-
 configs/convnext/README.md                    |  16 +-
 configs/danet/README.md                       |  44 ++---
 configs/deeplabv3/README.md                   | 110 +++++------
 configs/deeplabv3plus/README.md               | 126 ++++++-------
 configs/dmnet/README.md                       |  32 ++--
 configs/dnlnet/README.md                      |  32 ++--
 configs/dpt/README.md                         |   6 +-
 configs/encnet/README.md                      |  32 ++--
 configs/erfnet/README.md                      |   6 +-
 configs/fastfcn/README.md                     |  34 ++--
 configs/fastscnn/README.md                    |   6 +-
 configs/fcn/README.md                         | 102 +++++-----
 configs/gcnet/README.md                       |  44 ++---
 configs/hrnet/README.md                       | 110 +++++------
 configs/icnet/README.md                       |  28 +--
 configs/isanet/README.md                      |  44 ++---
 configs/knet/README.md                        |  18 +-
 configs/mae/README.md                         |   6 +-
 configs/mask2former/README.md                 |  34 ++--
 configs/maskformer/README.md                  |  12 +-
 configs/mobilenet_v2/README.md                |  24 +--
 configs/mobilenet_v3/README.md                |  12 +-
 configs/nonlocal_net/README.md                |  44 ++---
 configs/ocrnet/README.md                      |  64 +++----
 configs/pidnet/README.md                      |  12 +-
 configs/pidnet/metafile.yaml                  |   6 +-
 configs/point_rend/README.md                  |  16 +-
 configs/poolformer/README.md                  |  14 +-
 configs/psanet/README.md                      |  44 ++---
 configs/pspnet/README.md                      | 174 +++++++++---------
 configs/resnest/README.md                     |  24 +--
 configs/segformer/README.md                   |  34 ++--
 configs/segmenter/README.md                   |  14 +-
 configs/segnext/README.md                     |  16 +-
 configs/segnext/metafile.yaml                 |   8 +-
 configs/sem_fpn/README.md                     |  16 +-
 configs/setr/README.md                        |  22 +--
 configs/stdc/README.md                        |  12 +-
 configs/twins/README.md                       |  28 +--
 configs/unet/README.md                        |  70 +++----
 configs/upernet/README.md                     |  44 ++---
 configs/vit/README.md                         |  26 +--
 demo/MMSegmentation_Tutorial.ipynb            |   4 +-
 docker/Dockerfile                             |   2 +-
 docs/en/advanced_guides/add_models.md         |   6 +-
 docs/en/advanced_guides/data_flow.md          |  22 +--
 docs/en/advanced_guides/datasets.md           |  16 +-
 docs/en/advanced_guides/engine.md             |  24 +--
 docs/en/advanced_guides/evaluation.md         |   5 +-
 docs/en/advanced_guides/models.md             |  21 +--
 docs/en/get_started.md                        |   6 +-
 docs/en/model_zoo.md                          |  60 +++---
 docs/en/modelzoo_statistics.md                |  94 +++++-----
 docs/en/notes/faq.md                          |   2 +-
 docs/en/overview.md                           |   6 +-
 docs/en/switch_language.md                    |   4 +-
 docs/en/user_guides/2_dataset_prepare.md      |   2 +-
 docs/en/user_guides/3_inference.md            |   2 +-
 docs/zh_cn/advanced_guides/add_models.md      |   2 +-
 docs/zh_cn/advanced_guides/data_flow.md       |  22 +--
 docs/zh_cn/advanced_guides/datasets.md        |  14 +-
 docs/zh_cn/advanced_guides/engine.md          |  26 +--
 docs/zh_cn/get_started.md                     |   4 +-
 docs/zh_cn/user_guides/2_dataset_prepare.md   |   2 +-
 docs/zh_cn/user_guides/3_inference.md         |   2 +-
 mmseg/apis/mmseg_inferencer.py                |   4 +-
 mmseg/visualization/local_visualizer.py       |   4 +-
 projects/example_project/README.md            |  10 +-
 projects/faq.md                               |   2 +-
 projects/hssn/README.md                       |   6 +-
 projects/isnet/README.md                      |   8 +-
 projects/mapillary_dataset/README.md          |   2 +-
 .../docs/en/user_guides/2_dataset_prepare.md  |   2 +-
 81 files changed, 1058 insertions(+), 1074 deletions(-)

diff --git a/README.md b/README.md
index b7855918f8..e47f6d080c 100644
--- a/README.md
+++ b/README.md
@@ -97,7 +97,7 @@ Please refer to [get_started.md](docs/en/get_started.md#installation) for instal
 Please see [Overview](docs/en/overview.md) for the general introduction of MMSegmentation.
 
 Please see [user guides](https://mmsegmentation.readthedocs.io/en/1.x/user_guides/index.html#) for the basic usage of MMSegmentation.
-There are also [advanced tutorials](https://mmsegmentation.readthedocs.io/en/dev-1.x/advanced_guides/index.html) for in-depth understanding of mmseg design and implementation .
+There are also [advanced tutorials](https://mmsegmentation.readthedocs.io/en/main/advanced_guides/index.html) for in-depth understanding of mmseg design and implementation .
 
 A Colab tutorial is also provided. You may preview the notebook [here](demo/MMSegmentation_Tutorial.ipynb) or directly [run](https://colab.research.google.com/github/open-mmlab/mmsegmentation/blob/1.x/demo/MMSegmentation_Tutorial.ipynb) on Colab.
 
diff --git a/configs/ann/README.md b/configs/ann/README.md
index cbc1be2dc1..1281a9ee14 100644
--- a/configs/ann/README.md
+++ b/configs/ann/README.md
@@ -26,34 +26,34 @@ The non-local module works as a particularly useful technique for semantic segme
 
 ### Cityscapes
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                               |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| ANN    | R-50-D8  | 512x1024  |   40000 | 6        | 3.71           | V100   | 77.40 |         78.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_40k_cityscapes/ann_r50-d8_512x1024_40k_cityscapes_20200605_095211-049fc292.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_40k_cityscapes/ann_r50-d8_512x1024_40k_cityscapes_20200605_095211.log.json)     |
-| ANN    | R-101-D8 | 512x1024  |   40000 | 9.5      | 2.55           | V100   | 76.55 |         78.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_40k_cityscapes/ann_r101-d8_512x1024_40k_cityscapes_20200605_095243-adf6eece.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_40k_cityscapes/ann_r101-d8_512x1024_40k_cityscapes_20200605_095243.log.json) |
-| ANN    | R-50-D8  | 769x769   |   40000 | 6.8      | 1.70           | V100   | 78.89 |         80.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_40k_cityscapes/ann_r50-d8_769x769_40k_cityscapes_20200530_025712-2b46b04d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_40k_cityscapes/ann_r50-d8_769x769_40k_cityscapes_20200530_025712.log.json)         |
-| ANN    | R-101-D8 | 769x769   |   40000 | 10.7     | 1.15           | V100   | 79.32 |         80.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_40k_cityscapes/ann_r101-d8_769x769_40k_cityscapes_20200530_025720-059bff28.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_40k_cityscapes/ann_r101-d8_769x769_40k_cityscapes_20200530_025720.log.json)     |
-| ANN    | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 77.34 |         78.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_80k_cityscapes/ann_r50-d8_512x1024_80k_cityscapes_20200607_101911-5a9ad545.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_80k_cityscapes/ann_r50-d8_512x1024_80k_cityscapes_20200607_101911.log.json)     |
-| ANN    | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 77.14 |         78.81 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_80k_cityscapes/ann_r101-d8_512x1024_80k_cityscapes_20200607_013728-aceccc6e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_80k_cityscapes/ann_r101-d8_512x1024_80k_cityscapes_20200607_013728.log.json) |
-| ANN    | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 78.88 |         80.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_80k_cityscapes/ann_r50-d8_769x769_80k_cityscapes_20200607_044426-cc7ff323.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_80k_cityscapes/ann_r50-d8_769x769_80k_cityscapes_20200607_044426.log.json)         |
-| ANN    | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 78.80 |         80.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_80k_cityscapes/ann_r101-d8_769x769_80k_cityscapes_20200607_013713-a9d4be8d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_80k_cityscapes/ann_r101-d8_769x769_80k_cityscapes_20200607_013713.log.json)     |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                   | download                                                                                                                                                                                                                                                                                                                               |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ANN    | R-50-D8  | 512x1024  |   40000 | 6        | 3.71           | V100   | 77.40 |         78.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ann/ann_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_40k_cityscapes/ann_r50-d8_512x1024_40k_cityscapes_20200605_095211-049fc292.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_40k_cityscapes/ann_r50-d8_512x1024_40k_cityscapes_20200605_095211.log.json)     |
+| ANN    | R-101-D8 | 512x1024  |   40000 | 9.5      | 2.55           | V100   | 76.55 |         78.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ann/ann_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_40k_cityscapes/ann_r101-d8_512x1024_40k_cityscapes_20200605_095243-adf6eece.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_40k_cityscapes/ann_r101-d8_512x1024_40k_cityscapes_20200605_095243.log.json) |
+| ANN    | R-50-D8  | 769x769   |   40000 | 6.8      | 1.70           | V100   | 78.89 |         80.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ann/ann_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_40k_cityscapes/ann_r50-d8_769x769_40k_cityscapes_20200530_025712-2b46b04d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_40k_cityscapes/ann_r50-d8_769x769_40k_cityscapes_20200530_025712.log.json)         |
+| ANN    | R-101-D8 | 769x769   |   40000 | 10.7     | 1.15           | V100   | 79.32 |         80.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ann/ann_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_40k_cityscapes/ann_r101-d8_769x769_40k_cityscapes_20200530_025720-059bff28.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_40k_cityscapes/ann_r101-d8_769x769_40k_cityscapes_20200530_025720.log.json)     |
+| ANN    | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 77.34 |         78.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ann/ann_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_80k_cityscapes/ann_r50-d8_512x1024_80k_cityscapes_20200607_101911-5a9ad545.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_80k_cityscapes/ann_r50-d8_512x1024_80k_cityscapes_20200607_101911.log.json)     |
+| ANN    | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 77.14 |         78.81 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ann/ann_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_80k_cityscapes/ann_r101-d8_512x1024_80k_cityscapes_20200607_013728-aceccc6e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_80k_cityscapes/ann_r101-d8_512x1024_80k_cityscapes_20200607_013728.log.json) |
+| ANN    | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 78.88 |         80.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ann/ann_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_80k_cityscapes/ann_r50-d8_769x769_80k_cityscapes_20200607_044426-cc7ff323.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_80k_cityscapes/ann_r50-d8_769x769_80k_cityscapes_20200607_044426.log.json)         |
+| ANN    | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 78.80 |         80.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ann/ann_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_80k_cityscapes/ann_r101-d8_769x769_80k_cityscapes_20200607_013713-a9d4be8d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_80k_cityscapes/ann_r101-d8_769x769_80k_cityscapes_20200607_013713.log.json)     |
 
 ### ADE20K
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                                               |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| ANN    | R-50-D8  | 512x512   |   80000 | 9.1      | 21.01          | V100   | 41.01 |         42.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_80k_ade20k/ann_r50-d8_512x512_80k_ade20k_20200615_014818-26f75e11.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_80k_ade20k/ann_r50-d8_512x512_80k_ade20k_20200615_014818.log.json)         |
-| ANN    | R-101-D8 | 512x512   |   80000 | 12.5     | 14.12          | V100   | 42.94 |         44.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_80k_ade20k/ann_r101-d8_512x512_80k_ade20k_20200615_014818-c0153543.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_80k_ade20k/ann_r101-d8_512x512_80k_ade20k_20200615_014818.log.json)     |
-| ANN    | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 41.74 |         42.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_160k_ade20k/ann_r50-d8_512x512_160k_ade20k_20200615_231733-892247bc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_160k_ade20k/ann_r50-d8_512x512_160k_ade20k_20200615_231733.log.json)     |
-| ANN    | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 42.94 |         44.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_160k_ade20k/ann_r101-d8_512x512_160k_ade20k_20200615_231733-955eb1ec.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_160k_ade20k/ann_r101-d8_512x512_160k_ade20k_20200615_231733.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                               | download                                                                                                                                                                                                                                                                                                               |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ANN    | R-50-D8  | 512x512   |   80000 | 9.1      | 21.01          | V100   | 41.01 |         42.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ann/ann_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_80k_ade20k/ann_r50-d8_512x512_80k_ade20k_20200615_014818-26f75e11.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_80k_ade20k/ann_r50-d8_512x512_80k_ade20k_20200615_014818.log.json)         |
+| ANN    | R-101-D8 | 512x512   |   80000 | 12.5     | 14.12          | V100   | 42.94 |         44.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ann/ann_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_80k_ade20k/ann_r101-d8_512x512_80k_ade20k_20200615_014818-c0153543.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_80k_ade20k/ann_r101-d8_512x512_80k_ade20k_20200615_014818.log.json)     |
+| ANN    | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 41.74 |         42.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ann/ann_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_160k_ade20k/ann_r50-d8_512x512_160k_ade20k_20200615_231733-892247bc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_160k_ade20k/ann_r50-d8_512x512_160k_ade20k_20200615_231733.log.json)     |
+| ANN    | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 42.94 |         44.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ann/ann_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_160k_ade20k/ann_r101-d8_512x512_160k_ade20k_20200615_231733-955eb1ec.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_160k_ade20k/ann_r101-d8_512x512_160k_ade20k_20200615_231733.log.json) |
 
 ### Pascal VOC 2012 + Aug
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                   | download                                                                                                                                                                                                                                                                                                                   |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| ANN    | R-50-D8  | 512x512   |   20000 | 6        | 20.92          | V100   | 74.86 |         76.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_20k_voc12aug/ann_r50-d8_512x512_20k_voc12aug_20200617_222246-dfcb1c62.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_20k_voc12aug/ann_r50-d8_512x512_20k_voc12aug_20200617_222246.log.json)     |
-| ANN    | R-101-D8 | 512x512   |   20000 | 9.5      | 13.94          | V100   | 77.47 |         78.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_20k_voc12aug/ann_r101-d8_512x512_20k_voc12aug_20200617_222246-2fad0042.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_20k_voc12aug/ann_r101-d8_512x512_20k_voc12aug_20200617_222246.log.json) |
-| ANN    | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 76.56 |         77.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_40k_voc12aug/ann_r50-d8_512x512_40k_voc12aug_20200613_231314-b5dac322.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_40k_voc12aug/ann_r50-d8_512x512_40k_voc12aug_20200613_231314.log.json)     |
-| ANN    | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 76.70 |         78.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ann/ann_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_40k_voc12aug/ann_r101-d8_512x512_40k_voc12aug_20200613_231314-bd205bbe.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_40k_voc12aug/ann_r101-d8_512x512_40k_voc12aug_20200613_231314.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                | download                                                                                                                                                                                                                                                                                                                   |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ANN    | R-50-D8  | 512x512   |   20000 | 6        | 20.92          | V100   | 74.86 |         76.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ann/ann_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_20k_voc12aug/ann_r50-d8_512x512_20k_voc12aug_20200617_222246-dfcb1c62.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_20k_voc12aug/ann_r50-d8_512x512_20k_voc12aug_20200617_222246.log.json)     |
+| ANN    | R-101-D8 | 512x512   |   20000 | 9.5      | 13.94          | V100   | 77.47 |         78.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ann/ann_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_20k_voc12aug/ann_r101-d8_512x512_20k_voc12aug_20200617_222246-2fad0042.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_20k_voc12aug/ann_r101-d8_512x512_20k_voc12aug_20200617_222246.log.json) |
+| ANN    | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 76.56 |         77.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ann/ann_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_40k_voc12aug/ann_r50-d8_512x512_40k_voc12aug_20200613_231314-b5dac322.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_40k_voc12aug/ann_r50-d8_512x512_40k_voc12aug_20200613_231314.log.json)     |
+| ANN    | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 76.70 |         78.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ann/ann_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_40k_voc12aug/ann_r101-d8_512x512_40k_voc12aug_20200613_231314-bd205bbe.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_40k_voc12aug/ann_r101-d8_512x512_40k_voc12aug_20200613_231314.log.json) |
 
 ## Citation
 
diff --git a/configs/apcnet/README.md b/configs/apcnet/README.md
index 0d7f1d6614..9104f3c87f 100644
--- a/configs/apcnet/README.md
+++ b/configs/apcnet/README.md
@@ -26,25 +26,25 @@ Recent studies witnessed that context features can significantly improve the per
 
 ### Cityscapes
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| APCNet | R-50-D8  | 512x1024  |   40000 | 7.7      | 3.57           | V100   | 78.02 |         79.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_40k_cityscapes/apcnet_r50-d8_512x1024_40k_cityscapes_20201214_115717-5e88fa33.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_40k_cityscapes/apcnet_r50-d8_512x1024_40k_cityscapes-20201214_115717.log.json)     |
-| APCNet | R-101-D8 | 512x1024  |   40000 | 11.2     | 2.15           | V100   | 79.08 |         80.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_40k_cityscapes/apcnet_r101-d8_512x1024_40k_cityscapes_20201214_115716-abc9d111.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_40k_cityscapes/apcnet_r101-d8_512x1024_40k_cityscapes-20201214_115716.log.json) |
-| APCNet | R-50-D8  | 769x769   |   40000 | 8.7      | 1.52           | V100   | 77.89 |         79.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_40k_cityscapes/apcnet_r50-d8_769x769_40k_cityscapes_20201214_115717-2a2628d7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_40k_cityscapes/apcnet_r50-d8_769x769_40k_cityscapes-20201214_115717.log.json)         |
-| APCNet | R-101-D8 | 769x769   |   40000 | 12.7     | 1.03           | V100   | 77.96 |         79.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_40k_cityscapes/apcnet_r101-d8_769x769_40k_cityscapes_20201214_115718-b650de90.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_40k_cityscapes/apcnet_r101-d8_769x769_40k_cityscapes-20201214_115718.log.json)     |
-| APCNet | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 78.96 |         79.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_80k_cityscapes/apcnet_r50-d8_512x1024_80k_cityscapes_20201214_115716-987f51e3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_80k_cityscapes/apcnet_r50-d8_512x1024_80k_cityscapes-20201214_115716.log.json)     |
-| APCNet | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 79.64 |         80.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_80k_cityscapes/apcnet_r101-d8_512x1024_80k_cityscapes_20201214_115705-b1ff208a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_80k_cityscapes/apcnet_r101-d8_512x1024_80k_cityscapes-20201214_115705.log.json) |
-| APCNet | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 78.79 |         80.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_80k_cityscapes/apcnet_r50-d8_769x769_80k_cityscapes_20201214_115718-7ea9fa12.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_80k_cityscapes/apcnet_r50-d8_769x769_80k_cityscapes-20201214_115718.log.json)         |
-| APCNet | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 78.45 |         79.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_80k_cityscapes/apcnet_r101-d8_769x769_80k_cityscapes_20201214_115716-a7fbc2ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_80k_cityscapes/apcnet_r101-d8_769x769_80k_cityscapes-20201214_115716.log.json)     |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| APCNet | R-50-D8  | 512x1024  |   40000 | 7.7      | 3.57           | V100   | 78.02 |         79.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/apcnet/apcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_40k_cityscapes/apcnet_r50-d8_512x1024_40k_cityscapes_20201214_115717-5e88fa33.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_40k_cityscapes/apcnet_r50-d8_512x1024_40k_cityscapes-20201214_115717.log.json)     |
+| APCNet | R-101-D8 | 512x1024  |   40000 | 11.2     | 2.15           | V100   | 79.08 |         80.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/apcnet/apcnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_40k_cityscapes/apcnet_r101-d8_512x1024_40k_cityscapes_20201214_115716-abc9d111.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_40k_cityscapes/apcnet_r101-d8_512x1024_40k_cityscapes-20201214_115716.log.json) |
+| APCNet | R-50-D8  | 769x769   |   40000 | 8.7      | 1.52           | V100   | 77.89 |         79.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/apcnet/apcnet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_40k_cityscapes/apcnet_r50-d8_769x769_40k_cityscapes_20201214_115717-2a2628d7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_40k_cityscapes/apcnet_r50-d8_769x769_40k_cityscapes-20201214_115717.log.json)         |
+| APCNet | R-101-D8 | 769x769   |   40000 | 12.7     | 1.03           | V100   | 77.96 |         79.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/apcnet/apcnet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_40k_cityscapes/apcnet_r101-d8_769x769_40k_cityscapes_20201214_115718-b650de90.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_40k_cityscapes/apcnet_r101-d8_769x769_40k_cityscapes-20201214_115718.log.json)     |
+| APCNet | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 78.96 |         79.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/apcnet/apcnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_80k_cityscapes/apcnet_r50-d8_512x1024_80k_cityscapes_20201214_115716-987f51e3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_80k_cityscapes/apcnet_r50-d8_512x1024_80k_cityscapes-20201214_115716.log.json)     |
+| APCNet | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 79.64 |         80.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/apcnet/apcnet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_80k_cityscapes/apcnet_r101-d8_512x1024_80k_cityscapes_20201214_115705-b1ff208a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_80k_cityscapes/apcnet_r101-d8_512x1024_80k_cityscapes-20201214_115705.log.json) |
+| APCNet | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 78.79 |         80.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/apcnet/apcnet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_80k_cityscapes/apcnet_r50-d8_769x769_80k_cityscapes_20201214_115718-7ea9fa12.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_80k_cityscapes/apcnet_r50-d8_769x769_80k_cityscapes-20201214_115718.log.json)         |
+| APCNet | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 78.45 |         79.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/apcnet/apcnet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_80k_cityscapes/apcnet_r101-d8_769x769_80k_cityscapes_20201214_115716-a7fbc2ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_80k_cityscapes/apcnet_r101-d8_769x769_80k_cityscapes-20201214_115716.log.json)     |
 
 ### ADE20K
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| APCNet | R-50-D8  | 512x512   |   80000 | 10.1     | 19.61          | V100   | 42.20 |         43.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_80k_ade20k/apcnet_r50-d8_512x512_80k_ade20k_20201214_115705-a8626293.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_80k_ade20k/apcnet_r50-d8_512x512_80k_ade20k-20201214_115705.log.json)         |
-| APCNet | R-101-D8 | 512x512   |   80000 | 13.6     | 13.10          | V100   | 45.54 |         46.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_80k_ade20k/apcnet_r101-d8_512x512_80k_ade20k_20201214_115704-c656c3fb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_80k_ade20k/apcnet_r101-d8_512x512_80k_ade20k-20201214_115704.log.json)     |
-| APCNet | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 43.40 |         43.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_160k_ade20k/apcnet_r50-d8_512x512_160k_ade20k_20201214_115706-25fb92c2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_160k_ade20k/apcnet_r50-d8_512x512_160k_ade20k-20201214_115706.log.json)     |
-| APCNet | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 45.41 |         46.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/apcnet/apcnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_160k_ade20k/apcnet_r101-d8_512x512_160k_ade20k_20201214_115705-73f9a8d7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_160k_ade20k/apcnet_r101-d8_512x512_160k_ade20k-20201214_115705.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| APCNet | R-50-D8  | 512x512   |   80000 | 10.1     | 19.61          | V100   | 42.20 |         43.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/apcnet/apcnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_80k_ade20k/apcnet_r50-d8_512x512_80k_ade20k_20201214_115705-a8626293.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_80k_ade20k/apcnet_r50-d8_512x512_80k_ade20k-20201214_115705.log.json)         |
+| APCNet | R-101-D8 | 512x512   |   80000 | 13.6     | 13.10          | V100   | 45.54 |         46.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/apcnet/apcnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_80k_ade20k/apcnet_r101-d8_512x512_80k_ade20k_20201214_115704-c656c3fb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_80k_ade20k/apcnet_r101-d8_512x512_80k_ade20k-20201214_115704.log.json)     |
+| APCNet | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 43.40 |         43.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/apcnet/apcnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_160k_ade20k/apcnet_r50-d8_512x512_160k_ade20k_20201214_115706-25fb92c2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_160k_ade20k/apcnet_r50-d8_512x512_160k_ade20k-20201214_115706.log.json)     |
+| APCNet | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 45.41 |         46.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/apcnet/apcnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_160k_ade20k/apcnet_r101-d8_512x512_160k_ade20k_20201214_115705-73f9a8d7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_160k_ade20k/apcnet_r101-d8_512x512_160k_ade20k-20201214_115705.log.json) |
 
 ## Citation
 
diff --git a/configs/beit/README.md b/configs/beit/README.md
index 8e34e29410..b005c88c50 100644
--- a/configs/beit/README.md
+++ b/configs/beit/README.md
@@ -67,10 +67,10 @@ upernet_beit-large_fp16_8x1_640x640_160k_ade20k-8fc0dd5d.pth $GPUS --eval mIoU
 
 ### ADE20K
 
-| Method  | Backbone | Crop Size | pretrain     | pretrain img size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                              | download                                                                                                                                                                                                                                                                                                                                                 |
-| ------- | -------- | --------- | ------------ | ----------------- | ---------- | ------- | -------- | -------------- | ------ | ----- | ------------: | ----------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UPerNet | BEiT-B   | 640x640   | ImageNet-22K | 224x224           | 16         | 160000  | 15.88    | 2.00           | V100   | 53.08 |         53.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/beit/beit-base_upernet_8xb2-160k_ade20k-640x640.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-base_8x2_640x640_160k_ade20k/upernet_beit-base_8x2_640x640_160k_ade20k-eead221d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-base_8x2_640x640_160k_ade20k/upernet_beit-base_8x2_640x640_160k_ade20k.log.json)                         |
-| UPerNet | BEiT-L   | 640x640   | ImageNet-22K | 224x224           | 8          | 320000  | 22.64    | 0.96           | V100   | 56.33 |         56.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/beit/beit-large_upernet_8xb1-amp-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-large_fp16_8x1_640x640_160k_ade20k/upernet_beit-large_fp16_8x1_640x640_160k_ade20k-8fc0dd5d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-large_fp16_8x1_640x640_160k_ade20k/upernet_beit-large_fp16_8x1_640x640_160k_ade20k.log.json) |
+| Method  | Backbone | Crop Size | pretrain     | pretrain img size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                 |
+| ------- | -------- | --------- | ------------ | ----------------- | ---------- | ------- | -------- | -------------- | ------ | ----- | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UPerNet | BEiT-B   | 640x640   | ImageNet-22K | 224x224           | 16         | 160000  | 15.88    | 2.00           | V100   | 53.08 |         53.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/beit/beit-base_upernet_8xb2-160k_ade20k-640x640.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-base_8x2_640x640_160k_ade20k/upernet_beit-base_8x2_640x640_160k_ade20k-eead221d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-base_8x2_640x640_160k_ade20k/upernet_beit-base_8x2_640x640_160k_ade20k.log.json)                         |
+| UPerNet | BEiT-L   | 640x640   | ImageNet-22K | 224x224           | 8          | 320000  | 22.64    | 0.96           | V100   | 56.33 |         56.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/beit/beit-large_upernet_8xb1-amp-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-large_fp16_8x1_640x640_160k_ade20k/upernet_beit-large_fp16_8x1_640x640_160k_ade20k-8fc0dd5d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/beit/upernet_beit-large_fp16_8x1_640x640_160k_ade20k/upernet_beit-large_fp16_8x1_640x640_160k_ade20k.log.json) |
 
 ## Citation
 
diff --git a/configs/bisenetv1/README.md b/configs/bisenetv1/README.md
index c895fdfe63..a5058957f0 100644
--- a/configs/bisenetv1/README.md
+++ b/configs/bisenetv1/README.md
@@ -26,24 +26,24 @@ Semantic segmentation requires both rich spatial information and sizeable recept
 
 ### Cityscapes
 
-| Method    | Backbone               | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                             | download                                                                                                                                                                                                                                                                                                                                                                                                                               |
-| --------- | ---------------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| BiSeNetV1 | R-18-D32 (No Pretrain) | 1024x1024 |  160000 | 5.69     | 31.77          | V100   | 74.44 | 77.05         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r18-d32_4xb4-160k_cityscapes-1024x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes_20210922_172239-c55e78e2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes_20210922_172239.log.json)                                     |
-| BiSeNetV1 | R-18-D32               | 1024x1024 |  160000 | 5.69     | 31.77          | V100   | 74.37 | 76.91         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r18-d32-in1k-pre_4xb4-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210905_220251-8ba80eff.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210905_220251.log.json) |
-| BiSeNetV1 | R-18-D32 (4x8)         | 1024x1024 |  160000 | 11.17    | 31.77          | V100   | 75.16 | 77.24         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r18-d32-in1k-pre_4xb8-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes_20210905_220322-bb8db75f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes_20210905_220322.log.json) |
-| BiSeNetV1 | R-50-D32 (No Pretrain) | 1024x1024 |  160000 | 15.39    | 7.71           | V100   | 76.92 | 78.87         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r50-d32_4xb4-160k_cityscapes-1024x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes_20210923_222639-7b28a2a6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes_20210923_222639.log.json)                                     |
-| BiSeNetV1 | R-50-D32               | 1024x1024 |  160000 | 15.39    | 7.71           | V100   | 77.68 | 79.57         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r50-d32-in1k-pre_4xb4-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210917_234628-8b304447.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210917_234628.log.json) |
+| Method    | Backbone               | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| --------- | ---------------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| BiSeNetV1 | R-18-D32 (No Pretrain) | 1024x1024 |  160000 | 5.69     | 31.77          | V100   | 74.44 | 77.05         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/bisenetv1/bisenetv1_r18-d32_4xb4-160k_cityscapes-1024x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes_20210922_172239-c55e78e2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes_20210922_172239.log.json)                                     |
+| BiSeNetV1 | R-18-D32               | 1024x1024 |  160000 | 5.69     | 31.77          | V100   | 74.37 | 76.91         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/bisenetv1/bisenetv1_r18-d32-in1k-pre_4xb4-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210905_220251-8ba80eff.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210905_220251.log.json) |
+| BiSeNetV1 | R-18-D32 (4x8)         | 1024x1024 |  160000 | 11.17    | 31.77          | V100   | 75.16 | 77.24         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/bisenetv1/bisenetv1_r18-d32-in1k-pre_4xb8-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes_20210905_220322-bb8db75f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes_20210905_220322.log.json) |
+| BiSeNetV1 | R-50-D32 (No Pretrain) | 1024x1024 |  160000 | 15.39    | 7.71           | V100   | 76.92 | 78.87         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/bisenetv1/bisenetv1_r50-d32_4xb4-160k_cityscapes-1024x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes_20210923_222639-7b28a2a6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes_20210923_222639.log.json)                                     |
+| BiSeNetV1 | R-50-D32               | 1024x1024 |  160000 | 15.39    | 7.71           | V100   | 77.68 | 79.57         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/bisenetv1/bisenetv1_r50-d32-in1k-pre_4xb4-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210917_234628-8b304447.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210917_234628.log.json) |
 
 ### COCO-Stuff 164k
 
-| Method    | Backbone                | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                                | download                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
-| --------- | ----------------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| BiSeNetV1 | R-18-D32 (No Pretrain)  | 512x512   |  160000 | -        | -              | V100   | 25.45 | 26.15         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r18-d32_4xb4-160k_coco-stuff164k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211022_054328-046aa2f2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211022_054328.log.json)                                         |
-| BiSeNetV1 | R-18-D32                | 512x512   |  160000 | 6.33     | 74.24          | V100   | 28.55 | 29.26         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r18-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211023_013100-f700dbf7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211023_013100.log.json)     |
-| BiSeNetV1 | R-50-D32 (No Pretrain)  | 512x512   |  160000 | -        | -              | V100   | 29.82 | 30.33         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r50-d32_4xb4-160k_coco-stuff164k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_040616-d2bb0df4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_040616.log.json)                                         |
-| BiSeNetV1 | R-50-D32                | 512x512   |  160000 | 9.28     | 32.60          | V100   | 34.88 | 35.37         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r50-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_181932-66747911.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_181932.log.json)     |
-| BiSeNetV1 | R-101-D32 (No Pretrain) | 512x512   |  160000 | -        | -              | V100   | 31.14 | 31.76         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r50-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211102_164147-c6b32c3b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211102_164147.log.json)                                     |
-| BiSeNetV1 | R-101-D32               | 512x512   |  160000 | 10.36    | 25.25          | V100   | 37.38 | 37.99         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv1/bisenetv1_r101-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_225220-28c8f092.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_225220.log.json) |
+| Method    | Backbone                | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                             | download                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
+| --------- | ----------------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| BiSeNetV1 | R-18-D32 (No Pretrain)  | 512x512   |  160000 | -        | -              | V100   | 25.45 | 26.15         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/bisenetv1/bisenetv1_r18-d32_4xb4-160k_coco-stuff164k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211022_054328-046aa2f2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211022_054328.log.json)                                         |
+| BiSeNetV1 | R-18-D32                | 512x512   |  160000 | 6.33     | 74.24          | V100   | 28.55 | 29.26         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/bisenetv1/bisenetv1_r18-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211023_013100-f700dbf7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211023_013100.log.json)     |
+| BiSeNetV1 | R-50-D32 (No Pretrain)  | 512x512   |  160000 | -        | -              | V100   | 29.82 | 30.33         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/bisenetv1/bisenetv1_r50-d32_4xb4-160k_coco-stuff164k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_040616-d2bb0df4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_040616.log.json)                                         |
+| BiSeNetV1 | R-50-D32                | 512x512   |  160000 | 9.28     | 32.60          | V100   | 34.88 | 35.37         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/bisenetv1/bisenetv1_r50-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_181932-66747911.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_181932.log.json)     |
+| BiSeNetV1 | R-101-D32 (No Pretrain) | 512x512   |  160000 | -        | -              | V100   | 31.14 | 31.76         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/bisenetv1/bisenetv1_r50-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211102_164147-c6b32c3b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211102_164147.log.json)                                     |
+| BiSeNetV1 | R-101-D32               | 512x512   |  160000 | 10.36    | 25.25          | V100   | 37.38 | 37.99         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/bisenetv1/bisenetv1_r101-d32-in1k-pre_4xb4-160k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_225220-28c8f092.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_225220.log.json) |
 
 Note:
 
diff --git a/configs/bisenetv2/README.md b/configs/bisenetv2/README.md
index 1f44c01f36..a5871dfeb9 100644
--- a/configs/bisenetv2/README.md
+++ b/configs/bisenetv2/README.md
@@ -26,12 +26,12 @@ The low-level details and high-level semantics are both essential to the semanti
 
 ### Cityscapes
 
-| Method    | Backbone         | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                                                               |
-| --------- | ---------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| BiSeNetV2 | BiSeNetV2        | 1024x1024 |  160000 | 7.64     | 31.77          | V100   | 73.21 |         75.74 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv2/bisenetv2_fcn_4xb4-160k_cityscapes-1024x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes_20210902_015551-bcf10f09.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes_20210902_015551.log.json)                     |
-| BiSeNetV2 | BiSeNetV2 (OHEM) | 1024x1024 |  160000 | 7.64     | -              | V100   | 73.57 |         75.80 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv2/bisenetv2_fcn_4xb4-ohem-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes_20210902_112947-5f8103b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes_20210902_112947.log.json) |
-| BiSeNetV2 | BiSeNetV2 (4x8)  | 1024x1024 |  160000 | 15.05    | -              | V100   | 75.76 |         77.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv2/bisenetv2_fcn_4xb8-160k_cityscapes-1024x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes_20210903_000032-e1a2eed6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes_20210903_000032.log.json)                     |
-| BiSeNetV2 | BiSeNetV2 (FP16) | 1024x1024 |  160000 | 5.77     | 36.65          | V100   | 73.07 |         75.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/bisenetv2/bisenetv2_fcn_4xb4-amp-160k_cityscapes-1024x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes_20210902_045942-b979777b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes_20210902_045942.log.json) |
+| Method    | Backbone         | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                  | download                                                                                                                                                                                                                                                                                                                                                                                               |
+| --------- | ---------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| BiSeNetV2 | BiSeNetV2        | 1024x1024 |  160000 | 7.64     | 31.77          | V100   | 73.21 |         75.74 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/bisenetv2/bisenetv2_fcn_4xb4-160k_cityscapes-1024x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes_20210902_015551-bcf10f09.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes_20210902_015551.log.json)                     |
+| BiSeNetV2 | BiSeNetV2 (OHEM) | 1024x1024 |  160000 | 7.64     | -              | V100   | 73.57 |         75.80 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/bisenetv2/bisenetv2_fcn_4xb4-ohem-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes_20210902_112947-5f8103b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes_20210902_112947.log.json) |
+| BiSeNetV2 | BiSeNetV2 (4x8)  | 1024x1024 |  160000 | 15.05    | -              | V100   | 75.76 |         77.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/bisenetv2/bisenetv2_fcn_4xb8-160k_cityscapes-1024x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes_20210903_000032-e1a2eed6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes_20210903_000032.log.json)                     |
+| BiSeNetV2 | BiSeNetV2 (FP16) | 1024x1024 |  160000 | 5.77     | 36.65          | V100   | 73.07 |         75.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/bisenetv2/bisenetv2_fcn_4xb4-amp-160k_cityscapes-1024x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes_20210902_045942-b979777b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes_20210902_045942.log.json) |
 
 Note:
 
diff --git a/configs/ccnet/README.md b/configs/ccnet/README.md
index c7a0163495..64dd5f0298 100644
--- a/configs/ccnet/README.md
+++ b/configs/ccnet/README.md
@@ -26,34 +26,34 @@ Contextual information is vital in visual understanding problems, such as semant
 
 ### Cityscapes
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| CCNet  | R-50-D8  | 512x1024  |   40000 | 6        | 3.32           | V100   | 77.76 |         78.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_40k_cityscapes/ccnet_r50-d8_512x1024_40k_cityscapes_20200616_142517-4123f401.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_40k_cityscapes/ccnet_r50-d8_512x1024_40k_cityscapes_20200616_142517.log.json)     |
-| CCNet  | R-101-D8 | 512x1024  |   40000 | 9.5      | 2.31           | V100   | 76.35 |         78.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_40k_cityscapes/ccnet_r101-d8_512x1024_40k_cityscapes_20200616_142540-a3b84ba6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_40k_cityscapes/ccnet_r101-d8_512x1024_40k_cityscapes_20200616_142540.log.json) |
-| CCNet  | R-50-D8  | 769x769   |   40000 | 6.8      | 1.43           | V100   | 78.46 |         79.93 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_40k_cityscapes/ccnet_r50-d8_769x769_40k_cityscapes_20200616_145125-76d11884.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_40k_cityscapes/ccnet_r50-d8_769x769_40k_cityscapes_20200616_145125.log.json)         |
-| CCNet  | R-101-D8 | 769x769   |   40000 | 10.7     | 1.01           | V100   | 76.94 |         78.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_40k_cityscapes/ccnet_r101-d8_769x769_40k_cityscapes_20200617_101428-4f57c8d0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_40k_cityscapes/ccnet_r101-d8_769x769_40k_cityscapes_20200617_101428.log.json)     |
-| CCNet  | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 79.03 |         80.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_80k_cityscapes/ccnet_r50-d8_512x1024_80k_cityscapes_20200617_010421-869a3423.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_80k_cityscapes/ccnet_r50-d8_512x1024_80k_cityscapes_20200617_010421.log.json)     |
-| CCNet  | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 78.87 |         79.90 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_80k_cityscapes/ccnet_r101-d8_512x1024_80k_cityscapes_20200617_203935-ffae8917.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_80k_cityscapes/ccnet_r101-d8_512x1024_80k_cityscapes_20200617_203935.log.json) |
-| CCNet  | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 79.29 |         81.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_80k_cityscapes/ccnet_r50-d8_769x769_80k_cityscapes_20200617_010421-73eed8ca.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_80k_cityscapes/ccnet_r50-d8_769x769_80k_cityscapes_20200617_010421.log.json)         |
-| CCNet  | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 79.45 |         80.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_80k_cityscapes/ccnet_r101-d8_769x769_80k_cityscapes_20200618_011502-ad3cd481.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_80k_cityscapes/ccnet_r101-d8_769x769_80k_cityscapes_20200618_011502.log.json)     |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| CCNet  | R-50-D8  | 512x1024  |   40000 | 6        | 3.32           | V100   | 77.76 |         78.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ccnet/ccnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_40k_cityscapes/ccnet_r50-d8_512x1024_40k_cityscapes_20200616_142517-4123f401.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_40k_cityscapes/ccnet_r50-d8_512x1024_40k_cityscapes_20200616_142517.log.json)     |
+| CCNet  | R-101-D8 | 512x1024  |   40000 | 9.5      | 2.31           | V100   | 76.35 |         78.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ccnet/ccnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_40k_cityscapes/ccnet_r101-d8_512x1024_40k_cityscapes_20200616_142540-a3b84ba6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_40k_cityscapes/ccnet_r101-d8_512x1024_40k_cityscapes_20200616_142540.log.json) |
+| CCNet  | R-50-D8  | 769x769   |   40000 | 6.8      | 1.43           | V100   | 78.46 |         79.93 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ccnet/ccnet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_40k_cityscapes/ccnet_r50-d8_769x769_40k_cityscapes_20200616_145125-76d11884.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_40k_cityscapes/ccnet_r50-d8_769x769_40k_cityscapes_20200616_145125.log.json)         |
+| CCNet  | R-101-D8 | 769x769   |   40000 | 10.7     | 1.01           | V100   | 76.94 |         78.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ccnet/ccnet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_40k_cityscapes/ccnet_r101-d8_769x769_40k_cityscapes_20200617_101428-4f57c8d0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_40k_cityscapes/ccnet_r101-d8_769x769_40k_cityscapes_20200617_101428.log.json)     |
+| CCNet  | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 79.03 |         80.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ccnet/ccnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_80k_cityscapes/ccnet_r50-d8_512x1024_80k_cityscapes_20200617_010421-869a3423.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_80k_cityscapes/ccnet_r50-d8_512x1024_80k_cityscapes_20200617_010421.log.json)     |
+| CCNet  | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 78.87 |         79.90 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ccnet/ccnet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_80k_cityscapes/ccnet_r101-d8_512x1024_80k_cityscapes_20200617_203935-ffae8917.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_80k_cityscapes/ccnet_r101-d8_512x1024_80k_cityscapes_20200617_203935.log.json) |
+| CCNet  | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 79.29 |         81.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ccnet/ccnet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_80k_cityscapes/ccnet_r50-d8_769x769_80k_cityscapes_20200617_010421-73eed8ca.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_80k_cityscapes/ccnet_r50-d8_769x769_80k_cityscapes_20200617_010421.log.json)         |
+| CCNet  | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 79.45 |         80.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ccnet/ccnet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_80k_cityscapes/ccnet_r101-d8_769x769_80k_cityscapes_20200618_011502-ad3cd481.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_80k_cityscapes/ccnet_r101-d8_769x769_80k_cityscapes_20200618_011502.log.json)     |
 
 ### ADE20K
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| CCNet  | R-50-D8  | 512x512   |   80000 | 8.8      | 20.89          | V100   | 41.78 |         42.98 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_80k_ade20k/ccnet_r50-d8_512x512_80k_ade20k_20200615_014848-aa37f61e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_80k_ade20k/ccnet_r50-d8_512x512_80k_ade20k_20200615_014848.log.json)         |
-| CCNet  | R-101-D8 | 512x512   |   80000 | 12.2     | 14.11          | V100   | 43.97 |         45.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_80k_ade20k/ccnet_r101-d8_512x512_80k_ade20k_20200615_014848-1f4929a3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_80k_ade20k/ccnet_r101-d8_512x512_80k_ade20k_20200615_014848.log.json)     |
-| CCNet  | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 42.08 |         43.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_160k_ade20k/ccnet_r50-d8_512x512_160k_ade20k_20200616_084435-7c97193b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_160k_ade20k/ccnet_r50-d8_512x512_160k_ade20k_20200616_084435.log.json)     |
-| CCNet  | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 43.71 |         45.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_160k_ade20k/ccnet_r101-d8_512x512_160k_ade20k_20200616_000644-e849e007.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_160k_ade20k/ccnet_r101-d8_512x512_160k_ade20k_20200616_000644.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                   | download                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| CCNet  | R-50-D8  | 512x512   |   80000 | 8.8      | 20.89          | V100   | 41.78 |         42.98 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ccnet/ccnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_80k_ade20k/ccnet_r50-d8_512x512_80k_ade20k_20200615_014848-aa37f61e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_80k_ade20k/ccnet_r50-d8_512x512_80k_ade20k_20200615_014848.log.json)         |
+| CCNet  | R-101-D8 | 512x512   |   80000 | 12.2     | 14.11          | V100   | 43.97 |         45.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ccnet/ccnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_80k_ade20k/ccnet_r101-d8_512x512_80k_ade20k_20200615_014848-1f4929a3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_80k_ade20k/ccnet_r101-d8_512x512_80k_ade20k_20200615_014848.log.json)     |
+| CCNet  | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 42.08 |         43.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ccnet/ccnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_160k_ade20k/ccnet_r50-d8_512x512_160k_ade20k_20200616_084435-7c97193b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_160k_ade20k/ccnet_r50-d8_512x512_160k_ade20k_20200616_084435.log.json)     |
+| CCNet  | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 43.71 |         45.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ccnet/ccnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_160k_ade20k/ccnet_r101-d8_512x512_160k_ade20k_20200616_000644-e849e007.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_160k_ade20k/ccnet_r101-d8_512x512_160k_ade20k_20200616_000644.log.json) |
 
 ### Pascal VOC 2012 + Aug
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                               |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| CCNet  | R-50-D8  | 512x512   |   20000 | 6        | 20.45          | V100   | 76.17 |         77.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_20k_voc12aug/ccnet_r50-d8_512x512_20k_voc12aug_20200617_193212-fad81784.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_20k_voc12aug/ccnet_r50-d8_512x512_20k_voc12aug_20200617_193212.log.json)     |
-| CCNet  | R-101-D8 | 512x512   |   20000 | 9.5      | 13.64          | V100   | 77.27 |         79.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_20k_voc12aug/ccnet_r101-d8_512x512_20k_voc12aug_20200617_193212-0007b61d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_20k_voc12aug/ccnet_r101-d8_512x512_20k_voc12aug_20200617_193212.log.json) |
-| CCNet  | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 75.96 |         77.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_40k_voc12aug/ccnet_r50-d8_512x512_40k_voc12aug_20200613_232127-c2a15f02.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_40k_voc12aug/ccnet_r50-d8_512x512_40k_voc12aug_20200613_232127.log.json)     |
-| CCNet  | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 77.87 |         78.90 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ccnet/ccnet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_40k_voc12aug/ccnet_r101-d8_512x512_40k_voc12aug_20200613_232127-c30da577.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_40k_voc12aug/ccnet_r101-d8_512x512_40k_voc12aug_20200613_232127.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                    | download                                                                                                                                                                                                                                                                                                                               |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| CCNet  | R-50-D8  | 512x512   |   20000 | 6        | 20.45          | V100   | 76.17 |         77.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ccnet/ccnet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_20k_voc12aug/ccnet_r50-d8_512x512_20k_voc12aug_20200617_193212-fad81784.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_20k_voc12aug/ccnet_r50-d8_512x512_20k_voc12aug_20200617_193212.log.json)     |
+| CCNet  | R-101-D8 | 512x512   |   20000 | 9.5      | 13.64          | V100   | 77.27 |         79.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ccnet/ccnet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_20k_voc12aug/ccnet_r101-d8_512x512_20k_voc12aug_20200617_193212-0007b61d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_20k_voc12aug/ccnet_r101-d8_512x512_20k_voc12aug_20200617_193212.log.json) |
+| CCNet  | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 75.96 |         77.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ccnet/ccnet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_40k_voc12aug/ccnet_r50-d8_512x512_40k_voc12aug_20200613_232127-c2a15f02.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_40k_voc12aug/ccnet_r50-d8_512x512_40k_voc12aug_20200613_232127.log.json)     |
+| CCNet  | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 77.87 |         78.90 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ccnet/ccnet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_40k_voc12aug/ccnet_r101-d8_512x512_40k_voc12aug_20200613_232127-c30da577.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_40k_voc12aug/ccnet_r101-d8_512x512_40k_voc12aug_20200613_232127.log.json) |
 
 ## Citation
 
diff --git a/configs/cgnet/README.md b/configs/cgnet/README.md
index 60cde58291..96c9fcf515 100644
--- a/configs/cgnet/README.md
+++ b/configs/cgnet/README.md
@@ -26,10 +26,10 @@ The demand of applying semantic segmentation model on mobile devices has been in
 
 ### Cityscapes
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| CGNet  | M3N21    | 680x680   |   60000 | 7.5      | 30.51          | V100   | 65.63 |         68.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/cgnet/cgnet_fcn_4xb4-60k_cityscapes-680x680.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_680x680_60k_cityscapes/cgnet_680x680_60k_cityscapes_20201101_110253-4c0b2f2d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_680x680_60k_cityscapes/cgnet_680x680_60k_cityscapes-20201101_110253.log.json)     |
-| CGNet  | M3N21    | 512x1024  |   60000 | 8.3      | 31.14          | V100   | 68.27 |         70.33 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/cgnet/cgnet_fcn_4xb8-60k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_512x1024_60k_cityscapes/cgnet_512x1024_60k_cityscapes_20201101_110254-124ea03b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_512x1024_60k_cityscapes/cgnet_512x1024_60k_cityscapes-20201101_110254.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                   | download                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| CGNet  | M3N21    | 680x680   |   60000 | 7.5      | 30.51          | V100   | 65.63 |         68.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/cgnet/cgnet_fcn_4xb4-60k_cityscapes-680x680.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_680x680_60k_cityscapes/cgnet_680x680_60k_cityscapes_20201101_110253-4c0b2f2d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_680x680_60k_cityscapes/cgnet_680x680_60k_cityscapes-20201101_110253.log.json)     |
+| CGNet  | M3N21    | 512x1024  |   60000 | 8.3      | 31.14          | V100   | 68.27 |         70.33 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/cgnet/cgnet_fcn_4xb8-60k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_512x1024_60k_cityscapes/cgnet_512x1024_60k_cityscapes_20201101_110254-124ea03b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_512x1024_60k_cityscapes/cgnet_512x1024_60k_cityscapes-20201101_110254.log.json) |
 
 ## Citation
 
diff --git a/configs/convnext/README.md b/configs/convnext/README.md
index 91339377c0..cedf467557 100644
--- a/configs/convnext/README.md
+++ b/configs/convnext/README.md
@@ -49,14 +49,14 @@ The pre-trained models on ImageNet-1k or ImageNet-21k are used to fine-tune on t
 
 ### ADE20K
 
-| Method  | Backbone    | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                                       | download                                                                                                                                                                                                                                                                                                                                                                                             |
-| ------- | ----------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UPerNet | ConvNeXt-T  | 512x512   | 160000  | 4.23     | 19.90          | V100   | 46.11 | 46.62         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/convnext/convnext-tiny_upernet_8xb2-amp-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_tiny_fp16_512x512_160k_ade20k/upernet_convnext_tiny_fp16_512x512_160k_ade20k_20220227_124553-cad485de.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_tiny_fp16_512x512_160k_ade20k/upernet_convnext_tiny_fp16_512x512_160k_ade20k_20220227_124553.log.json)         |
-| UPerNet | ConvNeXt-S  | 512x512   | 160000  | 5.16     | 15.18          | V100   | 48.56 | 49.02         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/convnext/convnext-small_upernet_8xb2-amp-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_small_fp16_512x512_160k_ade20k/upernet_convnext_small_fp16_512x512_160k_ade20k_20220227_131208-1b1e394f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_small_fp16_512x512_160k_ade20k/upernet_convnext_small_fp16_512x512_160k_ade20k_20220227_131208.log.json)     |
-| UPerNet | ConvNeXt-B  | 512x512   | 160000  | 6.33     | 14.41          | V100   | 48.71 | 49.54         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/convnext/convnext-base_upernet_8xb2-amp-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_512x512_160k_ade20k/upernet_convnext_base_fp16_512x512_160k_ade20k_20220227_181227-02a24fc6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_512x512_160k_ade20k/upernet_convnext_base_fp16_512x512_160k_ade20k_20220227_181227.log.json)         |
-| UPerNet | ConvNeXt-B  | 640x640   | 160000  | 8.53     | 10.88          | V100   | 52.13 | 52.66         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/convnext/convnext-base_upernet_8xb2-amp-160k_ade20k-640x640.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_640x640_160k_ade20k/upernet_convnext_base_fp16_640x640_160k_ade20k_20220227_182859-9280e39b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_640x640_160k_ade20k/upernet_convnext_base_fp16_640x640_160k_ade20k_20220227_182859.log.json)         |
-| UPerNet | ConvNeXt-L  | 640x640   | 160000  | 12.08    | 7.69           | V100   | 53.16 | 53.38         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/convnext/convnext-large_upernet_8xb2-amp-160k_ade20k-640x640.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_large_fp16_640x640_160k_ade20k/upernet_convnext_large_fp16_640x640_160k_ade20k_20220226_040532-e57aa54d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_large_fp16_640x640_160k_ade20k/upernet_convnext_large_fp16_640x640_160k_ade20k_20220226_040532.log.json)     |
-| UPerNet | ConvNeXt-XL | 640x640   | 160000  | 26.16\*  | 6.33           | V100   | 53.58 | 54.11         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/convnext/convnext-xlarge_upernet_8xb2-amp-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_xlarge_fp16_640x640_160k_ade20k/upernet_convnext_xlarge_fp16_640x640_160k_ade20k_20220226_080344-95fc38c2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_xlarge_fp16_640x640_160k_ade20k/upernet_convnext_xlarge_fp16_640x640_160k_ade20k_20220226_080344.log.json) |
+| Method  | Backbone    | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                                    | download                                                                                                                                                                                                                                                                                                                                                                                             |
+| ------- | ----------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UPerNet | ConvNeXt-T  | 512x512   | 160000  | 4.23     | 19.90          | V100   | 46.11 | 46.62         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/convnext/convnext-tiny_upernet_8xb2-amp-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_tiny_fp16_512x512_160k_ade20k/upernet_convnext_tiny_fp16_512x512_160k_ade20k_20220227_124553-cad485de.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_tiny_fp16_512x512_160k_ade20k/upernet_convnext_tiny_fp16_512x512_160k_ade20k_20220227_124553.log.json)         |
+| UPerNet | ConvNeXt-S  | 512x512   | 160000  | 5.16     | 15.18          | V100   | 48.56 | 49.02         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/convnext/convnext-small_upernet_8xb2-amp-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_small_fp16_512x512_160k_ade20k/upernet_convnext_small_fp16_512x512_160k_ade20k_20220227_131208-1b1e394f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_small_fp16_512x512_160k_ade20k/upernet_convnext_small_fp16_512x512_160k_ade20k_20220227_131208.log.json)     |
+| UPerNet | ConvNeXt-B  | 512x512   | 160000  | 6.33     | 14.41          | V100   | 48.71 | 49.54         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/convnext/convnext-base_upernet_8xb2-amp-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_512x512_160k_ade20k/upernet_convnext_base_fp16_512x512_160k_ade20k_20220227_181227-02a24fc6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_512x512_160k_ade20k/upernet_convnext_base_fp16_512x512_160k_ade20k_20220227_181227.log.json)         |
+| UPerNet | ConvNeXt-B  | 640x640   | 160000  | 8.53     | 10.88          | V100   | 52.13 | 52.66         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/convnext/convnext-base_upernet_8xb2-amp-160k_ade20k-640x640.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_640x640_160k_ade20k/upernet_convnext_base_fp16_640x640_160k_ade20k_20220227_182859-9280e39b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_base_fp16_640x640_160k_ade20k/upernet_convnext_base_fp16_640x640_160k_ade20k_20220227_182859.log.json)         |
+| UPerNet | ConvNeXt-L  | 640x640   | 160000  | 12.08    | 7.69           | V100   | 53.16 | 53.38         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/convnext/convnext-large_upernet_8xb2-amp-160k_ade20k-640x640.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_large_fp16_640x640_160k_ade20k/upernet_convnext_large_fp16_640x640_160k_ade20k_20220226_040532-e57aa54d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_large_fp16_640x640_160k_ade20k/upernet_convnext_large_fp16_640x640_160k_ade20k_20220226_040532.log.json)     |
+| UPerNet | ConvNeXt-XL | 640x640   | 160000  | 26.16\*  | 6.33           | V100   | 53.58 | 54.11         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/convnext/convnext-xlarge_upernet_8xb2-amp-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_xlarge_fp16_640x640_160k_ade20k/upernet_convnext_xlarge_fp16_640x640_160k_ade20k_20220226_080344-95fc38c2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/convnext/upernet_convnext_xlarge_fp16_640x640_160k_ade20k/upernet_convnext_xlarge_fp16_640x640_160k_ade20k_20220226_080344.log.json) |
 
 Note:
 
diff --git a/configs/danet/README.md b/configs/danet/README.md
index b5841e23be..90194f3073 100644
--- a/configs/danet/README.md
+++ b/configs/danet/README.md
@@ -26,34 +26,34 @@ In this paper, we address the scene segmentation task by capturing rich contextu
 
 ### Cityscapes
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DANet  | R-50-D8  | 512x1024  |   40000 | 7.4      | 2.66           | V100   | 78.74 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_40k_cityscapes/danet_r50-d8_512x1024_40k_cityscapes_20200605_191324-c0dbfa5f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_40k_cityscapes/danet_r50-d8_512x1024_40k_cityscapes_20200605_191324.log.json)     |
-| DANet  | R-101-D8 | 512x1024  |   40000 | 10.9     | 1.99           | V100   | 80.52 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_40k_cityscapes/danet_r101-d8_512x1024_40k_cityscapes_20200605_200831-c57a7157.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_40k_cityscapes/danet_r101-d8_512x1024_40k_cityscapes_20200605_200831.log.json) |
-| DANet  | R-50-D8  | 769x769   |   40000 | 8.8      | 1.56           | V100   | 78.88 | 80.62         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_40k_cityscapes/danet_r50-d8_769x769_40k_cityscapes_20200530_025703-76681c60.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_40k_cityscapes/danet_r50-d8_769x769_40k_cityscapes_20200530_025703.log.json)         |
-| DANet  | R-101-D8 | 769x769   |   40000 | 12.8     | 1.07           | V100   | 79.88 | 81.47         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_40k_cityscapes/danet_r101-d8_769x769_40k_cityscapes_20200530_025717-dcb7fd4e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_40k_cityscapes/danet_r101-d8_769x769_40k_cityscapes_20200530_025717.log.json)     |
-| DANet  | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 79.34 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_80k_cityscapes/danet_r50-d8_512x1024_80k_cityscapes_20200607_133029-2bfa2293.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_80k_cityscapes/danet_r50-d8_512x1024_80k_cityscapes_20200607_133029.log.json)     |
-| DANet  | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 80.41 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_80k_cityscapes/danet_r101-d8_512x1024_80k_cityscapes_20200607_132918-955e6350.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_80k_cityscapes/danet_r101-d8_512x1024_80k_cityscapes_20200607_132918.log.json) |
-| DANet  | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 79.27 | 80.96         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_80k_cityscapes/danet_r50-d8_769x769_80k_cityscapes_20200607_132954-495689b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_80k_cityscapes/danet_r50-d8_769x769_80k_cityscapes_20200607_132954.log.json)         |
-| DANet  | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 80.47 | 82.02         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_80k_cityscapes/danet_r101-d8_769x769_80k_cityscapes_20200607_132918-f3a929e7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_80k_cityscapes/danet_r101-d8_769x769_80k_cityscapes_20200607_132918.log.json)     |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DANet  | R-50-D8  | 512x1024  |   40000 | 7.4      | 2.66           | V100   | 78.74 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_40k_cityscapes/danet_r50-d8_512x1024_40k_cityscapes_20200605_191324-c0dbfa5f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_40k_cityscapes/danet_r50-d8_512x1024_40k_cityscapes_20200605_191324.log.json)     |
+| DANet  | R-101-D8 | 512x1024  |   40000 | 10.9     | 1.99           | V100   | 80.52 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_40k_cityscapes/danet_r101-d8_512x1024_40k_cityscapes_20200605_200831-c57a7157.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_40k_cityscapes/danet_r101-d8_512x1024_40k_cityscapes_20200605_200831.log.json) |
+| DANet  | R-50-D8  | 769x769   |   40000 | 8.8      | 1.56           | V100   | 78.88 | 80.62         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_40k_cityscapes/danet_r50-d8_769x769_40k_cityscapes_20200530_025703-76681c60.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_40k_cityscapes/danet_r50-d8_769x769_40k_cityscapes_20200530_025703.log.json)         |
+| DANet  | R-101-D8 | 769x769   |   40000 | 12.8     | 1.07           | V100   | 79.88 | 81.47         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_40k_cityscapes/danet_r101-d8_769x769_40k_cityscapes_20200530_025717-dcb7fd4e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_40k_cityscapes/danet_r101-d8_769x769_40k_cityscapes_20200530_025717.log.json)     |
+| DANet  | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 79.34 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_80k_cityscapes/danet_r50-d8_512x1024_80k_cityscapes_20200607_133029-2bfa2293.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_80k_cityscapes/danet_r50-d8_512x1024_80k_cityscapes_20200607_133029.log.json)     |
+| DANet  | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 80.41 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_80k_cityscapes/danet_r101-d8_512x1024_80k_cityscapes_20200607_132918-955e6350.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_80k_cityscapes/danet_r101-d8_512x1024_80k_cityscapes_20200607_132918.log.json) |
+| DANet  | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 79.27 | 80.96         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_80k_cityscapes/danet_r50-d8_769x769_80k_cityscapes_20200607_132954-495689b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_80k_cityscapes/danet_r50-d8_769x769_80k_cityscapes_20200607_132954.log.json)         |
+| DANet  | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 80.47 | 82.02         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_80k_cityscapes/danet_r101-d8_769x769_80k_cityscapes_20200607_132918-f3a929e7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_80k_cityscapes/danet_r101-d8_769x769_80k_cityscapes_20200607_132918.log.json)     |
 
 ### ADE20K
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DANet  | R-50-D8  | 512x512   |   80000 | 11.5     | 21.20          | V100   | 41.66 |         42.90 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_80k_ade20k/danet_r50-d8_512x512_80k_ade20k_20200615_015125-edb18e08.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_80k_ade20k/danet_r50-d8_512x512_80k_ade20k_20200615_015125.log.json)         |
-| DANet  | R-101-D8 | 512x512   |   80000 | 15       | 14.18          | V100   | 43.64 |         45.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_80k_ade20k/danet_r101-d8_512x512_80k_ade20k_20200615_015126-d0357c73.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_80k_ade20k/danet_r101-d8_512x512_80k_ade20k_20200615_015126.log.json)     |
-| DANet  | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 42.45 |         43.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_160k_ade20k/danet_r50-d8_512x512_160k_ade20k_20200616_082340-9cb35dcd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_160k_ade20k/danet_r50-d8_512x512_160k_ade20k_20200616_082340.log.json)     |
-| DANet  | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 44.17 |         45.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_160k_ade20k/danet_r101-d8_512x512_160k_ade20k_20200616_082348-23bf12f9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_160k_ade20k/danet_r101-d8_512x512_160k_ade20k_20200616_082348.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                   | download                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DANet  | R-50-D8  | 512x512   |   80000 | 11.5     | 21.20          | V100   | 41.66 |         42.90 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_80k_ade20k/danet_r50-d8_512x512_80k_ade20k_20200615_015125-edb18e08.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_80k_ade20k/danet_r50-d8_512x512_80k_ade20k_20200615_015125.log.json)         |
+| DANet  | R-101-D8 | 512x512   |   80000 | 15       | 14.18          | V100   | 43.64 |         45.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_80k_ade20k/danet_r101-d8_512x512_80k_ade20k_20200615_015126-d0357c73.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_80k_ade20k/danet_r101-d8_512x512_80k_ade20k_20200615_015126.log.json)     |
+| DANet  | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 42.45 |         43.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_160k_ade20k/danet_r50-d8_512x512_160k_ade20k_20200616_082340-9cb35dcd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_160k_ade20k/danet_r50-d8_512x512_160k_ade20k_20200616_082340.log.json)     |
+| DANet  | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 44.17 |         45.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_160k_ade20k/danet_r101-d8_512x512_160k_ade20k_20200616_082348-23bf12f9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_160k_ade20k/danet_r101-d8_512x512_160k_ade20k_20200616_082348.log.json) |
 
 ### Pascal VOC 2012 + Aug
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                               |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DANet  | R-50-D8  | 512x512   |   20000 | 6.5      | 20.94          | V100   | 74.45 |         75.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_20k_voc12aug/danet_r50-d8_512x512_20k_voc12aug_20200618_070026-9e9e3ab3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_20k_voc12aug/danet_r50-d8_512x512_20k_voc12aug_20200618_070026.log.json)     |
-| DANet  | R-101-D8 | 512x512   |   20000 | 9.9      | 13.76          | V100   | 76.02 |         77.23 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_20k_voc12aug/danet_r101-d8_512x512_20k_voc12aug_20200618_070026-d48d23b2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_20k_voc12aug/danet_r101-d8_512x512_20k_voc12aug_20200618_070026.log.json) |
-| DANet  | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 76.37 |         77.29 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_40k_voc12aug/danet_r50-d8_512x512_40k_voc12aug_20200613_235526-426e3a64.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_40k_voc12aug/danet_r50-d8_512x512_40k_voc12aug_20200613_235526.log.json)     |
-| DANet  | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 76.51 |         77.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/danet/danet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_40k_voc12aug/danet_r101-d8_512x512_40k_voc12aug_20200613_223031-788e232a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_40k_voc12aug/danet_r101-d8_512x512_40k_voc12aug_20200613_223031.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                    | download                                                                                                                                                                                                                                                                                                                               |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DANet  | R-50-D8  | 512x512   |   20000 | 6.5      | 20.94          | V100   | 74.45 |         75.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_20k_voc12aug/danet_r50-d8_512x512_20k_voc12aug_20200618_070026-9e9e3ab3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_20k_voc12aug/danet_r50-d8_512x512_20k_voc12aug_20200618_070026.log.json)     |
+| DANet  | R-101-D8 | 512x512   |   20000 | 9.9      | 13.76          | V100   | 76.02 |         77.23 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_20k_voc12aug/danet_r101-d8_512x512_20k_voc12aug_20200618_070026-d48d23b2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_20k_voc12aug/danet_r101-d8_512x512_20k_voc12aug_20200618_070026.log.json) |
+| DANet  | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 76.37 |         77.29 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_40k_voc12aug/danet_r50-d8_512x512_40k_voc12aug_20200613_235526-426e3a64.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_40k_voc12aug/danet_r50-d8_512x512_40k_voc12aug_20200613_235526.log.json)     |
+| DANet  | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 76.51 |         77.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_40k_voc12aug/danet_r101-d8_512x512_40k_voc12aug_20200613_223031-788e232a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_40k_voc12aug/danet_r101-d8_512x512_40k_voc12aug_20200613_223031.log.json) |
 
 ## Citation
 
diff --git a/configs/deeplabv3/README.md b/configs/deeplabv3/README.md
index 836db6a9a5..df50b7f90a 100644
--- a/configs/deeplabv3/README.md
+++ b/configs/deeplabv3/README.md
@@ -27,79 +27,79 @@ DEEPLABv3_ResNet-D8 model structure
 
 ### Cityscapes
 
-| Method           | Backbone        | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                                                               |
-| ---------------- | --------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| DeepLabV3        | R-50-D8         | 512x1024  |   40000 | 6.1      | 2.57           | V100   | 79.09 |         80.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes/deeplabv3_r50-d8_512x1024_40k_cityscapes_20200605_022449-acadc2f8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes/deeplabv3_r50-d8_512x1024_40k_cityscapes_20200605_022449.log.json)                                 |
-| DeepLabV3        | R-101-D8        | 512x1024  |   40000 | 9.6      | 1.92           | V100   | 77.12 |         79.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb2-40k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_40k_cityscapes/deeplabv3_r101-d8_512x1024_40k_cityscapes_20200605_012241-7fd3f799.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_40k_cityscapes/deeplabv3_r101-d8_512x1024_40k_cityscapes_20200605_012241.log.json)                             |
-| DeepLabV3        | R-50-D8         | 769x769   |   40000 | 6.9      | 1.11           | V100   | 78.58 |         79.89 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_cityscapes-769x769.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_40k_cityscapes/deeplabv3_r50-d8_769x769_40k_cityscapes_20200606_113723-7eda553c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_40k_cityscapes/deeplabv3_r50-d8_769x769_40k_cityscapes_20200606_113723.log.json)                                     |
-| DeepLabV3        | R-101-D8        | 769x769   |   40000 | 10.9     | 0.83           | V100   | 79.27 |         80.11 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb2-40k_cityscapes-769x769.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_40k_cityscapes/deeplabv3_r101-d8_769x769_40k_cityscapes_20200606_113809-c64f889f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_40k_cityscapes/deeplabv3_r101-d8_769x769_40k_cityscapes_20200606_113809.log.json)                                 |
-| DeepLabV3        | R-18-D8         | 512x1024  |   80000 | 1.7      | 13.78          | V100   | 76.70 |         78.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r18-d8_4xb2-80k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_512x1024_80k_cityscapes/deeplabv3_r18-d8_512x1024_80k_cityscapes_20201225_021506-23dffbe2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_512x1024_80k_cityscapes/deeplabv3_r18-d8_512x1024_80k_cityscapes-20201225_021506.log.json)                                 |
-| DeepLabV3        | R-50-D8         | 512x1024  |   80000 | -        | -              | V100   | 79.32 |         80.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb2-80k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_80k_cityscapes/deeplabv3_r50-d8_512x1024_80k_cityscapes_20200606_113404-b92cfdd4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_80k_cityscapes/deeplabv3_r50-d8_512x1024_80k_cityscapes_20200606_113404.log.json)                                 |
-| DeepLabV3        | R-101-D8        | 512x1024  |   80000 | -        | -              | V100   | 80.20 |         81.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb2-80k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_80k_cityscapes/deeplabv3_r101-d8_512x1024_80k_cityscapes_20200606_113503-9e428899.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_80k_cityscapes/deeplabv3_r101-d8_512x1024_80k_cityscapes_20200606_113503.log.json)                             |
-| DeepLabV3 (FP16) | R-101-D8        | 512x1024  |   80000 | 5.75     | 3.86           | V100   | 80.48 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920-774d9cec.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920.log.json)         |
-| DeepLabV3        | R-18-D8         | 769x769   |   80000 | 1.9      | 5.55           | V100   | 76.60 |         78.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r18-d8_4xb2-80k_cityscapes-769x769.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_769x769_80k_cityscapes/deeplabv3_r18-d8_769x769_80k_cityscapes_20201225_021506-6452126a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_769x769_80k_cityscapes/deeplabv3_r18-d8_769x769_80k_cityscapes-20201225_021506.log.json)                                     |
-| DeepLabV3        | R-50-D8         | 769x769   |   80000 | -        | -              | V100   | 79.89 |         81.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb2-80k_cityscapes-769x769.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_80k_cityscapes/deeplabv3_r50-d8_769x769_80k_cityscapes_20200606_221338-788d6228.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_80k_cityscapes/deeplabv3_r50-d8_769x769_80k_cityscapes_20200606_221338.log.json)                                     |
-| DeepLabV3        | R-101-D8        | 769x769   |   80000 | -        | -              | V100   | 79.67 |         80.81 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb2-80k_cityscapes-769x769.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_80k_cityscapes/deeplabv3_r101-d8_769x769_80k_cityscapes_20200607_013353-60e95418.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_80k_cityscapes/deeplabv3_r101-d8_769x769_80k_cityscapes_20200607_013353.log.json)                                 |
-| DeepLabV3        | R-101-D16-MG124 | 512x1024  |   40000 | 4.7      | 6.96           | V100   | 76.71 |         78.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d16-mg124_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes_20200908_005644-67b0c992.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes-20200908_005644.log.json) |
-| DeepLabV3        | R-101-D16-MG124 | 512x1024  |   80000 | -        | -              | V100   | 78.36 |         79.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d16-mg124_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes_20200908_005644-57bb8425.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes-20200908_005644.log.json) |
-| DeepLabV3        | R-18b-D8        | 512x1024  |   80000 | 1.6      | 13.93          | V100   | 76.26 |         77.88 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r18b-d8_4xb2-80k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_512x1024_80k_cityscapes/deeplabv3_r18b-d8_512x1024_80k_cityscapes_20201225_094144-46040cef.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_512x1024_80k_cityscapes/deeplabv3_r18b-d8_512x1024_80k_cityscapes-20201225_094144.log.json)                             |
-| DeepLabV3        | R-50b-D8        | 512x1024  |   80000 | 6.0      | 2.74           | V100   | 79.63 |         80.98 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50b-d8_4xb2-80k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_512x1024_80k_cityscapes/deeplabv3_r50b-d8_512x1024_80k_cityscapes_20201225_155148-ec368954.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_512x1024_80k_cityscapes/deeplabv3_r50b-d8_512x1024_80k_cityscapes-20201225_155148.log.json)                             |
-| DeepLabV3        | R-101b-D8       | 512x1024  |   80000 | 9.5      | 1.81           | V100   | 80.01 |         81.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101b-d8_4xb2-80k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_512x1024_80k_cityscapes/deeplabv3_r101b-d8_512x1024_80k_cityscapes_20201226_171821-8fd49503.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_512x1024_80k_cityscapes/deeplabv3_r101b-d8_512x1024_80k_cityscapes-20201226_171821.log.json)                         |
-| DeepLabV3        | R-18b-D8        | 769x769   |   80000 | 1.8      | 5.79           | V100   | 75.63 |         77.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r18b-d8_4xb2-80k_cityscapes-769x769.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_769x769_80k_cityscapes/deeplabv3_r18b-d8_769x769_80k_cityscapes_20201225_094144-fdc985d9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_769x769_80k_cityscapes/deeplabv3_r18b-d8_769x769_80k_cityscapes-20201225_094144.log.json)                                 |
-| DeepLabV3        | R-50b-D8        | 769x769   |   80000 | 6.8      | 1.16           | V100   | 78.80 |         80.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50b-d8_4xb2-80k_cityscapes-769x769.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_769x769_80k_cityscapes/deeplabv3_r50b-d8_769x769_80k_cityscapes_20201225_155404-87fb0cf4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_769x769_80k_cityscapes/deeplabv3_r50b-d8_769x769_80k_cityscapes-20201225_155404.log.json)                                 |
-| DeepLabV3        | R-101b-D8       | 769x769   |   80000 | 10.7     | 0.82           | V100   | 79.41 |         80.73 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101b-d8_4xb2-80k_cityscapes-769x769.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_769x769_80k_cityscapes/deeplabv3_r101b-d8_769x769_80k_cityscapes_20201226_190843-9142ee57.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_769x769_80k_cityscapes/deeplabv3_r101b-d8_769x769_80k_cityscapes-20201226_190843.log.json)                             |
+| Method           | Backbone        | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                                                                               |
+| ---------------- | --------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| DeepLabV3        | R-50-D8         | 512x1024  |   40000 | 6.1      | 2.57           | V100   | 79.09 |         80.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes/deeplabv3_r50-d8_512x1024_40k_cityscapes_20200605_022449-acadc2f8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes/deeplabv3_r50-d8_512x1024_40k_cityscapes_20200605_022449.log.json)                                 |
+| DeepLabV3        | R-101-D8        | 512x1024  |   40000 | 9.6      | 1.92           | V100   | 77.12 |         79.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d8_4xb2-40k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_40k_cityscapes/deeplabv3_r101-d8_512x1024_40k_cityscapes_20200605_012241-7fd3f799.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_40k_cityscapes/deeplabv3_r101-d8_512x1024_40k_cityscapes_20200605_012241.log.json)                             |
+| DeepLabV3        | R-50-D8         | 769x769   |   40000 | 6.9      | 1.11           | V100   | 78.58 |         79.89 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_cityscapes-769x769.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_40k_cityscapes/deeplabv3_r50-d8_769x769_40k_cityscapes_20200606_113723-7eda553c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_40k_cityscapes/deeplabv3_r50-d8_769x769_40k_cityscapes_20200606_113723.log.json)                                     |
+| DeepLabV3        | R-101-D8        | 769x769   |   40000 | 10.9     | 0.83           | V100   | 79.27 |         80.11 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d8_4xb2-40k_cityscapes-769x769.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_40k_cityscapes/deeplabv3_r101-d8_769x769_40k_cityscapes_20200606_113809-c64f889f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_40k_cityscapes/deeplabv3_r101-d8_769x769_40k_cityscapes_20200606_113809.log.json)                                 |
+| DeepLabV3        | R-18-D8         | 512x1024  |   80000 | 1.7      | 13.78          | V100   | 76.70 |         78.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r18-d8_4xb2-80k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_512x1024_80k_cityscapes/deeplabv3_r18-d8_512x1024_80k_cityscapes_20201225_021506-23dffbe2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_512x1024_80k_cityscapes/deeplabv3_r18-d8_512x1024_80k_cityscapes-20201225_021506.log.json)                                 |
+| DeepLabV3        | R-50-D8         | 512x1024  |   80000 | -        | -              | V100   | 79.32 |         80.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r50-d8_4xb2-80k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_80k_cityscapes/deeplabv3_r50-d8_512x1024_80k_cityscapes_20200606_113404-b92cfdd4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_80k_cityscapes/deeplabv3_r50-d8_512x1024_80k_cityscapes_20200606_113404.log.json)                                 |
+| DeepLabV3        | R-101-D8        | 512x1024  |   80000 | -        | -              | V100   | 80.20 |         81.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d8_4xb2-80k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_80k_cityscapes/deeplabv3_r101-d8_512x1024_80k_cityscapes_20200606_113503-9e428899.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_80k_cityscapes/deeplabv3_r101-d8_512x1024_80k_cityscapes_20200606_113503.log.json)                             |
+| DeepLabV3 (FP16) | R-101-D8        | 512x1024  |   80000 | 5.75     | 3.86           | V100   | 80.48 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920-774d9cec.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920.log.json)         |
+| DeepLabV3        | R-18-D8         | 769x769   |   80000 | 1.9      | 5.55           | V100   | 76.60 |         78.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r18-d8_4xb2-80k_cityscapes-769x769.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_769x769_80k_cityscapes/deeplabv3_r18-d8_769x769_80k_cityscapes_20201225_021506-6452126a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_769x769_80k_cityscapes/deeplabv3_r18-d8_769x769_80k_cityscapes-20201225_021506.log.json)                                     |
+| DeepLabV3        | R-50-D8         | 769x769   |   80000 | -        | -              | V100   | 79.89 |         81.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r50-d8_4xb2-80k_cityscapes-769x769.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_80k_cityscapes/deeplabv3_r50-d8_769x769_80k_cityscapes_20200606_221338-788d6228.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_80k_cityscapes/deeplabv3_r50-d8_769x769_80k_cityscapes_20200606_221338.log.json)                                     |
+| DeepLabV3        | R-101-D8        | 769x769   |   80000 | -        | -              | V100   | 79.67 |         80.81 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d8_4xb2-80k_cityscapes-769x769.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_80k_cityscapes/deeplabv3_r101-d8_769x769_80k_cityscapes_20200607_013353-60e95418.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_80k_cityscapes/deeplabv3_r101-d8_769x769_80k_cityscapes_20200607_013353.log.json)                                 |
+| DeepLabV3        | R-101-D16-MG124 | 512x1024  |   40000 | 4.7      | 6.96           | V100   | 76.71 |         78.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d16-mg124_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes_20200908_005644-67b0c992.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes-20200908_005644.log.json) |
+| DeepLabV3        | R-101-D16-MG124 | 512x1024  |   80000 | -        | -              | V100   | 78.36 |         79.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d16-mg124_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes_20200908_005644-57bb8425.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes-20200908_005644.log.json) |
+| DeepLabV3        | R-18b-D8        | 512x1024  |   80000 | 1.6      | 13.93          | V100   | 76.26 |         77.88 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r18b-d8_4xb2-80k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_512x1024_80k_cityscapes/deeplabv3_r18b-d8_512x1024_80k_cityscapes_20201225_094144-46040cef.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_512x1024_80k_cityscapes/deeplabv3_r18b-d8_512x1024_80k_cityscapes-20201225_094144.log.json)                             |
+| DeepLabV3        | R-50b-D8        | 512x1024  |   80000 | 6.0      | 2.74           | V100   | 79.63 |         80.98 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r50b-d8_4xb2-80k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_512x1024_80k_cityscapes/deeplabv3_r50b-d8_512x1024_80k_cityscapes_20201225_155148-ec368954.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_512x1024_80k_cityscapes/deeplabv3_r50b-d8_512x1024_80k_cityscapes-20201225_155148.log.json)                             |
+| DeepLabV3        | R-101b-D8       | 512x1024  |   80000 | 9.5      | 1.81           | V100   | 80.01 |         81.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101b-d8_4xb2-80k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_512x1024_80k_cityscapes/deeplabv3_r101b-d8_512x1024_80k_cityscapes_20201226_171821-8fd49503.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_512x1024_80k_cityscapes/deeplabv3_r101b-d8_512x1024_80k_cityscapes-20201226_171821.log.json)                         |
+| DeepLabV3        | R-18b-D8        | 769x769   |   80000 | 1.8      | 5.79           | V100   | 75.63 |         77.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r18b-d8_4xb2-80k_cityscapes-769x769.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_769x769_80k_cityscapes/deeplabv3_r18b-d8_769x769_80k_cityscapes_20201225_094144-fdc985d9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_769x769_80k_cityscapes/deeplabv3_r18b-d8_769x769_80k_cityscapes-20201225_094144.log.json)                                 |
+| DeepLabV3        | R-50b-D8        | 769x769   |   80000 | 6.8      | 1.16           | V100   | 78.80 |         80.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r50b-d8_4xb2-80k_cityscapes-769x769.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_769x769_80k_cityscapes/deeplabv3_r50b-d8_769x769_80k_cityscapes_20201225_155404-87fb0cf4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_769x769_80k_cityscapes/deeplabv3_r50b-d8_769x769_80k_cityscapes-20201225_155404.log.json)                                 |
+| DeepLabV3        | R-101b-D8       | 769x769   |   80000 | 10.7     | 0.82           | V100   | 79.41 |         80.73 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101b-d8_4xb2-80k_cityscapes-769x769.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_769x769_80k_cityscapes/deeplabv3_r101b-d8_769x769_80k_cityscapes_20201226_190843-9142ee57.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_769x769_80k_cityscapes/deeplabv3_r101b-d8_769x769_80k_cityscapes-20201226_190843.log.json)                             |
 
 ### ADE20K
 
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                              | download                                                                                                                                                                                                                                                                                                                                                   |
-| --------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3 | R-50-D8  | 512x512   |   80000 | 8.9      | 14.76          | V100   | 42.42 |         43.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_80k_ade20k/deeplabv3_r50-d8_512x512_80k_ade20k_20200614_185028-0bb3f844.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_80k_ade20k/deeplabv3_r50-d8_512x512_80k_ade20k_20200614_185028.log.json)         |
-| DeepLabV3 | R-101-D8 | 512x512   |   80000 | 12.4     | 10.14          | V100   | 44.08 |         45.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_80k_ade20k/deeplabv3_r101-d8_512x512_80k_ade20k_20200615_021256-d89c7fa4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_80k_ade20k/deeplabv3_r101-d8_512x512_80k_ade20k_20200615_021256.log.json)     |
-| DeepLabV3 | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 42.66 |         44.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_160k_ade20k/deeplabv3_r50-d8_512x512_160k_ade20k_20200615_123227-5d0ee427.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_160k_ade20k/deeplabv3_r50-d8_512x512_160k_ade20k_20200615_123227.log.json)     |
-| DeepLabV3 | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 45.00 |         46.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_160k_ade20k/deeplabv3_r101-d8_512x512_160k_ade20k_20200615_105816-b1f72b3b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_160k_ade20k/deeplabv3_r101-d8_512x512_160k_ade20k_20200615_105816.log.json) |
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                   |
+| --------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3 | R-50-D8  | 512x512   |   80000 | 8.9      | 14.76          | V100   | 42.42 |         43.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_80k_ade20k/deeplabv3_r50-d8_512x512_80k_ade20k_20200614_185028-0bb3f844.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_80k_ade20k/deeplabv3_r50-d8_512x512_80k_ade20k_20200614_185028.log.json)         |
+| DeepLabV3 | R-101-D8 | 512x512   |   80000 | 12.4     | 10.14          | V100   | 44.08 |         45.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_80k_ade20k/deeplabv3_r101-d8_512x512_80k_ade20k_20200615_021256-d89c7fa4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_80k_ade20k/deeplabv3_r101-d8_512x512_80k_ade20k_20200615_021256.log.json)     |
+| DeepLabV3 | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 42.66 |         44.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_160k_ade20k/deeplabv3_r50-d8_512x512_160k_ade20k_20200615_123227-5d0ee427.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_160k_ade20k/deeplabv3_r50-d8_512x512_160k_ade20k_20200615_123227.log.json)     |
+| DeepLabV3 | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 45.00 |         46.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_160k_ade20k/deeplabv3_r101-d8_512x512_160k_ade20k_20200615_105816-b1f72b3b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_160k_ade20k/deeplabv3_r101-d8_512x512_160k_ade20k_20200615_105816.log.json) |
 
 ### Pascal VOC 2012 + Aug
 
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                               | download                                                                                                                                                                                                                                                                                                                                                       |
-| --------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3 | R-50-D8  | 512x512   |   20000 | 6.1      | 13.88          | V100   | 76.17 |         77.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_20k_voc12aug/deeplabv3_r50-d8_512x512_20k_voc12aug_20200617_010906-596905ef.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_20k_voc12aug/deeplabv3_r50-d8_512x512_20k_voc12aug_20200617_010906.log.json)     |
-| DeepLabV3 | R-101-D8 | 512x512   |   20000 | 9.6      | 9.81           | V100   | 78.70 |         79.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_20k_voc12aug/deeplabv3_r101-d8_512x512_20k_voc12aug_20200617_010932-8d13832f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_20k_voc12aug/deeplabv3_r101-d8_512x512_20k_voc12aug_20200617_010932.log.json) |
-| DeepLabV3 | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 77.68 |         78.78 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_40k_voc12aug/deeplabv3_r50-d8_512x512_40k_voc12aug_20200613_161546-2ae96e7e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_40k_voc12aug/deeplabv3_r50-d8_512x512_40k_voc12aug_20200613_161546.log.json)     |
-| DeepLabV3 | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 77.92 |         79.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_40k_voc12aug/deeplabv3_r101-d8_512x512_40k_voc12aug_20200613_161432-0017d784.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_40k_voc12aug/deeplabv3_r101-d8_512x512_40k_voc12aug_20200613_161432.log.json) |
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                       |
+| --------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3 | R-50-D8  | 512x512   |   20000 | 6.1      | 13.88          | V100   | 76.17 |         77.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_20k_voc12aug/deeplabv3_r50-d8_512x512_20k_voc12aug_20200617_010906-596905ef.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_20k_voc12aug/deeplabv3_r50-d8_512x512_20k_voc12aug_20200617_010906.log.json)     |
+| DeepLabV3 | R-101-D8 | 512x512   |   20000 | 9.6      | 9.81           | V100   | 78.70 |         79.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_20k_voc12aug/deeplabv3_r101-d8_512x512_20k_voc12aug_20200617_010932-8d13832f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_20k_voc12aug/deeplabv3_r101-d8_512x512_20k_voc12aug_20200617_010932.log.json) |
+| DeepLabV3 | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 77.68 |         78.78 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_40k_voc12aug/deeplabv3_r50-d8_512x512_40k_voc12aug_20200613_161546-2ae96e7e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_40k_voc12aug/deeplabv3_r50-d8_512x512_40k_voc12aug_20200613_161546.log.json)     |
+| DeepLabV3 | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 77.92 |         79.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_40k_voc12aug/deeplabv3_r101-d8_512x512_40k_voc12aug_20200613_161432-0017d784.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_40k_voc12aug/deeplabv3_r101-d8_512x512_40k_voc12aug_20200613_161432.log.json) |
 
 ### Pascal Context
 
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                                               |
-| --------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3 | R-101-D8 | 480x480   |   40000 | 9.2      | 7.09           | V100   | 46.55 |         47.81 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context/deeplabv3_r101-d8_480x480_40k_pascal_context_20200911_204118-1aa27336.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context/deeplabv3_r101-d8_480x480_40k_pascal_context-20200911_204118.log.json) |
-| DeepLabV3 | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 46.42 |         47.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context/deeplabv3_r101-d8_480x480_80k_pascal_context_20200911_170155-2a21fff3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context/deeplabv3_r101-d8_480x480_80k_pascal_context-20200911_170155.log.json) |
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                  | download                                                                                                                                                                                                                                                                                                                                                                               |
+| --------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3 | R-101-D8 | 480x480   |   40000 | 9.2      | 7.09           | V100   | 46.55 |         47.81 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context/deeplabv3_r101-d8_480x480_40k_pascal_context_20200911_204118-1aa27336.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context/deeplabv3_r101-d8_480x480_40k_pascal_context-20200911_204118.log.json) |
+| DeepLabV3 | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 46.42 |         47.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context/deeplabv3_r101-d8_480x480_80k_pascal_context_20200911_170155-2a21fff3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context/deeplabv3_r101-d8_480x480_80k_pascal_context-20200911_170155.log.json) |
 
 ### Pascal Context 59
 
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                                                           |
-| --------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3 | R-101-D8 | 480x480   |   40000 | -        | -              | V100   | 52.61 |         54.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context_59/deeplabv3_r101-d8_480x480_40k_pascal_context_59_20210416_110332-cb08ea46.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context_59/deeplabv3_r101-d8_480x480_40k_pascal_context_59-20210416_110332.log.json) |
-| DeepLabV3 | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 52.46 |         54.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context_59/deeplabv3_r101-d8_480x480_80k_pascal_context_59_20210416_113002-26303993.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context_59/deeplabv3_r101-d8_480x480_80k_pascal_context_59-20210416_113002.log.json) |
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                                                           |
+| --------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3 | R-101-D8 | 480x480   |   40000 | -        | -              | V100   | 52.61 |         54.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context_59/deeplabv3_r101-d8_480x480_40k_pascal_context_59_20210416_110332-cb08ea46.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context_59/deeplabv3_r101-d8_480x480_40k_pascal_context_59-20210416_110332.log.json) |
+| DeepLabV3 | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 52.46 |         54.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context_59/deeplabv3_r101-d8_480x480_80k_pascal_context_59_20210416_113002-26303993.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context_59/deeplabv3_r101-d8_480x480_80k_pascal_context_59-20210416_113002.log.json) |
 
 ### COCO-Stuff 10k
 
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                    | download                                                                                                                                                                                                                                                                                                                                                                                           |
-| --------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3 | R-50-D8  | 512x512   |   20000 | 9.6      | 10.8           | V100   | 34.66 |         36.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-20k_coco-stuff10k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025-b35f789d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025.log.json)     |
-| DeepLabV3 | R-101-D8 | 512x512   |   20000 | 13.2     | 8.7            | V100   | 37.30 |         38.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-20k_coco-stuff10k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025-c49752cb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025.log.json) |
-| DeepLabV3 | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 35.73 |         37.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-40k_coco-stuff10k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305-dc76f3ff.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305.log.json)     |
-| DeepLabV3 | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 37.81 |         38.80 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_coco-stuff10k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305-636cb433.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305.log.json) |
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                                                           |
+| --------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3 | R-50-D8  | 512x512   |   20000 | 9.6      | 10.8           | V100   | 34.66 |         36.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r50-d8_4xb4-20k_coco-stuff10k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025-b35f789d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025.log.json)     |
+| DeepLabV3 | R-101-D8 | 512x512   |   20000 | 13.2     | 8.7            | V100   | 37.30 |         38.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d8_4xb4-20k_coco-stuff10k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025-c49752cb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025.log.json) |
+| DeepLabV3 | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 35.73 |         37.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r50-d8_4xb4-40k_coco-stuff10k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305-dc76f3ff.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305.log.json)     |
+| DeepLabV3 | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 37.81 |         38.80 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d8_4xb4-40k_coco-stuff10k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305-636cb433.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305.log.json) |
 
 ### COCO-Stuff 164k
 
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                                                                                   |
-| --------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3 | R-50-D8  | 512x512   |   80000 | 9.6      | 10.8           | V100   | 39.38 |         40.03 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-80k_coco-stuff164k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k_20210709_163016-88675c24.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k_20210709_163016.log.json)         |
-| DeepLabV3 | R-101-D8 | 512x512   |   80000 | 13.2     | 8.7            | V100   | 40.87 |         41.50 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k_20210709_201252-13600dc2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k_20210709_201252.log.json)     |
-| DeepLabV3 | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 41.09 |         41.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k_20210709_163016-49f2812b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k_20210709_163016.log.json)     |
-| DeepLabV3 | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 41.82 |         42.49 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-160k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k_20210709_155402-f035acfd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k_20210709_155402.log.json) |
-| DeepLabV3 | R-50-D8  | 512x512   |  320000 | -        | -              | V100   | 41.37 |         42.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb4-320k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k_20210709_155403-51b21115.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k_20210709_155403.log.json)     |
-| DeepLabV3 | R-101-D8 | 512x512   |  320000 | -        | -              | V100   | 42.61 |         43.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3/deeplabv3_r101-d8_4xb4-320k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k_20210709_155402-3cbca14d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k_20210709_155402.log.json) |
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                   | download                                                                                                                                                                                                                                                                                                                                                                                                   |
+| --------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3 | R-50-D8  | 512x512   |   80000 | 9.6      | 10.8           | V100   | 39.38 |         40.03 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r50-d8_4xb4-80k_coco-stuff164k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k_20210709_163016-88675c24.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k_20210709_163016.log.json)         |
+| DeepLabV3 | R-101-D8 | 512x512   |   80000 | 13.2     | 8.7            | V100   | 40.87 |         41.50 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d8_4xb4-80k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k_20210709_201252-13600dc2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k_20210709_201252.log.json)     |
+| DeepLabV3 | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 41.09 |         41.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r50-d8_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k_20210709_163016-49f2812b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k_20210709_163016.log.json)     |
+| DeepLabV3 | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 41.82 |         42.49 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d8_4xb4-160k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k_20210709_155402-f035acfd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k_20210709_155402.log.json) |
+| DeepLabV3 | R-50-D8  | 512x512   |  320000 | -        | -              | V100   | 41.37 |         42.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r50-d8_4xb4-320k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k_20210709_155403-51b21115.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k_20210709_155403.log.json)     |
+| DeepLabV3 | R-101-D8 | 512x512   |  320000 | -        | -              | V100   | 42.61 |         43.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3/deeplabv3_r101-d8_4xb4-320k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k_20210709_155402-3cbca14d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k_20210709_155402.log.json) |
 
 Note:
 
diff --git a/configs/deeplabv3plus/README.md b/configs/deeplabv3plus/README.md
index 15c51a504a..04d01fa512 100644
--- a/configs/deeplabv3plus/README.md
+++ b/configs/deeplabv3plus/README.md
@@ -26,98 +26,98 @@ Spatial pyramid pooling module or encode-decoder structure are used in deep neur
 
 ### Cityscapes
 
-| Method            | Backbone        | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                                                                                       |
-| ----------------- | --------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| DeepLabV3+        | R-50-D8         | 512x1024  |   40000 | 7.5      | 3.94           | V100   | 79.61 |         81.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-40k_cityscapes-512x1024.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_40k_cityscapes/deeplabv3plus_r50-d8_512x1024_40k_cityscapes_20200605_094610-d222ffcd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_40k_cityscapes/deeplabv3plus_r50-d8_512x1024_40k_cityscapes_20200605_094610.log.json)                                 |
-| DeepLabV3+        | R-101-D8        | 512x1024  |   40000 | 11       | 2.60           | V100   | 80.21 |         81.82 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-40k_cityscapes-512x1024.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_40k_cityscapes/deeplabv3plus_r101-d8_512x1024_40k_cityscapes_20200605_094614-3769eecf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_40k_cityscapes/deeplabv3plus_r101-d8_512x1024_40k_cityscapes_20200605_094614.log.json)                             |
-| DeepLabV3+        | R-50-D8         | 769x769   |   40000 | 8.5      | 1.72           | V100   | 78.97 |         80.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-40k_cityscapes-769x769.py)                  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_40k_cityscapes/deeplabv3plus_r50-d8_769x769_40k_cityscapes_20200606_114143-1dcb0e3c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_40k_cityscapes/deeplabv3plus_r50-d8_769x769_40k_cityscapes_20200606_114143.log.json)                                     |
-| DeepLabV3+        | R-101-D8        | 769x769   |   40000 | 12.5     | 1.15           | V100   | 79.46 |         80.50 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-40k_cityscapes-769x769.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_40k_cityscapes/deeplabv3plus_r101-d8_769x769_40k_cityscapes_20200606_114304-ff414b9e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_40k_cityscapes/deeplabv3plus_r101-d8_769x769_40k_cityscapes_20200606_114304.log.json)                                 |
-| DeepLabV3+        | R-18-D8         | 512x1024  |   80000 | 2.2      | 14.27          | V100   | 76.89 |         78.76 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb2-80k_cityscapes-512x1024.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x1024_80k_cityscapes/deeplabv3plus_r18-d8_512x1024_80k_cityscapes_20201226_080942-cff257fe.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x1024_80k_cityscapes/deeplabv3plus_r18-d8_512x1024_80k_cityscapes-20201226_080942.log.json)                                 |
-| DeepLabV3+        | R-50-D8         | 512x1024  |   80000 | -        | -              | V100   | 80.09 |         81.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-512x1024.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes/deeplabv3plus_r50-d8_512x1024_80k_cityscapes_20200606_114049-f9fb496d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes/deeplabv3plus_r50-d8_512x1024_80k_cityscapes_20200606_114049.log.json)                                 |
-| DeepLabV3+        | R-101-D8        | 512x1024  |   80000 | -        | -              | V100   | 80.97 |         82.03 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-80k_cityscapes-512x1024.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143-068fcfe9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143.log.json)                             |
-| DeepLabV3+ (FP16) | R-101-D8        | 512x1024  |   80000 | 6.35     | 7.87           | V100   | 80.46 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920-f1104f4b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920.log.json)         |
-| DeepLabV3+        | R-18-D8         | 769x769   |   80000 | 2.5      | 5.74           | V100   | 76.26 |         77.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb2-80k_cityscapes-769x769.py)                  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_769x769_80k_cityscapes/deeplabv3plus_r18-d8_769x769_80k_cityscapes_20201226_083346-f326e06a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_769x769_80k_cityscapes/deeplabv3plus_r18-d8_769x769_80k_cityscapes-20201226_083346.log.json)                                     |
-| DeepLabV3+        | R-50-D8         | 769x769   |   80000 | -        | -              | V100   | 79.83 |         81.48 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-769x769.py)                  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes/deeplabv3plus_r50-d8_769x769_80k_cityscapes_20200606_210233-0e9dfdc4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes/deeplabv3plus_r50-d8_769x769_80k_cityscapes_20200606_210233.log.json)                                     |
-| DeepLabV3+        | R-101-D8        | 769x769   |   80000 | -        | -              | V100   | 80.65 |         81.47 | [config<sup>\[1\]</sup>](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes/deeplabv3plus_r101-d8_769x769_80k_cityscapes_20220406_154720-dfcc0b68.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes/deeplabv3plus_r101-d8_769x769_80k_cityscapes_20220406_154720.log.json)                                 |
-| DeepLabV3+        | R-101-D16-MG124 | 512x1024  |   40000 | 5.8      | 7.48           | V100   | 79.09 |         80.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/ddeeplabv3plus_r101-d16-mg124_4xb2-40k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes_20200908_005644-cf9ce186.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes-20200908_005644.log.json) |
-| DeepLabV3+        | R-101-D16-MG124 | 512x1024  |   80000 | 9.9      | -              | V100   | 79.90 |         81.33 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d16-mg124_4xb2-80k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes_20200908_005644-ee6158e0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes-20200908_005644.log.json) |
-| DeepLabV3+        | R-18b-D8        | 512x1024  |   80000 | 2.1      | 14.95          | V100   | 75.87 |         77.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18b-d8_4xb2-80k_cityscapes-512x1024.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes_20201226_090828-e451abd9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes-20201226_090828.log.json)                             |
-| DeepLabV3+        | R-50b-D8        | 512x1024  |   80000 | 7.4      | 3.94           | V100   | 80.28 |         81.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50b-d8_4xb2-80k_cityscapes-512x1024.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes_20201225_213645-a97e4e43.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes-20201225_213645.log.json)                             |
-| DeepLabV3+        | R-101b-D8       | 512x1024  |   80000 | 10.9     | 2.60           | V100   | 80.16 |         81.41 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101b-d8_4xb2-80k_cityscapes-512x1024.py)               | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes_20201226_190843-9c3c93a4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes-20201226_190843.log.json)                         |
-| DeepLabV3+        | R-18b-D8        | 769x769   |   80000 | 2.4      | 5.96           | V100   | 76.36 |         78.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18b-d8_4xb2-80k_cityscapes-769x769.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_769x769_80k_cityscapes/deeplabv3plus_r18b-d8_769x769_80k_cityscapes_20201226_151312-2c868aff.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_769x769_80k_cityscapes/deeplabv3plus_r18b-d8_769x769_80k_cityscapes-20201226_151312.log.json)                                 |
-| DeepLabV3+        | R-50b-D8        | 769x769   |   80000 | 8.4      | 1.72           | V100   | 79.41 |         80.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50b-d8_4xb2-80k_cityscapes-769x769.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_769x769_80k_cityscapes/deeplabv3plus_r50b-d8_769x769_80k_cityscapes_20201225_224655-8b596d1c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_769x769_80k_cityscapes/deeplabv3plus_r50b-d8_769x769_80k_cityscapes-20201225_224655.log.json)                                 |
-| DeepLabV3+        | R-101b-D8       | 769x769   |   80000 | 12.3     | 1.10           | V100   | 79.88 |         81.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101b-d8_4xb2-80k_cityscapes-769x769.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_769x769_80k_cityscapes/deeplabv3plus_r101b-d8_769x769_80k_cityscapes_20201226_205041-227cdf7c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_769x769_80k_cityscapes/deeplabv3plus_r101b-d8_769x769_80k_cityscapes-20201226_205041.log.json)                             |
+| Method            | Backbone        | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                                                                                                       |
+| ----------------- | --------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| DeepLabV3+        | R-50-D8         | 512x1024  |   40000 | 7.5      | 3.94           | V100   | 79.61 |         81.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-40k_cityscapes-512x1024.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_40k_cityscapes/deeplabv3plus_r50-d8_512x1024_40k_cityscapes_20200605_094610-d222ffcd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_40k_cityscapes/deeplabv3plus_r50-d8_512x1024_40k_cityscapes_20200605_094610.log.json)                                 |
+| DeepLabV3+        | R-101-D8        | 512x1024  |   40000 | 11       | 2.60           | V100   | 80.21 |         81.82 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-40k_cityscapes-512x1024.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_40k_cityscapes/deeplabv3plus_r101-d8_512x1024_40k_cityscapes_20200605_094614-3769eecf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_40k_cityscapes/deeplabv3plus_r101-d8_512x1024_40k_cityscapes_20200605_094614.log.json)                             |
+| DeepLabV3+        | R-50-D8         | 769x769   |   40000 | 8.5      | 1.72           | V100   | 78.97 |         80.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-40k_cityscapes-769x769.py)                  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_40k_cityscapes/deeplabv3plus_r50-d8_769x769_40k_cityscapes_20200606_114143-1dcb0e3c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_40k_cityscapes/deeplabv3plus_r50-d8_769x769_40k_cityscapes_20200606_114143.log.json)                                     |
+| DeepLabV3+        | R-101-D8        | 769x769   |   40000 | 12.5     | 1.15           | V100   | 79.46 |         80.50 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-40k_cityscapes-769x769.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_40k_cityscapes/deeplabv3plus_r101-d8_769x769_40k_cityscapes_20200606_114304-ff414b9e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_40k_cityscapes/deeplabv3plus_r101-d8_769x769_40k_cityscapes_20200606_114304.log.json)                                 |
+| DeepLabV3+        | R-18-D8         | 512x1024  |   80000 | 2.2      | 14.27          | V100   | 76.89 |         78.76 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb2-80k_cityscapes-512x1024.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x1024_80k_cityscapes/deeplabv3plus_r18-d8_512x1024_80k_cityscapes_20201226_080942-cff257fe.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x1024_80k_cityscapes/deeplabv3plus_r18-d8_512x1024_80k_cityscapes-20201226_080942.log.json)                                 |
+| DeepLabV3+        | R-50-D8         | 512x1024  |   80000 | -        | -              | V100   | 80.09 |         81.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-512x1024.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes/deeplabv3plus_r50-d8_512x1024_80k_cityscapes_20200606_114049-f9fb496d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes/deeplabv3plus_r50-d8_512x1024_80k_cityscapes_20200606_114049.log.json)                                 |
+| DeepLabV3+        | R-101-D8        | 512x1024  |   80000 | -        | -              | V100   | 80.97 |         82.03 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-80k_cityscapes-512x1024.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143-068fcfe9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143.log.json)                             |
+| DeepLabV3+ (FP16) | R-101-D8        | 512x1024  |   80000 | 6.35     | 7.87           | V100   | 80.46 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920-f1104f4b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920.log.json)         |
+| DeepLabV3+        | R-18-D8         | 769x769   |   80000 | 2.5      | 5.74           | V100   | 76.26 |         77.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb2-80k_cityscapes-769x769.py)                  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_769x769_80k_cityscapes/deeplabv3plus_r18-d8_769x769_80k_cityscapes_20201226_083346-f326e06a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_769x769_80k_cityscapes/deeplabv3plus_r18-d8_769x769_80k_cityscapes-20201226_083346.log.json)                                     |
+| DeepLabV3+        | R-50-D8         | 769x769   |   80000 | -        | -              | V100   | 79.83 |         81.48 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-769x769.py)                  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes/deeplabv3plus_r50-d8_769x769_80k_cityscapes_20200606_210233-0e9dfdc4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes/deeplabv3plus_r50-d8_769x769_80k_cityscapes_20200606_210233.log.json)                                     |
+| DeepLabV3+        | R-101-D8        | 769x769   |   80000 | -        | -              | V100   | 80.65 |         81.47 | [config<sup>\[1\]</sup>](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes/deeplabv3plus_r101-d8_769x769_80k_cityscapes_20220406_154720-dfcc0b68.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes/deeplabv3plus_r101-d8_769x769_80k_cityscapes_20220406_154720.log.json)                                 |
+| DeepLabV3+        | R-101-D16-MG124 | 512x1024  |   40000 | 5.8      | 7.48           | V100   | 79.09 |         80.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/ddeeplabv3plus_r101-d16-mg124_4xb2-40k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes_20200908_005644-cf9ce186.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes-20200908_005644.log.json) |
+| DeepLabV3+        | R-101-D16-MG124 | 512x1024  |   80000 | 9.9      | -              | V100   | 79.90 |         81.33 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r101-d16-mg124_4xb2-80k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes_20200908_005644-ee6158e0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes-20200908_005644.log.json) |
+| DeepLabV3+        | R-18b-D8        | 512x1024  |   80000 | 2.1      | 14.95          | V100   | 75.87 |         77.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r18b-d8_4xb2-80k_cityscapes-512x1024.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes_20201226_090828-e451abd9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes-20201226_090828.log.json)                             |
+| DeepLabV3+        | R-50b-D8        | 512x1024  |   80000 | 7.4      | 3.94           | V100   | 80.28 |         81.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r50b-d8_4xb2-80k_cityscapes-512x1024.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes_20201225_213645-a97e4e43.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes-20201225_213645.log.json)                             |
+| DeepLabV3+        | R-101b-D8       | 512x1024  |   80000 | 10.9     | 2.60           | V100   | 80.16 |         81.41 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r101b-d8_4xb2-80k_cityscapes-512x1024.py)               | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes_20201226_190843-9c3c93a4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes-20201226_190843.log.json)                         |
+| DeepLabV3+        | R-18b-D8        | 769x769   |   80000 | 2.4      | 5.96           | V100   | 76.36 |         78.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r18b-d8_4xb2-80k_cityscapes-769x769.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_769x769_80k_cityscapes/deeplabv3plus_r18b-d8_769x769_80k_cityscapes_20201226_151312-2c868aff.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_769x769_80k_cityscapes/deeplabv3plus_r18b-d8_769x769_80k_cityscapes-20201226_151312.log.json)                                 |
+| DeepLabV3+        | R-50b-D8        | 769x769   |   80000 | 8.4      | 1.72           | V100   | 79.41 |         80.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r50b-d8_4xb2-80k_cityscapes-769x769.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_769x769_80k_cityscapes/deeplabv3plus_r50b-d8_769x769_80k_cityscapes_20201225_224655-8b596d1c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_769x769_80k_cityscapes/deeplabv3plus_r50b-d8_769x769_80k_cityscapes-20201225_224655.log.json)                                 |
+| DeepLabV3+        | R-101b-D8       | 769x769   |   80000 | 12.3     | 1.10           | V100   | 79.88 |         81.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r101b-d8_4xb2-80k_cityscapes-769x769.py)                | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_769x769_80k_cityscapes/deeplabv3plus_r101b-d8_769x769_80k_cityscapes_20201226_205041-227cdf7c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_769x769_80k_cityscapes/deeplabv3plus_r101b-d8_769x769_80k_cityscapes-20201226_205041.log.json)                             |
 
 \[1\] The training of the model is sensitive to random seed, and the seed to train it is 1111.
 
 ### ADE20K
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                                                           |
-| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3+ | R-50-D8  | 512x512   |   80000 | 10.6     | 21.01          | V100   | 42.72 |         43.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_ade20k/deeplabv3plus_r50-d8_512x512_80k_ade20k_20200614_185028-bf1400d8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_ade20k/deeplabv3plus_r50-d8_512x512_80k_ade20k_20200614_185028.log.json)         |
-| DeepLabV3+ | R-101-D8 | 512x512   |   80000 | 14.1     | 14.16          | V100   | 44.60 |         46.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_ade20k/deeplabv3plus_r101-d8_512x512_80k_ade20k_20200615_014139-d5730af7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_ade20k/deeplabv3plus_r101-d8_512x512_80k_ade20k_20200615_014139.log.json)     |
-| DeepLabV3+ | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 43.95 |         44.93 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_160k_ade20k/deeplabv3plus_r50-d8_512x512_160k_ade20k_20200615_124504-6135c7e0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_160k_ade20k/deeplabv3plus_r50-d8_512x512_160k_ade20k_20200615_124504.log.json)     |
-| DeepLabV3+ | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 45.47 |         46.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_160k_ade20k/deeplabv3plus_r101-d8_512x512_160k_ade20k_20200615_123232-38ed86bb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_160k_ade20k/deeplabv3plus_r101-d8_512x512_160k_ade20k_20200615_123232.log.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                   | download                                                                                                                                                                                                                                                                                                                                                                           |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3+ | R-50-D8  | 512x512   |   80000 | 10.6     | 21.01          | V100   | 42.72 |         43.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_ade20k/deeplabv3plus_r50-d8_512x512_80k_ade20k_20200614_185028-bf1400d8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_ade20k/deeplabv3plus_r50-d8_512x512_80k_ade20k_20200614_185028.log.json)         |
+| DeepLabV3+ | R-101-D8 | 512x512   |   80000 | 14.1     | 14.16          | V100   | 44.60 |         46.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_ade20k/deeplabv3plus_r101-d8_512x512_80k_ade20k_20200615_014139-d5730af7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_ade20k/deeplabv3plus_r101-d8_512x512_80k_ade20k_20200615_014139.log.json)     |
+| DeepLabV3+ | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 43.95 |         44.93 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_160k_ade20k/deeplabv3plus_r50-d8_512x512_160k_ade20k_20200615_124504-6135c7e0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_160k_ade20k/deeplabv3plus_r50-d8_512x512_160k_ade20k_20200615_124504.log.json)     |
+| DeepLabV3+ | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 45.47 |         46.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_160k_ade20k/deeplabv3plus_r101-d8_512x512_160k_ade20k_20200615_123232-38ed86bb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_160k_ade20k/deeplabv3plus_r101-d8_512x512_160k_ade20k_20200615_123232.log.json) |
 
 ### Pascal VOC 2012 + Aug
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                       | download                                                                                                                                                                                                                                                                                                                                                                               |
-| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3+ | R-50-D8  | 512x512   |   20000 | 7.6      | 21             | V100   | 75.93 |         77.50 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_20k_voc12aug/deeplabv3plus_r50-d8_512x512_20k_voc12aug_20200617_102323-aad58ef1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_20k_voc12aug/deeplabv3plus_r50-d8_512x512_20k_voc12aug_20200617_102323.log.json)     |
-| DeepLabV3+ | R-101-D8 | 512x512   |   20000 | 11       | 13.88          | V100   | 77.22 |         78.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_20k_voc12aug/deeplabv3plus_r101-d8_512x512_20k_voc12aug_20200617_102345-c7ff3d56.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_20k_voc12aug/deeplabv3plus_r101-d8_512x512_20k_voc12aug_20200617_102345.log.json) |
-| DeepLabV3+ | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 76.81 |         77.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_40k_voc12aug/deeplabv3plus_r50-d8_512x512_40k_voc12aug_20200613_161759-e1b43aa9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_40k_voc12aug/deeplabv3plus_r50-d8_512x512_40k_voc12aug_20200613_161759.log.json)     |
-| DeepLabV3+ | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 78.62 |         79.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_40k_voc12aug/deeplabv3plus_r101-d8_512x512_40k_voc12aug_20200613_205333-faf03387.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_40k_voc12aug/deeplabv3plus_r101-d8_512x512_40k_voc12aug_20200613_205333.log.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                    | download                                                                                                                                                                                                                                                                                                                                                                               |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3+ | R-50-D8  | 512x512   |   20000 | 7.6      | 21             | V100   | 75.93 |         77.50 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_20k_voc12aug/deeplabv3plus_r50-d8_512x512_20k_voc12aug_20200617_102323-aad58ef1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_20k_voc12aug/deeplabv3plus_r50-d8_512x512_20k_voc12aug_20200617_102323.log.json)     |
+| DeepLabV3+ | R-101-D8 | 512x512   |   20000 | 11       | 13.88          | V100   | 77.22 |         78.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_20k_voc12aug/deeplabv3plus_r101-d8_512x512_20k_voc12aug_20200617_102345-c7ff3d56.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_20k_voc12aug/deeplabv3plus_r101-d8_512x512_20k_voc12aug_20200617_102345.log.json) |
+| DeepLabV3+ | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 76.81 |         77.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_40k_voc12aug/deeplabv3plus_r50-d8_512x512_40k_voc12aug_20200613_161759-e1b43aa9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_40k_voc12aug/deeplabv3plus_r50-d8_512x512_40k_voc12aug_20200613_161759.log.json)     |
+| DeepLabV3+ | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 78.62 |         79.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_40k_voc12aug/deeplabv3plus_r101-d8_512x512_40k_voc12aug_20200613_205333-faf03387.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_40k_voc12aug/deeplabv3plus_r101-d8_512x512_40k_voc12aug_20200613_205333.log.json) |
 
 ### Pascal Context
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                                                                       |
-| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3+ | R-101-D8 | 480x480   |   40000 | -        | 9.09           | V100   | 47.30 |         48.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context/deeplabv3plus_r101-d8_480x480_40k_pascal_context_20200911_165459-d3c8a29e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context/deeplabv3plus_r101-d8_480x480_40k_pascal_context-20200911_165459.log.json) |
-| DeepLabV3+ | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 47.23 |         48.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context/deeplabv3plus_r101-d8_480x480_80k_pascal_context_20200911_155322-145d3ee8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context/deeplabv3plus_r101-d8_480x480_80k_pascal_context-20200911_155322.log.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                                                                       |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3+ | R-101-D8 | 480x480   |   40000 | -        | 9.09           | V100   | 47.30 |         48.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context/deeplabv3plus_r101-d8_480x480_40k_pascal_context_20200911_165459-d3c8a29e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context/deeplabv3plus_r101-d8_480x480_40k_pascal_context-20200911_165459.log.json) |
+| DeepLabV3+ | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 47.23 |         48.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context/deeplabv3plus_r101-d8_480x480_80k_pascal_context_20200911_155322-145d3ee8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context/deeplabv3plus_r101-d8_480x480_80k_pascal_context-20200911_155322.log.json) |
 
 ### Pascal Context 59
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                                | download                                                                                                                                                                                                                                                                                                                                                                                                                   |
-| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3+ | R-101-D8 | 480x480   |   40000 | -        | -              | V100   | 52.86 |         54.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59_20210416_111233-ed937f15.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59-20210416_111233.log.json) |
-| DeepLabV3+ | R-101-D8 | 480x480   |   80000 | -        | -              | V100   |  53.2 |         54.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59_20210416_111127-7ca0331d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59-20210416_111127.log.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                             | download                                                                                                                                                                                                                                                                                                                                                                                                                   |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3+ | R-101-D8 | 480x480   |   40000 | -        | -              | V100   | 52.86 |         54.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59_20210416_111233-ed937f15.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59-20210416_111233.log.json) |
+| DeepLabV3+ | R-101-D8 | 480x480   |   80000 | -        | -              | V100   |  53.2 |         54.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59_20210416_111127-7ca0331d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59-20210416_111127.log.json) |
 
 ### LoveDA
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                                       |
-| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| DeepLabV3+ | R-18-D8  | 512x512   |   80000 | 1.93     | 25.57          | V100   | 50.28 |         50.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_loveda-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_loveda/deeplabv3plus_r18-d8_512x512_80k_loveda_20211104_132800-ce0fa0ca.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_loveda/deeplabv3plus_r18-d8_512x512_80k_loveda_20211104_132800.log.json)     |
-| DeepLabV3+ | R-50-D8  | 512x512   |   80000 | 7.37     | 6.00           | V100   | 50.99 |         50.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_loveda-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_loveda/deeplabv3plus_r50-d8_512x512_80k_loveda_20211105_080442-f0720392.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_loveda/deeplabv3plus_r50-d8_512x512_80k_loveda_20211105_080442.log.json)     |
-| DeepLabV3+ | R-101-D8 | 512x512   |   80000 | 10.84    | 4.33           | V100   | 51.47 |         51.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_loveda-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_loveda/deeplabv3plus_r101-d8_512x512_80k_loveda_20211105_110759-4c1f297e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_loveda/deeplabv3plus_r101-d8_512x512_80k_loveda_20211105_110759.log.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                  | download                                                                                                                                                                                                                                                                                                                                                                       |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| DeepLabV3+ | R-18-D8  | 512x512   |   80000 | 1.93     | 25.57          | V100   | 50.28 |         50.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_loveda-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_loveda/deeplabv3plus_r18-d8_512x512_80k_loveda_20211104_132800-ce0fa0ca.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_loveda/deeplabv3plus_r18-d8_512x512_80k_loveda_20211104_132800.log.json)     |
+| DeepLabV3+ | R-50-D8  | 512x512   |   80000 | 7.37     | 6.00           | V100   | 50.99 |         50.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_loveda-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_loveda/deeplabv3plus_r50-d8_512x512_80k_loveda_20211105_080442-f0720392.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_loveda/deeplabv3plus_r50-d8_512x512_80k_loveda_20211105_080442.log.json)     |
+| DeepLabV3+ | R-101-D8 | 512x512   |   80000 | 10.84    | 4.33           | V100   | 51.47 |         51.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_loveda-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_loveda/deeplabv3plus_r101-d8_512x512_80k_loveda_20211105_110759-4c1f297e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_loveda/deeplabv3plus_r101-d8_512x512_80k_loveda_20211105_110759.log.json) |
 
 ### Potsdam
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                                                           |
-| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3+ | R-18-D8  | 512x512   |   80000 | 1.91     | 81.68          | V100   | 77.09 |         78.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_potsdam/deeplabv3plus_r18-d8_512x512_80k_potsdam_20211219_020601-75fd5bc3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_potsdam/deeplabv3plus_r18-d8_512x512_80k_potsdam_20211219_020601.log.json)     |
-| DeepLabV3+ | R-50-D8  | 512x512   |   80000 | 7.36     | 26.44          | V100   | 78.33 |         79.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_potsdam/deeplabv3plus_r50-d8_512x512_80k_potsdam_20211219_031508-7e7a2b24.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_potsdam/deeplabv3plus_r50-d8_512x512_80k_potsdam_20211219_031508.log.json)     |
-| DeepLabV3+ | R-101-D8 | 512x512   |   80000 | 10.83    | 17.56          | V100   |  78.7 |         79.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_potsdam-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_potsdam/deeplabv3plus_r101-d8_512x512_80k_potsdam_20211219_031508-8b112708.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_potsdam/deeplabv3plus_r101-d8_512x512_80k_potsdam_20211219_031508.log.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                   | download                                                                                                                                                                                                                                                                                                                                                                           |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3+ | R-18-D8  | 512x512   |   80000 | 1.91     | 81.68          | V100   | 77.09 |         78.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_potsdam/deeplabv3plus_r18-d8_512x512_80k_potsdam_20211219_020601-75fd5bc3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_potsdam/deeplabv3plus_r18-d8_512x512_80k_potsdam_20211219_020601.log.json)     |
+| DeepLabV3+ | R-50-D8  | 512x512   |   80000 | 7.36     | 26.44          | V100   | 78.33 |         79.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_potsdam/deeplabv3plus_r50-d8_512x512_80k_potsdam_20211219_031508-7e7a2b24.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_potsdam/deeplabv3plus_r50-d8_512x512_80k_potsdam_20211219_031508.log.json)     |
+| DeepLabV3+ | R-101-D8 | 512x512   |   80000 | 10.83    | 17.56          | V100   |  78.7 |         79.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_potsdam-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_potsdam/deeplabv3plus_r101-d8_512x512_80k_potsdam_20211219_031508-8b112708.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_potsdam/deeplabv3plus_r101-d8_512x512_80k_potsdam_20211219_031508.log.json) |
 
 ### Vaihingen
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                                                                   |
-| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3+ | R-18-D8  | 512x512   |   80000 | 1.91     | 72.79          | V100   | 72.50 |         74.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen_20211231_230805-7626a263.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen_20211231_230805.log.json)     |
-| DeepLabV3+ | R-50-D8  | 512x512   |   80000 | 7.36     | 26.91          | V100   | 73.97 |         75.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen_20211231_230816-5040938d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen_20211231_230816.log.json)     |
-| DeepLabV3+ | R-101-D8 | 512x512   |   80000 | 10.83    | 18.59          | V100   | 73.06 |         74.14 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_vaihingen-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen_20211231_230816-8a095afa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen_20211231_230816.log.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                                                                   |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3+ | R-18-D8  | 512x512   |   80000 | 1.91     | 72.79          | V100   | 72.50 |         74.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen_20211231_230805-7626a263.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen_20211231_230805.log.json)     |
+| DeepLabV3+ | R-50-D8  | 512x512   |   80000 | 7.36     | 26.91          | V100   | 73.97 |         75.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen_20211231_230816-5040938d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen_20211231_230816.log.json)     |
+| DeepLabV3+ | R-101-D8 | 512x512   |   80000 | 10.83    | 18.59          | V100   | 73.06 |         74.14 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb4-80k_vaihingen-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen_20211231_230816-8a095afa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen_20211231_230816.log.json) |
 
 ### iSAID
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                   | download                                                                                                                                                                                                                                                                                                                                                                               |
-| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3+ | R-18-D8  | 896x896   |   80000 | 6.19     | 24.81          | V100   | 61.35 |         62.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid_20220110_180526-7059991d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid_20220110_180526.log.json) |
-| DeepLabV3+ | R-50-D8  | 896x896   |   80000 | 21.45    | 8.42           | V100   | 67.06 |         68.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid_20220110_180526-598be439.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid_20220110_180526.log.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                | download                                                                                                                                                                                                                                                                                                                                                                               |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3+ | R-18-D8  | 896x896   |   80000 | 6.19     | 24.81          | V100   | 61.35 |         62.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid_20220110_180526-7059991d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid_20220110_180526.log.json) |
+| DeepLabV3+ | R-50-D8  | 896x896   |   80000 | 21.45    | 8.42           | V100   | 67.06 |         68.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid_20220110_180526-598be439.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid_20220110_180526.log.json) |
 
 ### Mapillary Vistas v1.2
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                               | download                                                                                                                                                                                                                                                                                                                                                                                                                               |
-| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DeepLabV3+ | R-50-D8  | 1280x1280 |  300000 | 24.04    | 17.92          | A100   | 47.35 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280_20230301_110504-655f8e43.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280_20230301_110504.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3+ | R-50-D8  | 1280x1280 |  300000 | 24.04    | 17.92          | A100   | 47.35 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280_20230301_110504-655f8e43.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280_20230301_110504.json) |
 
 Note:
 
diff --git a/configs/dmnet/README.md b/configs/dmnet/README.md
index 6004c06ccb..b0cf94455e 100644
--- a/configs/dmnet/README.md
+++ b/configs/dmnet/README.md
@@ -26,25 +26,25 @@ Multi-scale representation provides an effective way toaddress scale variation o
 
 ### Cityscapes
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DMNet  | R-50-D8  | 512x1024  |   40000 | 7.0      | 3.66           | V100   | 77.78 |         79.14 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_40k_cityscapes/dmnet_r50-d8_512x1024_40k_cityscapes_20201215_042326-615373cf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_40k_cityscapes/dmnet_r50-d8_512x1024_40k_cityscapes-20201215_042326.log.json)     |
-| DMNet  | R-101-D8 | 512x1024  |   40000 | 10.6     | 2.54           | V100   | 78.37 |         79.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_40k_cityscapes/dmnet_r101-d8_512x1024_40k_cityscapes_20201215_043100-8291e976.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_40k_cityscapes/dmnet_r101-d8_512x1024_40k_cityscapes-20201215_043100.log.json) |
-| DMNet  | R-50-D8  | 769x769   |   40000 | 7.9      | 1.57           | V100   | 78.49 |         80.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_40k_cityscapes/dmnet_r50-d8_769x769_40k_cityscapes_20201215_093706-e7f0e23e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_40k_cityscapes/dmnet_r50-d8_769x769_40k_cityscapes-20201215_093706.log.json)         |
-| DMNet  | R-101-D8 | 769x769   |   40000 | 12.0     | 1.01           | V100   | 77.62 |         78.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_40k_cityscapes/dmnet_r101-d8_769x769_40k_cityscapes_20201215_081348-a74261f6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_40k_cityscapes/dmnet_r101-d8_769x769_40k_cityscapes-20201215_081348.log.json)     |
-| DMNet  | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 79.07 |         80.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_80k_cityscapes/dmnet_r50-d8_512x1024_80k_cityscapes_20201215_053728-3c8893b9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_80k_cityscapes/dmnet_r50-d8_512x1024_80k_cityscapes-20201215_053728.log.json)     |
-| DMNet  | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 79.64 |         80.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_80k_cityscapes/dmnet_r101-d8_512x1024_80k_cityscapes_20201215_031718-fa081cb8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_80k_cityscapes/dmnet_r101-d8_512x1024_80k_cityscapes-20201215_031718.log.json) |
-| DMNet  | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 79.22 |         80.55 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_80k_cityscapes/dmnet_r50-d8_769x769_80k_cityscapes_20201215_034006-6060840e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_80k_cityscapes/dmnet_r50-d8_769x769_80k_cityscapes-20201215_034006.log.json)         |
-| DMNet  | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 79.19 |         80.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_80k_cityscapes/dmnet_r101-d8_769x769_80k_cityscapes_20201215_082810-7f0de59a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_80k_cityscapes/dmnet_r101-d8_769x769_80k_cityscapes-20201215_082810.log.json)     |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DMNet  | R-50-D8  | 512x1024  |   40000 | 7.0      | 3.66           | V100   | 77.78 |         79.14 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dmnet/dmnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_40k_cityscapes/dmnet_r50-d8_512x1024_40k_cityscapes_20201215_042326-615373cf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_40k_cityscapes/dmnet_r50-d8_512x1024_40k_cityscapes-20201215_042326.log.json)     |
+| DMNet  | R-101-D8 | 512x1024  |   40000 | 10.6     | 2.54           | V100   | 78.37 |         79.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dmnet/dmnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_40k_cityscapes/dmnet_r101-d8_512x1024_40k_cityscapes_20201215_043100-8291e976.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_40k_cityscapes/dmnet_r101-d8_512x1024_40k_cityscapes-20201215_043100.log.json) |
+| DMNet  | R-50-D8  | 769x769   |   40000 | 7.9      | 1.57           | V100   | 78.49 |         80.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dmnet/dmnet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_40k_cityscapes/dmnet_r50-d8_769x769_40k_cityscapes_20201215_093706-e7f0e23e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_40k_cityscapes/dmnet_r50-d8_769x769_40k_cityscapes-20201215_093706.log.json)         |
+| DMNet  | R-101-D8 | 769x769   |   40000 | 12.0     | 1.01           | V100   | 77.62 |         78.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dmnet/dmnet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_40k_cityscapes/dmnet_r101-d8_769x769_40k_cityscapes_20201215_081348-a74261f6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_40k_cityscapes/dmnet_r101-d8_769x769_40k_cityscapes-20201215_081348.log.json)     |
+| DMNet  | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 79.07 |         80.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dmnet/dmnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_80k_cityscapes/dmnet_r50-d8_512x1024_80k_cityscapes_20201215_053728-3c8893b9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_80k_cityscapes/dmnet_r50-d8_512x1024_80k_cityscapes-20201215_053728.log.json)     |
+| DMNet  | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 79.64 |         80.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dmnet/dmnet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_80k_cityscapes/dmnet_r101-d8_512x1024_80k_cityscapes_20201215_031718-fa081cb8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_80k_cityscapes/dmnet_r101-d8_512x1024_80k_cityscapes-20201215_031718.log.json) |
+| DMNet  | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 79.22 |         80.55 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dmnet/dmnet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_80k_cityscapes/dmnet_r50-d8_769x769_80k_cityscapes_20201215_034006-6060840e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_80k_cityscapes/dmnet_r50-d8_769x769_80k_cityscapes-20201215_034006.log.json)         |
+| DMNet  | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 79.19 |         80.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dmnet/dmnet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_80k_cityscapes/dmnet_r101-d8_769x769_80k_cityscapes_20201215_082810-7f0de59a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_80k_cityscapes/dmnet_r101-d8_769x769_80k_cityscapes-20201215_082810.log.json)     |
 
 ### ADE20K
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DMNet  | R-50-D8  | 512x512   |   80000 | 9.4      | 20.95          | V100   | 42.37 |         43.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_80k_ade20k/dmnet_r50-d8_512x512_80k_ade20k_20201215_144744-f89092a6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_80k_ade20k/dmnet_r50-d8_512x512_80k_ade20k-20201215_144744.log.json)         |
-| DMNet  | R-101-D8 | 512x512   |   80000 | 13.0     | 13.88          | V100   | 45.34 |         46.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_80k_ade20k/dmnet_r101-d8_512x512_80k_ade20k_20201215_104812-bfa45311.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_80k_ade20k/dmnet_r101-d8_512x512_80k_ade20k-20201215_104812.log.json)     |
-| DMNet  | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 43.15 |         44.17 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_160k_ade20k/dmnet_r50-d8_512x512_160k_ade20k_20201215_115313-025ab3f9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_160k_ade20k/dmnet_r50-d8_512x512_160k_ade20k-20201215_115313.log.json)     |
-| DMNet  | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 45.42 |         46.76 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dmnet/dmnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_160k_ade20k/dmnet_r101-d8_512x512_160k_ade20k_20201215_111145-a0bc02ef.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_160k_ade20k/dmnet_r101-d8_512x512_160k_ade20k-20201215_111145.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                   | download                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DMNet  | R-50-D8  | 512x512   |   80000 | 9.4      | 20.95          | V100   | 42.37 |         43.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dmnet/dmnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_80k_ade20k/dmnet_r50-d8_512x512_80k_ade20k_20201215_144744-f89092a6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_80k_ade20k/dmnet_r50-d8_512x512_80k_ade20k-20201215_144744.log.json)         |
+| DMNet  | R-101-D8 | 512x512   |   80000 | 13.0     | 13.88          | V100   | 45.34 |         46.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dmnet/dmnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_80k_ade20k/dmnet_r101-d8_512x512_80k_ade20k_20201215_104812-bfa45311.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_80k_ade20k/dmnet_r101-d8_512x512_80k_ade20k-20201215_104812.log.json)     |
+| DMNet  | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 43.15 |         44.17 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dmnet/dmnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_160k_ade20k/dmnet_r50-d8_512x512_160k_ade20k_20201215_115313-025ab3f9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_160k_ade20k/dmnet_r50-d8_512x512_160k_ade20k-20201215_115313.log.json)     |
+| DMNet  | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 45.42 |         46.76 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dmnet/dmnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_160k_ade20k/dmnet_r101-d8_512x512_160k_ade20k_20201215_111145-a0bc02ef.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_160k_ade20k/dmnet_r101-d8_512x512_160k_ade20k-20201215_111145.log.json) |
 
 ## Citation
 
diff --git a/configs/dnlnet/README.md b/configs/dnlnet/README.md
index 12338c730c..6835ffd1ed 100644
--- a/configs/dnlnet/README.md
+++ b/configs/dnlnet/README.md
@@ -26,25 +26,25 @@ The non-local block is a popular module for strengthening the context modeling a
 
 ### Cityscapes
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                     |
-| ------ | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DNLNet | R-50-D8  | 512x1024  |   40000 |      7.3 | 2.56           | V100   | 78.61 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_40k_cityscapes/dnl_r50-d8_512x1024_40k_cityscapes_20200904_233629-53d4ea93.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_40k_cityscapes/dnl_r50-d8_512x1024_40k_cityscapes-20200904_233629.log.json)     |
-| DNLNet | R-101-D8 | 512x1024  |   40000 |     10.9 | 1.96           | V100   | 78.31 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_40k_cityscapes/dnl_r101-d8_512x1024_40k_cityscapes_20200904_233629-9928ffef.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_40k_cityscapes/dnl_r101-d8_512x1024_40k_cityscapes-20200904_233629.log.json) |
-| DNLNet | R-50-D8  | 769x769   |   40000 |      9.2 | 1.50           | V100   | 78.44 | 80.27         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_40k_cityscapes/dnl_r50-d8_769x769_40k_cityscapes_20200820_232206-0f283785.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_40k_cityscapes/dnl_r50-d8_769x769_40k_cityscapes-20200820_232206.log.json)         |
-| DNLNet | R-101-D8 | 769x769   |   40000 |     12.6 | 1.02           | V100   | 76.39 | 77.77         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_40k_cityscapes/dnl_r101-d8_769x769_40k_cityscapes_20200820_171256-76c596df.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_40k_cityscapes/dnl_r101-d8_769x769_40k_cityscapes-20200820_171256.log.json)     |
-| DNLNet | R-50-D8  | 512x1024  |   80000 |        - | -              | V100   | 79.33 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_80k_cityscapes/dnl_r50-d8_512x1024_80k_cityscapes_20200904_233629-58b2f778.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_80k_cityscapes/dnl_r50-d8_512x1024_80k_cityscapes-20200904_233629.log.json)     |
-| DNLNet | R-101-D8 | 512x1024  |   80000 |        - | -              | V100   | 80.41 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_80k_cityscapes/dnl_r101-d8_512x1024_80k_cityscapes_20200904_233629-758e2dd4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_80k_cityscapes/dnl_r101-d8_512x1024_80k_cityscapes-20200904_233629.log.json) |
-| DNLNet | R-50-D8  | 769x769   |   80000 |        - | -              | V100   | 79.36 | 80.70         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_80k_cityscapes/dnl_r50-d8_769x769_80k_cityscapes_20200820_011925-366bc4c7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_80k_cityscapes/dnl_r50-d8_769x769_80k_cityscapes-20200820_011925.log.json)         |
-| DNLNet | R-101-D8 | 769x769   |   80000 |        - | -              | V100   | 79.41 | 80.68         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_80k_cityscapes/dnl_r101-d8_769x769_80k_cityscapes_20200821_051111-95ff84ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_80k_cityscapes/dnl_r101-d8_769x769_80k_cityscapes-20200821_051111.log.json)     |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                     |
+| ------ | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | --------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DNLNet | R-50-D8  | 512x1024  |   40000 |      7.3 | 2.56           | V100   | 78.61 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dnlnet/dnl_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_40k_cityscapes/dnl_r50-d8_512x1024_40k_cityscapes_20200904_233629-53d4ea93.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_40k_cityscapes/dnl_r50-d8_512x1024_40k_cityscapes-20200904_233629.log.json)     |
+| DNLNet | R-101-D8 | 512x1024  |   40000 |     10.9 | 1.96           | V100   | 78.31 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dnlnet/dnl_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_40k_cityscapes/dnl_r101-d8_512x1024_40k_cityscapes_20200904_233629-9928ffef.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_40k_cityscapes/dnl_r101-d8_512x1024_40k_cityscapes-20200904_233629.log.json) |
+| DNLNet | R-50-D8  | 769x769   |   40000 |      9.2 | 1.50           | V100   | 78.44 | 80.27         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dnlnet/dnl_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_40k_cityscapes/dnl_r50-d8_769x769_40k_cityscapes_20200820_232206-0f283785.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_40k_cityscapes/dnl_r50-d8_769x769_40k_cityscapes-20200820_232206.log.json)         |
+| DNLNet | R-101-D8 | 769x769   |   40000 |     12.6 | 1.02           | V100   | 76.39 | 77.77         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dnlnet/dnl_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_40k_cityscapes/dnl_r101-d8_769x769_40k_cityscapes_20200820_171256-76c596df.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_40k_cityscapes/dnl_r101-d8_769x769_40k_cityscapes-20200820_171256.log.json)     |
+| DNLNet | R-50-D8  | 512x1024  |   80000 |        - | -              | V100   | 79.33 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dnlnet/dnl_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_80k_cityscapes/dnl_r50-d8_512x1024_80k_cityscapes_20200904_233629-58b2f778.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_80k_cityscapes/dnl_r50-d8_512x1024_80k_cityscapes-20200904_233629.log.json)     |
+| DNLNet | R-101-D8 | 512x1024  |   80000 |        - | -              | V100   | 80.41 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dnlnet/dnl_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_80k_cityscapes/dnl_r101-d8_512x1024_80k_cityscapes_20200904_233629-758e2dd4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_80k_cityscapes/dnl_r101-d8_512x1024_80k_cityscapes-20200904_233629.log.json) |
+| DNLNet | R-50-D8  | 769x769   |   80000 |        - | -              | V100   | 79.36 | 80.70         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dnlnet/dnl_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_80k_cityscapes/dnl_r50-d8_769x769_80k_cityscapes_20200820_011925-366bc4c7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_80k_cityscapes/dnl_r50-d8_769x769_80k_cityscapes-20200820_011925.log.json)         |
+| DNLNet | R-101-D8 | 769x769   |   80000 |        - | -              | V100   | 79.41 | 80.68         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dnlnet/dnl_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_80k_cityscapes/dnl_r101-d8_769x769_80k_cityscapes_20200821_051111-95ff84ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_80k_cityscapes/dnl_r101-d8_769x769_80k_cityscapes-20200821_051111.log.json)     |
 
 ### ADE20K
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                     | download                                                                                                                                                                                                                                                                                                                     |
-| ------ | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| DNLNet | R-50-D8  | 512x512   |   80000 |      8.8 | 20.66          | V100   | 41.76 | 42.99         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_80k_ade20k/dnl_r50-d8_512x512_80k_ade20k_20200826_183354-1cf6e0c1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_80k_ade20k/dnl_r50-d8_512x512_80k_ade20k-20200826_183354.log.json)         |
-| DNLNet | R-101-D8 | 512x512   |   80000 |     12.8 | 12.54          | V100   | 43.76 | 44.91         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_80k_ade20k/dnl_r101-d8_512x512_80k_ade20k_20200826_183354-d820d6ea.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_80k_ade20k/dnl_r101-d8_512x512_80k_ade20k-20200826_183354.log.json)     |
-| DNLNet | R-50-D8  | 512x512   |  160000 |        - | -              | V100   | 41.87 | 43.01         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_160k_ade20k/dnl_r50-d8_512x512_160k_ade20k_20200826_183350-37837798.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_160k_ade20k/dnl_r50-d8_512x512_160k_ade20k-20200826_183350.log.json)     |
-| DNLNet | R-101-D8 | 512x512   |  160000 |        - | -              | V100   | 44.25 | 45.78         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dnlnet/dnl_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_160k_ade20k/dnl_r101-d8_512x512_160k_ade20k_20200826_183350-ed522c61.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_160k_ade20k/dnl_r101-d8_512x512_160k_ade20k-20200826_183350.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                                                     |
+| ------ | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ----------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DNLNet | R-50-D8  | 512x512   |   80000 |      8.8 | 20.66          | V100   | 41.76 | 42.99         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dnlnet/dnl_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_80k_ade20k/dnl_r50-d8_512x512_80k_ade20k_20200826_183354-1cf6e0c1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_80k_ade20k/dnl_r50-d8_512x512_80k_ade20k-20200826_183354.log.json)         |
+| DNLNet | R-101-D8 | 512x512   |   80000 |     12.8 | 12.54          | V100   | 43.76 | 44.91         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dnlnet/dnl_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_80k_ade20k/dnl_r101-d8_512x512_80k_ade20k_20200826_183354-d820d6ea.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_80k_ade20k/dnl_r101-d8_512x512_80k_ade20k-20200826_183354.log.json)     |
+| DNLNet | R-50-D8  | 512x512   |  160000 |        - | -              | V100   | 41.87 | 43.01         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dnlnet/dnl_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_160k_ade20k/dnl_r50-d8_512x512_160k_ade20k_20200826_183350-37837798.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_160k_ade20k/dnl_r50-d8_512x512_160k_ade20k-20200826_183350.log.json)     |
+| DNLNet | R-101-D8 | 512x512   |  160000 |        - | -              | V100   | 44.25 | 45.78         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dnlnet/dnl_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_160k_ade20k/dnl_r101-d8_512x512_160k_ade20k_20200826_183350-ed522c61.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_160k_ade20k/dnl_r101-d8_512x512_160k_ade20k-20200826_183350.log.json) |
 
 ## Notes
 
diff --git a/configs/dpt/README.md b/configs/dpt/README.md
index 432d1dd226..b3a5573a65 100644
--- a/configs/dpt/README.md
+++ b/configs/dpt/README.md
@@ -44,9 +44,9 @@ This script convert model from `PRETRAIN_PATH` and store the converted model in
 
 ### ADE20K
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                               |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| DPT    | ViT-B    | 512x512   |  160000 | 8.09     | 10.41          | V100   | 46.97 |         48.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/dpt/dpt_vit-b16_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dpt/dpt_vit-b16_512x512_160k_ade20k/dpt_vit-b16_512x512_160k_ade20k-db31cf52.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dpt/dpt_vit-b16_512x512_160k_ade20k/dpt_vit-b16_512x512_160k_ade20k-20210809_172025.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                               | download                                                                                                                                                                                                                                                                                               |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| DPT    | ViT-B    | 512x512   |  160000 | 8.09     | 10.41          | V100   | 46.97 |         48.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dpt/dpt_vit-b16_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dpt/dpt_vit-b16_512x512_160k_ade20k/dpt_vit-b16_512x512_160k_ade20k-db31cf52.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/dpt/dpt_vit-b16_512x512_160k_ade20k/dpt_vit-b16_512x512_160k_ade20k-20210809_172025.log.json) |
 
 ## Citation
 
diff --git a/configs/encnet/README.md b/configs/encnet/README.md
index 31bbd98c6b..ff09bc32f8 100644
--- a/configs/encnet/README.md
+++ b/configs/encnet/README.md
@@ -26,25 +26,25 @@ Recent work has made significant progress in improving spatial resolution for pi
 
 ### Cityscapes
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| EncNet | R-50-D8  | 512x1024  |   40000 | 8.6      | 4.58           | V100   | 75.67 |         77.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_40k_cityscapes/encnet_r50-d8_512x1024_40k_cityscapes_20200621_220958-68638a47.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_40k_cityscapes/encnet_r50-d8_512x1024_40k_cityscapes-20200621_220958.log.json)     |
-| EncNet | R-101-D8 | 512x1024  |   40000 | 12.1     | 2.66           | V100   | 75.81 |         77.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_40k_cityscapes/encnet_r101-d8_512x1024_40k_cityscapes_20200621_220933-35e0a3e8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_40k_cityscapes/encnet_r101-d8_512x1024_40k_cityscapes-20200621_220933.log.json) |
-| EncNet | R-50-D8  | 769x769   |   40000 | 9.8      | 1.82           | V100   | 76.24 |         77.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_40k_cityscapes/encnet_r50-d8_769x769_40k_cityscapes_20200621_220958-3bcd2884.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_40k_cityscapes/encnet_r50-d8_769x769_40k_cityscapes-20200621_220958.log.json)         |
-| EncNet | R-101-D8 | 769x769   |   40000 | 13.7     | 1.26           | V100   | 74.25 |         76.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_40k_cityscapes/encnet_r101-d8_769x769_40k_cityscapes_20200621_220933-2fafed55.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_40k_cityscapes/encnet_r101-d8_769x769_40k_cityscapes-20200621_220933.log.json)     |
-| EncNet | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 77.94 |         79.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_80k_cityscapes/encnet_r50-d8_512x1024_80k_cityscapes_20200622_003554-fc5c5624.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_80k_cityscapes/encnet_r50-d8_512x1024_80k_cityscapes-20200622_003554.log.json)     |
-| EncNet | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 78.55 |         79.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_80k_cityscapes/encnet_r101-d8_512x1024_80k_cityscapes_20200622_003555-1de64bec.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_80k_cityscapes/encnet_r101-d8_512x1024_80k_cityscapes-20200622_003555.log.json) |
-| EncNet | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 77.44 |         78.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_80k_cityscapes/encnet_r50-d8_769x769_80k_cityscapes_20200622_003554-55096dcb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_80k_cityscapes/encnet_r50-d8_769x769_80k_cityscapes-20200622_003554.log.json)         |
-| EncNet | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 76.10 |         76.97 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_80k_cityscapes/encnet_r101-d8_769x769_80k_cityscapes_20200622_003555-470ef79d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_80k_cityscapes/encnet_r101-d8_769x769_80k_cityscapes-20200622_003555.log.json)     |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| EncNet | R-50-D8  | 512x1024  |   40000 | 8.6      | 4.58           | V100   | 75.67 |         77.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/encnet/encnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_40k_cityscapes/encnet_r50-d8_512x1024_40k_cityscapes_20200621_220958-68638a47.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_40k_cityscapes/encnet_r50-d8_512x1024_40k_cityscapes-20200621_220958.log.json)     |
+| EncNet | R-101-D8 | 512x1024  |   40000 | 12.1     | 2.66           | V100   | 75.81 |         77.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/encnet/encnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_40k_cityscapes/encnet_r101-d8_512x1024_40k_cityscapes_20200621_220933-35e0a3e8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_40k_cityscapes/encnet_r101-d8_512x1024_40k_cityscapes-20200621_220933.log.json) |
+| EncNet | R-50-D8  | 769x769   |   40000 | 9.8      | 1.82           | V100   | 76.24 |         77.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/encnet/encnet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_40k_cityscapes/encnet_r50-d8_769x769_40k_cityscapes_20200621_220958-3bcd2884.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_40k_cityscapes/encnet_r50-d8_769x769_40k_cityscapes-20200621_220958.log.json)         |
+| EncNet | R-101-D8 | 769x769   |   40000 | 13.7     | 1.26           | V100   | 74.25 |         76.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/encnet/encnet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_40k_cityscapes/encnet_r101-d8_769x769_40k_cityscapes_20200621_220933-2fafed55.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_40k_cityscapes/encnet_r101-d8_769x769_40k_cityscapes-20200621_220933.log.json)     |
+| EncNet | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 77.94 |         79.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/encnet/encnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_80k_cityscapes/encnet_r50-d8_512x1024_80k_cityscapes_20200622_003554-fc5c5624.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_80k_cityscapes/encnet_r50-d8_512x1024_80k_cityscapes-20200622_003554.log.json)     |
+| EncNet | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 78.55 |         79.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/encnet/encnet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_80k_cityscapes/encnet_r101-d8_512x1024_80k_cityscapes_20200622_003555-1de64bec.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_80k_cityscapes/encnet_r101-d8_512x1024_80k_cityscapes-20200622_003555.log.json) |
+| EncNet | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 77.44 |         78.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/encnet/encnet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_80k_cityscapes/encnet_r50-d8_769x769_80k_cityscapes_20200622_003554-55096dcb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_80k_cityscapes/encnet_r50-d8_769x769_80k_cityscapes-20200622_003554.log.json)         |
+| EncNet | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 76.10 |         76.97 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/encnet/encnet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_80k_cityscapes/encnet_r101-d8_769x769_80k_cityscapes_20200622_003555-470ef79d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_80k_cityscapes/encnet_r101-d8_769x769_80k_cityscapes-20200622_003555.log.json)     |
 
 ### ADE20K
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| EncNet | R-50-D8  | 512x512   |   80000 | 10.1     | 22.81          | V100   | 39.53 |         41.17 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_80k_ade20k/encnet_r50-d8_512x512_80k_ade20k_20200622_042412-44b46b04.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_80k_ade20k/encnet_r50-d8_512x512_80k_ade20k-20200622_042412.log.json)         |
-| EncNet | R-101-D8 | 512x512   |   80000 | 13.6     | 14.87          | V100   | 42.11 |         43.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_80k_ade20k/encnet_r101-d8_512x512_80k_ade20k_20200622_101128-dd35e237.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_80k_ade20k/encnet_r101-d8_512x512_80k_ade20k-20200622_101128.log.json)     |
-| EncNet | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 40.10 |         41.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_160k_ade20k/encnet_r50-d8_512x512_160k_ade20k_20200622_101059-b2db95e0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_160k_ade20k/encnet_r50-d8_512x512_160k_ade20k-20200622_101059.log.json)     |
-| EncNet | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 42.61 |         44.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet/encnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_160k_ade20k/encnet_r101-d8_512x512_160k_ade20k_20200622_073348-7989641f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_160k_ade20k/encnet_r101-d8_512x512_160k_ade20k-20200622_073348.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| EncNet | R-50-D8  | 512x512   |   80000 | 10.1     | 22.81          | V100   | 39.53 |         41.17 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/encnet/encnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_80k_ade20k/encnet_r50-d8_512x512_80k_ade20k_20200622_042412-44b46b04.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_80k_ade20k/encnet_r50-d8_512x512_80k_ade20k-20200622_042412.log.json)         |
+| EncNet | R-101-D8 | 512x512   |   80000 | 13.6     | 14.87          | V100   | 42.11 |         43.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/encnet/encnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_80k_ade20k/encnet_r101-d8_512x512_80k_ade20k_20200622_101128-dd35e237.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_80k_ade20k/encnet_r101-d8_512x512_80k_ade20k-20200622_101128.log.json)     |
+| EncNet | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 40.10 |         41.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/encnet/encnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_160k_ade20k/encnet_r50-d8_512x512_160k_ade20k_20200622_101059-b2db95e0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_160k_ade20k/encnet_r50-d8_512x512_160k_ade20k-20200622_101059.log.json)     |
+| EncNet | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 42.61 |         44.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/encnet/encnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_160k_ade20k/encnet_r101-d8_512x512_160k_ade20k_20200622_073348-7989641f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_160k_ade20k/encnet_r101-d8_512x512_160k_ade20k-20200622_073348.log.json) |
 
 ## Citation
 
diff --git a/configs/erfnet/README.md b/configs/erfnet/README.md
index e29afc485d..55d71973a3 100644
--- a/configs/erfnet/README.md
+++ b/configs/erfnet/README.md
@@ -26,9 +26,9 @@ Semantic segmentation is a challenging task that addresses most of the perceptio
 
 ### Cityscapes
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                     |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ---: | ------------- | ------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| ERFNet | ERFNet   | 512x1024  |  160000 | 6.04     | 15.26          | V100   | 72.5 | 74.75         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/erfnet/erfnet_fcn_4xb4-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/erfnet/erfnet_fcn_4x4_512x1024_160k_cityscapes/erfnet_fcn_4x4_512x1024_160k_cityscapes_20220704_162145-dc90157a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/erfnet/erfnet_fcn_4x4_512x1024_160k_cityscapes/erfnet_fcn_4x4_512x1024_160k_cityscapes_20220704_162145.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                                     |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ---: | ------------- | --------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| ERFNet | ERFNet   | 512x1024  |  160000 | 6.04     | 15.26          | V100   | 72.5 | 74.75         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/erfnet/erfnet_fcn_4xb4-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/erfnet/erfnet_fcn_4x4_512x1024_160k_cityscapes/erfnet_fcn_4x4_512x1024_160k_cityscapes_20220704_162145-dc90157a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/erfnet/erfnet_fcn_4x4_512x1024_160k_cityscapes/erfnet_fcn_4x4_512x1024_160k_cityscapes_20220704_162145.log.json) |
 
 Note:
 
diff --git a/configs/fastfcn/README.md b/configs/fastfcn/README.md
index 0b26a33edd..48644e57e3 100644
--- a/configs/fastfcn/README.md
+++ b/configs/fastfcn/README.md
@@ -26,30 +26,30 @@ Modern approaches for semantic segmentation usually employ dilated convolutions
 
 ### Cityscapes
 
-| Method              | Backbone       | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                       | download                                                                                                                                                                                                                                                                                                                                                                                                           |
-| ------------------- | -------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| FastFCN + DeepLabV3 | R-50-D32       | 512x1024  |   80000 | 5.67     | 2.64           | V100   | 79.12 | 80.58         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes_20210928_053722-5d1a2648.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes_20210928_053722.log.json)                 |
-| FastFCN + DeepLabV3 | R-50-D32 (4x4) | 512x1024  |   80000 | 9.79     | -              | V100   | 79.52 | 80.91         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357-72220849.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357.log.json) |
-| FastFCN + PSPNet    | R-50-D32       | 512x1024  |   80000 | 5.67     | 4.40           | V100   | 79.26 | 80.86         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes_20210928_053722-57749bed.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes_20210928_053722.log.json)                     |
-| FastFCN + PSPNet    | R-50-D32 (4x4) | 512x1024  |   80000 | 9.94     | -              | V100   | 78.76 | 80.03         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841-77e87b0a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841.log.json)     |
-| FastFCN + EncNet    | R-50-D32       | 512x1024  |   80000 | 8.15     | 4.77           | V100   | 77.97 | 79.92         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes_20210928_030036-78da5046.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes_20210928_030036.log.json)                     |
-| FastFCN + EncNet    | R-50-D32 (4x4) | 512x1024  |   80000 | 15.45    | -              | V100   |  78.6 | 80.25         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217-e1eb6dbb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217.log.json)     |
+| Method              | Backbone       | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                    | download                                                                                                                                                                                                                                                                                                                                                                                                           |
+| ------------------- | -------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| FastFCN + DeepLabV3 | R-50-D32       | 512x1024  |   80000 | 5.67     | 2.64           | V100   | 79.12 | 80.58         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes_20210928_053722-5d1a2648.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes_20210928_053722.log.json)                 |
+| FastFCN + DeepLabV3 | R-50-D32 (4x4) | 512x1024  |   80000 | 9.79     | -              | V100   | 79.52 | 80.91         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357-72220849.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357.log.json) |
+| FastFCN + PSPNet    | R-50-D32       | 512x1024  |   80000 | 5.67     | 4.40           | V100   | 79.26 | 80.86         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes_20210928_053722-57749bed.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes_20210928_053722.log.json)                     |
+| FastFCN + PSPNet    | R-50-D32 (4x4) | 512x1024  |   80000 | 9.94     | -              | V100   | 78.76 | 80.03         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841-77e87b0a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841.log.json)     |
+| FastFCN + EncNet    | R-50-D32       | 512x1024  |   80000 | 8.15     | 4.77           | V100   | 77.97 | 79.92         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes_20210928_030036-78da5046.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes_20210928_030036.log.json)                     |
+| FastFCN + EncNet    | R-50-D32 (4x4) | 512x1024  |   80000 | 15.45    | -              | V100   |  78.6 | 80.25         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217-e1eb6dbb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217.log.json)     |
 
 ### ADE20K
 
-| Method              | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                   | download                                                                                                                                                                                                                                                                                                                                                                           |
-| ------------------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FastFCN + DeepLabV3 | R-50-D32 | 512x1024  |   80000 | 8.46     | 12.06          | V100   | 41.88 | 42.91         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k_20211013_190619-3aa40f2d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k_20211013_190619.log.json)     |
-| FastFCN + DeepLabV3 | R-50-D32 | 512x1024  |  160000 | -        | -              | V100   | 43.58 | 44.92         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k_20211008_152246-27036aee.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k_20211008_152246.log.json) |
-| FastFCN + PSPNet    | R-50-D32 | 512x1024  |   80000 | 8.02     | 19.21          | V100   | 41.40 | 42.12         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k_20210930_225137-993d07c8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k_20210930_225137.log.json)         |
-| FastFCN + PSPNet    | R-50-D32 | 512x1024  |  160000 | -        | -              | V100   | 42.63 | 43.71         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k_20211008_105455-e8f5a2fd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k_20211008_105455.log.json)     |
-| FastFCN + EncNet    | R-50-D32 | 512x1024  |   80000 | 9.67     | 17.23          | V100   | 40.88 | 42.36         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k_20210930_225214-65aef6dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k_20210930_225214.log.json)         |
-| FastFCN + EncNet    | R-50-D32 | 512x1024  |  160000 | -        | -              | V100   | 42.50 | 44.21         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k_20211008_105456-d875ce3c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k_20211008_105456.log.json)     |
+| Method              | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                | download                                                                                                                                                                                                                                                                                                                                                                           |
+| ------------------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FastFCN + DeepLabV3 | R-50-D32 | 512x1024  |   80000 | 8.46     | 12.06          | V100   | 41.88 | 42.91         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k_20211013_190619-3aa40f2d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k_20211013_190619.log.json)     |
+| FastFCN + DeepLabV3 | R-50-D32 | 512x1024  |  160000 | -        | -              | V100   | 43.58 | 44.92         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k_20211008_152246-27036aee.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k_20211008_152246.log.json) |
+| FastFCN + PSPNet    | R-50-D32 | 512x1024  |   80000 | 8.02     | 19.21          | V100   | 41.40 | 42.12         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k_20210930_225137-993d07c8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k_20210930_225137.log.json)         |
+| FastFCN + PSPNet    | R-50-D32 | 512x1024  |  160000 | -        | -              | V100   | 42.63 | 43.71         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k_20211008_105455-e8f5a2fd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k_20211008_105455.log.json)     |
+| FastFCN + EncNet    | R-50-D32 | 512x1024  |   80000 | 9.67     | 17.23          | V100   | 40.88 | 42.36         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k_20210930_225214-65aef6dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k_20210930_225214.log.json)         |
+| FastFCN + EncNet    | R-50-D32 | 512x1024  |  160000 | -        | -              | V100   | 42.50 | 44.21         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k_20211008_105456-d875ce3c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k_20211008_105456.log.json)     |
 
 Note:
 
 - `4x4` means 4 GPUs with 4 samples per GPU in training, default setting is 4 GPUs with 2 samples per GPU in training.
-- Results of [DeepLabV3 (mIoU: 79.32)](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3), [PSPNet (mIoU: 78.55)](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet) and [ENCNet (mIoU: 77.94)](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/encnet) can be found in each original repository.
+- Results of [DeepLabV3 (mIoU: 79.32)](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3), [PSPNet (mIoU: 78.55)](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet) and [ENCNet (mIoU: 77.94)](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/encnet) can be found in each original repository.
 
 ## Citation
 
diff --git a/configs/fastscnn/README.md b/configs/fastscnn/README.md
index ea3449fd2c..6be981462a 100644
--- a/configs/fastscnn/README.md
+++ b/configs/fastscnn/README.md
@@ -26,9 +26,9 @@ The encoder-decoder framework is state-of-the-art for offline semantic image seg
 
 ### Cityscapes
 
-| Method   | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                               |
-| -------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| FastSCNN | FastSCNN | 512x1024  |  160000 | 3.3      | 56.45          | V100   | 70.96 | 72.65         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastscnn/fast_scnn_8xb4-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_lr0.12_8x4_160k_cityscapes/fast_scnn_lr0.12_8x4_160k_cityscapes_20210630_164853-0cec9937.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_lr0.12_8x4_160k_cityscapes/fast_scnn_lr0.12_8x4_160k_cityscapes_20210630_164853.log.json) |
+| Method   | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                                               |
+| -------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| FastSCNN | FastSCNN | 512x1024  |  160000 | 3.3      | 56.45          | V100   | 70.96 | 72.65         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastscnn/fast_scnn_8xb4-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_lr0.12_8x4_160k_cityscapes/fast_scnn_lr0.12_8x4_160k_cityscapes_20210630_164853-0cec9937.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_lr0.12_8x4_160k_cityscapes/fast_scnn_lr0.12_8x4_160k_cityscapes_20210630_164853.log.json) |
 
 ## Citation
 
diff --git a/configs/fcn/README.md b/configs/fcn/README.md
index 6134933710..cf7379ff3d 100644
--- a/configs/fcn/README.md
+++ b/configs/fcn/README.md
@@ -26,69 +26,69 @@ Convolutional networks are powerful visual models that yield hierarchies of feat
 
 ### Cityscapes
 
-| Method     | Backbone   | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device   |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                   |
-| ---------- | ---------- | --------- | ------: | -------- | -------------- | -------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN        | R-50-D8    | 512x1024  |   40000 | 5.7      | 4.17           | V100     | 72.25 |         73.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_40k_cityscapes/fcn_r50-d8_512x1024_40k_cityscapes_20200604_192608-efe53f0d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_40k_cityscapes/fcn_r50-d8_512x1024_40k_cityscapes_20200604_192608.log.json)                         |
-| FCN        | R-101-D8   | 512x1024  |   40000 | 9.2      | 2.66           | V100     | 75.45 |         76.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb2-40k_cityscapes-512x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_40k_cityscapes/fcn_r101-d8_512x1024_40k_cityscapes_20200604_181852-a883d3a1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_40k_cityscapes/fcn_r101-d8_512x1024_40k_cityscapes_20200604_181852.log.json)                     |
-| FCN        | R-50-D8    | 769x769   |   40000 | 6.5      | 1.80           | V100     | 71.47 |         72.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-769x769.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_40k_cityscapes/fcn_r50-d8_769x769_40k_cityscapes_20200606_113104-977b5d02.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_40k_cityscapes/fcn_r50-d8_769x769_40k_cityscapes_20200606_113104.log.json)                             |
-| FCN        | R-101-D8   | 769x769   |   40000 | 10.4     | 1.19           | V100     | 73.93 |         75.14 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb2-40k_cityscapes-769x769.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_40k_cityscapes/fcn_r101-d8_769x769_40k_cityscapes_20200606_113208-7d4ab69c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_40k_cityscapes/fcn_r101-d8_769x769_40k_cityscapes_20200606_113208.log.json)                         |
-| FCN        | R-18-D8    | 512x1024  |   80000 | 1.7      | 14.65          | V100     | 71.11 |         72.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_512x1024_80k_cityscapes/fcn_r18-d8_512x1024_80k_cityscapes_20201225_021327-6c50f8b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_512x1024_80k_cityscapes/fcn_r18-d8_512x1024_80k_cityscapes-20201225_021327.log.json)                         |
-| FCN        | R-50-D8    | 512x1024  |   80000 | -        |                | V100     | 73.61 |         74.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb2-80k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_80k_cityscapes/fcn_r50-d8_512x1024_80k_cityscapes_20200606_113019-03aa804d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_80k_cityscapes/fcn_r50-d8_512x1024_80k_cityscapes_20200606_113019.log.json)                         |
-| FCN        | R-101-D8   | 512x1024  |   80000 | -        | -              | V100     | 75.13 |         75.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb2-80k_cityscapes-512x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_80k_cityscapes/fcn_r101-d8_512x1024_80k_cityscapes_20200606_113038-3fb937eb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_80k_cityscapes/fcn_r101-d8_512x1024_80k_cityscapes_20200606_113038.log.json)                     |
-| FCN (FP16) | R-101-D8   | 512x1024  |   80000 | 5.37     | 8.64           | V100     | 76.80 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_fp16_512x1024_80k_cityscapes/fcn_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230921-fb13e883.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_fp16_512x1024_80k_cityscapes/fcn_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230921.log.json) |
-| FCN        | R-18-D8    | 769x769   |   80000 | 1.9      | 6.40           | V100     | 70.80 |         73.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-769x769.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_769x769_80k_cityscapes/fcn_r18-d8_769x769_80k_cityscapes_20201225_021451-9739d1b8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_769x769_80k_cityscapes/fcn_r18-d8_769x769_80k_cityscapes-20201225_021451.log.json)                             |
-| FCN        | R-50-D8    | 769x769   |   80000 | -        | -              | V100     | 72.64 |         73.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb2-80k_cityscapes-769x769.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_80k_cityscapes/fcn_r50-d8_769x769_80k_cityscapes_20200606_195749-f5caeabc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_80k_cityscapes/fcn_r50-d8_769x769_80k_cityscapes_20200606_195749.log.json)                             |
-| FCN        | R-101-D8   | 769x769   |   80000 | -        | -              | V100     | 75.52 |         76.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb2-80k_cityscapes-769x769.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_80k_cityscapes/fcn_r101-d8_769x769_80k_cityscapes_20200606_214354-45cbac68.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_80k_cityscapes/fcn_r101-d8_769x769_80k_cityscapes_20200606_214354.log.json)                         |
-| FCN        | R-18b-D8   | 512x1024  |   80000 | 1.6      | 16.74          | V100     | 70.24 |         72.77 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r18b-d8_4xb2-80k_cityscapes-512x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_512x1024_80k_cityscapes/fcn_r18b-d8_512x1024_80k_cityscapes_20201225_230143-92c0f445.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_512x1024_80k_cityscapes/fcn_r18b-d8_512x1024_80k_cityscapes-20201225_230143.log.json)                     |
-| FCN        | R-50b-D8   | 512x1024  |   80000 | 5.6      | 4.20           | V100     | 75.65 |         77.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50b-d8_4xb2-80k_cityscapes-512x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_512x1024_80k_cityscapes/fcn_r50b-d8_512x1024_80k_cityscapes_20201225_094221-82957416.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_512x1024_80k_cityscapes/fcn_r50b-d8_512x1024_80k_cityscapes-20201225_094221.log.json)                     |
-| FCN        | R-101b-D8  | 512x1024  |   80000 | 9.1      | 2.73           | V100     | 77.37 |         78.77 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101b-d8_4xb2-80k_cityscapes-512x1024.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_512x1024_80k_cityscapes/fcn_r101b-d8_512x1024_80k_cityscapes_20201226_160213-4543858f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_512x1024_80k_cityscapes/fcn_r101b-d8_512x1024_80k_cityscapes-20201226_160213.log.json)                 |
-| FCN        | R-18b-D8   | 769x769   |   80000 | 1.7      | 6.70           | V100     | 69.66 |         72.07 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r18b-d8_4xb2-80k_cityscapes-769x769.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_769x769_80k_cityscapes/fcn_r18b-d8_769x769_80k_cityscapes_20201226_004430-32d504e5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_769x769_80k_cityscapes/fcn_r18b-d8_769x769_80k_cityscapes-20201226_004430.log.json)                         |
-| FCN        | R-50b-D8   | 769x769   |   80000 | 6.3      | 1.82           | V100     | 73.83 |         76.60 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50b-d8_4xb2-80k_cityscapes-769x769.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_769x769_80k_cityscapes/fcn_r50b-d8_769x769_80k_cityscapes_20201225_094223-94552d38.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_769x769_80k_cityscapes/fcn_r50b-d8_769x769_80k_cityscapes-20201225_094223.log.json)                         |
-| FCN        | R-101b-D8  | 769x769   |   80000 | 10.3     | 1.15           | V100     | 77.02 |         78.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101b-d8_4xb2-80k_cityscapes-769x769.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_769x769_80k_cityscapes/fcn_r101b-d8_769x769_80k_cityscapes_20201226_170012-82be37e2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_769x769_80k_cityscapes/fcn_r101b-d8_769x769_80k_cityscapes-20201226_170012.log.json)                     |
-| FCN (D6)   | R-50-D16   | 512x1024  |   40000 | 3.4      | 10.22          | TITAN Xp | 77.06 |         78.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r50-d16_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes_20210305_130133-98d5d1bc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes-20210305_130133.log.json)         |
-| FCN (D6)   | R-50-D16   | 512x1024  |   80000 | -        | 10.35          | TITAN Xp | 77.27 |         78.88 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r50-d16_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_80k_cityscapes_20210306_115604-133c292f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_80k_cityscapes-20210306_115604.log.json)         |
-| FCN (D6)   | R-50-D16   | 769x769   |   40000 | 3.7      | 4.17           | TITAN Xp | 76.82 |         78.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r50-d16_4xb2-40k_cityscapes-769x769.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes_20210305_185744-1aab18ed.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes-20210305_185744.log.json)             |
-| FCN (D6)   | R-50-D16   | 769x769   |   80000 | -        | 4.15           | TITAN Xp | 77.04 |         78.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r50-d16_4xb2-80k_cityscapes-769x769.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes_20210305_200413-109d88eb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes-20210305_200413.log.json)             |
-| FCN (D6)   | R-101-D16  | 512x1024  |   40000 | 4.5      | 8.04           | TITAN Xp | 77.36 |         79.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r101-d16_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes_20210305_130337-9cf2b450.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes-20210305_130337.log.json)     |
-| FCN (D6)   | R-101-D16  | 512x1024  |   80000 | -        | 8.26           | TITAN Xp | 78.46 |         80.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r101-d16_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes_20210308_102747-cb336445.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes-20210308_102747.log.json)     |
-| FCN (D6)   | R-101-D16  | 769x769   |   40000 | 5.0      | 3.12           | TITAN Xp | 77.28 |         78.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r101-d16_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes_20210308_102453-60b114e9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes-20210308_102453.log.json)         |
-| FCN (D6)   | R-101-D16  | 769x769   |   80000 | -        | 3.21           | TITAN Xp | 78.06 |         79.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r101-d16_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes_20210306_120016-e33adc4f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes-20210306_120016.log.json)         |
-| FCN (D6)   | R-50b-D16  | 512x1024  |   80000 | 3.2      | 10.16          | TITAN Xp | 76.99 |         79.03 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r50b-d16_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_512x1024_80k_cityscapes/fcn_d6_r50b-d16_512x1024_80k_cityscapes_20210311_125550-6a0b62e9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_512x1024_80k_cityscapes/fcn_d6_r50b_d16_512x1024_80k_cityscapes-20210311_125550.log.json)     |
-| FCN (D6)   | R-50b-D16  | 769x769   |   80000 | 3.6      | 4.17           | TITAN Xp | 76.86 |         78.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r50b-d16_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_769x769_80k_cityscapes/fcn_d6_r50b-d16_769x769_80k_cityscapes_20210311_131012-d665f231.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_769x769_80k_cityscapes/fcn_d6_r50b_d16_769x769_80k_cityscapes-20210311_131012.log.json)         |
-| FCN (D6)   | R-101b-D16 | 512x1024  |   80000 | 4.3      | 8.46           | TITAN Xp | 77.72 |         79.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r101b-d16_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_512x1024_80k_cityscapes/fcn_d6_r101b-d16_512x1024_80k_cityscapes_20210311_144305-3f2eb5b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_512x1024_80k_cityscapes/fcn_d6_r101b_d16_512x1024_80k_cityscapes-20210311_144305.log.json) |
-| FCN (D6)   | R-101b-D16 | 769x769   |   80000 | 4.8      | 3.32           | TITAN Xp | 77.34 |         78.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn-d6_r101b-d16_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_769x769_80k_cityscapes/fcn_d6_r101b-d16_769x769_80k_cityscapes_20210311_154527-c4d8bfbc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_769x769_80k_cityscapes/fcn_d6_r101b_d16_769x769_80k_cityscapes-20210311_154527.log.json)     |
+| Method     | Backbone   | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device   |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                   |
+| ---------- | ---------- | --------- | ------: | -------- | -------------- | -------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN        | R-50-D8    | 512x1024  |   40000 | 5.7      | 4.17           | V100     | 72.25 |         73.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_40k_cityscapes/fcn_r50-d8_512x1024_40k_cityscapes_20200604_192608-efe53f0d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_40k_cityscapes/fcn_r50-d8_512x1024_40k_cityscapes_20200604_192608.log.json)                         |
+| FCN        | R-101-D8   | 512x1024  |   40000 | 9.2      | 2.66           | V100     | 75.45 |         76.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb2-40k_cityscapes-512x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_40k_cityscapes/fcn_r101-d8_512x1024_40k_cityscapes_20200604_181852-a883d3a1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_40k_cityscapes/fcn_r101-d8_512x1024_40k_cityscapes_20200604_181852.log.json)                     |
+| FCN        | R-50-D8    | 769x769   |   40000 | 6.5      | 1.80           | V100     | 71.47 |         72.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-769x769.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_40k_cityscapes/fcn_r50-d8_769x769_40k_cityscapes_20200606_113104-977b5d02.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_40k_cityscapes/fcn_r50-d8_769x769_40k_cityscapes_20200606_113104.log.json)                             |
+| FCN        | R-101-D8   | 769x769   |   40000 | 10.4     | 1.19           | V100     | 73.93 |         75.14 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb2-40k_cityscapes-769x769.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_40k_cityscapes/fcn_r101-d8_769x769_40k_cityscapes_20200606_113208-7d4ab69c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_40k_cityscapes/fcn_r101-d8_769x769_40k_cityscapes_20200606_113208.log.json)                         |
+| FCN        | R-18-D8    | 512x1024  |   80000 | 1.7      | 14.65          | V100     | 71.11 |         72.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_512x1024_80k_cityscapes/fcn_r18-d8_512x1024_80k_cityscapes_20201225_021327-6c50f8b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_512x1024_80k_cityscapes/fcn_r18-d8_512x1024_80k_cityscapes-20201225_021327.log.json)                         |
+| FCN        | R-50-D8    | 512x1024  |   80000 | -        |                | V100     | 73.61 |         74.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb2-80k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_80k_cityscapes/fcn_r50-d8_512x1024_80k_cityscapes_20200606_113019-03aa804d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_80k_cityscapes/fcn_r50-d8_512x1024_80k_cityscapes_20200606_113019.log.json)                         |
+| FCN        | R-101-D8   | 512x1024  |   80000 | -        | -              | V100     | 75.13 |         75.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb2-80k_cityscapes-512x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_80k_cityscapes/fcn_r101-d8_512x1024_80k_cityscapes_20200606_113038-3fb937eb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_80k_cityscapes/fcn_r101-d8_512x1024_80k_cityscapes_20200606_113038.log.json)                     |
+| FCN (FP16) | R-101-D8   | 512x1024  |   80000 | 5.37     | 8.64           | V100     | 76.80 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_fp16_512x1024_80k_cityscapes/fcn_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230921-fb13e883.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_fp16_512x1024_80k_cityscapes/fcn_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230921.log.json) |
+| FCN        | R-18-D8    | 769x769   |   80000 | 1.9      | 6.40           | V100     | 70.80 |         73.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-769x769.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_769x769_80k_cityscapes/fcn_r18-d8_769x769_80k_cityscapes_20201225_021451-9739d1b8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_769x769_80k_cityscapes/fcn_r18-d8_769x769_80k_cityscapes-20201225_021451.log.json)                             |
+| FCN        | R-50-D8    | 769x769   |   80000 | -        | -              | V100     | 72.64 |         73.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb2-80k_cityscapes-769x769.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_80k_cityscapes/fcn_r50-d8_769x769_80k_cityscapes_20200606_195749-f5caeabc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_80k_cityscapes/fcn_r50-d8_769x769_80k_cityscapes_20200606_195749.log.json)                             |
+| FCN        | R-101-D8   | 769x769   |   80000 | -        | -              | V100     | 75.52 |         76.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb2-80k_cityscapes-769x769.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_80k_cityscapes/fcn_r101-d8_769x769_80k_cityscapes_20200606_214354-45cbac68.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_80k_cityscapes/fcn_r101-d8_769x769_80k_cityscapes_20200606_214354.log.json)                         |
+| FCN        | R-18b-D8   | 512x1024  |   80000 | 1.6      | 16.74          | V100     | 70.24 |         72.77 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r18b-d8_4xb2-80k_cityscapes-512x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_512x1024_80k_cityscapes/fcn_r18b-d8_512x1024_80k_cityscapes_20201225_230143-92c0f445.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_512x1024_80k_cityscapes/fcn_r18b-d8_512x1024_80k_cityscapes-20201225_230143.log.json)                     |
+| FCN        | R-50b-D8   | 512x1024  |   80000 | 5.6      | 4.20           | V100     | 75.65 |         77.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50b-d8_4xb2-80k_cityscapes-512x1024.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_512x1024_80k_cityscapes/fcn_r50b-d8_512x1024_80k_cityscapes_20201225_094221-82957416.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_512x1024_80k_cityscapes/fcn_r50b-d8_512x1024_80k_cityscapes-20201225_094221.log.json)                     |
+| FCN        | R-101b-D8  | 512x1024  |   80000 | 9.1      | 2.73           | V100     | 77.37 |         78.77 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101b-d8_4xb2-80k_cityscapes-512x1024.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_512x1024_80k_cityscapes/fcn_r101b-d8_512x1024_80k_cityscapes_20201226_160213-4543858f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_512x1024_80k_cityscapes/fcn_r101b-d8_512x1024_80k_cityscapes-20201226_160213.log.json)                 |
+| FCN        | R-18b-D8   | 769x769   |   80000 | 1.7      | 6.70           | V100     | 69.66 |         72.07 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r18b-d8_4xb2-80k_cityscapes-769x769.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_769x769_80k_cityscapes/fcn_r18b-d8_769x769_80k_cityscapes_20201226_004430-32d504e5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_769x769_80k_cityscapes/fcn_r18b-d8_769x769_80k_cityscapes-20201226_004430.log.json)                         |
+| FCN        | R-50b-D8   | 769x769   |   80000 | 6.3      | 1.82           | V100     | 73.83 |         76.60 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50b-d8_4xb2-80k_cityscapes-769x769.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_769x769_80k_cityscapes/fcn_r50b-d8_769x769_80k_cityscapes_20201225_094223-94552d38.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_769x769_80k_cityscapes/fcn_r50b-d8_769x769_80k_cityscapes-20201225_094223.log.json)                         |
+| FCN        | R-101b-D8  | 769x769   |   80000 | 10.3     | 1.15           | V100     | 77.02 |         78.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101b-d8_4xb2-80k_cityscapes-769x769.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_769x769_80k_cityscapes/fcn_r101b-d8_769x769_80k_cityscapes_20201226_170012-82be37e2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_769x769_80k_cityscapes/fcn_r101b-d8_769x769_80k_cityscapes-20201226_170012.log.json)                     |
+| FCN (D6)   | R-50-D16   | 512x1024  |   40000 | 3.4      | 10.22          | TITAN Xp | 77.06 |         78.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r50-d16_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes_20210305_130133-98d5d1bc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes-20210305_130133.log.json)         |
+| FCN (D6)   | R-50-D16   | 512x1024  |   80000 | -        | 10.35          | TITAN Xp | 77.27 |         78.88 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r50-d16_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_80k_cityscapes_20210306_115604-133c292f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_80k_cityscapes-20210306_115604.log.json)         |
+| FCN (D6)   | R-50-D16   | 769x769   |   40000 | 3.7      | 4.17           | TITAN Xp | 76.82 |         78.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r50-d16_4xb2-40k_cityscapes-769x769.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes_20210305_185744-1aab18ed.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes-20210305_185744.log.json)             |
+| FCN (D6)   | R-50-D16   | 769x769   |   80000 | -        | 4.15           | TITAN Xp | 77.04 |         78.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r50-d16_4xb2-80k_cityscapes-769x769.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes_20210305_200413-109d88eb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes-20210305_200413.log.json)             |
+| FCN (D6)   | R-101-D16  | 512x1024  |   40000 | 4.5      | 8.04           | TITAN Xp | 77.36 |         79.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r101-d16_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes_20210305_130337-9cf2b450.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes-20210305_130337.log.json)     |
+| FCN (D6)   | R-101-D16  | 512x1024  |   80000 | -        | 8.26           | TITAN Xp | 78.46 |         80.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r101-d16_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes_20210308_102747-cb336445.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes-20210308_102747.log.json)     |
+| FCN (D6)   | R-101-D16  | 769x769   |   40000 | 5.0      | 3.12           | TITAN Xp | 77.28 |         78.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r101-d16_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes_20210308_102453-60b114e9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes-20210308_102453.log.json)         |
+| FCN (D6)   | R-101-D16  | 769x769   |   80000 | -        | 3.21           | TITAN Xp | 78.06 |         79.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r101-d16_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes_20210306_120016-e33adc4f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes-20210306_120016.log.json)         |
+| FCN (D6)   | R-50b-D16  | 512x1024  |   80000 | 3.2      | 10.16          | TITAN Xp | 76.99 |         79.03 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r50b-d16_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_512x1024_80k_cityscapes/fcn_d6_r50b-d16_512x1024_80k_cityscapes_20210311_125550-6a0b62e9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_512x1024_80k_cityscapes/fcn_d6_r50b_d16_512x1024_80k_cityscapes-20210311_125550.log.json)     |
+| FCN (D6)   | R-50b-D16  | 769x769   |   80000 | 3.6      | 4.17           | TITAN Xp | 76.86 |         78.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r50b-d16_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_769x769_80k_cityscapes/fcn_d6_r50b-d16_769x769_80k_cityscapes_20210311_131012-d665f231.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_769x769_80k_cityscapes/fcn_d6_r50b_d16_769x769_80k_cityscapes-20210311_131012.log.json)         |
+| FCN (D6)   | R-101b-D16 | 512x1024  |   80000 | 4.3      | 8.46           | TITAN Xp | 77.72 |         79.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r101b-d16_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_512x1024_80k_cityscapes/fcn_d6_r101b-d16_512x1024_80k_cityscapes_20210311_144305-3f2eb5b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_512x1024_80k_cityscapes/fcn_d6_r101b_d16_512x1024_80k_cityscapes-20210311_144305.log.json) |
+| FCN (D6)   | R-101b-D16 | 769x769   |   80000 | 4.8      | 3.32           | TITAN Xp | 77.34 |         78.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r101b-d16_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_769x769_80k_cityscapes/fcn_d6_r101b-d16_769x769_80k_cityscapes_20210311_154527-c4d8bfbc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_769x769_80k_cityscapes/fcn_d6_r101b_d16_769x769_80k_cityscapes-20210311_154527.log.json)     |
 
 ### ADE20K
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                                               |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN    | R-50-D8  | 512x512   |   80000 | 8.5      | 23.49          | V100   | 35.94 |         37.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_80k_ade20k/fcn_r50-d8_512x512_80k_ade20k_20200614_144016-f8ac5082.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_80k_ade20k/fcn_r50-d8_512x512_80k_ade20k_20200614_144016.log.json)         |
-| FCN    | R-101-D8 | 512x512   |   80000 | 12       | 14.78          | V100   | 39.61 |         40.83 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-80k_ade20k-512x512.pyy) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_80k_ade20k/fcn_r101-d8_512x512_80k_ade20k_20200615_014143-bc1809f7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_80k_ade20k/fcn_r101-d8_512x512_80k_ade20k_20200615_014143.log.json)     |
-| FCN    | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 36.10 |         38.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_160k_ade20k/fcn_r50-d8_512x512_160k_ade20k_20200615_100713-4edbc3b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_160k_ade20k/fcn_r50-d8_512x512_160k_ade20k_20200615_100713.log.json)     |
-| FCN    | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 39.91 |         41.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_160k_ade20k/fcn_r101-d8_512x512_160k_ade20k_20200615_105816-fd192bd5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_160k_ade20k/fcn_r101-d8_512x512_160k_ade20k_20200615_105816.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                               | download                                                                                                                                                                                                                                                                                                               |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN    | R-50-D8  | 512x512   |   80000 | 8.5      | 23.49          | V100   | 35.94 |         37.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_80k_ade20k/fcn_r50-d8_512x512_80k_ade20k_20200614_144016-f8ac5082.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_80k_ade20k/fcn_r50-d8_512x512_80k_ade20k_20200614_144016.log.json)         |
+| FCN    | R-101-D8 | 512x512   |   80000 | 12       | 14.78          | V100   | 39.61 |         40.83 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb4-80k_ade20k-512x512.pyy) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_80k_ade20k/fcn_r101-d8_512x512_80k_ade20k_20200615_014143-bc1809f7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_80k_ade20k/fcn_r101-d8_512x512_80k_ade20k_20200615_014143.log.json)     |
+| FCN    | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 36.10 |         38.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_160k_ade20k/fcn_r50-d8_512x512_160k_ade20k_20200615_100713-4edbc3b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_160k_ade20k/fcn_r50-d8_512x512_160k_ade20k_20200615_100713.log.json)     |
+| FCN    | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 39.91 |         41.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_160k_ade20k/fcn_r101-d8_512x512_160k_ade20k_20200615_105816-fd192bd5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_160k_ade20k/fcn_r101-d8_512x512_160k_ade20k_20200615_105816.log.json) |
 
 ### Pascal VOC 2012 + Aug
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                   | download                                                                                                                                                                                                                                                                                                                   |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN    | R-50-D8  | 512x512   |   20000 | 5.7      | 23.28          | V100   | 67.08 |         69.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_20k_voc12aug/fcn_r50-d8_512x512_20k_voc12aug_20200617_010715-52dc5306.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_20k_voc12aug/fcn_r50-d8_512x512_20k_voc12aug_20200617_010715.log.json)     |
-| FCN    | R-101-D8 | 512x512   |   20000 | 9.2      | 14.81          | V100   | 71.16 |         73.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_20k_voc12aug/fcn_r101-d8_512x512_20k_voc12aug_20200617_010842-0bb4e798.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_20k_voc12aug/fcn_r101-d8_512x512_20k_voc12aug_20200617_010842.log.json) |
-| FCN    | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 66.97 |         69.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_40k_voc12aug/fcn_r50-d8_512x512_40k_voc12aug_20200613_161222-5e2dbf40.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_40k_voc12aug/fcn_r50-d8_512x512_40k_voc12aug_20200613_161222.log.json)     |
-| FCN    | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 69.91 |         72.38 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_40k_voc12aug/fcn_r101-d8_512x512_40k_voc12aug_20200613_161240-4c8bcefd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_40k_voc12aug/fcn_r101-d8_512x512_40k_voc12aug_20200613_161240.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                | download                                                                                                                                                                                                                                                                                                                   |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN    | R-50-D8  | 512x512   |   20000 | 5.7      | 23.28          | V100   | 67.08 |         69.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_20k_voc12aug/fcn_r50-d8_512x512_20k_voc12aug_20200617_010715-52dc5306.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_20k_voc12aug/fcn_r50-d8_512x512_20k_voc12aug_20200617_010715.log.json)     |
+| FCN    | R-101-D8 | 512x512   |   20000 | 9.2      | 14.81          | V100   | 71.16 |         73.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_20k_voc12aug/fcn_r101-d8_512x512_20k_voc12aug_20200617_010842-0bb4e798.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_20k_voc12aug/fcn_r101-d8_512x512_20k_voc12aug_20200617_010842.log.json) |
+| FCN    | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 66.97 |         69.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_40k_voc12aug/fcn_r50-d8_512x512_40k_voc12aug_20200613_161222-5e2dbf40.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_40k_voc12aug/fcn_r50-d8_512x512_40k_voc12aug_20200613_161222.log.json)     |
+| FCN    | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 69.91 |         72.38 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_40k_voc12aug/fcn_r101-d8_512x512_40k_voc12aug_20200613_161240-4c8bcefd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_40k_voc12aug/fcn_r101-d8_512x512_40k_voc12aug_20200613_161240.log.json) |
 
 ### Pascal Context
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN    | R-101-D8 | 480x480   |   40000 | -        | 9.93           | V100   | 44.43 |         45.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context_20210421_154757-b5e97937.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context-20210421_154757.log.json) |
-| FCN    | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 44.13 |         45.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context_20210421_163310-4711813f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context-20210421_163310.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN    | R-101-D8 | 480x480   |   40000 | -        | 9.93           | V100   | 44.43 |         45.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context_20210421_154757-b5e97937.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context-20210421_154757.log.json) |
+| FCN    | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 44.13 |         45.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context_20210421_163310-4711813f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context-20210421_163310.log.json) |
 
 ### Pascal Context 59
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                       |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN    | R-101-D8 | 480x480   |   40000 | -        | -              | V100   | 48.42 |          50.4 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context_59/fcn_r101-d8_480x480_40k_pascal_context_59_20210415_230724-8cf83682.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context_59/fcn_r101-d8_480x480_40k_pascal_context_59-20210415_230724.log.json) |
-| FCN    | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 49.35 |         51.38 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r101-d8_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context_59/fcn_r101-d8_480x480_80k_pascal_context_59_20210416_110804-9a6f2c94.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context_59/fcn_r101-d8_480x480_80k_pascal_context_59-20210416_110804.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                       |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN    | R-101-D8 | 480x480   |   40000 | -        | -              | V100   | 48.42 |          50.4 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context_59/fcn_r101-d8_480x480_40k_pascal_context_59_20210415_230724-8cf83682.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context_59/fcn_r101-d8_480x480_40k_pascal_context_59-20210415_230724.log.json) |
+| FCN    | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 49.35 |         51.38 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context_59/fcn_r101-d8_480x480_80k_pascal_context_59_20210416_110804-9a6f2c94.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context_59/fcn_r101-d8_480x480_80k_pascal_context_59-20210416_110804.log.json) |
 
 Note:
 
diff --git a/configs/gcnet/README.md b/configs/gcnet/README.md
index 26a478808f..ba1a21e851 100644
--- a/configs/gcnet/README.md
+++ b/configs/gcnet/README.md
@@ -26,34 +26,34 @@ The Non-Local Network (NLNet) presents a pioneering approach for capturing long-
 
 ### Cityscapes
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| GCNet  | R-50-D8  | 512x1024  |   40000 | 5.8      | 3.93           | V100   | 77.69 |         78.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes/gcnet_r50-d8_512x1024_40k_cityscapes_20200618_074436-4b0fd17b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes/gcnet_r50-d8_512x1024_40k_cityscapes_20200618_074436.log.json)     |
-| GCNet  | R-101-D8 | 512x1024  |   40000 | 9.2      | 2.61           | V100   | 78.28 |         79.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes/gcnet_r101-d8_512x1024_40k_cityscapes_20200618_074436-5e62567f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes/gcnet_r101-d8_512x1024_40k_cityscapes_20200618_074436.log.json) |
-| GCNet  | R-50-D8  | 769x769   |   40000 | 6.5      | 1.67           | V100   | 78.12 |         80.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-769x769.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_40k_cityscapes/gcnet_r50-d8_769x769_40k_cityscapes_20200618_182814-a26f4471.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_40k_cityscapes/gcnet_r50-d8_769x769_40k_cityscapes_20200618_182814.log.json)         |
-| GCNet  | R-101-D8 | 769x769   |   40000 | 10.5     | 1.13           | V100   | 78.95 |         80.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_40k_cityscapes/gcnet_r101-d8_769x769_40k_cityscapes_20200619_092550-ca4f0a84.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_40k_cityscapes/gcnet_r101-d8_769x769_40k_cityscapes_20200619_092550.log.json)     |
-| GCNet  | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 78.48 |         80.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes/gcnet_r50-d8_512x1024_80k_cityscapes_20200618_074450-ef8f069b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes/gcnet_r50-d8_512x1024_80k_cityscapes_20200618_074450.log.json)     |
-| GCNet  | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 79.03 |         79.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb2-80k_cityscapes-512x1024.pyy) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes/gcnet_r101-d8_512x1024_80k_cityscapes_20200618_074450-778ebf69.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes/gcnet_r101-d8_512x1024_80k_cityscapes_20200618_074450.log.json) |
-| GCNet  | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 78.68 |         80.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb2-80k_cityscapes-769x769.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_80k_cityscapes/gcnet_r50-d8_769x769_80k_cityscapes_20200619_092516-4839565b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_80k_cityscapes/gcnet_r50-d8_769x769_80k_cityscapes_20200619_092516.log.json)         |
-| GCNet  | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 79.18 |         80.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_80k_cityscapes/gcnet_r101-d8_769x769_80k_cityscapes_20200619_092628-8e043423.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_80k_cityscapes/gcnet_r101-d8_769x769_80k_cityscapes_20200619_092628.log.json)     |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| GCNet  | R-50-D8  | 512x1024  |   40000 | 5.8      | 3.93           | V100   | 77.69 |         78.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes/gcnet_r50-d8_512x1024_40k_cityscapes_20200618_074436-4b0fd17b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes/gcnet_r50-d8_512x1024_40k_cityscapes_20200618_074436.log.json)     |
+| GCNet  | R-101-D8 | 512x1024  |   40000 | 9.2      | 2.61           | V100   | 78.28 |         79.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r101-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes/gcnet_r101-d8_512x1024_40k_cityscapes_20200618_074436-5e62567f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes/gcnet_r101-d8_512x1024_40k_cityscapes_20200618_074436.log.json) |
+| GCNet  | R-50-D8  | 769x769   |   40000 | 6.5      | 1.67           | V100   | 78.12 |         80.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-769x769.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_40k_cityscapes/gcnet_r50-d8_769x769_40k_cityscapes_20200618_182814-a26f4471.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_40k_cityscapes/gcnet_r50-d8_769x769_40k_cityscapes_20200618_182814.log.json)         |
+| GCNet  | R-101-D8 | 769x769   |   40000 | 10.5     | 1.13           | V100   | 78.95 |         80.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r101-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_40k_cityscapes/gcnet_r101-d8_769x769_40k_cityscapes_20200619_092550-ca4f0a84.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_40k_cityscapes/gcnet_r101-d8_769x769_40k_cityscapes_20200619_092550.log.json)     |
+| GCNet  | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 78.48 |         80.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes/gcnet_r50-d8_512x1024_80k_cityscapes_20200618_074450-ef8f069b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes/gcnet_r50-d8_512x1024_80k_cityscapes_20200618_074450.log.json)     |
+| GCNet  | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 79.03 |         79.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r101-d8_4xb2-80k_cityscapes-512x1024.pyy) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes/gcnet_r101-d8_512x1024_80k_cityscapes_20200618_074450-778ebf69.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes/gcnet_r101-d8_512x1024_80k_cityscapes_20200618_074450.log.json) |
+| GCNet  | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 78.68 |         80.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r50-d8_4xb2-80k_cityscapes-769x769.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_80k_cityscapes/gcnet_r50-d8_769x769_80k_cityscapes_20200619_092516-4839565b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_80k_cityscapes/gcnet_r50-d8_769x769_80k_cityscapes_20200619_092516.log.json)         |
+| GCNet  | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 79.18 |         80.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r101-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_80k_cityscapes/gcnet_r101-d8_769x769_80k_cityscapes_20200619_092628-8e043423.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_80k_cityscapes/gcnet_r101-d8_769x769_80k_cityscapes_20200619_092628.log.json)     |
 
 ### ADE20K
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| GCNet  | R-50-D8  | 512x512   |   80000 | 8.5      | 23.38          | V100   | 41.47 |         42.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_80k_ade20k/gcnet_r50-d8_512x512_80k_ade20k_20200614_185146-91a6da41.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_80k_ade20k/gcnet_r50-d8_512x512_80k_ade20k_20200614_185146.log.json)         |
-| GCNet  | R-101-D8 | 512x512   |   80000 | 12       | 15.20          | V100   | 42.82 |         44.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_80k_ade20k/gcnet_r101-d8_512x512_80k_ade20k_20200615_020811-c3fcb6dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_80k_ade20k/gcnet_r101-d8_512x512_80k_ade20k_20200615_020811.log.json)     |
-| GCNet  | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 42.37 |         43.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_160k_ade20k/gcnet_r50-d8_512x512_160k_ade20k_20200615_224122-d95f3e1f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_160k_ade20k/gcnet_r50-d8_512x512_160k_ade20k_20200615_224122.log.json)     |
-| GCNet  | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 43.69 |         45.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_160k_ade20k/gcnet_r101-d8_512x512_160k_ade20k_20200615_225406-615528d7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_160k_ade20k/gcnet_r101-d8_512x512_160k_ade20k_20200615_225406.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                   | download                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| GCNet  | R-50-D8  | 512x512   |   80000 | 8.5      | 23.38          | V100   | 41.47 |         42.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_80k_ade20k/gcnet_r50-d8_512x512_80k_ade20k_20200614_185146-91a6da41.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_80k_ade20k/gcnet_r50-d8_512x512_80k_ade20k_20200614_185146.log.json)         |
+| GCNet  | R-101-D8 | 512x512   |   80000 | 12       | 15.20          | V100   | 42.82 |         44.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_80k_ade20k/gcnet_r101-d8_512x512_80k_ade20k_20200615_020811-c3fcb6dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_80k_ade20k/gcnet_r101-d8_512x512_80k_ade20k_20200615_020811.log.json)     |
+| GCNet  | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 42.37 |         43.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_160k_ade20k/gcnet_r50-d8_512x512_160k_ade20k_20200615_224122-d95f3e1f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_160k_ade20k/gcnet_r50-d8_512x512_160k_ade20k_20200615_224122.log.json)     |
+| GCNet  | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 43.69 |         45.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_160k_ade20k/gcnet_r101-d8_512x512_160k_ade20k_20200615_225406-615528d7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_160k_ade20k/gcnet_r101-d8_512x512_160k_ade20k_20200615_225406.log.json) |
 
 ### Pascal VOC 2012 + Aug
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                               |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| GCNet  | R-50-D8  | 512x512   |   20000 | 5.8      | 23.35          | V100   | 76.42 |         77.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_20k_voc12aug/gcnet_r50-d8_512x512_20k_voc12aug_20200617_165701-3cbfdab1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_20k_voc12aug/gcnet_r50-d8_512x512_20k_voc12aug_20200617_165701.log.json)     |
-| GCNet  | R-101-D8 | 512x512   |   20000 | 9.2      | 14.80          | V100   | 77.41 |         78.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_20k_voc12aug/gcnet_r101-d8_512x512_20k_voc12aug_20200617_165713-6c720aa9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_20k_voc12aug/gcnet_r101-d8_512x512_20k_voc12aug_20200617_165713.log.json) |
-| GCNet  | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 76.24 |         77.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_40k_voc12aug/gcnet_r50-d8_512x512_40k_voc12aug_20200613_195105-9797336d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_40k_voc12aug/gcnet_r50-d8_512x512_40k_voc12aug_20200613_195105.log.json)     |
-| GCNet  | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 77.84 |         78.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/gcnet/gcnet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_40k_voc12aug/gcnet_r101-d8_512x512_40k_voc12aug_20200613_185806-1e38208d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_40k_voc12aug/gcnet_r101-d8_512x512_40k_voc12aug_20200613_185806.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                    | download                                                                                                                                                                                                                                                                                                                               |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| GCNet  | R-50-D8  | 512x512   |   20000 | 5.8      | 23.35          | V100   | 76.42 |         77.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_20k_voc12aug/gcnet_r50-d8_512x512_20k_voc12aug_20200617_165701-3cbfdab1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_20k_voc12aug/gcnet_r50-d8_512x512_20k_voc12aug_20200617_165701.log.json)     |
+| GCNet  | R-101-D8 | 512x512   |   20000 | 9.2      | 14.80          | V100   | 77.41 |         78.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_20k_voc12aug/gcnet_r101-d8_512x512_20k_voc12aug_20200617_165713-6c720aa9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_20k_voc12aug/gcnet_r101-d8_512x512_20k_voc12aug_20200617_165713.log.json) |
+| GCNet  | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 76.24 |         77.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_40k_voc12aug/gcnet_r50-d8_512x512_40k_voc12aug_20200613_195105-9797336d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_40k_voc12aug/gcnet_r50-d8_512x512_40k_voc12aug_20200613_195105.log.json)     |
+| GCNet  | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 77.84 |         78.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_40k_voc12aug/gcnet_r101-d8_512x512_40k_voc12aug_20200613_185806-1e38208d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_40k_voc12aug/gcnet_r101-d8_512x512_40k_voc12aug_20200613_185806.log.json) |
 
 ## Citation
 
diff --git a/configs/hrnet/README.md b/configs/hrnet/README.md
index 38a6bd0e76..b529fc895e 100644
--- a/configs/hrnet/README.md
+++ b/configs/hrnet/README.md
@@ -26,85 +26,85 @@ High-resolution representations are essential for position-sensitive vision prob
 
 ### Cityscapes
 
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                               |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN    | HRNetV2p-W18-Small | 512x1024  |   40000 | 1.7      | 23.74          | V100   | 73.86 |         75.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_40k_cityscapes/fcn_hr18s_512x1024_40k_cityscapes_20200601_014216-93db27d0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_40k_cityscapes/fcn_hr18s_512x1024_40k_cityscapes_20200601_014216.log.json)     |
-| FCN    | HRNetV2p-W18       | 512x1024  |   40000 | 2.9      | 12.97          | V100   | 77.19 |         78.92 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_40k_cityscapes/fcn_hr18_512x1024_40k_cityscapes_20200601_014216-f196fb4e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_40k_cityscapes/fcn_hr18_512x1024_40k_cityscapes_20200601_014216.log.json)         |
-| FCN    | HRNetV2p-W48       | 512x1024  |   40000 | 6.2      | 6.42           | V100   | 78.48 |         79.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_40k_cityscapes/fcn_hr48_512x1024_40k_cityscapes_20200601_014240-a989b146.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_40k_cityscapes/fcn_hr48_512x1024_40k_cityscapes_20200601_014240.log.json)         |
-| FCN    | HRNetV2p-W18-Small | 512x1024  |   80000 | -        | -              | V100   | 75.31 |         77.48 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_80k_cityscapes/fcn_hr18s_512x1024_80k_cityscapes_20200601_202700-1462b75d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_80k_cityscapes/fcn_hr18s_512x1024_80k_cityscapes_20200601_202700.log.json)     |
-| FCN    | HRNetV2p-W18       | 512x1024  |   80000 | -        | -              | V100   | 78.65 |         80.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_80k_cityscapes/fcn_hr18_512x1024_80k_cityscapes_20200601_223255-4e7b345e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_80k_cityscapes/fcn_hr18_512x1024_80k_cityscapes_20200601_223255.log.json)         |
-| FCN    | HRNetV2p-W48       | 512x1024  |   80000 | -        | -              | V100   | 79.93 |         80.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_80k_cityscapes/fcn_hr48_512x1024_80k_cityscapes_20200601_202606-58ea95d6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_80k_cityscapes/fcn_hr48_512x1024_80k_cityscapes_20200601_202606.log.json)         |
-| FCN    | HRNetV2p-W18-Small | 512x1024  |  160000 | -        | -              | V100   | 76.31 |         78.31 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb2-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_160k_cityscapes/fcn_hr18s_512x1024_160k_cityscapes_20200602_190901-4a0797ea.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_160k_cityscapes/fcn_hr18s_512x1024_160k_cityscapes_20200602_190901.log.json) |
-| FCN    | HRNetV2p-W18       | 512x1024  |  160000 | -        | -              | V100   | 78.80 |         80.74 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb2-160k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_160k_cityscapes/fcn_hr18_512x1024_160k_cityscapes_20200602_190822-221e4a4f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_160k_cityscapes/fcn_hr18_512x1024_160k_cityscapes_20200602_190822.log.json)     |
-| FCN    | HRNetV2p-W48       | 512x1024  |  160000 | -        | -              | V100   | 80.65 |         81.92 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb2-160k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_160k_cityscapes/fcn_hr48_512x1024_160k_cityscapes_20200602_190946-59b7973e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_160k_cityscapes/fcn_hr48_512x1024_160k_cityscapes_20200602_190946.log.json)     |
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                    | download                                                                                                                                                                                                                                                                                                                               |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN    | HRNetV2p-W18-Small | 512x1024  |   40000 | 1.7      | 23.74          | V100   | 73.86 |         75.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18s_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_40k_cityscapes/fcn_hr18s_512x1024_40k_cityscapes_20200601_014216-93db27d0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_40k_cityscapes/fcn_hr18s_512x1024_40k_cityscapes_20200601_014216.log.json)     |
+| FCN    | HRNetV2p-W18       | 512x1024  |   40000 | 2.9      | 12.97          | V100   | 77.19 |         78.92 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_40k_cityscapes/fcn_hr18_512x1024_40k_cityscapes_20200601_014216-f196fb4e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_40k_cityscapes/fcn_hr18_512x1024_40k_cityscapes_20200601_014216.log.json)         |
+| FCN    | HRNetV2p-W48       | 512x1024  |   40000 | 6.2      | 6.42           | V100   | 78.48 |         79.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr48_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_40k_cityscapes/fcn_hr48_512x1024_40k_cityscapes_20200601_014240-a989b146.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_40k_cityscapes/fcn_hr48_512x1024_40k_cityscapes_20200601_014240.log.json)         |
+| FCN    | HRNetV2p-W18-Small | 512x1024  |   80000 | -        | -              | V100   | 75.31 |         77.48 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18s_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_80k_cityscapes/fcn_hr18s_512x1024_80k_cityscapes_20200601_202700-1462b75d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_80k_cityscapes/fcn_hr18s_512x1024_80k_cityscapes_20200601_202700.log.json)     |
+| FCN    | HRNetV2p-W18       | 512x1024  |   80000 | -        | -              | V100   | 78.65 |         80.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_80k_cityscapes/fcn_hr18_512x1024_80k_cityscapes_20200601_223255-4e7b345e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_80k_cityscapes/fcn_hr18_512x1024_80k_cityscapes_20200601_223255.log.json)         |
+| FCN    | HRNetV2p-W48       | 512x1024  |   80000 | -        | -              | V100   | 79.93 |         80.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr48_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_80k_cityscapes/fcn_hr48_512x1024_80k_cityscapes_20200601_202606-58ea95d6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_80k_cityscapes/fcn_hr48_512x1024_80k_cityscapes_20200601_202606.log.json)         |
+| FCN    | HRNetV2p-W18-Small | 512x1024  |  160000 | -        | -              | V100   | 76.31 |         78.31 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18s_4xb2-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_160k_cityscapes/fcn_hr18s_512x1024_160k_cityscapes_20200602_190901-4a0797ea.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_160k_cityscapes/fcn_hr18s_512x1024_160k_cityscapes_20200602_190901.log.json) |
+| FCN    | HRNetV2p-W18       | 512x1024  |  160000 | -        | -              | V100   | 78.80 |         80.74 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18_4xb2-160k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_160k_cityscapes/fcn_hr18_512x1024_160k_cityscapes_20200602_190822-221e4a4f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_160k_cityscapes/fcn_hr18_512x1024_160k_cityscapes_20200602_190822.log.json)     |
+| FCN    | HRNetV2p-W48       | 512x1024  |  160000 | -        | -              | V100   | 80.65 |         81.92 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr48_4xb2-160k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_160k_cityscapes/fcn_hr48_512x1024_160k_cityscapes_20200602_190946-59b7973e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_160k_cityscapes/fcn_hr48_512x1024_160k_cityscapes_20200602_190946.log.json)     |
 
 ### ADE20K
 
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                                           |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| FCN    | HRNetV2p-W18-Small | 512x512   |   80000 | 3.8      | 38.66          | V100   | 31.38 |         32.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_ade20k/fcn_hr18s_512x512_80k_ade20k_20200614_144345-77fc814a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_ade20k/fcn_hr18s_512x512_80k_ade20k_20200614_144345.log.json)     |
-| FCN    | HRNetV2p-W18       | 512x512   |   80000 | 4.9      | 22.57          | V100   | 36.27 |         37.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20210827_114910-6c9382c0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20210827_114910.log.json)         |
-| FCN    | HRNetV2p-W48       | 512x512   |   80000 | 8.2      | 21.23          | V100   | 41.90 |         43.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_ade20k/fcn_hr48_512x512_80k_ade20k_20200614_193946-7ba5258d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_ade20k/fcn_hr48_512x512_80k_ade20k_20200614_193946.log.json)         |
-| FCN    | HRNetV2p-W18-Small | 512x512   |  160000 | -        | -              | V100   | 33.07 |         34.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20210829_174739-f1e7c2e7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20210829_174739.log.json) |
-| FCN    | HRNetV2p-W18       | 512x512   |  160000 | -        | -              | V100   | 36.79 |         38.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_160k_ade20k/fcn_hr18_512x512_160k_ade20k_20200614_214426-ca961836.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_160k_ade20k/fcn_hr18_512x512_160k_ade20k_20200614_214426.log.json)     |
-| FCN    | HRNetV2p-W48       | 512x512   |  160000 | -        | -              | V100   | 42.02 |         43.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_160k_ade20k/fcn_hr48_512x512_160k_ade20k_20200614_214407-a52fc02c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_160k_ade20k/fcn_hr48_512x512_160k_ade20k_20200614_214407.log.json)     |
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                               | download                                                                                                                                                                                                                                                                                                           |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| FCN    | HRNetV2p-W18-Small | 512x512   |   80000 | 3.8      | 38.66          | V100   | 31.38 |         32.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18s_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_ade20k/fcn_hr18s_512x512_80k_ade20k_20200614_144345-77fc814a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_ade20k/fcn_hr18s_512x512_80k_ade20k_20200614_144345.log.json)     |
+| FCN    | HRNetV2p-W18       | 512x512   |   80000 | 4.9      | 22.57          | V100   | 36.27 |         37.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20210827_114910-6c9382c0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20210827_114910.log.json)         |
+| FCN    | HRNetV2p-W48       | 512x512   |   80000 | 8.2      | 21.23          | V100   | 41.90 |         43.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr48_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_ade20k/fcn_hr48_512x512_80k_ade20k_20200614_193946-7ba5258d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_ade20k/fcn_hr48_512x512_80k_ade20k_20200614_193946.log.json)         |
+| FCN    | HRNetV2p-W18-Small | 512x512   |  160000 | -        | -              | V100   | 33.07 |         34.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18s_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20210829_174739-f1e7c2e7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20210829_174739.log.json) |
+| FCN    | HRNetV2p-W18       | 512x512   |  160000 | -        | -              | V100   | 36.79 |         38.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_160k_ade20k/fcn_hr18_512x512_160k_ade20k_20200614_214426-ca961836.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_160k_ade20k/fcn_hr18_512x512_160k_ade20k_20200614_214426.log.json)     |
+| FCN    | HRNetV2p-W48       | 512x512   |  160000 | -        | -              | V100   | 42.02 |         43.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr48_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_160k_ade20k/fcn_hr48_512x512_160k_ade20k_20200614_214407-a52fc02c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_160k_ade20k/fcn_hr48_512x512_160k_ade20k_20200614_214407.log.json)     |
 
 ### Pascal VOC 2012 + Aug
 
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                   | download                                                                                                                                                                                                                                                                                                               |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN    | HRNetV2p-W18-Small | 512x512   |   20000 | 1.8      | 43.36          | V100   |  65.5 |         68.89 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20210829_174910-0aceadb4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20210829_174910.log.json) |
-| FCN    | HRNetV2p-W18       | 512x512   |   20000 | 2.9      | 23.48          | V100   | 72.30 |         74.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_20k_voc12aug/fcn_hr18_512x512_20k_voc12aug_20200617_224503-488d45f7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_20k_voc12aug/fcn_hr18_512x512_20k_voc12aug_20200617_224503.log.json)     |
-| FCN    | HRNetV2p-W48       | 512x512   |   20000 | 6.2      | 22.05          | V100   | 75.87 |         78.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_20k_voc12aug/fcn_hr48_512x512_20k_voc12aug_20200617_224419-89de05cd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_20k_voc12aug/fcn_hr48_512x512_20k_voc12aug_20200617_224419.log.json)     |
-| FCN    | HRNetV2p-W18-Small | 512x512   |   40000 | -        | -              | V100   | 66.61 |         70.00 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_40k_voc12aug/fcn_hr18s_512x512_40k_voc12aug_20200614_000648-4f8d6e7f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_40k_voc12aug/fcn_hr18s_512x512_40k_voc12aug_20200614_000648.log.json) |
-| FCN    | HRNetV2p-W18       | 512x512   |   40000 | -        | -              | V100   | 72.90 |         75.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_40k_voc12aug/fcn_hr18_512x512_40k_voc12aug_20200613_224401-1b4b76cd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_40k_voc12aug/fcn_hr18_512x512_40k_voc12aug_20200613_224401.log.json)     |
-| FCN    | HRNetV2p-W48       | 512x512   |   40000 | -        | -              | V100   | 76.24 |         78.49 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_40k_voc12aug/fcn_hr48_512x512_40k_voc12aug_20200613_222111-1b0f18bc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_40k_voc12aug/fcn_hr48_512x512_40k_voc12aug_20200613_222111.log.json)     |
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                | download                                                                                                                                                                                                                                                                                                               |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN    | HRNetV2p-W18-Small | 512x512   |   20000 | 1.8      | 43.36          | V100   |  65.5 |         68.89 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18s_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20210829_174910-0aceadb4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20210829_174910.log.json) |
+| FCN    | HRNetV2p-W18       | 512x512   |   20000 | 2.9      | 23.48          | V100   | 72.30 |         74.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_20k_voc12aug/fcn_hr18_512x512_20k_voc12aug_20200617_224503-488d45f7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_20k_voc12aug/fcn_hr18_512x512_20k_voc12aug_20200617_224503.log.json)     |
+| FCN    | HRNetV2p-W48       | 512x512   |   20000 | 6.2      | 22.05          | V100   | 75.87 |         78.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr48_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_20k_voc12aug/fcn_hr48_512x512_20k_voc12aug_20200617_224419-89de05cd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_20k_voc12aug/fcn_hr48_512x512_20k_voc12aug_20200617_224419.log.json)     |
+| FCN    | HRNetV2p-W18-Small | 512x512   |   40000 | -        | -              | V100   | 66.61 |         70.00 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18s_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_40k_voc12aug/fcn_hr18s_512x512_40k_voc12aug_20200614_000648-4f8d6e7f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_40k_voc12aug/fcn_hr18s_512x512_40k_voc12aug_20200614_000648.log.json) |
+| FCN    | HRNetV2p-W18       | 512x512   |   40000 | -        | -              | V100   | 72.90 |         75.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_40k_voc12aug/fcn_hr18_512x512_40k_voc12aug_20200613_224401-1b4b76cd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_40k_voc12aug/fcn_hr18_512x512_40k_voc12aug_20200613_224401.log.json)     |
+| FCN    | HRNetV2p-W48       | 512x512   |   40000 | -        | -              | V100   | 76.24 |         78.49 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr48_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_40k_voc12aug/fcn_hr48_512x512_40k_voc12aug_20200613_222111-1b0f18bc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_40k_voc12aug/fcn_hr48_512x512_40k_voc12aug_20200613_222111.log.json)     |
 
 ### Pascal Context
 
-| Method | Backbone     | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                   |
-| ------ | ------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| FCN    | HRNetV2p-W48 | 480x480   |   40000 | 6.1      | 8.86           | V100   | 45.14 |         47.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context/fcn_hr48_480x480_40k_pascal_context_20200911_164852-667d00b0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context/fcn_hr48_480x480_40k_pascal_context-20200911_164852.log.json) |
-| FCN    | HRNetV2p-W48 | 480x480   |   80000 | -        | -              | V100   | 45.84 |         47.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context/fcn_hr48_480x480_80k_pascal_context_20200911_155322-847a6711.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context/fcn_hr48_480x480_80k_pascal_context-20200911_155322.log.json) |
+| Method | Backbone     | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                   |
+| ------ | ------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| FCN    | HRNetV2p-W48 | 480x480   |   40000 | 6.1      | 8.86           | V100   | 45.14 |         47.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr48_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context/fcn_hr48_480x480_40k_pascal_context_20200911_164852-667d00b0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context/fcn_hr48_480x480_40k_pascal_context-20200911_164852.log.json) |
+| FCN    | HRNetV2p-W48 | 480x480   |   80000 | -        | -              | V100   | 45.84 |         47.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr48_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context/fcn_hr48_480x480_80k_pascal_context_20200911_155322-847a6711.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context/fcn_hr48_480x480_80k_pascal_context-20200911_155322.log.json) |
 
 ### Pascal Context 59
 
-| Method | Backbone     | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                               |
-| ------ | ------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| FCN    | HRNetV2p-W48 | 480x480   |   40000 | -        | -              | V100   | 50.33 |         52.83 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context_59/fcn_hr48_480x480_40k_pascal_context_59_20210410_122738-b808b8b2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context_59/fcn_hr48_480x480_40k_pascal_context_59-20210410_122738.log.json) |
-| FCN    | HRNetV2p-W48 | 480x480   |   80000 | -        | -              | V100   | 51.12 |         53.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59_20210411_003240-3ae7081e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59-20210411_003240.log.json) |
+| Method | Backbone     | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                               |
+| ------ | ------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| FCN    | HRNetV2p-W48 | 480x480   |   40000 | -        | -              | V100   | 50.33 |         52.83 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr48_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context_59/fcn_hr48_480x480_40k_pascal_context_59_20210410_122738-b808b8b2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context_59/fcn_hr48_480x480_40k_pascal_context_59-20210410_122738.log.json) |
+| FCN    | HRNetV2p-W48 | 480x480   |   80000 | -        | -              | V100   | 51.12 |         53.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr48_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59_20210411_003240-3ae7081e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59-20210411_003240.log.json) |
 
 ### LoveDA
 
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                                       |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN    | HRNetV2p-W18-Small | 512x512   |   80000 | 1.59     | 24.87          | V100   | 49.28 |         49.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-80k_loveda-512x512.pyy) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_loveda/fcn_hr18s_512x512_80k_loveda_20211210_203228-60a86a7a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_loveda/fcn_hr18s_512x512_80k_loveda_20211210_203228.log.json) |
-| FCN    | HRNetV2p-W18       | 512x512   |   80000 | 2.76     | 12.92          | V100   | 50.81 |         50.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-80k_loveda-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_loveda/fcn_hr18_512x512_80k_loveda_20211210_203952-93d9c3b3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_loveda/fcn_hr18_512x512_80k_loveda_20211210_203952.log.json)     |
-| FCN    | HRNetV2p-W48       | 512x512   |   80000 | 6.20     | 9.61           | V100   | 51.42 |         51.64 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_loveda-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_loveda/fcn_hr48_512x512_80k_loveda_20211211_044756-67072f55.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_loveda/fcn_hr48_512x512_80k_loveda_20211211_044756.log.json)     |
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                               | download                                                                                                                                                                                                                                                                                                       |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN    | HRNetV2p-W18-Small | 512x512   |   80000 | 1.59     | 24.87          | V100   | 49.28 |         49.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18s_4xb4-80k_loveda-512x512.pyy) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_loveda/fcn_hr18s_512x512_80k_loveda_20211210_203228-60a86a7a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_loveda/fcn_hr18s_512x512_80k_loveda_20211210_203228.log.json) |
+| FCN    | HRNetV2p-W18       | 512x512   |   80000 | 2.76     | 12.92          | V100   | 50.81 |         50.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18_4xb4-80k_loveda-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_loveda/fcn_hr18_512x512_80k_loveda_20211210_203952-93d9c3b3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_loveda/fcn_hr18_512x512_80k_loveda_20211210_203952.log.json)     |
+| FCN    | HRNetV2p-W48       | 512x512   |   80000 | 6.20     | 9.61           | V100   | 51.42 |         51.64 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr48_4xb4-80k_loveda-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_loveda/fcn_hr48_512x512_80k_loveda_20211211_044756-67072f55.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_loveda/fcn_hr48_512x512_80k_loveda_20211211_044756.log.json)     |
 
 ### Potsdam
 
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                                           |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| FCN    | HRNetV2p-W18-Small | 512x512   |   80000 | 1.58     | 36.00          | V100   | 77.64 |          78.8 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-80k_potsdam-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_potsdam/fcn_hr18s_512x512_80k_potsdam_20211218_205517-ba32af63.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_potsdam/fcn_hr18s_512x512_80k_potsdam_20211218_205517.log.json) |
-| FCN    | HRNetV2p-W18       | 512x512   |   80000 | 2.76     | 19.25          | V100   | 78.26 |         79.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_potsdam/fcn_hr18_512x512_80k_potsdam_20211218_205517-5d0387ad.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_potsdam/fcn_hr18_512x512_80k_potsdam_20211218_205517.log.json)     |
-| FCN    | HRNetV2p-W48       | 512x512   |   80000 | 6.20     | 16.42          | V100   | 78.39 |         79.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_potsdam/fcn_hr48_512x512_80k_potsdam_20211219_020601-97434c78.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_potsdam/fcn_hr48_512x512_80k_potsdam_20211219_020601.log.json)     |
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                               | download                                                                                                                                                                                                                                                                                                           |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| FCN    | HRNetV2p-W18-Small | 512x512   |   80000 | 1.58     | 36.00          | V100   | 77.64 |          78.8 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18s_4xb4-80k_potsdam-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_potsdam/fcn_hr18s_512x512_80k_potsdam_20211218_205517-ba32af63.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_potsdam/fcn_hr18s_512x512_80k_potsdam_20211218_205517.log.json) |
+| FCN    | HRNetV2p-W18       | 512x512   |   80000 | 2.76     | 19.25          | V100   | 78.26 |         79.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_potsdam/fcn_hr18_512x512_80k_potsdam_20211218_205517-5d0387ad.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_potsdam/fcn_hr18_512x512_80k_potsdam_20211218_205517.log.json)     |
+| FCN    | HRNetV2p-W48       | 512x512   |   80000 | 6.20     | 16.42          | V100   | 78.39 |         79.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr48_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_potsdam/fcn_hr48_512x512_80k_potsdam_20211219_020601-97434c78.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_potsdam/fcn_hr48_512x512_80k_potsdam_20211219_020601.log.json)     |
 
 ### Vaihingen
 
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                    | download                                                                                                                                                                                                                                                                                                                                   |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| FCN    | HRNetV2p-W18-Small | 512x512   |   80000 | 1.58     | 38.11          | V100   | 71.81 |          73.1 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-80k_vaihingen-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_512x512_80k_vaihingen/fcn_hr18s_4x4_512x512_80k_vaihingen_20211231_230909-b23aae02.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_512x512_80k_vaihingen/fcn_hr18s_4x4_512x512_80k_vaihingen_20211231_230909.log.json) |
-| FCN    | HRNetV2p-W18       | 512x512   |   80000 | 2.76     | 19.55          | V100   | 72.57 |         74.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_512x512_80k_vaihingen/fcn_hr18_4x4_512x512_80k_vaihingen_20211231_231216-2ec3ae8a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_512x512_80k_vaihingen/fcn_hr18_4x4_512x512_80k_vaihingen_20211231_231216.log.json)     |
-| FCN    | HRNetV2p-W48       | 512x512   |   80000 | 6.20     | 17.25          | V100   | 72.50 |         73.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_512x512_80k_vaihingen/fcn_hr48_4x4_512x512_80k_vaihingen_20211231_231244-7133cb22.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_512x512_80k_vaihingen/fcn_hr48_4x4_512x512_80k_vaihingen_20211231_231244.log.json)     |
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                   |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| FCN    | HRNetV2p-W18-Small | 512x512   |   80000 | 1.58     | 38.11          | V100   | 71.81 |          73.1 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18s_4xb4-80k_vaihingen-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_512x512_80k_vaihingen/fcn_hr18s_4x4_512x512_80k_vaihingen_20211231_230909-b23aae02.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_512x512_80k_vaihingen/fcn_hr18s_4x4_512x512_80k_vaihingen_20211231_230909.log.json) |
+| FCN    | HRNetV2p-W18       | 512x512   |   80000 | 2.76     | 19.55          | V100   | 72.57 |         74.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_512x512_80k_vaihingen/fcn_hr18_4x4_512x512_80k_vaihingen_20211231_231216-2ec3ae8a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_512x512_80k_vaihingen/fcn_hr18_4x4_512x512_80k_vaihingen_20211231_231216.log.json)     |
+| FCN    | HRNetV2p-W48       | 512x512   |   80000 | 6.20     | 17.25          | V100   | 72.50 |         73.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr48_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_512x512_80k_vaihingen/fcn_hr48_4x4_512x512_80k_vaihingen_20211231_231244-7133cb22.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_512x512_80k_vaihingen/fcn_hr48_4x4_512x512_80k_vaihingen_20211231_231244.log.json)     |
 
 ### iSAID
 
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                | download                                                                                                                                                                                                                                                                                                                   |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN    | HRNetV2p-W18-Small | 896x896   |   80000 | 4.95     | 13.84          | V100   | 62.30 |         62.97 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18s_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_896x896_80k_isaid/fcn_hr18s_4x4_896x896_80k_isaid_20220118_001603-3cc0769b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_896x896_80k_isaid/fcn_hr18s_4x4_896x896_80k_isaid_20220118_001603.log.json) |
-| FCN    | HRNetV2p-W18       | 896x896   |   80000 | 8.30     | 7.71           | V100   | 65.06 |         65.60 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr18_4xb4-80k_isaid-896x896.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_896x896_80k_isaid/fcn_hr18_4x4_896x896_80k_isaid_20220110_182230-49bf752e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_896x896_80k_isaid/fcn_hr18_4x4_896x896_80k_isaid_20220110_182230.log.json)     |
-| FCN    | HRNetV2p-W48       | 896x896   |   80000 | 16.89    | 7.34           | V100   | 67.80 |         68.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/hrnet/fcn_hr48_4xb4-80k_isaid-896x896.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_896x896_80k_isaid/fcn_hr48_4x4_896x896_80k_isaid_20220114_174643-547fc420.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_896x896_80k_isaid/fcn_hr48_4x4_896x896_80k_isaid_20220114_174643.log.json)     |
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                             | download                                                                                                                                                                                                                                                                                                                   |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN    | HRNetV2p-W18-Small | 896x896   |   80000 | 4.95     | 13.84          | V100   | 62.30 |         62.97 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18s_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_896x896_80k_isaid/fcn_hr18s_4x4_896x896_80k_isaid_20220118_001603-3cc0769b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_896x896_80k_isaid/fcn_hr18s_4x4_896x896_80k_isaid_20220118_001603.log.json) |
+| FCN    | HRNetV2p-W18       | 896x896   |   80000 | 8.30     | 7.71           | V100   | 65.06 |         65.60 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr18_4xb4-80k_isaid-896x896.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_896x896_80k_isaid/fcn_hr18_4x4_896x896_80k_isaid_20220110_182230-49bf752e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_896x896_80k_isaid/fcn_hr18_4x4_896x896_80k_isaid_20220110_182230.log.json)     |
+| FCN    | HRNetV2p-W48       | 896x896   |   80000 | 16.89    | 7.34           | V100   | 67.80 |         68.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet/fcn_hr48_4xb4-80k_isaid-896x896.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_896x896_80k_isaid/fcn_hr48_4x4_896x896_80k_isaid_20220114_174643-547fc420.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_896x896_80k_isaid/fcn_hr48_4x4_896x896_80k_isaid_20220114_174643.log.json)     |
 
 Note:
 
diff --git a/configs/icnet/README.md b/configs/icnet/README.md
index 2b58c2eed8..fa2327fc39 100644
--- a/configs/icnet/README.md
+++ b/configs/icnet/README.md
@@ -26,20 +26,20 @@ We focus on the challenging task of real-time semantic segmentation in this pape
 
 ### Cityscapes
 
-| Method           | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                   | download                                                                                                                                                                                                                                                                                                                                                                               |
-| ---------------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| ICNet            | R-18-D8  | 832x832   |   80000 | 1.70     | 27.12          | V100   | 68.14 |         70.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r18-d8_4xb2-80k_cityscapes-832x832.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_80k_cityscapes/icnet_r18-d8_832x832_80k_cityscapes_20210925_225521-2e36638d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_80k_cityscapes/icnet_r18-d8_832x832_80k_cityscapes_20210925_225521.log.json)                                             |
-| ICNet            | R-18-D8  | 832x832   |  160000 | -        | -              | V100   | 71.64 |         74.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r18-d8_4xb2-160k_cityscapes-832x832.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_160k_cityscapes/icnet_r18-d8_832x832_160k_cityscapes_20210925_230153-2c6eb6e0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_160k_cityscapes/icnet_r18-d8_832x832_160k_cityscapes_20210925_230153.log.json)                                         |
-| ICNet (in1k-pre) | R-18-D8  | 832x832   |   80000 | -        | -              | V100   | 72.51 |         74.78 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r18-d8-in1k-pre_4xb2-80k_cityscapes-832x832.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes_20210925_230354-1cbe3022.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes_20210925_230354.log.json)         |
-| ICNet (in1k-pre) | R-18-D8  | 832x832   |  160000 | -        | -              | V100   | 74.43 |         76.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r18-d8-in1k-pre_4xb2-160k_cityscapes-832x832.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes_20210926_052702-619c8ae1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes_20210926_052702.log.json)     |
-| ICNet            | R-50-D8  | 832x832   |   80000 | 2.53     | 20.08          | V100   | 68.91 |         69.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r50-d8_4xb2-80k_cityscapes-832x832.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_80k_cityscapes/icnet_r50-d8_832x832_80k_cityscapes_20210926_044625-c6407341.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_80k_cityscapes/icnet_r50-d8_832x832_80k_cityscapes_20210926_044625.log.json)                                             |
-| ICNet            | R-50-D8  | 832x832   |  160000 | -        | -              | V100   | 73.82 |         75.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r50-d8_4xb2-160k_cityscapes-832x832.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_160k_cityscapes/icnet_r50-d8_832x832_160k_cityscapes_20210925_232612-a95f0d4e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_160k_cityscapes/icnet_r50-d8_832x832_160k_cityscapes_20210925_232612.log.json)                                         |
-| ICNet (in1k-pre) | R-50-D8  | 832x832   |   80000 | -        | -              | V100   | 74.58 |         76.41 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r50-d8-in1k-pre_4xb2-80k_cityscapes-832x832.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes_20210926_032943-1743dc7b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes_20210926_032943.log.json)         |
-| ICNet (in1k-pre) | R-50-D8  | 832x832   |  160000 | -        | -              | V100   | 76.29 |         78.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r50-d8-in1k-pre_4xb2-160k_cityscapes-832x832.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes_20210926_042715-ce310aea.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes_20210926_042715.log.json)     |
-| ICNet            | R-101-D8 | 832x832   |   80000 | 3.08     | 16.95          | V100   | 70.28 |         71.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r101-d8_4xb2-80k_cityscapes-832x832.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_80k_cityscapes/icnet_r101-d8_832x832_80k_cityscapes_20210926_072447-b52f936e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_80k_cityscapes/icnet_r101-d8_832x832_80k_cityscapes_20210926_072447.log.json)                                         |
-| ICNet            | R-101-D8 | 832x832   |  160000 | -        | -              | V100   | 73.80 |         76.10 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r101-d8_4xb2-160k_cityscapes-832x832.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_160k_cityscapes/icnet_r101-d8_832x832_160k_cityscapes_20210926_092350-3a1ebf1a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_160k_cityscapes/icnet_r101-d8_832x832_160k_cityscapes_20210926_092350.log.json)                                     |
-| ICNet (in1k-pre) | R-101-D8 | 832x832   |   80000 | -        | -              | V100   | 75.57 |         77.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r101-d8-in1k-pre_4xb2-80k_cityscapes-832x832.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes_20210926_020414-7ceb12c5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes_20210926_020414.log.json)     |
-| ICNet (in1k-pre) | R-101-D8 | 832x832   |  160000 | -        | -              | V100   | 76.15 |         77.98 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/icnet/icnet_r101-d8-in1k-pre_4xb2-160k_cityscapes-832x832.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes_20210925_232612-9484ae8a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes_20210925_232612.log.json) |
+| Method           | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                | download                                                                                                                                                                                                                                                                                                                                                                               |
+| ---------------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ICNet            | R-18-D8  | 832x832   |   80000 | 1.70     | 27.12          | V100   | 68.14 |         70.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/icnet/icnet_r18-d8_4xb2-80k_cityscapes-832x832.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_80k_cityscapes/icnet_r18-d8_832x832_80k_cityscapes_20210925_225521-2e36638d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_80k_cityscapes/icnet_r18-d8_832x832_80k_cityscapes_20210925_225521.log.json)                                             |
+| ICNet            | R-18-D8  | 832x832   |  160000 | -        | -              | V100   | 71.64 |         74.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/icnet/icnet_r18-d8_4xb2-160k_cityscapes-832x832.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_160k_cityscapes/icnet_r18-d8_832x832_160k_cityscapes_20210925_230153-2c6eb6e0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_160k_cityscapes/icnet_r18-d8_832x832_160k_cityscapes_20210925_230153.log.json)                                         |
+| ICNet (in1k-pre) | R-18-D8  | 832x832   |   80000 | -        | -              | V100   | 72.51 |         74.78 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/icnet/icnet_r18-d8-in1k-pre_4xb2-80k_cityscapes-832x832.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes_20210925_230354-1cbe3022.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes_20210925_230354.log.json)         |
+| ICNet (in1k-pre) | R-18-D8  | 832x832   |  160000 | -        | -              | V100   | 74.43 |         76.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/icnet/icnet_r18-d8-in1k-pre_4xb2-160k_cityscapes-832x832.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes_20210926_052702-619c8ae1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes_20210926_052702.log.json)     |
+| ICNet            | R-50-D8  | 832x832   |   80000 | 2.53     | 20.08          | V100   | 68.91 |         69.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/icnet/icnet_r50-d8_4xb2-80k_cityscapes-832x832.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_80k_cityscapes/icnet_r50-d8_832x832_80k_cityscapes_20210926_044625-c6407341.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_80k_cityscapes/icnet_r50-d8_832x832_80k_cityscapes_20210926_044625.log.json)                                             |
+| ICNet            | R-50-D8  | 832x832   |  160000 | -        | -              | V100   | 73.82 |         75.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/icnet/icnet_r50-d8_4xb2-160k_cityscapes-832x832.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_160k_cityscapes/icnet_r50-d8_832x832_160k_cityscapes_20210925_232612-a95f0d4e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_160k_cityscapes/icnet_r50-d8_832x832_160k_cityscapes_20210925_232612.log.json)                                         |
+| ICNet (in1k-pre) | R-50-D8  | 832x832   |   80000 | -        | -              | V100   | 74.58 |         76.41 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/icnet/icnet_r50-d8-in1k-pre_4xb2-80k_cityscapes-832x832.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes_20210926_032943-1743dc7b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes_20210926_032943.log.json)         |
+| ICNet (in1k-pre) | R-50-D8  | 832x832   |  160000 | -        | -              | V100   | 76.29 |         78.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/icnet/icnet_r50-d8-in1k-pre_4xb2-160k_cityscapes-832x832.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes_20210926_042715-ce310aea.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes_20210926_042715.log.json)     |
+| ICNet            | R-101-D8 | 832x832   |   80000 | 3.08     | 16.95          | V100   | 70.28 |         71.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/icnet/icnet_r101-d8_4xb2-80k_cityscapes-832x832.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_80k_cityscapes/icnet_r101-d8_832x832_80k_cityscapes_20210926_072447-b52f936e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_80k_cityscapes/icnet_r101-d8_832x832_80k_cityscapes_20210926_072447.log.json)                                         |
+| ICNet            | R-101-D8 | 832x832   |  160000 | -        | -              | V100   | 73.80 |         76.10 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/icnet/icnet_r101-d8_4xb2-160k_cityscapes-832x832.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_160k_cityscapes/icnet_r101-d8_832x832_160k_cityscapes_20210926_092350-3a1ebf1a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_160k_cityscapes/icnet_r101-d8_832x832_160k_cityscapes_20210926_092350.log.json)                                     |
+| ICNet (in1k-pre) | R-101-D8 | 832x832   |   80000 | -        | -              | V100   | 75.57 |         77.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/icnet/icnet_r101-d8-in1k-pre_4xb2-80k_cityscapes-832x832.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes_20210926_020414-7ceb12c5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes_20210926_020414.log.json)     |
+| ICNet (in1k-pre) | R-101-D8 | 832x832   |  160000 | -        | -              | V100   | 76.15 |         77.98 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/icnet/icnet_r101-d8-in1k-pre_4xb2-160k_cityscapes-832x832.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes_20210925_232612-9484ae8a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes_20210925_232612.log.json) |
 
 Note: `in1k-pre` means pretrained model is used.
 
diff --git a/configs/isanet/README.md b/configs/isanet/README.md
index da9f0104c5..c11744ffef 100644
--- a/configs/isanet/README.md
+++ b/configs/isanet/README.md
@@ -26,34 +26,34 @@ In this paper, we present a so-called interlaced sparse self-attention approach
 
 ### Cityscapes
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) |                                                                                                                            config | download                                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------- | -------: | -------------- | ------ | ----- | ------------: | --------------------------------------------------------------------------------------------------------------------------------: | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| ISANet | R-50-D8  | 512x1024  | 40000   |    5.869 | 2.91           | V100   | 78.49 |         79.44 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_40k_cityscapes/isanet_r50-d8_512x1024_40k_cityscapes_20210901_054739-981bd763.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_40k_cityscapes/isanet_r50-d8_512x1024_40k_cityscapes_20210901_054739.log.json)     |
-| ISANet | R-50-D8  | 512x1024  | 80000   |    5.869 | 2.91           | V100   | 78.68 |         80.25 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_80k_cityscapes/isanet_r50-d8_512x1024_80k_cityscapes_20210901_074202-89384497.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_80k_cityscapes/isanet_r50-d8_512x1024_80k_cityscapes_20210901_074202.log.json)     |
-| ISANet | R-50-D8  | 769x769   | 40000   |    6.759 | 1.54           | V100   | 78.70 |         80.28 |   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb2-40k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_40k_cityscapes/isanet_r50-d8_769x769_40k_cityscapes_20210903_050200-4ae7e65b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_40k_cityscapes/isanet_r50-d8_769x769_40k_cityscapes_20210903_050200.log.json)         |
-| ISANet | R-50-D8  | 769x769   | 80000   |    6.759 | 1.54           | V100   | 79.29 |         80.53 |   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_80k_cityscapes/isanet_r50-d8_769x769_80k_cityscapes_20210903_101126-99b54519.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_80k_cityscapes/isanet_r50-d8_769x769_80k_cityscapes_20210903_101126.log.json)         |
-| ISANet | R-101-D8 | 512x1024  | 40000   |    9.425 | 2.35           | V100   | 79.58 |         81.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_40k_cityscapes/isanet_r101-d8_512x1024_40k_cityscapes_20210901_145553-293e6bd6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_40k_cityscapes/isanet_r101-d8_512x1024_40k_cityscapes_20210901_145553.log.json) |
-| ISANet | R-101-D8 | 512x1024  | 80000   |    9.425 | 2.35           | V100   | 80.32 |         81.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_80k_cityscapes/isanet_r101-d8_512x1024_80k_cityscapes_20210901_145243-5b99c9b2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_80k_cityscapes/isanet_r101-d8_512x1024_80k_cityscapes_20210901_145243.log.json) |
-| ISANet | R-101-D8 | 769x769   | 40000   |   10.815 | 0.92           | V100   | 79.68 |         80.95 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb2-40k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_40k_cityscapes/isanet_r101-d8_769x769_40k_cityscapes_20210903_111320-509e7224.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_40k_cityscapes/isanet_r101-d8_769x769_40k_cityscapes_20210903_111320.log.json)     |
-| ISANet | R-101-D8 | 769x769   | 80000   |   10.815 | 0.92           | V100   | 80.61 |         81.59 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_80k_cityscapes/isanet_r101-d8_769x769_80k_cityscapes_20210903_111319-24f71dfa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_80k_cityscapes/isanet_r101-d8_769x769_80k_cityscapes_20210903_111319.log.json)     |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) |                                                                                                                         config | download                                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------- | -------: | -------------- | ------ | ----- | ------------: | -----------------------------------------------------------------------------------------------------------------------------: | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ISANet | R-50-D8  | 512x1024  | 40000   |    5.869 | 2.91           | V100   | 78.49 |         79.44 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/isanet/isanet_r50-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_40k_cityscapes/isanet_r50-d8_512x1024_40k_cityscapes_20210901_054739-981bd763.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_40k_cityscapes/isanet_r50-d8_512x1024_40k_cityscapes_20210901_054739.log.json)     |
+| ISANet | R-50-D8  | 512x1024  | 80000   |    5.869 | 2.91           | V100   | 78.68 |         80.25 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/isanet/isanet_r50-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_80k_cityscapes/isanet_r50-d8_512x1024_80k_cityscapes_20210901_074202-89384497.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_80k_cityscapes/isanet_r50-d8_512x1024_80k_cityscapes_20210901_074202.log.json)     |
+| ISANet | R-50-D8  | 769x769   | 40000   |    6.759 | 1.54           | V100   | 78.70 |         80.28 |   [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/isanet/isanet_r50-d8_4xb2-40k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_40k_cityscapes/isanet_r50-d8_769x769_40k_cityscapes_20210903_050200-4ae7e65b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_40k_cityscapes/isanet_r50-d8_769x769_40k_cityscapes_20210903_050200.log.json)         |
+| ISANet | R-50-D8  | 769x769   | 80000   |    6.759 | 1.54           | V100   | 79.29 |         80.53 |   [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/isanet/isanet_r50-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_80k_cityscapes/isanet_r50-d8_769x769_80k_cityscapes_20210903_101126-99b54519.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_80k_cityscapes/isanet_r50-d8_769x769_80k_cityscapes_20210903_101126.log.json)         |
+| ISANet | R-101-D8 | 512x1024  | 40000   |    9.425 | 2.35           | V100   | 79.58 |         81.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/isanet/isanet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_40k_cityscapes/isanet_r101-d8_512x1024_40k_cityscapes_20210901_145553-293e6bd6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_40k_cityscapes/isanet_r101-d8_512x1024_40k_cityscapes_20210901_145553.log.json) |
+| ISANet | R-101-D8 | 512x1024  | 80000   |    9.425 | 2.35           | V100   | 80.32 |         81.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/isanet/isanet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_80k_cityscapes/isanet_r101-d8_512x1024_80k_cityscapes_20210901_145243-5b99c9b2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_80k_cityscapes/isanet_r101-d8_512x1024_80k_cityscapes_20210901_145243.log.json) |
+| ISANet | R-101-D8 | 769x769   | 40000   |   10.815 | 0.92           | V100   | 79.68 |         80.95 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/isanet/isanet_r101-d8_4xb2-40k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_40k_cityscapes/isanet_r101-d8_769x769_40k_cityscapes_20210903_111320-509e7224.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_40k_cityscapes/isanet_r101-d8_769x769_40k_cityscapes_20210903_111320.log.json)     |
+| ISANet | R-101-D8 | 769x769   | 80000   |   10.815 | 0.92           | V100   | 80.61 |         81.59 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/isanet/isanet_r101-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_80k_cityscapes/isanet_r101-d8_769x769_80k_cityscapes_20210903_111319-24f71dfa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_80k_cityscapes/isanet_r101-d8_769x769_80k_cityscapes_20210903_111319.log.json)     |
 
 ### ADE20K
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) |                                                                                                                        config | download                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------- | -------: | -------------- | ------ | ----- | ------------: | ----------------------------------------------------------------------------------------------------------------------------: | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| ISANet | R-50-D8  | 512x512   | 80000   |      9.0 | 22.55          | V100   | 41.12 |         42.35 |   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_80k_ade20k/isanet_r50-d8_512x512_80k_ade20k_20210903_124557-6ed83a0c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_80k_ade20k/isanet_r50-d8_512x512_80k_ade20k_20210903_124557.log.json)         |
-| ISANet | R-50-D8  | 512x512   | 160000  |      9.0 | 22.55          | V100   | 42.59 |         43.07 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_160k_ade20k/isanet_r50-d8_512x512_160k_ade20k_20210903_104850-f752d0a3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_160k_ade20k/isanet_r50-d8_512x512_160k_ade20k_20210903_104850.log.json)     |
-| ISANet | R-101-D8 | 512x512   | 80000   |   12.562 | 10.56          | V100   | 43.51 |         44.38 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_80k_ade20k/isanet_r101-d8_512x512_80k_ade20k_20210903_162056-68b235c2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_80k_ade20k/isanet_r101-d8_512x512_80k_ade20k_20210903_162056.log.json)     |
-| ISANet | R-101-D8 | 512x512   | 160000  |   12.562 | 10.56          | V100   | 43.80 |          45.4 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_160k_ade20k/isanet_r101-d8_512x512_160k_ade20k_20210903_211431-a7879dcd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_160k_ade20k/isanet_r101-d8_512x512_160k_ade20k_20210903_211431.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) |                                                                                                                     config | download                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------- | -------: | -------------- | ------ | ----- | ------------: | -------------------------------------------------------------------------------------------------------------------------: | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ISANet | R-50-D8  | 512x512   | 80000   |      9.0 | 22.55          | V100   | 41.12 |         42.35 |   [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/isanet/isanet_r50-d8_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_80k_ade20k/isanet_r50-d8_512x512_80k_ade20k_20210903_124557-6ed83a0c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_80k_ade20k/isanet_r50-d8_512x512_80k_ade20k_20210903_124557.log.json)         |
+| ISANet | R-50-D8  | 512x512   | 160000  |      9.0 | 22.55          | V100   | 42.59 |         43.07 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/isanet/isanet_r50-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_160k_ade20k/isanet_r50-d8_512x512_160k_ade20k_20210903_104850-f752d0a3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_160k_ade20k/isanet_r50-d8_512x512_160k_ade20k_20210903_104850.log.json)     |
+| ISANet | R-101-D8 | 512x512   | 80000   |   12.562 | 10.56          | V100   | 43.51 |         44.38 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/isanet/isanet_r101-d8_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_80k_ade20k/isanet_r101-d8_512x512_80k_ade20k_20210903_162056-68b235c2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_80k_ade20k/isanet_r101-d8_512x512_80k_ade20k_20210903_162056.log.json)     |
+| ISANet | R-101-D8 | 512x512   | 160000  |   12.562 | 10.56          | V100   | 43.80 |          45.4 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/isanet/isanet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_160k_ade20k/isanet_r101-d8_512x512_160k_ade20k_20210903_211431-a7879dcd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_160k_ade20k/isanet_r101-d8_512x512_160k_ade20k_20210903_211431.log.json) |
 
 ### Pascal VOC 2012 + Aug
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) |                                                                                                                         config | download                                                                                                                                                                                                                                                                                                                                     |
-| ------ | -------- | --------- | ------- | -------: | -------------- | ------ | ----- | ------------: | -----------------------------------------------------------------------------------------------------------------------------: | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| ISANet | R-50-D8  | 512x512   | 20000   |      5.9 | 23.08          | V100   | 76.78 |         77.79 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_20k_voc12aug/isanet_r50-d8_512x512_20k_voc12aug_20210901_164838-79d59b80.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_20k_voc12aug/isanet_r50-d8_512x512_20k_voc12aug_20210901_164838.log.json)     |
-| ISANet | R-50-D8  | 512x512   | 40000   |      5.9 | 23.08          | V100   | 76.20 |         77.22 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r50-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_40k_voc12aug/isanet_r50-d8_512x512_40k_voc12aug_20210901_151349-7d08a54e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_40k_voc12aug/isanet_r50-d8_512x512_40k_voc12aug_20210901_151349.log.json)     |
-| ISANet | R-101-D8 | 512x512   | 20000   |    9.465 | 7.42           | V100   | 78.46 |         79.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_20k_voc12aug/isanet_r101-d8_512x512_20k_voc12aug_20210901_115805-3ccbf355.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_20k_voc12aug/isanet_r101-d8_512x512_20k_voc12aug_20210901_115805.log.json) |
-| ISANet | R-101-D8 | 512x512   | 40000   |    9.465 | 7.42           | V100   | 78.12 |         79.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/isanet/isanet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_40k_voc12aug/isanet_r101-d8_512x512_40k_voc12aug_20210901_145814-bc71233b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_40k_voc12aug/isanet_r101-d8_512x512_40k_voc12aug_20210901_145814.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) |                                                                                                                      config | download                                                                                                                                                                                                                                                                                                                                     |
+| ------ | -------- | --------- | ------- | -------: | -------------- | ------ | ----- | ------------: | --------------------------------------------------------------------------------------------------------------------------: | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ISANet | R-50-D8  | 512x512   | 20000   |      5.9 | 23.08          | V100   | 76.78 |         77.79 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/isanet/isanet_r50-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_20k_voc12aug/isanet_r50-d8_512x512_20k_voc12aug_20210901_164838-79d59b80.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_20k_voc12aug/isanet_r50-d8_512x512_20k_voc12aug_20210901_164838.log.json)     |
+| ISANet | R-50-D8  | 512x512   | 40000   |      5.9 | 23.08          | V100   | 76.20 |         77.22 |  [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/isanet/isanet_r50-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_40k_voc12aug/isanet_r50-d8_512x512_40k_voc12aug_20210901_151349-7d08a54e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_40k_voc12aug/isanet_r50-d8_512x512_40k_voc12aug_20210901_151349.log.json)     |
+| ISANet | R-101-D8 | 512x512   | 20000   |    9.465 | 7.42           | V100   | 78.46 |         79.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/isanet/isanet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_20k_voc12aug/isanet_r101-d8_512x512_20k_voc12aug_20210901_115805-3ccbf355.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_20k_voc12aug/isanet_r101-d8_512x512_20k_voc12aug_20210901_115805.log.json) |
+| ISANet | R-101-D8 | 512x512   | 40000   |    9.465 | 7.42           | V100   | 78.12 |         79.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/isanet/isanet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_40k_voc12aug/isanet_r101-d8_512x512_40k_voc12aug_20210901_145814-bc71233b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_40k_voc12aug/isanet_r101-d8_512x512_40k_voc12aug_20210901_145814.log.json) |
 
 ## Citation
 
diff --git a/configs/knet/README.md b/configs/knet/README.md
index 070c7256da..1f3f2ae268 100644
--- a/configs/knet/README.md
+++ b/configs/knet/README.md
@@ -26,15 +26,15 @@ Semantic, instance, and panoptic segmentations have been addressed using differe
 
 ### ADE20K
 
-| Method           | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                                                                         |
-| ---------------- | -------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| KNet + FCN       | R-50-D8  | 512x512   | 80000   | 7.01     | 19.24          | V100   | 43.60 | 45.12         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_r50-d8_fcn_8xb2-adamw-80k_ade20k-512x512.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_043751-abcab920.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_043751.log.json)                         |
-| KNet + PSPNet    | R-50-D8  | 512x512   | 80000   | 6.98     | 20.04          | V100   | 44.18 | 45.58         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_r50-d8_pspnet_8xb2-adamw-80k_ade20k-512x512.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_054634-d2c72240.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_054634.log.json)             |
-| KNet + DeepLabV3 | R-50-D8  | 512x512   | 80000   | 7.42     | 12.10          | V100   | 45.06 | 46.11         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_r50-d8_deeplabv3_8xb2-adamw-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_041642-00c8fbeb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_041642.log.json) |
-| KNet + UperNet   | R-50-D8  | 512x512   | 80000   | 7.34     | 17.11          | V100   | 43.45 | 44.07         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_r50-d8_upernet_8xb2-adamw-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220304_125657-215753b0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220304_125657.log.json)         |
-| KNet + UperNet   | Swin-T   | 512x512   | 80000   | 7.57     | 15.56          | V100   | 45.84 | 46.27         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_swin-t_upernet_8xb2-adamw-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k_20220303_133059-7545e1dc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k_20220303_133059.log.json)         |
-| KNet + UperNet   | Swin-L   | 512x512   | 80000   | 13.5     | 8.29           | V100   | 52.05 | 53.24         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_swin-l_upernet_8xb2-adamw-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k_20220303_154559-d8da9a90.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k_20220303_154559.log.json)         |
-| KNet + UperNet   | Swin-L   | 640x640   | 80000   | 13.54    | 8.29           | V100   | 52.21 | 53.34         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/knet/knet-s3_swin-l_upernet_8xb2-adamw-80k_ade20k-640x640.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k_20220301_220747-8787fc71.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k_20220301_220747.log.json)         |
+| Method           | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                                  | download                                                                                                                                                                                                                                                                                                                                                                                                         |
+| ---------------- | -------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | --------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| KNet + FCN       | R-50-D8  | 512x512   | 80000   | 7.01     | 19.24          | V100   | 43.60 | 45.12         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/knet/knet-s3_r50-d8_fcn_8xb2-adamw-80k_ade20k-512x512.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_043751-abcab920.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_043751.log.json)                         |
+| KNet + PSPNet    | R-50-D8  | 512x512   | 80000   | 6.98     | 20.04          | V100   | 44.18 | 45.58         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/knet/knet-s3_r50-d8_pspnet_8xb2-adamw-80k_ade20k-512x512.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_054634-d2c72240.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_054634.log.json)             |
+| KNet + DeepLabV3 | R-50-D8  | 512x512   | 80000   | 7.42     | 12.10          | V100   | 45.06 | 46.11         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/knet/knet-s3_r50-d8_deeplabv3_8xb2-adamw-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_041642-00c8fbeb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_041642.log.json) |
+| KNet + UperNet   | R-50-D8  | 512x512   | 80000   | 7.34     | 17.11          | V100   | 43.45 | 44.07         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/knet/knet-s3_r50-d8_upernet_8xb2-adamw-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220304_125657-215753b0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220304_125657.log.json)         |
+| KNet + UperNet   | Swin-T   | 512x512   | 80000   | 7.57     | 15.56          | V100   | 45.84 | 46.27         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/knet/knet-s3_swin-t_upernet_8xb2-adamw-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k_20220303_133059-7545e1dc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k_20220303_133059.log.json)         |
+| KNet + UperNet   | Swin-L   | 512x512   | 80000   | 13.5     | 8.29           | V100   | 52.05 | 53.24         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/knet/knet-s3_swin-l_upernet_8xb2-adamw-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k_20220303_154559-d8da9a90.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k_20220303_154559.log.json)         |
+| KNet + UperNet   | Swin-L   | 640x640   | 80000   | 13.54    | 8.29           | V100   | 52.21 | 53.34         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/knet/knet-s3_swin-l_upernet_8xb2-adamw-80k_ade20k-640x640.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k_20220301_220747-8787fc71.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k_20220301_220747.log.json)         |
 
 Note:
 
diff --git a/configs/mae/README.md b/configs/mae/README.md
index 94ade08823..d14e3830be 100644
--- a/configs/mae/README.md
+++ b/configs/mae/README.md
@@ -66,9 +66,9 @@ upernet_mae-base_fp16_8x2_512x512_160k_ade20k_20220426_174752-f92a2975.pth $GPUS
 
 ### ADE20K
 
-| Method  | Backbone | Crop Size | pretrain    | pretrain img size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                                       |
-| ------- | -------- | --------- | ----------- | ----------------- | ---------- | ------- | -------- | -------------- | ------ | ----- | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| UPerNet | ViT-B    | 512x512   | ImageNet-1K | 224x224           | 16         | 160000  | 9.96     | 7.14           | V100   | 48.13 |         48.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mae/mae-base_upernet_8xb2-amp-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mae/upernet_mae-base_fp16_8x2_512x512_160k_ade20k/upernet_mae-base_fp16_8x2_512x512_160k_ade20k_20220426_174752-f92a2975.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mae/upernet_mae-base_fp16_8x2_512x512_160k_ade20k/upernet_mae-base_fp16_8x2_512x512_160k_ade20k_20220426_174752.log.json) |
+| Method  | Backbone | Crop Size | pretrain    | pretrain img size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                                       |
+| ------- | -------- | --------- | ----------- | ----------------- | ---------- | ------- | -------- | -------------- | ------ | ----- | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| UPerNet | ViT-B    | 512x512   | ImageNet-1K | 224x224           | 16         | 160000  | 9.96     | 7.14           | V100   | 48.13 |         48.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mae/mae-base_upernet_8xb2-amp-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mae/upernet_mae-base_fp16_8x2_512x512_160k_ade20k/upernet_mae-base_fp16_8x2_512x512_160k_ade20k_20220426_174752-f92a2975.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mae/upernet_mae-base_fp16_8x2_512x512_160k_ade20k/upernet_mae-base_fp16_8x2_512x512_160k_ade20k_20220426_174752.log.json) |
 
 ## Citation
 
diff --git a/configs/mask2former/README.md b/configs/mask2former/README.md
index 02639bef58..c21ab0d0c6 100644
--- a/configs/mask2former/README.md
+++ b/configs/mask2former/README.md
@@ -28,26 +28,26 @@ pip install "mmdet>=3.0.0rc4"
 
 ### Cityscapes
 
-| Method      | Backbone       | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) |                                                                                                                                                       config | download                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
-| ----------- | -------------- | --------- | ------- | -------: | -------------- | ------ | ----- | ------------: | -----------------------------------------------------------------------------------------------------------------------------------------------------------: | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Mask2Former | R-50-D32       | 512x1024  | 90000   |     5.67 | 9.17           | A100   | 80.44 |             - |                      [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024/mask2former_r50_8xb2-90k_cityscapes-512x1024_20221202_140802-ffd9d750.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024/mask2former_r50_8xb2-90k_cityscapes-512x1024_20221202_140802.json)                                                                                      |
-| Mask2Former | R-101-D32      | 512x1024  | 90000   |     6.81 | 7.11           | A100   | 80.80 |             - |                     [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024/mask2former_r101_8xb2-90k_cityscapes-512x1024_20221130_031628-43e68666.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024/mask2former_r101_8xb2-90k_cityscapes-512x1024_20221130_031628.json))                                                                                 |
-| Mask2Former | Swin-T         | 512x1024  | 90000   |     6.36 | 7.18           | A100   | 81.71 |             - |                   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024/mask2former_swin-t_8xb2-90k_cityscapes-512x1024_20221127_144501-36c59341.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024/mask2former_swin-t_8xb2-90k_cityscapes-512x1024_20221127_144501.json))                                                                         |
-| Mask2Former | Swin-S         | 512x1024  | 90000   |     8.09 | 5.57           | A100   | 82.57 |             - |                   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024/mask2former_swin-s_8xb2-90k_cityscapes-512x1024_20221127_143802-9ab177f6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024/mask2former_swin-s_8xb2-90k_cityscapes-512x1024_20221127_143802.json))                                                                         |
-| Mask2Former | Swin-B (in22k) | 512x1024  | 90000   |    10.89 | 4.32           | A100   | 83.52 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221203_045030-9a86a225.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221203_045030.json)) |
-| Mask2Former | Swin-L (in22k) | 512x1024  | 90000   |    15.83 | 2.86           | A100   | 83.65 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221202_141901-28ad20f1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221202_141901.json)) |
+| Method      | Backbone       | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) |                                                                                                                                                    config | download                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
+| ----------- | -------------- | --------- | ------- | -------: | -------------- | ------ | ----- | ------------: | --------------------------------------------------------------------------------------------------------------------------------------------------------: | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Mask2Former | R-50-D32       | 512x1024  | 90000   |     5.67 | 9.17           | A100   | 80.44 |             - |                      [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024/mask2former_r50_8xb2-90k_cityscapes-512x1024_20221202_140802-ffd9d750.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024/mask2former_r50_8xb2-90k_cityscapes-512x1024_20221202_140802.json)                                                                                      |
+| Mask2Former | R-101-D32      | 512x1024  | 90000   |     6.81 | 7.11           | A100   | 80.80 |             - |                     [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024/mask2former_r101_8xb2-90k_cityscapes-512x1024_20221130_031628-43e68666.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024/mask2former_r101_8xb2-90k_cityscapes-512x1024_20221130_031628.json))                                                                                 |
+| Mask2Former | Swin-T         | 512x1024  | 90000   |     6.36 | 7.18           | A100   | 81.71 |             - |                   [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024/mask2former_swin-t_8xb2-90k_cityscapes-512x1024_20221127_144501-36c59341.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024/mask2former_swin-t_8xb2-90k_cityscapes-512x1024_20221127_144501.json))                                                                         |
+| Mask2Former | Swin-S         | 512x1024  | 90000   |     8.09 | 5.57           | A100   | 82.57 |             - |                   [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024/mask2former_swin-s_8xb2-90k_cityscapes-512x1024_20221127_143802-9ab177f6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024/mask2former_swin-s_8xb2-90k_cityscapes-512x1024_20221127_143802.json))                                                                         |
+| Mask2Former | Swin-B (in22k) | 512x1024  | 90000   |    10.89 | 4.32           | A100   | 83.52 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221203_045030-9a86a225.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221203_045030.json)) |
+| Mask2Former | Swin-L (in22k) | 512x1024  | 90000   |    15.83 | 2.86           | A100   | 83.65 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221202_141901-28ad20f1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221202_141901.json)) |
 
 ### ADE20K
 
-| Method      | Backbone       | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) |                                                                                                                                                   config | download                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
-| ----------- | -------------- | --------- | ------- | -------: | -------------- | ------ | ----- | ------------: | -------------------------------------------------------------------------------------------------------------------------------------------------------: | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Mask2Former | R-50-D32       | 512x512   | 160000  |     3.31 | 26.59          | A100   | 47.87 |             - |                      [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512/mask2former_r50_8xb2-160k_ade20k-512x512_20221204_000055-2d1f55f1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512/mask2former_r50_8xb2-160k_ade20k-512x512_20221204_000055.json))                                                                                     |
-| Mask2Former | R-101-D32      | 512x512   | 160000  |     4.09 | 22.97          | A100   | 48.60 |             - |                     [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512/mask2former_r101_8xb2-160k_ade20k-512x512_20221203_233905-b7135890.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512/mask2former_r101_8xb2-160k_ade20k-512x512_20221203_233905.json))                                                                                 |
-| Mask2Former | Swin-T         | 512x512   | 160000  |     3826 | 23.82          | A100   | 48.66 |             - |                   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512/mask2former_swin-t_8xb2-160k_ade20k-512x512_20221203_234230-7d64e5dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512/mask2former_swin-t_8xb2-160k_ade20k-512x512_20221203_234230.json))                                                                         |
-| Mask2Former | Swin-S         | 512x512   | 160000  |     3.74 | 19.69          | A100   | 51.24 |             - |                   [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512/mask2former_swin-s_8xb2-160k_ade20k-512x512_20221204_143905-e715144e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512/mask2former_swin-s_8xb2-160k_ade20k-512x512_20221204_143905.json))                                                                         |
-| Mask2Former | Swin-B         | 640x640   | 160000  |     5.66 | 12.48          | A100   | 52.44 |             - |  [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640_20221129_125118-a4a086d2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640_20221129_125118.json))     |
-| Mask2Former | Swin-B (in22k) | 640x640   | 160000  |     5.66 | 12.43          | A100   | 53.90 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235230-7ec0f569.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235230.json)) |
-| Mask2Former | Swin-L (in22k) | 640x640   | 160000  |     8.86 | 8.81           | A100   | 56.01 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235933-7120c214.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235933.json)) |
+| Method      | Backbone       | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) |                                                                                                                                                config | download                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
+| ----------- | -------------- | --------- | ------- | -------: | -------------- | ------ | ----- | ------------: | ----------------------------------------------------------------------------------------------------------------------------------------------------: | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Mask2Former | R-50-D32       | 512x512   | 160000  |     3.31 | 26.59          | A100   | 47.87 |             - |                      [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512/mask2former_r50_8xb2-160k_ade20k-512x512_20221204_000055-2d1f55f1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512/mask2former_r50_8xb2-160k_ade20k-512x512_20221204_000055.json))                                                                                     |
+| Mask2Former | R-101-D32      | 512x512   | 160000  |     4.09 | 22.97          | A100   | 48.60 |             - |                     [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512/mask2former_r101_8xb2-160k_ade20k-512x512_20221203_233905-b7135890.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512/mask2former_r101_8xb2-160k_ade20k-512x512_20221203_233905.json))                                                                                 |
+| Mask2Former | Swin-T         | 512x512   | 160000  |     3826 | 23.82          | A100   | 48.66 |             - |                   [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512/mask2former_swin-t_8xb2-160k_ade20k-512x512_20221203_234230-7d64e5dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512/mask2former_swin-t_8xb2-160k_ade20k-512x512_20221203_234230.json))                                                                         |
+| Mask2Former | Swin-S         | 512x512   | 160000  |     3.74 | 19.69          | A100   | 51.24 |             - |                   [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512/mask2former_swin-s_8xb2-160k_ade20k-512x512_20221204_143905-e715144e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512/mask2former_swin-s_8xb2-160k_ade20k-512x512_20221204_143905.json))                                                                         |
+| Mask2Former | Swin-B         | 640x640   | 160000  |     5.66 | 12.48          | A100   | 52.44 |             - |  [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640_20221129_125118-a4a086d2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640_20221129_125118.json))     |
+| Mask2Former | Swin-B (in22k) | 640x640   | 160000  |     5.66 | 12.43          | A100   | 53.90 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235230-7ec0f569.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235230.json)) |
+| Mask2Former | Swin-L (in22k) | 640x640   | 160000  |     8.86 | 8.81           | A100   | 56.01 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235933-7120c214.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235933.json)) |
 
 Note:
 
diff --git a/configs/maskformer/README.md b/configs/maskformer/README.md
index aa54a27088..a899bac090 100644
--- a/configs/maskformer/README.md
+++ b/configs/maskformer/README.md
@@ -34,12 +34,12 @@ pip install "mmdet>=3.0.0rc4"
 
 ### ADE20K
 
-| Method     | Backbone  | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                                       | download                                                                                                                                                                                                                                                                                                                                                                                                     |
-| ---------- | --------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| MaskFormer | R-50-D32  | 512x512   | 160000  | 3.29     | A100           | 42.20  | 44.29 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512/maskformer_r50-d32_8xb2-160k_ade20k-512x512_20221030_182724-3a9cfe45.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512/maskformer_r50-d32_8xb2-160k_ade20k-512x512_20221030_182724.json)                             |
-| MaskFormer | R-101-D32 | 512x512   | 160000  | 4.12     | A100           | 34.90  | 45.11 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512/maskformer_r101-d32_8xb2-160k_ade20k-512x512_20221031_223053-84adbfcb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512/maskformer_r101-d32_8xb2-160k_ade20k-512x512_20221031_223053.json)                         |
-| MaskFormer | Swin-T    | 512x512   | 160000  | 3.73     | A100           | 40.53  | 46.69 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512_20221114_232813-f14e7ce0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512_20221114_232813.json) |
-| MaskFormer | Swin-S    | 512x512   | 160000  | 5.33     | A100           | 26.98  | 49.36 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512_20221115_114710-723512c7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512_20221115_114710.json) |
+| Method     | Backbone  | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                                    | download                                                                                                                                                                                                                                                                                                                                                                                                     |
+| ---------- | --------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| MaskFormer | R-50-D32  | 512x512   | 160000  | 3.29     | A100           | 42.20  | 44.29 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512/maskformer_r50-d32_8xb2-160k_ade20k-512x512_20221030_182724-3a9cfe45.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512/maskformer_r50-d32_8xb2-160k_ade20k-512x512_20221030_182724.json)                             |
+| MaskFormer | R-101-D32 | 512x512   | 160000  | 4.12     | A100           | 34.90  | 45.11 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512/maskformer_r101-d32_8xb2-160k_ade20k-512x512_20221031_223053-84adbfcb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512/maskformer_r101-d32_8xb2-160k_ade20k-512x512_20221031_223053.json)                         |
+| MaskFormer | Swin-T    | 512x512   | 160000  | 3.73     | A100           | 40.53  | 46.69 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512_20221114_232813-f14e7ce0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512_20221114_232813.json) |
+| MaskFormer | Swin-S    | 512x512   | 160000  | 5.33     | A100           | 26.98  | 49.36 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512_20221115_114710-723512c7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512_20221115_114710.json) |
 
 Note:
 
diff --git a/configs/mobilenet_v2/README.md b/configs/mobilenet_v2/README.md
index 6d8e5945cb..bff5259129 100644
--- a/configs/mobilenet_v2/README.md
+++ b/configs/mobilenet_v2/README.md
@@ -27,21 +27,21 @@ The MobileNetV2 architecture is based on an inverted residual structure where th
 
 ### Cityscapes
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                                                                 |
-| ---------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN        | M-V2-D8  | 512x1024  |   80000 |      3.4 | 14.2           | A100   | 71.19 | 73.34         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024-20230224_185436-13fef4ea.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024_20230224_185436.json) |
-| PSPNet     | M-V2-D8  | 512x1024  |   80000 |      3.6 | 11.2           | V100   | 70.23 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_pspnet_4xb2-80k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x1024_80k_cityscapes/pspnet_m-v2-d8_512x1024_80k_cityscapes_20200825_124817-19e81d51.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x1024_80k_cityscapes/pspnet_m-v2-d8_512x1024_80k_cityscapes-20200825_124817.log.json)                                     |
-| DeepLabV3  | M-V2-D8  | 512x1024  |   80000 |      3.9 | 8.4            | V100   | 73.84 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3_4xb2-80k_cityscapes-512x1024.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x1024_80k_cityscapes/deeplabv3_m-v2-d8_512x1024_80k_cityscapes_20200825_124836-bef03590.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x1024_80k_cityscapes/deeplabv3_m-v2-d8_512x1024_80k_cityscapes-20200825_124836.log.json)                         |
-| DeepLabV3+ | M-V2-D8  | 512x1024  |   80000 |      5.1 | 8.4            | V100   | 75.20 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3plus_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes_20200825_124836-d256dd4b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes-20200825_124836.log.json)         |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                              | download                                                                                                                                                                                                                                                                                                                                                                                                 |
+| ---------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | --------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN        | M-V2-D8  | 512x1024  |   80000 |      3.4 | 14.2           | A100   | 71.19 | 73.34         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mobilenet_v2/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024-20230224_185436-13fef4ea.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024/mobilenet-v2-d8_fcn_4xb2-80k_cityscapes-512x1024_20230224_185436.json) |
+| PSPNet     | M-V2-D8  | 512x1024  |   80000 |      3.6 | 11.2           | V100   | 70.23 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mobilenet_v2/mobilenet-v2-d8_pspnet_4xb2-80k_cityscapes-512x1024.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x1024_80k_cityscapes/pspnet_m-v2-d8_512x1024_80k_cityscapes_20200825_124817-19e81d51.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x1024_80k_cityscapes/pspnet_m-v2-d8_512x1024_80k_cityscapes-20200825_124817.log.json)                                     |
+| DeepLabV3  | M-V2-D8  | 512x1024  |   80000 |      3.9 | 8.4            | V100   | 73.84 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3_4xb2-80k_cityscapes-512x1024.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x1024_80k_cityscapes/deeplabv3_m-v2-d8_512x1024_80k_cityscapes_20200825_124836-bef03590.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x1024_80k_cityscapes/deeplabv3_m-v2-d8_512x1024_80k_cityscapes-20200825_124836.log.json)                         |
+| DeepLabV3+ | M-V2-D8  | 512x1024  |   80000 |      5.1 | 8.4            | V100   | 75.20 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3plus_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes_20200825_124836-d256dd4b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes-20200825_124836.log.json)         |
 
 ### ADE20K
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                             | download                                                                                                                                                                                                                                                                                                                                                                         |
-| ---------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN        | M-V2-D8  | 512x512   |  160000 |      6.5 | 64.4           | V100   | 19.71 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_fcn_4xb4-160k_ade20k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/fcn_m-v2-d8_512x512_160k_ade20k/fcn_m-v2-d8_512x512_160k_ade20k_20200825_214953-c40e1095.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/fcn_m-v2-d8_512x512_160k_ade20k/fcn_m-v2-d8_512x512_160k_ade20k-20200825_214953.log.json)                                         |
-| PSPNet     | M-V2-D8  | 512x512   |  160000 |      6.5 | 57.7           | V100   | 29.68 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_pspnet_4xb4-160k_ade20k-512x512.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x512_160k_ade20k/pspnet_m-v2-d8_512x512_160k_ade20k_20200825_214953-f5942f7a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x512_160k_ade20k/pspnet_m-v2-d8_512x512_160k_ade20k-20200825_214953.log.json)                             |
-| DeepLabV3  | M-V2-D8  | 512x512   |  160000 |      6.8 | 39.9           | V100   | 34.08 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3_4xb4-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x512_160k_ade20k/deeplabv3_m-v2-d8_512x512_160k_ade20k_20200825_223255-63986343.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x512_160k_ade20k/deeplabv3_m-v2-d8_512x512_160k_ade20k-20200825_223255.log.json)                 |
-| DeepLabV3+ | M-V2-D8  | 512x512   |  160000 |      8.2 | 43.1           | V100   | 34.02 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3plus_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x512_160k_ade20k/deeplabv3plus_m-v2-d8_512x512_160k_ade20k_20200825_223255-465a01d4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x512_160k_ade20k/deeplabv3plus_m-v2-d8_512x512_160k_ade20k-20200825_223255.log.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                                                         |
+| ---------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN        | M-V2-D8  | 512x512   |  160000 |      6.5 | 64.4           | V100   | 19.71 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mobilenet_v2/mobilenet-v2-d8_fcn_4xb4-160k_ade20k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/fcn_m-v2-d8_512x512_160k_ade20k/fcn_m-v2-d8_512x512_160k_ade20k_20200825_214953-c40e1095.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/fcn_m-v2-d8_512x512_160k_ade20k/fcn_m-v2-d8_512x512_160k_ade20k-20200825_214953.log.json)                                         |
+| PSPNet     | M-V2-D8  | 512x512   |  160000 |      6.5 | 57.7           | V100   | 29.68 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mobilenet_v2/mobilenet-v2-d8_pspnet_4xb4-160k_ade20k-512x512.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x512_160k_ade20k/pspnet_m-v2-d8_512x512_160k_ade20k_20200825_214953-f5942f7a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x512_160k_ade20k/pspnet_m-v2-d8_512x512_160k_ade20k-20200825_214953.log.json)                             |
+| DeepLabV3  | M-V2-D8  | 512x512   |  160000 |      6.8 | 39.9           | V100   | 34.08 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3_4xb4-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x512_160k_ade20k/deeplabv3_m-v2-d8_512x512_160k_ade20k_20200825_223255-63986343.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x512_160k_ade20k/deeplabv3_m-v2-d8_512x512_160k_ade20k-20200825_223255.log.json)                 |
+| DeepLabV3+ | M-V2-D8  | 512x512   |  160000 |      8.2 | 43.1           | V100   | 34.02 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mobilenet_v2/mobilenet-v2-d8_deeplabv3plus_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x512_160k_ade20k/deeplabv3plus_m-v2-d8_512x512_160k_ade20k_20200825_223255-465a01d4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x512_160k_ade20k/deeplabv3plus_m-v2-d8_512x512_160k_ade20k-20200825_223255.log.json) |
 
 ## Citation
 
diff --git a/configs/mobilenet_v3/README.md b/configs/mobilenet_v3/README.md
index 3b63db7e50..8ed0a5692a 100644
--- a/configs/mobilenet_v3/README.md
+++ b/configs/mobilenet_v3/README.md
@@ -28,12 +28,12 @@ We present the next generation of MobileNets based on a combination of complemen
 
 ### Cityscapes
 
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                                                                     |
-| ------ | ------------------ | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| LRASPP | M-V3-D8            | 512x1024  |  320000 |      8.9 | 15.22          | V100   | 69.54 | 70.89         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v3/mobilenet-v3-d8_lraspp_4xb4-320k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_512x1024_320k_cityscapes/lraspp_m-v3-d8_512x1024_320k_cityscapes_20201224_220337-cfe8fb07.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_512x1024_320k_cityscapes/lraspp_m-v3-d8_512x1024_320k_cityscapes-20201224_220337.log.json)                                     |
-| LRASPP | M-V3-D8 (scratch)  | 512x1024  |  320000 |      8.9 | 14.77          | V100   | 67.87 | 69.78         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v3/mobilenet-v3-d8-scratch_lraspp_4xb4-320k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes_20201224_220337-9f29cd72.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes-20201224_220337.log.json)     |
-| LRASPP | M-V3s-D8           | 512x1024  |  320000 |      5.3 | 23.64          | V100   | 64.11 | 66.42         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v3/mobilenet-v3-d8-s_lraspp_4xb4-320k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_512x1024_320k_cityscapes/lraspp_m-v3s-d8_512x1024_320k_cityscapes_20201224_223935-61565b34.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_512x1024_320k_cityscapes/lraspp_m-v3s-d8_512x1024_320k_cityscapes-20201224_223935.log.json)                                 |
-| LRASPP | M-V3s-D8 (scratch) | 512x1024  |  320000 |      5.3 | 24.50          | V100   | 62.74 | 65.01         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/mobilenet_v3/mobilenet-v3-d8-scratch-s_lraspp_4xb4-320k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes_20201224_223935-03daeabb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes-20201224_223935.log.json) |
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                                  | download                                                                                                                                                                                                                                                                                                                                                                                                     |
+| ------ | ------------------ | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| LRASPP | M-V3-D8            | 512x1024  |  320000 |      8.9 | 15.22          | V100   | 69.54 | 70.89         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mobilenet_v3/mobilenet-v3-d8_lraspp_4xb4-320k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_512x1024_320k_cityscapes/lraspp_m-v3-d8_512x1024_320k_cityscapes_20201224_220337-cfe8fb07.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_512x1024_320k_cityscapes/lraspp_m-v3-d8_512x1024_320k_cityscapes-20201224_220337.log.json)                                     |
+| LRASPP | M-V3-D8 (scratch)  | 512x1024  |  320000 |      8.9 | 14.77          | V100   | 67.87 | 69.78         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mobilenet_v3/mobilenet-v3-d8-scratch_lraspp_4xb4-320k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes_20201224_220337-9f29cd72.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes-20201224_220337.log.json)     |
+| LRASPP | M-V3s-D8           | 512x1024  |  320000 |      5.3 | 23.64          | V100   | 64.11 | 66.42         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mobilenet_v3/mobilenet-v3-d8-s_lraspp_4xb4-320k_cityscapes-512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_512x1024_320k_cityscapes/lraspp_m-v3s-d8_512x1024_320k_cityscapes_20201224_223935-61565b34.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_512x1024_320k_cityscapes/lraspp_m-v3s-d8_512x1024_320k_cityscapes-20201224_223935.log.json)                                 |
+| LRASPP | M-V3s-D8 (scratch) | 512x1024  |  320000 |      5.3 | 24.50          | V100   | 62.74 | 65.01         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mobilenet_v3/mobilenet-v3-d8-scratch-s_lraspp_4xb4-320k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes_20201224_223935-03daeabb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes-20201224_223935.log.json) |
 
 ## Citation
 
diff --git a/configs/nonlocal_net/README.md b/configs/nonlocal_net/README.md
index 0a0fcf3725..4c3f49f981 100644
--- a/configs/nonlocal_net/README.md
+++ b/configs/nonlocal_net/README.md
@@ -26,34 +26,34 @@ Both convolutional and recurrent operations are building blocks that process one
 
 ### Cityscapes
 
-| Method      | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                    | download                                                                                                                                                                                                                                                                                                                                                                     |
-| ----------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| NonLocalNet | R-50-D8  | 512x1024  |   40000 | 7.4      | 2.72           | V100   | 78.24 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_40k_cityscapes/nonlocal_r50-d8_512x1024_40k_cityscapes_20200605_210748-c75e81e3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_40k_cityscapes/nonlocal_r50-d8_512x1024_40k_cityscapes_20200605_210748.log.json)     |
-| NonLocalNet | R-101-D8 | 512x1024  |   40000 | 10.9     | 1.95           | V100   | 78.66 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_40k_cityscapes/nonlocal_r101-d8_512x1024_40k_cityscapes_20200605_210748-d63729fa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_40k_cityscapes/nonlocal_r101-d8_512x1024_40k_cityscapes_20200605_210748.log.json) |
-| NonLocalNet | R-50-D8  | 769x769   |   40000 | 8.9      | 1.52           | V100   | 78.33 | 79.92         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_40k_cityscapes/nonlocal_r50-d8_769x769_40k_cityscapes_20200530_045243-82ef6749.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_40k_cityscapes/nonlocal_r50-d8_769x769_40k_cityscapes_20200530_045243.log.json)         |
-| NonLocalNet | R-101-D8 | 769x769   |   40000 | 12.8     | 1.05           | V100   | 78.57 | 80.29         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_40k_cityscapes/nonlocal_r101-d8_769x769_40k_cityscapes_20200530_045348-8fe9a9dc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_40k_cityscapes/nonlocal_r101-d8_769x769_40k_cityscapes_20200530_045348.log.json)     |
-| NonLocalNet | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 78.01 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_80k_cityscapes/nonlocal_r50-d8_512x1024_80k_cityscapes_20200607_193518-d6839fae.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_80k_cityscapes/nonlocal_r50-d8_512x1024_80k_cityscapes_20200607_193518.log.json)     |
-| NonLocalNet | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 78.93 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_80k_cityscapes/nonlocal_r101-d8_512x1024_80k_cityscapes_20200607_183411-32700183.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_80k_cityscapes/nonlocal_r101-d8_512x1024_80k_cityscapes_20200607_183411.log.json) |
-| NonLocalNet | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 79.05 | 80.68         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_80k_cityscapes/nonlocal_r50-d8_769x769_80k_cityscapes_20200607_193506-1f9792f6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_80k_cityscapes/nonlocal_r50-d8_769x769_80k_cityscapes_20200607_193506.log.json)         |
-| NonLocalNet | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 79.40 | 80.85         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_80k_cityscapes/nonlocal_r101-d8_769x769_80k_cityscapes_20200607_183428-0e1fa4f9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_80k_cityscapes/nonlocal_r101-d8_769x769_80k_cityscapes_20200607_183428.log.json)     |
+| Method      | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                                     |
+| ----------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| NonLocalNet | R-50-D8  | 512x1024  |   40000 | 7.4      | 2.72           | V100   | 78.24 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/nonlocal_net/nonlocal_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_40k_cityscapes/nonlocal_r50-d8_512x1024_40k_cityscapes_20200605_210748-c75e81e3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_40k_cityscapes/nonlocal_r50-d8_512x1024_40k_cityscapes_20200605_210748.log.json)     |
+| NonLocalNet | R-101-D8 | 512x1024  |   40000 | 10.9     | 1.95           | V100   | 78.66 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/nonlocal_net/nonlocal_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_40k_cityscapes/nonlocal_r101-d8_512x1024_40k_cityscapes_20200605_210748-d63729fa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_40k_cityscapes/nonlocal_r101-d8_512x1024_40k_cityscapes_20200605_210748.log.json) |
+| NonLocalNet | R-50-D8  | 769x769   |   40000 | 8.9      | 1.52           | V100   | 78.33 | 79.92         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/nonlocal_net/nonlocal_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_40k_cityscapes/nonlocal_r50-d8_769x769_40k_cityscapes_20200530_045243-82ef6749.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_40k_cityscapes/nonlocal_r50-d8_769x769_40k_cityscapes_20200530_045243.log.json)         |
+| NonLocalNet | R-101-D8 | 769x769   |   40000 | 12.8     | 1.05           | V100   | 78.57 | 80.29         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/nonlocal_net/nonlocal_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_40k_cityscapes/nonlocal_r101-d8_769x769_40k_cityscapes_20200530_045348-8fe9a9dc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_40k_cityscapes/nonlocal_r101-d8_769x769_40k_cityscapes_20200530_045348.log.json)     |
+| NonLocalNet | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 78.01 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/nonlocal_net/nonlocal_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_80k_cityscapes/nonlocal_r50-d8_512x1024_80k_cityscapes_20200607_193518-d6839fae.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_80k_cityscapes/nonlocal_r50-d8_512x1024_80k_cityscapes_20200607_193518.log.json)     |
+| NonLocalNet | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 78.93 | -             | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/nonlocal_net/nonlocal_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_80k_cityscapes/nonlocal_r101-d8_512x1024_80k_cityscapes_20200607_183411-32700183.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_80k_cityscapes/nonlocal_r101-d8_512x1024_80k_cityscapes_20200607_183411.log.json) |
+| NonLocalNet | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 79.05 | 80.68         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/nonlocal_net/nonlocal_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_80k_cityscapes/nonlocal_r50-d8_769x769_80k_cityscapes_20200607_193506-1f9792f6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_80k_cityscapes/nonlocal_r50-d8_769x769_80k_cityscapes_20200607_193506.log.json)         |
+| NonLocalNet | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 79.40 | 80.85         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/nonlocal_net/nonlocal_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_80k_cityscapes/nonlocal_r101-d8_769x769_80k_cityscapes_20200607_183428-0e1fa4f9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_80k_cityscapes/nonlocal_r101-d8_769x769_80k_cityscapes_20200607_183428.log.json)     |
 
 ### ADE20K
 
-| Method      | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                | download                                                                                                                                                                                                                                                                                                                                                     |
-| ----------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| NonLocalNet | R-50-D8  | 512x512   |   80000 | 9.1      | 21.37          | V100   | 40.75 |         42.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_80k_ade20k/nonlocal_r50-d8_512x512_80k_ade20k_20200615_015801-5ae0aa33.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_80k_ade20k/nonlocal_r50-d8_512x512_80k_ade20k_20200615_015801.log.json)         |
-| NonLocalNet | R-101-D8 | 512x512   |   80000 | 12.6     | 13.97          | V100   | 42.90 |         44.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_80k_ade20k/nonlocal_r101-d8_512x512_80k_ade20k_20200615_015758-24105919.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_80k_ade20k/nonlocal_r101-d8_512x512_80k_ade20k_20200615_015758.log.json)     |
-| NonLocalNet | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 42.03 |         43.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_160k_ade20k/nonlocal_r50-d8_512x512_160k_ade20k_20200616_005410-baef45e3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_160k_ade20k/nonlocal_r50-d8_512x512_160k_ade20k_20200616_005410.log.json)     |
-| NonLocalNet | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 44.63 |         45.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k/nonlocal_r101-d8_512x512_160k_ade20k_20210827_221502-7881aa1a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k/nonlocal_r101-d8_512x512_160k_ade20k_20210827_221502.log.json) |
+| Method      | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                             | download                                                                                                                                                                                                                                                                                                                                                     |
+| ----------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| NonLocalNet | R-50-D8  | 512x512   |   80000 | 9.1      | 21.37          | V100   | 40.75 |         42.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/nonlocal_net/nonlocal_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_80k_ade20k/nonlocal_r50-d8_512x512_80k_ade20k_20200615_015801-5ae0aa33.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_80k_ade20k/nonlocal_r50-d8_512x512_80k_ade20k_20200615_015801.log.json)         |
+| NonLocalNet | R-101-D8 | 512x512   |   80000 | 12.6     | 13.97          | V100   | 42.90 |         44.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/nonlocal_net/nonlocal_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_80k_ade20k/nonlocal_r101-d8_512x512_80k_ade20k_20200615_015758-24105919.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_80k_ade20k/nonlocal_r101-d8_512x512_80k_ade20k_20200615_015758.log.json)     |
+| NonLocalNet | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 42.03 |         43.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/nonlocal_net/nonlocal_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_160k_ade20k/nonlocal_r50-d8_512x512_160k_ade20k_20200616_005410-baef45e3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_160k_ade20k/nonlocal_r50-d8_512x512_160k_ade20k_20200616_005410.log.json)     |
+| NonLocalNet | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 44.63 |         45.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/nonlocal_net/nonlocal_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k/nonlocal_r101-d8_512x512_160k_ade20k_20210827_221502-7881aa1a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k/nonlocal_r101-d8_512x512_160k_ade20k_20210827_221502.log.json) |
 
 ### Pascal VOC 2012 + Aug
 
-| Method      | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                         |
-| ----------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| NonLocalNet | R-50-D8  | 512x512   |   20000 | 6.4      | 21.21          | V100   | 76.20 |         77.12 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_20k_voc12aug/nonlocal_r50-d8_512x512_20k_voc12aug_20200617_222613-07f2a57c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_20k_voc12aug/nonlocal_r50-d8_512x512_20k_voc12aug_20200617_222613.log.json)     |
-| NonLocalNet | R-101-D8 | 512x512   |   20000 | 9.8      | 14.01          | V100   | 78.15 |         78.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_20k_voc12aug/nonlocal_r101-d8_512x512_20k_voc12aug_20200617_222615-948c68ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_20k_voc12aug/nonlocal_r101-d8_512x512_20k_voc12aug_20200617_222615.log.json) |
-| NonLocalNet | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 76.65 |         77.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_40k_voc12aug/nonlocal_r50-d8_512x512_40k_voc12aug_20200614_000028-0139d4a9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_40k_voc12aug/nonlocal_r50-d8_512x512_40k_voc12aug_20200614_000028.log.json)     |
-| NonLocalNet | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 78.27 |         79.12 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/nonlocal_net/nonlocal_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_40k_voc12aug/nonlocal_r101-d8_512x512_40k_voc12aug_20200614_000028-7e5ff470.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_40k_voc12aug/nonlocal_r101-d8_512x512_40k_voc12aug_20200614_000028.log.json) |
+| Method      | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                              | download                                                                                                                                                                                                                                                                                                                                                         |
+| ----------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| NonLocalNet | R-50-D8  | 512x512   |   20000 | 6.4      | 21.21          | V100   | 76.20 |         77.12 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/nonlocal_net/nonlocal_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_20k_voc12aug/nonlocal_r50-d8_512x512_20k_voc12aug_20200617_222613-07f2a57c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_20k_voc12aug/nonlocal_r50-d8_512x512_20k_voc12aug_20200617_222613.log.json)     |
+| NonLocalNet | R-101-D8 | 512x512   |   20000 | 9.8      | 14.01          | V100   | 78.15 |         78.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/nonlocal_net/nonlocal_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_20k_voc12aug/nonlocal_r101-d8_512x512_20k_voc12aug_20200617_222615-948c68ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_20k_voc12aug/nonlocal_r101-d8_512x512_20k_voc12aug_20200617_222615.log.json) |
+| NonLocalNet | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 76.65 |         77.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/nonlocal_net/nonlocal_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_40k_voc12aug/nonlocal_r50-d8_512x512_40k_voc12aug_20200614_000028-0139d4a9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_40k_voc12aug/nonlocal_r50-d8_512x512_40k_voc12aug_20200614_000028.log.json)     |
+| NonLocalNet | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 78.27 |         79.12 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/nonlocal_net/nonlocal_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_40k_voc12aug/nonlocal_r101-d8_512x512_40k_voc12aug_20200614_000028-7e5ff470.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_40k_voc12aug/nonlocal_r101-d8_512x512_40k_voc12aug_20200614_000028.log.json) |
 
 ## Citation
 
diff --git a/configs/ocrnet/README.md b/configs/ocrnet/README.md
index 5b078f59c2..628a3b1597 100644
--- a/configs/ocrnet/README.md
+++ b/configs/ocrnet/README.md
@@ -28,47 +28,47 @@ In this paper, we address the problem of semantic segmentation and focus on the
 
 #### HRNet backbone
 
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                         |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| OCRNet | HRNetV2p-W18-Small | 512x1024  |   40000 | 3.5      | 10.45          | A100   | 76.61 |         78.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024_20230227_145026-6c052a14.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024_20230227_145026.json) |
-| OCRNet | HRNetV2p-W18       | 512x1024  |   40000 | 4.7      | 7.50           | V100   | 77.72 |         79.49 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_40k_cityscapes/ocrnet_hr18_512x1024_40k_cityscapes_20200601_033320-401c5bdd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_40k_cityscapes/ocrnet_hr18_512x1024_40k_cityscapes_20200601_033320.log.json)                     |
-| OCRNet | HRNetV2p-W48       | 512x1024  |   40000 | 8        | 4.22           | V100   | 80.58 |         81.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb2-40k_cityscapes-512x1024.pyy)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_40k_cityscapes/ocrnet_hr48_512x1024_40k_cityscapes_20200601_033336-55b32491.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_40k_cityscapes/ocrnet_hr48_512x1024_40k_cityscapes_20200601_033336.log.json)                     |
-| OCRNet | HRNetV2p-W18-Small | 512x1024  |   80000 | -        | -              | V100   | 77.16 |         78.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_80k_cityscapes/ocrnet_hr18s_512x1024_80k_cityscapes_20200601_222735-55979e63.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_80k_cityscapes/ocrnet_hr18s_512x1024_80k_cityscapes_20200601_222735.log.json)                 |
-| OCRNet | HRNetV2p-W18       | 512x1024  |   80000 | -        | -              | V100   | 78.57 |         80.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_80k_cityscapes/ocrnet_hr18_512x1024_80k_cityscapes_20200614_230521-c2e1dd4a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_80k_cityscapes/ocrnet_hr18_512x1024_80k_cityscapes_20200614_230521.log.json)                     |
-| OCRNet | HRNetV2p-W48       | 512x1024  |   80000 | -        | -              | V100   | 80.70 |         81.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_80k_cityscapes/ocrnet_hr48_512x1024_80k_cityscapes_20200601_222752-9076bcdf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_80k_cityscapes/ocrnet_hr48_512x1024_80k_cityscapes_20200601_222752.log.json)                     |
-| OCRNet | HRNetV2p-W18-Small | 512x1024  |  160000 | -        | -              | V100   | 78.45 |         79.97 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb2-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_160k_cityscapes/ocrnet_hr18s_512x1024_160k_cityscapes_20200602_191005-f4a7af28.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_160k_cityscapes/ocrnet_hr18s_512x1024_160k_cityscapes_20200602_191005.log.json)             |
-| OCRNet | HRNetV2p-W18       | 512x1024  |  160000 | -        | -              | V100   | 79.47 |         80.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb2-160k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_160k_cityscapes/ocrnet_hr18_512x1024_160k_cityscapes_20200602_191001-b9172d0c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_160k_cityscapes/ocrnet_hr18_512x1024_160k_cityscapes_20200602_191001.log.json)                 |
-| OCRNet | HRNetV2p-W48       | 512x1024  |  160000 | -        | -              | V100   | 81.35 |         82.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb2-160k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_160k_cityscapes/ocrnet_hr48_512x1024_160k_cityscapes_20200602_191037-dfbf1b0c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_160k_cityscapes/ocrnet_hr48_512x1024_160k_cityscapes_20200602_191037.log.json)                 |
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                         |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| OCRNet | HRNetV2p-W18-Small | 512x1024  |   40000 | 3.5      | 10.45          | A100   | 76.61 |         78.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024_20230227_145026-6c052a14.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024_20230227_145026.json) |
+| OCRNet | HRNetV2p-W18       | 512x1024  |   40000 | 4.7      | 7.50           | V100   | 77.72 |         79.49 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr18_4xb2-40k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_40k_cityscapes/ocrnet_hr18_512x1024_40k_cityscapes_20200601_033320-401c5bdd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_40k_cityscapes/ocrnet_hr18_512x1024_40k_cityscapes_20200601_033320.log.json)                     |
+| OCRNet | HRNetV2p-W48       | 512x1024  |   40000 | 8        | 4.22           | V100   | 80.58 |         81.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr48_4xb2-40k_cityscapes-512x1024.pyy)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_40k_cityscapes/ocrnet_hr48_512x1024_40k_cityscapes_20200601_033336-55b32491.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_40k_cityscapes/ocrnet_hr48_512x1024_40k_cityscapes_20200601_033336.log.json)                     |
+| OCRNet | HRNetV2p-W18-Small | 512x1024  |   80000 | -        | -              | V100   | 77.16 |         78.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr18s_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_80k_cityscapes/ocrnet_hr18s_512x1024_80k_cityscapes_20200601_222735-55979e63.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_80k_cityscapes/ocrnet_hr18s_512x1024_80k_cityscapes_20200601_222735.log.json)                 |
+| OCRNet | HRNetV2p-W18       | 512x1024  |   80000 | -        | -              | V100   | 78.57 |         80.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr18_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_80k_cityscapes/ocrnet_hr18_512x1024_80k_cityscapes_20200614_230521-c2e1dd4a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_80k_cityscapes/ocrnet_hr18_512x1024_80k_cityscapes_20200614_230521.log.json)                     |
+| OCRNet | HRNetV2p-W48       | 512x1024  |   80000 | -        | -              | V100   | 80.70 |         81.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr48_4xb2-80k_cityscapes-512x1024.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_80k_cityscapes/ocrnet_hr48_512x1024_80k_cityscapes_20200601_222752-9076bcdf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_80k_cityscapes/ocrnet_hr48_512x1024_80k_cityscapes_20200601_222752.log.json)                     |
+| OCRNet | HRNetV2p-W18-Small | 512x1024  |  160000 | -        | -              | V100   | 78.45 |         79.97 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr18s_4xb2-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_160k_cityscapes/ocrnet_hr18s_512x1024_160k_cityscapes_20200602_191005-f4a7af28.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_160k_cityscapes/ocrnet_hr18s_512x1024_160k_cityscapes_20200602_191005.log.json)             |
+| OCRNet | HRNetV2p-W18       | 512x1024  |  160000 | -        | -              | V100   | 79.47 |         80.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr18_4xb2-160k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_160k_cityscapes/ocrnet_hr18_512x1024_160k_cityscapes_20200602_191001-b9172d0c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_160k_cityscapes/ocrnet_hr18_512x1024_160k_cityscapes_20200602_191001.log.json)                 |
+| OCRNet | HRNetV2p-W48       | 512x1024  |  160000 | -        | -              | V100   | 81.35 |         82.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr48_4xb2-160k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_160k_cityscapes/ocrnet_hr48_512x1024_160k_cityscapes_20200602_191037-dfbf1b0c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_160k_cityscapes/ocrnet_hr48_512x1024_160k_cityscapes_20200602_191037.log.json)                 |
 
 #### ResNet backbone
 
-| Method | Backbone | Crop Size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ---------- | ------- | -------- | -------------- | ------ | ----- | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| OCRNet | R-101-D8 | 512x1024  | 8          | 40000   | -        | -              | V100   | 80.09 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes/ocrnet_r101-d8_512x1024_40k_b8_cityscapes_20200717_110721-02ac0f13.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes/ocrnet_r101-d8_512x1024_40k_b8_cityscapes_20200717_110721.log.json)     |
-| OCRNet | R-101-D8 | 512x1024  | 16         | 40000   | 8.8      | 3.02           | V100   | 80.30 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_r101-d8_8xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes/ocrnet_r101-d8_512x1024_40k_b16_cityscapes_20200723_193726-db500f80.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes/ocrnet_r101-d8_512x1024_40k_b16_cityscapes_20200723_193726.log.json) |
-| OCRNet | R-101-D8 | 512x1024  | 16         | 80000   | 8.8      | 3.02           | V100   | 80.81 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_r101-d8_8xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes/ocrnet_r101-d8_512x1024_80k_b16_cityscapes_20200723_192421-78688424.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes/ocrnet_r101-d8_512x1024_80k_b16_cityscapes_20200723_192421.log.json) |
+| Method | Backbone | Crop Size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ---------- | ------- | -------- | -------------- | ------ | ----- | ------------: | ------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| OCRNet | R-101-D8 | 512x1024  | 8          | 40000   | -        | -              | V100   | 80.09 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes/ocrnet_r101-d8_512x1024_40k_b8_cityscapes_20200717_110721-02ac0f13.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes/ocrnet_r101-d8_512x1024_40k_b8_cityscapes_20200717_110721.log.json)     |
+| OCRNet | R-101-D8 | 512x1024  | 16         | 40000   | 8.8      | 3.02           | V100   | 80.30 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_r101-d8_8xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes/ocrnet_r101-d8_512x1024_40k_b16_cityscapes_20200723_193726-db500f80.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes/ocrnet_r101-d8_512x1024_40k_b16_cityscapes_20200723_193726.log.json) |
+| OCRNet | R-101-D8 | 512x1024  | 16         | 80000   | 8.8      | 3.02           | V100   | 80.81 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_r101-d8_8xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes/ocrnet_r101-d8_512x1024_80k_b16_cityscapes_20200723_192421-78688424.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes/ocrnet_r101-d8_512x1024_80k_b16_cityscapes_20200723_192421.log.json) |
 
 ### ADE20K
 
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                     | download                                                                                                                                                                                                                                                                                                                         |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| OCRNet | HRNetV2p-W18-Small | 512x512   |   80000 | 6.7      | 28.98          | V100   | 35.06 |         35.80 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_80k_ade20k/ocrnet_hr18s_512x512_80k_ade20k_20200615_055600-e80b62af.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_80k_ade20k/ocrnet_hr18s_512x512_80k_ade20k_20200615_055600.log.json)     |
-| OCRNet | HRNetV2p-W18       | 512x512   |   80000 | 7.9      | 18.93          | V100   | 37.79 |         39.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_80k_ade20k/ocrnet_hr18_512x512_80k_ade20k_20200615_053157-d173d83b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_80k_ade20k/ocrnet_hr18_512x512_80k_ade20k_20200615_053157.log.json)         |
-| OCRNet | HRNetV2p-W48       | 512x512   |   80000 | 11.2     | 16.99          | V100   | 43.00 |         44.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_80k_ade20k/ocrnet_hr48_512x512_80k_ade20k_20200615_021518-d168c2d1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_80k_ade20k/ocrnet_hr48_512x512_80k_ade20k_20200615_021518.log.json)         |
-| OCRNet | HRNetV2p-W18-Small | 512x512   |  160000 | -        | -              | V100   | 37.19 |         38.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_160k_ade20k/ocrnet_hr18s_512x512_160k_ade20k_20200615_184505-8e913058.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_160k_ade20k/ocrnet_hr18s_512x512_160k_ade20k_20200615_184505.log.json) |
-| OCRNet | HRNetV2p-W18       | 512x512   |  160000 | -        | -              | V100   | 39.32 |         40.80 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_160k_ade20k/ocrnet_hr18_512x512_160k_ade20k_20200615_200940-d8fcd9d1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_160k_ade20k/ocrnet_hr18_512x512_160k_ade20k_20200615_200940.log.json)     |
-| OCRNet | HRNetV2p-W48       | 512x512   |  160000 | -        | -              | V100   | 43.25 |         44.88 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_160k_ade20k/ocrnet_hr48_512x512_160k_ade20k_20200615_184705-a073726d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_160k_ade20k/ocrnet_hr48_512x512_160k_ade20k_20200615_184705.log.json)     |
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                                                         |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| OCRNet | HRNetV2p-W18-Small | 512x512   |   80000 | 6.7      | 28.98          | V100   | 35.06 |         35.80 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr18s_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_80k_ade20k/ocrnet_hr18s_512x512_80k_ade20k_20200615_055600-e80b62af.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_80k_ade20k/ocrnet_hr18s_512x512_80k_ade20k_20200615_055600.log.json)     |
+| OCRNet | HRNetV2p-W18       | 512x512   |   80000 | 7.9      | 18.93          | V100   | 37.79 |         39.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr18_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_80k_ade20k/ocrnet_hr18_512x512_80k_ade20k_20200615_053157-d173d83b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_80k_ade20k/ocrnet_hr18_512x512_80k_ade20k_20200615_053157.log.json)         |
+| OCRNet | HRNetV2p-W48       | 512x512   |   80000 | 11.2     | 16.99          | V100   | 43.00 |         44.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr48_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_80k_ade20k/ocrnet_hr48_512x512_80k_ade20k_20200615_021518-d168c2d1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_80k_ade20k/ocrnet_hr48_512x512_80k_ade20k_20200615_021518.log.json)         |
+| OCRNet | HRNetV2p-W18-Small | 512x512   |  160000 | -        | -              | V100   | 37.19 |         38.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr18s_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_160k_ade20k/ocrnet_hr18s_512x512_160k_ade20k_20200615_184505-8e913058.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_160k_ade20k/ocrnet_hr18s_512x512_160k_ade20k_20200615_184505.log.json) |
+| OCRNet | HRNetV2p-W18       | 512x512   |  160000 | -        | -              | V100   | 39.32 |         40.80 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr18_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_160k_ade20k/ocrnet_hr18_512x512_160k_ade20k_20200615_200940-d8fcd9d1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_160k_ade20k/ocrnet_hr18_512x512_160k_ade20k_20200615_200940.log.json)     |
+| OCRNet | HRNetV2p-W48       | 512x512   |  160000 | -        | -              | V100   | 43.25 |         44.88 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr48_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_160k_ade20k/ocrnet_hr48_512x512_160k_ade20k_20200615_184705-a073726d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_160k_ade20k/ocrnet_hr48_512x512_160k_ade20k_20200615_184705.log.json)     |
 
 ### Pascal VOC 2012 + Aug
 
-| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                             |
-| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| OCRNet | HRNetV2p-W18-Small | 512x512   |   20000 | 3.5      | 31.55          | V100   | 71.70 |         73.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_20k_voc12aug/ocrnet_hr18s_512x512_20k_voc12aug_20200617_233913-02b04fcb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_20k_voc12aug/ocrnet_hr18s_512x512_20k_voc12aug_20200617_233913.log.json) |
-| OCRNet | HRNetV2p-W18       | 512x512   |   20000 | 4.7      | 19.91          | V100   | 74.75 |         77.11 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_20k_voc12aug/ocrnet_hr18_512x512_20k_voc12aug_20200617_233932-8954cbb7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_20k_voc12aug/ocrnet_hr18_512x512_20k_voc12aug_20200617_233932.log.json)     |
-| OCRNet | HRNetV2p-W48       | 512x512   |   20000 | 8.1      | 17.83          | V100   | 77.72 |         79.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_20k_voc12aug/ocrnet_hr48_512x512_20k_voc12aug_20200617_233932-9e82080a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_20k_voc12aug/ocrnet_hr48_512x512_20k_voc12aug_20200617_233932.log.json)     |
-| OCRNet | HRNetV2p-W18-Small | 512x512   |   40000 | -        | -              | V100   | 72.76 |         74.60 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18s_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_40k_voc12aug/ocrnet_hr18s_512x512_40k_voc12aug_20200614_002025-42b587ac.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_40k_voc12aug/ocrnet_hr18s_512x512_40k_voc12aug_20200614_002025.log.json) |
-| OCRNet | HRNetV2p-W18       | 512x512   |   40000 | -        | -              | V100   | 74.98 |         77.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr18_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_40k_voc12aug/ocrnet_hr18_512x512_40k_voc12aug_20200614_015958-714302be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_40k_voc12aug/ocrnet_hr18_512x512_40k_voc12aug_20200614_015958.log.json)     |
-| OCRNet | HRNetV2p-W48       | 512x512   |   40000 | -        | -              | V100   | 77.14 |         79.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/ocrnet/ocrnet_hr48_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_40k_voc12aug/ocrnet_hr48_512x512_40k_voc12aug_20200614_015958-255bc5ce.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_40k_voc12aug/ocrnet_hr48_512x512_40k_voc12aug_20200614_015958.log.json)     |
+| Method | Backbone           | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                    | download                                                                                                                                                                                                                                                                                                                             |
+| ------ | ------------------ | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| OCRNet | HRNetV2p-W18-Small | 512x512   |   20000 | 3.5      | 31.55          | V100   | 71.70 |         73.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr18s_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_20k_voc12aug/ocrnet_hr18s_512x512_20k_voc12aug_20200617_233913-02b04fcb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_20k_voc12aug/ocrnet_hr18s_512x512_20k_voc12aug_20200617_233913.log.json) |
+| OCRNet | HRNetV2p-W18       | 512x512   |   20000 | 4.7      | 19.91          | V100   | 74.75 |         77.11 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr18_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_20k_voc12aug/ocrnet_hr18_512x512_20k_voc12aug_20200617_233932-8954cbb7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_20k_voc12aug/ocrnet_hr18_512x512_20k_voc12aug_20200617_233932.log.json)     |
+| OCRNet | HRNetV2p-W48       | 512x512   |   20000 | 8.1      | 17.83          | V100   | 77.72 |         79.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr48_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_20k_voc12aug/ocrnet_hr48_512x512_20k_voc12aug_20200617_233932-9e82080a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_20k_voc12aug/ocrnet_hr48_512x512_20k_voc12aug_20200617_233932.log.json)     |
+| OCRNet | HRNetV2p-W18-Small | 512x512   |   40000 | -        | -              | V100   | 72.76 |         74.60 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr18s_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_40k_voc12aug/ocrnet_hr18s_512x512_40k_voc12aug_20200614_002025-42b587ac.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_40k_voc12aug/ocrnet_hr18s_512x512_40k_voc12aug_20200614_002025.log.json) |
+| OCRNet | HRNetV2p-W18       | 512x512   |   40000 | -        | -              | V100   | 74.98 |         77.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr18_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_40k_voc12aug/ocrnet_hr18_512x512_40k_voc12aug_20200614_015958-714302be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_40k_voc12aug/ocrnet_hr18_512x512_40k_voc12aug_20200614_015958.log.json)     |
+| OCRNet | HRNetV2p-W48       | 512x512   |   40000 | -        | -              | V100   | 77.14 |         79.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet/ocrnet_hr48_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_40k_voc12aug/ocrnet_hr48_512x512_40k_voc12aug_20200614_015958-255bc5ce.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_40k_voc12aug/ocrnet_hr48_512x512_40k_voc12aug_20200614_015958.log.json)     |
 
 ## Citation
 
diff --git a/configs/pidnet/README.md b/configs/pidnet/README.md
index c8c3f24799..e23efbd3f3 100644
--- a/configs/pidnet/README.md
+++ b/configs/pidnet/README.md
@@ -8,7 +8,7 @@
 
 <a href="https://github.com/XuJiacong/PIDNet">Official Repo</a>
 
-<a href="https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/pidnet.py">Code Snippet</a>
+<a href="https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/backbones/pidnet.py">Code Snippet</a>
 
 ## Abstract
 
@@ -26,11 +26,11 @@ Two-branch network architecture has shown its efficiency and effectiveness for r
 
 ### Cityscapes
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | ----------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PIDNet | PIDNet-S | 1024x1024 | 120000  | 3.38     | 80.82          | A100   | 78.74 | 80.87         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700-bb8e3bcc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700.json) |
-| PIDNet | PIDNet-M | 1024x1024 | 120000  | 5.14     | 71.98          | A100   | 80.22 | 82.05         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452-f9bcdbf3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452.json) |
-| PIDNet | PIDNet-L | 1024x1024 | 120000  | 5.83     | 60.06          | A100   | 80.89 | 82.37         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514-0783ca6b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | -------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PIDNet | PIDNet-S | 1024x1024 | 120000  | 3.38     | 80.82          | A100   | 78.74 | 80.87         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700-bb8e3bcc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700.json) |
+| PIDNet | PIDNet-M | 1024x1024 | 120000  | 5.14     | 71.98          | A100   | 80.22 | 82.05         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452-f9bcdbf3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452.json) |
+| PIDNet | PIDNet-L | 1024x1024 | 120000  | 5.83     | 60.06          | A100   | 80.89 | 82.37         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514-0783ca6b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514.json) |
 
 ## Notes
 
diff --git a/configs/pidnet/metafile.yaml b/configs/pidnet/metafile.yaml
index 9102ec51c5..51b514a487 100644
--- a/configs/pidnet/metafile.yaml
+++ b/configs/pidnet/metafile.yaml
@@ -33,7 +33,7 @@ Models:
   Paper:
     Title: 'PIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller'
     URL: https://arxiv.org/pdf/2206.02066.pdf
-  Code: https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/pidnet.py
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/backbones/pidnet.py
   Framework: PyTorch
 - Name: pidnet-m_2xb6-120k_1024x1024-cityscapes
   In Collection: PIDNet
@@ -57,7 +57,7 @@ Models:
   Paper:
     Title: 'PIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller'
     URL: https://arxiv.org/pdf/2206.02066.pdf
-  Code: https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/pidnet.py
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/backbones/pidnet.py
   Framework: PyTorch
 - Name: pidnet-l_2xb6-120k_1024x1024-cityscapes
   In Collection: PIDNet
@@ -81,5 +81,5 @@ Models:
   Paper:
     Title: 'PIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller'
     URL: https://arxiv.org/pdf/2206.02066.pdf
-  Code: https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/pidnet.py
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/backbones/pidnet.py
   Framework: PyTorch
diff --git a/configs/point_rend/README.md b/configs/point_rend/README.md
index 9aab8e03ee..487d3bcc7f 100644
--- a/configs/point_rend/README.md
+++ b/configs/point_rend/README.md
@@ -26,17 +26,17 @@ We present a new method for efficient high-quality image segmentation of objects
 
 ### Cityscapes
 
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                | download                                                                                                                                                                                                                                                                                                                                                         |
-| --------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PointRend | R-50     | 512x1024  |   80000 |      3.1 | 8.48           | V100   | 76.47 | 78.13         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/point_rend/pointrend_r50_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x1024_80k_cityscapes/pointrend_r50_512x1024_80k_cityscapes_20200711_015821-bb1ff523.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x1024_80k_cityscapes/pointrend_r50_512x1024_80k_cityscapes-20200715_214714.log.json)     |
-| PointRend | R-101    | 512x1024  |   80000 |      4.2 | 7.00           | V100   | 78.30 | 79.97         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/point_rend/pointrend_r101_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x1024_80k_cityscapes/pointrend_r101_512x1024_80k_cityscapes_20200711_170850-d0ca84be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x1024_80k_cityscapes/pointrend_r101_512x1024_80k_cityscapes-20200715_214824.log.json) |
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                             | download                                                                                                                                                                                                                                                                                                                                                         |
+| --------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PointRend | R-50     | 512x1024  |   80000 |      3.1 | 8.48           | V100   | 76.47 | 78.13         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/point_rend/pointrend_r50_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x1024_80k_cityscapes/pointrend_r50_512x1024_80k_cityscapes_20200711_015821-bb1ff523.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x1024_80k_cityscapes/pointrend_r50_512x1024_80k_cityscapes-20200715_214714.log.json)     |
+| PointRend | R-101    | 512x1024  |   80000 |      4.2 | 7.00           | V100   | 78.30 | 79.97         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/point_rend/pointrend_r101_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x1024_80k_cityscapes/pointrend_r101_512x1024_80k_cityscapes_20200711_170850-d0ca84be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x1024_80k_cityscapes/pointrend_r101_512x1024_80k_cityscapes-20200715_214824.log.json) |
 
 ### ADE20K
 
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                         |
-| --------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| PointRend | R-50     | 512x512   |  160000 |      5.1 | 17.31          | V100   | 37.64 | 39.17         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/point_rend/pointrend_r50_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x512_160k_ade20k/pointrend_r50_512x512_160k_ade20k_20200807_232644-ac3febf2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x512_160k_ade20k/pointrend_r50_512x512_160k_ade20k-20200807_232644.log.json)     |
-| PointRend | R-101    | 512x512   |  160000 |      6.1 | 15.50          | V100   | 40.02 | 41.60         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/point_rend/pointrend_r101_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x512_160k_ade20k/pointrend_r101_512x512_160k_ade20k_20200808_030852-8834902a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x512_160k_ade20k/pointrend_r101_512x512_160k_ade20k-20200808_030852.log.json) |
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                         |
+| --------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| PointRend | R-50     | 512x512   |  160000 |      5.1 | 17.31          | V100   | 37.64 | 39.17         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/point_rend/pointrend_r50_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x512_160k_ade20k/pointrend_r50_512x512_160k_ade20k_20200807_232644-ac3febf2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x512_160k_ade20k/pointrend_r50_512x512_160k_ade20k-20200807_232644.log.json)     |
+| PointRend | R-101    | 512x512   |  160000 |      6.1 | 15.50          | V100   | 40.02 | 41.60         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/point_rend/pointrend_r101_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x512_160k_ade20k/pointrend_r101_512x512_160k_ade20k_20200808_030852-8834902a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x512_160k_ade20k/pointrend_r101_512x512_160k_ade20k-20200808_030852.log.json) |
 
 ## Citation
 
diff --git a/configs/poolformer/README.md b/configs/poolformer/README.md
index ba563a9928..987db33d98 100644
--- a/configs/poolformer/README.md
+++ b/configs/poolformer/README.md
@@ -48,13 +48,13 @@ pip install "mmcls>=1.0.0rc0"
 
 ### ADE20K
 
-| Method | Backbone       | Crop Size | pretrain    | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | mIoU\* | mIoU\*(ms+flip) | config                                                                                                                               | download                                                                                                                                                                                                                                                                                                                                                                     |
-| ------ | -------------- | --------- | ----------- | ---------- | ------- | -------- | -------------- | ------ | ----- | ------------: | ------ | --------------: | ------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FPN    | PoolFormer-S12 | 512x512   | ImageNet-1K | 32         | 40000   | 4.17     | 23.48          | V100   | 36.68 |             - | 37.07  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/poolformer/fpn_poolformer_s12_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k/fpn_poolformer_s12_8x4_512x512_40k_ade20k_20220501_115154-b5aa2f49.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k/fpn_poolformer_s12_8x4_512x512_40k_ade20k_20220501_115154.log.json) |
-| FPN    | PoolFormer-S24 | 512x512   | ImageNet-1K | 32         | 40000   | 5.47     | 15.74          | V100   | 40.12 |             - | 40.36  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/poolformer/fpn_poolformer_s24_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k/fpn_poolformer_s24_8x4_512x512_40k_ade20k_20220503_222049-394a7cf7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k/fpn_poolformer_s24_8x4_512x512_40k_ade20k_20220503_222049.log.json) |
-| FPN    | PoolFormer-S36 | 512x512   | ImageNet-1K | 32         | 40000   | 6.77     | 11.34          | V100   | 41.61 |             - | 41.81  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/poolformer/fpn_poolformer_s36_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s36_8x4_512x512_40k_ade20k/fpn_poolformer_s36_8x4_512x512_40k_ade20k_20220501_151122-b47e607d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s36_8x4_512x512_40k_ade20k/fpn_poolformer_s36_8x4_512x512_40k_ade20k_20220501_151122.log.json) |
-| FPN    | PoolFormer-M36 | 512x512   | ImageNet-1K | 32         | 40000   | 8.59     | 8.97           | V100   | 41.95 |             - | 42.35  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/poolformer/fpn_poolformer_m36_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k/fpn_poolformer_m36_8x4_512x512_40k_ade20k_20220501_164230-3dc83921.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k/fpn_poolformer_m36_8x4_512x512_40k_ade20k_20220501_164230.log.json) |
-| FPN    | PoolFormer-M48 | 512x512   | ImageNet-1K | 32         | 40000   | 10.48    | 6.69           | V100   | 42.43 |             - | 42.76  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/poolformer/fpn_poolformer_m48_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k/fpn_poolformer_m48_8x4_512x512_40k_ade20k_20220504_003923-64168d3b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k/fpn_poolformer_m48_8x4_512x512_40k_ade20k_20220504_003923.log.json) |
+| Method | Backbone       | Crop Size | pretrain    | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | mIoU\* | mIoU\*(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                                     |
+| ------ | -------------- | --------- | ----------- | ---------- | ------- | -------- | -------------- | ------ | ----- | ------------: | ------ | --------------: | --------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FPN    | PoolFormer-S12 | 512x512   | ImageNet-1K | 32         | 40000   | 4.17     | 23.48          | V100   | 36.68 |             - | 37.07  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/poolformer/fpn_poolformer_s12_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k/fpn_poolformer_s12_8x4_512x512_40k_ade20k_20220501_115154-b5aa2f49.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k/fpn_poolformer_s12_8x4_512x512_40k_ade20k_20220501_115154.log.json) |
+| FPN    | PoolFormer-S24 | 512x512   | ImageNet-1K | 32         | 40000   | 5.47     | 15.74          | V100   | 40.12 |             - | 40.36  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/poolformer/fpn_poolformer_s24_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k/fpn_poolformer_s24_8x4_512x512_40k_ade20k_20220503_222049-394a7cf7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k/fpn_poolformer_s24_8x4_512x512_40k_ade20k_20220503_222049.log.json) |
+| FPN    | PoolFormer-S36 | 512x512   | ImageNet-1K | 32         | 40000   | 6.77     | 11.34          | V100   | 41.61 |             - | 41.81  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/poolformer/fpn_poolformer_s36_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s36_8x4_512x512_40k_ade20k/fpn_poolformer_s36_8x4_512x512_40k_ade20k_20220501_151122-b47e607d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s36_8x4_512x512_40k_ade20k/fpn_poolformer_s36_8x4_512x512_40k_ade20k_20220501_151122.log.json) |
+| FPN    | PoolFormer-M36 | 512x512   | ImageNet-1K | 32         | 40000   | 8.59     | 8.97           | V100   | 41.95 |             - | 42.35  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/poolformer/fpn_poolformer_m36_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k/fpn_poolformer_m36_8x4_512x512_40k_ade20k_20220501_164230-3dc83921.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k/fpn_poolformer_m36_8x4_512x512_40k_ade20k_20220501_164230.log.json) |
+| FPN    | PoolFormer-M48 | 512x512   | ImageNet-1K | 32         | 40000   | 10.48    | 6.69           | V100   | 42.43 |             - | 42.76  |               - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/poolformer/fpn_poolformer_m48_8xb4-40k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k/fpn_poolformer_m48_8x4_512x512_40k_ade20k_20220504_003923-64168d3b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k/fpn_poolformer_m48_8x4_512x512_40k_ade20k_20220504_003923.log.json) |
 
 Note:
 
diff --git a/configs/psanet/README.md b/configs/psanet/README.md
index d657326120..1f5680fbab 100644
--- a/configs/psanet/README.md
+++ b/configs/psanet/README.md
@@ -26,34 +26,34 @@ We notice information flow in convolutional neural networksis  restricted  insid
 
 ### Cityscapes
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSANet | R-50-D8  | 512x1024  |   40000 | 7        | 3.17           | V100   | 77.63 |         79.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_40k_cityscapes/psanet_r50-d8_512x1024_40k_cityscapes_20200606_103117-99fac37c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_40k_cityscapes/psanet_r50-d8_512x1024_40k_cityscapes_20200606_103117.log.json)     |
-| PSANet | R-101-D8 | 512x1024  |   40000 | 10.5     | 2.20           | V100   | 79.14 |         80.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_40k_cityscapes/psanet_r101-d8_512x1024_40k_cityscapes_20200606_001418-27b9cfa7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_40k_cityscapes/psanet_r101-d8_512x1024_40k_cityscapes_20200606_001418.log.json) |
-| PSANet | R-50-D8  | 769x769   |   40000 | 7.9      | 1.40           | V100   | 77.99 |         79.64 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_40k_cityscapes/psanet_r50-d8_769x769_40k_cityscapes_20200530_033717-d5365506.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_40k_cityscapes/psanet_r50-d8_769x769_40k_cityscapes_20200530_033717.log.json)         |
-| PSANet | R-101-D8 | 769x769   |   40000 | 11.9     | 0.98           | V100   | 78.43 |         80.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_40k_cityscapes/psanet_r101-d8_769x769_40k_cityscapes_20200530_035107-997da1e6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_40k_cityscapes/psanet_r101-d8_769x769_40k_cityscapes_20200530_035107.log.json)     |
-| PSANet | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 77.24 |         78.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_80k_cityscapes/psanet_r50-d8_512x1024_80k_cityscapes_20200606_161842-ab60a24f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_80k_cityscapes/psanet_r50-d8_512x1024_80k_cityscapes_20200606_161842.log.json)     |
-| PSANet | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 79.31 |         80.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_80k_cityscapes/psanet_r101-d8_512x1024_80k_cityscapes_20200606_161823-0f73a169.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_80k_cityscapes/psanet_r101-d8_512x1024_80k_cityscapes_20200606_161823.log.json) |
-| PSANet | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 79.31 |         80.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_80k_cityscapes/psanet_r50-d8_769x769_80k_cityscapes_20200606_225134-fe42f49e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_80k_cityscapes/psanet_r50-d8_769x769_80k_cityscapes_20200606_225134.log.json)         |
-| PSANet | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 79.69 |         80.89 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_80k_cityscapes/psanet_r101-d8_769x769_80k_cityscapes_20200606_214550-7665827b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_80k_cityscapes/psanet_r101-d8_769x769_80k_cityscapes_20200606_214550.log.json)     |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSANet | R-50-D8  | 512x1024  |   40000 | 7        | 3.17           | V100   | 77.63 |         79.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/psanet/psanet_r50-d8_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_40k_cityscapes/psanet_r50-d8_512x1024_40k_cityscapes_20200606_103117-99fac37c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_40k_cityscapes/psanet_r50-d8_512x1024_40k_cityscapes_20200606_103117.log.json)     |
+| PSANet | R-101-D8 | 512x1024  |   40000 | 10.5     | 2.20           | V100   | 79.14 |         80.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/psanet/psanet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_40k_cityscapes/psanet_r101-d8_512x1024_40k_cityscapes_20200606_001418-27b9cfa7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_40k_cityscapes/psanet_r101-d8_512x1024_40k_cityscapes_20200606_001418.log.json) |
+| PSANet | R-50-D8  | 769x769   |   40000 | 7.9      | 1.40           | V100   | 77.99 |         79.64 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/psanet/psanet_r50-d8_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_40k_cityscapes/psanet_r50-d8_769x769_40k_cityscapes_20200530_033717-d5365506.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_40k_cityscapes/psanet_r50-d8_769x769_40k_cityscapes_20200530_033717.log.json)         |
+| PSANet | R-101-D8 | 769x769   |   40000 | 11.9     | 0.98           | V100   | 78.43 |         80.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/psanet/psanet_r101-d8_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_40k_cityscapes/psanet_r101-d8_769x769_40k_cityscapes_20200530_035107-997da1e6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_40k_cityscapes/psanet_r101-d8_769x769_40k_cityscapes_20200530_035107.log.json)     |
+| PSANet | R-50-D8  | 512x1024  |   80000 | -        | -              | V100   | 77.24 |         78.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/psanet/psanet_r50-d8_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_80k_cityscapes/psanet_r50-d8_512x1024_80k_cityscapes_20200606_161842-ab60a24f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_80k_cityscapes/psanet_r50-d8_512x1024_80k_cityscapes_20200606_161842.log.json)     |
+| PSANet | R-101-D8 | 512x1024  |   80000 | -        | -              | V100   | 79.31 |         80.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/psanet/psanet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_80k_cityscapes/psanet_r101-d8_512x1024_80k_cityscapes_20200606_161823-0f73a169.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_80k_cityscapes/psanet_r101-d8_512x1024_80k_cityscapes_20200606_161823.log.json) |
+| PSANet | R-50-D8  | 769x769   |   80000 | -        | -              | V100   | 79.31 |         80.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/psanet/psanet_r50-d8_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_80k_cityscapes/psanet_r50-d8_769x769_80k_cityscapes_20200606_225134-fe42f49e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_80k_cityscapes/psanet_r50-d8_769x769_80k_cityscapes_20200606_225134.log.json)         |
+| PSANet | R-101-D8 | 769x769   |   80000 | -        | -              | V100   | 79.69 |         80.89 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/psanet/psanet_r101-d8_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_80k_cityscapes/psanet_r101-d8_769x769_80k_cityscapes_20200606_214550-7665827b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_80k_cityscapes/psanet_r101-d8_769x769_80k_cityscapes_20200606_214550.log.json)     |
 
 ### ADE20K
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSANet | R-50-D8  | 512x512   |   80000 | 9        | 18.91          | V100   | 41.14 |         41.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_80k_ade20k/psanet_r50-d8_512x512_80k_ade20k_20200614_144141-835e4b97.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_80k_ade20k/psanet_r50-d8_512x512_80k_ade20k_20200614_144141.log.json)         |
-| PSANet | R-101-D8 | 512x512   |   80000 | 12.5     | 13.13          | V100   | 43.80 |         44.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_80k_ade20k/psanet_r101-d8_512x512_80k_ade20k_20200614_185117-1fab60d4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_80k_ade20k/psanet_r101-d8_512x512_80k_ade20k_20200614_185117.log.json)     |
-| PSANet | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 41.67 |         42.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_160k_ade20k/psanet_r50-d8_512x512_160k_ade20k_20200615_161258-148077dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_160k_ade20k/psanet_r50-d8_512x512_160k_ade20k_20200615_161258.log.json)     |
-| PSANet | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 43.74 |         45.38 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_160k_ade20k/psanet_r101-d8_512x512_160k_ade20k_20200615_161537-dbfa564c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_160k_ade20k/psanet_r101-d8_512x512_160k_ade20k_20200615_161537.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSANet | R-50-D8  | 512x512   |   80000 | 9        | 18.91          | V100   | 41.14 |         41.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/psanet/psanet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_80k_ade20k/psanet_r50-d8_512x512_80k_ade20k_20200614_144141-835e4b97.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_80k_ade20k/psanet_r50-d8_512x512_80k_ade20k_20200614_144141.log.json)         |
+| PSANet | R-101-D8 | 512x512   |   80000 | 12.5     | 13.13          | V100   | 43.80 |         44.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/psanet/psanet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_80k_ade20k/psanet_r101-d8_512x512_80k_ade20k_20200614_185117-1fab60d4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_80k_ade20k/psanet_r101-d8_512x512_80k_ade20k_20200614_185117.log.json)     |
+| PSANet | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 41.67 |         42.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/psanet/psanet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_160k_ade20k/psanet_r50-d8_512x512_160k_ade20k_20200615_161258-148077dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_160k_ade20k/psanet_r50-d8_512x512_160k_ade20k_20200615_161258.log.json)     |
+| PSANet | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 43.74 |         45.38 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/psanet/psanet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_160k_ade20k/psanet_r101-d8_512x512_160k_ade20k_20200615_161537-dbfa564c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_160k_ade20k/psanet_r101-d8_512x512_160k_ade20k_20200615_161537.log.json) |
 
 ### Pascal VOC 2012 + Aug
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                     |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSANet | R-50-D8  | 512x512   |   20000 | 6.9      | 18.24          | V100   | 76.39 |         77.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_20k_voc12aug/psanet_r50-d8_512x512_20k_voc12aug_20200617_102413-2f1bbaa1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_20k_voc12aug/psanet_r50-d8_512x512_20k_voc12aug_20200617_102413.log.json)     |
-| PSANet | R-101-D8 | 512x512   |   20000 | 10.4     | 12.63          | V100   | 77.91 |         79.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_20k_voc12aug/psanet_r101-d8_512x512_20k_voc12aug_20200617_110624-946fef11.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_20k_voc12aug/psanet_r101-d8_512x512_20k_voc12aug_20200617_110624.log.json) |
-| PSANet | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 76.30 |         77.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_40k_voc12aug/psanet_r50-d8_512x512_40k_voc12aug_20200613_161946-f596afb5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_40k_voc12aug/psanet_r50-d8_512x512_40k_voc12aug_20200613_161946.log.json)     |
-| PSANet | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 77.73 |         79.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/psanet/psanet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_40k_voc12aug/psanet_r101-d8_512x512_40k_voc12aug_20200613_161946-1f560f9e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_40k_voc12aug/psanet_r101-d8_512x512_40k_voc12aug_20200613_161946.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                     |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSANet | R-50-D8  | 512x512   |   20000 | 6.9      | 18.24          | V100   | 76.39 |         77.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/psanet/psanet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_20k_voc12aug/psanet_r50-d8_512x512_20k_voc12aug_20200617_102413-2f1bbaa1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_20k_voc12aug/psanet_r50-d8_512x512_20k_voc12aug_20200617_102413.log.json)     |
+| PSANet | R-101-D8 | 512x512   |   20000 | 10.4     | 12.63          | V100   | 77.91 |         79.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/psanet/psanet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_20k_voc12aug/psanet_r101-d8_512x512_20k_voc12aug_20200617_110624-946fef11.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_20k_voc12aug/psanet_r101-d8_512x512_20k_voc12aug_20200617_110624.log.json) |
+| PSANet | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 76.30 |         77.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/psanet/psanet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_40k_voc12aug/psanet_r50-d8_512x512_40k_voc12aug_20200613_161946-f596afb5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_40k_voc12aug/psanet_r50-d8_512x512_40k_voc12aug_20200613_161946.log.json)     |
+| PSANet | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 77.73 |         79.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/psanet/psanet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_40k_voc12aug/psanet_r101-d8_512x512_40k_voc12aug_20200613_161946-1f560f9e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_40k_voc12aug/psanet_r101-d8_512x512_40k_voc12aug_20200613_161946.log.json) |
 
 ## Citation
 
diff --git a/configs/pspnet/README.md b/configs/pspnet/README.md
index e1c2c112cb..4209d259b7 100644
--- a/configs/pspnet/README.md
+++ b/configs/pspnet/README.md
@@ -31,128 +31,128 @@ PSPNet-R50 D8 model structure
 
 ### Cityscapes
 
-| Method        | Backbone      | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                                                                                                             |
-| ------------- | ------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| PSPNet        | R-50-D8       | 512x1024  |   40000 | 6.1      | 4.07           | V100   | 77.85 |         79.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338.log.json)                                                                                 |
-| PSPNet        | R-101-D8      | 512x1024  |   40000 | 9.6      | 2.68           | V100   | 78.34 |         79.74 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb2-40k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751-467e7cf4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751.log.json)                                                                             |
-| PSPNet        | R-50-D8       | 769x769   |   40000 | 6.9      | 1.76           | V100   | 78.26 |         79.88 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-769x769.py)             | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_40k_cityscapes/pspnet_r50-d8_769x769_40k_cityscapes_20200606_112725-86638686.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_40k_cityscapes/pspnet_r50-d8_769x769_40k_cityscapes_20200606_112725.log.json)                                                                                     |
-| PSPNet        | R-101-D8      | 769x769   |   40000 | 10.9     | 1.15           | V100   | 79.08 |         80.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb2-40k_cityscapes-769x769.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_40k_cityscapes/pspnet_r101-d8_769x769_40k_cityscapes_20200606_112753-61c6f5be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_40k_cityscapes/pspnet_r101-d8_769x769_40k_cityscapes_20200606_112753.log.json)                                                                                 |
-| PSPNet        | R-18-D8       | 512x1024  |   80000 | 1.7      | 15.71          | V100   | 74.87 |         76.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18-d8_4xb2-80k_cityscapes-512x1024.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x1024_80k_cityscapes/pspnet_r18-d8_512x1024_80k_cityscapes_20201225_021458-09ffa746.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x1024_80k_cityscapes/pspnet_r18-d8_512x1024_80k_cityscapes-20201225_021458.log.json)                                                                                 |
-| PSPNet        | R-50-D8       | 512x1024  |   80000 | -        | -              | V100   | 78.55 |         79.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_512x1024_80k_cityscapes_20200606_112131-2376f12b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_512x1024_80k_cityscapes_20200606_112131.log.json)                                                                                 |
-| PSPNet        | R-50b-D8 rsb  | 512x1024  |   80000 | 6.2      | 3.82           | V100   | 78.47 |         79.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8-rsb_4xb2-adamw-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220315_123238-588c30be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220315_123238.log.json)                                           |
-| PSPNet        | R-101-D8      | 512x1024  |   80000 | -        | -              | V100   | 79.76 |         81.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes/pspnet_r101-d8_512x1024_80k_cityscapes_20200606_112211-e1e1100f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes/pspnet_r101-d8_512x1024_80k_cityscapes_20200606_112211.log.json)                                                                             |
-| PSPNet (FP16) | R-101-D8      | 512x1024  |   80000 | 5.34     | 8.77           | V100   | 79.46 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_fp16_512x1024_80k_cityscapes/pspnet_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230919-a0875e5c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_fp16_512x1024_80k_cityscapes/pspnet_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230919.log.json)                                                         |
-| PSPNet        | R-18-D8       | 769x769   |   80000 | 1.9      | 6.20           | V100   | 75.90 |         77.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18-d8_4xb2-80k_cityscapes-769x769.py)             | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_769x769_80k_cityscapes/pspnet_r18-d8_769x769_80k_cityscapes_20201225_021458-3deefc62.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_769x769_80k_cityscapes/pspnet_r18-d8_769x769_80k_cityscapes-20201225_021458.log.json)                                                                                     |
-| PSPNet        | R-50-D8       | 769x769   |   80000 | -        | -              | V100   | 79.59 |         80.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-769x769.py)             | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_80k_cityscapes/pspnet_r50-d8_769x769_80k_cityscapes_20200606_210121-5ccf03dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_80k_cityscapes/pspnet_r50-d8_769x769_80k_cityscapes_20200606_210121.log.json)                                                                                     |
-| PSPNet        | R-101-D8      | 769x769   |   80000 | -        | -              | V100   | 79.77 |         81.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb2-80k_cityscapes-769x769.py)            | [model](https://download.oz1z1penmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_80k_cityscapes/pspnet_r101-d8_769x769_80k_cityscapes_20200606_225055-dba412fa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_80k_cityscapes/pspnet_r101-d8_769x769_80k_cityscapes_20200606_225055.log.json)                                                                             |
-| PSPNet        | R-18b-D8      | 512x1024  |   80000 | 1.5      | 16.28          | V100   | 74.23 |         75.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18b-d8_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_512x1024_80k_cityscapes/pspnet_r18b-d8_512x1024_80k_cityscapes_20201226_063116-26928a60.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_512x1024_80k_cityscapes/pspnet_r18b-d8_512x1024_80k_cityscapes-20201226_063116.log.json)                                                                             |
-| PSPNet        | R-50b-D8      | 512x1024  |   80000 | 6.0      | 4.30           | V100   | 78.22 |         79.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50b-d8_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_512x1024_80k_cityscapes/pspnet_r50b-d8_512x1024_80k_cityscapes_20201225_094315-6344287a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_512x1024_80k_cityscapes/pspnet_r50b-d8_512x1024_80k_cityscapes-20201225_094315.log.json)                                                                             |
-| PSPNet        | R-101b-D8     | 512x1024  |   80000 | 9.5      | 2.76           | V100   | 79.69 |         80.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101b-d8_4xb2-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes_20201226_170012-3a4d38ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes-20201226_170012.log.json)                                                                         |
-| PSPNet        | R-18b-D8      | 769x769   |   80000 | 1.7      | 6.41           | V100   | 74.92 |         76.90 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18b-d8_4xb2-80k_cityscapes-769x769.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_769x769_80k_cityscapes/pspnet_r18b-d8_769x769_80k_cityscapes_20201226_080942-bf98d186.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_769x769_80k_cityscapes/pspnet_r18b-d8_769x769_80k_cityscapes-20201226_080942.log.json)                                                                                 |
-| PSPNet        | R-50b-D8      | 769x769   |   80000 | 6.8      | 1.88           | V100   | 78.50 |         79.96 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50b-d8_4xb2-80k_cityscapes-769x769.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_769x769_80k_cityscapes/pspnet_r50b-d8_769x769_80k_cityscapes_20201225_094316-4c643cf6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_769x769_80k_cityscapes/pspnet_r50b-d8_769x769_80k_cityscapes-20201225_094316.log.json)                                                                                 |
-| PSPNet        | R-101b-D8     | 769x769   |   80000 | 10.8     | 1.17           | V100   | 78.87 |         80.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101b-d8_4xb2-80k_cityscapes-769x769.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_769x769_80k_cityscapes/pspnet_r101b-d8_769x769_80k_cityscapes_20201226_171823-f0e7c293.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_769x769_80k_cityscapes/pspnet_r101b-d8_769x769_80k_cityscapes-20201226_171823.log.json)                                                                             |
-| PSPNet        | R-50-D32      | 512x1024  |   80000 | 3.0      | 15.21          | V100   | 73.88 |         76.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50b-d32_4xb2-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_512x1024_80k_cityscapes/pspnet_r50-d32_512x1024_80k_cityscapes_20220316_224840-9092b254.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_512x1024_80k_cityscapes/pspnet_r50-d32_512x1024_80k_cityscapes_20220316_224840.log.json)                                                                             |
-| PSPNet        | R-50b-D32 rsb | 512x1024  |   80000 | 3.1      | 16.08          | V100   | 74.09 |         77.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d32_rsb_4xb2-adamw-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220316_141229-dd9c9610.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220316_141229.log.json) |
-| PSPNet        | R-50b-D32     | 512x1024  |   80000 | 2.9      | 15.41          | V100   | 72.61 |         75.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50b-d32_4xb2-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d32_512x1024_80k_cityscapes/pspnet_r50b-d32_512x1024_80k_cityscapes_20220311_152152-23bcaf8c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d32_512x1024_80k_cityscapes/pspnet_r50b-d32_512x1024_80k_cityscapes_20220311_152152.log.json)                                                                         |
+| Method        | Backbone      | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                   | download                                                                                                                                                                                                                                                                                                                                                                                                                             |
+| ------------- | ------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| PSPNet        | R-50-D8       | 512x1024  |   40000 | 6.1      | 4.07           | V100   | 77.85 |         79.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338.log.json)                                                                                 |
+| PSPNet        | R-101-D8      | 512x1024  |   40000 | 9.6      | 2.68           | V100   | 78.34 |         79.74 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb2-40k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751-467e7cf4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751.log.json)                                                                             |
+| PSPNet        | R-50-D8       | 769x769   |   40000 | 6.9      | 1.76           | V100   | 78.26 |         79.88 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-769x769.py)             | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_40k_cityscapes/pspnet_r50-d8_769x769_40k_cityscapes_20200606_112725-86638686.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_40k_cityscapes/pspnet_r50-d8_769x769_40k_cityscapes_20200606_112725.log.json)                                                                                     |
+| PSPNet        | R-101-D8      | 769x769   |   40000 | 10.9     | 1.15           | V100   | 79.08 |         80.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb2-40k_cityscapes-769x769.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_40k_cityscapes/pspnet_r101-d8_769x769_40k_cityscapes_20200606_112753-61c6f5be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_40k_cityscapes/pspnet_r101-d8_769x769_40k_cityscapes_20200606_112753.log.json)                                                                                 |
+| PSPNet        | R-18-D8       | 512x1024  |   80000 | 1.7      | 15.71          | V100   | 74.87 |         76.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r18-d8_4xb2-80k_cityscapes-512x1024.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x1024_80k_cityscapes/pspnet_r18-d8_512x1024_80k_cityscapes_20201225_021458-09ffa746.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x1024_80k_cityscapes/pspnet_r18-d8_512x1024_80k_cityscapes-20201225_021458.log.json)                                                                                 |
+| PSPNet        | R-50-D8       | 512x1024  |   80000 | -        | -              | V100   | 78.55 |         79.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-512x1024.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_512x1024_80k_cityscapes_20200606_112131-2376f12b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_512x1024_80k_cityscapes_20200606_112131.log.json)                                                                                 |
+| PSPNet        | R-50b-D8 rsb  | 512x1024  |   80000 | 6.2      | 3.82           | V100   | 78.47 |         79.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8-rsb_4xb2-adamw-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220315_123238-588c30be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220315_123238.log.json)                                           |
+| PSPNet        | R-101-D8      | 512x1024  |   80000 | -        | -              | V100   | 79.76 |         81.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes/pspnet_r101-d8_512x1024_80k_cityscapes_20200606_112211-e1e1100f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes/pspnet_r101-d8_512x1024_80k_cityscapes_20200606_112211.log.json)                                                                             |
+| PSPNet (FP16) | R-101-D8      | 512x1024  |   80000 | 5.34     | 8.77           | V100   | 79.46 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_fp16_512x1024_80k_cityscapes/pspnet_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230919-a0875e5c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_fp16_512x1024_80k_cityscapes/pspnet_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230919.log.json)                                                         |
+| PSPNet        | R-18-D8       | 769x769   |   80000 | 1.9      | 6.20           | V100   | 75.90 |         77.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r18-d8_4xb2-80k_cityscapes-769x769.py)             | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_769x769_80k_cityscapes/pspnet_r18-d8_769x769_80k_cityscapes_20201225_021458-3deefc62.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_769x769_80k_cityscapes/pspnet_r18-d8_769x769_80k_cityscapes-20201225_021458.log.json)                                                                                     |
+| PSPNet        | R-50-D8       | 769x769   |   80000 | -        | -              | V100   | 79.59 |         80.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-769x769.py)             | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_80k_cityscapes/pspnet_r50-d8_769x769_80k_cityscapes_20200606_210121-5ccf03dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_80k_cityscapes/pspnet_r50-d8_769x769_80k_cityscapes_20200606_210121.log.json)                                                                                     |
+| PSPNet        | R-101-D8      | 769x769   |   80000 | -        | -              | V100   | 79.77 |         81.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb2-80k_cityscapes-769x769.py)            | [model](https://download.oz1z1penmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_80k_cityscapes/pspnet_r101-d8_769x769_80k_cityscapes_20200606_225055-dba412fa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_80k_cityscapes/pspnet_r101-d8_769x769_80k_cityscapes_20200606_225055.log.json)                                                                             |
+| PSPNet        | R-18b-D8      | 512x1024  |   80000 | 1.5      | 16.28          | V100   | 74.23 |         75.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r18b-d8_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_512x1024_80k_cityscapes/pspnet_r18b-d8_512x1024_80k_cityscapes_20201226_063116-26928a60.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_512x1024_80k_cityscapes/pspnet_r18b-d8_512x1024_80k_cityscapes-20201226_063116.log.json)                                                                             |
+| PSPNet        | R-50b-D8      | 512x1024  |   80000 | 6.0      | 4.30           | V100   | 78.22 |         79.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50b-d8_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_512x1024_80k_cityscapes/pspnet_r50b-d8_512x1024_80k_cityscapes_20201225_094315-6344287a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_512x1024_80k_cityscapes/pspnet_r50b-d8_512x1024_80k_cityscapes-20201225_094315.log.json)                                                                             |
+| PSPNet        | R-101b-D8     | 512x1024  |   80000 | 9.5      | 2.76           | V100   | 79.69 |         80.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101b-d8_4xb2-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes_20201226_170012-3a4d38ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes-20201226_170012.log.json)                                                                         |
+| PSPNet        | R-18b-D8      | 769x769   |   80000 | 1.7      | 6.41           | V100   | 74.92 |         76.90 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r18b-d8_4xb2-80k_cityscapes-769x769.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_769x769_80k_cityscapes/pspnet_r18b-d8_769x769_80k_cityscapes_20201226_080942-bf98d186.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_769x769_80k_cityscapes/pspnet_r18b-d8_769x769_80k_cityscapes-20201226_080942.log.json)                                                                                 |
+| PSPNet        | R-50b-D8      | 769x769   |   80000 | 6.8      | 1.88           | V100   | 78.50 |         79.96 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50b-d8_4xb2-80k_cityscapes-769x769.py)            | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_769x769_80k_cityscapes/pspnet_r50b-d8_769x769_80k_cityscapes_20201225_094316-4c643cf6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_769x769_80k_cityscapes/pspnet_r50b-d8_769x769_80k_cityscapes-20201225_094316.log.json)                                                                                 |
+| PSPNet        | R-101b-D8     | 769x769   |   80000 | 10.8     | 1.17           | V100   | 78.87 |         80.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101b-d8_4xb2-80k_cityscapes-769x769.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_769x769_80k_cityscapes/pspnet_r101b-d8_769x769_80k_cityscapes_20201226_171823-f0e7c293.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_769x769_80k_cityscapes/pspnet_r101b-d8_769x769_80k_cityscapes-20201226_171823.log.json)                                                                             |
+| PSPNet        | R-50-D32      | 512x1024  |   80000 | 3.0      | 15.21          | V100   | 73.88 |         76.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50b-d32_4xb2-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_512x1024_80k_cityscapes/pspnet_r50-d32_512x1024_80k_cityscapes_20220316_224840-9092b254.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_512x1024_80k_cityscapes/pspnet_r50-d32_512x1024_80k_cityscapes_20220316_224840.log.json)                                                                             |
+| PSPNet        | R-50b-D32 rsb | 512x1024  |   80000 | 3.1      | 16.08          | V100   | 74.09 |         77.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d32_rsb_4xb2-adamw-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220316_141229-dd9c9610.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes/pspnet_r50-d32_rsb-pretrain_512x1024_adamw_80k_cityscapes_20220316_141229.log.json) |
+| PSPNet        | R-50b-D32     | 512x1024  |   80000 | 2.9      | 15.41          | V100   | 72.61 |         75.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50b-d32_4xb2-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d32_512x1024_80k_cityscapes/pspnet_r50b-d32_512x1024_80k_cityscapes_20220311_152152-23bcaf8c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d32_512x1024_80k_cityscapes/pspnet_r50b-d32_512x1024_80k_cityscapes_20220311_152152.log.json)                                                                         |
 
 ### ADE20K
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSPNet | R-50-D8  | 512x512   |   80000 | 8.5      | 23.53          | V100   | 41.13 |         41.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_ade20k/pspnet_r50-d8_512x512_80k_ade20k_20200615_014128-15a8b914.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_ade20k/pspnet_r50-d8_512x512_80k_ade20k_20200615_014128.log.json)         |
-| PSPNet | R-101-D8 | 512x512   |   80000 | 12       | 15.30          | V100   | 43.57 |         44.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_ade20k/pspnet_r101-d8_512x512_80k_ade20k_20200614_031423-b6e782f0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_ade20k/pspnet_r101-d8_512x512_80k_ade20k_20200614_031423.log.json)     |
-| PSPNet | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 42.48 |         43.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_160k_ade20k/pspnet_r50-d8_512x512_160k_ade20k_20200615_184358-1890b0bd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_160k_ade20k/pspnet_r50-d8_512x512_160k_ade20k_20200615_184358.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 44.39 |         45.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_160k_ade20k/pspnet_r101-d8_512x512_160k_ade20k_20200615_100650-967c316f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_160k_ade20k/pspnet_r101-d8_512x512_160k_ade20k_20200615_100650.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSPNet | R-50-D8  | 512x512   |   80000 | 8.5      | 23.53          | V100   | 41.13 |         41.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_ade20k/pspnet_r50-d8_512x512_80k_ade20k_20200615_014128-15a8b914.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_ade20k/pspnet_r50-d8_512x512_80k_ade20k_20200615_014128.log.json)         |
+| PSPNet | R-101-D8 | 512x512   |   80000 | 12       | 15.30          | V100   | 43.57 |         44.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_ade20k/pspnet_r101-d8_512x512_80k_ade20k_20200614_031423-b6e782f0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_ade20k/pspnet_r101-d8_512x512_80k_ade20k_20200614_031423.log.json)     |
+| PSPNet | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 42.48 |         43.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_160k_ade20k/pspnet_r50-d8_512x512_160k_ade20k_20200615_184358-1890b0bd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_160k_ade20k/pspnet_r50-d8_512x512_160k_ade20k_20200615_184358.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 44.39 |         45.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_160k_ade20k/pspnet_r101-d8_512x512_160k_ade20k_20200615_100650-967c316f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_160k_ade20k/pspnet_r101-d8_512x512_160k_ade20k_20200615_100650.log.json) |
 
 ### Pascal VOC 2012 + Aug
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                     |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSPNet | R-50-D8  | 512x512   |   20000 | 6.1      | 23.59          | V100   | 76.78 |         77.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_20k_voc12aug/pspnet_r50-d8_512x512_20k_voc12aug_20200617_101958-ed5dfbd9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_20k_voc12aug/pspnet_r50-d8_512x512_20k_voc12aug_20200617_101958.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |   20000 | 9.6      | 15.02          | V100   | 78.47 |         79.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_20k_voc12aug/pspnet_r101-d8_512x512_20k_voc12aug_20200617_102003-4aef3c9a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_20k_voc12aug/pspnet_r101-d8_512x512_20k_voc12aug_20200617_102003.log.json) |
-| PSPNet | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 77.29 |         78.48 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_40k_voc12aug/pspnet_r50-d8_512x512_40k_voc12aug_20200613_161222-ae9c1b8c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_40k_voc12aug/pspnet_r50-d8_512x512_40k_voc12aug_20200613_161222.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 78.52 |         79.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_40k_voc12aug/pspnet_r101-d8_512x512_40k_voc12aug_20200613_161222-bc933b18.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_40k_voc12aug/pspnet_r101-d8_512x512_40k_voc12aug_20200613_161222.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                     |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSPNet | R-50-D8  | 512x512   |   20000 | 6.1      | 23.59          | V100   | 76.78 |         77.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_20k_voc12aug/pspnet_r50-d8_512x512_20k_voc12aug_20200617_101958-ed5dfbd9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_20k_voc12aug/pspnet_r50-d8_512x512_20k_voc12aug_20200617_101958.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |   20000 | 9.6      | 15.02          | V100   | 78.47 |         79.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_20k_voc12aug/pspnet_r101-d8_512x512_20k_voc12aug_20200617_102003-4aef3c9a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_20k_voc12aug/pspnet_r101-d8_512x512_20k_voc12aug_20200617_102003.log.json) |
+| PSPNet | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 77.29 |         78.48 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_40k_voc12aug/pspnet_r50-d8_512x512_40k_voc12aug_20200613_161222-ae9c1b8c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_40k_voc12aug/pspnet_r50-d8_512x512_40k_voc12aug_20200613_161222.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 78.52 |         79.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_40k_voc12aug/pspnet_r101-d8_512x512_40k_voc12aug_20200613_161222-bc933b18.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_40k_voc12aug/pspnet_r101-d8_512x512_40k_voc12aug_20200613_161222.log.json) |
 
 ### Pascal Context
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                               | download                                                                                                                                                                                                                                                                                                                                                             |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSPNet | R-101-D8 | 480x480   |   40000 | 8.8      | 9.68           | V100   | 46.60 |         47.78 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context/pspnet_r101-d8_480x480_40k_pascal_context_20200911_211210-bf0f5d7c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context/pspnet_r101-d8_480x480_40k_pascal_context-20200911_211210.log.json) |
-| PSPNet | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 46.03 |         47.15 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context/pspnet_r101-d8_480x480_80k_pascal_context_20200911_190530-c86d6233.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context/pspnet_r101-d8_480x480_80k_pascal_context-20200911_190530.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                             |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSPNet | R-101-D8 | 480x480   |   40000 | 8.8      | 9.68           | V100   | 46.60 |         47.78 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context/pspnet_r101-d8_480x480_40k_pascal_context_20200911_211210-bf0f5d7c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context/pspnet_r101-d8_480x480_40k_pascal_context-20200911_211210.log.json) |
+| PSPNet | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 46.03 |         47.15 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context/pspnet_r101-d8_480x480_80k_pascal_context_20200911_190530-c86d6233.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context/pspnet_r101-d8_480x480_80k_pascal_context-20200911_190530.log.json) |
 
 ### Pascal Context 59
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                  | download                                                                                                                                                                                                                                                                                                                                                                         |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSPNet | R-101-D8 | 480x480   |   40000 | -        | -              | V100   | 52.02 |         53.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context_59/pspnet_r101-d8_480x480_40k_pascal_context_59_20210416_114524-86d44cd4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context_59/pspnet_r101-d8_480x480_40k_pascal_context_59-20210416_114524.log.json) |
-| PSPNet | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 52.47 |         53.99 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context_59/pspnet_r101-d8_480x480_80k_pascal_context_59_20210416_114418-fa6caaa2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context_59/pspnet_r101-d8_480x480_80k_pascal_context_59-20210416_114418.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                               | download                                                                                                                                                                                                                                                                                                                                                                         |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSPNet | R-101-D8 | 480x480   |   40000 | -        | -              | V100   | 52.02 |         53.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context_59/pspnet_r101-d8_480x480_40k_pascal_context_59_20210416_114524-86d44cd4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context_59/pspnet_r101-d8_480x480_40k_pascal_context_59-20210416_114524.log.json) |
+| PSPNet | R-101-D8 | 480x480   |   80000 | -        | -              | V100   | 52.47 |         53.99 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context_59/pspnet_r101-d8_480x480_80k_pascal_context_59_20210416_114418-fa6caaa2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context_59/pspnet_r101-d8_480x480_80k_pascal_context_59-20210416_114418.log.json) |
 
 ### Dark Zurich and Nighttime Driving
 
 We support evaluation results on these two datasets using models above trained on Cityscapes training set.
 
-| Method | Backbone  | Training Dataset        | Test Dataset              | mIoU  | config                                                                                                                                                     | evaluation checkpoint                                                                                                                                                                                                                                                                                                                                        |
-| ------ | --------- | ----------------------- | ------------------------- | ----- | ---------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| PSPNet | R-50-D8   | Cityscapes Training set | Dark Zurich               | 10.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024_dark-zurich-1920x1080.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338.log.json)         |
-| PSPNet | R-50-D8   | Cityscapes Training set | Nighttime Driving         | 23.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024_night-driving-1920x1080.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338.log.json)         |
-| PSPNet | R-50-D8   | Cityscapes Training set | Cityscapes Validation set | 77.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)                           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338.log.json)         |
-| PSPNet | R-101-D8  | Cityscapes Training set | Dark Zurich               | 10.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb2-40k_cityscapes-512x1024_dark-zurich-1920x1080.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751-467e7cf4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751.log.json)     |
-| PSPNet | R-101-D8  | Cityscapes Training set | Nighttime Driving         | 20.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb2-40k_cityscapes-512x1024_night-driving-1920x1080.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751-467e7cf4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751.log.json)     |
-| PSPNet | R-101-D8  | Cityscapes Training set | Cityscapes Validation set | 78.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb2-40k_cityscapes-512x1024.py)                          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751-467e7cf4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751.log.json)     |
-| PSPNet | R-101b-D8 | Cityscapes Training set | Dark Zurich               | 15.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101b-d8_4xb2-80k_cityscapes-512x1024_dark-zurich-1920x1080.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes_20201226_170012-3a4d38ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes-20201226_170012.log.json) |
-| PSPNet | R-101b-D8 | Cityscapes Training set | Nighttime Driving         | 22.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101b-d8_4xb2-80k_cityscapes-512x1024_night-driving-1920x1080.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes_20201226_170012-3a4d38ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes-20201226_170012.log.json) |
-| PSPNet | R-101b-D8 | Cityscapes Training set | Cityscapes Validation set | 79.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101b-d8_4xb2-80k_cityscapes-512x1024.py)                         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes_20201226_170012-3a4d38ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes-20201226_170012.log.json) |
+| Method | Backbone  | Training Dataset        | Test Dataset              | mIoU  | config                                                                                                                                                  | evaluation checkpoint                                                                                                                                                                                                                                                                                                                                        |
+| ------ | --------- | ----------------------- | ------------------------- | ----- | ------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| PSPNet | R-50-D8   | Cityscapes Training set | Dark Zurich               | 10.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024_dark-zurich-1920x1080.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338.log.json)         |
+| PSPNet | R-50-D8   | Cityscapes Training set | Nighttime Driving         | 23.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024_night-driving-1920x1080.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338.log.json)         |
+| PSPNet | R-50-D8   | Cityscapes Training set | Cityscapes Validation set | 77.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024.py)                           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338.log.json)         |
+| PSPNet | R-101-D8  | Cityscapes Training set | Dark Zurich               | 10.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb2-40k_cityscapes-512x1024_dark-zurich-1920x1080.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751-467e7cf4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751.log.json)     |
+| PSPNet | R-101-D8  | Cityscapes Training set | Nighttime Driving         | 20.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb2-40k_cityscapes-512x1024_night-driving-1920x1080.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751-467e7cf4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751.log.json)     |
+| PSPNet | R-101-D8  | Cityscapes Training set | Cityscapes Validation set | 78.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb2-40k_cityscapes-512x1024.py)                          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751-467e7cf4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751.log.json)     |
+| PSPNet | R-101b-D8 | Cityscapes Training set | Dark Zurich               | 15.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101b-d8_4xb2-80k_cityscapes-512x1024_dark-zurich-1920x1080.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes_20201226_170012-3a4d38ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes-20201226_170012.log.json) |
+| PSPNet | R-101b-D8 | Cityscapes Training set | Nighttime Driving         | 22.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101b-d8_4xb2-80k_cityscapes-512x1024_night-driving-1920x1080.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes_20201226_170012-3a4d38ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes-20201226_170012.log.json) |
+| PSPNet | R-101b-D8 | Cityscapes Training set | Cityscapes Validation set | 79.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101b-d8_4xb2-80k_cityscapes-512x1024.py)                         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes_20201226_170012-3a4d38ab.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes-20201226_170012.log.json) |
 
 ### COCO-Stuff 10k
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                              | download                                                                                                                                                                                                                                                                                                                                                                         |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSPNet | R-50-D8  | 512x512   |   20000 | 9.6      | 20.5           | V100   | 35.69 |         36.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-20k_coco-stuff10k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k_20210820_203258-b88df27f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k_20210820_203258.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |   20000 | 13.2     | 11.1           | V100   | 37.26 |         38.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-20k_coco-stuff10k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k_20210820_232135-76aae482.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k_20210820_232135.log.json) |
-| PSPNet | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 36.33 |         37.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-40k_coco-stuff10k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_030857-92e2902b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_030857.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 37.76 |         38.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-40k_coco-stuff10k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_014022-831aec95.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_014022.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                                         |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSPNet | R-50-D8  | 512x512   |   20000 | 9.6      | 20.5           | V100   | 35.69 |         36.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb4-20k_coco-stuff10k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k_20210820_203258-b88df27f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k_20210820_203258.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |   20000 | 13.2     | 11.1           | V100   | 37.26 |         38.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb4-20k_coco-stuff10k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k_20210820_232135-76aae482.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k_20210820_232135.log.json) |
+| PSPNet | R-50-D8  | 512x512   |   40000 | -        | -              | V100   | 36.33 |         37.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb4-40k_coco-stuff10k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_030857-92e2902b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_030857.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |   40000 | -        | -              | V100   | 37.76 |         38.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb4-40k_coco-stuff10k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_014022-831aec95.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_014022.log.json) |
 
 ### COCO-Stuff 164k
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                | download                                                                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSPNet | R-50-D8  | 512x512   |   80000 | 9.6      | 20.5           | V100   | 38.80 |         39.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-80k_coco-stuff164k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034-0e41b2db.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034.log.json)         |
-| PSPNet | R-101-D8 | 512x512   |   80000 | 13.2     | 11.1           | V100   | 40.34 |         40.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034-7eb41789.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034.log.json)     |
-| PSPNet | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 39.64 |         39.97 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004-51276a57.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 41.28 |         41.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-160k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004-4af9621b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004.log.json) |
-| PSPNet | R-50-D8  | 512x512   |  320000 | -        | -              | V100   | 40.53 |         40.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-320k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004-be9610cc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |  320000 | -        | -              | V100   | 41.95 |         42.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-320k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004-72220c60.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                             | download                                                                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSPNet | R-50-D8  | 512x512   |   80000 | 9.6      | 20.5           | V100   | 38.80 |         39.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb4-80k_coco-stuff164k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034-0e41b2db.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034.log.json)         |
+| PSPNet | R-101-D8 | 512x512   |   80000 | 13.2     | 11.1           | V100   | 40.34 |         40.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb4-80k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034-7eb41789.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034.log.json)     |
+| PSPNet | R-50-D8  | 512x512   |  160000 | -        | -              | V100   | 39.64 |         39.97 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb4-160k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004-51276a57.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |  160000 | -        | -              | V100   | 41.28 |         41.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb4-160k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004-4af9621b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004.log.json) |
+| PSPNet | R-50-D8  | 512x512   |  320000 | -        | -              | V100   | 40.53 |         40.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb4-320k_coco-stuff164k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004-be9610cc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |  320000 | -        | -              | V100   | 41.95 |         42.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb4-320k_coco-stuff164k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004-72220c60.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004.log.json) |
 
 ### LoveDA
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                             |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| PSPNet | R-18-D8  | 512x512   |   80000 | 1.45     | 26.87          | V100   | 48.62 |         47.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18-d8_4xb4-80k_loveda-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x512_80k_loveda/pspnet_r18-d8_512x512_80k_loveda_20211105_052100-b97697f1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x512_80k_loveda/pspnet_r18-d8_512x512_80k_loveda_20211105_052100.log.json)     |
-| PSPNet | R-50-D8  | 512x512   |   80000 | 6.14     | 6.60           | V100   | 50.46 |         50.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-80k_loveda-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_loveda/pspnet_r50-d8_512x512_80k_loveda_20211104_155728-88610f9f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_loveda/pspnet_r50-d8_512x512_80k_loveda_20211104_155728.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |   80000 | 9.61     | 4.58           | V100   | 51.86 |         51.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_loveda-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_loveda/pspnet_r101-d8_512x512_80k_loveda_20211104_153212-1c06c6a8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_loveda/pspnet_r101-d8_512x512_80k_loveda_20211104_153212.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                    | download                                                                                                                                                                                                                                                                                                                             |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| PSPNet | R-18-D8  | 512x512   |   80000 | 1.45     | 26.87          | V100   | 48.62 |         47.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r18-d8_4xb4-80k_loveda-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x512_80k_loveda/pspnet_r18-d8_512x512_80k_loveda_20211105_052100-b97697f1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x512_80k_loveda/pspnet_r18-d8_512x512_80k_loveda_20211105_052100.log.json)     |
+| PSPNet | R-50-D8  | 512x512   |   80000 | 6.14     | 6.60           | V100   | 50.46 |         50.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb4-80k_loveda-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_loveda/pspnet_r50-d8_512x512_80k_loveda_20211104_155728-88610f9f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_loveda/pspnet_r50-d8_512x512_80k_loveda_20211104_155728.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |   80000 | 9.61     | 4.58           | V100   | 51.86 |         51.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb4-80k_loveda-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_loveda/pspnet_r101-d8_512x512_80k_loveda_20211104_153212-1c06c6a8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_loveda/pspnet_r101-d8_512x512_80k_loveda_20211104_153212.log.json) |
 
 ### Potsdam
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                 |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSPNet | R-18-D8  | 512x512   |   80000 | 1.50     | 85.12          | V100   | 77.09 |         78.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18-d8_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_potsdam/pspnet_r18-d8_4x4_512x512_80k_potsdam_20211220_125612-7cd046e1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_potsdam/pspnet_r18-d8_4x4_512x512_80k_potsdam_20211220_125612.log.json)     |
-| PSPNet | R-50-D8  | 512x512   |   80000 | 6.14     | 30.21          | V100   | 78.12 |         78.98 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_potsdam/pspnet_r50-d8_4x4_512x512_80k_potsdam_20211219_043541-2dd5fe67.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_potsdam/pspnet_r50-d8_4x4_512x512_80k_potsdam_20211219_043541.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |   80000 | 9.61     | 19.40          | V100   | 78.62 |         79.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_potsdam-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_potsdam/pspnet_r101-d8_4x4_512x512_80k_potsdam_20211220_125612-aed036c4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_potsdam/pspnet_r101-d8_4x4_512x512_80k_potsdam_20211220_125612.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                 |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSPNet | R-18-D8  | 512x512   |   80000 | 1.50     | 85.12          | V100   | 77.09 |         78.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r18-d8_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_potsdam/pspnet_r18-d8_4x4_512x512_80k_potsdam_20211220_125612-7cd046e1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_potsdam/pspnet_r18-d8_4x4_512x512_80k_potsdam_20211220_125612.log.json)     |
+| PSPNet | R-50-D8  | 512x512   |   80000 | 6.14     | 30.21          | V100   | 78.12 |         78.98 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb4-80k_potsdam-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_potsdam/pspnet_r50-d8_4x4_512x512_80k_potsdam_20211219_043541-2dd5fe67.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_potsdam/pspnet_r50-d8_4x4_512x512_80k_potsdam_20211219_043541.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |   80000 | 9.61     | 19.40          | V100   | 78.62 |         79.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb4-80k_potsdam-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_potsdam/pspnet_r101-d8_4x4_512x512_80k_potsdam_20211220_125612-aed036c4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_potsdam/pspnet_r101-d8_4x4_512x512_80k_potsdam_20211220_125612.log.json) |
 
 ### Vaihingen
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                                         |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSPNet | R-18-D8  | 512x512   |   80000 | 1.45     | 85.06          | V100   | 71.46 |         73.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18-d8_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_vaihingen/pspnet_r18-d8_4x4_512x512_80k_vaihingen_20211228_160355-52a8a6f6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_vaihingen/pspnet_r18-d8_4x4_512x512_80k_vaihingen_20211228_160355.log.json)     |
-| PSPNet | R-50-D8  | 512x512   |   80000 | 6.14     | 30.29          | V100   | 72.36 |         73.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_vaihingen/pspnet_r50-d8_4x4_512x512_80k_vaihingen_20211228_160355-382f8f5b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_vaihingen/pspnet_r50-d8_4x4_512x512_80k_vaihingen_20211228_160355.log.json)     |
-| PSPNet | R-101-D8 | 512x512   |   80000 | 9.61     | 19.97          | V100   | 72.61 |         74.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r101-d8_4xb4-80k_vaihingen-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_vaihingen/pspnet_r101-d8_4x4_512x512_80k_vaihingen_20211231_230806-8eba0a09.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_vaihingen/pspnet_r101-d8_4x4_512x512_80k_vaihingen_20211231_230806.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                                                         |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSPNet | R-18-D8  | 512x512   |   80000 | 1.45     | 85.06          | V100   | 71.46 |         73.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r18-d8_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_vaihingen/pspnet_r18-d8_4x4_512x512_80k_vaihingen_20211228_160355-52a8a6f6.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_vaihingen/pspnet_r18-d8_4x4_512x512_80k_vaihingen_20211228_160355.log.json)     |
+| PSPNet | R-50-D8  | 512x512   |   80000 | 6.14     | 30.29          | V100   | 72.36 |         73.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb4-80k_vaihingen-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_vaihingen/pspnet_r50-d8_4x4_512x512_80k_vaihingen_20211228_160355-382f8f5b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_vaihingen/pspnet_r50-d8_4x4_512x512_80k_vaihingen_20211228_160355.log.json)     |
+| PSPNet | R-101-D8 | 512x512   |   80000 | 9.61     | 19.97          | V100   | 72.61 |         74.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r101-d8_4xb4-80k_vaihingen-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_vaihingen/pspnet_r101-d8_4x4_512x512_80k_vaihingen_20211231_230806-8eba0a09.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_vaihingen/pspnet_r101-d8_4x4_512x512_80k_vaihingen_20211231_230806.log.json) |
 
 ### iSAID
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                     |
-| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PSPNet | R-18-D8  | 896x896   |   80000 | 4.52     | 26.91          | V100   | 60.22 |         61.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r18-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_896x896_80k_isaid/pspnet_r18-d8_4x4_896x896_80k_isaid_20220110_180526-e84c0b6a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_896x896_80k_isaid/pspnet_r18-d8_4x4_896x896_80k_isaid_20220110_180526.log.json) |
-| PSPNet | R-50-D8  | 896x896   |   80000 | 16.58    | 8.88           | V100   | 65.36 |         66.48 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pspnet/pspnet_r50-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_896x896_80k_isaid/pspnet_r50-d8_4x4_896x896_80k_isaid_20220110_180629-1f21dc32.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_896x896_80k_isaid/pspnet_r50-d8_4x4_896x896_80k_isaid_20220110_180629.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                                                                     |
+| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PSPNet | R-18-D8  | 896x896   |   80000 | 4.52     | 26.91          | V100   | 60.22 |         61.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r18-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_896x896_80k_isaid/pspnet_r18-d8_4x4_896x896_80k_isaid_20220110_180526-e84c0b6a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_896x896_80k_isaid/pspnet_r18-d8_4x4_896x896_80k_isaid_20220110_180526.log.json) |
+| PSPNet | R-50-D8  | 896x896   |   80000 | 16.58    | 8.88           | V100   | 65.36 |         66.48 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_896x896_80k_isaid/pspnet_r50-d8_4x4_896x896_80k_isaid_20220110_180629-1f21dc32.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_896x896_80k_isaid/pspnet_r50-d8_4x4_896x896_80k_isaid_20220110_180629.log.json) |
 
 Note:
 
diff --git a/configs/resnest/README.md b/configs/resnest/README.md
index d27bbe2807..304791abe9 100644
--- a/configs/resnest/README.md
+++ b/configs/resnest/README.md
@@ -26,21 +26,21 @@ It is well known that featuremap attention and multi-path representation are imp
 
 ### Cityscapes
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                                               |
-| ---------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN        | S-101-D8 | 512x1024  |   80000 |     11.4 | 2.39           | V100   | 77.56 | 78.98         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_fcn_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x1024_80k_cityscapes/fcn_s101-d8_512x1024_80k_cityscapes_20200807_140631-f8d155b3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x1024_80k_cityscapes/fcn_s101-d8_512x1024_80k_cityscapes-20200807_140631.log.json)                                         |
-| PSPNet     | S-101-D8 | 512x1024  |   80000 |     11.8 | 2.52           | V100   | 78.57 | 79.19         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_pspnet_4xb2-80k_cityscapes512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x1024_80k_cityscapes/pspnet_s101-d8_512x1024_80k_cityscapes_20200807_140631-c75f3b99.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x1024_80k_cityscapes/pspnet_s101-d8_512x1024_80k_cityscapes-20200807_140631.log.json)                             |
-| DeepLabV3  | S-101-D8 | 512x1024  |   80000 |     11.9 | 1.88           | V100   | 79.67 | 80.51         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_deeplabv3_4xb2-80k_cityscapes-512x1024.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x1024_80k_cityscapes/deeplabv3_s101-d8_512x1024_80k_cityscapes_20200807_144429-b73c4270.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x1024_80k_cityscapes/deeplabv3_s101-d8_512x1024_80k_cityscapes-20200807_144429.log.json)                 |
-| DeepLabV3+ | S-101-D8 | 512x1024  |   80000 |     13.2 | 2.36           | V100   | 79.62 | 80.27         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_deeplabv3plus_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x1024_80k_cityscapes/deeplabv3plus_s101-d8_512x1024_80k_cityscapes_20200807_144429-1239eb43.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x1024_80k_cityscapes/deeplabv3plus_s101-d8_512x1024_80k_cityscapes-20200807_144429.log.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                                               |
+| ---------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN        | S-101-D8 | 512x1024  |   80000 |     11.4 | 2.39           | V100   | 77.56 | 78.98         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/resnest/resnest_s101-d8_fcn_4xb2-80k_cityscapes-512x1024.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x1024_80k_cityscapes/fcn_s101-d8_512x1024_80k_cityscapes_20200807_140631-f8d155b3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x1024_80k_cityscapes/fcn_s101-d8_512x1024_80k_cityscapes-20200807_140631.log.json)                                         |
+| PSPNet     | S-101-D8 | 512x1024  |   80000 |     11.8 | 2.52           | V100   | 78.57 | 79.19         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/resnest/resnest_s101-d8_pspnet_4xb2-80k_cityscapes512x1024.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x1024_80k_cityscapes/pspnet_s101-d8_512x1024_80k_cityscapes_20200807_140631-c75f3b99.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x1024_80k_cityscapes/pspnet_s101-d8_512x1024_80k_cityscapes-20200807_140631.log.json)                             |
+| DeepLabV3  | S-101-D8 | 512x1024  |   80000 |     11.9 | 1.88           | V100   | 79.67 | 80.51         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/resnest/resnest_s101-d8_deeplabv3_4xb2-80k_cityscapes-512x1024.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x1024_80k_cityscapes/deeplabv3_s101-d8_512x1024_80k_cityscapes_20200807_144429-b73c4270.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x1024_80k_cityscapes/deeplabv3_s101-d8_512x1024_80k_cityscapes-20200807_144429.log.json)                 |
+| DeepLabV3+ | S-101-D8 | 512x1024  |   80000 |     13.2 | 2.36           | V100   | 79.62 | 80.27         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/resnest/resnest_s101-d8_deeplabv3plus_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x1024_80k_cityscapes/deeplabv3plus_s101-d8_512x1024_80k_cityscapes_20200807_144429-1239eb43.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x1024_80k_cityscapes/deeplabv3plus_s101-d8_512x1024_80k_cityscapes-20200807_144429.log.json) |
 
 ### ADE20K
 
-| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                               |
-| ---------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | --------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FCN        | S-101-D8 | 512x512   |  160000 |     14.2 | 12.86          | V100   | 45.62 | 46.16         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_fcn_4xb4-160k_ade20k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x512_160k_ade20k/fcn_s101-d8_512x512_160k_ade20k_20200807_145416-d3160329.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x512_160k_ade20k/fcn_s101-d8_512x512_160k_ade20k-20200807_145416.log.json)                                         |
-| PSPNet     | S-101-D8 | 512x512   |  160000 |     14.2 | 13.02          | V100   | 45.44 | 46.28         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_pspnet_4xb4-160k_ade20k-512x512.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x512_160k_ade20k/pspnet_s101-d8_512x512_160k_ade20k_20200807_145416-a6daa92a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x512_160k_ade20k/pspnet_s101-d8_512x512_160k_ade20k-20200807_145416.log.json)                             |
-| DeepLabV3  | S-101-D8 | 512x512   |  160000 |     14.6 | 9.28           | V100   | 45.71 | 46.59         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_deeplabv3_4xb4-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x512_160k_ade20k/deeplabv3_s101-d8_512x512_160k_ade20k_20200807_144503-17ecabe5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x512_160k_ade20k/deeplabv3_s101-d8_512x512_160k_ade20k-20200807_144503.log.json)                 |
-| DeepLabV3+ | S-101-D8 | 512x512   |  160000 |     16.2 | 11.96          | V100   | 46.47 | 47.27         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/resnest/resnest_s101-d8_deeplabv3plus_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x512_160k_ade20k/deeplabv3plus_s101-d8_512x512_160k_ade20k_20200807_144503-27b26226.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x512_160k_ade20k/deeplabv3plus_s101-d8_512x512_160k_ade20k-20200807_144503.log.json) |
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                                               |
+| ---------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FCN        | S-101-D8 | 512x512   |  160000 |     14.2 | 12.86          | V100   | 45.62 | 46.16         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/resnest/resnest_s101-d8_fcn_4xb4-160k_ade20k-512x512.py)           | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x512_160k_ade20k/fcn_s101-d8_512x512_160k_ade20k_20200807_145416-d3160329.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x512_160k_ade20k/fcn_s101-d8_512x512_160k_ade20k-20200807_145416.log.json)                                         |
+| PSPNet     | S-101-D8 | 512x512   |  160000 |     14.2 | 13.02          | V100   | 45.44 | 46.28         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/resnest/resnest_s101-d8_pspnet_4xb4-160k_ade20k-512x512.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x512_160k_ade20k/pspnet_s101-d8_512x512_160k_ade20k_20200807_145416-a6daa92a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x512_160k_ade20k/pspnet_s101-d8_512x512_160k_ade20k-20200807_145416.log.json)                             |
+| DeepLabV3  | S-101-D8 | 512x512   |  160000 |     14.6 | 9.28           | V100   | 45.71 | 46.59         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/resnest/resnest_s101-d8_deeplabv3_4xb4-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x512_160k_ade20k/deeplabv3_s101-d8_512x512_160k_ade20k_20200807_144503-17ecabe5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x512_160k_ade20k/deeplabv3_s101-d8_512x512_160k_ade20k-20200807_144503.log.json)                 |
+| DeepLabV3+ | S-101-D8 | 512x512   |  160000 |     16.2 | 11.96          | V100   | 46.47 | 47.27         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/resnest/resnest_s101-d8_deeplabv3plus_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x512_160k_ade20k/deeplabv3plus_s101-d8_512x512_160k_ade20k_20200807_144503-27b26226.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x512_160k_ade20k/deeplabv3plus_s101-d8_512x512_160k_ade20k-20200807_144503.log.json) |
 
 ## Citation
 
diff --git a/configs/segformer/README.md b/configs/segformer/README.md
index 5dbf1215bc..f8999b0efa 100644
--- a/configs/segformer/README.md
+++ b/configs/segformer/README.md
@@ -38,15 +38,15 @@ This script convert model from `PRETRAIN_PATH` and store the converted model in
 
 ### ADE20K
 
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device   |  mIoU | mIoU(ms+flip) | config                                                                                                                             | download                                                                                                                                                                                                                                                                                                                                               |
-| --------- | -------- | --------- | ------: | -------: | -------------- | -------- | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| Segformer | MIT-B0   | 512x512   |  160000 |      2.1 | 51.32          | 1080 Ti  | 37.41 | 38.34         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b0_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_512x512_160k_ade20k/segformer_mit-b0_512x512_160k_ade20k_20210726_101530-8ffa8fda.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_512x512_160k_ade20k/segformer_mit-b0_512x512_160k_ade20k_20210726_101530.log.json) |
-| Segformer | MIT-B1   | 512x512   |  160000 |      2.6 | 47.66          | TITAN Xp | 40.97 | 42.54         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b1_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_512x512_160k_ade20k/segformer_mit-b1_512x512_160k_ade20k_20210726_112106-d70e859d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_512x512_160k_ade20k/segformer_mit-b1_512x512_160k_ade20k_20210726_112106.log.json) |
-| Segformer | MIT-B2   | 512x512   |  160000 |      3.6 | 30.88          | TITAN Xp | 45.58 | 47.03         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b2_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_512x512_160k_ade20k/segformer_mit-b2_512x512_160k_ade20k_20210726_112103-cbd414ac.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_512x512_160k_ade20k/segformer_mit-b2_512x512_160k_ade20k_20210726_112103.log.json) |
-| Segformer | MIT-B3   | 512x512   |  160000 |      4.8 | 22.11          | V100     | 47.82 | 48.81         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b3_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_512x512_160k_ade20k/segformer_mit-b3_512x512_160k_ade20k_20210726_081410-962b98d2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_512x512_160k_ade20k/segformer_mit-b3_512x512_160k_ade20k_20210726_081410.log.json) |
-| Segformer | MIT-B4   | 512x512   |  160000 |      6.1 | 15.45          | V100     | 48.46 | 49.76         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b4_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_512x512_160k_ade20k/segformer_mit-b4_512x512_160k_ade20k_20210728_183055-7f509d7d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_512x512_160k_ade20k/segformer_mit-b4_512x512_160k_ade20k_20210728_183055.log.json) |
-| Segformer | MIT-B5   | 512x512   |  160000 |      7.2 | 11.89          | V100     | 49.13 | 50.22         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b5_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_512x512_160k_ade20k/segformer_mit-b5_512x512_160k_ade20k_20210726_145235-94cedf59.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_512x512_160k_ade20k/segformer_mit-b5_512x512_160k_ade20k_20210726_145235.log.json) |
-| Segformer | MIT-B5   | 640x640   |  160000 |     11.5 | 11.30          | V100     | 49.62 | 50.36         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b5_8xb2-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_640x640_160k_ade20k/segformer_mit-b5_640x640_160k_ade20k_20210801_121243-41d2845b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_640x640_160k_ade20k/segformer_mit-b5_640x640_160k_ade20k_20210801_121243.log.json) |
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device   |  mIoU | mIoU(ms+flip) | config                                                                                                                          | download                                                                                                                                                                                                                                                                                                                                               |
+| --------- | -------- | --------- | ------: | -------: | -------------- | -------- | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| Segformer | MIT-B0   | 512x512   |  160000 |      2.1 | 51.32          | 1080 Ti  | 37.41 | 38.34         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segformer/segformer_mit-b0_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_512x512_160k_ade20k/segformer_mit-b0_512x512_160k_ade20k_20210726_101530-8ffa8fda.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_512x512_160k_ade20k/segformer_mit-b0_512x512_160k_ade20k_20210726_101530.log.json) |
+| Segformer | MIT-B1   | 512x512   |  160000 |      2.6 | 47.66          | TITAN Xp | 40.97 | 42.54         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segformer/segformer_mit-b1_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_512x512_160k_ade20k/segformer_mit-b1_512x512_160k_ade20k_20210726_112106-d70e859d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_512x512_160k_ade20k/segformer_mit-b1_512x512_160k_ade20k_20210726_112106.log.json) |
+| Segformer | MIT-B2   | 512x512   |  160000 |      3.6 | 30.88          | TITAN Xp | 45.58 | 47.03         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segformer/segformer_mit-b2_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_512x512_160k_ade20k/segformer_mit-b2_512x512_160k_ade20k_20210726_112103-cbd414ac.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_512x512_160k_ade20k/segformer_mit-b2_512x512_160k_ade20k_20210726_112103.log.json) |
+| Segformer | MIT-B3   | 512x512   |  160000 |      4.8 | 22.11          | V100     | 47.82 | 48.81         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segformer/segformer_mit-b3_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_512x512_160k_ade20k/segformer_mit-b3_512x512_160k_ade20k_20210726_081410-962b98d2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_512x512_160k_ade20k/segformer_mit-b3_512x512_160k_ade20k_20210726_081410.log.json) |
+| Segformer | MIT-B4   | 512x512   |  160000 |      6.1 | 15.45          | V100     | 48.46 | 49.76         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segformer/segformer_mit-b4_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_512x512_160k_ade20k/segformer_mit-b4_512x512_160k_ade20k_20210728_183055-7f509d7d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_512x512_160k_ade20k/segformer_mit-b4_512x512_160k_ade20k_20210728_183055.log.json) |
+| Segformer | MIT-B5   | 512x512   |  160000 |      7.2 | 11.89          | V100     | 49.13 | 50.22         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segformer/segformer_mit-b5_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_512x512_160k_ade20k/segformer_mit-b5_512x512_160k_ade20k_20210726_145235-94cedf59.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_512x512_160k_ade20k/segformer_mit-b5_512x512_160k_ade20k_20210726_145235.log.json) |
+| Segformer | MIT-B5   | 640x640   |  160000 |     11.5 | 11.30          | V100     | 49.62 | 50.36         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segformer/segformer_mit-b5_8xb2-160k_ade20k-640x640.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_640x640_160k_ade20k/segformer_mit-b5_640x640_160k_ade20k_20210801_121243-41d2845b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_640x640_160k_ade20k/segformer_mit-b5_640x640_160k_ade20k_20210801_121243.log.json) |
 
 Evaluation with AlignedResize:
 
@@ -80,14 +80,14 @@ test_pipeline = [
 
 The lower fps result is caused by the sliding window inference scheme (window size:1024x1024).
 
-| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                   | download                                                                                                                                                                                                                                                                                                                                                                                       |
-| --------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Segformer | MIT-B0   | 1024x1024 |  160000 |     3.64 | 4.74           | V100   | 76.54 | 78.22         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b0_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_8x1_1024x1024_160k_cityscapes/segformer_mit-b0_8x1_1024x1024_160k_cityscapes_20211208_101857-e7f88502.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_8x1_1024x1024_160k_cityscapes/segformer_mit-b0_8x1_1024x1024_160k_cityscapes_20211208_101857.log.json) |
-| Segformer | MIT-B1   | 1024x1024 |  160000 |     4.49 | 4.3            | V100   | 78.56 | 79.73         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b1_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_8x1_1024x1024_160k_cityscapes/segformer_mit-b1_8x1_1024x1024_160k_cityscapes_20211208_064213-655c7b3f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_8x1_1024x1024_160k_cityscapes/segformer_mit-b1_8x1_1024x1024_160k_cityscapes_20211208_064213.log.json) |
-| Segformer | MIT-B2   | 1024x1024 |  160000 |     7.42 | 3.36           | V100   | 81.08 | 82.18         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b2_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_8x1_1024x1024_160k_cityscapes/segformer_mit-b2_8x1_1024x1024_160k_cityscapes_20211207_134205-6096669a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_8x1_1024x1024_160k_cityscapes/segformer_mit-b2_8x1_1024x1024_160k_cityscapes_20211207_134205.log.json) |
-| Segformer | MIT-B3   | 1024x1024 |  160000 |    10.86 | 2.53           | V100   | 81.94 | 83.14         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b3_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_8x1_1024x1024_160k_cityscapes/segformer_mit-b3_8x1_1024x1024_160k_cityscapes_20211206_224823-a8f8a177.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_8x1_1024x1024_160k_cityscapes/segformer_mit-b3_8x1_1024x1024_160k_cityscapes_20211206_224823.log.json) |
-| Segformer | MIT-B4   | 1024x1024 |  160000 |    15.07 | 1.88           | V100   | 81.89 | 83.38         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b4_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_8x1_1024x1024_160k_cityscapes/segformer_mit-b4_8x1_1024x1024_160k_cityscapes_20211207_080709-07f6c333.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_8x1_1024x1024_160k_cityscapes/segformer_mit-b4_8x1_1024x1024_160k_cityscapes_20211207_080709.log.json) |
-| Segformer | MIT-B5   | 1024x1024 |  160000 |    18.00 | 1.39           | V100   | 82.25 | 83.48         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segformer/segformer_mit-b5_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_8x1_1024x1024_160k_cityscapes/segformer_mit-b5_8x1_1024x1024_160k_cityscapes_20211206_072934-87a052ec.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_8x1_1024x1024_160k_cityscapes/segformer_mit-b5_8x1_1024x1024_160k_cityscapes_20211206_072934.log.json) |
+| Method    | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                | download                                                                                                                                                                                                                                                                                                                                                                                       |
+| --------- | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Segformer | MIT-B0   | 1024x1024 |  160000 |     3.64 | 4.74           | V100   | 76.54 | 78.22         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segformer/segformer_mit-b0_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_8x1_1024x1024_160k_cityscapes/segformer_mit-b0_8x1_1024x1024_160k_cityscapes_20211208_101857-e7f88502.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_8x1_1024x1024_160k_cityscapes/segformer_mit-b0_8x1_1024x1024_160k_cityscapes_20211208_101857.log.json) |
+| Segformer | MIT-B1   | 1024x1024 |  160000 |     4.49 | 4.3            | V100   | 78.56 | 79.73         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segformer/segformer_mit-b1_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_8x1_1024x1024_160k_cityscapes/segformer_mit-b1_8x1_1024x1024_160k_cityscapes_20211208_064213-655c7b3f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_8x1_1024x1024_160k_cityscapes/segformer_mit-b1_8x1_1024x1024_160k_cityscapes_20211208_064213.log.json) |
+| Segformer | MIT-B2   | 1024x1024 |  160000 |     7.42 | 3.36           | V100   | 81.08 | 82.18         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segformer/segformer_mit-b2_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_8x1_1024x1024_160k_cityscapes/segformer_mit-b2_8x1_1024x1024_160k_cityscapes_20211207_134205-6096669a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_8x1_1024x1024_160k_cityscapes/segformer_mit-b2_8x1_1024x1024_160k_cityscapes_20211207_134205.log.json) |
+| Segformer | MIT-B3   | 1024x1024 |  160000 |    10.86 | 2.53           | V100   | 81.94 | 83.14         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segformer/segformer_mit-b3_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_8x1_1024x1024_160k_cityscapes/segformer_mit-b3_8x1_1024x1024_160k_cityscapes_20211206_224823-a8f8a177.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_8x1_1024x1024_160k_cityscapes/segformer_mit-b3_8x1_1024x1024_160k_cityscapes_20211206_224823.log.json) |
+| Segformer | MIT-B4   | 1024x1024 |  160000 |    15.07 | 1.88           | V100   | 81.89 | 83.38         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segformer/segformer_mit-b4_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_8x1_1024x1024_160k_cityscapes/segformer_mit-b4_8x1_1024x1024_160k_cityscapes_20211207_080709-07f6c333.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_8x1_1024x1024_160k_cityscapes/segformer_mit-b4_8x1_1024x1024_160k_cityscapes_20211207_080709.log.json) |
+| Segformer | MIT-B5   | 1024x1024 |  160000 |    18.00 | 1.39           | V100   | 82.25 | 83.48         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segformer/segformer_mit-b5_8xb1-160k_cityscapes-1024x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_8x1_1024x1024_160k_cityscapes/segformer_mit-b5_8x1_1024x1024_160k_cityscapes_20211206_072934-87a052ec.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_8x1_1024x1024_160k_cityscapes/segformer_mit-b5_8x1_1024x1024_160k_cityscapes_20211206_072934.log.json) |
 
 ## Citation
 
diff --git a/configs/segmenter/README.md b/configs/segmenter/README.md
index a9a64ae421..103b125472 100644
--- a/configs/segmenter/README.md
+++ b/configs/segmenter/README.md
@@ -55,13 +55,13 @@ In our default setting, pretrained models and their corresponding [ViT-AugReg](h
 
 ### ADE20K
 
-| Method           | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                                                       |
-| ---------------- | -------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Segmenter Mask   | ViT-T_16 | 512x512   | 160000  | 1.21     | 27.98          | V100   | 39.99 | 40.83         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segmenter/segmenter_vit-t_mask_8xb1-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-t_mask_8x1_512x512_160k_ade20k/segmenter_vit-t_mask_8x1_512x512_160k_ade20k_20220105_151706-ffcf7509.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-t_mask_8x1_512x512_160k_ade20k/segmenter_vit-t_mask_8x1_512x512_160k_ade20k_20220105_151706.log.json)         |
-| Segmenter Linear | ViT-S_16 | 512x512   | 160000  | 1.78     | 28.07          | V100   | 45.75 | 46.82         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segmenter/segmenter_vit-s_fcn_8xb1-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_linear_8x1_512x512_160k_ade20k/segmenter_vit-s_linear_8x1_512x512_160k_ade20k_20220105_151713-39658c46.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_linear_8x1_512x512_160k_ade20k/segmenter_vit-s_linear_8x1_512x512_160k_ade20k_20220105_151713.log.json) |
-| Segmenter Mask   | ViT-S_16 | 512x512   | 160000  | 2.03     | 24.80          | V100   | 46.19 | 47.85         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segmenter/segmenter_vit-s_mask_8xb1-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k/segmenter_vit-s_mask_8x1_512x512_160k_ade20k_20220105_151706-511bb103.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k/segmenter_vit-s_mask_8x1_512x512_160k_ade20k_20220105_151706.log.json)         |
-| Segmenter Mask   | ViT-B_16 | 512x512   | 160000  | 4.20     | 13.20          | V100   | 49.60 | 51.07         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segmenter/segmenter_vit-b_mask_8xb1-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k/segmenter_vit-b_mask_8x1_512x512_160k_ade20k_20220105_151706-bc533b08.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k/segmenter_vit-b_mask_8x1_512x512_160k_ade20k_20220105_151706.log.json)         |
-| Segmenter Mask   | ViT-L_16 | 640x640   | 160000  | 16.56    | 2.62           | V100   | 52.16 | 53.65         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segmenter/segmenter_vit-l_mask_8xb1-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k/segmenter_vit-l_mask_8x1_512x512_160k_ade20k_20220105_162750-7ef345be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k/segmenter_vit-l_mask_8x1_512x512_160k_ade20k_20220105_162750.log.json)         |
+| Method           | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                              | download                                                                                                                                                                                                                                                                                                                                                                                       |
+| ---------------- | -------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | ----------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Segmenter Mask   | ViT-T_16 | 512x512   | 160000  | 1.21     | 27.98          | V100   | 39.99 | 40.83         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segmenter/segmenter_vit-t_mask_8xb1-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-t_mask_8x1_512x512_160k_ade20k/segmenter_vit-t_mask_8x1_512x512_160k_ade20k_20220105_151706-ffcf7509.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-t_mask_8x1_512x512_160k_ade20k/segmenter_vit-t_mask_8x1_512x512_160k_ade20k_20220105_151706.log.json)         |
+| Segmenter Linear | ViT-S_16 | 512x512   | 160000  | 1.78     | 28.07          | V100   | 45.75 | 46.82         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segmenter/segmenter_vit-s_fcn_8xb1-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_linear_8x1_512x512_160k_ade20k/segmenter_vit-s_linear_8x1_512x512_160k_ade20k_20220105_151713-39658c46.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_linear_8x1_512x512_160k_ade20k/segmenter_vit-s_linear_8x1_512x512_160k_ade20k_20220105_151713.log.json) |
+| Segmenter Mask   | ViT-S_16 | 512x512   | 160000  | 2.03     | 24.80          | V100   | 46.19 | 47.85         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segmenter/segmenter_vit-s_mask_8xb1-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k/segmenter_vit-s_mask_8x1_512x512_160k_ade20k_20220105_151706-511bb103.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k/segmenter_vit-s_mask_8x1_512x512_160k_ade20k_20220105_151706.log.json)         |
+| Segmenter Mask   | ViT-B_16 | 512x512   | 160000  | 4.20     | 13.20          | V100   | 49.60 | 51.07         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segmenter/segmenter_vit-b_mask_8xb1-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k/segmenter_vit-b_mask_8x1_512x512_160k_ade20k_20220105_151706-bc533b08.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k/segmenter_vit-b_mask_8x1_512x512_160k_ade20k_20220105_151706.log.json)         |
+| Segmenter Mask   | ViT-L_16 | 640x640   | 160000  | 16.56    | 2.62           | V100   | 52.16 | 53.65         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segmenter/segmenter_vit-l_mask_8xb1-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k/segmenter_vit-l_mask_8x1_512x512_160k_ade20k_20220105_162750-7ef345be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k/segmenter_vit-l_mask_8x1_512x512_160k_ade20k_20220105_162750.log.json)         |
 
 ## Citation
 
diff --git a/configs/segnext/README.md b/configs/segnext/README.md
index 06b63be546..d7434a0621 100644
--- a/configs/segnext/README.md
+++ b/configs/segnext/README.md
@@ -8,7 +8,7 @@
 
 <a href="https://github.com/visual-attention-network/segnext">Official Repo</a>
 
-<a href="https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/mscan.py#L328">Code Snippet</a>
+<a href="https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/backbones/mscan.py#L328">Code Snippet</a>
 
 ## Abstract
 
@@ -26,12 +26,12 @@ We present SegNeXt, a simple convolutional network architecture for semantic seg
 
 ### ADE20K
 
-| Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                                                   |
-| ------- | -------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| SegNeXt | MSCAN-T  | 512x512   | 160000  | 17.88    | 52.38          | A100   | 41.50 | 42.59         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segnext/segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k_20230210_140244-05bd8466.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k_20230210_140244.log.json) |
-| SegNeXt | MSCAN-S  | 512x512   | 160000  | 21.47    | 42.27          | A100   | 44.16 | 45.81         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segnext/segnext_mscan-s_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k_20230214_113014-43013668.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k_20230214_113014.log.json) |
-| SegNeXt | MSCAN-B  | 512x512   | 160000  | 31.03    | 35.15          | A100   | 48.03 | 49.68         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segnext/segnext_mscan-b_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k_20230209_172053-b6f6c70c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k_20230209_172053.log.json) |
-| SegNeXt | MSCAN-L  | 512x512   | 160000  | 43.32    | 22.91          | A100   | 50.99 | 52.10         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/segnext/segnext_mscan-l_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k_20230209_172055-19b14b63.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k_20230209_172055.log.json) |
+| Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                              | download                                                                                                                                                                                                                                                                                                                                                                                   |
+| ------- | -------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | ----------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| SegNeXt | MSCAN-T  | 512x512   | 160000  | 17.88    | 52.38          | A100   | 41.50 | 42.59         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segnext/segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k_20230210_140244-05bd8466.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k_20230210_140244.log.json) |
+| SegNeXt | MSCAN-S  | 512x512   | 160000  | 21.47    | 42.27          | A100   | 44.16 | 45.81         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segnext/segnext_mscan-s_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k_20230214_113014-43013668.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k_20230214_113014.log.json) |
+| SegNeXt | MSCAN-B  | 512x512   | 160000  | 31.03    | 35.15          | A100   | 48.03 | 49.68         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segnext/segnext_mscan-b_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k_20230209_172053-b6f6c70c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k_20230209_172053.log.json) |
+| SegNeXt | MSCAN-L  | 512x512   | 160000  | 43.32    | 22.91          | A100   | 50.99 | 52.10         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segnext/segnext_mscan-l_1xb16-adamw-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k_20230209_172055-19b14b63.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k_20230209_172055.log.json) |
 
 Note:
 
@@ -39,7 +39,7 @@ Note:
 
 - The total batch size is 16. We trained for SegNeXt with a single GPU as the performance degrades significantly when using`SyncBN` (mainly in `OverlapPatchEmbed` modules of `MSCAN`) of PyTorch 1.9.
 
-- There will be subtle differences when model testing as Non-negative Matrix Factorization (NMF) in `LightHamHead` will be initialized randomly. To control this randomness, please set the random seed when model testing. You can modify [`./tools/test.py`](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/tools/test.py) like:
+- There will be subtle differences when model testing as Non-negative Matrix Factorization (NMF) in `LightHamHead` will be initialized randomly. To control this randomness, please set the random seed when model testing. You can modify [`./tools/test.py`](https://github.com/open-mmlab/mmsegmentation/blob/main/tools/test.py) like:
 
 ```python
 def main():
diff --git a/configs/segnext/metafile.yaml b/configs/segnext/metafile.yaml
index faa11c9784..3c8ff5bb92 100644
--- a/configs/segnext/metafile.yaml
+++ b/configs/segnext/metafile.yaml
@@ -33,7 +33,7 @@ Models:
   Paper:
     Title: 'SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation'
     URL: https://arxiv.org/abs/2209.08575
-  Code: https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/mscan.py#L328
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/backbones/mscan.py#L328
   Framework: PyTorch
 - Name: segnext_mscan-s_1xb16-adamw-160k_ade20k-512x512
   In Collection: SegNeXt
@@ -57,7 +57,7 @@ Models:
   Paper:
     Title: 'SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation'
     URL: https://arxiv.org/abs/2209.08575
-  Code: https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/mscan.py#L328
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/backbones/mscan.py#L328
   Framework: PyTorch
 - Name: segnext_mscan-b_1xb16-adamw-160k_ade20k-512x512
   In Collection: SegNeXt
@@ -81,7 +81,7 @@ Models:
   Paper:
     Title: 'SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation'
     URL: https://arxiv.org/abs/2209.08575
-  Code: https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/mscan.py#L328
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/backbones/mscan.py#L328
   Framework: PyTorch
 - Name: segnext_mscan-l_1xb16-adamw-160k_ade20k-512x512
   In Collection: SegNeXt
@@ -105,5 +105,5 @@ Models:
   Paper:
     Title: 'SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation'
     URL: https://arxiv.org/abs/2209.08575
-  Code: https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/backbones/mscan.py#L328
+  Code: https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/backbones/mscan.py#L328
   Framework: PyTorch
diff --git a/configs/sem_fpn/README.md b/configs/sem_fpn/README.md
index 8bbbd0eee0..697cf506e2 100644
--- a/configs/sem_fpn/README.md
+++ b/configs/sem_fpn/README.md
@@ -26,17 +26,17 @@ The recently introduced panoptic segmentation task has renewed our community's i
 
 ### Cityscapes
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FPN    | R-50     | 512x1024  |   80000 |      2.8 | 13.54          | V100   | 74.52 | 76.08         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/sem_fpn/fpn_r50_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x1024_80k_cityscapes/fpn_r50_512x1024_80k_cityscapes_20200717_021437-94018a0d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x1024_80k_cityscapes/fpn_r50_512x1024_80k_cityscapes-20200717_021437.log.json)     |
-| FPN    | R-101    | 512x1024  |   80000 |      3.9 | 10.29          | V100   | 75.80 | 77.40         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/sem_fpn/fpn_r101_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x1024_80k_cityscapes/fpn_r101_512x1024_80k_cityscapes_20200717_012416-c5800d4c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x1024_80k_cityscapes/fpn_r101_512x1024_80k_cityscapes-20200717_012416.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                    | download                                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FPN    | R-50     | 512x1024  |   80000 |      2.8 | 13.54          | V100   | 74.52 | 76.08         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/sem_fpn/fpn_r50_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x1024_80k_cityscapes/fpn_r50_512x1024_80k_cityscapes_20200717_021437-94018a0d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x1024_80k_cityscapes/fpn_r50_512x1024_80k_cityscapes-20200717_021437.log.json)     |
+| FPN    | R-101    | 512x1024  |   80000 |      3.9 | 10.29          | V100   | 75.80 | 77.40         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/sem_fpn/fpn_r101_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x1024_80k_cityscapes/fpn_r101_512x1024_80k_cityscapes_20200717_012416-c5800d4c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x1024_80k_cityscapes/fpn_r101_512x1024_80k_cityscapes-20200717_012416.log.json) |
 
 ### ADE20K
 
-| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                   | download                                                                                                                                                                                                                                                                                                           |
-| ------ | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| FPN    | R-50     | 512x512   |  160000 |      4.9 | 55.77          | V100   | 37.49 | 39.09         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/sem_fpn/fpn_r50_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x512_160k_ade20k/fpn_r50_512x512_160k_ade20k_20200718_131734-5b5a6ab9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x512_160k_ade20k/fpn_r50_512x512_160k_ade20k-20200718_131734.log.json)     |
-| FPN    | R-101    | 512x512   |  160000 |      5.9 | 40.58          | V100   | 39.35 | 40.72         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/sem_fpn/fpn_r101_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x512_160k_ade20k/fpn_r101_512x512_160k_ade20k_20200718_131734-306b5004.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x512_160k_ade20k/fpn_r101_512x512_160k_ade20k-20200718_131734.log.json) |
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                | download                                                                                                                                                                                                                                                                                                           |
+| ------ | -------- | --------- | ------: | -------: | -------------- | ------ | ----: | ------------- | --------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| FPN    | R-50     | 512x512   |  160000 |      4.9 | 55.77          | V100   | 37.49 | 39.09         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/sem_fpn/fpn_r50_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x512_160k_ade20k/fpn_r50_512x512_160k_ade20k_20200718_131734-5b5a6ab9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x512_160k_ade20k/fpn_r50_512x512_160k_ade20k-20200718_131734.log.json)     |
+| FPN    | R-101    | 512x512   |  160000 |      5.9 | 40.58          | V100   | 39.35 | 40.72         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/sem_fpn/fpn_r101_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x512_160k_ade20k/fpn_r101_512x512_160k_ade20k_20200718_131734-306b5004.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x512_160k_ade20k/fpn_r101_512x512_160k_ade20k-20200718_131734.log.json) |
 
 ## Citation
 
diff --git a/configs/setr/README.md b/configs/setr/README.md
index 556c625f41..15be6ec099 100644
--- a/configs/setr/README.md
+++ b/configs/setr/README.md
@@ -47,20 +47,20 @@ This script convert the model from `PRETRAIN_PATH` and store the converted model
 
 ### ADE20K
 
-| Method     | Backbone | Crop Size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                             |
-| ---------- | -------- | --------- | ---------- | ------- | -------- | -------------- | ------ | ----- | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| SETR Naive | ViT-L    | 512x512   | 16         | 160000  | 18.40    | 4.72           | V100   | 48.28 |         49.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l_naive_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_512x512_160k_b16_ade20k/setr_naive_512x512_160k_b16_ade20k_20210619_191258-061f24f5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_512x512_160k_b16_ade20k/setr_naive_512x512_160k_b16_ade20k_20210619_191258.log.json) |
-| SETR PUP   | ViT-L    | 512x512   | 16         | 160000  | 19.54    | 4.50           | V100   | 48.24 |         49.99 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l_pup_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_512x512_160k_b16_ade20k/setr_pup_512x512_160k_b16_ade20k_20210619_191343-7e0ce826.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_512x512_160k_b16_ade20k/setr_pup_512x512_160k_b16_ade20k_20210619_191343.log.json)         |
-| SETR MLA   | ViT-L    | 512x512   | 8          | 160000  | 10.96    | -              | V100   | 47.34 |         49.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l-mla_8xb1-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b8_ade20k/setr_mla_512x512_160k_b8_ade20k_20210619_191118-c6d21df0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b8_ade20k/setr_mla_512x512_160k_b8_ade20k_20210619_191118.log.json)             |
-| SETR MLA   | ViT-L    | 512x512   | 16         | 160000  | 17.30    | 5.25           | V100   | 47.39 |         49.37 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l_mla_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b16_ade20k/setr_mla_512x512_160k_b16_ade20k_20210619_191057-f9741de7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b16_ade20k/setr_mla_512x512_160k_b16_ade20k_20210619_191057.log.json)         |
+| Method     | Backbone | Crop Size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                     | download                                                                                                                                                                                                                                                                                                                             |
+| ---------- | -------- | --------- | ---------- | ------- | -------- | -------------- | ------ | ----- | ------------: | -------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| SETR Naive | ViT-L    | 512x512   | 16         | 160000  | 18.40    | 4.72           | V100   | 48.28 |         49.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/setr/setr_vit-l_naive_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_512x512_160k_b16_ade20k/setr_naive_512x512_160k_b16_ade20k_20210619_191258-061f24f5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_512x512_160k_b16_ade20k/setr_naive_512x512_160k_b16_ade20k_20210619_191258.log.json) |
+| SETR PUP   | ViT-L    | 512x512   | 16         | 160000  | 19.54    | 4.50           | V100   | 48.24 |         49.99 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/setr/setr_vit-l_pup_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_512x512_160k_b16_ade20k/setr_pup_512x512_160k_b16_ade20k_20210619_191343-7e0ce826.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_512x512_160k_b16_ade20k/setr_pup_512x512_160k_b16_ade20k_20210619_191343.log.json)         |
+| SETR MLA   | ViT-L    | 512x512   | 8          | 160000  | 10.96    | -              | V100   | 47.34 |         49.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/setr/setr_vit-l-mla_8xb1-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b8_ade20k/setr_mla_512x512_160k_b8_ade20k_20210619_191118-c6d21df0.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b8_ade20k/setr_mla_512x512_160k_b8_ade20k_20210619_191118.log.json)             |
+| SETR MLA   | ViT-L    | 512x512   | 16         | 160000  | 17.30    | 5.25           | V100   | 47.39 |         49.37 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/setr/setr_vit-l_mla_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b16_ade20k/setr_mla_512x512_160k_b16_ade20k_20210619_191057-f9741de7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b16_ade20k/setr_mla_512x512_160k_b16_ade20k_20210619_191057.log.json)         |
 
 ### Cityscapes
 
-| Method     | Backbone | Crop Size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                                                 |
-| ---------- | -------- | --------- | ---------- | ------- | -------- | -------------- | ------ | ----- | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| SETR Naive | ViT-L    | 768x768   | 8          | 80000   | 24.06    | 0.39           | V100   | 78.10 |         80.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l_naive_8xb1-80k_cityscapes-768x768.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_vit-large_8x1_768x768_80k_cityscapes/setr_naive_vit-large_8x1_768x768_80k_cityscapes_20211123_000505-20728e80.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_vit-large_8x1_768x768_80k_cityscapes/setr_naive_vit-large_8x1_768x768_80k_cityscapes_20211123_000505.log.json) |
-| SETR PUP   | ViT-L    | 768x768   | 8          | 80000   | 27.96    | 0.37           | V100   | 79.21 |         81.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l_pup_8xb1-80k_cityscapes-768x768.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_vit-large_8x1_768x768_80k_cityscapes/setr_pup_vit-large_8x1_768x768_80k_cityscapes_20211122_155115-f6f37b8f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_vit-large_8x1_768x768_80k_cityscapes/setr_pup_vit-large_8x1_768x768_80k_cityscapes_20211122_155115.log.json)         |
-| SETR MLA   | ViT-L    | 768x768   | 8          | 80000   | 24.10    | 0.41           | V100   | 77.00 |         79.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/setr/setr_vit-l_mla_8xb1-80k_cityscapes-768x768.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_vit-large_8x1_768x768_80k_cityscapes/setr_mla_vit-large_8x1_768x768_80k_cityscapes_20211119_101003-7f8dccbe.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_vit-large_8x1_768x768_80k_cityscapes/setr_mla_vit-large_8x1_768x768_80k_cityscapes_20211119_101003.log.json)         |
+| Method     | Backbone | Crop Size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                                                 |
+| ---------- | -------- | --------- | ---------- | ------- | -------- | -------------- | ------ | ----- | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| SETR Naive | ViT-L    | 768x768   | 8          | 80000   | 24.06    | 0.39           | V100   | 78.10 |         80.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/setr/setr_vit-l_naive_8xb1-80k_cityscapes-768x768.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_vit-large_8x1_768x768_80k_cityscapes/setr_naive_vit-large_8x1_768x768_80k_cityscapes_20211123_000505-20728e80.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_vit-large_8x1_768x768_80k_cityscapes/setr_naive_vit-large_8x1_768x768_80k_cityscapes_20211123_000505.log.json) |
+| SETR PUP   | ViT-L    | 768x768   | 8          | 80000   | 27.96    | 0.37           | V100   | 79.21 |         81.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/setr/setr_vit-l_pup_8xb1-80k_cityscapes-768x768.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_vit-large_8x1_768x768_80k_cityscapes/setr_pup_vit-large_8x1_768x768_80k_cityscapes_20211122_155115-f6f37b8f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_vit-large_8x1_768x768_80k_cityscapes/setr_pup_vit-large_8x1_768x768_80k_cityscapes_20211122_155115.log.json)         |
+| SETR MLA   | ViT-L    | 768x768   | 8          | 80000   | 24.10    | 0.41           | V100   | 77.00 |         79.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/setr/setr_vit-l_mla_8xb1-80k_cityscapes-768x768.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_vit-large_8x1_768x768_80k_cityscapes/setr_mla_vit-large_8x1_768x768_80k_cityscapes_20211119_101003-7f8dccbe.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_vit-large_8x1_768x768_80k_cityscapes/setr_mla_vit-large_8x1_768x768_80k_cityscapes_20211119_101003.log.json)         |
 
 ## Citation
 
diff --git a/configs/stdc/README.md b/configs/stdc/README.md
index 1efd65482f..3e8bf60688 100644
--- a/configs/stdc/README.md
+++ b/configs/stdc/README.md
@@ -46,12 +46,12 @@ This script convert model from `PRETRAIN_PATH` and store the converted model in
 
 ### Cityscapes
 
-| Method | Backbone             | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                             |
-| ------ | -------------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| STDC   | STDC1 (No Pretrain)  | 512x1024  |   80000 | 7.15     | 23.06          | V100   | 71.82 | 73.89         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/stdc/stdc1_4xb12-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_512x1024_80k_cityscapes/stdc1_512x1024_80k_cityscapes_20220224_073048-74e6920a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_512x1024_80k_cityscapes/stdc1_512x1024_80k_cityscapes_20220224_073048.log.json)                                     |
-| STDC   | STDC1                | 512x1024  |   80000 | -        | -              | V100   | 74.94 | 76.97         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/stdc/stdc1_in1k-pre_4xb12-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_in1k-pre_512x1024_80k_cityscapes/stdc1_in1k-pre_512x1024_80k_cityscapes_20220224_141648-3d4c2981.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_in1k-pre_512x1024_80k_cityscapes/stdc1_in1k-pre_512x1024_80k_cityscapes_20220224_141648.log.json) |
-| STDC   | STDC2  (No Pretrain) | 512x1024  |   80000 | 8.27     | 23.71          | V100   | 73.15 | 76.13         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/stdc/stdc2_4xb12-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_512x1024_80k_cityscapes/stdc2_512x1024_80k_cityscapes_20220222_132015-fb1e3a1a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_512x1024_80k_cityscapes/stdc2_512x1024_80k_cityscapes_20220222_132015.log.json)                                     |
-| STDC   | STDC2                | 512x1024  |   80000 | -        | -              | V100   | 76.67 | 78.67         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/stdc/stdc2_in1k-pre_4xb12-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_in1k-pre_512x1024_80k_cityscapes/stdc2_in1k-pre_512x1024_80k_cityscapes_20220224_073048-1f8f0f6c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_in1k-pre_512x1024_80k_cityscapes/stdc2_in1k-pre_512x1024_80k_cityscapes_20220224_073048.log.json) |
+| Method | Backbone             | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                             |
+| ------ | -------------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | ----------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| STDC   | STDC1 (No Pretrain)  | 512x1024  |   80000 | 7.15     | 23.06          | V100   | 71.82 | 73.89         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/stdc/stdc1_4xb12-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_512x1024_80k_cityscapes/stdc1_512x1024_80k_cityscapes_20220224_073048-74e6920a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_512x1024_80k_cityscapes/stdc1_512x1024_80k_cityscapes_20220224_073048.log.json)                                     |
+| STDC   | STDC1                | 512x1024  |   80000 | -        | -              | V100   | 74.94 | 76.97         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/stdc/stdc1_in1k-pre_4xb12-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_in1k-pre_512x1024_80k_cityscapes/stdc1_in1k-pre_512x1024_80k_cityscapes_20220224_141648-3d4c2981.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc1_in1k-pre_512x1024_80k_cityscapes/stdc1_in1k-pre_512x1024_80k_cityscapes_20220224_141648.log.json) |
+| STDC   | STDC2  (No Pretrain) | 512x1024  |   80000 | 8.27     | 23.71          | V100   | 73.15 | 76.13         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/stdc/stdc2_4xb12-80k_cityscapes-512x1024.py)          | [model](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_512x1024_80k_cityscapes/stdc2_512x1024_80k_cityscapes_20220222_132015-fb1e3a1a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_512x1024_80k_cityscapes/stdc2_512x1024_80k_cityscapes_20220222_132015.log.json)                                     |
+| STDC   | STDC2                | 512x1024  |   80000 | -        | -              | V100   | 76.67 | 78.67         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/stdc/stdc2_in1k-pre_4xb12-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_in1k-pre_512x1024_80k_cityscapes/stdc2_in1k-pre_512x1024_80k_cityscapes_20220224_073048-1f8f0f6c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/stdc/stdc2_in1k-pre_512x1024_80k_cityscapes/stdc2_in1k-pre_512x1024_80k_cityscapes_20220224_073048.log.json) |
 
 Note:
 
diff --git a/configs/twins/README.md b/configs/twins/README.md
index 306b65fac8..e4b3735b00 100644
--- a/configs/twins/README.md
+++ b/configs/twins/README.md
@@ -44,20 +44,20 @@ python tools/model_converters/twins2mmseg.py ./alt_gvt_base.pth ./pretrained/alt
 
 ### ADE20K
 
-| Method  | Backbone            | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                                                       |
-| ------- | ------------------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FPN     | Twins-PCPVT-S       | 512x512   | 80000   | 6.60     | 27.15          | V100   | 43.26 | 44.11         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_204132-41acd132.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_204132.log.json) |
-| UPerNet | Twins-PCPVT-S       | 512x512   | 160000  | 9.67     | 14.24          | V100   | 46.04 | 46.92         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-s_uperhead_8xb4-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k_20211201_233537-8e99c07a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k_20211201_233537.log.json)         |
-| FPN     | Twins-PCPVT-B       | 512x512   | 80000   | 8.41     | 19.67          | V100   | 45.66 | 46.48         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141019-d396db72.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141019.log.json) |
-| UPerNet | Twins-PCPVT-B (8x2) | 512x512   | 160000  | 6.46     | 12.04          | V100   | 47.91 | 48.64         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-b_uperhead_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k_20211130_141020-02094ea5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k_20211130_141020.log.json)         |
-| FPN     | Twins-PCPVT-L       | 512x512   | 80000   | 10.78    | 14.32          | V100   | 45.94 | 46.70         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_105226-bc6d61dc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_105226.log.json) |
-| UPerNet | Twins-PCPVT-L (8x2) | 512x512   | 160000  | 7.82     | 10.70          | V100   | 49.35 | 50.08         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k_20211201_075053-c6095c07.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k_20211201_075053.log.json)         |
-| FPN     | Twins-SVT-S         | 512x512   | 80000   | 5.80     | 29.79          | V100   | 44.47 | 45.42         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_svt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141006-0a0d3317.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141006.log.json)         |
-| UPerNet | SVT-S  (8x2)        | 512x512   | 160000  | 4.93     | 15.09          | V100   | 46.08 | 46.96         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_svt-s_uperhead_8xb2-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_uperhead_8x2_512x512_160k_ade20k/twins_svt-s_uperhead_8x2_512x512_160k_ade20k_20211130_141005-e48a2d94.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_uperhead_8x2_512x512_160k_ade20k/twins_svt-s_uperhead_8x2_512x512_160k_ade20k_20211130_141005.log.json)                 |
-| FPN     | Twins-SVT-B         | 512x512   | 80000   | 8.75     | 21.10          | V100   | 46.77 | 47.47         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_svt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_113849-88b2907c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_113849.log.json)         |
-| UPerNet | Twins-SVT-B  (8x2)  | 512x512   | 160000  | 6.77     | 12.66          | V100   | 48.04 | 48.87         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_svt-b_uperhead_8xb2-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_uperhead_8x2_512x512_160k_ade20k/twins_svt-b_uperhead_8x2_512x512_160k_ade20k_20211202_040826-0943a1f1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_uperhead_8x2_512x512_160k_ade20k/twins_svt-b_uperhead_8x2_512x512_160k_ade20k_20211202_040826.log.json)                 |
-| FPN     | Twins-SVT-L         | 512x512   | 80000   | 11.20    | 17.80          | V100   | 46.55 | 47.74         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_svt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141005-1d59bee2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141005.log.json)         |
-| UPerNet | Twins-SVT-L  (8x2)  | 512x512   | 160000  | 8.41     | 10.73          | V100   | 49.65 | 50.63         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/twins/twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_uperhead_8x2_512x512_160k_ade20k/twins_svt-l_uperhead_8x2_512x512_160k_ade20k_20211130_141005-3e2cae61.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_uperhead_8x2_512x512_160k_ade20k/twins_svt-l_uperhead_8x2_512x512_160k_ade20k_20211130_141005.log.json)                 |
+| Method  | Backbone            | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU  | mIoU(ms+flip) | config                                                                                                                              | download                                                                                                                                                                                                                                                                                                                                                                                       |
+| ------- | ------------------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | ----------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| FPN     | Twins-PCPVT-S       | 512x512   | 80000   | 6.60     | 27.15          | V100   | 43.26 | 44.11         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/twins/twins_pcpvt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_204132-41acd132.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_204132.log.json) |
+| UPerNet | Twins-PCPVT-S       | 512x512   | 160000  | 9.67     | 14.24          | V100   | 46.04 | 46.92         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/twins/twins_pcpvt-s_uperhead_8xb4-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k_20211201_233537-8e99c07a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k_20211201_233537.log.json)         |
+| FPN     | Twins-PCPVT-B       | 512x512   | 80000   | 8.41     | 19.67          | V100   | 45.66 | 46.48         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/twins/twins_pcpvt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141019-d396db72.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141019.log.json) |
+| UPerNet | Twins-PCPVT-B (8x2) | 512x512   | 160000  | 6.46     | 12.04          | V100   | 47.91 | 48.64         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/twins/twins_pcpvt-b_uperhead_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k_20211130_141020-02094ea5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k_20211130_141020.log.json)         |
+| FPN     | Twins-PCPVT-L       | 512x512   | 80000   | 10.78    | 14.32          | V100   | 45.94 | 46.70         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/twins/twins_pcpvt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_105226-bc6d61dc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_105226.log.json) |
+| UPerNet | Twins-PCPVT-L (8x2) | 512x512   | 160000  | 7.82     | 10.70          | V100   | 49.35 | 50.08         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/twins/twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k_20211201_075053-c6095c07.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k_20211201_075053.log.json)         |
+| FPN     | Twins-SVT-S         | 512x512   | 80000   | 5.80     | 29.79          | V100   | 44.47 | 45.42         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/twins/twins_svt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141006-0a0d3317.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141006.log.json)         |
+| UPerNet | SVT-S  (8x2)        | 512x512   | 160000  | 4.93     | 15.09          | V100   | 46.08 | 46.96         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/twins/twins_svt-s_uperhead_8xb2-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_uperhead_8x2_512x512_160k_ade20k/twins_svt-s_uperhead_8x2_512x512_160k_ade20k_20211130_141005-e48a2d94.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_uperhead_8x2_512x512_160k_ade20k/twins_svt-s_uperhead_8x2_512x512_160k_ade20k_20211130_141005.log.json)                 |
+| FPN     | Twins-SVT-B         | 512x512   | 80000   | 8.75     | 21.10          | V100   | 46.77 | 47.47         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/twins/twins_svt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_113849-88b2907c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_113849.log.json)         |
+| UPerNet | Twins-SVT-B  (8x2)  | 512x512   | 160000  | 6.77     | 12.66          | V100   | 48.04 | 48.87         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/twins/twins_svt-b_uperhead_8xb2-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_uperhead_8x2_512x512_160k_ade20k/twins_svt-b_uperhead_8x2_512x512_160k_ade20k_20211202_040826-0943a1f1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_uperhead_8x2_512x512_160k_ade20k/twins_svt-b_uperhead_8x2_512x512_160k_ade20k_20211202_040826.log.json)                 |
+| FPN     | Twins-SVT-L         | 512x512   | 80000   | 11.20    | 17.80          | V100   | 46.55 | 47.74         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/twins/twins_svt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141005-1d59bee2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141005.log.json)         |
+| UPerNet | Twins-SVT-L  (8x2)  | 512x512   | 160000  | 8.41     | 10.73          | V100   | 49.65 | 50.63         | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/twins/twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_uperhead_8x2_512x512_160k_ade20k/twins_svt-l_uperhead_8x2_512x512_160k_ade20k_20211130_141005-3e2cae61.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_uperhead_8x2_512x512_160k_ade20k/twins_svt-l_uperhead_8x2_512x512_160k_ade20k_20211130_141005.log.json)                 |
 
 Note:
 
diff --git a/configs/unet/README.md b/configs/unet/README.md
index e42cd0f91e..7225fbbf68 100644
--- a/configs/unet/README.md
+++ b/configs/unet/README.md
@@ -26,53 +26,53 @@ There is large consent that successful training of deep networks requires many t
 
 ### Cityscapes
 
-| Method     | Backbone    | Loss          | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                                     |
-| ---------- | ----------- | ------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UNet + FCN | UNet-S5-D16 | Cross Entropy | 512x1024  |  160000 | 17.91    | 3.05           | V100   | 69.10 |         71.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes_20211210_145204-6860854e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes_20211210_145204.log.json) |
+| Method     | Backbone    | Loss          | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                                     |
+| ---------- | ----------- | ------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UNet + FCN | UNet-S5-D16 | Cross Entropy | 512x1024  |  160000 | 17.91    | 3.05           | V100   | 69.10 |         71.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_fcn_4xb4-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes_20211210_145204-6860854e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes_20211210_145204.log.json) |
 
 ### DRIVE
 
-| Method           | Backbone    | Loss                 | Image Size | Crop Size | Stride | Lr schd | Mem (GB) | Inf time (fps) | Device | mDice |  Dice | config                                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                                                                         |
-| ---------------- | ----------- | -------------------- | ---------- | --------- | -----: | ------- | -------- | -------------: | ------ | ----: | ----: | ---------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 584x565    | 64x64     |  42x42 | 40000   | 0.680    |              - | V100   | 88.38 | 78.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-40k_drive-64x64.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_64x64_40k_drive/fcn_unet_s5-d16_64x64_40k_drive_20201223_191051-5daf6d3b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_64x64_40k_drive/unet_s5-d16_64x64_40k_drive-20201223_191051.log.json)                                                                                                 |
-| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 584x565    | 64x64     |  42x42 | 40000   | 0.582    |              - | V100   | 88.71 | 79.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201820-785de5c2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201820.log.json)                         |
-| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 584x565    | 64x64     |  42x42 | 40000   | 0.599    |              - | V100   | 88.35 | 78.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-40k_drive-64x64.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_64x64_40k_drive/pspnet_unet_s5-d16_64x64_40k_drive_20201227_181818-aac73387.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_64x64_40k_drive/pspnet_unet_s5-d16_64x64_40k_drive-20201227_181818.log.json)                                                                             |
-| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 584x565    | 64x64     |  42x42 | 40000   | 0.585    |              - | V100   | 88.76 | 79.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201821-22b3e3ba.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201821.log.json)             |
-| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 584x565    | 64x64     |  42x42 | 40000   | 0.596    |              - | V100   | 88.38 | 78.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_drive-64x64.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_64x64_40k_drive/deeplabv3_unet_s5-d16_64x64_40k_drive_20201226_094047-0671ff20.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_64x64_40k_drive/deeplabv3_unet_s5-d16_64x64_40k_drive-20201226_094047.log.json)                                                                 |
-| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 584x565    | 64x64     |  42x42 | 40000   | 0.582    |              - | V100   | 88.84 | 79.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201825-6bf0efd7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201825.log.json) |
+| Method           | Backbone    | Loss                 | Image Size | Crop Size | Stride | Lr schd | Mem (GB) | Inf time (fps) | Device | mDice |  Dice | config                                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                                                                                         |
+| ---------------- | ----------- | -------------------- | ---------- | --------- | -----: | ------- | -------- | -------------: | ------ | ----: | ----: | ------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 584x565    | 64x64     |  42x42 | 40000   | 0.680    |              - | V100   | 88.38 | 78.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_fcn_4xb4-40k_drive-64x64.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_64x64_40k_drive/fcn_unet_s5-d16_64x64_40k_drive_20201223_191051-5daf6d3b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_64x64_40k_drive/unet_s5-d16_64x64_40k_drive-20201223_191051.log.json)                                                                                                 |
+| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 584x565    | 64x64     |  42x42 | 40000   | 0.582    |              - | V100   | 88.71 | 79.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201820-785de5c2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201820.log.json)                         |
+| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 584x565    | 64x64     |  42x42 | 40000   | 0.599    |              - | V100   | 88.35 | 78.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_pspnet_4xb4-40k_drive-64x64.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_64x64_40k_drive/pspnet_unet_s5-d16_64x64_40k_drive_20201227_181818-aac73387.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_64x64_40k_drive/pspnet_unet_s5-d16_64x64_40k_drive-20201227_181818.log.json)                                                                             |
+| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 584x565    | 64x64     |  42x42 | 40000   | 0.585    |              - | V100   | 88.76 | 79.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201821-22b3e3ba.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201821.log.json)             |
+| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 584x565    | 64x64     |  42x42 | 40000   | 0.596    |              - | V100   | 88.38 | 78.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_drive-64x64.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_64x64_40k_drive/deeplabv3_unet_s5-d16_64x64_40k_drive_20201226_094047-0671ff20.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_64x64_40k_drive/deeplabv3_unet_s5-d16_64x64_40k_drive-20201226_094047.log.json)                                                                 |
+| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 584x565    | 64x64     |  42x42 | 40000   | 0.582    |              - | V100   | 88.84 | 79.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201825-6bf0efd7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201825.log.json) |
 
 ### STARE
 
-| Method           | Backbone    | Loss                 | Image Size | Crop Size | Stride | Lr schd | Mem (GB) | Inf time (fps) | Device | mDice |  Dice | config                                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                                                                                                 |
-| ---------------- | ----------- | -------------------- | ---------- | --------- | -----: | ------- | -------- | -------------: | ------ | ----: | ----: | ------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 605x700    | 128x128   |  85x85 | 40000   | 0.968    |              - | V100   | 89.78 | 81.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-40k_stare-128x128.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_stare/fcn_unet_s5-d16_128x128_40k_stare_20201223_191051-7d77e78b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_stare/unet_s5-d16_128x128_40k_stare-20201223_191051.log.json)                                                                                                 |
-| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 605x700    | 128x128   |  85x85 | 40000   | 0.986    |              - | V100   | 90.65 | 82.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201821-f75705a9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201821.log.json)                         |
-| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 605x700    | 128x128   |  85x85 | 40000   | 0.982    |              - | V100   | 89.89 | 81.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-40k_stare-128x128.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_stare/pspnet_unet_s5-d16_128x128_40k_stare_20201227_181818-3c2923c4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_stare/pspnet_unet_s5-d16_128x128_40k_stare-20201227_181818.log.json)                                                                             |
-| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 605x700    | 128x128   |  85x85 | 40000   | 1.028    |              - | V100   | 90.72 | 82.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201823-f1063ef7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201823.log.json)             |
-| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 605x700    | 128x128   |  85x85 | 40000   | 0.999    |              - | V100   | 89.73 | 80.93 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_stare-128x128.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_stare/deeplabv3_unet_s5-d16_128x128_40k_stare_20201226_094047-93dcb93c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_stare/deeplabv3_unet_s5-d16_128x128_40k_stare-20201226_094047.log.json)                                                                 |
-| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 605x700    | 128x128   |  85x85 | 40000   | 1.010    |              - | V100   | 90.65 | 82.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201825-21db614c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201825.log.json) |
+| Method           | Backbone    | Loss                 | Image Size | Crop Size | Stride | Lr schd | Mem (GB) | Inf time (fps) | Device | mDice |  Dice | config                                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                                                                                 |
+| ---------------- | ----------- | -------------------- | ---------- | --------- | -----: | ------- | -------- | -------------: | ------ | ----: | ----: | --------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 605x700    | 128x128   |  85x85 | 40000   | 0.968    |              - | V100   | 89.78 | 81.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_fcn_4xb4-40k_stare-128x128.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_stare/fcn_unet_s5-d16_128x128_40k_stare_20201223_191051-7d77e78b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_stare/unet_s5-d16_128x128_40k_stare-20201223_191051.log.json)                                                                                                 |
+| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 605x700    | 128x128   |  85x85 | 40000   | 0.986    |              - | V100   | 90.65 | 82.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201821-f75705a9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201821.log.json)                         |
+| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 605x700    | 128x128   |  85x85 | 40000   | 0.982    |              - | V100   | 89.89 | 81.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_pspnet_4xb4-40k_stare-128x128.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_stare/pspnet_unet_s5-d16_128x128_40k_stare_20201227_181818-3c2923c4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_stare/pspnet_unet_s5-d16_128x128_40k_stare-20201227_181818.log.json)                                                                             |
+| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 605x700    | 128x128   |  85x85 | 40000   | 1.028    |              - | V100   | 90.72 | 82.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201823-f1063ef7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201823.log.json)             |
+| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 605x700    | 128x128   |  85x85 | 40000   | 0.999    |              - | V100   | 89.73 | 80.93 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_stare-128x128.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_stare/deeplabv3_unet_s5-d16_128x128_40k_stare_20201226_094047-93dcb93c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_stare/deeplabv3_unet_s5-d16_128x128_40k_stare-20201226_094047.log.json)                                                                 |
+| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 605x700    | 128x128   |  85x85 | 40000   | 1.010    |              - | V100   | 90.65 | 82.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201825-21db614c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201825.log.json) |
 
 ### CHASE_DB1
 
-| Method           | Backbone    | Loss                 | Image Size | Crop Size | Stride | Lr schd | Mem (GB) | Inf time (fps) | Device | mDice |  Dice | config                                                                                                                                               | download                                                                                                                                                                                                                                                                                                                                                                                                                                 |
-| ---------------- | ----------- | -------------------- | ---------- | --------- | -----: | ------- | -------- | -------------: | ------ | ----: | ----: | ---------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 960x999    | 128x128   |  85x85 | 40000   | 0.968    |              - | V100   | 89.46 | 80.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-40k_chase-db1-128x128.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_chase_db1/fcn_unet_s5-d16_128x128_40k_chase_db1_20201223_191051-11543527.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_chase_db1/unet_s5-d16_128x128_40k_chase_db1-20201223_191051.log.json)                                                                                                 |
-| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 960x999    | 128x128   |  85x85 | 40000   | 0.986    |              - | V100   | 89.52 | 80.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201821-1c4eb7cf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201821.log.json)                         |
-| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 960x999    | 128x128   |  85x85 | 40000   | 0.982    |              - | V100   | 89.52 | 80.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-40k_chase-db1-128x128.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1/pspnet_unet_s5-d16_128x128_40k_chase_db1_20201227_181818-68d4e609.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1/pspnet_unet_s5-d16_128x128_40k_chase_db1-20201227_181818.log.json)                                                                             |
-| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 960x999    | 128x128   |  85x85 | 40000   | 1.028    |              - | V100   | 89.45 | 80.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201823-c0802c4d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201823.log.json)             |
-| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 960x999    | 128x128   |  85x85 | 40000   | 0.999    |              - | V100   | 89.57 | 80.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet_s5-d16_deeplabv3_4xb4-40k_chase-db1-128x128.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1/deeplabv3_unet_s5-d16_128x128_40k_chase_db1_20201226_094047-4c5aefa3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1/deeplabv3_unet_s5-d16_128x128_40k_chase_db1-20201226_094047.log.json)                                                                 |
-| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 960x999    | 128x128   |  85x85 | 40000   | 1.010    |              - | V100   | 89.49 | 80.37 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201825-4ef29df5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201825.log.json) |
+| Method           | Backbone    | Loss                 | Image Size | Crop Size | Stride | Lr schd | Mem (GB) | Inf time (fps) | Device | mDice |  Dice | config                                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+| ---------------- | ----------- | -------------------- | ---------- | --------- | -----: | ------- | -------- | -------------: | ------ | ----: | ----: | ------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 960x999    | 128x128   |  85x85 | 40000   | 0.968    |              - | V100   | 89.46 | 80.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_fcn_4xb4-40k_chase-db1-128x128.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_chase_db1/fcn_unet_s5-d16_128x128_40k_chase_db1_20201223_191051-11543527.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_chase_db1/unet_s5-d16_128x128_40k_chase_db1-20201223_191051.log.json)                                                                                                 |
+| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 960x999    | 128x128   |  85x85 | 40000   | 0.986    |              - | V100   | 89.52 | 80.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201821-1c4eb7cf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201821.log.json)                         |
+| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 960x999    | 128x128   |  85x85 | 40000   | 0.982    |              - | V100   | 89.52 | 80.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_pspnet_4xb4-40k_chase-db1-128x128.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1/pspnet_unet_s5-d16_128x128_40k_chase_db1_20201227_181818-68d4e609.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1/pspnet_unet_s5-d16_128x128_40k_chase_db1-20201227_181818.log.json)                                                                             |
+| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 960x999    | 128x128   |  85x85 | 40000   | 1.028    |              - | V100   | 89.45 | 80.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201823-c0802c4d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201823.log.json)             |
+| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 960x999    | 128x128   |  85x85 | 40000   | 0.999    |              - | V100   | 89.57 | 80.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet_s5-d16_deeplabv3_4xb4-40k_chase-db1-128x128.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1/deeplabv3_unet_s5-d16_128x128_40k_chase_db1_20201226_094047-4c5aefa3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1/deeplabv3_unet_s5-d16_128x128_40k_chase_db1-20201226_094047.log.json)                                                                 |
+| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 960x999    | 128x128   |  85x85 | 40000   | 1.010    |              - | V100   | 89.49 | 80.37 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201825-4ef29df5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201825.log.json) |
 
 ### HRF
 
-| Method           | Backbone    | Loss                 | Image Size | Crop Size |  Stride | Lr schd | Mem (GB) | Inf time (fps) | Device | mDice |  Dice | config                                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                                                                         |
-| ---------------- | ----------- | -------------------- | ---------- | --------- | ------: | ------- | -------- | -------------: | ------ | ----: | ----: | ---------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 2336x3504  | 256x256   | 170x170 | 40000   | 2.525    |              - | V100   | 88.92 | 79.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-40k_hrf-256x256.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_256x256_40k_hrf/fcn_unet_s5-d16_256x256_40k_hrf_20201223_173724-d89cf1ed.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_256x256_40k_hrf/unet_s5-d16_256x256_40k_hrf-20201223_173724.log.json)                                                                                                 |
-| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 2336x3504  | 256x256   | 170x170 | 40000   | 2.623    |              - | V100   | 89.64 | 80.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201821-c314da8a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201821.log.json)                         |
-| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 2336x3504  | 256x256   | 170x170 | 40000   | 2.588    |              - | V100   | 89.24 | 80.07 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-40k_hrf-256x256.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_256x256_40k_hrf/pspnet_unet_s5-d16_256x256_40k_hrf_20201227_181818-fdb7e29b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_256x256_40k_hrf/pspnet_unet_s5-d16_256x256_40k_hrf-20201227_181818.log.json)                                                                             |
-| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 2336x3504  | 256x256   | 170x170 | 40000   | 2.798    |              - | V100   | 89.69 | 80.96 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201823-53d492fa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201823.log.json)             |
-| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 2336x3504  | 256x256   | 170x170 | 40000   | 2.604    |              - | V100   | 89.32 | 80.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_hrf-256x256.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf/deeplabv3_unet_s5-d16_256x256_40k_hrf_20201226_094047-3a1fdf85.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf/deeplabv3_unet_s5-d16_256x256_40k_hrf-20201226_094047.log.json)                                                                 |
-| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 2336x3504  | 256x256   | 170x170 | 40000   | 2.607    |              - | V100   | 89.56 | 80.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_202032-59daf7a4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_202032.log.json) |
+| Method           | Backbone    | Loss                 | Image Size | Crop Size |  Stride | Lr schd | Mem (GB) | Inf time (fps) | Device | mDice |  Dice | config                                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                                                                                         |
+| ---------------- | ----------- | -------------------- | ---------- | --------- | ------: | ------- | -------- | -------------: | ------ | ----: | ----: | ------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 2336x3504  | 256x256   | 170x170 | 40000   | 2.525    |              - | V100   | 88.92 | 79.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_fcn_4xb4-40k_hrf-256x256.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_256x256_40k_hrf/fcn_unet_s5-d16_256x256_40k_hrf_20201223_173724-d89cf1ed.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_256x256_40k_hrf/unet_s5-d16_256x256_40k_hrf-20201223_173724.log.json)                                                                                                 |
+| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 2336x3504  | 256x256   | 170x170 | 40000   | 2.623    |              - | V100   | 89.64 | 80.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201821-c314da8a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201821.log.json)                         |
+| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 2336x3504  | 256x256   | 170x170 | 40000   | 2.588    |              - | V100   | 89.24 | 80.07 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_pspnet_4xb4-40k_hrf-256x256.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_256x256_40k_hrf/pspnet_unet_s5-d16_256x256_40k_hrf_20201227_181818-fdb7e29b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_256x256_40k_hrf/pspnet_unet_s5-d16_256x256_40k_hrf-20201227_181818.log.json)                                                                             |
+| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 2336x3504  | 256x256   | 170x170 | 40000   | 2.798    |              - | V100   | 89.69 | 80.96 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201823-53d492fa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201823.log.json)             |
+| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 2336x3504  | 256x256   | 170x170 | 40000   | 2.604    |              - | V100   | 89.32 | 80.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_hrf-256x256.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf/deeplabv3_unet_s5-d16_256x256_40k_hrf_20201226_094047-3a1fdf85.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf/deeplabv3_unet_s5-d16_256x256_40k_hrf-20201226_094047.log.json)                                                                 |
+| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 2336x3504  | 256x256   | 170x170 | 40000   | 2.607    |              - | V100   | 89.56 | 80.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_202032-59daf7a4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_202032.log.json) |
 
 Note:
 
diff --git a/configs/upernet/README.md b/configs/upernet/README.md
index 7d128090bf..c2babbd2a7 100644
--- a/configs/upernet/README.md
+++ b/configs/upernet/README.md
@@ -26,34 +26,34 @@ Humans recognize the visual world at multiple levels: we effortlessly categorize
 
 ### Cityscapes
 
-| Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                           | download                                                                                                                                                                                                                                                                                                                                           |
-| ------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UPerNet | R-50     | 512x1024  |   40000 | 6.4      | 4.25           | V100   | 77.10 |         78.37 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_40k_cityscapes/upernet_r50_512x1024_40k_cityscapes_20200605_094827-aa54cb54.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_40k_cityscapes/upernet_r50_512x1024_40k_cityscapes_20200605_094827.log.json)     |
-| UPerNet | R-101    | 512x1024  |   40000 | 7.4      | 3.79           | V100   | 78.69 |         80.11 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_40k_cityscapes/upernet_r101_512x1024_40k_cityscapes_20200605_094933-ebce3b10.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_40k_cityscapes/upernet_r101_512x1024_40k_cityscapes_20200605_094933.log.json) |
-| UPerNet | R-50     | 769x769   |   40000 | 7.2      | 1.76           | V100   | 77.98 |         79.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_40k_cityscapes/upernet_r50_769x769_40k_cityscapes_20200530_033048-92d21539.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_40k_cityscapes/upernet_r50_769x769_40k_cityscapes_20200530_033048.log.json)         |
-| UPerNet | R-101    | 769x769   |   40000 | 8.4      | 1.56           | V100   | 79.03 |         80.77 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_40k_cityscapes/upernet_r101_769x769_40k_cityscapes_20200530_040819-83c95d01.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_40k_cityscapes/upernet_r101_769x769_40k_cityscapes_20200530_040819.log.json)     |
-| UPerNet | R-50     | 512x1024  |   80000 | -        | -              | V100   | 78.19 |         79.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_80k_cityscapes/upernet_r50_512x1024_80k_cityscapes_20200607_052207-848beca8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_80k_cityscapes/upernet_r50_512x1024_80k_cityscapes_20200607_052207.log.json)     |
-| UPerNet | R-101    | 512x1024  |   80000 | -        | -              | V100   | 79.40 |         80.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_80k_cityscapes/upernet_r101_512x1024_80k_cityscapes_20200607_002403-f05f2345.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_80k_cityscapes/upernet_r101_512x1024_80k_cityscapes_20200607_002403.log.json) |
-| UPerNet | R-50     | 769x769   |   80000 | -        | -              | V100   | 79.39 |         80.92 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_80k_cityscapes/upernet_r50_769x769_80k_cityscapes_20200607_005107-82ae7d15.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_80k_cityscapes/upernet_r50_769x769_80k_cityscapes_20200607_005107.log.json)         |
-| UPerNet | R-101    | 769x769   |   80000 | -        | -              | V100   | 80.10 |         81.49 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_80k_cityscapes/upernet_r101_769x769_80k_cityscapes_20200607_001014-082fc334.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_80k_cityscapes/upernet_r101_769x769_80k_cityscapes_20200607_001014.log.json)     |
+| Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                           |
+| ------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UPerNet | R-50     | 512x1024  |   40000 | 6.4      | 4.25           | V100   | 77.10 |         78.37 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/upernet/upernet_r50_4xb2-40k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_40k_cityscapes/upernet_r50_512x1024_40k_cityscapes_20200605_094827-aa54cb54.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_40k_cityscapes/upernet_r50_512x1024_40k_cityscapes_20200605_094827.log.json)     |
+| UPerNet | R-101    | 512x1024  |   40000 | 7.4      | 3.79           | V100   | 78.69 |         80.11 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/upernet/upernet_r101_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_40k_cityscapes/upernet_r101_512x1024_40k_cityscapes_20200605_094933-ebce3b10.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_40k_cityscapes/upernet_r101_512x1024_40k_cityscapes_20200605_094933.log.json) |
+| UPerNet | R-50     | 769x769   |   40000 | 7.2      | 1.76           | V100   | 77.98 |         79.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/upernet/upernet_r50_4xb2-40k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_40k_cityscapes/upernet_r50_769x769_40k_cityscapes_20200530_033048-92d21539.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_40k_cityscapes/upernet_r50_769x769_40k_cityscapes_20200530_033048.log.json)         |
+| UPerNet | R-101    | 769x769   |   40000 | 8.4      | 1.56           | V100   | 79.03 |         80.77 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/upernet/upernet_r101_4xb2-40k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_40k_cityscapes/upernet_r101_769x769_40k_cityscapes_20200530_040819-83c95d01.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_40k_cityscapes/upernet_r101_769x769_40k_cityscapes_20200530_040819.log.json)     |
+| UPerNet | R-50     | 512x1024  |   80000 | -        | -              | V100   | 78.19 |         79.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/upernet/upernet_r50_4xb2-80k_cityscapes-512x1024.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_80k_cityscapes/upernet_r50_512x1024_80k_cityscapes_20200607_052207-848beca8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_80k_cityscapes/upernet_r50_512x1024_80k_cityscapes_20200607_052207.log.json)     |
+| UPerNet | R-101    | 512x1024  |   80000 | -        | -              | V100   | 79.40 |         80.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/upernet/upernet_r101_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_80k_cityscapes/upernet_r101_512x1024_80k_cityscapes_20200607_002403-f05f2345.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_80k_cityscapes/upernet_r101_512x1024_80k_cityscapes_20200607_002403.log.json) |
+| UPerNet | R-50     | 769x769   |   80000 | -        | -              | V100   | 79.39 |         80.92 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/upernet/upernet_r50_4xb2-80k_cityscapes-769x769.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_80k_cityscapes/upernet_r50_769x769_80k_cityscapes_20200607_005107-82ae7d15.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_80k_cityscapes/upernet_r50_769x769_80k_cityscapes_20200607_005107.log.json)         |
+| UPerNet | R-101    | 769x769   |   80000 | -        | -              | V100   | 80.10 |         81.49 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/upernet/upernet_r101_4xb2-80k_cityscapes-769x769.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_80k_cityscapes/upernet_r101_769x769_80k_cityscapes_20200607_001014-082fc334.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_80k_cityscapes/upernet_r101_769x769_80k_cityscapes_20200607_001014.log.json)     |
 
 ### ADE20K
 
-| Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                       | download                                                                                                                                                                                                                                                                                                                           |
-| ------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UPerNet | R-50     | 512x512   |   80000 | 8.1      | 23.40          | V100   | 40.70 |         41.81 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_80k_ade20k/upernet_r50_512x512_80k_ade20k_20200614_144127-ecc8377b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_80k_ade20k/upernet_r50_512x512_80k_ade20k_20200614_144127.log.json)         |
-| UPerNet | R-101    | 512x512   |   80000 | 9.1      | 20.34          | V100   | 42.91 |         43.96 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_80k_ade20k/upernet_r101_512x512_80k_ade20k_20200614_185117-32e4db94.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_80k_ade20k/upernet_r101_512x512_80k_ade20k_20200614_185117.log.json)     |
-| UPerNet | R-50     | 512x512   |  160000 | -        | -              | V100   | 42.05 |         42.78 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_160k_ade20k/upernet_r50_512x512_160k_ade20k_20200615_184328-8534de8d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_160k_ade20k/upernet_r50_512x512_160k_ade20k_20200615_184328.log.json)     |
-| UPerNet | R-101    | 512x512   |  160000 | -        | -              | V100   | 43.82 |         44.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_160k_ade20k/upernet_r101_512x512_160k_ade20k_20200615_161951-91b32684.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_160k_ade20k/upernet_r101_512x512_160k_ade20k_20200615_161951.log.json) |
+| Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                    | download                                                                                                                                                                                                                                                                                                                           |
+| ------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UPerNet | R-50     | 512x512   |   80000 | 8.1      | 23.40          | V100   | 40.70 |         41.81 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/upernet/upernet_r50_4xb4-80k_ade20k-512x512.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_80k_ade20k/upernet_r50_512x512_80k_ade20k_20200614_144127-ecc8377b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_80k_ade20k/upernet_r50_512x512_80k_ade20k_20200614_144127.log.json)         |
+| UPerNet | R-101    | 512x512   |   80000 | 9.1      | 20.34          | V100   | 42.91 |         43.96 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/upernet/upernet_r101_4xb4-80k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_80k_ade20k/upernet_r101_512x512_80k_ade20k_20200614_185117-32e4db94.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_80k_ade20k/upernet_r101_512x512_80k_ade20k_20200614_185117.log.json)     |
+| UPerNet | R-50     | 512x512   |  160000 | -        | -              | V100   | 42.05 |         42.78 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/upernet/upernet_r50_4xb4-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_160k_ade20k/upernet_r50_512x512_160k_ade20k_20200615_184328-8534de8d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_160k_ade20k/upernet_r50_512x512_160k_ade20k_20200615_184328.log.json)     |
+| UPerNet | R-101    | 512x512   |  160000 | -        | -              | V100   | 43.82 |         44.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/upernet/upernet_r101_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_160k_ade20k/upernet_r101_512x512_160k_ade20k_20200615_161951-91b32684.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_160k_ade20k/upernet_r101_512x512_160k_ade20k_20200615_161951.log.json) |
 
 ### Pascal VOC 2012 + Aug
 
-| Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                               |
-| ------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UPerNet | R-50     | 512x512   |   20000 | 6.4      | 23.17          | V100   | 74.82 |         76.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_20k_voc12aug/upernet_r50_512x512_20k_voc12aug_20200617_165330-5b5890a7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_20k_voc12aug/upernet_r50_512x512_20k_voc12aug_20200617_165330.log.json)     |
-| UPerNet | R-101    | 512x512   |   20000 | 7.5      | 19.98          | V100   | 77.10 |         78.29 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_20k_voc12aug/upernet_r101_512x512_20k_voc12aug_20200617_165629-f14e7f27.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_20k_voc12aug/upernet_r101_512x512_20k_voc12aug_20200617_165629.log.json) |
-| UPerNet | R-50     | 512x512   |   40000 | -        | -              | V100   | 75.92 |         77.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r50_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_40k_voc12aug/upernet_r50_512x512_40k_voc12aug_20200613_162257-ca9bcc6b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_40k_voc12aug/upernet_r50_512x512_40k_voc12aug_20200613_162257.log.json)     |
-| UPerNet | R-101    | 512x512   |   40000 | -        | -              | V100   | 77.43 |         78.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/upernet/upernet_r101_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_40k_voc12aug/upernet_r101_512x512_40k_voc12aug_20200613_163549-e26476ac.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_40k_voc12aug/upernet_r101_512x512_40k_voc12aug_20200613_163549.log.json) |
+| Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                     | download                                                                                                                                                                                                                                                                                                                               |
+| ------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UPerNet | R-50     | 512x512   |   20000 | 6.4      | 23.17          | V100   | 74.82 |         76.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/upernet/upernet_r50_4xb4-20k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_20k_voc12aug/upernet_r50_512x512_20k_voc12aug_20200617_165330-5b5890a7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_20k_voc12aug/upernet_r50_512x512_20k_voc12aug_20200617_165330.log.json)     |
+| UPerNet | R-101    | 512x512   |   20000 | 7.5      | 19.98          | V100   | 77.10 |         78.29 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/upernet/upernet_r101_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_20k_voc12aug/upernet_r101_512x512_20k_voc12aug_20200617_165629-f14e7f27.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_20k_voc12aug/upernet_r101_512x512_20k_voc12aug_20200617_165629.log.json) |
+| UPerNet | R-50     | 512x512   |   40000 | -        | -              | V100   | 75.92 |         77.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/upernet/upernet_r50_4xb4-40k_voc12aug-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_40k_voc12aug/upernet_r50_512x512_40k_voc12aug_20200613_162257-ca9bcc6b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_40k_voc12aug/upernet_r50_512x512_40k_voc12aug_20200613_162257.log.json)     |
+| UPerNet | R-101    | 512x512   |   40000 | -        | -              | V100   | 77.43 |         78.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/upernet/upernet_r101_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_40k_voc12aug/upernet_r101_512x512_40k_voc12aug_20200613_163549-e26476ac.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_40k_voc12aug/upernet_r101_512x512_40k_voc12aug_20200613_163549.log.json) |
 
 ## Citation
 
diff --git a/configs/vit/README.md b/configs/vit/README.md
index 26601d498f..f75326e8e4 100644
--- a/configs/vit/README.md
+++ b/configs/vit/README.md
@@ -44,19 +44,19 @@ This script convert model from `PRETRAIN_PATH` and store the converted model in
 
 ### ADE20K
 
-| Method  | Backbone          | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                  | download                                                                                                                                                                                                                                                                                                                   |
-| ------- | ----------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| UPerNet | ViT-B + MLN       | 512x512   |   80000 | 9.20     | 6.94           | V100   | 47.71 |         49.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_vit-b16_mln_upernet_8xb2-80k_ade20k-512x512.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/upernet_vit-b16_mln_512x512_80k_ade20k_20210624_130547-0403cee1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/20210624_130547.log.json)                |
-| UPerNet | ViT-B + MLN       | 512x512   |  160000 | 9.20     | 7.58           | V100   | 46.75 |         48.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_vit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/upernet_vit-b16_mln_512x512_160k_ade20k_20210624_130547-852fa768.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/20210623_192432.log.json)             |
-| UPerNet | ViT-B + LN + MLN  | 512x512   |  160000 | 9.21     | 6.82           | V100   | 47.73 |         49.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_vit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/upernet_vit-b16_ln_mln_512x512_160k_ade20k_20210621_172828-f444c077.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/20210621_172828.log.json)    |
-| UPerNet | DeiT-S            | 512x512   |   80000 | 4.68     | 29.85          | V100   | 42.96 |         43.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-s16_upernet_8xb2-80k_ade20k-512x512.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/upernet_deit-s16_512x512_80k_ade20k_20210624_095228-afc93ec2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/20210624_095228.log.json)                         |
-| UPerNet | DeiT-S            | 512x512   |  160000 | 4.68     | 29.19          | V100   | 42.87 |         43.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-s16_upernet_8xb2-160k_ade20k-512x512.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/upernet_deit-s16_512x512_160k_ade20k_20210621_160903-5110d916.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/20210621_160903.log.json)                      |
-| UPerNet | DeiT-S + MLN      | 512x512   |  160000 | 5.69     | 11.18          | V100   | 43.82 |         45.07 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-s16_mln_upernet_8xb2-160k_ade20k-512x512.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/upernet_deit-s16_mln_512x512_160k_ade20k_20210621_161021-fb9a5dfb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/20210621_161021.log.json)          |
-| UPerNet | DeiT-S + LN + MLN | 512x512   |  160000 | 5.69     | 12.39          | V100   | 43.52 |         45.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-s16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/upernet_deit-s16_ln_mln_512x512_160k_ade20k_20210621_161021-c0cd652f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/20210621_161021.log.json) |
-| UPerNet | DeiT-B            | 512x512   |   80000 | 7.75     | 9.69           | V100   | 45.24 |         46.73 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-b16_upernet_8xb2-80k_ade20k-512x512.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/upernet_deit-b16_512x512_80k_ade20k_20210624_130529-1e090789.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/20210624_130529.log.json)                         |
-| UPerNet | DeiT-B            | 512x512   |  160000 | 7.75     | 10.39          | V100   | 45.36 |         47.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-b16_upernet_8xb2-160k_ade20k-512x512.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/upernet_deit-b16_512x512_160k_ade20k_20210621_180100-828705d7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/20210621_180100.log.json)                      |
-| UPerNet | DeiT-B + MLN      | 512x512   |  160000 | 9.21     | 7.78           | V100   | 45.46 |         47.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/upernet_deit-b16_mln_512x512_160k_ade20k_20210621_191949-4e1450f3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/20210621_191949.log.json)          |
-| UPerNet | DeiT-B + LN + MLN | 512x512   |  160000 | 9.21     | 7.75           | V100   | 45.37 |         47.23 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_deit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/upernet_deit-b16_ln_mln_512x512_160k_ade20k_20210623_153535-8a959c14.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/20210623_153535.log.json) |
+| Method  | Backbone          | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                               | download                                                                                                                                                                                                                                                                                                                   |
+| ------- | ----------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UPerNet | ViT-B + MLN       | 512x512   |   80000 | 9.20     | 6.94           | V100   | 47.71 |         49.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/vit/vit_vit-b16_mln_upernet_8xb2-80k_ade20k-512x512.py)      | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/upernet_vit-b16_mln_512x512_80k_ade20k_20210624_130547-0403cee1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/20210624_130547.log.json)                |
+| UPerNet | ViT-B + MLN       | 512x512   |  160000 | 9.20     | 7.58           | V100   | 46.75 |         48.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/vit/vit_vit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py)     | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/upernet_vit-b16_mln_512x512_160k_ade20k_20210624_130547-852fa768.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/20210623_192432.log.json)             |
+| UPerNet | ViT-B + LN + MLN  | 512x512   |  160000 | 9.21     | 6.82           | V100   | 47.73 |         49.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/vit/vit_vit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/upernet_vit-b16_ln_mln_512x512_160k_ade20k_20210621_172828-f444c077.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/20210621_172828.log.json)    |
+| UPerNet | DeiT-S            | 512x512   |   80000 | 4.68     | 29.85          | V100   | 42.96 |         43.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/vit/vit_deit-s16_upernet_8xb2-80k_ade20k-512x512.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/upernet_deit-s16_512x512_80k_ade20k_20210624_095228-afc93ec2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/20210624_095228.log.json)                         |
+| UPerNet | DeiT-S            | 512x512   |  160000 | 4.68     | 29.19          | V100   | 42.87 |         43.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/vit/vit_deit-s16_upernet_8xb2-160k_ade20k-512x512.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/upernet_deit-s16_512x512_160k_ade20k_20210621_160903-5110d916.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/20210621_160903.log.json)                      |
+| UPerNet | DeiT-S + MLN      | 512x512   |  160000 | 5.69     | 11.18          | V100   | 43.82 |         45.07 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/vit/vit_deit-s16_mln_upernet_8xb2-160k_ade20k-512x512.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/upernet_deit-s16_mln_512x512_160k_ade20k_20210621_161021-fb9a5dfb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/20210621_161021.log.json)          |
+| UPerNet | DeiT-S + LN + MLN | 512x512   |  160000 | 5.69     | 12.39          | V100   | 43.52 |         45.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/vit/vit_deit-s16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/upernet_deit-s16_ln_mln_512x512_160k_ade20k_20210621_161021-c0cd652f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/20210621_161021.log.json) |
+| UPerNet | DeiT-B            | 512x512   |   80000 | 7.75     | 9.69           | V100   | 45.24 |         46.73 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/vit/vit_deit-b16_upernet_8xb2-80k_ade20k-512x512.py)         | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/upernet_deit-b16_512x512_80k_ade20k_20210624_130529-1e090789.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/20210624_130529.log.json)                         |
+| UPerNet | DeiT-B            | 512x512   |  160000 | 7.75     | 10.39          | V100   | 45.36 |         47.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/vit/vit_deit-b16_upernet_8xb2-160k_ade20k-512x512.py)        | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/upernet_deit-b16_512x512_160k_ade20k_20210621_180100-828705d7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/20210621_180100.log.json)                      |
+| UPerNet | DeiT-B + MLN      | 512x512   |  160000 | 9.21     | 7.78           | V100   | 45.46 |         47.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/vit/vit_deit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/upernet_deit-b16_mln_512x512_160k_ade20k_20210621_191949-4e1450f3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/20210621_191949.log.json)          |
+| UPerNet | DeiT-B + LN + MLN | 512x512   |  160000 | 9.21     | 7.75           | V100   | 45.37 |         47.23 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/vit/vit_deit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/upernet_deit-b16_ln_mln_512x512_160k_ade20k_20210623_153535-8a959c14.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/20210623_153535.log.json) |
 
 ## Citation
 
diff --git a/demo/MMSegmentation_Tutorial.ipynb b/demo/MMSegmentation_Tutorial.ipynb
index 1d92342ae6..ac8601b321 100644
--- a/demo/MMSegmentation_Tutorial.ipynb
+++ b/demo/MMSegmentation_Tutorial.ipynb
@@ -7,7 +7,7 @@
     "id": "view-in-github"
    },
    "source": [
-    "<a href=\"https://colab.research.google.com/github/open-mmlab/mmsegmentation/blob/dev-1.x/demo/MMSegmentation_Tutorial.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+    "<a href=\"https://colab.research.google.com/github/open-mmlab/mmsegmentation/blob/main/demo/MMSegmentation_Tutorial.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
    ]
   },
   {
@@ -89,7 +89,7 @@
    "outputs": [],
    "source": [
     "!rm -rf mmsegmentation\n",
-    "!git clone -b dev-1.x https://github.com/open-mmlab/mmsegmentation.git \n",
+    "!git clone -b main https://github.com/open-mmlab/mmsegmentation.git \n",
     "%cd mmsegmentation\n",
     "!pip install -e ."
    ]
diff --git a/docker/Dockerfile b/docker/Dockerfile
index 73a0fac121..982b09bdc6 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -28,7 +28,7 @@ RUN ["/bin/bash", "-c", "mim install mmengine"]
 RUN ["/bin/bash", "-c", "mim install mmcv==${MMCV}"]
 
 # Install MMSegmentation
-RUN git clone -b dev-1.x https://github.com/open-mmlab/mmsegmentation.git /mmsegmentation
+RUN git clone -b main https://github.com/open-mmlab/mmsegmentation.git /mmsegmentation
 WORKDIR /mmsegmentation
 ENV FORCE_CUDA="1"
 RUN pip install -r requirements.txt
diff --git a/docs/en/advanced_guides/add_models.md b/docs/en/advanced_guides/add_models.md
index e470e48ef2..ed5c9ce611 100644
--- a/docs/en/advanced_guides/add_models.md
+++ b/docs/en/advanced_guides/add_models.md
@@ -49,7 +49,7 @@ Here we show how to develop a new backbone with an example of MobileNet.
 
 ### Add new heads
 
-In MMSegmentation, we provide a [BaseDecodeHead](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/models/decode_heads/decode_head.py#L17) for developing all segmentation heads.
+In MMSegmentation, we provide a [BaseDecodeHead](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/decode_heads/decode_head.py#L17) for developing all segmentation heads.
 All newly implemented decode heads should be derived from it.
 Here we show how to develop a new head with the example of [PSPNet](https://arxiv.org/abs/1612.01105) as the following.
 
@@ -166,7 +166,7 @@ loss_decode=dict(type='MyLoss', loss_weight=1.0))
 
 ### Add new data preprocessor
 
-In MMSegmentation 1.x versions, we use [SegDataPreProcessor](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/data_preprocessor.py#L13) to copy data to the target device and preprocess the data into the model input format as default. Here we show how to develop a new data preprocessor.
+In MMSegmentation 1.x versions, we use [SegDataPreProcessor](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/data_preprocessor.py#L13) to copy data to the target device and preprocess the data into the model input format as default. Here we show how to develop a new data preprocessor.
 
 1. Create a new file `mmseg/models/my_datapreprocessor.py`.
 
@@ -204,7 +204,7 @@ In MMSegmentation 1.x versions, we use [SegDataPreProcessor](https://github.com/
 
 The segmentor is an algorithmic architecture in which users can customize their algorithms by adding customized components and defining the logic of algorithm execution. Please refer to [the model document](./models.md) for more details.
 
-Since the [BaseSegmentor](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/models/segmentors/base.py#L15) in MMSegmentation unifies three modes for a forward process, to develop a new segmentor, users need to overwrite `loss`, `predict` and `_forward` methods corresponding to the `loss`, `predict` and `tensor` modes.
+Since the [BaseSegmentor](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/segmentors/base.py#L15) in MMSegmentation unifies three modes for a forward process, to develop a new segmentor, users need to overwrite `loss`, `predict` and `_forward` methods corresponding to the `loss`, `predict` and `tensor` modes.
 
 Here we show how to develop a new segmentor.
 
diff --git a/docs/en/advanced_guides/data_flow.md b/docs/en/advanced_guides/data_flow.md
index 20d23084ab..404035aee4 100644
--- a/docs/en/advanced_guides/data_flow.md
+++ b/docs/en/advanced_guides/data_flow.md
@@ -16,7 +16,7 @@ val_cfg = dict(type='ValLoop')
 test_cfg = dict(type='TestLoop')
 ```
 
-In the above diagram, the red line indicates the [train_step](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/advanced_guides/models.md#train_step). At each training iteration, dataloader loads images from storage and transfer to data preprocessor, data preprocessor would put images to the specific device and stack data to batch, then model accepts the batch data as inputs, finally the outputs of the model would be sent to optimizer. The blue line indicates [val_step](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/advanced_guides/models.md#val_step) and [test_step](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/advanced_guides/models.md#test_step). The dataflow of these two process is similar to the `train_step` except the outputs of model, since model parameters are freezed when doing evaluation, the model output would be transferred to [Evaluator](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/advanced_guides/evaluation.md#ioumetric) to compute metrics.
+In the above diagram, the red line indicates the [train_step](./models.md#train_step). At each training iteration, dataloader loads images from storage and transfer to data preprocessor, data preprocessor would put images to the specific device and stack data to batch, then model accepts the batch data as inputs, finally the outputs of the model would be sent to optimizer. The blue line indicates [val_step](./models.md#val_step) and [test_step](./models.md#test_step). The dataflow of these two process is similar to the `train_step` except the outputs of model, since model parameters are freezed when doing evaluation, the model output would be transferred to [Evaluator](./evaluation.md#ioumetric) to compute metrics.
 
 ## Dataflow convention in MMSegmentation
 
@@ -26,7 +26,7 @@ From the diagram above, we could see the basic dataflow. In this section, we wou
 
 DataLoader is an essential component in training and testing pipelines of MMEngine. Conceptually, it is derived from and consistent with [PyTorch](https://pytorch.org/). DataLoader loads data from filesystem and the original data passes through data preparation pipeline, then it would be sent to Data Preprocessor.
 
-MMSegmentation defines the default data format at [PackSegInputs](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/datasets/transforms/formatting.py#L12), it's the last component of `train_pipeline` and `test_pipeline`. Please refer to [data transform documentation](https://mmsegmentation.readthedocs.io/en/dev-1.x/advanced_guides/transforms.html) for more information about data transform `pipeline`.
+MMSegmentation defines the default data format at [PackSegInputs](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/datasets/transforms/formatting.py#L12), it's the last component of `train_pipeline` and `test_pipeline`. Please refer to [data transform documentation](./transforms.md) for more information about data transform `pipeline`.
 
 Without any modifications, the return value of PackSegInputs is usually a `dict` and has only two keys, `inputs` and `data_samples`. The following pseudo-code shows the data types of the data loader output in mmseg, which is a batch of fetched data samples from the dataset, and data loader packs them into a dictionary of the list. `inputs` is the list of input tensors to the model and `data_samples` contains a list of input images' meta information and corresponding ground truth.
 
@@ -37,11 +37,11 @@ dict(
 )
 ```
 
-**Note:** [SegDataSample](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/structures/seg_data_sample.py) is a data structure interface of MMSegmentation, it is used as an interface between different components. `SegDataSample` implements the abstract data element `mmengine.structures.BaseDataElement`, please refer to [the SegDataSample documentation](https://mmsegmentation.readthedocs.io/en/1.x/advanced_guides/structures.html) and [data element documentation](https://mmengine.readthedocs.io/en/latest/advanced_tutorials/data_element.html) in [MMEngine](https://github.com/open-mmlab/mmengine) for more information.
+**Note:** [SegDataSample](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/structures/seg_data_sample.py) is a data structure interface of MMSegmentation, it is used as an interface between different components. `SegDataSample` implements the abstract data element `mmengine.structures.BaseDataElement`, please refer to [the SegDataSample documentation](./structures.md) and [data element documentation](https://mmengine.readthedocs.io/en/latest/advanced_tutorials/data_element.html) in [MMEngine](https://github.com/open-mmlab/mmengine) for more information.
 
 ### Data Preprocessor to Model
 
-Though drawn separately in the diagram [above](#overview-of-dataflow), data_preprocessor is a part of the model and thus can be found in [Model tutorial](https://mmsegmentation.readthedocs.io/en/dev-1.x/advanced_guides/models.html) at data preprocessor chapter.
+Though drawn separately in the diagram [above](#overview-of-dataflow), data_preprocessor is a part of the model and thus can be found in [Model tutorial](./models.md) at data preprocessor chapter.
 
 The return value of data preprocessor is a dictionary, containing `inputs` and `data_samples`, `inputs` is batched images, a 4D tensor, and some additional meta info used in data preprocesses would be added to the `data_samples`. When transferred to the network, the dictionary would be unpacked to two values. The following pseudo-codes show the return value of the data preprocessor and the input values of model.
 
@@ -59,21 +59,21 @@ class Network(BaseSegmentor):
         pass
 ```
 
-**Note:** Model forward has 3 kinds of mode, which is controlled by input argumentmode, please refer [model tutorial](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/advanced_guides/models.md) for more details.
+**Note:** Model forward has 3 kinds of mode, which is controlled by input argumentmode, please refer [model tutorial](./models.md) for more details.
 
 ### Model output
 
-As [model tutorial](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/advanced_guides/models.md#forward) mentioned 3 kinds of mode forward with 3 kinds of output. `train_step`and `test_step`(or `val_step`) correspond to `'loss'` and `'predict'` respectively.
+As [model tutorial](./models.md#forward) mentioned 3 kinds of mode forward with 3 kinds of output. `train_step`and `test_step`(or `val_step`) correspond to `'loss'` and `'predict'` respectively.
 
-In `test_step` or `val_step`, the inference results would be transferred to `Evaluator`. You might read the [evaluation document](https://mmsegmentation.readthedocs.io/en/dev-1.x/advanced_guides/evaluation.html) for more information about `Evaluator`.
+In `test_step` or `val_step`, the inference results would be transferred to `Evaluator`. You might read the [evaluation document](./evaluation.md) for more information about `Evaluator`.
 
-After inference, the [BaseSegmentor](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/segmentors/base.py#L15) in MMSegmentation would do a simple post process to pack inference results, the segmentation logits produced by the neural network, segmentation mask after the `argmax` operation and ground truth(if exists) would be packed into a similar `SegDataSample` instance. The return value of [postprocess_result](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/segmentors/base.py#L132) is a **`List` of `SegDataSample`**. Following diagram shows the key properties of these `SegDataSample` instances.
+After inference, the [BaseSegmentor](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/segmentors/base.py#L15) in MMSegmentation would do a simple post process to pack inference results, the segmentation logits produced by the neural network, segmentation mask after the `argmax` operation and ground truth(if exists) would be packed into a similar `SegDataSample` instance. The return value of [postprocess_result](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/segmentors/base.py#L132) is a **`List` of `SegDataSample`**. Following diagram shows the key properties of these `SegDataSample` instances.
 
 ![SegDataSample](https://user-images.githubusercontent.com/15952744/209912225-ab46a8d9-904a-43cb-8bf1-8bec4938ed29.png)
 
-The same as Data Preprocessor, loss function is also a part of the model, it's a property of [decode head](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/decode_heads/decode_head.py#L142).
+The same as Data Preprocessor, loss function is also a part of the model, it's a property of [decode head](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/decode_heads/decode_head.py#L142).
 
-In MMSegmentation, the method [loss_by_feat](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/decode_heads/decode_head.py#L291) of `decode_head` is an unified interface used to compute loss.
+In MMSegmentation, the method [loss_by_feat](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/decode_heads/decode_head.py#L291) of `decode_head` is an unified interface used to compute loss.
 
 Parameters:
 
@@ -84,4 +84,4 @@ Returns:
 
 - dict\[str, Tensor\]: a dictionary of loss components
 
-**Note:** The `train_step` transfers the loss into OptimWrapper to update the weights in model, please refer [train_step](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/advanced_guides/models.md#train_step) for more details.
+**Note:** The `train_step` transfers the loss into OptimWrapper to update the weights in model, please refer [train_step](./models.md#train_step) for more details.
diff --git a/docs/en/advanced_guides/datasets.md b/docs/en/advanced_guides/datasets.md
index a1b8044b3d..c655a3ff55 100644
--- a/docs/en/advanced_guides/datasets.md
+++ b/docs/en/advanced_guides/datasets.md
@@ -1,14 +1,14 @@
 # Dataset
 
-Dataset classes in MMSegmentation have two functions: (1) load data information after [data preparation](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/user_guides/2_dataset_prepare.md)
-and (2) send data into [dataset transform pipeline](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/datasets/basesegdataset.py#L141) to do [data augmentation](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/advanced_guides/transforms.md).
+Dataset classes in MMSegmentation have two functions: (1) load data information after [data preparation](../user_guides/2_dataset_prepare.md)
+and (2) send data into [dataset transform pipeline](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/datasets/basesegdataset.py#L141) to do [data augmentation](./transforms.md).
 There are 2 kinds of loaded information: (1) meta information which is original dataset information such as categories (classes) of dataset and their corresponding palette information, (2) data information which includes
 the path of dataset images and labels.
 The tutorial includes some main interfaces in MMSegmentation 1.x dataset class: methods of loading data information and modifying dataset classes in base dataset class, and the relationship between dataset and the data transform pipeline.
 
 ## Main Interfaces
 
-Take Cityscapes as an example, if you want to run the example, please download and [preprocess](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/user_guides/2_dataset_prepare.md#cityscapes)
+Take Cityscapes as an example, if you want to run the example, please download and [preprocess](../user_guides/2_dataset_prepare.md#cityscapes)
 Cityscapes dataset in `data` directory, before running the demo code:
 
 Instantiate Cityscapes training dataset:
@@ -108,7 +108,7 @@ print(dataset.metainfo)
 ```
 
 The return value of dataset `__getitem__` method is the output of data samples after data augmentation, whose type is also `dict`. It has two fields: `'inputs'` corresponding to images after data augmentation,
-and `'data_samples'` corresponding to `SegDataSample`\](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/advanced_guides/structures.md) which is new data structures in MMSegmentation 1.x,
+and `'data_samples'` corresponding to [`SegDataSample`](./structures.md) which is new data structures in MMSegmentation 1.x,
 and `gt_sem_seg` of `SegDataSample` has labels after data augmentation operations.
 
 ```python
@@ -179,19 +179,19 @@ print(dataset[0])
 
 ## BaseSegDataset
 
-As mentioned above, dataset classes have the same functions, we implemented  [`BaseSegDataset`](https://mmsegmentation.readthedocs.io/en/dev-1.x/api.html?highlight=BaseSegDataset#mmseg.datasets.BaseSegDataset) to reues the common functions.
+As mentioned above, dataset classes have the same functions, we implemented  [`BaseSegDataset`](https://mmsegmentation.readthedocs.io/en/main/api.html?highlight=BaseSegDataset#mmseg.datasets.BaseSegDataset) to reues the common functions.
 It inherits [`BaseDataset` of MMEngine](https://github.com/open-mmlab/mmengine/blob/main/docs/en/advanced_tutorials/basedataset.md) and follows unified initialization process of OpenMMLab. It supports the highly effective interior storing format, some functions like
 dataset concatenation and repeatedly sampling. In MMSegmentation `BaseSegDataset`, the **method of loading data information** (`load_data_list`) is redefined and adds new `get_label_map` method to **modify dataset classes information**.
 
 ### Loading Dataset Information
 
 The loaded data information includes the path of images samples and annotations samples, the detailed implementation could be found in
-[`load_data_list`](https://github.com/open-mmlab/mmsegmentation/blob/163277bfe0fa8fefb63ee5137917fafada1b301c/mmseg/datasets/basesegdataset.py#L231) of `BaseSegDataset` in MMSegmentation.
+[`load_data_list`](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/datasets/basesegdataset.py#L231) of `BaseSegDataset` in MMSegmentation.
 There are two main methods to acquire the path of images and labels:
 
 1. Load file paths according to the dirictory and suffix of input images and annotations
 
-If the dataset directory structure is organized as below, the [`load_data_list`](https://github.com/open-mmlab/mmsegmentation/blob/163277bfe0fa8fefb63ee5137917fafada1b301c/mmseg/datasets/basesegdataset.py#L231) can parse dataset directory Structure:
+If the dataset directory structure is organized as below, the [`load_data_list`](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/datasets/basesegdataset.py#L231) can parse dataset directory Structure:
 
 ```
 ├── data
@@ -344,7 +344,7 @@ print(dataset.metainfo)
 ```
 
 Meta information is different from default setting of Cityscapes dataset. Moreover, `label_map` field is also defined, which is used for modifying label index of each pixel on segmentation mask.
-The segmentation label would re-map class information by `label_map`, [here](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/datasets/basesegdataset.py#L151) is detailed implementation:
+The segmentation label would re-map class information by `label_map`, [here](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/datasets/basesegdataset.py#L151) is detailed implementation:
 
 ```python
 gt_semantic_seg_copy = gt_semantic_seg.copy()
diff --git a/docs/en/advanced_guides/engine.md b/docs/en/advanced_guides/engine.md
index 0ed08fa4b5..7acfe5ad64 100644
--- a/docs/en/advanced_guides/engine.md
+++ b/docs/en/advanced_guides/engine.md
@@ -70,14 +70,14 @@ It is not recommended for users to modify the default hook priorities. Please re
 
 The following are the default hooks used in MMSegmentation:
 
-|                                                           Hook                                                            |                                                          Function                                                          |     Priority      |
-| :-----------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------: | :---------------: |
-|            [IterTimerHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/iter_timer_hook.py)            |                                          Record the time spent on each iteration.                                          |    NORMAL (50)    |
-|               [LoggerHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/logger_hook.py)                | Collect log records from different components in `Runner` and output them to terminal, JSON file, tensorboard, wandb, etc. | BELOW_NORMAL (60) |
-|       [ParamSchedulerHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/param_scheduler_hook.py)       |                       Update some hyperparameters in the optimizer, such as learning rate momentum.                        |     LOW (70)      |
-|           [CheckpointHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/checkpoint_hook.py)            |                                              Regularly save checkpoint files.                                              |   VERY_LOW (90)   |
-|        [DistSamplerSeedHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/sampler_seed_hook.py)        |                                     Ensure the distributed sampler shuffle is enabled.                                     |    NORMAL (50)    |
-| [SegVisualizationHook](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/visualization/local_visualizer.py) |                                Visualize prediction results during validation and testing.                                 |    NORMAL (50)    |
+|                                                          Hook                                                          |                                                          Function                                                          |     Priority      |
+| :--------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------: | :---------------: |
+|          [IterTimerHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/iter_timer_hook.py)           |                                          Record the time spent on each iteration.                                          |    NORMAL (50)    |
+|              [LoggerHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/logger_hook.py)              | Collect log records from different components in `Runner` and output them to terminal, JSON file, tensorboard, wandb, etc. | BELOW_NORMAL (60) |
+|     [ParamSchedulerHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/param_scheduler_hook.py)      |                       Update some hyperparameters in the optimizer, such as learning rate momentum.                        |     LOW (70)      |
+|          [CheckpointHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/checkpoint_hook.py)          |                                              Regularly save checkpoint files.                                              |   VERY_LOW (90)   |
+|      [DistSamplerSeedHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/sampler_seed_hook.py)       |                                     Ensure the distributed sampler shuffle is enabled.                                     |    NORMAL (50)    |
+| [SegVisualizationHook](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/visualization/local_visualizer.py) |                                Visualize prediction results during validation and testing.                                 |    NORMAL (50)    |
 
 MMSegmentation registers some hooks with essential training functions in `default_hooks`:
 
@@ -149,7 +149,7 @@ custom_hooks = [
 
 ### SegVisualizationHook
 
-MMSegmentation implemented [`SegVisualizationHook`](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/engine/hooks/visualization_hook.py#L17), which is used to visualize prediction results during validation and testing.
+MMSegmentation implemented [`SegVisualizationHook`](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/engine/hooks/visualization_hook.py#L17), which is used to visualize prediction results during validation and testing.
 `SegVisualizationHook` overrides the `_after_iter` method in the base class `Hook`. During validation or testing, it calls the `add_datasample` method of `visualizer` to draw semantic segmentation results according to the specified iteration interval. The specific implementation is as follows:
 
 ```python
@@ -185,7 +185,7 @@ class SegVisualizationHook(Hook):
 
 ```
 
-For more details about visualization, you can check [here](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/user_guides/visualization.md).
+For more details about visualization, you can check [here](../user_guides/visualization.md).
 
 ## Optimizer
 
@@ -237,7 +237,7 @@ The default setting for `loss_scale` in [`AmpOptimWrapper`](https://github.com/o
 
 In model training, if you want to set different optimization strategies for different parameters in the optimizer, such as setting different learning rates, weight decay, and other hyperparameters, you can achieve this by setting `paramwise_cfg` in the `optim_wrapper` of the configuration file.
 
-The following config file uses the [ViT `optim_wrapper`](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_vit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py#L15-L27) as an example to introduce the use of `paramwise_cfg` parameters. During training, the weight decay parameter coefficients for the `pos_embed`, `mask_token`, and `norm` modules are set to 0. That is, during training, the weight decay for these modules will be changed to `weight_decay * decay_mult`=0.
+The following config file uses the [ViT `optim_wrapper`](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/vit/vit_vit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py#L15-L27) as an example to introduce the use of `paramwise_cfg` parameters. During training, the weight decay parameter coefficients for the `pos_embed`, `mask_token`, and `norm` modules are set to 0. That is, during training, the weight decay for these modules will be changed to `weight_decay * decay_mult`=0.
 
 ```python
 optimizer = dict(
@@ -259,7 +259,7 @@ Here, `decay_mult` refers to the weight decay coefficient for the corresponding
 
 The default optimizer wrapper constructor [`DefaultOptimWrapperConstructor`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/optim/optimizer/default_constructor.py#L19) builds the optimizer used in training based on the input `optim_wrapper` and `paramwise_cfg` defined in the `optim_wrapper`. When the functionality of [`DefaultOptimWrapperConstructor`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/optim/optimizer/default_constructor.py#L19) does not meet the requirements, you can customize the optimizer wrapper constructor to implement the configuration of hyperparameters.
 
-MMSegmentation has implemented the [`LearningRateDecayOptimizerConstructor`](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/engine/optimizers/layer_decay_optimizer_constructor.py#L104), which can decay the learning rate of model parameters in the backbone networks of ConvNeXt, BEiT, and MAE models during training according to the defined decay ratio (`decay_rate`). The configuration in the configuration file is as follows:
+MMSegmentation has implemented the [`LearningRateDecayOptimizerConstructor`](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/engine/optimizers/layer_decay_optimizer_constructor.py#L104), which can decay the learning rate of model parameters in the backbone networks of ConvNeXt, BEiT, and MAE models during training according to the defined decay ratio (`decay_rate`). The configuration in the configuration file is as follows:
 
 ```python
 optim_wrapper = dict(
diff --git a/docs/en/advanced_guides/evaluation.md b/docs/en/advanced_guides/evaluation.md
index 1e42db2a10..ca0beeeccf 100644
--- a/docs/en/advanced_guides/evaluation.md
+++ b/docs/en/advanced_guides/evaluation.md
@@ -2,10 +2,7 @@
 
 The evaluation procedure would be executed at [ValLoop](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/loops.py#L300) and [TestLoop](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/loops.py#L373), users can evaluate model performance during training or using the test script with simple settings in the configuration file. The `ValLoop` and `TestLoop` are properties of [Runner](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/runner.py#L59), they will be built the first time they are called. To build the `ValLoop` successfully, the `val_dataloader` and `val_evaluator` must be set when building `Runner` since `dataloader` and `evaluator` are required parameters, and the same goes for `TestLoop`. For more information about the Runner's design, please refer to the [documentation](https://github.com/open-mmlab/mmengine/blob/main/docs/en/design/runner.md) of [MMEngine](https://github.com/open-mmlab/mmengine).
 
-<center>
-  <img src='../../../resources/test_step.png' />
-  <center>test_step/val_step dataflow</center>
-</center>
+![test_step/val_step dataflow](https://user-images.githubusercontent.com/15952744/228828179-3269baa3-bebd-4c9a-9787-59e7d785fbcf.png)
 
 In MMSegmentation, we write the settings of dataloader and metrics in the config files of datasets and the configuration of the evaluation loop in the `schedule_x` config files by default.
 
diff --git a/docs/en/advanced_guides/models.md b/docs/en/advanced_guides/models.md
index 84e6cb6a9e..b0089869d9 100644
--- a/docs/en/advanced_guides/models.md
+++ b/docs/en/advanced_guides/models.md
@@ -34,15 +34,8 @@ MMSegmentation wraps `BaseModel` and implements the [BaseSegmentor](https://gith
 
 ### forward
 
-<center>
-  <img src='../../../resources/encoder_decoder_dataflow.png' />
-  <center>EncoderDecoder dataflow</center>
-</center>
-
-<center>
-  <center><img src='../../../resources/cascade_encoder_decoder_dataflow.png' /></center>
-  <center>CascadeEncoderDecoder dataflow</center>
-</center>
+![EncoderDecoder dataflow](https://user-images.githubusercontent.com/15952744/228827860-c0e34875-d370-4736-84f0-9560c26c9576.png)
+![CascadeEncoderDecoder dataflow](https://user-images.githubusercontent.com/15952744/228827987-aa214507-0c6d-4a08-8ce4-679b2b200b79.png)
 
 The `forward` method returns losses or predictions of training, validation, testing, and a simple inference process.
 
@@ -114,10 +107,7 @@ Returns:
 
 - Dict\[str, `torch.Tensor`\]: A `dict` of tensor for logging.
 
-<center>
-  <img src='../../../resources/train_step.png' />
-  <center>train_step dataflow</center>
-</center>
+![train_step dataflow](https://user-images.githubusercontent.com/15952744/228828089-a9ae1225-958d-4cf7-99af-9af8576f7ef7.png)
 
 ### val_step
 
@@ -131,10 +121,7 @@ Returns:
 
 - `list` - The predictions of given data.
 
-<center>
-  <img src='../../../resources/test_step.png' />
-  <center>test_step/val_step dataflow</center>
-</center>
+![test_step/val_step dataflow](https://user-images.githubusercontent.com/15952744/228828179-3269baa3-bebd-4c9a-9787-59e7d785fbcf.png)
 
 ### test_step
 
diff --git a/docs/en/get_started.md b/docs/en/get_started.md
index b082508693..3cda319065 100644
--- a/docs/en/get_started.md
+++ b/docs/en/get_started.md
@@ -51,7 +51,7 @@ mim install "mmcv>=2.0.0rc1"
 Case a: If you develop and run mmseg directly, install it from source:
 
 ```shell
-git clone -b dev-1.x https://github.com/open-mmlab/mmsegmentation.git
+git clone -b main https://github.com/open-mmlab/mmsegmentation.git
 cd mmsegmentation
 pip install -v -e .
 # '-v' means verbose, or more output
@@ -164,7 +164,7 @@ thus we only need to install MMCV and MMSegmentation with the following commands
 ```shell
 !git clone https://github.com/open-mmlab/mmsegmentation.git
 %cd mmsegmentation
-!git checkout dev-1.x
+!git checkout main
 !pip install -e .
 ```
 
@@ -181,7 +181,7 @@ Within Jupyter, the exclamation mark `!` is used to call external executables an
 
 ### Using MMSegmentation with Docker
 
-We provide a [Dockerfile](https://github.com/open-mmlab/mmsegmentation/blob/master/docker/Dockerfile) to build an image. Ensure that your [docker version](https://docs.docker.com/engine/install/) >=19.03.
+We provide a [Dockerfile](https://github.com/open-mmlab/mmsegmentation/blob/main/docker/Dockerfile) to build an image. Ensure that your [docker version](https://docs.docker.com/engine/install/) >=19.03.
 
 ```shell
 # build an image with PyTorch 1.11, CUDA 11.3
diff --git a/docs/en/model_zoo.md b/docs/en/model_zoo.md
index 782a47002f..6717df6cc7 100644
--- a/docs/en/model_zoo.md
+++ b/docs/en/model_zoo.md
@@ -34,123 +34,123 @@
 
 ### FCN
 
-Please refer to [FCN](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn) for details.
+Please refer to [FCN](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn) for details.
 
 ### PSPNet
 
-Please refer to [PSPNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/pspnet) for details.
+Please refer to [PSPNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet) for details.
 
 ### DeepLabV3
 
-Please refer to [DeepLabV3](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3) for details.
+Please refer to [DeepLabV3](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3) for details.
 
 ### PSANet
 
-Please refer to [PSANet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/psanet) for details.
+Please refer to [PSANet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/psanet) for details.
 
 ### DeepLabV3+
 
-Please refer to [DeepLabV3+](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus) for details.
+Please refer to [DeepLabV3+](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus) for details.
 
 ### UPerNet
 
-Please refer to [UPerNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet) for details.
+Please refer to [UPerNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/upernet) for details.
 
 ### NonLocal Net
 
-Please refer to [NonLocal Net](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/nonlocal_net) for details.
+Please refer to [NonLocal Net](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/nonlocal_net) for details.
 
 ### EncNet
 
-Please refer to [EncNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/encnet) for details.
+Please refer to [EncNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/encnet) for details.
 
 ### CCNet
 
-Please refer to [CCNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ccnet) for details.
+Please refer to [CCNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ccnet) for details.
 
 ### DANet
 
-Please refer to [DANet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/danet) for details.
+Please refer to [DANet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet) for details.
 
 ### APCNet
 
-Please refer to [APCNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/apcnet) for details.
+Please refer to [APCNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/apcnet) for details.
 
 ### HRNet
 
-Please refer to [HRNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet) for details.
+Please refer to [HRNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet) for details.
 
 ### GCNet
 
-Please refer to [GCNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/gcnet) for details.
+Please refer to [GCNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet) for details.
 
 ### DMNet
 
-Please refer to [DMNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/dmnet) for details.
+Please refer to [DMNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dmnet) for details.
 
 ### ANN
 
-Please refer to [ANN](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ann) for details.
+Please refer to [ANN](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ann) for details.
 
 ### OCRNet
 
-Please refer to [OCRNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ocrnet) for details.
+Please refer to [OCRNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet) for details.
 
 ### Fast-SCNN
 
-Please refer to [Fast-SCNN](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fastscnn) for details.
+Please refer to [Fast-SCNN](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastscnn) for details.
 
 ### ResNeSt
 
-Please refer to [ResNeSt](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/resnest) for details.
+Please refer to [ResNeSt](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/resnest) for details.
 
 ### Semantic FPN
 
-Please refer to [Semantic FPN](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/sem_fpn) for details.
+Please refer to [Semantic FPN](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/sem_fpn) for details.
 
 ### PointRend
 
-Please refer to [PointRend](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/point_rend) for details.
+Please refer to [PointRend](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/point_rend) for details.
 
 ### MobileNetV2
 
-Please refer to [MobileNetV2](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/mobilenet_v2) for details.
+Please refer to [MobileNetV2](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mobilenet_v2) for details.
 
 ### MobileNetV3
 
-Please refer to [MobileNetV3](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/mobilenet_v3) for details.
+Please refer to [MobileNetV3](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mobilenet_v3) for details.
 
 ### EMANet
 
-Please refer to [EMANet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/emanet) for details.
+Please refer to [EMANet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/emanet) for details.
 
 ### DNLNet
 
-Please refer to [DNLNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/dnlnet) for details.
+Please refer to [DNLNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dnlnet) for details.
 
 ### CGNet
 
-Please refer to [CGNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/cgnet) for details.
+Please refer to [CGNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/cgnet) for details.
 
 ### Mixed Precision (FP16) Training
 
-Please refer [Mixed Precision (FP16) Training on BiSeNetV2](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv2/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes.py) for details.
+Please refer [Mixed Precision (FP16) Training on BiSeNetV2](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/bisenetv2/bisenetv2_fcn_4xb4-160k_cityscapes-1024x1024.py) for details.
 
 ### U-Net
 
-Please refer to [U-Net](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/unet/README.md) for details.
+Please refer to [U-Net](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/README.md) for details.
 
 ### ViT
 
-Please refer to [ViT](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/README.md) for details.
+Please refer to [ViT](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/vit/README.md) for details.
 
 ### Swin
 
-Please refer to [Swin](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/README.md) for details.
+Please refer to [Swin](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/swin/README.md) for details.
 
 ### SETR
 
-Please refer to [SETR](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/setr/README.md) for details.
+Please refer to [SETR](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/setr/README.md) for details.
 
 ## Speed benchmark
 
diff --git a/docs/en/modelzoo_statistics.md b/docs/en/modelzoo_statistics.md
index c8fa46d013..e5e21a1474 100644
--- a/docs/en/modelzoo_statistics.md
+++ b/docs/en/modelzoo_statistics.md
@@ -7,96 +7,96 @@
 
 - Number of checkpoints: 612
 
-  - \[ALGORITHM\] [ANN](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ann) (16 ckpts)
+  - \[ALGORITHM\] [ANN](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ann) (16 ckpts)
 
-  - \[ALGORITHM\] [APCNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/apcnet) (12 ckpts)
+  - \[ALGORITHM\] [APCNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/apcnet) (12 ckpts)
 
-  - \[BACKBONE\] [BEiT](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/beit) (2 ckpts)
+  - \[BACKBONE\] [BEiT](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/beit) (2 ckpts)
 
-  - \[ALGORITHM\] [BiSeNetV1](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1) (11 ckpts)
+  - \[ALGORITHM\] [BiSeNetV1](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/bisenetv1) (11 ckpts)
 
-  - \[ALGORITHM\] [BiSeNetV2](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv2) (4 ckpts)
+  - \[ALGORITHM\] [BiSeNetV2](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/bisenetv2) (4 ckpts)
 
-  - \[ALGORITHM\] [CCNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ccnet) (16 ckpts)
+  - \[ALGORITHM\] [CCNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ccnet) (16 ckpts)
 
-  - \[ALGORITHM\] [CGNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/cgnet) (2 ckpts)
+  - \[ALGORITHM\] [CGNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/cgnet) (2 ckpts)
 
-  - \[BACKBONE\] [ConvNeXt](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/convnext) (6 ckpts)
+  - \[BACKBONE\] [ConvNeXt](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/convnext) (6 ckpts)
 
-  - \[ALGORITHM\] [DANet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/danet) (16 ckpts)
+  - \[ALGORITHM\] [DANet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet) (16 ckpts)
 
-  - \[ALGORITHM\] [DeepLabV3](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3) (41 ckpts)
+  - \[ALGORITHM\] [DeepLabV3](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3) (41 ckpts)
 
-  - \[ALGORITHM\] [DeepLabV3+](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus) (42 ckpts)
+  - \[ALGORITHM\] [DeepLabV3+](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3plus) (42 ckpts)
 
-  - \[ALGORITHM\] [DMNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/dmnet) (12 ckpts)
+  - \[ALGORITHM\] [DMNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dmnet) (12 ckpts)
 
-  - \[ALGORITHM\] [DNLNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/dnlnet) (12 ckpts)
+  - \[ALGORITHM\] [DNLNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dnlnet) (12 ckpts)
 
-  - \[ALGORITHM\] [DPT](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/dpt) (1 ckpts)
+  - \[ALGORITHM\] [DPT](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/dpt) (1 ckpts)
 
-  - \[ALGORITHM\] [EMANet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/emanet) (4 ckpts)
+  - \[ALGORITHM\] [EMANet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/emanet) (4 ckpts)
 
-  - \[ALGORITHM\] [EncNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/encnet) (12 ckpts)
+  - \[ALGORITHM\] [EncNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/encnet) (12 ckpts)
 
-  - \[ALGORITHM\] [ERFNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/erfnet) (1 ckpts)
+  - \[ALGORITHM\] [ERFNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/erfnet) (1 ckpts)
 
-  - \[ALGORITHM\] [FastFCN](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fastfcn) (12 ckpts)
+  - \[ALGORITHM\] [FastFCN](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn) (12 ckpts)
 
-  - \[ALGORITHM\] [Fast-SCNN](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fastscnn) (1 ckpts)
+  - \[ALGORITHM\] [Fast-SCNN](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastscnn) (1 ckpts)
 
-  - \[ALGORITHM\] [FCN](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn) (41 ckpts)
+  - \[ALGORITHM\] [FCN](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn) (41 ckpts)
 
-  - \[ALGORITHM\] [GCNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/gcnet) (16 ckpts)
+  - \[ALGORITHM\] [GCNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet) (16 ckpts)
 
-  - \[BACKBONE\] [HRNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet) (37 ckpts)
+  - \[BACKBONE\] [HRNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/hrnet) (37 ckpts)
 
-  - \[ALGORITHM\] [ICNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/icnet) (12 ckpts)
+  - \[ALGORITHM\] [ICNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/icnet) (12 ckpts)
 
-  - \[ALGORITHM\] [ISANet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/isanet) (16 ckpts)
+  - \[ALGORITHM\] [ISANet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/isanet) (16 ckpts)
 
-  - \[ALGORITHM\] [K-Net](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/knet) (7 ckpts)
+  - \[ALGORITHM\] [K-Net](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/knet) (7 ckpts)
 
-  - \[BACKBONE\] [MAE](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/mae) (1 ckpts)
+  - \[BACKBONE\] [MAE](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mae) (1 ckpts)
 
-  - \[ALGORITHM\] [Mask2Former](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/mask2former) (13 ckpts)
+  - \[ALGORITHM\] [Mask2Former](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mask2former) (13 ckpts)
 
-  - \[ALGORITHM\] [MaskFormer](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/maskformer) (4 ckpts)
+  - \[ALGORITHM\] [MaskFormer](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/maskformer) (4 ckpts)
 
-  - \[BACKBONE\] [MobileNetV2](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/mobilenet_v2) (8 ckpts)
+  - \[BACKBONE\] [MobileNetV2](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mobilenet_v2) (8 ckpts)
 
-  - \[BACKBONE\] [MobileNetV3](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/mobilenet_v3) (4 ckpts)
+  - \[BACKBONE\] [MobileNetV3](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mobilenet_v3) (4 ckpts)
 
-  - \[ALGORITHM\] [NonLocal Net](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/nonlocal_net) (16 ckpts)
+  - \[ALGORITHM\] [NonLocal Net](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/nonlocal_net) (16 ckpts)
 
-  - \[ALGORITHM\] [OCRNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ocrnet) (24 ckpts)
+  - \[ALGORITHM\] [OCRNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/ocrnet) (24 ckpts)
 
-  - \[ALGORITHM\] [PointRend](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/point_rend) (4 ckpts)
+  - \[ALGORITHM\] [PointRend](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/point_rend) (4 ckpts)
 
-  - \[BACKBONE\] [PoolFormer](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/poolformer) (5 ckpts)
+  - \[BACKBONE\] [PoolFormer](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/poolformer) (5 ckpts)
 
-  - \[ALGORITHM\] [PSANet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/psanet) (16 ckpts)
+  - \[ALGORITHM\] [PSANet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/psanet) (16 ckpts)
 
-  - \[ALGORITHM\] [PSPNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/pspnet) (54 ckpts)
+  - \[ALGORITHM\] [PSPNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet) (54 ckpts)
 
-  - \[BACKBONE\] [ResNeSt](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/resnest) (8 ckpts)
+  - \[BACKBONE\] [ResNeSt](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/resnest) (8 ckpts)
 
-  - \[ALGORITHM\] [SegFormer](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/segformer) (13 ckpts)
+  - \[ALGORITHM\] [SegFormer](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segformer) (13 ckpts)
 
-  - \[ALGORITHM\] [Segmenter](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/segmenter) (5 ckpts)
+  - \[ALGORITHM\] [Segmenter](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segmenter) (5 ckpts)
 
-  - \[ALGORITHM\] [Semantic FPN](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/sem_fpn) (4 ckpts)
+  - \[ALGORITHM\] [Semantic FPN](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/sem_fpn) (4 ckpts)
 
-  - \[ALGORITHM\] [SETR](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/setr) (7 ckpts)
+  - \[ALGORITHM\] [SETR](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/setr) (7 ckpts)
 
-  - \[ALGORITHM\] [STDC](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/stdc) (4 ckpts)
+  - \[ALGORITHM\] [STDC](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/stdc) (4 ckpts)
 
-  - \[BACKBONE\] [Swin Transformer](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin) (6 ckpts)
+  - \[BACKBONE\] [Swin Transformer](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/swin) (6 ckpts)
 
-  - \[BACKBONE\] [Twins](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/twins) (12 ckpts)
+  - \[BACKBONE\] [Twins](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/twins) (12 ckpts)
 
-  - \[ALGORITHM\] [UNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/unet) (25 ckpts)
+  - \[ALGORITHM\] [UNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet) (25 ckpts)
 
-  - \[ALGORITHM\] [UPerNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet) (16 ckpts)
+  - \[ALGORITHM\] [UPerNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/upernet) (16 ckpts)
 
-  - \[BACKBONE\] [Vision Transformer](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit) (11 ckpts)
+  - \[BACKBONE\] [Vision Transformer](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/vit) (11 ckpts)
diff --git a/docs/en/notes/faq.md b/docs/en/notes/faq.md
index fe5cac3834..5b9c35339b 100644
--- a/docs/en/notes/faq.md
+++ b/docs/en/notes/faq.md
@@ -26,5 +26,5 @@ Notes:
 
 ## How to know the number of GPUs needed to train the model
 
-- Infer from the name of the config file of the model. You can refer to the `Config Name Style` part of [Learn about Configs](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/en/tutorials/config.md). For example, for config file with name `segformer_mit-b0_8xb1-160k_cityscapes-1024x1024.py`, `8xb1` means training the model corresponding to it needs 8 GPUs, and the batch size of each GPU is 1.
+- Infer from the name of the config file of the model. You can refer to the `Config Name Style` part of [Learn about Configs](../user_guides/1_config.md). For example, for config file with name `segformer_mit-b0_8xb1-160k_cityscapes-1024x1024.py`, `8xb1` means training the model corresponding to it needs 8 GPUs, and the batch size of each GPU is 1.
 - Infer from the log file. Open the log file of the model and search `nGPU` in the file. The number of figures following `nGPU` is the number of GPUs needed to train the model. For instance, searching for `nGPU` in the log file yields the record `nGPU 0,1,2,3,4,5,6,7`, which indicates that eight GPUs are needed to train the model.
diff --git a/docs/en/overview.md b/docs/en/overview.md
index 399f343fd4..bbc0b8e32c 100644
--- a/docs/en/overview.md
+++ b/docs/en/overview.md
@@ -72,8 +72,8 @@ Here is a detailed step-by-step guide to learn more about MMSegmentation:
    please refer to the below guides to build your own segmentation project:
 
    - [Add new models](advanced_guides/add_models.md)
-   - [Add new datasets](advanced_guides/add_dataset.md)
-   - [Add new transforms](advanced_guides/add_transform.md)
+   - [Add new datasets](advanced_guides/add_datasets.md)
+   - [Add new transforms](advanced_guides/add_transforms.md)
    - [Customize runtime](advanced_guides/customize_runtime.md)
 
 5. If you are more familiar with MMSegmentation v0.x, there is documentation about migration from MMSegmentation v0.x to v1.x
@@ -82,4 +82,4 @@ Here is a detailed step-by-step guide to learn more about MMSegmentation:
 
 ## References
 
-- https://paperswithcode.com/task/semantic-segmentation/codeless#task-home
+- [Paper with code](https://paperswithcode.com/task/semantic-segmentation/codeless#task-home)
diff --git a/docs/en/switch_language.md b/docs/en/switch_language.md
index 80e30dc3ae..d6973b6c05 100644
--- a/docs/en/switch_language.md
+++ b/docs/en/switch_language.md
@@ -1,3 +1,3 @@
-## <a href='https://mmsegmentation.readthedocs.io/en/dev-1.x/'>English</a>
+## <a href='https://mmsegmentation.readthedocs.io/en/main/'>English</a>
 
-## <a href='https://mmsegmentation.readthedocs.io/zh_CN/dev-1.x/'>简体中文</a>
+## <a href='https://mmsegmentation.readthedocs.io/zh_CN/main/'>简体中文</a>
diff --git a/docs/en/user_guides/2_dataset_prepare.md b/docs/en/user_guides/2_dataset_prepare.md
index 63a1a8bb4a..d4fbfbf5d0 100644
--- a/docs/en/user_guides/2_dataset_prepare.md
+++ b/docs/en/user_guides/2_dataset_prepare.md
@@ -619,4 +619,4 @@ It includes 400 images for training, 400 images for validation and 400 images fo
   ```
 
 - You could set Datasets version with `MapillaryDataset_v1` and `MapillaryDataset_v2` in your configs.
-  View the Mapillary Vistas Datasets config file here [V1.2](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/datasets/mapillary_v1.py) and [V2.0](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/datasets/mapillary_v2.py)
+  View the Mapillary Vistas Datasets config file here [V1.2](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/_base_/datasets/mapillary_v1.py) and [V2.0](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/_base_/datasets/mapillary_v2.py)
diff --git a/docs/en/user_guides/3_inference.md b/docs/en/user_guides/3_inference.md
index 6650b2ed39..cacebd2f60 100644
--- a/docs/en/user_guides/3_inference.md
+++ b/docs/en/user_guides/3_inference.md
@@ -96,7 +96,7 @@ The model names can be found in models' metafile (configs/xxx/metafile.yaml), li
 - weights (str, optional) -  Path to the checkpoint. If it is not specified and model is a model name of metafile, the weights will be loaded from metafile. Defaults to None.
 - classes (list, optional) - Input classes for result rendering, as the prediction of segmentation model is a segment map with label indices, `classes` is a list which includes items responding to the label indices. If classes is not defined, visualizer will take `cityscapes` classes by default. Defaults to None.
 - palette (list, optional) - Input palette for result rendering, which is a list of colors responding to the classes. If the palette is not defined, the visualizer will take the palette of `cityscapes` by default. Defaults to None.
-- dataset_name (str, optional) - [Dataset name or alias](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/utils/class_names.py#L302-L317), visualizer will use the meta information of the dataset i.e. classes and palette, but the `classes` and `palette` have higher priority. Defaults to None.
+- dataset_name (str, optional) - [Dataset name or alias](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/utils/class_names.py#L302-L317), visualizer will use the meta information of the dataset i.e. classes and palette, but the `classes` and `palette` have higher priority. Defaults to None.
 - device (str, optional) - Device to run inference. If None, the available device will be automatically used. Defaults to None.
 - scope (str, optional) - The scope of the model. Defaults to 'mmseg'.
 
diff --git a/docs/zh_cn/advanced_guides/add_models.md b/docs/zh_cn/advanced_guides/add_models.md
index 2f0a5af0d1..e05c07c8ba 100644
--- a/docs/zh_cn/advanced_guides/add_models.md
+++ b/docs/zh_cn/advanced_guides/add_models.md
@@ -166,7 +166,7 @@ loss_decode=dict(type='MyLoss', loss_weight=1.0))
 
 ### 添加新的数据预处理器（data preprocessor）
 
-在 MMSegmentation 1.x 版本中，我们使用 [SegDataPreProcessor](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/data_preprocessor.py#L13) 将数据复制到目标设备，并将数据预处理为默认的模型输入格式。这里我们将展示如何开发一个新的数据预处理器。
+在 MMSegmentation 1.x 版本中，我们使用 [SegDataPreProcessor](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/data_preprocessor.py#L13) 将数据复制到目标设备，并将数据预处理为默认的模型输入格式。这里我们将展示如何开发一个新的数据预处理器。
 
 1. 创建一个新文件 `mmseg/models/my_datapreprocessor.py`。
 
diff --git a/docs/zh_cn/advanced_guides/data_flow.md b/docs/zh_cn/advanced_guides/data_flow.md
index 0716d36d1b..20dbe07e75 100644
--- a/docs/zh_cn/advanced_guides/data_flow.md
+++ b/docs/zh_cn/advanced_guides/data_flow.md
@@ -16,7 +16,7 @@ val_cfg = dict(type='ValLoop')
 test_cfg = dict(type='TestLoop')
 ```
 
-在上图中，红色线表示 [train_step](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/advanced_guides/models.md#train_step) ***（[中文链接待更新](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/advanced_guides/models.md#train_step)）*** ，在每次训练迭代中，数据加载器（dataloader）从存储中加载图像并传输到数据预处理器（data preprocessor），数据预处理器会将图像放到特定的设备上，并将数据堆叠到批处理中，之后模型接受批处理数据作为输入，最后将模型的输出发送给优化器（optimizer）。蓝色线表示 [val_step](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/advanced_guides/models.md#val_step) 和 [test_step](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/advanced_guides/models.md#test_step) ***（[中文链接待更新](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/advanced_guides/models.md#test_step)）*** 。这两个过程的数据流除了模型输出与 `train_step` 不同外，其余均和 `train_step` 类似。由于在评估时模型参数会被冻结，因此模型的输出将被传递给 [Evaluator](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/advanced_guides/evaluation.md#ioumetric) ***（[中文链接待更新](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/advanced_guides/evaluation.md#ioumetric)）***
+在上图中，红色线表示 [train_step](./models.md#train_step)，在每次训练迭代中，数据加载器（dataloader）从存储中加载图像并传输到数据预处理器（data preprocessor），数据预处理器会将图像放到特定的设备上，并将数据堆叠到批处理中，之后模型接受批处理数据作为输入，最后将模型的输出发送给优化器（optimizer）。蓝色线表示 [val_step](./models.md#val_step) 和 [test_step](./models.md#test_step)。这两个过程的数据流除了模型输出与 `train_step` 不同外，其余均和 `train_step` 类似。由于在评估时模型参数会被冻结，因此模型的输出将被传递给 [Evaluator](./evaluation.md#ioumetric)。
 来计算指标。
 
 ## MMSegmentation 中的数据流约定
@@ -28,7 +28,7 @@ test_cfg = dict(type='TestLoop')
 数据加载器（DataLoader）是 MMEngine 的训练和测试流程中的一个重要组件。
 从概念上讲，它源于 [PyTorch](https://pytorch.org/) 并保持一致。DataLoader 从文件系统加载数据，原始数据通过数据准备流程后被发送给数据预处理器。
 
-MMSegmentation 在 [PackSegInputs](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/datasets/transforms/formatting.py#L12) 中定义了默认数据格式， 它是 `train_pipeline` 和 `test_pipeline` 的最后一个组件。有关数据转换 `pipeline` 的更多信息，请参阅[数据转换文档](https://mmsegmentation.readthedocs.io/en/dev-1.x/advanced_guides/transforms.html)。 ***（[中文链接待更新](https://mmsegmentation.readthedocs.io/zh_CN/dev-1.x/advanced_guides/transforms.html)）***
+MMSegmentation 在 [PackSegInputs](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/datasets/transforms/formatting.py#L12) 中定义了默认数据格式， 它是 `train_pipeline` 和 `test_pipeline` 的最后一个组件。有关数据转换 `pipeline` 的更多信息，请参阅[数据转换文档](./transforms.md)。
 
 在没有任何修改的情况下，PackSegInputs 的返回值通常是一个包含 `inputs` 和 `data_samples` 的 `dict`。以下伪代码展示了 mmseg 中数据加载器输出的数据类型，它是从数据集中获取的一批数据样本，数据加载器将它们打包成一个字典列表。`inputs` 是输入进模型的张量列表，`data_samples` 包含了输入图像的 meta information 和相应的 ground truth。
 
@@ -39,11 +39,11 @@ dict(
 )
 ```
 
-**注意：** [SegDataSample](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/structures/seg_data_sample.py) 是 MMSegmentation 的数据结构接口，用于连接不同组件。`SegDataSample` 实现了抽象数据元素 `mmengine.structures.BaseDataElement`，更多信息请在  [MMEngine](https://github.com/open-mmlab/mmengine) 中参阅 [SegDataSample 文档](https://mmsegmentation.readthedocs.io/zh_CN/1.x/advanced_guides/structures.html)和[数据元素文档](https://mmengine.readthedocs.io/zh_CN/latest/advanced_tutorials/data_element.html)。
+**注意：** [SegDataSample](https://github.com/open-mmlab/mmsegmentation/blob/1.x/mmseg/structures/seg_data_sample.py) 是 MMSegmentation 的数据结构接口，用于连接不同组件。`SegDataSample` 实现了抽象数据元素 `mmengine.structures.BaseDataElement`，更多信息请在  [MMEngine](https://github.com/open-mmlab/mmengine) 中参阅 [SegDataSample 文档](./structures.md)和[数据元素文档](https://mmengine.readthedocs.io/zh_CN/latest/advanced_tutorials/data_element.html)。
 
 ### 数据预处理器到模型
 
-虽然在[上面的图](##数据流概述)中分开绘制了数据预处理器和模型，但数据预处理器是模型的一部分，因此可以在[模型教程](https://mmsegmentation.readthedocs.io/en/dev-1.x/advanced_guides/models.html)中找到数据预处理器章节。 ***（[中文链接待更新](https://mmsegmentation.readthedocs.io/zh_CN/dev-1.x/advanced_guides/models.html)）***
+虽然在[上面的图](##数据流概述)中分开绘制了数据预处理器和模型，但数据预处理器是模型的一部分，因此可以在[模型教程](./models.md)中找到数据预处理器章节。
 
 数据预处理器的返回值是一个包含 `inputs` 和 `data_samples` 的字典，其中 `inputs` 是批处理图像的 4D 张量，`data_samples` 中添加了一些用于数据预处理的额外元信息。当传递给网络时，字典将被解包为两个值。 以下伪代码展示了数据预处理器的返回值和模型的输入值。
 
@@ -61,22 +61,22 @@ class Network(BaseSegmentor):
         pass
 ```
 
-**注意：** 模型的前向传播有 3 种模式，由输入参数 mode 控制，更多信息请参阅[模型教程](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/advanced_guides/models.md)。 ***（[中文链接待更新](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/advanced_guides/models.md)）***
+**注意：** 模型的前向传播有 3 种模式，由输入参数 mode 控制，更多信息请参阅[模型教程](./models.md)。
 
 ### 模型输出
 
-如[模型教程](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/advanced_guides/models.md#forward) ***（[中文链接待更新](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/advanced_guides/models.md#forward)）*** 所提到的 3 种前向传播具有 3 种输出。
+如[模型教程](./models.md#forward) ***（[中文链接待更新](./models.md#forward)）*** 所提到的 3 种前向传播具有 3 种输出。
 `train_step` 和 `test_step`（或 `val_step`）分别对应于 `'loss'` 和 `'predict'`。
 
-在 `test_step` 或 `val_step` 中，推理结果会被传递给 `Evaluator` 。您可以参阅[评估文档](https://mmsegmentation.readthedocs.io/en/dev-1.x/advanced_guides/evaluation.html)  ***（[中文链接待更新](https://mmsegmentation.readthedocs.io/zh_CN/dev-1.x/advanced_guides/evaluation.html)）*** 来获取更多关于 `Evaluator` 的信息。
+在 `test_step` 或 `val_step` 中，推理结果会被传递给 `Evaluator` 。您可以参阅[评估文档](./evaluation.md)来获取更多关于 `Evaluator` 的信息。
 
-在推理后，MMSegmentation 中的 [BaseSegmentor](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/segmentors/base.py#L15) 会对推理结果进行简单的后处理以打包推理结果。神经网络生成的分割 logits，经过 `argmax` 操作后的分割 mask 和 ground truth（如果存在）将被打包到类似 `SegDataSample` 的实例。 [postprocess_result](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/segmentors/base.py#L132) 的返回值是一个 **`SegDataSample`的`List`**。下图显示了这些 `SegDataSample` 实例的关键属性。
+在推理后，MMSegmentation 中的 [BaseSegmentor](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/segmentors/base.py#L15) 会对推理结果进行简单的后处理以打包推理结果。神经网络生成的分割 logits，经过 `argmax` 操作后的分割 mask 和 ground truth（如果存在）将被打包到类似 `SegDataSample` 的实例。 [postprocess_result](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/segmentors/base.py#L132) 的返回值是一个 **`SegDataSample`的`List`**。下图显示了这些 `SegDataSample` 实例的关键属性。
 
 ![SegDataSample](https://user-images.githubusercontent.com/15952744/209912225-ab46a8d9-904a-43cb-8bf1-8bec4938ed29.png)
 
-与数据预处理器一致，损失函数也是模型的一部分，它是[解码头](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/decode_heads/decode_head.py#L142)的属性之一。
+与数据预处理器一致，损失函数也是模型的一部分，它是[解码头](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/decode_heads/decode_head.py#L142)的属性之一。
 
-在 MMSegmentation 中，`decode_head` 的 [loss_by_feat](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/models/decode_heads/decode_head.py#L291) 方法是用于计算损失的统一接口。
+在 MMSegmentation 中，`decode_head` 的 [loss_by_feat](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/decode_heads/decode_head.py#L291) 方法是用于计算损失的统一接口。
 
 参数：
 
@@ -87,4 +87,4 @@ class Network(BaseSegmentor):
 
 - dict\[str, Tensor\]：一个损失组件的字典
 
-**注意：**  `train_step` 将损失传递进 OptimWrapper 以更新模型中的权重，更多信息请参阅 [train_step](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/advanced_guides/models.md#train_step)。 ***（[中文链接待更新](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/advanced_guides/models.md#train_step)）***
+**注意：**  `train_step` 将损失传递进 OptimWrapper 以更新模型中的权重，更多信息请参阅 [train_step](./models.md#train_step)。
diff --git a/docs/zh_cn/advanced_guides/datasets.md b/docs/zh_cn/advanced_guides/datasets.md
index 546e97f70d..80852a04e5 100644
--- a/docs/zh_cn/advanced_guides/datasets.md
+++ b/docs/zh_cn/advanced_guides/datasets.md
@@ -1,10 +1,10 @@
 # 数据集
 
-在 MMSegmentation 算法库中, 所有 Dataset 类的功能有两个: 加载[预处理](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/user_guides/2_dataset_prepare.md) 之后的数据集的信息, 和将数据送入[数据集变换流水线](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/datasets/basesegdataset.py#L141) 中, 进行[数据变换操作](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/advanced_guides/transforms.md). 加载的数据集信息包括两类: 元信息 (meta information), 数据集本身的信息, 例如数据集总共的类别, 和它们对应调色盘信息: 数据信息 (data information) 是指每组数据中图片和对应标签的路径. 下文中介绍了 MMSegmentation 1.x 中数据集的常用接口, 和 mmseg 数据集基类中数据信息加载与修改数据集类别的逻辑, 以及数据集与数据变换流水线 (pipeline) 的关系.
+在 MMSegmentation 算法库中, 所有 Dataset 类的功能有两个: 加载[预处理](../user_guides/2_dataset_prepare.md) 之后的数据集的信息, 和将数据送入[数据集变换流水线](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/datasets/basesegdataset.py#L141) 中, 进行[数据变换操作](./transforms.md). 加载的数据集信息包括两类: 元信息 (meta information), 数据集本身的信息, 例如数据集总共的类别, 和它们对应调色盘信息: 数据信息 (data information) 是指每组数据中图片和对应标签的路径. 下文中介绍了 MMSegmentation 1.x 中数据集的常用接口, 和 mmseg 数据集基类中数据信息加载与修改数据集类别的逻辑, 以及数据集与数据变换流水线 (pipeline) 的关系.
 
 ## 常用接口
 
-以 Cityscapes 为例, 介绍数据集常用接口. 如需运行以下示例, 请在当前工作目录下的 `data` 目录下载并[预处理](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/user_guides/2_dataset_prepare.md#cityscapes) Cityscapes 数据集.
+以 Cityscapes 为例, 介绍数据集常用接口. 如需运行以下示例, 请在当前工作目录下的 `data` 目录下载并[预处理](../user_guides/2_dataset_prepare.md#cityscapes) Cityscapes 数据集.
 
 实例化 Cityscapes 训练数据集:
 
@@ -96,7 +96,7 @@ print(dataset.metainfo)
  'reduce_zero_label': False}
 ```
 
-数据集 `__getitem__` 方法的返回值, 是经过数据增强的样本数据的输出, 同样也是一个字典, 包括两个字段, `'inputs'` 字段是当前样本经过数据增强操作的图像, 类型为 torch.Tensor, `'data_samples'` 字段存放的数据类型是 MMSegmentation 1.x 新添加的数据结构 [`Segdatasample`](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/advanced_guides/structures.md), 其中`gt_sem_seg` 字段是经过数据增强的标签数据.
+数据集 `__getitem__` 方法的返回值, 是经过数据增强的样本数据的输出, 同样也是一个字典, 包括两个字段, `'inputs'` 字段是当前样本经过数据增强操作的图像, 类型为 torch.Tensor, `'data_samples'` 字段存放的数据类型是 MMSegmentation 1.x 新添加的数据结构 [`Segdatasample`](./structures.md), 其中`gt_sem_seg` 字段是经过数据增强的标签数据.
 
 ```python
 print(dataset[0])
@@ -166,13 +166,13 @@ print(dataset[0])
 
 ## BaseSegDataset
 
-由于 MMSegmentation 中的所有数据集的基本功能均包括(1) 加载[数据集预处理](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/user_guides/2_dataset_prepare.md) 之后的数据信息和 (2) 将数据送入数据变换流水线中进行数据变换, 因此在 MMSegmentation 中将其中的共同接口抽象成 [`BaseSegDataset`](https://mmsegmentation.readthedocs.io/en/dev-1.x/api.html?highlight=BaseSegDataset#mmseg.datasets.BaseSegDataset)，它继承自 [MMEngine 的 `BaseDataset`](https://github.com/open-mmlab/mmengine/blob/main/docs/en/advanced_tutorials/basedataset.md), 遵循 OpenMMLab 数据集初始化统一流程, 支持高效的内部数据存储格式, 支持数据集拼接、数据集重复采样等功能.
+由于 MMSegmentation 中的所有数据集的基本功能均包括(1) 加载[数据集预处理](../user_guides/2_dataset_prepare.md) 之后的数据信息和 (2) 将数据送入数据变换流水线中进行数据变换, 因此在 MMSegmentation 中将其中的共同接口抽象成 [`BaseSegDataset`](https://mmsegmentation.readthedocs.io/en/main/api.html?highlight=BaseSegDataset#mmseg.datasets.BaseSegDataset)，它继承自 [MMEngine 的 `BaseDataset`](https://github.com/open-mmlab/mmengine/blob/main/docs/en/advanced_tutorials/basedataset.md), 遵循 OpenMMLab 数据集初始化统一流程, 支持高效的内部数据存储格式, 支持数据集拼接、数据集重复采样等功能.
 在 MMSegmentation BaseSegDataset 中重新定义了**数据信息加载方法**（`load_data_list`）和并新增了 `get_label_map` 方法用来**修改数据集的类别信息**.
 
 ### 数据信息加载
 
-数据信息加载的内容是样本数据的图片路径和标签路径, 具体实现在 MMSegmentation 的 BaseSegDataset 的 [`load_data_list`](https://github.com/open-mmlab/mmsegmentation/blob/163277bfe0fa8fefb63ee5137917fafada1b301c/mmseg/datasets/basesegdataset.py#L231) 中.
-主要有两种获取图片和标签的路径方法, 如果当数据集目录按以下目录结构组织, [`load_data_list`](https://github.com/open-mmlab/mmsegmentation/blob/163277bfe0fa8fefb63ee5137917fafada1b301c/mmseg/datasets/basesegdataset.py#L231)) 会根据数据路径和后缀来解析.
+数据信息加载的内容是样本数据的图片路径和标签路径, 具体实现在 MMSegmentation 的 BaseSegDataset 的 [`load_data_list`](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/datasets/basesegdataset.py#L231) 中.
+主要有两种获取图片和标签的路径方法, 如果当数据集目录按以下目录结构组织, [`load_data_list`](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/datasets/basesegdataset.py#L231)) 会根据数据路径和后缀来解析.
 
 ```
 ├── data
@@ -322,7 +322,7 @@ print(dataset.metainfo)
  'reduce_zero_label': False}
 ```
 
-可以看到, 数据集元信息的类别和默认 Cityscapes 不同. 并且, 定义了标签重映射的字段 `label_map` 用来修改每个分割掩膜上的像素的类别索引, 分割标签类别会根据 `label_map`, 将类别重映射, [具体实现](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/datasets/basesegdataset.py#L151):
+可以看到, 数据集元信息的类别和默认 Cityscapes 不同. 并且, 定义了标签重映射的字段 `label_map` 用来修改每个分割掩膜上的像素的类别索引, 分割标签类别会根据 `label_map`, 将类别重映射, [具体实现](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/datasets/basesegdataset.py#L151):
 
 ```python
 gt_semantic_seg_copy = gt_semantic_seg.copy()
diff --git a/docs/zh_cn/advanced_guides/engine.md b/docs/zh_cn/advanced_guides/engine.md
index 7920ecfd87..79b4c8d229 100644
--- a/docs/zh_cn/advanced_guides/engine.md
+++ b/docs/zh_cn/advanced_guides/engine.md
@@ -66,16 +66,16 @@ OpenMMLab 将模型训练和测试过程抽象为 `Runner`, 插入钩子可以
 不建议用户修改默认钩子的优先级, 可以参考 [mmengine hooks 文档](https://github.com/open-mmlab/mmengine/blob/main/docs/zh_cn/tutorials/hook.md) 了解钩子优先级的定义.
 下面是 MMSegmentation 中所用到的默认钩子：
 
-|                                                           钩子                                                            |                                              功能                                               |      优先级       |
-| :-----------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | :---------------: |
-|            [IterTimerHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/iter_timer_hook.py)            |                                   记录 iteration 花费的时间.                                    |    NORMAL (50)    |
-|               [LoggerHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/logger_hook.py)                | 从 `Runner` 里不同的组件中收集日志记录, 并将其输出到终端, JSON 文件, tensorboard, wandb 等下游. | BELOW_NORMAL (60) |
-|       [ParamSchedulerHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/param_scheduler_hook.py)       |                          更新优化器里面的一些超参数, 例如学习率的动量.                          |     LOW (70)      |
-|           [CheckpointHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/checkpoint_hook.py)            |                                  规律性地保存 checkpoint 文件.                                  |   VERY_LOW (90)   |
-|        [DistSamplerSeedHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/sampler_seed_hook.py)        |                               确保分布式采样器 shuffle 是打开的.                                |    NORMAL (50)    |
-| [SegVisualizationHook](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/visualization/local_visualizer.py) |                                可视化验证和测试过程里的预测结果.                                |    NORMAL (50)    |
+|                                                          钩子                                                          |                                              功能                                               |      优先级       |
+| :--------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | :---------------: |
+|          [IterTimerHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/iter_timer_hook.py)           |                                   记录 iteration 花费的时间.                                    |    NORMAL (50)    |
+|              [LoggerHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/logger_hook.py)              | 从 `Runner` 里不同的组件中收集日志记录, 并将其输出到终端, JSON 文件, tensorboard, wandb 等下游. | BELOW_NORMAL (60) |
+|     [ParamSchedulerHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/param_scheduler_hook.py)      |                          更新优化器里面的一些超参数, 例如学习率的动量.                          |     LOW (70)      |
+|          [CheckpointHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/checkpoint_hook.py)          |                                  规律性地保存 checkpoint 文件.                                  |   VERY_LOW (90)   |
+|      [DistSamplerSeedHook](https://github.com/open-mmlab/mmengine/blob/main/mmengine/hooks/sampler_seed_hook.py)       |                               确保分布式采样器 shuffle 是打开的.                                |    NORMAL (50)    |
+| [SegVisualizationHook](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/visualization/local_visualizer.py) |                                可视化验证和测试过程里的预测结果.                                |    NORMAL (50)    |
 
-MMSegmentation 会在 [`defualt_hooks`](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/schedules/schedule_160k.py#L19-L25) 里面注册一些训练所必需功能的钩子::
+MMSegmentation 会在 [`defualt_hooks`](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/_base_/schedules/schedule_160k.py#L19-L25) 里面注册一些训练所必需功能的钩子::
 
 ```python
 default_hooks = dict(
@@ -147,7 +147,7 @@ custom_hooks = [
 
 ### SegVisualizationHook
 
-MMSegmentation 实现了 [`SegVisualizationHook`](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/engine/hooks/visualization_hook.py#L17), 用来在验证和测试时可视化预测结果.
+MMSegmentation 实现了 [`SegVisualizationHook`](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/engine/hooks/visualization_hook.py#L17), 用来在验证和测试时可视化预测结果.
 `SegVisualizationHook` 重写了基类 `Hook` 中的 `_after_iter` 方法, 在验证或测试时, 根据指定的迭代次数间隔调用 `visualizer` 的 `add_datasample` 方法绘制语义分割结果, 具体实现如下:
 
 ```python
@@ -183,7 +183,7 @@ class SegVisualizationHook(Hook):
 
 ```
 
-关于可视化更多的细节可以查看[这里](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/user_guides/visualization.md).
+关于可视化更多的细节可以查看[这里](../user_guides/visualization.md).
 
 ## 优化器
 
@@ -236,7 +236,7 @@ optim_wrapper = dict(type='AmpOptimWrapper', optimizer=optimizer)
 
 在模型训练中, 如果想在优化器里为不同参数分别设置优化策略, 例如设置不同的学习率、权重衰减等超参数, 可以通过设置配置文件里 `optim_wrapper` 中的 `paramwise_cfg` 来实现.
 
-下面的配置文件以 [ViT `optim_wrapper`](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/vit/vit_vit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py#L15-L27) 为例介绍 `paramwise_cfg` 参数使用.
+下面的配置文件以 [ViT `optim_wrapper`](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/vit/vit_vit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py#L15-L27) 为例介绍 `paramwise_cfg` 参数使用.
 训练时将 `pos_embed`, `mask_token`, `norm` 模块的 weight decay 参数的系数设置成 0.
 即: 在训练时, 这些模块的 weight decay 将被变为 `weight_decay * decay_mult`=0.
 
@@ -261,7 +261,7 @@ optim_wrapper = dict(
 
 默认的优化器封装构造器 [`DefaultOptimWrapperConstructor`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/optim/optimizer/default_constructor.py#L19) 根据输入的 `optim_wrapper` 和 `optim_wrapper` 中定义的 `paramwise_cfg` 来构建训练中使用的优化器. 当 [`DefaultOptimWrapperConstructor`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/optim/optimizer/default_constructor.py#L19) 功能不能满足需求时, 可以自定义优化器封装构造器来实现超参数的配置.
 
-MMSegmentation 中的实现了 [`LearningRateDecayOptimizerConstructor`](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/engine/optimizers/layer_decay_optimizer_constructor.py#L104), 可以对以 ConvNeXt, BEiT 和 MAE 为骨干网络的模型训练时, 骨干网络的模型参数的学习率按照定义的衰减比例（`decay_rate`）逐层递减, 在配置文件中的配置如下:
+MMSegmentation 中的实现了 [`LearningRateDecayOptimizerConstructor`](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/engine/optimizers/layer_decay_optimizer_constructor.py#L104), 可以对以 ConvNeXt, BEiT 和 MAE 为骨干网络的模型训练时, 骨干网络的模型参数的学习率按照定义的衰减比例（`decay_rate`）逐层递减, 在配置文件中的配置如下:
 
 ```python
 optim_wrapper = dict(
diff --git a/docs/zh_cn/get_started.md b/docs/zh_cn/get_started.md
index 38e93e9cb4..55360aab8f 100644
--- a/docs/zh_cn/get_started.md
+++ b/docs/zh_cn/get_started.md
@@ -51,7 +51,7 @@ mim install "mmcv>=2.0.0rc1"
 情况 a: 如果您想立刻开发和运行 mmsegmentation，您可通过源码安装：
 
 ```shell
-git clone -b dev-1.x https://github.com/open-mmlab/mmsegmentation.git
+git clone -b main https://github.com/open-mmlab/mmsegmentation.git
 cd mmsegmentation
 pip install -v -e .
 # '-v' 表示详细模式，更多的输出
@@ -164,7 +164,7 @@ MMSegmentation 可以在仅有 CPU 的版本上运行。在 CPU 模式，您可
 ```shell
 !git clone https://github.com/open-mmlab/mmsegmentation.git
 %cd mmsegmentation
-!git checkout dev-1.x
+!git checkout main
 !pip install -e .
 ```
 
diff --git a/docs/zh_cn/user_guides/2_dataset_prepare.md b/docs/zh_cn/user_guides/2_dataset_prepare.md
index 6d8cb18681..e5e6c76c47 100644
--- a/docs/zh_cn/user_guides/2_dataset_prepare.md
+++ b/docs/zh_cn/user_guides/2_dataset_prepare.md
@@ -615,4 +615,4 @@ python tools/convert_datasets/refuge.py --raw_data_root=/path/to/refuge/REFUGE2/
   ```
 
 - 您可以在配置中使用 `MapillaryDataset_v1` 和 `Mapillary Dataset_v2` 设置数据集版本。
-  在此处 [V1.2](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/datasets/mapillary_v1.py) 和 [V2.0](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/datasets/mapillary_v2.py) 查看 Mapillary Vistas 数据集配置文件
+  在此处 [V1.2](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/_base_/datasets/mapillary_v1.py) 和 [V2.0](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/_base_/datasets/mapillary_v2.py) 查看 Mapillary Vistas 数据集配置文件
diff --git a/docs/zh_cn/user_guides/3_inference.md b/docs/zh_cn/user_guides/3_inference.md
index ab68bb47e6..0afcb4b05d 100644
--- a/docs/zh_cn/user_guides/3_inference.md
+++ b/docs/zh_cn/user_guides/3_inference.md
@@ -96,7 +96,7 @@ print(type(results[0]))
 - weights（str，可选）- 权重的路径。如果未指定，并且模型是元文件中的模型名称，则权重将从元文件加载。默认为 None。
 - classes（list，可选）- 输入类别用于结果渲染，由于分割模型的预测结构是标签索引的分割图，`classes` 是一个相应的标签索引的类别列表。若 classes 没有定义，可视化工具将默认使用 `cityscapes` 的类别。默认为 None。
 - palette（list，可选）- 输入调色盘用于结果渲染，它是对应分类的配色列表。若 palette 没有定义，可视化工具将默认使用 `cityscapes` 的调色盘。默认为 None。
-- dataset_name（str，可选）- [数据集名称或别名](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/utils/class_names.py#L302-L317)，可视化工具将使用数据集的元信息，如类别和配色，但 `classes` 和 `palette` 具有更高的优先级。默认为 None。
+- dataset_name（str，可选）- [数据集名称或别名](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/utils/class_names.py#L302-L317)，可视化工具将使用数据集的元信息，如类别和配色，但 `classes` 和 `palette` 具有更高的优先级。默认为 None。
 - device（str，可选）- 运行推理的设备。如果无，则会自动使用可用的设备。默认为 None。
 - scope（str，可选）- 模型的作用域。默认为 'mmseg'。
 
diff --git a/mmseg/apis/mmseg_inferencer.py b/mmseg/apis/mmseg_inferencer.py
index cb387b10b3..1c72285c56 100644
--- a/mmseg/apis/mmseg_inferencer.py
+++ b/mmseg/apis/mmseg_inferencer.py
@@ -30,7 +30,7 @@ class MMSegInferencer(BaseInferencer):
 
     Args:
         model (str, optional): Path to the config file or the model name
-            defined in metafile. Take the `mmseg metafile <https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn.yml>`_
+            defined in metafile. Take the `mmseg metafile <https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/metafile.yaml>`_
             as an example the `model` could be
             "fcn_r50-d8_4xb2-40k_cityscapes-512x1024", and the weights of model
             will be download automatically. If use config file, like
@@ -48,7 +48,7 @@ class MMSegInferencer(BaseInferencer):
             a list of color palette responding to the classes. If palette is
             not defined, visualizer will take `cityscapes` palette by default.
             Defaults to None.
-        dataset_name (str, optional): `Dataset name or alias <https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/utils/class_names.py#L302-L317>`_
+        dataset_name (str, optional): `Dataset name or alias <https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/utils/class_names.py#L302-L317>`_
             visulizer will use the meta information of the dataset i.e. classes
             and palette, but the `classes` and `palette` have higher priority.
             Defaults to None.
diff --git a/mmseg/visualization/local_visualizer.py b/mmseg/visualization/local_visualizer.py
index d11ad79c81..504004dfcb 100644
--- a/mmseg/visualization/local_visualizer.py
+++ b/mmseg/visualization/local_visualizer.py
@@ -31,7 +31,7 @@ class SegLocalVisualizer(Visualizer):
             `cityscapes` classes by default. Defaults to None.
         palette (list, optional): Input palette for result rendering, which is
             a list of color palette responding to the classes. Defaults to None.
-        dataset_name (str, optional): `Dataset name or alias <https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/utils/class_names.py#L302-L317>`_
+        dataset_name (str, optional): `Dataset name or alias <https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/utils/class_names.py#L302-L317>`_
             visulizer will use the meta information of the dataset i.e. classes
             and palette, but the `classes` and `palette` have higher priority.
             Defaults to None.
@@ -133,7 +133,7 @@ def set_dataset_meta(self,
             palette (list, optional): Input palette for result rendering, which
                 is a list of color palette responding to the classes.
                 Defaults to None.
-            dataset_name (str, optional): `Dataset name or alias <https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/utils/class_names.py#L302-L317>`_
+            dataset_name (str, optional): `Dataset name or alias <https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/utils/class_names.py#L302-L317>`_
                 visulizer will use the meta information of the dataset i.e.
                 classes and palette, but the `classes` and `palette` have
                 higher priority. Defaults to None.
diff --git a/projects/example_project/README.md b/projects/example_project/README.md
index 4338b8acac..e4fd03cf4a 100644
--- a/projects/example_project/README.md
+++ b/projects/example_project/README.md
@@ -53,7 +53,7 @@ mim train mmsegmentation configs/fcn_dummy-r50-d8_4xb2-40k_cityscapes-512x1024.p
 mim test mmsegmentation configs/fcn_dummy-r50-d8_4xb2-40k_cityscapes-512x1024.py --work-dir work_dirs/dummy_resnet --checkpoint ${CHECKPOINT_PATH}
 ```
 
-> List the results as usually done in other model's README. \[Example\](https://github.com/open-mmlab/mmsegmentation/tree/dev-1.x/configs/fcn#results-and-models
+> List the results as usually done in other model's README. \[Example\](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fcn#results-and-models
 > You should claim whether this is based on the pre-trained weights, which are converted from the official release; or it's a reproduced result obtained from retraining the model in this project
 
 | Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                             | download                                                                                                                                                                                                                                                                                                                           |
@@ -113,11 +113,11 @@ Here is a checklist illustrating a usual development workflow of a successful pr
 
   - [ ] Type hints and docstrings
 
-> Ideally *all* the methods should have [type hints](https://www.pythontutorial.net/python-basics/python-type-hints/) and [docstrings](https://google.github.io/styleguide/pyguide.html#381-docstrings). [Example](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/utils/io.py#L9)
+> Ideally *all* the methods should have [type hints](https://www.pythontutorial.net/python-basics/python-type-hints/) and [docstrings](https://google.github.io/styleguide/pyguide.html#381-docstrings). [Example](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/utils/io.py#L9)
 
 - [ ] Unit tests
 
-> Unit tests for each module are required. [Example](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/tests/test_utils/test_io.py#L14)
+> Unit tests for each module are required. [Example](https://github.com/open-mmlab/mmsegmentation/blob/main/tests/test_utils/test_io.py#L14)
 
 - [ ] Code polishing
 
@@ -125,10 +125,10 @@ Here is a checklist illustrating a usual development workflow of a successful pr
 
 - [ ] Metafile.yml
 
-> It will be parsed by MIM and Inferencer. [Example](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn.yml)
+> It will be parsed by MIM and Inferencer. [Example](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn.yml)
 
 - [ ] Move your modules into the core package following the codebase's file hierarchy structure.
 
-> In particular, you may have to refactor this README into a standard one. [Example](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/README.md)
+> In particular, you may have to refactor this README into a standard one. [Example](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/README.md)
 
 - [ ] Refactor your modules into the core package following the codebase's file hierarchy structure.
diff --git a/projects/faq.md b/projects/faq.md
index 724c1cf6a5..dfda48ed09 100644
--- a/projects/faq.md
+++ b/projects/faq.md
@@ -1,6 +1,6 @@
 Q1: Why set up `projects/` folder?
 
-Implementing new models and features into OpenMMLab's algorithm libraries could be troublesome due to the rigorous requirements on code quality, which could hinder the fast iteration of SOTA models and might discourage our members from sharing their latest outcomes here. And that's why we have this `projects/` folder now, where some experimental features, frameworks and models are placed, only needed to satisfy the minimum requirement on the code quality, and can be used as standalone libraries. Users are welcome to use them if they [use MMSegmentation from source](https://mmsegmentation.readthedocs.io/en/dev-1.x/get_started.html#best-practices).
+Implementing new models and features into OpenMMLab's algorithm libraries could be troublesome due to the rigorous requirements on code quality, which could hinder the fast iteration of SOTA models and might discourage our members from sharing their latest outcomes here. And that's why we have this `projects/` folder now, where some experimental features, frameworks and models are placed, only needed to satisfy the minimum requirement on the code quality, and can be used as standalone libraries. Users are welcome to use them if they [use MMSegmentation from source](https://mmsegmentation.readthedocs.io/en/main/get_started.html#best-practices).
 
 Q2: Why should there be a checklist for a project?
 
diff --git a/projects/hssn/README.md b/projects/hssn/README.md
index c2a74c69f9..9dcbf37de0 100644
--- a/projects/hssn/README.md
+++ b/projects/hssn/README.md
@@ -41,9 +41,9 @@ bash tools/dist_test.sh projects/hssn/configs/hssn/hieraseg_deeplabv3plus_r101-d
 
 ### Cityscapes
 
-|   Method   | Backbone | Crop Size | mIoU  | mIoU (ms+flip) |                                                                                config                                                                                 |                                                                             model                                                                             |
-| :--------: | :------: | :-------: | :---: | :------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------: |
-| DeeplabV3+ | R-101-D8 | 512x1024  | 81.61 |     82.71      | [config](https://github.com/open-mmlab/mmsegmentation/tree/dev-1.x/projects/HieraSeg/configs/hieraseg/hieraseg_deeplabv3plus_r101-d8_4xb2-80l_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hieraseg/hieraseg_deeplabv3plus_r101-d8_4xb2-80k_cityscapes-512x1024_20230112_125023-bc59a3d1.pth) |
+|   Method   | Backbone | Crop Size | mIoU  | mIoU (ms+flip) |                                                                               config                                                                               |                                                                             model                                                                             |
+| :--------: | :------: | :-------: | :---: | :------------: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------: |
+| DeeplabV3+ | R-101-D8 | 512x1024  | 81.61 |     82.71      | [config](https://github.com/open-mmlab/mmsegmentation/tree/main/projects/HieraSeg/configs/hieraseg/hieraseg_deeplabv3plus_r101-d8_4xb2-80l_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hieraseg/hieraseg_deeplabv3plus_r101-d8_4xb2-80k_cityscapes-512x1024_20230112_125023-bc59a3d1.pth) |
 
 <img src="https://user-images.githubusercontent.com/50650583/210488953-e3e35ade-1132-47e1-9dfd-cf12b357ae80.png" width="50%"><img src="https://user-images.githubusercontent.com/50650583/210489746-e35ee229-3234-4292-a649-a8cd85f312ad.png" width="50%">
 
diff --git a/projects/isnet/README.md b/projects/isnet/README.md
index 3a3172a9d9..0a79ad6a4f 100644
--- a/projects/isnet/README.md
+++ b/projects/isnet/README.md
@@ -96,11 +96,11 @@ A project does not necessarily have to be finished in a single PR, but it's esse
 
   - [ ] Type hints and docstrings
 
-  <!-- Ideally *all* the methods should have [type hints](https://www.pythontutorial.net/python-basics/python-type-hints/) and [docstrings](https://google.github.io/styleguide/pyguide.html#381-docstrings). [Example](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/mmseg/utils/io.py#L9) -->
+  <!-- Ideally *all* the methods should have [type hints](https://www.pythontutorial.net/python-basics/python-type-hints/) and [docstrings](https://google.github.io/styleguide/pyguide.html#381-docstrings). [Example](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/utils/io.py#L9) -->
 
   - [ ] Unit tests
 
-  <!-- Unit tests for each module are required. [Example](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/tests/test_utils/test_io.py#L14) -->
+  <!-- Unit tests for each module are required. [Example](https://github.com/open-mmlab/mmsegmentation/blob/main/tests/test_utils/test_io.py#L14) -->
 
   - [ ] Code polishing
 
@@ -108,10 +108,10 @@ A project does not necessarily have to be finished in a single PR, but it's esse
 
   - [ ] Metafile.yml
 
-  <!-- It will be parsed by MIM and Inferencer. [Example](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn.yml) -->
+  <!-- It will be parsed by MIM and Inferencer. [Example](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn.yml) -->
 
 - [ ] Move your modules into the core package following the codebase's file hierarchy structure.
 
-  <!-- In particular, you may have to refactor this README into a standard one. [Example](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/README.md) -->
+  <!-- In particular, you may have to refactor this README into a standard one. [Example](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/README.md) -->
 
 - [ ] Refactor your modules into the core package following the codebase's file hierarchy structure.
diff --git a/projects/mapillary_dataset/README.md b/projects/mapillary_dataset/README.md
index cdc61d53a9..44a1e33ef9 100644
--- a/projects/mapillary_dataset/README.md
+++ b/projects/mapillary_dataset/README.md
@@ -10,7 +10,7 @@ This project implements **`Mapillary Vistas Dataset`**
 
 ### Dataset preparing
 
-Preparing `Mapillary Vistas Dataset` dataset following [Mapillary Vistas Dataset Preparing Guide](https://github.com/open-mmlab/mmsegmentation/tree/dev-1.x/projects/mapillary_dataset/docs/en/user_guides/2_dataset_prepare.md)
+Preparing `Mapillary Vistas Dataset` dataset following [Mapillary Vistas Dataset Preparing Guide](https://github.com/open-mmlab/mmsegmentation/tree/main/projects/mapillary_dataset/docs/en/user_guides/2_dataset_prepare.md)
 
 ```none
   mmsegmentation
diff --git a/projects/mapillary_dataset/docs/en/user_guides/2_dataset_prepare.md b/projects/mapillary_dataset/docs/en/user_guides/2_dataset_prepare.md
index fa07454330..c5cbc0f9b8 100644
--- a/projects/mapillary_dataset/docs/en/user_guides/2_dataset_prepare.md
+++ b/projects/mapillary_dataset/docs/en/user_guides/2_dataset_prepare.md
@@ -47,7 +47,7 @@
   ```
 
 - You could set Datasets version with `MapillaryDataset_v1` and `MapillaryDataset_v2` in your configs.
-  View the Mapillary Vistas Datasets config file here [V1.2](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/datasets/mapillary_v1.py) and  [V2.0](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/datasets/mapillary_v2.py)
+  View the Mapillary Vistas Datasets config file here [V1.2](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/_base_/datasets/mapillary_v1.py) and  [V2.0](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/_base_/datasets/mapillary_v2.py)
 
 - **View datasets labels index and palette**